diff options
author | Olof Johansson <olof@lixom.net> | 2019-11-12 00:13:22 +0300 |
---|---|---|
committer | Olof Johansson <olof@lixom.net> | 2019-11-12 00:13:23 +0300 |
commit | 57a54dfe4895222dcb8e22ca6f49bf42d1b197aa (patch) | |
tree | d25132f26720e6e9d88893fc3a77eea759a533ff /drivers | |
parent | 13c1eff1755bdea7fede4b238aadc0228e410dfe (diff) | |
parent | 141bef44e123c101c0da0443ab6b3cfa750f251a (diff) | |
download | linux-57a54dfe4895222dcb8e22ca6f49bf42d1b197aa.tar.xz |
Merge tag 'tegra-for-5.5-memory-v2' of git://git.kernel.org/pub/scm/linux/kernel/git/tegra/linux into arm/drivers
memory: tegra: Changes for v5.5-rc1
This contains a couple of fixes and adds support for EMC frequency
scaling on Tegra30.
* tag 'tegra-for-5.5-memory-v2' of git://git.kernel.org/pub/scm/linux/kernel/git/tegra/linux:
memory: tegra: Consolidate registers definition into common header
memory: tegra: Ensure timing control debug features are disabled
memory: tegra: Introduce Tegra30 EMC driver
memory: tegra: Do not handle error from wait_for_completion_timeout()
memory: tegra: Increase handshake timeout on Tegra20
memory: tegra: Print a brief info message about EMC timings
memory: tegra: Pre-configure debug register on Tegra20
memory: tegra: Include io.h instead of iopoll.h
memory: tegra: Adapt for Tegra20 clock driver changes
memory: tegra: Don't set EMC rate to maximum on probe for Tegra20
memory: tegra: Add gr2d and gr3d to DRM IOMMU group
memory: tegra: Set DMA mask based on supported address bits
clk: tegra: Add Tegra20/30 EMC clock implementation
Link: https://lore.kernel.org/r/20191111143836.4027200-1-thierry.reding@gmail.com
Signed-off-by: Olof Johansson <olof@lixom.net>
Diffstat (limited to 'drivers')
-rw-r--r-- | drivers/clk/tegra/Makefile | 2 | ||||
-rw-r--r-- | drivers/clk/tegra/clk-tegra20-emc.c | 293 | ||||
-rw-r--r-- | drivers/clk/tegra/clk-tegra20.c | 55 | ||||
-rw-r--r-- | drivers/clk/tegra/clk-tegra30.c | 38 | ||||
-rw-r--r-- | drivers/clk/tegra/clk.h | 3 | ||||
-rw-r--r-- | drivers/memory/tegra/Kconfig | 10 | ||||
-rw-r--r-- | drivers/memory/tegra/Makefile | 1 | ||||
-rw-r--r-- | drivers/memory/tegra/mc.c | 52 | ||||
-rw-r--r-- | drivers/memory/tegra/mc.h | 74 | ||||
-rw-r--r-- | drivers/memory/tegra/tegra114.c | 10 | ||||
-rw-r--r-- | drivers/memory/tegra/tegra124.c | 30 | ||||
-rw-r--r-- | drivers/memory/tegra/tegra20-emc.c | 134 | ||||
-rw-r--r-- | drivers/memory/tegra/tegra30-emc.c | 1232 | ||||
-rw-r--r-- | drivers/memory/tegra/tegra30.c | 34 |
14 files changed, 1767 insertions, 201 deletions
diff --git a/drivers/clk/tegra/Makefile b/drivers/clk/tegra/Makefile index 4812e45c2214..df966ca06788 100644 --- a/drivers/clk/tegra/Makefile +++ b/drivers/clk/tegra/Makefile @@ -17,7 +17,9 @@ obj-y += clk-tegra-fixed.o obj-y += clk-tegra-super-gen4.o obj-$(CONFIG_TEGRA_CLK_EMC) += clk-emc.o obj-$(CONFIG_ARCH_TEGRA_2x_SOC) += clk-tegra20.o +obj-$(CONFIG_ARCH_TEGRA_2x_SOC) += clk-tegra20-emc.o obj-$(CONFIG_ARCH_TEGRA_3x_SOC) += clk-tegra30.o +obj-$(CONFIG_ARCH_TEGRA_3x_SOC) += clk-tegra20-emc.o obj-$(CONFIG_ARCH_TEGRA_114_SOC) += clk-tegra114.o obj-$(CONFIG_ARCH_TEGRA_124_SOC) += clk-tegra124.o obj-$(CONFIG_TEGRA_CLK_DFLL) += clk-tegra124-dfll-fcpu.o diff --git a/drivers/clk/tegra/clk-tegra20-emc.c b/drivers/clk/tegra/clk-tegra20-emc.c new file mode 100644 index 000000000000..03bf0009a33c --- /dev/null +++ b/drivers/clk/tegra/clk-tegra20-emc.c @@ -0,0 +1,293 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * Based on drivers/clk/tegra/clk-emc.c + * Copyright (c) 2014, NVIDIA CORPORATION. All rights reserved. + * + * Author: Dmitry Osipenko <digetx@gmail.com> + * Copyright (C) 2019 GRATE-DRIVER project + */ + +#define pr_fmt(fmt) "tegra-emc-clk: " fmt + +#include <linux/bits.h> +#include <linux/clk-provider.h> +#include <linux/clk/tegra.h> +#include <linux/err.h> +#include <linux/io.h> +#include <linux/kernel.h> +#include <linux/slab.h> + +#include "clk.h" + +#define CLK_SOURCE_EMC_2X_CLK_DIVISOR_MASK GENMASK(7, 0) +#define CLK_SOURCE_EMC_2X_CLK_SRC_MASK GENMASK(31, 30) +#define CLK_SOURCE_EMC_2X_CLK_SRC_SHIFT 30 + +#define MC_EMC_SAME_FREQ BIT(16) +#define USE_PLLM_UD BIT(29) + +#define EMC_SRC_PLL_M 0 +#define EMC_SRC_PLL_C 1 +#define EMC_SRC_PLL_P 2 +#define EMC_SRC_CLK_M 3 + +static const char * const emc_parent_clk_names[] = { + "pll_m", "pll_c", "pll_p", "clk_m", +}; + +struct tegra_clk_emc { + struct clk_hw hw; + void __iomem *reg; + bool mc_same_freq; + bool want_low_jitter; + + tegra20_clk_emc_round_cb *round_cb; + void *cb_arg; +}; + +static inline struct tegra_clk_emc *to_tegra_clk_emc(struct clk_hw *hw) +{ + return container_of(hw, struct tegra_clk_emc, hw); +} + +static unsigned long emc_recalc_rate(struct clk_hw *hw, + unsigned long parent_rate) +{ + struct tegra_clk_emc *emc = to_tegra_clk_emc(hw); + u32 val, div; + + val = readl_relaxed(emc->reg); + div = val & CLK_SOURCE_EMC_2X_CLK_DIVISOR_MASK; + + return DIV_ROUND_UP(parent_rate * 2, div + 2); +} + +static u8 emc_get_parent(struct clk_hw *hw) +{ + struct tegra_clk_emc *emc = to_tegra_clk_emc(hw); + + return readl_relaxed(emc->reg) >> CLK_SOURCE_EMC_2X_CLK_SRC_SHIFT; +} + +static int emc_set_parent(struct clk_hw *hw, u8 index) +{ + struct tegra_clk_emc *emc = to_tegra_clk_emc(hw); + u32 val, div; + + val = readl_relaxed(emc->reg); + val &= ~CLK_SOURCE_EMC_2X_CLK_SRC_MASK; + val |= index << CLK_SOURCE_EMC_2X_CLK_SRC_SHIFT; + + div = val & CLK_SOURCE_EMC_2X_CLK_DIVISOR_MASK; + + if (index == EMC_SRC_PLL_M && div == 0 && emc->want_low_jitter) + val |= USE_PLLM_UD; + else + val &= ~USE_PLLM_UD; + + if (emc->mc_same_freq) + val |= MC_EMC_SAME_FREQ; + else + val &= ~MC_EMC_SAME_FREQ; + + writel_relaxed(val, emc->reg); + + fence_udelay(1, emc->reg); + + return 0; +} + +static int emc_set_rate(struct clk_hw *hw, unsigned long rate, + unsigned long parent_rate) +{ + struct tegra_clk_emc *emc = to_tegra_clk_emc(hw); + unsigned int index; + u32 val, div; + + div = div_frac_get(rate, parent_rate, 8, 1, 0); + + val = readl_relaxed(emc->reg); + val &= ~CLK_SOURCE_EMC_2X_CLK_DIVISOR_MASK; + val |= div; + + index = val >> CLK_SOURCE_EMC_2X_CLK_SRC_SHIFT; + + if (index == EMC_SRC_PLL_M && div == 0 && emc->want_low_jitter) + val |= USE_PLLM_UD; + else + val &= ~USE_PLLM_UD; + + if (emc->mc_same_freq) + val |= MC_EMC_SAME_FREQ; + else + val &= ~MC_EMC_SAME_FREQ; + + writel_relaxed(val, emc->reg); + + fence_udelay(1, emc->reg); + + return 0; +} + +static int emc_set_rate_and_parent(struct clk_hw *hw, + unsigned long rate, + unsigned long parent_rate, + u8 index) +{ + struct tegra_clk_emc *emc = to_tegra_clk_emc(hw); + u32 val, div; + + div = div_frac_get(rate, parent_rate, 8, 1, 0); + + val = readl_relaxed(emc->reg); + + val &= ~CLK_SOURCE_EMC_2X_CLK_SRC_MASK; + val |= index << CLK_SOURCE_EMC_2X_CLK_SRC_SHIFT; + + val &= ~CLK_SOURCE_EMC_2X_CLK_DIVISOR_MASK; + val |= div; + + if (index == EMC_SRC_PLL_M && div == 0 && emc->want_low_jitter) + val |= USE_PLLM_UD; + else + val &= ~USE_PLLM_UD; + + if (emc->mc_same_freq) + val |= MC_EMC_SAME_FREQ; + else + val &= ~MC_EMC_SAME_FREQ; + + writel_relaxed(val, emc->reg); + + fence_udelay(1, emc->reg); + + return 0; +} + +static int emc_determine_rate(struct clk_hw *hw, struct clk_rate_request *req) +{ + struct tegra_clk_emc *emc = to_tegra_clk_emc(hw); + struct clk_hw *parent_hw; + unsigned long divided_rate; + unsigned long parent_rate; + unsigned int i; + long emc_rate; + int div; + + emc_rate = emc->round_cb(req->rate, req->min_rate, req->max_rate, + emc->cb_arg); + if (emc_rate < 0) + return emc_rate; + + for (i = 0; i < ARRAY_SIZE(emc_parent_clk_names); i++) { + parent_hw = clk_hw_get_parent_by_index(hw, i); + + if (req->best_parent_hw == parent_hw) + parent_rate = req->best_parent_rate; + else + parent_rate = clk_hw_get_rate(parent_hw); + + if (emc_rate > parent_rate) + continue; + + div = div_frac_get(emc_rate, parent_rate, 8, 1, 0); + divided_rate = DIV_ROUND_UP(parent_rate * 2, div + 2); + + if (divided_rate != emc_rate) + continue; + + req->best_parent_rate = parent_rate; + req->best_parent_hw = parent_hw; + req->rate = emc_rate; + break; + } + + if (i == ARRAY_SIZE(emc_parent_clk_names)) { + pr_err_once("can't find parent for rate %lu emc_rate %lu\n", + req->rate, emc_rate); + return -EINVAL; + } + + return 0; +} + +static const