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, 480 insertions, 0 deletions

diff --git a/drivers/pci/controller/pci-thunder-pem.c b/drivers/pci/controller/pci-thunder-pem.c
new file mode 100644
index 000000000..06a9855cb
--- /dev/null
+++ b/drivers/pci/controller/pci-thunder-pem.c
@@ -0,0 +1,480 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2015 - 2016 Cavium, Inc.
+ */
+
+#include <linux/bitfield.h>
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/pci.h>
+#include <linux/of_address.h>
+#include <linux/of_pci.h>
+#include <linux/pci-acpi.h>
+#include <linux/pci-ecam.h>
+#include <linux/platform_device.h>
+#include <linux/io-64-nonatomic-lo-hi.h>
+#include "../pci.h"
+
+#if defined(CONFIG_PCI_HOST_THUNDER_PEM) || (defined(CONFIG_ACPI) && defined(CONFIG_PCI_QUIRKS))
+
+#define PEM_CFG_WR 0x28
+#define PEM_CFG_RD 0x30
+
+/*
+ * Enhanced Configuration Access Mechanism (ECAM)
+ *
+ * N.B. This is a non-standard platform-specific ECAM bus shift value.  For
+ * standard values defined in the PCI Express Base Specification see
+ * include/linux/pci-ecam.h.
+ */
+#define THUNDER_PCIE_ECAM_BUS_SHIFT	24
+
+struct thunder_pem_pci {
+	u32		ea_entry[3];
+	void __iomem	*pem_reg_base;
+};
+
+static int thunder_pem_bridge_read(struct pci_bus *bus, unsigned int devfn,
+				   int where, int size, u32 *val)
+{
+	u64 read_val, tmp_val;
+	struct pci_config_window *cfg = bus->sysdata;
+	struct thunder_pem_pci *pem_pci = (struct thunder_pem_pci *)cfg->priv;
+
+	if (devfn != 0 || where >= 2048)
+		return PCIBIOS_DEVICE_NOT_FOUND;
+
+	/*
+	 * 32-bit accesses only.  Write the address to the low order
+	 * bits of PEM_CFG_RD, then trigger the read by reading back.
+	 * The config data lands in the upper 32-bits of PEM_CFG_RD.
+	 */
+	read_val = where & ~3ull;
+	writeq(read_val, pem_pci->pem_reg_base + PEM_CFG_RD);
+	read_val = readq(pem_pci->pem_reg_base + PEM_CFG_RD);
+	read_val >>= 32;
+
+	/*
+	 * The config space contains some garbage, fix it up.  Also
+	 * synthesize an EA capability for the BAR used by MSI-X.
+	 */
+	switch (where & ~3) {
+	case 0x40:
+		read_val &= 0xffff00ff;
+		read_val |= 0x00007000; /* Skip MSI CAP */
+		break;
+	case 0x70: /* Express Cap */
+		/*
+		 * Change PME interrupt to vector 2 on T88 where it
+		 * reads as 0, else leave it alone.
+		 */
+		if (!(read_val & (0x1f << 25)))
+			read_val |= (2u << 25);
+		break;
+	case 0xb0: /* MSI-X Cap */
+		/* TableSize=2 or 4, Next Cap is EA */
+		read_val &= 0xc00000ff;
+		/*
+		 * If Express Cap(0x70) raw PME vector reads as 0 we are on
+		 * T88 and TableSize is reported as 4, else TableSize
+		 * is 2.
