* [PATCHv4 bpf-next 1/4] bpf: run devmap xdp_prog on flush instead of bulk enqueue
2021-04-02 12:19 [PATCHv4 bpf-next 0/4] xdp: extend xdp_redirect_map with broadcast support Hangbin Liu
@ 2021-04-02 12:19 ` Hangbin Liu
2021-04-02 12:19 ` [PATCHv4 bpf-next 2/4] xdp: extend xdp_redirect_map with broadcast support Hangbin Liu
` (2 subsequent siblings)
3 siblings, 0 replies; 15+ messages in thread
From: Hangbin Liu @ 2021-04-02 12:19 UTC (permalink / raw)
To: bpf
Cc: netdev, Toke Høiland-Jørgensen, Jiri Benc,
Jesper Dangaard Brouer, Eelco Chaudron, ast, Daniel Borkmann,
Lorenzo Bianconi, David Ahern, Andrii Nakryiko,
Alexei Starovoitov, John Fastabend, Maciej Fijalkowski,
Björn Töpel, Hangbin Liu
From: Jesper Dangaard Brouer <brouer@redhat.com>
This changes the devmap XDP program support to run the program when the
bulk queue is flushed instead of before the frame is enqueued. This has
a couple of benefits:
- It "sorts" the packets by destination devmap entry, and then runs the
same BPF program on all the packets in sequence. This ensures that we
keep the XDP program and destination device properties hot in I-cache.
- It makes the multicast implementation simpler because it can just
enqueue packets using bq_enqueue() without having to deal with the
devmap program at all.
The drawback is that if the devmap program drops the packet, the enqueue
step is redundant. However, arguably this is mostly visible in a
micro-benchmark, and with more mixed traffic the I-cache benefit should
win out. The performance impact of just this patch is as follows:
When bq_xmit_all() is called from bq_enqueue(), another packet will
always be enqueued immediately after, so clearing dev_rx, xdp_prog and
flush_node in bq_xmit_all() is redundant. Move the clear to __dev_flush(),
and only check them once in bq_enqueue() since they are all modified together.
By using xdp_redirect_map in sample/bpf and send pkts via pktgen cmd:
./pktgen_sample03_burst_single_flow.sh -i eno1 -d $dst_ip -m $dst_mac -t 10 -s 64
And do XDP_DROP on veth peer.
There are about +/- 0.1M deviation for native testing, the performance
improved for the base-case, but some drop back with xdp devmap prog attached.
Version | Test | Generic | Native | Native + 2nd xdp_prog
5.12 rc2 | xdp_redirect_map i40e->i40e | 2.0M | 9.8M | 8.4M
5.12 rc2 | xdp_redirect_map i40e->veth | 1.8M | 12.0M | 10.0M
5.12 rc2 + patch | xdp_redirect_map i40e->i40e | 2.0M | 10.0M | 8.0M
5.12 rc2 + patch | xdp_redirect_map i40e->veth | 1.8M | 12.4M | 9.5M
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
---
v3: rebase the code based on Lorenzo's "Move drop error path to devmap
for XDP_REDIRECT"
v2: no update
---
kernel/bpf/devmap.c | 127 ++++++++++++++++++++++++++------------------
1 file changed, 76 insertions(+), 51 deletions(-)
diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c
index aa516472ce46..3980fb3bfb09 100644
--- a/kernel/bpf/devmap.c
+++ b/kernel/bpf/devmap.c
@@ -57,6 +57,7 @@ struct xdp_dev_bulk_queue {
struct list_head flush_node;
struct net_device *dev;
struct net_device *dev_rx;
+ struct bpf_prog *xdp_prog;
unsigned int count;
};
@@ -326,22 +327,71 @@ bool dev_map_can_have_prog(struct bpf_map *map)
return false;
}
+static int dev_map_bpf_prog_run(struct bpf_prog *xdp_prog,
+ struct xdp_frame **frames, int n,
+ struct net_device *dev)
+{
+ struct xdp_txq_info txq = { .dev = dev };
+ struct xdp_buff xdp;
+ int i, nframes = 0;
+
+ for (i = 0; i < n; i++) {
+ struct xdp_frame *xdpf = frames[i];
+ u32 act;
+ int err;
+
+ xdp_convert_frame_to_buff(xdpf, &xdp);
+ xdp.txq = &txq;
+
+ act = bpf_prog_run_xdp(xdp_prog, &xdp);
+ switch (act) {
+ case XDP_PASS:
+ err = xdp_update_frame_from_buff(&xdp, xdpf);
+ if (unlikely(err < 0))
+ xdp_return_frame_rx_napi(xdpf);
+ else
+ frames[nframes++] = xdpf;
+ break;
+ default:
+ bpf_warn_invalid_xdp_action(act);
+ fallthrough;
+ case XDP_ABORTED:
+ trace_xdp_exception(dev, xdp_prog, act);
+ fallthrough;
+ case XDP_DROP:
+ xdp_return_frame_rx_napi(xdpf);
+ break;
+ }
+ }
+ return nframes; /* sent frames count */
+}
+
static void bq_xmit_all(struct xdp_dev_bulk_queue *bq, u32 flags)
{
struct net_device *dev = bq->dev;
- int sent = 0, err = 0;
+ int sent = 0, drops = 0, err = 0;
+ unsigned int cnt = bq->count;
+ int to_send = cnt;
int i;
- if (unlikely(!bq->count))
+ if (unlikely(!cnt))
return;
- for (i = 0; i < bq->count; i++) {
+ for (i = 0; i < cnt; i++) {
struct xdp_frame *xdpf = bq->q[i];
prefetch(xdpf);
}
- sent = dev->netdev_ops->ndo_xdp_xmit(dev, bq->count, bq->q, flags);
+ if (bq->xdp_prog) {
+ to_send = dev_map_bpf_prog_run(bq->xdp_prog, bq->q, cnt, dev);
+ if (!to_send)
+ goto out;
+
+ drops = cnt - to_send;
+ }
+
+ sent = dev->netdev_ops->ndo_xdp_xmit(dev, to_send, bq->q, flags);
if (sent < 0) {
/* If ndo_xdp_xmit fails with an errno, no frames have
* been xmit'ed.
@@ -353,13 +403,13 @@ static void bq_xmit_all(struct xdp_dev_bulk_queue *bq, u32 flags)
/* If not all frames have been transmitted, it is our
* responsibility to free them
*/
- for (i = sent; unlikely(i < bq->count); i++)
+ for (i = sent; unlikely(i < to_send); i++)
xdp_return_frame_rx_napi(bq->q[i]);
- trace_xdp_devmap_xmit(bq->dev_rx, dev, sent, bq->count - sent, err);
- bq->dev_rx = NULL;
+out:
+ drops = cnt - sent;
bq->count = 0;
- __list_del_clearprev(&bq->flush_node);
+ trace_xdp_devmap_xmit(bq->dev_rx, dev, sent, drops, err);
}
/* __dev_flush is called from xdp_do_flush() which _must_ be signaled
@@ -377,8 +427,12 @@ void __dev_flush(void)
struct list_head *flush_list = this_cpu_ptr(&dev_flush_list);
struct xdp_dev_bulk_queue *bq, *tmp;
- list_for_each_entry_safe(bq, tmp, flush_list, flush_node)
+ list_for_each_entry_safe(bq, tmp, flush_list, flush_node) {
bq_xmit_all(bq, XDP_XMIT_FLUSH);
+ bq->dev_rx = NULL;
+ bq->xdp_prog = NULL;
+ __list_del_clearprev(&bq->flush_node);
+ }
}
/* rcu_read_lock (from syscall and BPF contexts) ensures that if a delete and/or
@@ -401,7 +455,7 @@ static void *__dev_map_lookup_elem(struct bpf_map *map, u32 key)
* Thus, safe percpu variable access.
*/
static void bq_enqueue(struct net_device *dev, struct xdp_frame *xdpf,
- struct net_device *dev_rx)
+ struct net_device *dev_rx, struct bpf_prog *xdp_prog)
{
struct list_head *flush_list = this_cpu_ptr(&dev_flush_list);
struct xdp_dev_bulk_queue *bq = this_cpu_ptr(dev->xdp_bulkq);
@@ -412,18 +466,22 @@ static void bq_enqueue(struct net_device *dev, struct xdp_frame *xdpf,
/* Ingress dev_rx will be the same for all xdp_frame's in
* bulk_queue, because bq stored per-CPU and must be flushed
* from net_device drivers NAPI func end.
+ *
+ * Do the same with xdp_prog and flush_list since these fields
+ * are only ever modified together.
*/
- if (!bq->dev_rx)
+ if (!bq->dev_rx) {
bq->dev_rx = dev_rx;
+ bq->xdp_prog = xdp_prog;
+ list_add(&bq->flush_node, flush_list);
+ }
bq->q[bq->count++] = xdpf;
-
- if (!bq->flush_node.prev)
- list_add(&bq->flush_node, flush_list);
}
static inline int __xdp_enqueue(struct net_device *dev, struct xdp_buff *xdp,
- struct net_device *dev_rx)
+ struct net_device *dev_rx,
+ struct bpf_prog *xdp_prog)
{
struct xdp_frame *xdpf;
int err;
@@ -439,42 +497,14 @@ static inline int __xdp_enqueue(struct net_device *dev, struct xdp_buff *xdp,
if (unlikely(!xdpf))
return -EOVERFLOW;
- bq_enqueue(dev, xdpf, dev_rx);
+ bq_enqueue(dev, xdpf, dev_rx, xdp_prog);
return 0;
}
-static struct xdp_buff *dev_map_run_prog(struct net_device *dev,
- struct xdp_buff *xdp,
- struct bpf_prog *xdp_prog)
-{
- struct xdp_txq_info txq = { .dev = dev };
- u32 act;
-
- xdp_set_data_meta_invalid(xdp);
- xdp->txq = &txq;
-
- act = bpf_prog_run_xdp(xdp_prog, xdp);
- switch (act) {
- case XDP_PASS:
- return xdp;
- case XDP_DROP:
- break;
- default:
- bpf_warn_invalid_xdp_action(act);
- fallthrough;
- case XDP_ABORTED:
- trace_xdp_exception(dev, xdp_prog, act);
- break;
- }
-
- xdp_return_buff(xdp);
- return NULL;
-}
-
int dev_xdp_enqueue(struct net_device *dev, struct xdp_buff *xdp,
struct net_device *dev_rx)
{
- return __xdp_enqueue(dev, xdp, dev_rx);
+ return __xdp_enqueue(dev, xdp, dev_rx, NULL);
}
int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp,
@@ -482,12 +512,7 @@ int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp,
{
struct net_device *dev = dst->dev;
- if (dst->xdp_prog) {
- xdp = dev_map_run_prog(dev, xdp, dst->xdp_prog);
- if (!xdp)
- return 0;
- }
- return __xdp_enqueue(dev, xdp, dev_rx);
+ return __xdp_enqueue(dev, xdp, dev_rx, dst->xdp_prog);
}
int dev_map_generic_redirect(struct bpf_dtab_netdev *dst, struct sk_buff *skb,
--
2.26.3
^ permalink raw reply related [flat|nested] 15+ messages in thread* [PATCHv4 bpf-next 2/4] xdp: extend xdp_redirect_map with broadcast support
2021-04-02 12:19 [PATCHv4 bpf-next 0/4] xdp: extend xdp_redirect_map with broadcast support Hangbin Liu
2021-04-02 12:19 ` [PATCHv4 bpf-next 1/4] bpf: run devmap xdp_prog on flush instead of bulk enqueue Hangbin Liu
@ 2021-04-02 12:19 ` Hangbin Liu
2021-04-06 0:24 ` John Fastabend
2021-04-06 11:17 ` Toke Høiland-Jørgensen
2021-04-02 12:19 ` [PATCHv4 bpf-next 3/4] sample/bpf: add xdp_redirect_map_multi for redirect_map broadcast test Hangbin Liu
2021-04-02 12:19 ` [PATCHv4 bpf-next 4/4] selftests/bpf: add xdp_redirect_multi test Hangbin Liu
3 siblings, 2 replies; 15+ messages in thread
From: Hangbin Liu @ 2021-04-02 12:19 UTC (permalink / raw)
To: bpf
Cc: netdev, Toke Høiland-Jørgensen, Jiri Benc,
Jesper Dangaard Brouer, Eelco Chaudron, ast, Daniel Borkmann,
Lorenzo Bianconi, David Ahern, Andrii Nakryiko,
Alexei Starovoitov, John Fastabend, Maciej Fijalkowski,
Björn Töpel, Hangbin Liu
This patch add two flags BPF_F_BROADCAST and BPF_F_EXCLUDE_INGRESS to extend
xdp_redirect_map for broadcast support.
Keep the general data path in net/core/filter.c and the native data
path in kernel/bpf/devmap.c so we can use direct calls to get better
performace.
Here is the performance result by using xdp_redirect_{map, map_multi} in
sample/bpf and send pkts via pktgen cmd:
./pktgen_sample03_burst_single_flow.sh -i eno1 -d $dst_ip -m $dst_mac -t 10 -s 64
There are some drop back as we need to loop the map and get each interface.
Version | Test | Generic | Native
5.12 rc2 | redirect_map i40e->i40e | 2.0M | 9.8M
5.12 rc2 | redirect_map i40e->veth | 1.8M | 12.0M
5.12 rc2 + patch | redirect_map i40e->i40e | 2.0M | 9.6M
5.12 rc2 + patch | redirect_map i40e->veth | 1.7M | 12.0M
5.12 rc2 + patch | redirect_map multi i40e->i40e | 1.6M | 7.8M
5.12 rc2 + patch | redirect_map multi i40e->veth | 1.4M | 9.3M
5.12 rc2 + patch | redirect_map multi i40e->mlx4+veth | 1.0M | 3.4M
Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
---
v4:
a) add a new argument flag_mask to __bpf_xdp_redirect_map() filter out
invalid map.
b) __bpf_xdp_redirect_map() sets the map pointer if the broadcast flag
is set and clears it if the flag isn't set
c) xdp_do_redirect() does the READ_ONCE/WRITE_ONCE on ri->map to check
if we should enqueue multi
v3:
a) Rebase the code on Björn's "bpf, xdp: Restructure redirect actions".
- Add struct bpf_map *map back to struct bpf_redirect_info as we need
it for multicast.
- Add bpf_clear_redirect_map() back for devmap.c
- Add devmap_lookup_elem() as we need it in general path.
b) remove tmp_key in devmap_get_next_obj()
v2: Fix flag renaming issue in v1
---
include/linux/bpf.h | 22 ++++++
include/linux/filter.h | 18 ++++-
include/net/xdp.h | 1 +
include/uapi/linux/bpf.h | 17 ++++-
kernel/bpf/cpumap.c | 3 +-
kernel/bpf/devmap.c | 133 ++++++++++++++++++++++++++++++++-
net/core/filter.c | 97 +++++++++++++++++++++++-
net/core/xdp.c | 29 +++++++
net/xdp/xskmap.c | 3 +-
tools/include/uapi/linux/bpf.h | 17 ++++-
10 files changed, 326 insertions(+), 14 deletions(-)
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 9fdd839b418c..d5745c6000bc 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -1492,11 +1492,15 @@ struct sk_buff;
struct bpf_dtab_netdev;
struct bpf_cpu_map_entry;
+struct bpf_dtab_netdev *devmap_lookup_elem(struct bpf_map *map, u32 key);
void __dev_flush(void);
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);
+bool dst_dev_is_ingress(struct bpf_dtab_netdev *obj, int ifindex);
+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);
bool dev_map_can_have_prog(struct bpf_map *map);
@@ -1639,6 +1643,11 @@ static inline int bpf_obj_get_user(const char __user *pathname, int flags)
return -EOPNOTSUPP;
}
+static inline struct net_device *devmap_lookup_elem(struct bpf_map *map, u32 key)
+{
+ return NULL;
+}
+
static inline bool dev_map_can_have_prog(struct bpf_map *map)
{
return false;
@@ -1666,6 +1675,19 @@ int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp,
return 0;
}
+static inline
+bool dst_dev_is_ingress(struct bpf_dtab_netdev *obj, int ifindex)
+{
+ return false;
+}
+
+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,
diff --git a/include/linux/filter.h b/include/linux/filter.h
index 9a09547bc7ba..e4885b42d754 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 +1465,18 @@ 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, u64 flag_mask,
void *lookup_elem(struct bpf_map *map, u32 key))
{
struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info);
/* Lower bits of the flags are used as return code on lookup failure */
- if (unlikely(flags > XDP_TX))
+ if (unlikely(flags & ~(BPF_F_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 +1484,21 @@ 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 & BPF_F_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/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 49371eba98ba..fe2c35bcc880 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -2513,8 +2513,12 @@ 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.
@@ -5015,6 +5019,15 @@ 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_F_ACTION_MASK (XDP_ABORTED | XDP_DROP | XDP_PASS | XDP_TX)
+#define BPF_F_REDIR_MASK (BPF_F_BROADCAST | BPF_F_EXCLUDE_INGRESS)
+
#define __bpf_md_ptr(type, name) \
union { \
type name; \
diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c
index 0cf2791d5099..2c33a7a09783 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 3980fb3bfb09..c8452c5f40f8 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. */
@@ -451,6 +452,24 @@ static void *__dev_map_lookup_elem(struct bpf_map *map, u32 key)
return obj;
}
+struct bpf_dtab_netdev *devmap_lookup_elem(struct bpf_map *map, u32 key)
+{
+ struct bpf_dtab_netdev *obj = NULL;
+
+ switch (map->map_type) {
+ case BPF_MAP_TYPE_DEVMAP:
+ obj = __dev_map_lookup_elem(map, key);
+ break;
+ case BPF_MAP_TYPE_DEVMAP_HASH:
+ obj = __dev_map_hash_lookup_elem(map, key);
+ break;
+ default:
+ break;
+ }
+
+ return obj;
+}
+
/* Runs under RCU-read-side, plus in softirq under NAPI protection.
* Thus, safe percpu variable access.
