diff options
Diffstat (limited to 'drivers/memory/tegra/tegra20-emc.c')
-rw-r--r-- | drivers/memory/tegra/tegra20-emc.c | 520 |
1 files changed, 470 insertions, 50 deletions
diff --git a/drivers/memory/tegra/tegra20-emc.c b/drivers/memory/tegra/tegra20-emc.c index 027f46287dbf..686aaf477d8a 100644 --- a/drivers/memory/tegra/tegra20-emc.c +++ b/drivers/memory/tegra/tegra20-emc.c @@ -8,19 +8,27 @@ #include <linux/clk.h> #include <linux/clk/tegra.h> #include <linux/debugfs.h> +#include <linux/devfreq.h> #include <linux/err.h> +#include <linux/interconnect-provider.h> #include <linux/interrupt.h> #include <linux/io.h> #include <linux/iopoll.h> #include <linux/kernel.h> #include <linux/module.h> +#include <linux/mutex.h> #include <linux/of.h> #include <linux/platform_device.h> +#include <linux/pm_opp.h> +#include <linux/slab.h> #include <linux/sort.h> #include <linux/types.h> +#include <soc/tegra/common.h> #include <soc/tegra/fuse.h> +#include "mc.h" + #define EMC_INTSTATUS 0x000 #define EMC_INTMASK 0x004 #define EMC_DBG 0x008 @@ -62,6 +70,11 @@ #define EMC_ODT_READ 0x0b4 #define EMC_FBIO_CFG5 0x104 #define EMC_FBIO_CFG6 0x114 +#define EMC_STAT_CONTROL 0x160 +#define EMC_STAT_LLMC_CONTROL 0x178 +#define EMC_STAT_PWR_CLOCK_LIMIT 0x198 +#define EMC_STAT_PWR_CLOCKS 0x19c +#define EMC_STAT_PWR_COUNT 0x1a0 #define EMC_AUTO_CAL_INTERVAL 0x2a8 #define EMC_CFG_2 0x2b8 #define EMC_CFG_DIG_DLL 0x2bc @@ -88,6 +101,12 @@ #define EMC_DBG_READ_DQM_CTRL BIT(9) #define EMC_DBG_CFG_PRIORITY BIT(24) +#define EMC_FBIO_CFG5_DRAM_WIDTH_X16 BIT(4) + +#define EMC_PWR_GATHER_CLEAR (1 << 8) +#define EMC_PWR_GATHER_DISABLE (2 << 8) +#define EMC_PWR_GATHER_ENABLE (3 << 8) + static const u16 emc_timing_registers[] = { EMC_RC, EMC_RFC, @@ -142,11 +161,26 @@ struct emc_timing { u32 data[ARRAY_SIZE(emc_timing_registers)]; }; +enum emc_rate_request_type { + EMC_RATE_DEVFREQ, + EMC_RATE_DEBUG, + EMC_RATE_ICC, + EMC_RATE_TYPE_MAX, +}; + +struct emc_rate_request { + unsigned long min_rate; + unsigned long max_rate; +}; + struct tegra_emc { struct device *dev; + struct tegra_mc *mc; + struct icc_provider provider; struct notifier_block clk_nb; struct clk *clk; void __iomem *regs; + unsigned int dram_bus_width; struct emc_timing *timings; unsigned int num_timings; @@ -156,6 +190,17 @@ struct tegra_emc { unsigned long min_rate; unsigned long max_rate; } debugfs; + + /* + * There are multiple sources in the EMC driver which could request + * a min/max clock rate, these rates are contained in this array. + */ + struct emc_rate_request requested_rate[EMC_RATE_TYPE_MAX]; + + /* protect shared rate-change code path */ + struct mutex rate_lock; + + struct devfreq_simple_ondemand_data ondemand_data; }; static irqreturn_t tegra_emc_isr(int irq, void *data) @@ -383,6 +428,11 @@ tegra_emc_find_node_by_ram_code(struct device *dev) u32 value, ram_code; int err; + if (of_get_child_count(dev->of_node) == 0) { + dev_info(dev, "device-tree doesn't have memory timings\n"); + return NULL; + } + if (!of_property_read_bool(dev->of_node, "nvidia,use-ram-code")) return of_node_get(dev->of_node); @@ -408,7 +458,7 @@ 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; - u32 emc_cfg, emc_dbg; + u32 emc_cfg, emc_dbg, emc_fbio; emc_cfg = readl_relaxed(emc->regs + EMC_CFG_2); @@ -439,6 +489,15 @@ static int emc_setup_hw(struct tegra_emc *emc) emc_dbg &= ~EMC_DBG_FORCE_UPDATE; writel_relaxed(emc_dbg, emc->regs + EMC_DBG); + emc_fbio = readl_relaxed(emc->regs + EMC_FBIO_CFG5); + + if (emc_fbio & EMC_FBIO_CFG5_DRAM_WIDTH_X16) + emc->dram_bus_width = 16; + else + emc->dram_bus_width = 32; + + dev_info(emc->dev, "%ubit DRAM bus\n", emc->dram_bus_width); + return 0; } @@ -451,6 +510,9 @@ static long emc_round_rate(unsigned long rate, struct tegra_emc *emc = arg; unsigned int i; + if (!emc->num_timings) + return clk_get_rate(emc->clk); + min_rate = min(min_rate, emc->timings[emc->num_timings - 1].rate); for (i = 0; i < emc->num_timings; i++) { @@ -480,6 +542,83 @@ static long emc_round_rate(unsigned long rate, return timing->rate; } +static void tegra_emc_rate_requests_init(struct tegra_emc *emc) +{ + unsigned int i; + + for (i = 0; i < EMC_RATE_TYPE_MAX; i++) { + emc->requested_rate[i].min_rate = 0; + emc->requested_rate[i].max_rate = ULONG_MAX; + } +} + +static int emc_request_rate(struct tegra_emc *emc, + unsigned long new_min_rate, + unsigned long new_max_rate, + enum emc_rate_request_type type) +{ + struct emc_rate_request *req = emc->requested_rate; + unsigned long min_rate = 0, max_rate = ULONG_MAX; + unsigned int i; + int err; + + /* select minimum and maximum rates among the requested rates */ + for (i = 0; i < EMC_RATE_TYPE_MAX; i++, req++) { + if (i == type) { + min_rate = max(new_min_rate, min_rate); + max_rate = min(new_max_rate, max_rate); + } else { + min_rate = max(req->min_rate, min_rate); + max_rate = min(req->max_rate, max_rate); + } + } + + if (min_rate > max_rate) { + dev_err_ratelimited(emc->dev, "%s: type %u: out of range: %lu %lu\n", + __func__, type, min_rate, max_rate); + return -ERANGE; + } + + /* + * EMC rate-changes should go via OPP API because it manages voltage + * changes. + */ + err = dev_pm_opp_set_rate(emc->dev, min_rate); + if (err) + return err; + + emc->requested_rate[type].min_rate = new_min_rate; + emc->requested_rate[type].max_rate = new_max_rate; + + return 0; +} + +static int emc_set_min_rate(struct tegra_emc *emc, unsigned long rate, + enum emc_rate_request_type type) +{ + struct emc_rate_request *req = &emc->requested_rate[type]; + int ret; + + mutex_lock(&emc->rate_lock); + ret = emc_request_rate(emc, rate, req->max_rate, type); + mutex_unlock(&emc->rate_lock); + + return ret; +} + +static int emc_set_max_rate(struct tegra_emc *emc, unsigned long rate, + enum emc_rate_request_type type) +{ + struct emc_rate_request *req = &emc->requested_rate[type]; + int ret; + + mutex_lock(&emc->rate_lock); + ret = emc_request_rate(emc, req->min_rate, rate, type); + mutex_unlock(&emc->rate_lock); + + return ret; +} + /* * debugfs interface * @@ -563,7 +702,7 @@ static int tegra_emc_debug_min_rate_set(void *data, u64 rate) if (!tegra_emc_validate_rate(emc, rate)) return -EINVAL; - err = clk_set_min_rate(emc->clk, rate); + err = emc_set_min_rate(emc, rate, EMC_RATE_DEBUG); if (err < 0) return err; @@ -593,7 +732,7 @@ static int tegra_emc_debug_max_rate_set(void *data, u64 rate) if (!tegra_emc_validate_rate(emc, rate)) return -EINVAL; - err = clk_set_max_rate(emc->clk, rate); + err = emc_set_max_rate(emc, rate, EMC_RATE_DEBUG); if (err < 0) return err; @@ -650,47 +789,330 @@ static void tegra_emc_debugfs_init(struct