struct clk_ops tegra_clk_emc_ops = { + .recalc_rate = emc_recalc_rate, + .get_parent = emc_get_parent, + .set_parent = emc_set_parent, + .set_rate = emc_set_rate, + .set_rate_and_parent = emc_set_rate_and_parent, + .determine_rate = emc_determine_rate, +}; + +void tegra20_clk_set_emc_round_callback(tegra20_clk_emc_round_cb *round_cb, + void *cb_arg) +{ + struct clk *clk = __clk_lookup("emc"); + struct tegra_clk_emc *emc; + struct clk_hw *hw; + + if (clk) { + hw = __clk_get_hw(clk); + emc = to_tegra_clk_emc(hw); + + emc->round_cb = round_cb; + emc->cb_arg = cb_arg; + } +} + +bool tegra20_clk_emc_driver_available(struct clk_hw *emc_hw) +{ + return to_tegra_clk_emc(emc_hw)->round_cb != NULL; +} + +struct clk *tegra20_clk_register_emc(void __iomem *ioaddr, bool low_jitter) +{ + struct tegra_clk_emc *emc; + struct clk_init_data init; + struct clk *clk; + + emc = kzalloc(sizeof(*emc), GFP_KERNEL); + if (!emc) + return NULL; + + /* + * EMC stands for External Memory Controller. + * + * We don't want EMC clock to be disabled ever by gating its + * parent and whatnot because system is busted immediately in that + * case, hence the clock is marked as critical. + */ + init.name = "emc"; + init.ops = &tegra_clk_emc_ops; + init.flags = CLK_IS_CRITICAL; + init.parent_names = emc_parent_clk_names; + init.num_parents = ARRAY_SIZE(emc_parent_clk_names); + + emc->reg = ioaddr; + emc->hw.init = &init; + emc->want_low_jitter = low_jitter; + + clk = clk_register(NULL, &emc->hw); + if (IS_ERR(clk)) { + kfree(emc); + return NULL; + } + + return clk; +} + +int tegra20_clk_prepare_emc_mc_same_freq(struct clk *emc_clk, bool same) +{ + struct tegra_clk_emc *emc; + struct clk_hw *hw; + + if (!emc_clk) + return -EINVAL; + + hw = __clk_get_hw(emc_clk); + emc = to_tegra_clk_emc(hw); + emc->mc_same_freq = same; + + return 0; +} diff --git a/drivers/clk/tegra/clk-tegra20.c b/drivers/clk/tegra/clk-tegra20.c index bcd871134f45..cceefbd67a3b 100644 --- a/drivers/clk/tegra/clk-tegra20.c +++ b/drivers/clk/tegra/clk-tegra20.c @@ -130,8 +130,6 @@ static struct cpu_clk_suspend_context { static void __iomem *clk_base; static void __iomem *pmc_base; -static DEFINE_SPINLOCK(emc_lock); - #define TEGRA_INIT_DATA_MUX(_name, _parents, _offset, \ _clk_num, _gate_flags, _clk_id) \ TEGRA_INIT_DATA(_name, NULL, NULL, _parents, _offset, \ @@ -760,7 +758,6 @@ static const char *pwm_parents[] = { "pll_p", "pll_c", "audio", "clk_m", static const char *mux_pllpcm_clkm[] = { "pll_p", "pll_c", "pll_m", "clk_m" }; static const char *mux_pllpdc_clkm[] = { "pll_p", "pll_d_out0", "pll_c", "clk_m" }; -static const char *mux_pllmcp_clkm[] = { "pll_m", "pll_c", "pll_p", "clk_m" }; static struct tegra_periph_init_data tegra_periph_clk_list[] = { TEGRA_INIT_DATA_MUX("i2s1", i2s1_parents, CLK_SOURCE_I2S1, 11, TEGRA_PERIPH_ON_APB, TEGRA20_CLK_I2S1), @@ -787,41 +784,6 @@ static struct tegra_periph_init_data tegra_periph_nodiv_clk_list[] = { TEGRA_INIT_DATA_NODIV("disp2", mux_pllpdc_clkm, CLK_SOURCE_DISP2, 30, 2, 26, 0, TEGRA20_CLK_DISP2), }; -static void __init tegra20_emc_clk_init(void) -{ - const u32 use_pllm_ud = BIT(29); - struct clk *clk; - u32 emc_reg; - - clk = clk_register_mux(NULL, "emc_mux", mux_pllmcp_clkm, - ARRAY_SIZE(mux_pllmcp_clkm), - CLK_SET_RATE_NO_REPARENT, - clk_base + CLK_SOURCE_EMC, - 30, 2, 0, &emc_lock); - - clk = tegra_clk_register_mc("mc", "emc_mux", clk_base + CLK_SOURCE_EMC, - &emc_lock); - clks[TEGRA20_CLK_MC] = clk; - - /* un-divided pll_m_out0 is currently unsupported */ - emc_reg = readl_relaxed(clk_base + CLK_SOURCE_EMC); - if (emc_reg & use_pllm_ud) { - pr_err("%s: un-divided PllM_out0 used as clock source\n", - __func__); - return; - } - - /* - * Note that 'emc_mux' source and 'emc' rate shouldn't be changed at - * the same time due to a HW bug, this won't happen because we're - * defining 'emc_mux' and 'emc' as distinct clocks. - */ - clk = tegra_clk_register_divider("emc", "emc_mux", - clk_base + CLK_SOURCE_EMC, CLK_IS_CRITICAL, - TEGRA_DIVIDER_INT, 0, 8, 1, &emc_lock); - clks[TEGRA20_CLK_EMC] = clk; -} - static void __init tegra20_periph_clk_init(void) { struct tegra_periph_init_data *data; @@ -835,7 +797,13 @@ static void __init tegra20_periph_clk_init(void) clks[TEGRA20_CLK_AC97] = clk; /* emc */ - tegra20_emc_clk_init(); + clk = tegra20_clk_register_emc(clk_base + CLK_SOURCE_EMC, false); + + clks[TEGRA20_CLK_EMC] = clk; + + clk = tegra_clk_register_mc("mc", "emc", clk_base + CLK_SOURCE_EMC, + NULL); + clks[TEGRA20_CLK_MC] = clk; /* dsi */ clk = tegra_clk_register_periph_gate("dsi", "pll_d", 0, clk_base, 0, @@ -1115,6 +1083,8 @@ static struct clk *tegra20_clk_src_onecell_get(struct of_phandle_args *clkspec, if (IS_ERR(clk)) return clk; + hw = __clk_get_hw(clk); + /* * Tegra20 CDEV1 and CDEV2 clocks are a bit special case, their parent * clock is created by the pinctrl driver. It is possible for clk user @@ -1124,13 +1094,16 @@ static struct clk *tegra20_clk_src_onecell_get(struct of_phandle_args *clkspec, */ if (clkspec->args[0] == TEGRA20_CLK_CDEV1 || clkspec->args[0] == TEGRA20_CLK_CDEV2) { - hw = __clk_get_hw(clk); - parent_hw = clk_hw_get_parent(hw); if (!parent_hw) return ERR_PTR(-EPROBE_DEFER); } + if (clkspec->args[0] == TEGRA20_CLK_EMC) { + if (!tegra20_clk_emc_driver_available(hw)) + return ERR_PTR(-EPROBE_DEFER); + } + return clk; } diff --git a/drivers/clk/tegra/clk-tegra30.c b/drivers/clk/tegra/clk-tegra30.c index 7b4c6a488527..95b0e4a16dd5 100644 --- a/drivers/clk/tegra/clk-tegra30.c +++ b/drivers/clk/tegra/clk-tegra30.c @@ -151,7 +151,6 @@ static unsigned long input_freq; static DEFINE_SPINLOCK(cml_lock); static DEFINE_SPINLOCK(pll_d_lock); -static DEFINE_SPINLOCK(emc_lock); #define TEGRA_INIT_DATA_MUX(_name, _parents, _offset, \ _clk_num, _gate_flags, _clk_id) \ @@ -808,7 +807,7 @@ static struct tegra_clk tegra30_clks[tegra_clk_max] __initdata = { [tegra_clk_pll_a] = { .dt_id = TEGRA30_CLK_PLL_A, .present = true }, [tegra_clk_pll_a_out0] = { .dt_id = TEGRA30_CLK_PLL_A_OUT0, .present = true }, [tegra_clk_cec] = { .dt_id = TEGRA30_CLK_CEC, .present = true }, - [tegra_clk_emc] = { .dt_id = TEGRA30_CLK_EMC, .present = true }, + [tegra_clk_emc] = { .dt_id = TEGRA30_CLK_EMC, .present = false }, }; static const char *pll_e_parents[] = { "pll_ref", "pll_p" }; @@ -995,7 +994,6 @@ static void __init tegra30_super_clk_init(void) static const char *mux_pllacp_clkm[] = { "pll_a_out0", "unused", "pll_p", "clk_m" }; static const char *mux_pllpcm_clkm[] = { "pll_p", "pll_c", "pll_m", "clk_m" }; -static const char *mux_pllmcp_clkm[] = { "pll_m", "pll_c", "pll_p", "clk_m" }; static const char *spdif_out_parents[] = { "pll_a_out0", "spdif_2x", "pll_p", "clk_m" }; static const char *mux_pllmcpa[] = { "pll_m", "pll_c", "pll_p", "pll_a_out0" }; @@ -1044,14 +1042,12 @@ static void __init tegra30_periph_clk_init(void) clks[TEGRA30_CLK_AFI] = clk; /* emc */ - clk = clk_register_mux(NULL, "emc_mux", mux_pllmcp_clkm, - ARRAY_SIZE(mux_pllmcp_clkm), - CLK_SET_RATE_NO_REPARENT, - clk_base + CLK_SOURCE_EMC, - 30, 2, 0, &emc_lock); + clk = tegra20_clk_register_emc(clk_base + CLK_SOURCE_EMC, true); + + clks[TEGRA30_CLK_EMC] = clk; - clk = tegra_clk_register_mc("mc", "emc_mux", clk_base + CLK_SOURCE_EMC, - &emc_lock); + clk = tegra_clk_register_mc("mc", "emc", clk_base + CLK_SOURCE_EMC, + NULL); clks[TEGRA30_CLK_MC] = clk; /* cml0 */ @@ -1302,6 +1298,26 @@ static struct tegra_audio_clk_info tegra30_audio_plls[] = { { "pll_a", &pll_a_params, tegra_clk_pll_a, "pll_p_out1" }, }; +static struct clk *tegra30_clk_src_onecell_get(struct of_phandle_args *clkspec, + void *data) +{ + struct clk_hw *hw; + struct clk *clk; + + clk = of_clk_src_onecell_get(clkspec, data); + if (IS_ERR(clk)) + return clk; + + hw = __clk_get_hw(clk); + + if (clkspec->args[0] == TEGRA30_CLK_EMC) { + if (!tegra20_clk_emc_driver_available(hw)) + return ERR_PTR(-EPROBE_DEFER); + } + + return clk; +} + static void __init tegra30_clock_init(struct device_node *np) { struct device_node *node; @@ -1345,7 +1361,7 @@ static void __init tegra30_clock_init(struct device_node *np) tegra_init_dup_clks(tegra_clk_duplicates, clks, TEGRA30_CLK_CLK_MAX); - tegra_add_of_provider(np, of_clk_src_onecell_get); + tegra_add_of_provider(np, tegra30_clk_src_onecell_get); tegra_register_devclks(devclks, ARRAY_SIZE(devclks)); tegra_clk_apply_init_table = tegra30_clock_apply_init_table; diff --git a/drivers/clk/tegra/clk.h b/drivers/clk/tegra/clk.h index 905bf1096558..20b3ee123050 100644 --- a/drivers/clk/tegra/clk.h +++ b/drivers/clk/tegra/clk.h @@ -838,4 +838,7 @@ int div_frac_get(unsigned long rate, unsigned parent_rate, u8 width, udelay(delay); \ } while (0) +bool tegra20_clk_emc_driver_available(struct clk_hw *emc_hw); +struct clk *tegra20_clk_register_emc(void __iomem *ioaddr, bool low_jitter); + #endif /* TEGRA_CLK_H */ diff --git a/drivers/memory/tegra/Kconfig b/drivers/memory/tegra/Kconfig index 4680124ddcab..fbfbaada61a2 100644 --- a/drivers/memory/tegra/Kconfig +++ b/drivers/memory/tegra/Kconfig @@ -17,6 +17,16 @@ config TEGRA20_EMC This driver is required to change memory timings / clock rate for external memory. +config TEGRA30_EMC + bool "NVIDIA Tegra30 External Memory Controller driver" + default y + depends on TEGRA_MC && ARCH_TEGRA_3x_SOC + help + This driver is for the External Memory Controller (EMC) found on + Tegra30 chips. The EMC controls the external DRAM on the board. + This driver is required to change memory timings / clock rate for + external memory. + config TEGRA124_EMC bool "NVIDIA Tegra124 External Memory Controller driver" default y diff --git a/drivers/memory/tegra/Makefile b/drivers/memory/tegra/Makefile index 3971a6b7c487..3d23c4261104 100644 --- a/drivers/memory/tegra/Makefile +++ b/drivers/memory/tegra/Makefile @@ -11,5 +11,6 @@ tegra-mc-$(CONFIG_ARCH_TEGRA_210_SOC) += tegra210.o obj-$(CONFIG_TEGRA_MC) += tegra-mc.o obj-$(CONFIG_TEGRA20_EMC) += tegra20-emc.o +obj-$(CONFIG_TEGRA30_EMC) += tegra30-emc.o obj-$(CONFIG_TEGRA124_EMC) += tegra124-emc.o obj-$(CONFIG_ARCH_TEGRA_186_SOC) += tegra186.o diff --git a/drivers/memory/tegra/mc.c b/drivers/memory/tegra/mc.c index 3d8d322511c5..ec8403557ed4 100644 --- a/drivers/memory/tegra/mc.c +++ b/drivers/memory/tegra/mc.c @@ -5,6 +5,7 @@ #include <linux/clk.h> #include <linux/delay.h> +#include <linux/dma-mapping.h> #include <linux/interrupt.h> #include <linux/kernel.h> #include <linux/module.h> @@ -18,39 +19,6 @@ #include "mc.h" -#define MC_INTSTATUS 0x000 - -#define MC_INTMASK 0x004 - -#define MC_ERR_STATUS 0x08 -#define MC_ERR_STATUS_TYPE_SHIFT 28 -#define MC_ERR_STATUS_TYPE_INVALID_SMMU_PAGE (6 << MC_ERR_STATUS_TYPE_SHIFT) -#define MC_ERR_STATUS_TYPE_MASK (0x7 << MC_ERR_STATUS_TYPE_SHIFT) -#define MC_ERR_STATUS_READABLE (1 << 27) -#define MC_ERR_STATUS_WRITABLE (1 << 26) -#define MC_ERR_STATUS_NONSECURE (1 << 25) -#define MC_ERR_STATUS_ADR_HI_SHIFT 20 -#define MC_ERR_STATUS_ADR_HI_MASK 0x3 -#define MC_ERR_STATUS_SECURITY (1 << 17) -#define MC_ERR_STATUS_RW (1 << 16) - -#define MC_ERR_ADR 0x0c - -#define MC_GART_ERROR_REQ 0x30 -#define MC_DECERR_EMEM_OTHERS_STATUS 0x58 -#define MC_SECURITY_VIOLATION_STATUS 0x74 - -#define MC_EMEM_ARB_CFG 0x90 -#define MC_EMEM_ARB_CFG_CYCLES_PER_UPDATE(x) (((x) & 0x1ff) << 0) -#define MC_EMEM_ARB_CFG_CYCLES_PER_UPDATE_MASK 0x1ff -#define MC_EMEM_ARB_MISC0 0xd8 - -#define MC_EMEM_ADR_CFG 0x54 -#define MC_EMEM_ADR_CFG_EMEM_NUMDEV BIT(0) - -#define MC_TIMING_CONTROL 0xfc -#define MC_TIMING_UPDATE BIT(0) - static const struct of_device_id tegra_mc_of_match[] = { #ifdef CONFIG_ARCH_TEGRA_2x_SOC { .compatible = "nvidia,tegra20-mc-gart", .data = &tegra20_mc_soc }, @@ -307,7 +275,7 @@ static int tegra_mc_setup_latency_allowance(struct tegra_mc *mc) return 0; } -void tegra_mc_write_emem_configuration(struct tegra_mc *mc, unsigned long rate) +int tegra_mc_write_emem_configuration(struct tegra_mc *mc, unsigned long rate) { unsigned int i; struct tegra_mc_timing *timing = NULL; @@ -322,11 +290,13 @@ void tegra_mc_write_emem_configuration(struct tegra_mc *mc, unsigned long rate) if (!timing) { dev_err(mc->dev, "no memory timing registered for rate %lu\n", rate); - return; + return -EINVAL; } for (i = 0; i < mc->soc->num_emem_regs; ++i) mc_writel(mc, timing->emem_data[i], mc->soc->emem_regs[i]); + + return 0; } unsigned int tegra_mc_get_emem_device_count(struct tegra_mc *mc) @@ -626,6 +596,7 @@ static int tegra_mc_probe(struct platform_device *pdev) struct resource *res; struct tegra_mc *mc; void *isr; + u64 mask; int err; mc = devm_kzalloc(&pdev->dev, sizeof(*mc), GFP_KERNEL); @@ -637,6 +608,14 @@ static int tegra_mc_probe(struct platform_device *pdev) mc->soc = of_device_get_match_data(&pdev->dev); mc->dev = &pdev->dev; + mask = DMA_BIT_MASK(mc->soc->num_address_bits); + + err = dma_coerce_mask_and_coherent(&pdev->dev, mask); + if (err < 0) { + dev_err(&pdev->dev, "failed to set DMA mask: %d\n", err); + return err; + } + /* length of MC tick in nanoseconds */ mc->tick = 30; @@ -658,6 +637,9 @@ static int tegra_mc_probe(struct platform_device *pdev) } else #endif { + /* ensure that debug features are disabled */ + mc_writel(mc, 0x00000000, MC_TIMING_CONTROL_DBG); + err = tegra_mc_setup_latency_allowance(mc); if (err < 0) { dev_err(&pdev->dev, diff --git a/drivers/memory/tegra/mc.h b/drivers/memory/tegra/mc.h index f9353494b708..957c6eb74ff9 100644 --- a/drivers/memory/tegra/mc.h +++ b/drivers/memory/tegra/mc.h @@ -6,20 +6,76 @@ #ifndef MEMORY_TEGRA_MC_H #define MEMORY_TEGRA_MC_H +#include <linux/bits.h> #include <linux/io.h> #include <linux/types.h> #include <soc/tegra/mc.h> -#define MC_INT_DECERR_MTS (1 << 16) -#define MC_INT_SECERR_SEC (1 << 13) -#define MC_INT_DECERR_VPR (1 << 12) -#define MC_INT_INVALID_APB_ASID_UPDATE (1 << 11) -#define MC_INT_INVALID_SMMU_PAGE (1 << 10) -#define MC_INT_ARBITRATION_EMEM (1 << 9) -#define MC_INT_SECURITY_VIOLATION (1 << 8) -#define MC_INT_INVALID_GART_PAGE (1 << 7) -#define MC_INT_DECERR_EMEM (1 << 6) +#define MC_INTSTATUS 0x00 +#define MC_INTMASK 0x04 +#define MC_ERR_STATUS 0x08 +#define MC_ERR_ADR 0x0c +#define MC_GART_ERROR_REQ 0x30 +#define MC_EMEM_ADR_CFG 0x54 +#define MC_DECERR_EMEM_OTHERS_STATUS 0x58 +#define MC_SECURITY_VIOLATION_STATUS 0x74 +#define MC_EMEM_ARB_CFG 0x90 +#define MC_EMEM_ARB_OUTSTANDING_REQ 0x94 +#define MC_EMEM_ARB_TIMING_RCD 0x98 +#define MC_EMEM_ARB_TIMING_RP 0x9c +#define MC_EMEM_ARB_TIMING_RC 0xa0 +#define MC_EMEM_ARB_TIMING_RAS 0xa4 +#define MC_EMEM_ARB_TIMING_FAW 0xa8 +#define MC_EMEM_ARB_TIMING_RRD 0xac +#define MC_EMEM_ARB_TIMING_RAP2PRE 0xb0 +#define MC_EMEM_ARB_TIMING_WAP2PRE 0xb4 +#define MC_EMEM_ARB_TIMING_R2R 0xb8 +#define MC_EMEM_ARB_TIMING_W2W 0xbc +#define MC_EMEM_ARB_TIMING_R2W 0xc0 +#define MC_EMEM_ARB_TIMING_W2R 0xc4 +#define MC_EMEM_ARB_DA_TURNS 0xd0 +#define MC_EMEM_ARB_DA_COVERS 0xd4 +#define MC_EMEM_ARB_MISC0 0xd8 +#define MC_EMEM_ARB_MISC1 0xdc +#define MC_EMEM_ARB_RING1_THROTTLE 0xe0 +#define MC_EMEM_ARB_OVERRIDE 0xe8 +#define MC_TIMING_CONTROL_DBG 0xf8 +#define MC_TIMING_CONTROL 0xfc + +#define MC_INT_DECERR_MTS BIT(16) +#define MC_INT_SECERR_SEC BIT(13) +#define MC_INT_DECERR_VPR BIT(12) +#define MC_INT_INVALID_APB_ASID_UPDATE BIT(11) +#define MC_INT_INVALID_SMMU_PAGE BIT(10) +#define MC_INT_ARBITRATION_EMEM BIT(9) +#define MC_INT_SECURITY_VIOLATION BIT(8) +#define MC_INT_INVALID_GART_PAGE BIT(7) +#define MC_INT_DECERR_EMEM BIT(6) + +#define MC_ERR_STATUS_TYPE_SHIFT 28 +#define MC_ERR_STATUS_TYPE_INVALID_SMMU_PAGE (0x6 << 28) +#define MC_ERR_STATUS_TYPE_MASK (0x7 << 28) +#define MC_ERR_STATUS_READABLE BIT(27) +#define MC_ERR_STATUS_WRITABLE BIT(26) +#define MC_ERR_STATUS_NONSECURE BIT(25) +#define MC_ERR_STATUS_ADR_HI_SHIFT 20 +#define MC_ERR_STATUS_ADR_HI_MASK 0x3 +#define MC_ERR_STATUS_SECURITY BIT(17) +#define MC_ERR_STATUS_RW BIT(16) + +#define MC_EMEM_ADR_CFG_EMEM_NUMDEV BIT(0) + +#define MC_EMEM_ARB_CFG_CYCLES_PER_UPDATE(x) ((x) & 0x1ff) +#define MC_EMEM_ARB_CFG_CYCLES_PER_UPDATE_MASK 0x1ff + +#define MC_EMEM_ARB_OUTSTANDING_REQ_MAX_MASK 0x1ff +#define MC_EMEM_ARB_OUTSTANDING_REQ_HOLDOFF_OVERRIDE BIT(30) +#define MC_EMEM_ARB_OUTSTANDING_REQ_LIMIT_ENABLE BIT(31) + +#define MC_EMEM_ARB_OVERRIDE_EACK_MASK 0x3 + +#define MC_TIMING_UPDATE BIT(0) static inline u32 mc_readl(struct tegra_mc *mc, unsigned long offset) { diff --git a/drivers/memory/tegra/tegra114.c b/drivers/memory/tegra/tegra114.c index ac8351b5beeb..48ef01c3ff90 100644 --- a/drivers/memory/tegra/tegra114.c +++ b/drivers/memory/tegra/tegra114.c @@ -909,16 +909,18 @@ static const struct tegra_smmu_swgroup tegra114_swgroups[] = { { .name = "tsec", .swgroup = TEGRA_SWGROUP_TSEC, .reg = 0x294 }, }; -static