From 8ac6c7a54ed1b98d142dce24b11c6de6a1e239a5 Mon Sep 17 00:00:00 2001 From: hc <hc@nodka.com> Date: Tue, 22 Oct 2024 10:36:11 +0000 Subject: [PATCH] 修改4g拨号为QMI,需要在系统里后台执行quectel-CM --- kernel/drivers/gpu/host1x/dev.c | 375 ++++++++++++++++++++++++++++++++++++++++------------ 1 files changed, 286 insertions(+), 89 deletions(-) diff --git a/kernel/drivers/gpu/host1x/dev.c b/kernel/drivers/gpu/host1x/dev.c index d88073e..9f674a8 100644 --- a/kernel/drivers/gpu/host1x/dev.c +++ b/kernel/drivers/gpu/host1x/dev.c @@ -1,19 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Tegra host1x driver * * Copyright (c) 2010-2013, NVIDIA Corporation. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * You should have received a copy of the GNU General Public License - * along with this program. If not, see <http://www.gnu.org/licenses/>. */ #include <linux/clk.h> @@ -29,6 +18,10 @@ #include <trace/events/host1x.h> #undef CREATE_TRACE_POINTS +#if IS_ENABLED(CONFIG_ARM_DMA_USE_IOMMU) +#include <asm/dma-iommu.h> +#endif + #include "bus.h" #include "channel.h" #include "debug.h" @@ -40,6 +33,7 @@ #include "hw/host1x04.h" #include "hw/host1x05.h" #include "hw/host1x06.h" +#include "hw/host1x07.h" void host1x_hypervisor_writel(struct host1x *host1x, u32 v, u32 r) { @@ -83,6 +77,10 @@ .init = host1x01_init, .sync_offset = 0x3000, .dma_mask = DMA_BIT_MASK(32), + .has_wide_gather = false, + .has_hypervisor = false, + .num_sid_entries = 0, + .sid_table = NULL, }; static const struct host1x_info host1x02_info = { @@ -93,6 +91,10 @@ .init = host1x02_init, .sync_offset = 0x3000, .dma_mask = DMA_BIT_MASK(32), + .has_wide_gather = false, + .has_hypervisor = false, + .num_sid_entries = 0, + .sid_table = NULL, }; static const struct host1x_info host1x04_info = { @@ -103,6 +105,10 @@ .init = host1x04_init, .sync_offset = 0x2100, .dma_mask = DMA_BIT_MASK(34), + .has_wide_gather = false, + .has_hypervisor = false, + .num_sid_entries = 0, + .sid_table = NULL, }; static const struct host1x_info host1x05_info = { @@ -113,6 +119,19 @@ .init = host1x05_init, .sync_offset = 0x2100, .dma_mask = DMA_BIT_MASK(34), + .has_wide_gather = false, + .has_hypervisor = false, + .num_sid_entries = 0, + .sid_table = NULL, +}; + +static const struct host1x_sid_entry tegra186_sid_table[] = { + { + /* VIC */ + .base = 0x1af0, + .offset = 0x30, + .limit = 0x34 + }, }; static const struct host1x_info host1x06_info = { @@ -122,11 +141,38 @@ .nb_bases = 16, .init = host1x06_init, .sync_offset = 0x0, - .dma_mask = DMA_BIT_MASK(34), + .dma_mask = DMA_BIT_MASK(40), + .has_wide_gather = true, .has_hypervisor = true, + .num_sid_entries = ARRAY_SIZE(tegra186_sid_table), + .sid_table = tegra186_sid_table, +}; + +static const struct host1x_sid_entry tegra194_sid_table[] = { + { + /* VIC */ + .base = 0x1af0, + .offset = 0x30, + .limit = 0x34 + }, +}; + +static const struct host1x_info host1x07_info = { + .nb_channels = 63, + .nb_pts = 704, + .nb_mlocks = 32, + .nb_bases = 0, + .init = host1x07_init, + .sync_offset = 0x0, + .dma_mask = DMA_BIT_MASK(40), + .has_wide_gather = true, + .has_hypervisor = true, + .num_sid_entries = ARRAY_SIZE(tegra194_sid_table), + .sid_table = tegra194_sid_table, }; static const struct of_device_id host1x_of_match[] = { + { .compatible = "nvidia,tegra194-host1x", .data = &host1x07_info, }, { .compatible = "nvidia,tegra186-host1x", .data = &host1x06_info, }, { .compatible = "nvidia,tegra210-host1x", .data = &host1x05_info, }, { .compatible = "nvidia,tegra124-host1x", .data = &host1x04_info, }, @@ -136,6 +182,183 @@ { }, }; MODULE_DEVICE_TABLE(of, host1x_of_match); + +static void host1x_setup_sid_table(struct host1x *host) +{ + const struct host1x_info *info = host->info; + unsigned int i; + + for (i = 0; i < info->num_sid_entries; i++) { + const struct host1x_sid_entry *entry = &info->sid_table[i]; + + host1x_hypervisor_writel(host, entry->offset, entry->base); + host1x_hypervisor_writel(host, entry->limit, entry->base + 4); + } +} + +static bool host1x_wants_iommu(struct host1x *host1x) +{ + /* Our IOMMU usage policy doesn't currently play well with GART */ + if (of_machine_is_compatible("nvidia,tegra20")) + return false; + + /* + * If we support addressing a maximum of 32 bits of physical memory + * and if the host1x firewall is enabled, there's no need to enable + * IOMMU support. This can happen for example on Tegra20, Tegra30 + * and Tegra114. + * + * Tegra124 and later can address up to 34 bits of physical memory and + * many platforms come equipped with more than 2 GiB of system memory, + * which requires crossing the 4 GiB boundary. But there's a catch: on + * SoCs before Tegra186 (i.e. Tegra124 and Tegra210), the host1x can + * only address up to 32 bits of memory in GATHER opcodes, which means + * that command buffers need to either be in the first 2 GiB of system + * memory (which could quickly lead to memory exhaustion), or command + * buffers need to be treated differently from other buffers (which is + * not possible with the current ABI). + * + * A third option is to use the IOMMU in these cases to make sure all + * buffers will be mapped into a 32-bit IOVA space that host1x can + * address. This allows all of the system memory to be used and works + * within the limitations of the host1x on these SoCs. + * + * In summary, default to enable IOMMU on Tegra124 and later. For any + * of the earlier SoCs, only use the IOMMU for additional safety when + * the host1x firewall is disabled. + */ + if (host1x->info->dma_mask <= DMA_BIT_MASK(32)) { + if (IS_ENABLED(CONFIG_TEGRA_HOST1X_FIREWALL)) + return false; + } + + return true; +} + +static struct iommu_domain *host1x_iommu_attach(struct host1x *host) +{ + struct iommu_domain *domain = iommu_get_domain_for_dev(host->dev); + int err; + +#if IS_ENABLED(CONFIG_ARM_DMA_USE_IOMMU) + if (host->dev->archdata.mapping) { + struct dma_iommu_mapping *mapping = + to_dma_iommu_mapping(host->dev); + arm_iommu_detach_device(host->dev); + arm_iommu_release_mapping(mapping); + + domain = iommu_get_domain_for_dev(host->dev); + } +#endif + + /* + * We may not always want to enable IOMMU support (for example if the + * host1x firewall is already enabled and we don't support addressing + * more than 32 bits of physical memory), so check for that first. + * + * Similarly, if host1x is already attached to an IOMMU (via the DMA + * API), don't try to attach again. + */ + if (!host1x_wants_iommu(host) || domain) + return domain; + + host->group = iommu_group_get(host->dev); + if (host->group) { + struct iommu_domain_geometry *geometry; + dma_addr_t start, end; + unsigned long order; + + err = iova_cache_get(); + if (err < 0) + goto put_group; + + host->domain = iommu_domain_alloc(&platform_bus_type); + if (!host->domain) { + err = -ENOMEM; + goto put_cache; + } + + err = iommu_attach_group(host->domain, host->group); + if (err) { + if (err == -ENODEV) + err = 0; + + goto free_domain; + } + + geometry = &host->domain->geometry; + start = geometry->aperture_start & host->info->dma_mask; + end = geometry->aperture_end & host->info->dma_mask; + + order = __ffs(host->domain->pgsize_bitmap); + init_iova_domain(&host->iova, 1UL << order, start >> order); + host->iova_end = end; + + domain = host->domain; + } + + return domain; + +free_domain: + iommu_domain_free(host->domain); + host->domain = NULL; +put_cache: + iova_cache_put(); +put_group: + iommu_group_put(host->group); + host->group = NULL; + + return ERR_PTR(err); +} + +static int host1x_iommu_init(struct host1x *host) +{ + u64 mask = host->info->dma_mask; + struct iommu_domain *domain; + int err; + + domain = host1x_iommu_attach(host); + if (IS_ERR(domain)) { + err = PTR_ERR(domain); + dev_err(host->dev, "failed to attach to IOMMU: %d\n", err); + return err; + } + + /* + * If we're not behind an IOMMU make sure we don't get push buffers + * that are allocated outside of the range addressable by the GATHER + * opcode. + * + * Newer generations of Tegra (Tegra186 and later) support a wide + * variant of the GATHER opcode that allows addressing more bits. + */ + if (!domain && !host->info->has_wide_gather) + mask = DMA_BIT_MASK(32); + + err = dma_coerce_mask_and_coherent(host->dev, mask); + if (err < 0) { + dev_err(host->dev, "failed to set DMA mask: %d\n", err); + return err; + } + + return 0; +} + +static void host1x_iommu_exit(struct host1x *host) +{ + if (host->domain) { + put_iova_domain(&host->iova); + iommu_detach_group(host->domain, host->group); + + iommu_domain_free(host->domain); + host->domain = NULL; + + iova_cache_put(); + + iommu_group_put(host->group); + host->group = NULL; + } +} static int host1x_probe(struct platform_device *pdev) { @@ -173,10 +396,8 @@ } syncpt_irq = platform_get_irq(pdev, 0); - if (syncpt_irq < 0) { - dev_err(&pdev->dev, "failed to get IRQ: %d\n", syncpt_irq); + if (syncpt_irq < 0) return syncpt_irq; - } mutex_init(&host->devices_lock); INIT_LIST_HEAD(&host->devices); @@ -196,7 +417,8 @@ return PTR_ERR(host->hv_regs); } - dma_set_mask_and_coherent(host->dev, host->info->dma_mask); + host->dev->dma_parms = &host->dma_parms; + dma_set_max_seg_size(host->dev, UINT_MAX); if (host->info->init) { err = host->info->init(host); @@ -206,8 +428,11 @@ host->clk = devm_clk_get(&pdev->dev, NULL); if (IS_ERR(host->clk)) { - dev_err(&pdev->dev, "failed to get clock\n"); err = PTR_ERR(host->clk); + + if (err != -EPROBE_DEFER) + dev_err(&pdev->dev, "failed to get clock: %d\n", err); + return err; } @@ -218,109 +443,73 @@ return err; } - if (IS_ENABLED(CONFIG_TEGRA_HOST1X_FIREWALL)) - goto skip_iommu; - - host->group = iommu_group_get(&pdev->dev); - if (host->group) { - struct iommu_domain_geometry *geometry; - unsigned long order; - - err = iova_cache_get(); - if (err < 0) - goto put_group; - - host->domain = iommu_domain_alloc(&platform_bus_type); - if (!host->domain) { - err = -ENOMEM; - goto put_cache; - } - - err = iommu_attach_group(host->domain, host->group); - if (err) { - if (err == -ENODEV) { - iommu_domain_free(host->domain); - host->domain = NULL; - iova_cache_put(); - iommu_group_put(host->group); - host->group = NULL; - goto skip_iommu; - } - - goto fail_free_domain; - } - - geometry = &host->domain->geometry; - - order = __ffs(host->domain->pgsize_bitmap); - init_iova_domain(&host->iova, 1UL << order, - geometry->aperture_start >> order); - host->iova_end = geometry->aperture_end; + err = host1x_iommu_init(host); + if (err < 0) { + dev_err(&pdev->dev, "failed to setup IOMMU: %d\n", err); + return err; } -skip_iommu: err = host1x_channel_list_init(&host->channel_list, host->info->nb_channels); if (err) { dev_err(&pdev->dev, "failed to initialize channel list\n"); - goto fail_detach_device; + goto iommu_exit; } err = clk_prepare_enable(host->clk); if (err < 0) { dev_err(&pdev->dev, "failed to enable clock\n"); - goto fail_free_channels; + goto free_channels; } err = reset_control_deassert(host->rst); if (err < 0) { dev_err(&pdev->dev, "failed to deassert reset: %d\n", err); - goto fail_unprepare_disable; + goto unprepare_disable; } err = host1x_syncpt_init(host); if (err) { dev_err(&pdev->dev, "failed to initialize syncpts\n"); - goto fail_reset_assert; + goto reset_assert; } err = host1x_intr_init(host, syncpt_irq); if (err) { dev_err(&pdev->dev, "failed to initialize interrupts\n"); - goto fail_deinit_syncpt; + goto deinit_syncpt; } host1x_debug_init(host); + if (host->info->has_hypervisor) + host1x_setup_sid_table(host); + err = host1x_register(host); if (err < 0) - goto fail_deinit_intr; + goto deinit_debugfs; + + err = devm_of_platform_populate(&pdev->dev); + if (err < 0) + goto unregister; return 0; -fail_deinit_intr: +unregister: + host1x_unregister(host); +deinit_debugfs: + host1x_debug_deinit(host); host1x_intr_deinit(host); -fail_deinit_syncpt: +deinit_syncpt: host1x_syncpt_deinit(host); -fail_reset_assert: +reset_assert: reset_control_assert(host->rst); -fail_unprepare_disable: +unprepare_disable: clk_disable_unprepare(host->clk); -fail_free_channels: +free_channels: host1x_channel_list_free(&host->channel_list); -fail_detach_device: - if (host->group && host->domain) { - put_iova_domain(&host->iova); - iommu_detach_group(host->domain, host->group); - } -fail_free_domain: - if (host->domain) - iommu_domain_free(host->domain); -put_cache: - if (host->group) - iova_cache_put(); -put_group: - iommu_group_put(host->group); +iommu_exit: + host1x_iommu_exit(host); return err; } @@ -330,18 +519,13 @@ struct host1x *host = platform_get_drvdata(pdev); host1x_unregister(host); + host1x_debug_deinit(host); host1x_intr_deinit(host); host1x_syncpt_deinit(host); reset_control_assert(host->rst); clk_disable_unprepare(host->clk); - - if (host->domain) { - put_iova_domain(&host->iova); - iommu_detach_group(host->domain, host->group); - iommu_domain_free(host->domain); - iova_cache_put(); - iommu_group_put(host->group); - } + host1x_channel_list_free(&host->channel_list); + host1x_iommu_exit(host); return 0; } @@ -383,6 +567,19 @@ } module_exit(tegra_host1x_exit); +/** + * host1x_get_dma_mask() - query the supported DMA mask for host1x + * @host1x: host1x instance + * + * Note that this returns the supported DMA mask for host1x, which can be + * different from the applicable DMA mask under certain circumstances. + */ +u64 host1x_get_dma_mask(struct host1x *host1x) +{ + return host1x->info->dma_mask; +} +EXPORT_SYMBOL(host1x_get_dma_mask); + MODULE_AUTHOR("Thierry Reding <thierry.reding@avionic-design.de>"); MODULE_AUTHOR("Terje Bergstrom <tbergstrom@nvidia.com>"); MODULE_DESCRIPTION("Host1x driver for Tegra products"); -- Gitblit v1.6.2