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().
  ...

10 files changed, 1361 insertions, 0 deletions

diff --git a/drivers/virt/coco/efi_secret/Kconfig b/drivers/virt/coco/efi_secret/Kconfig
new file mode 100644
index 000000000..4404d198f
--- /dev/null
+++ b/drivers/virt/coco/efi_secret/Kconfig
@@ -0,0 +1,16 @@
+# SPDX-License-Identifier: GPL-2.0-only
+config EFI_SECRET
+	tristate "EFI secret area securityfs support"
+	depends on EFI && X86_64
+	select EFI_COCO_SECRET
+	select SECURITYFS
+	help
+	  This is a driver for accessing the EFI secret area via securityfs.
+	  The EFI secret area is a memory area designated by the firmware for
+	  confidential computing secret injection (for example for AMD SEV
+	  guests).  The driver exposes the secrets as files in
+	  <securityfs>/secrets/coco.  Files can be read and deleted (deleting
+	  a file wipes the secret from memory).
+
+	  To compile this driver as a module, choose M here.
+	  The module will be called efi_secret.
diff --git a/drivers/virt/coco/efi_secret/Makefile b/drivers/virt/coco/efi_secret/Makefile
new file mode 100644
index 000000000..c7047ce80
--- /dev/null
+++ b/drivers/virt/coco/efi_secret/Makefile
@@ -0,0 +1,2 @@
+# SPDX-License-Identifier: GPL-2.0-only
+obj-$(CONFIG_EFI_SECRET) += efi_secret.o
diff --git a/drivers/virt/coco/efi_secret/efi_secret.c b/drivers/virt/coco/efi_secret/efi_secret.c
new file mode 100644
index 000000000..e700a5ef7
--- /dev/null
+++ b/drivers/virt/coco/efi_secret/efi_secret.c
@@ -0,0 +1,349 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * efi_secret module
+ *
+ * Copyright (C) 2022 IBM Corporation
+ * Author: Dov Murik <dovmurik@linux.ibm.com>
+ */
+
+/**
+ * DOC: efi_secret: Allow reading EFI confidential computing (coco) secret area
+ * via securityfs interface.
+ *
+ * When the module is loaded (and securityfs is mounted, typically under
+ * /sys/kernel/security), a "secrets/coco" directory is created in securityfs.
+ * In it, a file is created for each secret entry.  The name of each such file
+ * is the GUID of the secret entry, and its content is the secret data.
+ */
+
+#include <linux/platform_device.h>
+#include <linux/seq_file.h>
+#include <linux/fs.h>
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/io.h>
+#include <linux/security.h>
+#include <linux/efi.h>
+#include <linux/cacheflush.h>
+
+#define EFI_SECRET_NUM_FILES 64
+
+struct efi_secret {
+	struct dentry *secrets_dir;
+	struct dentry *fs_dir;
+	struct dentry *fs_files[EFI_SECRET_NUM_FILES];
+	void __iomem *secret_data;
+	u64 secret_data_len;
+};
+
+/*
+ * Structure of the EFI secret area
+ *
+ * Offset   Length
+ * (bytes)  (bytes)  Usage
+ * -------  -------  -----
+ *       0       16  Secret table header GUID (must be 1e74f542-71dd-4d66-963e-ef4287ff173b)
+ *      16        4  Length of bytes of the entire secret area
+ *
+ *      20       16  First secret entry's GUID
+ *      36        4  First secret entry's length in bytes (= 16 + 4 + x)
+ *      40        x  First secret entry's data
+ *
+ *    40+x       16  Second secret entry's GUID
+ *    56+x        4  Second secret entry's length in bytes (= 16 + 4 + y)
+ *    60+x        y  Second secret entry's data
+ *
+ * (... and so on for additional entries)
+ *
+ * The GUID of each secret entry designates the usage of the secret data.
+ */
+
+/**
+ * struct secret_header - Header of entire secret area; this should be followed
+ * by instances of struct secret_entry.
+ * @guid:	Must be EFI_SECRET_TABLE_HEADER_GUID
+ * @len:	Length in bytes of entire secret area, including header
+ */
+struct secret_header {
+	efi_guid_t guid;
+	u32 len;
+} __attribute((packed));
+
+/**
+ * struct secret_entry - Holds one secret entry
+ * @guid:	Secret-specific GUID (or NULL_GUID if this secret entry was deleted)
+ * @len:	Length of secret entry, including its guid and len fields
+ * @data:	The secret data (full of zeros if this secret entry was deleted)
+ */
+struct secret_entry {
+	efi_guid_t guid;
+	u32 len;
+	u8 data[];
+} __attribute((packed));
+
+static size_t secret_entry_data_len(struct secret_entry *e)
+{
+	return e->len - sizeof(*e);
+}
+
+static struct efi_secret the_efi_secret;
+
+static inline struct efi_secret *efi_secret_get(void)
+{
+	return &the_efi_secret;
+}
+
+static int efi_secret_bin_file_show(struct seq_file *file, void *data)
+{
+	struct secret_entry *e = file->private;
+
+	if (e)
+		seq_write(file, e->data, secret_entry_data_len(e));
+
+	return 0;
+}
+DEFINE_SHOW_ATTRIBUTE(efi_secret_bin_file);
+
+/*
+ * Overwrite memory content with zeroes, and ensure that dirty cache lines are
+ * actually written back to memory, to clear out the secret.
