aboutsummaryrefslogtreecommitdiffstats
path: root/kernel/trace/bpf_trace.c
diff options
context:
space:
mode:
Diffstat (limited to 'kernel/trace/bpf_trace.c')
-rw-r--r--kernel/trace/bpf_trace.c740
1 files changed, 709 insertions, 31 deletions
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index ae9755037b7e..1ed08967fb97 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -17,6 +17,11 @@
#include <linux/error-injection.h>
#include <linux/btf_ids.h>
#include <linux/bpf_lsm.h>
+#include <linux/fprobe.h>
+#include <linux/bsearch.h>
+#include <linux/sort.h>
+#include <linux/key.h>
+#include <linux/verification.h>
#include <net/bpf_sk_storage.h>
@@ -77,6 +82,8 @@ u64 bpf_get_stack(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5);
static int bpf_btf_printf_prepare(struct btf_ptr *ptr, u32 btf_ptr_size,
u64 flags, const struct btf **btf,
s32 *btf_id);
+static u64 bpf_kprobe_multi_cookie(struct bpf_run_ctx *ctx);
+static u64 bpf_kprobe_multi_entry_ip(struct bpf_run_ctx *ctx);
/**
* trace_call_bpf - invoke BPF program
@@ -124,7 +131,10 @@ 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);
@@ -332,8 +342,6 @@ BPF_CALL_3(bpf_probe_write_user, void __user *, unsafe_ptr, const void *, src,
if (unlikely(in_interrupt() ||
current->flags & (PF_KTHREAD | PF_EXITING)))
return -EPERM;
- if (unlikely(uaccess_kernel()))
- return -EPERM;
if (unlikely(!nmi_uaccess_okay()))
return -EPERM;
@@ -345,7 +353,7 @@ static const struct bpf_func_proto bpf_probe_write_user_proto = {
.gpl_only = true,
.ret_type = RET_INTEGER,
.arg1_type = ARG_ANYTHING,
- .arg2_type = ARG_PTR_TO_MEM,
+ .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY,
.arg3_type = ARG_CONST_SIZE,
};
@@ -394,7 +402,7 @@ static const struct bpf_func_proto bpf_trace_printk_proto = {
.func = bpf_trace_printk,
.gpl_only = true,
.ret_type = RET_INTEGER,
- .arg1_type = ARG_PTR_TO_MEM,
+ .arg1_type = ARG_PTR_TO_MEM | MEM_RDONLY,
.arg2_type = ARG_CONST_SIZE,
};
@@ -450,9 +458,9 @@ static const struct bpf_func_proto bpf_trace_vprintk_proto = {
.func = bpf_trace_vprintk,
.gpl_only = true,
.ret_type = RET_INTEGER,
- .arg1_type = ARG_PTR_TO_MEM,
+ .arg1_type = ARG_PTR_TO_MEM | MEM_RDONLY,
.arg2_type = ARG_CONST_SIZE,
- .arg3_type = ARG_PTR_TO_MEM_OR_NULL,
+ .arg3_type = ARG_PTR_TO_MEM | PTR_MAYBE_NULL | MEM_RDONLY,
.arg4_type = ARG_CONST_SIZE_OR_ZERO,
};
@@ -492,9 +500,9 @@ static const struct bpf_func_proto bpf_seq_printf_proto = {
.ret_type = RET_INTEGER,
.arg1_type = ARG_PTR_TO_BTF_ID,
.arg1_btf_id = &btf_seq_file_ids[0],
- .arg2_type = ARG_PTR_TO_MEM,
+ .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY,
.arg3_type = ARG_CONST_SIZE,
- .arg4_type = ARG_PTR_TO_MEM_OR_NULL,
+ .arg4_type = ARG_PTR_TO_MEM | PTR_MAYBE_NULL | MEM_RDONLY,
.arg5_type = ARG_CONST_SIZE_OR_ZERO,
};
@@ -509,7 +517,7 @@ static const struct bpf_func_proto bpf_seq_write_proto = {
.ret_type = RET_INTEGER,
.arg1_type = ARG_PTR_TO_BTF_ID,
.arg1_btf_id = &btf_seq_file_ids[0],
- .arg2_type = ARG_PTR_TO_MEM,
+ .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY,
.arg3_type = ARG_CONST_SIZE_OR_ZERO,
};
@@ -533,7 +541,7 @@ static const struct bpf_func_proto bpf_seq_printf_btf_proto = {
.ret_type = RET_INTEGER,
.arg1_type = ARG_PTR_TO_BTF_ID,
.arg1_btf_id = &btf_seq_file_ids[0],
- .arg2_type = ARG_PTR_TO_MEM,
+ .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY,
.arg3_type = ARG_CONST_SIZE_OR_ZERO,
.arg4_type = ARG_ANYTHING,
};
