[Patch v2 0/9] Tegra234 Memory interconnect support

[Patch v2 0/9] Tegra234 Memory interconnect support

[Sumit Gupta]

This patch series adds memory interconnect support for Tegra234 SoC.
It is used to dynamically scale DRAM Frequency as per the bandwidth
requests from different Memory Controller (MC) clients.
MC Clients use ICC Framework's icc_set_bw() api to dynamically request
for the DRAM bandwidth (BW). As per path, the request will be routed
from MC to the EMC driver. MC driver passes the request info like the
Client ID, type, and frequency request info to the BPMP-FW which will
set the final DRAM freq considering all exisiting requests.

MC and EMC are the ICC providers. Nodes in path for a request will be:
     Client[1-n] -> MC -> EMC -> EMEM/DRAM

The patch series also adds interconnect support in below client drivers:
1) CPUFREQ driver for scaling bandwidth with CPU frequency. For that,
   added per cluster OPP table which will be used in the CPUFREQ driver
   by requesting the minimum BW respective to the given CPU frequency in
   the OPP table of given cluster.
2) PCIE driver to request BW required for different modes.

---
v1[1] -> v2:
- moved BW setting to tegra234_mc_icc_set() from EMC driver.
- moved sw clients to the 'tegra_mc_clients' table.
- point 'node->data' to the entry within 'tegra_mc_clients'.
- removed 'struct tegra_icc_node' and get client info using 'node->data'.
- changed error handling in and around tegra_emc_interconnect_init().
- moved 'tegra-icc.h' from 'include/soc/tegra' to 'include/linux'.
- added interconnect support to PCIE driver in 'Patch 9'.
- merged 'Patch 9 & 10' from [1] to get num_channels and use.
- merged 'Patch 2 & 3' from [1] to add ISO and NISO clients.
- added 'Acked-by' of Krzysztof from 'Patch 05/10' of [1].
- Removed 'Patch 7' from [1] as that is merged now.

Sumit Gupta (9):
  firmware: tegra: add function to get BPMP data
  memory: tegra: add interconnect support for DRAM scaling in Tegra234
  memory: tegra: add mc clients for Tegra234
  memory: tegra: add software mc clients in Tegra234
  dt-bindings: tegra: add icc ids for dummy MC clients
  arm64: tegra: Add cpu OPP tables and interconnects property
  cpufreq: tegra194: add OPP support and set bandwidth
  memory: tegra: make cpu cluster bw request a multiple of mc channels
  PCI: tegra194: add interconnect support in Tegra234

 arch/arm64/boot/dts/nvidia/tegra234.dtsi   | 276 ++++++++++
 drivers/cpufreq/tegra194-cpufreq.c         | 152 +++++-
 drivers/firmware/tegra/bpmp.c              |  38 ++
 drivers/memory/tegra/mc.c                  |  24 +
 drivers/memory/tegra/mc.h                  |   1 +
 drivers/memory/tegra/tegra186-emc.c        | 117 ++++
 drivers/memory/tegra/tegra234.c            | 593 ++++++++++++++++++++-
 drivers/pci/controller/dwc/pcie-tegra194.c |  40 +-
 include/dt-bindings/memory/tegra234-mc.h   |   5 +
 include/linux/tegra-icc.h                  |  65 +++
 include/soc/tegra/bpmp.h                   |   5 +
 include/soc/tegra/mc.h                     |   6 +
 12 files changed, 1300 insertions(+), 22 deletions(-)
 create mode 100644 include/linux/tegra-icc.h

[1] https://lore.kernel.org/lkml/20221220160240.27494-1-sumitg@nvidia.com/T/

-- 
2.17.1

[Patch v2 1/9] firmware: tegra: add function to get BPMP data

[Sumit Gupta]

Add new function 'of_tegra_bpmp_get()' which can be
used by other drivers like MC to get BPMP data without
adding any property in respective drivers DT node.

Signed-off-by: Sumit Gupta <sumitg@nvidia.com>
---
 drivers/firmware/tegra/bpmp.c | 38 +++++++++++++++++++++++++++++++++++
 include/soc/tegra/bpmp.h      |  5 +++++
 2 files changed, 43 insertions(+)

diff --git a/drivers/firmware/tegra/bpmp.c b/drivers/firmware/tegra/bpmp.c
index 042c2043929d..d825067a223a 100644
--- a/drivers/firmware/tegra/bpmp.c
+++ b/drivers/firmware/tegra/bpmp.c
@@ -39,6 +39,44 @@ channel_to_ops(struct tegra_bpmp_channel *channel)
 	return bpmp->soc->ops;
 }
 
+struct tegra_bpmp *of_tegra_bpmp_get(void)
+{
+	struct platform_device *pdev;
+	struct device_node *bpmp_dev;
+	struct tegra_bpmp *bpmp;
+
+	/* Check for bpmp device status in DT */
+	bpmp_dev = of_find_compatible_node(NULL, NULL, "nvidia,tegra186-bpmp");
+	if (!bpmp_dev) {
+		bpmp = ERR_PTR(-ENODEV);
+		goto err_out;
+	}
+	if (!of_device_is_available(bpmp_dev)) {
+		bpmp = ERR_PTR(-ENODEV);
+		goto err_put;
+	}
+
+	pdev = of_find_device_by_node(bpmp_dev);
+	if (!pdev) {
+		bpmp = ERR_PTR(-ENODEV);
+		goto err_put;
+	}
+
+	bpmp = platform_get_drvdata(pdev);
+	if (!bpmp) {
+		bpmp = ERR_PTR(-EPROBE_DEFER);
+		put_device(&pdev->dev);
+		goto err_put;
+	}
+
+	return bpmp;
+err_put:
+	of_node_put(bpmp_dev);
+err_out:
+	return bpmp;
+}
+EXPORT_SYMBOL_GPL(of_tegra_bpmp_get);
+
 struct tegra_bpmp *tegra_bpmp_get(struct device *dev)
 {
 	struct platform_device *pdev;
diff --git a/include/soc/tegra/bpmp.h b/include/soc/tegra/bpmp.h
index 5842e38bb288..9fd3aa9e69bb 100644
--- a/include/soc/tegra/bpmp.h
+++ b/include/soc/tegra/bpmp.h
@@ -120,6 +120,7 @@ struct tegra_bpmp_message {
 };
 
 #if IS_ENABLED(CONFIG_TEGRA_BPMP)
+struct tegra_bpmp *of_tegra_bpmp_get(void);
 struct tegra_bpmp *tegra_bpmp_get(struct device *dev);
 void tegra_bpmp_put(struct tegra_bpmp *bpmp);
 int tegra_bpmp_transfer_atomic(struct tegra_bpmp *bpmp,
@@ -135,6 +136,10 @@ void tegra_bpmp_free_mrq(struct tegra_bpmp *bpmp, unsigned int mrq,
 			 void *data);
 bool tegra_bpmp_mrq_is_supported(struct tegra_bpmp *bpmp, unsigned int mrq);
 #else
+static inline struct tegra_bpmp *of_tegra_bpmp_get(void)
+{
+	return ERR_PTR(-EOPNOTSUPP);
+}
 static inline struct tegra_bpmp *tegra_bpmp_get(struct device *dev)
 {
 	return ERR_PTR(-ENOTSUPP);
-- 
2.17.1

[Patch v2 2/9] memory: tegra: add interconnect support for DRAM scaling in Tegra234

[Sumit Gupta]

Add Interconnect framework support to dynamically set the DRAM
bandwidth from different clients. Both the MC and EMC drivers are
added as ICC providers. The path for any request is:
 MC-Client[1-n] -> MC -> EMC -> EMEM/DRAM

MC client's request for bandwidth will go to the MC driver which
passes the client request info like BPMP Client ID, Client type
and the Bandwidth to the BPMP-FW. The final DRAM freq to achieve
the requested bandwidth is set by the BPMP-FW based on the passed
parameters.

Signed-off-by: Sumit Gupta <sumitg@nvidia.com>
---
 drivers/memory/tegra/mc.c           |   5 +
 drivers/memory/tegra/tegra186-emc.c | 117 +++++++++++++++++++++++
 drivers/memory/tegra/tegra234.c     | 139 +++++++++++++++++++++++++++-
 include/linux/tegra-icc.h           |  65 +++++++++++++
 include/soc/tegra/mc.h              |   5 +
 5 files changed, 330 insertions(+), 1 deletion(-)
 create mode 100644 include/linux/tegra-icc.h

diff --git a/drivers/memory/tegra/mc.c b/drivers/memory/tegra/mc.c
index 592907546ee6..7318eaa3819c 100644
--- a/drivers/memory/tegra/mc.c
+++ b/drivers/memory/tegra/mc.c
@@ -15,6 +15,7 @@
 #include <linux/platform_device.h>
 #include <linux/slab.h>
 #include <linux/sort.h>
+#include <linux/tegra-icc.h>
 
 #include <soc/tegra/fuse.h>
 
@@ -792,6 +793,8 @@ static int tegra_mc_interconnect_setup(struct tegra_mc *mc)
 	mc->provider.data = &mc->provider;
 	mc->provider.set = mc->soc->icc_ops->set;
 	mc->provider.aggregate = mc->soc->icc_ops->aggregate;
+	mc->provider.get_bw = mc->soc->icc_ops->get_bw;
+	mc->provider.xlate = mc->soc->icc_ops->xlate;
 	mc->provider.xlate_extended = mc->soc->icc_ops->xlate_extended;
 
 	err = icc_provider_add(&mc->provider);
@@ -828,6 +831,8 @@ static int tegra_mc_interconnect_setup(struct tegra_mc *mc)
 		err = icc_link_create(node, TEGRA_ICC_MC);
 		if (err)
 			goto remove_nodes;
+
+		node->data = (char *)&(mc->soc->clients[i]);
 	}
 
 	return 0;
diff --git a/drivers/memory/tegra/tegra186-emc.c b/drivers/memory/tegra/tegra186-emc.c
index 26e763bde92a..756a5fefb383 100644
--- a/drivers/memory/tegra/tegra186-emc.c
+++ b/drivers/memory/tegra/tegra186-emc.c
@@ -7,9 +7,11 @@
 #include <linux/debugfs.h>
 #include <linux/module.h>
 #include <linux/mod_devicetable.h>
+#include <linux/of_platform.h>
 #include <linux/platform_device.h>
 
 #include <soc/tegra/bpmp.h>
+#include "mc.h"
 
 struct tegra186_emc_dvfs {
 	unsigned long latency;
@@ -29,8 +31,15 @@ struct tegra186_emc {
 		unsigned long min_rate;
 		unsigned long max_rate;
 	} debugfs;
+
+	struct icc_provider provider;
 };
 
+static inline struct tegra186_emc *to_tegra186_emc(struct icc_provider *provider)
+{
+	return container_of(provider, struct tegra186_emc, provider);
+}
+
 /*
  * debugfs interface
  *
@@ -146,11 +155,104 @@ DEFINE_DEBUGFS_ATTRIBUTE(tegra186_emc_debug_max_rate_fops,
 			  tegra186_emc_debug_max_rate_get,
 			  tegra186_emc_debug_max_rate_set, "%llu\n");
 
+/*
+ * tegra_emc_icc_set_bw() - Set BW api for EMC provider
+ * @src: ICC node for External Memory Controller (EMC)
+ * @dst: ICC node for External Memory (DRAM)
+ *
+ * Do nothing here as info to BPMP-FW is now passed in the BW set function
+ * of the MC driver. BPMP-FW sets the final Freq based on the passed values.
+ */
+static int tegra_emc_icc_set_bw(struct icc_node *src, struct icc_node *dst)
+{
+	return 0;
+}
+
+static struct icc_node *
+tegra_emc_of_icc_xlate(struct of_phandle_args *spec, void *data)
+{
+	struct icc_provider *provider = data;
+	struct icc_node *node;
+
+	/* External Memory is the only possible ICC route */
+	list_for_each_entry(node, &provider->nodes, node_list) {
+		if (node->id != TEGRA_ICC_EMEM)
+			continue;
+
+		return node;
+	}
+
+	return ERR_PTR(-EPROBE_DEFER);
+}
+
+static int tegra_emc_icc_get_init_bw(struct icc_node *node, u32 *avg, u32 *peak)
+{
+	*avg = 0;
+	*peak = 0;
+
+	return 0;
+}
+
+static int tegra_emc_interconnect_init(struct tegra186_emc *emc)
+{
+	struct tegra_mc *mc = dev_get_drvdata(emc->dev->parent);
+	const struct tegra_mc_soc *soc = mc->soc;
+	struct icc_node *node;
+	int err;
+
+	emc->provider.dev = emc->dev;
+	emc->provider.set = tegra_emc_icc_set_bw;
+	emc->provider.data = &emc->provider;
+	emc->provider.aggregate = soc->icc_ops->aggregate;
+	emc->provider.xlate = tegra_emc_of_icc_xlate;
+	emc->provider.get_bw = tegra_emc_icc_get_init_bw;
+
+	err = icc_provider_add(&emc->provider);
+	if (err)
+		goto err_msg;
+
+	/* create External Memory Controller node */
+	node = icc_node_create(TEGRA_ICC_EMC);
+	if (IS_ERR(node)) {
+		err = PTR_ERR(node);
+		goto del_provider;
+	}
+
+	node->name = "External Memory Controller";
+	icc_node_add(node, &emc->provider);
+
+	/* link External Memory Controller to External Memory (DRAM) */
+	err = icc_link_create(node, TEGRA_ICC_EMEM);
+	if (err)
+		goto remove_nodes;
+
+	/* create External Memory node */
+	node = icc_node_create(TEGRA_ICC_EMEM);
+	if (IS_ERR(node)) {
+		err = PTR_ERR(node);
+		goto remove_nodes;
+	}
+
+	node->name = "External Memory (DRAM)";
+	icc_node_add(node, &emc->provider);
+
+	return 0;
+remove_nodes:
+	icc_nodes_remove(&emc->provider);
+del_provider:
+	icc_provider_del(&emc->provider);
+err_msg:
+	dev_err(emc->dev, "failed to initialize ICC: %d\n", err);
+
+	return err;
+}
+
 static int tegra186_emc_probe(struct platform_device *pdev)
 {
 	struct mrq_emc_dvfs_latency_response response;
 	struct tegra_bpmp_message msg;
 	struct tegra186_emc *emc;
+	struct tegra_mc *mc;
 	unsigned int i;
 	int err;
 
