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, 467 insertions, 0 deletions

diff --git a/drivers/cxl/cxlmem.h b/drivers/cxl/cxlmem.h
new file mode 100644
index 000000000..ab138004f
--- /dev/null
+++ b/drivers/cxl/cxlmem.h
@@ -0,0 +1,467 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/* Copyright(c) 2020-2021 Intel Corporation. */
+#ifndef __CXL_MEM_H__
+#define __CXL_MEM_H__
+#include <uapi/linux/cxl_mem.h>
+#include <linux/cdev.h>
+#include "cxl.h"
+
+/* CXL 2.0 8.2.8.5.1.1 Memory Device Status Register */
+#define CXLMDEV_STATUS_OFFSET 0x0
+#define   CXLMDEV_DEV_FATAL BIT(0)
+#define   CXLMDEV_FW_HALT BIT(1)
+#define   CXLMDEV_STATUS_MEDIA_STATUS_MASK GENMASK(3, 2)
+#define     CXLMDEV_MS_NOT_READY 0
+#define     CXLMDEV_MS_READY 1
+#define     CXLMDEV_MS_ERROR 2
+#define     CXLMDEV_MS_DISABLED 3
+#define CXLMDEV_READY(status)                                                  \
+	(FIELD_GET(CXLMDEV_STATUS_MEDIA_STATUS_MASK, status) ==                \
+	 CXLMDEV_MS_READY)
+#define   CXLMDEV_MBOX_IF_READY BIT(4)
+#define   CXLMDEV_RESET_NEEDED_MASK GENMASK(7, 5)
+#define     CXLMDEV_RESET_NEEDED_NOT 0
+#define     CXLMDEV_RESET_NEEDED_COLD 1
+#define     CXLMDEV_RESET_NEEDED_WARM 2
+#define     CXLMDEV_RESET_NEEDED_HOT 3
+#define     CXLMDEV_RESET_NEEDED_CXL 4
+#define CXLMDEV_RESET_NEEDED(status)                                           \
+	(FIELD_GET(CXLMDEV_RESET_NEEDED_MASK, status) !=                       \
+	 CXLMDEV_RESET_NEEDED_NOT)
+
+/**
+ * struct cxl_memdev - CXL bus object representing a Type-3 Memory Device
+ * @dev: driver core device object
+ * @cdev: char dev core object for ioctl operations
+ * @cxlds: The device state backing this device
+ * @detach_work: active memdev lost a port in its ancestry
+ * @cxl_nvb: coordinate removal of @cxl_nvd if present
+ * @cxl_nvd: optional bridge to an nvdimm if the device supports pmem
+ * @id: id number of this memdev instance.
+ */
+struct cxl_memdev {
+	struct device dev;
+	struct cdev cdev;
+	struct cxl_dev_state *cxlds;
+	struct work_struct detach_work;
+	struct cxl_nvdimm_bridge *cxl_nvb;
+	struct cxl_nvdimm *cxl_nvd;
+	int id;
+};
+
+static inline struct cxl_memdev *to_cxl_memdev(struct device *dev)
+{
+	return container_of(dev, struct cxl_memdev, dev);
+}
+
+static inline struct cxl_port *cxled_to_port(struct cxl_endpoint_decoder *cxled)
+{
+	return to_cxl_port(cxled->cxld.dev.parent);
+}
+
+static inline struct cxl_port *cxlrd_to_port(struct cxl_root_decoder *cxlrd)
+{
+	return to_cxl_port(cxlrd->cxlsd.cxld.dev.parent);
+}
+
+static inline struct cxl_memdev *
+cxled_to_memdev(struct cxl_endpoint_decoder *cxled)
+{
+	struct cxl_port *port = to_cxl_port(cxled->cxld.dev.parent);
+
+	return to_cxl_memdev(port->uport);
+}
+
+bool is_cxl_memdev(struct device *dev);
+static inline bool is_cxl_endpoint(struct cxl_port *port)
+{
+	return is_cxl_memdev(port->uport);
+}
+
+struct cxl_memdev *devm_cxl_add_memdev(struct cxl_dev_state *cxlds);
+
+static inline struct cxl_ep *cxl_ep_load(struct cxl_port *port,
+					 struct cxl_memdev *cxlmd)
+{
+	if (!port)
+		return NULL;
+
+	return xa_load(&port->endpoints, (unsigned long)&cxlmd->dev);
+}
+
+/**
+ * struct cxl_mbox_cmd - A command to be submitted to hardware.
