From 5ce6e77c7edf7310a0ff9532fd6b9693c082ab32 Mon Sep 17 00:00:00 2001
From: Yonghong Song <yhs@fb.com>
Date: Thu, 23 Jul 2020 11:41:16 -0700
Subject: bpf: Implement bpf iterator for sock local storage map

The bpf iterator for bpf sock local storage map
is implemented. User space interacts with sock
local storage map with fd as a key and storage value.
In kernel, passing fd to the bpf program does not
really make sense. In this case, the sock itself is
passed to bpf program.

Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20200723184116.590602-1-yhs@fb.com
---
 net/core/bpf_sk_storage.c | 206 ++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 206 insertions(+)

(limited to 'net/core')

diff --git a/net/core/bpf_sk_storage.c b/net/core/bpf_sk_storage.c
index 6f921c4ddc2c..eafcd15e7dfd 100644
--- a/net/core/bpf_sk_storage.c
+++ b/net/core/bpf_sk_storage.c
@@ -6,6 +6,7 @@
 #include <linux/types.h>
 #include <linux/spinlock.h>
 #include <linux/bpf.h>
+#include <linux/btf_ids.h>
 #include <net/bpf_sk_storage.h>
 #include <net/sock.h>
 #include <uapi/linux/sock_diag.h>
@@ -1217,3 +1218,208 @@ int bpf_sk_storage_diag_put(struct bpf_sk_storage_diag *diag,
 	return err;
 }
 EXPORT_SYMBOL_GPL(bpf_sk_storage_diag_put);
+
+struct bpf_iter_seq_sk_storage_map_info {
+	struct bpf_map *map;
+	unsigned int bucket_id;
+	unsigned skip_elems;
+};
+
+static struct bpf_sk_storage_elem *
+bpf_sk_storage_map_seq_find_next(struct bpf_iter_seq_sk_storage_map_info *info,
+				 struct bpf_sk_storage_elem *prev_selem)
+{
+	struct bpf_sk_storage *sk_storage;
+	struct bpf_sk_storage_elem *selem;
+	u32 skip_elems = info->skip_elems;
+	struct bpf_sk_storage_map *smap;
+	u32 bucket_id = info->bucket_id;
+	u32 i, count, n_buckets;
+	struct bucket *b;
+
+	smap = (struct bpf_sk_storage_map *)info->map;
+	n_buckets = 1U << smap->bucket_log;
+	if (bucket_id >= n_buckets)
+		return NULL;
+
+	/* try to find next selem in the same bucket */
+	selem = prev_selem;
+	count = 0;
+	while (selem) {
+		selem = hlist_entry_safe(selem->map_node.next,
+					 struct bpf_sk_storage_elem, map_node);
+		if (!selem) {
+			/* not found, unlock and go to the next bucket */
+			b = &smap->buckets[bucket_id++];
+			raw_spin_unlock_bh(&b->lock);
+			skip_elems = 0;
+			break;
+		}
+		sk_storage = rcu_dereference_raw(selem->sk_storage);
+		if (sk_storage) {
+			info->skip_elems = skip_elems + count;
+			return selem;
+		}
+		count++;
+	}
+
+	for (i = bucket_id; i < (1U << smap->bucket_log); i++) {
+		b = &smap->buckets[i];
+		raw_spin_lock_bh(&b->lock);
+		count = 0;
+		hlist_for_each_entry(selem, &b->list, map_node) {
+			sk_storage = rcu_dereference_raw(selem->sk_storage);
+			if (sk_storage && count >= skip_elems) {
+				info->bucket_id = i;
+				info->skip_elems = count;
+				return selem;
+			}
+			count++;
+		}
+		raw_spin_unlock_bh(&b->lock);
+		skip_elems = 0;
+	}
+
+	info->bucket_id = i;
+	info->skip_elems = 0;
+	return NULL;
+}
+
+static void *bpf_sk_storage_map_seq_start(struct seq_file *seq, loff_t *pos)
+{
+	struct bpf_sk_storage_elem *selem;
+
+	selem = bpf_sk_storage_map_seq_find_next(seq->private, NULL);
+	if (!selem)
+		return NULL;
+
+	if (*pos == 0)
+		++*pos;
+	return selem;
+}
+
+static void *bpf_sk_storage_map_seq_next(struct seq_file *seq, void *v,
+					 loff_t *pos)
+{
+	struct bpf_iter_seq_sk_storage_map_info *info = seq->private;
+
+	++*pos;
+	++info->skip_elems;
+	return bpf_sk_storage_map_seq_find_next(seq->private, v);
+}
+
+struct bpf_iter__bpf_sk_storage_map {
+	__bpf_md_ptr(struct bpf_iter_meta *, meta);
+	__bpf_md_ptr(struct bpf_map *, map);
+	__bpf_md_ptr(struct sock *, sk);
+	__bpf_md_ptr(void *, value);
+};
+
+DEFINE_BPF_ITER_FUNC(bpf_sk_storage_map, struct bpf_iter_meta *meta,
+		     struct bpf_map *map, struct sock *sk,
+		     void *value)
+
+static int __bpf_sk_storage_map_seq_show(struct seq_file *seq,
+					 struct bpf_sk_storage_elem *selem)
+{
+	struct bpf_iter_seq_sk_storage_map_info *info = seq->private;
+	struct bpf_iter__bpf_sk_storage_map ctx = {};
+	struct bpf_sk_storage *sk_storage;
+	struct bpf_iter_meta meta;
+	struct bpf_prog *prog;
+	int ret = 0;
+
+	meta.seq = seq;
+	prog = bpf_iter_get_info(&meta, selem == NULL);
+	if (prog) {
+		ctx.meta = &meta;
+		ctx.map = info->map;
+		if (selem) {
+			sk_storage = rcu_dereference_raw(selem->sk_storage);
+			ctx.sk = sk_storage->sk;
+			ctx.value = SDATA(selem)->data;
+		}
+		ret = bpf_iter_run_prog(prog, &ctx);
+	}
+
+	return ret;
+}
+
+static int bpf_sk_storage_map_seq_show(struct seq_file *seq, void *v)
+{
+	return __bpf_sk_storage_map_seq_show(seq, v);
+}
+
+static void bpf_sk_storage_map_seq_stop(struct seq_file *seq, void *v)
+{
+	struct bpf_iter_seq_sk_storage_map_info *info = seq->private;
+	struct bpf_sk_storage_map *smap;
+	struct bucket *b;
+
+	if (!v) {
+		(void)__bpf_sk_storage_map_seq_show(seq, v);
+	} else {
+		smap = (struct bpf_sk_storage_map *)info->map;
+		b = &smap->buckets[info->bucket_id];
+		raw_spin_unlock_bh(&b->lock);
+	}
+}
+
+static int bpf_iter_init_sk_storage_map(void *priv_data,
+					struct bpf_iter_aux_info *aux)
+{
+	struct bpf_iter_seq_sk_storage_map_info *seq_info = priv_data;
+
+	seq_info->map = aux->map;
+	return 0;
+}
+
+static int bpf_iter_check_map(struct bpf_prog *prog,
+			      struct bpf_iter_aux_info *aux)
+{
+	struct bpf_map *map = aux->map;
+
+	if (map->map_type != BPF_MAP_TYPE_SK_STORAGE)
+		return -EINVAL;
+
+	if (prog->aux->max_rdonly_access > map->value_size)
+		return -EACCES;
+
+	return 0;
+}
+
+static const struct seq_operations bpf_sk_storage_map_seq_ops = {
+	.start  = bpf_sk_storage_map_seq_start,
+	.next   = bpf_sk_storage_map_seq_next,
+	.stop   = bpf_sk_storage_map_seq_stop,
+	.show   = bpf_sk_storage_map_seq_show,
+};
+
+static const struct bpf_iter_seq_info iter_seq_info = {
+	.seq_ops		= &bpf_sk_storage_map_seq_ops,
+	.init_seq_private	= bpf_iter_init_sk_storage_map,
+	.fini_seq_private	= NULL,
+	.seq_priv_size		= sizeof(struct bpf_iter_seq_sk_storage_map_info),
+};
+
+static struct bpf_iter_reg bpf_sk_storage_map_reg_info = {
+	.target			= "bpf_sk_storage_map",
+	.check_target		= bpf_iter_check_map,
+	.req_linfo		= BPF_ITER_LINK_MAP_FD,
+	.ctx_arg_info_size	= 2,
+	.ctx_arg_info		= {
+		{ offsetof(struct bpf_iter__bpf_sk_storage_map, sk),
+		  PTR_TO_BTF_ID_OR_NULL },
+		{ offsetof(struct bpf_iter__bpf_sk_storage_map, value),
+		  PTR_TO_RDWR_BUF_OR_NULL },
+	},
+	.seq_info		= &iter_seq_info,
+};
+
+static int __init bpf_sk_storage_map_iter_init(void)
+{
+	bpf_sk_storage_map_reg_info.ctx_arg_info[0].btf_id =
+		btf_sock_ids[BTF_SOCK_TYPE_SOCK];
+	return bpf_iter_reg_target(&bpf_sk_storage_map_reg_info);
+}
+late_initcall(bpf_sk_storage_map_iter_init);
-- 
cgit v1.2.3


From 7f0a838254bdd9114b978ef2541a6ce330307e9e Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andriin@fb.com>
Date: Tue, 21 Jul 2020 23:45:55 -0700
Subject: bpf, xdp: Maintain info on attached XDP BPF programs in net_device

Instead of delegating to drivers, maintain information about which BPF
programs are attached in which XDP modes (generic/skb, driver, or hardware)
locally in net_device. This effectively obsoletes XDP_QUERY_PROG command.

Such re-organization simplifies existing code already. But it also allows to
further add bpf_link-based XDP attachments without drivers having to know
about any of this at all, which seems like a good setup.
XDP_SETUP_PROG/XDP_SETUP_PROG_HW are just low-level commands to driver to
install/uninstall active BPF program. All the higher-level concerns about
prog/link interaction will be contained within generic driver-agnostic logic.

All the XDP_QUERY_PROG calls to driver in dev_xdp_uninstall() were removed.
It's not clear for me why dev_xdp_uninstall() were passing previous prog_flags
when resetting installed programs. That seems unnecessary, plus most drivers
don't populate prog_flags anyways. Having XDP_SETUP_PROG vs XDP_SETUP_PROG_HW
should be enough of an indicator of what is required of driver to correctly
reset active BPF program. dev_xdp_uninstall() is also generalized as an
iteration over all three supported mode.