@@ -158,6 +260,9 @@ static int tegra186_emc_probe(struct platform_device *pdev)
 	if (!emc)
 		return -ENOMEM;
 
+	platform_set_drvdata(pdev, emc);
+	emc->dev = &pdev->dev;
+
 	emc->bpmp = tegra_bpmp_get(&pdev->dev);
 	if (IS_ERR(emc->bpmp))
 		return dev_err_probe(&pdev->dev, PTR_ERR(emc->bpmp), "failed to get BPMP\n");
@@ -236,6 +341,17 @@ static int tegra186_emc_probe(struct platform_device *pdev)
 	debugfs_create_file("max_rate", S_IRUGO | S_IWUSR, emc->debugfs.root,
 			    emc, &tegra186_emc_debug_max_rate_fops);
 
+	mc = dev_get_drvdata(emc->dev->parent);
+	if (mc && mc->soc->icc_ops) {
+		if (tegra_bpmp_mrq_is_supported(emc->bpmp, MRQ_BWMGR_INT)) {
+			err = tegra_emc_interconnect_init(emc);
+			if (err)
+				goto put_bpmp;
+		} else {
+			dev_info(&pdev->dev, "MRQ_BWMGR_INT not present\n");
+		}
+	}
+
 	return 0;
 
 put_bpmp:
@@ -272,6 +388,7 @@ static struct platform_driver tegra186_emc_driver = {
 		.name = "tegra186-emc",
 		.of_match_table = tegra186_emc_of_match,
 		.suppress_bind_attrs = true,
+		.sync_state = icc_sync_state,
 	},
 	.probe = tegra186_emc_probe,
 	.remove = tegra186_emc_remove,
diff --git a/drivers/memory/tegra/tegra234.c b/drivers/memory/tegra/tegra234.c
index 02dcc5748bba..b40229926558 100644
--- a/drivers/memory/tegra/tegra234.c
+++ b/drivers/memory/tegra/tegra234.c
@@ -1,18 +1,24 @@
 // SPDX-License-Identifier: GPL-2.0-only
 /*
- * Copyright (C) 2021-2022, NVIDIA CORPORATION.  All rights reserved.
+ * Copyright (C) 20212-2023, NVIDIA CORPORATION.  All rights reserved.
  */
 
 #include <soc/tegra/mc.h>
 
 #include <dt-bindings/memory/tegra234-mc.h>
+#include <linux/interconnect.h>
+#include <linux/of_device.h>
+#include <linux/tegra-icc.h>
 
+#include <soc/tegra/bpmp.h>
 #include "mc.h"
 
 static const struct tegra_mc_client tegra234_mc_clients[] = {
 	{
 		.id = TEGRA234_MEMORY_CLIENT_MGBEARD,
 		.name = "mgbeard",
+		.bpmp_id = TEGRA_ICC_BPMP_EQOS,
+		.type = TEGRA_ICC_NISO,
 		.sid = TEGRA234_SID_MGBE,
 		.regs = {
 			.sid = {
@@ -23,6 +29,8 @@ static const struct tegra_mc_client tegra234_mc_clients[] = {
 	}, {
 		.id = TEGRA234_MEMORY_CLIENT_MGBEBRD,
 		.name = "mgbebrd",
+		.bpmp_id = TEGRA_ICC_BPMP_EQOS,
+		.type = TEGRA_ICC_NISO,
 		.sid = TEGRA234_SID_MGBE_VF1,
 		.regs = {
 			.sid = {
@@ -33,6 +41,8 @@ static const struct tegra_mc_client tegra234_mc_clients[] = {
 	}, {
 		.id = TEGRA234_MEMORY_CLIENT_MGBECRD,
 		.name = "mgbecrd",
+		.bpmp_id = TEGRA_ICC_BPMP_EQOS,
+		.type = TEGRA_ICC_NISO,
 		.sid = TEGRA234_SID_MGBE_VF2,
 		.regs = {
 			.sid = {
@@ -43,6 +53,8 @@ static const struct tegra_mc_client tegra234_mc_clients[] = {
 	}, {
 		.id = TEGRA234_MEMORY_CLIENT_MGBEDRD,
 		.name = "mgbedrd",
+		.bpmp_id = TEGRA_ICC_BPMP_EQOS,
+		.type = TEGRA_ICC_NISO,
 		.sid = TEGRA234_SID_MGBE_VF3,
 		.regs = {
 			.sid = {
@@ -52,6 +64,8 @@ static const struct tegra_mc_client tegra234_mc_clients[] = {
 		},
 	}, {
 		.id = TEGRA234_MEMORY_CLIENT_MGBEAWR,
+		.bpmp_id = TEGRA_ICC_BPMP_EQOS,
+		.type = TEGRA_ICC_NISO,
 		.name = "mgbeawr",
 		.sid = TEGRA234_SID_MGBE,
 		.regs = {
@@ -63,6 +77,8 @@ static const struct tegra_mc_client tegra234_mc_clients[] = {
 	}, {
 		.id = TEGRA234_MEMORY_CLIENT_MGBEBWR,
 		.name = "mgbebwr",
+		.bpmp_id = TEGRA_ICC_BPMP_EQOS,
+		.type = TEGRA_ICC_NISO,
 		.sid = TEGRA234_SID_MGBE_VF1,
 		.regs = {
 			.sid = {
@@ -73,6 +89,8 @@ static const struct tegra_mc_client tegra234_mc_clients[] = {
 	}, {
 		.id = TEGRA234_MEMORY_CLIENT_MGBECWR,
 		.name = "mgbecwr",
+		.bpmp_id = TEGRA_ICC_BPMP_EQOS,
+		.type = TEGRA_ICC_NISO,
 		.sid = TEGRA234_SID_MGBE_VF2,
 		.regs = {
 			.sid = {
@@ -83,6 +101,8 @@ static const struct tegra_mc_client tegra234_mc_clients[] = {
 	}, {
 		.id = TEGRA234_MEMORY_CLIENT_SDMMCRAB,
 		.name = "sdmmcrab",
+		.bpmp_id = TEGRA_ICC_BPMP_SDMMC_4,
+		.type = TEGRA_ICC_NISO,
 		.sid = TEGRA234_SID_SDMMC4,
 		.regs = {
 			.sid = {
@@ -93,6 +113,8 @@ static const struct tegra_mc_client tegra234_mc_clients[] = {
 	}, {
 		.id = TEGRA234_MEMORY_CLIENT_MGBEDWR,
 		.name = "mgbedwr",
+		.bpmp_id = TEGRA_ICC_BPMP_EQOS,
+		.type = TEGRA_ICC_NISO,
 		.sid = TEGRA234_SID_MGBE_VF3,
 		.regs = {
 			.sid = {
@@ -103,6 +125,8 @@ static const struct tegra_mc_client tegra234_mc_clients[] = {
 	}, {
 		.id = TEGRA234_MEMORY_CLIENT_SDMMCWAB,
 		.name = "sdmmcwab",
+		.bpmp_id = TEGRA_ICC_BPMP_SDMMC_4,
+		.type = TEGRA_ICC_NISO,
 		.sid = TEGRA234_SID_SDMMC4,
 		.regs = {
 			.sid = {
@@ -153,6 +177,8 @@ static const struct tegra_mc_client tegra234_mc_clients[] = {
 	}, {
 		.id = TEGRA234_MEMORY_CLIENT_APEDMAR,
 		.name = "apedmar",
+		.bpmp_id = TEGRA_ICC_BPMP_APEDMA,
+		.type = TEGRA_ICC_ISO_AUDIO,
 		.sid = TEGRA234_SID_APE,
 		.regs = {
 			.sid = {
@@ -163,6 +189,8 @@ static const struct tegra_mc_client tegra234_mc_clients[] = {
 	}, {
 		.id = TEGRA234_MEMORY_CLIENT_APEDMAW,
 		.name = "apedmaw",
+		.bpmp_id = TEGRA_ICC_BPMP_APEDMA,
+		.type = TEGRA_ICC_ISO_AUDIO,
 		.sid = TEGRA234_SID_APE,
 		.regs = {
 			.sid = {
@@ -333,6 +361,114 @@ static const struct tegra_mc_client tegra234_mc_clients[] = {
 	},
 };
 