@@ -679,6 +687,7 @@ BPF_CALL_5(bpf_perf_event_output, struct pt_regs *, regs, struct bpf_map *, map,
perf_sample_data_init(sd, 0, 0);
sd->raw = &raw;
+ sd->sample_flags |= PERF_SAMPLE_RAW;
err = __bpf_perf_event_output(regs, map, flags, sd);
@@ -694,7 +703,7 @@ static const struct bpf_func_proto bpf_perf_event_output_proto = {
.arg1_type = ARG_PTR_TO_CTX,
.arg2_type = ARG_CONST_MAP_PTR,
.arg3_type = ARG_ANYTHING,
- .arg4_type = ARG_PTR_TO_MEM,
+ .arg4_type = ARG_PTR_TO_MEM | MEM_RDONLY,
.arg5_type = ARG_CONST_SIZE_OR_ZERO,
};
@@ -737,6 +746,7 @@ u64 bpf_event_output(struct bpf_map *map, u64 flags, void *meta, u64 meta_size,
perf_fetch_caller_regs(regs);
perf_sample_data_init(sd, 0, 0);
sd->raw = &raw;
+ sd->sample_flags |= PERF_SAMPLE_RAW;
ret = __bpf_perf_event_output(regs, map, flags, sd);
out:
@@ -764,7 +774,7 @@ const struct bpf_func_proto bpf_get_current_task_btf_proto = {
.func = bpf_get_current_task_btf,
.gpl_only = true,
.ret_type = RET_PTR_TO_BTF_ID,
- .ret_btf_id = &btf_task_struct_ids[0],
+ .ret_btf_id = &btf_tracing_ids[BTF_TRACING_TYPE_TASK],
};
BPF_CALL_1(bpf_task_pt_regs, struct task_struct *, task)
@@ -779,7 +789,7 @@ const struct bpf_func_proto bpf_task_pt_regs_proto = {
.func = bpf_task_pt_regs,
.gpl_only = true,
.arg1_type = ARG_PTR_TO_BTF_ID,
- .arg1_btf_id = &btf_task_struct_ids[0],
+ .arg1_btf_id = &btf_tracing_ids[BTF_TRACING_TYPE_TASK],
.ret_type = RET_PTR_TO_BTF_ID,
.ret_btf_id = &bpf_task_pt_regs_ids[0],
};
@@ -835,8 +845,6 @@ static int bpf_send_signal_common(u32 sig, enum pid_type type)
*/
if (unlikely(current->flags & (PF_KTHREAD | PF_EXITING)))
return -EPERM;
- if (unlikely(uaccess_kernel()))
- return -EPERM;
if (unlikely(!nmi_uaccess_okay()))
return -EPERM;
@@ -1004,7 +1012,7 @@ const struct bpf_func_proto bpf_snprintf_btf_proto = {
.ret_type = RET_INTEGER,
.arg1_type = ARG_PTR_TO_MEM,
.arg2_type = ARG_CONST_SIZE,
- .arg3_type = ARG_PTR_TO_MEM,
+ .arg3_type = ARG_PTR_TO_MEM | MEM_RDONLY,
.arg4_type = ARG_CONST_SIZE,
.arg5_type = ARG_ANYTHING,
};
@@ -1012,7 +1020,7 @@ const struct bpf_func_proto bpf_snprintf_btf_proto = {
BPF_CALL_1(bpf_get_func_ip_tracing, void *, ctx)
{
/* This helper call is inlined by verifier. */
- return ((u64 *)ctx)[-1];
+ return ((u64 *)ctx)[-2];
}
static const struct bpf_func_proto bpf_get_func_ip_proto_tracing = {
@@ -1022,11 +1030,30 @@ static const struct bpf_func_proto bpf_get_func_ip_proto_tracing = {
.arg1_type = ARG_PTR_TO_CTX,
};
+#ifdef CONFIG_X86_KERNEL_IBT
+static unsigned long get_entry_ip(unsigned long fentry_ip)
+{
+ u32 instr;
+
+ /* Being extra safe in here in case entry ip is on the page-edge. */
+ if (get_kernel_nofault(instr, (u32 *) fentry_ip - 1))
+ return fentry_ip;
+ if (is_endbr(instr))
+ fentry_ip -= ENDBR_INSN_SIZE;
+ return fentry_ip;
+}
+#else
+#define get_entry_ip(fentry_ip) fentry_ip
+#endif
+
BPF_CALL_1(bpf_get_func_ip_kprobe, struct pt_regs *, regs)
{
struct kprobe *kp = kprobe_running();
- return kp ? (uintptr_t)kp->addr : 0;
+ if (!kp || !(kp->flags & KPROBE_FLAG_ON_FUNC_ENTRY))
+ return 0;
+
+ return get_entry_ip((uintptr_t)kp->addr);
}
static const struct bpf_func_proto bpf_get_func_ip_proto_kprobe = {
@@ -1036,6 +1063,30 @@ static const struct bpf_func_proto bpf_get_func_ip_proto_kprobe = {
.arg1_type = ARG_PTR_TO_CTX,
};
+BPF_CALL_1(bpf_get_func_ip_kprobe_multi, struct pt_regs *, regs)
+{
+ return bpf_kprobe_multi_entry_ip(current->bpf_ctx);
+}
+
