Merge tag 'net-next-5.11' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next

Pull networking updates from Jakub Kicinski:
 "Core:

   - support "prefer busy polling" NAPI operation mode, where we defer
     softirq for some time expecting applications to periodically busy
     poll

   - AF_XDP: improve efficiency by more batching and hindering the
     adjacency cache prefetcher

   - af_packet: make packet_fanout.arr size configurable up to 64K

   - tcp: optimize TCP zero copy receive in presence of partial or
     unaligned reads making zero copy a performance win for much smaller
     messages

   - XDP: add bulk APIs for returning / freeing frames

   - sched: support fragmenting IP packets as they come out of conntrack

   - net: allow virtual netdevs to forward UDP L4 and fraglist GSO skbs

  BPF:

   - BPF switch from crude rlimit-based to memcg-based memory accounting

   - BPF type format information for kernel modules and related tracing
     enhancements

   - BPF implement task local storage for BPF LSM

   - allow the FENTRY/FEXIT/RAW_TP tracing programs to use
     bpf_sk_storage

  Protocols:

   - mptcp: improve multiple xmit streams support, memory accounting and
     many smaller improvements

   - TLS: support CHACHA20-POLY1305 cipher

   - seg6: add support for SRv6 End.DT4/DT6 behavior

   - sctp: Implement RFC 6951: UDP Encapsulation of SCTP

   - ppp_generic: add ability to bridge channels directly

   - bridge: Connectivity Fault Management (CFM) support as is defined
     in IEEE 802.1Q section 12.14.

  Drivers:

   - mlx5: make use of the new auxiliary bus to organize the driver
     internals

   - mlx5: more accurate port TX timestamping support

   - mlxsw:
      - improve the efficiency of offloaded next hop updates by using
        the new nexthop object API
      - support blackhole nexthops
      - support IEEE 802.1ad (Q-in-Q) bridging

   - rtw88: major bluetooth co-existance improvements

   - iwlwifi: support new 6 GHz frequency band

   - ath11k: Fast Initial Link Setup (FILS)

   - mt7915: dual band concurrent (DBDC) support

   - net: ipa: add basic support for IPA v4.5

  Refactor:

   - a few pieces of in_interrupt() cleanup work from Sebastian Andrzej
     Siewior

   - phy: add support for shared interrupts; get rid of multiple driver
     APIs and have the drivers write a full IRQ handler, slight growth
     of driver code should be compensated by the simpler API which also
     allows shared IRQs

   - add common code for handling netdev per-cpu counters

   - move TX packet re-allocation from Ethernet switch tag drivers to a
     central place

   - improve efficiency and rename nla_strlcpy

   - number of W=1 warning cleanups as we now catch those in a patchwork
     build bot

  Old code removal:

   - wan: delete the DLCI / SDLA drivers

   - wimax: move to staging

   - wifi: remove old WDS wifi bridging support"

* tag 'net-next-5.11' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1922 commits)
  net: hns3: fix expression that is currently always true
  net: fix proc_fs init handling in af_packet and tls
  nfc: pn533: convert comma to semicolon
  af_vsock: Assign the vsock transport considering the vsock address flags
  af_vsock: Set VMADDR_FLAG_TO_HOST flag on the receive path
  vsock_addr: Check for supported flag values
  vm_sockets: Add VMADDR_FLAG_TO_HOST vsock flag
  vm_sockets: Add flags field in the vsock address data structure
  net: Disable NETIF_F_HW_TLS_TX when HW_CSUM is disabled
  tcp: Add logic to check for SYN w/ data in tcp_simple_retransmit
  net: mscc: ocelot: install MAC addresses in .ndo_set_rx_mode from process context
  nfc: s3fwrn5: Release the nfc firmware
  net: vxget: clean up sparse warnings
  mlxsw: spectrum_router: Use eXtended mezzanine to offload IPv4 router
  mlxsw: spectrum: Set KVH XLT cache mode for Spectrum2/3
  mlxsw: spectrum_router_xm: Introduce basic XM cache flushing
  mlxsw: reg: Add Router LPM Cache Enable Register
  mlxsw: reg: Add Router LPM Cache ML Delete Register
  mlxsw: spectrum_router_xm: Implement L-value tracking for M-index
  mlxsw: reg: Add XM Router M Table Register
  ...