+		 */
+		writeq(0x70, pem_pci->pem_reg_base + PEM_CFG_RD);
+		tmp_val = readq(pem_pci->pem_reg_base + PEM_CFG_RD);
+		tmp_val >>= 32;
+		if (!(tmp_val & (0x1f << 25)))
+			read_val |= 0x0003bc00;
+		else
+			read_val |= 0x0001bc00;
+		break;
+	case 0xb4:
+		/* Table offset=0, BIR=0 */
+		read_val = 0x00000000;
+		break;
+	case 0xb8:
+		/* BPA offset=0xf0000, BIR=0 */
+		read_val = 0x000f0000;
+		break;
+	case 0xbc:
+		/* EA, 1 entry, no next Cap */
+		read_val = 0x00010014;
+		break;
+	case 0xc0:
+		/* DW2 for type-1 */
+		read_val = 0x00000000;
+		break;
+	case 0xc4:
+		/* Entry BEI=0, PP=0x00, SP=0xff, ES=3 */
+		read_val = 0x80ff0003;
+		break;
+	case 0xc8:
+		read_val = pem_pci->ea_entry[0];
+		break;
+	case 0xcc:
+		read_val = pem_pci->ea_entry[1];
+		break;
+	case 0xd0:
+		read_val = pem_pci->ea_entry[2];
+		break;
+	default:
+		break;
+	}
+	read_val >>= (8 * (where & 3));
+	switch (size) {
+	case 1:
+		read_val &= 0xff;
+		break;
+	case 2:
+		read_val &= 0xffff;
+		break;
+	default:
+		break;
+	}
+	*val = read_val;
+	return PCIBIOS_SUCCESSFUL;
+}
+
+static int thunder_pem_config_read(struct pci_bus *bus, unsigned int devfn,
+				   int where, int size, u32 *val)
+{
+	struct pci_config_window *cfg = bus->sysdata;
+
+	if (bus->number < cfg->busr.start ||
+	    bus->number > cfg->busr.end)
+		return PCIBIOS_DEVICE_NOT_FOUND;
+
+	/*
+	 * The first device on the bus is the PEM PCIe bridge.
+	 * Special case its config access.
+	 */
+	if (bus->number == cfg->busr.start)
+		return thunder_pem_bridge_read(bus, devfn, where, size, val);
+
+	return pci_generic_config_read(bus, devfn, where, size, val);
+}
+
+/*
+ * Some of the w1c_bits below also include read-only or non-writable
+ * reserved bits, this makes the code simpler and is OK as the bits
+ * are not affected by writing zeros to them.
+ */
+static u32 thunder_pem_bridge_w1c_bits(u64 where_aligned)
+{
+	u32 w1c_bits = 0;
+
+	switch (where_aligned) {
+	case 0x04: /* Command/Status */
+	case 0x1c: /* Base and I/O Limit/Secondary Status */
+		w1c_bits = 0xff000000;
+		break;
+	case 0x44: /* Power Management Control and Status */
+		w1c_bits = 0xfffffe00;
+		break;
+	case 0x78: /* Device Control/Device Status */
+	case 0x80: /* Link Control/Link Status */
+	case 0x88: /* Slot Control/Slot Status */
+	case 0x90: /* Root Status */
+	case 0xa0: /* Link Control 2 Registers/Link Status 2 */
+		w1c_bits = 0xffff0000;
+		break;
+	case 0x104: /* Uncorrectable Error Status */
+	case 0x110: /* Correctable Error Status */
+	case 0x130: /* Error Status */
+	case 0x160: /* Link Control 4 */
+		w1c_bits = 0xffffffff;
+		break;
+	default:
+		break;
+	}
+	return w1c_bits;
+}
+
+/* Some bits must be written to one so they appear to be read-only. */
+static u32 thunder_pem_bridge_w1_bits(u64 where_aligned)
+{
+	u32 w1_bits;
+
+	switch (where_aligned) {
+	case 0x1c: /* I/O Base / I/O Limit, Secondary Status */
+		/* Force 32-bit I/O addressing. */
+		w1_bits = 0x0101;
+		break;
+	case 0x24: /* Prefetchable Memory Base / Prefetchable Memory Limit */
+		/* Force 64-bit addressing */
+		w1_bits = 0x00010001;
+		break;
+	default:
+		w1_bits = 0;
+		break;
+	}
+	return w1_bits;
+}
+
+static int thunder_pem_bridge_write(struct pci_bus *bus, unsigned int devfn,
+				    int where, int size, u32 val)
+{
+	struct pci_config_window *cfg = bus->sysdata;
+	struct thunder_pem_pci *pem_pci = (struct thunder_pem_pci *)cfg->priv;
+	u64 write_val, read_val;
+	u64 where_aligned = where & ~3ull;
+	u32 mask = 0;
+
+
+	if (devfn != 0 || where >= 2048)
+		return PCIBIOS_DEVICE_NOT_FOUND;
+
+	/*
+	 * 32-bit accesses only.  If the write is for a size smaller
+	 * than 32-bits, we must first read the 32-bit value and merge
+	 * in the desired bits and then write the whole 32-bits back
+	 * out.
