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, 750 insertions, 0 deletions

diff --git a/drivers/infiniband/core/security.c b/drivers/infiniband/core/security.c
new file mode 100644
index 000000000..3512c2e54
--- /dev/null
+++ b/drivers/infiniband/core/security.c
@@ -0,0 +1,750 @@
+/*
+ * Copyright (c) 2016 Mellanox Technologies Ltd.  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 <linux/security.h>
+#include <linux/completion.h>
+#include <linux/list.h>
+
+#include <rdma/ib_verbs.h>
+#include <rdma/ib_cache.h>
+#include "core_priv.h"
+#include "mad_priv.h"
+
+static LIST_HEAD(mad_agent_list);
+/* Lock to protect mad_agent_list */
+static DEFINE_SPINLOCK(mad_agent_list_lock);
+
+static struct pkey_index_qp_list *get_pkey_idx_qp_list(struct ib_port_pkey *pp)
+{
+	struct pkey_index_qp_list *pkey = NULL;
+	struct pkey_index_qp_list *tmp_pkey;
+	struct ib_device *dev = pp->sec->dev;
+
+	spin_lock(&dev->port_data[pp->port_num].pkey_list_lock);
+	list_for_each_entry (tmp_pkey, &dev->port_data[pp->port_num].pkey_list,
+			     pkey_index_list) {
+		if (tmp_pkey->pkey_index == pp->pkey_index) {
+			pkey = tmp_pkey;
+			break;
+		}
+	}
+	spin_unlock(&dev->port_data[pp->port_num].pkey_list_lock);
+	return pkey;
+}
+
+static int get_pkey_and_subnet_prefix(struct ib_port_pkey *pp,
+				      u16 *pkey,
+				      u64 *subnet_prefix)
+{
+	struct ib_device *dev = pp->sec->dev;
+	int ret;
+
+	ret = ib_get_cached_pkey(dev, pp->port_num, pp->pkey_index, pkey);
+	if (ret)
+		return ret;
+
+	ib_get_cached_subnet_prefix(dev, pp->port_num, subnet_prefix);
+
+	return ret;
+}
+
+static int enforce_qp_pkey_security(u16 pkey,
+				    u64 subnet_prefix,
+				    struct ib_qp_security *qp_sec)
+{
+	struct ib_qp_security *shared_qp_sec;
+	int ret;
+
+	ret = security_ib_pkey_access(qp_sec->security, subnet_prefix, pkey);
+	if (ret)
+		return ret;
+
+	list_for_each_entry(shared_qp_sec,
+			    &qp_sec->shared_qp_list,
+			    shared_qp_list) {
+		ret = security_ib_pkey_access(shared_qp_sec->security,
+					      subnet_prefix,
+					      pkey);
+		if (ret)
+			return ret;
+	}
+	return 0;
+}
+
+/* The caller of this function must hold the QP security
+ * mutex of the QP of the security structure in *pps.
+ *
+ * It takes separate ports_pkeys and security structure
+ * because in some cases the pps will be for a new settings
+ * or the pps will be for the real QP and security structure
+ * will be for a shared QP.
+ */
+static int check_qp_port_pkey_settings(struct ib_ports_pkeys *pps,
+				       struct ib_qp_security *sec)
+{
+	u64 subnet_prefix;
+	u16 pkey;
+	int ret = 0;
+
+	if (!pps)
+		return 0;
+
+	if (pps->main.state != IB_PORT_PKEY_NOT_VALID) {
+		ret = get_pkey_and_subnet_prefix(&pps->main,
+						 &pkey,
+						 &subnet_prefix);
+		if (ret)
+			return ret;
+
+		ret = enforce_qp_pkey_security(pkey,
+					       subnet_prefix,
+					       sec);
+		if (ret)
+			return ret;
+	}
+
+	if (pps->alt.state != IB_PORT_PKEY_NOT_VALID) {
+		ret = get_pkey_and_subnet_prefix(&pps->alt,
+						 &pkey,
+						 &subnet_prefix);
+		if (ret)
+			return ret;
+
+		ret = enforce_qp_pkey_security(pkey,
+					       subnet_prefix,
+					       sec);
+	}
+
+	return ret;
+}
+
+/* The caller of this function must hold the QP security
+ * mutex.