Signed-off-by: Andrii Nakryiko <andriin@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20200722064603.3350758-3-andriin@fb.com
---
 include/linux/netdevice.h |  17 ++++-
 net/core/dev.c            | 158 ++++++++++++++++++++++++++--------------------
 net/core/rtnetlink.c      |   5 +-
 3 files changed, 105 insertions(+), 75 deletions(-)

(limited to 'net/core')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index ac2cd3f49aba..cad44b40c776 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -889,6 +889,17 @@ struct netlink_ext_ack;
 struct xdp_umem;
 struct xdp_dev_bulk_queue;
 
+enum bpf_xdp_mode {
+	XDP_MODE_SKB = 0,
+	XDP_MODE_DRV = 1,
+	XDP_MODE_HW = 2,
+	__MAX_XDP_MODE
+};
+
+struct bpf_xdp_entity {
+	struct bpf_prog *prog;
+};
+
 struct netdev_bpf {
 	enum bpf_netdev_command command;
 	union {
@@ -2142,6 +2153,9 @@ struct net_device {
 #endif
 	const struct udp_tunnel_nic_info	*udp_tunnel_nic_info;
 	struct udp_tunnel_nic	*udp_tunnel_nic;
+
+	/* protected by rtnl_lock */
+	struct bpf_xdp_entity	xdp_state[__MAX_XDP_MODE];
 };
 #define to_net_dev(d) container_of(d, struct net_device, dev)
 
@@ -3817,8 +3831,7 @@ 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, int expected_fd, u32 flags);
-u32 __dev_xdp_query(struct net_device *dev, bpf_op_t xdp_op,
-		    enum bpf_netdev_command cmd);
+u32 dev_xdp_prog_id(struct net_device *dev, enum bpf_xdp_mode mode);
 int xdp_umem_query(struct net_device *dev, u16 queue_id);
 
 int __dev_forward_skb(struct net_device *dev, struct sk_buff *skb);
diff --git a/net/core/dev.c b/net/core/dev.c
index fe2e387eed29..bf38fde667e9 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -8716,84 +8716,103 @@ int dev_change_proto_down_generic(struct net_device *dev, bool proto_down)
 }
 EXPORT_SYMBOL(dev_change_proto_down_generic);
 
-u32 __dev_xdp_query(struct net_device *dev, bpf_op_t bpf_op,
-		    enum bpf_netdev_command cmd)
+static enum bpf_xdp_mode dev_xdp_mode(u32 flags)
 {
-	struct netdev_bpf xdp;
+	if (flags & XDP_FLAGS_HW_MODE)
+		return XDP_MODE_HW;
+	if (flags & XDP_FLAGS_DRV_MODE)
+		return XDP_MODE_DRV;
+	return XDP_MODE_SKB;
+}
 
-	if (!bpf_op)
-		return 0;
+static bpf_op_t dev_xdp_bpf_op(struct net_device *dev, enum bpf_xdp_mode mode)
+{
+	switch (mode) {
+	case XDP_MODE_SKB:
+		return generic_xdp_install;
+	case XDP_MODE_DRV:
+	case XDP_MODE_HW:
+		return dev->netdev_ops->ndo_bpf;
+	default:
+		return NULL;
+	};
+}
 
-	memset(&xdp, 0, sizeof(xdp));
-	xdp.command = cmd;
+static struct bpf_prog *dev_xdp_prog(struct net_device *dev,
+				     enum bpf_xdp_mode mode)
+{
+	return dev->xdp_state[mode].prog;
+}
+
+u32 dev_xdp_prog_id(struct net_device *dev, enum bpf_xdp_mode mode)
+{
+	struct bpf_prog *prog = dev_xdp_prog(dev, mode);
 
-	/* Query must always succeed. */
-	WARN_ON(bpf_op(dev, &xdp) < 0 && cmd == XDP_QUERY_PROG);
+	return prog ? prog->aux->id : 0;
+}
 
-	return xdp.prog_id;
+static void dev_xdp_set_prog(struct net_device *dev, enum bpf_xdp_mode mode,
+			     struct bpf_prog *prog)
+{
+	dev->xdp_state[mode].prog = prog;
 }
 
-static int dev_xdp_install(struct net_device *dev, bpf_op_t bpf_op,
-			   struct netlink_ext_ack *extack, u32 flags,
-			   struct bpf_prog *prog)
+static int dev_xdp_install(struct net_device *dev, enum bpf_xdp_mode mode,
+			   bpf_op_t bpf_op, struct netlink_ext_ack *extack,
+			   u32 flags, struct bpf_prog *prog)
 {
-	bool non_hw = !(flags & XDP_FLAGS_HW_MODE);
-	struct bpf_prog *prev_prog = NULL;
 	struct netdev_bpf xdp;
 	int err;
 
-	if (non_hw) {
-		prev_prog = bpf_prog_by_id(__dev_xdp_query(dev, bpf_op,
-							   XDP_QUERY_PROG));
-		if (IS_ERR(prev_prog))
-			prev_prog = NULL;
-	}
-
 	memset(&xdp, 0, sizeof(xdp));
-	if (flags & XDP_FLAGS_HW_MODE)
-		xdp.command = XDP_SETUP_PROG_HW;
-	else
-		xdp.command = XDP_SETUP_PROG;
+	xdp.command = mode == XDP_MODE_HW ? XDP_SETUP_PROG_HW : XDP_SETUP_PROG;
 	xdp.extack = extack;
 	xdp.flags = flags;
 	xdp.prog = prog;
 
+	/* Drivers assume refcnt is already incremented (i.e, prog pointer is
+	 * "moved" into driver), so they don't increment it on their own, but
+	 * they do decrement refcnt when program is detached or replaced.
+	 * Given net_device also owns link/prog, we need to bump refcnt here
+	 * to prevent drivers from underflowing it.
+	 */
+	if (prog)
+		bpf_prog_inc(prog);
 	err = bpf_op(dev, &xdp);
-	if (!err && non_hw)
-		bpf_prog_change_xdp(prev_prog, prog);
+	if (err) {
+		if (prog)
+			bpf_prog_put(prog);
+		return err;
+	}
 
-	if (prev_prog)
-		bpf_prog_put(prev_prog);
+	if (mode != XDP_MODE_HW)
+		bpf_prog_change_xdp(dev_xdp_prog(dev, mode), prog);
 
-	return err;
+	return 0;
 }
 
 static void dev_xdp_uninstall(struct net_device *dev)
 {
-	struct netdev_bpf xdp;
-	bpf_op_t ndo_bpf;
+	struct bpf_prog *prog;
+	enum bpf_xdp_mode mode;
+	bpf_op_t bpf_op;
 
-	/* Remove generic XDP */
-	WARN_ON(dev_xdp_install(dev, generic_xdp_install, NULL, 0, NULL));
+	ASSERT_RTNL();
 
-	/* Remove from the driver */
-	ndo_bpf = dev->netdev_ops->ndo_bpf;
-	if (!ndo_bpf)
-		return;
+	for (mode = XDP_MODE_SKB; mode < __MAX_XDP_MODE; mode++) {
+		prog = dev_xdp_prog(dev, mode);
+		if (!prog)
+			continue;
 
-	memset(&xdp, 0, sizeof(xdp));
-	xdp.command = XDP_QUERY_PROG;
-	WARN_ON(ndo_bpf(dev, &xdp));
-	if (xdp.prog_id)
-		WARN_ON(dev_xdp_install(dev, ndo_bpf, NULL, xdp.prog_flags,
-					NULL));
+		bpf_op = dev_xdp_bpf_op(dev, mode);
+		if (!bpf_op)
+			continue;
 
-	/* Remove HW offload */
-	memset(&xdp, 0, sizeof(xdp));
-	xdp.command = XDP_QUERY_PROG_HW;
-	if (!ndo_bpf(dev, &xdp) && xdp.prog_id)
-		WARN_ON(dev_xdp_install(dev, ndo_bpf, NULL, xdp.prog_flags,
-					NULL));
+		WARN_ON(dev_xdp_install(dev, mode, bpf_op, NULL, 0, NULL));
+
+		bpf_prog_put(prog);
+		dev_xdp_set_prog(dev, mode, NULL);
+	}
 }
 
 /**
@@ -8810,29 +8829,22 @@ int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack,
 		      int fd, int expected_fd, u32 flags)
 {
 	const struct net_device_ops *ops = dev->netdev_ops;
-	enum bpf_netdev_command query;
+	enum bpf_xdp_mode mode = dev_xdp_mode(flags);
+	bool offload = mode == XDP_MODE_HW;
 	u32 prog_id, expected_id = 0;
-	bpf_op_t bpf_op, bpf_chk;
 	struct bpf_prog *prog;
-	bool offload;
+	bpf_op_t bpf_op;
 	int err;
 
 	ASSERT_RTNL();
 
-	offload = flags & XDP_FLAGS_HW_MODE;
-	query = offload ? XDP_QUERY_PROG_HW : XDP_QUERY_PROG;
-
-	bpf_op = bpf_chk = ops->ndo_bpf;
-	if (!bpf_op && (flags & (XDP_FLAGS_DRV_MODE | XDP_FLAGS_HW_MODE))) {
+	bpf_op = dev_xdp_bpf_op(dev, mode);
+	if (!bpf_op) {
 		NL_SET_ERR_MSG(extack, "underlying driver does not support XDP in native mode");
 		return -EOPNOTSUPP;
 	}
-	if (!bpf_op || (flags & XDP_FLAGS_SKB_MODE))
-		bpf_op = generic_xdp_install;
-	if (bpf_op == bpf_chk)
-		bpf_chk = generic_xdp_install;
 
-	prog_id = __dev_xdp_query(dev, bpf_op, query);
+	prog_id = dev_xdp_prog_id(dev, mode);
 	if (flags & XDP_FLAGS_REPLACE) {
 		if (expected_fd >= 0) {
 			prog = bpf_prog_get_type_dev(expected_fd,
@@ -8850,8 +8862,11 @@ int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack,
 		}
 	}
 	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");
+		enum bpf_xdp_mode other_mode = mode == XDP_MODE_SKB
+					       ? XDP_MODE_DRV : XDP_MODE_SKB;
+
+		if (!offload && dev_xdp_prog_id(dev, other_mode)) {
+			NL_SET_ERR_MSG(extack, "Native and generic XDP can't be active at the same time");
 			return -EEXIST;
 		}
 
@@ -8866,7 +8881,7 @@ int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack,
 			return PTR_ERR(prog);
 
 		if (!offload && bpf_prog_is_dev_bound(prog->aux)) {
-			NL_SET_ERR_MSG(extack, "using device-bound program without HW_MODE flag is not supported");
+			NL_SET_ERR_MSG(extack, "Using device-bound program without HW_MODE flag is not supported");
 			bpf_prog_put(prog);
 			return -EINVAL;
 		}
@@ -8895,11 +8910,14 @@ int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack,
 		prog = NULL;
 	}
 
-	err = dev_xdp_install(dev, bpf_op, extack, flags, prog);
-	if (err < 0 && prog)
+	err = dev_xdp_install(dev, mode, bpf_op, extack, flags, prog);
+	if (err < 0 && prog) {
 		bpf_prog_put(prog);
+		return err;
+	}
+	dev_xdp_set_prog(dev, mode, prog);
 
-	return err;
+	return 0;
 }
 
 /**
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 85a4b0101f76..58c484a28395 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -1416,13 +1416,12 @@ static u32 rtnl_xdp_prog_skb(struct net_device *dev)
 
 static u32 rtnl_xdp_prog_drv(struct net_device *dev)
 {
-	return __dev_xdp_query(dev, dev->netdev_ops->ndo_bpf, XDP_QUERY_PROG);
+	return dev_xdp_prog_id(dev, XDP_MODE_DRV);
 }
 
 static u32 rtnl_xdp_prog_hw(struct net_device *dev)
 {
-	return __dev_xdp_query(dev, dev->netdev_ops->ndo_bpf,
-			       XDP_QUERY_PROG_HW);
+	return dev_xdp_prog_id(dev, XDP_MODE_HW);
 }
 
 static int rtnl_xdp_report_one(struct sk_buff *skb, struct net_device *dev,
-- 
cgit v1.2.3


From d4baa9368a5e4d694e787e0442ddd6ab95d6fd96 Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andriin@fb.com>
Date: Tue, 21 Jul 2020 23:45:56 -0700
Subject: bpf, xdp: Extract common XDP program attachment logic

Further refactor XDP attachment code. dev_change_xdp_fd() is split into two
parts: getting bpf_progs from FDs and attachment logic, working with
bpf_progs. This makes attachment  logic a bit more straightforward and
prepares code for bpf_xdp_link inclusion, which will share the common logic.

