summaryrefslogtreecommitdiff
path: root/kernel
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2024-01-19 04:33:50 +0300
committerLinus Torvalds <torvalds@linux-foundation.org>2024-01-19 04:33:50 +0300
commit736b5545d39ca59d4332a60e56cc8a1a5e264a8e (patch)
tree3200528110fab00e0f0d3a311b6e3ad2fcd86edd /kernel
parented8d84530ab0a3b7b370e8b28f12179314dcfcc3 (diff)
parent925781a471d8156011e8f8c1baf61bbe020dac55 (diff)
downloadlinux-736b5545d39ca59d4332a60e56cc8a1a5e264a8e.tar.xz
Merge tag 'net-6.8-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net
Pull networking fixes from Jakub Kicinski: "Including fixes from bpf and netfilter. Previous releases - regressions: - Revert "net: rtnetlink: Enslave device before bringing it up", breaks the case inverse to the one it was trying to fix - net: dsa: fix oob access in DSA's netdevice event handler dereference netdev_priv() before check its a DSA port - sched: track device in tcf_block_get/put_ext() only for clsact binder types - net: tls, fix WARNING in __sk_msg_free when record becomes full during splice and MORE hint set - sfp-bus: fix SFP mode detect from bitrate - drv: stmmac: prevent DSA tags from breaking COE Previous releases - always broken: - bpf: fix no forward progress in in bpf_iter_udp if output buffer is too small - bpf: reject variable offset alu on registers with a type of PTR_TO_FLOW_KEYS to prevent oob access - netfilter: tighten input validation - net: add more sanity check in virtio_net_hdr_to_skb() - rxrpc: fix use of Don't Fragment flag on RESPONSE packets, avoid infinite loop - amt: do not use the portion of skb->cb area which may get clobbered - mptcp: improve validation of the MPTCPOPT_MP_JOIN MCTCP option Misc: - spring cleanup of inactive maintainers" * tag 'net-6.8-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (88 commits) i40e: Include types.h to some headers ipv6: mcast: fix data-race in ipv6_mc_down / mld_ifc_work selftests: mlxsw: qos_pfc: Adjust the test to support 8 lanes selftests: mlxsw: qos_pfc: Remove wrong description mlxsw: spectrum_router: Register netdevice notifier before nexthop mlxsw: spectrum_acl_tcam: Fix stack corruption mlxsw: spectrum_acl_tcam: Fix NULL pointer dereference in error path mlxsw: spectrum_acl_erp: Fix error flow of pool allocation failure ethtool: netlink: Add missing ethnl_ops_begin/complete selftests: bonding: Add more missing config options selftests: netdevsim: add a config file libbpf: warn on unexpected __arg_ctx type when rewriting BTF selftests/bpf: add tests confirming type logic in kernel for __arg_ctx bpf: enforce types for __arg_ctx-tagged arguments in global subprogs bpf: extract bpf_ctx_convert_map logic and make it more reusable libbpf: feature-detect arg:ctx tag support in kernel ipvs: avoid stat macros calls from preemptible context netfilter: nf_tables: reject NFT_SET_CONCAT with not field length description netfilter: nf_tables: skip dead set elements in netlink dump netfilter: nf_tables: do not allow mismatch field size and set key length ...
