diff options
Diffstat (limited to 'drivers')
207 files changed, 2167 insertions, 1830 deletions
diff --git a/drivers/base/arch_topology.c b/drivers/base/arch_topology.c index eaa1b8d2d39d..46cbe4471e78 100644 --- a/drivers/base/arch_topology.c +++ b/drivers/base/arch_topology.c @@ -724,7 +724,7 @@ const struct cpumask *cpu_clustergroup_mask(int cpu) */ if (cpumask_subset(cpu_coregroup_mask(cpu), &cpu_topology[cpu].cluster_sibling)) - return get_cpu_mask(cpu); + return topology_sibling_cpumask(cpu); return &cpu_topology[cpu].cluster_sibling; } diff --git a/drivers/base/driver.c b/drivers/base/driver.c index 15a75afe6b84..676b6275d5b5 100644 --- a/drivers/base/driver.c +++ b/drivers/base/driver.c @@ -63,6 +63,12 @@ int driver_set_override(struct device *dev, const char **override, if (len >= (PAGE_SIZE - 1)) return -EINVAL; + /* + * Compute the real length of the string in case userspace sends us a + * bunch of \0 characters like python likes to do. + */ + len = strlen(s); + if (!len) { /* Empty string passed - clear override */ device_lock(dev); diff --git a/drivers/base/regmap/regmap-spi.c b/drivers/base/regmap/regmap-spi.c index 719323bc6c7f..37ab23a9d034 100644 --- a/drivers/base/regmap/regmap-spi.c +++ b/drivers/base/regmap/regmap-spi.c @@ -113,6 +113,7 @@ static const struct regmap_bus *regmap_get_spi_bus(struct spi_device *spi, const struct regmap_config *config) { size_t max_size = spi_max_transfer_size(spi); + size_t max_msg_size, reg_reserve_size; struct regmap_bus *bus; if (max_size != SIZE_MAX) { @@ -120,9 +121,16 @@ static const struct regmap_bus *regmap_get_spi_bus(struct spi_device *spi, if (!bus) return ERR_PTR(-ENOMEM); + max_msg_size = spi_max_message_size(spi); + reg_reserve_size = config->reg_bits / BITS_PER_BYTE + + config->pad_bits / BITS_PER_BYTE; + if (max_size + reg_reserve_size > max_msg_size) + max_size -= reg_reserve_size; + bus->free_on_exit = true; bus->max_raw_read = max_size; bus->max_raw_write = max_size; + return bus; } diff --git a/drivers/dma/ti/k3-udma-private.c b/drivers/dma/ti/k3-udma-private.c index d4f1e4e9603a..85e00701473c 100644 --- a/drivers/dma/ti/k3-udma-private.c +++ b/drivers/dma/ti/k3-udma-private.c @@ -31,14 +31,14 @@ struct udma_dev *of_xudma_dev_get(struct device_node *np, const char *property) } pdev = of_find_device_by_node(udma_node); + if (np != udma_node) + of_node_put(udma_node); + if (!pdev) { pr_debug("UDMA device not found\n"); return ERR_PTR(-EPROBE_DEFER); } - if (np != udma_node) - of_node_put(udma_node); - ud = platform_get_drvdata(pdev); if (!ud) { pr_debug("UDMA has not been probed\n"); diff --git a/drivers/dma/xilinx/xilinx_dma.c b/drivers/dma/xilinx/xilinx_dma.c index 6276934d4d2b..8cd4e69dc7b4 100644 --- a/drivers/dma/xilinx/xilinx_dma.c +++ b/drivers/dma/xilinx/xilinx_dma.c @@ -3040,9 +3040,10 @@ static int xilinx_dma_probe(struct platform_device *pdev) /* Request and map I/O memory */ xdev->regs = devm_platform_ioremap_resource(pdev, 0); - if (IS_ERR(xdev->regs)) - return PTR_ERR(xdev->regs); - + if (IS_ERR(xdev->regs)) { + err = PTR_ERR(xdev->regs); + goto disable_clks; + } /* Retrieve the DMA engine properties from the device tree */ xdev->max_buffer_len = GENMASK(XILINX_DMA_MAX_TRANS_LEN_MAX - 1, 0); xdev->s2mm_chan_id = xdev->dma_config->max_channels / 2; @@ -3070,7 +3071,7 @@ static int xilinx_dma_probe(struct platform_device *pdev) if (err < 0) { dev_err(xdev->dev, "missing xlnx,num-fstores property\n"); - return err; + goto disable_clks; } err = of_property_read_u32(node, "xlnx,flush-fsync", @@ -3090,7 +3091,11 @@ static int xilinx_dma_probe(struct platform_device *pdev) xdev->ext_addr = false; /* Set the dma mask bits */ - dma_set_mask_and_coherent(xdev->dev, DMA_BIT_MASK(addr_width)); + err = dma_set_mask_and_coherent(xdev->dev, DMA_BIT_MASK(addr_width)); + if (err < 0) { + dev_err(xdev->dev, "DMA mask error %d\n", err); + goto disable_clks; + } /* Initialize the DMA engine */ xdev->common.dev = &pdev->dev; @@ -3137,7 +3142,7 @@ static int xilinx_dma_probe(struct platform_device *pdev) for_each_child_of_node(node, child) { err = xilinx_dma_child_probe(xdev, child); if (err < 0) - goto disable_clks; + goto error; } if (xdev->dma_config->dmatype == XDMA_TYPE_VDMA) { @@ -3172,12 +3177,12 @@ static int xilinx_dma_probe(struct platform_device *pdev) return 0; -disable_clks: - xdma_disable_allclks(xdev); error: for (i = 0; i < xdev->dma_config->max_channels; i++) if (xdev->chan[i]) xilinx_dma_chan_remove(xdev->chan[i]); +disable_clks: + xdma_disable_allclks(xdev); return err; } diff --git a/drivers/dma/xilinx/zynqmp_dma.c b/drivers/dma/xilinx/zynqmp_dma.c index dc299ab36818..3f4ee3954384 100644 --- a/drivers/dma/xilinx/zynqmp_dma.c +++ b/drivers/dma/xilinx/zynqmp_dma.c @@ -849,7 +849,7 @@ static struct dma_async_tx_descriptor *zynqmp_dma_prep_memcpy( zynqmp_dma_desc_config_eod(chan, desc); async_tx_ack(&first->async_tx); - first->async_tx.flags = flags; + first->async_tx.flags = (enum dma_ctrl_flags)flags; return &first->async_tx; } diff --git a/drivers/firmware/efi/efibc.c b/drivers/firmware/efi/efibc.c index 8ced7af8e56d..4f9fb086eab7 100644 --- a/drivers/firmware/efi/efibc.c +++ b/drivers/firmware/efi/efibc.c @@ -48,6 +48,9 @@ static int efibc_reboot_notifier_call(struct notifier_block *notifier, return NOTIFY_DONE; wdata = kmalloc(MAX_DATA_LEN * sizeof(efi_char16_t), GFP_KERNEL); + if (!wdata) + return NOTIFY_DONE; + for (l = 0; l < MAX_DATA_LEN - 1 && str[l] != '\0'; l++) wdata[l] = str[l]; wdata[l] = L'\0'; diff --git a/drivers/firmware/efi/libstub/secureboot.c b/drivers/firmware/efi/libstub/secureboot.c index 8a18930f3eb6..516f4f0069bd 100644 --- a/drivers/firmware/efi/libstub/secureboot.c +++ b/drivers/firmware/efi/libstub/secureboot.c @@ -14,7 +14,7 @@ /* SHIM variables */ static const efi_guid_t shim_guid = EFI_SHIM_LOCK_GUID; -static const efi_char16_t shim_MokSBState_name[] = L"MokSBState"; +static const efi_char16_t shim_MokSBState_name[] = L"MokSBStateRT"; static efi_status_t get_var(efi_char16_t *name, efi_guid_t *vendor, u32 *attr, unsigned long *data_size, void *data) @@ -43,8 +43,8 @@ enum efi_secureboot_mode efi_get_secureboot(void) /* * See if a user has put the shim into insecure mode. If so, and if the - * variable doesn't have the runtime attribute set, we might as well - * honor that. + * variable doesn't have the non-volatile attribute set, we might as + * well honor that. */ size = sizeof(moksbstate); status = get_efi_var(shim_MokSBState_name, &shim_guid, @@ -53,7 +53,7 @@ enum efi_secureboot_mode efi_get_secureboot(void) /* If it fails, we don't care why. Default to secure */ if (status != EFI_SUCCESS) goto secure_boot_enabled; - if (!(attr & EFI_VARIABLE_RUNTIME_ACCESS) && moksbstate == 1) + if (!(attr & EFI_VARIABLE_NON_VOLATILE) && moksbstate == 1) return efi_secureboot_mode_disabled; secure_boot_enabled: diff --git a/drivers/firmware/efi/libstub/x86-stub.c b/drivers/firmware/efi/libstub/x86-stub.c index 43ca665af610..7a7abc8959d2 100644 --- a/drivers/firmware/efi/libstub/x86-stub.c +++ b/drivers/firmware/efi/libstub/x86-stub.c @@ -516,6 +516,13 @@ efi_status_t __efiapi efi_pe_entry(efi_handle_t handle, hdr->ramdisk_image = 0; hdr->ramdisk_size = 0; + /* + * Disregard any setup data that was provided by the bootloader: + * setup_data could be pointing anywhere, and we have no way of + * authenticating or validating the payload. + */ + hdr->setup_data = 0; + efi_stub_entry(handle, sys_table_arg, boot_params); /* not reached */ diff --git a/drivers/gpio/gpio-ftgpio010.c b/drivers/gpio/gpio-ftgpio010.c index f422c3e129a0..f77a965f5780 100644 --- a/drivers/gpio/gpio-ftgpio010.c +++ b/drivers/gpio/gpio-ftgpio010.c @@ -41,14 +41,12 @@ * struct ftgpio_gpio - Gemini GPIO state container * @dev: containing device for this instance * @gc: gpiochip for this instance - * @irq: irqchip for this instance * @base: remapped I/O-memory base * @clk: silicon clock */ struct ftgpio_gpio { struct device *dev; struct gpio_chip gc; - struct irq_chip irq; void __iomem *base; struct clk *clk; }; @@ -70,6 +68,7 @@ static void ftgpio_gpio_mask_irq(struct irq_data *d) val = readl(g->base + GPIO_INT_EN); val &= ~BIT(irqd_to_hwirq(d)); writel(val, g->base + GPIO_INT_EN); + gpiochip_disable_irq(gc, irqd_to_hwirq(d)); } static void ftgpio_gpio_unmask_irq(struct irq_data *d) @@ -78,6 +77,7 @@ static void ftgpio_gpio_unmask_irq(struct irq_data *d) struct ftgpio_gpio *g = gpiochip_get_data(gc); u32 val; + gpiochip_enable_irq(gc, irqd_to_hwirq(d)); val = readl(g->base + GPIO_INT_EN); val |= BIT(irqd_to_hwirq(d)); writel(val, g->base + GPIO_INT_EN); @@ -221,6 +221,16 @@ static int ftgpio_gpio_set_config(struct gpio_chip *gc, unsigned int offset, return 0; } +static const struct irq_chip ftgpio_irq_chip = { + .name = "FTGPIO010", + .irq_ack = ftgpio_gpio_ack_irq, + .irq_mask = ftgpio_gpio_mask_irq, + .irq_unmask = ftgpio_gpio_unmask_irq, + .irq_set_type = ftgpio_gpio_set_irq_type, + .flags = IRQCHIP_IMMUTABLE, + GPIOCHIP_IRQ_RESOURCE_HELPERS, +}; + static int ftgpio_gpio_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; @@ -277,14 +287,8 @@ static int ftgpio_gpio_probe(struct platform_device *pdev) if (!IS_ERR(g->clk)) g->gc.set_config = ftgpio_gpio_set_config; - g->irq.name = "FTGPIO010"; - g->irq.irq_ack = ftgpio_gpio_ack_irq; - g->irq.irq_mask = ftgpio_gpio_mask_irq; - g->irq.irq_unmask = ftgpio_gpio_unmask_irq; - g->irq.irq_set_type = ftgpio_gpio_set_irq_type; - girq = &g->gc.irq; - girq->chip = &g->irq; + gpio_irq_chip_set_chip(girq, &ftgpio_irq_chip); girq->parent_handler = ftgpio_gpio_irq_handler; girq->num_parents = 1; girq->parents = devm_kcalloc(dev, 1, sizeof(*girq->parents), diff --git a/drivers/gpio/gpio-ixp4xx.c b/drivers/gpio/gpio-ixp4xx.c index 312309be0287..56656fb519f8 100644 --- a/drivers/gpio/gpio-ixp4xx.c +++ b/drivers/gpio/gpio-ixp4xx.c @@ -63,6 +63,14 @@ static void ixp4xx_gpio_irq_ack(struct irq_data *d) __raw_writel(BIT(d->hwirq), g->base + IXP4XX_REG_GPIS); } +static void ixp4xx_gpio_mask_irq(struct irq_data *d) +{ + struct gpio_chip *gc = irq_data_get_irq_chip_data(d); + + irq_chip_mask_parent(d); + gpiochip_disable_irq(gc, d->hwirq); +} + static void ixp4xx_gpio_irq_unmask(struct irq_data *d) { struct gpio_chip *gc = irq_data_get_irq_chip_data(d); @@ -72,6 +80,7 @@ static void ixp4xx_gpio_irq_unmask(struct irq_data *d) if (!(g->irq_edge & BIT(d->hwirq))) ixp4xx_gpio_irq_ack(d); + gpiochip_enable_irq(gc, d->hwirq); irq_chip_unmask_parent(d); } @@ -149,12 +158,14 @@ static int ixp4xx_gpio_irq_set_type(struct irq_data *d, unsigned int type) return irq_chip_set_type_parent(d, IRQ_TYPE_LEVEL_HIGH); } -static struct irq_chip ixp4xx_gpio_irqchip = { +static const struct irq_chip ixp4xx_gpio_irqchip = { .name = "IXP4GPIO", .irq_ack = ixp4xx_gpio_irq_ack, - .irq_mask = irq_chip_mask_parent, + .irq_mask = ixp4xx_gpio_mask_irq, .irq_unmask = ixp4xx_gpio_irq_unmask, .irq_set_type = ixp4xx_gpio_irq_set_type, + .flags = IRQCHIP_IMMUTABLE, + GPIOCHIP_IRQ_RESOURCE_HELPERS, }; static int ixp4xx_gpio_child_to_parent_hwirq(struct gpio_chip *gc, @@ -263,7 +274,7 @@ static int ixp4xx_gpio_probe(struct platform_device *pdev) g->gc.owner = THIS_MODULE; girq = &g->gc.irq; - girq->chip = &ixp4xx_gpio_irqchip; + gpio_irq_chip_set_chip(girq, &ixp4xx_gpio_irqchip); girq->fwnode = g->fwnode; girq->parent_domain = parent; girq->child_to_parent_hwirq = ixp4xx_gpio_child_to_parent_hwirq; diff --git a/drivers/gpio/gpio-mockup.c b/drivers/gpio/gpio-mockup.c index a2e505a7545c..523dfd17dd92 100644 --- a/drivers/gpio/gpio-mockup.c +++ b/drivers/gpio/gpio-mockup.c @@ -533,8 +533,10 @@ static int __init gpio_mockup_register_chip(int idx) } fwnode = fwnode_create_software_node(properties, NULL); - if (IS_ERR(fwnode)) + if (IS_ERR(fwnode)) { + kfree_strarray(line_names, ngpio); return PTR_ERR(fwnode); + } pdevinfo.name = "gpio-mockup"; pdevinfo.id = idx; @@ -597,9 +599,9 @@ static int __init gpio_mockup_init(void) static void __exit gpio_mockup_exit(void) { + gpio_mockup_unregister_pdevs(); debugfs_remove_recursive(gpio_mockup_dbg_dir); platform_driver_unregister(&gpio_mockup_driver); - gpio_mockup_unregister_pdevs(); } module_init(gpio_mockup_init); diff --git a/drivers/gpio/gpio-mpc8xxx.c b/drivers/gpio/gpio-mpc8xxx.c index 15049822937a..3eb08cd1fdc0 100644 --- a/drivers/gpio/gpio-mpc8xxx.c +++ b/drivers/gpio/gpio-mpc8xxx.c @@ -169,6 +169,7 @@ static int mpc8xxx_irq_set_type(struct irq_data *d, unsigned int flow_type) switch (flow_type) { case IRQ_TYPE_EDGE_FALLING: + case IRQ_TYPE_LEVEL_LOW: raw_spin_lock_irqsave(&mpc8xxx_gc->lock, flags); gc->write_reg(mpc8xxx_gc->regs + GPIO_ICR, gc->read_reg(mpc8xxx_gc->regs + GPIO_ICR) diff --git a/drivers/gpio/gpio-mt7621.c b/drivers/gpio/gpio-mt7621.c index d8a26e503ca5..f163f5ca857b 100644 --- a/drivers/gpio/gpio-mt7621.c +++ b/drivers/gpio/gpio-mt7621.c @@ -112,6 +112,8 @@ mediatek_gpio_irq_unmask(struct irq_data *d) unsigned long flags; u32 rise, fall, high, low; + gpiochip_enable_irq(gc, d->hwirq); + spin_lock_irqsave(&rg->lock, flags); rise = mtk_gpio_r32(rg, GPIO_REG_REDGE); fall = mtk_gpio_r32(rg, GPIO_REG_FEDGE); @@ -143,6 +145,8 @@ mediatek_gpio_irq_mask(struct irq_data *d) mtk_gpio_w32(rg, GPIO_REG_HLVL, high & ~BIT(pin)); mtk_gpio_w32(rg, GPIO_REG_LLVL, low & ~BIT(pin)); spin_unlock_irqrestore(&rg->lock, flags); + + gpiochip_disable_irq(gc, d->hwirq); } static int @@ -204,6 +208,16 @@ mediatek_gpio_xlate(struct gpio_chip *chip, return gpio % MTK_BANK_WIDTH; } +static