Merge remote-tracking branch 'tip/x86/sgx' into kvm-next

Pull generic x86 SGX changes needed to support SGX in virtual machines.

Documentation/x86/sgx.rst

@@ -209,3 +209,44 @@ An application may be loaded into a container enclave which is specially
 configured with a library OS and run-time which permits the application to run.
 The enclave run-time and library OS work together to execute the application
 when a thread enters the enclave.
+
+Impact of Potential Kernel SGX Bugs
+===================================
+
+EPC leaks
+---------
+
+When EPC page leaks happen, a WARNING like this is shown in dmesg:
+
+"EREMOVE returned ... and an EPC page was leaked.  SGX may become unusable..."
+
+This is effectively a kernel use-after-free of an EPC page, and due
+to the way SGX works, the bug is detected at freeing. Rather than
+adding the page back to the pool of available EPC pages, the kernel
+intentionally leaks the page to avoid additional errors in the future.
+
+When this happens, the kernel will likely soon leak more EPC pages, and
+SGX will likely become unusable because the memory available to SGX is
+limited. However, while this may be fatal to SGX, the rest of the kernel
+is unlikely to be impacted and should continue to work.
+
+As a result, when this happpens, user should stop running any new
+SGX workloads, (or just any new workloads), and migrate all valuable
+workloads. Although a machine reboot can recover all EPC memory, the bug
+should be reported to Linux developers.
+
+
+Virtual EPC
+===========
+
+The implementation has also a virtual EPC driver to support SGX enclaves
+in guests. Unlike the SGX driver, an EPC page allocated by the virtual
+EPC driver doesn't have a specific enclave associated with it. This is
+because KVM doesn't track how a guest uses EPC pages.
+
+As a result, the SGX core page reclaimer doesn't support reclaiming EPC
+pages allocated to KVM guests through the virtual EPC driver. If the
+user wants to deploy SGX applications both on the host and in guests
+on the same machine, the user should reserve enough EPC (by taking out
+total virtual EPC size of all SGX VMs from the physical EPC size) for
+host SGX applications so they can run with acceptable performance.

MAINTAINERS

@@ -9274,6 +9274,7 @@ Q:	https://patchwork.kernel.org/project/intel-sgx/list/
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git x86/sgx
 F:	Documentation/x86/sgx.rst
 F:	arch/x86/entry/vdso/vsgx.S
+F:	arch/x86/include/asm/sgx.h
 F:	arch/x86/include/uapi/asm/sgx.h
 F:	arch/x86/kernel/cpu/sgx/*
 F:	tools/testing/selftests/sgx/*

arch/x86/Kconfig

@@ -1931,6 +1931,7 @@ config X86_SGX
 	depends on CRYPTO_SHA256=y
 	select SRCU
 	select MMU_NOTIFIER
+	select NUMA_KEEP_MEMINFO if NUMA
 	help
 	  Intel(R) Software Guard eXtensions (SGX) is a set of CPU instructions
 	  that can be used by applications to set aside private regions of code

arch/x86/include/asm/cpufeatures.h

@@ -290,6 +290,8 @@
 #define X86_FEATURE_FENCE_SWAPGS_KERNEL	(11*32+ 5) /* "" LFENCE in kernel entry SWAPGS path */
 #define X86_FEATURE_SPLIT_LOCK_DETECT	(11*32+ 6) /* #AC for split lock */
 #define X86_FEATURE_PER_THREAD_MBA	(11*32+ 7) /* "" Per-thread Memory Bandwidth Allocation */
+#define X86_FEATURE_SGX1		(11*32+ 8) /* "" Basic SGX */
+#define X86_FEATURE_SGX2		(11*32+ 9) /* "" SGX Enclave Dynamic Memory Management (EDMM) */
 
