summaryrefslogtreecommitdiffstats
path: root/net/bpf
diff options
context:
space:
mode:
Diffstat (limited to '')
-rw-r--r--net/bpf/Makefile2
-rw-r--r--net/bpf/test_run.c904
-rw-r--r--net/bpfilter/.gitignore2
-rw-r--r--net/bpfilter/Kconfig23
-rw-r--r--net/bpfilter/Makefile20
-rw-r--r--net/bpfilter/bpfilter_kern.c136
-rw-r--r--net/bpfilter/bpfilter_umh_blob.S7
-rw-r--r--net/bpfilter/main.c64
-rw-r--r--net/bpfilter/msgfmt.h17
9 files changed, 1175 insertions, 0 deletions
diff --git a/net/bpf/Makefile b/net/bpf/Makefile
new file mode 100644
index 000000000..1c0a98d8c
--- /dev/null
+++ b/net/bpf/Makefile
@@ -0,0 +1,2 @@
+# SPDX-License-Identifier: GPL-2.0-only
+obj-$(CONFIG_BPF_SYSCALL) := test_run.o
diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c
new file mode 100644
index 000000000..7df14a0e3
--- /dev/null
+++ b/net/bpf/test_run.c
@@ -0,0 +1,904 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (c) 2017 Facebook
+ */
+#include <linux/bpf.h>
+#include <linux/slab.h>
+#include <linux/vmalloc.h>
+#include <linux/etherdevice.h>
+#include <linux/filter.h>
+#include <linux/sched/signal.h>
+#include <net/bpf_sk_storage.h>
+#include <net/sock.h>
+#include <net/tcp.h>
+#include <net/net_namespace.h>
+#include <linux/error-injection.h>
+#include <linux/smp.h>
+#include <linux/sock_diag.h>
+
+#define CREATE_TRACE_POINTS
+#include <trace/events/bpf_test_run.h>
+
+struct bpf_test_timer {
+ enum { NO_PREEMPT, NO_MIGRATE } mode;
+ u32 i;
+ u64 time_start, time_spent;
+};
+
+static void bpf_test_timer_enter(struct bpf_test_timer *t)
+ __acquires(rcu)
+{
+ rcu_read_lock();
+ if (t->mode == NO_PREEMPT)
+ preempt_disable();
+ else
+ migrate_disable();
+
+ t->time_start = ktime_get_ns();
+}
+
+static void bpf_test_timer_leave(struct bpf_test_timer *t)
+ __releases(rcu)
+{
+ t->time_start = 0;
+
+ if (t->mode == NO_PREEMPT)
+ preempt_enable();
+ else
+ migrate_enable();
+ rcu_read_unlock();
+}
+
+static bool bpf_test_timer_continue(struct bpf_test_timer *t, u32 repeat, int *err, u32 *duration)
+ __must_hold(rcu)
+{
+ t->i++;
+ if (t->i >= repeat) {
+ /* We're done. */
+ t->time_spent += ktime_get_ns() - t->time_start;
+ do_div(t->time_spent, t->i);
+ *duration = t->time_spent > U32_MAX ? U32_MAX : (u32)t->time_spent;
+ *err = 0;
+ goto reset;
+ }
+
+ if (signal_pending(current)) {
+ /* During iteration: we've been cancelled, abort. */
+ *err = -EINTR;
+ goto reset;
+ }
+
+ if (need_resched()) {
+ /* During iteration: we need to reschedule between runs. */
+ t->time_spent += ktime_get_ns() - t->time_start;
+ bpf_test_timer_leave(t);
+ cond_resched();
+ bpf_test_timer_enter(t);
+ }
+
+ /* Do another round. */
+ return true;
+
+reset:
+ t->i = 0;
+ return false;
+}
+
+static int bpf_test_run(struct bpf_prog *prog, void *ctx, u32 repeat,
+ u32 *retval, u32 *time, bool xdp)
+{
+ struct bpf_cgroup_storage *storage[MAX_BPF_CGROUP_STORAGE_TYPE] = { NULL };
+ struct bpf_test_timer t = { NO_MIGRATE };
+ enum bpf_cgroup_storage_type stype;
+ int ret;
+
+ for_each_cgroup_storage_type(stype) {
+ storage[stype] = bpf_cgroup_storage_alloc(prog, stype);
+ if (IS_ERR(storage[stype])) {
+ storage[stype] = NULL;
+ for_each_cgroup_storage_type(stype)
+ bpf_cgroup_storage_free(storage[stype]);
+ return -ENOMEM;
+ }
+ }
+
+ if (!repeat)
+ repeat = 1;
+
+ bpf_test_timer_enter(&t);
+ do {
+ ret = bpf_cgroup_storage_set(storage);
+ if (ret)
+ break;
+
+ if (xdp)
+ *retval = bpf_prog_run_xdp(prog, ctx);
+ else
+ *retval = BPF_PROG_RUN(prog, ctx);
+
+ bpf_cgroup_storage_unset();
+
+ } while (bpf_test_timer_continue(&t, repeat, &ret, time));
+ bpf_test_timer_leave(&t);
+
+ for_each_cgroup_storage_type(stype)
+ bpf_cgroup_storage_free(storage[stype]);
+
+ return ret;
+}
+
+static int bpf_test_finish(const union bpf_attr *kattr,
+ union bpf_attr __user *uattr, const void *data,
+ u32 size, u32 retval, u32 duration)
+{
+ void __user *data_out = u64_to_user_ptr(kattr->test.data_out);
+ int err = -EFAULT;
+ u32 copy_size = size;
+
+ /* Clamp copy if the user has provided a size hint, but copy the full
+ * buffer if not to retain old behaviour.
