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

Daniel Borkmann says:

====================
pull-request: bpf-next 2018-01-07

The following pull-request contains BPF updates for your *net-next* tree.

The main changes are:

1) Add a start of a framework for extending struct xdp_buff without
   having the overhead of populating every data at runtime. Idea
   is to have a new per-queue struct xdp_rxq_info that holds read
   mostly data (currently that is, queue number and a pointer to
   the corresponding netdev) which is set up during rxqueue config
   time. When a XDP program is invoked, struct xdp_buff holds a
   pointer to struct xdp_rxq_info that the BPF program can then
   walk. The user facing BPF program that uses struct xdp_md for
   context can use these members directly, and the verifier rewrites
   context access transparently by walking the xdp_rxq_info and
   net_device pointers to load the data, from Jesper.

2) Redo the reporting of offload device information to user space
   such that it works in combination with network namespaces. The
   latter is reported through a device/inode tuple as similarly
   done in other subsystems as well (e.g. perf) in order to identify
   the namespace. For this to work, ns_get_path() has been generalized
   such that the namespace can be retrieved not only from a specific
   task (perf case), but also from a callback where we deduce the
   netns (ns_common) from a netdevice. bpftool support using the new
   uapi info and extensive test cases for test_offload.py in BPF
   selftests have been added as well, from Jakub.

3) Add two bpftool improvements: i) properly report the bpftool
   version such that it corresponds to the version from the kernel
   source tree. So pick the right linux/version.h from the source
   tree instead of the installed one. ii) fix bpftool and also
   bpf_jit_disasm build with bintutils >= 2.9. The reason for the
   build breakage is that binutils library changed the function
   signature to select the disassembler. Given this is needed in
   multiple tools, add a proper feature detection to the
   tools/build/features infrastructure, from Roman.

4) Implement the BPF syscall command BPF_MAP_GET_NEXT_KEY for the
   stacktrace map. It is currently unimplemented, but there are
   use cases where user space needs to walk all stacktrace map
   entries e.g. for dumping or deleting map entries w/o having to
   close and recreate the map. Add BPF selftests along with it,
   from Yonghong.

5) Few follow-up cleanups for the bpftool cgroup code: i) rename
   the cgroup 'list' command into 'show' as we have it for other
   subcommands as well, ii) then alias the 'show' command such that
   'list' is accepted which is also common practice in iproute2,
   and iii) remove couple of newlines from error messages using
   p_err(), from Jakub.

6) Two follow-up cleanups to sockmap code: i) remove the unused
   bpf_compute_data_end_sk_skb() function and ii) only build the
   sockmap infrastructure when CONFIG_INET is enabled since it's
   only aware of TCP sockets at this time, from John.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

4 files changed, 152 insertions, 11 deletions

diff --git a/net/core/Makefile b/net/core/Makefile
index 1fd0a9c88b1b..6dbbba8c57ae 100644
--- a/net/core/Makefile
+++ b/net/core/Makefile
@@ -11,7 +11,7 @@ obj-$(CONFIG_SYSCTL) += sysctl_net_core.o
 obj-y		     += dev.o ethtool.o dev_addr_lists.o dst.o netevent.o \
 			neighbour.o rtnetlink.o utils.o link_watch.o filter.o \
 			sock_diag.o dev_ioctl.o tso.o sock_reuseport.o \
-			fib_notifier.o
+			fib_notifier.o xdp.o
 
 obj-y += net-sysfs.o
 obj-$(CONFIG_PROC_FS) += net-procfs.o
diff --git a/net/core/dev.c b/net/core/dev.c
index 2eb66c0d9cdb..d7925ef8743d 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -3906,9 +3906,33 @@ drop:
 	return NET_RX_DROP;
 }
 
