summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
Diffstat
-rw-r--r--include/linux/bpf.h20
-rw-r--r--include/linux/filter.h19
-rw-r--r--include/net/xdp.h1
-rw-r--r--include/trace/events/xdp.h6
-rw-r--r--include/uapi/linux/bpf.h14
-rw-r--r--kernel/bpf/cpumap.c3
-rw-r--r--kernel/bpf/devmap.c183
-rw-r--r--net/core/filter.c37
-rw-r--r--net/core/xdp.c28
-rw-r--r--net/xdp/xskmap.c3
-rw-r--r--tools/include/uapi/linux/bpf.h14
11 files changed, 313 insertions, 15 deletions
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 1e9a0ff3217b..86dec5001ae2 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -1501,8 +1501,13 @@ int dev_xdp_enqueue(struct net_device *dev, struct xdp_buff *xdp,
struct net_device *dev_rx);
int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp,
struct net_device *dev_rx);
+int dev_map_enqueue_multi(struct xdp_buff *xdp, struct net_device *dev_rx,
+ struct bpf_map *map, bool exclude_ingress);
int dev_map_generic_redirect(struct bpf_dtab_netdev *dst, struct sk_buff *skb,
struct bpf_prog *xdp_prog);
+int dev_map_redirect_multi(struct net_device *dev, struct sk_buff *skb,
+ struct bpf_prog *xdp_prog, struct bpf_map *map,
+ bool exclude_ingress);
bool dev_map_can_have_prog(struct bpf_map *map);
void __cpu_map_flush(void);
@@ -1670,6 +1675,13 @@ int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp,
return 0;
}
+static inline
+int dev_map_enqueue_multi(struct xdp_buff *xdp, struct net_device *dev_rx,
+ struct bpf_map *map, bool exclude_ingress)
+{
+ return 0;
+}
+
struct sk_buff;
static inline int dev_map_generic_redirect(struct bpf_dtab_netdev *dst,
@@ -1679,6 +1691,14 @@ static inline int dev_map_generic_redirect(struct bpf_dtab_netdev *dst,
return 0;
}
+static inline
+int dev_map_redirect_multi(struct net_device *dev, struct sk_buff *skb,
+ struct bpf_prog *xdp_prog, struct bpf_map *map,
+ bool exclude_ingress)
+{
+ return 0;
+}
+
static inline void __cpu_map_flush(void)
{
}
diff --git a/include/linux/filter.h b/include/linux/filter.h
index 9a09547bc7ba..c5ad7df029ed 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -646,6 +646,7 @@ struct bpf_redirect_info {
u32 flags;
u32 tgt_index;
void *tgt_value;
+ struct bpf_map *map;
u32 map_id;
enum bpf_map_type map_type;
u32 kern_flags;
@@ -1464,17 +1465,19 @@ static inline bool bpf_sk_lookup_run_v6(struct net *net, int protocol,
}
#endif /* IS_ENABLED(CONFIG_IPV6) */
-static __always_inline int __bpf_xdp_redirect_map(struct bpf_map *map, u32 ifindex, u64 flags,
+static __always_inline int __bpf_xdp_redirect_map(struct bpf_map *map, u32 ifindex,
+ u64 flags, const u64 flag_mask,
void *lookup_elem(struct bpf_map *map, u32 key))
{
struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info);
+ const u64 action_mask = XDP_ABORTED | XDP_DROP | XDP_PASS | XDP_TX;
/* Lower bits of the flags are used as return code on lookup failure */
- if (unlikely(flags > XDP_TX))
+ if (unlikely(flags & ~(action_mask | flag_mask)))
return XDP_ABORTED;
ri->tgt_value = lookup_elem(map, ifindex);
- if (unlikely(!ri->tgt_value)) {
+ if (unlikely(!ri->tgt_value) && !(flags & BPF_F_BROADCAST)) {
/* If the lookup fails we want to clear out the state in the
* redirect_info struct completely, so that if an eBPF program
