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, 672 insertions, 0 deletions

diff --git a/drivers/platform/x86/intel/sdsi.c b/drivers/platform/x86/intel/sdsi.c
new file mode 100644
index 000000000..9e0ea2cdd
--- /dev/null
+++ b/drivers/platform/x86/intel/sdsi.c
@@ -0,0 +1,672 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Intel On Demand (Software Defined Silicon) driver
+ *
+ * Copyright (c) 2022, Intel Corporation.
+ * All Rights Reserved.
+ *
+ * Author: "David E. Box" <david.e.box@linux.intel.com>
+ */
+
+#include <linux/auxiliary_bus.h>
+#include <linux/bits.h>
+#include <linux/bitfield.h>
+#include <linux/device.h>
+#include <linux/iopoll.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/pci.h>
+#include <linux/slab.h>
+#include <linux/sysfs.h>
+#include <linux/types.h>
+#include <linux/uaccess.h>
+
+#include "vsec.h"
+
+#define ACCESS_TYPE_BARID		2
+#define ACCESS_TYPE_LOCAL		3
+
+#define SDSI_MIN_SIZE_DWORDS		276
+#define SDSI_SIZE_MAILBOX		1024
+#define SDSI_SIZE_REGS			80
+#define SDSI_SIZE_CMD			sizeof(u64)
+
+/*
+ * Write messages are currently up to the size of the mailbox
+ * while read messages are up to 4 times the size of the
+ * mailbox, sent in packets
+ */
+#define SDSI_SIZE_WRITE_MSG		SDSI_SIZE_MAILBOX
+#define SDSI_SIZE_READ_MSG		(SDSI_SIZE_MAILBOX * 4)
+
+#define SDSI_ENABLED_FEATURES_OFFSET	16
+#define SDSI_FEATURE_SDSI		BIT(3)
+#define SDSI_FEATURE_METERING		BIT(26)
+
+#define SDSI_SOCKET_ID_OFFSET		64
+#define SDSI_SOCKET_ID			GENMASK(3, 0)
+
+#define SDSI_MBOX_CMD_SUCCESS		0x40
+#define SDSI_MBOX_CMD_TIMEOUT		0x80
+
+#define MBOX_TIMEOUT_US			2000
+#define MBOX_TIMEOUT_ACQUIRE_US		1000
+#define MBOX_POLLING_PERIOD_US		100
+#define MBOX_ACQUIRE_NUM_RETRIES	5
+#define MBOX_ACQUIRE_RETRY_DELAY_MS	500
+#define MBOX_MAX_PACKETS		4
+
+#define MBOX_OWNER_NONE			0x00
+#define MBOX_OWNER_INBAND		0x01
+
+#define CTRL_RUN_BUSY			BIT(0)
+#define CTRL_READ_WRITE			BIT(1)
+#define CTRL_SOM			BIT(2)
+#define CTRL_EOM			BIT(3)
+#define CTRL_OWNER			GENMASK(5, 4)
+#define CTRL_COMPLETE			BIT(6)
+#define CTRL_READY			BIT(7)
+#define CTRL_STATUS			GENMASK(15, 8)
+#define CTRL_PACKET_SIZE		GENMASK(31, 16)
+#define CTRL_MSG_SIZE			GENMASK(63, 48)
+
+#define DISC_TABLE_SIZE			12
+#define DT_ACCESS_TYPE			GENMASK(3, 0)
+#define DT_SIZE				GENMASK(27, 12)
+#define DT_TBIR				GENMASK(2, 0)
+#define DT_OFFSET(v)			((v) & GENMASK(31, 3))
+
+#define SDSI_GUID_V1			0x006DD191
+#define GUID_V1_CNTRL_SIZE		8
+#define GUID_V1_REGS_SIZE		72
+#define SDSI_GUID_V2			0xF210D9EF
+#define GUID_V2_CNTRL_SIZE		16
+#define GUID_V2_REGS_SIZE		80
+
+enum sdsi_command {
+	SDSI_CMD_PROVISION_AKC		= 0x0004,
+	SDSI_CMD_PROVISION_CAP		= 0x0008,
+	SDSI_CMD_READ_STATE		= 0x0010,
+	SDSI_CMD_READ_METER		= 0x0014,
+};
+
+struct sdsi_mbox_info {
+	u64	*payload;
+	void	*buffer;
+	int	size;
+};
+
+struct disc_table {
+	u32	access_info;
+	u32	guid;
+	u32	offset;
+};
+
+struct sdsi_priv {