Diffstat (limited to 'kernel')
-rw-r--r--kernel/bpf/btf.c231
-rw-r--r--kernel/bpf/verifier.c4
2 files changed, 209 insertions, 26 deletions
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index 51e8b4bee0c8..596471189176 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -5615,21 +5615,46 @@ static u8 bpf_ctx_convert_map[] = {
#undef BPF_MAP_TYPE
#undef BPF_LINK_TYPE
-const struct btf_member *
-btf_get_prog_ctx_type(struct bpf_verifier_log *log, const struct btf *btf,
- const struct btf_type *t, enum bpf_prog_type prog_type,
- int arg)
+static const struct btf_type *find_canonical_prog_ctx_type(enum bpf_prog_type prog_type)
{
const struct btf_type *conv_struct;
- const struct btf_type *ctx_struct;
const struct btf_member *ctx_type;
- const char *tname, *ctx_tname;
conv_struct = bpf_ctx_convert.t;
- if (!conv_struct) {
- bpf_log(log, "btf_vmlinux is malformed\n");
+ if (!conv_struct)
return NULL;
- }
+ /* prog_type is valid bpf program type. No need for bounds check. */
+ ctx_type = btf_type_member(conv_struct) + bpf_ctx_convert_map[prog_type] * 2;
+ /* ctx_type is a pointer to prog_ctx_type in vmlinux.
+ * Like 'struct __sk_buff'
+ */
+ return btf_type_by_id(btf_vmlinux, ctx_type->type);
+}
+
+static int find_kern_ctx_type_id(enum bpf_prog_type prog_type)
+{
+ const struct btf_type *conv_struct;
+ const struct btf_member *ctx_type;
+
+ conv_struct = bpf_ctx_convert.t;
+ if (!conv_struct)
+ return -EFAULT;
+ /* prog_type is valid bpf program type. No need for bounds check. */
+ ctx_type = btf_type_member(conv_struct) + bpf_ctx_convert_map[prog_type] * 2 + 1;
+ /* ctx_type is a pointer to prog_ctx_type in vmlinux.
+ * Like 'struct sk_buff'
+ */
+ return ctx_type->type;
+}
+
+const struct btf_type *
+btf_get_prog_ctx_type(struct bpf_verifier_log *log, const struct btf *btf,
+ const struct btf_type *t, enum bpf_prog_type prog_type,
+ int arg)
+{
+ const struct btf_type *ctx_type;
+ const char *tname, *ctx_tname;
+
t = btf_type_by_id(btf, t->type);
while (btf_type_is_modifier(t))
t = btf_type_by_id(btf, t->type);
@@ -5646,17 +5671,15 @@ btf_get_prog_ctx_type(struct bpf_verifier_log *log, const struct btf *btf,
bpf_log(log, "arg#%d struct doesn't have a name\n", arg);
return NULL;
}
- /* prog_type is valid bpf program type. No need for bounds check. */
- ctx_type = btf_type_member(conv_struct) + bpf_ctx_convert_map[prog_type] * 2;
- /* ctx_struct is a pointer to prog_ctx_type in vmlinux.
- * Like 'struct __sk_buff'
- */
- ctx_struct = btf_type_by_id(btf_vmlinux, ctx_type->type);
- if (!ctx_struct)
+
+ ctx_type = find_canonical_prog_ctx_type(prog_type);
+ if (!ctx_type) {
+ bpf_log(log, "btf_vmlinux is malformed\n");
/* should not happen */
return NULL;
+ }
again:
- ctx_tname = btf_name_by_offset(btf_vmlinux, ctx_struct->name_off);
+ ctx_tname = btf_name_by_offset(btf_vmlinux, ctx_type->name_off);
if (!ctx_tname) {
/* should not happen */
bpf_log(log, "Please fix kernel include/linux/bpf_types.h\n");
@@ -5677,28 +5700,167 @@ again:
/* bpf_user_pt_regs_t is a typedef, so resolve it to
* underlying struct and check name again
*/
