x86/sgx: Add an SGX misc driver interface

Intel(R) SGX is a new hardware functionality that can be used by
applications to set aside private regions of code and data called
enclaves. New hardware protects enclave code and data from outside
access and modification.

Add a driver that presents a device file and ioctl API to build and
manage enclaves.

 [ bp: Small touchups, remove unused encl variable in sgx_encl_find() as
   Reported-by: kernel test robot <lkp@intel.com> ]
Signed-off-by: Jarkko Sakkinen <jarkko@kernel.org>
Co-developed-by: Sean Christopherson <sean.j.christopherson@intel.com>
Signed-off-by: Sean Christopherson <sean.j.christopherson@intel.com>
Signed-off-by: Borislav Petkov <bp@suse.de>
Tested-by: Jethro Beekman <jethro@fortanix.com>
Link: https://lkml.kernel.org/r/20201112220135.165028-12-jarkko@kernel.org

arch/x86/kernel/cpu/sgx/Makefile

 obj-y += \
+	driver.o \
+	encl.o \
 	main.o

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

+// SPDX-License-Identifier: GPL-2.0
+/*  Copyright(c) 2016-20 Intel Corporation. */
+
+#include <linux/acpi.h>
+#include <linux/miscdevice.h>
+#include <linux/mman.h>
+#include <linux/security.h>
+#include <linux/suspend.h>
+#include <asm/traps.h>
+#include "driver.h"
+#include "encl.h"
+
+static int sgx_open(struct inode *inode, struct file *file)
+{
+	struct sgx_encl *encl;
+
+	encl = kzalloc(sizeof(*encl), GFP_KERNEL);
+	if (!encl)
+		return -ENOMEM;
+
+	xa_init(&encl->page_array);
+	mutex_init(&encl->lock);
+
+	file->private_data = encl;
+
+	return 0;
+}
+
+static int sgx_release(struct inode *inode, struct file *file)
+{
+	struct sgx_encl *encl = file->private_data;
+	struct sgx_encl_page *entry;
+	unsigned long index;
+
+	xa_for_each(&encl->page_array, index, entry) {
+		if (entry->epc_page) {
+			sgx_free_epc_page(entry->epc_page);
+			encl->secs_child_cnt--;
+			entry->epc_page = NULL;
+		}
+
+		kfree(entry);
+	}
+
+	xa_destroy(&encl->page_array);
+
+	if (!encl->secs_child_cnt && encl->secs.epc_page) {
+		sgx_free_epc_page(encl->secs.epc_page);
+		encl->secs.epc_page = NULL;
+	}
+
+	/* Detect EPC page leaks. */
+	WARN_ON_ONCE(encl->secs_child_cnt);
+	WARN_ON_ONCE(encl->secs.epc_page);
+
+	kfree(encl);
+	return 0;
+}
+
+static int sgx_mmap(struct file *file, struct vm_area_struct *vma)
+{
+	struct sgx_encl *encl = file->private_data;
+	int ret;
+
+	ret = sgx_encl_may_map(encl, vma->vm_start, vma->vm_end, vma->vm_flags);
+	if (ret)
+		return ret;
+
+	vma->vm_ops = &sgx_vm_ops;
+	vma->vm_flags |= VM_PFNMAP | VM_DONTEXPAND | VM_DONTDUMP | VM_IO;
+	vma->vm_private_data = encl;
+
+	return 0;
+}
+
+static unsigned long sgx_get_unmapped_area(struct file *file,
+					   unsigned long addr,
+					   unsigned long len,
+					   unsigned long pgoff,
+					   unsigned long flags)
+{
+	if ((flags & MAP_TYPE) == MAP_PRIVATE)
+		return -EINVAL;
+
+	if (flags & MAP_FIXED)
+		return addr;
+
+	return current->mm->get_unmapped_area(file, addr, len, pgoff, flags);
+}
+
+static const struct file_operations sgx_encl_fops = {
+	.owner			= THIS_MODULE,
+	.open			= sgx_open,
+	.release		= sgx_release,
+	.mmap			= sgx_mmap,
+	.get_unmapped_area	= sgx_get_unmapped_area,
+};
+
+static struct miscdevice sgx_dev_enclave = {
+	.minor = MISC_DYNAMIC_MINOR,
+	.name = "sgx_enclave",
+	.nodename = "sgx_enclave",
+	.fops = &sgx_encl_fops,
+};
+
+int __init sgx_drv_init(void)
+{
+	if (!cpu_feature_enabled(X86_FEATURE_SGX_LC))
+		return -ENODEV;
+
+	return misc_register(&sgx_dev_enclave);
+}

arch/x86/kernel/cpu/sgx/driver.h

+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __ARCH_SGX_DRIVER_H__
+#define __ARCH_SGX_DRIVER_H__
+
+#include <crypto/hash.h>
+#include <linux/kref.h>
+#include <linux/mmu_notifier.h>
+#include <linux/radix-tree.h>
+#include <linux/rwsem.h>
+#include <linux/sched.h>
+#include <linux/workqueue.h>
+#include "sgx.h"
+
+int sgx_drv_init(void);
+
+#endif /* __ARCH_X86_SGX_DRIVER_H__ */

