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, 561 insertions, 0 deletions

diff --git a/drivers/pci/controller/pcie-rcar-ep.c b/drivers/pci/controller/pcie-rcar-ep.c
new file mode 100644
index 000000000..f9682df1d
--- /dev/null
+++ b/drivers/pci/controller/pcie-rcar-ep.c
@@ -0,0 +1,561 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * PCIe endpoint driver for Renesas R-Car SoCs
+ *  Copyright (c) 2020 Renesas Electronics Europe GmbH
+ *
+ * Author: Lad Prabhakar <prabhakar.mahadev-lad.rj@bp.renesas.com>
+ */
+
+#include <linux/delay.h>
+#include <linux/of_address.h>
+#include <linux/of_platform.h>
+#include <linux/pci.h>
+#include <linux/pci-epc.h>
+#include <linux/platform_device.h>
+#include <linux/pm_runtime.h>
+
+#include "pcie-rcar.h"
+
+#define RCAR_EPC_MAX_FUNCTIONS		1
+
+/* Structure representing the PCIe interface */
+struct rcar_pcie_endpoint {
+	struct rcar_pcie	pcie;
+	phys_addr_t		*ob_mapped_addr;
+	struct pci_epc_mem_window *ob_window;
+	u8			max_functions;
+	unsigned int		bar_to_atu[MAX_NR_INBOUND_MAPS];
+	unsigned long		*ib_window_map;
+	u32			num_ib_windows;
+	u32			num_ob_windows;
+};
+
+static void rcar_pcie_ep_hw_init(struct rcar_pcie *pcie)
+{
+	u32 val;
+
+	rcar_pci_write_reg(pcie, 0, PCIETCTLR);
+
+	/* Set endpoint mode */
+	rcar_pci_write_reg(pcie, 0, PCIEMSR);
+
+	/* Initialize default capabilities. */
+	rcar_rmw32(pcie, REXPCAP(0), 0xff, PCI_CAP_ID_EXP);
+	rcar_rmw32(pcie, REXPCAP(PCI_EXP_FLAGS),
+		   PCI_EXP_FLAGS_TYPE, PCI_EXP_TYPE_ENDPOINT << 4);
+	rcar_rmw32(pcie, RCONF(PCI_HEADER_TYPE), 0x7f,
+		   PCI_HEADER_TYPE_NORMAL);
+
+	/* Write out the physical slot number = 0 */
+	rcar_rmw32(pcie, REXPCAP(PCI_EXP_SLTCAP), PCI_EXP_SLTCAP_PSN, 0);
+
+	val = rcar_pci_read_reg(pcie, EXPCAP(1));
+	/* device supports fixed 128 bytes MPSS */
+	val &= ~GENMASK(2, 0);
+	rcar_pci_write_reg(pcie, val, EXPCAP(1));
+
+	val = rcar_pci_read_reg(pcie, EXPCAP(2));
+	/* read requests size 128 bytes */
+	val &= ~GENMASK(14, 12);
+	/* payload size 128 bytes */
+	val &= ~GENMASK(7, 5);
+	rcar_pci_write_reg(pcie, val, EXPCAP(2));
+
+	/* Set target link speed to 5.0 GT/s */
+	rcar_rmw32(pcie, EXPCAP(12), PCI_EXP_LNKSTA_CLS,
+		   PCI_EXP_LNKSTA_CLS_5_0GB);
+
+	/* Set the completion timer timeout to the maximum 50ms. */
+	rcar_rmw32(pcie, TLCTLR + 1, 0x3f, 50);
+
+	/* Terminate list of capabilities (Next Capability Offset=0) */
+	rcar_rmw32(pcie, RVCCAP(0), 0xfff00000, 0);
+
+	/* flush modifications */
+	wmb();
+}
+
+static int rcar_pcie_ep_get_window(struct rcar_pcie_endpoint *ep,
+				   phys_addr_t addr)
+{
+	int i;
+
+	for (i = 0; i < ep->num_ob_windows; i++)
+		if (ep->ob_window[i].phys_base == addr)
+			return i;
+
+	return -EINVAL;
+}
+
+static int rcar_pcie_parse_outbound_ranges(struct rcar_pcie_endpoint *ep,
+					   struct platform_device *pdev)
+{
+	struct rcar_pcie *pcie = &ep->pcie;
+	char outbound_name[10];
+	struct resource *res;
+	unsigned int i = 0;
+
+	ep->num_ob_windows = 0;
