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, 351 insertions, 0 deletions

diff --git a/drivers/media/platform/qcom/venus/firmware.c b/drivers/media/platform/qcom/venus/firmware.c
new file mode 100644
index 000000000..142d4c740
--- /dev/null
+++ b/drivers/media/platform/qcom/venus/firmware.c
@@ -0,0 +1,351 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2017 Linaro Ltd.
+ */
+
+#include <linux/device.h>
+#include <linux/firmware.h>
+#include <linux/kernel.h>
+#include <linux/iommu.h>
+#include <linux/io.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/platform_device.h>
+#include <linux/of_device.h>
+#include <linux/qcom_scm.h>
+#include <linux/sizes.h>
+#include <linux/soc/qcom/mdt_loader.h>
+
+#include "core.h"
+#include "firmware.h"
+#include "hfi_venus_io.h"
+
+#define VENUS_PAS_ID			9
+#define VENUS_FW_MEM_SIZE		(6 * SZ_1M)
+#define VENUS_FW_START_ADDR		0x0
+
+static void venus_reset_cpu(struct venus_core *core)
+{
+	u32 fw_size = core->fw.mapped_mem_size;
+	void __iomem *wrapper_base;
+
+	if (IS_V6(core))
+		wrapper_base = core->wrapper_tz_base;
+	else
+		wrapper_base = core->wrapper_base;
+
+	writel(0, wrapper_base + WRAPPER_FW_START_ADDR);
+	writel(fw_size, wrapper_base + WRAPPER_FW_END_ADDR);
+	writel(0, wrapper_base + WRAPPER_CPA_START_ADDR);
+	writel(fw_size, wrapper_base + WRAPPER_CPA_END_ADDR);
+	writel(0, wrapper_base + WRAPPER_NONPIX_START_ADDR);
+	writel(0, wrapper_base + WRAPPER_NONPIX_END_ADDR);
+
+	if (IS_V6(core)) {
+		/* Bring XTSS out of reset */
+		writel(0, wrapper_base + WRAPPER_TZ_XTSS_SW_RESET);
+	} else {
+		writel(0x0, wrapper_base + WRAPPER_CPU_CGC_DIS);
+		writel(0x0, wrapper_base + WRAPPER_CPU_CLOCK_CONFIG);
+
+		/* Bring ARM9 out of reset */
+		writel(0, wrapper_base + WRAPPER_A9SS_SW_RESET);
+	}
+}
+
+int venus_set_hw_state(struct venus_core *core, bool resume)
+{
+	int ret;
+
+	if (core->use_tz) {
+		ret = qcom_scm_set_remote_state(resume, 0);
+		if (resume && ret == -EINVAL)
+			ret = 0;
+		return ret;
+	}
+
+	if (resume) {
+		venus_reset_cpu(core);
+	} else {
+		if (IS_V6(core))
+			writel(WRAPPER_XTSS_SW_RESET_BIT,
+			       core->wrapper_tz_base + WRAPPER_TZ_XTSS_SW_RESET);
+		else
+			writel(WRAPPER_A9SS_SW_RESET_BIT,
+			       core->wrapper_base + WRAPPER_A9SS_SW_RESET);
+	}
+
+	return 0;
+}
+
+static int venus_load_fw(struct venus_core *core, const char *fwname,
+			 phys_addr_t *mem_phys, size_t *mem_size)
+{
+	const struct firmware *mdt;
+	struct device_node *node;
+	struct device *dev;
+	struct resource r;
+	ssize_t fw_size;
+	void *mem_va;
+	int ret;
+
+	*mem_phys = 0;
+	*mem_size = 0;
+
+	dev = core->dev;
+	node = of_parse_phandle(dev->of_node, "memory-region", 0);
+	if (!node) {
+		dev_err(dev, "no memory-region specified\n");
+		return -EINVAL;
+	}
+
+	ret = of_address_to_resource(node, 0, &r);
