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, 674 insertions, 0 deletions

diff --git a/arch/s390/pci/pci_clp.c b/arch/s390/pci/pci_clp.c
new file mode 100644
index 000000000..ee367798e
--- /dev/null
+++ b/arch/s390/pci/pci_clp.c
@@ -0,0 +1,674 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright IBM Corp. 2012
+ *
+ * Author(s):
+ *   Jan Glauber <jang@linux.vnet.ibm.com>
+ */
+
+#define KMSG_COMPONENT "zpci"
+#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
+
+#include <linux/compat.h>
+#include <linux/kernel.h>
+#include <linux/miscdevice.h>
+#include <linux/slab.h>
+#include <linux/err.h>
+#include <linux/delay.h>
+#include <linux/pci.h>
+#include <linux/uaccess.h>
+#include <asm/asm-extable.h>
+#include <asm/pci_debug.h>
+#include <asm/pci_clp.h>
+#include <asm/clp.h>
+#include <uapi/asm/clp.h>
+
+#include "pci_bus.h"
+
+bool zpci_unique_uid;
+
+void update_uid_checking(bool new)
+{
+	if (zpci_unique_uid != new)
+		zpci_dbg(3, "uid checking:%d\n", new);
+
+	zpci_unique_uid = new;
+}
+
+static inline void zpci_err_clp(unsigned int rsp, int rc)
+{
+	struct {
+		unsigned int rsp;
+		int rc;
+	} __packed data = {rsp, rc};
+
+	zpci_err_hex(&data, sizeof(data));
+}
+
+/*
+ * Call Logical Processor with c=1, lps=0 and command 1
+ * to get the bit mask of installed logical processors
+ */
+static inline int clp_get_ilp(unsigned long *ilp)
+{
+	unsigned long mask;
+	int cc = 3;
+
+	asm volatile (
+		"	.insn	rrf,0xb9a00000,%[mask],%[cmd],8,0\n"
+		"0:	ipm	%[cc]\n"
+		"	srl	%[cc],28\n"
+		"1:\n"
+		EX_TABLE(0b, 1b)
+		: [cc] "+d" (cc), [mask] "=d" (mask) : [cmd] "a" (1)
+		: "cc");
+	*ilp = mask;
+	return cc;
+}
+
+/*
+ * Call Logical Processor with c=0, the give constant lps and an lpcb request.
+ */
+static __always_inline int clp_req(void *data, unsigned int lps)
+{
+	struct { u8 _[CLP_BLK_SIZE]; } *req = data;
+	u64 ignored;
+	int cc = 3;
+
+	asm volatile (
+		"	.insn	rrf,0xb9a00000,%[ign],%[req],0,%[lps]\n"
+		"0:	ipm	%[cc]\n"
+		"	srl	%[cc],28\n"
+		"1:\n"
+		EX_TABLE(0b, 1b)
+		: [cc] "+d" (cc), [ign] "=d" (ignored), "+m" (*req)
+		: [req] "a" (req), [lps] "i" (lps)
+		: "cc");
+	return cc;
+}
+
+static void *clp_alloc_block(gfp_t gfp_mask)
+{
+	return (void *) __get_free_pages(gfp_mask, get_order(CLP_BLK_SIZE));
+}
+
+static void clp_free_block(void *ptr)
+{
+	free_pages((unsigned long) ptr, get_order(CLP_BLK_SIZE));
+}
+
+static void clp_store_query_pci_fngrp(struct zpci_dev *zdev,
+				      struct clp_rsp_query_pci_grp *response)
+{
+	zdev->tlb_refresh = response->refresh;
+	zdev->dma_mask = response->dasm;
+	zdev->msi_addr = response->msia;
+	zdev->max_msi = response->noi;
+	zdev->fmb_update = response->mui;
+	zdev->version = response->version;
+	zdev->maxstbl = response->maxstbl;
+	zdev->dtsm = response->dtsm;
