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, 749 insertions, 0 deletions

diff --git a/drivers/acpi/nfit/intel.c b/drivers/acpi/nfit/intel.c
new file mode 100644
index 000000000..3902759ab
--- /dev/null
+++ b/drivers/acpi/nfit/intel.c
@@ -0,0 +1,749 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright(c) 2018 Intel Corporation. All rights reserved. */
+#include <linux/libnvdimm.h>
+#include <linux/ndctl.h>
+#include <linux/acpi.h>
+#include <linux/memregion.h>
+#include <asm/smp.h>
+#include "intel.h"
+#include "nfit.h"
+
+static ssize_t firmware_activate_noidle_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	struct nvdimm_bus *nvdimm_bus = to_nvdimm_bus(dev);
+	struct nvdimm_bus_descriptor *nd_desc = to_nd_desc(nvdimm_bus);
+	struct acpi_nfit_desc *acpi_desc = to_acpi_desc(nd_desc);
+
+	return sprintf(buf, "%s\n", acpi_desc->fwa_noidle ? "Y" : "N");
+}
+
+static ssize_t firmware_activate_noidle_store(struct device *dev,
+		struct device_attribute *attr, const char *buf, size_t size)
+{
+	struct nvdimm_bus *nvdimm_bus = to_nvdimm_bus(dev);
+	struct nvdimm_bus_descriptor *nd_desc = to_nd_desc(nvdimm_bus);
+	struct acpi_nfit_desc *acpi_desc = to_acpi_desc(nd_desc);
+	ssize_t rc;
+	bool val;
+
+	rc = kstrtobool(buf, &val);
+	if (rc)
+		return rc;
+	if (val != acpi_desc->fwa_noidle)
+		acpi_desc->fwa_cap = NVDIMM_FWA_CAP_INVALID;
+	acpi_desc->fwa_noidle = val;
+	return size;
+}
+DEVICE_ATTR_RW(firmware_activate_noidle);
+
+bool intel_fwa_supported(struct nvdimm_bus *nvdimm_bus)
+{
+	struct nvdimm_bus_descriptor *nd_desc = to_nd_desc(nvdimm_bus);
+	struct acpi_nfit_desc *acpi_desc = to_acpi_desc(nd_desc);
+	unsigned long *mask;
+
+	if (!test_bit(NVDIMM_BUS_FAMILY_INTEL, &nd_desc->bus_family_mask))
+		return false;
+
+	mask = &acpi_desc->family_dsm_mask[NVDIMM_BUS_FAMILY_INTEL];
+	return *mask == NVDIMM_BUS_INTEL_FW_ACTIVATE_CMDMASK;
+}
+
+static unsigned long intel_security_flags(struct nvdimm *nvdimm,
+		enum nvdimm_passphrase_type ptype)
+{
+	struct nfit_mem *nfit_mem = nvdimm_provider_data(nvdimm);
+	unsigned long security_flags = 0;
+	struct {
+		struct nd_cmd_pkg pkg;
+		struct nd_intel_get_security_state cmd;
+	} nd_cmd = {
+		.pkg = {
+			.nd_command = NVDIMM_INTEL_GET_SECURITY_STATE,
+			.nd_family = NVDIMM_FAMILY_INTEL,
+			.nd_size_out =
+				sizeof(struct nd_intel_get_security_state),
+			.nd_fw_size =
+				sizeof(struct nd_intel_get_security_state),
+		},
+	};
+	int rc;
+
+	if (!test_bit(NVDIMM_INTEL_GET_SECURITY_STATE, &nfit_mem->dsm_mask))
+		return 0;
+
+	/*
+	 * Short circuit the state retrieval while we are doing overwrite.
+	 * The DSM spec states that the security state is indeterminate
+	 * until the overwrite DSM completes.
