diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2021-11-02 16:20:58 +0300 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2021-11-02 16:20:58 +0300 |
commit | fc02cb2b37fe2cbf1d3334b9f0f0eab9431766c4 (patch) | |
tree | 93b16bc48fdc3be4a1adccbf4c7de92a5e8440e1 /kernel | |
parent | bfc484fe6abba4b89ec9330e0e68778e2a9856b2 (diff) | |
parent | 84882cf72cd774cf16fd338bdbf00f69ac9f9194 (diff) | |
download | linux-fc02cb2b37fe2cbf1d3334b9f0f0eab9431766c4.tar.xz |
Merge tag 'net-next-for-5.16' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next
Pull networking updates from Jakub Kicinski:
"Core:
- Remove socket skb caches
- Add a SO_RESERVE_MEM socket op to forward allocate buffer space and
avoid memory accounting overhead on each message sent
- Introduce managed neighbor entries - added by control plane and
resolved by the kernel for use in acceleration paths (BPF / XDP
right now, HW offload users will benefit as well)
- Make neighbor eviction on link down controllable by userspace to
work around WiFi networks with bad roaming implementations
- vrf: Rework interaction with netfilter/conntrack
- fq_codel: implement L4S style ce_threshold_ect1 marking
- sch: Eliminate unnecessary RCU waits in mini_qdisc_pair_swap()
BPF:
- Add support for new btf kind BTF_KIND_TAG, arbitrary type tagging
as implemented in LLVM14
- Introduce bpf_get_branch_snapshot() to capture Last Branch Records
- Implement variadic trace_printk helper
- Add a new Bloomfilter map type
- Track <8-byte scalar spill and refill
- Access hw timestamp through BPF's __sk_buff
- Disallow unprivileged BPF by default
- Document BPF licensing
Netfilter:
- Introduce egress hook for looking at raw outgoing packets
- Allow matching on and modifying inner headers / payload data
- Add NFT_META_IFTYPE to match on the interface type either from
ingress or egress
Protocols:
- Multi-Path TCP:
- increase default max additional subflows to 2
- rework forward memory allocation
- add getsockopts: MPTCP_INFO, MPTCP_TCPINFO, MPTCP_SUBFLOW_ADDRS
- MCTP flow support allowing lower layer drivers to configure msg
muxing as needed
- Automatic Multicast Tunneling (AMT) driver based on RFC7450
- HSR support the redbox supervision frames (IEC-62439-3:2018)
- Support for the ip6ip6 encapsulation of IOAM
- Netlink interface for CAN-FD's Transmitter Delay Compensation
- Support SMC-Rv2 eliminating the current same-subnet restriction, by
exploiting the UDP encapsulation feature of RoCE adapters
- TLS: add SM4 GCM/CCM crypto support
- Bluetooth: initial support for link quality and audio/codec offload
Driver APIs:
- Add a batched interface for RX buffer allocation in AF_XDP buffer
pool
- ethtool: Add ability to control transceiver modules' power mode
- phy: Introduce supported interfaces bitmap to express MAC
capabilities and simplify PHY code
- Drop rtnl_lock from DSA .port_fdb_{add,del} callbacks
New drivers:
- WiFi driver for Realtek 8852AE 802.11ax devices (rtw89)
- Ethernet driver for ASIX AX88796C SPI device (x88796c)
Drivers:
- Broadcom PHYs
- support 72165, 7712 16nm PHYs
- support IDDQ-SR for additional power savings
- PHY support for QCA8081, QCA9561 PHYs
- NXP DPAA2: support for IRQ coalescing
- NXP Ethernet (enetc): support for software TCP segmentation
- Renesas Ethernet (ravb) - support DMAC and EMAC blocks of
Gigabit-capable IP found on RZ/G2L SoC
- Intel 100G Ethernet
- support for eswitch offload of TC/OvS flow API, including
offload of GRE, VxLAN, Geneve tunneling
- support application device queues - ability to assign Rx and Tx
queues to application threads
- PTP and PPS (pulse-per-second) extensions
- Broadcom Ethernet (bnxt)
- devlink health reporting and device reload extensions
- Mellanox Ethernet (mlx5)
- offload macvlan interfaces
- support HW offload of TC rules involving OVS internal ports
- support HW-GRO and header/data split
- support application device queues
- Marvell OcteonTx2:
- add XDP support for PF
- add PTP support for VF
- Qualcomm Ethernet switch (qca8k): support for QCA8328
- Realtek Ethernet DSA switch (rtl8366rb)
- support bridge offload
- support STP, fast aging, disabling address learning
- support for Realtek RTL8365MB-VC, a 4+1 port 10M/100M/1GE switch
- Mellanox Ethernet/IB switch (mlxsw)
- multi-level qdisc hierarchy offload (e.g. RED, prio and shaping)
- offload root TBF qdisc as port shaper
- support multiple routing interface MAC address prefixes
- support for IP-in-IP with IPv6 underlay
- MediaTek WiFi (mt76)
- mt7921 - ASPM, 6GHz, SDIO and testmode support
- mt7915 - LED and TWT support
- Qualcomm WiFi (ath11k)
- include channel rx and tx time in survey dump statistics
- support for 80P80 and 160 MHz bandwidths
- support channel 2 in 6 GHz band
- spectral scan support for QCN9074
- support for rx decapsulation offload (data frames in 802.3
format)
- Qualcomm phone SoC WiFi (wcn36xx)
- enable Idle Mode Power Save (IMPS) to reduce power consumption
during idle
- Bluetooth driver support for MediaTek MT7922 and MT7921
- Enable support for AOSP Bluetooth extension in Qualcomm WCN399x and
Realtek 8822C/8852A
- Microsoft vNIC driver (mana)
- support hibernation and kexec
- Google vNIC driver (gve)
- support for jumbo frames
- implement Rx page reuse
Refactor:
- Make all writes to netdev->dev_addr go thru helpers, so that we can
add this address to the address rbtree and handle the updates
- Various TCP cleanups and optimizations including improvements to
CPU cache use
- Simplify the gnet_stats, Qdisc stats' handling and remove
qdisc->running sequence counter
- Driver changes and API updates to address devlink locking
deficiencies"
* tag 'net-next-for-5.16' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (2122 commits)
Revert "net: avoid double accounting for pure zerocopy skbs"
selftests: net: add arp_ndisc_evict_nocarrier
net: ndisc: introduce ndisc_evict_nocarrier sysctl parameter
net: arp: introduce arp_evict_nocarrier sysctl parameter
libbpf: Deprecate AF_XDP support
kbuild: Unify options for BTF generation for vmlinux and modules
selftests/bpf: Add a testcase for 64-bit bounds propagation issue.
bpf: Fix propagation of signed bounds from 64-bit min/max into 32-bit.
bpf: Fix propagation of bounds from 64-bit min/max into 32-bit and var_off.
net: vmxnet3: remove multiple false checks in vmxnet3_ethtool.c
net: avoid double accounting for pure zerocopy skbs
tcp: rename sk_wmem_free_skb
netdevsim: fix uninit value in nsim_drv_configure_vfs()
selftests/bpf: Fix also no-alu32 strobemeta selftest
bpf: Add missing map_delete_elem method to bloom filter map
selftests/bpf: Add bloom map success test for userspace calls
bpf: Add alignment padding for "map_extra" + consolidate holes
bpf: Bloom filter map naming fixups
selftests/bpf: Add test cases for struct_ops prog
bpf: Add dummy BPF STRUCT_OPS for test purpose
...
Diffstat (limited to 'kernel')
-rw-r--r-- | kernel/bpf/Kconfig | 7 | ||||
-rw-r--r-- | kernel/bpf/Makefile | 2 | ||||
-rw-r--r-- | kernel/bpf/arraymap.c | 7 | ||||
-rw-r--r-- | kernel/bpf/bloom_filter.c | 204 | ||||
-rw-r--r-- | kernel/bpf/bpf_struct_ops.c | 32 | ||||
-rw-r--r-- | kernel/bpf/bpf_struct_ops_types.h | 3 | ||||
-rw-r--r-- | kernel/bpf/btf.c | 183 | ||||
-rw-r--r-- | kernel/bpf/core.c | 9 | ||||
-rw-r--r-- | kernel/bpf/hashtab.c | 13 | ||||
-rw-r--r-- | kernel/bpf/helpers.c | 11 | ||||
-rw-r--r-- | kernel/bpf/preload/.gitignore | 4 | ||||
-rw-r--r-- | kernel/bpf/preload/Makefile | 26 | ||||
-rw-r--r-- | kernel/bpf/preload/iterators/Makefile | 38 | ||||
-rw-r--r-- | kernel/bpf/syscall.c | 77 | ||||
-rw-r--r-- | kernel/bpf/trampoline.c | 15 | ||||
-rw-r--r-- | kernel/bpf/verifier.c | 373 | ||||
-rw-r--r-- | kernel/events/core.c | 2 | ||||
-rw-r--r-- | kernel/trace/bpf_trace.c | 102 |
18 files changed, 948 insertions, 160 deletions
