mmc: core: Remove bounce buffer in mmc_send_cxd_data()

It is expected that Extended CSD register (the size of this register
is larger than CID/CSD) will be referenced more frequently as more
fields have been added to Extended CSD and it seems that it is not
a good option to double the memory used.

This patch is intended to avoid the use of bounce buffer for reading
Extended CSD register in mmc_send_cxd_data(). It will provide a better
performance gain by removing memcpy() overhead for a half KiB and
a redundant bounce buffer allocated repeatedly at the cost of providing
DMA-capable buffer from upper caller (but on-stack buffer is allowed
with no performance gain).
Signed-off-by: Kyungsik Lee <kyungsik.lee@lge.com>
Reviewed-by: Venkatraman S <svenkatr@ti.com>
Signed-off-by: Chris Ball <cjb@laptop.org>

drivers/mmc/core/mmc_ops.c

@@ -230,6 +230,10 @@ mmc_send_cxd_native(struct mmc_host *host, u32 arg, u32 *cxd, int opcode)
 	return 0;
 }
 
+/*
+ * NOTE: void *buf, caller for the buf is required to use DMA-capable
+ * buffer or on-stack buffer (with some overhead in callee).
+ */
 static int
 mmc_send_cxd_data(struct mmc_card *card, struct mmc_host *host,
 		u32 opcode, void *buf, unsigned len)
@@ -239,13 +243,19 @@ mmc_send_cxd_data(struct mmc_card *card, struct mmc_host *host,
 	struct mmc_data data = {0};
 	struct scatterlist sg;
 	void *data_buf;
+	int is_on_stack;
 
-	/* dma onto stack is unsafe/nonportable, but callers to this
-	 * routine normally provide temporary on-stack buffers ...
-	 */
-	data_buf = kmalloc(len, GFP_KERNEL);
-	if (data_buf == NULL)
-		return -ENOMEM;
+	is_on_stack = object_is_on_stack(buf);
+	if (is_on_stack) {
+		/*
+		 * dma onto stack is unsafe/nonportable, but callers to this
+		 * routine normally provide temporary on-stack buffers ...
+		 */
+		data_buf = kmalloc(len, GFP_KERNEL);
+		if (!data_buf)
+			return -ENOMEM;
+	} else
+		data_buf = buf;
 
 	mrq.cmd = &cmd;
 	mrq.data = &data;
@@ -280,8 +290,10 @@ mmc_send_cxd_data(struct mmc_card *card, struct mmc_host *host,
 
 	mmc_wait_for_req(host, &mrq);
 
-	memcpy(buf, data_buf, len);
-	kfree(data_buf);
+	if (is_on_stack) {
+		memcpy(buf, data_buf, len);
+		kfree(data_buf);
+	}
 
 	if (cmd.error)
 		return cmd.error;
@@ -294,24 +306,32 @@ mmc_send_cxd_data(struct mmc_card *card, struct mmc_host *host,
 int mmc_send_csd(struct mmc_card *card, u32 *csd)
 {
 	int ret, i;
+	u32 *csd_tmp;
 
 	if (!mmc_host_is_spi(card->host))
 		return mmc_send_cxd_native(card->host, card->rca << 16,
 				csd, MMC_SEND_CSD);
 
-	ret = mmc_send_cxd_data(card, card->host, MMC_SEND_CSD, csd, 16);
+	csd_tmp = kmalloc(16, GFP_KERNEL);
+	if (!csd_tmp)
+		return -ENOMEM;
+
+	ret = mmc_send_cxd_data(card, card->host, MMC_SEND_CSD, csd_tmp, 16);
 	if (ret)
-		return ret;
+		goto err;
 
 	for (i = 0;i < 4;i++)
-		csd[i] = be32_to_cpu(csd[i]);
+		csd[i] = be32_to_cpu(csd_tmp[i]);
 
-	return 0;
+err:
+	kfree(csd_tmp);
+	return ret;
 }
 
 int mmc_send_cid(struct mmc_host *host, u32 *cid)
 {
 	int ret, i;
+	u32 *cid_tmp;
 
 	if (!mmc_host_is_spi(host)) {
 		if (!host->card)
@@ -320,14 +340,20 @@ int mmc_send_cid(struct mmc_host *host, u32 *cid)
 				cid, MMC_SEND_CID);
 	}
 
-	ret = mmc_send_cxd_data(NULL, host, MMC_SEND_CID, cid, 16);
+	cid_tmp = kmalloc(16, GFP_KERNEL);
+	if (!cid_tmp)
+		return -ENOMEM;
+
+	ret = mmc_send_cxd_data(NULL, host, MMC_SEND_CID, cid_tmp, 16);
 	if (ret)
-		return ret;
+		goto err;
 
 	for (i = 0;i < 4;i++)
-		cid[i] = be32_to_cpu(cid[i]);
+		cid[i] = be32_to_cpu(cid_tmp[i]);
 
-	return 0;
+err:
+	kfree(cid_tmp);
+	return ret;
 }
 
 int mmc_send_ext_csd(struct mmc_card *card, u8 *ext_csd)