summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
-rw-r--r--Documentation/bpf/index.rst1
-rw-r--r--Documentation/bpf/kfuncs.rst170
-rw-r--r--include/linux/bpf.h3
-rw-r--r--include/linux/btf.h65
-rw-r--r--include/linux/btf_ids.h68
-rw-r--r--include/net/netfilter/nf_conntrack_core.h19
-rw-r--r--kernel/bpf/btf.c123
-rw-r--r--kernel/bpf/verifier.c14
-rw-r--r--net/bpf/test_run.c75
-rw-r--r--net/ipv4/bpf_tcp_ca.c18
-rw-r--r--net/ipv4/tcp_bbr.c24
-rw-r--r--net/ipv4/tcp_cubic.c20
-rw-r--r--net/ipv4/tcp_dctcp.c20
-rw-r--r--net/netfilter/nf_conntrack_bpf.c365
-rw-r--r--net/netfilter/nf_conntrack_core.c62
-rw-r--r--net/netfilter/nf_conntrack_netlink.c54
-rw-r--r--tools/bpf/resolve_btfids/main.c40
-rw-r--r--tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c10
-rw-r--r--tools/testing/selftests/bpf/prog_tests/bpf_nf.c64
-rw-r--r--tools/testing/selftests/bpf/progs/test_bpf_nf.c85
-rw-r--r--tools/testing/selftests/bpf/progs/test_bpf_nf_fail.c134
-rw-r--r--tools/testing/selftests/bpf/verifier/bpf_loop_inline.c1
-rw-r--r--tools/testing/selftests/bpf/verifier/calls.c53
23 files changed, 1139 insertions, 349 deletions
diff --git a/Documentation/bpf/index.rst b/Documentation/bpf/index.rst
index 96056a7447c7..1bc2c5c58bdb 100644
--- a/Documentation/bpf/index.rst
+++ b/Documentation/bpf/index.rst
@@ -19,6 +19,7 @@ that goes into great technical depth about the BPF Architecture.
faq
syscall_api
helpers
+ kfuncs
programs
maps
bpf_prog_run
diff --git a/Documentation/bpf/kfuncs.rst b/Documentation/bpf/kfuncs.rst
new file mode 100644
index 000000000000..c0b7dae6dbf5
--- /dev/null
+++ b/Documentation/bpf/kfuncs.rst
@@ -0,0 +1,170 @@
+=============================
+BPF Kernel Functions (kfuncs)
+=============================
+
+1. Introduction
+===============
+
+BPF Kernel Functions or more commonly known as kfuncs are functions in the Linux
+kernel which are exposed for use by BPF programs. Unlike normal BPF helpers,
+kfuncs do not have a stable interface and can change from one kernel release to
+another. Hence, BPF programs need to be updated in response to changes in the
+kernel.
+
+2. Defining a kfunc
+===================
+
+There are two ways to expose a kernel function to BPF programs, either make an
+existing function in the kernel visible, or add a new wrapper for BPF. In both
+cases, care must be taken that BPF program can only call such function in a
+valid context. To enforce this, visibility of a kfunc can be per program type.
+
+If you are not creating a BPF wrapper for existing kernel function, skip ahead
+to :ref:`BPF_kfunc_nodef`.
+
+2.1 Creating a wrapper kfunc
+----------------------------
+
+When defining a wrapper kfunc, the wrapper function should have extern linkage.
+This prevents the compiler from optimizing away dead code, as this wrapper kfunc
+is not invoked anywhere in the kernel itself. It is not necessary to provide a
+prototype in a header for the wrapper kfunc.
+
+An example is given below::
+
+ /* Disables missing prototype warnings */
+ __diag_push();
+ __diag_ignore_all("-Wmissing-prototypes",
+ "Global kfuncs as their definitions will be in BTF");
+
+ struct task_struct *bpf_find_get_task_by_vpid(pid_t nr)
+ {
+ return find_get_task_by_vpid(nr);
+ }
+
+ __diag_pop();
+
+A wrapper kfunc is often needed when we need to annotate parameters of the
+kfunc. Otherwise one may directly make the kfunc visible to the BPF program by
+registering it with the BPF subsystem. See :ref:`BPF_kfunc_nodef`.
+
+2.2 Annotating kfunc parameters
+-------------------------------
+
+Similar to BPF helpers, there is sometime need for additional context required
+by the verifier to make the usage of kernel functions safer and more useful.
+Hence, we can annotate a parameter by suffixing the name of the argument of the
+kfunc with a __tag, where tag may be one of the supported annotations.
+
+2.2.1 __sz Annotation
+---------------------
+
+This annotation is used to indicate a memory and size pair in the argument list.
+An example is given below::
+
+ void bpf_memzero(void *mem, int mem__sz)
+ {
+ ...
+ }
+
+Here, the verifier will treat first argument as a PTR_TO_MEM, and second
+argument as its size. By default, without __sz annotation, the size of the type
+of the pointer is used. Without __sz annotation, a kfunc cannot accept a void
+pointer.
+
+.. _BPF_kfunc_nodef:
+
+2.3 Using an existing kernel function
+-------------------------------------
+
+When an existing function in the kernel is fit for consumption by BPF programs,
+it can be directly registered with the BPF subsystem. However, care must still
+be taken to review the context in which it will be invoked by the BPF program
+and whether it is safe to do so.
+
+2.4 Annotating kfuncs
+---------------------
+
+In addition to kfuncs' arguments, verifier may need more information about the
+type of kfunc(s) being registered with the BPF subsystem. To do so, we define
+flags on a set of kfuncs as follows::
+
+ BTF_SET8_START(bpf_task_set)
+ BTF_ID_FLAGS(func, bpf_get_task_pid, KF_ACQUIRE | KF_RET_NULL)
+ BTF_ID_FLAGS(func, bpf_put_pid, KF_RELEASE)
+ BTF_SET8_END(bpf_task_set)
+
+This set encodes the BTF ID of each kfunc listed above, and encodes the flags
+along with it. Ofcourse, it is also allowed to specify no flags.
+
+2.4.1 KF_ACQUIRE flag
+---------------------
+
+The KF_ACQUIRE flag is used to indicate that the kfunc returns a pointer to a
+refcounted object. The verifier will then ensure that the pointer to the object
+is eventually released using a release kfunc, or transferred to a map using a
+referenced kptr (by invoking bpf_kptr_xchg). If not, the verifier fails the
+loading of the BPF program until no lingering references remain in all possible
+explored states of the program.
+
+2.4.2 KF_RET_NULL flag
+----------------------
+
+The KF_RET_NULL flag is used to indicate that the pointer returned by the kfunc
+may be NULL. Hence, it forces the user to do a NULL check on the pointer
+returned from the kfunc before making use of it (dereferencing or passing to
+another helper). This flag is often used in pairing with KF_ACQUIRE flag, but
+both are orthogonal to each other.
+
+2.4.3 KF_RELEASE flag
+---------------------
+
+The KF_RELEASE flag is used to indicate that the kfunc releases the pointer
+passed in to it. There can be only one referenced pointer that can be passed in.
+All copies of the pointer being released are invalidated as a result of invoking
+kfunc with this flag.
+
+2.4.4 KF_KPTR_GET flag
+----------------------
+
+The KF_KPTR_GET flag is used to indicate that the kfunc takes the first argument
+as a pointer to kptr, safely increments the refcount of the object it points to,
+and returns a reference to the user. The rest of the arguments may be normal
+arguments of a kfunc. The KF_KPTR_GET flag should be used in conjunction with
+KF_ACQUIRE and KF_RET_NULL flags.
+
+2.4.5 KF_TRUSTED_ARGS flag
+--------------------------
+
+The KF_TRUSTED_ARGS flag is used for kfuncs taking pointer arguments. It
+indicates that the all pointer arguments will always be refcounted, and have
+their offset set to 0. It can be used to enforce that a pointer to a refcounted
+object acquired from a kfunc or BPF helper is passed as an argument to this
+kfunc without any modifications (e.g. pointer arithmetic) such that it is
+trusted and points to the original object. This flag is often used for kfuncs
+that operate (change some property, perform some operation) on an object that
+was obtained using an acquire kfunc. Such kfuncs need an unchanged pointer to
+ensure the integrity of the operation being performed on the expected object.
+
+2.5 Registering the kfuncs
+--------------------------
+
+Once the kfunc is prepared for use, the final step to making it visible is
+registering it with the BPF subsystem. Registration is done per BPF program
+type. An example is shown below::
+
+ BTF_SET8_START(bpf_task_set)
+ BTF_ID_FLAGS(func, bpf_get_task_pid, KF_ACQUIRE | KF_RET_NULL)
+ BTF_ID_FLAGS(func, bpf_put_pid, KF_RELEASE)
+ BTF_SET8_END(bpf_task_set)
+
+ static const struct btf_kfunc_id_set bpf_task_kfunc_set = {
+ .owner = THIS_MODULE,
+ .set = &bpf_task_set,
+ };
+
+ static int init_subsystem(void)
+ {
+ return register_btf_kfunc_id_set(BPF_PROG_TYPE_TRACING, &bpf_task_kfunc_set);
+ }
+ late_initcall(init_subsystem);
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 11950029284f..a97751d845c9 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -1924,7 +1924,8 @@ int btf_check_subprog_arg_match(struct bpf_verifier_env *env, int subprog,
struct bpf_reg_state *regs);
int btf_check_kfunc_arg_match(struct bpf_verifier_env *env,
const struct btf *btf, u32 func_id,
- struct bpf_reg_state *regs);
+ struct bpf_reg_state *regs,
+ u32 kfunc_flags);
int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog,
struct bpf_reg_state *reg);
int btf_check_type_match(struct bpf_verifier_log *log, const struct bpf_prog *prog,
diff --git a/include/linux/btf.h b/include/linux/btf.h
index 1bfed7fa0428..cdb376d53238 100644
--- a/include/linux/btf.h
+++ b/include/linux/btf.h
@@ -12,14 +12,43 @@
#define BTF_TYPE_EMIT(type) ((void)(type *)0)
#define BTF_TYPE_EMIT_ENUM(enum_val) ((void)enum_val)
-enum btf_kfunc_type {
- BTF_KFUNC_TYPE_CHECK,
- BTF_KFUNC_TYPE_ACQUIRE,
- BTF_KFUNC_TYPE_RELEASE,
- BTF_KFUNC_TYPE_RET_NULL,
- BTF_KFUNC_TYPE_KPTR_ACQUIRE,
- BTF_KFUNC_TYPE_MAX,
-};
+/* These need to be macros, as the expressions are used in assembler input */
+#define KF_ACQUIRE (1 << 0) /* kfunc is an acquire function */
+#define KF_RELEASE (1 << 1) /* kfunc is a release function */
+#define KF_RET_NULL (1 << 2) /* kfunc returns a pointer that may be NULL */
+#define KF_KPTR_GET (1 << 3) /* kfunc returns reference to a kptr */
+/* Trusted arguments are those which are meant to be referenced arguments with
+ * unchanged offset. It is used to enforce that pointers obtained from acquire
+ * kfuncs remain unmodified when being passed to helpers taking trusted args.
+ *
+ * Consider
+ * struct foo {
+ * int data;
+ * struct foo *next;
+ * };
+ *
+ * struct bar {
+ * int data;
+ * struct foo f;
+ * };
+ *
+ * struct foo *f = alloc_foo(); // Acquire kfunc
+ * struct bar *b = alloc_bar(); // Acquire kfunc
+ *
+ * If a kfunc set_foo_data() wants to operate only on the allocated object, it
+ * will set the KF_TRUSTED_ARGS flag, which will prevent unsafe usage like:
+ *
+ * set_foo_data(f, 42); // Allowed
+ * set_foo_data(f->next, 42); // Rejected, non-referenced pointer
+ * set_foo_data(&f->next, 42);// Rejected, referenced, but wrong type
+ * set_foo_data(&b->f, 42); // Rejected, referenced, but bad offset
+ *
+ * In the final case, usually for the purposes of type matching, it is deduced
+ * by looking at the type of the member at the offset, but due to the
+ * requirement of trusted argument, this deduction will be strict and not done
+ * for this case.
