[PATCH v8 11/14] crypto: qce - convert to auxiliary bus

[Bartosz Golaszewski <bartosz.golaszewski@oss.qualcomm.com>]

This driver is disabled in arm64 defconfig but one of its
functionalities - scaling down the interconnect votes to 0 when unused -
will be moved to an always-enabled core qce driver. This upcoming core
driver will also be in charge of registering the qcrypto device on the
auxiliary bus so that it may be enabled if desired.

As the first step: convert the driver to using the auxiliary bus and
remove the interconnect management from the code. Update the power
management as required and make sure to use the parent struct device
for DMA.

Signed-off-by: Bartosz Golaszewski <bartosz.golaszewski@oss.qualcomm.com>
---
 drivers/crypto/Kconfig        |  2 +
 drivers/crypto/qce/aead.c     | 12 +++---
 drivers/crypto/qce/core.c     | 93 +++++++++++++++++++------------------------
 drivers/crypto/qce/core.h     |  5 ++-
 drivers/crypto/qce/sha.c      | 12 +++---
 drivers/crypto/qce/skcipher.c | 12 +++---
 6 files changed, 66 insertions(+), 70 deletions(-)

diff --git a/drivers/crypto/Kconfig b/drivers/crypto/Kconfig
index baf6c4a4c8aed663e89ae2468a7e9ed9dcb66f34..9d42c5f7820dc6ac54d4f2b631a93917d842fcf2 100644
--- a/drivers/crypto/Kconfig
+++ b/drivers/crypto/Kconfig
@@ -530,6 +530,8 @@ config CRYPTO_DEV_QCE
 	tristate "Qualcomm crypto engine offloader"
 	depends on ARCH_QCOM || COMPILE_TEST
 	depends on HAS_IOMEM
+	depends on PM
+	select AUXILIARY_BUS
 	help
 	  This driver supports Qualcomm crypto engine offloader hardware. To
 	  compile this driver as a module, choose M here. The module will be
diff --git a/drivers/crypto/qce/aead.c b/drivers/crypto/qce/aead.c
index a38f7f9854437a923b8fffb3dbddbfc0e3b44b97..6f33a89bb38436cc0b0d37b4209010b410e5201c 100644
--- a/drivers/crypto/qce/aead.c
+++ b/drivers/crypto/qce/aead.c
@@ -44,9 +44,9 @@ static void qce_aead_done(void *data)
 		dev_dbg(qce->dev, "aead dma termination error (%d)\n",
 			error);
 	if (diff_dst)
-		dma_unmap_sg(qce->dev, rctx->src_sg, rctx->src_nents, dir_src);
+		dma_unmap_sg(qce->dma_dev, rctx->src_sg, rctx->src_nents, dir_src);
 
-	dma_unmap_sg(qce->dev, rctx->dst_sg, rctx->dst_nents, dir_dst);
+	dma_unmap_sg(qce->dma_dev, rctx->dst_sg, rctx->dst_nents, dir_dst);
 
 	if (IS_CCM(rctx->flags)) {
 		if (req->assoclen) {
@@ -442,14 +442,14 @@ qce_aead_async_req_handle(struct crypto_async_request *async_req)
 
 	if (ret)
 		return ret;
-	dst_nents = dma_map_sg(qce->dev, rctx->dst_sg, rctx->dst_nents, dir_dst);
+	dst_nents = dma_map_sg(qce->dma_dev, rctx->dst_sg, rctx->dst_nents, dir_dst);
 	if (!dst_nents) {
 		ret = -EIO;
 		goto error_free;
 	}
 