+	struct mutex		mb_lock;	/* Mailbox access lock */
+	struct device		*dev;
+	void __iomem		*control_addr;
+	void __iomem		*mbox_addr;
+	void __iomem		*regs_addr;
+	int			control_size;
+	int			maibox_size;
+	int			registers_size;
+	u32			guid;
+	u32			features;
+};
+
+/* SDSi mailbox operations must be performed using 64bit mov instructions */
+static __always_inline void
+sdsi_memcpy64_toio(u64 __iomem *to, const u64 *from, size_t count_bytes)
+{
+	size_t count = count_bytes / sizeof(*to);
+	int i;
+
+	for (i = 0; i < count; i++)
+		writeq(from[i], &to[i]);
+}
+
+static __always_inline void
+sdsi_memcpy64_fromio(u64 *to, const u64 __iomem *from, size_t count_bytes)
+{
+	size_t count = count_bytes / sizeof(*to);
+	int i;
+
+	for (i = 0; i < count; i++)
+		to[i] = readq(&from[i]);
+}
+
+static inline void sdsi_complete_transaction(struct sdsi_priv *priv)
+{
+	u64 control = FIELD_PREP(CTRL_COMPLETE, 1);
+
+	lockdep_assert_held(&priv->mb_lock);
+	writeq(control, priv->control_addr);
+}
+
+static int sdsi_status_to_errno(u32 status)
+{
+	switch (status) {
+	case SDSI_MBOX_CMD_SUCCESS:
+		return 0;
+	case SDSI_MBOX_CMD_TIMEOUT:
+		return -ETIMEDOUT;
+	default:
+		return -EIO;
+	}
+}
+
+static int sdsi_mbox_cmd_read(struct sdsi_priv *priv, struct sdsi_mbox_info *info,
+			      size_t *data_size)
+{
+	struct device *dev = priv->dev;
+	u32 total, loop, eom, status, message_size;
+	u64 control;
+	int ret;
+
+	lockdep_assert_held(&priv->mb_lock);
+
+	/* Format and send the read command */
+	control = FIELD_PREP(CTRL_EOM, 1) |
+		  FIELD_PREP(CTRL_SOM, 1) |
+		  FIELD_PREP(CTRL_RUN_BUSY, 1) |
+		  FIELD_PREP(CTRL_PACKET_SIZE, info->size);
+	writeq(control, priv->control_addr);
+
+	/* For reads, data sizes that are larger than the mailbox size are read in packets. */
+	total = 0;
+	loop = 0;
+	do {
+		void *buf = info->buffer + (SDSI_SIZE_MAILBOX * loop);
+		u32 packet_size;
+
+		/* Poll on ready bit */
+		ret = readq_poll_timeout(priv->control_addr, control, control & CTRL_READY,
+					 MBOX_POLLING_PERIOD_US, MBOX_TIMEOUT_US);
+		if (ret)
+			break;
+
+		eom = FIELD_GET(CTRL_EOM, control);
+		status = FIELD_GET(CTRL_STATUS, control);
+		packet_size = FIELD_GET(CTRL_PACKET_SIZE, control);
+		message_size = FIELD_GET(CTRL_MSG_SIZE, control);
+
+		ret = sdsi_status_to_errno(status);
+		if (ret)
+			break;
+
+		/* Only the last packet can be less than the mailbox size. */
+		if (!eom && packet_size != SDSI_SIZE_MAILBOX) {
+			dev_err(dev, "Invalid packet size\n");
+			ret = -EPROTO;
+			break;
+		}
+
+		if (packet_size > SDSI_SIZE_MAILBOX) {
+			dev_err(dev, "Packet size too large\n");
+			ret = -EPROTO;
+			break;
+		}
+
+		sdsi_memcpy64_fromio(buf, priv->mbox_addr, round_up(packet_size, SDSI_SIZE_CMD));
+
+		total += packet_size;
+
+		sdsi_complete_transaction(priv);
+	} while (!eom && ++loop < MBOX_MAX_PACKETS);
+
+	if (ret) {
+		sdsi_complete_transaction(priv);
+		return ret;
+	}
+
+	if (!eom) {
+		dev_err(dev, "Exceeded read attempts\n");