+ */
+#define KF_TRUSTED_ARGS (1 << 4) /* kfunc only takes trusted pointer arguments */
struct btf;
struct btf_member;
@@ -30,16 +59,7 @@ struct btf_id_set;
struct btf_kfunc_id_set {
struct module *owner;
- union {
- struct {
- struct btf_id_set *check_set;
- struct btf_id_set *acquire_set;
- struct btf_id_set *release_set;
- struct btf_id_set *ret_null_set;
- struct btf_id_set *kptr_acquire_set;
- };
- struct btf_id_set *sets[BTF_KFUNC_TYPE_MAX];
- };
+ struct btf_id_set8 *set;
};
struct btf_id_dtor_kfunc {
@@ -378,9 +398,9 @@ const struct btf_type *btf_type_by_id(const struct btf *btf, u32 type_id);
const char *btf_name_by_offset(const struct btf *btf, u32 offset);
struct btf *btf_parse_vmlinux(void);
struct btf *bpf_prog_get_target_btf(const struct bpf_prog *prog);
-bool btf_kfunc_id_set_contains(const struct btf *btf,
+u32 *btf_kfunc_id_set_contains(const struct btf *btf,
enum bpf_prog_type prog_type,
- enum btf_kfunc_type type, u32 kfunc_btf_id);
+ u32 kfunc_btf_id);
int register_btf_kfunc_id_set(enum bpf_prog_type prog_type,
const struct btf_kfunc_id_set *s);
s32 btf_find_dtor_kfunc(struct btf *btf, u32 btf_id);
@@ -397,12 +417,11 @@ static inline const char *btf_name_by_offset(const struct btf *btf,
{
return NULL;
}
-static inline bool btf_kfunc_id_set_contains(const struct btf *btf,
+static inline u32 *btf_kfunc_id_set_contains(const struct btf *btf,
enum bpf_prog_type prog_type,
- enum btf_kfunc_type type,
u32 kfunc_btf_id)
{
- return false;
+ return NULL;
}
static inline int register_btf_kfunc_id_set(enum bpf_prog_type prog_type,
const struct btf_kfunc_id_set *s)
diff --git a/include/linux/btf_ids.h b/include/linux/btf_ids.h
index 252a4befeab1..3cb0741e71d7 100644
--- a/include/linux/btf_ids.h
+++ b/include/linux/btf_ids.h
@@ -8,6 +8,15 @@ struct btf_id_set {
u32 ids[];
};
+struct btf_id_set8 {
+ u32 cnt;
+ u32 flags;
+ struct {
+ u32 id;
+ u32 flags;
+ } pairs[];
+};
+
#ifdef CONFIG_DEBUG_INFO_BTF
#include <linux/compiler.h> /* for __PASTE */
@@ -25,7 +34,7 @@ struct btf_id_set {
#define BTF_IDS_SECTION ".BTF_ids"
-#define ____BTF_ID(symbol) \
+#define ____BTF_ID(symbol, word) \
asm( \
".pushsection " BTF_IDS_SECTION ",\"a\"; \n" \
".local " #symbol " ; \n" \
@@ -33,10 +42,11 @@ asm( \
".size " #symbol ", 4; \n" \
#symbol ": \n" \
".zero 4 \n" \
+word \
".popsection; \n");
-#define __BTF_ID(symbol) \
- ____BTF_ID(symbol)
+#define __BTF_ID(symbol, word) \
+ ____BTF_ID(symbol, word)
#define __ID(prefix) \
__PASTE(prefix, __COUNTER__)
@@ -46,7 +56,14 @@ asm( \
* to 4 zero bytes.
*/
#define BTF_ID(prefix, name) \
- __BTF_ID(__ID(__BTF_ID__##prefix##__##name##__))
+ __BTF_ID(__ID(__BTF_ID__##prefix##__##name##__), "")
+
+#define ____BTF_ID_FLAGS(prefix, name, flags) \
+ __BTF_ID(__ID(__BTF_ID__##prefix##__##name##__), ".long " #flags "\n")
+#define __BTF_ID_FLAGS(prefix, name, flags, ...) \
+ ____BTF_ID_FLAGS(prefix, name, flags)
+#define BTF_ID_FLAGS(prefix, name, ...) \
+ __BTF_ID_FLAGS(prefix, name, ##__VA_ARGS__, 0)
/*
* The BTF_ID_LIST macro defines pure (unsorted) list
@@ -145,10 +162,51 @@ asm( \
".popsection; \n"); \
extern struct btf_id_set name;
+/*
+ * The BTF_SET8_START/END macros pair defines sorted list of
+ * BTF IDs and their flags plus its members count, with the
+ * following layout:
+ *
+ * BTF_SET8_START(list)
+ * BTF_ID_FLAGS(type1, name1, flags)
+ * BTF_ID_FLAGS(type2, name2, flags)
+ * BTF_SET8_END(list)
+ *
+ * __BTF_ID__set8__list:
+ * .zero 8
+ * list:
+ * __BTF_ID__type1__name1__3:
+ * .zero 4
+ * .word (1 << 0) | (1 << 2)
+ * __BTF_ID__type2__name2__5:
+ * .zero 4
+ * .word (1 << 3) | (1 << 1) | (1 << 2)
+ *
+ */
+#define __BTF_SET8_START(name, scope) \
+asm( \
+".pushsection " BTF_IDS_SECTION ",\"a\"; \n" \
+"." #scope " __BTF_ID__set8__" #name "; \n" \
+"__BTF_ID__set8__" #name ":; \n" \
+".zero 8 \n" \
+".popsection; \n");
+
+#define BTF_SET8_START(name) \
+__BTF_ID_LIST(name, local) \
+__BTF_SET8_START(name, local)
+
+#define BTF_SET8_END(name) \
+asm( \
+".pushsection " BTF_IDS_SECTION ",\"a\"; \n" \
+".size __BTF_ID__set8__" #name ", .-" #name " \n" \
+".popsection; \n"); \
+extern struct btf_id_set8 name;
+
#else
#define BTF_ID_LIST(name) static u32 __maybe_unused name[5];
#define BTF_ID(prefix, name)
+#define BTF_ID_FLAGS(prefix, name, flags)
#define BTF_ID_UNUSED
#define BTF_ID_LIST_GLOBAL(name, n) u32 __maybe_unused name[n];
#define BTF_ID_LIST_SINGLE(name, prefix, typename) static u32 __maybe_unused name[1];
@@ -156,6 +214,8 @@ extern struct btf_id_set name;
#define BTF_SET_START(name) static struct btf_id_set __maybe_unused name = { 0 };
#define BTF_SET_START_GLOBAL(name) static struct btf_id_set __maybe_unused name = { 0 };
#define BTF_SET_END(name)
+#define BTF_SET8_START(name) static struct btf_id_set8 __maybe_unused name = { 0 };
+#define BTF_SET8_END(name) static struct btf_id_set8 __maybe_unused name = { 0 };
#endif /* CONFIG_DEBUG_INFO_BTF */
diff --git a/include/net/netfilter/nf_conntrack_core.h b/include/net/netfilter/nf_conntrack_core.h
index 37866c8386e2..3cd3a6e631aa 100644
--- a/include/net/netfilter/nf_conntrack_core.h
+++ b/include/net/netfilter/nf_conntrack_core.h
@@ -84,4 +84,23 @@ void nf_conntrack_lock(spinlock_t *lock);
extern spinlock_t nf_conntrack_expect_lock;
+/* ctnetlink code shared by both ctnetlink and nf_conntrack_bpf */
+
+#if (IS_BUILTIN(CONFIG_NF_CONNTRACK) && IS_ENABLED(CONFIG_DEBUG_INFO_BTF)) || \
+ (IS_MODULE(CONFIG_NF_CONNTRACK) && IS_ENABLED(CONFIG_DEBUG_INFO_BTF_MODULES) || \
+ IS_ENABLED(CONFIG_NF_CT_NETLINK))
+
+static inline void __nf_ct_set_timeout(struct nf_conn *ct, u64 timeout)
+{
+ if (timeout > INT_MAX)
+ timeout = INT_MAX;
+ WRITE_ONCE(ct->timeout, nfct_time_stamp + (u32)timeout);
+}
+
+int __nf_ct_change_timeout(struct nf_conn *ct, u64 cta_timeout);
+void __nf_ct_change_status(struct nf_conn *ct, unsigned long on, unsigned long off);
+int nf_ct_change_status_common(struct nf_conn *ct, unsigned int status);
+
+#endif
+
#endif /* _NF_CONNTRACK_CORE_H */
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index 5869f03bcb6e..7ac971ea98d1 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -213,7 +213,7 @@ enum {
};
struct btf_kfunc_set_tab {
- struct btf_id_set *sets[BTF_KFUNC_HOOK_MAX][BTF_KFUNC_TYPE_MAX];
+ struct btf_id_set8 *sets[BTF_KFUNC_HOOK_MAX];
};
struct btf_id_dtor_kfunc_tab {
@@ -1616,7 +1616,7 @@ static void btf_free_id(struct btf *btf)
static void btf_free_kfunc_set_tab(struct btf *btf)
{
struct btf_kfunc_set_tab *tab = btf->kfunc_set_tab;
- int hook, type;
+ int hook;
if (!tab)
return;
@@ -1625,10 +1625,8 @@ static void btf_free_kfunc_set_tab(struct btf *btf)
*/
if (btf_is_module(btf))
goto free_tab;
- for (hook = 0; hook < ARRAY_SIZE(tab->sets); hook++) {
- for (type = 0; type < ARRAY_SIZE(tab->sets[0]); type++)
- kfree(tab->sets[hook][type]);
- }
+ for (hook = 0; hook < ARRAY_SIZE(tab->sets); hook++)
+ kfree(tab->sets[hook]);
free_tab:
kfree(tab);
btf->kfunc_set_tab = NULL;
@@ -6172,13 +6170,14 @@ static bool is_kfunc_arg_mem_size(const struct btf *btf,
static int btf_check_func_arg_match(struct bpf_verifier_env *env,
const struct btf *btf, u32 func_id,
struct bpf_reg_state *regs,
- bool ptr_to_mem_ok)
+ bool ptr_to_mem_ok,
+ u32 kfunc_flags)
{
enum bpf_prog_type prog_type = resolve_prog_type(env->prog);
+ bool rel = false, kptr_get = false, trusted_arg = false;
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;
@@ -6210,10 +6209,9 @@ static int btf_check_func_arg_match(struct bpf_verifier_env *env,
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);
+ rel = kfunc_flags & KF_RELEASE;
+ kptr_get = kfunc_flags & KF_KPTR_GET;
+ trusted_arg = kfunc_flags & KF_TRUSTED_ARGS;
}
/* check that BTF function arguments match actual types that the
@@ -6238,10 +6236,19 @@ static int btf_check_func_arg_match(struct bpf_verifier_env *env,
return -EINVAL;
}
+ /* Check if argument must be a referenced pointer, args + i has
+ * been verified to be a pointer (after skipping modifiers).
+ */
+ if (is_kfunc && trusted_arg && !reg->ref_obj_id) {
+ bpf_log(log, "R%d must be referenced\n", regno);
+ return -EINVAL;
+ }
+
ref_t = btf_type_skip_modifiers(btf, t->type, &ref_id);
ref_tname = btf_name_by_offset(btf, ref_t->name_off);
- if (rel && reg->ref_obj_id)
+ /* Trusted args have the same offset checks as release arguments */
+ if (trusted_arg || (rel && reg->ref_obj_id))
arg_type |= OBJ_RELEASE;
ret = check_func_arg_reg_off(env, reg, regno, arg_type);
if (ret < 0)
@@ -6339,7 +6346,8 @@ 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, rel && reg->ref_obj_id)) {
+ reg->off, btf, ref_id,
+ trusted_arg || (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,
@@ -6442,7 +6450,7 @@ int btf_check_subprog_arg_match(struct bpf_verifier_env *env, int subprog,
return -EINVAL;
is_global = prog->aux->func_info_aux[subprog].linkage == BTF_FUNC_GLOBAL;
- err = btf_check_func_arg_match(env, btf, btf_id, regs, is_global);
+ err = btf_check_func_arg_match(env, btf, btf_id, regs, is_global, 0);
/* Compiler optimizations can remove arguments from static functions
* or mismatched type can be passed into a global function.
