diff options
| author | Jakub Kicinski | 2023-04-13 16:11:22 -0700 |
|---|---|---|
| committer | Jakub Kicinski | 2023-04-13 16:43:38 -0700 |
| commit | c2865b1122595e69e7df52d01f7f02338b8babca (patch) | |
| tree | e1bfb26b2d31ce0bf590cabafc8e3a0ff1bece4c /kernel/bpf | |
| parent | 800e68c44ffe71f9715f745b38fd1af6910b3773 (diff) | |
| parent | 8c5c2a4898e3d6bad86e29d471e023c8a19ba799 (diff) | |
Daniel Borkmann says:
====================
pull-request: bpf-next 2023-04-13
We've added 260 non-merge commits during the last 36 day(s) which contain
a total of 356 files changed, 21786 insertions(+), 11275 deletions(-).
The main changes are:
1) Rework BPF verifier log behavior and implement it as a rotating log
by default with the option to retain old-style fixed log behavior,
from Andrii Nakryiko.
2) Adds support for using {FOU,GUE} encap with an ipip device operating
in collect_md mode and add a set of BPF kfuncs for controlling encap
params, from Christian Ehrig.
3) Allow BPF programs to detect at load time whether a particular kfunc
exists or not, and also add support for this in light skeleton,
from Alexei Starovoitov.
4) Optimize hashmap lookups when key size is multiple of 4,
from Anton Protopopov.
5) Enable RCU semantics for task BPF kptrs and allow referenced kptr
tasks to be stored in BPF maps, from David Vernet.
6) Add support for stashing local BPF kptr into a map value via
bpf_kptr_xchg(). This is useful e.g. for rbtree node creation
for new cgroups, from Dave Marchevsky.
7) Fix BTF handling of is_int_ptr to skip modifiers to work around
tracing issues where a program cannot be attached, from Feng Zhou.
8) Migrate a big portion of test_verifier unit tests over to
test_progs -a verifier_* via inline asm to ease {read,debug}ability,
from Eduard Zingerman.
9) Several updates to the instruction-set.rst documentation
which is subject to future IETF standardization
(https://lwn.net/Articles/926882/), from Dave Thaler.
10) Fix BPF verifier in the __reg_bound_offset's 64->32 tnum sub-register
known bits information propagation, from Daniel Borkmann.
11) Add skb bitfield compaction work related to BPF with the overall goal
to make more of the sk_buff bits optional, from Jakub Kicinski.
12) BPF selftest cleanups for build id extraction which stand on its own
from the upcoming integration work of build id into struct file object,
from Jiri Olsa.
13) Add fixes and optimizations for xsk descriptor validation and several
selftest improvements for xsk sockets, from Kal Conley.
14) Add BPF links for struct_ops and enable switching implementations
of BPF TCP cong-ctls under a given name by replacing backing
struct_ops map, from Kui-Feng Lee.
15) Remove a misleading BPF verifier env->bypass_spec_v1 check on variable
offset stack read as earlier Spectre checks cover this,
from Luis Gerhorst.
16) Fix issues in copy_from_user_nofault() for BPF and other tracers
to resemble copy_from_user_nmi() from safety PoV, from Florian Lehner
and Alexei Starovoitov.
17) Add --json-summary option to test_progs in order for CI tooling to
ease parsing of test results, from Manu Bretelle.
18) Batch of improvements and refactoring to prep for upcoming
bpf_local_storage conversion to bpf_mem_cache_{alloc,free} allocator,
from Martin KaFai Lau.
19) Improve bpftool's visual program dump which produces the control
flow graph in a DOT format by adding C source inline annotations,
from Quentin Monnet.
20) Fix attaching fentry/fexit/fmod_ret/lsm to modules by extracting
the module name from BTF of the target and searching kallsyms of
the correct module, from Viktor Malik.
21) Improve BPF verifier handling of '<const> <cond> <non_const>'
to better detect whether in particular jmp32 branches are taken,
from Yonghong Song.
22) Allow BPF TCP cong-ctls to write app_limited of struct tcp_sock.
A built-in cc or one from a kernel module is already able to write
to app_limited, from Yixin Shen.
Conflicts:
Documentation/bpf/bpf_devel_QA.rst
b7abcd9c656b ("bpf, doc: Link to submitting-patches.rst for general patch submission info")
0f10f647f455 ("bpf, docs: Use internal linking for link to netdev subsystem doc")
https://lore.kernel.org/all/20230307095812.236eb1be@canb.auug.org.au/
include/net/ip_tunnels.h
bc9d003dc48c3 ("ip_tunnel: Preserve pointer const in ip_tunnel_info_opts")
ac931d4cdec3d ("ipip,ip_tunnel,sit: Add FOU support for externally controlled ipip devices")
https://lore.kernel.org/all/20230413161235.4093777-1-broonie@kernel.org/
net/bpf/test_run.c
e5995bc7e2ba ("bpf, test_run: fix crashes due to XDP frame overwriting/corruption")
294635a8165a ("bpf, test_run: fix &xdp_frame misplacement for LIVE_FRAMES")
https://lore.kernel.org/all/20230320102619.05b80a98@canb.auug.org.au/
====================
Link: https://lore.kernel.org/r/20230413191525.7295-1-daniel@iogearbox.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Diffstat (limited to 'kernel/bpf')
| -rw-r--r-- | kernel/bpf/Makefile | 3 | ||||
| -rw-r--r-- | kernel/bpf/arraymap.c | 12 | ||||
| -rw-r--r-- | kernel/bpf/bloom_filter.c | 29 | ||||
| -rw-r--r-- | kernel/bpf/bpf_cgrp_storage.c | 23 | ||||
| -rw-r--r-- | kernel/bpf/bpf_inode_storage.c | 22 | ||||
| -rw-r--r-- | kernel/bpf/bpf_iter.c | 70 | ||||
| -rw-r--r-- | kernel/bpf/bpf_local_storage.c | 382 | ||||
| -rw-r--r-- | kernel/bpf/bpf_struct_ops.c | 260 | ||||
| -rw-r--r-- | kernel/bpf/bpf_task_storage.c | 27 | ||||
| -rw-r--r-- | kernel/bpf/btf.c | 279 | ||||
| -rw-r--r-- | kernel/bpf/cpumap.c | 8 | ||||
| -rw-r--r-- | kernel/bpf/cpumask.c | 43 | ||||
| -rw-r--r-- | kernel/bpf/devmap.c | 24 | ||||
| -rw-r--r-- | kernel/bpf/hashtab.c | 38 | ||||
| -rw-r--r-- | kernel/bpf/helpers.c | 139 | ||||
| -rw-r--r-- | kernel/bpf/local_storage.c | 6 | ||||
| -rw-r--r-- | kernel/bpf/log.c | 330 | ||||
| -rw-r--r-- | kernel/bpf/lpm_trie.c | 6 | ||||
| -rw-r--r-- | kernel/bpf/memalloc.c | 59 | ||||
| -rw-r--r-- | kernel/bpf/queue_stack_maps.c | 22 | ||||
| -rw-r--r-- | kernel/bpf/reuseport_array.c | 2 | ||||
| -rw-r--r-- | kernel/bpf/ringbuf.c | 6 | ||||
| -rw-r--r-- | kernel/bpf/stackmap.c | 6 | ||||
| -rw-r--r-- | kernel/bpf/syscall.c | 112 | ||||
| -rw-r--r-- | kernel/bpf/trampoline.c | 28 | ||||
| -rw-r--r-- | kernel/bpf/verifier.c | 1096 |
26 files changed, 2246 insertions, 786 deletions
diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile index 02242614dcc7..1d3892168d32 100644 --- a/kernel/bpf/Makefile +++ b/kernel/bpf/Makefile @@ -6,7 +6,8 @@ cflags-nogcse-$(CONFIG_X86)$(CONFIG_CC_IS_GCC) := -fno-gcse endif CFLAGS_core.o += $(call cc-disable-warning, override-init) $(cflags-nogcse-yy) -obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o inode.o helpers.o tnum.o bpf_iter.o map_iter.o task_iter.o prog_iter.o link_iter.o +obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o inode.o helpers.o tnum.o log.o +obj-$(CONFIG_BPF_SYSCALL) += bpf_iter.o map_iter.o task_iter.o prog_iter.o link_iter.o obj-$(CONFIG_BPF_SYSCALL) += hashtab.o arraymap.o percpu_freelist.o bpf_lru_list.o lpm_trie.o map_in_map.o bloom_filter.o obj-$(CONFIG_BPF_SYSCALL) += local_storage.o queue_stack_maps.o ringbuf.o obj-$(CONFIG_BPF_SYSCALL) += bpf_local_storage.o bpf_task_storage.o diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c index 1588c793a715..2058e89b5ddd 100644 --- a/kernel/bpf/arraymap.c +++ b/kernel/bpf/arraymap.c @@ -307,8 +307,8 @@ static int array_map_get_next_key(struct bpf_map *map, void *key, void *next_key } /* Called from syscall or from eBPF program */ -static int array_map_update_elem(struct bpf_map *map, void *key, void *value, - u64 map_flags) +static long array_map_update_elem(struct bpf_map *map, void *key, void *value, + u64 map_flags) { struct bpf_array *array = container_of(map, struct bpf_array, map); u32 index = *(u32 *)key; @@ -386,7 +386,7 @@ int bpf_percpu_array_update(struct bpf_map *map, void *key, void *value, } /* Called from syscall or from eBPF program */ -static int array_map_delete_elem(struct bpf_map *map, void *key) +static long array_map_delete_elem(struct bpf_map *map, void *key) { return -EINVAL; } @@ -686,8 +686,8 @@ static const struct bpf_iter_seq_info iter_seq_info = { .seq_priv_size = sizeof(struct bpf_iter_seq_array_map_info), }; -static int bpf_for_each_array_elem(struct bpf_map *map, bpf_callback_t callback_fn, - void *callback_ctx, u64 flags) +static long bpf_for_each_array_elem(struct bpf_map *map, bpf_callback_t callback_fn, + void *callback_ctx, u64 flags) { u32 i, key, num_elems = 0; struct bpf_array *array; @@ -871,7 +871,7 @@ int bpf_fd_array_map_update_elem(struct bpf_map *map, struct file *map_file, return 0; } -static int fd_array_map_delete_elem(struct bpf_map *map, void *key) +static long fd_array_map_delete_elem(struct bpf_map *map, void *key) { struct bpf_array *array = container_of(map, struct bpf_array, map); void *old_ptr; diff --git a/kernel/bpf/bloom_filter.c b/kernel/bpf/bloom_filter.c index 6350c5d35a9b..540331b610a9 100644 --- a/kernel/bpf/bloom_filter.c +++ b/kernel/bpf/bloom_filter.c @@ -16,13 +16,6 @@ struct bpf_bloom_filter { struct bpf_map map; u32 bitset_mask; u32 hash_seed; - /* If the size of the values in the bloom filter is u32 aligned, - * then it is more performant to use jhash2 as the underlying hash - * function, else we use jhash. This tracks the number of u32s - * in an u32-aligned value size. If the value size is not u32 aligned, - * this will be 0. - */ - u32 aligned_u32_count; u32 nr_hash_funcs; unsigned long bitset[]; }; @@ -32,16 +25,15 @@ static u32 hash(struct bpf_bloom_filter *bloom, void *value, { u32 h; - if (bloom->aligned_u32_count) - h = jhash2(value, bloom->aligned_u32_count, - bloom->hash_seed + index); + if (likely(value_size % 4 == 0)) + h = jhash2(value, value_size / 4, bloom->hash_seed + index); else h = jhash(value, value_size, bloom->hash_seed + index); return h & bloom->bitset_mask; } -static int bloom_map_peek_elem(struct bpf_map *map, void *value) +static long bloom_map_peek_elem(struct bpf_map *map, void *value) { struct bpf_bloom_filter *bloom = container_of(map, struct bpf_bloom_filter, map); @@ -56,7 +48,7 @@ static int bloom_map_peek_elem(struct bpf_map *map, void *value) return 0; } -static int bloom_map_push_elem(struct bpf_map *map, void *value, u64 flags) +static long bloom_map_push_elem(struct bpf_map *map, void *value, u64 flags) { struct bpf_bloom_filter *bloom = container_of(map, struct bpf_bloom_filter, map); @@ -73,12 +65,12 @@ static int bloom_map_push_elem(struct bpf_map *map, void *value, u64 flags) return 0; } -static int bloom_map_pop_elem(struct bpf_map *map, void *value) +static long bloom_map_pop_elem(struct bpf_map *map, void *value) { return -EOPNOTSUPP; } -static int bloom_map_delete_elem(struct bpf_map *map, void *value) +static long bloom_map_delete_elem(struct bpf_map *map, void *value) { return -EOPNOTSUPP; } @@ -152,11 +144,6 @@ static struct bpf_map *bloom_map_alloc(union bpf_attr *attr) bloom->nr_hash_funcs = nr_hash_funcs; bloom->bitset_mask = bitset_mask; - /* Check whether the value size is u32-aligned */ - if ((attr->value_size & (sizeof(u32) - 1)) == 0) - bloom->aligned_u32_count = - attr->value_size / sizeof(u32); - if (!(attr->map_flags & BPF_F_ZERO_SEED)) bloom->hash_seed = get_random_u32(); @@ -177,8 +164,8 @@ static void *bloom_map_lookup_elem(struct bpf_map *map, void *key) return ERR_PTR(-EINVAL); } -static int bloom_map_update_elem(struct bpf_map *map, void *key, - void *value, u64 flags) +static long bloom_map_update_elem(struct bpf_map *map, void *key, + void *value, u64 flags) { /* The eBPF program should use map_push_elem instead */ return -EINVAL; diff --git a/kernel/bpf/bpf_cgrp_storage.c b/kernel/bpf/bpf_cgrp_storage.c index 9ae07aedaf23..d44fe8dd9732 100644 --- a/kernel/bpf/bpf_cgrp_storage.c +++ b/kernel/bpf/bpf_cgrp_storage.c @@ -46,8 +46,6 @@ static struct bpf_local_storage __rcu **cgroup_storage_ptr(void *owner) void bpf_cgrp_storage_free(struct cgroup *cgroup) { struct bpf_local_storage *local_storage; - bool free_cgroup_storage = false; - unsigned long flags; rcu_read_lock(); local_storage = rcu_dereference(cgroup->bpf_cgrp_storage); @@ -57,14 +55,9 @@ void bpf_cgrp_storage_free(struct cgroup *cgroup) } bpf_cgrp_storage_lock(); - raw_spin_lock_irqsave(&local_storage->lock, flags); - free_cgroup_storage = bpf_local_storage_unlink_nolock(local_storage); - raw_spin_unlock_irqrestore(&local_storage->lock, flags); + bpf_local_storage_destroy(local_storage); bpf_cgrp_storage_unlock(); rcu_read_unlock(); - - if (free_cgroup_storage) - kfree_rcu(local_storage, rcu); } static struct bpf_local_storage_data * @@ -100,8 +93,8 @@ static void *bpf_cgrp_storage_lookup_elem(struct bpf_map *map, void *key) return sdata ? sdata->data : NULL; } -static int bpf_cgrp_storage_update_elem(struct bpf_map *map, void *key, - void *value, u64 map_flags) +static long bpf_cgrp_storage_update_elem(struct bpf_map *map, void *key, + void *value, u64 map_flags) { struct bpf_local_storage_data *sdata; struct cgroup *cgroup; @@ -128,11 +121,11 @@ static int cgroup_storage_delete(struct cgroup *cgroup, struct bpf_map *map) if (!sdata) return -ENOENT; - bpf_selem_unlink(SELEM(sdata), true); + bpf_selem_unlink(SELEM(sdata), false); return 0; } -static int bpf_cgrp_storage_delete_elem(struct bpf_map *map, void *key) +static long bpf_cgrp_storage_delete_elem(struct bpf_map *map, void *key) { struct cgroup *cgroup; int err, fd; @@ -156,7 +149,7 @@ static int notsupp_get_next_key(struct bpf_map *map, void *key, void *next_key) static struct bpf_map *cgroup_storage_map_alloc(union bpf_attr *attr) { - return bpf_local_storage_map_alloc(attr, &cgroup_cache); + return bpf_local_storage_map_alloc(attr, &cgroup_cache, true); } static void cgroup_storage_map_free(struct bpf_map *map) @@ -231,7 +224,7 @@ const struct bpf_func_proto bpf_cgrp_storage_get_proto = { .gpl_only = false, .ret_type = RET_PTR_TO_MAP_VALUE_OR_NULL, .arg1_type = ARG_CONST_MAP_PTR, - .arg2_type = ARG_PTR_TO_BTF_ID, + .arg2_type = ARG_PTR_TO_BTF_ID_OR_NULL, .arg2_btf_id = &bpf_cgroup_btf_id[0], .arg3_type = ARG_PTR_TO_MAP_VALUE_OR_NULL, .arg4_type = ARG_ANYTHING, @@ -242,6 +235,6 @@ const struct bpf_func_proto bpf_cgrp_storage_delete_proto = { .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_CONST_MAP_PTR, - .arg2_type = ARG_PTR_TO_BTF_ID, + .arg2_type = ARG_PTR_TO_BTF_ID_OR_NULL, .arg2_btf_id = &bpf_cgroup_btf_id[0], }; diff --git a/kernel/bpf/bpf_inode_storage.c b/kernel/bpf/bpf_inode_storage.c index 43e2619c8167..a4d93df78c75 100644 --- a/kernel/bpf/bpf_inode_storage.c +++ b/kernel/bpf/bpf_inode_storage.c @@ -57,7 +57,6 @@ static struct bpf_local_storage_data *inode_storage_lookup(struct inode *inode, void bpf_inode_storage_free(struct inode *inode) { struct bpf_local_storage *local_storage; - bool free_inode_storage = false; struct bpf_storage_blob *bsb; bsb = bpf_inode(inode); @@ -72,13 +71,8 @@ void bpf_inode_storage_free(struct inode *inode) return; } - raw_spin_lock_bh(&local_storage->lock); - free_inode_storage = bpf_local_storage_unlink_nolock(local_storage); - raw_spin_unlock_bh(&local_storage->lock); + bpf_local_storage_destroy(local_storage); rcu_read_unlock(); - - if (free_inode_storage) - kfree_rcu(local_storage, rcu); } static void *bpf_fd_inode_storage_lookup_elem(struct bpf_map *map, void *key) @@ -97,8 +91,8 @@ static void *bpf_fd_inode_storage_lookup_elem(struct bpf_map *map, void *key) return sdata ? sdata->data : NULL; } -static int bpf_fd_inode_storage_update_elem(struct bpf_map *map, void *key, - void *value, u64 map_flags) +static long bpf_fd_inode_storage_update_elem(struct bpf_map *map, void *key, + void *value, u64 map_flags) { struct bpf_local_storage_data *sdata; struct file *f; @@ -128,12 +122,12 @@ static int inode_storage_delete(struct inode *inode, struct bpf_map *map) if (!sdata) return -ENOENT; - bpf_selem_unlink(SELEM(sdata), true); + bpf_selem_unlink(SELEM(sdata), false); return 0; } -static int bpf_fd_inode_storage_delete_elem(struct bpf_map *map, void *key) +static long bpf_fd_inode_storage_delete_elem(struct bpf_map *map, void *key) { struct file *f; int fd, err; @@ -205,7 +199,7 @@ static int notsupp_get_next_key(struct bpf_map *map, void *key, static struct bpf_map *inode_storage_map_alloc(union bpf_attr *attr) { - return bpf_local_storage_map_alloc(attr, &inode_cache); + return bpf_local_storage_map_alloc(attr, &inode_cache, false); } static void inode_storage_map_free(struct bpf_map *map) @@ -235,7 +229,7 @@ const struct bpf_func_proto bpf_inode_storage_get_proto = { .gpl_only = false, .ret_type = RET_PTR_TO_MAP_VALUE_OR_NULL, .arg1_type = ARG_CONST_MAP_PTR, - .arg2_type = ARG_PTR_TO_BTF_ID, + .arg2_type = ARG_PTR_TO_BTF_ID_OR_NULL, .arg2_btf_id = &bpf_inode_storage_btf_ids[0], .arg3_type = ARG_PTR_TO_MAP_VALUE_OR_NULL, .arg4_type = ARG_ANYTHING, @@ -246,6 +240,6 @@ const struct bpf_func_proto bpf_inode_storage_delete_proto = { .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_CONST_MAP_PTR, - .arg2_type = ARG_PTR_TO_BTF_ID, + .arg2_type = ARG_PTR_TO_BTF_ID_OR_NULL, .arg2_btf_id = &bpf_inode_storage_btf_ids[0], }; diff --git a/kernel/bpf/bpf_iter.c b/kernel/bpf/bpf_iter.c index 5dc307bdeaeb..96856f130cbf 100644 --- a/kernel/bpf/bpf_iter.c +++ b/kernel/bpf/bpf_iter.c @@ -776,3 +776,73 @@ const struct bpf_func_proto bpf_loop_proto = { .arg3_type = ARG_PTR_TO_STACK_OR_NULL, .arg4_type = ARG_ANYTHING, }; + +struct bpf_iter_num_kern { + int cur; /* current value, inclusive */ + int end; /* final value, exclusive */ +} __aligned(8); + +__diag_push(); +__diag_ignore_all("-Wmissing-prototypes", + "Global functions as their definitions will be in vmlinux BTF"); + +__bpf_kfunc int bpf_iter_num_new(struct bpf_iter_num *it, int start, int end) +{ + struct bpf_iter_num_kern *s = (void *)it; + + BUILD_BUG_ON(sizeof(struct bpf_iter_num_kern) != sizeof(struct bpf_iter_num)); + BUILD_BUG_ON(__alignof__(struct bpf_iter_num_kern) != __alignof__(struct bpf_iter_num)); + + BTF_TYPE_EMIT(struct btf_iter_num); + + /* start == end is legit, it's an empty range and we'll just get NULL + * on first (and any subsequent) bpf_iter_num_next() call + */ + if (start > end) { + s->cur = s->end = 0; + return -EINVAL; + } + + /* avoid overflows, e.g., if start == INT_MIN and end == INT_MAX */ + if ((s64)end - (s64)start > BPF_MAX_LOOPS) { + s->cur = s->end = 0; + return -E2BIG; + } + + /* user will call bpf_iter_num_next() first, + * which will set s->cur to exactly start value; + * underflow shouldn't matter + */ + s->cur = start - 1; + s->end = end; + + return 0; +} + +__bpf_kfunc int *bpf_iter_num_next(struct bpf_iter_num* it) +{ + struct bpf_iter_num_kern *s = (void *)it; + + /* check failed initialization or if we are done (same behavior); + * need to be careful about overflow, so convert to s64 for checks, + * e.g., if s->cur == s->end == INT_MAX, we can't just do + * s->cur + 1 >= s->end + */ + if ((s64)(s->cur + 1) >= s->end) { + s->cur = s->end = 0; + return NULL; + } + + s->cur++; + + return &s->cur; +} + +__bpf_kfunc void bpf_iter_num_destroy(struct bpf_iter_num *it) +{ + struct bpf_iter_num_kern *s = (void *)it; + + s->cur = s->end = 0; +} + +__diag_pop(); diff --git a/kernel/bpf/bpf_local_storage.c b/kernel/bpf/bpf_local_storage.c index d3ba3f2db640..47d9948d768f 100644 --- a/kernel/bpf/bpf_local_storage.c +++ b/kernel/bpf/bpf_local_storage.c @@ -80,8 +80,24 @@ bpf_selem_alloc(struct bpf_local_storage_map *smap, void *owner, if (charge_mem && mem_charge(smap, owner, smap->elem_size)) return NULL; - selem = bpf_map_kzalloc(&smap->map, smap->elem_size, - gfp_flags | __GFP_NOWARN); + if (smap->bpf_ma) { + migrate_disable(); + selem = bpf_mem_cache_alloc_flags(&smap->selem_ma, gfp_flags); + migrate_enable(); + if (selem) + /* Keep the original bpf_map_kzalloc behavior + * before started using the bpf_mem_cache_alloc. + * + * No need to use zero_map_value. The bpf_selem_free() + * only does bpf_mem_cache_free when there is + * no other bpf prog is using the selem. + */ + memset(SDATA(selem)->data, 0, smap->map.value_size); + } else { + selem = bpf_map_kzalloc(&smap->map, smap->elem_size, + gfp_flags | __GFP_NOWARN); + } + if (selem) { if (value) copy_map_value(&smap->map, SDATA(selem)->data, value); @@ -95,7 +111,8 @@ bpf_selem_alloc(struct bpf_local_storage_map *smap, void *owner, return NULL; } -void bpf_local_storage_free_rcu(struct rcu_head *rcu) +/* rcu tasks trace callback for bpf_ma == false */ +static void __bpf_local_storage_free_trace_rcu(struct rcu_head *rcu) { struct bpf_local_storage *local_storage; @@ -109,28 +126,66 @@ void bpf_local_storage_free_rcu(struct rcu_head *rcu) kfree_rcu(local_storage, rcu); } -static void bpf_selem_free_fields_rcu(struct rcu_head *rcu) +static void bpf_local_storage_free_rcu(struct rcu_head *rcu) { - struct bpf_local_storage_elem *selem; - struct bpf_local_storage_map *smap; + struct bpf_local_storage *local_storage; - selem = container_of(rcu, struct bpf_local_storage_elem, rcu); - /* protected by the rcu_barrier*() */ - smap = rcu_dereference_protected(SDATA(selem)->smap, true); - bpf_obj_free_fields(smap->map.record, SDATA(selem)->data); - kfree(selem); + local_storage = container_of(rcu, struct bpf_local_storage, rcu); + bpf_mem_cache_raw_free(local_storage); } -static void bpf_selem_free_fields_trace_rcu(struct rcu_head *rcu) +static void bpf_local_storage_free_trace_rcu(struct rcu_head *rcu) { - /* Free directly if Tasks Trace RCU GP also implies RCU GP */ if (rcu_trace_implies_rcu_gp()) - bpf_selem_free_fields_rcu(rcu); + bpf_local_storage_free_rcu(rcu); else - call_rcu(rcu, bpf_selem_free_fields_rcu); + call_rcu(rcu, bpf_local_storage_free_rcu); } -static void bpf_selem_free_trace_rcu(struct rcu_head *rcu) +/* Handle bpf_ma == false */ +static void __bpf_local_storage_free(struct