+
+	switch (response->version) {
+	case 1:
+		zdev->max_bus_speed = PCIE_SPEED_5_0GT;
+		break;
+	default:
+		zdev->max_bus_speed = PCI_SPEED_UNKNOWN;
+		break;
+	}
+}
+
+static int clp_query_pci_fngrp(struct zpci_dev *zdev, u8 pfgid)
+{
+	struct clp_req_rsp_query_pci_grp *rrb;
+	int rc;
+
+	rrb = clp_alloc_block(GFP_KERNEL);
+	if (!rrb)
+		return -ENOMEM;
+
+	memset(rrb, 0, sizeof(*rrb));
+	rrb->request.hdr.len = sizeof(rrb->request);
+	rrb->request.hdr.cmd = CLP_QUERY_PCI_FNGRP;
+	rrb->response.hdr.len = sizeof(rrb->response);
+	rrb->request.pfgid = pfgid;
+
+	rc = clp_req(rrb, CLP_LPS_PCI);
+	if (!rc && rrb->response.hdr.rsp == CLP_RC_OK)
+		clp_store_query_pci_fngrp(zdev, &rrb->response);
+	else {
+		zpci_err("Q PCI FGRP:\n");
+		zpci_err_clp(rrb->response.hdr.rsp, rc);
+		rc = -EIO;
+	}
+	clp_free_block(rrb);
+	return rc;
+}
+
+static int clp_store_query_pci_fn(struct zpci_dev *zdev,
+				  struct clp_rsp_query_pci *response)
+{
+	int i;
+
+	for (i = 0; i < PCI_STD_NUM_BARS; i++) {
+		zdev->bars[i].val = le32_to_cpu(response->bar[i]);
+		zdev->bars[i].size = response->bar_size[i];
+	}
+	zdev->start_dma = response->sdma;
+	zdev->end_dma = response->edma;
+	zdev->pchid = response->pchid;
+	zdev->pfgid = response->pfgid;
+	zdev->pft = response->pft;
+	zdev->vfn = response->vfn;
+	zdev->port = response->port;
+	zdev->uid = response->uid;
+	zdev->fmb_length = sizeof(u32) * response->fmb_len;
+	zdev->rid_available = response->rid_avail;
+	zdev->is_physfn = response->is_physfn;
+	if (!s390_pci_no_rid && zdev->rid_available)
+		zdev->devfn = response->rid & ZPCI_RID_MASK_DEVFN;
+
+	memcpy(zdev->pfip, response->pfip, sizeof(zdev->pfip));
+	if (response->util_str_avail) {
+		memcpy(zdev->util_str, response->util_str,
+		       sizeof(zdev->util_str));
+		zdev->util_str_avail = 1;
+	}
+	zdev->mio_capable = response->mio_addr_avail;
+	for (i = 0; i < PCI_STD_NUM_BARS; i++) {
+		if (!(response->mio.valid & (1 << (PCI_STD_NUM_BARS - i - 1))))
+			continue;
+
+		zdev->bars[i].mio_wb = (void __iomem *) response->mio.addr[i].wb;
+		zdev->bars[i].mio_wt = (void __iomem *) response->mio.addr[i].wt;
+	}
+	return 0;
+}
+
+int clp_query_pci_fn(struct zpci_dev *zdev)
+{
+	struct clp_req_rsp_query_pci *rrb;
+	int rc;
+
+	rrb = clp_alloc_block(GFP_KERNEL);
+	if (!rrb)
+		return -ENOMEM;
+
+	memset(rrb, 0, sizeof(*rrb));
+	rrb->request.hdr.len = sizeof(rrb->request);
+	rrb->request.hdr.cmd = CLP_QUERY_PCI_FN;
+	rrb->response.hdr.len = sizeof(rrb->response);
+	rrb->request.fh = zdev->fh;
+
+	rc = clp_req(rrb, CLP_LPS_PCI);
+	if (!rc && rrb->response.hdr.rsp == CLP_RC_OK) {
+		rc = clp_store_query_pci_fn(zdev, &rrb->response);
+		if (rc)
+			goto out;
+		rc = clp_query_pci_fngrp(zdev, rrb->response.pfgid);
+	} else {
+		zpci_err("Q PCI FN:\n");
