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

Pull networking updates from David Miller:
 "Some highlights from this development cycle:

   1) Big refactoring of ipv6 route and neigh handling to support
      nexthop objects configurable as units from userspace. From David
      Ahern.

   2) Convert explored_states in BPF verifier into a hash table,
      significantly decreased state held for programs with bpf2bpf
      calls, from Alexei Starovoitov.

   3) Implement bpf_send_signal() helper, from Yonghong Song.

   4) Various classifier enhancements to mvpp2 driver, from Maxime
      Chevallier.

   5) Add aRFS support to hns3 driver, from Jian Shen.

   6) Fix use after free in inet frags by allocating fqdirs dynamically
      and reworking how rhashtable dismantle occurs, from Eric Dumazet.

   7) Add act_ctinfo packet classifier action, from Kevin
      Darbyshire-Bryant.

   8) Add TFO key backup infrastructure, from Jason Baron.

   9) Remove several old and unused ISDN drivers, from Arnd Bergmann.

  10) Add devlink notifications for flash update status to mlxsw driver,
      from Jiri Pirko.

  11) Lots of kTLS offload infrastructure fixes, from Jakub Kicinski.

  12) Add support for mv88e6250 DSA chips, from Rasmus Villemoes.

  13) Various enhancements to ipv6 flow label handling, from Eric
      Dumazet and Willem de Bruijn.

  14) Support TLS offload in nfp driver, from Jakub Kicinski, Dirk van
      der Merwe, and others.

  15) Various improvements to axienet driver including converting it to
      phylink, from Robert Hancock.

  16) Add PTP support to sja1105 DSA driver, from Vladimir Oltean.

  17) Add mqprio qdisc offload support to dpaa2-eth, from Ioana
      Radulescu.

  18) Add devlink health reporting to mlx5, from Moshe Shemesh.

  19) Convert stmmac over to phylink, from Jose Abreu.

  20) Add PTP PHC (Physical Hardware Clock) support to mlxsw, from
      Shalom Toledo.

  21) Add nftables SYNPROXY support, from Fernando Fernandez Mancera.

  22) Convert tcp_fastopen over to use SipHash, from Ard Biesheuvel.

  23) Track spill/fill of constants in BPF verifier, from Alexei
      Starovoitov.

  24) Support bounded loops in BPF, from Alexei Starovoitov.

  25) Various page_pool API fixes and improvements, from Jesper Dangaard
      Brouer.

  26) Just like ipv4, support ref-countless ipv6 route handling. From
      Wei Wang.

  27) Support VLAN offloading in aquantia driver, from Igor Russkikh.

  28) Add AF_XDP zero-copy support to mlx5, from Maxim Mikityanskiy.

  29) Add flower GRE encap/decap support to nfp driver, from Pieter
      Jansen van Vuuren.

  30) Protect against stack overflow when using act_mirred, from John
      Hurley.

  31) Allow devmap map lookups from eBPF, from Toke Høiland-Jørgensen.

  32) Use page_pool API in netsec driver, Ilias Apalodimas.

  33) Add Google gve network driver, from Catherine Sullivan.

  34) More indirect call avoidance, from Paolo Abeni.

  35) Add kTLS TX HW offload support to mlx5, from Tariq Toukan.

  36) Add XDP_REDIRECT support to bnxt_en, from Andy Gospodarek.

  37) Add MPLS manipulation actions to TC, from John Hurley.

  38) Add sending a packet to connection tracking from TC actions, and
      then allow flower classifier matching on conntrack state. From
      Paul Blakey.

  39) Netfilter hw offload support, from Pablo Neira Ayuso"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (2080 commits)
  net/mlx5e: Return in default case statement in tx_post_resync_params
  mlx5: Return -EINVAL when WARN_ON_ONCE triggers in mlx5e_tls_resync().
  net: dsa: add support for BRIDGE_MROUTER attribute
  pkt_sched: Include const.h
  net: netsec: remove static declaration for netsec_set_tx_de()
  net: netsec: remove superfluous if statement
  netfilter: nf_tables: add hardware offload support
  net: flow_offload: rename tc_cls_flower_offload to flow_cls_offload
  net: flow_offload: add flow_block_cb_is_busy() and use it
  net: sched: remove tcf block API
  drivers: net: use flow block API
  net: sched: use flow block API
  net: flow_offload: add flow_block_cb_{priv, incref, decref}()
  net: flow_offload: add list handling functions
  net: flow_offload: add flow_block_cb_alloc() and flow_block_cb_free()
  net: flow_offload: rename TCF_BLOCK_BINDER_TYPE_* to FLOW_BLOCK_BINDER_TYPE_*
  net: flow_offload: rename TC_BLOCK_{UN}BIND to FLOW_BLOCK_{UN}BIND
  net: flow_offload: add flow_block_cb_setup_simple()
  net: hisilicon: Add an tx_desc to adapt HI13X1_GMAC
  net: hisilicon: Add an rx_desc to adapt HI13X1_GMAC
  ...