+static struct netdev_rx_queue *netif_get_rxqueue(struct sk_buff *skb)
+{
+	struct net_device *dev = skb->dev;
+	struct netdev_rx_queue *rxqueue;
+
+	rxqueue = dev->_rx;
+
+	if (skb_rx_queue_recorded(skb)) {
+		u16 index = skb_get_rx_queue(skb);
+
+		if (unlikely(index >= dev->real_num_rx_queues)) {
+			WARN_ONCE(dev->real_num_rx_queues > 1,
+				  "%s received packet on queue %u, but number "
+				  "of RX queues is %u\n",
+				  dev->name, index, dev->real_num_rx_queues);
+
+			return rxqueue; /* Return first rxqueue */
+		}
+		rxqueue += index;
+	}
+	return rxqueue;
+}
+
 static u32 netif_receive_generic_xdp(struct sk_buff *skb,
 				     struct bpf_prog *xdp_prog)
 {
+	struct netdev_rx_queue *rxqueue;
 	u32 metalen, act = XDP_DROP;
 	struct xdp_buff xdp;
 	void *orig_data;
@@ -3952,6 +3976,9 @@ static u32 netif_receive_generic_xdp(struct sk_buff *skb,
 	xdp.data_hard_start = skb->data - skb_headroom(skb);
 	orig_data = xdp.data;
 
+	rxqueue = netif_get_rxqueue(skb);
+	xdp.rxq = &rxqueue->xdp_rxq;
+
 	act = bpf_prog_run_xdp(xdp_prog, &xdp);
 
 	off = xdp.data - orig_data;
@@ -7589,12 +7616,12 @@ void netif_stacked_transfer_operstate(const struct net_device *rootdev,
 }
 EXPORT_SYMBOL(netif_stacked_transfer_operstate);
 
-#ifdef CONFIG_SYSFS
 static int netif_alloc_rx_queues(struct net_device *dev)
 {
 	unsigned int i, count = dev->num_rx_queues;
 	struct netdev_rx_queue *rx;
 	size_t sz = count * sizeof(*rx);
+	int err = 0;
 
 	BUG_ON(count < 1);
 
@@ -7604,11 +7631,39 @@ static int netif_alloc_rx_queues(struct net_device *dev)
 
 	dev->_rx = rx;
 
-	for (i = 0; i < count; i++)
+	for (i = 0; i < count; i++) {
 		rx[i].dev = dev;
+
+		/* XDP RX-queue setup */
+		err = xdp_rxq_info_reg(&rx[i].xdp_rxq, dev, i);
+		if (err < 0)
+			goto err_rxq_info;
+	}
 	return 0;
+
+err_rxq_info:
+	/* Rollback successful reg's and free other resources */
+	while (i--)
+		xdp_rxq_info_unreg(&rx[i].xdp_rxq);
+	kfree(dev->_rx);
+	dev->_rx = NULL;
+	return err;
+}
+
+static void netif_free_rx_queues(struct net_device *dev)
+{
+	unsigned int i, count = dev->num_rx_queues;
+	struct netdev_rx_queue *rx;
+
+	/* netif_alloc_rx_queues alloc failed, resources have been unreg'ed */
+	if (!dev->_rx)
+		return;
+
+	rx = dev->_rx;
+
+	for (i = 0; i < count; i++)
+		xdp_rxq_info_unreg(&rx[i].xdp_rxq);
 }
-#endif
 
 static void netdev_init_one_queue(struct net_device *dev,
 				  struct netdev_queue *queue, void *_unused)
@@ -8169,12 +8224,10 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name,
 		return NULL;
 	}
 
-#ifdef CONFIG_SYSFS
 	if (rxqs < 1) {
 		pr_err("alloc_netdev: Unable to allocate device with zero RX queues\n");
 		return NULL;
 	}
-#endif
 
 	alloc_size = sizeof(struct net_device);
 	if (sizeof_priv) {
@@ -8231,12 +8284,10 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name,
 	if (netif_alloc_netdev_queues(dev))
 		goto free_all;
 
-#ifdef CONFIG_SYSFS
 	dev->num_rx_queues = rxqs;
 	dev->real_num_rx_queues = rxqs;
 	if (netif_alloc_rx_queues(dev))
 		goto free_all;
-#endif
 
 	strcpy(dev->name, name);
 	dev->name_assign_type = name_assign_type;
@@ -8275,9 +8326,7 @@ void free_netdev(struct net_device *dev)
 
 	might_sleep();
 	netif_free_tx_queues(dev);
-#ifdef CONFIG_SYSFS
-	kvfree(dev->_rx);
-#endif
+	netif_free_rx_queues(dev);
 
 	kfree(rcu_dereference_protected(dev->ingress_queue, 1));
 