* performs multiple lookups, the last one always takes
@@ -1482,13 +1485,21 @@ static __always_inline int __bpf_xdp_redirect_map(struct bpf_map *map, u32 ifind
*/
ri->map_id = INT_MAX; /* Valid map id idr range: [1,INT_MAX[ */
ri->map_type = BPF_MAP_TYPE_UNSPEC;
- return flags;
+ return flags & action_mask;
}
ri->tgt_index = ifindex;
ri->map_id = map->id;
ri->map_type = map->map_type;
+ if (flags & BPF_F_BROADCAST) {
+ WRITE_ONCE(ri->map, map);
+ ri->flags = flags;
+ } else {
+ WRITE_ONCE(ri->map, NULL);
+ ri->flags = 0;
+ }
+
return XDP_REDIRECT;
}
diff --git a/include/net/xdp.h b/include/net/xdp.h
index a5bc214a49d9..5533f0ab2afc 100644
--- a/include/net/xdp.h
+++ b/include/net/xdp.h
@@ -170,6 +170,7 @@ struct sk_buff *__xdp_build_skb_from_frame(struct xdp_frame *xdpf,
struct sk_buff *xdp_build_skb_from_frame(struct xdp_frame *xdpf,
struct net_device *dev);
int xdp_alloc_skb_bulk(void **skbs, int n_skb, gfp_t gfp);
+struct xdp_frame *xdpf_clone(struct xdp_frame *xdpf);
static inline
void xdp_convert_frame_to_buff(struct xdp_frame *frame, struct xdp_buff *xdp)
diff --git a/include/trace/events/xdp.h b/include/trace/events/xdp.h
index fcad3645a70b..c40fc97f9417 100644
--- a/include/trace/events/xdp.h
+++ b/include/trace/events/xdp.h
@@ -110,7 +110,11 @@ DECLARE_EVENT_CLASS(xdp_redirect_template,
u32 ifindex = 0, map_index = index;
if (map_type == BPF_MAP_TYPE_DEVMAP || map_type == BPF_MAP_TYPE_DEVMAP_HASH) {
- ifindex = ((struct _bpf_dtab_netdev *)tgt)->dev->ifindex;
+ /* Just leave to_ifindex to 0 if do broadcast redirect,
+ * as tgt will be NULL.
+ */
+ if (tgt)
+ ifindex = ((struct _bpf_dtab_netdev *)tgt)->dev->ifindex;
} else if (map_type == BPF_MAP_TYPE_UNSPEC && map_id == INT_MAX) {
ifindex = index;
map_index = 0;
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 562adeac1d67..2c1ba70abbf1 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -2555,8 +2555,12 @@ union bpf_attr {
* The lower two bits of *flags* are used as the return code if
* the map lookup fails. This is so that the return value can be
* one of the XDP program return codes up to **XDP_TX**, as chosen
- * by the caller. Any higher bits in the *flags* argument must be
- * unset.
+ * by the caller. The higher bits of *flags* can be set to
+ * BPF_F_BROADCAST or BPF_F_EXCLUDE_INGRESS as defined below.
+ *
+ * With BPF_F_BROADCAST the packet will be broadcasted to all the
+ * interfaces in the map, with BPF_F_EXCLUDE_INGRESS the ingress
+ * interface will be excluded when do broadcasting.
*
* See also **bpf_redirect**\ (), which only supports redirecting
* to an ifindex, but doesn't require a map to do so.
@@ -5122,6 +5126,12 @@ enum {
BPF_F_BPRM_SECUREEXEC = (1ULL << 0),
};
+/* Flags for bpf_redirect_map helper */
+enum {
+ BPF_F_BROADCAST = (1ULL << 3),
+ BPF_F_EXCLUDE_INGRESS = (1ULL << 4),
+};
+
#define __bpf_md_ptr(type, name) \
union { \
type name; \
diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c
index 5dd3e866599a..a1a0c4e791c6 100644
--- a/kernel/bpf/cpumap.c
+++ b/kernel/bpf/cpumap.c
@@ -601,7 +601,8 @@ static int cpu_map_get_next_key(struct bpf_map *map, void *key, void *next_key)
static int cpu_map_redirect(struct bpf_map *map, u32 ifindex, u64 flags)
