Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next

Pull networking updates from David Miller:

 1) Significantly shrink the core networking routing structures. Result
    of http://vger.kernel.org/~davem/seoul2017_netdev_keynote.pdf

 2) Add netdevsim driver for testing various offloads, from Jakub
    Kicinski.

 3) Support cross-chip FDB operations in DSA, from Vivien Didelot.

 4) Add a 2nd listener hash table for TCP, similar to what was done for
    UDP. From Martin KaFai Lau.

 5) Add eBPF based queue selection to tun, from Jason Wang.

 6) Lockless qdisc support, from John Fastabend.

 7) SCTP stream interleave support, from Xin Long.

 8) Smoother TCP receive autotuning, from Eric Dumazet.

 9) Lots of erspan tunneling enhancements, from William Tu.

10) Add true function call support to BPF, from Alexei Starovoitov.

11) Add explicit support for GRO HW offloading, from Michael Chan.

12) Support extack generation in more netlink subsystems. From Alexander
    Aring, Quentin Monnet, and Jakub Kicinski.

13) Add 1000BaseX, flow control, and EEE support to mvneta driver. From
    Russell King.

14) Add flow table abstraction to netfilter, from Pablo Neira Ayuso.

15) Many improvements and simplifications to the NFP driver bpf JIT,
    from Jakub Kicinski.

16) Support for ipv6 non-equal cost multipath routing, from Ido
    Schimmel.

17) Add resource abstration to devlink, from Arkadi Sharshevsky.

18) Packet scheduler classifier shared filter block support, from Jiri
    Pirko.

19) Avoid locking in act_csum, from Davide Caratti.

20) devinet_ioctl() simplifications from Al viro.

21) More TCP bpf improvements from Lawrence Brakmo.

22) Add support for onlink ipv6 route flag, similar to ipv4, from David
    Ahern.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1925 commits)
  tls: Add support for encryption using async offload accelerator
  ip6mr: fix stale iterator
  net/sched: kconfig: Remove blank help texts
  openvswitch: meter: Use 64-bit arithmetic instead of 32-bit
  tcp_nv: fix potential integer overflow in tcpnv_acked
  r8169: fix RTL8168EP take too long to complete driver initialization.
  qmi_wwan: Add support for Quectel EP06
  rtnetlink: enable IFLA_IF_NETNSID for RTM_NEWLINK
  ipmr: Fix ptrdiff_t print formatting
  ibmvnic: Wait for device response when changing MAC
  qlcnic: fix deadlock bug
  tcp: release sk_frag.page in tcp_disconnect
  ipv4: Get the address of interface correctly.
  net_sched: gen_estimator: fix lockdep splat
  net: macb: Handle HRESP error
  net/mlx5e: IPoIB, Fix copy-paste bug in flow steering refactoring
  ipv6: addrconf: break critical section in addrconf_verify_rtnl()
  ipv6: change route cache aging logic
  i40e/i40evf: Update DESC_NEEDED value to reflect larger value
  bnxt_en: cleanup DIM work on device shutdown
  ...

1 files changed, 170 insertions, 28 deletions

diff --git a/drivers/net/ethernet/netronome/nfp/bpf/offload.c b/drivers/net/ethernet/netronome/nfp/bpf/offload.c
index bc879ae..0a77323 100644
--- a/drivers/net/ethernet/netronome/nfp/bpf/offload.c
+++ b/drivers/net/ethernet/netronome/nfp/bpf/offload.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2016 Netronome Systems, Inc.
+ * Copyright (C) 2016-2017 Netronome Systems, Inc.
  *
  * This software is dual licensed under the GNU General License Version 2,
  * June 1991 as shown in the file COPYING in the top-level directory of this
@@ -36,18 +36,23 @@
  * Netronome network device driver: TC offload functions for PF and VF
  */
 
+#define pr_fmt(fmt)	"NFP net bpf: " fmt
+
+#include <linux/bpf.h>
 #include <linux/kernel.h>
 #include <linux/netdevice.h>
 #include <linux/pci.h>
 #include <linux/jiffies.h>
 #include <linux/timer.h>
 #include <linux/list.h>
+#include <linux/mm.h>
 
 #include <net/pkt_cls.h>
 #include <net/tc_act/tc_gact.h>
 #include <net/tc_act/tc_mirred.h>
 
 #include "main.h"
+#include "../nfp_app.h"
 #include "../nfp_net_ctrl.h"
 #include "../nfp_net.h"
 