 /* Intel-defined CPU features, CPUID level 0x00000007:1 (EAX), word 12 */
 #define X86_FEATURE_AVX_VNNI		(12*32+ 4) /* AVX VNNI instructions */

arch/x86/kernel/cpu/sgx/arch.h → arch/x86/include/asm/sgx.h

@@ -2,15 +2,20 @@
 /**
  * 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.
+ * Intel Software Guard Extensions (SGX) support.
  */
-#ifndef _ASM_X86_SGX_ARCH_H
-#define _ASM_X86_SGX_ARCH_H
+#ifndef _ASM_X86_SGX_H
+#define _ASM_X86_SGX_H
 
 #include <linux/bits.h>
 #include <linux/types.h>
 
+/*
+ * This file contains both data structures defined by SGX architecture and Linux
+ * defined software data structures and functions.  The two should not be mixed
+ * together for better readibility.  The architectural definitions come first.
+ */
+
 /* The SGX specific CPUID function. */
 #define SGX_CPUID		0x12
 /* EPC enumeration. */
@@ -22,16 +27,36 @@
 /* The bitmask for the EPC section type. */
 #define SGX_CPUID_EPC_MASK	GENMASK(3, 0)
 
+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,
+	EAUG	= 0x0D,
+	EMODPR	= 0x0E,
+	EMODT	= 0x0F,
+};
+
 /**
  * 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_CHILD_PRESENT		SECS has child pages present in the EPC.
  * %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_CHILD_PRESENT		= 13,
 	SGX_INVALID_EINITTOKEN		= 16,
 	SGX_UNMASKED_EVENT		= 128,
 };
@@ -335,4 +360,19 @@ struct sgx_sigstruct {
 
 #define SGX_LAUNCH_TOKEN_SIZE 304
 
-#endif /* _ASM_X86_SGX_ARCH_H */
+/*
+ * Do not put any hardware-defined SGX structure representations below this
+ * comment!
+ */
+
+#ifdef CONFIG_X86_SGX_KVM
+int sgx_virt_ecreate(struct sgx_pageinfo *pageinfo, void __user *secs,
+		     int *trapnr);
+int sgx_virt_einit(void __user *sigstruct, void __user *token,
+		   void __user *secs, u64 *lepubkeyhash, int *trapnr);
+#endif
+
+int sgx_set_attribute(unsigned long *allowed_attributes,
+		      unsigned int attribute_fd);
+
+#endif /* _ASM_X86_SGX_H */

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      },
 	{}
 };
 

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 @@ void init_ia32_feat_ctl(struct cpuinfo_x86 *c)
 	}
 
 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);
+		}
 	}
 }

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 },

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

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;
 }

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);
+}

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 */

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;

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 @@ static int sgx_encl_add_page(struct sgx_encl *encl, unsigned long src,
 	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 @@ static long sgx_ioc_enclave_init(struct sgx_encl *encl, void __user *arg)
 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)

arch/x86/kernel/cpu/sgx/main.c

 // 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 @@ static void sgx_reclaim_pages(void)
 		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);
 

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
@@ -29,29 +33,26 @@ struct sgx_epc_page {
 	struct list_head list;
 };
 
+/*
+ * 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 */

arch/x86/kernel/cpu/sgx/virt.c

+// 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);

arch/x86/kvm/Kconfig

@@ -84,6 +84,18 @@ config KVM_INTEL
 	  To compile this as a module, choose M here: the module
 	  will be called kvm-intel.
 
+config X86_SGX_KVM
+	bool "Software Guard eXtensions (SGX) Virtualization"
+	depends on X86_SGX && KVM_INTEL
+	help
+
+	  Enables KVM guests to create SGX enclaves.
+
+	  This includes support to expose "raw" unreclaimable enclave memory to
+	  guests via a device node, e.g. /dev/sgx_vepc.
+
+	  If unsure, say N.
+
 config KVM_AMD
 	tristate "KVM for AMD processors support"
 	depends on KVM

tools/testing/selftests/sgx/defines.h

@@ -14,7 +14,7 @@
 #define __aligned(x) __attribute__((__aligned__(x)))
 #define __packed __attribute__((packed))
 
