Merge tag 'x86_sgx_for_v5.13' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 SGX updates from Borislav Petkov:
 "Add the guest side of SGX support in KVM guests. Work by Sean
  Christopherson, Kai Huang and Jarkko Sakkinen.

  Along with the usual fixes, cleanups and improvements"

* tag 'x86_sgx_for_v5.13' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (21 commits)
  x86/sgx: Mark sgx_vepc_vm_ops static
  x86/sgx: Do not update sgx_nr_free_pages in sgx_setup_epc_section()
  x86/sgx: Move provisioning device creation out of SGX driver
  x86/sgx: Add helpers to expose ECREATE and EINIT to KVM
  x86/sgx: Add helper to update SGX_LEPUBKEYHASHn MSRs
  x86/sgx: Add encls_faulted() helper
  x86/sgx: Add SGX2 ENCLS leaf definitions (EAUG, EMODPR and EMODT)
  x86/sgx: Move ENCLS leaf definitions to sgx.h
  x86/sgx: Expose SGX architectural definitions to the kernel
  x86/sgx: Initialize virtual EPC driver even when SGX driver is disabled
  x86/cpu/intel: Allow SGX virtualization without Launch Control support
  x86/sgx: Introduce virtual EPC for use by KVM guests
  x86/sgx: Add SGX_CHILD_PRESENT hardware error code
  x86/sgx: Wipe out EREMOVE from sgx_free_epc_page()
  x86/cpufeatures: Add SGX1 and SGX2 sub-features
  x86/cpufeatures: Make SGX_LC feature bit depend on SGX bit
  x86/sgx: Remove unnecessary kmap() from sgx_ioc_enclave_init()
  selftests/sgx: Use getauxval() to simplify test code
  selftests/sgx: Improve error detection and messages
  x86/sgx: Add a basic NUMA allocation scheme to sgx_alloc_epc_page()
  ...

13 files changed, 698 insertions, 521 deletions

diff --git a/arch/x86/kernel/cpu/cpuid-deps.c b/arch/x86/kernel/cpu/cpuid-deps.c
index 42af31b64c2c..defda61f372d 100644
--- a/arch/x86/kernel/cpu/cpuid-deps.c
+++ b/arch/x86/kernel/cpu/cpuid-deps.c
@@ -72,6 +72,9 @@ static const struct cpuid_dep cpuid_deps[] = {
 	{ X86_FEATURE_AVX512_FP16,		X86_FEATURE_AVX512BW  },
 	{ X86_FEATURE_ENQCMD,			X86_FEATURE_XSAVES    },
 	{ X86_FEATURE_PER_THREAD_MBA,		X86_FEATURE_MBA       },
+	{ X86_FEATURE_SGX_LC,			X86_FEATURE_SGX	      },
+	{ X86_FEATURE_SGX1,			X86_FEATURE_SGX       },
+	{ X86_FEATURE_SGX2,			X86_FEATURE_SGX1      },
 	{}
 };
 
diff --git a/arch/x86/kernel/cpu/feat_ctl.c b/arch/x86/kernel/cpu/feat_ctl.c
index 3b1b01f2b248..da696eb4821a 100644
--- a/arch/x86/kernel/cpu/feat_ctl.c
+++ b/arch/x86/kernel/cpu/feat_ctl.c
@@ -93,15 +93,9 @@ static void init_vmx_capabilities(struct cpuinfo_x86 *c)
 }
 #endif /* CONFIG_X86_VMX_FEATURE_NAMES */
 
-static void clear_sgx_caps(void)
-{
-	setup_clear_cpu_cap(X86_FEATURE_SGX);
-	setup_clear_cpu_cap(X86_FEATURE_SGX_LC);
-}
-
 static int __init nosgx(char *str)
 {
-	clear_sgx_caps();
+	setup_clear_cpu_cap(X86_FEATURE_SGX);
 
 	return 0;
 }
@@ -110,23 +104,30 @@ early_param("nosgx", nosgx);
 
 void init_ia32_feat_ctl(struct cpuinfo_x86 *c)
 {
+	bool enable_sgx_kvm = false, enable_sgx_driver = false;
 	bool tboot = tboot_enabled();
-	bool enable_sgx;
+	bool enable_vmx;
 	u64 msr;
 
 	if (rdmsrl_safe(MSR_IA32_FEAT_CTL, &msr)) {
 		clear_cpu_cap(c, X86_FEATURE_VMX);
-		clear_sgx_caps();
+		clear_cpu_cap(c, X86_FEATURE_SGX);
 		return;
 	}
 
-	/*
-	 * Enable SGX if and only if the kernel supports SGX and Launch Control
-	 * is supported, i.e. disable SGX if the LE hash MSRs can't be written.
-	 */
-	enable_sgx = cpu_has(c, X86_FEATURE_SGX) &&
-		     cpu_has(c, X86_FEATURE_SGX_LC) &&
-		     IS_ENABLED(CONFIG_X86_SGX);
+	enable_vmx = cpu_has(c, X86_FEATURE_VMX) &&
+		     IS_ENABLED(CONFIG_KVM_INTEL);
+
+	if (cpu_has(c, X86_FEATURE_SGX) && IS_ENABLED(CONFIG_X86_SGX)) {
+		/*
+		 * Separate out SGX driver enabling from KVM.  This allows KVM
+		 * guests to use SGX even if the kernel SGX driver refuses to
+		 * use it.  This happens if flexible Launch Control is not
+		 * available.
+		 */
+		enable_sgx_driver = cpu_has(c, X86_FEATURE_SGX_LC);
+		enable_sgx_kvm = enable_vmx && IS_ENABLED(CONFIG_X86_SGX_KVM);
+	}
 
 	if (msr & FEAT_CTL_LOCKED)
 		goto update_caps;
@@ -142,15 +143,18 @@ void init_ia32_feat_ctl(struct cpuinfo_x86 *c)
 	 * i.e. KVM is enabled, to avoid unnecessarily adding an attack vector
 	 * for the kernel, e.g. using VMX to hide malicious code.
 	 */
-	if (cpu_has(c, X86_FEATURE_VMX) && IS_ENABLED(CONFIG_KVM_INTEL)) {
+	if (enable_vmx) {
 		msr |= FEAT_CTL_VMX_ENABLED_OUTSIDE_SMX;
 
 		if (tboot)
 			msr |= FEAT_CTL_VMX_ENABLED_INSIDE_SMX;
 	}
 
-	if (enable_sgx)
-		msr |= FEAT_CTL_SGX_ENABLED | FEAT_CTL_SGX_LC_ENABLED;
+	if (enable_sgx_kvm || enable_sgx_driver) {
+		msr |= FEAT_CTL_SGX_ENABLED;
+		if (enable_sgx_driver)
+			msr |= FEAT_CTL_SGX_LC_ENABLED;
+	}
 
 	wrmsrl(MSR_IA32_FEAT_CTL, msr);
 