+		return -EPROTO;
+	}
+
+	/* Message size check is only valid for multi-packet transfers */
+	if (loop && total != message_size)
+		dev_warn(dev, "Read count %u differs from expected count %u\n",
+			 total, message_size);
+
+	*data_size = total;
+
+	return 0;
+}
+
+static int sdsi_mbox_cmd_write(struct sdsi_priv *priv, struct sdsi_mbox_info *info)
+{
+	u64 control;
+	u32 status;
+	int ret;
+
+	lockdep_assert_held(&priv->mb_lock);
+
+	/* Write rest of the payload */
+	sdsi_memcpy64_toio(priv->mbox_addr + SDSI_SIZE_CMD, info->payload + 1,
+			   info->size - SDSI_SIZE_CMD);
+
+	/* Format and send the write command */
+	control = FIELD_PREP(CTRL_EOM, 1) |
+		  FIELD_PREP(CTRL_SOM, 1) |
+		  FIELD_PREP(CTRL_RUN_BUSY, 1) |
+		  FIELD_PREP(CTRL_READ_WRITE, 1) |
+		  FIELD_PREP(CTRL_PACKET_SIZE, info->size);
+	writeq(control, priv->control_addr);
+
+	/* Poll on ready bit */
+	ret = readq_poll_timeout(priv->control_addr, control, control & CTRL_READY,
+				 MBOX_POLLING_PERIOD_US, MBOX_TIMEOUT_US);
+
+	if (ret)
+		goto release_mbox;
+
+	status = FIELD_GET(CTRL_STATUS, control);
+	ret = sdsi_status_to_errno(status);
+
+release_mbox:
+	sdsi_complete_transaction(priv);
+
+	return ret;
+}
+
+static int sdsi_mbox_acquire(struct sdsi_priv *priv, struct sdsi_mbox_info *info)
+{
+	u64 control;
+	u32 owner;
+	int ret, retries = 0;
+
+	lockdep_assert_held(&priv->mb_lock);
+
+	/* Check mailbox is available */
+	control = readq(priv->control_addr);
+	owner = FIELD_GET(CTRL_OWNER, control);
+	if (owner != MBOX_OWNER_NONE)
+		return -EBUSY;
+
+	/*
+	 * If there has been no recent transaction and no one owns the mailbox,
+	 * we should acquire it in under 1ms. However, if we've accessed it
+	 * recently it may take up to 2.1 seconds to acquire it again.
+	 */
+	do {
+		/* Write first qword of payload */
+		writeq(info->payload[0], priv->mbox_addr);
+
+		/* Check for ownership */
+		ret = readq_poll_timeout(priv->control_addr, control,
+			FIELD_GET(CTRL_OWNER, control) == MBOX_OWNER_INBAND,
+			MBOX_POLLING_PERIOD_US, MBOX_TIMEOUT_ACQUIRE_US);
+
+		if (FIELD_GET(CTRL_OWNER, control) == MBOX_OWNER_NONE &&
+		    retries++ < MBOX_ACQUIRE_NUM_RETRIES) {
+			msleep(MBOX_ACQUIRE_RETRY_DELAY_MS);
+			continue;
+		}
+
+		/* Either we got it or someone else did. */
+		break;
+	} while (true);
+
+	return ret;
+}
+
+static int sdsi_mbox_write(struct sdsi_priv *priv, struct sdsi_mbox_info *info)
+{
+	int ret;
+
+	lockdep_assert_held(&priv->mb_lock);
+
+	ret = sdsi_mbox_acquire(priv, info);
+	if (ret)
+		return ret;
+
+	return sdsi_mbox_cmd_write(priv, info);
+}
+
+static int sdsi_mbox_read(struct sdsi_priv *priv, struct sdsi_mbox_info *info, size_t *data_size)
+{
+	int ret;
+
+	lockdep_assert_held(&priv->mb_lock);
+
+	ret = sdsi_mbox_acquire(priv, info);
+	if (ret)
+		return ret;
+
+	return sdsi_mbox_cmd_read(priv, info, data_size);
+}
+
+static ssize_t sdsi_provision(struct sdsi_priv *priv, char *buf, size_t count,