@@ -55,11 +60,10 @@ static int
 nfp_prog_prepare(struct nfp_prog *nfp_prog, const struct bpf_insn *prog,
 		 unsigned int cnt)
 {
+	struct nfp_insn_meta *meta;
 	unsigned int i;
 
 	for (i = 0; i < cnt; i++) {
-		struct nfp_insn_meta *meta;
-
 		meta = kzalloc(sizeof(*meta), GFP_KERNEL);
 		if (!meta)
 			return -ENOMEM;
@@ -70,6 +74,8 @@ nfp_prog_prepare(struct nfp_prog *nfp_prog, const struct bpf_insn *prog,
 		list_add_tail(&meta->l, &nfp_prog->insns);
 	}
 
+	nfp_bpf_jit_prepare(nfp_prog, cnt);
+
 	return 0;
 }
 
@@ -84,8 +90,9 @@ static void nfp_prog_free(struct nfp_prog *nfp_prog)
 	kfree(nfp_prog);
 }
 
-int nfp_bpf_verifier_prep(struct nfp_app *app, struct nfp_net *nn,
-			  struct netdev_bpf *bpf)
+static int
+nfp_bpf_verifier_prep(struct nfp_app *app, struct nfp_net *nn,
+		      struct netdev_bpf *bpf)
 {
 	struct bpf_prog *prog = bpf->verifier.prog;
 	struct nfp_prog *nfp_prog;
@@ -98,6 +105,7 @@ int nfp_bpf_verifier_prep(struct nfp_app *app, struct nfp_net *nn,
 
 	INIT_LIST_HEAD(&nfp_prog->insns);
 	nfp_prog->type = prog->type;
+	nfp_prog->bpf = app->priv;
 
 	ret = nfp_prog_prepare(nfp_prog, prog->insnsi, prog->len);
 	if (ret)
@@ -114,12 +122,12 @@ err_free:
 	return ret;
 }
 
-int nfp_bpf_translate(struct nfp_app *app, struct nfp_net *nn,
-		      struct bpf_prog *prog)
+static int nfp_bpf_translate(struct nfp_net *nn, struct bpf_prog *prog)
 {
 	struct nfp_prog *nfp_prog = prog->aux->offload->dev_priv;
 	unsigned int stack_size;
 	unsigned int max_instr;
+	int err;
 
 	stack_size = nn_readb(nn, NFP_NET_CFG_BPF_STACK_SZ) * 64;
 	if (prog->aux->stack_depth > stack_size) {
@@ -127,50 +135,179 @@ int nfp_bpf_translate(struct nfp_app *app, struct nfp_net *nn,
 			prog->aux->stack_depth, stack_size);
 		return -EOPNOTSUPP;
 	}
-
-	nfp_prog->stack_depth = prog->aux->stack_depth;
-	nfp_prog->start_off = nn_readw(nn, NFP_NET_CFG_BPF_START);
-	nfp_prog->tgt_done = nn_readw(nn, NFP_NET_CFG_BPF_DONE);
+	nfp_prog->stack_depth = round_up(prog->aux->stack_depth, 4);
 
 	max_instr = nn_readw(nn, NFP_NET_CFG_BPF_MAX_LEN);
 	nfp_prog->__prog_alloc_len = max_instr * sizeof(u64);
 
-	nfp_prog->prog = kmalloc(nfp_prog->__prog_alloc_len, GFP_KERNEL);
+	nfp_prog->prog = kvmalloc(nfp_prog->__prog_alloc_len, GFP_KERNEL);
 	if (!nfp_prog->prog)
 		return -ENOMEM;
 
-	return nfp_bpf_jit(nfp_prog);
+	err = nfp_bpf_jit(nfp_prog);
+	if (err)
+		return err;
+
+	prog->aux->offload->jited_len = nfp_prog->prog_len * sizeof(u64);
+	prog->aux->offload->jited_image = nfp_prog->prog;
+
+	return 0;
 }
 
-int nfp_bpf_destroy(struct nfp_app *app, struct nfp_net *nn,
-		    struct bpf_prog *prog)
+static int nfp_bpf_destroy(struct nfp_net *nn, struct bpf_prog *prog)
 {
 	struct nfp_prog *nfp_prog = prog->aux->offload->dev_priv;
 
