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

Pull networking updates from David Miller:

 1) Add TX fast path in mac80211, from Johannes Berg.

 2) Add TSO/GRO support to ibmveth, from Thomas Falcon

 3) Move away from cached routes in ipv6, just like ipv4, from Martin
    KaFai Lau.

 4) Lots of new rhashtable tests, from Thomas Graf.

 5) Run ingress qdisc lockless, from Alexei Starovoitov.

 6) Allow servers to fetch TCP packet headers for SYN packets of new
    connections, for fingerprinting.  From Eric Dumazet.

 7) Add mode parameter to pktgen, for testing receive.  From Alexei
    Starovoitov.

 8) Cache access optimizations via simplifications of build_skb(), from
    Alexander Duyck.

 9) Move page frag allocator under mm/, also from Alexander.

10) Add xmit_more support to hv_netvsc, from KY Srinivasan.

11) Add a counter guard in case we try to perform endless reclassify
    loops in the packet scheduler.

12) Extern flow dissector to be programmable and use it in new "Flower"
    classifier.  From Jiri Pirko.

13) AF_PACKET fanout rollover fixes, performance improvements, and new
    statistics.  From Willem de Bruijn.

14) Add netdev driver for GENEVE tunnels, from John W Linville.

15) Add ingress netfilter hooks and filtering, from Pablo Neira Ayuso.

16) Fix handling of epoll edge triggers in TCP, from Eric Dumazet.

17) Add an ECN retry fallback for the initial TCP handshake, from Daniel
    Borkmann.

18) Add tail call support to BPF, from Alexei Starovoitov.

19) Add several pktgen helper scripts, from Jesper Dangaard Brouer.

20) Add zerocopy support to AF_UNIX, from Hannes Frederic Sowa.

21) Favor even port numbers for allocation to connect() requests, and
    odd port numbers for bind(0), in an effort to help avoid
    ip_local_port_range exhaustion.  From Eric Dumazet.

22) Add Cavium ThunderX driver, from Sunil Goutham.

23) Allow bpf programs to access skb_iif and dev->ifindex SKB metadata,
    from Alexei Starovoitov.

24) Add support for T6 chips in cxgb4vf driver, from Hariprasad Shenai.

25) Double TCP Small Queues default to 256K to accomodate situations
    like the XEN driver and wireless aggregation.  From Wei Liu.

26) Add more entropy inputs to flow dissector, from Tom Herbert.

27) Add CDG congestion control algorithm to TCP, from Kenneth Klette
    Jonassen.

28) Convert ipset over to RCU locking, from Jozsef Kadlecsik.

29) Track and act upon link status of ipv4 route nexthops, from Andy
    Gospodarek.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1670 commits)
  bridge: vlan: flush the dynamically learned entries on port vlan delete
  bridge: multicast: add a comment to br_port_state_selection about blocking state
  net: inet_diag: export IPV6_V6ONLY sockopt
  stmmac: troubleshoot unexpected bits in des0 & des1
  net: ipv4 sysctl option to ignore routes when nexthop link is down
  net: track link-status of ipv4 nexthops
  net: switchdev: ignore unsupported bridge flags
  net: Cavium: Fix MAC address setting in shutdown state
  drivers: net: xgene: fix for ACPI support without ACPI
  ip: report the original address of ICMP messages
  net/mlx5e: Prefetch skb data on RX
  net/mlx5e: Pop cq outside mlx5e_get_cqe
  net/mlx5e: Remove mlx5e_cq.sqrq back-pointer
  net/mlx5e: Remove extra spaces
  net/mlx5e: Avoid TX CQE generation if more xmit packets expected
  net/mlx5e: Avoid redundant dev_kfree_skb() upon NOP completion
  net/mlx5e: Remove re-assignment of wq type in mlx5e_enable_rq()
  net/mlx5e: Use skb_shinfo(skb)->gso_segs rather than counting them
  net/mlx5e: Static mapping of netdev priv resources to/from netdev TX queues
  net/mlx4_en: Use HW counters for rx/tx bytes/packets in PF device
  ...