{
- return __bpf_xdp_redirect_map(map, ifindex, flags, __cpu_map_lookup_elem);
+ return __bpf_xdp_redirect_map(map, ifindex, flags, 0,
+ __cpu_map_lookup_elem);
}
static int cpu_map_btf_id;
diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c
index 642264e32abd..f9148daab0e3 100644
--- a/kernel/bpf/devmap.c
+++ b/kernel/bpf/devmap.c
@@ -198,6 +198,7 @@ static void dev_map_free(struct bpf_map *map)
list_del_rcu(&dtab->list);
spin_unlock(&dev_map_lock);
+ bpf_clear_redirect_map(map);
synchronize_rcu();
/* Make sure prior __dev_map_entry_free() have completed. */
@@ -515,6 +516,99 @@ int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp,
return __xdp_enqueue(dev, xdp, dev_rx, dst->xdp_prog);
}
+static bool is_valid_dst(struct bpf_dtab_netdev *obj, struct xdp_buff *xdp,
+ int exclude_ifindex)
+{
+ if (!obj || obj->dev->ifindex == exclude_ifindex ||
+ !obj->dev->netdev_ops->ndo_xdp_xmit)
+ return false;
+
+ if (xdp_ok_fwd_dev(obj->dev, xdp->data_end - xdp->data))
+ return false;
+
+ return true;
+}
+
+static int dev_map_enqueue_clone(struct bpf_dtab_netdev *obj,
+ struct net_device *dev_rx,
+ struct xdp_frame *xdpf)
+{
+ struct xdp_frame *nxdpf;
+
+ nxdpf = xdpf_clone(xdpf);
+ if (!nxdpf)
+ return -ENOMEM;
+
+ bq_enqueue(obj->dev, nxdpf, dev_rx, obj->xdp_prog);
+
+ return 0;
+}
+
+int dev_map_enqueue_multi(struct xdp_buff *xdp, struct net_device *dev_rx,
+ struct bpf_map *map, bool exclude_ingress)
+{
+ struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map);
+ int exclude_ifindex = exclude_ingress ? dev_rx->ifindex : 0;
+ struct bpf_dtab_netdev *dst, *last_dst = NULL;
+ struct hlist_head *head;
+ struct xdp_frame *xdpf;
+ unsigned int i;
+ int err;
+
+ xdpf = xdp_convert_buff_to_frame(xdp);
+ if (unlikely(!xdpf))
+ return -EOVERFLOW;
+
+ if (map->map_type == BPF_MAP_TYPE_DEVMAP) {
+ for (i = 0; i < map->max_entries; i++) {
+ dst = READ_ONCE(dtab->netdev_map[i]);
+ if (!is_valid_dst(dst, xdp, exclude_ifindex))
+ continue;
+
+ /* we only need n-1 clones; last_dst enqueued below */
+ if (!last_dst) {
+ last_dst = dst;
+ continue;
+ }
+
+ err = dev_map_enqueue_clone(last_dst, dev_rx, xdpf);
+ if (err)
+ return err;
+
+ last_dst = dst;
+ }
+ } else { /* BPF_MAP_TYPE_DEVMAP_HASH */
+ for (i = 0; i < dtab->n_buckets; i++) {
+ head = dev_map_index_hash(dtab, i);
+ hlist_for_each_entry_rcu(dst, head, index_hlist,
+ lockdep_is_held(&dtab->index_lock)) {
+ if (!is_valid_dst(dst, xdp, exclude_ifindex))
+ continue;
+
+ /* we only need n-1 clones; last_dst enqueued below */
+ if (!last_dst) {
+ last_dst = dst;
+ continue;
+ }
+
+ err = dev_map_enqueue_clone(last_dst, dev_rx, xdpf);
+ if (err)
+ return err;
+
+ last_dst = dst;
+ }
+ }
+ }
+
+ /* consume the last copy of the frame */
+ if (last_dst)
+ bq_enqueue(last_dst->dev, xdpf, dev_rx, last_dst->xdp_prog);
+ else
+ xdp_return_frame_rx_napi(xdpf); /* dtab is empty */
+
+ return 0;
+}
+
int dev_map_generic_redirect(struct bpf_dtab_netdev *dst, struct sk_buff *skb,
struct bpf_prog *xdp_prog)
{
@@ -529,6 +623,87 @@ int dev_map_generic_redirect(struct bpf_dtab_netdev *dst, struct sk_buff *skb,
return 0;
}
+static int dev_map_redirect_clone(struct bpf_dtab_netdev *dst,
