[PATCH v24 13/14] crypto: qce - Add BAM DMA support for crypto register I/O

From: Bartosz Golaszewski <[email protected]>

Switch to using BAM DMA for register I/O in addition to passing data. To
that end: provide the necessary infrastructure in the driver, modify the
ordering of operations as required and replace all direct register writes
with wrappers queueing DMA command descriptors.

Signed-off-by: Bartosz Golaszewski <[email protected]>
Reviewed-by: Manivannan Sadhasivam <[email protected]>
Signed-off-by: Bartosz Golaszewski <[email protected]>
---
 drivers/crypto/qce/aead.c     |  10 ++--
 drivers/crypto/qce/common.c   |  20 ++++---
 drivers/crypto/qce/dma.c      | 122 ++++++++++++++++++++++++++++++++++++++++--
 drivers/crypto/qce/dma.h      |   5 ++
 drivers/crypto/qce/sha.c      |  10 ++--
 drivers/crypto/qce/skcipher.c |  10 ++--
 6 files changed, 146 insertions(+), 31 deletions(-)

diff --git a/drivers/crypto/qce/aead.c b/drivers/crypto/qce/aead.c
index 1461a08e6c58b00e60aa35515f3392c096726f6a..544a3cf8709248a5f3eb2b669e30b09183d3a69d 100644
--- a/drivers/crypto/qce/aead.c
+++ b/drivers/crypto/qce/aead.c
@@ -463,17 +463,17 @@ qce_aead_async_req_handle(struct crypto_async_request *async_req)
 			src_nents = dst_nents - 1;
 	}
 
-	ret = qce_dma_prep_sgs(&qce->dma, rctx->src_sg, src_nents, rctx->dst_sg, dst_nents,
-			       qce_aead_done, async_req);
+	ret = qce_start(async_req, tmpl->crypto_alg_type);
 	if (ret)
 		goto error_unmap_src;
 
-	qce_dma_issue_pending(&qce->dma);
-
-	ret = qce_start(async_req, tmpl->crypto_alg_type);
+	ret = qce_dma_prep_sgs(&qce->dma, rctx->src_sg, src_nents, rctx->dst_sg, dst_nents,
+			       qce_aead_done, async_req);
 	if (ret)
 		goto error_terminate;
 
+	qce_dma_issue_pending(&qce->dma);
+
 	return 0;
 
 error_terminate:
diff --git a/drivers/crypto/qce/common.c b/drivers/crypto/qce/common.c
index 54a78a57f63028f01870a3edeb8e390f523bb190..37bb6f03244d317a887aeb0aa10cefe327b4ce05 100644
--- a/drivers/crypto/qce/common.c
+++ b/drivers/crypto/qce/common.c
@@ -25,7 +25,7 @@ static inline u32 qce_read(struct qce_device *qce, u32 offset)
 
 static inline void qce_write(struct qce_device *qce, u32 offset, u32 val)
 {
-	writel(val, qce->base + offset);
+	qce_write_dma(qce, offset, val);
 }
 
 static inline void qce_write_array(struct qce_device *qce, u32 offset,
@@ -82,6 +82,8 @@ static void qce_setup_config(struct qce_device *qce)
 {
 	u32 config;
 
+	qce_clear_bam_transaction(qce);
+
 	/* get big endianness */
 	config = qce_config_reg(qce, 0);
 
@@ -90,12 +92,14 @@ static void qce_setup_config(struct qce_device *qce)
 	qce_write(qce, REG_CONFIG, config);
 }
 
-static inline void qce_crypto_go(struct qce_device *qce, bool result_dump)
+static inline int qce_crypto_go(struct qce_device *qce, bool result_dump)
 {
 	if (result_dump)
 		qce_write(qce, REG_GOPROC, BIT(GO_SHIFT) | BIT(RESULTS_DUMP_SHIFT));
 	else
 		qce_write(qce, REG_GOPROC, BIT(GO_SHIFT));
+
+	return qce_submit_cmd_desc(qce);
 }
 
 #if defined(CONFIG_CRYPTO_DEV_QCE_SHA) || defined(CONFIG_CRYPTO_DEV_QCE_AEAD)
@@ -223,9 +227,7 @@ static int qce_setup_regs_ahash(struct crypto_async_request *async_req)
 	config = qce_config_reg(qce, 1);
 	qce_write(qce, REG_CONFIG, config);
 