+static const struct bpf_func_proto bpf_get_func_ip_proto_kprobe_multi = {
+ .func = bpf_get_func_ip_kprobe_multi,
+ .gpl_only = false,
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_PTR_TO_CTX,
+};
+
+BPF_CALL_1(bpf_get_attach_cookie_kprobe_multi, struct pt_regs *, regs)
+{
+ return bpf_kprobe_multi_cookie(current->bpf_ctx);
+}
+
+static const struct bpf_func_proto bpf_get_attach_cookie_proto_kmulti = {
+ .func = bpf_get_attach_cookie_kprobe_multi,
+ .gpl_only = false,
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_PTR_TO_CTX,
+};
+
BPF_CALL_1(bpf_get_attach_cookie_trace, void *, ctx)
{
struct bpf_trace_run_ctx *run_ctx;
@@ -1063,6 +1114,21 @@ 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
@@ -1091,6 +1157,231 @@ static const struct bpf_func_proto bpf_get_branch_snapshot_proto = {
.arg2_type = ARG_CONST_SIZE_OR_ZERO,
};
+BPF_CALL_3(get_func_arg, void *, ctx, u32, n, u64 *, value)
+{
+ /* This helper call is inlined by verifier. */
+ u64 nr_args = ((u64 *)ctx)[-1];
+
+ if ((u64) n >= nr_args)
+ return -EINVAL;
+ *value = ((u64 *)ctx)[n];
+ return 0;
+}
+
+static const struct bpf_func_proto bpf_get_func_arg_proto = {
+ .func = get_func_arg,
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_PTR_TO_CTX,
+ .arg2_type = ARG_ANYTHING,
+ .arg3_type = ARG_PTR_TO_LONG,
+};
+
+BPF_CALL_2(get_func_ret, void *, ctx, u64 *, value)
+{
+ /* This helper call is inlined by verifier. */
+ u64 nr_args = ((u64 *)ctx)[-1];
+
+ *value = ((u64 *)ctx)[nr_args];
+ return 0;
+}
+
+static const struct bpf_func_proto bpf_get_func_ret_proto = {
+ .func = get_func_ret,
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_PTR_TO_CTX,
+ .arg2_type = ARG_PTR_TO_LONG,
+};
+
+BPF_CALL_1(get_func_arg_cnt, void *, ctx)
+{
+ /* This helper call is inlined by verifier. */
+ return ((u64 *)ctx)[-1];
+}
+
+static const struct bpf_func_proto bpf_get_func_arg_cnt_proto = {
+ .func = get_func_arg_cnt,
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_PTR_TO_CTX,
+};
+
+#ifdef CONFIG_KEYS
+__diag_push();
+__diag_ignore_all("-Wmissing-prototypes",
+ "kfuncs which will be used in BPF programs");
+
+/**
+ * bpf_lookup_user_key - lookup a key by its serial
+ * @serial: key handle serial number
+ * @flags: lookup-specific flags
+ *
+ * Search a key with a given *serial* and the provided *flags*.
+ * If found, increment the reference count of the key by one, and
+ * return it in the bpf_key structure.
+ *
+ * The bpf_key structure must be passed to bpf_key_put() when done
+ * with it, so that the key reference count is decremented and the
+ * bpf_key structure is freed.
+ *
+ * Permission checks are deferred to the time the key is used by
+ * one of the available key-specific kfuncs.
+ *
+ * Set *flags* with KEY_LOOKUP_CREATE, to attempt creating a requested
+ * special keyring (e.g. session keyring), if it doesn't yet exist.
+ * Set *flags* with KEY_LOOKUP_PARTIAL, to lookup a key without waiting
+ * for the key construction, and to retrieve uninstantiated keys (keys
+ * without data attached to them).
+ *
+ * Return: a bpf_key pointer with a valid key pointer if the key is found, a
+ * NULL pointer otherwise.
+ */
+struct bpf_key *bpf_lookup_user_key(u32 serial, u64 flags)
+{
+ key_ref_t key_ref;
+ struct bpf_key *bkey;
+
+ if (flags & ~KEY_LOOKUP_ALL)
+ return NULL;
+
+ /*
+ * Permission check is deferred until the key is used, as the
+ * intent of the caller is unknown here.
