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, 765 insertions, 0 deletions

diff --git a/drivers/iommu/mtk_iommu_v1.c b/drivers/iommu/mtk_iommu_v1.c
new file mode 100644
index 000000000..ca581ff1c
--- /dev/null
+++ b/drivers/iommu/mtk_iommu_v1.c
@@ -0,0 +1,765 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * IOMMU API for MTK architected m4u v1 implementations
+ *
+ * Copyright (c) 2015-2016 MediaTek Inc.
+ * Author: Honghui Zhang <honghui.zhang@mediatek.com>
+ *
+ * Based on driver/iommu/mtk_iommu.c
+ */
+#include <linux/bug.h>
+#include <linux/clk.h>
+#include <linux/component.h>
+#include <linux/device.h>
+#include <linux/dma-mapping.h>
+#include <linux/err.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/iommu.h>
+#include <linux/iopoll.h>
+#include <linux/list.h>
+#include <linux/module.h>
+#include <linux/of_address.h>
+#include <linux/of_irq.h>
+#include <linux/of_platform.h>
+#include <linux/platform_device.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <asm/barrier.h>
+#include <asm/dma-iommu.h>
+#include <dt-bindings/memory/mtk-memory-port.h>
+#include <dt-bindings/memory/mt2701-larb-port.h>
+#include <soc/mediatek/smi.h>
+
+#define REG_MMU_PT_BASE_ADDR			0x000
+
+#define F_ALL_INVLD				0x2
+#define F_MMU_INV_RANGE				0x1
+#define F_INVLD_EN0				BIT(0)
+#define F_INVLD_EN1				BIT(1)
+
+#define F_MMU_FAULT_VA_MSK			0xfffff000
+#define MTK_PROTECT_PA_ALIGN			128
+
+#define REG_MMU_CTRL_REG			0x210
+#define F_MMU_CTRL_COHERENT_EN			BIT(8)
+#define REG_MMU_IVRP_PADDR			0x214
+#define REG_MMU_INT_CONTROL			0x220
+#define F_INT_TRANSLATION_FAULT			BIT(0)
+#define F_INT_MAIN_MULTI_HIT_FAULT		BIT(1)
+#define F_INT_INVALID_PA_FAULT			BIT(2)
+#define F_INT_ENTRY_REPLACEMENT_FAULT		BIT(3)
+#define F_INT_TABLE_WALK_FAULT			BIT(4)
+#define F_INT_TLB_MISS_FAULT			BIT(5)
+#define F_INT_PFH_DMA_FIFO_OVERFLOW		BIT(6)
+#define F_INT_MISS_DMA_FIFO_OVERFLOW		BIT(7)
+
+#define F_MMU_TF_PROTECT_SEL(prot)		(((prot) & 0x3) << 5)
+#define F_INT_CLR_BIT				BIT(12)
+
+#define REG_MMU_FAULT_ST			0x224
+#define REG_MMU_FAULT_VA			0x228
+#define REG_MMU_INVLD_PA			0x22C
+#define REG_MMU_INT_ID				0x388
+#define REG_MMU_INVALIDATE			0x5c0
+#define REG_MMU_INVLD_START_A			0x5c4
+#define REG_MMU_INVLD_END_A			0x5c8
+
+#define REG_MMU_INV_SEL				0x5d8
+#define REG_MMU_STANDARD_AXI_MODE		0x5e8
+
+#define REG_MMU_DCM				0x5f0
+#define F_MMU_DCM_ON				BIT(1)
+#define REG_MMU_CPE_DONE			0x60c
+#define F_DESC_VALID				0x2
+#define F_DESC_NONSEC				BIT(3)
+#define MT2701_M4U_TF_LARB(TF)			(6 - (((TF) >> 13) & 0x7))
+#define MT2701_M4U_TF_PORT(TF)			(((TF) >> 8) & 0xF)
+/* MTK generation one iommu HW only support 4K size mapping */
+#define MT2701_IOMMU_PAGE_SHIFT			12
+#define MT2701_IOMMU_PAGE_SIZE			(1UL << MT2701_IOMMU_PAGE_SHIFT)
+#define MT2701_LARB_NR_MAX			3
+
+/*
+ * MTK m4u support 4GB iova address space, and only support 4K page
+ * mapping. So the pagetable size should be exactly as 4M.
