summaryrefslogtreecommitdiffstats
path: root/arch
diff options
context:
space:
mode:
Diffstat (limited to 'arch')
-rw-r--r--arch/x86/kernel/cpu/sgx/Makefile1
-rw-r--r--arch/x86/kernel/cpu/sgx/sgx.h9
-rw-r--r--arch/x86/kernel/cpu/sgx/virt.c259
-rw-r--r--arch/x86/kvm/Kconfig12
4 files changed, 281 insertions, 0 deletions
diff --git a/arch/x86/kernel/cpu/sgx/Makefile b/arch/x86/kernel/cpu/sgx/Makefile
index 91d3dc784a29..9c1656779b2a 100644
--- a/arch/x86/kernel/cpu/sgx/Makefile
+++ b/arch/x86/kernel/cpu/sgx/Makefile
@@ -3,3 +3,4 @@ obj-y += \
encl.o \
ioctl.o \
main.o
+obj-$(CONFIG_X86_SGX_KVM) += virt.o
diff --git a/arch/x86/kernel/cpu/sgx/sgx.h b/arch/x86/kernel/cpu/sgx/sgx.h
index 4aa40c627819..4854f3980edd 100644
--- a/arch/x86/kernel/cpu/sgx/sgx.h
+++ b/arch/x86/kernel/cpu/sgx/sgx.h
@@ -84,4 +84,13 @@ 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 */
diff --git a/arch/x86/kernel/cpu/sgx/virt.c b/arch/x86/kernel/cpu/sgx/virt.c
new file mode 100644
index 000000000000..259cc46ad78c
--- /dev/null
+++ b/arch/x86/kernel/cpu/sgx/virt.c
@@ -0,0 +1,259 @@
+// 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_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);
+}
diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig
index a788d5120d4d..f6b93a35ce14 100644
--- a/arch/x86/kvm/Kconfig
+++ b/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
generated by cgit v1.2.3 (git 2.25.1) at 2024-11-05 13:22:12 +0000