+ */
+ key_ref = lookup_user_key(serial, flags, KEY_DEFER_PERM_CHECK);
+ if (IS_ERR(key_ref))
+ return NULL;
+
+ bkey = kmalloc(sizeof(*bkey), GFP_KERNEL);
+ if (!bkey) {
+ key_put(key_ref_to_ptr(key_ref));
+ return NULL;
+ }
+
+ bkey->key = key_ref_to_ptr(key_ref);
+ bkey->has_ref = true;
+
+ return bkey;
+}
+
+/**
+ * bpf_lookup_system_key - lookup a key by a system-defined ID
+ * @id: key ID
+ *
+ * Obtain a bpf_key structure with a key pointer set to the passed key ID.
+ * The key pointer is marked as invalid, to prevent bpf_key_put() from
+ * attempting to decrement the key reference count on that pointer. The key
+ * pointer set in such way is currently understood only by
+ * verify_pkcs7_signature().
+ *
+ * Set *id* to one of the values defined in include/linux/verification.h:
+ * 0 for the primary keyring (immutable keyring of system keys);
+ * VERIFY_USE_SECONDARY_KEYRING for both the primary and secondary keyring
+ * (where keys can be added only if they are vouched for by existing keys
+ * in those keyrings); VERIFY_USE_PLATFORM_KEYRING for the platform
+ * keyring (primarily used by the integrity subsystem to verify a kexec'ed
+ * kerned image and, possibly, the initramfs signature).
+ *
+ * Return: a bpf_key pointer with an invalid key pointer set from the
+ * pre-determined ID on success, a NULL pointer otherwise
+ */
+struct bpf_key *bpf_lookup_system_key(u64 id)
+{
+ struct bpf_key *bkey;
+
+ if (system_keyring_id_check(id) < 0)
+ return NULL;
+
+ bkey = kmalloc(sizeof(*bkey), GFP_ATOMIC);
+ if (!bkey)
+ return NULL;
+
+ bkey->key = (struct key *)(unsigned long)id;
+ bkey->has_ref = false;
+
+ return bkey;
+}
+
+/**
+ * bpf_key_put - decrement key reference count if key is valid and free bpf_key
+ * @bkey: bpf_key structure
+ *
+ * Decrement the reference count of the key inside *bkey*, if the pointer
+ * is valid, and free *bkey*.
+ */
+void bpf_key_put(struct bpf_key *bkey)
+{
+ if (bkey->has_ref)
+ key_put(bkey->key);
+
+ kfree(bkey);
+}
+
+#ifdef CONFIG_SYSTEM_DATA_VERIFICATION
+/**
+ * bpf_verify_pkcs7_signature - verify a PKCS#7 signature
+ * @data_ptr: data to verify
+ * @sig_ptr: signature of the data
+ * @trusted_keyring: keyring with keys trusted for signature verification
+ *
+ * Verify the PKCS#7 signature *sig_ptr* against the supplied *data_ptr*
+ * with keys in a keyring referenced by *trusted_keyring*.
+ *
+ * Return: 0 on success, a negative value on error.
+ */
+int bpf_verify_pkcs7_signature(struct bpf_dynptr_kern *data_ptr,
+ struct bpf_dynptr_kern *sig_ptr,
+ struct bpf_key *trusted_keyring)
+{
+ int ret;
+
+ if (trusted_keyring->has_ref) {
+ /*
+ * Do the permission check deferred in bpf_lookup_user_key().
+ * See bpf_lookup_user_key() for more details.
+ *
+ * A call to key_task_permission() here would be redundant, as
+ * it is already done by keyring_search() called by
+ * find_asymmetric_key().