+/*
+ * tegra234_mc_icc_set() - Pass MC client info to the BPMP-FW
+ * @src: ICC node for Memory Controller's (MC) Client
+ * @dst: ICC node for Memory Controller (MC)
+ *
+ * Passing the current request info from the MC to the BPMP-FW where
+ * LA and PTSA registers are accessed and the final EMC freq is set
+ * based on client_id, type, latency and bandwidth.
+ * icc_set_bw() makes set_bw calls for both MC and EMC providers in
+ * sequence. Both the calls are protected by 'mutex_lock(&icc_lock)'.
+ * So, the data passed won't be updated by concurrent set calls from
+ * other clients.
+ */
+static int tegra234_mc_icc_set(struct icc_node *src, struct icc_node *dst)
+{
+	struct tegra_mc *mc = icc_provider_to_tegra_mc(dst->provider);
+	struct mrq_bwmgr_int_request bwmgr_req = { 0 };
+	struct mrq_bwmgr_int_response bwmgr_resp = { 0 };
+	const struct tegra_mc_client *pclient = src->data;
+	struct tegra_bpmp_message msg;
+	struct tegra_bpmp *bpmp;
+	int ret;
+
+	/*
+	 * Same Src and Dst node will happen during boot from icc_node_add().
+	 * This can be used to pre-initialize and set bandwidth for all clients
+	 * before their drivers are loaded. We are skipping this case as for us,
+	 * the pre-initialization already happened in Bootloader(MB2) and BPMP-FW.
+	 */
+	if (src->id == dst->id)
+		return 0;
+
+	bpmp = of_tegra_bpmp_get();
+	if (IS_ERR(bpmp)) {
+		ret = PTR_ERR(bpmp);
+		return ret;
+	}
+
+	if (pclient->type == TEGRA_ICC_NISO)
+		bwmgr_req.bwmgr_calc_set_req.niso_bw = src->avg_bw;
+	else
+		bwmgr_req.bwmgr_calc_set_req.iso_bw = src->avg_bw;
+
+	bwmgr_req.bwmgr_calc_set_req.client_id = pclient->bpmp_id;
+
+	bwmgr_req.cmd = CMD_BWMGR_INT_CALC_AND_SET;
+	bwmgr_req.bwmgr_calc_set_req.mc_floor = src->peak_bw;
+	bwmgr_req.bwmgr_calc_set_req.floor_unit = BWMGR_INT_UNIT_KBPS;
+
+	memset(&msg, 0, sizeof(msg));
+	msg.mrq = MRQ_BWMGR_INT;
+	msg.tx.data = &bwmgr_req;
+	msg.tx.size = sizeof(bwmgr_req);
+	msg.rx.data = &bwmgr_resp;
+	msg.rx.size = sizeof(bwmgr_resp);
+
+	ret = tegra_bpmp_transfer(bpmp, &msg);
+	if (ret < 0) {
+		dev_err(mc->dev, "BPMP transfer failed: %d\n", ret);
+		goto error;
+	}
+	if (msg.rx.ret < 0) {
+		pr_err("failed to set bandwidth for %u: %d\n",
+		       bwmgr_req.bwmgr_calc_set_req.client_id, msg.rx.ret);
+		ret = -EINVAL;
+	}
+
+error:
+	tegra_bpmp_put(bpmp);
+	return ret;
+}
+
+static struct icc_node*
+tegra234_mc_of_icc_xlate(struct of_phandle_args *spec, void *data)
+{
+	struct tegra_mc *mc = icc_provider_to_tegra_mc(data);
+	unsigned int cl_id = spec->args[0];
+	struct icc_node *node;
+
+	list_for_each_entry(node, &mc->provider.nodes, node_list) {
+		if (node->id != cl_id)
+			continue;
+
+		return node;
+	}
+
+	/*
+	 * If a client driver calls devm_of_icc_get() before the MC driver
+	 * is probed, then return EPROBE_DEFER to the client driver.
+	 */
+	return ERR_PTR(-EPROBE_DEFER);
+}
+
+static int tegra234_mc_icc_get_init_bw(struct icc_node *node, u32 *avg, u32 *peak)
+{
+	*avg = 0;
+	*peak = 0;
+
+	return 0;
+}
+
+static const struct tegra_mc_icc_ops tegra234_mc_icc_ops = {
+	.xlate = tegra234_mc_of_icc_xlate,
+	.aggregate = icc_std_aggregate,
+	.get_bw = tegra234_mc_icc_get_init_bw,
+	.set = tegra234_mc_icc_set,
+};
+
 const struct tegra_mc_soc tegra234_mc_soc = {
 	.num_clients = ARRAY_SIZE(tegra234_mc_clients),
 	.clients = tegra234_mc_clients,
@@ -345,6 +481,7 @@ const struct tegra_mc_soc tegra234_mc_soc = {
 		   MC_INT_SECURITY_VIOLATION | MC_INT_DECERR_EMEM,
 	.has_addr_hi_reg = true,
 	.ops = &tegra186_mc_ops,
+	.icc_ops = &tegra234_mc_icc_ops,
 	.ch_intmask = 0x0000ff00,
 	.global_intstatus_channel_shift = 8,
 	/*
diff --git a/include/linux/tegra-icc.h b/include/linux/tegra-icc.h
new file mode 100644
index 000000000000..4b4d4bee290c
--- /dev/null
+++ b/include/linux/tegra-icc.h
@@ -0,0 +1,65 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2022-2023 NVIDIA CORPORATION.  All rights reserved.
+ */
+
+#ifndef LINUX_TEGRA_ICC_H
+#define LINUX_TEGRA_ICC_H
+
+enum tegra_icc_client_type {
+	TEGRA_ICC_NONE,
+	TEGRA_ICC_NISO,
+	TEGRA_ICC_ISO_DISPLAY,
+	TEGRA_ICC_ISO_VI,
+	TEGRA_ICC_ISO_AUDIO,
+	TEGRA_ICC_ISO_VIFAL,
+};
+
+/* ICC ID's for MC client's used in BPMP */
+#define TEGRA_ICC_BPMP_DEBUG		1
+#define TEGRA_ICC_BPMP_CPU_CLUSTER0	2
+#define TEGRA_ICC_BPMP_CPU_CLUSTER1	3
+#define TEGRA_ICC_BPMP_CPU_CLUSTER2	4
+#define TEGRA_ICC_BPMP_GPU		5
+#define TEGRA_ICC_BPMP_CACTMON		6
+#define TEGRA_ICC_BPMP_DISPLAY		7
+#define TEGRA_ICC_BPMP_VI		8
+#define TEGRA_ICC_BPMP_EQOS		9
+#define TEGRA_ICC_BPMP_PCIE_0		10
+#define TEGRA_ICC_BPMP_PCIE_1		11
+#define TEGRA_ICC_BPMP_PCIE_2		12
+#define TEGRA_ICC_BPMP_PCIE_3		13
+#define TEGRA_ICC_BPMP_PCIE_4		14
+#define TEGRA_ICC_BPMP_PCIE_5		15
+#define TEGRA_ICC_BPMP_PCIE_6		16
+#define TEGRA_ICC_BPMP_PCIE_7		17
+#define TEGRA_ICC_BPMP_PCIE_8		18
+#define TEGRA_ICC_BPMP_PCIE_9		19
+#define TEGRA_ICC_BPMP_PCIE_10		20
+#define TEGRA_ICC_BPMP_DLA_0		21
+#define TEGRA_ICC_BPMP_DLA_1		22
+#define TEGRA_ICC_BPMP_SDMMC_1		23
+#define TEGRA_ICC_BPMP_SDMMC_2		24
+#define TEGRA_ICC_BPMP_SDMMC_3		25
+#define TEGRA_ICC_BPMP_SDMMC_4		26
+#define TEGRA_ICC_BPMP_NVDEC		27
+#define TEGRA_ICC_BPMP_NVENC		28
+#define TEGRA_ICC_BPMP_NVJPG_0		29
+#define TEGRA_ICC_BPMP_NVJPG_1		30
+#define TEGRA_ICC_BPMP_OFAA		31
+#define TEGRA_ICC_BPMP_XUSB_HOST	32
+#define TEGRA_ICC_BPMP_XUSB_DEV		33
+#define TEGRA_ICC_BPMP_TSEC		34
+#define TEGRA_ICC_BPMP_VIC		35
+#define TEGRA_ICC_BPMP_APE		36
+#define TEGRA_ICC_BPMP_APEDMA		37
+#define TEGRA_ICC_BPMP_SE		38
+#define TEGRA_ICC_BPMP_ISP		39
+#define TEGRA_ICC_BPMP_HDA		40
+#define TEGRA_ICC_BPMP_VIFAL		41
+#define TEGRA_ICC_BPMP_VI2FAL		42
+#define TEGRA_ICC_BPMP_VI2		43
+#define TEGRA_ICC_BPMP_RCE		44
+#define TEGRA_ICC_BPMP_PVA		45
+
+#endif /* LINUX_TEGRA_ICC_H */
diff --git a/include/soc/tegra/mc.h b/include/soc/tegra/mc.h
index 51a2263e1bc5..fefac9622987 100644
--- a/include/soc/tegra/mc.h
+++ b/include/soc/tegra/mc.h
@@ -13,6 +13,7 @@
 #include <linux/irq.h>
 #include <linux/reset-controller.h>
 #include <linux/types.h>
+#include <linux/tegra-icc.h>
 
 struct clk;
 struct device;
@@ -26,6 +27,8 @@ struct tegra_mc_timing {
 
 struct tegra_mc_client {
 	unsigned int id;
+	unsigned int bpmp_id;
+	enum tegra_icc_client_type type;
 	const char *name;
 	/*
 	 * For Tegra210 and earlier, this is the SWGROUP ID used for IOVA translations in the
@@ -166,8 +169,10 @@ struct tegra_mc_icc_ops {
 	int (*set)(struct icc_node *src, struct icc_node *dst);
 	int (*aggregate)(struct icc_node *node, u32 tag, u32 avg_bw,
 			 u32 peak_bw, u32 *agg_avg, u32 *agg_peak);
+	struct icc_node* (*xlate)(struct of_phandle_args *spec, void *data);
 	struct icc_node_data *(*xlate_extended)(struct of_phandle_args *spec,
 						void *data);
+	int (*get_bw)(struct icc_node *node, u32 *avg, u32 *peak);
 };
 
 struct tegra_mc_ops {
-- 
2.17.1

[Patch v2 3/9] memory: tegra: add mc clients for Tegra234

[Sumit Gupta]

Add few Isochronous (ISO) and Non-ISO MC clients.
ISO clients have guaranteed bandwidth requirement.
PCIE clients added to the mc_clients table represent
each controller in Tegra234.

Signed-off-by: Sumit Gupta <sumitg@nvidia.com>
---
 drivers/memory/tegra/tegra234.c | 420 ++++++++++++++++++++++++++++++++
 1 file changed, 420 insertions(+)

diff --git a/drivers/memory/tegra/tegra234.c b/drivers/memory/tegra/tegra234.c
index b40229926558..7ca744036f59 100644
--- a/drivers/memory/tegra/tegra234.c
+++ b/drivers/memory/tegra/tegra234.c
@@ -15,6 +15,30 @@
 
