Support SGX2 V5: Seg-fault with EACCEPT for large number of EPC pages

* Support SGX2 V5: Seg-fault with EACCEPT for large number of EPC pages
@ 2022-07-29 16:01 Dhanraj, Vijay
  2022-07-29 16:37 ` Dave Hansen
                   ` (2 more replies)
  0 siblings, 3 replies; 10+ messages in thread
From: Dhanraj, Vijay @ 2022-07-29 16:01 UTC (permalink / raw)
  To: Chatre, Reinette, dave.hansen, jarkko, linux-sgx; +Cc: Huang, Haitao

Hi All,

I recently tested the V5 version of the patch with Gramine and ran into a seg-fault during EPC allocation that is `EAUG`ing via `EACCEPT`. Allocation worked fine for smaller requests and even up to 2GBs. But when I tried with 4GB allocation I got a seg-fault.
Huang, Haitao and I created a simple patch to repro this issue using the SGX selftests and we do see the issue when using V5 (5.18.0-rc5) but cannot repro the issue in V4 (5.18.0-rc2). Not sure if this is a driver issue or kernel, can you please check?

Results with V5 using modified `augment_via_eaccept` test:
#  RUN           enclave.augment_via_eaccept ...
# main.c:1135:augment_via_eaccept:test enclave: total_size = 8192, seg->size = 8192
# main.c:1135:augment_via_eaccept:test enclave: total_size = 12288, seg->size = 4096
# main.c:1135:augment_via_eaccept:test enclave: total_size = 36864, seg->size = 24576
# main.c:1135:augment_via_eaccept:test enclave: total_size = 40960, seg->size = 4096
# main.c:1153:augment_via_eaccept:mmaping pages at end of enclave...
# main.c:1167:augment_via_eaccept:Entering enclave to run EACCEPT for each page of 8589934592 bytes may take a while ...
# main.c:1184:augment_via_eaccept:Expected self->run.exception_vector (14) == 0 (0)
# main.c:1185:augment_via_eaccept:Expected self->run.exception_error_code (4) == 0 (0)
# main.c:1186:augment_via_eaccept:Expected self->run.exception_addr (140106113478656) == 0 (0)
# main.c:1188:augment_via_eaccept:Expected self->run.function (3) == EEXIT (4)
# augment_via_eaccept: Test terminated by assertion

Results with V4 using modified `augment_via_eaccept` test:
#  RUN           enclave.augment_via_eaccept ...
# main.c:1135:augment_via_eaccept:test enclave: total_size = 8192, seg->size = 8192
# main.c:1135:augment_via_eaccept:test enclave: total_size = 12288, seg->size = 4096
# main.c:1135:augment_via_eaccept:test enclave: total_size = 36864, seg->size = 24576
# main.c:1135:augment_via_eaccept:test enclave: total_size = 40960, seg->size = 4096
# main.c:1153:augment_via_eaccept:mmaping pages at end of enclave...
# main.c:1167:augment_via_eaccept:Entering enclave to run EACCEPT for each page of 8589934592 bytes may take a while ...
#            OK  enclave.augment_via_eaccept


Test Patch:

diff --git a/tools/testing/selftests/sgx/load.c b/tools/testing/selftests/sgx/load.c
index 94bdeac1cf04..7de1b15c90b1 100644
--- a/tools/testing/selftests/sgx/load.c
+++ b/tools/testing/selftests/sgx/load.c
@@ -171,7 +171,8 @@ uint64_t encl_get_entry(struct encl *encl, const char *symbol)
 	return 0;
 }
 
-bool encl_load(const char *path, struct encl *encl, unsigned long heap_size)
+bool encl_load(const char *path, struct encl *encl, unsigned long heap_size,
+			   unsigned long edmm_size)
 {
 	const char device_path[] = "/dev/sgx_enclave";
 	struct encl_segment *seg;
@@ -300,7 +301,7 @@ bool encl_load(const char *path, struct encl *encl, unsigned long heap_size)
 
 	encl->src_size = encl->segment_tbl[j].offset + encl->segment_tbl[j].size;
 
