x86/sgx: Support complete page removal

The SGX2 page removal flow was introduced in previous patch and is
as follows:
1) Change the type of the pages to be removed to SGX_PAGE_TYPE_TRIM
   using the ioctl() SGX_IOC_ENCLAVE_MODIFY_TYPES introduced in
   previous patch.
2) Approve the page removal by running ENCLU[EACCEPT] from within
   the enclave.
3) Initiate actual page removal using the ioctl()
   SGX_IOC_ENCLAVE_REMOVE_PAGES introduced here.

Support the final step of the SGX2 page removal flow with ioctl()
SGX_IOC_ENCLAVE_REMOVE_PAGES. With this ioctl() the user specifies
a page range that should be removed. All pages in the provided
range should have the SGX_PAGE_TYPE_TRIM page type and the request
will fail with EPERM (Operation not permitted) if a page that does
not have the correct type is encountered. Page removal can fail
on any page within the provided range. Support partial success by
returning the number of pages that were successfully removed.

Since actual page removal will succeed even if ENCLU[EACCEPT] was not
run from within the enclave the ENCLU[EMODPR] instruction with RWX
permissions is used as a no-op mechanism to ensure ENCLU[EACCEPT] was
successfully run from within the enclave before the enclave page is
removed.

If the user omits running SGX_IOC_ENCLAVE_REMOVE_PAGES the pages will
still be removed when the enclave is unloaded.

Signed-off-by: Reinette Chatre <reinette.chatre@intel.com>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Reviewed-by: Jarkko Sakkinen <jarkko@kernel.org>
Tested-by: Haitao Huang <haitao.huang@intel.com>
Tested-by: Vijay Dhanraj <vijay.dhanraj@intel.com>
Tested-by: Jarkko Sakkinen <jarkko@kernel.org>
Link: https://lkml.kernel.org/r/b75ee93e96774e38bb44a24b8e9bbfb67b08b51b.1652137848.git.reinette.chatre@intel.com

1 files changed, 145 insertions, 0 deletions

diff --git a/arch/x86/kernel/cpu/sgx/ioctl.c b/arch/x86/kernel/cpu/sgx/ioctl.c
index 9ccafbfc4811..1a2595f261d3 100644
--- a/arch/x86/kernel/cpu/sgx/ioctl.c
+++ b/arch/x86/kernel/cpu/sgx/ioctl.c
@@ -1071,6 +1071,148 @@ static long sgx_ioc_enclave_modify_types(struct sgx_encl *encl,
 	return ret;
 }
 