+		zpci_err_clp(rrb->response.hdr.rsp, rc);
+		rc = -EIO;
+	}
+out:
+	clp_free_block(rrb);
+	return rc;
+}
+
+/**
+ * clp_set_pci_fn() - Execute a command on a PCI function
+ * @zdev: Function that will be affected
+ * @fh: Out parameter for updated function handle
+ * @nr_dma_as: DMA address space number
+ * @command: The command code to execute
+ *
+ * Returns: 0 on success, < 0 for Linux errors (e.g. -ENOMEM), and
+ * > 0 for non-success platform responses
+ */
+static int clp_set_pci_fn(struct zpci_dev *zdev, u32 *fh, u8 nr_dma_as, u8 command)
+{
+	struct clp_req_rsp_set_pci *rrb;
+	int rc, retries = 100;
+	u32 gisa = 0;
+
+	*fh = 0;
+	rrb = clp_alloc_block(GFP_KERNEL);
+	if (!rrb)
+		return -ENOMEM;
+
+	if (command != CLP_SET_DISABLE_PCI_FN)
+		gisa = zdev->gisa;
+
+	do {
+		memset(rrb, 0, sizeof(*rrb));
+		rrb->request.hdr.len = sizeof(rrb->request);
+		rrb->request.hdr.cmd = CLP_SET_PCI_FN;
+		rrb->response.hdr.len = sizeof(rrb->response);
+		rrb->request.fh = zdev->fh;
+		rrb->request.oc = command;
+		rrb->request.ndas = nr_dma_as;
+		rrb->request.gisa = gisa;
+
+		rc = clp_req(rrb, CLP_LPS_PCI);
+		if (rrb->response.hdr.rsp == CLP_RC_SETPCIFN_BUSY) {
+			retries--;
+			if (retries < 0)
+				break;
+			msleep(20);
+		}
+	} while (rrb->response.hdr.rsp == CLP_RC_SETPCIFN_BUSY);
+
+	if (!rc && rrb->response.hdr.rsp == CLP_RC_OK) {
+		*fh = rrb->response.fh;
+	} else {
+		zpci_err("Set PCI FN:\n");
+		zpci_err_clp(rrb->response.hdr.rsp, rc);
+		if (!rc)
+			rc = rrb->response.hdr.rsp;
+	}
+	clp_free_block(rrb);
+	return rc;
+}
+
+int clp_setup_writeback_mio(void)
+{
+	struct clp_req_rsp_slpc_pci *rrb;
+	u8  wb_bit_pos;
+	int rc;
+
+	rrb = clp_alloc_block(GFP_KERNEL);
+	if (!rrb)
+		return -ENOMEM;
+
+	memset(rrb, 0, sizeof(*rrb));
+	rrb->request.hdr.len = sizeof(rrb->request);
+	rrb->request.hdr.cmd = CLP_SLPC;
+	rrb->response.hdr.len = sizeof(rrb->response);
+
+	rc = clp_req(rrb, CLP_LPS_PCI);
+	if (!rc && rrb->response.hdr.rsp == CLP_RC_OK) {
+		if (rrb->response.vwb) {
+			wb_bit_pos = rrb->response.mio_wb;
+			set_bit_inv(wb_bit_pos, &mio_wb_bit_mask);
+			zpci_dbg(3, "wb bit: %d\n", wb_bit_pos);
+		} else {
+			zpci_dbg(3, "wb bit: n.a.\n");
+		}
+
+	} else {
+		zpci_err("SLPC PCI:\n");
+		zpci_err_clp(rrb->response.hdr.rsp, rc);
+		rc = -EIO;
+	}
+	clp_free_block(rrb);
+	return rc;
+}
+
+int clp_enable_fh(struct zpci_dev *zdev, u32 *fh, u8 nr_dma_as)
+{
+	int rc;
+
+	rc = clp_set_pci_fn(zdev, fh, nr_dma_as, CLP_SET_ENABLE_PCI_FN);
+	zpci_dbg(3, "ena fid:%x, fh:%x, rc:%d\n", zdev->fid, *fh, rc);
+	if (!rc && zpci_use_mio(zdev)) {
+		rc = clp_set_pci_fn(zdev, fh, nr_dma_as, CLP_SET_ENABLE_MIO);
+		zpci_dbg(3, "ena mio fid:%x, fh:%x, rc:%d\n",
+				zdev->fid, *fh, rc);
+		if (rc)
+			clp_disable_fh(zdev, fh);
+	}
+	return rc;
+}
+