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

+// SPDX-License-Identifier: GPL-2.0
+/*  Copyright(c) 2016-20 Intel Corporation. */
+
+#include <linux/lockdep.h>
+#include <linux/mm.h>
+#include <linux/mman.h>
+#include <linux/shmem_fs.h>
+#include <linux/suspend.h>
+#include <linux/sched/mm.h>
+#include "arch.h"
+#include "encl.h"
+#include "encls.h"
+#include "sgx.h"
+
+static struct sgx_encl_page *sgx_encl_load_page(struct sgx_encl *encl,
+						unsigned long addr,
+						unsigned long vm_flags)
+{
+	unsigned long vm_prot_bits = vm_flags & (VM_READ | VM_WRITE | VM_EXEC);
+	struct sgx_encl_page *entry;
+
+	entry = xa_load(&encl->page_array, PFN_DOWN(addr));
+	if (!entry)
+		return ERR_PTR(-EFAULT);
+
+	/*
+	 * Verify that the faulted page has equal or higher build time
+	 * permissions than the VMA permissions (i.e. the subset of {VM_READ,
+	 * VM_WRITE, VM_EXECUTE} in vma->vm_flags).
+	 */
+	if ((entry->vm_max_prot_bits & vm_prot_bits) != vm_prot_bits)
+		return ERR_PTR(-EFAULT);
+
+	/* No page found. */
+	if (!entry->epc_page)
+		return ERR_PTR(-EFAULT);
+
+	/* Entry successfully located. */
+	return entry;
+}
+
+static vm_fault_t sgx_vma_fault(struct vm_fault *vmf)
+{
+	unsigned long addr = (unsigned long)vmf->address;
+	struct vm_area_struct *vma = vmf->vma;
+	struct sgx_encl_page *entry;
+	unsigned long phys_addr;
+	struct sgx_encl *encl;
+	vm_fault_t ret;
+
+	encl = vma->vm_private_data;
+
+	mutex_lock(&encl->lock);
+
+	entry = sgx_encl_load_page(encl, addr, vma->vm_flags);
+	if (IS_ERR(entry)) {
+		mutex_unlock(&encl->lock);
+
+		return VM_FAULT_SIGBUS;
+	}
+
+	phys_addr = sgx_get_epc_phys_addr(entry->epc_page);
+
+	ret = vmf_insert_pfn(vma, addr, PFN_DOWN(phys_addr));
+	if (ret != VM_FAULT_NOPAGE) {
+		mutex_unlock(&encl->lock);
+
+		return VM_FAULT_SIGBUS;
+	}
+
+	mutex_unlock(&encl->lock);
+
+	return VM_FAULT_NOPAGE;
+}
+
+/**
+ * sgx_encl_may_map() - Check if a requested VMA mapping is allowed
+ * @encl:		an enclave pointer
+ * @start:		lower bound of the address range, inclusive
+ * @end:		upper bound of the address range, exclusive
+ * @vm_flags:		VMA flags
+ *
+ * Iterate through the enclave pages contained within [@start, @end) to verify
+ * that the permissions requested by a subset of {VM_READ, VM_WRITE, VM_EXEC}
+ * do not contain any permissions that are not contained in the build time
+ * permissions of any of the enclave pages within the given address range.
+ *
+ * An enclave creator must declare the strongest permissions that will be
+ * needed for each enclave page. This ensures that mappings have the identical
+ * or weaker permissions than the earlier declared permissions.
+ *
+ * Return: 0 on success, -EACCES otherwise
+ */
+int sgx_encl_may_map(struct sgx_encl *encl, unsigned long start,
+		     unsigned long end, unsigned long vm_flags)
+{
+	unsigned long vm_prot_bits = vm_flags & (VM_READ | VM_WRITE | VM_EXEC);
+	struct sgx_encl_page *page;
+	unsigned long count = 0;
+	int ret = 0;
+
+	XA_STATE(xas, &encl->page_array, PFN_DOWN(start));
+
+	/*
+	 * Disallow READ_IMPLIES_EXEC tasks as their VMA permissions might
+	 * conflict with the enclave page permissions.
+	 */
+	if (current->personality & READ_IMPLIES_EXEC)
+		return -EACCES;
+
+	mutex_lock(&encl->lock);
+	xas_lock(&xas);
+	xas_for_each(&xas, page, PFN_DOWN(end - 1)) {
+		if (~page->vm_max_prot_bits & vm_prot_bits) {
+			ret = -EACCES;
+			break;
+		}
+
+		/* Reschedule on every XA_CHECK_SCHED iteration. */
+		if (!(++count % XA_CHECK_SCHED)) {
+			xas_pause(&xas);
+			xas_unlock(&xas);
+			mutex_unlock(&encl->lock);
+
+			cond_resched();
+
+			mutex_lock(&encl->lock);
+			xas_lock(&xas);
+		}
+	}
+	xas_unlock(&xas);
+	mutex_unlock(&encl->lock);
+
+	return ret;
+}
+
+static int sgx_vma_mprotect(struct vm_area_struct *vma, unsigned long start,
+			    unsigned long end, unsigned long newflags)
+{
+	return sgx_encl_may_map(vma->vm_private_data, start, end, newflags);
+}
+
+const struct vm_operations_struct sgx_vm_ops = {
+	.fault = sgx_vma_fault,
+	.mprotect = sgx_vma_mprotect,
+};