+ */
+ ret = key_validate(trusted_keyring->key);
+ if (ret < 0)
+ return ret;
+ }
+
+ return verify_pkcs7_signature(data_ptr->data,
+ bpf_dynptr_get_size(data_ptr),
+ sig_ptr->data,
+ bpf_dynptr_get_size(sig_ptr),
+ trusted_keyring->key,
+ VERIFYING_UNSPECIFIED_SIGNATURE, NULL,
+ NULL);
+}
+#endif /* CONFIG_SYSTEM_DATA_VERIFICATION */
+
+__diag_pop();
+
+BTF_SET8_START(key_sig_kfunc_set)
+BTF_ID_FLAGS(func, bpf_lookup_user_key, KF_ACQUIRE | KF_RET_NULL | KF_SLEEPABLE)
+BTF_ID_FLAGS(func, bpf_lookup_system_key, KF_ACQUIRE | KF_RET_NULL)
+BTF_ID_FLAGS(func, bpf_key_put, KF_RELEASE)
+#ifdef CONFIG_SYSTEM_DATA_VERIFICATION
+BTF_ID_FLAGS(func, bpf_verify_pkcs7_signature, KF_SLEEPABLE)
+#endif
+BTF_SET8_END(key_sig_kfunc_set)
+
+static const struct btf_kfunc_id_set bpf_key_sig_kfunc_set = {
+ .owner = THIS_MODULE,
+ .set = &key_sig_kfunc_set,
+};
+
+static int __init bpf_key_sig_kfuncs_init(void)
+{
+ return register_btf_kfunc_id_set(BPF_PROG_TYPE_TRACING,
+ &bpf_key_sig_kfunc_set);
+}
+
+late_initcall(bpf_key_sig_kfuncs_init);
+#endif /* CONFIG_KEYS */
+
static const struct bpf_func_proto *
bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
{
@@ -1107,6 +1398,8 @@ 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:
@@ -1188,6 +1481,8 @@ bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
return &bpf_get_task_stack_proto;
case BPF_FUNC_copy_from_user:
return prog->aux->sleepable ? &bpf_copy_from_user_proto : NULL;
+ case BPF_FUNC_copy_from_user_task:
+ return prog->aux->sleepable ? &bpf_copy_from_user_task_proto : NULL;
case BPF_FUNC_snprintf_btf:
return &bpf_snprintf_btf_proto;
case BPF_FUNC_per_cpu_ptr:
@@ -1206,6 +1501,8 @@ bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
return &bpf_get_func_ip_proto_tracing;
case BPF_FUNC_get_branch_snapshot:
return &bpf_get_branch_snapshot_proto;
+ case BPF_FUNC_find_vma:
+ return &bpf_find_vma_proto;
case BPF_FUNC_trace_vprintk:
return bpf_get_trace_vprintk_proto();
default:
@@ -1228,9 +1525,13 @@ kprobe_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
return &bpf_override_return_proto;
#endif
case BPF_FUNC_get_func_ip:
- return &bpf_get_func_ip_proto_kprobe;
+ return prog->expected_attach_type == BPF_TRACE_KPROBE_MULTI ?
+ &bpf_get_func_ip_proto_kprobe_multi :
+ &bpf_get_func_ip_proto_kprobe;
case BPF_FUNC_get_attach_cookie:
- return &bpf_get_attach_cookie_proto_trace;
+ return prog->expected_attach_type == BPF_TRACE_KPROBE_MULTI ?
+ &bpf_get_attach_cookie_proto_kmulti :
+ &bpf_get_attach_cookie_proto_trace;
default:
return bpf_tracing_func_proto(func_id, prog);
}
@@ -1285,7 +1586,7 @@ static const struct bpf_func_proto bpf_perf_event_output_proto_tp = {
.arg1_type = ARG_PTR_TO_CTX,
.arg2_type = ARG_CONST_MAP_PTR,
.arg3_type = ARG_ANYTHING,
- .arg4_type = ARG_PTR_TO_MEM,
+ .arg4_type = ARG_PTR_TO_MEM | MEM_RDONLY,
.arg5_type = ARG_CONST_SIZE_OR_ZERO,
};
@@ -1400,9 +1701,6 @@ static const struct bpf_func_proto bpf_perf_prog_read_value_proto = {
BPF_CALL_4(bpf_read_branch_records, struct bpf_perf_event_data_kern *, ctx,
void *, buf, u32, size, u64, flags)
{
-#ifndef CONFIG_X86
- return -ENOENT;
-#else
static const u32 br_entry_size = sizeof(struct perf_branch_entry);
struct perf_branch_stack *br_stack = ctx->data->br_stack;
u32 to_copy;
@@ -1410,8 +1708,11 @@ BPF_CALL_4(bpf_read_branch_records, struct bpf_perf_event_data_kern *, ctx,
if (unlikely(flags & ~BPF_F_GET_BRANCH_RECORDS_SIZE))
return -EINVAL;
+ if (unlikely(!(ctx->data->sample_flags & PERF_SAMPLE_BRANCH_STACK)))
