@@ -1,2 +1,4 @@
obj-y += \
+ driver.o \
+ encl.o \
main.o
new file mode 100644
@@ -0,0 +1,173 @@
+// SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause)
+// Copyright(c) 2016-18 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"
+
+u64 sgx_encl_size_max_32;
+u64 sgx_encl_size_max_64;
+u32 sgx_misc_reserved_mask;
+u64 sgx_attributes_reserved_mask;
+u64 sgx_xfrm_reserved_mask = ~0x3;
+u32 sgx_xsave_size_tbl[64];
+
+static int sgx_open(struct inode *inode, struct file *file)
+{
+ struct sgx_encl *encl;
+ int ret;
+
+ encl = kzalloc(sizeof(*encl), GFP_KERNEL);
+ if (!encl)
+ return -ENOMEM;
+
+ atomic_set(&encl->flags, 0);
+ kref_init(&encl->refcount);
+ xa_init(&encl->page_array);
+ mutex_init(&encl->lock);
+ INIT_LIST_HEAD(&encl->mm_list);
+ spin_lock_init(&encl->mm_lock);
+
+ ret = init_srcu_struct(&encl->srcu);
+ if (ret) {
+ kfree(encl);
+ return ret;
+ }
+
+ 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_mm *encl_mm;
+
+ for ( ; ; ) {
+ spin_lock(&encl->mm_lock);
+
+ if (list_empty(&encl->mm_list)) {
+ encl_mm = NULL;
+ } else {
+ encl_mm = list_first_entry(&encl->mm_list,
+ struct sgx_encl_mm, list);
+ list_del_rcu(&encl_mm->list);
+ }
+
+ spin_unlock(&encl->mm_lock);
+
+ /* The list is empty, ready to go. */
+ if (!encl_mm)
+ break;
+
+ synchronize_srcu(&encl->srcu);
+ mmu_notifier_unregister(&encl_mm->mmu_notifier, encl_mm->mm);
+ kfree(encl_mm);
+ }
+
+ mutex_lock(&encl->lock);
+ atomic_or(SGX_ENCL_DEAD, &encl->flags);
+ mutex_unlock(&encl->lock);
+
+ kref_put(&encl->refcount, sgx_encl_release);
+ 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;
+
+ ret = sgx_encl_mm_add(encl, vma->vm_mm);
+ 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 = "enclave",
+ .nodename = "sgx/enclave",
+ .fops = &sgx_encl_fops,
+};
+
+int __init sgx_drv_init(void)
+{
+ unsigned int eax, ebx, ecx, edx;
+ u64 attr_mask, xfrm_mask;
+ int ret;
+ int i;
+
+ if (!boot_cpu_has(X86_FEATURE_SGX_LC)) {
+ pr_info("The public key MSRs are not writable.\n");
+ return -ENODEV;
+ }
+
+ cpuid_count(SGX_CPUID, 0, &eax, &ebx, &ecx, &edx);
+ sgx_misc_reserved_mask = ~ebx | SGX_MISC_RESERVED_MASK;
+ sgx_encl_size_max_64 = 1ULL << ((edx >> 8) & 0xFF);
+ sgx_encl_size_max_32 = 1ULL << (edx & 0xFF);
+
+ cpuid_count(SGX_CPUID, 1, &eax, &ebx, &ecx, &edx);
+
+ attr_mask = (((u64)ebx) << 32) + (u64)eax;
+ sgx_attributes_reserved_mask = ~attr_mask | SGX_ATTR_RESERVED_MASK;
+
+ if (boot_cpu_has(X86_FEATURE_OSXSAVE)) {
+ xfrm_mask = (((u64)edx) << 32) + (u64)ecx;
+
+ for (i = 2; i < 64; i++) {
+ cpuid_count(0x0D, i, &eax, &ebx, &ecx, &edx);
+ if ((1UL << i) & xfrm_mask)
+ sgx_xsave_size_tbl[i] = eax + ebx;
+ }
+
+ sgx_xfrm_reserved_mask = ~xfrm_mask;
+ }
+
+ ret = misc_register(&sgx_dev_enclave);
+ if (ret) {
+ pr_err("Creating /dev/sgx/enclave failed with %d.\n", ret);
+ return ret;
+ }
+
+ return 0;
+}
new file mode 100644
@@ -0,0 +1,29 @@
+/* SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause) */
+#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"
+
+#define SGX_EINIT_SPIN_COUNT 20
+#define SGX_EINIT_SLEEP_COUNT 50
+#define SGX_EINIT_SLEEP_TIME 20
+
+extern u64 sgx_encl_size_max_32;
+extern u64 sgx_encl_size_max_64;
+extern u32 sgx_misc_reserved_mask;
+extern u64 sgx_attributes_reserved_mask;
+extern u64 sgx_xfrm_reserved_mask;
+extern u32 sgx_xsave_size_tbl[64];
+
+long sgx_ioctl(struct file *filep, unsigned int cmd, unsigned long arg);
+
+int sgx_drv_init(void);
+
+#endif /* __ARCH_X86_SGX_DRIVER_H__ */
new file mode 100644
@@ -0,0 +1,331 @@
+// SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause)
+// Copyright(c) 2016-18 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)
+{
+ struct sgx_encl_page *entry;
+ unsigned int flags;
+
+ /* If process was forked, VMA is still there but vm_private_data is set
+ * to NULL.