@@ -173,10 +177,29 @@ update_caps:
 	}
 
 update_sgx:
-	if (!(msr & FEAT_CTL_SGX_ENABLED) ||
-	    !(msr & FEAT_CTL_SGX_LC_ENABLED) || !enable_sgx) {
-		if (enable_sgx)
-			pr_err_once("SGX disabled by BIOS\n");
-		clear_sgx_caps();
+	if (!(msr & FEAT_CTL_SGX_ENABLED)) {
+		if (enable_sgx_kvm || enable_sgx_driver)
+			pr_err_once("SGX disabled by BIOS.\n");
+		clear_cpu_cap(c, X86_FEATURE_SGX);
+		return;
+	}
+
+	/*
+	 * VMX feature bit may be cleared due to being disabled in BIOS,
+	 * in which case SGX virtualization cannot be supported either.
+	 */
+	if (!cpu_has(c, X86_FEATURE_VMX) && enable_sgx_kvm) {
+		pr_err_once("SGX virtualization disabled due to lack of VMX.\n");
+		enable_sgx_kvm = 0;
+	}
+
+	if (!(msr & FEAT_CTL_SGX_LC_ENABLED) && enable_sgx_driver) {
+		if (!enable_sgx_kvm) {
+			pr_err_once("SGX Launch Control is locked. Disable SGX.\n");
+			clear_cpu_cap(c, X86_FEATURE_SGX);
+		} else {
+			pr_err_once("SGX Launch Control is locked. Support SGX virtualization only.\n");
+			clear_cpu_cap(c, X86_FEATURE_SGX_LC);
+		}
 	}
 }
diff --git a/arch/x86/kernel/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c
index 972ec3bfa9c0..21d1f062895a 100644
--- a/arch/x86/kernel/cpu/scattered.c
+++ b/arch/x86/kernel/cpu/scattered.c
@@ -36,6 +36,8 @@ static const struct cpuid_bit cpuid_bits[] = {
 	{ X86_FEATURE_CDP_L2,		CPUID_ECX,  2, 0x00000010, 2 },
 	{ X86_FEATURE_MBA,		CPUID_EBX,  3, 0x00000010, 0 },
 	{ X86_FEATURE_PER_THREAD_MBA,	CPUID_ECX,  0, 0x00000010, 3 },
+	{ X86_FEATURE_SGX1,		CPUID_EAX,  0, 0x00000012, 0 },
+	{ X86_FEATURE_SGX2,		CPUID_EAX,  1, 0x00000012, 0 },
 	{ X86_FEATURE_HW_PSTATE,	CPUID_EDX,  7, 0x80000007, 0 },
 	{ X86_FEATURE_CPB,		CPUID_EDX,  9, 0x80000007, 0 },
 	{ X86_FEATURE_PROC_FEEDBACK,    CPUID_EDX, 11, 0x80000007, 0 },
diff --git a/arch/x86/kernel/cpu/sgx/Makefile b/arch/x86/kernel/cpu/sgx/Makefile
index 91d3dc784a29..9c1656779b2a 100644
--- a/arch/x86/kernel/cpu/sgx/Makefile
+++ b/arch/x86/kernel/cpu/sgx/Makefile
@@ -3,3 +3,4 @@ obj-y += \
 	encl.o \
 	ioctl.o \
 	main.o
+obj-$(CONFIG_X86_SGX_KVM)	+= virt.o
diff --git a/arch/x86/kernel/cpu/sgx/arch.h b/arch/x86/kernel/cpu/sgx/arch.h
deleted file mode 100644
index dd7602c44c72..000000000000
--- a/arch/x86/kernel/cpu/sgx/arch.h
+++ /dev/null
@@ -1,338 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/**
- * Copyright(c) 2016-20 Intel Corporation.
- *
- * Contains data structures defined by the SGX architecture.  Data structures
- * defined by the Linux software stack should not be placed here.
- */
-#ifndef _ASM_X86_SGX_ARCH_H
-#define _ASM_X86_SGX_ARCH_H
-
-#include <linux/bits.h>
-#include <linux/types.h>
-
-/* The SGX specific CPUID function. */
-#define SGX_CPUID		0x12
-/* EPC enumeration. */
-#define SGX_CPUID_EPC		2
-/* An invalid EPC section, i.e. the end marker. */
-#define SGX_CPUID_EPC_INVALID	0x0
-/* A valid EPC section. */
-#define SGX_CPUID_EPC_SECTION	0x1
-/* The bitmask for the EPC section type. */
-#define SGX_CPUID_EPC_MASK	GENMASK(3, 0)
-
-/**
- * enum sgx_return_code - The return code type for ENCLS, ENCLU and ENCLV
- * %SGX_NOT_TRACKED:		Previous ETRACK's shootdown sequence has not
- *				been completed yet.
- * %SGX_INVALID_EINITTOKEN:	EINITTOKEN is invalid and enclave signer's
- *				public key does not match IA32_SGXLEPUBKEYHASH.
- * %SGX_UNMASKED_EVENT:		An unmasked event, e.g. INTR, was received
- */
-enum sgx_return_code {
-	SGX_NOT_TRACKED			= 11,
-	SGX_INVALID_EINITTOKEN		= 16,
-	SGX_UNMASKED_EVENT		= 128,
-};
-
-/* The modulus size for 3072-bit RSA keys. */
-#define SGX_MODULUS_SIZE 384
-
-/**
- * enum sgx_miscselect - additional information to an SSA frame
- * %SGX_MISC_EXINFO:	Report #PF or #GP to the SSA frame.
- *
- * Save State Area (SSA) is a stack inside the enclave used to store processor
- * state when an exception or interrupt occurs. This enum defines additional
- * information stored to an SSA frame.
- */
-enum sgx_miscselect {
-	SGX_MISC_EXINFO		= BIT(0),
-};
-
-#define SGX_MISC_RESERVED_MASK	GENMASK_ULL(63, 1)
-
-#define SGX_SSA_GPRS_SIZE		184
-#define SGX_SSA_MISC_EXINFO_SIZE	16
-
-/**
- * enum sgx_attributes - the attributes field in &struct sgx_secs
- * %SGX_ATTR_INIT:		Enclave can be entered (is initialized).
- * %SGX_ATTR_DEBUG:		Allow ENCLS(EDBGRD) and ENCLS(EDBGWR).
- * %SGX_ATTR_MODE64BIT:		Tell that this a 64-bit enclave.
- * %SGX_ATTR_PROVISIONKEY:      Allow to use provisioning keys for remote
- *				attestation.
- * %SGX_ATTR_KSS:		Allow to use key separation and sharing (KSS).
- * %SGX_ATTR_EINITTOKENKEY:	Allow to use token signing key that is used to
- *				sign cryptographic tokens that can be passed to
- *				EINIT as an authorization to run an enclave.
- */
-enum sgx_attribute {
-	SGX_ATTR_INIT		= BIT(0),
-	SGX_ATTR_DEBUG		= BIT(1),
-	SGX_ATTR_MODE64BIT	= BIT(2),
-	SGX_ATTR_PROVISIONKEY	= BIT(4),
-	SGX_ATTR_EINITTOKENKEY	= BIT(5),
-	SGX_ATTR_KSS		= BIT(7),
-};
-
-#define SGX_ATTR_RESERVED_MASK	(BIT_ULL(3) | BIT_ULL(6) | GENMASK_ULL(63, 8))
-
-/**
- * struct sgx_secs - SGX Enclave Control Structure (SECS)
- * @size:		size of the address space
- * @base:		base address of the  address space
- * @ssa_frame_size:	size of an SSA frame
- * @miscselect:		additional information stored to an SSA frame
- * @attributes:		attributes for enclave
- * @xfrm:		XSave-Feature Request Mask (subset of XCR0)
- * @mrenclave:		SHA256-hash of the enclave contents
- * @mrsigner:		SHA256-hash of the public key used to sign the SIGSTRUCT
- * @config_id:		a user-defined value that is used in key derivation
- * @isv_prod_id:	a user-defined value that is used in key derivation
- * @isv_svn:		a user-defined value that is used in key derivation
- * @config_svn:		a user-defined value that is used in key derivation
- *
- * SGX Enclave Control Structure (SECS) is a special enclave page that is not
- * visible in the address space. In fact, this structure defines the address
- * range and other global attributes for the enclave and it is the first EPC
- * page created for any enclave. It is moved from a temporary buffer to an EPC
- * by the means of ENCLS[ECREATE] function.
- */
-struct sgx_secs {
-	u64 size;
-	u64 base;
-	u32 ssa_frame_size;
-	u32 miscselect;
-	u8  reserved1[24];
-	u64 attributes;
-	u64 xfrm;
-	u32 mrenclave[8];
-	u8  reserved2[32];
-	u32 mrsigner[8];
-	u8  reserved3[32];
-	u32 config_id[16];
-	u16 isv_prod_id;
-	u16 isv_svn;
-	u16 config_svn;
-	u8  reserved4[3834];
-} __packed;
-
-/**
- * enum sgx_tcs_flags - execution flags for TCS
- * %SGX_TCS_DBGOPTIN:	If enabled allows single-stepping and breakpoints
- *			inside an enclave. It is cleared by EADD but can
- *			be set later with EDBGWR.
- */
-enum sgx_tcs_flags {
-	SGX_TCS_DBGOPTIN	= 0x01,
-};
-
