Merge tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-nextgrafted

Pull networking updates from Jakub Kicinski:
 "Core:

   - Add dedicated kmem_cache for typical/small skb->head, avoid having
     to access struct page at kfree time, and improve memory use.

   - Introduce sysctl to set default RPS configuration for new netdevs.

   - Define Netlink protocol specification format which can be used to
     describe messages used by each family and auto-generate parsers.
     Add tools for generating kernel data structures and uAPI headers.

   - Expose all net/core sysctls inside netns.

   - Remove 4s sleep in netpoll if carrier is instantly detected on
     boot.

   - Add configurable limit of MDB entries per port, and port-vlan.

   - Continue populating drop reasons throughout the stack.

   - Retire a handful of legacy Qdiscs and classifiers.

  Protocols:

   - Support IPv4 big TCP (TSO frames larger than 64kB).

   - Add IP_LOCAL_PORT_RANGE socket option, to control local port range
     on socket by socket basis.

   - Track and report in procfs number of MPTCP sockets used.

   - Support mixing IPv4 and IPv6 flows in the in-kernel MPTCP path
     manager.

   - IPv6: don't check net.ipv6.route.max_size and rely on garbage
     collection to free memory (similarly to IPv4).

   - Support Penultimate Segment Pop (PSP) flavor in SRv6 (RFC8986).

   - ICMP: add per-rate limit counters.

   - Add support for user scanning requests in ieee802154.

   - Remove static WEP support.

   - Support minimal Wi-Fi 7 Extremely High Throughput (EHT) rate
     reporting.

   - WiFi 7 EHT channel puncturing support (client & AP).

  BPF:

   - Add a rbtree data structure following the "next-gen data structure"
     precedent set by recently added linked list, that is, by using
     kfunc + kptr instead of adding a new BPF map type.

   - Expose XDP hints via kfuncs with initial support for RX hash and
     timestamp metadata.

   - Add BPF_F_NO_TUNNEL_KEY extension to bpf_skb_set_tunnel_key to
     better support decap on GRE tunnel devices not operating in collect
     metadata.

   - Improve x86 JIT's codegen for PROBE_MEM runtime error checks.

   - Remove the need for trace_printk_lock for bpf_trace_printk and
     bpf_trace_vprintk helpers.

   - Extend libbpf's bpf_tracing.h support for tracing arguments of
     kprobes/uprobes and syscall as a special case.

   - Significantly reduce the search time for module symbols by
     livepatch and BPF.

   - Enable cpumasks to be used as kptrs, which is useful for tracing
     programs tracking which tasks end up running on which CPUs in
     different time intervals.

   - Add support for BPF trampoline on s390x and riscv64.

   - Add capability to export the XDP features supported by the NIC.

   - Add __bpf_kfunc tag for marking kernel functions as kfuncs.

   - Add cgroup.memory=nobpf kernel parameter option to disable BPF
     memory accounting for container environments.

  Netfilter:

   - Remove the CLUSTERIP target. It has been marked as obsolete for
     years, and we still have WARN splats wrt races of the out-of-band
     /proc interface installed by this target.

   - Add 'destroy' commands to nf_tables. They are identical to the
     existing 'delete' commands, but do not return an error if the
     referenced object (set, chain, rule...) did not exist.

  Driver API:

   - Improve cpumask_local_spread() locality to help NICs set the right
     IRQ affinity on AMD platforms.

   - Separate C22 and C45 MDIO bus transactions more clearly.

   - Introduce new DCB table to control DSCP rewrite on egress.

   - Support configuration of Physical Layer Collision Avoidance (PLCA)
     Reconciliation Sublayer (RS) (802.3cg-2019). Modern version of
     shared medium Ethernet.

   - Support for MAC Merge layer (IEEE 802.3-2018 clause 99). Allowing
     preemption of low priority frames by high priority frames.

   - Add support for controlling MACSec offload using netlink SET.

   - Rework devlink instance refcounts to allow registration and
     de-registration under the instance lock. Split the code into
     multiple files, drop some of the unnecessarily granular locks and
     factor out common parts of netlink operation handling.

   - Add TX frame aggregation parameters (for USB drivers).