 static const struct tegra_mc_client tegra234_mc_clients[] = {
 	{
+		.id = TEGRA234_MEMORY_CLIENT_HDAR,
+		.name = "hdar",
+		.bpmp_id = TEGRA_ICC_BPMP_HDA,
+		.type = TEGRA_ICC_ISO_AUDIO,
+		.sid = TEGRA234_SID_HDA,
+		.regs = {
+			.sid = {
+				.override = 0xa8,
+				.security = 0xac,
+			},
+		},
+	}, {
+		.id = TEGRA234_MEMORY_CLIENT_HDAW,
+		.name = "hdaw",
+		.bpmp_id = TEGRA_ICC_BPMP_HDA,
+		.type = TEGRA_ICC_ISO_AUDIO,
+		.sid = TEGRA234_SID_HDA,
+		.regs = {
+			.sid = {
+				.override = 0x1a8,
+				.security = 0x1ac,
+			},
+		},
+	}, {
 		.id = TEGRA234_MEMORY_CLIENT_MGBEARD,
 		.name = "mgbeard",
 		.bpmp_id = TEGRA_ICC_BPMP_EQOS,
@@ -134,6 +158,90 @@ static const struct tegra_mc_client tegra234_mc_clients[] = {
 				.security = 0x33c,
 			},
 		},
+	}, {
+		.id = TEGRA234_MEMORY_CLIENT_VI2W,
+		.name = "vi2w",
+		.bpmp_id = TEGRA_ICC_BPMP_VI2,
+		.type = TEGRA_ICC_ISO_VI,
+		.sid = TEGRA234_SID_ISO_VI2,
+		.regs = {
+			.sid = {
+				.override = 0x380,
+				.security = 0x384,
+			},
+		},
+	}, {
+		.id = TEGRA234_MEMORY_CLIENT_VI2FALR,
+		.name = "vi2falr",
+		.bpmp_id = TEGRA_ICC_BPMP_VI2FAL,
+		.type = TEGRA_ICC_ISO_VIFAL,
+		.sid = TEGRA234_SID_ISO_VI2FALC,
+		.regs = {
+			.sid = {
+				.override = 0x388,
+				.security = 0x38c,
+			},
+		},
+	}, {
+		.id = TEGRA234_MEMORY_CLIENT_VI2FALW,
+		.name = "vi2falw",
+		.bpmp_id = TEGRA_ICC_BPMP_VI2FAL,
+		.type = TEGRA_ICC_ISO_VIFAL,
+		.sid = TEGRA234_SID_ISO_VI2FALC,
+		.regs = {
+			.sid = {
+				.override = 0x3e0,
+				.security = 0x3e4,
+			},
+		},
+	}, {
+		.id = TEGRA234_MEMORY_CLIENT_APER,
+		.name = "aper",
+		.bpmp_id = TEGRA_ICC_BPMP_APE,
+		.type = TEGRA_ICC_ISO_AUDIO,
+		.sid = TEGRA234_SID_APE,
+		.regs = {
+			.sid = {
+				.override = 0x3d0,
+				.security = 0x3d4,
+			},
+		},
+	}, {
+		.id = TEGRA234_MEMORY_CLIENT_APEW,
+		.name = "apew",
+		.bpmp_id = TEGRA_ICC_BPMP_APE,
+		.type = TEGRA_ICC_ISO_AUDIO,
+		.sid = TEGRA234_SID_APE,
+		.regs = {
+			.sid = {
+				.override = 0x3d8,
+				.security = 0x3dc,
+			},
+		},
+	}, {
+		.id = TEGRA234_MEMORY_CLIENT_NVDISPLAYR,
+		.name = "nvdisplayr",
+		.bpmp_id = TEGRA_ICC_BPMP_DISPLAY,
+		.type = TEGRA_ICC_ISO_DISPLAY,
+		.sid = TEGRA234_SID_ISO_NVDISPLAY,
+		.regs = {
+			.sid = {
+				.override = 0x490,
+				.security = 0x494,
+			},
+		},
+	}, {
+		.id = TEGRA234_MEMORY_CLIENT_NVDISPLAYR1,
+		.name = "nvdisplayr1",
+		.bpmp_id = TEGRA_ICC_BPMP_DISPLAY,
+		.type = TEGRA_ICC_ISO_DISPLAY,
+		.sid = TEGRA234_SID_ISO_NVDISPLAY,
+		.regs = {
+			.sid = {
+				.override = 0x508,
+				.security = 0x50c,
+			},
+		},
 	}, {
 		.id = TEGRA234_MEMORY_CLIENT_BPMPR,
 		.name = "bpmpr",
@@ -358,6 +466,318 @@ static const struct tegra_mc_client tegra234_mc_clients[] = {
 				.security = 0x37c,
 			},
 		},
+	}, {
+		.id = TEGRA234_MEMORY_CLIENT_PCIE0R,
+		.name = "pcie0r",
+		.bpmp_id = TEGRA_ICC_BPMP_PCIE_0,
+		.type = TEGRA_ICC_NISO,
+		.sid = TEGRA234_SID_PCIE0,
+		.regs = {
+			.sid = {
+				.override = 0x6c0,
+				.security = 0x6c4,
+			},
+		},
+	}, {
+		.id = TEGRA234_MEMORY_CLIENT_PCIE0W,
+		.name = "pcie0w",
+		.bpmp_id = TEGRA_ICC_BPMP_PCIE_0,
+		.type = TEGRA_ICC_NISO,
+		.sid = TEGRA234_SID_PCIE0,
+		.regs = {
+			.sid = {
+				.override = 0x6c8,
+				.security = 0x6cc,
+			},
+		},
+	}, {
+		.id = TEGRA234_MEMORY_CLIENT_PCIE1R,
+		.name = "pcie1r",
+		.bpmp_id = TEGRA_ICC_BPMP_PCIE_1,
+		.type = TEGRA_ICC_NISO,
+		.sid = TEGRA234_SID_PCIE1,
+		.regs = {
+			.sid = {
+				.override = 0x6d0,
+				.security = 0x6d4,
+			},
+		},
+	}, {
+		.id = TEGRA234_MEMORY_CLIENT_PCIE1W,
+		.name = "pcie1w",
+		.bpmp_id = TEGRA_ICC_BPMP_PCIE_1,
+		.type = TEGRA_ICC_NISO,
+		.sid = TEGRA234_SID_PCIE1,
+		.regs = {
+			.sid = {
+				.override = 0x6d8,
+				.security = 0x6dc,
+			},
+		},
+	}, {
+		.id = TEGRA234_MEMORY_CLIENT_PCIE2AR,
+		.name = "pcie2ar",
+		.bpmp_id = TEGRA_ICC_BPMP_PCIE_2,
+		.type = TEGRA_ICC_NISO,
+		.sid = TEGRA234_SID_PCIE2,
+		.regs = {
+			.sid = {
+				.override = 0x6e0,
+				.security = 0x6e4,
+			},
+		},
+	}, {
+		.id = TEGRA234_MEMORY_CLIENT_PCIE2AW,
+		.name = "pcie2aw",
+		.bpmp_id = TEGRA_ICC_BPMP_PCIE_2,
+		.type = TEGRA_ICC_NISO,
+		.sid = TEGRA234_SID_PCIE2,
+		.regs = {
+			.sid = {
+				.override = 0x6e8,
+				.security = 0x6ec,
+			},
+		},
+	}, {
+		.id = TEGRA234_MEMORY_CLIENT_PCIE3R,
+		.name = "pcie3r",
+		.bpmp_id = TEGRA_ICC_BPMP_PCIE_3,
+		.type = TEGRA_ICC_NISO,
+		.sid = TEGRA234_SID_PCIE3,
+		.regs = {
+			.sid = {
+				.override = 0x6f0,
+				.security = 0x6f4,
+			},
+		},
+	}, {
+		.id = TEGRA234_MEMORY_CLIENT_PCIE3W,
+		.name = "pcie3w",
+		.bpmp_id = TEGRA_ICC_BPMP_PCIE_3,
+		.type = TEGRA_ICC_NISO,
+		.sid = TEGRA234_SID_PCIE3,
+		.regs = {
+			.sid = {
+				.override = 0x6f8,
+				.security = 0x6fc,
+			},
+		},
+	}, {
+		.id = TEGRA234_MEMORY_CLIENT_PCIE4R,
+		.name = "pcie4r",
+		.bpmp_id = TEGRA_ICC_BPMP_PCIE_4,
+		.type = TEGRA_ICC_NISO,
+		.sid = TEGRA234_SID_PCIE4,
+		.regs = {
+			.sid = {
+				.override = 0x700,
+				.security = 0x704,
+			},
+		},
+	}, {
+		.id = TEGRA234_MEMORY_CLIENT_PCIE4W,
+		.name = "pcie4w",
+		.bpmp_id = TEGRA_ICC_BPMP_PCIE_4,
+		.type = TEGRA_ICC_NISO,
+		.sid = TEGRA234_SID_PCIE4,
+		.regs = {
+			.sid = {
+				.override = 0x708,
+				.security = 0x70c,
+			},
+		},
+	}, {
+		.id = TEGRA234_MEMORY_CLIENT_PCIE5R,
+		.name = "pcie5r",
+		.bpmp_id = TEGRA_ICC_BPMP_PCIE_5,
+		.type = TEGRA_ICC_NISO,
+		.sid = TEGRA234_SID_PCIE5,
+		.regs = {
+			.sid = {
+				.override = 0x710,
+				.security = 0x714,
+			},
+		},
+	}, {
+		.id = TEGRA234_MEMORY_CLIENT_PCIE5W,
+		.name = "pcie5w",
+		.bpmp_id = TEGRA_ICC_BPMP_PCIE_5,
+		.type = TEGRA_ICC_NISO,
+		.sid = TEGRA234_SID_PCIE5,
+		.regs = {
+			.sid = {
+				.override = 0x718,
+				.security = 0x71c,
+			},
+		},
+	}, {
+		.id = TEGRA234_MEMORY_CLIENT_PCIE5R1,
+		.name = "pcie5r1",
+		.bpmp_id = TEGRA_ICC_BPMP_PCIE_5,
+		.type = TEGRA_ICC_NISO,
+		.sid = TEGRA234_SID_PCIE5,
+		.regs = {
+			.sid = {
+				.override = 0x778,
+				.security = 0x77c,
+			},
+		},
+	}, {
+		.id = TEGRA234_MEMORY_CLIENT_PCIE6AR,
+		.name = "pcie6ar",
+		.bpmp_id = TEGRA_ICC_BPMP_PCIE_6,
+		.type = TEGRA_ICC_NISO,
+		.sid = TEGRA234_SID_PCIE6,
+		.regs = {
+			.sid = {
+				.override = 0x140,
+				.security = 0x144,
+			},
+		},
+	}, {
+		.id = TEGRA234_MEMORY_CLIENT_PCIE6AW,
+		.name = "pcie6aw",
+		.bpmp_id = TEGRA_ICC_BPMP_PCIE_6,
+		.type = TEGRA_ICC_NISO,
+		.sid = TEGRA234_SID_PCIE6,
+		.regs = {
+			.sid = {
+				.override = 0x148,
+				.security = 0x14c,
+			},
+		},
+	}, {
+		.id = TEGRA234_MEMORY_CLIENT_PCIE6AR1,
+		.name = "pcie6ar1",
+		.bpmp_id = TEGRA_ICC_BPMP_PCIE_6,
+		.type = TEGRA_ICC_NISO,
+		.sid = TEGRA234_SID_PCIE6,
+		.regs = {
+			.sid = {
+				.override = 0x1e8,
+				.security = 0x1ec,
+			},
+		},
+	}, {
+		.id = TEGRA234_MEMORY_CLIENT_PCIE7AR,
+		.name = "pcie7ar",
+		.bpmp_id = TEGRA_ICC_BPMP_PCIE_7,
+		.type = TEGRA_ICC_NISO,
+		.sid = TEGRA234_SID_PCIE7,
+		.regs = {
+			.sid = {
+				.override = 0x150,
+				.security = 0x154,
+			},
+		},
+	}, {
+		.id = TEGRA234_MEMORY_CLIENT_PCIE7AW,
+		.name = "pcie7aw",
+		.bpmp_id = TEGRA_ICC_BPMP_PCIE_7,
+		.type = TEGRA_ICC_NISO,
+		.sid = TEGRA234_SID_PCIE7,
+		.regs = {
+			.sid = {
+				.override = 0x180,
+				.security = 0x184,
+			},
+		},
+	}, {
+		.id = TEGRA234_MEMORY_CLIENT_PCIE7AR1,
+		.name = "pcie7ar1",
+		.bpmp_id = TEGRA_ICC_BPMP_PCIE_7,
+		.type = TEGRA_ICC_NISO,
+		.sid = TEGRA234_SID_PCIE7,
+		.regs = {
+			.sid = {
+				.override = 0x248,
+				.security = 0x24c,
+			},
+		},
+	}, {
+		.id = TEGRA234_MEMORY_CLIENT_PCIE8AR,
+		.name = "pcie8ar",
+		.bpmp_id = TEGRA_ICC_BPMP_PCIE_8,
+		.type = TEGRA_ICC_NISO,
+		.sid = TEGRA234_SID_PCIE8,
+		.regs = {
+			.sid = {
+				.override = 0x190,
+				.security = 0x194,
+			},
+		},
+	}, {
+		.id = TEGRA234_MEMORY_CLIENT_PCIE8AW,
+		.name = "pcie8aw",
+		.bpmp_id = TEGRA_ICC_BPMP_PCIE_8,
+		.type = TEGRA_ICC_NISO,
+		.sid = TEGRA234_SID_PCIE8,
+		.regs = {
+			.sid = {
+				.override = 0x1d8,
+				.security = 0x1dc,
+			},
+		},
+	}, {
+		.id = TEGRA234_MEMORY_CLIENT_PCIE9AR,
+		.name = "pcie9ar",
+		.bpmp_id = TEGRA_ICC_BPMP_PCIE_9,
+		.type = TEGRA_ICC_NISO,
+		.sid = TEGRA234_SID_PCIE9,
+		.regs = {
+			.sid = {
+				.override = 0x1e0,
+				.security = 0x1e4,
+			},
+		},
+	}, {
+		.id = TEGRA234_MEMORY_CLIENT_PCIE9AW,
+		.name = "pcie9aw",
+		.bpmp_id = TEGRA_ICC_BPMP_PCIE_9,
+		.type = TEGRA_ICC_NISO,
+		.sid = TEGRA234_SID_PCIE9,
+		.regs = {
+			.sid = {
+				.override = 0x1f0,
+				.security = 0x1f4,
+			},
+		},
+	}, {
+		.id = TEGRA234_MEMORY_CLIENT_PCIE10AR,
+		.name = "pcie10ar",
+		.bpmp_id = TEGRA_ICC_BPMP_PCIE_10,
+		.type = TEGRA_ICC_NISO,
+		.sid = TEGRA234_SID_PCIE10,
+		.regs = {
+			.sid = {
+				.override = 0x1f8,
+				.security = 0x1fc,
+			},
+		},
+	}, {
+		.id = TEGRA234_MEMORY_CLIENT_PCIE10AW,
+		.name = "pcie10aw",
+		.bpmp_id = TEGRA_ICC_BPMP_PCIE_10,
+		.type = TEGRA_ICC_NISO,
+		.sid = TEGRA234_SID_PCIE10,
+		.regs = {
+			.sid = {
+				.override = 0x200,
+				.security = 0x204,
+			},
+		},
+	}, {
+		.id = TEGRA234_MEMORY_CLIENT_PCIE10AR1,
+		.name = "pcie10ar1",
+		.bpmp_id = TEGRA_ICC_BPMP_PCIE_10,
+		.type = TEGRA_ICC_NISO,
+		.sid = TEGRA234_SID_PCIE10,
+		.regs = {
+			.sid = {
+				.override = 0x240,
+				.security = 0x244,
+			},
+		},
 	},
 };
 
-- 
2.17.1

[Patch v2 4/9] memory: tegra: add software mc clients in Tegra234

[Sumit Gupta]

Add dummy Memory Controller clients to represent CPU clusters.
They will be used by the CPUFREQ driver to scale DRAM FREQ
with the CPU FREQ.
---
 drivers/memory/tegra/tegra234.c | 15 +++++++++++++++
 1 file changed, 15 insertions(+)

diff --git a/drivers/memory/tegra/tegra234.c b/drivers/memory/tegra/tegra234.c
index 7ca744036f59..0c666e52bf46 100644
--- a/drivers/memory/tegra/tegra234.c
+++ b/drivers/memory/tegra/tegra234.c
@@ -778,6 +778,21 @@ static const struct tegra_mc_client tegra234_mc_clients[] = {
 				.security = 0x244,
 			},
 		},
+	}, {
+		.id = TEGRA_ICC_MC_CPU_CLUSTER0,
+		.name = "sw_cluster0",
+		.bpmp_id = TEGRA_ICC_BPMP_CPU_CLUSTER0,
+		.type = TEGRA_ICC_NISO,
+	}, {
+		.id = TEGRA_ICC_MC_CPU_CLUSTER1,
+		.name = "sw_cluster1",
+		.bpmp_id = TEGRA_ICC_BPMP_CPU_CLUSTER1,
+		.type = TEGRA_ICC_NISO,
+	}, {
+		.id = TEGRA_ICC_MC_CPU_CLUSTER2,
+		.name = "sw_cluster2",
+		.bpmp_id = TEGRA_ICC_BPMP_CPU_CLUSTER2,
+		.type = TEGRA_ICC_NISO,
 	},
 };
 
-- 
2.17.1

[Patch v2 5/9] dt-bindings: tegra: add icc ids for dummy MC clients

[Sumit Gupta]

Add ICC id's for dummy software clients representing CCPLEX clusters.

Signed-off-by: Sumit Gupta <sumitg@nvidia.com>
Acked-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
---
 include/dt-bindings/memory/tegra234-mc.h | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/include/dt-bindings/memory/tegra234-mc.h b/include/dt-bindings/memory/tegra234-mc.h
index 347e55e89a2a..6e60d55491b3 100644
--- a/include/dt-bindings/memory/tegra234-mc.h
+++ b/include/dt-bindings/memory/tegra234-mc.h
@@ -536,4 +536,9 @@
 #define TEGRA234_MEMORY_CLIENT_NVJPG1SRD 0x123
 #define TEGRA234_MEMORY_CLIENT_NVJPG1SWR 0x124
 
+/* ICC ID's for dummy MC clients used to represent CPU Clusters */
+#define TEGRA_ICC_MC_CPU_CLUSTER0       1003
+#define TEGRA_ICC_MC_CPU_CLUSTER1       1004
+#define TEGRA_ICC_MC_CPU_CLUSTER2       1005
+
 #endif
-- 
2.17.1

[Patch v2 6/9] arm64: tegra: Add cpu OPP tables and interconnects property

[Sumit Gupta]

Add OPP table and interconnects property to scale DDR frequency with
CPU frequency for better performance. Each operating point entry of
the OPP table has CPU freq to per MC channel bandwidth mapping.
One table is added for each cluster even though the table data is
same because the bandwidth request is per cluster. This is done
because OPP framework creates a single icc path and hence single
bandwidth request if the table is marked as 'opp-shared' and shared
among all clusters. For us, the OPP table data is same but the MC
Client ID argument to interconnects property is different for each
cluster. So, having per cluster table makes different icc path for
each cluster and helps to make per cluster BW requests.