+	for (i = 0; i < RCAR_PCI_MAX_RESOURCES; i++) {
+		sprintf(outbound_name, "memory%u", i);
+		res = platform_get_resource_byname(pdev,
+						   IORESOURCE_MEM,
+						   outbound_name);
+		if (!res) {
+			dev_err(pcie->dev, "missing outbound window %u\n", i);
+			return -EINVAL;
+		}
+		if (!devm_request_mem_region(&pdev->dev, res->start,
+					     resource_size(res),
+					     outbound_name)) {
+			dev_err(pcie->dev, "Cannot request memory region %s.\n",
+				outbound_name);
+			return -EIO;
+		}
+
+		ep->ob_window[i].phys_base = res->start;
+		ep->ob_window[i].size = resource_size(res);
+		/* controller doesn't support multiple allocation
+		 * from same window, so set page_size to window size
+		 */
+		ep->ob_window[i].page_size = resource_size(res);
+	}
+	ep->num_ob_windows = i;
+
+	return 0;
+}
+
+static int rcar_pcie_ep_get_pdata(struct rcar_pcie_endpoint *ep,
+				  struct platform_device *pdev)
+{
+	struct rcar_pcie *pcie = &ep->pcie;
+	struct pci_epc_mem_window *window;
+	struct device *dev = pcie->dev;
+	struct resource res;
+	int err;
+
+	err = of_address_to_resource(dev->of_node, 0, &res);
+	if (err)
+		return err;
+	pcie->base = devm_ioremap_resource(dev, &res);
+	if (IS_ERR(pcie->base))
+		return PTR_ERR(pcie->base);
+
+	ep->ob_window = devm_kcalloc(dev, RCAR_PCI_MAX_RESOURCES,
+				     sizeof(*window), GFP_KERNEL);
+	if (!ep->ob_window)
+		return -ENOMEM;
+
+	rcar_pcie_parse_outbound_ranges(ep, pdev);
+
+	err = of_property_read_u8(dev->of_node, "max-functions",
+				  &ep->max_functions);
+	if (err < 0 || ep->max_functions > RCAR_EPC_MAX_FUNCTIONS)
+		ep->max_functions = RCAR_EPC_MAX_FUNCTIONS;
+
+	return 0;
+}
+
+static int rcar_pcie_ep_write_header(struct pci_epc *epc, u8 fn, u8 vfn,
+				     struct pci_epf_header *hdr)
+{
+	struct rcar_pcie_endpoint *ep = epc_get_drvdata(epc);
+	struct rcar_pcie *pcie = &ep->pcie;
+	u32 val;
+
+	if (!fn)
+		val = hdr->vendorid;
+	else
+		val = rcar_pci_read_reg(pcie, IDSETR0);
+	val |= hdr->deviceid << 16;
+	rcar_pci_write_reg(pcie, val, IDSETR0);
+
+	val = hdr->revid;
+	val |= hdr->progif_code << 8;
+	val |= hdr->subclass_code << 16;
+	val |= hdr->baseclass_code << 24;
+	rcar_pci_write_reg(pcie, val, IDSETR1);
+
+	if (!fn)
+		val = hdr->subsys_vendor_id;
+	else
+		val = rcar_pci_read_reg(pcie, SUBIDSETR);
+	val |= hdr->subsys_id << 16;
+	rcar_pci_write_reg(pcie, val, SUBIDSETR);
+
+	if (hdr->interrupt_pin > PCI_INTERRUPT_INTA)
+		return -EINVAL;
+	val = rcar_pci_read_reg(pcie, PCICONF(15));
+	val |= (hdr->interrupt_pin << 8);
+	rcar_pci_write_reg(pcie, val, PCICONF(15));
+
+	return 0;
+}
+
+static int rcar_pcie_ep_set_bar(struct pci_epc *epc, u8 func_no, u8 vfunc_no,
+				struct pci_epf_bar *epf_bar)
+{
+	int flags = epf_bar->flags | LAR_ENABLE | LAM_64BIT;
+	struct rcar_pcie_endpoint *ep = epc_get_drvdata(epc);
+	u64 size = 1ULL << fls64(epf_bar->size - 1);
+	dma_addr_t cpu_addr = epf_bar->phys_addr;
+	enum pci_barno bar = epf_bar->barno;
+	struct rcar_pcie *pcie = &ep->pcie;
