Merge branch 'bpf-big-map-entries'

Jakub Kicinski says:

====================
This series makes the control message parsing for interacting
with BPF maps more flexible.  Up until now we had a hard limit
in the ABI for key and value size to be 64B at most.  Using
TLV capability allows us to support large map entries.
====================

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>

7 files changed, 142 insertions, 22 deletions

diff --git a/drivers/net/ethernet/netronome/nfp/bpf/cmsg.c b/drivers/net/ethernet/netronome/nfp/bpf/cmsg.c
index 2572a4b91c7c..fdcd2bc98916 100644
--- a/drivers/net/ethernet/netronome/nfp/bpf/cmsg.c
+++ b/drivers/net/ethernet/netronome/nfp/bpf/cmsg.c
@@ -89,15 +89,32 @@ nfp_bpf_cmsg_alloc(struct nfp_app_bpf *bpf, unsigned int size)
 	return skb;
 }
 
+static unsigned int
+nfp_bpf_cmsg_map_req_size(struct nfp_app_bpf *bpf, unsigned int n)
+{
+	unsigned int size;
+
+	size = sizeof(struct cmsg_req_map_op);
+	size += (bpf->cmsg_key_sz + bpf->cmsg_val_sz) * n;
+
+	return size;
+}
+
 static struct sk_buff *
 nfp_bpf_cmsg_map_req_alloc(struct nfp_app_bpf *bpf, unsigned int n)
 {
+	return nfp_bpf_cmsg_alloc(bpf, nfp_bpf_cmsg_map_req_size(bpf, n));
+}
+
+static unsigned int
+nfp_bpf_cmsg_map_reply_size(struct nfp_app_bpf *bpf, unsigned int n)
+{
 	unsigned int size;
 
-	size = sizeof(struct cmsg_req_map_op);
-	size += sizeof(struct cmsg_key_value_pair) * n;
+	size = sizeof(struct cmsg_reply_map_op);
+	size += (bpf->cmsg_key_sz + bpf->cmsg_val_sz) * n;
 
-	return nfp_bpf_cmsg_alloc(bpf, size);
+	return size;
 }
 
 static u8 nfp_bpf_cmsg_get_type(struct sk_buff *skb)
@@ -338,6 +355,34 @@ void nfp_bpf_ctrl_free_map(struct nfp_app_bpf *bpf, struct nfp_bpf_map *nfp_map)
 	dev_consume_skb_any(skb);
 }
 
+static void *
+nfp_bpf_ctrl_req_key(struct nfp_app_bpf *bpf, struct cmsg_req_map_op *req,
+		     unsigned int n)
+{
+	return &req->data[bpf->cmsg_key_sz * n + bpf->cmsg_val_sz * n];
+}
+
+static void *
+nfp_bpf_ctrl_req_val(struct nfp_app_bpf *bpf, struct cmsg_req_map_op *req,
+		     unsigned int n)
+{
+	return &req->data[bpf->cmsg_key_sz * (n + 1) + bpf->cmsg_val_sz * n];
+}
+
+static void *
+nfp_bpf_ctrl_reply_key(struct nfp_app_bpf *bpf, struct cmsg_reply_map_op *reply,
+		       unsigned int n)
+{
+	return &reply->data[bpf->cmsg_key_sz * n + bpf->cmsg_val_sz * n];
+}
+
+static void *
+nfp_bpf_ctrl_reply_val(struct nfp_app_bpf *bpf, struct cmsg_reply_map_op *reply,
+		       unsigned int n)
+{
+	return &reply->data[bpf->cmsg_key_sz * (n + 1) + bpf->cmsg_val_sz * n];
+}
+
 static int
 nfp_bpf_ctrl_entry_op(struct bpf_offloaded_map *offmap,
 		      enum nfp_bpf_cmsg_type op,
@@ -366,12 +411,13 @@ nfp_bpf_ctrl_entry_op(struct bpf_offloaded_map *offmap,
 
 	/* Copy inputs */
 	if (key)
-		memcpy(&req->elem[0].key, key, map->key_size);
+		memcpy(nfp_bpf_ctrl_req_key(bpf, req, 0), key, map->key_size);
 	if (value)
-		memcpy(&req->elem[0].value, value, map->value_size);
+		memcpy(nfp_bpf_ctrl_req_val(bpf, req, 0), value,
+		       map->value_size);
 
 	skb = nfp_bpf_cmsg_communicate(bpf, skb, op,
-				       sizeof(*reply) + sizeof(*reply->elem));
+				       nfp_bpf_cmsg_map_reply_size(bpf, 1));
 	if (IS_ERR(skb))
 		return PTR_ERR(skb);
 