+ */
+ if (kattr->test.data_size_out &&
+ copy_size > kattr->test.data_size_out) {
+ copy_size = kattr->test.data_size_out;
+ err = -ENOSPC;
+ }
+
+ if (data_out && copy_to_user(data_out, data, copy_size))
+ goto out;
+ if (copy_to_user(&uattr->test.data_size_out, &size, sizeof(size)))
+ goto out;
+ if (copy_to_user(&uattr->test.retval, &retval, sizeof(retval)))
+ goto out;
+ if (copy_to_user(&uattr->test.duration, &duration, sizeof(duration)))
+ goto out;
+ if (err != -ENOSPC)
+ err = 0;
+out:
+ trace_bpf_test_finish(&err);
+ return err;
+}
+
+/* Integer types of various sizes and pointer combinations cover variety of
+ * architecture dependent calling conventions. 7+ can be supported in the
+ * future.
+ */
+__diag_push();
+__diag_ignore(GCC, 8, "-Wmissing-prototypes",
+ "Global functions as their definitions will be in vmlinux BTF");
+int noinline bpf_fentry_test1(int a)
+{
+ return a + 1;
+}
+
+int noinline bpf_fentry_test2(int a, u64 b)
+{
+ return a + b;
+}
+
+int noinline bpf_fentry_test3(char a, int b, u64 c)
+{
+ return a + b + c;
+}
+
+int noinline bpf_fentry_test4(void *a, char b, int c, u64 d)
+{
+ return (long)a + b + c + d;
+}
+
+int noinline bpf_fentry_test5(u64 a, void *b, short c, int d, u64 e)
+{
+ return a + (long)b + c + d + e;
+}
+
+int noinline bpf_fentry_test6(u64 a, void *b, short c, int d, void *e, u64 f)
+{
+ return a + (long)b + c + d + (long)e + f;
+}
+
+struct bpf_fentry_test_t {
+ struct bpf_fentry_test_t *a;
+};
+
+int noinline bpf_fentry_test7(struct bpf_fentry_test_t *arg)
+{
+ return (long)arg;
+}
+
+int noinline bpf_fentry_test8(struct bpf_fentry_test_t *arg)
+{
+ return (long)arg->a;
+}
+
+int noinline bpf_modify_return_test(int a, int *b)
+{
+ *b += 1;
+ return a + *b;
+}
+__diag_pop();
+
+ALLOW_ERROR_INJECTION(bpf_modify_return_test, ERRNO);
+
+static void *bpf_test_init(const union bpf_attr *kattr, u32 size,
+ u32 headroom, u32 tailroom)
+{
+ void __user *data_in = u64_to_user_ptr(kattr->test.data_in);
+ u32 user_size = kattr->test.data_size_in;
+ void *data;
+
+ if (size < ETH_HLEN || size > PAGE_SIZE - headroom - tailroom)
+ return ERR_PTR(-EINVAL);
+
+ if (user_size > size)
+ return ERR_PTR(-EMSGSIZE);
+
+ size = SKB_DATA_ALIGN(size);
+ data = kzalloc(size + headroom + tailroom, GFP_USER);
+ if (!data)
+ return ERR_PTR(-ENOMEM);
+
+ if (copy_from_user(data + headroom, data_in, user_size)) {
+ kfree(data);
+ return ERR_PTR(-EFAULT);
+ }
+
+ return data;
+}
+
+int bpf_prog_test_run_tracing(struct bpf_prog *prog,
+ const union bpf_attr *kattr,
+ union bpf_attr __user *uattr)
+{
+ struct bpf_fentry_test_t arg = {};
+ u16 side_effect = 0, ret = 0;
+ int b = 2, err = -EFAULT;
+ u32 retval = 0;
+
+ if (kattr->test.flags || kattr->test.cpu)
+ return -EINVAL;
+
+ switch (prog->expected_attach_type) {
+ case BPF_TRACE_FENTRY:
+ case BPF_TRACE_FEXIT:
+ if (bpf_fentry_test1(1) != 2 ||
+ bpf_fentry_test2(2, 3) != 5 ||
+ bpf_fentry_test3(4, 5, 6) != 15 ||
+ bpf_fentry_test4((void *)7, 8, 9, 10) != 34 ||
+ bpf_fentry_test5(11, (void *)12, 13, 14, 15) != 65 ||
+ bpf_fentry_test6(16, (void *)17, 18, 19, (void *)20, 21) != 111 ||
+ bpf_fentry_test7((struct bpf_fentry_test_t *)0) != 0 ||
+ bpf_fentry_test8(&arg) != 0)
+ goto out;
+ break;
+ case BPF_MODIFY_RETURN:
+ ret = bpf_modify_return_test(1, &b);
+ if (b != 2)
+ side_effect = 1;
+ break;
+ default:
+ goto out;
+ }
+
+ retval = ((u32)side_effect << 16) | ret;
+ if (copy_to_user(&uattr->test.retval, &retval, sizeof(retval)))
+ goto out;
+
+ err = 0;
+out:
+ trace_bpf_test_finish(&err);