*/
@@ -515,6 +534,114 @@ int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp,
return __xdp_enqueue(dev, xdp, dev_rx, dst->xdp_prog);
}
+/* Use direct call in fast path instead of map->ops->map_get_next_key() */
+static int devmap_get_next_key(struct bpf_map *map, void *key, void *next_key)
+{
+ switch (map->map_type) {
+ case BPF_MAP_TYPE_DEVMAP:
+ return dev_map_get_next_key(map, key, next_key);
+ case BPF_MAP_TYPE_DEVMAP_HASH:
+ return dev_map_hash_get_next_key(map, key, next_key);
+ default:
+ break;
+ }
+
+ return -ENOENT;
+}
+
+bool dst_dev_is_ingress(struct bpf_dtab_netdev *dst, int ifindex)
+{
+ return dst->dev->ifindex == ifindex;
+}
+
+static struct bpf_dtab_netdev *devmap_get_next_obj(struct xdp_buff *xdp,
+ struct bpf_map *map,
+ u32 *key, u32 *next_key,
+ int ex_ifindex)
+{
+ struct bpf_dtab_netdev *obj;
+ struct net_device *dev;
+ u32 index;
+ int err;
+
+ err = devmap_get_next_key(map, key, next_key);
+ if (err)
+ return NULL;
+
+ /* When using dev map hash, we could restart the hashtab traversal
+ * in case the key has been updated/removed in the mean time.
+ * So we may end up potentially looping due to traversal restarts
+ * from first elem.
+ *
+ * Let's use map's max_entries to limit the loop number.
+ */
+ for (index = 0; index < map->max_entries; index++) {
+ obj = devmap_lookup_elem(map, *next_key);
+ if (!obj || dst_dev_is_ingress(obj, ex_ifindex))
+ goto find_next;
+
+ dev = obj->dev;
+
+ if (!dev->netdev_ops->ndo_xdp_xmit)
+ goto find_next;
+
+ err = xdp_ok_fwd_dev(dev, xdp->data_end - xdp->data);
+ if (unlikely(err))
+ goto find_next;
+
+ return obj;
+
+find_next:
+ key = next_key;
+ err = devmap_get_next_key(map, key, next_key);
+ if (err)
+ break;
+ }
+
+ return NULL;
+}
+
+int dev_map_enqueue_multi(struct xdp_buff *xdp, struct net_device *dev_rx,
+ struct bpf_map *map, bool exclude_ingress)
+{
+ struct bpf_dtab_netdev *obj = NULL, *next_obj = NULL;
+ struct xdp_frame *xdpf, *nxdpf;
+ u32 key, next_key;
+ int ex_ifindex;
+
+ ex_ifindex = exclude_ingress ? dev_rx->ifindex : 0;
+
+ /* Find first available obj */
+ obj = devmap_get_next_obj(xdp, map, NULL, &key, ex_ifindex);
+ if (!obj)
+ return -ENOENT;
+
+ xdpf = xdp_convert_buff_to_frame(xdp);
+ if (unlikely(!xdpf))
+ return -EOVERFLOW;
+
+ for (;;) {
+ /* Check if we still have one more available obj */
+ next_obj = devmap_get_next_obj(xdp, map, &key, &next_key, ex_ifindex);
+ if (!next_obj) {
+ bq_enqueue(obj->dev, xdpf, dev_rx, obj->xdp_prog);
+ return 0;
+ }
+
+ nxdpf = xdpf_clone(xdpf);
+ if (unlikely(!nxdpf)) {
+ xdp_return_frame_rx_napi(xdpf);
+ return -ENOMEM;
+ }
+
+ bq_enqueue(obj->dev, nxdpf, dev_rx, obj->xdp_prog);
+
+ /* Deal with next obj */
+ obj = next_obj;
+ key = next_key;
+ }
+}
+
int dev_map_generic_redirect(struct bpf_dtab_netdev *dst, struct sk_buff *skb,
struct bpf_prog *xdp_prog)
{
@@ -755,12 +882,14 @@ 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_REDIR_MASK,
+ __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_REDIR_MASK,
+ __dev_map_hash_lookup_elem);
}
static int dev_map_btf_id;
diff --git a/net/core/filter.c b/net/core/filter.c
index cae56d08a670..08a4d3869056 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -3926,6 +3926,23 @@ 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)
{
@@ -3933,16 +3950,28 @@ 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;
+ bool exclude_ingress;
+ struct bpf_map *map;
int err;
ri->map_id = 0; /* Valid map id idr range: [1,INT_MAX[ */
ri->map_type = BPF_MAP_TYPE_UNSPEC;
+ map = READ_ONCE(ri->map);
+ if (map) {
+ WRITE_ONCE(ri->map, NULL);
+ exclude_ingress = ri->flags & BPF_F_EXCLUDE_INGRESS;
+ ri->flags = 0;
+ }
+
switch (map_type) {
case BPF_MAP_TYPE_DEVMAP:
fallthrough;
case BPF_MAP_TYPE_DEVMAP_HASH:
- err = dev_map_enqueue(fwd, xdp, dev);
+ if (map)
+ err = dev_map_enqueue_multi(xdp, dev, map, exclude_ingress);
+ else
+ err = dev_map_enqueue(fwd, xdp, dev);
break;
case BPF_MAP_TYPE_CPUMAP:
err = cpu_map_enqueue(fwd, xdp, dev);
@@ -3976,6 +4005,57 @@ int xdp_do_redirect(struct net_device *dev, struct xdp_buff *xdp,
}
EXPORT_SYMBOL_GPL(xdp_do_redirect);
+static 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_netdev *dst;
+ u32 key, next_key, index;
+ struct sk_buff *nskb;
+ void *fwd;
+ int err;
+
+ err = map->ops->map_get_next_key(map, NULL, &key);
+ if (err)
+ return err;
+
+ /* When using dev map hash, we could restart the hashtab traversal
+ * in case the key has been updated/removed in the mean time.
+ * So we may end up potentially looping due to traversal restarts
+ * from first elem.
+ *
+ * Let's use map's max_entries to limit the loop number.
+ */
+
+ for (index = 0; index < map->max_entries; index++) {
+ fwd = devmap_lookup_elem(map, key);
+ if (fwd) {
+ dst = (struct bpf_dtab_netdev *)fwd;
+ if (dst_dev_is_ingress(dst, exclude_ingress ? dev->ifindex : 0))
+ goto find_next;
+
+ nskb = skb_clone(skb, GFP_ATOMIC);
+ if (!nskb)
+ return -ENOMEM;
+
+ /* Try forword next one no mater the current forward
+ * succeed or not.
+ */
+ dev_map_generic_redirect(dst, nskb, xdp_prog);
+ }
+
+find_next:
+ err = map->ops->map_get_next_key(map, &key, &next_key);
+ if (err)
+ break;
+
+ key = next_key;
+ }
+
+ consume_skb(skb);
+ return 0;
+}
+
static int xdp_do_generic_redirect_map(struct net_device *dev,
struct sk_buff *skb,
struct xdp_buff *xdp,
@@ -3984,13 +4064,26 @@ 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);
+ bool exclude_ingress;
+ struct bpf_map *map;
int err;
+ map = READ_ONCE(ri->map);
+ if (map) {
+ WRITE_ONCE(ri->map, NULL);
+ exclude_ingress = ri->flags & BPF_F_EXCLUDE_INGRESS;
+ ri->flags = 0;
+ }
+
switch (map_type) {
case BPF_MAP_TYPE_DEVMAP:
fallthrough;
case BPF_MAP_TYPE_DEVMAP_HASH:
- err = dev_map_generic_redirect(fwd, skb, xdp_prog);
+ if (map)
+ err = dev_map_redirect_multi(dev, skb, xdp_prog, map,
+ 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 05354976c1fc..aba84d04642b 100644
--- a/net/core/xdp.c
+++ b/net/core/xdp.c
@@ -583,3 +583,32 @@ 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;
+}
+EXPORT_SYMBOL_GPL(xdpf_clone);
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 69902603012c..46e42a783f4e 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -2513,8 +2513,12 @@ 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.
@@ -5009,6 +5013,15 @@ 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_F_ACTION_MASK (XDP_ABORTED | XDP_DROP | XDP_PASS | XDP_TX)
+#define BPF_F_REDIR_MASK (BPF_F_BROADCAST | BPF_F_EXCLUDE_INGRESS)
+
#define __bpf_md_ptr(type, name) \
union { \
type name; \
--
2.26.3
^ permalink raw reply related [flat|nested] 15+ messages in thread* RE: [PATCHv4 bpf-next 2/4] xdp: extend xdp_redirect_map with broadcast support
2021-04-02 12:19 ` [PATCHv4 bpf-next 2/4] xdp: extend xdp_redirect_map with broadcast support Hangbin Liu
@ 2021-04-06 0:24 ` John Fastabend
2021-04-06 6:38 ` Hangbin Liu
2021-04-06 11:17 ` Toke Høiland-Jørgensen
1 sibling, 1 reply; 15+ messages in thread
From: John Fastabend @ 2021-04-06 0:24 UTC (permalink / raw)
To: Hangbin Liu, bpf
Cc: netdev, Toke Høiland-Jørgensen, Jiri Benc,
Jesper Dangaard Brouer, Eelco Chaudron, ast, Daniel Borkmann,
Lorenzo Bianconi, David Ahern, Andrii Nakryiko,
Alexei Starovoitov, John Fastabend, Maciej Fijalkowski,
Björn Töpel, Hangbin Liu
Hangbin Liu wrote:
> This patch add two flags BPF_F_BROADCAST and BPF_F_EXCLUDE_INGRESS to extend
> xdp_redirect_map for broadcast support.
>
> Keep the general data path in net/core/filter.c and the native data
> path in kernel/bpf/devmap.c so we can use direct calls to get better
> performace.
>
> Here is the performance result by using xdp_redirect_{map, map_multi} in
> sample/bpf and send pkts via pktgen cmd:
> ./pktgen_sample03_burst_single_flow.sh -i eno1 -d $dst_ip -m $dst_mac -t 10 -s 64
>
> There are some drop back as we need to loop the map and get each interface.
>
> Version | Test | Generic | Native
> 5.12 rc2 | redirect_map i40e->i40e | 2.0M | 9.8M
> 5.12 rc2 | redirect_map i40e->veth | 1.8M | 12.0M
Are these are 10gbps i40e ports? Sorry if I asked this earlier, maybe
add a note in the commit if another respin is needed.
> 5.12 rc2 + patch | redirect_map i40e->i40e | 2.0M | 9.6M
> 5.12 rc2 + patch | redirect_map i40e->veth | 1.7M | 12.0M
> 5.12 rc2 + patch | redirect_map multi i40e->i40e | 1.6M | 7.8M
> 5.12 rc2 + patch | redirect_map multi i40e->veth | 1.4M | 9.3M
> 5.12 rc2 + patch | redirect_map multi i40e->mlx4+veth | 1.0M | 3.4M
>
> Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
>
> ---
> v4:
> a) add a new argument flag_mask to __bpf_xdp_redirect_map() filter out
> invalid map.
> b) __bpf_xdp_redirect_map() sets the map pointer if the broadcast flag
> is set and clears it if the flag isn't set
> c) xdp_do_redirect() does the READ_ONCE/WRITE_ONCE on ri->map to check
> if we should enqueue multi
>
> v3:
> a) Rebase the code on Björn's "bpf, xdp: Restructure redirect actions".
> - Add struct bpf_map *map back to struct bpf_redirect_info as we need
> it for multicast.
> - Add bpf_clear_redirect_map() back for devmap.c
> - Add devmap_lookup_elem() as we need it in general path.
> b) remove tmp_key in devmap_get_next_obj()
>
> v2: Fix flag renaming issue in v1
> ---
> include/linux/bpf.h | 22 ++++++
> include/linux/filter.h | 18 ++++-
> include/net/xdp.h | 1 +
> include/uapi/linux/bpf.h | 17 ++++-
> kernel/bpf/cpumap.c | 3 +-
> kernel/bpf/devmap.c | 133 ++++++++++++++++++++++++++++++++-
> net/core/filter.c | 97 +++++++++++++++++++++++-
> net/core/xdp.c | 29 +++++++
> net/xdp/xskmap.c | 3 +-
> tools/include/uapi/linux/bpf.h | 17 ++++-
> 10 files changed, 326 insertions(+), 14 deletions(-)
>
[...]
> static int cpu_map_btf_id;
> diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c
> index 3980fb3bfb09..c8452c5f40f8 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);
Is this a bugfix? If its needed here wouldn't we also need it in the
devmap case.
> synchronize_rcu();
>
> /* Make sure prior __dev_map_entry_free() have completed. */
[...]
> +
> +static struct bpf_dtab_netdev *devmap_get_next_obj(struct xdp_buff *xdp,
> + struct bpf_map *map,
> + u32 *key, u32 *next_key,
> + int ex_ifindex)
> +{
> + struct bpf_dtab_netdev *obj;
> + struct net_device *dev;
> + u32 index;
> + int err;
> +
> + err = devmap_get_next_key(map, key, next_key);
> + if (err)
> + return NULL;
> +
> + /* When using dev map hash, we could restart the hashtab traversal
> + * in case the key has been updated/removed in the mean time.
> + * So we may end up potentially looping due to traversal restarts
> + * from first elem.
> + *
> + * Let's use map's max_entries to limit the loop number.
> + */
> + for (index = 0; index < map->max_entries; index++) {
> + obj = devmap_lookup_elem(map, *next_key);
> + if (!obj || dst_dev_is_ingress(obj, ex_ifindex))
> + goto find_next;
> +
> + dev = obj->dev;
> +
> + if (!dev->netdev_ops->ndo_xdp_xmit)
> + goto find_next;
> +
> + err = xdp_ok_fwd_dev(dev, xdp->data_end - xdp->data);
> + if (unlikely(err))
> + goto find_next;
> +
> + return obj;
> +
> +find_next:
> + key = next_key;
> + err = devmap_get_next_key(map, key, next_key);
> + if (err)
> + break;
> + }
I'm missing something. Either an elaborated commit message or comment
is probably needed. I've been looking at this block for 30 minutes and
can't see how we avoid sending duplicate frames on a single interface?
Can you check this code flow,
dev_map_enqueue_multi()
for (;;) {
next_obj = devmap_get_next_obj(...)
for (index = 0; index < map->max_entries; index++) {
obj = devmap_lookup_elem();
if (!obj) goto find_next
key = next_key;
err = devmap_get_next_key()
if (!key) goto find_first
for (i = 0; i < dtab->n_buckets; i++)
return *next <- now *next_key is point back
at first entry
// loop back through and find first obj and return that
}
bq_enqueue(...) // enqueue original obj
obj = next_obj;
key = next_key;
... // we are going to enqueue first obj, but how do we know
// this hasn't already been sent? Presumably if we have
// a delete in the hash table in the middle of a multicast
// operation this might happen?
}
> +
> + return NULL;
> +}
> +
> +int dev_map_enqueue_multi(struct xdp_buff *xdp, struct net_device *dev_rx,
> + struct bpf_map *map, bool exclude_ingress)
> +{
> + struct bpf_dtab_netdev *obj = NULL, *next_obj = NULL;
> + struct xdp_frame *xdpf, *nxdpf;
> + u32 key, next_key;
> + int ex_ifindex;
> +
> + ex_ifindex = exclude_ingress ? dev_rx->ifindex : 0;
> +
> + /* Find first available obj */
> + obj = devmap_get_next_obj(xdp, map, NULL, &key, ex_ifindex);
> + if (!obj)
> + return -ENOENT;
> +
> + xdpf = xdp_convert_buff_to_frame(xdp);
> + if (unlikely(!xdpf))
> + return -EOVERFLOW;
> +
> + for (;;) {
A nit take it or not. These for (;;) loops always seem a bit odd to me
when we really don't want it to run forever. I prefer
while (!next_obj)
but a matter of style I guess.
> + /* Check if we still have one more available obj */
> + next_obj = devmap_get_next_obj(xdp, map, &key, &next_key, ex_ifindex);
> + if (!next_obj) {
> + bq_enqueue(obj->dev, xdpf, dev_rx, obj->xdp_prog);
> + return 0;
> + }
> +
> + nxdpf = xdpf_clone(xdpf);
> + if (unlikely(!nxdpf)) {
> + xdp_return_frame_rx_napi(xdpf);
> + return -ENOMEM;
> + }
> +
> + bq_enqueue(obj->dev, nxdpf, dev_rx, obj->xdp_prog);
> +
> + /* Deal with next obj */
> + obj = next_obj;
> + key = next_key;
> + }
> +}
> +
Thanks,
John
^ permalink raw reply [flat|nested] 15+ messages in thread* Re: [PATCHv4 bpf-next 2/4] xdp: extend xdp_redirect_map with broadcast support
2021-04-06 0:24 ` John Fastabend
@ 2021-04-06 6:38 ` Hangbin Liu
2021-04-06 10:19 ` Toke Høiland-Jørgensen
0 siblings, 1 reply; 15+ messages in thread
From: Hangbin Liu @ 2021-04-06 6:38 UTC (permalink / raw)
To: John Fastabend
Cc: bpf, netdev, Toke Høiland-Jørgensen, Jiri Benc,
Jesper Dangaard Brouer, Eelco Chaudron, ast, Daniel Borkmann,
Lorenzo Bianconi, David Ahern, Andrii Nakryiko,
Alexei Starovoitov, Maciej Fijalkowski, Björn Töpel
On Mon, Apr 05, 2021 at 05:24:48PM -0700, John Fastabend wrote:
> Hangbin Liu wrote:
> > This patch add two flags BPF_F_BROADCAST and BPF_F_EXCLUDE_INGRESS to extend
> > xdp_redirect_map for broadcast support.
> >
> > Keep the general data path in net/core/filter.c and the native data
> > path in kernel/bpf/devmap.c so we can use direct calls to get better
> > performace.
> >
> > Here is the performance result by using xdp_redirect_{map, map_multi} in
> > sample/bpf and send pkts via pktgen cmd:
> > ./pktgen_sample03_burst_single_flow.sh -i eno1 -d $dst_ip -m $dst_mac -t 10 -s 64
> >
> > There are some drop back as we need to loop the map and get each interface.
