Merge tag 'net-next-5.15' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next

Pull networking updates from Jakub Kicinski:
 "Core:

   - Enable memcg accounting for various networking objects.

  BPF:

   - Introduce bpf timers.

   - Add perf link and opaque bpf_cookie which the program can read out
     again, to be used in libbpf-based USDT library.

   - Add bpf_task_pt_regs() helper to access user space pt_regs in
     kprobes, to help user space stack unwinding.

   - Add support for UNIX sockets for BPF sockmap.

   - Extend BPF iterator support for UNIX domain sockets.

   - Allow BPF TCP congestion control progs and bpf iterators to call
     bpf_setsockopt(), e.g. to switch to another congestion control
     algorithm.

  Protocols:

   - Support IOAM Pre-allocated Trace with IPv6.

   - Support Management Component Transport Protocol.

   - bridge: multicast: add vlan support.

   - netfilter: add hooks for the SRv6 lightweight tunnel driver.

   - tcp:
       - enable mid-stream window clamping (by user space or BPF)
       - allow data-less, empty-cookie SYN with TFO_SERVER_COOKIE_NOT_REQD
       - more accurate DSACK processing for RACK-TLP

   - mptcp:
       - add full mesh path manager option
       - add partial support for MP_FAIL
       - improve use of backup subflows
       - optimize option processing

   - af_unix: add OOB notification support.

   - ipv6: add IFLA_INET6_RA_MTU to expose MTU value advertised by the
     router.

   - mac80211: Target Wake Time support in AP mode.

   - can: j1939: extend UAPI to notify about RX status.

  Driver APIs:

   - Add page frag support in page pool API.

   - Many improvements to the DSA (distributed switch) APIs.

   - ethtool: extend IRQ coalesce uAPI with timer reset modes.

   - devlink: control which auxiliary devices are created.

   - Support CAN PHYs via the generic PHY subsystem.

   - Proper cross-chip support for tag_8021q.

   - Allow TX forwarding for the software bridge data path to be
     offloaded to capable devices.

  Drivers:

   - veth: more flexible channels number configuration.

   - openvswitch: introduce per-cpu upcall dispatch.

   - Add internet mix (IMIX) mode to pktgen.

   - Transparently handle XDP operations in the bonding driver.

   - Add LiteETH network driver.

   - Renesas (ravb):
       - support Gigabit Ethernet IP

   - NXP Ethernet switch (sja1105):
       - fast aging support
       - support for "H" switch topologies
       - traffic termination for ports under VLAN-aware bridge

   - Intel 1G Ethernet
       - support getcrosststamp() with PCIe PTM (Precision Time
         Measurement) for better time sync
       - support Credit-Based Shaper (CBS) offload, enabling HW traffic
         prioritization and bandwidth reservation

   - Broadcom Ethernet (bnxt)
       - support pulse-per-second output
       - support larger Rx rings

   - Mellanox Ethernet (mlx5)
       - support ethtool RSS contexts and MQPRIO channel mode
       - support LAG offload with bridging
       - support devlink rate limit API
       - support packet sampling on tunnels

   - Huawei Ethernet (hns3):
       - basic devlink support
       - add extended IRQ coalescing support
       - report extended link state

   - Netronome Ethernet (nfp):
       - add conntrack offload support

   - Broadcom WiFi (brcmfmac):
       - add WPA3 Personal with FT to supported cipher suites
       - support 43752 SDIO device

   - Intel WiFi (iwlwifi):
       - support scanning hidden 6GHz networks
       - support for a new hardware family (Bz)

   - Xen pv driver:
       - harden netfront against malicious backends

   - Qualcomm mobile
       - ipa: refactor power management and enable automatic suspend
       - mhi: move MBIM to WWAN subsystem interfaces

  Refactor:

   - Ambient BPF run context and cgroup storage cleanup.

   - Compat rework for ndo_ioctl.

  Old code removal:

   - prism54 remove the obsoleted driver, deprecated by the p54 driver.

