bpf: Add support for XDP programs in DEVMAP entries

index a51d9fb7a359..a1459de0914e 100644
@@ -60,12 +60,18 @@ struct xdp_dev_bulk_queue {
 	unsigned int count;
 };
 
+/* DEVMAP values */
+struct bpf_devmap_val {
+	u32 ifindex;   /* device index */
+};
+
 struct bpf_dtab_netdev {
 	struct net_device *dev; /* must be first member, due to tracepoint */
 	struct hlist_node index_hlist;
 	struct bpf_dtab *dtab;
 	struct rcu_head rcu;
 	unsigned int idx;
+	struct bpf_devmap_val val;
 };
 
 struct bpf_dtab {

@@ -472,18 +478,15 @@ int dev_map_generic_redirect(struct bpf_dtab_netdev *dst, struct sk_buff *skb,
 static void *dev_map_lookup_elem(struct bpf_map *map, void *key)
 {
 	struct bpf_dtab_netdev *obj = __dev_map_lookup_elem(map, *(u32 *)key);
-	struct net_device *dev = obj ? obj->dev : NULL;
 
-	return dev ? &dev->ifindex : NULL;
+	return obj ? &obj->val : NULL;
 }
 
 static void *dev_map_hash_lookup_elem(struct bpf_map *map, void *key)
 {
 	struct bpf_dtab_netdev *obj = __dev_map_hash_lookup_elem(map,
 								*(u32 *)key);
-	struct net_device *dev = obj ? obj->dev : NULL;
-
-	return dev ? &dev->ifindex : NULL;
+	return obj ? &obj->val : NULL;
 }
 
 static void __dev_map_entry_free(struct rcu_head *rcu)

@@ -541,7 +544,7 @@ static int dev_map_hash_delete_elem(struct bpf_map *map, void *key)
 
 static struct bpf_dtab_netdev *__dev_map_alloc_node(struct net *net,
 						    struct bpf_dtab *dtab,
-						    u32 ifindex,
+						    struct bpf_devmap_val *val,
 						    unsigned int idx)
 {
 	struct bpf_dtab_netdev *dev;

@@ -551,16 +554,18 @@ static struct bpf_dtab_netdev *__dev_map_alloc_node(struct net *net,
 	if (!dev)
 		return ERR_PTR(-ENOMEM);
 
-	dev->dev = dev_get_by_index(net, ifindex);
-	if (!dev->dev) {
-		kfree(dev);
-		return ERR_PTR(-EINVAL);
-	}
+	dev->dev = dev_get_by_index(net, val->ifindex);
+	if (!dev->dev)
+		goto err_out;
 
 	dev->idx = idx;
 	dev->dtab = dtab;
+	dev->val.ifindex = val->ifindex;
 
 	return dev;
+err_out:
+	kfree(dev);
+	return ERR_PTR(-EINVAL);
 }
 
 static int __dev_map_update_elem(struct net *net, struct bpf_map *map,

@@ -568,7 +573,7 @@ static int __dev_map_update_elem(struct net *net, struct bpf_map *map,
 {
 	struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map);
 	struct bpf_dtab_netdev *dev, *old_dev;
-	u32 ifindex = *(u32 *)value;
+	struct bpf_devmap_val val = { };
 	u32 i = *(u32 *)key;
 
 	if (unlikely(map_flags > BPF_EXIST))

@@ -578,10 +583,13 @@ static int __dev_map_update_elem(struct net *net, struct bpf_map *map,
 	if (unlikely(map_flags == BPF_NOEXIST))
 		return -EEXIST;
 
-	if (!ifindex) {
+	/* already verified value_size <= sizeof val */
+	memcpy(&val, value, map->value_size);
+
+	if (!val.ifindex) {
 		dev = NULL;
 	} else {
-		dev = __dev_map_alloc_node(net, dtab, ifindex, i);
+		dev = __dev_map_alloc_node(net, dtab, &val, i);
 		if (IS_ERR(dev))
 			return PTR_ERR(dev);
 	}

@@ -609,12 +617,15 @@ static int __dev_map_hash_update_elem(struct net *net, struct bpf_map *map,
 {
 	struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map);
 	struct bpf_dtab_netdev *dev, *old_dev;
-	u32 ifindex = *(u32 *)value;
+	struct bpf_devmap_val val = { };
 	u32 idx = *(u32 *)key;
 	unsigned long flags;
 	int err = -EEXIST;
 