+	 */
+	if (nvdimm_in_overwrite(nvdimm) && ptype == NVDIMM_USER)
+		return BIT(NVDIMM_SECURITY_OVERWRITE);
+
+	rc = nvdimm_ctl(nvdimm, ND_CMD_CALL, &nd_cmd, sizeof(nd_cmd), NULL);
+	if (rc < 0 || nd_cmd.cmd.status) {
+		pr_err("%s: security state retrieval failed (%d:%#x)\n",
+				nvdimm_name(nvdimm), rc, nd_cmd.cmd.status);
+		return 0;
+	}
+
+	/* check and see if security is enabled and locked */
+	if (ptype == NVDIMM_MASTER) {
+		if (nd_cmd.cmd.extended_state & ND_INTEL_SEC_ESTATE_ENABLED)
+			set_bit(NVDIMM_SECURITY_UNLOCKED, &security_flags);
+		else
+			set_bit(NVDIMM_SECURITY_DISABLED, &security_flags);
+		if (nd_cmd.cmd.extended_state & ND_INTEL_SEC_ESTATE_PLIMIT)
+			set_bit(NVDIMM_SECURITY_FROZEN, &security_flags);
+		return security_flags;
+	}
+
+	if (nd_cmd.cmd.state & ND_INTEL_SEC_STATE_UNSUPPORTED)
+		return 0;
+
+	if (nd_cmd.cmd.state & ND_INTEL_SEC_STATE_ENABLED) {
+		if (nd_cmd.cmd.state & ND_INTEL_SEC_STATE_FROZEN ||
+		    nd_cmd.cmd.state & ND_INTEL_SEC_STATE_PLIMIT)
+			set_bit(NVDIMM_SECURITY_FROZEN, &security_flags);
+
+		if (nd_cmd.cmd.state & ND_INTEL_SEC_STATE_LOCKED)
+			set_bit(NVDIMM_SECURITY_LOCKED, &security_flags);
+		else
+			set_bit(NVDIMM_SECURITY_UNLOCKED, &security_flags);
+	} else
+		set_bit(NVDIMM_SECURITY_DISABLED, &security_flags);
+
+	return security_flags;
+}
+
+static int intel_security_freeze(struct nvdimm *nvdimm)
+{
+	struct nfit_mem *nfit_mem = nvdimm_provider_data(nvdimm);
+	struct {
+		struct nd_cmd_pkg pkg;
+		struct nd_intel_freeze_lock cmd;
+	} nd_cmd = {
+		.pkg = {
+			.nd_command = NVDIMM_INTEL_FREEZE_LOCK,
+			.nd_family = NVDIMM_FAMILY_INTEL,
+			.nd_size_out = ND_INTEL_STATUS_SIZE,
+			.nd_fw_size = ND_INTEL_STATUS_SIZE,
+		},
+	};
+	int rc;
+
+	if (!test_bit(NVDIMM_INTEL_FREEZE_LOCK, &nfit_mem->dsm_mask))
+		return -ENOTTY;
+
+	rc = nvdimm_ctl(nvdimm, ND_CMD_CALL, &nd_cmd, sizeof(nd_cmd), NULL);
+	if (rc < 0)
+		return rc;
+	if (nd_cmd.cmd.status)
+		return -EIO;
+	return 0;
+}
+
+static int intel_security_change_key(struct nvdimm *nvdimm,
+		const struct nvdimm_key_data *old_data,
+		const struct nvdimm_key_data *new_data,
+		enum nvdimm_passphrase_type ptype)
+{
+	struct nfit_mem *nfit_mem = nvdimm_provider_data(nvdimm);
+	unsigned int cmd = ptype == NVDIMM_MASTER ?