diff --git a/kernel/bpf/Kconfig b/kernel/bpf/Kconfig index a82d6de86522..d24d518ddd63 100644 --- a/kernel/bpf/Kconfig +++ b/kernel/bpf/Kconfig @@ -64,6 +64,7 @@ config BPF_JIT_DEFAULT_ON config BPF_UNPRIV_DEFAULT_OFF bool "Disable unprivileged BPF by default" + default y depends on BPF_SYSCALL help Disables unprivileged BPF by default by setting the corresponding @@ -72,6 +73,12 @@ config BPF_UNPRIV_DEFAULT_OFF disable it by setting it to 1 (from which no other transition to 0 is possible anymore). + Unprivileged BPF could be used to exploit certain potential + speculative execution side-channel vulnerabilities on unmitigated + affected hardware. + + If you are unsure how to answer this question, answer Y. + source "kernel/bpf/preload/Kconfig" config BPF_LSM diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile index 7f33098ca63f..cf6ca339f3cd 100644 --- a/kernel/bpf/Makefile +++ b/kernel/bpf/Makefile @@ -7,7 +7,7 @@ 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 -obj-$(CONFIG_BPF_SYSCALL) += hashtab.o arraymap.o percpu_freelist.o bpf_lru_list.o lpm_trie.o map_in_map.o +obj-$(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 obj-${CONFIG_BPF_LSM} += bpf_inode_storage.o diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c index 447def540544..c7a5be3bf8be 100644 --- a/kernel/bpf/arraymap.c +++ b/kernel/bpf/arraymap.c @@ -645,7 +645,7 @@ 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, void *callback_fn, +static int 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; @@ -668,9 +668,8 @@ static int bpf_for_each_array_elem(struct bpf_map *map, void *callback_fn, val = array->value + array->elem_size * i; num_elems++; key = i; - ret = BPF_CAST_CALL(callback_fn)((u64)(long)map, - (u64)(long)&key, (u64)(long)val, - (u64)(long)callback_ctx, 0); + ret = callback_fn((u64)(long)map, (u64)(long)&key, + (u64)(long)val, (u64)(long)callback_ctx, 0); /* return value: 0 - continue, 1 - stop and return */ if (ret) break; diff --git a/kernel/bpf/bloom_filter.c b/kernel/bpf/bloom_filter.c new file mode 100644 index 000000000000..277a05e9c984 --- /dev/null +++ b/kernel/bpf/bloom_filter.c @@ -0,0 +1,204 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2021 Facebook */ + +#include <linux/bitmap.h> +#include <linux/bpf.h> +#include <linux/btf.h> +#include <linux/err.h> +#include <linux/jhash.h> +#include <linux/random.h> + +#define BLOOM_CREATE_FLAG_MASK \ + (BPF_F_NUMA_NODE | BPF_F_ZERO_SEED | BPF_F_ACCESS_MASK) + +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[]; +}; + +static u32 hash(struct bpf_bloom_filter *bloom, void *value, + u32 value_size, u32 index) +{ + u32 h; + + if (bloom->aligned_u32_count) + h = jhash2(value, bloom->aligned_u32_count, + 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) +{ + struct bpf_bloom_filter *bloom = + container_of(map, struct bpf_bloom_filter, map); + u32 i, h; + + for (i = 0; i < bloom->nr_hash_funcs; i++) { + h = hash(bloom, value, map->value_size, i); + if (!test_bit(h, bloom->bitset)) + return -ENOENT; + } + + return 0; +} + +static int 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); + u32 i, h; + + if (flags != BPF_ANY) + return -EINVAL; + + for (i = 0; i < bloom->nr_hash_funcs; i++) { + h = hash(bloom, value, map->value_size, i); + set_bit(h, bloom->bitset); + } + + return 0; +} + +static int bloom_map_pop_elem(struct bpf_map *map, void *value) +{ + return -EOPNOTSUPP; +} + +static int bloom_map_delete_elem(struct bpf_map *map, void *value) +{ + return -EOPNOTSUPP; +} + +static struct bpf_map *bloom_map_alloc(union bpf_attr *attr) +{ + u32 bitset_bytes, bitset_mask, nr_hash_funcs, nr_bits; + int numa_node = bpf_map_attr_numa_node(attr); + struct bpf_bloom_filter *bloom; + + if (!bpf_capable()) + return ERR_PTR(-EPERM); + + if (attr->key_size != 0 || attr->value_size == 0 || + attr->max_entries == 0 || + attr->map_flags & ~BLOOM_CREATE_FLAG_MASK || + !bpf_map_flags_access_ok(attr->map_flags) || + /* The lower 4 bits of map_extra (0xF) specify the number + * of hash functions + */ + (attr->map_extra & ~0xF)) + return ERR_PTR(-EINVAL); + + nr_hash_funcs = attr->map_extra; + if (nr_hash_funcs == 0) + /* Default to using 5 hash functions if unspecified */ + nr_hash_funcs = 5; + + /* For the bloom filter, the optimal bit array size that minimizes the + * false positive probability is n * k / ln(2) where n is the number of + * expected entries in the bloom filter and k is the number of hash + * functions. We use 7 / 5 to approximate 1 / ln(2). + * + * We round this up to the nearest power of two to enable more efficient + * hashing using bitmasks. The bitmask will be the bit array size - 1. + * + * If this overflows a u32, the bit array size will have 2^32 (4 + * GB) bits. + */ + if (check_mul_overflow(attr->max_entries, nr_hash_funcs, &nr_bits) || + check_mul_overflow(nr_bits / 5, (u32)7, &nr_bits) || + nr_bits > (1UL << 31)) { + /* The bit array size is 2^32 bits but to avoid overflowing the + * u32, we use U32_MAX, which will round up to the equivalent + * number of bytes + */ + bitset_bytes = BITS_TO_BYTES(U32_MAX); + bitset_mask = U32_MAX; + } else { + if (nr_bits <= BITS_PER_LONG) + nr_bits = BITS_PER_LONG; + else + nr_bits = roundup_pow_of_two(nr_bits); + bitset_bytes = BITS_TO_BYTES(nr_bits); + bitset_mask = nr_bits - 1; + } + + bitset_bytes = roundup(bitset_bytes, sizeof(unsigned long)); + bloom = bpf_map_area_alloc(sizeof(*bloom) + bitset_bytes, numa_node); + + if (!bloom) + return ERR_PTR(-ENOMEM); + + bpf_map_init_from_attr(&bloom->map, 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_int(); + + return &bloom->map; +} + +static void bloom_map_free(struct bpf_map *map) +{ + struct bpf_bloom_filter *bloom = + container_of(map, struct bpf_bloom_filter, map); + + bpf_map_area_free(bloom); +} + +static void *bloom_map_lookup_elem(struct bpf_map *map, void *key) +{ + /* The eBPF program should use map_peek_elem instead */ + return ERR_PTR(-EINVAL); +} + +static int 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; +} + +static int bloom_map_check_btf(const struct bpf_map *map, + const struct btf *btf, + const struct btf_type *key_type, + const struct btf_type *value_type) +{ + /* Bloom filter maps are keyless */ + return btf_type_is_void(key_type) ? 0 : -EINVAL; +} + +static int bpf_bloom_map_btf_id; +const struct bpf_map_ops bloom_filter_map_ops = { + .map_meta_equal = bpf_map_meta_equal, + .map_alloc = bloom_map_alloc, + .map_free = bloom_map_free, + .map_push_elem = bloom_map_push_elem, + .map_peek_elem = bloom_map_peek_elem, + .map_pop_elem = bloom_map_pop_elem, + .map_lookup_elem = bloom_map_lookup_elem, + .map_update_elem = bloom_map_update_elem, + .map_delete_elem = bloom_map_delete_elem, + .map_check_btf = bloom_map_check_btf, + .map_btf_name = "bpf_bloom_filter", + .map_btf_id = &bpf_bloom_map_btf_id, +}; diff --git a/kernel/bpf/bpf_struct_ops.c b/kernel/bpf/bpf_struct_ops.c index 9abcc33f02cf..8ecfe4752769 100644 --- a/kernel/bpf/bpf_struct_ops.c +++ b/kernel/bpf/bpf_struct_ops.c @@ -93,6 +93,9 @@ const struct bpf_verifier_ops bpf_struct_ops_verifier_ops = { }; const struct bpf_prog_ops bpf_struct_ops_prog_ops = { +#ifdef CONFIG_NET + .test_run = bpf_struct_ops_test_run, +#endif }; static const struct btf_type *module_type; @@ -312,6 +315,20 @@ static int check_zero_holes(const struct btf_type *t, void *data) return 0; } +int bpf_struct_ops_prepare_trampoline(struct bpf_tramp_progs *tprogs, + struct bpf_prog *prog, + const struct btf_func_model *model, + void *image, void *image_end) +{ + u32 flags; + + tprogs[BPF_TRAMP_FENTRY].progs[0] = prog; + tprogs[BPF_TRAMP_FENTRY].nr_progs = 1; + flags = model->ret_size > 0 ? BPF_TRAMP_F_RET_FENTRY_RET : 0; + return arch_prepare_bpf_trampoline(NULL, image, image_end, + model, flags, tprogs, NULL); +} + static int bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key, void *value, u64 flags) { @@ -323,7 +340,7 @@ static int bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key, struct bpf_tramp_progs *tprogs = NULL; void *udata, *kdata; int prog_fd, err = 0; - void *image; + void *image, *image_end; u32 i; if (flags) @@ -363,12 +380,12 @@ static int bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key, udata = &uvalue->data; kdata = &kvalue->data; image = st_map->image; + image_end = st_map->image + PAGE_SIZE; for_each_member(i, t, member) { const struct btf_type *mtype, *ptype; struct bpf_prog *prog; u32 moff; - u32 flags; moff = btf_member_bit_offset(t, member) / 8; ptype = btf_type_resolve_ptr(btf_vmlinux, member->type, NULL); @@ -430,14 +447,9 @@ static int bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key, goto reset_unlock; } - tprogs[BPF_TRAMP_FENTRY].progs[0] = prog; - tprogs[BPF_TRAMP_FENTRY].nr_progs = 1; - flags = st_ops->func_models[i].ret_size > 0 ? - BPF_TRAMP_F_RET_FENTRY_RET : 0; - err = arch_prepare_bpf_trampoline(NULL, image, - st_map->image + PAGE_SIZE, - &st_ops->func_models[i], - flags, tprogs, NULL); + err = bpf_struct_ops_prepare_trampoline(tprogs, prog, + &st_ops->func_models[i], + image, image_end); if (err < 0) goto reset_unlock; diff --git a/kernel/bpf/bpf_struct_ops_types.h b/kernel/bpf/bpf_struct_ops_types.h index 066d83ea1c99..5678a9ddf817 100644 --- a/kernel/bpf/bpf_struct_ops_types.h +++ b/kernel/bpf/bpf_struct_ops_types.h @@ -2,6 +2,9 @@ /* internal file - do not include directly */ #ifdef CONFIG_BPF_JIT +#ifdef CONFIG_NET +BPF_STRUCT_OPS_TYPE(bpf_dummy_ops) +#endif #ifdef CONFIG_INET #include <net/tcp.h> BPF_STRUCT_OPS_TYPE(tcp_congestion_ops) diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index dfe61df4f974..dbc3ad07e21b 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -281,6 +281,7 @@ static const char * const btf_kind_str[NR_BTF_KINDS] = { [BTF_KIND_VAR] = "VAR", [BTF_KIND_DATASEC] = "DATASEC", [BTF_KIND_FLOAT] = "FLOAT", + [BTF_KIND_DECL_TAG] = "DECL_TAG", }; const char *btf_type_str(const struct btf_type *t) @@ -459,6 +460,17 @@ static bool btf_type_is_datasec(const struct btf_type *t) return BTF_INFO_KIND(t->info) == BTF_KIND_DATASEC; } +static bool btf_type_is_decl_tag(const struct btf_type *t) +{ + return BTF_INFO_KIND(t->info) == BTF_KIND_DECL_TAG; +} + +static bool btf_type_is_decl_tag_target(const struct btf_type *t) +{ + return btf_type_is_func(t) || btf_type_is_struct(t) || + btf_type_is_var(t) || btf_type_is_typedef(t); +} + u32 btf_nr_types(const struct btf *btf) { u32 total = 0; @@ -537,6 +549,7 @@ const struct btf_type *btf_type_resolve_func_ptr(const struct btf *btf, static bool btf_type_is_resolve_source_only(const struct btf_type *t) { return btf_type_is_var(t) || + btf_type_is_decl_tag(t) || btf_type_is_datasec(t); } @@ -563,6 +576,7 @@ static bool btf_type_needs_resolve(const struct btf_type *t) btf_type_is_struct(t) || btf_type_is_array(t) || btf_type_is_var(t) || + btf_type_is_decl_tag(t) || btf_type_is_datasec(t); } @@ -616,6 +630,11 @@ static const struct btf_var *btf_type_var(const struct btf_type *t) return (const struct btf_var *)(t + 1); } +static const struct btf_decl_tag *btf_type_decl_tag(const struct btf_type *t) +{ + return (const struct btf_decl_tag *)(t + 1); +} + static const struct btf_kind_operations *btf_type_ops(const struct btf_type *t) { return kind_ops[BTF_INFO_KIND(t->info)]; @@ -3801,6 +3820,110 @@ static const struct btf_kind_operations float_ops = { .show = btf_df_show, }; +static s32 btf_decl_tag_check_meta(struct btf_verifier_env *env, + const struct btf_type *t, + u32 meta_left) +{ + const struct btf_decl_tag *tag; + u32 meta_needed = sizeof(*tag); + s32 component_idx; + const char *value; + + if (meta_left < meta_needed) { + btf_verifier_log_basic(env, t, + "meta_left:%u meta_needed:%u", + meta_left, meta_needed); + return -EINVAL; + } + + value = btf_name_by_offset(env->btf, t->name_off); + if (!value || !value[0]) { + btf_verifier_log_type(env, t, "Invalid value"); + return -EINVAL; + } + + if (btf_type_vlen(t)) { + btf_verifier_log_type(env, t, "vlen != 0"); + return -EINVAL; + } + + if (btf_type_kflag(t)) { + btf_verifier_log_type(env, t, "Invalid btf_info kind_flag"); + return -EINVAL; + } + + component_idx = btf_type_decl_tag(t)->component_idx; + if (component_idx < -1) { + btf_verifier_log_type(env, t, "Invalid component_idx"); + return -EINVAL; + } + + btf_verifier_log_type(env, t, NULL); + + return meta_needed; +} + +static int btf_decl_tag_resolve(struct btf_verifier_env *env, + const struct resolve_vertex *v) +{ + const struct btf_type *next_type; + const struct btf_type *t = v->t; + u32 next_type_id = t->type; + struct btf *btf = env->btf; + s32 component_idx; + u32 vlen; + + next_type = btf_type_by_id(btf, next_type_id); + if (!next_type || !btf_type_is_decl_tag_target(next_type)) { + btf_verifier_log_type(env, v->t, "Invalid type_id"); + return -EINVAL; + } + + if (!env_type_is_resolve_sink(env, next_type) && + !env_type_is_resolved(env, next_type_id)) + return env_stack_push(env, next_type, next_type_id); + + component_idx = btf_type_decl_tag(t)->component_idx; + if (component_idx != -1) { + if (btf_type_is_var(next_type) || btf_type_is_typedef(next_type)) { + btf_verifier_log_type(env, v->t, "Invalid component_idx"); + return -EINVAL; + } + + if (btf_type_is_struct(next_type)) { + vlen = btf_type_vlen(next_type); + } else { + /* next_type should be a function */ + next_type = btf_type_by_id(btf, next_type->type); + vlen = btf_type_vlen(next_type); + } + + if ((u32)component_idx >= vlen) { + btf_verifier_log_type(env, v->t, "Invalid component_idx"); + return -EINVAL; + } + } + + env_stack_pop_resolved(env, next_type_id, 0); + + return 0; +} + +static void btf_decl_tag_log(struct btf_verifier_env *env, const struct btf_type *t) +{ + btf_verifier_log(env, "type=%u component_idx=%d", t->type, + btf_type_decl_tag(t)->component_idx); +} + +static const struct btf_kind_operations decl_tag_ops = { + .check_meta = btf_decl_tag_check_meta, + .resolve = btf_decl_tag_resolve, + .check_member = btf_df_check_member, + .check_kflag_member = btf_df_check_kflag_member, + .log_details = btf_decl_tag_log, + .show = btf_df_show, +}; + static int btf_func_proto_check(struct btf_verifier_env *env, const struct btf_type *t) { @@ -3935,6 +4058,7 @@ static const struct btf_kind_operations * const kind_ops[NR_BTF_KINDS] = { [BTF_KIND_VAR] = &var_ops, [BTF_KIND_DATASEC] = &datasec_ops, [BTF_KIND_FLOAT] = &float_ops, + [BTF_KIND_DECL_TAG] = &decl_tag_ops, }; static s32 btf_check_meta(struct btf_verifier_env *env, @@ -4019,6 +4143,10 @@ static bool btf_resolve_valid(struct btf_verifier_env *env, return !btf_resolved_type_id(btf, type_id) && !btf_resolved_type_size(btf, type_id); + if (btf_type_is_decl_tag(t)) + return btf_resolved_type_id(btf, type_id) && + !btf_resolved_type_size(btf, type_id); + if (btf_type_is_modifier(t) || btf_type_is_ptr(t) || btf_type_is_var(t)) { t = btf_type_id_resolve(btf, &type_id); @@ -6215,3 +6343,58 @@ const struct bpf_func_proto bpf_btf_find_by_name_kind_proto = { }; BTF_ID_LIST_GLOBAL_SINGLE(btf_task_struct_ids, struct, task_struct) + +/* BTF ID set registration API for modules */ + +struct kfunc_btf_id_list { + struct list_head list; + struct mutex mutex; +}; + +#ifdef CONFIG_DEBUG_INFO_BTF_MODULES + +void register_kfunc_btf_id_set(struct kfunc_btf_id_list *l, + struct kfunc_btf_id_set *s) +{ + mutex_lock(&l->mutex); + list_add(&s->list, &l->list); + mutex_unlock(&l->mutex); +} +EXPORT_SYMBOL_GPL(register_kfunc_btf_id_set); + +void unregister_kfunc_btf_id_set(struct kfunc_btf_id_list *l, + struct kfunc_btf_id_set *s) +{ + mutex_lock(&l->mutex); + list_del_init(&s->list); + mutex_unlock(&l->mutex); +} +EXPORT_SYMBOL_GPL(unregister_kfunc_btf_id_set); + +bool bpf_check_mod_kfunc_call(struct kfunc_btf_id_list *klist, u32 kfunc_id, + struct module *owner) +{ + struct kfunc_btf_id_set *s; + + if (!owner) + return false; + mutex_lock(&klist->mutex); + list_for_each_entry(s, &klist->list, list) { + if (s->owner == owner && btf_id_set_contains(s->set, kfunc_id)) { + mutex_unlock(&klist->mutex); + return true; + } + } + mutex_unlock(&klist->mutex); + return false; +} + +#endif + +#define DEFINE_KFUNC_BTF_ID_LIST(name) \ + struct kfunc_btf_id_list name = { LIST_HEAD_INIT(name.list), \ + __MUTEX_INITIALIZER(name.mutex) }; \ + EXPORT_SYMBOL_GPL(name) + +DEFINE_KFUNC_BTF_ID_LIST(bpf_tcp_ca_kfunc_list); +DEFINE_KFUNC_BTF_ID_LIST(prog_test_kfunc_list); diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 6e3ae90ad107..327e3996eadb 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -32,6 +32,7 @@ #include <linux/perf_event.h> #include <linux/extable.h> #include <linux/log2.h> +#include <linux/bpf_verifier.h> #include <asm/barrier.h> #include <asm/unaligned.h> @@ -2263,6 +2264,9 @@ static void bpf_prog_free_deferred(struct work_struct *work) int i; aux = container_of(work, struct bpf_prog_aux, work); +#ifdef CONFIG_BPF_SYSCALL + bpf_free_kfunc_btf_tab(aux->kfunc_btf_tab); +#endif bpf_free_used_maps(aux); bpf_free_used_btfs(aux); if (bpf_prog_is_dev_bound(aux)) @@ -2365,6 +2369,11 @@ const struct bpf_func_proto * __weak bpf_get_trace_printk_proto(void) return NULL; } +const struct bpf_func_proto * __weak bpf_get_trace_vprintk_proto(void) +{ + return NULL; +} + u64 __weak bpf_event_output(struct bpf_map *map, u64 flags, void *meta, u64 meta_size, void *ctx, u64 ctx_size, bpf_ctx_copy_t ctx_copy) diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index 32471ba02708..d29af9988f37 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -668,7 +668,7 @@ static int htab_map_gen_lookup(struct bpf_map *map, struct bpf_insn *insn_buf) BUILD_BUG_ON(!__same_type(&__htab_map_lookup_elem, (void *(*)(struct bpf_map *map, void *key))NULL)); - *insn++ = BPF_EMIT_CALL(BPF_CAST_CALL(__htab_map_lookup_elem)); + *insn++ = BPF_EMIT_CALL(__htab_map_lookup_elem); *insn++ = BPF_JMP_IMM(BPF_JEQ, ret, 0, 1); *insn++ = BPF_ALU64_IMM(BPF_ADD, ret, offsetof(struct htab_elem, key) + @@ -709,7 +709,7 @@ static int htab_lru_map_gen_lookup(struct bpf_map *map, BUILD_BUG_ON(!