+ */
+ if (!encl)
+ return ERR_PTR(-EFAULT);
+
+ flags = atomic_read(&encl->flags);
+ if ((flags & SGX_ENCL_DEAD) || !(flags & SGX_ENCL_INITIALIZED))
+ return ERR_PTR(-EFAULT);
+
+ entry = xa_load(&encl->page_array, PFN_DOWN(addr));
+ if (!entry)
+ return ERR_PTR(-EFAULT);
+
+ /* Page is already resident in the EPC. */
+ if (entry->epc_page)
+ return entry;
+
+ return ERR_PTR(-EFAULT);
+}
+
+static void sgx_mmu_notifier_release(struct mmu_notifier *mn,
+ struct mm_struct *mm)
+{
+ struct sgx_encl_mm *encl_mm = container_of(mn, struct sgx_encl_mm, mmu_notifier);
+ struct sgx_encl_mm *tmp = NULL;
+
+ /*
+ * The enclave itself can remove encl_mm. Note, objects can't be moved
+ * off an RCU protected list, but deletion is ok.
+ */
+ spin_lock(&encl_mm->encl->mm_lock);
+ list_for_each_entry(tmp, &encl_mm->encl->mm_list, list) {
+ if (tmp == encl_mm) {
+ list_del_rcu(&encl_mm->list);
+ break;
+ }
+ }
+ spin_unlock(&encl_mm->encl->mm_lock);
+
+ if (tmp == encl_mm) {
+ synchronize_srcu(&encl_mm->encl->srcu);
+ mmu_notifier_put(mn);
+ }
+}
+
+static void sgx_mmu_notifier_free(struct mmu_notifier *mn)
+{
+ struct sgx_encl_mm *encl_mm = container_of(mn, struct sgx_encl_mm, mmu_notifier);
+
+ kfree(encl_mm);
+}
+
+static const struct mmu_notifier_ops sgx_mmu_notifier_ops = {
+ .release = sgx_mmu_notifier_release,
+ .free_notifier = sgx_mmu_notifier_free,
+};
+
+static struct sgx_encl_mm *sgx_encl_find_mm(struct sgx_encl *encl,
+ struct mm_struct *mm)
+{
+ struct sgx_encl_mm *encl_mm = NULL;
+ struct sgx_encl_mm *tmp;
+ int idx;
+
+ idx = srcu_read_lock(&encl->srcu);
+
+ list_for_each_entry_rcu(tmp, &encl->mm_list, list) {
+ if (tmp->mm == mm) {
+ encl_mm = tmp;
+ break;
+ }
+ }
+
+ srcu_read_unlock(&encl->srcu, idx);
+
+ return encl_mm;
+}
+
+int sgx_encl_mm_add(struct sgx_encl *encl, struct mm_struct *mm)
+{
+ struct sgx_encl_mm *encl_mm;
+ int ret;
+
+ /* mm_list can be accessed only by a single thread at a time. */
+ mmap_assert_write_locked(mm);
+
+ if (atomic_read(&encl->flags) & SGX_ENCL_DEAD)
+ return -EINVAL;
+
+ /*
+ * mm_structs are kept on mm_list until the mm or the enclave dies,
+ * i.e. once an mm is off the list, it's gone for good, therefore it's
+ * impossible to get a false positive on @mm due to a stale mm_list.