+/**
+ * sgx_encl_remove_pages() - Remove trimmed pages from SGX enclave
+ * @encl:	Enclave to which the pages belong
+ * @params:	Checked parameters from user on which pages need to be removed
+ *
+ * Return:
+ * - 0:		Success.
+ * - -errno:	Otherwise.
+ */
+static long sgx_encl_remove_pages(struct sgx_encl *encl,
+				  struct sgx_enclave_remove_pages *params)
+{
+	struct sgx_encl_page *entry;
+	struct sgx_secinfo secinfo;
+	unsigned long addr;
+	unsigned long c;
+	void *epc_virt;
+	int ret;
+
+	memset(&secinfo, 0, sizeof(secinfo));
+	secinfo.flags = SGX_SECINFO_R | SGX_SECINFO_W | SGX_SECINFO_X;
+
+	for (c = 0 ; c < params->length; c += PAGE_SIZE) {
+		addr = encl->base + params->offset + c;
+
+		mutex_lock(&encl->lock);
+
+		entry = sgx_encl_load_page(encl, addr);
+		if (IS_ERR(entry)) {
+			ret = PTR_ERR(entry) == -EBUSY ? -EAGAIN : -EFAULT;
+			goto out_unlock;
+		}
+
+		if (entry->type != SGX_PAGE_TYPE_TRIM) {
+			ret = -EPERM;
+			goto out_unlock;
+		}
+
+		/*
+		 * ENCLS[EMODPR] is a no-op instruction used to inform if
+		 * ENCLU[EACCEPT] was run from within the enclave. If
+		 * ENCLS[EMODPR] is run with RWX on a trimmed page that is
+		 * not yet accepted then it will return
+		 * %SGX_PAGE_NOT_MODIFIABLE, after the trimmed page is
+		 * accepted the instruction will encounter a page fault.
+		 */
+		epc_virt = sgx_get_epc_virt_addr(entry->epc_page);
+		ret = __emodpr(&secinfo, epc_virt);
+		if (!encls_faulted(ret) || ENCLS_TRAPNR(ret) != X86_TRAP_PF) {
+			ret = -EPERM;
+			goto out_unlock;
+		}
+
+		if (sgx_unmark_page_reclaimable(entry->epc_page)) {
+			ret = -EBUSY;
+			goto out_unlock;
+		}
+
+		/*
+		 * Do not keep encl->lock because of dependency on
+		 * mmap_lock acquired in sgx_zap_enclave_ptes().
+		 */
+		mutex_unlock(&encl->lock);
+
+		sgx_zap_enclave_ptes(encl, addr);
+
+		mutex_lock(&encl->lock);
+
+		sgx_encl_free_epc_page(entry->epc_page);
+		encl->secs_child_cnt--;
+		entry->epc_page = NULL;
+		xa_erase(&encl->page_array, PFN_DOWN(entry->desc));
+		sgx_encl_shrink(encl, NULL);
+		kfree(entry);
+
+		mutex_unlock(&encl->lock);
+	}
+
+	ret = 0;
+	goto out;
+
+out_unlock:
+	mutex_unlock(&encl->lock);
+out:
+	params->count = c;
+
+	return ret;
+}
+
+/**
+ * sgx_ioc_enclave_remove_pages() - handler for %SGX_IOC_ENCLAVE_REMOVE_PAGES
+ * @encl:	an enclave pointer
+ * @arg:	userspace pointer to &struct sgx_enclave_remove_pages instance
+ *
+ * Final step of the flow removing pages from an initialized enclave. The
+ * complete flow is:
+ *
+ * 1) User changes the type of the pages to be removed to %SGX_PAGE_TYPE_TRIM
+ *    using the %SGX_IOC_ENCLAVE_MODIFY_TYPES ioctl().
+ * 2) User approves the page removal by running ENCLU[EACCEPT] from within
+ *    the enclave.
+ * 3) User initiates actual page removal using the
+ *    %SGX_IOC_ENCLAVE_REMOVE_PAGES ioctl() that is handled here.
+ *
+ * First remove any page table entries pointing to the page and then proceed
+ * with the actual removal of the enclave page and data in support of it.
+ *
+ * VA pages are not affected by this removal. It is thus possible that the
+ * enclave may end up with more VA pages than needed to support all its
+ * pages.
+ *
+ * Return:
+ * - 0:		Success
+ * - -errno:	Otherwise
+ */
+static long sgx_ioc_enclave_remove_pages(struct sgx_encl *encl,
+					 void __user *arg)
+{
+	struct sgx_enclave_remove_pages params;
+	long ret;
+
+	ret = sgx_ioc_sgx2_ready(encl);
+	if (ret)
+		return ret;
+
+	if (copy_from_user(&params, arg, sizeof(params)))
+		return -EFAULT;
+
+	if (sgx_validate_offset_length(encl, params.offset, params.length))
+		return -EINVAL;
+
+	if (params.count)
+		return -EINVAL;
+
+	ret = sgx_encl_remove_pages(encl, &params);
+
+	if (copy_to_user(arg, &params, sizeof(params)))
+		return -EFAULT;
+
+	return ret;
+}
+
 long sgx_ioctl(struct file *filep, unsigned int cmd, unsigned long arg)
 {
 	struct sgx_encl *encl = filep->private_data;
@@ -1099,6 +1241,9 @@ long sgx_ioctl(struct file *filep, unsigned int cmd, unsigned long arg)
 	case SGX_IOC_ENCLAVE_MODIFY_TYPES:
 		ret = sgx_ioc_enclave_modify_types(encl, (void __user *)arg);
 		break;
+	case SGX_IOC_ENCLAVE_REMOVE_PAGES:
+		ret = sgx_ioc_enclave_remove_pages(encl, (void __user *)arg);
+		break;
 	default:
 		ret = -ENOIOCTLCMD;
 		break;