-	qce_crypto_go(qce, true);
-
-	return 0;
+	return qce_crypto_go(qce, true);
 }
 #endif
 
@@ -386,9 +388,7 @@ static int qce_setup_regs_skcipher(struct crypto_async_request *async_req)
 	config = qce_config_reg(qce, 1);
 	qce_write(qce, REG_CONFIG, config);
 
-	qce_crypto_go(qce, true);
-
-	return 0;
+	return qce_crypto_go(qce, true);
 }
 #endif
 
@@ -535,9 +535,7 @@ static int qce_setup_regs_aead(struct crypto_async_request *async_req)
 	qce_write(qce, REG_CONFIG, config);
 
 	/* Start the process */
-	qce_crypto_go(qce, !IS_CCM(flags));
-
-	return 0;
+	return qce_crypto_go(qce, !IS_CCM(flags));
 }
 #endif
 
diff --git a/drivers/crypto/qce/dma.c b/drivers/crypto/qce/dma.c
index 26347e9fc078adede712722107e74958538accdf..88d253d9147cfc9ed275653f7fd248538378194a 100644
--- a/drivers/crypto/qce/dma.c
+++ b/drivers/crypto/qce/dma.c
@@ -4,6 +4,8 @@
  */
 
 #include <linux/device.h>
+#include <linux/dma/qcom_bam_dma.h>
+#include <linux/dma-mapping.h>
 #include <linux/dmaengine.h>
 #include <crypto/scatterwalk.h>
 
@@ -11,6 +13,98 @@
 #include "dma.h"
 
 #define QCE_IGNORE_BUF_SZ		(2 * QCE_BAM_BURST_SIZE)
+#define QCE_BAM_CMD_SGL_SIZE		128
+#define QCE_BAM_CMD_ELEMENT_SIZE	128
+
+struct qce_desc_info {
+	struct dma_async_tx_descriptor *dma_desc;
+	enum dma_data_direction dir;
+};
+
+struct qce_bam_transaction {
+	struct bam_cmd_element bam_ce[QCE_BAM_CMD_ELEMENT_SIZE];
+	struct scatterlist wr_sgl[QCE_BAM_CMD_SGL_SIZE];
+	struct qce_desc_info *desc;
+	u32 bam_ce_idx;
+	u32 pre_bam_ce_idx;
+	u32 wr_sgl_cnt;
+};
+
+void qce_clear_bam_transaction(struct qce_device *qce)
+{
+	struct qce_bam_transaction *bam_txn = qce->dma.bam_txn;
+
+	bam_txn->bam_ce_idx = 0;
+	bam_txn->wr_sgl_cnt = 0;
+	bam_txn->pre_bam_ce_idx = 0;
+}
+
+int qce_submit_cmd_desc(struct qce_device *qce)
+{
+	struct qce_desc_info *qce_desc = qce->dma.bam_txn->desc;
+	struct qce_bam_transaction *bam_txn = qce->dma.bam_txn;
+	struct dma_async_tx_descriptor *dma_desc;
+	struct dma_chan *chan = qce->dma.rxchan;
+	unsigned long attrs = DMA_PREP_CMD;
+	dma_cookie_t cookie;
+	unsigned int mapped;
+	int ret;
+
+	mapped = dma_map_sg(qce->dev, bam_txn->wr_sgl, bam_txn->wr_sgl_cnt, DMA_TO_DEVICE);
+	if (!mapped)
+		return -ENOMEM;
+
+	dma_desc = dmaengine_prep_slave_sg(chan, bam_txn->wr_sgl, mapped, DMA_MEM_TO_DEV, attrs);
+	if (!dma_desc) {
+		ret = -ENOMEM;
+		goto err_unmap_sg;
+	}
+
+	qce_desc->dma_desc = dma_desc;
+	cookie = dmaengine_submit(qce_desc->dma_desc);
+
+	ret = dma_submit_error(cookie);
+	if (ret)
+		goto err_free_desc;
+
+	return 0;
+
+err_free_desc:
+	dmaengine_desc_free(dma_desc);
+err_unmap_sg:
+	dma_unmap_sg(qce->dev, bam_txn->wr_sgl, bam_txn->wr_sgl_cnt, DMA_TO_DEVICE);
+	return ret;
+}
+
+static void qce_prep_dma_cmd_desc(struct qce_device *qce, struct qce_dma_data *dma,
+				  unsigned int addr, void *buf)
+{
+	struct qce_bam_transaction *bam_txn = dma->bam_txn;
+	struct bam_cmd_element *bam_ce_buf;
+	int bam_ce_size, cnt, idx;
+
+	idx = bam_txn->bam_ce_idx;
+	bam_ce_buf = &bam_txn->bam_ce[idx];
+	bam_prep_ce_le32(bam_ce_buf, addr, BAM_WRITE_COMMAND, *((__le32 *)buf));
+
+	bam_ce_buf = &bam_txn->bam_ce[bam_txn->pre_bam_ce_idx];
+	bam_txn->bam_ce_idx++;
+	bam_ce_size = (bam_txn->bam_ce_idx - bam_txn->pre_bam_ce_idx) * sizeof(*bam_ce_buf);
+
+	cnt = bam_txn->wr_sgl_cnt;
+
+	sg_set_buf(&bam_txn->wr_sgl[cnt], bam_ce_buf, bam_ce_size);
+
+	++bam_txn->wr_sgl_cnt;
+	bam_txn->pre_bam_ce_idx = bam_txn->bam_ce_idx;
+}
+
+void qce_write_dma(struct qce_device *qce, unsigned int offset, u32 val)
+{
+	unsigned int reg_addr = ((unsigned int)(qce->base_phys) + offset);
+
+	qce_prep_dma_cmd_desc(qce, &qce->dma, reg_addr, &val);
+}
 