+ */
+#define M2701_IOMMU_PGT_SIZE			SZ_4M
+
+struct mtk_iommu_v1_suspend_reg {
+	u32			standard_axi_mode;
+	u32			dcm_dis;
+	u32			ctrl_reg;
+	u32			int_control0;
+};
+
+struct mtk_iommu_v1_data {
+	void __iomem			*base;
+	int				irq;
+	struct device			*dev;
+	struct clk			*bclk;
+	phys_addr_t			protect_base; /* protect memory base */
+	struct mtk_iommu_v1_domain	*m4u_dom;
+
+	struct iommu_device		iommu;
+	struct dma_iommu_mapping	*mapping;
+	struct mtk_smi_larb_iommu	larb_imu[MTK_LARB_NR_MAX];
+
+	struct mtk_iommu_v1_suspend_reg	reg;
+};
+
+struct mtk_iommu_v1_domain {
+	spinlock_t			pgtlock; /* lock for page table */
+	struct iommu_domain		domain;
+	u32				*pgt_va;
+	dma_addr_t			pgt_pa;
+	struct mtk_iommu_v1_data	*data;
+};
+
+static int mtk_iommu_v1_bind(struct device *dev)
+{
+	struct mtk_iommu_v1_data *data = dev_get_drvdata(dev);
+
+	return component_bind_all(dev, &data->larb_imu);
+}
+
+static void mtk_iommu_v1_unbind(struct device *dev)
+{
+	struct mtk_iommu_v1_data *data = dev_get_drvdata(dev);
+
+	component_unbind_all(dev, &data->larb_imu);
+}
+
+static struct mtk_iommu_v1_domain *to_mtk_domain(struct iommu_domain *dom)
+{
+	return container_of(dom, struct mtk_iommu_v1_domain, domain);
+}
+
+static const int mt2701_m4u_in_larb[] = {
+	LARB0_PORT_OFFSET, LARB1_PORT_OFFSET,
+	LARB2_PORT_OFFSET, LARB3_PORT_OFFSET
+};
+
+static inline int mt2701_m4u_to_larb(int id)
+{
+	int i;
+
+	for (i = ARRAY_SIZE(mt2701_m4u_in_larb) - 1; i >= 0; i--)
+		if ((id) >= mt2701_m4u_in_larb[i])
+			return i;
+
+	return 0;
+}
+
+static inline int mt2701_m4u_to_port(int id)
+{
+	int larb = mt2701_m4u_to_larb(id);
+
+	return id - mt2701_m4u_in_larb[larb];
+}
+
+static void mtk_iommu_v1_tlb_flush_all(struct mtk_iommu_v1_data *data)
+{
+	writel_relaxed(F_INVLD_EN1 | F_INVLD_EN0,
+			data->base + REG_MMU_INV_SEL);
+	writel_relaxed(F_ALL_INVLD, data->base + REG_MMU_INVALIDATE);
+	wmb(); /* Make sure the tlb flush all done */
+}
+
+static void mtk_iommu_v1_tlb_flush_range(struct mtk_iommu_v1_data *data,
+					 unsigned long iova, size_t size)
+{
+	int ret;
+	u32 tmp;
+
+	writel_relaxed(F_INVLD_EN1 | F_INVLD_EN0,
+		data->base + REG_MMU_INV_SEL);
+	writel_relaxed(iova & F_MMU_FAULT_VA_MSK,
+		data->base + REG_MMU_INVLD_START_A);
+	writel_relaxed((iova + size - 1) & F_MMU_FAULT_VA_MSK,
+		data->base + REG_MMU_INVLD_END_A);
+	writel_relaxed(F_MMU_INV_RANGE, data->base + REG_MMU_INVALIDATE);
+
+	ret = readl_poll_timeout_atomic(data->base + REG_MMU_CPE_DONE,
+				tmp, tmp != 0, 10, 100000);
+	if (ret) {
+		dev_warn(data->dev,
+			 "Partial TLB flush timed out, falling back to full flush\n");
+		mtk_iommu_v1_tlb_flush_all(data);
+	}
+	/* Clear the CPE status */
+	writel_relaxed(0, data->base + REG_MMU_CPE_DONE);
+}
+
+static irqreturn_t mtk_iommu_v1_isr(int irq, void *dev_id)
+{