-	for (encl->encl_size = 4096; encl->encl_size < encl->src_size; )
+	for (encl->encl_size = 4096; encl->encl_size < encl->src_size + edmm_size;)
 		encl->encl_size <<= 1;
 
 	return true;
diff --git a/tools/testing/selftests/sgx/main.c b/tools/testing/selftests/sgx/main.c
index 9820b3809c69..8d7ce9389c8f 100644
--- a/tools/testing/selftests/sgx/main.c
+++ b/tools/testing/selftests/sgx/main.c
@@ -25,6 +25,8 @@ static const uint64_t MAGIC = 0x1122334455667788ULL;
 static const uint64_t MAGIC2 = 0x8877665544332211ULL;
 vdso_sgx_enter_enclave_t vdso_sgx_enter_enclave;
 
+static const unsigned long edmm_size = 8589934592; //8G
+
 /*
  * Security Information (SECINFO) data structure needed by a few SGX
  * instructions (eg. ENCLU[EACCEPT] and ENCLU[EMODPE]) holds meta-data
@@ -183,7 +185,7 @@ static bool setup_test_encl(unsigned long heap_size, struct encl *encl,
 	unsigned int i;
 	void *addr;
 
-	if (!encl_load("test_encl.elf", encl, heap_size)) {
+	if (!encl_load("test_encl.elf", encl, heap_size, edmm_size)) {
 		encl_delete(encl);
 		TH_LOG("Failed to load the test enclave.");
 		return false;
@@ -1104,14 +1106,19 @@ TEST_F(enclave, augment)
  * Test for the addition of pages to an initialized enclave via a
  * pre-emptive run of EACCEPT on page to be added.
  */
-TEST_F(enclave, augment_via_eaccept)
+/*
+ * Test for the addition of pages to an initialized enclave via a
+ * pre-emptive run of EACCEPT on page to be added.
+ */
+/*TEST_F(enclave, augment_via_eaccept)*/
+TEST_F_TIMEOUT(enclave, augment_via_eaccept, 900)
 {
 	struct encl_op_get_from_addr get_addr_op;
 	struct encl_op_put_to_addr put_addr_op;
 	struct encl_op_eaccept eaccept_op;
 	size_t total_size = 0;
 	void *addr;
-	int i;
+	unsigned long i;
 
 	if (!sgx2_supported())
 		SKIP(return, "SGX2 not supported");
@@ -1125,6 +1132,7 @@ TEST_F(enclave, augment_via_eaccept)
 		struct encl_segment *seg = &self->encl.segment_tbl[i];
 
 		total_size += seg->size;
+		TH_LOG("test enclave: total_size = %ld, seg->size = %ld", total_size, seg->size);
 	}
 
 	/*
@@ -1132,7 +1140,7 @@ TEST_F(enclave, augment_via_eaccept)
 	 * test enclave since enclave size must be a power of 2 in bytes while
 	 * test_encl does not consume it all.
 	 */
-	EXPECT_LT(total_size + PAGE_SIZE, self->encl.encl_size);
+	EXPECT_LT(total_size + edmm_size, self->encl.encl_size);
 
 	/*
 	 * mmap() a page at end of existing enclave to be used for dynamic
@@ -1142,10 +1150,10 @@ TEST_F(enclave, augment_via_eaccept)
 	 * falls into the enclave's address range but not backed
 	 * by existing enclave pages.
 	 */
-
-	addr = mmap((void *)self->encl.encl_base + total_size, PAGE_SIZE,
-		    PROT_READ | PROT_WRITE | PROT_EXEC, MAP_SHARED | MAP_FIXED,
-		    self->encl.fd, 0);
+	TH_LOG("mmaping pages at end of enclave...");
+	addr = mmap((void *)self->encl.encl_base + total_size, edmm_size,
+			PROT_READ | PROT_WRITE | PROT_EXEC, MAP_SHARED | MAP_FIXED,
+			self->encl.fd, 0);
 	EXPECT_NE(addr, MAP_FAILED);
 
 	self->run.exception_vector = 0;
@@ -1156,25 +1164,29 @@ TEST_F(enclave, augment_via_eaccept)
 	 * Run EACCEPT on new page to trigger the #PF->EAUG->EACCEPT(again
 	 * without a #PF). All should be transparent to userspace.
 	 */
-	eaccept_op.epc_addr = self->encl.encl_base + total_size;
+	TH_LOG("Entering enclave to run EACCEPT for each page of %zd bytes may take a while ...",
+			edmm_size);
 	eaccept_op.flags = SGX_SECINFO_R | SGX_SECINFO_W | SGX_SECINFO_REG | SGX_SECINFO_PENDING;
 	eaccept_op.ret = 0;
 	eaccept_op.header.type = ENCL_OP_EACCEPT;
 
