crypto: ccp - Fix base RSA function for version 5 CCPs

Version 5 devices have requirements for buffer lengths, as well as
parameter format (e.g. bits vs. bytes). Fix the base CCP driver
code to meet requirements all supported versions.

Signed-off-by: Gary R Hook <gary.hook@amd.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>

drivers/crypto/ccp/ccp-dev-v5.c

@@ -469,7 +469,7 @@ static int ccp5_perform_rsa(struct ccp_op *op)
 	CCP5_CMD_PROT(&desc) = 0;
 
 	function.raw = 0;
-	CCP_RSA_SIZE(&function) = op->u.rsa.mod_size >> 3;
+	CCP_RSA_SIZE(&function) = (op->u.rsa.mod_size + 7) >> 3;
 	CCP5_CMD_FUNCTION(&desc) = function.raw;
 
 	CCP5_CMD_LEN(&desc) = op->u.rsa.input_len;
@@ -484,10 +484,10 @@ static int ccp5_perform_rsa(struct ccp_op *op)
 	CCP5_CMD_DST_HI(&desc) = ccp_addr_hi(&op->dst.u.dma);
 	CCP5_CMD_DST_MEM(&desc) = CCP_MEMTYPE_SYSTEM;
 
-	/* Exponent is in LSB memory */
+	/* Key (Exponent) is in external memory */
-	CCP5_CMD_KEY_LO(&desc) = op->sb_key * LSB_ITEM_SIZE;
+	CCP5_CMD_KEY_LO(&desc) = ccp_addr_lo(&op->exp.u.dma);
-	CCP5_CMD_KEY_HI(&desc) = 0;
+	CCP5_CMD_KEY_HI(&desc) = ccp_addr_hi(&op->exp.u.dma);
-	CCP5_CMD_KEY_MEM(&desc) = CCP_MEMTYPE_SB;
+	CCP5_CMD_KEY_MEM(&desc) = CCP_MEMTYPE_SYSTEM;
 
 	return ccp5_do_cmd(&desc, op->cmd_q);
 }

drivers/crypto/ccp/ccp-ops.c

@@ -1731,8 +1731,7 @@ static int ccp_run_sha_cmd(struct ccp_cmd_queue *cmd_q, struct ccp_cmd *cmd)
 static int ccp_run_rsa_cmd(struct ccp_cmd_queue *cmd_q, struct ccp_cmd *cmd)
 {
 	struct ccp_rsa_engine *rsa = &cmd->u.rsa;
-	struct ccp_dm_workarea exp, src;
+	struct ccp_dm_workarea exp, src, dst;
-	struct ccp_data dst;
 	struct ccp_op op;
 	unsigned int sb_count, i_len, o_len;
 	int ret;
@@ -1743,30 +1742,40 @@ static int ccp_run_rsa_cmd(struct ccp_cmd_queue *cmd_q, struct ccp_cmd *cmd)
 	if (!rsa->exp || !rsa->mod || !rsa->src || !rsa->dst)
 		return -EINVAL;
 
+	memset(&op, 0, sizeof(op));
+	op.cmd_q = cmd_q;
+	op.jobid = CCP_NEW_JOBID(cmd_q->ccp);
+
 	/* The RSA modulus must precede the message being acted upon, so
 	 * it must be copied to a DMA area where the message and the
 	 * modulus can be concatenated.  Therefore the input buffer
 	 * length required is twice the output buffer length (which
-	 * must be a multiple of 256-bits).
+	 * must be a multiple of 256-bits).  Compute o_len, i_len in bytes.
+	 * Buffer sizes must be a multiple of 32 bytes; rounding up may be
+	 * required.
 	 */
-	o_len = ((rsa->key_size + 255) / 256) * 32;
+	o_len = 32 * ((rsa->key_size + 255) / 256);
 	i_len = o_len * 2;
 
+	if (cmd_q->ccp->vdata->version < CCP_VERSION(5, 0)) {
+		/* sb_count is the number of storage block slots required
+		 * for the modulus.
+		 */
 		sb_count = o_len / CCP_SB_BYTES;
-
+		op.sb_key = cmd_q->ccp->vdata->perform->sballoc(cmd_q,
-	memset(&op, 0, sizeof(op));
+								sb_count);
-	op.cmd_q = cmd_q;
-	op.jobid = CCP_NEW_JOBID(cmd_q->ccp);
-	op.sb_key = cmd_q->ccp->vdata->perform->sballoc(cmd_q, sb_count);
-
 		if (!op.sb_key)
 			return -EIO;
+	} else {
+		/* A version 5 device allows a modulus size that will not fit
+		 * in the LSB, so the command will transfer it from memory.
+		 * Set the sb key to the default, even though it's not used.
+		 */
+		op.sb_key = cmd_q->sb_key;
+	}
 
