summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
-rw-r--r--Documentation/admin-guide/kernel-parameters.txt2
-rw-r--r--Documentation/virt/coco/sev-guest.rst155
-rw-r--r--Documentation/virt/index.rst1
-rw-r--r--Documentation/x86/x86_64/boot-options.rst14
-rw-r--r--Documentation/x86/zero-page.rst2
-rw-r--r--arch/x86/boot/compressed/Makefile1
-rw-r--r--arch/x86/boot/compressed/acpi.c176
-rw-r--r--arch/x86/boot/compressed/early_serial_console.c3
-rw-r--r--arch/x86/boot/compressed/efi.c234
-rw-r--r--arch/x86/boot/compressed/efi.h126
-rw-r--r--arch/x86/boot/compressed/head_64.S37
-rw-r--r--arch/x86/boot/compressed/ident_map_64.c39
-rw-r--r--arch/x86/boot/compressed/idt_64.c18
-rw-r--r--arch/x86/boot/compressed/kaslr.c3
-rw-r--r--arch/x86/boot/compressed/mem_encrypt.S36
-rw-r--r--arch/x86/boot/compressed/misc.c5
-rw-r--r--arch/x86/boot/compressed/misc.h56
-rw-r--r--arch/x86/boot/compressed/pgtable_64.c3
-rw-r--r--arch/x86/boot/compressed/sev.c263
-rw-r--r--arch/x86/boot/cpucheck.c30
-rw-r--r--arch/x86/boot/msr.h26
-rw-r--r--arch/x86/coco/core.c3
-rw-r--r--arch/x86/entry/entry_64.S6
-rw-r--r--arch/x86/entry/entry_64_compat.S5
-rw-r--r--arch/x86/include/asm/bootparam_utils.h1
-rw-r--r--arch/x86/include/asm/cpuid.h34
-rw-r--r--arch/x86/include/asm/msr-index.h2
-rw-r--r--arch/x86/include/asm/msr.h11
-rw-r--r--arch/x86/include/asm/proto.h4
-rw-r--r--arch/x86/include/asm/ptrace.h4
-rw-r--r--arch/x86/include/asm/setup.h1
-rw-r--r--arch/x86/include/asm/sev-common.h82
-rw-r--r--arch/x86/include/asm/sev.h137
-rw-r--r--arch/x86/include/asm/shared/msr.h15
-rw-r--r--arch/x86/include/asm/svm.h171
-rw-r--r--arch/x86/include/uapi/asm/bootparam.h4
-rw-r--r--arch/x86/include/uapi/asm/svm.h13
-rw-r--r--arch/x86/kernel/Makefile2
-rw-r--r--arch/x86/kernel/cpu/common.c4
-rw-r--r--arch/x86/kernel/head64.c29
-rw-r--r--arch/x86/kernel/head_64.S37
-rw-r--r--arch/x86/kernel/probe_roms.c13
-rw-r--r--arch/x86/kernel/sev-shared.c534
-rw-r--r--arch/x86/kernel/sev.c855
-rw-r--r--arch/x86/kernel/smpboot.c3
-rw-r--r--arch/x86/kvm/cpuid.c19
-rw-r--r--arch/x86/kvm/svm/sev.c22
-rw-r--r--arch/x86/kvm/svm/svm.c8
-rw-r--r--arch/x86/kvm/svm/svm.h4
-rw-r--r--arch/x86/mm/mem_encrypt.c4
-rw-r--r--arch/x86/mm/mem_encrypt_amd.c71
-rw-r--r--arch/x86/mm/mem_encrypt_identity.c8
-rw-r--r--arch/x86/realmode/init.c2
-rw-r--r--drivers/virt/Kconfig2
-rw-r--r--drivers/virt/Makefile1
-rw-r--r--drivers/virt/coco/sev-guest/Kconfig14
-rw-r--r--drivers/virt/coco/sev-guest/Makefile2
-rw-r--r--drivers/virt/coco/sev-guest/sev-guest.c743
-rw-r--r--drivers/virt/coco/sev-guest/sev-guest.h63
-rw-r--r--include/linux/cc_platform.h8
-rw-r--r--include/linux/efi.h1
-rw-r--r--include/uapi/linux/sev-guest.h80
62 files changed, 3860 insertions, 392 deletions
diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index 297c852c53f8..0c648a867dfa 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -5383,6 +5383,8 @@
serialnumber [BUGS=X86-32]
+ sev=option[,option...] [X86-64] See Documentation/x86/x86_64/boot-options.rst
+
shapers= [NET]
Maximal number of shapers.
diff --git a/Documentation/virt/coco/sev-guest.rst b/Documentation/virt/coco/sev-guest.rst
new file mode 100644
index 000000000000..bf593e88cfd9
--- /dev/null
+++ b/Documentation/virt/coco/sev-guest.rst
@@ -0,0 +1,155 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+===================================================================
+The Definitive SEV Guest API Documentation
+===================================================================
+
+1. General description
+======================
+
+The SEV API is a set of ioctls that are used by the guest or hypervisor
+to get or set a certain aspect of the SEV virtual machine. The ioctls belong
+to the following classes:
+
+ - Hypervisor ioctls: These query and set global attributes which affect the
+ whole SEV firmware. These ioctl are used by platform provisioning tools.
+
+ - Guest ioctls: These query and set attributes of the SEV virtual machine.
+
+2. API description
+==================
+
+This section describes ioctls that is used for querying the SEV guest report
+from the SEV firmware. For each ioctl, the following information is provided
+along with a description:
+
+ Technology:
+ which SEV technology provides this ioctl. SEV, SEV-ES, SEV-SNP or all.
+
+ Type:
+ hypervisor or guest. The ioctl can be used inside the guest or the
+ hypervisor.
+
+ Parameters:
+ what parameters are accepted by the ioctl.
+
+ Returns:
+ the return value. General error numbers (-ENOMEM, -EINVAL)
+ are not detailed, but errors with specific meanings are.
+
+The guest ioctl should be issued on a file descriptor of the /dev/sev-guest device.
+The ioctl accepts struct snp_user_guest_request. The input and output structure is
+specified through the req_data and resp_data field respectively. If the ioctl fails
+to execute due to a firmware error, then fw_err code will be set otherwise the
+fw_err will be set to 0x00000000000000ff.
+
+The firmware checks that the message sequence counter is one greater than
+the guests message sequence counter. If guest driver fails to increment message
+counter (e.g. counter overflow), then -EIO will be returned.
+
+::
+
+ struct snp_guest_request_ioctl {
+ /* Message version number */
+ __u32 msg_version;
+
+ /* Request and response structure address */
+ __u64 req_data;
+ __u64 resp_data;
+
+ /* firmware error code on failure (see psp-sev.h) */
+ __u64 fw_err;
+ };
+
+2.1 SNP_GET_REPORT
+------------------
+
+:Technology: sev-snp
+:Type: guest ioctl
+:Parameters (in): struct snp_report_req
+:Returns (out): struct snp_report_resp on success, -negative on error
+
+The SNP_GET_REPORT ioctl can be used to query the attestation report from the
+SEV-SNP firmware. The ioctl uses the SNP_GUEST_REQUEST (MSG_REPORT_REQ) command
+provided by the SEV-SNP firmware to query the attestation report.
+
+On success, the snp_report_resp.data will contains the report. The report
+contain the format described in the SEV-SNP specification. See the SEV-SNP
+specification for further details.
+
+2.2 SNP_GET_DERIVED_KEY
+-----------------------
+:Technology: sev-snp
+:Type: guest ioctl
+:Parameters (in): struct snp_derived_key_req
+:Returns (out): struct snp_derived_key_resp on success, -negative on error
+
+The SNP_GET_DERIVED_KEY ioctl can be used to get a key derive from a root key.
+The derived key can be used by the guest for any purpose, such as sealing keys
+or communicating with external entities.
+
+The ioctl uses the SNP_GUEST_REQUEST (MSG_KEY_REQ) command provided by the
+SEV-SNP firmware to derive the key. See SEV-SNP specification for further details
+on the various fields passed in the key derivation request.
+
+On success, the snp_derived_key_resp.data contains the derived key value. See
+the SEV-SNP specification for further details.
+
+
+2.3 SNP_GET_EXT_REPORT
+----------------------
+:Technology: sev-snp
+:Type: guest ioctl
+:Parameters (in/out): struct snp_ext_report_req
+:Returns (out): struct snp_report_resp on success, -negative on error
+
+The SNP_GET_EXT_REPORT ioctl is similar to the SNP_GET_REPORT. The difference is
+related to the additional certificate data that is returned with the report.
+The certificate data returned is being provided by the hypervisor through the
+SNP_SET_EXT_CONFIG.
+
+The ioctl uses the SNP_GUEST_REQUEST (MSG_REPORT_REQ) command provided by the SEV-SNP
+firmware to get the attestation report.
+
+On success, the snp_ext_report_resp.data will contain the attestation report
+and snp_ext_report_req.certs_address will contain the certificate blob. If the
+length of the blob is smaller than expected then snp_ext_report_req.certs_len will
+be updated with the expected value.
+
+See GHCB specification for further detail on how to parse the certificate blob.
+
+3. SEV-SNP CPUID Enforcement
+============================
+
+SEV-SNP guests can access a special page that contains a table of CPUID values
+that have been validated by the PSP as part of the SNP_LAUNCH_UPDATE firmware
+command. It provides the following assurances regarding the validity of CPUID
+values:
+
+ - Its address is obtained via bootloader/firmware (via CC blob), and those
+ binaries will be measured as part of the SEV-SNP attestation report.
+ - Its initial state will be encrypted/pvalidated, so attempts to modify
+ it during run-time will result in garbage being written, or #VC exceptions
+ being generated due to changes in validation state if the hypervisor tries
+ to swap the backing page.
+ - Attempts to bypass PSP checks by the hypervisor by using a normal page, or
+ a non-CPUID encrypted page will change the measurement provided by the
+ SEV-SNP attestation report.
+ - The CPUID page contents are *not* measured, but attempts to modify the
+ expected contents of a CPUID page as part of guest initialization will be
+ gated by the PSP CPUID enforcement policy checks performed on the page
+ during SNP_LAUNCH_UPDATE, and noticeable later if the guest owner
+ implements their own checks of the CPUID values.
+
+It is important to note that this last assurance is only useful if the kernel
+has taken care to make use of the SEV-SNP CPUID throughout all stages of boot.
+Otherwise, guest owner attestation provides no assurance that the kernel wasn't
+fed incorrect values at some point during boot.
+
+
+Reference
+---------
+
+SEV-SNP and GHCB specification: developer.amd.com/sev
+
+The driver is based on SEV-SNP firmware spec 0.9 and GHCB spec version 2.0.
diff --git a/Documentation/virt/index.rst b/Documentation/virt/index.rst
index edea7fea95a8..492f0920b988 100644
--- a/Documentation/virt/index.rst
+++ b/Documentation/virt/index.rst
@@ -13,6 +13,7 @@ Linux Virtualization Support
guest-halt-polling
ne_overview
acrn/index
+ coco/sev-guest
.. only:: html and subproject
diff --git a/Documentation/x86/x86_64/boot-options.rst b/Documentation/x86/x86_64/boot-options.rst
index 07aa0007f346..4efb1fa039ef 100644
--- a/Documentation/x86/x86_64/boot-options.rst
+++ b/Documentation/x86/x86_64/boot-options.rst
@@ -310,3 +310,17 @@ Miscellaneous
Do not use GB pages for kernel direct mappings.
gbpages
Use GB pages for kernel direct mappings.
+
+
+AMD SEV (Secure Encrypted Virtualization)
+=========================================
+Options relating to AMD SEV, specified via the following format:
+
+::
+
+ sev=option1[,option2]
+
+The available options are:
+
+ debug
+ Enable debug messages.
diff --git a/Documentation/x86/zero-page.rst b/Documentation/x86/zero-page.rst
index f088f5881666..45aa9cceb4f1 100644
--- a/Documentation/x86/zero-page.rst
+++ b/Documentation/x86/zero-page.rst
@@ -19,6 +19,7 @@ Offset/Size Proto Name Meaning
058/008 ALL tboot_addr Physical address of tboot shared page
060/010 ALL ist_info Intel SpeedStep (IST) BIOS support information
(struct ist_info)
+070/008 ALL acpi_rsdp_addr Physical address of ACPI RSDP table
080/010 ALL hd0_info hd0 disk parameter, OBSOLETE!!
090/010 ALL hd1_info hd1 disk parameter, OBSOLETE!!
0A0/010 ALL sys_desc_table System description table (struct sys_desc_table),
@@ -27,6 +28,7 @@ Offset/Size Proto Name Meaning
0C0/004 ALL ext_ramdisk_image ramdisk_image high 32bits
0C4/004 ALL ext_ramdisk_size ramdisk_size high 32bits
0C8/004 ALL ext_cmd_line_ptr cmd_line_ptr high 32bits
+13C/004 ALL cc_blob_address Physical address of Confidential Computing blob
140/080 ALL edid_info Video mode setup (struct edid_info)
1C0/020 ALL efi_info EFI 32 information (struct efi_info)
1E0/004 ALL alt_mem_k Alternative mem check, in KB
diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile
index 6115274fe10f..e69c3d2e0628 100644
--- a/arch/x86/boot/compressed/Makefile
+++ b/arch/x86/boot/compressed/Makefile
@@ -103,6 +103,7 @@ endif
vmlinux-objs-$(CONFIG_ACPI) += $(obj)/acpi.o
vmlinux-objs-$(CONFIG_EFI_MIXED) += $(obj)/efi_thunk_$(BITS).o
+vmlinux-objs-$(CONFIG_EFI) += $(obj)/efi.o
efi-obj-$(CONFIG_EFI_STUB) = $(objtree)/drivers/firmware/efi/libstub/lib.a
$(obj)/vmlinux: $(vmlinux-objs-y) $(efi-obj-y) FORCE
diff --git a/arch/x86/boot/compressed/acpi.c b/arch/x86/boot/compressed/acpi.c
index 8bcbcee54aa1..9caf89063e77 100644
--- a/arch/x86/boot/compressed/acpi.c
+++ b/arch/x86/boot/compressed/acpi.c
@@ -3,10 +3,9 @@
#include "misc.h"
#include "error.h"
#include "../string.h"
+#include "efi.h"
#include <linux/numa.h>
-#include <linux/efi.h>
-#include <asm/efi.h>
/*
* Longest parameter of 'acpi=' is 'copy_dsdt', plus an extra '\0'
@@ -20,153 +19,56 @@
*/
struct mem_vector immovable_mem[MAX_NUMNODES*2];
-/*
- * Search EFI system tables for RSDP. If both ACPI_20_TABLE_GUID and
- * ACPI_TABLE_GUID are found, take the former, which has more features.
- */
static acpi_physical_address
-__efi_get_rsdp_addr(unsigned long config_tables, unsigned int nr_tables,
- bool efi_64)
+__efi_get_rsdp_addr(unsigned long cfg_tbl_pa, unsigned int cfg_tbl_len)
{
- acpi_physical_address rsdp_addr = 0;
-
#ifdef CONFIG_EFI
- int i;
-
- /* Get EFI tables from systab. */
- for (i = 0; i < nr_tables; i++) {
- acpi_physical_address table;
- efi_guid_t guid;
-
- if (efi_64) {
- efi_config_table_64_t *tbl = (efi_config_table_64_t *)config_tables + i;
-
- guid = tbl->guid;
- table = tbl->table;
-
- if (!IS_ENABLED(CONFIG_X86_64) && table >> 32) {
- debug_putstr("Error getting RSDP address: EFI config table located above 4GB.\n");
- return 0;
- }
- } else {
- efi_config_table_32_t *tbl = (efi_config_table_32_t *)config_tables + i;
-
- guid = tbl->guid;
- table = tbl->table;
- }
+ unsigned long rsdp_addr;
+ int ret;
- if (!(efi_guidcmp(guid, ACPI_TABLE_GUID)))
- rsdp_addr = table;
- else if (!(efi_guidcmp(guid, ACPI_20_TABLE_GUID)))
- return table;
- }
+ /*
+ * Search EFI system tables for RSDP. Preferred is ACPI_20_TABLE_GUID to
+ * ACPI_TABLE_GUID because it has more features.
+ */
+ rsdp_addr = efi_find_vendor_table(boot_params, cfg_tbl_pa, cfg_tbl_len,
+ ACPI_20_TABLE_GUID);
+ if (rsdp_addr)
+ return (acpi_physical_address)rsdp_addr;
+
+ /* No ACPI_20_TABLE_GUID found, fallback to ACPI_TABLE_GUID. */
+ rsdp_addr = efi_find_vendor_table(boot_params, cfg_tbl_pa, cfg_tbl_len,
+ ACPI_TABLE_GUID);
+ if (rsdp_addr)
+ return (acpi_physical_address)rsdp_addr;
+
+ debug_putstr("Error getting RSDP address.\n");
#endif
- return rsdp_addr;
-}
-
-/* EFI/kexec support is 64-bit only. */
-#ifdef CONFIG_X86_64
-static struct efi_setup_data *get_kexec_setup_data_addr(void)
-{
- struct setup_data *data;
- u64 pa_data;
-
- pa_data = boot_params->hdr.setup_data;
- while (pa_data) {
- data = (struct setup_data *)pa_data;
- if (data->type == SETUP_EFI)
- return (struct efi_setup_data *)(pa_data + sizeof(struct setup_data));
-
- pa_data = data->next;
- }
- return NULL;
-}
-
-static acpi_physical_address kexec_get_rsdp_addr(void)
-{
- efi_system_table_64_t *systab;
- struct efi_setup_data *esd;
- struct efi_info *ei;
- char *sig;
-
- esd = (struct efi_setup_data *)get_kexec_setup_data_addr();
- if (!esd)
- return 0;
-
- if (!esd->tables) {
- debug_putstr("Wrong kexec SETUP_EFI data.\n");
- return 0;
- }
-
- ei = &boot_params->efi_info;
- sig = (char *)&ei->efi_loader_signature;
- if (strncmp(sig, EFI64_LOADER_SIGNATURE, 4)) {
- debug_putstr("Wrong kexec EFI loader signature.\n");
- return 0;
- }
-
- /* Get systab from boot params. */
- systab = (efi_system_table_64_t *) (ei->efi_systab | ((__u64)ei->efi_systab_hi << 32));
- if (!systab)
- error("EFI system table not found in kexec boot_params.");
-
- return __efi_get_rsdp_addr((unsigned long)esd->tables, systab->nr_tables, true);
+ return 0;
}
-#else
-static acpi_physical_address kexec_get_rsdp_addr(void) { return 0; }
-#endif /* CONFIG_X86_64 */
static acpi_physical_address efi_get_rsdp_addr(void)
{
#ifdef CONFIG_EFI
- unsigned long systab, config_tables;
+ unsigned long cfg_tbl_pa = 0;
+ unsigned int cfg_tbl_len;
+ unsigned long systab_pa;
unsigned int nr_tables;
- struct efi_info *ei;
- bool efi_64;
- char *sig;
-
- ei = &boot_params->efi_info;
- sig = (char *)&ei->efi_loader_signature;
-
- if (!strncmp(sig, EFI64_LOADER_SIGNATURE, 4)) {
- efi_64 = true;
- } else if (!strncmp(sig, EFI32_LOADER_SIGNATURE, 4)) {
- efi_64 = false;
- } else {
- debug_putstr("Wrong EFI loader signature.\n");
- return 0;
- }
+ enum efi_type et;
+ int ret;
- /* Get systab from boot params. */
-#ifdef CONFIG_X86_64
- systab = ei->efi_systab | ((__u64)ei->efi_systab_hi << 32);
-#else
- if (ei->efi_systab_hi || ei->efi_memmap_hi) {
- debug_putstr("Error getting RSDP address: EFI system table located above 4GB.\n");
+ et = efi_get_type(boot_params);
+ if (et == EFI_TYPE_NONE)
return 0;
- }
- systab = ei->efi_systab;
-#endif
- if (!systab)
- error("EFI system table not found.");
- /* Handle EFI bitness properly */
- if (efi_64) {
- efi_system_table_64_t *stbl = (efi_system_table_64_t *)systab;
+ systab_pa = efi_get_system_table(boot_params);
+ if (!systab_pa)
+ error("EFI support advertised, but unable to locate system table.");
- config_tables = stbl->tables;
- nr_tables = stbl->nr_tables;
- } else {
- efi_system_table_32_t *stbl = (efi_system_table_32_t *)systab;
+ ret = efi_get_conf_table(boot_params, &cfg_tbl_pa, &cfg_tbl_len);
+ if (ret || !cfg_tbl_pa)
+ error("EFI config table not found.");
- config_tables = stbl->tables;
- nr_tables = stbl->nr_tables;
- }
-
- if (!config_tables)
- error("EFI config tables not found.");
-
- return __efi_get_rsdp_addr(config_tables, nr_tables, efi_64);
+ return __efi_get_rsdp_addr(cfg_tbl_pa, cfg_tbl_len);
#else
return 0;
#endif
@@ -256,14 +158,6 @@ acpi_physical_address get_rsdp_addr(void)
pa = boot_params->acpi_rsdp_addr;
- /*
- * Try to get EFI data from setup_data. This can happen when we're a
- * kexec'ed kernel and kexec(1) has passed all the required EFI info to
- * us.
- */
- if (!pa)
- pa = kexec_get_rsdp_addr();
-
if (!pa)
pa = efi_get_rsdp_addr();
diff --git a/arch/x86/boot/compressed/early_serial_console.c b/arch/x86/boot/compressed/early_serial_console.c
index 261e81fb9582..70a8d1706d0f 100644
--- a/arch/x86/boot/compressed/early_serial_console.c
+++ b/arch/x86/boot/compressed/early_serial_console.c
@@ -1,5 +1,6 @@
#include "misc.h"
-int early_serial_base;
+/* This might be accessed before .bss is cleared, so use .data instead. */
+int early_serial_base __section(".data");
#include "../early_serial_console.c"
diff --git a/arch/x86/boot/compressed/efi.c b/arch/x86/boot/compressed/efi.c
new file mode 100644
index 000000000000..6edd034b0b30
--- /dev/null
+++ b/arch/x86/boot/compressed/efi.c
@@ -0,0 +1,234 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Helpers for early access to EFI configuration table.
+ *
+ * Originally derived from arch/x86/boot/compressed/acpi.c
+ */
+
+#include "misc.h"
+
+/**
+ * efi_get_type - Given a pointer to boot_params, determine the type of EFI environment.
+ *
+ * @bp: pointer to boot_params
+ *
+ * Return: EFI_TYPE_{32,64} for valid EFI environments, EFI_TYPE_NONE otherwise.
+ */
+enum efi_type efi_get_type(struct boot_params *bp)
+{
+ struct efi_info *ei;
+ enum efi_type et;
+ const char *sig;
+
+ ei = &bp->efi_info;
+ sig = (char *)&ei->efi_loader_signature;
+
+ if (!strncmp(sig, EFI64_LOADER_SIGNATURE, 4)) {
+ et = EFI_TYPE_64;
+ } else if (!strncmp(sig, EFI32_LOADER_SIGNATURE, 4)) {
+ et = EFI_TYPE_32;
+ } else {
+ debug_putstr("No EFI environment detected.\n");
+ et = EFI_TYPE_NONE;
+ }
+
+#ifndef CONFIG_X86_64
+ /*
+ * Existing callers like acpi.c treat this case as an indicator to
+ * fall-through to non-EFI, rather than an error, so maintain that
+ * functionality here as well.