__same_type(&__htab_map_lookup_elem, (void *(*)(struct bpf_map *map, void *key))NULL)); - *insn++ = BPF_EMIT_CALL(BPF_CAST_CALL(__htab_map_lookup_elem)); + *insn++ = BPF_EMIT_CALL(__htab_map_lookup_elem); *insn++ = BPF_JMP_IMM(BPF_JEQ, ret, 0, 4); *insn++ = BPF_LDX_MEM(BPF_B, ref_reg, ret, offsetof(struct htab_elem, lru_node) + @@ -2049,7 +2049,7 @@ 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, void *callback_fn, +static int 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); @@ -2089,9 +2089,8 @@ static int bpf_for_each_hash_elem(struct bpf_map *map, void *callback_fn, val = elem->key + roundup_key_size; } num_elems++; - ret = BPF_CAST_CALL(callback_fn)((u64)(long)map, - (u64)(long)key, (u64)(long)val, - (u64)(long)callback_ctx, 0); + ret = callback_fn((u64)(long)map, (u64)(long)key, + (u64)(long)val, (u64)(long)callback_ctx, 0); /* return value: 0 - continue, 1 - stop and return */ if (ret) { rcu_read_unlock(); @@ -2397,7 +2396,7 @@ static int htab_of_map_gen_lookup(struct bpf_map *map, BUILD_BUG_ON(!__same_type(&__htab_map_lookup_elem, (void *(*)(struct bpf_map *map, void *key))NULL)); - *insn++ = BPF_EMIT_CALL(BPF_CAST_CALL(__htab_map_lookup_elem)); + *insn++ = BPF_EMIT_CALL(__htab_map_lookup_elem); *insn++ = BPF_JMP_IMM(BPF_JEQ, ret, 0, 2); *insn++ = BPF_ALU64_IMM(BPF_ADD, ret, offsetof(struct htab_elem, key) + diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index 9aabf84afd4b..1ffd469c217f 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -979,15 +979,13 @@ out: return err; } -#define MAX_SNPRINTF_VARARGS 12 - BPF_CALL_5(bpf_snprintf, char *, str, u32, str_size, char *, fmt, const void *, data, u32, data_len) { int err, num_args; u32 *bin_args; - if (data_len % 8 || data_len > MAX_SNPRINTF_VARARGS * 8 || + if (data_len % 8 || data_len > MAX_BPRINTF_VARARGS * 8 || (data_len && !data)) return -EINVAL; num_args = data_len / 8; @@ -1058,7 +1056,7 @@ static enum hrtimer_restart bpf_timer_cb(struct hrtimer *hrtimer) struct bpf_hrtimer *t = container_of(hrtimer, struct bpf_hrtimer, timer); struct bpf_map *map = t->map; void *value = t->value; - void *callback_fn; + bpf_callback_t callback_fn; void *key; u32 idx; @@ -1083,8 +1081,7 @@ static enum hrtimer_restart bpf_timer_cb(struct hrtimer *hrtimer) key = value - round_up(map->key_size, 8); } - BPF_CAST_CALL(callback_fn)((u64)(long)map, (u64)(long)key, - (u64)(long)value, 0, 0); + callback_fn((u64)(long)map, (u64)(long)key, (u64)(long)value, 0, 0); /* The verifier checked that return value is zero. */ this_cpu_write(hrtimer_running, NULL); @@ -1437,6 +1434,8 @@ bpf_base_func_proto(enum bpf_func_id func_id) return &bpf_snprintf_proto; case BPF_FUNC_task_pt_regs: return &bpf_task_pt_regs_proto; + case BPF_FUNC_trace_vprintk: + return bpf_get_trace_vprintk_proto(); default: return NULL; } diff --git a/kernel/bpf/preload/.gitignore b/kernel/bpf/preload/.gitignore index 856a4c5ad0dd..9452322902a5 100644 --- a/kernel/bpf/preload/.gitignore +++ b/kernel/bpf/preload/.gitignore @@ -1,4 +1,2 @@ -/FEATURE-DUMP.libbpf -/bpf_helper_defs.h -/feature +/libbpf /bpf_preload_umd diff --git a/kernel/bpf/preload/Makefile b/kernel/bpf/preload/Makefile index 1951332dd15f..1400ac58178e 100644 --- a/kernel/bpf/preload/Makefile +++ b/kernel/bpf/preload/Makefile @@ -1,21 +1,35 @@ # SPDX-License-Identifier: GPL-2.0 LIBBPF_SRCS = $(srctree)/tools/lib/bpf/ -LIBBPF_A = $(obj)/libbpf.a -LIBBPF_OUT = $(abspath $(obj)) +LIBBPF_OUT = $(abspath $(obj))/libbpf +LIBBPF_A = $(LIBBPF_OUT)/libbpf.a +LIBBPF_DESTDIR = $(LIBBPF_OUT) +LIBBPF_INCLUDE = $(LIBBPF_DESTDIR)/include # Although not in use by libbpf's Makefile, set $(O) so that the "dummy" test # in tools/scripts/Makefile.include always succeeds when building the kernel # with $(O) pointing to a relative path, as in "make O=build bindeb-pkg". -$(LIBBPF_A): - $(Q)$(MAKE) -C $(LIBBPF_SRCS) O=$(LIBBPF_OUT)/ OUTPUT=$(LIBBPF_OUT)/ $(LIBBPF_OUT)/libbpf.a +$(LIBBPF_A): | $(LIBBPF_OUT) + $(Q)$(MAKE) -C $(LIBBPF_SRCS) O=$(LIBBPF_OUT)/ OUTPUT=$(LIBBPF_OUT)/ \ + DESTDIR=$(LIBBPF_DESTDIR) prefix= \ + $(LIBBPF_OUT)/libbpf.a install_headers + +libbpf_hdrs: $(LIBBPF_A) + +.PHONY: libbpf_hdrs + +$(LIBBPF_OUT): + $(call msg,MKDIR,$@) + $(Q)mkdir -p $@ userccflags += -I $(srctree)/tools/include/ -I $(srctree)/tools/include/uapi \ - -I $(srctree)/tools/lib/ -Wno-unused-result + -I $(LIBBPF_INCLUDE) -Wno-unused-result userprogs := bpf_preload_umd -clean-files := $(userprogs) bpf_helper_defs.h FEATURE-DUMP.libbpf staticobjs/ feature/ +clean-files := libbpf/ + +$(obj)/iterators/iterators.o: | libbpf_hdrs bpf_preload_umd-objs := iterators/iterators.o bpf_preload_umd-userldlibs := $(LIBBPF_A) -lelf -lz diff --git a/kernel/bpf/preload/iterators/Makefile b/kernel/bpf/preload/iterators/Makefile index 28fa8c1440f4..b8bd60511227 100644 --- a/kernel/bpf/preload/iterators/Makefile +++ b/kernel/bpf/preload/iterators/Makefile @@ -1,18 +1,26 @@ # SPDX-License-Identifier: GPL-2.0 OUTPUT := .output +abs_out := $(abspath $(OUTPUT)) + CLANG ?= clang LLC ?= llc LLVM_STRIP ?= llvm-strip + +TOOLS_PATH := $(abspath ../../../../tools) +BPFTOOL_SRC := $(TOOLS_PATH)/bpf/bpftool +BPFTOOL_OUTPUT := $(abs_out)/bpftool DEFAULT_BPFTOOL := $(OUTPUT)/sbin/bpftool BPFTOOL ?= $(DEFAULT_BPFTOOL) -LIBBPF_SRC := $(abspath ../../../../tools/lib/bpf) -BPFOBJ := $(OUTPUT)/libbpf.a -BPF_INCLUDE := $(OUTPUT) -INCLUDES := -I$(OUTPUT) -I$(BPF_INCLUDE) -I$(abspath ../../../../tools/lib) \ - -I$(abspath ../../../../tools/include/uapi) + +LIBBPF_SRC := $(TOOLS_PATH)/lib/bpf +LIBBPF_OUTPUT := $(abs_out)/libbpf +LIBBPF_DESTDIR := $(LIBBPF_OUTPUT) +LIBBPF_INCLUDE := $(LIBBPF_DESTDIR)/include +BPFOBJ := $(LIBBPF_OUTPUT)/libbpf.a + +INCLUDES := -I$(OUTPUT) -I$(LIBBPF_INCLUDE) -I$(TOOLS_PATH)/include/uapi CFLAGS := -g -Wall -abs_out := $(abspath $(OUTPUT)) ifeq ($(V),1) Q = msg = @@ -44,14 +52,18 @@ $(OUTPUT)/iterators.bpf.o: iterators.bpf.c $(BPFOBJ) | $(OUTPUT) -c $(filter %.c,$^) -o $@ && \ $(LLVM_STRIP) -g $@ -$(OUTPUT): +$(OUTPUT) $(LIBBPF_OUTPUT) $(BPFTOOL_OUTPUT): $(call msg,MKDIR,$@) - $(Q)mkdir -p $(OUTPUT) + $(Q)mkdir -p $@ -$(BPFOBJ): $(wildcard $(LIBBPF_SRC)/*.[ch] $(LIBBPF_SRC)/Makefile) | $(OUTPUT) +$(BPFOBJ): $(wildcard $(LIBBPF_SRC)/*.[ch] $(LIBBPF_SRC)/Makefile) | $(LIBBPF_OUTPUT) $(Q)$(MAKE) $(submake_extras) -C $(LIBBPF_SRC) \ - OUTPUT=$(abspath $(dir $@))/ $(abspath $@) + OUTPUT=$(abspath $(dir $@))/ prefix= \ + DESTDIR=$(LIBBPF_DESTDIR) $(abspath $@) install_headers -$(DEFAULT_BPFTOOL): - $(Q)$(MAKE) $(submake_extras) -C ../../../../tools/bpf/bpftool \ - prefix= OUTPUT=$(abs_out)/ DESTDIR=$(abs_out) install +$(DEFAULT_BPFTOOL): $(BPFOBJ) | $(BPFTOOL_OUTPUT) + $(Q)$(MAKE) $(submake_extras) -C $(BPFTOOL_SRC) \ + OUTPUT=$(BPFTOOL_OUTPUT)/ \ + LIBBPF_OUTPUT=$(LIBBPF_OUTPUT)/ \ + LIBBPF_DESTDIR=$(LIBBPF_DESTDIR)/ \ + prefix= DESTDIR=$(abs_out)/ install-bin diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 1cad6979a0d0..50f96ea4452a 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -199,7 +199,8 @@ static int bpf_map_update_value(struct bpf_map *map, struct fd f, void *key, err = bpf_fd_reuseport_array_update_elem(map, key, value, flags); } else if (map->map_type == BPF_MAP_TYPE_QUEUE || - map->map_type == BPF_MAP_TYPE_STACK) { + map->map_type == BPF_MAP_TYPE_STACK || + map->map_type == BPF_MAP_TYPE_BLOOM_FILTER) { err = map->ops->map_push_elem(map, value, flags); } else { rcu_read_lock(); @@ -238,7 +239,8 @@ static int bpf_map_copy_value(struct bpf_map *map, void *key, void *value, } else if (map->map_type == BPF_MAP_TYPE_REUSEPORT_SOCKARRAY) { err = bpf_fd_reuseport_array_lookup_elem(map, key, value); } else if (map->map_type == BPF_MAP_TYPE_QUEUE || - map->map_type == BPF_MAP_TYPE_STACK) { + map->map_type == BPF_MAP_TYPE_STACK || + map->map_type == BPF_MAP_TYPE_BLOOM_FILTER) { err = map->ops->map_peek_elem(map, value); } else if (map->map_type == BPF_MAP_TYPE_STRUCT_OPS) { /* struct_ops map requires directly updating "value" */ @@ -348,6 +350,7 @@ void bpf_map_init_from_attr(struct bpf_map *map, union bpf_attr *attr) map->max_entries = attr->max_entries; map->map_flags = bpf_map_flags_retain_permanent(attr->map_flags); map->numa_node = bpf_map_attr_numa_node(attr); + map->map_extra = attr->map_extra; } static int bpf_map_alloc_id(struct bpf_map *map) @@ -555,6 +558,7 @@ static void bpf_map_show_fdinfo(struct seq_file *m, struct file *filp) "value_size:\t%u\n" "max_entries:\t%u\n" "map_flags:\t%#x\n" + "map_extra:\t%#llx\n" "memlock:\t%lu\n" "map_id:\t%u\n" "frozen:\t%u\n", @@ -563,6 +567,7 @@ static void bpf_map_show_fdinfo(struct seq_file *m, struct file *filp) map->value_size, map->max_entries, map->map_flags, + (unsigned long long)map->map_extra, bpf_map_memory_footprint(map), map->id, READ_ONCE(map->frozen)); @@ -812,7 +817,7 @@ static