+ */
+ if (sgx_encl_find_mm(encl, mm))
+ return 0;
+
+ encl_mm = kzalloc(sizeof(*encl_mm), GFP_KERNEL);
+ if (!encl_mm)
+ return -ENOMEM;
+
+ encl_mm->encl = encl;
+ encl_mm->mm = mm;
+ encl_mm->mmu_notifier.ops = &sgx_mmu_notifier_ops;
+
+ ret = __mmu_notifier_register(&encl_mm->mmu_notifier, mm);
+ if (ret) {
+ kfree(encl_mm);
+ return ret;
+ }
+
+ spin_lock(&encl->mm_lock);
+ list_add_rcu(&encl_mm->list, &encl->mm_list);
+ spin_unlock(&encl->mm_lock);
+
+ return 0;
+}
+
+static void sgx_vma_open(struct vm_area_struct *vma)
+{
+ struct sgx_encl *encl = vma->vm_private_data;
+
+ if (!encl)
+ return;
+
+ if (sgx_encl_mm_add(encl, vma->vm_mm))
+ vma->vm_private_data = NULL;
+}
+
+static unsigned int sgx_vma_fault(struct vm_fault *vmf)
+{
+ unsigned long addr = (unsigned long)vmf->address;
+ struct vm_area_struct *vma = vmf->vma;
+ struct sgx_encl *encl = vma->vm_private_data;
+ struct sgx_encl_page *entry;
+ int ret = VM_FAULT_NOPAGE;
+ unsigned long pfn;
+
+ if (!encl)
+ return VM_FAULT_SIGBUS;
+
+ mutex_lock(&encl->lock);
+
+ entry = sgx_encl_load_page(encl, addr);
+ if (IS_ERR(entry)) {
+ if (unlikely(PTR_ERR(entry) != -EBUSY))
+ ret = VM_FAULT_SIGBUS;
+
+ goto out;
+ }
+
+ if (!follow_pfn(vma, addr, &pfn))
+ goto out;
+
+ ret = vmf_insert_pfn(vma, addr, PFN_DOWN(entry->epc_page->desc));
+ if (ret != VM_FAULT_NOPAGE) {
+ ret = VM_FAULT_SIGBUS;
+ goto out;
+ }
+
+out:
+ mutex_unlock(&encl->lock);
+ return ret;
+}
+
+/**
+ * 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_prot_bits: requested protections of the address range
+ *
+ * Iterate through the enclave pages contained within [@start, @end) to verify
+ * the permissions requested by @vm_prot_bits do not exceed that of any enclave
+ * page to be mapped.
+ *
+ * Return:
+ * 0 on success,
+ * -EACCES if VMA permissions exceed enclave page permissions
+ */
+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);
+ unsigned long idx_start = PFN_DOWN(start);
+ unsigned long idx_end = PFN_DOWN(end - 1);
+ struct sgx_encl_page *page;
+
+ XA_STATE(xas, &encl->page_array, idx_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;
+
+ xas_for_each(&xas, page, idx_end)
+ if (!page || (~page->vm_max_prot_bits & vm_prot_bits))
+ return -EACCES;
+
+ return 0;
+}
+
+static int sgx_vma_mprotect(struct vm_area_struct *vma,
+ struct vm_area_struct **pprev, unsigned long start,
+ unsigned long end, unsigned long newflags)
+{
+ int ret;
+
+ ret = sgx_encl_may_map(vma->vm_private_data, start, end, newflags);
+ if (ret)
+ return ret;
+
+ return mprotect_fixup(vma, pprev, start, end, newflags);
+}
+
+const struct vm_operations_struct sgx_vm_ops = {
+ .open = sgx_vma_open,
+ .fault = sgx_vma_fault,
+ .mprotect = sgx_vma_mprotect,
+};
+
+/**
+ * sgx_encl_find - find an enclave
+ * @mm: mm struct of the current process
+ * @addr: address in the ELRANGE
+ * @vma: the resulting VMA
+ *
+ * Find an enclave identified by the given address. Give back a VMA that is
+ * part of the enclave and located in that address. The VMA is given back if it
+ * is a proper enclave VMA even if an &sgx_encl instance does not exist yet
+ * (enclave creation has not been performed).