+	u32 mask;
+	int idx;
+	int err;
+
+	idx = find_first_zero_bit(ep->ib_window_map, ep->num_ib_windows);
+	if (idx >= ep->num_ib_windows) {
+		dev_err(pcie->dev, "no free inbound window\n");
+		return -EINVAL;
+	}
+
+	if ((flags & PCI_BASE_ADDRESS_SPACE) == PCI_BASE_ADDRESS_SPACE_IO)
+		flags |= IO_SPACE;
+
+	ep->bar_to_atu[bar] = idx;
+	/* use 64-bit BARs */
+	set_bit(idx, ep->ib_window_map);
+	set_bit(idx + 1, ep->ib_window_map);
+
+	if (cpu_addr > 0) {
+		unsigned long nr_zeros = __ffs64(cpu_addr);
+		u64 alignment = 1ULL << nr_zeros;
+
+		size = min(size, alignment);
+	}
+
+	size = min(size, 1ULL << 32);
+
+	mask = roundup_pow_of_two(size) - 1;
+	mask &= ~0xf;
+
+	rcar_pcie_set_inbound(pcie, cpu_addr,
+			      0x0, mask | flags, idx, false);
+
+	err = rcar_pcie_wait_for_phyrdy(pcie);
+	if (err) {
+		dev_err(pcie->dev, "phy not ready\n");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static void rcar_pcie_ep_clear_bar(struct pci_epc *epc, u8 fn, u8 vfn,
+				   struct pci_epf_bar *epf_bar)
+{
+	struct rcar_pcie_endpoint *ep = epc_get_drvdata(epc);
+	enum pci_barno bar = epf_bar->barno;
+	u32 atu_index = ep->bar_to_atu[bar];
+
+	rcar_pcie_set_inbound(&ep->pcie, 0x0, 0x0, 0x0, bar, false);
+
+	clear_bit(atu_index, ep->ib_window_map);
+	clear_bit(atu_index + 1, ep->ib_window_map);
+}
+
+static int rcar_pcie_ep_set_msi(struct pci_epc *epc, u8 fn, u8 vfn,
+				u8 interrupts)
+{
+	struct rcar_pcie_endpoint *ep = epc_get_drvdata(epc);
+	struct rcar_pcie *pcie = &ep->pcie;
+	u32 flags;
+
+	flags = rcar_pci_read_reg(pcie, MSICAP(fn));
+	flags |= interrupts << MSICAP0_MMESCAP_OFFSET;
+	rcar_pci_write_reg(pcie, flags, MSICAP(fn));
+
+	return 0;
+}
+
+static int rcar_pcie_ep_get_msi(struct pci_epc *epc, u8 fn, u8 vfn)
+{
+	struct rcar_pcie_endpoint *ep = epc_get_drvdata(epc);
+	struct rcar_pcie *pcie = &ep->pcie;
+	u32 flags;
+
+	flags = rcar_pci_read_reg(pcie, MSICAP(fn));
+	if (!(flags & MSICAP0_MSIE))
+		return -EINVAL;
+
+	return ((flags & MSICAP0_MMESE_MASK) >> MSICAP0_MMESE_OFFSET);
+}
+
+static int rcar_pcie_ep_map_addr(struct pci_epc *epc, u8 fn, u8 vfn,
+				 phys_addr_t addr, u64 pci_addr, size_t size)
+{
+	struct rcar_pcie_endpoint *ep = epc_get_drvdata(epc);
+	struct rcar_pcie *pcie = &ep->pcie;
+	struct resource_entry win;
+	struct resource res;
+	int window;
+	int err;
+
+	/* check if we have a link. */
+	err = rcar_pcie_wait_for_dl(pcie);
+	if (err) {
+		dev_err(pcie->dev, "link not up\n");
+		return err;
+	}
+
+	window = rcar_pcie_ep_get_window(ep, addr);
+	if (window < 0) {
+		dev_err(pcie->dev, "failed to get corresponding window\n");
+		return -EINVAL;
+	}
+
+	memset(&win, 0x0, sizeof(win));
+	memset(&res, 0x0, sizeof(res));
+	res.start = pci_addr;
+	res.end = pci_addr + size - 1;
+	res.flags = IORESOURCE_MEM;
+	win.res = &res;
+
+	rcar_pcie_set_outbound(pcie, window, &win);
+
+	ep->ob_mapped_addr[window] = addr;
+
+	return 0;
+}
+
+static void rcar_pcie_ep_unmap_addr(struct pci_epc *epc, u8 fn, u8 vfn,