+ return -ENOENT;
+
if (unlikely(!br_stack))
- return -EINVAL;
+ return -ENOENT;
if (flags & BPF_F_GET_BRANCH_RECORDS_SIZE)
return br_stack->nr * br_entry_size;
@@ -1423,7 +1724,6 @@ BPF_CALL_4(bpf_read_branch_records, struct bpf_perf_event_data_kern *, ctx,
memcpy(buf, br_stack->entries, to_copy);
return to_copy;
-#endif
}
static const struct bpf_func_proto bpf_read_branch_records_proto = {
@@ -1511,12 +1811,13 @@ static const struct bpf_func_proto bpf_perf_event_output_proto_raw_tp = {
.arg1_type = ARG_PTR_TO_CTX,
.arg2_type = ARG_CONST_MAP_PTR,
.arg3_type = ARG_ANYTHING,
- .arg4_type = ARG_PTR_TO_MEM,
+ .arg4_type = ARG_PTR_TO_MEM | MEM_RDONLY,
.arg5_type = ARG_CONST_SIZE_OR_ZERO,
};
extern const struct bpf_func_proto bpf_skb_output_proto;
extern const struct bpf_func_proto bpf_xdp_output_proto;
+extern const struct bpf_func_proto bpf_xdp_get_buff_len_trace_proto;
BPF_CALL_3(bpf_get_stackid_raw_tp, struct bpf_raw_tracepoint_args *, args,
struct bpf_map *, map, u64, flags)
@@ -1565,7 +1866,7 @@ static const struct bpf_func_proto bpf_get_stack_proto_raw_tp = {
.gpl_only = true,
.ret_type = RET_INTEGER,
.arg1_type = ARG_PTR_TO_CTX,
- .arg2_type = ARG_PTR_TO_MEM,
+ .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY,
.arg3_type = ARG_CONST_SIZE_OR_ZERO,
.arg4_type = ARG_ANYTHING,
};
@@ -1608,6 +1909,8 @@ 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:
@@ -1616,6 +1919,8 @@ tracing_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
return &bpf_sock_from_file_proto;
case BPF_FUNC_get_socket_cookie:
return &bpf_get_socket_ptr_cookie_proto;
+ case BPF_FUNC_xdp_get_buff_len:
+ return &bpf_xdp_get_buff_len_trace_proto;
#endif
case BPF_FUNC_seq_printf:
return prog->expected_attach_type == BPF_TRACE_ITER ?
@@ -1631,6 +1936,14 @@ tracing_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
NULL;
case BPF_FUNC_d_path:
return &bpf_d_path_proto;
+ case BPF_FUNC_get_func_arg:
+ return bpf_prog_has_trampoline(prog) ? &bpf_get_func_arg_proto : NULL;
+ case BPF_FUNC_get_func_ret:
+ 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)
@@ -1827,7 +2140,7 @@ int perf_event_attach_bpf_prog(struct perf_event *event,
event->prog = prog;
event->bpf_cookie = bpf_cookie;
rcu_assign_pointer(event->tp_event->prog_array, new_array);
- bpf_prog_array_free(old_array);
+ bpf_prog_array_free_sleepable(old_array);
unlock:
mutex_unlock(&bpf_event_mutex);
@@ -1853,7 +2166,7 @@ void perf_event_detach_bpf_prog(struct perf_event *event)
bpf_prog_array_delete_safe(old_array, event->prog);
} else {
rcu_assign_pointer(event->tp_event->prog_array, new_array);
- bpf_prog_array_free(old_array);
+ bpf_prog_array_free_sleepable(old_array);
}
bpf_prog_put(event->prog);
@@ -1933,9 +2246,15 @@ static __always_inline
void __bpf_trace_run(struct bpf_prog *prog, u64 *args)
{
cant_sleep();
+ if (unlikely(this_cpu_inc_return(*(prog->active)) != 1)) {
+ bpf_prog_inc_misses_counter(prog);
+ goto out;
+ }
rcu_read_lock();
(void) bpf_prog_run(prog, args);
rcu_read_unlock();
+out:
+ this_cpu_dec(*(prog->active));
}
#define UNPACK(...) __VA_ARGS__
@@ -2125,3 +2444,362 @@ static int __init bpf_event_init(void)
fs_initcall(bpf_event_init);
#endif /* CONFIG_MODULES */
+
+#ifdef CONFIG_FPROBE
+struct bpf_kprobe_multi_link {
+ struct bpf_link link;
+ struct fprobe fp;
+ unsigned long *addrs;
+ u64 *cookies;
+ u32 cnt;
+};
+
+struct bpf_kprobe_multi_run_ctx {
+ struct bpf_run_ctx run_ctx;
+ struct bpf_kprobe_multi_link *link;
+ 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_array(cnt, sizeof(*syms), GFP_KERNEL);
