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, 604 insertions, 0 deletions

diff --git a/drivers/infiniband/hw/mlx4/cm.c b/drivers/infiniband/hw/mlx4/cm.c
new file mode 100644
index 000000000..12b481d13
--- /dev/null
+++ b/drivers/infiniband/hw/mlx4/cm.c
@@ -0,0 +1,604 @@
+/*
+ * Copyright (c) 2012 Mellanox Technologies. All rights reserved.
+ *
+ * This software is available to you under a choice of one of two
+ * licenses.  You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the
+ * OpenIB.org BSD license below:
+ *
+ *     Redistribution and use in source and binary forms, with or
+ *     without modification, are permitted provided that the following
+ *     conditions are met:
+ *
+ *      - Redistributions of source code must retain the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer.
+ *
+ *      - Redistributions in binary form must reproduce the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer in the documentation and/or other materials
+ *        provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#include <rdma/ib_mad.h>
+
+#include <linux/mlx4/cmd.h>
+#include <linux/rbtree.h>
+#include <linux/idr.h>
+#include <rdma/ib_cm.h>
+
+#include "mlx4_ib.h"
+
+#define CM_CLEANUP_CACHE_TIMEOUT  (30 * HZ)
+
+struct id_map_entry {
+	struct rb_node node;
+
+	u32 sl_cm_id;
+	u32 pv_cm_id;
+	int slave_id;
+	int scheduled_delete;
+	struct mlx4_ib_dev *dev;
+
+	struct list_head list;
+	struct delayed_work timeout;
+};
+
+struct rej_tmout_entry {
+	int slave;
+	u32 rem_pv_cm_id;
+	struct delayed_work timeout;
+	struct xarray *xa_rej_tmout;
+};
+
+struct cm_generic_msg {
+	struct ib_mad_hdr hdr;
+
+	__be32 local_comm_id;
+	__be32 remote_comm_id;
+	unsigned char unused[2];
+	__be16 rej_reason;
+};
+
+struct cm_sidr_generic_msg {
+	struct ib_mad_hdr hdr;
+	__be32 request_id;
+};
+
+struct cm_req_msg {
+	unsigned char unused[0x60];
+	union ib_gid primary_path_sgid;
+};
+
+static struct workqueue_struct *cm_wq;
+
+static void set_local_comm_id(struct ib_mad *mad, u32 cm_id)
+{
+	if (mad->mad_hdr.attr_id == CM_SIDR_REQ_ATTR_ID) {
+		struct cm_sidr_generic_msg *msg =
+			(struct cm_sidr_generic_msg *)mad;
+		msg->request_id = cpu_to_be32(cm_id);
+	} else if (mad->mad_hdr.attr_id == CM_SIDR_REP_ATTR_ID) {
+		pr_err("trying to set local_comm_id in SIDR_REP\n");
+		return;
+	} else {
+		struct cm_generic_msg *msg = (struct cm_generic_msg *)mad;
+		msg->local_comm_id = cpu_to_be32(cm_id);
+	}
+}
+
+static u32 get_local_comm_id(struct ib_mad *mad)
+{
+	if (mad->mad_hdr.attr_id == CM_SIDR_REQ_ATTR_ID) {
+		struct cm_sidr_generic_msg *msg =
+			(struct cm_sidr_generic_msg *)mad;
+		return be32_to_cpu(msg->request_id);
+	} else if (mad->mad_hdr.attr_id == CM_SIDR_REP_ATTR_ID) {
+		pr_err("trying to set local_comm_id in SIDR_REP\n");
+		return -1;
+	} else {