 	if (diff_dst) {
-		src_nents = dma_map_sg(qce->dev, rctx->src_sg, rctx->src_nents, dir_src);
+		src_nents = dma_map_sg(qce->dma_dev, rctx->src_sg, rctx->src_nents, dir_src);
 		if (src_nents < 0) {
 			ret = src_nents;
 			goto error_unmap_dst;
@@ -478,9 +478,9 @@ qce_aead_async_req_handle(struct crypto_async_request *async_req)
 	qce_dma_terminate_all(&qce->dma);
 error_unmap_src:
 	if (diff_dst)
-		dma_unmap_sg(qce->dev, req->src, rctx->src_nents, dir_src);
+		dma_unmap_sg(qce->dma_dev, req->src, rctx->src_nents, dir_src);
 error_unmap_dst:
-	dma_unmap_sg(qce->dev, rctx->dst_sg, rctx->dst_nents, dir_dst);
+	dma_unmap_sg(qce->dma_dev, rctx->dst_sg, rctx->dst_nents, dir_dst);
 error_free:
 	if (IS_CCM(rctx->flags) && rctx->assoclen) {
 		sg_free_table(&rctx->src_tbl);
diff --git a/drivers/crypto/qce/core.c b/drivers/crypto/qce/core.c
index 5b1bf7a50f88c890da1f0820fb9e070b3d3f4708..31f1ad8938ab3bbe76b2ae4799eb2797efe704ed 100644
--- a/drivers/crypto/qce/core.c
+++ b/drivers/crypto/qce/core.c
@@ -3,15 +3,16 @@
  * Copyright (c) 2010-2014, The Linux Foundation. All rights reserved.
  */
 
+#include <linux/auxiliary_bus.h>
 #include <linux/cleanup.h>
 #include <linux/clk.h>
 #include <linux/device.h>
+#include <linux/device-id/auxiliary.h>
 #include <linux/dma-mapping.h>
-#include <linux/interconnect.h>
 #include <linux/interrupt.h>
 #include <linux/module.h>
 #include <linux/moduleparam.h>
-#include <linux/platform_device.h>
+#include <linux/of_address.h>
 #include <linux/pm.h>
 #include <linux/pm_runtime.h>
 #include <linux/types.h>
@@ -28,8 +29,6 @@ module_param(do_register_algos, bool, 0444);
 
 #define QCE_QUEUE_LENGTH	1
 
-#define QCE_DEFAULT_MEM_BANDWIDTH	393600
-
 static const struct qce_algo_ops *qce_ops[] = {
 #ifdef CONFIG_CRYPTO_DEV_QCE_SKCIPHER
 	&skcipher_ops,
@@ -93,11 +92,6 @@ static int qce_handle_queue(struct qce_device *qce,
 	struct crypto_async_request *async_req, *backlog;
 	int ret, err;
 
-	PM_RUNTIME_ACQUIRE_AUTOSUSPEND(qce->dev, pm);
-	ret = PM_RUNTIME_ACQUIRE_ERR(&pm);
-	if (ret)
-		return ret;
-
 	scoped_guard(mutex, &qce->lock) {
 		if (req)
 			ret = crypto_enqueue_request(&qce->queue, req);
@@ -120,8 +114,21 @@ static int qce_handle_queue(struct qce_device *qce,
 			crypto_request_complete(backlog, -EINPROGRESS);
 	}
 
+	/*
+	 * Hold the device resumed across that whole window instead of just
+	 * across this function, or autosuspend could gate the engine clocks
+	 * while the DMA is still in flight.
+	 */
+	err = pm_runtime_resume_and_get(qce->dev);
+	if (err) {
+		qce->result = err;
+		schedule_work(&qce->done_work);
+		return ret;
+	}
+
 	err = qce_handle_request(async_req);
 	if (err) {
+		pm_runtime_put_autosuspend(qce->dev);
 		qce->result = err;
 		schedule_work(&qce->done_work);
 	}
@@ -154,6 +161,7 @@ static int qce_async_request_enqueue(struct qce_device *qce,
 
 static void qce_async_request_done(struct qce_device *qce, int ret)
 {
+	pm_runtime_put_autosuspend(qce->dev);
 	qce->result = ret;
 	schedule_work(&qce->done_work);
 }
@@ -194,10 +202,12 @@ static int qce_check_version(struct qce_device *qce)
 	return 0;
 }
 
