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, 612 insertions, 0 deletions

diff --git a/drivers/misc/sgi-gru/grufile.c b/drivers/misc/sgi-gru/grufile.c
new file mode 100644
index 000000000..7ffcfc0bb
--- /dev/null
+++ b/drivers/misc/sgi-gru/grufile.c
@@ -0,0 +1,612 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * SN Platform GRU Driver
+ *
+ *              FILE OPERATIONS & DRIVER INITIALIZATION
+ *
+ * This file supports the user system call for file open, close, mmap, etc.
+ * This also incudes the driver initialization code.
+ *
+ *  (C) Copyright 2020 Hewlett Packard Enterprise Development LP
+ *  Copyright (c) 2008-2014 Silicon Graphics, Inc.  All Rights Reserved.
+ */
+
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/slab.h>
+#include <linux/mm.h>
+#include <linux/io.h>
+#include <linux/spinlock.h>
+#include <linux/device.h>
+#include <linux/miscdevice.h>
+#include <linux/interrupt.h>
+#include <linux/proc_fs.h>
+#include <linux/uaccess.h>
+#ifdef CONFIG_X86_64
+#include <asm/uv/uv_irq.h>
+#endif
+#include <asm/uv/uv.h>
+#include "gru.h"
+#include "grulib.h"
+#include "grutables.h"
+
+#include <asm/uv/uv_hub.h>
+#include <asm/uv/uv_mmrs.h>
+
+struct gru_blade_state *gru_base[GRU_MAX_BLADES] __read_mostly;
+unsigned long gru_start_paddr __read_mostly;
+void *gru_start_vaddr __read_mostly;
+unsigned long gru_end_paddr __read_mostly;
+unsigned int gru_max_gids __read_mostly;
+struct gru_stats_s gru_stats;
+
+/* Guaranteed user available resources on each node */
+static int max_user_cbrs, max_user_dsr_bytes;
+
+static struct miscdevice gru_miscdev;
+
+static int gru_supported(void)
+{
+	return is_uv_system() &&
+		(uv_hub_info->hub_revision < UV3_HUB_REVISION_BASE);
+}
+
+/*
+ * gru_vma_close
+ *
+ * Called when unmapping a device mapping. Frees all gru resources
+ * and tables belonging to the vma.
+ */
+static void gru_vma_close(struct vm_area_struct *vma)
+{
+	struct gru_vma_data *vdata;
+	struct gru_thread_state *gts;
+	struct list_head *entry, *next;
+
+	if (!vma->vm_private_data)
+		return;
+
+	vdata = vma->vm_private_data;
+	vma->vm_private_data = NULL;
+	gru_dbg(grudev, "vma %p, file %p, vdata %p\n", vma, vma->vm_file,
+				vdata);
+	list_for_each_safe(entry, next, &vdata->vd_head) {
+		gts =
+		    list_entry(entry, struct gru_thread_state, ts_next);
+		list_del(&gts->ts_next);
+		mutex_lock(&gts->ts_ctxlock);
+		if (gts->ts_gru)
+			gru_unload_context(gts, 0);
+		mutex_unlock(&gts->ts_ctxlock);
+		gts_drop(gts);
+	}
+	kfree(vdata);
+	STAT(vdata_free);
+}
+
+/*
+ * gru_file_mmap
+ *
+ * Called when mmapping the device.  Initializes the vma with a fault handler
+ * and private data structure necessary to allocate, track, and free the
+ * underlying pages.