bpf_local_storage *local_storage, + bool vanilla_rcu) +{ + if (vanilla_rcu) + kfree_rcu(local_storage, rcu); + else + call_rcu_tasks_trace(&local_storage->rcu, + __bpf_local_storage_free_trace_rcu); +} + +static void bpf_local_storage_free(struct bpf_local_storage *local_storage, + struct bpf_local_storage_map *smap, + bool bpf_ma, bool reuse_now) +{ + if (!local_storage) + return; + + if (!bpf_ma) { + __bpf_local_storage_free(local_storage, reuse_now); + return; + } + + if (!reuse_now) { + call_rcu_tasks_trace(&local_storage->rcu, + bpf_local_storage_free_trace_rcu); + return; + } + + if (smap) { + migrate_disable(); + bpf_mem_cache_free(&smap->storage_ma, local_storage); + migrate_enable(); + } else { + /* smap could be NULL if the selem that triggered + * this 'local_storage' creation had been long gone. + * In this case, directly do call_rcu(). + */ + call_rcu(&local_storage->rcu, bpf_local_storage_free_rcu); + } +} + +/* rcu tasks trace callback for bpf_ma == false */ +static void __bpf_selem_free_trace_rcu(struct rcu_head *rcu) { struct bpf_local_storage_elem *selem; @@ -141,17 +196,66 @@ static void bpf_selem_free_trace_rcu(struct rcu_head *rcu) kfree_rcu(selem, rcu); } +/* Handle bpf_ma == false */ +static void __bpf_selem_free(struct bpf_local_storage_elem *selem, + bool vanilla_rcu) +{ + if (vanilla_rcu) + kfree_rcu(selem, rcu); + else + call_rcu_tasks_trace(&selem->rcu, __bpf_selem_free_trace_rcu); +} + +static void bpf_selem_free_rcu(struct rcu_head *rcu) +{ + struct bpf_local_storage_elem *selem; + + selem = container_of(rcu, struct bpf_local_storage_elem, rcu); + bpf_mem_cache_raw_free(selem); +} + +static void bpf_selem_free_trace_rcu(struct rcu_head *rcu) +{ + if (rcu_trace_implies_rcu_gp()) + bpf_selem_free_rcu(rcu); + else + call_rcu(rcu, bpf_selem_free_rcu); +} + +void bpf_selem_free(struct bpf_local_storage_elem *selem, + struct bpf_local_storage_map *smap, + bool reuse_now) +{ + bpf_obj_free_fields(smap->map.record, SDATA(selem)->data); + + if (!smap->bpf_ma) { + __bpf_selem_free(selem, reuse_now); + return; + } + + if (!reuse_now) { + call_rcu_tasks_trace(&selem->rcu, bpf_selem_free_trace_rcu); + } else { + /* Instead of using the vanilla call_rcu(), + * bpf_mem_cache_free will be able to reuse selem + * immediately. + */ + migrate_disable(); + bpf_mem_cache_free(&smap->selem_ma, selem); + migrate_enable(); + } +} + /* local_storage->lock must be held and selem->local_storage == local_storage. * The caller must ensure selem->smap is still valid to be * dereferenced for its smap->elem_size and smap->cache_idx. */ static bool bpf_selem_unlink_storage_nolock(struct bpf_local_storage *local_storage, struct bpf_local_storage_elem *selem, - bool uncharge_mem, bool use_trace_rcu) + bool uncharge_mem, bool reuse_now) { struct bpf_local_storage_map *smap; bool free_local_storage; - struct btf_record *rec; void *owner; smap = rcu_dereference_check(SDATA(selem)->smap, bpf_rcu_lock_held()); @@ -192,35 +296,55 @@ static bool bpf_selem_unlink_storage_nolock(struct bpf_local_storage *local_stor SDATA(selem)) RCU_INIT_POINTER(local_storage->cache[smap->cache_idx], NULL); - /* A different RCU callback is chosen whenever we need to free - * additional fields in selem data before freeing selem. - * bpf_local_storage_map_free only executes rcu_barrier to wait for RCU - * callbacks when it has special fields, hence we can only conditionally - * dereference smap, as by this time the map might have already been - * freed without waiting for our call_rcu callback if it did not have - * any special fields. + bpf_selem_free(selem, smap, reuse_now); + + if (rcu_access_pointer(local_storage->smap) == smap) + RCU_INIT_POINTER(local_storage->smap, NULL); + + return free_local_storage; +} + +static bool check_storage_bpf_ma(struct bpf_local_storage *local_storage, + struct bpf_local_storage_map *storage_smap, + struct bpf_local_storage_elem *selem) +{ + + struct bpf_local_storage_map *selem_smap; + + /* local_storage->smap may be NULL. If it is, get the bpf_ma + * from any selem in the local_storage->list. The bpf_ma of all + * local_storage and selem should have the same value + * for the same map type. + * + * If the local_storage->list is already empty, the caller will not + * care about the bpf_ma value also because the caller is not + * responsibile to free the local_storage. */ - rec = smap->map.record; - if (use_trace_rcu) { - if (!IS_ERR_OR_NULL(rec)) - call_rcu_tasks_trace(&selem->rcu, bpf_selem_free_fields_trace_rcu); - else - call_rcu_tasks_trace(&selem->rcu, bpf_selem_free_trace_rcu); - } else { - if (!IS_ERR_OR_NULL(rec)) - call_rcu(&selem->rcu, bpf_selem_free_fields_rcu); - else - kfree_rcu(selem, rcu); + + if (storage_smap) + return storage_smap->bpf_ma; + + if (!selem) { + struct hlist_node *n; + + n = rcu_dereference_check(hlist_first_rcu(&local_storage->list), + bpf_rcu_lock_held()); + if (!n) + return false; + + selem = hlist_entry(n, struct bpf_local_storage_elem, snode); } + selem_smap = rcu_dereference_check(SDATA(selem)->smap, bpf_rcu_lock_held()); - return free_local_storage; + return selem_smap->bpf_ma; } -static void __bpf_selem_unlink_storage(struct bpf_local_storage_elem *selem, - bool use_trace_rcu) +static void bpf_selem_unlink_storage(struct bpf_local_storage_elem *selem, + bool reuse_now) { + struct bpf_local_storage_map *storage_smap; struct bpf_local_storage *local_storage; - bool free_local_storage = false; + bool bpf_ma, free_local_storage = false; unsigned long flags; if (unlikely(!selem_linked_to_storage_lockless(selem))) @@ -229,19 +353,18 @@ static void __bpf_selem_unlink_storage(struct bpf_local_storage_elem *selem, local_storage = rcu_dereference_check(selem->local_storage, bpf_rcu_lock_held()); + storage_smap = rcu_dereference_check(local_storage->smap, + bpf_rcu_lock_held()); + bpf_ma = check_storage_bpf_ma(local_storage, storage_smap, selem); + raw_spin_lock_irqsave(&local_storage->lock, flags); if (likely(selem_linked_to_storage(selem))) free_local_storage = bpf_selem_unlink_storage_nolock( - local_storage, selem, true, use_trace_rcu); + local_storage, selem, true, reuse_now); raw_spin_unlock_irqrestore(&local_storage->lock, flags); - if (free_local_storage) { - if (use_trace_rcu) - call_rcu_tasks_trace(&local_storage->rcu, - bpf_local_storage_free_rcu); - else - kfree_rcu(local_storage, rcu); - } + if (free_local_storage) + bpf_local_storage_free(local_storage, storage_smap, bpf_ma, reuse_now); } void bpf_selem_link_storage_nolock(struct bpf_local_storage *local_storage, @@ -251,7 +374,7 @@ void bpf_selem_link_storage_nolock(struct bpf_local_storage *local_storage, hlist_add_head_rcu(&selem->snode, &local_storage->list); } -void bpf_selem_unlink_map(struct bpf_local_storage_elem *selem) +static void bpf_selem_unlink_map(struct bpf_local_storage_elem *selem) { struct bpf_local_storage_map *smap; struct bpf_local_storage_map_bucket *b; @@ -281,14 +404,14 @@ void bpf_selem_link_map(struct bpf_local_storage_map *smap, raw_spin_unlock_irqrestore(&b->lock, flags); } -void bpf_selem_unlink(struct bpf_local_storage_elem *selem, bool use_trace_rcu) +void bpf_selem_unlink(struct bpf_local_storage_elem *selem, bool reuse_now) { /* Always unlink from map before unlinking from local_storage * because selem will be freed after successfully unlinked from * the local_storage. */ bpf_selem_unlink_map(selem); - __bpf_selem_unlink_storage(selem, use_trace_rcu); + bpf_selem_unlink_storage(selem, reuse_now); } /* If cacheit_lockit is false, this lookup function is lockless */ @@ -361,13 +484,21 @@ int bpf_local_storage_alloc(void *owner, if (err) return err; - storage = bpf_map_kzalloc(&smap->map, sizeof(*storage), - gfp_flags | __GFP_NOWARN); + if (smap->bpf_ma) { + migrate_disable(); + storage = bpf_mem_cache_alloc_flags(&smap->storage_ma, gfp_flags); + migrate_enable(); + } else { + storage = bpf_map_kzalloc(&smap->map, sizeof(*storage), + gfp_flags | __GFP_NOWARN); + } + if (!storage) { err = -ENOMEM; goto uncharge; } + RCU_INIT_POINTER(storage->smap, smap); INIT_HLIST_HEAD(&storage->list); raw_spin_lock_init(&storage->lock); storage->owner = owner; @@ -407,7 +538,7 @@ int bpf_local_storage_alloc(void *owner, return 0; uncharge: - kfree(storage); + bpf_local_storage_free(storage, smap, smap->bpf_ma, true); mem_uncharge(smap, owner, sizeof(*storage)); return err; } @@ -451,7 +582,7 @@ bpf_local_storage_update(void *owner, struct bpf_local_storage_map *smap, err = bpf_local_storage_alloc(owner, smap, selem, gfp_flags); if (err) { - kfree(selem); + bpf_selem_free(selem, smap, true); mem_uncharge(smap, owner, smap->elem_size); return ERR_PTR(err); } @@ -534,7 +665,7 @@ bpf_local_storage_update(void *owner, struct bpf_local_storage_map *smap, if (old_sdata) { bpf_selem_unlink_map(SELEM(old_sdata)); bpf_selem_unlink_storage_nolock(local_storage, SELEM(old_sdata), - false, true); + false, false); } unlock: @@ -545,7 +676,7 @@ unlock_err: raw_spin_unlock_irqrestore(&local_storage->lock, flags); if (selem) { mem_uncharge(smap, owner, smap->elem_size); - kfree(selem); + bpf_selem_free(selem, smap, true); } return ERR_PTR(err); } @@ -601,40 +732,6 @@ int bpf_local_storage_map_alloc_check(union bpf_attr *attr) return 0; } -static struct bpf_local_storage_map *__bpf_local_storage_map_alloc(union bpf_attr *attr) -{ - struct bpf_local_storage_map *smap; - unsigned int i; - u32 nbuckets; - - smap = bpf_map_area_alloc(sizeof(*smap), NUMA_NO_NODE); - if (!smap) - return ERR_PTR(-ENOMEM); - bpf_map_init_from_attr(&smap->map, attr); - - nbuckets = roundup_pow_of_two(num_possible_cpus()); - /* Use at least 2 buckets, select_bucket() is undefined behavior with 1 bucket */ - nbuckets = max_t(u32, 2, nbuckets); - smap->bucket_log = ilog2(nbuckets); - - smap->buckets = bpf_map_kvcalloc(&smap->map, sizeof(*smap->buckets), - nbuckets, GFP_USER | __GFP_NOWARN); - if (!smap->buckets) { - bpf_map_area_free(smap); - return ERR_PTR(-ENOMEM); - } - - for (i = 0; i < nbuckets; i++) { - INIT_HLIST_HEAD(&smap->buckets[i].list); - raw_spin_lock_init(&smap->buckets[i].lock); - } - - smap->elem_size = offsetof(struct bpf_local_storage_elem, - sdata.data[attr->value_size]); - - return smap; -} - int bpf_local_storage_map_check_btf(const struct bpf_map *map, const struct btf *btf, const struct btf_type *key_type, @@ -652,11 +749,16 @@ int bpf_local_storage_map_check_btf(const struct bpf_map *map, return 0; } -bool bpf_local_storage_unlink_nolock(struct bpf_local_storage *local_storage) +void bpf_local_storage_destroy(struct bpf_local_storage *local_storage) { + struct bpf_local_storage_map *storage_smap; struct bpf_local_storage_elem *selem; - bool free_storage = false; + bool bpf_ma, free_storage = false; struct hlist_node *n; + unsigned long flags; + + storage_smap = rcu_dereference_check(local_storage->smap, bpf_rcu_lock_held()); + bpf_ma = check_storage_bpf_ma(local_storage, storage_smap, NULL); /* Neither the bpf_prog nor the bpf_map's syscall * could be modifying the local_storage->list now. @@ -667,6 +769,7 @@ bool bpf_local_storage_unlink_nolock(struct bpf_local_storage *local_storage) * when unlinking elem from the local_storage->list and * the map's bucket->list. */ + raw_spin_lock_irqsave(&local_storage->lock, flags); hlist_for_each_entry_safe(selem, n, &local_storage->list, snode) { /* Always unlink from map before unlinking from * local_storage. @@ -679,10 +782,12 @@ bool bpf_local_storage_unlink_nolock(struct bpf_local_storage *local_storage) * of the loop will set the free_cgroup_storage to true. */ free_storage = bpf_selem_unlink_storage_nolock( - local_storage, selem, false, false); + local_storage, selem, false, true); } + raw_spin_unlock_irqrestore(&local_storage->lock, flags); - return free_storage; + if (free_storage) + bpf_local_storage_free(local_storage, storage_smap, bpf_ma, true); } u64 bpf_local_storage_map_mem_usage(const struct bpf_map *map) @@ -695,18 +800,71 @@ u64 bpf_local_storage_map_mem_usage(const struct bpf_map *map) return usage; } +/* When bpf_ma == true, the bpf_mem_alloc is used to allocate and free memory. + * A deadlock free allocator is useful for storage that the bpf prog can easily + * get a hold of the owner PTR_TO_BTF_ID in any context. eg. bpf_get_current_task_btf. + * The task and cgroup storage fall into this case. The bpf_mem_alloc reuses + * memory immediately. To be reuse-immediate safe, the owner destruction + * code path needs to go through a rcu grace period before calling + * bpf_local_storage_destroy(). + * + * When bpf_ma == false, the kmalloc and kfree are used. + */ struct bpf_map * bpf_local_storage_map_alloc(union bpf_attr *attr, - struct bpf_local_storage_cache *cache) + struct bpf_local_storage_cache *cache, + bool bpf_ma) { struct bpf_local_storage_map *smap; + unsigned int i; + u32 nbuckets; + int err; + + smap = bpf_map_area_alloc(sizeof(*smap), NUMA_NO_NODE); + if (!smap) + return ERR_PTR(-ENOMEM); + bpf_map_init_from_attr(&smap->map, attr); + + nbuckets = roundup_pow_of_two(num_possible_cpus()); + /* Use at least 2 buckets, select_bucket() is undefined behavior with 1 bucket */ + nbuckets = max_t(u32, 2, nbuckets); + smap->bucket_log = ilog2(nbuckets); - smap = __bpf_local_storage_map_alloc(attr); - if (IS_ERR(smap)) - return ERR_CAST(smap); + smap->buckets = bpf_map_kvcalloc(&smap->map, sizeof(*smap->buckets), + nbuckets, GFP_USER | __GFP_NOWARN); + if (!smap->buckets) { + err = -ENOMEM; + goto free_smap; + } + + for (i = 0; i < nbuckets; i++) { + INIT_HLIST_HEAD(&smap->buckets[i].list); + raw_spin_lock_init(&smap->buckets[i].lock); + } + + smap->elem_size = offsetof(struct bpf_local_storage_elem, + sdata.data[attr->value_size]); + + smap->bpf_ma = bpf_ma; + if (bpf_ma) { + err = bpf_mem_alloc_init(&smap->selem_ma, smap->elem_size, false); + if (err) + goto free_smap; + + err = bpf_mem_alloc_init(&smap->storage_ma, sizeof(struct bpf_local_storage), false); + if (err) { + bpf_mem_alloc_destroy(&smap->selem_ma); + goto free_smap; + } + } smap->cache_idx = bpf_local_storage_cache_idx_get(cache); return &smap->map; + +free_smap: + kvfree(smap->buckets); + bpf_map_area_free(smap); + return ERR_PTR(err); } void bpf_local_storage_map_free(struct bpf_map *map, @@ -748,7 +906,7 @@ void bpf_local_storage_map_free(struct bpf_map *map, migrate_disable(); this_cpu_inc(*busy_counter); } - bpf_selem_unlink(selem, false); + bpf_selem_unlink(selem, true); if (busy_counter) { this_cpu_dec(*busy_counter); migrate_enable(); @@ -772,26 +930,10 @@ void bpf_local_storage_map_free(struct bpf_map *map, */ synchronize_rcu(); - /* Only delay freeing of smap, buckets are not needed anymore */ - kvfree(smap->buckets); - - /* When local storage has special fields, callbacks for - * bpf_selem_free_fields_rcu and bpf_selem_free_fields_trace_rcu will - * keep using the map BTF record, we need to execute an RCU barrier to - * wait for them as the record will be freed right after our map_free - * callback. - */ - if (!IS_ERR_OR_NULL(smap->map.record)) { - rcu_barrier_tasks_trace(); - /* We cannot skip rcu_barrier() when rcu_trace_implies_rcu_gp() - * is true, because while call_rcu invocation is skipped in that - * case in bpf_selem_free_fields_trace_rcu (and all local - * storage maps pass use_trace_rcu = true), there can be - * call_rcu callbacks based on use_trace_rcu = false in the - * while ((selem = ...)) loop above or when owner's free path - * calls bpf_local_storage_unlink_nolock. - */ - rcu_barrier(); + if (smap->bpf_ma) { + bpf_mem_alloc_destroy(&smap->selem_ma); + bpf_mem_alloc_destroy(&smap->storage_ma); } + kvfree(smap->buckets); bpf_map_area_free(smap); } diff --git a/kernel/bpf/bpf_struct_ops.c b/kernel/bpf/bpf_struct_ops.c index 38903fb52f98..d3f0a4825fa6 100644 --- a/kernel/bpf/bpf_struct_ops.c +++ b/kernel/bpf/bpf_struct_ops.c @@ -11,11 +11,13 @@ #include <linux/refcount.h> #include <linux/mutex.h> #include <linux/btf_ids.h> +#include <linux/rcupdate_wait.h> enum bpf_struct_ops_state { BPF_STRUCT_OPS_STATE_INIT, BPF_STRUCT_OPS_STATE_INUSE, BPF_STRUCT_OPS_STATE_TOBEFREE, + BPF_STRUCT_OPS_STATE_READY, }; #define BPF_STRUCT_OPS_COMMON_VALUE \ @@ -58,6 +60,13 @@ struct bpf_struct_ops_map { struct bpf_struct_ops_value kvalue; }; +struct bpf_struct_ops_link { + struct bpf_link link; + struct bpf_map __rcu *map; +}; + +static DEFINE_MUTEX(update_mutex); + #define VALUE_PREFIX "bpf_struct_ops_" #define VALUE_PREFIX_LEN (sizeof(VALUE_PREFIX) - 1) @@ -249,6 +258,7 @@ int bpf_struct_ops_map_sys_lookup_elem(struct bpf_map *map, void *key, struct bpf_struct_ops_map *st_map = (struct bpf_struct_ops_map *)map; struct bpf_struct_ops_value *uvalue, *kvalue; enum bpf_struct_ops_state state; + s64 refcnt; if (unlikely(*(u32 *)key != 0)) return -ENOENT; @@ -267,7 +277,14 @@ int bpf_struct_ops_map_sys_lookup_elem(struct bpf_map *map, void *key, uvalue = value; memcpy(uvalue, st_map->uvalue, map->value_size); uvalue->state = state; - refcount_set(&uvalue->refcnt, refcount_read(&kvalue->refcnt)); + + /* This value offers the user space a general estimate of how + * many sockets are still utilizing this struct_ops for TCP + * congestion control. The number might not be exact, but it + * should sufficiently meet our present goals. + */ + refcnt = atomic64_read(&map->refcnt) - atomic64_read(&map->usercnt); + refcount_set(&uvalue->refcnt, max_t(s64, refcnt, 0)); return 0; } @@ -349,8 +366,8 @@ int bpf_struct_ops_prepare_trampoline(struct bpf_tramp_links *tlinks, model, flags, tlinks, NULL); } -static int bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key, - void *value, u64 flags) +static long bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key, + void *value, u64 flags) { struct bpf_struct_ops_map *st_map = (struct bpf_struct_ops_map *)map; const struct bpf_struct_ops *st_ops = st_map->st_ops; @@ -491,12 +508,29 @@ static int bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key, *(unsigned long *)(udata + moff) = prog->aux->id; } - refcount_set(&kvalue->refcnt, 1); - bpf_map_inc(map); + if (st_map->map.map_flags & BPF_F_LINK) { + err = st_ops->validate(kdata); + if (err) + goto reset_unlock; + set_memory_rox((long)st_map->image, 1); + /* Let bpf_link handle registration & unregistration. + * + * Pair with smp_load_acquire() during lookup_elem(). + */ + smp_store_release(&kvalue->state, BPF_STRUCT_OPS_STATE_READY); + goto unlock; + } set_memory_rox((long)st_map->image, 1); err = st_ops->reg(kdata); if (likely(!err)) { + /* This refcnt increment on the map here after + * 'st_ops->reg()' is secure since the state of the + * map must be set to INIT at this moment, and thus + * bpf_struct_ops_map_delete_elem() can't unregister + * or transition it to TOBEFREE concurrently. + */ + bpf_map_inc(map); /* Pair with smp_load_acquire() during lookup_elem(). * It ensures the above udata updates (e.g. prog->aux->id) * can be seen once BPF_STRUCT_OPS_STATE_INUSE is set. @@ -512,7 +546,6 @@ static int bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key, */ set_memory_nx((long)st_map->image, 1); set_memory_rw((long)st_map->image, 1); - bpf_map_put(map); reset_unlock: bpf_struct_ops_map_put_progs(st_map); @@ -524,20 +557,22 @@ unlock: return err; } -static int bpf_struct_ops_map_delete_elem(struct bpf_map *map, void *key) +static long bpf_struct_ops_map_delete_elem(struct bpf_map *map, void *key) { enum bpf_struct_ops_state prev_state; struct bpf_struct_ops_map *st_map; st_map = (struct bpf_struct_ops_map *)map; + if (st_map->map.map_flags & BPF_F_LINK) + return -EOPNOTSUPP; + prev_state = cmpxchg(&st_map->kvalue.state, BPF_STRUCT_OPS_STATE_INUSE, BPF_STRUCT_OPS_STATE_TOBEFREE); switch (prev_state) { case BPF_STRUCT_OPS_STATE_INUSE: st_map->st_ops->unreg(&st_map->kvalue.data); - if (refcount_dec_and_test(&st_map->kvalue.refcnt)) - bpf_map_put(map); + bpf_map_put(map); return 0; case BPF_STRUCT_OPS_STATE_TOBEFREE: return -EINPROGRESS; @@ -570,7 +605,7 @@ static void bpf_struct_ops_map_seq_show_elem(struct bpf_map *map, void *key, kfree(value); } -static void bpf_struct_ops_map_free(struct bpf_map *map) +static void __bpf_struct_ops_map_free(struct bpf_map *map) { struct bpf_struct_ops_map *st_map = (struct bpf_struct_ops_map *)map; @@ -582,10 +617,32 @@ static void bpf_struct_ops_map_free(struct bpf_map *map) bpf_map_area_free(st_map); } +static void bpf_struct_ops_map_free(struct bpf_map *map) +{ + /* The struct_ops's function may switch to another struct_ops. + * + * For example, bpf_tcp_cc_x->init() may switch to + * another tcp_cc_y by calling + * setsockopt(TCP_CONGESTION, "tcp_cc_y"). + * During the switch, bpf_struct_ops_put(tcp_cc_x) is called + * and its refcount may reach 0 which then free its + * trampoline image while tcp_cc_x is still running. + * + * A vanilla rcu gp is to wait for all bpf-tcp-cc prog + * to finish. bpf-tcp-cc prog is non sleepable. + * A rcu_tasks gp is to wait for the last few insn + * in the tramopline image to finish before releasing + * the trampoline image. + */ + synchronize_rcu_mult(call_rcu, call_rcu_tasks); + + __bpf_struct_ops_map_free(map); +} + static int bpf_struct_ops_map_alloc_check(union bpf_attr *attr) { if (attr->key_size != sizeof(unsigned int) || attr->max_entries != 1 || - attr->map_flags || !attr->btf_vmlinux_value_type_id) + (attr->map_flags & ~BPF_F_LINK) || !attr->btf_vmlinux_value_type_id) return -EINVAL; return 0; } @@ -609,6 +666,9 @@ static struct bpf_map *bpf_struct_ops_map_alloc(union bpf_attr *attr) if (attr->value_size != vt->size) return ERR_PTR(-EINVAL); + if (attr->map_flags & BPF_F_LINK && (!st_ops->validate || !st_ops->update)) + return ERR_PTR(-EOPNOTSUPP); + t = st_ops->type; st_map_size = sizeof(*st_map) + @@ -630,7 +690,7 @@ static struct bpf_map *bpf_struct_ops_map_alloc(union bpf_attr *attr) NUMA_NO_NODE); st_map->image = bpf_jit_alloc_exec(PAGE_SIZE); if (!st_map->uvalue || !st_map->links || !st_map->image) { - bpf_struct_ops_map_free(map); + __bpf_struct_ops_map_free(map); return ERR_PTR(-ENOMEM); } @@ -676,41 +736,175 @@ const struct bpf_map_ops bpf_struct_ops_map_ops = { bool bpf_struct_ops_get(const void *kdata) { struct bpf_struct_ops_value *kvalue; + struct bpf_struct_ops_map *st_map; + struct bpf_map *map; kvalue = container_of(kdata, struct bpf_struct_ops_value, data); + st_map = container_of(kvalue, struct bpf_struct_ops_map, kvalue); - return refcount_inc_not_zero(&kvalue->refcnt); + map = __bpf_map_inc_not_zero(&st_map->map, false); + return !IS_ERR(map); } -static void bpf_struct_ops_put_rcu(struct rcu_head *head) +void bpf_struct_ops_put(const void *kdata) { + struct bpf_struct_ops_value *kvalue; struct bpf_struct_ops_map *st_map; - st_map = container_of(head, struct bpf_struct_ops_map, rcu); + kvalue = container_of(kdata, struct bpf_struct_ops_value, data); + st_map = container_of(kvalue, struct bpf_struct_ops_map, kvalue); + bpf_map_put(&st_map->map); } -void bpf_struct_ops_put(const void *kdata) +static bool bpf_struct_ops_valid_to_reg(struct bpf_map *map) { - struct bpf_struct_ops_value *kvalue; + struct bpf_struct_ops_map *st_map = (struct bpf_struct_ops_map *)map; - kvalue = container_of(kdata, struct bpf_struct_ops_value, data); - if (refcount_dec_and_test(&kvalue->refcnt)) { - struct bpf_struct_ops_map *st_map; + return map->map_type == BPF_MAP_TYPE_STRUCT_OPS && + map->map_flags & BPF_F_LINK && + /* Pair with smp_store_release() during map_update */ + smp_load_acquire(&st_map->kvalue.state) == BPF_STRUCT_OPS_STATE_READY; +} - st_map = container_of(kvalue, struct bpf_struct_ops_map, - kvalue); - /* The struct_ops's function may switch to another struct_ops. - * - * For example, bpf_tcp_cc_x->init() may switch to - * another tcp_cc_y by calling - * setsockopt(TCP_CONGESTION, "tcp_cc_y"). - * During the switch, bpf_struct_ops_put(tcp_cc_x) is called - * and its map->refcnt may reach 0 which then free its - * trampoline image while tcp_cc_x is still running. - * - * Thus, a rcu grace period is needed here. +static void bpf_struct_ops_map_link_dealloc(struct bpf_link *link) +{ + struct bpf_struct_ops_link *st_link; + struct bpf_struct_ops_map *st_map; + + st_link = container_of(link, struct bpf_struct_ops_link, link); + st_map = (struct bpf_struct_ops_map *) + rcu_dereference_protected(st_link->map, true); + if (st_map) { + /* st_link->map can be NULL if + * bpf_struct_ops_link_create() fails to register. */ - call_rcu(&st_map->rcu, bpf_struct_ops_put_rcu); + st_map->st_ops->unreg(&st_map->kvalue.data); + bpf_map_put(&st_map->map); + } + kfree(st_link); +} + +static void bpf_struct_ops_map_link_show_fdinfo(const struct bpf_link *link, + struct seq_file *seq) +{ + struct bpf_struct_ops_link *st_link; + struct bpf_map *map; + + st_link = container_of(link, struct bpf_struct_ops_link, link); + rcu_read_lock(); + map = rcu_dereference(st_link->map); + seq_printf(seq, "map_id:\t%d\n", map->id); + rcu_read_unlock(); +} + +static int bpf_struct_ops_map_link_fill_link_info(const struct bpf_link *link, + struct bpf_link_info *info) +{ + struct bpf_struct_ops_link *st_link; + struct bpf_map *map; + + st_link = container_of(link, struct bpf_struct_ops_link, link); + rcu_read_lock(); + map = rcu_dereference(st_link->map); + info->struct_ops.map_id = map->id; + rcu_read_unlock(); + return 0; +} + +static int bpf_struct_ops_map_link_update(struct bpf_link *link, struct bpf_map *new_map, + struct bpf_map *expected_old_map) +{ + struct bpf_struct_ops_map *st_map, *old_st_map; + struct bpf_map *old_map; + struct bpf_struct_ops_link *st_link; + int err = 0; + + st_link = container_of(link, struct bpf_struct_ops_link, link); + st_map = container_of(new_map, struct bpf_struct_ops_map, map); + + if (!bpf_struct_ops_valid_to_reg(new_map)) + return -EINVAL; + + mutex_lock(&update_mutex); + + old_map = rcu_dereference_protected(st_link->map, lockdep_is_held(&update_mutex)); + if (expected_old_map && old_map != expected_old_map) { + err = -EPERM; + goto err_out; + } + + old_st_map = container_of(old_map, struct bpf_struct_ops_map, map); + /* The new and old struct_ops must be the same type. */ + if (st_map->st_ops != old_st_map->st_ops) { + err = -EINVAL; + goto err_out; } + + err = st_map->st_ops->update(st_map->kvalue.data, old_st_map->kvalue.data); + if (err) + goto err_out; + + bpf_map_inc(new_map); + rcu_assign_pointer(st_link->map, new_map); + bpf_map_put(old_map); + +err_out: + mutex_unlock(&update_mutex); + + return err; } + +static const struct bpf_link_ops bpf_struct_ops_map_lops = { + .dealloc = bpf_struct_ops_map_link_dealloc, + .show_fdinfo = bpf_struct_ops_map_link_show_fdinfo, + .fill_link_info = bpf_struct_ops_map_link_fill_link_info, + .update_map = bpf_struct_ops_map_link_update, +}; + +int bpf_struct_ops_link_create(union bpf_attr *attr) +{ + struct bpf_struct_ops_link *link = NULL; + struct bpf_link_primer link_primer; + struct bpf_struct_ops_map *st_map; + struct bpf_map *map; + int err; + + map = bpf_map_get(attr->link_create.map_fd); + if (IS_ERR(map)) + return PTR_ERR(map); + + st_map = (struct bpf_struct_ops_map *)map; + + if (!bpf_struct_ops_valid_to_reg(map)) { + err = -EINVAL; + goto err_out; + } + + link = kzalloc(sizeof(*link), GFP_USER); + if (!link) { + err = -ENOMEM; + goto err_out; + } + bpf_link_init(&link->link, BPF_LINK_TYPE_STRUCT_OPS, &bpf_struct_ops_map_lops, NULL); + + err = bpf_link_prime(&link->link, &link_primer); + if (err) + goto err_out; + + err = st_map->st_ops->reg(st_map->kvalue.data); + if (err) { + bpf_link_cleanup(&link_primer); + link = NULL; + goto err_out; + } + RCU_INIT_POINTER(link->map, map); + + return bpf_link_settle(&link_primer); + +err_out: + bpf_map_put(map); + kfree(link); + return err; +} + diff --git a/kernel/bpf/bpf_task_storage.c b/kernel/bpf/bpf_task_storage.c index 20f942229f3c..adf6dfe0ba68 100644 --- a/kernel/bpf/bpf_task_storage.c +++ b/kernel/bpf/bpf_task_storage.c @@ -72,8 +72,6 @@ task_storage_lookup(struct task_struct *task, struct bpf_map *map, void bpf_task_storage_free(struct task_struct *task) { struct bpf_local_storage *local_storage; - bool free_task_storage = false; - unsigned long flags; rcu_read_lock(); @@ -84,14 +82,9 @@ void bpf_task_storage_free(struct task_struct *task) } bpf_task_storage_lock(); - raw_spin_lock_irqsave(&local_storage->lock, flags); - free_task_storage = bpf_local_storage_unlink_nolock(local_storage); - raw_spin_unlock_irqrestore(&local_storage->lock, flags); + bpf_local_storage_destroy(local_storage); bpf_task_storage_unlock(); rcu_read_unlock(); - - if (free_task_storage) - kfree_rcu(local_storage, rcu); } static void *bpf_pid_task_storage_lookup_elem(struct bpf_map *map, void *key) @@ -127,8 +120,8 @@ out: return ERR_PTR(err); } -static int bpf_pid_task_storage_update_elem(struct bpf_map *map, void *key, - void *value, u64 map_flags) +static long bpf_pid_task_storage_update_elem(struct bpf_map *map, void *key, + void *value, u64 map_flags) { struct bpf_local_storage_data *sdata; struct task_struct *task; @@ -175,12 +168,12 @@ static int task_storage_delete(struct task_struct *task, struct bpf_map *map, if (!nobusy) return -EBUSY; - bpf_selem_unlink(SELEM(sdata), true); + bpf_selem_unlink(SELEM(sdata), false); return 0; } -static int bpf_pid_task_storage_delete_elem(struct bpf_map *map, void *key) +static long bpf_pid_task_storage_delete_elem(struct bpf_map *map, void *key) { struct task_struct *task; unsigned int f_flags; @@ -316,7 +309,7 @@ static int notsupp_get_next_key(struct bpf_map *map, void *key, void *next_key) static struct bpf_map *task_storage_map_alloc(union bpf_attr *attr) { - return bpf_local_storage_map_alloc(attr, &task_cache); + return bpf_local_storage_map_alloc(attr, &task_cache, true); } static void task_storage_map_free(struct bpf_map *map) @@ -345,7 +338,7 @@ const struct bpf_func_proto bpf_task_storage_get_recur_proto = { .gpl_only = false, .ret_type = RET_PTR_TO_MAP_VALUE_OR_NULL, .arg1_type = ARG_CONST_MAP_PTR, - .arg2_type = ARG_PTR_TO_BTF_ID, + .arg2_type = ARG_PTR_TO_BTF_ID_OR_NULL, .arg2_btf_id = &btf_tracing_ids[BTF_TRACING_TYPE_TASK], .arg3_type = ARG_PTR_TO_MAP_VALUE_OR_NULL, .arg4_type = ARG_ANYTHING, @@ -356,7 +349,7 @@ const struct bpf_func_proto bpf_task_storage_get_proto = { .gpl_only = false, .ret_type = RET_PTR_TO_MAP_VALUE_OR_NULL, .arg1_type = ARG_CONST_MAP_PTR, - .arg2_type = ARG_PTR_TO_BTF_ID, + .arg2_type = ARG_PTR_TO_BTF_ID_OR_NULL, .arg2_btf_id = &btf_tracing_ids[BTF_TRACING_TYPE_TASK], .arg3_type = ARG_PTR_TO_MAP_VALUE_OR_NULL, .arg4_type = ARG_ANYTHING, @@ -367,7 +360,7 @@ const struct bpf_func_proto bpf_task_storage_delete_recur_proto = { .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_CONST_MAP_PTR, - .arg2_type = ARG_PTR_TO_BTF_ID, + .arg2_type = ARG_PTR_TO_BTF_ID_OR_NULL, .arg2_btf_id = &btf_tracing_ids[BTF_TRACING_TYPE_TASK], }; @@ -376,6 +369,6 @@ const struct bpf_func_proto bpf_task_storage_delete_proto = { .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_CONST_MAP_PTR, - .arg2_type = ARG_PTR_TO_BTF_ID, + .arg2_type = ARG_PTR_TO_BTF_ID_OR_NULL, .arg2_btf_id = &btf_tracing_ids[BTF_TRACING_TYPE_TASK], }; diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 1853beaed4be..2c2d1fb9f410 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -3231,12 +3231,6 @@ static void btf_struct_log(struct btf_verifier_env *env, btf_verifier_log(env, "size=%u vlen=%u", t->size, btf_type_vlen(t)); } -enum btf_field_info_type { - BTF_FIELD_SPIN_LOCK, - BTF_FIELD_TIMER, - BTF_FIELD_KPTR, -}; - enum { BTF_FIELD_IGNORE = 0, BTF_FIELD_FOUND = 1, @@ -3562,7 +3556,10 @@ static int btf_parse_kptr(const struct btf *btf, struct btf_field *field, { struct module *mod = NULL; const struct btf_type *t; - struct btf *kernel_btf; + /* If a matching btf type is found in kernel or module BTFs, kptr_ref + * is that BTF, otherwise it's program BTF + */ + struct btf *kptr_btf; int ret; s32 id; @@ -3571,7 +3568,20 @@ static int btf_parse_kptr(const struct btf *btf, struct btf_field *field, */ t = btf_type_by_id(btf, info->kptr.type_id); id = bpf_find_btf_id(__btf_name_by_offset(btf, t->name_off), BTF_INFO_KIND(t->info), - &kernel_btf); + &kptr_btf); + if (id == -ENOENT) { + /* btf_parse_kptr should only be called w/ btf = program BTF */ + WARN_ON_ONCE(btf_is_kernel(btf)); + + /* Type exists only in program BTF. Assume that it's a MEM_ALLOC + * kptr allocated via bpf_obj_new + */ + field->kptr.dtor = NULL; + id = info->kptr.type_id; + kptr_btf = (struct btf *)btf; + btf_get(kptr_btf); + goto found_dtor; + } if (id < 0) return id; @@ -3588,20 +3598,20 @@ static int btf_parse_kptr(const struct btf *btf, struct btf_field *field, * can be used as a referenced pointer and be stored in a map at * the same time. */ - dtor_btf_id = btf_find_dtor_kfunc(kernel_btf, id); + dtor_btf_id = btf_find_dtor_kfunc(kptr_btf, id); if (dtor_btf_id < 0) { ret = dtor_btf_id; goto end_btf; } - dtor_func = btf_type_by_id(kernel_btf, dtor_btf_id); + dtor_func = btf_type_by_id(kptr_btf, dtor_btf_id); if (!dtor_func) { ret = -ENOENT; goto end_btf; } - if (btf_is_module(kernel_btf)) { - mod = btf_try_get_module(kernel_btf); + if (btf_is_module(kptr_btf)) { + mod = btf_try_get_module(kptr_btf); if (!mod) { ret = -ENXIO; goto end_btf; @@ -3611,7 +3621,7 @@ static int btf_parse_kptr(const struct btf *btf, struct btf_field *field, /* We already verified dtor_func to be btf_type_is_func * in register_btf_id_dtor_kfuncs. */ - dtor_func_name = __btf_name_by_offset(kernel_btf, dtor_func->name_off); + dtor_func_name = __btf_name_by_offset(kptr_btf, dtor_func->name_off); addr = kallsyms_lookup_name(dtor_func_name); if (!addr) { ret = -EINVAL; @@ -3620,14 +3630,15 @@ static int btf_parse_kptr(const struct btf *btf, struct btf_field *field, field->kptr.dtor = (void *)addr; } +found_dtor: field->kptr.btf_id = id; - field->kptr.btf = kernel_btf; + field->kptr.btf = kptr_btf; field->kptr.module = mod; return 0; end_mod: module_put(mod); end_btf: - btf_put(kernel_btf); + btf_put(kptr_btf); return ret; } @@ -5494,38 +5505,45 @@ static int btf_check_type_tags(struct btf_verifier_env *env, return 0; } -static struct btf *btf_parse(bpfptr_t btf_data, u32 btf_data_size, - u32 log_level, char __user *log_ubuf, u32 log_size) +static int finalize_log(struct bpf_verifier_log *log, bpfptr_t uattr, u32 uattr_size) { + u32 log_true_size; + int err; + + err = bpf_vlog_finalize(log, &log_true_size); + + if (uattr_size >= offsetofend(union bpf_attr, btf_log_true_size) && + copy_to_bpfptr_offset(uattr, offsetof(union bpf_attr, btf_log_true_size), + &log_true_size, sizeof(log_true_size))) + err = -EFAULT; + + return err; +} + +static struct btf *btf_parse(const union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size) +{ + bpfptr_t btf_data = make_bpfptr(attr->btf, uattr.is_kernel); + char __user *log_ubuf = u64_to_user_ptr(attr->btf_log_buf); struct btf_struct_metas *struct_meta_tab; struct btf_verifier_env *env = NULL; - struct bpf_verifier_log *log; struct btf *btf = NULL; u8 *data; - int err; + int err, ret; - if (btf_data_size > BTF_MAX_SIZE) + if (attr->btf_size > BTF_MAX_SIZE) return ERR_PTR(-E2BIG); env = kzalloc(sizeof(*env), GFP_KERNEL | __GFP_NOWARN); if (!env) return ERR_PTR(-ENOMEM); - log = &env->log; - if (log_level || log_ubuf || log_size) { - /* user requested verbose verifier output - * and supplied buffer to store the verification trace - */ - log->level = log_level; - log->ubuf = log_ubuf; - log->len_total = log_size; - - /* log attributes have to be sane */ - if (!bpf_verifier_log_attr_valid(log)) { - err = -EINVAL; - goto errout; - } - } + /* user could have requested verbose verifier output + * and supplied buffer to store the verification trace + */ + err = bpf_vlog_init(&env->log, attr->btf_log_level, + log_ubuf, attr->btf_log_size); + if (err) + goto errout_free; btf = kzalloc(sizeof(*btf), GFP_KERNEL | __GFP_NOWARN); if (!btf) { @@ -5534,16 +5552,16 @@ static struct btf *btf_parse(bpfptr_t btf_data, u32 btf_data_size, } env->btf = btf; - data = kvmalloc(btf_data_size, GFP_KERNEL | __GFP_NOWARN); + data = kvmalloc(attr->btf_size, GFP_KERNEL | __GFP_NOWARN); if (!data) { err = -ENOMEM; goto errout; } btf->data = data; - btf->data_size = btf_data_size; + btf->data_size = attr->btf_size; - if (copy_from_bpfptr(data, btf_data, btf_data_size)) { + if (copy_from_bpfptr(data, btf_data, attr->btf_size)) { err = -EFAULT; goto errout; } @@ -5566,7 +5584,7 @@ static struct btf *btf_parse(bpfptr_t btf_data, u32 btf_data_size, if (err) goto errout; - struct_meta_tab = btf_parse_struct_metas(log, btf); + struct_meta_tab = btf_parse_struct_metas(&env->log, btf); if (IS_ERR(struct_meta_tab)) { err = PTR_ERR(struct_meta_tab); goto errout; @@ -5583,10 +5601,9 @@ static struct btf *btf_parse(bpfptr_t btf_data, u32 btf_data_size, } } - if (log->level && bpf_verifier_log_full(log)) { - err = -ENOSPC; - goto errout_meta; - } + err = finalize_log(&env->log, uattr, uattr_size); + if (err) + goto errout_free; btf_verifier_env_free(env); refcount_set(&btf->refcnt, 1); @@ -5595,6 +5612,11 @@ static struct btf *btf_parse(bpfptr_t btf_data, u32 btf_data_size, errout_meta: btf_free_struct_meta_tab(btf); errout: + /* overwrite err with -ENOSPC or -EFAULT */ + ret = finalize_log(&env->log, uattr, uattr_size); + if (ret) + err = ret; +errout_free: btf_verifier_env_free(env); if (btf) btf_free(btf); @@ -5900,12 +5922,8 @@ struct btf *bpf_prog_get_target_btf(const struct bpf_prog *prog) static bool is_int_ptr(struct btf *btf, const struct btf_type *t) { - /* t comes in already as a pointer */ - t = btf_type_by_id(btf, t->type); - - /* allow const */ - if (BTF_INFO_KIND(t->info) == BTF_KIND_CONST) - t = btf_type_by_id(btf, t->type); + /* skip modifiers */ + t = btf_type_skip_modifiers(btf, t->type, NULL); return btf_type_is_int(t); } @@ -6156,7 +6174,8 @@ enum bpf_struct_walk_result { static int btf_struct_walk(struct bpf_verifier_log *log, const struct btf *btf, const struct btf_type *t, int off, int size, - u32 *next_btf_id, enum bpf_type_flag *flag) + u32 *next_btf_id, enum bpf_type_flag *flag, + const char **field_name) { u32 i, moff, mtrue_end, msize = 0, total_nelems = 0; const struct btf_type *mtype, *elem_type = NULL; @@ -6385,6 +6404,8 @@ error: if (btf_type_is_struct(stype)) { *next_btf_id = id; *flag |= tmp_flag; + if (field_name) + *field_name = mname; return WALK_PTR; } } @@ -6411,7 +6432,8 @@ error: int btf_struct_access(struct bpf_verifier_log *log, const struct bpf_reg_state *reg, int off, int size, enum bpf_access_type atype __maybe_unused, - u32 *next_btf_id, enum bpf_type_flag *flag) + u32 *next_btf_id, enum bpf_type_flag *flag, + const char **field_name) { const struct btf *btf = reg->btf; enum bpf_type_flag tmp_flag = 0; @@ -6443,7 +6465,7 @@ int btf_struct_access(struct bpf_verifier_log *log, t = btf_type_by_id(btf, id); do { - err = btf_struct_walk(log, btf, t, off, size, &id, &tmp_flag); + err = btf_struct_walk(log, btf, t, off, size, &id, &tmp_flag, field_name); switch (err) { case WALK_PTR: @@ -6518,7 +6540,7 @@ again: type = btf_type_by_id(btf, id); if (!type) return false; - err = btf_struct_walk(log, btf, type, off, 1, &id, &flag); + err = btf_struct_walk(log, btf, type, off, 1, &id, &flag, NULL); if (err != WALK_STRUCT) return false; @@ -7199,15 +7221,12 @@ static int __btf_new_fd(struct btf *btf) return anon_inode_getfd("btf", &btf_fops, btf, O_RDONLY | O_CLOEXEC); } -int btf_new_fd(const union bpf_attr *attr, bpfptr_t uattr) +int btf_new_fd(const union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size) { struct btf *btf; int ret; - btf = btf_parse(make_bpfptr(attr->btf, uattr.is_kernel), - attr->btf_size, attr->btf_log_level, - u64_to_user_ptr(attr->btf_log_buf), - attr->btf_log_size); + btf = btf_parse(attr, uattr, uattr_size); if (IS_ERR(btf)) return PTR_ERR(btf); @@ -7597,6 +7616,108 @@ BTF_ID_LIST_GLOBAL(btf_tracing_ids, MAX_BTF_TRACING_TYPE) BTF_TRACING_TYPE_xxx #undef BTF_TRACING_TYPE +static int btf_check_iter_kfuncs(struct btf *btf, const char *func_name, + const struct btf_type *func, u32 func_flags) +{ + u32 flags = func_flags & (KF_ITER_NEW | KF_ITER_NEXT | KF_ITER_DESTROY); + const char *name, *sfx, *iter_name; + const struct btf_param *arg; + const struct btf_type *t; + char exp_name[128]; + u32 nr_args; + + /* exactly one of KF_ITER_{NEW,NEXT,DESTROY} can be set */ + if (!flags || (flags & (flags - 1))) + return -EINVAL; + + /* any BPF iter kfunc should have `struct bpf_iter_<type> *` first arg */ + nr_args = btf_type_vlen(func); + if (nr_args < 1) + return -EINVAL; + + arg = &btf_params(func)[0]; + t = btf_type_skip_modifiers(btf, arg->type, NULL); + if (!t || !btf_type_is_ptr(t)) + return -EINVAL; + t = btf_type_skip_modifiers(btf, t->type, NULL); + if (!t || !__btf_type_is_struct(t)) + return -EINVAL; + + name = btf_name_by_offset(btf, t->name_off); + if (!name || strncmp(name, ITER_PREFIX, sizeof(ITER_PREFIX) - 1)) + return -EINVAL; + + /* sizeof(struct bpf_iter_<type>) should be a multiple of 8 to + * fit nicely in stack slots + */ + if (t->size == 0 || (t->size % 8)) + return -EINVAL; + + /* validate bpf_iter_<type>_{new,next,destroy}(struct bpf_iter_<type> *) + * naming pattern + */ + iter_name = name + sizeof(ITER_PREFIX) - 1; + if (flags & KF_ITER_NEW) + sfx = "new"; + else if (flags & KF_ITER_NEXT) + sfx = "next"; + else /* (flags & KF_ITER_DESTROY) */ + sfx = "destroy"; + + snprintf(exp_name, sizeof(exp_name), "bpf_iter_%s_%s", iter_name, sfx); + if (strcmp(func_name, exp_name)) + return -EINVAL; + + /* only iter constructor should have extra arguments */ + if (!