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

Pull networking updates from David Miller:

 1) Allow setting bluetooth L2CAP modes via socket option, from Luiz
    Augusto von Dentz.

 2) Add GSO partial support to igc, from Sasha Neftin.

 3) Several cleanups and improvements to r8169 from Heiner Kallweit.

 4) Add IF_OPER_TESTING link state and use it when ethtool triggers a
    device self-test. From Andrew Lunn.

 5) Start moving away from custom driver versions, use the globally
    defined kernel version instead, from Leon Romanovsky.

 6) Support GRO vis gro_cells in DSA layer, from Alexander Lobakin.

 7) Allow hard IRQ deferral during NAPI, from Eric Dumazet.

 8) Add sriov and vf support to hinic, from Luo bin.

 9) Support Media Redundancy Protocol (MRP) in the bridging code, from
    Horatiu Vultur.

10) Support netmap in the nft_nat code, from Pablo Neira Ayuso.

11) Allow UDPv6 encapsulation of ESP in the ipsec code, from Sabrina
    Dubroca. Also add ipv6 support for espintcp.

12) Lots of ReST conversions of the networking documentation, from Mauro
    Carvalho Chehab.

13) Support configuration of ethtool rxnfc flows in bcmgenet driver,
    from Doug Berger.

14) Allow to dump cgroup id and filter by it in inet_diag code, from
    Dmitry Yakunin.

15) Add infrastructure to export netlink attribute policies to
    userspace, from Johannes Berg.

16) Several optimizations to sch_fq scheduler, from Eric Dumazet.

17) Fallback to the default qdisc if qdisc init fails because otherwise
    a packet scheduler init failure will make a device inoperative. From
    Jesper Dangaard Brouer.

18) Several RISCV bpf jit optimizations, from Luke Nelson.

19) Correct the return type of the ->ndo_start_xmit() method in several
    drivers, it's netdev_tx_t but many drivers were using
    'int'. From Yunjian Wang.

20) Add an ethtool interface for PHY master/slave config, from Oleksij
    Rempel.

21) Add BPF iterators, from Yonghang Song.

22) Add cable test infrastructure, including ethool interfaces, from
    Andrew Lunn. Marvell PHY driver is the first to support this
    facility.

23) Remove zero-length arrays all over, from Gustavo A. R. Silva.

24) Calculate and maintain an explicit frame size in XDP, from Jesper
    Dangaard Brouer.

25) Add CAP_BPF, from Alexei Starovoitov.

26) Support terse dumps in the packet scheduler, from Vlad Buslov.

27) Support XDP_TX bulking in dpaa2 driver, from Ioana Ciornei.

28) Add devm_register_netdev(), from Bartosz Golaszewski.

29) Minimize qdisc resets, from Cong Wang.

30) Get rid of kernel_getsockopt and kernel_setsockopt in order to
    eliminate set_fs/get_fs calls. From Christoph Hellwig.

* git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (2517 commits)
  selftests: net: ip_defrag: ignore EPERM
  net_failover: fixed rollback in net_failover_open()
  Revert "tipc: Fix potential tipc_aead refcnt leak in tipc_crypto_rcv"
  Revert "tipc: Fix potential tipc_node refcnt leak in tipc_rcv"
  vmxnet3: allow rx flow hash ops only when rss is enabled
  hinic: add set_channels ethtool_ops support
  selftests/bpf: Add a default $(CXX) value
  tools/bpf: Don't use $(COMPILE.c)
  bpf, selftests: Use bpf_probe_read_kernel
  s390/bpf: Use bcr 0,%0 as tail call nop filler
  s390/bpf: Maintain 8-byte stack alignment
  selftests/bpf: Fix verifier test
  selftests/bpf: Fix sample_cnt shared between two threads
  bpf, selftests: Adapt cls_redirect to call csum_level helper
  bpf: Add csum_level helper for fixing up csum levels
  bpf: Fix up bpf_skb_adjust_room helper's skb csum setting
  sfc: add missing annotation for efx_ef10_try_update_nic_stats_vf()
  crypto/chtls: IPv6 support for inline TLS
  Crypto/chcr: Fixes a coccinile check error
  Crypto/chcr: Fixes compilations warnings
  ...