   - Add a new attr TCA_EXT_WARN_MSG to report TC (offload) warning
     messages with notifications for debug.

   - Allow offloading of UDP NEW connections via act_ct.

   - Add support for per action HW stats in TC.

   - Support hardware miss to TC action (continue processing in SW from
     a specific point in the action chain).

   - Warn if old Wireless Extension user space interface is used with
     modern cfg80211/mac80211 drivers. Do not support Wireless
     Extensions for Wi-Fi 7 devices at all. Everyone should switch to
     using nl80211 interface instead.

   - Improve the CAN bit timing configuration. Use extack to return
     error messages directly to user space, update the SJW handling,
     including the definition of a new default value that will benefit
     CAN-FD controllers, by increasing their oscillator tolerance.

  New hardware / drivers:

   - Ethernet:
      - nVidia BlueField-3 support (control traffic driver)
      - Ethernet support for imx93 SoCs
      - Motorcomm yt8531 gigabit Ethernet PHY
      - onsemi NCN26000 10BASE-T1S PHY (with support for PLCA)
      - Microchip LAN8841 PHY (incl. cable diagnostics and PTP)
      - Amlogic gxl MDIO mux

   - WiFi:
      - RealTek RTL8188EU (rtl8xxxu)
      - Qualcomm Wi-Fi 7 devices (ath12k)

   - CAN:
      - Renesas R-Car V4H

  Drivers:

   - Bluetooth:
      - Set Per Platform Antenna Gain (PPAG) for Intel controllers.

   - Ethernet NICs:
      - Intel (1G, igc):
         - support TSN / Qbv / packet scheduling features of i226 model
      - Intel (100G, ice):
         - use GNSS subsystem instead of TTY
         - multi-buffer XDP support
         - extend support for GPIO pins to E823 devices
      - nVidia/Mellanox:
         - update the shared buffer configuration on PFC commands
         - implement PTP adjphase function for HW offset control
         - TC support for Geneve and GRE with VF tunnel offload
         - more efficient crypto key management method
         - multi-port eswitch support
      - Netronome/Corigine:
         - add DCB IEEE support
         - support IPsec offloading for NFP3800
      - Freescale/NXP (enetc):
         - support XDP_REDIRECT for XDP non-linear buffers
         - improve reconfig, avoid link flap and waiting for idle
         - support MAC Merge layer
      - Other NICs:
         - sfc/ef100: add basic devlink support for ef100
         - ionic: rx_push mode operation (writing descriptors via MMIO)
         - bnxt: use the auxiliary bus abstraction for RDMA
         - r8169: disable ASPM and reset bus in case of tx timeout
         - cpsw: support QSGMII mode for J721e CPSW9G
         - cpts: support pulse-per-second output
         - ngbe: add an mdio bus driver
         - usbnet: optimize usbnet_bh() by avoiding unnecessary queuing
         - r8152: handle devices with FW with NCM support
         - amd-xgbe: support 10Mbps, 2.5GbE speeds and rx-adaptation
         - virtio-net: support multi buffer XDP
         - virtio/vsock: replace virtio_vsock_pkt with sk_buff
         - tsnep: XDP support

   - Ethernet high-speed switches:
      - nVidia/Mellanox (mlxsw):
         - add support for latency TLV (in FW control messages)
      - Microchip (sparx5):
         - separate explicit and implicit traffic forwarding rules, make
           the implicit rules always active
         - add support for egress DSCP rewrite
         - IS0 VCAP support (Ingress Classification)
         - IS2 VCAP filters (protos, L3 addrs, L4 ports, flags, ToS
           etc.)
         - ES2 VCAP support (Egress Access Control)
         - support for Per-Stream Filtering and Policing (802.1Q,
           8.6.5.1)

   - Ethernet embedded switches:
      - Marvell (mv88e6xxx):
         - add MAB (port auth) offload support
         - enable PTP receive for mv88e6390
      - NXP (ocelot):
         - support MAC Merge layer
         - support for the the vsc7512 internal copper phys
      - Microchip:
         - lan9303: convert to PHYLINK
         - lan966x: support TC flower filter statistics
         - lan937x: PTP support for KSZ9563/KSZ8563 and LAN937x
         - lan937x: support Credit Based Shaper configuration
         - ksz9477: support Energy Efficient Ethernet
      - other:
         - qca8k: convert to regmap read/write API, use bulk operations
         - rswitch: Improve TX timestamp accuracy

   - Intel WiFi (iwlwifi):
      - EHT (Wi-Fi 7) rate reporting
      - STEP equalizer support: transfer some STEP (connection to radio
        on platforms with integrated wifi) related parameters from the
        BIOS to the firmware.