const struct irq_chip mt7621_irq_chip = { + .name = "mt7621-gpio", + .irq_mask_ack = mediatek_gpio_irq_mask, + .irq_mask = mediatek_gpio_irq_mask, + .irq_unmask = mediatek_gpio_irq_unmask, + .irq_set_type = mediatek_gpio_irq_type, + .flags = IRQCHIP_IMMUTABLE, + GPIOCHIP_IRQ_RESOURCE_HELPERS, +}; + static int mediatek_gpio_bank_probe(struct device *dev, int bank) { @@ -238,11 +252,6 @@ mediatek_gpio_bank_probe(struct device *dev, int bank) return -ENOMEM; rg->chip.offset = bank * MTK_BANK_WIDTH; - rg->irq_chip.name = dev_name(dev); - rg->irq_chip.irq_unmask = mediatek_gpio_irq_unmask; - rg->irq_chip.irq_mask = mediatek_gpio_irq_mask; - rg->irq_chip.irq_mask_ack = mediatek_gpio_irq_mask; - rg->irq_chip.irq_set_type = mediatek_gpio_irq_type; if (mtk->gpio_irq) { struct gpio_irq_chip *girq; @@ -262,7 +271,7 @@ mediatek_gpio_bank_probe(struct device *dev, int bank) } girq = &rg->chip.irq; - girq->chip = &rg->irq_chip; + gpio_irq_chip_set_chip(girq, &mt7621_irq_chip); /* This will let us handle the parent IRQ in the driver */ girq->parent_handler = NULL; girq->num_parents = 0; diff --git a/drivers/gpio/gpio-rockchip.c b/drivers/gpio/gpio-rockchip.c index f91e876fd969..bb50335239ac 100644 --- a/drivers/gpio/gpio-rockchip.c +++ b/drivers/gpio/gpio-rockchip.c @@ -419,11 +419,11 @@ static int rockchip_irq_set_type(struct irq_data *d, unsigned int type) goto out; } else { bank->toggle_edge_mode |= mask; - level |= mask; + level &= ~mask; /* * Determine gpio state. If 1 next interrupt should be - * falling otherwise rising. + * low otherwise high. */ data = readl(bank->reg_base + bank->gpio_regs->ext_port); if (data & mask) diff --git a/drivers/gpio/gpio-tqmx86.c b/drivers/gpio/gpio-tqmx86.c index fa4bc7481f9a..e739dcea61b2 100644 --- a/drivers/gpio/gpio-tqmx86.c +++ b/drivers/gpio/gpio-tqmx86.c @@ -307,6 +307,8 @@ static int tqmx86_gpio_probe(struct platform_device *pdev) girq->default_type = IRQ_TYPE_NONE; girq->handler = handle_simple_irq; girq->init_valid_mask = tqmx86_init_irq_valid_mask; + + irq_domain_set_pm_device(girq->domain, dev); } ret = devm_gpiochip_add_data(dev, chip, gpio); @@ -315,8 +317,6 @@ static int tqmx86_gpio_probe(struct platform_device *pdev) goto out_pm_dis; } - irq_domain_set_pm_device(girq->domain, dev); - dev_info(dev, "GPIO functionality initialized with %d pins\n", chip->ngpio); diff --git a/drivers/gpio/gpiolib-cdev.c b/drivers/gpio/gpiolib-cdev.c index f8041d4898d1..92f185575e94 100644 --- a/drivers/gpio/gpiolib-cdev.c +++ b/drivers/gpio/gpiolib-cdev.c @@ -1986,7 +1986,6 @@ static int lineevent_create(struct gpio_device *gdev, void __user *ip) ret = -ENODEV; goto out_free_le; } - le->irq = irq; if (eflags & GPIOEVENT_REQUEST_RISING_EDGE) irqflags |= test_bit(FLAG_ACTIVE_LOW, &desc->flags) ? @@ -2000,7 +1999,7 @@ static int lineevent_create(struct gpio_device *gdev, void __user *ip) init_waitqueue_head(&le->wait); /* Request a thread to read the events */ - ret = request_threaded_irq(le->irq, + ret = request_threaded_irq(irq, lineevent_irq_handler, lineevent_irq_thread, irqflags, @@ -2009,6 +2008,8 @@ static int lineevent_create(struct gpio_device *gdev, void __user *ip) if (ret) goto out_free_le; + le->irq = irq; + fd = get_unused_fd_flags(O_RDONLY | O_CLOEXEC); if (fd < 0) { ret = fd; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c index cbd593f7d553..2170db83e41d 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c @@ -1728,7 +1728,7 @@ int amdgpu_amdkfd_gpuvm_alloc_memory_of_gpu( add_kgd_mem_to_kfd_bo_list(*mem, avm->process_info, user_addr); if (user_addr) { - pr_debug("creating userptr BO for user_addr = %llu\n", user_addr); + pr_debug("creating userptr BO for user_addr = %llx\n", user_addr); ret = init_user_pages(*mem, user_addr, criu_resume); if (ret) goto allocate_init_user_pages_failed; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index 1400abee9f40..be7aff2d4a57 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -2365,8 +2365,16 @@ static int amdgpu_device_ip_init(struct amdgpu_device *adev) } adev->ip_blocks[i].status.sw = true; - /* need to do gmc hw init early so we can allocate gpu mem */ - if (adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_GMC) { + if (adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_COMMON) { + /* need to do common hw init early so everything is set up for gmc */ + r = adev->ip_blocks[i].version->funcs->hw_init((void *)adev); + if (r) { + DRM_ERROR("hw_init %d failed %d\n", i, r); + goto init_failed; + } + adev->ip_blocks[i].status.hw = true; + } else if (adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_GMC) { + /* need to do gmc hw init early so we can allocate gpu mem */ /* Try to reserve bad pages early */ if (amdgpu_sriov_vf(adev)) amdgpu_virt_exchange_data(adev); @@ -3052,8 +3060,8 @@ static int amdgpu_device_ip_reinit_early_sriov(struct amdgpu_device *adev) int i, r; static enum amd_ip_block_type ip_order[] = { - AMD_IP_BLOCK_TYPE_GMC, AMD_IP_BLOCK_TYPE_COMMON, + AMD_IP_BLOCK_TYPE_GMC, AMD_IP_BLOCK_TYPE_PSP, AMD_IP_BLOCK_TYPE_IH, }; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c index c20922a5af9f..5b09c8f4fe95 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c @@ -38,6 +38,7 @@ #include <linux/pci.h> #include <linux/pm_runtime.h> #include <drm/drm_crtc_helper.h> +#include <drm/drm_damage_helper.h> #include <drm/drm_edid.h> #include <drm/drm_gem_framebuffer_helper.h> #include <drm/drm_fb_helper.h> @@ -496,6 +497,7 @@ bool amdgpu_display_ddc_probe(struct amdgpu_connector *amdgpu_connector, static const struct drm_framebuffer_funcs amdgpu_fb_funcs = { .destroy = drm_gem_fb_destroy, .create_handle = drm_gem_fb_create_handle, + .dirty = drm_atomic_helper_dirtyfb, }; uint32_t amdgpu_display_supported_domains(struct amdgpu_device *adev, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c index 9f7a5e393f85..c9dec2434f37 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c @@ -486,11 +486,14 @@ static int psp_sw_fini(void *handle) release_firmware(psp->ta_fw); psp->ta_fw = NULL; } - if (adev->psp.cap_fw) { + if (psp->cap_fw) { release_firmware(psp->cap_fw); psp->cap_fw = NULL; } - + if (psp->toc_fw) { + release_firmware(psp->toc_fw); + psp->toc_fw = NULL; + } if (adev->ip_versions[MP0_HWIP][0] == IP_VERSION(11, 0, 0) || adev->ip_versions[MP0_HWIP][0] == IP_VERSION(11, 0, 7)) psp_sysfs_fini(adev); @@ -753,7 +756,7 @@ static int psp_tmr_init(struct psp_context *psp) } pptr = amdgpu_sriov_vf(psp->adev) ? &tmr_buf : NULL; - ret = amdgpu_bo_create_kernel(psp->adev, tmr_size, PSP_TMR_SIZE(psp->adev), + ret = amdgpu_bo_create_kernel(psp->adev, tmr_size, PSP_TMR_ALIGNMENT, AMDGPU_GEM_DOMAIN_VRAM, &psp->tmr_bo, &psp->tmr_mc_addr, pptr); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.h index c32b74bd970f..e593e8c2a54d 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.h @@ -36,6 +36,7 @@ #define PSP_CMD_BUFFER_SIZE 0x1000 #define PSP_1_MEG 0x100000 #define PSP_TMR_SIZE(adev) ((adev)->asic_type == CHIP_ALDEBARAN ? 0x800000 : 0x400000) +#define PSP_TMR_ALIGNMENT 0x100000 #define PSP_FW_NAME_LEN 0x24 enum psp_shared_mem_size { diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c index ff5361f5c2d4..12c6f97945a5 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c @@ -1811,7 +1811,8 @@ static void amdgpu_ras_log_on_err_counter(struct amdgpu_device *adev) amdgpu_ras_query_error_status(adev, &info); if (adev->ip_versions[MP0_HWIP][0] != IP_VERSION(11, 0, 2) && - adev->ip_versions[MP0_HWIP][0] != IP_VERSION(11, 0, 4)) { + adev->ip_versions[MP0_HWIP][0] != IP_VERSION(11, 0, 4) && + adev->ip_versions[MP0_HWIP][0] != IP_VERSION(13, 0, 0)) { if (amdgpu_ras_reset_error_status(adev, info.head.block)) dev_warn(adev->dev, "Failed to reset error counter and error status"); } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.h index ebed3f5226db..96b6cf4c4d54 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.h @@ -390,6 +390,7 @@ union amdgpu_firmware_header { struct rlc_firmware_header_v2_1 rlc_v2_1; struct rlc_firmware_header_v2_2 rlc_v2_2; struct rlc_firmware_header_v2_3 rlc_v2_3; + struct rlc_firmware_header_v2_4 rlc_v2_4; struct sdma_firmware_header_v1_0 sdma; struct sdma_firmware_header_v1_1 sdma_v1_1; struct sdma_firmware_header_v2_0 sdma_v2_0; diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v2_3.c b/drivers/gpu/drm/amd/amdgpu/nbio_v2_3.c index b465baa26762..aa761ff3a5fa 100644 --- a/drivers/gpu/drm/amd/amdgpu/nbio_v2_3.c +++ b/drivers/gpu/drm/amd/amdgpu/nbio_v2_3.c @@ -380,6 +380,7 @@ static void nbio_v2_3_enable_aspm(struct amdgpu_device *adev, WREG32_PCIE(smnPCIE_LC_CNTL, data); } +#ifdef CONFIG_PCIEASPM static void nbio_v2_3_program_ltr(struct amdgpu_device *adev) { uint32_t def, data; @@ -401,9 +402,11 @@ static void nbio_v2_3_program_ltr(struct amdgpu_device *adev) if (def != data) WREG32_PCIE(smnBIF_CFG_DEV0_EPF0_DEVICE_CNTL2, data); } +#endif static void nbio_v2_3_program_aspm(struct amdgpu_device *adev) { +#ifdef CONFIG_PCIEASPM uint32_t def, data; def = data = RREG32_PCIE(smnPCIE_LC_CNTL); @@ -459,7 +462,10 @@ static void nbio_v2_3_program_aspm(struct amdgpu_device *adev) if (def != data) WREG32_PCIE(smnPCIE_LC_CNTL6, data); - nbio_v2_3_program_ltr(adev); + /* Don't bother about LTR if LTR is not enabled + * in the path */ + if (adev->pdev->ltr_path) + nbio_v2_3_program_ltr(adev); def = data = RREG32_SOC15(NBIO, 0, mmRCC_BIF_STRAP3); data |= 0x5DE0 << RCC_BIF_STRAP3__STRAP_VLINK_ASPM_IDLE_TIMER__SHIFT; @@ -483,6 +489,7 @@ static void nbio_v2_3_program_aspm(struct amdgpu_device *adev) data &= ~PCIE_LC_CNTL3__LC_DSC_DONT_ENTER_L23_AFTER_PME_ACK_MASK; if (def != data) WREG32_PCIE(smnPCIE_LC_CNTL3, data); +#endif } static void nbio_v2_3_apply_lc_spc_mode_wa(struct amdgpu_device *adev) diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v6_1.c b/drivers/gpu/drm/amd/amdgpu/nbio_v6_1.c index f7f6ddebd3e4..37615a77287b 100644 --- a/drivers/gpu/drm/amd/amdgpu/nbio_v6_1.c +++ b/drivers/gpu/drm/amd/amdgpu/nbio_v6_1.c @@ -282,6 +282,7 @@ static void nbio_v6_1_init_registers(struct amdgpu_device *adev) mmBIF_BX_DEV0_EPF0_VF0_HDP_MEM_COHERENCY_FLUSH_CNTL) << 2; } +#ifdef CONFIG_PCIEASPM static void nbio_v6_1_program_ltr(struct amdgpu_device *adev) { uint32_t def, data; @@ -303,9 +304,11 @@ static void nbio_v6_1_program_ltr(struct amdgpu_device *adev) if (def != data) WREG32_PCIE(smnBIF_CFG_DEV0_EPF0_DEVICE_CNTL2, data); } +#endif static void nbio_v6_1_program_aspm(struct amdgpu_device *adev) { +#ifdef CONFIG_PCIEASPM uint32_t def, data; def = data = RREG32_PCIE(smnPCIE_LC_CNTL); @@ -361,7 +364,10 @@ static void nbio_v6_1_program_aspm(struct amdgpu_device *adev) if (def != data) WREG32_PCIE(smnPCIE_LC_CNTL6, data); - nbio_v6_1_program_ltr(adev); + /* Don't bother about LTR if LTR is not enabled + * in the path */ + if (adev->pdev->ltr_path) + nbio_v6_1_program_ltr(adev); def = data = RREG32_PCIE(smnRCC_BIF_STRAP3); data |= 0x5DE0 << RCC_BIF_STRAP3__STRAP_VLINK_ASPM_IDLE_TIMER__SHIFT; @@ -385,6 +391,7 @@ static void nbio_v6_1_program_aspm(struct amdgpu_device *adev) data &= ~PCIE_LC_CNTL3__LC_DSC_DONT_ENTER_L23_AFTER_PME_ACK_MASK; if (def != data) WREG32_PCIE(smnPCIE_LC_CNTL3, data); +#endif } const struct amdgpu_nbio_funcs nbio_v6_1_funcs = { diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c b/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c index 11848d1e238b..19455a725939 100644 --- a/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c +++ b/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c @@ -673,6 +673,7 @@ struct amdgpu_nbio_ras nbio_v7_4_ras = { }; +#ifdef CONFIG_PCIEASPM static void nbio_v7_4_program_ltr(struct amdgpu_device *adev) { uint32_t def, data; @@ -694,9 +695,11 @@ static void nbio_v7_4_program_ltr(struct amdgpu_device *adev) if (def != data) WREG32_PCIE(smnBIF_CFG_DEV0_EPF0_DEVICE_CNTL2, data); } +#endif static void nbio_v7_4_program_aspm(struct amdgpu_device *adev) { +#ifdef CONFIG_PCIEASPM uint32_t def, data; if (adev->ip_versions[NBIO_HWIP][0] == IP_VERSION(7, 4, 4)) @@ -755,7 +758,10 @@ static void nbio_v7_4_program_aspm(struct amdgpu_device *adev) if (def != data) WREG32_PCIE(smnPCIE_LC_CNTL6, data); - nbio_v7_4_program_ltr(adev); + /* Don't bother about LTR if LTR is not enabled + * in the path */ + if (adev->pdev->ltr_path) + nbio_v7_4_program_ltr(adev); def = data = RREG32_PCIE(smnRCC_BIF_STRAP3); data |= 0x5DE0 << RCC_BIF_STRAP3__STRAP_VLINK_ASPM_IDLE_TIMER__SHIFT; @@ -779,6 +785,7 @@ static void nbio_v7_4_program_aspm(struct amdgpu_device *adev) data &= ~PCIE_LC_CNTL3__LC_DSC_DONT_ENTER_L23_AFTER_PME_ACK_MASK; if (def != data) WREG32_PCIE(smnPCIE_LC_CNTL3, data); +#endif } const struct amdgpu_nbio_funcs nbio_v7_4_funcs = { diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v7_7.c b/drivers/gpu/drm/amd/amdgpu/nbio_v7_7.c index 1dc95ef21da6..def89379b51a 100644 --- a/drivers/gpu/drm/amd/amdgpu/nbio_v7_7.c +++ b/drivers/gpu/drm/amd/amdgpu/nbio_v7_7.c @@ -28,6 +28,14 @@ #include "nbio/nbio_7_7_0_sh_mask.h" #include <uapi/linux/kfd_ioctl.h> +static void nbio_v7_7_remap_hdp_registers(struct amdgpu_device *adev) +{ + WREG32_SOC15(NBIO, 0, regBIF_BX0_REMAP_HDP_MEM_FLUSH_CNTL, + adev->rmmio_remap.reg_offset + KFD_MMIO_REMAP_HDP_MEM_FLUSH_CNTL); + WREG32_SOC15(NBIO, 0, regBIF_BX0_REMAP_HDP_REG_FLUSH_CNTL, + adev->rmmio_remap.reg_offset + KFD_MMIO_REMAP_HDP_REG_FLUSH_CNTL); +} + static u32 nbio_v7_7_get_rev_id(struct amdgpu_device *adev) { u32 tmp; @@ -68,12 +76,6 @@ static void nbio_v7_7_sdma_doorbell_range(struct