@@ -6455,9 +6463,10 @@ int btf_check_subprog_arg_match(struct bpf_verifier_env *env, int subprog,
int btf_check_kfunc_arg_match(struct bpf_verifier_env *env,
const struct btf *btf, u32 func_id,
- struct bpf_reg_state *regs)
+ struct bpf_reg_state *regs,
+ u32 kfunc_flags)
{
- return btf_check_func_arg_match(env, btf, func_id, regs, true);
+ return btf_check_func_arg_match(env, btf, func_id, regs, true, kfunc_flags);
}
/* Convert BTF of a function into bpf_reg_state if possible
@@ -6854,6 +6863,11 @@ bool btf_id_set_contains(const struct btf_id_set *set, u32 id)
return bsearch(&id, set->ids, set->cnt, sizeof(u32), btf_id_cmp_func) != NULL;
}
+static void *btf_id_set8_contains(const struct btf_id_set8 *set, u32 id)
+{
+ return bsearch(&id, set->pairs, set->cnt, sizeof(set->pairs[0]), btf_id_cmp_func);
+}
+
enum {
BTF_MODULE_F_LIVE = (1 << 0),
};
@@ -7102,16 +7116,16 @@ BTF_TRACING_TYPE_xxx
/* Kernel Function (kfunc) BTF ID set registration API */
-static int __btf_populate_kfunc_set(struct btf *btf, enum btf_kfunc_hook hook,
- enum btf_kfunc_type type,
- struct btf_id_set *add_set, bool vmlinux_set)
+static int btf_populate_kfunc_set(struct btf *btf, enum btf_kfunc_hook hook,
+ struct btf_id_set8 *add_set)
{
+ bool vmlinux_set = !btf_is_module(btf);
struct btf_kfunc_set_tab *tab;
- struct btf_id_set *set;
+ struct btf_id_set8 *set;
u32 set_cnt;
int ret;
- if (hook >= BTF_KFUNC_HOOK_MAX || type >= BTF_KFUNC_TYPE_MAX) {
+ if (hook >= BTF_KFUNC_HOOK_MAX) {
ret = -EINVAL;
goto end;
}
@@ -7127,7 +7141,7 @@ static int __btf_populate_kfunc_set(struct btf *btf, enum btf_kfunc_hook hook,
btf->kfunc_set_tab = tab;
}
- set = tab->sets[hook][type];
+ set = tab->sets[hook];
/* Warn when register_btf_kfunc_id_set is called twice for the same hook
* for module sets.
*/
@@ -7141,7 +7155,7 @@ static int __btf_populate_kfunc_set(struct btf *btf, enum btf_kfunc_hook hook,
* pointer and return.
*/
if (!vmlinux_set) {
- tab->sets[hook][type] = add_set;
+ tab->sets[hook] = add_set;
return 0;
}
@@ -7150,7 +7164,7 @@ static int __btf_populate_kfunc_set(struct btf *btf, enum btf_kfunc_hook hook,
* and concatenate all individual sets being registered. While each set
* is individually sorted, they may become unsorted when concatenated,
* hence re-sorting the final set again is required to make binary
- * searching the set using btf_id_set_contains function work.
+ * searching the set using btf_id_set8_contains function work.
*/
set_cnt = set ? set->cnt : 0;
@@ -7165,8 +7179,8 @@ static int __btf_populate_kfunc_set(struct btf *btf, enum btf_kfunc_hook hook,
}
/* Grow set */
- set = krealloc(tab->sets[hook][type],
- offsetof(struct btf_id_set, ids[set_cnt + add_set->cnt]),
+ set = krealloc(tab->sets[hook],
+ offsetof(struct btf_id_set8, pairs[set_cnt + add_set->cnt]),
GFP_KERNEL | __GFP_NOWARN);
if (!set) {
ret = -ENOMEM;
@@ -7174,15 +7188,15 @@ static int __btf_populate_kfunc_set(struct btf *btf, enum btf_kfunc_hook hook,
}
/* For newly allocated set, initialize set->cnt to 0 */
- if (!tab->sets[hook][type])
+ if (!tab->sets[hook])
set->cnt = 0;
- tab->sets[hook][type] = set;
+ tab->sets[hook] = set;
/* Concatenate the two sets */
- memcpy(set->ids + set->cnt, add_set->ids, add_set->cnt * sizeof(set->ids[0]));
+ memcpy(set->pairs + set->cnt, add_set->pairs, add_set->cnt * sizeof(set->pairs[0]));
set->cnt += add_set->cnt;
- sort(set->ids, set->cnt, sizeof(set->ids[0]), btf_id_cmp_func, NULL);
+ sort(set->pairs, set->cnt, sizeof(set->pairs[0]), btf_id_cmp_func, NULL);
return 0;
end:
@@ -7190,38 +7204,25 @@ end:
return ret;
}
-static int btf_populate_kfunc_set(struct btf *btf, enum btf_kfunc_hook hook,
- const struct btf_kfunc_id_set *kset)
-{
- bool vmlinux_set = !btf_is_module(btf);
- int type, ret = 0;
-
- for (type = 0; type < ARRAY_SIZE(kset->sets); type++) {
- if (!kset->sets[type])
- continue;
-
- ret = __btf_populate_kfunc_set(btf, hook, type, kset->sets[type], vmlinux_set);
- if (ret)
- break;
- }
- return ret;
-}
-
-static bool __btf_kfunc_id_set_contains(const struct btf *btf,
+static u32 *__btf_kfunc_id_set_contains(const struct btf *btf,
enum btf_kfunc_hook hook,
- enum btf_kfunc_type type,
u32 kfunc_btf_id)
{
- struct btf_id_set *set;
+ struct btf_id_set8 *set;
+ u32 *id;
- if (hook >= BTF_KFUNC_HOOK_MAX || type >= BTF_KFUNC_TYPE_MAX)
- return false;
+ if (hook >= BTF_KFUNC_HOOK_MAX)
+ return NULL;
if (!btf->kfunc_set_tab)
- return false;
- set = btf->kfunc_set_tab->sets[hook][type];
+ return NULL;
+ set = btf->kfunc_set_tab->sets[hook];
if (!set)
- return false;
- return btf_id_set_contains(set, kfunc_btf_id);
+ return NULL;
+ id = btf_id_set8_contains(set, kfunc_btf_id);
+ if (!id)
+ return NULL;
+ /* The flags for BTF ID are located next to it */
+ return id + 1;
}
static int bpf_prog_type_to_kfunc_hook(enum bpf_prog_type prog_type)
@@ -7249,14 +7250,14 @@ static int bpf_prog_type_to_kfunc_hook(enum bpf_prog_type prog_type)
* keeping the reference for the duration of the call provides the necessary
* protection for looking up a well-formed btf->kfunc_set_tab.
*/
-bool btf_kfunc_id_set_contains(const struct btf *btf,
+u32 *btf_kfunc_id_set_contains(const struct btf *btf,
enum bpf_prog_type prog_type,
- enum btf_kfunc_type type, u32 kfunc_btf_id)
+ u32 kfunc_btf_id)
{
enum btf_kfunc_hook hook;
hook = bpf_prog_type_to_kfunc_hook(prog_type);
- return __btf_kfunc_id_set_contains(btf, hook, type, kfunc_btf_id);
+ return __btf_kfunc_id_set_contains(btf, hook, kfunc_btf_id);
}
/* This function must be invoked only from initcalls/module init functions */
@@ -7283,7 +7284,7 @@ int register_btf_kfunc_id_set(enum bpf_prog_type prog_type,
return PTR_ERR(btf);
hook = bpf_prog_type_to_kfunc_hook(prog_type);
- ret = btf_populate_kfunc_set(btf, hook, kset);
+ ret = btf_populate_kfunc_set(btf, hook, kset->set);
btf_put(btf);
return ret;
}
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 7c1e056624f9..096fdac70165 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -7562,6 +7562,7 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
int err, insn_idx = *insn_idx_p;
const struct btf_param *args;
struct btf *desc_btf;
+ u32 *kfunc_flags;
bool acq;
/* skip for now, but return error when we find this in fixup_kfunc_call */
@@ -7577,18 +7578,16 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
func_name = btf_name_by_offset(desc_btf, func->name_off);
func_proto = btf_type_by_id(desc_btf, func->type);
- if (!btf_kfunc_id_set_contains(desc_btf, resolve_prog_type(env->prog),
- BTF_KFUNC_TYPE_CHECK, func_id)) {
+ kfunc_flags = btf_kfunc_id_set_contains(desc_btf, resolve_prog_type(env->prog), func_id);
+ if (!kfunc_flags) {
verbose(env, "calling kernel function %s is not allowed\n",
func_name);
return -EACCES;
}
-
- acq = btf_kfunc_id_set_contains(desc_btf, resolve_prog_type(env->prog),
- BTF_KFUNC_TYPE_ACQUIRE, func_id);
+ acq = *kfunc_flags & KF_ACQUIRE;
/* Check the arguments */
- err = btf_check_kfunc_arg_match(env, desc_btf, func_id, regs);
+ err = btf_check_kfunc_arg_match(env, desc_btf, func_id, regs, *kfunc_flags);
if (err < 0)
return err;
/* In case of release function, we get register number of refcounted
@@ -7632,8 +7631,7 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
regs[BPF_REG_0].btf = desc_btf;
regs[BPF_REG_0].type = PTR_TO_BTF_ID;
regs[BPF_REG_0].btf_id = ptr_type_id;
- if (btf_kfunc_id_set_contains(desc_btf, resolve_prog_type(env->prog),
- BTF_KFUNC_TYPE_RET_NULL, func_id)) {
+ if (*kfunc_flags & KF_RET_NULL) {
regs[BPF_REG_0].type |= PTR_MAYBE_NULL;
/* For mark_ptr_or_null_reg, see 93c230e3f5bd6 */
regs[BPF_REG_0].id = ++env->id_gen;
diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c
index dc9dc0bedca0..cbc9cd5058cb 100644
--- a/net/bpf/test_run.c
+++ b/net/bpf/test_run.c
@@ -691,52 +691,35 @@ noinline void bpf_kfunc_call_test_mem_len_fail2(u64 *mem, int len)
{
}
+noinline void bpf_kfunc_call_test_ref(struct prog_test_ref_kfunc *p)
+{
+}
+
__diag_pop();
ALLOW_ERROR_INJECTION(bpf_modify_return_test, ERRNO);
-BTF_SET_START(test_sk_check_kfunc_ids)
-BTF_ID(func, bpf_kfunc_call_test1)
-BTF_ID(func, bpf_kfunc_call_test2)
-BTF_ID(func, bpf_kfunc_call_test3)
-BTF_ID(func, bpf_kfunc_call_test_acquire)
-BTF_ID(func, bpf_kfunc_call_memb_acquire)
-BTF_ID(func, bpf_kfunc_call_test_release)
-BTF_ID(func, bpf_kfunc_call_memb_release)
-BTF_ID(func, bpf_kfunc_call_memb1_release)
-BTF_ID(func, bpf_kfunc_call_test_kptr_get)
-BTF_ID(func, bpf_kfunc_call_test_pass_ctx)
-BTF_ID(func, bpf_kfunc_call_test_pass1)
-BTF_ID(func, bpf_kfunc_call_test_pass2)
-BTF_ID(func, bpf_kfunc_call_test_fail1)
-BTF_ID(func, bpf_kfunc_call_test_fail2)
-BTF_ID(func, bpf_kfunc_call_test_fail3)
-BTF_ID(func, bpf_kfunc_call_test_mem_len_pass1)
-BTF_ID(func, bpf_kfunc_call_test_mem_len_fail1)
-BTF_ID(func, bpf_kfunc_call_test_mem_len_fail2)
-BTF_SET_END(test_sk_check_kfunc_ids)