+ return err;
+}
+
+struct bpf_raw_tp_test_run_info {
+ struct bpf_prog *prog;
+ void *ctx;
+ u32 retval;
+};
+
+static void
+__bpf_prog_test_run_raw_tp(void *data)
+{
+ struct bpf_raw_tp_test_run_info *info = data;
+
+ rcu_read_lock();
+ info->retval = BPF_PROG_RUN(info->prog, info->ctx);
+ rcu_read_unlock();
+}
+
+int bpf_prog_test_run_raw_tp(struct bpf_prog *prog,
+ const union bpf_attr *kattr,
+ union bpf_attr __user *uattr)
+{
+ void __user *ctx_in = u64_to_user_ptr(kattr->test.ctx_in);
+ __u32 ctx_size_in = kattr->test.ctx_size_in;
+ struct bpf_raw_tp_test_run_info info;
+ int cpu = kattr->test.cpu, err = 0;
+ int current_cpu;
+
+ /* doesn't support data_in/out, ctx_out, duration, or repeat */
+ if (kattr->test.data_in || kattr->test.data_out ||
+ kattr->test.ctx_out || kattr->test.duration ||
+ kattr->test.repeat)
+ return -EINVAL;
+
+ if (ctx_size_in < prog->aux->max_ctx_offset ||
+ ctx_size_in > MAX_BPF_FUNC_ARGS * sizeof(u64))
+ return -EINVAL;
+
+ if ((kattr->test.flags & BPF_F_TEST_RUN_ON_CPU) == 0 && cpu != 0)
+ return -EINVAL;
+
+ if (ctx_size_in) {
+ info.ctx = kzalloc(ctx_size_in, GFP_USER);
+ if (!info.ctx)
+ return -ENOMEM;
+ if (copy_from_user(info.ctx, ctx_in, ctx_size_in)) {
+ err = -EFAULT;
+ goto out;
+ }
+ } else {
+ info.ctx = NULL;
+ }
+
+ info.prog = prog;
+
+ current_cpu = get_cpu();
+ if ((kattr->test.flags & BPF_F_TEST_RUN_ON_CPU) == 0 ||
+ cpu == current_cpu) {
+ __bpf_prog_test_run_raw_tp(&info);
+ } else if (cpu >= nr_cpu_ids || !cpu_online(cpu)) {
+ /* smp_call_function_single() also checks cpu_online()
+ * after csd_lock(). However, since cpu is from user
+ * space, let's do an extra quick check to filter out
+ * invalid value before smp_call_function_single().
+ */
+ err = -ENXIO;
+ } else {
+ err = smp_call_function_single(cpu, __bpf_prog_test_run_raw_tp,
+ &info, 1);
+ }
+ put_cpu();
+
+ if (!err &&
+ copy_to_user(&uattr->test.retval, &info.retval, sizeof(u32)))
+ err = -EFAULT;
+
+out:
+ kfree(info.ctx);
+ return err;
+}
+
+static void *bpf_ctx_init(const union bpf_attr *kattr, u32 max_size)
+{
+ void __user *data_in = u64_to_user_ptr(kattr->test.ctx_in);
+ void __user *data_out = u64_to_user_ptr(kattr->test.ctx_out);
+ u32 size = kattr->test.ctx_size_in;
+ void *data;
+ int err;
+
+ if (!data_in && !data_out)
+ return NULL;
+
+ data = kzalloc(max_size, GFP_USER);
+ if (!data)
+ return ERR_PTR(-ENOMEM);
+
+ if (data_in) {
+ err = bpf_check_uarg_tail_zero(data_in, max_size, size);
+ if (err) {
+ kfree(data);
+ return ERR_PTR(err);
+ }
+
+ size = min_t(u32, max_size, size);
+ if (copy_from_user(data, data_in, size)) {
+ kfree(data);
+ return ERR_PTR(-EFAULT);
+ }
+ }
+ return data;
+}
+
+static int bpf_ctx_finish(const union bpf_attr *kattr,
+ union bpf_attr __user *uattr, const void *data,
+ u32 size)
+{
+ void __user *data_out = u64_to_user_ptr(kattr->test.ctx_out);
+ int err = -EFAULT;
+ u32 copy_size = size;
+
+ if (!data || !data_out)
+ return 0;
+
+ if (copy_size > kattr->test.ctx_size_out) {
+ copy_size = kattr->test.ctx_size_out;
+ err = -ENOSPC;
+ }
+
+ if (copy_to_user(data_out, data, copy_size))
+ goto out;
+ if (copy_to_user(&uattr->test.ctx_size_out, &size, sizeof(size)))
+ goto out;
+ if (err != -ENOSPC)
+ err = 0;
+out:
+ return err;
+}
+
+/**
+ * range_is_zero - test whether buffer is initialized
+ * @buf: buffer to check
+ * @from: check from this position
+ * @to: check up until (excluding) this position
+ *
+ * This function returns true if the there is a non-zero byte
+ * in the buf in the range [from,to).
