1 files changed, 146 insertions, 80 deletions

diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c
index 9728dbd4c66c..655efac6f133 100644
--- a/net/bpf/test_run.c
+++ b/net/bpf/test_run.c
@@ -29,7 +29,6 @@
 #include <trace/events/bpf_test_run.h>
 
 struct bpf_test_timer {
-	enum { NO_PREEMPT, NO_MIGRATE } mode;
 	u32 i;
 	u64 time_start, time_spent;
 };
@@ -37,12 +36,7 @@ struct bpf_test_timer {
 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();
-
+	rcu_read_lock_dont_migrate();
 	t->time_start = ktime_get_ns();
 }
 
@@ -50,12 +44,7 @@ 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();
+	rcu_read_unlock_migrate();
 }
 
 static bool bpf_test_timer_continue(struct bpf_test_timer *t, int iterations,
@@ -374,7 +363,7 @@ static int bpf_test_run_xdp_live(struct bpf_prog *prog, struct xdp_buff *ctx,
 
 {
 	struct xdp_test_data xdp = { .batch_size = batch_size };
-	struct bpf_test_timer t = { .mode = NO_MIGRATE };
+	struct bpf_test_timer t = {};
 	int ret;
 
 	if (!repeat)
@@ -404,7 +393,7 @@ static int bpf_test_run(struct bpf_prog *prog, void *ctx, u32 repeat,
 	struct bpf_prog_array_item item = {.prog = prog};
 	struct bpf_run_ctx *old_ctx;
 	struct bpf_cg_run_ctx run_ctx;
-	struct bpf_test_timer t = { NO_MIGRATE };
+	struct bpf_test_timer t = {};
 	enum bpf_cgroup_storage_type stype;
 	int ret;
 
@@ -447,7 +436,7 @@ static int bpf_test_run(struct bpf_prog *prog, void *ctx, u32 repeat,
 
 static int bpf_test_finish(const union bpf_attr *kattr,
 			   union bpf_attr __user *uattr, const void *data,
-			   struct skb_shared_info *sinfo, u32 size,
+			   struct skb_shared_info *sinfo, u32 size, u32 frag_size,
 			   u32 retval, u32 duration)
 {
 	void __user *data_out = u64_to_user_ptr(kattr->test.data_out);
@@ -464,7 +453,7 @@ static int bpf_test_finish(const union bpf_attr *kattr,
 	}
 
 	if (data_out) {
-		int len = sinfo ? copy_size - sinfo->xdp_frags_size : copy_size;
+		int len = sinfo ? copy_size - frag_size : copy_size;
 
 		if (len < 0) {
 			err = -ENOSPC;
@@ -524,27 +513,27 @@ __bpf_kfunc int bpf_fentry_test1(int a)
 }
 EXPORT_SYMBOL_GPL(bpf_fentry_test1);
 
-int noinline bpf_fentry_test2(int a, u64 b)
+noinline int bpf_fentry_test2(int a, u64 b)
 {
 	return a + b;
 }
 
-int noinline bpf_fentry_test3(char a, int b, u64 c)
+noinline int 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)
+noinline int 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)
+noinline int 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)
+noinline int bpf_fentry_test6(u64 a, void *b, short c, int d, void *e, u64 f)
 {
 	return a + (long)b + c + d + (long)e + f;
 }
@@ -553,13 +542,13 @@ struct bpf_fentry_test_t {
 	struct bpf_fentry_test_t *a;
 };
 
-int noinline bpf_fentry_test7(struct bpf_fentry_test_t *arg)
+noinline int bpf_fentry_test7(struct bpf_fentry_test_t *arg)
 {
-	asm volatile ("": "+r"(arg));
+	asm volatile ("" : "+r"(arg));
 	return (long)arg;
 }
 
-int noinline bpf_fentry_test8(struct bpf_fentry_test_t *arg)
+noinline int bpf_fentry_test8(struct bpf_fentry_test_t *arg)
 {
 	return (long)arg->a;
 }
@@ -569,12 +558,12 @@ __bpf_kfunc u32 bpf_fentry_test9(u32 *a)
 	return *a;
 }
 
-int noinline bpf_fentry_test10(const void *a)
+noinline int bpf_fentry_test10(const void *a)
 {
 	return (long)a;
 }
 
-void noinline bpf_fentry_test_sinfo(struct skb_shared_info *sinfo)
+noinline void bpf_fentry_test_sinfo(struct skb_shared_info *sinfo)
 {
 }
 
@@ -598,7 +587,7 @@ __bpf_kfunc int bpf_modify_return_test_tp(int nonce)
 	return nonce;
 }
 