+int clp_disable_fh(struct zpci_dev *zdev, u32 *fh)
+{
+	int rc;
+
+	if (!zdev_enabled(zdev))
+		return 0;
+
+	rc = clp_set_pci_fn(zdev, fh, 0, CLP_SET_DISABLE_PCI_FN);
+	zpci_dbg(3, "dis fid:%x, fh:%x, rc:%d\n", zdev->fid, *fh, rc);
+	return rc;
+}
+
+static int clp_list_pci_req(struct clp_req_rsp_list_pci *rrb,
+			    u64 *resume_token, int *nentries)
+{
+	int rc;
+
+	memset(rrb, 0, sizeof(*rrb));
+	rrb->request.hdr.len = sizeof(rrb->request);
+	rrb->request.hdr.cmd = CLP_LIST_PCI;
+	/* store as many entries as possible */
+	rrb->response.hdr.len = CLP_BLK_SIZE - LIST_PCI_HDR_LEN;
+	rrb->request.resume_token = *resume_token;
+
+	/* Get PCI function handle list */
+	rc = clp_req(rrb, CLP_LPS_PCI);
+	if (rc || rrb->response.hdr.rsp != CLP_RC_OK) {
+		zpci_err("List PCI FN:\n");
+		zpci_err_clp(rrb->response.hdr.rsp, rc);
+		return -EIO;
+	}
+
+	update_uid_checking(rrb->response.uid_checking);
+	WARN_ON_ONCE(rrb->response.entry_size !=
+		sizeof(struct clp_fh_list_entry));
+
+	*nentries = (rrb->response.hdr.len - LIST_PCI_HDR_LEN) /
+		rrb->response.entry_size;
+	*resume_token = rrb->response.resume_token;
+
+	return rc;
+}
+
+static int clp_list_pci(struct clp_req_rsp_list_pci *rrb, void *data,
+			void (*cb)(struct clp_fh_list_entry *, void *))
+{
+	u64 resume_token = 0;
+	int nentries, i, rc;
+
+	do {
+		rc = clp_list_pci_req(rrb, &resume_token, &nentries);
+		if (rc)
+			return rc;
+		for (i = 0; i < nentries; i++)
+			cb(&rrb->response.fh_list[i], data);
+	} while (resume_token);
+
+	return rc;
+}
+
+static int clp_find_pci(struct clp_req_rsp_list_pci *rrb, u32 fid,
+			struct clp_fh_list_entry *entry)
+{
+	struct clp_fh_list_entry *fh_list;
+	u64 resume_token = 0;
+	int nentries, i, rc;
+
+	do {
+		rc = clp_list_pci_req(rrb, &resume_token, &nentries);
+		if (rc)
+			return rc;
+		fh_list = rrb->response.fh_list;
+		for (i = 0; i < nentries; i++) {
+			if (fh_list[i].fid == fid) {
+				*entry = fh_list[i];
+				return 0;
+			}
+		}
+	} while (resume_token);
+
+	return -ENODEV;
+}
+
+static void __clp_add(struct clp_fh_list_entry *entry, void *data)
+{
+	struct zpci_dev *zdev;
+
+	if (!entry->vendor_id)
+		return;
+
+	zdev = get_zdev_by_fid(entry->fid);
+	if (zdev) {
+		zpci_zdev_put(zdev);
+		return;
+	}
+	zpci_create_device(entry->fid, entry->fh, entry->config_state);
+}
+
+int clp_scan_pci_devices(void)
+{
+	struct clp_req_rsp_list_pci *rrb;
+	int rc;
+
+	rrb = clp_alloc_block(GFP_KERNEL);
+	if (!rrb)
+		return -ENOMEM;
+
+	rc = clp_list_pci(rrb, NULL, __clp_add);
+
+	clp_free_block(rrb);
+	return rc;
+}
+
+/*
+ * Get the current function handle of the function matching @fid
+ */
+int clp_refresh_fh(u32 fid, u32 *fh)
+{
+	struct clp_req_rsp_list_pci *rrb;
+	struct clp_fh_list_entry entry;
+	int rc;
+
+	rrb = clp_alloc_block(GFP_NOWAIT);
+	if (!rrb)