+ */
+static void wipe_memory(void *addr, size_t size)
+{
+	memzero_explicit(addr, size);
+#ifdef CONFIG_X86
+	clflush_cache_range(addr, size);
+#endif
+}
+
+static int efi_secret_unlink(struct inode *dir, struct dentry *dentry)
+{
+	struct efi_secret *s = efi_secret_get();
+	struct inode *inode = d_inode(dentry);
+	struct secret_entry *e = (struct secret_entry *)inode->i_private;
+	int i;
+
+	if (e) {
+		/* Zero out the secret data */
+		wipe_memory(e->data, secret_entry_data_len(e));
+		e->guid = NULL_GUID;
+	}
+
+	inode->i_private = NULL;
+
+	for (i = 0; i < EFI_SECRET_NUM_FILES; i++)
+		if (s->fs_files[i] == dentry)
+			s->fs_files[i] = NULL;
+
+	/*
+	 * securityfs_remove tries to lock the directory's inode, but we reach
+	 * the unlink callback when it's already locked
+	 */
+	inode_unlock(dir);
+	securityfs_remove(dentry);
+	inode_lock(dir);
+
+	return 0;
+}
+
+static const struct inode_operations efi_secret_dir_inode_operations = {
+	.lookup         = simple_lookup,
+	.unlink         = efi_secret_unlink,
+};
+
+static int efi_secret_map_area(struct platform_device *dev)
+{
+	int ret;
+	struct efi_secret *s = efi_secret_get();
+	struct linux_efi_coco_secret_area *secret_area;
+
+	if (efi.coco_secret == EFI_INVALID_TABLE_ADDR) {
+		dev_err(&dev->dev, "Secret area address is not available\n");
+		return -EINVAL;
+	}
+
+	secret_area = memremap(efi.coco_secret, sizeof(*secret_area), MEMREMAP_WB);
+	if (secret_area == NULL) {
+		dev_err(&dev->dev, "Could not map secret area EFI config entry\n");
+		return -ENOMEM;
+	}
+	if (!secret_area->base_pa || secret_area->size < sizeof(struct secret_header)) {
+		dev_err(&dev->dev,
+			"Invalid secret area memory location (base_pa=0x%llx size=0x%llx)\n",
+			secret_area->base_pa, secret_area->size);
+		ret = -EINVAL;
+		goto unmap;
+	}
+
+	s->secret_data = ioremap_encrypted(secret_area->base_pa, secret_area->size);
+	if (s->secret_data == NULL) {
+		dev_err(&dev->dev, "Could not map secret area\n");
+		ret = -ENOMEM;
+		goto unmap;
+	}
+
+	s->secret_data_len = secret_area->size;
+	ret = 0;
+
+unmap:
+	memunmap(secret_area);
+	return ret;
+}
+
+static void efi_secret_securityfs_teardown(struct platform_device *dev)
+{
+	struct efi_secret *s = efi_secret_get();
+	int i;
+
+	for (i = (EFI_SECRET_NUM_FILES - 1); i >= 0; i--) {
+		securityfs_remove(s->fs_files[i]);
+		s->fs_files[i] = NULL;
+	}
+
+	securityfs_remove(s->fs_dir);
+	s->fs_dir = NULL;
+
+	securityfs_remove(s->secrets_dir);
+	s->secrets_dir = NULL;
+
+	dev_dbg(&dev->dev, "Removed securityfs entries\n");
+}
+
+static int efi_secret_securityfs_setup(struct platform_device *dev)
+{
+	struct efi_secret *s = efi_secret_get();
+	int ret = 0, i = 0, bytes_left;
+	unsigned char *ptr;
+	struct secret_header *h;
+	struct secret_entry *e;
+	struct dentry *dent;
+	char guid_str[EFI_VARIABLE_GUID_LEN + 1];
+
+	ptr = (void __force *)s->secret_data;
+	h = (struct secret_header *)ptr;
+	if (efi_guidcmp(h->guid, EFI_SECRET_TABLE_HEADER_GUID)) {
+		/*
+		 * This is not an error: it just means that EFI defines secret
+		 * area but it was not populated by the Guest Owner.
+		 */
+		dev_dbg(&dev->dev, "EFI secret area does not start with correct GUID\n");
+		return -ENODEV;
+	}
+	if (h->len < sizeof(*h)) {
+		dev_err(&dev->dev, "EFI secret area reported length is too small\n");
+		return -EINVAL;
+	}
+	if (h->len > s->secret_data_len) {
+		dev_err(&dev->dev, "EFI secret area reported length is too big\n");
+		return -EINVAL;
+	}
+
+	s->secrets_dir = NULL;
+	s->fs_dir = NULL;
+	memset(s->fs_files, 0, sizeof(s->fs_files));
+
+	dent = securityfs_create_dir("secrets", NULL);
+	if (IS_ERR(dent)) {
+		dev_err(&dev->dev, "Error creating secrets securityfs directory entry err=%ld\n",
+			PTR_ERR(dent));
+		return PTR_ERR(dent);
+	}
+	s->secrets_dir = dent;
+
+	dent = securityfs_create_dir("coco", s->secrets_dir);
+	if (IS_ERR(dent)) {
+		dev_err(&dev->dev, "Error creating coco securityfs directory entry err=%ld\n",
+			PTR_ERR(dent));
+		return PTR_ERR(dent);
+	}
+	d_inode(dent)->i_op = &efi_secret_dir_inode_operations;
+	s->fs_dir = dent;
+
+	bytes_left = h->len - sizeof(*h);
+	ptr += sizeof(*h);
+	while (bytes_left >= (int)sizeof(*e) && i < EFI_SECRET_NUM_FILES) {
+		e = (struct secret_entry *)ptr;
+		if (e->len < sizeof(*e) || e->len > (unsigned int)bytes_left) {
+			dev_err(&dev->dev, "EFI secret area is corrupted\n");
+			ret = -EINVAL;
+			goto err_cleanup;
+		}
+
+		/* Skip deleted entries (which will have NULL_GUID) */
+		if (efi_guidcmp(e->guid, NULL_GUID)) {
+			efi_guid_to_str(&e->guid, guid_str);
+
+			dent = securityfs_create_file(guid_str, 0440, s->fs_dir, (void *)e,
+						      &efi_secret_bin_file_fops);
+			if (IS_ERR(dent)) {
+				dev_err(&dev->dev, "Error creating efi_secret securityfs entry\n");
+				ret = PTR_ERR(dent);
+				goto err_cleanup;
+			}
+
+			s->fs_files[i++] = dent;
+		}
+		ptr += e->len;
+		bytes_left -= e->len;
+	}
+
+	dev_info(&dev->dev, "Created %d entries in securityfs secrets/coco\n", i);
+	return 0;
+
+err_cleanup:
+	efi_secret_securityfs_teardown(dev);
+	return ret;
+}
+
+static void efi_secret_unmap_area(void)
+{
+	struct efi_secret *s = efi_secret_get();
+
+	if (s->secret_data) {
+		iounmap(s->secret_data);
+		s->secret_data = NULL;
+		s->secret_data_len = 0;
+	}
+}
+
+static int efi_secret_probe(struct platform_device *dev)
+{
+	int ret;
+
+	ret = efi_secret_map_area(dev);
+	if (ret)
+		return ret;
+
+	ret = efi_secret_securityfs_setup(dev);
+	if (ret)
+		goto err_unmap;
+
+	return ret;
+
+err_unmap:
+	efi_secret_unmap_area();
+	return ret;
+}
+
+static int efi_secret_remove(struct platform_device *dev)
+{
+	efi_secret_securityfs_teardown(dev);
+	efi_secret_unmap_area();
+	return 0;
+}
+
+static struct platform_driver efi_secret_driver = {
+	.probe = efi_secret_probe,
+	.remove = efi_secret_remove,
+	.driver = {
+		.name = "efi_secret",
+	},
+};
+
+module_platform_driver(efi_secret_driver);
+
+MODULE_DESCRIPTION("Confidential computing EFI secret area access");
+MODULE_AUTHOR("IBM");
+MODULE_LICENSE("GPL");
+MODULE_ALIAS("platform:efi_secret");
diff --git a/drivers/virt/coco/sev-guest/Kconfig b/drivers/virt/coco/sev-guest/Kconfig
new file mode 100644
index 000000000..f9db0799a
--- /dev/null
+++ b/drivers/virt/coco/sev-guest/Kconfig
@@ -0,0 +1,14 @@
+config SEV_GUEST
+	tristate "AMD SEV Guest driver"
+	default m
+	depends on AMD_MEM_ENCRYPT
+	select CRYPTO_AEAD2
+	select CRYPTO_GCM
+	help
+	  SEV-SNP firmware provides the guest a mechanism to communicate with
+	  the PSP without risk from a malicious hypervisor who wishes to read,
+	  alter, drop or replay the messages sent. The driver provides
+	  userspace interface to communicate with the PSP to request the
+	  attestation report and more.