+		struct cm_generic_msg *msg = (struct cm_generic_msg *)mad;
+		return be32_to_cpu(msg->local_comm_id);
+	}
+}
+
+static void set_remote_comm_id(struct ib_mad *mad, u32 cm_id)
+{
+	if (mad->mad_hdr.attr_id == CM_SIDR_REP_ATTR_ID) {
+		struct cm_sidr_generic_msg *msg =
+			(struct cm_sidr_generic_msg *)mad;
+		msg->request_id = cpu_to_be32(cm_id);
+	} else if (mad->mad_hdr.attr_id == CM_SIDR_REQ_ATTR_ID) {
+		pr_err("trying to set remote_comm_id in SIDR_REQ\n");
+		return;
+	} else {
+		struct cm_generic_msg *msg = (struct cm_generic_msg *)mad;
+		msg->remote_comm_id = cpu_to_be32(cm_id);
+	}
+}
+
+static u32 get_remote_comm_id(struct ib_mad *mad)
+{
+	if (mad->mad_hdr.attr_id == CM_SIDR_REP_ATTR_ID) {
+		struct cm_sidr_generic_msg *msg =
+			(struct cm_sidr_generic_msg *)mad;
+		return be32_to_cpu(msg->request_id);
+	} else if (mad->mad_hdr.attr_id == CM_SIDR_REQ_ATTR_ID) {
+		pr_err("trying to set remote_comm_id in SIDR_REQ\n");
+		return -1;
+	} else {
+		struct cm_generic_msg *msg = (struct cm_generic_msg *)mad;
+		return be32_to_cpu(msg->remote_comm_id);
+	}
+}
+
+static union ib_gid gid_from_req_msg(struct ib_device *ibdev, struct ib_mad *mad)
+{
+	struct cm_req_msg *msg = (struct cm_req_msg *)mad;
+
+	return msg->primary_path_sgid;
+}
+
+/* Lock should be taken before called */
+static struct id_map_entry *
+id_map_find_by_sl_id(struct ib_device *ibdev, u32 slave_id, u32 sl_cm_id)
+{
+	struct rb_root *sl_id_map = &to_mdev(ibdev)->sriov.sl_id_map;
+	struct rb_node *node = sl_id_map->rb_node;
+
+	while (node) {
+		struct id_map_entry *id_map_entry =
+			rb_entry(node, struct id_map_entry, node);
+
+		if (id_map_entry->sl_cm_id > sl_cm_id)
+			node = node->rb_left;
+		else if (id_map_entry->sl_cm_id < sl_cm_id)
+			node = node->rb_right;
+		else if (id_map_entry->slave_id > slave_id)
+			node = node->rb_left;
+		else if (id_map_entry->slave_id < slave_id)
+			node = node->rb_right;
+		else
+			return id_map_entry;
+	}
+	return NULL;
+}
+
+static void id_map_ent_timeout(struct work_struct *work)
+{
+	struct delayed_work *delay = to_delayed_work(work);
+	struct id_map_entry *ent = container_of(delay, struct id_map_entry, timeout);
+	struct id_map_entry *found_ent;
+	struct mlx4_ib_dev *dev = ent->dev;
+	struct mlx4_ib_sriov *sriov = &dev->sriov;
+	struct rb_root *sl_id_map = &sriov->sl_id_map;
+
+	spin_lock(&sriov->id_map_lock);
+	if (!xa_erase(&sriov->pv_id_table, ent->pv_cm_id))
+		goto out;
+	found_ent = id_map_find_by_sl_id(&dev->ib_dev, ent->slave_id, ent->sl_cm_id);
+	if (found_ent && found_ent == ent)
+		rb_erase(&found_ent->node, sl_id_map);
+
+out:
+	list_del(&ent->list);
+	spin_unlock(&sriov->id_map_lock);
+	kfree(ent);
+}
+
+static void sl_id_map_add(struct ib_device *ibdev, struct id_map_entry *new)
+{
+	struct rb_root *sl_id_map = &to_mdev(ibdev)->sriov.sl_id_map;
