Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next

Pull networking updates from David Miller:
 "Highlights:

   1) Support AES128-CCM ciphers in kTLS, from Vakul Garg.

   2) Add fib_sync_mem to control the amount of dirty memory we allow to
      queue up between synchronize RCU calls, from David Ahern.

   3) Make flow classifier more lockless, from Vlad Buslov.

   4) Add PHY downshift support to aquantia driver, from Heiner
      Kallweit.

   5) Add SKB cache for TCP rx and tx, from Eric Dumazet. This reduces
      contention on SLAB spinlocks in heavy RPC workloads.

   6) Partial GSO offload support in XFRM, from Boris Pismenny.

   7) Add fast link down support to ethtool, from Heiner Kallweit.

   8) Use siphash for IP ID generator, from Eric Dumazet.

   9) Pull nexthops even further out from ipv4/ipv6 routes and FIB
      entries, from David Ahern.

  10) Move skb->xmit_more into a per-cpu variable, from Florian
      Westphal.

  11) Improve eBPF verifier speed and increase maximum program size,
      from Alexei Starovoitov.

  12) Eliminate per-bucket spinlocks in rhashtable, and instead use bit
      spinlocks. From Neil Brown.

  13) Allow tunneling with GUE encap in ipvs, from Jacky Hu.

  14) Improve link partner cap detection in generic PHY code, from
      Heiner Kallweit.

  15) Add layer 2 encap support to bpf_skb_adjust_room(), from Alan
      Maguire.

  16) Remove SKB list implementation assumptions in SCTP, your's truly.

  17) Various cleanups, optimizations, and simplifications in r8169
      driver. From Heiner Kallweit.

  18) Add memory accounting on TX and RX path of SCTP, from Xin Long.

  19) Switch PHY drivers over to use dynamic featue detection, from
      Heiner Kallweit.

  20) Support flow steering without masking in dpaa2-eth, from Ioana
      Ciocoi.

  21) Implement ndo_get_devlink_port in netdevsim driver, from Jiri
      Pirko.

  22) Increase the strict parsing of current and future netlink
      attributes, also export such policies to userspace. From Johannes
      Berg.

  23) Allow DSA tag drivers to be modular, from Andrew Lunn.

  24) Remove legacy DSA probing support, also from Andrew Lunn.

  25) Allow ll_temac driver to be used on non-x86 platforms, from Esben
      Haabendal.

  26) Add a generic tracepoint for TX queue timeouts to ease debugging,
      from Cong Wang.

  27) More indirect call optimizations, from Paolo Abeni"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1763 commits)
  cxgb4: Fix error path in cxgb4_init_module
  net: phy: improve pause mode reporting in phy_print_status
  dt-bindings: net: Fix a typo in the phy-mode list for ethernet bindings
  net: macb: Change interrupt and napi enable order in open
  net: ll_temac: Improve error message on error IRQ
  net/sched: remove block pointer from common offload structure
  net: ethernet: support of_get_mac_address new ERR_PTR error
  net: usb: smsc: fix warning reported by kbuild test robot
  staging: octeon-ethernet: Fix of_get_mac_address ERR_PTR check
  net: dsa: support of_get_mac_address new ERR_PTR error
  net: dsa: sja1105: Fix status initialization in sja1105_get_ethtool_stats
  vrf: sit mtu should not be updated when vrf netdev is the link
  net: dsa: Fix error cleanup path in dsa_init_module
  l2tp: Fix possible NULL pointer dereference
  taprio: add null check on sched_nest to avoid potential null pointer dereference
  net: mvpp2: cls: fix less than zero check on a u32 variable
  net_sched: sch_fq: handle non connected flows
  net_sched: sch_fq: do not assume EDT packets are ordered
  net: hns3: use devm_kcalloc when allocating desc_cb
  net: hns3: some cleanup for struct hns3_enet_ring
  ...

1 files changed, 161 insertions, 42 deletions

diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c
index fab142b796ef..33e0dc168c16 100644
--- a/net/bpf/test_run.c
+++ b/net/bpf/test_run.c
@@ -10,9 +10,13 @@
 #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>
 
+#define CREATE_TRACE_POINTS
+#include <trace/events/bpf_test_run.h>
+
 static int bpf_test_run(struct bpf_prog *prog, void *ctx, u32 repeat,
 			u32 *retval, u32 *time)
 {
@@ -100,6 +104,7 @@ static int bpf_test_finish(const union bpf_attr *kattr,
 	if (err != -ENOSPC)
 		err = 0;
 out:
+	trace_bpf_test_finish(&err);
 	return err;
 }
 
@@ -123,12 +128,126 @@ static void *bpf_test_init(const union bpf_attr *kattr, u32 size,
 	return data;
 }
 
