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, 18 insertions, 19 deletions

diff --git a/drivers/net/wireless/mediatek/mt76/dma.c b/drivers/net/wireless/mediatek/mt76/dma.c
index 214fc95b8a33..73eeb00d5aa6 100644
--- a/drivers/net/wireless/mediatek/mt76/dma.c
+++ b/drivers/net/wireless/mediatek/mt76/dma.c
@@ -72,9 +72,11 @@ mt76_free_pending_txwi(struct mt76_dev *dev)
 {
 	struct mt76_txwi_cache *t;
 
+	local_bh_disable();
 	while ((t = __mt76_get_txwi(dev)) != NULL)
 		dma_unmap_single(dev->dev, t->dma_addr, dev->drv->txwi_size,
 				 DMA_TO_DEVICE);
+	local_bh_enable();
 }
 
 static int
@@ -86,6 +88,7 @@ mt76_dma_alloc_queue(struct mt76_dev *dev, struct mt76_queue *q,
 	int i;
 
 	spin_lock_init(&q->lock);
+	spin_lock_init(&q->cleanup_lock);
 
 	q->regs = dev->mmio.regs + ring_base + idx * MT_RING_SIZE;
 	q->ndesc = n_desc;
@@ -215,16 +218,15 @@ mt76_dma_kick_queue(struct mt76_dev *dev, struct mt76_queue *q)
 }
 
 static void
-mt76_dma_tx_cleanup(struct mt76_dev *dev, enum mt76_txq_id qid, bool flush)
+mt76_dma_tx_cleanup(struct mt76_dev *dev, struct mt76_queue *q, bool flush)
 {
-	struct mt76_queue *q = dev->q_tx[qid];
 	struct mt76_queue_entry entry;
-	bool wake = false;
 	int last;
 
 	if (!q)
 		return;
 
+	spin_lock_bh(&q->cleanup_lock);
 	if (flush)
 		last = -1;
 	else
@@ -237,13 +239,13 @@ mt76_dma_tx_cleanup(struct mt76_dev *dev, enum mt76_txq_id qid, bool flush)
 		if (entry.txwi) {
 			if (!(dev->drv->drv_flags & MT_DRV_TXWI_NO_FREE))
 				mt76_put_txwi(dev, entry.txwi);
-			wake = !flush;
 		}
 
 		if (!flush && q->tail == last)
 			last = readl(&q->regs->dma_idx);
 
 	}
+	spin_unlock_bh(&q->cleanup_lock);
 
 	if (flush) {
 		spin_lock_bh(&q->lock);
@@ -252,16 +254,8 @@ mt76_dma_tx_cleanup(struct mt76_dev *dev, enum mt76_txq_id qid, bool flush)
 		spin_unlock_bh(&q->lock);
 	}
 
-	wake = wake && q->stopped &&
-	       qid < IEEE80211_NUM_ACS && q->queued < q->ndesc - 8;
-	if (wake)
-		q->stopped = false;
-
 	if (!q->queued)
 		wake_up(&dev->tx_wait);
-
-	if (wake)
-		ieee80211_wake_queue(dev->hw, qid);
 }
 
 static void *
@@ -312,10 +306,9 @@ mt76_dma_dequeue(struct mt76_dev *dev, struct mt76_queue *q, bool flush,
 }
 
 static int
-mt76_dma_tx_queue_skb_raw(struct mt76_dev *dev, enum mt76_txq_id qid,
+mt76_dma_tx_queue_skb_raw(struct mt76_dev *dev, struct mt76_queue *q,
 			  struct sk_buff *skb, u32 tx_info)
 {
-	struct mt76_queue *q = dev->q_tx[qid];
 	struct mt76_queue_buf buf;
 	dma_addr_t addr;
 
@@ -343,11 +336,10 @@ error:
 }
 
 static int
-mt76_dma_tx_queue_skb(struct mt76_dev *dev, enum mt76_txq_id qid,
+mt76_dma_tx_queue_skb(struct mt76_dev *dev, struct mt76_queue *q,
 		      struct sk_buff *skb, struct mt76_wcid *wcid,
 		      struct ieee80211_sta *sta)
 {
-	struct mt76_queue *q = dev->q_tx[qid];
 	struct mt76_tx_info tx_info = {
 		.skb = skb,
 	};
@@ -397,7 +389,7 @@ mt76_dma_tx_queue_skb(struct mt76_dev *dev, enum mt76_txq_id qid,
 
 	dma_sync_single_for_cpu(dev->dev, t->dma_addr, dev->drv->txwi_size,
 				DMA_TO_DEVICE);
-	ret = dev->drv->tx_prepare_skb(dev, txwi, qid, wcid, sta, &tx_info);
+	ret = dev->drv->tx_prepare_skb(dev, txwi, q->qid, wcid, sta, &tx_info);
 	dma_sync_single_for_device(dev->dev, t->dma_addr, dev->drv->txwi_size,
 				   DMA_TO_DEVICE);
 	if (ret < 0)
@@ -661,8 +653,15 @@ void mt76_dma_cleanup(struct mt76_dev *dev)
 
 	mt76_worker_disable(&dev->tx_worker);
 	netif_napi_del(&dev->tx_napi);
-	for (i = 0; i < ARRAY_SIZE(dev->q_tx); i++)
-		mt76_dma_tx_cleanup(dev, i, true);
+
+	for (i = 0; i < ARRAY_SIZE(dev->phy.q_tx); i++) {
+		mt76_dma_tx_cleanup(dev, dev->phy.q_tx[i], true);
+		if (dev->phy2)
+			mt76_dma_tx_cleanup(dev, dev->phy2->q_tx[i], true);
+	}
+
+	for (i = 0; i < ARRAY_SIZE(dev->q_mcu); i++)
+		mt76_dma_tx_cleanup(dev, dev->q_mcu[i], true);
 
 	mt76_for_each_q_rx(dev, i) {
 		netif_napi_del(&dev->napi[i]);