+ */
+ if (ei->efi_systab_hi || ei->efi_memmap_hi) {
+ debug_putstr("EFI system table is located above 4GB and cannot be accessed.\n");
+ et = EFI_TYPE_NONE;
+ }
+#endif
+
+ return et;
+}
+
+/**
+ * efi_get_system_table - Given a pointer to boot_params, retrieve the physical address
+ * of the EFI system table.
+ *
+ * @bp: pointer to boot_params
+ *
+ * Return: EFI system table address on success. On error, return 0.
+ */
+unsigned long efi_get_system_table(struct boot_params *bp)
+{
+ unsigned long sys_tbl_pa;
+ struct efi_info *ei;
+ enum efi_type et;
+
+ /* Get systab from boot params. */
+ ei = &bp->efi_info;
+#ifdef CONFIG_X86_64
+ sys_tbl_pa = ei->efi_systab | ((__u64)ei->efi_systab_hi << 32);
+#else
+ sys_tbl_pa = ei->efi_systab;
+#endif
+ if (!sys_tbl_pa) {
+ debug_putstr("EFI system table not found.");
+ return 0;
+ }
+
+ return sys_tbl_pa;
+}
+
+/*
+ * EFI config table address changes to virtual address after boot, which may
+ * not be accessible for the kexec'd kernel. To address this, kexec provides
+ * the initial physical address via a struct setup_data entry, which is
+ * checked for here, along with some sanity checks.
+ */
+static struct efi_setup_data *get_kexec_setup_data(struct boot_params *bp,
+ enum efi_type et)
+{
+#ifdef CONFIG_X86_64
+ struct efi_setup_data *esd = NULL;
+ struct setup_data *data;
+ u64 pa_data;
+
+ pa_data = bp->hdr.setup_data;
+ while (pa_data) {
+ data = (struct setup_data *)pa_data;
+ if (data->type == SETUP_EFI) {
+ esd = (struct efi_setup_data *)(pa_data + sizeof(struct setup_data));
+ break;
+ }
+
+ pa_data = data->next;
+ }
+
+ /*
+ * Original ACPI code falls back to attempting normal EFI boot in these
+ * cases, so maintain existing behavior by indicating non-kexec
+ * environment to the caller, but print them for debugging.
+ */
+ if (esd && !esd->tables) {
+ debug_putstr("kexec EFI environment missing valid configuration table.\n");
+ return NULL;
+ }
+
+ return esd;
+#endif
+ return NULL;
+}
+
+/**
+ * efi_get_conf_table - Given a pointer to boot_params, locate and return the physical
+ * address of EFI configuration table.
+ *
+ * @bp: pointer to boot_params
+ * @cfg_tbl_pa: location to store physical address of config table
+ * @cfg_tbl_len: location to store number of config table entries
+ *
+ * Return: 0 on success. On error, return params are left unchanged.
+ */
+int efi_get_conf_table(struct boot_params *bp, unsigned long *cfg_tbl_pa,
+ unsigned int *cfg_tbl_len)
+{
+ unsigned long sys_tbl_pa;
+ enum efi_type et;
+ int ret;
+
+ if (!cfg_tbl_pa || !cfg_tbl_len)
+ return -EINVAL;
+
+ sys_tbl_pa = efi_get_system_table(bp);
+ if (!sys_tbl_pa)
+ return -EINVAL;
+
+ /* Handle EFI bitness properly */
+ et = efi_get_type(bp);
+ if (et == EFI_TYPE_64) {
+ efi_system_table_64_t *stbl = (efi_system_table_64_t *)sys_tbl_pa;
+ struct efi_setup_data *esd;
+
+ /* kexec provides an alternative EFI conf table, check for it. */
+ esd = get_kexec_setup_data(bp, et);
+
+ *cfg_tbl_pa = esd ? esd->tables : stbl->tables;
+ *cfg_tbl_len = stbl->nr_tables;
+ } else if (et == EFI_TYPE_32) {
+ efi_system_table_32_t *stbl = (efi_system_table_32_t *)sys_tbl_pa;
+
+ *cfg_tbl_pa = stbl->tables;
+ *cfg_tbl_len = stbl->nr_tables;
+ } else {
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+/* Get vendor table address/guid from EFI config table at the given index */
+static int get_vendor_table(void *cfg_tbl, unsigned int idx,
+ unsigned long *vendor_tbl_pa,
+ efi_guid_t *vendor_tbl_guid,
+ enum efi_type et)
+{
+ if (et == EFI_TYPE_64) {
+ efi_config_table_64_t *tbl_entry = (efi_config_table_64_t *)cfg_tbl + idx;
+
+ if (!IS_ENABLED(CONFIG_X86_64) && tbl_entry->table >> 32) {
+ debug_putstr("Error: EFI config table entry located above 4GB.\n");
+ return -EINVAL;
+ }
+
+ *vendor_tbl_pa = tbl_entry->table;
+ *vendor_tbl_guid = tbl_entry->guid;
+
+ } else if (et == EFI_TYPE_32) {
+ efi_config_table_32_t *tbl_entry = (efi_config_table_32_t *)cfg_tbl + idx;
+
+ *vendor_tbl_pa = tbl_entry->table;
+ *vendor_tbl_guid = tbl_entry->guid;
+ } else {
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+/**
+ * efi_find_vendor_table - Given EFI config table, search it for the physical
+ * address of the vendor table associated with GUID.
+ *
+ * @bp: pointer to boot_params
+ * @cfg_tbl_pa: pointer to EFI configuration table
+ * @cfg_tbl_len: number of entries in EFI configuration table
+ * @guid: GUID of vendor table
+ *
+ * Return: vendor table address on success. On error, return 0.
+ */
+unsigned long efi_find_vendor_table(struct boot_params *bp,
+ unsigned long cfg_tbl_pa,
+ unsigned int cfg_tbl_len,
+ efi_guid_t guid)
+{
+ enum efi_type et;
+ unsigned int i;
+
+ et = efi_get_type(bp);
+ if (et == EFI_TYPE_NONE)
+ return 0;
+
+ for (i = 0; i < cfg_tbl_len; i++) {
+ unsigned long vendor_tbl_pa;
+ efi_guid_t vendor_tbl_guid;
+ int ret;
+
+ ret = get_vendor_table((void *)cfg_tbl_pa, i,
+ &vendor_tbl_pa,
+ &vendor_tbl_guid, et);
+ if (ret)
+ return 0;
+
+ if (!efi_guidcmp(guid, vendor_tbl_guid))
+ return vendor_tbl_pa;
+ }
+
+ return 0;
+}
diff --git a/arch/x86/boot/compressed/efi.h b/arch/x86/boot/compressed/efi.h
new file mode 100644
index 000000000000..7db2f41b54cd
--- /dev/null
+++ b/arch/x86/boot/compressed/efi.h
@@ -0,0 +1,126 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef BOOT_COMPRESSED_EFI_H
+#define BOOT_COMPRESSED_EFI_H
+
+#if defined(_LINUX_EFI_H) || defined(_ASM_X86_EFI_H)
+#error Please do not include kernel proper namespace headers
+#endif
+
+typedef guid_t efi_guid_t __aligned(__alignof__(u32));
+
+#define EFI_GUID(a, b, c, d...) (efi_guid_t){ { \
+ (a) & 0xff, ((a) >> 8) & 0xff, ((a) >> 16) & 0xff, ((a) >> 24) & 0xff, \
+ (b) & 0xff, ((b) >> 8) & 0xff, \
+ (c) & 0xff, ((c) >> 8) & 0xff, d } }
+
+#define ACPI_TABLE_GUID EFI_GUID(0xeb9d2d30, 0x2d88, 0x11d3, 0x9a, 0x16, 0x00, 0x90, 0x27, 0x3f, 0xc1, 0x4d)
+#define ACPI_20_TABLE_GUID EFI_GUID(0x8868e871, 0xe4f1, 0x11d3, 0xbc, 0x22, 0x00, 0x80, 0xc7, 0x3c, 0x88, 0x81)
+#define EFI_CC_BLOB_GUID EFI_GUID(0x067b1f5f, 0xcf26, 0x44c5, 0x85, 0x54, 0x93, 0xd7, 0x77, 0x91, 0x2d, 0x42)
+
+#define EFI32_LOADER_SIGNATURE "EL32"
+#define EFI64_LOADER_SIGNATURE "EL64"
+
+/*
+ * Generic EFI table header
+ */
+typedef struct {
+ u64 signature;
+ u32 revision;
+ u32 headersize;
+ u32 crc32;
+ u32 reserved;
+} efi_table_hdr_t;
+
+#define EFI_CONVENTIONAL_MEMORY 7
+
+#define EFI_MEMORY_MORE_RELIABLE \
+ ((u64)0x0000000000010000ULL) /* higher reliability */
+#define EFI_MEMORY_SP ((u64)0x0000000000040000ULL) /* soft reserved */
+
+#define EFI_PAGE_SHIFT 12
+
+typedef struct {
+ u32 type;
+ u32 pad;
+ u64 phys_addr;
+ u64 virt_addr;
+ u64 num_pages;
+ u64 attribute;
+} efi_memory_desc_t;
+
+#define efi_early_memdesc_ptr(map, desc_size, n) \
+ (efi_memory_desc_t *)((void *)(map) + ((n) * (desc_size)))
+
+typedef struct {
+ efi_guid_t guid;
+ u64 table;
+} efi_config_table_64_t;
+
+typedef struct {
+ efi_guid_t guid;
+ u32 table;
+} efi_config_table_32_t;
+
+typedef struct {
+ efi_table_hdr_t hdr;
+ u64 fw_vendor; /* physical addr of CHAR16 vendor string */
+ u32 fw_revision;
+ u32 __pad1;
+ u64 con_in_handle;
+ u64 con_in;
+ u64 con_out_handle;
+ u64 con_out;
+ u64 stderr_handle;
+ u64 stderr;
+ u64 runtime;
+ u64 boottime;
+ u32 nr_tables;
+ u32 __pad2;
+ u64 tables;
+} efi_system_table_64_t;
+
+typedef struct {
+ efi_table_hdr_t hdr;
+ u32 fw_vendor; /* physical addr of CHAR16 vendor string */
+ u32 fw_revision;
+ u32 con_in_handle;
+ u32 con_in;
+ u32 con_out_handle;
+ u32 con_out;
+ u32 stderr_handle;
+ u32 stderr;
+ u32 runtime;
+ u32 boottime;
+ u32 nr_tables;
+ u32 tables;
+} efi_system_table_32_t;
+
+/* kexec external ABI */
+struct efi_setup_data {
+ u64 fw_vendor;
+ u64 __unused;
+ u64 tables;
+ u64 smbios;
+ u64 reserved[8];
+};
+
+static inline int efi_guidcmp (efi_guid_t left, efi_guid_t right)
+{
+ return memcmp(&left, &right, sizeof (efi_guid_t));
+}
+
+#ifdef CONFIG_EFI
+bool __pure __efi_soft_reserve_enabled(void);
+
+static inline bool __pure efi_soft_reserve_enabled(void)
+{
+ return IS_ENABLED(CONFIG_EFI_SOFT_RESERVE)
+ && __efi_soft_reserve_enabled();
+}
+#else
+static inline bool efi_soft_reserve_enabled(void)
+{
+ return false;
+}
+#endif /* CONFIG_EFI */
+#endif /* BOOT_COMPRESSED_EFI_H */
diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S
index dea95301196b..4cd661165d4a 100644
--- a/arch/x86/boot/compressed/head_64.S
+++ b/arch/x86/boot/compressed/head_64.S
@@ -189,11 +189,11 @@ SYM_FUNC_START(startup_32)
subl $32, %eax /* Encryption bit is always above bit 31 */
bts %eax, %edx /* Set encryption mask for page tables */
/*
- * Mark SEV as active in sev_status so that startup32_check_sev_cbit()
- * will do a check. The sev_status memory will be fully initialized
- * with the contents of MSR_AMD_SEV_STATUS later in
- * set_sev_encryption_mask(). For now it is sufficient to know that SEV
- * is active.
+ * Set MSR_AMD64_SEV_ENABLED_BIT in sev_status so that
+ * startup32_check_sev_cbit() will do a check. sev_enable() will
+ * initialize sev_status with all the bits reported by
+ * MSR_AMD_SEV_STATUS later, but only MSR_AMD64_SEV_ENABLED_BIT
+ * needs to be set for now.
*/
movl $1, rva(sev_status)(%ebp)
1:
@@ -447,6 +447,23 @@ SYM_CODE_START(startup_64)
call load_stage1_idt
popq %rsi
+#ifdef CONFIG_AMD_MEM_ENCRYPT
+ /*
+ * Now that the stage1 interrupt handlers are set up, #VC exceptions from
+ * CPUID instructions can be properly handled for SEV-ES guests.
+ *
+ * For SEV-SNP, the CPUID table also needs to be set up in advance of any
+ * CPUID instructions being issued, so go ahead and do that now via
+ * sev_enable(), which will also handle the rest of the SEV-related
+ * detection/setup to ensure that has been done in advance of any dependent
+ * code.
+ */
+ pushq %rsi
+ movq %rsi, %rdi /* real mode address */
+ call sev_enable
+ popq %rsi
+#endif
+
/*
* paging_prepare() sets up the trampoline and checks if we need to
* enable 5-level paging.
@@ -558,17 +575,7 @@ SYM_FUNC_START_LOCAL_NOALIGN(.Lrelocated)
shrq $3, %rcx
rep stosq
-/*
- * If running as an SEV guest, the encryption mask is required in the
- * page-table setup code below. When the guest also has SEV-ES enabled
- * set_sev_encryption_mask() will cause #VC exceptions, but the stage2
- * handler can't map its GHCB because the page-table is not set up yet.
- * So set up the encryption mask here while still on the stage1 #VC
- * handler. Then load stage2 IDT and switch to the kernel's own
- * page-table.
- */
pushq %rsi
- call set_sev_encryption_mask
call load_stage2_idt
/* Pass boot_params to initialize_identity_maps() */
diff --git a/arch/x86/boot/compressed/ident_map_64.c b/arch/x86/boot/compressed/ident_map_64.c
index f7213d0943b8..44c350d627c7 100644
--- a/arch/x86/boot/compressed/ident_map_64.c
+++ b/arch/x86/boot/compressed/ident_map_64.c
@@ -90,7 +90,7 @@ static struct x86_mapping_info mapping_info;
/*
* Adds the specified range to the identity mappings.
*/
-static void add_identity_map(unsigned long start, unsigned long end)
+void kernel_add_identity_map(unsigned long start, unsigned long end)
{
int ret;
@@ -157,14 +157,15 @@ void initialize_identity_maps(void *rmode)
* explicitly here in case the compressed kernel does not touch them,
* or does not touch all the pages covering them.
*/
- add_identity_map((unsigned long)_head, (unsigned long)_end);
+ kernel_add_identity_map((unsigned long)_head, (unsigned long)_end);
boot_params = rmode;
- add_identity_map((unsigned long)boot_params, (unsigned long)(boot_params + 1));
+ kernel_add_identity_map((unsigned long)boot_params, (unsigned long)(boot_params + 1));
cmdline = get_cmd_line_ptr();
- add_identity_map(cmdline, cmdline + COMMAND_LINE_SIZE);
+ kernel_add_identity_map(cmdline, cmdline + COMMAND_LINE_SIZE);
+
+ sev_prep_identity_maps(top_level_pgt);
/* Load the new page-table. */
- sev_verify_cbit(top_level_pgt);
write_cr3(top_level_pgt);
}
@@ -246,10 +247,10 @@ static int set_clr_page_flags(struct x86_mapping_info *info,
* It should already exist, but keep things generic.
*
* To map the page just read from it and fault it in if there is no
- * mapping yet. add_identity_map() can't be called here because that
- * would unconditionally map the address on PMD level, destroying any
- * PTE-level mappings that might already exist. Use assembly here so
- * the access won't be optimized away.
+ * mapping yet. kernel_add_identity_map() can't be called here because
+ * that would unconditionally map the address on PMD level, destroying
+ * any PTE-level mappings that might already exist. Use assembly here
+ * so the access won't be optimized away.
*/
asm volatile("mov %[address], %%r9"
:: [address] "g" (*(unsigned long *)address)
@@ -275,15 +276,31 @@ static int set_clr_page_flags(struct x86_mapping_info *info,
* Changing encryption attributes of a page requires to flush it from
* the caches.
*/
- if ((set | clr) & _PAGE_ENC)
+ if ((set | clr) & _PAGE_ENC) {
clflush_page(address);
+ /*
+ * If the encryption attribute is being cleared, change the page state
+ * to shared in the RMP table.
+ */
+ if (clr)
+ snp_set_page_shared(__pa(address & PAGE_MASK));
+ }
+
/* Update PTE */
pte = *ptep;
pte = pte_set_flags(pte, set);
pte = pte_clear_flags(pte, clr);
set_pte(ptep, pte);
+ /*
+ * If the encryption attribute is being set, then change the page state to
+ * private in the RMP entry. The page state change must be done after the PTE
+ * is updated.
+ */
+ if (set & _PAGE_ENC)
+ snp_set_page_private(__pa(address & PAGE_MASK));
+
/* Flush TLB after changing encryption attribute */
write_cr3(top_level_pgt);
@@ -347,5 +364,5 @@ void do_boot_page_fault(struct pt_regs *regs, unsigned long error_code)
* Error code is sane - now identity map the 2M region around
* the faulting address.
*/
- add_identity_map(address, end);
+ kernel_add_identity_map(address, end);
}
diff --git a/arch/x86/boot/compressed/idt_64.c b/arch/x86/boot/compressed/idt_64.c
index 9b93567d663a..6debb816e83d 100644
--- a/arch/x86/boot/compressed/idt_64.c
+++ b/arch/x86/boot/compressed/idt_64.c
@@ -39,7 +39,23 @@ void load_stage1_idt(void)
load_boot_idt(&boot_idt_desc);
}
-/* Setup IDT after kernel jumping to .Lrelocated */
+/*
+ * Setup IDT after kernel jumping to .Lrelocated.
+ *
+ * initialize_identity_maps() needs a #PF handler to be setup
+ * in order to be able to fault-in identity mapping ranges; see
+ * do_boot_page_fault().
+ *
+ * This #PF handler setup needs to happen in load_stage2_idt() where the
+ * IDT is loaded and there the #VC IDT entry gets setup too.
+ *
+ * In order to be able to handle #VCs, one needs a GHCB which
+ * gets setup with an already set up pagetable, which is done in
+ * initialize_identity_maps(). And there's the catch 22: the boot #VC
+ * handler do_boot_stage2_vc() needs to call early_setup_ghcb() itself
+ * (and, especially set_page_decrypted()) because the SEV-ES setup code
+ * cannot initialize a GHCB as there's no #PF handler yet...
+ */
void load_stage2_idt(void)
{
boot_idt_desc.address = (unsigned long)boot_idt;
diff --git a/arch/x86/boot/compressed/kaslr.c b/arch/x86/boot/compressed/kaslr.c
index 411b268bc0a2..4a3f223973f4 100644
--- a/arch/x86/boot/compressed/kaslr.c
+++ b/arch/x86/boot/compressed/kaslr.c
@@ -22,15 +22,14 @@
#include "misc.h"
#include "error.h"
#include "../string.h"
+#include "efi.h"
#include <generated/compile.h>
#include <linux/module.h>
#include <linux/uts.h>
#include <linux/utsname.h>
#include <linux/ctype.h>
-#include <linux/efi.h>
#include <generated/utsrelease.h>
-#include <asm/efi.h>
#define _SETUP
#include <asm/setup.h> /* For COMMAND_LINE_SIZE */
diff --git a/arch/x86/boot/compressed/mem_encrypt.S b/arch/x86/boot/compressed/mem_encrypt.S
index a63424d13627..a73e4d783cae 100644
--- a/arch/x86/boot/compressed/mem_encrypt.S
+++ b/arch/x86/boot/compressed/mem_encrypt.S
@@ -187,42 +187,6 @@ SYM_CODE_END(startup32_vc_handler)
.code64
#include "../../kernel/sev_verify_cbit.S"
-SYM_FUNC_START(set_sev_encryption_mask)
-#ifdef CONFIG_AMD_MEM_ENCRYPT
- push %rbp
- push %rdx
-
- movq %rsp, %rbp /* Save current stack pointer */
-
- call get_sev_encryption_bit /* Get the encryption bit position */
- testl %eax, %eax
- jz .Lno_sev_mask
-
- bts %rax, sme_me_mask(%rip) /* Create the encryption mask */
-
- /*
- * Read MSR_AMD64_SEV again and store it to sev_status. Can't do this in
- * get_sev_encryption_bit() because this function is 32-bit code and
- * shared between 64-bit and 32-bit boot path.