Signed-off-by: Andrii Nakryiko <andriin@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20200722064603.3350758-4-andriin@fb.com
---
 net/core/dev.c | 165 +++++++++++++++++++++++++++++++--------------------------
 1 file changed, 91 insertions(+), 74 deletions(-)

(limited to 'net/core')

diff --git a/net/core/dev.c b/net/core/dev.c
index bf38fde667e9..521ce031ee35 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -8815,111 +8815,128 @@ static void dev_xdp_uninstall(struct net_device *dev)
 	}
 }
 
-/**
- *	dev_change_xdp_fd - set or clear a bpf program for a device rx path
- *	@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, int expected_fd, u32 flags)
+static int dev_xdp_attach(struct net_device *dev, struct netlink_ext_ack *extack,
+			  struct bpf_prog *new_prog, struct bpf_prog *old_prog,
+			  u32 flags)
 {
-	const struct net_device_ops *ops = dev->netdev_ops;
-	enum bpf_xdp_mode mode = dev_xdp_mode(flags);
-	bool offload = mode == XDP_MODE_HW;
-	u32 prog_id, expected_id = 0;
-	struct bpf_prog *prog;
+	struct bpf_prog *cur_prog;
+	enum bpf_xdp_mode mode;
 	bpf_op_t bpf_op;
 	int err;
 
 	ASSERT_RTNL();
 
-	bpf_op = dev_xdp_bpf_op(dev, mode);
-	if (!bpf_op) {
-		NL_SET_ERR_MSG(extack, "underlying driver does not support XDP in native mode");
-		return -EOPNOTSUPP;
+	/* just one XDP mode bit should be set, zero defaults to SKB mode */
+	if (hweight32(flags & XDP_FLAGS_MODES) > 1) {
+		NL_SET_ERR_MSG(extack, "Only one XDP mode flag can be set");
+		return -EINVAL;
+	}
+	/* old_prog != NULL implies XDP_FLAGS_REPLACE is set */
+	if (old_prog && !(flags & XDP_FLAGS_REPLACE)) {
+		NL_SET_ERR_MSG(extack, "XDP_FLAGS_REPLACE is not specified");
+		return -EINVAL;
 	}
 
-	prog_id = dev_xdp_prog_id(dev, mode);
-	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;
-		}
+	mode = dev_xdp_mode(flags);
+	cur_prog = dev_xdp_prog(dev, mode);
+	if ((flags & XDP_FLAGS_REPLACE) && cur_prog != old_prog) {
+		NL_SET_ERR_MSG(extack, "Active program does not match expected");
+		return -EEXIST;
 	}
-	if (fd >= 0) {
+	if ((flags & XDP_FLAGS_UPDATE_IF_NOEXIST) && cur_prog) {
+		NL_SET_ERR_MSG(extack, "XDP program already attached");
+		return -EBUSY;
+	}
+
+	if (new_prog) {
+		bool offload = mode == XDP_MODE_HW;
 		enum bpf_xdp_mode other_mode = mode == XDP_MODE_SKB
 					       ? XDP_MODE_DRV : XDP_MODE_SKB;
 
-		if (!offload && dev_xdp_prog_id(dev, other_mode)) {
+		if (!offload && dev_xdp_prog(dev, other_mode)) {
 			NL_SET_ERR_MSG(extack, "Native and generic XDP can't be active at the same time");
 			return -EEXIST;
 		}
-
-		if ((flags & XDP_FLAGS_UPDATE_IF_NOEXIST) && prog_id) {
-			NL_SET_ERR_MSG(extack, "XDP program already attached");
-			return -EBUSY;
-		}
-
-		prog = bpf_prog_get_type_dev(fd, BPF_PROG_TYPE_XDP,
-					     bpf_op == ops->ndo_bpf);
-		if (IS_ERR(prog))
-			return PTR_ERR(prog);
-
-		if (!offload && bpf_prog_is_dev_bound(prog->aux)) {
+		if (!offload && bpf_prog_is_dev_bound(new_prog->aux)) {
 			NL_SET_ERR_MSG(extack, "Using device-bound program without HW_MODE flag is not supported");
-			bpf_prog_put(prog);
 			return -EINVAL;
 		}
-
-		if (prog->expected_attach_type == BPF_XDP_DEVMAP) {
+		if (new_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;
 		}
-
-		if (prog->expected_attach_type == BPF_XDP_CPUMAP) {
-			NL_SET_ERR_MSG(extack,
-				       "BPF_XDP_CPUMAP programs can not be attached to a device");
-			bpf_prog_put(prog);
+		if (new_prog->expected_attach_type == BPF_XDP_CPUMAP) {
+			NL_SET_ERR_MSG(extack, "BPF_XDP_CPUMAP programs can not be attached to a device");
 			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);
-			return 0;
+	/* don't call drivers if the effective program didn't change */
+	if (new_prog != cur_prog) {
+		bpf_op = dev_xdp_bpf_op(dev, mode);
+		if (!bpf_op) {
+			NL_SET_ERR_MSG(extack, "Underlying driver does not support XDP in native mode");
+			return -EOPNOTSUPP;
 		}
-	} else {
-		if (!prog_id)
-			return 0;
-		prog = NULL;
-	}
 
-	err = dev_xdp_install(dev, mode, bpf_op, extack, flags, prog);
-	if (err < 0 && prog) {
-		bpf_prog_put(prog);
-		return err;
+		err = dev_xdp_install(dev, mode, bpf_op, extack, flags, new_prog);
+		if (err)
+			return err;
 	}
-	dev_xdp_set_prog(dev, mode, prog);
+
+	dev_xdp_set_prog(dev, mode, new_prog);
+	if (cur_prog)
+		bpf_prog_put(cur_prog);
 
 	return 0;
 }
 
+/**
+ *	dev_change_xdp_fd - set or clear a bpf program for a device rx path
+ *	@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, int expected_fd, u32 flags)
+{
+	enum bpf_xdp_mode mode = dev_xdp_mode(flags);
+	struct bpf_prog *new_prog = NULL, *old_prog = NULL;
+	int err;
+
+	ASSERT_RTNL();
+
+	if (fd >= 0) {
+		new_prog = bpf_prog_get_type_dev(fd, BPF_PROG_TYPE_XDP,
+						 mode != XDP_MODE_SKB);
+		if (IS_ERR(new_prog))
+			return PTR_ERR(new_prog);
+	}
+
+	if (expected_fd >= 0) {
+		old_prog = bpf_prog_get_type_dev(expected_fd, BPF_PROG_TYPE_XDP,
+						 mode != XDP_MODE_SKB);
+		if (IS_ERR(old_prog)) {
+			err = PTR_ERR(old_prog);
+			old_prog = NULL;
+			goto err_out;
+		}
+	}
+
+	err = dev_xdp_attach(dev, extack, new_prog, old_prog, flags);
+
+err_out:
+	if (err && new_prog)
+		bpf_prog_put(new_prog);
+	if (old_prog)
+		bpf_prog_put(old_prog);
+	return err;
+}
+
 /**
  *	dev_new_index	-	allocate an ifindex
  *	@net: the applicable net namespace
-- 
cgit v1.2.3


From aa8d3a716b59db6c1ad6c68fb8aa05e31980da60 Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andriin@fb.com>
Date: Tue, 21 Jul 2020 23:45:57 -0700
Subject: bpf, xdp: Add bpf_link-based XDP attachment API

Add bpf_link-based API (bpf_xdp_link) to attach BPF XDP program through
BPF_LINK_CREATE command.

bpf_xdp_link is mutually exclusive with direct BPF program attachment,
previous BPF program should be detached prior to attempting to create a new
bpf_xdp_link attachment (for a given XDP mode). Once BPF link is attached, it
can't be replaced by other BPF program attachment or link attachment. It will
be detached only when the last BPF link FD is closed.

bpf_xdp_link will be auto-detached when net_device is shutdown, similarly to
how other BPF links behave (cgroup, flow_dissector). At that point bpf_link
will become defunct, but won't be destroyed until last FD is closed.

Signed-off-by: Andrii Nakryiko <andriin@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20200722064603.3350758-5-andriin@fb.com
---
 include/linux/netdevice.h |   4 ++
 include/uapi/linux/bpf.h  |   7 +-
 kernel/bpf/syscall.c      |   5 ++
 net/core/dev.c            | 169 ++++++++++++++++++++++++++++++++++++++++++++--
 4 files changed, 178 insertions(+), 7 deletions(-)

(limited to 'net/core')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index cad44b40c776..7d3c412fcfe5 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -888,6 +888,7 @@ struct bpf_prog_offload_ops;
 struct netlink_ext_ack;
 struct xdp_umem;
 struct xdp_dev_bulk_queue;
+struct bpf_xdp_link;
 
 enum bpf_xdp_mode {
 	XDP_MODE_SKB = 0,
@@ -898,6 +899,7 @@ enum bpf_xdp_mode {
 
 struct bpf_xdp_entity {
 	struct bpf_prog *prog;
+	struct bpf_xdp_link *link;
 };
 
 struct netdev_bpf {
@@ -3831,7 +3833,9 @@ 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, int expected_fd, u32 flags);
+int bpf_xdp_link_attach(const union bpf_attr *attr, struct bpf_prog *prog);
 u32 dev_xdp_prog_id(struct net_device *dev, enum bpf_xdp_mode mode);
+
 int xdp_umem_query(struct net_device *dev, u16 queue_id);
 
 int __dev_forward_skb(struct net_device *dev, struct sk_buff *skb);
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 828c2f6438f2..87823fb9c123 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -230,6 +230,7 @@ enum bpf_attach_type {
 	BPF_CGROUP_INET_SOCK_RELEASE,
 	BPF_XDP_CPUMAP,
 	BPF_SK_LOOKUP,
+	BPF_XDP,
 	__MAX_BPF_ATTACH_TYPE
 };
 
@@ -242,6 +243,7 @@ enum bpf_link_type {
 	BPF_LINK_TYPE_CGROUP = 3,
 	BPF_LINK_TYPE_ITER = 4,
 	BPF_LINK_TYPE_NETNS = 5,
+	BPF_LINK_TYPE_XDP = 6,
 