diff --git a/net/core/filter.c b/net/core/filter.c
index 130b842c3a15..acdb94c0e97f 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -4304,6 +4304,25 @@ static u32 xdp_convert_ctx_access(enum bpf_access_type type,
 				      si->dst_reg, si->src_reg,
 				      offsetof(struct xdp_buff, data_end));
 		break;
+	case offsetof(struct xdp_md, ingress_ifindex):
+		*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct xdp_buff, rxq),
+				      si->dst_reg, si->src_reg,
+				      offsetof(struct xdp_buff, rxq));
+		*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct xdp_rxq_info, dev),
+				      si->dst_reg, si->dst_reg,
+				      offsetof(struct xdp_rxq_info, dev));
+		*insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg,
+				      bpf_target_off(struct net_device,
+						     ifindex, 4, target_size));
+		break;
+	case offsetof(struct xdp_md, rx_queue_index):
+		*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct xdp_buff, rxq),
+				      si->dst_reg, si->src_reg,
+				      offsetof(struct xdp_buff, rxq));
+		*insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg,
+				      bpf_target_off(struct xdp_rxq_info,
+						queue_index, 4, target_size));
+		break;
 	}
 
 	return insn - insn_buf;
diff --git a/net/core/xdp.c b/net/core/xdp.c
new file mode 100644
index 000000000000..097a0f74e004
--- /dev/null
+++ b/net/core/xdp.c
@@ -0,0 +1,73 @@
+/* net/core/xdp.c
+ *
+ * Copyright (c) 2017 Jesper Dangaard Brouer, Red Hat Inc.
+ * Released under terms in GPL version 2.  See COPYING.
+ */
+#include <linux/types.h>
+#include <linux/mm.h>
+
+#include <net/xdp.h>
+
+#define REG_STATE_NEW		0x0
+#define REG_STATE_REGISTERED	0x1
+#define REG_STATE_UNREGISTERED	0x2
+#define REG_STATE_UNUSED	0x3
+
+void xdp_rxq_info_unreg(struct xdp_rxq_info *xdp_rxq)
+{
+	/* Simplify driver cleanup code paths, allow unreg "unused" */
+	if (xdp_rxq->reg_state == REG_STATE_UNUSED)
+		return;
+
+	WARN(!(xdp_rxq->reg_state == REG_STATE_REGISTERED), "Driver BUG");
+
+	xdp_rxq->reg_state = REG_STATE_UNREGISTERED;
+	xdp_rxq->dev = NULL;
+}
+EXPORT_SYMBOL_GPL(xdp_rxq_info_unreg);
+
+static void xdp_rxq_info_init(struct xdp_rxq_info *xdp_rxq)
+{
+	memset(xdp_rxq, 0, sizeof(*xdp_rxq));
+}
+
+/* Returns 0 on success, negative on failure */
+int xdp_rxq_info_reg(struct xdp_rxq_info *xdp_rxq,
+		     struct net_device *dev, u32 queue_index)
+{
+	if (xdp_rxq->reg_state == REG_STATE_UNUSED) {
+		WARN(1, "Driver promised not to register this");
+		return -EINVAL;
+	}
+
+	if (xdp_rxq->reg_state == REG_STATE_REGISTERED) {
+		WARN(1, "Missing unregister, handled but fix driver");
+		xdp_rxq_info_unreg(xdp_rxq);
+	}
+
+	if (!dev) {
+		WARN(1, "Missing net_device from driver");
+		return -ENODEV;
+	}
+
+	/* State either UNREGISTERED or NEW */
+	xdp_rxq_info_init(xdp_rxq);
+	xdp_rxq->dev = dev;
+	xdp_rxq->queue_index = queue_index;
+
+	xdp_rxq->reg_state = REG_STATE_REGISTERED;
+	return 0;
+}
+EXPORT_SYMBOL_GPL(xdp_rxq_info_reg);
+
+void xdp_rxq_info_unused(struct xdp_rxq_info *xdp_rxq)
+{
+	xdp_rxq->reg_state = REG_STATE_UNUSED;
+}
+EXPORT_SYMBOL_GPL(xdp_rxq_info_unused);
+
+bool xdp_rxq_info_is_reg(struct xdp_rxq_info *xdp_rxq)
+{
+	return (xdp_rxq->reg_state == REG_STATE_REGISTERED);
+}
+EXPORT_SYMBOL_GPL(xdp_rxq_info_is_reg);