- */
- movl $MSR_AMD64_SEV, %ecx /* Read the SEV MSR */
- rdmsr
-
- /* Store MSR value in sev_status */
- shlq $32, %rdx
- orq %rdx, %rax
- movq %rax, sev_status(%rip)
-
-.Lno_sev_mask:
- movq %rbp, %rsp /* Restore original stack pointer */
-
- pop %rdx
- pop %rbp
-#endif
-
- xor %rax, %rax
- RET
-SYM_FUNC_END(set_sev_encryption_mask)
.data
diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c
index 1cdcaf34ee36..ca6820f99b40 100644
--- a/arch/x86/boot/compressed/misc.c
+++ b/arch/x86/boot/compressed/misc.c
@@ -53,7 +53,10 @@ memptr free_mem_end_ptr;
static char *vidmem;
static int vidport;
-static int lines, cols;
+
+/* These might be accessed before .bss is cleared, so use .data instead. */
+static int lines __section(".data");
+static int cols __section(".data");
#ifdef CONFIG_KERNEL_GZIP
#include "../../../../lib/decompress_inflate.c"
diff --git a/arch/x86/boot/compressed/misc.h b/arch/x86/boot/compressed/misc.h
index 16ed360b6692..4ca2857ea041 100644
--- a/arch/x86/boot/compressed/misc.h
+++ b/arch/x86/boot/compressed/misc.h
@@ -34,6 +34,8 @@
#define BOOT_BOOT_H
#include "../ctype.h"
+#include "efi.h"
+
#ifdef CONFIG_X86_64
#define memptr long
#else
@@ -120,17 +122,23 @@ static inline void console_init(void)
{ }
#endif
-void set_sev_encryption_mask(void);
-
#ifdef CONFIG_AMD_MEM_ENCRYPT
+void sev_enable(struct boot_params *bp);
void sev_es_shutdown_ghcb(void);
extern bool sev_es_check_ghcb_fault(unsigned long address);
+void snp_set_page_private(unsigned long paddr);
+void snp_set_page_shared(unsigned long paddr);
+void sev_prep_identity_maps(unsigned long top_level_pgt);
#else
+static inline void sev_enable(struct boot_params *bp) { }
static inline void sev_es_shutdown_ghcb(void) { }
static inline bool sev_es_check_ghcb_fault(unsigned long address)
{
return false;
}
+static inline void snp_set_page_private(unsigned long paddr) { }
+static inline void snp_set_page_shared(unsigned long paddr) { }
+static inline void sev_prep_identity_maps(unsigned long top_level_pgt) { }
#endif
/* acpi.c */
@@ -151,6 +159,7 @@ static inline int count_immovable_mem_regions(void) { return 0; }
#ifdef CONFIG_X86_5LEVEL
extern unsigned int __pgtable_l5_enabled, pgdir_shift, ptrs_per_p4d;
#endif
+extern void kernel_add_identity_map(unsigned long start, unsigned long end);
/* Used by PAGE_KERN* macros: */
extern pteval_t __default_kernel_pte_mask;
@@ -172,4 +181,47 @@ void boot_stage2_vc(void);
unsigned long sev_verify_cbit(unsigned long cr3);
+enum efi_type {
+ EFI_TYPE_64,
+ EFI_TYPE_32,
+ EFI_TYPE_NONE,
+};
+
+#ifdef CONFIG_EFI
+/* helpers for early EFI config table access */
+enum efi_type efi_get_type(struct boot_params *bp);
+unsigned long efi_get_system_table(struct boot_params *bp);
+int efi_get_conf_table(struct boot_params *bp, unsigned long *cfg_tbl_pa,
+ unsigned int *cfg_tbl_len);
+unsigned long efi_find_vendor_table(struct boot_params *bp,
+ unsigned long cfg_tbl_pa,
+ unsigned int cfg_tbl_len,
+ efi_guid_t guid);
+#else
+static inline enum efi_type efi_get_type(struct boot_params *bp)
+{
+ return EFI_TYPE_NONE;
+}
+
+static inline unsigned long efi_get_system_table(struct boot_params *bp)
+{
+ return 0;
+}
+
+static inline int efi_get_conf_table(struct boot_params *bp,
+ unsigned long *cfg_tbl_pa,
+ unsigned int *cfg_tbl_len)
+{
+ return -ENOENT;
+}
+
+static inline unsigned long efi_find_vendor_table(struct boot_params *bp,
+ unsigned long cfg_tbl_pa,
+ unsigned int cfg_tbl_len,
+ efi_guid_t guid)
+{
+ return 0;
+}
+#endif /* CONFIG_EFI */
+
#endif /* BOOT_COMPRESSED_MISC_H */
diff --git a/arch/x86/boot/compressed/pgtable_64.c b/arch/x86/boot/compressed/pgtable_64.c
index a1733319a22a..2ac12ff4111b 100644
--- a/arch/x86/boot/compressed/pgtable_64.c
+++ b/arch/x86/boot/compressed/pgtable_64.c
@@ -1,11 +1,10 @@
// SPDX-License-Identifier: GPL-2.0
#include "misc.h"
-#include <linux/efi.h>
#include <asm/e820/types.h>
#include <asm/processor.h>
-#include <asm/efi.h>
#include "pgtable.h"
#include "../string.h"
+#include "efi.h"
#define BIOS_START_MIN 0x20000U /* 128K, less than this is insane */
#define BIOS_START_MAX 0x9f000U /* 640K, absolute maximum */
diff --git a/arch/x86/boot/compressed/sev.c b/arch/x86/boot/compressed/sev.c
index 28bcf04c022e..52f989f6acc2 100644
--- a/arch/x86/boot/compressed/sev.c
+++ b/arch/x86/boot/compressed/sev.c
@@ -20,8 +20,10 @@
#include <asm/fpu/xcr.h>
#include <asm/ptrace.h>
#include <asm/svm.h>
+#include <asm/cpuid.h>
#include "error.h"
+#include "../msr.h"
struct ghcb boot_ghcb_page __aligned(PAGE_SIZE);
struct ghcb *boot_ghcb;
@@ -56,23 +58,19 @@ static unsigned long insn_get_seg_base(struct pt_regs *regs, int seg_reg_idx)
static inline u64 sev_es_rd_ghcb_msr(void)
{
- unsigned long low, high;
+ struct msr m;
- asm volatile("rdmsr" : "=a" (low), "=d" (high) :
- "c" (MSR_AMD64_SEV_ES_GHCB));
+ boot_rdmsr(MSR_AMD64_SEV_ES_GHCB, &m);
- return ((high << 32) | low);
+ return m.q;
}
static inline void sev_es_wr_ghcb_msr(u64 val)
{
- u32 low, high;
+ struct msr m;
- low = val & 0xffffffffUL;
- high = val >> 32;
-
- asm volatile("wrmsr" : : "c" (MSR_AMD64_SEV_ES_GHCB),
- "a"(low), "d" (high) : "memory");
+ m.q = val;
+ boot_wrmsr(MSR_AMD64_SEV_ES_GHCB, &m);
}
static enum es_result vc_decode_insn(struct es_em_ctxt *ctxt)
@@ -119,11 +117,54 @@ static enum es_result vc_read_mem(struct es_em_ctxt *ctxt,
/* Include code for early handlers */
#include "../../kernel/sev-shared.c"
-static bool early_setup_sev_es(void)
+static inline bool sev_snp_enabled(void)
+{
+ return sev_status & MSR_AMD64_SEV_SNP_ENABLED;
+}
+
+static void __page_state_change(unsigned long paddr, enum psc_op op)
+{
+ u64 val;
+
+ if (!sev_snp_enabled())
+ return;
+
+ /*
+ * If private -> shared then invalidate the page before requesting the
+ * state change in the RMP table.
+ */
+ if (op == SNP_PAGE_STATE_SHARED && pvalidate(paddr, RMP_PG_SIZE_4K, 0))
+ sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_PVALIDATE);
+
+ /* Issue VMGEXIT to change the page state in RMP table. */
+ sev_es_wr_ghcb_msr(GHCB_MSR_PSC_REQ_GFN(paddr >> PAGE_SHIFT, op));
+ VMGEXIT();
+
+ /* Read the response of the VMGEXIT. */
+ val = sev_es_rd_ghcb_msr();
+ if ((GHCB_RESP_CODE(val) != GHCB_MSR_PSC_RESP) || GHCB_MSR_PSC_RESP_VAL(val))
+ sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_PSC);
+
+ /*
+ * Now that page state is changed in the RMP table, validate it so that it is
+ * consistent with the RMP entry.
+ */
+ if (op == SNP_PAGE_STATE_PRIVATE && pvalidate(paddr, RMP_PG_SIZE_4K, 1))
+ sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_PVALIDATE);
+}
+
+void snp_set_page_private(unsigned long paddr)
+{
+ __page_state_change(paddr, SNP_PAGE_STATE_PRIVATE);
+}
+
+void snp_set_page_shared(unsigned long paddr)
{
- if (!sev_es_negotiate_protocol())
- sev_es_terminate(GHCB_SEV_ES_PROT_UNSUPPORTED);
+ __page_state_change(paddr, SNP_PAGE_STATE_SHARED);
+}
+static bool early_setup_ghcb(void)
+{
if (set_page_decrypted((unsigned long)&boot_ghcb_page))
return false;
@@ -135,6 +176,10 @@ static bool early_setup_sev_es(void)
/* Initialize lookup tables for the instruction decoder */
inat_init_tables();
+ /* SNP guest requires the GHCB GPA must be registered */
+ if (sev_snp_enabled())
+ snp_register_ghcb_early(__pa(&boot_ghcb_page));
+
return true;
}
@@ -174,8 +219,8 @@ void do_boot_stage2_vc(struct pt_regs *regs, unsigned long exit_code)
struct es_em_ctxt ctxt;
enum es_result result;
- if (!boot_ghcb && !early_setup_sev_es())
- sev_es_terminate(GHCB_SEV_ES_GEN_REQ);
+ if (!boot_ghcb && !early_setup_ghcb())
+ sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SEV_ES_GEN_REQ);
vc_ghcb_invalidate(boot_ghcb);
result = vc_init_em_ctxt(&ctxt, regs, exit_code);
@@ -202,5 +247,191 @@ finish:
if (result == ES_OK)
vc_finish_insn(&ctxt);
else if (result != ES_RETRY)
- sev_es_terminate(GHCB_SEV_ES_GEN_REQ);
+ sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SEV_ES_GEN_REQ);
+}
+
+static void enforce_vmpl0(void)
+{
+ u64 attrs;
+ int err;
+
+ /*
+ * RMPADJUST modifies RMP permissions of a lesser-privileged (numerically
+ * higher) privilege level. Here, clear the VMPL1 permission mask of the
+ * GHCB page. If the guest is not running at VMPL0, this will fail.
+ *
+ * If the guest is running at VMPL0, it will succeed. Even if that operation
+ * modifies permission bits, it is still ok to do so currently because Linux
+ * SNP guests are supported only on VMPL0 so VMPL1 or higher permission masks
+ * changing is a don't-care.
+ */
+ attrs = 1;
+ if (rmpadjust((unsigned long)&boot_ghcb_page, RMP_PG_SIZE_4K, attrs))
+ sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_NOT_VMPL0);
+}
+
+void sev_enable(struct boot_params *bp)
+{
+ unsigned int eax, ebx, ecx, edx;
+ struct msr m;
+ bool snp;
+
+ /*
+ * Setup/preliminary detection of SNP. This will be sanity-checked
+ * against CPUID/MSR values later.
+ */
+ snp = snp_init(bp);
+
+ /* Check for the SME/SEV support leaf */
+ eax = 0x80000000;
+ ecx = 0;
+ native_cpuid(&eax, &ebx, &ecx, &edx);
+ if (eax < 0x8000001f)
+ return;
+
+ /*
+ * Check for the SME/SEV feature:
+ * CPUID Fn8000_001F[EAX]
+ * - Bit 0 - Secure Memory Encryption support
+ * - Bit 1 - Secure Encrypted Virtualization support
+ * CPUID Fn8000_001F[EBX]
+ * - Bits 5:0 - Pagetable bit position used to indicate encryption
+ */
+ eax = 0x8000001f;
+ ecx = 0;
+ native_cpuid(&eax, &ebx, &ecx, &edx);
+ /* Check whether SEV is supported */
+ if (!(eax & BIT(1))) {
+ if (snp)
+ error("SEV-SNP support indicated by CC blob, but not CPUID.");
+ return;
+ }
+
+ /* Set the SME mask if this is an SEV guest. */
+ boot_rdmsr(MSR_AMD64_SEV, &m);
+ sev_status = m.q;
+ if (!(sev_status & MSR_AMD64_SEV_ENABLED))
+ return;
+
+ /* Negotiate the GHCB protocol version. */
+ if (sev_status & MSR_AMD64_SEV_ES_ENABLED) {
+ if (!sev_es_negotiate_protocol())
+ sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SEV_ES_PROT_UNSUPPORTED);
+ }
+
+ /*
+ * SNP is supported in v2 of the GHCB spec which mandates support for HV
+ * features.
+ */
+ if (sev_status & MSR_AMD64_SEV_SNP_ENABLED) {
+ if (!(get_hv_features() & GHCB_HV_FT_SNP))
+ sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SNP_UNSUPPORTED);
+
+ enforce_vmpl0();
+ }
+
+ if (snp && !(sev_status & MSR_AMD64_SEV_SNP_ENABLED))
+ error("SEV-SNP supported indicated by CC blob, but not SEV status MSR.");
+
+ sme_me_mask = BIT_ULL(ebx & 0x3f);
+}
+
+/* Search for Confidential Computing blob in the EFI config table. */
+static struct cc_blob_sev_info *find_cc_blob_efi(struct boot_params *bp)
+{
+ unsigned long cfg_table_pa;
+ unsigned int cfg_table_len;
+ int ret;
+
+ ret = efi_get_conf_table(bp, &cfg_table_pa, &cfg_table_len);
+ if (ret)
+ return NULL;
+
+ return (struct cc_blob_sev_info *)efi_find_vendor_table(bp, cfg_table_pa,
+ cfg_table_len,
+ EFI_CC_BLOB_GUID);
+}
+
+/*
+ * Initial set up of SNP relies on information provided by the
+ * Confidential Computing blob, which can be passed to the boot kernel
+ * by firmware/bootloader in the following ways:
+ *
+ * - via an entry in the EFI config table
+ * - via a setup_data structure, as defined by the Linux Boot Protocol
+ *
+ * Scan for the blob in that order.
+ */
+static struct cc_blob_sev_info *find_cc_blob(struct boot_params *bp)
+{
+ struct cc_blob_sev_info *cc_info;
+
+ cc_info = find_cc_blob_efi(bp);
+ if (cc_info)
+ goto found_cc_info;
+
+ cc_info = find_cc_blob_setup_data(bp);
+ if (!cc_info)
+ return NULL;
+
+found_cc_info:
+ if (cc_info->magic != CC_BLOB_SEV_HDR_MAGIC)
+ sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SNP_UNSUPPORTED);
+
+ return cc_info;
+}
+
+/*
+ * Indicate SNP based on presence of SNP-specific CC blob. Subsequent checks
+ * will verify the SNP CPUID/MSR bits.
+ */
+bool snp_init(struct boot_params *bp)
+{
+ struct cc_blob_sev_info *cc_info;
+
+ if (!bp)
+ return false;
+
+ cc_info = find_cc_blob(bp);
+ if (!cc_info)
+ return false;
+
+ /*
+ * If a SNP-specific Confidential Computing blob is present, then
+ * firmware/bootloader have indicated SNP support. Verifying this
+ * involves CPUID checks which will be more reliable if the SNP
+ * CPUID table is used. See comments over snp_setup_cpuid_table() for
+ * more details.
+ */
+ setup_cpuid_table(cc_info);
+
+ /*
+ * Pass run-time kernel a pointer to CC info via boot_params so EFI
+ * config table doesn't need to be searched again during early startup
+ * phase.
+ */
+ bp->cc_blob_address = (u32)(unsigned long)cc_info;
+
+ return true;
+}
+
+void sev_prep_identity_maps(unsigned long top_level_pgt)
+{
+ /*
+ * The Confidential Computing blob is used very early in uncompressed
+ * kernel to find the in-memory CPUID table to handle CPUID
+ * instructions. Make sure an identity-mapping exists so it can be
+ * accessed after switchover.
+ */
+ if (sev_snp_enabled()) {
+ unsigned long cc_info_pa = boot_params->cc_blob_address;
+ struct cc_blob_sev_info *cc_info;
+
+ kernel_add_identity_map(cc_info_pa, cc_info_pa + sizeof(*cc_info));
+
+ cc_info = (struct cc_blob_sev_info *)cc_info_pa;
+ kernel_add_identity_map(cc_info->cpuid_phys, cc_info->cpuid_phys + cc_info->cpuid_len);
+ }
+
+ sev_verify_cbit(top_level_pgt);
}
diff --git a/arch/x86/boot/cpucheck.c b/arch/x86/boot/cpucheck.c
index e1478d32de1a..fed8d13ce252 100644
--- a/arch/x86/boot/cpucheck.c
+++ b/arch/x86/boot/cpucheck.c
@@ -27,6 +27,7 @@
#include <asm/required-features.h>
#include <asm/msr-index.h>
#include "string.h"
+#include "msr.h"
static u32 err_flags[NCAPINTS];
@@ -130,12 +131,11 @@ int check_cpu(int *cpu_level_ptr, int *req_level_ptr, u32 **err_flags_ptr)
/* If this is an AMD and we're only missing SSE+SSE2, try to
turn them on */
- u32 ecx = MSR_K7_HWCR;
- u32 eax, edx;
+ struct msr m;
- asm("rdmsr" : "=a" (eax), "=d" (edx) : "c" (ecx));
- eax &= ~(1 << 15);
- asm("wrmsr" : : "a" (eax), "d" (edx), "c" (ecx));
+ boot_rdmsr(MSR_K7_HWCR, &m);
+ m.l &= ~(1 << 15);
+ boot_wrmsr(MSR_K7_HWCR, &m);
get_cpuflags(); /* Make sure it really did something */
err = check_cpuflags();
@@ -145,28 +145,28 @@ int check_cpu(int *cpu_level_ptr, int *req_level_ptr, u32 **err_flags_ptr)
/* If this is a VIA C3, we might have to enable CX8
explicitly */
- u32 ecx = MSR_VIA_FCR;
- u32 eax, edx;
+ struct msr m;
- asm("rdmsr" : "=a" (eax), "=d" (edx) : "c" (ecx));
- eax |= (1<<1)|(1<<7);
- asm("wrmsr" : : "a" (eax), "d" (edx), "c" (ecx));
+ boot_rdmsr(MSR_VIA_FCR, &m);
+ m.l |= (1 << 1) | (1 << 7);
+ boot_wrmsr(MSR_VIA_FCR, &m);
set_bit(X86_FEATURE_CX8, cpu.flags);
err = check_cpuflags();
} else if (err == 0x01 && is_transmeta()) {
/* Transmeta might have masked feature bits in word 0 */
- u32 ecx = 0x80860004;
- u32 eax, edx;
+ struct msr m, m_tmp;
u32 level = 1;
- asm("rdmsr" : "=a" (eax), "=d" (edx) : "c" (ecx));
- asm("wrmsr" : : "a" (~0), "d" (edx), "c" (ecx));
+ boot_rdmsr(0x80860004, &m);
+ m_tmp = m;
+ m_tmp.l = ~0;
+ boot_wrmsr(0x80860004, &m_tmp);
asm("cpuid"
: "+a" (level), "=d" (cpu.flags[0])
: : "ecx", "ebx");
- asm("wrmsr" : : "a" (eax), "d" (edx), "c" (ecx));
+ boot_wrmsr(0x80860004, &m);
err = check_cpuflags();
} else if (err == 0x01 &&
diff --git a/arch/x86/boot/msr.h b/arch/x86/boot/msr.h
new file mode 100644
index 000000000000..aed66f7ae199
--- /dev/null
+++ b/arch/x86/boot/msr.h
@@ -0,0 +1,26 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Helpers/definitions related to MSR access.
+ */
+
+#ifndef BOOT_MSR_H
+#define BOOT_MSR_H
+
+#include <asm/shared/msr.h>
+
+/*
+ * The kernel proper already defines rdmsr()/wrmsr(), but they are not for the
+ * boot kernel since they rely on tracepoint/exception handling infrastructure
+ * that's not available here.
+ */
+static inline void boot_rdmsr(unsigned int reg, struct msr *m)
+{
+ asm volatile("rdmsr" : "=a" (m->l), "=d" (m->h) : "c" (reg));
+}
+
+static inline void boot_wrmsr(unsigned int reg, const struct msr *m)
+{
+ asm volatile("wrmsr" : : "c" (reg), "a"(m->l), "d" (m->h) : "memory");
+}
+
+#endif /* BOOT_MSR_H */
diff --git a/arch/x86/coco/core.c b/arch/x86/coco/core.c
index fc1365dd927e..dafd4881ce29 100644
--- a/arch/x86/coco/core.c
+++ b/arch/x86/coco/core.c
@@ -57,6 +57,9 @@ static bool amd_cc_platform_has(enum cc_attr attr)
return (sev_status & MSR_AMD64_SEV_ENABLED) &&
!(sev_status & MSR_AMD64_SEV_ES_ENABLED);
+ case CC_ATTR_GUEST_SEV_SNP:
+ return sev_status & MSR_AMD64_SEV_SNP_ENABLED;
+
default:
return false;
}
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index 73d958522b6a..c8119dd97556 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -215,8 +215,13 @@ syscall_return_via_sysret:
popq %rdi
popq %rsp
+SYM_INNER_LABEL(entry_SYSRETQ_unsafe_stack, SYM_L_GLOBAL)
+ ANNOTATE_NOENDBR
swapgs
sysretq
+SYM_INNER_LABEL(entry_SYSRETQ_end, SYM_L_GLOBAL)
+ ANNOTATE_NOENDBR
+ int3
SYM_CODE_END(entry_SYSCALL_64)
/*
@@ -508,6 +513,7 @@ SYM_CODE_START(\asmsym)
call vc_switch_off_ist
movq %rax, %rsp /* Switch to new stack */
+ ENCODE_FRAME_POINTER
UNWIND_HINT_REGS
/* Update pt_regs */
diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S
index 4fdb007cddbd..8011021d7ce8 100644
--- a/arch/x86/entry/entry_64_compat.S
+++ b/arch/x86/entry/entry_64_compat.S
@@ -297,6 +297,8 @@ sysret32_from_system_call:
* code. We zero R8-R10 to avoid info leaks.