+			      enum sdsi_command command)
+{
+	struct sdsi_mbox_info info;
+	int ret;
+
+	if (count > (SDSI_SIZE_WRITE_MSG - SDSI_SIZE_CMD))
+		return -EOVERFLOW;
+
+	/* Qword aligned message + command qword */
+	info.size = round_up(count, SDSI_SIZE_CMD) + SDSI_SIZE_CMD;
+
+	info.payload = kzalloc(info.size, GFP_KERNEL);
+	if (!info.payload)
+		return -ENOMEM;
+
+	/* Copy message to payload buffer */
+	memcpy(info.payload, buf, count);
+
+	/* Command is last qword of payload buffer */
+	info.payload[(info.size - SDSI_SIZE_CMD) / SDSI_SIZE_CMD] = command;
+
+	ret = mutex_lock_interruptible(&priv->mb_lock);
+	if (ret)
+		goto free_payload;
+	ret = sdsi_mbox_write(priv, &info);
+	mutex_unlock(&priv->mb_lock);
+
+free_payload:
+	kfree(info.payload);
+
+	if (ret)
+		return ret;
+
+	return count;
+}
+
+static ssize_t provision_akc_write(struct file *filp, struct kobject *kobj,
+				   struct bin_attribute *attr, char *buf, loff_t off,
+				   size_t count)
+{
+	struct device *dev = kobj_to_dev(kobj);
+	struct sdsi_priv *priv = dev_get_drvdata(dev);
+
+	if (off)
+		return -ESPIPE;
+
+	return sdsi_provision(priv, buf, count, SDSI_CMD_PROVISION_AKC);
+}
+static BIN_ATTR_WO(provision_akc, SDSI_SIZE_WRITE_MSG);
+
+static ssize_t provision_cap_write(struct file *filp, struct kobject *kobj,
+				   struct bin_attribute *attr, char *buf, loff_t off,
+				   size_t count)
+{
+	struct device *dev = kobj_to_dev(kobj);
+	struct sdsi_priv *priv = dev_get_drvdata(dev);
+
+	if (off)
+		return -ESPIPE;
+
+	return sdsi_provision(priv, buf, count, SDSI_CMD_PROVISION_CAP);
+}
+static BIN_ATTR_WO(provision_cap, SDSI_SIZE_WRITE_MSG);
+
+static ssize_t
+certificate_read(u64 command, struct sdsi_priv *priv, char *buf, loff_t off,
+		 size_t count)
+{
+	struct sdsi_mbox_info info;
+	size_t size;
+	int ret;
+
+	if (off)
+		return 0;
+
+	/* Buffer for return data */
+	info.buffer = kmalloc(SDSI_SIZE_READ_MSG, GFP_KERNEL);
+	if (!info.buffer)
+		return -ENOMEM;
+
+	info.payload = &command;
+	info.size = sizeof(command);
+
+	ret = mutex_lock_interruptible(&priv->mb_lock);
+	if (ret)
+		goto free_buffer;
+	ret = sdsi_mbox_read(priv, &info, &size);
+	mutex_unlock(&priv->mb_lock);
+	if (ret < 0)
+		goto free_buffer;
+
+	if (size > count)
+		size = count;
+
+	memcpy(buf, info.buffer, size);
+
+free_buffer:
+	kfree(info.buffer);
+
+	if (ret)
+		return ret;
+
+	return size;
+}
+
+static ssize_t
+state_certificate_read(struct file *filp, struct kobject *kobj,
+		       struct bin_attribute *attr, char *buf, loff_t off,
+		       size_t count)
+{
+	struct device *dev = kobj_to_dev(kobj);
+	struct sdsi_priv *priv = dev_get_drvdata(dev);
+
+	return certificate_read(SDSI_CMD_READ_STATE, priv, buf, off, count);
+}
+static BIN_ATTR_ADMIN_RO(state_certificate, SDSI_SIZE_READ_MSG);
+
+static ssize_t
+meter_certificate_read(struct file *filp, struct kobject *kobj,
+		       struct bin_attribute *attr, char *buf, loff_t off,
+		       size_t count)