+
+	  If you choose 'M' here, this module will be called sev-guest.
diff --git a/drivers/virt/coco/sev-guest/Makefile b/drivers/virt/coco/sev-guest/Makefile
new file mode 100644
index 000000000..63d67c277
--- /dev/null
+++ b/drivers/virt/coco/sev-guest/Makefile
@@ -0,0 +1,2 @@
+# SPDX-License-Identifier: GPL-2.0-only
+obj-$(CONFIG_SEV_GUEST) += sev-guest.o
diff --git a/drivers/virt/coco/sev-guest/sev-guest.c b/drivers/virt/coco/sev-guest/sev-guest.c
new file mode 100644
index 000000000..4ec4174e0
--- /dev/null
+++ b/drivers/virt/coco/sev-guest/sev-guest.c
@@ -0,0 +1,801 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * AMD Secure Encrypted Virtualization (SEV) guest driver interface
+ *
+ * Copyright (C) 2021 Advanced Micro Devices, Inc.
+ *
+ * Author: Brijesh Singh <brijesh.singh@amd.com>
+ */
+
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/types.h>
+#include <linux/mutex.h>
+#include <linux/io.h>
+#include <linux/platform_device.h>
+#include <linux/miscdevice.h>
+#include <linux/set_memory.h>
+#include <linux/fs.h>
+#include <crypto/aead.h>
+#include <linux/scatterlist.h>
+#include <linux/psp-sev.h>
+#include <uapi/linux/sev-guest.h>
+#include <uapi/linux/psp-sev.h>
+
+#include <asm/svm.h>
+#include <asm/sev.h>
+
+#include "sev-guest.h"
+
+#define DEVICE_NAME	"sev-guest"
+#define AAD_LEN		48
+#define MSG_HDR_VER	1
+
+struct snp_guest_crypto {
+	struct crypto_aead *tfm;
+	u8 *iv, *authtag;
+	int iv_len, a_len;
+};
+
+struct snp_guest_dev {
+	struct device *dev;
+	struct miscdevice misc;
+
+	void *certs_data;
+	struct snp_guest_crypto *crypto;
+	struct snp_guest_msg *request, *response;
+	struct snp_secrets_page_layout *layout;
+	struct snp_req_data input;
+	u32 *os_area_msg_seqno;
+	u8 *vmpck;
+};
+
+static u32 vmpck_id;
+module_param(vmpck_id, uint, 0444);
+MODULE_PARM_DESC(vmpck_id, "The VMPCK ID to use when communicating with the PSP.");
+
+/* Mutex to serialize the shared buffer access and command handling. */
+static DEFINE_MUTEX(snp_cmd_mutex);
+
+static bool is_vmpck_empty(struct snp_guest_dev *snp_dev)
+{
+	char zero_key[VMPCK_KEY_LEN] = {0};
+
+	if (snp_dev->vmpck)
+		return !memcmp(snp_dev->vmpck, zero_key, VMPCK_KEY_LEN);
+
+	return true;
+}
+
+/*
+ * If an error is received from the host or AMD Secure Processor (ASP) there
+ * are two options. Either retry the exact same encrypted request or discontinue
+ * using the VMPCK.
+ *
+ * This is because in the current encryption scheme GHCB v2 uses AES-GCM to
+ * encrypt the requests. The IV for this scheme is the sequence number. GCM
+ * cannot tolerate IV reuse.
+ *
+ * The ASP FW v1.51 only increments the sequence numbers on a successful
+ * guest<->ASP back and forth and only accepts messages at its exact sequence
+ * number.
+ *
+ * So if the sequence number were to be reused the encryption scheme is
+ * vulnerable. If the sequence number were incremented for a fresh IV the ASP
+ * will reject the request.
+ */
+static void snp_disable_vmpck(struct snp_guest_dev *snp_dev)
+{
+	dev_alert(snp_dev->dev, "Disabling vmpck_id %d to prevent IV reuse.\n",
+		  vmpck_id);
+	memzero_explicit(snp_dev->vmpck, VMPCK_KEY_LEN);
+	snp_dev->vmpck = NULL;
+}
+
+static inline u64 __snp_get_msg_seqno(struct snp_guest_dev *snp_dev)
+{
+	u64 count;
+
+	lockdep_assert_held(&snp_cmd_mutex);
+
+	/* Read the current message sequence counter from secrets pages */
+	count = *snp_dev->os_area_msg_seqno;
+
+	return count + 1;
+}
+
+/* Return a non-zero on success */
+static u64 snp_get_msg_seqno(struct snp_guest_dev *snp_dev)
+{
+	u64 count = __snp_get_msg_seqno(snp_dev);
+
+	/*
+	 * The message sequence counter for the SNP guest request is a  64-bit
+	 * value but the version 2 of GHCB specification defines a 32-bit storage
+	 * for it. If the counter exceeds the 32-bit value then return zero.
+	 * The caller should check the return value, but if the caller happens to
+	 * not check the value and use it, then the firmware treats zero as an
+	 * invalid number and will fail the  message request.
+	 */
+	if (count >= UINT_MAX) {
+		dev_err(snp_dev->dev, "request message sequence counter overflow\n");
+		return 0;
+	}
+
+	return count;
+}
+
+static void snp_inc_msg_seqno(struct snp_guest_dev *snp_dev)
+{
+	/*
+	 * The counter is also incremented by the PSP, so increment it by 2
+	 * and save in secrets page.