-int noinline bpf_fentry_shadow_test(int a)
+noinline int bpf_fentry_shadow_test(int a)
 {
 	return a + 1;
 }
@@ -665,7 +654,7 @@ static void *bpf_test_init(const union bpf_attr *kattr, u32 user_size,
 	void __user *data_in = u64_to_user_ptr(kattr->test.data_in);
 	void *data;
 
-	if (user_size < ETH_HLEN || user_size > PAGE_SIZE - headroom - tailroom)
+	if (user_size > PAGE_SIZE - headroom - tailroom)
 		return ERR_PTR(-EINVAL);
 
 	size = SKB_DATA_ALIGN(size);
@@ -910,6 +899,12 @@ static int convert___skb_to_skb(struct sk_buff *skb, struct __sk_buff *__skb)
 	/* cb is allowed */
 
 	if (!range_is_zero(__skb, offsetofend(struct __sk_buff, cb),
+			   offsetof(struct __sk_buff, data_end)))
+		return -EINVAL;
+
+	/* data_end is allowed, but not copied to skb */
+
+	if (!range_is_zero(__skb, offsetofend(struct __sk_buff, data_end),
 			   offsetof(struct __sk_buff, tstamp)))
 		return -EINVAL;
 
@@ -950,6 +945,11 @@ static int convert___skb_to_skb(struct sk_buff *skb, struct __sk_buff *__skb)
 
 	if (__skb->gso_segs > GSO_MAX_SEGS)
 		return -EINVAL;
+
+	/* Currently GSO type is zero/unset. If this gets extended with
+	 * a small list of accepted GSO types in future, the filter for
+	 * an unset GSO type in bpf_clone_redirect() can be lifted.
+	 */
 	skb_shinfo(skb)->gso_segs = __skb->gso_segs;
 	skb_shinfo(skb)->gso_size = __skb->gso_size;
 	skb_shinfo(skb)->hwtstamps.hwtstamp = __skb->hwtstamp;
@@ -984,43 +984,39 @@ static struct proto bpf_dummy_proto = {
 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;
+	bool is_l2 = false, is_direct_pkt_access = false, is_lwt = false;
+	u32 tailroom = SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
 	struct net *net = current->nsproxy->net_ns;
 	struct net_device *dev = net->loopback_dev;
-	u32 size = kattr->test.data_size_in;
+	u32 headroom = NET_SKB_PAD + NET_IP_ALIGN;
+	u32 linear_sz = kattr->test.data_size_in;
 	u32 repeat = kattr->test.repeat;
 	struct __sk_buff *ctx = NULL;
+	struct sk_buff *skb = NULL;
+	struct sock *sk = NULL;
 	u32 retval, duration;
 	int hh_len = ETH_HLEN;
-	struct sk_buff *skb;
-	struct sock *sk;
-	void *data;
+	void *data = NULL;
 	int ret;
 
 	if ((kattr->test.flags & ~BPF_F_TEST_SKB_CHECKSUM_COMPLETE) ||
 	    kattr->test.cpu || kattr->test.batch_size)
 		return -EINVAL;
 
-	data = bpf_test_init(kattr, kattr->test.data_size_in,
-			     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);
-	}
+	if (kattr->test.data_size_in < ETH_HLEN)
+		return -EINVAL;
 
 	switch (prog->type) {
 	case BPF_PROG_TYPE_SCHED_CLS:
 	case BPF_PROG_TYPE_SCHED_ACT:
+		is_direct_pkt_access = true;
 		is_l2 = true;
-		fallthrough;
+		break;
 	case BPF_PROG_TYPE_LWT_IN:
 	case BPF_PROG_TYPE_LWT_OUT:
 	case BPF_PROG_TYPE_LWT_XMIT:
+		is_lwt = true;
+		fallthrough;
 	case BPF_PROG_TYPE_CGROUP_SKB:
 		is_direct_pkt_access = true;
 		break;
@@ -1028,25 +1024,88 @@ int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr,
 		break;
 	}
 