Signed-off-by: Sumit Gupta <sumitg@nvidia.com>
---
 arch/arm64/boot/dts/nvidia/tegra234.dtsi | 276 +++++++++++++++++++++++
 1 file changed, 276 insertions(+)

diff --git a/arch/arm64/boot/dts/nvidia/tegra234.dtsi b/arch/arm64/boot/dts/nvidia/tegra234.dtsi
index 8fe8eda7654d..e995df13277d 100644
--- a/arch/arm64/boot/dts/nvidia/tegra234.dtsi
+++ b/arch/arm64/boot/dts/nvidia/tegra234.dtsi
@@ -3013,6 +3013,9 @@
 
 			enable-method = "psci";
 
+			operating-points-v2 = <&cl0_opp_tbl>;
+			interconnects = <&mc TEGRA_ICC_MC_CPU_CLUSTER0 &emc>;
+
 			i-cache-size = <65536>;
 			i-cache-line-size = <64>;
 			i-cache-sets = <256>;
@@ -3029,6 +3032,9 @@
 
 			enable-method = "psci";
 
+			operating-points-v2 = <&cl0_opp_tbl>;
+			interconnects = <&mc TEGRA_ICC_MC_CPU_CLUSTER0 &emc>;
+
 			i-cache-size = <65536>;
 			i-cache-line-size = <64>;
 			i-cache-sets = <256>;
@@ -3045,6 +3051,9 @@
 
 			enable-method = "psci";
 
+			operating-points-v2 = <&cl0_opp_tbl>;
+			interconnects = <&mc TEGRA_ICC_MC_CPU_CLUSTER0 &emc>;
+
 			i-cache-size = <65536>;
 			i-cache-line-size = <64>;
 			i-cache-sets = <256>;
@@ -3061,6 +3070,9 @@
 
 			enable-method = "psci";
 
+			operating-points-v2 = <&cl0_opp_tbl>;
+			interconnects = <&mc TEGRA_ICC_MC_CPU_CLUSTER0 &emc>;
+
 			i-cache-size = <65536>;
 			i-cache-line-size = <64>;
 			i-cache-sets = <256>;
@@ -3077,6 +3089,9 @@
 
 			enable-method = "psci";
 
+			operating-points-v2 = <&cl1_opp_tbl>;
+			interconnects = <&mc TEGRA_ICC_MC_CPU_CLUSTER1 &emc>;
+
 			i-cache-size = <65536>;
 			i-cache-line-size = <64>;
 			i-cache-sets = <256>;
@@ -3093,6 +3108,9 @@
 
 			enable-method = "psci";
 
+			operating-points-v2 = <&cl1_opp_tbl>;
+			interconnects = <&mc TEGRA_ICC_MC_CPU_CLUSTER1 &emc>;
+
 			i-cache-size = <65536>;
 			i-cache-line-size = <64>;
 			i-cache-sets = <256>;
@@ -3109,6 +3127,9 @@
 
 			enable-method = "psci";
 
+			operating-points-v2 = <&cl1_opp_tbl>;
+			interconnects = <&mc TEGRA_ICC_MC_CPU_CLUSTER1 &emc>;
+
 			i-cache-size = <65536>;
 			i-cache-line-size = <64>;
 			i-cache-sets = <256>;
@@ -3125,6 +3146,9 @@
 
 			enable-method = "psci";
 
+			operating-points-v2 = <&cl1_opp_tbl>;
+			interconnects = <&mc TEGRA_ICC_MC_CPU_CLUSTER1 &emc>;
+
 			i-cache-size = <65536>;
 			i-cache-line-size = <64>;
 			i-cache-sets = <256>;
@@ -3141,6 +3165,9 @@
 
 			enable-method = "psci";
 
+			operating-points-v2 = <&cl2_opp_tbl>;
+			interconnects = <&mc TEGRA_ICC_MC_CPU_CLUSTER2 &emc>;
+
 			i-cache-size = <65536>;
 			i-cache-line-size = <64>;
 			i-cache-sets = <256>;
@@ -3157,6 +3184,9 @@
 
 			enable-method = "psci";
 
+			operating-points-v2 = <&cl2_opp_tbl>;
+			interconnects = <&mc TEGRA_ICC_MC_CPU_CLUSTER2 &emc>;
+
 			i-cache-size = <65536>;
 			i-cache-line-size = <64>;
 			i-cache-sets = <256>;
@@ -3173,6 +3203,9 @@
 
 			enable-method = "psci";
 
+			operating-points-v2 = <&cl2_opp_tbl>;
+			interconnects = <&mc TEGRA_ICC_MC_CPU_CLUSTER2 &emc>;
+
 			i-cache-size = <65536>;
 			i-cache-line-size = <64>;
 			i-cache-sets = <256>;
@@ -3189,6 +3222,9 @@
 
 			enable-method = "psci";
 
+			operating-points-v2 = <&cl2_opp_tbl>;
+			interconnects = <&mc TEGRA_ICC_MC_CPU_CLUSTER2 &emc>;
+
 			i-cache-size = <65536>;
 			i-cache-line-size = <64>;
 			i-cache-sets = <256>;
@@ -3445,4 +3481,244 @@
 		interrupt-parent = <&gic>;
 		always-on;
 	};
+
+	cl0_opp_tbl: opp-table-cluster0 {
+		compatible = "operating-points-v2";
+		opp-shared;
+
+		cl0_ch1_opp1: opp-115200000 {
+			  opp-hz = /bits/ 64 <115200000>;
+			  opp-peak-kBps = <816000>;
+		};
+
+		cl0_ch1_opp2: opp-268800000 {
+			opp-hz = /bits/ 64 <268800000>;
+			opp-peak-kBps = <816000>;
+		};
+
+		cl0_ch1_opp3: opp-422400000 {
+			opp-hz = /bits/ 64 <422400000>;
+			opp-peak-kBps = <816000>;
+		};
+
+		cl0_ch1_opp4: opp-576000000 {
+			opp-hz = /bits/ 64 <576000000>;
+			opp-peak-kBps = <816000>;
+		};
+
+		cl0_ch1_opp5: opp-729600000 {
+			opp-hz = /bits/ 64 <729600000>;
+			opp-peak-kBps = <816000>;
+		};
+
+		cl0_ch1_opp6: opp-883200000 {
+			opp-hz = /bits/ 64 <883200000>;
+			opp-peak-kBps = <816000>;
+		};
+
+		cl0_ch1_opp7: opp-1036800000 {
+			opp-hz = /bits/ 64 <1036800000>;
+			opp-peak-kBps = <816000>;
+		};
+
+		cl0_ch1_opp8: opp-1190400000 {
+			opp-hz = /bits/ 64 <1190400000>;
+			opp-peak-kBps = <816000>;
+		};
+
+		cl0_ch1_opp9: opp-1344000000 {
+			opp-hz = /bits/ 64 <1344000000>;
+			opp-peak-kBps = <1632000>;
+		};
+
+		cl0_ch1_opp10: opp-1497600000 {
+			opp-hz = /bits/ 64 <1497600000>;
+			opp-peak-kBps = <1632000>;
+		};
+
+		cl0_ch1_opp11: opp-1651200000 {
+			opp-hz = /bits/ 64 <1651200000>;
+			opp-peak-kBps = <2660000>;
+		};
+
+		cl0_ch1_opp12: opp-1804800000 {
+			opp-hz = /bits/ 64 <1804800000>;
+			opp-peak-kBps = <2660000>;
+		};
+
+		cl0_ch1_opp13: opp-1958400000 {
+			opp-hz = /bits/ 64 <1958400000>;
+			opp-peak-kBps = <3200000>;
+		};
+
+		cl0_ch1_opp14: opp-2112000000 {
+			opp-hz = /bits/ 64 <2112000000>;
+			opp-peak-kBps = <6400000>;
+		};
+
+		cl0_ch1_opp15: opp-2201600000 {
+			opp-hz = /bits/ 64 <2201600000>;
+			opp-peak-kBps = <6400000>;
+		};
+	};
+
+	cl1_opp_tbl: opp-table-cluster1 {
+		compatible = "operating-points-v2";
+		opp-shared;
+
+		cl1_ch1_opp1: opp-115200000 {
+			  opp-hz = /bits/ 64 <115200000>;
+			  opp-peak-kBps = <816000>;
+		};
+
+		cl1_ch1_opp2: opp-268800000 {
+			opp-hz = /bits/ 64 <268800000>;
+			opp-peak-kBps = <816000>;
+		};
+
+		cl1_ch1_opp3: opp-422400000 {
+			opp-hz = /bits/ 64 <422400000>;
+			opp-peak-kBps = <816000>;
+		};
+
+		cl1_ch1_opp4: opp-576000000 {
+			opp-hz = /bits/ 64 <576000000>;
+			opp-peak-kBps = <816000>;
+		};
+
+		cl1_ch1_opp5: opp-729600000 {
+			opp-hz = /bits/ 64 <729600000>;
+			opp-peak-kBps = <816000>;
+		};
+
+		cl1_ch1_opp6: opp-883200000 {
+			opp-hz = /bits/ 64 <883200000>;
+			opp-peak-kBps = <816000>;
+		};
+
+		cl1_ch1_opp7: opp-1036800000 {
+			opp-hz = /bits/ 64 <1036800000>;
+			opp-peak-kBps = <816000>;
+		};
+
+		cl1_ch1_opp8: opp-1190400000 {
+			opp-hz = /bits/ 64 <1190400000>;
+			opp-peak-kBps = <816000>;
+		};
+
+		cl1_ch1_opp9: opp-1344000000 {
+			opp-hz = /bits/ 64 <1344000000>;
+			opp-peak-kBps = <1632000>;
+		};
+
+		cl1_ch1_opp10: opp-1497600000 {
+			opp-hz = /bits/ 64 <1497600000>;
+			opp-peak-kBps = <1632000>;
+		};
+
+		cl1_ch1_opp11: opp-1651200000 {
+			opp-hz = /bits/ 64 <1651200000>;
+			opp-peak-kBps = <2660000>;
+		};
+
+		cl1_ch1_opp12: opp-1804800000 {
+			opp-hz = /bits/ 64 <1804800000>;
+			opp-peak-kBps = <2660000>;
+		};
+
+		cl1_ch1_opp13: opp-1958400000 {
+			opp-hz = /bits/ 64 <1958400000>;
+			opp-peak-kBps = <3200000>;
+		};
+
+		cl1_ch1_opp14: opp-2112000000 {
+			opp-hz = /bits/ 64 <2112000000>;
+			opp-peak-kBps = <6400000>;
+		};
+
+		cl1_ch1_opp15: opp-2201600000 {
+			opp-hz = /bits/ 64 <2201600000>;
+			opp-peak-kBps = <6400000>;
+		};
+	};
+
+	cl2_opp_tbl: opp-table-cluster2 {
+		compatible = "operating-points-v2";
+		opp-shared;
+
+		cl2_ch1_opp1: opp-115200000 {
+			  opp-hz = /bits/ 64 <115200000>;
+			  opp-peak-kBps = <816000>;
+		};
+
+		cl2_ch1_opp2: opp-268800000 {
+			opp-hz = /bits/ 64 <268800000>;
+			opp-peak-kBps = <816000>;
+		};
+
+		cl2_ch1_opp3: opp-422400000 {
+			opp-hz = /bits/ 64 <422400000>;
+			opp-peak-kBps = <816000>;
+		};
+
+		cl2_ch1_opp4: opp-576000000 {
+			opp-hz = /bits/ 64 <576000000>;
+			opp-peak-kBps = <816000>;
+		};
+
+		cl2_ch1_opp5: opp-729600000 {
+			opp-hz = /bits/ 64 <729600000>;
+			opp-peak-kBps = <816000>;
+		};
+
+		cl2_ch1_opp6: opp-883200000 {
+			opp-hz = /bits/ 64 <883200000>;
+			opp-peak-kBps = <816000>;
+		};
+
+		cl2_ch1_opp7: opp-1036800000 {
+			opp-hz = /bits/ 64 <1036800000>;
+			opp-peak-kBps = <816000>;
+		};
+
+		cl2_ch1_opp8: opp-1190400000 {
+			opp-hz = /bits/ 64 <1190400000>;
+			opp-peak-kBps = <816000>;
+		};
+
+		cl2_ch1_opp9: opp-1344000000 {
+			opp-hz = /bits/ 64 <1344000000>;
+			opp-peak-kBps = <1632000>;
+		};
+
+		cl2_ch1_opp10: opp-1497600000 {
+			opp-hz = /bits/ 64 <1497600000>;
+			opp-peak-kBps = <1632000>;
+		};
+
+		cl2_ch1_opp11: opp-1651200000 {
+			opp-hz = /bits/ 64 <1651200000>;
+			opp-peak-kBps = <2660000>;
+		};
+
+		cl2_ch1_opp12: opp-1804800000 {
+			opp-hz = /bits/ 64 <1804800000>;
+			opp-peak-kBps = <2660000>;
+		};
+
+		cl2_ch1_opp13: opp-1958400000 {
+			opp-hz = /bits/ 64 <1958400000>;
+			opp-peak-kBps = <3200000>;
+		};
+
+		cl2_ch1_opp14: opp-2112000000 {
+			opp-hz = /bits/ 64 <2112000000>;
+			opp-peak-kBps = <6400000>;
+		};
+
+		cl2_ch1_opp15: opp-2201600000 {
+			opp-hz = /bits/ 64 <2201600000>;
+			opp-peak-kBps = <6400000>;
+		};
+	};
 };
-- 
2.17.1

[Patch v2 7/9] cpufreq: tegra194: add OPP support and set bandwidth

[Sumit Gupta]

Add support to use OPP table from DT in Tegra194 cpufreq driver.
Tegra SoC's receive the frequency lookup table (LUT) from BPMP-FW.
Cross check the OPP's present in DT against the LUT from BPMP-FW
and enable only those DT OPP's which are present in LUT also.

The OPP table in DT has CPU Frequency to bandwidth mapping where
the bandwidth value is per MC channel. DRAM bandwidth depends on the
number of MC channels which can vary as per the boot configuration.
This per channel bandwidth from OPP table will be later converted by
MC driver to final bandwidth value by multiplying with number of
channels before sending the request to BPMP-FW.

If OPP table is not present in DT, then use the LUT from BPMP-FW
directy as the CPU frequency table and not do the DRAM frequency
scaling which is same as the current behavior.