   - Qualcomm 802.11ax WiFi (ath11k):
      - IPQ5018 support
      - Fine Timing Measurement (FTM) responder role support
      - channel 177 support

   - MediaTek WiFi (mt76):
      - per-PHY LED support
      - mt7996: EHT (Wi-Fi 7) support
      - Wireless Ethernet Dispatch (WED) reset support
      - switch to using page pool allocator

   - RealTek WiFi (rtw89):
      - support new version of Bluetooth co-existance

   - Mobile:
      - rmnet: support TX aggregation"

* tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1872 commits)
  page_pool: add a comment explaining the fragment counter usage
  net: ethtool: fix __ethtool_dev_mm_supported() implementation
  ethtool: pse-pd: Fix double word in comments
  xsk: add linux/vmalloc.h to xsk.c
  sefltests: netdevsim: wait for devlink instance after netns removal
  selftest: fib_tests: Always cleanup before exit
  net/mlx5e: Align IPsec ASO result memory to be as required by hardware
  net/mlx5e: TC, Set CT miss to the specific ct action instance
  net/mlx5e: Rename CHAIN_TO_REG to MAPPED_OBJ_TO_REG
  net/mlx5: Refactor tc miss handling to a single function
  net/mlx5: Kconfig: Make tc offload depend on tc skb extension
  net/sched: flower: Support hardware miss to tc action
  net/sched: flower: Move filter handle initialization earlier
  net/sched: cls_api: Support hardware miss to tc action
  net/sched: Rename user cookie and act cookie
  sfc: fix builds without CONFIG_RTC_LIB
  sfc: clean up some inconsistent indentings
  net/mlx4_en: Introduce flexible array to silence overflow warning
  net: lan966x: Fix possible deadlock inside PTP
  net/ulp: Remove redundant ->clone() test in inet_clone_ulp().
  ...