+ * @opcode: (input) The command set and command submitted to hardware.
+ * @payload_in: (input) Pointer to the input payload.
+ * @payload_out: (output) Pointer to the output payload. Must be allocated by
+ *		 the caller.
+ * @size_in: (input) Number of bytes to load from @payload_in.
+ * @size_out: (input) Max number of bytes loaded into @payload_out.
+ *            (output) Number of bytes generated by the device. For fixed size
+ *            outputs commands this is always expected to be deterministic. For
+ *            variable sized output commands, it tells the exact number of bytes
+ *            written.
+ * @min_out: (input) internal command output payload size validation
+ * @return_code: (output) Error code returned from hardware.
+ *
+ * This is the primary mechanism used to send commands to the hardware.
+ * All the fields except @payload_* correspond exactly to the fields described in
+ * Command Register section of the CXL 2.0 8.2.8.4.5. @payload_in and
+ * @payload_out are written to, and read from the Command Payload Registers
+ * defined in CXL 2.0 8.2.8.4.8.
+ */
+struct cxl_mbox_cmd {
+	u16 opcode;
+	void *payload_in;
+	void *payload_out;
+	size_t size_in;
+	size_t size_out;
+	size_t min_out;
+	u16 return_code;
+};
+
+/*
+ * Per CXL 2.0 Section 8.2.8.4.5.1
+ */
+#define CMD_CMD_RC_TABLE							\
+	C(SUCCESS, 0, NULL),							\
+	C(BACKGROUND, -ENXIO, "background cmd started successfully"),           \
+	C(INPUT, -ENXIO, "cmd input was invalid"),				\
+	C(UNSUPPORTED, -ENXIO, "cmd is not supported"),				\
+	C(INTERNAL, -ENXIO, "internal device error"),				\
+	C(RETRY, -ENXIO, "temporary error, retry once"),			\
+	C(BUSY, -ENXIO, "ongoing background operation"),			\
+	C(MEDIADISABLED, -ENXIO, "media access is disabled"),			\
+	C(FWINPROGRESS, -ENXIO,	"one FW package can be transferred at a time"), \
+	C(FWOOO, -ENXIO, "FW package content was transferred out of order"),    \
+	C(FWAUTH, -ENXIO, "FW package authentication failed"),			\
+	C(FWSLOT, -ENXIO, "FW slot is not supported for requested operation"),  \
+	C(FWROLLBACK, -ENXIO, "rolled back to the previous active FW"),         \
+	C(FWRESET, -ENXIO, "FW failed to activate, needs cold reset"),		\
+	C(HANDLE, -ENXIO, "one or more Event Record Handles were invalid"),     \
+	C(PADDR, -ENXIO, "physical address specified is invalid"),		\
+	C(POISONLMT, -ENXIO, "poison injection limit has been reached"),        \
+	C(MEDIAFAILURE, -ENXIO, "permanent issue with the media"),		\
+	C(ABORT, -ENXIO, "background cmd was aborted by device"),               \
+	C(SECURITY, -ENXIO, "not valid in the current security state"),         \
+	C(PASSPHRASE, -ENXIO, "phrase doesn't match current set passphrase"),   \
+	C(MBUNSUPPORTED, -ENXIO, "unsupported on the mailbox it was issued on"),\
+	C(PAYLOADLEN, -ENXIO, "invalid payload length")
+
+#undef C
+#define C(a, b, c) CXL_MBOX_CMD_RC_##a
+enum  { CMD_CMD_RC_TABLE };
+#undef C
+#define C(a, b, c) { b, c }
+struct cxl_mbox_cmd_rc {
+	int err;
+	const char *desc;
+};
+
+static const
+struct cxl_mbox_cmd_rc cxl_mbox_cmd_rctable[] ={ CMD_CMD_RC_TABLE };
+#undef C
+
+static inline const char *cxl_mbox_cmd_rc2str(struct cxl_mbox_cmd *mbox_cmd)
+{
+	return cxl_mbox_cmd_rctable[mbox_cmd->return_code].desc;
+}
+
+static inline int cxl_mbox_cmd_rc2errno(struct cxl_mbox_cmd *mbox_cmd)
+{
+	return cxl_mbox_cmd_rctable[mbox_cmd->return_code].err;
+}
+
+/*
+ * CXL 2.0 - Memory capacity multiplier
+ * See Section 8.2.9.5
+ *
+ * Volatile, Persistent, and Partition capacities are specified to be in
+ * multiples of 256MB - define a multiplier to convert to/from bytes.