+	ctx = bpf_ctx_init(kattr, sizeof(struct __sk_buff));
+	if (IS_ERR(ctx))
+		return PTR_ERR(ctx);
+
+	if (ctx) {
+		if (ctx->data_end > kattr->test.data_size_in || ctx->data || ctx->data_meta) {
+			ret = -EINVAL;
+			goto out;
+		}
+		if (ctx->data_end) {
+			/* Non-linear LWT test_run is unsupported for now. */
+			if (is_lwt) {
+				ret = -EINVAL;
+				goto out;
+			}
+			linear_sz = max(ETH_HLEN, ctx->data_end);
+		}
+	}
+
+	linear_sz = min_t(u32, linear_sz, PAGE_SIZE - headroom - tailroom);
+
+	data = bpf_test_init(kattr, linear_sz, linear_sz, headroom, tailroom);
+	if (IS_ERR(data)) {
+		ret = PTR_ERR(data);
+		data = NULL;
+		goto out;
+	}
+
 	sk = sk_alloc(net, AF_UNSPEC, GFP_USER, &bpf_dummy_proto, 1);
 	if (!sk) {
-		kfree(data);
-		kfree(ctx);
-		return -ENOMEM;
+		ret = -ENOMEM;
+		goto out;
 	}
 	sock_init_data(NULL, sk);
 
 	skb = slab_build_skb(data);
 	if (!skb) {
-		kfree(data);
-		kfree(ctx);
-		sk_free(sk);
-		return -ENOMEM;
+		ret = -ENOMEM;
+		goto out;
 	}
 	skb->sk = sk;
 
+	data = NULL; /* data released via kfree_skb */
+
 	skb_reserve(skb, NET_SKB_PAD + NET_IP_ALIGN);
-	__skb_put(skb, size);
+	__skb_put(skb, linear_sz);
+
+	if (unlikely(kattr->test.data_size_in > linear_sz)) {
+		void __user *data_in = u64_to_user_ptr(kattr->test.data_in);
+		struct skb_shared_info *sinfo = skb_shinfo(skb);
+		u32 copied = linear_sz;
+
+		while (copied < kattr->test.data_size_in) {
+			struct page *page;
+			u32 data_len;
+
+			if (sinfo->nr_frags == MAX_SKB_FRAGS) {
+				ret = -ENOMEM;
+				goto out;
+			}
+
+			page = alloc_page(GFP_KERNEL);
+			if (!page) {
+				ret = -ENOMEM;
+				goto out;
+			}
+
+			data_len = min_t(u32, kattr->test.data_size_in - copied,
+					 PAGE_SIZE);
+			skb_fill_page_desc(skb, sinfo->nr_frags, page, 0, data_len);
+
+			if (copy_from_user(page_address(page), data_in + copied,
+					   data_len)) {
+				ret = -EFAULT;
+				goto out;
+			}
+			skb->data_len += data_len;
+			skb->truesize += PAGE_SIZE;
+			skb->len += data_len;
+			copied += data_len;
+		}
+	}
 
 	if (ctx && ctx->ifindex > 1) {
 		dev = dev_get_by_index(net, ctx->ifindex);
@@ -1126,12 +1185,11 @@ int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr,
 
 	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, NULL, size, retval,
-			      duration);
+	if (skb_is_nonlinear(skb))
+		/* bpf program can never convert linear skb to non-linear */
+		WARN_ON_ONCE(linear_sz == kattr->test.data_size_in);
+	ret = bpf_test_finish(kattr, uattr, skb->data, skb_shinfo(skb), skb->len,
+			      skb->data_len, retval, duration);
 	if (!ret)
 		ret = bpf_ctx_finish(kattr, uattr, ctx,
 				     sizeof(struct __sk_buff));
@@ -1139,7 +1197,9 @@ out:
 	if (dev && dev != net->loopback_dev)
 		dev_put(dev);
 	kfree_skb(skb);
-	sk_free(sk);
+	kfree(data);
+	if (sk)
+		sk_free(sk);
 	kfree(ctx);
 	return ret;
 }
@@ -1207,9 +1267,9 @@ int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr,
 {
 	bool do_live = (kattr->test.flags & BPF_F_TEST_XDP_LIVE_FRAMES);
 	u32 tailroom = SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
+	u32 retval = 0, meta_sz = 0, duration, max_linear_sz, size;
+	u32 linear_sz = kattr->test.data_size_in;
 	u32 batch_size = kattr->test.batch_size;
-	u32 retval = 0, duration, max_data_sz;
-	u32 size = kattr->test.data_size_in;
 	u32 headroom = XDP_PACKET_HEADROOM;
 	u32 repeat = kattr->test.repeat;
 	struct netdev_rx_queue *rxqueue;
@@ -1246,39 +1306,45 @@ int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr,
 
 	if (ctx) {
 		/* There can't be user provided data before the meta data */
-		if (ctx->data_meta || ctx->data_end != size ||
+		if (ctx->data_meta || ctx->data_end > kattr->test.data_size_in ||
 		    ctx->data > ctx->data_end ||
 		    unlikely(xdp_metalen_invalid(ctx->data)) ||
 		    (do_live && (kattr->test.data_out || kattr->test.ctx_out)))
 			goto free_ctx;
 		/* Meta data is allocated from the headroom */
 		headroom -= ctx->data;
-	}
 