const unsigned int tegra114_group_display[] = { +static const unsigned int tegra114_group_drm[] = { TEGRA_SWGROUP_DC, TEGRA_SWGROUP_DCB, + TEGRA_SWGROUP_G2, + TEGRA_SWGROUP_NV, }; static const struct tegra_smmu_group_soc tegra114_groups[] = { { - .name = "display", - .swgroups = tegra114_group_display, - .num_swgroups = ARRAY_SIZE(tegra114_group_display), + .name = "drm", + .swgroups = tegra114_group_drm, + .num_swgroups = ARRAY_SIZE(tegra114_group_drm), }, }; diff --git a/drivers/memory/tegra/tegra124.c b/drivers/memory/tegra/tegra124.c index 5d0ccb2be206..493b5dc3a4b3 100644 --- a/drivers/memory/tegra/tegra124.c +++ b/drivers/memory/tegra/tegra124.c @@ -10,26 +10,6 @@ #include "mc.h" -#define MC_EMEM_ARB_CFG 0x90 -#define MC_EMEM_ARB_OUTSTANDING_REQ 0x94 -#define MC_EMEM_ARB_TIMING_RCD 0x98 -#define MC_EMEM_ARB_TIMING_RP 0x9c -#define MC_EMEM_ARB_TIMING_RC 0xa0 -#define MC_EMEM_ARB_TIMING_RAS 0xa4 -#define MC_EMEM_ARB_TIMING_FAW 0xa8 -#define MC_EMEM_ARB_TIMING_RRD 0xac -#define MC_EMEM_ARB_TIMING_RAP2PRE 0xb0 -#define MC_EMEM_ARB_TIMING_WAP2PRE 0xb4 -#define MC_EMEM_ARB_TIMING_R2R 0xb8 -#define MC_EMEM_ARB_TIMING_W2W 0xbc -#define MC_EMEM_ARB_TIMING_R2W 0xc0 -#define MC_EMEM_ARB_TIMING_W2R 0xc4 -#define MC_EMEM_ARB_DA_TURNS 0xd0 -#define MC_EMEM_ARB_DA_COVERS 0xd4 -#define MC_EMEM_ARB_MISC0 0xd8 -#define MC_EMEM_ARB_MISC1 0xdc -#define MC_EMEM_ARB_RING1_THROTTLE 0xe0 - static const struct tegra_mc_client tegra124_mc_clients[] = { { .id = 0x00, @@ -974,16 +954,18 @@ static const struct tegra_smmu_swgroup tegra124_swgroups[] = { { .name = "vi", .swgroup = TEGRA_SWGROUP_VI, .reg = 0x280 }, }; -static const unsigned int tegra124_group_display[] = { +static const unsigned int tegra124_group_drm[] = { TEGRA_SWGROUP_DC, TEGRA_SWGROUP_DCB, + TEGRA_SWGROUP_GPU, + TEGRA_SWGROUP_VIC, }; static const struct tegra_smmu_group_soc tegra124_groups[] = { { - .name = "display", - .swgroups = tegra124_group_display, - .num_swgroups = ARRAY_SIZE(tegra124_group_display), + .name = "drm", + .swgroups = tegra124_group_drm, + .num_swgroups = ARRAY_SIZE(tegra124_group_drm), }, }; diff --git a/drivers/memory/tegra/tegra20-emc.c b/drivers/memory/tegra/tegra20-emc.c index 9ee5bef49e47..1b23b1c34476 100644 --- a/drivers/memory/tegra/tegra20-emc.c +++ b/drivers/memory/tegra/tegra20-emc.c @@ -6,10 +6,11 @@ */ #include <linux/clk.h> +#include <linux/clk/tegra.h> #include <linux/completion.h> #include <linux/err.h> #include <linux/interrupt.h> -#include <linux/iopoll.h> +#include <linux/io.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/of.h> @@ -21,6 +22,7 @@ #define EMC_INTSTATUS 0x000 #define EMC_INTMASK 0x004 +#define EMC_DBG 0x008 #define EMC_TIMING_CONTROL 0x028 #define EMC_RC 0x02c #define EMC_RFC 0x030 @@ -79,6 +81,12 @@ #define EMC_REFRESH_OVERFLOW_INT BIT(3) #define EMC_CLKCHANGE_COMPLETE_INT BIT(4) +#define EMC_DBG_READ_MUX_ASSEMBLY BIT(0) +#define EMC_DBG_WRITE_MUX_ACTIVE BIT(1) +#define EMC_DBG_FORCE_UPDATE BIT(2) +#define EMC_DBG_READ_DQM_CTRL BIT(9) +#define EMC_DBG_CFG_PRIORITY BIT(24) + static const u16 emc_timing_registers[] = { EMC_RC, EMC_RFC, @@ -137,9 +145,6 @@ struct tegra_emc { struct device *dev; struct completion clk_handshake_complete; struct notifier_block clk_nb; - struct clk *backup_clk; - struct clk *emc_mux; - struct clk *pll_m; struct clk *clk; void __iomem *regs; @@ -219,7 +224,7 @@ static int emc_prepare_timing_change(struct tegra_emc *emc, unsigned long rate) static int emc_complete_timing_change(struct tegra_emc *emc, bool flush) { - long timeout; + unsigned long timeout; dev_dbg(emc->dev, "%s: flush %d\n", __func__, flush); @@ -231,14 +236,10 @@ static int emc_complete_timing_change(struct tegra_emc *emc, bool flush) } timeout = wait_for_completion_timeout(&emc->clk_handshake_complete, - usecs_to_jiffies(100)); + msecs_to_jiffies(100)); if (timeout == 0) { dev_err(emc->dev, "EMC-CAR handshake failed\n"); return -EIO; - } else if (timeout < 0) { - dev_err(emc->dev, "failed to wait for EMC-CAR handshake: %ld\n", - timeout); - return timeout; } return 0; @@ -363,6 +364,13 @@ static int tegra_emc_load_timings_from_dt(struct tegra_emc *emc, sort(emc->timings, emc->num_timings, sizeof(*timing), cmp_timings, NULL); + dev_info(emc->dev, + "got %u timings for RAM code %u (min %luMHz max %luMHz)\n", + emc->num_timings, + tegra_read_ram_code(), + emc->timings[0].rate / 1000000, + emc->timings[emc->num_timings - 1].rate / 1000000); + return 0; } @@ -398,7 +406,7 @@ tegra_emc_find_node_by_ram_code(struct device *dev) static int emc_setup_hw(struct tegra_emc *emc) { u32 intmask = EMC_REFRESH_OVERFLOW_INT | EMC_CLKCHANGE_COMPLETE_INT; - u32 emc_cfg; + u32 emc_cfg, emc_dbg; emc_cfg = readl_relaxed(emc->regs + EMC_CFG_2); @@ -421,42 +429,53 @@ static int emc_setup_hw(struct tegra_emc *emc) writel_relaxed(intmask, emc->regs + EMC_INTMASK); writel_relaxed(intmask, emc->regs + EMC_INTSTATUS); + /* ensure that unwanted debug features are disabled */ + emc_dbg = readl_relaxed(emc->regs + EMC_DBG); + emc_dbg |= EMC_DBG_CFG_PRIORITY; + emc_dbg &= ~EMC_DBG_READ_MUX_ASSEMBLY; + emc_dbg &= ~EMC_DBG_WRITE_MUX_ACTIVE; + emc_dbg &= ~EMC_DBG_FORCE_UPDATE; + writel_relaxed(emc_dbg, emc->regs + EMC_DBG); + return 0; } -static int emc_init(struct tegra_emc *emc, unsigned long rate) +static long emc_round_rate(unsigned long rate, + unsigned long min_rate, + unsigned long max_rate, + void *arg) { - int err; + struct emc_timing *timing = NULL; + struct tegra_emc *emc = arg; + unsigned int i; - err = clk_set_parent(emc->emc_mux, emc->backup_clk); - if (err) { - dev_err(emc->dev, - "failed to reparent to backup source: %d\n", err); - return err; - } + min_rate = min(min_rate, emc->timings[emc->num_timings - 1].rate); - err = clk_set_rate(emc->pll_m, rate); - if (err) { - dev_err(emc->dev, - "failed to change pll_m rate: %d\n", err); - return err; - } + for (i = 0; i < emc->num_timings; i++) { + if (emc->timings[i].rate < rate && i != emc->num_timings - 1) + continue; - err = clk_set_parent(emc->emc_mux, emc->pll_m); - if (err) { - dev_err(emc->dev, - "failed to reparent to pll_m: %d\n", err); - return err; + if (emc->timings[i].rate > max_rate) { + i = max(i, 1u) - 1; + + if (emc->timings[i].rate < min_rate) + break; + } + + if (emc->timings[i].rate < min_rate) + continue; + + timing = &emc->timings[i]; + break; } - err = clk_set_rate(emc->clk, rate); - if (err) { - dev_err(emc->dev, - "failed to change emc rate: %d\n", err); - return err; + if (!timing) { + dev_err(emc->dev, "no timing for rate %lu min %lu max %lu\n", + rate, min_rate, max_rate); + return -EINVAL; } - return 0; + return timing->rate; } static int tegra_emc_probe(struct platform_device *pdev) @@ -515,57 +534,26 @@ static int tegra_emc_probe(struct platform_device *pdev) return err; } + tegra20_clk_set_emc_round_callback(emc_round_rate, emc); + emc->clk = devm_clk_get(&pdev->dev, "emc"); if (IS_ERR(emc->clk)) { err = PTR_ERR(emc->clk); dev_err(&pdev->dev, "failed to get emc clock: %d\n", err); - return err; - } - - emc->pll_m = clk_get_sys(NULL, "pll_m"); - if (IS_ERR(emc->pll_m)) { - err = PTR_ERR(emc->pll_m); - dev_err(&pdev->dev, "failed to get pll_m clock: %d\n", err); - return err; - } - - emc->backup_clk = clk_get_sys(NULL, "pll_p"); - if (IS_ERR(emc->backup_clk)) { - err = PTR_ERR(emc->backup_clk); - dev_err(&pdev->dev, "failed to get pll_p clock: %d\n", err); - goto put_pll_m; - } - - emc->emc_mux = clk_get_parent(emc->clk); - if (IS_ERR(emc->emc_mux)) { - err = PTR_ERR(emc->emc_mux); - dev_err(&pdev->dev, "failed to get emc_mux clock: %d\n", err); - goto put_backup; + goto unset_cb; } err = clk_notifier_register(emc->clk, &emc->clk_nb); if (err) { dev_err(&pdev->dev, "failed to register clk notifier: %d\n", err); - goto put_backup; - } - - /* set DRAM clock rate to maximum */ - err = emc_init(emc, emc->timings[emc->num_timings - 1].rate); - if (err) { - dev_err(&pdev->dev, "failed to initialize EMC clock rate: %d\n", - err); - goto unreg_notifier; + goto unset_cb; } return 0; -unreg_notifier: - clk_notifier_unregister(emc->clk, &emc->clk_nb); -put_backup: - clk_put(emc->backup_clk); -put_pll_m: - clk_put(emc->pll_m); +unset_cb: + tegra20_clk_set_emc_round_callback(NULL, NULL); return err; } diff --git a/drivers/memory/tegra/tegra30-emc.c b/drivers/memory/tegra/tegra30-emc.c new file mode 100644 index 000000000000..6929980bf907 --- /dev/null +++ b/drivers/memory/tegra/tegra30-emc.c @@ -0,0 +1,1232 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * Tegra30 External Memory Controller driver + * + * Based on downstream driver from NVIDIA and tegra124-emc.c + * Copyright (C) 2011-2014 NVIDIA Corporation + * + * Author: Dmitry Osipenko <digetx@gmail.com> + * Copyright (C) 2019 GRATE-DRIVER project + */ + +#include <linux/clk.h> +#include <linux/clk/tegra.h> +#include <linux/completion.h> +#include <linux/delay.h> +#include <linux/err.h> +#include <linux/interrupt.h> +#include <linux/io.h> +#include <linux/iopoll.