+		NVDIMM_INTEL_SET_MASTER_PASSPHRASE :
+		NVDIMM_INTEL_SET_PASSPHRASE;
+	struct {
+		struct nd_cmd_pkg pkg;
+		struct nd_intel_set_passphrase cmd;
+	} nd_cmd = {
+		.pkg = {
+			.nd_family = NVDIMM_FAMILY_INTEL,
+			.nd_size_in = ND_INTEL_PASSPHRASE_SIZE * 2,
+			.nd_size_out = ND_INTEL_STATUS_SIZE,
+			.nd_fw_size = ND_INTEL_STATUS_SIZE,
+			.nd_command = cmd,
+		},
+	};
+	int rc;
+
+	if (!test_bit(cmd, &nfit_mem->dsm_mask))
+		return -ENOTTY;
+
+	memcpy(nd_cmd.cmd.old_pass, old_data->data,
+			sizeof(nd_cmd.cmd.old_pass));
+	memcpy(nd_cmd.cmd.new_pass, new_data->data,
+			sizeof(nd_cmd.cmd.new_pass));
+	rc = nvdimm_ctl(nvdimm, ND_CMD_CALL, &nd_cmd, sizeof(nd_cmd), NULL);
+	if (rc < 0)
+		return rc;
+
+	switch (nd_cmd.cmd.status) {
+	case 0:
+		return 0;
+	case ND_INTEL_STATUS_INVALID_PASS:
+		return -EINVAL;
+	case ND_INTEL_STATUS_NOT_SUPPORTED:
+		return -EOPNOTSUPP;
+	case ND_INTEL_STATUS_INVALID_STATE:
+	default:
+		return -EIO;
+	}
+}
+
+static int __maybe_unused intel_security_unlock(struct nvdimm *nvdimm,
+		const struct nvdimm_key_data *key_data)
+{
+	struct nfit_mem *nfit_mem = nvdimm_provider_data(nvdimm);
+	struct {
+		struct nd_cmd_pkg pkg;
+		struct nd_intel_unlock_unit cmd;
+	} nd_cmd = {
+		.pkg = {
+			.nd_command = NVDIMM_INTEL_UNLOCK_UNIT,
+			.nd_family = NVDIMM_FAMILY_INTEL,
+			.nd_size_in = ND_INTEL_PASSPHRASE_SIZE,
+			.nd_size_out = ND_INTEL_STATUS_SIZE,
+			.nd_fw_size = ND_INTEL_STATUS_SIZE,
+		},
+	};
+	int rc;
+
+	if (!test_bit(NVDIMM_INTEL_UNLOCK_UNIT, &nfit_mem->dsm_mask))
+		return -ENOTTY;
+
+	memcpy(nd_cmd.cmd.passphrase, key_data->data,
+			sizeof(nd_cmd.cmd.passphrase));
+	rc = nvdimm_ctl(nvdimm, ND_CMD_CALL, &nd_cmd, sizeof(nd_cmd), NULL);
+	if (rc < 0)
+		return rc;
+	switch (nd_cmd.cmd.status) {
+	case 0:
+		break;
+	case ND_INTEL_STATUS_INVALID_PASS:
+		return -EINVAL;
+	default:
+		return -EIO;
+	}
+
+	return 0;
+}
+
+static int intel_security_disable(struct nvdimm *nvdimm,
+		const struct nvdimm_key_data *key_data)
+{
+	int rc;
+	struct nfit_mem *nfit_mem = nvdimm_provider_data(nvdimm);
+	struct {
+		struct nd_cmd_pkg pkg;
+		struct nd_intel_disable_passphrase cmd;
+	} nd_cmd = {
+		.pkg = {
+			.nd_command = NVDIMM_INTEL_DISABLE_PASSPHRASE,
+			.nd_family = NVDIMM_FAMILY_INTEL,
+			.nd_size_in = ND_INTEL_PASSPHRASE_SIZE,
+			.nd_size_out = ND_INTEL_STATUS_SIZE,
+			.nd_fw_size = ND_INTEL_STATUS_SIZE,
+		},
+	};
+
+	if (!test_bit(NVDIMM_INTEL_DISABLE_PASSPHRASE, &nfit_mem->dsm_mask))
+		return -ENOTTY;
+
+	memcpy(nd_cmd.cmd.passphrase, key_data->data,
+			sizeof(nd_cmd.cmd.passphrase));
+	rc = nvdimm_ctl(nvdimm, ND_CMD_CALL, &nd_cmd, sizeof(nd_cmd), NULL);
+	if (rc < 0)
+		return rc;
+
+	switch (nd_cmd.cmd.status) {
+	case 0:
+		break;
+	case ND_INTEL_STATUS_INVALID_PASS:
+		return -EINVAL;
+	case ND_INTEL_STATUS_INVALID_STATE:
+	default:
+		return -ENXIO;
+	}
+
+	return 0;
+}
+
+static int __maybe_unused intel_security_erase(struct nvdimm *nvdimm,
+		const struct nvdimm_key_data *key,
+		enum nvdimm_passphrase_type ptype)
+{
+	int rc;
+	struct nfit_mem *nfit_mem = nvdimm_provider_data(nvdimm);
+	unsigned int cmd = ptype == NVDIMM_MASTER ?