-#define SGX_TCS_RESERVED_MASK	GENMASK_ULL(63, 1)
-#define SGX_TCS_RESERVED_SIZE	4024
-
-/**
- * struct sgx_tcs - Thread Control Structure (TCS)
- * @state:		used to mark an entered TCS
- * @flags:		execution flags (cleared by EADD)
- * @ssa_offset:		SSA stack offset relative to the enclave base
- * @ssa_index:		the current SSA frame index (cleard by EADD)
- * @nr_ssa_frames:	the number of frame in the SSA stack
- * @entry_offset:	entry point offset relative to the enclave base
- * @exit_addr:		address outside the enclave to exit on an exception or
- *			interrupt
- * @fs_offset:		offset relative to the enclave base to become FS
- *			segment inside the enclave
- * @gs_offset:		offset relative to the enclave base to become GS
- *			segment inside the enclave
- * @fs_limit:		size to become a new FS-limit (only 32-bit enclaves)
- * @gs_limit:		size to become a new GS-limit (only 32-bit enclaves)
- *
- * Thread Control Structure (TCS) is an enclave page visible in its address
- * space that defines an entry point inside the enclave. A thread enters inside
- * an enclave by supplying address of TCS to ENCLU(EENTER). A TCS can be entered
- * by only one thread at a time.
- */
-struct sgx_tcs {
-	u64 state;
-	u64 flags;
-	u64 ssa_offset;
-	u32 ssa_index;
-	u32 nr_ssa_frames;
-	u64 entry_offset;
-	u64 exit_addr;
-	u64 fs_offset;
-	u64 gs_offset;
-	u32 fs_limit;
-	u32 gs_limit;
-	u8  reserved[SGX_TCS_RESERVED_SIZE];
-} __packed;
-
-/**
- * struct sgx_pageinfo - an enclave page descriptor
- * @addr:	address of the enclave page
- * @contents:	pointer to the page contents
- * @metadata:	pointer either to a SECINFO or PCMD instance
- * @secs:	address of the SECS page
- */
-struct sgx_pageinfo {
-	u64 addr;
-	u64 contents;
-	u64 metadata;
-	u64 secs;
-} __packed __aligned(32);
-
-
-/**
- * enum sgx_page_type - bits in the SECINFO flags defining the page type
- * %SGX_PAGE_TYPE_SECS:	a SECS page
- * %SGX_PAGE_TYPE_TCS:	a TCS page
- * %SGX_PAGE_TYPE_REG:	a regular page
- * %SGX_PAGE_TYPE_VA:	a VA page
- * %SGX_PAGE_TYPE_TRIM:	a page in trimmed state
- */
-enum sgx_page_type {
-	SGX_PAGE_TYPE_SECS,
-	SGX_PAGE_TYPE_TCS,
-	SGX_PAGE_TYPE_REG,
-	SGX_PAGE_TYPE_VA,
-	SGX_PAGE_TYPE_TRIM,
-};
-
-#define SGX_NR_PAGE_TYPES	5
-#define SGX_PAGE_TYPE_MASK	GENMASK(7, 0)
-
-/**
- * enum sgx_secinfo_flags - the flags field in &struct sgx_secinfo
- * %SGX_SECINFO_R:	allow read
- * %SGX_SECINFO_W:	allow write
- * %SGX_SECINFO_X:	allow execution
- * %SGX_SECINFO_SECS:	a SECS page
- * %SGX_SECINFO_TCS:	a TCS page
- * %SGX_SECINFO_REG:	a regular page
- * %SGX_SECINFO_VA:	a VA page
- * %SGX_SECINFO_TRIM:	a page in trimmed state
- */
-enum sgx_secinfo_flags {
-	SGX_SECINFO_R			= BIT(0),
-	SGX_SECINFO_W			= BIT(1),
-	SGX_SECINFO_X			= BIT(2),
-	SGX_SECINFO_SECS		= (SGX_PAGE_TYPE_SECS << 8),
-	SGX_SECINFO_TCS			= (SGX_PAGE_TYPE_TCS << 8),
-	SGX_SECINFO_REG			= (SGX_PAGE_TYPE_REG << 8),
-	SGX_SECINFO_VA			= (SGX_PAGE_TYPE_VA << 8),
-	SGX_SECINFO_TRIM		= (SGX_PAGE_TYPE_TRIM << 8),
-};
-
-#define SGX_SECINFO_PERMISSION_MASK	GENMASK_ULL(2, 0)
-#define SGX_SECINFO_PAGE_TYPE_MASK	(SGX_PAGE_TYPE_MASK << 8)
-#define SGX_SECINFO_RESERVED_MASK	~(SGX_SECINFO_PERMISSION_MASK | \
-					  SGX_SECINFO_PAGE_TYPE_MASK)
-
-/**
- * struct sgx_secinfo - describes attributes of an EPC page
- * @flags:	permissions and type
- *
- * Used together with ENCLS leaves that add or modify an EPC page to an
- * enclave to define page permissions and type.
- */
-struct sgx_secinfo {
-	u64 flags;
-	u8  reserved[56];
-} __packed __aligned(64);
-
-#define SGX_PCMD_RESERVED_SIZE 40
-
-/**
- * struct sgx_pcmd - Paging Crypto Metadata (PCMD)
- * @enclave_id:	enclave identifier
- * @mac:	MAC over PCMD, page contents and isvsvn
- *
- * PCMD is stored for every swapped page to the regular memory. When ELDU loads
- * the page back it recalculates the MAC by using a isvsvn number stored in a
- * VA page. Together these two structures bring integrity and rollback
- * protection.
- */
-struct sgx_pcmd {
-	struct sgx_secinfo secinfo;
-	u64 enclave_id;
-	u8  reserved[SGX_PCMD_RESERVED_SIZE];
-	u8  mac[16];
-} __packed __aligned(128);
-
-#define SGX_SIGSTRUCT_RESERVED1_SIZE 84
-#define SGX_SIGSTRUCT_RESERVED2_SIZE 20
-#define SGX_SIGSTRUCT_RESERVED3_SIZE 32
-#define SGX_SIGSTRUCT_RESERVED4_SIZE 12
-
-/**
- * struct sgx_sigstruct_header -  defines author of the enclave
- * @header1:		constant byte string
- * @vendor:		must be either 0x0000 or 0x8086
- * @date:		YYYYMMDD in BCD
- * @header2:		costant byte string
- * @swdefined:		software defined value
- */
-struct sgx_sigstruct_header {
-	u64 header1[2];
-	u32 vendor;
-	u32 date;
-	u64 header2[2];
-	u32 swdefined;
-	u8  reserved1[84];
-} __packed;
-
-/**
- * struct sgx_sigstruct_body - defines contents of the enclave
- * @miscselect:		additional information stored to an SSA frame
- * @misc_mask:		required miscselect in SECS
- * @attributes:		attributes for enclave
- * @xfrm:		XSave-Feature Request Mask (subset of XCR0)
- * @attributes_mask:	required attributes in SECS
- * @xfrm_mask:		required XFRM in SECS
- * @mrenclave:		SHA256-hash of the enclave contents
- * @isvprodid:		a user-defined value that is used in key derivation
- * @isvsvn:		a user-defined value that is used in key derivation
- */
-struct sgx_sigstruct_body {
-	u32 miscselect;
-	u32 misc_mask;
-	u8  reserved2[20];
-	u64 attributes;
-	u64 xfrm;
-	u64 attributes_mask;
-	u64 xfrm_mask;
-	u8  mrenclave[32];
-	u8  reserved3[32];
-	u16 isvprodid;
-	u16 isvsvn;
-} __packed;
-
-/**
- * struct sgx_sigstruct - an enclave signature
- * @header:		defines author of the enclave
- * @modulus:		the modulus of the public key
- * @exponent:		the exponent of the public key
- * @signature:		the signature calculated over the fields except modulus,
- * @body:		defines contents of the enclave
- * @q1:			a value used in RSA signature verification
- * @q2:			a value used in RSA signature verification
- *
- * Header and body are the parts that are actual signed. The remaining fields
- * define the signature of the enclave.
- */
-struct sgx_sigstruct {
-	struct sgx_sigstruct_header header;
-	u8  modulus[SGX_MODULUS_SIZE];
-	u32 exponent;
-	u8  signature[SGX_MODULUS_SIZE];
-	struct sgx_sigstruct_body body;
-	u8  reserved4[12];
-	u8  q1[SGX_MODULUS_SIZE];
-	u8  q2[SGX_MODULUS_SIZE];
-} __packed;
-
-#define SGX_LAUNCH_TOKEN_SIZE 304
-
-#endif /* _ASM_X86_SGX_ARCH_H */
diff --git a/arch/x86/kernel/cpu/sgx/driver.c b/arch/x86/kernel/cpu/sgx/driver.c
index 8ce6d8371cfb..aa9b8b868867 100644
--- a/arch/x86/kernel/cpu/sgx/driver.c
+++ b/arch/x86/kernel/cpu/sgx/driver.c
@@ -136,10 +136,6 @@ static const struct file_operations sgx_encl_fops = {
 	.get_unmapped_area	= sgx_get_unmapped_area,
 };
 