@@ -382,9 +428,11 @@ nfp_bpf_ctrl_entry_op(struct bpf_offloaded_map *offmap,
 
 	/* Copy outputs */
 	if (out_key)
-		memcpy(out_key, &reply->elem[0].key, map->key_size);
+		memcpy(out_key, nfp_bpf_ctrl_reply_key(bpf, reply, 0),
+		       map->key_size);
 	if (out_value)
-		memcpy(out_value, &reply->elem[0].value, map->value_size);
+		memcpy(out_value, nfp_bpf_ctrl_reply_val(bpf, reply, 0),
+		       map->value_size);
 
 	dev_consume_skb_any(skb);
 
@@ -428,6 +476,13 @@ int nfp_bpf_ctrl_getnext_entry(struct bpf_offloaded_map *offmap,
 				     key, NULL, 0, next_key, NULL);
 }
 
+unsigned int nfp_bpf_ctrl_cmsg_mtu(struct nfp_app_bpf *bpf)
+{
+	return max3((unsigned int)NFP_NET_DEFAULT_MTU,
+		    nfp_bpf_cmsg_map_req_size(bpf, 1),
+		    nfp_bpf_cmsg_map_reply_size(bpf, 1));
+}
+
 void nfp_bpf_ctrl_msg_rx(struct nfp_app *app, struct sk_buff *skb)
 {
 	struct nfp_app_bpf *bpf = app->priv;
diff --git a/drivers/net/ethernet/netronome/nfp/bpf/fw.h b/drivers/net/ethernet/netronome/nfp/bpf/fw.h
index e4f9b7ec8528..813644e90b27 100644
--- a/drivers/net/ethernet/netronome/nfp/bpf/fw.h
+++ b/drivers/net/ethernet/netronome/nfp/bpf/fw.h
@@ -52,6 +52,7 @@ enum bpf_cap_tlv_type {
 	NFP_BPF_CAP_TYPE_RANDOM		= 4,
 	NFP_BPF_CAP_TYPE_QUEUE_SELECT	= 5,
 	NFP_BPF_CAP_TYPE_ADJUST_TAIL	= 6,
+	NFP_BPF_CAP_TYPE_ABI_VERSION	= 7,
 };
 
 struct nfp_bpf_cap_tlv_func {
@@ -98,6 +99,7 @@ enum nfp_bpf_cmsg_type {
 #define CMSG_TYPE_MAP_REPLY_BIT		7
 #define __CMSG_REPLY(req)		(BIT(CMSG_TYPE_MAP_REPLY_BIT) | (req))
 
+/* BPF ABIv2 fixed-length control message fields */
 #define CMSG_MAP_KEY_LW			16
 #define CMSG_MAP_VALUE_LW		16
 
@@ -147,24 +149,19 @@ struct cmsg_reply_map_free_tbl {
 	__be32 count;
 };
 
-struct cmsg_key_value_pair {
-	__be32 key[CMSG_MAP_KEY_LW];
-	__be32 value[CMSG_MAP_VALUE_LW];
-};
-
 struct cmsg_req_map_op {
 	struct cmsg_hdr hdr;
 	__be32 tid;
 	__be32 count;
 	__be32 flags;
-	struct cmsg_key_value_pair elem[0];
+	u8 data[0];
 };
 
 struct cmsg_reply_map_op {
 	struct cmsg_reply_map_simple reply_hdr;
 	__be32 count;
 	__be32 resv;
-	struct cmsg_key_value_pair elem[0];
+	u8 data[0];
 };
 
 struct cmsg_bpf_event {
diff --git a/drivers/net/ethernet/netronome/nfp/bpf/main.c b/drivers/net/ethernet/netronome/nfp/bpf/main.c
index 970af07f4656..d9d37aa860e0 100644
--- a/drivers/net/ethernet/netronome/nfp/bpf/main.c
+++ b/drivers/net/ethernet/netronome/nfp/bpf/main.c
@@ -54,11 +54,14 @@ const struct rhashtable_params nfp_bpf_maps_neutral_params = {
 static bool nfp_net_ebpf_capable(struct nfp_net *nn)
 {
 #ifdef __LITTLE_ENDIAN
-	if (nn->cap & NFP_NET_CFG_CTRL_BPF &&
-	    nn_readb(nn, NFP_NET_CFG_BPF_ABI) == NFP_NET_BPF_ABI)
-		return true;
-#endif
+	struct nfp_app_bpf *bpf = nn->app->priv;
+
+	return nn->cap & NFP_NET_CFG_CTRL_BPF &&
+	       bpf->abi_version &&
+	       nn_readb(nn, NFP_NET_CFG_BPF_ABI) == bpf->abi_version;
+#else
 	return false;
+#endif
 }
 