Now, as the CPU Frequency table is being controlling through OPP
table in DT. Keeping fewer entries in the table will create less
frequency steps and can help to scale fast to high frequencies
when required.

Signed-off-by: Sumit Gupta <sumitg@nvidia.com>
---
 drivers/cpufreq/tegra194-cpufreq.c | 152 ++++++++++++++++++++++++++---
 1 file changed, 139 insertions(+), 13 deletions(-)

diff --git a/drivers/cpufreq/tegra194-cpufreq.c b/drivers/cpufreq/tegra194-cpufreq.c
index 5890e25d7f77..cda1ab12cdde 100644
--- a/drivers/cpufreq/tegra194-cpufreq.c
+++ b/drivers/cpufreq/tegra194-cpufreq.c
@@ -12,6 +12,7 @@
 #include <linux/of_platform.h>
 #include <linux/platform_device.h>
 #include <linux/slab.h>
+#include <linux/units.h>
 
 #include <asm/smp_plat.h>
 
@@ -65,12 +66,32 @@ struct tegra_cpufreq_soc {
 
 struct tegra194_cpufreq_data {
 	void __iomem *regs;
-	struct cpufreq_frequency_table **tables;
+	struct cpufreq_frequency_table **bpmp_luts;
 	const struct tegra_cpufreq_soc *soc;
+	bool icc_dram_bw_scaling;
 };
 
 static struct workqueue_struct *read_counters_wq;
 
+static int tegra_cpufreq_set_bw(struct cpufreq_policy *policy, unsigned long freq_khz)
+{
+	struct dev_pm_opp *opp;
+	struct device *dev;
+	int ret;
+
+	dev = get_cpu_device(policy->cpu);
+	if (!dev)
+		return -ENODEV;
+
+	opp = dev_pm_opp_find_freq_exact(dev, freq_khz * KHZ, true);
+	if (IS_ERR(opp))
+		return PTR_ERR(opp);
+
+	ret = dev_pm_opp_set_opp(dev, opp);
+	dev_pm_opp_put(opp);
+	return ret;
+}
+
 static void tegra_get_cpu_mpidr(void *mpidr)
 {
 	*((u64 *)mpidr) = read_cpuid_mpidr() & MPIDR_HWID_BITMASK;
@@ -354,7 +375,7 @@ static unsigned int tegra194_get_speed(u32 cpu)
 	 * to the last written ndiv value from freq_table. This is
 	 * done to return consistent value.
 	 */
-	cpufreq_for_each_valid_entry(pos, data->tables[clusterid]) {
+	cpufreq_for_each_valid_entry(pos, data->bpmp_luts[clusterid]) {
 		if (pos->driver_data != ndiv)
 			continue;
 
@@ -369,16 +390,93 @@ static unsigned int tegra194_get_speed(u32 cpu)
 	return rate;
 }
 
+int tegra_cpufreq_init_cpufreq_table(struct cpufreq_policy *policy,
+				     struct cpufreq_frequency_table *bpmp_lut,
+				     struct cpufreq_frequency_table **opp_table)
+{
+	struct tegra194_cpufreq_data *data = cpufreq_get_driver_data();
+	struct cpufreq_frequency_table *freq_table = NULL;
+	struct cpufreq_frequency_table *pos;
+	struct device *cpu_dev;
+	struct dev_pm_opp *opp;
+	unsigned long rate;
+	int ret, max_opps;
+	int j = 0;
+
+	cpu_dev = get_cpu_device(policy->cpu);
+	if (!cpu_dev) {
+		pr_err("%s: failed to get cpu%d device\n", __func__, policy->cpu);
+		return -ENODEV;
+	}
+
+	/* Initialize OPP table mentioned in operating-points-v2 property in DT */
+	ret = dev_pm_opp_of_add_table_indexed(cpu_dev, 0);
+	if (!ret) {
+		max_opps = dev_pm_opp_get_opp_count(cpu_dev);
+		if (max_opps <= 0) {
+			dev_err(cpu_dev, "Failed to add OPPs\n");
+			return max_opps;
+		}
+
+		/* Disable all opps and cross-validate against LUT later */
+		for (rate = 0; ; rate++) {
+			opp = dev_pm_opp_find_freq_ceil(cpu_dev, &rate);
+			if (IS_ERR(opp))
+				break;
+
+			dev_pm_opp_put(opp);
+			dev_pm_opp_disable(cpu_dev, rate);
+		}
+	} else {
+		dev_err(cpu_dev, "Invalid or empty opp table in device tree\n");
+		data->icc_dram_bw_scaling = false;
+		return ret;
+	}
+
+	freq_table = kcalloc((max_opps + 1), sizeof(*freq_table), GFP_KERNEL);
+	if (!freq_table)
+		return -ENOMEM;
+
+	/*
+	 * Cross check the frequencies from BPMP-FW LUT against the OPP's present in DT.
+	 * Enable only those DT OPP's which are present in LUT also.
+	 */
+	cpufreq_for_each_valid_entry(pos, bpmp_lut) {
+		opp = dev_pm_opp_find_freq_exact(cpu_dev, pos->frequency * KHZ, false);
+		if (IS_ERR(opp))
+			continue;
+
+		ret = dev_pm_opp_enable(cpu_dev, pos->frequency * KHZ);
+		if (ret < 0)
+			return ret;
+
+		freq_table[j].driver_data = pos->driver_data;
+		freq_table[j].frequency = pos->frequency;
+		j++;
+	}
+
+	freq_table[j].driver_data = pos->driver_data;
+	freq_table[j].frequency = CPUFREQ_TABLE_END;
+
+	*opp_table = &freq_table[0];
+
+	dev_pm_opp_set_sharing_cpus(cpu_dev, policy->cpus);
+
+	return ret;
+}
+
 static int tegra194_cpufreq_init(struct cpufreq_policy *policy)
 {
 	struct tegra194_cpufreq_data *data = cpufreq_get_driver_data();
 	int maxcpus_per_cluster = data->soc->maxcpus_per_cluster;
+	struct cpufreq_frequency_table *freq_table;
+	struct cpufreq_frequency_table *bpmp_lut;
 	u32 start_cpu, cpu;
 	u32 clusterid;
+	int ret;
 
 	data->soc->ops->get_cpu_cluster_id(policy->cpu, NULL, &clusterid);
-
-	if (clusterid >= data->soc->num_clusters || !data->tables[clusterid])
+	if (clusterid >= data->soc->num_clusters || !data->bpmp_luts[clusterid])
 		return -EINVAL;
 
 	start_cpu = rounddown(policy->cpu, maxcpus_per_cluster);
@@ -387,9 +485,22 @@ static int tegra194_cpufreq_init(struct cpufreq_policy *policy)
 		if (cpu_possible(cpu))
 			cpumask_set_cpu(cpu, policy->cpus);
 	}
-	policy->freq_table = data->tables[clusterid];
 	policy->cpuinfo.transition_latency = TEGRA_CPUFREQ_TRANSITION_LATENCY;
 
+	bpmp_lut = data->bpmp_luts[clusterid];
+
+	if (data->icc_dram_bw_scaling) {
+		ret = tegra_cpufreq_init_cpufreq_table(policy, bpmp_lut, &freq_table);
+		if (!ret) {
+			policy->freq_table = freq_table;
+			return 0;
+		}
+	}
+
+	data->icc_dram_bw_scaling = false;
+	policy->freq_table = bpmp_lut;
+	pr_info("OPP tables missing from DT, EMC frequency scaling disabled\n");
+
 	return 0;
 }
 
@@ -406,6 +517,9 @@ static int tegra194_cpufreq_set_target(struct cpufreq_policy *policy,
 	 */
 	data->soc->ops->set_cpu_ndiv(policy, (u64)tbl->driver_data);
 
+	if (data->icc_dram_bw_scaling)
+		tegra_cpufreq_set_bw(policy, tbl->frequency);
+
 	return 0;
 }
 
@@ -439,8 +553,8 @@ static void tegra194_cpufreq_free_resources(void)
 }
 
 static struct cpufreq_frequency_table *
-init_freq_table(struct platform_device *pdev, struct tegra_bpmp *bpmp,
-		unsigned int cluster_id)
+tegra_cpufreq_bpmp_read_lut(struct platform_device *pdev, struct tegra_bpmp *bpmp,
+			    unsigned int cluster_id)
 {
 	struct cpufreq_frequency_table *freq_table;
 	struct mrq_cpu_ndiv_limits_response resp;
@@ -515,6 +629,7 @@ static int tegra194_cpufreq_probe(struct platform_device *pdev)
 	const struct tegra_cpufreq_soc *soc;
 	struct tegra194_cpufreq_data *data;
 	struct tegra_bpmp *bpmp;
+	struct device *cpu_dev;
 	int err, i;
 
 	data = devm_kzalloc(&pdev->dev, sizeof(*data), GFP_KERNEL);
@@ -530,9 +645,9 @@ static int tegra194_cpufreq_probe(struct platform_device *pdev)
 		return -EINVAL;
 	}
 
-	data->tables = devm_kcalloc(&pdev->dev, data->soc->num_clusters,
-				    sizeof(*data->tables), GFP_KERNEL);
-	if (!data->tables)
+	data->bpmp_luts = devm_kcalloc(&pdev->dev, data->soc->num_clusters,
+				       sizeof(*data->bpmp_luts), GFP_KERNEL);
+	if (!data->bpmp_luts)
 		return -ENOMEM;
 
 	if (soc->actmon_cntr_base) {
@@ -556,15 +671,26 @@ static int tegra194_cpufreq_probe(struct platform_device *pdev)
 	}
 
 	for (i = 0; i < data->soc->num_clusters; i++) {
-		data->tables[i] = init_freq_table(pdev, bpmp, i);
-		if (IS_ERR(data->tables[i])) {
-			err = PTR_ERR(data->tables[i]);
+		data->bpmp_luts[i] = tegra_cpufreq_bpmp_read_lut(pdev, bpmp, i);
+		if (IS_ERR(data->bpmp_luts[i])) {
+			err = PTR_ERR(data->bpmp_luts[i]);
 			goto err_free_res;
 		}
 	}
 
 	tegra194_cpufreq_driver.driver_data = data;
 
+	/* Check for optional OPPv2 and interconnect paths on CPU0 to enable ICC scaling */
+	cpu_dev = get_cpu_device(0);
+	if (!cpu_dev)
+		return -EPROBE_DEFER;
+
+	if (dev_pm_opp_of_get_opp_desc_node(cpu_dev)) {
+		err = dev_pm_opp_of_find_icc_paths(cpu_dev, NULL);
+		if (!err)
+			data->icc_dram_bw_scaling = true;
+	}
+
 	err = cpufreq_register_driver(&tegra194_cpufreq_driver);
 	if (!err)
 		goto put_bpmp;
-- 
2.17.1

[Patch v2 8/9] memory: tegra: make cpu cluster bw request a multiple of mc channels

[Sumit Gupta]

Make CPU cluster's bandwidth (BW) request a multiple of MC channels.
CPU OPP tables have BW info per MC channel. But, the actual BW depends
on the number of MC channels which can change as per the boot config.
Get the number of MC channels which are actually enabled in current
boot configuration and multiply the BW request from a CPU cluster with
the number of enabled MC channels. This is not required to be done for
other MC clients.

Signed-off-by: Sumit Gupta <sumitg@nvidia.com>
---
 drivers/memory/tegra/mc.c       | 19 +++++++++++++++++++
 drivers/memory/tegra/mc.h       |  1 +
 drivers/memory/tegra/tegra234.c | 21 ++++++++++++++++++++-
 include/soc/tegra/mc.h          |  1 +
 4 files changed, 41 insertions(+), 1 deletion(-)

diff --git a/drivers/memory/tegra/mc.c b/drivers/memory/tegra/mc.c
index 7318eaa3819c..de3af77fb80c 100644
--- a/drivers/memory/tegra/mc.c
+++ b/drivers/memory/tegra/mc.c
@@ -845,6 +845,23 @@ static int tegra_mc_interconnect_setup(struct tegra_mc *mc)
 	return err;
 }
 
+static void tegra_mc_num_channel_enabled(struct tegra_mc *mc)
+{
+	unsigned int i;
+	u32 value;
+
+	value = mc_ch_readl(mc, 0, MC_EMEM_ADR_CFG_CHANNEL_ENABLE);
+	if (value <= 0) {
+		mc->num_channels = mc->soc->num_channels;
+		return;
+	}
+
+	for (i = 0; i < 32; i++) {
+		if (value & BIT(i))
+			mc->num_channels++;
+	}
+}
+
 static int tegra_mc_probe(struct platform_device *pdev)
 {
 	struct tegra_mc *mc;
@@ -883,6 +900,8 @@ static int tegra_mc_probe(struct platform_device *pdev)
 			return err;
 	}
 