-	max_data_sz = PAGE_SIZE - headroom - tailroom;
-	if (size > max_data_sz) {
-		/* disallow live data mode for jumbo frames */
-		if (do_live)
-			goto free_ctx;
-		size = max_data_sz;
+		meta_sz = ctx->data;
+		linear_sz = ctx->data_end;
 	}
 
-	data = bpf_test_init(kattr, size, max_data_sz, headroom, tailroom);
+	max_linear_sz = PAGE_SIZE - headroom - tailroom;
+	linear_sz = min_t(u32, linear_sz, max_linear_sz);
+
+	/* disallow live data mode for jumbo frames */
+	if (do_live && kattr->test.data_size_in > linear_sz)
+		goto free_ctx;
+
+	if (kattr->test.data_size_in - meta_sz < ETH_HLEN)
+		goto free_ctx;
+
+	data = bpf_test_init(kattr, linear_sz, max_linear_sz, headroom, tailroom);
 	if (IS_ERR(data)) {
 		ret = PTR_ERR(data);
 		goto free_ctx;
 	}
 
 	rxqueue = __netif_get_rx_queue(current->nsproxy->net_ns->loopback_dev, 0);
-	rxqueue->xdp_rxq.frag_size = headroom + max_data_sz + tailroom;
+	rxqueue->xdp_rxq.frag_size = PAGE_SIZE;
 	xdp_init_buff(&xdp, rxqueue->xdp_rxq.frag_size, &rxqueue->xdp_rxq);
-	xdp_prepare_buff(&xdp, data, headroom, size, true);
+	xdp_prepare_buff(&xdp, data, headroom, linear_sz, true);
 	sinfo = xdp_get_shared_info_from_buff(&xdp);
 
 	ret = xdp_convert_md_to_buff(ctx, &xdp);
 	if (ret)
 		goto free_data;
 
+	size = linear_sz;
 	if (unlikely(kattr->test.data_size_in > size)) {
 		void __user *data_in = u64_to_user_ptr(kattr->test.data_in);
 
@@ -1331,7 +1397,7 @@ int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr,
 		goto out;
 
 	size = xdp.data_end - xdp.data_meta + sinfo->xdp_frags_size;
-	ret = bpf_test_finish(kattr, uattr, xdp.data_meta, sinfo, size,
+	ret = bpf_test_finish(kattr, uattr, xdp.data_meta, sinfo, size, sinfo->xdp_frags_size,
 			      retval, duration);
 	if (!ret)
 		ret = bpf_ctx_finish(kattr, uattr, ctx,
@@ -1368,7 +1434,7 @@ 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 };
+	struct bpf_test_timer t = {};
 	u32 size = kattr->test.data_size_in;
 	struct bpf_flow_dissector ctx = {};
 	u32 repeat = kattr->test.repeat;
@@ -1422,7 +1488,7 @@ int bpf_prog_test_run_flow_dissector(struct bpf_prog *prog,
 		goto out;
 
 	ret = bpf_test_finish(kattr, uattr, &flow_keys, NULL,
-			      sizeof(flow_keys), retval, duration);
+			      sizeof(flow_keys), 0, retval, duration);
 	if (!ret)
 		ret = bpf_ctx_finish(kattr, uattr, user_ctx,
 				     sizeof(struct bpf_flow_keys));
@@ -1436,7 +1502,7 @@ out:
 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_test_timer t = {};
 	struct bpf_prog_array *progs = NULL;
 	struct bpf_sk_lookup_kern ctx = {};
 	u32 repeat = kattr->test.repeat;
@@ -1523,7 +1589,7 @@ int bpf_prog_test_run_sk_lookup(struct bpf_prog *prog, const union bpf_attr *kat
 		user_ctx->cookie = sock_gen_cookie(ctx.selected_sk);
 	}
 
-	ret = bpf_test_finish(kattr, uattr, NULL, NULL, 0, retval, duration);
+	ret = bpf_test_finish(kattr, uattr, NULL, NULL, 0, 0, retval, duration);
 	if (!ret)
 		ret = bpf_ctx_finish(kattr, uattr, user_ctx, sizeof(*user_ctx));
 
@@ -1723,7 +1789,7 @@ int bpf_prog_test_run_nf(struct bpf_prog *prog,
 	if (ret)
 		goto out;
 
-	ret = bpf_test_finish(kattr, uattr, NULL, NULL, 0, retval, duration);
+	ret = bpf_test_finish(kattr, uattr, NULL, NULL, 0, 0, retval, duration);
 
 out:
 	kfree(user_ctx);