+	struct mtk_iommu_v1_data *data = dev_id;
+	struct mtk_iommu_v1_domain *dom = data->m4u_dom;
+	u32 int_state, regval, fault_iova, fault_pa;
+	unsigned int fault_larb, fault_port;
+
+	/* Read error information from registers */
+	int_state = readl_relaxed(data->base + REG_MMU_FAULT_ST);
+	fault_iova = readl_relaxed(data->base + REG_MMU_FAULT_VA);
+
+	fault_iova &= F_MMU_FAULT_VA_MSK;
+	fault_pa = readl_relaxed(data->base + REG_MMU_INVLD_PA);
+	regval = readl_relaxed(data->base + REG_MMU_INT_ID);
+	fault_larb = MT2701_M4U_TF_LARB(regval);
+	fault_port = MT2701_M4U_TF_PORT(regval);
+
+	/*
+	 * MTK v1 iommu HW could not determine whether the fault is read or
+	 * write fault, report as read fault.
+	 */
+	if (report_iommu_fault(&dom->domain, data->dev, fault_iova,
+			IOMMU_FAULT_READ))
+		dev_err_ratelimited(data->dev,
+			"fault type=0x%x iova=0x%x pa=0x%x larb=%d port=%d\n",
+			int_state, fault_iova, fault_pa,
+			fault_larb, fault_port);
+
+	/* Interrupt clear */
+	regval = readl_relaxed(data->base + REG_MMU_INT_CONTROL);
+	regval |= F_INT_CLR_BIT;
+	writel_relaxed(regval, data->base + REG_MMU_INT_CONTROL);
+
+	mtk_iommu_v1_tlb_flush_all(data);
+
+	return IRQ_HANDLED;
+}
+
+static void mtk_iommu_v1_config(struct mtk_iommu_v1_data *data,
+				struct device *dev, bool enable)
+{
+	struct mtk_smi_larb_iommu    *larb_mmu;
+	unsigned int                 larbid, portid;
+	struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev);
+	int i;
+
+	for (i = 0; i < fwspec->num_ids; ++i) {
+		larbid = mt2701_m4u_to_larb(fwspec->ids[i]);
+		portid = mt2701_m4u_to_port(fwspec->ids[i]);
+		larb_mmu = &data->larb_imu[larbid];
+
+		dev_dbg(dev, "%s iommu port: %d\n",
+			enable ? "enable" : "disable", portid);
+
+		if (enable)
+			larb_mmu->mmu |= MTK_SMI_MMU_EN(portid);
+		else
+			larb_mmu->mmu &= ~MTK_SMI_MMU_EN(portid);
+	}
+}
+
+static int mtk_iommu_v1_domain_finalise(struct mtk_iommu_v1_data *data)
+{
+	struct mtk_iommu_v1_domain *dom = data->m4u_dom;
+
+	spin_lock_init(&dom->pgtlock);
+
+	dom->pgt_va = dma_alloc_coherent(data->dev, M2701_IOMMU_PGT_SIZE,
+					 &dom->pgt_pa, GFP_KERNEL);
+	if (!dom->pgt_va)
+		return -ENOMEM;
+
+	writel(dom->pgt_pa, data->base + REG_MMU_PT_BASE_ADDR);
+
+	dom->data = data;
+
+	return 0;
+}
+
+static struct iommu_domain *mtk_iommu_v1_domain_alloc(unsigned type)
+{
+	struct mtk_iommu_v1_domain *dom;
+
+	if (type != IOMMU_DOMAIN_UNMANAGED)
+		return NULL;
+
+	dom = kzalloc(sizeof(*dom), GFP_KERNEL);
+	if (!dom)
+		return NULL;
+
+	return &dom->domain;
+}
+
+static void mtk_iommu_v1_domain_free(struct iommu_domain *domain)
+{
+	struct mtk_iommu_v1_domain *dom = to_mtk_domain(domain);
+	struct mtk_iommu_v1_data *data = dom->data;
+
+	dma_free_coherent(data->dev, M2701_IOMMU_PGT_SIZE,
+			dom->pgt_va, dom->pgt_pa);
+	kfree(to_mtk_domain(domain));