+ */
+#define CXL_CAPACITY_MULTIPLIER SZ_256M
+
+/**
+ * struct cxl_endpoint_dvsec_info - Cached DVSEC info
+ * @mem_enabled: cached value of mem_enabled in the DVSEC, PCIE_DEVICE
+ * @ranges: Number of active HDM ranges this device uses.
+ * @dvsec_range: cached attributes of the ranges in the DVSEC, PCIE_DEVICE
+ */
+struct cxl_endpoint_dvsec_info {
+	bool mem_enabled;
+	int ranges;
+	struct range dvsec_range[2];
+};
+
+/**
+ * struct cxl_dev_state - The driver device state
+ *
+ * cxl_dev_state represents the CXL driver/device state.  It provides an
+ * interface to mailbox commands as well as some cached data about the device.
+ * Currently only memory devices are represented.
+ *
+ * @dev: The device associated with this CXL state
+ * @cxlmd: The device representing the CXL.mem capabilities of @dev
+ * @regs: Parsed register blocks
+ * @cxl_dvsec: Offset to the PCIe device DVSEC
+ * @rcd: operating in RCD mode (CXL 3.0 9.11.8 CXL Devices Attached to an RCH)
+ * @payload_size: Size of space for payload
+ *                (CXL 2.0 8.2.8.4.3 Mailbox Capabilities Register)
+ * @lsa_size: Size of Label Storage Area
+ *                (CXL 2.0 8.2.9.5.1.1 Identify Memory Device)
+ * @mbox_mutex: Mutex to synchronize mailbox access.
+ * @firmware_version: Firmware version for the memory device.
+ * @enabled_cmds: Hardware commands found enabled in CEL.
+ * @exclusive_cmds: Commands that are kernel-internal only
+ * @dpa_res: Overall DPA resource tree for the device
+ * @pmem_res: Active Persistent memory capacity configuration
+ * @ram_res: Active Volatile memory capacity configuration
+ * @total_bytes: sum of all possible capacities
+ * @volatile_only_bytes: hard volatile capacity
+ * @persistent_only_bytes: hard persistent capacity
+ * @partition_align_bytes: alignment size for partition-able capacity
+ * @active_volatile_bytes: sum of hard + soft volatile
+ * @active_persistent_bytes: sum of hard + soft persistent
+ * @next_volatile_bytes: volatile capacity change pending device reset
+ * @next_persistent_bytes: persistent capacity change pending device reset
+ * @component_reg_phys: register base of component registers
+ * @info: Cached DVSEC information about the device.
+ * @serial: PCIe Device Serial Number
+ * @doe_mbs: PCI DOE mailbox array
+ * @mbox_send: @dev specific transport for transmitting mailbox commands
+ *
+ * See section 8.2.9.5.2 Capacity Configuration and Label Storage for
+ * details on capacity parameters.
+ */
+struct cxl_dev_state {
+	struct device *dev;
+	struct cxl_memdev *cxlmd;
+
+	struct cxl_regs regs;
+	int cxl_dvsec;
+
+	bool rcd;
+	size_t payload_size;
+	size_t lsa_size;
+	struct mutex mbox_mutex; /* Protects device mailbox and firmware */
+	char firmware_version[0x10];
+	DECLARE_BITMAP(enabled_cmds, CXL_MEM_COMMAND_ID_MAX);
+	DECLARE_BITMAP(exclusive_cmds, CXL_MEM_COMMAND_ID_MAX);
+
+	struct resource dpa_res;
+	struct resource pmem_res;
+	struct resource ram_res;
+	u64 total_bytes;
+	u64 volatile_only_bytes;
+	u64 persistent_only_bytes;
+	u64 partition_align_bytes;
+
+	u64 active_volatile_bytes;
+	u64 active_persistent_bytes;
+	u64 next_volatile_bytes;
+	u64 next_persistent_bytes;
+
+	resource_size_t component_reg_phys;