+	if (ret)
+		goto err_put_node;
+
+	ret = request_firmware(&mdt, fwname, dev);
+	if (ret < 0)
+		goto err_put_node;
+
+	fw_size = qcom_mdt_get_size(mdt);
+	if (fw_size < 0) {
+		ret = fw_size;
+		goto err_release_fw;
+	}
+
+	*mem_phys = r.start;
+	*mem_size = resource_size(&r);
+
+	if (*mem_size < fw_size || fw_size > VENUS_FW_MEM_SIZE) {
+		ret = -EINVAL;
+		goto err_release_fw;
+	}
+
+	mem_va = memremap(r.start, *mem_size, MEMREMAP_WC);
+	if (!mem_va) {
+		dev_err(dev, "unable to map memory region: %pR\n", &r);
+		ret = -ENOMEM;
+		goto err_release_fw;
+	}
+
+	if (core->use_tz)
+		ret = qcom_mdt_load(dev, mdt, fwname, VENUS_PAS_ID,
+				    mem_va, *mem_phys, *mem_size, NULL);
+	else
+		ret = qcom_mdt_load_no_init(dev, mdt, fwname, VENUS_PAS_ID,
+					    mem_va, *mem_phys, *mem_size, NULL);
+
+	memunmap(mem_va);
+err_release_fw:
+	release_firmware(mdt);
+err_put_node:
+	of_node_put(node);
+	return ret;
+}
+
+static int venus_boot_no_tz(struct venus_core *core, phys_addr_t mem_phys,
+			    size_t mem_size)
+{
+	struct iommu_domain *iommu;
+	struct device *dev;
+	int ret;
+
+	dev = core->fw.dev;
+	if (!dev)
+		return -EPROBE_DEFER;
+
+	iommu = core->fw.iommu_domain;
+	core->fw.mapped_mem_size = mem_size;
+
+	ret = iommu_map(iommu, VENUS_FW_START_ADDR, mem_phys, mem_size,
+			IOMMU_READ | IOMMU_WRITE | IOMMU_PRIV);
+	if (ret) {
+		dev_err(dev, "could not map video firmware region\n");
+		return ret;
+	}
+
+	venus_reset_cpu(core);
+
+	return 0;
+}
+
+static int venus_shutdown_no_tz(struct venus_core *core)
+{
+	const size_t mapped = core->fw.mapped_mem_size;
+	struct iommu_domain *iommu;
+	size_t unmapped;
+	u32 reg;
+	struct device *dev = core->fw.dev;
+	void __iomem *wrapper_base = core->wrapper_base;
+	void __iomem *wrapper_tz_base = core->wrapper_tz_base;
+
+	if (IS_V6(core)) {
+		/* Assert the reset to XTSS */
+		reg = readl(wrapper_tz_base + WRAPPER_TZ_XTSS_SW_RESET);
+		reg |= WRAPPER_XTSS_SW_RESET_BIT;
+		writel(reg, wrapper_tz_base + WRAPPER_TZ_XTSS_SW_RESET);
+	} else {
+		/* Assert the reset to ARM9 */
+		reg = readl(wrapper_base + WRAPPER_A9SS_SW_RESET);
+		reg |= WRAPPER_A9SS_SW_RESET_BIT;
+		writel(reg, wrapper_base + WRAPPER_A9SS_SW_RESET);
+	}
+
+	iommu = core->fw.iommu_domain;
+
+	if (core->fw.mapped_mem_size && iommu) {
+		unmapped = iommu_unmap(iommu, VENUS_FW_START_ADDR, mapped);
+
+		if (unmapped != mapped)
+			dev_err(dev, "failed to unmap firmware\n");
+		else
+			core->fw.mapped_mem_size = 0;
+	}
+
+	return 0;
+}
+
+int venus_boot(struct venus_core *core)
+{
+	struct device *dev = core->dev;
+	const struct venus_resources *res = core->res;
+	const char *fwpath = NULL;
+	phys_addr_t mem_phys;
+	size_t mem_size;
+	int ret;
+
+	if (!IS_ENABLED(CONFIG_QCOM_MDT_LOADER) ||
+	    (core->use_tz && !qcom_scm_is_available()))