-	EXPECT_EQ(ENCL_CALL(&eaccept_op, &self->run, true), 0);
+	for (i = 0; i < edmm_size; i += 4096) {
+		eaccept_op.epc_addr = (uint64_t)(addr + i);
 
-	if (self->run.exception_vector == 14 &&
-	    self->run.exception_error_code == 4 &&
-	    self->run.exception_addr == self->encl.encl_base + total_size) {
-		munmap(addr, PAGE_SIZE);
-		SKIP(return, "Kernel does not support adding pages to initialized enclave");
-	}
+		EXPECT_EQ(ENCL_CALL(&eaccept_op, &self->run, true), 0);
+		if (self->run.exception_vector == 14 &&
+			self->run.exception_error_code == 4 &&
+			self->run.exception_addr == self->encl.encl_base) {
+			munmap(addr, edmm_size);
+			SKIP(return, "Kernel does not support adding pages to initialized enclave");
+		}
 
-	EXPECT_EEXIT(&self->run);
-	EXPECT_EQ(self->run.exception_vector, 0);
-	EXPECT_EQ(self->run.exception_error_code, 0);
-	EXPECT_EQ(self->run.exception_addr, 0);
-	EXPECT_EQ(eaccept_op.ret, 0);
+		EXPECT_EQ(self->run.exception_vector, 0);
+		EXPECT_EQ(self->run.exception_error_code, 0);
+		EXPECT_EQ(self->run.exception_addr, 0);
+		ASSERT_EQ(eaccept_op.ret, 0);
+		ASSERT_EQ(self->run.function, EEXIT);
+	}
 
 	/*
 	 * New page should be accessible from within enclave - attempt to
@@ -1207,7 +1219,7 @@ TEST_F(enclave, augment_via_eaccept)
 	EXPECT_EQ(self->run.exception_error_code, 0);
 	EXPECT_EQ(self->run.exception_addr, 0);
 
-	munmap(addr, PAGE_SIZE);
+	munmap(addr, edmm_size);
 }
 
 /*
diff --git a/tools/testing/selftests/sgx/main.h b/tools/testing/selftests/sgx/main.h
index fc585be97e2f..fe5d39ac0e1e 100644
--- a/tools/testing/selftests/sgx/main.h
+++ b/tools/testing/selftests/sgx/main.h
@@ -35,7 +35,8 @@ extern unsigned char sign_key[];
 extern unsigned char sign_key_end[];
 
 void encl_delete(struct encl *ctx);
-bool encl_load(const char *path, struct encl *encl, unsigned long heap_size);
+bool encl_load(const char *path, struct encl *encl, unsigned long heap_size,
+			   unsigned long edmm_size);
 bool encl_measure(struct encl *encl);
 bool encl_build(struct encl *encl);
 uint64_t encl_get_entry(struct encl *encl, const char *symbol);
diff --git a/tools/testing/selftests/sgx/sigstruct.c b/tools/testing/selftests/sgx/sigstruct.c
index 50c5ab1aa6fa..6000cf0e4975 100644
--- a/tools/testing/selftests/sgx/sigstruct.c
+++ b/tools/testing/selftests/sgx/sigstruct.c
@@ -343,7 +343,7 @@ bool encl_measure(struct encl *encl)
 	if (!ctx)
 		goto err;
 
-	if (!mrenclave_ecreate(ctx, encl->src_size))
+	if (!mrenclave_ecreate(ctx, encl->encl_size))
 		goto err;
 
 	for (i = 0; i < encl->nr_segments; i++) {
-- 
2.17.1


Thanks,
-Vijay

^ permalink raw reply related	[flat|nested] 10+ messages in thread