 	MAX_BPF_LINK_TYPE,
 };
@@ -614,7 +616,10 @@ union bpf_attr {
 
 	struct { /* struct used by BPF_LINK_CREATE command */
 		__u32		prog_fd;	/* eBPF program to attach */
-		__u32		target_fd;	/* object to attach to */
+		union {
+			__u32		target_fd;	/* object to attach to */
+			__u32		target_ifindex; /* target ifindex */
+		};
 		__u32		attach_type;	/* attach type */
 		__u32		flags;		/* extra flags */
 	} link_create;
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index ee290b1f2d9e..0e8c88db7e7a 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -2824,6 +2824,8 @@ attach_type_to_prog_type(enum bpf_attach_type attach_type)
 		return BPF_PROG_TYPE_TRACING;
 	case BPF_SK_LOOKUP:
 		return BPF_PROG_TYPE_SK_LOOKUP;
+	case BPF_XDP:
+		return BPF_PROG_TYPE_XDP;
 	default:
 		return BPF_PROG_TYPE_UNSPEC;
 	}
@@ -3921,6 +3923,9 @@ static int link_create(union bpf_attr *attr)
 	case BPF_PROG_TYPE_SK_LOOKUP:
 		ret = netns_bpf_link_create(attr, prog);
 		break;
+	case BPF_PROG_TYPE_XDP:
+		ret = bpf_xdp_link_attach(attr, prog);
+		break;
 	default:
 		ret = -EINVAL;
 	}
diff --git a/net/core/dev.c b/net/core/dev.c
index 521ce031ee35..e24248f3d675 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -8716,6 +8716,12 @@ int dev_change_proto_down_generic(struct net_device *dev, bool proto_down)
 }
 EXPORT_SYMBOL(dev_change_proto_down_generic);
 
+struct bpf_xdp_link {
+	struct bpf_link link;
+	struct net_device *dev; /* protected by rtnl_lock, no refcnt held */
+	int flags;
+};
+
 static enum bpf_xdp_mode dev_xdp_mode(u32 flags)
 {
 	if (flags & XDP_FLAGS_HW_MODE)
@@ -8738,9 +8744,19 @@ static bpf_op_t dev_xdp_bpf_op(struct net_device *dev, enum bpf_xdp_mode mode)
 	};
 }
 
+static struct bpf_xdp_link *dev_xdp_link(struct net_device *dev,
+					 enum bpf_xdp_mode mode)
+{
+	return dev->xdp_state[mode].link;
+}
+
 static struct bpf_prog *dev_xdp_prog(struct net_device *dev,
 				     enum bpf_xdp_mode mode)
 {
+	struct bpf_xdp_link *link = dev_xdp_link(dev, mode);
+
+	if (link)
+		return link->link.prog;
 	return dev->xdp_state[mode].prog;
 }
 
@@ -8751,9 +8767,17 @@ u32 dev_xdp_prog_id(struct net_device *dev, enum bpf_xdp_mode mode)
 	return prog ? prog->aux->id : 0;
 }
 
+static void dev_xdp_set_link(struct net_device *dev, enum bpf_xdp_mode mode,
+			     struct bpf_xdp_link *link)
+{
+	dev->xdp_state[mode].link = link;
+	dev->xdp_state[mode].prog = NULL;
+}
+
 static void dev_xdp_set_prog(struct net_device *dev, enum bpf_xdp_mode mode,
 			     struct bpf_prog *prog)
 {
+	dev->xdp_state[mode].link = NULL;
 	dev->xdp_state[mode].prog = prog;
 }
 
@@ -8793,6 +8817,7 @@ static int dev_xdp_install(struct net_device *dev, enum bpf_xdp_mode mode,
 
 static void dev_xdp_uninstall(struct net_device *dev)
 {
+	struct bpf_xdp_link *link;
 	struct bpf_prog *prog;
 	enum bpf_xdp_mode mode;
 	bpf_op_t bpf_op;
@@ -8810,14 +8835,20 @@ static void dev_xdp_uninstall(struct net_device *dev)
 
 		WARN_ON(dev_xdp_install(dev, mode, bpf_op, NULL, 0, NULL));
 
-		bpf_prog_put(prog);
-		dev_xdp_set_prog(dev, mode, NULL);
+		/* auto-detach link from net device */
+		link = dev_xdp_link(dev, mode);
+		if (link)
+			link->dev = NULL;
+		else
+			bpf_prog_put(prog);
+
+		dev_xdp_set_link(dev, mode, NULL);
 	}
 }
 
 static int dev_xdp_attach(struct net_device *dev, struct netlink_ext_ack *extack,
-			  struct bpf_prog *new_prog, struct bpf_prog *old_prog,
-			  u32 flags)
+			  struct bpf_xdp_link *link, struct bpf_prog *new_prog,
+			  struct bpf_prog *old_prog, u32 flags)
 {
 	struct bpf_prog *cur_prog;
 	enum bpf_xdp_mode mode;
@@ -8826,6 +8857,14 @@ static int dev_xdp_attach(struct net_device *dev, struct netlink_ext_ack *extack
 
 	ASSERT_RTNL();
 
+	/* either link or prog attachment, never both */
+	if (link && (new_prog || old_prog))
+		return -EINVAL;
+	/* link supports only XDP mode flags */
+	if (link && (flags & ~XDP_FLAGS_MODES)) {
+		NL_SET_ERR_MSG(extack, "Invalid XDP flags for BPF link attachment");
+		return -EINVAL;
+	}
 	/* just one XDP mode bit should be set, zero defaults to SKB mode */
 	if (hweight32(flags & XDP_FLAGS_MODES) > 1) {
 		NL_SET_ERR_MSG(extack, "Only one XDP mode flag can be set");
@@ -8838,7 +8877,18 @@ static int dev_xdp_attach(struct net_device *dev, struct netlink_ext_ack *extack
 	}
 
 	mode = dev_xdp_mode(flags);
+	/* can't replace attached link */
+	if (dev_xdp_link(dev, mode)) {
+		NL_SET_ERR_MSG(extack, "Can't replace active BPF XDP link");
+		return -EBUSY;
+	}
+
 	cur_prog = dev_xdp_prog(dev, mode);
+	/* can't replace attached prog with link */
+	if (link && cur_prog) {
+		NL_SET_ERR_MSG(extack, "Can't replace active XDP program with BPF link");
+		return -EBUSY;
+	}
 	if ((flags & XDP_FLAGS_REPLACE) && cur_prog != old_prog) {
 		NL_SET_ERR_MSG(extack, "Active program does not match expected");
 		return -EEXIST;
@@ -8848,6 +8898,10 @@ static int dev_xdp_attach(struct net_device *dev, struct netlink_ext_ack *extack
 		return -EBUSY;
 	}
 
+	/* put effective new program into new_prog */
+	if (link)
+		new_prog = link->link.prog;
+
 	if (new_prog) {
 		bool offload = mode == XDP_MODE_HW;
 		enum bpf_xdp_mode other_mode = mode == XDP_MODE_SKB
@@ -8884,13 +8938,116 @@ static int dev_xdp_attach(struct net_device *dev, struct netlink_ext_ack *extack
 			return err;
 	}
 
-	dev_xdp_set_prog(dev, mode, new_prog);
+	if (link)
+		dev_xdp_set_link(dev, mode, link);
+	else
+		dev_xdp_set_prog(dev, mode, new_prog);
 	if (cur_prog)
 		bpf_prog_put(cur_prog);
 
 	return 0;
 }
 
+static int dev_xdp_attach_link(struct net_device *dev,
+			       struct netlink_ext_ack *extack,
+			       struct bpf_xdp_link *link)
+{
+	return dev_xdp_attach(dev, extack, link, NULL, NULL, link->flags);
+}
+
+static int dev_xdp_detach_link(struct net_device *dev,
+			       struct netlink_ext_ack *extack,
+			       struct bpf_xdp_link *link)
+{
+	enum bpf_xdp_mode mode;
+	bpf_op_t bpf_op;
+
+	ASSERT_RTNL();
+
+	mode = dev_xdp_mode(link->flags);
+	if (dev_xdp_link(dev, mode) != link)
+		return -EINVAL;
+
+	bpf_op = dev_xdp_bpf_op(dev, mode);
+	WARN_ON(dev_xdp_install(dev, mode, bpf_op, NULL, 0, NULL));
+	dev_xdp_set_link(dev, mode, NULL);
+	return 0;
+}
+
+static void bpf_xdp_link_release(struct bpf_link *link)
+{
+	struct bpf_xdp_link *xdp_link = container_of(link, struct bpf_xdp_link, link);
+
+	rtnl_lock();
+
+	/* if racing with net_device's tear down, xdp_link->dev might be
+	 * already NULL, in which case link was already auto-detached
+	 */
+	if (xdp_link->dev)
+		WARN_ON(dev_xdp_detach_link(xdp_link->dev, NULL, xdp_link));
+
+	rtnl_unlock();
+}
+
+static void bpf_xdp_link_dealloc(struct bpf_link *link)
+{
+	struct bpf_xdp_link *xdp_link = container_of(link, struct bpf_xdp_link, link);
+
+	kfree(xdp_link);
+}
+
+static const struct bpf_link_ops bpf_xdp_link_lops = {
+	.release = bpf_xdp_link_release,
+	.dealloc = bpf_xdp_link_dealloc,
+};
+
+int bpf_xdp_link_attach(const union bpf_attr *attr, struct bpf_prog *prog)
+{
+	struct net *net = current->nsproxy->net_ns;
+	struct bpf_link_primer link_primer;
+	struct bpf_xdp_link *link;
+	struct net_device *dev;
+	int err, fd;
+
+	dev = dev_get_by_index(net, attr->link_create.target_ifindex);
+	if (!dev)
+		return -EINVAL;
+
+	link = kzalloc(sizeof(*link), GFP_USER);
+	if (!link) {
+		err = -ENOMEM;
+		goto out_put_dev;
+	}
+
+	bpf_link_init(&link->link, BPF_LINK_TYPE_XDP, &bpf_xdp_link_lops, prog);
+	link->dev = dev;
+	link->flags = attr->link_create.flags;
+
+	err = bpf_link_prime(&link->link, &link_primer);
+	if (err) {
+		kfree(link);
+		goto out_put_dev;
+	}
+
+	rtnl_lock();
+	err = dev_xdp_attach_link(dev, NULL, link);
+	rtnl_unlock();
+
+	if (err) {
+		bpf_link_cleanup(&link_primer);
+		goto out_put_dev;
+	}
+
+	fd = bpf_link_settle(&link_primer);
+	/* link itself doesn't hold dev's refcnt to not complicate shutdown */
+	dev_put(dev);
+	return fd;
+
+out_put_dev:
+	dev_put(dev);
+	return err;
+}
+
 /**
  *	dev_change_xdp_fd - set or clear a bpf program for a device rx path
  *	@dev: device
@@ -8927,7 +9084,7 @@ int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack,
 		}
 	}
 
-	err = dev_xdp_attach(dev, extack, new_prog, old_prog, flags);
+	err = dev_xdp_attach(dev, extack, NULL, new_prog, old_prog, flags);
 
 err_out:
 	if (err && new_prog)
-- 
cgit v1.2.3


From 026a4c28e1db3b0cb99cd9a3e495d4a8b632fa74 Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andriin@fb.com>
Date: Tue, 21 Jul 2020 23:45:58 -0700
Subject: bpf, xdp: Implement LINK_UPDATE for BPF XDP link

Add support for LINK_UPDATE command for BPF XDP link to enable reliable
replacement of underlying BPF program.