-const struct file_operations sgx_provision_fops = {
-	.owner			= THIS_MODULE,
-};
-
 static struct miscdevice sgx_dev_enclave = {
 	.minor = MISC_DYNAMIC_MINOR,
 	.name = "sgx_enclave",
@@ -147,13 +143,6 @@ static struct miscdevice sgx_dev_enclave = {
 	.fops = &sgx_encl_fops,
 };
 
-static struct miscdevice sgx_dev_provision = {
-	.minor = MISC_DYNAMIC_MINOR,
-	.name = "sgx_provision",
-	.nodename = "sgx_provision",
-	.fops = &sgx_provision_fops,
-};
-
 int __init sgx_drv_init(void)
 {
 	unsigned int eax, ebx, ecx, edx;
@@ -187,11 +176,5 @@ int __init sgx_drv_init(void)
 	if (ret)
 		return ret;
 
-	ret = misc_register(&sgx_dev_provision);
-	if (ret) {
-		misc_deregister(&sgx_dev_enclave);
-		return ret;
-	}
-
 	return 0;
 }
diff --git a/arch/x86/kernel/cpu/sgx/encl.c b/arch/x86/kernel/cpu/sgx/encl.c
index 7449ef33f081..3be203297988 100644
--- a/arch/x86/kernel/cpu/sgx/encl.c
+++ b/arch/x86/kernel/cpu/sgx/encl.c
@@ -7,7 +7,7 @@
 #include <linux/shmem_fs.h>
 #include <linux/suspend.h>
 #include <linux/sched/mm.h>
-#include "arch.h"
+#include <asm/sgx.h>
 #include "encl.h"
 #include "encls.h"
 #include "sgx.h"
@@ -78,7 +78,7 @@ static struct sgx_epc_page *sgx_encl_eldu(struct sgx_encl_page *encl_page,
 
 	ret = __sgx_encl_eldu(encl_page, epc_page, secs_page);
 	if (ret) {
-		sgx_free_epc_page(epc_page);
+		sgx_encl_free_epc_page(epc_page);
 		return ERR_PTR(ret);
 	}
 
@@ -404,7 +404,7 @@ void sgx_encl_release(struct kref *ref)
 			if (sgx_unmark_page_reclaimable(entry->epc_page))
 				continue;
 
-			sgx_free_epc_page(entry->epc_page);
+			sgx_encl_free_epc_page(entry->epc_page);
 			encl->secs_child_cnt--;
 			entry->epc_page = NULL;
 		}
@@ -415,7 +415,7 @@ void sgx_encl_release(struct kref *ref)
 	xa_destroy(&encl->page_array);
 
 	if (!encl->secs_child_cnt && encl->secs.epc_page) {
-		sgx_free_epc_page(encl->secs.epc_page);
+		sgx_encl_free_epc_page(encl->secs.epc_page);
 		encl->secs.epc_page = NULL;
 	}
 
@@ -423,7 +423,7 @@ void sgx_encl_release(struct kref *ref)
 		va_page = list_first_entry(&encl->va_pages, struct sgx_va_page,
 					   list);
 		list_del(&va_page->list);
-		sgx_free_epc_page(va_page->epc_page);
+		sgx_encl_free_epc_page(va_page->epc_page);
 		kfree(va_page);
 	}
 
@@ -686,7 +686,7 @@ struct sgx_epc_page *sgx_alloc_va_page(void)
 	ret = __epa(sgx_get_epc_virt_addr(epc_page));
 	if (ret) {
 		WARN_ONCE(1, "EPA returned %d (0x%x)", ret, ret);
-		sgx_free_epc_page(epc_page);
+		sgx_encl_free_epc_page(epc_page);
 		return ERR_PTR(-EFAULT);
 	}
 
@@ -735,3 +735,24 @@ bool sgx_va_page_full(struct sgx_va_page *va_page)
 
 	return slot == SGX_VA_SLOT_COUNT;
 }
+
+/**
+ * sgx_encl_free_epc_page - free an EPC page assigned to an enclave
+ * @page:	EPC page to be freed
+ *
+ * Free an EPC page assigned to an enclave. It does EREMOVE for the page, and
+ * only upon success, it puts the page back to free page list.  Otherwise, it
+ * gives a WARNING to indicate page is leaked.
+ */
+void sgx_encl_free_epc_page(struct sgx_epc_page *page)
+{
+	int ret;
+
+	WARN_ON_ONCE(page->flags & SGX_EPC_PAGE_RECLAIMER_TRACKED);
+
+	ret = __eremove(sgx_get_epc_virt_addr(page));
+	if (WARN_ONCE(ret, EREMOVE_ERROR_MESSAGE, ret, ret))
+		return;
+
+	sgx_free_epc_page(page);
+}
diff --git a/arch/x86/kernel/cpu/sgx/encl.h b/arch/x86/kernel/cpu/sgx/encl.h
index d8d30ccbef4c..6e74f85b6264 100644
--- a/arch/x86/kernel/cpu/sgx/encl.h
+++ b/arch/x86/kernel/cpu/sgx/encl.h
@@ -115,5 +115,6 @@ struct sgx_epc_page *sgx_alloc_va_page(void);
 unsigned int sgx_alloc_va_slot(struct sgx_va_page *va_page);
 void sgx_free_va_slot(struct sgx_va_page *va_page, unsigned int offset);
 bool sgx_va_page_full(struct sgx_va_page *va_page);
+void sgx_encl_free_epc_page(struct sgx_epc_page *page);
 
 #endif /* _X86_ENCL_H */
diff --git a/arch/x86/kernel/cpu/sgx/encls.h b/arch/x86/kernel/cpu/sgx/encls.h
index 443188fe7e70..9b204843b78d 100644
--- a/arch/x86/kernel/cpu/sgx/encls.h
+++ b/arch/x86/kernel/cpu/sgx/encls.h
@@ -11,21 +11,6 @@
 #include <asm/traps.h>
 #include "sgx.h"
 
-enum sgx_encls_function {
-	ECREATE	= 0x00,
-	EADD	= 0x01,
-	EINIT	= 0x02,
-	EREMOVE	= 0x03,
-	EDGBRD	= 0x04,
-	EDGBWR	= 0x05,
-	EEXTEND	= 0x06,
-	ELDU	= 0x08,
-	EBLOCK	= 0x09,
-	EPA	= 0x0A,
-	EWB	= 0x0B,
-	ETRACK	= 0x0C,
-};
-
 /**
  * ENCLS_FAULT_FLAG - flag signifying an ENCLS return code is a trapnr
  *
@@ -55,6 +40,19 @@ enum sgx_encls_function {
 	} while (0);							  \
 }
 
+/*
+ * encls_faulted() - Check if an ENCLS leaf faulted given an error code
+ * @ret:	the return value of an ENCLS leaf function call
+ *
+ * Return:
+ * - true:	ENCLS leaf faulted.
+ * - false:	Otherwise.
+ */
+static inline bool encls_faulted(int ret)
+{
+	return ret & ENCLS_FAULT_FLAG;
+}
+
 /**
  * encls_failed() - Check if an ENCLS function failed
  * @ret:	the return value of an ENCLS function call
@@ -65,7 +63,7 @@ enum sgx_encls_function {
  */
 static inline bool encls_failed(int ret)
 {
-	if (ret & ENCLS_FAULT_FLAG)
+	if (encls_faulted(ret))
 		return ENCLS_TRAPNR(ret) != X86_TRAP_PF;
 
 	return !!ret;
diff --git a/arch/x86/kernel/cpu/sgx/ioctl.c b/arch/x86/kernel/cpu/sgx/ioctl.c
index 90a5caf76939..83df20e3e633 100644
--- a/arch/x86/kernel/cpu/sgx/ioctl.c
+++ b/arch/x86/kernel/cpu/sgx/ioctl.c
@@ -2,6 +2,7 @@
 /*  Copyright(c) 2016-20 Intel Corporation. */
 
 #include <asm/mman.h>
+#include <asm/sgx.h>
 #include <linux/mman.h>
 #include <linux/delay.h>
 #include <linux/file.h>
@@ -47,7 +48,7 @@ static void sgx_encl_shrink(struct sgx_encl *encl, struct sgx_va_page *va_page)
 	encl->page_cnt--;
 
 	if (va_page) {
-		sgx_free_epc_page(va_page->epc_page);
+		sgx_encl_free_epc_page(va_page->epc_page);
 		list_del(&va_page->list);
 		kfree(va_page);
 	}
@@ -117,7 +118,7 @@ static int sgx_encl_create(struct sgx_encl *encl, struct sgx_secs *secs)
 	return 0;
 
 err_out:
-	sgx_free_epc_page(encl->secs.epc_page);
+	sgx_encl_free_epc_page(encl->secs.epc_page);
 	encl->secs.epc_page = NULL;
 
 err_out_backing:
@@ -365,7 +366,7 @@ err_out_unlock:
 	mmap_read_unlock(current->mm);
 
 err_out_free:
-	sgx_free_epc_page(epc_page);
+	sgx_encl_free_epc_page(epc_page);
 	kfree(encl_page);
 
 	return ret;
@@ -495,7 +496,7 @@ static int sgx_encl_init(struct sgx_encl *encl, struct sgx_sigstruct *sigstruct,
 			 void *token)
 {
 	u64 mrsigner[4];
-	int i, j, k;
+	int i, j;
 	void *addr;
 	int ret;
 
@@ -544,8 +545,7 @@ static int sgx_encl_init(struct sgx_encl *encl, struct sgx_sigstruct *sigstruct,
 
 			preempt_disable();
 
-			for (k = 0; k < 4; k++)
-				wrmsrl(MSR_IA32_SGXLEPUBKEYHASH0 + k, mrsigner[k]);
+			sgx_update_lepubkeyhash(mrsigner);
 
 			ret = __einit(sigstruct, token, addr);
 
@@ -568,7 +568,7 @@ static int sgx_encl_init(struct sgx_encl *encl, struct sgx_sigstruct *sigstruct,
 		}
 	}
 