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/of_platform.h> +#include <linux/platform_device.h> +#include <linux/sort.h> +#include <linux/types.h> + +#include <soc/tegra/fuse.h> + +#include "mc.h" + +#define EMC_INTSTATUS 0x000 +#define EMC_INTMASK 0x004 +#define EMC_DBG 0x008 +#define EMC_CFG 0x00c +#define EMC_REFCTRL 0x020 +#define EMC_TIMING_CONTROL 0x028 +#define EMC_RC 0x02c +#define EMC_RFC 0x030 +#define EMC_RAS 0x034 +#define EMC_RP 0x038 +#define EMC_R2W 0x03c +#define EMC_W2R 0x040 +#define EMC_R2P 0x044 +#define EMC_W2P 0x048 +#define EMC_RD_RCD 0x04c +#define EMC_WR_RCD 0x050 +#define EMC_RRD 0x054 +#define EMC_REXT 0x058 +#define EMC_WDV 0x05c +#define EMC_QUSE 0x060 +#define EMC_QRST 0x064 +#define EMC_QSAFE 0x068 +#define EMC_RDV 0x06c +#define EMC_REFRESH 0x070 +#define EMC_BURST_REFRESH_NUM 0x074 +#define EMC_PDEX2WR 0x078 +#define EMC_PDEX2RD 0x07c +#define EMC_PCHG2PDEN 0x080 +#define EMC_ACT2PDEN 0x084 +#define EMC_AR2PDEN 0x088 +#define EMC_RW2PDEN 0x08c +#define EMC_TXSR 0x090 +#define EMC_TCKE 0x094 +#define EMC_TFAW 0x098 +#define EMC_TRPAB 0x09c +#define EMC_TCLKSTABLE 0x0a0 +#define EMC_TCLKSTOP 0x0a4 +#define EMC_TREFBW 0x0a8 +#define EMC_QUSE_EXTRA 0x0ac +#define EMC_ODT_WRITE 0x0b0 +#define EMC_ODT_READ 0x0b4 +#define EMC_WEXT 0x0b8 +#define EMC_CTT 0x0bc +#define EMC_MRS_WAIT_CNT 0x0c8 +#define EMC_MRS 0x0cc +#define EMC_EMRS 0x0d0 +#define EMC_SELF_REF 0x0e0 +#define EMC_MRW 0x0e8 +#define EMC_XM2DQSPADCTRL3 0x0f8 +#define EMC_FBIO_SPARE 0x100 +#define EMC_FBIO_CFG5 0x104 +#define EMC_FBIO_CFG6 0x114 +#define EMC_CFG_RSV 0x120 +#define EMC_AUTO_CAL_CONFIG 0x2a4 +#define EMC_AUTO_CAL_INTERVAL 0x2a8 +#define EMC_AUTO_CAL_STATUS 0x2ac +#define EMC_STATUS 0x2b4 +#define EMC_CFG_2 0x2b8 +#define EMC_CFG_DIG_DLL 0x2bc +#define EMC_CFG_DIG_DLL_PERIOD 0x2c0 +#define EMC_CTT_DURATION 0x2d8 +#define EMC_CTT_TERM_CTRL 0x2dc +#define EMC_ZCAL_INTERVAL 0x2e0 +#define EMC_ZCAL_WAIT_CNT 0x2e4 +#define EMC_ZQ_CAL 0x2ec +#define EMC_XM2CMDPADCTRL 0x2f0 +#define EMC_XM2DQSPADCTRL2 0x2fc +#define EMC_XM2DQPADCTRL2 0x304 +#define EMC_XM2CLKPADCTRL 0x308 +#define EMC_XM2COMPPADCTRL 0x30c +#define EMC_XM2VTTGENPADCTRL 0x310 +#define EMC_XM2VTTGENPADCTRL2 0x314 +#define EMC_XM2QUSEPADCTRL 0x318 +#define EMC_DLL_XFORM_DQS0 0x328 +#define EMC_DLL_XFORM_DQS1 0x32c +#define EMC_DLL_XFORM_DQS2 0x330 +#define EMC_DLL_XFORM_DQS3 0x334 +#define EMC_DLL_XFORM_DQS4 0x338 +#define EMC_DLL_XFORM_DQS5 0x33c +#define EMC_DLL_XFORM_DQS6 0x340 +#define EMC_DLL_XFORM_DQS7 0x344 +#define EMC_DLL_XFORM_QUSE0 0x348 +#define EMC_DLL_XFORM_QUSE1 0x34c +#define EMC_DLL_XFORM_QUSE2 0x350 +#define EMC_DLL_XFORM_QUSE3 0x354 +#define EMC_DLL_XFORM_QUSE4 0x358 +#define EMC_DLL_XFORM_QUSE5 0x35c +#define EMC_DLL_XFORM_QUSE6 0x360 +#define EMC_DLL_XFORM_QUSE7 0x364 +#define EMC_DLL_XFORM_DQ0 0x368 +#define EMC_DLL_XFORM_DQ1 0x36c +#define EMC_DLL_XFORM_DQ2 0x370 +#define EMC_DLL_XFORM_DQ3 0x374 +#define EMC_DLI_TRIM_TXDQS0 0x3a8 +#define EMC_DLI_TRIM_TXDQS1 0x3ac +#define EMC_DLI_TRIM_TXDQS2 0x3b0 +#define EMC_DLI_TRIM_TXDQS3 0x3b4 +#define EMC_DLI_TRIM_TXDQS4 0x3b8 +#define EMC_DLI_TRIM_TXDQS5 0x3bc +#define EMC_DLI_TRIM_TXDQS6 0x3c0 +#define EMC_DLI_TRIM_TXDQS7 0x3c4 +#define EMC_STALL_THEN_EXE_BEFORE_CLKCHANGE 0x3c8 +#define EMC_STALL_THEN_EXE_AFTER_CLKCHANGE 0x3cc +#define EMC_UNSTALL_RW_AFTER_CLKCHANGE 0x3d0 +#define EMC_SEL_DPD_CTRL 0x3d8 +#define EMC_PRE_REFRESH_REQ_CNT 0x3dc +#define EMC_DYN_SELF_REF_CONTROL 0x3e0 +#define EMC_TXSRDLL 0x3e4 + +#define EMC_STATUS_TIMING_UPDATE_STALLED BIT(23) + +#define EMC_MODE_SET_DLL_RESET BIT(8) +#define EMC_MODE_SET_LONG_CNT BIT(26) + +#define EMC_SELF_REF_CMD_ENABLED BIT(0) + +#define DRAM_DEV_SEL_ALL (0 << 30) +#define DRAM_DEV_SEL_0 (2 << 30) +#define DRAM_DEV_SEL_1 (1 << 30) +#define DRAM_BROADCAST(num) \ + ((num) > 1 ? DRAM_DEV_SEL_ALL : DRAM_DEV_SEL_0) + +#define EMC_ZQ_CAL_CMD BIT(0) +#define EMC_ZQ_CAL_LONG BIT(4) +#define EMC_ZQ_CAL_LONG_CMD_DEV0 \ + (DRAM_DEV_SEL_0 | EMC_ZQ_CAL_LONG | EMC_ZQ_CAL_CMD) +#define EMC_ZQ_CAL_LONG_CMD_DEV1 \ + (DRAM_DEV_SEL_1 | EMC_ZQ_CAL_LONG | EMC_ZQ_CAL_CMD) + +#define EMC_DBG_READ_MUX_ASSEMBLY BIT(0) +#define EMC_DBG_WRITE_MUX_ACTIVE BIT(1) +#define EMC_DBG_FORCE_UPDATE BIT(2) +#define EMC_DBG_CFG_PRIORITY BIT(24) + +#define EMC_CFG5_QUSE_MODE_SHIFT 13 +#define EMC_CFG5_QUSE_MODE_MASK (7 << EMC_CFG5_QUSE_MODE_SHIFT) + +#define EMC_CFG5_QUSE_MODE_INTERNAL_LPBK 2 +#define EMC_CFG5_QUSE_MODE_PULSE_INTERN 3 + +#define EMC_SEL_DPD_CTRL_QUSE_DPD_ENABLE BIT(9) + +#define EMC_XM2COMPPADCTRL_VREF_CAL_ENABLE BIT(10) + +#define EMC_XM2QUSEPADCTRL_IVREF_ENABLE BIT(4) + +#define EMC_XM2DQSPADCTRL2_VREF_ENABLE BIT(5) +#define EMC_XM2DQSPADCTRL3_VREF_ENABLE BIT(5) + +#define EMC_AUTO_CAL_STATUS_ACTIVE BIT(31) + +#define EMC_FBIO_CFG5_DRAM_TYPE_MASK 0x3 + +#define EMC_MRS_WAIT_CNT_SHORT_WAIT_MASK 0x3ff +#define EMC_MRS_WAIT_CNT_LONG_WAIT_SHIFT 16 +#define EMC_MRS_WAIT_CNT_LONG_WAIT_MASK \ + (0x3ff << EMC_MRS_WAIT_CNT_LONG_WAIT_SHIFT) + +#define EMC_REFCTRL_DEV_SEL_MASK 0x3 +#define EMC_REFCTRL_ENABLE BIT(31) +#define EMC_REFCTRL_ENABLE_ALL(num) \ + (((num) > 1 ? 0 : 2) | EMC_REFCTRL_ENABLE) +#define EMC_REFCTRL_DISABLE_ALL(num) ((num) > 1 ? 0 : 2) + +#define EMC_CFG_PERIODIC_QRST BIT(21) +#define EMC_CFG_DYN_SREF_ENABLE BIT(28) + +#define EMC_CLKCHANGE_REQ_ENABLE BIT(0) +#define EMC_CLKCHANGE_PD_ENABLE BIT(1) +#define EMC_CLKCHANGE_SR_ENABLE BIT(2) + +#define EMC_TIMING_UPDATE BIT(0) + +#define EMC_REFRESH_OVERFLOW_INT BIT(3) +#define EMC_CLKCHANGE_COMPLETE_INT BIT(4) + +enum emc_dram_type { + DRAM_TYPE_DDR3, + DRAM_TYPE_DDR1, + DRAM_TYPE_LPDDR2, + DRAM_TYPE_DDR2, +}; + +enum emc_dll_change { + DLL_CHANGE_NONE, + DLL_CHANGE_ON, + DLL_CHANGE_OFF +}; + +static const u16 emc_timing_registers[] = { + [0] = EMC_RC, + [1] = EMC_RFC, + [2] = EMC_RAS, + [3] = EMC_RP, + [4] = EMC_R2W, + [5] = EMC_W2R, + [6] = EMC_R2P, + [7] = EMC_W2P, + [8] = EMC_RD_RCD, + [9] = EMC_WR_RCD, + [10] = EMC_RRD, + [11] = EMC_REXT, + [12] = EMC_WEXT, + [13] = EMC_WDV, + [14] = EMC_QUSE, + [15] = EMC_QRST, + [16] = EMC_QSAFE, + [17] = EMC_RDV, + [18] = EMC_REFRESH, + [19] = EMC_BURST_REFRESH_NUM, + [20] = EMC_PRE_REFRESH_REQ_CNT, + [21] = EMC_PDEX2WR, + [22] = EMC_PDEX2RD, + [23] = EMC_PCHG2PDEN, + [24] = EMC_ACT2PDEN, + [25] = EMC_AR2PDEN, + [26] = EMC_RW2PDEN, + [27] = EMC_TXSR, + [28] = EMC_TXSRDLL, + [29] = EMC_TCKE, + [30] = EMC_TFAW, + [31] = EMC_TRPAB, + [32] = EMC_TCLKSTABLE, + [33] = EMC_TCLKSTOP, + [34] = EMC_TREFBW, + [35] = EMC_QUSE_EXTRA, + [36] = EMC_FBIO_CFG6, + [37] = EMC_ODT_WRITE, + [38] = EMC_ODT_READ, + [39] = EMC_FBIO_CFG5, + [40] = EMC_CFG_DIG_DLL, + [41] = EMC_CFG_DIG_DLL_PERIOD, + [42] = EMC_DLL_XFORM_DQS0, + [43] = EMC_DLL_XFORM_DQS1, + [44] = EMC_DLL_XFORM_DQS2, + [45] = EMC_DLL_XFORM_DQS3, + [46] = EMC_DLL_XFORM_DQS4, + [47] = EMC_DLL_XFORM_DQS5, + [48] = EMC_DLL_XFORM_DQS6, + [49] = EMC_DLL_XFORM_DQS7, + [50] = EMC_DLL_XFORM_QUSE0, + [51] = EMC_DLL_XFORM_QUSE1, + [52] = EMC_DLL_XFORM_QUSE2, + [53] = EMC_DLL_XFORM_QUSE3, + [54] = EMC_DLL_XFORM_QUSE4, + [55] = EMC_DLL_XFORM_QUSE5, + [56] = EMC_DLL_XFORM_QUSE6, + [57] = EMC_DLL_XFORM_QUSE7, + [58] = EMC_DLI_TRIM_TXDQS0, + [59] = EMC_DLI_TRIM_TXDQS1, + [60] = EMC_DLI_TRIM_TXDQS2, + [61] = EMC_DLI_TRIM_TXDQS3, + [62] = EMC_DLI_TRIM_TXDQS4, + [63] = EMC_DLI_TRIM_TXDQS5, + [64] = EMC_DLI_TRIM_TXDQS6, + [65] = EMC_DLI_TRIM_TXDQS7, + [66] = EMC_DLL_XFORM_DQ0, + [67] = EMC_DLL_XFORM_DQ1, + [68] = EMC_DLL_XFORM_DQ2, + [69] = EMC_DLL_XFORM_DQ3, + [70] = EMC_XM2CMDPADCTRL, + [71] = EMC_XM2DQSPADCTRL2, + [72] = EMC_XM2DQPADCTRL2, + [73] = EMC_XM2CLKPADCTRL, + [74] = EMC_XM2COMPPADCTRL, + [75] = EMC_XM2VTTGENPADCTRL, + [76] = EMC_XM2VTTGENPADCTRL2, + [77] = EMC_XM2QUSEPADCTRL, + [78] = EMC_XM2DQSPADCTRL3, + [79] = EMC_CTT_TERM_CTRL, + [80] = EMC_ZCAL_INTERVAL, + [81] = EMC_ZCAL_WAIT_CNT, + [82] = EMC_MRS_WAIT_CNT, + [83] = EMC_AUTO_CAL_CONFIG, + [84] = EMC_CTT, + [85] = EMC_CTT_DURATION, + [86] = EMC_DYN_SELF_REF_CONTROL, + [87] = EMC_FBIO_SPARE, + [88] = EMC_CFG_RSV, +}; + +struct