+	u64 serial;
+
+	struct xarray doe_mbs;
+
+	int (*mbox_send)(struct cxl_dev_state *cxlds, struct cxl_mbox_cmd *cmd);
+};
+
+enum cxl_opcode {
+	CXL_MBOX_OP_INVALID		= 0x0000,
+	CXL_MBOX_OP_RAW			= CXL_MBOX_OP_INVALID,
+	CXL_MBOX_OP_GET_FW_INFO		= 0x0200,
+	CXL_MBOX_OP_ACTIVATE_FW		= 0x0202,
+	CXL_MBOX_OP_GET_SUPPORTED_LOGS	= 0x0400,
+	CXL_MBOX_OP_GET_LOG		= 0x0401,
+	CXL_MBOX_OP_IDENTIFY		= 0x4000,
+	CXL_MBOX_OP_GET_PARTITION_INFO	= 0x4100,
+	CXL_MBOX_OP_SET_PARTITION_INFO	= 0x4101,
+	CXL_MBOX_OP_GET_LSA		= 0x4102,
+	CXL_MBOX_OP_SET_LSA		= 0x4103,
+	CXL_MBOX_OP_GET_HEALTH_INFO	= 0x4200,
+	CXL_MBOX_OP_GET_ALERT_CONFIG	= 0x4201,
+	CXL_MBOX_OP_SET_ALERT_CONFIG	= 0x4202,
+	CXL_MBOX_OP_GET_SHUTDOWN_STATE	= 0x4203,
+	CXL_MBOX_OP_SET_SHUTDOWN_STATE	= 0x4204,
+	CXL_MBOX_OP_GET_POISON		= 0x4300,
+	CXL_MBOX_OP_INJECT_POISON	= 0x4301,
+	CXL_MBOX_OP_CLEAR_POISON	= 0x4302,
+	CXL_MBOX_OP_GET_SCAN_MEDIA_CAPS	= 0x4303,
+	CXL_MBOX_OP_SCAN_MEDIA		= 0x4304,
+	CXL_MBOX_OP_GET_SCAN_MEDIA	= 0x4305,
+	CXL_MBOX_OP_GET_SECURITY_STATE	= 0x4500,
+	CXL_MBOX_OP_SET_PASSPHRASE	= 0x4501,
+	CXL_MBOX_OP_DISABLE_PASSPHRASE	= 0x4502,
+	CXL_MBOX_OP_UNLOCK		= 0x4503,
+	CXL_MBOX_OP_FREEZE_SECURITY	= 0x4504,
+	CXL_MBOX_OP_PASSPHRASE_SECURE_ERASE	= 0x4505,
+	CXL_MBOX_OP_MAX			= 0x10000
+};
+
+#define DEFINE_CXL_CEL_UUID                                                    \
+	UUID_INIT(0xda9c0b5, 0xbf41, 0x4b78, 0x8f, 0x79, 0x96, 0xb1, 0x62,     \
+		  0x3b, 0x3f, 0x17)
+
+#define DEFINE_CXL_VENDOR_DEBUG_UUID                                           \
+	UUID_INIT(0xe1819d9, 0x11a9, 0x400c, 0x81, 0x1f, 0xd6, 0x07, 0x19,     \
+		  0x40, 0x3d, 0x86)
+
+struct cxl_mbox_get_supported_logs {
+	__le16 entries;
+	u8 rsvd[6];
+	struct cxl_gsl_entry {
+		uuid_t uuid;
+		__le32 size;
+	} __packed entry[];
+}  __packed;
+
+struct cxl_cel_entry {
+	__le16 opcode;
+	__le16 effect;
+} __packed;
+
+struct cxl_mbox_get_log {
+	uuid_t uuid;
+	__le32 offset;
+	__le32 length;
+} __packed;
+
+/* See CXL 2.0 Table 175 Identify Memory Device Output Payload */
+struct cxl_mbox_identify {
+	char fw_revision[0x10];
+	__le64 total_capacity;
+	__le64 volatile_capacity;
+	__le64 persistent_capacity;
+	__le64 partition_align;
+	__le16 info_event_log_size;
+	__le16 warning_event_log_size;
+	__le16 failure_event_log_size;
+	__le16 fatal_event_log_size;
+	__le32 lsa_size;
+	u8 poison_list_max_mer[3];
+	__le16 inject_poison_limit;
+	u8 poison_caps;
+	u8 qos_telemetry_caps;
+} __packed;
+
+struct cxl_mbox_get_partition_info {
+	__le64 active_volatile_cap;
+	__le64 active_persistent_cap;
+	__le64 next_volatile_cap;
+	__le64 next_persistent_cap;
+} __packed;
+
+struct cxl_mbox_get_lsa {
+	__le32 offset;
+	__le32 length;
+} __packed;
+
+struct cxl_mbox_set_lsa {
+	__le32 offset;
+	__le32 reserved;
+	u8 data[];
+} __packed;
+
+struct cxl_mbox_set_partition_info {
+	__le64 volatile_capacity;
+	u8 flags;
+} __packed;
+
+#define  CXL_SET_PARTITION_IMMEDIATE_FLAG	BIT(0)
+
+/**
+ * struct cxl_mem_command - Driver representation of a memory device command
+ * @info: Command information as it exists for the UAPI
+ * @opcode: The actual bits used for the mailbox protocol
+ * @flags: Set of flags effecting driver behavior.