+ */
+static int gru_file_mmap(struct file *file, struct vm_area_struct *vma)
+{
+	if ((vma->vm_flags & (VM_SHARED | VM_WRITE)) != (VM_SHARED | VM_WRITE))
+		return -EPERM;
+
+	if (vma->vm_start & (GRU_GSEG_PAGESIZE - 1) ||
+				vma->vm_end & (GRU_GSEG_PAGESIZE - 1))
+		return -EINVAL;
+
+	vma->vm_flags |= VM_IO | VM_PFNMAP | VM_LOCKED |
+			 VM_DONTCOPY | VM_DONTEXPAND | VM_DONTDUMP;
+	vma->vm_page_prot = PAGE_SHARED;
+	vma->vm_ops = &gru_vm_ops;
+
+	vma->vm_private_data = gru_alloc_vma_data(vma, 0);
+	if (!vma->vm_private_data)
+		return -ENOMEM;
+
+	gru_dbg(grudev, "file %p, vaddr 0x%lx, vma %p, vdata %p\n",
+		file, vma->vm_start, vma, vma->vm_private_data);
+	return 0;
+}
+
+/*
+ * Create a new GRU context
+ */
+static int gru_create_new_context(unsigned long arg)
+{
+	struct gru_create_context_req req;
+	struct vm_area_struct *vma;
+	struct gru_vma_data *vdata;
+	int ret = -EINVAL;
+
+	if (copy_from_user(&req, (void __user *)arg, sizeof(req)))
+		return -EFAULT;
+
+	if (req.data_segment_bytes > max_user_dsr_bytes)
+		return -EINVAL;
+	if (req.control_blocks > max_user_cbrs || !req.maximum_thread_count)
+		return -EINVAL;
+
+	if (!(req.options & GRU_OPT_MISS_MASK))
+		req.options |= GRU_OPT_MISS_FMM_INTR;
+
+	mmap_write_lock(current->mm);
+	vma = gru_find_vma(req.gseg);
+	if (vma) {
+		vdata = vma->vm_private_data;
+		vdata->vd_user_options = req.options;
+		vdata->vd_dsr_au_count =
+		    GRU_DS_BYTES_TO_AU(req.data_segment_bytes);
+		vdata->vd_cbr_au_count = GRU_CB_COUNT_TO_AU(req.control_blocks);
+		vdata->vd_tlb_preload_count = req.tlb_preload_count;
+		ret = 0;
+	}
+	mmap_write_unlock(current->mm);
+
+	return ret;
+}
+
+/*
+ * Get GRU configuration info (temp - for emulator testing)
+ */
+static long gru_get_config_info(unsigned long arg)
+{
+	struct gru_config_info info;
+	int nodesperblade;
+
+	if (num_online_nodes() > 1 &&
+			(uv_node_to_blade_id(1) == uv_node_to_blade_id(0)))
+		nodesperblade = 2;
+	else
+		nodesperblade = 1;
+	memset(&info, 0, sizeof(info));
+	info.cpus = num_online_cpus();
+	info.nodes = num_online_nodes();
+	info.blades = info.nodes / nodesperblade;
+	info.chiplets = GRU_CHIPLETS_PER_BLADE * info.blades;
+
+	if (copy_to_user((void __user *)arg, &info, sizeof(info)))
+		return -EFAULT;
+	return 0;
+}
+
+/*
+ * gru_file_unlocked_ioctl
+ *
+ * Called to update file attributes via IOCTL calls.
+ */
+static long gru_file_unlocked_ioctl(struct file *file, unsigned int req,
+				    unsigned long arg)
+{
+	int err = -EBADRQC;
+
+	gru_dbg(grudev, "file %p, req 0x%x, 0x%lx\n", file, req, arg);
+
+	switch (req) {
+	case GRU_CREATE_CONTEXT:
+		err = gru_create_new_context(arg);
+		break;
+	case GRU_SET_CONTEXT_OPTION:
+		err = gru_set_context_option(arg);
+		break;
+	case GRU_USER_GET_EXCEPTION_DETAIL:
+		err = gru_get_exception_detail(arg);
+		break;
+	case GRU_USER_UNLOAD_CONTEXT:
+		err = gru_user_unload_context(arg);
+		break;
+	case GRU_USER_FLUSH_TLB:
+		err = gru_user_flush_tlb(arg);
+		break;
+	case GRU_USER_CALL_OS:
+		err = gru_handle_user_call_os(arg);
+		break;
+	case GRU_GET_GSEG_STATISTICS:
+		err = gru_get_gseg_statistics(arg);
+		break;
+	case GRU_KTEST:
+		err = gru_ktest(arg);
+		break;
+	case GRU_GET_CONFIG_INFO:
+		err = gru_get_config_info(arg);
+		break;
+	case GRU_DUMP_CHIPLET_STATE:
+		err = gru_dump_chiplet_request(arg);
+		break;
+	}
+	return err;
+}
+
+/*
+ * Called at init time to build tables for all GRUs that are present in the
+ * system.