> >
> > Version | Test | Generic | Native
> > 5.12 rc2 | redirect_map i40e->i40e | 2.0M | 9.8M
> > 5.12 rc2 | redirect_map i40e->veth | 1.8M | 12.0M
>
> Are these are 10gbps i40e ports? Sorry if I asked this earlier, maybe
> add a note in the commit if another respin is needed.
Yes, I will add it if there is an update.
> > diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c
> > index 3980fb3bfb09..c8452c5f40f8 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);
>
> Is this a bugfix? If its needed here wouldn't we also need it in the
> devmap case.
No, in ee75aef23afe ("bpf, xdp: Restructure redirect actions") this function
was removed. I added it back as we use ri->map again.
What devmap case you mean?
>
> > synchronize_rcu();
> >
> > /* Make sure prior __dev_map_entry_free() have completed. */
>
> [...]
>
> > +
> > +static struct bpf_dtab_netdev *devmap_get_next_obj(struct xdp_buff *xdp,
> > + struct bpf_map *map,
> > + u32 *key, u32 *next_key,
> > + int ex_ifindex)
> > +{
> > + struct bpf_dtab_netdev *obj;
> > + struct net_device *dev;
> > + u32 index;
> > + int err;
> > +
> > + err = devmap_get_next_key(map, key, next_key);
> > + if (err)
> > + return NULL;
> > +
> > + /* When using dev map hash, we could restart the hashtab traversal
> > + * in case the key has been updated/removed in the mean time.
> > + * So we may end up potentially looping due to traversal restarts
> > + * from first elem.
> > + *
> > + * Let's use map's max_entries to limit the loop number.
> > + */
> > + for (index = 0; index < map->max_entries; index++) {
> > + obj = devmap_lookup_elem(map, *next_key);
> > + if (!obj || dst_dev_is_ingress(obj, ex_ifindex))
> > + goto find_next;
> > +
> > + dev = obj->dev;
> > +
> > + if (!dev->netdev_ops->ndo_xdp_xmit)
> > + goto find_next;
> > +
> > + err = xdp_ok_fwd_dev(dev, xdp->data_end - xdp->data);
> > + if (unlikely(err))
> > + goto find_next;
> > +
> > + return obj;
> > +
> > +find_next:
> > + key = next_key;
> > + err = devmap_get_next_key(map, key, next_key);
> > + if (err)
> > + break;
> > + }
>
> I'm missing something. Either an elaborated commit message or comment
> is probably needed. I've been looking at this block for 30 minutes and
> can't see how we avoid sending duplicate frames on a single interface?
> Can you check this code flow,
>
> dev_map_enqueue_multi()
> for (;;) {
> next_obj = devmap_get_next_obj(...)
> for (index = 0; index < map->max_entries; index++) {
> obj = devmap_lookup_elem();
> if (!obj) goto find_next
> key = next_key;
> err = devmap_get_next_key()
> if (!key) goto find_first
> for (i = 0; i < dtab->n_buckets; i++)
> return *next <- now *next_key is point back
> at first entry
> // loop back through and find first obj and return that
devmap_get_next_key() will loop to find the first one if there is no
key or dev. In normal time it will stop after the latest one.
> }
> bq_enqueue(...) // enqueue original obj
> obj = next_obj;
> key = next_key;
> ... // we are going to enqueue first obj, but how do we know
> // this hasn't already been sent? Presumably if we have
> // a delete in the hash table in the middle of a multicast
> // operation this might happen?
> }
And yes, there is an corner case that if we removed a dev during multicast,
there is an possibility that restart from the first key. But given that
this is an unlikely case, and in normal internet there is also a possibility
of duplicate/lost packet. This should also be acceptable?
For the loop limit, Daniel suggested to add it:
https://lore.kernel.org/bpf/609c2fdf-09b7-b86e-26c0-ad386770ac33@iogearbox.net/
> > +
> > + return NULL;
> > +}
> > +
> > +int dev_map_enqueue_multi(struct xdp_buff *xdp, struct net_device *dev_rx,
> > + struct bpf_map *map, bool exclude_ingress)
> > +{
> > + struct bpf_dtab_netdev *obj = NULL, *next_obj = NULL;
> > + struct xdp_frame *xdpf, *nxdpf;
> > + u32 key, next_key;
> > + int ex_ifindex;
> > +
> > + ex_ifindex = exclude_ingress ? dev_rx->ifindex : 0;
> > +
> > + /* Find first available obj */
> > + obj = devmap_get_next_obj(xdp, map, NULL, &key, ex_ifindex);
> > + if (!obj)
> > + return -ENOENT;
> > +
> > + xdpf = xdp_convert_buff_to_frame(xdp);
> > + if (unlikely(!xdpf))
> > + return -EOVERFLOW;
> > +
> > + for (;;) {
>
> A nit take it or not. These for (;;) loops always seem a bit odd to me
> when we really don't want it to run forever. I prefer
>
> while (!next_obj)
>
> but a matter of style I guess.
OK, I will do it if there is an respin.
Thank
Hangbin
^ permalink raw reply [flat|nested] 15+ messages in thread* Re: [PATCHv4 bpf-next 2/4] xdp: extend xdp_redirect_map with broadcast support
2021-04-06 6:38 ` Hangbin Liu
@ 2021-04-06 10:19 ` Toke Høiland-Jørgensen
2021-04-06 21:49 ` John Fastabend
0 siblings, 1 reply; 15+ messages in thread
From: Toke Høiland-Jørgensen @ 2021-04-06 10:19 UTC (permalink / raw)
To: Hangbin Liu, John Fastabend
Cc: bpf, netdev, Jiri Benc, Jesper Dangaard Brouer, Eelco Chaudron,
ast, Daniel Borkmann, Lorenzo Bianconi, David Ahern,
Andrii Nakryiko, Alexei Starovoitov, Maciej Fijalkowski,
Björn Töpel
Hangbin Liu <liuhangbin@gmail.com> writes:
> On Mon, Apr 05, 2021 at 05:24:48PM -0700, John Fastabend wrote:
>> Hangbin Liu wrote:
>> > This patch add two flags BPF_F_BROADCAST and BPF_F_EXCLUDE_INGRESS to extend
>> > xdp_redirect_map for broadcast support.
>> >
>> > Keep the general data path in net/core/filter.c and the native data
>> > path in kernel/bpf/devmap.c so we can use direct calls to get better
>> > performace.
>> >
>> > Here is the performance result by using xdp_redirect_{map, map_multi} in
>> > sample/bpf and send pkts via pktgen cmd:
>> > ./pktgen_sample03_burst_single_flow.sh -i eno1 -d $dst_ip -m $dst_mac -t 10 -s 64
>> >
>> > There are some drop back as we need to loop the map and get each interface.
>> >
>> > Version | Test | Generic | Native
>> > 5.12 rc2 | redirect_map i40e->i40e | 2.0M | 9.8M
>> > 5.12 rc2 | redirect_map i40e->veth | 1.8M | 12.0M
>>
>> Are these are 10gbps i40e ports? Sorry if I asked this earlier, maybe
>> add a note in the commit if another respin is needed.
>
> Yes, I will add it if there is an update.
>
>> > diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c
>> > index 3980fb3bfb09..c8452c5f40f8 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);
>>
>> Is this a bugfix? If its needed here wouldn't we also need it in the
>> devmap case.
>
> No, in ee75aef23afe ("bpf, xdp: Restructure redirect actions") this function
> was removed. I added it back as we use ri->map again.
>
> What devmap case you mean?
>
>>
>> > synchronize_rcu();
>> >
>> > /* Make sure prior __dev_map_entry_free() have completed. */
>>
>> [...]
>>
>> > +
>> > +static struct bpf_dtab_netdev *devmap_get_next_obj(struct xdp_buff *xdp,
>> > + struct bpf_map *map,
>> > + u32 *key, u32 *next_key,
>> > + int ex_ifindex)
>> > +{
>> > + struct bpf_dtab_netdev *obj;
>> > + struct net_device *dev;
>> > + u32 index;
>> > + int err;
>> > +
>> > + err = devmap_get_next_key(map, key, next_key);
>> > + if (err)
>> > + return NULL;
>> > +
>> > + /* When using dev map hash, we could restart the hashtab traversal
>> > + * in case the key has been updated/removed in the mean time.
>> > + * So we may end up potentially looping due to traversal restarts
>> > + * from first elem.
>> > + *
>> > + * Let's use map's max_entries to limit the loop number.
>> > + */
>> > + for (index = 0; index < map->max_entries; index++) {
>> > + obj = devmap_lookup_elem(map, *next_key);
>> > + if (!obj || dst_dev_is_ingress(obj, ex_ifindex))
>> > + goto find_next;
>> > +
>> > + dev = obj->dev;
>> > +
>> > + if (!dev->netdev_ops->ndo_xdp_xmit)
>> > + goto find_next;
>> > +
>> > + err = xdp_ok_fwd_dev(dev, xdp->data_end - xdp->data);
>> > + if (unlikely(err))
>> > + goto find_next;
>> > +
>> > + return obj;
>> > +
>> > +find_next:
>> > + key = next_key;
>> > + err = devmap_get_next_key(map, key, next_key);
>> > + if (err)
>> > + break;
>> > + }
>>
>> I'm missing something. Either an elaborated commit message or comment
>> is probably needed. I've been looking at this block for 30 minutes and
>> can't see how we avoid sending duplicate frames on a single interface?
>> Can you check this code flow,
>>
>> dev_map_enqueue_multi()
>> for (;;) {
>> next_obj = devmap_get_next_obj(...)
>> for (index = 0; index < map->max_entries; index++) {
>> obj = devmap_lookup_elem();
>> if (!obj) goto find_next
>> key = next_key;
>> err = devmap_get_next_key()
>> if (!key) goto find_first
>> for (i = 0; i < dtab->n_buckets; i++)
>> return *next <- now *next_key is point back
>> at first entry
>> // loop back through and find first obj and return that
>
> devmap_get_next_key() will loop to find the first one if there is no
> key or dev. In normal time it will stop after the latest one.
>> }
>> bq_enqueue(...) // enqueue original obj
>> obj = next_obj;
>> key = next_key;
>> ... // we are going to enqueue first obj, but how do we know
>> // this hasn't already been sent? Presumably if we have
>> // a delete in the hash table in the middle of a multicast
>> // operation this might happen?
>> }
>
> And yes, there is an corner case that if we removed a dev during multicast,
> there is an possibility that restart from the first key. But given that
> this is an unlikely case, and in normal internet there is also a possibility
> of duplicate/lost packet. This should also be acceptable?
In my mind this falls under "acceptable corner cases". I.e., if you're
going to use the map for redirect and you expect to be updating it while
you're doing so, don't use a hashmap. But if you will not be updating
the map (or find the possible duplication acceptable), you can use the
hashmap and gain the benefit of being able to index by ifindex.
But John does have a point that this is not obvious; so maybe it should
be pointed out in the helper documentation?
-Toke
^ permalink raw reply [flat|nested] 15+ messages in thread* Re: [PATCHv4 bpf-next 2/4] xdp: extend xdp_redirect_map with broadcast support
2021-04-06 10:19 ` Toke Høiland-Jørgensen
@ 2021-04-06 21:49 ` John Fastabend
2021-04-06 22:19 ` Toke Høiland-Jørgensen
0 siblings, 1 reply; 15+ messages in thread
From: John Fastabend @ 2021-04-06 21:49 UTC (permalink / raw)
To: Toke Høiland-Jørgensen, Hangbin Liu, John Fastabend
Cc: bpf, netdev, Jiri Benc, Jesper Dangaard Brouer, Eelco Chaudron,
ast, Daniel Borkmann, Lorenzo Bianconi, David Ahern,
Andrii Nakryiko, Alexei Starovoitov, Maciej Fijalkowski,
Björn Töpel
Toke Høiland-Jørgensen wrote:
> Hangbin Liu <liuhangbin@gmail.com> writes:
>
> > On Mon, Apr 05, 2021 at 05:24:48PM -0700, John Fastabend wrote:
> >> Hangbin Liu wrote:
> >> > This patch add two flags BPF_F_BROADCAST and BPF_F_EXCLUDE_INGRESS to extend
> >> > xdp_redirect_map for broadcast support.
> >> >
> >> > Keep the general data path in net/core/filter.c and the native data
> >> > path in kernel/bpf/devmap.c so we can use direct calls to get better
> >> > performace.
> >> >
> >> > Here is the performance result by using xdp_redirect_{map, map_multi} in
> >> > sample/bpf and send pkts via pktgen cmd:
> >> > ./pktgen_sample03_burst_single_flow.sh -i eno1 -d $dst_ip -m $dst_mac -t 10 -s 64
> >> >
> >> > There are some drop back as we need to loop the map and get each interface.
> >> >
> >> > Version | Test | Generic | Native
> >> > 5.12 rc2 | redirect_map i40e->i40e | 2.0M | 9.8M
> >> > 5.12 rc2 | redirect_map i40e->veth | 1.8M | 12.0M
> >>
> >> Are these are 10gbps i40e ports? Sorry if I asked this earlier, maybe
> >> add a note in the commit if another respin is needed.
> >
> > Yes, I will add it if there is an update.
> >
> >> > diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c
> >> > index 3980fb3bfb09..c8452c5f40f8 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);
> >>
> >> Is this a bugfix? If its needed here wouldn't we also need it in the
> >> devmap case.
> >
> > No, in ee75aef23afe ("bpf, xdp: Restructure redirect actions") this function
> > was removed. I added it back as we use ri->map again.
> >
> > What devmap case you mean?
> >
> >>
> >> > synchronize_rcu();
> >> >
> >> > /* Make sure prior __dev_map_entry_free() have completed. */
> >>
> >> [...]
> >>
> >> > +
> >> > +static struct bpf_dtab_netdev *devmap_get_next_obj(struct xdp_buff *xdp,
> >> > + struct bpf_map *map,
> >> > + u32 *key, u32 *next_key,
> >> > + int ex_ifindex)
> >> > +{
> >> > + struct bpf_dtab_netdev *obj;
> >> > + struct net_device *dev;
> >> > + u32 index;
> >> > + int err;
> >> > +
> >> > + err = devmap_get_next_key(map, key, next_key);
> >> > + if (err)
> >> > + return NULL;
> >> > +
> >> > + /* When using dev map hash, we could restart the hashtab traversal
> >> > + * in case the key has been updated/removed in the mean time.
> >> > + * So we may end up potentially looping due to traversal restarts
> >> > + * from first elem.
> >> > + *
> >> > + * Let's use map's max_entries to limit the loop number.
> >> > + */
> >> > + for (index = 0; index < map->max_entries; index++) {
> >> > + obj = devmap_lookup_elem(map, *next_key);
> >> > + if (!obj || dst_dev_is_ingress(obj, ex_ifindex))
> >> > + goto find_next;
> >> > +
> >> > + dev = obj->dev;
> >> > +
> >> > + if (!dev->netdev_ops->ndo_xdp_xmit)
> >> > + goto find_next;
> >> > +
> >> > + err = xdp_ok_fwd_dev(dev, xdp->data_end - xdp->data);
> >> > + if (unlikely(err))
> >> > + goto find_next;
> >> > +
> >> > + return obj;
> >> > +
> >> > +find_next:
> >> > + key = next_key;
> >> > + err = devmap_get_next_key(map, key, next_key);
> >> > + if (err)
> >> > + break;
> >> > + }
> >>
> >> I'm missing something. Either an elaborated commit message or comment
> >> is probably needed. I've been looking at this block for 30 minutes and
> >> can't see how we avoid sending duplicate frames on a single interface?
> >> Can you check this code flow,
> >>
> >> dev_map_enqueue_multi()
> >> for (;;) {
> >> next_obj = devmap_get_next_obj(...)
> >> for (index = 0; index < map->max_entries; index++) {
> >> obj = devmap_lookup_elem();
> >> if (!obj) goto find_next
> >> key = next_key;
> >> err = devmap_get_next_key()
> >> if (!key) goto find_first
> >> for (i = 0; i < dtab->n_buckets; i++)
> >> return *next <- now *next_key is point back
> >> at first entry
> >> // loop back through and find first obj and return that
> >
> > devmap_get_next_key() will loop to find the first one if there is no
> > key or dev. In normal time it will stop after the latest one.
> >> }
> >> bq_enqueue(...) // enqueue original obj
> >> obj = next_obj;
> >> key = next_key;
> >> ... // we are going to enqueue first obj, but how do we know
> >> // this hasn't already been sent? Presumably if we have
> >> // a delete in the hash table in the middle of a multicast
> >> // operation this might happen?
> >> }
> >
> > And yes, there is an corner case that if we removed a dev during multicast,
> > there is an possibility that restart from the first key. But given that
> > this is an unlikely case, and in normal internet there is also a possibility
> > of duplicate/lost packet. This should also be acceptable?
>
> In my mind this falls under "acceptable corner cases". I.e., if you're
> going to use the map for redirect and you expect to be updating it while
> you're doing so, don't use a hashmap. But if you will not be updating
> the map (or find the possible duplication acceptable), you can use the
> hashmap and gain the benefit of being able to index by ifindex.
In a Kubernetes setup its going to be hard, if possible at all, to restrict
the map from moving as interfaces/IPs are going to be dynamic. Using a
hash map has nice benefits of not having to figure out how to put ifindex's
into the array. Although on some early implementations I wrote a small
hashing algorithm over the top of array, so that could work.
I don't know how well multicast applications might handle duplicate packets.
I wouldn't be too surprised if it was problematic. On the other hand missing
an entry that was just added is likely OK. There is no way to know from
network/user side if the entry was actually added before multicast op and
skipped or insert happened just after multicast op. And vice versa for a
delete dev, no way to know the multicast op happened before/after the
delete.
Have we consider doing something like the batch lookup ops over hashtab?
I don't mind "missing" values so if we just walk the list?
head = dev_map_index_hash(dtab, i)
// collect all my devs and get ready to send multicast
hlist_nulls_for_each_entry_safe(dev, next, head, index_hlist) {
enqueue(dev, skb)
}
// submit the queue of entries and do all the work to actually xmit
submit_enqueued();
We don't have to care about keys just walk the hash list?
>
> But John does have a point that this is not obvious; so maybe it should
> be pointed out in the helper documentation?
At minimum it needs to be documented, but really I want to fix it. I
can see the confused end users sending me bug reports already about
duplicate packets.