-	if (ret & ENCLS_FAULT_FLAG) {
+	if (encls_faulted(ret)) {
 		if (encls_failed(ret))
 			ENCLS_WARN(ret, "EINIT");
 
@@ -604,7 +604,6 @@ static long sgx_ioc_enclave_init(struct sgx_encl *encl, void __user *arg)
 {
 	struct sgx_sigstruct *sigstruct;
 	struct sgx_enclave_init init_arg;
-	struct page *initp_page;
 	void *token;
 	int ret;
 
@@ -615,11 +614,15 @@ static long sgx_ioc_enclave_init(struct sgx_encl *encl, void __user *arg)
 	if (copy_from_user(&init_arg, arg, sizeof(init_arg)))
 		return -EFAULT;
 
-	initp_page = alloc_page(GFP_KERNEL);
-	if (!initp_page)
+	/*
+	 * 'sigstruct' must be on a page boundary and 'token' on a 512 byte
+	 * boundary.  kmalloc() will give this alignment when allocating
+	 * PAGE_SIZE bytes.
+	 */
+	sigstruct = kmalloc(PAGE_SIZE, GFP_KERNEL);
+	if (!sigstruct)
 		return -ENOMEM;
 
-	sigstruct = kmap(initp_page);
 	token = (void *)((unsigned long)sigstruct + PAGE_SIZE / 2);
 	memset(token, 0, SGX_LAUNCH_TOKEN_SIZE);
 
@@ -645,8 +648,7 @@ static long sgx_ioc_enclave_init(struct sgx_encl *encl, void __user *arg)
 	ret = sgx_encl_init(encl, sigstruct, token);
 
 out:
-	kunmap(initp_page);
-	__free_page(initp_page);
+	kfree(sigstruct);
 	return ret;
 }
 
@@ -665,24 +667,11 @@ out:
 static long sgx_ioc_enclave_provision(struct sgx_encl *encl, void __user *arg)
 {
 	struct sgx_enclave_provision params;
-	struct file *file;
 
 	if (copy_from_user(&params, arg, sizeof(params)))
 		return -EFAULT;
 
-	file = fget(params.fd);
-	if (!file)
-		return -EINVAL;
-
-	if (file->f_op != &sgx_provision_fops) {
-		fput(file);
-		return -EINVAL;
-	}
-
-	encl->attributes_mask |= SGX_ATTR_PROVISIONKEY;
-
-	fput(file);
-	return 0;
+	return sgx_set_attribute(&encl->attributes_mask, params.fd);
 }
 
 long sgx_ioctl(struct file *filep, unsigned int cmd, unsigned long arg)
diff --git a/arch/x86/kernel/cpu/sgx/main.c b/arch/x86/kernel/cpu/sgx/main.c
index 8df81a3ed945..ad904747419e 100644
--- a/arch/x86/kernel/cpu/sgx/main.c
+++ b/arch/x86/kernel/cpu/sgx/main.c
@@ -1,14 +1,17 @@
 // SPDX-License-Identifier: GPL-2.0
 /*  Copyright(c) 2016-20 Intel Corporation. */
 
+#include <linux/file.h>
 #include <linux/freezer.h>
 #include <linux/highmem.h>
 #include <linux/kthread.h>
+#include <linux/miscdevice.h>
 #include <linux/pagemap.h>
 #include <linux/ratelimit.h>
 #include <linux/sched/mm.h>
 #include <linux/sched/signal.h>
 #include <linux/slab.h>
+#include <asm/sgx.h>
 #include "driver.h"
 #include "encl.h"
 #include "encls.h"
@@ -23,42 +26,58 @@ static DECLARE_WAIT_QUEUE_HEAD(ksgxd_waitq);
  * with sgx_reclaimer_lock acquired.
  */
 static LIST_HEAD(sgx_active_page_list);
-
 static DEFINE_SPINLOCK(sgx_reclaimer_lock);
 
+/* The free page list lock protected variables prepend the lock. */
+static unsigned long sgx_nr_free_pages;
+
+/* Nodes with one or more EPC sections. */
+static nodemask_t sgx_numa_mask;
+
+/*
+ * Array with one list_head for each possible NUMA node.  Each
+ * list contains all the sgx_epc_section's which are on that
+ * node.
+ */
+static struct sgx_numa_node *sgx_numa_nodes;
+
+static LIST_HEAD(sgx_dirty_page_list);
+
 /*
- * Reset dirty EPC pages to uninitialized state. Laundry can be left with SECS
- * pages whose child pages blocked EREMOVE.
+ * Reset post-kexec EPC pages to the uninitialized state. The pages are removed
+ * from the input list, and made available for the page allocator. SECS pages
+ * prepending their children in the input list are left intact.
  */
-static void sgx_sanitize_section(struct sgx_epc_section *section)
+static void __sgx_sanitize_pages(struct list_head *dirty_page_list)
 {
 	struct sgx_epc_page *page;
 	LIST_HEAD(dirty);
 	int ret;
 
-	/* init_laundry_list is thread-local, no need for a lock: */
-	while (!list_empty(&section->init_laundry_list)) {
+	/* dirty_page_list is thread-local, no need for a lock: */
+	while (!list_empty(dirty_page_list)) {
 		if (kthread_should_stop())
 			return;
 
-		/* needed for access to ->page_list: */
-		spin_lock(&section->lock);
-
-		page = list_first_entry(&section->init_laundry_list,
-					struct sgx_epc_page, list);
+		page = list_first_entry(dirty_page_list, struct sgx_epc_page, list);
 
 		ret = __eremove(sgx_get_epc_virt_addr(page));
-		if (!ret)
-			list_move(&page->list, &section->page_list);
-		else
+		if (!ret) {
+			/*
+			 * page is now sanitized.  Make it available via the SGX
+			 * page allocator:
+			 */
+			list_del(&page->list);
+			sgx_free_epc_page(page);
+		} else {
+			/* The page is not yet clean - move to the dirty list. */
 			list_move_tail(&page->list, &dirty);
-
-		spin_unlock(&section->lock);
+		}
 
 		cond_resched();
 	}
 
-	list_splice(&dirty, &section->init_laundry_list);
+	list_splice(&dirty, dirty_page_list);
 }
 
 static bool sgx_reclaimer_age(struct sgx_epc_page *epc_page)
@@ -278,7 +297,7 @@ static void sgx_reclaimer_write(struct sgx_epc_page *epc_page,
 
 		sgx_encl_ewb(encl->secs.epc_page, &secs_backing);
 
-		sgx_free_epc_page(encl->secs.epc_page);
+		sgx_encl_free_epc_page(encl->secs.epc_page);
 		encl->secs.epc_page = NULL;
 
 		sgx_encl_put_backing(&secs_backing, true);
@@ -308,6 +327,7 @@ static void sgx_reclaim_pages(void)
 	struct sgx_epc_section *section;
 	struct sgx_encl_page *encl_page;
 	struct sgx_epc_page *epc_page;
+	struct sgx_numa_node *node;
 	pgoff_t page_index;
 	int cnt = 0;
 	int ret;
@@ -379,50 +399,33 @@ skip:
 		epc_page->flags &= ~SGX_EPC_PAGE_RECLAIMER_TRACKED;
 
 		section = &sgx_epc_sections[epc_page->section];
-		spin_lock(&section->lock);
-		list_add_tail(&epc_page->list, &section->page_list);
-		section->free_cnt++;
-		spin_unlock(&section->lock);
-	}
-}
-
-static unsigned long sgx_nr_free_pages(void)
-{
-	unsigned long cnt = 0;
-	int i;
-
-	for (i = 0; i < sgx_nr_epc_sections; i++)
-		cnt += sgx_epc_sections[i].free_cnt;
+		node = section->node;
 
-	return cnt;
+		spin_lock(&node->lock);
+		list_add_tail(&epc_page->list, &node->free_page_list);
+		sgx_nr_free_pages++;
+		spin_unlock(&node->lock);
+	}
 }
 
 static bool sgx_should_reclaim(unsigned long watermark)
 {
-	return sgx_nr_free_pages() < watermark &&
-	       !list_empty(&sgx_active_page_list);
+	return sgx_nr_free_pages < watermark && !list_empty(&sgx_active_page_list);
 }
 
 static int ksgxd(void *p)
 {
-	int i;
-
 	set_freezable();
 
 	/*
 	 * Sanitize pages in order to recover from kexec(). The 2nd pass is
 	 * required for SECS pages, whose child pages blocked EREMOVE.
 	 */
-	for (i = 0; i < sgx_nr_epc_sections; i++)
-		sgx_sanitize_section(&sgx_epc_sections[i]);
-
-	for (i = 0; i < sgx_nr_epc_sections; i++) {
-		sgx_sanitize_section(&sgx_epc_sections[i]);
+	__sgx_sanitize_pages(&sgx_dirty_page_list);
+	__sgx_sanitize_pages(&sgx_dirty_page_list);
 