+ */
+static void gru_init_chiplet(struct gru_state *gru, unsigned long paddr,
+			     void *vaddr, int blade_id, int chiplet_id)
+{
+	spin_lock_init(&gru->gs_lock);
+	spin_lock_init(&gru->gs_asid_lock);
+	gru->gs_gru_base_paddr = paddr;
+	gru->gs_gru_base_vaddr = vaddr;
+	gru->gs_gid = blade_id * GRU_CHIPLETS_PER_BLADE + chiplet_id;
+	gru->gs_blade = gru_base[blade_id];
+	gru->gs_blade_id = blade_id;
+	gru->gs_chiplet_id = chiplet_id;
+	gru->gs_cbr_map = (GRU_CBR_AU == 64) ? ~0 : (1UL << GRU_CBR_AU) - 1;
+	gru->gs_dsr_map = (1UL << GRU_DSR_AU) - 1;
+	gru->gs_asid_limit = MAX_ASID;
+	gru_tgh_flush_init(gru);
+	if (gru->gs_gid >= gru_max_gids)
+		gru_max_gids = gru->gs_gid + 1;
+	gru_dbg(grudev, "bid %d, gid %d, vaddr %p (0x%lx)\n",
+		blade_id, gru->gs_gid, gru->gs_gru_base_vaddr,
+		gru->gs_gru_base_paddr);
+}
+
+static int gru_init_tables(unsigned long gru_base_paddr, void *gru_base_vaddr)
+{
+	int pnode, nid, bid, chip;
+	int cbrs, dsrbytes, n;
+	int order = get_order(sizeof(struct gru_blade_state));
+	struct page *page;
+	struct gru_state *gru;
+	unsigned long paddr;
+	void *vaddr;
+
+	max_user_cbrs = GRU_NUM_CB;
+	max_user_dsr_bytes = GRU_NUM_DSR_BYTES;
+	for_each_possible_blade(bid) {
+		pnode = uv_blade_to_pnode(bid);
+		nid = uv_blade_to_memory_nid(bid);/* -1 if no memory on blade */
+		page = alloc_pages_node(nid, GFP_KERNEL, order);
+		if (!page)
+			goto fail;
+		gru_base[bid] = page_address(page);
+		memset(gru_base[bid], 0, sizeof(struct gru_blade_state));
+		gru_base[bid]->bs_lru_gru = &gru_base[bid]->bs_grus[0];
+		spin_lock_init(&gru_base[bid]->bs_lock);
+		init_rwsem(&gru_base[bid]->bs_kgts_sema);
+
+		dsrbytes = 0;
+		cbrs = 0;
+		for (gru = gru_base[bid]->bs_grus, chip = 0;
+				chip < GRU_CHIPLETS_PER_BLADE;
+				chip++, gru++) {
+			paddr = gru_chiplet_paddr(gru_base_paddr, pnode, chip);
+			vaddr = gru_chiplet_vaddr(gru_base_vaddr, pnode, chip);
+			gru_init_chiplet(gru, paddr, vaddr, bid, chip);
+			n = hweight64(gru->gs_cbr_map) * GRU_CBR_AU_SIZE;
+			cbrs = max(cbrs, n);
+			n = hweight64(gru->gs_dsr_map) * GRU_DSR_AU_BYTES;
+			dsrbytes = max(dsrbytes, n);
+		}
+		max_user_cbrs = min(max_user_cbrs, cbrs);
+		max_user_dsr_bytes = min(max_user_dsr_bytes, dsrbytes);
+	}
+
+	return 0;
+
+fail:
+	for (bid--; bid >= 0; bid--)
+		free_pages((unsigned long)gru_base[bid], order);
+	return -ENOMEM;
+}
+
+static void gru_free_tables(void)
+{
+	int bid;
+	int order = get_order(sizeof(struct gru_state) *
+			      GRU_CHIPLETS_PER_BLADE);
+
+	for (bid = 0; bid < GRU_MAX_BLADES; bid++)
+		free_pages((unsigned long)gru_base[bid], order);
+}
+
+static unsigned long gru_chiplet_cpu_to_mmr(int chiplet, int cpu, int *corep)
+{
+	unsigned long mmr = 0;
+	int core;
+
+	/*
+	 * We target the cores of a blade and not the hyperthreads themselves.
+	 * There is a max of 8 cores per socket and 2 sockets per blade,
+	 * making for a max total of 16 cores (i.e., 16 CPUs without
+	 * hyperthreading and 32 CPUs with hyperthreading).