amdgpu_device *adev, int instan doorbell_range = REG_SET_FIELD(doorbell_range, GDC0_BIF_CSDMA_DOORBELL_RANGE, SIZE, doorbell_size); - doorbell_range = REG_SET_FIELD(doorbell_range, - GDC0_BIF_SDMA0_DOORBELL_RANGE, - OFFSET, doorbell_index); - doorbell_range = REG_SET_FIELD(doorbell_range, - GDC0_BIF_SDMA0_DOORBELL_RANGE, - SIZE, doorbell_size); } else { doorbell_range = REG_SET_FIELD(doorbell_range, GDC0_BIF_SDMA0_DOORBELL_RANGE, @@ -342,4 +344,5 @@ const struct amdgpu_nbio_funcs nbio_v7_7_funcs = { .get_clockgating_state = nbio_v7_7_get_clockgating_state, .ih_control = nbio_v7_7_ih_control, .init_registers = nbio_v7_7_init_registers, + .remap_hdp_registers = nbio_v7_7_remap_hdp_registers, }; diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c index 65181efba50e..56424f75dd2c 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c @@ -1504,6 +1504,11 @@ static int sdma_v4_0_start(struct amdgpu_device *adev) WREG32_SDMA(i, mmSDMA0_CNTL, temp); if (!amdgpu_sriov_vf(adev)) { + ring = &adev->sdma.instance[i].ring; + adev->nbio.funcs->sdma_doorbell_range(adev, i, + ring->use_doorbell, ring->doorbell_index, + adev->doorbell_index.sdma_doorbell_range); + /* unhalt engine */ temp = RREG32_SDMA(i, mmSDMA0_F32_CNTL); temp = REG_SET_FIELD(temp, SDMA0_F32_CNTL, HALT, 0); diff --git a/drivers/gpu/drm/amd/amdgpu/soc15.c b/drivers/gpu/drm/amd/amdgpu/soc15.c index fde6154f2009..183024d7c184 100644 --- a/drivers/gpu/drm/amd/amdgpu/soc15.c +++ b/drivers/gpu/drm/amd/amdgpu/soc15.c @@ -1211,25 +1211,6 @@ static int soc15_common_sw_fini(void *handle) return 0; } -static void soc15_doorbell_range_init(struct amdgpu_device *adev) -{ - int i; - struct amdgpu_ring *ring; - - /* sdma/ih doorbell range are programed by hypervisor */ - if (!amdgpu_sriov_vf(adev)) { - for (i = 0; i < adev->sdma.num_instances; i++) { - ring = &adev->sdma.instance[i].ring; - adev->nbio.funcs->sdma_doorbell_range(adev, i, - ring->use_doorbell, ring->doorbell_index, - adev->doorbell_index.sdma_doorbell_range); - } - - adev->nbio.funcs->ih_doorbell_range(adev, adev->irq.ih.use_doorbell, - adev->irq.ih.doorbell_index); - } -} - static int soc15_common_hw_init(void *handle) { struct amdgpu_device *adev = (struct amdgpu_device *)handle; @@ -1249,12 +1230,6 @@ static int soc15_common_hw_init(void *handle) /* enable the doorbell aperture */ soc15_enable_doorbell_aperture(adev, true); - /* HW doorbell routing policy: doorbell writing not - * in SDMA/IH/MM/ACV range will be routed to CP. So - * we need to init SDMA/IH/MM/ACV doorbell range prior - * to CP ip block init and ring test. - */ - soc15_doorbell_range_init(adev); return 0; } diff --git a/drivers/gpu/drm/amd/amdgpu/soc21.c b/drivers/gpu/drm/amd/amdgpu/soc21.c index 55284b24f113..2e50db3b761e 100644 --- a/drivers/gpu/drm/amd/amdgpu/soc21.c +++ b/drivers/gpu/drm/amd/amdgpu/soc21.c @@ -421,6 +421,7 @@ static bool soc21_need_full_reset(struct amdgpu_device *adev) { switch (adev->ip_versions[GC_HWIP][0]) { case IP_VERSION(11, 0, 0): + return amdgpu_ras_is_supported(adev, AMDGPU_RAS_BLOCK__UMC); case IP_VERSION(11, 0, 2): return false; default: diff --git a/drivers/gpu/drm/amd/amdgpu/vega10_ih.c b/drivers/gpu/drm/amd/amdgpu/vega10_ih.c index 03b7066471f9..1e83db0c5438 100644 --- a/drivers/gpu/drm/amd/amdgpu/vega10_ih.c +++ b/drivers/gpu/drm/amd/amdgpu/vega10_ih.c @@ -289,6 +289,10 @@ static int vega10_ih_irq_init(struct amdgpu_device *adev) } } + if (!amdgpu_sriov_vf(adev)) + adev->nbio.funcs->ih_doorbell_range(adev, adev->irq.ih.use_doorbell, + adev->irq.ih.doorbell_index); + pci_set_master(adev->pdev); /* enable interrupts */ diff --git a/drivers/gpu/drm/amd/amdgpu/vega20_ih.c b/drivers/gpu/drm/amd/amdgpu/vega20_ih.c index 2022ffbb8dba..59dfca093155 100644 --- a/drivers/gpu/drm/amd/amdgpu/vega20_ih.c +++ b/drivers/gpu/drm/amd/amdgpu/vega20_ih.c @@ -340,6 +340,10 @@ static int vega20_ih_irq_init(struct amdgpu_device *adev) } } + if (!amdgpu_sriov_vf(adev)) + adev->nbio.funcs->ih_doorbell_range(adev, adev->irq.ih.use_doorbell, + adev->irq.ih.doorbell_index); + pci_set_master(adev->pdev); /* enable interrupts */ diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c index 0e48824f55e3..ee242d9d8b06 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c @@ -3288,6 +3288,7 @@ void crtc_debugfs_init(struct drm_crtc *crtc) &crc_win_y_end_fops); debugfs_create_file_unsafe("crc_win_update", 0644, dir, crtc, &crc_win_update_fops); + dput(dir); #endif debugfs_create_file("amdgpu_current_bpc", 0644, crtc->debugfs_entry, crtc, &amdgpu_current_bpc_fops); diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_clk_mgr.c index beb025cd3dc2..9781a8dbc238 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_clk_mgr.c @@ -670,6 +670,8 @@ static void dcn314_clk_mgr_helper_populate_bw_params(struct clk_mgr_internal *cl } ASSERT(bw_params->clk_table.entries[i-1].dcfclk_mhz); bw_params->vram_type = bios_info->memory_type; + + bw_params->dram_channel_width_bytes = bios_info->memory_type == 0x22 ? 8 : 4; bw_params->num_channels = bios_info->ma_channel_number ? bios_info->ma_channel_number : 4; for (i = 0; i < WM_SET_COUNT; i++) { diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_stream.c b/drivers/gpu/drm/amd/display/dc/core/dc_stream.c index f62d50901d92..0c85ab5933b4 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_stream.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_stream.c @@ -329,7 +329,7 @@ bool dc_stream_set_cursor_attributes( dc = stream->ctx->dc; - if (attributes->height * attributes->width * 4 > 16384) + if (dc->debug.allow_sw_cursor_fallback && attributes->height * attributes->width * 4 > 16384) if (stream->mall_stream_config.type == SUBVP_MAIN) return false; diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h index 5908b60db313..dbf8158b832e 100644 --- a/drivers/gpu/drm/amd/display/dc/dc.h +++ b/drivers/gpu/drm/amd/display/dc/dc.h @@ -745,6 +745,7 @@ struct dc_debug_options { bool disable_fixed_vs_aux_timeout_wa; bool force_disable_subvp; bool force_subvp_mclk_switch; + bool allow_sw_cursor_fallback; bool force_usr_allow; /* uses value at boot and disables switch */ bool disable_dtb_ref_clk_switch; diff --git a/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.c b/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.c index 09b304507bad..52a61b3e5a8b 100644 --- a/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.c +++ b/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.c @@ -417,44 +417,42 @@ static void populate_subvp_cmd_drr_info(struct dc *dc, struct dc_crtc_timing *main_timing = &subvp_pipe->stream->timing; struct dc_crtc_timing *phantom_timing = &subvp_pipe->stream->mall_stream_config.paired_stream->timing; struct dc_crtc_timing *drr_timing = &vblank_pipe->stream->timing; - int16_t drr_frame_us = 0; - int16_t min_drr_supported_us = 0; - int16_t max_drr_supported_us = 0; - int16_t max_drr_vblank_us = 0; - int16_t max_drr_mallregion_us = 0; - int16_t mall_region_us = 0; - int16_t prefetch_us = 0; - int16_t subvp_active_us = 0; - int16_t drr_active_us = 0; - int16_t min_vtotal_supported = 0; - int16_t max_vtotal_supported = 0; + uint16_t drr_frame_us = 0; + uint16_t min_drr_supported_us = 0; + uint16_t max_drr_supported_us = 0; + uint16_t max_drr_vblank_us = 0; + uint16_t max_drr_mallregion_us = 0; + uint16_t mall_region_us = 0; + uint16_t prefetch_us = 0; + uint16_t subvp_active_us = 0; + uint16_t drr_active_us = 0; + uint16_t min_vtotal_supported = 0; + uint16_t max_vtotal_supported = 0; pipe_data->pipe_config.vblank_data.drr_info.drr_in_use = true; pipe_data->pipe_config.vblank_data.drr_info.use_ramping = false; // for now don't use ramping pipe_data->pipe_config.vblank_data.drr_info.drr_window_size_ms = 4; // hardcode 4ms DRR window for now - drr_frame_us = div64_s64(drr_timing->v_total * drr_timing->h_total, - (int64_t)(drr_timing->pix_clk_100hz * 100) * 1000000); + drr_frame_us = div64_u64(((uint64_t)drr_timing->v_total * drr_timing->h_total * 1000000), + (((uint64_t)drr_timing->pix_clk_100hz * 100))); // P-State allow width and FW delays already included phantom_timing->v_addressable - mall_region_us = div64_s64(phantom_timing->v_addressable * phantom_timing->h_total, - (int64_t)(phantom_timing->pix_clk_100hz * 100) * 1000000); + mall_region_us = div64_u64(((uint64_t)phantom_timing->v_addressable * phantom_timing->h_total * 1000000), + (((uint64_t)phantom_timing->pix_clk_100hz * 100))); min_drr_supported_us = drr_frame_us + mall_region_us + SUBVP_DRR_MARGIN_US; - min_vtotal_supported = div64_s64(drr_timing->pix_clk_100hz * 100 * - (div64_s64((int64_t)min_drr_supported_us, 1000000)), - (int64_t)drr_timing->h_total); - - prefetch_us = div64_s64((phantom_timing->v_total - phantom_timing->v_front_porch) * phantom_timing->h_total, - (int64_t)(phantom_timing->pix_clk_100hz * 100) * 1000000 + - dc->caps.subvp_prefetch_end_to_mall_start_us); - subvp_active_us = div64_s64(main_timing->v_addressable * main_timing->h_total, - (int64_t)(main_timing->pix_clk_100hz * 100) * 1000000); - drr_active_us = div64_s64(drr_timing->v_addressable * drr_timing->h_total, - (int64_t)(drr_timing->pix_clk_100hz * 100) * 1000000); - max_drr_vblank_us = div64_s64((int64_t)(subvp_active_us - prefetch_us - drr_active_us), 2) + drr_active_us; + min_vtotal_supported = div64_u64(((uint64_t)drr_timing->pix_clk_100hz * 100 * min_drr_supported_us), + (((uint64_t)drr_timing->h_total * 1000000))); + + prefetch_us = div64_u64(((uint64_t)(phantom_timing->v_total - phantom_timing->v_front_porch) * phantom_timing->h_total * 1000000), + (((uint64_t)phantom_timing->pix_clk_100hz * 100) + dc->caps.subvp_prefetch_end_to_mall_start_us)); + subvp_active_us = div64_u64(((uint64_t)main_timing->v_addressable * main_timing->h_total * 1000000), + (((uint64_t)main_timing->pix_clk_100hz * 100))); + drr_active_us = div64_u64(((uint64_t)drr_timing->v_addressable * drr_timing->h_total * 1000000), + (((uint64_t)drr_timing->pix_clk_100hz * 100))); + max_drr_vblank_us = div64_u64((subvp_active_us - prefetch_us - drr_active_us), 2) + drr_active_us; max_drr_mallregion_us = subvp_active_us - prefetch_us - mall_region_us; max_drr_supported_us = max_drr_vblank_us > max_drr_mallregion_us ? max_drr_vblank_us : max_drr_mallregion_us; - max_vtotal_supported = div64_s64(drr_timing->pix_clk_100hz * 100 * (div64_s64((int64_t)max_drr_supported_us, 1000000)), - (int64_t)drr_timing->h_total); + max_vtotal_supported = div64_u64(((uint64_t)drr_timing->pix_clk_100hz * 100 * max_drr_supported_us), + (((uint64_t)drr_timing->h_total * 1000000))); pipe_data->pipe_config.vblank_data.drr_info.min_vtotal_supported = min_vtotal_supported; pipe_data->pipe_config.vblank_data.drr_info.max_vtotal_supported = max_vtotal_supported; @@ -548,10 +546,12 @@ static void update_subvp_prefetch_end_to_mall_start(struct dc *dc, struct dc_crtc_timing *phantom_timing1 = &subvp_pipes[1]->stream->mall_stream_config.paired_stream->timing; struct dmub_cmd_fw_assisted_mclk_switch_pipe_data_v2 *pipe_data = NULL; - subvp0_prefetch_us = div64_s64((phantom_timing0->v_total - phantom_timing0->v_front_porch) * phantom_timing0->h_total, - (int64_t)(phantom_timing0->pix_clk_100hz * 100) * 1000000 + dc->caps.subvp_prefetch_end_to_mall_start_us); - subvp1_prefetch_us = div64_s64((phantom_timing1->v_total - phantom_timing1->v_front_porch) * phantom_timing1->h_total, - (int64_t)(phantom_timing1->pix_clk_100hz * 100) * 1000000 + dc->caps.subvp_prefetch_end_to_mall_start_us); + subvp0_prefetch_us = div64_u64(((uint64_t)(phantom_timing0->v_total - phantom_timing0->v_front_porch) * + (uint64_t)phantom_timing0->h_total * 1000000), + (((uint64_t)phantom_timing0->pix_clk_100hz * 100) + dc->caps.subvp_prefetch_end_to_mall_start_us)); + subvp1_prefetch_us = div64_u64(((uint64_t)(phantom_timing1->v_total - phantom_timing1->v_front_porch) * + (uint64_t)phantom_timing1->h_total * 1000000), + (((uint64_t)phantom_timing1->pix_clk_100hz * 100) + dc->caps.subvp_prefetch_end_to_mall_start_us)); // Whichever SubVP PIPE has the smaller prefetch (including the prefetch end to mall start time) // should increase it's prefetch time to match the other @@ -559,16 +559,17 @@ static void update_subvp_prefetch_end_to_mall_start(struct dc *dc, pipe_data = &cmd->fw_assisted_mclk_switch_v2.config_data.pipe_data[1]; prefetch_delta_us = subvp0_prefetch_us - subvp1_prefetch_us; pipe_data->pipe_config.subvp_data.prefetch_to_mall_start_lines = - div64_s64(((div64_s64((int64_t)(dc->caps.subvp_prefetch_end_to_mall_start_us + prefetch_delta_us), 1000000)) * - (phantom_timing1->pix_clk_100hz * 100) + phantom_timing1->h_total - 1), - (int64_t)phantom_timing1->h_total); + div64_u64(((uint64_t)(dc->caps.subvp_prefetch_end_to_mall_start_us + prefetch_delta_us) * + ((uint64_t)phantom_timing1->pix_clk_100hz * 100) + ((uint64_t)phantom_timing1->h_total * 1000000 - 1)), + ((uint64_t)phantom_timing1->h_total * 1000000)); + } else if (subvp1_prefetch_us > subvp0_prefetch_us) { pipe_data = &cmd->fw_assisted_mclk_switch_v2.config_data.pipe_data[0]; prefetch_delta_us = subvp1_prefetch_us - subvp0_prefetch_us; pipe_data->pipe_config.subvp_data.prefetch_to_mall_start_lines = - div64_s64(((div64_s64((int64_t)(dc->caps.subvp_prefetch_end_to_mall_start_us + prefetch_delta_us), 1000000)) * - (phantom_timing0->pix_clk_100hz * 100) + phantom_timing0->h_total - 1), - (int64_t)phantom_timing0->h_total); + div64_u64(((uint64_t)(dc->caps.subvp_prefetch_end_to_mall_start_us + prefetch_delta_us) * + ((uint64_t)phantom_timing0->pix_clk_100hz * 100) + ((uint64_t)phantom_timing0->h_total * 1000000 - 1)), + ((uint64_t)phantom_timing0->h_total * 1000000)); } } @@ -630,13 +631,11 @@ static void populate_subvp_cmd_pipe_info(struct dc *dc, // Round up pipe_data->pipe_config.subvp_data.prefetch_to_mall_start_lines = - div64_s64(((div64_s64((int64_t)dc->caps.subvp_prefetch_end_to_mall_start_us, 1000000)) * - (phantom_timing->pix_clk_100hz * 100) + phantom_timing->h_total - 1), - (int64_t)phantom_timing->h_total); + div64_u64(((uint64_t)dc->caps.subvp_prefetch_end_to_mall_start_us * ((uint64_t)phantom_timing->pix_clk_100hz * 100) + + ((uint64_t)phantom_timing->h_total * 1000000 - 1)), ((uint64_t)phantom_timing->h_total * 1000000)); pipe_data->pipe_config.subvp_data.processing_delay_lines = - div64_s64(((div64_s64((int64_t)dc->caps.subvp_fw_processing_delay_us, 1000000)) * - (phantom_timing->pix_clk_100hz * 100) + phantom_timing->h_total - 1), - (int64_t)phantom_timing->h_total); + div64_u64(((uint64_t)(dc->caps.subvp_fw_processing_delay_us) * ((uint64_t)phantom_timing->pix_clk_100hz * 100) + + ((uint64_t)phantom_timing->h_total * 1000000 - 1)), ((uint64_t)phantom_timing->h_total * 1000000)); // Find phantom pipe index based on phantom stream for (j = 0; j < dc->res_pool->pipe_count; j++) { struct pipe_ctx *phantom_pipe = &context->res_ctx.pipe_ctx[j]; diff --git a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_dio_stream_encoder.c b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_dio_stream_encoder.c index e3351ddc566c..06d8638db696 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_dio_stream_encoder.c +++ b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_dio_stream_encoder.c @@ -67,8 +67,7 @@ static void enc314_disable_fifo(struct stream_encoder *enc) { struct dcn10_stream_encoder *enc1 = DCN10STRENC_FROM_STRENC(enc); - REG_UPDATE_2(DIG_FIFO_CTRL0, DIG_FIFO_ENABLE, 0, - DIG_FIFO_READ_START_LEVEL, 0); + REG_UPDATE(DIG_FIFO_CTRL0, DIG_FIFO_ENABLE, 0); } static void enc314_dp_set_odm_combine( diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hubp.c b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hubp.c index 6ec1c52535b9..2038cbda33f7 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hubp.c +++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hubp.c @@ -103,6 +103,11 @@ void hubp32_cursor_set_attributes( enum cursor_lines_per_chunk lpc = hubp2_get_lines_per_chunk( attr->width, attr->color_format); + //Round cursor width up to next multiple of 64 + uint32_t cursor_width = ((attr->width + 63) / 64) * 64; + uint32_t cursor_height = attr->height; + uint32_t cursor_size = cursor_width * cursor_height; + hubp->curs_attr = *attr; REG_UPDATE(CURSOR_SURFACE_ADDRESS_HIGH, @@ -126,7 +131,24 @@ void hubp32_cursor_set_attributes( /* used to shift the cursor chunk request deadline */ CURSOR0_CHUNK_HDL_ADJUST, 3); - if (attr->width * attr->height * 4 > 16384) + switch (attr->color_format) { + case CURSOR_MODE_MONO: + cursor_size /= 2; + break; + case CURSOR_MODE_COLOR_1BIT_AND: + case CURSOR_MODE_COLOR_PRE_MULTIPLIED_ALPHA: + case CURSOR_MODE_COLOR_UN_PRE_MULTIPLIED_ALPHA: + cursor_size *= 4; + break; + + case CURSOR_MODE_COLOR_64BIT_FP_PRE_MULTIPLIED: + case CURSOR_MODE_COLOR_64BIT_FP_UN_PRE_MULTIPLIED: + default: + cursor_size *= 8; + break; + } + + if (cursor_size > 16384) REG_UPDATE(DCHUBP_MALL_CONFIG, USE_MALL_FOR_CURSOR, true); else REG_UPDATE(DCHUBP_MALL_CONFIG, USE_MALL_FOR_CURSOR, false); diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.c index 8d9d96c39808..344fe7535df5 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.c @@ -741,7 +741,29 @@ void dcn32_update_mall_sel(struct dc *dc, struct dc_state *context) struct hubp *hubp = pipe->plane_res.hubp; if (pipe->stream && pipe->plane_state && hubp && hubp->funcs->hubp_update_mall_sel) { - if (hubp->curs_attr.width * hubp->curs_attr.height * 4 > 16384) + //Round cursor width up to next multiple of 64 + int cursor_width = ((hubp->curs_attr.width + 63) / 64) * 64; + int cursor_height = hubp->curs_attr.height; + int cursor_size = cursor_width * cursor_height; + + switch (hubp->curs_attr.color_format) { + case CURSOR_MODE_MONO: + cursor_size /= 2; + break; + case CURSOR_MODE_COLOR_1BIT_AND: + case CURSOR_MODE_COLOR_PRE_MULTIPLIED_ALPHA: + case CURSOR_MODE_COLOR_UN_PRE_MULTIPLIED_ALPHA: + cursor_size *= 4; + break; + + case CURSOR_MODE_COLOR_64BIT_FP_PRE_MULTIPLIED: + case CURSOR_MODE_COLOR_64BIT_FP_UN_PRE_MULTIPLIED: + default: + cursor_size *= 8; + break; + } + + if (cursor_size > 16384) cache_cursor = true; if (pipe->stream->mall_stream_config.type == SUBVP_PHANTOM) { diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.c b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.c index 8b887b552f2c..c3b783cea8a0 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.c @@ -871,6 +871,7 @@ static const struct dc_debug_options debug_defaults_drv = { .exit_idle_opt_for_cursor_updates = true, .enable_single_display_2to1_odm_policy = true, .enable_dp_dig_pixel_rate_div_policy = 1, + .allow_sw_cursor_fallback = false, }; static const struct dc_debug_options debug_defaults_diags = { @@ -2039,7 +2040,8 @@ static bool dcn32_resource_construct( dc->caps.max_downscale_ratio = 600; dc->caps.i2c_speed_in_khz = 100; dc->caps.i2c_speed_in_khz_hdcp = 100; /*1.4 w/a applied by default*/ - dc->caps.max_cursor_size = 256; + /* TODO: Bring max_cursor_size back to 256 after subvp cursor corruption is fixed*/ + dc->caps.max_cursor_size = 64; dc->caps.min_horizontal_blanking_period = 80; dc->caps.dmdata_alloc_size = 2048; dc->caps.mall_size_per_mem_channel = 0; diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.h b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.h index 1e7e6201c880..cf15d0e5e9b4 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.h +++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.h @@ -30,6 +30,9 @@ #define DCN3_2_DET_SEG_SIZE 64 #define DCN3_2_MALL_MBLK_SIZE_BYTES 65536 // 64 * 1024 +#define DCN3_2_MBLK_WIDTH 128 +#define DCN3_2_MBLK_HEIGHT_4BPE 128 +#define DCN3_2_MBLK_HEIGHT_8BPE 64 #define TO_DCN32_RES_POOL(pool)\ container_of(pool, struct dcn32_resource_pool, base) diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource_helpers.c b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource_helpers.c index ab918fe38f6a..1f195c5b3377 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource_helpers.c +++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource_helpers.c @@ -46,7 +46,6 @@ uint32_t dcn32_helper_calculate_num_ways_for_subvp(struct dc *dc, struct dc_state *context) { uint32_t num_ways = 0; - uint32_t mall_region_pixels = 0; uint32_t bytes_per_pixel = 0; uint32_t cache_lines_used = 0; uint32_t lines_per_way = 0; @@ -54,20 +53,64 @@ uint32_t dcn32_helper_calculate_num_ways_for_subvp(struct dc *dc, struct dc_stat uint32_t bytes_in_mall = 0; uint32_t num_mblks = 0; uint32_t cache_lines_per_plane = 0; - uint32_t i = 0; + uint32_t i = 0, j = 0; + uint32_t mblk_width = 0; + uint32_t mblk_height = 0; + uint32_t full_vp_width_blk_aligned = 0; + uint32_t full_vp_height_blk_aligned = 0; + uint32_t mall_alloc_width_blk_aligned = 0; + uint32_t mall_alloc_height_blk_aligned = 0; + uint32_t full_vp_height = 0; for (i = 0; i < dc->res_pool->pipe_count; i++) { struct pipe_ctx *pipe = &context->res_ctx.pipe_ctx[i]; // Find the phantom pipes - if (pipe->stream && pipe->plane_state && !pipe->top_pipe && + if (pipe->stream && pipe->plane_state && !pipe->top_pipe && !pipe->prev_odm_pipe && pipe->stream->mall_stream_config.type == SUBVP_PHANTOM) { - bytes_per_pixel = pipe->plane_state->format >= SURFACE_PIXEL_FORMAT_GRPH_ARGB16161616 ? 8 : 4; - mall_region_pixels = pipe->plane_state->plane_size.surface_pitch * pipe->stream->timing.v_addressable; + struct pipe_ctx *main_pipe = NULL; + + /* Get full viewport height from main pipe (required for MBLK calculation) */ + for (j = 0; j < dc->res_pool->pipe_count; j++) { + main_pipe = &context->res_ctx.pipe_ctx[j]; + if (main_pipe->stream == pipe->stream->mall_stream_config.paired_stream) { + full_vp_height = main_pipe->plane_res.scl_data.viewport.height; + break; + } + } - // For bytes required in MALL, calculate based on number of MBlks required - num_mblks = (mall_region_pixels * bytes_per_pixel + - DCN3_2_MALL_MBLK_SIZE_BYTES - 1) / DCN3_2_MALL_MBLK_SIZE_BYTES; + bytes_per_pixel = pipe->plane_state->format >= SURFACE_PIXEL_FORMAT_GRPH_ARGB16161616 ? 8 : 4; + mblk_width = DCN3_2_MBLK_WIDTH; + mblk_height = bytes_per_pixel == 4 ? DCN3_2_MBLK_HEIGHT_4BPE : DCN3_2_MBLK_HEIGHT_8BPE; + + /* full_vp_width_blk_aligned = FLOOR(vp_x_start + full_vp_width + blk_width - 1, blk_width) - + * FLOOR(vp_x_start, blk_width) + */ + full_vp_width_blk_aligned = ((pipe->plane_res.scl_data.viewport.x + + pipe->plane_res.scl_data.viewport.width + mblk_width - 1) / mblk_width * mblk_width) + + (pipe->plane_res.scl_data.viewport.x / mblk_width * mblk_width); + + /* full_vp_height_blk_aligned = FLOOR(vp_y_start + full_vp_height + blk_height - 1, blk_height) - + * FLOOR(vp_y_start, blk_height) + */ + full_vp_height_blk_aligned = ((pipe->plane_res.scl_data.viewport.y + + full_vp_height + mblk_height - 1) / mblk_height * mblk_height) + + (pipe->plane_res.scl_data.viewport.y / mblk_height * mblk_height); + + /* mall_alloc_width_blk_aligned_l/c = full_vp_width_blk_aligned_l/c */ + mall_alloc_width_blk_aligned = full_vp_width_blk_aligned; + + /* mall_alloc_height_blk_aligned_l/c = CEILING(sub_vp_height_l/c - 1, blk_height_l/c) + blk_height_l/c */ + mall_alloc_height_blk_aligned = (pipe->stream->timing.v_addressable - 1 + mblk_height - 1) / + mblk_height * mblk_height + mblk_height; + + /* full_mblk_width_ub_l/c = mall_alloc_width_blk_aligned_l/c; + * full_mblk_height_ub_l/c = mall_alloc_height_blk_aligned_l/c; + * num_mblk_l/c = (full_mblk_width_ub_l/c / mblk_width_l/c) * (full_mblk_height_ub_l/c / mblk_height_l/c); + * (Should be divisible, but round up if not) + */ + num_mblks = ((mall_alloc_width_blk_aligned + mblk_width - 1) / mblk_width) * + ((mall_alloc_height_blk_aligned + mblk_height - 1) / mblk_height); bytes_in_mall = num_mblks * DCN3_2_MALL_MBLK_SIZE_BYTES; // cache lines used is total bytes / cache_line size. Add +2 for worst case alignment // (MALL is 64-byte aligned) diff --git a/drivers/gpu/drm/amd/display/dc/dcn321/dcn321_resource.c b/drivers/gpu/drm/amd/display/dc/dcn321/dcn321_resource.c index c8b7d6ff38f4..7309eed33a61 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn321/dcn321_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn321/dcn321_resource.c @@ -872,6 +872,7 @@ static const struct dc_debug_options debug_defaults_drv = { .exit_idle_opt_for_cursor_updates = true, .enable_single_display_2to1_odm_policy = true, .enable_dp_dig_pixel_rate_div_policy = 1, + .allow_sw_cursor_fallback = false, }; static const struct dc_debug_options debug_defaults_diags = { @@ -1651,7 +1652,8 @@ static bool dcn321_resource_construct( dc->caps.max_downscale_ratio = 600; dc->caps.i2c_speed_in_khz = 100; dc->caps.i2c_speed_in_khz_hdcp = 100; /*1.4 w/a applied by default*/ - dc->caps.max_cursor_size = 256; + /* TODO: Bring max cursor size back to 256 after subvp cursor corruption is fixed*/ + dc->caps.max_cursor_size = 64; dc->caps.min_horizontal_blanking_period = 80; dc->caps.dmdata_alloc_size = 2048; dc->caps.mall_size_per_mem_channel = 0; diff --git a/drivers/gpu/drm/amd/display/dc/dml/Makefile b/drivers/gpu/drm/amd/display/dc/dml/Makefile index 86a3b5bfd699..cb81ed2fbd53 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/Makefile +++ b/drivers/gpu/drm/amd/display/dc/dml/Makefile @@ -70,6 +70,8 @@ CFLAGS_$(AMDDALPATH)/dc/dml/dcn30/display_mode_vba_30.o := $(dml_ccflags) $(fram CFLAGS_$(AMDDALPATH)/dc/dml/dcn30/display_rq_dlg_calc_30.o := $(dml_ccflags) CFLAGS_$(AMDDALPATH)/dc/dml/dcn31/display_mode_vba_31.o := $(dml_ccflags) $(frame_warn_flag) CFLAGS_$(AMDDALPATH)/dc/dml/dcn31/display_rq_dlg_calc_31.o := $(dml_ccflags) +CFLAGS_$(AMDDALPATH)/dc/dml/dcn314/display_mode_vba_314.o := $(dml_ccflags) $(frame_warn_flag) +CFLAGS_$(AMDDALPATH)/dc/dml/dcn314/display_rq_dlg_calc_314.o := $(dml_ccflags) CFLAGS_$(AMDDALPATH)/dc/dml/dcn314/dcn314_fpu.o := $(dml_ccflags) CFLAGS_$(AMDDALPATH)/dc/dml/dcn30/dcn30_fpu.o := $(dml_ccflags) CFLAGS_$(AMDDALPATH)/dc/dml/dcn32/dcn32_fpu.o := $(dml_ccflags) @@ -123,6 +125,7 @@ DML += dcn20/display_rq_dlg_calc_20v2.o dcn20/display_mode_vba_20v2.o DML += dcn21/display_rq_dlg_calc_21.o dcn21/display_mode_vba_21.o DML += dcn30/dcn30_fpu.o dcn30/display_mode_vba_30.o dcn30/display_rq_dlg_calc_30.o DML += dcn31/display_mode_vba_31.o dcn31/display_rq_dlg_calc_31.o +DML += dcn314/display_mode_vba_314.o dcn314/display_rq_dlg_calc_314.o DML += dcn32/display_mode_vba_32.o dcn32/display_rq_dlg_calc_32.o dcn32/display_mode_vba_util_32.o DML += dcn31/dcn31_fpu.o DML += dcn32/dcn32_fpu.o diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn30/display_mode_vba_30.c b/drivers/gpu/drm/amd/display/dc/dml/dcn30/display_mode_vba_30.c index 876b321b30ca..1cb858dd6ea0 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn30/display_mode_vba_30.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn30/display_mode_vba_30.c @@ -6610,8 +6610,7 @@ static double CalculateUrgentLatency( return ret; } - -static void UseMinimumDCFCLK( +static noinline_for_stack void UseMinimumDCFCLK( struct display_mode_lib *mode_lib, int MaxInterDCNTileRepeaters, int MaxPrefetchMode, diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn31/display_mode_vba_31.c b/drivers/gpu/drm/amd/display/dc/dml/dcn31/display_mode_vba_31.c index d63b4209b14c..8ca66f1644dc 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn31/display_mode_vba_31.