emc_timing { + unsigned long rate; + + u32 data[ARRAY_SIZE(emc_timing_registers)]; + + u32 emc_auto_cal_interval; + u32 emc_mode_1; + u32 emc_mode_2; + u32 emc_mode_reset; + u32 emc_zcal_cnt_long; + bool emc_cfg_periodic_qrst; + bool emc_cfg_dyn_self_ref; +}; + +struct tegra_emc { + struct device *dev; + struct tegra_mc *mc; + struct completion clk_handshake_complete; + struct notifier_block clk_nb; + struct clk *clk; + void __iomem *regs; + unsigned int irq; + + struct emc_timing *timings; + unsigned int num_timings; + + u32 mc_override; + u32 emc_cfg; + + u32 emc_mode_1; + u32 emc_mode_2; + u32 emc_mode_reset; + + bool vref_cal_toggle : 1; + bool zcal_long : 1; + bool dll_on : 1; + bool prepared : 1; + bool bad_state : 1; +}; + +static irqreturn_t tegra_emc_isr(int irq, void *data) +{ + struct tegra_emc *emc = data; + u32 intmask = EMC_REFRESH_OVERFLOW_INT | EMC_CLKCHANGE_COMPLETE_INT; + u32 status; + + status = readl_relaxed(emc->regs + EMC_INTSTATUS) & intmask; + if (!status) + return IRQ_NONE; + + /* notify about EMC-CAR handshake completion */ + if (status & EMC_CLKCHANGE_COMPLETE_INT) + complete(&emc->clk_handshake_complete); + + /* notify about HW problem */ + if (status & EMC_REFRESH_OVERFLOW_INT) + dev_err_ratelimited(emc->dev, + "refresh request overflow timeout\n"); + + /* clear interrupts */ + writel_relaxed(status, emc->regs + EMC_INTSTATUS); + + return IRQ_HANDLED; +} + +static struct emc_timing *emc_find_timing(struct tegra_emc *emc, + unsigned long rate) +{ + struct emc_timing *timing = NULL; + unsigned int i; + + for (i = 0; i < emc->num_timings; i++) { + if (emc->timings[i].rate >= rate) { + timing = &emc->timings[i]; + break; + } + } + + if (!timing) { + dev_err(emc->dev, "no timing for rate %lu\n", rate); + return NULL; + } + + return timing; +} + +static bool emc_dqs_preset(struct tegra_emc *emc, struct emc_timing *timing, + bool *schmitt_to_vref) +{ + bool preset = false; + u32 val; + + if (timing->data[71] & EMC_XM2DQSPADCTRL2_VREF_ENABLE) { + val = readl_relaxed(emc->regs + EMC_XM2DQSPADCTRL2); + + if (!(val & EMC_XM2DQSPADCTRL2_VREF_ENABLE)) { + val |= EMC_XM2DQSPADCTRL2_VREF_ENABLE; + writel_relaxed(val, emc->regs + EMC_XM2DQSPADCTRL2); + + preset = true; + } + } + + if (timing->data[78] & EMC_XM2DQSPADCTRL3_VREF_ENABLE) { + val = readl_relaxed(emc->regs + EMC_XM2DQSPADCTRL3); + + if (!(val & EMC_XM2DQSPADCTRL3_VREF_ENABLE)) { + val |= EMC_XM2DQSPADCTRL3_VREF_ENABLE; + writel_relaxed(val, emc->regs + EMC_XM2DQSPADCTRL3); + + preset = true; + } + } + + if (timing->data[77] & EMC_XM2QUSEPADCTRL_IVREF_ENABLE) { + val = readl_relaxed(emc->regs + EMC_XM2QUSEPADCTRL); + + if (!(val & EMC_XM2QUSEPADCTRL_IVREF_ENABLE)) { + val |= EMC_XM2QUSEPADCTRL_IVREF_ENABLE; + writel_relaxed(val, emc->regs + EMC_XM2QUSEPADCTRL); + + *schmitt_to_vref = true; + preset = true; + } + } + + return preset; +} + +static int emc_seq_update_timing(struct tegra_emc *emc) +{ + u32 val; + int err; + + writel_relaxed(EMC_TIMING_UPDATE, emc->regs + EMC_TIMING_CONTROL); + + err = readl_relaxed_poll_timeout_atomic(emc->regs + EMC_STATUS, val, + !(val & EMC_STATUS_TIMING_UPDATE_STALLED), + 1, 200); + if (err) { + dev_err(emc->dev, "failed to update timing: %d\n", err); + return err; + } + + return 0; +} + +static int emc_prepare_mc_clk_cfg(struct tegra_emc *emc, unsigned long rate) +{ + struct tegra_mc *mc = emc->mc; + unsigned int misc0_index = 16; + unsigned int i; + bool same; + + for (i = 0; i < mc->num_timings; i++) { + if (mc->timings[i].rate != rate) + continue; + + if (mc->timings[i].emem_data[misc0_index] & BIT(27)) + same = true; + else + same = false; + + return tegra20_clk_prepare_emc_mc_same_freq(emc->clk, same); + } + + return -EINVAL; +} + +static int emc_prepare_timing_change(struct tegra_emc *emc, unsigned long rate) +{ + struct emc_timing *timing = emc_find_timing(emc, rate); + enum emc_dll_change dll_change; + enum emc_dram_type dram_type; + bool schmitt_to_vref = false; + unsigned int pre_wait = 0; + bool qrst_used = false; + unsigned int dram_num; + unsigned int i; + u32 fbio_cfg5; + u32 emc_dbg; + u32 val; + int err; + + if (!timing || emc->bad_state) + return -EINVAL; + + dev_dbg(emc->dev, "%s: using timing rate %lu for requested rate %lu\n", + __func__, timing->rate, rate); + + emc->bad_state = true; + + err = emc_prepare_mc_clk_cfg(emc, rate); + if (err) { + dev_err(emc->dev, "mc clock preparation failed: %d\n", err); + return err; + } + + emc->vref_cal_toggle = false; + emc->mc_override = mc_readl(emc->mc, MC_EMEM_ARB_OVERRIDE); + emc->emc_cfg = readl_relaxed(emc->regs + EMC_CFG); + emc_dbg = readl_relaxed(emc->regs + EMC_DBG); + + if (emc->dll_on == !!(timing->emc_mode_1 & 0x1)) + dll_change = DLL_CHANGE_NONE; + else if (timing->emc_mode_1 & 0x1) + dll_change = DLL_CHANGE_ON; + else + dll_change = DLL_CHANGE_OFF; + + emc->dll_on = !!(timing->emc_mode_1 & 0x1); + + if (timing->data[80] && !readl_relaxed(emc->regs + EMC_ZCAL_INTERVAL)) + emc->zcal_long = true; + else + emc->zcal_long = false; + + fbio_cfg5 = readl_relaxed(emc->regs + EMC_FBIO_CFG5); + dram_type = fbio_cfg5 & EMC_FBIO_CFG5_DRAM_TYPE_MASK; + + dram_num = tegra_mc_get_emem_device_count(emc->mc); + + /* disable dynamic self-refresh */ + if (emc->emc_cfg & EMC_CFG_DYN_SREF_ENABLE) { + emc->emc_cfg &= ~EMC_CFG_DYN_SREF_ENABLE; + writel_relaxed(emc->emc_cfg, emc->regs + EMC_CFG); + + pre_wait = 5; + } + + /* update MC arbiter settings */ + val = mc_readl(emc->mc, MC_EMEM_ARB_OUTSTANDING_REQ); + if (!(val & MC_EMEM_ARB_OUTSTANDING_REQ_HOLDOFF_OVERRIDE) || + ((val & MC_EMEM_ARB_OUTSTANDING_REQ_MAX_MASK) > 0x50)) { + + val = MC_EMEM_ARB_OUTSTANDING_REQ_LIMIT_ENABLE | + MC_EMEM_ARB_OUTSTANDING_REQ_HOLDOFF_OVERRIDE | 0x50; + mc_writel(emc->mc, val, MC_EMEM_ARB_OUTSTANDING_REQ); + mc_writel(emc->mc, MC_TIMING_UPDATE, MC_TIMING_CONTROL); + } + + if (emc->mc_override & MC_EMEM_ARB_OVERRIDE_EACK_MASK) + mc_writel(emc->mc, + emc->mc_override & ~MC_EMEM_ARB_OVERRIDE_EACK_MASK, + MC_EMEM_ARB_OVERRIDE); + + /* check DQ/DQS VREF delay */ + if (emc_dqs_preset(emc, timing, &schmitt_to_vref)) { + if (pre_wait < 3) + pre_wait = 3; + } + + if (pre_wait) { + err = emc_seq_update_timing(emc); + if (err) + return err; + + udelay(pre_wait); + } + + /* disable auto-calibration if VREF mode is switching */ + if (timing->emc_auto_cal_interval) { + val = readl_relaxed(emc->regs + EMC_XM2COMPPADCTRL); + val ^= timing->data[74]; + + if (val & EMC_XM2COMPPADCTRL_VREF_CAL_ENABLE) { + writel_relaxed(0, emc->regs + EMC_AUTO_CAL_INTERVAL); + + err = readl_relaxed_poll_timeout_atomic( + emc->regs + EMC_AUTO_CAL_STATUS, val, + !(val & EMC_AUTO_CAL_STATUS_ACTIVE), 1, 300); + if (err) { + dev_err(emc->dev, + "failed to disable auto-cal: %d\n", + err); + return err; + } + + emc->vref_cal_toggle = true; + } + } + + /* program shadow registers */ + for (i = 0; i < ARRAY_SIZE(timing->data); i++) { + /* EMC_XM2CLKPADCTRL should be programmed separately */ + if (i != 73) + writel_relaxed(timing->data[i], + emc->regs + emc_timing_registers[i]); + } + + err = tegra_mc_write_emem_configuration(emc->mc, timing->rate); + if (err) + return err; + + /* DDR3: predict MRS long wait count */ + if (dram_type == DRAM_TYPE_DDR3 && dll_change == DLL_CHANGE_ON) { + u32 cnt = 512; + + if (emc->zcal_long) + cnt -= dram_num * 256; + + val = timing->data[82] & EMC_MRS_WAIT_CNT_SHORT_WAIT_MASK; + if (cnt < val) + cnt = val; + + val = timing->data[82] & ~EMC_MRS_WAIT_CNT_LONG_WAIT_MASK; + val |= (cnt << EMC_MRS_WAIT_CNT_LONG_WAIT_SHIFT) & + EMC_MRS_WAIT_CNT_LONG_WAIT_MASK; + + writel_relaxed(val, emc->regs + EMC_MRS_WAIT_CNT); + } + + /* disable interrupt since read access is prohibited after stalling */ + disable_irq(emc->irq); + + /* this read also completes the writes */ + val = readl_relaxed(emc->regs + EMC_SEL_DPD_CTRL); + + if (!