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, 523 insertions, 0 deletions

diff --git a/drivers/edac/x38_edac.c b/drivers/edac/x38_edac.c
new file mode 100644
index 000000000..49ab5721a
--- /dev/null
+++ b/drivers/edac/x38_edac.c
@@ -0,0 +1,523 @@
+/*
+ * Intel X38 Memory Controller kernel module
+ * Copyright (C) 2008 Cluster Computing, Inc.
+ *
+ * This file may be distributed under the terms of the
+ * GNU General Public License.
+ *
+ * This file is based on i3200_edac.c
+ *
+ */
+
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/pci.h>
+#include <linux/pci_ids.h>
+#include <linux/edac.h>
+
+#include <linux/io-64-nonatomic-lo-hi.h>
+#include "edac_module.h"
+
+#define EDAC_MOD_STR		"x38_edac"
+
+#define PCI_DEVICE_ID_INTEL_X38_HB	0x29e0
+
+#define X38_RANKS		8
+#define X38_RANKS_PER_CHANNEL	4
+#define X38_CHANNELS		2
+
+/* Intel X38 register addresses - device 0 function 0 - DRAM Controller */
+
+#define X38_MCHBAR_LOW	0x48	/* MCH Memory Mapped Register BAR */
+#define X38_MCHBAR_HIGH	0x4c
+#define X38_MCHBAR_MASK	0xfffffc000ULL	/* bits 35:14 */
+#define X38_MMR_WINDOW_SIZE	16384
+
+#define X38_TOM	0xa0	/* Top of Memory (16b)
+				 *
+				 * 15:10 reserved
+				 *  9:0  total populated physical memory
+				 */
+#define X38_TOM_MASK	0x3ff	/* bits 9:0 */
+#define X38_TOM_SHIFT 26	/* 64MiB grain */
+
+#define X38_ERRSTS	0xc8	/* Error Status Register (16b)
+				 *
+				 * 15    reserved
+				 * 14    Isochronous TBWRR Run Behind FIFO Full
+				 *       (ITCV)
+				 * 13    Isochronous TBWRR Run Behind FIFO Put
+				 *       (ITSTV)
+				 * 12    reserved
+				 * 11    MCH Thermal Sensor Event
+				 *       for SMI/SCI/SERR (GTSE)
+				 * 10    reserved
+				 *  9    LOCK to non-DRAM Memory Flag (LCKF)
+				 *  8    reserved
+				 *  7    DRAM Throttle Flag (DTF)
+				 *  6:2  reserved
+				 *  1    Multi-bit DRAM ECC Error Flag (DMERR)
+				 *  0    Single-bit DRAM ECC Error Flag (DSERR)
+				 */
+#define X38_ERRSTS_UE		0x0002
+#define X38_ERRSTS_CE		0x0001
+#define X38_ERRSTS_BITS	(X38_ERRSTS_UE | X38_ERRSTS_CE)
+
+
+/* Intel  MMIO register space - device 0 function 0 - MMR space */
+
+#define X38_C0DRB	0x200	/* Channel 0 DRAM Rank Boundary (16b x 4)
+				 *
+				 * 15:10 reserved
+				 *  9:0  Channel 0 DRAM Rank Boundary Address
+				 */
+#define X38_C1DRB	0x600	/* Channel 1 DRAM Rank Boundary (16b x 4) */
+#define X38_DRB_MASK	0x3ff	/* bits 9:0 */
+#define X38_DRB_SHIFT 26	/* 64MiB grain */
+
+#define X38_C0ECCERRLOG 0x280	/* Channel 0 ECC Error Log (64b)
+				 *
+				 * 63:48 Error Column Address (ERRCOL)
+				 * 47:32 Error Row Address (ERRROW)
+				 * 31:29 Error Bank Address (ERRBANK)
+				 * 28:27 Error Rank Address (ERRRANK)
+				 * 26:24 reserved
+				 * 23:16 Error Syndrome (ERRSYND)
+				 * 15: 2 reserved
+				 *    1  Multiple Bit Error Status (MERRSTS)
+				 *    0  Correctable Error Status (CERRSTS)
+				 */
+#define X38_C1ECCERRLOG 0x680	/* Channel 1 ECC Error Log (64b) */
+#define X38_ECCERRLOG_CE	0x1
+#define X38_ECCERRLOG_UE	0x2
+#define X38_ECCERRLOG_RANK_BITS	0x18000000
+#define X38_ECCERRLOG_SYNDROME_BITS	0xff0000
+
+#define X38_CAPID0 0xe0	/* see P.94 of spec for details */
+
+static int x38_channel_num;
+
+static int how_many_channel(struct pci_dev *pdev)
+{
+	unsigned char capid0_8b; /* 8th byte of CAPID0 */
+