- if (!btf_type_is_modifier(ctx_struct))
+ if (!btf_type_is_modifier(ctx_type))
return NULL;
- while (btf_type_is_modifier(ctx_struct))
- ctx_struct = btf_type_by_id(btf_vmlinux, ctx_struct->type);
+ while (btf_type_is_modifier(ctx_type))
+ ctx_type = btf_type_by_id(btf_vmlinux, ctx_type->type);
goto again;
}
return ctx_type;
}
+/* forward declarations for arch-specific underlying types of
+ * bpf_user_pt_regs_t; this avoids the need for arch-specific #ifdef
+ * compilation guards below for BPF_PROG_TYPE_PERF_EVENT checks, but still
+ * works correctly with __builtin_types_compatible_p() on respective
+ * architectures
+ */
+struct user_regs_struct;
+struct user_pt_regs;
+
+static int btf_validate_prog_ctx_type(struct bpf_verifier_log *log, const struct btf *btf,
+ const struct btf_type *t, int arg,
+ enum bpf_prog_type prog_type,
+ enum bpf_attach_type attach_type)
+{
+ const struct btf_type *ctx_type;
+ const char *tname, *ctx_tname;
+
+ if (!btf_is_ptr(t)) {
+ bpf_log(log, "arg#%d type isn't a pointer\n", arg);
+ return -EINVAL;
+ }
+ t = btf_type_by_id(btf, t->type);
+
+ /* KPROBE and PERF_EVENT programs allow bpf_user_pt_regs_t typedef */
+ if (prog_type == BPF_PROG_TYPE_KPROBE || prog_type == BPF_PROG_TYPE_PERF_EVENT) {
+ while (btf_type_is_modifier(t) && !btf_type_is_typedef(t))
+ t = btf_type_by_id(btf, t->type);
+
+ if (btf_type_is_typedef(t)) {
+ tname = btf_name_by_offset(btf, t->name_off);
+ if (tname && strcmp(tname, "bpf_user_pt_regs_t") == 0)
+ return 0;
+ }
+ }
+
+ /* all other program types don't use typedefs for context type */
+ while (btf_type_is_modifier(t))
+ t = btf_type_by_id(btf, t->type);
+
+ /* `void *ctx __arg_ctx` is always valid */
+ if (btf_type_is_void(t))
+ return 0;
+
+ tname = btf_name_by_offset(btf, t->name_off);
+ if (str_is_empty(tname)) {
+ bpf_log(log, "arg#%d type doesn't have a name\n", arg);
+ return -EINVAL;
+ }
+
+ /* special cases */
+ switch (prog_type) {
+ case BPF_PROG_TYPE_KPROBE:
+ if (__btf_type_is_struct(t) && strcmp(tname, "pt_regs") == 0)
+ return 0;
+ break;
+ case BPF_PROG_TYPE_PERF_EVENT:
+ if (__builtin_types_compatible_p(bpf_user_pt_regs_t, struct pt_regs) &&
+ __btf_type_is_struct(t) && strcmp(tname, "pt_regs") == 0)
+ return 0;
+ if (__builtin_types_compatible_p(bpf_user_pt_regs_t, struct user_pt_regs) &&
+ __btf_type_is_struct(t) && strcmp(tname, "user_pt_regs") == 0)
+ return 0;
+ if (__builtin_types_compatible_p(bpf_user_pt_regs_t, struct user_regs_struct) &&
+ __btf_type_is_struct(t) && strcmp(tname, "user_regs_struct") == 0)
+ return 0;
+ break;
+ case BPF_PROG_TYPE_RAW_TRACEPOINT:
+ case BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE:
+ /* allow u64* as ctx */
+ if (btf_is_int(t) && t->size == 8)
+ return 0;
+ break;
+ case BPF_PROG_TYPE_TRACING:
+ switch (attach_type) {
+ case BPF_TRACE_RAW_TP:
+ /* tp_btf program is TRACING, so need special case here */
+ if (__btf_type_is_struct(t) &&
+ strcmp(tname, "bpf_raw_tracepoint_args") == 0)
+ return 0;
+ /* allow u64* as ctx */
+ if (btf_is_int(t) && t->size == 8)
+ return 0;
+ break;
+ case BPF_TRACE_ITER:
+ /* allow struct bpf_iter__xxx types only */
