diff options
| author | Linus Torvalds | 2022-05-25 12:22:58 -0700 |
|---|---|---|
| committer | Linus Torvalds | 2022-05-25 12:22:58 -0700 |
| commit | 7e062cda7d90543ac8c7700fc7c5527d0c0f22ad (patch) | |
| tree | 2f1602595d9416be41cc2e88a659ba4c145734b9 /kernel | |
| parent | 5d1772b1739b085721431eef0c0400f3aff01abf (diff) | |
| parent | 57d7becda9c9e612e6b00676f2eecfac3e719e88 (diff) | |
Merge tag 'net-next-5.19' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next
Pull networking updates from Jakub Kicinski:
"Core
----
- Support TCPv6 segmentation offload with super-segments larger than
64k bytes using the IPv6 Jumbogram extension header (AKA BIG TCP).
- Generalize skb freeing deferral to per-cpu lists, instead of
per-socket lists.
- Add a netdev statistic for packets dropped due to L2 address
mismatch (rx_otherhost_dropped).
- Continue work annotating skb drop reasons.
- Accept alternative netdev names (ALT_IFNAME) in more netlink
requests.
- Add VLAN support for AF_PACKET SOCK_RAW GSO.
- Allow receiving skb mark from the socket as a cmsg.
- Enable memcg accounting for veth queues, sysctl tables and IPv6.
BPF
---
- Add libbpf support for User Statically-Defined Tracing (USDTs).
- Speed up symbol resolution for kprobes multi-link attachments.
- Support storing typed pointers to referenced and unreferenced
objects in BPF maps.
- Add support for BPF link iterator.
- Introduce access to remote CPU map elements in BPF per-cpu map.
- Allow middle-of-the-road settings for the
kernel.unprivileged_bpf_disabled sysctl.
- Implement basic types of dynamic pointers e.g. to allow for
dynamically sized ringbuf reservations without extra memory copies.
Protocols
---------
- Retire port only listening_hash table, add a second bind table
hashed by port and address. Avoid linear list walk when binding to
very popular ports (e.g. 443).
- Add bridge FDB bulk flush filtering support allowing user space to
remove all FDB entries matching a condition.
- Introduce accept_unsolicited_na sysctl for IPv6 to implement
router-side changes for RFC9131.
- Support for MPTCP path manager in user space.
- Add MPTCP support for fallback to regular TCP for connections that
have never connected additional subflows or transmitted
out-of-sequence data (partial support for RFC8684 fallback).
- Avoid races in MPTCP-level window tracking, stabilize and improve
throughput.
- Support lockless operation of GRE tunnels with seq numbers enabled.
- WiFi support for host based BSS color collision detection.
- Add support for SO_TXTIME/SCM_TXTIME on CAN sockets.
- Support transmission w/o flow control in CAN ISOTP (ISO 15765-2).
- Support zero-copy Tx with TLS 1.2 crypto offload (sendfile).
- Allow matching on the number of VLAN tags via tc-flower.
- Add tracepoint for tcp_set_ca_state().
Driver API
----------
- Improve error reporting from classifier and action offload.
- Add support for listing line cards in switches (devlink).
- Add helpers for reporting page pool statistics with ethtool -S.
- Add support for reading clock cycles when using PTP virtual clocks,
instead of having the driver convert to time before reporting. This
makes it possible to report time from different vclocks.
- Support configuring low-latency Tx descriptor push via ethtool.
- Separate Clause 22 and Clause 45 MDIO accesses more explicitly.
New hardware / drivers
----------------------
- Ethernet:
- Marvell's Octeon NIC PCI Endpoint support (octeon_ep)
- Sunplus SP7021 SoC (sp7021_emac)
- Add support for Renesas RZ/V2M (in ravb)
- Add support for MediaTek mt7986 switches (in mtk_eth_soc)
- Ethernet PHYs:
- ADIN1100 industrial PHYs (w/ 10BASE-T1L and SQI reporting)
- TI DP83TD510 PHY
- Microchip LAN8742/LAN88xx PHYs
- WiFi:
- Driver for pureLiFi X, XL, XC devices (plfxlc)
- Driver for Silicon Labs devices (wfx)
- Support for WCN6750 (in ath11k)
- Support Realtek 8852ce devices (in rtw89)
- Mobile:
- MediaTek T700 modems (Intel 5G 5000 M.2 cards)
- CAN:
- ctucanfd: add support for CTU CAN FD open-source IP core from
Czech Technical University in Prague
Drivers
-------
- Delete a number of old drivers still using virt_to_bus().
- Ethernet NICs:
- intel: support TSO on tunnels MPLS
- broadcom: support multi-buffer XDP
- nfp: support VF rate limiting
- sfc: use hardware tx timestamps for more than PTP
- mlx5: multi-port eswitch support
- hyper-v: add support for XDP_REDIRECT
- atlantic: XDP support (including multi-buffer)
- macb: improve real-time perf by deferring Tx processing to NAPI
- High-speed Ethernet switches:
- mlxsw: implement basic line card information querying
- prestera: add support for traffic policing on ingress and egress
- Embedded Ethernet switches:
- lan966x: add support for packet DMA (FDMA)
- lan966x: add support for PTP programmable pins
- ti: cpsw_new: enable bc/mc storm prevention
- Qualcomm 802.11ax WiFi (ath11k):
- Wake-on-WLAN support for QCA6390 and WCN6855
- device recovery (firmware restart) support
- support setting Specific Absorption Rate (SAR) for WCN6855
- read country code from SMBIOS for WCN6855/QCA6390
- enable keep-alive during WoWLAN suspend
- implement remain-on-channel support
- MediaTek WiFi (mt76):
- support Wireless Ethernet Dispatch offloading packet movement
between the Ethernet switch and WiFi interfaces
- non-standard VHT MCS10-11 support
- mt7921 AP mode support
- mt7921 IPv6 NS offload support
- Ethernet PHYs:
- micrel: ksz9031/ksz9131: cabletest support
- lan87xx: SQI support for T1 PHYs
- lan937x: add interrupt support for link detection"
* tag 'net-next-5.19' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1809 commits)
ptp: ocp: Add firmware header checks
ptp: ocp: fix PPS source selector debugfs reporting
ptp: ocp: add .init function for sma_op vector
ptp: ocp: vectorize the sma accessor functions
ptp: ocp: constify selectors
ptp: ocp: parameterize input/output sma selectors
ptp: ocp: revise firmware display
ptp: ocp: add Celestica timecard PCI ids
ptp: ocp: Remove #ifdefs around PCI IDs
ptp: ocp: 32-bit fixups for pci start address
Revert "net/smc: fix listen processing for SMC-Rv2"
ath6kl: Use cc-disable-warning to disable -Wdangling-pointer
selftests/bpf: Dynptr tests
bpf: Add dynptr data slices
bpf: Add bpf_dynptr_read and bpf_dynptr_write
bpf: Dynptr support for ring buffers
bpf: Add bpf_dynptr_from_mem for local dynptrs
bpf: Add verifier support for dynptrs
bpf: Suppress 'passing zero to PTR_ERR' warning
bpf: Introduce bpf_arch_text_invalidate for bpf_prog_pack
...
Diffstat (limited to 'kernel')
33 files changed, 2705 insertions, 683 deletions
diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile index c1a9be6a4b9f..057ba8e01e70 100644 --- a/kernel/bpf/Makefile +++ b/kernel/bpf/Makefile @@ -6,7 +6,7 @@ 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 +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) += 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 7f145aefbff8..fe40d3b9458f 100644 --- a/kernel/bpf/arraymap.c +++ b/kernel/bpf/arraymap.c @@ -11,6 +11,7 @@ #include <linux/perf_event.h> #include <uapi/linux/btf.h> #include <linux/rcupdate_trace.h> +#include <linux/btf_ids.h> #include "map_in_map.h" @@ -242,6 +243,20 @@ static void *percpu_array_map_lookup_elem(struct bpf_map *map, void *key) return this_cpu_ptr(array->pptrs[index & array->index_mask]); } +static void *percpu_array_map_lookup_percpu_elem(struct bpf_map *map, void *key, u32 cpu) +{ + struct bpf_array *array = container_of(map, struct bpf_array, map); + u32 index = *(u32 *)key; + + if (cpu >= nr_cpu_ids) + return NULL; + + if (unlikely(index >= array->map.max_entries)) + return NULL; + + return per_cpu_ptr(array->pptrs[index & array->index_mask], cpu); +} + int bpf_percpu_array_copy(struct bpf_map *map, void *key, void *value) { struct bpf_array *array = container_of(map, struct bpf_array, map); @@ -287,10 +302,12 @@ static int array_map_get_next_key(struct bpf_map *map, void *key, void *next_key return 0; } -static void check_and_free_timer_in_array(struct bpf_array *arr, void *val) +static void check_and_free_fields(struct bpf_array *arr, void *val) { - if (unlikely(map_value_has_timer(&arr->map))) + if (map_value_has_timer(&arr->map)) bpf_timer_cancel_and_free(val + arr->map.timer_off); + if (map_value_has_kptrs(&arr->map)) + bpf_map_free_kptrs(&arr->map, val); } /* Called from syscall or from eBPF program */ @@ -327,7 +344,7 @@ static int array_map_update_elem(struct bpf_map *map, void *key, void *value, copy_map_value_locked(map, val, value, false); else copy_map_value(map, val, value); - check_and_free_timer_in_array(array, val); + check_and_free_fields(array, val); } return 0; } @@ -386,7 +403,8 @@ static void array_map_free_timers(struct bpf_map *map) struct bpf_array *array = container_of(map, struct bpf_array, map); int i; - if (likely(!map_value_has_timer(map))) + /* We don't reset or free kptr on uref dropping to zero. */ + if (!map_value_has_timer(map)) return; for (i = 0; i < array->map.max_entries; i++) @@ -398,6 +416,13 @@ static void array_map_free_timers(struct bpf_map *map) static void array_map_free(struct bpf_map *map) { struct bpf_array *array = container_of(map, struct bpf_array, map); + int i; + + if (map_value_has_kptrs(map)) { + for (i = 0; i < array->map.max_entries; i++) + bpf_map_free_kptrs(map, array->value + array->elem_size * i); + bpf_map_free_kptr_off_tab(map); + } if (array->map.map_type == BPF_MAP_TYPE_PERCPU_ARRAY) bpf_array_free_percpu(array); @@ -680,7 +705,7 @@ static int bpf_for_each_array_elem(struct bpf_map *map, bpf_callback_t callback_ return num_elems; } -static int array_map_btf_id; +BTF_ID_LIST_SINGLE(array_map_btf_ids, struct, bpf_array) const struct bpf_map_ops array_map_ops = { .map_meta_equal = array_map_meta_equal, .map_alloc_check = array_map_alloc_check, @@ -701,12 +726,10 @@ const struct bpf_map_ops array_map_ops = { .map_update_batch = generic_map_update_batch, .map_set_for_each_callback_args = map_set_for_each_callback_args, .map_for_each_callback = bpf_for_each_array_elem, - .map_btf_name = "bpf_array", - .map_btf_id = &array_map_btf_id, + .map_btf_id = &array_map_btf_ids[0], .iter_seq_info = &iter_seq_info, }; -static int percpu_array_map_btf_id; const struct bpf_map_ops percpu_array_map_ops = { .map_meta_equal = bpf_map_meta_equal, .map_alloc_check = array_map_alloc_check, @@ -716,14 +739,14 @@ const struct bpf_map_ops percpu_array_map_ops = { .map_lookup_elem = percpu_array_map_lookup_elem, .map_update_elem = array_map_update_elem, .map_delete_elem = array_map_delete_elem, + .map_lookup_percpu_elem = percpu_array_map_lookup_percpu_elem, .map_seq_show_elem = percpu_array_map_seq_show_elem, .map_check_btf = array_map_check_btf, .map_lookup_batch = generic_map_lookup_batch, .map_update_batch = generic_map_update_batch, .map_set_for_each_callback_args = map_set_for_each_callback_args, .map_for_each_callback = bpf_for_each_array_elem, - .map_btf_name = "bpf_array", - .map_btf_id = &percpu_array_map_btf_id, + .map_btf_id = &array_map_btf_ids[0], .iter_seq_info = &iter_seq_info, }; @@ -1102,7 +1125,6 @@ static void prog_array_map_free(struct bpf_map *map) * Thus, prog_array_map cannot be used as an inner_map * and map_meta_equal is not implemented. */ -static int prog_array_map_btf_id; const struct bpf_map_ops prog_array_map_ops = { .map_alloc_check = fd_array_map_alloc_check, .map_alloc = prog_array_map_alloc, @@ -1118,8 +1140,7 @@ const struct bpf_map_ops prog_array_map_ops = { .map_fd_sys_lookup_elem = prog_fd_array_sys_lookup_elem, .map_release_uref = prog_array_map_clear, .map_seq_show_elem = prog_array_map_seq_show_elem, - .map_btf_name = "bpf_array", - .map_btf_id = &prog_array_map_btf_id, + .map_btf_id = &array_map_btf_ids[0], }; static struct bpf_event_entry *bpf_event_entry_gen(struct file *perf_file, @@ -1208,7 +1229,6 @@ static void perf_event_fd_array_map_free(struct bpf_map *map) fd_array_map_free(map); } -static int perf_event_array_map_btf_id; const struct bpf_map_ops perf_event_array_map_ops = { .map_meta_equal = bpf_map_meta_equal, .map_alloc_check = fd_array_map_alloc_check, @@ -1221,8 +1241,7 @@ const struct bpf_map_ops perf_event_array_map_ops = { .map_fd_put_ptr = perf_event_fd_array_put_ptr, .map_release = perf_event_fd_array_release, .map_check_btf = map_check_no_btf, - .map_btf_name = "bpf_array", - .map_btf_id = &perf_event_array_map_btf_id, + .map_btf_id = &array_map_btf_ids[0], }; #ifdef CONFIG_CGROUPS @@ -1245,7 +1264,6 @@ static void cgroup_fd_array_free(struct bpf_map *map) fd_array_map_free(map); } -static int cgroup_array_map_btf_id; const struct bpf_map_ops cgroup_array_map_ops = { .map_meta_equal = bpf_map_meta_equal, .map_alloc_check = fd_array_map_alloc_check, @@ -1257,8 +1275,7 @@ const struct bpf_map_ops cgroup_array_map_ops = { .map_fd_get_ptr = cgroup_fd_array_get_ptr, .map_fd_put_ptr = cgroup_fd_array_put_ptr, .map_check_btf = map_check_no_btf, - .map_btf_name = "bpf_array", - .map_btf_id = &cgroup_array_map_btf_id, + .map_btf_id = &array_map_btf_ids[0], }; #endif @@ -1332,7 +1349,6 @@ static int array_of_map_gen_lookup(struct bpf_map *map, return insn - insn_buf; } -static int array_of_maps_map_btf_id; const struct bpf_map_ops array_of_maps_map_ops = { .map_alloc_check = fd_array_map_alloc_check, .map_alloc = array_of_map_alloc, @@ -1344,7 +1360,8 @@ const struct bpf_map_ops array_of_maps_map_ops = { .map_fd_put_ptr = bpf_map_fd_put_ptr, .map_fd_sys_lookup_elem = bpf_map_fd_sys_lookup_elem, .map_gen_lookup = array_of_map_gen_lookup, + .map_lookup_batch = generic_map_lookup_batch, + .map_update_batch = generic_map_update_batch, .map_check_btf = map_check_no_btf, - .map_btf_name = "bpf_array", - .map_btf_id = &array_of_maps_map_btf_id, + .map_btf_id = &array_map_btf_ids[0], }; diff --git a/kernel/bpf/bloom_filter.c b/kernel/bpf/bloom_filter.c index b141a1346f72..b9ea539a5561 100644 --- a/kernel/bpf/bloom_filter.c +++ b/kernel/bpf/bloom_filter.c @@ -7,6 +7,7 @@ #include <linux/err.h> #include <linux/jhash.h> #include <linux/random.h> +#include <linux/btf_ids.h> #define BLOOM_CREATE_FLAG_MASK \ (BPF_F_NUMA_NODE | BPF_F_ZERO_SEED | BPF_F_ACCESS_MASK) @@ -192,7 +193,7 @@ static int bloom_map_check_btf(const struct bpf_map *map, return btf_type_is_void(key_type) ? 0 : -EINVAL; } -static int bpf_bloom_map_btf_id; +BTF_ID_LIST_SINGLE(bpf_bloom_map_btf_ids, struct, bpf_bloom_filter) const struct bpf_map_ops bloom_filter_map_ops = { .map_meta_equal = bpf_map_meta_equal, .map_alloc = bloom_map_alloc, @@ -205,6 +206,5 @@ const struct bpf_map_ops bloom_filter_map_ops = { .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, + .map_btf_id = &bpf_bloom_map_btf_ids[0], }; diff --git a/kernel/bpf/bpf_inode_storage.c b/kernel/bpf/bpf_inode_storage.c index 96be8d518885..5f7683b19199 100644 --- a/kernel/bpf/bpf_inode_storage.c +++ b/kernel/bpf/bpf_inode_storage.c @@ -90,7 +90,7 @@ void bpf_inode_storage_free(struct inode *inode) */ bpf_selem_unlink_map(selem); free_inode_storage = bpf_selem_unlink_storage_nolock( - local_storage, selem, false); + local_storage, selem, false, false); } raw_spin_unlock_bh(&local_storage->lock); rcu_read_unlock(); @@ -149,7 +149,7 @@ static int inode_storage_delete(struct inode *inode, struct bpf_map *map) if (!sdata) return -ENOENT; - bpf_selem_unlink(SELEM(sdata)); + bpf_selem_unlink(SELEM(sdata), true); return 0; } @@ -245,7 +245,8 @@ static void inode_storage_map_free(struct bpf_map *map) bpf_local_storage_map_free(smap, NULL); } -static int inode_storage_map_btf_id; +BTF_ID_LIST_SINGLE(inode_storage_map_btf_ids, struct, + bpf_local_storage_map) const struct bpf_map_ops inode_storage_map_ops = { .map_meta_equal = bpf_map_meta_equal, .map_alloc_check = bpf_local_storage_map_alloc_check, @@ -256,8 +257,7 @@ const struct bpf_map_ops inode_storage_map_ops = { .map_update_elem = bpf_fd_inode_storage_update_elem, .map_delete_elem = bpf_fd_inode_storage_delete_elem, .map_check_btf = bpf_local_storage_map_check_btf, - .map_btf_name = "bpf_local_storage_map", - .map_btf_id = &inode_storage_map_btf_id, + .map_btf_id = &inode_storage_map_btf_ids[0], .map_owner_storage_ptr = inode_storage_ptr, }; diff --git a/kernel/bpf/bpf_iter.c b/kernel/bpf/bpf_iter.c index 110029ede71e..d5d96ceca105 100644 --- a/kernel/bpf/bpf_iter.c +++ b/kernel/bpf/bpf_iter.c @@ -330,35 +330,34 @@ static void cache_btf_id(struct bpf_iter_target_info *tinfo, bool bpf_iter_prog_supported(struct bpf_prog *prog) { const char *attach_fname = prog->aux->attach_func_name; + struct bpf_iter_target_info *tinfo = NULL, *iter; u32 prog_btf_id = prog->aux->attach_btf_id; const char *prefix = BPF_ITER_FUNC_PREFIX; - struct bpf_iter_target_info *tinfo; int prefix_len = strlen(prefix); - bool supported = false; if (strncmp(attach_fname, prefix, prefix_len)) return false; mutex_lock(&targets_mutex); - list_for_each_entry(tinfo, &targets, list) { - if (tinfo->btf_id && tinfo->btf_id == prog_btf_id) { - supported = true; + list_for_each_entry(iter, &targets, list) { + if (iter->btf_id && iter->btf_id == prog_btf_id) { + tinfo = iter; break; } - if (!strcmp(attach_fname + prefix_len, tinfo->reg_info->target)) { - cache_btf_id(tinfo, prog); - supported = true; + if (!strcmp(attach_fname + prefix_len, iter->reg_info->target)) { + cache_btf_id(iter, prog); + tinfo = iter; break; } } mutex_unlock(&targets_mutex); - if (supported) { + if (tinfo) { prog->aux->ctx_arg_info_size = tinfo->reg_info->ctx_arg_info_size; prog->aux->ctx_arg_info = tinfo->reg_info->ctx_arg_info; } - return supported; + return tinfo != NULL; } const struct bpf_func_proto * @@ -499,12 +498,11 @@ bool bpf_link_is_iter(struct bpf_link *link) int bpf_iter_link_attach(const union bpf_attr *attr, bpfptr_t uattr, struct bpf_prog *prog) { + struct bpf_iter_target_info *tinfo = NULL, *iter; struct bpf_link_primer link_primer; - struct bpf_iter_target_info *tinfo; union bpf_iter_link_info linfo; struct bpf_iter_link *link; u32 prog_btf_id, linfo_len; - bool existed = false; bpfptr_t ulinfo; int err; @@ -530,14 +528,14 @@ int bpf_iter_link_attach(const union bpf_attr *attr, bpfptr_t uattr, prog_btf_id = prog->aux->attach_btf_id; mutex_lock(&targets_mutex); - list_for_each_entry(tinfo, &targets, list) { - if (tinfo->btf_id == prog_btf_id) { - existed = true; + list_for_each_entry(iter, &targets, list) { + if (iter->btf_id == prog_btf_id) { + tinfo = iter; break; } } mutex_unlock(&targets_mutex); - if (!existed) + if (!tinfo) return -ENOENT; link = kzalloc(sizeof(*link), GFP_USER | __GFP_NOWARN); @@ -547,7 +545,7 @@ int bpf_iter_link_attach(const union bpf_attr *attr, bpfptr_t uattr, bpf_link_init(&link->link, BPF_LINK_TYPE_ITER, &bpf_iter_link_lops, prog); link->tinfo = tinfo; - err = bpf_link_prime(&link->link, &link_primer); + err = bpf_link_prime(&link->link, &link_primer); if (err) { kfree(link); return err; diff --git a/kernel/bpf/bpf_local_storage.c b/kernel/bpf/bpf_local_storage.c index 01aa2b51ec4d..8ce40fd869f6 100644 --- a/kernel/bpf/bpf_local_storage.c +++ b/kernel/bpf/bpf_local_storage.c @@ -106,7 +106,7 @@ static void bpf_selem_free_rcu(struct rcu_head *rcu) */ bool bpf_selem_unlink_storage_nolock(struct bpf_local_storage *local_storage, struct bpf_local_storage_elem *selem, - bool uncharge_mem) + bool uncharge_mem, bool use_trace_rcu) { struct bpf_local_storage_map *smap; bool free_local_storage; @@ -150,11 +150,16 @@ bool bpf_selem_unlink_storage_nolock(struct bpf_local_storage *local_storage, SDATA(selem)) RCU_INIT_POINTER(local_storage->cache[smap->cache_idx], NULL); - call_rcu_tasks_trace(&selem->rcu, bpf_selem_free_rcu); + if (use_trace_rcu) + call_rcu_tasks_trace(&selem->rcu, bpf_selem_free_rcu); + else + kfree_rcu(selem, rcu); + return free_local_storage; } -static void __bpf_selem_unlink_storage(struct bpf_local_storage_elem *selem) +static void __bpf_selem_unlink_storage(struct bpf_local_storage_elem *selem, + bool use_trace_rcu) { struct bpf_local_storage *local_storage; bool free_local_storage = false; @@ -169,12 +174,16 @@ static void __bpf_selem_unlink_storage(struct bpf_local_storage_elem *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); + local_storage, selem, true, use_trace_rcu); raw_spin_unlock_irqrestore(&local_storage->lock, flags); - if (free_local_storage) - call_rcu_tasks_trace(&local_storage->rcu, + 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); + } } void bpf_selem_link_storage_nolock(struct bpf_local_storage *local_storage, @@ -214,14 +223,14 @@ 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) +void bpf_selem_unlink(struct bpf_local_storage_elem *selem, bool use_trace_rcu) { /* 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); + __bpf_selem_unlink_storage(selem, use_trace_rcu); } struct bpf_local_storage_data * @@ -466,7 +475,7 @@ 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); + false, true); } unlock: @@ -548,7 +557,7 @@ void bpf_local_storage_map_free(struct bpf_local_storage_map *smap, migrate_disable(); __this_cpu_inc(*busy_counter); } - bpf_selem_unlink(selem); + bpf_selem_unlink(selem, false); if (busy_counter) { __this_cpu_dec(*busy_counter); migrate_enable(); diff --git a/kernel/bpf/bpf_lsm.c b/kernel/bpf/bpf_lsm.c index 064eccba641d..c1351df9f7ee 100644 --- a/kernel/bpf/bpf_lsm.c +++ b/kernel/bpf/bpf_lsm.c @@ -117,6 +117,21 @@ static const struct bpf_func_proto bpf_ima_file_hash_proto = { .allowed = bpf_ima_inode_hash_allowed, }; +BPF_CALL_1(bpf_get_attach_cookie, void *, ctx) +{ + struct bpf_trace_run_ctx *run_ctx; + + run_ctx = container_of(current->bpf_ctx, struct bpf_trace_run_ctx, run_ctx); + return run_ctx->bpf_cookie; +} + +static const struct bpf_func_proto bpf_get_attach_cookie_proto = { + .func = bpf_get_attach_cookie, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, +}; + static const struct bpf_func_proto * bpf_lsm_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { @@ -141,6 +156,8 @@ bpf_lsm_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return prog->aux->sleepable ? &bpf_ima_inode_hash_proto : NULL; case BPF_FUNC_ima_file_hash: return prog->aux->sleepable ? &bpf_ima_file_hash_proto : NULL; + case BPF_FUNC_get_attach_cookie: + return bpf_prog_has_trampoline(prog) ? &bpf_get_attach_cookie_proto : NULL; default: return tracing_prog_func_proto(func_id, prog); } diff --git a/kernel/bpf/bpf_struct_ops.c b/kernel/bpf/bpf_struct_ops.c index 21069dbe9138..d9a3c9207240 100644 --- a/kernel/bpf/bpf_struct_ops.c +++ b/kernel/bpf/bpf_struct_ops.c @@ -10,6 +10,7 @@ #include <linux/seq_file.h> #include <linux/refcount.h> #include <linux/mutex.h> +#include <linux/btf_ids.h> enum bpf_struct_ops_state { BPF_STRUCT_OPS_STATE_INIT, @@ -32,15 +33,15 @@ struct bpf_struct_ops_map { const struct bpf_struct_ops *st_ops; /* protect map_update */ struct mutex lock; - /* progs has all the bpf_prog that is populated + /* link has all the bpf_links that is populated * to the func