+	 */
+	core = uv_cpu_core_number(cpu) + UV_MAX_INT_CORES * uv_cpu_socket_number(cpu);
+	if (core >= GRU_NUM_TFM || uv_cpu_ht_number(cpu))
+		return 0;
+
+	if (chiplet == 0) {
+		mmr = UVH_GR0_TLB_INT0_CONFIG +
+		    core * (UVH_GR0_TLB_INT1_CONFIG - UVH_GR0_TLB_INT0_CONFIG);
+	} else if (chiplet == 1) {
+		mmr = UVH_GR1_TLB_INT0_CONFIG +
+		    core * (UVH_GR1_TLB_INT1_CONFIG - UVH_GR1_TLB_INT0_CONFIG);
+	} else {
+		BUG();
+	}
+
+	*corep = core;
+	return mmr;
+}
+
+#ifdef CONFIG_IA64
+
+static int gru_irq_count[GRU_CHIPLETS_PER_BLADE];
+
+static void gru_noop(struct irq_data *d)
+{
+}
+
+static struct irq_chip gru_chip[GRU_CHIPLETS_PER_BLADE] = {
+	[0 ... GRU_CHIPLETS_PER_BLADE - 1] {
+		.irq_mask	= gru_noop,
+		.irq_unmask	= gru_noop,
+		.irq_ack	= gru_noop
+	}
+};
+
+static int gru_chiplet_setup_tlb_irq(int chiplet, char *irq_name,
+			irq_handler_t irq_handler, int cpu, int blade)
+{
+	unsigned long mmr;
+	int irq = IRQ_GRU + chiplet;
+	int ret, core;
+
+	mmr = gru_chiplet_cpu_to_mmr(chiplet, cpu, &core);
+	if (mmr == 0)
+		return 0;
+
+	if (gru_irq_count[chiplet] == 0) {
+		gru_chip[chiplet].name = irq_name;
+		ret = irq_set_chip(irq, &gru_chip[chiplet]);
+		if (ret) {
+			printk(KERN_ERR "%s: set_irq_chip failed, errno=%d\n",
+			       GRU_DRIVER_ID_STR, -ret);
+			return ret;
+		}
+
+		ret = request_irq(irq, irq_handler, 0, irq_name, NULL);
+		if (ret) {
+			printk(KERN_ERR "%s: request_irq failed, errno=%d\n",
+			       GRU_DRIVER_ID_STR, -ret);
+			return ret;
+		}
+	}
+	gru_irq_count[chiplet]++;
+
+	return 0;
+}
+
+static void gru_chiplet_teardown_tlb_irq(int chiplet, int cpu, int blade)
+{
+	unsigned long mmr;
+	int core, irq = IRQ_GRU + chiplet;
+
+	if (gru_irq_count[chiplet] == 0)
+		return;
+
+	mmr = gru_chiplet_cpu_to_mmr(chiplet, cpu, &core);
+	if (mmr == 0)
+		return;
+
+	if (--gru_irq_count[chiplet] == 0)
+		free_irq(irq, NULL);
+}
+
+#elif defined CONFIG_X86_64
+
+static int gru_chiplet_setup_tlb_irq(int chiplet, char *irq_name,
+			irq_handler_t irq_handler, int cpu, int blade)
+{
+	unsigned long mmr;
+	int irq, core;
+	int ret;
+
+	mmr = gru_chiplet_cpu_to_mmr(chiplet, cpu, &core);
+	if (mmr == 0)
+		return 0;
+
+	irq = uv_setup_irq(irq_name, cpu, blade, mmr, UV_AFFINITY_CPU);
+	if (irq < 0) {
+		printk(KERN_ERR "%s: uv_setup_irq failed, errno=%d\n",
+		       GRU_DRIVER_ID_STR, -irq);
+		return irq;
+	}
+
+	ret = request_irq(irq, irq_handler, 0, irq_name, NULL);
+	if (ret) {
+		uv_teardown_irq(irq);
+		printk(KERN_ERR "%s: request_irq failed, errno=%d\n",
+		       GRU_DRIVER_ID_STR, -ret);
+		return ret;
+	}
+	gru_base[blade]->bs_grus[chiplet].gs_irq[core] = irq;
+	return 0;
+}
+
+static void gru_chiplet_teardown_tlb_irq(int chiplet, int cpu, int blade)
+{
+	int irq, core;
+	unsigned long mmr;
+
+	mmr = gru_chiplet_cpu_to_mmr(chiplet, cpu, &core);
+	if (mmr) {
+		irq = gru_base[blade]->bs_grus[chiplet].gs_irq[core];
+		if (irq) {
+			free_irq(irq, NULL);
+			uv_teardown_irq(irq);
+		}
+	}
+}
+
+#endif
+
+static void gru_teardown_tlb_irqs(void)
+{
+	int blade;
+	int cpu;
+
+	for_each_online_cpu(cpu) {
+		blade = uv_cpu_to_blade_id(cpu);
+		gru_chiplet_teardown_tlb_irq(0, cpu, blade);
+		gru_chiplet_teardown_tlb_irq(1, cpu, blade);
+	}
+	for_each_possible_blade(blade) {
+		if (uv_blade_nr_possible_cpus(blade))
+			continue;
+		gru_chiplet_teardown_tlb_irq(0, 0, blade);
+		gru_chiplet_teardown_tlb_irq(1, 0, blade);
+	}
+}
+
+static int gru_setup_tlb_irqs(void)
+{
+	int blade;
+	int cpu;
+	int ret;
+
+	for_each_online_cpu(cpu) {
+		blade = uv_cpu_to_blade_id(cpu);
+		ret = gru_chiplet_setup_tlb_irq(0, "GRU0_TLB", gru0_intr, cpu, blade);
+		if (ret != 0)
+			goto exit1;
+
+		ret = gru_chiplet_setup_tlb_irq(1, "GRU1_TLB", gru1_intr, cpu, blade);
+		if (ret != 0)
+			goto exit1;
+	}
+	for_each_possible_blade(blade) {
+		if (uv_blade_nr_possible_cpus(blade))
+			continue;
+		ret = gru_chiplet_setup_tlb_irq(0, "GRU0_TLB", gru_intr_mblade, 0, blade);
+		if (ret != 0)
+			goto exit1;
+
+		ret = gru_chiplet_setup_tlb_irq(1, "GRU1_TLB", gru_intr_mblade, 0, blade);
+		if (ret != 0)
+			goto exit1;
+	}
+
+	return 0;
+
+exit1:
+	gru_teardown_tlb_irqs();
+	return ret;
+}
+
+/*
+ * gru_init
+ *
+ * Called at boot or module load time to initialize the GRUs.