-	/* The RSA exponent may span multiple (32-byte) SB entries and must
+	/* The RSA exponent must be in little endian format. Reverse its
-	 * be in little endian format. Reverse copy each 32-byte chunk
+	 * byte order.
-	 * of the exponent (En chunk to E0 chunk, E(n-1) chunk to E1 chunk)
-	 * and each byte within that chunk and do not perform any byte swap
-	 * operations on the passthru operation.
 	 */
 	ret = ccp_init_dm_workarea(&exp, cmd_q, o_len, DMA_TO_DEVICE);
 	if (ret)
@@ -1775,12 +1784,23 @@ static int ccp_run_rsa_cmd(struct ccp_cmd_queue *cmd_q, struct ccp_cmd *cmd)
 	ret = ccp_reverse_set_dm_area(&exp, 0, rsa->exp, 0, rsa->exp_len);
 	if (ret)
 		goto e_exp;
+
+	if (cmd_q->ccp->vdata->version < CCP_VERSION(5, 0)) {
+		/* Copy the exponent to the local storage block, using
+		 * as many 32-byte blocks as were allocated above. It's
+		 * already little endian, so no further change is required.
+		 */
 		ret = ccp_copy_to_sb(cmd_q, &exp, op.jobid, op.sb_key,
 				     CCP_PASSTHRU_BYTESWAP_NOOP);
 		if (ret) {
 			cmd->engine_error = cmd_q->cmd_error;
 			goto e_exp;
 		}
+	} else {
+		/* The exponent can be retrieved from memory via DMA. */
+		op.exp.u.dma.address = exp.dma.address;
+		op.exp.u.dma.offset = 0;
+	}
 
 	/* Concatenate the modulus and the message. Both the modulus and
 	 * the operands must be in little endian format.  Since the input
@@ -1798,8 +1818,7 @@ static int ccp_run_rsa_cmd(struct ccp_cmd_queue *cmd_q, struct ccp_cmd *cmd)
 		goto e_src;
 
 	/* Prepare the output area for the operation */
-	ret = ccp_init_data(&dst, cmd_q, rsa->dst, rsa->mod_len,
+	ret = ccp_init_dm_workarea(&dst, cmd_q, o_len, DMA_FROM_DEVICE);
-			    o_len, DMA_FROM_DEVICE);
 	if (ret)
 		goto e_src;
 
@@ -1807,7 +1826,7 @@ static int ccp_run_rsa_cmd(struct ccp_cmd_queue *cmd_q, struct ccp_cmd *cmd)
 	op.src.u.dma.address = src.dma.address;
 	op.src.u.dma.offset = 0;
 	op.src.u.dma.length = i_len;
-	op.dst.u.dma.address = dst.dm_wa.dma.address;
+	op.dst.u.dma.address = dst.dma.address;
 	op.dst.u.dma.offset = 0;
 	op.dst.u.dma.length = o_len;
 
@@ -1820,10 +1839,10 @@ static int ccp_run_rsa_cmd(struct ccp_cmd_queue *cmd_q, struct ccp_cmd *cmd)
 		goto e_dst;
 	}
 
-	ccp_reverse_get_dm_area(&dst.dm_wa, 0, rsa->dst, 0, rsa->mod_len);
+	ccp_reverse_get_dm_area(&dst, 0, rsa->dst, 0, rsa->mod_len);
 
 e_dst:
-	ccp_free_data(&dst, cmd_q);
+	ccp_dm_free(&dst);
 
 e_src:
 	ccp_dm_free(&src);
@@ -1832,6 +1851,7 @@ static int ccp_run_rsa_cmd(struct ccp_cmd_queue *cmd_q, struct ccp_cmd *cmd)
 	ccp_dm_free(&exp);
 
 e_sb:
+	if (cmd_q->ccp->vdata->version < CCP_VERSION(5, 0))
 		cmd_q->ccp->vdata->perform->sbfree(cmd_q, op.sb_key, sb_count);
 
 	return ret;