+ */
+static void qp_to_error(struct ib_qp_security *sec)
+{
+	struct ib_qp_security *shared_qp_sec;
+	struct ib_qp_attr attr = {
+		.qp_state = IB_QPS_ERR
+	};
+	struct ib_event event = {
+		.event = IB_EVENT_QP_FATAL
+	};
+
+	/* If the QP is in the process of being destroyed
+	 * the qp pointer in the security structure is
+	 * undefined.  It cannot be modified now.
+	 */
+	if (sec->destroying)
+		return;
+
+	ib_modify_qp(sec->qp,
+		     &attr,
+		     IB_QP_STATE);
+
+	if (sec->qp->event_handler && sec->qp->qp_context) {
+		event.element.qp = sec->qp;
+		sec->qp->event_handler(&event,
+				       sec->qp->qp_context);
+	}
+
+	list_for_each_entry(shared_qp_sec,
+			    &sec->shared_qp_list,
+			    shared_qp_list) {
+		struct ib_qp *qp = shared_qp_sec->qp;
+
+		if (qp->event_handler && qp->qp_context) {
+			event.element.qp = qp;
+			event.device = qp->device;
+			qp->event_handler(&event,
+					  qp->qp_context);
+		}
+	}
+}
+
+static inline void check_pkey_qps(struct pkey_index_qp_list *pkey,
+				  struct ib_device *device,
+				  u32 port_num,
+				  u64 subnet_prefix)
+{
+	struct ib_port_pkey *pp, *tmp_pp;
+	bool comp;
+	LIST_HEAD(to_error_list);
+	u16 pkey_val;
+
+	if (!ib_get_cached_pkey(device,
+				port_num,
+				pkey->pkey_index,
+				&pkey_val)) {
+		spin_lock(&pkey->qp_list_lock);
+		list_for_each_entry(pp, &pkey->qp_list, qp_list) {
+			if (atomic_read(&pp->sec->error_list_count))
+				continue;
+
+			if (enforce_qp_pkey_security(pkey_val,
+						     subnet_prefix,
+						     pp->sec)) {
+				atomic_inc(&pp->sec->error_list_count);
+				list_add(&pp->to_error_list,
+					 &to_error_list);
+			}
+		}
+		spin_unlock(&pkey->qp_list_lock);
+	}
+
+	list_for_each_entry_safe(pp,
+				 tmp_pp,
+				 &to_error_list,
+				 to_error_list) {
+		mutex_lock(&pp->sec->mutex);
+		qp_to_error(pp->sec);
+		list_del(&pp->to_error_list);
+		atomic_dec(&pp->sec->error_list_count);
+		comp = pp->sec->destroying;
+		mutex_unlock(&pp->sec->mutex);
+
+		if (comp)
+			complete(&pp->sec->error_complete);
+	}
+}
+
+/* The caller of this function must hold the QP security
+ * mutex.
+ */
+static int port_pkey_list_insert(struct ib_port_pkey *pp)
+{
+	struct pkey_index_qp_list *tmp_pkey;
+	struct pkey_index_qp_list *pkey;
+	struct ib_device *dev;
+	u32 port_num = pp->port_num;
+	int ret = 0;
+
+	if (pp->state != IB_PORT_PKEY_VALID)
+		return 0;
+
+	dev = pp->sec->dev;
+
+	pkey = get_pkey_idx_qp_list(pp);
+
+	if (!pkey) {
+		bool found = false;
+
+		pkey = kzalloc(sizeof(*pkey), GFP_KERNEL);
+		if (!pkey)
+			return -ENOMEM;
+
+		spin_lock(&dev->port_data[port_num].pkey_list_lock);
+		/* Check for the PKey again.  A racing process may
+		 * have created it.