+	struct rb_node **link = &sl_id_map->rb_node, *parent = NULL;
+	struct id_map_entry *ent;
+	int slave_id = new->slave_id;
+	int sl_cm_id = new->sl_cm_id;
+
+	ent = id_map_find_by_sl_id(ibdev, slave_id, sl_cm_id);
+	if (ent) {
+		pr_debug("overriding existing sl_id_map entry (cm_id = %x)\n",
+			 sl_cm_id);
+
+		rb_replace_node(&ent->node, &new->node, sl_id_map);
+		return;
+	}
+
+	/* Go to the bottom of the tree */
+	while (*link) {
+		parent = *link;
+		ent = rb_entry(parent, struct id_map_entry, node);
+
+		if (ent->sl_cm_id > sl_cm_id || (ent->sl_cm_id == sl_cm_id && ent->slave_id > slave_id))
+			link = &(*link)->rb_left;
+		else
+			link = &(*link)->rb_right;
+	}
+
+	rb_link_node(&new->node, parent, link);
+	rb_insert_color(&new->node, sl_id_map);
+}
+
+static struct id_map_entry *
+id_map_alloc(struct ib_device *ibdev, int slave_id, u32 sl_cm_id)
+{
+	int ret;
+	struct id_map_entry *ent;
+	struct mlx4_ib_sriov *sriov = &to_mdev(ibdev)->sriov;
+
+	ent = kmalloc(sizeof (struct id_map_entry), GFP_KERNEL);
+	if (!ent)
+		return ERR_PTR(-ENOMEM);
+
+	ent->sl_cm_id = sl_cm_id;
+	ent->slave_id = slave_id;
+	ent->scheduled_delete = 0;
+	ent->dev = to_mdev(ibdev);
+	INIT_DELAYED_WORK(&ent->timeout, id_map_ent_timeout);
+
+	ret = xa_alloc_cyclic(&sriov->pv_id_table, &ent->pv_cm_id, ent,
+			xa_limit_32b, &sriov->pv_id_next, GFP_KERNEL);
+	if (ret >= 0) {
+		spin_lock(&sriov->id_map_lock);
+		sl_id_map_add(ibdev, ent);
+		list_add_tail(&ent->list, &sriov->cm_list);
+		spin_unlock(&sriov->id_map_lock);
+		return ent;
+	}
+
+	/*error flow*/
+	kfree(ent);
+	mlx4_ib_warn(ibdev, "Allocation failed (err:0x%x)\n", ret);
+	return ERR_PTR(-ENOMEM);
+}
+
+static struct id_map_entry *
+id_map_get(struct ib_device *ibdev, int *pv_cm_id, int slave_id, int sl_cm_id)
+{
+	struct id_map_entry *ent;
+	struct mlx4_ib_sriov *sriov = &to_mdev(ibdev)->sriov;
+
+	spin_lock(&sriov->id_map_lock);
+	if (*pv_cm_id == -1) {
+		ent = id_map_find_by_sl_id(ibdev, slave_id, sl_cm_id);
+		if (ent)
+			*pv_cm_id = (int) ent->pv_cm_id;
+	} else
+		ent = xa_load(&sriov->pv_id_table, *pv_cm_id);
+	spin_unlock(&sriov->id_map_lock);
+
+	return ent;
+}
+
+static void schedule_delayed(struct ib_device *ibdev, struct id_map_entry *id)
+{
+	struct mlx4_ib_sriov *sriov = &to_mdev(ibdev)->sriov;
+	unsigned long flags;
+
+	spin_lock(&sriov->id_map_lock);
+	spin_lock_irqsave(&sriov->going_down_lock, flags);
+	/*make sure that there is no schedule inside the scheduled work.*/
+	if (!sriov->is_going_down && !id->scheduled_delete) {
+		id->scheduled_delete = 1;
+		queue_delayed_work(cm_wq, &id->timeout, CM_CLEANUP_CACHE_TIMEOUT);
+	} else if (id->scheduled_delete) {
+		/* Adjust timeout if already scheduled */
+		mod_delayed_work(cm_wq, &id->timeout, CM_CLEANUP_CACHE_TIMEOUT);
+	}
+	spin_unlock_irqrestore(&sriov->going_down_lock, flags);