ptr of the kernel's struct * (in kvalue.data). */ - struct bpf_prog **progs; + struct bpf_link **links; /* image is a page that has all the trampolines * that stores the func args before calling the bpf_prog. * A PAGE_SIZE "image" is enough to store all trampoline for - * "progs[]". + * "links[]". */ void *image; /* uvalue->data stores the kernel struct @@ -263,7 +264,7 @@ int bpf_struct_ops_map_sys_lookup_elem(struct bpf_map *map, void *key, /* No lock is needed. state and refcnt do not need * to be updated together under atomic context. */ - uvalue = (struct bpf_struct_ops_value *)value; + uvalue = value; memcpy(uvalue, st_map->uvalue, map->value_size); uvalue->state = state; refcount_set(&uvalue->refcnt, refcount_read(&kvalue->refcnt)); @@ -282,9 +283,9 @@ static void bpf_struct_ops_map_put_progs(struct bpf_struct_ops_map *st_map) u32 i; for (i = 0; i < btf_type_vlen(t); i++) { - if (st_map->progs[i]) { - bpf_prog_put(st_map->progs[i]); - st_map->progs[i] = NULL; + if (st_map->links[i]) { + bpf_link_put(st_map->links[i]); + st_map->links[i] = NULL; } } } @@ -315,18 +316,34 @@ 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, +static void bpf_struct_ops_link_release(struct bpf_link *link) +{ +} + +static void bpf_struct_ops_link_dealloc(struct bpf_link *link) +{ + struct bpf_tramp_link *tlink = container_of(link, struct bpf_tramp_link, link); + + kfree(tlink); +} + +const struct bpf_link_ops bpf_struct_ops_link_lops = { + .release = bpf_struct_ops_link_release, + .dealloc = bpf_struct_ops_link_dealloc, +}; + +int bpf_struct_ops_prepare_trampoline(struct bpf_tramp_links *tlinks, + struct bpf_tramp_link *link, 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; + tlinks[BPF_TRAMP_FENTRY].links[0] = link; + tlinks[BPF_TRAMP_FENTRY].nr_links = 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); + model, flags, tlinks, NULL); } static int bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key, @@ -337,7 +354,7 @@ static int bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key, struct bpf_struct_ops_value *uvalue, *kvalue; const struct btf_member *member; const struct btf_type *t = st_ops->type; - struct bpf_tramp_progs *tprogs = NULL; + struct bpf_tramp_links *tlinks = NULL; void *udata, *kdata; int prog_fd, err = 0; void *image, *image_end; @@ -353,7 +370,7 @@ static int bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key, if (err) return err; - uvalue = (struct bpf_struct_ops_value *)value; + uvalue = value; err = check_zero_holes(t, uvalue->data); if (err) return err; @@ -361,8 +378,8 @@ static int bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key, if (uvalue->state || refcount_read(&uvalue->refcnt)) return -EINVAL; - tprogs = kcalloc(BPF_TRAMP_MAX, sizeof(*tprogs), GFP_KERNEL); - if (!tprogs) + tlinks = kcalloc(BPF_TRAMP_MAX, sizeof(*tlinks), GFP_KERNEL); + if (!tlinks) return -ENOMEM; uvalue = (struct bpf_struct_ops_value *)st_map->uvalue; @@ -385,6 +402,7 @@ static int bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key, for_each_member(i, t, member) { const struct btf_type *mtype, *ptype; struct bpf_prog *prog; + struct bpf_tramp_link *link; u32 moff; moff = __btf_member_bit_offset(t, member) / 8; @@ -438,16 +456,26 @@ static int bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key, err = PTR_ERR(prog); goto reset_unlock; } - st_map->progs[i] = prog; if (prog->type != BPF_PROG_TYPE_STRUCT_OPS || prog->aux->attach_btf_id != st_ops->type_id || prog->expected_attach_type != i) { + bpf_prog_put(prog); err = -EINVAL; goto reset_unlock; } - err = bpf_struct_ops_prepare_trampoline(tprogs, prog, + link = kzalloc(sizeof(*link), GFP_USER); + if (!link) { + bpf_prog_put(prog); + err = -ENOMEM; + goto reset_unlock; + } + bpf_link_init(&link->link, BPF_LINK_TYPE_STRUCT_OPS, + &bpf_struct_ops_link_lops, prog); + st_map->links[i] = &link->link; + + err = bpf_struct_ops_prepare_trampoline(tlinks, link, &st_ops->func_models[i], image, image_end); if (err < 0) @@ -490,7 +518,7 @@ reset_unlock: memset(uvalue, 0, map->value_size); memset(kvalue, 0, map->value_size); unlock: - kfree(tprogs); + kfree(tlinks); mutex_unlock(&st_map->lock); return err; } @@ -545,9 +573,9 @@ static void bpf_struct_ops_map_free(struct bpf_map *map) { struct bpf_struct_ops_map *st_map = (struct bpf_struct_ops_map *)map; - if (st_map->progs) + if (st_map->links) bpf_struct_ops_map_put_progs(st_map); - bpf_map_area_free(st_map->progs); + bpf_map_area_free(st_map->links); bpf_jit_free_exec(st_map->image); bpf_map_area_free(st_map->uvalue); bpf_map_area_free(st_map); @@ -596,11 +624,11 @@ static struct bpf_map *bpf_struct_ops_map_alloc(union bpf_attr *attr) map = &st_map->map; st_map->uvalue = bpf_map_area_alloc(vt->size, NUMA_NO_NODE); - st_map->progs = - bpf_map_area_alloc(btf_type_vlen(t) * sizeof(struct bpf_prog *), + st_map->links = + bpf_map_area_alloc(btf_type_vlen(t) * sizeof(struct bpf_links *), NUMA_NO_NODE); st_map->image = bpf_jit_alloc_exec(PAGE_SIZE); - if (!st_map->uvalue || !st_map->progs || !st_map->image) { + if (!st_map->uvalue || !st_map->links || !st_map->image) { bpf_struct_ops_map_free(map); return ERR_PTR(-ENOMEM); } @@ -612,7 +640,7 @@ static struct bpf_map *bpf_struct_ops_map_alloc(union bpf_attr *attr) return map; } -static int bpf_struct_ops_map_btf_id; +BTF_ID_LIST_SINGLE(bpf_struct_ops_map_btf_ids, struct, bpf_struct_ops_map) const struct bpf_map_ops bpf_struct_ops_map_ops = { .map_alloc_check = bpf_struct_ops_map_alloc_check, .map_alloc = bpf_struct_ops_map_alloc, @@ -622,8 +650,7 @@ const struct bpf_map_ops bpf_struct_ops_map_ops = { .map_delete_elem = bpf_struct_ops_map_delete_elem, .map_update_elem = bpf_struct_ops_map_update_elem, .map_seq_show_elem = bpf_struct_ops_map_seq_show_elem, - .map_btf_name = "bpf_struct_ops_map", - .map_btf_id = &bpf_struct_ops_map_btf_id, + .map_btf_id = &bpf_struct_ops_map_btf_ids[0], }; /* "const void *" because some subsystem is diff --git a/kernel/bpf/bpf_task_storage.c b/kernel/bpf/bpf_task_storage.c index 6638a0ecc3d2..e9014dc62682 100644 --- a/kernel/bpf/bpf_task_storage.c +++ b/kernel/bpf/bpf_task_storage.c @@ -102,7 +102,7 @@ void bpf_task_storage_free(struct task_struct *task) */ bpf_selem_unlink_map(selem); free_task_storage = bpf_selem_unlink_storage_nolock( - local_storage, selem, false); + local_storage, selem, false, false); } raw_spin_unlock_irqrestore(&local_storage->lock, flags); bpf_task_storage_unlock(); @@ -192,7 +192,7 @@ static int task_storage_delete(struct task_struct *task, struct bpf_map *map) if (!sdata) return -ENOENT; - bpf_selem_unlink(SELEM(sdata)); + bpf_selem_unlink(SELEM(sdata), true); return 0; } @@ -307,7 +307,7 @@ static void task_storage_map_free(struct bpf_map *map) bpf_local_storage_map_free(smap, &bpf_task_storage_busy); } -static int task_storage_map_btf_id; +BTF_ID_LIST_SINGLE(task_storage_map_btf_ids, struct, bpf_local_storage_map) const struct bpf_map_ops task_storage_map_ops = { .map_meta_equal = bpf_map_meta_equal, .map_alloc_check = bpf_local_storage_map_alloc_check, @@ -318,8 +318,7 @@ const struct bpf_map_ops task_storage_map_ops = { .map_update_elem = bpf_pid_task_storage_update_elem, .map_delete_elem = bpf_pid_task_storage_delete_elem, .map_check_btf = bpf_local_storage_map_check_btf, - .map_btf_name = "bpf_local_storage_map", - .map_btf_id = &task_storage_map_btf_id, + .map_btf_id = &task_storage_map_btf_ids[0], .map_owner_storage_ptr = task_storage_ptr, }; diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 0918a39279f6..7bccaa4646e5 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -202,17 +202,25 @@ enum btf_kfunc_hook { BTF_KFUNC_HOOK_XDP, BTF_KFUNC_HOOK_TC, BTF_KFUNC_HOOK_STRUCT_OPS, + BTF_KFUNC_HOOK_TRACING, + BTF_KFUNC_HOOK_SYSCALL, BTF_KFUNC_HOOK_MAX, }; enum { BTF_KFUNC_SET_MAX_CNT = 32, + BTF_DTOR_KFUNC_MAX_CNT = 256, }; struct btf_kfunc_set_tab { struct btf_id_set *sets[BTF_KFUNC_HOOK_MAX][BTF_KFUNC_TYPE_MAX]; }; +struct btf_id_dtor_kfunc_tab { + u32 cnt; + struct btf_id_dtor_kfunc dtors[]; +}; + struct btf { void *data; struct btf_type **types; @@ -228,6 +236,7 @@ struct btf { u32 id; struct rcu_head rcu; struct btf_kfunc_set_tab *kfunc_set_tab; + struct btf_id_dtor_kfunc_tab *dtor_kfunc_tab; /* split BTF support */ struct btf *base_btf; @@ -1616,8 +1625,19 @@ free_tab: btf->kfunc_set_tab = NULL; } +static void btf_free_dtor_kfunc_tab(struct btf *btf) +{ + struct btf_id_dtor_kfunc_tab *tab = btf->dtor_kfunc_tab; + + if (!tab) + return; + kfree(tab); + btf->dtor_kfunc_tab = NULL; +} + static void btf_free(struct btf *btf) { + btf_free_dtor_kfunc_tab(btf); btf_free_kfunc_set_tab(btf); kvfree(btf->types); kvfree(btf->resolved_sizes); @@ -3163,24 +3183,86 @@ 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_type { + BTF_FIELD_SPIN_LOCK, + BTF_FIELD_TIMER, + BTF_FIELD_KPTR, +}; + +enum { + BTF_FIELD_IGNORE = 0, + BTF_FIELD_FOUND = 1, +}; + +struct btf_field_info { + u32 type_id; + u32 off; + enum bpf_kptr_type type; +}; + +static int btf_find_struct(const struct btf *btf, const struct btf_type *t, + u32 off, int sz, struct btf_field_info *info) +{ + if (!__btf_type_is_struct(t)) + return BTF_FIELD_IGNORE; + if (t->size != sz) + return BTF_FIELD_IGNORE; + info->off = off; + return BTF_FIELD_FOUND; +} + +static int btf_find_kptr(const struct btf *btf, const struct btf_type *t, + u32 off, int sz, struct btf_field_info *info) +{ + enum bpf_kptr_type type; + u32 res_id; + + /* For PTR, sz is always == 8 */ + if (!btf_type_is_ptr(t)) + return BTF_FIELD_IGNORE; + t = btf_type_by_id(btf, t->type); + + if (!btf_type_is_type_tag(t)) + return BTF_FIELD_IGNORE; + /* Reject extra tags */ + if (btf_type_is_type_tag(btf_type_by_id(btf, t->type))) + return -EINVAL; + if (!strcmp("kptr", __btf_name_by_offset(btf, t->name_off))) + type = BPF_KPTR_UNREF; + else if (!strcmp("kptr_ref", __btf_name_by_offset(btf, t->name_off))) + type = BPF_KPTR_REF; + else + return -EINVAL; + + /* Get the base type */ + t = btf_type_skip_modifiers(btf, t->type, &res_id); + /* Only pointer to struct is allowed */ + if (!__btf_type_is_struct(t)) + return -EINVAL; + + info->type_id = res_id; + info->off = off; + info->type = type; + return BTF_FIELD_FOUND; +} + static int btf_find_struct_field(const struct btf *btf, const struct btf_type *t, - const char *name, int sz, int align) + const char *name, int sz, int align, + enum btf_field_type field_type, + struct btf_field_info *info, int info_cnt) { const struct btf_member *member; - u32 i, off = -ENOENT; + struct btf_field_info tmp; + int ret, idx = 0; + u32 i, off; for_each_member(i, t, member) { const struct btf_type *member_type = btf_type_by_id(btf, member->type); - if (!__btf_type_is_struct(member_type)) - continue; - if (member_type->size != sz) - continue; - if (strcmp(__btf_name_by_offset(btf, member_type->name_off), name)) + + if (name && strcmp(__btf_name_by_offset(btf, member_type->name_off), name)) continue; - if (off != -ENOENT) - /* only one such field is allowed */ - return -E2BIG; + off = __btf_member_bit_offset(t, member); if (off % 8) /* valid C code cannot generate such BTF */ @@ -3188,46 +3270,115 @@ static int btf_find_struct_field(const struct btf *btf, const struct btf_type *t off /= 8; if (off % align) return -EINVAL; + + switch (field_type) { + case BTF_FIELD_SPIN_LOCK: + case BTF_FIELD_TIMER: + ret = btf_find_struct(btf, member_type, off, sz, + idx < info_cnt ? &info[idx] : &tmp); + if (ret < 0) + return ret; + break; + case BTF_FIELD_KPTR: + ret = btf_find_kptr(btf, member_type, off, sz, + idx < info_cnt ? &info[idx] : &tmp); + if (ret < 0) + return ret; + break; + default: + return -EFAULT; + } + + if (ret == BTF_FIELD_IGNORE) + continue; + if (idx >= info_cnt) + return -E2BIG; + ++idx; } - return off; + return idx; } static int btf_find_datasec_var(const struct btf *btf, const struct btf_type *t, - const char *name, int sz, int align) + const char *name, int sz, int align, + enum btf_field_type field_type, + struct btf_field_info *info, int info_cnt) { const struct btf_var_secinfo *vsi; - u32 i, off = -ENOENT; + struct btf_field_info tmp; + int ret, idx = 0; + u32 i, off; for_each_vsi(i, t, vsi) { const struct btf_type *var = btf_type_by_id(btf, vsi->type); const struct btf_type *var_type = btf_type_by_id(btf, var->type); - if (!__btf_type_is_struct(var_type)) - continue; - if (var_type->size != sz) + off = vsi->offset; + + if (name && strcmp(__btf_name_by_offset(btf, var_type->name_off), name)) continue; if (vsi->size != sz) continue; - if (strcmp(__btf_name_by_offset(btf, var_type->name_off), name)) - continue; - if (off != -ENOENT) - /* only one such field is allowed */ - return -E2BIG; - off = vsi->offset; if (off % align) return -EINVAL; + + switch (field_type) { + case BTF_FIELD_SPIN_LOCK: + case BTF_FIELD_TIMER: + ret = btf_find_struct(btf, var_type, off, sz, + idx < info_cnt ? &info[idx] : &tmp); + if (ret < 0) + return ret; + break; + case BTF_FIELD_KPTR: + ret = btf_find_kptr(btf, var_type, off, sz, + idx < info_cnt ? &info[idx] : &tmp); + if (ret < 0) + return ret; + break; + default: + return -EFAULT; + } + + if (ret == BTF_FIELD_IGNORE) + continue; + if (idx >= info_cnt) + return -E2BIG; + ++idx; } - return off; + return idx; } static int btf_find_field(const struct btf *btf, const struct btf_type *t, - const char *name, int sz, int align) + enum btf_field_type field_type, + struct btf_field_info *info, int info_cnt) { + const char *name; + int sz, align; + + switch (field_type) { + case BTF_FIELD_SPIN_LOCK: + name = "bpf_spin_lock"; + sz = sizeof(struct bpf_spin_lock); + align = __alignof__(struct bpf_spin_lock); + break; + case BTF_FIELD_TIMER: + name = "bpf_timer"; + sz = sizeof(struct bpf_timer); + align = __alignof__(struct bpf_timer); + break; + case BTF_FIELD_KPTR: + name = NULL; + sz = sizeof(u64); + align = 8; + break; + default: + return -EFAULT; + } if (__btf_type_is_struct(t)) - return btf_find_struct_field(btf, t, name, sz, align); + return btf_find_struct_field(btf, t, name, sz, align, field_type, info, info_cnt); else if (btf_type_is_datasec(t)) - return btf_find_datasec_var(btf, t, name, sz, align); + return btf_find_datasec_var(btf, t, name, sz, align, field_type, info, info_cnt); return -EINVAL; } @@ -3237,16 +3388,130 @@ static int btf_find_field(const struct btf *btf, const struct btf_type *t, */ int btf_find_spin_lock(const struct btf *btf, const struct btf_type *t) { - return btf_find_field(btf, t, "bpf_spin_lock", - sizeof(struct bpf_spin_lock), - __alignof__(struct bpf_spin_lock)); + struct btf_field_info info; + int ret; + + ret = btf_find_field(btf, t, BTF_FIELD_SPIN_LOCK, &info, 1); + if (ret < 0) + return ret; + if (!ret) + return -ENOENT; + return info.off; } int btf_find_timer(const struct btf *btf, const struct btf_type *t) { - return btf_find_field(btf, t, "bpf_timer", - sizeof(struct bpf_timer), - __alignof__(struct bpf_timer)); + struct btf_field_info info; + int ret; + + ret = btf_find_field(btf, t, BTF_FIELD_TIMER, &info, 1); + if (ret < 0) + return ret; + if (!ret) + return -ENOENT; + return info.off; +} + +struct bpf_map_value_off *btf_parse_kptrs(const struct btf *btf, + const struct btf_type *t) +{ + struct btf_field_info info_arr[BPF_MAP_VALUE_OFF_MAX]; + struct bpf_map_value_off *tab; + struct btf *kernel_btf = NULL; + struct module *mod = NULL; + int ret, i, nr_off; + + ret = btf_find_field(btf, t, BTF_FIELD_KPTR, info_arr, ARRAY_SIZE(info_arr)); + if (ret < 0) + return ERR_PTR(ret); + if (!ret) + return NULL; + + nr_off = ret; + tab = kzalloc(offsetof(struct bpf_map_value_off, off[nr_off]), GFP_KERNEL | __GFP_NOWARN); + if (!tab) + return ERR_PTR(-ENOMEM); + + for (i = 0; i < nr_off; i++) { + const struct btf_type *t; + s32 id; + + /* Find type in map BTF, and use it to look up the matching type + * in vmlinux or module BTFs, by name and kind. + */ + t = btf_type_by_id(btf, info_arr[i].type_id); + id = bpf_find_btf_id(__btf_name_by_offset(btf, t->name_off), BTF_INFO_KIND(t->info), + &kernel_btf); + if (id < 0) { + ret = id; + goto end; + } + + /* Find and stash the function pointer for the destruction function that + * needs to be eventually invoked from the map free path. + */ + if (info_arr[i].type == BPF_KPTR_REF) { + const struct btf_type *dtor_func; + const char *dtor_func_name; + unsigned long addr; + s32 dtor_btf_id; + + /* This call also serves as a whitelist of allowed objects that + * 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); + if (dtor_btf_id < 0) { + ret = dtor_btf_id; + goto end_btf; + } + + dtor_func = btf_type_by_id(kernel_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 (!mod) { + ret = -ENXIO; + goto end_btf; + } + } + + /* 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); + addr = kallsyms_lookup_name(dtor_func_name); + if (!addr) { + ret = -EINVAL; + goto end_mod; + } + tab->off[i].kptr.dtor = (void *)addr; + } + + tab->off[i].offset = info_arr[i].off; + tab->off[i].type = info_arr[i].type; + tab->off[i].kptr.btf_id = id; + tab->off[i].kptr.btf = kernel_btf; + tab->off[i].kptr.module = mod; + } + tab->nr_off = nr_off; + return tab; +end_mod: + module_put(mod); +end_btf: + btf_put(kernel_btf); +end: + while (i--) { + btf_put(tab->off[i].kptr.btf); + if (tab->off[i].kptr.module) + module_put(tab->off[i].kptr.module); + } + kfree(tab); + return ERR_PTR(ret); } static void __btf_struct_show(const struct btf *btf, const struct btf_type *t, @@ -4541,6 +4806,48 @@ static int btf_parse_hdr(struct btf_verifier_env *env) return 0; } +static int btf_check_type_tags(struct btf_verifier_env *env, + struct btf *btf, int start_id) +{ + int i, n, good_id = start_id - 1; + bool in_tags; + + n = btf_nr_types(btf); + for (i = start_id; i < n; i++) { + const struct btf_type *t; + u32 cur_id = i; + + t = btf_type_by_id(btf, i); + if (!t) + return -EINVAL; + if (!btf_type_is_modifier(t)) + continue; + + cond_resched(); + + in_tags = btf_type_is_type_tag(t); + while (btf_type_is_modifier(t)) { + if (btf_type_is_type_tag(t)) { + if (!in_tags) { + btf_verifier_log(env, "Type tags don't precede modifiers"); + return -EINVAL; + } + } else if (in_tags) { + in_tags = false; + } + if (cur_id <= good_id) + break; + /* Move to next type */ + cur_id = t->type; + t = btf_type_by_id(btf, cur_id); + if (!t) + return -EINVAL; + } + good_id = i; + } + 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) { @@ -4608,6 +4915,10 @@ static struct btf *btf_parse(bpfptr_t btf_data, u32 btf_data_size, if (err) goto errout; + err = btf_check_type_tags(env, btf, 1); + if (err) + goto errout; + if (log->level && bpf_verifier_log_full(log)) { err = -ENOSPC; goto errout; @@ -4716,41 +5027,6 @@ btf_get_prog_ctx_type(struct bpf_verifier_log *log, const struct btf *btf, return ctx_type; } -static const struct bpf_map_ops * const btf_vmlinux_map_ops[] = { -#define BPF_PROG_TYPE(_id, _name, prog_ctx_type, kern_ctx_type) -#define BPF_LINK_TYPE(_id, _name) -#define BPF_MAP_TYPE(_id, _ops) \ - [_id] = &_ops, -#include <linux/bpf_types.h> -#undef BPF_PROG_TYPE -#undef BPF_LINK_TYPE -#undef BPF_MAP_TYPE -}; - -static int btf_vmlinux_map_ids_init(const struct btf *btf, - struct bpf_verifier_log *log) -{ - const struct bpf_map_ops *ops; - int i, btf_id; - - for (i = 0; i < ARRAY_SIZE(btf_vmlinux_map_ops); ++i) { - ops = btf_vmlinux_map_ops[i]; - if (!ops || (!ops->map_btf_name && !ops->map_btf_id)) - continue; - if (!ops->map_btf_name || !ops->map_btf_id) { - bpf_log(log, "map type %d is misconfigured\n", i); - return -EINVAL; - } - btf_id = btf_find_by_name_kind(btf, ops->map_btf_name, - BTF_KIND_STRUCT); - if (btf_id < 0) - return btf_id; - *ops->map_btf_id = btf_id; - } - - return 0; -} - static int btf_translate_to_vmlinux(struct bpf_verifier_log *log, struct btf *btf, const struct btf_type *t, @@ -4809,14 +5085,13 @@ struct btf *btf_parse_vmlinux(void) if (err) goto errout; + err = btf_check_type_tags(env, btf, 1); + if (err) + goto errout; + /* btf_parse_vmlinux() runs under bpf_verifier_lock */ bpf_ctx_convert.t = btf_type_by_id(btf, bpf_ctx_convert_btf_id[0]); - /* find bpf map structs for map_ptr access checking */ - err = btf_vmlinux_map_ids_init(btf, log); - if (err < 0) - goto errout; - bpf_struct_ops_init(btf, log); refcount_set(&btf->refcnt, 1); @@ -4894,6 +5169,10 @@ static struct btf *btf_parse_module(const char *module_name, const void *data, u if (err) goto errout; + err = btf_check_type_tags(env, btf, btf_nr_types(base_btf)); + if (err) + goto errout; + btf_verifier_env_free(env); refcount_set(&btf->refcnt, 1); return btf; @@ -5429,7 +5708,8 @@ static bool btf_types_are_same(const struct btf *btf1, u32 id1, bool btf_struct_ids_match(struct bpf_verifier_log *log, const struct btf *btf, u32 id, int off, - const struct btf *need_btf, u32 need_type_id) + const struct btf *need_btf, u32 need_type_id, + bool strict) { const struct btf_type *type; enum bpf_type_flag flag; @@ -5438,7 +5718,12 @@ bool btf_struct_ids_match(struct bpf_verifier_log *log, /* Are we already done? */ if (off == 0 && btf_types_are_same(btf, id, need_btf, need_type_id)) return true; - + /* In case of strict type match, we do not walk struct, the top level + * type match must succeed. When strict is true, off should have already + * been 0. + */ + if (strict) + return false; again: type = btf_type_by_id(btf, id); if (!type) @@ -5772,11 +6057,11 @@ static int btf_check_func_arg_match(struct bpf_verifier_env *env, struct bpf_verifier_log *log = &env->log; u32 i, nargs, ref_id, ref_obj_id = 0; bool is_kfunc = btf_is_kernel(btf); + bool rel = false, kptr_get = false; const char *func_name, *ref_tname; const struct btf_type *t, *ref_t; const struct btf_param *args; int ref_regno = 0, ret; - bool rel = false; t = btf_type_by_id(btf, func_id); if (!t || !btf_type_is_func(t)) { @@ -5802,14 +6087,19 @@ static int btf_check_func_arg_match(struct bpf_verifier_env *env, return -EINVAL; } - /* Only kfunc can be release func */ - if (is_kfunc) + if (is_kfunc) { + /* Only kfunc can be release func */ rel = btf_kfunc_id_set_contains(btf, resolve_prog_type(env->prog), BTF_KFUNC_TYPE_RELEASE, func_id); + kptr_get = btf_kfunc_id_set_contains(btf, resolve_prog_type(env->prog), + BTF_KFUNC_TYPE_KPTR_ACQUIRE, func_id); + } + /* check that BTF function arguments match actual types that the * verifier sees. */ for (i = 0; i < nargs; i++) { + enum bpf_arg_type arg_type = ARG_DONTCARE; u32 regno = i + 1; struct bpf_reg_state *reg = ®s[regno]; @@ -5830,12 +6120,58 @@ static int btf_check_func_arg_match(struct bpf_verifier_env *env, ref_t = btf_type_skip_modifiers(btf, t->type, &ref_id); ref_tname = btf_name_by_offset(btf, ref_t->name_off); - ret = check_func_arg_reg_off(env, reg, regno, ARG_DONTCARE, rel); + if (rel && reg->ref_obj_id) + arg_type |= OBJ_RELEASE; + ret = check_func_arg_reg_off(env, reg, regno, arg_type); if (ret < 0) return ret; - if (btf_get_prog_ctx_type(log, btf, t, - env->prog->type, i)) { + /* kptr_get is only true for kfunc */ + if (i == 0 && kptr_get) { + struct bpf_map_value_off_desc *off_desc; + + if (reg->type != PTR_TO_MAP_VALUE) { + bpf_log(log, "arg#0 expected pointer to map value\n"); + return -EINVAL; + } + + /* check_func_arg_reg_off allows var_off for + * PTR_TO_MAP_VALUE, but we need fixed offset to find + * off_desc. + */ + if (!tnum_is_const(reg->var_off)) { + bpf_log(log, "arg#0 must have constant offset\n"); + return -EINVAL; + } + + off_desc = bpf_map_kptr_off_contains(reg->map_ptr, reg->off + reg->var_off.value); + if (!off_desc || off_desc->type != BPF_KPTR_REF) { + bpf_log(log, "arg#0 no referenced kptr at map value offset=%llu\n", + reg->off + reg->var_off.value); + return -EINVAL; + } + + if (!btf_type_is_ptr(ref_t)) { + bpf_log(log, "arg#0 BTF type must be a double pointer\n"); + return -EINVAL; + } + + ref_t = btf_type_skip_modifiers(btf, ref_t->type, &ref_id); + ref_tname = btf_name_by_offset(btf, ref_t->name_off); + + if (!btf_type_is_struct(ref_t)) { + bpf_log(log, "kernel function %s args#%d pointer type %s %s is not supported\n", + func_name, i, btf_type_str(ref_t), ref_tname); + return -EINVAL; + } + if (!btf_struct_ids_match(log, btf, ref_id, 0, off_desc->kptr.btf, + off_desc->kptr.btf_id, true)) { + bpf_log(log, "kernel function %s args#%d expected pointer to %s %s\n", + func_name, i, btf_type_str(ref_t), ref_tname); + return -EINVAL; + } + /* rest of the arguments can be anything, like normal kfunc */ + } else if (btf_get_prog_ctx_type(log, btf, t, env->prog->type, i)) { /* If function expects ctx type in BTF check that caller * is passing PTR_TO_CTX. */ @@ -5862,11 +6198,7 @@ static int btf_check_func_arg_match(struct bpf_verifier_env *env, if (reg->type == PTR_TO_BTF_ID) { reg_btf = reg->btf; reg_ref_id = reg->btf_id; - /* Ensure only one argument is referenced - * PTR_TO_BTF_ID, check_func_arg_reg_off relies - * on only one referenced register being allowed - * for kfuncs. - */ + /* Ensure only one argument is referenced PTR_TO_BTF_ID */ if (reg->ref_obj_id) { if (ref_obj_id) { bpf_log(log, "verifier internal error: more than one arg with ref_obj_id R%d %u %u\n", @@ -5886,7 +6218,7 @@ static int btf_check_func_arg_match(struct bpf_verifier_env *env, reg_ref_tname = btf_name_by_offset(reg_btf, reg_ref_t->name_off); if (!btf_struct_ids_match(log, reg_btf, reg_ref_id, - reg->off, btf, ref_id)) { + reg->off, btf, ref_id, rel && reg->ref_obj_id)) { bpf_log(log, "kernel function %s args#%d expected pointer to %s %s but R%d has a pointer to %s %s\n", func_name, i, btf_type_str(ref_t), ref_tname, @@ -6780,6 +7112,10 @@ static int bpf_prog_type_to_kfunc_hook(enum bpf_prog_type prog_type) return BTF_KFUNC_HOOK_TC; case BPF_PROG_TYPE_STRUCT_OPS: return BTF_KFUNC_HOOK_STRUCT_OPS; + case BPF_PROG_TYPE_TRACING: + return BTF_KFUNC_HOOK_TRACING; + case BPF_PROG_TYPE_SYSCALL: + return BTF_KFUNC_HOOK_SYSCALL; default: return BTF_KFUNC_HOOK_MAX; } @@ -6832,6 +7168,138 @@ int register_btf_kfunc_id_set(enum bpf_prog_type prog_type, } EXPORT_SYMBOL_GPL(register_btf_kfunc_id_set); +s32 btf_find_dtor_kfunc(struct btf *btf, u32 btf_id) +{ + struct btf_id_dtor_kfunc_tab *tab = btf->dtor_kfunc_tab; + struct btf_id_dtor_kfunc *dtor; + + if (!tab) + return -ENOENT; + /* Even though the size of tab->dtors[0] is > sizeof(u32), we only need + * to compare the first u32 with btf_id, so we can reuse btf_id_cmp_func. + */ + BUILD_BUG_ON(offsetof(struct btf_id_dtor_kfunc, btf_id) != 0); + dtor = bsearch(&btf_id, tab->dtors, tab->cnt, sizeof(tab->dtors[0]), btf_id_cmp_func); + if (!dtor) + return -ENOENT; + return dtor->kfunc_btf_id; +} + +static int btf_check_dtor_kfuncs(struct btf *btf, const struct btf_id_dtor_kfunc *dtors, u32 cnt) +{ + const struct btf_type *dtor_func, *dtor_func_proto, *t; + const struct btf_param *args; + s32 dtor_btf_id; + u32 nr_args, i; + + for (i = 0; i < cnt; i++) { + dtor_btf_id = dtors[i].kfunc_btf_id; + + dtor_func = btf_type_by_id(btf, dtor_btf_id); + if (!dtor_func || !btf_type_is_func(dtor_func)) + return -EINVAL; + + dtor_func_proto = btf_type_by_id(btf, dtor_func->type); + if (!dtor_func_proto || !btf_type_is_func_proto(dtor_func_proto)) + return -EINVAL; + + /* Make sure the prototype of the destructor kfunc is 'void func(type *)' */ + t = btf_type_by_id(btf, dtor_func_proto->type); + if (!t || !btf_type_is_void(t)) + return -EINVAL; + + nr_args = btf_type_vlen(dtor_func_proto); + if (nr_args != 1) + return -EINVAL; + args = btf_params(dtor_func_proto); + t = btf_type_by_id(btf, args[0].type); + /* Allow any pointer type, as width on targets Linux supports + * will be same for all pointer types (i.e. sizeof(void *)) + */ + if (!t || !btf_type_is_ptr(t)) + return -EINVAL; + } + return 0; +} + +/* This function must be invoked only from initcalls/module init functions */ +int register_btf_id_dtor_kfuncs(const struct btf_id_dtor_kfunc *dtors, u32 add_cnt, + struct module *owner) +{ + struct btf_id_dtor_kfunc_tab *tab; + struct btf *btf; + u32 tab_cnt; + int ret; + + btf = btf_get_module_btf(owner); + if (!btf) { + if (!owner && IS_ENABLED(CONFIG_DEBUG_INFO_BTF)) { + pr_err("missing vmlinux BTF, cannot register dtor kfuncs\n"); + return -ENOENT; + } + if (owner && IS_ENABLED(CONFIG_DEBUG_INFO_BTF_MODULES)) { + pr_err("missing module BTF, cannot register dtor kfuncs\n"); + return -ENOENT; + } + return 0; + } + if (IS_ERR(btf)) + return PTR_ERR(btf); + + if (add_cnt >= BTF_DTOR_KFUNC_MAX_CNT) { + pr_err("cannot register more than %d kfunc destructors\n", BTF_DTOR_KFUNC_MAX_CNT); + ret = -E2BIG; + goto end; + } + + /* Ensure that the prototype of dtor kfuncs being registered is sane */ + ret = btf_check_dtor_kfuncs(btf, dtors, add_cnt); + if (ret < 0) + goto end; + + tab = btf->dtor_kfunc_tab; + /* Only one call allowed for modules */ + if (WARN_ON_ONCE(tab && btf_is_module(btf))) { + ret = -EINVAL; + goto end; + } + + tab_cnt = tab ? tab->cnt : 0; + if (tab_cnt > U32_MAX - add_cnt) { + ret = -EOVERFLOW; + goto end; + } + if (tab_cnt + add_cnt >= BTF_DTOR_KFUNC_MAX_CNT) { + pr_err("cannot register more than %d kfunc destructors\n", BTF_DTOR_KFUNC_MAX_CNT); + ret = -E2BIG; + goto end; + } + + tab = krealloc(btf->dtor_kfunc_tab, + offsetof(struct btf_id_dtor_kfunc_tab, dtors[tab_cnt + add_cnt]), + GFP_KERNEL | __GFP_NOWARN); + if (!tab) { + ret = -ENOMEM; + goto end; + } + + if (!btf->dtor_kfunc_tab) + tab->cnt = 0; + btf->dtor_kfunc_tab = tab; + + memcpy(tab->dtors + tab->cnt, dtors, add_cnt * sizeof(tab->dtors[0])); + tab->cnt += add_cnt; + + sort(tab->dtors, tab->cnt, sizeof(tab->dtors[0]), btf_id_cmp_func, NULL); + + return 0; +end: + btf_free_dtor_kfunc_tab(btf); + btf_put(btf); + return ret; +} +EXPORT_SYMBOL_GPL(register_btf_id_dtor_kfuncs); + #define MAX_TYPES_ARE_COMPAT_DEPTH 2 static diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c index 128028efda64..afb414b26d01 100644 --- a/kernel/bpf/cgroup.c +++ b/kernel/bpf/cgroup.c @@ -22,6 +22,45 @@ DEFINE_STATIC_KEY_ARRAY_FALSE(cgroup_bpf_enabled_key, MAX_CGROUP_BPF_ATTACH_TYPE); EXPORT_SYMBOL(cgroup_bpf_enabled_key); +/* __always_inline is necessary to prevent indirect call through run_prog + * function pointer. + */ +static __always_inline int +bpf_prog_run_array_cg(const struct cgroup_bpf *cgrp, + enum cgroup_bpf_attach_type atype, + const void *ctx, bpf_prog_run_fn run_prog, + int retval, u32 *ret_flags) +{ + const struct bpf_prog_array_item *item; + const struct bpf_prog *prog; + const struct bpf_prog_array *array; + struct bpf_run_ctx *old_run_ctx; + struct bpf_cg_run_ctx run_ctx; + u32 func_ret; + + run_ctx.retval = retval; + migrate_disable(); + rcu_read_lock(); + array = rcu_dereference(cgrp->effective[atype]); + item = &array->items[0]; + old_run_ctx = bpf_set_run_ctx(&run_ctx.run_ctx); + while ((prog = READ_ONCE(item->prog))) { + run_ctx.prog_item = item; + func_ret = run_prog(prog, ctx); + if (ret_flags) { + *(ret_flags) |= (func_ret >> 1); + func_ret &= 1; + } + if (!func_ret && !IS_ERR_VALUE((long)run_ctx.retval)) + run_ctx.retval = -EPERM; + item++; + } + bpf_reset_run_ctx(old_run_ctx); + rcu_read_unlock(); + migrate_enable(); + return run_ctx.retval; +} + void cgroup_bpf_offline(struct cgroup *cgrp) { cgroup_get(cgrp); @@ -1075,11 +1114,38 @@ int __cgroup_bpf_run_filter_skb(struct sock *sk, bpf_compute_and_save_data_end(skb, &saved_data_end); if (atype == CGROUP_INET_EGRESS) { - ret = BPF_PROG_CGROUP_INET_EGRESS_RUN_ARRAY( - cgrp->bpf.effective[atype], skb, __bpf_prog_run_save_cb); + u32 flags = 0; + bool cn; + + ret = bpf_prog_run_array_cg(&cgrp->bpf, atype, skb, + __bpf_prog_run_save_cb, 0, &flags); + + /* Return values of CGROUP EGRESS BPF programs are: + * 0: drop packet + * 1: keep packet + * 2: drop packet and cn + * 3: keep packet and cn + * + * The returned value is then converted to one of the NET_XMIT + * or an error code that is then interpreted as drop packet + * (and no cn): + * 0: NET_XMIT_SUCCESS skb should be transmitted + * 1: NET_XMIT_DROP skb should be dropped and cn + * 2: NET_XMIT_CN skb should be transmitted and cn + * 3: -err skb should be dropped + */ + + cn = flags & BPF_RET_SET_CN; + if (ret && !IS_ERR_VALUE((long)ret)) + ret = -EFAULT; + if (!ret) + ret = (cn ? NET_XMIT_CN : NET_XMIT_SUCCESS); + else + ret = (cn ? NET_XMIT_DROP : ret); } else { - ret = BPF_PROG_RUN_ARRAY_CG(cgrp->bpf.effective[atype], skb, - __bpf_prog_run_save_cb, 0); + ret = bpf_prog_run_array_cg(&cgrp->bpf, atype, + skb, __bpf_prog_run_save_cb, 0, + NULL); if (ret && !IS_ERR_VALUE((long)ret)) ret = -EFAULT; } @@ -1109,8 +1175,8 @@ int __cgroup_bpf_run_filter_sk(struct sock *sk, { struct cgroup *cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data); - return BPF_PROG_RUN_ARRAY_CG(cgrp->bpf.effective[atype], sk, - bpf_prog_run, 0); + return bpf_prog_run_array_cg(&cgrp->bpf, atype, sk, bpf_prog_run, 0, + NULL); } EXPORT_SYMBOL(__cgroup_bpf_run_filter_sk); @@ -1155,8 +1221,8 @@ int __cgroup_bpf_run_filter_sock_addr(struct sock *sk, } cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data); - return BPF_PROG_RUN_ARRAY_CG_FLAGS(cgrp->bpf.effective[atype], &ctx, - bpf_prog_run, 0, flags); + return bpf_prog_run_array_cg(&cgrp->bpf, atype, &ctx, bpf_prog_run, + 0, flags); } EXPORT_SYMBOL(__cgroup_bpf_run_filter_sock_addr); @@ -1182,8 +1248,8 @@ int __cgroup_bpf_run_filter_sock_ops(struct sock *sk, { struct cgroup *cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data); - return BPF_PROG_RUN_ARRAY_CG(cgrp->bpf.effective[atype], sock_ops, - bpf_prog_run, 0); + return bpf_prog_run_array_cg(&cgrp->bpf, atype, sock_ops, bpf_prog_run, + 0, NULL); } EXPORT_SYMBOL(__cgroup_bpf_run_filter_sock_ops); @@ -1200,8 +1266,8 @@ int __cgroup_bpf_check_dev_permission(short dev_type, u32 major, u32 minor, rcu_read_lock(); cgrp = task_dfl_cgroup(current); - ret = BPF_PROG_RUN_ARRAY_CG(cgrp->bpf.effective[atype], &ctx, - bpf_prog_run, 0); + ret = bpf_prog_run_array_cg(&cgrp->bpf, atype, &ctx, bpf_prog_run, 0, + NULL); rcu_read_unlock(); return ret; @@ -1366,8 +1432,8 @@ int __cgroup_bpf_run_filter_sysctl(struct ctl_table_header *head, rcu_read_lock(); cgrp = task_dfl_cgroup(current); - ret = BPF_PROG_RUN_ARRAY_CG(cgrp->bpf.effective[atype], &ctx, - bpf_prog_run, 0); + ret = bpf_prog_run_array_cg(&cgrp->bpf, atype, &ctx, bpf_prog_run, 0, + NULL); rcu_read_unlock(); kfree(ctx.cur_val); @@ -1459,8 +1525,8 @@ int __cgroup_bpf_run_filter_setsockopt(struct sock *sk, int *level, } lock_sock(sk); - ret = BPF_PROG_RUN_ARRAY_CG(cgrp->bpf.effective[CGROUP_SETSOCKOPT], - &ctx, bpf_prog_run, 0); + ret = bpf_prog_run_array_cg(&cgrp->bpf, CGROUP_SETSOCKOPT, + &ctx, bpf_prog_run, 0, NULL); release_sock(sk); if (ret) @@ -1559,8 +1625,8 @@ int __cgroup_bpf_run_filter_getsockopt(struct sock *sk, int level, } lock_sock(sk); - ret = BPF_PROG_RUN_ARRAY_CG(cgrp->bpf.effective[CGROUP_GETSOCKOPT], - &ctx, bpf_prog_run, retval); + ret = bpf_prog_run_array_cg(&cgrp->bpf, CGROUP_GETSOCKOPT, + &ctx, bpf_prog_run, retval, NULL); release_sock(sk); if (ret < 0) @@ -1608,8 +1674,8 @@ int __cgroup_bpf_run_filter_getsockopt_kern(struct sock *sk, int level, * be called if that data shouldn't be "exported". */ - ret = BPF_PROG_RUN_ARRAY_CG(cgrp->bpf.effective[CGROUP_GETSOCKOPT], - &ctx, bpf_prog_run, retval); + ret = bpf_prog_run_array_cg(&cgrp->bpf, CGROUP_GETSOCKOPT, + &ctx, bpf_prog_run, retval, NULL); if (ret < 0) return ret; diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 13e9dbeeedf3..cacd8684c3c4 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -873,7 +873,7 @@ static size_t select_bpf_prog_pack_size(void) return size; } -static struct bpf_prog_pack *alloc_new_pack(void) +static struct bpf_prog_pack *alloc_new_pack(bpf_jit_fill_hole_t bpf_fill_ill_insns) { struct bpf_prog_pack *pack; @@ -886,6 +886,7 @@ static struct bpf_prog_pack *alloc_new_pack(void) kfree(pack); return NULL; } + bpf_fill_ill_insns(pack->ptr, bpf_prog_pack_size); bitmap_zero(pack->bitmap, bpf_prog_pack_size / BPF_PROG_CHUNK_SIZE); list_add_tail(&pack->list, &pack_list); @@ -895,7 +896,7 @@ static struct bpf_prog_pack *alloc_new_pack(void) return pack; } -static void *bpf_prog_pack_alloc(u32 size) +static void *bpf_prog_pack_alloc(u32 size, bpf_jit_fill_hole_t bpf_fill_ill_insns) { unsigned int nbits = BPF_PROG_SIZE_TO_NBITS(size); struct bpf_prog_pack *pack; @@ -910,6 +911,7 @@ static void *bpf_prog_pack_alloc(u32 size) size = round_up(size, PAGE_SIZE); ptr = module_alloc(size); if (ptr) { + bpf_fill_ill_insns(ptr, size); set_vm_flush_reset_perms(ptr); set_memory_ro((unsigned long)ptr, size / PAGE_SIZE); set_memory_x((unsigned long)ptr, size / PAGE_SIZE); @@ -923,7 +925,7 @@ static void *bpf_prog_pack_alloc(u32 size) goto found_free_area; } - pack = alloc_new_pack(); + pack = alloc_new_pack(bpf_fill_ill_insns); if (!pack) goto out; @@ -966,6 +968,9 @@ static void bpf_prog_pack_free(struct bpf_binary_header *hdr) nbits = BPF_PROG_SIZE_TO_NBITS(hdr->size); pos = ((unsigned long)hdr - (unsigned long)pack_ptr) >> BPF_PROG_CHUNK_SHIFT; + WARN_ONCE(bpf_arch_text_invalidate(hdr, hdr->size), + "bpf_prog_pack bug: missing bpf_arch_text_invalidate?\n"); + bitmap_clear(pack->bitmap, pos, nbits); if (bitmap_find_next_zero_area(pack->bitmap, bpf_prog_chunk_count(), 0, bpf_prog_chunk_count(), 0) == 0) { @@ -1102,7 +1107,7 @@ bpf_jit_binary_pack_alloc(unsigned int proglen, u8 **image_ptr, if (bpf_jit_charge_modmem(size)) return NULL; - ro_header = bpf_prog_pack_alloc(size); + ro_header = bpf_prog_pack_alloc(size, bpf_fill_ill_insns); if (!ro_header) { bpf_jit_uncharge_modmem(size); return NULL; @@ -1434,6 +1439,16 @@ struct bpf_prog *bpf_jit_blind_constants(struct bpf_prog *prog) insn = clone->insnsi; for (i = 0; i < insn_cnt; i++, insn++) { + if (bpf_pseudo_func(insn)) { + /* ld_imm64 with an address of bpf subprog is not + * a user controlled constant. Don't randomize it, + * since it will conflict with jit_subprogs() logic. + */ + insn++; + i++; + continue; + } + /* We temporarily need to hold the original ld64 insn * so that we can still access the first part in the * second blinding run. @@ -2619,6 +2634,7 @@ const struct bpf_func_proto bpf_map_delete_elem_proto __weak; const struct bpf_func_proto bpf_map_push_elem_proto __weak; const struct bpf_func_proto bpf_map_pop_elem_proto __weak; const struct bpf_func_proto bpf_map_peek_elem_proto __weak; +const struct bpf_func_proto bpf_map_lookup_percpu_elem_proto __weak; const struct bpf_func_proto bpf_spin_lock_proto __weak; const struct bpf_func_proto bpf_spin_unlock_proto __weak; const struct bpf_func_proto bpf_jiffies64_proto __weak; @@ -2727,6 +2743,11 @@ void * __weak bpf_arch_text_copy(void *dst, void *src, size_t len) return ERR_PTR(-ENOTSUPP); } +int __weak bpf_arch_text_invalidate(void *dst, size_t len) +{ + return -ENOTSUPP; +} + DEFINE_STATIC_KEY_FALSE(bpf_stats_enabled_key); EXPORT_SYMBOL(bpf_stats_enabled_key); diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c index 650e5d21f90d..f4860ac756cd 100644 --- a/kernel/bpf/cpumap.c +++ b/kernel/bpf/cpumap.c @@ -27,6 +27,7 @@ #include <linux/kthread.h> #include <linux/capability.h> #include <trace/events/xdp.h> +#include <linux/btf_ids.h> #include <linux/netdevice.h> /* netif_receive_skb_list */ #include <linux/etherdevice.h> /* eth_type_trans */ @@ -673,7 +674,7 @@ static int cpu_map_redirect(struct bpf_map *map, u32 ifindex, u64 flags) __cpu_map_lookup_elem); } -static int cpu_map_btf_id; +BTF_ID_LIST_SINGLE(cpu_map_btf_ids, struct, bpf_cpu_map) const struct bpf_map_ops cpu_map_ops = { .map_meta_equal = bpf_map_meta_equal, .map_alloc = cpu_map_alloc, @@ -683,8 +684,7 @@ const struct bpf_map_ops cpu_map_ops = { .map_lookup_elem = cpu_map_lookup_elem, .map_get_next_key = cpu_map_get_next_key, .map_check_btf = map_check_no_btf, - .map_btf_name = "bpf_cpu_map", - .map_btf_id = &cpu_map_btf_id, + .map_btf_id = &cpu_map_btf_ids[0], .map_redirect = cpu_map_redirect, }; diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c index 038f6d7a83e4..c2867068e5bd 100644 --- a/kernel/bpf/devmap.c +++ b/kernel/bpf/devmap.c @@ -48,6 +48,7 @@ #include <net/xdp.h> #include <linux/filter.h> #include <trace/events/xdp.h> +#include <linux/btf_ids.h> #define DEV_CREATE_FLAG_MASK \ (BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY) @@ -1005,7 +1006,7 @@ static int dev_hash_map_redirect(struct bpf_map *map, u32 ifindex, u64 flags) __dev_map_hash_lookup_elem); } -static int dev_map_btf_id; +BTF_ID_LIST_SINGLE(dev_map_btf_ids, struct, bpf_dtab) const struct bpf_map_ops dev_map_ops = { .map_meta_equal = bpf_map_meta_equal, .map_alloc = dev_map_alloc, @@ -1015,12 +1016,10 @@ const struct bpf_map_ops dev_map_ops = { .map_update_elem = dev_map_update_elem, .map_delete_elem = dev_map_delete_elem, .map_check_btf = map_check_no_btf, - .map_btf_name = "bpf_dtab", - .map_btf_id = &dev_map_btf_id, + .map_btf_id = &dev_map_btf_ids[0], .map_redirect = dev_map_redirect, }; -static int dev_map_hash_map_btf_id; const struct bpf_map_ops dev_map_hash_ops = { .map_meta_equal = bpf_map_meta_equal, .map_alloc = dev_map_alloc, @@ -1030,8 +1029,7 @@ const struct bpf_map_ops dev_map_hash_ops = { .map_update_elem = dev_map_hash_update_elem, .map_delete_elem = dev_map_hash_delete_elem, .map_check_btf = map_check_no_btf, - .map_btf_name = "bpf_dtab", - .map_btf_id = &dev_map_hash_map_btf_id, + .map_btf_id = &dev_map_btf_ids[0], .map_redirect = dev_hash_map_redirect, }; diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index 65877967f414..17fb69c0e0dc 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -10,6 +10,7 @@ #include <linux/random.h> #include <uapi/linux/btf.h> #include <linux/rcupdate_trace.h> +#include <linux/btf_ids.h> #include "percpu_freelist.h" #include "bpf_lru_list.h" #include "map_in_map.h" @@ -139,7 +140,7 @@ static inline bool htab_use_raw_lock(const struct bpf_htab *htab) static void htab_init_buckets(struct bpf_htab *htab) { - unsigned i; + unsigned int i; for (i = 0; i < htab->n_buckets; i++) { INIT_HLIST_NULLS_HEAD(&htab->buckets[i].head, i); @@ -238,7 +239,7 @@ static void htab_free_prealloced_timers(struct bpf_htab *htab) u32 num_entries = htab->map.max_entries; int i; - if (likely(!map_value_has_timer(&htab->map))) + if (!map_value_has_timer(&htab->map)) return; if (htab_has_extra_elems(htab)) num_entries += num_possible_cpus(); @@ -254,6 +255,25 @@ static void htab_free_prealloced_timers(struct bpf_htab *htab) } } +static void htab_free_prealloced_kptrs(struct bpf_htab *htab) +{ + u32 num_entries = htab->map.max_entries; + int i; + + if (!map_value_has_kptrs(&htab->map)) + return; + if (htab_has_extra_elems(htab)) + num_entries += num_possible_cpus(); + + for (i = 0; i < num_entries; i++) { + struct htab_elem *elem; + + elem = get_htab_elem(htab, i); + bpf_map_free_kptrs(&htab->map, elem->key + round_up(htab->map.key_size, 8)); + cond_resched(); + } +} + static void htab_free_elems(struct bpf_htab *htab) { int i; @@ -725,12 +745,15 @@ static int htab_lru_map_gen_lookup(struct bpf_map *map, return insn - insn_buf; } -static void check_and_free_timer(struct bpf_htab *htab, struct htab_elem *elem) +static void check_and_free_fields(struct bpf_htab *htab, + struct htab_elem *elem) { - if (unlikely(map_value_has_timer(&htab->map))) - bpf_timer_cancel_and_free(elem->key + - round_up(htab->map.key_size, 8) + - htab->map.timer_off); + void *map_value = elem->key + round_up(htab->map.key_size, 8); + + if (map_value_has_timer(&htab->map)) + bpf_timer_cancel_and_free(map_value + htab->map.timer_off); + if (map_value_has_kptrs(&htab->map)) + bpf_map_free_kptrs(&htab->map, map_value); } /* It is called from the bpf_lru_list when the LRU needs to delete @@ -738,7 +761,7 @@ static void check_and_free_timer(struct bpf_htab *htab, struct htab_elem *elem) */ static bool htab_lru_map_delete_node(void *arg, struct bpf_lru_node *node) { - struct bpf_htab *htab = (struct bpf_htab *)arg; + struct bpf_htab *htab = arg; struct htab_elem *l = NULL, *tgt_l; struct hlist_nulls_head *head; struct hlist_nulls_node *n; @@ -757,7 +780,7 @@ static bool htab_lru_map_delete_node(void *arg, struct bpf_lru_node *node) hlist_nulls_for_each_entry_rcu(l, n, head, hash_node) if (l == tgt_l) { hlist_nulls_del_rcu(&l->hash_node); - check_and_free_timer(htab, l); + check_and_free_fields(htab, l); break; } @@ -829,7 +852,7 @@ static void htab_elem_free(struct bpf_htab *htab, struct htab_elem *l) { if (htab->map.map_type == BPF_MAP_TYPE_PERCPU_HASH) free_percpu(htab_elem_get_ptr(l, htab->map.key_size)); - check_and_free_timer(htab, l); + check_and_free_fields(htab, l); kfree(l); } @@ -857,7 +880,7 @@ static void free_htab_elem(struct bpf_htab *htab, struct htab_elem *l) htab_put_fd_value(htab, l); if (htab_is_prealloc(htab)) { - check_and_free_timer(htab, l); + check_and_free_fields(htab, l); __pcpu_freelist_push(&htab->freelist, &l->fnode); } else { atomic_dec(&htab->count); @@ -1104,7 +1127,7 @@ static int htab_map_update_elem(struct bpf_map *map, void *key, void *value, if (!htab_is_prealloc(htab)) free_htab_elem(htab, l_old); else - check_and_free_timer(htab, l_old); + check_and_free_fields(htab, l_old); } ret = 0; err: @@ -1114,7 +1137,7 @@ err: static void htab_lru_push_free(struct bpf_htab *htab, struct htab_elem *elem) { - check_and_free_timer(htab, elem); + check_and_free_fields(htab, elem); bpf_lru_push_free(&htab->lru, &elem->lru_node); } @@ -1419,8 +1442,14 @@ static void htab_free_malloced_timers(struct bpf_htab *htab) struct hlist_nulls_node *n; struct htab_elem *l; - hlist_nulls_for_each_entry(l, n, head, hash_node) - check_and_free_timer(htab, l); + hlist_nulls_for_each_entry(l, n, head, hash_node) { + /* We don't reset or free kptr on uref dropping to zero, + * hence just free timer. + */ + bpf_timer_cancel_and_free(l->key + + round_up(htab->map.key_size, 8) + + htab->map.timer_off); + } cond_resched_rcu(); } rcu_read_unlock(); @@ -1430,7 +1459,8 @@ static void htab_map_free_timers(struct bpf_map *map) { struct bpf_htab *htab = container_of(map, struct bpf_htab, map); - if (likely(!map_value_has_timer(&htab->map))) + /* We don't reset or free kptr on uref dropping to zero. */ + if (!map_value_has_timer(&htab->map)) return; if (!htab_is_prealloc(htab)) htab_free_malloced_timers(htab); @@ -1453,11 +1483,14 @@ static void htab_map_free(struct bpf_map *map) * not have executed. Wait for them. */ rcu_barrier(); - if (!htab_is_prealloc(htab)) + if (!htab_is_prealloc(htab)) { delete_all_elements(htab); - else + } else { + htab_free_prealloced_kptrs(htab); prealloc_destroy(htab); + } + bpf_map_free_kptr_off_tab(map); free_percpu(htab->extra_elems); bpf_map_area_free(htab->buckets); for (i = 0; i < HASHTAB_MAP_LOCK_COUNT; i++) @@ -1594,7 +1627,7 @@ __htab_map_lookup_and_delete_batch(struct bpf_map *map, void __user *uvalues = u64_to_user_ptr(attr->batch.values); void __user *ukeys = u64_to_user_ptr(attr->batch.keys); void __user *ubatch = u64_to_user_ptr(attr->batch.in_batch); - u32 batch, max_count, size, bucket_size; + u32 batch, max_count, size, bucket_size, map_id; struct htab_elem *node_to_free = NULL; u64 elem_map_flags, map_flags; struct hlist_nulls_head *head; @@ -1719,6 +1752,14 @@ again_nocopy: } } else { value = l->key + roundup_key_size; + if (map->map_type == BPF_MAP_TYPE_HASH_OF_MAPS) { + struct bpf_map **inner_map = value; + + /* Actual value is the id of the inner map */ + map_id = map->ops->map_fd_sys_lookup_elem(*inner_map); + value = &map_id; + } + if (elem_map_flags & BPF_F_LOCK) copy_map_value_locked(map, dst_val, value, true); @@ -2105,7 +2146,7 @@ out: return num_elems; } -static int htab_map_btf_id; +BTF_ID_LIST_SINGLE(htab_map_btf_ids, struct, bpf_htab) const struct bpf_map_ops htab_map_ops = { .map_meta_equal = bpf_map_meta_equal, .map_alloc_check = htab_map_alloc_check, @@ -2122,12 +2163,10 @@ const struct bpf_map_ops htab_map_ops = { .map_set_for_each_callback_args = map_set_for_each_callback_args, .map_for_each_callback = bpf_for_each_hash_elem, BATCH_OPS(htab), - .map_btf_name = "bpf_htab", - .map_btf_id = &htab_map_btf_id, + .map_btf_id = &htab_map_btf_ids[0], .iter_seq_info = &iter_seq_info, }; -static int htab_lru_map_btf_id; const struct bpf_map_ops htab_lru_map_ops = { .map_meta_equal = bpf_map_meta_equal, .map_alloc_check = htab_map_alloc_check, @@ -2145,8 +2184,7 @@ const struct bpf_map_ops htab_lru_map_ops = { .map_set_for_each_callback_args = map_set_for_each_callback_args, .map_for_each_callback = bpf_for_each_hash_elem, BATCH_OPS(htab_lru), - .map_btf_name = "bpf_htab", - .map_btf_id = &htab_lru_map_btf_id, + .map_btf_id = &htab_map_btf_ids[0], .iter_seq_info = &iter_seq_info, }; @@ -2161,6 +2199,20 @@ static void *htab_percpu_map_lookup_elem(struct bpf_map *map, void *key) return NULL; } +static void *htab_percpu_map_lookup_percpu_elem(struct bpf_map *map, void *key, u32 cpu) +{ + struct htab_elem *l; + + if (cpu >= nr_cpu_ids) + return NULL; + + l = __htab_map_lookup_elem(map, key); + if (l) + return per_cpu_ptr(htab_elem_get_ptr(l, map->key_size), cpu); + else + return NULL; +} + static void *htab_lru_percpu_map_lookup_elem(struct bpf_map *map, void *key) { struct htab_elem *l = __htab_map_lookup_elem(map, key); @@ -2173,6 +2225,22 @@ static void *htab_lru_percpu_map_lookup_elem(struct bpf_map *map, void *key) return NULL; } +static void *htab_lru_percpu_map_lookup_percpu_elem(struct bpf_map *map, void *key, u32 cpu) +{ + struct htab_elem *l; + + if (cpu >= nr_cpu_ids) + return NULL; + + l = __htab_map_lookup_elem(map, key); + if (l) { + bpf_lru_node_set_ref(&l->lru_node); + return per_cpu_ptr(htab_elem_get_ptr(l, map->key_size), cpu); + } + + return NULL; +} + int bpf_percpu_hash_copy(struct bpf_map *map, void *key, void *value) { struct htab_elem *l; @@ -2252,7 +2320,6 @@ static void htab_percpu_map_seq_show_elem(struct bpf_map *map, void *key, rcu_read_unlock(); } -static int htab_percpu_map_btf_id; const struct bpf_map_ops htab_percpu_map_ops = { .map_meta_equal = bpf_map_meta_equal, .map_alloc_check = htab_map_alloc_check, @@ -2263,16 +2330,15 @@ const struct bpf_map_ops htab_percpu_map_ops = { .map_lookup_and_delete_elem = htab_percpu_map_lookup_and_delete_elem, .map_update_elem = htab_percpu_map_update_elem, .map_delete_elem = htab_map_delete_elem, + .map_lookup_percpu_elem = htab_percpu_map_lookup_percpu_elem, .map_seq_show_elem = htab_percpu_map_seq_show_elem, .map_set_for_each_callback_args = map_set_for_each_callback_args, .map_for_each_callback = bpf_for_each_hash_elem, BATCH_OPS(htab_percpu), - .map_btf_name = "bpf_htab", - .map_btf_id = &htab_percpu_map_btf_id, + .map_btf_id = &htab_map_btf_ids[0], .iter_seq_info = &iter_seq_info, }; -static int htab_lru_percpu_map_btf_id; const struct bpf_map_ops htab_lru_percpu_map_ops = { .map_meta_equal = bpf_map_meta_equal, .map_alloc_check = htab_map_alloc_check, @@ -2283,12 +2349,12 @@ const struct bpf_map_ops htab_lru_percpu_map_ops = { .map_lookup_and_delete_elem = htab_lru_percpu_map_lookup_and_delete_elem, .map_update_elem = htab_lru_percpu_map_update_elem, .map_delete_elem = htab_lru_map_delete_elem, + .map_lookup_percpu_elem = htab_lru_percpu_map_lookup_percpu_elem, .map_seq_show_elem = htab_percpu_map_seq_show_elem, .map_set_for_each_callback_args = map_set_for_each_callback_args, .map_for_each_callback = bpf_for_each_hash_elem, BATCH_OPS(htab_lru_percpu), - .map_btf_name = "bpf_htab", - .map_btf_id = &htab_lru_percpu_map_btf_id, + .map_btf_id = &htab_map_btf_ids[0], .iter_seq_info = &iter_seq_info, }; @@ -2412,7 +2478,6 @@ static void htab_of_map_free(struct bpf_map *map) fd_htab_map_free(map); } -static int htab_of_maps_map_btf_id; const struct bpf_map_ops htab_of_maps_map_ops = { .map_alloc_check = fd_htab_map_alloc_check, .map_alloc = htab_of_map_alloc, @@ -2425,6 +2490,6 @@ const struct bpf_map_ops htab_of_maps_map_ops = { .map_fd_sys_lookup_elem = bpf_map_fd_sys_lookup_elem, .map_gen_lookup = htab_of_map_gen_lookup, .map_check_btf = map_check_no_btf, - .map_btf_name = "bpf_htab", - .map_btf_id = &htab_of_maps_map_btf_id, + BATCH_OPS(htab), + .map_btf_id = &htab_map_btf_ids[0], }; diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index 315053ef6a75..225806a02efb 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -103,7 +103,7 @@ const struct bpf_func_proto bpf_map_pop_elem_proto = { .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_CONST_MAP_PTR, - .arg2_type = ARG_PTR_TO_UNINIT_MAP_VALUE, + .arg2_type = ARG_PTR_TO_MAP_VALUE | MEM_UNINIT, }; BPF_CALL_2(bpf_map_peek_elem, struct bpf_map *, map, void *, value) @@ -116,7 +116,23 @@ const struct bpf_func_proto bpf_map_peek_elem_proto = { .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_CONST_MAP_PTR, - .arg2_type = ARG_PTR_TO_UNINIT_MAP_VALUE, + .arg2_type = ARG_PTR_TO_MAP_VALUE | MEM_UNINIT, +}; + +BPF_CALL_3(bpf_map_lookup_percpu_elem, struct bpf_map *, map, void *, key, u32, cpu) +{ + WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_bh_held()); + return (unsigned long) map->ops->map_lookup_percpu_elem(map, key, cpu); +} + +const struct bpf_func_proto bpf_map_lookup_percpu_elem_proto = { + .func = bpf_map_lookup_percpu_elem, + .gpl_only = false, + .pkt_access = true, + .ret_type = RET_PTR_TO_MAP_VALUE_OR_NULL, + .arg1_type = ARG_CONST_MAP_PTR, + .arg2_type = ARG_PTR_TO_MAP_KEY, + .arg3_type = ARG_ANYTHING, }; const struct bpf_func_proto bpf_get_prandom_u32_proto = { @@ -1374,6 +1390,191 @@ out: kfree(t); } +BPF_CALL_2(bpf_kptr_xchg, void *, map_value, void *, ptr) +{ + unsigned long *kptr = map_value; + + return xchg(kptr, (unsigned long)ptr); +} + +/* Unlike other PTR_TO_BTF_ID helpers the btf_id in bpf_kptr_xchg() + * helper is determined dynamically by the verifier. + */ +#define BPF_PTR_POISON ((void *)((0xeB9FUL << 2) + POISON_POINTER_DELTA)) + +const struct bpf_func_proto bpf_kptr_xchg_proto = { + .func = bpf_kptr_xchg, + .gpl_only = false, + .ret_type = RET_PTR_TO_BTF_ID_OR_NULL, + .ret_btf_id = BPF_PTR_POISON, + .arg1_type = ARG_PTR_TO_KPTR, + .arg2_type = ARG_PTR_TO_BTF_ID_OR_NULL | OBJ_RELEASE, + .arg2_btf_id = BPF_PTR_POISON, +}; + +/* Since the upper 8 bits of dynptr->size is reserved, the + * maximum supported size is 2^24 - 1. + */ +#define DYNPTR_MAX_SIZE ((1UL << 24) - 1) +#define DYNPTR_TYPE_SHIFT 28 +#define DYNPTR_SIZE_MASK 0xFFFFFF +#define DYNPTR_RDONLY_BIT BIT(31) + +static bool bpf_dynptr_is_rdonly(struct bpf_dynptr_kern *ptr) +{ + return ptr->size & DYNPTR_RDONLY_BIT; +} + +static void bpf_dynptr_set_type(struct bpf_dynptr_kern *ptr, enum bpf_dynptr_type type) +{ + ptr->size |= type << DYNPTR_TYPE_SHIFT; +} + +static u32 bpf_dynptr_get_size(struct bpf_dynptr_kern *ptr) +{ + return ptr->size & DYNPTR_SIZE_MASK; +} + +int bpf_dynptr_check_size(u32 size) +{ + return size > DYNPTR_MAX_SIZE ? -E2BIG : 0; +} + +void bpf_dynptr_init(struct bpf_dynptr_kern *ptr, void *data, + enum bpf_dynptr_type type, u32 offset, u32 size) +{ + ptr->data = data; + ptr->offset = offset; + ptr->size = size; + bpf_dynptr_set_type(ptr, type); +} + +void bpf_dynptr_set_null(struct bpf_dynptr_kern *ptr) +{ + memset(ptr, 0, sizeof(*ptr)); +} + +static int bpf_dynptr_check_off_len(struct bpf_dynptr_kern *ptr, u32 offset, u32 len) +{ + u32 size = bpf_dynptr_get_size(ptr); + + if (len > size || offset > size - len) + return -E2BIG; + + return 0; +} + +BPF_CALL_4(bpf_dynptr_from_mem, void *, data, u32, size, u64, flags, struct bpf_dynptr_kern *, ptr) +{ + int err; + + err = bpf_dynptr_check_size(size); + if (err) + goto error; + + /* flags is currently unsupported */ + if (flags) { + err = -EINVAL; + goto error; + } + + bpf_dynptr_init(ptr, data, BPF_DYNPTR_TYPE_LOCAL, 0, size); + + return 0; + +error: + bpf_dynptr_set_null(ptr); + return err; +} + +const struct bpf_func_proto bpf_dynptr_from_mem_proto = { + .func = bpf_dynptr_from_mem, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_UNINIT_MEM, + .arg2_type = ARG_CONST_SIZE_OR_ZERO, + .arg3_type = ARG_ANYTHING, + .arg4_type = ARG_PTR_TO_DYNPTR | DYNPTR_TYPE_LOCAL | MEM_UNINIT, +}; + +BPF_CALL_4(bpf_dynptr_read, void *, dst, u32, len, struct bpf_dynptr_kern *, src, u32, offset) +{ + int err; + + if (!src->data) + return -EINVAL; + + err = bpf_dynptr_check_off_len(src, offset, len); + if (err) + return err; + + memcpy(dst, src->data + src->offset + offset, len); + + return 0; +} + +const struct bpf_func_proto bpf_dynptr_read_proto = { + .func = bpf_dynptr_read, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_UNINIT_MEM, + .arg2_type = ARG_CONST_SIZE_OR_ZERO, + .arg3_type = ARG_PTR_TO_DYNPTR, + .arg4_type = ARG_ANYTHING, +}; + +BPF_CALL_4(bpf_dynptr_write, struct bpf_dynptr_kern *, dst, u32, offset, void *, src, u32, len) +{ + int err; + + if (!dst->data || bpf_dynptr_is_rdonly(dst)) + return -EINVAL; + + err = bpf_dynptr_check_off_len(dst, offset, len); + if (err) + return err; + + memcpy(dst->data + dst->offset + offset, src, len); + + return 0; +} + +const struct bpf_func_proto bpf_dynptr_write_proto = { + .func = bpf_dynptr_write, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_DYNPTR, + .arg2_type = ARG_ANYTHING, + .arg3_type = ARG_PTR_TO_MEM | MEM_RDONLY, + .arg4_type = ARG_CONST_SIZE_OR_ZERO, +}; + +BPF_CALL_3(bpf_dynptr_data, struct bpf_dynptr_kern *, ptr, u32, offset, u32, len) +{ + int err; + + if (!ptr->data) + return 0; + + err = bpf_dynptr_check_off_len(ptr, offset, len); + if (err) + return 0; + + if (bpf_dynptr_is_rdonly(ptr)) + return 0; + + return (unsigned long)(ptr->data + ptr->offset + offset); +} + +const struct bpf_func_proto bpf_dynptr_data_proto = { + .func = bpf_dynptr_data, + .gpl_only = false, + .ret_type = RET_PTR_TO_DYNPTR_MEM_OR_NULL, + .arg1_type = ARG_PTR_TO_DYNPTR, + .arg2_type = ARG_ANYTHING, + .arg3_type = ARG_CONST_ALLOC_SIZE_OR_ZERO, +}; + const struct bpf_func_proto bpf_get_current_task_proto __weak; const struct bpf_func_proto bpf_get_current_task_btf_proto __weak; const struct bpf_func_proto bpf_probe_read_user_proto __weak; @@ -1398,6 +1599,8 @@ bpf_base_func_proto(enum bpf_func_id func_id) return &bpf_map_pop_elem_proto; case BPF_FUNC_map_peek_elem: return &bpf_map_peek_elem_proto; + case BPF_FUNC_map_lookup_percpu_elem: + return &bpf_map_lookup_percpu_elem_proto; case BPF_FUNC_get_prandom_u32: return &bpf_get_prandom_u32_proto; case BPF_FUNC_get_smp_processor_id: @@ -1420,12 +1623,26 @@ bpf_base_func_proto(enum bpf_func_id func_id) return &bpf_ringbuf_discard_proto; case BPF_FUNC_ringbuf_query: return &bpf_ringbuf_query_proto; + case BPF_FUNC_ringbuf_reserve_dynptr: + return &bpf_ringbuf_reserve_dynptr_proto; + case BPF_FUNC_ringbuf_submit_dynptr: + return &bpf_ringbuf_submit_dynptr_proto; + case BPF_FUNC_ringbuf_discard_dynptr: + return &bpf_ringbuf_discard_dynptr_proto; case BPF_FUNC_for_each_map_elem: return &bpf_for_each_map_elem_proto; case BPF_FUNC_loop: return &bpf_loop_proto; case BPF_FUNC_strncmp: return &bpf_strncmp_proto; + case BPF_FUNC_dynptr_from_mem: + return &bpf_dynptr_from_mem_proto; + case BPF_FUNC_dynptr_read: + return &bpf_dynptr_read_proto; + case BPF_FUNC_dynptr_write: + return &bpf_dynptr_write_proto; + case BPF_FUNC_dynptr_data: + return &bpf_dynptr_data_proto; default: break; } @@ -1452,6 +1669,8 @@ bpf_base_func_proto(enum bpf_func_id func_id) return &bpf_timer_start_proto; case BPF_FUNC_timer_cancel: return &bpf_timer_cancel_proto; + case BPF_FUNC_kptr_xchg: + return &bpf_kptr_xchg_proto; default: break; } diff --git a/kernel/bpf/link_iter.c b/kernel/bpf/link_iter.c new file mode 100644 index 000000000000..fec8005a121c --- /dev/null +++ b/kernel/bpf/link_iter.c @@ -0,0 +1,107 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright (c) 2022 Red Hat, Inc. */ +#include <linux/bpf.h> +#include <linux/fs.h> +#include <linux/filter.h> +#include <linux/kernel.h> +#include <linux/btf_ids.h> + +struct bpf_iter_seq_link_info { + u32 link_id; +}; + +static void *bpf_link_seq_start(struct seq_file *seq, loff_t *pos) +{ + struct bpf_iter_seq_link_info *info = seq->private; + struct bpf_link *link; + + link = bpf_link_get_curr_or_next(&info->link_id); + if (!link) + return NULL; + + if (*pos == 0) + ++*pos; + return link; +} + +static void *bpf_link_seq_next(struct seq_file *seq, void *v, loff_t *pos) +{ + struct bpf_iter_seq_link_info *info = seq->private; + + ++*pos; + ++info->link_id; + bpf_link_put((struct bpf_link *)v); + return bpf_link_get_curr_or_next(&info->link_id); +} + +struct bpf_iter__bpf_link { + __bpf_md_ptr(struct bpf_iter_meta *, meta); + __bpf_md_ptr(struct bpf_link *, link); +}; + +DEFINE_BPF_ITER_FUNC(bpf_link, struct bpf_iter_meta *meta, struct bpf_link *link) + +static int __bpf_link_seq_show(struct seq_file *seq, void *v, bool in_stop) +{ + struct bpf_iter__bpf_link ctx; + struct bpf_iter_meta meta; + struct bpf_prog *prog; + int ret = 0; + + ctx.meta = &meta; + ctx.link = v; + meta.seq = seq; + prog = bpf_iter_get_info(&meta, in_stop); + if (prog) + ret = bpf_iter_run_prog(prog, &ctx); + + return ret; +} + +static int bpf_link_seq_show(struct seq_file *seq, void *v) +{ + return __bpf_link_seq_show(seq, v, false); +} + +static void bpf_link_seq_stop(struct seq_file *seq, void *v) +{ + if (!v) + (void)__bpf_link_seq_show(seq, v, true); + else + bpf_link_put((struct bpf_link *)v); +} + +static const struct seq_operations bpf_link_seq_ops = { + .start = bpf_link_seq_start, + .next = bpf_link_seq_next, + .stop = bpf_link_seq_stop, + .show = bpf_link_seq_show, +}; + +BTF_ID_LIST(btf_bpf_link_id) +BTF_ID(struct, bpf_link) + +static const struct bpf_iter_seq_info bpf_link_seq_info = { + .seq_ops = &bpf_link_seq_ops, + .init_seq_private = NULL, + .fini_seq_private = NULL, + .seq_priv_size = sizeof(struct bpf_iter_seq_link_info), +}; + +static struct bpf_iter_reg bpf_link_reg_info = { + .target = "bpf_link", + .ctx_arg_info_size = 1, + .ctx_arg_info = { + { offsetof(struct bpf_iter__bpf_link, link), + PTR_TO_BTF_ID_OR_NULL }, + }, + .seq_info = &bpf_link_seq_info, +}; + +static int __init bpf_link_iter_init(void) +{ + bpf_link_reg_info.ctx_arg_info[0].btf_id = *btf_bpf_link_id; + return bpf_iter_reg_target(&bpf_link_reg_info); +} + +late_initcall(bpf_link_iter_init); diff --git a/kernel/bpf/local_storage.c b/kernel/bpf/local_storage.c index 497916060ac7..8654fc97f5fe 100644 --- a/kernel/bpf/local_storage.c +++ b/kernel/bpf/local_storage.c @@ -9,6 +9,7 @@ #include <linux/rbtree.h> #include <linux/slab.h> #include <uapi/linux/btf.h> +#include <linux/btf_ids.h> #ifdef CONFIG_CGROUP_BPF @@ -446,7 +447,8 @@ static void cgroup_storage_seq_show_elem(struct bpf_map *map, void *key, rcu_read_unlock(); } -static int cgroup_storage_map_btf_id; +BTF_ID_LIST_SINGLE(cgroup_storage_map_btf_ids, struct, + bpf_cgroup_storage_map) const struct bpf_map_ops cgroup_storage_map_ops = { .map_alloc = cgroup_storage_map_alloc, .map_free = cgroup_storage_map_free, @@ -456,8 +458,7 @@ const struct bpf_map_ops cgroup_storage_map_ops = { .map_delete_elem = cgroup_storage_delete_elem, .map_check_btf = cgroup_storage_check_btf, .map_seq_show_elem = cgroup_storage_seq_show_elem, - .map_btf_name = "bpf_cgroup_storage_map", - .map_btf_id = &cgroup_storage_map_btf_id, + .map_btf_id = &cgroup_storage_map_btf_ids[0], }; int bpf_cgroup_storage_assign(struct bpf_prog_aux *aux, struct bpf_map *_map) diff --git a/kernel/bpf/lpm_trie.c b/kernel/bpf/lpm_trie.c index 5763cc7ac4f1..f0d05a3cc4b9 100644 --- a/kernel/bpf/lpm_trie.c +++ b/kernel/bpf/lpm_trie.c @@ -14,6 +14,7 @@ #include <linux/vmalloc.h> #include <net/ipv6.h> #include <uapi/linux/btf.h> +#include <linux/btf_ids.h> /* Intermediate node */ #define LPM_TREE_NODE_FLAG_IM BIT(0) @@ -719,7 +720,7 @@ static int trie_check_btf(const struct bpf_map *map, -EINVAL : 0; } -static int trie_map_btf_id; +BTF_ID_LIST_SINGLE(trie_map_btf_ids, struct, lpm_trie) const struct bpf_map_ops trie_map_ops = { .map_meta_equal = bpf_map_meta_equal, .map_alloc = trie_alloc, @@ -732,6 +733,5 @@ const struct bpf_map_ops trie_map_ops = { .map_update_batch = generic_map_update_batch, .map_delete_batch = generic_map_delete_batch, .map_check_btf = trie_check_btf, - .map_btf_name = "lpm_trie", - .map_btf_id = &trie_map_btf_id, + .map_btf_id = &trie_map_btf_ids[0], }; diff --git a/kernel/bpf/map_in_map.c b/kernel/bpf/map_in_map.c index 5cd8f5277279..135205d0d560 100644 --- a/kernel/bpf/map_in_map.c +++ b/kernel/bpf/map_in_map.c @@ -52,6 +52,7 @@ struct bpf_map *bpf_map_meta_alloc(int inner_map_ufd) inner_map_meta->max_entries = inner_map->max_entries; inner_map_meta->spin_lock_off = inner_map->spin_lock_off; inner_map_meta->timer_off = inner_map->timer_off; + inner_map_meta->kptr_off_tab = bpf_map_copy_kptr_off_tab(inner_map); if (inner_map->btf) { btf_get(inner_map->btf); inner_map_meta->btf = inner_map->btf; @@ -71,6 +72,7 @@ struct bpf_map *bpf_map_meta_alloc(int inner_map_ufd) void bpf_map_meta_free(struct bpf_map *map_meta) { + bpf_map_free_kptr_off_tab(map_meta); btf_put(map_meta->btf); kfree(map_meta); } @@ -83,7 +85,8 @@ bool bpf_map_meta_equal(const struct bpf_map *meta0, meta0->key_size == meta1->key_size && meta0->value_size == meta1->value_size && meta0->timer_off == meta1->timer_off && - meta0->map_flags == meta1->map_flags; + meta0->map_flags == meta1->map_flags && + bpf_map_equal_kptr_off_tab(meta0, meta1); } void *bpf_map_fd_get_ptr(struct bpf_map *map, diff --git a/kernel/bpf/queue_stack_maps.c b/kernel/bpf/queue_stack_maps.c index f9c734aaa990..a1c0794ae49d 100644 --- a/kernel/bpf/queue_stack_maps.c +++ b/kernel/bpf/queue_stack_maps.c @@ -8,6 +8,7 @@ #include <linux/list.h> #include <linux/slab.h> #include <linux/capability.h> +#include <linux/btf_ids.h> #include "percpu_freelist.h" #define QUEUE_STACK_CREATE_FLAG_MASK \ @@ -247,7 +248,7 @@ static int queue_stack_map_get_next_key(struct bpf_map *map, void *key, return -EINVAL; } -static int queue_map_btf_id; +BTF_ID_LIST_SINGLE(queue_map_btf_ids, struct, bpf_queue_stack) const struct bpf_map_ops queue_map_ops = { .map_meta_equal = bpf_map_meta_equal, .map_alloc_check = queue_stack_map_alloc_check, @@ -260,11 +261,9 @@ const struct bpf_map_ops queue_map_ops = { .map_pop_elem = queue_map_pop_elem, .map_peek_elem = queue_map_peek_elem, .map_get_next_key = queue_stack_map_get_next_key, - .map_btf_name = "bpf_queue_stack", - .map_btf_id = &queue_map_btf_id, + .map_btf_id = &queue_map_btf_ids[0], }; -static int stack_map_btf_id; const struct bpf_map_ops stack_map_ops = { .map_meta_equal = bpf_map_meta_equal, .map_alloc_check = queue_stack_map_alloc_check, @@ -277,6 +276,5 @@ const struct bpf_map_ops stack_map_ops = { .map_pop_elem = stack_map_pop_elem, .map_peek_elem = stack_map_peek_elem, .map_get_next_key = queue_stack_map_get_next_key, - .map_btf_name = "bpf_queue_stack", - .map_btf_id = &stack_map_btf_id, + .map_btf_id = &queue_map_btf_ids[0], }; diff --git a/kernel/bpf/reuseport_array.c b/kernel/bpf/reuseport_array.c index 8251243022a2..e2618fb5870e 100644 --- a/kernel/bpf/reuseport_array.c +++ b/kernel/bpf/reuseport_array.c @@ -6,6 +6,7 @@ #include <linux/err.h> #include <linux/sock_diag.h> #include <net/sock_reuseport.h> +#include <linux/btf_ids.h> struct reuseport_array { struct bpf_map map; @@ -337,7 +338,7 @@ static int reuseport_array_get_next_key(struct bpf_map *map, void *key, return 0; } -static int reuseport_array_map_btf_id; +BTF_ID_LIST_SINGLE(reuseport_array_map_btf_ids, struct, reuseport_array) const struct bpf_map_ops reuseport_array_ops = { .map_meta_equal = bpf_map_meta_equal, .map_alloc_check = reuseport_array_alloc_check, @@ -346,6 +347,5 @@ const struct bpf_map_ops reuseport_array_ops = { .map_lookup_elem = reuseport_array_lookup_elem, .map_get_next_key = reuseport_array_get_next_key, .map_delete_elem = reuseport_array_delete_elem, - .map_btf_name = "reuseport_array", - .map_btf_id = &reuseport_array_map_btf_id, + .map_btf_id = &reuseport_array_map_btf_ids[0], }; diff --git a/kernel/bpf/ringbuf.c b/kernel/bpf/ringbuf.c index 710ba9de12ce..ded4faeca192 100644 --- a/kernel/bpf/ringbuf.c +++ b/kernel/bpf/ringbuf.c @@ -10,6 +10,7 @@ #include <linux/poll.h> #include <linux/kmemleak.h> #include <uapi/linux/btf.h> +#include <linux/btf_ids.h> #define RINGBUF_CREATE_FLAG_MASK (BPF_F_NUMA_NODE) @@ -263,7 +264,7 @@ static __poll_t ringbuf_map_poll(struct bpf_map *map, struct file *filp, return 0; } -static int ringbuf_map_btf_id; +BTF_ID_LIST_SINGLE(ringbuf_map_btf_ids, struct, bpf_ringbuf_map) const struct bpf_map_ops ringbuf_map_ops = { .map_meta_equal = bpf_map_meta_equal, .map_alloc = ringbuf_map_alloc, @@ -274,8 +275,7 @@ const struct bpf_map_ops ringbuf_map_ops = { .map_update_elem = ringbuf_map_update_elem, .map_delete_elem = ringbuf_map_delete_elem, .map_get_next_key = ringbuf_map_get_next_key, - .map_btf_name = "bpf_ringbuf_map", - .map_btf_id = &ringbuf_map_btf_id, + .map_btf_id = &ringbuf_map_btf_ids[0], }; /* Given pointer to ring buffer record metadata and struct bpf_ringbuf itself, @@ -404,7 +404,7 @@ BPF_CALL_2(bpf_ringbuf_submit, void *, sample, u64, flags) const struct bpf_func_proto bpf_ringbuf_submit_proto = { .func = bpf_ringbuf_submit, .ret_type = RET_VOID, - .arg1_type = ARG_PTR_TO_ALLOC_MEM, + .arg1_type = ARG_PTR_TO_ALLOC_MEM | OBJ_RELEASE, .arg2_type = ARG_ANYTHING, }; @@ -417,7 +417,7 @@ BPF_CALL_2(bpf_ringbuf_discard, void *, sample, u64, flags) const struct bpf_func_proto bpf_ringbuf_discard_proto = { .func = bpf_ringbuf_discard, .ret_type = RET_VOID, - .arg1_type = ARG_PTR_TO_ALLOC_MEM, + .arg1_type = ARG_PTR_TO_ALLOC_MEM | OBJ_RELEASE, .arg2_type = ARG_ANYTHING, }; @@ -475,3 +475,81 @@ const struct bpf_func_proto bpf_ringbuf_query_proto = { .arg1_type = ARG_CONST_MAP_PTR, .arg2_type = ARG_ANYTHING, }; + +BPF_CALL_4(bpf_ringbuf_reserve_dynptr, struct bpf_map *, map, u32, size, u64, flags, + struct bpf_dynptr_kern *, ptr) +{ + struct bpf_ringbuf_map *rb_map; + void *sample; + int err; + + if (unlikely(flags)) { + bpf_dynptr_set_null(ptr); + return -EINVAL; + } + + err = bpf_dynptr_check_size(size); + if (err) { + bpf_dynptr_set_null(ptr); + return err; + } + + rb_map = container_of(map, struct bpf_ringbuf_map, map); + + sample = __bpf_ringbuf_reserve(rb_map->rb, size); + if (!sample) { + bpf_dynptr_set_null(ptr); + return -EINVAL; + } + + bpf_dynptr_init(ptr, sample, BPF_DYNPTR_TYPE_RINGBUF, 0, size); + + return 0; +} + +const struct bpf_func_proto bpf_ringbuf_reserve_dynptr_proto = { + .func = bpf_ringbuf_reserve_dynptr, + .ret_type = RET_INTEGER, + .arg1_type = ARG_CONST_MAP_PTR, + .arg2_type = ARG_ANYTHING, + .arg3_type = ARG_ANYTHING, + .arg4_type = ARG_PTR_TO_DYNPTR | DYNPTR_TYPE_RINGBUF | MEM_UNINIT, +}; + +BPF_CALL_2(bpf_ringbuf_submit_dynptr, struct bpf_dynptr_kern *, ptr, u64, flags) +{ + if (!ptr->data) + return 0; + + bpf_ringbuf_commit(ptr->data, flags, false /* discard */); + + bpf_dynptr_set_null(ptr); + + return 0; +} + +const struct bpf_func_proto bpf_ringbuf_submit_dynptr_proto = { + .func = bpf_ringbuf_submit_dynptr, + .ret_type = RET_VOID, + .arg1_type = ARG_PTR_TO_DYNPTR | DYNPTR_TYPE_RINGBUF | OBJ_RELEASE, + .arg2_type = ARG_ANYTHING, +}; + +BPF_CALL_2(bpf_ringbuf_discard_dynptr, struct bpf_dynptr_kern *, ptr, u64, flags) +{ + if (!ptr->data) + return 0; + + bpf_ringbuf_commit(ptr->data, flags, true /* discard */); + + bpf_dynptr_set_null(ptr); + + return 0; +} + +const struct bpf_func_proto bpf_ringbuf_discard_dynptr_proto = { + .func = bpf_ringbuf_discard_dynptr, + .ret_type = RET_VOID, + .arg1_type = ARG_PTR_TO_DYNPTR | DYNPTR_TYPE_RINGBUF | OBJ_RELEASE, + .arg2_type = ARG_ANYTHING, +}; diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c index 34725bfa1e97..1adbe67cdb95 100644 --- a/kernel/bpf/stackmap.c +++ b/kernel/bpf/stackmap.c @@ -100,13 +100,11 @@ static struct bpf_map *stack_map_alloc(union bpf_attr *attr) return ERR_PTR(-E2BIG); cost = n_buckets * sizeof(struct stack_map_bucket *) + sizeof(*smap); - cost += n_buckets * (value_size + sizeof(struct stack_map_bucket)); smap = bpf_map_area_alloc(cost, bpf_map_attr_numa_node(attr)); if (!smap) return ERR_PTR(-ENOMEM); bpf_map_init_from_attr(&smap->map, attr); - smap->map.value_size = value_size; smap->n_buckets = n_buckets; err = get_callchain_buffers(sysctl_perf_event_max_stack); @@ -656,7 +654,7 @@ static void stack_map_free(struct bpf_map *map) put_callchain_buffers(); } -static int stack_trace_map_btf_id; +BTF_ID_LIST_SINGLE(stack_trace_map_btf_ids, struct, bpf_stack_map) const struct bpf_map_ops stack_trace_map_ops = { .map_meta_equal = bpf_map_meta_equal, .map_alloc = stack_map_alloc, @@ -666,6 +664,5 @@ const struct bpf_map_ops stack_trace_map_ops = { .map_update_elem = stack_map_update_elem, .map_delete_elem = stack_map_delete_elem, .map_check_btf = map_check_no_btf, - .map_btf_name = "bpf_stack_map", - .map_btf_id = &stack_trace_map_btf_id, + .map_btf_id = &stack_trace_map_btf_ids[0], }; diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index cdaa1152436a..2b69306d3c6e 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -6,6 +6,7 @@ #include <linux/bpf_trace.h> #include <linux/bpf_lirc.h> #include <linux/bpf_verifier.h> +#include <linux/bsearch.h> #include <linux/btf.h> #include <linux/syscalls.h> #include <linux/slab.h> @@ -29,6 +30,7 @@ #include <linux/pgtable.h> #include <linux/bpf_lsm.h> #include <linux/poll.h> +#include <linux/sort.h> #include <linux/bpf-netns.h> #include <linux/rcupdate_trace.h> #include <linux/memcontrol.h> @@ -473,14 +475,128 @@ static void bpf_map_release_memcg(struct bpf_map *map) } #endif +static int bpf_map_kptr_off_cmp(const void *a, const void *b) +{ + const struct bpf_map_value_off_desc *off_desc1 = a, *off_desc2 = b; + + if (off_desc1->offset < off_desc2->offset) + return -1; + else if (off_desc1->offset > off_desc2->offset) + return 1; + return 0; +} + +struct bpf_map_value_off_desc *bpf_map_kptr_off_contains(struct bpf_map *map, u32 offset) +{ + /* Since members are iterated in btf_find_field in increasing order, + * offsets appended to kptr_off_tab are in increasing order, so we can + * do bsearch to find exact match. + */ + struct bpf_map_value_off *tab; + + if (!map_value_has_kptrs(map)) + return NULL; + tab = map->kptr_off_tab; + return bsearch(&offset, tab->off, tab->nr_off, sizeof(tab->off[0]), bpf_map_kptr_off_cmp); +} + +void bpf_map_free_kptr_off_tab(struct bpf_map *map) +{ + struct bpf_map_value_off *tab = map->kptr_off_tab; + int i; + + if (!map_value_has_kptrs(map)) + return; + for (i = 0; i < tab->nr_off; i++) { + if (tab->off[i].kptr.module) + module_put(tab->off[i].kptr.module); + btf_put(tab->off[i].kptr.btf); + } + kfree(tab); + map->kptr_off_tab = NULL; +} + +struct bpf_map_value_off *bpf_map_copy_kptr_off_tab(const struct bpf_map *map) +{ + struct bpf_map_value_off *tab = map->kptr_off_tab, *new_tab; + int size, i; + + if (!map_value_has_kptrs(map)) + return ERR_PTR(-ENOENT); + size = offsetof(struct bpf_map_value_off, off[tab->nr_off]); + new_tab = kmemdup(tab, size, GFP_KERNEL | __GFP_NOWARN); + if (!new_tab) + return ERR_PTR(-ENOMEM); + /* Do a deep copy of the kptr_off_tab */ + for (i = 0; i < tab->nr_off; i++) { + btf_get(tab->off[i].kptr.btf); + if (tab->off[i].kptr.module && !try_module_get(tab->off[i].kptr.module)) { + while (i--) { + if (tab->off[i].kptr.module) + module_put(tab->off[i].kptr.module); + btf_put(tab->off[i].kptr.btf); + } + kfree(new_tab); + return ERR_PTR(-ENXIO); + } + } + return new_tab; +} + +bool bpf_map_equal_kptr_off_tab(const struct bpf_map *map_a, const struct bpf_map *map_b) +{ + struct bpf_map_value_off *tab_a = map_a->kptr_off_tab, *tab_b = map_b->kptr_off_tab; + bool a_has_kptr = map_value_has_kptrs(map_a), b_has_kptr = map_value_has_kptrs(map_b); + int size; + + if (!a_has_kptr && !b_has_kptr) + return true; + if (a_has_kptr != b_has_kptr) + return false; + if (tab_a->nr_off != tab_b->nr_off) + return false; + size = offsetof(struct bpf_map_value_off, off[tab_a->nr_off]); + return !memcmp(tab_a, tab_b, size); +} + +/* Caller must ensure map_value_has_kptrs is true. Note that this function can + * be called on a map value while the map_value is visible to BPF programs, as + * it ensures the correct synchronization, and we already enforce the same using + * the bpf_kptr_xchg helper on the BPF program side for referenced kptrs. + */ +void bpf_map_free_kptrs(struct bpf_map *map, void *map_value) +{ + struct bpf_map_value_off *tab = map->kptr_off_tab; + unsigned long *btf_id_ptr; + int i; + + for (i = 0; i < tab->nr_off; i++) { + struct bpf_map_value_off_desc *off_desc = &tab->off[i]; + unsigned long old_ptr; + + btf_id_ptr = map_value + off_desc->offset; + if (off_desc->type == BPF_KPTR_UNREF) { + u64 *p = (u64 *)btf_id_ptr; + + WRITE_ONCE(p, 0); + continue; + } + old_ptr = xchg(btf_id_ptr, 0); + off_desc->kptr.dtor((void *)old_ptr); + } +} + /* called from workqueue */ static void bpf_map_free_deferred(struct work_struct *work) { struct bpf_map *map = container_of(work, struct bpf_map, work); security_bpf_map_free(map); + kfree(map->off_arr); bpf_map_release_memcg(map); - /* implementation dependent freeing */ + /* implementation dependent freeing, map_free callback also does + * bpf_map_free_kptr_off_tab, if needed. + */ map->ops->map_free(map); } @@ -640,7 +756,7 @@ static int bpf_map_mmap(struct file *filp, struct vm_area_struct *vma) int err; if (!map->ops->map_mmap || map_value_has_spin_lock(map) || - map_value_has_timer(map)) + map_value_has_timer(map) || map_value_has_kptrs(map)) return -ENOTSUPP; if (!(vma->vm_flags & VM_SHARED)) @@ -767,6 +883,84 @@ int map_check_no_btf(const struct bpf_map *map, return -ENOTSUPP; } +static int map_off_arr_cmp(const void *_a, const void *_b, const void *priv) +{ + const u32 a = *(const u32 *)_a; + const u32 b = *(const u32 *)_b; + + if (a < b) + return -1; + else if (a > b) + return 1; + return 0; +} + +static void map_off_arr_swap(void *_a, void *_b, int size, const void *priv) +{ + struct bpf_map *map = (struct bpf_map *)priv; + u32 *off_base = map->off_arr->field_off; + u32 *a = _a, *b = _b; + u8 *sz_a, *sz_b; + + sz_a = map->off_arr->field_sz + (a - off_base); + sz_b = map->off_arr->field_sz + (b - off_base); + + swap(*a, *b); + swap(*sz_a, *sz_b); +} + +static int bpf_map_alloc_off_arr(struct bpf_map *map) +{ + bool has_spin_lock = map_value_has_spin_lock(map); + bool has_timer = map_value_has_timer(map); + bool has_kptrs = map_value_has_kptrs(map); + struct bpf_map_off_arr *off_arr; + u32 i; + + if (!has_spin_lock && !has_timer && !has_kptrs) { + map->off_arr = NULL; + return 0; + } + + off_arr = kmalloc(sizeof(*map->off_arr), GFP_KERNEL | __GFP_NOWARN); + if (!off_arr) + return -ENOMEM; + map->off_arr = off_arr; + + off_arr->cnt = 0; + if (has_spin_lock) { + i = off_arr->cnt; + + off_arr->field_off[i] = map->spin_lock_off; + off_arr->field_sz[i] = sizeof(struct bpf_spin_lock); + off_arr->cnt++; + } + if (has_timer) { + i = off_arr->cnt; + + off_arr->field_off[i] = map->timer_off; + off_arr->field_sz[i] = sizeof(struct bpf_timer); + off_arr->cnt++; + } + if (has_kptrs) { + struct bpf_map_value_off *tab = map->kptr_off_tab; + u32 *off = &off_arr->field_off[off_arr->cnt]; + u8 *sz = &off_arr->field_sz[off_arr->cnt]; + + for (i = 0; i < tab->nr_off; i++) { + *off++ = tab->off[i].offset; + *sz++ = sizeof(u64); + } + off_arr->cnt += tab->nr_off; + } + + if (off_arr->cnt == 1) + return 0; + sort_r(off_arr->field_off, off_arr->cnt, sizeof(off_arr->field_off[0]), + map_off_arr_cmp, map_off_arr_swap, map); + return 0; +} + static int map_check_btf(struct bpf_map *map, const struct btf *btf, u32 btf_key_id, u32 btf_value_id) { @@ -820,10 +1014,34 @@ static int map_check_btf(struct bpf_map *map, const struct btf *btf, return -EOPNOTSUPP; } - if (map->ops->map_check_btf) + map->kptr_off_tab = btf_parse_kptrs(btf, value_type); + if (map_value_has_kptrs(map)) { + if (!bpf_capable()) { + ret = -EPERM; + goto free_map_tab; + } + if (map->map_flags & (BPF_F_RDONLY_PROG | BPF_F_WRONLY_PROG)) { + ret = -EACCES; + goto free_map_tab; + } + if (map->map_type != BPF_MAP_TYPE_HASH && + map->map_type != BPF_MAP_TYPE_LRU_HASH && + map->map_type != BPF_MAP_TYPE_ARRAY) { + ret = -EOPNOTSUPP; + goto free_map_tab; + } + } + + if (map->ops->map_check_btf) { ret = map->ops->map_check_btf(map, btf, key_type, value_type); + if (ret < 0) + goto free_map_tab; + } return ret; +free_map_tab: + bpf_map_free_kptr_off_tab(map); + return ret; } #define BPF_MAP_CREATE_LAST_FIELD map_extra @@ -912,10 +1130,14 @@ static int map_create(union bpf_attr *attr) attr->btf_vmlinux_value_type_id; } - err = security_bpf_map_alloc(map); + err = bpf_map_alloc_off_arr(map); if (err) goto free_map; + err = security_bpf_map_alloc(map); + if (err) + goto free_map_off_arr; + err = bpf_map_alloc_id(map); if (err) goto free_map_sec; @@ -938,6 +1160,8 @@ static int map_create(union bpf_attr *attr) free_map_sec: security_bpf_map_free(map); +free_map_off_arr: + kfree(map->off_arr); free_map: btf_put(map->btf); map->ops->map_free(map); @@ -1639,7 +1863,7 @@ static int map_freeze(const union bpf_attr *attr) return PTR_ERR(map); if (map->map_type == BPF_MAP_TYPE_STRUCT_OPS || - map_value_has_timer(map)) { + map_value_has_timer(map) || map_value_has_kptrs(map)) { fdput(f); return -ENOTSUPP; } @@ -2640,19 +2864,12 @@ struct bpf_link *bpf_link_get_from_fd(u32 ufd) } EXPORT_SYMBOL(bpf_link_get_from_fd); -struct bpf_tracing_link { - struct bpf_link link; - enum bpf_attach_type attach_type; - struct bpf_trampoline *trampoline; - struct bpf_prog *tgt_prog; -}; - static void bpf_tracing_link_release(struct bpf_link *link) { struct bpf_tracing_link *tr_link = - container_of(link, struct bpf_tracing_link, link); + container_of(link, struct bpf_tracing_link, link.link); - WARN_ON_ONCE(bpf_trampoline_unlink_prog(link->prog, + WARN_ON_ONCE(bpf_trampoline_unlink_prog(&tr_link->link, tr_link->trampoline)); bpf_trampoline_put(tr_link->trampoline); @@ -2665,7 +2882,7 @@ static void bpf_tracing_link_release(struct bpf_link *link) static void bpf_tracing_link_dealloc(struct bpf_link *link) { struct bpf_tracing_link *tr_link = - container_of(link, struct bpf_tracing_link, link); + container_of(link, struct bpf_tracing_link, link.link); kfree(tr_link); } @@ -2674,7 +2891,7 @@ static void bpf_tracing_link_show_fdinfo(const struct bpf_link *link, struct seq_file *seq) { struct bpf_tracing_link *tr_link = - container_of(link, struct bpf_tracing_link, link); + container_of(link, struct bpf_tracing_link, link.link); seq_printf(seq, "attach_type:\t%d\n", @@ -2685,7 +2902,7 @@ static int bpf_tracing_link_fill_link_info(const struct bpf_link *link, struct bpf_link_info *info) { struct bpf_tracing_link *tr_link = - container_of(link, struct bpf_tracing_link, link); + container_of(link, struct bpf_tracing_link, link.link); info->tracing.attach_type = tr_link->attach_type; bpf_trampoline_unpack_key(tr_link->trampoline->key, @@ -2704,7 +2921,8 @@ static const struct bpf_link_ops bpf_tracing_link_lops = { static int bpf_tracing_prog_attach(struct bpf_prog *prog, int tgt_prog_fd, - u32 btf_id) + u32 btf_id, + u64 bpf_cookie) { struct bpf_link_primer link_primer; struct bpf_prog *tgt_prog = NULL; @@ -2766,9 +2984,10 @@ static int bpf_tracing_prog_attach(struct bpf_prog *prog, err = -ENOMEM; goto out_put_prog; } - bpf_link_init(&link->link, BPF_LINK_TYPE_TRACING, + bpf_link_init(&link->link.link, BPF_LINK_TYPE_TRACING, &bpf_tracing_link_lops, prog); link->attach_type = prog->expected_attach_type; + link->link.cookie = bpf_cookie; mutex_lock(&prog->aux->dst_mutex); @@ -2836,11 +3055,11 @@ static int bpf_tracing_prog_attach(struct bpf_prog *prog, tgt_prog = prog->aux->dst_prog; } - err = bpf_link_prime(&link->link, &link_primer); + err = bpf_link_prime(&link->link.link, &link_primer); if (err) goto out_unlock; - err = bpf_trampoline_link_prog(prog, tr); + err = bpf_trampoline_link_prog(&link->link, tr); if (err) { bpf_link_cleanup(&link_primer); link = NULL; @@ -3030,66 +3249,45 @@ static int bpf_perf_link_attach(const union bpf_attr *attr, struct bpf_prog *pro } #endif /* CONFIG_PERF_EVENTS */ -#define BPF_RAW_TRACEPOINT_OPEN_LAST_FIELD raw_tracepoint.prog_fd - -static int bpf_raw_tracepoint_open(const union bpf_attr *attr) +static int bpf_raw_tp_link_attach(struct bpf_prog *prog, + const char __user *user_tp_name) { struct bpf_link_primer link_primer; struct bpf_raw_tp_link *link; struct bpf_raw_event_map *btp; - struct bpf_prog *prog; const char *tp_name; char buf[128]; int err; - if (CHECK_ATTR(BPF_RAW_TRACEPOINT_OPEN)) - return -EINVAL; - - prog = bpf_prog_get(attr->raw_tracepoint.prog_fd); - if (IS_ERR(prog)) - return PTR_ERR(prog); - switch (prog->type) { case BPF_PROG_TYPE_TRACING: case BPF_PROG_TYPE_EXT: case BPF_PROG_TYPE_LSM: - if (attr->raw_tracepoint.name) { + if (user_tp_name) /* The attach point for this category of programs * should be specified via btf_id during program load. */ - err = -EINVAL; - goto out_put_prog; - } + return -EINVAL; if (prog->type == BPF_PROG_TYPE_TRACING && prog->expected_attach_type == BPF_TRACE_RAW_TP) { tp_name = prog->aux->attach_func_name; break; } - err = bpf_tracing_prog_attach(prog, 0, 0); - if (err >= 0) - return err; - goto out_put_prog; + return bpf_tracing_prog_attach(prog, 0, 0, 0); case BPF_PROG_TYPE_RAW_TRACEPOINT: case BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE: - if (strncpy_from_user(buf, - u64_to_user_ptr(attr->raw_tracepoint.name), - sizeof(buf) - 1) < 0) { - err = -EFAULT; - goto out_put_prog; - } + if (strncpy_from_user(buf, user_tp_name, sizeof(buf) - 1) < 0) + return -EFAULT; buf[sizeof(buf) - 1] = 0; tp_name = buf; break; default: - err = -EINVAL; - goto out_put_prog; + return -EINVAL; } btp = bpf_get_raw_tracepoint(tp_name); - if (!btp) { - err = -ENOENT; - goto out_put_prog; - } + if (!btp) + return -ENOENT; link = kzalloc(sizeof(*link), GFP_USER); if (!link) { @@ -3116,11 +3314,29 @@ static int bpf_raw_tracepoint_open(const union bpf_attr *attr) out_put_btp: bpf_put_raw_tracepoint(btp); -out_put_prog: - bpf_prog_put(prog); return err; } +#define BPF_RAW_TRACEPOINT_OPEN_LAST_FIELD raw_tracepoint.prog_fd + +static int bpf_raw_tracepoint_open(const union bpf_attr *attr) +{ + struct bpf_prog *prog; + int fd; + + if (CHECK_ATTR(BPF_RAW_TRACEPOINT_OPEN)) + return -EINVAL; + + prog = bpf_prog_get(attr->raw_tracepoint.prog_fd); + if (IS_ERR(prog)) + return PTR_ERR(prog); + + fd = bpf_raw_tp_link_attach(prog, u64_to_user_ptr(attr->raw_tracepoint.name)); + if (fd < 0) + bpf_prog_put(prog); + return fd; +} + static int bpf_prog_attach_check_attach_type(const struct bpf_prog *prog, enum bpf_attach_type attach_type) { @@ -3189,7 +3405,13 @@ attach_type_to_prog_type(enum bpf_attach_type attach_type) case BPF_CGROUP_SETSOCKOPT: return BPF_PROG_TYPE_CGROUP_SOCKOPT; case BPF_TRACE_ITER: + case BPF_TRACE_RAW_TP: + case BPF_TRACE_FENTRY: + case BPF_TRACE_FEXIT: + case BPF_MODIFY_RETURN: return BPF_PROG_TYPE_TRACING; + case BPF_LSM_MAC: + return BPF_PROG_TYPE_LSM; case BPF_SK_LOOKUP: return BPF_PROG_TYPE_SK_LOOKUP; case BPF_XDP: @@ -4246,21 +4468,6 @@ err_put: return err; } -static int tracing_bpf_link_attach(const union bpf_attr *attr, bpfptr_t uattr, - struct bpf_prog *prog) -{ - if (attr->link_create.attach_type != prog->expected_attach_type) - return -EINVAL; - - if (prog->expected_attach_type == BPF_TRACE_ITER) - return bpf_iter_link_attach(attr, uattr, prog); - else if (prog->type == BPF_PROG_TYPE_EXT) - return bpf_tracing_prog_attach(prog, - attr->link_create.target_fd, - attr->link_create.target_btf_id); - return -EINVAL; -} - #define BPF_LINK_CREATE_LAST_FIELD link_create.kprobe_multi.cookies static int link_create(union bpf_attr *attr, bpfptr_t uattr) { @@ -4282,15 +4489,13 @@ static int link_create(union bpf_attr *attr, bpfptr_t uattr) switch (prog->type) { case BPF_PROG_TYPE_EXT: - ret = tracing_bpf_link_attach(attr, uattr, prog); - goto out; + break; case BPF_PROG_TYPE_PERF_EVENT: case BPF_PROG_TYPE_TRACEPOINT: if (attr->link_create.attach_type != BPF_PERF_EVENT) { ret = -EINVAL; goto out; } - ptype = prog->type; break; case BPF_PROG_TYPE_KPROBE: if (attr->link_create.attach_type != BPF_PERF_EVENT && @@ -4298,7 +4503,6 @@ static int link_create(union bpf_attr *attr, bpfptr_t uattr) ret = -EINVAL; goto out; } - ptype = prog->type; break; default: ptype = attach_type_to_prog_type(attr->link_create.attach_type); @@ -4309,7 +4513,7 @@ static int link_create(union bpf_attr *attr, bpfptr_t uattr) break; } - switch (ptype) { + switch (prog->type) { case BPF_PROG_TYPE_CGROUP_SKB: case BPF_PROG_TYPE_CGROUP_SOCK: case BPF_PROG_TYPE_CGROUP_SOCK_ADDR: @@ -4319,8 +4523,27 @@ static int link_create(union bpf_attr *attr, bpfptr_t uattr) case BPF_PROG_TYPE_CGROUP_SOCKOPT: ret = cgroup_bpf_link_attach(attr, prog); break; + case BPF_PROG_TYPE_EXT: + ret = bpf_tracing_prog_attach(prog, + attr->link_create.target_fd, + attr->link_create.target_btf_id, + attr->link_create.tracing.cookie); + break; + case BPF_PROG_TYPE_LSM: case BPF_PROG_TYPE_TRACING: - ret = tracing_bpf_link_attach(attr, uattr, prog); + if (attr->link_create.attach_type != prog->expected_attach_type) { + ret = -EINVAL; + goto out; + } + if (prog->expected_attach_type == BPF_TRACE_RAW_TP) + ret = bpf_raw_tp_link_attach(prog, NULL); + else if (prog->expected_attach_type == BPF_TRACE_ITER) + ret = bpf_iter_link_attach(attr, uattr, prog); + else + ret = bpf_tracing_prog_attach(prog, + attr->link_create.target_fd, + attr->link_create.target_btf_id, + attr->link_create.tracing.cookie); break; case BPF_PROG_TYPE_FLOW_DISSECTOR: case BPF_PROG_TYPE_SK_LOOKUP: @@ -4454,6 +4677,25 @@ struct bpf_link *bpf_link_by_id(u32 id) return link; } +struct bpf_link *bpf_link_get_curr_or_next(u32 *id) +{ + struct bpf_link *link; + + spin_lock_bh(&link_idr_lock); +again: + link = idr_get_next(&link_idr, id); + if (link) { + link = bpf_link_inc_not_zero(link); + if (IS_ERR(link)) { + (*id)++; + goto again; + } + } + spin_unlock_bh(&link_idr_lock); + + return link; +} + #define BPF_LINK_GET_FD_BY_ID_LAST_FIELD link_id static int bpf_link_get_fd_by_id(const union bpf_attr *attr) @@ -4621,9 +4863,21 @@ out_prog_put: static int __sys_bpf(int cmd, bpfptr_t uattr, unsigned int size) { union bpf_attr attr; + bool capable; int err; - if (sysctl_unprivileged_bpf_disabled && !bpf_capable()) + capable = bpf_capable() || !sysctl_unprivileged_bpf_disabled; + + /* Intent here is for unprivileged_bpf_disabled to block key object + * creation commands for unprivileged users; other actions depend + * of fd availability and access to bpffs, so are dependent on + * object creation success. Capabilities are later verified for + * operations such as load and map create, so even with unprivileged + * BPF disabled, capability checks are still carried out for these + * and other operations. + */ + if (!capable && + (cmd == BPF_MAP_CREATE || cmd == BPF_PROG_LOAD)) return -EPERM; err = bpf_check_uarg_tail_zero(uattr, sizeof(attr), size); @@ -4782,6 +5036,7 @@ static bool syscall_prog_is_valid_access(int off, int size, BPF_CALL_3(bpf_sys_bpf, int, cmd, union bpf_attr *, attr, u32, attr_size) { struct bpf_prog * __maybe_unused prog; + struct bpf_tramp_run_ctx __maybe_unused run_ctx; switch (cmd) { case BPF_MAP_CREATE: @@ -4809,13 +5064,15 @@ BPF_CALL_3(bpf_sys_bpf, int, cmd, union bpf_attr *, attr, u32, attr_size) return -EINVAL; } - if (!__bpf_prog_enter_sleepable(prog)) { + run_ctx.bpf_cookie = 0; + run_ctx.saved_run_ctx = NULL; + if (!