(flags & KF_ITER_NEW) && nr_args != 1) + return -EINVAL; + + if (flags & KF_ITER_NEXT) { + /* bpf_iter_<type>_next() should return pointer */ + t = btf_type_skip_modifiers(btf, func->type, NULL); + if (!t || !btf_type_is_ptr(t)) + return -EINVAL; + } + + if (flags & KF_ITER_DESTROY) { + /* bpf_iter_<type>_destroy() should return void */ + t = btf_type_by_id(btf, func->type); + if (!t || !btf_type_is_void(t)) + return -EINVAL; + } + + return 0; +} + +static int btf_check_kfunc_protos(struct btf *btf, u32 func_id, u32 func_flags) +{ + const struct btf_type *func; + const char *func_name; + int err; + + /* any kfunc should be FUNC -> FUNC_PROTO */ + func = btf_type_by_id(btf, func_id); + if (!func || !btf_type_is_func(func)) + return -EINVAL; + + /* sanity check kfunc name */ + func_name = btf_name_by_offset(btf, func->name_off); + if (!func_name || !func_name[0]) + return -EINVAL; + + func = btf_type_by_id(btf, func->type); + if (!func || !btf_type_is_func_proto(func)) + return -EINVAL; + + if (func_flags & (KF_ITER_NEW | KF_ITER_NEXT | KF_ITER_DESTROY)) { + err = btf_check_iter_kfuncs(btf, func_name, func, func_flags); + if (err) + return err; + } + + return 0; +} + /* Kernel Function (kfunc) BTF ID set registration API */ static int btf_populate_kfunc_set(struct btf *btf, enum btf_kfunc_hook hook, @@ -7773,7 +7894,7 @@ static int __register_btf_kfunc_id_set(enum btf_kfunc_hook hook, const struct btf_kfunc_id_set *kset) { struct btf *btf; - int ret; + int ret, i; btf = btf_get_module_btf(kset->owner); if (!btf) { @@ -7790,7 +7911,15 @@ static int __register_btf_kfunc_id_set(enum btf_kfunc_hook hook, if (IS_ERR(btf)) return PTR_ERR(btf); + for (i = 0; i < kset->set->cnt; i++) { + ret = btf_check_kfunc_protos(btf, kset->set->pairs[i].id, + kset->set->pairs[i].flags); + if (ret) + goto err_out; + } + ret = btf_populate_kfunc_set(btf, hook, kset->set); +err_out: btf_put(btf); return ret; } @@ -8368,16 +8497,15 @@ out: bool btf_nested_type_is_trusted(struct bpf_verifier_log *log, const struct bpf_reg_state *reg, - int off, const char *suffix) + const char *field_name, u32 btf_id, const char *suffix) { struct btf *btf = reg->btf; const struct btf_type *walk_type, *safe_type; const char *tname; char safe_tname[64]; long ret, safe_id; - const struct btf_member *member, *m_walk = NULL; + const struct btf_member *member; u32 i; - const char *walk_name; walk_type = btf_type_by_id(btf, reg->btf_id); if (!walk_type) @@ -8397,30 +8525,17 @@ bool btf_nested_type_is_trusted(struct bpf_verifier_log *log, if (!safe_type) return false; - for_each_member(i, walk_type, member) { - u32 moff; - - /* We're looking for the PTR_TO_BTF_ID member in the struct - * type we're walking which matches the specified offset. - * Below, we'll iterate over the fields in the safe variant of - * the struct and see if any of them has a matching type / - * name. - */ - moff = __btf_member_bit_offset(walk_type, member) / 8; - if (off == moff) { - m_walk = member; - break; - } - } - if (m_walk == NULL) - return false; - - walk_name = __btf_name_by_offset(btf, m_walk->name_off); for_each_member(i, safe_type, member) { const char *m_name = __btf_name_by_offset(btf, member->name_off); + const struct btf_type *mtype = btf_type_by_id(btf, member->type); + u32 id; + + if (!btf_type_is_ptr(mtype)) + continue; + btf_type_skip_modifiers(btf, mtype->type, &id); /* If we match on both type and name, the field is considered trusted. */ - if (m_walk->type == member->type && !strcmp(walk_name, m_name)) + if (btf_id == id && !strcmp(field_name, m_name)) return true; } diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c index 871809e71b4e..8ec18faa74ac 100644 --- a/kernel/bpf/cpumap.c +++ b/kernel/bpf/cpumap.c @@ -540,7 +540,7 @@ static void __cpu_map_entry_replace(struct bpf_cpu_map *cmap, } } -static int cpu_map_delete_elem(struct bpf_map *map, void *key) +static long cpu_map_delete_elem(struct bpf_map *map, void *key) { struct bpf_cpu_map *cmap = container_of(map, struct bpf_cpu_map, map); u32 key_cpu = *(u32 *)key; @@ -553,8 +553,8 @@ static int cpu_map_delete_elem(struct bpf_map *map, void *key) return 0; } -static int cpu_map_update_elem(struct bpf_map *map, void *key, void *value, - u64 map_flags) +static long cpu_map_update_elem(struct bpf_map *map, void *key, void *value, + u64 map_flags) { struct bpf_cpu_map *cmap = container_of(map, struct bpf_cpu_map, map); struct bpf_cpumap_val cpumap_value = {}; @@ -667,7 +667,7 @@ static int cpu_map_get_next_key(struct bpf_map *map, void *key, void *next_key) return 0; } -static int cpu_map_redirect(struct bpf_map *map, u64 index, u64 flags) +static long cpu_map_redirect(struct bpf_map *map, u64 index, u64 flags) { return __bpf_xdp_redirect_map(map, index, flags, 0, __cpu_map_lookup_elem); diff --git a/kernel/bpf/cpumask.c b/kernel/bpf/cpumask.c index b6587ec40f1b..7efdf5d770ca 100644 --- a/kernel/bpf/cpumask.c +++ b/kernel/bpf/cpumask.c @@ -9,6 +9,7 @@ /** * struct bpf_cpumask - refcounted BPF cpumask wrapper structure * @cpumask: The actual cpumask embedded in the struct. + * @rcu: The RCU head used to free the cpumask with RCU safety. * @usage: Object reference counter. When the refcount goes to 0, the * memory is released back to the BPF allocator, which provides * RCU safety. @@ -24,6 +25,7 @@ */ struct bpf_cpumask { cpumask_t cpumask; + struct rcu_head rcu; refcount_t usage; }; @@ -80,32 +82,14 @@ __bpf_kfunc struct bpf_cpumask *bpf_cpumask_acquire(struct bpf_cpumask *cpumask) return cpumask; } -/** - * bpf_cpumask_kptr_get() - Attempt to acquire a reference to a BPF cpumask - * stored in a map. - * @cpumaskp: A pointer to a BPF cpumask map value. - * - * Attempts to acquire a reference to a BPF cpumask stored in a map value. The - * cpumask returned by this function must either be embedded in a map as a - * kptr, or freed with bpf_cpumask_release(). This function may return NULL if - * no BPF cpumask was found in the specified map value. - */ -__bpf_kfunc struct bpf_cpumask *bpf_cpumask_kptr_get(struct bpf_cpumask **cpumaskp) +static void cpumask_free_cb(struct rcu_head *head) { struct bpf_cpumask *cpumask; - /* The BPF memory allocator frees memory backing its caches in an RCU - * callback. Thus, we can safely use RCU to ensure that the cpumask is - * safe to read. - */ - rcu_read_lock(); - - cpumask = READ_ONCE(*cpumaskp); - if (cpumask && !refcount_inc_not_zero(&cpumask->usage)) - cpumask = NULL; - - rcu_read_unlock(); - return cpumask; + cpumask = container_of(head, struct bpf_cpumask, rcu); + migrate_disable(); + bpf_mem_cache_free(&bpf_cpumask_ma, cpumask); + migrate_enable(); } /** @@ -118,14 +102,8 @@ __bpf_kfunc struct bpf_cpumask *bpf_cpumask_kptr_get(struct bpf_cpumask **cpumas */ __bpf_kfunc void bpf_cpumask_release(struct bpf_cpumask *cpumask) { - if (!cpumask) - return; - - if (refcount_dec_and_test(&cpumask->usage)) { - migrate_disable(); - bpf_mem_cache_free(&bpf_cpumask_ma, cpumask); - migrate_enable(); - } + if (refcount_dec_and_test(&cpumask->usage)) + call_rcu(&cpumask->rcu, cpumask_free_cb); } /** @@ -424,9 +402,8 @@ __diag_pop(); BTF_SET8_START(cpumask_kfunc_btf_ids) BTF_ID_FLAGS(func, bpf_cpumask_create, KF_ACQUIRE | KF_RET_NULL) -BTF_ID_FLAGS(func, bpf_cpumask_release, KF_RELEASE | KF_TRUSTED_ARGS) +BTF_ID_FLAGS(func, bpf_cpumask_release, KF_RELEASE) BTF_ID_FLAGS(func, bpf_cpumask_acquire, KF_ACQUIRE | KF_TRUSTED_ARGS) -BTF_ID_FLAGS(func, bpf_cpumask_kptr_get, KF_ACQUIRE | KF_KPTR_GET | KF_RET_NULL) BTF_ID_FLAGS(func, bpf_cpumask_first, KF_RCU) BTF_ID_FLAGS(func, bpf_cpumask_first_zero, KF_RCU) BTF_ID_FLAGS(func, bpf_cpumask_set_cpu, KF_RCU) diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c index 19b036a228f7..802692fa3905 100644 --- a/kernel/bpf/devmap.c +++ b/kernel/bpf/devmap.c @@ -809,7 +809,7 @@ static void __dev_map_entry_free(struct rcu_head *rcu) kfree(dev); } -static int dev_map_delete_elem(struct bpf_map *map, void *key) +static long dev_map_delete_elem(struct bpf_map *map, void *key) { struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); struct bpf_dtab_netdev *old_dev; @@ -826,7 +826,7 @@ static int dev_map_delete_elem(struct bpf_map *map, void *key) return 0; } -static int dev_map_hash_delete_elem(struct bpf_map *map, void *key) +static long dev_map_hash_delete_elem(struct bpf_map *map, void *key) { struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); struct bpf_dtab_netdev *old_dev; @@ -897,8 +897,8 @@ err_out: return ERR_PTR(-EINVAL); } -static int __dev_map_update_elem(struct net *net, struct bpf_map *map, - void *key, void *value, u64 map_flags) +static long __dev_map_update_elem(struct net *net, struct bpf_map *map, + void *key, void *value, u64 map_flags) { struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); struct bpf_dtab_netdev *dev, *old_dev; @@ -939,15 +939,15 @@ static int __dev_map_update_elem(struct net *net, struct bpf_map *map, return 0; } -static int dev_map_update_elem(struct bpf_map *map, void *key, void *value, - u64 map_flags) +static long dev_map_update_elem(struct bpf_map *map, void *key, void *value, + u64 map_flags) { return __dev_map_update_elem(current->nsproxy->net_ns, map, key, value, map_flags); } -static int __dev_map_hash_update_elem(struct net *net, struct bpf_map *map, - void *key, void *value, u64 map_flags) +static long __dev_map_hash_update_elem(struct net *net, struct bpf_map *map, + void *key, void *value, u64 map_flags) { struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); struct bpf_dtab_netdev *dev, *old_dev; @@ -999,21 +999,21 @@ out_err: return err; } -static int dev_map_hash_update_elem(struct bpf_map *map, void *key, void *value, - u64 map_flags) +static long dev_map_hash_update_elem(struct bpf_map *map, void *key, void *value, + u64 map_flags) { return __dev_map_hash_update_elem(current->nsproxy->net_ns, map, key, value, map_flags); } -static int dev_map_redirect(struct bpf_map *map, u64 ifindex, u64 flags) +static long dev_map_redirect(struct bpf_map *map, u64 ifindex, u64 flags) { return __bpf_xdp_redirect_map(map, ifindex, flags, BPF_F_BROADCAST | BPF_F_EXCLUDE_INGRESS, __dev_map_lookup_elem); } -static int dev_hash_map_redirect(struct bpf_map *map, u64 ifindex, u64 flags) +static long dev_hash_map_redirect(struct bpf_map *map, u64 ifindex, u64 flags) { return __bpf_xdp_redirect_map(map, ifindex, flags, BPF_F_BROADCAST | BPF_F_EXCLUDE_INGRESS, diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index 0df4b0c10f59..00c253b84bf5 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -607,6 +607,8 @@ free_htab: static inline u32 htab_map_hash(const void *key, u32 key_len, u32 hashrnd) { + if (likely(key_len % 4 == 0)) + return jhash2(key, key_len / 4, hashrnd); return jhash(key, key_len, hashrnd); } @@ -1073,8 +1075,8 @@ static int check_flags(struct bpf_htab *htab, struct htab_elem *l_old, } /* Called from syscall or from eBPF program */ -static int htab_map_update_elem(struct bpf_map *map, void *key, void *value, - u64 map_flags) +static long htab_map_update_elem(struct bpf_map *map, void *key, void *value, + u64 map_flags) { struct bpf_htab *htab = container_of(map, struct bpf_htab, map); struct htab_elem *l_new = NULL, *l_old; @@ -1175,8 +1177,8 @@ static void htab_lru_push_free(struct bpf_htab *htab, struct htab_elem *elem) bpf_lru_push_free(&htab->lru, &elem->lru_node); } -static int htab_lru_map_update_elem(struct bpf_map *map, void *key, void *value, - u64 map_flags) +static long htab_lru_map_update_elem(struct bpf_map *map, void *key, void *value, + u64 map_flags) { struct bpf_htab *htab = container_of(map, struct bpf_htab, map); struct htab_elem *l_new, *l_old = NULL; @@ -1242,9 +1244,9 @@ err: return ret; } -static int __htab_percpu_map_update_elem(struct bpf_map *map, void *key, - void *value, u64 map_flags, - bool onallcpus) +static long __htab_percpu_map_update_elem(struct bpf_map *map, void *key, + void *value, u64 map_flags, + bool onallcpus) { struct bpf_htab *htab = container_of(map, struct bpf_htab, map); struct htab_elem *l_new = NULL, *l_old; @@ -1297,9 +1299,9 @@ err: return ret; } -static int __htab_lru_percpu_map_update_elem(struct bpf_map *map, void *key, - void *value, u64 map_flags, - bool onallcpus) +static long __htab_lru_percpu_map_update_elem(struct bpf_map *map, void *key, + void *value, u64 map_flags, + bool onallcpus) { struct bpf_htab *htab = container_of(map, struct bpf_htab, map); struct htab_elem *l_new = NULL, *l_old; @@ -1364,21 +1366,21 @@ err: return ret; } -static int htab_percpu_map_update_elem(struct bpf_map *map, void *key, - void *value, u64 map_flags) +static long htab_percpu_map_update_elem(struct bpf_map *map, void *key, + void *value, u64 map_flags) { return __htab_percpu_map_update_elem(map, key, value, map_flags, false); } -static int htab_lru_percpu_map_update_elem(struct bpf_map *map, void *key, - void *value, u64 map_flags) +static long htab_lru_percpu_map_update_elem(struct bpf_map *map, void *key, + void *value, u64 map_flags) { return __htab_lru_percpu_map_update_elem(map, key, value, map_flags, false); } /* Called from syscall or from eBPF program */ -static int htab_map_delete_elem(struct bpf_map *map, void *key) +static long htab_map_delete_elem(struct bpf_map *map, void *key) { struct bpf_htab *htab = container_of(map, struct bpf_htab, map); struct hlist_nulls_head *head; @@ -1414,7 +1416,7 @@ static int htab_map_delete_elem(struct bpf_map *map, void *key) return ret; } -static int htab_lru_map_delete_elem(struct bpf_map *map, void *key) +static long htab_lru_map_delete_elem(struct bpf_map *map, void *key) { struct bpf_htab *htab = container_of(map, struct bpf_htab, map); struct hlist_nulls_head *head; @@ -2134,8 +2136,8 @@ static const struct bpf_iter_seq_info iter_seq_info = { .seq_priv_size = sizeof(struct bpf_iter_seq_hash_map_info), }; -static int bpf_for_each_hash_elem(struct bpf_map *map, bpf_callback_t callback_fn, - void *callback_ctx, u64 flags) +static long bpf_for_each_hash_elem(struct bpf_map *map, bpf_callback_t callback_fn, + void *callback_ctx, u64 flags) { struct bpf_htab *htab = container_of(map, struct bpf_htab, map); struct hlist_nulls_head *head; diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index 637ac4e92e75..f04e60a4847f 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -18,6 +18,7 @@ #include <linux/pid_namespace.h> #include <linux/poison.h> #include <linux/proc_ns.h> +#include <linux/sched/task.h> #include <linux/security.h> #include <linux/btf_ids.h> #include <linux/bpf_mem_alloc.h> @@ -257,7 +258,7 @@ BPF_CALL_2(bpf_get_current_comm, char *, buf, u32, size) goto err_clear; /* Verifier guarantees that size > 0 */ - strscpy(buf, task->comm, size); + strscpy_pad(buf, task->comm, size); return 0; err_clear: memset(buf, 0, size); @@ -571,7 +572,7 @@ static const struct bpf_func_proto bpf_strncmp_proto = { .func = bpf_strncmp, .gpl_only = false, .ret_type = RET_INTEGER, - .arg1_type = ARG_PTR_TO_MEM, + .arg1_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg2_type = ARG_CONST_SIZE, .arg3_type = ARG_PTR_TO_CONST_STR, }; @@ -1896,14 +1897,19 @@ __bpf_kfunc void *bpf_obj_new_impl(u64 local_type_id__k, void *meta__ign) return p; } +void __bpf_obj_drop_impl(void *p, const struct btf_record *rec) +{ + if (rec) + bpf_obj_free_fields(rec, p); + bpf_mem_free(&bpf_global_ma, p); +} + __bpf_kfunc void bpf_obj_drop_impl(void *p__alloc, void *meta__ign) { struct btf_struct_meta *meta = meta__ign; void *p = p__alloc; - if (meta) - bpf_obj_free_fields(meta->record, p); - bpf_mem_free(&bpf_global_ma, p); + __bpf_obj_drop_impl(p, meta ? meta->record : NULL); } static void __bpf_list_add(struct bpf_list_node *node, struct bpf_list_head *head, bool tail) @@ -2008,73 +2014,8 @@ __bpf_kfunc struct bpf_rb_node *bpf_rbtree_first(struct bpf_rb_root *root) */ __bpf_kfunc struct task_struct *bpf_task_acquire(struct task_struct *p) { - return get_task_struct(p); -} - -/** - * bpf_task_acquire_not_zero - Acquire a reference to a rcu task object. A task - * acquired by this kfunc which is not stored in a map as a kptr, must be - * released by calling bpf_task_release(). - * @p: The task on which a reference is being acquired. - */ -__bpf_kfunc struct task_struct *bpf_task_acquire_not_zero(struct task_struct *p) -{ - /* For the time being this function returns NULL, as it's not currently - * possible to safely acquire a reference to a task with RCU protection - * using get_task_struct() and put_task_struct(). This is due to the - * slightly odd mechanics of p->rcu_users, and how task RCU protection - * works. - * - * A struct task_struct is refcounted by two different refcount_t - * fields: - * - * 1. p->usage: The "true" refcount field which tracks a task's - * lifetime. The task is freed as soon as this - * refcount drops to 0. - * - * 2. p->rcu_users: An "RCU users" refcount field which is statically - * initialized to 2, and is co-located in a union with - * a struct rcu_head field (p->rcu). p->rcu_users - * essentially encapsulates a single p->usage - * refcount, and when p->rcu_users goes to 0, an RCU - * callback is scheduled on the struct rcu_head which - * decrements the p->usage refcount. - * - * There are two important implications to this task refcounting logic - * described above. The first is that - * refcount_inc_not_zero(&p->rcu_users) cannot be used anywhere, as - * after the refcount goes to 0, the RCU callback being scheduled will - * cause the memory backing the refcount to again be nonzero due to the - * fields sharing a union. The other is that we can't rely on RCU to - * guarantee that a task is valid in a BPF program. This is because a - * task could have already transitioned to being in the TASK_DEAD - * state, had its rcu_users refcount go to 0, and its rcu callback - * invoked in which it drops its single p->usage reference. At this - * point the task will be freed as soon as the last p->usage reference - * goes to 0, without waiting for another RCU gp to elapse. The only - * way that a BPF program can guarantee that a task is valid is in this - * scenario is to hold a p->usage refcount itself. - * - * Until we're able to resolve this issue, either by pulling - * p->rcu_users and p->rcu out of the union, or by getting rid of - * p->usage and just using p->rcu_users for refcounting, we'll just - * return NULL here. - */ - return NULL; -} - -/** - * bpf_task_kptr_get - Acquire a reference on a struct task_struct kptr. A task - * kptr acquired by this kfunc which is not subsequently stored in a map, must - * be released by calling bpf_task_release(). - * @pp: A pointer to a task kptr on which a reference is being acquired. - */ -__bpf_kfunc struct task_struct *bpf_task_kptr_get(struct task_struct **pp) -{ - /* We must return NULL here until we have clarity on how to properly - * leverage RCU for ensuring a task's lifetime. See the comment above - * in bpf_task_acquire_not_zero() for more details. - */ + if (refcount_inc_not_zero(&p->rcu_users)) + return p; return NULL; } @@ -2084,10 +2025,7 @@ __bpf_kfunc struct task_struct *bpf_task_kptr_get(struct task_struct **pp) */ __bpf_kfunc void bpf_task_release(struct task_struct *p) { - if (!p) - return; - - put_task_struct(p); + put_task_struct_rcu_user(p); } #ifdef CONFIG_CGROUPS @@ -2099,39 +2037,7 @@ __bpf_kfunc void bpf_task_release(struct task_struct *p) */ __bpf_kfunc struct cgroup *bpf_cgroup_acquire(struct cgroup *cgrp) { - cgroup_get(cgrp); - return cgrp; -} - -/** - * bpf_cgroup_kptr_get - Acquire a reference on a struct cgroup kptr. A cgroup - * kptr acquired by this kfunc which is not subsequently stored in a map, must - * be released by calling bpf_cgroup_release(). - * @cgrpp: A pointer to a cgroup kptr on which a reference is being acquired. - */ -__bpf_kfunc struct cgroup *bpf_cgroup_kptr_get(struct cgroup **cgrpp) -{ - struct cgroup *cgrp; - - rcu_read_lock(); - /* Another context could remove the cgroup from the map and release it - * at any time, including after we've done the lookup above. This is - * safe because we're in an RCU read region, so the cgroup is - * guaranteed to remain valid until at least the rcu_read_unlock() - * below. - */ - cgrp = READ_ONCE(*cgrpp); - - if (cgrp && !cgroup_tryget(cgrp)) - /* If the cgroup had been removed from the map and freed as - * described above, cgroup_tryget() will return false. The - * cgroup will be freed at some point after the current RCU gp - * has ended, so just return NULL to the user. - */ - cgrp = NULL; - rcu_read_unlock(); - - return cgrp; + return cgroup_tryget(cgrp) ? cgrp : NULL; } /** @@ -2143,9 +2049,6 @@ __bpf_kfunc struct cgroup *bpf_cgroup_kptr_get(struct cgroup **cgrpp) */ __bpf_kfunc void bpf_cgroup_release(struct cgroup *cgrp) { - if (!cgrp) - return; - cgroup_put(cgrp); } @@ -2200,7 +2103,7 @@ __bpf_kfunc struct task_struct *bpf_task_from_pid(s32 pid) rcu_read_lock(); p = find_task_by_pid_ns(pid, &init_pid_ns); if (p) - bpf_task_acquire(p); + p = bpf_task_acquire(p); rcu_read_unlock(); return p; @@ -2372,17 +2275,14 @@ BTF_ID_FLAGS(func, bpf_list_push_front) BTF_ID_FLAGS(func, bpf_list_push_back) BTF_ID_FLAGS(func, bpf_list_pop_front, KF_ACQUIRE | KF_RET_NULL) BTF_ID_FLAGS(func, bpf_list_pop_back, KF_ACQUIRE | KF_RET_NULL) -BTF_ID_FLAGS(func, bpf_task_acquire, KF_ACQUIRE | KF_TRUSTED_ARGS) -BTF_ID_FLAGS(func, bpf_task_acquire_not_zero, KF_ACQUIRE | KF_RCU | KF_RET_NULL) -BTF_ID_FLAGS(func, bpf_task_kptr_get, KF_ACQUIRE | KF_KPTR_GET | KF_RET_NULL) +BTF_ID_FLAGS(func, bpf_task_acquire, KF_ACQUIRE | KF_RCU | KF_RET_NULL) BTF_ID_FLAGS(func, bpf_task_release, KF_RELEASE) BTF_ID_FLAGS(func, bpf_rbtree_remove, KF_ACQUIRE) BTF_ID_FLAGS(func, bpf_rbtree_add) BTF_ID_FLAGS(func, bpf_rbtree_first, KF_RET_NULL) #ifdef CONFIG_CGROUPS -BTF_ID_FLAGS(func, bpf_cgroup_acquire, KF_ACQUIRE | KF_TRUSTED_ARGS) -BTF_ID_FLAGS(func, bpf_cgroup_kptr_get, KF_ACQUIRE | KF_KPTR_GET | KF_RET_NULL) +BTF_ID_FLAGS(func, bpf_cgroup_acquire, KF_ACQUIRE | KF_RCU | KF_RET_NULL) BTF_ID_FLAGS(func, bpf_cgroup_release, KF_RELEASE) BTF_ID_FLAGS(func, bpf_cgroup_ancestor, KF_ACQUIRE | KF_RCU | KF_RET_NULL) BTF_ID_FLAGS(func, bpf_cgroup_from_id, KF_ACQUIRE | KF_RET_NULL) @@ -2411,6 +2311,9 @@ BTF_ID_FLAGS(func, bpf_rcu_read_lock) BTF_ID_FLAGS(func, bpf_rcu_read_unlock) BTF_ID_FLAGS(func, bpf_dynptr_slice, KF_RET_NULL) BTF_ID_FLAGS(func, bpf_dynptr_slice_rdwr, KF_RET_NULL) +BTF_ID_FLAGS(func, bpf_iter_num_new, KF_ITER_NEW) +BTF_ID_FLAGS(func, bpf_iter_num_next, KF_ITER_NEXT | KF_RET_NULL) +BTF_ID_FLAGS(func, bpf_iter_num_destroy, KF_ITER_DESTROY) BTF_SET8_END(common_btf_ids) static const struct btf_kfunc_id_set common_kfunc_set = { diff --git a/kernel/bpf/local_storage.c b/kernel/bpf/local_storage.c index a993560f200a..4c7bbec4a9e4 100644 --- a/kernel/bpf/local_storage.c +++ b/kernel/bpf/local_storage.c @@ -141,8 +141,8 @@ static void *cgroup_storage_lookup_elem(struct bpf_map *_map, void *key) return &READ_ONCE(storage->buf)->data[0]; } -static int cgroup_storage_update_elem(struct bpf_map *map, void *key, - void *value, u64 flags) +static long cgroup_storage_update_elem(struct bpf_map *map, void *key, + void *value, u64 flags) { struct bpf_cgroup_storage *storage; struct bpf_storage_buffer *new; @@ -348,7 +348,7 @@ static void cgroup_storage_map_free(struct bpf_map *_map) bpf_map_area_free(map); } -static int cgroup_storage_delete_elem(struct bpf_map *map, void *key) +static long cgroup_storage_delete_elem(struct bpf_map *map, void *key) { return -EINVAL; } diff --git a/kernel/bpf/log.c b/kernel/bpf/log.c new file mode 100644 index 000000000000..046ddff37a76 --- /dev/null +++ b/kernel/bpf/log.c @@ -0,0 +1,330 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com + * Copyright (c) 2016 Facebook + * Copyright (c) 2018 Covalent IO, Inc. http://covalent.io + */ +#include <uapi/linux/btf.h> +#include <linux/kernel.h> +#include <linux/types.h> +#include <linux/bpf.h> +#include <linux/bpf_verifier.h> +#include <linux/math64.h> + +static bool bpf_verifier_log_attr_valid(const struct bpf_verifier_log *log) +{ + /* ubuf and len_total should both be specified (or not) together */ + if (!!log->ubuf != !!log->len_total) + return false; + /* log buf without log_level is meaningless */ + if (log->ubuf && log->level == 0) + return false; + if (log->level & ~BPF_LOG_MASK) + return false; + if (log->len_total > UINT_MAX >> 2) + return false; + return true; +} + +int bpf_vlog_init(struct bpf_verifier_log *log, u32 log_level, + char __user *log_buf, u32 log_size) +{ + log->level = log_level; + log->ubuf = log_buf; + log->len_total = log_size; + + /* log attributes have to be sane */ + if (!bpf_verifier_log_attr_valid(log)) + return -EINVAL; + + return 0; +} + +static void bpf_vlog_update_len_max(struct bpf_verifier_log *log, u32 add_len) +{ + /* add_len includes terminal \0, so no need for +1. */ + u64 len = log->end_pos + add_len; + + /* log->len_max could be larger than our current len due to + * bpf_vlog_reset() calls, so we maintain the max of any length at any + * previous point + */ + if (len > UINT_MAX) + log->len_max = UINT_MAX; + else if (len > log->len_max) + log->len_max = len; +} + +void bpf_verifier_vlog(struct bpf_verifier_log *log, const char *fmt, + va_list args) +{ + u64 cur_pos; + u32 new_n, n; + + n = vscnprintf(log->kbuf, BPF_VERIFIER_TMP_LOG_SIZE, fmt, args); + + WARN_ONCE(n >= BPF_VERIFIER_TMP_LOG_SIZE - 1, + "verifier log line truncated - local buffer too short\n"); + + if (log->level == BPF_LOG_KERNEL) { + bool newline = n > 0 && log->kbuf[n - 1] == '\n'; + + pr_err("BPF: %s%s", log->kbuf, newline ? "" : "\n"); + return; + } + + n += 1; /* include terminating zero */ + bpf_vlog_update_len_max(log, n); + + if (log->level & BPF_LOG_FIXED) { + /* check if we have at least something to put into user buf */ + new_n = 0; + if (log->end_pos < log->len_total) { + new_n = min_t(u32, log->len_total - log->end_pos, n); + log->kbuf[new_n - 1] = '\0'; + } + + cur_pos = log->end_pos; + log->end_pos += n - 1; /* don't count terminating '\0' */ + + if (log->ubuf && new_n && + copy_to_user(log->ubuf + cur_pos, log->kbuf, new_n)) + goto fail; + } else { + u64 new_end, new_start; + u32 buf_start, buf_end, new_n; + + new_end = log->end_pos + n; + if (new_end - log->start_pos >= log->len_total) + new_start = new_end - log->len_total; + else + new_start = log->start_pos; + + log->start_pos = new_start; + log->end_pos = new_end - 1; /* don't count terminating '\0' */ + + if (!log->ubuf) + return; + + new_n = min(n, log->len_total); + cur_pos = new_end - new_n; + div_u64_rem(cur_pos, log->len_total, &buf_start); + div_u64_rem(new_end, log->len_total, &buf_end); + /* new_end and buf_end are exclusive indices, so if buf_end is + * exactly zero, then it actually points right to the end of + * ubuf and there is no wrap around + */ + if (buf_end == 0) + buf_end = log->len_total; + + /* if buf_start > buf_end, we wrapped around; + * if buf_start == buf_end, then we fill ubuf completely; we + * can't have buf_start == buf_end to mean that there is + * nothing to write, because we always write at least + * something, even if terminal '\0' + */ + if (buf_start < buf_end) { + /* message fits within contiguous chunk of ubuf */ + if (copy_to_user(log->ubuf + buf_start, + log->kbuf + n - new_n, + buf_end - buf_start)) + goto fail; + } else { + /* message wraps around the end of ubuf, copy in two chunks */ + if (copy_to_user(log->ubuf + buf_start, + log->kbuf + n - new_n, + log->len_total - buf_start)) + goto fail; + if (copy_to_user(log->ubuf, + log->kbuf + n - buf_end, + buf_end)) + goto fail; + } + } + + return; +fail: + log->ubuf = NULL; +} + +void bpf_vlog_reset(struct bpf_verifier_log *log, u64 new_pos) +{ + char zero = 0; + u32 pos; + + if (WARN_ON_ONCE(new_pos > log->end_pos)) + return; + + if (!bpf_verifier_log_needed(log) || log->level == BPF_LOG_KERNEL) + return; + + /* if position to which we reset is beyond current log window, + * then we didn't preserve any useful content and should adjust + * start_pos to end up with an empty log (start_pos == end_pos) + */ + log->end_pos = new_pos; + if (log->end_pos < log->start_pos) + log->start_pos = log->end_pos; + + if (!log->ubuf) + return; + + if (log->level & BPF_LOG_FIXED) + pos = log->end_pos + 1; + else + div_u64_rem(new_pos, log->len_total, &pos); + + if (pos < log->len_total && put_user(zero, log->ubuf + pos)) + log->ubuf = NULL; +} + +static void bpf_vlog_reverse_kbuf(char *buf, int len) +{ + int i, j; + + for (i = 0, j = len - 1; i < j; i++, j--) + swap(buf[i], buf[j]); +} + +static int bpf_vlog_reverse_ubuf(struct bpf_verifier_log *log, int start, int end) +{ + /* we split log->kbuf into two equal parts for both ends of array */ + int n = sizeof(log->kbuf) / 2, nn; + char *lbuf = log->kbuf, *rbuf = log->kbuf + n; + + /* Read ubuf's section [start, end) two chunks at a time, from left + * and right side; within each chunk, swap all the bytes; after that + * reverse the order of lbuf and rbuf and write result back to ubuf. + * This way we'll end up with swapped contents of specified + * [start, end) ubuf segment. + */ + while (end - start > 1) { + nn = min(n, (end - start ) / 2); + + if (copy_from_user(lbuf, log->ubuf + start, nn)) + return -EFAULT; + if (copy_from_user(rbuf, log->ubuf + end - nn, nn)) + return -EFAULT; + + bpf_vlog_reverse_kbuf(lbuf, nn); + bpf_vlog_reverse_kbuf(rbuf, nn); + + /* we write lbuf to the right end of ubuf, while rbuf to the + * left one to end up with properly reversed overall ubuf + */ + if (copy_to_user(log->ubuf + start, rbuf, nn)) + return -EFAULT; + if (copy_to_user(log->ubuf + end - nn, lbuf, nn)) + return -EFAULT; + + start += nn; + end -= nn; + } + + return 0; +} + +int bpf_vlog_finalize(struct bpf_verifier_log *log, u32 *log_size_actual) +{ + u32 sublen; + int err; + + *log_size_actual = 0; + if (!log || log->level == 0 || log->level == BPF_LOG_KERNEL) + return 0; + + if (!log->ubuf) + goto skip_log_rotate; + /* If we never truncated log, there is nothing to move around. */ + if (log->start_pos == 0) + goto skip_log_rotate; + + /* Otherwise we need to rotate log contents to make it start from the + * buffer beginning and be a continuous zero-terminated string. Note + * that if log->start_pos != 0 then we definitely filled up entire log + * buffer with no gaps, and we just need to shift buffer contents to + * the left by (log->start_pos % log->len_total) bytes. + * + * Unfortunately, user buffer could be huge and we don't want to + * allocate temporary kernel memory of the same size just to shift + * contents in a straightforward fashion. Instead, we'll be clever and + * do in-place array rotation. This is a leetcode-style problem, which + * could be solved by three rotations. + * + * Let's say we have log buffer that has to be shifted left by 7 bytes + * (spaces and vertical bar is just for demonstrative purposes): + * E F G H I J K | A B C D + * + * First, we reverse entire array: + * D C B A | K J I H G F E + * + * Then we rotate first 4 bytes (DCBA) and separately last 7 bytes + * (KJIHGFE), resulting in a properly rotated array: + * A B C D | E F G H I J K + * + * We'll utilize log->kbuf to read user memory chunk by chunk, swap + * bytes, and write them back. Doing it byte-by-byte would be + * unnecessarily inefficient. Altogether we are going to read and + * write each byte twice, for total 4 memory copies between kernel and + * user space. + */ + + /* length of the chopped off part that will be the beginning; + * len(ABCD) in the example above + */ + div_u64_rem(log->start_pos, log->len_total, &sublen); + sublen = log->len_total - sublen; + + err = bpf_vlog_reverse_ubuf(log, 0, log->len_total); + err = err ?: bpf_vlog_reverse_ubuf(log, 0, sublen); + err = err ?: bpf_vlog_reverse_ubuf(log, sublen, log->len_total); + if (err) + log->ubuf = NULL; + +skip_log_rotate: + *log_size_actual = log->len_max; + + /* properly initialized log has either both ubuf!=NULL and len_total>0 + * or ubuf==NULL and len_total==0, so if this condition doesn't hold, + * we got a fault somewhere along the way, so report it back + */ + if (!!log->ubuf != !!log->len_total) + return -EFAULT; + + /* did truncation actually happen? */ + if (log->ubuf && log->len_max > log->len_total) + return -ENOSPC; + + return 0; +} + +/* log_level controls verbosity level of eBPF verifier. + * bpf_verifier_log_write() is used to dump the verification trace to the log, + * so the user can figure out what's wrong with the program + */ +__printf(2, 3) void bpf_verifier_log_write(struct bpf_verifier_env *env, + const char *fmt, ...) +{ + va_list args; + + if (!bpf_verifier_log_needed(&env->log)) + return; + + va_start(args, fmt); + bpf_verifier_vlog(&env->log, fmt, args); + va_end(args); +} +EXPORT_SYMBOL_GPL(bpf_verifier_log_write); + +__printf(2, 3) void bpf_log(struct bpf_verifier_log *log, + const char *fmt, ...) +{ + va_list args; + + if (!bpf_verifier_log_needed(log)) + return; + + va_start(args, fmt); + bpf_verifier_vlog(log, fmt, args); + va_end(args); +} +EXPORT_SYMBOL_GPL(bpf_log); diff --git a/kernel/bpf/lpm_trie.c b/kernel/bpf/lpm_trie.c index dc23f2ac9cde..e0d3ddf2037a 100644 --- a/kernel/bpf/lpm_trie.c +++ b/kernel/bpf/lpm_trie.c @@ -300,8 +300,8 @@ static struct lpm_trie_node *lpm_trie_node_alloc(const struct lpm_trie *trie, } /* Called from syscall or from eBPF program */ -static int trie_update_elem(struct bpf_map *map, - void *_key, void *value, u64 flags) +static long trie_update_elem(struct bpf_map *map, + void *_key, void *value, u64 flags) { struct lpm_trie *trie = container_of(map, struct lpm_trie, map); struct lpm_trie_node *node, *im_node = NULL, *new_node = NULL; @@ -431,7 +431,7 @@ out: } /* Called from syscall or from eBPF program */ -static int trie_delete_elem(struct bpf_map *map, void *_key) +static long trie_delete_elem(struct bpf_map *map, void *_key) { struct lpm_trie *trie = container_of(map, struct lpm_trie, map); struct bpf_lpm_trie_key *key = _key; diff --git a/kernel/bpf/memalloc.c b/kernel/bpf/memalloc.c index 5fcdacbb8439..410637c225fb 100644 --- a/kernel/bpf/memalloc.c +++ b/kernel/bpf/memalloc.c @@ -121,15 +121,8 @@ static struct llist_node notrace *__llist_del_first(struct llist_head *head) return entry; } -static void *__alloc(struct bpf_mem_cache *c, int node) +static void *__alloc(struct bpf_mem_cache *c, int node, gfp_t flags) { - /* Allocate, but don't deplete atomic reserves that typical - * GFP_ATOMIC would do. irq_work runs on this cpu and kmalloc - * will allocate from the current numa node which is what we - * want here. - */ - gfp_t flags = GFP_NOWAIT | __GFP_NOWARN | __GFP_ACCOUNT; - if (c->percpu_size) { void **obj = kmalloc_node(c->percpu_size, flags, node); void *pptr = __alloc_percpu_gfp(c->unit_size, 8, flags); @@ -185,7 +178,12 @@ static void alloc_bulk(struct bpf_mem_cache *c, int cnt, int node) */ obj = __llist_del_first(&c->free_by_rcu); if (!obj) { - obj = __alloc(c, node); + /* Allocate, but don't deplete atomic reserves that typical + * GFP_ATOMIC would do. irq_work runs on this cpu and kmalloc + * will allocate from the current numa node which is what we + * want here. + */ + obj = __alloc(c, node, GFP_NOWAIT | __GFP_NOWARN | __GFP_ACCOUNT); if (!obj) break; } @@ -676,3 +674,46 @@ void notrace bpf_mem_cache_free(struct bpf_mem_alloc *ma, void *ptr) unit_free(this_cpu_ptr(ma->cache), ptr); } + +/* Directly does a kfree() without putting 'ptr' back to the free_llist + * for reuse and without waiting for a rcu_tasks_trace gp. + * The caller must first go through the rcu_tasks_trace gp for 'ptr' + * before calling bpf_mem_cache_raw_free(). + * It could be used when the rcu_tasks_trace callback does not have + * a hold on the original bpf_mem_alloc object that allocated the + * 'ptr'. This should only be used in the uncommon code path. + * Otherwise, the bpf_mem_alloc's free_llist cannot be refilled + * and may affect performance. + */ +void bpf_mem_cache_raw_free(void *ptr) +{ + if (!ptr) + return; + + kfree(ptr - LLIST_NODE_SZ); +} + +/* When flags == GFP_KERNEL, it signals that the caller will not cause + * deadlock when using kmalloc. bpf_mem_cache_alloc_flags() will use + * kmalloc if the free_llist is empty. + */ +void notrace *bpf_mem_cache_alloc_flags(struct bpf_mem_alloc *ma, gfp_t flags) +{ + struct bpf_mem_cache *c; + void *ret; + + c = this_cpu_ptr(ma->cache); + + ret = unit_alloc(c); + if (!ret && flags == GFP_KERNEL) { + struct mem_cgroup *memcg, *old_memcg; + + memcg = get_memcg(c); + old_memcg = set_active_memcg(memcg); + ret = __alloc(c, NUMA_NO_NODE, GFP_KERNEL | __GFP_NOWARN | __GFP_ACCOUNT); + set_active_memcg(old_memcg); + mem_cgroup_put(memcg); + } + + return !ret ? NULL : ret + LLIST_NODE_SZ; +} diff --git a/kernel/bpf/queue_stack_maps.c b/kernel/bpf/queue_stack_maps.c index 63ecbbcb349d..601609164ef3 100644 --- a/kernel/bpf/queue_stack_maps.c +++ b/kernel/bpf/queue_stack_maps.c @@ -95,7 +95,7 @@ static void queue_stack_map_free(struct bpf_map *map) bpf_map_area_free(qs); } -static int __queue_map_get(struct bpf_map *map, void *value, bool delete) +static long __queue_map_get(struct bpf_map *map, void *value, bool delete) { struct bpf_queue_stack *qs = bpf_queue_stack(map); unsigned long flags; @@ -124,7 +124,7 @@ out: } -static int __stack_map_get(struct bpf_map *map, void *value, bool delete) +static long __stack_map_get(struct bpf_map *map, void *value, bool delete) { struct bpf_queue_stack *qs = bpf_queue_stack(map); unsigned long flags; @@ -156,32 +156,32 @@ out: } /* Called from syscall or from eBPF program */ -static int queue_map_peek_elem(struct bpf_map *map, void *value) +static long queue_map_peek_elem(struct bpf_map *map, void *value) { return __queue_map_get(map, value, false); } /* Called from syscall or from eBPF program */ -static int stack_map_peek_elem(struct bpf_map *map, void *value) +static long stack_map_peek_elem(struct bpf_map *map, void *value) { return __stack_map_get(map, value, false); } /* Called from syscall or from eBPF program */ -static int queue_map_pop_elem(struct bpf_map *map, void *value) +static long queue_map_pop_elem(struct bpf_map *map, void *value) { return __queue_map_get(map, value, true); } /* Called from syscall or from eBPF program */ -static int stack_map_pop_elem(struct bpf_map *map, void *value) +static long stack_map_pop_elem(struct bpf_map *map, void *value) { return __stack_map_get(map, value, true); } /* Called from syscall or from eBPF program */ -static int queue_stack_map_push_elem(struct bpf_map *map, void *value, - u64 flags) +static long queue_stack_map_push_elem(struct bpf_map *map, void *value, + u64 flags) { struct bpf_queue_stack *qs = bpf_queue_stack(map); unsigned long irq_flags; @@ -227,14 +227,14 @@ static void *queue_stack_map_lookup_elem(struct bpf_map *map, void *key) } /* Called from syscall or from eBPF program */ -static int queue_stack_map_update_elem(struct bpf_map *map, void *key, - void *value, u64 flags) +static long queue_stack_map_update_elem(struct bpf_map *map, void *key, + void *value, u64 flags) { return -EINVAL; } /* Called from syscall or from eBPF program */ -static int queue_stack_map_delete_elem(struct bpf_map *map, void *key) +static long queue_stack_map_delete_elem(struct bpf_map *map, void *key) { return -EINVAL; } diff --git a/kernel/bpf/reuseport_array.c b/kernel/bpf/reuseport_array.c index 71cb72f5b733..cbf2d8d784b8 100644 --- a/kernel/bpf/reuseport_array.c +++ b/kernel/bpf/reuseport_array.c @@ -59,7 +59,7 @@ static void *reuseport_array_lookup_elem(struct bpf_map *map, void *key) } /* Called from syscall only */ -static int reuseport_array_delete_elem(struct bpf_map *map, void *key) +static long reuseport_array_delete_elem(struct bpf_map *map, void *key) { struct reuseport_array *array = reuseport_array(map); u32 index = *(u32 *)key; diff --git a/kernel/bpf/ringbuf.c b/kernel/bpf/ringbuf.c index 0d2a45ff83f1..875ac9b698d9 100644 --- a/kernel/bpf/ringbuf.c +++ b/kernel/bpf/ringbuf.c @@ -242,13 +242,13 @@ static void *ringbuf_map_lookup_elem(struct bpf_map *map, void *key) return ERR_PTR(-ENOTSUPP); } -static int ringbuf_map_update_elem(struct bpf_map *map, void *key, void *value, - u64 flags) +static long ringbuf_map_update_elem(struct bpf_map *map, void *key, void *value, + u64 flags) { return -ENOTSUPP; } -static int ringbuf_map_delete_elem(struct bpf_map *map, void *key) +static long ringbuf_map_delete_elem(struct bpf_map *map, void *key) { return -ENOTSUPP; } diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c index 0f1d8dced933..b25fce425b2c 100644 --- a/kernel/bpf/stackmap.c +++ b/kernel/bpf/stackmap.c @@ -618,14 +618,14 @@ static int stack_map_get_next_key(struct bpf_map *map, void *key, return 0; } -static int stack_map_update_elem(struct bpf_map *map, void *key, void *value, - u64 map_flags) +static long stack_map_update_elem(struct bpf_map *map, void *key, void *value, + u64 map_flags) { return -EINVAL; } /* Called from syscall or from eBPF program */ -static int stack_map_delete_elem(struct bpf_map *map, void *key) +static long stack_map_delete_elem(struct bpf_map *map, void *key) { struct bpf_stack_map *smap = container_of(map, struct bpf_stack_map, map); struct stack_map_bucket *old_bucket; diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index f406dfa13792..6d575505f89c 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -520,14 +520,14 @@ static int btf_field_cmp(const void *a, const void *b) } struct btf_field *btf_record_find(const struct btf_record *rec, u32 offset, - enum btf_field_type type) + u32 field_mask) { struct btf_field *field; - if (IS_ERR_OR_NULL(rec) || !(rec->field_mask & type)) + if (IS_ERR_OR_NULL(rec) || !(rec->field_mask & field_mask)) return NULL; field = bsearch(&offset, rec->fields, rec->cnt, sizeof(rec->fields[0]), btf_field_cmp); - if (!field || !(field->type & type)) + if (!field || !(field->type & field_mask)) return NULL; return field; } @@ -650,6 +650,8 @@ void bpf_obj_free_timer(const struct btf_record *rec, void *obj) bpf_timer_cancel_and_free(obj + rec->timer_off); } +extern void __bpf_obj_drop_impl(void *p, const struct btf_record *rec); + void bpf_obj_free_fields(const struct btf_record *rec, void *obj) { const struct btf_field *fields; @@ -659,8 +661,10 @@ void bpf_obj_free_fields(const struct btf_record *rec, void *obj) return; fields = rec->fields; for (i = 0; i < rec->cnt; i++) { + struct btf_struct_meta *pointee_struct_meta; const struct btf_field *field = &fields[i]; void *field_ptr = obj + field->offset; + void *xchgd_field; switch (fields[i].type) { case BPF_SPIN_LOCK: @@ -672,7 +676,22 @@ void bpf_obj_free_fields(const struct btf_record *rec, void *obj) WRITE_ONCE(*(u64 *)field_ptr, 0); break; case BPF_KPTR_REF: - field->kptr.dtor((void *)xchg((unsigned long *)field_ptr, 0)); + xchgd_field = (void *)xchg((unsigned long *)field_ptr, 0); + if (!xchgd_field) + break; + + if (!btf_is_kernel(field->kptr.btf)) { + pointee_struct_meta = btf_find_struct_meta(field->kptr.btf, + field->kptr.btf_id); + WARN_ON_ONCE(!pointee_struct_meta); + migrate_disable(); + __bpf_obj_drop_impl(xchgd_field, pointee_struct_meta ? + pointee_struct_meta->record : + NULL); + migrate_enable(); + } else { + field->kptr.dtor(xchgd_field); + } break; case BPF_LIST_HEAD: if (WARN_ON_ONCE(rec->spin_lock_off < 0)) @@ -1287,8 +1306,10 @@ struct bpf_map *bpf_map_get_with_uref(u32 ufd) return map; } -/* map_idr_lock should have been held */ -static struct bpf_map *__bpf_map_inc_not_zero(struct bpf_map *map, bool uref) +/* map_idr_lock should have been held or the map should have been + * protected by rcu read lock. + */ +struct bpf_map *__bpf_map_inc_not_zero(struct bpf_map *map, bool uref) { int refold; @@ -2051,6 +2072,7 @@ static void __bpf_prog_put_noref(struct bpf_prog *prog, bool deferred) { bpf_prog_kallsyms_del_all(prog); btf_put(prog->aux->btf); + module_put(prog->aux->mod); kvfree(prog->aux->jited_linfo); kvfree(prog->aux->linfo); kfree(prog->aux->kfunc_tab); @@ -2479,9 +2501,9 @@ static bool is_perfmon_prog_type(enum bpf_prog_type prog_type) } /* last field in 'union bpf_attr' used by this command */ -#define BPF_PROG_LOAD_LAST_FIELD core_relo_rec_size +#define BPF_PROG_LOAD_LAST_FIELD log_true_size -static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr) +static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size) { enum bpf_prog_type type = attr->prog_type; struct bpf_prog *prog, *dst_prog = NULL; @@ -2631,7 +2653,7 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr) goto free_prog_sec; /* run eBPF verifier */ - err = bpf_check(&prog, attr, uattr); + err = bpf_check(&prog, attr, uattr, uattr_size); if (err < 0) goto free_used_maps; @@ -2806,16 +2828,19 @@ static void bpf_link_show_fdinfo(struct seq_file *m, struct file *filp) const struct bpf_prog *prog = link->prog; char prog_tag[sizeof(prog->tag) * 2 + 1] = { }; - bin2hex(prog_tag, prog->tag, sizeof(prog->tag)); seq_printf(m, "link_type:\t%s\n" - "link_id:\t%u\n" - "prog_tag:\t%s\n" - "prog_id:\t%u\n", + "link_id:\t%u\n", bpf_link_type_strs[link->type], - link->id, - prog_tag, - prog->aux->id); + link->id); + if (prog) { + bin2hex(prog_tag, prog->tag, sizeof(prog->tag)); + seq_printf(m, + "prog_tag:\t%s\n" + "prog_id:\t%u\n", + prog_tag, + prog->aux->id); + } if (link->ops->show_fdinfo) link->ops->show_fdinfo(link, m); } @@ -3097,6 +3122,11 @@ static int bpf_tracing_prog_attach(struct bpf_prog *prog, if (err) goto out_unlock; + if (tgt_info.tgt_mod) { + module_put(prog->aux->mod); + prog->aux->mod = tgt_info.tgt_mod; + } + tr = bpf_trampoline_get(key, &tgt_info); if (!tr) { err = -ENOMEM; @@ -4290,7 +4320,8 @@ static int bpf_link_get_info_by_fd(struct file *file, info.type = link->type; info.id = link->id; - info.prog_id = link->prog->aux->id; + if (link->prog) + info.prog_id = link->prog->aux->id; if (link->ops->fill_link_info) { err = link->ops->fill_link_info(link, &info); @@ -4340,9 +4371,9 @@ static int bpf_obj_get_info_by_fd(const union bpf_attr *attr, return err; } -#define BPF_BTF_LOAD_LAST_FIELD btf_log_level +#define BPF_BTF_LOAD_LAST_FIELD btf_log_true_size -static int bpf_btf_load(const union bpf_attr *attr, bpfptr_t uattr) +static int bpf_btf_load(const union bpf_attr *attr, bpfptr_t uattr, __u32 uattr_size) { if (CHECK_ATTR(BPF_BTF_LOAD)) return -EINVAL; @@ -4350,7 +4381,7 @@ static int bpf_btf_load(const union bpf_attr *attr, bpfptr_t uattr) if (!bpf_capable()) return -EPERM; - return btf_new_fd(attr, uattr); + return btf_new_fd(attr, uattr, uattr_size); } #define BPF_BTF_GET_FD_BY_ID_LAST_FIELD btf_id @@ -4553,6 +4584,9 @@ static int link_create(union bpf_attr *attr, bpfptr_t uattr) if (CHECK_ATTR(BPF_LINK_CREATE)) return -EINVAL; + if (attr->link_create.attach_type == BPF_STRUCT_OPS) + return bpf_struct_ops_link_create(attr); + prog = bpf_prog_get(attr->link_create.prog_fd); if (IS_ERR(prog)) return PTR_ERR(prog); @@ -4651,6 +4685,35 @@ out: return ret; } +static int link_update_map(struct bpf_link *link, union bpf_attr *attr) +{ + struct bpf_map *new_map, *old_map = NULL; + int ret; + + new_map = bpf_map_get(attr->link_update.new_map_fd); + if (IS_ERR(new_map)) + return PTR_ERR(new_map); + + if (attr->link_update.flags & BPF_F_REPLACE) { + old_map = bpf_map_get(attr->link_update.old_map_fd); + if (IS_ERR(old_map)) { + ret = PTR_ERR(old_map); + goto out_put; + } + } else if (attr->link_update.old_map_fd) { + ret = -EINVAL; + goto out_put; + } + + ret = link->ops->update_map(link, new_map, old_map); + + if (old_map) + bpf_map_put(old_map); +out_put: + bpf_map_put(new_map); + return ret; +} + #define BPF_LINK_UPDATE_LAST_FIELD link_update.old_prog_fd static int link_update(union bpf_attr *attr) @@ -4671,6 +4734,11 @@ static int link_update(union bpf_attr *attr) if (IS_ERR(link)) return PTR_ERR(link); + if (link->ops->update_map) { + ret = link_update_map(link, attr); + goto out_put_link; + } + new_prog = bpf_prog_get(attr->link_update.new_prog_fd); if (IS_ERR(new_prog)) { ret = PTR_ERR(new_prog); @@ -4991,7 +5059,7 @@ static int __sys_bpf(int cmd, bpfptr_t uattr, unsigned int size) err = map_freeze(&attr); break; case BPF_PROG_LOAD: - err = bpf_prog_load(&attr, uattr); + err = bpf_prog_load(&attr, uattr, size); break; case BPF_OBJ_PIN: err = bpf_obj_pin(&attr); @@ -5036,7 +5104,7 @@ static int __sys_bpf(int cmd, bpfptr_t uattr, unsigned int size) err = bpf_raw_tracepoint_open(&attr); break; case BPF_BTF_LOAD: - err = bpf_btf_load(&attr, uattr); + err = bpf_btf_load(&attr, uattr, size); break; case BPF_BTF_GET_FD_BY_ID: err = bpf_btf_get_fd_by_id(&attr); diff --git a/kernel/bpf/trampoline.c b/kernel/bpf/trampoline.c index d0ed7d6f5eec..f61d5138b12b 100644 --- a/kernel/bpf/trampoline.c +++ b/kernel/bpf/trampoline.c @@ -9,7 +9,6 @@ #include <linux/btf.h> #include <linux/rcupdate_trace.h> #include <linux/rcupdate_wait.h> -#include <linux/module.h> #include <linux/static_call.h> #include <linux/bpf_verifier.h> #include <linux/bpf_lsm.h> @@ -172,26 +171,6 @@ out: return tr; } -static int bpf_trampoline_module_get(struct bpf_trampoline *tr) -{ - struct module *mod; - int err = 0; - - preempt_disable(); - mod = __module_text_address((unsigned long) tr->func.addr); - if (mod && !try_module_get(mod)) - err = -ENOENT; - preempt_enable(); - tr->mod = mod; - return err; -} - -static void bpf_trampoline_module_put(struct bpf_trampoline *tr) -{ - module_put(tr->mod); - tr->mod = NULL; -} - static int unregister_fentry(struct bpf_trampoline *tr, void *old_addr) { void *ip = tr->func.addr; @@ -202,8 +181,6 @@ static int unregister_fentry(struct bpf_trampoline *tr, void *old_addr) else ret = bpf_arch_text_poke(ip, BPF_MOD_CALL, old_addr, NULL); - if (!ret) - bpf_trampoline_module_put(tr); return ret; } @@ -238,9 +215,6 @@ static int register_fentry(struct bpf_trampoline *tr, void *new_addr) tr->func.ftrace_managed = true; } - if (bpf_trampoline_module_get(tr)) - return -ENOENT; - if (tr->func.ftrace_managed) { ftrace_set_filter_ip(tr->fops, (unsigned long)ip, 0, 1); ret = register_ftrace_direct_multi(tr->fops, (long)new_addr); @@ -248,8 +222,6 @@ static int register_fentry(struct bpf_trampoline *tr, void *new_addr) ret = bpf_arch_text_poke(ip, BPF_MOD_CALL, NULL, new_addr); } - if (ret) - bpf_trampoline_module_put(tr); return ret; } diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index b2116ca78d9a..d6db6de3e9ea 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -24,6 +24,7 @@ #include <linux/bpf_lsm.h> #include <linux/btf_ids.h> #include <linux/poison.h> +#include <linux/module.h> #include "disasm.h" @@ -302,6 +303,10 @@ struct bpf_kfunc_call_arg_meta { enum bpf_dynptr_type type; u32 id; } initialized_dynptr; + struct { + u8 spi; + u8 frameno; + } iter; u64 mem_size; }; @@ -330,61 +335,6 @@ find_linfo(const struct bpf_verifier_env *env, u32 insn_off) return &linfo[i - 1]; } -void bpf_verifier_vlog(struct bpf_verifier_log *log, const char *fmt, - va_list args) -{ - unsigned int n; - - n = vscnprintf(log->kbuf, BPF_VERIFIER_TMP_LOG_SIZE, fmt, args); - - WARN_ONCE(n >= BPF_VERIFIER_TMP_LOG_SIZE - 1, - "verifier log line truncated - local buffer too short\n"); - - if (log->level == BPF_LOG_KERNEL) { - bool newline = n > 0 && log->kbuf[n - 1] == '\n'; - - pr_err("BPF: %s%s", log->kbuf, newline ? "" : "\n"); - return; - } - - n = min(log->len_total - log->len_used - 1, n); - log->kbuf[n] = '\0'; - if (!copy_to_user(log->ubuf + log->len_used, log->kbuf, n + 1)) - log->len_used += n; - else - log->ubuf = NULL; -} - -static void bpf_vlog_reset(struct bpf_verifier_log *log, u32 new_pos) -{ - char zero = 0; - - if (!bpf_verifier_log_needed(log)) - return; - - log->len_used = new_pos; - if (put_user(zero, log->ubuf + new_pos)) - log->ubuf = NULL; -} - -/* log_level controls verbosity level of eBPF verifier. - * bpf_verifier_log_write() is used to dump the verification trace to the log, - * so the user can figure out what's wrong with the program - */ -__printf(2, 3) void bpf_verifier_log_write(struct bpf_verifier_env *env, - const char *fmt, ...) -{ - va_list args; - - if (!bpf_verifier_log_needed(&env->log)) - return; - - va_start(args, fmt); - bpf_verifier_vlog(&env->log, fmt, args); - va_end(args); -} -EXPORT_SYMBOL_GPL(bpf_verifier_log_write); - __printf(2, 3) static void verbose(void *private_data, const char *fmt, ...) { struct bpf_verifier_env *env = private_data; @@ -398,20 +348,6 @@ __printf(2, 3) static void verbose(void *private_data, const char *fmt, ...) va_end(args); } -__printf(2, 3) void bpf_log(struct bpf_verifier_log *log, - const char *fmt, ...) -{ - va_list args; - - if (!bpf_verifier_log_needed(log)) - return; - - va_start(args, fmt); - bpf_verifier_vlog(log, fmt, args); - va_end(args); -} -EXPORT_SYMBOL_GPL(bpf_log); - static const char *ltrim(const char *s) { while (isspace(*s)) @@ -481,8 +417,17 @@ static bool type_is_sk_pointer(enum bpf_reg_type type) type == PTR_TO_XDP_SOCK; } +static bool type_may_be_null(u32 type) +{ + return type & PTR_MAYBE_NULL; +} + static bool reg_type_not_null(enum bpf_reg_type type) { + if (type_may_be_null(type)) + return false; + + type = base_type(type); return type == PTR_TO_SOCKET || type == PTR_TO_TCP_SOCK || type == PTR_TO_MAP_VALUE || @@ -526,11 +471,6 @@ static bool type_is_rdonly_mem(u32 type) return type & MEM_RDONLY; } -static bool type_may_be_null(u32 type) -{ - return type & PTR_MAYBE_NULL; -} - static bool is_acquire_function(enum bpf_func_id func_id, const struct bpf_map *map) { @@ -668,6 +608,7 @@ static char slot_type_char[] = { [STACK_MISC] = 'm', [STACK_ZERO] = '0', [STACK_DYNPTR] = 'd', + [STACK_ITER] = 'i', }; static void print_liveness(struct bpf_verifier_env *env, @@ -742,7 +683,12 @@ static int dynptr_get_spi(struct bpf_verifier_env *env, struct bpf_reg_state *re return stack_slot_obj_get_spi(env, reg, "dynptr", BPF_DYNPTR_NR_SLOTS); } -static const char *kernel_type_name(const struct btf* btf, u32 id) +static int iter_get_spi(struct bpf_verifier_env *env, struct bpf_reg_state *reg, int nr_slots) +{ + return stack_slot_obj_get_spi(env, reg, "iter", nr_slots); +} + +static const char *btf_type_name(const struct btf *btf, u32 id) { return btf_name_by_offset(btf, btf_type_by_id(btf, id)->name_off); } @@ -766,6 +712,30 @@ static const char *dynptr_type_str(enum bpf_dynptr_type type) } } +static const char *iter_type_str(const struct btf *btf, u32 btf_id) +{ + if (!btf || btf_id == 0) + return "<invalid>"; + + /* we already validated that type is valid and has conforming name */ + return btf_type_name(btf, btf_id) + sizeof(ITER_PREFIX) - 1; +} + +static const char *iter_state_str(enum bpf_iter_state state) +{ + switch (state) { + case BPF_ITER_STATE_ACTIVE: + return "active"; + case BPF_ITER_STATE_DRAINED: + return "drained"; + case BPF_ITER_STATE_INVALID: + return "<invalid>"; + default: + WARN_ONCE(1, "unknown iter state %d\n", state); + return "<unknown>"; + } +} + static void mark_reg_scratched(struct bpf_verifier_env *env, u32 regno) { env->scratched_regs |= 1U << regno; @@ -1118,6 +1088,157 @@ static bool is_dynptr_type_expected(struct bpf_verifier_env *env, struct bpf_reg } } +static void __mark_reg_known_zero(struct bpf_reg_state *reg); + +static int mark_stack_slots_iter(struct bpf_verifier_env *env, + struct bpf_reg_state *reg, int insn_idx, + struct btf *btf, u32 btf_id, int nr_slots) +{ + struct bpf_func_state *state = func(env, reg); + int spi, i, j, id; + + spi = iter_get_spi(env, reg, nr_slots); + if (spi < 0) + return spi; + + id = acquire_reference_state(env, insn_idx); + if (id < 0) + return id; + + for (i = 0; i < nr_slots; i++) { + struct bpf_stack_state *slot = &state->stack[spi - i]; + struct bpf_reg_state *st = &slot->spilled_ptr; + + __mark_reg_known_zero(st); + st->type = PTR_TO_STACK; /* we don't have dedicated reg type */ + st->live |= REG_LIVE_WRITTEN; + st->ref_obj_id = i == 0 ? id : 0; + st->iter.btf = btf; + st->iter.btf_id = btf_id; + st->iter.state = BPF_ITER_STATE_ACTIVE; + st->iter.depth = 0; + + for (j = 0; j < BPF_REG_SIZE; j++) + slot->slot_type[j] = STACK_ITER; + + mark_stack_slot_scratched(env, spi - i); + } + + return 0; +} + +static int unmark_stack_slots_iter(struct bpf_verifier_env *env, + struct bpf_reg_state *reg, int nr_slots) +{ + struct bpf_func_state *state = func(env, reg); + int spi, i, j; + + spi = iter_get_spi(env, reg, nr_slots); + if (spi < 0) + return spi; + + for (i = 0; i < nr_slots; i++) { + struct bpf_stack_state *slot = &state->stack[spi - i]; + struct bpf_reg_state *st = &slot->spilled_ptr; + + if (i == 0) + WARN_ON_ONCE(release_reference(env, st->ref_obj_id)); + + __mark_reg_not_init(env, st); + + /* see unmark_stack_slots_dynptr() for why we need to set REG_LIVE_WRITTEN */ + st->live |= REG_LIVE_WRITTEN; + + for (j = 0; j < BPF_REG_SIZE; j++) + slot->slot_type[j] = STACK_INVALID; + + mark_stack_slot_scratched(env, spi - i); + } + + return 0; +} + +static bool is_iter_reg_valid_uninit(struct bpf_verifier_env *env, + struct bpf_reg_state *reg, int nr_slots) +{ + struct bpf_func_state *state = func(env, reg); + int spi, i, j; + + /* For -ERANGE (i.e. spi not falling into allocated stack slots), we + * will do check_mem_access to check and update stack bounds later, so + * return true for that case. + */ + spi = iter_get_spi(env, reg, nr_slots); + if (spi == -ERANGE) + return true; + if (spi < 0) + return false; + + for (i = 0; i < nr_slots; i++) { + struct bpf_stack_state *slot = &state->stack[spi - i]; + + for (j = 0; j < BPF_REG_SIZE; j++) + if (slot->slot_type[j] == STACK_ITER) + return false; + } + + return true; +} + +static bool is_iter_reg_valid_init(struct bpf_verifier_env *env, struct bpf_reg_state *reg, + struct btf *btf, u32 btf_id, int nr_slots) +{ + struct bpf_func_state *state = func(env, reg); + int spi, i, j; + + spi = iter_get_spi(env, reg, nr_slots); + if (spi < 0) + return false; + + for (i = 0; i < nr_slots; i++) { + struct bpf_stack_state *slot = &state->stack[spi - i]; + struct bpf_reg_state *st = &slot->spilled_ptr; + + /* only main (first) slot has ref_obj_id set */ + if (i == 0 && !st->ref_obj_id) + return false; + if (i != 0 && st->ref_obj_id) + return false; + if (st->iter.btf != btf || st->iter.btf_id != btf_id) + return false; + + for (j = 0; j < BPF_REG_SIZE; j++) + if (slot->slot_type[j] != STACK_ITER) + return false; + } + + return true; +} + +/* Check if given stack slot is "special": + * - spilled register state (STACK_SPILL); + * - dynptr state (STACK_DYNPTR); + * - iter state (STACK_ITER). + */ +static bool is_stack_slot_special(const struct bpf_stack_state *stack) +{ + enum bpf_stack_slot_type type = stack->slot_type[BPF_REG_SIZE - 1]; + + switch (type) { + case STACK_SPILL: + case STACK_DYNPTR: + case STACK_ITER: + return true; + case STACK_INVALID: + case STACK_MISC: + case STACK_ZERO: + return false; + default: + WARN_ONCE(1, "unknown stack slot type %d\n", type); + return true; + } +} + /* The reg state of a pointer or a bounded scalar was saved when * it was spilled to the stack. */ @@ -1164,7 +1285,7 @@ static void print_verifier_state(struct bpf_verifier_env *env, verbose(env, "%s", reg_type_str(env, t)); if (base_type(t) == PTR_TO_BTF_ID) - verbose(env, "%s", kernel_type_name(reg->btf, reg->btf_id)); + verbose(env, "%s", btf_type_name(reg->btf, reg->btf_id)); verbose(env, "("); /* * _a stands for append, was shortened to avoid multiline statements below. @@ -1267,6 +1388,19 @@ static void print_verifier_state(struct bpf_verifier_env *env, if (reg->ref_obj_id) verbose(env, "(ref_id=%d)", reg->ref_obj_id); break; + case STACK_ITER: + /* only main slot has ref_obj_id set; skip others */ + reg = &state->stack[i].spilled_ptr; + if (!reg->ref_obj_id) + continue; + + verbose(env, " fp%d", (-i - 1) * BPF_REG_SIZE); + print_liveness(env, reg->live); + verbose(env, "=iter_%s(ref_id=%d,state=%s,depth=%u)", + iter_type_str(reg->iter.btf, reg->iter.btf_id), + reg->ref_obj_id, iter_state_str(reg->iter.state), + reg->iter.depth); + break; case STACK_MISC: case STACK_ZERO: default: @@ -1305,10 +1439,10 @@ static inline u32 vlog_alignment(u32 pos) static void print_insn_state(struct bpf_verifier_env *env, const struct bpf_func_state *state) { - if (env->prev_log_len && env->prev_log_len == env->log.len_used) { + if (env->prev_log_pos && env->prev_log_pos == env->log.end_pos) { /* remove new line character */ - bpf_vlog_reset(&env->log, env->prev_log_len - 1); - verbose(env, "%*c;", vlog_alignment(env->prev_insn_print_len), ' '); + bpf_vlog_reset(&env->log, env->prev_log_pos - 1); + verbose(env, "%*c;", vlog_alignment(env->prev_insn_print_pos), ' '); } else { verbose(env, "%d:", env->insn_idx); } @@ -1616,7 +1750,7 @@ static struct bpf_verifier_state *push_stack(struct bpf_verifier_env *env, elem->insn_idx = insn_idx; elem->prev_insn_idx = prev_insn_idx; elem->next = env->head; - elem->log_pos = env->log.len_used; + elem->log_pos = env->log.end_pos; env->head = elem; env->stack_size++; err = copy_verifier_state(&elem->st, cur); @@ -1946,9 +2080,9 @@ static void __reg_bound_offset(struct bpf_reg_state *reg) struct tnum var64_off = tnum_intersect(reg->var_off, tnum_range(reg->umin_value, reg->umax_value)); - struct tnum var32_off = tnum_intersect(tnum_subreg(reg->var_off), - tnum_range(reg->u32_min_value, - reg->u32_max_value)); + struct tnum var32_off = tnum_intersect(tnum_subreg(var64_off), + tnum_range(reg->u32_min_value, + reg->u32_max_value)); reg->var_off = tnum_or(tnum_clear_subreg(var64_off), var32_off); } @@ -2152,7 +2286,7 @@ static struct bpf_verifier_state *push_async_cb(struct bpf_verifier_env *env, elem->insn_idx = insn_idx; elem->prev_insn_idx = prev_insn_idx; elem->next = env->head; - elem->log_pos = env->log.len_used; + elem->log_pos = env->log.end_pos; env->head = elem; env->stack_size++; if (env->stack_size > BPF_COMPLEXITY_LIMIT_JMP_SEQ) { @@ -2710,6 +2844,25 @@ static int mark_dynptr_read(struct bpf_verifier_env *env, struct bpf_reg_state * state->stack[spi - 1].spilled_ptr.parent, REG_LIVE_READ64); } +static int mark_iter_read(struct bpf_verifier_env *env, struct bpf_reg_state *reg, + int spi, int nr_slots) +{ + struct bpf_func_state *state = func(env, reg); + int err, i; + + for (i = 0; i < nr_slots; i++) { + struct bpf_reg_state *st = &state->stack[spi - i].spilled_ptr; + + err = mark_reg_read(env, st, st->parent, REG_LIVE_READ64); + if (err) + return err; + + mark_stack_slot_scratched(env, spi - i); + } + + 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. @@ -3691,8 +3844,8 @@ static int check_stack_write_fixed_off(struct bpf_verifier_env *env, /* regular write of data into stack destroys any spilled ptr */ state->stack[spi].spilled_ptr.type = NOT_INIT; - /* Mark slots as STACK_MISC if they belonged to spilled ptr. */ - if (is_spilled_reg(&state->stack[spi])) + /* Mark slots as STACK_MISC if they belonged to spilled ptr/dynptr/iter. */ + if (is_stack_slot_special(&state->stack[spi])) for (i = 0; i < BPF_REG_SIZE; i++) scrub_spilled_slot(&state->stack[spi].slot_type[i]); @@ -4085,17 +4238,13 @@ static int check_stack_read(struct bpf_verifier_env *env, } /* Variable offset is prohibited for unprivileged mode for simplicity * since it requires corresponding support in Spectre masking for stack - * ALU. See also retrieve_ptr_limit(). + * ALU. See also retrieve_ptr_limit(). The check in + * check_stack_access_for_ptr_arithmetic() called by + * adjust_ptr_min_max_vals() prevents users from creating stack pointers + * with variable offsets, therefore no check is required here. Further, + * just checking it here would be insufficient as speculative stack + * writes could still lead to unsafe speculative behaviour. */ - if (!env->bypass_spec_v1 && var_off) { - char tn_buf[48]; - - tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off); - verbose(env, "R%d variable offset stack access prohibited for !root, var_off=%s\n", - ptr_regno, tn_buf); - return -EACCES; - } - if (!var_off) { off += reg->var_off.value; err = check_stack_read_fixed_off(env, state, off, size, @@ -4301,7 +4450,7 @@ static int map_kptr_match_type(struct bpf_verifier_env *env, struct btf_field *kptr_field, struct bpf_reg_state *reg, u32 regno) { - const char *targ_name = kernel_type_name(kptr_field->kptr.btf, kptr_field->kptr.btf_id); + const char *targ_name = btf_type_name(kptr_field->kptr.btf, kptr_field->kptr.btf_id); int perm_flags = PTR_MAYBE_NULL | PTR_TRUSTED | MEM_RCU; const char *reg_name = ""; @@ -4317,7 +4466,7 @@ static int map_kptr_match_type(struct bpf_verifier_env *env, return -EINVAL; } /* We need to verify reg->type and reg->btf, before accessing reg->btf */ - reg_name = kernel_type_name(reg->btf, reg->btf_id); + reg_name = btf_type_name(reg->btf, reg->btf_id); /* For ref_ptr case, release function check should ensure we get one * referenced PTR_TO_BTF_ID, and that its fixed offset is 0. For the @@ -4381,6 +4530,8 @@ static bool in_rcu_cs(struct bpf_verifier_env *env) BTF_SET_START(rcu_protected_types) BTF_ID(struct, prog_test_ref_kfunc) BTF_ID(struct, cgroup) +BTF_ID(struct, bpf_cpumask) +BTF_ID(struct, task_struct) BTF_SET_END(rcu_protected_types) static bool rcu_protected_object(const struct btf *btf, u32 btf_id) @@ -4754,6 +4905,11 @@ static bool is_rcu_reg(const struct bpf_reg_state *reg) return reg->type & MEM_RCU; } +static void clear_trusted_flags(enum bpf_type_flag *flag) +{ + *flag &= ~(BPF_REG_TRUSTED_MODIFIERS | MEM_RCU); +} + static int check_pkt_ptr_alignment(struct bpf_verifier_env *env, const struct bpf_reg_state *reg, int off, int size, bool strict) @@ -5158,6 +5314,7 @@ static int bpf_map_direct_read(struct bpf_map *map, int off, int size, u64 *val) } #define BTF_TYPE_SAFE_RCU(__type) __PASTE(__type, __safe_rcu) +#define BTF_TYPE_SAFE_RCU_OR_NULL(__type) __PASTE(__type, __safe_rcu_or_null) #define BTF_TYPE_SAFE_TRUSTED(__type) __PASTE(__type, __safe_trusted) /* @@ -5174,18 +5331,39 @@ BTF_TYPE_SAFE_RCU(struct task_struct) { struct task_struct *group_leader; }; +BTF_TYPE_SAFE_RCU(struct cgroup) { + /* cgrp->kn is always accessible as documented in kernel/cgroup/cgroup.c */ + struct kernfs_node *kn; +}; + BTF_TYPE_SAFE_RCU(struct css_set) { struct cgroup *dfl_cgrp; }; +/* RCU trusted: these fields are trusted in RCU CS and can be NULL */ +BTF_TYPE_SAFE_RCU_OR_NULL(struct mm_struct) { + struct file __rcu *exe_file; +}; + +/* skb->sk, req->sk are not RCU protected, but we mark them as such + * because bpf prog accessible sockets are SOCK_RCU_FREE. + */ +BTF_TYPE_SAFE_RCU_OR_NULL(struct sk_buff) { + struct sock *sk; +}; + +BTF_TYPE_SAFE_RCU_OR_NULL(struct request_sock) { + struct sock *sk; +}; + /* full trusted: these fields are trusted even outside of RCU CS and never NULL */ BTF_TYPE_SAFE_TRUSTED(struct bpf_iter_meta) { - __bpf_md_ptr(struct seq_file *, seq); + struct seq_file *seq; }; BTF_TYPE_SAFE_TRUSTED(struct bpf_iter__task) { - __bpf_md_ptr(struct bpf_iter_meta *, meta); - __bpf_md_ptr(struct task_struct *, task); + struct bpf_iter_meta *meta; + struct task_struct *task; }; BTF_TYPE_SAFE_TRUSTED(struct linux_binprm) { @@ -5207,17 +5385,29 @@ BTF_TYPE_SAFE_TRUSTED(struct socket) { static bool type_is_rcu(struct bpf_verifier_env *env, struct bpf_reg_state *reg, - int off) + const char *field_name, u32 btf_id) { BTF_TYPE_EMIT(BTF_TYPE_SAFE_RCU(struct task_struct)); + BTF_TYPE_EMIT(BTF_TYPE_SAFE_RCU(struct cgroup)); BTF_TYPE_EMIT(BTF_TYPE_SAFE_RCU(struct