Signed-off-by: Andrii Nakryiko <andriin@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20200722064603.3350758-6-andriin@fb.com
---
 net/core/dev.c | 43 +++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 43 insertions(+)

(limited to 'net/core')

diff --git a/net/core/dev.c b/net/core/dev.c
index e24248f3d675..49f284f51a22 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -8996,9 +8996,52 @@ static void bpf_xdp_link_dealloc(struct bpf_link *link)
 	kfree(xdp_link);
 }
 
+static int bpf_xdp_link_update(struct bpf_link *link, struct bpf_prog *new_prog,
+			       struct bpf_prog *old_prog)
+{
+	struct bpf_xdp_link *xdp_link = container_of(link, struct bpf_xdp_link, link);
+	enum bpf_xdp_mode mode;
+	bpf_op_t bpf_op;
+	int err = 0;
+
+	rtnl_lock();
+
+	/* link might have been auto-released already, so fail */
+	if (!xdp_link->dev) {
+		err = -ENOLINK;
+		goto out_unlock;
+	}
+
+	if (old_prog && link->prog != old_prog) {
+		err = -EPERM;
+		goto out_unlock;
+	}
+	old_prog = link->prog;
+	if (old_prog == new_prog) {
+		/* no-op, don't disturb drivers */
+		bpf_prog_put(new_prog);
+		goto out_unlock;
+	}
+
+	mode = dev_xdp_mode(xdp_link->flags);
+	bpf_op = dev_xdp_bpf_op(xdp_link->dev, mode);
+	err = dev_xdp_install(xdp_link->dev, mode, bpf_op, NULL,
+			      xdp_link->flags, new_prog);
+	if (err)
+		goto out_unlock;
+
+	old_prog = xchg(&link->prog, new_prog);
+	bpf_prog_put(old_prog);
+
+out_unlock:
+	rtnl_unlock();
+	return err;
+}
+
 static const struct bpf_link_ops bpf_xdp_link_lops = {
 	.release = bpf_xdp_link_release,
 	.dealloc = bpf_xdp_link_dealloc,
+	.update_prog = bpf_xdp_link_update,
 };
 
 int bpf_xdp_link_attach(const union bpf_attr *attr, struct bpf_prog *prog)
-- 
cgit v1.2.3


From c1931c9784ebb5787c0784c112fb8baa5e8455b3 Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andriin@fb.com>
Date: Tue, 21 Jul 2020 23:45:59 -0700
Subject: bpf: Implement BPF XDP link-specific introspection APIs

Implement XDP link-specific show_fdinfo and link_info to emit ifindex.

Signed-off-by: Andrii Nakryiko <andriin@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20200722064603.3350758-7-andriin@fb.com
---
 include/uapi/linux/bpf.h |  3 +++
 net/core/dev.c           | 31 +++++++++++++++++++++++++++++++
 2 files changed, 34 insertions(+)

(limited to 'net/core')

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 87823fb9c123..e1ba4ae6a916 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -4069,6 +4069,9 @@ struct bpf_link_info {
 			__u32 netns_ino;
 			__u32 attach_type;
 		} netns;
+		struct {
+			__u32 ifindex;
+		} xdp;
 	};
 } __attribute__((aligned(8)));
 
diff --git a/net/core/dev.c b/net/core/dev.c
index 49f284f51a22..82ce0920b172 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -8996,6 +8996,35 @@ static void bpf_xdp_link_dealloc(struct bpf_link *link)
 	kfree(xdp_link);
 }
 
+static void bpf_xdp_link_show_fdinfo(const struct bpf_link *link,
+				     struct seq_file *seq)
+{
+	struct bpf_xdp_link *xdp_link = container_of(link, struct bpf_xdp_link, link);
+	u32 ifindex = 0;
+
+	rtnl_lock();
+	if (xdp_link->dev)
+		ifindex = xdp_link->dev->ifindex;
+	rtnl_unlock();
+
+	seq_printf(seq, "ifindex:\t%u\n", ifindex);
+}
+
+static int bpf_xdp_link_fill_link_info(const struct bpf_link *link,
+				       struct bpf_link_info *info)
+{
+	struct bpf_xdp_link *xdp_link = container_of(link, struct bpf_xdp_link, link);
+	u32 ifindex = 0;
+
+	rtnl_lock();
+	if (xdp_link->dev)
+		ifindex = xdp_link->dev->ifindex;
+	rtnl_unlock();
+
+	info->xdp.ifindex = ifindex;
+	return 0;
+}
+
 static int bpf_xdp_link_update(struct bpf_link *link, struct bpf_prog *new_prog,
 			       struct bpf_prog *old_prog)
 {
@@ -9041,6 +9070,8 @@ out_unlock:
 static const struct bpf_link_ops bpf_xdp_link_lops = {
 	.release = bpf_xdp_link_release,
 	.dealloc = bpf_xdp_link_dealloc,
+	.show_fdinfo = bpf_xdp_link_show_fdinfo,
+	.fill_link_info = bpf_xdp_link_fill_link_info,
 	.update_prog = bpf_xdp_link_update,
 };
 
-- 
cgit v1.2.3


From e8407fdeb9a6866784e249881f6c786a0835faba Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andriin@fb.com>
Date: Tue, 21 Jul 2020 23:46:02 -0700
Subject: bpf, xdp: Remove XDP_QUERY_PROG and XDP_QUERY_PROG_HW XDP commands

Now that BPF program/link management is centralized in generic net_device
code, kernel code never queries program id from drivers, so
XDP_QUERY_PROG/XDP_QUERY_PROG_HW commands are unnecessary.

This patch removes all the implementations of those commands in kernel, along
the xdp_attachment_query().

This patch was compile-tested on allyesconfig.

Signed-off-by: Andrii Nakryiko <andriin@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20200722064603.3350758-10-andriin@fb.com
---
 drivers/net/ethernet/amazon/ena/ena_netdev.c       |  6 ------
 drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c      |  4 ----
 drivers/net/ethernet/cavium/thunder/nicvf_main.c   |  3 ---
 drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c   |  5 -----
 drivers/net/ethernet/intel/i40e/i40e_main.c        |  3 ---
 drivers/net/ethernet/intel/ice/ice_main.c          |  3 ---
 drivers/net/ethernet/intel/ixgbe/ixgbe_main.c      |  4 ----
 drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c  |  6 ------
 drivers/net/ethernet/marvell/mvneta.c              |  5 -----
 drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c    |  3 ---
 drivers/net/ethernet/mellanox/mlx4/en_netdev.c     | 24 ----------------------
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c  | 18 ----------------
 .../net/ethernet/netronome/nfp/nfp_net_common.c    |  4 ----
 drivers/net/ethernet/qlogic/qede/qede_filter.c     |  3 ---
 drivers/net/ethernet/sfc/efx.c                     |  5 -----
 drivers/net/ethernet/socionext/netsec.c            |  3 ---
 drivers/net/ethernet/ti/cpsw_priv.c                |  3 ---
 drivers/net/hyperv/netvsc_bpf.c                    | 21 +------------------
 drivers/net/netdevsim/bpf.c                        |  4 ----
 drivers/net/netdevsim/netdevsim.h                  |  2 +-
 drivers/net/tun.c                                  | 15 --------------
 drivers/net/veth.c                                 | 15 --------------
 drivers/net/virtio_net.c                           | 17 ---------------
 drivers/net/xen-netfront.c                         | 21 -------------------
 include/linux/netdevice.h                          |  8 --------
 include/net/xdp.h                                  |  2 --
 net/core/dev.c                                     |  4 ----
 net/core/xdp.c                                     |  9 --------
 28 files changed, 2 insertions(+), 218 deletions(-)

(limited to 'net/core')

diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c
index 6478c1e0d137..2a6c9725e092 100644
--- a/drivers/net/ethernet/amazon/ena/ena_netdev.c
+++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c
@@ -576,15 +576,9 @@ static int ena_xdp_set(struct net_device *netdev, struct netdev_bpf *bpf)
  */
 static int ena_xdp(struct net_device *netdev, struct netdev_bpf *bpf)
 {
-	struct ena_adapter *adapter = netdev_priv(netdev);
-
 	switch (bpf->command) {
 	case XDP_SETUP_PROG:
 		return ena_xdp_set(netdev, bpf);
-	case XDP_QUERY_PROG:
-		bpf->prog_id = adapter->xdp_bpf_prog ?
-			adapter->xdp_bpf_prog->aux->id : 0;
-		break;
 	default:
 		return -EINVAL;
 	}
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
index 5e3b4a3b69ea..2704a4709bc7 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
@@ -330,10 +330,6 @@ int bnxt_xdp(struct net_device *dev, struct netdev_bpf *xdp)
 	case XDP_SETUP_PROG:
 		rc = bnxt_xdp_set(bp, xdp->prog);
 		break;
-	case XDP_QUERY_PROG:
-		xdp->prog_id = bp->xdp_prog ? bp->xdp_prog->aux->id : 0;
-		rc = 0;
-		break;
 	default:
 		rc = -EINVAL;
 		break;
diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_main.c b/drivers/net/ethernet/cavium/thunder/nicvf_main.c
index 2ba0ce115e63..1c6163934e20 100644
--- a/drivers/net/ethernet/cavium/thunder/nicvf_main.c
+++ b/drivers/net/ethernet/cavium/thunder/nicvf_main.c
@@ -1906,9 +1906,6 @@ static int nicvf_xdp(struct net_device *netdev, struct netdev_bpf *xdp)
 	switch (xdp->command) {
 	case XDP_SETUP_PROG:
 		return nicvf_xdp_setup(nic, xdp->prog);
-	case XDP_QUERY_PROG:
-		xdp->prog_id = nic->xdp_prog ? nic->xdp_prog->aux->id : 0;
-		return 0;
 	default:
 		return -EINVAL;
 	}
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
index 9b4028c0e34c..17f6bcafc944 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
@@ -2077,14 +2077,9 @@ out_err:
 
