Add initial OPP and SoC core voltage scaling support to the video
decoder driver. This is required for enabling system-wide DVFS on
older Tegra SoCs.
Tested-by: Peter Geis <pgwipeout@xxxxxxxxx>
Tested-by: Nicolas Chauvet <kwizart@xxxxxxxxx>
Signed-off-by: Dmitry Osipenko <digetx@xxxxxxxxx>
---
drivers/staging/media/tegra-vde/Kconfig | 1 +
drivers/staging/media/tegra-vde/vde.c | 127 ++++++++++++++++++++++++
drivers/staging/media/tegra-vde/vde.h | 1 +
3 files changed, 129 insertions(+)
diff --git a/drivers/staging/media/tegra-vde/Kconfig b/drivers/staging/media/tegra-vde/Kconfig
index 0dc78afd09e0..0ebfe5b07a30 100644
--- a/drivers/staging/media/tegra-vde/Kconfig
+++ b/drivers/staging/media/tegra-vde/Kconfig
@@ -4,6 +4,7 @@ config TEGRA_VDE
depends on ARCH_TEGRA || COMPILE_TEST
select DMA_SHARED_BUFFER
select IOMMU_IOVA
+ select PM_OPP
select SRAM
help
Say Y here to enable support for the NVIDIA Tegra video decoder
diff --git a/drivers/staging/media/tegra-vde/vde.c b/drivers/staging/media/tegra-vde/vde.c
index 28845b5bafaf..9ad43a862eef 100644
--- a/drivers/staging/media/tegra-vde/vde.c
+++ b/drivers/staging/media/tegra-vde/vde.c
@@ -15,11 +15,13 @@
#include <linux/miscdevice.h>
#include <linux/module.h>
#include <linux/of_device.h>
+#include <linux/pm_opp.h>
#include <linux/pm_runtime.h>
#include <linux/reset.h>
#include <linux/slab.h>
#include <linux/uaccess.h>
+#include <soc/tegra/fuse.h>
#include <soc/tegra/pmc.h>
#include "uapi.h"
@@ -926,6 +928,9 @@ static __maybe_unused int tegra_vde_runtime_suspend(struct device *dev)
clk_disable_unprepare(vde->clk);
+ /* remove performance/voltage vote */
+ dev_pm_opp_set_rate(dev, 0);
+
return 0;
}
@@ -934,6 +939,12 @@ static __maybe_unused int tegra_vde_runtime_resume(struct device *dev)
struct tegra_vde *vde = dev_get_drvdata(dev);
int err;
+ err = dev_pm_opp_set_rate(dev, vde->default_clk_rate);
+ if (err) {
+ dev_err(dev, "Failed to set clock rate: %d\n", err);
+ return err;
+ }
+
err = tegra_powergate_sequence_power_up(TEGRA_POWERGATE_VDEC,
vde->clk, vde->rst);
if (err) {
@@ -944,6 +955,118 @@ static __maybe_unused int tegra_vde_runtime_resume(struct device *dev)
return 0;
}
+static void tegra_vde_deinit_opp_table(void *data)
+{
+ struct device *dev = data;
+ struct opp_table *opp_table;
+
+ opp_table = dev_pm_opp_get_opp_table(dev);
+ dev_pm_opp_of_remove_table(dev);
+ dev_pm_opp_put_supported_hw(opp_table);
+ dev_pm_opp_put_regulators(opp_table);
+ dev_pm_opp_put_opp_table(opp_table);
+}
+
+static int devm_tegra_vde_init_opp_table(struct device *dev,
+ struct tegra_vde *vde)
+{
+ struct opp_table *opp_table, *hw_opp_table;
+ const char *rname = "core";
+ struct dev_pm_opp *opp;
+ unsigned long rate;
+ u32 hw_version;
+ int err;
+
+ /* voltage scaling is optional */
+ if (device_property_present(dev, "core-supply"))
+ opp_table = dev_pm_opp_set_regulators(dev, &rname, 1);
+ else
+ opp_table = dev_pm_opp_get_opp_table(dev);
+
+ if (IS_ERR(opp_table))
+ return dev_err_probe(dev, PTR_ERR(opp_table),
+ "Failed to prepare OPP table\n");
+
+ if (of_machine_is_compatible("nvidia,tegra20"))
+ hw_version = BIT(tegra_sku_info.soc_process_id);
+ else
+ hw_version = BIT(tegra_sku_info.soc_speedo_id);
+
+ hw_opp_table = dev_pm_opp_set_supported_hw(dev, &hw_version, 1);
+ err = PTR_ERR_OR_ZERO(hw_opp_table);
+ if (err) {
+ dev_err(dev, "Failed to set supported HW: %d\n", err);
+ goto put_table;
+ }
+
+ /*
+ * OPP table presence is optional and we want the set_rate() of OPP
+ * API to work similarly to clk_set_rate() if table is missing in a
+ * device-tree. The add_table() errors out if OPP is missing in DT.