1 files changed, 64 insertions, 9 deletions

diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net.h b/drivers/net/ethernet/netronome/nfp/nfp_net.h
index df9aff2684ed..5d6c3738b494 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net.h
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net.h
@@ -12,11 +12,14 @@
 #ifndef _NFP_NET_H_
 #define _NFP_NET_H_
 
+#include <linux/atomic.h>
 #include <linux/interrupt.h>
 #include <linux/list.h>
 #include <linux/netdevice.h>
 #include <linux/pci.h>
 #include <linux/io-64-nonatomic-hi-lo.h>
+#include <linux/semaphore.h>
+#include <linux/workqueue.h>
 #include <net/xdp.h>
 
 #include "nfp_net_ctrl.h"
@@ -238,7 +241,7 @@ struct nfp_net_tx_ring {
 #define PCIE_DESC_RX_I_TCP_CSUM_OK	cpu_to_le16(BIT(11))
 #define PCIE_DESC_RX_I_UDP_CSUM		cpu_to_le16(BIT(10))
 #define PCIE_DESC_RX_I_UDP_CSUM_OK	cpu_to_le16(BIT(9))
-#define PCIE_DESC_RX_BPF		cpu_to_le16(BIT(8))
+#define PCIE_DESC_RX_DECRYPTED		cpu_to_le16(BIT(8))
 #define PCIE_DESC_RX_EOP		cpu_to_le16(BIT(7))
 #define PCIE_DESC_RX_IP4_CSUM		cpu_to_le16(BIT(6))
 #define PCIE_DESC_RX_IP4_CSUM_OK	cpu_to_le16(BIT(5))
@@ -365,6 +368,7 @@ struct nfp_net_rx_ring {
  * @hw_csum_rx_inner_ok: Counter of packets where the inner HW checksum was OK
  * @hw_csum_rx_complete: Counter of packets with CHECKSUM_COMPLETE reported
  * @hw_csum_rx_error:	 Counter of packets with bad checksums
+ * @hw_tls_rx:	    Number of packets with TLS decrypted by hardware
  * @tx_sync:	    Seqlock for atomic updates of TX stats
  * @tx_pkts:	    Number of Transmitted packets
  * @tx_bytes:	    Number of Transmitted bytes
@@ -372,6 +376,11 @@ struct nfp_net_rx_ring {
  * @hw_csum_tx_inner:	 Counter of inner TX checksum offload requests
  * @tx_gather:	    Counter of packets with Gather DMA
  * @tx_lso:	    Counter of LSO packets sent
+ * @hw_tls_tx:	    Counter of TLS packets sent with crypto offloaded to HW
+ * @tls_tx_fallback:	Counter of TLS packets sent which had to be encrypted
+ *			by the fallback path because packets came out of order
+ * @tls_tx_no_fallback:	Counter of TLS packets not sent because the fallback
+ *			path could not encrypt them
  * @tx_errors:	    How many TX errors were encountered
  * @tx_busy:        How often was TX busy (no space)?
  * @rx_replace_buf_alloc_fail:	Counter of RX buffer allocation failures
@@ -392,7 +401,7 @@ struct nfp_net_r_vector {
 		struct {
 			struct tasklet_struct tasklet;
 			struct sk_buff_head queue;
-			struct spinlock lock;
+			spinlock_t lock;
 		};
 	};
 
@@ -408,22 +417,30 @@ struct nfp_net_r_vector {
 	u64 hw_csum_rx_ok;
 	u64 hw_csum_rx_inner_ok;
 	u64 hw_csum_rx_complete;
+	u64 hw_tls_rx;
+
+	u64 hw_csum_rx_error;
+	u64 rx_replace_buf_alloc_fail;
 
 	struct nfp_net_tx_ring *xdp_ring;
 
 	struct u64_stats_sync tx_sync;
 	u64 tx_pkts;
 	u64 tx_bytes;
-	u64 hw_csum_tx;
+
+	u64 ____cacheline_aligned_in_smp hw_csum_tx;
 	u64 hw_csum_tx_inner;
 	u64 tx_gather;
 	u64 tx_lso;
+	u64 hw_tls_tx;
 
-	u64 hw_csum_rx_error;
-	u64 rx_replace_buf_alloc_fail;
+	u64 tls_tx_fallback;
+	u64 tls_tx_no_fallback;
 	u64 tx_errors;
 	u64 tx_busy;
 