tegra_emc *emc) emc, &tegra_emc_debug_max_rate_fops); } +static inline struct tegra_emc * +to_tegra_emc_provider(struct icc_provider *provider) +{ + return container_of(provider, struct tegra_emc, provider); +} + +static struct icc_node_data * +emc_of_icc_xlate_extended(struct of_phandle_args *spec, void *data) +{ + struct icc_provider *provider = data; + struct icc_node_data *ndata; + 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; + + ndata = kzalloc(sizeof(*ndata), GFP_KERNEL); + if (!ndata) + return ERR_PTR(-ENOMEM); + + /* + * SRC and DST nodes should have matching TAG in order to have + * it set by default for a requested path. + */ + ndata->tag = TEGRA_MC_ICC_TAG_ISO; + ndata->node = node; + + return ndata; + } + + return ERR_PTR(-EPROBE_DEFER); +} + +static int emc_icc_set(struct icc_node *src, struct icc_node *dst) +{ + struct tegra_emc *emc = to_tegra_emc_provider(dst->provider); + unsigned long long peak_bw = icc_units_to_bps(dst->peak_bw); + unsigned long long avg_bw = icc_units_to_bps(dst->avg_bw); + unsigned long long rate = max(avg_bw, peak_bw); + unsigned int dram_data_bus_width_bytes; + int err; + + /* + * Tegra20 EMC runs on x2 clock rate of SDRAM bus because DDR data + * is sampled on both clock edges. This means that EMC clock rate + * equals to the peak data-rate. + */ + dram_data_bus_width_bytes = emc->dram_bus_width / 8; + do_div(rate, dram_data_bus_width_bytes); + rate = min_t(u64, rate, U32_MAX); + + err = emc_set_min_rate(emc, rate, EMC_RATE_ICC); + if (err) + return err; + + return 0; +} + +static int tegra_emc_interconnect_init(struct tegra_emc *emc) +{ + const struct tegra_mc_soc *soc; + struct icc_node *node; + int err; + + emc->mc = devm_tegra_memory_controller_get(emc->dev); + if (IS_ERR(emc->mc)) + return PTR_ERR(emc->mc); + + soc = emc->mc->soc; + + emc->provider.dev = emc->dev; + emc->provider.set = emc_icc_set; + emc->provider.data = &emc->provider; + emc->provider.aggregate = soc->icc_ops->aggregate; + emc->provider.xlate_extended = emc_of_icc_xlate_extended; + + 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 tegra_emc_opp_table_init(struct tegra_emc *emc) +{ + u32 hw_version = BIT(tegra_sku_info.soc_process_id); + struct opp_table *clk_opp_table, *hw_opp_table; + int err; + + clk_opp_table = dev_pm_opp_set_clkname(emc->dev, NULL); + err = PTR_ERR_OR_ZERO(clk_opp_table); + if (err) { + dev_err(emc->dev, "failed to set OPP clk: %d\n", err); + return err; + } + + hw_opp_table = dev_pm_opp_set_supported_hw(emc->dev, &hw_version, 1); + err = PTR_ERR_OR_ZERO(hw_opp_table); + if (err) { + dev_err(emc->dev, "failed to set OPP supported HW: %d\n", err); + goto put_clk_table; + } + + err = dev_pm_opp_of_add_table(emc->dev); + if (err) { + if (err == -ENODEV) + dev_err(emc->dev, "OPP table not found, please update your device tree\n"); + else + dev_err(emc->dev, "failed to add OPP table: %d\n", err); + + goto put_hw_table; + } + + dev_info(emc->dev, "OPP HW ver. 0x%x, current clock rate %lu MHz\n", + hw_version, clk_get_rate(emc->clk) / 1000000); + + /* first dummy rate-set initializes voltage state */ + err = dev_pm_opp_set_rate(emc->dev, clk_get_rate(emc->clk)); + if (err) { + dev_err(emc->dev, "failed to initialize OPP clock: %d\n", err); + goto remove_table; + } + + return 