   - wan: remove sbni/granch driver"

* tag 'net-next-5.15' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1715 commits)
  net: Add depends on OF_NET for LiteX's LiteETH
  ipv6: seg6: remove duplicated include
  net: hns3: remove unnecessary spaces
  net: hns3: add some required spaces
  net: hns3: clean up a type mismatch warning
  net: hns3: refine function hns3_set_default_feature()
  ipv6: remove duplicated 'net/lwtunnel.h' include
  net: w5100: check return value after calling platform_get_resource()
  net/mlxbf_gige: Make use of devm_platform_ioremap_resourcexxx()
  net: mdio: mscc-miim: Make use of the helper function devm_platform_ioremap_resource()
  net: mdio-ipq4019: Make use of devm_platform_ioremap_resource()
  fou: remove sparse errors
  ipv4: fix endianness issue in inet_rtm_getroute_build_skb()
  octeontx2-af: Set proper errorcode for IPv4 checksum errors
  octeontx2-af: Fix static code analyzer reported issues
  octeontx2-af: Fix mailbox errors in nix_rss_flowkey_cfg
  octeontx2-af: Fix loop in free and unmap counter
  af_unix: fix potential NULL deref in unix_dgram_connect()
  dpaa2-eth: Replace strlcpy with strscpy
  octeontx2-af: Use NDC TX for transmit packet data
  ...

1 files changed, 116 insertions, 23 deletions

diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c
index caa16bf30fb5..2eb0e55ef54d 100644
--- a/net/bpf/test_run.c
+++ b/net/bpf/test_run.c
@@ -16,6 +16,7 @@
 #include <linux/error-injection.h>
 #include <linux/smp.h>
 #include <linux/sock_diag.h>
+#include <net/xdp.h>
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/bpf_test_run.h>
@@ -88,17 +89,19 @@ reset:
 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_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 };
 	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;
+		item.cgroup_storage[stype] = bpf_cgroup_storage_alloc(prog, stype);
+		if (IS_ERR(item.cgroup_storage[stype])) {
+			item.cgroup_storage[stype] = NULL;
 			for_each_cgroup_storage_type(stype)
-				bpf_cgroup_storage_free(storage[stype]);
+				bpf_cgroup_storage_free(item.cgroup_storage[stype]);
 			return -ENOMEM;
 		}
 	}
@@ -107,22 +110,19 @@ static int bpf_test_run(struct bpf_prog *prog, void *ctx, u32 repeat,
 		repeat = 1;
 
 	bpf_test_timer_enter(&t);
+	old_ctx = bpf_set_run_ctx(&run_ctx.run_ctx);
 	do {
-		ret = bpf_cgroup_storage_set(storage);
-		if (ret)
-			break;
-
+		run_ctx.prog_item = &item;
 		if (xdp)
 			*retval = bpf_prog_run_xdp(prog, ctx);
 		else
-			*retval = BPF_PROG_RUN(prog, ctx);
-
-		bpf_cgroup_storage_unset();
+			*retval = bpf_prog_run(prog, ctx);
 	} while (bpf_test_timer_continue(&t, repeat, &ret, time));
+	bpf_reset_run_ctx(old_ctx);
 	bpf_test_timer_leave(&t);
 
 	for_each_cgroup_storage_type(stype)
-		bpf_cgroup_storage_free(storage[stype]);
+		bpf_cgroup_storage_free(item.cgroup_storage[stype]);
 
 	return ret;
 }
@@ -327,7 +327,7 @@ __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);
+	info->retval = bpf_prog_run(info->prog, info->ctx);
 	rcu_read_unlock();
 }
 
