The RK3576 NPU domains need a short settle time after the idle request is released before the registers behind the domain answer. Without it the QoS writes that rockchip_pmu_restore_qos() issues land while the domain is still coming up, and the NPU throws an async SError on the first cold power-on.
Give rockchip_domain_info an optional delay_us and wait for it between releasing idle and restoring QoS. Rename DOMAIN_M_O_R_G to DOMAIN_M_O_R_G_W for the settle delay it now carries; RK3576 is its only user, so the old spelling is not kept around. The suffix scheme does not survive this cleanly and it is worth saying so rather than leaving it for review. The letters name fields, but R already means two things in this family: DOMAIN_M_O_R takes r_status and r_offset AND a regulator under one R, while DOMAIN_M_R has no repair fields and its R is the regulator. DOMAIN_M_O_R_G's R was the repair pair -- it did not set need_regulator at all -- so the paragraph below, which gives it one, adds a field the name does not mention. Naming it _W_R or _RG would be inventing a convention rather than following one. Say which you would rather have. While the macro is being rewritten, give it the regulator argument that DOMAIN_M_O_R and DOMAIN_M_R already take. Without .need_regulator set, rockchip_pd_regulator_enable() returns early for every RK3576 domain, so a domain-supply in the device tree is never looked up and never enabled. Add a DOMAIN_RK3576_R spelling that passes true and use it for RK3576_PD_NPU, which is the one RK3576 domain with a rail of its own; every other domain passes false and is unchanged. Two things beyond the delay, both worth saying out loud because neither is what the subject describes. RK3576_PD_NPU also gets need_regulator here, which makes rockchip_pm_add_one_domain() call rockchip_pd_power(pd, false) at probe on all thirteen in-tree rk3576 boards. Only rock-4d enables an NPU core, and it is the one that declares the supply, so on the other twelve ->power_on never runs and the regulator is never looked up at all. It is deliberate, and it is what the delay is for: without the domain being forced off at probe, a bootloader that leaves the NPU powered means ->power_on is never called and neither the delay nor 10/14's reset pulse ever runs. This is not new behaviour in this driver. RK3588_PD_NPU has carried need_regulator since it was added and its req_mask is 0 exactly as this one's is, so rockchip_pd_power(pd, false) has been running at probe on every rk3588 board, with rockchip_pmu_set_idle_request() returning immediately because there is no request to make. Of the forty-nine in-tree rk3588 board files, twenty-one enable an NPU core and declare the supply, twenty-six do not enable one at all so ->power_on never runs for them, and two enable it with no supply: quartzpro64 and youyeetoo-yy3588 take the dummy regulator and the one line dev_warn from the regulator core today. The idle handshake lives in the child domains and on both SoCs they keep it: NPUTOP, NPU0 and NPU1 carry req and idle masks of their own. If that is too much for one patch, say so and it splits. Signed-off-by: Jiaxing Hu <[email protected]> Reviewed-by: Abel Vesa <[email protected]> --- drivers/pmdomain/rockchip/pm-domains.c | 56 ++++++++++++++++---------- 1 file changed, 34 insertions(+), 22 deletions(-) diff --git