-#include "../../../../arch/x86/kernel/cpu/sgx/arch.h"
+#include "../../../../arch/x86/include/asm/sgx.h"
 #include "../../../../arch/x86/include/asm/enclu.h"
 #include "../../../../arch/x86/include/uapi/asm/sgx.h"
 

tools/testing/selftests/sgx/load.c

@@ -45,19 +45,19 @@ static bool encl_map_bin(const char *path, struct encl *encl)
 
 	fd = open(path, O_RDONLY);
 	if (fd == -1)  {
-		perror("open()");
+		perror("enclave executable open()");
 		return false;
 	}
 
 	ret = stat(path, &sb);
 	if (ret) {
-		perror("stat()");
+		perror("enclave executable stat()");
 		goto err;
 	}
 
 	bin = mmap(NULL, sb.st_size, PROT_READ, MAP_PRIVATE, fd, 0);
 	if (bin == MAP_FAILED) {
-		perror("mmap()");
+		perror("enclave executable mmap()");
 		goto err;
 	}
 
@@ -90,8 +90,7 @@ static bool encl_ioc_create(struct encl *encl)
 	ioc.src = (unsigned long)secs;
 	rc = ioctl(encl->fd, SGX_IOC_ENCLAVE_CREATE, &ioc);
 	if (rc) {
-		fprintf(stderr, "SGX_IOC_ENCLAVE_CREATE failed: errno=%d\n",
-			errno);
+		perror("SGX_IOC_ENCLAVE_CREATE failed");
 		munmap((void *)secs->base, encl->encl_size);
 		return false;
 	}
@@ -116,31 +115,72 @@ static bool encl_ioc_add_pages(struct encl *encl, struct encl_segment *seg)
 
 	rc = ioctl(encl->fd, SGX_IOC_ENCLAVE_ADD_PAGES, &ioc);
 	if (rc < 0) {
-		fprintf(stderr, "SGX_IOC_ENCLAVE_ADD_PAGES failed: errno=%d.\n",
-			errno);
+		perror("SGX_IOC_ENCLAVE_ADD_PAGES failed");
 		return false;
 	}
 
 	return true;
 }
 
+
+
 bool encl_load(const char *path, struct encl *encl)
 {
+	const char device_path[] = "/dev/sgx_enclave";
 	Elf64_Phdr *phdr_tbl;
 	off_t src_offset;
 	Elf64_Ehdr *ehdr;
+	struct stat sb;
+	void *ptr;
 	int i, j;
 	int ret;
+	int fd = -1;
 
 	memset(encl, 0, sizeof(*encl));
 
-	ret = open("/dev/sgx_enclave", O_RDWR);
-	if (ret < 0) {
-		fprintf(stderr, "Unable to open /dev/sgx_enclave\n");
+	fd = open(device_path, O_RDWR);
+	if (fd < 0) {
+		perror("Unable to open /dev/sgx_enclave");
+		goto err;
+	}
+
+	ret = stat(device_path, &sb);
+	if (ret) {
+		perror("device file stat()");
+		goto err;
+	}
+
+	/*
+	 * This just checks if the /dev file has these permission
+	 * bits set.  It does not check that the current user is
+	 * the owner or in the owning group.
+	 */
+	if (!(sb.st_mode & (S_IXUSR | S_IXGRP | S_IXOTH))) {
+		fprintf(stderr, "no execute permissions on device file %s\n", device_path);
+		goto err;
+	}
+
+	ptr = mmap(NULL, PAGE_SIZE, PROT_READ, MAP_SHARED, fd, 0);
+	if (ptr == (void *)-1) {
+		perror("mmap for read");
+		goto err;
+	}
+	munmap(ptr, PAGE_SIZE);
+
+#define ERR_MSG \
+"mmap() succeeded for PROT_READ, but failed for PROT_EXEC.\n" \
+" Check that current user has execute permissions on %s and \n" \
+" that /dev does not have noexec set: mount | grep \"/dev .*noexec\"\n" \
+" If so, remount it executable: mount -o remount,exec /dev\n\n"
+
+	ptr = mmap(NULL, PAGE_SIZE, PROT_EXEC, MAP_SHARED, fd, 0);
+	if (ptr == (void *)-1) {
+		fprintf(stderr, ERR_MSG, device_path);
 		goto err;
 	}
+	munmap(ptr, PAGE_SIZE);
 