*/
movq RSP-ORIG_RAX(%rsp), %rsp
+SYM_INNER_LABEL(entry_SYSRETL_compat_unsafe_stack, SYM_L_GLOBAL)
+ ANNOTATE_NOENDBR
/*
* The original userspace %rsp (RSP-ORIG_RAX(%rsp)) is stored
@@ -314,6 +316,9 @@ sysret32_from_system_call:
xorl %r10d, %r10d
swapgs
sysretl
+SYM_INNER_LABEL(entry_SYSRETL_compat_end, SYM_L_GLOBAL)
+ ANNOTATE_NOENDBR
+ int3
SYM_CODE_END(entry_SYSCALL_compat)
/*
diff --git a/arch/x86/include/asm/bootparam_utils.h b/arch/x86/include/asm/bootparam_utils.h
index 981fe923a59f..53e9b0620d96 100644
--- a/arch/x86/include/asm/bootparam_utils.h
+++ b/arch/x86/include/asm/bootparam_utils.h
@@ -74,6 +74,7 @@ static void sanitize_boot_params(struct boot_params *boot_params)
BOOT_PARAM_PRESERVE(hdr),
BOOT_PARAM_PRESERVE(e820_table),
BOOT_PARAM_PRESERVE(eddbuf),
+ BOOT_PARAM_PRESERVE(cc_blob_address),
};
memset(&scratch, 0, sizeof(scratch));
diff --git a/arch/x86/include/asm/cpuid.h b/arch/x86/include/asm/cpuid.h
new file mode 100644
index 000000000000..70b2db18165e
--- /dev/null
+++ b/arch/x86/include/asm/cpuid.h
@@ -0,0 +1,34 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * CPUID-related helpers/definitions
+ *
+ * Derived from arch/x86/kvm/cpuid.c
+ */
+
+#ifndef _ASM_X86_CPUID_H
+#define _ASM_X86_CPUID_H
+
+static __always_inline bool cpuid_function_is_indexed(u32 function)
+{
+ switch (function) {
+ case 4:
+ case 7:
+ case 0xb:
+ case 0xd:
+ case 0xf:
+ case 0x10:
+ case 0x12:
+ case 0x14:
+ case 0x17:
+ case 0x18:
+ case 0x1d:
+ case 0x1e:
+ case 0x1f:
+ case 0x8000001d:
+ return true;
+ }
+
+ return false;
+}
+
+#endif /* _ASM_X86_CPUID_H */
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index ee15311b6be1..5555b2f9af46 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -502,8 +502,10 @@
#define MSR_AMD64_SEV 0xc0010131
#define MSR_AMD64_SEV_ENABLED_BIT 0
#define MSR_AMD64_SEV_ES_ENABLED_BIT 1
+#define MSR_AMD64_SEV_SNP_ENABLED_BIT 2
#define MSR_AMD64_SEV_ENABLED BIT_ULL(MSR_AMD64_SEV_ENABLED_BIT)
#define MSR_AMD64_SEV_ES_ENABLED BIT_ULL(MSR_AMD64_SEV_ES_ENABLED_BIT)
+#define MSR_AMD64_SEV_SNP_ENABLED BIT_ULL(MSR_AMD64_SEV_SNP_ENABLED_BIT)
#define MSR_AMD64_VIRT_SPEC_CTRL 0xc001011f
diff --git a/arch/x86/include/asm/msr.h b/arch/x86/include/asm/msr.h
index d42e6c6b47b1..65ec1965cd28 100644
--- a/arch/x86/include/asm/msr.h
+++ b/arch/x86/include/asm/msr.h
@@ -10,16 +10,7 @@
#include <asm/errno.h>
#include <asm/cpumask.h>
#include <uapi/asm/msr.h>
-
-struct msr {
- union {
- struct {
- u32 l;
- u32 h;
- };
- u64 q;
- };
-};
+#include <asm/shared/msr.h>
struct msr_info {
u32 msr_no;
diff --git a/arch/x86/include/asm/proto.h b/arch/x86/include/asm/proto.h
index feed36d44d04..f042cfc9938f 100644
--- a/arch/x86/include/asm/proto.h
+++ b/arch/x86/include/asm/proto.h
@@ -13,6 +13,8 @@ void syscall_init(void);
#ifdef CONFIG_X86_64
void entry_SYSCALL_64(void);
void entry_SYSCALL_64_safe_stack(void);
+void entry_SYSRETQ_unsafe_stack(void);
+void entry_SYSRETQ_end(void);
long do_arch_prctl_64(struct task_struct *task, int option, unsigned long arg2);
#endif
@@ -28,6 +30,8 @@ void entry_SYSENTER_compat(void);
void __end_entry_SYSENTER_compat(void);
void entry_SYSCALL_compat(void);
void entry_SYSCALL_compat_safe_stack(void);
+void entry_SYSRETL_compat_unsafe_stack(void);
+void entry_SYSRETL_compat_end(void);
void entry_INT80_compat(void);
#ifdef CONFIG_XEN_PV
void xen_entry_INT80_compat(void);
diff --git a/arch/x86/include/asm/ptrace.h b/arch/x86/include/asm/ptrace.h
index 4357e0f2cd5f..f4db78b09c8f 100644
--- a/arch/x86/include/asm/ptrace.h
+++ b/arch/x86/include/asm/ptrace.h
@@ -186,9 +186,13 @@ static __always_inline bool ip_within_syscall_gap(struct pt_regs *regs)
bool ret = (regs->ip >= (unsigned long)entry_SYSCALL_64 &&
regs->ip < (unsigned long)entry_SYSCALL_64_safe_stack);
+ ret = ret || (regs->ip >= (unsigned long)entry_SYSRETQ_unsafe_stack &&
+ regs->ip < (unsigned long)entry_SYSRETQ_end);
#ifdef CONFIG_IA32_EMULATION
ret = ret || (regs->ip >= (unsigned long)entry_SYSCALL_compat &&
regs->ip < (unsigned long)entry_SYSCALL_compat_safe_stack);
+ ret = ret || (regs->ip >= (unsigned long)entry_SYSRETL_compat_unsafe_stack &&
+ regs->ip < (unsigned long)entry_SYSRETL_compat_end);
#endif
return ret;
diff --git a/arch/x86/include/asm/setup.h b/arch/x86/include/asm/setup.h
index 896e48d45828..a1b107f2a12a 100644
--- a/arch/x86/include/asm/setup.h
+++ b/arch/x86/include/asm/setup.h
@@ -50,7 +50,6 @@ extern unsigned long saved_video_mode;
extern void reserve_standard_io_resources(void);
extern void i386_reserve_resources(void);
extern unsigned long __startup_64(unsigned long physaddr, struct boot_params *bp);
-extern unsigned long __startup_secondary_64(void);
extern void startup_64_setup_env(unsigned long physbase);
extern void early_setup_idt(void);
extern void __init do_early_exception(struct pt_regs *regs, int trapnr);
diff --git a/arch/x86/include/asm/sev-common.h b/arch/x86/include/asm/sev-common.h
index 1b2fd32b42fe..b8357d6ecd47 100644
--- a/arch/x86/include/asm/sev-common.h
+++ b/arch/x86/include/asm/sev-common.h
@@ -57,9 +57,79 @@
#define GHCB_MSR_AP_RESET_HOLD_REQ 0x006
#define GHCB_MSR_AP_RESET_HOLD_RESP 0x007
+/* GHCB GPA Register */
+#define GHCB_MSR_REG_GPA_REQ 0x012
+#define GHCB_MSR_REG_GPA_REQ_VAL(v) \
+ /* GHCBData[63:12] */ \
+ (((u64)((v) & GENMASK_ULL(51, 0)) << 12) | \
+ /* GHCBData[11:0] */ \
+ GHCB_MSR_REG_GPA_REQ)
+
+#define GHCB_MSR_REG_GPA_RESP 0x013
+#define GHCB_MSR_REG_GPA_RESP_VAL(v) \
+ /* GHCBData[63:12] */ \
+ (((u64)(v) & GENMASK_ULL(63, 12)) >> 12)
+
+/*
+ * SNP Page State Change Operation
+ *
+ * GHCBData[55:52] - Page operation:
+ * 0x0001 Page assignment, Private
+ * 0x0002 Page assignment, Shared
+ */
+enum psc_op {
+ SNP_PAGE_STATE_PRIVATE = 1,
+ SNP_PAGE_STATE_SHARED,
+};
+
+#define GHCB_MSR_PSC_REQ 0x014
+#define GHCB_MSR_PSC_REQ_GFN(gfn, op) \
+ /* GHCBData[55:52] */ \
+ (((u64)((op) & 0xf) << 52) | \
+ /* GHCBData[51:12] */ \
+ ((u64)((gfn) & GENMASK_ULL(39, 0)) << 12) | \
+ /* GHCBData[11:0] */ \
+ GHCB_MSR_PSC_REQ)
+
+#define GHCB_MSR_PSC_RESP 0x015
+#define GHCB_MSR_PSC_RESP_VAL(val) \
+ /* GHCBData[63:32] */ \
+ (((u64)(val) & GENMASK_ULL(63, 32)) >> 32)
+
/* GHCB Hypervisor Feature Request/Response */
#define GHCB_MSR_HV_FT_REQ 0x080
#define GHCB_MSR_HV_FT_RESP 0x081
+#define GHCB_MSR_HV_FT_RESP_VAL(v) \
+ /* GHCBData[63:12] */ \
+ (((u64)(v) & GENMASK_ULL(63, 12)) >> 12)
+
+#define GHCB_HV_FT_SNP BIT_ULL(0)
+#define GHCB_HV_FT_SNP_AP_CREATION BIT_ULL(1)
+
+/* SNP Page State Change NAE event */
+#define VMGEXIT_PSC_MAX_ENTRY 253
+
+struct psc_hdr {
+ u16 cur_entry;
+ u16 end_entry;
+ u32 reserved;
+} __packed;
+
+struct psc_entry {
+ u64 cur_page : 12,
+ gfn : 40,
+ operation : 4,
+ pagesize : 1,
+ reserved : 7;
+} __packed;
+
+struct snp_psc_desc {
+ struct psc_hdr hdr;
+ struct psc_entry entries[VMGEXIT_PSC_MAX_ENTRY];
+} __packed;
+
+/* Guest message request error code */
+#define SNP_GUEST_REQ_INVALID_LEN BIT_ULL(32)
#define GHCB_MSR_TERM_REQ 0x100
#define GHCB_MSR_TERM_REASON_SET_POS 12
@@ -73,8 +143,20 @@
/* GHCBData[23:16] */ \
((((u64)reason_val) & 0xff) << 16))
+/* Error codes from reason set 0 */
+#define SEV_TERM_SET_GEN 0
#define GHCB_SEV_ES_GEN_REQ 0
#define GHCB_SEV_ES_PROT_UNSUPPORTED 1
+#define GHCB_SNP_UNSUPPORTED 2
+
+/* Linux-specific reason codes (used with reason set 1) */
+#define SEV_TERM_SET_LINUX 1
+#define GHCB_TERM_REGISTER 0 /* GHCB GPA registration failure */
+#define GHCB_TERM_PSC 1 /* Page State Change failure */
+#define GHCB_TERM_PVALIDATE 2 /* Pvalidate failure */
+#define GHCB_TERM_NOT_VMPL0 3 /* SNP guest is not running at VMPL-0 */
+#define GHCB_TERM_CPUID 4 /* CPUID-validation failure */
+#define GHCB_TERM_CPUID_HV 5 /* CPUID failure during hypervisor fallback */
#define GHCB_RESP_CODE(v) ((v) & GHCB_MSR_INFO_MASK)
diff --git a/arch/x86/include/asm/sev.h b/arch/x86/include/asm/sev.h
index ec060c433589..19514524f0f8 100644
--- a/arch/x86/include/asm/sev.h
+++ b/arch/x86/include/asm/sev.h
@@ -11,9 +11,10 @@
#include <linux/types.h>
#include <asm/insn.h>
#include <asm/sev-common.h>
+#include <asm/bootparam.h>
-#define GHCB_PROTO_OUR 0x0001UL
-#define GHCB_PROTOCOL_MAX 1ULL
+#define GHCB_PROTOCOL_MIN 1ULL
+#define GHCB_PROTOCOL_MAX 2ULL
#define GHCB_DEFAULT_USAGE 0ULL
#define VMGEXIT() { asm volatile("rep; vmmcall\n\r"); }
@@ -42,6 +43,24 @@ struct es_em_ctxt {
struct es_fault_info fi;
};
+/*
+ * AMD SEV Confidential computing blob structure. The structure is
+ * defined in OVMF UEFI firmware header:
+ * https://github.com/tianocore/edk2/blob/master/OvmfPkg/Include/Guid/ConfidentialComputingSevSnpBlob.h
+ */
+#define CC_BLOB_SEV_HDR_MAGIC 0x45444d41
+struct cc_blob_sev_info {
+ u32 magic;
+ u16 version;
+ u16 reserved;
+ u64 secrets_phys;
+ u32 secrets_len;
+ u32 rsvd1;
+ u64 cpuid_phys;
+ u32 cpuid_len;
+ u32 rsvd2;
+} __packed;
+
void do_vc_no_ghcb(struct pt_regs *regs, unsigned long exit_code);
static inline u64 lower_bits(u64 val, unsigned int bits)
@@ -60,6 +79,61 @@ extern void vc_no_ghcb(void);
extern void vc_boot_ghcb(void);
extern bool handle_vc_boot_ghcb(struct pt_regs *regs);
+/* Software defined (when rFlags.CF = 1) */
+#define PVALIDATE_FAIL_NOUPDATE 255
+
+/* RMP page size */
+#define RMP_PG_SIZE_4K 0
+
+#define RMPADJUST_VMSA_PAGE_BIT BIT(16)
+
+/* SNP Guest message request */
+struct snp_req_data {
+ unsigned long req_gpa;
+ unsigned long resp_gpa;
+ unsigned long data_gpa;
+ unsigned int data_npages;
+};
+
+struct sev_guest_platform_data {
+ u64 secrets_gpa;
+};
+
+/*
+ * The secrets page contains 96-bytes of reserved field that can be used by
+ * the guest OS. The guest OS uses the area to save the message sequence
+ * number for each VMPCK.
+ *
+ * See the GHCB spec section Secret page layout for the format for this area.
+ */
+struct secrets_os_area {
+ u32 msg_seqno_0;
+ u32 msg_seqno_1;
+ u32 msg_seqno_2;
+ u32 msg_seqno_3;
+ u64 ap_jump_table_pa;
+ u8 rsvd[40];
+ u8 guest_usage[32];
+} __packed;
+
+#define VMPCK_KEY_LEN 32
+
+/* See the SNP spec version 0.9 for secrets page format */
+struct snp_secrets_page_layout {
+ u32 version;
+ u32 imien : 1,
+ rsvd1 : 31;
+ u32 fms;
+ u32 rsvd2;
+ u8 gosvw[16];
+ u8 vmpck0[VMPCK_KEY_LEN];
+ u8 vmpck1[VMPCK_KEY_LEN];
+ u8 vmpck2[VMPCK_KEY_LEN];
+ u8 vmpck3[VMPCK_KEY_LEN];
+ struct secrets_os_area os_area;
+ u8 rsvd3[3840];
+} __packed;
+
#ifdef CONFIG_AMD_MEM_ENCRYPT
extern struct static_key_false sev_es_enable_key;
extern void __sev_es_ist_enter(struct pt_regs *regs);
@@ -87,12 +161,71 @@ extern enum es_result sev_es_ghcb_hv_call(struct ghcb *ghcb,
struct es_em_ctxt *ctxt,
u64 exit_code, u64 exit_info_1,
u64 exit_info_2);
+static inline int rmpadjust(unsigned long vaddr, bool rmp_psize, unsigned long attrs)
+{
+ int rc;
+
+ /* "rmpadjust" mnemonic support in binutils 2.36 and newer */
+ asm volatile(".byte 0xF3,0x0F,0x01,0xFE\n\t"
+ : "=a"(rc)
+ : "a"(vaddr), "c"(rmp_psize), "d"(attrs)
+ : "memory", "cc");
+
+ return rc;
+}
+static inline int pvalidate(unsigned long vaddr, bool rmp_psize, bool validate)
+{
+ bool no_rmpupdate;
+ int rc;
+
+ /* "pvalidate" mnemonic support in binutils 2.36 and newer */
+ asm volatile(".byte 0xF2, 0x0F, 0x01, 0xFF\n\t"
+ CC_SET(c)
+ : CC_OUT(c) (no_rmpupdate), "=a"(rc)
+ : "a"(vaddr), "c"(rmp_psize), "d"(validate)
+ : "memory", "cc");
+
+ if (no_rmpupdate)
+ return PVALIDATE_FAIL_NOUPDATE;
+
+ return rc;
+}
+void setup_ghcb(void);
+void __init early_snp_set_memory_private(unsigned long vaddr, unsigned long paddr,
+ unsigned int npages);
+void __init early_snp_set_memory_shared(unsigned long vaddr, unsigned long paddr,
+ unsigned int npages);
+void __init snp_prep_memory(unsigned long paddr, unsigned int sz, enum psc_op op);
+void snp_set_memory_shared(unsigned long vaddr, unsigned int npages);
+void snp_set_memory_private(unsigned long vaddr, unsigned int npages);
+void snp_set_wakeup_secondary_cpu(void);
+bool snp_init(struct boot_params *bp);
+void snp_abort(void);
+int snp_issue_guest_request(u64 exit_code, struct snp_req_data *input, unsigned long *fw_err);
#else
static inline void sev_es_ist_enter(struct pt_regs *regs) { }
static inline void sev_es_ist_exit(void) { }
static inline int sev_es_setup_ap_jump_table(struct real_mode_header *rmh) { return 0; }
static inline void sev_es_nmi_complete(void) { }
static inline int sev_es_efi_map_ghcbs(pgd_t *pgd) { return 0; }
+static inline int pvalidate(unsigned long vaddr, bool rmp_psize, bool validate) { return 0; }
+static inline int rmpadjust(unsigned long vaddr, bool rmp_psize, unsigned long attrs) { return 0; }
+static inline void setup_ghcb(void) { }
+static inline void __init
+early_snp_set_memory_private(unsigned long vaddr, unsigned long paddr, unsigned int npages) { }
+static inline void __init
+early_snp_set_memory_shared(unsigned long vaddr, unsigned long paddr, unsigned int npages) { }
+static inline void __init snp_prep_memory(unsigned long paddr, unsigned int sz, enum psc_op op) { }
+static inline void snp_set_memory_shared(unsigned long vaddr, unsigned int npages) { }
+static inline void snp_set_memory_private(unsigned long vaddr, unsigned int npages) { }
+static inline void snp_set_wakeup_secondary_cpu(void) { }
+static inline bool snp_init(struct boot_params *bp) { return false; }
+static inline void snp_abort(void) { }
+static inline int snp_issue_guest_request(u64 exit_code, struct snp_req_data *input,
+ unsigned long *fw_err)
+{
+ return -ENOTTY;
+}
#endif
#endif
diff --git a/arch/x86/include/asm/shared/msr.h b/arch/x86/include/asm/shared/msr.h
new file mode 100644
index 000000000000..1e6ec10b3a15
--- /dev/null
+++ b/arch/x86/include/asm/shared/msr.h
@@ -0,0 +1,15 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_X86_SHARED_MSR_H
+#define _ASM_X86_SHARED_MSR_H
+
+struct msr {
+ union {
+ struct {
+ u32 l;
+ u32 h;
+ };
+ u64 q;
+ };
+};
+
+#endif /* _ASM_X86_SHARED_MSR_H */
diff --git a/arch/x86/include/asm/svm.h b/arch/x86/include/asm/svm.h
index f70a5108d464..ec623e7da33d 100644
--- a/arch/x86/include/asm/svm.h
+++ b/arch/x86/include/asm/svm.h
@@ -271,6 +271,7 @@ struct vmcb_seg {
u64 base;
} __packed;
+/* Save area definition for legacy and SEV-MEM guests */
struct vmcb_save_area {
struct vmcb_seg es;
struct vmcb_seg cs;
@@ -282,12 +283,12 @@ struct vmcb_save_area {
struct vmcb_seg ldtr;
struct vmcb_seg idtr;
struct vmcb_seg tr;
- u8 reserved_1[43];
+ u8 reserved_1[42];
+ u8 vmpl;
u8 cpl;
u8 reserved_2[4];
u64 efer;
- u8 reserved_3[104];
- u64 xss; /* Valid for SEV-ES only */
+ u8 reserved_3[112];
u64 cr4;
u64 cr3;
u64 cr0;
@@ -297,7 +298,9 @@ struct vmcb_save_area {
u64 rip;
u8 reserved_4[88];
u64 rsp;
- u8 reserved_5[24];
+ u64 s_cet;
+ u64 ssp;
+ u64 isst_addr;
u64 rax;
u64 star;
u64 lstar;
@@ -308,29 +311,145 @@ struct vmcb_save_area {
u64 sysenter_esp;
u64 sysenter_eip;
u64 cr2;
- u8 reserved_6[32];
+ u8 reserved_5[32];
u64 g_pat;
u64 dbgctl;
u64 br_from;
u64 br_to;
u64 last_excp_from;
u64 last_excp_to;
-
- /*
- * The following part of the save area is valid only for
- * SEV-ES guests when referenced through the GHCB or for
- * saving to the host save area.
- */
- u8 reserved_7[72];
+ u8 reserved_6[72];
u32 spec_ctrl; /* Guest version of SPEC_CTRL at 0x2E0 */
- u8 reserved_7b[4];
+} __packed;
+
+/* Save area definition for SEV-ES and SEV-SNP guests */
+struct sev_es_save_area {
+ struct vmcb_seg es;
+ struct vmcb_seg cs;
+ struct vmcb_seg ss;
+ struct vmcb_seg ds;
+ struct vmcb_seg fs;
+ struct vmcb_seg gs;
+ struct vmcb_seg gdtr;
+ struct vmcb_seg ldtr;
+ struct vmcb_seg idtr;
+ struct vmcb_seg tr;
+ u64 vmpl0_ssp;
+ u64 vmpl1_ssp;
+ u64 vmpl2_ssp;
+ u64 vmpl3_ssp;
+ u64 u_cet;
+ u8 reserved_1[2];
+ u8 vmpl;
+ u8 cpl;
+ u8 reserved_2[4];
+ u64 efer;
+ u8 reserved_3[104];
+ u64 xss;
+ u64 cr4;
+ u64 cr3;
+ u64 cr0;
+ u64 dr7;
+ u64 dr6;
+ u64 rflags;
+ u64 rip;
+ u64 dr0;
+ u64 dr1;
+ u64 dr2;
+ u64 dr3;
+ u64 dr0_addr_mask;
+ u64 dr1_addr_mask;
+ u64 dr2_addr_mask;
+ u64 dr3_addr_mask;
+ u8 reserved_4[24];
+ u64 rsp;
+ u64 s_cet;
+ u64 ssp;
+ u64 isst_addr;
+ u64 rax;
+ u64 star;
+ u64 lstar;
+ u64 cstar;
+ u64 sfmask;
+ u64 kernel_gs_base;
+ u64 sysenter_cs;
+ u64 sysenter_esp;
+ u64 sysenter_eip;
+ u64 cr2;
+ u8 reserved_5[32];
+ u64 g_pat;
+ u64 dbgctl;
+ u64 br_from;
+ u64 br_to;
+ u64 last_excp_from;
+ u64 last_excp_to;
+ u8 reserved_7[80];
u32 pkru;
- u8 reserved_7a[20];
- u64 reserved_8; /* rax already available at 0x01f8 */
+ u8 reserved_8[20];
+ u64 reserved_9; /* rax already available at 0x01f8 */
+ u64 rcx;
+ u64 rdx;
+ u64 rbx;
+ u64 reserved_10; /* rsp already available at 0x01d8 */
+ u64 rbp;
+ u64 rsi;
+ u64 rdi;
+ u64 r8;
+ u64 r9;
+ u64 r10;
+ u64 r11;
+ u64 r12;
+ u64 r13;
+ u64 r14;
+ u64 r15;
+ u8 reserved_11[16];
+ u64 guest_exit_info_1;
+ u64 guest_exit_info_2;
+ u64 guest_exit_int_info;
+ u64 guest_nrip;
+ u64 sev_features;
+ u64 vintr_ctrl;
+ u64 guest_exit_code;
+ u64 virtual_tom;
+ u64 tlb_id;
+ u64 pcpu_id;
+ u64 event_inj;
+ u64 xcr0;
+ u8 reserved_12[16];
+
+ /* Floating point area */
+ u64 x87_dp;
+ u32 mxcsr;
+ u16 x87_ftw;
+ u16 x87_fsw;
+ u16 x87_fcw;
+ u16 x87_fop;
+ u16 x87_ds;
+ u16 x87_cs;
+ u64 x87_rip;
+ u8 fpreg_x87[80];
+ u8 fpreg_xmm[256];
+ u8 fpreg_ymm[256];
+} __packed;
+
+struct ghcb_save_area {
+ u8 reserved_1[203];
+ u8 cpl;
+ u8 reserved_2[116];
+ u64 xss;
+ u8 reserved_3[24];
+ u64 dr7;
+ u8 reserved_4[16];
+ u64 rip;
+ u8 reserved_5[88];
+ u64 rsp;
+ u8 reserved_6[24];
+ u64 rax;
+ u8 reserved_7[264];
u64 rcx;
u64 rdx;
u64 rbx;
- u64 reserved_9; /* rsp already available at 0x01d8 */
+ u8 reserved_8[8];
u64 rbp;
u64 rsi;
u64 rdi;
@@ -342,22 +461,24 @@ struct vmcb_save_area {
u64 r13;
u64 r14;
u64 r15;
- u8 reserved_10[16];
+ u8 reserved_9[16];
u64 sw_exit_code;
u64 sw_exit_info_1;
u64 sw_exit_info_2;
u64 sw_scratch;
- u8 reserved_11[56];
+ u8 reserved_10[56];
u64 xcr0;
u8 valid_bitmap[16];
u64 x87_state_gpa;
} __packed;
+#define GHCB_SHARED_BUF_SIZE 2032
+
struct ghcb {
- struct vmcb_save_area save;
- u8 reserved_save[2048 - sizeof(struct vmcb_save_area)];
+ struct ghcb_save_area save;
+ u8 reserved_save[2048 - sizeof(struct ghcb_save_area)];
- u8 shared_buffer[2032];
+ u8 shared_buffer[GHCB_SHARED_BUF_SIZE];
u8 reserved_1[10];
u16 protocol_version; /* negotiated SEV-ES/GHCB protocol version */
@@ -365,13 +486,17 @@ struct ghcb {
} __packed;
-#define EXPECTED_VMCB_SAVE_AREA_SIZE 1032
+#define EXPECTED_VMCB_SAVE_AREA_SIZE 740
+#define EXPECTED_GHCB_SAVE_AREA_SIZE 1032
+#define EXPECTED_SEV_ES_SAVE_AREA_SIZE 1648
#define EXPECTED_VMCB_CONTROL_AREA_SIZE 1024
#define EXPECTED_GHCB_SIZE PAGE_SIZE
static inline void __unused_size_checks(void)
{
BUILD_BUG_ON(sizeof(struct vmcb_save_area) != EXPECTED_VMCB_SAVE_AREA_SIZE);
+ BUILD_BUG_ON(sizeof(struct ghcb_save_area) != EXPECTED_GHCB_SAVE_AREA_SIZE);
+ BUILD_BUG_ON(sizeof(struct sev_es_save_area) != EXPECTED_SEV_ES_SAVE_AREA_SIZE);
BUILD_BUG_ON(sizeof(struct vmcb_control_area) != EXPECTED_VMCB_CONTROL_AREA_SIZE);
BUILD_BUG_ON(sizeof(struct ghcb) != EXPECTED_GHCB_SIZE);
}
@@ -441,7 +566,7 @@ struct vmcb {
/* GHCB Accessor functions */
#define GHCB_BITMAP_IDX(field) \
- (offsetof(struct vmcb_save_area, field) / sizeof(u64))
+ (offsetof(struct ghcb_save_area, field) / sizeof(u64))
#define DEFINE_GHCB_ACCESSORS(field) \
static inline bool ghcb_##field##_is_valid(const struct ghcb *ghcb) \
diff --git a/arch/x86/include/uapi/asm/bootparam.h b/arch/x86/include/uapi/asm/bootparam.h
index b25d3f82c2f3..bea5cdcdf532 100644
--- a/arch/x86/include/uapi/asm/bootparam.h
+++ b/arch/x86/include/uapi/asm/bootparam.h
@@ -10,6 +10,7 @@
#define SETUP_EFI 4
#define SETUP_APPLE_PROPERTIES 5
#define SETUP_JAILHOUSE 6
+#define SETUP_CC_BLOB 7
#define SETUP_INDIRECT (1<<31)
@@ -187,7 +188,8 @@ struct boot_params {
__u32 ext_ramdisk_image; /* 0x0c0 */
__u32 ext_ramdisk_size; /* 0x0c4 */
__u32 ext_cmd_line_ptr; /* 0x0c8 */
- __u8 _pad4[116]; /* 0x0cc */
+ __u8 _pad4[112]; /* 0x0cc */
+ __u32 cc_blob_address; /* 0x13c */
struct edid_info edid_info; /* 0x140 */
struct efi_info efi_info; /* 0x1c0 */
__u32 alt_mem_k; /* 0x1e0 */
diff --git a/arch/x86/include/uapi/asm/svm.h b/arch/x86/include/uapi/asm/svm.h
index efa969325ede..f69c168391aa 100644
--- a/arch/x86/include/uapi/asm/svm.h
+++ b/arch/x86/include/uapi/asm/svm.h
@@ -108,6 +108,14 @@
#define SVM_VMGEXIT_AP_JUMP_TABLE 0x80000005
#define SVM_VMGEXIT_SET_AP_JUMP_TABLE 0
#define SVM_VMGEXIT_GET_AP_JUMP_TABLE 1
+#define SVM_VMGEXIT_PSC 0x80000010
+#define SVM_VMGEXIT_GUEST_REQUEST 0x80000011
+#define SVM_VMGEXIT_EXT_GUEST_REQUEST 0x80000012
+#define SVM_VMGEXIT_AP_CREATION 0x80000013
+#define SVM_VMGEXIT_AP_CREATE_ON_INIT 0
+#define SVM_VMGEXIT_AP_CREATE 1
+#define SVM_VMGEXIT_AP_DESTROY 2
+#define SVM_VMGEXIT_HV_FEATURES 0x8000fffd
#define SVM_VMGEXIT_UNSUPPORTED_EVENT 0x8000ffff
/* Exit code reserved for hypervisor/software use */
@@ -218,6 +226,11 @@
{ SVM_VMGEXIT_NMI_COMPLETE, "vmgexit_nmi_complete" }, \
{ SVM_VMGEXIT_AP_HLT_LOOP, "vmgexit_ap_hlt_loop" }, \
{ SVM_VMGEXIT_AP_JUMP_TABLE, "vmgexit_ap_jump_table" }, \
+ { SVM_VMGEXIT_PSC, "vmgexit_page_state_change" }, \
+ { SVM_VMGEXIT_GUEST_REQUEST, "vmgexit_guest_request" }, \
+ { SVM_VMGEXIT_EXT_GUEST_REQUEST, "vmgexit_ext_guest_request" }, \
+ { SVM_VMGEXIT_AP_CREATION, "vmgexit_ap_creation" }, \
+ { SVM_VMGEXIT_HV_FEATURES, "vmgexit_hypervisor_feature" }, \
{ SVM_EXIT_ERR, "invalid_guest_state" }
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index c41ef42adbe8..1a2dc328cb5e 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -46,8 +46,6 @@ endif