-
-BTF_SET_START(test_sk_acquire_kfunc_ids)
-BTF_ID(func, bpf_kfunc_call_test_acquire)
-BTF_ID(func, bpf_kfunc_call_memb_acquire)
-BTF_ID(func, bpf_kfunc_call_test_kptr_get)
-BTF_SET_END(test_sk_acquire_kfunc_ids)
-
-BTF_SET_START(test_sk_release_kfunc_ids)
-BTF_ID(func, bpf_kfunc_call_test_release)
-BTF_ID(func, bpf_kfunc_call_memb_release)
-BTF_ID(func, bpf_kfunc_call_memb1_release)
-BTF_SET_END(test_sk_release_kfunc_ids)
-
-BTF_SET_START(test_sk_ret_null_kfunc_ids)
-BTF_ID(func, bpf_kfunc_call_test_acquire)
-BTF_ID(func, bpf_kfunc_call_memb_acquire)
-BTF_ID(func, bpf_kfunc_call_test_kptr_get)
-BTF_SET_END(test_sk_ret_null_kfunc_ids)
-
-BTF_SET_START(test_sk_kptr_acquire_kfunc_ids)
-BTF_ID(func, bpf_kfunc_call_test_kptr_get)
-BTF_SET_END(test_sk_kptr_acquire_kfunc_ids)
+BTF_SET8_START(test_sk_check_kfunc_ids)
+BTF_ID_FLAGS(func, bpf_kfunc_call_test1)
+BTF_ID_FLAGS(func, bpf_kfunc_call_test2)
+BTF_ID_FLAGS(func, bpf_kfunc_call_test3)
+BTF_ID_FLAGS(func, bpf_kfunc_call_test_acquire, KF_ACQUIRE | KF_RET_NULL)
+BTF_ID_FLAGS(func, bpf_kfunc_call_memb_acquire, KF_ACQUIRE | KF_RET_NULL)
+BTF_ID_FLAGS(func, bpf_kfunc_call_test_release, KF_RELEASE)
+BTF_ID_FLAGS(func, bpf_kfunc_call_memb_release, KF_RELEASE)
+BTF_ID_FLAGS(func, bpf_kfunc_call_memb1_release, KF_RELEASE)
+BTF_ID_FLAGS(func, bpf_kfunc_call_test_kptr_get, KF_ACQUIRE | KF_RET_NULL | KF_KPTR_GET)
+BTF_ID_FLAGS(func, bpf_kfunc_call_test_pass_ctx)
+BTF_ID_FLAGS(func, bpf_kfunc_call_test_pass1)
+BTF_ID_FLAGS(func, bpf_kfunc_call_test_pass2)
+BTF_ID_FLAGS(func, bpf_kfunc_call_test_fail1)
+BTF_ID_FLAGS(func, bpf_kfunc_call_test_fail2)
+BTF_ID_FLAGS(func, bpf_kfunc_call_test_fail3)
+BTF_ID_FLAGS(func, bpf_kfunc_call_test_mem_len_pass1)
+BTF_ID_FLAGS(func, bpf_kfunc_call_test_mem_len_fail1)
+BTF_ID_FLAGS(func, bpf_kfunc_call_test_mem_len_fail2)
+BTF_ID_FLAGS(func, bpf_kfunc_call_test_ref, KF_TRUSTED_ARGS)
+BTF_SET8_END(test_sk_check_kfunc_ids)
static void *bpf_test_init(const union bpf_attr *kattr, u32 user_size,
u32 size, u32 headroom, u32 tailroom)
@@ -1620,12 +1603,8 @@ out:
}
static const struct btf_kfunc_id_set bpf_prog_test_kfunc_set = {
- .owner = THIS_MODULE,
- .check_set = &test_sk_check_kfunc_ids,
- .acquire_set = &test_sk_acquire_kfunc_ids,
- .release_set = &test_sk_release_kfunc_ids,
- .ret_null_set = &test_sk_ret_null_kfunc_ids,
- .kptr_acquire_set = &test_sk_kptr_acquire_kfunc_ids
+ .owner = THIS_MODULE,
+ .set = &test_sk_check_kfunc_ids,
};
BTF_ID_LIST(bpf_prog_test_dtor_kfunc_ids)
diff --git a/net/ipv4/bpf_tcp_ca.c b/net/ipv4/bpf_tcp_ca.c
index 7a181631b995..85a9e500c42d 100644
--- a/net/ipv4/bpf_tcp_ca.c
+++ b/net/ipv4/bpf_tcp_ca.c
@@ -197,17 +197,17 @@ bpf_tcp_ca_get_func_proto(enum bpf_func_id func_id,
}
}
-BTF_SET_START(bpf_tcp_ca_check_kfunc_ids)
-BTF_ID(func, tcp_reno_ssthresh)
-BTF_ID(func, tcp_reno_cong_avoid)
-BTF_ID(func, tcp_reno_undo_cwnd)
-BTF_ID(func, tcp_slow_start)
-BTF_ID(func, tcp_cong_avoid_ai)
-BTF_SET_END(bpf_tcp_ca_check_kfunc_ids)
+BTF_SET8_START(bpf_tcp_ca_check_kfunc_ids)
+BTF_ID_FLAGS(func, tcp_reno_ssthresh)
+BTF_ID_FLAGS(func, tcp_reno_cong_avoid)
+BTF_ID_FLAGS(func, tcp_reno_undo_cwnd)
+BTF_ID_FLAGS(func, tcp_slow_start)
+BTF_ID_FLAGS(func, tcp_cong_avoid_ai)
+BTF_SET8_END(bpf_tcp_ca_check_kfunc_ids)
static const struct btf_kfunc_id_set bpf_tcp_ca_kfunc_set = {
- .owner = THIS_MODULE,
- .check_set = &bpf_tcp_ca_check_kfunc_ids,
+ .owner = THIS_MODULE,
+ .set = &bpf_tcp_ca_check_kfunc_ids,
};
static const struct bpf_verifier_ops bpf_tcp_ca_verifier_ops = {
diff --git a/net/ipv4/tcp_bbr.c b/net/ipv4/tcp_bbr.c
index 075e744bfb48..54eec33c6e1c 100644
--- a/net/ipv4/tcp_bbr.c
+++ b/net/ipv4/tcp_bbr.c
@@ -1154,24 +1154,24 @@ static struct tcp_congestion_ops tcp_bbr_cong_ops __read_mostly = {
.set_state = bbr_set_state,
};
-BTF_SET_START(tcp_bbr_check_kfunc_ids)
+BTF_SET8_START(tcp_bbr_check_kfunc_ids)
#ifdef CONFIG_X86
#ifdef CONFIG_DYNAMIC_FTRACE
-BTF_ID(func, bbr_init)
-BTF_ID(func, bbr_main)
-BTF_ID(func, bbr_sndbuf_expand)
-BTF_ID(func, bbr_undo_cwnd)
-BTF_ID(func, bbr_cwnd_event)
-BTF_ID(func, bbr_ssthresh)
-BTF_ID(func, bbr_min_tso_segs)
-BTF_ID(func, bbr_set_state)
+BTF_ID_FLAGS(func, bbr_init)
+BTF_ID_FLAGS(func, bbr_main)
+BTF_ID_FLAGS(func, bbr_sndbuf_expand)
+BTF_ID_FLAGS(func, bbr_undo_cwnd)
+BTF_ID_FLAGS(func, bbr_cwnd_event)
+BTF_ID_FLAGS(func, bbr_ssthresh)
+BTF_ID_FLAGS(func, bbr_min_tso_segs)
+BTF_ID_FLAGS(func, bbr_set_state)
#endif
#endif
-BTF_SET_END(tcp_bbr_check_kfunc_ids)
+BTF_SET8_END(tcp_bbr_check_kfunc_ids)
static const struct btf_kfunc_id_set tcp_bbr_kfunc_set = {
- .owner = THIS_MODULE,
- .check_set = &tcp_bbr_check_kfunc_ids,
+ .owner = THIS_MODULE,
+ .set = &tcp_bbr_check_kfunc_ids,
};
static int __init bbr_register(void)
diff --git a/net/ipv4/tcp_cubic.c b/net/ipv4/tcp_cubic.c
index 68178e7280ce..768c10c1f649 100644
--- a/net/ipv4/tcp_cubic.c
+++ b/net/ipv4/tcp_cubic.c
@@ -485,22 +485,22 @@ static struct tcp_congestion_ops cubictcp __read_mostly = {
.name = "cubic",
};
-BTF_SET_START(tcp_cubic_check_kfunc_ids)
+BTF_SET8_START(tcp_cubic_check_kfunc_ids)
#ifdef CONFIG_X86
#ifdef CONFIG_DYNAMIC_FTRACE
-BTF_ID(func, cubictcp_init)
-BTF_ID(func, cubictcp_recalc_ssthresh)
-BTF_ID(func, cubictcp_cong_avoid)
-BTF_ID(func, cubictcp_state)
-BTF_ID(func, cubictcp_cwnd_event)
-BTF_ID(func, cubictcp_acked)
+BTF_ID_FLAGS(func, cubictcp_init)
+BTF_ID_FLAGS(func, cubictcp_recalc_ssthresh)
+BTF_ID_FLAGS(func, cubictcp_cong_avoid)
+BTF_ID_FLAGS(func, cubictcp_state)
+BTF_ID_FLAGS(func, cubictcp_cwnd_event)
+BTF_ID_FLAGS(func, cubictcp_acked)
#endif
#endif
-BTF_SET_END(tcp_cubic_check_kfunc_ids)
+BTF_SET8_END(tcp_cubic_check_kfunc_ids)
static const struct btf_kfunc_id_set tcp_cubic_kfunc_set = {
- .owner = THIS_MODULE,
- .check_set = &tcp_cubic_check_kfunc_ids,
+ .owner = THIS_MODULE,
+ .set = &tcp_cubic_check_kfunc_ids,
};
static int __init cubictcp_register(void)
diff --git a/net/ipv4/tcp_dctcp.c b/net/ipv4/tcp_dctcp.c
index ab034a4e9324..2a6c0dd665a4 100644
--- a/net/ipv4/tcp_dctcp.c
+++ b/net/ipv4/tcp_dctcp.c
@@ -239,22 +239,22 @@ static struct tcp_congestion_ops dctcp_reno __read_mostly = {
.name = "dctcp-reno",
};
-BTF_SET_START(tcp_dctcp_check_kfunc_ids)
+BTF_SET8_START(tcp_dctcp_check_kfunc_ids)
#ifdef CONFIG_X86
#ifdef CONFIG_DYNAMIC_FTRACE
-BTF_ID(func, dctcp_init)
-BTF_ID(func, dctcp_update_alpha)
-BTF_ID(func, dctcp_cwnd_event)
-BTF_ID(func, dctcp_ssthresh)
-BTF_ID(func, dctcp_cwnd_undo)
-BTF_ID(func, dctcp_state)
+BTF_ID_FLAGS(func, dctcp_init)
+BTF_ID_FLAGS(func, dctcp_update_alpha)
+BTF_ID_FLAGS(func, dctcp_cwnd_event)
+BTF_ID_FLAGS(func, dctcp_ssthresh)
+BTF_ID_FLAGS(func, dctcp_cwnd_undo)
+BTF_ID_FLAGS(func, dctcp_state)
#endif
#endif
-BTF_SET_END(tcp_dctcp_check_kfunc_ids)
+BTF_SET8_END(tcp_dctcp_check_kfunc_ids)
static const struct btf_kfunc_id_set tcp_dctcp_kfunc_set = {
- .owner = THIS_MODULE,
- .check_set = &tcp_dctcp_check_kfunc_ids,
+ .owner = THIS_MODULE,
+ .set = &tcp_dctcp_check_kfunc_ids,
};
static int __init dctcp_register(void)
diff --git a/net/netfilter/nf_conntrack_bpf.c b/net/netfilter/nf_conntrack_bpf.c
index bc4d5cd63a94..1cd87b28c9b0 100644
--- a/net/netfilter/nf_conntrack_bpf.c
+++ b/net/netfilter/nf_conntrack_bpf.c
@@ -55,57 +55,131 @@ enum {
NF_BPF_CT_OPTS_SZ = 12,
};
-static struct nf_conn *__bpf_nf_ct_lookup(struct net *net,
- struct bpf_sock_tuple *bpf_tuple,
- u32 tuple_len, u8 protonum,
- s32 netns_id, u8 *dir)
+static int bpf_nf_ct_tuple_parse(struct bpf_sock_tuple *bpf_tuple,
+ u32 tuple_len, u8 protonum, u8 dir,
+ struct nf_conntrack_tuple *tuple)
{
- struct nf_conntrack_tuple_hash *hash;
- struct nf_conntrack_tuple tuple;
- struct nf_conn *ct;
+ union nf_inet_addr *src = dir ? &tuple->dst.u3 : &tuple->src.u3;
+ union nf_inet_addr *dst = dir ? &tuple->src.u3 : &tuple->dst.u3;
+ union nf_conntrack_man_proto *sport = dir ? (void *)&tuple->dst.u
+ : &tuple->src.u;
+ union nf_conntrack_man_proto *dport = dir ? &tuple->src.u
+ : (void *)&tuple->dst.u;
if (unlikely(protonum != IPPROTO_TCP && protonum != IPPROTO_UDP))
- return ERR_PTR(-EPROTO);
- if (unlikely(netns_id < BPF_F_CURRENT_NETNS))
- return ERR_PTR(-EINVAL);
+ return -EPROTO;
+
+ memset(tuple, 0, sizeof(*tuple));
- memset(&tuple, 0, sizeof(tuple));
switch (tuple_len) {
case sizeof(bpf_tuple->ipv4):
- tuple.src.l3num = AF_INET;
- tuple.src.u3.ip = bpf_tuple->ipv4.saddr;
- tuple.src.u.tcp.port = bpf_tuple->ipv4.sport;
- tuple.dst.u3.ip = bpf_tuple->ipv4.daddr;
- tuple.dst.u.tcp.port = bpf_tuple->ipv4.dport;
+ tuple->src.l3num = AF_INET;
+ src->ip = bpf_tuple->ipv4.saddr;
+ sport->tcp.port = bpf_tuple->ipv4.sport;
+ dst->ip = bpf_tuple->ipv4.daddr;
+ dport->tcp.port = bpf_tuple->ipv4.dport;
break;
case sizeof(bpf_tuple->ipv6):
- tuple.src.l3num = AF_INET6;
- memcpy(tuple.src.u3.ip6, bpf_tuple->ipv6.saddr, sizeof(bpf_tuple->ipv6.saddr));