-	if (unlikely(map_flags > BPF_EXIST || !ifindex))
+	/* already verified value_size <= sizeof val */
+	memcpy(&val, value, map->value_size);
+
+	if (unlikely(map_flags > BPF_EXIST || !val.ifindex))
 		return -EINVAL;
 
 	spin_lock_irqsave(&dtab->index_lock, flags);

@@ -623,7 +634,7 @@ static int __dev_map_hash_update_elem(struct net *net, struct bpf_map *map,
 	if (old_dev && (map_flags & BPF_NOEXIST))
 		goto out_err;
 
-	dev = __dev_map_alloc_node(net, dtab, ifindex, idx);
+	dev = __dev_map_alloc_node(net, dtab, &val, idx);
 	if (IS_ERR(dev)) {
 		err = PTR_ERR(dev);
 		goto out_err;

index e5884f7f801c..e042311f991f 100644
@@ -1250,6 +1250,7 @@ int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp,
 		    struct net_device *dev_rx);
 int dev_map_generic_redirect(struct bpf_dtab_netdev *dst, struct sk_buff *skb,
 			     struct bpf_prog *xdp_prog);
+bool dev_map_can_have_prog(struct bpf_map *map);
 
 struct bpf_cpu_map_entry *__cpu_map_lookup_elem(struct bpf_map *map, u32 key);
 void __cpu_map_flush(void);

@@ -1363,6 +1364,10 @@ static inline struct net_device  *__dev_map_hash_lookup_elem(struct bpf_map *map
 {
 	return NULL;
 }
+static inline bool dev_map_can_have_prog(struct bpf_map *map)
+{
+	return false;
+}
 
 static inline void __dev_flush(void)
 {

index 974ca6e948e3..65d7717bce2f 100644
@@ -225,6 +225,7 @@ enum bpf_attach_type {
 	BPF_CGROUP_INET6_GETPEERNAME,
 	BPF_CGROUP_INET4_GETSOCKNAME,
 	BPF_CGROUP_INET6_GETSOCKNAME,
+	BPF_XDP_DEVMAP,
 	__MAX_BPF_ATTACH_TYPE
 };
 

183 lines not on this page · raw message

index ae37586f6ee8..10684833f864 100644
@@ -5420,6 +5420,18 @@ static int generic_xdp_install(struct net_device *dev, struct netdev_bpf *xdp)
 	struct bpf_prog *new = xdp->prog;
 	int ret = 0;
 
+	if (new) {
+		u32 i;
+
+		/* generic XDP does not work with DEVMAPs that can
+		 * have a bpf_prog installed on an entry
+		 */
+		for (i = 0; i < new->aux->used_map_cnt; i++) {
+			if (dev_map_can_have_prog(new->aux->used_maps[i]))
+				return -EINVAL;
+		}
+	}
+
 	switch (xdp->command) {
 	case XDP_SETUP_PROG:
 		rcu_assign_pointer(dev->xdp_prog, new);

@@ -8835,6 +8847,12 @@ int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack,
 			return -EINVAL;
 		}
 
+		if (prog->expected_attach_type == BPF_XDP_DEVMAP) {
+			NL_SET_ERR_MSG(extack, "BPF_XDP_DEVMAP programs can not be attached to a device");
+			bpf_prog_put(prog);
+			return -EINVAL;
+		}
+
 		/* prog->aux->id may be 0 for orphaned device-bound progs */
 		if (prog->aux->id && prog->aux->id == prog_id) {
 			bpf_prog_put(prog);

index 974ca6e948e3..65d7717bce2f 100644
@@ -225,6 +225,7 @@ enum bpf_attach_type {
 	BPF_CGROUP_INET6_GETPEERNAME,
 	BPF_CGROUP_INET4_GETSOCKNAME,
 	BPF_CGROUP_INET6_GETSOCKNAME,
+	BPF_XDP_DEVMAP,
 	__MAX_BPF_ATTACH_TYPE
 };
 

index 90f11760bd12..d54022959491 100644
@@ -61,12 +61,17 @@ struct xdp_rxq_info {
 	struct xdp_mem_info mem;
 } ____cacheline_aligned; /* perf critical, avoid false-sharing */
 