+	 */
+	*snp_dev->os_area_msg_seqno += 2;
+}
+
+static inline struct snp_guest_dev *to_snp_dev(struct file *file)
+{
+	struct miscdevice *dev = file->private_data;
+
+	return container_of(dev, struct snp_guest_dev, misc);
+}
+
+static struct snp_guest_crypto *init_crypto(struct snp_guest_dev *snp_dev, u8 *key, size_t keylen)
+{
+	struct snp_guest_crypto *crypto;
+
+	crypto = kzalloc(sizeof(*crypto), GFP_KERNEL_ACCOUNT);
+	if (!crypto)
+		return NULL;
+
+	crypto->tfm = crypto_alloc_aead("gcm(aes)", 0, 0);
+	if (IS_ERR(crypto->tfm))
+		goto e_free;
+
+	if (crypto_aead_setkey(crypto->tfm, key, keylen))
+		goto e_free_crypto;
+
+	crypto->iv_len = crypto_aead_ivsize(crypto->tfm);
+	crypto->iv = kmalloc(crypto->iv_len, GFP_KERNEL_ACCOUNT);
+	if (!crypto->iv)
+		goto e_free_crypto;
+
+	if (crypto_aead_authsize(crypto->tfm) > MAX_AUTHTAG_LEN) {
+		if (crypto_aead_setauthsize(crypto->tfm, MAX_AUTHTAG_LEN)) {
+			dev_err(snp_dev->dev, "failed to set authsize to %d\n", MAX_AUTHTAG_LEN);
+			goto e_free_iv;
+		}
+	}
+
+	crypto->a_len = crypto_aead_authsize(crypto->tfm);
+	crypto->authtag = kmalloc(crypto->a_len, GFP_KERNEL_ACCOUNT);
+	if (!crypto->authtag)
+		goto e_free_iv;
+
+	return crypto;
+
+e_free_iv:
+	kfree(crypto->iv);
+e_free_crypto:
+	crypto_free_aead(crypto->tfm);
+e_free:
+	kfree(crypto);
+
+	return NULL;
+}
+
+static void deinit_crypto(struct snp_guest_crypto *crypto)
+{
+	crypto_free_aead(crypto->tfm);
+	kfree(crypto->iv);
+	kfree(crypto->authtag);
+	kfree(crypto);
+}
+
+static int enc_dec_message(struct snp_guest_crypto *crypto, struct snp_guest_msg *msg,
+			   u8 *src_buf, u8 *dst_buf, size_t len, bool enc)
+{
+	struct snp_guest_msg_hdr *hdr = &msg->hdr;
+	struct scatterlist src[3], dst[3];
+	DECLARE_CRYPTO_WAIT(wait);
+	struct aead_request *req;
+	int ret;
+
+	req = aead_request_alloc(crypto->tfm, GFP_KERNEL);
+	if (!req)
+		return -ENOMEM;
+
+	/*
+	 * AEAD memory operations:
+	 * +------ AAD -------+------- DATA -----+---- AUTHTAG----+
+	 * |  msg header      |  plaintext       |  hdr->authtag  |
+	 * | bytes 30h - 5Fh  |    or            |                |
+	 * |                  |   cipher         |                |
+	 * +------------------+------------------+----------------+
+	 */
+	sg_init_table(src, 3);
+	sg_set_buf(&src[0], &hdr->algo, AAD_LEN);
+	sg_set_buf(&src[1], src_buf, hdr->msg_sz);
+	sg_set_buf(&src[2], hdr->authtag, crypto->a_len);
+
+	sg_init_table(dst, 3);
+	sg_set_buf(&dst[0], &hdr->algo, AAD_LEN);
+	sg_set_buf(&dst[1], dst_buf, hdr->msg_sz);
+	sg_set_buf(&dst[2], hdr->authtag, crypto->a_len);
+
+	aead_request_set_ad(req, AAD_LEN);
+	aead_request_set_tfm(req, crypto->tfm);
+	aead_request_set_callback(req, 0, crypto_req_done, &wait);
+
+	aead_request_set_crypt(req, src, dst, len, crypto->iv);
+	ret = crypto_wait_req(enc ? crypto_aead_encrypt(req) : crypto_aead_decrypt(req), &wait);
+
+	aead_request_free(req);
+	return ret;
+}
+
+static int __enc_payload(struct snp_guest_dev *snp_dev, struct snp_guest_msg *msg,
+			 void *plaintext, size_t len)
+{
+	struct snp_guest_crypto *crypto = snp_dev->crypto;
+	struct snp_guest_msg_hdr *hdr = &msg->hdr;
+
+	memset(crypto->iv, 0, crypto->iv_len);
+	memcpy(crypto->iv, &hdr->msg_seqno, sizeof(hdr->msg_seqno));
+
+	return enc_dec_message(crypto, msg, plaintext, msg->payload, len, true);
+}
+
+static int dec_payload(struct snp_guest_dev *snp_dev, struct snp_guest_msg *msg,
+		       void *plaintext, size_t len)
+{
+	struct snp_guest_crypto *crypto = snp_dev->crypto;
+	struct snp_guest_msg_hdr *hdr = &msg->hdr;
+
+	/* Build IV with response buffer sequence number */
+	memset(crypto->iv, 0, crypto->iv_len);
+	memcpy(crypto->iv, &hdr->msg_seqno, sizeof(hdr->msg_seqno));
+
+	return enc_dec_message(crypto, msg, msg->payload, plaintext, len, false);
+}
+
+static int verify_and_dec_payload(struct snp_guest_dev *snp_dev, void *payload, u32 sz)
+{
+	struct snp_guest_crypto *crypto = snp_dev->crypto;
+	struct snp_guest_msg *resp = snp_dev->response;
+	struct snp_guest_msg *req = snp_dev->request;
+	struct snp_guest_msg_hdr *req_hdr = &req->hdr;
+	struct snp_guest_msg_hdr *resp_hdr = &resp->hdr;
+
+	dev_dbg(snp_dev->dev, "response [seqno %lld type %d version %d sz %d]\n",
+		resp_hdr->msg_seqno, resp_hdr->msg_type, resp_hdr->msg_version, resp_hdr->msg_sz);
+
+	/* Verify that the sequence counter is incremented by 1 */
+	if (unlikely(resp_hdr->msg_seqno != (req_hdr->msg_seqno + 1)))
+		return -EBADMSG;
+
+	/* Verify response message type and version number. */
+	if (resp_hdr->msg_type != (req_hdr->msg_type + 1) ||
+	    resp_hdr->msg_version != req_hdr->msg_version)
+		return -EBADMSG;
+
+	/*
+	 * If the message size is greater than our buffer length then return
+	 * an error.