+		 */
+		list_for_each_entry(tmp_pkey,
+				    &dev->port_data[port_num].pkey_list,
+				    pkey_index_list) {
+			if (tmp_pkey->pkey_index == pp->pkey_index) {
+				kfree(pkey);
+				pkey = tmp_pkey;
+				found = true;
+				break;
+			}
+		}
+
+		if (!found) {
+			pkey->pkey_index = pp->pkey_index;
+			spin_lock_init(&pkey->qp_list_lock);
+			INIT_LIST_HEAD(&pkey->qp_list);
+			list_add(&pkey->pkey_index_list,
+				 &dev->port_data[port_num].pkey_list);
+		}
+		spin_unlock(&dev->port_data[port_num].pkey_list_lock);
+	}
+
+	spin_lock(&pkey->qp_list_lock);
+	list_add(&pp->qp_list, &pkey->qp_list);
+	spin_unlock(&pkey->qp_list_lock);
+
+	pp->state = IB_PORT_PKEY_LISTED;
+
+	return ret;
+}
+
+/* The caller of this function must hold the QP security
+ * mutex.
+ */
+static void port_pkey_list_remove(struct ib_port_pkey *pp)
+{
+	struct pkey_index_qp_list *pkey;
+
+	if (pp->state != IB_PORT_PKEY_LISTED)
+		return;
+
+	pkey = get_pkey_idx_qp_list(pp);
+
+	spin_lock(&pkey->qp_list_lock);
+	list_del(&pp->qp_list);
+	spin_unlock(&pkey->qp_list_lock);
+
+	/* The setting may still be valid, i.e. after
+	 * a destroy has failed for example.
+	 */
+	pp->state = IB_PORT_PKEY_VALID;
+}
+
+static void destroy_qp_security(struct ib_qp_security *sec)
+{
+	security_ib_free_security(sec->security);
+	kfree(sec->ports_pkeys);
+	kfree(sec);
+}
+
+/* The caller of this function must hold the QP security
+ * mutex.
+ */
+static struct ib_ports_pkeys *get_new_pps(const struct ib_qp *qp,
+					  const struct ib_qp_attr *qp_attr,
+					  int qp_attr_mask)
+{
+	struct ib_ports_pkeys *new_pps;
+	struct ib_ports_pkeys *qp_pps = qp->qp_sec->ports_pkeys;
+
+	new_pps = kzalloc(sizeof(*new_pps), GFP_KERNEL);
+	if (!new_pps)
+		return NULL;
+
+	if (qp_attr_mask & IB_QP_PORT)
+		new_pps->main.port_num = qp_attr->port_num;
+	else if (qp_pps)
+		new_pps->main.port_num = qp_pps->main.port_num;
+
+	if (qp_attr_mask & IB_QP_PKEY_INDEX)
+		new_pps->main.pkey_index = qp_attr->pkey_index;
+	else if (qp_pps)
+		new_pps->main.pkey_index = qp_pps->main.pkey_index;
+
+	if (((qp_attr_mask & IB_QP_PKEY_INDEX) &&
+	     (qp_attr_mask & IB_QP_PORT)) ||
+	    (qp_pps && qp_pps->main.state != IB_PORT_PKEY_NOT_VALID))
+		new_pps->main.state = IB_PORT_PKEY_VALID;
+
+	if (qp_attr_mask & IB_QP_ALT_PATH) {
+		new_pps->alt.port_num = qp_attr->alt_port_num;
+		new_pps->alt.pkey_index = qp_attr->alt_pkey_index;
+		new_pps->alt.state = IB_PORT_PKEY_VALID;
+	} else if (qp_pps) {
+		new_pps->alt.port_num = qp_pps->alt.port_num;
+		new_pps->alt.pkey_index = qp_pps->alt.pkey_index;
+		if (qp_pps->alt.state != IB_PORT_PKEY_NOT_VALID)
+			new_pps->alt.state = IB_PORT_PKEY_VALID;
+	}
+
+	new_pps->main.sec = qp->qp_sec;
+	new_pps->alt.sec = qp->qp_sec;
+	return new_pps;
+}
+
+int ib_open_shared_qp_security(struct ib_qp *qp, struct ib_device *dev)
+{
+	struct ib_qp *real_qp = qp->real_qp;
+	int ret;
+
+	ret = ib_create_qp_security(qp, dev);
+
+	if (ret)
+		return ret;
+
+	if (!qp->qp_sec)
+		return 0;
+