+ if (__btf_type_is_struct(t) &&
+ strncmp(tname, "bpf_iter__", sizeof("bpf_iter__") - 1) == 0)
+ return 0;
+ break;
+ case BPF_TRACE_FENTRY:
+ case BPF_TRACE_FEXIT:
+ case BPF_MODIFY_RETURN:
+ /* allow u64* as ctx */
+ if (btf_is_int(t) && t->size == 8)
+ return 0;
+ break;
+ default:
+ break;
+ }
+ break;
+ case BPF_PROG_TYPE_LSM:
+ case BPF_PROG_TYPE_STRUCT_OPS:
+ /* allow u64* as ctx */
+ if (btf_is_int(t) && t->size == 8)
+ return 0;
+ break;
+ case BPF_PROG_TYPE_TRACEPOINT:
+ case BPF_PROG_TYPE_SYSCALL:
+ case BPF_PROG_TYPE_EXT:
+ return 0; /* anything goes */
+ default:
+ break;
+ }
+
+ ctx_type = find_canonical_prog_ctx_type(prog_type);
+ if (!ctx_type) {
+ /* should not happen */
+ bpf_log(log, "btf_vmlinux is malformed\n");
+ return -EINVAL;
+ }
+
+ /* resolve typedefs and check that underlying structs are matching as well */
+ while (btf_type_is_modifier(ctx_type))
+ ctx_type = btf_type_by_id(btf_vmlinux, ctx_type->type);
+
+ /* if program type doesn't have distinctly named struct type for
+ * context, then __arg_ctx argument can only be `void *`, which we
+ * already checked above
+ */
+ if (!__btf_type_is_struct(ctx_type)) {
+ bpf_log(log, "arg#%d should be void pointer\n", arg);
+ return -EINVAL;
+ }
+
+ ctx_tname = btf_name_by_offset(btf_vmlinux, ctx_type->name_off);
+ if (!__btf_type_is_struct(t) || strcmp(ctx_tname, tname) != 0) {
+ bpf_log(log, "arg#%d should be `struct %s *`\n", arg, ctx_tname);
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
static int btf_translate_to_vmlinux(struct bpf_verifier_log *log,
struct btf *btf,
const struct btf_type *t,
enum bpf_prog_type prog_type,
int arg)
{
- const struct btf_member *prog_ctx_type, *kern_ctx_type;
-
- prog_ctx_type = btf_get_prog_ctx_type(log, btf, t, prog_type, arg);
- if (!prog_ctx_type)
+ if (!btf_get_prog_ctx_type(log, btf, t, prog_type, arg))
return -ENOENT;
- kern_ctx_type = prog_ctx_type + 1;
- return kern_ctx_type->type;
+ return find_kern_ctx_type_id(prog_type);
}
int get_kern_ctx_btf_id(struct bpf_verifier_log *log, enum bpf_prog_type prog_type)
@@ -6934,6 +7096,23 @@ int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog)
return -EINVAL;
}
+ for (i = 0; i < nargs; i++) {
+ const char *tag;
+
+ if (sub->args[i].arg_type != ARG_PTR_TO_CTX)
+ continue;
+
+ /* check if arg has "arg:ctx" tag */
+ t = btf_type_by_id(btf, args[i].type);
+ tag = btf_find_decl_tag_value(btf, fn_t, i, "arg:");
+ if (IS_ERR_OR_NULL(tag) || strcmp(tag, "ctx") != 0)
+ continue;
+
+ if (btf_validate_prog_ctx_type(log, btf, t, i, prog_type,
+ prog->expected_attach_type))
+ return -EINVAL;
+ }
+
sub->arg_cnt = nargs;
sub->args_cached = true;
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index adbf330d364b..65f598694d55 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -12826,6 +12826,10 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env,
}
switch (base_type(ptr_reg->type)) {
+ case PTR_TO_FLOW_KEYS:
+ if (known)
+ break;
+ fallthrough;
case CONST_PTR_TO_MAP:
/* smin_val represents the known value */
if (known && smin_val == 0 && opcode == BPF_ADD)