-		/* Should never happen. */
-		if (!list_empty(&sgx_epc_sections[i].init_laundry_list))
-			WARN(1, "EPC section %d has unsanitized pages.\n", i);
-	}
+	/* sanity check: */
+	WARN_ON(!list_empty(&sgx_dirty_page_list));
 
 	while (!kthread_should_stop()) {
 		if (try_to_freeze())
@@ -454,45 +457,56 @@ static bool __init sgx_page_reclaimer_init(void)
 	return true;
 }
 
-static struct sgx_epc_page *__sgx_alloc_epc_page_from_section(struct sgx_epc_section *section)
+static struct sgx_epc_page *__sgx_alloc_epc_page_from_node(int nid)
 {
-	struct sgx_epc_page *page;
+	struct sgx_numa_node *node = &sgx_numa_nodes[nid];
+	struct sgx_epc_page *page = NULL;
 
-	spin_lock(&section->lock);
+	spin_lock(&node->lock);
 
-	if (list_empty(&section->page_list)) {
-		spin_unlock(&section->lock);
+	if (list_empty(&node->free_page_list)) {
+		spin_unlock(&node->lock);
 		return NULL;
 	}
 
-	page = list_first_entry(&section->page_list, struct sgx_epc_page, list);
+	page = list_first_entry(&node->free_page_list, struct sgx_epc_page, list);
 	list_del_init(&page->list);
-	section->free_cnt--;
+	sgx_nr_free_pages--;
+
+	spin_unlock(&node->lock);
 
-	spin_unlock(&section->lock);
 	return page;
 }
 
 /**
  * __sgx_alloc_epc_page() - Allocate an EPC page
  *
- * Iterate through EPC sections and borrow a free EPC page to the caller. When a
- * page is no longer needed it must be released with sgx_free_epc_page().
+ * Iterate through NUMA nodes and reserve ia free EPC page to the caller. Start
+ * from the NUMA node, where the caller is executing.
  *
  * Return:
- *   an EPC page,
- *   -errno on error
+ * - an EPC page:	A borrowed EPC pages were available.
+ * - NULL:		Out of EPC pages.
  */
 struct sgx_epc_page *__sgx_alloc_epc_page(void)
 {
-	struct sgx_epc_section *section;
 	struct sgx_epc_page *page;
-	int i;
+	int nid_of_current = numa_node_id();
+	int nid = nid_of_current;
 
-	for (i = 0; i < sgx_nr_epc_sections; i++) {
-		section = &sgx_epc_sections[i];
+	if (node_isset(nid_of_current, sgx_numa_mask)) {
+		page = __sgx_alloc_epc_page_from_node(nid_of_current);
+		if (page)
+			return page;
+	}
+
+	/* Fall back to the non-local NUMA nodes: */
+	while (true) {
+		nid = next_node_in(nid, sgx_numa_mask);
+		if (nid == nid_of_current)
+			break;
 
-		page = __sgx_alloc_epc_page_from_section(section);
+		page = __sgx_alloc_epc_page_from_node(nid);
 		if (page)
 			return page;
 	}
@@ -598,23 +612,22 @@ struct sgx_epc_page *sgx_alloc_epc_page(void *owner, bool reclaim)
  * sgx_free_epc_page() - Free an EPC page
  * @page:	an EPC page
  *
- * Call EREMOVE for an EPC page and insert it back to the list of free pages.
+ * Put the EPC page back to the list of free pages. It's the caller's
+ * responsibility to make sure that the page is in uninitialized state. In other
+ * words, do EREMOVE, EWB or whatever operation is necessary before calling
+ * this function.
  */
 void sgx_free_epc_page(struct sgx_epc_page *page)
 {
 	struct sgx_epc_section *section = &sgx_epc_sections[page->section];
-	int ret;
+	struct sgx_numa_node *node = section->node;
 
-	WARN_ON_ONCE(page->flags & SGX_EPC_PAGE_RECLAIMER_TRACKED);
+	spin_lock(&node->lock);
 
-	ret = __eremove(sgx_get_epc_virt_addr(page));
-	if (WARN_ONCE(ret, "EREMOVE returned %d (0x%x)", ret, ret))
-		return;
+	list_add_tail(&page->list, &node->free_page_list);
+	sgx_nr_free_pages++;
 
-	spin_lock(&section->lock);
-	list_add_tail(&page->list, &section->page_list);
-	section->free_cnt++;
-	spin_unlock(&section->lock);
+	spin_unlock(&node->lock);
 }
 
 static bool __init sgx_setup_epc_section(u64 phys_addr, u64 size,
@@ -635,18 +648,14 @@ static bool __init sgx_setup_epc_section(u64 phys_addr, u64 size,
 	}
 
 	section->phys_addr = phys_addr;
-	spin_lock_init(&section->lock);
-	INIT_LIST_HEAD(&section->page_list);
-	INIT_LIST_HEAD(&section->init_laundry_list);
 
 	for (i = 0; i < nr_pages; i++) {
 		section->pages[i].section = index;
 		section->pages[i].flags = 0;
 		section->pages[i].owner = NULL;
-		list_add_tail(&section->pages[i].list, &section->init_laundry_list);
+		list_add_tail(&section->pages[i].list, &sgx_dirty_page_list);
 	}
 
-	section->free_cnt = nr_pages;
 	return true;
 }
 
@@ -665,8 +674,13 @@ static bool __init sgx_page_cache_init(void)
 {
 	u32 eax, ebx, ecx, edx, type;
 	u64 pa, size;
+	int nid;
 	int i;
 
+	sgx_numa_nodes = kmalloc_array(num_possible_nodes(), sizeof(*sgx_numa_nodes), GFP_KERNEL);
+	if (!sgx_numa_nodes)
+		return false;
+
 	for (i = 0; i < ARRAY_SIZE(sgx_epc_sections); i++) {
 		cpuid_count(SGX_CPUID, i + SGX_CPUID_EPC, &eax, &ebx, &ecx, &edx);
 
@@ -689,6 +703,21 @@ static bool __init sgx_page_cache_init(void)
 			break;
 		}
 
+		nid = numa_map_to_online_node(phys_to_target_node(pa));
+		if (nid == NUMA_NO_NODE) {
+			/* The physical address is already printed above. */
+			pr_warn(FW_BUG "Unable to map EPC section to online node. Fallback to the NUMA node 0.\n");
+			nid = 0;
+		}
+
+		if (!node_isset(nid, sgx_numa_mask)) {
+			spin_lock_init(&sgx_numa_nodes[nid].lock);
+			INIT_LIST_HEAD(&sgx_numa_nodes[nid].free_page_list);
+			node_set(nid, sgx_numa_mask);
+		}
+
+		sgx_epc_sections[i].node =  &sgx_numa_nodes[nid];
+
 		sgx_nr_epc_sections++;
 	}
 
@@ -700,6 +729,67 @@ static bool __init sgx_page_cache_init(void)
 	return true;
 }
 
+/*
+ * Update the SGX_LEPUBKEYHASH MSRs to the values specified by caller.
+ * Bare-metal driver requires to update them to hash of enclave's signer
+ * before EINIT. KVM needs to update them to guest's virtual MSR values
+ * before doing EINIT from guest.
+ */
+void sgx_update_lepubkeyhash(u64 *lepubkeyhash)
+{
+	int i;
+
+	WARN_ON_ONCE(preemptible());
+
+	for (i = 0; i < 4; i++)
+		wrmsrl(MSR_IA32_SGXLEPUBKEYHASH0 + i, lepubkeyhash[i]);
+}
+
+const struct file_operations sgx_provision_fops = {
+	.owner			= THIS_MODULE,
+};
+
+static struct miscdevice sgx_dev_provision = {
+	.minor = MISC_DYNAMIC_MINOR,
+	.name = "sgx_provision",
+	.nodename = "sgx_provision",
+	.fops = &sgx_provision_fops,
+};
+
+/**
+ * sgx_set_attribute() - Update allowed attributes given file descriptor
+ * @allowed_attributes:		Pointer to allowed enclave attributes
+ * @attribute_fd:		File descriptor for specific attribute
+ *
+ * Append enclave attribute indicated by file descriptor to allowed
+ * attributes. Currently only SGX_ATTR_PROVISIONKEY indicated by
+ * /dev/sgx_provision is supported.
+ *
+ * Return:
+ * -0:		SGX_ATTR_PROVISIONKEY is appended to allowed_attributes
+ * -EINVAL:	Invalid, or not supported file descriptor
+ */
+int sgx_set_attribute(unsigned long *allowed_attributes,
+		      unsigned int attribute_fd)
+{
+	struct file *file;
+
+	file = fget(attribute_fd);
+	if (!file)
+		return -EINVAL;
+
+	if (file->f_op != &sgx_provision_fops) {
+		fput(file);
+		return -EINVAL;
+	}
+
+	*allowed_attributes |= SGX_ATTR_PROVISIONKEY;
+
+	fput(file);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(sgx_set_attribute);
+
 static int __init sgx_init(void)
 {
 	int ret;
@@ -716,12 +806,28 @@ static int __init sgx_init(void)
 		goto err_page_cache;
 	}
 