- tuple.src.u.tcp.port = bpf_tuple->ipv6.sport;
- memcpy(tuple.dst.u3.ip6, bpf_tuple->ipv6.daddr, sizeof(bpf_tuple->ipv6.daddr));
- tuple.dst.u.tcp.port = bpf_tuple->ipv6.dport;
+ tuple->src.l3num = AF_INET6;
+ memcpy(src->ip6, bpf_tuple->ipv6.saddr, sizeof(bpf_tuple->ipv6.saddr));
+ sport->tcp.port = bpf_tuple->ipv6.sport;
+ memcpy(dst->ip6, bpf_tuple->ipv6.daddr, sizeof(bpf_tuple->ipv6.daddr));
+ dport->tcp.port = bpf_tuple->ipv6.dport;
break;
default:
- return ERR_PTR(-EAFNOSUPPORT);
+ return -EAFNOSUPPORT;
+ }
+ tuple->dst.protonum = protonum;
+ tuple->dst.dir = dir;
+
+ return 0;
+}
+
+static struct nf_conn *
+__bpf_nf_ct_alloc_entry(struct net *net, struct bpf_sock_tuple *bpf_tuple,
+ u32 tuple_len, struct bpf_ct_opts *opts, u32 opts_len,
+ u32 timeout)
+{
+ struct nf_conntrack_tuple otuple, rtuple;
+ struct nf_conn *ct;
+ int err;
+
+ if (!opts || !bpf_tuple || opts->reserved[0] || opts->reserved[1] ||
+ opts_len != NF_BPF_CT_OPTS_SZ)
+ return ERR_PTR(-EINVAL);
+
+ if (unlikely(opts->netns_id < BPF_F_CURRENT_NETNS))
+ return ERR_PTR(-EINVAL);
+
+ err = bpf_nf_ct_tuple_parse(bpf_tuple, tuple_len, opts->l4proto,
+ IP_CT_DIR_ORIGINAL, &otuple);
+ if (err < 0)
+ return ERR_PTR(err);
+
+ err = bpf_nf_ct_tuple_parse(bpf_tuple, tuple_len, opts->l4proto,
+ IP_CT_DIR_REPLY, &rtuple);
+ if (err < 0)
+ return ERR_PTR(err);
+
+ if (opts->netns_id >= 0) {
+ net = get_net_ns_by_id(net, opts->netns_id);
+ if (unlikely(!net))
+ return ERR_PTR(-ENONET);
}
- tuple.dst.protonum = protonum;
+ ct = nf_conntrack_alloc(net, &nf_ct_zone_dflt, &otuple, &rtuple,
+ GFP_ATOMIC);
+ if (IS_ERR(ct))
+ goto out;
+
+ memset(&ct->proto, 0, sizeof(ct->proto));
+ __nf_ct_set_timeout(ct, timeout * HZ);
+ ct->status |= IPS_CONFIRMED;
+
+out:
+ if (opts->netns_id >= 0)
+ put_net(net);
+
+ return ct;
+}
+
+static struct nf_conn *__bpf_nf_ct_lookup(struct net *net,
+ struct bpf_sock_tuple *bpf_tuple,
+ u32 tuple_len, struct bpf_ct_opts *opts,
+ u32 opts_len)
+{
+ struct nf_conntrack_tuple_hash *hash;
+ struct nf_conntrack_tuple tuple;
+ struct nf_conn *ct;
+ int err;
+
+ if (!opts || !bpf_tuple || opts->reserved[0] || opts->reserved[1] ||
+ opts_len != NF_BPF_CT_OPTS_SZ)
+ return ERR_PTR(-EINVAL);
+ if (unlikely(opts->l4proto != IPPROTO_TCP && opts->l4proto != IPPROTO_UDP))
+ return ERR_PTR(-EPROTO);
+ if (unlikely(opts->netns_id < BPF_F_CURRENT_NETNS))
+ return ERR_PTR(-EINVAL);
+
+ err = bpf_nf_ct_tuple_parse(bpf_tuple, tuple_len, opts->l4proto,
+ IP_CT_DIR_ORIGINAL, &tuple);
+ if (err < 0)
+ return ERR_PTR(err);
- if (netns_id >= 0) {
- net = get_net_ns_by_id(net, netns_id);
+ if (opts->netns_id >= 0) {
+ net = get_net_ns_by_id(net, opts->netns_id);
if (unlikely(!net))
return ERR_PTR(-ENONET);
}
hash = nf_conntrack_find_get(net, &nf_ct_zone_dflt, &tuple);
- if (netns_id >= 0)
+ if (opts->netns_id >= 0)
put_net(net);
if (!hash)
return ERR_PTR(-ENOENT);
ct = nf_ct_tuplehash_to_ctrack(hash);
- if (dir)
- *dir = NF_CT_DIRECTION(hash);
+ opts->dir = NF_CT_DIRECTION(hash);
return ct;
}
@@ -114,6 +188,43 @@ __diag_push();
__diag_ignore_all("-Wmissing-prototypes",
"Global functions as their definitions will be in nf_conntrack BTF");
+struct nf_conn___init {
+ struct nf_conn ct;
+};
+
+/* bpf_xdp_ct_alloc - Allocate a new CT entry
+ *
+ * Parameters:
+ * @xdp_ctx - Pointer to ctx (xdp_md) in XDP program
+ * Cannot be NULL
+ * @bpf_tuple - Pointer to memory representing the tuple to look up
+ * Cannot be NULL
+ * @tuple__sz - Length of the tuple structure
+ * Must be one of sizeof(bpf_tuple->ipv4) or
+ * sizeof(bpf_tuple->ipv6)
+ * @opts - Additional options for allocation (documented above)
+ * Cannot be NULL
+ * @opts__sz - Length of the bpf_ct_opts structure
+ * Must be NF_BPF_CT_OPTS_SZ (12)
+ */
+struct nf_conn___init *
+bpf_xdp_ct_alloc(struct xdp_md *xdp_ctx, struct bpf_sock_tuple *bpf_tuple,
+ u32 tuple__sz, struct bpf_ct_opts *opts, u32 opts__sz)
+{
+ struct xdp_buff *ctx = (struct xdp_buff *)xdp_ctx;
+ struct nf_conn *nfct;
+
+ nfct = __bpf_nf_ct_alloc_entry(dev_net(ctx->rxq->dev), bpf_tuple, tuple__sz,
+ opts, opts__sz, 10);
+ if (IS_ERR(nfct)) {
+ if (opts)
+ opts->error = PTR_ERR(nfct);
+ return NULL;
+ }
+
+ return (struct nf_conn___init *)nfct;
+}
+
/* bpf_xdp_ct_lookup - Lookup CT entry for the given tuple, and acquire a
* reference to it
*
@@ -138,25 +249,50 @@ bpf_xdp_ct_lookup(struct xdp_md *xdp_ctx, struct bpf_sock_tuple *bpf_tuple,
struct net *caller_net;
struct nf_conn *nfct;
- BUILD_BUG_ON(sizeof(struct bpf_ct_opts) != NF_BPF_CT_OPTS_SZ);
-
- if (!opts)
- return NULL;
- if (!bpf_tuple || opts->reserved[0] || opts->reserved[1] ||
- opts__sz != NF_BPF_CT_OPTS_SZ) {
- opts->error = -EINVAL;
- return NULL;
- }
caller_net = dev_net(ctx->rxq->dev);
- nfct = __bpf_nf_ct_lookup(caller_net, bpf_tuple, tuple__sz, opts->l4proto,
- opts->netns_id, &opts->dir);
+ nfct = __bpf_nf_ct_lookup(caller_net, bpf_tuple, tuple__sz, opts, opts__sz);
if (IS_ERR(nfct)) {
- opts->error = PTR_ERR(nfct);
+ if (opts)
+ opts->error = PTR_ERR(nfct);
return NULL;
}
return nfct;
}
+/* bpf_skb_ct_alloc - Allocate a new CT entry
+ *
+ * Parameters:
+ * @skb_ctx - Pointer to ctx (__sk_buff) in TC program
+ * Cannot be NULL
+ * @bpf_tuple - Pointer to memory representing the tuple to look up
+ * Cannot be NULL
+ * @tuple__sz - Length of the tuple structure
+ * Must be one of sizeof(bpf_tuple->ipv4) or
+ * sizeof(bpf_tuple->ipv6)
+ * @opts - Additional options for allocation (documented above)
+ * Cannot be NULL
+ * @opts__sz - Length of the bpf_ct_opts structure
+ * Must be NF_BPF_CT_OPTS_SZ (12)
+ */
+struct nf_conn___init *
+bpf_skb_ct_alloc(struct __sk_buff *skb_ctx, struct bpf_sock_tuple *bpf_tuple,
+ u32 tuple__sz, struct bpf_ct_opts *opts, u32 opts__sz)
+{
+ struct sk_buff *skb = (struct sk_buff *)skb_ctx;
+ struct nf_conn *nfct;
+ struct net *net;
+
+ net = skb->dev ? dev_net(skb->dev) : sock_net(skb->sk);
+ nfct = __bpf_nf_ct_alloc_entry(net, bpf_tuple, tuple__sz, opts, opts__sz, 10);
+ if (IS_ERR(nfct)) {
+ if (opts)
+ opts->error = PTR_ERR(nfct);
+ return NULL;
+ }
+
+ return (struct nf_conn___init *)nfct;
+}
+
/* bpf_skb_ct_lookup - Lookup CT entry for the given tuple, and acquire a
* reference to it
*
@@ -181,20 +317,31 @@ bpf_skb_ct_lookup(struct __sk_buff *skb_ctx, struct bpf_sock_tuple *bpf_tuple,
struct net *caller_net;
struct nf_conn *nfct;
- BUILD_BUG_ON(sizeof(struct bpf_ct_opts) != NF_BPF_CT_OPTS_SZ);
-
- if (!opts)
- return NULL;
- if (!bpf_tuple || opts->reserved[0] || opts->reserved[1] ||
- opts__sz != NF_BPF_CT_OPTS_SZ) {
- opts->error = -EINVAL;
- return NULL;
- }
caller_net = skb->dev ? dev_net(skb->dev) : sock_net(skb->sk);
- nfct = __bpf_nf_ct_lookup(caller_net, bpf_tuple, tuple__sz, opts->l4proto,
- opts->netns_id, &opts->dir);
+ nfct = __bpf_nf_ct_lookup(caller_net, bpf_tuple, tuple__sz, opts, opts__sz);
if (IS_ERR(nfct)) {
- opts->error = PTR_ERR(nfct);
+ if (opts)
+ opts->error = PTR_ERR(nfct);
+ return NULL;
+ }
+ return nfct;
+}
+
+/* bpf_ct_insert_entry - Add the provided entry into a CT map
+ *
+ * This must be invoked for referenced PTR_TO_BTF_ID.
+ *
+ * @nfct - Pointer to referenced nf_conn___init object, obtained
+ * using bpf_xdp_ct_alloc or bpf_skb_ct_alloc.
+ */
+struct nf_conn *bpf_ct_insert_entry(struct nf_conn___init *nfct_i)
+{
+ struct nf_conn *nfct = (struct nf_conn *)nfct_i;
+ int err;
+
+ err = nf_conntrack_hash_check_insert(nfct);
+ if (err < 0) {
+ nf_conntrack_free(nfct);
return NULL;
}
return nfct;
@@ -217,50 +364,90 @@ void bpf_ct_release(struct nf_conn *nfct)
nf_ct_put(nfct);
}
+/* bpf_ct_set_timeout - Set timeout of allocated nf_conn
+ *
+ * Sets the default timeout of newly allocated nf_conn before insertion.
+ * This helper must be invoked for refcounted pointer to nf_conn___init.
+ *
+ * Parameters:
+ * @nfct - Pointer to referenced nf_conn object, obtained using
+ * bpf_xdp_ct_alloc or bpf_skb_ct_alloc.
+ * @timeout - Timeout in msecs.
+ */
+void bpf_ct_set_timeout(struct nf_conn___init *nfct, u32 timeout)
+{
+ __nf_ct_set_timeout((struct nf_conn *)nfct, msecs_to_jiffies(timeout));
+}
+
+/* bpf_ct_change_timeout - Change timeout of inserted nf_conn
+ *
+ * Change timeout associated of the inserted or looked up nf_conn.
+ * This helper must be invoked for refcounted pointer to nf_conn.
+ *
+ * Parameters:
+ * @nfct - Pointer to referenced nf_conn object, obtained using
+ * bpf_ct_insert_entry, bpf_xdp_ct_lookup, or bpf_skb_ct_lookup.
+ * @timeout - New timeout in msecs.
+ */
+int bpf_ct_change_timeout(struct nf_conn *nfct, u32 timeout)
+{
+ return __nf_ct_change_timeout(nfct, msecs_to_jiffies(timeout));
+}
+
+/* bpf_ct_set_status - Set status field of allocated nf_conn
+ *
+ * Set the status field of the newly allocated nf_conn before insertion.
+ * This must be invoked for referenced PTR_TO_BTF_ID to nf_conn___init.