+{
+	struct device *dev = kobj_to_dev(kobj);
+	struct sdsi_priv *priv = dev_get_drvdata(dev);
+
+	return certificate_read(SDSI_CMD_READ_METER, priv, buf, off, count);
+}
+static BIN_ATTR_ADMIN_RO(meter_certificate, SDSI_SIZE_READ_MSG);
+
+static ssize_t registers_read(struct file *filp, struct kobject *kobj,
+			      struct bin_attribute *attr, char *buf, loff_t off,
+			      size_t count)
+{
+	struct device *dev = kobj_to_dev(kobj);
+	struct sdsi_priv *priv = dev_get_drvdata(dev);
+	void __iomem *addr = priv->regs_addr;
+	int size =  priv->registers_size;
+
+	/*
+	 * The check below is performed by the sysfs caller based on the static
+	 * file size. But this may be greater than the actual size which is based
+	 * on the GUID. So check here again based on actual size before reading.
+	 */
+	if (off >= size)
+		return 0;
+
+	if (off + count > size)
+		count = size - off;
+
+	memcpy_fromio(buf, addr + off, count);
+
+	return count;
+}
+static BIN_ATTR_ADMIN_RO(registers, SDSI_SIZE_REGS);
+
+static struct bin_attribute *sdsi_bin_attrs[] = {
+	&bin_attr_registers,
+	&bin_attr_state_certificate,
+	&bin_attr_meter_certificate,
+	&bin_attr_provision_akc,
+	&bin_attr_provision_cap,
+	NULL
+};
+
+static umode_t
+sdsi_battr_is_visible(struct kobject *kobj, struct bin_attribute *attr, int n)
+{
+	struct device *dev = kobj_to_dev(kobj);
+	struct sdsi_priv *priv = dev_get_drvdata(dev);
+
+	/* Registers file is always readable if the device is present */
+	if (attr == &bin_attr_registers)
+		return attr->attr.mode;
+
+	/* All other attributes not visible if BIOS has not enabled On Demand */
+	if (!(priv->features & SDSI_FEATURE_SDSI))
+		return 0;
+
+	if (attr == &bin_attr_meter_certificate)
+		return (priv->features & SDSI_FEATURE_METERING) ?
+				attr->attr.mode : 0;
+
+	return attr->attr.mode;
+}
+
+static ssize_t guid_show(struct device *dev, struct device_attribute *attr, char *buf)
+{
+	struct sdsi_priv *priv = dev_get_drvdata(dev);
+
+	return sysfs_emit(buf, "0x%x\n", priv->guid);
+}
+static DEVICE_ATTR_RO(guid);
+
+static struct attribute *sdsi_attrs[] = {
+	&dev_attr_guid.attr,
+	NULL
+};
+
+static const struct attribute_group sdsi_group = {
+	.attrs = sdsi_attrs,
+	.bin_attrs = sdsi_bin_attrs,
+	.is_bin_visible = sdsi_battr_is_visible,
+};
+__ATTRIBUTE_GROUPS(sdsi);
+
+static int sdsi_get_layout(struct sdsi_priv *priv, struct disc_table *table)
+{
+	switch (table->guid) {
+	case SDSI_GUID_V1:
+		priv->control_size = GUID_V1_CNTRL_SIZE;
+		priv->registers_size = GUID_V1_REGS_SIZE;
+		break;
+	case SDSI_GUID_V2:
+		priv->control_size = GUID_V2_CNTRL_SIZE;
+		priv->registers_size = GUID_V2_REGS_SIZE;
+		break;
+	default:
+		dev_err(priv->dev, "Unrecognized GUID 0x%x\n", table->guid);
+		return -EINVAL;
+	}
+	return 0;
+}
+
+static int sdsi_map_mbox_registers(struct sdsi_priv *priv, struct pci_dev *parent,
+				   struct disc_table *disc_table, struct resource *disc_res)
+{