+ */
+static inline bool range_is_zero(void *buf, size_t from, size_t to)
+{
+ return !memchr_inv((u8 *)buf + from, 0, to - from);
+}
+
+static int convert___skb_to_skb(struct sk_buff *skb, struct __sk_buff *__skb)
+{
+ struct qdisc_skb_cb *cb = (struct qdisc_skb_cb *)skb->cb;
+
+ if (!__skb)
+ return 0;
+
+ /* make sure the fields we don't use are zeroed */
+ if (!range_is_zero(__skb, 0, offsetof(struct __sk_buff, mark)))
+ return -EINVAL;
+
+ /* mark is allowed */
+
+ if (!range_is_zero(__skb, offsetofend(struct __sk_buff, mark),
+ offsetof(struct __sk_buff, priority)))
+ return -EINVAL;
+
+ /* priority is allowed */
+
+ if (!range_is_zero(__skb, offsetofend(struct __sk_buff, priority),
+ offsetof(struct __sk_buff, ifindex)))
+ return -EINVAL;
+
+ /* ifindex is allowed */
+
+ if (!range_is_zero(__skb, offsetofend(struct __sk_buff, ifindex),
+ offsetof(struct __sk_buff, cb)))
+ return -EINVAL;
+
+ /* cb is allowed */
+
+ if (!range_is_zero(__skb, offsetofend(struct __sk_buff, cb),
+ offsetof(struct __sk_buff, tstamp)))
+ return -EINVAL;
+
+ /* tstamp is allowed */
+ /* wire_len is allowed */
+ /* gso_segs is allowed */
+
+ if (!range_is_zero(__skb, offsetofend(struct __sk_buff, gso_segs),
+ offsetof(struct __sk_buff, gso_size)))
+ return -EINVAL;
+
+ /* gso_size is allowed */
+
+ if (!range_is_zero(__skb, offsetofend(struct __sk_buff, gso_size),
+ sizeof(struct __sk_buff)))
+ return -EINVAL;
+
+ skb->mark = __skb->mark;
+ skb->priority = __skb->priority;
+ skb->tstamp = __skb->tstamp;
+ memcpy(&cb->data, __skb->cb, QDISC_CB_PRIV_LEN);
+
+ if (__skb->wire_len == 0) {
+ cb->pkt_len = skb->len;
+ } else {
+ if (__skb->wire_len < skb->len ||
+ __skb->wire_len > GSO_MAX_SIZE)
+ return -EINVAL;
+ cb->pkt_len = __skb->wire_len;
+ }
+
+ if (__skb->gso_segs > GSO_MAX_SEGS)
+ return -EINVAL;
+ skb_shinfo(skb)->gso_segs = __skb->gso_segs;
+ skb_shinfo(skb)->gso_size = __skb->gso_size;
+
+ return 0;
+}
+
+static void convert_skb_to___skb(struct sk_buff *skb, struct __sk_buff *__skb)
+{
+ struct qdisc_skb_cb *cb = (struct qdisc_skb_cb *)skb->cb;
+
+ if (!__skb)
+ return;
+
+ __skb->mark = skb->mark;
+ __skb->priority = skb->priority;
+ __skb->ifindex = skb->dev->ifindex;
+ __skb->tstamp = skb->tstamp;
+ memcpy(__skb->cb, &cb->data, QDISC_CB_PRIV_LEN);
+ __skb->wire_len = cb->pkt_len;
+ __skb->gso_segs = skb_shinfo(skb)->gso_segs;
+}
+
+static struct proto bpf_dummy_proto = {
+ .name = "bpf_dummy",
+ .owner = THIS_MODULE,
+ .obj_size = sizeof(struct sock),
+};
+
+int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr,
+ union bpf_attr __user *uattr)
+{
+ bool is_l2 = false, is_direct_pkt_access = false;
+ struct net *net = current->nsproxy->net_ns;
+ struct net_device *dev = net->loopback_dev;
+ u32 size = kattr->test.data_size_in;
+ u32 repeat = kattr->test.repeat;
+ struct __sk_buff *ctx = NULL;
+ u32 retval, duration;
+ int hh_len = ETH_HLEN;
+ struct sk_buff *skb;
+ struct sock *sk;
+ void *data;
+ int ret;
+
+ if (kattr->test.flags || kattr->test.cpu)
+ return -EINVAL;
+
+ data = bpf_test_init(kattr, size, NET_SKB_PAD + NET_IP_ALIGN,
+ SKB_DATA_ALIGN(sizeof(struct skb_shared_info)));
+ if (IS_ERR(data))
+ return PTR_ERR(data);
+
+ ctx = bpf_ctx_init(kattr, sizeof(struct __sk_buff));
+ if (IS_ERR(ctx)) {
+ kfree(data);
+ return PTR_ERR(ctx);
+ }
+
+ switch (prog->type) {
+ case BPF_PROG_TYPE_SCHED_CLS:
+ case BPF_PROG_TYPE_SCHED_ACT:
+ is_l2 = true;
+ fallthrough;
+ case BPF_PROG_TYPE_LWT_IN:
+ case BPF_PROG_TYPE_LWT_OUT:
+ case BPF_PROG_TYPE_LWT_XMIT:
+ is_direct_pkt_access = true;
+ break;
+ default:
+ break;
+ }
+
+ sk = sk_alloc(net, AF_UNSPEC, GFP_USER, &bpf_dummy_proto, 1);
+ if (!sk) {
+ kfree(data);
+ kfree(ctx);
+ return -ENOMEM;
+ }
+ sock_init_data(NULL, sk);
+
+ skb = build_skb(data, 0);