+	 */
+	if (unlikely((resp_hdr->msg_sz + crypto->a_len) > sz))
+		return -EBADMSG;
+
+	/* Decrypt the payload */
+	return dec_payload(snp_dev, resp, payload, resp_hdr->msg_sz + crypto->a_len);
+}
+
+static int enc_payload(struct snp_guest_dev *snp_dev, u64 seqno, int version, u8 type,
+			void *payload, size_t sz)
+{
+	struct snp_guest_msg *req = snp_dev->request;
+	struct snp_guest_msg_hdr *hdr = &req->hdr;
+
+	memset(req, 0, sizeof(*req));
+
+	hdr->algo = SNP_AEAD_AES_256_GCM;
+	hdr->hdr_version = MSG_HDR_VER;
+	hdr->hdr_sz = sizeof(*hdr);
+	hdr->msg_type = type;
+	hdr->msg_version = version;
+	hdr->msg_seqno = seqno;
+	hdr->msg_vmpck = vmpck_id;
+	hdr->msg_sz = sz;
+
+	/* Verify the sequence number is non-zero */
+	if (!hdr->msg_seqno)
+		return -ENOSR;
+
+	dev_dbg(snp_dev->dev, "request [seqno %lld type %d version %d sz %d]\n",
+		hdr->msg_seqno, hdr->msg_type, hdr->msg_version, hdr->msg_sz);
+
+	return __enc_payload(snp_dev, req, payload, sz);
+}
+
+static int handle_guest_request(struct snp_guest_dev *snp_dev, u64 exit_code, int msg_ver,
+				u8 type, void *req_buf, size_t req_sz, void *resp_buf,
+				u32 resp_sz, __u64 *fw_err)
+{
+	unsigned long err;
+	u64 seqno;
+	int rc;
+
+	/* Get message sequence and verify that its a non-zero */
+	seqno = snp_get_msg_seqno(snp_dev);
+	if (!seqno)
+		return -EIO;
+
+	memset(snp_dev->response, 0, sizeof(struct snp_guest_msg));
+
+	/* Encrypt the userspace provided payload */
+	rc = enc_payload(snp_dev, seqno, msg_ver, type, req_buf, req_sz);
+	if (rc)
+		return rc;
+
+	/*
+	 * Call firmware to process the request. In this function the encrypted
+	 * message enters shared memory with the host. So after this call the
+	 * sequence number must be incremented or the VMPCK must be deleted to
+	 * prevent reuse of the IV.
+	 */
+	rc = snp_issue_guest_request(exit_code, &snp_dev->input, &err);
+
+	/*
+	 * If the extended guest request fails due to having too small of a
+	 * certificate data buffer, retry the same guest request without the
+	 * extended data request in order to increment the sequence number
+	 * and thus avoid IV reuse.
+	 */
+	if (exit_code == SVM_VMGEXIT_EXT_GUEST_REQUEST &&
+	    err == SNP_GUEST_REQ_INVALID_LEN) {
+		const unsigned int certs_npages = snp_dev->input.data_npages;
+
+		exit_code = SVM_VMGEXIT_GUEST_REQUEST;
+
+		/*
+		 * If this call to the firmware succeeds, the sequence number can
+		 * be incremented allowing for continued use of the VMPCK. If
+		 * there is an error reflected in the return value, this value
+		 * is checked further down and the result will be the deletion
+		 * of the VMPCK and the error code being propagated back to the
+		 * user as an ioctl() return code.
+		 */
+		rc = snp_issue_guest_request(exit_code, &snp_dev->input, &err);
+
+		/*
+		 * Override the error to inform callers the given extended
+		 * request buffer size was too small and give the caller the
+		 * required buffer size.
+		 */
+		err = SNP_GUEST_REQ_INVALID_LEN;
+		snp_dev->input.data_npages = certs_npages;
+	}
+
+	if (fw_err)
+		*fw_err = err;
+
+	if (rc) {
+		dev_alert(snp_dev->dev,
+			  "Detected error from ASP request. rc: %d, fw_err: %llu\n",
+			  rc, *fw_err);
+		goto disable_vmpck;
+	}
+
+	rc = verify_and_dec_payload(snp_dev, resp_buf, resp_sz);
+	if (rc) {
+		dev_alert(snp_dev->dev,
+			  "Detected unexpected decode failure from ASP. rc: %d\n",
+			  rc);
+		goto disable_vmpck;
+	}
+
+	/* Increment to new message sequence after payload decryption was successful. */
+	snp_inc_msg_seqno(snp_dev);
+
+	return 0;
+
+disable_vmpck:
+	snp_disable_vmpck(snp_dev);
+	return rc;
+}
+
+static int get_report(struct snp_guest_dev *snp_dev, struct snp_guest_request_ioctl *arg)
+{
+	struct snp_guest_crypto *crypto = snp_dev->crypto;
+	struct snp_report_resp *resp;
+	struct snp_report_req req;
+	int rc, resp_len;
+
+	lockdep_assert_held(&snp_cmd_mutex);
+
+	if (!arg->req_data || !arg->resp_data)
+		return -EINVAL;
+
+	if (copy_from_user(&req, (void __user *)arg->req_data, sizeof(req)))
+		return -EFAULT;
+
+	/*
+	 * The intermediate response buffer is used while decrypting the
+	 * response payload. Make sure that it has enough space to cover the
+	 * authtag.
+	 */
+	resp_len = sizeof(resp->data) + crypto->a_len;
+	resp = kzalloc(resp_len, GFP_KERNEL_ACCOUNT);
+	if (!resp)
+		return -ENOMEM;
+
+	rc = handle_guest_request(snp_dev, SVM_VMGEXIT_GUEST_REQUEST, arg->msg_version,
+				  SNP_MSG_REPORT_REQ, &req, sizeof(req), resp->data,
+				  resp_len, &arg->fw_err);
+	if (rc)
+		goto e_free;
+
+	if (copy_to_user((void __user *)arg->resp_data, resp, sizeof(*resp)))
+		rc = -EFAULT;
+
+e_free:
+	kfree(resp);
+	return rc;
+}
+
+static int get_derived_key(struct snp_guest_dev *snp_dev, struct snp_guest_request_ioctl *arg)
+{
+	struct snp_guest_crypto *crypto = snp_dev->crypto;
+	struct snp_derived_key_resp resp = {0};
+	struct snp_derived_key_req req;
+	int rc, resp_len;
+	/* Response data is 64 bytes and max authsize for GCM is 16 bytes. */
+	u8 buf[64 + 16];
+
+	lockdep_assert_held(&snp_cmd_mutex);
+
+	if (!arg->req_data || !arg->resp_data)
+		return -EINVAL;
+
+	/*
+	 * The intermediate response buffer is used while decrypting the
+	 * response payload. Make sure that it has enough space to cover the
+	 * authtag.