+ if (!syms)
+ goto error;
+
+ buf = kvmalloc_array(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;
+
+ kmulti_link = container_of(link, struct bpf_kprobe_multi_link, link);
+ unregister_fprobe(&kmulti_link->fp);
+}
+
+static void bpf_kprobe_multi_link_dealloc(struct bpf_link *link)
+{
+ struct bpf_kprobe_multi_link *kmulti_link;
+
+ kmulti_link = container_of(link, struct bpf_kprobe_multi_link, link);
+ kvfree(kmulti_link->addrs);
+ kvfree(kmulti_link->cookies);
+ kfree(kmulti_link);
+}
+
+static const struct bpf_link_ops bpf_kprobe_multi_link_lops = {
+ .release = bpf_kprobe_multi_link_release,
+ .dealloc = bpf_kprobe_multi_link_dealloc,
+};
+
+static void bpf_kprobe_multi_cookie_swap(void *a, void *b, int size, const void *priv)
+{
+ const struct bpf_kprobe_multi_link *link = priv;
+ unsigned long *addr_a = a, *addr_b = b;
+ u64 *cookie_a, *cookie_b;
+
+ 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 */
+ swap(*addr_a, *addr_b);
+ swap(*cookie_a, *cookie_b);
+}
+
+static int __bpf_kprobe_multi_cookie_cmp(const void *a, const void *b)
+{
+ const unsigned long *addr_a = a, *addr_b = b;
+
+ if (*addr_a == *addr_b)
+ return 0;
+ return *addr_a < *addr_b ? -1 : 1;
+}
+
+static int bpf_kprobe_multi_cookie_cmp(const void *a, const void *b, const void *priv)
+{
+ return __bpf_kprobe_multi_cookie_cmp(a, b);
+}
+
+static u64 bpf_kprobe_multi_cookie(struct bpf_run_ctx *ctx)
+{
+ struct bpf_kprobe_multi_run_ctx *run_ctx;
+ struct bpf_kprobe_multi_link *link;
+ u64 *cookie, entry_ip;
+ unsigned long *addr;
+
+ if (WARN_ON_ONCE(!ctx))
+ return 0;
+ run_ctx = container_of(current->bpf_ctx, struct bpf_kprobe_multi_run_ctx, run_ctx);
+ link = run_ctx->link;
+ if (!link->cookies)
+ return 0;
+ entry_ip = run_ctx->entry_ip;
+ addr = bsearch(&entry_ip, link->addrs, link->cnt, sizeof(entry_ip),
+ __bpf_kprobe_multi_cookie_cmp);
+ if (!addr)
+ return 0;
+ cookie = link->cookies + (addr - link->addrs);
+ return *cookie;
+}
+
+static u64 bpf_kprobe_multi_entry_ip(struct bpf_run_ctx *ctx)
+{
+ struct bpf_kprobe_multi_run_ctx *run_ctx;
+
+ run_ctx = container_of(current->bpf_ctx, struct bpf_kprobe_multi_run_ctx, run_ctx);
+ return run_ctx->entry_ip;
+}
+
+static int
+kprobe_multi_link_prog_run(struct bpf_kprobe_multi_link *link,
+ unsigned long entry_ip, struct pt_regs *regs)
+{
+ struct bpf_kprobe_multi_run_ctx run_ctx = {
+ .link = link,
+ .entry_ip = entry_ip,
+ };
+ struct bpf_run_ctx *old_run_ctx;
+ int err;
+
+ if (unlikely(__this_cpu_inc_return(bpf_prog_active) != 1)) {
+ err = 0;
+ goto out;
+ }
+
+ migrate_disable();
+ rcu_read_lock();
+ old_run_ctx = bpf_set_run_ctx(&run_ctx.run_ctx);
+ err = bpf_prog_run(link->link.prog, regs);
+ bpf_reset_run_ctx(old_run_ctx);
+ rcu_read_unlock();
+ migrate_enable();
+
+ out:
+ __this_cpu_dec(bpf_prog_active);
+ return err;
+}
+
+static void
+kprobe_multi_link_handler(struct fprobe *fp, unsigned long fentry_ip,
+ struct pt_regs *regs)
+{
+ struct bpf_kprobe_multi_link *link;
+
+ link = container_of(fp, struct bpf_kprobe_multi_link, fp);
+ kprobe_multi_link_prog_run(link, get_entry_ip(fentry_ip), regs);
+}
+
+static int symbols_cmp_r(const void *a, const void *b, const void *priv)
+{
+ const char **str_a = (const char **) a;
+ const char **str_b = (const char **) b;
+
+ return strcmp(*str_a, *str_b);
+}
+
+struct multi_symbols_sort {
+ const char **funcs;
+ u64 *cookies;
+};
+
+static void symbols_swap_r(void *a, void *b, int size, const void *priv)
+{