+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, priority)))
+		return -EINVAL;
+
+	/* priority is allowed */
+
+	if (!range_is_zero(__skb, offsetof(struct __sk_buff, priority) +
+			   FIELD_SIZEOF(struct __sk_buff, priority),
+			   offsetof(struct __sk_buff, cb)))
+		return -EINVAL;
+
+	/* cb is allowed */
+
+	if (!range_is_zero(__skb, offsetof(struct __sk_buff, cb) +
+			   FIELD_SIZEOF(struct __sk_buff, cb),
+			   sizeof(struct __sk_buff)))
+		return -EINVAL;
+
+	skb->priority = __skb->priority;
+	memcpy(&cb->data, __skb->cb, QDISC_CB_PRIV_LEN);
+
+	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->priority = skb->priority;
+	memcpy(__skb->cb, &cb->data, QDISC_CB_PRIV_LEN);
+}
+
 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;
 	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;
@@ -141,6 +260,12 @@ int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr,
 	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:
@@ -158,6 +283,7 @@ int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr,
 	sk = kzalloc(sizeof(struct sock), GFP_USER);
 	if (!sk) {
 		kfree(data);
+		kfree(ctx);
 		return -ENOMEM;
 	}
 	sock_net_set(sk, current->nsproxy->net_ns);
@@ -166,6 +292,7 @@ int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr,
 	skb = build_skb(data, 0);
 	if (!skb) {
 		kfree(data);
+		kfree(ctx);
 		kfree(sk);
 		return -ENOMEM;
 	}
@@ -180,32 +307,38 @@ int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr,
 		__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);
-	if (ret) {
-		kfree_skb(skb);
-		kfree(sk);
-		return ret;
-	}
+	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)) {
-				kfree_skb(skb);
-				kfree(sk);
-				return -ENOMEM;
+				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:
 	kfree_skb(skb);
+	bpf_sk_storage_free(sk);
 	kfree(sk);
+	kfree(ctx);
 	return ret;
 }
 
@@ -220,6 +353,9 @@ int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr,
 	void *data;
 	int ret;
 
+	if (kattr->test.ctx_in || kattr->test.ctx_out)
+		return -EINVAL;
+
 	data = bpf_test_init(kattr, size, XDP_PACKET_HEADROOM + NET_IP_ALIGN, 0);
 	if (IS_ERR(data))
 		return PTR_ERR(data);
@@ -249,13 +385,12 @@ int bpf_prog_test_run_flow_dissector(struct bpf_prog *prog,
 				     union bpf_attr __user *uattr)
 {
 	u32 size = kattr->test.data_size_in;
+	struct bpf_flow_dissector ctx = {};
 	u32 repeat = kattr->test.repeat;
 	struct bpf_flow_keys flow_keys;
 	u64 time_start, time_spent = 0;
-	struct bpf_skb_data_end *cb;
+	const struct ethhdr *eth;
 	u32 retval, duration;
-	struct sk_buff *skb;
-	struct sock *sk;
 	void *data;
 	int ret;
 	u32 i;
@@ -263,46 +398,31 @@ int bpf_prog_test_run_flow_dissector(struct bpf_prog *prog,
 	if (prog->type != BPF_PROG_TYPE_FLOW_DISSECTOR)
 		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);
-
-	sk = kzalloc(sizeof(*sk), GFP_USER);
-	if (!sk) {
-		kfree(data);
-		return -ENOMEM;
-	}
-	sock_net_set(sk, current->nsproxy->net_ns);
-	sock_init_data(NULL, sk);
+	if (kattr->test.ctx_in || kattr->test.ctx_out)
+		return -EINVAL;
 
-	skb = build_skb(data, 0);
-	if (!skb) {
-		kfree(data);
-		kfree(sk);
-		return -ENOMEM;
-	}
-	skb->sk = sk;
+	if (size < ETH_HLEN)
+		return -EINVAL;
 
-	skb_reserve(skb, NET_SKB_PAD + NET_IP_ALIGN);
-	__skb_put(skb, size);
-	skb->protocol = eth_type_trans(skb,
-				       current->nsproxy->net_ns->loopback_dev);
-	skb_reset_network_header(skb);
+	data = bpf_test_init(kattr, size, 0, 0);
+	if (IS_ERR(data))
+		return PTR_ERR(data);
 
-	cb = (struct bpf_skb_data_end *)skb->cb;
-	cb->qdisc_cb.flow_keys = &flow_keys;
+	eth = (struct ethhdr *)data;
 
 	if (!repeat)
 		repeat = 1;
 
+	ctx.flow_keys = &flow_keys;
+	ctx.data = data;
+	ctx.data_end = (__u8 *)data + size;
+
 	rcu_read_lock();
 	preempt_disable();
 	time_start = ktime_get_ns();
 	for (i = 0; i < repeat; i++) {
-		retval = __skb_flow_bpf_dissect(prog, skb,
-						&flow_keys_dissector,
-						&flow_keys);
+		retval = bpf_flow_dissect(prog, &ctx, eth->h_proto, ETH_HLEN,
+					  size);
 
 		if (signal_pending(current)) {
 			preempt_enable();
@@ -335,7 +455,6 @@ int bpf_prog_test_run_flow_dissector(struct bpf_prog *prog,
 			      retval, duration);
 
 out:
-	kfree_skb(skb);
-	kfree(sk);
+	kfree(data);
 	return ret;
 }