+}
+
+static int mtk_iommu_v1_attach_device(struct iommu_domain *domain, struct device *dev)
+{
+	struct mtk_iommu_v1_data *data = dev_iommu_priv_get(dev);
+	struct mtk_iommu_v1_domain *dom = to_mtk_domain(domain);
+	struct dma_iommu_mapping *mtk_mapping;
+	int ret;
+
+	/* Only allow the domain created internally. */
+	mtk_mapping = data->mapping;
+	if (mtk_mapping->domain != domain)
+		return 0;
+
+	if (!data->m4u_dom) {
+		data->m4u_dom = dom;
+		ret = mtk_iommu_v1_domain_finalise(data);
+		if (ret) {
+			data->m4u_dom = NULL;
+			return ret;
+		}
+	}
+
+	mtk_iommu_v1_config(data, dev, true);
+	return 0;
+}
+
+static void mtk_iommu_v1_detach_device(struct iommu_domain *domain, struct device *dev)
+{
+	struct mtk_iommu_v1_data *data = dev_iommu_priv_get(dev);
+
+	mtk_iommu_v1_config(data, dev, false);
+}
+
+static int mtk_iommu_v1_map(struct iommu_domain *domain, unsigned long iova,
+			    phys_addr_t paddr, size_t pgsize, size_t pgcount,
+			    int prot, gfp_t gfp, size_t *mapped)
+{
+	struct mtk_iommu_v1_domain *dom = to_mtk_domain(domain);
+	unsigned long flags;
+	unsigned int i;
+	u32 *pgt_base_iova = dom->pgt_va + (iova  >> MT2701_IOMMU_PAGE_SHIFT);
+	u32 pabase = (u32)paddr;
+
+	spin_lock_irqsave(&dom->pgtlock, flags);
+	for (i = 0; i < pgcount; i++) {
+		if (pgt_base_iova[i])
+			break;
+		pgt_base_iova[i] = pabase | F_DESC_VALID | F_DESC_NONSEC;
+		pabase += MT2701_IOMMU_PAGE_SIZE;
+	}
+
+	spin_unlock_irqrestore(&dom->pgtlock, flags);
+
+	*mapped = i * MT2701_IOMMU_PAGE_SIZE;
+	mtk_iommu_v1_tlb_flush_range(dom->data, iova, *mapped);
+
+	return i == pgcount ? 0 : -EEXIST;
+}
+
+static size_t mtk_iommu_v1_unmap(struct iommu_domain *domain, unsigned long iova,
+				 size_t pgsize, size_t pgcount,
+				 struct iommu_iotlb_gather *gather)
+{
+	struct mtk_iommu_v1_domain *dom = to_mtk_domain(domain);
+	unsigned long flags;
+	u32 *pgt_base_iova = dom->pgt_va + (iova  >> MT2701_IOMMU_PAGE_SHIFT);
+	size_t size = pgcount * MT2701_IOMMU_PAGE_SIZE;
+
+	spin_lock_irqsave(&dom->pgtlock, flags);
+	memset(pgt_base_iova, 0, pgcount * sizeof(u32));
+	spin_unlock_irqrestore(&dom->pgtlock, flags);
+
+	mtk_iommu_v1_tlb_flush_range(dom->data, iova, size);
+
+	return size;
+}
+
+static phys_addr_t mtk_iommu_v1_iova_to_phys(struct iommu_domain *domain, dma_addr_t iova)
+{
+	struct mtk_iommu_v1_domain *dom = to_mtk_domain(domain);
+	unsigned long flags;
+	phys_addr_t pa;
+
+	spin_lock_irqsave(&dom->pgtlock, flags);
+	pa = *(dom->pgt_va + (iova >> MT2701_IOMMU_PAGE_SHIFT));
+	pa = pa & (~(MT2701_IOMMU_PAGE_SIZE - 1));
+	spin_unlock_irqrestore(&dom->pgtlock, flags);
+
+	return pa;
+}
+
+static const struct iommu_ops mtk_iommu_v1_ops;
+
+/*
+ * MTK generation one iommu HW only support one iommu domain, and all the client
+ * sharing the same iova address space.