+		NVDIMM_INTEL_MASTER_SECURE_ERASE : NVDIMM_INTEL_SECURE_ERASE;
+	struct {
+		struct nd_cmd_pkg pkg;
+		struct nd_intel_secure_erase cmd;
+	} nd_cmd = {
+		.pkg = {
+			.nd_family = NVDIMM_FAMILY_INTEL,
+			.nd_size_in = ND_INTEL_PASSPHRASE_SIZE,
+			.nd_size_out = ND_INTEL_STATUS_SIZE,
+			.nd_fw_size = ND_INTEL_STATUS_SIZE,
+			.nd_command = cmd,
+		},
+	};
+
+	if (!test_bit(cmd, &nfit_mem->dsm_mask))
+		return -ENOTTY;
+
+	memcpy(nd_cmd.cmd.passphrase, key->data,
+			sizeof(nd_cmd.cmd.passphrase));
+	rc = nvdimm_ctl(nvdimm, ND_CMD_CALL, &nd_cmd, sizeof(nd_cmd), NULL);
+	if (rc < 0)
+		return rc;
+
+	switch (nd_cmd.cmd.status) {
+	case 0:
+		break;
+	case ND_INTEL_STATUS_NOT_SUPPORTED:
+		return -EOPNOTSUPP;
+	case ND_INTEL_STATUS_INVALID_PASS:
+		return -EINVAL;
+	case ND_INTEL_STATUS_INVALID_STATE:
+	default:
+		return -ENXIO;
+	}
+
+	return 0;
+}
+
+static int __maybe_unused intel_security_query_overwrite(struct nvdimm *nvdimm)
+{
+	int rc;
+	struct nfit_mem *nfit_mem = nvdimm_provider_data(nvdimm);
+	struct {
+		struct nd_cmd_pkg pkg;
+		struct nd_intel_query_overwrite cmd;
+	} nd_cmd = {
+		.pkg = {
+			.nd_command = NVDIMM_INTEL_QUERY_OVERWRITE,
+			.nd_family = NVDIMM_FAMILY_INTEL,
+			.nd_size_out = ND_INTEL_STATUS_SIZE,
+			.nd_fw_size = ND_INTEL_STATUS_SIZE,
+		},
+	};
+
+	if (!test_bit(NVDIMM_INTEL_QUERY_OVERWRITE, &nfit_mem->dsm_mask))
+		return -ENOTTY;
+
+	rc = nvdimm_ctl(nvdimm, ND_CMD_CALL, &nd_cmd, sizeof(nd_cmd), NULL);
+	if (rc < 0)
+		return rc;
+
+	switch (nd_cmd.cmd.status) {
+	case 0:
+		break;
+	case ND_INTEL_STATUS_OQUERY_INPROGRESS:
+		return -EBUSY;
+	default:
+		return -ENXIO;
+	}
+
+	return 0;
+}
+
+static int __maybe_unused intel_security_overwrite(struct nvdimm *nvdimm,
+		const struct nvdimm_key_data *nkey)
+{
+	int rc;
+	struct nfit_mem *nfit_mem = nvdimm_provider_data(nvdimm);
+	struct {
+		struct nd_cmd_pkg pkg;
+		struct nd_intel_overwrite cmd;
+	} nd_cmd = {
+		.pkg = {
+			.nd_command = NVDIMM_INTEL_OVERWRITE,
+			.nd_family = NVDIMM_FAMILY_INTEL,
+			.nd_size_in = ND_INTEL_PASSPHRASE_SIZE,
+			.nd_size_out = ND_INTEL_STATUS_SIZE,
+			.nd_fw_size = ND_INTEL_STATUS_SIZE,
+		},
+	};
+