+ struct sk_buff *skb,
+ struct bpf_prog *xdp_prog)
+{
+ struct sk_buff *nskb;
+ int err;
+
+ nskb = skb_clone(skb, GFP_ATOMIC);
+ if (!nskb)
+ return -ENOMEM;
+
+ err = dev_map_generic_redirect(dst, nskb, xdp_prog);
+ if (unlikely(err)) {
+ consume_skb(nskb);
+ return err;
+ }
+
+ return 0;
+}
+
+int dev_map_redirect_multi(struct net_device *dev, struct sk_buff *skb,
+ struct bpf_prog *xdp_prog, struct bpf_map *map,
+ bool exclude_ingress)
+{
+ struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map);
+ int exclude_ifindex = exclude_ingress ? dev->ifindex : 0;
+ struct bpf_dtab_netdev *dst, *last_dst = NULL;
+ struct hlist_head *head;
+ struct hlist_node *next;
+ unsigned int i;
+ int err;
+
+ if (map->map_type == BPF_MAP_TYPE_DEVMAP) {
+ for (i = 0; i < map->max_entries; i++) {
+ dst = READ_ONCE(dtab->netdev_map[i]);
+ if (!dst || dst->dev->ifindex == exclude_ifindex)
+ continue;
+
+ /* we only need n-1 clones; last_dst enqueued below */
+ if (!last_dst) {
+ last_dst = dst;
+ continue;
+ }
+
+ err = dev_map_redirect_clone(last_dst, skb, xdp_prog);
+ if (err)
+ return err;
+
+ last_dst = dst;
+ }
+ } else { /* BPF_MAP_TYPE_DEVMAP_HASH */
+ for (i = 0; i < dtab->n_buckets; i++) {
+ head = dev_map_index_hash(dtab, i);
+ hlist_for_each_entry_safe(dst, next, head, index_hlist) {
+ if (!dst || dst->dev->ifindex == exclude_ifindex)
+ continue;
+
+ /* we only need n-1 clones; last_dst enqueued below */
+ if (!last_dst) {
+ last_dst = dst;
+ continue;
+ }
+
+ err = dev_map_redirect_clone(last_dst, skb, xdp_prog);
+ if (err)
+ return err;
+
+ last_dst = dst;
+ }
+ }
+ }
+
+ /* consume the first skb and return */
+ if (last_dst)
+ return dev_map_generic_redirect(last_dst, skb, xdp_prog);
+
+ /* dtab is empty */
+ consume_skb(skb);
+ return 0;
+}
+
static void *dev_map_lookup_elem(struct bpf_map *map, void *key)
{
struct bpf_dtab_netdev *obj = __dev_map_lookup_elem(map, *(u32 *)key);
@@ -755,12 +930,16 @@ static int dev_map_hash_update_elem(struct bpf_map *map, void *key, void *value,
static int dev_map_redirect(struct bpf_map *map, u32 ifindex, u64 flags)
{
- return __bpf_xdp_redirect_map(map, ifindex, flags, __dev_map_lookup_elem);
+ return __bpf_xdp_redirect_map(map, ifindex, flags,
+ BPF_F_BROADCAST | BPF_F_EXCLUDE_INGRESS,
+ __dev_map_lookup_elem);
}
static int dev_hash_map_redirect(struct bpf_map *map, u32 ifindex, u64 flags)
{
- return __bpf_xdp_redirect_map(map, ifindex, flags, __dev_map_hash_lookup_elem);
+ return __bpf_xdp_redirect_map(map, ifindex, flags,
+ BPF_F_BROADCAST | BPF_F_EXCLUDE_INGRESS,
+ __dev_map_hash_lookup_elem);
}
static int dev_map_btf_id;
diff --git a/net/core/filter.c b/net/core/filter.c
index 582ac196fd94..caa88955562e 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -3930,6 +3930,23 @@ void xdp_do_flush(void)
}
EXPORT_SYMBOL_GPL(xdp_do_flush);
+void bpf_clear_redirect_map(struct bpf_map *map)
+{
+ struct bpf_redirect_info *ri;
+ int cpu;
+
+ for_each_possible_cpu(cpu) {
+ ri = per_cpu_ptr(&bpf_redirect_info, cpu);
+ /* Avoid polluting remote cacheline due to writes if
+ * not needed. Once we pass this test, we need the
+ * cmpxchg() to make sure it hasn't been changed in
+ * the meantime by remote CPU.
