[PATCH v2 00/25] KVM SGX virtualization support

@@ -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 */

@@ -73,6 +73,8 @@ static const struct cpuid_dep cpuid_deps[] = {
 	{ 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      },
 	{}
 };
 

@@ -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 },

@@ -26,12 +26,14 @@
  * 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,
 };

@@ -381,6 +381,27 @@ const struct vm_operations_struct sgx_vm_ops = {
 	.access = sgx_vma_access,
 };
 
+static void sgx_encl_free_epc_page(struct sgx_epc_page *epc_page)
+{
+	int ret;
+
+	WARN_ON_ONCE(epc_page->flags & SGX_EPC_PAGE_RECLAIMER_TRACKED);
+
+	/*
+	 * Give a message to remind EPC page is leaked when EREMOVE fails,
+	 * and requires machine reboot to get leaked pages back. This can
+	 * be improved in future by adding stats of leaked pages, etc.
+	 */
+#define EREMOVE_ERROR_MESSAGE \
+	"EREMOVE returned %d (0x%x).  EPC page leaked.  Reboot required to retrieve leaked pages."
+	ret = __eremove(sgx_get_epc_virt_addr(epc_page));
+	if (WARN_ONCE(ret, EREMOVE_ERROR_MESSAGE, ret, ret))
+		return;
+#undef EREMOVE_ERROR_MESSAGE
+
+	sgx_free_epc_page(epc_page);
+}
+
 /**
  * sgx_encl_release - Destroy an enclave instance
  * @kref:	address of a kref inside &sgx_encl

@@ -404,7 +425,7 @@ 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 +436,7 @@ 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(entry->epc_page);
 		encl->secs.epc_page = NULL;
 	}
 

@@ -423,7 +444,7 @@ 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(entry->epc_page);
 		kfree(va_page);
 	}
 

@@ -598,18 +598,14 @@ 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;
-
-	WARN_ON_ONCE(page->flags & SGX_EPC_PAGE_RECLAIMER_TRACKED);
-
-	ret = __eremove(sgx_get_epc_virt_addr(page));
-	if (WARN_ONCE(ret, "EREMOVE returned %d (0x%x)", ret, ret))
-		return;
 
 	spin_lock(&section->lock);
 	list_add_tail(&page->list, &section->page_list);

@@ -1941,6 +1941,18 @@ config X86_SGX
 
 	  If unsure, say N.
 
+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 EFI
 	bool "EFI runtime service support"
 	depends on ACPI

@@ -3,3 +3,4 @@ obj-y += \
 	encl.o \
 	ioctl.o \
 	main.o
+obj-$(CONFIG_X86_SGX_KVM)	+= virt.o

@@ -83,4 +83,13 @@ 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
+
 #endif /* _X86_SGX_H */

@@ -0,0 +1,260 @@
+// 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;
+}
+
+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 (EPC page 0x%lx): unexpected error: %d\n",
+			  sgx_get_epc_phys_addr(epc_page), 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 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 (!boot_cpu_has(X86_FEATURE_VMX))
+		return -ENODEV;
+
+	INIT_LIST_HEAD(&zombie_secs_pages);
+	mutex_init(&zombie_secs_pages_lock);
+
+	return misc_register(&sgx_vepc_dev);
+}

@@ -72,6 +72,7 @@ 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	      },
 	{}
 };
 

@@ -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;
 }

@@ -116,7 +110,7 @@ void init_ia32_feat_ctl(struct cpuinfo_x86 *c)
 
 	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;
 	}
 

@@ -177,6 +171,6 @@ void init_ia32_feat_ctl(struct cpuinfo_x86 *c)
 	    !(msr & FEAT_CTL_SGX_LC_ENABLED) || !enable_sgx) {
 		if (enable_sgx)
 			pr_err_once("SGX disabled by BIOS\n");
-		clear_sgx_caps();
+		clear_cpu_cap(c, X86_FEATURE_SGX);
 	}
 }

@@ -104,8 +104,9 @@ 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)) {

@@ -114,13 +115,19 @@ void init_ia32_feat_ctl(struct cpuinfo_x86 *c)
 		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 Faunch 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;

@@ -136,15 +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);
 

@@ -167,10 +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");
+	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);
+		}
 	}
 }

@@ -712,7 +712,15 @@ static int __init sgx_init(void)
 		goto err_page_cache;
 	}
 
-	ret = sgx_drv_init();
+	/*
+	 * 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() & !!sgx_vepc_init();
 	if (ret)
 		goto err_kthread;
 

@@ -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. */

@@ -337,4 +342,9 @@ 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
+ * line!
+ */
+
+#endif /* _ASM_X86_SGX_H */

@@ -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"

@@ -8,7 +8,7 @@
 #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

@@ -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"
 

@@ -27,6 +27,21 @@
 /* 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,
+};
+
 /**
  * enum sgx_return_code - The return code type for ENCLS, ENCLU and ENCLV
  * %SGX_NOT_TRACKED:		Previous ETRACK's shootdown sequence has not

@@ -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
  *

@@ -40,6 +40,9 @@ enum sgx_encls_function {
 	EPA	= 0x0A,
 	EWB	= 0x0B,
 	ETRACK	= 0x0C,
+	EAUG	= 0x0D,
+	EMODPR	= 0x0E,
+	EMODT	= 0x0F,
 };
 
 /**

@@ -495,7 +495,7 @@ 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 +544,7 @@ 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);
 

@@ -696,6 +696,23 @@ 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]);
+}
+
 static int __init sgx_init(void)
 {
 	int ret;

@@ -92,4 +92,6 @@ static inline int __init sgx_vepc_init(void)
 }
 #endif
 
+void sgx_update_lepubkeyhash(u64 *lepubkeyhash);
+
 #endif /* _X86_SGX_H */

@@ -40,6 +40,19 @@
 	} 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

@@ -50,7 +63,7 @@
  */
 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;

@@ -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");
 

@@ -372,4 +372,7 @@ 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 */

@@ -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;
 }

@@ -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>

@@ -664,24 +665,11 @@ 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)

@@ -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"

@@ -713,6 +716,51 @@ void sgx_update_lepubkeyhash(u64 *lepubkeyhash)
 		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;