[U-Boot] [PATCH] crypto/fsl: fix BLOB encapsulation and decapsulation

[Clemens Gruber]

The blob_encap and blob_decap functions were not flushing the dcache
before passing data to CAAM/DMA and not invalidating the dcache when
getting data back.
Therefore, blob encapsulation and decapsulation failed with errors like
the following due to data cache incoherency:
"40000006: DECO: desc idx 0: Invalid KEY command"

To ensure coherency, we allocate aligned memory to store the data passed
to/from CAAM and flush/invalidate the memory regions.
Blobs can now be encapsulated and decapsulated with the blob cmd as well
as from board code by calling blob_encap and blob_decap directly.

Tested on an i.MX6Q board.

Signed-off-by: Clemens Gruber <clemens.gruber at pqgruber.com>
---
 drivers/crypto/fsl/fsl_blob.c | 99 ++++++++++++++++++++++++++++++++++++-------
 1 file changed, 83 insertions(+), 16 deletions(-)

diff --git a/drivers/crypto/fsl/fsl_blob.c b/drivers/crypto/fsl/fsl_blob.c
index 38c6f9486b..65ce21f4af 100644
--- a/drivers/crypto/fsl/fsl_blob.c
+++ b/drivers/crypto/fsl/fsl_blob.c
@@ -7,6 +7,7 @@
 
 #include <common.h>
 #include <malloc.h>
+#include <memalign.h>
 #include <fsl_sec.h>
 #include <linux/errno.h>
 #include "jobdesc.h"
@@ -15,56 +16,122 @@
 
 int blob_decap(u8 *key_mod, u8 *src, u8 *dst, u32 len)
 {
-	int ret, i = 0;
+	ALLOC_CACHE_ALIGN_BUFFER(u8, aligned_key_mod, 16);
+	u8 *aligned_src, *aligned_dst;
+	int ret, size, i = 0;
 	u32 *desc;
 
 	printf("\nDecapsulating blob to get data\n");
-	desc = malloc(sizeof(int) * MAX_CAAM_DESCSIZE);
+	desc = malloc_cache_aligned(sizeof(int) * MAX_CAAM_DESCSIZE);
 	if (!desc) {
 		debug("Not enough memory for descriptor allocation\n");
-		return -1;
+		return -ENOMEM;
 	}
 
-	inline_cnstr_jobdesc_blob_decap(desc, key_mod, src, dst, len);
+	aligned_src = malloc_cache_aligned(BLOB_SIZE(len));
+	aligned_dst = malloc_cache_aligned(len);
+	if (!aligned_src || !aligned_dst) {
+		debug("Not enough memory for blob allocations\n");
+		return -ENOMEM;
+	}
+
+	memcpy(aligned_key_mod, key_mod, 16);
+	size = ALIGN(16, ARCH_DMA_MINALIGN);
+	flush_dcache_range((unsigned long)aligned_key_mod,
+			   (unsigned long)aligned_key_mod + size);
+
+	memcpy(aligned_src, src, BLOB_SIZE(len));
+	size = ALIGN(BLOB_SIZE(len), ARCH_DMA_MINALIGN);
+	flush_dcache_range((unsigned long)aligned_src,
+			   (unsigned long)aligned_src + size);
+
+	inline_cnstr_jobdesc_blob_decap(desc, aligned_key_mod, aligned_src,
+					aligned_dst, len);
 
 	debug("Descriptor dump:\n");
 	for (i = 0; i < 14; i++)
 		debug("Word[%d]: %08x\n", i, *(desc + i));
+
+	size = ALIGN(sizeof(int) * MAX_CAAM_DESCSIZE, ARCH_DMA_MINALIGN);
+	flush_dcache_range((unsigned long)desc,
+			   (unsigned long)desc + size);
+
 	ret = run_descriptor_jr(desc);
 
-	if (ret)
-		printf("Error in Decapsulation %d\n", ret);
-	else
-		printf("Decapsulation Success\n");
+	if (ret) {
+		printf("Error in blob decapsulation: %d\n", ret);
+	} else {
+		size = ALIGN(len, ARCH_DMA_MINALIGN);
+		invalidate_dcache_range((unsigned long)aligned_dst,
+					(unsigned long)aligned_dst + size);
+		memcpy(dst, aligned_dst, len);
+
+		puts("Blob decapsulation successful.\n");
+	}
 
+	free(aligned_dst);
+	free(aligned_src);
 	free(desc);
 	return ret;
 }
 
 int blob_encap(u8 *key_mod, u8 *src, u8 *dst, u32 len)
 {
-	int ret, i = 0;
+	ALLOC_CACHE_ALIGN_BUFFER(u8, aligned_key_mod, 16);
+	u8 *aligned_src, *aligned_dst;
+	int ret, size, i = 0;
 	u32 *desc;
 
 	printf("\nEncapsulating data to form blob\n");
-	desc = malloc(sizeof(int) * MAX_CAAM_DESCSIZE);
+	desc = malloc_cache_aligned(sizeof(int) * MAX_CAAM_DESCSIZE);
 	if (!desc) {
 		debug("Not enough memory for descriptor allocation\n");
-		return -1;
+		return -ENOMEM;
 	}
 
-	inline_cnstr_jobdesc_blob_encap(desc, key_mod, src, dst, len);
+	aligned_src = malloc_cache_aligned(len);
+	aligned_dst = malloc_cache_aligned(BLOB_SIZE(len));
+	if (!aligned_src || !aligned_dst) {
+		debug("Not enough memory for blob allocations\n");
+		return -ENOMEM;
+	}
+
+	memcpy(aligned_key_mod, key_mod, 16);
+	size = ALIGN(16, ARCH_DMA_MINALIGN);
+	flush_dcache_range((unsigned long)aligned_key_mod,
+			   (unsigned long)aligned_key_mod + size);
+
+	memcpy(aligned_src, src, len);
+	size = ALIGN(len, ARCH_DMA_MINALIGN);
+	flush_dcache_range((unsigned long)aligned_src,
+			   (unsigned long)aligned_src + size);
+
+	inline_cnstr_jobdesc_blob_encap(desc, aligned_key_mod, aligned_src,
+					aligned_dst, len);
 
 	debug("Descriptor dump:\n");
 	for (i = 0; i < 14; i++)
 		debug("Word[%d]: %08x\n", i, *(desc + i));
+
+	size = ALIGN(sizeof(int) * MAX_CAAM_DESCSIZE, ARCH_DMA_MINALIGN);
+	flush_dcache_range((unsigned long)desc,
+			   (unsigned long)desc + size);
+
 	ret = run_descriptor_jr(desc);
 
-	if (ret)
-		printf("Error in Encapsulation %d\n", ret);
-	else
-		printf("Encapsulation Success\n");
+	if (ret) {
+		printf("Error in blob encapsulation: %d\n", ret);
+	} else {
+		size = ALIGN(BLOB_SIZE(len), ARCH_DMA_MINALIGN);
+		invalidate_dcache_range((unsigned long)aligned_dst,
+					(unsigned long)aligned_dst + size);
+		memcpy(dst, aligned_dst, BLOB_SIZE(len));
+
+		puts("Blob encapsulation successful.\n");
+	}
 
+	free(aligned_dst);
+	free(aligned_src);
 	free(desc);
 	return ret;
 }
-- 
2.15.1