+ */
+ if (unlikely(READ_ONCE(ri->map) == map))
+ cmpxchg(&ri->map, map, NULL);
+ }
+}
+
int xdp_do_redirect(struct net_device *dev, struct xdp_buff *xdp,
struct bpf_prog *xdp_prog)
{
@@ -3937,6 +3954,7 @@ int xdp_do_redirect(struct net_device *dev, struct xdp_buff *xdp,
enum bpf_map_type map_type = ri->map_type;
void *fwd = ri->tgt_value;
u32 map_id = ri->map_id;
+ struct bpf_map *map;
int err;
ri->map_id = 0; /* Valid map id idr range: [1,INT_MAX[ */
@@ -3946,7 +3964,14 @@ int xdp_do_redirect(struct net_device *dev, struct xdp_buff *xdp,
case BPF_MAP_TYPE_DEVMAP:
fallthrough;
case BPF_MAP_TYPE_DEVMAP_HASH:
- err = dev_map_enqueue(fwd, xdp, dev);
+ map = READ_ONCE(ri->map);
+ if (unlikely(map)) {
+ WRITE_ONCE(ri->map, NULL);
+ err = dev_map_enqueue_multi(xdp, dev, map,
+ ri->flags & BPF_F_EXCLUDE_INGRESS);
+ } else {
+ err = dev_map_enqueue(fwd, xdp, dev);
+ }
break;
case BPF_MAP_TYPE_CPUMAP:
err = cpu_map_enqueue(fwd, xdp, dev);
@@ -3988,13 +4013,21 @@ static int xdp_do_generic_redirect_map(struct net_device *dev,
enum bpf_map_type map_type, u32 map_id)
{
struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info);
+ struct bpf_map *map;
int err;
switch (map_type) {
case BPF_MAP_TYPE_DEVMAP:
fallthrough;
case BPF_MAP_TYPE_DEVMAP_HASH:
- err = dev_map_generic_redirect(fwd, skb, xdp_prog);
+ map = READ_ONCE(ri->map);
+ if (unlikely(map)) {
+ WRITE_ONCE(ri->map, NULL);
+ err = dev_map_redirect_multi(dev, skb, xdp_prog, map,
+ ri->flags & BPF_F_EXCLUDE_INGRESS);
+ } else {
+ err = dev_map_generic_redirect(fwd, skb, xdp_prog);
+ }
if (unlikely(err))
goto err;
break;
diff --git a/net/core/xdp.c b/net/core/xdp.c
index 858276e72c68..725d20f1b100 100644
--- a/net/core/xdp.c
+++ b/net/core/xdp.c
@@ -584,3 +584,31 @@ struct sk_buff *xdp_build_skb_from_frame(struct xdp_frame *xdpf,
return __xdp_build_skb_from_frame(xdpf, skb, dev);
}
EXPORT_SYMBOL_GPL(xdp_build_skb_from_frame);
+
+struct xdp_frame *xdpf_clone(struct xdp_frame *xdpf)
+{
+ unsigned int headroom, totalsize;
+ struct xdp_frame *nxdpf;
+ struct page *page;
+ void *addr;
+
+ headroom = xdpf->headroom + sizeof(*xdpf);
+ totalsize = headroom + xdpf->len;
+
+ if (unlikely(totalsize > PAGE_SIZE))
+ return NULL;
+ page = dev_alloc_page();
+ if (!page)
+ return NULL;
+ addr = page_to_virt(page);
+
+ memcpy(addr, xdpf, totalsize);
+
+ nxdpf = addr;
+ nxdpf->data = addr + headroom;
+ nxdpf->frame_sz = PAGE_SIZE;
+ nxdpf->mem.type = MEM_TYPE_PAGE_ORDER0;
+ nxdpf->mem.id = 0;
+
+ return nxdpf;
+}
diff --git a/net/xdp/xskmap.c b/net/xdp/xskmap.c
index 67b4ce504852..9df75ea4a567 100644
--- a/net/xdp/xskmap.c
+++ b/net/xdp/xskmap.c
@@ -226,7 +226,8 @@ static int xsk_map_delete_elem(struct bpf_map *map, void *key)
static int xsk_map_redirect(struct bpf_map *map, u32 ifindex, u64 flags)
{
- return __bpf_xdp_redirect_map(map, ifindex, flags, __xsk_map_lookup_elem);
+ return __bpf_xdp_redirect_map(map, ifindex, flags, 0,
+ __xsk_map_lookup_elem);
}
void xsk_map_try_sock_delete(struct xsk_map *map, struct xdp_sock *xs,
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 562adeac1d67..2c1ba70abbf1 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -2555,8 +2555,12 @@ union bpf_attr {
* The lower two bits of *flags* are used as the return code if
* the map lookup fails. This is so that the return value can be
* one of the XDP program return codes up to **XDP_TX**, as chosen
- * by the caller. Any higher bits in the *flags* argument must be
- * unset.
+ * by the caller. The higher bits of *flags* can be set to
+ * BPF_F_BROADCAST or BPF_F_EXCLUDE_INGRESS as defined below.
+ *
+ * With BPF_F_BROADCAST the packet will be broadcasted to all the
+ * interfaces in the map, with BPF_F_EXCLUDE_INGRESS the ingress
+ * interface will be excluded when do broadcasting.
*
* See also **bpf_redirect**\ (), which only supports redirecting
* to an ifindex, but doesn't require a map to do so.
@@ -5122,6 +5126,12 @@ enum {
BPF_F_BPRM_SECUREEXEC = (1ULL << 0),
};
+/* Flags for bpf_redirect_map helper */
+enum {
+ BPF_F_BROADCAST = (1ULL << 3),
+ BPF_F_EXCLUDE_INGRESS = (1ULL << 4),
+};
+
#define __bpf_md_ptr(type, name) \
union { \
type name; \
generated by cgit (git 2.34.1) at 2024-06-26 08:42:41 +0000