>
> -Toke
>
^ permalink raw reply [flat|nested] 15+ messages in thread* Re: [PATCHv4 bpf-next 2/4] xdp: extend xdp_redirect_map with broadcast support
2021-04-06 21:49 ` John Fastabend
@ 2021-04-06 22:19 ` Toke Høiland-Jørgensen
2021-04-06 22:29 ` John Fastabend
0 siblings, 1 reply; 15+ messages in thread
From: Toke Høiland-Jørgensen @ 2021-04-06 22:19 UTC (permalink / raw)
To: John Fastabend, Hangbin Liu
Cc: bpf, netdev, Jiri Benc, Jesper Dangaard Brouer, Eelco Chaudron,
ast, Daniel Borkmann, Lorenzo Bianconi, David Ahern,
Andrii Nakryiko, Alexei Starovoitov, Maciej Fijalkowski,
Björn Töpel
John Fastabend <john.fastabend@gmail.com> writes:
> Toke Høiland-Jørgensen wrote:
>> Hangbin Liu <liuhangbin@gmail.com> writes:
>>
>> > On Mon, Apr 05, 2021 at 05:24:48PM -0700, John Fastabend wrote:
>> >> Hangbin Liu wrote:
>> >> > This patch add two flags BPF_F_BROADCAST and BPF_F_EXCLUDE_INGRESS to extend
>> >> > xdp_redirect_map for broadcast support.
>> >> >
>> >> > Keep the general data path in net/core/filter.c and the native data
>> >> > path in kernel/bpf/devmap.c so we can use direct calls to get better
>> >> > performace.
>> >> >
>> >> > Here is the performance result by using xdp_redirect_{map, map_multi} in
>> >> > sample/bpf and send pkts via pktgen cmd:
>> >> > ./pktgen_sample03_burst_single_flow.sh -i eno1 -d $dst_ip -m $dst_mac -t 10 -s 64
>> >> >
>> >> > There are some drop back as we need to loop the map and get each interface.
>> >> >
>> >> > Version | Test | Generic | Native
>> >> > 5.12 rc2 | redirect_map i40e->i40e | 2.0M | 9.8M
>> >> > 5.12 rc2 | redirect_map i40e->veth | 1.8M | 12.0M
>> >>
>> >> Are these are 10gbps i40e ports? Sorry if I asked this earlier, maybe
>> >> add a note in the commit if another respin is needed.
>> >
>> > Yes, I will add it if there is an update.
>> >
>> >> > diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c
>> >> > index 3980fb3bfb09..c8452c5f40f8 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);
>> >>
>> >> Is this a bugfix? If its needed here wouldn't we also need it in the
>> >> devmap case.
>> >
>> > No, in ee75aef23afe ("bpf, xdp: Restructure redirect actions") this function
>> > was removed. I added it back as we use ri->map again.
>> >
>> > What devmap case you mean?
>> >
>> >>
>> >> > synchronize_rcu();
>> >> >
>> >> > /* Make sure prior __dev_map_entry_free() have completed. */
>> >>
>> >> [...]
>> >>
>> >> > +
>> >> > +static struct bpf_dtab_netdev *devmap_get_next_obj(struct xdp_buff *xdp,
>> >> > + struct bpf_map *map,
>> >> > + u32 *key, u32 *next_key,
>> >> > + int ex_ifindex)
>> >> > +{
>> >> > + struct bpf_dtab_netdev *obj;
>> >> > + struct net_device *dev;
>> >> > + u32 index;
>> >> > + int err;
>> >> > +
>> >> > + err = devmap_get_next_key(map, key, next_key);
>> >> > + if (err)
>> >> > + return NULL;
>> >> > +
>> >> > + /* When using dev map hash, we could restart the hashtab traversal
>> >> > + * in case the key has been updated/removed in the mean time.
>> >> > + * So we may end up potentially looping due to traversal restarts
>> >> > + * from first elem.
>> >> > + *
>> >> > + * Let's use map's max_entries to limit the loop number.
>> >> > + */
>> >> > + for (index = 0; index < map->max_entries; index++) {
>> >> > + obj = devmap_lookup_elem(map, *next_key);
>> >> > + if (!obj || dst_dev_is_ingress(obj, ex_ifindex))
>> >> > + goto find_next;
>> >> > +
>> >> > + dev = obj->dev;
>> >> > +
>> >> > + if (!dev->netdev_ops->ndo_xdp_xmit)
>> >> > + goto find_next;
>> >> > +
>> >> > + err = xdp_ok_fwd_dev(dev, xdp->data_end - xdp->data);
>> >> > + if (unlikely(err))
>> >> > + goto find_next;
>> >> > +
>> >> > + return obj;
>> >> > +
>> >> > +find_next:
>> >> > + key = next_key;
>> >> > + err = devmap_get_next_key(map, key, next_key);
>> >> > + if (err)
>> >> > + break;
>> >> > + }
>> >>
>> >> I'm missing something. Either an elaborated commit message or comment
>> >> is probably needed. I've been looking at this block for 30 minutes and
>> >> can't see how we avoid sending duplicate frames on a single interface?
>> >> Can you check this code flow,
>> >>
>> >> dev_map_enqueue_multi()
>> >> for (;;) {
>> >> next_obj = devmap_get_next_obj(...)
>> >> for (index = 0; index < map->max_entries; index++) {
>> >> obj = devmap_lookup_elem();
>> >> if (!obj) goto find_next
>> >> key = next_key;
>> >> err = devmap_get_next_key()
>> >> if (!key) goto find_first
>> >> for (i = 0; i < dtab->n_buckets; i++)
>> >> return *next <- now *next_key is point back
>> >> at first entry
>> >> // loop back through and find first obj and return that
>> >
>> > devmap_get_next_key() will loop to find the first one if there is no
>> > key or dev. In normal time it will stop after the latest one.
>> >> }
>> >> bq_enqueue(...) // enqueue original obj
>> >> obj = next_obj;
>> >> key = next_key;
>> >> ... // we are going to enqueue first obj, but how do we know
>> >> // this hasn't already been sent? Presumably if we have
>> >> // a delete in the hash table in the middle of a multicast
>> >> // operation this might happen?
>> >> }
>> >
>> > And yes, there is an corner case that if we removed a dev during multicast,
>> > there is an possibility that restart from the first key. But given that
>> > this is an unlikely case, and in normal internet there is also a possibility
>> > of duplicate/lost packet. This should also be acceptable?
>>
>> In my mind this falls under "acceptable corner cases". I.e., if you're
>> going to use the map for redirect and you expect to be updating it while
>> you're doing so, don't use a hashmap. But if you will not be updating
>> the map (or find the possible duplication acceptable), you can use the
>> hashmap and gain the benefit of being able to index by ifindex.
>
> In a Kubernetes setup its going to be hard, if possible at all, to restrict
> the map from moving as interfaces/IPs are going to be dynamic. Using a
> hash map has nice benefits of not having to figure out how to put ifindex's
> into the array. Although on some early implementations I wrote a small
> hashing algorithm over the top of array, so that could work.
>
> I don't know how well multicast applications might handle duplicate packets.
> I wouldn't be too surprised if it was problematic. On the other hand missing
> an entry that was just added is likely OK. There is no way to know from
> network/user side if the entry was actually added before multicast op and
> skipped or insert happened just after multicast op. And vice versa for a
> delete dev, no way to know the multicast op happened before/after the
> delete.
>
> Have we consider doing something like the batch lookup ops over hashtab?
> I don't mind "missing" values so if we just walk the list?
>
> head = dev_map_index_hash(dtab, i)
> // collect all my devs and get ready to send multicast
> hlist_nulls_for_each_entry_safe(dev, next, head, index_hlist) {
> enqueue(dev, skb)
> }
> // submit the queue of entries and do all the work to actually xmit
> submit_enqueued();
>
> We don't have to care about keys just walk the hash list?
So you'd wrap that in a loop like:
for (i = 0; i < dtab->n_buckets; i++) {
head = dev_map_index_hash(dtab, i);
hlist_nulls_for_each_entry_safe(dev, next, head, index_hlist) {
bq_enqueue(dev, xdpf, dev_rx, obj->xdp_prog);
}
}
or? Yeah, I guess that would work!
It would mean that dev_map_enqueue_multi() would need more in-depth
knowledge into the map type, so would likely need to be two different
functions for the two different map types, living in devmap.c - but
that's probably acceptable.
And while we're doing that, the array-map version can also loop over all
indexes up to max_entries, instead of stopping at the first index that
doesn't have an entry like it does now (right now, it looks like if you
populate entries 0 and 2 in an array-map only one copy of the packet
will be sent, to index 0).
It makes it a bit more awkward to do Hangbin's clever trick to avoid
doing an extra copy by aborting the loop early. But I guess the same
technique could apply...
-Toke
^ permalink raw reply [flat|nested] 15+ messages in thread* Re: [PATCHv4 bpf-next 2/4] xdp: extend xdp_redirect_map with broadcast support
2021-04-06 22:19 ` Toke Høiland-Jørgensen
@ 2021-04-06 22:29 ` John Fastabend
2021-04-06 23:10 ` Toke Høiland-Jørgensen
0 siblings, 1 reply; 15+ messages in thread
From: John Fastabend @ 2021-04-06 22:29 UTC (permalink / raw)
To: Toke Høiland-Jørgensen, John Fastabend, Hangbin Liu
Cc: bpf, netdev, Jiri Benc, Jesper Dangaard Brouer, Eelco Chaudron,
ast, Daniel Borkmann, Lorenzo Bianconi, David Ahern,
Andrii Nakryiko, Alexei Starovoitov, Maciej Fijalkowski,
Björn Töpel
Toke Høiland-Jørgensen wrote:
> John Fastabend <john.fastabend@gmail.com> writes:
>
> > Toke Høiland-Jørgensen wrote:
> >> Hangbin Liu <liuhangbin@gmail.com> writes:
> >>
> >> > On Mon, Apr 05, 2021 at 05:24:48PM -0700, John Fastabend wrote:
> >> >> Hangbin Liu wrote:
> >> >> > This patch add two flags BPF_F_BROADCAST and BPF_F_EXCLUDE_INGRESS to extend
> >> >> > xdp_redirect_map for broadcast support.
> >> >> >
> >> >> > Keep the general data path in net/core/filter.c and the native data
> >> >> > path in kernel/bpf/devmap.c so we can use direct calls to get better
> >> >> > performace.
> >> >> >
> >> >> > Here is the performance result by using xdp_redirect_{map, map_multi} in
> >> >> > sample/bpf and send pkts via pktgen cmd:
> >> >> > ./pktgen_sample03_burst_single_flow.sh -i eno1 -d $dst_ip -m $dst_mac -t 10 -s 64
> >> >> >
> >> >> > There are some drop back as we need to loop the map and get each interface.
> >> >> >
> >> >> > Version | Test | Generic | Native
> >> >> > 5.12 rc2 | redirect_map i40e->i40e | 2.0M | 9.8M
> >> >> > 5.12 rc2 | redirect_map i40e->veth | 1.8M | 12.0M
> >> >>
> >> >> Are these are 10gbps i40e ports? Sorry if I asked this earlier, maybe
> >> >> add a note in the commit if another respin is needed.
> >> >
> >> > Yes, I will add it if there is an update.
> >> >
> >> >> > diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c
> >> >> > index 3980fb3bfb09..c8452c5f40f8 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);
> >> >>
> >> >> Is this a bugfix? If its needed here wouldn't we also need it in the
> >> >> devmap case.
> >> >
> >> > No, in ee75aef23afe ("bpf, xdp: Restructure redirect actions") this function
> >> > was removed. I added it back as we use ri->map again.
> >> >
> >> > What devmap case you mean?
> >> >
> >> >>
> >> >> > synchronize_rcu();
> >> >> >
> >> >> > /* Make sure prior __dev_map_entry_free() have completed. */
> >> >>
> >> >> [...]
> >> >>
> >> >> > +
> >> >> > +static struct bpf_dtab_netdev *devmap_get_next_obj(struct xdp_buff *xdp,
> >> >> > + struct bpf_map *map,
> >> >> > + u32 *key, u32 *next_key,
> >> >> > + int ex_ifindex)
> >> >> > +{
> >> >> > + struct bpf_dtab_netdev *obj;
> >> >> > + struct net_device *dev;
> >> >> > + u32 index;
> >> >> > + int err;
> >> >> > +
> >> >> > + err = devmap_get_next_key(map, key, next_key);
> >> >> > + if (err)
> >> >> > + return NULL;
> >> >> > +
> >> >> > + /* When using dev map hash, we could restart the hashtab traversal
> >> >> > + * in case the key has been updated/removed in the mean time.
> >> >> > + * So we may end up potentially looping due to traversal restarts
> >> >> > + * from first elem.
> >> >> > + *
> >> >> > + * Let's use map's max_entries to limit the loop number.
> >> >> > + */
> >> >> > + for (index = 0; index < map->max_entries; index++) {
> >> >> > + obj = devmap_lookup_elem(map, *next_key);
> >> >> > + if (!obj || dst_dev_is_ingress(obj, ex_ifindex))
> >> >> > + goto find_next;
> >> >> > +
> >> >> > + dev = obj->dev;
> >> >> > +
> >> >> > + if (!dev->netdev_ops->ndo_xdp_xmit)
> >> >> > + goto find_next;
> >> >> > +
> >> >> > + err = xdp_ok_fwd_dev(dev, xdp->data_end - xdp->data);
> >> >> > + if (unlikely(err))
> >> >> > + goto find_next;
> >> >> > +
> >> >> > + return obj;
> >> >> > +
> >> >> > +find_next:
> >> >> > + key = next_key;
> >> >> > + err = devmap_get_next_key(map, key, next_key);
> >> >> > + if (err)
> >> >> > + break;
> >> >> > + }
> >> >>
> >> >> I'm missing something. Either an elaborated commit message or comment
> >> >> is probably needed. I've been looking at this block for 30 minutes and
> >> >> can't see how we avoid sending duplicate frames on a single interface?
> >> >> Can you check this code flow,
> >> >>
> >> >> dev_map_enqueue_multi()
> >> >> for (;;) {
> >> >> next_obj = devmap_get_next_obj(...)
> >> >> for (index = 0; index < map->max_entries; index++) {
> >> >> obj = devmap_lookup_elem();
> >> >> if (!obj) goto find_next
> >> >> key = next_key;
> >> >> err = devmap_get_next_key()
> >> >> if (!key) goto find_first
> >> >> for (i = 0; i < dtab->n_buckets; i++)
> >> >> return *next <- now *next_key is point back
> >> >> at first entry
> >> >> // loop back through and find first obj and return that
> >> >
> >> > devmap_get_next_key() will loop to find the first one if there is no
> >> > key or dev. In normal time it will stop after the latest one.
> >> >> }
> >> >> bq_enqueue(...) // enqueue original obj
> >> >> obj = next_obj;
> >> >> key = next_key;
> >> >> ... // we are going to enqueue first obj, but how do we know
> >> >> // this hasn't already been sent? Presumably if we have
> >> >> // a delete in the hash table in the middle of a multicast
> >> >> // operation this might happen?
> >> >> }
> >> >
> >> > And yes, there is an corner case that if we removed a dev during multicast,
> >> > there is an possibility that restart from the first key. But given that
> >> > this is an unlikely case, and in normal internet there is also a possibility
> >> > of duplicate/lost packet. This should also be acceptable?
> >>
> >> In my mind this falls under "acceptable corner cases". I.e., if you're
> >> going to use the map for redirect and you expect to be updating it while
> >> you're doing so, don't use a hashmap. But if you will not be updating
> >> the map (or find the possible duplication acceptable), you can use the
> >> hashmap and gain the benefit of being able to index by ifindex.
> >
> > In a Kubernetes setup its going to be hard, if possible at all, to restrict
> > the map from moving as interfaces/IPs are going to be dynamic. Using a
> > hash map has nice benefits of not having to figure out how to put ifindex's
> > into the array. Although on some early implementations I wrote a small
> > hashing algorithm over the top of array, so that could work.
> >
> > I don't know how well multicast applications might handle duplicate packets.
> > I wouldn't be too surprised if it was problematic. On the other hand missing
> > an entry that was just added is likely OK. There is no way to know from
> > network/user side if the entry was actually added before multicast op and
> > skipped or insert happened just after multicast op. And vice versa for a
> > delete dev, no way to know the multicast op happened before/after the
> > delete.
> >
> > Have we consider doing something like the batch lookup ops over hashtab?
> > I don't mind "missing" values so if we just walk the list?
> >
> > head = dev_map_index_hash(dtab, i)
> > // collect all my devs and get ready to send multicast
> > hlist_nulls_for_each_entry_safe(dev, next, head, index_hlist) {
> > enqueue(dev, skb)
> > }
> > // submit the queue of entries and do all the work to actually xmit
> > submit_enqueued();
> >
> > We don't have to care about keys just walk the hash list?
>
> So you'd wrap that in a loop like:
>
> for (i = 0; i < dtab->n_buckets; i++) {
> head = dev_map_index_hash(dtab, i);
> hlist_nulls_for_each_entry_safe(dev, next, head, index_hlist) {
> bq_enqueue(dev, xdpf, dev_rx, obj->xdp_prog);
> }
> }
>
> or? Yeah, I guess that would work!
Nice. Thanks for sticking with this Hangbin its taking us a bit, but
I think above works on my side at least.
>
> It would mean that dev_map_enqueue_multi() would need more in-depth
> knowledge into the map type, so would likely need to be two different
> functions for the two different map types, living in devmap.c - but
> that's probably acceptable.
Yeah, I think thats fine.
>
> And while we're doing that, the array-map version can also loop over all
> indexes up to max_entries, instead of stopping at the first index that
> doesn't have an entry like it does now (right now, it looks like if you
> populate entries 0 and 2 in an array-map only one copy of the packet
> will be sent, to index 0).
Right, this is likely needed anyways. At least when I was doing prototypes
of using array maps I often ended up with holes in the map. Just imagine
adding a set of devs and then removing one, its not likely to be the
last one you insert.
>
> It makes it a bit more awkward to do Hangbin's clever trick to avoid
> doing an extra copy by aborting the loop early. But I guess the same
> technique could apply...