 static int
@@ -342,6 +345,26 @@ nfp_bpf_parse_cap_adjust_tail(struct nfp_app_bpf *bpf, void __iomem *value,
 	return 0;
 }
 
+static int
+nfp_bpf_parse_cap_abi_version(struct nfp_app_bpf *bpf, void __iomem *value,
+			      u32 length)
+{
+	if (length < 4) {
+		nfp_err(bpf->app->cpp, "truncated ABI version TLV: %d\n",
+			length);
+		return -EINVAL;
+	}
+
+	bpf->abi_version = readl(value);
+	if (bpf->abi_version < 2 || bpf->abi_version > 3) {
+		nfp_warn(bpf->app->cpp, "unsupported BPF ABI version: %d\n",
+			 bpf->abi_version);
+		bpf->abi_version = 0;
+	}
+
+	return 0;
+}
+
 static int nfp_bpf_parse_capabilities(struct nfp_app *app)
 {
 	struct nfp_cpp *cpp = app->pf->cpp;
@@ -393,6 +416,11 @@ static int nfp_bpf_parse_capabilities(struct nfp_app *app)
 							  length))
 				goto err_release_free;
 			break;
+		case NFP_BPF_CAP_TYPE_ABI_VERSION:
+			if (nfp_bpf_parse_cap_abi_version(app->priv, value,
+							  length))
+				goto err_release_free;
+			break;
 		default:
 			nfp_dbg(cpp, "unknown BPF capability: %d\n", type);
 			break;
@@ -414,6 +442,11 @@ err_release_free:
 	return -EINVAL;
 }
 
+static void nfp_bpf_init_capabilities(struct nfp_app_bpf *bpf)
+{
+	bpf->abi_version = 2; /* Original BPF ABI version */
+}
+
 static int nfp_bpf_ndo_init(struct nfp_app *app, struct net_device *netdev)
 {
 	struct nfp_app_bpf *bpf = app->priv;
@@ -447,10 +480,21 @@ static int nfp_bpf_init(struct nfp_app *app)
 	if (err)
 		goto err_free_bpf;
 
+	nfp_bpf_init_capabilities(bpf);
+
 	err = nfp_bpf_parse_capabilities(app);
 	if (err)
 		goto err_free_neutral_maps;
 
+	if (bpf->abi_version < 3) {
+		bpf->cmsg_key_sz = CMSG_MAP_KEY_LW * 4;
+		bpf->cmsg_val_sz = CMSG_MAP_VALUE_LW * 4;
+	} else {
+		bpf->cmsg_key_sz = bpf->maps.max_key_sz;
+		bpf->cmsg_val_sz = bpf->maps.max_val_sz;
+		app->ctrl_mtu = nfp_bpf_ctrl_cmsg_mtu(bpf);
+	}
+
 	bpf->bpf_dev = bpf_offload_dev_create();
 	err = PTR_ERR_OR_ZERO(bpf->bpf_dev);
 	if (err)
diff --git a/drivers/net/ethernet/netronome/nfp/bpf/main.h b/drivers/net/ethernet/netronome/nfp/bpf/main.h
index dbd00982fd2b..792ebc4081a3 100644
--- a/drivers/net/ethernet/netronome/nfp/bpf/main.h
+++ b/drivers/net/ethernet/netronome/nfp/bpf/main.h
@@ -121,12 +121,17 @@ enum pkt_vec {
  * @cmsg_replies:	received cmsg replies waiting to be consumed
  * @cmsg_wq:		work queue for waiting for cmsg replies
  *
+ * @cmsg_key_sz:	size of key in cmsg element array
+ * @cmsg_val_sz:	size of value in cmsg element array
+ *
  * @map_list:		list of offloaded maps
  * @maps_in_use:	number of currently offloaded maps
  * @map_elems_in_use:	number of elements allocated to offloaded maps
  *
  * @maps_neutral:	hash table of offload-neutral maps (on pointer)
  *
+ * @abi_version:	global BPF ABI version
+ *
  * @adjust_head:	adjust head capability
  * @adjust_head.flags:		extra flags for adjust head
  * @adjust_head.off_min:	minimal packet offset within buffer required
@@ -164,12 +169,17 @@ struct nfp_app_bpf {
 	struct sk_buff_head cmsg_replies;
 	struct wait_queue_head cmsg_wq;
 