+	mutex_lock(&real_qp->qp_sec->mutex);
+	ret = check_qp_port_pkey_settings(real_qp->qp_sec->ports_pkeys,
+					  qp->qp_sec);
+
+	if (ret)
+		goto ret;
+
+	if (qp != real_qp)
+		list_add(&qp->qp_sec->shared_qp_list,
+			 &real_qp->qp_sec->shared_qp_list);
+ret:
+	mutex_unlock(&real_qp->qp_sec->mutex);
+	if (ret)
+		destroy_qp_security(qp->qp_sec);
+
+	return ret;
+}
+
+void ib_close_shared_qp_security(struct ib_qp_security *sec)
+{
+	struct ib_qp *real_qp = sec->qp->real_qp;
+
+	mutex_lock(&real_qp->qp_sec->mutex);
+	list_del(&sec->shared_qp_list);
+	mutex_unlock(&real_qp->qp_sec->mutex);
+
+	destroy_qp_security(sec);
+}
+
+int ib_create_qp_security(struct ib_qp *qp, struct ib_device *dev)
+{
+	unsigned int i;
+	bool is_ib = false;
+	int ret;
+
+	rdma_for_each_port (dev, i) {
+		is_ib = rdma_protocol_ib(dev, i);
+		if (is_ib)
+			break;
+	}
+
+	/* If this isn't an IB device don't create the security context */
+	if (!is_ib)
+		return 0;
+
+	qp->qp_sec = kzalloc(sizeof(*qp->qp_sec), GFP_KERNEL);
+	if (!qp->qp_sec)
+		return -ENOMEM;
+
+	qp->qp_sec->qp = qp;
+	qp->qp_sec->dev = dev;
+	mutex_init(&qp->qp_sec->mutex);
+	INIT_LIST_HEAD(&qp->qp_sec->shared_qp_list);
+	atomic_set(&qp->qp_sec->error_list_count, 0);
+	init_completion(&qp->qp_sec->error_complete);
+	ret = security_ib_alloc_security(&qp->qp_sec->security);
+	if (ret) {
+		kfree(qp->qp_sec);
+		qp->qp_sec = NULL;
+	}
+
+	return ret;
+}
+EXPORT_SYMBOL(ib_create_qp_security);
+
+void ib_destroy_qp_security_begin(struct ib_qp_security *sec)
+{
+	/* Return if not IB */
+	if (!sec)
+		return;
+
+	mutex_lock(&sec->mutex);
+
+	/* Remove the QP from the lists so it won't get added to
+	 * a to_error_list during the destroy process.
+	 */
+	if (sec->ports_pkeys) {
+		port_pkey_list_remove(&sec->ports_pkeys->main);
+		port_pkey_list_remove(&sec->ports_pkeys->alt);
+	}
+
+	/* If the QP is already in one or more of those lists
+	 * the destroying flag will ensure the to error flow
+	 * doesn't operate on an undefined QP.
+	 */
+	sec->destroying = true;
+
+	/* Record the error list count to know how many completions
+	 * to wait for.
+	 */
+	sec->error_comps_pending = atomic_read(&sec->error_list_count);
+
+	mutex_unlock(&sec->mutex);
+}
+
+void ib_destroy_qp_security_abort(struct ib_qp_security *sec)
+{
+	int ret;
+	int i;
+
+	/* Return if not IB */
+	if (!sec)
+		return;
+
+	/* If a concurrent cache update is in progress this
+	 * QP security could be marked for an error state
+	 * transition.  Wait for this to complete.
+	 */
+	for (i = 0; i < sec->error_comps_pending; i++)
+		wait_for_completion(&sec->error_complete);
+
+	mutex_lock(&sec->mutex);
+	sec->destroying = false;
+
+	/* Restore the position in the lists and verify
+	 * access is still allowed in case a cache update
+	 * occurred while attempting to destroy.
+	 *
+	 * Because these setting were listed already
+	 * and removed during ib_destroy_qp_security_begin
+	 * we know the pkey_index_qp_list for the PKey
+	 * already exists so port_pkey_list_insert won't fail.