+	/* Cold data follows */
+
 	u32 irq_vector;
 	irq_handler_t handler;
 	char name[IFNAMSIZ + 8];
@@ -458,6 +475,7 @@ struct nfp_stat_pair {
  * @netdev:		Backpointer to net_device structure
  * @is_vf:		Is the driver attached to a VF?
  * @chained_metadata_format:  Firemware will use new metadata format
+ * @ktls_tx:		Is kTLS TX enabled?
  * @rx_dma_dir:		Mapping direction for RX buffers
  * @rx_dma_off:		Offset at which DMA packets (for XDP headroom)
  * @rx_offset:		Offset in the RX buffers where packet data starts
@@ -482,6 +500,7 @@ struct nfp_net_dp {
 
 	u8 is_vf:1;
 	u8 chained_metadata_format:1;
+	u8 ktls_tx:1;
 
 	u8 rx_dma_dir;
 	u8 rx_offset;
@@ -549,7 +568,7 @@ struct nfp_net_dp {
  * @reconfig_timer:	Timer for async reading of reconfig results
  * @reconfig_in_progress_update:	Update FW is processing now (debug only)
  * @bar_lock:		vNIC config BAR access lock, protects: update,
- *			mailbox area
+ *			mailbox area, crypto TLV
  * @link_up:            Is the link up?
  * @link_status_lock:	Protects @link_* and ensures atomicity with BAR reading
  * @rx_coalesce_usecs:      RX interrupt moderation usecs delay parameter
@@ -562,6 +581,18 @@ struct nfp_net_dp {
  * @tx_bar:             Pointer to mapped TX queues
  * @rx_bar:             Pointer to mapped FL/RX queues
  * @tlv_caps:		Parsed TLV capabilities
+ * @ktls_tx_conn_cnt:	Number of offloaded kTLS TX connections
+ * @ktls_rx_conn_cnt:	Number of offloaded kTLS RX connections
+ * @ktls_conn_id_gen:	Trivial generator for kTLS connection ids (for TX)
+ * @ktls_no_space:	Counter of firmware rejecting kTLS connection due to
+ *			lack of space
+ * @mbox_cmsg:		Common Control Message via vNIC mailbox state
+ * @mbox_cmsg.queue:	CCM mbox queue of pending messages
+ * @mbox_cmsg.wq:	CCM mbox wait queue of waiting processes
+ * @mbox_cmsg.workq:	CCM mbox work queue for @wait_work and @runq_work
+ * @mbox_cmsg.wait_work:    CCM mbox posted msg reconfig wait work
+ * @mbox_cmsg.runq_work:    CCM mbox posted msg queue runner work
+ * @mbox_cmsg.tag:	CCM mbox message tag allocator
  * @debugfs_dir:	Device directory in debugfs
  * @vnic_list:		Entry on device vNIC list
  * @pdev:		Backpointer to PCI device
@@ -620,7 +651,7 @@ struct nfp_net {
 	struct timer_list reconfig_timer;
 	u32 reconfig_in_progress_update;
 
-	struct mutex bar_lock;
+	struct semaphore bar_lock;
 
 	u32 rx_coalesce_usecs;
 	u32 rx_coalesce_max_frames;
@@ -637,6 +668,22 @@ struct nfp_net {
 
 	struct nfp_net_tlv_caps tlv_caps;
 
+	unsigned int ktls_tx_conn_cnt;
+	unsigned int ktls_rx_conn_cnt;
+
+	atomic64_t ktls_conn_id_gen;
+
+	atomic_t ktls_no_space;
+
+	struct {
+		struct sk_buff_head queue;
+		wait_queue_head_t wq;
+		struct workqueue_struct *workq;
+		struct work_struct wait_work;
+		struct work_struct runq_work;
+		u16 tag;
+	} mbox_cmsg;
+
 	struct dentry *debugfs_dir;
 
 	struct list_head vnic_list;
@@ -848,12 +895,17 @@ static inline void nfp_ctrl_unlock(struct nfp_net *nn)
 
 static inline void nn_ctrl_bar_lock(struct nfp_net *nn)
 {
-	mutex_lock(&nn->bar_lock);
+	down(&nn->bar_lock);
+}
+
+static inline bool nn_ctrl_bar_trylock(struct nfp_net *nn)
+{
+	return !down_trylock(&nn->bar_lock);
 }
 
 static inline void nn_ctrl_bar_unlock(struct nfp_net *nn)
 {
-	mutex_unlock(&nn->bar_lock);
+	up(&nn->bar_lock);
 }
 
 /* Globals */
@@ -883,6 +935,7 @@ void nfp_ctrl_close(struct nfp_net *nn);
 
 void nfp_net_set_ethtool_ops(struct net_device *netdev);
 void nfp_net_info(struct nfp_net *nn);
+int __nfp_net_reconfig(struct nfp_net *nn, u32 update);
 int nfp_net_reconfig(struct nfp_net *nn, u32 update);
 unsigned int nfp_net_rss_key_sz(struct nfp_net *nn);
 void nfp_net_rss_write_itbl(struct nfp_net *nn);
@@ -891,6 +944,8 @@ void nfp_net_coalesce_write_cfg(struct nfp_net *nn);
 int nfp_net_mbox_lock(struct nfp_net *nn, unsigned int data_size);
 int nfp_net_mbox_reconfig(struct nfp_net *nn, u32 mbox_cmd);
 int nfp_net_mbox_reconfig_and_unlock(struct nfp_net *nn, u32 mbox_cmd);
+void nfp_net_mbox_reconfig_post(struct nfp_net *nn, u32 update);
+int nfp_net_mbox_reconfig_wait_posted(struct nfp_net *nn);
 
 unsigned int
 nfp_net_irqs_alloc(struct pci_dev *pdev, struct msix_entry *irq_entries,