-static int qce_crypto_probe(struct platform_device *pdev)
+static int qce_crypto_probe(struct auxiliary_device *auxdev,
+			    const struct auxiliary_device_id *id)
 {
-	struct device *dev = &pdev->dev;
+	struct device *dev = &auxdev->dev;
 	struct qce_device *qce;
+	struct resource res;
 	int ret;
 
 	qce = devm_kzalloc(dev, sizeof(*qce), GFP_KERNEL);
@@ -205,13 +215,18 @@ static int qce_crypto_probe(struct platform_device *pdev)
 		return -ENOMEM;
 
 	qce->dev = dev;
-	platform_set_drvdata(pdev, qce);
+	qce->dma_dev = dev->parent;
+	auxiliary_set_drvdata(auxdev, qce);
+
+	ret = of_address_to_resource(dev->of_node, 0, &res);
+	if (ret)
+		return ret;
 
-	qce->base = devm_platform_ioremap_resource(pdev, 0);
+	qce->base = devm_ioremap_resource(dev, &res);
 	if (IS_ERR(qce->base))
 		return PTR_ERR(qce->base);
 
-	ret = dma_set_mask_and_coherent(dev, DMA_BIT_MASK(32));
+	ret = dma_set_mask_and_coherent(qce->dma_dev, DMA_BIT_MASK(32));
 	if (ret < 0)
 		return ret;
 
@@ -227,10 +242,6 @@ static int qce_crypto_probe(struct platform_device *pdev)
 	if (IS_ERR(qce->bus))
 		return PTR_ERR(qce->bus);
 
-	qce->mem_path = devm_of_icc_get(dev, "memory");
-	if (IS_ERR(qce->mem_path))
-		return PTR_ERR(qce->mem_path);
-
 	/*
 	 * Enable runtime PM after clocks and ICC path are acquired so that
 	 * the resume callback can enable clocks and apply the ICC bandwidth
@@ -240,7 +251,10 @@ static int qce_crypto_probe(struct platform_device *pdev)
 	if (ret)
 		return ret;
 
-	PM_RUNTIME_ACQUIRE_AUTOSUSPEND(dev, pm);
+	pm_runtime_set_autosuspend_delay(dev, 100);
+	pm_runtime_use_autosuspend(dev);
+
+	PM_RUNTIME_ACQUIRE_IF_ENABLED_AUTOSUSPEND(dev, pm);
 	ret = PM_RUNTIME_ACQUIRE_ERR(&pm);
 	if (ret)
 		return ret;
@@ -269,31 +283,17 @@ static int qce_crypto_probe(struct platform_device *pdev)
 			return ret;
 	}
 
-	/* Configure autosuspend after successful init */
-	pm_runtime_set_autosuspend_delay(dev, 100);
-	pm_runtime_use_autosuspend(dev);
-	pm_runtime_mark_last_busy(dev);
-
 	return 0;
 }
 
 static int qce_runtime_suspend(struct device *dev)
 {
 	struct qce_device *qce = dev_get_drvdata(dev);
-	int ret;
 
 	clk_disable_unprepare(qce->core);
 	clk_disable_unprepare(qce->iface);
 	clk_disable_unprepare(qce->bus);
 
-	ret = icc_set_bw(qce->mem_path, 0, 0);
-	if (ret) {
-		clk_prepare_enable(qce->bus);
-		clk_prepare_enable(qce->iface);
-		clk_prepare_enable(qce->core);
-		return ret;
-	}
-
 	return 0;
 }
 
@@ -302,14 +302,9 @@ static int qce_runtime_resume(struct device *dev)
 	struct qce_device *qce = dev_get_drvdata(dev);
 	int ret;
 
-	ret = icc_set_bw(qce->mem_path, QCE_DEFAULT_MEM_BANDWIDTH,
-			 QCE_DEFAULT_MEM_BANDWIDTH);
-	if (ret)
-		return ret;
-
 	ret = clk_prepare_enable(qce->core);
 	if (ret)
-		goto err_core;
+		return ret;
 
 	ret = clk_prepare_enable(qce->iface);
 	if (ret)
@@ -325,8 +320,7 @@ static int qce_runtime_resume(struct device *dev)
 	clk_disable_unprepare(qce->iface);
 err_iface:
 	clk_disable_unprepare(qce->core);
-err_core:
-	icc_set_bw(qce->mem_path, 0, 0);
+
 	return ret;
 }
 