+ if (!skb) {
+ kfree(data);
+ kfree(ctx);
+ sk_free(sk);
+ return -ENOMEM;
+ }
+ skb->sk = sk;
+
+ skb_reserve(skb, NET_SKB_PAD + NET_IP_ALIGN);
+ __skb_put(skb, size);
+ if (ctx && ctx->ifindex > 1) {
+ dev = dev_get_by_index(net, ctx->ifindex);
+ if (!dev) {
+ ret = -ENODEV;
+ goto out;
+ }
+ }
+ skb->protocol = eth_type_trans(skb, dev);
+ skb_reset_network_header(skb);
+
+ switch (skb->protocol) {
+ case htons(ETH_P_IP):
+ sk->sk_family = AF_INET;
+ if (sizeof(struct iphdr) <= skb_headlen(skb)) {
+ sk->sk_rcv_saddr = ip_hdr(skb)->saddr;
+ sk->sk_daddr = ip_hdr(skb)->daddr;
+ }
+ break;
+#if IS_ENABLED(CONFIG_IPV6)
+ case htons(ETH_P_IPV6):
+ sk->sk_family = AF_INET6;
+ if (sizeof(struct ipv6hdr) <= skb_headlen(skb)) {
+ sk->sk_v6_rcv_saddr = ipv6_hdr(skb)->saddr;
+ sk->sk_v6_daddr = ipv6_hdr(skb)->daddr;
+ }
+ break;
+#endif
+ default:
+ break;
+ }
+
+ if (is_l2)
+ __skb_push(skb, hh_len);
+ if (is_direct_pkt_access)
+ bpf_compute_data_pointers(skb);
+ ret = convert___skb_to_skb(skb, ctx);
+ if (ret)
+ goto out;
+ ret = bpf_test_run(prog, skb, repeat, &retval, &duration, false);
+ if (ret)
+ goto out;
+ if (!is_l2) {
+ if (skb_headroom(skb) < hh_len) {
+ int nhead = HH_DATA_ALIGN(hh_len - skb_headroom(skb));
+
+ if (pskb_expand_head(skb, nhead, 0, GFP_USER)) {
+ ret = -ENOMEM;
+ goto out;
+ }
+ }
+ memset(__skb_push(skb, hh_len), 0, hh_len);
+ }
+ convert_skb_to___skb(skb, ctx);
+
+ size = skb->len;
+ /* bpf program can never convert linear skb to non-linear */
+ if (WARN_ON_ONCE(skb_is_nonlinear(skb)))
+ size = skb_headlen(skb);
+ ret = bpf_test_finish(kattr, uattr, skb->data, size, retval, duration);
+ if (!ret)
+ ret = bpf_ctx_finish(kattr, uattr, ctx,
+ sizeof(struct __sk_buff));
+out:
+ if (dev && dev != net->loopback_dev)
+ dev_put(dev);
+ kfree_skb(skb);
+ sk_free(sk);
+ kfree(ctx);
+ return ret;
+}
+
+int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr,
+ union bpf_attr __user *uattr)
+{
+ u32 tailroom = SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
+ u32 headroom = XDP_PACKET_HEADROOM;
+ u32 size = kattr->test.data_size_in;
+ u32 repeat = kattr->test.repeat;
+ struct netdev_rx_queue *rxqueue;
+ struct xdp_buff xdp = {};
+ u32 retval, duration;
+ u32 max_data_sz;
+ void *data;
+ int ret;
+
+ if (prog->expected_attach_type == BPF_XDP_DEVMAP ||
+ prog->expected_attach_type == BPF_XDP_CPUMAP)
+ return -EINVAL;
+ if (kattr->test.ctx_in || kattr->test.ctx_out)
+ return -EINVAL;
+
+ /* XDP have extra tailroom as (most) drivers use full page */
+ max_data_sz = 4096 - headroom - tailroom;
+
+ data = bpf_test_init(kattr, max_data_sz, headroom, tailroom);
+ if (IS_ERR(data))
+ return PTR_ERR(data);
+
+ xdp.data_hard_start = data;
+ xdp.data = data + headroom;
+ xdp.data_meta = xdp.data;
+ xdp.data_end = xdp.data + size;
+ xdp.frame_sz = headroom + max_data_sz + tailroom;
+
+ rxqueue = __netif_get_rx_queue(current->nsproxy->net_ns->loopback_dev, 0);
+ xdp.rxq = &rxqueue->xdp_rxq;
+ bpf_prog_change_xdp(NULL, prog);
+ ret = bpf_test_run(prog, &xdp, repeat, &retval, &duration, true);
+ if (ret)
+ goto out;
+ if (xdp.data != data + headroom || xdp.data_end != xdp.data + size)
+ size = xdp.data_end - xdp.data;
+ ret = bpf_test_finish(kattr, uattr, xdp.data, size, retval, duration);
+out:
+ bpf_prog_change_xdp(prog, NULL);
+ kfree(data);
+ return ret;
+}
+
+static int verify_user_bpf_flow_keys(struct bpf_flow_keys *ctx)
+{
+ /* make sure the fields we don't use are zeroed */
+ if (!range_is_zero(ctx, 0, offsetof(struct bpf_flow_keys, flags)))
+ return -EINVAL;
+
+ /* flags is allowed */
+
+ if (!range_is_zero(ctx, offsetofend(struct bpf_flow_keys, flags),
+ sizeof(struct bpf_flow_keys)))
+ return -EINVAL;
+
+ return 0;
+}
+
+int bpf_prog_test_run_flow_dissector(struct bpf_prog *prog,