 static int dpaa2_eth_xdp(struct net_device *dev, struct netdev_bpf *xdp)
 {
-	struct dpaa2_eth_priv *priv = netdev_priv(dev);
-
 	switch (xdp->command) {
 	case XDP_SETUP_PROG:
 		return setup_xdp(dev, xdp->prog);
-	case XDP_QUERY_PROG:
-		xdp->prog_id = priv->xdp_prog ? priv->xdp_prog->aux->id : 0;
-		break;
 	default:
 		return -EINVAL;
 	}
diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index dadbfb3d2a2b..d8315811cbdf 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -12923,9 +12923,6 @@ static int i40e_xdp(struct net_device *dev,
 	switch (xdp->command) {
 	case XDP_SETUP_PROG:
 		return i40e_xdp_setup(vsi, xdp->prog);
-	case XDP_QUERY_PROG:
-		xdp->prog_id = vsi->xdp_prog ? vsi->xdp_prog->aux->id : 0;
-		return 0;
 	case XDP_SETUP_XSK_UMEM:
 		return i40e_xsk_umem_setup(vsi, xdp->xsk.umem,
 					   xdp->xsk.queue_id);
diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index 16a4096bb780..231f4b6e93d0 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -2292,9 +2292,6 @@ static int ice_xdp(struct net_device *dev, struct netdev_bpf *xdp)
 	switch (xdp->command) {
 	case XDP_SETUP_PROG:
 		return ice_xdp_setup_prog(vsi, xdp->prog, xdp->extack);
-	case XDP_QUERY_PROG:
-		xdp->prog_id = vsi->xdp_prog ? vsi->xdp_prog->aux->id : 0;
-		return 0;
 	case XDP_SETUP_XSK_UMEM:
 		return ice_xsk_umem_setup(vsi, xdp->xsk.umem,
 					  xdp->xsk.queue_id);
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index 4d898ff21a46..6f32b1706ab9 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -10190,10 +10190,6 @@ static int ixgbe_xdp(struct net_device *dev, struct netdev_bpf *xdp)
 	switch (xdp->command) {
 	case XDP_SETUP_PROG:
 		return ixgbe_xdp_setup(dev, xdp->prog);
-	case XDP_QUERY_PROG:
-		xdp->prog_id = adapter->xdp_prog ?
-			adapter->xdp_prog->aux->id : 0;
-		return 0;
 	case XDP_SETUP_XSK_UMEM:
 		return ixgbe_xsk_umem_setup(adapter, xdp->xsk.umem,
 					    xdp->xsk.queue_id);
diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
index 6e9a397db583..a6267569bfa9 100644
--- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
+++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
@@ -4502,15 +4502,9 @@ static int ixgbevf_xdp_setup(struct net_device *dev, struct bpf_prog *prog)
 
 static int ixgbevf_xdp(struct net_device *dev, struct netdev_bpf *xdp)
 {
-	struct ixgbevf_adapter *adapter = netdev_priv(dev);
-
 	switch (xdp->command) {
 	case XDP_SETUP_PROG:
 		return ixgbevf_xdp_setup(dev, xdp->prog);
-	case XDP_QUERY_PROG:
-		xdp->prog_id = adapter->xdp_prog ?
-			       adapter->xdp_prog->aux->id : 0;
-		return 0;
 	default:
 		return -EINVAL;
 	}
diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c
index 2c9277e73cef..6e3f9e2f883b 100644
--- a/drivers/net/ethernet/marvell/mvneta.c
+++ b/drivers/net/ethernet/marvell/mvneta.c
@@ -4442,14 +4442,9 @@ static int mvneta_xdp_setup(struct net_device *dev, struct bpf_prog *prog,
 
 static int mvneta_xdp(struct net_device *dev, struct netdev_bpf *xdp)
 {
-	struct mvneta_port *pp = netdev_priv(dev);
-
 	switch (xdp->command) {
 	case XDP_SETUP_PROG:
 		return mvneta_xdp_setup(dev, xdp->prog, xdp->extack);
-	case XDP_QUERY_PROG:
-		xdp->prog_id = pp->xdp_prog ? pp->xdp_prog->aux->id : 0;
-		return 0;
 	default:
 		return -EINVAL;
 	}
diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
index 6a3f356640a0..cd5e9d60307e 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
@@ -4656,9 +4656,6 @@ static int mvpp2_xdp(struct net_device *dev, struct netdev_bpf *xdp)
 	switch (xdp->command) {
 	case XDP_SETUP_PROG:
 		return mvpp2_xdp_setup(port, xdp);
-	case XDP_QUERY_PROG:
-		xdp->prog_id = port->xdp_prog ? port->xdp_prog->aux->id : 0;
-		return 0;
 	default:
 		return -EINVAL;
 	}
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
index 2b8608f8f0a9..106513f772c3 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
@@ -2802,35 +2802,11 @@ unlock_out:
 	return err;
 }
 
-static u32 mlx4_xdp_query(struct net_device *dev)
-{
-	struct mlx4_en_priv *priv = netdev_priv(dev);
-	struct mlx4_en_dev *mdev = priv->mdev;
-	const struct bpf_prog *xdp_prog;
-	u32 prog_id = 0;
-
-	if (!priv->tx_ring_num[TX_XDP])
-		return prog_id;
-
-	mutex_lock(&mdev->state_lock);
-	xdp_prog = rcu_dereference_protected(
-		priv->rx_ring[0]->xdp_prog,
-		lockdep_is_held(&mdev->state_lock));
-	if (xdp_prog)
-		prog_id = xdp_prog->aux->id;
-	mutex_unlock(&mdev->state_lock);
-
-	return prog_id;
-}
-
 static int mlx4_xdp(struct net_device *dev, struct netdev_bpf *xdp)
 {
 	switch (xdp->command) {
 	case XDP_SETUP_PROG:
 		return mlx4_xdp_set(dev, xdp->prog);
-	case XDP_QUERY_PROG:
-		xdp->prog_id = mlx4_xdp_query(dev);
-		return 0;
 	default:
 		return -EINVAL;
 	}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 9d5d8b28bcd8..aa4fb503dac3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -4518,29 +4518,11 @@ unlock:
 	return err;
 }
 
-static u32 mlx5e_xdp_query(struct net_device *dev)
-{
-	struct mlx5e_priv *priv = netdev_priv(dev);
-	const struct bpf_prog *xdp_prog;
-	u32 prog_id = 0;
-
-	mutex_lock(&priv->state_lock);
-	xdp_prog = priv->channels.params.xdp_prog;
-	if (xdp_prog)
-		prog_id = xdp_prog->aux->id;
-	mutex_unlock(&priv->state_lock);
-
-	return prog_id;
-}
-
 static int mlx5e_xdp(struct net_device *dev, struct netdev_bpf *xdp)
 {
 	switch (xdp->command) {
 	case XDP_SETUP_PROG:
 		return mlx5e_xdp_set(dev, xdp->prog);
-	case XDP_QUERY_PROG:
-		xdp->prog_id = mlx5e_xdp_query(dev);
-		return 0;
 	case XDP_SETUP_XSK_UMEM:
 		return mlx5e_xsk_setup_umem(dev, xdp->xsk.umem,
 					    xdp->xsk.queue_id);
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
index 44608873d3d9..39ee23e8c0bf 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
@@ -3614,10 +3614,6 @@ static int nfp_net_xdp(struct net_device *netdev, struct netdev_bpf *xdp)
 		return nfp_net_xdp_setup_drv(nn, xdp);
 	case XDP_SETUP_PROG_HW:
 		return nfp_net_xdp_setup_hw(nn, xdp);
-	case XDP_QUERY_PROG:
-		return xdp_attachment_query(&nn->xdp, xdp);
-	case XDP_QUERY_PROG_HW:
-		return xdp_attachment_query(&nn->xdp_hw, xdp);
 	default:
 		return nfp_app_bpf(nn->app, nn, xdp);
 	}
diff --git a/drivers/net/ethernet/qlogic/qede/qede_filter.c b/drivers/net/ethernet/qlogic/qede/qede_filter.c
index b7d0b6ccebd3..f961f65d9372 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_filter.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_filter.c
@@ -1045,9 +1045,6 @@ int qede_xdp(struct net_device *dev, struct netdev_bpf *xdp)
 	switch (xdp->command) {
 	case XDP_SETUP_PROG:
 		return qede_xdp_set(edev, xdp->prog);
-	case XDP_QUERY_PROG:
-		xdp->prog_id = edev->xdp_prog ? edev->xdp_prog->aux->id : 0;
-		return 0;
 	default:
 		return -EINVAL;
 	}
diff --git a/drivers/net/ethernet/sfc/efx.c b/drivers/net/ethernet/sfc/efx.c
index f16b4f236031..d60acaa3879d 100644
--- a/drivers/net/ethernet/sfc/efx.c
+++ b/drivers/net/ethernet/sfc/efx.c
@@ -653,15 +653,10 @@ static int efx_xdp_setup_prog(struct efx_nic *efx, struct bpf_prog *prog)
 static int efx_xdp(struct net_device *dev, struct netdev_bpf *xdp)
 {
 	struct efx_nic *efx = netdev_priv(dev);
-	struct bpf_prog *xdp_prog;
 
 	switch (xdp->command) {
 	case XDP_SETUP_PROG:
 		return efx_xdp_setup_prog(efx, xdp->prog);
-	case XDP_QUERY_PROG:
-		xdp_prog = rtnl_dereference(efx->xdp_prog);
-		xdp->prog_id = xdp_prog ? xdp_prog->aux->id : 0;
-		return 0;
 	default:
 		return -EINVAL;
 	}
diff --git a/drivers/net/ethernet/socionext/netsec.c b/drivers/net/ethernet/socionext/netsec.c
index 0f366cc50b74..25db667fa879 100644
--- a/drivers/net/ethernet/socionext/netsec.c
+++ b/drivers/net/ethernet/socionext/netsec.c
@@ -1811,9 +1811,6 @@ static int netsec_xdp(struct net_device *ndev, struct netdev_bpf *xdp)
 	switch (xdp->command) {
 	case XDP_SETUP_PROG:
 		return netsec_xdp_setup(priv, xdp->prog, xdp->extack);
-	case XDP_QUERY_PROG:
-		xdp->prog_id = priv->xdp_prog ? priv->xdp_prog->aux->id : 0;
-		return 0;
 	default:
 		return -EINVAL;
 	}
diff --git a/drivers/net/ethernet/ti/cpsw_priv.c b/drivers/net/ethernet/ti/cpsw_priv.c
index a399f3659346..d6d7a7d9c7ad 100644
--- a/drivers/net/ethernet/ti/cpsw_priv.c
+++ b/drivers/net/ethernet/ti/cpsw_priv.c
@@ -1286,9 +1286,6 @@ int cpsw_ndo_bpf(struct net_device *ndev, struct netdev_bpf *bpf)
 	case XDP_SETUP_PROG:
 		return cpsw_xdp_prog_setup(priv, bpf);
 
-	case XDP_QUERY_PROG:
-		return xdp_attachment_query(&priv->xdpi, bpf);
-
 	default:
 		return -EINVAL;
 	}
diff --git a/drivers/net/hyperv/netvsc_bpf.c b/drivers/net/hyperv/netvsc_bpf.c
index 8e4141552423..440486d9c999 100644
--- a/drivers/net/hyperv/netvsc_bpf.c
+++ b/drivers/net/hyperv/netvsc_bpf.c
@@ -163,16 +163,6 @@ int netvsc_vf_setxdp(struct net_device *vf_netdev, struct bpf_prog *prog)
 	return ret;
 }
 
