crypto/fsl: fix BLOB encapsulation and decapsulation

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 require the key_mod, src and dst buffers to be
aligned to the cache line size and flush/invalidate the memory regions.
The same requirements apply to the job descriptor.

Tested on an i.MX6Q board.

Reviewed-by: Sumit Garg <sumit.garg@nxp.com>
Signed-off-by: Clemens Gruber <clemens.gruber@pqgruber.com>

drivers/crypto/fsl/fsl_blob.c

@@ -7,63 +7,138 @@
 
 #include <common.h>
 #include <malloc.h>
+#include <memalign.h>
 #include <fsl_sec.h>
 #include <linux/errno.h>
 #include "jobdesc.h"
 #include "desc.h"
 #include "jr.h"
 
+/**
+ * blob_decap() - Decapsulate the data from a blob
+ * @key_mod:    - Key modifier address
+ * @src:        - Source address (blob)
+ * @dst:        - Destination address (data)
+ * @len:        - Size of decapsulated data
+ *
+ * Note: Start and end of the key_mod, src and dst buffers have to be aligned to
+ * the cache line size (ARCH_DMA_MINALIGN) for the CAAM operation to succeed.
+ *
+ * Returns zero on success, negative on error.
+ */
 int blob_decap(u8 *key_mod, u8 *src, u8 *dst, u32 len)
 {
-	int ret, i = 0;
+	int ret, size, i = 0;
 	u32 *desc;
 
+	if (!IS_ALIGNED((uintptr_t)key_mod, ARCH_DMA_MINALIGN) ||
+	    !IS_ALIGNED((uintptr_t)src, ARCH_DMA_MINALIGN) ||
+	    !IS_ALIGNED((uintptr_t)dst, ARCH_DMA_MINALIGN)) {
+		puts("Error: blob_decap: Address arguments are not aligned!\n");
+		return -EINVAL;
+	}
+
 	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;
 	}
 
+	size = ALIGN(16, ARCH_DMA_MINALIGN);
+	flush_dcache_range((unsigned long)key_mod,
+			   (unsigned long)key_mod + size);
+
+	size = ALIGN(BLOB_SIZE(len), ARCH_DMA_MINALIGN);
+	flush_dcache_range((unsigned long)src,
+			   (unsigned long)src + size);
+
 	inline_cnstr_jobdesc_blob_decap(desc, key_mod, src, 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)
+	if (ret) {
-		printf("Error in Decapsulation %d\n", ret);
+		printf("Error in blob decapsulation: %d\n", ret);
-	else
+	} else {
-		printf("Decapsulation Success\n");
+		size = ALIGN(len, ARCH_DMA_MINALIGN);
+		invalidate_dcache_range((unsigned long)dst,
+					(unsigned long)dst + size);
+
+		puts("Blob decapsulation successful.\n");
+	}
 
 	free(desc);
 	return ret;
 }
 
+/**
+ * blob_encap() - Encapsulate the data as a blob
+ * @key_mod:    - Key modifier address
+ * @src:        - Source address (data)
+ * @dst:        - Destination address (blob)
+ * @len:        - Size of data to be encapsulated
+ *
+ * Note: Start and end of the key_mod, src and dst buffers have to be aligned to
+ * the cache line size (ARCH_DMA_MINALIGN) for the CAAM operation to succeed.
+ *
+ * Returns zero on success, negative on error.
+ */
 int blob_encap(u8 *key_mod, u8 *src, u8 *dst, u32 len)
 {
-	int ret, i = 0;
+	int ret, size, i = 0;
 	u32 *desc;
 
+	if (!IS_ALIGNED((uintptr_t)key_mod, ARCH_DMA_MINALIGN) ||
+	    !IS_ALIGNED((uintptr_t)src, ARCH_DMA_MINALIGN) ||
+	    !IS_ALIGNED((uintptr_t)dst, ARCH_DMA_MINALIGN)) {
+		puts("Error: blob_encap: Address arguments are not aligned!\n");
+		return -EINVAL;
+	}
+
 	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;
 	}
 
+	size = ALIGN(16, ARCH_DMA_MINALIGN);
+	flush_dcache_range((unsigned long)key_mod,
+			   (unsigned long)key_mod + size);
+
+	size = ALIGN(len, ARCH_DMA_MINALIGN);
+	flush_dcache_range((unsigned long)src,
+			   (unsigned long)src + size);
+
 	inline_cnstr_jobdesc_blob_encap(desc, key_mod, src, 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)
+	if (ret) {
-		printf("Error in Encapsulation %d\n", ret);
+		printf("Error in blob encapsulation: %d\n", ret);
-	else
+	} else {
-		printf("Encapsulation Success\n");
+		size = ALIGN(BLOB_SIZE(len), ARCH_DMA_MINALIGN);
+		invalidate_dcache_range((unsigned long)dst,
+					(unsigned long)dst + size);
+
+		puts("Blob encapsulation successful.\n");
+	}
 
 	free(desc);
 	return ret;

include/fsl_sec.h

@@ -215,6 +215,8 @@ struct sg_entry {
 #define SG_ENTRY_OFFSET_SHIFT	0
 };
 
+#define BLOB_SIZE(x)		((x) + 32 + 16) /* Blob buffer size */
+
 #if defined(CONFIG_MX6) || defined(CONFIG_MX7)
 /* Job Ring Base Address */
 #define JR_BASE_ADDR(x) (CONFIG_SYS_FSL_SEC_ADDR + 0x1000 * (x + 1))
@@ -274,8 +276,6 @@ struct sg_entry {
 #define PERM			0x0000B008      /* Clear on release, lock SMAP
 						 * lock SMAG group 1 Blob */
 
-#define BLOB_SIZE(x)       (x + 32 + 16) /* Blob buffer size */
-
 /* HAB WRAPPED KEY header */
 #define WRP_HDR_SIZE		0x08
 #define HDR_TAG			0x81