Some Rockchip domains come out of power-on with their bus interface in an undefined state. On the RK3576 NPU this shows up as a hang on the first register access after the domain is switched on, and pulsing the domain's resets at this point clears it.
Take the domain node's resets if it has any, and pulse them between releasing idle and restoring QoS. The resets are optional, so domains that do not list any are unaffected. The cycle goes before the settle delay 9/14 adds, not after it. A domain that asks for both is asking to settle before the QoS registers answer, and a reset deasserted after the delay would leave nothing between the deassert and rockchip_pmu_restore_qos(). On RK3576 PD_NPU0 and PD_NPU1 ask for both, and the reset they cycle is SRST_A_RKNN0/1_BIU, the bus interface those QoS writes go through. It only runs when the domain actually changes state: rockchip_pd_power() returns early when the hardware already reads the state being asked for. A bootloader that leaves the NPU powered would therefore skip both this and the delay, which is why 9/14 gives RK3576_PD_NPU need_regulator and forces the domain off at probe. No in-tree DTS puts resets in a power-domain node today, so every other Rockchip SoC takes the optional get's NULL and is unchanged. Signed-off-by: Jiaxing Hu <[email protected]> Reviewed-by: Abel Vesa <[email protected]> --- drivers/pmdomain/rockchip/pm-domains.c | 27 ++++++++++++++++++++++++++ 1 file changed, 27 insertions(+) diff --git a/drivers/pmdomain/rockchip/pm-domains.c b/drivers/pmdomain/rockchip/pm-domains.c index 39988efd8..6cc8d6efd 100644 --- a/drivers/pmdomain/rockchip/pm-domains.c +++ b/drivers/pmdomain/rockchip/pm-domains.c @@ -19,6 +19,7 @@ #include <linux/of_clk.h> #include <linux/clk.h> #include <linux/delay.h> +#include <linux/reset.h> #include <linux/regmap.h> #include <linux/regulator/consumer.h> #include <linux/mfd/syscon.h> @@ -103,6 +104,7 @@ struct rockchip_pm_domain { struct clk_bulk_data *clks; struct device_node *node; struct regulator *supply; + struct reset_control *resets; }; struct rockchip_pmu { @@ -688,6 +690,21 @@ static int rockchip_pd_power(struct rockchip_pm_domain *pd, bool power_on) if (ret < 0) goto out; + /* + * Optional: some domains need their resets cycled once power + * is on. This goes BEFORE the settle delay, not after: a + * domain that asks for both is asking to settle before the + * QoS registers answer, and a reset deasserted after the + * delay would leave nothing between it and the QoS writes. + * On RK3576 the reset being cycled is the NPU core's bus + * interface, which is what those writes go through. + */ + if (pd->resets) { + reset_control_assert(pd->resets); + usleep_range(10, 20); + reset_control_deassert(pd->resets); + } + /* Some domains need to settle before the QoS registers answer. */ if (pd->info->delay_us) udelay(pd->info->delay_us); @@ -861,6 +878,14 @@ static int rockchip_pm_add_one_domain(struct rockchip_pmu *pmu, if (error) goto err_put_clocks; + pd->resets = of_reset_control_array_get_optional_exclusive(node); + if (IS_ERR(pd->resets)) { + error = dev_err_probe(pmu->dev, PTR_ERR(pd->resets), + "%pOFn: failed to get resets\n", node); + pd->resets = NULL; + goto err_unprepare_clocks; + } + pd->num_qos = of_count_phandle_with_args(node, "pm_qos", NULL); @@ -931,6 +956,7 @@ static int rockchip_pm_add_one_domain(struct rockchip_pmu *pmu, clk_bulk_unprepare(pd->num_clks, pd->clks); err_put_clocks: clk_bulk_put(pd->num_clks, pd->clks); + reset_control_put(pd->resets); return error; } @@ -949,6 +975,7 @@ static void rockchip_pm_remove_one_domain(struct rockchip_pm_domain *pd) clk_bulk_unprepare(pd->num_clks, pd->clks); clk_bulk_put(pd->num_clks, pd->clks); + reset_control_put(pd->resets); /* protect the zeroing of pm->num_clks */ mutex_lock(&pd->pmu->mutex); -- 2.43.0