1 files changed, 384 insertions, 0 deletions

diff --git a/drivers/net/wireless/mediatek/mt76/sdio_txrx.c b/drivers/net/wireless/mediatek/mt76/sdio_txrx.c
new file mode 100644
index 000000000..ddd8c0cc7
--- /dev/null
+++ b/drivers/net/wireless/mediatek/mt76/sdio_txrx.c
@@ -0,0 +1,384 @@
+// SPDX-License-Identifier: ISC
+/* Copyright (C) 2020 MediaTek Inc.
+ *
+ * Author: Felix Fietkau <nbd@nbd.name>
+ *	   Lorenzo Bianconi <lorenzo@kernel.org>
+ *	   Sean Wang <sean.wang@mediatek.com>
+ */
+
+#include <linux/kernel.h>
+#include <linux/iopoll.h>
+#include <linux/module.h>
+
+#include <linux/mmc/host.h>
+#include <linux/mmc/sdio_ids.h>
+#include <linux/mmc/sdio_func.h>
+
+#include "trace.h"
+#include "sdio.h"
+#include "mt76.h"
+
+static int mt76s_refill_sched_quota(struct mt76_dev *dev, u32 *data)
+{
+	u32 ple_ac_data_quota[] = {
+		FIELD_GET(TXQ_CNT_L, data[4]), /* VO */
+		FIELD_GET(TXQ_CNT_H, data[3]), /* VI */
+		FIELD_GET(TXQ_CNT_L, data[3]), /* BE */
+		FIELD_GET(TXQ_CNT_H, data[2]), /* BK */
+	};
+	u32 pse_ac_data_quota[] = {
+		FIELD_GET(TXQ_CNT_H, data[1]), /* VO */
+		FIELD_GET(TXQ_CNT_L, data[1]), /* VI */
+		FIELD_GET(TXQ_CNT_H, data[0]), /* BE */
+		FIELD_GET(TXQ_CNT_L, data[0]), /* BK */
+	};
+	u32 pse_mcu_quota = FIELD_GET(TXQ_CNT_L, data[2]);
+	u32 pse_data_quota = 0, ple_data_quota = 0;
+	struct mt76_sdio *sdio = &dev->sdio;
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(pse_ac_data_quota); i++) {
+		pse_data_quota += pse_ac_data_quota[i];
+		ple_data_quota += ple_ac_data_quota[i];
+	}
+
+	if (!pse_data_quota && !ple_data_quota && !pse_mcu_quota)
+		return 0;
+
+	sdio->sched.pse_mcu_quota += pse_mcu_quota;
+	sdio->sched.pse_data_quota += pse_data_quota;
+	sdio->sched.ple_data_quota += ple_data_quota;
+
+	return pse_data_quota + ple_data_quota + pse_mcu_quota;
+}
+
+static struct sk_buff *
+mt76s_build_rx_skb(void *data, int data_len, int buf_len)
+{
+	int len = min_t(int, data_len, MT_SKB_HEAD_LEN);
+	struct sk_buff *skb;
+
+	skb = alloc_skb(len, GFP_KERNEL);
+	if (!skb)
+		return NULL;
+
+	skb_put_data(skb, data, len);
+	if (data_len > len) {
+		struct page *page;
+
+		data += len;
+		page = virt_to_head_page(data);
+		skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags,
+				page, data - page_address(page),
+				data_len - len, buf_len);
+		get_page(page);
+	}
+
+	return skb;
+}
+
+static int
+mt76s_rx_run_queue(struct mt76_dev *dev, enum mt76_rxq_id qid,
+		   struct mt76s_intr *intr)
+{
+	struct mt76_queue *q = &dev->q_rx[qid];
+	struct mt76_sdio *sdio = &dev->sdio;
+	int len = 0, err, i;
+	struct page *page;
+	u8 *buf, *end;
+
+	for (i = 0; i < intr->rx.num[qid]; i++)
+		len += round_up(intr->rx.len[qid][i] + 4, 4);
+
+	if (!len)
+		return 0;
+
+	if (len > sdio->func->cur_blksize)
+		len = roundup(len, sdio->func->cur_blksize);
+
+	page = __dev_alloc_pages(GFP_KERNEL, get_order(len));
+	if (!page)
+		return -ENOMEM;
+
+	buf = page_address(page);
+
+	sdio_claim_host(sdio->func);
+	err = sdio_readsb(sdio->func, buf, MCR_WRDR(qid), len);
+	sdio_release_host(sdio->func);
+
+	if (err < 0) {
+		dev_err(dev->dev, "sdio read data failed:%d\n", err);