+		return -ENOMEM;
+
+	rc = clp_find_pci(rrb, fid, &entry);
+	if (!rc)
+		*fh = entry.fh;
+
+	clp_free_block(rrb);
+	return rc;
+}
+
+int clp_get_state(u32 fid, enum zpci_state *state)
+{
+	struct clp_req_rsp_list_pci *rrb;
+	struct clp_fh_list_entry entry;
+	int rc;
+
+	rrb = clp_alloc_block(GFP_ATOMIC);
+	if (!rrb)
+		return -ENOMEM;
+
+	rc = clp_find_pci(rrb, fid, &entry);
+	if (!rc) {
+		*state = entry.config_state;
+	} else if (rc == -ENODEV) {
+		*state = ZPCI_FN_STATE_RESERVED;
+		rc = 0;
+	}
+
+	clp_free_block(rrb);
+	return rc;
+}
+
+static int clp_base_slpc(struct clp_req *req, struct clp_req_rsp_slpc *lpcb)
+{
+	unsigned long limit = PAGE_SIZE - sizeof(lpcb->request);
+
+	if (lpcb->request.hdr.len != sizeof(lpcb->request) ||
+	    lpcb->response.hdr.len > limit)
+		return -EINVAL;
+	return clp_req(lpcb, CLP_LPS_BASE) ? -EOPNOTSUPP : 0;
+}
+
+static int clp_base_command(struct clp_req *req, struct clp_req_hdr *lpcb)
+{
+	switch (lpcb->cmd) {
+	case 0x0001: /* store logical-processor characteristics */
+		return clp_base_slpc(req, (void *) lpcb);
+	default:
+		return -EINVAL;
+	}
+}
+
+static int clp_pci_slpc(struct clp_req *req, struct clp_req_rsp_slpc_pci *lpcb)
+{
+	unsigned long limit = PAGE_SIZE - sizeof(lpcb->request);
+
+	if (lpcb->request.hdr.len != sizeof(lpcb->request) ||
+	    lpcb->response.hdr.len > limit)
+		return -EINVAL;
+	return clp_req(lpcb, CLP_LPS_PCI) ? -EOPNOTSUPP : 0;
+}
+
+static int clp_pci_list(struct clp_req *req, struct clp_req_rsp_list_pci *lpcb)
+{
+	unsigned long limit = PAGE_SIZE - sizeof(lpcb->request);
+
+	if (lpcb->request.hdr.len != sizeof(lpcb->request) ||
+	    lpcb->response.hdr.len > limit)
+		return -EINVAL;
+	if (lpcb->request.reserved2 != 0)
+		return -EINVAL;
+	return clp_req(lpcb, CLP_LPS_PCI) ? -EOPNOTSUPP : 0;
+}
+
+static int clp_pci_query(struct clp_req *req,
+			 struct clp_req_rsp_query_pci *lpcb)
+{
+	unsigned long limit = PAGE_SIZE - sizeof(lpcb->request);
+
+	if (lpcb->request.hdr.len != sizeof(lpcb->request) ||
+	    lpcb->response.hdr.len > limit)
+		return -EINVAL;
+	if (lpcb->request.reserved2 != 0 || lpcb->request.reserved3 != 0)
+		return -EINVAL;
+	return clp_req(lpcb, CLP_LPS_PCI) ? -EOPNOTSUPP : 0;
+}
+
+static int clp_pci_query_grp(struct clp_req *req,
+			     struct clp_req_rsp_query_pci_grp *lpcb)
+{
+	unsigned long limit = PAGE_SIZE - sizeof(lpcb->request);
+
+	if (lpcb->request.hdr.len != sizeof(lpcb->request) ||
+	    lpcb->response.hdr.len > limit)
+		return -EINVAL;
+	if (lpcb->request.reserved2 != 0 || lpcb->request.reserved3 != 0 ||
+	    lpcb->request.reserved4 != 0)
+		return -EINVAL;
+	return clp_req(lpcb, CLP_LPS_PCI) ? -EOPNOTSUPP : 0;
+}
+
+static int clp_pci_command(struct clp_req *req, struct clp_req_hdr *lpcb)
+{
+	switch (lpcb->cmd) {