-	kfree(nfp_prog->prog);
+	kvfree(nfp_prog->prog);
 	nfp_prog_free(nfp_prog);
 
 	return 0;
 }
 
-static int nfp_net_bpf_load(struct nfp_net *nn, struct bpf_prog *prog)
+static int
+nfp_bpf_map_get_next_key(struct bpf_offloaded_map *offmap,
+			 void *key, void *next_key)
+{
+	if (!key)
+		return nfp_bpf_ctrl_getfirst_entry(offmap, next_key);
+	return nfp_bpf_ctrl_getnext_entry(offmap, key, next_key);
+}
+
+static int
+nfp_bpf_map_delete_elem(struct bpf_offloaded_map *offmap, void *key)
+{
+	if (offmap->map.map_type == BPF_MAP_TYPE_ARRAY)
+		return -EINVAL;
+	return nfp_bpf_ctrl_del_entry(offmap, key);
+}
+
+static const struct bpf_map_dev_ops nfp_bpf_map_ops = {
+	.map_get_next_key	= nfp_bpf_map_get_next_key,
+	.map_lookup_elem	= nfp_bpf_ctrl_lookup_entry,
+	.map_update_elem	= nfp_bpf_ctrl_update_entry,
+	.map_delete_elem	= nfp_bpf_map_delete_elem,
+};
+
+static int
+nfp_bpf_map_alloc(struct nfp_app_bpf *bpf, struct bpf_offloaded_map *offmap)
+{
+	struct nfp_bpf_map *nfp_map;
+	long long int res;
+
+	if (!bpf->maps.types)
+		return -EOPNOTSUPP;
+
+	if (offmap->map.map_flags ||
+	    offmap->map.numa_node != NUMA_NO_NODE) {
+		pr_info("map flags are not supported\n");
+		return -EINVAL;
+	}
+
+	if (!(bpf->maps.types & 1 << offmap->map.map_type)) {
+		pr_info("map type not supported\n");
+		return -EOPNOTSUPP;
+	}
+	if (bpf->maps.max_maps == bpf->maps_in_use) {
+		pr_info("too many maps for a device\n");
+		return -ENOMEM;
+	}
+	if (bpf->maps.max_elems - bpf->map_elems_in_use <
+	    offmap->map.max_entries) {
+		pr_info("map with too many elements: %u, left: %u\n",
+			offmap->map.max_entries,
+			bpf->maps.max_elems - bpf->map_elems_in_use);
+		return -ENOMEM;
+	}
+	if (offmap->map.key_size > bpf->maps.max_key_sz ||
+	    offmap->map.value_size > bpf->maps.max_val_sz ||
+	    round_up(offmap->map.key_size, 8) +
+	    round_up(offmap->map.value_size, 8) > bpf->maps.max_elem_sz) {
+		pr_info("elements don't fit in device constraints\n");
+		return -ENOMEM;
+	}
+
+	nfp_map = kzalloc(sizeof(*nfp_map), GFP_USER);
+	if (!nfp_map)
+		return -ENOMEM;
+
+	offmap->dev_priv = nfp_map;
+	nfp_map->offmap = offmap;
+	nfp_map->bpf = bpf;
+
+	res = nfp_bpf_ctrl_alloc_map(bpf, &offmap->map);
+	if (res < 0) {
+		kfree(nfp_map);
+		return res;
+	}
+
+	nfp_map->tid = res;
+	offmap->dev_ops = &nfp_bpf_map_ops;
+	bpf->maps_in_use++;
+	bpf->map_elems_in_use += offmap->map.max_entries;
+	list_add_tail(&nfp_map->l, &bpf->map_list);
+
+	return 0;
+}
+
+static int
+nfp_bpf_map_free(struct nfp_app_bpf *bpf, struct bpf_offloaded_map *offmap)
+{
+	struct nfp_bpf_map *nfp_map = offmap->dev_priv;
+
+	nfp_bpf_ctrl_free_map(bpf, nfp_map);
+	list_del_init(&nfp_map->l);
+	bpf->map_elems_in_use -= offmap->map.max_entries;
+	bpf->maps_in_use--;
+	kfree(nfp_map);
+
+	return 0;
+}
+
+int nfp_ndo_bpf(struct nfp_app *app, struct nfp_net *nn, struct netdev_bpf *bpf)
+{
+	switch (bpf->command) {
+	case BPF_OFFLOAD_VERIFIER_PREP:
+		return nfp_bpf_verifier_prep(app, nn, bpf);
+	case BPF_OFFLOAD_TRANSLATE:
+		return nfp_bpf_translate(nn, bpf->offload.prog);
+	case BPF_OFFLOAD_DESTROY:
+		return nfp_bpf_destroy(nn, bpf->offload.prog);
+	case BPF_OFFLOAD_MAP_ALLOC:
+		return nfp_bpf_map_alloc(app->priv, bpf->offmap);
+	case BPF_OFFLOAD_MAP_FREE:
+		return nfp_bpf_map_free(app->priv, bpf->offmap);
+	default:
+		return -EINVAL;
+	}
+}
+
+static int
+nfp_net_bpf_load(struct nfp_net *nn, struct bpf_prog *prog,
+		 struct netlink_ext_ack *extack)
 {
 	struct nfp_prog *nfp_prog = prog->aux->offload->dev_priv;
 	unsigned int max_mtu;
 	dma_addr_t dma_addr;
+	void *img;
 	int err;
 