+ */
+static int mtk_iommu_v1_create_mapping(struct device *dev, struct of_phandle_args *args)
+{
+	struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev);
+	struct mtk_iommu_v1_data *data;
+	struct platform_device *m4updev;
+	struct dma_iommu_mapping *mtk_mapping;
+	int ret;
+
+	if (args->args_count != 1) {
+		dev_err(dev, "invalid #iommu-cells(%d) property for IOMMU\n",
+			args->args_count);
+		return -EINVAL;
+	}
+
+	if (!fwspec) {
+		ret = iommu_fwspec_init(dev, &args->np->fwnode, &mtk_iommu_v1_ops);
+		if (ret)
+			return ret;
+		fwspec = dev_iommu_fwspec_get(dev);
+	} else if (dev_iommu_fwspec_get(dev)->ops != &mtk_iommu_v1_ops) {
+		return -EINVAL;
+	}
+
+	if (!dev_iommu_priv_get(dev)) {
+		/* Get the m4u device */
+		m4updev = of_find_device_by_node(args->np);
+		if (WARN_ON(!m4updev))
+			return -EINVAL;
+
+		dev_iommu_priv_set(dev, platform_get_drvdata(m4updev));
+	}
+
+	ret = iommu_fwspec_add_ids(dev, args->args, 1);
+	if (ret)
+		return ret;
+
+	data = dev_iommu_priv_get(dev);
+	mtk_mapping = data->mapping;
+	if (!mtk_mapping) {
+		/* MTK iommu support 4GB iova address space. */
+		mtk_mapping = arm_iommu_create_mapping(&platform_bus_type,
+						0, 1ULL << 32);
+		if (IS_ERR(mtk_mapping))
+			return PTR_ERR(mtk_mapping);
+
+		data->mapping = mtk_mapping;
+	}
+
+	return 0;
+}
+
+static int mtk_iommu_v1_def_domain_type(struct device *dev)
+{
+	return IOMMU_DOMAIN_UNMANAGED;
+}
+
+static struct iommu_device *mtk_iommu_v1_probe_device(struct device *dev)
+{
+	struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev);
+	struct of_phandle_args iommu_spec;
+	struct mtk_iommu_v1_data *data;
+	int err, idx = 0, larbid, larbidx;
+	struct device_link *link;
+	struct device *larbdev;
+
+	/*
+	 * In the deferred case, free the existed fwspec.
+	 * Always initialize the fwspec internally.