+				    phys_addr_t addr)
+{
+	struct rcar_pcie_endpoint *ep = epc_get_drvdata(epc);
+	struct resource_entry win;
+	struct resource res;
+	int idx;
+
+	for (idx = 0; idx < ep->num_ob_windows; idx++)
+		if (ep->ob_mapped_addr[idx] == addr)
+			break;
+
+	if (idx >= ep->num_ob_windows)
+		return;
+
+	memset(&win, 0x0, sizeof(win));
+	memset(&res, 0x0, sizeof(res));
+	win.res = &res;
+	rcar_pcie_set_outbound(&ep->pcie, idx, &win);
+
+	ep->ob_mapped_addr[idx] = 0;
+}
+
+static int rcar_pcie_ep_assert_intx(struct rcar_pcie_endpoint *ep,
+				    u8 fn, u8 intx)
+{
+	struct rcar_pcie *pcie = &ep->pcie;
+	u32 val;
+
+	val = rcar_pci_read_reg(pcie, PCIEMSITXR);
+	if ((val & PCI_MSI_FLAGS_ENABLE)) {
+		dev_err(pcie->dev, "MSI is enabled, cannot assert INTx\n");
+		return -EINVAL;
+	}
+
+	val = rcar_pci_read_reg(pcie, PCICONF(1));
+	if ((val & INTDIS)) {
+		dev_err(pcie->dev, "INTx message transmission is disabled\n");
+		return -EINVAL;
+	}
+
+	val = rcar_pci_read_reg(pcie, PCIEINTXR);
+	if ((val & ASTINTX)) {
+		dev_err(pcie->dev, "INTx is already asserted\n");
+		return -EINVAL;
+	}
+
+	val |= ASTINTX;
+	rcar_pci_write_reg(pcie, val, PCIEINTXR);
+	usleep_range(1000, 1001);
+	val = rcar_pci_read_reg(pcie, PCIEINTXR);
+	val &= ~ASTINTX;
+	rcar_pci_write_reg(pcie, val, PCIEINTXR);
+
+	return 0;
+}
+
+static int rcar_pcie_ep_assert_msi(struct rcar_pcie *pcie,
+				   u8 fn, u8 interrupt_num)
+{
+	u16 msi_count;
+	u32 val;
+
+	/* Check MSI enable bit */
+	val = rcar_pci_read_reg(pcie, MSICAP(fn));
+	if (!(val & MSICAP0_MSIE))
+		return -EINVAL;
+
+	/* Get MSI numbers from MME */
+	msi_count = ((val & MSICAP0_MMESE_MASK) >> MSICAP0_MMESE_OFFSET);
+	msi_count = 1 << msi_count;
+
+	if (!interrupt_num || interrupt_num > msi_count)
+		return -EINVAL;
+
+	val = rcar_pci_read_reg(pcie, PCIEMSITXR);
+	rcar_pci_write_reg(pcie, val | (interrupt_num - 1), PCIEMSITXR);
+
+	return 0;
+}
+
+static int rcar_pcie_ep_raise_irq(struct pci_epc *epc, u8 fn, u8 vfn,
+				  enum pci_epc_irq_type type,
+				  u16 interrupt_num)
+{
+	struct rcar_pcie_endpoint *ep = epc_get_drvdata(epc);
+
+	switch (type) {
+	case PCI_EPC_IRQ_LEGACY:
+		return rcar_pcie_ep_assert_intx(ep, fn, 0);
+
+	case PCI_EPC_IRQ_MSI:
+		return rcar_pcie_ep_assert_msi(&ep->pcie, fn, interrupt_num);
+
+	default:
+		return -EINVAL;
+	}
+}
+
+static int rcar_pcie_ep_start(struct pci_epc *epc)
+{
+	struct rcar_pcie_endpoint *ep = epc_get_drvdata(epc);
+
+	rcar_pci_write_reg(&ep->pcie, MACCTLR_INIT_VAL, MACCTLR);
+	rcar_pci_write_reg(&ep->pcie, CFINIT, PCIETCTLR);
+
+	return 0;
+}
+
+static void rcar_pcie_ep_stop(struct pci_epc *epc)
+{
+	struct rcar_pcie_endpoint *ep = epc_get_drvdata(epc);
+
+	rcar_pci_write_reg(&ep->pcie, 0, PCIETCTLR);
+}
+
+static const struct pci_epc_features rcar_pcie_epc_features = {
+	.linkup_notifier = false,
+	.msi_capable = true,
+	.msix_capable = false,
+	/* use 64-bit BARs so mark BAR[1,3,5] as reserved */
+	.reserved_bar = 1 << BAR_1 | 1 << BAR_3 | 1 << BAR_5,
