x86/sgx/virt: implement SGX_IOC_VEPC_REMOVE ioctl

For bare-metal SGX on real hardware, the hardware provides guarantees
SGX state at reboot.  For instance, all pages start out uninitialized.
The vepc driver provides a similar guarantee today for freshly-opened
vepc instances, but guests such as Windows expect all pages to be in
uninitialized state on startup, including after every guest reboot.

Some userspace implementations of virtual SGX would rather avoid having
to close and reopen the /dev/sgx_vepc file descriptor and re-mmap the
virtual EPC.  For example, they could sandbox themselves after the guest
starts and forbid further calls to open(), in order to mitigate exploits
from untrusted guests.

Therefore, add a ioctl that does this with EREMOVE.  Userspace can
invoke the ioctl to bring its vEPC pages back to uninitialized state.
There is a possibility that some pages fail to be removed if they are
SECS pages, and the child and SECS pages could be in separate vEPC
regions.  Therefore, the ioctl returns the number of EREMOVE failures,
telling userspace to try the ioctl again after it's done with all
vEPC regions.  A more verbose description of the correct usage and
the possible error conditions is documented in sgx.rst.

Reviewed-by: Jarkko Sakkinen <jarkko@kernel.org>
Reviewed-by: Dave Hansen <dave.hansen@linux.intel.com>
Reviewed-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Link: https://lkml.kernel.org/r/20211021201155.1523989-3-pbonzini@redhat.com

1 files changed, 53 insertions, 0 deletions

diff --git a/arch/x86/kernel/cpu/sgx/virt.c b/arch/x86/kernel/cpu/sgx/virt.c
index 59cdf3f742ac..6a77a14eee38 100644
--- a/arch/x86/kernel/cpu/sgx/virt.c
+++ b/arch/x86/kernel/cpu/sgx/virt.c
@@ -150,6 +150,41 @@ static int sgx_vepc_free_page(struct sgx_epc_page *epc_page)
 	return 0;
 }
 
+static long sgx_vepc_remove_all(struct sgx_vepc *vepc)
+{
+	struct sgx_epc_page *entry;
+	unsigned long index;
+	long failures = 0;
+
+	xa_for_each(&vepc->page_array, index, entry) {
+		int ret = sgx_vepc_remove_page(entry);
+		if (ret) {
+			if (ret == SGX_CHILD_PRESENT) {
+				/* The page is a SECS, userspace will retry.  */
+				failures++;
+			} else {
+				/*
+				 * Report errors due to #GP or SGX_ENCLAVE_ACT; do not
+				 * WARN, as userspace can induce said failures by
+				 * calling the ioctl concurrently on multiple vEPCs or
+				 * while one or more CPUs is running the enclave.  Only
+				 * a #PF on EREMOVE indicates a kernel/hardware issue.
+				 */
+				WARN_ON_ONCE(encls_faulted(ret) &&
+					     ENCLS_TRAPNR(ret) != X86_TRAP_GP);
+				return -EBUSY;
+			}
+		}
+		cond_resched();
+	}
+
+	/*
+	 * Return the number of SECS pages that failed to be removed, so
+	 * userspace knows that it has to retry.
+	 */
+	return failures;
+}
+
 static int sgx_vepc_release(struct inode *inode, struct file *file)
 {
 	struct sgx_vepc *vepc = file->private_data;
@@ -235,9 +270,27 @@ static int sgx_vepc_open(struct inode *inode, struct file *file)
 	return 0;
 }
 
+static long sgx_vepc_ioctl(struct file *file,
+			   unsigned int cmd, unsigned long arg)
+{
+	struct sgx_vepc *vepc = file->private_data;
+
+	switch (cmd) {
+	case SGX_IOC_VEPC_REMOVE_ALL:
+		if (arg)
+			return -EINVAL;
+		return sgx_vepc_remove_all(vepc);
+
+	default:
+		return -ENOTTY;
+	}
+}
+
 static const struct file_operations sgx_vepc_fops = {
 	.owner		= THIS_MODULE,
 	.open		= sgx_vepc_open,
+	.unlocked_ioctl	= sgx_vepc_ioctl,
+	.compat_ioctl	= sgx_vepc_ioctl,
 	.release	= sgx_vepc_release,
 	.mmap		= sgx_vepc_mmap,
 };