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn31/display_mode_vba_31.c @@ -251,33 +251,13 @@ static void CalculateRowBandwidth( static void CalculateFlipSchedule( struct display_mode_lib *mode_lib, + unsigned int k, double HostVMInefficiencyFactor, double UrgentExtraLatency, double UrgentLatency, - unsigned int GPUVMMaxPageTableLevels, - bool HostVMEnable, - unsigned int HostVMMaxNonCachedPageTableLevels, - bool GPUVMEnable, - double HostVMMinPageSize, double PDEAndMetaPTEBytesPerFrame, double MetaRowBytes, - double DPTEBytesPerRow, - double BandwidthAvailableForImmediateFlip, - unsigned int TotImmediateFlipBytes, - enum source_format_class SourcePixelFormat, - double LineTime, - double VRatio, - double VRatioChroma, - double Tno_bw, - bool DCCEnable, - unsigned int dpte_row_height, - unsigned int meta_row_height, - unsigned int dpte_row_height_chroma, - unsigned int meta_row_height_chroma, - double *DestinationLinesToRequestVMInImmediateFlip, - double *DestinationLinesToRequestRowInImmediateFlip, - double *final_flip_bw, - bool *ImmediateFlipSupportedForPipe); + double DPTEBytesPerRow); static double CalculateWriteBackDelay( enum source_format_class WritebackPixelFormat, double WritebackHRatio, @@ -311,64 +291,28 @@ static void CalculateVupdateAndDynamicMetadataParameters( static void CalculateWatermarksAndDRAMSpeedChangeSupport( struct display_mode_lib *mode_lib, unsigned int PrefetchMode, - unsigned int NumberOfActivePlanes, - unsigned int MaxLineBufferLines, - unsigned int LineBufferSize, - unsigned int WritebackInterfaceBufferSize, double DCFCLK, double ReturnBW, - bool SynchronizedVBlank, - unsigned int dpte_group_bytes[], - unsigned int MetaChunkSize, double UrgentLatency, double ExtraLatency, - double WritebackLatency, - double WritebackChunkSize, double SOCCLK, - double DRAMClockChangeLatency, - double SRExitTime, - double SREnterPlusExitTime, - double SRExitZ8Time, - double SREnterPlusExitZ8Time, double DCFCLKDeepSleep, unsigned int DETBufferSizeY[], unsigned int DETBufferSizeC[], unsigned int SwathHeightY[], unsigned int SwathHeightC[], - unsigned int LBBitPerPixel[], double SwathWidthY[], double SwathWidthC[], - double HRatio[], - double HRatioChroma[], - unsigned int vtaps[], - unsigned int VTAPsChroma[], - double VRatio[], - double VRatioChroma[], - unsigned int HTotal[], - double PixelClock[], - unsigned int BlendingAndTiming[], unsigned int DPPPerPlane[], double BytePerPixelDETY[], double BytePerPixelDETC[], - double DSTXAfterScaler[], - double DSTYAfterScaler[], - bool WritebackEnable[], - enum source_format_class WritebackPixelFormat[], - double WritebackDestinationWidth[], - double WritebackDestinationHeight[], - double WritebackSourceHeight[], bool UnboundedRequestEnabled, int unsigned CompressedBufferSizeInkByte, enum clock_change_support *DRAMClockChangeSupport, - double *UrgentWatermark, - double *WritebackUrgentWatermark, - double *DRAMClockChangeWatermark, - double *WritebackDRAMClockChangeWatermark, double *StutterExitWatermark, double *StutterEnterPlusExitWatermark, double *Z8StutterExitWatermark, - double *Z8StutterEnterPlusExitWatermark, - double *MinActiveDRAMClockChangeLatencySupported); + double *Z8StutterEnterPlusExitWatermark); static void CalculateDCFCLKDeepSleep( struct display_mode_lib *mode_lib, @@ -2904,33 +2848,13 @@ static void DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerforman for (k = 0; k < v->NumberOfActivePlanes; ++k) { CalculateFlipSchedule( mode_lib, + k, HostVMInefficiencyFactor, v->UrgentExtraLatency, v->UrgentLatency, - v->GPUVMMaxPageTableLevels, - v->HostVMEnable, - v->HostVMMaxNonCachedPageTableLevels, - v->GPUVMEnable, - v->HostVMMinPageSize, v->PDEAndMetaPTEBytesFrame[k], v->MetaRowByte[k], - v->PixelPTEBytesPerRow[k], - v->BandwidthAvailableForImmediateFlip, - v->TotImmediateFlipBytes, - v->SourcePixelFormat[k], - v->HTotal[k] / v->PixelClock[k], - v->VRatio[k], - v->VRatioChroma[k], - v->Tno_bw[k], - v->DCCEnable[k], - v->dpte_row_height[k], - v->meta_row_height[k], - v->dpte_row_height_chroma[k], - v->meta_row_height_chroma[k], - &v->DestinationLinesToRequestVMInImmediateFlip[k], - &v->DestinationLinesToRequestRowInImmediateFlip[k], - &v->final_flip_bw[k], - &v->ImmediateFlipSupportedForPipe[k]); + v->PixelPTEBytesPerRow[k]); } v->total_dcn_read_bw_with_flip = 0.0; @@ -3017,64 +2941,28 @@ static void DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerforman CalculateWatermarksAndDRAMSpeedChangeSupport( mode_lib, PrefetchMode, - v->NumberOfActivePlanes, - v->MaxLineBufferLines, - v->LineBufferSize, - v->WritebackInterfaceBufferSize, v->DCFCLK, v->ReturnBW, - v->SynchronizedVBlank, - v->dpte_group_bytes, - v->MetaChunkSize, v->UrgentLatency, v->UrgentExtraLatency, - v->WritebackLatency, - v->WritebackChunkSize, v->SOCCLK, - v->DRAMClockChangeLatency, - v->SRExitTime, - v->SREnterPlusExitTime, - v->SRExitZ8Time, - v->SREnterPlusExitZ8Time, v->DCFCLKDeepSleep, v->DETBufferSizeY, v->DETBufferSizeC, v->SwathHeightY, v->SwathHeightC, - v->LBBitPerPixel, v->SwathWidthY, v->SwathWidthC, - v->HRatio, - v->HRatioChroma, - v->vtaps, - v->VTAPsChroma, - v->VRatio, - v->VRatioChroma, - v->HTotal, - v->PixelClock, - v->BlendingAndTiming, v->DPPPerPlane, v->BytePerPixelDETY, v->BytePerPixelDETC, - v->DSTXAfterScaler, - v->DSTYAfterScaler, - v->WritebackEnable, - v->WritebackPixelFormat, - v->WritebackDestinationWidth, - v->WritebackDestinationHeight, - v->WritebackSourceHeight, v->UnboundedRequestEnabled, v->CompressedBufferSizeInkByte, &DRAMClockChangeSupport, - &v->UrgentWatermark, - &v->WritebackUrgentWatermark, - &v->DRAMClockChangeWatermark, - &v->WritebackDRAMClockChangeWatermark, &v->StutterExitWatermark, &v->StutterEnterPlusExitWatermark, &v->Z8StutterExitWatermark, - &v->Z8StutterEnterPlusExitWatermark, - &v->MinActiveDRAMClockChangeLatencySupported); + &v->Z8StutterEnterPlusExitWatermark); for (k = 0; k < v->NumberOfActivePlanes; ++k) { if (v->WritebackEnable[k] == true) { @@ -3598,61 +3486,43 @@ static void CalculateRowBandwidth( static void CalculateFlipSchedule( struct display_mode_lib *mode_lib, + unsigned int k, double HostVMInefficiencyFactor, double UrgentExtraLatency, double UrgentLatency, - unsigned int GPUVMMaxPageTableLevels, - bool HostVMEnable, - unsigned int HostVMMaxNonCachedPageTableLevels, - bool GPUVMEnable, - double HostVMMinPageSize, double PDEAndMetaPTEBytesPerFrame, double MetaRowBytes, - double DPTEBytesPerRow, - double BandwidthAvailableForImmediateFlip, - unsigned int TotImmediateFlipBytes, - enum source_format_class SourcePixelFormat, - double LineTime, - double VRatio, - double VRatioChroma, - double Tno_bw, - bool DCCEnable, - unsigned int dpte_row_height, - unsigned int meta_row_height, - unsigned int dpte_row_height_chroma, - unsigned int meta_row_height_chroma, - double *DestinationLinesToRequestVMInImmediateFlip, - double *DestinationLinesToRequestRowInImmediateFlip, - double *final_flip_bw, - bool *ImmediateFlipSupportedForPipe) + double DPTEBytesPerRow) { + struct vba_vars_st *v = &mode_lib->vba; double min_row_time = 0.0; unsigned int HostVMDynamicLevelsTrips; double TimeForFetchingMetaPTEImmediateFlip; double TimeForFetchingRowInVBlankImmediateFlip; double ImmediateFlipBW; + double LineTime = v->HTotal[k] / v->PixelClock[k]; - if (GPUVMEnable == true && HostVMEnable == true) { - HostVMDynamicLevelsTrips = HostVMMaxNonCachedPageTableLevels; + if (v->GPUVMEnable == true && v->HostVMEnable == true) { + HostVMDynamicLevelsTrips = v->HostVMMaxNonCachedPageTableLevels; } else { HostVMDynamicLevelsTrips = 0; } - if (GPUVMEnable == true || DCCEnable == true) { - ImmediateFlipBW = (PDEAndMetaPTEBytesPerFrame + MetaRowBytes + DPTEBytesPerRow) * BandwidthAvailableForImmediateFlip / TotImmediateFlipBytes; + if (v->GPUVMEnable == true || v->DCCEnable[k] == true) { + ImmediateFlipBW = (PDEAndMetaPTEBytesPerFrame + MetaRowBytes + DPTEBytesPerRow) * v->BandwidthAvailableForImmediateFlip / v->TotImmediateFlipBytes; } - if (GPUVMEnable == true) { + if (v->GPUVMEnable == true) { TimeForFetchingMetaPTEImmediateFlip = dml_max3( - Tno_bw + PDEAndMetaPTEBytesPerFrame * HostVMInefficiencyFactor / ImmediateFlipBW, - UrgentExtraLatency + UrgentLatency * (GPUVMMaxPageTableLevels * (HostVMDynamicLevelsTrips + 1) - 1), + v->Tno_bw[k] + PDEAndMetaPTEBytesPerFrame * HostVMInefficiencyFactor / ImmediateFlipBW, + UrgentExtraLatency + UrgentLatency * (v->GPUVMMaxPageTableLevels * (HostVMDynamicLevelsTrips + 1) - 1), LineTime / 4.0); } else { TimeForFetchingMetaPTEImmediateFlip = 0; } - *DestinationLinesToRequestVMInImmediateFlip = dml_ceil(4.0 * (TimeForFetchingMetaPTEImmediateFlip / LineTime), 1) / 4.0; - if ((GPUVMEnable == true || DCCEnable == true)) { + v->DestinationLinesToRequestVMInImmediateFlip[k] = dml_ceil(4.0 * (TimeForFetchingMetaPTEImmediateFlip / LineTime), 1) / 4.0; + if ((v->GPUVMEnable == true || v->DCCEnable[k] == true)) { TimeForFetchingRowInVBlankImmediateFlip = dml_max3( (MetaRowBytes + DPTEBytesPerRow * HostVMInefficiencyFactor) / ImmediateFlipBW, UrgentLatency * (HostVMDynamicLevelsTrips + 1), @@ -3661,54 +3531,54 @@ static void CalculateFlipSchedule( TimeForFetchingRowInVBlankImmediateFlip = 0; } - *DestinationLinesToRequestRowInImmediateFlip = dml_ceil(4.0 * (TimeForFetchingRowInVBlankImmediateFlip / LineTime), 1) / 4.0; + v->DestinationLinesToRequestRowInImmediateFlip[k] = dml_ceil(4.0 * (TimeForFetchingRowInVBlankImmediateFlip / LineTime), 1) / 4.0; - if (GPUVMEnable == true) { - *final_flip_bw = dml_max( - PDEAndMetaPTEBytesPerFrame * HostVMInefficiencyFactor / (*DestinationLinesToRequestVMInImmediateFlip * LineTime), - (MetaRowBytes + DPTEBytesPerRow * HostVMInefficiencyFactor) / (*DestinationLinesToRequestRowInImmediateFlip * LineTime)); - } else if ((GPUVMEnable == true || DCCEnable == true)) { - *final_flip_bw = (MetaRowBytes + DPTEBytesPerRow * HostVMInefficiencyFactor) / (*DestinationLinesToRequestRowInImmediateFlip * LineTime); + if (v->GPUVMEnable == true) { + v->final_flip_bw[k] = dml_max( + PDEAndMetaPTEBytesPerFrame * HostVMInefficiencyFactor / (v->DestinationLinesToRequestVMInImmediateFlip[k] * LineTime), + (MetaRowBytes + DPTEBytesPerRow * HostVMInefficiencyFactor) / (v->DestinationLinesToRequestRowInImmediateFlip[k] * LineTime)); + } else if ((v->GPUVMEnable == true || v->DCCEnable[k] == true)) { + v->final_flip_bw[k] = (MetaRowBytes + DPTEBytesPerRow * HostVMInefficiencyFactor) / (v->DestinationLinesToRequestRowInImmediateFlip[k] * LineTime); } else { - *final_flip_bw = 0; + v->final_flip_bw[k] = 0; } - if (SourcePixelFormat == dm_420_8 || SourcePixelFormat == dm_420_10 || SourcePixelFormat == dm_rgbe_alpha) { - if (GPUVMEnable == true && DCCEnable != true) { - min_row_time = dml_min(dpte_row_height * LineTime / VRatio, dpte_row_height_chroma * LineTime / VRatioChroma); - } else if (GPUVMEnable != true && DCCEnable == true) { - min_row_time = dml_min(meta_row_height * LineTime / VRatio, meta_row_height_chroma * LineTime / VRatioChroma); + if (v->SourcePixelFormat[k] == dm_420_8 || v->SourcePixelFormat[k] == dm_420_10 || v->SourcePixelFormat[k] == dm_rgbe_alpha) { + if (v->GPUVMEnable == true && v->DCCEnable[k] != true) { + min_row_time = dml_min(v->dpte_row_height[k] * LineTime / v->VRatio[k], v->dpte_row_height_chroma[k] * LineTime / v->VRatioChroma[k]); + } else if (v->GPUVMEnable != true && v->DCCEnable[k] == true) { + min_row_time = dml_min(v->meta_row_height[k] * LineTime / v->VRatio[k], v->meta_row_height_chroma[k] * LineTime / v->VRatioChroma[k]); } else { min_row_time = dml_min4( - dpte_row_height * LineTime / VRatio, - meta_row_height * LineTime / VRatio, - dpte_row_height_chroma * LineTime / VRatioChroma, - meta_row_height_chroma * LineTime / VRatioChroma); + v->dpte_row_height[k] * LineTime / v->VRatio[k], + v->meta_row_height[k] * LineTime / v->VRatio[k], + v->dpte_row_height_chroma[k] * LineTime / v->VRatioChroma[k], + v->meta_row_height_chroma[k] * LineTime / v->VRatioChroma[k]); } } else { - if (GPUVMEnable == true && DCCEnable != true) { - min_row_time = dpte_row_height * LineTime / VRatio; - } else if (GPUVMEnable != true && DCCEnable == true) { - min_row_time = meta_row_height * LineTime / VRatio; + if (v->GPUVMEnable == true && v->DCCEnable[k] != true) { + min_row_time = v->dpte_row_height[k] * LineTime / v->VRatio[k]; + } else if (v->GPUVMEnable != true && v->DCCEnable[k] == true) { + min_row_time = v->meta_row_height[k] * LineTime / v->VRatio[k]; } else { - min_row_time = dml_min(dpte_row_height * LineTime / VRatio, meta_row_height * LineTime / VRatio); + min_row_time = dml_min(v->dpte_row_height[k] * LineTime / v->VRatio[k], v->meta_row_height[k] * LineTime / v->VRatio[k]); } } - if (*DestinationLinesToRequestVMInImmediateFlip >= 32 || *DestinationLinesToRequestRowInImmediateFlip >= 16 + if (v->DestinationLinesToRequestVMInImmediateFlip[k] >= 32 || v->DestinationLinesToRequestRowInImmediateFlip[k] >= 16 || TimeForFetchingMetaPTEImmediateFlip + 2 * TimeForFetchingRowInVBlankImmediateFlip > min_row_time) { - *ImmediateFlipSupportedForPipe = false; + v->ImmediateFlipSupportedForPipe[k] = false; } else { - *ImmediateFlipSupportedForPipe = true; + v->ImmediateFlipSupportedForPipe[k] = true; } #ifdef __DML_VBA_DEBUG__ - dml_print("DML::%s: DestinationLinesToRequestVMInImmediateFlip = %f\n", __func__, *DestinationLinesToRequestVMInImmediateFlip); - dml_print("DML::%s: DestinationLinesToRequestRowInImmediateFlip = %f\n", __func__, *DestinationLinesToRequestRowInImmediateFlip); + dml_print("DML::%s: DestinationLinesToRequestVMInImmediateFlip = %f\n", __func__, v->DestinationLinesToRequestVMInImmediateFlip[k]); + dml_print("DML::%s: DestinationLinesToRequestRowInImmediateFlip = %f\n", __func__, v->DestinationLinesToRequestRowInImmediateFlip[k]); dml_print("DML::%s: TimeForFetchingMetaPTEImmediateFlip = %f\n", __func__, TimeForFetchingMetaPTEImmediateFlip); dml_print("DML::%s: TimeForFetchingRowInVBlankImmediateFlip = %f\n", __func__, TimeForFetchingRowInVBlankImmediateFlip); dml_print("DML::%s: min_row_time = %f\n", __func__, min_row_time); - dml_print("DML::%s: ImmediateFlipSupportedForPipe = %d\n", __func__, *ImmediateFlipSupportedForPipe); + dml_print("DML::%s: ImmediateFlipSupportedForPipe = %d\n", __func__, v->ImmediateFlipSupportedForPipe[k]); #endif } @@ -5300,33 +5170,13 @@ void dml31_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l for (k = 0; k < v->NumberOfActivePlanes; k++) { CalculateFlipSchedule( mode_lib, + k, HostVMInefficiencyFactor, v->ExtraLatency, v->UrgLatency[i], - v->GPUVMMaxPageTableLevels, - v->HostVMEnable, - v->HostVMMaxNonCachedPageTableLevels, - v->GPUVMEnable, - v->HostVMMinPageSize, v->PDEAndMetaPTEBytesPerFrame[i][j][k], v->MetaRowBytes[i][j][k], - v->DPTEBytesPerRow[i][j][k], - v->BandwidthAvailableForImmediateFlip, - v->TotImmediateFlipBytes, - v->SourcePixelFormat[k], - v->HTotal[k] / v->PixelClock[k], - v->VRatio[k], - v->VRatioChroma[k], - v->Tno_bw[k], - v->DCCEnable[k], - v->dpte_row_height[k], - v->meta_row_height[k], - v->dpte_row_height_chroma[k], - v->meta_row_height_chroma[k], - &v->DestinationLinesToRequestVMInImmediateFlip[k], - &v->DestinationLinesToRequestRowInImmediateFlip[k], - &v->final_flip_bw[k], - &v->ImmediateFlipSupportedForPipe[k]); + v->DPTEBytesPerRow[i][j][k]); } v->total_dcn_read_bw_with_flip = 0.0; for (k = 0; k < v->NumberOfActivePlanes; k++) { @@ -5384,64 +5234,28 @@ void dml31_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l CalculateWatermarksAndDRAMSpeedChangeSupport( mode_lib, v->PrefetchModePerState[i][j], - v->NumberOfActivePlanes, - v->MaxLineBufferLines, - v->LineBufferSize, - v->WritebackInterfaceBufferSize, v->DCFCLKState[i][j], v->ReturnBWPerState[i][j], - v->SynchronizedVBlank, - v->dpte_group_bytes, - v->MetaChunkSize, v->UrgLatency[i], v->ExtraLatency, - v->WritebackLatency, - v->WritebackChunkSize, v->SOCCLKPerState[i], - v->DRAMClockChangeLatency, - v->SRExitTime, - v->SREnterPlusExitTime, - v->SRExitZ8Time, - v->SREnterPlusExitZ8Time, v->ProjectedDCFCLKDeepSleep[i][j], v->DETBufferSizeYThisState, v->DETBufferSizeCThisState, v->SwathHeightYThisState, v->SwathHeightCThisState, - v->LBBitPerPixel, v->SwathWidthYThisState, v->SwathWidthCThisState, - v->HRatio, - v->HRatioChroma, - v->vtaps, - v->VTAPsChroma, - v->VRatio, - v->VRatioChroma, - v->HTotal, - v->PixelClock, - v->BlendingAndTiming, v->NoOfDPPThisState, v->BytePerPixelInDETY, v->BytePerPixelInDETC, - v->DSTXAfterScaler, - v->DSTYAfterScaler, - v->WritebackEnable, - v->WritebackPixelFormat, - v->WritebackDestinationWidth, - v->WritebackDestinationHeight, - v->WritebackSourceHeight, UnboundedRequestEnabledThisState, CompressedBufferSizeInkByteThisState, &v->DRAMClockChangeSupport[i][j], - &v->UrgentWatermark, - &v->WritebackUrgentWatermark, - &v->DRAMClockChangeWatermark, - &v->WritebackDRAMClockChangeWatermark, - &dummy, &dummy, &dummy, &dummy, - &v->MinActiveDRAMClockChangeLatencySupported); + &dummy); } } @@ -5566,64 +5380,28 @@ void dml31_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l static void CalculateWatermarksAndDRAMSpeedChangeSupport( struct display_mode_lib *mode_lib, unsigned int PrefetchMode, - unsigned int NumberOfActivePlanes, - unsigned int MaxLineBufferLines, - unsigned int LineBufferSize, - unsigned int WritebackInterfaceBufferSize, double DCFCLK, double ReturnBW, - bool SynchronizedVBlank, - unsigned int dpte_group_bytes[], - unsigned int MetaChunkSize, double UrgentLatency, double ExtraLatency, - double WritebackLatency, - double WritebackChunkSize, double SOCCLK, - double DRAMClockChangeLatency, - double SRExitTime, - double SREnterPlusExitTime, - double SRExitZ8Time, - double SREnterPlusExitZ8Time, double DCFCLKDeepSleep, unsigned int DETBufferSizeY[], unsigned int DETBufferSizeC[], unsigned int SwathHeightY[], unsigned int SwathHeightC[], - unsigned int LBBitPerPixel[], double SwathWidthY[], double SwathWidthC[], - double HRatio[], - double HRatioChroma[], - unsigned int vtaps[], - unsigned int VTAPsChroma[], - double VRatio[], - double VRatioChroma[], - unsigned int HTotal[], - double PixelClock[], - unsigned int BlendingAndTiming[], unsigned int DPPPerPlane[], double BytePerPixelDETY[], double BytePerPixelDETC[], - double DSTXAfterScaler[], - double DSTYAfterScaler[], - bool WritebackEnable[], - enum source_format_class WritebackPixelFormat[], - double WritebackDestinationWidth[], - double WritebackDestinationHeight[], - double WritebackSourceHeight[], bool UnboundedRequestEnabled, int unsigned CompressedBufferSizeInkByte, enum clock_change_support *DRAMClockChangeSupport, - double *UrgentWatermark, - double *WritebackUrgentWatermark, - double *DRAMClockChangeWatermark, - double *WritebackDRAMClockChangeWatermark, double *StutterExitWatermark, double *StutterEnterPlusExitWatermark, double *Z8StutterExitWatermark, - double *Z8StutterEnterPlusExitWatermark, - double *MinActiveDRAMClockChangeLatencySupported) + double *Z8StutterEnterPlusExitWatermark) { struct vba_vars_st *v = &mode_lib->vba; double EffectiveLBLatencyHidingY; @@ -5643,103 +5421,103 @@ static void CalculateWatermarksAndDRAMSpeedChangeSupport( double TotalPixelBW = 0.0; int k, j; - *UrgentWatermark = UrgentLatency + ExtraLatency; + v->UrgentWatermark = UrgentLatency + ExtraLatency; #ifdef __DML_VBA_DEBUG__ dml_print("DML::%s: UrgentLatency = %f\n", __func__, UrgentLatency); dml_print("DML::%s: ExtraLatency = %f\n", __func__, ExtraLatency); - dml_print("DML::%s: UrgentWatermark = %f\n", __func__, *UrgentWatermark); + dml_print("DML::%s: UrgentWatermark = %f\n", __func__, v->UrgentWatermark); #endif - *DRAMClockChangeWatermark = DRAMClockChangeLatency + *UrgentWatermark; + v->DRAMClockChangeWatermark = v->DRAMClockChangeLatency + v->UrgentWatermark; #ifdef __DML_VBA_DEBUG__ - dml_print("DML::%s: DRAMClockChangeLatency = %f\n", __func__, DRAMClockChangeLatency); - dml_print("DML::%s: DRAMClockChangeWatermark = %f\n", __func__, *DRAMClockChangeWatermark); + dml_print("DML::%s: v->DRAMClockChangeLatency = %f\n", __func__, v->DRAMClockChangeLatency); + dml_print("DML::%s: DRAMClockChangeWatermark = %f\n", __func__, v->DRAMClockChangeWatermark); #endif v->TotalActiveWriteback = 0; - for (k = 0; k < NumberOfActivePlanes; ++k) { - if (WritebackEnable[k] == true) { + for (k = 0; k < v->NumberOfActivePlanes; ++k) { + if (v->WritebackEnable[k] == true) { v->TotalActiveWriteback = v->TotalActiveWriteback + 1; } } if (v->TotalActiveWriteback <= 1) { - *WritebackUrgentWatermark = WritebackLatency; + v->WritebackUrgentWatermark = v->WritebackLatency; } else { - *WritebackUrgentWatermark = WritebackLatency + WritebackChunkSize * 1024.0 / 32.0 / SOCCLK; + v->WritebackUrgentWatermark = v->WritebackLatency + v->WritebackChunkSize * 1024.0 / 32.0 / SOCCLK; } if (v->TotalActiveWriteback <= 1) { - *WritebackDRAMClockChangeWatermark = DRAMClockChangeLatency + WritebackLatency; + v->WritebackDRAMClockChangeWatermark = v->DRAMClockChangeLatency + v->WritebackLatency; } else { - *WritebackDRAMClockChangeWatermark = DRAMClockChangeLatency + WritebackLatency + WritebackChunkSize * 1024.0 / 32.0 / SOCCLK; + v->WritebackDRAMClockChangeWatermark = v->DRAMClockChangeLatency + v->WritebackLatency + v->WritebackChunkSize * 1024.0 / 32.0 / SOCCLK; } - for (k = 0; k < NumberOfActivePlanes; ++k) { + for (k = 0; k < v->NumberOfActivePlanes; ++k) { TotalPixelBW = TotalPixelBW - + DPPPerPlane[k] * (SwathWidthY[k] * BytePerPixelDETY[k] * VRatio[k] + SwathWidthC[k] * BytePerPixelDETC[k] * VRatioChroma[k]) - / (HTotal[k] / PixelClock[k]); + + DPPPerPlane[k] * (SwathWidthY[k] * BytePerPixelDETY[k] * v->VRatio[k] + SwathWidthC[k] * BytePerPixelDETC[k] * v->VRatioChroma[k]) + / (v->HTotal[k] / v->PixelClock[k]); } - for (k = 0; k < NumberOfActivePlanes; ++k) { + for (k = 0; k < v->NumberOfActivePlanes; ++k) { double EffectiveDETBufferSizeY = DETBufferSizeY[k]; v->LBLatencyHidingSourceLinesY = dml_min( - (double) MaxLineBufferLines, - dml_floor(LineBufferSize / LBBitPerPixel[k] / (SwathWidthY[k] / dml_max(HRatio[k], 1.0)), 1)) - (vtaps[k] - 1); + (double) v->MaxLineBufferLines, + dml_floor(v->LineBufferSize / v->LBBitPerPixel[k] / (SwathWidthY[k] / dml_max(v->HRatio[k], 1.0)), 1)) - (v->vtaps[k] - 1); v->LBLatencyHidingSourceLinesC = dml_min( - (double) MaxLineBufferLines, - dml_floor(LineBufferSize / LBBitPerPixel[k] / (SwathWidthC[k] / dml_max(HRatioChroma[k], 1.0)), 1)) - (VTAPsChroma[k] - 1); + (double) v->MaxLineBufferLines, + dml_floor(v->LineBufferSize / v->LBBitPerPixel[k] / (SwathWidthC[k] / dml_max(v->HRatioChroma[k], 1.0)), 1)) - (v->VTAPsChroma[k] - 1); - EffectiveLBLatencyHidingY = v->LBLatencyHidingSourceLinesY / VRatio[k] * (HTotal[k] / PixelClock[k]); + EffectiveLBLatencyHidingY = v->LBLatencyHidingSourceLinesY / v->VRatio[k] * (v->HTotal[k] / v->PixelClock[k]); - EffectiveLBLatencyHidingC = v->LBLatencyHidingSourceLinesC / VRatioChroma[k] * (HTotal[k] / PixelClock[k]); + EffectiveLBLatencyHidingC = v->LBLatencyHidingSourceLinesC / v->VRatioChroma[k] * (v->HTotal[k] / v->PixelClock[k]); if (UnboundedRequestEnabled) { EffectiveDETBufferSizeY = EffectiveDETBufferSizeY - + CompressedBufferSizeInkByte * 1024 * SwathWidthY[k] * BytePerPixelDETY[k] * VRatio[k] / (HTotal[k] / PixelClock[k]) / TotalPixelBW; + + CompressedBufferSizeInkByte * 1024 * SwathWidthY[k] * BytePerPixelDETY[k] * v->VRatio[k] / (v->HTotal[k] / v->PixelClock[k]) / TotalPixelBW; } LinesInDETY[k] = (double) EffectiveDETBufferSizeY / BytePerPixelDETY[k] / SwathWidthY[k]; LinesInDETYRoundedDownToSwath[k] = dml_floor(LinesInDETY[k], SwathHeightY[k]); - FullDETBufferingTimeY = LinesInDETYRoundedDownToSwath[k] * (HTotal[k] / PixelClock[k]) / VRatio[k]; + FullDETBufferingTimeY = LinesInDETYRoundedDownToSwath[k] * (v->HTotal[k] / v->PixelClock[k]) / v->VRatio[k]; if (BytePerPixelDETC[k] > 0) { LinesInDETC = v->DETBufferSizeC[k] / BytePerPixelDETC[k] / SwathWidthC[k]; LinesInDETCRoundedDownToSwath = dml_floor(LinesInDETC, SwathHeightC[k]); - FullDETBufferingTimeC = LinesInDETCRoundedDownToSwath * (HTotal[k] / PixelClock[k]) / VRatioChroma[k]; + FullDETBufferingTimeC = LinesInDETCRoundedDownToSwath * (v->HTotal[k] / v->PixelClock[k]) / v->VRatioChroma[k]; } else { LinesInDETC = 0; FullDETBufferingTimeC = 999999; } ActiveDRAMClockChangeLatencyMarginY = EffectiveLBLatencyHidingY + FullDETBufferingTimeY - - ((double) DSTXAfterScaler[k] / HTotal[k] + DSTYAfterScaler[k]) * HTotal[k] / PixelClock[k] - *UrgentWatermark - *DRAMClockChangeWatermark; + - ((double) v->DSTXAfterScaler[k] / v->HTotal[k] + v->DSTYAfterScaler[k]) * v->HTotal[k] / v->PixelClock[k] - v->UrgentWatermark - v->DRAMClockChangeWatermark; - if (NumberOfActivePlanes > 1) { + if (v->NumberOfActivePlanes > 1) { ActiveDRAMClockChangeLatencyMarginY = ActiveDRAMClockChangeLatencyMarginY - - (1 - 1.0 / NumberOfActivePlanes) * SwathHeightY[k] * HTotal[k] / PixelClock[k] / VRatio[k]; + - (1 - 1.0 / v->NumberOfActivePlanes) * SwathHeightY[k] * v->HTotal[k] / v->PixelClock[k] / v->VRatio[k]; } if (BytePerPixelDETC[k] > 0) { ActiveDRAMClockChangeLatencyMarginC = EffectiveLBLatencyHidingC + FullDETBufferingTimeC - - ((double) DSTXAfterScaler[k] / HTotal[k] + DSTYAfterScaler[k]) * HTotal[k] / PixelClock[k] - *UrgentWatermark - *DRAMClockChangeWatermark; + - ((double) v->DSTXAfterScaler[k] / v->HTotal[k] + v->DSTYAfterScaler[k]) * v->HTotal[k] / v->PixelClock[k] - v->UrgentWatermark - v->DRAMClockChangeWatermark; - if (NumberOfActivePlanes > 1) { + if (v->NumberOfActivePlanes > 1) { ActiveDRAMClockChangeLatencyMarginC = ActiveDRAMClockChangeLatencyMarginC - - (1 - 1.0 / NumberOfActivePlanes) * SwathHeightC[k] * HTotal[k] / PixelClock[k] / VRatioChroma[k]; + - (1 - 1.0 / v->NumberOfActivePlanes) * SwathHeightC[k] * v->HTotal[k] / v->PixelClock[k] / v->VRatioChroma[k]; } v->ActiveDRAMClockChangeLatencyMargin[k] = dml_min(ActiveDRAMClockChangeLatencyMarginY, ActiveDRAMClockChangeLatencyMarginC); } else { v->ActiveDRAMClockChangeLatencyMargin[k] = ActiveDRAMClockChangeLatencyMarginY; } - if (WritebackEnable[k] == true) { - WritebackDRAMClockChangeLatencyHiding = WritebackInterfaceBufferSize * 1024 - / (WritebackDestinationWidth[k] * WritebackDestinationHeight[k] / (WritebackSourceHeight[k] * HTotal[k] / PixelClock[k]) * 4); - if (WritebackPixelFormat[k] == dm_444_64) { + if (v->WritebackEnable[k] == true) { + WritebackDRAMClockChangeLatencyHiding = v->WritebackInterfaceBufferSize * 1024 + / (v->WritebackDestinationWidth[k] * v->WritebackDestinationHeight[k] / (v->WritebackSourceHeight[k] * v->HTotal[k] / v->PixelClock[k]) * 4); + if (v->WritebackPixelFormat[k] == dm_444_64) { WritebackDRAMClockChangeLatencyHiding = WritebackDRAMClockChangeLatencyHiding / 2; } WritebackDRAMClockChangeLatencyMargin = WritebackDRAMClockChangeLatencyHiding - v->WritebackDRAMClockChangeWatermark; @@ -5749,14 +5527,14 @@ static void CalculateWatermarksAndDRAMSpeedChangeSupport( v->MinActiveDRAMClockChangeMargin = 999999; PlaneWithMinActiveDRAMClockChangeMargin = 0; - for (k = 0; k < NumberOfActivePlanes; ++k) { + for (k = 0; k < v->NumberOfActivePlanes; ++k) { if (v->ActiveDRAMClockChangeLatencyMargin[k] < v->MinActiveDRAMClockChangeMargin) { v->MinActiveDRAMClockChangeMargin = v->ActiveDRAMClockChangeLatencyMargin[k]; - if (BlendingAndTiming[k] == k) { + if (v->BlendingAndTiming[k] == k) { PlaneWithMinActiveDRAMClockChangeMargin = k; } else { - for (j = 0; j < NumberOfActivePlanes; ++j) { - if (BlendingAndTiming[k] == j) { + for (j = 0; j < v->NumberOfActivePlanes; ++j) { + if (v->BlendingAndTiming[k] == j) { PlaneWithMinActiveDRAMClockChangeMargin = j; } } @@ -5764,11 +5542,11 @@ static void CalculateWatermarksAndDRAMSpeedChangeSupport( } } - *MinActiveDRAMClockChangeLatencySupported = v->MinActiveDRAMClockChangeMargin + DRAMClockChangeLatency; + v->MinActiveDRAMClockChangeLatencySupported = v->MinActiveDRAMClockChangeMargin + v->DRAMClockChangeLatency ; SecondMinActiveDRAMClockChangeMarginOneDisplayInVBLank = 999999; - for (k = 0; k < NumberOfActivePlanes; ++k) { - if (!