+	 */
+	if (fwspec) {
+		iommu_fwspec_free(dev);
+		fwspec = dev_iommu_fwspec_get(dev);
+	}
+
+	while (!of_parse_phandle_with_args(dev->of_node, "iommus",
+					   "#iommu-cells",
+					   idx, &iommu_spec)) {
+
+		err = mtk_iommu_v1_create_mapping(dev, &iommu_spec);
+		of_node_put(iommu_spec.np);
+		if (err)
+			return ERR_PTR(err);
+
+		/* dev->iommu_fwspec might have changed */
+		fwspec = dev_iommu_fwspec_get(dev);
+		idx++;
+	}
+
+	if (!fwspec || fwspec->ops != &mtk_iommu_v1_ops)
+		return ERR_PTR(-ENODEV); /* Not a iommu client device */
+
+	data = dev_iommu_priv_get(dev);
+
+	/* Link the consumer device with the smi-larb device(supplier) */
+	larbid = mt2701_m4u_to_larb(fwspec->ids[0]);
+	if (larbid >= MT2701_LARB_NR_MAX)
+		return ERR_PTR(-EINVAL);
+
+	for (idx = 1; idx < fwspec->num_ids; idx++) {
+		larbidx = mt2701_m4u_to_larb(fwspec->ids[idx]);
+		if (larbid != larbidx) {
+			dev_err(dev, "Can only use one larb. Fail@larb%d-%d.\n",
+				larbid, larbidx);
+			return ERR_PTR(-EINVAL);
+		}
+	}
+
+	larbdev = data->larb_imu[larbid].dev;
+	if (!larbdev)
+		return ERR_PTR(-EINVAL);
+
+	link = device_link_add(dev, larbdev,
+			       DL_FLAG_PM_RUNTIME | DL_FLAG_STATELESS);
+	if (!link)
+		dev_err(dev, "Unable to link %s\n", dev_name(larbdev));
+
+	return &data->iommu;
+}
+
+static void mtk_iommu_v1_probe_finalize(struct device *dev)
+{
+	struct dma_iommu_mapping *mtk_mapping;
+	struct mtk_iommu_v1_data *data;
+	int err;
+
+	data        = dev_iommu_priv_get(dev);
+	mtk_mapping = data->mapping;
+
+	err = arm_iommu_attach_device(dev, mtk_mapping);
+	if (err)
+		dev_err(dev, "Can't create IOMMU mapping - DMA-OPS will not work\n");
+}
+
+static void mtk_iommu_v1_release_device(struct device *dev)
+{
+	struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev);
+	struct mtk_iommu_v1_data *data;
+	struct device *larbdev;
+	unsigned int larbid;
+
+	data = dev_iommu_priv_get(dev);
+	larbid = mt2701_m4u_to_larb(fwspec->ids[0]);
+	larbdev = data->larb_imu[larbid].dev;
+	device_link_remove(dev, larbdev);
+}
+
+static int mtk_iommu_v1_hw_init(const struct mtk_iommu_v1_data *data)
+{
+	u32 regval;
+	int ret;
+
+	ret = clk_prepare_enable(data->bclk);
+	if (ret) {
+		dev_err(data->dev, "Failed to enable iommu bclk(%d)\n", ret);
+		return ret;
+	}
+
+	regval = F_MMU_CTRL_COHERENT_EN | F_MMU_TF_PROTECT_SEL(2);
+	writel_relaxed(regval, data->base + REG_MMU_CTRL_REG);
+
+	regval = F_INT_TRANSLATION_FAULT |
+		F_INT_MAIN_MULTI_HIT_FAULT |
+		F_INT_INVALID_PA_FAULT |
+		F_INT_ENTRY_REPLACEMENT_FAULT |
+		F_INT_TABLE_WALK_FAULT |
+		F_INT_TLB_MISS_FAULT |
+		F_INT_PFH_DMA_FIFO_OVERFLOW |
+		F_INT_MISS_DMA_FIFO_OVERFLOW;
+	writel_relaxed(regval, data->base + REG_MMU_INT_CONTROL);
+
+	/* protect memory,hw will write here while translation fault */
+	writel_relaxed(data->protect_base,
+			data->base + REG_MMU_IVRP_PADDR);
+
+	writel_relaxed(F_MMU_DCM_ON, data->base + REG_MMU_DCM);