a/drivers/pmdomain/rockchip/pm-domains.c b/drivers/pmdomain/rockchip/pm-domains.c index ba66ae719..39988efd8 100644 --- a/drivers/pmdomain/rockchip/pm-domains.c +++ b/drivers/pmdomain/rockchip/pm-domains.c @@ -18,6 +18,7 @@ #include <linux/of_address.h> #include <linux/of_clk.h> #include <linux/clk.h> +#include <linux/delay.h> #include <linux/regmap.h> #include <linux/regulator/consumer.h> #include <linux/mfd/syscon.h> @@ -59,6 +60,7 @@ struct rockchip_domain_info { u32 pwr_offset; u32 mem_offset; u32 req_offset; + u32 delay_us; }; struct rockchip_pmu_info { @@ -185,7 +187,7 @@ struct rockchip_pmu { .need_regulator = regulator, \ } -#define DOMAIN_M_O_R_G(_name, p_offset, pwr, status, m_offset, m_status, r_status, r_offset, req, idle, ack, g_mask, wakeup) \ +#define DOMAIN_M_O_R_G_W(_name, p_offset, pwr, status, m_offset, m_status, r_status, r_offset, req, idle, ack, g_mask, delay, wakeup, regulator) \ { \ .name = _name, \ .pwr_offset = p_offset, \ @@ -200,8 +202,10 @@ struct rockchip_pmu { .req_mask = (req), \ .idle_mask = (idle), \ .clk_ungate_mask = (g_mask), \ + .delay_us = (delay), \ .ack_mask = (ack), \ .active_wakeup = wakeup, \ + .need_regulator = regulator, \ } #define DOMAIN_M_R(_name, pwr, status, req, idle, ack, wakeup, regulator) \ @@ -258,8 +262,11 @@ struct rockchip_pmu { #define DOMAIN_RK3568(name, pwr, req, wakeup, regulator) \ DOMAIN_M_R(name, pwr, pwr, req, req, req, wakeup, regulator) -#define DOMAIN_RK3576(name, p_offset, pwr, status, r_status, r_offset, req, idle, g_mask, wakeup) \ - DOMAIN_M_O_R_G(name, p_offset, pwr, status, 0, r_status, r_status, r_offset, req, idle, idle, g_mask, wakeup) +#define DOMAIN_RK3576(name, p_offset, pwr, status, r_status, r_offset, req, idle, g_mask, delay, wakeup) \ + DOMAIN_M_O_R_G_W(name, p_offset, pwr, status, 0, r_status, r_status, r_offset, req, idle, idle, g_mask, delay, wakeup, false) + +#define DOMAIN_RK3576_R(name, p_offset, pwr, status, r_status, r_offset, req, idle, g_mask, delay, wakeup) \ + DOMAIN_M_O_R_G_W(name, p_offset, pwr, status, 0, r_status, r_status, r_offset, req, idle, idle, g_mask, delay, wakeup, true) /* * Dynamic Memory Controller may need to coordinate with us -- see @@ -681,6 +688,10 @@ static int rockchip_pd_power(struct rockchip_pm_domain *pd, bool power_on) if (ret < 0) goto out; + /* Some domains need to settle before the QoS registers answer. */ + if (pd->info->delay_us) + udelay(pd->info->delay_us); + rockchip_pmu_restore_qos(pd); } @@ -1300,25 +1311,26 @@ static const struct rockchip_domain_info rk3568_pm_domains[] = { }; static const struct rockchip_domain_info rk3576_pm_domains[] = { - [RK3576_PD_NPU] = DOMAIN_RK3576("npu", 0x0, BIT(0), BIT(0), 0, 0x0, 0, 0, 0, false), - [RK3576_PD_NVM] = DOMAIN_RK3576("nvm", 0x0, BIT(6), 0, BIT(6), 0x4, BIT(2), BIT(18), BIT(2), false), - [RK3576_PD_SDGMAC] = DOMAIN_RK3576("sdgmac", 0x0, BIT(7), 0, BIT(7), 0x4, BIT(1), BIT(17), 0x6, false), - [RK3576_PD_AUDIO] = DOMAIN_RK3576("audio", 0x0, BIT(8), 0, BIT(8), 0x4, BIT(0), BIT(16), BIT(0), false), - [RK3576_PD_PHP] = DOMAIN_RK3576("php", 0x0, BIT(9), 0, BIT(9), 0x0, BIT(15), BIT(15), BIT(15), false), - [RK3576_PD_SUBPHP] = DOMAIN_RK3576("subphp", 0x0, BIT(10), 0, BIT(10), 0x0, 0, 0, 0, false), - [RK3576_PD_VOP] = DOMAIN_RK3576("vop", 0x0, BIT(11), 0, BIT(11), 0x0, 0x6000, 0x6000, 0x6000, false), - [RK3576_PD_VO1] = DOMAIN_RK3576("vo1", 0x0, BIT(14), 