+ *
+ * Parameters:
+ * @nfct - Pointer to referenced nf_conn object, obtained using
+ * bpf_xdp_ct_alloc or bpf_skb_ct_alloc.
+ * @status - New status value.
+ */
+int bpf_ct_set_status(const struct nf_conn___init *nfct, u32 status)
+{
+ return nf_ct_change_status_common((struct nf_conn *)nfct, status);
+}
+
+/* bpf_ct_change_status - Change status of inserted nf_conn
+ *
+ * Change the status field of the provided connection tracking entry.
+ * This must be invoked for referenced PTR_TO_BTF_ID to nf_conn.
+ *
+ * Parameters:
+ * @nfct - Pointer to referenced nf_conn object, obtained using
+ * bpf_ct_insert_entry, bpf_xdp_ct_lookup or bpf_skb_ct_lookup.
+ * @status - New status value.
+ */
+int bpf_ct_change_status(struct nf_conn *nfct, u32 status)
+{
+ return nf_ct_change_status_common(nfct, status);
+}
+
__diag_pop()
-BTF_SET_START(nf_ct_xdp_check_kfunc_ids)
-BTF_ID(func, bpf_xdp_ct_lookup)
-BTF_ID(func, bpf_ct_release)
-BTF_SET_END(nf_ct_xdp_check_kfunc_ids)
-
-BTF_SET_START(nf_ct_tc_check_kfunc_ids)
-BTF_ID(func, bpf_skb_ct_lookup)
-BTF_ID(func, bpf_ct_release)
-BTF_SET_END(nf_ct_tc_check_kfunc_ids)
-
-BTF_SET_START(nf_ct_acquire_kfunc_ids)
-BTF_ID(func, bpf_xdp_ct_lookup)
-BTF_ID(func, bpf_skb_ct_lookup)
-BTF_SET_END(nf_ct_acquire_kfunc_ids)
-
-BTF_SET_START(nf_ct_release_kfunc_ids)
-BTF_ID(func, bpf_ct_release)
-BTF_SET_END(nf_ct_release_kfunc_ids)
-
-/* Both sets are identical */
-#define nf_ct_ret_null_kfunc_ids nf_ct_acquire_kfunc_ids
-
-static const struct btf_kfunc_id_set nf_conntrack_xdp_kfunc_set = {
- .owner = THIS_MODULE,
- .check_set = &nf_ct_xdp_check_kfunc_ids,
- .acquire_set = &nf_ct_acquire_kfunc_ids,
- .release_set = &nf_ct_release_kfunc_ids,
- .ret_null_set = &nf_ct_ret_null_kfunc_ids,
-};
+BTF_SET8_START(nf_ct_kfunc_set)
+BTF_ID_FLAGS(func, bpf_xdp_ct_alloc, KF_ACQUIRE | KF_RET_NULL)
+BTF_ID_FLAGS(func, bpf_xdp_ct_lookup, KF_ACQUIRE | KF_RET_NULL)
+BTF_ID_FLAGS(func, bpf_skb_ct_alloc, KF_ACQUIRE | KF_RET_NULL)
+BTF_ID_FLAGS(func, bpf_skb_ct_lookup, KF_ACQUIRE | KF_RET_NULL)
+BTF_ID_FLAGS(func, bpf_ct_insert_entry, KF_ACQUIRE | KF_RET_NULL | KF_RELEASE)
+BTF_ID_FLAGS(func, bpf_ct_release, KF_RELEASE)
+BTF_ID_FLAGS(func, bpf_ct_set_timeout, KF_TRUSTED_ARGS)
+BTF_ID_FLAGS(func, bpf_ct_change_timeout, KF_TRUSTED_ARGS)
+BTF_ID_FLAGS(func, bpf_ct_set_status, KF_TRUSTED_ARGS)
+BTF_ID_FLAGS(func, bpf_ct_change_status, KF_TRUSTED_ARGS)
+BTF_SET8_END(nf_ct_kfunc_set)
-static const struct btf_kfunc_id_set nf_conntrack_tc_kfunc_set = {
- .owner = THIS_MODULE,
- .check_set = &nf_ct_tc_check_kfunc_ids,
- .acquire_set = &nf_ct_acquire_kfunc_ids,
- .release_set = &nf_ct_release_kfunc_ids,
- .ret_null_set = &nf_ct_ret_null_kfunc_ids,
+static const struct btf_kfunc_id_set nf_conntrack_kfunc_set = {
+ .owner = THIS_MODULE,
+ .set = &nf_ct_kfunc_set,
};
int register_nf_conntrack_bpf(void)
{
int ret;
- ret = register_btf_kfunc_id_set(BPF_PROG_TYPE_XDP, &nf_conntrack_xdp_kfunc_set);
- return ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_SCHED_CLS, &nf_conntrack_tc_kfunc_set);
+ ret = register_btf_kfunc_id_set(BPF_PROG_TYPE_XDP, &nf_conntrack_kfunc_set);
+ return ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_SCHED_CLS, &nf_conntrack_kfunc_set);
}
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index 082a2fd8d85b..66a0aa8dbc3b 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -2786,3 +2786,65 @@ err_expect:
free_percpu(net->ct.stat);
return ret;
}
+
+#if (IS_BUILTIN(CONFIG_NF_CONNTRACK) && IS_ENABLED(CONFIG_DEBUG_INFO_BTF)) || \
+ (IS_MODULE(CONFIG_NF_CONNTRACK) && IS_ENABLED(CONFIG_DEBUG_INFO_BTF_MODULES) || \
+ IS_ENABLED(CONFIG_NF_CT_NETLINK))
+
+/* ctnetlink code shared by both ctnetlink and nf_conntrack_bpf */
+
+int __nf_ct_change_timeout(struct nf_conn *ct, u64 timeout)
+{
+ if (test_bit(IPS_FIXED_TIMEOUT_BIT, &ct->status))
+ return -EPERM;
+
+ __nf_ct_set_timeout(ct, timeout);
+
+ if (test_bit(IPS_DYING_BIT, &ct->status))
+ return -ETIME;
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(__nf_ct_change_timeout);
+
+void __nf_ct_change_status(struct nf_conn *ct, unsigned long on, unsigned long off)
+{
+ unsigned int bit;
+
+ /* Ignore these unchangable bits */
+ on &= ~IPS_UNCHANGEABLE_MASK;
+ off &= ~IPS_UNCHANGEABLE_MASK;
+
+ for (bit = 0; bit < __IPS_MAX_BIT; bit++) {
+ if (on & (1 << bit))
+ set_bit(bit, &ct->status);
+ else if (off & (1 << bit))
+ clear_bit(bit, &ct->status);
+ }
+}
+EXPORT_SYMBOL_GPL(__nf_ct_change_status);
+
+int nf_ct_change_status_common(struct nf_conn *ct, unsigned int status)
+{
+ unsigned long d;
+
+ d = ct->status ^ status;
+
+ if (d & (IPS_EXPECTED|IPS_CONFIRMED|IPS_DYING))
+ /* unchangeable */
+ return -EBUSY;
+
+ if (d & IPS_SEEN_REPLY && !(status & IPS_SEEN_REPLY))
+ /* SEEN_REPLY bit can only be set */
+ return -EBUSY;
+
+ if (d & IPS_ASSURED && !(status & IPS_ASSURED))
+ /* ASSURED bit can only be set */
+ return -EBUSY;
+
+ __nf_ct_change_status(ct, status, 0);
+ return 0;
+}
+EXPORT_SYMBOL_GPL(nf_ct_change_status_common);
+
+#endif
diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c
index 722af5e309ba..e02832ef9b9f 100644
--- a/net/netfilter/nf_conntrack_netlink.c
+++ b/net/netfilter/nf_conntrack_netlink.c
@@ -1890,45 +1890,10 @@ ctnetlink_parse_nat_setup(struct nf_conn *ct,
}
#endif
-static void
-__ctnetlink_change_status(struct nf_conn *ct, unsigned long on,
- unsigned long off)
-{
- unsigned int bit;
-
- /* Ignore these unchangable bits */
- on &= ~IPS_UNCHANGEABLE_MASK;
- off &= ~IPS_UNCHANGEABLE_MASK;
-
- for (bit = 0; bit < __IPS_MAX_BIT; bit++) {
- if (on & (1 << bit))
- set_bit(bit, &ct->status);
- else if (off & (1 << bit))
- clear_bit(bit, &ct->status);
- }
-}
-
static int
ctnetlink_change_status(struct nf_conn *ct, const struct nlattr * const cda[])
{
- unsigned long d;
- unsigned int status = ntohl(nla_get_be32(cda[CTA_STATUS]));
- d = ct->status ^ status;
-
- if (d & (IPS_EXPECTED|IPS_CONFIRMED|IPS_DYING))
- /* unchangeable */
- return -EBUSY;
-
- if (d & IPS_SEEN_REPLY && !(status & IPS_SEEN_REPLY))
- /* SEEN_REPLY bit can only be set */
- return -EBUSY;
-
- if (d & IPS_ASSURED && !(status & IPS_ASSURED))
- /* ASSURED bit can only be set */
- return -EBUSY;
-
- __ctnetlink_change_status(ct, status, 0);
- return 0;
+ return nf_ct_change_status_common(ct, ntohl(nla_get_be32(cda[CTA_STATUS])));
}
static int
@@ -2023,16 +1988,7 @@ static int ctnetlink_change_helper(struct nf_conn *ct,
static int ctnetlink_change_timeout(struct nf_conn *ct,
const struct nlattr * const cda[])
{
- u64 timeout = (u64)ntohl(nla_get_be32(cda[CTA_TIMEOUT])) * HZ;
-
- if (timeout > INT_MAX)
- timeout = INT_MAX;
- WRITE_ONCE(ct->timeout, nfct_time_stamp + (u32)timeout);
-
- if (test_bit(IPS_DYING_BIT, &ct->status))
- return -ETIME;
-
- return 0;
+ return __nf_ct_change_timeout(ct, (u64)ntohl(nla_get_be32(cda[CTA_TIMEOUT])) * HZ);
}
#if defined(CONFIG_NF_CONNTRACK_MARK)
@@ -2292,9 +2248,7 @@ ctnetlink_create_conntrack(struct net *net,
goto err1;
timeout = (u64)ntohl(nla_get_be32(cda[CTA_TIMEOUT])) * HZ;
- if (timeout > INT_MAX)
- timeout = INT_MAX;
- ct->timeout = (u32)timeout + nfct_time_stamp;
+ __nf_ct_set_timeout(ct, timeout);
rcu_read_lock();
if (cda[CTA_HELP]) {
@@ -2836,7 +2790,7 @@ ctnetlink_update_status(struct nf_conn *ct, const struct nlattr * const cda[])
* unchangeable bits but do not error out. Also user programs
* are allowed to clear the bits that they are allowed to change.
*/
- __ctnetlink_change_status(ct, status, ~status);
+ __nf_ct_change_status(ct, status, ~status);
return 0;
}
diff --git a/tools/bpf/resolve_btfids/main.c b/tools/bpf/resolve_btfids/main.c
index 5d26f3c6f918..80cd7843c677 100644
--- a/tools/bpf/resolve_btfids/main.c
+++ b/tools/bpf/resolve_btfids/main.c
@@ -45,6 +45,19 @@
* .zero 4
* __BTF_ID__func__vfs_fallocate__4:
* .zero 4
+ *
+ * set8 - store symbol size into first 4 bytes and sort following
+ * ID list
+ *
+ * __BTF_ID__set8__list:
+ * .zero 8
+ * list:
+ * __BTF_ID__func__vfs_getattr__3:
+ * .zero 4
+ * .word (1 << 0) | (1 << 2)
+ * __BTF_ID__func__vfs_fallocate__5:
+ * .zero 4
+ * .word (1 << 3) | (1 << 1) | (1 << 2)
*/
#define _GNU_SOURCE
@@ -72,6 +85,7 @@
#define BTF_TYPEDEF "typedef"
#define BTF_FUNC "func"
#define BTF_SET "set"
+#define BTF_SET8 "set8"
#define ADDR_CNT 100
@@ -84,6 +98,7 @@ struct btf_id {
};
int addr_cnt;
bool is_set;
+ bool is_set8;
Elf64_Addr addr[ADDR_CNT];
};
@@ -231,14 +246,14 @@ static char *get_id(const char *prefix_end)
return id;
}
-static struct btf_id *add_set(struct object *obj, char *name)
+static struct btf_id *add_set(struct object *obj, char *name, bool is_set8)
{
/*
* __BTF_ID__set__name
* name = ^
* id = ^
*/
- char *id = name + sizeof(BTF_SET "__") - 1;
+ char *id = name + (is_set8 ? sizeof(BTF_SET8 "__") : sizeof(BTF_SET "__")) - 1;
int len = strlen(name);
if (id >= name + len) {
@@ -444,9 +459,21 @@ static int symbols_collect(struct object *obj)
} else if (!strncmp(prefix, BTF_FUNC, sizeof(BTF_FUNC) - 1)) {
obj->nr_funcs++;
id = add_symbol(&obj->funcs, prefix, sizeof(BTF_FUNC) - 1);
+ /* set8 */
+ } else if (!strncmp(prefix, BTF_SET8, sizeof(BTF_SET8) - 1)) {
+ id = add_set(obj, prefix, true);
+ /*
+ * SET8 objects store list's count, which is encoded
+ * in symbol's size, together with 'cnt' field hence
+ * that - 1.