+
+	if (devm_request_irq(data->dev, data->irq, mtk_iommu_v1_isr, 0,
+			     dev_name(data->dev), (void *)data)) {
+		writel_relaxed(0, data->base + REG_MMU_PT_BASE_ADDR);
+		clk_disable_unprepare(data->bclk);
+		dev_err(data->dev, "Failed @ IRQ-%d Request\n", data->irq);
+		return -ENODEV;
+	}
+
+	return 0;
+}
+
+static const struct iommu_ops mtk_iommu_v1_ops = {
+	.domain_alloc	= mtk_iommu_v1_domain_alloc,
+	.probe_device	= mtk_iommu_v1_probe_device,
+	.probe_finalize = mtk_iommu_v1_probe_finalize,
+	.release_device	= mtk_iommu_v1_release_device,
+	.def_domain_type = mtk_iommu_v1_def_domain_type,
+	.device_group	= generic_device_group,
+	.pgsize_bitmap	= MT2701_IOMMU_PAGE_SIZE,
+	.owner          = THIS_MODULE,
+	.default_domain_ops = &(const struct iommu_domain_ops) {
+		.attach_dev	= mtk_iommu_v1_attach_device,
+		.detach_dev	= mtk_iommu_v1_detach_device,
+		.map_pages	= mtk_iommu_v1_map,
+		.unmap_pages	= mtk_iommu_v1_unmap,
+		.iova_to_phys	= mtk_iommu_v1_iova_to_phys,
+		.free		= mtk_iommu_v1_domain_free,
+	}
+};
+
+static const struct of_device_id mtk_iommu_v1_of_ids[] = {
+	{ .compatible = "mediatek,mt2701-m4u", },
+	{}
+};
+
+static const struct component_master_ops mtk_iommu_v1_com_ops = {
+	.bind		= mtk_iommu_v1_bind,
+	.unbind		= mtk_iommu_v1_unbind,
+};
+
+static int mtk_iommu_v1_probe(struct platform_device *pdev)
+{
+	struct device			*dev = &pdev->dev;
+	struct mtk_iommu_v1_data	*data;
+	struct resource			*res;
+	struct component_match		*match = NULL;
+	void				*protect;
+	int				larb_nr, ret, i;
+
+	data = devm_kzalloc(dev, sizeof(*data), GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
+
+	data->dev = dev;
+
+	/* Protect memory. HW will access here while translation fault.*/
+	protect = devm_kzalloc(dev, MTK_PROTECT_PA_ALIGN * 2,
+			GFP_KERNEL | GFP_DMA);
+	if (!protect)
+		return -ENOMEM;
+	data->protect_base = ALIGN(virt_to_phys(protect), MTK_PROTECT_PA_ALIGN);
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	data->base = devm_ioremap_resource(dev, res);
+	if (IS_ERR(data->base))
+		return PTR_ERR(data->base);
+
+	data->irq = platform_get_irq(pdev, 0);
+	if (data->irq < 0)
+		return data->irq;
+
+	data->bclk = devm_clk_get(dev, "bclk");
+	if (IS_ERR(data->bclk))
+		return PTR_ERR(data->bclk);
+
+	larb_nr = of_count_phandle_with_args(dev->of_node,
+					     "mediatek,larbs", NULL);
+	if (larb_nr < 0)
+		return larb_nr;
+
+	for (i = 0; i < larb_nr; i++) {
+		struct device_node *larbnode;
+		struct platform_device *plarbdev;
+
+		larbnode = of_parse_phandle(dev->of_node, "mediatek,larbs", i);
+		if (!larbnode)
+			return -EINVAL;
+
+		if (!of_device_is_available(larbnode)) {
+			of_node_put(larbnode);
+			continue;
+		}
+
+		plarbdev = of_find_device_by_node(larbnode);
+		if (!plarbdev) {
+			of_node_put(larbnode);
+			return -ENODEV;
+		}
+		if (!plarbdev->dev.driver) {
+			of_node_put(larbnode);