# non-deterministic coverage.
KCOV_INSTRUMENT := n
-CFLAGS_head$(BITS).o += -fno-stack-protector
-
CFLAGS_irq.o := -I $(srctree)/$(src)/../include/asm/trace
obj-y := process_$(BITS).o signal.o
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index e342ae4db3c4..f0baf1b7522e 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -60,6 +60,7 @@
#include <asm/uv/uv.h>
#include <asm/sigframe.h>
#include <asm/traps.h>
+#include <asm/sev.h>
#include "cpu.h"
@@ -2126,6 +2127,9 @@ void cpu_init_exception_handling(void)
load_TR_desc();
+ /* GHCB needs to be setup to handle #VC. */
+ setup_ghcb();
+
/* Finally load the IDT */
load_current_idt();
}
diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c
index 4f5ecbbaae77..c185f4831498 100644
--- a/arch/x86/kernel/head64.c
+++ b/arch/x86/kernel/head64.c
@@ -143,7 +143,20 @@ static unsigned long __head sme_postprocess_startup(struct boot_params *bp, pmdv
if (sme_get_me_mask()) {
vaddr = (unsigned long)__start_bss_decrypted;
vaddr_end = (unsigned long)__end_bss_decrypted;
+
for (; vaddr < vaddr_end; vaddr += PMD_SIZE) {
+ /*
+ * On SNP, transition the page to shared in the RMP table so that
+ * it is consistent with the page table attribute change.
+ *
+ * __start_bss_decrypted has a virtual address in the high range
+ * mapping (kernel .text). PVALIDATE, by way of
+ * early_snp_set_memory_shared(), requires a valid virtual
+ * address but the kernel is currently running off of the identity
+ * mapping so use __pa() to get a *currently* valid virtual address.
+ */
+ early_snp_set_memory_shared(__pa(vaddr), __pa(vaddr), PTRS_PER_PMD);
+
i = pmd_index(vaddr);
pmd[i] -= sme_get_me_mask();
}
@@ -192,9 +205,6 @@ unsigned long __head __startup_64(unsigned long physaddr,
if (load_delta & ~PMD_PAGE_MASK)
for (;;);
- /* Activate Secure Memory Encryption (SME) if supported and enabled */
- sme_enable(bp);
-
/* Include the SME encryption mask in the fixup value */
load_delta += sme_get_me_mask();
@@ -308,15 +318,6 @@ unsigned long __head __startup_64(unsigned long physaddr,
return sme_postprocess_startup(bp, pmd);
}
-unsigned long __startup_secondary_64(void)
-{
- /*
- * Return the SME encryption mask (if SME is active) to be used as a
- * modifier for the initial pgdir entry programmed into CR3.
- */
- return sme_get_me_mask();
-}
-
/* Wipe all early page tables except for the kernel symbol map */
static void __init reset_early_page_tables(void)
{
@@ -600,8 +601,10 @@ static void startup_64_load_idt(unsigned long physbase)
void early_setup_idt(void)
{
/* VMM Communication Exception */
- if (IS_ENABLED(CONFIG_AMD_MEM_ENCRYPT))
+ if (IS_ENABLED(CONFIG_AMD_MEM_ENCRYPT)) {
+ setup_ghcb();
set_bringup_idt_handler(bringup_idt_table, X86_TRAP_VC, vc_boot_ghcb);
+ }
bringup_idt_descr.address = (unsigned long)bringup_idt_table;
native_load_idt(&bringup_idt_descr);
diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
index b8e3019547a5..7bac9a4bdf7c 100644
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -65,10 +65,39 @@ SYM_CODE_START_NOALIGN(startup_64)
leaq (__end_init_task - FRAME_SIZE)(%rip), %rsp
leaq _text(%rip), %rdi
+
+ /*
+ * initial_gs points to initial fixed_percpu_data struct with storage for
+ * the stack protector canary. Global pointer fixups are needed at this
+ * stage, so apply them as is done in fixup_pointer(), and initialize %gs
+ * such that the canary can be accessed at %gs:40 for subsequent C calls.
+ */
+ movl $MSR_GS_BASE, %ecx
+ movq initial_gs(%rip), %rax
+ movq $_text, %rdx
+ subq %rdx, %rax
+ addq %rdi, %rax
+ movq %rax, %rdx
+ shrq $32, %rdx
+ wrmsr
+
pushq %rsi
call startup_64_setup_env
popq %rsi
+#ifdef CONFIG_AMD_MEM_ENCRYPT
+ /*
+ * Activate SEV/SME memory encryption if supported/enabled. This needs to
+ * be done now, since this also includes setup of the SEV-SNP CPUID table,
+ * which needs to be done before any CPUID instructions are executed in
+ * subsequent code.
+ */
+ movq %rsi, %rdi
+ pushq %rsi
+ call sme_enable
+ popq %rsi
+#endif
+
/* Now switch to __KERNEL_CS so IRET works reliably */
pushq $__KERNEL_CS
leaq .Lon_kernel_cs(%rip), %rax
@@ -134,9 +163,11 @@ SYM_INNER_LABEL(secondary_startup_64_no_verify, SYM_L_GLOBAL)
* Retrieve the modifier (SME encryption mask if SME is active) to be
* added to the initial pgdir entry that will be programmed into CR3.
*/
- pushq %rsi
- call __startup_secondary_64
- popq %rsi
+#ifdef CONFIG_AMD_MEM_ENCRYPT
+ movq sme_me_mask, %rax
+#else
+ xorq %rax, %rax
+#endif
/* Form the CR3 value being sure to include the CR3 modifier */
addq $(init_top_pgt - __START_KERNEL_map), %rax
diff --git a/arch/x86/kernel/probe_roms.c b/arch/x86/kernel/probe_roms.c
index 36e84d904260..319fef37d9dc 100644
--- a/arch/x86/kernel/probe_roms.c
+++ b/arch/x86/kernel/probe_roms.c
@@ -21,6 +21,7 @@
#include <asm/sections.h>
#include <asm/io.h>
#include <asm/setup_arch.h>
+#include <asm/sev.h>
static struct resource system_rom_resource = {
.name = "System ROM",
@@ -197,11 +198,21 @@ static int __init romchecksum(const unsigned char *rom, unsigned long length)
void __init probe_roms(void)
{
- const unsigned char *rom;
unsigned long start, length, upper;
+ const unsigned char *rom;
unsigned char c;
int i;
+ /*
+ * The ROM memory range is not part of the e820 table and is therefore not
+ * pre-validated by BIOS. The kernel page table maps the ROM region as encrypted
+ * memory, and SNP requires encrypted memory to be validated before access.
+ * Do that here.
+ */
+ snp_prep_memory(video_rom_resource.start,
+ ((system_rom_resource.end + 1) - video_rom_resource.start),
+ SNP_PAGE_STATE_PRIVATE);
+
/* video rom */
upper = adapter_rom_resources[0].start;
for (start = video_rom_resource.start; start < upper; start += 2048) {
diff --git a/arch/x86/kernel/sev-shared.c b/arch/x86/kernel/sev-shared.c
index ce987688bbc0..b478edf43bec 100644
--- a/arch/x86/kernel/sev-shared.c
+++ b/arch/x86/kernel/sev-shared.c
@@ -14,6 +14,68 @@
#define has_cpuflag(f) boot_cpu_has(f)
#endif
+/* I/O parameters for CPUID-related helpers */
+struct cpuid_leaf {
+ u32 fn;
+ u32 subfn;
+ u32 eax;
+ u32 ebx;
+ u32 ecx;
+ u32 edx;
+};
+
+/*
+ * Individual entries of the SNP CPUID table, as defined by the SNP
+ * Firmware ABI, Revision 0.9, Section 7.1, Table 14.
+ */
+struct snp_cpuid_fn {
+ u32 eax_in;
+ u32 ecx_in;
+ u64 xcr0_in;
+ u64 xss_in;
+ u32 eax;
+ u32 ebx;
+ u32 ecx;
+ u32 edx;
+ u64 __reserved;
+} __packed;
+
+/*
+ * SNP CPUID table, as defined by the SNP Firmware ABI, Revision 0.9,
+ * Section 8.14.2.6. Also noted there is the SNP firmware-enforced limit
+ * of 64 entries per CPUID table.
+ */
+#define SNP_CPUID_COUNT_MAX 64
+
+struct snp_cpuid_table {
+ u32 count;
+ u32 __reserved1;
+ u64 __reserved2;
+ struct snp_cpuid_fn fn[SNP_CPUID_COUNT_MAX];
+} __packed;
+
+/*
+ * Since feature negotiation related variables are set early in the boot
+ * process they must reside in the .data section so as not to be zeroed
+ * out when the .bss section is later cleared.
+ *
+ * GHCB protocol version negotiated with the hypervisor.
+ */
+static u16 ghcb_version __ro_after_init;
+
+/* Copy of the SNP firmware's CPUID page. */
+static struct snp_cpuid_table cpuid_table_copy __ro_after_init;
+
+/*
+ * These will be initialized based on CPUID table so that non-present
+ * all-zero leaves (for sparse tables) can be differentiated from
+ * invalid/out-of-range leaves. This is needed since all-zero leaves
+ * still need to be post-processed.
+ */
+static u32 cpuid_std_range_max __ro_after_init;
+static u32 cpuid_hyp_range_max __ro_after_init;
+static u32 cpuid_ext_range_max __ro_after_init;
+
static bool __init sev_es_check_cpu_features(void)
{
if (!has_cpuflag(X86_FEATURE_RDRAND)) {
@@ -24,15 +86,12 @@ static bool __init sev_es_check_cpu_features(void)
return true;
}
-static void __noreturn sev_es_terminate(unsigned int reason)
+static void __noreturn sev_es_terminate(unsigned int set, unsigned int reason)
{
u64 val = GHCB_MSR_TERM_REQ;
- /*
- * Tell the hypervisor what went wrong - only reason-set 0 is
- * currently supported.
- */
- val |= GHCB_SEV_TERM_REASON(0, reason);
+ /* Tell the hypervisor what went wrong. */
+ val |= GHCB_SEV_TERM_REASON(set, reason);
/* Request Guest Termination from Hypvervisor */
sev_es_wr_ghcb_msr(val);
@@ -42,6 +101,42 @@ static void __noreturn sev_es_terminate(unsigned int reason)
asm volatile("hlt\n" : : : "memory");
}
+/*
+ * The hypervisor features are available from GHCB version 2 onward.
+ */
+static u64 get_hv_features(void)
+{
+ u64 val;
+
+ if (ghcb_version < 2)
+ return 0;
+
+ sev_es_wr_ghcb_msr(GHCB_MSR_HV_FT_REQ);
+ VMGEXIT();
+
+ val = sev_es_rd_ghcb_msr();
+ if (GHCB_RESP_CODE(val) != GHCB_MSR_HV_FT_RESP)
+ return 0;
+
+ return GHCB_MSR_HV_FT_RESP_VAL(val);
+}
+
+static void snp_register_ghcb_early(unsigned long paddr)
+{
+ unsigned long pfn = paddr >> PAGE_SHIFT;
+ u64 val;
+
+ sev_es_wr_ghcb_msr(GHCB_MSR_REG_GPA_REQ_VAL(pfn));
+ VMGEXIT();
+
+ val = sev_es_rd_ghcb_msr();
+
+ /* If the response GPA is not ours then abort the guest */
+ if ((GHCB_RESP_CODE(val) != GHCB_MSR_REG_GPA_RESP) ||
+ (GHCB_MSR_REG_GPA_RESP_VAL(val) != pfn))
+ sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_REGISTER);
+}
+
static bool sev_es_negotiate_protocol(void)
{
u64 val;
@@ -54,10 +149,12 @@ static bool sev_es_negotiate_protocol(void)
if (GHCB_MSR_INFO(val) != GHCB_MSR_SEV_INFO_RESP)
return false;
- if (GHCB_MSR_PROTO_MAX(val) < GHCB_PROTO_OUR ||
- GHCB_MSR_PROTO_MIN(val) > GHCB_PROTO_OUR)
+ if (GHCB_MSR_PROTO_MAX(val) < GHCB_PROTOCOL_MIN ||
+ GHCB_MSR_PROTO_MIN(val) > GHCB_PROTOCOL_MAX)
return false;
+ ghcb_version = min_t(size_t, GHCB_MSR_PROTO_MAX(val), GHCB_PROTOCOL_MAX);
+
return true;
}
@@ -104,10 +201,7 @@ static enum es_result verify_exception_info(struct ghcb *ghcb, struct es_em_ctxt
if (ret == 1) {
u64 info = ghcb->save.sw_exit_info_2;
- unsigned long v;
-
- info = ghcb->save.sw_exit_info_2;
- v = info & SVM_EVTINJ_VEC_MASK;
+ unsigned long v = info & SVM_EVTINJ_VEC_MASK;
/* Check if exception information from hypervisor is sane. */
if ((info & SVM_EVTINJ_VALID) &&
@@ -130,7 +224,7 @@ enum es_result sev_es_ghcb_hv_call(struct ghcb *ghcb, bool set_ghcb_msr,
u64 exit_info_1, u64 exit_info_2)
{
/* Fill in protocol and format specifiers */
- ghcb->protocol_version = GHCB_PROTOCOL_MAX;
+ ghcb->protocol_version = ghcb_version;
ghcb->ghcb_usage = GHCB_DEFAULT_USAGE;
ghcb_set_sw_exit_code(ghcb, exit_code);
@@ -150,6 +244,290 @@ enum es_result sev_es_ghcb_hv_call(struct ghcb *ghcb, bool set_ghcb_msr,
return verify_exception_info(ghcb, ctxt);
}
+static int __sev_cpuid_hv(u32 fn, int reg_idx, u32 *reg)
+{
+ u64 val;
+
+ sev_es_wr_ghcb_msr(GHCB_CPUID_REQ(fn, reg_idx));
+ VMGEXIT();
+ val = sev_es_rd_ghcb_msr();
+ if (GHCB_RESP_CODE(val) != GHCB_MSR_CPUID_RESP)
+ return -EIO;
+
+ *reg = (val >> 32);
+
+ return 0;
+}
+
+static int sev_cpuid_hv(struct cpuid_leaf *leaf)
+{
+ int ret;
+
+ /*
+ * MSR protocol does not support fetching non-zero subfunctions, but is
+ * sufficient to handle current early-boot cases. Should that change,
+ * make sure to report an error rather than ignoring the index and
+ * grabbing random values. If this issue arises in the future, handling
+ * can be added here to use GHCB-page protocol for cases that occur late
+ * enough in boot that GHCB page is available.
+ */
+ if (cpuid_function_is_indexed(leaf->fn) && leaf->subfn)
+ return -EINVAL;
+
+ ret = __sev_cpuid_hv(leaf->fn, GHCB_CPUID_REQ_EAX, &leaf->eax);
+ ret = ret ? : __sev_cpuid_hv(leaf->fn, GHCB_CPUID_REQ_EBX, &leaf->ebx);
+ ret = ret ? : __sev_cpuid_hv(leaf->fn, GHCB_CPUID_REQ_ECX, &leaf->ecx);
+ ret = ret ? : __sev_cpuid_hv(leaf->fn, GHCB_CPUID_REQ_EDX, &leaf->edx);
+
+ return ret;
+}
+
+/*
+ * This may be called early while still running on the initial identity
+ * mapping. Use RIP-relative addressing to obtain the correct address
+ * while running with the initial identity mapping as well as the
+ * switch-over to kernel virtual addresses later.
+ */
+static const struct snp_cpuid_table *snp_cpuid_get_table(void)
+{
+ void *ptr;
+
+ asm ("lea cpuid_table_copy(%%rip), %0"
+ : "=r" (ptr)
+ : "p" (&cpuid_table_copy));
+
+ return ptr;
+}
+
+/*
+ * The SNP Firmware ABI, Revision 0.9, Section 7.1, details the use of
+ * XCR0_IN and XSS_IN to encode multiple versions of 0xD subfunctions 0
+ * and 1 based on the corresponding features enabled by a particular
+ * combination of XCR0 and XSS registers so that a guest can look up the
+ * version corresponding to the features currently enabled in its XCR0/XSS
+ * registers. The only values that differ between these versions/table
+ * entries is the enabled XSAVE area size advertised via EBX.
+ *
+ * While hypervisors may choose to make use of this support, it is more
+ * robust/secure for a guest to simply find the entry corresponding to the
+ * base/legacy XSAVE area size (XCR0=1 or XCR0=3), and then calculate the
+ * XSAVE area size using subfunctions 2 through 64, as documented in APM
+ * Volume 3, Rev 3.31, Appendix E.3.8, which is what is done here.
+ *
+ * Since base/legacy XSAVE area size is documented as 0x240, use that value
+ * directly rather than relying on the base size in the CPUID table.
+ *
+ * Return: XSAVE area size on success, 0 otherwise.
+ */
+static u32 snp_cpuid_calc_xsave_size(u64 xfeatures_en, bool compacted)
+{
+ const struct snp_cpuid_table *cpuid_table = snp_cpuid_get_table();
+ u64 xfeatures_found = 0;
+ u32 xsave_size = 0x240;
+ int i;
+
+ for (i = 0; i < cpuid_table->count; i++) {
+ const struct snp_cpuid_fn *e = &cpuid_table->fn[i];
+
+ if (!(e->eax_in == 0xD && e->ecx_in > 1 && e->ecx_in < 64))
+ continue;
+ if (!(xfeatures_en & (BIT_ULL(e->ecx_in))))
+ continue;
+ if (xfeatures_found & (BIT_ULL(e->ecx_in)))
+ continue;
+
+ xfeatures_found |= (BIT_ULL(e->ecx_in));
+
+ if (compacted)
+ xsave_size += e->eax;
+ else
+ xsave_size = max(xsave_size, e->eax + e->ebx);
+ }
+
+ /*
+ * Either the guest set unsupported XCR0/XSS bits, or the corresponding
+ * entries in the CPUID table were not present. This is not a valid
+ * state to be in.