+ *
+ *  * %CXL_CMD_FLAG_FORCE_ENABLE: In cases of error, commands with this flag
+ *    will be enabled by the driver regardless of what hardware may have
+ *    advertised.
+ *
+ * The cxl_mem_command is the driver's internal representation of commands that
+ * are supported by the driver. Some of these commands may not be supported by
+ * the hardware. The driver will use @info to validate the fields passed in by
+ * the user then submit the @opcode to the hardware.
+ *
+ * See struct cxl_command_info.
+ */
+struct cxl_mem_command {
+	struct cxl_command_info info;
+	enum cxl_opcode opcode;
+	u32 flags;
+#define CXL_CMD_FLAG_NONE 0
+#define CXL_CMD_FLAG_FORCE_ENABLE BIT(0)
+};
+
+#define CXL_PMEM_SEC_STATE_USER_PASS_SET	0x01
+#define CXL_PMEM_SEC_STATE_MASTER_PASS_SET	0x02
+#define CXL_PMEM_SEC_STATE_LOCKED		0x04
+#define CXL_PMEM_SEC_STATE_FROZEN		0x08
+#define CXL_PMEM_SEC_STATE_USER_PLIMIT		0x10
+#define CXL_PMEM_SEC_STATE_MASTER_PLIMIT	0x20
+
+/* set passphrase input payload */
+struct cxl_set_pass {
+	u8 type;
+	u8 reserved[31];
+	/* CXL field using NVDIMM define, same length */
+	u8 old_pass[NVDIMM_PASSPHRASE_LEN];
+	u8 new_pass[NVDIMM_PASSPHRASE_LEN];
+} __packed;
+
+/* disable passphrase input payload */
+struct cxl_disable_pass {
+	u8 type;
+	u8 reserved[31];
+	u8 pass[NVDIMM_PASSPHRASE_LEN];
+} __packed;
+
+/* passphrase secure erase payload */
+struct cxl_pass_erase {
+	u8 type;
+	u8 reserved[31];
+	u8 pass[NVDIMM_PASSPHRASE_LEN];
+} __packed;
+
+enum {
+	CXL_PMEM_SEC_PASS_MASTER = 0,
+	CXL_PMEM_SEC_PASS_USER,
+};
+
+int cxl_internal_send_cmd(struct cxl_dev_state *cxlds,
+			  struct cxl_mbox_cmd *cmd);
+int cxl_dev_state_identify(struct cxl_dev_state *cxlds);
+int cxl_await_media_ready(struct cxl_dev_state *cxlds);
+int cxl_enumerate_cmds(struct cxl_dev_state *cxlds);
+int cxl_mem_create_range_info(struct cxl_dev_state *cxlds);
+struct cxl_dev_state *cxl_dev_state_create(struct device *dev);
+void set_exclusive_cxl_commands(struct cxl_dev_state *cxlds, unsigned long *cmds);
+void clear_exclusive_cxl_commands(struct cxl_dev_state *cxlds, unsigned long *cmds);
+#ifdef CONFIG_CXL_SUSPEND
+void cxl_mem_active_inc(void);
+void cxl_mem_active_dec(void);
+#else
+static inline void cxl_mem_active_inc(void)
+{
+}
+static inline void cxl_mem_active_dec(void)
+{
+}
+#endif
+
+struct cxl_hdm {
+	struct cxl_component_regs regs;
+	unsigned int decoder_count;
+	unsigned int target_count;
+	unsigned int interleave_mask;
+	struct cxl_port *port;
+};
+
+struct seq_file;
+struct dentry *cxl_debugfs_create_dir(const char *dir);
+void cxl_dpa_debug(struct seq_file *file, struct cxl_dev_state *cxlds);
+#endif /* __CXL_MEM_H__ */