+	 */
+	resp_len = sizeof(resp.data) + crypto->a_len;
+	if (sizeof(buf) < resp_len)
+		return -ENOMEM;
+
+	if (copy_from_user(&req, (void __user *)arg->req_data, sizeof(req)))
+		return -EFAULT;
+
+	rc = handle_guest_request(snp_dev, SVM_VMGEXIT_GUEST_REQUEST, arg->msg_version,
+				  SNP_MSG_KEY_REQ, &req, sizeof(req), buf, resp_len,
+				  &arg->fw_err);
+	if (rc)
+		return rc;
+
+	memcpy(resp.data, buf, sizeof(resp.data));
+	if (copy_to_user((void __user *)arg->resp_data, &resp, sizeof(resp)))
+		rc = -EFAULT;
+
+	/* The response buffer contains the sensitive data, explicitly clear it. */
+	memzero_explicit(buf, sizeof(buf));
+	memzero_explicit(&resp, sizeof(resp));
+	return rc;
+}
+
+static int get_ext_report(struct snp_guest_dev *snp_dev, struct snp_guest_request_ioctl *arg)
+{
+	struct snp_guest_crypto *crypto = snp_dev->crypto;
+	struct snp_ext_report_req req;
+	struct snp_report_resp *resp;
+	int ret, npages = 0, resp_len;
+
+	lockdep_assert_held(&snp_cmd_mutex);
+
+	if (!arg->req_data || !arg->resp_data)
+		return -EINVAL;
+
+	if (copy_from_user(&req, (void __user *)arg->req_data, sizeof(req)))
+		return -EFAULT;
+
+	/* userspace does not want certificate data */
+	if (!req.certs_len || !req.certs_address)
+		goto cmd;
+
+	if (req.certs_len > SEV_FW_BLOB_MAX_SIZE ||
+	    !IS_ALIGNED(req.certs_len, PAGE_SIZE))
+		return -EINVAL;
+
+	if (!access_ok((const void __user *)req.certs_address, req.certs_len))
+		return -EFAULT;
+
+	/*
+	 * Initialize the intermediate buffer with all zeros. This buffer
+	 * is used in the guest request message to get the certs blob from
+	 * the host. If host does not supply any certs in it, then copy
+	 * zeros to indicate that certificate data was not provided.
+	 */
+	memset(snp_dev->certs_data, 0, req.certs_len);
+	npages = req.certs_len >> PAGE_SHIFT;
+cmd:
+	/*
+	 * The intermediate response buffer is used while decrypting the
+	 * response payload. Make sure that it has enough space to cover the
+	 * authtag.
+	 */
+	resp_len = sizeof(resp->data) + crypto->a_len;
+	resp = kzalloc(resp_len, GFP_KERNEL_ACCOUNT);
+	if (!resp)
+		return -ENOMEM;
+
+	snp_dev->input.data_npages = npages;
+	ret = handle_guest_request(snp_dev, SVM_VMGEXIT_EXT_GUEST_REQUEST, arg->msg_version,
+				   SNP_MSG_REPORT_REQ, &req.data,
+				   sizeof(req.data), resp->data, resp_len, &arg->fw_err);
+
+	/* If certs length is invalid then copy the returned length */
+	if (arg->fw_err == SNP_GUEST_REQ_INVALID_LEN) {
+		req.certs_len = snp_dev->input.data_npages << PAGE_SHIFT;
+
+		if (copy_to_user((void __user *)arg->req_data, &req, sizeof(req)))
+			ret = -EFAULT;
+	}
+
+	if (ret)
+		goto e_free;
+
+	if (npages &&
+	    copy_to_user((void __user *)req.certs_address, snp_dev->certs_data,
+			 req.certs_len)) {
+		ret = -EFAULT;
+		goto e_free;
+	}
+
+	if (copy_to_user((void __user *)arg->resp_data, resp, sizeof(*resp)))
+		ret = -EFAULT;
+
+e_free:
+	kfree(resp);
+	return ret;
+}
+
+static long snp_guest_ioctl(struct file *file, unsigned int ioctl, unsigned long arg)
+{
+	struct snp_guest_dev *snp_dev = to_snp_dev(file);
+	void __user *argp = (void __user *)arg;
+	struct snp_guest_request_ioctl input;
+	int ret = -ENOTTY;
+
+	if (copy_from_user(&input, argp, sizeof(input)))
+		return -EFAULT;
+
+	input.fw_err = 0xff;
+
+	/* Message version must be non-zero */
+	if (!input.msg_version)
+		return -EINVAL;
+
+	mutex_lock(&snp_cmd_mutex);
+
+	/* Check if the VMPCK is not empty */
+	if (is_vmpck_empty(snp_dev)) {
+		dev_err_ratelimited(snp_dev->dev, "VMPCK is disabled\n");
+		mutex_unlock(&snp_cmd_mutex);
+		return -ENOTTY;
+	}
+
+	switch (ioctl) {
+	case SNP_GET_REPORT:
+		ret = get_report(snp_dev, &input);
+		break;
+	case SNP_GET_DERIVED_KEY:
+		ret = get_derived_key(snp_dev, &input);
+		break;
+	case SNP_GET_EXT_REPORT:
+		ret = get_ext_report(snp_dev, &input);
+		break;
+	default:
+		break;
+	}
+
+	mutex_unlock(&snp_cmd_mutex);
+
+	if (input.fw_err && copy_to_user(argp, &input, sizeof(input)))
+		return -EFAULT;
+
+	return ret;
+}
+
+static void free_shared_pages(void *buf, size_t sz)
+{
+	unsigned int npages = PAGE_ALIGN(sz) >> PAGE_SHIFT;
+	int ret;
+
+	if (!buf)
+		return;
+
+	ret = set_memory_encrypted((unsigned long)buf, npages);
+	if (ret) {
+		WARN_ONCE(ret, "failed to restore encryption mask (leak it)\n");
+		return;
+	}
+
+	__free_pages(virt_to_page(buf), get_order(sz));
+}
+
+static void *alloc_shared_pages(struct device *dev, size_t sz)
+{
+	unsigned int npages = PAGE_ALIGN(sz) >> PAGE_SHIFT;
+	struct page *page;
+	int ret;
+
+	page = alloc_pages(GFP_KERNEL_ACCOUNT, get_order(sz));
+	if (!page)
+		return NULL;
+
+	ret = set_memory_decrypted((unsigned long)page_address(page), npages);