+	if (!test_bit(NVDIMM_INTEL_OVERWRITE, &nfit_mem->dsm_mask))
+		return -ENOTTY;
+
+	memcpy(nd_cmd.cmd.passphrase, nkey->data,
+			sizeof(nd_cmd.cmd.passphrase));
+	rc = nvdimm_ctl(nvdimm, ND_CMD_CALL, &nd_cmd, sizeof(nd_cmd), NULL);
+	if (rc < 0)
+		return rc;
+
+	switch (nd_cmd.cmd.status) {
+	case 0:
+		return 0;
+	case ND_INTEL_STATUS_OVERWRITE_UNSUPPORTED:
+		return -ENOTSUPP;
+	case ND_INTEL_STATUS_INVALID_PASS:
+		return -EINVAL;
+	case ND_INTEL_STATUS_INVALID_STATE:
+	default:
+		return -ENXIO;
+	}
+}
+
+static const struct nvdimm_security_ops __intel_security_ops = {
+	.get_flags = intel_security_flags,
+	.freeze = intel_security_freeze,
+	.change_key = intel_security_change_key,
+	.disable = intel_security_disable,
+#ifdef CONFIG_X86
+	.unlock = intel_security_unlock,
+	.erase = intel_security_erase,
+	.overwrite = intel_security_overwrite,
+	.query_overwrite = intel_security_query_overwrite,
+#endif
+};
+
+const struct nvdimm_security_ops *intel_security_ops = &__intel_security_ops;
+
+static int intel_bus_fwa_businfo(struct nvdimm_bus_descriptor *nd_desc,
+		struct nd_intel_bus_fw_activate_businfo *info)
+{
+	struct {
+		struct nd_cmd_pkg pkg;
+		struct nd_intel_bus_fw_activate_businfo cmd;
+	} nd_cmd = {
+		.pkg = {
+			.nd_command = NVDIMM_BUS_INTEL_FW_ACTIVATE_BUSINFO,
+			.nd_family = NVDIMM_BUS_FAMILY_INTEL,
+			.nd_size_out =
+				sizeof(struct nd_intel_bus_fw_activate_businfo),
+			.nd_fw_size =
+				sizeof(struct nd_intel_bus_fw_activate_businfo),
+		},
+	};
+	int rc;
+
+	rc = nd_desc->ndctl(nd_desc, NULL, ND_CMD_CALL, &nd_cmd, sizeof(nd_cmd),
+			NULL);
+	*info = nd_cmd.cmd;
+	return rc;
+}
+
+/* The fw_ops expect to be called with the nvdimm_bus_lock() held */
+static enum nvdimm_fwa_state intel_bus_fwa_state(
+		struct nvdimm_bus_descriptor *nd_desc)
+{
+	struct acpi_nfit_desc *acpi_desc = to_acpi_desc(nd_desc);
+	struct nd_intel_bus_fw_activate_businfo info;
+	struct device *dev = acpi_desc->dev;
+	enum nvdimm_fwa_state state;
+	int rc;
+
+	/*
+	 * It should not be possible for platform firmware to return
+	 * busy because activate is a synchronous operation. Treat it
+	 * similar to invalid, i.e. always refresh / poll the status.