+ const union bpf_attr *kattr,
+ union bpf_attr __user *uattr)
+{
+ struct bpf_test_timer t = { NO_PREEMPT };
+ u32 size = kattr->test.data_size_in;
+ struct bpf_flow_dissector ctx = {};
+ u32 repeat = kattr->test.repeat;
+ struct bpf_flow_keys *user_ctx;
+ struct bpf_flow_keys flow_keys;
+ const struct ethhdr *eth;
+ unsigned int flags = 0;
+ u32 retval, duration;
+ void *data;
+ int ret;
+
+ if (prog->type != BPF_PROG_TYPE_FLOW_DISSECTOR)
+ return -EINVAL;
+
+ if (kattr->test.flags || kattr->test.cpu)
+ return -EINVAL;
+
+ if (size < ETH_HLEN)
+ return -EINVAL;
+
+ data = bpf_test_init(kattr, size, 0, 0);
+ if (IS_ERR(data))
+ return PTR_ERR(data);
+
+ eth = (struct ethhdr *)data;
+
+ if (!repeat)
+ repeat = 1;
+
+ user_ctx = bpf_ctx_init(kattr, sizeof(struct bpf_flow_keys));
+ if (IS_ERR(user_ctx)) {
+ kfree(data);
+ return PTR_ERR(user_ctx);
+ }
+ if (user_ctx) {
+ ret = verify_user_bpf_flow_keys(user_ctx);
+ if (ret)
+ goto out;
+ flags = user_ctx->flags;
+ }
+
+ ctx.flow_keys = &flow_keys;
+ ctx.data = data;
+ ctx.data_end = (__u8 *)data + size;
+
+ bpf_test_timer_enter(&t);
+ do {
+ retval = bpf_flow_dissect(prog, &ctx, eth->h_proto, ETH_HLEN,
+ size, flags);
+ } while (bpf_test_timer_continue(&t, repeat, &ret, &duration));
+ bpf_test_timer_leave(&t);
+
+ if (ret < 0)
+ goto out;
+
+ ret = bpf_test_finish(kattr, uattr, &flow_keys, sizeof(flow_keys),
+ retval, duration);
+ if (!ret)
+ ret = bpf_ctx_finish(kattr, uattr, user_ctx,
+ sizeof(struct bpf_flow_keys));
+
+out:
+ kfree(user_ctx);
+ kfree(data);
+ return ret;
+}
+
+int bpf_prog_test_run_sk_lookup(struct bpf_prog *prog, const union bpf_attr *kattr,
+ union bpf_attr __user *uattr)
+{
+ struct bpf_test_timer t = { NO_PREEMPT };
+ struct bpf_prog_array *progs = NULL;
+ struct bpf_sk_lookup_kern ctx = {};
+ u32 repeat = kattr->test.repeat;
+ struct bpf_sk_lookup *user_ctx;
+ u32 retval, duration;
+ int ret = -EINVAL;
+
+ if (prog->type != BPF_PROG_TYPE_SK_LOOKUP)
+ return -EINVAL;
+
+ if (kattr->test.flags || kattr->test.cpu)
+ return -EINVAL;
+
+ if (kattr->test.data_in || kattr->test.data_size_in || kattr->test.data_out ||
+ kattr->test.data_size_out)
+ return -EINVAL;
+
+ if (!repeat)
+ repeat = 1;
+
+ user_ctx = bpf_ctx_init(kattr, sizeof(*user_ctx));
+ if (IS_ERR(user_ctx))
+ return PTR_ERR(user_ctx);
+
+ if (!user_ctx)
+ return -EINVAL;
+
+ if (user_ctx->sk)
+ goto out;
+
+ if (!range_is_zero(user_ctx, offsetofend(typeof(*user_ctx), local_port), sizeof(*user_ctx)))
+ goto out;
+
+ if (user_ctx->local_port > U16_MAX || user_ctx->remote_port > U16_MAX) {
+ ret = -ERANGE;
+ goto out;
+ }
+
+ ctx.family = (u16)user_ctx->family;
+ ctx.protocol = (u16)user_ctx->protocol;
+ ctx.dport = (u16)user_ctx->local_port;
+ ctx.sport = (__force __be16)user_ctx->remote_port;
+
+ switch (ctx.family) {
+ case AF_INET:
+ ctx.v4.daddr = (__force __be32)user_ctx->local_ip4;
+ ctx.v4.saddr = (__force __be32)user_ctx->remote_ip4;
+ break;
+
+#if IS_ENABLED(CONFIG_IPV6)
+ case AF_INET6:
+ ctx.v6.daddr = (struct in6_addr *)user_ctx->local_ip6;
+ ctx.v6.saddr = (struct in6_addr *)user_ctx->remote_ip6;
+ break;
+#endif
+
+ default:
+ ret = -EAFNOSUPPORT;
+ goto out;
+ }
+
+ progs = bpf_prog_array_alloc(1, GFP_KERNEL);
+ if (!progs) {
+ ret = -ENOMEM;
+ goto out;
+ }
+
+ progs->items[0].prog = prog;
+
+ bpf_test_timer_enter(&t);
+ do {
+ ctx.selected_sk = NULL;
+ retval = BPF_PROG_SK_LOOKUP_RUN_ARRAY(progs, ctx, BPF_PROG_RUN);
+ } while (bpf_test_timer_continue(&t, repeat, &ret, &duration));
+ bpf_test_timer_leave(&t);
+
+ if (ret < 0)
+ goto out;
+
+ user_ctx->cookie = 0;
+ if (ctx.selected_sk) {
+ if (ctx.selected_sk->sk_reuseport && !ctx.no_reuseport) {
+ ret = -EOPNOTSUPP;
+ goto out;
+ }
+
+ user_ctx->cookie = sock_gen_cookie(ctx.selected_sk);