__bpf_prog_enter_sleepable(prog, &run_ctx)) { /* recursion detected */ bpf_prog_put(prog); return -EBUSY; } attr->test.retval = bpf_prog_run(prog, (void *) (long) attr->test.ctx_in); - __bpf_prog_exit_sleepable(prog, 0 /* bpf_prog_run does runtime stats */); + __bpf_prog_exit_sleepable(prog, 0 /* bpf_prog_run does runtime stats */, &run_ctx); bpf_prog_put(prog); return 0; #endif @@ -4908,3 +5165,90 @@ const struct bpf_verifier_ops bpf_syscall_verifier_ops = { const struct bpf_prog_ops bpf_syscall_prog_ops = { .test_run = bpf_prog_test_run_syscall, }; + +#ifdef CONFIG_SYSCTL +static int bpf_stats_handler(struct ctl_table *table, int write, + void *buffer, size_t *lenp, loff_t *ppos) +{ + struct static_key *key = (struct static_key *)table->data; + static int saved_val; + int val, ret; + struct ctl_table tmp = { + .data = &val, + .maxlen = sizeof(val), + .mode = table->mode, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, + }; + + if (write && !capable(CAP_SYS_ADMIN)) + return -EPERM; + + mutex_lock(&bpf_stats_enabled_mutex); + val = saved_val; + ret = proc_dointvec_minmax(&tmp, write, buffer, lenp, ppos); + if (write && !ret && val != saved_val) { + if (val) + static_key_slow_inc(key); + else + static_key_slow_dec(key); + saved_val = val; + } + mutex_unlock(&bpf_stats_enabled_mutex); + return ret; +} + +void __weak unpriv_ebpf_notify(int new_state) +{ +} + +static int bpf_unpriv_handler(struct ctl_table *table, int write, + void *buffer, size_t *lenp, loff_t *ppos) +{ + int ret, unpriv_enable = *(int *)table->data; + bool locked_state = unpriv_enable == 1; + struct ctl_table tmp = *table; + + if (write && !capable(CAP_SYS_ADMIN)) + return -EPERM; + + tmp.data = &unpriv_enable; + ret = proc_dointvec_minmax(&tmp, write, buffer, lenp, ppos); + if (write && !ret) { + if (locked_state && unpriv_enable != 1) + return -EPERM; + *(int *)table->data = unpriv_enable; + } + + unpriv_ebpf_notify(unpriv_enable); + + return ret; +} + +static struct ctl_table bpf_syscall_table[] = { + { + .procname = "unprivileged_bpf_disabled", + .data = &sysctl_unprivileged_bpf_disabled, + .maxlen = sizeof(sysctl_unprivileged_bpf_disabled), + .mode = 0644, + .proc_handler = bpf_unpriv_handler, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_TWO, + }, + { + .procname = "bpf_stats_enabled", + .data = &bpf_stats_enabled_key.key, + .maxlen = sizeof(bpf_stats_enabled_key), + .mode = 0644, + .proc_handler = bpf_stats_handler, + }, + { } +}; + +static int __init bpf_syscall_sysctl_init(void) +{ + register_sysctl_init("kernel", bpf_syscall_table); + return 0; +} +late_initcall(bpf_syscall_sysctl_init); +#endif /* CONFIG_SYSCTL */ diff --git a/kernel/bpf/task_iter.c b/kernel/bpf/task_iter.c index d94696198ef8..8c921799def4 100644 --- a/kernel/bpf/task_iter.c +++ b/kernel/bpf/task_iter.c @@ -99,7 +99,6 @@ static int __task_seq_show(struct seq_file *seq, struct task_struct *task, if (!prog) return 0; - meta.seq = seq; ctx.meta = &meta; ctx.task = task; return bpf_iter_run_prog(prog, &ctx); diff --git a/kernel/bpf/trampoline.c b/kernel/bpf/trampoline.c index ada97751ae1b..93c7675f0c9e 100644 --- a/kernel/bpf/trampoline.c +++ b/kernel/bpf/trampoline.c @@ -30,9 +30,12 @@ static DEFINE_MUTEX(trampoline_mutex); bool bpf_prog_has_trampoline(const struct bpf_prog *prog) { enum bpf_attach_type eatype = prog->expected_attach_type; + enum bpf_prog_type ptype = prog->type; - return eatype == BPF_TRACE_FENTRY || eatype == BPF_TRACE_FEXIT || - eatype == BPF_MODIFY_RETURN; + return (ptype == BPF_PROG_TYPE_TRACING && + (eatype == BPF_TRACE_FENTRY || eatype == BPF_TRACE_FEXIT || + eatype == BPF_MODIFY_RETURN)) || + (ptype == BPF_PROG_TYPE_LSM && eatype == BPF_LSM_MAC); } void *bpf_jit_alloc_exec_page(void) @@ -168,30 +171,30 @@ static int register_fentry(struct bpf_trampoline *tr, void *new_addr) return ret; } -static struct bpf_tramp_progs * +static struct bpf_tramp_links * bpf_trampoline_get_progs(const struct bpf_trampoline *tr, int *total, bool *ip_arg) { - const struct bpf_prog_aux *aux; - struct bpf_tramp_progs *tprogs; - struct bpf_prog **progs; + struct bpf_tramp_link *link; + struct bpf_tramp_links *tlinks; + struct bpf_tramp_link **links; int kind; *total = 0; - tprogs = kcalloc(BPF_TRAMP_MAX, sizeof(*tprogs), GFP_KERNEL); - if (!tprogs) + tlinks = kcalloc(BPF_TRAMP_MAX, sizeof(*tlinks), GFP_KERNEL); + if (!tlinks) return ERR_PTR(-ENOMEM); for (kind = 0; kind < BPF_TRAMP_MAX; kind++) { - tprogs[kind].nr_progs = tr->progs_cnt[kind]; + tlinks[kind].nr_links = tr->progs_cnt[kind]; *total += tr->progs_cnt[kind]; - progs = tprogs[kind].progs; + links = tlinks[kind].links; - hlist_for_each_entry(aux, &tr->progs_hlist[kind], tramp_hlist) { - *ip_arg |= aux->prog->call_get_func_ip; - *progs++ = aux->prog; + hlist_for_each_entry(link, &tr->progs_hlist[kind], tramp_hlist) { + *ip_arg |= link->link.prog->call_get_func_ip; + *links++ = link; } } - return tprogs; + return tlinks; } static void __bpf_tramp_image_put_deferred(struct work_struct *work) @@ -330,14 +333,14 @@ out: static int bpf_trampoline_update(struct bpf_trampoline *tr) { struct bpf_tramp_image *im; - struct bpf_tramp_progs *tprogs; + struct bpf_tramp_links *tlinks; u32 flags = BPF_TRAMP_F_RESTORE_REGS; bool ip_arg = false; int err, total; - tprogs = bpf_trampoline_get_progs(tr, &total, &ip_arg); - if (IS_ERR(tprogs)) - return PTR_ERR(tprogs); + tlinks = bpf_trampoline_get_progs(tr, &total, &ip_arg); + if (IS_ERR(tlinks)) + return PTR_ERR(tlinks); if (total == 0) { err = unregister_fentry(tr, tr->cur_image->image); @@ -353,15 +356,15 @@ static int bpf_trampoline_update(struct bpf_trampoline *tr) goto out; } - if (tprogs[BPF_TRAMP_FEXIT].nr_progs || - tprogs[BPF_TRAMP_MODIFY_RETURN].nr_progs) + if (tlinks[BPF_TRAMP_FEXIT].nr_links || + tlinks[BPF_TRAMP_MODIFY_RETURN].nr_links) flags = BPF_TRAMP_F_CALL_ORIG | BPF_TRAMP_F_SKIP_FRAME; if (ip_arg) flags |= BPF_TRAMP_F_IP_ARG; err = arch_prepare_bpf_trampoline(im, im->image, im->image + PAGE_SIZE, - &tr->func.model, flags, tprogs, + &tr->func.model, flags, tlinks, tr->func.addr); if (err < 0) goto out; @@ -381,7 +384,7 @@ static int bpf_trampoline_update(struct bpf_trampoline *tr) tr->cur_image = im; tr->selector++; out: - kfree(tprogs); + kfree(tlinks); return err; } @@ -407,13 +410,14 @@ static enum bpf_tramp_prog_type bpf_attach_type_to_tramp(struct bpf_prog *prog) } } -int bpf_trampoline_link_prog(struct bpf_prog *prog, struct bpf_trampoline *tr) +int bpf_trampoline_link_prog(struct bpf_tramp_link *link, struct bpf_trampoline *tr) { enum bpf_tramp_prog_type kind; + struct bpf_tramp_link *link_exiting; int err = 0; - int cnt; + int cnt = 0, i; - kind = bpf_attach_type_to_tramp(prog); + kind = bpf_attach_type_to_tramp(link->link.prog); mutex_lock(&tr->mutex); if (tr->extension_prog) { /* cannot attach fentry/fexit if extension prog is attached. @@ -422,32 +426,43 @@ int bpf_trampoline_link_prog(struct bpf_prog *prog, struct bpf_trampoline *tr) err = -EBUSY; goto out; } - cnt = tr->progs_cnt[BPF_TRAMP_FENTRY] + tr->progs_cnt[BPF_TRAMP_FEXIT]; + + for (i = 0; i < BPF_TRAMP_MAX; i++) + cnt += tr->progs_cnt[i]; + if (kind == BPF_TRAMP_REPLACE) { /* Cannot attach extension if fentry/fexit are in use. */ if (cnt) { err = -EBUSY; goto out; } - tr->extension_prog = prog; + tr->extension_prog = link->link.prog; err = bpf_arch_text_poke(tr->func.addr, BPF_MOD_JUMP, NULL, - prog->bpf_func); + link->link.prog->bpf_func); goto out; } - if (cnt >= BPF_MAX_TRAMP_PROGS) { + if (cnt >= BPF_MAX_TRAMP_LINKS) { err = -E2BIG; goto out; } - if (!hlist_unhashed(&prog->aux->tramp_hlist)) { + if (!hlist_unhashed(&link->tramp_hlist)) { + /* prog already linked */ + err = -EBUSY; + goto out; + } + hlist_for_each_entry(link_exiting, &tr->progs_hlist[kind], tramp_hlist) { + if (link_exiting->link.prog != link->link.prog) + continue; /* prog already linked */ err = -EBUSY; goto out; } - hlist_add_head(&prog->aux->tramp_hlist, &tr->progs_hlist[kind]); + + hlist_add_head(&link->tramp_hlist, &tr->progs_hlist[kind]); tr->progs_cnt[kind]++; err = bpf_trampoline_update(tr); if (err) { - hlist_del_init(&prog->aux->tramp_hlist); + hlist_del_init(&link->tramp_hlist); tr->progs_cnt[kind]--; } out: @@ -456,12 +471,12 @@ out: } /* bpf_trampoline_unlink_prog() should never fail. */ -int bpf_trampoline_unlink_prog(struct bpf_prog *prog, struct bpf_trampoline *tr) +int bpf_trampoline_unlink_prog(struct bpf_tramp_link *link, struct bpf_trampoline *tr) { enum bpf_tramp_prog_type kind; int err; - kind = bpf_attach_type_to_tramp(prog); + kind = bpf_attach_type_to_tramp(link->link.prog); mutex_lock(&tr->mutex); if (kind == BPF_TRAMP_REPLACE) { WARN_ON_ONCE(!tr->extension_prog); @@ -470,7 +485,7 @@ int bpf_trampoline_unlink_prog(struct bpf_prog *prog, struct bpf_trampoline *tr) tr->extension_prog = NULL; goto out; } - hlist_del_init(&prog->aux->tramp_hlist); + hlist_del_init(&link->tramp_hlist); tr->progs_cnt[kind]--; err = bpf_trampoline_update(tr); out: @@ -500,16 +515,19 @@ out: void bpf_trampoline_put(struct bpf_trampoline *tr) { + int i; + if (!tr) return; mutex_lock(&trampoline_mutex); if (!refcount_dec_and_test(&tr->refcnt)) goto out; WARN_ON_ONCE(mutex_is_locked(&tr->mutex)); - if (WARN_ON_ONCE(!hlist_empty(&tr->progs_hlist[BPF_TRAMP_FENTRY]))) - goto out; - if (WARN_ON_ONCE(!hlist_empty(&tr->progs_hlist[BPF_TRAMP_FEXIT]))) - goto out; + + for (i = 0; i < BPF_TRAMP_MAX; i++) + if (WARN_ON_ONCE(!hlist_empty(&tr->progs_hlist[i]))) + goto out; + /* This code will be executed even when the last bpf_tramp_image * is alive. All progs are detached from the trampoline and the * trampoline image is patched with jmp into epilogue to skip @@ -559,11 +577,14 @@ static void notrace inc_misses_counter(struct bpf_prog *prog) * [2..MAX_U64] - execute bpf prog and record execution time. * This is start time. */ -u64 notrace __bpf_prog_enter(struct bpf_prog *prog) +u64 notrace __bpf_prog_enter(struct bpf_prog *prog, struct bpf_tramp_run_ctx *run_ctx) __acquires(RCU) { rcu_read_lock(); migrate_disable(); + + run_ctx->saved_run_ctx = bpf_set_run_ctx(&run_ctx->run_ctx); + if (unlikely(__this_cpu_inc_return(*(prog->active)) != 1)) { inc_misses_counter(prog); return 0; @@ -593,29 +614,38 @@ static void notrace update_prog_stats(struct bpf_prog *prog, } } -void notrace __bpf_prog_exit(struct bpf_prog *prog, u64 start) +void notrace __bpf_prog_exit(struct bpf_prog *prog, u64 start, struct bpf_tramp_run_ctx *run_ctx) __releases(RCU) { + bpf_reset_run_ctx(run_ctx->saved_run_ctx); + update_prog_stats(prog, start); __this_cpu_dec(*(prog->active)); migrate_enable(); rcu_read_unlock(); } -u64 notrace __bpf_prog_enter_sleepable(struct bpf_prog *prog) +u64 notrace __bpf_prog_enter_sleepable(struct bpf_prog *prog, struct bpf_tramp_run_ctx *run_ctx) { rcu_read_lock_trace(); migrate_disable(); might_fault(); + if (unlikely(__this_cpu_inc_return(*(prog->active)) != 1)) { inc_misses_counter(prog); return 0; } + + run_ctx->saved_run_ctx = bpf_set_run_ctx(&run_ctx->run_ctx); + return bpf_prog_start_time(); } -void notrace __bpf_prog_exit_sleepable(struct bpf_prog *prog, u64 start) +void notrace __bpf_prog_exit_sleepable(struct bpf_prog *prog, u64 start, + struct bpf_tramp_run_ctx *run_ctx) { + bpf_reset_run_ctx(run_ctx->saved_run_ctx); + update_prog_stats(prog, start); __this_cpu_dec(*(prog->active)); migrate_enable(); @@ -635,7 +665,7 @@ void notrace __bpf_tramp_exit(struct bpf_tramp_image *tr) int __weak arch_prepare_bpf_trampoline(struct bpf_tramp_image *tr, void *image, void *image_end, const struct btf_func_model *m, u32 flags, - struct bpf_tramp_progs *tprogs, + struct bpf_tramp_links *tlinks, void *orig_call) { return -ENOTSUPP; diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index d175b70067b3..aedac2ac02b9 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -187,6 +187,9 @@ struct bpf_verifier_stack_elem { POISON_POINTER_DELTA)) #define BPF_MAP_PTR(X) ((struct bpf_map *)((X) & ~BPF_MAP_PTR_UNPRIV)) +static int acquire_reference_state(struct bpf_verifier_env *env, int insn_idx); +static int release_reference(struct bpf_verifier_env *env, int ref_obj_id); + static bool bpf_map_ptr_poisoned(const struct bpf_insn_aux_data *aux) { return BPF_MAP_PTR(aux->map_ptr_state) == BPF_MAP_PTR_POISON; @@ -245,6 +248,7 @@ struct bpf_call_arg_meta { struct bpf_map *map_ptr; bool raw_mode; bool pkt_access; + u8 release_regno; int regno; int access_size; int mem_size; @@ -257,6 +261,8 @@ struct bpf_call_arg_meta { struct btf *ret_btf; u32 ret_btf_id; u32 subprogno; + struct bpf_map_value_off_desc *kptr_off_desc; + u8 uninit_dynptr_regno; }; struct btf *btf_vmlinux; @@ -471,17 +477,6 @@ static bool type_may_be_null(u32 type) return type & PTR_MAYBE_NULL; } -/* Determine whether the function releases some resources allocated by another - * function call. The first reference type argument will be assumed to be - * released by release_reference(). - */ -static bool is_release_function(enum bpf_func_id func_id) -{ - return func_id == BPF_FUNC_sk_release || - func_id == BPF_FUNC_ringbuf_submit || - func_id == BPF_FUNC_ringbuf_discard; -} - static bool may_be_acquire_function(enum bpf_func_id func_id) { return func_id == BPF_FUNC_sk_lookup_tcp || @@ -499,7 +494,8 @@ static bool is_acquire_function(enum bpf_func_id func_id, if (func_id == BPF_FUNC_sk_lookup_tcp || func_id == BPF_FUNC_sk_lookup_udp || func_id == BPF_FUNC_skc_lookup_tcp || - func_id == BPF_FUNC_ringbuf_reserve) + func_id == BPF_FUNC_ringbuf_reserve || + func_id == BPF_FUNC_kptr_xchg) return true; if (func_id == BPF_FUNC_map_lookup_elem && @@ -517,6 +513,7 @@ static bool is_ptr_cast_function(enum bpf_func_id func_id) func_id == BPF_FUNC_skc_to_tcp_sock || func_id == BPF_FUNC_skc_to_tcp6_sock || func_id == BPF_FUNC_skc_to_udp6_sock || + func_id == BPF_FUNC_skc_to_mptcp_sock || func_id == BPF_FUNC_skc_to_tcp_timewait_sock || func_id == BPF_FUNC_skc_to_tcp_request_sock; } @@ -575,6 +572,8 @@ static const char *reg_type_str(struct bpf_verifier_env *env, strncpy(prefix, "user_", 32); if (type & MEM_PERCPU) strncpy(prefix, "percpu_", 32); + if (type & PTR_UNTRUSTED) + strncpy(prefix, "untrusted_", 32); snprintf(env->type_str_buf, TYPE_STR_BUF_LEN, "%s%s%s", prefix, str[base_type(type)], postfix); @@ -586,6 +585,7 @@ static char slot_type_char[] = { [STACK_SPILL] = 'r', [STACK_MISC] = 'm', [STACK_ZERO] = '0', + [STACK_DYNPTR] = 'd', }; static void print_liveness(struct bpf_verifier_env *env, @@ -601,6 +601,25 @@ static void print_liveness(struct bpf_verifier_env *env, verbose(env, "D"); } +static int get_spi(s32 off) +{ + return (-off - 1) / BPF_REG_SIZE; +} + +static bool is_spi_bounds_valid(struct bpf_func_state *state, int spi, int nr_slots) +{ + int allocated_slots = state->allocated_stack / BPF_REG_SIZE; + + /* We need to check that slots between [spi - nr_slots + 1, spi] are + * within [0, allocated_stack). + * + * Please note that the spi grows downwards. For example, a dynptr + * takes the size of two stack slots; the first slot will be at + * spi and the second slot will be at spi - 1. + */ + return spi - nr_slots + 1 >= 0 && spi < allocated_slots; +} + static struct bpf_func_state *func(struct bpf_verifier_env *env, const struct bpf_reg_state *reg) { @@ -652,6 +671,132 @@ static void mark_verifier_state_scratched(struct bpf_verifier_env *env) env->scratched_stack_slots = ~0ULL; } +static enum bpf_dynptr_type arg_to_dynptr_type(enum bpf_arg_type arg_type) +{ + switch (arg_type & DYNPTR_TYPE_FLAG_MASK) { + case DYNPTR_TYPE_LOCAL: + return BPF_DYNPTR_TYPE_LOCAL; + case DYNPTR_TYPE_RINGBUF: + return BPF_DYNPTR_TYPE_RINGBUF; + default: + return BPF_DYNPTR_TYPE_INVALID; + } +} + +static bool dynptr_type_refcounted(enum bpf_dynptr_type type) +{ + return type == BPF_DYNPTR_TYPE_RINGBUF; +} + +static int mark_stack_slots_dynptr(struct bpf_verifier_env *env, struct bpf_reg_state *reg, + enum bpf_arg_type arg_type, int insn_idx) +{ + struct bpf_func_state *state = func(env, reg); + enum bpf_dynptr_type type; + int spi, i, id; + + spi = get_spi(reg->off); + + if (!is_spi_bounds_valid(state, spi, BPF_DYNPTR_NR_SLOTS)) + return -EINVAL; + + for (i = 0; i < BPF_REG_SIZE; i++) { + state->stack[spi].slot_type[i] = STACK_DYNPTR; + state->stack[spi - 1].slot_type[i] = STACK_DYNPTR; + } + + type = arg_to_dynptr_type(arg_type); + if (type == BPF_DYNPTR_TYPE_INVALID) + return -EINVAL; + + state->stack[spi].spilled_ptr.dynptr.first_slot = true; + state->stack[spi].spilled_ptr.dynptr.type = type; + state->stack[spi - 1].spilled_ptr.dynptr.type = type; + + if (dynptr_type_refcounted(type)) { + /* The id is used to track proper releasing */ + id = acquire_reference_state(env, insn_idx); + if (id < 0) + return id; + + state->stack[spi].spilled_ptr.id = id; + state->stack[spi - 1].spilled_ptr.id = id; + } + + return 0; +} + +static int unmark_stack_slots_dynptr(struct bpf_verifier_env *env, struct bpf_reg_state *reg) +{ + struct bpf_func_state *state = func(env, reg); + int spi, i; + + spi = get_spi(reg->off); + + if (!is_spi_bounds_valid(state, spi, BPF_DYNPTR_NR_SLOTS)) + return -EINVAL; + + for (i = 0; i < BPF_REG_SIZE; i++) { + state->stack[spi].slot_type[i] = STACK_INVALID; + state->stack[spi - 1].slot_type[i] = STACK_INVALID; + } + + /* Invalidate any slices associated with this dynptr */ + if (dynptr_type_refcounted(state->stack[spi].spilled_ptr.dynptr.type)) { + release_reference(env, state->stack[spi].spilled_ptr.id); + state->stack[spi].spilled_ptr.id = 0; + state->stack[spi - 1].spilled_ptr.id = 0; + } + + state->stack[spi].spilled_ptr.dynptr.first_slot = false; + state->stack[spi].spilled_ptr.dynptr.type = 0; + state->stack[spi - 1].spilled_ptr.dynptr.type = 0; + + return 0; +} + +static bool is_dynptr_reg_valid_uninit(struct bpf_verifier_env *env, struct bpf_reg_state *reg) +{ + struct bpf_func_state *state = func(env, reg); + int spi = get_spi(reg->off); + int i; + + if (!is_spi_bounds_valid(state, spi, BPF_DYNPTR_NR_SLOTS)) + return true; + + for (i = 0; i < BPF_REG_SIZE; i++) { + if (state->stack[spi].slot_type[i] == STACK_DYNPTR || + state->stack[spi - 1].slot_type[i] == STACK_DYNPTR) + return false; + } + + return true; +} + +static bool is_dynptr_reg_valid_init(struct bpf_verifier_env *env, struct bpf_reg_state *reg, + enum bpf_arg_type arg_type) +{ + struct bpf_func_state *state = func(env, reg); + int spi = get_spi(reg->off); + int i; + + if (!is_spi_bounds_valid(state, spi, BPF_DYNPTR_NR_SLOTS) || + !state->stack[spi].spilled_ptr.dynptr.first_slot) + return false; + + for (i = 0; i < BPF_REG_SIZE; i++) { + if (state->stack[spi].slot_type[i] != STACK_DYNPTR || + state->stack[spi - 1].slot_type[i] != STACK_DYNPTR) + return false; + } + + /* ARG_PTR_TO_DYNPTR takes any type of dynptr */ + if (arg_type == ARG_PTR_TO_DYNPTR) + return true; + + return state->stack[spi].spilled_ptr.dynptr.type == arg_to_dynptr_type(arg_type); +} + /* The reg state of a pointer or a bounded scalar was saved when * it was spilled to the stack. */ @@ -1821,8 +1966,7 @@ void bpf_free_kfunc_btf_tab(struct bpf_kfunc_btf_tab *tab) kfree(tab); } -static struct btf *find_kfunc_desc_btf(struct bpf_verifier_env *env, - u32 func_id, s16 offset) +static struct btf *find_kfunc_desc_btf(struct bpf_verifier_env *env, s16 offset) { if (offset) { if (offset < 0) { @@ -1897,7 +2041,7 @@ static int add_kfunc_call(struct bpf_verifier_env *env, u32 func_id, s16 offset) prog_aux->kfunc_btf_tab = btf_tab; } - desc_btf = find_kfunc_desc_btf(env, func_id, offset); + desc_btf = find_kfunc_desc_btf(env, offset); if (IS_ERR(desc_btf)) { verbose(env, "failed to find BTF for kernel function\n"); return PTR_ERR(desc_btf); @@ -2366,7 +2510,7 @@ static const char *disasm_kfunc_name(void *data, const struct bpf_insn *insn) if (insn->src_reg != BPF_PSEUDO_KFUNC_CALL) return NULL; - desc_btf = find_kfunc_desc_btf(data, insn->imm, insn->off); + desc_btf = find_kfunc_desc_btf(data, insn->off); if (IS_ERR(desc_btf)) return "<error>"; @@ -3211,7 +3355,7 @@ static int check_stack_read_fixed_off(struct bpf_verifier_env *env, return 0; } -enum stack_access_src { +enum bpf_access_src { ACCESS_DIRECT = 1, /* the access is performed by an instruction */ ACCESS_HELPER = 2, /* the access is performed by a helper */ }; @@ -3219,7 +3363,7 @@ enum stack_access_src { static int check_stack_range_initialized(struct bpf_verifier_env *env, int regno, int off, int access_size, bool zero_size_allowed, - enum stack_access_src type, + enum bpf_access_src type, struct bpf_call_arg_meta *meta); static struct bpf_reg_state *reg_state(struct bpf_verifier_env *env, int regno) @@ -3469,9 +3613,175 @@ static int check_mem_region_access(struct bpf_verifier_env *env, u32 regno, return 0; } +static int __check_ptr_off_reg(struct bpf_verifier_env *env, + const struct bpf_reg_state *reg, int regno, + bool fixed_off_ok) +{ + /* Access to this pointer-typed register or passing it to a helper + * is only allowed in its original, unmodified form. + */ + + if (reg->off < 0) { + verbose(env, "negative offset %s ptr R%d off=%d disallowed\n", + reg_type_str(env, reg->type), regno, reg->off); + return -EACCES; + } + + if (!fixed_off_ok && reg->off) { + verbose(env, "dereference of modified %s ptr R%d off=%d disallowed\n", + reg_type_str(env, reg->type), regno, reg->off); + return -EACCES; + } + + if (!tnum_is_const(reg->var_off) || reg->var_off.value) { + char tn_buf[48]; + + tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off); + verbose(env, "variable %s access var_off=%s disallowed\n", + reg_type_str(env, reg->type), tn_buf); + return -EACCES; + } + + return 0; +} + +int check_ptr_off_reg(struct bpf_verifier_env *env, + const struct bpf_reg_state *reg, int regno) +{ + return __check_ptr_off_reg(env, reg, regno, false); +} + +static int map_kptr_match_type(struct bpf_verifier_env *env, + struct bpf_map_value_off_desc *off_desc, + struct bpf_reg_state *reg, u32 regno) +{ + const char *targ_name = kernel_type_name(off_desc->kptr.btf, off_desc->kptr.btf_id); + int perm_flags = PTR_MAYBE_NULL; + const char *reg_name = ""; + + /* Only unreferenced case accepts untrusted pointers */ + if (off_desc->type == BPF_KPTR_UNREF) + perm_flags |= PTR_UNTRUSTED; + + if (base_type(reg->type) != PTR_TO_BTF_ID || (type_flag(reg->type) & ~perm_flags)) + goto bad_type; + + if (!btf_is_kernel(reg->btf)) { + verbose(env, "R%d must point to kernel BTF\n", regno); + 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); + + /* 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 + * normal store of unreferenced kptr, we must ensure var_off is zero. + * Since ref_ptr cannot be accessed directly by BPF insns, checks for + * reg->off and reg->ref_obj_id are not needed here. + */ + if (__check_ptr_off_reg(env, reg, regno, true)) + return -EACCES; + + /* A full type match is needed, as BTF can be vmlinux or module BTF, and + * we also need to take into account the reg->off. + * + * We want to support cases like: + * + * struct foo { + * struct bar br; + * struct baz bz; + * }; + * + * struct foo *v; + * v = func(); // PTR_TO_BTF_ID + * val->foo = v; // reg->off is zero, btf and btf_id match type + * val->bar = &v->br; // reg->off