+struct xdp_txq_info {
+	struct net_device *dev;
+};
+
 struct xdp_buff {
 	void *data;
 	void *data_end;
 	void *data_meta;
 	void *data_hard_start;
 	struct xdp_rxq_info *rxq;
+	struct xdp_txq_info *txq;
 	u32 frame_sz; /* frame size to deduce data_hard_end/reserved tailroom*/
 };
 

index 65d7717bce2f..f74bc4a2385e 100644
@@ -3706,6 +3706,8 @@ struct xdp_md {
 	/* Below access go through struct xdp_rxq_info */
 	__u32 ingress_ifindex; /* rxq->dev->ifindex */
 	__u32 rx_queue_index;  /* rxq->queue_index  */
+
+	__u32 egress_ifindex;  /* txq->dev->ifindex */
 };
 
 enum sk_action {

index 0089d56617ec..c04fb1c72f5e 100644
@@ -476,8 +476,11 @@ static struct xdp_buff *dev_map_run_prog(struct net_device *dev,
 					 struct xdp_buff *xdp,
 					 struct bpf_prog *xdp_prog)
 {
+	struct xdp_txq_info txq = { .dev = dev };
 	u32 act;
 
+	xdp->txq = &txq;
+
 	act = bpf_prog_run_xdp(xdp_prog, xdp);
 	switch (act) {
 	case XDP_PASS:

index a6fc23447f12..2e9dbfd8e60c 100644
@@ -7014,6 +7014,13 @@ static bool xdp_is_valid_access(int off, int size,
 				const struct bpf_prog *prog,
 				struct bpf_insn_access_aux *info)
 {
+	if (prog->expected_attach_type != BPF_XDP_DEVMAP) {
+		switch (off) {
+		case offsetof(struct xdp_md, egress_ifindex):
+			return false;
+		}
+	}
+
 	if (type == BPF_WRITE) {
 		if (bpf_prog_is_dev_bound(prog->aux)) {
 			switch (off) {

@@ -7967,6 +7974,16 @@ static u32 xdp_convert_ctx_access(enum bpf_access_type type,
 				      offsetof(struct xdp_rxq_info,
 					       queue_index));
 		break;
+	case offsetof(struct xdp_md, egress_ifindex):
+		*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct xdp_buff, txq),
+				      si->dst_reg, si->src_reg,
+				      offsetof(struct xdp_buff, txq));
+		*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct xdp_txq_info, dev),
+				      si->dst_reg, si->dst_reg,
+				      offsetof(struct xdp_txq_info, dev));
+		*insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg,
+				      offsetof(struct net_device, ifindex));
+		break;
 	}
 
 	return insn - insn_buf;

index 65d7717bce2f..f74bc4a2385e 100644
@@ -3706,6 +3706,8 @@ struct xdp_md {
 	/* Below access go through struct xdp_rxq_info */
 	__u32 ingress_ifindex; /* rxq->dev->ifindex */
 	__u32 rx_queue_index;  /* rxq->queue_index  */
+
+	__u32 egress_ifindex;  /* txq->dev->ifindex */
 };
 
 enum sk_action {

index 74d967619dcf..85d4f1c5fc52 100644
@@ -6657,6 +6657,8 @@ static const struct bpf_sec_def section_defs[] = {
 		.expected_attach_type = BPF_TRACE_ITER,
 		.is_attach_btf = true,
 		.attach_fn = attach_iter),
+	BPF_EAPROG_SEC("xdp_devmap",		BPF_PROG_TYPE_XDP,
+						BPF_XDP_DEVMAP),
 	BPF_PROG_SEC("xdp",			BPF_PROG_TYPE_XDP),
 	BPF_PROG_SEC("perf_event",		BPF_PROG_TYPE_PERF_EVENT),
 	BPF_PROG_SEC("lwt_in",			BPF_PROG_TYPE_LWT_IN),