 	max_mtu = nn_readb(nn, NFP_NET_CFG_BPF_INL_MTU) * 64 - 32;
 	if (max_mtu < nn->dp.netdev->mtu) {
-		nn_info(nn, "BPF offload not supported with MTU larger than HW packet split boundary\n");
+		NL_SET_ERR_MSG_MOD(extack, "BPF offload not supported with MTU larger than HW packet split boundary");
 		return -EOPNOTSUPP;
 	}
 
-	dma_addr = dma_map_single(nn->dp.dev, nfp_prog->prog,
+	img = nfp_bpf_relo_for_vnic(nfp_prog, nn->app_priv);
+	if (IS_ERR(img))
+		return PTR_ERR(img);
+
+	dma_addr = dma_map_single(nn->dp.dev, img,
 				  nfp_prog->prog_len * sizeof(u64),
 				  DMA_TO_DEVICE);
-	if (dma_mapping_error(nn->dp.dev, dma_addr))
+	if (dma_mapping_error(nn->dp.dev, dma_addr)) {
+		kfree(img);
 		return -ENOMEM;
+	}
 
 	nn_writew(nn, NFP_NET_CFG_BPF_SIZE, nfp_prog->prog_len);
 	nn_writeq(nn, NFP_NET_CFG_BPF_ADDR, dma_addr);
@@ -178,15 +315,18 @@ static int nfp_net_bpf_load(struct nfp_net *nn, struct bpf_prog *prog)
 	/* Load up the JITed code */
 	err = nfp_net_reconfig(nn, NFP_NET_CFG_UPDATE_BPF);
 	if (err)
-		nn_err(nn, "FW command error while loading BPF: %d\n", err);
+		NL_SET_ERR_MSG_MOD(extack,
+				   "FW command error while loading BPF");
 
 	dma_unmap_single(nn->dp.dev, dma_addr, nfp_prog->prog_len * sizeof(u64),
 			 DMA_TO_DEVICE);
+	kfree(img);
 
 	return err;
 }
 
-static void nfp_net_bpf_start(struct nfp_net *nn)
+static void
+nfp_net_bpf_start(struct nfp_net *nn, struct netlink_ext_ack *extack)
 {
 	int err;
 
@@ -195,7 +335,8 @@ static void nfp_net_bpf_start(struct nfp_net *nn)
 	nn_writel(nn, NFP_NET_CFG_CTRL, nn->dp.ctrl);
 	err = nfp_net_reconfig(nn, NFP_NET_CFG_UPDATE_GEN);
 	if (err)
-		nn_err(nn, "FW command error while enabling BPF: %d\n", err);
+		NL_SET_ERR_MSG_MOD(extack,
+				   "FW command error while enabling BPF");
 }
 
 static int nfp_net_bpf_stop(struct nfp_net *nn)
@@ -210,12 +351,12 @@ static int nfp_net_bpf_stop(struct nfp_net *nn)
 }
 
 int nfp_net_bpf_offload(struct nfp_net *nn, struct bpf_prog *prog,
-			bool old_prog)
+			bool old_prog, struct netlink_ext_ack *extack)
 {
 	int err;
 
 	if (prog) {
-		struct bpf_dev_offload *offload = prog->aux->offload;
+		struct bpf_prog_offload *offload = prog->aux->offload;
 
 		if (!offload)
 			return -EINVAL;
@@ -228,7 +369,8 @@ int nfp_net_bpf_offload(struct nfp_net *nn, struct bpf_prog *prog,
 
 		cap = nn_readb(nn, NFP_NET_CFG_BPF_CAP);
 		if (!(cap & NFP_NET_BPF_CAP_RELO)) {
-			nn_err(nn, "FW does not support live reload\n");
+			NL_SET_ERR_MSG_MOD(extack,
+					   "FW does not support live reload");
 			return -EBUSY;
 		}
 	}
@@ -240,12 +382,12 @@ int nfp_net_bpf_offload(struct nfp_net *nn, struct bpf_prog *prog,
 	if (old_prog && !prog)
 		return nfp_net_bpf_stop(nn);
 
-	err = nfp_net_bpf_load(nn, prog);
+	err = nfp_net_bpf_load(nn, prog, extack);
 	if (err)
 		return err;
 
 	if (!old_prog)
-		nfp_net_bpf_start(nn);
+		nfp_net_bpf_start(nn, extack);
 
 	return 0;
 }