@@ -688,6 +688,64 @@ out:
 	return ret;
 }
 
+static int xdp_convert_md_to_buff(struct xdp_md *xdp_md, struct xdp_buff *xdp)
+{
+	unsigned int ingress_ifindex, rx_queue_index;
+	struct netdev_rx_queue *rxqueue;
+	struct net_device *device;
+
+	if (!xdp_md)
+		return 0;
+
+	if (xdp_md->egress_ifindex != 0)
+		return -EINVAL;
+
+	ingress_ifindex = xdp_md->ingress_ifindex;
+	rx_queue_index = xdp_md->rx_queue_index;
+
+	if (!ingress_ifindex && rx_queue_index)
+		return -EINVAL;
+
+	if (ingress_ifindex) {
+		device = dev_get_by_index(current->nsproxy->net_ns,
+					  ingress_ifindex);
+		if (!device)
+			return -ENODEV;
+
+		if (rx_queue_index >= device->real_num_rx_queues)
+			goto free_dev;
+
+		rxqueue = __netif_get_rx_queue(device, rx_queue_index);
+
+		if (!xdp_rxq_info_is_reg(&rxqueue->xdp_rxq))
+			goto free_dev;
+
+		xdp->rxq = &rxqueue->xdp_rxq;
+		/* The device is now tracked in the xdp->rxq for later
+		 * dev_put()
+		 */
+	}
+
+	xdp->data = xdp->data_meta + xdp_md->data;
+	return 0;
+
+free_dev:
+	dev_put(device);
+	return -EINVAL;
+}
+
+static void xdp_convert_buff_to_md(struct xdp_buff *xdp, struct xdp_md *xdp_md)
+{
+	if (!xdp_md)
+		return;
+
+	xdp_md->data = xdp->data - xdp->data_meta;
+	xdp_md->data_end = xdp->data_end - xdp->data_meta;
+
+	if (xdp_md->ingress_ifindex)
+		dev_put(xdp->rxq->dev);
+}
+
 int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr,
 			  union bpf_attr __user *uattr)
 {
@@ -698,38 +756,73 @@ int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr,
 	struct netdev_rx_queue *rxqueue;
 	struct xdp_buff xdp = {};
 	u32 retval, duration;
+	struct xdp_md *ctx;
 	u32 max_data_sz;
 	void *data;
-	int ret;
+	int ret = -EINVAL;
 
 	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;
+
+	ctx = bpf_ctx_init(kattr, sizeof(struct xdp_md));
+	if (IS_ERR(ctx))
+		return PTR_ERR(ctx);
+
+	if (ctx) {
+		/* There can't be user provided data before the meta data */
+		if (ctx->data_meta || ctx->data_end != size ||
+		    ctx->data > ctx->data_end ||
+		    unlikely(xdp_metalen_invalid(ctx->data)))
+			goto free_ctx;
+		/* Meta data is allocated from the headroom */
+		headroom -= ctx->data;
+	}
 
 	/* 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);
+	if (IS_ERR(data)) {
+		ret = PTR_ERR(data);
+		goto free_ctx;
+	}
 
 	rxqueue = __netif_get_rx_queue(current->nsproxy->net_ns->loopback_dev, 0);
 	xdp_init_buff(&xdp, headroom + max_data_sz + tailroom,
 		      &rxqueue->xdp_rxq);
 	xdp_prepare_buff(&xdp, data, headroom, size, true);
 
+	ret = xdp_convert_md_to_buff(ctx, &xdp);
+	if (ret)
+		goto free_data;
+
 	bpf_prog_change_xdp(NULL, prog);
 	ret = bpf_test_run(prog, &xdp, repeat, &retval, &duration, true);
+	/* We convert the xdp_buff back to an xdp_md before checking the return
+	 * code so the reference count of any held netdevice will be decremented
+	 * even if the test run failed.
+	 */
+	xdp_convert_buff_to_md(&xdp, ctx);
 	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);
+
+	if (xdp.data_meta != data + headroom ||
+	    xdp.data_end != xdp.data_meta + size)
+		size = xdp.data_end - xdp.data_meta;
+
+	ret = bpf_test_finish(kattr, uattr, xdp.data_meta, size, retval,
+			      duration);
+	if (!ret)
+		ret = bpf_ctx_finish(kattr, uattr, ctx,
+				     sizeof(struct xdp_md));
+
 out:
 	bpf_prog_change_xdp(prog, NULL);
+free_data:
 	kfree(data);
+free_ctx:
+	kfree(ctx);
 	return ret;
 }
 
@@ -896,7 +989,7 @@ int bpf_prog_test_run_sk_lookup(struct bpf_prog *prog, const union bpf_attr *kat
 	bpf_test_timer_enter(&t);
 	do {
 		ctx.selected_sk = NULL;
-		retval = BPF_PROG_SK_LOOKUP_RUN_ARRAY(progs, ctx, BPF_PROG_RUN);
+		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);