+	pci_read_config_byte(pdev, X38_CAPID0 + 8, &capid0_8b);
+	if (capid0_8b & 0x20) {	/* check DCD: Dual Channel Disable */
+		edac_dbg(0, "In single channel mode\n");
+		x38_channel_num = 1;
+	} else {
+		edac_dbg(0, "In dual channel mode\n");
+		x38_channel_num = 2;
+	}
+
+	return x38_channel_num;
+}
+
+static unsigned long eccerrlog_syndrome(u64 log)
+{
+	return (log & X38_ECCERRLOG_SYNDROME_BITS) >> 16;
+}
+
+static int eccerrlog_row(int channel, u64 log)
+{
+	return ((log & X38_ECCERRLOG_RANK_BITS) >> 27) |
+		(channel * X38_RANKS_PER_CHANNEL);
+}
+
+enum x38_chips {
+	X38 = 0,
+};
+
+struct x38_dev_info {
+	const char *ctl_name;
+};
+
+struct x38_error_info {
+	u16 errsts;
+	u16 errsts2;
+	u64 eccerrlog[X38_CHANNELS];
+};
+
+static const struct x38_dev_info x38_devs[] = {
+	[X38] = {
+		.ctl_name = "x38"},
+};
+
+static struct pci_dev *mci_pdev;
+static int x38_registered = 1;
+
+
+static void x38_clear_error_info(struct mem_ctl_info *mci)
+{
+	struct pci_dev *pdev;
+
+	pdev = to_pci_dev(mci->pdev);
+
+	/*
+	 * Clear any error bits.
+	 * (Yes, we really clear bits by writing 1 to them.)
+	 */
+	pci_write_bits16(pdev, X38_ERRSTS, X38_ERRSTS_BITS,
+			 X38_ERRSTS_BITS);
+}
+
+static void x38_get_and_clear_error_info(struct mem_ctl_info *mci,
+				 struct x38_error_info *info)
+{
+	struct pci_dev *pdev;
+	void __iomem *window = mci->pvt_info;
+
+	pdev = to_pci_dev(mci->pdev);
+
+	/*
+	 * This is a mess because there is no atomic way to read all the
+	 * registers at once and the registers can transition from CE being
+	 * overwritten by UE.
+	 */
+	pci_read_config_word(pdev, X38_ERRSTS, &info->errsts);
+	if (!(info->errsts & X38_ERRSTS_BITS))
+		return;
+
+	info->eccerrlog[0] = lo_hi_readq(window + X38_C0ECCERRLOG);
+	if (x38_channel_num == 2)
+		info->eccerrlog[1] = lo_hi_readq(window + X38_C1ECCERRLOG);
+
+	pci_read_config_word(pdev, X38_ERRSTS, &info->errsts2);
+
+	/*
+	 * If the error is the same for both reads then the first set
+	 * of reads is valid.  If there is a change then there is a CE
+	 * with no info and the second set of reads is valid and
+	 * should be UE info.
+	 */
+	if ((info->errsts ^ info->errsts2) & X38_ERRSTS_BITS) {
+		info->eccerrlog[0] = lo_hi_readq(window + X38_C0ECCERRLOG);
+		if (x38_channel_num == 2)
+			info->eccerrlog[1] =
+				lo_hi_readq(window + X38_C1ECCERRLOG);
+	}
+
+	x38_clear_error_info(mci);
+}
+
+static void x38_process_error_info(struct mem_ctl_info *mci,
+				struct x38_error_info *info)
+{
+	int channel;
+	u64 log;
+
+	if (!(info->errsts & X38_ERRSTS_BITS))
+		return;
+
+	if ((info->errsts ^ info->errsts2) & X38_ERRSTS_BITS) {
+		edac_mc_handle_error(HW_EVENT_ERR_UNCORRECTED, mci, 1, 0, 0, 0,
+				     -1, -1, -1,
+				     "UE overwrote CE", "");
+		info->errsts = info->errsts2;
+	}
+
+	for (channel = 0; channel < x38_channel_num; channel++) {
+		log = info->eccerrlog[channel];
+		if (log & X38_ECCERRLOG_UE) {
+			edac_mc_handle_error(HW_EVENT_ERR_UNCORRECTED, mci, 1,
+					     0, 0, 0,
+					     eccerrlog_row(channel, log),
+					     -1, -1,
+					     "x38 UE", "");
+		} else if (log & X38_ECCERRLOG_CE) {
+			edac_mc_handle_error(HW_EVENT_ERR_CORRECTED, mci, 1,
+					     0, 0, eccerrlog_syndrome(log),
+					     eccerrlog_row(channel, log),
+					     -1, -1,
+					     "x38 CE", "");
+		}
+	}
+}
+