int map_check_btf(struct bpf_map *map, const struct btf *btf, return ret; } -#define BPF_MAP_CREATE_LAST_FIELD btf_vmlinux_value_type_id +#define BPF_MAP_CREATE_LAST_FIELD map_extra /* called via syscall */ static int map_create(union bpf_attr *attr) { @@ -833,6 +838,10 @@ static int map_create(union bpf_attr *attr) return -EINVAL; } + if (attr->map_type != BPF_MAP_TYPE_BLOOM_FILTER && + attr->map_extra != 0) + return -EINVAL; + f_flags = bpf_get_file_flag(attr->map_flags); if (f_flags < 0) return f_flags; @@ -1082,6 +1091,14 @@ static int map_lookup_elem(union bpf_attr *attr) if (!value) goto free_key; + if (map->map_type == BPF_MAP_TYPE_BLOOM_FILTER) { + if (copy_from_user(value, uvalue, value_size)) + err = -EFAULT; + else + err = bpf_map_copy_value(map, key, value, attr->flags); + goto free_value; + } + err = bpf_map_copy_value(map, key, value, attr->flags); if (err) goto free_value; @@ -1807,8 +1824,14 @@ static int bpf_prog_release(struct inode *inode, struct file *filp) return 0; } +struct bpf_prog_kstats { + u64 nsecs; + u64 cnt; + u64 misses; +}; + static void bpf_prog_get_stats(const struct bpf_prog *prog, - struct bpf_prog_stats *stats) + struct bpf_prog_kstats *stats) { u64 nsecs = 0, cnt = 0, misses = 0; int cpu; @@ -1821,9 +1844,9 @@ static void bpf_prog_get_stats(const struct bpf_prog *prog, st = per_cpu_ptr(prog->stats, cpu); do { start = u64_stats_fetch_begin_irq(&st->syncp); - tnsecs = st->nsecs; - tcnt = st->cnt; - tmisses = st->misses; + tnsecs = u64_stats_read(&st->nsecs); + tcnt = u64_stats_read(&st->cnt); + tmisses = u64_stats_read(&st->misses); } while (u64_stats_fetch_retry_irq(&st->syncp, start)); nsecs += tnsecs; cnt += tcnt; @@ -1839,7 +1862,7 @@ static void bpf_prog_show_fdinfo(struct seq_file *m, struct file *filp) { const struct bpf_prog *prog = filp->private_data; char prog_tag[sizeof(prog->tag) * 2 + 1] = { }; - struct bpf_prog_stats stats; + struct bpf_prog_kstats stats; bpf_prog_get_stats(prog, &stats); bin2hex(prog_tag, prog->tag, sizeof(prog->tag)); @@ -1851,7 +1874,8 @@ static void bpf_prog_show_fdinfo(struct seq_file *m, struct file *filp) "prog_id:\t%u\n" "run_time_ns:\t%llu\n" "run_cnt:\t%llu\n" - "recursion_misses:\t%llu\n", + "recursion_misses:\t%llu\n" + "verified_insns:\t%u\n", prog->type, prog->jited, prog_tag, @@ -1859,7 +1883,8 @@ static void bpf_prog_show_fdinfo(struct seq_file *m, struct file *filp) prog->aux->id, stats.nsecs, stats.cnt, - stats.misses); + stats.misses, + prog->aux->verified_insns); } #endif @@ -3578,7 +3603,7 @@ static int bpf_prog_get_info_by_fd(struct file *file, struct bpf_prog_info __user *uinfo = u64_to_user_ptr(attr->info.info); struct bpf_prog_info info; u32 info_len = attr->info.info_len; - struct bpf_prog_stats stats; + struct bpf_prog_kstats stats; char __user *uinsns; u32 ulen; int err; @@ -3628,6 +3653,8 @@ static int bpf_prog_get_info_by_fd(struct file *file, info.run_cnt = stats.cnt; info.recursion_misses = stats.misses; + info.verified_insns = prog->aux->verified_insns; + if (!bpf_capable()) { info.jited_prog_len = 0; info.xlated_prog_len = 0; @@ -3874,6 +3901,7 @@ static int bpf_map_get_info_by_fd(struct file *file, info.value_size = map->value_size; info.max_entries = map->max_entries; info.map_flags = map->map_flags; + info.map_extra = map->map_extra; memcpy(info.name, map->name, sizeof(map->name)); if (map->btf) { @@ -4756,6 +4784,31 @@ static const struct bpf_func_proto bpf_sys_close_proto = { .arg1_type = ARG_ANYTHING, }; +BPF_CALL_4(bpf_kallsyms_lookup_name, const char *, name, int, name_sz, int, flags, u64 *, res) +{ + if (flags) + return -EINVAL; + + if (name_sz <= 1 || name[name_sz - 1]) + return -EINVAL; + + if (!bpf_dump_raw_ok(current_cred())) + return -EPERM; + + *res = kallsyms_lookup_name(name); + return *res ? 0 : -ENOENT; +} + +const struct bpf_func_proto bpf_kallsyms_lookup_name_proto = { + .func = bpf_kallsyms_lookup_name, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_MEM, + .arg2_type = ARG_CONST_SIZE, + .arg3_type = ARG_ANYTHING, + .arg4_type = ARG_PTR_TO_LONG, +}; + static const struct bpf_func_proto * syscall_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { @@ -4766,6 +4819,8 @@ syscall_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_btf_find_by_name_kind_proto; case BPF_FUNC_sys_close: return &bpf_sys_close_proto; + case BPF_FUNC_kallsyms_lookup_name: + return &bpf_kallsyms_lookup_name_proto; default: return tracing_prog_func_proto(func_id, prog); } diff --git a/kernel/bpf/trampoline.c b/kernel/bpf/trampoline.c index fe1e857324e6..e98de5e73ba5 100644 --- a/kernel/bpf/trampoline.c +++ b/kernel/bpf/trampoline.c @@ -10,6 +10,7 @@ #include <linux/rcupdate_trace.h> #include <linux/rcupdate_wait.h> #include <linux/module.h> +#include <linux/static_call.h> /* dummy _ops. The verifier will operate on target program's ops. */ const struct bpf_verifier_ops bpf_extension_verifier_ops = { @@ -526,7 +527,7 @@ out: } #define NO_START_TIME 1 -static u64 notrace bpf_prog_start_time(void) +static __always_inline u64 notrace bpf_prog_start_time(void) { u64 start = NO_START_TIME; @@ -544,7 +545,7 @@ static void notrace inc_misses_counter(struct bpf_prog *prog) stats = this_cpu_ptr(prog->stats); u64_stats_update_begin(&stats->syncp); - stats->misses++; + u64_stats_inc(&stats->misses); u64_stats_update_end(&stats->syncp); } @@ -585,11 +586,13 @@ static void notrace update_prog_stats(struct bpf_prog *prog, * Hence check that 'start' is valid. */ start > NO_START_TIME) { + unsigned long flags; + stats = this_cpu_ptr(prog->stats); - u64_stats_update_begin(&stats->syncp); - stats->cnt++; - stats->nsecs += sched_clock() - start; - u64_stats_update_end(&stats->syncp); + flags = u64_stats_update_begin_irqsave(&stats->syncp); + u64_stats_inc(&stats->cnt); + u64_stats_add(&stats->nsecs, sched_clock() - start); + u64_stats_update_end_irqrestore(&stats->syncp, flags); } } diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index de006552be8a..f0dca726ebfd 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -612,6 +612,20 @@ static const char *kernel_type_name(const struct btf* btf, u32 id) return btf_name_by_offset(btf, btf_type_by_id(btf, id)->name_off); } +/* The reg state of a pointer or a bounded scalar was saved when + * it was spilled to the stack. + */ +static bool is_spilled_reg(const struct bpf_stack_state *stack) +{ + return stack->slot_type[BPF_REG_SIZE - 1] == STACK_SPILL; +} + +static void scrub_spilled_slot(u8 *stype) +{ + if (*stype != STACK_INVALID) + *stype = STACK_MISC; +} + static void print_verifier_state(struct bpf_verifier_env *env, const struct bpf_func_state *state) { @@ -717,7 +731,7 @@ static void print_verifier_state(struct bpf_verifier_env *env, continue; verbose(env, " fp%d", (-i - 1) * BPF_REG_SIZE); print_liveness(env, state->stack[i].spilled_ptr.live); - if (state->stack[i].slot_type[0] == STACK_SPILL) { + if (is_spilled_reg(&state->stack[i])) { reg = &state->stack[i].spilled_ptr; t = reg->type; verbose(env, "=%s", reg_type_str[t]); @@ -1406,12 +1420,12 @@ static void __reg_combine_32_into_64(struct bpf_reg_state *reg) static bool __reg64_bound_s32(s64 a) { - return a > S32_MIN && a < S32_MAX; + return a >= S32_MIN && a <= S32_MAX; } static bool __reg64_bound_u32(u64 a) { - return a > U32_MIN && a < U32_MAX; + return a >= U32_MIN && a <= U32_MAX; } static void __reg_combine_64_into_32(struct bpf_reg_state *reg) @@ -1626,52 +1640,168 @@ static int add_subprog(struct bpf_verifier_env *env, int off) return env->subprog_cnt - 1; } +#define MAX_KFUNC_DESCS 256 +#define MAX_KFUNC_BTFS 256 + struct bpf_kfunc_desc { struct btf_func_model func_model; u32 func_id; s32 imm; + u16 offset; +}; + +struct bpf_kfunc_btf { + struct btf *btf; + struct module *module; + u16 offset; }; -#define MAX_KFUNC_DESCS 256 struct bpf_kfunc_desc_tab { struct bpf_kfunc_desc descs[MAX_KFUNC_DESCS]; u32 nr_descs; }; -static int kfunc_desc_cmp_by_id(const void *a, const void *b) +struct bpf_kfunc_btf_tab { + struct bpf_kfunc_btf descs[MAX_KFUNC_BTFS]; + u32 nr_descs; +}; + +static int kfunc_desc_cmp_by_id_off(const void *a, const void *b) { const struct bpf_kfunc_desc *d0 = a; const struct bpf_kfunc_desc *d1 = b; /* func_id is not greater than BTF_MAX_TYPE */ - return d0->func_id - d1->func_id; + return d0->func_id - d1->func_id ?: d0->offset - d1->offset; +} + +static int kfunc_btf_cmp_by_off(const void *a, const void *b) +{ + const struct bpf_kfunc_btf *d0 = a; + const struct bpf_kfunc_btf *d1 = b; + + return d0->offset - d1->offset; } static const struct bpf_kfunc_desc * -find_kfunc_desc(const struct bpf_prog *prog, u32 func_id) +find_kfunc_desc(const struct