+	case 0x0001: /* store logical-processor characteristics */
+		return clp_pci_slpc(req, (void *) lpcb);
+	case 0x0002: /* list PCI functions */
+		return clp_pci_list(req, (void *) lpcb);
+	case 0x0003: /* query PCI function */
+		return clp_pci_query(req, (void *) lpcb);
+	case 0x0004: /* query PCI function group */
+		return clp_pci_query_grp(req, (void *) lpcb);
+	default:
+		return -EINVAL;
+	}
+}
+
+static int clp_normal_command(struct clp_req *req)
+{
+	struct clp_req_hdr *lpcb;
+	void __user *uptr;
+	int rc;
+
+	rc = -EINVAL;
+	if (req->lps != 0 && req->lps != 2)
+		goto out;
+
+	rc = -ENOMEM;
+	lpcb = clp_alloc_block(GFP_KERNEL);
+	if (!lpcb)
+		goto out;
+
+	rc = -EFAULT;
+	uptr = (void __force __user *)(unsigned long) req->data_p;
+	if (copy_from_user(lpcb, uptr, PAGE_SIZE) != 0)
+		goto out_free;
+
+	rc = -EINVAL;
+	if (lpcb->fmt != 0 || lpcb->reserved1 != 0 || lpcb->reserved2 != 0)
+		goto out_free;
+
+	switch (req->lps) {
+	case 0:
+		rc = clp_base_command(req, lpcb);
+		break;
+	case 2:
+		rc = clp_pci_command(req, lpcb);
+		break;
+	}
+	if (rc)
+		goto out_free;
+
+	rc = -EFAULT;
+	if (copy_to_user(uptr, lpcb, PAGE_SIZE) != 0)
+		goto out_free;
+
+	rc = 0;
+
+out_free:
+	clp_free_block(lpcb);
+out:
+	return rc;
+}
+
+static int clp_immediate_command(struct clp_req *req)
+{
+	void __user *uptr;
+	unsigned long ilp;
+	int exists;
+
+	if (req->cmd > 1 || clp_get_ilp(&ilp) != 0)
+		return -EINVAL;
+
+	uptr = (void __force __user *)(unsigned long) req->data_p;
+	if (req->cmd == 0) {
+		/* Command code 0: test for a specific processor */
+		exists = test_bit_inv(req->lps, &ilp);
+		return put_user(exists, (int __user *) uptr);
+	}
+	/* Command code 1: return bit mask of installed processors */
+	return put_user(ilp, (unsigned long __user *) uptr);
+}
+
+static long clp_misc_ioctl(struct file *filp, unsigned int cmd,
+			   unsigned long arg)
+{
+	struct clp_req req;
+	void __user *argp;
+
+	if (cmd != CLP_SYNC)
+		return -EINVAL;
+
+	argp = is_compat_task() ? compat_ptr(arg) : (void __user *) arg;
+	if (copy_from_user(&req, argp, sizeof(req)))
+		return -EFAULT;
+	if (req.r != 0)
+		return -EINVAL;
+	return req.c ? clp_immediate_command(&req) : clp_normal_command(&req);
+}
+
+static int clp_misc_release(struct inode *inode, struct file *filp)
+{
+	return 0;
+}
+
+static const struct file_operations clp_misc_fops = {
+	.owner = THIS_MODULE,
+	.open = nonseekable_open,
+	.release = clp_misc_release,
+	.unlocked_ioctl = clp_misc_ioctl,
+	.compat_ioctl = clp_misc_ioctl,
+	.llseek = no_llseek,
+};
+
+static struct miscdevice clp_misc_device = {
+	.minor = MISC_DYNAMIC_MINOR,
+	.name = "clp",
+	.fops = &clp_misc_fops,
+};
+
+static int __init clp_misc_init(void)
+{
+	return misc_register(&clp_misc_device);
+}
+
+device_initcall(clp_misc_init);