-	ret = sgx_drv_init();
+	ret = misc_register(&sgx_dev_provision);
 	if (ret)
 		goto err_kthread;
 
+	/*
+	 * Always try to initialize the native *and* KVM drivers.
+	 * The KVM driver is less picky than the native one and
+	 * can function if the native one is not supported on the
+	 * current system or fails to initialize.
+	 *
+	 * Error out only if both fail to initialize.
+	 */
+	ret = sgx_drv_init();
+
+	if (sgx_vepc_init() && ret)
+		goto err_provision;
+
 	return 0;
 
+err_provision:
+	misc_deregister(&sgx_dev_provision);
+
 err_kthread:
 	kthread_stop(ksgxd_tsk);
 
diff --git a/arch/x86/kernel/cpu/sgx/sgx.h b/arch/x86/kernel/cpu/sgx/sgx.h
index 5fa42d143feb..4628acec0009 100644
--- a/arch/x86/kernel/cpu/sgx/sgx.h
+++ b/arch/x86/kernel/cpu/sgx/sgx.h
@@ -8,11 +8,15 @@
 #include <linux/rwsem.h>
 #include <linux/types.h>
 #include <asm/asm.h>
-#include "arch.h"
+#include <asm/sgx.h>
 
 #undef pr_fmt
 #define pr_fmt(fmt) "sgx: " fmt
 
+#define EREMOVE_ERROR_MESSAGE \
+	"EREMOVE returned %d (0x%x) and an EPC page was leaked. SGX may become unusable. " \
+	"Refer to Documentation/x86/sgx.rst for more information."
+
 #define SGX_MAX_EPC_SECTIONS		8
 #define SGX_EEXTEND_BLOCK_SIZE		256
 #define SGX_NR_TO_SCAN			16
@@ -30,28 +34,25 @@ struct sgx_epc_page {
 };
 
 /*
+ * Contains the tracking data for NUMA nodes having EPC pages. Most importantly,
+ * the free page list local to the node is stored here.
+ */
+struct sgx_numa_node {
+	struct list_head free_page_list;
+	spinlock_t lock;
+};
+
+/*
  * The firmware can define multiple chunks of EPC to the different areas of the
  * physical memory e.g. for memory areas of the each node. This structure is
  * used to store EPC pages for one EPC section and virtual memory area where
  * the pages have been mapped.
- *
- * 'lock' must be held before accessing 'page_list' or 'free_cnt'.
  */
 struct sgx_epc_section {
 	unsigned long phys_addr;
 	void *virt_addr;
 	struct sgx_epc_page *pages;
-
-	spinlock_t lock;
-	struct list_head page_list;
-	unsigned long free_cnt;
-
-	/*
-	 * Pages which need EREMOVE run on them before they can be
-	 * used.  Only safe to be accessed in ksgxd and init code.
-	 * Not protected by locks.
-	 */
-	struct list_head init_laundry_list;
+	struct sgx_numa_node *node;
 };
 
 extern struct sgx_epc_section sgx_epc_sections[SGX_MAX_EPC_SECTIONS];
@@ -83,4 +84,15 @@ void sgx_mark_page_reclaimable(struct sgx_epc_page *page);
 int sgx_unmark_page_reclaimable(struct sgx_epc_page *page);
 struct sgx_epc_page *sgx_alloc_epc_page(void *owner, bool reclaim);
 