+		return -EPROBE_DEFER;
+
+	ret = of_property_read_string_index(dev->of_node, "firmware-name", 0,
+					    &fwpath);
+	if (ret)
+		fwpath = core->res->fwname;
+
+	ret = venus_load_fw(core, fwpath, &mem_phys, &mem_size);
+	if (ret) {
+		dev_err(dev, "fail to load video firmware\n");
+		return -EINVAL;
+	}
+
+	core->fw.mem_size = mem_size;
+	core->fw.mem_phys = mem_phys;
+
+	if (core->use_tz)
+		ret = qcom_scm_pas_auth_and_reset(VENUS_PAS_ID);
+	else
+		ret = venus_boot_no_tz(core, mem_phys, mem_size);
+
+	if (ret)
+		return ret;
+
+	if (core->use_tz && res->cp_size) {
+		ret = qcom_scm_mem_protect_video_var(res->cp_start,
+						     res->cp_size,
+						     res->cp_nonpixel_start,
+						     res->cp_nonpixel_size);
+		if (ret) {
+			qcom_scm_pas_shutdown(VENUS_PAS_ID);
+			dev_err(dev, "set virtual address ranges fail (%d)\n",
+				ret);
+			return ret;
+		}
+	}
+
+	return 0;
+}
+
+int venus_shutdown(struct venus_core *core)
+{
+	int ret;
+
+	if (core->use_tz)
+		ret = qcom_scm_pas_shutdown(VENUS_PAS_ID);
+	else
+		ret = venus_shutdown_no_tz(core);
+
+	return ret;
+}
+
+int venus_firmware_init(struct venus_core *core)
+{
+	struct platform_device_info info;
+	struct iommu_domain *iommu_dom;
+	struct platform_device *pdev;
+	struct device_node *np;
+	int ret;
+
+	np = of_get_child_by_name(core->dev->of_node, "video-firmware");
+	if (!np) {
+		core->use_tz = true;
+		return 0;
+	}
+
+	memset(&info, 0, sizeof(info));
+	info.fwnode = &np->fwnode;
+	info.parent = core->dev;
+	info.name = np->name;
+	info.dma_mask = DMA_BIT_MASK(32);
+
+	pdev = platform_device_register_full(&info);
+	if (IS_ERR(pdev)) {
+		of_node_put(np);
+		return PTR_ERR(pdev);
+	}
+
+	pdev->dev.of_node = np;
+
+	ret = of_dma_configure(&pdev->dev, np, true);
+	if (ret) {
+		dev_err(core->dev, "dma configure fail\n");
+		goto err_unregister;
+	}
+
+	core->fw.dev = &pdev->dev;
+
+	iommu_dom = iommu_domain_alloc(&platform_bus_type);
+	if (!iommu_dom) {
+		dev_err(core->fw.dev, "Failed to allocate iommu domain\n");
+		ret = -ENOMEM;
+		goto err_unregister;
+	}
+
+	ret = iommu_attach_device(iommu_dom, core->fw.dev);
+	if (ret) {
+		dev_err(core->fw.dev, "could not attach device\n");
+		goto err_iommu_free;
+	}
+
+	core->fw.iommu_domain = iommu_dom;
+
+	of_node_put(np);
+
+	return 0;
+
+err_iommu_free:
+	iommu_domain_free(iommu_dom);
+err_unregister:
+	platform_device_unregister(pdev);
+	of_node_put(np);
+	return ret;
+}
+
+void venus_firmware_deinit(struct venus_core *core)
+{
+	struct iommu_domain *iommu;
+
+	if (!core->fw.dev)
+		return;
+
+	iommu = core->fw.iommu_domain;
+
+	iommu_detach_device(iommu, core->fw.dev);
+
+	if (core->fw.iommu_domain) {
+		iommu_domain_free(iommu);
+		core->fw.iommu_domain = NULL;
+	}
+
+	platform_device_unregister(to_platform_device(core->fw.dev));
+}