+	tegra_mc_num_channel_enabled(mc);
+
 	if (mc->soc->ops && mc->soc->ops->handle_irq) {
 		mc->irq = platform_get_irq(pdev, 0);
 		if (mc->irq < 0)
diff --git a/drivers/memory/tegra/mc.h b/drivers/memory/tegra/mc.h
index bc01586b6560..c3f6655bec60 100644
--- a/drivers/memory/tegra/mc.h
+++ b/drivers/memory/tegra/mc.h
@@ -53,6 +53,7 @@
 #define MC_ERR_ROUTE_SANITY_ADR				0x9c4
 #define MC_ERR_GENERALIZED_CARVEOUT_STATUS		0xc00
 #define MC_ERR_GENERALIZED_CARVEOUT_ADR			0xc04
+#define MC_EMEM_ADR_CFG_CHANNEL_ENABLE			0xdf8
 #define MC_GLOBAL_INTSTATUS				0xf24
 #define MC_ERR_ADR_HI					0x11fc
 
diff --git a/drivers/memory/tegra/tegra234.c b/drivers/memory/tegra/tegra234.c
index 0c666e52bf46..0b608b820b28 100644
--- a/drivers/memory/tegra/tegra234.c
+++ b/drivers/memory/tegra/tegra234.c
@@ -868,6 +868,25 @@ static int tegra234_mc_icc_set(struct icc_node *src, struct icc_node *dst)
 	return ret;
 }
 
+static int tegra234_mc_icc_aggregate(struct icc_node *node, u32 tag, u32 avg_bw,
+				     u32 peak_bw, u32 *agg_avg, u32 *agg_peak)
+{
+	struct icc_provider *p = node->provider;
+	struct tegra_mc *mc = icc_provider_to_tegra_mc(p);
+
+	if (node->id == TEGRA_ICC_MC_CPU_CLUSTER0 ||
+	    node->id == TEGRA_ICC_MC_CPU_CLUSTER1 ||
+	    node->id == TEGRA_ICC_MC_CPU_CLUSTER2) {
+		if (mc)
+			peak_bw = peak_bw * mc->num_channels;
+	}
+
+	*agg_avg += avg_bw;
+	*agg_peak = max(*agg_peak, peak_bw);
+
+	return 0;
+}
+
 static struct icc_node*
 tegra234_mc_of_icc_xlate(struct of_phandle_args *spec, void *data)
 {
@@ -899,7 +918,7 @@ static int tegra234_mc_icc_get_init_bw(struct icc_node *node, u32 *avg, u32 *pea
 
 static const struct tegra_mc_icc_ops tegra234_mc_icc_ops = {
 	.xlate = tegra234_mc_of_icc_xlate,
-	.aggregate = icc_std_aggregate,
+	.aggregate = tegra234_mc_icc_aggregate,
 	.get_bw = tegra234_mc_icc_get_init_bw,
 	.set = tegra234_mc_icc_set,
 };
diff --git a/include/soc/tegra/mc.h b/include/soc/tegra/mc.h
index fefac9622987..2fe6f0217a39 100644
--- a/include/soc/tegra/mc.h
+++ b/include/soc/tegra/mc.h
@@ -233,6 +233,7 @@ struct tegra_mc {
 
 	struct tegra_mc_timing *timings;
 	unsigned int num_timings;
+	unsigned int num_channels;
 
 	struct reset_controller_dev reset;
 
-- 
2.17.1

[Patch v2 9/9] PCI: tegra194: add interconnect support in Tegra234

[Sumit Gupta]

Add support to request DRAM bandwidth with Memory Interconnect
in Tegra234 SoC. The DRAM BW required for different modes depends
on speed (Gen-1/2/3/4) and width/lanes (x1/x2/x4/x8).

Suggested-by: Manikanta Maddireddy <mmaddireddy@nvidia.com>
Signed-off-by: Sumit Gupta <sumitg@nvidia.com>
---
 drivers/pci/controller/dwc/pcie-tegra194.c | 40 +++++++++++++++++-----
 1 file changed, 32 insertions(+), 8 deletions(-)

diff --git a/drivers/pci/controller/dwc/pcie-tegra194.c b/drivers/pci/controller/dwc/pcie-tegra194.c
index 09825b4a075e..d2513c9d3feb 100644
--- a/drivers/pci/controller/dwc/pcie-tegra194.c
+++ b/drivers/pci/controller/dwc/pcie-tegra194.c
@@ -15,6 +15,7 @@
 #include <linux/gpio.h>
 #include <linux/gpio/consumer.h>
 #include <linux/interrupt.h>
+#include <linux/interconnect.h>
 #include <linux/iopoll.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
@@ -287,6 +288,7 @@ struct tegra_pcie_dw {
 	unsigned int pex_rst_irq;
 	int ep_state;
 	long link_status;
+	struct icc_path *icc_path;
 };
 
 static inline struct tegra_pcie_dw *to_tegra_pcie(struct dw_pcie *pci)
@@ -309,6 +311,24 @@ struct tegra_pcie_soc {
 	enum dw_pcie_device_mode mode;
 };
 
+static void tegra_pcie_icc_set(struct tegra_pcie_dw *pcie)
+{
+	struct dw_pcie *pci = &pcie->pci;
+	u32 val, speed, width;
+
+	val = dw_pcie_readw_dbi(pci, pcie->pcie_cap_base + PCI_EXP_LNKSTA);
+
+	speed = FIELD_GET(PCI_EXP_LNKSTA_CLS, val);
+	width = FIELD_GET(PCI_EXP_LNKSTA_NLW, val);
+
+	val = width * (PCIE_SPEED2MBS_ENC(pcie_link_speed[speed]) / BITS_PER_BYTE);
+
+	if (icc_set_bw(pcie->icc_path, MBps_to_icc(val), 0))
+		dev_err(pcie->dev, "can't set bw[%u]\n", val);
+
+	clk_set_rate(pcie->core_clk, pcie_gen_freq[speed - 1]);
+}
+
 static void apply_bad_link_workaround(struct dw_pcie_rp *pp)
 {
 	struct dw_pcie *pci = to_dw_pcie_from_pp(pp);
@@ -452,14 +472,12 @@ static irqreturn_t tegra_pcie_ep_irq_thread(int irq, void *arg)
 	struct tegra_pcie_dw *pcie = arg;
 	struct dw_pcie_ep *ep = &pcie->pci.ep;
 	struct dw_pcie *pci = &pcie->pci;
-	u32 val, speed;
+	u32 val;
 
 	if (test_and_clear_bit(0, &pcie->link_status))
 		dw_pcie_ep_linkup(ep);
 
-	speed = dw_pcie_readw_dbi(pci, pcie->pcie_cap_base + PCI_EXP_LNKSTA) &
-		PCI_EXP_LNKSTA_CLS;
-	clk_set_rate(pcie->core_clk, pcie_gen_freq[speed - 1]);
+	tegra_pcie_icc_set(pcie);
 
 	if (pcie->of_data->has_ltr_req_fix)
 		return IRQ_HANDLED;
@@ -945,9 +963,9 @@ static int tegra_pcie_dw_host_init(struct dw_pcie_rp *pp)
 
 static int tegra_pcie_dw_start_link(struct dw_pcie *pci)
 {
-	u32 val, offset, speed, tmp;
 	struct tegra_pcie_dw *pcie = to_tegra_pcie(pci);
 	struct dw_pcie_rp *pp = &pci->pp;
+	u32 val, offset, tmp;
 	bool retry = true;
 
 	if (pcie->of_data->mode == DW_PCIE_EP_TYPE) {
@@ -1018,9 +1036,7 @@ static int tegra_pcie_dw_start_link(struct dw_pcie *pci)
 		goto retry_link;
 	}
 
-	speed = dw_pcie_readw_dbi(pci, pcie->pcie_cap_base + PCI_EXP_LNKSTA) &
-		PCI_EXP_LNKSTA_CLS;
-	clk_set_rate(pcie->core_clk, pcie_gen_freq[speed - 1]);
+	tegra_pcie_icc_set(pcie);
 
 	tegra_pcie_enable_interrupts(pp);
 
@@ -2224,6 +2240,14 @@ static int tegra_pcie_dw_probe(struct platform_device *pdev)
 
 	platform_set_drvdata(pdev, pcie);
 
+	pcie->icc_path = devm_of_icc_get(&pdev->dev, "write");
+	ret = PTR_ERR_OR_ZERO(pcie->icc_path);
+	if (ret) {
+		tegra_bpmp_put(pcie->bpmp);
+		dev_err_probe(&pdev->dev, ret, "failed to get write interconnect\n");
+		return ret;
+	}
+
 	switch (pcie->of_data->mode) {
 	case DW_PCIE_RC_TYPE:
 		ret = devm_request_irq(dev, pp->irq, tegra_pcie_rp_irq_handler,
-- 
2.17.1

Re: [Patch v2 7/9] cpufreq: tegra194: add OPP support and set bandwidth

[Viresh Kumar]

On 20-02-23, 19:35, Sumit Gupta wrote:
> +static int tegra_cpufreq_set_bw(struct cpufreq_policy *policy, unsigned long freq_khz)
> +{
> +	struct dev_pm_opp *opp;
> +	struct device *dev;
> +	int ret;
> +
> +	dev = get_cpu_device(policy->cpu);
> +	if (!dev)
> +		return -ENODEV;
> +
> +	opp = dev_pm_opp_find_freq_exact(dev, freq_khz * KHZ, true);
> +	if (IS_ERR(opp))
> +		return PTR_ERR(opp);
> +
> +	ret = dev_pm_opp_set_opp(dev, opp);
> +	dev_pm_opp_put(opp);

What about dev_pm_opp_set_rate() instead ?

> +	return ret;
> +}

-- 
viresh

Re: [Patch v2 7/9] cpufreq: tegra194: add OPP support and set bandwidth

[Sumit Gupta]

On 22/02/23 09:33, Viresh Kumar wrote:
> External email: Use caution opening links or attachments
> 
> 
> On 20-02-23, 19:35, Sumit Gupta wrote:
>> +static int tegra_cpufreq_set_bw(struct cpufreq_policy *policy, unsigned long freq_khz)
>> +{
>> +     struct dev_pm_opp *opp;
>> +     struct device *dev;
>> +     int ret;
>> +
>> +     dev = get_cpu_device(policy->cpu);
>> +     if (!dev)
>> +             return -ENODEV;
>> +
>> +     opp = dev_pm_opp_find_freq_exact(dev, freq_khz * KHZ, true);
>> +     if (IS_ERR(opp))
>> +             return PTR_ERR(opp);
>> +
>> +     ret = dev_pm_opp_set_opp(dev, opp);
>> +     dev_pm_opp_put(opp);
> 
> What about dev_pm_opp_set_rate() instead ?
> 
>> +     return ret;
>> +}
> 
> --
> viresh

Tried using it and got below crash. It seems to be coming because we 
don't have clocks property within CPU node for SoC's having BPMP-FW.

  Unable to handle kernel NULL pointer dereference at virtual address 
000000000000002e
  ....
  Call trace:
   clk_round_rate+0x38/0xd8
   dev_pm_opp_set_rate+0xe4/0x1a8
   tegra194_cpufreq_set_target+0x74/0x88
   __cpufreq_driver_target+0x154/0x250
   cpufreq_online+0x7b4/0x9ac

Thanks,
Sumit

Re: [Patch v2 7/9] cpufreq: tegra194: add OPP support and set bandwidth

[Thierry Reding]

[-- Attachment #1: Type: text/plain, Size: 2186 bytes --]

On Thu, Feb 23, 2023 at 03:06:26PM +0530, Sumit Gupta wrote:
> 
> 
> On 22/02/23 09:33, Viresh Kumar wrote:
> > External email: Use caution opening links or attachments
> > 
> > 
> > On 20-02-23, 19:35, Sumit Gupta wrote:
> > > +static int tegra_cpufreq_set_bw(struct cpufreq_policy *policy, unsigned long freq_khz)
> > > +{
> > > +     struct dev_pm_opp *opp;
> > > +     struct device *dev;
> > > +     int ret;
> > > +
> > > +     dev = get_cpu_device(policy->cpu);
> > > +     if (!dev)
> > > +             return -ENODEV;
> > > +
> > > +     opp = dev_pm_opp_find_freq_exact(dev, freq_khz * KHZ, true);
> > > +     if (IS_ERR(opp))
> > > +             return PTR_ERR(opp);
> > > +
> > > +     ret = dev_pm_opp_set_opp(dev, opp);
> > > +     dev_pm_opp_put(opp);
> > 
> > What about dev_pm_opp_set_rate() instead ?
> > 
> > > +     return ret;
> > > +}
> > 
> > --
> > viresh
> 
> Tried using it and got below crash. It seems to be coming because we don't
> have clocks property within CPU node for SoC's having BPMP-FW.
> 
>  Unable to handle kernel NULL pointer dereference at virtual address
> 000000000000002e
>  ....
>  Call trace:
>   clk_round_rate+0x38/0xd8
>   dev_pm_opp_set_rate+0xe4/0x1a8
>   tegra194_cpufreq_set_target+0x74/0x88
>   __cpufreq_driver_target+0x154/0x250
>   cpufreq_online+0x7b4/0x9ac

Can you try to find out what exactly is happening here? The clock
framework should be able to deal with NULL clock pointers just fine.
Although, looking at the OPP table code, it seems like we don't use
clk_get_optional(), so opp_table->clk may end up being a pointer-
encoded error. Perhaps we need something like this:

--- >8 ---
diff --git a/drivers/opp/core.c b/drivers/opp/core.c
index e87567dbe99f..d7baeb6ac697 100644
--- a/drivers/opp/core.c
+++ b/drivers/opp/core.c
@@ -1397,6 +1397,7 @@ static struct opp_table *_update_opp_table_clk(struct device *dev,
 		 * frequency in opp->rates and also parse the entries in DT.
 		 */
 		opp_table->clk_count = 1;
+		opp_table->clk = NULL;
 
 		dev_dbg(dev, "%s: Couldn't find clock: %d\n", __func__, ret);
 		return opp_table;
--- >8 ---

Thierry

[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 833 bytes --]

Re: [Patch v2 7/9] cpufreq: tegra194: add OPP support and set bandwidth

[Viresh Kumar]

On 27-02-23, 13:44, Thierry Reding wrote:
> On Thu, Feb 23, 2023 at 03:06:26PM +0530, Sumit Gupta wrote:
> > On 22/02/23 09:33, Viresh Kumar wrote:
> > Tried using it and got below crash. It seems to be coming because we don't
> > have clocks property within CPU node for SoC's having BPMP-FW.
> > 
> >  Unable to handle kernel NULL pointer dereference at virtual address
> > 000000000000002e
> >  ....
> >  Call trace:
> >   clk_round_rate+0x38/0xd8
> >   dev_pm_opp_set_rate+0xe4/0x1a8
> >   tegra194_cpufreq_set_target+0x74/0x88
> >   __cpufreq_driver_target+0x154/0x250
> >   cpufreq_online+0x7b4/0x9ac
> 
> Can you try to find out what exactly is happening here? The clock
> framework should be able to deal with NULL clock pointers just fine.
> Although, looking at the OPP table code, it seems like we don't use
> clk_get_optional(), so opp_table->clk may end up being a pointer-
> encoded error. Perhaps we need something like this:
> 
> --- >8 ---
> diff --git a/drivers/opp/core.c b/drivers/opp/core.c
> index e87567dbe99f..d7baeb6ac697 100644
> --- a/drivers/opp/core.c
> +++ b/drivers/opp/core.c
> @@ -1397,6 +1397,7 @@ static struct opp_table *_update_opp_table_clk(struct device *dev,
>  		 * frequency in opp->rates and also parse the entries in DT.
>  		 */
>  		opp_table->clk_count = 1;
> +		opp_table->clk = NULL;
>  
>  		dev_dbg(dev, "%s: Couldn't find clock: %d\n", __func__, ret);
>  		return opp_table;

I didn't reply earlier as I had nothing more to say and Sumit's
initial approach was correct. Maybe I should have I have clarified
this then.