>
> -Toke
>
^ permalink raw reply [flat|nested] 15+ messages in thread* Re: [PATCHv4 bpf-next 2/4] xdp: extend xdp_redirect_map with broadcast support
2021-04-06 22:29 ` John Fastabend
@ 2021-04-06 23:10 ` Toke Høiland-Jørgensen
2021-04-08 23:30 ` John Fastabend
0 siblings, 1 reply; 15+ messages in thread
From: Toke Høiland-Jørgensen @ 2021-04-06 23:10 UTC (permalink / raw)
To: John Fastabend, John Fastabend, Hangbin Liu
Cc: bpf, netdev, Jiri Benc, Jesper Dangaard Brouer, Eelco Chaudron,
ast, Daniel Borkmann, Lorenzo Bianconi, David Ahern,
Andrii Nakryiko, Alexei Starovoitov, Maciej Fijalkowski,
Björn Töpel
John Fastabend <john.fastabend@gmail.com> writes:
> Toke Høiland-Jørgensen wrote:
>> John Fastabend <john.fastabend@gmail.com> writes:
>>
>> > Toke Høiland-Jørgensen wrote:
>> >> Hangbin Liu <liuhangbin@gmail.com> writes:
>> >>
>> >> > On Mon, Apr 05, 2021 at 05:24:48PM -0700, John Fastabend wrote:
>> >> >> Hangbin Liu wrote:
>> >> >> > This patch add two flags BPF_F_BROADCAST and BPF_F_EXCLUDE_INGRESS to extend
>> >> >> > xdp_redirect_map for broadcast support.
>> >> >> >
>> >> >> > Keep the general data path in net/core/filter.c and the native data
>> >> >> > path in kernel/bpf/devmap.c so we can use direct calls to get better
>> >> >> > performace.
>> >> >> >
>> >> >> > Here is the performance result by using xdp_redirect_{map, map_multi} in
>> >> >> > sample/bpf and send pkts via pktgen cmd:
>> >> >> > ./pktgen_sample03_burst_single_flow.sh -i eno1 -d $dst_ip -m $dst_mac -t 10 -s 64
>> >> >> >
>> >> >> > There are some drop back as we need to loop the map and get each interface.
>> >> >> >
>> >> >> > Version | Test | Generic | Native
>> >> >> > 5.12 rc2 | redirect_map i40e->i40e | 2.0M | 9.8M
>> >> >> > 5.12 rc2 | redirect_map i40e->veth | 1.8M | 12.0M
>> >> >>
>> >> >> Are these are 10gbps i40e ports? Sorry if I asked this earlier, maybe
>> >> >> add a note in the commit if another respin is needed.
>> >> >
>> >> > Yes, I will add it if there is an update.
>> >> >
>> >> >> > diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c
>> >> >> > index 3980fb3bfb09..c8452c5f40f8 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);
>> >> >>
>> >> >> Is this a bugfix? If its needed here wouldn't we also need it in the
>> >> >> devmap case.
>> >> >
>> >> > No, in ee75aef23afe ("bpf, xdp: Restructure redirect actions") this function
>> >> > was removed. I added it back as we use ri->map again.
>> >> >
>> >> > What devmap case you mean?
>> >> >
>> >> >>
>> >> >> > synchronize_rcu();
>> >> >> >
>> >> >> > /* Make sure prior __dev_map_entry_free() have completed. */
>> >> >>
>> >> >> [...]
>> >> >>
>> >> >> > +
>> >> >> > +static struct bpf_dtab_netdev *devmap_get_next_obj(struct xdp_buff *xdp,
>> >> >> > + struct bpf_map *map,
>> >> >> > + u32 *key, u32 *next_key,
>> >> >> > + int ex_ifindex)
>> >> >> > +{
>> >> >> > + struct bpf_dtab_netdev *obj;
>> >> >> > + struct net_device *dev;
>> >> >> > + u32 index;
>> >> >> > + int err;
>> >> >> > +
>> >> >> > + err = devmap_get_next_key(map, key, next_key);
>> >> >> > + if (err)
>> >> >> > + return NULL;
>> >> >> > +
>> >> >> > + /* When using dev map hash, we could restart the hashtab traversal
>> >> >> > + * in case the key has been updated/removed in the mean time.
>> >> >> > + * So we may end up potentially looping due to traversal restarts
>> >> >> > + * from first elem.
>> >> >> > + *
>> >> >> > + * Let's use map's max_entries to limit the loop number.
>> >> >> > + */
>> >> >> > + for (index = 0; index < map->max_entries; index++) {
>> >> >> > + obj = devmap_lookup_elem(map, *next_key);
>> >> >> > + if (!obj || dst_dev_is_ingress(obj, ex_ifindex))
>> >> >> > + goto find_next;
>> >> >> > +
>> >> >> > + dev = obj->dev;
>> >> >> > +
>> >> >> > + if (!dev->netdev_ops->ndo_xdp_xmit)
>> >> >> > + goto find_next;
>> >> >> > +
>> >> >> > + err = xdp_ok_fwd_dev(dev, xdp->data_end - xdp->data);
>> >> >> > + if (unlikely(err))
>> >> >> > + goto find_next;
>> >> >> > +
>> >> >> > + return obj;
>> >> >> > +
>> >> >> > +find_next:
>> >> >> > + key = next_key;
>> >> >> > + err = devmap_get_next_key(map, key, next_key);
>> >> >> > + if (err)
>> >> >> > + break;
>> >> >> > + }
>> >> >>
>> >> >> I'm missing something. Either an elaborated commit message or comment
>> >> >> is probably needed. I've been looking at this block for 30 minutes and
>> >> >> can't see how we avoid sending duplicate frames on a single interface?
>> >> >> Can you check this code flow,
>> >> >>
>> >> >> dev_map_enqueue_multi()
>> >> >> for (;;) {
>> >> >> next_obj = devmap_get_next_obj(...)
>> >> >> for (index = 0; index < map->max_entries; index++) {
>> >> >> obj = devmap_lookup_elem();
>> >> >> if (!obj) goto find_next
>> >> >> key = next_key;
>> >> >> err = devmap_get_next_key()
>> >> >> if (!key) goto find_first
>> >> >> for (i = 0; i < dtab->n_buckets; i++)
>> >> >> return *next <- now *next_key is point back
>> >> >> at first entry
>> >> >> // loop back through and find first obj and return that
>> >> >
>> >> > devmap_get_next_key() will loop to find the first one if there is no
>> >> > key or dev. In normal time it will stop after the latest one.
>> >> >> }
>> >> >> bq_enqueue(...) // enqueue original obj
>> >> >> obj = next_obj;
>> >> >> key = next_key;
>> >> >> ... // we are going to enqueue first obj, but how do we know
>> >> >> // this hasn't already been sent? Presumably if we have
>> >> >> // a delete in the hash table in the middle of a multicast
>> >> >> // operation this might happen?
>> >> >> }
>> >> >
>> >> > And yes, there is an corner case that if we removed a dev during multicast,
>> >> > there is an possibility that restart from the first key. But given that
>> >> > this is an unlikely case, and in normal internet there is also a possibility
>> >> > of duplicate/lost packet. This should also be acceptable?
>> >>
>> >> In my mind this falls under "acceptable corner cases". I.e., if you're
>> >> going to use the map for redirect and you expect to be updating it while
>> >> you're doing so, don't use a hashmap. But if you will not be updating
>> >> the map (or find the possible duplication acceptable), you can use the
>> >> hashmap and gain the benefit of being able to index by ifindex.
>> >
>> > In a Kubernetes setup its going to be hard, if possible at all, to restrict
>> > the map from moving as interfaces/IPs are going to be dynamic. Using a
>> > hash map has nice benefits of not having to figure out how to put ifindex's
>> > into the array. Although on some early implementations I wrote a small
>> > hashing algorithm over the top of array, so that could work.
>> >
>> > I don't know how well multicast applications might handle duplicate packets.
>> > I wouldn't be too surprised if it was problematic. On the other hand missing
>> > an entry that was just added is likely OK. There is no way to know from
>> > network/user side if the entry was actually added before multicast op and
>> > skipped or insert happened just after multicast op. And vice versa for a
>> > delete dev, no way to know the multicast op happened before/after the
>> > delete.
>> >
>> > Have we consider doing something like the batch lookup ops over hashtab?
>> > I don't mind "missing" values so if we just walk the list?
>> >
>> > head = dev_map_index_hash(dtab, i)
>> > // collect all my devs and get ready to send multicast
>> > hlist_nulls_for_each_entry_safe(dev, next, head, index_hlist) {
>> > enqueue(dev, skb)
>> > }
>> > // submit the queue of entries and do all the work to actually xmit
>> > submit_enqueued();
>> >
>> > We don't have to care about keys just walk the hash list?
>>
>> So you'd wrap that in a loop like:
>>
>> for (i = 0; i < dtab->n_buckets; i++) {
>> head = dev_map_index_hash(dtab, i);
>> hlist_nulls_for_each_entry_safe(dev, next, head, index_hlist) {
>> bq_enqueue(dev, xdpf, dev_rx, obj->xdp_prog);
>> }
>> }
>>
>> or? Yeah, I guess that would work!
>
> Nice. Thanks for sticking with this Hangbin its taking us a bit, but
> I think above works on my side at least.
>
>>
>> It would mean that dev_map_enqueue_multi() would need more in-depth
>> knowledge into the map type, so would likely need to be two different
>> functions for the two different map types, living in devmap.c - but
>> that's probably acceptable.
>
> Yeah, I think thats fine.
>
>>
>> And while we're doing that, the array-map version can also loop over all
>> indexes up to max_entries, instead of stopping at the first index that
>> doesn't have an entry like it does now (right now, it looks like if you
>> populate entries 0 and 2 in an array-map only one copy of the packet
>> will be sent, to index 0).
>
> Right, this is likely needed anyways. At least when I was doing prototypes
> of using array maps I often ended up with holes in the map. Just imagine
> adding a set of devs and then removing one, its not likely to be the
> last one you insert.
Yeah, totally. Would have pointed it out if I'd noticed before, but I
was too trusting in the abstraction of get_next_key() etc :)
-Toke
^ permalink raw reply [flat|nested] 15+ messages in thread* Re: [PATCHv4 bpf-next 2/4] xdp: extend xdp_redirect_map with broadcast support
2021-04-06 23:10 ` Toke Høiland-Jørgensen
@ 2021-04-08 23:30 ` John Fastabend
2021-04-09 2:45 ` Hangbin Liu
0 siblings, 1 reply; 15+ messages in thread
From: John Fastabend @ 2021-04-08 23:30 UTC (permalink / raw)
To: Toke Høiland-Jørgensen, John Fastabend, John Fastabend,
Hangbin Liu
Cc: bpf, netdev, Jiri Benc, Jesper Dangaard Brouer, Eelco Chaudron,
ast, Daniel Borkmann, Lorenzo Bianconi, David Ahern,
Andrii Nakryiko, Alexei Starovoitov, Maciej Fijalkowski,
Björn Töpel
Toke Høiland-Jørgensen wrote:
> John Fastabend <john.fastabend@gmail.com> writes:
>
> > Toke Høiland-Jørgensen wrote:
> >> John Fastabend <john.fastabend@gmail.com> writes:
> >>
> >> > Toke Høiland-Jørgensen wrote:
> >> >> Hangbin Liu <liuhangbin@gmail.com> writes:
> >> >>
> >> >> > On Mon, Apr 05, 2021 at 05:24:48PM -0700, John Fastabend wrote:
> >> >> >> Hangbin Liu wrote:
> >> >> >> > This patch add two flags BPF_F_BROADCAST and BPF_F_EXCLUDE_INGRESS to extend
> >> >> >> > xdp_redirect_map for broadcast support.
[...]
> >> > Have we consider doing something like the batch lookup ops over hashtab?
> >> > I don't mind "missing" values so if we just walk the list?
> >> >
> >> > head = dev_map_index_hash(dtab, i)
> >> > // collect all my devs and get ready to send multicast
> >> > hlist_nulls_for_each_entry_safe(dev, next, head, index_hlist) {
> >> > enqueue(dev, skb)
> >> > }
> >> > // submit the queue of entries and do all the work to actually xmit
> >> > submit_enqueued();
> >> >
> >> > We don't have to care about keys just walk the hash list?
> >>
> >> So you'd wrap that in a loop like:
> >>
> >> for (i = 0; i < dtab->n_buckets; i++) {
> >> head = dev_map_index_hash(dtab, i);
> >> hlist_nulls_for_each_entry_safe(dev, next, head, index_hlist) {
> >> bq_enqueue(dev, xdpf, dev_rx, obj->xdp_prog);
> >> }
> >> }
> >>
> >> or? Yeah, I guess that would work!
> >
> > Nice. Thanks for sticking with this Hangbin its taking us a bit, but
> > I think above works on my side at least.
> >
> >>
> >> It would mean that dev_map_enqueue_multi() would need more in-depth
> >> knowledge into the map type, so would likely need to be two different
> >> functions for the two different map types, living in devmap.c - but
> >> that's probably acceptable.
> >
> > Yeah, I think thats fine.
> >
> >>
> >> And while we're doing that, the array-map version can also loop over all
> >> indexes up to max_entries, instead of stopping at the first index that
> >> doesn't have an entry like it does now (right now, it looks like if you
> >> populate entries 0 and 2 in an array-map only one copy of the packet
> >> will be sent, to index 0).
> >
> > Right, this is likely needed anyways. At least when I was doing prototypes
> > of using array maps I often ended up with holes in the map. Just imagine
> > adding a set of devs and then removing one, its not likely to be the
> > last one you insert.
>
> Yeah, totally. Would have pointed it out if I'd noticed before, but I
> was too trusting in the abstraction of get_next_key() etc :)
Hangbin,
If possible please try to capture some of the design discussion in
the commit message on the next rev along with the tradeoffs we are making
so we don't lose these important details. Some of these points are fairly
subtle calling them out will surely save (for me at least) some thinking
when I pick this up when it lands in a released kernel.
Thanks!
^ permalink raw reply [flat|nested] 15+ messages in thread* Re: [PATCHv4 bpf-next 2/4] xdp: extend xdp_redirect_map with broadcast support
2021-04-08 23:30 ` John Fastabend
@ 2021-04-09 2:45 ` Hangbin Liu
0 siblings, 0 replies; 15+ messages in thread
From: Hangbin Liu @ 2021-04-09 2:45 UTC (permalink / raw)
To: John Fastabend
Cc: Toke Høiland-Jørgensen, bpf, netdev, Jiri Benc,
Jesper Dangaard Brouer, Eelco Chaudron, ast, Daniel Borkmann,
Lorenzo Bianconi, David Ahern, Andrii Nakryiko,
Alexei Starovoitov, Maciej Fijalkowski, Björn Töpel
On Thu, Apr 08, 2021 at 04:30:45PM -0700, John Fastabend wrote:
> Hangbin,
>
> If possible please try to capture some of the design discussion in
> the commit message on the next rev along with the tradeoffs we are making
> so we don't lose these important details. Some of these points are fairly
> subtle calling them out will surely save (for me at least) some thinking
> when I pick this up when it lands in a released kernel.
OK, I will try. There are too many rounds discussion. Please forgive me
if I missed something.
Thanks
Hangbin
^ permalink raw reply [flat|nested] 15+ messages in thread
* Re: [PATCHv4 bpf-next 2/4] xdp: extend xdp_redirect_map with broadcast support
2021-04-02 12:19 ` [PATCHv4 bpf-next 2/4] xdp: extend xdp_redirect_map with broadcast support Hangbin Liu
2021-04-06 0:24 ` John Fastabend
@ 2021-04-06 11:17 ` Toke Høiland-Jørgensen
1 sibling, 0 replies; 15+ messages in thread
From: Toke Høiland-Jørgensen @ 2021-04-06 11:17 UTC (permalink / raw)
To: Hangbin Liu, bpf
Cc: netdev, Jiri Benc, Jesper Dangaard Brouer, Eelco Chaudron, ast,
Daniel Borkmann, Lorenzo Bianconi, David Ahern, Andrii Nakryiko,
Alexei Starovoitov, John Fastabend, Maciej Fijalkowski,
Björn Töpel, Hangbin Liu
Hangbin Liu <liuhangbin@gmail.com> writes:
> This patch add two flags BPF_F_BROADCAST and BPF_F_EXCLUDE_INGRESS to extend
> xdp_redirect_map for broadcast support.
>
> Keep the general data path in net/core/filter.c and the native data
> path in kernel/bpf/devmap.c so we can use direct calls to get better
> performace.
>
> Here is the performance result by using xdp_redirect_{map, map_multi} in
> sample/bpf and send pkts via pktgen cmd:
> ./pktgen_sample03_burst_single_flow.sh -i eno1 -d $dst_ip -m $dst_mac -t 10 -s 64
>
> There are some drop back as we need to loop the map and get each interface.
>
> Version | Test | Generic | Native
> 5.12 rc2 | redirect_map i40e->i40e | 2.0M | 9.8M
> 5.12 rc2 | redirect_map i40e->veth | 1.8M | 12.0M
> 5.12 rc2 + patch | redirect_map i40e->i40e | 2.0M | 9.6M
> 5.12 rc2 + patch | redirect_map i40e->veth | 1.7M | 12.0M
> 5.12 rc2 + patch | redirect_map multi i40e->i40e | 1.6M | 7.8M
> 5.12 rc2 + patch | redirect_map multi i40e->veth | 1.4M | 9.3M
> 5.12 rc2 + patch | redirect_map multi i40e->mlx4+veth | 1.0M | 3.4M
>
> Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
>
> ---
> v4:
> a) add a new argument flag_mask to __bpf_xdp_redirect_map() filter out
> invalid map.
> b) __bpf_xdp_redirect_map() sets the map pointer if the broadcast flag
> is set and clears it if the flag isn't set
> c) xdp_do_redirect() does the READ_ONCE/WRITE_ONCE on ri->map to check
> if we should enqueue multi
>
> v3:
> a) Rebase the code on Björn's "bpf, xdp: Restructure redirect actions".
> - Add struct bpf_map *map back to struct bpf_redirect_info as we need
> it for multicast.