1 files changed, 231 insertions, 74 deletions

diff --git a/net/openvswitch/meter.c b/net/openvswitch/meter.c
index 5010d1ddd4bd..3d3d8e094546 100644
--- a/net/openvswitch/meter.c
+++ b/net/openvswitch/meter.c
@@ -12,6 +12,7 @@
 #include <linux/openvswitch.h>
 #include <linux/netlink.h>
 #include <linux/rculist.h>
+#include <linux/swap.h>
 
 #include <net/netlink.h>
 #include <net/genetlink.h>
@@ -19,8 +20,6 @@
 #include "datapath.h"
 #include "meter.h"
 
-#define METER_HASH_BUCKETS 1024
-
 static const struct nla_policy meter_policy[OVS_METER_ATTR_MAX + 1] = {
 	[OVS_METER_ATTR_ID] = { .type = NLA_U32, },
 	[OVS_METER_ATTR_KBPS] = { .type = NLA_FLAG },
@@ -39,6 +38,11 @@ static const struct nla_policy band_policy[OVS_BAND_ATTR_MAX + 1] = {
 	[OVS_BAND_ATTR_STATS] = { .len = sizeof(struct ovs_flow_stats) },
 };
 
+static u32 meter_hash(struct dp_meter_instance *ti, u32 id)
+{
+	return id % ti->n_meters;
+}
+
 static void ovs_meter_free(struct dp_meter *meter)
 {
 	if (!meter)
@@ -47,40 +51,162 @@ static void ovs_meter_free(struct dp_meter *meter)
 	kfree_rcu(meter, rcu);
 }
 
-static struct hlist_head *meter_hash_bucket(const struct datapath *dp,
-					    u32 meter_id)
-{
-	return &dp->meters[meter_id & (METER_HASH_BUCKETS - 1)];
-}
-
 /* Call with ovs_mutex or RCU read lock. */
-static struct dp_meter *lookup_meter(const struct datapath *dp,
+static struct dp_meter *lookup_meter(const struct dp_meter_table *tbl,
 				     u32 meter_id)
 {
+	struct dp_meter_instance *ti = rcu_dereference_ovsl(tbl->ti);
+	u32 hash = meter_hash(ti, meter_id);
 	struct dp_meter *meter;
-	struct hlist_head *head;
 
-	head = meter_hash_bucket(dp, meter_id);
-	hlist_for_each_entry_rcu(meter, head, dp_hash_node,
-				lockdep_ovsl_is_held()) {
-		if (meter->id == meter_id)
-			return meter;
-	}
+	meter = rcu_dereference_ovsl(ti->dp_meters[hash]);
+	if (meter && likely(meter->id == meter_id))
+		return meter;
+
 	return NULL;
 }
 
-static void attach_meter(struct datapath *dp, struct dp_meter *meter)
+static struct dp_meter_instance *dp_meter_instance_alloc(const u32 size)
+{
+	struct dp_meter_instance *ti;
+
+	ti = kvzalloc(sizeof(*ti) +
+		      sizeof(struct dp_meter *) * size,
+		      GFP_KERNEL);
+	if (!ti)
+		return NULL;
+
+	ti->n_meters = size;
+
+	return ti;
+}
+
+static void dp_meter_instance_free(struct dp_meter_instance *ti)
+{
+	kvfree(ti);
+}
+
+static void dp_meter_instance_free_rcu(struct rcu_head *rcu)
 {
-	struct hlist_head *head = meter_hash_bucket(dp, meter->id);
+	struct dp_meter_instance *ti;
 
-	hlist_add_head_rcu(&meter->dp_hash_node, head);
+	ti = container_of(rcu, struct dp_meter_instance, rcu);
+	kvfree(ti);
 }
 