The OPP core supports dev_pm_opp_set_rate() only for devices that can
set the rate, for everything else dev_pm_opp_set_opp() is the right
choice. I suggested dev_pm_opp_set_rate() earlier as I thought rate is
supported here.

-- 
viresh

Re: [Patch v2 0/9] Tegra234 Memory interconnect support

[Krzysztof Kozlowski]

On 20/02/2023 15:05, Sumit Gupta wrote:
> This patch series adds memory interconnect support for Tegra234 SoC.
> It is used to dynamically scale DRAM Frequency as per the bandwidth
> requests from different Memory Controller (MC) clients.
> MC Clients use ICC Framework's icc_set_bw() api to dynamically request
> for the DRAM bandwidth (BW). As per path, the request will be routed
> from MC to the EMC driver. MC driver passes the request info like the
> Client ID, type, and frequency request info to the BPMP-FW which will
> set the final DRAM freq considering all exisiting requests.
> 
> MC and EMC are the ICC providers. Nodes in path for a request will be:
>      Client[1-n] -> MC -> EMC -> EMEM/DRAM
> 
> The patch series also adds interconnect support in below client drivers:
> 1) CPUFREQ driver for scaling bandwidth with CPU frequency. For that,
>    added per cluster OPP table which will be used in the CPUFREQ driver
>    by requesting the minimum BW respective to the given CPU frequency in
>    the OPP table of given cluster.
> 2) PCIE driver to request BW required for different modes.

No dependencies or ordering written, so I am free to take memory
controller bits, I assume.

Best regards,
Krzysztof

Re: [Patch v2 0/9] Tegra234 Memory interconnect support

[Krzysztof Kozlowski]

On 06/03/2023 16:05, Krzysztof Kozlowski wrote:
> On 20/02/2023 15:05, Sumit Gupta wrote:
>> This patch series adds memory interconnect support for Tegra234 SoC.
>> It is used to dynamically scale DRAM Frequency as per the bandwidth
>> requests from different Memory Controller (MC) clients.
>> MC Clients use ICC Framework's icc_set_bw() api to dynamically request
>> for the DRAM bandwidth (BW). As per path, the request will be routed
>> from MC to the EMC driver. MC driver passes the request info like the
>> Client ID, type, and frequency request info to the BPMP-FW which will
>> set the final DRAM freq considering all exisiting requests.
>>
>> MC and EMC are the ICC providers. Nodes in path for a request will be:
>>      Client[1-n] -> MC -> EMC -> EMEM/DRAM
>>
>> The patch series also adds interconnect support in below client drivers:
>> 1) CPUFREQ driver for scaling bandwidth with CPU frequency. For that,
>>    added per cluster OPP table which will be used in the CPUFREQ driver
>>    by requesting the minimum BW respective to the given CPU frequency in
>>    the OPP table of given cluster.
>> 2) PCIE driver to request BW required for different modes.
> 
> No dependencies or ordering written, so I am free to take memory
> controller bits, I assume.

And not.. NAK, since you decided to ignore my comments. Really, we do
not have time for such useless ping pong.

Best regards,
Krzysztof

Re: [Patch v2 0/9] Tegra234 Memory interconnect support

[Sumit Gupta]

On 06/03/23 20:35, Krzysztof Kozlowski wrote:
> External email: Use caution opening links or attachments
> 
> 
> On 20/02/2023 15:05, Sumit Gupta wrote:
>> This patch series adds memory interconnect support for Tegra234 SoC.
>> It is used to dynamically scale DRAM Frequency as per the bandwidth
>> requests from different Memory Controller (MC) clients.
>> MC Clients use ICC Framework's icc_set_bw() api to dynamically request
>> for the DRAM bandwidth (BW). As per path, the request will be routed
>> from MC to the EMC driver. MC driver passes the request info like the
>> Client ID, type, and frequency request info to the BPMP-FW which will
>> set the final DRAM freq considering all exisiting requests.
>>
>> MC and EMC are the ICC providers. Nodes in path for a request will be:
>>       Client[1-n] -> MC -> EMC -> EMEM/DRAM
>>
>> The patch series also adds interconnect support in below client drivers:
>> 1) CPUFREQ driver for scaling bandwidth with CPU frequency. For that,
>>     added per cluster OPP table which will be used in the CPUFREQ driver
>>     by requesting the minimum BW respective to the given CPU frequency in
>>     the OPP table of given cluster.
>> 2) PCIE driver to request BW required for different modes.
> 
> No dependencies or ordering written, so I am free to take memory
> controller bits, I assume.
> 
> Best regards,
> Krzysztof
> 

Apologies for not mentioning the order in cover letter. The patches are 
divided into below groups.
  Patch [9]: Memory Interconnect support in PCI (MC client)
  Patch [4-8]: Memory Interconnect support in CPUFREQ (MC client)
  Patch [1-3]: Memory Interconnect base support

Both the Memory Controller (MC) client patches are dependent on the 
'Memory Interconnect base support patch [1-3]'.

Thanks,
Sumit

Re: [Patch v2 0/9] Tegra234 Memory interconnect support

[Sumit Gupta]

On 06/03/23 20:37, Krzysztof Kozlowski wrote:
> External email: Use caution opening links or attachments
> 
> 
> On 06/03/2023 16:05, Krzysztof Kozlowski wrote:
>> On 20/02/2023 15:05, Sumit Gupta wrote:
>>> This patch series adds memory interconnect support for Tegra234 SoC.
>>> It is used to dynamically scale DRAM Frequency as per the bandwidth
>>> requests from different Memory Controller (MC) clients.
>>> MC Clients use ICC Framework's icc_set_bw() api to dynamically request
>>> for the DRAM bandwidth (BW). As per path, the request will be routed
>>> from MC to the EMC driver. MC driver passes the request info like the
>>> Client ID, type, and frequency request info to the BPMP-FW which will
>>> set the final DRAM freq considering all exisiting requests.
>>>
>>> MC and EMC are the ICC providers. Nodes in path for a request will be:
>>>       Client[1-n] -> MC -> EMC -> EMEM/DRAM
>>>
>>> The patch series also adds interconnect support in below client drivers:
>>> 1) CPUFREQ driver for scaling bandwidth with CPU frequency. For that,
>>>     added per cluster OPP table which will be used in the CPUFREQ driver
>>>     by requesting the minimum BW respective to the given CPU frequency in
>>>     the OPP table of given cluster.
>>> 2) PCIE driver to request BW required for different modes.
>>
>> No dependencies or ordering written, so I am free to take memory
>> controller bits, I assume.
> 
> And not.. NAK, since you decided to ignore my comments. Really, we do
> not have time for such useless ping pong.
> 
> Best regards,
> Krzysztof
> 

Hi Krzysztof,

I tried to address the comments given during review of v1 in v2.
I am sorry if in case I missed any suggestion. Please let me know so I 
can incorporate that.

Thanks,
Sumit

Re: [Patch v2 0/9] Tegra234 Memory interconnect support

[Krzysztof Kozlowski]

On 06/03/2023 21:43, Sumit Gupta wrote:
> 
> 
> On 06/03/23 20:37, Krzysztof Kozlowski wrote:
>> External email: Use caution opening links or attachments
>>
>>
>> On 06/03/2023 16:05, Krzysztof Kozlowski wrote:
>>> On 20/02/2023 15:05, Sumit Gupta wrote:
>>>> This patch series adds memory interconnect support for Tegra234 SoC.
>>>> It is used to dynamically scale DRAM Frequency as per the bandwidth
>>>> requests from different Memory Controller (MC) clients.
>>>> MC Clients use ICC Framework's icc_set_bw() api to dynamically request
>>>> for the DRAM bandwidth (BW). As per path, the request will be routed
>>>> from MC to the EMC driver. MC driver passes the request info like the
>>>> Client ID, type, and frequency request info to the BPMP-FW which will
>>>> set the final DRAM freq considering all exisiting requests.
>>>>
>>>> MC and EMC are the ICC providers. Nodes in path for a request will be:
>>>>       Client[1-n] -> MC -> EMC -> EMEM/DRAM
>>>>
>>>> The patch series also adds interconnect support in below client drivers:
>>>> 1) CPUFREQ driver for scaling bandwidth with CPU frequency. For that,
>>>>     added per cluster OPP table which will be used in the CPUFREQ driver
>>>>     by requesting the minimum BW respective to the given CPU frequency in
>>>>     the OPP table of given cluster.
>>>> 2) PCIE driver to request BW required for different modes.
>>>
>>> No dependencies or ordering written, so I am free to take memory
>>> controller bits, I assume.
>>
>> And not.. NAK, since you decided to ignore my comments. Really, we do
>> not have time for such useless ping pong.
>>
>> Best regards,
>> Krzysztof
>>
> 
> Hi Krzysztof,
> 
> I tried to address the comments given during review of v1 in v2.
> I am sorry if in case I missed any suggestion. Please let me know so I 
> can incorporate that.
> 

I never got any feedback and my first glance suggested nothing changed.
Let me check again.

Best regards,
Krzysztof

Re: [Patch v2 2/9] memory: tegra: add interconnect support for DRAM scaling in Tegra234

[Krzysztof Kozlowski]

On 20/02/2023 15:05, Sumit Gupta wrote:
> Add Interconnect framework support to dynamically set the DRAM
> bandwidth from different clients. Both the MC and EMC drivers are
> added as ICC providers. The path for any request is:
>  MC-Client[1-n] -> MC -> EMC -> EMEM/DRAM
> 
> MC client's request for bandwidth will go to the MC driver which
> passes the client request info like BPMP Client ID, Client type
> and the Bandwidth to the BPMP-FW. The final DRAM freq to achieve
> the requested bandwidth is set by the BPMP-FW based on the passed
> parameters.
> 
> Signed-off-by: Sumit Gupta <sumitg@nvidia.com>
> ---


Acked-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>

Best regards,
Krzysztof

Re: [Patch v2 3/9] memory: tegra: add mc clients for Tegra234

[Krzysztof Kozlowski]

On 20/02/2023 15:05, Sumit Gupta wrote:
> Add few Isochronous (ISO) and Non-ISO MC clients.
> ISO clients have guaranteed bandwidth requirement.
> PCIE clients added to the mc_clients table represent
> each controller in Tegra234.
> 
> Signed-off-by: Sumit Gupta <sumitg@nvidia.com>
> ---
>  drivers/memory/tegra/tegra234.c | 420 ++++++++++++++++++++++++++++++++
>  1 file changed, 420 insertions(+)


Acked-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>

Best regards,
Krzysztof

Re: [Patch v2 4/9] memory: tegra: add software mc clients in Tegra234

[Krzysztof Kozlowski]

On 20/02/2023 15:05, Sumit Gupta wrote:
> Add dummy Memory Controller clients to represent CPU clusters.
> They will be used by the CPUFREQ driver to scale DRAM FREQ
> with the CPU FREQ.
> ---
>  drivers/memory/tegra/tegra234.c | 15 +++++++++++++++
>  1 file changed, 15 insertions(+)


Acked-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>

Best regards,
Krzysztof

Re: [Patch v2 8/9] memory: tegra: make cpu cluster bw request a multiple of mc channels

[Krzysztof Kozlowski]

On 20/02/2023 15:05, Sumit Gupta wrote:
> Make CPU cluster's bandwidth (BW) request a multiple of MC channels.
> CPU OPP tables have BW info per MC channel. But, the actual BW depends
> on the number of MC channels which can change as per the boot config.
> Get the number of MC channels which are actually enabled in current
> boot configuration and multiply the BW request from a CPU cluster with
> the number of enabled MC channels. This is not required to be done for
> other MC clients.
> 


Acked-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>

Best regards,
Krzysztof