> - Add bpf_clear_redirect_map() back for devmap.c
> - Add devmap_lookup_elem() as we need it in general path.
> b) remove tmp_key in devmap_get_next_obj()
>
> v2: Fix flag renaming issue in v1
> ---
> include/linux/bpf.h | 22 ++++++
> include/linux/filter.h | 18 ++++-
> include/net/xdp.h | 1 +
> include/uapi/linux/bpf.h | 17 ++++-
> kernel/bpf/cpumap.c | 3 +-
> kernel/bpf/devmap.c | 133 ++++++++++++++++++++++++++++++++-
> net/core/filter.c | 97 +++++++++++++++++++++++-
> net/core/xdp.c | 29 +++++++
> net/xdp/xskmap.c | 3 +-
> tools/include/uapi/linux/bpf.h | 17 ++++-
> 10 files changed, 326 insertions(+), 14 deletions(-)
>
> diff --git a/include/linux/bpf.h b/include/linux/bpf.h
> index 9fdd839b418c..d5745c6000bc 100644
> --- a/include/linux/bpf.h
> +++ b/include/linux/bpf.h
> @@ -1492,11 +1492,15 @@ struct sk_buff;
> struct bpf_dtab_netdev;
> struct bpf_cpu_map_entry;
>
> +struct bpf_dtab_netdev *devmap_lookup_elem(struct bpf_map *map, u32 key);
> void __dev_flush(void);
> 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);
> +bool dst_dev_is_ingress(struct bpf_dtab_netdev *obj, int ifindex);
> +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);
> bool dev_map_can_have_prog(struct bpf_map *map);
> @@ -1639,6 +1643,11 @@ static inline int bpf_obj_get_user(const char __user *pathname, int flags)
> return -EOPNOTSUPP;
> }
>
> +static inline struct net_device *devmap_lookup_elem(struct bpf_map *map, u32 key)
> +{
> + return NULL;
> +}
> +
> static inline bool dev_map_can_have_prog(struct bpf_map *map)
> {
> return false;
> @@ -1666,6 +1675,19 @@ int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp,
> return 0;
> }
>
> +static inline
> +bool dst_dev_is_ingress(struct bpf_dtab_netdev *obj, int ifindex)
> +{
> + return false;
> +}
> +
> +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,
> diff --git a/include/linux/filter.h b/include/linux/filter.h
> index 9a09547bc7ba..e4885b42d754 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 +1465,18 @@ 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, u64 flag_mask,
> void *lookup_elem(struct bpf_map *map, u32 key))
> {
> struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info);
>
> /* Lower bits of the flags are used as return code on lookup failure */
> - if (unlikely(flags > XDP_TX))
> + if (unlikely(flags & ~(BPF_F_ACTION_MASK | flag_mask)))
> return XDP_ABORTED;
Are we sure that the compiler is smart enough to combine the OR flags
here at compile-time? I guess it should be since it's an always_inline,
but it would be good to check that we don't end up with multiple bit
operations at runtime...
> 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 +1484,21 @@ 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 & BPF_F_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/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
> index 49371eba98ba..fe2c35bcc880 100644
> --- a/include/uapi/linux/bpf.h
> +++ b/include/uapi/linux/bpf.h
> @@ -2513,8 +2513,12 @@ 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.
> @@ -5015,6 +5019,15 @@ 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_F_ACTION_MASK (XDP_ABORTED | XDP_DROP | XDP_PASS | XDP_TX)
> +#define BPF_F_REDIR_MASK (BPF_F_BROADCAST | BPF_F_EXCLUDE_INGRESS)
> +
> #define __bpf_md_ptr(type, name) \
> union { \
> type name; \
> diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c
> index 0cf2791d5099..2c33a7a09783 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 3980fb3bfb09..c8452c5f40f8 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. */
> @@ -451,6 +452,24 @@ static void *__dev_map_lookup_elem(struct bpf_map *map, u32 key)
> return obj;
> }
>
> +struct bpf_dtab_netdev *devmap_lookup_elem(struct bpf_map *map, u32 key)
> +{
> + struct bpf_dtab_netdev *obj = NULL;
> +
> + switch (map->map_type) {
> + case BPF_MAP_TYPE_DEVMAP:
> + obj = __dev_map_lookup_elem(map, key);
> + break;
> + case BPF_MAP_TYPE_DEVMAP_HASH:
> + obj = __dev_map_hash_lookup_elem(map, key);
> + break;
> + default:
> + break;
> + }
> +
> + return obj;
> +}
> +
> /* Runs under RCU-read-side, plus in softirq under NAPI protection.
> * Thus, safe percpu variable access.
> */
> @@ -515,6 +534,114 @@ int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp,
> return __xdp_enqueue(dev, xdp, dev_rx, dst->xdp_prog);
> }
>
> +/* Use direct call in fast path instead of map->ops->map_get_next_key() */
> +static int devmap_get_next_key(struct bpf_map *map, void *key, void *next_key)
> +{
> + switch (map->map_type) {
> + case BPF_MAP_TYPE_DEVMAP:
> + return dev_map_get_next_key(map, key, next_key);
> + case BPF_MAP_TYPE_DEVMAP_HASH:
> + return dev_map_hash_get_next_key(map, key, next_key);
> + default:
> + break;
> + }
> +
> + return -ENOENT;
> +}
> +
> +bool dst_dev_is_ingress(struct bpf_dtab_netdev *dst, int ifindex)
> +{
> + return dst->dev->ifindex == ifindex;
> +}
> +
> +static struct bpf_dtab_netdev *devmap_get_next_obj(struct xdp_buff *xdp,
> + struct bpf_map *map,
> + u32 *key, u32 *next_key,
> + int ex_ifindex)
> +{
> + struct bpf_dtab_netdev *obj;
> + struct net_device *dev;
> + u32 index;
> + int err;
> +
> + err = devmap_get_next_key(map, key, next_key);
> + if (err)
> + return NULL;
> +
> + /* When using dev map hash, we could restart the hashtab traversal
> + * in case the key has been updated/removed in the mean time.
> + * So we may end up potentially looping due to traversal restarts
> + * from first elem.
> + *
> + * Let's use map's max_entries to limit the loop number.
> + */
> + for (index = 0; index < map->max_entries; index++) {
> + obj = devmap_lookup_elem(map, *next_key);
> + if (!obj || dst_dev_is_ingress(obj, ex_ifindex))
> + goto find_next;
> +
> + dev = obj->dev;
> +
> + if (!dev->netdev_ops->ndo_xdp_xmit)
> + goto find_next;
> +
> + err = xdp_ok_fwd_dev(dev, xdp->data_end - xdp->data);
> + if (unlikely(err))
> + goto find_next;
> +
> + return obj;
> +
> +find_next:
> + key = next_key;
> + err = devmap_get_next_key(map, key, next_key);
> + if (err)
> + break;
> + }
> +
> + return NULL;
> +}
> +
> +int dev_map_enqueue_multi(struct xdp_buff *xdp, struct net_device *dev_rx,
> + struct bpf_map *map, bool exclude_ingress)
> +{
> + struct bpf_dtab_netdev *obj = NULL, *next_obj = NULL;
> + struct xdp_frame *xdpf, *nxdpf;
> + u32 key, next_key;
> + int ex_ifindex;
> +
> + ex_ifindex = exclude_ingress ? dev_rx->ifindex : 0;
> +
> + /* Find first available obj */
> + obj = devmap_get_next_obj(xdp, map, NULL, &key, ex_ifindex);
> + if (!obj)
> + return -ENOENT;
> +
> + xdpf = xdp_convert_buff_to_frame(xdp);
> + if (unlikely(!xdpf))
> + return -EOVERFLOW;
> +
> + for (;;) {
> + /* Check if we still have one more available obj */
> + next_obj = devmap_get_next_obj(xdp, map, &key, &next_key, ex_ifindex);
> + if (!next_obj) {
> + bq_enqueue(obj->dev, xdpf, dev_rx, obj->xdp_prog);
> + return 0;
> + }
> +
> + nxdpf = xdpf_clone(xdpf);
> + if (unlikely(!nxdpf)) {
> + xdp_return_frame_rx_napi(xdpf);
> + return -ENOMEM;
> + }
> +
> + bq_enqueue(obj->dev, nxdpf, dev_rx, obj->xdp_prog);
> +
> + /* Deal with next obj */
> + obj = next_obj;
> + key = next_key;
> + }
> +}
> +
> int dev_map_generic_redirect(struct bpf_dtab_netdev *dst, struct sk_buff *skb,
> struct bpf_prog *xdp_prog)
> {
> @@ -755,12 +882,14 @@ 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_REDIR_MASK,
> + __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_REDIR_MASK,
> + __dev_map_hash_lookup_elem);
> }
>
> static int dev_map_btf_id;
> diff --git a/net/core/filter.c b/net/core/filter.c
> index cae56d08a670..08a4d3869056 100644
> --- a/net/core/filter.c
> +++ b/net/core/filter.c
> @@ -3926,6 +3926,23 @@ 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)
> {
> @@ -3933,16 +3950,28 @@ 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;
> + bool exclude_ingress;
> + struct bpf_map *map;
> int err;
>
> ri->map_id = 0; /* Valid map id idr range: [1,INT_MAX[ */
> ri->map_type = BPF_MAP_TYPE_UNSPEC;
>
> + map = READ_ONCE(ri->map);
> + if (map) {
> + WRITE_ONCE(ri->map, NULL);
> + exclude_ingress = ri->flags & BPF_F_EXCLUDE_INGRESS;
> + ri->flags = 0;
> + }
I would just drop this block entirely...
> +
> switch (map_type) {
> case BPF_MAP_TYPE_DEVMAP:
> fallthrough;
> case BPF_MAP_TYPE_DEVMAP_HASH:
> - err = dev_map_enqueue(fwd, xdp, dev);
...and instead just add a line here like:
map = xchg(&ri->map, NULL);
This will make it much clearer that the read of map belongs with the
devmap types. And you don't actually need to clear the flags (since now
they will always be set in the helper), so you can just use ri->flags &
BPF_F_EXCLUDE_INGRESS directly in the function call below like you did
before.
> + if (map)
> + err = dev_map_enqueue_multi(xdp, dev, map, exclude_ingress);
> + else
> + err = dev_map_enqueue(fwd, xdp, dev);
> break;
> case BPF_MAP_TYPE_CPUMAP:
> err = cpu_map_enqueue(fwd, xdp, dev);
> @@ -3976,6 +4005,57 @@ int xdp_do_redirect(struct net_device *dev, struct xdp_buff *xdp,
> }
> EXPORT_SYMBOL_GPL(xdp_do_redirect);
>
> +static 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_netdev *dst;
> + u32 key, next_key, index;
> + struct sk_buff *nskb;
> + void *fwd;
> + int err;
> +
> + err = map->ops->map_get_next_key(map, NULL, &key);
> + if (err)
> + return err;
> +
> + /* When using dev map hash, we could restart the hashtab traversal
> + * in case the key has been updated/removed in the mean time.
> + * So we may end up potentially looping due to traversal restarts
> + * from first elem.
> + *
> + * Let's use map's max_entries to limit the loop number.
> + */
> +
> + for (index = 0; index < map->max_entries; index++) {
> + fwd = devmap_lookup_elem(map, key);
> + if (fwd) {
> + dst = (struct bpf_dtab_netdev *)fwd;
> + if (dst_dev_is_ingress(dst, exclude_ingress ? dev->ifindex : 0))
> + goto find_next;
> +
> + nskb = skb_clone(skb, GFP_ATOMIC);
> + if (!nskb)
> + return -ENOMEM;
> +
> + /* Try forword next one no mater the current forward
> + * succeed or not.
> + */
> + dev_map_generic_redirect(dst, nskb, xdp_prog);
> + }
> +
> +find_next:
> + err = map->ops->map_get_next_key(map, &key, &next_key);
> + if (err)
> + break;
> +
> + key = next_key;
> + }
> +
> + consume_skb(skb);
> + return 0;
> +}
> +
> static int xdp_do_generic_redirect_map(struct net_device *dev,
> struct sk_buff *skb,
> struct xdp_buff *xdp,
> @@ -3984,13 +4064,26 @@ 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);
> + bool exclude_ingress;
> + struct bpf_map *map;
> int err;
>
> + map = READ_ONCE(ri->map);
> + if (map) {
> + WRITE_ONCE(ri->map, NULL);
> + exclude_ingress = ri->flags & BPF_F_EXCLUDE_INGRESS;
> + ri->flags = 0;
> + }
(same as above)
-Toke
^ permalink raw reply [flat|nested] 15+ messages in thread
* [PATCHv4 bpf-next 3/4] sample/bpf: add xdp_redirect_map_multi for redirect_map broadcast test
2021-04-02 12:19 [PATCHv4 bpf-next 0/4] xdp: extend xdp_redirect_map with broadcast support Hangbin Liu
2021-04-02 12:19 ` [PATCHv4 bpf-next 1/4] bpf: run devmap xdp_prog on flush instead of bulk enqueue Hangbin Liu
2021-04-02 12:19 ` [PATCHv4 bpf-next 2/4] xdp: extend xdp_redirect_map with broadcast support Hangbin Liu
@ 2021-04-02 12:19 ` Hangbin Liu
2021-04-02 12:19 ` [PATCHv4 bpf-next 4/4] selftests/bpf: add xdp_redirect_multi test Hangbin Liu
3 siblings, 0 replies; 15+ messages in thread
From: Hangbin Liu @ 2021-04-02 12:19 UTC (permalink / raw)
To: bpf
Cc: netdev, Toke Høiland-Jørgensen, Jiri Benc,
Jesper Dangaard Brouer, Eelco Chaudron, ast, Daniel Borkmann,
Lorenzo Bianconi, David Ahern, Andrii Nakryiko,
Alexei Starovoitov, John Fastabend, Maciej Fijalkowski,
Björn Töpel, Hangbin Liu
This is a sample for xdp redirect broadcast. In the sample we could forward
all packets between given interfaces. There is also an option -X that could
enable 2nd xdp_prog on egress interface.
Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
---
samples/bpf/Makefile | 3 +
samples/bpf/xdp_redirect_map_multi_kern.c | 87 +++++++
samples/bpf/xdp_redirect_map_multi_user.c | 302 ++++++++++++++++++++++
3 files changed, 392 insertions(+)
create mode 100644 samples/bpf/xdp_redirect_map_multi_kern.c
create mode 100644 samples/bpf/xdp_redirect_map_multi_user.c
diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile
index 45ceca4e2c70..520434ea966f 100644
--- a/samples/bpf/Makefile
+++ b/samples/bpf/Makefile
@@ -41,6 +41,7 @@ tprogs-y += test_map_in_map
tprogs-y += per_socket_stats_example
tprogs-y += xdp_redirect
tprogs-y += xdp_redirect_map
+tprogs-y += xdp_redirect_map_multi
tprogs-y += xdp_redirect_cpu
tprogs-y += xdp_monitor
tprogs-y += xdp_rxq_info
@@ -99,6 +100,7 @@ test_map_in_map-objs := test_map_in_map_user.o
per_socket_stats_example-objs := cookie_uid_helper_example.o
xdp_redirect-objs := xdp_redirect_user.o
xdp_redirect_map-objs := xdp_redirect_map_user.o
+xdp_redirect_map_multi-objs := xdp_redirect_map_multi_user.o
xdp_redirect_cpu-objs := xdp_redirect_cpu_user.o
xdp_monitor-objs := xdp_monitor_user.o
xdp_rxq_info-objs := xdp_rxq_info_user.o
@@ -160,6 +162,7 @@ always-y += tcp_tos_reflect_kern.o
always-y += tcp_dumpstats_kern.o
always-y += xdp_redirect_kern.o
always-y += xdp_redirect_map_kern.o
+always-y += xdp_redirect_map_multi_kern.o
always-y += xdp_redirect_cpu_kern.o
always-y += xdp_monitor_kern.o
always-y += xdp_rxq_info_kern.o
diff --git a/samples/bpf/xdp_redirect_map_multi_kern.c b/samples/bpf/xdp_redirect_map_multi_kern.c
new file mode 100644
index 000000000000..e6be70225ee1
--- /dev/null
+++ b/samples/bpf/xdp_redirect_map_multi_kern.c
@@ -0,0 +1,87 @@
+// SPDX-License-Identifier: GPL-2.0
+#define KBUILD_MODNAME "foo"
+#include <uapi/linux/bpf.h>
+#include <linux/in.h>
+#include <linux/if_ether.h>
+#include <linux/ip.h>
+#include <linux/ipv6.h>
+#include <bpf/bpf_helpers.h>
+
+struct {
+ __uint(type, BPF_MAP_TYPE_DEVMAP_HASH);
+ __uint(key_size, sizeof(int));
+ __uint(value_size, sizeof(int));
+ __uint(max_entries, 32);
+} forward_map_general SEC(".maps");
+
+struct {
+ __uint(type, BPF_MAP_TYPE_DEVMAP_HASH);
+ __uint(key_size, sizeof(int));
+ __uint(value_size, sizeof(struct bpf_devmap_val));
+ __uint(max_entries, 32);
+} forward_map_native SEC(".maps");
+
+struct {
+ __uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
+ __type(key, u32);
+ __type(value, long);
+ __uint(max_entries, 1);
+} rxcnt SEC(".maps");
+
+/* map to store egress interfaces mac addresses, set the
+ * max_entries to 1 and extend it in user sapce prog.