1 files changed, 47 insertions, 48 deletions

diff --git a/drivers/net/wireless/ath/ath10k/pci.h b/drivers/net/wireless/ath/ath10k/pci.h
index bddf54320160..d7696ddc03c4 100644
--- a/drivers/net/wireless/ath/ath10k/pci.h
+++ b/drivers/net/wireless/ath/ath10k/pci.h
@@ -185,6 +185,41 @@ struct ath10k_pci {
 	/* Map CE id to ce_state */
 	struct ath10k_ce_pipe ce_states[CE_COUNT_MAX];
 	struct timer_list rx_post_retry;
+
+	/* Due to HW quirks it is recommended to disable ASPM during device
+	 * bootup. To do that the original PCI-E Link Control is stored before
+	 * device bootup is executed and re-programmed later.
+	 */
+	u16 link_ctl;
+
+	/* Protects ps_awake and ps_wake_refcount */
+	spinlock_t ps_lock;
+
+	/* The device has a special powersave-oriented register. When device is
+	 * considered asleep it drains less power and driver is forbidden from
+	 * accessing most MMIO registers. If host were to access them without
+	 * waking up the device might scribble over host memory or return
+	 * 0xdeadbeef readouts.
+	 */
+	unsigned long ps_wake_refcount;
+
+	/* Waking up takes some time (up to 2ms in some cases) so it can be bad
+	 * for latency. To mitigate this the device isn't immediately allowed
+	 * to sleep after all references are undone - instead there's a grace
+	 * period after which the powersave register is updated unless some
+	 * activity to/from device happened in the meantime.
+	 *
+	 * Also see comments on ATH10K_PCI_SLEEP_GRACE_PERIOD_MSEC.
+	 */
+	struct timer_list ps_timer;
+
+	/* MMIO registers are used to communicate with the device. With
+	 * intensive traffic accessing powersave register would be a bit
+	 * wasteful overhead and would needlessly stall CPU. It is far more
+	 * efficient to rely on a variable in RAM and update it only upon
+	 * powersave register state changes.
+	 */
+	bool ps_awake;
 };
 
 static inline struct ath10k_pci *ath10k_pci_priv(struct ath10k *ar)
@@ -209,61 +244,25 @@ static inline struct ath10k_pci *ath10k_pci_priv(struct ath10k *ar)
  * for this device; but that's not guaranteed.
  */
 #define TARG_CPU_SPACE_TO_CE_SPACE(ar, pci_addr, addr)			\
-	(((ioread32((pci_addr)+(SOC_CORE_BASE_ADDRESS|			\
+	(((ath10k_pci_read32(ar, (SOC_CORE_BASE_ADDRESS |		\
 	  CORE_CTRL_ADDRESS)) & 0x7ff) << 21) |				\
 	 0x100000 | ((addr) & 0xfffff))
 
 /* Wait up to this many Ms for a Diagnostic Access CE operation to complete */
 #define DIAG_ACCESS_CE_TIMEOUT_MS 10
 
-/* Target exposes its registers for direct access. However before host can
- * access them it needs to make sure the target is awake (ath10k_pci_wake,
- * ath10k_pci_wake_wait, ath10k_pci_is_awake). Once target is awake it won't go
- * to sleep unless host tells it to (ath10k_pci_sleep).
- *
- * If host tries to access target registers without waking it up it can
- * scribble over host memory.
- *
- * If target is asleep waking it up may take up to even 2ms.
- */
-
-static inline void ath10k_pci_write32(struct ath10k *ar, u32 offset,
-				      u32 value)
-{
-	struct ath10k_pci *ar_pci = ath10k_pci_priv(ar);
-
-	iowrite32(value, ar_pci->mem + offset);
-}
-
-static inline u32 ath10k_pci_read32(struct ath10k *ar, u32 offset)
-{
-	struct ath10k_pci *ar_pci = ath10k_pci_priv(ar);
-
-	return ioread32(ar_pci->mem + offset);
-}
-
-static inline u32 ath10k_pci_soc_read32(struct ath10k *ar, u32 addr)
-{
-	return ath10k_pci_read32(ar, RTC_SOC_BASE_ADDRESS + addr);
-}
-
-static inline void ath10k_pci_soc_write32(struct ath10k *ar, u32 addr, u32 val)
-{
-	ath10k_pci_write32(ar, RTC_SOC_BASE_ADDRESS + addr, val);
-}
-
-static inline u32 ath10k_pci_reg_read32(struct ath10k *ar, u32 addr)
-{
-	struct ath10k_pci *ar_pci = ath10k_pci_priv(ar);
-
-	return ioread32(ar_pci->mem + PCIE_LOCAL_BASE_ADDRESS + addr);
-}
+void ath10k_pci_write32(struct ath10k *ar, u32 offset, u32 value);
+void ath10k_pci_soc_write32(struct ath10k *ar, u32 addr, u32 val);
+void ath10k_pci_reg_write32(struct ath10k *ar, u32 addr, u32 val);
 
-static inline void ath10k_pci_reg_write32(struct ath10k *ar, u32 addr, u32 val)
-{
-	struct ath10k_pci *ar_pci = ath10k_pci_priv(ar);
+u32 ath10k_pci_read32(struct ath10k *ar, u32 offset);
+u32 ath10k_pci_soc_read32(struct ath10k *ar, u32 addr);
+u32 ath10k_pci_reg_read32(struct ath10k *ar, u32 addr);
 
-	iowrite32(val, ar_pci->mem + PCIE_LOCAL_BASE_ADDRESS + addr);
-}
+/* QCA6174 is known to have Tx/Rx issues when SOC_WAKE register is poked too
+ * frequently. To avoid this put SoC to sleep after a very conservative grace
+ * period. Adjust with great care.
+ */
+#define ATH10K_PCI_SLEEP_GRACE_PERIOD_MSEC 60
 
 #endif /* _PCI_H_ */