+ *
+ * Return:
+ * 0 on success,
+ * -EINVAL if an enclave was not found,
+ * -ENOENT if the enclave has not been created yet
+ */
+int sgx_encl_find(struct mm_struct *mm, unsigned long addr,
+ struct vm_area_struct **vma)
+{
+ struct vm_area_struct *result;
+ struct sgx_encl *encl;
+
+ result = find_vma(mm, addr);
+ if (!result || result->vm_ops != &sgx_vm_ops || addr < result->vm_start)
+ return -EINVAL;
+
+ encl = result->vm_private_data;
+ *vma = result;
+
+ return encl ? 0 : -ENOENT;
+}
+
+/**
+ * sgx_encl_destroy() - destroy enclave resources
+ * @encl: an enclave pointer
+ */
+void sgx_encl_destroy(struct sgx_encl *encl)
+{
+ struct sgx_encl_page *entry;
+ unsigned long index;
+
+ atomic_or(SGX_ENCL_DEAD, &encl->flags);
+
+ 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;
+ }
+}
+
+/**
+ * sgx_encl_release - Destroy an enclave instance
+ * @kref: address of a kref inside &sgx_encl
+ *
+ * Used together with kref_put(). Frees all the resources associated with the
+ * enclave and the instance itself.
+ */
+void sgx_encl_release(struct kref *ref)
+{
+ struct sgx_encl *encl = container_of(ref, struct sgx_encl, refcount);
+
+ sgx_encl_destroy(encl);
+
+ if (encl->backing)
+ fput(encl->backing);
+
+ cleanup_srcu_struct(&encl->srcu);
+
+ WARN_ON_ONCE(!list_empty(&encl->mm_list));
+
+ /* Detect EPC page leak's. */
+ WARN_ON_ONCE(encl->secs_child_cnt);
+ WARN_ON_ONCE(encl->secs.epc_page);
+
+ kfree(encl);
+}
new file mode 100644
@@ -0,0 +1,85 @@
+/* SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause) */
+/**
+ * Copyright(c) 2016-19 Intel Corporation.
+ */
+#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"
+
+/**
+ * enum sgx_encl_page_desc - defines bits for an enclave page's descriptor
+ * %SGX_ENCL_PAGE_ADDR_MASK: Holds the virtual address of the page.
+ *
+ * The page address for SECS is zero and is used by the subsystem to recognize
+ * the SECS page.
+ */
+enum sgx_encl_page_desc {
+ /* Bits 11:3 are available when the page is not swapped. */
+ SGX_ENCL_PAGE_ADDR_MASK = PAGE_MASK,
+};
+
+#define SGX_ENCL_PAGE_ADDR(page) \
+ ((page)->desc & SGX_ENCL_PAGE_ADDR_MASK)
+
+struct sgx_encl_page {
+ unsigned long desc;
+ unsigned long vm_max_prot_bits;
+ struct sgx_epc_page *epc_page;
+ struct sgx_encl *encl;
+};
+
+enum sgx_encl_flags {
+ SGX_ENCL_CREATED = BIT(0),
+ SGX_ENCL_INITIALIZED = BIT(1),
+ SGX_ENCL_DEBUG = BIT(2),
+ SGX_ENCL_DEAD = BIT(3),
+ SGX_ENCL_IOCTL = BIT(4),
+};
+
+struct sgx_encl_mm {
+ struct sgx_encl *encl;
+ struct mm_struct *mm;
+ struct list_head list;
+ struct mmu_notifier mmu_notifier;
+};
+
+struct sgx_encl {
+ atomic_t flags;
+ unsigned int page_cnt;
+ unsigned int secs_child_cnt;
+ struct mutex lock;
+ struct list_head mm_list;
+ spinlock_t mm_lock;
+ struct file *backing;
+ struct kref refcount;
+ struct srcu_struct srcu;
+ unsigned long base;
+ unsigned long size;
+ unsigned long ssaframesize;
+ struct xarray page_array;
+ struct sgx_encl_page secs;
+ cpumask_t cpumask;
+};
+
+extern const struct vm_operations_struct sgx_vm_ops;
+
+int sgx_encl_find(struct mm_struct *mm, unsigned long addr,
+ struct vm_area_struct **vma);
+void sgx_encl_destroy(struct sgx_encl *encl);
+void sgx_encl_release(struct kref *ref);
+int sgx_encl_mm_add(struct sgx_encl *encl, struct mm_struct *mm);
+int sgx_encl_may_map(struct sgx_encl *encl, unsigned long start,
+ unsigned long end, unsigned long vm_flags);
+
+#endif /* _X86_ENCL_H */
@@ -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];
@@ -260,6 +262,8 @@ static bool __init sgx_page_cache_init(void)
static void __init sgx_init(void)
{
+ int ret;
+
if (!boot_cpu_has(X86_FEATURE_SGX))
return;
@@ -269,8 +273,15 @@ 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(ksgxswapd_tsk);
+
err_page_cache:
sgx_page_cache_teardown();
}