+	.bar_fixed_64bit = 1 << BAR_0 | 1 << BAR_2 | 1 << BAR_4,
+	.bar_fixed_size[0] = 128,
+	.bar_fixed_size[2] = 256,
+	.bar_fixed_size[4] = 256,
+};
+
+static const struct pci_epc_features*
+rcar_pcie_ep_get_features(struct pci_epc *epc, u8 func_no, u8 vfunc_no)
+{
+	return &rcar_pcie_epc_features;
+}
+
+static const struct pci_epc_ops rcar_pcie_epc_ops = {
+	.write_header	= rcar_pcie_ep_write_header,
+	.set_bar	= rcar_pcie_ep_set_bar,
+	.clear_bar	= rcar_pcie_ep_clear_bar,
+	.set_msi	= rcar_pcie_ep_set_msi,
+	.get_msi	= rcar_pcie_ep_get_msi,
+	.map_addr	= rcar_pcie_ep_map_addr,
+	.unmap_addr	= rcar_pcie_ep_unmap_addr,
+	.raise_irq	= rcar_pcie_ep_raise_irq,
+	.start		= rcar_pcie_ep_start,
+	.stop		= rcar_pcie_ep_stop,
+	.get_features	= rcar_pcie_ep_get_features,
+};
+
+static const struct of_device_id rcar_pcie_ep_of_match[] = {
+	{ .compatible = "renesas,r8a774c0-pcie-ep", },
+	{ .compatible = "renesas,rcar-gen3-pcie-ep" },
+	{ },
+};
+
+static int rcar_pcie_ep_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct rcar_pcie_endpoint *ep;
+	struct rcar_pcie *pcie;
+	struct pci_epc *epc;
+	int err;
+
+	ep = devm_kzalloc(dev, sizeof(*ep), GFP_KERNEL);
+	if (!ep)
+		return -ENOMEM;
+
+	pcie = &ep->pcie;
+	pcie->dev = dev;
+
+	pm_runtime_enable(dev);
+	err = pm_runtime_resume_and_get(dev);
+	if (err < 0) {
+		dev_err(dev, "pm_runtime_resume_and_get failed\n");
+		goto err_pm_disable;
+	}
+
+	err = rcar_pcie_ep_get_pdata(ep, pdev);
+	if (err < 0) {
+		dev_err(dev, "failed to request resources: %d\n", err);
+		goto err_pm_put;
+	}
+
+	ep->num_ib_windows = MAX_NR_INBOUND_MAPS;
+	ep->ib_window_map =
+			devm_kcalloc(dev, BITS_TO_LONGS(ep->num_ib_windows),
+				     sizeof(long), GFP_KERNEL);
+	if (!ep->ib_window_map) {
+		err = -ENOMEM;
+		dev_err(dev, "failed to allocate memory for inbound map\n");
+		goto err_pm_put;
+	}
+
+	ep->ob_mapped_addr = devm_kcalloc(dev, ep->num_ob_windows,
+					  sizeof(*ep->ob_mapped_addr),
+					  GFP_KERNEL);
+	if (!ep->ob_mapped_addr) {
+		err = -ENOMEM;
+		dev_err(dev, "failed to allocate memory for outbound memory pointers\n");
+		goto err_pm_put;
+	}
+
+	epc = devm_pci_epc_create(dev, &rcar_pcie_epc_ops);
+	if (IS_ERR(epc)) {
+		dev_err(dev, "failed to create epc device\n");
+		err = PTR_ERR(epc);
+		goto err_pm_put;
+	}
+
+	epc->max_functions = ep->max_functions;
+	epc_set_drvdata(epc, ep);
+
+	rcar_pcie_ep_hw_init(pcie);
+
+	err = pci_epc_multi_mem_init(epc, ep->ob_window, ep->num_ob_windows);
+	if (err < 0) {
+		dev_err(dev, "failed to initialize the epc memory space\n");
+		goto err_pm_put;
+	}
+
+	return 0;
+
+err_pm_put:
+	pm_runtime_put(dev);
+
+err_pm_disable:
+	pm_runtime_disable(dev);
+
+	return err;
+}
+
+static struct platform_driver rcar_pcie_ep_driver = {
+	.driver = {
+		.name = "rcar-pcie-ep",
+		.of_match_table = rcar_pcie_ep_of_match,
+		.suppress_bind_attrs = true,
+	},
+	.probe = rcar_pcie_ep_probe,
+};
+builtin_platform_driver(rcar_pcie_ep_driver);