+		put_page(page);
+		return err;
+	}
+
+	end = buf + len;
+	i = 0;
+
+	while (i < intr->rx.num[qid] && buf < end) {
+		int index = (q->head + i) % q->ndesc;
+		struct mt76_queue_entry *e = &q->entry[index];
+		__le32 *rxd = (__le32 *)buf;
+
+		/* parse rxd to get the actual packet length */
+		len = le32_get_bits(rxd[0], GENMASK(15, 0));
+
+		/* Optimized path for TXS */
+		if (!dev->drv->rx_check || dev->drv->rx_check(dev, buf, len)) {
+			e->skb = mt76s_build_rx_skb(buf, len,
+						    round_up(len + 4, 4));
+			if (!e->skb)
+				break;
+
+			if (q->queued + i + 1 == q->ndesc)
+				break;
+			i++;
+		}
+		buf += round_up(len + 4, 4);
+	}
+	put_page(page);
+
+	spin_lock_bh(&q->lock);
+	q->head = (q->head + i) % q->ndesc;
+	q->queued += i;
+	spin_unlock_bh(&q->lock);
+
+	return i;
+}
+
+static int mt76s_rx_handler(struct mt76_dev *dev)
+{
+	struct mt76_sdio *sdio = &dev->sdio;
+	struct mt76s_intr intr;
+	int nframes = 0, ret;
+
+	ret = sdio->parse_irq(dev, &intr);
+	if (ret)
+		return ret;
+
+	trace_dev_irq(dev, intr.isr, 0);
+
+	if (intr.isr & WHIER_RX0_DONE_INT_EN) {
+		ret = mt76s_rx_run_queue(dev, 0, &intr);
+		if (ret > 0) {
+			mt76_worker_schedule(&sdio->net_worker);
+			nframes += ret;
+		}
+	}
+
+	if (intr.isr & WHIER_RX1_DONE_INT_EN) {
+		ret = mt76s_rx_run_queue(dev, 1, &intr);
+		if (ret > 0) {
+			mt76_worker_schedule(&sdio->net_worker);
+			nframes += ret;
+		}
+	}
+
+	nframes += !!mt76s_refill_sched_quota(dev, intr.tx.wtqcr);
+
+	return nframes;
+}
+
+static int
+mt76s_tx_pick_quota(struct mt76_sdio *sdio, bool mcu, int buf_sz,
+		    int *pse_size, int *ple_size)
+{
+	int pse_sz;
+
+	pse_sz = DIV_ROUND_UP(buf_sz + sdio->sched.deficit,
+			      sdio->sched.pse_page_size);
+
+	if (mcu && sdio->hw_ver == MT76_CONNAC2_SDIO)
+		pse_sz = 1;
+
+	if (mcu) {
+		if (sdio->sched.pse_mcu_quota < *pse_size + pse_sz)
+			return -EBUSY;
+	} else {
+		if (sdio->sched.pse_data_quota < *pse_size + pse_sz ||
+		    sdio->sched.ple_data_quota < *ple_size + 1)
+			return -EBUSY;
+
+		*ple_size = *ple_size + 1;
+	}
+	*pse_size = *pse_size + pse_sz;
+
+	return 0;
+}
+
+static void
+mt76s_tx_update_quota(struct mt76_sdio *sdio, bool mcu, int pse_size,
+		      int ple_size)
+{
+	if (mcu) {
+		sdio->sched.pse_mcu_quota -= pse_size;
+	} else {
+		sdio->sched.pse_data_quota -= pse_size;
+		sdio->sched.ple_data_quota -= ple_size;
+	}
+}
+
+static int __mt76s_xmit_queue(struct mt76_dev *dev, u8 *data, int len)
+{
+	struct mt76_sdio *sdio = &dev->sdio;
+	int err;
+
+	if (len > sdio->func->cur_blksize)
+		len = roundup(len, sdio->func->cur_blksize);
+
+	sdio_claim_host(sdio->func);
+	err = sdio_writesb(sdio->func, MCR_WTDR1, data, len);
+	sdio_release_host(sdio->func);
+
+	if (err)
+		dev_err(dev->dev, "sdio write failed: %d\n", err);
+
+	return err;
+}
+
+static int mt76s_tx_run_queue(struct mt76_dev *dev, struct mt76_queue *q)
+{
+	int err, nframes = 0, len = 0, pse_sz = 0, ple_sz = 0;
+	bool mcu = q == dev->q_mcu[MT_MCUQ_WM];
+	struct mt76_sdio *sdio = &dev->sdio;
+	u8 pad;
+
+	while (q->first != q->head) {
+		struct mt76_queue_entry *e = &q->entry[q->first];