+	spin_unlock(&sriov->id_map_lock);
+}
+
+#define REJ_REASON(m) be16_to_cpu(((struct cm_generic_msg *)(m))->rej_reason)
+int mlx4_ib_multiplex_cm_handler(struct ib_device *ibdev, int port, int slave_id,
+		struct ib_mad *mad)
+{
+	struct id_map_entry *id;
+	u32 sl_cm_id;
+	int pv_cm_id = -1;
+
+	if (mad->mad_hdr.attr_id == CM_REQ_ATTR_ID ||
+	    mad->mad_hdr.attr_id == CM_REP_ATTR_ID ||
+	    mad->mad_hdr.attr_id == CM_MRA_ATTR_ID ||
+	    mad->mad_hdr.attr_id == CM_SIDR_REQ_ATTR_ID ||
+	    (mad->mad_hdr.attr_id == CM_REJ_ATTR_ID && REJ_REASON(mad) == IB_CM_REJ_TIMEOUT)) {
+		sl_cm_id = get_local_comm_id(mad);
+		id = id_map_get(ibdev, &pv_cm_id, slave_id, sl_cm_id);
+		if (id)
+			goto cont;
+		id = id_map_alloc(ibdev, slave_id, sl_cm_id);
+		if (IS_ERR(id)) {
+			mlx4_ib_warn(ibdev, "%s: id{slave: %d, sl_cm_id: 0x%x} Failed to id_map_alloc\n",
+				__func__, slave_id, sl_cm_id);
+			return PTR_ERR(id);
+		}
+	} else if (mad->mad_hdr.attr_id == CM_REJ_ATTR_ID ||
+		   mad->mad_hdr.attr_id == CM_SIDR_REP_ATTR_ID) {
+		return 0;
+	} else {
+		sl_cm_id = get_local_comm_id(mad);
+		id = id_map_get(ibdev, &pv_cm_id, slave_id, sl_cm_id);
+	}
+
+	if (!id) {
+		pr_debug("id{slave: %d, sl_cm_id: 0x%x} is NULL! attr_id: 0x%x\n",
+			 slave_id, sl_cm_id, be16_to_cpu(mad->mad_hdr.attr_id));
+		return -EINVAL;
+	}
+
+cont:
+	set_local_comm_id(mad, id->pv_cm_id);
+
+	if (mad->mad_hdr.attr_id == CM_DREQ_ATTR_ID)
+		schedule_delayed(ibdev, id);
+	return 0;
+}
+
+static void rej_tmout_timeout(struct work_struct *work)
+{
+	struct delayed_work *delay = to_delayed_work(work);
+	struct rej_tmout_entry *item = container_of(delay, struct rej_tmout_entry, timeout);
+	struct rej_tmout_entry *deleted;
+
+	deleted = xa_cmpxchg(item->xa_rej_tmout, item->rem_pv_cm_id, item, NULL, 0);
+
+	if (deleted != item)
+		pr_debug("deleted(%p) != item(%p)\n", deleted, item);
+
+	kfree(item);
+}
+
+static int alloc_rej_tmout(struct mlx4_ib_sriov *sriov, u32 rem_pv_cm_id, int slave)
+{
+	struct rej_tmout_entry *item;
+	struct rej_tmout_entry *old;
+	int ret = 0;
+
+	xa_lock(&sriov->xa_rej_tmout);
+	item = xa_load(&sriov->xa_rej_tmout, (unsigned long)rem_pv_cm_id);
+
+	if (item) {
+		if (xa_err(item))
+			ret =  xa_err(item);
+		else
+			/* If a retry, adjust delayed work */
+			mod_delayed_work(cm_wq, &item->timeout, CM_CLEANUP_CACHE_TIMEOUT);
+		goto err_or_exists;
+	}
+	xa_unlock(&sriov->xa_rej_tmout);
+
+	item = kmalloc(sizeof(*item), GFP_KERNEL);
+	if (!item)
+		return -ENOMEM;
+
+	INIT_DELAYED_WORK(&item->timeout, rej_tmout_timeout);
+	item->slave = slave;
+	item->rem_pv_cm_id = rem_pv_cm_id;
+	item->xa_rej_tmout = &sriov->xa_rej_tmout;
+
+	old = xa_cmpxchg(&sriov->xa_rej_tmout, (unsigned long)rem_pv_cm_id, NULL, item, GFP_KERNEL);
+	if (old) {
+		pr_debug(
+			"Non-null old entry (%p) or error (%d) when inserting\n",