0, BIT(14), 0x0, BIT(12), BIT(12), 0x7000, false), - [RK3576_PD_VO0] = DOMAIN_RK3576("vo0", 0x0, BIT(15), 0, BIT(15), 0x0, BIT(11), BIT(11), 0x6800, false), - [RK3576_PD_USB] = DOMAIN_RK3576("usb", 0x4, BIT(0), 0, BIT(16), 0x0, BIT(10), BIT(10), 0x6400, true), - [RK3576_PD_VI] = DOMAIN_RK3576("vi", 0x4, BIT(1), 0, BIT(17), 0x0, BIT(9), BIT(9), BIT(9), false), - [RK3576_PD_VEPU0] = DOMAIN_RK3576("vepu0", 0x4, BIT(2), 0, BIT(18), 0x0, BIT(7), BIT(7), 0x280, false), - [RK3576_PD_VEPU1] = DOMAIN_RK3576("vepu1", 0x4, BIT(3), 0, BIT(19), 0x0, BIT(8), BIT(8), BIT(8), false), - [RK3576_PD_VDEC] = DOMAIN_RK3576("vdec", 0x4, BIT(4), 0, BIT(20), 0x0, BIT(6), BIT(6), BIT(6), false), - [RK3576_PD_VPU] = DOMAIN_RK3576("vpu", 0x4, BIT(5), 0, BIT(21), 0x0, BIT(5), BIT(5), BIT(5), false), - [RK3576_PD_NPUTOP] = DOMAIN_RK3576("nputop", 0x4, BIT(6), 0, BIT(22), 0x0, 0x18, 0x18, 0x18, false), - [RK3576_PD_NPU0] = DOMAIN_RK3576("npu0", 0x4, BIT(7), 0, BIT(23), 0x0, BIT(1), BIT(1), 0x1a, false), - [RK3576_PD_NPU1] = DOMAIN_RK3576("npu1", 0x4, BIT(8), 0, BIT(24), 0x0, BIT(2), BIT(2), 0x1c, false), - [RK3576_PD_GPU] = DOMAIN_RK3576("gpu", 0x4, BIT(9), 0, BIT(25), 0x0, BIT(0), BIT(0), BIT(0), false), + /* name p_offset pwr status r_status r_offset req idle g_mask delay wakeup */ + [RK3576_PD_NPU] = DOMAIN_RK3576_R("npu", 0x0, BIT(0), BIT(0), 0, 0x0, 0, 0, 0, 0, false), + [RK3576_PD_NVM] = DOMAIN_RK3576("nvm", 0x0, BIT(6), 0, BIT(6), 0x4, BIT(2), BIT(18), BIT(2), 0, false), + [RK3576_PD_SDGMAC] = DOMAIN_RK3576("sdgmac", 0x0, BIT(7), 0, BIT(7), 0x4, BIT(1), BIT(17), 0x6, 0, false), + [RK3576_PD_AUDIO] = DOMAIN_RK3576("audio", 0x0, BIT(8), 0, BIT(8), 0x4, BIT(0), BIT(16), BIT(0), 0, false), + [RK3576_PD_PHP] = DOMAIN_RK3576("php", 0x0, BIT(9), 0, BIT(9), 0x0, BIT(15), BIT(15), BIT(15), 0, false), + [RK3576_PD_SUBPHP] = DOMAIN_RK3576("subphp", 0x0, BIT(10), 0, BIT(10), 0x0, 0, 0, 0, 0, false), + [RK3576_PD_VOP] = DOMAIN_RK3576("vop", 0x0, BIT(11), 0, BIT(11), 0x0, 0x6000, 0x6000, 0x6000, 0, false), + [RK3576_PD_VO1] = DOMAIN_RK3576("vo1", 0x0, BIT(14), 0, BIT(14), 0x0, BIT(12), BIT(12), 0x7000, 0, false), + [RK3576_PD_VO0] = DOMAIN_RK3576("vo0", 0x0, BIT(15), 0, BIT(15), 0x0, BIT(11), BIT(11), 0x6800, 0, false), + [RK3576_PD_USB] = DOMAIN_RK3576("usb", 0x4, BIT(0), 0, BIT(16), 0x0, BIT(10), BIT(10), 0x6400, 0, true), + [RK3576_PD_VI] = DOMAIN_RK3576("vi", 0x4, BIT(1), 0, BIT(17), 0x0, BIT(9), BIT(9), BIT(9), 0, false), + [RK3576_PD_VEPU0] = DOMAIN_RK3576("vepu0", 0x4, BIT(2), 0, BIT(18), 0x0, BIT(7), BIT(7), 0x280, 0, false), + [RK3576_PD_VEPU1] = DOMAIN_RK3576("vepu1", 0x4, BIT(3), 0, BIT(19), 0x0, BIT(8), BIT(8), BIT(8), 0, false), + [RK3576_PD_VDEC] = DOMAIN_RK3576("vdec", 0x4, BIT(4), 0, BIT(20), 0x0, BIT(6), BIT(6), BIT(6), 0, false), + [RK3576_PD_VPU] = DOMAIN_RK3576("vpu", 0x4, BIT(5), 0, BIT(21), 0x0, BIT(5), BIT(5), BIT(5), 0, false), + [RK3576_PD_NPUTOP] = DOMAIN_RK3576("nputop", 0x4, BIT(6), 0, BIT(22), 0x0, 0x18, 0x18, 0x18, 15, false), + [RK3576_PD_NPU0] = DOMAIN_RK3576("npu0", 0x4, BIT(7), 0, BIT(23), 0x0, BIT(1), BIT(1), 0x1a, 15, false), + [RK3576_PD_NPU1] = DOMAIN_RK3576("npu1", 0x4, BIT(8), 0, BIT(24), 0x0, BIT(2), BIT(2), 0x1c, 15, false), + [RK3576_PD_GPU] = DOMAIN_RK3576("gpu", 0x4, BIT(9), 0, BIT(25), 0x0, BIT(0), BIT(0), BIT(0), 0, false), }; static const struct rockchip_domain_info rk3588_pm_domains[] = { -- 2.43.0