@@ -335,25 +329,22 @@ static const struct dev_pm_ops qce_crypto_pm_ops = {
 	SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend, pm_runtime_force_resume)
 };
 
-static const struct of_device_id qce_crypto_of_match[] = {
-	{ .compatible = "qcom,crypto-v5.1", },
-	{ .compatible = "qcom,crypto-v5.4", },
-	{ .compatible = "qcom,qce", },
+static const struct auxiliary_device_id qce_crypto_ids[] = {
+	{ .name = "qce.crypto", },
 	{}
 };
-MODULE_DEVICE_TABLE(of, qce_crypto_of_match);
+MODULE_DEVICE_TABLE(auxiliary, qce_crypto_ids);
 
-static struct platform_driver qce_crypto_driver = {
+static struct auxiliary_driver qce_crypto_driver = {
 	.probe = qce_crypto_probe,
+	.id_table = qce_crypto_ids,
 	.driver = {
-		.name = KBUILD_MODNAME,
-		.of_match_table = qce_crypto_of_match,
+		.name = "qce-crypto",
 		.pm = pm_ptr(&qce_crypto_pm_ops),
 	},
 };
-module_platform_driver(qce_crypto_driver);
+module_auxiliary_driver(qce_crypto_driver);
 
 MODULE_LICENSE("GPL v2");
 MODULE_DESCRIPTION("Qualcomm crypto engine driver");
-MODULE_ALIAS("platform:" KBUILD_MODNAME);
 MODULE_AUTHOR("The Linux Foundation");
diff --git a/drivers/crypto/qce/core.h b/drivers/crypto/qce/core.h
index eb6fa7a8b64a81daf9ad5304a3ae4e5e597a70b8..6eda6e617b811420c0c3cc53988cb15a23abafe2 100644
--- a/drivers/crypto/qce/core.h
+++ b/drivers/crypto/qce/core.h
@@ -20,6 +20,9 @@
  * @result: result of current transform
  * @base: virtual IO base
  * @dev: pointer to device structure
+ * @dma_dev: pointer to the device to use for DMA mapping calls; this is the
+ *           auxiliary bus device's parent, which is the one that actually
+ *           went through DMA/IOMMU configuration
  * @core: core device clock
  * @iface: interface clock
  * @bus: bus clock
@@ -37,8 +40,8 @@ struct qce_device {
 	int result;
 	void __iomem *base;
 	struct device *dev;
+	struct device *dma_dev;
 	struct clk *core, *iface, *bus;
-	struct icc_path *mem_path;
 	struct qce_dma_data dma;
 	int burst_size;
 	unsigned int pipe_pair_id;
diff --git a/drivers/crypto/qce/sha.c b/drivers/crypto/qce/sha.c
index a9a55bc5bc310d82a52b5637655007990da5b7a8..a5b55f5a861d072ac7a82e178f9ab223f892418b 100644
--- a/drivers/crypto/qce/sha.c
+++ b/drivers/crypto/qce/sha.c
@@ -47,8 +47,8 @@ static void qce_ahash_done(void *data)
 	if (error)
 		dev_dbg(qce->dev, "ahash dma termination error (%d)\n", error);
 
-	dma_unmap_sg(qce->dev, req->src, rctx->src_nents, DMA_TO_DEVICE);
-	dma_unmap_sg(qce->dev, &rctx->result_sg, 1, DMA_FROM_DEVICE);
+	dma_unmap_sg(qce->dma_dev, req->src, rctx->src_nents, DMA_TO_DEVICE);
+	dma_unmap_sg(qce->dma_dev, &rctx->result_sg, 1, DMA_FROM_DEVICE);
 
 	memcpy(rctx->digest, result->auth_iv, digestsize);
 	if (req->result && rctx->last_blk)
@@ -93,13 +93,13 @@ static int qce_ahash_async_req_handle(struct crypto_async_request *async_req)
 		return rctx->src_nents;
 	}
 