-	encl->fd = ret;
+	encl->fd = fd;
 
 	if (!encl_map_bin(path, encl))
 		goto err;
@@ -217,6 +257,8 @@ bool encl_load(const char *path, struct encl *encl)
 	return true;
 
 err:
+	if (fd != -1)
+		close(fd);
 	encl_delete(encl);
 	return false;
 }
@@ -229,7 +271,7 @@ static bool encl_map_area(struct encl *encl)
 	area = mmap(NULL, encl_size * 2, PROT_NONE,
 		    MAP_PRIVATE | MAP_ANONYMOUS, -1, 0);
 	if (area == MAP_FAILED) {
-		perror("mmap");
+		perror("reservation mmap()");
 		return false;
 	}
 
@@ -268,8 +310,7 @@ bool encl_build(struct encl *encl)
 	ioc.sigstruct = (uint64_t)&encl->sigstruct;
 	ret = ioctl(encl->fd, SGX_IOC_ENCLAVE_INIT, &ioc);
 	if (ret) {
-		fprintf(stderr, "SGX_IOC_ENCLAVE_INIT failed: errno=%d\n",
-			errno);
+		perror("SGX_IOC_ENCLAVE_INIT failed");
 		return false;
 	}
 

tools/testing/selftests/sgx/main.c

@@ -15,6 +15,7 @@
 #include <sys/stat.h>
 #include <sys/time.h>
 #include <sys/types.h>
+#include <sys/auxv.h>
 #include "defines.h"
 #include "main.h"
 #include "../kselftest.h"
@@ -28,24 +29,6 @@ struct vdso_symtab {
 	Elf64_Word *elf_hashtab;
 };
 
-static void *vdso_get_base_addr(char *envp[])
-{
-	Elf64_auxv_t *auxv;
-	int i;
-
-	for (i = 0; envp[i]; i++)
-		;
-
-	auxv = (Elf64_auxv_t *)&envp[i + 1];
-
-	for (i = 0; auxv[i].a_type != AT_NULL; i++) {
-		if (auxv[i].a_type == AT_SYSINFO_EHDR)
-			return (void *)auxv[i].a_un.a_val;
-	}
-
-	return NULL;
-}
-
 static Elf64_Dyn *vdso_get_dyntab(void *addr)
 {
 	Elf64_Ehdr *ehdr = addr;
@@ -162,7 +145,7 @@ static int user_handler(long rdi, long rsi, long rdx, long ursp, long r8, long r
 	return 0;
 }
 
-int main(int argc, char *argv[], char *envp[])
+int main(int argc, char *argv[])
 {
 	struct sgx_enclave_run run;
 	struct vdso_symtab symtab;
@@ -195,7 +178,7 @@ int main(int argc, char *argv[], char *envp[])
 		addr = mmap((void *)encl.encl_base + seg->offset, seg->size,
 			    seg->prot, MAP_SHARED | MAP_FIXED, encl.fd, 0);
 		if (addr == MAP_FAILED) {
-			fprintf(stderr, "mmap() failed, errno=%d.\n", errno);
+			perror("mmap() segment failed");
 			exit(KSFT_FAIL);
 		}
 	}
@@ -203,7 +186,8 @@ int main(int argc, char *argv[], char *envp[])
 	memset(&run, 0, sizeof(run));
 	run.tcs = encl.encl_base;
 
-	addr = vdso_get_base_addr(envp);
+	/* Get vDSO base address */
+	addr = (void *)getauxval(AT_SYSINFO_EHDR);
 	if (!addr)
 		goto err;