 static void qce_dma_terminate(void *data)
 {
@@ -39,6 +133,16 @@ int devm_qce_dma_request(struct qce_device *qce)
 		return dev_err_probe(dev, PTR_ERR(dma->rxchan),
 				     "Failed to get RX DMA channel\n");
 
+	dma->bam_txn = devm_kzalloc(dev, sizeof(*dma->bam_txn), GFP_KERNEL);
+	if (!dma->bam_txn)
+		return -ENOMEM;
+
+	dma->bam_txn->desc = devm_kzalloc(dev, sizeof(*dma->bam_txn->desc), GFP_KERNEL);
+	if (!dma->bam_txn->desc)
+		return -ENOMEM;
+
+	sg_init_table(dma->bam_txn->wr_sgl, QCE_BAM_CMD_SGL_SIZE);
+
 	return devm_add_action_or_reset(dev, qce_dma_terminate, dma);
 }
 
@@ -98,28 +202,36 @@ int qce_dma_prep_sgs(struct qce_dma_data *dma, struct scatterlist *rx_sg,
 {
 	struct dma_chan *rxchan = dma->rxchan;
 	struct dma_chan *txchan = dma->txchan;
-	unsigned long flags = DMA_PREP_INTERRUPT | DMA_CTRL_ACK;
+	unsigned long txflags = DMA_PREP_INTERRUPT | DMA_CTRL_ACK;
+	unsigned long rxflags = txflags | DMA_PREP_FENCE;
 	int ret;
 
-	ret = qce_dma_prep_sg(rxchan, rx_sg, rx_nents, flags, DMA_MEM_TO_DEV,
+	ret = qce_dma_prep_sg(rxchan, rx_sg, rx_nents, rxflags, DMA_MEM_TO_DEV,
 			     NULL, NULL);
 	if (ret)
 		return ret;
 
-	return qce_dma_prep_sg(txchan, tx_sg, tx_nents, flags, DMA_DEV_TO_MEM,
+	return qce_dma_prep_sg(txchan, tx_sg, tx_nents, txflags, DMA_DEV_TO_MEM,
 			       cb, cb_param);
 }
 
 void qce_dma_issue_pending(struct qce_dma_data *dma)
 {
-	dma_async_issue_pending(dma->rxchan);
 	dma_async_issue_pending(dma->txchan);
+	dma_async_issue_pending(dma->rxchan);
 }
 
 int qce_dma_terminate_all(struct qce_dma_data *dma)
 {
+	struct qce_device *qce = container_of(dma, struct qce_device, dma);
+	struct qce_bam_transaction *bam_txn = dma->bam_txn;
 	int ret;
 