+			old, xa_err(old));
+		kfree(item);
+		return xa_err(old);
+	}
+
+	queue_delayed_work(cm_wq, &item->timeout, CM_CLEANUP_CACHE_TIMEOUT);
+
+	return 0;
+
+err_or_exists:
+	xa_unlock(&sriov->xa_rej_tmout);
+	return ret;
+}
+
+static int lookup_rej_tmout_slave(struct mlx4_ib_sriov *sriov, u32 rem_pv_cm_id)
+{
+	struct rej_tmout_entry *item;
+	int slave;
+
+	xa_lock(&sriov->xa_rej_tmout);
+	item = xa_load(&sriov->xa_rej_tmout, (unsigned long)rem_pv_cm_id);
+
+	if (!item || xa_err(item)) {
+		pr_debug("Could not find slave. rem_pv_cm_id 0x%x error: %d\n",
+			 rem_pv_cm_id, xa_err(item));
+		slave = !item ? -ENOENT : xa_err(item);
+	} else {
+		slave = item->slave;
+	}
+	xa_unlock(&sriov->xa_rej_tmout);
+
+	return slave;
+}
+
+int mlx4_ib_demux_cm_handler(struct ib_device *ibdev, int port, int *slave,
+			     struct ib_mad *mad)
+{
+	struct mlx4_ib_sriov *sriov = &to_mdev(ibdev)->sriov;
+	u32 rem_pv_cm_id = get_local_comm_id(mad);
+	u32 pv_cm_id;
+	struct id_map_entry *id;
+	int sts;
+
+	if (mad->mad_hdr.attr_id == CM_REQ_ATTR_ID ||
+	    mad->mad_hdr.attr_id == CM_SIDR_REQ_ATTR_ID) {
+		union ib_gid gid;
+
+		if (!slave)
+			return 0;
+
+		gid = gid_from_req_msg(ibdev, mad);
+		*slave = mlx4_ib_find_real_gid(ibdev, port, gid.global.interface_id);
+		if (*slave < 0) {
+			mlx4_ib_warn(ibdev, "failed matching slave_id by gid (0x%llx)\n",
+				     be64_to_cpu(gid.global.interface_id));
+			return -ENOENT;
+		}
+
+		sts = alloc_rej_tmout(sriov, rem_pv_cm_id, *slave);
+		if (sts)
+			/* Even if this fails, we pass on the REQ to the slave */
+			pr_debug("Could not allocate rej_tmout entry. rem_pv_cm_id 0x%x slave %d status %d\n",
+				 rem_pv_cm_id, *slave, sts);
+
+		return 0;
+	}
+
+	pv_cm_id = get_remote_comm_id(mad);
+	id = id_map_get(ibdev, (int *)&pv_cm_id, -1, -1);
+
+	if (!id) {
+		if (mad->mad_hdr.attr_id == CM_REJ_ATTR_ID &&
+		    REJ_REASON(mad) == IB_CM_REJ_TIMEOUT && slave) {
+			*slave = lookup_rej_tmout_slave(sriov, rem_pv_cm_id);
+
+			return (*slave < 0) ? *slave : 0;
+		}
+		pr_debug("Couldn't find an entry for pv_cm_id 0x%x, attr_id 0x%x\n",
+			 pv_cm_id, be16_to_cpu(mad->mad_hdr.attr_id));
+		return -ENOENT;
+	}
+
+	if (slave)
+		*slave = id->slave_id;
+	set_remote_comm_id(mad, id->sl_cm_id);
+
+	if (mad->mad_hdr.attr_id == CM_DREQ_ATTR_ID ||
+	    mad->mad_hdr.attr_id == CM_REJ_ATTR_ID)
+		schedule_delayed(ibdev, id);
+
+	return 0;
+}
+
+void mlx4_ib_cm_paravirt_init(struct mlx4_ib_dev *dev)
+{
+	spin_lock_init(&dev->sriov.id_map_lock);
+	INIT_LIST_HEAD(&dev->sriov.cm_list);
+	dev->sriov.sl_id_map = RB_ROOT;
+	xa_init_flags(&dev->sriov.pv_id_table, XA_FLAGS_ALLOC);
+	xa_init(&dev->sriov.xa_rej_tmout);
+}
+
+static void rej_tmout_xa_cleanup(struct mlx4_ib_sriov *sriov, int slave)
+{
+	struct rej_tmout_entry *item;
+	bool flush_needed = false;
+	unsigned long id;