+			return -EPROBE_DEFER;
+		}
+		data->larb_imu[i].dev = &plarbdev->dev;
+
+		component_match_add_release(dev, &match, component_release_of,
+					    component_compare_of, larbnode);
+	}
+
+	platform_set_drvdata(pdev, data);
+
+	ret = mtk_iommu_v1_hw_init(data);
+	if (ret)
+		return ret;
+
+	ret = iommu_device_sysfs_add(&data->iommu, &pdev->dev, NULL,
+				     dev_name(&pdev->dev));
+	if (ret)
+		goto out_clk_unprepare;
+
+	ret = iommu_device_register(&data->iommu, &mtk_iommu_v1_ops, dev);
+	if (ret)
+		goto out_sysfs_remove;
+
+	ret = component_master_add_with_match(dev, &mtk_iommu_v1_com_ops, match);
+	if (ret)
+		goto out_dev_unreg;
+	return ret;
+
+out_dev_unreg:
+	iommu_device_unregister(&data->iommu);
+out_sysfs_remove:
+	iommu_device_sysfs_remove(&data->iommu);
+out_clk_unprepare:
+	clk_disable_unprepare(data->bclk);
+	return ret;
+}
+
+static int mtk_iommu_v1_remove(struct platform_device *pdev)
+{
+	struct mtk_iommu_v1_data *data = platform_get_drvdata(pdev);
+
+	iommu_device_sysfs_remove(&data->iommu);
+	iommu_device_unregister(&data->iommu);
+
+	clk_disable_unprepare(data->bclk);
+	devm_free_irq(&pdev->dev, data->irq, data);
+	component_master_del(&pdev->dev, &mtk_iommu_v1_com_ops);
+	return 0;
+}
+
+static int __maybe_unused mtk_iommu_v1_suspend(struct device *dev)
+{
+	struct mtk_iommu_v1_data *data = dev_get_drvdata(dev);
+	struct mtk_iommu_v1_suspend_reg *reg = &data->reg;
+	void __iomem *base = data->base;
+
+	reg->standard_axi_mode = readl_relaxed(base +
+					       REG_MMU_STANDARD_AXI_MODE);
+	reg->dcm_dis = readl_relaxed(base + REG_MMU_DCM);
+	reg->ctrl_reg = readl_relaxed(base + REG_MMU_CTRL_REG);
+	reg->int_control0 = readl_relaxed(base + REG_MMU_INT_CONTROL);
+	return 0;
+}
+
+static int __maybe_unused mtk_iommu_v1_resume(struct device *dev)
+{
+	struct mtk_iommu_v1_data *data = dev_get_drvdata(dev);
+	struct mtk_iommu_v1_suspend_reg *reg = &data->reg;
+	void __iomem *base = data->base;
+
+	writel_relaxed(data->m4u_dom->pgt_pa, base + REG_MMU_PT_BASE_ADDR);
+	writel_relaxed(reg->standard_axi_mode,
+		       base + REG_MMU_STANDARD_AXI_MODE);
+	writel_relaxed(reg->dcm_dis, base + REG_MMU_DCM);
+	writel_relaxed(reg->ctrl_reg, base + REG_MMU_CTRL_REG);
+	writel_relaxed(reg->int_control0, base + REG_MMU_INT_CONTROL);
+	writel_relaxed(data->protect_base, base + REG_MMU_IVRP_PADDR);
+	return 0;
+}
+
+static const struct dev_pm_ops mtk_iommu_v1_pm_ops = {
+	SET_SYSTEM_SLEEP_PM_OPS(mtk_iommu_v1_suspend, mtk_iommu_v1_resume)
+};
+
+static struct platform_driver mtk_iommu_v1_driver = {
+	.probe	= mtk_iommu_v1_probe,
+	.remove	= mtk_iommu_v1_remove,
+	.driver	= {
+		.name = "mtk-iommu-v1",
+		.of_match_table = mtk_iommu_v1_of_ids,
+		.pm = &mtk_iommu_v1_pm_ops,
+	}
+};
+module_platform_driver(mtk_iommu_v1_driver);
+
+MODULE_DESCRIPTION("IOMMU API for MediaTek M4U v1 implementations");
+MODULE_LICENSE("GPL v2");