 	ret = dmaengine_terminate_all(dma->rxchan);
-	return ret ?: dmaengine_terminate_all(dma->txchan);
+	if (ret)
+		return ret;
+
+	dma_unmap_sg(qce->dev, bam_txn->wr_sgl, bam_txn->wr_sgl_cnt, DMA_TO_DEVICE);
+
+	return dmaengine_terminate_all(dma->txchan);
 }
diff --git a/drivers/crypto/qce/dma.h b/drivers/crypto/qce/dma.h
index 483789d9fa98e79d1283de8297bf2fc2a773f3a7..f05dfa9e6b25bd60e32f45079a8bc7e6a4cf81f9 100644
--- a/drivers/crypto/qce/dma.h
+++ b/drivers/crypto/qce/dma.h
@@ -8,6 +8,7 @@
 
 #include <linux/dmaengine.h>
 
+struct qce_bam_transaction;
 struct qce_device;
 
 /* maximum data transfer block size between BAM and CE */
@@ -32,6 +33,7 @@ struct qce_dma_data {
 	struct dma_chan *txchan;
 	struct dma_chan *rxchan;
 	struct qce_result_dump *result_buf;
+	struct qce_bam_transaction *bam_txn;
 };
 
 int devm_qce_dma_request(struct qce_device *qce);
@@ -43,5 +45,8 @@ int qce_dma_terminate_all(struct qce_dma_data *dma);
 struct scatterlist *
 qce_sgtable_add(struct sg_table *sgt, struct scatterlist *sg_add,
 		unsigned int max_len);
+void qce_write_dma(struct qce_device *qce, unsigned int offset, u32 val);
+int qce_submit_cmd_desc(struct qce_device *qce);
+void qce_clear_bam_transaction(struct qce_device *qce);
 
 #endif /* _DMA_H_ */
diff --git a/drivers/crypto/qce/sha.c b/drivers/crypto/qce/sha.c
index 5476d4d30fae7eb72bbcbcdd7d8be7a76f6732c2..5cfd769a59a791a79da42e2a5b0554ad974f7631 100644
--- a/drivers/crypto/qce/sha.c
+++ b/drivers/crypto/qce/sha.c
@@ -109,17 +109,17 @@ static int qce_ahash_async_req_handle(struct crypto_async_request *async_req)
 		goto error_unmap_src;
 	}
 
-	ret = qce_dma_prep_sgs(&qce->dma, req->src, rctx->src_nents,
-			       &rctx->result_sg, 1, qce_ahash_done, async_req);
+	ret = qce_start(async_req, tmpl->crypto_alg_type);
 	if (ret)
 		goto error_unmap_dst;
 
-	qce_dma_issue_pending(&qce->dma);
-
-	ret = qce_start(async_req, tmpl->crypto_alg_type);
+	ret = qce_dma_prep_sgs(&qce->dma, req->src, rctx->src_nents,
+			       &rctx->result_sg, 1, qce_ahash_done, async_req);
 	if (ret)
 		goto error_terminate;
 
+	qce_dma_issue_pending(&qce->dma);
+
 	return 0;
 
 error_terminate:
diff --git a/drivers/crypto/qce/skcipher.c b/drivers/crypto/qce/skcipher.c
index a9b59e68df4b6837805d45391f5a5fe43fd47709..b4ef3748fbb4dde542b0307f32d4c871b7c33ac2 100644
--- a/drivers/crypto/qce/skcipher.c
+++ b/drivers/crypto/qce/skcipher.c
@@ -142,18 +142,18 @@ qce_skcipher_async_req_handle(struct crypto_async_request *async_req)
 		src_nents = dst_nents - 1;
 	}
 
+	ret = qce_start(async_req, tmpl->crypto_alg_type);
+	if (ret)
+		goto error_unmap_src;
+
 	ret = qce_dma_prep_sgs(&qce->dma, rctx->src_sg, src_nents,
 			       rctx->dst_sg, dst_nents,
 			       qce_skcipher_done, async_req);
 	if (ret)
-		goto error_unmap_src;
+		goto error_terminate;
 
 	qce_dma_issue_pending(&qce->dma);
 
-	ret = qce_start(async_req, tmpl->crypto_alg_type);
-	if (ret)
-		goto error_terminate;
-
 	return 0;
 
 error_terminate:

-- 
2.47.3