+	 */
+	switch (size) {
+	case 1:
+		writeq(where_aligned, pem_pci->pem_reg_base + PEM_CFG_RD);
+		read_val = readq(pem_pci->pem_reg_base + PEM_CFG_RD);
+		read_val >>= 32;
+		mask = ~(0xff << (8 * (where & 3)));
+		read_val &= mask;
+		val = (val & 0xff) << (8 * (where & 3));
+		val |= (u32)read_val;
+		break;
+	case 2:
+		writeq(where_aligned, pem_pci->pem_reg_base + PEM_CFG_RD);
+		read_val = readq(pem_pci->pem_reg_base + PEM_CFG_RD);
+		read_val >>= 32;
+		mask = ~(0xffff << (8 * (where & 3)));
+		read_val &= mask;
+		val = (val & 0xffff) << (8 * (where & 3));
+		val |= (u32)read_val;
+		break;
+	default:
+		break;
+	}
+
+	/*
+	 * By expanding the write width to 32 bits, we may
+	 * inadvertently hit some W1C bits that were not intended to
+	 * be written.  Calculate the mask that must be applied to the
+	 * data to be written to avoid these cases.
+	 */
+	if (mask) {
+		u32 w1c_bits = thunder_pem_bridge_w1c_bits(where);
+
+		if (w1c_bits) {
+			mask &= w1c_bits;
+			val &= ~mask;
+		}
+	}
+
+	/*
+	 * Some bits must be read-only with value of one.  Since the
+	 * access method allows these to be cleared if a zero is
+	 * written, force them to one before writing.
+	 */
+	val |= thunder_pem_bridge_w1_bits(where_aligned);
+
+	/*
+	 * Low order bits are the config address, the high order 32
+	 * bits are the data to be written.
+	 */
+	write_val = (((u64)val) << 32) | where_aligned;
+	writeq(write_val, pem_pci->pem_reg_base + PEM_CFG_WR);
+	return PCIBIOS_SUCCESSFUL;
+}
+
+static int thunder_pem_config_write(struct pci_bus *bus, unsigned int devfn,
+				    int where, int size, u32 val)
+{
+	struct pci_config_window *cfg = bus->sysdata;
+
+	if (bus->number < cfg->busr.start ||
+	    bus->number > cfg->busr.end)
+		return PCIBIOS_DEVICE_NOT_FOUND;
+	/*
+	 * The first device on the bus is the PEM PCIe bridge.
+	 * Special case its config access.
+	 */
+	if (bus->number == cfg->busr.start)
+		return thunder_pem_bridge_write(bus, devfn, where, size, val);
+
+
+	return pci_generic_config_write(bus, devfn, where, size, val);
+}
+
+static int thunder_pem_init(struct device *dev, struct pci_config_window *cfg,
+			    struct resource *res_pem)
+{
+	struct thunder_pem_pci *pem_pci;
+	resource_size_t bar4_start;
+
+	pem_pci = devm_kzalloc(dev, sizeof(*pem_pci), GFP_KERNEL);
+	if (!pem_pci)
+		return -ENOMEM;
+
+	pem_pci->pem_reg_base = devm_ioremap(dev, res_pem->start, 0x10000);
+	if (!pem_pci->pem_reg_base)
+		return -ENOMEM;
+
+	/*
+	 * The MSI-X BAR for the PEM and AER interrupts is located at
+	 * a fixed offset from the PEM register base.  Generate a
+	 * fragment of the synthesized Enhanced Allocation capability
+	 * structure here for the BAR.
+	 */
+	bar4_start = res_pem->start + 0xf00000;
+	pem_pci->ea_entry[0] = lower_32_bits(bar4_start) | 2;
+	pem_pci->ea_entry[1] = lower_32_bits(res_pem->end - bar4_start) & ~3u;
+	pem_pci->ea_entry[2] = upper_32_bits(bar4_start);
+
+	cfg->priv = pem_pci;
+	return 0;
+}
+
+#if defined(CONFIG_ACPI) && defined(CONFIG_PCI_QUIRKS)
+
+#define PEM_RES_BASE		0x87e0c0000000ULL
+#define PEM_NODE_MASK		GENMASK_ULL(45, 44)
+#define PEM_INDX_MASK		GENMASK_ULL(26, 24)
+#define PEM_MIN_DOM_IN_NODE	4
+#define PEM_MAX_DOM_IN_NODE	10
+
+static void thunder_pem_reserve_range(struct device *dev, int seg,
+				      struct resource *r)
+{
+	resource_size_t start = r->start, end = r->end;
+	struct resource *res;
+	const char *regionid;
+