-	ret = dma_map_sg(qce->dev, req->src, rctx->src_nents, DMA_TO_DEVICE);
+	ret = dma_map_sg(qce->dma_dev, req->src, rctx->src_nents, DMA_TO_DEVICE);
 	if (!ret)
 		return -EIO;
 
 	sg_init_one(&rctx->result_sg, qce->dma.result_buf, QCE_RESULT_BUF_SZ);
 
-	ret = dma_map_sg(qce->dev, &rctx->result_sg, 1, DMA_FROM_DEVICE);
+	ret = dma_map_sg(qce->dma_dev, &rctx->result_sg, 1, DMA_FROM_DEVICE);
 	if (!ret) {
 		ret = -EIO;
 		goto error_unmap_src;
@@ -121,9 +121,9 @@ static int qce_ahash_async_req_handle(struct crypto_async_request *async_req)
 error_terminate:
 	qce_dma_terminate_all(&qce->dma);
 error_unmap_dst:
-	dma_unmap_sg(qce->dev, &rctx->result_sg, 1, DMA_FROM_DEVICE);
+	dma_unmap_sg(qce->dma_dev, &rctx->result_sg, 1, DMA_FROM_DEVICE);
 error_unmap_src:
-	dma_unmap_sg(qce->dev, req->src, rctx->src_nents, DMA_TO_DEVICE);
+	dma_unmap_sg(qce->dma_dev, req->src, rctx->src_nents, DMA_TO_DEVICE);
 	return ret;
 }
 
diff --git a/drivers/crypto/qce/skcipher.c b/drivers/crypto/qce/skcipher.c
index 35bd59656931c5f12614405490f1e254849b9eb5..c77d96e7a7506153bed1447331dec0aba7d56828 100644
--- a/drivers/crypto/qce/skcipher.c
+++ b/drivers/crypto/qce/skcipher.c
@@ -49,8 +49,8 @@ static void qce_skcipher_done(void *data)
 			error);
 
 	if (diff_dst)
-		dma_unmap_sg(qce->dev, rctx->src_sg, rctx->src_nents, dir_src);
-	dma_unmap_sg(qce->dev, rctx->dst_sg, rctx->dst_nents, dir_dst);
+		dma_unmap_sg(qce->dma_dev, rctx->src_sg, rctx->src_nents, dir_src);
+	dma_unmap_sg(qce->dma_dev, rctx->dst_sg, rctx->dst_nents, dir_dst);
 
 	sg_free_table(&rctx->dst_tbl);
 
@@ -139,14 +139,14 @@ qce_skcipher_async_req_handle(struct crypto_async_request *async_req)
 	sg_mark_end(sg);
 	rctx->dst_sg = rctx->dst_tbl.sgl;
 
-	dst_nents = dma_map_sg(qce->dev, rctx->dst_sg, rctx->dst_nents, dir_dst);
+	dst_nents = dma_map_sg(qce->dma_dev, rctx->dst_sg, rctx->dst_nents, dir_dst);
 	if (!dst_nents) {
 		ret = -EIO;
 		goto error_free;
 	}
 
 	if (diff_dst) {
-		src_nents = dma_map_sg(qce->dev, req->src, rctx->src_nents, dir_src);
+		src_nents = dma_map_sg(qce->dma_dev, req->src, rctx->src_nents, dir_src);
 		if (!src_nents) {
 			ret = -EIO;
 			goto error_unmap_dst;
@@ -175,9 +175,9 @@ qce_skcipher_async_req_handle(struct crypto_async_request *async_req)
 	qce_dma_terminate_all(&qce->dma);
 error_unmap_src:
 	if (diff_dst)
-		dma_unmap_sg(qce->dev, req->src, rctx->src_nents, dir_src);
+		dma_unmap_sg(qce->dma_dev, req->src, rctx->src_nents, dir_src);
 error_unmap_dst:
-	dma_unmap_sg(qce->dev, rctx->dst_sg, rctx->dst_nents, dir_dst);
+	dma_unmap_sg(qce->dma_dev, rctx->dst_sg, rctx->dst_nents, dir_dst);
 error_free:
 	sg_free_table(&rctx->dst_tbl);
 	return ret;

-- 
2.47.3