is still zero, but we need to retry with + * // first member type of struct after comparison fails + * val->baz = &v->bz; // reg->off is non-zero, so struct needs to be walked + * // to match type + * + * In the kptr_ref case, check_func_arg_reg_off already ensures reg->off + * is zero. We must also ensure that btf_struct_ids_match does not walk + * the struct to match type against first member of struct, i.e. reject + * second case from above. Hence, when type is BPF_KPTR_REF, we set + * strict mode to true for type match. + */ + if (!btf_struct_ids_match(&env->log, reg->btf, reg->btf_id, reg->off, + off_desc->kptr.btf, off_desc->kptr.btf_id, + off_desc->type == BPF_KPTR_REF)) + goto bad_type; + return 0; +bad_type: + verbose(env, "invalid kptr access, R%d type=%s%s ", regno, + reg_type_str(env, reg->type), reg_name); + verbose(env, "expected=%s%s", reg_type_str(env, PTR_TO_BTF_ID), targ_name); + if (off_desc->type == BPF_KPTR_UNREF) + verbose(env, " or %s%s\n", reg_type_str(env, PTR_TO_BTF_ID | PTR_UNTRUSTED), + targ_name); + else + verbose(env, "\n"); + return -EINVAL; +} + +static int check_map_kptr_access(struct bpf_verifier_env *env, u32 regno, + int value_regno, int insn_idx, + struct bpf_map_value_off_desc *off_desc) +{ + struct bpf_insn *insn = &env->prog->insnsi[insn_idx]; + int class = BPF_CLASS(insn->code); + struct bpf_reg_state *val_reg; + + /* Things we already checked for in check_map_access and caller: + * - Reject cases where variable offset may touch kptr + * - size of access (must be BPF_DW) + * - tnum_is_const(reg->var_off) + * - off_desc->offset == off + reg->var_off.value + */ + /* Only BPF_[LDX,STX,ST] | BPF_MEM | BPF_DW is supported */ + if (BPF_MODE(insn->code) != BPF_MEM) { + verbose(env, "kptr in map can only be accessed using BPF_MEM instruction mode\n"); + return -EACCES; + } + + /* We only allow loading referenced kptr, since it will be marked as + * untrusted, similar to unreferenced kptr. + */ + if (class != BPF_LDX && off_desc->type == BPF_KPTR_REF) { + verbose(env, "store to referenced kptr disallowed\n"); + return -EACCES; + } + + if (class == BPF_LDX) { + val_reg = reg_state(env, value_regno); + /* We can simply mark the value_regno receiving the pointer + * value from map as PTR_TO_BTF_ID, with the correct type. + */ + mark_btf_ld_reg(env, cur_regs(env), value_regno, PTR_TO_BTF_ID, off_desc->kptr.btf, + off_desc->kptr.btf_id, PTR_MAYBE_NULL | PTR_UNTRUSTED); + /* For mark_ptr_or_null_reg */ + val_reg->id = ++env->id_gen; + } else if (class == BPF_STX) { + val_reg = reg_state(env, value_regno); + if (!register_is_null(val_reg) && + map_kptr_match_type(env, off_desc, val_reg, value_regno)) + return -EACCES; + } else if (class == BPF_ST) { + if (insn->imm) { + verbose(env, "BPF_ST imm must be 0 when storing to kptr at off=%u\n", + off_desc->offset); + return -EACCES; + } + } else { + verbose(env, "kptr in map can only be accessed using BPF_LDX/BPF_STX/BPF_ST\n"); + return -EACCES; + } + return 0; +} + /* check read/write into a map element with possible variable offset */ static int check_map_access(struct bpf_verifier_env *env, u32 regno, - int off, int size, bool zero_size_allowed) + int off, int size, bool zero_size_allowed, + enum bpf_access_src src) { struct bpf_verifier_state *vstate = env->cur_state; struct bpf_func_state *state = vstate->frame[vstate->curframe]; @@ -3507,6 +3817,36 @@ static int check_map_access(struct bpf_verifier_env *env, u32 regno, return -EACCES; } } + if (map_value_has_kptrs(map)) { + struct bpf_map_value_off *tab = map->kptr_off_tab; + int i; + + for (i = 0; i < tab->nr_off; i++) { + u32 p = tab->off[i].offset; + + if (reg->smin_value + off < p + sizeof(u64) && + p < reg->umax_value + off + size) { + if (src != ACCESS_DIRECT) { + verbose(env, "kptr cannot be accessed indirectly by helper\n"); + return -EACCES; + } + if (!tnum_is_const(reg->var_off)) { + verbose(env, "kptr access cannot have variable offset\n"); + return -EACCES; + } + if (p != off + reg->var_off.value) { + verbose(env, "kptr access misaligned expected=%u off=%llu\n", + p, off + reg->var_off.value); + return -EACCES; + } + if (size != bpf_size_to_bytes(BPF_DW)) { + verbose(env, "kptr access size must be BPF_DW\n"); + return -EACCES; + } + break; + } + } + } return err; } @@ -3980,44 +4320,6 @@ static int get_callee_stack_depth(struct bpf_verifier_env *env, } #endif -static int __check_ptr_off_reg(struct bpf_verifier_env *env, - const struct bpf_reg_state *reg, int regno, - bool fixed_off_ok) -{ - /* Access to this pointer-typed register or passing it to a helper - * is only allowed in its original, unmodified form. - */ - - if (reg->off < 0) { - verbose(env, "negative offset %s ptr R%d off=%d disallowed\n", - reg_type_str(env, reg->type), regno, reg->off); - return -EACCES; - } - - if (!fixed_off_ok && reg->off) { - verbose(env, "dereference of modified %s ptr R%d off=%d disallowed\n", - reg_type_str(env, reg->type), regno, reg->off); - return -EACCES; - } - - if (!tnum_is_const(reg->var_off) || reg->var_off.value) { - char tn_buf[48]; - - tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off); - verbose(env, "variable %s access var_off=%s disallowed\n", - reg_type_str(env, reg->type), tn_buf); - return -EACCES; - } - - return 0; -} - -int check_ptr_off_reg(struct bpf_verifier_env *env, - const struct bpf_reg_state *reg, int regno) -{ - return __check_ptr_off_reg(env, reg, regno, false); -} - static int __check_buffer_access(struct bpf_verifier_env *env, const char *buf_info, const struct bpf_reg_state *reg, @@ -4224,6 +4526,12 @@ static int check_ptr_to_btf_access(struct bpf_verifier_env *env, if (ret < 0) return ret; + /* If this is an untrusted pointer, all pointers formed by walking it + * also inherit the untrusted flag. + */ + if (type_flag(reg->type) & PTR_UNTRUSTED) + flag |= PTR_UNTRUSTED; + if (atype == BPF_READ && value_regno >= 0) mark_btf_ld_reg(env, regs, value_regno, ret, reg->btf, btf_id, flag); @@ -4316,7 +4624,7 @@ static int check_stack_slot_within_bounds(int off, static int check_stack_access_within_bounds( struct bpf_verifier_env *env, int regno, int off, int access_size, - enum stack_access_src src, enum bpf_access_type type) + enum bpf_access_src src, enum bpf_access_type type) { struct bpf_reg_state *regs = cur_regs(env); struct bpf_reg_state *reg = regs + regno; @@ -4412,6 +4720,8 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn if (value_regno >= 0) mark_reg_unknown(env, regs, value_regno); } else if (reg->type == PTR_TO_MAP_VALUE) { + struct bpf_map_value_off_desc *kptr_off_desc = NULL; + if (t == BPF_WRITE && value_regno >= 0 && is_pointer_value(env, value_regno)) { verbose(env, "R%d leaks addr into map\n", value_regno); @@ -4420,8 +4730,16 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn err = check_map_access_type(env, regno, off, size, t); if (err) return err; - err = check_map_access(env, regno, off, size, false); - if (!err && t == BPF_READ && value_regno >= 0) { + err = check_map_access(env, regno, off, size, false, ACCESS_DIRECT); + if (err) + return err; + if (tnum_is_const(reg->var_off)) + kptr_off_desc = bpf_map_kptr_off_contains(reg->map_ptr, + off + reg->var_off.value); + if (kptr_off_desc) { + err = check_map_kptr_access(env, regno, value_regno, insn_idx, + kptr_off_desc); + } else if (t == BPF_READ && value_regno >= 0) { struct bpf_map *map = reg->map_ptr; /* if map is read-only, track its contents as scalars */ @@ -4724,7 +5042,7 @@ static int check_atomic(struct bpf_verifier_env *env, int insn_idx, struct bpf_i static int check_stack_range_initialized( struct bpf_verifier_env *env, int regno, int off, int access_size, bool zero_size_allowed, - enum stack_access_src type, struct bpf_call_arg_meta *meta) + enum bpf_access_src type, struct bpf_call_arg_meta *meta) { struct bpf_reg_state *reg = reg_state(env, regno); struct bpf_func_state *state = func(env, reg); @@ -4861,6 +5179,11 @@ static int check_helper_mem_access(struct bpf_verifier_env *env, int regno, return check_packet_access(env, regno, reg->off, access_size, zero_size_allowed); case PTR_TO_MAP_KEY: + if (meta && meta->raw_mode) { + verbose(env, "R%d cannot write into %s\n", regno, + reg_type_str(env, reg->type)); + return -EACCES; + } return check_mem_region_access(env, regno, reg->off, access_size, reg->map_ptr->key_size, false); case PTR_TO_MAP_VALUE: @@ -4869,15 +5192,25 @@ static int check_helper_mem_access(struct bpf_verifier_env *env, int regno, BPF_READ)) return -EACCES; return check_map_access(env, regno, reg->off, access_size, - zero_size_allowed); + zero_size_allowed, ACCESS_HELPER); case PTR_TO_MEM: + if (type_is_rdonly_mem(reg->type)) { + if (meta && meta->raw_mode) { + verbose(env, "R%d cannot write into %s\n", regno, + reg_type_str(env, reg->type)); + return -EACCES; + } + } return check_mem_region_access(env, regno, reg->off, access_size, reg->mem_size, zero_size_allowed); case PTR_TO_BUF: if (type_is_rdonly_mem(reg->type)) { - if (meta && meta->raw_mode) + if (meta && meta->raw_mode) { + verbose(env, "R%d cannot write into %s\n", regno, + reg_type_str(env, reg->type)); return -EACCES; + } max_access = &env->prog->aux->max_rdonly_access; } else { @@ -4919,8 +5252,7 @@ static int check_mem_size_reg(struct bpf_verifier_env *env, * out. Only upper bounds can be learned because retval is an * int type and negative retvals are allowed. */ - if (meta) - meta->msize_max_value = reg->umax_value; + meta->msize_max_value = reg->umax_value; /* The register is SCALAR_VALUE; the access check * happens using its boundaries. @@ -4963,24 +5295,33 @@ static int check_mem_size_reg(struct bpf_verifier_env *env, int check_mem_reg(struct bpf_verifier_env *env, struct bpf_reg_state *reg, u32 regno, u32 mem_size) { + bool may_be_null = type_may_be_null(reg->type); + struct bpf_reg_state saved_reg; + struct bpf_call_arg_meta meta; + int err; + if (register_is_null(reg)) return 0; - if (type_may_be_null(reg->type)) { - /* Assuming that the register contains a value check if the memory - * access is safe. Temporarily save and restore the register's state as - * the conversion shouldn't be visible to a caller. - */ - const struct bpf_reg_state saved_reg = *reg; - int rv; - + memset(&meta, 0, sizeof(meta)); + /* Assuming that the register contains a value check if the memory + * access is safe. Temporarily save and restore the register's state as + * the conversion shouldn't be visible to a caller. + */ + if (may_be_null) { + saved_reg = *reg; mark_ptr_not_null_reg(reg); - rv = check_helper_mem_access(env, regno, mem_size, true, NULL); - *reg = saved_reg; - return rv; } - return check_helper_mem_access(env, regno, mem_size, true, NULL); + err = check_helper_mem_access(env, regno, mem_size, true, &meta); + /* Check access for BPF_WRITE */ + meta.raw_mode = true; + err = err ?: check_helper_mem_access(env, regno, mem_size, true, &meta); + + if (may_be_null) + *reg = saved_reg; + + return err; } int check_kfunc_mem_size_reg(struct bpf_verifier_env *env, struct bpf_reg_state *reg, @@ -4989,16 +5330,22 @@ int check_kfunc_mem_size_reg(struct bpf_verifier_env *env, struct bpf_reg_state struct bpf_reg_state *mem_reg = &cur_regs(env)[regno - 1]; bool may_be_null = type_may_be_null(mem_reg->type); struct bpf_reg_state saved_reg; + struct bpf_call_arg_meta meta; int err; WARN_ON_ONCE(regno < BPF_REG_2 || regno > BPF_REG_5); + memset(&meta, 0, sizeof(meta)); + if (may_be_null) { saved_reg = *mem_reg; mark_ptr_not_null_reg(mem_reg); } - err = check_mem_size_reg(env, reg, regno, true, NULL); + err = check_mem_size_reg(env, reg, regno, true, &meta); + /* Check access for BPF_WRITE */ + meta.raw_mode = true; + err = err ?: check_mem_size_reg(env, reg, regno, true, &meta); if (may_be_null) *mem_reg = saved_reg; @@ -5134,10 +5481,51 @@ static int process_timer_func(struct bpf_verifier_env *env, int regno, return 0; } -static bool arg_type_is_mem_ptr(enum bpf_arg_type type) +static int process_kptr_func(struct bpf_verifier_env *env, int regno, + struct bpf_call_arg_meta *meta) { - return base_type(type) == ARG_PTR_TO_MEM || - base_type(type) == ARG_PTR_TO_UNINIT_MEM; + struct bpf_reg_state *regs = cur_regs(env), *reg = ®s[regno]; + struct bpf_map_value_off_desc *off_desc; + struct bpf_map *map_ptr = reg->map_ptr; + u32 kptr_off; + int ret; + + if (!tnum_is_const(reg->var_off)) { + verbose(env, + "R%d doesn't have constant offset. kptr has to be at the constant offset\n", + regno); + return -EINVAL; + } + if (!map_ptr->btf) { + verbose(env, "map '%s' has to have BTF in order to use bpf_kptr_xchg\n", + map_ptr->name); + return -EINVAL; + } + if (!map_value_has_kptrs(map_ptr)) { + ret = PTR_ERR_OR_ZERO(map_ptr->kptr_off_tab); + if (ret == -E2BIG) + verbose(env, "map '%s' has more than %d kptr\n", map_ptr->name, + BPF_MAP_VALUE_OFF_MAX); + else if (ret == -EEXIST) + verbose(env, "map '%s' has repeating kptr BTF tags\n", map_ptr->name); + else + verbose(env, "map '%s' has no valid kptr\n", map_ptr->name); + return -EINVAL; + } + + meta->map_ptr = map_ptr; + kptr_off = reg->off + reg->var_off.value; + off_desc = bpf_map_kptr_off_contains(map_ptr, kptr_off); + if (!off_desc) { + verbose(env, "off=%d doesn't point to kptr\n", kptr_off); + return -EACCES; + } + if (off_desc->type != BPF_KPTR_REF) { + verbose(env, "off=%d kptr isn't referenced kptr\n", kptr_off); + return -EACCES; + } + meta->kptr_off_desc = off_desc; + return 0; } static bool arg_type_is_mem_size(enum bpf_arg_type type) @@ -5157,6 +5545,16 @@ static bool arg_type_is_int_ptr(enum bpf_arg_type type) type == ARG_PTR_TO_LONG; } +static bool arg_type_is_release(enum bpf_arg_type type) +{ + return type & OBJ_RELEASE; +} + +static bool arg_type_is_dynptr(enum bpf_arg_type type) +{ + return base_type(type) == ARG_PTR_TO_DYNPTR; +} + static int int_ptr_type_to_size(enum bpf_arg_type type) { if (type == ARG_PTR_TO_INT) @@ -5269,11 +5667,11 @@ static const struct bpf_reg_types func_ptr_types = { .types = { PTR_TO_FUNC } }; static const struct bpf_reg_types stack_ptr_types = { .types = { PTR_TO_STACK } }; static const struct bpf_reg_types const_str_ptr_types = { .types = { PTR_TO_MAP_VALUE } }; static const struct bpf_reg_types timer_types = { .types = { PTR_TO_MAP_VALUE } }; +static const struct bpf_reg_types kptr_types = { .types = { PTR_TO_MAP_VALUE } }; static const struct bpf_reg_types *compatible_reg_types[__BPF_ARG_TYPE_MAX] = { [ARG_PTR_TO_MAP_KEY] = &map_key_value_types, [ARG_PTR_TO_MAP_VALUE] = &map_key_value_types, - [ARG_PTR_TO_UNINIT_MAP_VALUE] = &map_key_value_types, [ARG_CONST_SIZE] = &scalar_types, [ARG_CONST_SIZE_OR_ZERO] = &scalar_types, [ARG_CONST_ALLOC_SIZE_OR_ZERO] = &scalar_types, @@ -5287,7 +5685,6 @@ static const struct bpf_reg_types *compatible_reg_types[__BPF_ARG_TYPE_MAX] = { [ARG_PTR_TO_BTF_ID] = &btf_ptr_types, [ARG_PTR_TO_SPIN_LOCK] = &spin_lock_types, [ARG_PTR_TO_MEM] = &mem_types, - [ARG_PTR_TO_UNINIT_MEM] = &mem_types, [ARG_PTR_TO_ALLOC_MEM] = &alloc_mem_types, [ARG_PTR_TO_INT] = &int_ptr_types, [ARG_PTR_TO_LONG] = &int_ptr_types, @@ -5296,11 +5693,14 @@ static const struct bpf_reg_types *compatible_reg_types[__BPF_ARG_TYPE_MAX] = { [ARG_PTR_TO_STACK] = &stack_ptr_types, [ARG_PTR_TO_CONST_STR] = &const_str_ptr_types, [ARG_PTR_TO_TIMER] = &timer_types, + [ARG_PTR_TO_KPTR] = &kptr_types, + [ARG_PTR_TO_DYNPTR] = &stack_ptr_types, }; static int check_reg_type(struct bpf_verifier_env *env, u32 regno, enum bpf_arg_type arg_type, - const u32 *arg_btf_id) + const u32 *arg_btf_id, + struct bpf_call_arg_meta *meta) { struct bpf_reg_state *regs = cur_regs(env), *reg = ®s[regno]; enum bpf_reg_type expected, type = reg->type; @@ -5345,6 +5745,13 @@ static int check_reg_type(struct bpf_verifier_env *env, u32 regno, found: if (reg->type == PTR_TO_BTF_ID) { + /* For bpf_sk_release, it needs to match against first member + * 'struct sock_common', hence make an exception for it. This + * allows bpf_sk_release to work for multiple socket types. + */ + bool strict_type_match = arg_type_is_release(arg_type) && + meta->func_id != BPF_FUNC_sk_release; + if (!arg_btf_id) { if (!compatible->btf_id) { verbose(env, "verifier internal error: missing arg compatible BTF ID\n"); @@ -5353,8 +5760,12 @@ found: arg_btf_id = compatible->btf_id; } - if (!btf_struct_ids_match(&env->log, reg->btf, reg->btf_id, reg->off, - btf_vmlinux, *arg_btf_id)) { + if (meta->func_id == BPF_FUNC_kptr_xchg) { + if (map_kptr_match_type(env, meta->kptr_off_desc, reg, regno)) + return -EACCES; + } else if (!btf_struct_ids_match(&env->log, reg->btf, reg->btf_id, reg->off, + 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)); @@ -5367,15 +5778,19 @@ found: int check_func_arg_reg_off(struct bpf_verifier_env *env, const struct bpf_reg_state *reg, int regno, - enum bpf_arg_type arg_type, - bool is_release_func) + enum bpf_arg_type arg_type) { - bool fixed_off_ok = false, release_reg; enum bpf_reg_type type = reg->type; + bool fixed_off_ok = false; switch ((u32)type) { - case SCALAR_VALUE: /* Pointer types where reg offset is explicitly allowed: */ + case PTR_TO_STACK: + if (arg_type_is_dynptr(arg_type) && reg->off % BPF_REG_SIZE) { + verbose(env, "cannot pass in dynptr at an offset\n"); + return -EINVAL; + } + fallthrough; case PTR_TO_PACKET: case PTR_TO_PACKET_META: case PTR_TO_MAP_KEY: @@ -5385,11 +5800,11 @@ int check_func_arg_reg_off(struct bpf_verifier_env *env, case PTR_TO_MEM | MEM_ALLOC: case PTR_TO_BUF: case PTR_TO_BUF | MEM_RDONLY: - case PTR_TO_STACK: + case SCALAR_VALUE: /* Some of the argument types nevertheless require a * zero register offset. */ - if (arg_type != ARG_PTR_TO_ALLOC_MEM) + if (base_type(arg_type) != ARG_PTR_TO_ALLOC_MEM) return 0; break; /* All the rest must be rejected, except PTR_TO_BTF_ID which allows @@ -5397,19 +5812,17 @@ int check_func_arg_reg_off(struct bpf_verifier_env *env, */ case PTR_TO_BTF_ID: /* When referenced PTR_TO_BTF_ID is passed to release function, - * it's fixed offset must be 0. We rely on the property that - * only one referenced register can be passed to BPF helpers and - * kfuncs. In the other cases, fixed offset can be non-zero. + * it's fixed offset must be 0. In the other cases, fixed offset + * can be non-zero. */ - release_reg = is_release_func && reg->ref_obj_id; - if (release_reg && reg->off) { + if (arg_type_is_release(arg_type) && reg->off) { verbose(env, "R%d must have zero offset when passed to release func\n", regno); return -EINVAL; } - /* For release_reg == true, fixed_off_ok must be false, but we - * already checked and rejected reg->off != 0 above, so set to - * true to allow fixed offset for all other cases. + /* For arg is release pointer, fixed_off_ok must be false, but + * we already checked and rejected reg->off != 0 above, so set + * to true to allow fixed offset for all other cases. */ fixed_off_ok = true; break; @@ -5419,6 +5832,14 @@ int check_func_arg_reg_off(struct bpf_verifier_env *env, return __check_ptr_off_reg(env, reg, regno, fixed_off_ok); } +static u32 stack_slot_get_id(struct bpf_verifier_env *env, struct bpf_reg_state *reg) +{ + struct bpf_func_state *state = func(env, reg); + int spi = get_spi(reg->off); + + return state->stack[spi].spilled_ptr.id; +} + static int check_func_arg(struct bpf_verifier_env *env, u32 arg, struct bpf_call_arg_meta *meta, const struct bpf_func_proto *fn) @@ -5451,8 +5872,7 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 arg, return -EACCES; } - if (base_type(arg_type) == ARG_PTR_TO_MAP_VALUE || - base_type(arg_type) == ARG_PTR_TO_UNINIT_MAP_VALUE) { + if (base_type(arg_type) == ARG_PTR_TO_MAP_VALUE) { err = resolve_map_arg_type(env, meta, &arg_type); if (err) return err; @@ -5464,18 +5884,37 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 arg, */ goto skip_type_check; - err = check_reg_type(env, regno, arg_type, fn->arg_btf_id[arg]); + err = check_reg_type(env, regno, arg_type, fn->arg_btf_id[arg], meta); if (err) return err; - err = check_func_arg_reg_off(env, reg, regno, arg_type, is_release_function(meta->func_id)); + err = check_func_arg_reg_off(env, reg, regno, arg_type); if (err) return err; skip_type_check: - /* check_func_arg_reg_off relies on only one referenced register being - * allowed for BPF helpers. - */ + if (arg_type_is_release(arg_type)) { + if (arg_type_is_dynptr(arg_type)) { + struct bpf_func_state *state = func(env, reg); + int spi = get_spi(reg->off); + + if (!is_spi_bounds_valid(state, spi, BPF_DYNPTR_NR_SLOTS) || + !state->stack[spi].spilled_ptr.id) { + verbose(env, "arg %d is an unacquired reference\n", regno); + return -EINVAL; + } + } else if (!reg->ref_obj_id && !register_is_null(reg)) { + verbose(env, "R%d must be referenced when passed to release function\n", + regno); + return -EINVAL; + } + if (meta->release_regno) { + verbose(env, "verifier internal error: more than one release argument\n"); + return -EFAULT; + } + meta->release_regno = regno; + } + if (reg->ref_obj_id) { if (meta->ref_obj_id) { verbose(env, "verifier internal error: more than one arg with ref_obj_id R%d %u %u\n", @@ -5528,8 +5967,7 @@ skip_type_check: err = check_helper_mem_access(env, regno, meta->map_ptr->key_size, false, NULL); - } else if (base_type(arg_type) == ARG_PTR_TO_MAP_VALUE || - base_type(arg_type) == ARG_PTR_TO_UNINIT_MAP_VALUE) { + } else if (base_type(arg_type) == ARG_PTR_TO_MAP_VALUE) { if (type_may_be_null(arg_type) && register_is_null(reg)) return 0; @@ -5541,7 +5979,7 @@ skip_type_check: verbose(env, "invalid map_ptr to access map->value\n"); return -EACCES; } - meta->raw_mode = (arg_type == ARG_PTR_TO_UNINIT_MAP_VALUE); + meta->raw_mode = arg_type & MEM_UNINIT; err = check_helper_mem_access(env, regno, meta->map_ptr->value_size, false, meta); @@ -5568,15 +6006,49 @@ skip_type_check: return -EACCES; } else if (arg_type == ARG_PTR_TO_FUNC) { meta->subprogno = reg->subprogno; - } else if (arg_type_is_mem_ptr(arg_type)) { + } else if (base_type(arg_type) == ARG_PTR_TO_MEM) { /* The access to this pointer is only checked when we hit the * next is_mem_size argument below. */ - meta->raw_mode = (arg_type == ARG_PTR_TO_UNINIT_MEM); + meta->raw_mode = arg_type & MEM_UNINIT; } else if (arg_type_is_mem_size(arg_type)) { bool zero_size_allowed = (arg_type == ARG_CONST_SIZE_OR_ZERO); err = check_mem_size_reg(env, reg, regno, zero_size_allowed, meta); + } else if (arg_type_is_dynptr(arg_type)) { + if (arg_type & MEM_UNINIT) { + if (!is_dynptr_reg_valid_uninit(env, reg)) { + verbose(env, "Dynptr has to be an uninitialized dynptr\n"); + return -EINVAL; + } + + /* We only support one dynptr being uninitialized at the moment, + * which is sufficient for the helper functions we have right now. + */ + if (meta->uninit_dynptr_regno) { + verbose(env, "verifier internal error: multiple uninitialized dynptr args\n"); + return -EFAULT; + } + + meta->uninit_dynptr_regno = regno; + } else if (!is_dynptr_reg_valid_init(env, reg, arg_type)) { + const char *err_extra = ""; + + switch (arg_type & DYNPTR_TYPE_FLAG_MASK) { + case DYNPTR_TYPE_LOCAL: + err_extra = "local "; + break; + case DYNPTR_TYPE_RINGBUF: + err_extra = "ringbuf "; + break; + default: + break; + } + + verbose(env, "Expected an initialized %sdynptr as arg #%d\n", + err_extra, arg + 1); + return -EINVAL; + } } else if (arg_type_is_alloc_size(arg_type)) { if (!tnum_is_const(reg->var_off)) { verbose(env, "R%d is not a known constant'\n", @@ -5613,7 +6085,8 @@ skip_type_check: } err = check_map_access(env, regno, reg->off, - map->value_size - reg->off, false); + map->value_size - reg->off, false, + ACCESS_HELPER); if (err) return err; @@ -5629,6 +6102,9 @@ skip_type_check: verbose(env, "string is not zero-terminated\n"); return -EINVAL; } + } else if (arg_type == ARG_PTR_TO_KPTR) { + if (process_kptr_func(env, regno, meta)) + return -EACCES; } return err; @@ -5694,7 +6170,10 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env, case BPF_MAP_TYPE_RINGBUF: if (func_id != BPF_FUNC_ringbuf_output && func_id != BPF_FUNC_ringbuf_reserve && - func_id != BPF_FUNC_ringbuf_query) + func_id != BPF_FUNC_ringbuf_query && + func_id != BPF_FUNC_ringbuf_reserve_dynptr && + func_id != BPF_FUNC_ringbuf_submit_dynptr && + func_id != BPF_FUNC_ringbuf_discard_dynptr) goto error; break; case BPF_MAP_TYPE_STACK_TRACE: @@ -5810,6 +6289,9 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env, case BPF_FUNC_ringbuf_output: case BPF_FUNC_ringbuf_reserve: case BPF_FUNC_ringbuf_query: + case BPF_FUNC_ringbuf_reserve_dynptr: + case BPF_FUNC_ringbuf_submit_dynptr: + case BPF_FUNC_ringbuf_discard_dynptr: if (map->map_type != BPF_MAP_TYPE_RINGBUF) goto error; break; @@ -5864,6 +6346,12 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env, map->map_type != BPF_MAP_TYPE_BLOOM_FILTER) goto error; break; + case BPF_FUNC_map_lookup_percpu_elem: + if (map->map_type != BPF_MAP_TYPE_PERCPU_ARRAY && + map->map_type != BPF_MAP_TYPE_PERCPU_HASH && + map->map_type != BPF_MAP_TYPE_LRU_PERCPU_HASH) + goto error; + break; case BPF_FUNC_sk_storage_get: case BPF_FUNC_sk_storage_delete: if (map->map_type != BPF_MAP_TYPE_SK_STORAGE) @@ -5915,10 +6403,8 @@ static bool check_raw_mode_ok(const struct bpf_func_proto *fn) static bool check_args_pair_invalid(enum bpf_arg_type arg_curr, enum bpf_arg_type arg_next) { - return (arg_type_is_mem_ptr(arg_curr) && - !arg_type_is_mem_size(arg_next)) || - (!arg_type_is_mem_ptr(arg_curr) && - arg_type_is_mem_size(arg_next)); + return (base_type(arg_curr) == ARG_PTR_TO_MEM) != + arg_type_is_mem_size(arg_next); } static bool check_arg_pair_ok(const struct bpf_func_proto *fn) @@ -5929,7 +6415,7 @@ static bool check_arg_pair_ok(const struct bpf_func_proto *fn) * helper function specification. */ if (arg_type_is_mem_size(fn->arg1_type) || - arg_type_is_mem_ptr(fn->arg5_type) || + base_type(fn->arg5_type) == ARG_PTR_TO_MEM || check_args_pair_invalid(fn->arg1_type, fn->arg2_type) || check_args_pair_invalid(fn->arg2_type, fn->arg3_type) || check_args_pair_invalid(fn->arg3_type, fn->arg4_type) || @@ -5971,17 +6457,18 @@ static bool check_btf_id_ok(const struct bpf_func_proto *fn) int i; for (i = 0; i < ARRAY_SIZE(fn->arg_type); i++) { - if (fn->arg_type[i] == ARG_PTR_TO_BTF_ID && !fn->arg_btf_id[i]) + if (base_type(fn->arg_type[i]) == ARG_PTR_TO_BTF_ID && !fn->arg_btf_id[i]) return false; - if (fn->arg_type[i] != ARG_PTR_TO_BTF_ID && fn->arg_btf_id[i]) + if (base_type(fn->arg_type[i]) != ARG_PTR_TO_BTF_ID && fn->arg_btf_id[i]) return false; } return true; } -static int check_func_proto(const struct bpf_func_proto *fn, int func_id) +static int check_func_proto(const struct bpf_func_proto *fn, int func_id, + struct bpf_call_arg_meta *meta) { return check_raw_mode_ok(fn) && check_arg_pair_ok(fn) && @@ -6476,7 +6963,8 @@ record_func_map(struct bpf_verifier_env *env, struct bpf_call_arg_meta *meta, func_id != BPF_FUNC_map_pop_elem && func_id != BPF_FUNC_map_peek_elem && func_id != BPF_FUNC_for_each_map_elem && - func_id != BPF_FUNC_redirect_map) + func_id != BPF_FUNC_redirect_map && + func_id != BPF_FUNC_map_lookup_percpu_elem) return 0; if (map == NULL) { @@ -6665,7 +7153,7 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn memset(&meta, 0, sizeof(meta)); meta.pkt_access = fn->pkt_access; - err = check_func_proto(fn, func_id); + err = check_func_proto(fn, func_id, &meta); if (err) { verbose(env, "kernel subsystem misconfigured func %s#%d\n", func_id_name(func_id), func_id); @@ -6698,8 +7186,35 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn return err; } - if (is_release_function(func_id)) { - err = release_reference(env, meta.ref_obj_id); + regs = cur_regs(env); + + if (meta.uninit_dynptr_regno) { + /* we write BPF_DW bits (8 bytes) at a time */ + for (i = 0; i < BPF_DYNPTR_SIZE; i += 8) { + err = check_mem_access(env, insn_idx, meta.uninit_dynptr_regno, + i, BPF_DW, BPF_WRITE, -1, false); + if (err) + return err; + } + + err = mark_stack_slots_dynptr(env, ®s[meta.uninit_dynptr_regno], + fn->arg_type[meta.uninit_dynptr_regno - BPF_REG_1], + insn_idx); + if (err) + return err; + } + + if (meta.release_regno) { + err = -EINVAL; + if (arg_type_is_dynptr(fn->arg_type[meta.release_regno - BPF_REG_1])) + err = unmark_stack_slots_dynptr(env, ®s[meta.release_regno]); + else if (meta.ref_obj_id) + err = release_reference(env, meta.ref_obj_id); + /* meta.ref_obj_id can only be 0 if register that is meant to be + * released is NULL, which must be > R0. + */ + else if (register_is_null(®s[meta.release_regno])) + err = 0; if (err) { verbose(env, "func %s#%d reference has not been acquired before\n", func_id_name(func_id), func_id); @@ -6707,8 +7222,6 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn } } - regs = cur_regs(env); - switch (func_id) { case BPF_FUNC_tail_call: err = check_reference_leak(env); @@ -6745,6 +7258,12 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn err = __check_func_call(env, insn, insn_idx_p, meta.subprogno, set_loop_callback_state); break; + case BPF_FUNC_dynptr_from_mem: + if (regs[BPF_REG_1].type != PTR_TO_MAP_VALUE) { + verbose(env, "Unsupported reg type %s for bpf_dynptr_from_mem data\n", + reg_type_str(env, regs[BPF_REG_1].type)); + return -EACCES; + } } if (err) @@ -6832,21 +7351,25 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn regs[BPF_REG_0].btf_id = meta.ret_btf_id; } } else if (base_type(ret_type) == RET_PTR_TO_BTF_ID) { + struct btf *ret_btf; int ret_btf_id; mark_reg_known_zero(env, regs, BPF_REG_0); regs[BPF_REG_0].type = PTR_TO_BTF_ID | ret_flag; - ret_btf_id = *fn->ret_btf_id; + if (func_id == BPF_FUNC_kptr_xchg) { + ret_btf = meta.kptr_off_desc->kptr.btf; + ret_btf_id = meta.kptr_off_desc->kptr.btf_id; + } else { + ret_btf = btf_vmlinux; + ret_btf_id = *fn->ret_btf_id; + } if (ret_btf_id == 0) { verbose(env, "invalid return type %u of func %s#%d\n", base_type(ret_type), func_id_name(func_id), func_id); return -EINVAL; } - /* current BPF helper definitions are only coming from - * built-in code with type IDs from vmlinux BTF - */ - regs[BPF_REG_0].btf = btf_vmlinux; + regs[BPF_REG_0].btf = ret_btf; regs[BPF_REG_0].btf_id = ret_btf_id; } else { verbose(env, "unknown return type %u of func %s#%d\n", @@ -6869,6 +7392,21 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn regs[BPF_REG_0].id = id; /* For release_reference() */ regs[BPF_REG_0].ref_obj_id = id; + } else if (func_id == BPF_FUNC_dynptr_data) { + int dynptr_id = 0, i; + + /* Find the id of the dynptr we're acquiring a reference to */ + for (i = 0; i < MAX_BPF_FUNC_REG_ARGS; i++) { + if (arg_type_is_dynptr(fn->arg_type[i])) { + if (dynptr_id) { + verbose(env, "verifier internal error: multiple dynptr args in func\n"); + return -EFAULT; + } + dynptr_id = stack_slot_get_id(env, ®s[BPF_REG_1 + i]); + } + } + /* For release_reference() */ + regs[BPF_REG_0].ref_obj_id = dynptr_id; } do_refine_retval_range(regs, fn->ret_type, func_id, &meta); @@ -6951,7 +7489,7 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn, if (!insn->imm) return 0; - desc_btf = find_kfunc_desc_btf(env, insn->imm, insn->off); + desc_btf = find_kfunc_desc_btf(env, insn->off); if (IS_ERR(desc_btf)) return PTR_ERR(desc_btf); @@ -7433,7 +7971,7 @@ static int sanitize_check_bounds(struct bpf_verifier_env *env, return -EACCES; break; case PTR_TO_MAP_VALUE: - if (check_map_access(env, dst, dst_reg->off, 1, false)) { + if (check_map_access(env, dst, dst_reg->off, 1, false, ACCESS_HELPER)) { verbose(env, "R%d pointer arithmetic of map value goes out of range, " "prohibited for !root\n", dst); return -EACCES; @@ -12822,7 +13360,7 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env) if (!ctx_access) continue; - switch (env->insn_aux_data[i + delta].ptr_type) { + switch ((int)env->insn_aux_data[i + delta].ptr_type) { case PTR_TO_CTX: if (!ops->convert_ctx_access) continue; @@ -12839,6 +13377,7 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env) convert_ctx_access = bpf_xdp_sock_convert_ctx_access; break; case PTR_TO_BTF_ID: + case PTR_TO_BTF_ID | PTR_UNTRUSTED: if (type == BPF_READ) { insn->code = BPF_LDX | BPF_PROBE_MEM | BPF_SIZE((insn)->code); @@ -13524,7 +14063,8 @@ static int do_misc_fixups(struct bpf_verifier_env *env) insn->imm == BPF_FUNC_map_pop_elem || insn->imm == BPF_FUNC_map_peek_elem || insn->imm == BPF_FUNC_redirect_map || - insn->imm == BPF_FUNC_for_each_map_elem)) { + insn->imm == BPF_FUNC_for_each_map_elem || + insn->imm == BPF_FUNC_map_lookup_percpu_elem)) { aux = &env->insn_aux_data[i + delta]; if (bpf_map_ptr_poisoned(aux)) goto patch_call_imm; @@ -13573,6 +14113,8 @@ static int do_misc_fixups(struct bpf_verifier_env *env) bpf_callback_t callback_fn, void *callback_ctx, u64 flags))NULL)); + BUILD_BUG_ON(!__same_type(ops->map_lookup_percpu_elem, + (void *(*)(struct bpf_map *map, void *key, u32 cpu))NULL)); patch_map_ops_generic: switch (insn->imm) { @@ -13600,6 +14142,9 @@ patch_map_ops_generic: case BPF_FUNC_for_each_map_elem: insn->imm = BPF_CALL_IMM(ops->map_for_each_callback); continue; + case BPF_FUNC_map_lookup_percpu_elem: + insn->imm = BPF_CALL_IMM(ops->map_lookup_percpu_elem); + continue; } goto patch_call_imm; diff --git a/kernel/kallsyms.c b/kernel/kallsyms.c index 79f2eb617a62..fbdf8d3279ac 100644 --- a/kernel/kallsyms.c +++ b/kernel/kallsyms.c @@ -29,6 +29,7 @@ #include <linux/compiler.h> #include <linux/module.h> #include <linux/kernel.h> +#include <linux/bsearch.h> /* * These will be re-linked against their real values @@ -228,7 +229,6 @@ unsigned long kallsyms_lookup_name(const char *name) return module_kallsyms_lookup_name(name); } -#ifdef CONFIG_LIVEPATCH /* * Iterate over all symbols in vmlinux. For symbols from modules use * module_kallsyms_on_each_symbol instead. @@ -251,7 +251,6 @@ int kallsyms_on_each_symbol(int (*fn)(void *, const char *, struct module *, } return 0; } -#endif /* CONFIG_LIVEPATCH */ static unsigned long get_symbol_pos(unsigned long addr, unsigned long *symbolsize, diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 5b7b1a82ae6a..82bcf5e3009f 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -62,7 +62,6 @@ #include <linux/binfmts.h> #include <linux/sched/sysctl.h> #include <linux/kexec.h> -#include <linux/bpf.h> #include <linux/mount.h> #include <linux/userfaultfd_k.h> #include <linux/latencytop.h> @@ -148,66 +147,6 @@ static const int max_extfrag_threshold = 1000; #endif /* CONFIG_SYSCTL */ -#if defined(CONFIG_BPF_SYSCALL) && defined(CONFIG_SYSCTL) -static int bpf_stats_handler(struct ctl_table *table, int write, - void *buffer, size_t *lenp, loff_t *ppos) -{ - struct static_key *key = (struct static_key *)table->data; - static int saved_val; - int val, ret; - struct ctl_table tmp = { - .data = &val, - .maxlen = sizeof(val), - .mode = table->mode, - .extra1 = SYSCTL_ZERO, - .extra2 = SYSCTL_ONE, - }; - - if (write && !capable(CAP_SYS_ADMIN)) - return -EPERM; - - mutex_lock(&bpf_stats_enabled_mutex); - val = saved_val; - ret = proc_dointvec_minmax(&tmp, write, buffer, lenp, ppos); - if (write && !ret && val != saved_val) { - if (val) - static_key_slow_inc(key); - else - static_key_slow_dec(key); - saved_val = val; - } - mutex_unlock(&bpf_stats_enabled_mutex); - return ret; -} - -void __weak unpriv_ebpf_notify(int new_state) -{ -} - -static int bpf_unpriv_handler(struct ctl_table *table, int write, - void *buffer, size_t *lenp, loff_t *ppos) -{ - int ret, unpriv_enable = *(int *)table->data; - bool locked_state = unpriv_enable == 1; - struct ctl_table tmp = *table; - - if (write && !capable(CAP_SYS_ADMIN)) - return -EPERM; - - tmp.data = &unpriv_enable; - ret = proc_dointvec_minmax(&tmp, write, buffer, lenp, ppos); - if (write && !ret) { - if (locked_state && unpriv_enable != 1) - return -EPERM; - *(int *)table->data = unpriv_enable; - } - - unpriv_ebpf_notify(unpriv_enable); - - return ret; -} -#endif /* CONFIG_BPF_SYSCALL && CONFIG_SYSCTL */ - /* * /proc/sys support */ @@ -2288,24 +2227,6 @@ static struct ctl_table kern_table[] = { .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, -#ifdef CONFIG_BPF_SYSCALL - { - .procname = "unprivileged_bpf_disabled", - .data = &sysctl_unprivileged_bpf_disabled, - .maxlen = sizeof(sysctl_unprivileged_bpf_disabled), - .mode = 0644, - .proc_handler = bpf_unpriv_handler, - .extra1 = SYSCTL_ZERO, - .extra2 = SYSCTL_TWO, - }, - { - .procname = "bpf_stats_enabled", - .data = &bpf_stats_enabled_key.key, - .maxlen = sizeof(bpf_stats_enabled_key), - .mode = 0644, - .proc_handler = bpf_stats_handler, - }, -#endif #if defined(CONFIG_TREE_RCU) { .procname = "panic_on_rcu_stall", diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index d8553f46caa2..10b157a6d73e 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -129,7 +129,10 @@ unsigned int trace_call_bpf(struct trace_event_call *call, void *ctx) * out of events when it was updated in between this and the * rcu_dereference() which is accepted risk. */ - ret = BPF_PROG_RUN_ARRAY(call->prog_array, ctx, bpf_prog_run); + rcu_read_lock(); + ret = bpf_prog_run_array(rcu_dereference(call->prog_array), + ctx, bpf_prog_run); + rcu_read_unlock(); out: __this_cpu_dec(bpf_prog_active); @@ -1088,6 +1091,21 @@ static const struct bpf_func_proto bpf_get_attach_cookie_proto_pe = { .arg1_type = ARG_PTR_TO_CTX, }; +BPF_CALL_1(bpf_get_attach_cookie_tracing, void *, ctx) +{ + struct bpf_trace_run_ctx *run_ctx; + + run_ctx = container_of(current->bpf_ctx, struct bpf_trace_run_ctx, run_ctx); + return run_ctx->bpf_cookie; +} + +static const struct bpf_func_proto bpf_get_attach_cookie_proto_tracing = { + .func = bpf_get_attach_cookie_tracing, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, +}; + BPF_CALL_3(bpf_get_branch_snapshot, void *, buf, u32, size, u64, flags) { #ifndef CONFIG_X86 @@ -1179,6 +1197,8 @@ bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_map_pop_elem_proto; case BPF_FUNC_map_peek_elem: return &bpf_map_peek_elem_proto; + case BPF_FUNC_map_lookup_percpu_elem: + return &bpf_map_lookup_percpu_elem_proto; case BPF_FUNC_ktime_get_ns: return &bpf_ktime_get_ns_proto; case BPF_FUNC_ktime_get_boot_ns: @@ -1685,6 +1705,8 @@ tracing_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_skc_to_udp6_sock_proto; case BPF_FUNC_skc_to_unix_sock: return &bpf_skc_to_unix_sock_proto; + case BPF_FUNC_skc_to_mptcp_sock: + return &bpf_skc_to_mptcp_sock_proto; case BPF_FUNC_sk_storage_get: return &bpf_sk_storage_get_tracing_proto; case BPF_FUNC_sk_storage_delete: @@ -1716,6 +1738,8 @@ tracing_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return bpf_prog_has_trampoline(prog) ? &bpf_get_func_ret_proto : NULL; case BPF_FUNC_get_func_arg_cnt: return bpf_prog_has_trampoline(prog) ? &bpf_get_func_arg_cnt_proto : NULL; + case BPF_FUNC_get_attach_cookie: + return bpf_prog_has_trampoline(prog) ? &bpf_get_attach_cookie_proto_tracing : NULL; default: fn = raw_tp_prog_func_proto(func_id, prog); if (!fn && prog->expected_attach_type == BPF_TRACE_ITER) @@ -2226,6 +2250,59 @@ struct bpf_kprobe_multi_run_ctx { unsigned long entry_ip; }; +struct user_syms { + const char **syms; + char *buf; +}; + +static int copy_user_syms(struct user_syms *us, unsigned long __user *usyms, u32 cnt) +{ + unsigned long __user usymbol; + const char **syms = NULL; + char *buf = NULL, *p; + int err = -ENOMEM; + unsigned int i; + + syms = kvmalloc(cnt * sizeof(*syms), GFP_KERNEL); + if (!syms) + goto error; + + buf = kvmalloc(cnt * KSYM_NAME_LEN, GFP_KERNEL); + if (!buf) + goto error; + + for (p = buf, i = 0; i < cnt; i++) { + if (__get_user(usymbol, usyms + i)) { + err = -EFAULT; + goto error; + } + err = strncpy_from_user(p, (const char __user *) usymbol, KSYM_NAME_LEN); + if (err == KSYM_NAME_LEN) + err = -E2BIG; + if (err < 0) + goto error; + syms[i] = p; + p += err + 1; + } + + us->syms = syms; + us->buf = buf; + return 0; + +error: + if (err) { + kvfree(syms); + kvfree(buf); + } + return err; +} + +static void free_user_syms(struct user_syms *us) +{ + kvfree(us->syms); + kvfree(us->buf); +} + static void bpf_kprobe_multi_link_release(struct bpf_link *link) { struct bpf_kprobe_multi_link *kmulti_link; @@ -2254,15 +2331,13 @@ static void bpf_kprobe_multi_cookie_swap(void *a, void *b, int size, const void const struct bpf_kprobe_multi_link *link = priv; unsigned long *addr_a = a, *addr_b = b; u64 *cookie_a, *cookie_b; - unsigned long tmp1; - u64 tmp2; cookie_a = link->cookies + (addr_a - link->addrs); cookie_b = link->cookies + (addr_b - link->addrs); /* swap addr_a/addr_b and cookie_a/cookie_b values */ - tmp1 = *addr_a; *addr_a = *addr_b; *addr_b = tmp1; - tmp2 = *cookie_a; *cookie_a = *cookie_b; *cookie_b = tmp2; + swap(*addr_a, *addr_b); + swap(*cookie_a, *cookie_b); } static int __bpf_kprobe_multi_cookie_cmp(const void *a, const void *b) @@ -2348,53 +2423,12 @@ kprobe_multi_link_handler(struct fprobe *fp, unsigned long entry_ip, kprobe_multi_link_prog_run(link, entry_ip, regs); } -static int -kprobe_multi_resolve_syms(const void __user *usyms, u32 cnt, - unsigned long *addrs) +static int symbols_cmp(const void *a, const void *b) { - unsigned long addr, size; - const char __user **syms; - int err = -ENOMEM; - unsigned int i; - char *func; - - size = cnt * sizeof(*syms); - syms = kvzalloc(size, GFP_KERNEL); - if (!syms) - return -ENOMEM; - - func = kmalloc(KSYM_NAME_LEN, GFP_KERNEL); - if (!func) - goto error; - - if (copy_from_user(syms, usyms, size)) { - err = -EFAULT; - goto error; - } - - for (i = 0; i < cnt; i++) { - err = strncpy_from_user(func, syms[i], KSYM_NAME_LEN); - if (err == KSYM_NAME_LEN) - err = -E2BIG; - if (err < 0) - goto error; - err = -EINVAL; - addr = kallsyms_lookup_name(func); - if (!addr) - goto error; - if (!kallsyms_lookup_size_offset(addr, &size, NULL)) - goto error; - addr = ftrace_location_range(addr, addr + size - 1); - if (!addr) - goto error; - addrs[i] = addr; - } + const char **str_a = (const char **) a; + const char **str_b = (const char **) b; - err = 0; -error: - kvfree(syms); - kfree(func); - return err; + return strcmp(*str_a, *str_b); } int bpf_kprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *prog) @@ -2440,7 +2474,15 @@ int bpf_kprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *pr goto error; } } else { - err = kprobe_multi_resolve_syms(usyms, cnt, addrs); + struct user_syms us; + + err = copy_user_syms(&us, usyms, cnt); + if (err) + goto error; + + sort(us.syms, cnt, sizeof(*us.syms), symbols_cmp, NULL); + err = ftrace_lookup_symbols(us.syms, cnt, addrs); + free_user_syms(&us); if (err) goto error; } diff --git a/kernel/trace/fprobe.c b/kernel/trace/fprobe.c index 89d9f994ebb0..aac63ca9c3d1 100644 --- a/kernel/trace/fprobe.c +++ b/kernel/trace/fprobe.c @@ -85,39 +85,31 @@ static void fprobe_exit_handler(struct rethook_node *rh, void *data, } NOKPROBE_SYMBOL(fprobe_exit_handler); +static int symbols_cmp(const void *a, const void *b) +{ + const char **str_a = (const char **) a; + const char **str_b = (const char **) b; + + return strcmp(*str_a, *str_b); +} + /* Convert ftrace location address from symbols */ static unsigned long *get_ftrace_locations(const char **syms, int num) { - unsigned long addr, size; unsigned long *addrs; - int i; /* Convert symbols to symbol address */ addrs = kcalloc(num, sizeof(*addrs), GFP_KERNEL); if (!addrs) return ERR_PTR(-ENOMEM); - for (i = 0; i < num; i++) { - addr = kallsyms_lookup_name(syms[i]); - if (!addr) /* Maybe wrong symbol */ - goto error; - - /* Convert symbol address to ftrace location. */ - if (!kallsyms_lookup_size_offset(addr, &size, NULL) || !size) - goto error; + /* ftrace_lookup_symbols expects sorted symbols */ + sort(syms, num, sizeof(*syms), symbols_cmp, NULL); - addr = ftrace_location_range(addr, addr + size - 1); - if (!addr) /* No dynamic ftrace there. */ - goto error; + if (!ftrace_lookup_symbols(syms, num, addrs)) + return addrs; - addrs[i] = addr; - } - - return addrs; - -error: kfree(addrs); - return ERR_PTR(-ENOENT); } diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index af899b058c8d..674add0aafb3 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -7964,3 +7964,65 @@ ftrace_enable_sysctl(struct ctl_table *table, int write, mutex_unlock(&ftrace_lock); return ret; } + +static int symbols_cmp(const void *a, const void *b) +{ + const char **str_a = (const char **) a; + const char **str_b = (const char **) b; + + return strcmp(*str_a, *str_b); +} + +struct kallsyms_data { + unsigned long *addrs; + const char **syms; + size_t cnt; + size_t found; +}; + +static int kallsyms_callback(void *data, const char *name, + struct module *mod, unsigned long addr) +{ + struct kallsyms_data *args = data; + + if (!bsearch(&name, args->syms, args->cnt, sizeof(*args->syms), symbols_cmp)) + return 0; + + addr = ftrace_location(addr); + if (!addr) + return 0; + + args->addrs[args->found++] = addr; + return args->found == args->cnt ? 1 : 0; +} + +/** + * ftrace_lookup_symbols - Lookup addresses for array of symbols + * + * @sorted_syms: array of symbols pointers symbols to resolve, + * must be alphabetically sorted + * @cnt: number of symbols/addresses in @syms/@addrs arrays + * @addrs: array for storing resulting addresses + * + * This function looks up addresses for array of symbols provided in + * @syms array (must be alphabetically sorted) and stores them in + * @addrs array, which needs to be big enough to store at least @cnt + * addresses. + * + * This function returns 0 if all provided symbols are found, + * -ESRCH otherwise. + */ +int ftrace_lookup_symbols(const char **sorted_syms, size_t cnt, unsigned long *addrs) +{ + struct kallsyms_data args; + int err; + + args.addrs = addrs; + args.syms = sorted_syms; + args.cnt = cnt; + args.found = 0; + err = kallsyms_on_each_symbol(kallsyms_callback, &args); + if (err < 0) + return err; + return args.found == args.cnt ? 0 : -ESRCH; +} |