+	u32 access_type = FIELD_GET(DT_ACCESS_TYPE, disc_table->access_info);
+	u32 size = FIELD_GET(DT_SIZE, disc_table->access_info);
+	u32 tbir = FIELD_GET(DT_TBIR, disc_table->offset);
+	u32 offset = DT_OFFSET(disc_table->offset);
+	struct resource res = {};
+
+	/* Starting location of SDSi MMIO region based on access type */
+	switch (access_type) {
+	case ACCESS_TYPE_LOCAL:
+		if (tbir) {
+			dev_err(priv->dev, "Unsupported BAR index %u for access type %u\n",
+				tbir, access_type);
+			return -EINVAL;
+		}
+
+		/*
+		 * For access_type LOCAL, the base address is as follows:
+		 * base address = end of discovery region + base offset + 1
+		 */
+		res.start = disc_res->end + offset + 1;
+		break;
+
+	case ACCESS_TYPE_BARID:
+		res.start = pci_resource_start(parent, tbir) + offset;
+		break;
+
+	default:
+		dev_err(priv->dev, "Unrecognized access_type %u\n", access_type);
+		return -EINVAL;
+	}
+
+	res.end = res.start + size * sizeof(u32) - 1;
+	res.flags = IORESOURCE_MEM;
+
+	priv->control_addr = devm_ioremap_resource(priv->dev, &res);
+	if (IS_ERR(priv->control_addr))
+		return PTR_ERR(priv->control_addr);
+
+	priv->mbox_addr = priv->control_addr + priv->control_size;
+	priv->regs_addr = priv->mbox_addr + SDSI_SIZE_MAILBOX;
+
+	priv->features = readq(priv->regs_addr + SDSI_ENABLED_FEATURES_OFFSET);
+
+	return 0;
+}
+
+static int sdsi_probe(struct auxiliary_device *auxdev, const struct auxiliary_device_id *id)
+{
+	struct intel_vsec_device *intel_cap_dev = auxdev_to_ivdev(auxdev);
+	struct disc_table disc_table;
+	struct resource *disc_res;
+	void __iomem *disc_addr;
+	struct sdsi_priv *priv;
+	int ret;
+
+	priv = devm_kzalloc(&auxdev->dev, sizeof(*priv), GFP_KERNEL);
+	if (!priv)
+		return -ENOMEM;
+
+	priv->dev = &auxdev->dev;
+	mutex_init(&priv->mb_lock);
+	auxiliary_set_drvdata(auxdev, priv);
+
+	/* Get the SDSi discovery table */
+	disc_res = &intel_cap_dev->resource[0];
+	disc_addr = devm_ioremap_resource(&auxdev->dev, disc_res);
+	if (IS_ERR(disc_addr))
+		return PTR_ERR(disc_addr);
+
+	memcpy_fromio(&disc_table, disc_addr, DISC_TABLE_SIZE);
+
+	priv->guid = disc_table.guid;
+
+	/* Get guid based layout info */
+	ret = sdsi_get_layout(priv, &disc_table);
+	if (ret)
+		return ret;
+
+	/* Map the SDSi mailbox registers */
+	ret = sdsi_map_mbox_registers(priv, intel_cap_dev->pcidev, &disc_table, disc_res);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+
+static const struct auxiliary_device_id sdsi_aux_id_table[] = {
+	{ .name = "intel_vsec.sdsi" },
+	{}
+};
+MODULE_DEVICE_TABLE(auxiliary, sdsi_aux_id_table);
+
+static struct auxiliary_driver sdsi_aux_driver = {
+	.driver = {
+		.dev_groups = sdsi_groups,
+	},
+	.id_table	= sdsi_aux_id_table,
+	.probe		= sdsi_probe,
+	/* No remove. All resources are handled under devm */
+};
+module_auxiliary_driver(sdsi_aux_driver);
+
+MODULE_AUTHOR("David E. Box <david.e.box@linux.intel.com>");
+MODULE_DESCRIPTION("Intel On Demand (SDSi) driver");
+MODULE_LICENSE("GPL");