+#ifdef CONFIG_X86_SGX_KVM
+int __init sgx_vepc_init(void);
+#else
+static inline int __init sgx_vepc_init(void)
+{
+	return -ENODEV;
+}
+#endif
+
+void sgx_update_lepubkeyhash(u64 *lepubkeyhash);
+
 #endif /* _X86_SGX_H */
diff --git a/arch/x86/kernel/cpu/sgx/virt.c b/arch/x86/kernel/cpu/sgx/virt.c
new file mode 100644
index 000000000000..6ad165a5c0cc
--- /dev/null
+++ b/arch/x86/kernel/cpu/sgx/virt.c
@@ -0,0 +1,376 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Device driver to expose SGX enclave memory to KVM guests.
+ *
+ * Copyright(c) 2021 Intel Corporation.
+ */
+
+#include <linux/miscdevice.h>
+#include <linux/mm.h>
+#include <linux/mman.h>
+#include <linux/sched/mm.h>
+#include <linux/sched/signal.h>
+#include <linux/slab.h>
+#include <linux/xarray.h>
+#include <asm/sgx.h>
+#include <uapi/asm/sgx.h>
+
+#include "encls.h"
+#include "sgx.h"
+
+struct sgx_vepc {
+	struct xarray page_array;
+	struct mutex lock;
+};
+
+/*
+ * Temporary SECS pages that cannot be EREMOVE'd due to having child in other
+ * virtual EPC instances, and the lock to protect it.
+ */
+static struct mutex zombie_secs_pages_lock;
+static struct list_head zombie_secs_pages;
+
+static int __sgx_vepc_fault(struct sgx_vepc *vepc,
+			    struct vm_area_struct *vma, unsigned long addr)
+{
+	struct sgx_epc_page *epc_page;
+	unsigned long index, pfn;
+	int ret;
+
+	WARN_ON(!mutex_is_locked(&vepc->lock));
+
+	/* Calculate index of EPC page in virtual EPC's page_array */
+	index = vma->vm_pgoff + PFN_DOWN(addr - vma->vm_start);
+
+	epc_page = xa_load(&vepc->page_array, index);
+	if (epc_page)
+		return 0;
+
+	epc_page = sgx_alloc_epc_page(vepc, false);
+	if (IS_ERR(epc_page))
+		return PTR_ERR(epc_page);
+
+	ret = xa_err(xa_store(&vepc->page_array, index, epc_page, GFP_KERNEL));
+	if (ret)
+		goto err_free;
+
+	pfn = PFN_DOWN(sgx_get_epc_phys_addr(epc_page));
+
+	ret = vmf_insert_pfn(vma, addr, pfn);
+	if (ret != VM_FAULT_NOPAGE) {
+		ret = -EFAULT;
+		goto err_delete;
+	}
+
+	return 0;
+
+err_delete:
+	xa_erase(&vepc->page_array, index);
+err_free:
+	sgx_free_epc_page(epc_page);
+	return ret;
+}
+
+static vm_fault_t sgx_vepc_fault(struct vm_fault *vmf)
+{
+	struct vm_area_struct *vma = vmf->vma;
+	struct sgx_vepc *vepc = vma->vm_private_data;
+	int ret;
+
+	mutex_lock(&vepc->lock);
+	ret = __sgx_vepc_fault(vepc, vma, vmf->address);
+	mutex_unlock(&vepc->lock);
+
+	if (!ret)
+		return VM_FAULT_NOPAGE;
+
+	if (ret == -EBUSY && (vmf->flags & FAULT_FLAG_ALLOW_RETRY)) {
+		mmap_read_unlock(vma->vm_mm);
+		return VM_FAULT_RETRY;
+	}
+
+	return VM_FAULT_SIGBUS;
+}
+
+static const struct vm_operations_struct sgx_vepc_vm_ops = {
+	.fault = sgx_vepc_fault,
+};
+
+static int sgx_vepc_mmap(struct file *file, struct vm_area_struct *vma)
+{
+	struct sgx_vepc *vepc = file->private_data;
+
+	if (!(vma->vm_flags & VM_SHARED))
+		return -EINVAL;
+
+	vma->vm_ops = &sgx_vepc_vm_ops;
+	/* Don't copy VMA in fork() */
+	vma->vm_flags |= VM_PFNMAP | VM_IO | VM_DONTDUMP | VM_DONTCOPY;
+	vma->vm_private_data = vepc;
+
+	return 0;
+}
+
+static int sgx_vepc_free_page(struct sgx_epc_page *epc_page)
+{
+	int ret;
+
+	/*
+	 * Take a previously guest-owned EPC page and return it to the
+	 * general EPC page pool.
+	 *
+	 * Guests can not be trusted to have left this page in a good
+	 * state, so run EREMOVE on the page unconditionally.  In the
+	 * case that a guest properly EREMOVE'd this page, a superfluous
+	 * EREMOVE is harmless.
+	 */
+	ret = __eremove(sgx_get_epc_virt_addr(epc_page));
+	if (ret) {
+		/*
+		 * Only SGX_CHILD_PRESENT is expected, which is because of
+		 * EREMOVE'ing an SECS still with child, in which case it can
+		 * be handled by EREMOVE'ing the SECS again after all pages in
+		 * virtual EPC have been EREMOVE'd. See comments in below in
+		 * sgx_vepc_release().
+		 *
+		 * The user of virtual EPC (KVM) needs to guarantee there's no
+		 * logical processor is still running in the enclave in guest,
+		 * otherwise EREMOVE will get SGX_ENCLAVE_ACT which cannot be
+		 * handled here.
+		 */
+		WARN_ONCE(ret != SGX_CHILD_PRESENT, EREMOVE_ERROR_MESSAGE,
+			  ret, ret);
+		return ret;
+	}
+
+	sgx_free_epc_page(epc_page);
+
+	return 0;
+}
+
+static int sgx_vepc_release(struct inode *inode, struct file *file)
+{
+	struct sgx_vepc *vepc = file->private_data;
+	struct sgx_epc_page *epc_page, *tmp, *entry;
+	unsigned long index;
+
+	LIST_HEAD(secs_pages);
+
+	xa_for_each(&vepc->page_array, index, entry) {
+		/*
+		 * Remove all normal, child pages.  sgx_vepc_free_page()
+		 * will fail if EREMOVE fails, but this is OK and expected on
+		 * SECS pages.  Those can only be EREMOVE'd *after* all their
+		 * child pages. Retries below will clean them up.
+		 */
+		if (sgx_vepc_free_page(entry))
+			continue;
+
+		xa_erase(&vepc->page_array, index);
+	}
+
+	/*
+	 * Retry EREMOVE'ing pages.  This will clean up any SECS pages that
+	 * only had children in this 'epc' area.
+	 */
+	xa_for_each(&vepc->page_array, index, entry) {
+		epc_page = entry;
+		/*
+		 * An EREMOVE failure here means that the SECS page still
+		 * has children.  But, since all children in this 'sgx_vepc'
+		 * have been removed, the SECS page must have a child on
+		 * another instance.
+		 */
+		if (sgx_vepc_free_page(epc_page))
+			list_add_tail(&epc_page->list, &secs_pages);
+
+		xa_erase(&vepc->page_array, index);
+	}
+
+	/*
+	 * SECS pages are "pinned" by child pages, and "unpinned" once all
+	 * children have been EREMOVE'd.  A child page in this instance
+	 * may have pinned an SECS page encountered in an earlier release(),
+	 * creating a zombie.  Since some children were EREMOVE'd above,
+	 * try to EREMOVE all zombies in the hopes that one was unpinned.
+	 */
+	mutex_lock(&zombie_secs_pages_lock);
+	list_for_each_entry_safe(epc_page, tmp, &zombie_secs_pages, list) {
+		/*
+		 * Speculatively remove the page from the list of zombies,
+		 * if the page is successfully EREMOVE'd it will be added to
+		 * the list of free pages.  If EREMOVE fails, throw the page
+		 * on the local list, which will be spliced on at the end.
+		 */
+		list_del(&epc_page->list);
+
+		if (sgx_vepc_free_page(epc_page))
+			list_add_tail(&epc_page->list, &secs_pages);
+	}
+
+	if (!list_empty(&secs_pages))
+		list_splice_tail(&secs_pages, &zombie_secs_pages);
+	mutex_unlock(&zombie_secs_pages_lock);
+
+	kfree(vepc);
+
+	return 0;
+}
+
+static int sgx_vepc_open(struct inode *inode, struct file *file)
+{
+	struct sgx_vepc *vepc;
+
+	vepc = kzalloc(sizeof(struct sgx_vepc), GFP_KERNEL);
+	if (!vepc)
+		return -ENOMEM;
+	mutex_init(&vepc->lock);
+	xa_init(&vepc->page_array);
+
+	file->private_data = vepc;
+
+	return 0;
+}
+
+static const struct file_operations sgx_vepc_fops = {
+	.owner		= THIS_MODULE,
+	.open		= sgx_vepc_open,
+	.release	= sgx_vepc_release,
+	.mmap		= sgx_vepc_mmap,
+};
+
+static struct miscdevice sgx_vepc_dev = {
+	.minor		= MISC_DYNAMIC_MINOR,
+	.name		= "sgx_vepc",
+	.nodename	= "sgx_vepc",
+	.fops		= &sgx_vepc_fops,
+};
+
+int __init sgx_vepc_init(void)
+{
+	/* SGX virtualization requires KVM to work */
+	if (!cpu_feature_enabled(X86_FEATURE_VMX))
+		return -ENODEV;
+
+	INIT_LIST_HEAD(&zombie_secs_pages);
+	mutex_init(&zombie_secs_pages_lock);
+
+	return misc_register(&sgx_vepc_dev);
+}
+
+/**
+ * sgx_virt_ecreate() - Run ECREATE on behalf of guest
+ * @pageinfo:	Pointer to PAGEINFO structure
+ * @secs:	Userspace pointer to SECS page
+ * @trapnr:	trap number injected to guest in case of ECREATE error
+ *
+ * Run ECREATE on behalf of guest after KVM traps ECREATE for the purpose
+ * of enforcing policies of guest's enclaves, and return the trap number
+ * which should be injected to guest in case of any ECREATE error.
+ *
+ * Return:
+ * -  0:	ECREATE was successful.
+ * - <0:	on error.
+ */
+int sgx_virt_ecreate(struct sgx_pageinfo *pageinfo, void __user *secs,
+		     int *trapnr)
+{
+	int ret;
+
+	/*
+	 * @secs is an untrusted, userspace-provided address.  It comes from
+	 * KVM and is assumed to be a valid pointer which points somewhere in
+	 * userspace.  This can fault and call SGX or other fault handlers when
+	 * userspace mapping @secs doesn't exist.
+	 *
+	 * Add a WARN() to make sure @secs is already valid userspace pointer
+	 * from caller (KVM), who should already have handled invalid pointer
+	 * case (for instance, made by malicious guest).  All other checks,
+	 * such as alignment of @secs, are deferred to ENCLS itself.
+	 */
+	if (WARN_ON_ONCE(!access_ok(secs, PAGE_SIZE)))
+		return -EINVAL;
+
+	__uaccess_begin();
+	ret = __ecreate(pageinfo, (void *)secs);
+	__uaccess_end();
+
+	if (encls_faulted(ret)) {
+		*trapnr = ENCLS_TRAPNR(ret);
+		return -EFAULT;
+	}
+
+	/* ECREATE doesn't return an error code, it faults or succeeds. */
+	WARN_ON_ONCE(ret);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(sgx_virt_ecreate);
+
+static int __sgx_virt_einit(void __user *sigstruct, void __user *token,
+			    void __user *secs)
+{
+	int ret;
+
+	/*
+	 * Make sure all userspace pointers from caller (KVM) are valid.
+	 * All other checks deferred to ENCLS itself.  Also see comment
+	 * for @secs in sgx_virt_ecreate().
+	 */
+#define SGX_EINITTOKEN_SIZE	304
+	if (WARN_ON_ONCE(!access_ok(sigstruct, sizeof(struct sgx_sigstruct)) ||
+			 !access_ok(token, SGX_EINITTOKEN_SIZE) ||
+			 !access_ok(secs, PAGE_SIZE)))
+		return -EINVAL;
+
+	__uaccess_begin();
+	ret = __einit((void *)sigstruct, (void *)token, (void *)secs);
+	__uaccess_end();
+
+	return ret;
+}
+
+/**
+ * sgx_virt_einit() - Run EINIT on behalf of guest
+ * @sigstruct:		Userspace pointer to SIGSTRUCT structure
+ * @token:		Userspace pointer to EINITTOKEN structure
+ * @secs:		Userspace pointer to SECS page
+ * @lepubkeyhash:	Pointer to guest's *virtual* SGX_LEPUBKEYHASH MSR values
+ * @trapnr:		trap number injected to guest in case of EINIT error
+ *
+ * Run EINIT on behalf of guest after KVM traps EINIT. If SGX_LC is available
+ * in host, SGX driver may rewrite the hardware values at wish, therefore KVM
+ * needs to update hardware values to guest's virtual MSR values in order to
+ * ensure EINIT is executed with expected hardware values.
+ *
+ * Return:
+ * -  0:	EINIT was successful.
+ * - <0:	on error.
+ */
+int sgx_virt_einit(void __user *sigstruct, void __user *token,
+		   void __user *secs, u64 *lepubkeyhash, int *trapnr)
+{
+	int ret;
+
+	if (!cpu_feature_enabled(X86_FEATURE_SGX_LC)) {
+		ret = __sgx_virt_einit(sigstruct, token, secs);
+	} else {
+		preempt_disable();
+
+		sgx_update_lepubkeyhash(lepubkeyhash);
+
+		ret = __sgx_virt_einit(sigstruct, token, secs);
+		preempt_enable();
+	}
+
+	/* Propagate up the error from the WARN_ON_ONCE in __sgx_virt_einit() */
+	if (ret == -EINVAL)
+		return ret;
+
+	if (encls_faulted(ret)) {
+		*trapnr = ENCLS_TRAPNR(ret);
+		return -EFAULT;
+	}
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(sgx_virt_einit);