+ */
+ if (xfeatures_found != (xfeatures_en & GENMASK_ULL(63, 2)))
+ return 0;
+
+ return xsave_size;
+}
+
+static bool
+snp_cpuid_get_validated_func(struct cpuid_leaf *leaf)
+{
+ const struct snp_cpuid_table *cpuid_table = snp_cpuid_get_table();
+ int i;
+
+ for (i = 0; i < cpuid_table->count; i++) {
+ const struct snp_cpuid_fn *e = &cpuid_table->fn[i];
+
+ if (e->eax_in != leaf->fn)
+ continue;
+
+ if (cpuid_function_is_indexed(leaf->fn) && e->ecx_in != leaf->subfn)
+ continue;
+
+ /*
+ * For 0xD subfunctions 0 and 1, only use the entry corresponding
+ * to the base/legacy XSAVE area size (XCR0=1 or XCR0=3, XSS=0).
+ * See the comments above snp_cpuid_calc_xsave_size() for more
+ * details.
+ */
+ if (e->eax_in == 0xD && (e->ecx_in == 0 || e->ecx_in == 1))
+ if (!(e->xcr0_in == 1 || e->xcr0_in == 3) || e->xss_in)
+ continue;
+
+ leaf->eax = e->eax;
+ leaf->ebx = e->ebx;
+ leaf->ecx = e->ecx;
+ leaf->edx = e->edx;
+
+ return true;
+ }
+
+ return false;
+}
+
+static void snp_cpuid_hv(struct cpuid_leaf *leaf)
+{
+ if (sev_cpuid_hv(leaf))
+ sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_CPUID_HV);
+}
+
+static int snp_cpuid_postprocess(struct cpuid_leaf *leaf)
+{
+ struct cpuid_leaf leaf_hv = *leaf;
+
+ switch (leaf->fn) {
+ case 0x1:
+ snp_cpuid_hv(&leaf_hv);
+
+ /* initial APIC ID */
+ leaf->ebx = (leaf_hv.ebx & GENMASK(31, 24)) | (leaf->ebx & GENMASK(23, 0));
+ /* APIC enabled bit */
+ leaf->edx = (leaf_hv.edx & BIT(9)) | (leaf->edx & ~BIT(9));
+
+ /* OSXSAVE enabled bit */
+ if (native_read_cr4() & X86_CR4_OSXSAVE)
+ leaf->ecx |= BIT(27);
+ break;
+ case 0x7:
+ /* OSPKE enabled bit */
+ leaf->ecx &= ~BIT(4);
+ if (native_read_cr4() & X86_CR4_PKE)
+ leaf->ecx |= BIT(4);
+ break;
+ case 0xB:
+ leaf_hv.subfn = 0;
+ snp_cpuid_hv(&leaf_hv);
+
+ /* extended APIC ID */
+ leaf->edx = leaf_hv.edx;
+ break;
+ case 0xD: {
+ bool compacted = false;
+ u64 xcr0 = 1, xss = 0;
+ u32 xsave_size;
+
+ if (leaf->subfn != 0 && leaf->subfn != 1)
+ return 0;
+
+ if (native_read_cr4() & X86_CR4_OSXSAVE)
+ xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK);
+ if (leaf->subfn == 1) {
+ /* Get XSS value if XSAVES is enabled. */
+ if (leaf->eax & BIT(3)) {
+ unsigned long lo, hi;
+
+ asm volatile("rdmsr" : "=a" (lo), "=d" (hi)
+ : "c" (MSR_IA32_XSS));
+ xss = (hi << 32) | lo;
+ }
+
+ /*
+ * The PPR and APM aren't clear on what size should be
+ * encoded in 0xD:0x1:EBX when compaction is not enabled
+ * by either XSAVEC (feature bit 1) or XSAVES (feature
+ * bit 3) since SNP-capable hardware has these feature
+ * bits fixed as 1. KVM sets it to 0 in this case, but
+ * to avoid this becoming an issue it's safer to simply
+ * treat this as unsupported for SNP guests.
+ */
+ if (!(leaf->eax & (BIT(1) | BIT(3))))
+ return -EINVAL;
+
+ compacted = true;
+ }
+
+ xsave_size = snp_cpuid_calc_xsave_size(xcr0 | xss, compacted);
+ if (!xsave_size)
+ return -EINVAL;
+
+ leaf->ebx = xsave_size;
+ }
+ break;
+ case 0x8000001E:
+ snp_cpuid_hv(&leaf_hv);
+
+ /* extended APIC ID */
+ leaf->eax = leaf_hv.eax;
+ /* compute ID */
+ leaf->ebx = (leaf->ebx & GENMASK(31, 8)) | (leaf_hv.ebx & GENMASK(7, 0));
+ /* node ID */
+ leaf->ecx = (leaf->ecx & GENMASK(31, 8)) | (leaf_hv.ecx & GENMASK(7, 0));
+ break;
+ default:
+ /* No fix-ups needed, use values as-is. */
+ break;
+ }
+
+ return 0;
+}
+
+/*
+ * Returns -EOPNOTSUPP if feature not enabled. Any other non-zero return value
+ * should be treated as fatal by caller.
+ */
+static int snp_cpuid(struct cpuid_leaf *leaf)
+{
+ const struct snp_cpuid_table *cpuid_table = snp_cpuid_get_table();
+
+ if (!cpuid_table->count)
+ return -EOPNOTSUPP;
+
+ if (!snp_cpuid_get_validated_func(leaf)) {
+ /*
+ * Some hypervisors will avoid keeping track of CPUID entries
+ * where all values are zero, since they can be handled the
+ * same as out-of-range values (all-zero). This is useful here
+ * as well as it allows virtually all guest configurations to
+ * work using a single SNP CPUID table.
+ *
+ * To allow for this, there is a need to distinguish between
+ * out-of-range entries and in-range zero entries, since the
+ * CPUID table entries are only a template that may need to be
+ * augmented with additional values for things like
+ * CPU-specific information during post-processing. So if it's
+ * not in the table, set the values to zero. Then, if they are
+ * within a valid CPUID range, proceed with post-processing
+ * using zeros as the initial values. Otherwise, skip
+ * post-processing and just return zeros immediately.
+ */
+ leaf->eax = leaf->ebx = leaf->ecx = leaf->edx = 0;
+
+ /* Skip post-processing for out-of-range zero leafs. */
+ if (!(leaf->fn <= cpuid_std_range_max ||
+ (leaf->fn >= 0x40000000 && leaf->fn <= cpuid_hyp_range_max) ||
+ (leaf->fn >= 0x80000000 && leaf->fn <= cpuid_ext_range_max)))
+ return 0;
+ }
+
+ return snp_cpuid_postprocess(leaf);
+}
+
/*
* Boot VC Handler - This is the first VC handler during boot, there is no GHCB
* page yet, so it only supports the MSR based communication with the
@@ -157,40 +535,33 @@ enum es_result sev_es_ghcb_hv_call(struct ghcb *ghcb, bool set_ghcb_msr,
*/
void __init do_vc_no_ghcb(struct pt_regs *regs, unsigned long exit_code)
{
+ unsigned int subfn = lower_bits(regs->cx, 32);
unsigned int fn = lower_bits(regs->ax, 32);
- unsigned long val;
+ struct cpuid_leaf leaf;
+ int ret;
/* Only CPUID is supported via MSR protocol */
if (exit_code != SVM_EXIT_CPUID)
goto fail;
- sev_es_wr_ghcb_msr(GHCB_CPUID_REQ(fn, GHCB_CPUID_REQ_EAX));
- VMGEXIT();
- val = sev_es_rd_ghcb_msr();
- if (GHCB_RESP_CODE(val) != GHCB_MSR_CPUID_RESP)
- goto fail;
- regs->ax = val >> 32;
+ leaf.fn = fn;
+ leaf.subfn = subfn;
- sev_es_wr_ghcb_msr(GHCB_CPUID_REQ(fn, GHCB_CPUID_REQ_EBX));
- VMGEXIT();
- val = sev_es_rd_ghcb_msr();
- if (GHCB_RESP_CODE(val) != GHCB_MSR_CPUID_RESP)
- goto fail;
- regs->bx = val >> 32;
+ ret = snp_cpuid(&leaf);
+ if (!ret)
+ goto cpuid_done;
- sev_es_wr_ghcb_msr(GHCB_CPUID_REQ(fn, GHCB_CPUID_REQ_ECX));
- VMGEXIT();
- val = sev_es_rd_ghcb_msr();
- if (GHCB_RESP_CODE(val) != GHCB_MSR_CPUID_RESP)
+ if (ret != -EOPNOTSUPP)
goto fail;
- regs->cx = val >> 32;
- sev_es_wr_ghcb_msr(GHCB_CPUID_REQ(fn, GHCB_CPUID_REQ_EDX));
- VMGEXIT();
- val = sev_es_rd_ghcb_msr();
- if (GHCB_RESP_CODE(val) != GHCB_MSR_CPUID_RESP)
+ if (sev_cpuid_hv(&leaf))
goto fail;
- regs->dx = val >> 32;
+
+cpuid_done:
+ regs->ax = leaf.eax;
+ regs->bx = leaf.ebx;
+ regs->cx = leaf.ecx;
+ regs->dx = leaf.edx;
/*
* This is a VC handler and the #VC is only raised when SEV-ES is
@@ -221,7 +592,7 @@ void __init do_vc_no_ghcb(struct pt_regs *regs, unsigned long exit_code)
fail:
/* Terminate the guest */
- sev_es_terminate(GHCB_SEV_ES_GEN_REQ);
+ sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SEV_ES_GEN_REQ);
}
static enum es_result vc_insn_string_read(struct es_em_ctxt *ctxt,
@@ -481,12 +852,37 @@ static enum es_result vc_handle_ioio(struct ghcb *ghcb, struct es_em_ctxt *ctxt)
return ret;
}
+static int vc_handle_cpuid_snp(struct pt_regs *regs)
+{
+ struct cpuid_leaf leaf;
+ int ret;
+
+ leaf.fn = regs->ax;
+ leaf.subfn = regs->cx;
+ ret = snp_cpuid(&leaf);
+ if (!ret) {
+ regs->ax = leaf.eax;
+ regs->bx = leaf.ebx;
+ regs->cx = leaf.ecx;
+ regs->dx = leaf.edx;
+ }
+
+ return ret;
+}
+
static enum es_result vc_handle_cpuid(struct ghcb *ghcb,
struct es_em_ctxt *ctxt)
{
struct pt_regs *regs = ctxt->regs;
u32 cr4 = native_read_cr4();
enum es_result ret;
+ int snp_cpuid_ret;
+
+ snp_cpuid_ret = vc_handle_cpuid_snp(regs);
+ if (!snp_cpuid_ret)
+ return ES_OK;
+ if (snp_cpuid_ret != -EOPNOTSUPP)
+ return ES_VMM_ERROR;
ghcb_set_rax(ghcb, regs->ax);
ghcb_set_rcx(ghcb, regs->cx);
@@ -538,3 +934,67 @@ static enum es_result vc_handle_rdtsc(struct ghcb *ghcb,
return ES_OK;
}
+
+struct cc_setup_data {
+ struct setup_data header;
+ u32 cc_blob_address;
+};
+
+/*
+ * Search for a Confidential Computing blob passed in as a setup_data entry
+ * via the Linux Boot Protocol.
+ */
+static struct cc_blob_sev_info *find_cc_blob_setup_data(struct boot_params *bp)
+{
+ struct cc_setup_data *sd = NULL;
+ struct setup_data *hdr;
+
+ hdr = (struct setup_data *)bp->hdr.setup_data;
+
+ while (hdr) {
+ if (hdr->type == SETUP_CC_BLOB) {
+ sd = (struct cc_setup_data *)hdr;
+ return (struct cc_blob_sev_info *)(unsigned long)sd->cc_blob_address;
+ }
+ hdr = (struct setup_data *)hdr->next;
+ }
+
+ return NULL;
+}
+
+/*
+ * Initialize the kernel's copy of the SNP CPUID table, and set up the
+ * pointer that will be used to access it.
+ *
+ * Maintaining a direct mapping of the SNP CPUID table used by firmware would
+ * be possible as an alternative, but the approach is brittle since the
+ * mapping needs to be updated in sync with all the changes to virtual memory
+ * layout and related mapping facilities throughout the boot process.
+ */
+static void __init setup_cpuid_table(const struct cc_blob_sev_info *cc_info)
+{
+ const struct snp_cpuid_table *cpuid_table_fw, *cpuid_table;
+ int i;
+
+ if (!cc_info || !cc_info->cpuid_phys || cc_info->cpuid_len < PAGE_SIZE)
+ sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_CPUID);
+
+ cpuid_table_fw = (const struct snp_cpuid_table *)cc_info->cpuid_phys;
+ if (!cpuid_table_fw->count || cpuid_table_fw->count > SNP_CPUID_COUNT_MAX)
+ sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_CPUID);
+
+ cpuid_table = snp_cpuid_get_table();
+ memcpy((void *)cpuid_table, cpuid_table_fw, sizeof(*cpuid_table));
+
+ /* Initialize CPUID ranges for range-checking. */
+ for (i = 0; i < cpuid_table->count; i++) {
+ const struct snp_cpuid_fn *fn = &cpuid_table->fn[i];
+
+ if (fn->eax_in == 0x0)
+ cpuid_std_range_max = fn->eax;
+ else if (fn->eax_in == 0x40000000)
+ cpuid_hyp_range_max = fn->eax;
+ else if (fn->eax_in == 0x80000000)
+ cpuid_ext_range_max = fn->eax;
+ }
+}
diff --git a/arch/x86/kernel/sev.c b/arch/x86/kernel/sev.c
index e6d316a01fdd..c05f0124c410 100644
--- a/arch/x86/kernel/sev.c
+++ b/arch/x86/kernel/sev.c
@@ -18,6 +18,10 @@
#include <linux/memblock.h>
#include <linux/kernel.h>
#include <linux/mm.h>
+#include <linux/cpumask.h>
+#include <linux/efi.h>
+#include <linux/platform_device.h>
+#include <linux/io.h>
#include <asm/cpu_entry_area.h>
#include <asm/stacktrace.h>
@@ -31,9 +35,28 @@
#include <asm/svm.h>
#include <asm/smp.h>
#include <asm/cpu.h>
+#include <asm/apic.h>
+#include <asm/cpuid.h>
+#include <asm/cmdline.h>
#define DR7_RESET_VALUE 0x400
+/* AP INIT values as documented in the APM2 section "Processor Initialization State" */
+#define AP_INIT_CS_LIMIT 0xffff
+#define AP_INIT_DS_LIMIT 0xffff
+#define AP_INIT_LDTR_LIMIT 0xffff
+#define AP_INIT_GDTR_LIMIT 0xffff
+#define AP_INIT_IDTR_LIMIT 0xffff
+#define AP_INIT_TR_LIMIT 0xffff
+#define AP_INIT_RFLAGS_DEFAULT 0x2
+#define AP_INIT_DR6_DEFAULT 0xffff0ff0
+#define AP_INIT_GPAT_DEFAULT 0x0007040600070406ULL
+#define AP_INIT_XCR0_DEFAULT 0x1
+#define AP_INIT_X87_FTW_DEFAULT 0x5555
+#define AP_INIT_X87_FCW_DEFAULT 0x0040
+#define AP_INIT_CR0_DEFAULT 0x60000010
+#define AP_INIT_MXCSR_DEFAULT 0x1f80
+
/* For early boot hypervisor communication in SEV-ES enabled guests */
static struct ghcb boot_ghcb_page __bss_decrypted __aligned(PAGE_SIZE);
@@ -41,7 +64,10 @@ static struct ghcb boot_ghcb_page __bss_decrypted __aligned(PAGE_SIZE);
* Needs to be in the .data section because we need it NULL before bss is
* cleared
*/
-static struct ghcb __initdata *boot_ghcb;
+static struct ghcb *boot_ghcb __section(".data");
+
+/* Bitmap of SEV features supported by the hypervisor */
+static u64 sev_hv_features __ro_after_init;
/* #VC handler runtime per-CPU data */
struct sev_es_runtime_data {
@@ -87,6 +113,15 @@ struct ghcb_state {
static DEFINE_PER_CPU(struct sev_es_runtime_data*, runtime_data);
DEFINE_STATIC_KEY_FALSE(sev_es_enable_key);
+static DEFINE_PER_CPU(struct sev_es_save_area *, sev_vmsa);
+
+struct sev_config {
+ __u64 debug : 1,
+ __reserved : 63;
+};
+
+static struct sev_config sev_cfg __read_mostly;
+
static __always_inline bool on_vc_stack(struct pt_regs *regs)
{
unsigned long sp = regs->sp;
@@ -523,13 +558,68 @@ void noinstr __sev_es_nmi_complete(void)
__sev_put_ghcb(&state);
}
-static u64 get_jump_table_addr(void)
+static u64 __init get_secrets_page(void)
+{
+ u64 pa_data = boot_params.cc_blob_address;
+ struct cc_blob_sev_info info;
+ void *map;
+
+ /*
+ * The CC blob contains the address of the secrets page, check if the
+ * blob is present.
+ */
+ if (!pa_data)
+ return 0;
+
+ map = early_memremap(pa_data, sizeof(info));
+ if (!map) {
+ pr_err("Unable to locate SNP secrets page: failed to map the Confidential Computing blob.\n");
+ return 0;
+ }
+ memcpy(&info, map, sizeof(info));
+ early_memunmap(map, sizeof(info));
+
+ /* smoke-test the secrets page passed */
+ if (!info.secrets_phys || info.secrets_len != PAGE_SIZE)
+ return 0;
+
+ return info.secrets_phys;
+}
+
+static u64 __init get_snp_jump_table_addr(void)
+{
+ struct snp_secrets_page_layout *layout;
+ void __iomem *mem;
+ u64 pa, addr;
+
+ pa = get_secrets_page();
+ if (!pa)
+ return 0;
+
+ mem = ioremap_encrypted(pa, PAGE_SIZE);
+ if (!mem) {
+ pr_err("Unable to locate AP jump table address: failed to map the SNP secrets page.\n");
+ return 0;
+ }
+
+ layout = (__force struct snp_secrets_page_layout *)mem;
+
+ addr = layout->os_area.ap_jump_table_pa;
+ iounmap(mem);
+
+ return addr;
+}
+
+static u64 __init get_jump_table_addr(void)
{
struct ghcb_state state;
unsigned long flags;
struct ghcb *ghcb;
u64 ret = 0;
+ if (cc_platform_has(CC_ATTR_GUEST_SEV_SNP))
+ return get_snp_jump_table_addr();
+
local_irq_save(flags);
ghcb = __sev_get_ghcb(&state);
@@ -553,7 +643,496 @@ static u64 get_jump_table_addr(void)
return ret;
}
-int sev_es_setup_ap_jump_table(struct real_mode_header *rmh)
+static void pvalidate_pages(unsigned long vaddr, unsigned int npages, bool validate)
+{
+ unsigned long vaddr_end;
+ int rc;
+
+ vaddr = vaddr & PAGE_MASK;
+ vaddr_end = vaddr + (npages << PAGE_SHIFT);
+
+ while (vaddr < vaddr_end) {
+ rc = pvalidate(vaddr, RMP_PG_SIZE_4K, validate);
+ if (WARN(rc, "Failed to validate address 0x%lx ret %d", vaddr, rc))
+ sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_PVALIDATE);
+
+ vaddr = vaddr + PAGE_SIZE;
+ }
+}
+
+static void __init early_set_pages_state(unsigned long paddr, unsigned int npages, enum psc_op op)
+{
+ unsigned long paddr_end;
+ u64 val;
+
+ paddr = paddr & PAGE_MASK;
+ paddr_end = paddr + (npages << PAGE_SHIFT);
+
+ while (paddr < paddr_end) {
+ /*
+ * Use the MSR protocol because this function can be called before
+ * the GHCB is established.
+ */
+ sev_es_wr_ghcb_msr(GHCB_MSR_PSC_REQ_GFN(paddr >> PAGE_SHIFT, op));
+ VMGEXIT();
+
+ val = sev_es_rd_ghcb_msr();
+
+ if (WARN(GHCB_RESP_CODE(val) != GHCB_MSR_PSC_RESP,
+ "Wrong PSC response code: 0x%x\n",
+ (unsigned int)GHCB_RESP_CODE(val)))
+ goto e_term;
+
+ if (WARN(GHCB_MSR_PSC_RESP_VAL(val),
+ "Failed to change page state to '%s' paddr 0x%lx error 0x%llx\n",
+ op == SNP_PAGE_STATE_PRIVATE ? "private" : "shared",
+ paddr, GHCB_MSR_PSC_RESP_VAL(val)))
+ goto e_term;
+
+ paddr = paddr + PAGE_SIZE;
+ }
+
+ return;
+
+e_term:
+ sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_PSC);
+}
+
+void __init early_snp_set_memory_private(unsigned long vaddr, unsigned long paddr,
+ unsigned int npages)
+{
+ if (!cc_platform_has(CC_ATTR_GUEST_SEV_SNP))
+ return;
+
+ /*
+ * Ask the hypervisor to mark the memory pages as private in the RMP
+ * table.
+ */
+ early_set_pages_state(paddr, npages, SNP_PAGE_STATE_PRIVATE);
+
+ /* Validate the memory pages after they've been added in the RMP table. */
+ pvalidate_pages(vaddr, npages, true);
+}
+
+void __init early_snp_set_memory_shared(unsigned long vaddr, unsigned long paddr,
+ unsigned int npages)
+{
+ if (!cc_platform_has(CC_ATTR_GUEST_SEV_SNP))
+ return;
+
+ /* Invalidate the memory pages before they are marked shared in the RMP table. */
+ pvalidate_pages(vaddr, npages, false);
+
+ /* Ask hypervisor to mark the memory pages shared in the RMP table. */
+ early_set_pages_state(paddr, npages, SNP_PAGE_STATE_SHARED);
+}
+
+void __init snp_prep_memory(unsigned long paddr, unsigned int sz, enum psc_op op)
+{
+ unsigned long vaddr, npages;
+
+ vaddr = (unsigned long)__va(paddr);
+ npages = PAGE_ALIGN(sz) >> PAGE_SHIFT;
+
+ if (op == SNP_PAGE_STATE_PRIVATE)
+ early_snp_set_memory_private(vaddr, paddr, npages);
+ else if (op == SNP_PAGE_STATE_SHARED)
+ early_snp_set_memory_shared(vaddr, paddr, npages);
+ else
+ WARN(1, "invalid memory op %d\n", op);
+}
+
+static int vmgexit_psc(struct snp_psc_desc *desc)
+{
+ int cur_entry, end_entry, ret = 0;
+ struct snp_psc_desc *data;
+ struct ghcb_state state;
+ struct es_em_ctxt ctxt;
+ unsigned long flags;
+ struct ghcb *ghcb;
+
+ /*
+ * __sev_get_ghcb() needs to run with IRQs disabled because it is using
+ * a per-CPU GHCB.
+ */
+ local_irq_save(flags);
+
+ ghcb = __sev_get_ghcb(&state);
+ if (!ghcb) {
+ ret = 1;
+ goto out_unlock;
+ }
+
+ /* Copy the input desc into GHCB shared buffer */
+ data = (struct snp_psc_desc *)ghcb->shared_buffer;
+ memcpy(ghcb->shared_buffer, desc, min_t(int, GHCB_SHARED_BUF_SIZE, sizeof(*desc)));
+
+ /*
+ * As per the GHCB specification, the hypervisor can resume the guest
+ * before processing all the entries. Check whether all the entries
+ * are processed. If not, then keep retrying. Note, the hypervisor
+ * will update the data memory directly to indicate the status, so
+ * reference the data->hdr everywhere.