css_set)); - return btf_nested_type_is_trusted(&env->log, reg, off, "__safe_rcu"); + return btf_nested_type_is_trusted(&env->log, reg, field_name, btf_id, "__safe_rcu"); +} + +static bool type_is_rcu_or_null(struct bpf_verifier_env *env, + struct bpf_reg_state *reg, + const char *field_name, u32 btf_id) +{ + BTF_TYPE_EMIT(BTF_TYPE_SAFE_RCU_OR_NULL(struct mm_struct)); + BTF_TYPE_EMIT(BTF_TYPE_SAFE_RCU_OR_NULL(struct sk_buff)); + BTF_TYPE_EMIT(BTF_TYPE_SAFE_RCU_OR_NULL(struct request_sock)); + + return btf_nested_type_is_trusted(&env->log, reg, field_name, btf_id, "__safe_rcu_or_null"); } static bool type_is_trusted(struct bpf_verifier_env *env, struct bpf_reg_state *reg, - int off) + const char *field_name, u32 btf_id) { BTF_TYPE_EMIT(BTF_TYPE_SAFE_TRUSTED(struct bpf_iter_meta)); BTF_TYPE_EMIT(BTF_TYPE_SAFE_TRUSTED(struct bpf_iter__task)); @@ -5226,7 +5416,7 @@ static bool type_is_trusted(struct bpf_verifier_env *env, BTF_TYPE_EMIT(BTF_TYPE_SAFE_TRUSTED(struct dentry)); BTF_TYPE_EMIT(BTF_TYPE_SAFE_TRUSTED(struct socket)); - return btf_nested_type_is_trusted(&env->log, reg, off, "__safe_trusted"); + return btf_nested_type_is_trusted(&env->log, reg, field_name, btf_id, "__safe_trusted"); } static int check_ptr_to_btf_access(struct bpf_verifier_env *env, @@ -5238,8 +5428,9 @@ static int check_ptr_to_btf_access(struct bpf_verifier_env *env, struct bpf_reg_state *reg = regs + regno; const struct btf_type *t = btf_type_by_id(reg->btf, reg->btf_id); const char *tname = btf_name_by_offset(reg->btf, t->name_off); + const char *field_name = NULL; enum bpf_type_flag flag = 0; - u32 btf_id; + u32 btf_id = 0; int ret; if (!env->allow_ptr_leaks) { @@ -5284,12 +5475,12 @@ static int check_ptr_to_btf_access(struct bpf_verifier_env *env, return -EACCES; } - if (env->ops->btf_struct_access && !type_is_alloc(reg->type)) { + if (env->ops->btf_struct_access && !type_is_alloc(reg->type) && atype == BPF_WRITE) { if (!btf_is_kernel(reg->btf)) { verbose(env, "verifier internal error: reg->btf must be kernel btf\n"); return -EFAULT; } - ret = env->ops->btf_struct_access(&env->log, reg, off, size, atype, &btf_id, &flag); + ret = env->ops->btf_struct_access(&env->log, reg, off, size); } else { /* Writes are permitted with default btf_struct_access for * program allocated objects (which always have ref_obj_id > 0), @@ -5306,7 +5497,7 @@ static int check_ptr_to_btf_access(struct bpf_verifier_env *env, return -EFAULT; } - ret = btf_struct_access(&env->log, reg, off, size, atype, &btf_id, &flag); + ret = btf_struct_access(&env->log, reg, off, size, atype, &btf_id, &flag, &field_name); } if (ret < 0) @@ -5334,20 +5525,21 @@ static int check_ptr_to_btf_access(struct bpf_verifier_env *env, * A regular RCU-protected pointer with __rcu tag can also be deemed * trusted if we are in an RCU CS. Such pointer can be NULL. */ - if (type_is_trusted(env, reg, off)) { + if (type_is_trusted(env, reg, field_name, btf_id)) { flag |= PTR_TRUSTED; } else if (in_rcu_cs(env) && !type_may_be_null(reg->type)) { - if (type_is_rcu(env, reg, off)) { + if (type_is_rcu(env, reg, field_name, btf_id)) { /* ignore __rcu tag and mark it MEM_RCU */ flag |= MEM_RCU; - } else if (flag & MEM_RCU) { + } else if (flag & MEM_RCU || + type_is_rcu_or_null(env, reg, field_name, btf_id)) { /* __rcu tagged pointers can be NULL */ - flag |= PTR_MAYBE_NULL; + flag |= MEM_RCU | PTR_MAYBE_NULL; } else if (flag & (MEM_PERCPU | MEM_USER)) { /* keep as-is */ } else { - /* walking unknown pointers yields untrusted pointer */ - flag = PTR_UNTRUSTED; + /* walking unknown pointers yields old deprecated PTR_TO_BTF_ID */ + clear_trusted_flags(&flag); } } else { /* @@ -5361,7 +5553,7 @@ static int check_ptr_to_btf_access(struct bpf_verifier_env *env, } } else { /* Old compat. Deprecated */ - flag &= ~PTR_TRUSTED; + clear_trusted_flags(&flag); } if (atype == BPF_READ && value_regno >= 0) @@ -5420,7 +5612,7 @@ static int check_ptr_to_map_access(struct bpf_verifier_env *env, /* Simulate access to a PTR_TO_BTF_ID */ memset(&map_reg, 0, sizeof(map_reg)); mark_btf_ld_reg(env, &map_reg, 0, PTR_TO_BTF_ID, btf_vmlinux, *map->ops->map_btf_id, 0); - ret = btf_struct_access(&env->log, &map_reg, off, size, atype, &btf_id, &flag); + ret = btf_struct_access(&env->log, &map_reg, off, size, atype, &btf_id, &flag, NULL); if (ret < 0) return ret; @@ -6086,6 +6278,9 @@ static int check_helper_mem_access(struct bpf_verifier_env *env, int regno, env, regno, reg->off, access_size, zero_size_allowed, ACCESS_HELPER, meta); + case PTR_TO_BTF_ID: + return check_ptr_to_btf_access(env, regs, regno, reg->off, + access_size, BPF_READ, -1); case PTR_TO_CTX: /* in case the function doesn't know how to access the context, * (because we are in a program of type SYSCALL for example), we @@ -6506,6 +6701,203 @@ static int process_dynptr_func(struct bpf_verifier_env *env, int regno, int insn return err; } +static u32 iter_ref_obj_id(struct bpf_verifier_env *env, struct bpf_reg_state *reg, int spi) +{ + struct bpf_func_state *state = func(env, reg); + + return state->stack[spi].spilled_ptr.ref_obj_id; +} + +static bool is_iter_kfunc(struct bpf_kfunc_call_arg_meta *meta) +{ + return meta->kfunc_flags & (KF_ITER_NEW | KF_ITER_NEXT | KF_ITER_DESTROY); +} + +static bool is_iter_new_kfunc(struct bpf_kfunc_call_arg_meta *meta) +{ + return meta->kfunc_flags & KF_ITER_NEW; +} + +static bool is_iter_next_kfunc(struct bpf_kfunc_call_arg_meta *meta) +{ + return meta->kfunc_flags & KF_ITER_NEXT; +} + +static bool is_iter_destroy_kfunc(struct bpf_kfunc_call_arg_meta *meta) +{ + return meta->kfunc_flags & KF_ITER_DESTROY; +} + +static bool is_kfunc_arg_iter(struct bpf_kfunc_call_arg_meta *meta, int arg) +{ + /* btf_check_iter_kfuncs() guarantees that first argument of any iter + * kfunc is iter state pointer + */ + return arg == 0 && is_iter_kfunc(meta); +} + +static int process_iter_arg(struct bpf_verifier_env *env, int regno, int insn_idx, + struct bpf_kfunc_call_arg_meta *meta) +{ + struct bpf_reg_state *regs = cur_regs(env), *reg = ®s[regno]; + const struct btf_type *t; + const struct btf_param *arg; + int spi, err, i, nr_slots; + u32 btf_id; + + /* btf_check_iter_kfuncs() ensures we don't need to validate anything here */ + arg = &btf_params(meta->func_proto)[0]; + t = btf_type_skip_modifiers(meta->btf, arg->type, NULL); /* PTR */ + t = btf_type_skip_modifiers(meta->btf, t->type, &btf_id); /* STRUCT */ + nr_slots = t->size / BPF_REG_SIZE; + + if (is_iter_new_kfunc(meta)) { + /* bpf_iter_<type>_new() expects pointer to uninit iter state */ + if (!is_iter_reg_valid_uninit(env, reg, nr_slots)) { + verbose(env, "expected uninitialized iter_%s as arg #%d\n", + iter_type_str(meta->btf, btf_id), regno); + return -EINVAL; + } + + for (i = 0; i < nr_slots * 8; i += BPF_REG_SIZE) { + err = check_mem_access(env, insn_idx, regno, + i, BPF_DW, BPF_WRITE, -1, false); + if (err) + return err; + } + + err = mark_stack_slots_iter(env, reg, insn_idx, meta->btf, btf_id, nr_slots); + if (err) + return err; + } else { + /* iter_next() or iter_destroy() expect initialized iter state*/ + if (!is_iter_reg_valid_init(env, reg, meta->btf, btf_id, nr_slots)) { + verbose(env, "expected an initialized iter_%s as arg #%d\n", + iter_type_str(meta->btf, btf_id), regno); + return -EINVAL; + } + + spi = iter_get_spi(env, reg, nr_slots); + if (spi < 0) + return spi; + + err = mark_iter_read(env, reg, spi, nr_slots); + if (err) + return err; + + /* remember meta->iter info for process_iter_next_call() */ + meta->iter.spi = spi; + meta->iter.frameno = reg->frameno; + meta->ref_obj_id = iter_ref_obj_id(env, reg, spi); + + if (is_iter_destroy_kfunc(meta)) { + err = unmark_stack_slots_iter(env, reg, nr_slots); + if (err) + return err; + } + } + + return 0; +} + +/* process_iter_next_call() is called when verifier gets to iterator's next + * "method" (e.g., bpf_iter_num_next() for numbers iterator) call. We'll refer + * to it as just "iter_next()" in comments below. + * + * BPF verifier relies on a crucial contract for any iter_next() + * implementation: it should *eventually* return NULL, and once that happens + * it should keep returning NULL. That is, once iterator exhausts elements to + * iterate, it should never reset or spuriously return new elements. + * + * With the assumption of such contract, process_iter_next_call() simulates + * a fork in the verifier state to validate loop logic correctness and safety + * without having to simulate infinite amount of iterations. + * + * In current state, we first assume that iter_next() returned NULL and + * iterator state is set to DRAINED (BPF_ITER_STATE_DRAINED). In such + * conditions we should not form an infinite loop and should eventually reach + * exit. + * + * Besides that, we also fork current state and enqueue it for later + * verification. In a forked state we keep iterator state as ACTIVE + * (BPF_ITER_STATE_ACTIVE) and assume non-NULL return from iter_next(). We + * also bump iteration depth to prevent erroneous infinite loop detection + * later on (see iter_active_depths_differ() comment for details). In this + * state we assume that we'll eventually loop back to another iter_next() + * calls (it could be in exactly same location or in some other instruction, + * it doesn't matter, we don't make any unnecessary assumptions about this, + * everything revolves around iterator state in a stack slot, not which + * instruction is calling iter_next()). When that happens, we either will come + * to iter_next() with equivalent state and can conclude that next iteration + * will proceed in exactly the same way as we just verified, so it's safe to + * assume that loop converges. If not, we'll go on another iteration + * simulation with a different input state, until all possible starting states + * are validated or we reach maximum number of instructions limit. + * + * This way, we will either exhaustively discover all possible input states + * that iterator loop can start with and eventually will converge, or we'll + * effectively regress into bounded loop simulation logic and either reach + * maximum number of instructions if loop is not provably convergent, or there + * is some statically known limit on number of iterations (e.g., if there is + * an explicit `if n > 100 then break;` statement somewhere in the loop). + * + * One very subtle but very important aspect is that we *always* simulate NULL + * condition first (as the current state) before we simulate non-NULL case. + * This has to do with intricacies of scalar precision tracking. By simulating + * "exit condition" of iter_next() returning NULL first, we make sure all the + * relevant precision marks *that will be set **after** we exit iterator loop* + * are propagated backwards to common parent state of NULL and non-NULL + * branches. Thanks to that, state equivalence checks done later in forked + * state, when reaching iter_next() for ACTIVE iterator, can assume that + * precision marks are finalized and won't change. Because simulating another + * ACTIVE iterator iteration won't change them (because given same input + * states we'll end up with exactly same output states which we are currently + * comparing; and verification after the loop already propagated back what + * needs to be **additionally** tracked as precise). It's subtle, grok + * precision tracking for more intuitive understanding. + */ +static int process_iter_next_call(struct bpf_verifier_env *env, int insn_idx, + struct bpf_kfunc_call_arg_meta *meta) +{ + struct bpf_verifier_state *cur_st = env->cur_state, *queued_st; + struct bpf_func_state *cur_fr = cur_st->frame[cur_st->curframe], *queued_fr; + struct bpf_reg_state *cur_iter, *queued_iter; + int iter_frameno = meta->iter.frameno; + int iter_spi = meta->iter.spi; + + BTF_TYPE_EMIT(struct bpf_iter); + + cur_iter = &env->cur_state->frame[iter_frameno]->stack[iter_spi].spilled_ptr; + + if (cur_iter->iter.state != BPF_ITER_STATE_ACTIVE && + cur_iter->iter.state != BPF_ITER_STATE_DRAINED) { + verbose(env, "verifier internal error: unexpected iterator state %d (%s)\n", + cur_iter->iter.state, iter_state_str(cur_iter->iter.state)); + return -EFAULT; + } + + if (cur_iter->iter.state == BPF_ITER_STATE_ACTIVE) { + /* branch out active iter state */ + queued_st = push_stack(env, insn_idx + 1, insn_idx, false); + if (!queued_st) + return -ENOMEM; + + queued_iter = &queued_st->frame[iter_frameno]->stack[iter_spi].spilled_ptr; + queued_iter->iter.state = BPF_ITER_STATE_ACTIVE; + queued_iter->iter.depth++; + + queued_fr = queued_st->frame[queued_st->curframe]; + mark_ptr_not_null_reg(&queued_fr->regs[BPF_REG_0]); + } + + /* switch to DRAINED state, but keep the depth unchanged */ + /* mark current iter state as drained and assume returned NULL */ + cur_iter->iter.state = BPF_ITER_STATE_DRAINED; + __mark_reg_const_zero(&cur_fr->regs[BPF_REG_0]); + + return 0; +} + static bool arg_type_is_mem_size(enum bpf_arg_type type) { return type == ARG_CONST_SIZE || @@ -6600,6 +6992,7 @@ static const struct bpf_reg_types mem_types = { PTR_TO_MEM, PTR_TO_MEM | MEM_RINGBUF, PTR_TO_BUF, + PTR_TO_BTF_ID | PTR_TRUSTED, }, }; @@ -6709,6 +7102,9 @@ static int check_reg_type(struct bpf_verifier_env *env, u32 regno, if (arg_type & PTR_MAYBE_NULL) type &= ~PTR_MAYBE_NULL; + if (meta->func_id == BPF_FUNC_kptr_xchg && type & MEM_ALLOC) + type &= ~MEM_ALLOC; + for (i = 0; i < ARRAY_SIZE(compatible->types); i++) { expected = compatible->types[i]; if (expected == NOT_INIT) @@ -6728,10 +7124,23 @@ found: if (base_type(reg->type) != PTR_TO_BTF_ID) return 0; + if (compatible == &mem_types) { + if (!(arg_type & MEM_RDONLY)) { + verbose(env, + "%s() may write into memory pointed by R%d type=%s\n", + func_id_name(meta->func_id), + regno, reg_type_str(env, reg->type)); + return -EACCES; + } + return 0; + } + switch ((int)reg->type) { case PTR_TO_BTF_ID: case PTR_TO_BTF_ID | PTR_TRUSTED: case PTR_TO_BTF_ID | MEM_RCU: + case PTR_TO_BTF_ID | PTR_MAYBE_NULL: + case PTR_TO_BTF_ID | PTR_MAYBE_NULL | MEM_RCU: { /* For bpf_sk_release, it needs to match against first member * 'struct sock_common', hence make an exception for it. This @@ -6740,6 +7149,12 @@ found: bool strict_type_match = arg_type_is_release(arg_type) && meta->func_id != BPF_FUNC_sk_release; + if (type_may_be_null(reg->type) && + (!type_may_be_null(arg_type) || arg_type_is_release(arg_type))) { + verbose(env, "Possibly NULL pointer passed to helper arg%d\n", regno); + return -EACCES; + } + if (!arg_btf_id) { if (!compatible->btf_id) { verbose(env, "verifier internal error: missing arg compatible BTF ID\n"); @@ -6763,15 +7178,16 @@ found: btf_vmlinux, *arg_btf_id, strict_type_match)) { verbose(env, "R%d is of type %s but %s is expected\n", - regno, kernel_type_name(reg->btf, reg->btf_id), - kernel_type_name(btf_vmlinux, *arg_btf_id)); + regno, btf_type_name(reg->btf, reg->btf_id), + btf_type_name(btf_vmlinux, *arg_btf_id)); return -EACCES; } } break; } case PTR_TO_BTF_ID | MEM_ALLOC: - if (meta->func_id != BPF_FUNC_spin_lock && meta->func_id != BPF_FUNC_spin_unlock) { + if (meta->func_id != BPF_FUNC_spin_lock && meta->func_id != BPF_FUNC_spin_unlock && + meta->func_id != BPF_FUNC_kptr_xchg) { verbose(env, "verifier internal error: unimplemented handling of MEM_ALLOC\n"); return -EFAULT; } @@ -6834,7 +7250,7 @@ int check_func_arg_reg_off(struct bpf_verifier_env *env, verbose(env, "R%d must have zero offset when passed to release func\n", regno); verbose(env, "No graph node or root found at R%d type:%s off:%d\n", regno, - kernel_type_name(reg->btf, reg->btf_id), reg->off); + btf_type_name(reg->btf, reg->btf_id), reg->off); return -EINVAL; } @@ -8737,6 +9153,8 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn if (func_id == BPF_FUNC_kptr_xchg) { ret_btf = meta.kptr_field->kptr.btf; ret_btf_id = meta.kptr_field->kptr.btf_id; + if (!btf_is_kernel(ret_btf)) + regs[BPF_REG_0].type |= MEM_ALLOC; } else { if (fn->ret_btf_id == BPF_PTR_POISON) { verbose(env, "verifier internal error:"); @@ -8870,7 +9288,7 @@ static bool is_kfunc_release(struct bpf_kfunc_call_arg_meta *meta) static bool is_kfunc_trusted_args(struct bpf_kfunc_call_arg_meta *meta) { - return meta->kfunc_flags & KF_TRUSTED_ARGS; + return (meta->kfunc_flags & KF_TRUSTED_ARGS) || is_kfunc_release(meta); } static bool is_kfunc_sleepable(struct bpf_kfunc_call_arg_meta *meta) @@ -9099,6 +9517,7 @@ enum kfunc_ptr_arg_type { KF_ARG_PTR_TO_ALLOC_BTF_ID, /* Allocated object */ KF_ARG_PTR_TO_KPTR, /* PTR_TO_KPTR but type specific */ KF_ARG_PTR_TO_DYNPTR, + KF_ARG_PTR_TO_ITER, KF_ARG_PTR_TO_LIST_HEAD, KF_ARG_PTR_TO_LIST_NODE, KF_ARG_PTR_TO_BTF_ID, /* Also covers reg2btf_ids conversions */ @@ -9220,6 +9639,9 @@ get_kfunc_ptr_arg_type(struct bpf_verifier_env *env, if (is_kfunc_arg_dynptr(meta->btf, &args[argno])) return KF_ARG_PTR_TO_DYNPTR; + if (is_kfunc_arg_iter(meta, argno)) + return KF_ARG_PTR_TO_ITER; + if (is_kfunc_arg_list_head(meta->btf, &args[argno])) return KF_ARG_PTR_TO_LIST_HEAD; @@ -9848,6 +10270,7 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_ break; case KF_ARG_PTR_TO_KPTR: case KF_ARG_PTR_TO_DYNPTR: + case KF_ARG_PTR_TO_ITER: case KF_ARG_PTR_TO_LIST_HEAD: case KF_ARG_PTR_TO_LIST_NODE: case KF_ARG_PTR_TO_RB_ROOT: @@ -9944,6 +10367,11 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_ break; } + case KF_ARG_PTR_TO_ITER: + ret = process_iter_arg(env, regno, insn_idx, meta); + if (ret < 0) + return ret; + break; case KF_ARG_PTR_TO_LIST_HEAD: if (reg->type != PTR_TO_MAP_VALUE && reg->type != (PTR_TO_BTF_ID | MEM_ALLOC)) { @@ -10079,24 +10507,21 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_ return 0; } -static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn, - int *insn_idx_p) +static int fetch_kfunc_meta(struct bpf_verifier_env *env, + struct bpf_insn *insn, + struct bpf_kfunc_call_arg_meta *meta, + const char **kfunc_name) { - const struct btf_type *t, *func, *func_proto, *ptr_type; - u32 i, nargs, func_id, ptr_type_id, release_ref_obj_id; - struct bpf_reg_state *regs = cur_regs(env); - const char *func_name, *ptr_type_name; - bool sleepable, rcu_lock, rcu_unlock; - struct bpf_kfunc_call_arg_meta meta; - int err, insn_idx = *insn_idx_p; - const struct btf_param *args; - const struct btf_type *ret_t; + const struct btf_type *func, *func_proto; + u32 func_id, *kfunc_flags; + const char *func_name; struct btf *desc_btf; - u32 *kfunc_flags; - /* skip for now, but return error when we find this in fixup_kfunc_call */ + if (kfunc_name) + *kfunc_name = NULL; + if (!insn->imm) - return 0; + return -EINVAL; desc_btf = find_kfunc_desc_btf(env, insn->off); if (IS_ERR(desc_btf)) @@ -10105,22 +10530,53 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn, func_id = insn->imm; func = btf_type_by_id(desc_btf, func_id); func_name = btf_name_by_offset(desc_btf, func->name_off); + if (kfunc_name) + *kfunc_name = func_name; func_proto = btf_type_by_id(desc_btf, func->type); kfunc_flags = btf_kfunc_id_set_contains(desc_btf, resolve_prog_type(env->prog), func_id); if (!kfunc_flags) { - verbose(env, "calling kernel function %s is not allowed\n", - func_name); return -EACCES; } - /* Prepare kfunc call metadata */ - memset(&meta, 0, sizeof(meta)); - meta.btf = desc_btf; - meta.func_id = func_id; - meta.kfunc_flags = *kfunc_flags; - meta.func_proto = func_proto; - meta.func_name = func_name; + memset(meta, 0, sizeof(*meta)); + meta->btf = desc_btf; + meta->func_id = func_id; + meta->kfunc_flags = *kfunc_flags; + meta->func_proto = func_proto; + meta->func_name = func_name; + + return 0; +} + +static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn, + int *insn_idx_p) +{ + const struct btf_type *t, *ptr_type; + u32 i, nargs, ptr_type_id, release_ref_obj_id; + struct bpf_reg_state *regs = cur_regs(env); + const char *func_name, *ptr_type_name; + bool sleepable, rcu_lock, rcu_unlock; + struct bpf_kfunc_call_arg_meta meta; + struct bpf_insn_aux_data *insn_aux; + int err, insn_idx = *insn_idx_p; + const struct btf_param *args; + const struct btf_type *ret_t; + struct btf *desc_btf; + + /* skip for now, but return error when we find this in fixup_kfunc_call */ + if (!insn->imm) + return 0; + + err = fetch_kfunc_meta(env, insn, &meta, &func_name); + if (err == -EACCES && func_name) + verbose(env, "calling kernel function %s is not allowed\n", func_name); + if (err) + return err; + desc_btf = meta.btf; + insn_aux = &env->insn_aux_data[insn_idx]; + + insn_aux->is_iter_next = is_iter_next_kfunc(&meta); if (is_kfunc_destructive(&meta) && !capable(CAP_SYS_BOOT)) { verbose(env, "destructive kfunc calls require CAP_SYS_BOOT capability\n"); @@ -10173,7 +10629,7 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn, err = release_reference(env, regs[meta.release_regno].ref_obj_id); if (err) { verbose(env, "kfunc %s#%d reference has not been acquired before\n", - func_name, func_id); + func_name, meta.func_id); return err; } } @@ -10185,14 +10641,14 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn, err = ref_convert_owning_non_owning(env, release_ref_obj_id); if (err) { verbose(env, "kfunc %s#%d conversion of owning ref to non-owning failed\n", - func_name, func_id); + func_name, meta.func_id); return err; } err = release_reference(env, release_ref_obj_id); if (err) { verbose(env, "kfunc %s#%d reference has not been acquired before\n", - func_name, func_id); + func_name, meta.func_id); return err; } } @@ -10202,7 +10658,7 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn, set_rbtree_add_callback_state); if (err) { verbose(env, "kfunc %s#%d failed callback verification\n", - func_name, func_id); + func_name, meta.func_id); return err; } } @@ -10211,7 +10667,7 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn, mark_reg_not_init(env, regs, caller_saved[i]); /* Check return type */ - t = btf_type_skip_modifiers(desc_btf, func_proto->type, NULL); + t = btf_type_skip_modifiers(desc_btf, meta.func_proto->type, NULL); if (is_kfunc_acquire(&meta) && !btf_type_is_struct_ptr(meta.btf, t)) { /* Only exception is bpf_obj_new_impl */ @@ -10260,13 +10716,9 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn, regs[BPF_REG_0].btf = ret_btf; regs[BPF_REG_0].btf_id = ret_btf_id; - env->insn_aux_data[insn_idx].obj_new_size = ret_t->size; - env->insn_aux_data[insn_idx].kptr_struct_meta = + insn_aux->obj_new_size = ret_t->size; + insn_aux->kptr_struct_meta = btf_find_struct_meta(ret_btf, ret_btf_id); - } else if (meta.func_id == special_kfunc_list[KF_bpf_obj_drop_impl]) { - env->insn_aux_data[insn_idx].kptr_struct_meta = - btf_find_struct_meta(meta.arg_obj_drop.btf, - meta.arg_obj_drop.btf_id); } else if (meta.func_id == special_kfunc_list[KF_bpf_list_pop_front] || meta.func_id == special_kfunc_list[KF_bpf_list_pop_back]) { struct btf_field *field = meta.arg_list_head.field; @@ -10395,10 +10847,18 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn, if (reg_may_point_to_spin_lock(®s[BPF_REG_0]) && !regs[BPF_REG_0].id) regs[BPF_REG_0].id = ++env->id_gen; - } /* else { add_kfunc_call() ensures it is btf_type_is_void(t) } */ + } else if (btf_type_is_void(t)) { + if (meta.btf == btf_vmlinux && btf_id_set_contains(&special_kfunc_set, meta.func_id)) { + if (meta.func_id == special_kfunc_list[KF_bpf_obj_drop_impl]) { + insn_aux->kptr_struct_meta = + btf_find_struct_meta(meta.arg_obj_drop.btf, + meta.arg_obj_drop.btf_id); + } + } + } - nargs = btf_type_vlen(func_proto); - args = (const struct btf_param *)(func_proto + 1); + nargs = btf_type_vlen(meta.func_proto); + args = (const struct btf_param *)(meta.func_proto + 1); for (i = 0; i < nargs; i++) { u32 regno = i + 1; @@ -10410,6 +10870,12 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn, mark_btf_func_reg_size(env, regno, t->size); } + if (is_iter_next_kfunc(&meta)) { + err = process_iter_next_call(env, insn_idx, &meta); + if (err) + return err; + } + return 0; } @@ -12116,10 +12582,14 @@ static int is_branch32_taken(struct bpf_reg_state *reg, u32 val, u8 opcode) case BPF_JEQ: if (tnum_is_const(subreg)) return !!tnum_equals_const(subreg, val); + else if (val < reg->u32_min_value || val > reg->u32_max_value) + return 0; break; case BPF_JNE: if (tnum_is_const(subreg)) return !tnum_equals_const(subreg, val); + else if (val < reg->u32_min_value || val > reg->u32_max_value) + return 1; break; case BPF_JSET: if ((~subreg.mask & subreg.value) & val) @@ -12189,10 +12659,14 @@ static int is_branch64_taken(struct bpf_reg_state *reg, u64 val, u8 opcode) case BPF_JEQ: if (tnum_is_const(reg->var_off)) return !!tnum_equals_const(reg->var_off, val); + else if (val < reg->umin_value || val > reg->umax_value) + return 0; break; case BPF_JNE: if (tnum_is_const(reg->var_off)) return !tnum_equals_const(reg->var_off, val); + else if (val < reg->umin_value || val > reg->umax_value) + return 1; break; case BPF_JSET: if ((~reg->var_off.mask & reg->var_off.value) & val) @@ -12813,6 +13287,18 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env, src_reg->var_off.value, opcode, is_jmp32); + } else if (dst_reg->type == SCALAR_VALUE && + is_jmp32 && tnum_is_const(tnum_subreg(dst_reg->var_off))) { + pred = is_branch_taken(src_reg, + tnum_subreg(dst_reg->var_off).value, + flip_opcode(opcode), + is_jmp32); + } else if (dst_reg->type == SCALAR_VALUE && + !is_jmp32 && tnum_is_const(dst_reg->var_off)) { + pred = is_branch_taken(src_reg, + dst_reg->var_off.value, + flip_opcode(opcode), + is_jmp32); } else if (reg_is_pkt_pointer_any(dst_reg) && reg_is_pkt_pointer_any(src_reg) && !is_jmp32) { @@ -13407,6 +13893,17 @@ static bool is_prune_point(struct bpf_verifier_env *env, int insn_idx) return env->insn_aux_data[insn_idx].prune_point; } +static void mark_force_checkpoint(struct bpf_verifier_env *env, int idx) +{ + env->insn_aux_data[idx].force_checkpoint = true; +} + +static bool is_force_checkpoint(struct bpf_verifier_env *env, int insn_idx) +{ + return env->insn_aux_data[insn_idx].force_checkpoint; +} + + enum { DONE_EXPLORING = 0, KEEP_EXPLORING = 1, @@ -13522,6 +14019,26 @@ static int visit_insn(int t, struct bpf_verifier_env *env) * async state will be pushed for further exploration. */ mark_prune_point(env, t); + if (insn->src_reg == BPF_PSEUDO_KFUNC_CALL) { + struct bpf_kfunc_call_arg_meta meta; + + ret = fetch_kfunc_meta(env, insn, &meta, NULL); + if (ret == 0 && is_iter_next_kfunc(&meta)) { + mark_prune_point(env, t); + /* Checking and saving state checkpoints at iter_next() call + * is crucial for fast convergence of open-coded iterator loop + * logic, so we need to force it. If we don't do that, + * is_state_visited() might skip saving a checkpoint, causing + * unnecessarily long sequence of not checkpointed + * instructions and jumps, leading to exhaustion of jump + * history buffer, and potentially other undesired outcomes. + * It is expected that with correct open-coded iterators + * convergence will happen quickly, so we don't run a risk of + * exhausting memory. + */ + mark_force_checkpoint(env, t); + } + } return visit_func_call_insn(t, insns, env, insn->src_reg == BPF_PSEUDO_CALL); case BPF_JA: @@ -14275,6 +14792,8 @@ static bool stacksafe(struct bpf_verifier_env *env, struct bpf_func_state *old, * didn't use them */ for (i = 0; i < old->allocated_stack; i++) { + struct bpf_reg_state *old_reg, *cur_reg; + spi = i / BPF_REG_SIZE; if (!(old->stack[spi].spilled_ptr.live & REG_LIVE_READ)) { @@ -14331,9 +14850,6 @@ static bool stacksafe(struct bpf_verifier_env *env, struct bpf_func_state *old, return false; break; case STACK_DYNPTR: - { - const struct bpf_reg_state *old_reg, *cur_reg; - old_reg = &old->stack[spi].spilled_ptr; cur_reg = &cur->stack[spi].spilled_ptr; if (old_reg->dynptr.type != cur_reg->dynptr.type || @@ -14341,7 +14857,22 @@ static bool stacksafe(struct bpf_verifier_env *env, struct bpf_func_state *old, !check_ids(old_reg->ref_obj_id, cur_reg->ref_obj_id, idmap)) return false; break; - } + case STACK_ITER: + old_reg = &old->stack[spi].spilled_ptr; + cur_reg = &cur->stack[spi].spilled_ptr; + /* iter.depth is not compared between states as it + * doesn't matter for correctness and would otherwise + * prevent convergence; we maintain it only to prevent + * infinite loop check triggering, see + * iter_active_depths_differ() + */ + if (old_reg->iter.btf != cur_reg->iter.btf || + old_reg->iter.btf_id != cur_reg->iter.btf_id || + old_reg->iter.state != cur_reg->iter.state || + /* ignore {old_reg,cur_reg}->iter.depth, see above */ + !check_ids(old_reg->ref_obj_id, cur_reg->ref_obj_id, idmap)) + return false; + break; case STACK_MISC: case STACK_ZERO: case STACK_INVALID: @@ -14555,10 +15086,11 @@ static int propagate_precision(struct bpf_verifier_env *env, state_reg = state->regs; for (i = 0; i < BPF_REG_FP; i++, state_reg++) { if (state_reg->type != SCALAR_VALUE || - !state_reg->precise) + !state_reg->precise || + !(state_reg->live & REG_LIVE_READ)) continue; if (env->log.level & BPF_LOG_LEVEL2) - verbose(env, "frame %d: propagating r%d\n", i, fr); + verbose(env, "frame %d: propagating r%d\n", fr, i); err = mark_chain_precision_frame(env, fr, i); if (err < 0) return err; @@ -14569,11 +15101,12 @@ static int propagate_precision(struct bpf_verifier_env *env, continue; state_reg = &state->stack[i].spilled_ptr; if (state_reg->type != SCALAR_VALUE || - !state_reg->precise) + !state_reg->precise || + !(state_reg->live & REG_LIVE_READ)) continue; if (env->log.level & BPF_LOG_LEVEL2) verbose(env, "frame %d: propagating fp%d\n", - (-i - 1) * BPF_REG_SIZE, fr); + fr, (-i - 1) * BPF_REG_SIZE); err = mark_chain_precision_stack_frame(env, fr, i); if (err < 0) return err; @@ -14600,6 +15133,92 @@ static bool states_maybe_looping(struct bpf_verifier_state *old, return true; } +static bool is_iter_next_insn(struct bpf_verifier_env *env, int insn_idx) +{ + return env->insn_aux_data[insn_idx].is_iter_next; +} + +/* is_state_visited() handles iter_next() (see process_iter_next_call() for + * terminology) calls specially: as opposed to bounded BPF loops, it *expects* + * states to match, which otherwise would look like an infinite loop. So while + * iter_next() calls are taken care of, we still need to be careful and + * prevent erroneous and too eager declaration of "ininite loop", when + * iterators are involved. + * + * Here's a situation in pseudo-BPF assembly form: + * + * 0: again: ; set up iter_next() call args + * 1: r1 = &it ; <CHECKPOINT HERE> + * 2: call bpf_iter_num_next ; this is iter_next() call + * 3: if r0 == 0 goto done + * 4: ... something useful here ... + * 5: goto again ; another iteration + * 6: done: + * 7: r1 = &it + * 8: call bpf_iter_num_destroy ; clean up iter state + * 9: exit + * + * This is a typical loop. Let's assume that we have a prune point at 1:, + * before we get to `call bpf_iter_num_next` (e.g., because of that `goto + * again`, assuming other heuristics don't get in a way). + * + * When we first time come to 1:, let's say we have some state X. We proceed + * to 2:, fork states, enqueue ACTIVE, validate NULL case successfully, exit. + * Now we come back to validate that forked ACTIVE state. We proceed through + * 3-5, come to goto, jump to 1:. Let's assume our state didn't change, so we + * are converging. But the problem is that we don't know that yet, as this + * convergence has to happen at iter_next() call site only. So if nothing is + * done, at 1: verifier will use bounded loop logic and declare infinite + * looping (and would be *technically* correct, if not for iterator's + * "eventual sticky NULL" contract, see process_iter_next_call()). But we + * don't want that. So what we do in process_iter_next_call() when we go on + * another ACTIVE iteration, we bump slot->iter.depth, to mark that it's + * a different iteration. So when we suspect an infinite loop, we additionally + * check if any of the *ACTIVE* iterator states depths differ. If yes, we + * pretend we are not looping and wait for next iter_next() call. + * + * This only applies to ACTIVE state. In DRAINED state we don't expect to + * loop, because that would actually mean infinite loop, as DRAINED state is + * "sticky", and so we'll keep returning into the same instruction with the + * same state (at least in one of possible code paths). + * + * This approach allows to keep infinite loop heuristic even in the face of + * active iterator. E.g., C snippet below is and will be detected as + * inifintely looping: + * + * struct bpf_iter_num it; + * int *p, x; + * + * bpf_iter_num_new(&it, 0, 10); + * while ((p = bpf_iter_num_next(&t))) { + * x = p; + * while (x--) {} // <<-- infinite loop here + * } + * + */ +static bool iter_active_depths_differ(struct bpf_verifier_state *old, struct bpf_verifier_state *cur) +{ + struct bpf_reg_state *slot, *cur_slot; + struct bpf_func_state *state; + int i, fr; + + for (fr = old->curframe; fr >= 0; fr--) { + state = old->frame[fr]; + for (i = 0; i < state->allocated_stack / BPF_REG_SIZE; i++) { + if (state->stack[i].slot_type[0] != STACK_ITER) + continue; + + slot = &state->stack[i].spilled_ptr; + if (slot->iter.state != BPF_ITER_STATE_ACTIVE) + continue; + + cur_slot = &cur->frame[fr]->stack[i].spilled_ptr; + if (cur_slot->iter.depth != slot->iter.depth) + return true; + } + } + return false; +} static int is_state_visited(struct bpf_verifier_env *env, int insn_idx) { @@ -14607,7 +15226,8 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx) struct bpf_verifier_state_list *sl, **pprev; struct bpf_verifier_state *cur = env->cur_state, *new; int i, j, err, states_cnt = 0; - bool add_new_state = env->test_state_freq ? true : false; + bool force_new_state = env->test_state_freq || is_force_checkpoint(env, insn_idx); + bool add_new_state = force_new_state; /* bpf progs typically have pruning point every 4 instructions * http://vger.kernel.org/bpfconf2019.html#session-1 @@ -14647,8 +15267,46 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx) * Since the verifier still needs to catch infinite loops * inside async callbacks. */ - } else if (states_maybe_looping(&sl->state, cur) && - states_equal(env, &sl->state, cur)) { + goto skip_inf_loop_check; + } + /* BPF open-coded iterators loop detection is special. + * states_maybe_looping() logic is too simplistic in detecting + * states that *might* be equivalent, because it doesn't know + * about ID remapping, so don't even perform it. + * See process_iter_next_call() and iter_active_depths_differ() + * for overview of the logic. When current and one of parent + * states are detected as equivalent, it's a good thing: we prove + * convergence and can stop simulating further iterations. + * It's safe to assume that iterator loop will finish, taking into + * account iter_next() contract of eventually returning + * sticky NULL result. + */ + if (is_iter_next_insn(env, insn_idx)) { + if (states_equal(env, &sl->state, cur)) { + struct bpf_func_state *cur_frame; + struct bpf_reg_state *iter_state, *iter_reg; + int spi; + + cur_frame = cur->frame[cur->curframe]; + /* btf_check_iter_kfuncs() enforces that + * iter state pointer is always the first arg + */ + iter_reg = &cur_frame->regs[BPF_REG_1]; + /* current state is valid due to states_equal(), + * so we can assume valid iter and reg state, + * no need for extra (re-)validations + */ + spi = __get_spi(iter_reg->off + iter_reg->var_off.value); + iter_state = &func(env, iter_reg)->stack[spi].spilled_ptr; + if (iter_state->iter.state == BPF_ITER_STATE_ACTIVE) + goto hit; + } + goto skip_inf_loop_check; + } + /* attempt to detect infinite loop to avoid unnecessary doomed work */ + if (states_maybe_looping(&sl->state, cur) && + states_equal(env, &sl->state, cur) && + !iter_active_depths_differ(&sl->state, cur)) { verbose_linfo(env, insn_idx, "; "); verbose(env, "infinite loop detected at insn %d\n", insn_idx); return -EINVAL; @@ -14665,13 +15323,15 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx) * This threshold shouldn't be too high either, since states * at the end of the loop are likely to be useful in pruning. */ - if (!env->test_state_freq && +skip_inf_loop_check: + if (!force_new_state && env->jmps_processed - env->prev_jmps_processed < 20 && env->insn_processed - env->prev_insn_processed < 100) add_new_state = false; goto miss; } if (states_equal(env, &sl->state, cur)) { +hit: sl->hit_cnt++; /* reached equivalent register/stack state, * prune the search. @@ -14978,11 +15638,11 @@ static int do_check(struct bpf_verifier_env *env) print_insn_state(env, state->frame[state->curframe]); verbose_linfo(env, env->insn_idx, "; "); - env->prev_log_len = env->log.len_used; + env->prev_log_pos = env->log.end_pos; verbose(env, "%d: ", env->insn_idx); print_bpf_insn(&cbs, insn, env->allow_ptr_leaks); - env->prev_insn_print_len = env->log.len_used - env->prev_log_len; - env->prev_log_len = env->log.len_used; + env->prev_insn_print_pos = env->log.end_pos - env->prev_log_pos; + env->prev_log_pos = env->log.end_pos; } if (bpf_prog_is_offloaded(env->prog->aux)) { @@ -15301,8 +15961,8 @@ static int check_pseudo_btf_id(struct bpf_verifier_env *env, goto err_put; } - if (!btf_type_is_var(t)) { - verbose(env, "pseudo btf_id %d in ldimm64 isn't KIND_VAR.\n", id); + if (!btf_type_is_var(t) && !btf_type_is_func(t)) { + verbose(env, "pseudo btf_id %d in ldimm64 isn't KIND_VAR or KIND_FUNC\n", id); err = -EINVAL; goto err_put; } @@ -15315,6 +15975,14 @@ static int check_pseudo_btf_id(struct bpf_verifier_env *env, err = -ENOENT; goto err_put; } + insn[0].imm = (u32)addr; + insn[1].imm = addr >> 32; + + if (btf_type_is_func(t)) { + aux->btf_var.reg_type = PTR_TO_MEM | MEM_RDONLY; + aux->btf_var.mem_size = 0; + goto check_btf; + } datasec_id = find_btf_percpu_datasec(btf); if (datasec_id > 0) { @@ -15327,9 +15995,6 @@ static int check_pseudo_btf_id(struct bpf_verifier_env *env, } } - insn[0].imm = (u32)addr; - insn[1].imm = addr >> 32; - type = t->type; t = btf_type_skip_modifiers(btf, type, NULL); if (percpu) { @@ -15357,7 +16022,7 @@ static int check_pseudo_btf_id(struct bpf_verifier_env *env, aux->btf_var.btf = btf; aux->btf_var.btf_id = type; } - +check_btf: /* check whether we recorded this BTF (and maybe module) already */ for (i = 0; i < env->used_btf_cnt; i++) { if (env->used_btfs[i].btf == btf) { @@ -17032,21 +17697,21 @@ static int do_misc_fixups(struct bpf_verifier_env *env) BUILD_BUG_ON(!__same_type(ops->map_lookup_elem, (void *(*)(struct bpf_map *map, void *key))NULL)); BUILD_BUG_ON(!__same_type(ops->map_delete_elem, - (int (*)(struct bpf_map *map, void *key))NULL)); + (long (*)(struct bpf_map *map, void *key))NULL)); BUILD_BUG_ON(!__same_type(ops->map_update_elem, - (int (*)(struct bpf_map *map, void *key, void *value, + (long (*)(struct bpf_map *map, void *key, void *value, u64 flags))NULL)); BUILD_BUG_ON(!__same_type(ops->map_push_elem, - (int (*)(struct bpf_map *map, void *value, + (long (*)(struct bpf_map *map, void *value, u64 flags))NULL)); BUILD_BUG_ON(!__same_type(ops->map_pop_elem, - (int (*)(struct bpf_map *map, void *value))NULL)); + (long (*)(struct bpf_map *map, void *value))NULL)); BUILD_BUG_ON(!__same_type(ops->map_peek_elem, - (int (*)(struct bpf_map *map, void *value))NULL)); + (long (*)(struct bpf_map *map, void *value))NULL)); BUILD_BUG_ON(!__same_type(ops->map_redirect, - (int (*)(struct bpf_map *map, u64 index, u64 flags))NULL)); + (long (*)(struct bpf_map *map, u64 index, u64 flags))NULL)); BUILD_BUG_ON(!__same_type(ops->map_for_each_callback, - (int (*)(struct bpf_map *map, + (long (*)(struct bpf_map *map, bpf_callback_t callback_fn, void *callback_ctx, u64 flags))NULL)); @@ -17654,6 +18319,7 @@ int bpf_check_attach_target(struct bpf_verifier_log *log, const char *tname; struct btf *btf; long addr = 0; + struct module *mod = NULL; if (!btf_id) { bpf_log(log, "Tracing programs must provide btf_id\n"); @@ -17827,8 +18493,17 @@ int bpf_check_attach_target(struct bpf_verifier_log *log, else addr = (long) tgt_prog->aux->func[subprog]->bpf_func; } else { - addr = kallsyms_lookup_name(tname); + if (btf_is_module(btf)) { + mod = btf_try_get_module(btf); + if (mod) + addr = find_kallsyms_symbol_value(mod, tname); + else + addr = 0; + } else { + addr = kallsyms_lookup_name(tname); + } if (!addr) { + module_put(mod); bpf_log(log, "The address of function %s cannot be found\n", tname); @@ -17868,11 +18543,13 @@ int bpf_check_attach_target(struct bpf_verifier_log *log, break; } if (ret) { + module_put(mod); bpf_log(log, "%s is not sleepable\n", tname); return ret; } } else if (prog->expected_attach_type == BPF_MODIFY_RETURN) { if (tgt_prog) { + module_put(mod); bpf_log(log, "can't modify return codes of BPF programs\n"); return -EINVAL; } @@ -17881,6 +18558,7 @@ int bpf_check_attach_target(struct bpf_verifier_log *log, !check_attach_modify_return(addr, tname)) ret = 0; if (ret) { + module_put(mod); bpf_log(log, "%s() is not modifiable\n", tname); return ret; } @@ -17891,6 +18569,7 @@ int bpf_check_attach_target(struct bpf_verifier_log *log, tgt_info->tgt_addr = addr; tgt_info->tgt_name = tname; tgt_info->tgt_type = t; + tgt_info->tgt_mod = mod; return 0; } @@ -17970,6 +18649,7 @@ static int check_attach_btf_id(struct bpf_verifier_env *env) /* store info about the attachment target that will be used later */ prog->aux->attach_func_proto = tgt_info.tgt_type; prog->aux->attach_func_name = tgt_info.tgt_name; + prog->aux->mod = tgt_info.tgt_mod; if (tgt_prog) { prog->aux->saved_dst_prog_type = tgt_prog->type; @@ -18014,12 +18694,12 @@ struct btf *bpf_get_btf_vmlinux(void) return btf_vmlinux; } -int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, bpfptr_t uattr) +int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, bpfptr_t uattr, __u32 uattr_size) { u64 start_time = ktime_get_ns(); struct bpf_verifier_env *env; - struct bpf_verifier_log *log; - int i, len, ret = -EINVAL; + int i, len, ret = -EINVAL, err; + u32 log_true_size; bool is_priv; /* no program is valid */ @@ -18032,7 +18712,6 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, bpfptr_t uattr) env = kzalloc(sizeof(struct bpf_verifier_env), GFP_KERNEL); if (!env) return -ENOMEM; - log = &env->log; len = (*prog)->len; env->insn_aux_data = @@ -18053,20 +18732,14 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, bpfptr_t uattr) if (!is_priv) mutex_lock(&bpf_verifier_lock); - if (attr->log_level || attr->log_buf || attr->log_size) { - /* user requested verbose verifier output - * and supplied buffer to store the verification trace - */ - log->level = attr->log_level; - log->ubuf = (char __user *) (unsigned long) attr->log_buf; - log->len_total = attr->log_size; - - /* log attributes have to be sane */ - if (!bpf_verifier_log_attr_valid(log)) { - ret = -EINVAL; - goto err_unlock; - } - } + /* user could have requested verbose verifier output + * and supplied buffer to store the verification trace + */ + ret = bpf_vlog_init(&env->log, attr->log_level, + (char __user *) (unsigned long) attr->log_buf, + attr->log_size); + if (ret) + goto err_unlock; mark_verifier_state_clean(env); @@ -18180,9 +18853,14 @@ skip_full_check: print_verification_stats(env); env->prog->aux->verified_insns = env->insn_processed; - if (log->level && bpf_verifier_log_full(log)) - ret = -ENOSPC; - if (log->level && !log->ubuf) { + /* preserve original error even if log finalization is successful */ + err = bpf_vlog_finalize(&env->log, &log_true_size); + if (err) + ret = err; + + if (uattr_size >= offsetofend(union bpf_attr, log_true_size) && + copy_to_bpfptr_offset(uattr, offsetof(union bpf_attr, log_true_size), + &log_true_size, sizeof(log_true_size))) { ret = -EFAULT; goto err_release_maps; } |