bpf_prog *prog, u32 func_id, u16 offset) { struct bpf_kfunc_desc desc = { .func_id = func_id, + .offset = offset, }; struct bpf_kfunc_desc_tab *tab; tab = prog->aux->kfunc_tab; return bsearch(&desc, tab->descs, tab->nr_descs, - sizeof(tab->descs[0]), kfunc_desc_cmp_by_id); + sizeof(tab->descs[0]), kfunc_desc_cmp_by_id_off); +} + +static struct btf *__find_kfunc_desc_btf(struct bpf_verifier_env *env, + s16 offset, struct module **btf_modp) +{ + struct bpf_kfunc_btf kf_btf = { .offset = offset }; + struct bpf_kfunc_btf_tab *tab; + struct bpf_kfunc_btf *b; + struct module *mod; + struct btf *btf; + int btf_fd; + + tab = env->prog->aux->kfunc_btf_tab; + b = bsearch(&kf_btf, tab->descs, tab->nr_descs, + sizeof(tab->descs[0]), kfunc_btf_cmp_by_off); + if (!b) { + if (tab->nr_descs == MAX_KFUNC_BTFS) { + verbose(env, "too many different module BTFs\n"); + return ERR_PTR(-E2BIG); + } + + if (bpfptr_is_null(env->fd_array)) { + verbose(env, "kfunc offset > 0 without fd_array is invalid\n"); + return ERR_PTR(-EPROTO); + } + + if (copy_from_bpfptr_offset(&btf_fd, env->fd_array, + offset * sizeof(btf_fd), + sizeof(btf_fd))) + return ERR_PTR(-EFAULT); + + btf = btf_get_by_fd(btf_fd); + if (IS_ERR(btf)) { + verbose(env, "invalid module BTF fd specified\n"); + return btf; + } + + if (!btf_is_module(btf)) { + verbose(env, "BTF fd for kfunc is not a module BTF\n"); + btf_put(btf); + return ERR_PTR(-EINVAL); + } + + mod = btf_try_get_module(btf); + if (!mod) { + btf_put(btf); + return ERR_PTR(-ENXIO); + } + + b = &tab->descs[tab->nr_descs++]; + b->btf = btf; + b->module = mod; + b->offset = offset; + + sort(tab->descs, tab->nr_descs, sizeof(tab->descs[0]), + kfunc_btf_cmp_by_off, NULL); + } + if (btf_modp) + *btf_modp = b->module; + return b->btf; +} + +void bpf_free_kfunc_btf_tab(struct bpf_kfunc_btf_tab *tab) +{ + if (!tab) + return; + + while (tab->nr_descs--) { + module_put(tab->descs[tab->nr_descs].module); + btf_put(tab->descs[tab->nr_descs].btf); + } + kfree(tab); +} + +static struct btf *find_kfunc_desc_btf(struct bpf_verifier_env *env, + u32 func_id, s16 offset, + struct module **btf_modp) +{ + if (offset) { + if (offset < 0) { + /* In the future, this can be allowed to increase limit + * of fd index into fd_array, interpreted as u16. + */ + verbose(env, "negative offset disallowed for kernel module function call\n"); + return ERR_PTR(-EINVAL); + } + + return __find_kfunc_desc_btf(env, offset, btf_modp); + } + return btf_vmlinux ?: ERR_PTR(-ENOENT); } -static int add_kfunc_call(struct bpf_verifier_env *env, u32 func_id) +static int add_kfunc_call(struct bpf_verifier_env *env, u32 func_id, s16 offset) { const struct btf_type *func, *func_proto; + struct bpf_kfunc_btf_tab *btf_tab; struct bpf_kfunc_desc_tab *tab; struct bpf_prog_aux *prog_aux; struct bpf_kfunc_desc *desc; const char *func_name; + struct btf *desc_btf; unsigned long addr; int err; prog_aux = env->prog->aux; tab = prog_aux->kfunc_tab; + btf_tab = prog_aux->kfunc_btf_tab; if (!tab) { if (!btf_vmlinux) { verbose(env, "calling kernel function is not supported without CONFIG_DEBUG_INFO_BTF\n"); @@ -1699,7 +1829,29 @@ static int add_kfunc_call(struct bpf_verifier_env *env, u32 func_id) prog_aux->kfunc_tab = tab; } - if (find_kfunc_desc(env->prog, func_id)) + /* func_id == 0 is always invalid, but instead of returning an error, be + * conservative and wait until the code elimination pass before returning + * error, so that invalid calls that get pruned out can be in BPF programs + * loaded from userspace. It is also required that offset be untouched + * for such calls. + */ + if (!func_id && !offset) + return 0; + + if (!btf_tab && offset) { + btf_tab = kzalloc(sizeof(*btf_tab), GFP_KERNEL); + if (!btf_tab) + return -ENOMEM; + prog_aux->kfunc_btf_tab = btf_tab; + } + + desc_btf = find_kfunc_desc_btf(env, func_id, offset, NULL); + if (IS_ERR(desc_btf)) { + verbose(env, "failed to find BTF for kernel function\n"); + return PTR_ERR(desc_btf); + } + + if (find_kfunc_desc(env->prog, func_id, offset)) return 0; if (tab->nr_descs == MAX_KFUNC_DESCS) { @@ -1707,20 +1859,20 @@ static int add_kfunc_call(struct bpf_verifier_env *env, u32 func_id) return -E2BIG; } - func = btf_type_by_id(btf_vmlinux, func_id); + func = btf_type_by_id(desc_btf, func_id); if (!func || !btf_type_is_func(func)) { verbose(env, "kernel btf_id %u is not a function\n", func_id); return -EINVAL; } - func_proto = btf_type_by_id(btf_vmlinux, func->type); + func_proto = btf_type_by_id(desc_btf, func->type); if (!func_proto || !btf_type_is_func_proto(func_proto)) { verbose(env, "kernel function btf_id %u does not have a valid func_proto\n", func_id); return -EINVAL; } - func_name = btf_name_by_offset(btf_vmlinux, func->name_off); + func_name = btf_name_by_offset(desc_btf, func->name_off); addr = kallsyms_lookup_name(func_name); if (!addr) { verbose(env, "cannot find address for kernel function %s\n", @@ -1730,13 +1882,14 @@ static int add_kfunc_call(struct bpf_verifier_env *env, u32 func_id) desc = &tab->descs[tab->nr_descs++]; desc->func_id = func_id; - desc->imm = BPF_CAST_CALL(addr) - __bpf_call_base; - err = btf_distill_func_proto(&env->log, btf_vmlinux, + desc->imm = BPF_CALL_IMM(addr); + desc->offset = offset; + err = btf_distill_func_proto(&env->log, desc_btf, func_proto, func_name, &desc->func_model); if (!err) sort(tab->descs, tab->nr_descs, sizeof(tab->descs[0]), - kfunc_desc_cmp_by_id, NULL); + kfunc_desc_cmp_by_id_off, NULL); return err; } @@ -1815,7 +1968,7 @@ static int add_subprog_and_kfunc(struct bpf_verifier_env *env) } else if (bpf_pseudo_call(insn)) { ret = add_subprog(env, i + insn->imm + 1); } else { - ret = add_kfunc_call(env, insn->imm); + ret = add_kfunc_call(env, insn->imm, insn->off); } if (ret < 0) @@ -2152,12 +2305,17 @@ static int get_prev_insn_idx(struct bpf_verifier_state *st, int i, static const char *disasm_kfunc_name(void *data, const struct bpf_insn *insn) { const struct btf_type *func; + struct btf *desc_btf; if (insn->src_reg != BPF_PSEUDO_KFUNC_CALL) return NULL; - func = btf_type_by_id(btf_vmlinux, insn->imm); - return btf_name_by_offset(btf_vmlinux, func->name_off); + desc_btf = find_kfunc_desc_btf(data, insn->imm, insn->off, NULL); + if (IS_ERR(desc_btf)) + return "<error>"; + + func = btf_type_by_id(desc_btf, insn->imm); + return btf_name_by_offset(desc_btf, func->name_off); } /* For given verifier state backtrack_insn() is called from the last insn to @@ -2373,7 +2531,7 @@ static void mark_all_scalars_precise(struct bpf_verifier_env *env, reg->precise = true; } for (j = 0; j < func->allocated_stack / BPF_REG_SIZE; j++) { - if (func->stack[j].slot_type[0] != STACK_SPILL) + if (!is_spilled_reg(&func->stack[j])) continue; reg = &func->stack[j].spilled_ptr; if (reg->type != SCALAR_VALUE) @@ -2415,7 +2573,7 @@ static int __mark_chain_precision(struct bpf_verifier_env *env, int regno, } while (spi >= 0) { - if (func->stack[spi].slot_type[0] != STACK_SPILL) { + if (!is_spilled_reg(&func->stack[spi])) { stack_mask = 0; break; } @@ -2514,7 +2672,7 @@ static int __mark_chain_precision(struct bpf_verifier_env *env, int regno, return 0; } - if (func->stack[i].slot_type[0] != STACK_SPILL) { + if (!is_spilled_reg(&func->stack[i])) { stack_mask &= ~(1ull << i); continue; } @@ -2626,15 +2784,21 @@ static bool __is_pointer_value(bool allow_ptr_leaks, } static void save_register_state(struct bpf_func_state *state, - int spi, struct bpf_reg_state *reg) + int spi, struct bpf_reg_state *reg, + int size) { int i; state->stack[spi].spilled_ptr = *reg; - state->stack[spi].spilled_ptr.live |= REG_LIVE_WRITTEN; + if (size == BPF_REG_SIZE) + state->stack[spi].spilled_ptr.live |= REG_LIVE_WRITTEN; + + for (i = BPF_REG_SIZE; i > BPF_REG_SIZE - size; i--) + state->stack[spi].slot_type[i - 1] = STACK_SPILL; - for (i = 0; i < BPF_REG_SIZE; i++) - state->stack[spi].slot_type[i] = STACK_SPILL; + /* size < 8 bytes spill */ + for (; i; i--) + scrub_spilled_slot(&state->stack[spi].slot_type[i - 1]); } /* check_stack_{read,write}_fixed_off functions track spill/fill of registers, @@ -2681,7 +2845,7 @@ static int check_stack_write_fixed_off(struct bpf_verifier_env *env, env->insn_aux_data[insn_idx].sanitize_stack_spill = true; } - if (reg && size == BPF_REG_SIZE && register_is_bounded(reg) && + if (reg && !