xdp: Support specifying expected existing program when attaching XDP

While it is currently possible for userspace to specify that an existing
XDP program should not be replaced when attaching to an interface, there is
no mechanism to safely replace a specific XDP program with another.

This patch adds a new netlink attribute, IFLA_XDP_EXPECTED_FD, which can be
set along with IFLA_XDP_FD. If set, the kernel will check that the program
currently loaded on the interface matches the expected one, and fail the
operation if it does not. This corresponds to a 'cmpxchg' memory operation.
Setting the new attribute with a negative value means that no program is
expected to be attached, which corresponds to setting the UPDATE_IF_NOEXIST
flag.

A new companion flag, XDP_FLAGS_REPLACE, is also added to explicitly
request checking of the EXPECTED_FD attribute. This is needed for userspace
to discover whether the kernel supports the new attribute.

Signed-off-by: Toke Høiland-Jørgensen <[email protected]>
Signed-off-by: Alexei Starovoitov <[email protected]>
Reviewed-by: Jakub Kicinski <[email protected]>
Link: https://lore.kernel.org/bpf/[email protected]

Author: tohojo

include/linux/netdevice.h

@@ -3768,7 +3768,7 @@ struct sk_buff *dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev,
 
 typedef int (*bpf_op_t)(struct net_device *dev, struct netdev_bpf *bpf);
 int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack,
-		      int fd, u32 flags);
+		      int fd, int expected_fd, u32 flags);
 u32 __dev_xdp_query(struct net_device *dev, bpf_op_t xdp_op,
 		    enum bpf_netdev_command cmd);
 int xdp_umem_query(struct net_device *dev, u16 queue_id);

include/uapi/linux/if_link.h

@@ -972,11 +972,12 @@ enum {
 #define XDP_FLAGS_SKB_MODE		(1U << 1)
 #define XDP_FLAGS_DRV_MODE		(1U << 2)
 #define XDP_FLAGS_HW_MODE		(1U << 3)
+#define XDP_FLAGS_REPLACE		(1U << 4)
 #define XDP_FLAGS_MODES			(XDP_FLAGS_SKB_MODE | \
 					 XDP_FLAGS_DRV_MODE | \
 					 XDP_FLAGS_HW_MODE)
 #define XDP_FLAGS_MASK			(XDP_FLAGS_UPDATE_IF_NOEXIST | \
-					 XDP_FLAGS_MODES)
+					 XDP_FLAGS_MODES | XDP_FLAGS_REPLACE)
 
 /* These are stored into IFLA_XDP_ATTACHED on dump. */
 enum {
@@ -996,6 +997,7 @@ enum {
 	IFLA_XDP_DRV_PROG_ID,
 	IFLA_XDP_SKB_PROG_ID,
 	IFLA_XDP_HW_PROG_ID,
+	IFLA_XDP_EXPECTED_FD,
 	__IFLA_XDP_MAX,
 };
 

net/core/dev.c

@@ -8655,15 +8655,17 @@ static void dev_xdp_uninstall(struct net_device *dev)
  *	@dev: device
  *	@extack: netlink extended ack
  *	@fd: new program fd or negative value to clear
+ *	@expected_fd: old program fd that userspace expects to replace or clear
  *	@flags: xdp-related flags
  *
  *	Set or clear a bpf program for a device
  */
 int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack,
-		      int fd, u32 flags)
+		      int fd, int expected_fd, u32 flags)
 {
 	const struct net_device_ops *ops = dev->netdev_ops;
 	enum bpf_netdev_command query;
+	u32 prog_id, expected_id = 0;
 	struct bpf_prog *prog = NULL;
 	bpf_op_t bpf_op, bpf_chk;
 	bool offload;
@@ -8684,15 +8686,29 @@ int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack,
 	if (bpf_op == bpf_chk)
 		bpf_chk = generic_xdp_install;
 
-	if (fd >= 0) {
-		u32 prog_id;
+	prog_id = __dev_xdp_query(dev, bpf_op, query);
+	if (flags & XDP_FLAGS_REPLACE) {
+		if (expected_fd >= 0) {
+			prog = bpf_prog_get_type_dev(expected_fd,
+						     BPF_PROG_TYPE_XDP,
+						     bpf_op == ops->ndo_bpf);
+			if (IS_ERR(prog))
+				return PTR_ERR(prog);
+			expected_id = prog->aux->id;
+			bpf_prog_put(prog);
+		}
 
+		if (prog_id != expected_id) {
+			NL_SET_ERR_MSG(extack, "Active program does not match expected");
+			return -EEXIST;
+		}
+	}
+	if (fd >= 0) {
 		if (!offload && __dev_xdp_query(dev, bpf_chk, XDP_QUERY_PROG)) {
 			NL_SET_ERR_MSG(extack, "native and generic XDP can't be active at the same time");
 			return -EEXIST;
 		}
 
-		prog_id = __dev_xdp_query(dev, bpf_op, query);
 		if ((flags & XDP_FLAGS_UPDATE_IF_NOEXIST) && prog_id) {
 			NL_SET_ERR_MSG(extack, "XDP program already attached");
 			return -EBUSY;
@@ -8715,7 +8731,7 @@ int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack,
 			return 0;
 		}
 	} else {
-		if (!__dev_xdp_query(dev, bpf_op, query))
+		if (!prog_id)
 			return 0;
 	}
 

net/core/rtnetlink.c

@@ -1872,7 +1872,9 @@ static const struct nla_policy ifla_port_policy[IFLA_PORT_MAX+1] = {
 };
 
 static const struct nla_policy ifla_xdp_policy[IFLA_XDP_MAX + 1] = {
+	[IFLA_XDP_UNSPEC]	= { .strict_start_type = IFLA_XDP_EXPECTED_FD },
 	[IFLA_XDP_FD]		= { .type = NLA_S32 },
+	[IFLA_XDP_EXPECTED_FD]	= { .type = NLA_S32 },
 	[IFLA_XDP_ATTACHED]	= { .type = NLA_U8 },
 	[IFLA_XDP_FLAGS]	= { .type = NLA_U32 },
 	[IFLA_XDP_PROG_ID]	= { .type = NLA_U32 },
@@ -2799,8 +2801,20 @@ static int do_setlink(const struct sk_buff *skb,
 		}
 
 		if (xdp[IFLA_XDP_FD]) {
+			int expected_fd = -1;
+
+			if (xdp_flags & XDP_FLAGS_REPLACE) {
+				if (!xdp[IFLA_XDP_EXPECTED_FD]) {
+					err = -EINVAL;
+					goto errout;
+				}
+				expected_fd =
+					nla_get_s32(xdp[IFLA_XDP_EXPECTED_FD]);
+			}
+
 			err = dev_change_xdp_fd(dev, extack,
 						nla_get_s32(xdp[IFLA_XDP_FD]),
+						expected_fd,
 						xdp_flags);
 			if (err)
 				goto errout;