+ */
+ if (id) {
+ id->cnt = sym.st_size / sizeof(uint64_t) - 1;
+ id->is_set8 = true;
+ }
/* set */
} else if (!strncmp(prefix, BTF_SET, sizeof(BTF_SET) - 1)) {
- id = add_set(obj, prefix);
+ id = add_set(obj, prefix, false);
/*
* SET objects store list's count, which is encoded
* in symbol's size, together with 'cnt' field hence
@@ -571,7 +598,8 @@ static int id_patch(struct object *obj, struct btf_id *id)
int *ptr = data->d_buf;
int i;
- if (!id->id && !id->is_set)
+ /* For set, set8, id->id may be 0 */
+ if (!id->id && !id->is_set && !id->is_set8)
pr_err("WARN: resolve_btfids: unresolved symbol %s\n", id->name);
for (i = 0; i < id->addr_cnt; i++) {
@@ -643,13 +671,13 @@ static int sets_patch(struct object *obj)
}
idx = idx / sizeof(int);
- base = &ptr[idx] + 1;
+ base = &ptr[idx] + (id->is_set8 ? 2 : 1);
cnt = ptr[idx];
pr_debug("sorting addr %5lu: cnt %6d [%s]\n",
(idx + 1) * sizeof(int), cnt, id->name);
- qsort(base, cnt, sizeof(int), cmp_id);
+ qsort(base, cnt, id->is_set8 ? sizeof(uint64_t) : sizeof(int), cmp_id);
next = rb_next(next);
}
diff --git a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c
index e585e1cefc77..792cb15bac40 100644
--- a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c
+++ b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c
@@ -148,13 +148,13 @@ static struct bin_attribute bin_attr_bpf_testmod_file __ro_after_init = {
.write = bpf_testmod_test_write,
};
-BTF_SET_START(bpf_testmod_check_kfunc_ids)
-BTF_ID(func, bpf_testmod_test_mod_kfunc)
-BTF_SET_END(bpf_testmod_check_kfunc_ids)
+BTF_SET8_START(bpf_testmod_check_kfunc_ids)
+BTF_ID_FLAGS(func, bpf_testmod_test_mod_kfunc)
+BTF_SET8_END(bpf_testmod_check_kfunc_ids)
static const struct btf_kfunc_id_set bpf_testmod_kfunc_set = {
- .owner = THIS_MODULE,
- .check_set = &bpf_testmod_check_kfunc_ids,
+ .owner = THIS_MODULE,
+ .set = &bpf_testmod_check_kfunc_ids,
};
extern int bpf_fentry_test1(int a);
diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_nf.c b/tools/testing/selftests/bpf/prog_tests/bpf_nf.c
index dd30b1e3a67c..7a74a1579076 100644
--- a/tools/testing/selftests/bpf/prog_tests/bpf_nf.c
+++ b/tools/testing/selftests/bpf/prog_tests/bpf_nf.c
@@ -2,13 +2,29 @@
#include <test_progs.h>
#include <network_helpers.h>
#include "test_bpf_nf.skel.h"
+#include "test_bpf_nf_fail.skel.h"
+
+static char log_buf[1024 * 1024];
+
+struct {
+ const char *prog_name;
+ const char *err_msg;
+} test_bpf_nf_fail_tests[] = {
+ { "alloc_release", "kernel function bpf_ct_release args#0 expected pointer to STRUCT nf_conn but" },
+ { "insert_insert", "kernel function bpf_ct_insert_entry args#0 expected pointer to STRUCT nf_conn___init but" },
+ { "lookup_insert", "kernel function bpf_ct_insert_entry args#0 expected pointer to STRUCT nf_conn___init but" },
+ { "set_timeout_after_insert", "kernel function bpf_ct_set_timeout args#0 expected pointer to STRUCT nf_conn___init but" },
+ { "set_status_after_insert", "kernel function bpf_ct_set_status args#0 expected pointer to STRUCT nf_conn___init but" },
+ { "change_timeout_after_alloc", "kernel function bpf_ct_change_timeout args#0 expected pointer to STRUCT nf_conn but" },
+ { "change_status_after_alloc", "kernel function bpf_ct_change_status args#0 expected pointer to STRUCT nf_conn but" },
+};
enum {
TEST_XDP,
TEST_TC_BPF,
};
-void test_bpf_nf_ct(int mode)
+static void test_bpf_nf_ct(int mode)
{
struct test_bpf_nf *skel;
int prog_fd, err;
@@ -39,14 +55,60 @@ void test_bpf_nf_ct(int mode)
ASSERT_EQ(skel->bss->test_enonet_netns_id, -ENONET, "Test ENONET for bad but valid netns_id");
ASSERT_EQ(skel->bss->test_enoent_lookup, -ENOENT, "Test ENOENT for failed lookup");
ASSERT_EQ(skel->bss->test_eafnosupport, -EAFNOSUPPORT, "Test EAFNOSUPPORT for invalid len__tuple");
+ ASSERT_EQ(skel->data->test_alloc_entry, 0, "Test for alloc new entry");
+ ASSERT_EQ(skel->data->test_insert_entry, 0, "Test for insert new entry");
+ ASSERT_EQ(skel->data->test_succ_lookup, 0, "Test for successful lookup");
+ /* allow some tolerance for test_delta_timeout value to avoid races. */
+ ASSERT_GT(skel->bss->test_delta_timeout, 8, "Test for min ct timeout update");
+ ASSERT_LE(skel->bss->test_delta_timeout, 10, "Test for max ct timeout update");
+ /* expected status is IPS_SEEN_REPLY */
+ ASSERT_EQ(skel->bss->test_status, 2, "Test for ct status update ");
end:
test_bpf_nf__destroy(skel);
}
+static void test_bpf_nf_ct_fail(const char *prog_name, const char *err_msg)
+{
+ LIBBPF_OPTS(bpf_object_open_opts, opts, .kernel_log_buf = log_buf,
+ .kernel_log_size = sizeof(log_buf),
+ .kernel_log_level = 1);
+ struct test_bpf_nf_fail *skel;
+ struct bpf_program *prog;
+ int ret;
+
+ skel = test_bpf_nf_fail__open_opts(&opts);
+ if (!ASSERT_OK_PTR(skel, "test_bpf_nf_fail__open"))
+ return;
+
+ prog = bpf_object__find_program_by_name(skel->obj, prog_name);
+ if (!ASSERT_OK_PTR(prog, "bpf_object__find_program_by_name"))
+ goto end;
+
+ bpf_program__set_autoload(prog, true);
+
+ ret = test_bpf_nf_fail__load(skel);
+ if (!ASSERT_ERR(ret, "test_bpf_nf_fail__load must fail"))
+ goto end;
+
+ if (!ASSERT_OK_PTR(strstr(log_buf, err_msg), "expected error message")) {
+ fprintf(stderr, "Expected: %s\n", err_msg);
+ fprintf(stderr, "Verifier: %s\n", log_buf);
+ }
+
+end:
+ test_bpf_nf_fail__destroy(skel);
+}
+
void test_bpf_nf(void)
{
+ int i;
if (test__start_subtest("xdp-ct"))
test_bpf_nf_ct(TEST_XDP);
if (test__start_subtest("tc-bpf-ct"))
test_bpf_nf_ct(TEST_TC_BPF);
+ for (i = 0; i < ARRAY_SIZE(test_bpf_nf_fail_tests); i++) {
+ if (test__start_subtest(test_bpf_nf_fail_tests[i].prog_name))
+ test_bpf_nf_ct_fail(test_bpf_nf_fail_tests[i].prog_name,
+ test_bpf_nf_fail_tests[i].err_msg);
+ }
}
diff --git a/tools/testing/selftests/bpf/progs/test_bpf_nf.c b/tools/testing/selftests/bpf/progs/test_bpf_nf.c
index f00a9731930e..196cd8dfe42a 100644
--- a/tools/testing/selftests/bpf/progs/test_bpf_nf.c
+++ b/tools/testing/selftests/bpf/progs/test_bpf_nf.c
@@ -8,6 +8,8 @@
#define EINVAL 22
#define ENOENT 2
+extern unsigned long CONFIG_HZ __kconfig;
+
int test_einval_bpf_tuple = 0;
int test_einval_reserved = 0;
int test_einval_netns_id = 0;
@@ -16,6 +18,11 @@ int test_eproto_l4proto = 0;
int test_enonet_netns_id = 0;
int test_enoent_lookup = 0;
int test_eafnosupport = 0;
+int test_alloc_entry = -EINVAL;
+int test_insert_entry = -EAFNOSUPPORT;
+int test_succ_lookup = -ENOENT;
+u32 test_delta_timeout = 0;
+u32 test_status = 0;
struct nf_conn;
@@ -26,31 +33,44 @@ struct bpf_ct_opts___local {
u8 reserved[3];
} __attribute__((preserve_access_index));
+struct nf_conn *bpf_xdp_ct_alloc(struct xdp_md *, struct bpf_sock_tuple *, u32,
+ struct bpf_ct_opts___local *, u32) __ksym;
struct nf_conn *bpf_xdp_ct_lookup(struct xdp_md *, struct bpf_sock_tuple *, u32,
struct bpf_ct_opts___local *, u32) __ksym;
+struct nf_conn *bpf_skb_ct_alloc(struct __sk_buff *, struct bpf_sock_tuple *, u32,
+ struct bpf_ct_opts___local *, u32) __ksym;
struct nf_conn *bpf_skb_ct_lookup(struct __sk_buff *, struct bpf_sock_tuple *, u32,
struct bpf_ct_opts___local *, u32) __ksym;
+struct nf_conn *bpf_ct_insert_entry(struct nf_conn *) __ksym;
void bpf_ct_release(struct nf_conn *) __ksym;
+void bpf_ct_set_timeout(struct nf_conn *, u32) __ksym;
+int bpf_ct_change_timeout(struct nf_conn *, u32) __ksym;
+int bpf_ct_set_status(struct nf_conn *, u32) __ksym;
+int bpf_ct_change_status(struct nf_conn *, u32) __ksym;
static __always_inline void
-nf_ct_test(struct nf_conn *(*func)(void *, struct bpf_sock_tuple *, u32,
- struct bpf_ct_opts___local *, u32),
+nf_ct_test(struct nf_conn *(*lookup_fn)(void *, struct bpf_sock_tuple *, u32,
+ struct bpf_ct_opts___local *, u32),
+ struct nf_conn *(*alloc_fn)(void *, struct bpf_sock_tuple *, u32,
+ struct bpf_ct_opts___local *, u32),
void *ctx)
{
struct bpf_ct_opts___local opts_def = { .l4proto = IPPROTO_TCP, .netns_id = -1 };
struct bpf_sock_tuple bpf_tuple;
struct nf_conn *ct;
+ int err;
__builtin_memset(&bpf_tuple, 0, sizeof(bpf_tuple.ipv4));
- ct = func(ctx, NULL, 0, &opts_def, sizeof(opts_def));
+ ct = lookup_fn(ctx, NULL, 0, &opts_def, sizeof(opts_def));
if (ct)
bpf_ct_release(ct);
else
test_einval_bpf_tuple = opts_def.error;
opts_def.reserved[0] = 1;
- ct = func(ctx, &bpf_tuple, sizeof(bpf_tuple.ipv4), &opts_def, sizeof(opts_def));
+ ct = lookup_fn(ctx, &bpf_tuple, sizeof(bpf_tuple.ipv4), &opts_def,
+ sizeof(opts_def));
opts_def.reserved[0] = 0;
opts_def.l4proto = IPPROTO_TCP;
if (ct)
@@ -59,21 +79,24 @@ nf_ct_test(struct nf_conn *(*func)(void *, struct bpf_sock_tuple *, u32,
test_einval_reserved = opts_def.error;
opts_def.netns_id = -2;
- ct = func(ctx, &bpf_tuple, sizeof(bpf_tuple.ipv4), &opts_def, sizeof(opts_def));
+ ct = lookup_fn(ctx, &bpf_tuple, sizeof(bpf_tuple.ipv4), &opts_def,
+ sizeof(opts_def));
opts_def.netns_id = -1;
if (ct)
bpf_ct_release(ct);
else
test_einval_netns_id = opts_def.error;
- ct = func(ctx, &bpf_tuple, sizeof(bpf_tuple.ipv4), &opts_def, sizeof(opts_def) - 1);