+	 */
+	switch (acpi_desc->fwa_state) {
+	case NVDIMM_FWA_INVALID:
+	case NVDIMM_FWA_BUSY:
+		break;
+	default:
+		/* check if capability needs to be refreshed */
+		if (acpi_desc->fwa_cap == NVDIMM_FWA_CAP_INVALID)
+			break;
+		return acpi_desc->fwa_state;
+	}
+
+	/* Refresh with platform firmware */
+	rc = intel_bus_fwa_businfo(nd_desc, &info);
+	if (rc)
+		return NVDIMM_FWA_INVALID;
+
+	switch (info.state) {
+	case ND_INTEL_FWA_IDLE:
+		state = NVDIMM_FWA_IDLE;
+		break;
+	case ND_INTEL_FWA_BUSY:
+		state = NVDIMM_FWA_BUSY;
+		break;
+	case ND_INTEL_FWA_ARMED:
+		if (info.activate_tmo > info.max_quiesce_tmo)
+			state = NVDIMM_FWA_ARM_OVERFLOW;
+		else
+			state = NVDIMM_FWA_ARMED;
+		break;
+	default:
+		dev_err_once(dev, "invalid firmware activate state %d\n",
+				info.state);
+		return NVDIMM_FWA_INVALID;
+	}
+
+	/*
+	 * Capability data is available in the same payload as state. It
+	 * is expected to be static.
+	 */
+	if (acpi_desc->fwa_cap == NVDIMM_FWA_CAP_INVALID) {
+		if (info.capability & ND_INTEL_BUS_FWA_CAP_FWQUIESCE)
+			acpi_desc->fwa_cap = NVDIMM_FWA_CAP_QUIESCE;
+		else if (info.capability & ND_INTEL_BUS_FWA_CAP_OSQUIESCE) {
+			/*
+			 * Skip hibernate cycle by default if platform
+			 * indicates that it does not need devices to be
+			 * quiesced.
+			 */
+			acpi_desc->fwa_cap = NVDIMM_FWA_CAP_LIVE;
+		} else
+			acpi_desc->fwa_cap = NVDIMM_FWA_CAP_NONE;
+	}
+
+	acpi_desc->fwa_state = state;
+
+	return state;
+}
+
+static enum nvdimm_fwa_capability intel_bus_fwa_capability(
+		struct nvdimm_bus_descriptor *nd_desc)
+{
+	struct acpi_nfit_desc *acpi_desc = to_acpi_desc(nd_desc);
+
+	if (acpi_desc->fwa_cap > NVDIMM_FWA_CAP_INVALID)
+		return acpi_desc->fwa_cap;
+
+	if (intel_bus_fwa_state(nd_desc) > NVDIMM_FWA_INVALID)
+		return acpi_desc->fwa_cap;
+
+	return NVDIMM_FWA_CAP_INVALID;
+}
+
+static int intel_bus_fwa_activate(struct nvdimm_bus_descriptor *nd_desc)
+{
+	struct acpi_nfit_desc *acpi_desc = to_acpi_desc(nd_desc);
+	struct {
+		struct nd_cmd_pkg pkg;
+		struct nd_intel_bus_fw_activate cmd;
+	} nd_cmd = {
+		.pkg = {
+			.nd_command = NVDIMM_BUS_INTEL_FW_ACTIVATE,
+			.nd_family = NVDIMM_BUS_FAMILY_INTEL,
+			.nd_size_in = sizeof(nd_cmd.cmd.iodev_state),
+			.nd_size_out =
+				sizeof(struct nd_intel_bus_fw_activate),
+			.nd_fw_size =
+				sizeof(struct nd_intel_bus_fw_activate),
+		},
+		/*
+		 * Even though activate is run from a suspended context,
+		 * for safety, still ask platform firmware to force
+		 * quiesce devices by default. Let a module
+		 * parameter override that policy.
+		 */
+		.cmd = {
+			.iodev_state = acpi_desc->fwa_noidle
+				? ND_INTEL_BUS_FWA_IODEV_OS_IDLE
+				: ND_INTEL_BUS_FWA_IODEV_FORCE_IDLE,
+		},
+	};
+	int rc;
+
+	switch (intel_bus_fwa_state(nd_desc)) {
+	case NVDIMM_FWA_ARMED:
+	case NVDIMM_FWA_ARM_OVERFLOW:
+		break;
+	default:
+		return -ENXIO;
+	}
+
+	rc = nd_desc->ndctl(nd_desc, NULL, ND_CMD_CALL, &nd_cmd, sizeof(nd_cmd),
+			NULL);
+
+	/*
+	 * Whether the command succeeded, or failed, the agent checking
+	 * for the result needs to query the DIMMs individually.