new file mode 100644
index 000000000000..8454d5b96058
@@ -0,0 +1,97 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <uapi/linux/bpf.h>
+#include <linux/if_link.h>
+#include <test_progs.h>
+
+#include "test_xdp_devmap_helpers.skel.h"
+#include "test_xdp_with_devmap_helpers.skel.h"
+
+#define IFINDEX_LO 1
+
+struct bpf_devmap_val {
+	u32 ifindex;   /* device index */
+	union {
+		int fd;  /* prog fd on map write */
+		u32 id;  /* prog id on map read */
+	} bpf_prog;
+};
+
+void test_xdp_with_devmap_helpers(void)
+{
+	struct test_xdp_with_devmap_helpers *skel;
+	struct bpf_prog_info info = {};
+	struct bpf_devmap_val val = {
+		.ifindex = IFINDEX_LO,
+	};
+	__u32 len = sizeof(info);
+	__u32 duration, idx = 0;
+	int err, dm_fd, map_fd;
+
+
+	skel = test_xdp_with_devmap_helpers__open_and_load();
+	if (CHECK_FAIL(!skel)) {
+		perror("test_xdp_with_devmap_helpers__open_and_load");
+		return;
+	}
+
+	/* can not attach program with DEVMAPs that allow programs
+	 * as xdp generic
+	 */
+	dm_fd = bpf_program__fd(skel->progs.xdp_redir_prog);
+	err = bpf_set_link_xdp_fd(IFINDEX_LO, dm_fd, XDP_FLAGS_SKB_MODE);
+	CHECK(err == 0, "Generic attach of program with 8-byte devmap",
+	      "should have failed\n");
+
+	dm_fd = bpf_program__fd(skel->progs.xdp_dummy_dm);
+	map_fd = bpf_map__fd(skel->maps.dm_ports);
+	err = bpf_obj_get_info_by_fd(dm_fd, &info, &len);
+	if (CHECK_FAIL(err))
+		goto out_close;
+
+	val.bpf_prog.fd = dm_fd;
+	err = bpf_map_update_elem(map_fd, &idx, &val, 0);
+	CHECK(err, "Add program to devmap entry",
+	      "err %d errno %d\n", err, errno);
+
+	err = bpf_map_lookup_elem(map_fd, &idx, &val);
+	CHECK(err, "Read devmap entry", "err %d errno %d\n", err, errno);
+	CHECK(info.id != val.bpf_prog.id, "Expected program id in devmap entry",
+	      "expected %u read %u\n", info.id, val.bpf_prog.id);
+
+	/* can not attach BPF_XDP_DEVMAP program to a device */
+	err = bpf_set_link_xdp_fd(IFINDEX_LO, dm_fd, XDP_FLAGS_SKB_MODE);
+	CHECK(err == 0, "Attach of BPF_XDP_DEVMAP program",
+	      "should have failed\n");
+
+	val.ifindex = 1;
+	val.bpf_prog.fd = bpf_program__fd(skel->progs.xdp_dummy_prog);
+	err = bpf_map_update_elem(map_fd, &idx, &val, 0);
+	CHECK(err == 0, "Add non-BPF_XDP_DEVMAP program to devmap entry",
+	      "should have failed\n");
+
+out_close:
+	test_xdp_with_devmap_helpers__destroy(skel);
+}
+
+void test_neg_xdp_devmap_helpers(void)
+{
+	struct test_xdp_devmap_helpers *skel;
+	__u32 duration;
+
+	skel = test_xdp_devmap_helpers__open_and_load();
+	if (CHECK(skel,
+		  "Load of XDP program accessing egress ifindex without attach type",
+		  "should have failed\n")) {
+		test_xdp_devmap_helpers__destroy(skel);
+	}
+}
+
+
+void test_xdp_devmap_attach(void)
+{
+	if (test__start_subtest("DEVMAP with programs in entries"))
+		test_xdp_with_devmap_helpers();
+
+	if (test__start_subtest("Verifier check of DEVMAP programs"))
+		test_neg_xdp_devmap_helpers();
+}

new file mode 100644
index 000000000000..e5c0f131c8a7
@@ -0,0 +1,22 @@
+// SPDX-License-Identifier: GPL-2.0
+/* fails to load without expected_attach_type = BPF_XDP_DEVMAP
+ * because of access to egress_ifindex
+ */
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+
+SEC("xdp_dm_log")
+int xdpdm_devlog(struct xdp_md *ctx)
+{
+	char fmt[] = "devmap redirect: dev %u -> dev %u len %u\n";
+	void *data_end = (void *)(long)ctx->data_end;
+	void *data = (void *)(long)ctx->data;
+	unsigned int len = data_end - data;
+
+	bpf_trace_printk(fmt, sizeof(fmt),
+			 ctx->ingress_ifindex, ctx->egress_ifindex, len);
+
+	return XDP_PASS;
+}
+
+char _license[] SEC("license") = "GPL";

44 lines not on this page · raw message