+ */
+struct {
+ __uint(type, BPF_MAP_TYPE_ARRAY);
+ __type(key, u32);
+ __type(value, __be64);
+ __uint(max_entries, 1);
+} mac_map SEC(".maps");
+
+static int xdp_redirect_map(struct xdp_md *ctx, void *forward_map)
+{
+ long *value;
+ u32 key = 0;
+
+ /* count packet in global counter */
+ value = bpf_map_lookup_elem(&rxcnt, &key);
+ if (value)
+ *value += 1;
+
+ return bpf_redirect_map(forward_map, key, BPF_F_REDIR_MASK);
+}
+
+SEC("xdp_redirect_general")
+int xdp_redirect_map_general(struct xdp_md *ctx)
+{
+ return xdp_redirect_map(ctx, &forward_map_general);
+}
+
+SEC("xdp_redirect_native")
+int xdp_redirect_map_native(struct xdp_md *ctx)
+{
+ return xdp_redirect_map(ctx, &forward_map_native);
+}
+
+SEC("xdp_devmap/map_prog")
+int xdp_devmap_prog(struct xdp_md *ctx)
+{
+ void *data_end = (void *)(long)ctx->data_end;
+ void *data = (void *)(long)ctx->data;
+ u32 key = ctx->egress_ifindex;
+ struct ethhdr *eth = data;
+ __be64 *mac;
+ u64 nh_off;
+
+ nh_off = sizeof(*eth);
+ if (data + nh_off > data_end)
+ return XDP_DROP;
+
+ mac = bpf_map_lookup_elem(&mac_map, &key);
+ if (mac)
+ __builtin_memcpy(eth->h_source, mac, ETH_ALEN);
+
+ return XDP_PASS;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/samples/bpf/xdp_redirect_map_multi_user.c b/samples/bpf/xdp_redirect_map_multi_user.c
new file mode 100644
index 000000000000..84cdbbed20b7
--- /dev/null
+++ b/samples/bpf/xdp_redirect_map_multi_user.c
@@ -0,0 +1,302 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/bpf.h>
+#include <linux/if_link.h>
+#include <assert.h>
+#include <errno.h>
+#include <signal.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <net/if.h>
+#include <unistd.h>
+#include <libgen.h>
+#include <sys/resource.h>
+#include <sys/ioctl.h>
+#include <sys/types.h>
+#include <sys/socket.h>
+#include <netinet/in.h>
+
+#include "bpf_util.h"
+#include <bpf/bpf.h>
+#include <bpf/libbpf.h>
+
+#define MAX_IFACE_NUM 32
+
+static __u32 xdp_flags = XDP_FLAGS_UPDATE_IF_NOEXIST;
+static int ifaces[MAX_IFACE_NUM] = {};
+static int rxcnt_map_fd;
+
+static void int_exit(int sig)
+{
+ __u32 prog_id = 0;
+ int i;
+
+ for (i = 0; ifaces[i] > 0; i++) {
+ if (bpf_get_link_xdp_id(ifaces[i], &prog_id, xdp_flags)) {
+ printf("bpf_get_link_xdp_id failed\n");
+ exit(1);
+ }
+ if (prog_id)
+ bpf_set_link_xdp_fd(ifaces[i], -1, xdp_flags);
+ }
+
+ exit(0);
+}
+
+static void poll_stats(int interval)
+{
+ unsigned int nr_cpus = bpf_num_possible_cpus();
+ __u64 values[nr_cpus], prev[nr_cpus];
+
+ memset(prev, 0, sizeof(prev));
+
+ while (1) {
+ __u64 sum = 0;
+ __u32 key = 0;
+ int i;
+
+ sleep(interval);
+ assert(bpf_map_lookup_elem(rxcnt_map_fd, &key, values) == 0);
+ for (i = 0; i < nr_cpus; i++)
+ sum += (values[i] - prev[i]);
+ if (sum)
+ printf("Forwarding %10llu pkt/s\n", sum / interval);
+ memcpy(prev, values, sizeof(values));
+ }
+}
+
+static int get_mac_addr(unsigned int ifindex, void *mac_addr)
+{
+ char ifname[IF_NAMESIZE];
+ struct ifreq ifr;
+ int fd, ret = -1;
+
+ fd = socket(AF_INET, SOCK_DGRAM, 0);
+ if (fd < 0)
+ return ret;
+
+ if (!if_indextoname(ifindex, ifname))
+ goto err_out;
+
+ strcpy(ifr.ifr_name, ifname);
+
+ if (ioctl(fd, SIOCGIFHWADDR, &ifr) != 0)
+ goto err_out;
+
+ memcpy(mac_addr, ifr.ifr_hwaddr.sa_data, 6 * sizeof(char));
+ ret = 0;
+
+err_out:
+ close(fd);
+ return ret;
+}
+
+static int update_mac_map(struct bpf_object *obj)
+{
+ int i, ret = -1, mac_map_fd;
+ unsigned char mac_addr[6];
+ unsigned int ifindex;
+
+ mac_map_fd = bpf_object__find_map_fd_by_name(obj, "mac_map");
+ if (mac_map_fd < 0) {
+ printf("find mac map fd failed\n");
+ return ret;
+ }
+
+ for (i = 0; ifaces[i] > 0; i++) {
+ ifindex = ifaces[i];
+
+ ret = get_mac_addr(ifindex, mac_addr);
+ if (ret < 0) {
+ printf("get interface %d mac failed\n", ifindex);
+ return ret;
+ }
+
+ ret = bpf_map_update_elem(mac_map_fd, &ifindex, mac_addr, 0);
+ if (ret) {
+ perror("bpf_update_elem mac_map_fd");
+ return ret;
+ }
+ }
+
+ return 0;
+}
+
+static void usage(const char *prog)
+{
+ fprintf(stderr,
+ "usage: %s [OPTS] <IFNAME|IFINDEX> <IFNAME|IFINDEX> ...\n"
+ "OPTS:\n"
+ " -S use skb-mode\n"
+ " -N enforce native mode\n"
+ " -F force loading prog\n"
+ " -X load xdp program on egress\n",
+ prog);
+}
+
+int main(int argc, char **argv)
+{
+ int i, ret, opt, forward_map_fd, max_ifindex = 0;
+ struct bpf_program *ingress_prog, *egress_prog;
+ int ingress_prog_fd, egress_prog_fd = 0;
+ struct bpf_devmap_val devmap_val;
+ bool attach_egress_prog = false;
+ char ifname[IF_NAMESIZE];
+ struct bpf_map *mac_map;
+ struct bpf_object *obj;
+ unsigned int ifindex;
+ char filename[256];
+
+ while ((opt = getopt(argc, argv, "SNFX")) != -1) {
+ switch (opt) {
+ case 'S':
+ xdp_flags |= XDP_FLAGS_SKB_MODE;
+ break;
+ case 'N':
+ /* default, set below */
+ break;
+ case 'F':
+ xdp_flags &= ~XDP_FLAGS_UPDATE_IF_NOEXIST;
+ break;
+ case 'X':
+ attach_egress_prog = true;
+ break;
+ default:
+ usage(basename(argv[0]));
+ return 1;
+ }
+ }
+
+ if (!(xdp_flags & XDP_FLAGS_SKB_MODE)) {
+ xdp_flags |= XDP_FLAGS_DRV_MODE;
+ } else if (attach_egress_prog) {
+ printf("Load xdp program on egress with SKB mode not supported yet\n");
+ return 1;
+ }
+
+ if (optind == argc) {
+ printf("usage: %s <IFNAME|IFINDEX> <IFNAME|IFINDEX> ...\n", argv[0]);
+ return 1;
+ }
+
+ printf("Get interfaces");
+ for (i = 0; i < MAX_IFACE_NUM && argv[optind + i]; i++) {
+ ifaces[i] = if_nametoindex(argv[optind + i]);
+ if (!ifaces[i])
+ ifaces[i] = strtoul(argv[optind + i], NULL, 0);
+ if (!if_indextoname(ifaces[i], ifname)) {
+ perror("Invalid interface name or i");
+ return 1;
+ }
+
+ /* Find the largest index number */
+ if (ifaces[i] > max_ifindex)
+ max_ifindex = ifaces[i];
+
+ printf(" %d", ifaces[i]);
+ }
+ printf("\n");
+
+ snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]);
+
+ obj = bpf_object__open(filename);
+ if (libbpf_get_error(obj)) {
+ printf("ERROR: opening BPF object file failed\n");
+ obj = NULL;
+ goto err_out;
+ }
+
+ /* Reset the map size to max ifindex + 1 */
+ if (attach_egress_prog) {
+ mac_map = bpf_object__find_map_by_name(obj, "mac_map");
+ ret = bpf_map__resize(mac_map, max_ifindex + 1);
+ if (ret < 0) {
+ printf("ERROR: reset mac map size failed\n");
+ goto err_out;
+ }
+ }
+
+ /* load BPF program */
+ if (bpf_object__load(obj)) {
+ printf("ERROR: loading BPF object file failed\n");
+ goto err_out;
+ }
+
+ if (xdp_flags & XDP_FLAGS_SKB_MODE) {
+ ingress_prog = bpf_object__find_program_by_name(obj, "xdp_redirect_map_general");
+ forward_map_fd = bpf_object__find_map_fd_by_name(obj, "forward_map_general");
+ } else {
+ ingress_prog = bpf_object__find_program_by_name(obj, "xdp_redirect_map_native");
+ forward_map_fd = bpf_object__find_map_fd_by_name(obj, "forward_map_native");
+ }
+ if (!ingress_prog || forward_map_fd < 0) {
+ printf("finding ingress_prog/forward_map in obj file failed\n");
+ goto err_out;
+ }
+
+ ingress_prog_fd = bpf_program__fd(ingress_prog);
+ if (ingress_prog_fd < 0) {
+ printf("find ingress_prog fd failed\n");
+ goto err_out;
+ }
+
+ rxcnt_map_fd = bpf_object__find_map_fd_by_name(obj, "rxcnt");
+ if (rxcnt_map_fd < 0) {
+ printf("bpf_object__find_map_fd_by_name failed\n");
+ goto err_out;
+ }
+
+ if (attach_egress_prog) {
+ /* Update mac_map with all egress interfaces' mac addr */
+ if (update_mac_map(obj) < 0) {
+ printf("Error: update mac map failed");
+ goto err_out;
+ }
+
+ /* Find egress prog fd */
+ egress_prog = bpf_object__find_program_by_name(obj, "xdp_devmap_prog");
+ if (!egress_prog) {
+ printf("finding egress_prog in obj file failed\n");
+ goto err_out;
+ }
+ egress_prog_fd = bpf_program__fd(egress_prog);
+ if (egress_prog_fd < 0) {
+ printf("find egress_prog fd failed\n");
+ goto err_out;
+ }
+ }
+
+ /* Remove attached program when program is interrupted or killed */
+ signal(SIGINT, int_exit);
+ signal(SIGTERM, int_exit);
+
+ /* Init forward multicast groups */
+ for (i = 0; ifaces[i] > 0; i++) {
+ ifindex = ifaces[i];
+
+ /* bind prog_fd to each interface */
+ ret = bpf_set_link_xdp_fd(ifindex, ingress_prog_fd, xdp_flags);
+ if (ret) {
+ printf("Set xdp fd failed on %d\n", ifindex);
+ goto err_out;
+ }
+
+ /* Add all the interfaces to forward group and attach
+ * egress devmap programe if exist
+ */
+ devmap_val.ifindex = ifindex;
+ devmap_val.bpf_prog.fd = egress_prog_fd;
+ ret = bpf_map_update_elem(forward_map_fd, &ifindex, &devmap_val, 0);
+ if (ret) {
+ perror("bpf_map_update_elem forward_map");
+ goto err_out;
+ }
+ }
+
+ poll_stats(2);
+
+ return 0;
+
+err_out:
+ return 1;
+}
--
2.26.3
^ permalink raw reply related [flat|nested] 15+ messages in thread* [PATCHv4 bpf-next 4/4] selftests/bpf: add xdp_redirect_multi test
2021-04-02 12:19 [PATCHv4 bpf-next 0/4] xdp: extend xdp_redirect_map with broadcast support Hangbin Liu
` (2 preceding siblings ...)
2021-04-02 12:19 ` [PATCHv4 bpf-next 3/4] sample/bpf: add xdp_redirect_map_multi for redirect_map broadcast test Hangbin Liu
@ 2021-04-02 12:19 ` Hangbin Liu
3 siblings, 0 replies; 15+ messages in thread
From: Hangbin Liu @ 2021-04-02 12:19 UTC (permalink / raw)
To: bpf
Cc: netdev, Toke Høiland-Jørgensen, Jiri Benc,
Jesper Dangaard Brouer, Eelco Chaudron, ast, Daniel Borkmann,
Lorenzo Bianconi, David Ahern, Andrii Nakryiko,
Alexei Starovoitov, John Fastabend, Maciej Fijalkowski,
Björn Töpel, Hangbin Liu
Add a bpf selftest for new helper xdp_redirect_map_multi(). In this
test there are 3 forward groups and 1 exclude group. The test will
redirect each interface's packets to all the interfaces in the forward
group, and exclude the interface in exclude map.
Two maps (DEVMAP, DEVMAP_HASH) and two xdp modes (generic, drive) will
be tested. XDP egress program will also be tested by setting pkt src MAC
to egress interface's MAC address.
For more test details, you can find it in the test script. Here is
the test result.
]# ./test_xdp_redirect_multi.sh
Pass: xdpgeneric arp ns1-2
Pass: xdpgeneric arp ns1-3
Pass: xdpgeneric arp ns1-4
Pass: xdpgeneric ping ns1-2
Pass: xdpgeneric ping ns1-3
Pass: xdpgeneric ping ns1-4
Pass: xdpgeneric ping6 ns1-2
Pass: xdpgeneric ping6 ns1-1 number
Pass: xdpgeneric ping6 ns1-2 number
Pass: xdpdrv arp ns1-2
Pass: xdpdrv arp ns1-3
Pass: xdpdrv arp ns1-4
Pass: xdpdrv ping ns1-2
Pass: xdpdrv ping ns1-3
Pass: xdpdrv ping ns1-4
Pass: xdpdrv ping6 ns1-2
Pass: xdpdrv ping6 ns1-1 number
Pass: xdpdrv ping6 ns1-2 number
Pass: xdpegress mac ns1-2
Pass: xdpegress mac ns1-3
Pass: xdpegress mac ns1-4
Summary: PASS 21, FAIL 0
Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
---
v4: add a IPv6 test to validates that single redirect still works
after multicast redirect.
v2-v3: no update
---
tools/testing/selftests/bpf/Makefile | 3 +-
.../bpf/progs/xdp_redirect_multi_kern.c | 99 ++++++++
.../selftests/bpf/test_xdp_redirect_multi.sh | 205 +++++++++++++++
.../selftests/bpf/xdp_redirect_multi.c | 236 ++++++++++++++++++
4 files changed, 542 insertions(+), 1 deletion(-)
create mode 100644 tools/testing/selftests/bpf/progs/xdp_redirect_multi_kern.c
create mode 100755 tools/testing/selftests/bpf/test_xdp_redirect_multi.sh
create mode 100644 tools/testing/selftests/bpf/xdp_redirect_multi.c
diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index 6448c626498f..0c08b662a64e 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -49,6 +49,7 @@ TEST_FILES = xsk_prereqs.sh \
# Order correspond to 'make run_tests' order
TEST_PROGS := test_kmod.sh \
test_xdp_redirect.sh \
+ test_xdp_redirect_multi.sh \
test_xdp_meta.sh \
test_xdp_veth.sh \
test_offload.py \
@@ -79,7 +80,7 @@ TEST_PROGS_EXTENDED := with_addr.sh \
TEST_GEN_PROGS_EXTENDED = test_sock_addr test_skb_cgroup_id_user \
flow_dissector_load test_flow_dissector test_tcp_check_syncookie_user \
test_lirc_mode2_user xdping test_cpp runqslower bench bpf_testmod.ko \
- xdpxceiver
+ xdpxceiver xdp_redirect_multi
TEST_CUSTOM_PROGS = $(OUTPUT)/urandom_read
diff --git a/tools/testing/selftests/bpf/progs/xdp_redirect_multi_kern.c b/tools/testing/selftests/bpf/progs/xdp_redirect_multi_kern.c
new file mode 100644
index 000000000000..099bf444acab
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/xdp_redirect_multi_kern.c
@@ -0,0 +1,99 @@
+// SPDX-License-Identifier: GPL-2.0
+#define KBUILD_MODNAME "foo"
+#include <string.h>
+#include <linux/in.h>
+#include <linux/if_ether.h>
+#include <linux/if_packet.h>
+#include <linux/ip.h>
+#include <linux/ipv6.h>
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
+
+/* It would be easier to use a key:if_index, value:if_index map, but it
+ * will need a very large entries as the if_index number may get very large,
+ * this would affect the performace. So the DEVMAP here is just for testing.
+ */
+struct {
+ __uint(type, BPF_MAP_TYPE_DEVMAP);
+ __uint(key_size, sizeof(int));
+ __uint(value_size, sizeof(int));
+ __uint(max_entries, 1024);
+} map_v4 SEC(".maps");
+
+struct {
+ __uint(type, BPF_MAP_TYPE_DEVMAP_HASH);
+ __uint(key_size, sizeof(int));
+ __uint(value_size, sizeof(int));
+ __uint(max_entries, 128);
+} map_all SEC(".maps");
+
+struct {
+ __uint(type, BPF_MAP_TYPE_DEVMAP_HASH);
+ __uint(key_size, sizeof(int));
+ __uint(value_size, sizeof(struct bpf_devmap_val));
+ __uint(max_entries, 128);
+} map_egress SEC(".maps");
+
+/* map to store egress interfaces mac addresses */
+struct {
+ __uint(type, BPF_MAP_TYPE_HASH);
+ __type(key, __u32);
+ __type(value, __be64);
+ __uint(max_entries, 128);
+} mac_map SEC(".maps");
+
+SEC("xdp_redirect_map_multi")
+int xdp_redirect_map_multi_prog(struct xdp_md *ctx)
+{
+ void *data_end = (void *)(long)ctx->data_end;
+ void *data = (void *)(long)ctx->data;
+ int if_index = ctx->ingress_ifindex;
+ struct ethhdr *eth = data;
+ __u16 h_proto;
+ __u64 nh_off;
+
+ nh_off = sizeof(*eth);
+ if (data + nh_off > data_end)
+ return XDP_DROP;
+
+ h_proto = eth->h_proto;
+
+ if (h_proto == bpf_htons(ETH_P_IP))
+ return bpf_redirect_map(&map_v4, 0, BPF_F_REDIR_MASK);
+ else if (h_proto == bpf_htons(ETH_P_IPV6))
+ return bpf_redirect_map(&map_all, if_index, 0);
+ else
+ return bpf_redirect_map(&map_all, 0, BPF_F_REDIR_MASK);
+}
+
+/* The following 2 progs are for 2nd devmap prog testing */
+SEC("xdp_redirect_map_ingress")
+int xdp_redirect_map_all_prog(struct xdp_md *ctx)
+{
+ return bpf_redirect_map(&map_egress, 0, BPF_F_REDIR_MASK);
+}
+
+SEC("xdp_devmap/map_prog")
+int xdp_devmap_prog(struct xdp_md *ctx)
+{
+ void *data_end = (void *)(long)ctx->data_end;
+ void *data = (void *)(long)ctx->data;
+ __u32 key = ctx->egress_ifindex;
+ struct ethhdr *eth = data;
+ __u64 nh_off;
+ __be64 *mac;
+
+ nh_off = sizeof(*eth);
+ if (data + nh_off > data_end)
+ return XDP_DROP;
+
+ mac = bpf_map_lookup_elem(&mac_map, &key);
+ if (mac)
+ __builtin_memcpy(eth->h_source, mac, ETH_ALEN);
+
+ return XDP_PASS;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/test_xdp_redirect_multi.sh b/tools/testing/selftests/bpf/test_xdp_redirect_multi.sh
new file mode 100755
index 000000000000..414f331823d2
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_xdp_redirect_multi.sh
@@ -0,0 +1,205 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# Test topology:
+# - - - - - - - - - - - - - - - - - - - - - - - - -
+# | veth1 veth2 veth3 veth4 | ... init net
+# - -| - - - - - - | - - - - - - | - - - - - - | - -
+# --------- --------- --------- ---------
+# | veth0 | | veth0 | | veth0 | | veth0 | ...