+ *
+ * The strategy here is to wait for the hypervisor to change the page
+ * state in the RMP table before guest accesses the memory pages. If the
+ * page state change was not successful, then later memory access will
+ * result in a crash.
+ */
+ cur_entry = data->hdr.cur_entry;
+ end_entry = data->hdr.end_entry;
+
+ while (data->hdr.cur_entry <= data->hdr.end_entry) {
+ ghcb_set_sw_scratch(ghcb, (u64)__pa(data));
+
+ /* This will advance the shared buffer data points to. */
+ ret = sev_es_ghcb_hv_call(ghcb, true, &ctxt, SVM_VMGEXIT_PSC, 0, 0);
+
+ /*
+ * Page State Change VMGEXIT can pass error code through
+ * exit_info_2.
+ */
+ if (WARN(ret || ghcb->save.sw_exit_info_2,
+ "SNP: PSC failed ret=%d exit_info_2=%llx\n",
+ ret, ghcb->save.sw_exit_info_2)) {
+ ret = 1;
+ goto out;
+ }
+
+ /* Verify that reserved bit is not set */
+ if (WARN(data->hdr.reserved, "Reserved bit is set in the PSC header\n")) {
+ ret = 1;
+ goto out;
+ }
+
+ /*
+ * Sanity check that entry processing is not going backwards.
+ * This will happen only if hypervisor is tricking us.
+ */
+ if (WARN(data->hdr.end_entry > end_entry || cur_entry > data->hdr.cur_entry,
+"SNP: PSC processing going backward, end_entry %d (got %d) cur_entry %d (got %d)\n",
+ end_entry, data->hdr.end_entry, cur_entry, data->hdr.cur_entry)) {
+ ret = 1;
+ goto out;
+ }
+ }
+
+out:
+ __sev_put_ghcb(&state);
+
+out_unlock:
+ local_irq_restore(flags);
+
+ return ret;
+}
+
+static void __set_pages_state(struct snp_psc_desc *data, unsigned long vaddr,
+ unsigned long vaddr_end, int op)
+{
+ struct psc_hdr *hdr;
+ struct psc_entry *e;
+ unsigned long pfn;
+ int i;
+
+ hdr = &data->hdr;
+ e = data->entries;
+
+ memset(data, 0, sizeof(*data));
+ i = 0;
+
+ while (vaddr < vaddr_end) {
+ if (is_vmalloc_addr((void *)vaddr))
+ pfn = vmalloc_to_pfn((void *)vaddr);
+ else
+ pfn = __pa(vaddr) >> PAGE_SHIFT;
+
+ e->gfn = pfn;
+ e->operation = op;
+ hdr->end_entry = i;
+
+ /*
+ * Current SNP implementation doesn't keep track of the RMP page
+ * size so use 4K for simplicity.
+ */
+ e->pagesize = RMP_PG_SIZE_4K;
+
+ vaddr = vaddr + PAGE_SIZE;
+ e++;
+ i++;
+ }
+
+ if (vmgexit_psc(data))
+ sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_PSC);
+}
+
+static void set_pages_state(unsigned long vaddr, unsigned int npages, int op)
+{
+ unsigned long vaddr_end, next_vaddr;
+ struct snp_psc_desc *desc;
+
+ desc = kmalloc(sizeof(*desc), GFP_KERNEL_ACCOUNT);
+ if (!desc)
+ panic("SNP: failed to allocate memory for PSC descriptor\n");
+
+ vaddr = vaddr & PAGE_MASK;
+ vaddr_end = vaddr + (npages << PAGE_SHIFT);
+
+ while (vaddr < vaddr_end) {
+ /* Calculate the last vaddr that fits in one struct snp_psc_desc. */
+ next_vaddr = min_t(unsigned long, vaddr_end,
+ (VMGEXIT_PSC_MAX_ENTRY * PAGE_SIZE) + vaddr);
+
+ __set_pages_state(desc, vaddr, next_vaddr, op);
+
+ vaddr = next_vaddr;
+ }
+
+ kfree(desc);
+}
+
+void snp_set_memory_shared(unsigned long vaddr, unsigned int npages)
+{
+ if (!cc_platform_has(CC_ATTR_GUEST_SEV_SNP))
+ return;
+
+ pvalidate_pages(vaddr, npages, false);
+
+ set_pages_state(vaddr, npages, SNP_PAGE_STATE_SHARED);
+}
+
+void snp_set_memory_private(unsigned long vaddr, unsigned int npages)
+{
+ if (!cc_platform_has(CC_ATTR_GUEST_SEV_SNP))
+ return;
+
+ set_pages_state(vaddr, npages, SNP_PAGE_STATE_PRIVATE);
+
+ pvalidate_pages(vaddr, npages, true);
+}
+
+static int snp_set_vmsa(void *va, bool vmsa)
+{
+ u64 attrs;
+
+ /*
+ * Running at VMPL0 allows the kernel to change the VMSA bit for a page
+ * using the RMPADJUST instruction. However, for the instruction to
+ * succeed it must target the permissions of a lesser privileged
+ * (higher numbered) VMPL level, so use VMPL1 (refer to the RMPADJUST
+ * instruction in the AMD64 APM Volume 3).
+ */
+ attrs = 1;
+ if (vmsa)
+ attrs |= RMPADJUST_VMSA_PAGE_BIT;
+
+ return rmpadjust((unsigned long)va, RMP_PG_SIZE_4K, attrs);
+}
+
+#define __ATTR_BASE (SVM_SELECTOR_P_MASK | SVM_SELECTOR_S_MASK)
+#define INIT_CS_ATTRIBS (__ATTR_BASE | SVM_SELECTOR_READ_MASK | SVM_SELECTOR_CODE_MASK)
+#define INIT_DS_ATTRIBS (__ATTR_BASE | SVM_SELECTOR_WRITE_MASK)
+
+#define INIT_LDTR_ATTRIBS (SVM_SELECTOR_P_MASK | 2)
+#define INIT_TR_ATTRIBS (SVM_SELECTOR_P_MASK | 3)
+
+static void *snp_alloc_vmsa_page(void)
+{
+ struct page *p;
+
+ /*
+ * Allocate VMSA page to work around the SNP erratum where the CPU will
+ * incorrectly signal an RMP violation #PF if a large page (2MB or 1GB)
+ * collides with the RMP entry of VMSA page. The recommended workaround
+ * is to not use a large page.
+ *
+ * Allocate an 8k page which is also 8k-aligned.
+ */
+ p = alloc_pages(GFP_KERNEL_ACCOUNT | __GFP_ZERO, 1);
+ if (!p)
+ return NULL;
+
+ split_page(p, 1);
+
+ /* Free the first 4k. This page may be 2M/1G aligned and cannot be used. */
+ __free_page(p);
+
+ return page_address(p + 1);
+}
+
+static void snp_cleanup_vmsa(struct sev_es_save_area *vmsa)
+{
+ int err;
+
+ err = snp_set_vmsa(vmsa, false);
+ if (err)
+ pr_err("clear VMSA page failed (%u), leaking page\n", err);
+ else
+ free_page((unsigned long)vmsa);
+}
+
+static int wakeup_cpu_via_vmgexit(int apic_id, unsigned long start_ip)
+{
+ struct sev_es_save_area *cur_vmsa, *vmsa;
+ struct ghcb_state state;
+ unsigned long flags;
+ struct ghcb *ghcb;
+ u8 sipi_vector;
+ int cpu, ret;
+ u64 cr4;
+
+ /*
+ * The hypervisor SNP feature support check has happened earlier, just check
+ * the AP_CREATION one here.
+ */
+ if (!(sev_hv_features & GHCB_HV_FT_SNP_AP_CREATION))
+ return -EOPNOTSUPP;
+
+ /*
+ * Verify the desired start IP against the known trampoline start IP
+ * to catch any future new trampolines that may be introduced that
+ * would require a new protected guest entry point.
+ */
+ if (WARN_ONCE(start_ip != real_mode_header->trampoline_start,
+ "Unsupported SNP start_ip: %lx\n", start_ip))
+ return -EINVAL;
+
+ /* Override start_ip with known protected guest start IP */
+ start_ip = real_mode_header->sev_es_trampoline_start;
+
+ /* Find the logical CPU for the APIC ID */
+ for_each_present_cpu(cpu) {
+ if (arch_match_cpu_phys_id(cpu, apic_id))
+ break;
+ }
+ if (cpu >= nr_cpu_ids)
+ return -EINVAL;
+
+ cur_vmsa = per_cpu(sev_vmsa, cpu);
+
+ /*
+ * A new VMSA is created each time because there is no guarantee that
+ * the current VMSA is the kernels or that the vCPU is not running. If
+ * an attempt was done to use the current VMSA with a running vCPU, a
+ * #VMEXIT of that vCPU would wipe out all of the settings being done
+ * here.
+ */
+ vmsa = (struct sev_es_save_area *)snp_alloc_vmsa_page();
+ if (!vmsa)
+ return -ENOMEM;
+
+ /* CR4 should maintain the MCE value */
+ cr4 = native_read_cr4() & X86_CR4_MCE;
+
+ /* Set the CS value based on the start_ip converted to a SIPI vector */
+ sipi_vector = (start_ip >> 12);
+ vmsa->cs.base = sipi_vector << 12;
+ vmsa->cs.limit = AP_INIT_CS_LIMIT;
+ vmsa->cs.attrib = INIT_CS_ATTRIBS;
+ vmsa->cs.selector = sipi_vector << 8;
+
+ /* Set the RIP value based on start_ip */
+ vmsa->rip = start_ip & 0xfff;
+
+ /* Set AP INIT defaults as documented in the APM */
+ vmsa->ds.limit = AP_INIT_DS_LIMIT;
+ vmsa->ds.attrib = INIT_DS_ATTRIBS;
+ vmsa->es = vmsa->ds;
+ vmsa->fs = vmsa->ds;
+ vmsa->gs = vmsa->ds;
+ vmsa->ss = vmsa->ds;
+
+ vmsa->gdtr.limit = AP_INIT_GDTR_LIMIT;
+ vmsa->ldtr.limit = AP_INIT_LDTR_LIMIT;
+ vmsa->ldtr.attrib = INIT_LDTR_ATTRIBS;
+ vmsa->idtr.limit = AP_INIT_IDTR_LIMIT;
+ vmsa->tr.limit = AP_INIT_TR_LIMIT;
+ vmsa->tr.attrib = INIT_TR_ATTRIBS;
+
+ vmsa->cr4 = cr4;
+ vmsa->cr0 = AP_INIT_CR0_DEFAULT;
+ vmsa->dr7 = DR7_RESET_VALUE;
+ vmsa->dr6 = AP_INIT_DR6_DEFAULT;
+ vmsa->rflags = AP_INIT_RFLAGS_DEFAULT;
+ vmsa->g_pat = AP_INIT_GPAT_DEFAULT;
+ vmsa->xcr0 = AP_INIT_XCR0_DEFAULT;
+ vmsa->mxcsr = AP_INIT_MXCSR_DEFAULT;
+ vmsa->x87_ftw = AP_INIT_X87_FTW_DEFAULT;
+ vmsa->x87_fcw = AP_INIT_X87_FCW_DEFAULT;
+
+ /* SVME must be set. */
+ vmsa->efer = EFER_SVME;
+
+ /*
+ * Set the SNP-specific fields for this VMSA:
+ * VMPL level
+ * SEV_FEATURES (matches the SEV STATUS MSR right shifted 2 bits)
+ */
+ vmsa->vmpl = 0;
+ vmsa->sev_features = sev_status >> 2;
+
+ /* Switch the page over to a VMSA page now that it is initialized */
+ ret = snp_set_vmsa(vmsa, true);
+ if (ret) {
+ pr_err("set VMSA page failed (%u)\n", ret);
+ free_page((unsigned long)vmsa);
+
+ return -EINVAL;
+ }
+
+ /* Issue VMGEXIT AP Creation NAE event */
+ local_irq_save(flags);
+
+ ghcb = __sev_get_ghcb(&state);
+
+ vc_ghcb_invalidate(ghcb);
+ ghcb_set_rax(ghcb, vmsa->sev_features);
+ ghcb_set_sw_exit_code(ghcb, SVM_VMGEXIT_AP_CREATION);
+ ghcb_set_sw_exit_info_1(ghcb, ((u64)apic_id << 32) | SVM_VMGEXIT_AP_CREATE);
+ ghcb_set_sw_exit_info_2(ghcb, __pa(vmsa));
+
+ sev_es_wr_ghcb_msr(__pa(ghcb));
+ VMGEXIT();
+
+ if (!ghcb_sw_exit_info_1_is_valid(ghcb) ||
+ lower_32_bits(ghcb->save.sw_exit_info_1)) {
+ pr_err("SNP AP Creation error\n");
+ ret = -EINVAL;
+ }
+
+ __sev_put_ghcb(&state);
+
+ local_irq_restore(flags);
+
+ /* Perform cleanup if there was an error */
+ if (ret) {
+ snp_cleanup_vmsa(vmsa);
+ vmsa = NULL;
+ }
+
+ /* Free up any previous VMSA page */
+ if (cur_vmsa)
+ snp_cleanup_vmsa(cur_vmsa);
+
+ /* Record the current VMSA page */
+ per_cpu(sev_vmsa, cpu) = vmsa;
+
+ return ret;
+}
+
+void snp_set_wakeup_secondary_cpu(void)
+{
+ if (!cc_platform_has(CC_ATTR_GUEST_SEV_SNP))
+ return;
+
+ /*
+ * Always set this override if SNP is enabled. This makes it the
+ * required method to start APs under SNP. If the hypervisor does
+ * not support AP creation, then no APs will be started.
+ */
+ apic->wakeup_secondary_cpu = wakeup_cpu_via_vmgexit;
+}
+
+int __init sev_es_setup_ap_jump_table(struct real_mode_header *rmh)
{
u16 startup_cs, startup_ip;
phys_addr_t jump_table_pa;
@@ -644,15 +1223,39 @@ static enum es_result vc_handle_msr(struct ghcb *ghcb, struct es_em_ctxt *ctxt)
return ret;
}
-/*
- * This function runs on the first #VC exception after the kernel
- * switched to virtual addresses.
- */
-static bool __init sev_es_setup_ghcb(void)
+static void snp_register_per_cpu_ghcb(void)
+{
+ struct sev_es_runtime_data *data;
+ struct ghcb *ghcb;
+
+ data = this_cpu_read(runtime_data);
+ ghcb = &data->ghcb_page;
+
+ snp_register_ghcb_early(__pa(ghcb));
+}
+
+void setup_ghcb(void)
{
+ if (!cc_platform_has(CC_ATTR_GUEST_STATE_ENCRYPT))
+ return;
+
/* First make sure the hypervisor talks a supported protocol. */
if (!sev_es_negotiate_protocol())
- return false;
+ sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SEV_ES_GEN_REQ);
+
+ /*
+ * Check whether the runtime #VC exception handler is active. It uses
+ * the per-CPU GHCB page which is set up by sev_es_init_vc_handling().
+ *
+ * If SNP is active, register the per-CPU GHCB page so that the runtime
+ * exception handler can use it.
+ */
+ if (initial_vc_handler == (unsigned long)kernel_exc_vmm_communication) {
+ if (cc_platform_has(CC_ATTR_GUEST_SEV_SNP))
+ snp_register_per_cpu_ghcb();
+
+ return;
+ }
/*
* Clear the boot_ghcb. The first exception comes in before the bss
@@ -663,7 +1266,9 @@ static bool __init sev_es_setup_ghcb(void)
/* Alright - Make the boot-ghcb public */
boot_ghcb = &boot_ghcb_page;
- return true;
+ /* SNP guest requires that GHCB GPA must be registered. */
+ if (cc_platform_has(CC_ATTR_GUEST_SEV_SNP))
+ snp_register_ghcb_early(__pa(&boot_ghcb_page));
}
#ifdef CONFIG_HOTPLUG_CPU
@@ -766,6 +1371,17 @@ void __init sev_es_init_vc_handling(void)
if (!sev_es_check_cpu_features())
panic("SEV-ES CPU Features missing");
+ /*
+ * SNP is supported in v2 of the GHCB spec which mandates support for HV
+ * features.
+ */
+ if (cc_platform_has(CC_ATTR_GUEST_SEV_SNP)) {
+ sev_hv_features = get_hv_features();
+
+ if (!(sev_hv_features & GHCB_HV_FT_SNP))
+ sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SNP_UNSUPPORTED);
+ }
+
/* Enable SEV-ES special handling */
static_branch_enable(&sev_es_enable_key);
@@ -1337,7 +1953,7 @@ DEFINE_IDTENTRY_VC_KERNEL(exc_vmm_communication)
show_regs(regs);
/* Ask hypervisor to sev_es_terminate */
- sev_es_terminate(GHCB_SEV_ES_GEN_REQ);
+ sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SEV_ES_GEN_REQ);
/* If that fails and we get here - just panic */
panic("Returned from Terminate-Request to Hypervisor\n");
@@ -1383,10 +1999,6 @@ bool __init handle_vc_boot_ghcb(struct pt_regs *regs)
struct es_em_ctxt ctxt;
enum es_result result;
- /* Do initial setup or terminate the guest */
- if (unlikely(boot_ghcb == NULL && !sev_es_setup_ghcb()))
- sev_es_terminate(GHCB_SEV_ES_GEN_REQ);
-
vc_ghcb_invalidate(boot_ghcb);
result = vc_init_em_ctxt(&ctxt, regs, exit_code);
@@ -1425,6 +2037,215 @@ bool __init handle_vc_boot_ghcb(struct pt_regs *regs)
fail:
show_regs(regs);
- while (true)
- halt();
+ sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SEV_ES_GEN_REQ);
+}
+
+/*
+ * Initial set up of SNP relies on information provided by the
+ * Confidential Computing blob, which can be passed to the kernel
+ * in the following ways, depending on how it is booted:
+ *
+ * - when booted via the boot/decompress kernel:
+ * - via boot_params
+ *
+ * - when booted directly by firmware/bootloader (e.g. CONFIG_PVH):
+ * - via a setup_data entry, as defined by the Linux Boot Protocol
+ *
+ * Scan for the blob in that order.
+ */
+static __init struct cc_blob_sev_info *find_cc_blob(struct boot_params *bp)
+{
+ struct cc_blob_sev_info *cc_info;
+
+ /* Boot kernel would have passed the CC blob via boot_params. */
+ if (bp->cc_blob_address) {
+ cc_info = (struct cc_blob_sev_info *)(unsigned long)bp->cc_blob_address;
+ goto found_cc_info;
+ }
+
+ /*
+ * If kernel was booted directly, without the use of the
+ * boot/decompression kernel, the CC blob may have been passed via
+ * setup_data instead.
+ */
+ cc_info = find_cc_blob_setup_data(bp);
+ if (!cc_info)
+ return NULL;
+
+found_cc_info:
+ if (cc_info->magic != CC_BLOB_SEV_HDR_MAGIC)
+ snp_abort();
+
+ return cc_info;
+}
+
+bool __init snp_init(struct boot_params *bp)
+{
+ struct cc_blob_sev_info *cc_info;
+
+ if (!bp)
+ return false;
+
+ cc_info = find_cc_blob(bp);
+ if (!cc_info)
+ return false;
+
+ setup_cpuid_table(cc_info);
+
+ /*
+ * The CC blob will be used later to access the secrets page. Cache
+ * it here like the boot kernel does.
+ */
+ bp->cc_blob_address = (u32)(unsigned long)cc_info;
+
+ return true;
+}
+
+void __init snp_abort(void)
+{
+ sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SNP_UNSUPPORTED);
+}
+
+static void dump_cpuid_table(void)
+{
+ const struct snp_cpuid_table *cpuid_table = snp_cpuid_get_table();
+ int i = 0;
+
+ pr_info("count=%d reserved=0x%x reserved2=0x%llx\n",
+ cpuid_table->count, cpuid_table->__reserved1, cpuid_table->__reserved2);
+
+ for (i = 0; i < SNP_CPUID_COUNT_MAX; i++) {
+ const struct snp_cpuid_fn *fn = &cpuid_table->fn[i];
+
+ pr_info("index=%3d fn=0x%08x subfn=0x%08x: eax=0x%08x ebx=0x%08x ecx=0x%08x edx=0x%08x xcr0_in=0x%016llx xss_in=0x%016llx reserved=0x%016llx\n",
+ i, fn->eax_in, fn->ecx_in, fn->eax, fn->ebx, fn->ecx,
+ fn->edx, fn->xcr0_in, fn->xss_in, fn->__reserved);
+ }
+}
+
+/*
+ * It is useful from an auditing/testing perspective to provide an easy way
+ * for the guest owner to know that the CPUID table has been initialized as
+ * expected, but that initialization happens too early in boot to print any
+ * sort of indicator, and there's not really any other good place to do it,
+ * so do it here.
+ */
+static int __init report_cpuid_table(void)
+{
+ const struct snp_cpuid_table *cpuid_table = snp_cpuid_get_table();
+
+ if (!cpuid_table->count)
+ return 0;
+
+ pr_info("Using SNP CPUID table, %d entries present.\n",
+ cpuid_table->count);
+
+ if (sev_cfg.debug)
+ dump_cpuid_table();
+
+ return 0;
+}
+arch_initcall(report_cpuid_table);
+
+static int __init init_sev_config(char *str)
+{
+ char *s;
+
+ while ((s = strsep(&str, ","))) {
+ if (!strcmp(s, "debug")) {
+ sev_cfg.debug = true;
+ continue;
+ }
+
+ pr_info("SEV command-line option '%s' was not recognized\n", s);
+ }
+
+ return 1;
+}
+__setup("sev=", init_sev_config);
+
+int snp_issue_guest_request(u64 exit_code, struct snp_req_data *input, unsigned long *fw_err)
+{
+ struct ghcb_state state;
+ struct es_em_ctxt ctxt;
+ unsigned long flags;
+ struct ghcb *ghcb;
+ int ret;
+
+ if (!cc_platform_has(CC_ATTR_GUEST_SEV_SNP))
+ return -ENODEV;
+
+ if (!fw_err)
+ return -EINVAL;
+
+ /*
+ * __sev_get_ghcb() needs to run with IRQs disabled because it is using
+ * a per-CPU GHCB.