+	 * Increment the activation count to invalidate all the DIMM
+	 * states at once (it's otherwise not possible to take
+	 * acpi_desc->init_mutex in this context)
+	 */
+	acpi_desc->fwa_state = NVDIMM_FWA_INVALID;
+	acpi_desc->fwa_count++;
+
+	dev_dbg(acpi_desc->dev, "result: %d\n", rc);
+
+	return rc;
+}
+
+static const struct nvdimm_bus_fw_ops __intel_bus_fw_ops = {
+	.activate_state = intel_bus_fwa_state,
+	.capability = intel_bus_fwa_capability,
+	.activate = intel_bus_fwa_activate,
+};
+
+const struct nvdimm_bus_fw_ops *intel_bus_fw_ops = &__intel_bus_fw_ops;
+
+static int intel_fwa_dimminfo(struct nvdimm *nvdimm,
+		struct nd_intel_fw_activate_dimminfo *info)
+{
+	struct {
+		struct nd_cmd_pkg pkg;
+		struct nd_intel_fw_activate_dimminfo cmd;
+	} nd_cmd = {
+		.pkg = {
+			.nd_command = NVDIMM_INTEL_FW_ACTIVATE_DIMMINFO,
+			.nd_family = NVDIMM_FAMILY_INTEL,
+			.nd_size_out =
+				sizeof(struct nd_intel_fw_activate_dimminfo),
+			.nd_fw_size =
+				sizeof(struct nd_intel_fw_activate_dimminfo),
+		},
+	};
+	int rc;
+
+	rc = nvdimm_ctl(nvdimm, ND_CMD_CALL, &nd_cmd, sizeof(nd_cmd), NULL);
+	*info = nd_cmd.cmd;
+	return rc;
+}
+
+static enum nvdimm_fwa_state intel_fwa_state(struct nvdimm *nvdimm)
+{
+	struct nfit_mem *nfit_mem = nvdimm_provider_data(nvdimm);
+	struct acpi_nfit_desc *acpi_desc = nfit_mem->acpi_desc;
+	struct nd_intel_fw_activate_dimminfo info;
+	int rc;
+
+	/*
+	 * Similar to the bus state, since activate is synchronous the
+	 * busy state should resolve within the context of 'activate'.
+	 */
+	switch (nfit_mem->fwa_state) {
+	case NVDIMM_FWA_INVALID:
+	case NVDIMM_FWA_BUSY:
+		break;
+	default:
+		/* If no activations occurred the old state is still valid */
+		if (nfit_mem->fwa_count == acpi_desc->fwa_count)
+			return nfit_mem->fwa_state;
+	}
+
+	rc = intel_fwa_dimminfo(nvdimm, &info);
+	if (rc)
+		return NVDIMM_FWA_INVALID;
+
+	switch (info.state) {
+	case ND_INTEL_FWA_IDLE:
+		nfit_mem->fwa_state = NVDIMM_FWA_IDLE;
+		break;
+	case ND_INTEL_FWA_BUSY:
+		nfit_mem->fwa_state = NVDIMM_FWA_BUSY;
+		break;
+	case ND_INTEL_FWA_ARMED:
+		nfit_mem->fwa_state = NVDIMM_FWA_ARMED;
+		break;
+	default:
+		nfit_mem->fwa_state = NVDIMM_FWA_INVALID;
+		break;
+	}
+
+	switch (info.result) {
+	case ND_INTEL_DIMM_FWA_NONE:
+		nfit_mem->fwa_result = NVDIMM_FWA_RESULT_NONE;
+		break;
+	case ND_INTEL_DIMM_FWA_SUCCESS:
+		nfit_mem->fwa_result = NVDIMM_FWA_RESULT_SUCCESS;
+		break;
+	case ND_INTEL_DIMM_FWA_NOTSTAGED:
+		nfit_mem->fwa_result = NVDIMM_FWA_RESULT_NOTSTAGED;