+static void x38_check(struct mem_ctl_info *mci)
+{
+	struct x38_error_info info;
+
+	x38_get_and_clear_error_info(mci, &info);
+	x38_process_error_info(mci, &info);
+}
+
+static void __iomem *x38_map_mchbar(struct pci_dev *pdev)
+{
+	union {
+		u64 mchbar;
+		struct {
+			u32 mchbar_low;
+			u32 mchbar_high;
+		};
+	} u;
+	void __iomem *window;
+
+	pci_read_config_dword(pdev, X38_MCHBAR_LOW, &u.mchbar_low);
+	pci_write_config_dword(pdev, X38_MCHBAR_LOW, u.mchbar_low | 0x1);
+	pci_read_config_dword(pdev, X38_MCHBAR_HIGH, &u.mchbar_high);
+	u.mchbar &= X38_MCHBAR_MASK;
+
+	if (u.mchbar != (resource_size_t)u.mchbar) {
+		printk(KERN_ERR
+			"x38: mmio space beyond accessible range (0x%llx)\n",
+			(unsigned long long)u.mchbar);
+		return NULL;
+	}
+
+	window = ioremap(u.mchbar, X38_MMR_WINDOW_SIZE);
+	if (!window)
+		printk(KERN_ERR "x38: cannot map mmio space at 0x%llx\n",
+			(unsigned long long)u.mchbar);
+
+	return window;
+}
+
+
+static void x38_get_drbs(void __iomem *window,
+			u16 drbs[X38_CHANNELS][X38_RANKS_PER_CHANNEL])
+{
+	int i;
+
+	for (i = 0; i < X38_RANKS_PER_CHANNEL; i++) {
+		drbs[0][i] = readw(window + X38_C0DRB + 2*i) & X38_DRB_MASK;
+		drbs[1][i] = readw(window + X38_C1DRB + 2*i) & X38_DRB_MASK;
+	}
+}
+
+static bool x38_is_stacked(struct pci_dev *pdev,
+			u16 drbs[X38_CHANNELS][X38_RANKS_PER_CHANNEL])
+{
+	u16 tom;
+
+	pci_read_config_word(pdev, X38_TOM, &tom);
+	tom &= X38_TOM_MASK;
+
+	return drbs[X38_CHANNELS - 1][X38_RANKS_PER_CHANNEL - 1] == tom;
+}
+
+static unsigned long drb_to_nr_pages(
+			u16 drbs[X38_CHANNELS][X38_RANKS_PER_CHANNEL],
+			bool stacked, int channel, int rank)
+{
+	int n;
+
+	n = drbs[channel][rank];
+	if (rank > 0)
+		n -= drbs[channel][rank - 1];
+	if (stacked && (channel == 1) && drbs[channel][rank] ==
+				drbs[channel][X38_RANKS_PER_CHANNEL - 1]) {
+		n -= drbs[0][X38_RANKS_PER_CHANNEL - 1];
+	}
+
+	n <<= (X38_DRB_SHIFT - PAGE_SHIFT);
+	return n;
+}
+
+static int x38_probe1(struct pci_dev *pdev, int dev_idx)
+{
+	int rc;
+	int i, j;
+	struct mem_ctl_info *mci = NULL;
+	struct edac_mc_layer layers[2];
+	u16 drbs[X38_CHANNELS][X38_RANKS_PER_CHANNEL];
+	bool stacked;
+	void __iomem *window;
+
+	edac_dbg(0, "MC:\n");
+
+	window = x38_map_mchbar(pdev);
+	if (!window)
+		return -ENODEV;
+
+	x38_get_drbs(window, drbs);
+
+	how_many_channel(pdev);
+
+	/* FIXME: unconventional pvt_info usage */
+	layers[0].type = EDAC_MC_LAYER_CHIP_SELECT;
+	layers[0].size = X38_RANKS;
+	layers[0].is_virt_csrow = true;
+	layers[1].type = EDAC_MC_LAYER_CHANNEL;
+	layers[1].size = x38_channel_num;
+	layers[1].is_virt_csrow = false;
+	mci = edac_mc_alloc(0, ARRAY_SIZE(layers), layers, 0);
+	if (!mci)
+		return -ENOMEM;
+
+	edac_dbg(3, "MC: init mci\n");
+
+	mci->pdev = &pdev->dev;
+	mci->mtype_cap = MEM_FLAG_DDR2;
+
+	mci->edac_ctl_cap = EDAC_FLAG_SECDED;
+	mci->edac_cap = EDAC_FLAG_SECDED;
+
+	mci->mod_name = EDAC_MOD_STR;
+	mci->ctl_name = x38_devs[dev_idx].ctl_name;
+	mci->dev_name = pci_name(pdev);
+	mci->edac_check = x38_check;
+	mci->ctl_page_to_phys = NULL;
+	mci->pvt_info = window;
+
+	stacked = x38_is_stacked(pdev, drbs);
+
+	/*
+	 * The dram rank boundary (DRB) reg values are boundary addresses
+	 * for each DRAM rank with a granularity of 64MB.  DRB regs are
+	 * cumulative; the last one will contain the total memory
+	 * contained in all ranks.