+ }
+
+ ret = bpf_test_finish(kattr, uattr, NULL, 0, retval, duration);
+ if (!ret)
+ ret = bpf_ctx_finish(kattr, uattr, user_ctx, sizeof(*user_ctx));
+
+out:
+ bpf_prog_array_free(progs);
+ kfree(user_ctx);
+ return ret;
+}
diff --git a/net/bpfilter/.gitignore b/net/bpfilter/.gitignore
new file mode 100644
index 000000000..f34e85ee8
--- /dev/null
+++ b/net/bpfilter/.gitignore
@@ -0,0 +1,2 @@
+# SPDX-License-Identifier: GPL-2.0-only
+bpfilter_umh
diff --git a/net/bpfilter/Kconfig b/net/bpfilter/Kconfig
new file mode 100644
index 000000000..8ad0233ce
--- /dev/null
+++ b/net/bpfilter/Kconfig
@@ -0,0 +1,23 @@
+# SPDX-License-Identifier: GPL-2.0-only
+menuconfig BPFILTER
+ bool "BPF based packet filtering framework (BPFILTER)"
+ depends on NET && BPF && INET
+ select USERMODE_DRIVER
+ help
+ This builds experimental bpfilter framework that is aiming to
+ provide netfilter compatible functionality via BPF
+
+if BPFILTER
+config BPFILTER_UMH
+ tristate "bpfilter kernel module with user mode helper"
+ depends on CC_CAN_LINK
+ depends on m || CC_CAN_LINK_STATIC
+ default m
+ help
+ This builds bpfilter kernel module with embedded user mode helper
+
+ Note: To compile this as built-in, your toolchain must support
+ building static binaries, since rootfs isn't mounted at the time
+ when __init functions are called and do_execv won't be able to find
+ the elf interpreter.
+endif
diff --git a/net/bpfilter/Makefile b/net/bpfilter/Makefile
new file mode 100644
index 000000000..cdac82b8c
--- /dev/null
+++ b/net/bpfilter/Makefile
@@ -0,0 +1,20 @@
+# SPDX-License-Identifier: GPL-2.0
+#
+# Makefile for the Linux BPFILTER layer.
+#
+
+userprogs := bpfilter_umh
+bpfilter_umh-objs := main.o
+userccflags += -I $(srctree)/tools/include/ -I $(srctree)/tools/include/uapi
+
+ifeq ($(CONFIG_BPFILTER_UMH), y)
+# builtin bpfilter_umh should be linked with -static
+# since rootfs isn't mounted at the time of __init
+# function is called and do_execv won't find elf interpreter
+userldflags += -static
+endif
+
+$(obj)/bpfilter_umh_blob.o: $(obj)/bpfilter_umh
+
+obj-$(CONFIG_BPFILTER_UMH) += bpfilter.o
+bpfilter-objs += bpfilter_kern.o bpfilter_umh_blob.o
diff --git a/net/bpfilter/bpfilter_kern.c b/net/bpfilter/bpfilter_kern.c
new file mode 100644
index 000000000..51a941b56
--- /dev/null
+++ b/net/bpfilter/bpfilter_kern.c
@@ -0,0 +1,136 @@
+// SPDX-License-Identifier: GPL-2.0
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/umh.h>
+#include <linux/bpfilter.h>
+#include <linux/sched.h>
+#include <linux/sched/signal.h>
+#include <linux/fs.h>
+#include <linux/file.h>
+#include "msgfmt.h"
+
+extern char bpfilter_umh_start;
+extern char bpfilter_umh_end;
+
+static void shutdown_umh(void)
+{
+ struct umd_info *info = &bpfilter_ops.info;
+ struct pid *tgid = info->tgid;
+
+ if (tgid) {
+ kill_pid(tgid, SIGKILL, 1);
+ wait_event(tgid->wait_pidfd, thread_group_exited(tgid));
+ bpfilter_umh_cleanup(info);
+ }
+}
+
+static void __stop_umh(void)
+{
+ if (IS_ENABLED(CONFIG_INET))
+ shutdown_umh();
+}
+
+static int bpfilter_send_req(struct mbox_request *req)
+{
+ struct mbox_reply reply;
+ loff_t pos = 0;
+ ssize_t n;
+
+ if (!bpfilter_ops.info.tgid)
+ return -EFAULT;
+ pos = 0;
+ n = kernel_write(bpfilter_ops.info.pipe_to_umh, req, sizeof(*req),
+ &pos);
+ if (n != sizeof(*req)) {
+ pr_err("write fail %zd\n", n);
+ goto stop;
+ }
+ pos = 0;
+ n = kernel_read(bpfilter_ops.info.pipe_from_umh, &reply, sizeof(reply),
+ &pos);
+ if (n != sizeof(reply)) {
+ pr_err("read fail %zd\n", n);
+ goto stop;
+ }
+ return reply.status;
+stop:
+ __stop_umh();
+ return -EFAULT;
+}
+
+static int bpfilter_process_sockopt(struct sock *sk, int optname,
+ sockptr_t optval, unsigned int optlen,
+ bool is_set)
+{
+ struct mbox_request req = {