+		break;
+	case ND_INTEL_DIMM_FWA_NEEDRESET:
+		nfit_mem->fwa_result = NVDIMM_FWA_RESULT_NEEDRESET;
+		break;
+	case ND_INTEL_DIMM_FWA_MEDIAFAILED:
+	case ND_INTEL_DIMM_FWA_ABORT:
+	case ND_INTEL_DIMM_FWA_NOTSUPP:
+	case ND_INTEL_DIMM_FWA_ERROR:
+	default:
+		nfit_mem->fwa_result = NVDIMM_FWA_RESULT_FAIL;
+		break;
+	}
+
+	nfit_mem->fwa_count = acpi_desc->fwa_count;
+
+	return nfit_mem->fwa_state;
+}
+
+static enum nvdimm_fwa_result intel_fwa_result(struct nvdimm *nvdimm)
+{
+	struct nfit_mem *nfit_mem = nvdimm_provider_data(nvdimm);
+	struct acpi_nfit_desc *acpi_desc = nfit_mem->acpi_desc;
+
+	if (nfit_mem->fwa_count == acpi_desc->fwa_count
+			&& nfit_mem->fwa_result > NVDIMM_FWA_RESULT_INVALID)
+		return nfit_mem->fwa_result;
+
+	if (intel_fwa_state(nvdimm) > NVDIMM_FWA_INVALID)
+		return nfit_mem->fwa_result;
+
+	return NVDIMM_FWA_RESULT_INVALID;
+}
+
+static int intel_fwa_arm(struct nvdimm *nvdimm, enum nvdimm_fwa_trigger arm)
+{
+	struct nfit_mem *nfit_mem = nvdimm_provider_data(nvdimm);
+	struct acpi_nfit_desc *acpi_desc = nfit_mem->acpi_desc;
+	struct {
+		struct nd_cmd_pkg pkg;
+		struct nd_intel_fw_activate_arm cmd;
+	} nd_cmd = {
+		.pkg = {
+			.nd_command = NVDIMM_INTEL_FW_ACTIVATE_ARM,
+			.nd_family = NVDIMM_FAMILY_INTEL,
+			.nd_size_in = sizeof(nd_cmd.cmd.activate_arm),
+			.nd_size_out =
+				sizeof(struct nd_intel_fw_activate_arm),
+			.nd_fw_size =
+				sizeof(struct nd_intel_fw_activate_arm),
+		},
+		.cmd = {
+			.activate_arm = arm == NVDIMM_FWA_ARM
+				? ND_INTEL_DIMM_FWA_ARM
+				: ND_INTEL_DIMM_FWA_DISARM,
+		},
+	};
+	int rc;
+
+	switch (intel_fwa_state(nvdimm)) {
+	case NVDIMM_FWA_INVALID:
+		return -ENXIO;
+	case NVDIMM_FWA_BUSY:
+		return -EBUSY;
+	case NVDIMM_FWA_IDLE:
+		if (arm == NVDIMM_FWA_DISARM)
+			return 0;
+		break;
+	case NVDIMM_FWA_ARMED:
+		if (arm == NVDIMM_FWA_ARM)
+			return 0;
+		break;
+	default:
+		return -ENXIO;
+	}
+
+	/*
+	 * Invalidate the bus-level state, now that we're committed to
+	 * changing the 'arm' state.
+	 */
+	acpi_desc->fwa_state = NVDIMM_FWA_INVALID;
+	nfit_mem->fwa_state = NVDIMM_FWA_INVALID;
+
+	rc = nvdimm_ctl(nvdimm, ND_CMD_CALL, &nd_cmd, sizeof(nd_cmd), NULL);
+
+	dev_dbg(acpi_desc->dev, "%s result: %d\n", arm == NVDIMM_FWA_ARM
+			? "arm" : "disarm", rc);
+	return rc;
+}
+
+static const struct nvdimm_fw_ops __intel_fw_ops = {
+	.activate_state = intel_fwa_state,
+	.activate_result = intel_fwa_result,
+	.arm = intel_fwa_arm,
+};
+
+const struct nvdimm_fw_ops *intel_fw_ops = &__intel_fw_ops;