+	if (ret) {
+		dev_err(dev, "failed to mark page shared, ret=%d\n", ret);
+		__free_pages(page, get_order(sz));
+		return NULL;
+	}
+
+	return page_address(page);
+}
+
+static const struct file_operations snp_guest_fops = {
+	.owner	= THIS_MODULE,
+	.unlocked_ioctl = snp_guest_ioctl,
+};
+
+static u8 *get_vmpck(int id, struct snp_secrets_page_layout *layout, u32 **seqno)
+{
+	u8 *key = NULL;
+
+	switch (id) {
+	case 0:
+		*seqno = &layout->os_area.msg_seqno_0;
+		key = layout->vmpck0;
+		break;
+	case 1:
+		*seqno = &layout->os_area.msg_seqno_1;
+		key = layout->vmpck1;
+		break;
+	case 2:
+		*seqno = &layout->os_area.msg_seqno_2;
+		key = layout->vmpck2;
+		break;
+	case 3:
+		*seqno = &layout->os_area.msg_seqno_3;
+		key = layout->vmpck3;
+		break;
+	default:
+		break;
+	}
+
+	return key;
+}
+
+static int __init sev_guest_probe(struct platform_device *pdev)
+{
+	struct snp_secrets_page_layout *layout;
+	struct sev_guest_platform_data *data;
+	struct device *dev = &pdev->dev;
+	struct snp_guest_dev *snp_dev;
+	struct miscdevice *misc;
+	void __iomem *mapping;
+	int ret;
+
+	if (!dev->platform_data)
+		return -ENODEV;
+
+	data = (struct sev_guest_platform_data *)dev->platform_data;
+	mapping = ioremap_encrypted(data->secrets_gpa, PAGE_SIZE);
+	if (!mapping)
+		return -ENODEV;
+
+	layout = (__force void *)mapping;
+
+	ret = -ENOMEM;
+	snp_dev = devm_kzalloc(&pdev->dev, sizeof(struct snp_guest_dev), GFP_KERNEL);
+	if (!snp_dev)
+		goto e_unmap;
+
+	ret = -EINVAL;
+	snp_dev->vmpck = get_vmpck(vmpck_id, layout, &snp_dev->os_area_msg_seqno);
+	if (!snp_dev->vmpck) {
+		dev_err(dev, "invalid vmpck id %d\n", vmpck_id);
+		goto e_unmap;
+	}
+
+	/* Verify that VMPCK is not zero. */
+	if (is_vmpck_empty(snp_dev)) {
+		dev_err(dev, "vmpck id %d is null\n", vmpck_id);
+		goto e_unmap;
+	}
+
+	platform_set_drvdata(pdev, snp_dev);
+	snp_dev->dev = dev;
+	snp_dev->layout = layout;
+
+	/* Allocate the shared page used for the request and response message. */
+	snp_dev->request = alloc_shared_pages(dev, sizeof(struct snp_guest_msg));
+	if (!snp_dev->request)
+		goto e_unmap;
+
+	snp_dev->response = alloc_shared_pages(dev, sizeof(struct snp_guest_msg));
+	if (!snp_dev->response)
+		goto e_free_request;
+
+	snp_dev->certs_data = alloc_shared_pages(dev, SEV_FW_BLOB_MAX_SIZE);
+	if (!snp_dev->certs_data)
+		goto e_free_response;
+
+	ret = -EIO;
+	snp_dev->crypto = init_crypto(snp_dev, snp_dev->vmpck, VMPCK_KEY_LEN);
+	if (!snp_dev->crypto)
+		goto e_free_cert_data;
+
+	misc = &snp_dev->misc;
+	misc->minor = MISC_DYNAMIC_MINOR;
+	misc->name = DEVICE_NAME;
+	misc->fops = &snp_guest_fops;
+
+	/* initial the input address for guest request */
+	snp_dev->input.req_gpa = __pa(snp_dev->request);
+	snp_dev->input.resp_gpa = __pa(snp_dev->response);
+	snp_dev->input.data_gpa = __pa(snp_dev->certs_data);
+
+	ret =  misc_register(misc);
+	if (ret)
+		goto e_free_cert_data;
+
+	dev_info(dev, "Initialized SEV guest driver (using vmpck_id %d)\n", vmpck_id);
+	return 0;
+
+e_free_cert_data:
+	free_shared_pages(snp_dev->certs_data, SEV_FW_BLOB_MAX_SIZE);
+e_free_response:
+	free_shared_pages(snp_dev->response, sizeof(struct snp_guest_msg));
+e_free_request:
+	free_shared_pages(snp_dev->request, sizeof(struct snp_guest_msg));
+e_unmap:
+	iounmap(mapping);
+	return ret;
+}
+
+static int __exit sev_guest_remove(struct platform_device *pdev)
+{
+	struct snp_guest_dev *snp_dev = platform_get_drvdata(pdev);
+
+	free_shared_pages(snp_dev->certs_data, SEV_FW_BLOB_MAX_SIZE);
+	free_shared_pages(snp_dev->response, sizeof(struct snp_guest_msg));
+	free_shared_pages(snp_dev->request, sizeof(struct snp_guest_msg));
+	deinit_crypto(snp_dev->crypto);
+	misc_deregister(&snp_dev->misc);
+
+	return 0;
+}
+
+/*
+ * This driver is meant to be a common SEV guest interface driver and to
+ * support any SEV guest API. As such, even though it has been introduced
+ * with the SEV-SNP support, it is named "sev-guest".
+ */
+static struct platform_driver sev_guest_driver = {
+	.remove		= __exit_p(sev_guest_remove),
+	.driver		= {
+		.name = "sev-guest",
+	},
+};
+
+module_platform_driver_probe(sev_guest_driver, sev_guest_probe);
+
+MODULE_AUTHOR("Brijesh Singh <brijesh.singh@amd.com>");
+MODULE_LICENSE("GPL");
+MODULE_VERSION("1.0.0");
+MODULE_DESCRIPTION("AMD SEV Guest Driver");
+MODULE_ALIAS("platform:sev-guest");
diff --git a/drivers/virt/coco/sev-guest/sev-guest.h b/drivers/virt/coco/sev-guest/sev-guest.h
new file mode 100644
index 000000000..21bda26fd
--- /dev/null
+++ b/drivers/virt/coco/sev-guest/sev-guest.h
@@ -0,0 +1,63 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2021 Advanced Micro Devices, Inc.