-static void detach_meter(struct dp_meter *meter)
+static int
+dp_meter_instance_realloc(struct dp_meter_table *tbl, u32 size)
+{
+	struct dp_meter_instance *ti = rcu_dereference_ovsl(tbl->ti);
+	int n_meters = min(size, ti->n_meters);
+	struct dp_meter_instance *new_ti;
+	int i;
+
+	new_ti = dp_meter_instance_alloc(size);
+	if (!new_ti)
+		return -ENOMEM;
+
+	for (i = 0; i < n_meters; i++)
+		if (rcu_dereference_ovsl(ti->dp_meters[i]))
+			new_ti->dp_meters[i] = ti->dp_meters[i];
+
+	rcu_assign_pointer(tbl->ti, new_ti);
+	call_rcu(&ti->rcu, dp_meter_instance_free_rcu);
+
+	return 0;
+}
+
+static void dp_meter_instance_insert(struct dp_meter_instance *ti,
+				     struct dp_meter *meter)
+{
+	u32 hash;
+
+	hash = meter_hash(ti, meter->id);
+	rcu_assign_pointer(ti->dp_meters[hash], meter);
+}
+
+static void dp_meter_instance_remove(struct dp_meter_instance *ti,
+				     struct dp_meter *meter)
 {
+	u32 hash;
+
+	hash = meter_hash(ti, meter->id);
+	RCU_INIT_POINTER(ti->dp_meters[hash], NULL);
+}
+
+static int attach_meter(struct dp_meter_table *tbl, struct dp_meter *meter)
+{
+	struct dp_meter_instance *ti = rcu_dereference_ovsl(tbl->ti);
+	u32 hash = meter_hash(ti, meter->id);
+	int err;
+
+	/* In generally, slots selected should be empty, because
+	 * OvS uses id-pool to fetch a available id.
+	 */
+	if (unlikely(rcu_dereference_ovsl(ti->dp_meters[hash])))
+		return -EBUSY;
+
+	dp_meter_instance_insert(ti, meter);
+
+	/* That function is thread-safe. */
+	tbl->count++;
+	if (tbl->count >= tbl->max_meters_allowed) {
+		err = -EFBIG;
+		goto attach_err;
+	}
+
+	if (tbl->count >= ti->n_meters &&
+	    dp_meter_instance_realloc(tbl, ti->n_meters * 2)) {
+		err = -ENOMEM;
+		goto attach_err;
+	}
+
+	return 0;
+
+attach_err:
+	dp_meter_instance_remove(ti, meter);
+	tbl->count--;
+	return err;
+}
+
+static int detach_meter(struct dp_meter_table *tbl, struct dp_meter *meter)
+{
+	struct dp_meter_instance *ti;
+
 	ASSERT_OVSL();
-	if (meter)
-		hlist_del_rcu(&meter->dp_hash_node);
+	if (!meter)
+		return 0;
+
+	ti = rcu_dereference_ovsl(tbl->ti);
+	dp_meter_instance_remove(ti, meter);
+
+	tbl->count--;
+
+	/* Shrink the meter array if necessary. */
+	if (ti->n_meters > DP_METER_ARRAY_SIZE_MIN &&
+	    tbl->count <= (ti->n_meters / 4)) {
+		int half_size = ti->n_meters / 2;
+		int i;
+
+		/* Avoid hash collision, don't move slots to other place.
+		 * Make sure there are no references of meters in array
+		 * which will be released.
+		 */
+		for (i = half_size; i < ti->n_meters; i++)
+			if (rcu_dereference_ovsl(ti->dp_meters[i]))
+				goto out;
+
+		if (dp_meter_instance_realloc(tbl, half_size))
+			goto shrink_err;
+	}
+
+out:
+	return 0;
+
+shrink_err:
+	dp_meter_instance_insert(ti, meter);
+	tbl->count++;
+	return -ENOMEM;
 }
 
 static struct sk_buff *
@@ -116,12 +242,11 @@ static int ovs_meter_cmd_reply_stats(struct sk_buff *reply, u32 meter_id,
 	if (nla_put_u32(reply, OVS_METER_ATTR_ID, meter_id))
 		goto error;
 
-	if (!meter)
-		return 0;
-
 	if (nla_put(reply, OVS_METER_ATTR_STATS,
-		    sizeof(struct ovs_flow_stats), &meter->stats) ||
-	    nla_put_u64_64bit(reply, OVS_METER_ATTR_USED, meter->used,
+		    sizeof(struct ovs_flow_stats), &meter->stats))
+		goto error;
+
+	if (nla_put_u64_64bit(reply, OVS_METER_ATTR_USED, meter->used,
 			      OVS_METER_ATTR_PAD))
 		goto error;
 
@@ -150,18 +275,32 @@ error:
 
 static int ovs_meter_cmd_features(struct sk_buff *skb, struct genl_info *info)
 {
-	struct sk_buff *reply;
+	struct ovs_header *ovs_header = info->userhdr;
 	struct ovs_header *ovs_reply_header;
 	struct nlattr *nla, *band_nla;
-	int err;
+	struct sk_buff *reply;
+	struct datapath *dp;
+	int err = -EMSGSIZE;
 
 	reply = ovs_meter_cmd_reply_start(info, OVS_METER_CMD_FEATURES,
 					  &ovs_reply_header);
 	if (IS_ERR(reply))
 		return PTR_ERR(reply);
 