+ *
+ * Clock rate should be pre-initialized (i.e. it's non-zero) either
+ * by clock driver or by assigned clocks in a device-tree.
+ */
+ if (!device_property_present(dev, "operating-points-v2")) {
+ vde->default_clk_rate = clk_get_rate(vde->clk);
+ goto add_action;
+ }
+
+ err = dev_pm_opp_of_add_table(dev);
+ if (err) {
+ dev_err(dev, "Failed to add OPP table: %d\n", err);
+ goto put_hw;
+ }
+
+ /*
+ * If voltage regulator presents, then we could select the fastest
+ * clock rate, but driver doesn't support frequency scaling yet,
+ * hence the top freq OPP may vote for a very high voltage that will
+ * produce lot's of heat. Let's select OPP for the current/default
+ * rate for now.
+ *
+ * Clock rate should be pre-initialized (i.e. it's non-zero) either
+ * by clock driver or by assigned clocks in a device-tree.
+ */
+ rate = clk_get_rate(vde->clk);
+
+ /* find suitable OPP for the clock rate supportable by SoC */
+ opp = dev_pm_opp_find_freq_ceil(dev, &rate);
+
+ if (opp == ERR_PTR(-ERANGE))
+ opp = dev_pm_opp_find_freq_floor(dev, &rate);
+
+ err = PTR_ERR_OR_ZERO(opp);
+ if (err) {
+ dev_err(dev, "failed to get OPP for %ld Hz: %d\n",
+ rate, err);
+ goto remove_table;
+ }
+
+ dev_pm_opp_put(opp);
+
+ vde->default_clk_rate = clk_round_rate(vde->clk, rate);
+
+add_action:
+ err = devm_add_action(dev, tegra_vde_deinit_opp_table, dev);
+ if (err)
+ goto remove_table;
+
+ dev_info(dev, "OPP HW ver. 0x%x, clock rate %lu MHz\n",
+ hw_version, vde->default_clk_rate / 1000000);
+
+ return 0;
+
+remove_table:
+ dev_pm_opp_of_remove_table(dev);
+put_hw:
+ dev_pm_opp_put_supported_hw(opp_table);
+put_table:
+ dev_pm_opp_put_regulators(opp_table);
+
+ return err;
+}
+
static int tegra_vde_probe(struct platform_device *pdev)
{
struct device *dev = &pdev->dev;
@@ -1024,6 +1147,10 @@ static int tegra_vde_probe(struct platform_device *pdev)
return err;
}
+ err = devm_tegra_vde_init_opp_table(dev, vde);
+ if (err)
+ return dev_err_probe(dev, err, "Failed to initialize OPP\n");
+
vde->iram_pool = of_gen_pool_get(dev->of_node, "iram", 0);
if (!vde->iram_pool) {
dev_err(dev, "Could not get IRAM pool\n");
diff --git a/drivers/staging/media/tegra-vde/vde.h b/drivers/staging/media/tegra-vde/vde.h
index 5561291b0c88..da83c2d6af8b 100644
--- a/drivers/staging/media/tegra-vde/vde.h
+++ b/drivers/staging/media/tegra-vde/vde.h
@@ -48,6 +48,7 @@ struct tegra_vde {
struct iova_domain iova;
struct iova *iova_resv_static_addresses;
struct iova *iova_resv_last_page;
+ unsigned long default_clk_rate;
dma_addr_t iram_lists_addr;
u32 *iram;
};
--
2.27.0