arch/x86/kernel/cpu/sgx/encl.h

+/* SPDX-License-Identifier: GPL-2.0 */
+/**
+ * Copyright(c) 2016-20 Intel Corporation.
+ *
+ * Contains the software defined data structures for enclaves.
+ */
+#ifndef _X86_ENCL_H
+#define _X86_ENCL_H
+
+#include <linux/cpumask.h>
+#include <linux/kref.h>
+#include <linux/list.h>
+#include <linux/mm_types.h>
+#include <linux/mmu_notifier.h>
+#include <linux/mutex.h>
+#include <linux/notifier.h>
+#include <linux/srcu.h>
+#include <linux/workqueue.h>
+#include <linux/xarray.h>
+#include "sgx.h"
+
+struct sgx_encl_page {
+	unsigned long desc;
+	unsigned long vm_max_prot_bits;
+	struct sgx_epc_page *epc_page;
+	struct sgx_encl *encl;
+};
+
+struct sgx_encl {
+	unsigned long base;
+	unsigned long size;
+	unsigned int page_cnt;
+	unsigned int secs_child_cnt;
+	struct mutex lock;
+	struct xarray page_array;
+	struct sgx_encl_page secs;
+};
+
+extern const struct vm_operations_struct sgx_vm_ops;
+
+static inline int sgx_encl_find(struct mm_struct *mm, unsigned long addr,
+				struct vm_area_struct **vma)
+{
+	struct vm_area_struct *result;
+
+	result = find_vma(mm, addr);
+	if (!result || result->vm_ops != &sgx_vm_ops || addr < result->vm_start)
+		return -EINVAL;
+
+	*vma = result;
+
+	return 0;
+}
+
+int sgx_encl_may_map(struct sgx_encl *encl, unsigned long start,
+		     unsigned long end, unsigned long vm_flags);
+
+#endif /* _X86_ENCL_H */

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

@@ -9,6 +9,8 @@
 #include <linux/sched/mm.h>
 #include <linux/sched/signal.h>
 #include <linux/slab.h>
+#include "driver.h"
+#include "encl.h"
 #include "encls.h"
 
 struct sgx_epc_section sgx_epc_sections[SGX_MAX_EPC_SECTIONS];
@@ -232,9 +234,10 @@ static bool __init sgx_page_cache_init(void)
 
 static void __init sgx_init(void)
 {
+	int ret;
 	int i;
 
-	if (!boot_cpu_has(X86_FEATURE_SGX))
+	if (!cpu_feature_enabled(X86_FEATURE_SGX))
 		return;
 
 	if (!sgx_page_cache_init())
@@ -243,8 +246,15 @@ static void __init sgx_init(void)
 	if (!sgx_page_reclaimer_init())
 		goto err_page_cache;
 
+	ret = sgx_drv_init();
+	if (ret)
+		goto err_kthread;
+
 	return;
 
+err_kthread:
+	kthread_stop(ksgxd_tsk);
+
 err_page_cache:
 	for (i = 0; i < sgx_nr_epc_sections; i++) {
 		vfree(sgx_epc_sections[i].pages);