+ *
+ * Author: Brijesh Singh <brijesh.singh@amd.com>
+ *
+ * SEV-SNP API spec is available at https://developer.amd.com/sev
+ */
+
+#ifndef __VIRT_SEVGUEST_H__
+#define __VIRT_SEVGUEST_H__
+
+#include <linux/types.h>
+
+#define MAX_AUTHTAG_LEN		32
+
+/* See SNP spec SNP_GUEST_REQUEST section for the structure */
+enum msg_type {
+	SNP_MSG_TYPE_INVALID = 0,
+	SNP_MSG_CPUID_REQ,
+	SNP_MSG_CPUID_RSP,
+	SNP_MSG_KEY_REQ,
+	SNP_MSG_KEY_RSP,
+	SNP_MSG_REPORT_REQ,
+	SNP_MSG_REPORT_RSP,
+	SNP_MSG_EXPORT_REQ,
+	SNP_MSG_EXPORT_RSP,
+	SNP_MSG_IMPORT_REQ,
+	SNP_MSG_IMPORT_RSP,
+	SNP_MSG_ABSORB_REQ,
+	SNP_MSG_ABSORB_RSP,
+	SNP_MSG_VMRK_REQ,
+	SNP_MSG_VMRK_RSP,
+
+	SNP_MSG_TYPE_MAX
+};
+
+enum aead_algo {
+	SNP_AEAD_INVALID,
+	SNP_AEAD_AES_256_GCM,
+};
+
+struct snp_guest_msg_hdr {
+	u8 authtag[MAX_AUTHTAG_LEN];
+	u64 msg_seqno;
+	u8 rsvd1[8];
+	u8 algo;
+	u8 hdr_version;
+	u16 hdr_sz;
+	u8 msg_type;
+	u8 msg_version;
+	u16 msg_sz;
+	u32 rsvd2;
+	u8 msg_vmpck;
+	u8 rsvd3[35];
+} __packed;
+
+struct snp_guest_msg {
+	struct snp_guest_msg_hdr hdr;
+	u8 payload[4000];
+} __packed;
+
+#endif /* __VIRT_SEVGUEST_H__ */
diff --git a/drivers/virt/coco/tdx-guest/Kconfig b/drivers/virt/coco/tdx-guest/Kconfig
new file mode 100644
index 000000000..14246fc2f
--- /dev/null
+++ b/drivers/virt/coco/tdx-guest/Kconfig
@@ -0,0 +1,10 @@
+config TDX_GUEST_DRIVER
+	tristate "TDX Guest driver"
+	depends on INTEL_TDX_GUEST
+	help
+	  The driver provides userspace interface to communicate with
+	  the TDX module to request the TDX guest details like attestation
+	  report.
+
+	  To compile this driver as module, choose M here. The module will
+	  be called tdx-guest.
diff --git a/drivers/virt/coco/tdx-guest/Makefile b/drivers/virt/coco/tdx-guest/Makefile
new file mode 100644
index 000000000..775cb463f
--- /dev/null
+++ b/drivers/virt/coco/tdx-guest/Makefile
@@ -0,0 +1,2 @@
+# SPDX-License-Identifier: GPL-2.0
+obj-$(CONFIG_TDX_GUEST_DRIVER) += tdx-guest.o
diff --git a/drivers/virt/coco/tdx-guest/tdx-guest.c b/drivers/virt/coco/tdx-guest/tdx-guest.c
new file mode 100644
index 000000000..5e44a0fa6
--- /dev/null
+++ b/drivers/virt/coco/tdx-guest/tdx-guest.c
@@ -0,0 +1,102 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * TDX guest user interface driver
+ *
+ * Copyright (C) 2022 Intel Corporation
+ */
+
+#include <linux/kernel.h>
+#include <linux/miscdevice.h>
+#include <linux/mm.h>
+#include <linux/module.h>
+#include <linux/mod_devicetable.h>
+#include <linux/string.h>
+#include <linux/uaccess.h>
+
+#include <uapi/linux/tdx-guest.h>
+
+#include <asm/cpu_device_id.h>
+#include <asm/tdx.h>
+
+static long tdx_get_report0(struct tdx_report_req __user *req)
+{
+	u8 *reportdata, *tdreport;
+	long ret;
+
+	reportdata = kmalloc(TDX_REPORTDATA_LEN, GFP_KERNEL);
+	if (!reportdata)
+		return -ENOMEM;
+
+	tdreport = kzalloc(TDX_REPORT_LEN, GFP_KERNEL);
+	if (!tdreport) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	if (copy_from_user(reportdata, req->reportdata, TDX_REPORTDATA_LEN)) {
+		ret = -EFAULT;
+		goto out;
+	}
+
+	/* Generate TDREPORT0 using "TDG.MR.REPORT" TDCALL */
+	ret = tdx_mcall_get_report0(reportdata, tdreport);
+	if (ret)
+		goto out;
+
+	if (copy_to_user(req->tdreport, tdreport, TDX_REPORT_LEN))
+		ret = -EFAULT;
+
+out:
+	kfree(reportdata);
+	kfree(tdreport);
+
+	return ret;
+}
+
+static long tdx_guest_ioctl(struct file *file, unsigned int cmd,
+			    unsigned long arg)
+{
+	switch (cmd) {
+	case TDX_CMD_GET_REPORT0:
+		return tdx_get_report0((struct tdx_report_req __user *)arg);
+	default:
+		return -ENOTTY;
+	}
+}
+
+static const struct file_operations tdx_guest_fops = {
+	.owner = THIS_MODULE,
+	.unlocked_ioctl = tdx_guest_ioctl,
+	.llseek = no_llseek,
+};
+
+static struct miscdevice tdx_misc_dev = {
+	.name = KBUILD_MODNAME,
+	.minor = MISC_DYNAMIC_MINOR,
+	.fops = &tdx_guest_fops,
+};
+
+static const struct x86_cpu_id tdx_guest_ids[] = {
+	X86_MATCH_FEATURE(X86_FEATURE_TDX_GUEST, NULL),
+	{}
+};
+MODULE_DEVICE_TABLE(x86cpu, tdx_guest_ids);
+
+static int __init tdx_guest_init(void)
+{
+	if (!x86_match_cpu(tdx_guest_ids))
+		return -ENODEV;
+
+	return misc_register(&tdx_misc_dev);
+}
+module_init(tdx_guest_init);
+
+static void __exit tdx_guest_exit(void)
+{
+	misc_deregister(&tdx_misc_dev);
+}
+module_exit(tdx_guest_exit);
+
+MODULE_AUTHOR("Kuppuswamy Sathyanarayanan <sathyanarayanan.kuppuswamy@linux.intel.com>");
+MODULE_DESCRIPTION("TDX Guest Driver");
+MODULE_LICENSE("GPL");