+		struct sk_buff *iter;
+
+		smp_rmb();
+
+		if (test_bit(MT76_MCU_RESET, &dev->phy.state))
+			goto next;
+
+		if (!test_bit(MT76_STATE_MCU_RUNNING, &dev->phy.state)) {
+			__skb_put_zero(e->skb, 4);
+			err = __skb_grow(e->skb, roundup(e->skb->len,
+							 sdio->func->cur_blksize));
+			if (err)
+				return err;
+			err = __mt76s_xmit_queue(dev, e->skb->data,
+						 e->skb->len);
+			if (err)
+				return err;
+
+			goto next;
+		}
+
+		pad = roundup(e->skb->len, 4) - e->skb->len;
+		if (len + e->skb->len + pad + 4 > dev->sdio.xmit_buf_sz)
+			break;
+
+		if (mt76s_tx_pick_quota(sdio, mcu, e->buf_sz, &pse_sz,
+					&ple_sz))
+			break;
+
+		memcpy(sdio->xmit_buf + len, e->skb->data, skb_headlen(e->skb));
+		len += skb_headlen(e->skb);
+		nframes++;
+
+		skb_walk_frags(e->skb, iter) {
+			memcpy(sdio->xmit_buf + len, iter->data, iter->len);
+			len += iter->len;
+			nframes++;
+		}
+
+		if (unlikely(pad)) {
+			memset(sdio->xmit_buf + len, 0, pad);
+			len += pad;
+		}
+next:
+		q->first = (q->first + 1) % q->ndesc;
+		e->done = true;
+	}
+
+	if (nframes) {
+		memset(sdio->xmit_buf + len, 0, 4);
+		err = __mt76s_xmit_queue(dev, sdio->xmit_buf, len + 4);
+		if (err)
+			return err;
+	}
+	mt76s_tx_update_quota(sdio, mcu, pse_sz, ple_sz);
+
+	mt76_worker_schedule(&sdio->status_worker);
+
+	return nframes;
+}
+
+void mt76s_txrx_worker(struct mt76_sdio *sdio)
+{
+	struct mt76_dev *dev = container_of(sdio, struct mt76_dev, sdio);
+	int i, nframes, ret;
+
+	/* disable interrupt */
+	sdio_claim_host(sdio->func);
+	sdio_writel(sdio->func, WHLPCR_INT_EN_CLR, MCR_WHLPCR, NULL);
+	sdio_release_host(sdio->func);
+
+	do {
+		nframes = 0;
+
+		/* tx */
+		for (i = 0; i <= MT_TXQ_PSD; i++) {
+			ret = mt76s_tx_run_queue(dev, dev->phy.q_tx[i]);
+			if (ret > 0)
+				nframes += ret;
+		}
+		ret = mt76s_tx_run_queue(dev, dev->q_mcu[MT_MCUQ_WM]);
+		if (ret > 0)
+			nframes += ret;
+
+		/* rx */
+		ret = mt76s_rx_handler(dev);
+		if (ret > 0)
+			nframes += ret;
+
+		if (test_bit(MT76_MCU_RESET, &dev->phy.state) ||
+		    test_bit(MT76_STATE_SUSPEND, &dev->phy.state)) {
+			if (!mt76s_txqs_empty(dev))
+				continue;
+			else
+				wake_up(&sdio->wait);
+		}
+	} while (nframes > 0);
+
+	/* enable interrupt */
+	sdio_claim_host(sdio->func);
+	sdio_writel(sdio->func, WHLPCR_INT_EN_SET, MCR_WHLPCR, NULL);
+	sdio_release_host(sdio->func);
+}
+EXPORT_SYMBOL_GPL(mt76s_txrx_worker);
+
+void mt76s_sdio_irq(struct sdio_func *func)
+{
+	struct mt76_dev *dev = sdio_get_drvdata(func);
+	struct mt76_sdio *sdio = &dev->sdio;
+
+	if (!test_bit(MT76_STATE_INITIALIZED, &dev->phy.state) ||
+	    test_bit(MT76_MCU_RESET, &dev->phy.state))
+		return;
+
+	sdio_writel(sdio->func, WHLPCR_INT_EN_CLR, MCR_WHLPCR, NULL);
+	mt76_worker_schedule(&sdio->txrx_worker);
+}
+EXPORT_SYMBOL_GPL(mt76s_sdio_irq);
+
+bool mt76s_txqs_empty(struct mt76_dev *dev)
+{
+	struct mt76_queue *q;
+	int i;
+
+	for (i = 0; i <= MT_TXQ_PSD + 1; i++) {
+		if (i <= MT_TXQ_PSD)
+			q = dev->phy.q_tx[i];
+		else
+			q = dev->q_mcu[MT_MCUQ_WM];
+
+		if (q->first != q->head)
+			return false;
+	}
+
+	return true;
+}
+EXPORT_SYMBOL_GPL(mt76s_txqs_empty);