1 files changed, 29 insertions, 16 deletions

diff --git a/net/netfilter/ipset/ip_set_hash_gen.h b/net/netfilter/ipset/ip_set_hash_gen.h
index 521e970be402..5f1208ad049e 100644
--- a/net/netfilter/ipset/ip_set_hash_gen.h
+++ b/net/netfilter/ipset/ip_set_hash_gen.h
@@ -37,18 +37,18 @@
  */
 
 /* Number of elements to store in an initial array block */
-#define AHASH_INIT_SIZE			4
+#define AHASH_INIT_SIZE			2
 /* Max number of elements to store in an array block */
-#define AHASH_MAX_SIZE			(3 * AHASH_INIT_SIZE)
+#define AHASH_MAX_SIZE			(6 * AHASH_INIT_SIZE)
 /* Max muber of elements in the array block when tuned */
 #define AHASH_MAX_TUNED			64
 
+#define AHASH_MAX(h)			((h)->bucketsize)
+
 /* Max number of elements can be tuned */
 #ifdef IP_SET_HASH_WITH_MULTI
-#define AHASH_MAX(h)			((h)->ahash_max)
-
 static u8
-tune_ahash_max(u8 curr, u32 multi)
+tune_bucketsize(u8 curr, u32 multi)
 {
 	u32 n;
 
@@ -61,12 +61,10 @@ tune_ahash_max(u8 curr, u32 multi)
 	 */
 	return n > curr && n <= AHASH_MAX_TUNED ? n : curr;
 }
-
-#define TUNE_AHASH_MAX(h, multi)	\
-	((h)->ahash_max = tune_ahash_max((h)->ahash_max, multi))
+#define TUNE_BUCKETSIZE(h, multi)	\
+	((h)->bucketsize = tune_bucketsize((h)->bucketsize, multi))
 #else
-#define AHASH_MAX(h)			AHASH_MAX_SIZE
-#define TUNE_AHASH_MAX(h, multi)
+#define TUNE_BUCKETSIZE(h, multi)
 #endif
 
 /* A hash bucket */
@@ -321,9 +319,7 @@ struct htype {
 #ifdef IP_SET_HASH_WITH_MARKMASK
 	u32 markmask;		/* markmask value for mark mask to store */
 #endif
-#ifdef IP_SET_HASH_WITH_MULTI
-	u8 ahash_max;		/* max elements in an array block */
-#endif
+	u8 bucketsize;		/* max elements in an array block */
 #ifdef IP_SET_HASH_WITH_NETMASK
 	u8 netmask;		/* netmask value for subnets to store */
 #endif
@@ -950,7 +946,7 @@ mtype_add(struct ip_set *set, void *value, const struct ip_set_ext *ext,
 		goto set_full;
 	/* Create a new slot */
 	if (n->pos >= n->size) {
-		TUNE_AHASH_MAX(h, multi);
+		TUNE_BUCKETSIZE(h, multi);
 		if (n->size >= AHASH_MAX(h)) {
 			/* Trigger rehashing */
 			mtype_data_next(&h->next, d);
@@ -1305,6 +1301,11 @@ mtype_head(struct ip_set *set, struct sk_buff *skb)
 	if (nla_put_u32(skb, IPSET_ATTR_MARKMASK, h->markmask))
 		goto nla_put_failure;
 #endif
+	if (set->flags & IPSET_CREATE_FLAG_BUCKETSIZE) {
+		if (nla_put_u8(skb, IPSET_ATTR_BUCKETSIZE, h->bucketsize) ||
+		    nla_put_net32(skb, IPSET_ATTR_INITVAL, htonl(h->initval)))
+			goto nla_put_failure;
+	}
 	if (nla_put_net32(skb, IPSET_ATTR_REFERENCES, htonl(set->ref)) ||
 	    nla_put_net32(skb, IPSET_ATTR_MEMSIZE, htonl(memsize)) ||
 	    nla_put_net32(skb, IPSET_ATTR_ELEMENTS, htonl(elements)))
@@ -1547,8 +1548,20 @@ IPSET_TOKEN(HTYPE, _create)(struct net *net, struct ip_set *set,
 #ifdef IP_SET_HASH_WITH_MARKMASK
 	h->markmask = markmask;
 #endif
-	get_random_bytes(&h->initval, sizeof(h->initval));
-
+	if (tb[IPSET_ATTR_INITVAL])
+		h->initval = ntohl(nla_get_be32(tb[IPSET_ATTR_INITVAL]));
+	else
+		get_random_bytes(&h->initval, sizeof(h->initval));
+	h->bucketsize = AHASH_MAX_SIZE;
+	if (tb[IPSET_ATTR_BUCKETSIZE]) {
+		h->bucketsize = nla_get_u8(tb[IPSET_ATTR_BUCKETSIZE]);
+		if (h->bucketsize < AHASH_INIT_SIZE)
+			h->bucketsize = AHASH_INIT_SIZE;
+		else if (h->bucketsize > AHASH_MAX_SIZE)
+			h->bucketsize = AHASH_MAX_SIZE;
+		else if (h->bucketsize % 2)
+			h->bucketsize += 1;
+	}
 	t->htable_bits = hbits;
 	t->maxelem = h->maxelem / ahash_numof_locks(hbits);
 	RCU_INIT_POINTER(h->table, t);