+# --------- --------- --------- ---------
+# ns1 ns2 ns3 ns4
+#
+# Forward maps:
+# map_all has interfaces: veth1, veth2, veth3, veth4, ... (All traffic except IPv4)
+# map_v4 has interfaces: veth1, veth3, veth4, ... (For IPv4 traffic only)
+# map_egress has all interfaces and redirect all pkts
+# Map type:
+# map_v4 use DEVMAP, others use DEVMAP_HASH
+#
+# Test modules:
+# XDP modes: generic, native, native + egress_prog
+#
+# Test cases:
+# ARP:
+# ns1 -> gw: ns2, ns3, ns4 should receive the arp request
+# IPv4:
+# ping test: ns1 -> ns2 (block), ns1 -> ns3 (pass), ns1 -> ns4 (pass)
+# IPv6:
+# ping test: ns1 -> ns2 (block), echo requests will be redirect back
+# egress_prog:
+# all src mac should be egress interface's mac
+#
+
+
+# netns numbers
+NUM=4
+IFACES=""
+DRV_MODE="xdpgeneric xdpdrv xdpegress"
+PASS=0
+FAIL=0
+
+test_pass()
+{
+ echo "Pass: $@"
+ PASS=$((PASS + 1))
+}
+
+test_fail()
+{
+ echo "fail: $@"
+ FAIL=$((FAIL + 1))
+}
+
+clean_up()
+{
+ for i in $(seq $NUM); do
+ ip link del veth$i 2> /dev/null
+ ip netns del ns$i 2> /dev/null
+ done
+}
+
+# Kselftest framework requirement - SKIP code is 4.
+check_env()
+{
+ ip link set dev lo xdpgeneric off &>/dev/null
+ if [ $? -ne 0 ];then
+ echo "selftests: [SKIP] Could not run test without the ip xdpgeneric support"
+ exit 4
+ fi
+
+ which tcpdump &>/dev/null
+ if [ $? -ne 0 ];then
+ echo "selftests: [SKIP] Could not run test without tcpdump"
+ exit 4
+ fi
+}
+
+setup_ns()
+{
+ local mode=$1
+ IFACES=""
+
+ if [ "$mode" = "xdpegress" ]; then
+ mode="xdpdrv"
+ fi
+
+ for i in $(seq $NUM); do
+ ip netns add ns$i
+ ip link add veth$i type veth peer name veth0 netns ns$i
+ ip link set veth$i up
+ ip -n ns$i link set veth0 up
+
+ ip -n ns$i addr add 192.0.2.$i/24 dev veth0
+ ip -n ns$i addr add 2001:db8::$i/64 dev veth0
+ ip -n ns$i link set veth0 $mode obj \
+ xdp_dummy.o sec xdp_dummy &> /dev/null || \
+ { test_fail "Unable to load dummy xdp" && exit 1; }
+ IFACES="$IFACES veth$i"
+ veth_mac[$i]=$(ip link show veth$i | awk '/link\/ether/ {print $2}')
+ done
+}
+
+do_egress_tests()
+{
+ local mode=$1
+
+ # mac test
+ ip netns exec ns2 tcpdump -e -i veth0 -nn -l -e &> mac_ns1-2_${mode}.log &
+ ip netns exec ns3 tcpdump -e -i veth0 -nn -l -e &> mac_ns1-3_${mode}.log &
+ ip netns exec ns4 tcpdump -e -i veth0 -nn -l -e &> mac_ns1-4_${mode}.log &
+ ip netns exec ns1 ping 192.0.2.254 -c 4 &> /dev/null
+ sleep 2
+ pkill -9 tcpdump
+
+ # mac check
+ grep -q "${veth_mac[2]} > ff:ff:ff:ff:ff:ff" mac_ns1-2_${mode}.log && \
+ test_pass "$mode mac ns1-2" || test_fail "$mode mac ns1-2"
+ grep -q "${veth_mac[3]} > ff:ff:ff:ff:ff:ff" mac_ns1-3_${mode}.log && \
+ test_pass "$mode mac ns1-3" || test_fail "$mode mac ns1-3"
+ grep -q "${veth_mac[4]} > ff:ff:ff:ff:ff:ff" mac_ns1-4_${mode}.log && \
+ test_pass "$mode mac ns1-4" || test_fail "$mode mac ns1-4"
+}
+
+do_ping_tests()
+{
+ local mode=$1
+
+ # arp test
+ ip netns exec ns2 tcpdump -i veth0 -nn -l -e &> arp_ns1-2_${mode}.log &
+ ip netns exec ns3 tcpdump -i veth0 -nn -l -e &> arp_ns1-3_${mode}.log &
+ ip netns exec ns4 tcpdump -i veth0 -nn -l -e &> arp_ns1-4_${mode}.log &
+ ip netns exec ns1 ping 192.0.2.254 -c 4 &> /dev/null
+ sleep 2
+ pkill -9 tcpdump
+ grep -q "Request who-has 192.0.2.254 tell 192.0.2.1" arp_ns1-2_${mode}.log && \
+ test_pass "$mode arp ns1-2" || test_fail "$mode arp ns1-2"
+ grep -q "Request who-has 192.0.2.254 tell 192.0.2.1" arp_ns1-3_${mode}.log && \
+ test_pass "$mode arp ns1-3" || test_fail "$mode arp ns1-3"
+ grep -q "Request who-has 192.0.2.254 tell 192.0.2.1" arp_ns1-4_${mode}.log && \
+ test_pass "$mode arp ns1-4" || test_fail "$mode arp ns1-4"
+
+ # ping test
+ ip netns exec ns1 ping 192.0.2.2 -c 4 &> /dev/null && \
+ test_fail "$mode ping ns1-2" || test_pass "$mode ping ns1-2"
+ ip netns exec ns1 ping 192.0.2.3 -c 4 &> /dev/null && \
+ test_pass "$mode ping ns1-3" || test_fail "$mode ping ns1-3"
+ ip netns exec ns1 ping 192.0.2.4 -c 4 &> /dev/null && \
+ test_pass "$mode ping ns1-4" || test_fail "$mode ping ns1-4"
+
+ # ping6 test: echo request should be redirect back to itself, not others
+ ip netns exec ns1 ip neigh add 2001:db8::2 dev veth0 lladdr 00:00:00:00:00:02
+ ip netns exec ns1 tcpdump -i veth0 -nn -l &> ping6_ns1_${mode}.log &
+ ip netns exec ns2 tcpdump -i veth0 -nn -l &> ping6_ns2_${mode}.log &
+ sleep 2
+ ip netns exec ns1 ping6 2001:db8::2 -c 2 &> /dev/null && \
+ test_fail "$mode ping6 ns1-2" || test_pass "$mode ping6 ns1-2"
+ sleep 2
+ pkill -9 tcpdump
+ ns1_echo_num=$(grep "ICMP6, echo request" ping6_ns1_${mode}.log | wc -l)
+ [ $ns1_echo_num -eq 4 ] && test_pass "$mode ping6 ns1-1 number" || \
+ test_fail "$mode ping6 ns1-1 number"
+ ns2_echo_num=$(grep "ICMP6, echo request" ping6_ns2_${mode}.log | wc -l)
+ [ $ns2_echo_num -eq 0 ] && test_pass "$mode ping6 ns1-2 number" || \
+ test_fail "$mode ping6 ns1-2 number"
+}
+
+do_tests()
+{
+ local mode=$1
+ local drv_p
+
+ case ${mode} in
+ xdpdrv) drv_p="-N";;
+ xdpegress) drv_p="-X";;
+ xdpgeneric) drv_p="-S";;
+ esac
+
+ ./xdp_redirect_multi $drv_p $IFACES &> xdp_redirect_${mode}.log &
+ xdp_pid=$!
+ sleep 10
+
+ if [ "$mode" = "xdpegress" ]; then
+ do_egress_tests $mode
+ else
+ do_ping_tests $mode
+ fi
+
+ kill $xdp_pid
+}
+
+trap clean_up 0 2 3 6 9
+
+check_env
+rm -f xdp_redirect_*.log arp_ns*.log ping6_ns*.log mac_ns*.log
+
+for mode in ${DRV_MODE}; do
+ setup_ns $mode
+ do_tests $mode
+ sleep 10
+ clean_up
+ sleep 5
+done
+
+echo "Summary: PASS $PASS, FAIL $FAIL"
+[ $FAIL -eq 0 ] && exit 0 || exit 1
diff --git a/tools/testing/selftests/bpf/xdp_redirect_multi.c b/tools/testing/selftests/bpf/xdp_redirect_multi.c
new file mode 100644
index 000000000000..6a282dde90bd
--- /dev/null
+++ b/tools/testing/selftests/bpf/xdp_redirect_multi.c
@@ -0,0 +1,236 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/bpf.h>
+#include <linux/if_link.h>
+#include <assert.h>
+#include <errno.h>
+#include <signal.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <net/if.h>
+#include <unistd.h>
+#include <libgen.h>
+#include <sys/resource.h>
+#include <sys/ioctl.h>
+#include <sys/types.h>
+#include <sys/socket.h>
+#include <netinet/in.h>
+
+#include "bpf_util.h"
+#include <bpf/bpf.h>
+#include <bpf/libbpf.h>
+
+#define MAX_IFACE_NUM 32
+#define MAX_INDEX_NUM 1024
+
+static __u32 xdp_flags = XDP_FLAGS_UPDATE_IF_NOEXIST;
+static int ifaces[MAX_IFACE_NUM] = {};
+
+static void int_exit(int sig)
+{
+ __u32 prog_id = 0;
+ int i;
+
+ for (i = 0; ifaces[i] > 0; i++) {
+ if (bpf_get_link_xdp_id(ifaces[i], &prog_id, xdp_flags)) {
+ printf("bpf_get_link_xdp_id failed\n");
+ exit(1);
+ }
+ if (prog_id)
+ bpf_set_link_xdp_fd(ifaces[i], -1, xdp_flags);
+ }
+
+ exit(0);
+}
+
+static int get_mac_addr(unsigned int ifindex, void *mac_addr)
+{
+ char ifname[IF_NAMESIZE];
+ struct ifreq ifr;
+ int fd, ret = -1;
+
+ fd = socket(AF_INET, SOCK_DGRAM, 0);
+ if (fd < 0)
+ return ret;
+
+ if (!if_indextoname(ifindex, ifname))
+ goto err_out;
+
+ strcpy(ifr.ifr_name, ifname);
+
+ if (ioctl(fd, SIOCGIFHWADDR, &ifr) != 0)
+ goto err_out;
+
+ memcpy(mac_addr, ifr.ifr_hwaddr.sa_data, 6 * sizeof(char));
+ ret = 0;
+
+err_out:
+ close(fd);
+ return ret;
+}
+
+static void usage(const char *prog)
+{
+ fprintf(stderr,
+ "usage: %s [OPTS] <IFNAME|IFINDEX> <IFNAME|IFINDEX> ...\n"
+ "OPTS:\n"
+ " -S use skb-mode\n"
+ " -N enforce native mode\n"
+ " -F force loading prog\n"
+ " -X load xdp program on egress\n",
+ prog);
+}
+
+int main(int argc, char **argv)
+{
+ int prog_fd, group_all, group_v4, mac_map;
+ struct bpf_program *ingress_prog, *egress_prog;
+ struct bpf_prog_load_attr prog_load_attr = {
+ .prog_type = BPF_PROG_TYPE_UNSPEC,
+ };
+ int i, ret, opt, egress_prog_fd = 0;
+ struct bpf_devmap_val devmap_val;
+ bool attach_egress_prog = false;
+ unsigned char mac_addr[6];
+ char ifname[IF_NAMESIZE];
+ struct bpf_object *obj;
+ unsigned int ifindex;
+ char filename[256];
+
+ while ((opt = getopt(argc, argv, "SNFX")) != -1) {
+ switch (opt) {
+ case 'S':
+ xdp_flags |= XDP_FLAGS_SKB_MODE;
+ break;
+ case 'N':
+ /* default, set below */
+ break;
+ case 'F':
+ xdp_flags &= ~XDP_FLAGS_UPDATE_IF_NOEXIST;
+ break;
+ case 'X':
+ attach_egress_prog = true;
+ break;
+ default:
+ usage(basename(argv[0]));
+ return 1;
+ }
+ }
+
+ if (!(xdp_flags & XDP_FLAGS_SKB_MODE)) {
+ xdp_flags |= XDP_FLAGS_DRV_MODE;
+ } else if (attach_egress_prog) {
+ printf("Load xdp program on egress with SKB mode not supported yet\n");
+ goto err_out;
+ }
+
+ if (optind == argc) {
+ printf("usage: %s <IFNAME|IFINDEX> <IFNAME|IFINDEX> ...\n", argv[0]);
+ goto err_out;
+ }
+
+ printf("Get interfaces");
+ for (i = 0; i < MAX_IFACE_NUM && argv[optind + i]; i++) {
+ ifaces[i] = if_nametoindex(argv[optind + i]);
+ if (!ifaces[i])
+ ifaces[i] = strtoul(argv[optind + i], NULL, 0);
+ if (!if_indextoname(ifaces[i], ifname)) {
+ perror("Invalid interface name or i");
+ goto err_out;
+ }
+ if (ifaces[i] > MAX_INDEX_NUM) {
+ printf("Interface index to large\n");
+ goto err_out;
+ }
+ printf(" %d", ifaces[i]);
+ }
+ printf("\n");
+
+ snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]);
+ prog_load_attr.file = filename;
+
+ if (bpf_prog_load_xattr(&prog_load_attr, &obj, &prog_fd))
+ goto err_out;
+
+ if (attach_egress_prog)
+ group_all = bpf_object__find_map_fd_by_name(obj, "map_egress");
+ else
+ group_all = bpf_object__find_map_fd_by_name(obj, "map_all");
+ group_v4 = bpf_object__find_map_fd_by_name(obj, "map_v4");
+ mac_map = bpf_object__find_map_fd_by_name(obj, "mac_map");
+
+ if (group_all < 0 || group_v4 < 0 || mac_map < 0) {
+ printf("bpf_object__find_map_fd_by_name failed\n");
+ goto err_out;
+ }
+
+ if (attach_egress_prog) {
+ /* Find ingress/egress prog for 2nd xdp prog */
+ ingress_prog = bpf_object__find_program_by_name(obj, "xdp_redirect_map_all_prog");
+ egress_prog = bpf_object__find_program_by_name(obj, "xdp_devmap_prog");
+ if (!ingress_prog || !egress_prog) {
+ printf("finding ingress/egress_prog in obj file failed\n");
+ goto err_out;
+ }
+ prog_fd = bpf_program__fd(ingress_prog);
+ egress_prog_fd = bpf_program__fd(egress_prog);
+ if (prog_fd < 0 || egress_prog_fd < 0) {
+ printf("find egress_prog fd failed\n");
+ goto err_out;
+ }
+ }
+
+ signal(SIGINT, int_exit);
+ signal(SIGTERM, int_exit);
+
+ /* Init forward multicast groups and exclude group */
+ for (i = 0; ifaces[i] > 0; i++) {
+ ifindex = ifaces[i];
+
+ if (attach_egress_prog) {
+ ret = get_mac_addr(ifindex, mac_addr);
+ if (ret < 0) {
+ printf("get interface %d mac failed\n", ifindex);
+ goto err_out;
+ }
+ ret = bpf_map_update_elem(mac_map, &ifindex, mac_addr, 0);
+ if (ret) {
+ perror("bpf_update_elem mac_map failed\n");
+ goto err_out;
+ }
+ }
+
+ /* Add all the interfaces to group all */
+ devmap_val.ifindex = ifindex;
+ devmap_val.bpf_prog.fd = egress_prog_fd;
+ ret = bpf_map_update_elem(group_all, &ifindex, &devmap_val, 0);
+ if (ret) {
+ perror("bpf_map_update_elem");
+ goto err_out;
+ }
+
+ /* For testing: skip adding the 2nd interfaces to group v4 */
+ if (i != 1) {
+ ret = bpf_map_update_elem(group_v4, &ifindex, &ifindex, 0);
+ if (ret) {
+ perror("bpf_map_update_elem");
+ goto err_out;
+ }
+ }
+
+ /* bind prog_fd to each interface */
+ ret = bpf_set_link_xdp_fd(ifindex, prog_fd, xdp_flags);
+ if (ret) {
+ printf("Set xdp fd failed on %d\n", ifindex);
+ goto err_out;
+ }
+ }
+
+ /* sleep some time for testing */
+ sleep(999);
+
+ return 0;
+
+err_out:
+ return 1;
+}
--
2.26.3
^ permalink raw reply related [flat|nested] 15+ messages in thread