+ .is_set = is_set,
+ .pid = current->pid,
+ .cmd = optname,
+ .addr = (uintptr_t)optval.user,
+ .len = optlen,
+ };
+ if (uaccess_kernel() || sockptr_is_kernel(optval)) {
+ pr_err("kernel access not supported\n");
+ return -EFAULT;
+ }
+ return bpfilter_send_req(&req);
+}
+
+static int start_umh(void)
+{
+ struct mbox_request req = { .pid = current->pid };
+ int err;
+
+ /* fork usermode process */
+ err = fork_usermode_driver(&bpfilter_ops.info);
+ if (err)
+ return err;
+ pr_info("Loaded bpfilter_umh pid %d\n", pid_nr(bpfilter_ops.info.tgid));
+
+ /* health check that usermode process started correctly */
+ if (bpfilter_send_req(&req) != 0) {
+ shutdown_umh();
+ return -EFAULT;
+ }
+
+ return 0;
+}
+
+static int __init load_umh(void)
+{
+ int err;
+
+ err = umd_load_blob(&bpfilter_ops.info,
+ &bpfilter_umh_start,
+ &bpfilter_umh_end - &bpfilter_umh_start);
+ if (err)
+ return err;
+
+ mutex_lock(&bpfilter_ops.lock);
+ err = start_umh();
+ if (!err && IS_ENABLED(CONFIG_INET)) {
+ bpfilter_ops.sockopt = &bpfilter_process_sockopt;
+ bpfilter_ops.start = &start_umh;
+ }
+ mutex_unlock(&bpfilter_ops.lock);
+ if (err)
+ umd_unload_blob(&bpfilter_ops.info);
+ return err;
+}
+
+static void __exit fini_umh(void)
+{
+ mutex_lock(&bpfilter_ops.lock);
+ if (IS_ENABLED(CONFIG_INET)) {
+ shutdown_umh();
+ bpfilter_ops.start = NULL;
+ bpfilter_ops.sockopt = NULL;
+ }
+ mutex_unlock(&bpfilter_ops.lock);
+
+ umd_unload_blob(&bpfilter_ops.info);
+}
+module_init(load_umh);
+module_exit(fini_umh);
+MODULE_LICENSE("GPL");
diff --git a/net/bpfilter/bpfilter_umh_blob.S b/net/bpfilter/bpfilter_umh_blob.S
new file mode 100644
index 000000000..40311d10d
--- /dev/null
+++ b/net/bpfilter/bpfilter_umh_blob.S
@@ -0,0 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+ .section .init.rodata, "a"
+ .global bpfilter_umh_start
+bpfilter_umh_start:
+ .incbin "net/bpfilter/bpfilter_umh"
+ .global bpfilter_umh_end
+bpfilter_umh_end:
diff --git a/net/bpfilter/main.c b/net/bpfilter/main.c
new file mode 100644
index 000000000..291a92546
--- /dev/null
+++ b/net/bpfilter/main.c
@@ -0,0 +1,64 @@
+// SPDX-License-Identifier: GPL-2.0
+#define _GNU_SOURCE
+#include <sys/uio.h>
+#include <errno.h>
+#include <stdio.h>
+#include <sys/socket.h>
+#include <fcntl.h>
+#include <unistd.h>
+#include "../../include/uapi/linux/bpf.h"
+#include <asm/unistd.h>
+#include "msgfmt.h"
+
+FILE *debug_f;
+
+static int handle_get_cmd(struct mbox_request *cmd)
+{
+ switch (cmd->cmd) {
+ case 0:
+ return 0;
+ default:
+ break;
+ }
+ return -ENOPROTOOPT;
+}
+
+static int handle_set_cmd(struct mbox_request *cmd)
+{
+ return -ENOPROTOOPT;
+}
+
+static void loop(void)
+{
+ while (1) {
+ struct mbox_request req;
+ struct mbox_reply reply;
+ int n;
+
+ n = read(0, &req, sizeof(req));
+ if (n != sizeof(req)) {
+ fprintf(debug_f, "invalid request %d\n", n);
+ return;
+ }
+
+ reply.status = req.is_set ?
+ handle_set_cmd(&req) :
+ handle_get_cmd(&req);
+
+ n = write(1, &reply, sizeof(reply));
+ if (n != sizeof(reply)) {
+ fprintf(debug_f, "reply failed %d\n", n);
+ return;
+ }
+ }
+}
+
+int main(void)
+{
+ debug_f = fopen("/dev/kmsg", "w");
+ setvbuf(debug_f, 0, _IOLBF, 0);
+ fprintf(debug_f, "<5>Started bpfilter\n");
+ loop();
+ fclose(debug_f);
+ return 0;
+}
diff --git a/net/bpfilter/msgfmt.h b/net/bpfilter/msgfmt.h
new file mode 100644
index 000000000..98d121c62
--- /dev/null
+++ b/net/bpfilter/msgfmt.h
@@ -0,0 +1,17 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _NET_BPFILTER_MSGFMT_H
+#define _NET_BPFILTER_MSGFMT_H
+
+struct mbox_request {
+ __u64 addr;
+ __u32 len;
+ __u32 is_set;
+ __u32 cmd;
+ __u32 pid;
+};
+
+struct mbox_reply {
+ __u32 status;
+};
+
+#endif
generated by cgit v1.2.3 (git 2.39.1) at 2024-12-12 16:56:18 +0000