+	regionid = kasprintf(GFP_KERNEL, "PEM RC:%d", seg);
+	if (!regionid)
+		return;
+
+	res = request_mem_region(start, end - start + 1, regionid);
+	if (res)
+		res->flags &= ~IORESOURCE_BUSY;
+	else
+		kfree(regionid);
+
+	dev_info(dev, "%pR %s reserved\n", r,
+		 res ? "has been" : "could not be");
+}
+
+static void thunder_pem_legacy_fw(struct acpi_pci_root *root,
+				 struct resource *res_pem)
+{
+	int node = acpi_get_node(root->device->handle);
+	int index;
+
+	if (node == NUMA_NO_NODE)
+		node = 0;
+
+	index = root->segment - PEM_MIN_DOM_IN_NODE;
+	index -= node * PEM_MAX_DOM_IN_NODE;
+	res_pem->start = PEM_RES_BASE | FIELD_PREP(PEM_NODE_MASK, node) |
+					FIELD_PREP(PEM_INDX_MASK, index);
+	res_pem->flags = IORESOURCE_MEM;
+}
+
+static int thunder_pem_acpi_init(struct pci_config_window *cfg)
+{
+	struct device *dev = cfg->parent;
+	struct acpi_device *adev = to_acpi_device(dev);
+	struct acpi_pci_root *root = acpi_driver_data(adev);
+	struct resource *res_pem;
+	int ret;
+
+	res_pem = devm_kzalloc(&adev->dev, sizeof(*res_pem), GFP_KERNEL);
+	if (!res_pem)
+		return -ENOMEM;
+
+	ret = acpi_get_rc_resources(dev, "CAVA02B", root->segment, res_pem);
+
+	/*
+	 * If we fail to gather resources it means that we run with old
+	 * FW where we need to calculate PEM-specific resources manually.
+	 */
+	if (ret) {
+		thunder_pem_legacy_fw(root, res_pem);
+		/*
+		 * Reserve 64K size PEM specific resources. The full 16M range
+		 * size is required for thunder_pem_init() call.
+		 */
+		res_pem->end = res_pem->start + SZ_64K - 1;
+		thunder_pem_reserve_range(dev, root->segment, res_pem);
+		res_pem->end = res_pem->start + SZ_16M - 1;
+
+		/* Reserve PCI configuration space as well. */
+		thunder_pem_reserve_range(dev, root->segment, &cfg->res);
+	}
+
+	return thunder_pem_init(dev, cfg, res_pem);
+}
+
+const struct pci_ecam_ops thunder_pem_ecam_ops = {
+	.bus_shift	= THUNDER_PCIE_ECAM_BUS_SHIFT,
+	.init		= thunder_pem_acpi_init,
+	.pci_ops	= {
+		.map_bus	= pci_ecam_map_bus,
+		.read		= thunder_pem_config_read,
+		.write		= thunder_pem_config_write,
+	}
+};
+
+#endif
+
+#ifdef CONFIG_PCI_HOST_THUNDER_PEM
+
+static int thunder_pem_platform_init(struct pci_config_window *cfg)
+{
+	struct device *dev = cfg->parent;
+	struct platform_device *pdev = to_platform_device(dev);
+	struct resource *res_pem;
+
+	if (!dev->of_node)
+		return -EINVAL;
+
+	/*
+	 * The second register range is the PEM bridge to the PCIe
+	 * bus.  It has a different config access method than those
+	 * devices behind the bridge.
+	 */
+	res_pem = platform_get_resource(pdev, IORESOURCE_MEM, 1);
+	if (!res_pem) {
+		dev_err(dev, "missing \"reg[1]\"property\n");
+		return -EINVAL;
+	}
+
+	return thunder_pem_init(dev, cfg, res_pem);
+}
+
+static const struct pci_ecam_ops pci_thunder_pem_ops = {
+	.bus_shift	= THUNDER_PCIE_ECAM_BUS_SHIFT,
+	.init		= thunder_pem_platform_init,
+	.pci_ops	= {
+		.map_bus	= pci_ecam_map_bus,
+		.read		= thunder_pem_config_read,
+		.write		= thunder_pem_config_write,
+	}
+};
+
+static const struct of_device_id thunder_pem_of_match[] = {
+	{
+		.compatible = "cavium,pci-host-thunder-pem",
+		.data = &pci_thunder_pem_ops,
+	},
+	{ },
+};
+
+static struct platform_driver thunder_pem_driver = {
+	.driver = {
+		.name = KBUILD_MODNAME,
+		.of_match_table = thunder_pem_of_match,
+		.suppress_bind_attrs = true,
+	},
+	.probe = pci_host_common_probe,
+};
+builtin_platform_driver(thunder_pem_driver);
+
+#endif
+#endif