+	int cnt = 0;
+
+	xa_lock(&sriov->xa_rej_tmout);
+	xa_for_each(&sriov->xa_rej_tmout, id, item) {
+		if (slave < 0 || slave == item->slave) {
+			mod_delayed_work(cm_wq, &item->timeout, 0);
+			flush_needed = true;
+			++cnt;
+		}
+	}
+	xa_unlock(&sriov->xa_rej_tmout);
+
+	if (flush_needed) {
+		flush_workqueue(cm_wq);
+		pr_debug("Deleted %d entries in xarray for slave %d during cleanup\n",
+			 cnt, slave);
+	}
+
+	if (slave < 0)
+		WARN_ON(!xa_empty(&sriov->xa_rej_tmout));
+}
+
+/* slave = -1 ==> all slaves */
+/* TBD -- call paravirt clean for single slave.  Need for slave RESET event */
+void mlx4_ib_cm_paravirt_clean(struct mlx4_ib_dev *dev, int slave)
+{
+	struct mlx4_ib_sriov *sriov = &dev->sriov;
+	struct rb_root *sl_id_map = &sriov->sl_id_map;
+	struct list_head lh;
+	struct rb_node *nd;
+	int need_flush = 0;
+	struct id_map_entry *map, *tmp_map;
+	/* cancel all delayed work queue entries */
+	INIT_LIST_HEAD(&lh);
+	spin_lock(&sriov->id_map_lock);
+	list_for_each_entry_safe(map, tmp_map, &dev->sriov.cm_list, list) {
+		if (slave < 0 || slave == map->slave_id) {
+			if (map->scheduled_delete)
+				need_flush |= !cancel_delayed_work(&map->timeout);
+		}
+	}
+
+	spin_unlock(&sriov->id_map_lock);
+
+	if (need_flush)
+		flush_workqueue(cm_wq); /* make sure all timers were flushed */
+
+	/* now, remove all leftover entries from databases*/
+	spin_lock(&sriov->id_map_lock);
+	if (slave < 0) {
+		while (rb_first(sl_id_map)) {
+			struct id_map_entry *ent =
+				rb_entry(rb_first(sl_id_map),
+					 struct id_map_entry, node);
+
+			rb_erase(&ent->node, sl_id_map);
+			xa_erase(&sriov->pv_id_table, ent->pv_cm_id);
+		}
+		list_splice_init(&dev->sriov.cm_list, &lh);
+	} else {
+		/* first, move nodes belonging to slave to db remove list */
+		nd = rb_first(sl_id_map);
+		while (nd) {
+			struct id_map_entry *ent =
+				rb_entry(nd, struct id_map_entry, node);
+			nd = rb_next(nd);
+			if (ent->slave_id == slave)
+				list_move_tail(&ent->list, &lh);
+		}
+		/* remove those nodes from databases */
+		list_for_each_entry_safe(map, tmp_map, &lh, list) {
+			rb_erase(&map->node, sl_id_map);
+			xa_erase(&sriov->pv_id_table, map->pv_cm_id);
+		}
+
+		/* add remaining nodes from cm_list */
+		list_for_each_entry_safe(map, tmp_map, &dev->sriov.cm_list, list) {
+			if (slave == map->slave_id)
+				list_move_tail(&map->list, &lh);
+		}
+	}
+
+	spin_unlock(&sriov->id_map_lock);
+
+	/* free any map entries left behind due to cancel_delayed_work above */
+	list_for_each_entry_safe(map, tmp_map, &lh, list) {
+		list_del(&map->list);
+		kfree(map);
+	}
+
+	rej_tmout_xa_cleanup(sriov, slave);
+}
+
+int mlx4_ib_cm_init(void)
+{
+	cm_wq = alloc_workqueue("mlx4_ib_cm", 0, 0);
+	if (!cm_wq)
+		return -ENOMEM;
+
+	return 0;
+}
+
+void mlx4_ib_cm_destroy(void)
+{
+	destroy_workqueue(cm_wq);
+}