+	unsigned int cmsg_key_sz;
+	unsigned int cmsg_val_sz;
+
 	struct list_head map_list;
 	unsigned int maps_in_use;
 	unsigned int map_elems_in_use;
 
 	struct rhashtable maps_neutral;
 
+	u32 abi_version;
+
 	struct nfp_bpf_cap_adjust_head {
 		u32 flags;
 		int off_min;
@@ -492,6 +502,7 @@ nfp_bpf_goto_meta(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta,
 
 void *nfp_bpf_relo_for_vnic(struct nfp_prog *nfp_prog, struct nfp_bpf_vnic *bv);
 
+unsigned int nfp_bpf_ctrl_cmsg_mtu(struct nfp_app_bpf *bpf);
 long long int
 nfp_bpf_ctrl_alloc_map(struct nfp_app_bpf *bpf, struct bpf_map *map);
 void
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_app.h b/drivers/net/ethernet/netronome/nfp/nfp_app.h
index 4e1eb3395648..c896eb8f87a1 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_app.h
+++ b/drivers/net/ethernet/netronome/nfp/nfp_app.h
@@ -40,6 +40,8 @@
 
 #include "nfp_net_repr.h"
 
+#define NFP_APP_CTRL_MTU_MAX	U32_MAX
+
 struct bpf_prog;
 struct net_device;
 struct netdev_bpf;
@@ -178,6 +180,7 @@ struct nfp_app_type {
  * @ctrl:	pointer to ctrl vNIC struct
  * @reprs:	array of pointers to representors
  * @type:	pointer to const application ops and info
+ * @ctrl_mtu:	MTU to set on the control vNIC (set in .init())
  * @priv:	app-specific priv data
  */
 struct nfp_app {
@@ -189,6 +192,7 @@ struct nfp_app {
 	struct nfp_reprs __rcu *reprs[NFP_REPR_TYPE_MAX + 1];
 
 	const struct nfp_app_type *type;
+	unsigned int ctrl_mtu;
 	void *priv;
 };
 
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
index d05e37fcc1b2..8e8dc0db2493 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
@@ -3877,10 +3877,20 @@ int nfp_net_init(struct nfp_net *nn)
 		return err;
 
 	/* Set default MTU and Freelist buffer size */
-	if (nn->max_mtu < NFP_NET_DEFAULT_MTU)
+	if (!nfp_net_is_data_vnic(nn) && nn->app->ctrl_mtu) {
+		if (nn->app->ctrl_mtu <= nn->max_mtu) {
+			nn->dp.mtu = nn->app->ctrl_mtu;
+		} else {
+			if (nn->app->ctrl_mtu != NFP_APP_CTRL_MTU_MAX)
+				nn_warn(nn, "app requested MTU above max supported %u > %u\n",
+					nn->app->ctrl_mtu, nn->max_mtu);
+			nn->dp.mtu = nn->max_mtu;
+		}
+	} else if (nn->max_mtu < NFP_NET_DEFAULT_MTU) {
 		nn->dp.mtu = nn->max_mtu;
-	else
+	} else {
 		nn->dp.mtu = NFP_NET_DEFAULT_MTU;
+	}
 	nn->dp.fl_bufsz = nfp_net_calc_fl_bufsz(&nn->dp);
 
 	if (nfp_app_ctrl_uses_data_vnics(nn->app))
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_ctrl.h b/drivers/net/ethernet/netronome/nfp/nfp_net_ctrl.h
index 44d3ea75d043..4c6fb9ecb72c 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_ctrl.h
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_ctrl.h
@@ -264,7 +264,6 @@
  * %NFP_NET_CFG_BPF_ADDR:	DMA address of the buffer with JITed BPF code
  */
 #define NFP_NET_CFG_BPF_ABI		0x0080
-#define   NFP_NET_BPF_ABI		2
 #define NFP_NET_CFG_BPF_CAP		0x0081
 #define   NFP_NET_BPF_CAP_RELO		(1 << 0) /* seamless reload */
 #define NFP_NET_CFG_BPF_MAX_LEN		0x0082