+ */
+static int __init gru_init(void)
+{
+	int ret;
+
+	if (!gru_supported())
+		return 0;
+
+#if defined CONFIG_IA64
+	gru_start_paddr = 0xd000000000UL; /* ZZZZZZZZZZZZZZZZZZZ fixme */
+#else
+	gru_start_paddr = uv_read_local_mmr(UVH_RH_GAM_GRU_OVERLAY_CONFIG) &
+				0x7fffffffffffUL;
+#endif
+	gru_start_vaddr = __va(gru_start_paddr);
+	gru_end_paddr = gru_start_paddr + GRU_MAX_BLADES * GRU_SIZE;
+	printk(KERN_INFO "GRU space: 0x%lx - 0x%lx\n",
+	       gru_start_paddr, gru_end_paddr);
+	ret = misc_register(&gru_miscdev);
+	if (ret) {
+		printk(KERN_ERR "%s: misc_register failed\n",
+		       GRU_DRIVER_ID_STR);
+		goto exit0;
+	}
+
+	ret = gru_proc_init();
+	if (ret) {
+		printk(KERN_ERR "%s: proc init failed\n", GRU_DRIVER_ID_STR);
+		goto exit1;
+	}
+
+	ret = gru_init_tables(gru_start_paddr, gru_start_vaddr);
+	if (ret) {
+		printk(KERN_ERR "%s: init tables failed\n", GRU_DRIVER_ID_STR);
+		goto exit2;
+	}
+
+	ret = gru_setup_tlb_irqs();
+	if (ret != 0)
+		goto exit3;
+
+	gru_kservices_init();
+
+	printk(KERN_INFO "%s: v%s\n", GRU_DRIVER_ID_STR,
+	       GRU_DRIVER_VERSION_STR);
+	return 0;
+
+exit3:
+	gru_free_tables();
+exit2:
+	gru_proc_exit();
+exit1:
+	misc_deregister(&gru_miscdev);
+exit0:
+	return ret;
+
+}
+
+static void __exit gru_exit(void)
+{
+	if (!gru_supported())
+		return;
+
+	gru_teardown_tlb_irqs();
+	gru_kservices_exit();
+	gru_free_tables();
+	misc_deregister(&gru_miscdev);
+	gru_proc_exit();
+	mmu_notifier_synchronize();
+}
+
+static const struct file_operations gru_fops = {
+	.owner		= THIS_MODULE,
+	.unlocked_ioctl	= gru_file_unlocked_ioctl,
+	.mmap		= gru_file_mmap,
+	.llseek		= noop_llseek,
+};
+
+static struct miscdevice gru_miscdev = {
+	.minor		= MISC_DYNAMIC_MINOR,
+	.name		= "gru",
+	.fops		= &gru_fops,
+};
+
+const struct vm_operations_struct gru_vm_ops = {
+	.close		= gru_vma_close,
+	.fault		= gru_fault,
+};
+
+#ifndef MODULE
+fs_initcall(gru_init);
+#else
+module_init(gru_init);
+#endif
+module_exit(gru_exit);
+
+module_param(gru_options, ulong, 0644);
+MODULE_PARM_DESC(gru_options, "Various debug options");
+
+MODULE_AUTHOR("Silicon Graphics, Inc.");
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION(GRU_DRIVER_ID_STR GRU_DRIVER_VERSION_STR);
+MODULE_VERSION(GRU_DRIVER_VERSION_STR);
+