-static u32 netvsc_xdp_query(struct netvsc_device *nvdev)
-{
-	struct bpf_prog *prog = netvsc_xdp_get(nvdev);
-
-	if (prog)
-		return prog->aux->id;
-
-	return 0;
-}
-
 int netvsc_bpf(struct net_device *dev, struct netdev_bpf *bpf)
 {
 	struct net_device_context *ndevctx = netdev_priv(dev);
@@ -182,12 +172,7 @@ int netvsc_bpf(struct net_device *dev, struct netdev_bpf *bpf)
 	int ret;
 
 	if (!nvdev || nvdev->destroy) {
-		if (bpf->command == XDP_QUERY_PROG) {
-			bpf->prog_id = 0;
-			return 0; /* Query must always succeed */
-		} else {
-			return -ENODEV;
-		}
+		return -ENODEV;
 	}
 
 	switch (bpf->command) {
@@ -208,10 +193,6 @@ int netvsc_bpf(struct net_device *dev, struct netdev_bpf *bpf)
 
 		return ret;
 
-	case XDP_QUERY_PROG:
-		bpf->prog_id = netvsc_xdp_query(nvdev);
-		return 0;
-
 	default:
 		return -EINVAL;
 	}
diff --git a/drivers/net/netdevsim/bpf.c b/drivers/net/netdevsim/bpf.c
index 0b362b8dac17..2e90512f3bbe 100644
--- a/drivers/net/netdevsim/bpf.c
+++ b/drivers/net/netdevsim/bpf.c
@@ -551,10 +551,6 @@ int nsim_bpf(struct net_device *dev, struct netdev_bpf *bpf)
 	ASSERT_RTNL();
 
 	switch (bpf->command) {
-	case XDP_QUERY_PROG:
-		return xdp_attachment_query(&ns->xdp, bpf);
-	case XDP_QUERY_PROG_HW:
-		return xdp_attachment_query(&ns->xdp_hw, bpf);
 	case XDP_SETUP_PROG:
 		err = nsim_setup_prog_checks(ns, bpf);
 		if (err)
diff --git a/drivers/net/netdevsim/netdevsim.h b/drivers/net/netdevsim/netdevsim.h
index d164052e0393..284f7092241d 100644
--- a/drivers/net/netdevsim/netdevsim.h
+++ b/drivers/net/netdevsim/netdevsim.h
@@ -121,7 +121,7 @@ static inline void nsim_bpf_uninit(struct netdevsim *ns)
 
 static inline int nsim_bpf(struct net_device *dev, struct netdev_bpf *bpf)
 {
-	return bpf->command == XDP_QUERY_PROG ? 0 : -EOPNOTSUPP;
+	return -EOPNOTSUPP;
 }
 
 static inline int nsim_bpf_disable_tc(struct netdevsim *ns)
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 7adeb91bd368..061bebe25cb1 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -1184,26 +1184,11 @@ static int tun_xdp_set(struct net_device *dev, struct bpf_prog *prog,
 	return 0;
 }
 
-static u32 tun_xdp_query(struct net_device *dev)
-{
-	struct tun_struct *tun = netdev_priv(dev);
-	const struct bpf_prog *xdp_prog;
-
-	xdp_prog = rtnl_dereference(tun->xdp_prog);
-	if (xdp_prog)
-		return xdp_prog->aux->id;
-
-	return 0;
-}
-
 static int tun_xdp(struct net_device *dev, struct netdev_bpf *xdp)
 {
 	switch (xdp->command) {
 	case XDP_SETUP_PROG:
 		return tun_xdp_set(dev, xdp->prog, xdp->extack);
-	case XDP_QUERY_PROG:
-		xdp->prog_id = tun_xdp_query(dev);
-		return 0;
 	default:
 		return -EINVAL;
 	}
diff --git a/drivers/net/veth.c b/drivers/net/veth.c
index b594f03eeddb..e56cd562a664 100644
--- a/drivers/net/veth.c
+++ b/drivers/net/veth.c
@@ -1198,26 +1198,11 @@ err:
 	return err;
 }
 
-static u32 veth_xdp_query(struct net_device *dev)
-{
-	struct veth_priv *priv = netdev_priv(dev);
-	const struct bpf_prog *xdp_prog;
-
-	xdp_prog = priv->_xdp_prog;
-	if (xdp_prog)
-		return xdp_prog->aux->id;
-
-	return 0;
-}
-
 static int veth_xdp(struct net_device *dev, struct netdev_bpf *xdp)
 {
 	switch (xdp->command) {
 	case XDP_SETUP_PROG:
 		return veth_xdp_set(dev, xdp->prog, xdp->extack);
-	case XDP_QUERY_PROG:
-		xdp->prog_id = veth_xdp_query(dev);
-		return 0;
 	default:
 		return -EINVAL;
 	}
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index ba38765dc490..6fa8fe5ef160 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -2490,28 +2490,11 @@ err:
 	return err;
 }
 
-static u32 virtnet_xdp_query(struct net_device *dev)
-{
-	struct virtnet_info *vi = netdev_priv(dev);
-	const struct bpf_prog *xdp_prog;
-	int i;
-
-	for (i = 0; i < vi->max_queue_pairs; i++) {
-		xdp_prog = rtnl_dereference(vi->rq[i].xdp_prog);
-		if (xdp_prog)
-			return xdp_prog->aux->id;
-	}
-	return 0;
-}
-
 static int virtnet_xdp(struct net_device *dev, struct netdev_bpf *xdp)
 {
 	switch (xdp->command) {
 	case XDP_SETUP_PROG:
 		return virtnet_xdp_set(dev, xdp->prog, xdp->extack);
-	case XDP_QUERY_PROG:
-		xdp->prog_id = virtnet_xdp_query(dev);
-		return 0;
 	default:
 		return -EINVAL;
 	}
diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c
index a63e550c370e..458be6882b98 100644
--- a/drivers/net/xen-netfront.c
+++ b/drivers/net/xen-netfront.c
@@ -1480,32 +1480,11 @@ static int xennet_xdp_set(struct net_device *dev, struct bpf_prog *prog,
 	return 0;
 }
 
-static u32 xennet_xdp_query(struct net_device *dev)
-{
-	unsigned int num_queues = dev->real_num_tx_queues;
-	struct netfront_info *np = netdev_priv(dev);
-	const struct bpf_prog *xdp_prog;
-	struct netfront_queue *queue;
-	unsigned int i;
-
-	for (i = 0; i < num_queues; ++i) {
-		queue = &np->queues[i];
-		xdp_prog = rtnl_dereference(queue->xdp_prog);
-		if (xdp_prog)
-			return xdp_prog->aux->id;
-	}
-
-	return 0;
-}
-
 static int xennet_xdp(struct net_device *dev, struct netdev_bpf *xdp)
 {
 	switch (xdp->command) {
 	case XDP_SETUP_PROG:
 		return xennet_xdp_set(dev, xdp->prog, xdp->extack);
-	case XDP_QUERY_PROG:
-		xdp->prog_id = xennet_xdp_query(dev);
-		return 0;
 	default:
 		return -EINVAL;
 	}
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 7d3c412fcfe5..1046763cd0dc 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -876,8 +876,6 @@ enum bpf_netdev_command {
 	 */
 	XDP_SETUP_PROG,
 	XDP_SETUP_PROG_HW,
-	XDP_QUERY_PROG,
-	XDP_QUERY_PROG_HW,
 	/* BPF program for offload callbacks, invoked at program load time. */
 	BPF_OFFLOAD_MAP_ALLOC,
 	BPF_OFFLOAD_MAP_FREE,
@@ -911,12 +909,6 @@ struct netdev_bpf {
 			struct bpf_prog *prog;
 			struct netlink_ext_ack *extack;
 		};
-		/* XDP_QUERY_PROG, XDP_QUERY_PROG_HW */
-		struct {
-			u32 prog_id;
-			/* flags with which program was installed */
-			u32 prog_flags;
-		};
 		/* BPF_OFFLOAD_MAP_ALLOC, BPF_OFFLOAD_MAP_FREE */
 		struct {
 			struct bpf_offloaded_map *offmap;
diff --git a/include/net/xdp.h b/include/net/xdp.h
index dbe9c60797e1..3814fb631d52 100644
--- a/include/net/xdp.h
+++ b/include/net/xdp.h
@@ -240,8 +240,6 @@ struct xdp_attachment_info {
 };
 
 struct netdev_bpf;
-int xdp_attachment_query(struct xdp_attachment_info *info,
-			 struct netdev_bpf *bpf);
 bool xdp_attachment_flags_ok(struct xdp_attachment_info *info,
 			     struct netdev_bpf *bpf);
 void xdp_attachment_setup(struct xdp_attachment_info *info,
diff --git a/net/core/dev.c b/net/core/dev.c
index 82ce0920b172..a2a57988880a 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -5468,10 +5468,6 @@ static int generic_xdp_install(struct net_device *dev, struct netdev_bpf *xdp)
 		}
 		break;
 
-	case XDP_QUERY_PROG:
-		xdp->prog_id = old ? old->aux->id : 0;
-		break;
-
 	default:
 		ret = -EINVAL;
 		break;
diff --git a/net/core/xdp.c b/net/core/xdp.c
index 3c45f99e26d5..48aba933a5a8 100644
--- a/net/core/xdp.c
+++ b/net/core/xdp.c
@@ -400,15 +400,6 @@ void __xdp_release_frame(void *data, struct xdp_mem_info *mem)
 }
 EXPORT_SYMBOL_GPL(__xdp_release_frame);
 
-int xdp_attachment_query(struct xdp_attachment_info *info,
-			 struct netdev_bpf *bpf)
-{
-	bpf->prog_id = info->prog ? info->prog->aux->id : 0;
-	bpf->prog_flags = info->prog ? info->flags : 0;
-	return 0;
-}
-EXPORT_SYMBOL_GPL(xdp_attachment_query);
-
 bool xdp_attachment_flags_ok(struct xdp_attachment_info *info,
 			     struct netdev_bpf *bpf)
 {
-- 
cgit v1.2.3


From f7c6cb1d9728dea9d9f131ef57303d6821afb0f8 Mon Sep 17 00:00:00 2001
From: Stanislav Fomichev <sdf@google.com>
Date: Tue, 28 Jul 2020 17:31:03 -0700
Subject: bpf: Expose socket storage to BPF_PROG_TYPE_CGROUP_SOCK

This lets us use socket storage from the following hooks:

* BPF_CGROUP_INET_SOCK_CREATE
* BPF_CGROUP_INET_SOCK_RELEASE
* BPF_CGROUP_INET4_POST_BIND
* BPF_CGROUP_INET6_POST_BIND

Using existing 'bpf_sk_storage_get_proto' doesn't work because
second argument is ARG_PTR_TO_SOCKET. Even though
BPF_PROG_TYPE_CGROUP_SOCK hooks operate on 'struct bpf_sock',
the verifier still considers it as a PTR_TO_CTX.
That's why I'm adding another 'bpf_sk_storage_get_cg_sock_proto'
definition strictly for BPF_PROG_TYPE_CGROUP_SOCK which accepts
ARG_PTR_TO_CTX which is really 'struct sock' for this program type.