(off % BPF_REG_SIZE) && register_is_bounded(reg) && !register_is_null(reg) && env->bpf_capable) { if (dst_reg != BPF_REG_FP) { /* The backtracking logic can only recognize explicit @@ -2694,7 +2858,7 @@ static int check_stack_write_fixed_off(struct bpf_verifier_env *env, if (err) return err; } - save_register_state(state, spi, reg); + save_register_state(state, spi, reg, size); } else if (reg && is_spillable_regtype(reg->type)) { /* register containing pointer is being spilled into stack */ if (size != BPF_REG_SIZE) { @@ -2706,16 +2870,16 @@ static int check_stack_write_fixed_off(struct bpf_verifier_env *env, verbose(env, "cannot spill pointers to stack into stack frame of the caller\n"); return -EINVAL; } - save_register_state(state, spi, reg); + save_register_state(state, spi, reg, size); } else { u8 type = STACK_MISC; /* 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 (state->stack[spi].slot_type[0] == STACK_SPILL) + if (is_spilled_reg(&state->stack[spi])) for (i = 0; i < BPF_REG_SIZE; i++) - state->stack[spi].slot_type[i] = STACK_MISC; + scrub_spilled_slot(&state->stack[spi].slot_type[i]); /* only mark the slot as written if all 8 bytes were written * otherwise read propagation may incorrectly stop too soon @@ -2918,23 +3082,50 @@ static int check_stack_read_fixed_off(struct bpf_verifier_env *env, struct bpf_func_state *state = vstate->frame[vstate->curframe]; int i, slot = -off - 1, spi = slot / BPF_REG_SIZE; struct bpf_reg_state *reg; - u8 *stype; + u8 *stype, type; stype = reg_state->stack[spi].slot_type; reg = ®_state->stack[spi].spilled_ptr; - if (stype[0] == STACK_SPILL) { + if (is_spilled_reg(®_state->stack[spi])) { if (size != BPF_REG_SIZE) { + u8 scalar_size = 0; + if (reg->type != SCALAR_VALUE) { verbose_linfo(env, env->insn_idx, "; "); verbose(env, "invalid size of register fill\n"); return -EACCES; } - if (dst_regno >= 0) { + + mark_reg_read(env, reg, reg->parent, REG_LIVE_READ64); + if (dst_regno < 0) + return 0; + + for (i = BPF_REG_SIZE; i > 0 && stype[i - 1] == STACK_SPILL; i--) + scalar_size++; + + if (!(off % BPF_REG_SIZE) && size == scalar_size) { + /* The earlier check_reg_arg() has decided the + * subreg_def for this insn. Save it first. + */ + s32 subreg_def = state->regs[dst_regno].subreg_def; + + state->regs[dst_regno] = *reg; + state->regs[dst_regno].subreg_def = subreg_def; + } else { + for (i = 0; i < size; i++) { + type = stype[(slot - i) % BPF_REG_SIZE]; + if (type == STACK_SPILL) + continue; + if (type == STACK_MISC) + continue; + verbose(env, "invalid read from stack off %d+%d size %d\n", + off, i, size); + return -EACCES; + } mark_reg_unknown(env, state->regs, dst_regno); - state->regs[dst_regno].live |= REG_LIVE_WRITTEN; } - mark_reg_read(env, reg, reg->parent, REG_LIVE_READ64); + state->regs[dst_regno].live |= REG_LIVE_WRITTEN; return 0; } for (i = 1; i < BPF_REG_SIZE; i++) { @@ -2965,8 +3156,6 @@ static int check_stack_read_fixed_off(struct bpf_verifier_env *env, } mark_reg_read(env, reg, reg->parent, REG_LIVE_READ64); } else { - u8 type; - for (i = 0; i < size; i++) { type = stype[(slot - i) % BPF_REG_SIZE]; if (type == STACK_MISC) @@ -4514,17 +4703,17 @@ static int check_stack_range_initialized( goto mark; } - if (state->stack[spi].slot_type[0] == STACK_SPILL && + if (is_spilled_reg(&state->stack[spi]) && state->stack[spi].spilled_ptr.type == PTR_TO_BTF_ID) goto mark; - if (state->stack[spi].slot_type[0] == STACK_SPILL && + if (is_spilled_reg(&state->stack[spi]) && (state->stack[spi].spilled_ptr.type == SCALAR_VALUE || env->allow_ptr_leaks)) { if (clobber) { __mark_reg_unknown(env, &state->stack[spi].spilled_ptr); for (j = 0; j < BPF_REG_SIZE; j++) - state->stack[spi].slot_type[j] = STACK_MISC; + scrub_spilled_slot(&state->stack[spi].slot_type[j]); } goto mark; } @@ -4813,7 +5002,10 @@ static int resolve_map_arg_type(struct bpf_verifier_env *env, return -EINVAL; } break; - + case BPF_MAP_TYPE_BLOOM_FILTER: + if (meta->func_id == BPF_FUNC_map_peek_elem) + *arg_type = ARG_PTR_TO_MAP_VALUE; + break; default: break; } @@ -5388,6 +5580,11 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env, func_id != BPF_FUNC_task_storage_delete) goto error; break; + case BPF_MAP_TYPE_BLOOM_FILTER: + if (func_id != BPF_FUNC_map_peek_elem && + func_id != BPF_FUNC_map_push_elem) + goto error; + break; default: break; } @@ -5455,13 +5652,18 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env, map->map_type != BPF_MAP_TYPE_SOCKHASH) goto error; break; - case BPF_FUNC_map_peek_elem: case BPF_FUNC_map_pop_elem: - case BPF_FUNC_map_push_elem: if (map->map_type != BPF_MAP_TYPE_QUEUE && map->map_type != BPF_MAP_TYPE_STACK) goto error; break; + case BPF_FUNC_map_peek_elem: + case BPF_FUNC_map_push_elem: + if (map->map_type != BPF_MAP_TYPE_QUEUE && + map->map_type != BPF_MAP_TYPE_STACK && + map->map_type != BPF_MAP_TYPE_BLOOM_FILTER) + goto error; + break; case BPF_FUNC_sk_storage_get: case BPF_FUNC_sk_storage_delete: if (map->map_type != BPF_MAP_TYPE_SK_STORAGE) @@ -6485,23 +6687,33 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn) struct bpf_reg_state *regs = cur_regs(env); const char *func_name, *ptr_type_name; u32 i, nargs, func_id, ptr_type_id; + struct module *btf_mod = NULL; const struct btf_param *args; + struct btf *desc_btf; int err; + /* skip for now, but return error when we find this in fixup_kfunc_call */ + if (!insn->imm) + return 0; + + desc_btf = find_kfunc_desc_btf(env, insn->imm, insn->off, &btf_mod); + if (IS_ERR(desc_btf)) + return PTR_ERR(desc_btf); + func_id = insn->imm; - func = btf_type_by_id(btf_vmlinux, func_id); - func_name = btf_name_by_offset(btf_vmlinux, func->name_off); - func_proto = btf_type_by_id(btf_vmlinux, func->type); + func = btf_type_by_id(desc_btf, func_id); + func_name = btf_name_by_offset(desc_btf, func->name_off); + func_proto = btf_type_by_id(desc_btf, func->type); if (!env->ops->check_kfunc_call || - !env->ops->check_kfunc_call(func_id)) { + !env->ops->check_kfunc_call(func_id, btf_mod)) { verbose(env, "calling kernel function %s is not allowed\n", func_name); return -EACCES; } /* Check the arguments */ - err = btf_check_kfunc_arg_match(env, btf_vmlinux, func_id, regs); + err = btf_check_kfunc_arg_match(env, desc_btf, func_id, regs); if (err) return err; @@ -6509,15 +6721,15 @@ 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(btf_vmlinux, func_proto->type, NULL); + t = btf_type_skip_modifiers(desc_btf, func_proto->type, NULL); if (btf_type_is_scalar(t)) { mark_reg_unknown(env, regs, BPF_REG_0); mark_btf_func_reg_size(env, BPF_REG_0, t->size); } else if (btf_type_is_ptr(t)) { - ptr_type = btf_type_skip_modifiers(btf_vmlinux, t->type, + ptr_type = btf_type_skip_modifiers(desc_btf, t->type, &ptr_type_id); if (!btf_type_is_struct(ptr_type)) { - ptr_type_name = btf_name_by_offset(btf_vmlinux, + ptr_type_name = btf_name_by_offset(desc_btf, ptr_type->name_off); verbose(env, "kernel function %s returns pointer type %s %s is not supported\n", func_name, btf_type_str(ptr_type), @@ -6525,7 +6737,7 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn) return -EINVAL; } mark_reg_known_zero(env, regs, BPF_REG_0); - regs[BPF_REG_0].btf = btf_vmlinux; + regs[BPF_REG_0].btf = desc_btf; regs[BPF_REG_0].type = PTR_TO_BTF_ID; regs[BPF_REG_0].btf_id = ptr_type_id; mark_btf_func_reg_size(env, BPF_REG_0, sizeof(void *)); @@ -6536,7 +6748,7 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn) for (i = 0; i < nargs; i++) { u32 regno = i + 1; - t = btf_type_skip_modifiers(btf_vmlinux, args[i].type, NULL); + t = btf_type_skip_modifiers(desc_btf, args[i].type, NULL); if (btf_type_is_ptr(t)) mark_btf_func_reg_size(env, regno, sizeof(void *)); else @@ -10356,9 +10568,9 @@ static bool stacksafe(struct bpf_verifier_env *env, struct bpf_func_state *old, * return false to continue verification of this path */ return false; - if (i % BPF_REG_SIZE) + if (i % BPF_REG_SIZE != BPF_REG_SIZE - 1) continue; - if (old->stack[spi].slot_type[0] != STACK_SPILL) + if (!is_spilled_reg(&old->stack[spi])) continue; if (!regsafe(env, &old->stack[spi].spilled_ptr, &cur->stack[spi].spilled_ptr, idmap)) @@ -10565,7 +10777,7 @@ static int propagate_precision(struct bpf_verifier_env *env, } for (i = 0; i < state->allocated_stack / BPF_REG_SIZE; i++) { - if (state->stack[i].slot_type[0] != STACK_SPILL) + if (!is_spilled_reg(&state->stack[i])) continue; state_reg = &state->stack[i].spilled_ptr; if (state_reg->type != SCALAR_VALUE || @@ -11076,7 +11288,8 @@ static int do_check(struct bpf_verifier_env *env) env->jmps_processed++; if (opcode == BPF_CALL) { if (BPF_SRC(insn->code) != BPF_K || - insn->off != 0 || + (insn->src_reg != BPF_PSEUDO_KFUNC_CALL + && insn->off != 0) || (insn->src_reg != BPF_REG_0 && insn->src_reg != BPF_PSEUDO_CALL && insn->src_reg != BPF_PSEUDO_KFUNC_CALL) || @@ -12432,6 +12645,7 @@ static int jit_subprogs(struct bpf_verifier_env *env) func[i]->aux->stack_depth = env->subprog_info[i].stack_depth; func[i]->jit_requested = 1; func[i]->aux->kfunc_tab = prog->aux->kfunc_tab; + func[i]->aux->kfunc_btf_tab = prog->aux->kfunc_btf_tab; func[i]->aux->linfo = prog->aux->linfo; func[i]->aux->nr_linfo = prog->aux->nr_linfo; func[i]->aux->jited_linfo = prog->aux->jited_linfo; @@ -12469,8 +12683,7 @@ static int jit_subprogs(struct bpf_verifier_env *env) if (!bpf_pseudo_call(insn)) continue; subprog = insn->off; - insn->imm = BPF_CAST_CALL(func[subprog]->bpf_func) - - __bpf_call_base; + insn->imm = BPF_CALL_IMM(func[subprog]->bpf_func); } /* we use the aux data to keep a list of the start addresses @@ -12618,10 +12831,15 @@ static int fixup_kfunc_call(struct bpf_verifier_env *env, { const struct bpf_kfunc_desc *desc; + if (!insn->imm) { + verbose(env, "invalid kernel function call not eliminated in verifier pass\n"); + return -EINVAL; + } + /* insn->imm has the btf func_id. Replace it with * an address (relative to __bpf_base_call). */ - desc = find_kfunc_desc(env->prog, insn->imm); + desc = find_kfunc_desc(env->prog, insn->imm, insn->off); if (!desc) { verbose(env, "verifier internal error: kernel function descriptor not found for func_id %u\n", insn->imm); @@ -12902,7 +13120,8 @@ static int do_misc_fixups(struct bpf_verifier_env *env) insn->imm == BPF_FUNC_map_push_elem || insn->imm == BPF_FUNC_map_pop_elem || insn->imm == BPF_FUNC_map_peek_elem || - insn->imm == BPF_FUNC_redirect_map)) { + insn->imm == BPF_FUNC_redirect_map || + insn->imm == BPF_FUNC_for_each_map_elem)) { aux = &env->insn_aux_data[i + delta]; if (bpf_map_ptr_poisoned(aux)) goto patch_call_imm; @@ -12946,36 +13165,37 @@ static int do_misc_fixups(struct bpf_verifier_env *env) (int (*)(struct bpf_map *map, void *value))NULL)); BUILD_BUG_ON(!__same_type(ops->map_redirect, (int (*)(struct bpf_map *map, u32 ifindex, u64 flags))NULL)); + BUILD_BUG_ON(!__same_type(ops->map_for_each_callback, + (int (*)(struct bpf_map *map, + bpf_callback_t callback_fn, + void *callback_ctx, + u64 flags))NULL)); patch_map_ops_generic: switch (insn->imm) { case BPF_FUNC_map_lookup_elem: - insn->imm = BPF_CAST_CALL(ops->map_lookup_elem) - - __bpf_call_base; + insn->imm = BPF_CALL_IMM(ops->map_lookup_elem); continue; case BPF_FUNC_map_update_elem: - insn->imm = BPF_CAST_CALL(ops->map_update_elem) - - __bpf_call_base; + insn->imm = BPF_CALL_IMM(ops->map_update_elem); continue; case BPF_FUNC_map_delete_elem: - insn->imm = BPF_CAST_CALL(ops->map_delete_elem) - - __bpf_call_base; + insn->imm = BPF_CALL_IMM(ops->map_delete_elem); continue; case BPF_FUNC_map_push_elem: - insn->imm = BPF_CAST_CALL(ops->map_push_elem) - - __bpf_call_base; + insn->imm = BPF_CALL_IMM(ops->map_push_elem); continue; case BPF_FUNC_map_pop_elem: - insn->imm = BPF_CAST_CALL(ops->map_pop_elem) - - __bpf_call_base; + insn->imm = BPF_CALL_IMM(ops->map_pop_elem); continue; case BPF_FUNC_map_peek_elem: - insn->imm = BPF_CAST_CALL(ops->map_peek_elem) - - __bpf_call_base; + insn->imm = BPF_CALL_IMM(ops->map_peek_elem); continue; case BPF_FUNC_redirect_map: - insn->imm = BPF_CAST_CALL(ops->map_redirect) - - __bpf_call_base; + insn->imm = BPF_CALL_IMM(ops->map_redirect); + continue; + case BPF_FUNC_for_each_map_elem: + insn->imm = BPF_CALL_IMM(ops->map_for_each_callback); continue; } @@ -13826,6 +14046,7 @@ skip_full_check: env->verification_time = ktime_get_ns() - start_time; print_verification_stats(env); + env->prog->aux->verified_insns = env->insn_processed; if (log->level && bpf_verifier_log_full(log)) ret = -ENOSPC; diff --git a/kernel/events/core.c b/kernel/events/core.c index a89b01b7e59a..f2253ea729a2 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -13491,3 +13491,5 @@ struct cgroup_subsys perf_event_cgrp_subsys = { .threaded = true, }; #endif /* CONFIG_CGROUP_PERF */ + +DEFINE_STATIC_CALL_RET0(perf_snapshot_branch_stack, perf_snapshot_branch_stack_t); diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 8e2eb950aa82..7396488793ff 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -398,7 +398,7 @@ static const struct bpf_func_proto bpf_trace_printk_proto = { .arg2_type = ARG_CONST_SIZE, }; -const struct bpf_func_proto *bpf_get_trace_printk_proto(void) +static void __set_printk_clr_event(void) { /* * This program might be calling bpf_trace_printk, @@ -410,11 +410,57 @@ const struct bpf_func_proto *bpf_get_trace_printk_proto(void) */ if (trace_set_clr_event("bpf_trace", "bpf_trace_printk", 1)) pr_warn_ratelimited("could not enable bpf_trace_printk events"); +} +const struct bpf_func_proto *bpf_get_trace_printk_proto(void) +{ + __set_printk_clr_event(); return &bpf_trace_printk_proto; } -#define MAX_SEQ_PRINTF_VARARGS 12 +BPF_CALL_4(bpf_trace_vprintk, char *, fmt, u32, fmt_size, const void *, data, + u32, data_len) +{ + static char buf[BPF_TRACE_PRINTK_SIZE]; + unsigned long flags; + int ret, num_args; + u32 *bin_args; + + if (data_len & 7 || data_len > MAX_BPRINTF_VARARGS * 8 || + (data_len && !data)) + return -EINVAL; + num_args = data_len / 8; + + ret = bpf_bprintf_prepare(fmt, fmt_size, data, &bin_args, num_args); + if (ret < 0) + return ret; + + raw_spin_lock_irqsave(&trace_printk_lock, flags); + ret = bstr_printf(buf, sizeof(buf), fmt, bin_args); + + trace_bpf_trace_printk(buf); + raw_spin_unlock_irqrestore(&trace_printk_lock, flags); + + bpf_bprintf_cleanup(); + + return ret; +} + +static const struct bpf_func_proto bpf_trace_vprintk_proto = { + .func = bpf_trace_vprintk, + .gpl_only = true, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_MEM, + .arg2_type = ARG_CONST_SIZE, + .arg3_type = ARG_PTR_TO_MEM_OR_NULL, + .arg4_type = ARG_CONST_SIZE_OR_ZERO, +}; + +const struct bpf_func_proto *bpf_get_trace_vprintk_proto(void) +{ + __set_printk_clr_event(); + return &bpf_trace_vprintk_proto; +} BPF_CALL_5(bpf_seq_printf, struct seq_file *, m, char *, fmt, u32, fmt_size, const void *, data, u32, data_len) @@ -422,7 +468,7 @@ BPF_CALL_5(bpf_seq_printf, struct seq_file *, m, char *, fmt, u32, fmt_size, int err, num_args; u32 *bin_args; - if (data_len & 7 || data_len > MAX_SEQ_PRINTF_VARARGS * 8 || + if (data_len & 7 || data_len > MAX_BPRINTF_VARARGS * 8 || (data_len && !data)) return -EINVAL; num_args = data_len / 8; @@ -1017,6 +1063,34 @@ static const struct bpf_func_proto bpf_get_attach_cookie_proto_pe = { .arg1_type = ARG_PTR_TO_CTX, }; +BPF_CALL_3(bpf_get_branch_snapshot, void *, buf, u32, size, u64, flags) +{ +#ifndef CONFIG_X86 + return -ENOENT; +#else + static const u32 br_entry_size = sizeof(struct perf_branch_entry); + u32 entry_cnt = size / br_entry_size; + + entry_cnt = static_call(perf_snapshot_branch_stack)(buf, entry_cnt); + + if (unlikely(flags)) + return -EINVAL; + + if (!entry_cnt) + return -ENOENT; + + return entry_cnt * br_entry_size; +#endif +} + +static const struct bpf_func_proto bpf_get_branch_snapshot_proto = { + .func = bpf_get_branch_snapshot, + .gpl_only = true, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_UNINIT_MEM, + .arg2_type = ARG_CONST_SIZE_OR_ZERO, +}; + static const struct bpf_func_proto * bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { @@ -1132,6 +1206,10 @@ bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_snprintf_proto; case BPF_FUNC_get_func_ip: return &bpf_get_func_ip_proto_tracing; + case BPF_FUNC_get_branch_snapshot: + return &bpf_get_branch_snapshot_proto; + case BPF_FUNC_trace_vprintk: + return bpf_get_trace_vprintk_proto(); default: return bpf_base_func_proto(func_id); } @@ -1530,6 +1608,8 @@ tracing_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_skc_to_tcp_request_sock_proto; case BPF_FUNC_skc_to_udp6_sock: return &bpf_skc_to_udp6_sock_proto; + case BPF_FUNC_skc_to_unix_sock: + return &bpf_skc_to_unix_sock_proto; case BPF_FUNC_sk_storage_get: return &bpf_sk_storage_get_tracing_proto; case BPF_FUNC_sk_storage_delete: @@ -1566,13 +1646,7 @@ static bool raw_tp_prog_is_valid_access(int off, int size, const struct bpf_prog *prog, struct bpf_insn_access_aux *info) { - if (off < 0 || off >= sizeof(__u64) * MAX_BPF_FUNC_ARGS) - return false; - if (type != BPF_READ) - return false; - if (off % size != 0) - return false; - return true; + return bpf_tracing_ctx_access(off, size, type); } static bool tracing_prog_is_valid_access(int off, int size, @@ -1580,13 +1654,7 @@ static bool tracing_prog_is_valid_access(int off, int size, const struct bpf_prog *prog, struct bpf_insn_access_aux *info) { - if (off < 0 || off >= sizeof(__u64) * MAX_BPF_FUNC_ARGS) - return false; - if (type != BPF_READ) - return false; - if (off % size != 0) - return false; - return btf_ctx_access(off, size, type, prog, info); + return bpf_tracing_btf_ctx_access(off, size, type, prog, info); } int __weak bpf_prog_test_run_tracing(struct bpf_prog *prog, |