+ const struct multi_symbols_sort *data = priv;
+ const char **name_a = a, **name_b = b;
+
+ swap(*name_a, *name_b);
+
+ /* If defined, swap also related cookies. */
+ if (data->cookies) {
+ u64 *cookie_a, *cookie_b;
+
+ cookie_a = data->cookies + (name_a - data->funcs);
+ cookie_b = data->cookies + (name_b - data->funcs);
+ swap(*cookie_a, *cookie_b);
+ }
+}
+
+int bpf_kprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *prog)
+{
+ struct bpf_kprobe_multi_link *link = NULL;
+ struct bpf_link_primer link_primer;
+ void __user *ucookies;
+ unsigned long *addrs;
+ u32 flags, cnt, size;
+ void __user *uaddrs;
+ u64 *cookies = NULL;
+ void __user *usyms;
+ int err;
+
+ /* no support for 32bit archs yet */
+ if (sizeof(u64) != sizeof(void *))
+ return -EOPNOTSUPP;
+
+ if (prog->expected_attach_type != BPF_TRACE_KPROBE_MULTI)
+ return -EINVAL;
+
+ flags = attr->link_create.kprobe_multi.flags;
+ if (flags & ~BPF_F_KPROBE_MULTI_RETURN)
+ return -EINVAL;
+
+ uaddrs = u64_to_user_ptr(attr->link_create.kprobe_multi.addrs);
+ usyms = u64_to_user_ptr(attr->link_create.kprobe_multi.syms);
+ if (!!uaddrs == !!usyms)
+ return -EINVAL;
+
+ cnt = attr->link_create.kprobe_multi.cnt;
+ if (!cnt)
+ return -EINVAL;
+
+ size = cnt * sizeof(*addrs);
+ addrs = kvmalloc_array(cnt, sizeof(*addrs), GFP_KERNEL);
+ if (!addrs)
+ return -ENOMEM;
+
+ ucookies = u64_to_user_ptr(attr->link_create.kprobe_multi.cookies);
+ if (ucookies) {
+ cookies = kvmalloc_array(cnt, sizeof(*addrs), GFP_KERNEL);
+ if (!cookies) {
+ err = -ENOMEM;
+ goto error;
+ }
+ if (copy_from_user(cookies, ucookies, size)) {
+ err = -EFAULT;
+ goto error;
+ }
+ }
+
+ if (uaddrs) {
+ if (copy_from_user(addrs, uaddrs, size)) {
+ err = -EFAULT;
+ goto error;
+ }
+ } else {
+ struct multi_symbols_sort data = {
+ .cookies = cookies,
+ };
+ struct user_syms us;
+
+ err = copy_user_syms(&us, usyms, cnt);
+ if (err)
+ goto error;
+
+ if (cookies)
+ data.funcs = us.syms;
+
+ sort_r(us.syms, cnt, sizeof(*us.syms), symbols_cmp_r,
+ symbols_swap_r, &data);
+
+ err = ftrace_lookup_symbols(us.syms, cnt, addrs);
+ free_user_syms(&us);
+ if (err)
+ goto error;
+ }
+
+ link = kzalloc(sizeof(*link), GFP_KERNEL);
+ if (!link) {
+ err = -ENOMEM;
+ goto error;
+ }
+
+ bpf_link_init(&link->link, BPF_LINK_TYPE_KPROBE_MULTI,
+ &bpf_kprobe_multi_link_lops, prog);
+
+ err = bpf_link_prime(&link->link, &link_primer);
+ if (err)
+ goto error;
+
+ if (flags & BPF_F_KPROBE_MULTI_RETURN)
+ link->fp.exit_handler = kprobe_multi_link_handler;
+ else
+ link->fp.entry_handler = kprobe_multi_link_handler;
+
+ link->addrs = addrs;
+ link->cookies = cookies;
+ link->cnt = cnt;
+
+ if (cookies) {
+ /*
+ * Sorting addresses will trigger sorting cookies as well
+ * (check bpf_kprobe_multi_cookie_swap). This way we can
+ * find cookie based on the address in bpf_get_attach_cookie
+ * helper.
+ */
+ sort_r(addrs, cnt, sizeof(*addrs),
+ bpf_kprobe_multi_cookie_cmp,
+ bpf_kprobe_multi_cookie_swap,
+ link);
+ }
+
+ err = register_fprobe_ips(&link->fp, addrs, cnt);
+ if (err) {
+ bpf_link_cleanup(&link_primer);
+ return err;
+ }
+
+ return bpf_link_settle(&link_primer);
+
+error:
+ kfree(link);
+ kvfree(addrs);
+ kvfree(cookies);
+ return err;
+}
+#else /* !CONFIG_FPROBE */
+int bpf_kprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *prog)
+{
+ return -EOPNOTSUPP;
+}
+static u64 bpf_kprobe_multi_cookie(struct bpf_run_ctx *ctx)
+{
+ return 0;
+}
+static u64 bpf_kprobe_multi_entry_ip(struct bpf_run_ctx *ctx)
+{
+ return 0;
+}
+#endif