+	 */
+	if (sec->ports_pkeys) {
+		port_pkey_list_insert(&sec->ports_pkeys->main);
+		port_pkey_list_insert(&sec->ports_pkeys->alt);
+	}
+
+	ret = check_qp_port_pkey_settings(sec->ports_pkeys, sec);
+	if (ret)
+		qp_to_error(sec);
+
+	mutex_unlock(&sec->mutex);
+}
+
+void ib_destroy_qp_security_end(struct ib_qp_security *sec)
+{
+	int i;
+
+	/* Return if not IB */
+	if (!sec)
+		return;
+
+	/* If a concurrent cache update is occurring we must
+	 * wait until this QP security structure is processed
+	 * in the QP to error flow before destroying it because
+	 * the to_error_list is in use.
+	 */
+	for (i = 0; i < sec->error_comps_pending; i++)
+		wait_for_completion(&sec->error_complete);
+
+	destroy_qp_security(sec);
+}
+
+void ib_security_cache_change(struct ib_device *device,
+			      u32 port_num,
+			      u64 subnet_prefix)
+{
+	struct pkey_index_qp_list *pkey;
+
+	list_for_each_entry (pkey, &device->port_data[port_num].pkey_list,
+			     pkey_index_list) {
+		check_pkey_qps(pkey,
+			       device,
+			       port_num,
+			       subnet_prefix);
+	}
+}
+
+void ib_security_release_port_pkey_list(struct ib_device *device)
+{
+	struct pkey_index_qp_list *pkey, *tmp_pkey;
+	unsigned int i;
+
+	rdma_for_each_port (device, i) {
+		list_for_each_entry_safe(pkey,
+					 tmp_pkey,
+					 &device->port_data[i].pkey_list,
+					 pkey_index_list) {
+			list_del(&pkey->pkey_index_list);
+			kfree(pkey);
+		}
+	}
+}
+
+int ib_security_modify_qp(struct ib_qp *qp,
+			  struct ib_qp_attr *qp_attr,
+			  int qp_attr_mask,
+			  struct ib_udata *udata)
+{
+	int ret = 0;
+	struct ib_ports_pkeys *tmp_pps;
+	struct ib_ports_pkeys *new_pps = NULL;
+	struct ib_qp *real_qp = qp->real_qp;
+	bool special_qp = (real_qp->qp_type == IB_QPT_SMI ||
+			   real_qp->qp_type == IB_QPT_GSI ||
+			   real_qp->qp_type >= IB_QPT_RESERVED1);
+	bool pps_change = ((qp_attr_mask & (IB_QP_PKEY_INDEX | IB_QP_PORT)) ||
+			   (qp_attr_mask & IB_QP_ALT_PATH));
+
+	WARN_ONCE((qp_attr_mask & IB_QP_PORT &&
+		   rdma_protocol_ib(real_qp->device, qp_attr->port_num) &&
+		   !real_qp->qp_sec),
+		   "%s: QP security is not initialized for IB QP: %u\n",
+		   __func__, real_qp->qp_num);
+
+	/* The port/pkey settings are maintained only for the real QP. Open
+	 * handles on the real QP will be in the shared_qp_list. When
+	 * enforcing security on the real QP all the shared QPs will be
+	 * checked as well.
+	 */
+
+	if (pps_change && !special_qp && real_qp->qp_sec) {
+		mutex_lock(&real_qp->qp_sec->mutex);
+		new_pps = get_new_pps(real_qp,
+				      qp_attr,
+				      qp_attr_mask);
+		if (!new_pps) {
+			mutex_unlock(&real_qp->qp_sec->mutex);
+			return -ENOMEM;
+		}
+		/* Add this QP to the lists for the new port
+		 * and pkey settings before checking for permission
+		 * in case there is a concurrent cache update
+		 * occurring.  Walking the list for a cache change
+		 * doesn't acquire the security mutex unless it's
+		 * sending the QP to error.
+		 */
+		ret = port_pkey_list_insert(&new_pps->main);
+
+		if (!ret)
+			ret = port_pkey_list_insert(&new_pps->alt);
+
+		if (!ret)
+			ret = check_qp_port_pkey_settings(new_pps,
+							  real_qp->qp_sec);
+	}
+
+	if (!ret)
+		ret = real_qp->device->ops.modify_qp(real_qp,
+						     qp_attr,
+						     qp_attr_mask,
+						     udata);
+
+	if (new_pps) {
+		/* Clean up the lists and free the appropriate
+		 * ports_pkeys structure.