+	 */
+	for (i = 0; i < mci->nr_csrows; i++) {
+		unsigned long nr_pages;
+		struct csrow_info *csrow = mci->csrows[i];
+
+		nr_pages = drb_to_nr_pages(drbs, stacked,
+			i / X38_RANKS_PER_CHANNEL,
+			i % X38_RANKS_PER_CHANNEL);
+
+		if (nr_pages == 0)
+			continue;
+
+		for (j = 0; j < x38_channel_num; j++) {
+			struct dimm_info *dimm = csrow->channels[j]->dimm;
+
+			dimm->nr_pages = nr_pages / x38_channel_num;
+			dimm->grain = nr_pages << PAGE_SHIFT;
+			dimm->mtype = MEM_DDR2;
+			dimm->dtype = DEV_UNKNOWN;
+			dimm->edac_mode = EDAC_UNKNOWN;
+		}
+	}
+
+	x38_clear_error_info(mci);
+
+	rc = -ENODEV;
+	if (edac_mc_add_mc(mci)) {
+		edac_dbg(3, "MC: failed edac_mc_add_mc()\n");
+		goto fail;
+	}
+
+	/* get this far and it's successful */
+	edac_dbg(3, "MC: success\n");
+	return 0;
+
+fail:
+	iounmap(window);
+	if (mci)
+		edac_mc_free(mci);
+
+	return rc;
+}
+
+static int x38_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
+{
+	int rc;
+
+	edac_dbg(0, "MC:\n");
+
+	if (pci_enable_device(pdev) < 0)
+		return -EIO;
+
+	rc = x38_probe1(pdev, ent->driver_data);
+	if (!mci_pdev)
+		mci_pdev = pci_dev_get(pdev);
+
+	return rc;
+}
+
+static void x38_remove_one(struct pci_dev *pdev)
+{
+	struct mem_ctl_info *mci;
+
+	edac_dbg(0, "\n");
+
+	mci = edac_mc_del_mc(&pdev->dev);
+	if (!mci)
+		return;
+
+	iounmap(mci->pvt_info);
+
+	edac_mc_free(mci);
+}
+
+static const struct pci_device_id x38_pci_tbl[] = {
+	{
+	 PCI_VEND_DEV(INTEL, X38_HB), PCI_ANY_ID, PCI_ANY_ID, 0, 0,
+	 X38},
+	{
+	 0,
+	 }			/* 0 terminated list. */
+};
+
+MODULE_DEVICE_TABLE(pci, x38_pci_tbl);
+
+static struct pci_driver x38_driver = {
+	.name = EDAC_MOD_STR,
+	.probe = x38_init_one,
+	.remove = x38_remove_one,
+	.id_table = x38_pci_tbl,
+};
+
+static int __init x38_init(void)
+{
+	int pci_rc;
+
+	edac_dbg(3, "MC:\n");
+
+	/* Ensure that the OPSTATE is set correctly for POLL or NMI */
+	opstate_init();
+
+	pci_rc = pci_register_driver(&x38_driver);
+	if (pci_rc < 0)
+		goto fail0;
+
+	if (!mci_pdev) {
+		x38_registered = 0;
+		mci_pdev = pci_get_device(PCI_VENDOR_ID_INTEL,
+					PCI_DEVICE_ID_INTEL_X38_HB, NULL);
+		if (!mci_pdev) {
+			edac_dbg(0, "x38 pci_get_device fail\n");
+			pci_rc = -ENODEV;
+			goto fail1;
+		}
+
+		pci_rc = x38_init_one(mci_pdev, x38_pci_tbl);
+		if (pci_rc < 0) {
+			edac_dbg(0, "x38 init fail\n");
+			pci_rc = -ENODEV;
+			goto fail1;
+		}
+	}
+
+	return 0;
+
+fail1:
+	pci_unregister_driver(&x38_driver);
+
+fail0:
+	pci_dev_put(mci_pdev);
+
+	return pci_rc;
+}
+
+static void __exit x38_exit(void)
+{
+	edac_dbg(3, "MC:\n");
+
+	pci_unregister_driver(&x38_driver);
+	if (!x38_registered) {
+		x38_remove_one(mci_pdev);
+		pci_dev_put(mci_pdev);
+	}
+}
+
+module_init(x38_init);
+module_exit(x38_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Cluster Computing, Inc. Hitoshi Mitake");
+MODULE_DESCRIPTION("MC support for Intel X38 memory hub controllers");
+
+module_param(edac_op_state, int, 0444);
+MODULE_PARM_DESC(edac_op_state, "EDAC Error Reporting state: 0=Poll,1=NMI");