Signed-off-by: Stanislav Fomichev <sdf@google.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Song Liu <songliubraving@fb.com>
Link: https://lore.kernel.org/bpf/20200729003104.1280813-1-sdf@google.com
---
 net/core/bpf_sk_storage.c | 10 ++++++++++
 net/core/filter.c         |  3 +++
 2 files changed, 13 insertions(+)

(limited to 'net/core')

diff --git a/net/core/bpf_sk_storage.c b/net/core/bpf_sk_storage.c
index eafcd15e7dfd..d3377c90a291 100644
--- a/net/core/bpf_sk_storage.c
+++ b/net/core/bpf_sk_storage.c
@@ -944,6 +944,16 @@ const struct bpf_func_proto bpf_sk_storage_get_proto = {
 	.arg4_type	= ARG_ANYTHING,
 };
 
+const struct bpf_func_proto bpf_sk_storage_get_cg_sock_proto = {
+	.func		= bpf_sk_storage_get,
+	.gpl_only	= false,
+	.ret_type	= RET_PTR_TO_MAP_VALUE_OR_NULL,
+	.arg1_type	= ARG_CONST_MAP_PTR,
+	.arg2_type	= ARG_PTR_TO_CTX, /* context is 'struct sock' */
+	.arg3_type	= ARG_PTR_TO_MAP_VALUE_OR_NULL,
+	.arg4_type	= ARG_ANYTHING,
+};
+
 const struct bpf_func_proto bpf_sk_storage_delete_proto = {
 	.func		= bpf_sk_storage_delete,
 	.gpl_only	= false,
diff --git a/net/core/filter.c b/net/core/filter.c
index 29e3455122f7..7124f0fe6974 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -6187,6 +6187,7 @@ bool bpf_helper_changes_pkt_data(void *func)
 }
 
 const struct bpf_func_proto bpf_event_output_data_proto __weak;
+const struct bpf_func_proto bpf_sk_storage_get_cg_sock_proto __weak;
 
 static const struct bpf_func_proto *
 sock_filter_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
@@ -6219,6 +6220,8 @@ sock_filter_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 	case BPF_FUNC_get_cgroup_classid:
 		return &bpf_get_cgroup_classid_curr_proto;
 #endif
+	case BPF_FUNC_sk_storage_get:
+		return &bpf_sk_storage_get_cg_sock_proto;
 	default:
 		return bpf_base_func_proto(func_id);
 	}
-- 
cgit v1.2.3


From 73b11c2ab072d5b0599d1e12cc126f55ee306daf Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andriin@fb.com>
Date: Fri, 31 Jul 2020 11:28:26 -0700
Subject: bpf: Add support for forced LINK_DETACH command

Add LINK_DETACH command to force-detach bpf_link without destroying it. It has
the same behavior as auto-detaching of bpf_link due to cgroup dying for
bpf_cgroup_link or net_device being destroyed for bpf_xdp_link. In such case,
bpf_link is still a valid kernel object, but is defuncts and doesn't hold BPF
program attached to corresponding BPF hook. This functionality allows users
with enough access rights to manually force-detach attached bpf_link without
killing respective owner process.

This patch implements LINK_DETACH for cgroup, xdp, and netns links, mostly
re-using existing link release handling code.

Signed-off-by: Andrii Nakryiko <andriin@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Song Liu <songliubraving@fb.com>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Link: https://lore.kernel.org/bpf/20200731182830.286260-2-andriin@fb.com
---
 include/linux/bpf.h        |  1 +
 include/uapi/linux/bpf.h   |  5 +++++
 kernel/bpf/cgroup.c        | 15 ++++++++++++++-
 kernel/bpf/net_namespace.c |  8 ++++++++
 kernel/bpf/syscall.c       | 26 ++++++++++++++++++++++++++
 net/core/dev.c             | 11 ++++++++++-
 6 files changed, 64 insertions(+), 2 deletions(-)

(limited to 'net/core')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 40c5e206ecf2..cef4ef0d2b4e 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -793,6 +793,7 @@ struct bpf_link {
 struct bpf_link_ops {
 	void (*release)(struct bpf_link *link);
 	void (*dealloc)(struct bpf_link *link);
+	int (*detach)(struct bpf_link *link);
 	int (*update_prog)(struct bpf_link *link, struct bpf_prog *new_prog,
 			   struct bpf_prog *old_prog);
 	void (*show_fdinfo)(const struct bpf_link *link, struct seq_file *seq);
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index eb5e0c38eb2c..b134e679e9db 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -117,6 +117,7 @@ enum bpf_cmd {
 	BPF_LINK_GET_NEXT_ID,
 	BPF_ENABLE_STATS,
 	BPF_ITER_CREATE,
+	BPF_LINK_DETACH,
 };
 
 enum bpf_map_type {
@@ -634,6 +635,10 @@ union bpf_attr {
 		__u32		old_prog_fd;
 	} link_update;
 
+	struct {
+		__u32		link_fd;
+	} link_detach;
+
 	struct { /* struct used by BPF_ENABLE_STATS command */
 		__u32		type;
 	} enable_stats;
diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c
index 957cce1d5168..83ff127ef7ae 100644
--- a/kernel/bpf/cgroup.c
+++ b/kernel/bpf/cgroup.c
@@ -814,6 +814,7 @@ static void bpf_cgroup_link_release(struct bpf_link *link)
 {
 	struct bpf_cgroup_link *cg_link =
 		container_of(link, struct bpf_cgroup_link, link);
+	struct cgroup *cg;
 
 	/* link might have been auto-detached by dying cgroup already,
 	 * in that case our work is done here
@@ -832,8 +833,12 @@ static void bpf_cgroup_link_release(struct bpf_link *link)
 	WARN_ON(__cgroup_bpf_detach(cg_link->cgroup, NULL, cg_link,
 				    cg_link->type));
 
+	cg = cg_link->cgroup;
+	cg_link->cgroup = NULL;
+
 	mutex_unlock(&cgroup_mutex);
-	cgroup_put(cg_link->cgroup);
+
+	cgroup_put(cg);
 }
 
 static void bpf_cgroup_link_dealloc(struct bpf_link *link)
@@ -844,6 +849,13 @@ static void bpf_cgroup_link_dealloc(struct bpf_link *link)
 	kfree(cg_link);
 }
 
+static int bpf_cgroup_link_detach(struct bpf_link *link)
+{
+	bpf_cgroup_link_release(link);
+
+	return 0;
+}
+
 static void bpf_cgroup_link_show_fdinfo(const struct bpf_link *link,
 					struct seq_file *seq)
 {
@@ -883,6 +895,7 @@ static int bpf_cgroup_link_fill_link_info(const struct bpf_link *link,
 static const struct bpf_link_ops bpf_cgroup_link_lops = {
 	.release = bpf_cgroup_link_release,
 	.dealloc = bpf_cgroup_link_dealloc,
+	.detach = bpf_cgroup_link_detach,
 	.update_prog = cgroup_bpf_replace,
 	.show_fdinfo = bpf_cgroup_link_show_fdinfo,
 	.fill_link_info = bpf_cgroup_link_fill_link_info,
diff --git a/kernel/bpf/net_namespace.c b/kernel/bpf/net_namespace.c
index 71405edd667c..542f275bf252 100644
--- a/kernel/bpf/net_namespace.c
+++ b/kernel/bpf/net_namespace.c
@@ -142,9 +142,16 @@ static void bpf_netns_link_release(struct bpf_link *link)
 	bpf_prog_array_free(old_array);
 
 out_unlock:
+	net_link->net = NULL;
 	mutex_unlock(&netns_bpf_mutex);
 }
 
+static int bpf_netns_link_detach(struct bpf_link *link)
+{
+	bpf_netns_link_release(link);
+	return 0;
+}
+
 static void bpf_netns_link_dealloc(struct bpf_link *link)
 {
 	struct bpf_netns_link *net_link =
@@ -228,6 +235,7 @@ static void bpf_netns_link_show_fdinfo(const struct bpf_link *link,
 static const struct bpf_link_ops bpf_netns_link_ops = {
 	.release = bpf_netns_link_release,
 	.dealloc = bpf_netns_link_dealloc,
+	.detach = bpf_netns_link_detach,
 	.update_prog = bpf_netns_link_update_prog,
 	.fill_link_info = bpf_netns_link_fill_info,
 	.show_fdinfo = bpf_netns_link_show_fdinfo,
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index cd3d599e9e90..2f343ce15747 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -3991,6 +3991,29 @@ out_put_link:
 	return ret;
 }
 
+#define BPF_LINK_DETACH_LAST_FIELD link_detach.link_fd
+
+static int link_detach(union bpf_attr *attr)
+{
+	struct bpf_link *link;
+	int ret;
+
+	if (CHECK_ATTR(BPF_LINK_DETACH))
+		return -EINVAL;
+
+	link = bpf_link_get_from_fd(attr->link_detach.link_fd);
+	if (IS_ERR(link))
+		return PTR_ERR(link);
+
+	if (link->ops->detach)
+		ret = link->ops->detach(link);
+	else
+		ret = -EOPNOTSUPP;
+
+	bpf_link_put(link);
+	return ret;
+}
+
 static int bpf_link_inc_not_zero(struct bpf_link *link)
 {
 	return atomic64_fetch_add_unless(&link->refcnt, 1, 0) ? 0 : -ENOENT;
@@ -4240,6 +4263,9 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz
 	case BPF_ITER_CREATE:
 		err = bpf_iter_create(&attr);
 		break;
+	case BPF_LINK_DETACH:
+		err = link_detach(&attr);
+		break;
 	default:
 		err = -EINVAL;
 		break;
diff --git a/net/core/dev.c b/net/core/dev.c
index a2a57988880a..c8b911b10187 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -8979,12 +8979,20 @@ static void bpf_xdp_link_release(struct bpf_link *link)
 	/* if racing with net_device's tear down, xdp_link->dev might be
 	 * already NULL, in which case link was already auto-detached
 	 */
-	if (xdp_link->dev)
+	if (xdp_link->dev) {
 		WARN_ON(dev_xdp_detach_link(xdp_link->dev, NULL, xdp_link));
+		xdp_link->dev = NULL;
+	}
 
 	rtnl_unlock();
 }
 
+static int bpf_xdp_link_detach(struct bpf_link *link)
+{
+	bpf_xdp_link_release(link);
+	return 0;
+}
+
 static void bpf_xdp_link_dealloc(struct bpf_link *link)
 {
 	struct bpf_xdp_link *xdp_link = container_of(link, struct bpf_xdp_link, link);
@@ -9066,6 +9074,7 @@ out_unlock:
 static const struct bpf_link_ops bpf_xdp_link_lops = {
 	.release = bpf_xdp_link_release,
 	.dealloc = bpf_xdp_link_dealloc,
+	.detach = bpf_xdp_link_detach,
 	.show_fdinfo = bpf_xdp_link_show_fdinfo,
 	.fill_link_info = bpf_xdp_link_fill_link_info,
 	.update_prog = bpf_xdp_link_update,
-- 
cgit v1.2.3