0; + +remove_table: + dev_pm_opp_of_remove_table(emc->dev); +put_hw_table: + dev_pm_opp_put_supported_hw(hw_opp_table); +put_clk_table: + dev_pm_opp_put_clkname(clk_opp_table); + + return err; +} + +static void devm_tegra_emc_unset_callback(void *data) +{ + tegra20_clk_set_emc_round_callback(NULL, NULL); +} + +static void devm_tegra_emc_unreg_clk_notifier(void *data) +{ + struct tegra_emc *emc = data; + + clk_notifier_unregister(emc->clk, &emc->clk_nb); +} + +static int tegra_emc_init_clk(struct tegra_emc *emc) +{ + int err; + + tegra20_clk_set_emc_round_callback(emc_round_rate, emc); + + err = devm_add_action_or_reset(emc->dev, devm_tegra_emc_unset_callback, + NULL); + if (err) + return err; + + emc->clk = devm_clk_get(emc->dev, NULL); + if (IS_ERR(emc->clk)) { + dev_err(emc->dev, "failed to get EMC clock: %pe\n", emc->clk); + return PTR_ERR(emc->clk); + } + + err = clk_notifier_register(emc->clk, &emc->clk_nb); + if (err) { + dev_err(emc->dev, "failed to register clk notifier: %d\n", err); + return err; + } + + err = devm_add_action_or_reset(emc->dev, + devm_tegra_emc_unreg_clk_notifier, emc); + if (err) + return err; + + return 0; +} + +static int tegra_emc_devfreq_target(struct device *dev, unsigned long *freq, + u32 flags) +{ + struct tegra_emc *emc = dev_get_drvdata(dev); + struct dev_pm_opp *opp; + unsigned long rate; + + opp = devfreq_recommended_opp(dev, freq, flags); + if (IS_ERR(opp)) { + dev_err(dev, "failed to find opp for %lu Hz\n", *freq); + return PTR_ERR(opp); + } + + rate = dev_pm_opp_get_freq(opp); + dev_pm_opp_put(opp); + + return emc_set_min_rate(emc, rate, EMC_RATE_DEVFREQ); +} + +static int tegra_emc_devfreq_get_dev_status(struct device *dev, + struct devfreq_dev_status *stat) +{ + struct tegra_emc *emc = dev_get_drvdata(dev); + + /* freeze counters */ + writel_relaxed(EMC_PWR_GATHER_DISABLE, emc->regs + EMC_STAT_CONTROL); + + /* + * busy_time: number of clocks EMC request was accepted + * total_time: number of clocks PWR_GATHER control was set to ENABLE + */ + stat->busy_time = readl_relaxed(emc->regs + EMC_STAT_PWR_COUNT); + stat->total_time = readl_relaxed(emc->regs + EMC_STAT_PWR_CLOCKS); + stat->current_frequency = clk_get_rate(emc->clk); + + /* clear counters and restart */ + writel_relaxed(EMC_PWR_GATHER_CLEAR, emc->regs + EMC_STAT_CONTROL); + writel_relaxed(EMC_PWR_GATHER_ENABLE, emc->regs + EMC_STAT_CONTROL); + + return 0; +} + +static struct devfreq_dev_profile tegra_emc_devfreq_profile = { + .polling_ms = 30, + .target = tegra_emc_devfreq_target, + .get_dev_status = tegra_emc_devfreq_get_dev_status, +}; + +static int tegra_emc_devfreq_init(struct tegra_emc *emc) +{ + struct devfreq *devfreq; + + /* + * PWR_COUNT is 1/2 of PWR_CLOCKS at max, and thus, the up-threshold + * should be less than 50. Secondly, multiple active memory clients + * may cause over 20% of lost clock cycles due to stalls caused by + * competing memory accesses. This means that threshold should be + * set to a less than 30 in order to have a properly working governor. + */ + emc->ondemand_data.upthreshold = 20; + + /* + * Reset statistic gathers state, select global bandwidth for the + * statistics collection mode and set clocks counter saturation + * limit to maximum. + */ + writel_relaxed(0x00000000, emc->regs + EMC_STAT_CONTROL); + writel_relaxed(0x00000000, emc->regs + EMC_STAT_LLMC_CONTROL); + writel_relaxed(0xffffffff, emc->regs + EMC_STAT_PWR_CLOCK_LIMIT); + + devfreq = devm_devfreq_add_device(emc->dev, &tegra_emc_devfreq_profile, + DEVFREQ_GOV_SIMPLE_ONDEMAND, + &emc->ondemand_data); + if (IS_ERR(devfreq)) { + dev_err(emc->dev, "failed to initialize devfreq: %pe", devfreq); + return PTR_ERR(devfreq); + } + + return 0; +} + static int tegra_emc_probe(struct platform_device *pdev) { struct device_node *np; struct tegra_emc *emc; - struct resource *res; int irq, err; - /* driver has nothing to do in a case of memory timing absence */ - if (of_get_child_count(pdev->dev.of_node) == 0) { - dev_info(&pdev->dev, - "EMC device tree node doesn't have memory timings\n"); - return 0; - } - irq = platform_get_irq(pdev, 0); if (irq < 0) { - dev_err(&pdev->dev, "interrupt not specified\n"); dev_err(&pdev->dev, "please update your device tree\n"); return irq; } - np = tegra_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); + if (!emc) return -ENOMEM; - } + mutex_init(&emc->rate_lock); emc->clk_nb.notifier_call = tegra_emc_clk_change_notify; emc->dev = &pdev->dev; - err = tegra_emc_load_timings_from_dt(emc, np); - of_node_put(np); - if (err) - return err; + np = tegra_emc_find_node_by_ram_code(&pdev->dev); + if (np) { + err = tegra_emc_load_timings_from_dt(emc, np); + of_node_put(np); + if (err) + return err; + } - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - emc->regs = devm_ioremap_resource(&pdev->dev, res); + emc->regs = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(emc->regs)) return PTR_ERR(emc->regs); @@ -701,41 +1123,39 @@ static int tegra_emc_probe(struct platform_device *pdev) err = devm_request_irq(&pdev->dev, irq, tegra_emc_isr, 0, dev_name(&pdev->dev), emc); if (err) { - dev_err(&pdev->dev, "failed to request IRQ#%u: %d\n", irq, 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 = tegra_emc_init_clk(emc); + if (err) + return err; - 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; - } + err = tegra_emc_opp_table_init(emc); + if (err) + return err; platform_set_drvdata(pdev, emc); + tegra_emc_rate_requests_init(emc); tegra_emc_debugfs_init(emc); + tegra_emc_interconnect_init(emc); + tegra_emc_devfreq_init(emc); - return 0; - -unset_cb: - tegra20_clk_set_emc_round_callback(NULL, NULL); + /* + * Don't allow the kernel module to be unloaded. Unloading adds some + * extra complexity which doesn't really worth the effort in a case of + * this driver. + */ + try_module_get(THIS_MODULE); - return err; + return 0; } static const struct of_device_id tegra_emc_of_match[] = { { .compatible = "nvidia,tegra20-emc", }, {}, }; +MODULE_DEVICE_TABLE(of, tegra_emc_of_match); static struct platform_driver tegra_emc_driver = { .probe = tegra_emc_probe, @@ -743,11 +1163,11 @@ static struct platform_driver tegra_emc_driver = { .name = "tegra20-emc", .of_match_table = tegra_emc_of_match, .suppress_bind_attrs = true, + .sync_state = icc_sync_state, }, }; +module_platform_driver(tegra_emc_driver); -static int __init tegra_emc_init(void) -{ - return platform_driver_register(&tegra_emc_driver); -} -subsys_initcall(tegra_emc_init); +MODULE_AUTHOR("Dmitry Osipenko <digetx@gmail.com>"); +MODULE_DESCRIPTION("NVIDIA Tegra20 EMC driver"); +MODULE_LICENSE("GPL v2"); |