-	if (nla_put_u32(reply, OVS_METER_ATTR_MAX_METERS, U32_MAX) ||
-	    nla_put_u32(reply, OVS_METER_ATTR_MAX_BANDS, DP_MAX_BANDS))
+	ovs_lock();
+	dp = get_dp(sock_net(skb->sk), ovs_header->dp_ifindex);
+	if (!dp) {
+		err = -ENODEV;
+		goto exit_unlock;
+	}
+
+	if (nla_put_u32(reply, OVS_METER_ATTR_MAX_METERS,
+			dp->meter_tbl.max_meters_allowed))
+		goto exit_unlock;
+
+	ovs_unlock();
+
+	if (nla_put_u32(reply, OVS_METER_ATTR_MAX_BANDS, DP_MAX_BANDS))
 		goto nla_put_failure;
 
 	nla = nla_nest_start_noflag(reply, OVS_METER_ATTR_BANDS);
@@ -180,9 +319,10 @@ static int ovs_meter_cmd_features(struct sk_buff *skb, struct genl_info *info)
 	genlmsg_end(reply, ovs_reply_header);
 	return genlmsg_reply(reply, info);
 
+exit_unlock:
+	ovs_unlock();
 nla_put_failure:
 	nlmsg_free(reply);
-	err = -EMSGSIZE;
 	return err;
 }
 
@@ -252,8 +392,8 @@ static struct dp_meter *dp_meter_create(struct nlattr **a)
 		 *
 		 * Start with a full bucket.
 		 */
-		band->bucket = (band->burst_size + band->rate) * 1000;
-		band_max_delta_t = band->bucket / band->rate;
+		band->bucket = (band->burst_size + band->rate) * 1000ULL;
+		band_max_delta_t = div_u64(band->bucket, band->rate);
 		if (band_max_delta_t > meter->max_delta_t)
 			meter->max_delta_t = band_max_delta_t;
 		band++;
@@ -273,14 +413,14 @@ static int ovs_meter_cmd_set(struct sk_buff *skb, struct genl_info *info)
 	struct sk_buff *reply;
 	struct ovs_header *ovs_reply_header;
 	struct ovs_header *ovs_header = info->userhdr;
+	struct dp_meter_table *meter_tbl;
 	struct datapath *dp;
 	int err;
 	u32 meter_id;
 	bool failed;
 
-	if (!a[OVS_METER_ATTR_ID]) {
-		return -ENODEV;
-	}
+	if (!a[OVS_METER_ATTR_ID])
+		return -EINVAL;
 
 	meter = dp_meter_create(a);
 	if (IS_ERR_OR_NULL(meter))
@@ -300,12 +440,18 @@ static int ovs_meter_cmd_set(struct sk_buff *skb, struct genl_info *info)
 		goto exit_unlock;
 	}
 
+	meter_tbl = &dp->meter_tbl;
 	meter_id = nla_get_u32(a[OVS_METER_ATTR_ID]);
 
-	/* Cannot fail after this. */
-	old_meter = lookup_meter(dp, meter_id);
-	detach_meter(old_meter);
-	attach_meter(dp, meter);
+	old_meter = lookup_meter(meter_tbl, meter_id);
+	err = detach_meter(meter_tbl, old_meter);
+	if (err)
+		goto exit_unlock;
+
+	err = attach_meter(meter_tbl, meter);
+	if (err)
+		goto exit_unlock;
+
 	ovs_unlock();
 
 	/* Build response with the meter_id and stats from
@@ -337,14 +483,14 @@ exit_free_meter:
 
 static int ovs_meter_cmd_get(struct sk_buff *skb, struct genl_info *info)
 {
-	struct nlattr **a = info->attrs;
-	u32 meter_id;
 	struct ovs_header *ovs_header = info->userhdr;
 	struct ovs_header *ovs_reply_header;
+	struct nlattr **a = info->attrs;
+	struct dp_meter *meter;
+	struct sk_buff *reply;
 	struct datapath *dp;
+	u32 meter_id;
 	int err;
-	struct sk_buff *reply;
-	struct dp_meter *meter;
 
 	if (!a[OVS_METER_ATTR_ID])
 		return -EINVAL;
@@ -365,7 +511,7 @@ static int ovs_meter_cmd_get(struct sk_buff *skb, struct genl_info *info)
 	}
 
 	/* Locate meter, copy stats. */
-	meter = lookup_meter(dp, meter_id);
+	meter = lookup_meter(&dp->meter_tbl, meter_id);
 	if (!meter) {
 		err = -ENOENT;
 		goto exit_unlock;
@@ -390,18 +536,17 @@ exit_unlock:
 
 static int ovs_meter_cmd_del(struct sk_buff *skb, struct genl_info *info)
 {
-	struct nlattr **a = info->attrs;
-	u32 meter_id;
 	struct ovs_header *ovs_header = info->userhdr;
 	struct ovs_header *ovs_reply_header;
+	struct nlattr **a = info->attrs;
+	struct dp_meter *old_meter;
+	struct sk_buff *reply;
 	struct datapath *dp;
+	u32 meter_id;
 	int err;
-	struct sk_buff *reply;
-	struct dp_meter *old_meter;
 
 	if (!a[OVS_METER_ATTR_ID])
 		return -EINVAL;
-	meter_id = nla_get_u32(a[OVS_METER_ATTR_ID]);
 
 	reply = ovs_meter_cmd_reply_start(info, OVS_METER_CMD_DEL,
 					  &ovs_reply_header);
@@ -416,14 +561,19 @@ static int ovs_meter_cmd_del(struct sk_buff *skb, struct genl_info *info)
 		goto exit_unlock;
 	}
 