+ ct = lookup_fn(ctx, &bpf_tuple, sizeof(bpf_tuple.ipv4), &opts_def,
+ sizeof(opts_def) - 1);
if (ct)
bpf_ct_release(ct);
else
test_einval_len_opts = opts_def.error;
opts_def.l4proto = IPPROTO_ICMP;
- ct = func(ctx, &bpf_tuple, sizeof(bpf_tuple.ipv4), &opts_def, sizeof(opts_def));
+ ct = lookup_fn(ctx, &bpf_tuple, sizeof(bpf_tuple.ipv4), &opts_def,
+ sizeof(opts_def));
opts_def.l4proto = IPPROTO_TCP;
if (ct)
bpf_ct_release(ct);
@@ -81,37 +104,75 @@ nf_ct_test(struct nf_conn *(*func)(void *, struct bpf_sock_tuple *, u32,
test_eproto_l4proto = opts_def.error;
opts_def.netns_id = 0xf00f;
- ct = func(ctx, &bpf_tuple, sizeof(bpf_tuple.ipv4), &opts_def, sizeof(opts_def));
+ ct = lookup_fn(ctx, &bpf_tuple, sizeof(bpf_tuple.ipv4), &opts_def,
+ sizeof(opts_def));
opts_def.netns_id = -1;
if (ct)
bpf_ct_release(ct);
else
test_enonet_netns_id = opts_def.error;
- ct = func(ctx, &bpf_tuple, sizeof(bpf_tuple.ipv4), &opts_def, sizeof(opts_def));
+ ct = lookup_fn(ctx, &bpf_tuple, sizeof(bpf_tuple.ipv4), &opts_def,
+ sizeof(opts_def));
if (ct)
bpf_ct_release(ct);
else
test_enoent_lookup = opts_def.error;
- ct = func(ctx, &bpf_tuple, sizeof(bpf_tuple.ipv4) - 1, &opts_def, sizeof(opts_def));
+ ct = lookup_fn(ctx, &bpf_tuple, sizeof(bpf_tuple.ipv4) - 1, &opts_def,
+ sizeof(opts_def));
if (ct)
bpf_ct_release(ct);
else
test_eafnosupport = opts_def.error;
+
+ bpf_tuple.ipv4.saddr = bpf_get_prandom_u32(); /* src IP */
+ bpf_tuple.ipv4.daddr = bpf_get_prandom_u32(); /* dst IP */
+ bpf_tuple.ipv4.sport = bpf_get_prandom_u32(); /* src port */
+ bpf_tuple.ipv4.dport = bpf_get_prandom_u32(); /* dst port */
+
+ ct = alloc_fn(ctx, &bpf_tuple, sizeof(bpf_tuple.ipv4), &opts_def,
+ sizeof(opts_def));
+ if (ct) {
+ struct nf_conn *ct_ins;
+
+ bpf_ct_set_timeout(ct, 10000);
+ bpf_ct_set_status(ct, IPS_CONFIRMED);
+
+ ct_ins = bpf_ct_insert_entry(ct);
+ if (ct_ins) {
+ struct nf_conn *ct_lk;
+
+ ct_lk = lookup_fn(ctx, &bpf_tuple, sizeof(bpf_tuple.ipv4),
+ &opts_def, sizeof(opts_def));
+ if (ct_lk) {
+ /* update ct entry timeout */
+ bpf_ct_change_timeout(ct_lk, 10000);
+ test_delta_timeout = ct_lk->timeout - bpf_jiffies64();
+ test_delta_timeout /= CONFIG_HZ;
+ test_status = IPS_SEEN_REPLY;
+ bpf_ct_change_status(ct_lk, IPS_SEEN_REPLY);
+ bpf_ct_release(ct_lk);
+ test_succ_lookup = 0;
+ }
+ bpf_ct_release(ct_ins);
+ test_insert_entry = 0;
+ }
+ test_alloc_entry = 0;
+ }
}
SEC("xdp")
int nf_xdp_ct_test(struct xdp_md *ctx)
{
- nf_ct_test((void *)bpf_xdp_ct_lookup, ctx);
+ nf_ct_test((void *)bpf_xdp_ct_lookup, (void *)bpf_xdp_ct_alloc, ctx);
return 0;
}
SEC("tc")
int nf_skb_ct_test(struct __sk_buff *ctx)
{
- nf_ct_test((void *)bpf_skb_ct_lookup, ctx);
+ nf_ct_test((void *)bpf_skb_ct_lookup, (void *)bpf_skb_ct_alloc, ctx);
return 0;
}
diff --git a/tools/testing/selftests/bpf/progs/test_bpf_nf_fail.c b/tools/testing/selftests/bpf/progs/test_bpf_nf_fail.c
new file mode 100644
index 000000000000..bf79af15c808
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_bpf_nf_fail.c
@@ -0,0 +1,134 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <vmlinux.h>
+#include <bpf/bpf_tracing.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_core_read.h>
+
+struct nf_conn;
+
+struct bpf_ct_opts___local {
+ s32 netns_id;
+ s32 error;
+ u8 l4proto;
+ u8 reserved[3];
+} __attribute__((preserve_access_index));
+
+struct nf_conn *bpf_skb_ct_alloc(struct __sk_buff *, struct bpf_sock_tuple *, u32,
+ struct bpf_ct_opts___local *, u32) __ksym;
+struct nf_conn *bpf_skb_ct_lookup(struct __sk_buff *, struct bpf_sock_tuple *, u32,
+ struct bpf_ct_opts___local *, u32) __ksym;
+struct nf_conn *bpf_ct_insert_entry(struct nf_conn *) __ksym;
+void bpf_ct_release(struct nf_conn *) __ksym;
+void bpf_ct_set_timeout(struct nf_conn *, u32) __ksym;
+int bpf_ct_change_timeout(struct nf_conn *, u32) __ksym;
+int bpf_ct_set_status(struct nf_conn *, u32) __ksym;
+int bpf_ct_change_status(struct nf_conn *, u32) __ksym;
+
+SEC("?tc")
+int alloc_release(struct __sk_buff *ctx)
+{
+ struct bpf_ct_opts___local opts = {};
+ struct bpf_sock_tuple tup = {};
+ struct nf_conn *ct;
+
+ ct = bpf_skb_ct_alloc(ctx, &tup, sizeof(tup.ipv4), &opts, sizeof(opts));
+ if (!ct)
+ return 0;
+ bpf_ct_release(ct);
+ return 0;
+}
+
+SEC("?tc")
+int insert_insert(struct __sk_buff *ctx)
+{
+ struct bpf_ct_opts___local opts = {};
+ struct bpf_sock_tuple tup = {};
+ struct nf_conn *ct;
+
+ ct = bpf_skb_ct_alloc(ctx, &tup, sizeof(tup.ipv4), &opts, sizeof(opts));
+ if (!ct)
+ return 0;
+ ct = bpf_ct_insert_entry(ct);
+ if (!ct)
+ return 0;
+ ct = bpf_ct_insert_entry(ct);
+ return 0;
+}
+
+SEC("?tc")
+int lookup_insert(struct __sk_buff *ctx)
+{
+ struct bpf_ct_opts___local opts = {};
+ struct bpf_sock_tuple tup = {};
+ struct nf_conn *ct;
+
+ ct = bpf_skb_ct_lookup(ctx, &tup, sizeof(tup.ipv4), &opts, sizeof(opts));
+ if (!ct)
+ return 0;
+ bpf_ct_insert_entry(ct);
+ return 0;
+}
+
+SEC("?tc")
+int set_timeout_after_insert(struct __sk_buff *ctx)
+{
+ struct bpf_ct_opts___local opts = {};
+ struct bpf_sock_tuple tup = {};
+ struct nf_conn *ct;
+
+ ct = bpf_skb_ct_alloc(ctx, &tup, sizeof(tup.ipv4), &opts, sizeof(opts));
+ if (!ct)
+ return 0;
+ ct = bpf_ct_insert_entry(ct);
+ if (!ct)
+ return 0;
+ bpf_ct_set_timeout(ct, 0);
+ return 0;
+}
+
+SEC("?tc")
+int set_status_after_insert(struct __sk_buff *ctx)
+{
+ struct bpf_ct_opts___local opts = {};
+ struct bpf_sock_tuple tup = {};
+ struct nf_conn *ct;
+
+ ct = bpf_skb_ct_alloc(ctx, &tup, sizeof(tup.ipv4), &opts, sizeof(opts));
+ if (!ct)
+ return 0;
+ ct = bpf_ct_insert_entry(ct);
+ if (!ct)
+ return 0;
+ bpf_ct_set_status(ct, 0);
+ return 0;
+}
+
+SEC("?tc")
+int change_timeout_after_alloc(struct __sk_buff *ctx)
+{
+ struct bpf_ct_opts___local opts = {};
+ struct bpf_sock_tuple tup = {};
+ struct nf_conn *ct;
+
+ ct = bpf_skb_ct_alloc(ctx, &tup, sizeof(tup.ipv4), &opts, sizeof(opts));
+ if (!ct)
+ return 0;
+ bpf_ct_change_timeout(ct, 0);
+ return 0;
+}
+
+SEC("?tc")
+int change_status_after_alloc(struct __sk_buff *ctx)
+{
+ struct bpf_ct_opts___local opts = {};
+ struct bpf_sock_tuple tup = {};
+ struct nf_conn *ct;
+
+ ct = bpf_skb_ct_alloc(ctx, &tup, sizeof(tup.ipv4), &opts, sizeof(opts));
+ if (!ct)
+ return 0;
+ bpf_ct_change_status(ct, 0);
+ return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/verifier/bpf_loop_inline.c b/tools/testing/selftests/bpf/verifier/bpf_loop_inline.c
index 2d0023659d88..a535d41dc20d 100644
--- a/tools/testing/selftests/bpf/verifier/bpf_loop_inline.c
+++ b/tools/testing/selftests/bpf/verifier/bpf_loop_inline.c
@@ -251,6 +251,7 @@
.expected_insns = { PSEUDO_CALL_INSN() },
.unexpected_insns = { HELPER_CALL_INSN() },
.result = ACCEPT,
+ .prog_type = BPF_PROG_TYPE_TRACEPOINT,
.func_info = { { 0, MAIN_TYPE }, { 16, CALLBACK_TYPE } },
.func_info_cnt = 2,
BTF_TYPES
diff --git a/tools/testing/selftests/bpf/verifier/calls.c b/tools/testing/selftests/bpf/verifier/calls.c
index 743ed34c1238..3fb4f69b1962 100644
--- a/tools/testing/selftests/bpf/verifier/calls.c
+++ b/tools/testing/selftests/bpf/verifier/calls.c
@@ -219,6 +219,59 @@
.errstr = "variable ptr_ access var_off=(0x0; 0x7) disallowed",
},
{
+ "calls: invalid kfunc call: referenced arg needs refcounted PTR_TO_BTF_ID",
+ .insns = {
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -8),
+ BPF_ST_MEM(BPF_DW, BPF_REG_1, 0, 0),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, BPF_PSEUDO_KFUNC_CALL, 0, 0),
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
+ BPF_EXIT_INSN(),
+ BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, BPF_PSEUDO_KFUNC_CALL, 0, 0),
+ BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_6, 16),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, BPF_PSEUDO_KFUNC_CALL, 0, 0),
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .prog_type = BPF_PROG_TYPE_SCHED_CLS,
+ .fixup_kfunc_btf_id = {
+ { "bpf_kfunc_call_test_acquire", 3 },
+ { "bpf_kfunc_call_test_ref", 8 },
+ { "bpf_kfunc_call_test_ref", 10 },
+ },
+ .result_unpriv = REJECT,
+ .result = REJECT,
+ .errstr = "R1 must be referenced",
+},
+{
+ "calls: valid kfunc call: referenced arg needs refcounted PTR_TO_BTF_ID",
+ .insns = {
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -8),
+ BPF_ST_MEM(BPF_DW, BPF_REG_1, 0, 0),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, BPF_PSEUDO_KFUNC_CALL, 0, 0),
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
+ BPF_EXIT_INSN(),
+ BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, BPF_PSEUDO_KFUNC_CALL, 0, 0),
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, BPF_PSEUDO_KFUNC_CALL, 0, 0),
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .prog_type = BPF_PROG_TYPE_SCHED_CLS,
+ .fixup_kfunc_btf_id = {
+ { "bpf_kfunc_call_test_acquire", 3 },
+ { "bpf_kfunc_call_test_ref", 8 },
+ { "bpf_kfunc_call_test_release", 10 },
+ },
+ .result_unpriv = REJECT,
+ .result = ACCEPT,
+},
+{
"calls: basic sanity",
.insns = {
BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 2),