+		 */
+		if (ret) {
+			tmp_pps = new_pps;
+		} else {
+			tmp_pps = real_qp->qp_sec->ports_pkeys;
+			real_qp->qp_sec->ports_pkeys = new_pps;
+		}
+
+		if (tmp_pps) {
+			port_pkey_list_remove(&tmp_pps->main);
+			port_pkey_list_remove(&tmp_pps->alt);
+		}
+		kfree(tmp_pps);
+		mutex_unlock(&real_qp->qp_sec->mutex);
+	}
+	return ret;
+}
+
+static int ib_security_pkey_access(struct ib_device *dev,
+				   u32 port_num,
+				   u16 pkey_index,
+				   void *sec)
+{
+	u64 subnet_prefix;
+	u16 pkey;
+	int ret;
+
+	if (!rdma_protocol_ib(dev, port_num))
+		return 0;
+
+	ret = ib_get_cached_pkey(dev, port_num, pkey_index, &pkey);
+	if (ret)
+		return ret;
+
+	ib_get_cached_subnet_prefix(dev, port_num, &subnet_prefix);
+
+	return security_ib_pkey_access(sec, subnet_prefix, pkey);
+}
+
+void ib_mad_agent_security_change(void)
+{
+	struct ib_mad_agent *ag;
+
+	spin_lock(&mad_agent_list_lock);
+	list_for_each_entry(ag,
+			    &mad_agent_list,
+			    mad_agent_sec_list)
+		WRITE_ONCE(ag->smp_allowed,
+			   !security_ib_endport_manage_subnet(ag->security,
+				dev_name(&ag->device->dev), ag->port_num));
+	spin_unlock(&mad_agent_list_lock);
+}
+
+int ib_mad_agent_security_setup(struct ib_mad_agent *agent,
+				enum ib_qp_type qp_type)
+{
+	int ret;
+
+	if (!rdma_protocol_ib(agent->device, agent->port_num))
+		return 0;
+
+	INIT_LIST_HEAD(&agent->mad_agent_sec_list);
+
+	ret = security_ib_alloc_security(&agent->security);
+	if (ret)
+		return ret;
+
+	if (qp_type != IB_QPT_SMI)
+		return 0;
+
+	spin_lock(&mad_agent_list_lock);
+	ret = security_ib_endport_manage_subnet(agent->security,
+						dev_name(&agent->device->dev),
+						agent->port_num);
+	if (ret)
+		goto free_security;
+
+	WRITE_ONCE(agent->smp_allowed, true);
+	list_add(&agent->mad_agent_sec_list, &mad_agent_list);
+	spin_unlock(&mad_agent_list_lock);
+	return 0;
+
+free_security:
+	spin_unlock(&mad_agent_list_lock);
+	security_ib_free_security(agent->security);
+	return ret;
+}
+
+void ib_mad_agent_security_cleanup(struct ib_mad_agent *agent)
+{
+	if (!rdma_protocol_ib(agent->device, agent->port_num))
+		return;
+
+	if (agent->qp->qp_type == IB_QPT_SMI) {
+		spin_lock(&mad_agent_list_lock);
+		list_del(&agent->mad_agent_sec_list);
+		spin_unlock(&mad_agent_list_lock);
+	}
+
+	security_ib_free_security(agent->security);
+}
+
+int ib_mad_enforce_security(struct ib_mad_agent_private *map, u16 pkey_index)
+{
+	if (!rdma_protocol_ib(map->agent.device, map->agent.port_num))
+		return 0;
+
+	if (map->agent.qp->qp_type == IB_QPT_SMI) {
+		if (!READ_ONCE(map->agent.smp_allowed))
+			return -EACCES;
+		return 0;
+	}
+
+	return ib_security_pkey_access(map->agent.device,
+				       map->agent.port_num,
+				       pkey_index,
+				       map->agent.security);
+}