-	old_meter = lookup_meter(dp, meter_id);
+	meter_id = nla_get_u32(a[OVS_METER_ATTR_ID]);
+	old_meter = lookup_meter(&dp->meter_tbl, meter_id);
 	if (old_meter) {
 		spin_lock_bh(&old_meter->lock);
 		err = ovs_meter_cmd_reply_stats(reply, meter_id, old_meter);
 		WARN_ON(err);
 		spin_unlock_bh(&old_meter->lock);
-		detach_meter(old_meter);
+
+		err = detach_meter(&dp->meter_tbl, old_meter);
+		if (err)
+			goto exit_unlock;
 	}
+
 	ovs_unlock();
 	ovs_meter_free(old_meter);
 	genlmsg_end(reply, ovs_reply_header);
@@ -443,16 +593,16 @@ exit_unlock:
 bool ovs_meter_execute(struct datapath *dp, struct sk_buff *skb,
 		       struct sw_flow_key *key, u32 meter_id)
 {
-	struct dp_meter *meter;
-	struct dp_meter_band *band;
 	long long int now_ms = div_u64(ktime_get_ns(), 1000 * 1000);
 	long long int long_delta_ms;
-	u32 delta_ms;
-	u32 cost;
+	struct dp_meter_band *band;
+	struct dp_meter *meter;
 	int i, band_exceeded_max = -1;
 	u32 band_exceeded_rate = 0;
+	u32 delta_ms;
+	u32 cost;
 
-	meter = lookup_meter(dp, meter_id);
+	meter = lookup_meter(&dp->meter_tbl, meter_id);
 	/* Do not drop the packet when there is no meter. */
 	if (!meter)
 		return false;
@@ -570,32 +720,39 @@ struct genl_family dp_meter_genl_family __ro_after_init = {
 
 int ovs_meters_init(struct datapath *dp)
 {
-	int i;
-
-	dp->meters = kmalloc_array(METER_HASH_BUCKETS,
-				   sizeof(struct hlist_head), GFP_KERNEL);
+	struct dp_meter_table *tbl = &dp->meter_tbl;
+	struct dp_meter_instance *ti;
+	unsigned long free_mem_bytes;
 
-	if (!dp->meters)
+	ti = dp_meter_instance_alloc(DP_METER_ARRAY_SIZE_MIN);
+	if (!ti)
 		return -ENOMEM;
 
-	for (i = 0; i < METER_HASH_BUCKETS; i++)
-		INIT_HLIST_HEAD(&dp->meters[i]);
+	/* Allow meters in a datapath to use ~3.12% of physical memory. */
+	free_mem_bytes = nr_free_buffer_pages() * (PAGE_SIZE >> 5);
+	tbl->max_meters_allowed = min(free_mem_bytes / sizeof(struct dp_meter),
+				      DP_METER_NUM_MAX);
+	if (!tbl->max_meters_allowed)
+		goto out_err;
+
+	rcu_assign_pointer(tbl->ti, ti);
+	tbl->count = 0;
 
 	return 0;
+
+out_err:
+	dp_meter_instance_free(ti);
+	return -ENOMEM;
 }
 
 void ovs_meters_exit(struct datapath *dp)
 {
+	struct dp_meter_table *tbl = &dp->meter_tbl;
+	struct dp_meter_instance *ti = rcu_dereference_raw(tbl->ti);
 	int i;
 
-	for (i = 0; i < METER_HASH_BUCKETS; i++) {
-		struct hlist_head *head = &dp->meters[i];
-		struct dp_meter *meter;
-		struct hlist_node *n;
-
-		hlist_for_each_entry_safe(meter, n, head, dp_hash_node)
-			kfree(meter);
-	}
+	for (i = 0; i < ti->n_meters; i++)
+		ovs_meter_free(rcu_dereference_raw(ti->dp_meters[i]));
 
-	kfree(dp->meters);
+	dp_meter_instance_free(ti);
 }