(val & EMC_SEL_DPD_CTRL_QUSE_DPD_ENABLE) && schmitt_to_vref) { + u32 cur_mode, new_mode; + + cur_mode = fbio_cfg5 & EMC_CFG5_QUSE_MODE_MASK; + cur_mode >>= EMC_CFG5_QUSE_MODE_SHIFT; + + new_mode = timing->data[39] & EMC_CFG5_QUSE_MODE_MASK; + new_mode >>= EMC_CFG5_QUSE_MODE_SHIFT; + + if ((cur_mode != EMC_CFG5_QUSE_MODE_PULSE_INTERN && + cur_mode != EMC_CFG5_QUSE_MODE_INTERNAL_LPBK) || + (new_mode != EMC_CFG5_QUSE_MODE_PULSE_INTERN && + new_mode != EMC_CFG5_QUSE_MODE_INTERNAL_LPBK)) + qrst_used = true; + } + + /* flow control marker 1 */ + writel_relaxed(0x1, emc->regs + EMC_STALL_THEN_EXE_BEFORE_CLKCHANGE); + + /* enable periodic reset */ + if (qrst_used) { + writel_relaxed(emc_dbg | EMC_DBG_WRITE_MUX_ACTIVE, + emc->regs + EMC_DBG); + writel_relaxed(emc->emc_cfg | EMC_CFG_PERIODIC_QRST, + emc->regs + EMC_CFG); + writel_relaxed(emc_dbg, emc->regs + EMC_DBG); + } + + /* disable auto-refresh to save time after clock change */ + writel_relaxed(EMC_REFCTRL_DISABLE_ALL(dram_num), + emc->regs + EMC_REFCTRL); + + /* turn off DLL and enter self-refresh on DDR3 */ + if (dram_type == DRAM_TYPE_DDR3) { + if (dll_change == DLL_CHANGE_OFF) + writel_relaxed(timing->emc_mode_1, + emc->regs + EMC_EMRS); + + writel_relaxed(DRAM_BROADCAST(dram_num) | + EMC_SELF_REF_CMD_ENABLED, + emc->regs + EMC_SELF_REF); + } + + /* flow control marker 2 */ + writel_relaxed(0x1, emc->regs + EMC_STALL_THEN_EXE_AFTER_CLKCHANGE); + + /* enable write-active MUX, update unshadowed pad control */ + writel_relaxed(emc_dbg | EMC_DBG_WRITE_MUX_ACTIVE, emc->regs + EMC_DBG); + writel_relaxed(timing->data[73], emc->regs + EMC_XM2CLKPADCTRL); + + /* restore periodic QRST and disable write-active MUX */ + val = !!(emc->emc_cfg & EMC_CFG_PERIODIC_QRST); + if (qrst_used || timing->emc_cfg_periodic_qrst != val) { + if (timing->emc_cfg_periodic_qrst) + emc->emc_cfg |= EMC_CFG_PERIODIC_QRST; + else + emc->emc_cfg &= ~EMC_CFG_PERIODIC_QRST; + + writel_relaxed(emc->emc_cfg, emc->regs + EMC_CFG); + } + writel_relaxed(emc_dbg, emc->regs + EMC_DBG); + + /* exit self-refresh on DDR3 */ + if (dram_type == DRAM_TYPE_DDR3) + writel_relaxed(DRAM_BROADCAST(dram_num), + emc->regs + EMC_SELF_REF); + + /* set DRAM-mode registers */ + if (dram_type == DRAM_TYPE_DDR3) { + if (timing->emc_mode_1 != emc->emc_mode_1) + writel_relaxed(timing->emc_mode_1, + emc->regs + EMC_EMRS); + + if (timing->emc_mode_2 != emc->emc_mode_2) + writel_relaxed(timing->emc_mode_2, + emc->regs + EMC_EMRS); + + if (timing->emc_mode_reset != emc->emc_mode_reset || + dll_change == DLL_CHANGE_ON) { + val = timing->emc_mode_reset; + if (dll_change == DLL_CHANGE_ON) { + val |= EMC_MODE_SET_DLL_RESET; + val |= EMC_MODE_SET_LONG_CNT; + } else { + val &= ~EMC_MODE_SET_DLL_RESET; + } + writel_relaxed(val, emc->regs + EMC_MRS); + } + } else { + if (timing->emc_mode_2 != emc->emc_mode_2) + writel_relaxed(timing->emc_mode_2, + emc->regs + EMC_MRW); + + if (timing->emc_mode_1 != emc->emc_mode_1) + writel_relaxed(timing->emc_mode_1, + emc->regs + EMC_MRW); + } + + emc->emc_mode_1 = timing->emc_mode_1; + emc->emc_mode_2 = timing->emc_mode_2; + emc->emc_mode_reset = timing->emc_mode_reset; + + /* issue ZCAL command if turning ZCAL on */ + if (emc->zcal_long) { + writel_relaxed(EMC_ZQ_CAL_LONG_CMD_DEV0, + emc->regs + EMC_ZQ_CAL); + + if (dram_num > 1) + writel_relaxed(EMC_ZQ_CAL_LONG_CMD_DEV1, + emc->regs + EMC_ZQ_CAL); + } + + /* re-enable auto-refresh */ + writel_relaxed(EMC_REFCTRL_ENABLE_ALL(dram_num), + emc->regs + EMC_REFCTRL); + + /* flow control marker 3 */ + writel_relaxed(0x1, emc->regs + EMC_UNSTALL_RW_AFTER_CLKCHANGE); + + reinit_completion(&emc->clk_handshake_complete); + + /* interrupt can be re-enabled now */ + enable_irq(emc->irq); + + emc->bad_state = false; + emc->prepared = true; + + return 0; +} + +static int emc_complete_timing_change(struct tegra_emc *emc, + unsigned long rate) +{ + struct emc_timing *timing = emc_find_timing(emc, rate); + unsigned long timeout; + int ret; + + timeout = wait_for_completion_timeout(&emc->clk_handshake_complete, + msecs_to_jiffies(100)); + if (timeout == 0) { + dev_err(emc->dev, "emc-car handshake failed\n"); + emc->bad_state = true; + return -EIO; + } + + /* restore auto-calibration */ + if (emc->vref_cal_toggle) + writel_relaxed(timing->emc_auto_cal_interval, + emc->regs + EMC_AUTO_CAL_INTERVAL); + + /* restore dynamic self-refresh */ + if (timing->emc_cfg_dyn_self_ref) { + emc->emc_cfg |= EMC_CFG_DYN_SREF_ENABLE; + writel_relaxed(emc->emc_cfg, emc->regs + EMC_CFG); + } + + /* set number of clocks to wait after each ZQ command */ + if (emc->zcal_long) + writel_relaxed(timing->emc_zcal_cnt_long, + emc->regs + EMC_ZCAL_WAIT_CNT); + + udelay(2); + /* update restored timing */ + ret = emc_seq_update_timing(emc); + if (ret) + emc->bad_state = true; + + /* restore early ACK */ + mc_writel(emc->mc, emc->mc_override, MC_EMEM_ARB_OVERRIDE); + + emc->prepared = false; + + return ret; +} + +static int emc_unprepare_timing_change(struct tegra_emc *emc, + unsigned long rate) +{ + if (emc->prepared && !emc->bad_state) { + /* shouldn't ever happen in practice */ + dev_err(emc->dev, "timing configuration can't be reverted\n"); + emc->bad_state = true; + } + + return 0; +} + +static int emc_clk_change_notify(struct notifier_block *nb, + unsigned long msg, void *data) +{ + struct tegra_emc *emc = container_of(nb, struct tegra_emc, clk_nb); + struct clk_notifier_data *cnd = data; + int err; + + switch (msg) { + case PRE_RATE_CHANGE: + err = emc_prepare_timing_change(emc, cnd->new_rate); + break; + + case ABORT_RATE_CHANGE: + err = emc_unprepare_timing_change(emc, cnd->old_rate); + break; + + case POST_RATE_CHANGE: + err = emc_complete_timing_change(emc, cnd->new_rate); + break; + + default: + return NOTIFY_DONE; + } + + return notifier_from_errno(err); +} + +static int load_one_timing_from_dt(struct tegra_emc *emc, + struct emc_timing *timing, + struct device_node *node) +{ + u32 value; + int err; + + err = of_property_read_u32(node, "clock-frequency", &value); + if (err) { + dev_err(emc->dev, "timing %pOF: failed to read rate: %d\n", + node, err); + return err; + } + + timing->rate = value; + + err = of_property_read_u32_array(node, "nvidia,emc-configuration", + timing->data, + ARRAY_SIZE(emc_timing_registers)); + if (err) { + dev_err(emc->dev, + "timing %pOF: failed to read emc timing data: %d\n", + node, err); + return err; + } + +#define EMC_READ_BOOL(prop, dtprop) \ + timing->prop = of_property_read_bool(node, dtprop); + +#define EMC_READ_U32(prop, dtprop) \ + err = of_property_read_u32(node, dtprop, &timing->prop); \ + if (err) { \ + dev_err(emc->dev, \ + "timing %pOFn: failed to read " #prop ": %d\n", \ + node, err); \ + return err; \ + } + + EMC_READ_U32(emc_auto_cal_interval, "nvidia,emc-auto-cal-interval") + EMC_READ_U32(emc_mode_1, "nvidia,emc-mode-1") + EMC_READ_U32(emc_mode_2, "nvidia,emc-mode-2") + EMC_READ_U32(emc_mode_reset, "nvidia,emc-mode-reset") + EMC_READ_U32(emc_zcal_cnt_long, "nvidia,emc-zcal-cnt-long") + EMC_READ_BOOL(emc_cfg_dyn_self_ref, "nvidia,emc-cfg-dyn-self-ref") + EMC_READ_BOOL(emc_cfg_periodic_qrst, "nvidia,emc-cfg-periodic-qrst") + +#undef EMC_READ_U32 +#undef EMC_READ_BOOL + + dev_dbg(emc->dev, "%s: %pOF: rate %lu\n", __func__, node, timing->rate); + + return 0; +} + +static int cmp_timings(const void *_a, const void *_b) +{ + const struct emc_timing *a = _a; + const struct emc_timing *b = _b; + + if (a->rate < b->rate) + return -1; + + if (a->rate > b->rate) + return 1; + + return 0; +} + +static int emc_check_mc_timings(struct tegra_emc *emc) +{ + struct tegra_mc *mc = emc->mc; + unsigned int i; + + if (emc->num_timings != mc->num_timings) { + dev_err(emc->dev, "emc/mc timings number mismatch: %u %u\n", + emc->num_timings, mc->num_timings); + return -EINVAL; + } + + for (i = 0; i < mc->num_timings; i++) { + if (emc->timings[i].rate != mc->timings[i].rate) { + dev_err(emc->dev, + "emc/mc timing rate mismatch: %lu %lu\n", + emc->timings[i].rate, mc->timings[i].rate); + return -EINVAL; + } + } + + return 0; +} + +static int emc_load_timings_from_dt(struct tegra_emc *emc, + struct device_node *node) +{ + struct device_node *child; + struct emc_timing *timing; + int child_count; + int err; + + child_count = of_get_child_count(node); + if (!child_count) { + dev_err(emc->dev, "no memory timings in: %pOF\n", node); + return -EINVAL; + } + + emc->timings = devm_kcalloc(emc->dev, child_count, sizeof(*timing), + GFP_KERNEL); + if (!emc->timings) + return -ENOMEM; + + emc->num_timings = child_count; + timing = emc->timings; + + for_each_child_of_node(node, child) { + err = load_one_timing_from_dt(emc, timing++, child); + if (err) { + of_node_put(child); + return err; + } + } + + sort(emc->timings, emc->num_timings, sizeof(*timing), cmp_timings, + NULL); + + err = emc_check_mc_timings(emc); + if (err) + return err; + + dev_info(emc->dev, + "got %u timings for RAM code %u (min %luMHz max %luMHz)\n", + emc->num_timings, + tegra_read_ram_code(), + emc->timings[0].rate / 1000000, + emc->timings[emc->num_timings - 1].rate / 1000000); + + return 0; +} + +static struct device_node *emc_find_node_by_ram_code(struct device *dev) +{ + struct device_node *np; + u32 value, ram_code; + int err; + + ram_code = tegra_read_ram_code(); + + for_each_child_of_node(dev->of_node, np) { + err = of_property_read_u32(np, "nvidia,ram-code", &value); + if (err || value != ram_code) + continue; + + return np; + } + + dev_err(dev, "no memory timings for RAM code %u found in device-tree\n", + ram_code); + + return NULL; +} + +static int emc_setup_hw(struct tegra_emc *emc) +{ + u32 intmask = EMC_REFRESH_OVERFLOW_INT | EMC_CLKCHANGE_COMPLETE_INT; + u32 fbio_cfg5, emc_cfg, emc_dbg; + enum emc_dram_type dram_type; + + fbio_cfg5 = readl_relaxed(emc->regs + EMC_FBIO_CFG5); + dram_type = fbio_cfg5 & EMC_FBIO_CFG5_DRAM_TYPE_MASK; + + emc_cfg = readl_relaxed(emc->regs + EMC_CFG_2); + + /* enable EMC and CAR to handshake on PLL divider/source changes */ + emc_cfg |= EMC_CLKCHANGE_REQ_ENABLE; + + /* configure clock change mode accordingly to DRAM type */ + switch (dram_type) { + case DRAM_TYPE_LPDDR2: + emc_cfg |= EMC_CLKCHANGE_PD_ENABLE; + emc_cfg &= ~EMC_CLKCHANGE_SR_ENABLE; + break; + + default: + emc_cfg &= ~EMC_CLKCHANGE_SR_ENABLE; + emc_cfg &= ~EMC_CLKCHANGE_PD_ENABLE; + break; + } + + writel_relaxed(emc_cfg, emc->regs + EMC_CFG_2); + + /* initialize interrupt */ + writel_relaxed(intmask, emc->regs + EMC_INTMASK); + writel_relaxed(0xffffffff, emc->regs + EMC_INTSTATUS); + + /* ensure that unwanted debug features are disabled */ + emc_dbg = readl_relaxed(emc->regs + EMC_DBG); + emc_dbg |= EMC_DBG_CFG_PRIORITY; + emc_dbg &= ~EMC_DBG_READ_MUX_ASSEMBLY; + emc_dbg &= ~EMC_DBG_WRITE_MUX_ACTIVE; + emc_dbg &= ~EMC_DBG_FORCE_UPDATE; + writel_relaxed(emc_dbg, emc->regs + EMC_DBG); + + return 0; +} + +static long emc_round_rate(unsigned long rate, + unsigned long min_rate, + unsigned long max_rate, + void *arg) +{ + struct emc_timing *timing = NULL; + struct tegra_emc *emc = arg; + unsigned int i; + + min_rate = min(min_rate, emc->timings[emc->num_timings - 1].rate); + + for (i = 0; i < emc->num_timings; i++) { + if (emc->timings[i].rate < rate && i != emc->num_timings - 1) + continue; + + if (emc->timings[i].rate > max_rate) { + i = max(i, 1u) - 1; + + if (emc->timings[i].rate < min_rate) + break; + } + + if (emc->timings[i].rate < min_rate) + continue; + + timing = &emc->timings[i]; + break; + } + + if (!timing) { + dev_err(emc->dev, "no timing for rate %lu min %lu max %lu\n", + rate, min_rate, max_rate); + return -EINVAL; + } + + return timing->rate; +} + +static int tegra_emc_probe(struct platform_device *pdev) +{ + struct platform_device *mc; + struct device_node *np; + struct tegra_emc *emc; + int err; + + if (of_get_child_count(pdev->dev.of_node) == 0) { + dev_info(&pdev->dev, + "device-tree node doesn't have memory timings\n"); + return 0; + } + + np = of_parse_phandle(pdev->dev.of_node, "nvidia,memory-controller", 0); + if (!np) { + dev_err(&pdev->dev, "could not get memory controller node\n"); + return -ENOENT; + } + + mc = of_find_device_by_node(np); + of_node_put(np); + if (!mc) + return -ENOENT; + + np = emc_find_node_by_ram_code(&pdev->dev); + if (!np) + return -EINVAL; + + emc = devm_kzalloc(&pdev->dev, sizeof(*emc), GFP_KERNEL); + if (!emc) { + of_node_put(np); + return -ENOMEM; + } + + emc->mc = platform_get_drvdata(mc); + if (!emc->mc) + return -EPROBE_DEFER; + + init_completion(&emc->clk_handshake_complete); + emc->clk_nb.notifier_call = emc_clk_change_notify; + emc->dev = &pdev->dev; + + err = emc_load_timings_from_dt(emc, np); + of_node_put(np); + if (err) + return err; + + emc->regs = devm_platform_ioremap_resource(pdev, 0); + if (IS_ERR(emc->regs)) + return PTR_ERR(emc->regs); + + err = emc_setup_hw(emc); + if (err) + return err; + + err = platform_get_irq(pdev, 0); + if (err < 0) { + dev_err(&pdev->dev, "interrupt not specified: %d\n", err); + return err; + } + emc->irq = err; + + err = devm_request_irq(&pdev->dev, emc->irq, tegra_emc_isr, 0, + dev_name(&pdev->dev), emc); + if (err) { + dev_err(&pdev->dev, "failed to request irq: %d\n", err); + return err; + } + + tegra20_clk_set_emc_round_callback(emc_round_rate, emc); + + emc->clk = devm_clk_get(&pdev->dev, "emc"); + if (IS_ERR(emc->clk)) { + err = PTR_ERR(emc->clk); + dev_err(&pdev->dev, "failed to get emc clock: %d\n", err); + goto unset_cb; + } + + err = clk_notifier_register(emc->clk, &emc->clk_nb); + if (err) { + dev_err(&pdev->dev, "failed to register clk notifier: %d\n", + err); + goto unset_cb; + } + + platform_set_drvdata(pdev, emc); + + return 0; + +unset_cb: + tegra20_clk_set_emc_round_callback(NULL, NULL); + + return err; +} + +static int tegra_emc_suspend(struct device *dev) +{ + struct tegra_emc *emc = dev_get_drvdata(dev); + + /* + * Suspending in a bad state will hang machine. The "prepared" var + * shall be always false here unless it's a kernel bug that caused + * suspending in a wrong order. + */ + if (WARN_ON(emc->prepared) || emc->bad_state) + return -EINVAL; + + emc->bad_state = true; + + return 0; +} + +static int tegra_emc_resume(struct device *dev) +{ + struct tegra_emc *emc = dev_get_drvdata(dev); + + emc_setup_hw(emc); + emc->bad_state = false; + + return 0; +} + +static const struct dev_pm_ops tegra_emc_pm_ops = { + .suspend = tegra_emc_suspend, + .resume = tegra_emc_resume, +}; + +static const struct of_device_id tegra_emc_of_match[] = { + { .compatible = "nvidia,tegra30-emc", }, + {}, +}; + +static struct platform_driver tegra_emc_driver = { + .probe = tegra_emc_probe, + .driver = { + .name = "tegra30-emc", + .of_match_table = tegra_emc_of_match, + .pm = &tegra_emc_pm_ops, + .suppress_bind_attrs = true, + }, +}; + +static int __init tegra_emc_init(void) +{ + return platform_driver_register(&tegra_emc_driver); +} +subsys_initcall(tegra_emc_init); diff --git a/drivers/memory/tegra/tegra30.c b/drivers/memory/tegra/tegra30.c index 14788fc2f9e8..fcdd812eed80 100644 --- a/drivers/memory/tegra/tegra30.c +++ b/drivers/memory/tegra/tegra30.c @@ -10,6 +10,27 @@ #include "mc.h" +static const unsigned long tegra30_mc_emem_regs[] = { + MC_EMEM_ARB_CFG, + MC_EMEM_ARB_OUTSTANDING_REQ, + MC_EMEM_ARB_TIMING_RCD, + MC_EMEM_ARB_TIMING_RP, + MC_EMEM_ARB_TIMING_RC, + MC_EMEM_ARB_TIMING_RAS, + MC_EMEM_ARB_TIMING_FAW, + MC_EMEM_ARB_TIMING_RRD, + MC_EMEM_ARB_TIMING_RAP2PRE, + MC_EMEM_ARB_TIMING_WAP2PRE, + MC_EMEM_ARB_TIMING_R2R, + MC_EMEM_ARB_TIMING_W2W, + MC_EMEM_ARB_TIMING_R2W, + MC_EMEM_ARB_TIMING_W2R, + MC_EMEM_ARB_DA_TURNS, + MC_EMEM_ARB_DA_COVERS, + MC_EMEM_ARB_MISC0, + MC_EMEM_ARB_RING1_THROTTLE, +}; + static const struct tegra_mc_client tegra30_mc_clients[] = { { .id = 0x00, @@ -931,16 +952,19 @@ static const struct tegra_smmu_swgroup tegra30_swgroups[] = { { .name = "isp", .swgroup = TEGRA_SWGROUP_ISP, .reg = 0x258 }, }; -static const unsigned int tegra30_group_display[] = { +static const unsigned int tegra30_group_drm[] = { TEGRA_SWGROUP_DC, TEGRA_SWGROUP_DCB, + TEGRA_SWGROUP_G2, + TEGRA_SWGROUP_NV, + TEGRA_SWGROUP_NV2, }; static const struct tegra_smmu_group_soc tegra30_groups[] = { { - .name = "display", - .swgroups = tegra30_group_display, - .num_swgroups = ARRAY_SIZE(tegra30_group_display), + .name = "drm", + .swgroups = tegra30_group_drm, + .num_swgroups = ARRAY_SIZE(tegra30_group_drm), }, }; @@ -994,6 +1018,8 @@ const struct tegra_mc_soc tegra30_mc_soc = { .atom_size = 16, .client_id_mask = 0x7f, .smmu = &tegra30_smmu_soc, + .emem_regs = tegra30_mc_emem_regs, + .num_emem_regs = ARRAY_SIZE(tegra30_mc_emem_regs), .intmask = MC_INT_INVALID_SMMU_PAGE | MC_INT_SECURITY_VIOLATION | MC_INT_DECERR_EMEM, .reset_ops = &tegra_mc_reset_ops_common, |