+ */
+ local_irq_save(flags);
+
+ ghcb = __sev_get_ghcb(&state);
+ if (!ghcb) {
+ ret = -EIO;
+ goto e_restore_irq;
+ }
+
+ vc_ghcb_invalidate(ghcb);
+
+ if (exit_code == SVM_VMGEXIT_EXT_GUEST_REQUEST) {
+ ghcb_set_rax(ghcb, input->data_gpa);
+ ghcb_set_rbx(ghcb, input->data_npages);
+ }
+
+ ret = sev_es_ghcb_hv_call(ghcb, true, &ctxt, exit_code, input->req_gpa, input->resp_gpa);
+ if (ret)
+ goto e_put;
+
+ if (ghcb->save.sw_exit_info_2) {
+ /* Number of expected pages are returned in RBX */
+ if (exit_code == SVM_VMGEXIT_EXT_GUEST_REQUEST &&
+ ghcb->save.sw_exit_info_2 == SNP_GUEST_REQ_INVALID_LEN)
+ input->data_npages = ghcb_get_rbx(ghcb);
+
+ *fw_err = ghcb->save.sw_exit_info_2;
+
+ ret = -EIO;
+ }
+
+e_put:
+ __sev_put_ghcb(&state);
+e_restore_irq:
+ local_irq_restore(flags);
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(snp_issue_guest_request);
+
+static struct platform_device sev_guest_device = {
+ .name = "sev-guest",
+ .id = -1,
+};
+
+static int __init snp_init_platform_device(void)
+{
+ struct sev_guest_platform_data data;
+ u64 gpa;
+
+ if (!cc_platform_has(CC_ATTR_GUEST_SEV_SNP))
+ return -ENODEV;
+
+ gpa = get_secrets_page();
+ if (!gpa)
+ return -ENODEV;
+
+ data.secrets_gpa = gpa;
+ if (platform_device_add_data(&sev_guest_device, &data, sizeof(data)))
+ return -ENODEV;
+
+ if (platform_device_register(&sev_guest_device))
+ return -ENODEV;
+
+ pr_info("SNP guest platform device initialized.\n");
+ return 0;
}
+device_initcall(snp_init_platform_device);
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 2ef14772dc04..85d7b1c5eb70 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -82,6 +82,7 @@
#include <asm/spec-ctrl.h>
#include <asm/hw_irq.h>
#include <asm/stackprotector.h>
+#include <asm/sev.h>
/* representing HT siblings of each logical CPU */
DEFINE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_sibling_map);
@@ -1430,6 +1431,8 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus)
smp_quirk_init_udelay();
speculative_store_bypass_ht_init();
+
+ snp_set_wakeup_secondary_cpu();
}
void arch_thaw_secondary_cpus_begin(void)
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index 0c1ba6aa0765..de6d44e07e34 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -19,6 +19,7 @@
#include <asm/user.h>
#include <asm/fpu/xstate.h>
#include <asm/sgx.h>
+#include <asm/cpuid.h>
#include "cpuid.h"
#include "lapic.h"
#include "mmu.h"
@@ -744,24 +745,8 @@ static struct kvm_cpuid_entry2 *do_host_cpuid(struct kvm_cpuid_array *array,
cpuid_count(entry->function, entry->index,
&entry->eax, &entry->ebx, &entry->ecx, &entry->edx);
- switch (function) {
- case 4:
- case 7:
- case 0xb:
- case 0xd:
- case 0xf:
- case 0x10:
- case 0x12:
- case 0x14:
- case 0x17:
- case 0x18:
- case 0x1d:
- case 0x1e:
- case 0x1f:
- case 0x8000001d:
+ if (cpuid_function_is_indexed(function))
entry->flags |= KVM_CPUID_FLAG_SIGNIFCANT_INDEX;
- break;
- }
return entry;
}
diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index 7c392873626f..636c77ef55fc 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -562,12 +562,20 @@ e_unpin:
static int sev_es_sync_vmsa(struct vcpu_svm *svm)
{
- struct vmcb_save_area *save = &svm->vmcb->save;
+ struct sev_es_save_area *save = svm->sev_es.vmsa;
/* Check some debug related fields before encrypting the VMSA */
- if (svm->vcpu.guest_debug || (save->dr7 & ~DR7_FIXED_1))
+ if (svm->vcpu.guest_debug || (svm->vmcb->save.dr7 & ~DR7_FIXED_1))
return -EINVAL;
+ /*
+ * SEV-ES will use a VMSA that is pointed to by the VMCB, not
+ * the traditional VMSA that is part of the VMCB. Copy the
+ * traditional VMSA as it has been built so far (in prep
+ * for LAUNCH_UPDATE_VMSA) to be the initial SEV-ES state.
+ */
+ memcpy(save, &svm->vmcb->save, sizeof(svm->vmcb->save));
+
/* Sync registgers */
save->rax = svm->vcpu.arch.regs[VCPU_REGS_RAX];
save->rbx = svm->vcpu.arch.regs[VCPU_REGS_RBX];
@@ -595,14 +603,6 @@ static int sev_es_sync_vmsa(struct vcpu_svm *svm)
save->xss = svm->vcpu.arch.ia32_xss;
save->dr6 = svm->vcpu.arch.dr6;
- /*
- * SEV-ES will use a VMSA that is pointed to by the VMCB, not
- * the traditional VMSA that is part of the VMCB. Copy the
- * traditional VMSA as it has been built so far (in prep
- * for LAUNCH_UPDATE_VMSA) to be the initial SEV-ES state.
- */
- memcpy(svm->sev_es.vmsa, save, sizeof(*save));
-
return 0;
}
@@ -2966,7 +2966,7 @@ void sev_es_vcpu_reset(struct vcpu_svm *svm)
sev_enc_bit));
}
-void sev_es_prepare_switch_to_guest(struct vmcb_save_area *hostsa)
+void sev_es_prepare_switch_to_guest(struct sev_es_save_area *hostsa)
{
/*
* As an SEV-ES guest, hardware will restore the host state on VMEXIT,
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index 7e45d03cd018..17d334ef5430 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -1270,8 +1270,8 @@ static void svm_prepare_switch_to_guest(struct kvm_vcpu *vcpu)
*/
vmsave(__sme_page_pa(sd->save_area));
if (sev_es_guest(vcpu->kvm)) {
- struct vmcb_save_area *hostsa;
- hostsa = (struct vmcb_save_area *)(page_address(sd->save_area) + 0x400);
+ struct sev_es_save_area *hostsa;
+ hostsa = (struct sev_es_save_area *)(page_address(sd->save_area) + 0x400);
sev_es_prepare_switch_to_guest(hostsa);
}
@@ -3117,8 +3117,8 @@ static void dump_vmcb(struct kvm_vcpu *vcpu)
"tr:",
save01->tr.selector, save01->tr.attrib,
save01->tr.limit, save01->tr.base);
- pr_err("cpl: %d efer: %016llx\n",
- save->cpl, save->efer);
+ pr_err("vmpl: %d cpl: %d efer: %016llx\n",
+ save->vmpl, save->cpl, save->efer);
pr_err("%-15s %016llx %-13s %016llx\n",
"cr0:", save->cr0, "cr2:", save->cr2);
pr_err("%-15s %016llx %-13s %016llx\n",
diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h
index f76deff71002..2d83845b9032 100644
--- a/arch/x86/kvm/svm/svm.h
+++ b/arch/x86/kvm/svm/svm.h
@@ -181,7 +181,7 @@ struct svm_nested_state {
struct vcpu_sev_es_state {
/* SEV-ES support */
- struct vmcb_save_area *vmsa;
+ struct sev_es_save_area *vmsa;
struct ghcb *ghcb;
struct kvm_host_map ghcb_map;
bool received_first_sipi;
@@ -622,7 +622,7 @@ int sev_es_string_io(struct vcpu_svm *svm, int size, unsigned int port, int in);
void sev_es_init_vmcb(struct vcpu_svm *svm);
void sev_es_vcpu_reset(struct vcpu_svm *svm);
void sev_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, u8 vector);
-void sev_es_prepare_switch_to_guest(struct vmcb_save_area *hostsa);
+void sev_es_prepare_switch_to_guest(struct sev_es_save_area *hostsa);
void sev_es_unmap_ghcb(struct vcpu_svm *svm);
/* vmenter.S */
diff --git a/arch/x86/mm/mem_encrypt.c b/arch/x86/mm/mem_encrypt.c
index 50d209939c66..f85868c031c6 100644
--- a/arch/x86/mm/mem_encrypt.c
+++ b/arch/x86/mm/mem_encrypt.c
@@ -62,6 +62,10 @@ static void print_mem_encrypt_feature_info(void)
if (cc_platform_has(CC_ATTR_GUEST_STATE_ENCRYPT))
pr_cont(" SEV-ES");
+ /* Secure Nested Paging */
+ if (cc_platform_has(CC_ATTR_GUEST_SEV_SNP))
+ pr_cont(" SEV-SNP");
+
pr_cont("\n");
}
diff --git a/arch/x86/mm/mem_encrypt_amd.c b/arch/x86/mm/mem_encrypt_amd.c
index 6169053c2854..d3c88d9ef8d6 100644
--- a/arch/x86/mm/mem_encrypt_amd.c
+++ b/arch/x86/mm/mem_encrypt_amd.c
@@ -31,6 +31,7 @@
#include <asm/processor-flags.h>
#include <asm/msr.h>
#include <asm/cmdline.h>
+#include <asm/sev.h>
#include "mm_internal.h"
@@ -48,6 +49,36 @@ EXPORT_SYMBOL(sme_me_mask);
static char sme_early_buffer[PAGE_SIZE] __initdata __aligned(PAGE_SIZE);
/*
+ * SNP-specific routine which needs to additionally change the page state from
+ * private to shared before copying the data from the source to destination and
+ * restore after the copy.
+ */
+static inline void __init snp_memcpy(void *dst, void *src, size_t sz,
+ unsigned long paddr, bool decrypt)
+{
+ unsigned long npages = PAGE_ALIGN(sz) >> PAGE_SHIFT;
+
+ if (decrypt) {
+ /*
+ * @paddr needs to be accessed decrypted, mark the page shared in
+ * the RMP table before copying it.
+ */
+ early_snp_set_memory_shared((unsigned long)__va(paddr), paddr, npages);
+
+ memcpy(dst, src, sz);
+
+ /* Restore the page state after the memcpy. */
+ early_snp_set_memory_private((unsigned long)__va(paddr), paddr, npages);
+ } else {
+ /*
+ * @paddr need to be accessed encrypted, no need for the page state
+ * change.
+ */
+ memcpy(dst, src, sz);
+ }
+}
+
+/*
* This routine does not change the underlying encryption setting of the
* page(s) that map this memory. It assumes that eventually the memory is
* meant to be accessed as either encrypted or decrypted but the contents
@@ -95,8 +126,13 @@ static void __init __sme_early_enc_dec(resource_size_t paddr,
* Use a temporary buffer, of cache-line multiple size, to
* avoid data corruption as documented in the APM.
*/
- memcpy(sme_early_buffer, src, len);
- memcpy(dst, sme_early_buffer, len);
+ if (cc_platform_has(CC_ATTR_GUEST_SEV_SNP)) {
+ snp_memcpy(sme_early_buffer, src, len, paddr, enc);
+ snp_memcpy(dst, sme_early_buffer, len, paddr, !enc);
+ } else {
+ memcpy(sme_early_buffer, src, len);
+ memcpy(dst, sme_early_buffer, len);
+ }
early_memunmap(dst, len);
early_memunmap(src, len);
@@ -280,11 +316,24 @@ static void enc_dec_hypercall(unsigned long vaddr, int npages, bool enc)
static void amd_enc_status_change_prepare(unsigned long vaddr, int npages, bool enc)
{
+ /*
+ * To maintain the security guarantees of SEV-SNP guests, make sure
+ * to invalidate the memory before encryption attribute is cleared.
+ */
+ if (cc_platform_has(CC_ATTR_GUEST_SEV_SNP) && !enc)
+ snp_set_memory_shared(vaddr, npages);
}
/* Return true unconditionally: return value doesn't matter for the SEV side */
static bool amd_enc_status_change_finish(unsigned long vaddr, int npages, bool enc)
{
+ /*
+ * After memory is mapped encrypted in the page table, validate it
+ * so that it is consistent with the page table updates.
+ */
+ if (cc_platform_has(CC_ATTR_GUEST_SEV_SNP) && enc)
+ snp_set_memory_private(vaddr, npages);
+
if (!cc_platform_has(CC_ATTR_HOST_MEM_ENCRYPT))
enc_dec_hypercall(vaddr, npages, enc);
@@ -322,14 +371,28 @@ static void __init __set_clr_pte_enc(pte_t *kpte, int level, bool enc)
clflush_cache_range(__va(pa), size);
/* Encrypt/decrypt the contents in-place */
- if (enc)
+ if (enc) {
sme_early_encrypt(pa, size);
- else
+ } else {
sme_early_decrypt(pa, size);
+ /*
+ * ON SNP, the page state in the RMP table must happen
+ * before the page table updates.
+ */
+ early_snp_set_memory_shared((unsigned long)__va(pa), pa, 1);
+ }
+
/* Change the page encryption mask. */
new_pte = pfn_pte(pfn, new_prot);
set_pte_atomic(kpte, new_pte);
+
+ /*
+ * If page is set encrypted in the page table, then update the RMP table to
+ * add this page as private.
+ */
+ if (enc)
+ early_snp_set_memory_private((unsigned long)__va(pa), pa, 1);
}
static int __init early_set_memory_enc_dec(unsigned long vaddr,
diff --git a/arch/x86/mm/mem_encrypt_identity.c b/arch/x86/mm/mem_encrypt_identity.c
index b43bc24d2bb6..f415498d3175 100644
--- a/arch/x86/mm/mem_encrypt_identity.c
+++ b/arch/x86/mm/mem_encrypt_identity.c
@@ -45,6 +45,7 @@
#include <asm/sections.h>
#include <asm/cmdline.h>
#include <asm/coco.h>
+#include <asm/sev.h>
#include "mm_internal.h"
@@ -509,8 +510,11 @@ void __init sme_enable(struct boot_params *bp)
bool active_by_default;
unsigned long me_mask;
char buffer[16];
+ bool snp;
u64 msr;
+ snp = snp_init(bp);
+
/* Check for the SME/SEV support leaf */
eax = 0x80000000;
ecx = 0;
@@ -542,6 +546,10 @@ void __init sme_enable(struct boot_params *bp)
sev_status = __rdmsr(MSR_AMD64_SEV);
feature_mask = (sev_status & MSR_AMD64_SEV_ENABLED) ? AMD_SEV_BIT : AMD_SME_BIT;
+ /* The SEV-SNP CC blob should never be present unless SEV-SNP is enabled. */
+ if (snp && !(sev_status & MSR_AMD64_SEV_SNP_ENABLED))
+ snp_abort();
+
/* Check if memory encryption is enabled */
if (feature_mask == AMD_SME_BIT) {
/*
diff --git a/arch/x86/realmode/init.c b/arch/x86/realmode/init.c
index c5e29db02a46..41d7669a97ad 100644
--- a/arch/x86/realmode/init.c
+++ b/arch/x86/realmode/init.c
@@ -67,7 +67,7 @@ void __init reserve_real_mode(void)
memblock_reserve(0, SZ_1M);
}
-static void sme_sev_setup_real_mode(struct trampoline_header *th)
+static void __init sme_sev_setup_real_mode(struct trampoline_header *th)
{
#ifdef CONFIG_AMD_MEM_ENCRYPT
if (cc_platform_has(CC_ATTR_HOST_MEM_ENCRYPT))
diff --git a/drivers/virt/Kconfig b/drivers/virt/Kconfig
index c877da072d4d..87ef258cec64 100644
--- a/drivers/virt/Kconfig
+++ b/drivers/virt/Kconfig
@@ -50,4 +50,6 @@ source "drivers/virt/acrn/Kconfig"
source "drivers/virt/coco/efi_secret/Kconfig"
+source "drivers/virt/coco/sev-guest/Kconfig"
+
endif
diff --git a/drivers/virt/Makefile b/drivers/virt/Makefile
index 067b5427f40f..093674e05c40 100644
--- a/drivers/virt/Makefile
+++ b/drivers/virt/Makefile
@@ -10,3 +10,4 @@ obj-y += vboxguest/
obj-$(CONFIG_NITRO_ENCLAVES) += nitro_enclaves/
obj-$(CONFIG_ACRN_HSM) += acrn/
obj-$(CONFIG_EFI_SECRET) += coco/efi_secret/
+obj-$(CONFIG_SEV_GUEST) += coco/sev-guest/
diff --git a/drivers/virt/coco/sev-guest/Kconfig b/drivers/virt/coco/sev-guest/Kconfig
new file mode 100644
index 000000000000..f9db0799ae67
--- /dev/null
+++ b/drivers/virt/coco/sev-guest/Kconfig
@@ -0,0 +1,14 @@
+config SEV_GUEST
+ tristate "AMD SEV Guest driver"
+ default m
+ depends on AMD_MEM_ENCRYPT
+ select CRYPTO_AEAD2
+ select CRYPTO_GCM
+ help
+ SEV-SNP firmware provides the guest a mechanism to communicate with
+ the PSP without risk from a malicious hypervisor who wishes to read,
+ alter, drop or replay the messages sent. The driver provides
+ userspace interface to communicate with the PSP to request the
+ attestation report and more.
+
+ If you choose 'M' here, this module will be called sev-guest.
diff --git a/drivers/virt/coco/sev-guest/Makefile b/drivers/virt/coco/sev-guest/Makefile
new file mode 100644
index 000000000000..63d67c27723a
--- /dev/null
+++ b/drivers/virt/coco/sev-guest/Makefile
@@ -0,0 +1,2 @@
+# SPDX-License-Identifier: GPL-2.0-only
+obj-$(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 000000000000..90ce16b6e05f
--- /dev/null
+++ b/drivers/virt/coco/sev-guest/sev-guest.c
@@ -0,0 +1,743 @@
+// 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;
+}
+
+static void snp_disable_vmpck(struct snp_guest_dev *snp_dev)
+{
+ 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_auth;
+
+ return crypto;
+
+e_free_auth:
+ kfree(crypto->authtag);
+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 */
+ rc = snp_issue_guest_request(exit_code, &snp_dev->input, &err);
+ if (fw_err)
+ *fw_err = err;
+
+ if (rc)
+ return rc;
+
+ /*
+ * The verify_and_dec_payload() will fail only if the hypervisor is
+ * actively modifying the message header or corrupting the encrypted payload.
+ * This hints that hypervisor is acting in a bad faith. Disable the VMPCK so that
+ * the key cannot be used for any communication. The key is disabled to ensure
+ * that AES-GCM does not use the same IV while encrypting the request payload.
+ */
+ rc = verify_and_dec_payload(snp_dev, resp_buf, resp_sz);
+ if (rc) {
+ dev_alert(snp_dev->dev,
+ "Detected unexpected decode failure, disabling the vmpck_id %d\n",
+ vmpck_id);
+ snp_disable_vmpck(snp_dev);
+ return rc;
+ }
+
+ /* Increment to new message sequence after payload decryption was successful. */
+ snp_inc_msg_seqno(snp_dev);
+
+ return 0;
+}
+
+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;
+ int ret;
+
+ if (!dev->platform_data)
+ return -ENODEV;
+
+ data = (struct sev_guest_platform_data *)dev->platform_data;
+ layout = (__force void *)ioremap_encrypted(data->secrets_gpa, PAGE_SIZE);
+ if (!layout)
+ return -ENODEV;
+
+ 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(layout);
+ 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");
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 000000000000..21bda26fdb95
--- /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/include/linux/cc_platform.h b/include/linux/cc_platform.h
index efd8205282da..d08dd65b5c43 100644
--- a/include/linux/cc_platform.h
+++ b/include/linux/cc_platform.h
@@ -72,6 +72,14 @@ enum cc_attr {
* Examples include TDX guest & SEV.
*/
CC_ATTR_GUEST_UNROLL_STRING_IO,
+
+ /**
+ * @CC_ATTR_SEV_SNP: Guest SNP is active.
+ *
+ * The platform/OS is running as a guest/virtual machine and actively
+ * using AMD SEV-SNP features.
+ */
+ CC_ATTR_GUEST_SEV_SNP,
};
#ifdef CONFIG_ARCH_HAS_CC_PLATFORM
diff --git a/include/linux/efi.h b/include/linux/efi.h
index 0412304ce34e..db424f3dc3f2 100644
--- a/include/linux/efi.h
+++ b/include/linux/efi.h
@@ -393,6 +393,7 @@ void efi_native_runtime_setup(void);
#define EFI_CERT_SHA256_GUID EFI_GUID(0xc1c41626, 0x504c, 0x4092, 0xac, 0xa9, 0x41, 0xf9, 0x36, 0x93, 0x43, 0x28)
#define EFI_CERT_X509_GUID EFI_GUID(0xa5c059a1, 0x94e4, 0x4aa7, 0x87, 0xb5, 0xab, 0x15, 0x5c, 0x2b, 0xf0, 0x72)
#define EFI_CERT_X509_SHA256_GUID EFI_GUID(0x3bd2a492, 0x96c0, 0x4079, 0xb4, 0x20, 0xfc, 0xf9, 0x8e, 0xf1, 0x03, 0xed)
+#define EFI_CC_BLOB_GUID EFI_GUID(0x067b1f5f, 0xcf26, 0x44c5, 0x85, 0x54, 0x93, 0xd7, 0x77, 0x91, 0x2d, 0x42)
/*
* This GUID is used to pass to the kernel proper the struct screen_info
diff --git a/include/uapi/linux/sev-guest.h b/include/uapi/linux/sev-guest.h
new file mode 100644
index 000000000000..256aaeff7e65
--- /dev/null
+++ b/include/uapi/linux/sev-guest.h
@@ -0,0 +1,80 @@
+/* SPDX-License-Identifier: GPL-2.0-only WITH Linux-syscall-note */
+/*
+ * Userspace interface for AMD SEV and SNP guest driver.
+ *
+ * Copyright (C) 2021 Advanced Micro Devices, Inc.
+ *
+ * Author: Brijesh Singh <brijesh.singh@amd.com>
+ *
+ * SEV API specification is available at: https://developer.amd.com/sev/
+ */
+
+#ifndef __UAPI_LINUX_SEV_GUEST_H_
+#define __UAPI_LINUX_SEV_GUEST_H_
+
+#include <linux/types.h>
+
+struct snp_report_req {
+ /* user data that should be included in the report */
+ __u8 user_data[64];
+
+ /* The vmpl level to be included in the report */
+ __u32 vmpl;
+
+ /* Must be zero filled */
+ __u8 rsvd[28];
+};
+
+struct snp_report_resp {
+ /* response data, see SEV-SNP spec for the format */
+ __u8 data[4000];
+};
+
+struct snp_derived_key_req {
+ __u32 root_key_select;
+ __u32 rsvd;
+ __u64 guest_field_select;
+ __u32 vmpl;
+ __u32 guest_svn;
+ __u64 tcb_version;
+};
+
+struct snp_derived_key_resp {
+ /* response data, see SEV-SNP spec for the format */
+ __u8 data[64];
+};
+
+struct snp_guest_request_ioctl {
+ /* message version number (must be non-zero) */
+ __u8 msg_version;
+
+ /* Request and response structure address */
+ __u64 req_data;
+ __u64 resp_data;
+
+ /* firmware error code on failure (see psp-sev.h) */
+ __u64 fw_err;
+};
+
+struct snp_ext_report_req {
+ struct snp_report_req data;
+
+ /* where to copy the certificate blob */
+ __u64 certs_address;
+
+ /* length of the certificate blob */
+ __u32 certs_len;
+};
+
+#define SNP_GUEST_REQ_IOC_TYPE 'S'
+
+/* Get SNP attestation report */
+#define SNP_GET_REPORT _IOWR(SNP_GUEST_REQ_IOC_TYPE, 0x0, struct snp_guest_request_ioctl)
+
+/* Get a derived key from the root */
+#define SNP_GET_DERIVED_KEY _IOWR(SNP_GUEST_REQ_IOC_TYPE, 0x1, struct snp_guest_request_ioctl)
+
+/* Get SNP extended report as defined in the GHCB specification version 2. */
+#define SNP_GET_EXT_REPORT _IOWR(SNP_GUEST_REQ_IOC_TYPE, 0x2, struct snp_guest_request_ioctl)
+
+#endif /* __UAPI_LINUX_SEV_GUEST_H_ */