((k == PlaneWithMinActiveDRAMClockChangeMargin) && (BlendingAndTiming[k] == k)) && !(BlendingAndTiming[k] == PlaneWithMinActiveDRAMClockChangeMargin) + for (k = 0; k < v->NumberOfActivePlanes; ++k) { + if (!((k == PlaneWithMinActiveDRAMClockChangeMargin) && (v->BlendingAndTiming[k] == k)) && !(v->BlendingAndTiming[k] == PlaneWithMinActiveDRAMClockChangeMargin) && v->ActiveDRAMClockChangeLatencyMargin[k] < SecondMinActiveDRAMClockChangeMarginOneDisplayInVBLank) { SecondMinActiveDRAMClockChangeMarginOneDisplayInVBLank = v->ActiveDRAMClockChangeLatencyMargin[k]; } @@ -5776,25 +5554,25 @@ static void CalculateWatermarksAndDRAMSpeedChangeSupport( v->TotalNumberOfActiveOTG = 0; - for (k = 0; k < NumberOfActivePlanes; ++k) { - if (BlendingAndTiming[k] == k) { + for (k = 0; k < v->NumberOfActivePlanes; ++k) { + if (v->BlendingAndTiming[k] == k) { v->TotalNumberOfActiveOTG = v->TotalNumberOfActiveOTG + 1; } } if (v->MinActiveDRAMClockChangeMargin > 0 && PrefetchMode == 0) { *DRAMClockChangeSupport = dm_dram_clock_change_vactive; - } else if ((SynchronizedVBlank == true || v->TotalNumberOfActiveOTG == 1 + } else if ((v->SynchronizedVBlank == true || v->TotalNumberOfActiveOTG == 1 || SecondMinActiveDRAMClockChangeMarginOneDisplayInVBLank > 0) && PrefetchMode == 0) { *DRAMClockChangeSupport = dm_dram_clock_change_vblank; } else { *DRAMClockChangeSupport = dm_dram_clock_change_unsupported; } - *StutterExitWatermark = SRExitTime + ExtraLatency + 10 / DCFCLKDeepSleep; - *StutterEnterPlusExitWatermark = (SREnterPlusExitTime + ExtraLatency + 10 / DCFCLKDeepSleep); - *Z8StutterExitWatermark = SRExitZ8Time + ExtraLatency + 10 / DCFCLKDeepSleep; - *Z8StutterEnterPlusExitWatermark = SREnterPlusExitZ8Time + ExtraLatency + 10 / DCFCLKDeepSleep; + *StutterExitWatermark = v->SRExitTime + ExtraLatency + 10 / DCFCLKDeepSleep; + *StutterEnterPlusExitWatermark = (v->SREnterPlusExitTime + ExtraLatency + 10 / DCFCLKDeepSleep); + *Z8StutterExitWatermark = v->SRExitZ8Time + ExtraLatency + 10 / DCFCLKDeepSleep; + *Z8StutterEnterPlusExitWatermark = v->SREnterPlusExitZ8Time + ExtraLatency + 10 / DCFCLKDeepSleep; #ifdef __DML_VBA_DEBUG__ dml_print("DML::%s: StutterExitWatermark = %f\n", __func__, *StutterExitWatermark); diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn314/dcn314_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn314/dcn314_fpu.c index 34a5d0f87b5f..4bb3b31ea7e0 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn314/dcn314_fpu.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn314/dcn314_fpu.c @@ -194,6 +194,9 @@ void dcn314_update_bw_bounding_box_fpu(struct dc *dc, struct clk_bw_params *bw_p dcn3_14_ip.max_num_otg = dc->res_pool->res_cap->num_timing_generator; dcn3_14_ip.max_num_dpp = dc->res_pool->pipe_count; + if (bw_params->dram_channel_width_bytes > 0) + dcn3_14_soc.dram_channel_width_bytes = bw_params->dram_channel_width_bytes; + if (bw_params->num_channels > 0) dcn3_14_soc.num_chans = bw_params->num_channels; @@ -262,7 +265,7 @@ void dcn314_update_bw_bounding_box_fpu(struct dc *dc, struct clk_bw_params *bw_p } if (!IS_FPGA_MAXIMUS_DC(dc->ctx->dce_environment)) - dml_init_instance(&dc->dml, &dcn3_14_soc, &dcn3_14_ip, DML_PROJECT_DCN31); + dml_init_instance(&dc->dml, &dcn3_14_soc, &dcn3_14_ip, DML_PROJECT_DCN314); else dml_init_instance(&dc->dml, &dcn3_14_soc, &dcn3_14_ip, DML_PROJECT_DCN31_FPGA); } diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn314/display_mode_vba_314.c b/drivers/gpu/drm/amd/display/dc/dml/dcn314/display_mode_vba_314.c index fc4d7474c111..01f3fad172f3 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn314/display_mode_vba_314.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn314/display_mode_vba_314.c @@ -61,7 +61,7 @@ // fudge factor for min dcfclk calclation #define __DML_MIN_DCFCLK_FACTOR__ 1.15 -struct { +typedef struct { double DPPCLK; double DISPCLK; double PixelClock; @@ -1599,7 +1599,7 @@ static void CalculateDCCConfiguration( int segment_order_vert_contiguous_luma; int segment_order_vert_contiguous_chroma; - enum { + typedef enum { REQ_256Bytes, REQ_128BytesNonContiguous, REQ_128BytesContiguous, REQ_NA } RequestType; RequestType RequestLuma; @@ -4071,9 +4071,7 @@ void dml314_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_ v->SourceFormatPixelAndScanSupport = true; for (k = 0; k < v->NumberOfActivePlanes; k++) { - if ((v->SurfaceTiling[k] == dm_sw_linear && (!(v->SourceScan[k] != dm_vert) || v->DCCEnable[k] == true)) - || ((v->SurfaceTiling[k] == dm_sw_64kb_d || v->SurfaceTiling[k] == dm_sw_64kb_d_t - || v->SurfaceTiling[k] == dm_sw_64kb_d_x) && !(v->SourcePixelFormat[k] == dm_444_64))) { + if (v->SurfaceTiling[k] == dm_sw_linear && (!(v->SourceScan[k] != dm_vert) || v->DCCEnable[k] == true)) { v->SourceFormatPixelAndScanSupport = false; } } @@ -7157,12 +7155,13 @@ static double CalculateExtraLatencyBytes( HostVMDynamicLevels = dml_max(0, (int) HostVMMaxNonCachedPageTableLevels - 1); else HostVMDynamicLevels = dml_max(0, (int) HostVMMaxNonCachedPageTableLevels - 2); - else + } else { HostVMDynamicLevels = 0; + } ret = ReorderingBytes + (TotalNumberOfActiveDPP * PixelChunkSizeInKByte + TotalNumberOfDCCActiveDPP * MetaChunkSize) * 1024.0; - if (GPUVMEnable == true) + if (GPUVMEnable == true) { for (k = 0; k < NumberOfActivePlanes; ++k) ret = ret + NumberOfDPP[k] * dpte_group_bytes[k] * (1 + 8 * HostVMDynamicLevels) * HostVMInefficiencyFactor; } diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_32.c b/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_32.c index cb2025771646..9a60f27eceaa 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_32.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_32.c @@ -755,30 +755,18 @@ static void DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerforman v->dummy_vars.DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerformanceCalculation.myPipe.BytePerPixelY = v->BytePerPixelY[k]; v->dummy_vars.DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerformanceCalculation.myPipe.BytePerPixelC = v->BytePerPixelC[k]; v->dummy_vars.DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerformanceCalculation.myPipe.ProgressiveToInterlaceUnitInOPP = mode_lib->vba.ProgressiveToInterlaceUnitInOPP; - v->ErrorResult[k] = dml32_CalculatePrefetchSchedule(v->dummy_vars.DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerformanceCalculation.HostVMInefficiencyFactor, - &v->dummy_vars.DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerformanceCalculation.myPipe, v->DSCDelay[k], - mode_lib->vba.DPPCLKDelaySubtotal + mode_lib->vba.DPPCLKDelayCNVCFormater, - mode_lib->vba.DPPCLKDelaySCL, - mode_lib->vba.DPPCLKDelaySCLLBOnly, - mode_lib->vba.DPPCLKDelayCNVCCursor, - mode_lib->vba.DISPCLKDelaySubtotal, - (unsigned int) (v->SwathWidthY[k] / mode_lib->vba.HRatio[k]), - mode_lib->vba.OutputFormat[k], - mode_lib->vba.MaxInterDCNTileRepeaters, + v->ErrorResult[k] = dml32_CalculatePrefetchSchedule( + v, + k, + v->dummy_vars.DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerformanceCalculation.HostVMInefficiencyFactor, + &v->dummy_vars.DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerformanceCalculation.myPipe, + v->DSCDelay[k], + (unsigned int) (v->SwathWidthY[k] / v->HRatio[k]), dml_min(v->VStartupLines, v->MaxVStartupLines[k]), v->MaxVStartupLines[k], - mode_lib->vba.GPUVMMaxPageTableLevels, - mode_lib->vba.GPUVMEnable, - mode_lib->vba.HostVMEnable, - mode_lib->vba.HostVMMaxNonCachedPageTableLevels, - mode_lib->vba.HostVMMinPageSize, - mode_lib->vba.DynamicMetadataEnable[k], - mode_lib->vba.DynamicMetadataVMEnabled, - mode_lib->vba.DynamicMetadataLinesBeforeActiveRequired[k], - mode_lib->vba.DynamicMetadataTransmittedBytes[k], v->UrgentLatency, v->UrgentExtraLatency, - mode_lib->vba.TCalc, + v->TCalc, v->PDEAndMetaPTEBytesFrame[k], v->MetaRowByte[k], v->PixelPTEBytesPerRow[k], @@ -792,8 +780,8 @@ static void DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerforman v->MaxNumSwathC[k], v->swath_width_luma_ub[k], v->swath_width_chroma_ub[k], - mode_lib->vba.SwathHeightY[k], - mode_lib->vba.SwathHeightC[k], + v->SwathHeightY[k], + v->SwathHeightC[k], TWait, /* Output */ &v->DSTXAfterScaler[k], @@ -1163,58 +1151,28 @@ static void DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerforman v->dummy_vars.DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerformanceCalculation.mmSOCParameters.SMNLatency = mode_lib->vba.SMNLatency; dml32_CalculateWatermarksMALLUseAndDRAMSpeedChangeSupport( - mode_lib->vba.USRRetrainingRequiredFinal, - mode_lib->vba.UsesMALLForPStateChange, - mode_lib->vba.PrefetchModePerState[mode_lib->vba.VoltageLevel][mode_lib->vba.maxMpcComb], - mode_lib->vba.NumberOfActiveSurfaces, - mode_lib->vba.MaxLineBufferLines, - mode_lib->vba.LineBufferSizeFinal, - mode_lib->vba.WritebackInterfaceBufferSize, - mode_lib->vba.DCFCLK, - mode_lib->vba.ReturnBW, - mode_lib->vba.SynchronizeTimingsFinal, - mode_lib->vba.SynchronizeDRRDisplaysForUCLKPStateChangeFinal, - mode_lib->vba.DRRDisplay, - v->dpte_group_bytes, - v->meta_row_height, - v->meta_row_height_chroma, + v, + v->PrefetchModePerState[v->VoltageLevel][v->maxMpcComb], + v->DCFCLK, + v->ReturnBW, v->dummy_vars.DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerformanceCalculation.mmSOCParameters, - mode_lib->vba.WritebackChunkSize, - mode_lib->vba.SOCCLK, + v->SOCCLK, v->DCFCLKDeepSleep, - mode_lib->vba.DETBufferSizeY, - mode_lib->vba.DETBufferSizeC, - mode_lib->vba.SwathHeightY, - mode_lib->vba.SwathHeightC, - mode_lib->vba.LBBitPerPixel, + v->DETBufferSizeY, + v->DETBufferSizeC, + v->SwathHeightY, + v->SwathHeightC, v->SwathWidthY, v->SwathWidthC, - mode_lib->vba.HRatio, - mode_lib->vba.HRatioChroma, - mode_lib->vba.vtaps, - mode_lib->vba.VTAPsChroma, - mode_lib->vba.VRatio, - mode_lib->vba.VRatioChroma, - mode_lib->vba.HTotal, - mode_lib->vba.VTotal, - mode_lib->vba.VActive, - mode_lib->vba.PixelClock, - mode_lib->vba.BlendingAndTiming, - mode_lib->vba.DPPPerPlane, + v->DPPPerPlane, v->BytePerPixelDETY, v->BytePerPixelDETC, v->DSTXAfterScaler, v->DSTYAfterScaler, - mode_lib->vba.WritebackEnable, - mode_lib->vba.WritebackPixelFormat, - mode_lib->vba.WritebackDestinationWidth, - mode_lib->vba.WritebackDestinationHeight, - mode_lib->vba.WritebackSourceHeight, v->UnboundedRequestEnabled, v->CompressedBufferSizeInkByte, /* Output */ - &v->Watermark, &v->dummy_vars.DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerformanceCalculation.dummy_dramchange_support, v->MaxActiveDRAMClockChangeLatencySupported, v->SubViewportLinesNeededInMALL, @@ -1806,10 +1764,10 @@ void dml32_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l &mode_lib->vba.Read256BlockHeightC[k], &mode_lib->vba.Read256BlockWidthY[k], &mode_lib->vba.Read256BlockWidthC[k], - &mode_lib->vba.MicroTileHeightY[k], - &mode_lib->vba.MicroTileHeightC[k], - &mode_lib->vba.MicroTileWidthY[k], - &mode_lib->vba.MicroTileWidthC[k]); + &mode_lib->vba.MacroTileHeightY[k], + &mode_lib->vba.MacroTileHeightC[k], + &mode_lib->vba.MacroTileWidthY[k], + &mode_lib->vba.MacroTileWidthC[k]); } /*Bandwidth Support Check*/ @@ -2659,10 +2617,10 @@ void dml32_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l mode_lib->vba.Read256BlockWidthC, mode_lib->vba.Read256BlockHeightY, mode_lib->vba.Read256BlockHeightC, - mode_lib->vba.MicroTileWidthY, - mode_lib->vba.MicroTileWidthC, - mode_lib->vba.MicroTileHeightY, - mode_lib->vba.MicroTileHeightC, + mode_lib->vba.MacroTileWidthY, + mode_lib->vba.MacroTileWidthC, + mode_lib->vba.MacroTileHeightY, + mode_lib->vba.MacroTileHeightC, /* Output */ mode_lib->vba.SurfaceSizeInMALL, @@ -2709,10 +2667,10 @@ void dml32_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l v->dummy_vars.dml32_ModeSupportAndSystemConfigurationFull.SurfParameters[k].BlockHeight256BytesY = mode_lib->vba.Read256BlockHeightY[k]; v->dummy_vars.dml32_ModeSupportAndSystemConfigurationFull.SurfParameters[k].BlockWidth256BytesC = mode_lib->vba.Read256BlockWidthC[k]; v->dummy_vars.dml32_ModeSupportAndSystemConfigurationFull.SurfParameters[k].BlockHeight256BytesC = mode_lib->vba.Read256BlockHeightC[k]; - v->dummy_vars.dml32_ModeSupportAndSystemConfigurationFull.SurfParameters[k].BlockWidthY = mode_lib->vba.MicroTileWidthY[k]; - v->dummy_vars.dml32_ModeSupportAndSystemConfigurationFull.SurfParameters[k].BlockHeightY = mode_lib->vba.MicroTileHeightY[k]; - v->dummy_vars.dml32_ModeSupportAndSystemConfigurationFull.SurfParameters[k].BlockWidthC = mode_lib->vba.MicroTileWidthC[k]; - v->dummy_vars.dml32_ModeSupportAndSystemConfigurationFull.SurfParameters[k].BlockHeightC = mode_lib->vba.MicroTileHeightC[k]; + v->dummy_vars.dml32_ModeSupportAndSystemConfigurationFull.SurfParameters[k].BlockWidthY = mode_lib->vba.MacroTileWidthY[k]; + v->dummy_vars.dml32_ModeSupportAndSystemConfigurationFull.SurfParameters[k].BlockHeightY = mode_lib->vba.MacroTileHeightY[k]; + v->dummy_vars.dml32_ModeSupportAndSystemConfigurationFull.SurfParameters[k].BlockWidthC = mode_lib->vba.MacroTileWidthC[k]; + v->dummy_vars.dml32_ModeSupportAndSystemConfigurationFull.SurfParameters[k].BlockHeightC = mode_lib->vba.MacroTileHeightC[k]; v->dummy_vars.dml32_ModeSupportAndSystemConfigurationFull.SurfParameters[k].InterlaceEnable = mode_lib->vba.Interlace[k]; v->dummy_vars.dml32_ModeSupportAndSystemConfigurationFull.SurfParameters[k].HTotal = mode_lib->vba.HTotal[k]; v->dummy_vars.dml32_ModeSupportAndSystemConfigurationFull.SurfParameters[k].DCCEnable = mode_lib->vba.DCCEnable[k]; @@ -3258,63 +3216,47 @@ void dml32_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l mode_lib->vba.NoTimeForPrefetch[i][j][k] = dml32_CalculatePrefetchSchedule( + v, + k, v->dummy_vars.dml32_ModeSupportAndSystemConfigurationFull.HostVMInefficiencyFactor, &v->dummy_vars.dml32_ModeSupportAndSystemConfigurationFull.myPipe, - mode_lib->vba.DSCDelayPerState[i][k], - mode_lib->vba.DPPCLKDelaySubtotal + - mode_lib->vba.DPPCLKDelayCNVCFormater, - mode_lib->vba.DPPCLKDelaySCL, - mode_lib->vba.DPPCLKDelaySCLLBOnly, - mode_lib->vba.DPPCLKDelayCNVCCursor, - mode_lib->vba.DISPCLKDelaySubtotal, - mode_lib->vba.SwathWidthYThisState[k] / - mode_lib->vba.HRatio[k], - mode_lib->vba.OutputFormat[k], - mode_lib->vba.MaxInterDCNTileRepeaters, - dml_min(mode_lib->vba.MaxVStartup, - mode_lib->vba.MaximumVStartup[i][j][k]), - mode_lib->vba.MaximumVStartup[i][j][k], - mode_lib->vba.GPUVMMaxPageTableLevels, - mode_lib->vba.GPUVMEnable, mode_lib->vba.HostVMEnable, - mode_lib->vba.HostVMMaxNonCachedPageTableLevels, - mode_lib->vba.HostVMMinPageSize, - mode_lib->vba.DynamicMetadataEnable[k], - mode_lib->vba.DynamicMetadataVMEnabled, - mode_lib->vba.DynamicMetadataLinesBeforeActiveRequired[k], - mode_lib->vba.DynamicMetadataTransmittedBytes[k], - mode_lib->vba.UrgLatency[i], - mode_lib->vba.ExtraLatency, - mode_lib->vba.TimeCalc, - mode_lib->vba.PDEAndMetaPTEBytesPerFrame[i][j][k], - mode_lib->vba.MetaRowBytes[i][j][k], - mode_lib->vba.DPTEBytesPerRow[i][j][k], - mode_lib->vba.PrefetchLinesY[i][j][k], - mode_lib->vba.SwathWidthYThisState[k], - mode_lib->vba.PrefillY[k], - mode_lib->vba.MaxNumSwY[k], - mode_lib->vba.PrefetchLinesC[i][j][k], - mode_lib->vba.SwathWidthCThisState[k], - mode_lib->vba.PrefillC[k], - mode_lib->vba.MaxNumSwC[k], - mode_lib->vba.swath_width_luma_ub_this_state[k], - mode_lib->vba.swath_width_chroma_ub_this_state[k], - mode_lib->vba.SwathHeightYThisState[k], - mode_lib->vba.SwathHeightCThisState[k], mode_lib->vba.TWait, + v->DSCDelayPerState[i][k], + v->SwathWidthYThisState[k] / v->HRatio[k], + dml_min(v->MaxVStartup, v->MaximumVStartup[i][j][k]), + v->MaximumVStartup[i][j][k], + v->UrgLatency[i], + v->ExtraLatency, + v->TimeCalc, + v->PDEAndMetaPTEBytesPerFrame[i][j][k], + v->MetaRowBytes[i][j][k], + v->DPTEBytesPerRow[i][j][k], + v->PrefetchLinesY[i][j][k], + v->SwathWidthYThisState[k], + v->PrefillY[k], + v->MaxNumSwY[k], + v->PrefetchLinesC[i][j][k], + v->SwathWidthCThisState[k], + v->PrefillC[k], + v->MaxNumSwC[k], + v->swath_width_luma_ub_this_state[k], + v->swath_width_chroma_ub_this_state[k], + v->SwathHeightYThisState[k], + v->SwathHeightCThisState[k], v->TWait, /* Output */ &v->dummy_vars.dml32_ModeSupportAndSystemConfigurationFull.DSTXAfterScaler[k], &v->dummy_vars.dml32_ModeSupportAndSystemConfigurationFull.DSTYAfterScaler[k], - &mode_lib->vba.LineTimesForPrefetch[k], - &mode_lib->vba.PrefetchBW[k], - &mode_lib->vba.LinesForMetaPTE[k], - &mode_lib->vba.LinesForMetaAndDPTERow[k], - &mode_lib->vba.VRatioPreY[i][j][k], - &mode_lib->vba.VRatioPreC[i][j][k], - &mode_lib->vba.RequiredPrefetchPixelDataBWLuma[0][0][k], - &mode_lib->vba.RequiredPrefetchPixelDataBWChroma[0][0][k], - &mode_lib->vba.NoTimeForDynamicMetadata[i][j][k], - &mode_lib->vba.Tno_bw[k], - &mode_lib->vba.prefetch_vmrow_bw[k], + &v->LineTimesForPrefetch[k], + &v->PrefetchBW[k], + &v->LinesForMetaPTE[k], + &v->LinesForMetaAndDPTERow[k], + &v->VRatioPreY[i][j][k], + &v->VRatioPreC[i][j][k], + &v->RequiredPrefetchPixelDataBWLuma[0][0][k], + &v->RequiredPrefetchPixelDataBWChroma[0][0][k], + &v->NoTimeForDynamicMetadata[i][j][k], + &v->Tno_bw[k], + &v->prefetch_vmrow_bw[k], &v->dummy_vars.dml32_ModeSupportAndSystemConfigurationFull.dummy_single[0], // double *Tdmdl_vm &v->dummy_vars.dml32_ModeSupportAndSystemConfigurationFull.dummy_single[1], // double *Tdmdl &v->dummy_vars.dml32_ModeSupportAndSystemConfigurationFull.dummy_single[2], // double *TSetup @@ -3557,62 +3499,32 @@ void dml32_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l { dml32_CalculateWatermarksMALLUseAndDRAMSpeedChangeSupport( - mode_lib->vba.USRRetrainingRequiredFinal, - mode_lib->vba.UsesMALLForPStateChange, - mode_lib->vba.PrefetchModePerState[i][j], - mode_lib->vba.NumberOfActiveSurfaces, - mode_lib->vba.MaxLineBufferLines, - mode_lib->vba.LineBufferSizeFinal, - mode_lib->vba.WritebackInterfaceBufferSize, - mode_lib->vba.DCFCLKState[i][j], - mode_lib->vba.ReturnBWPerState[i][j], - mode_lib->vba.SynchronizeTimingsFinal, - mode_lib->vba.SynchronizeDRRDisplaysForUCLKPStateChangeFinal, - mode_lib->vba.DRRDisplay, - mode_lib->vba.dpte_group_bytes, - mode_lib->vba.meta_row_height, - mode_lib->vba.meta_row_height_chroma, + v, + v->PrefetchModePerState[i][j], + v->DCFCLKState[i][j], + v->ReturnBWPerState[i][j], v->dummy_vars.dml32_ModeSupportAndSystemConfigurationFull.mSOCParameters, - mode_lib->vba.WritebackChunkSize, - mode_lib->vba.SOCCLKPerState[i], - mode_lib->vba.ProjectedDCFCLKDeepSleep[i][j], - mode_lib->vba.DETBufferSizeYThisState, - mode_lib->vba.DETBufferSizeCThisState, - mode_lib->vba.SwathHeightYThisState, - mode_lib->vba.SwathHeightCThisState, - mode_lib->vba.LBBitPerPixel, - mode_lib->vba.SwathWidthYThisState, // 24 - mode_lib->vba.SwathWidthCThisState, - mode_lib->vba.HRatio, - mode_lib->vba.HRatioChroma, - mode_lib->vba.vtaps, - mode_lib->vba.VTAPsChroma, - mode_lib->vba.VRatio, - mode_lib->vba.VRatioChroma, - mode_lib->vba.HTotal, - mode_lib->vba.VTotal, - mode_lib->vba.VActive, - mode_lib->vba.PixelClock, - mode_lib->vba.BlendingAndTiming, - mode_lib->vba.NoOfDPPThisState, - mode_lib->vba.BytePerPixelInDETY, - mode_lib->vba.BytePerPixelInDETC, + v->SOCCLKPerState[i], + v->ProjectedDCFCLKDeepSleep[i][j], + v->DETBufferSizeYThisState, + v->DETBufferSizeCThisState, + v->SwathHeightYThisState, + v->SwathHeightCThisState, + v->SwathWidthYThisState, // 24 + v->SwathWidthCThisState, + v->NoOfDPPThisState, + v->BytePerPixelInDETY, + v->BytePerPixelInDETC, v->dummy_vars.dml32_ModeSupportAndSystemConfigurationFull.DSTXAfterScaler, v->dummy_vars.dml32_ModeSupportAndSystemConfigurationFull.DSTYAfterScaler, - mode_lib->vba.WritebackEnable, - mode_lib->vba.WritebackPixelFormat, - mode_lib->vba.WritebackDestinationWidth, - mode_lib->vba.WritebackDestinationHeight, - mode_lib->vba.WritebackSourceHeight, - mode_lib->vba.UnboundedRequestEnabledThisState, - mode_lib->vba.CompressedBufferSizeInkByteThisState, + v->UnboundedRequestEnabledThisState, + v->CompressedBufferSizeInkByteThisState, /* Output */ - &mode_lib->vba.Watermark, // Store the values in vba - &mode_lib->vba.DRAMClockChangeSupport[i][j], + &v->DRAMClockChangeSupport[i][j], &v->dummy_vars.dml32_ModeSupportAndSystemConfigurationFull.dummy_single2[0], // double *MaxActiveDRAMClockChangeLatencySupported &v->dummy_vars.dml32_ModeSupportAndSystemConfigurationFull.dummy_integer[0], // Long SubViewportLinesNeededInMALL[] - &mode_lib->vba.FCLKChangeSupport[i][j], + &v->FCLKChangeSupport[i][j], &v->dummy_vars.dml32_ModeSupportAndSystemConfigurationFull.dummy_single2[1], // double *MinActiveFCLKChangeLatencySupported &mode_lib->vba.USRRetrainingSupport[i][j], mode_lib->vba.ActiveDRAMClockChangeLatencyMargin); diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_util_32.c b/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_util_32.c index 05fc14a47fba..59c2547d01b1 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_util_32.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_util_32.c @@ -3363,28 +3363,14 @@ double dml32_CalculateExtraLatency( } // CalculateExtraLatency bool dml32_CalculatePrefetchSchedule( + struct vba_vars_st *v, + unsigned int k, double HostVMInefficiencyFactor, DmlPipe *myPipe, unsigned int DSCDelay, - double DPPCLKDelaySubtotalPlusCNVCFormater, - double DPPCLKDelaySCL, - double DPPCLKDelaySCLLBOnly, - double DPPCLKDelayCNVCCursor, - double DISPCLKDelaySubtotal, unsigned int DPP_RECOUT_WIDTH, - enum output_format_class OutputFormat, - unsigned int MaxInterDCNTileRepeaters, unsigned int VStartup, unsigned int MaxVStartup, - unsigned int GPUVMPageTableLevels, - bool GPUVMEnable, - bool HostVMEnable, - unsigned int HostVMMaxNonCachedPageTableLevels, - double HostVMMinPageSize, - bool DynamicMetadataEnable, - bool DynamicMetadataVMEnabled, - int DynamicMetadataLinesBeforeActiveRequired, - unsigned int DynamicMetadataTransmittedBytes, double UrgentLatency, double UrgentExtraLatency, double TCalc, @@ -3425,6 +3411,7 @@ bool dml32_CalculatePrefetchSchedule( double *VUpdateWidthPix, double *VReadyOffsetPix) { + double DPPCLKDelaySubtotalPlusCNVCFormater = v->DPPCLKDelaySubtotal + v->DPPCLKDelayCNVCFormater; bool MyError = false; unsigned int DPPCycles, DISPCLKCycles; double DSTTotalPixelsAfterScaler; @@ -3461,27 +3448,27 @@ bool dml32_CalculatePrefetchSchedule( double Tsw_est1 = 0; double Tsw_est3 = 0; - if (GPUVMEnable == true && HostVMEnable == true) - HostVMDynamicLevelsTrips = HostVMMaxNonCachedPageTableLevels; + if (v->GPUVMEnable == true && v->HostVMEnable == true) + HostVMDynamicLevelsTrips = v->HostVMMaxNonCachedPageTableLevels; else HostVMDynamicLevelsTrips = 0; #ifdef __DML_VBA_DEBUG__ - dml_print("DML::%s: GPUVMEnable = %d\n", __func__, GPUVMEnable); - dml_print("DML::%s: GPUVMPageTableLevels = %d\n", __func__, GPUVMPageTableLevels); + dml_print("DML::%s: v->GPUVMEnable = %d\n", __func__, v->GPUVMEnable); + dml_print("DML::%s: v->GPUVMMaxPageTableLevels = %d\n", __func__, v->GPUVMMaxPageTableLevels); dml_print("DML::%s: DCCEnable = %d\n", __func__, myPipe->DCCEnable); - dml_print("DML::%s: HostVMEnable=%d HostVMInefficiencyFactor=%f\n", - __func__, HostVMEnable, HostVMInefficiencyFactor); + dml_print("DML::%s: v->HostVMEnable=%d HostVMInefficiencyFactor=%f\n", + __func__, v->HostVMEnable, HostVMInefficiencyFactor); #endif dml32_CalculateVUpdateAndDynamicMetadataParameters( - MaxInterDCNTileRepeaters, + v->MaxInterDCNTileRepeaters, myPipe->Dppclk, myPipe->Dispclk, myPipe->DCFClkDeepSleep, myPipe->PixelClock, myPipe->HTotal, myPipe->VBlank, - DynamicMetadataTransmittedBytes, - DynamicMetadataLinesBeforeActiveRequired, + v->DynamicMetadataTransmittedBytes[k], + v->DynamicMetadataLinesBeforeActiveRequired[k], myPipe->InterlaceEnable, myPipe->ProgressiveToInterlaceUnitInOPP, TSetup, @@ -3496,19 +3483,19 @@ bool dml32_CalculatePrefetchSchedule( LineTime = myPipe->HTotal / myPipe->PixelClock; trip_to_mem = UrgentLatency; - Tvm_trips = UrgentExtraLatency + trip_to_mem * (GPUVMPageTableLevels * (HostVMDynamicLevelsTrips + 1) - 1); + Tvm_trips = UrgentExtraLatency + trip_to_mem * (v->GPUVMMaxPageTableLevels * (HostVMDynamicLevelsTrips + 1) - 1); - if (DynamicMetadataVMEnabled == true) + if (v->DynamicMetadataVMEnabled == true) *Tdmdl = TWait + Tvm_trips + trip_to_mem; else *Tdmdl = TWait + UrgentExtraLatency; #ifdef __DML_VBA_ALLOW_DELTA__ - if (DynamicMetadataEnable == false) + if (v->DynamicMetadataEnable[k] == false) *Tdmdl = 0.0; #endif - if (DynamicMetadataEnable == true) { + if (v->DynamicMetadataEnable[k] == true) { if (VStartup * LineTime < *TSetup + *Tdmdl + Tdmbf + Tdmec + Tdmsks) { *NotEnoughTimeForDynamicMetadata = true; #ifdef __DML_VBA_DEBUG__ @@ -3528,17 +3515,17 @@ bool dml32_CalculatePrefetchSchedule( *NotEnoughTimeForDynamicMetadata = false; } - *Tdmdl_vm = (DynamicMetadataEnable == true && DynamicMetadataVMEnabled == true && - GPUVMEnable == true ? TWait + Tvm_trips : 0); + *Tdmdl_vm = (v->DynamicMetadataEnable[k] == true && v->DynamicMetadataVMEnabled == true && + v->GPUVMEnable == true ? TWait + Tvm_trips : 0); if (myPipe->ScalerEnabled) - DPPCycles = DPPCLKDelaySubtotalPlusCNVCFormater + DPPCLKDelaySCL; + DPPCycles = DPPCLKDelaySubtotalPlusCNVCFormater + v->DPPCLKDelaySCL; else - DPPCycles = DPPCLKDelaySubtotalPlusCNVCFormater + DPPCLKDelaySCLLBOnly; + DPPCycles = DPPCLKDelaySubtotalPlusCNVCFormater + v->DPPCLKDelaySCLLBOnly; - DPPCycles = DPPCycles + myPipe->NumberOfCursors * DPPCLKDelayCNVCCursor; + DPPCycles = DPPCycles + myPipe->NumberOfCursors * v->DPPCLKDelayCNVCCursor; - DISPCLKCycles = DISPCLKDelaySubtotal; + DISPCLKCycles = v->DISPCLKDelaySubtotal; if (myPipe->Dppclk == 0.0 || myPipe->Dispclk == 0.0) return true; @@ -3564,7 +3551,7 @@ bool dml32_CalculatePrefetchSchedule( dml_print("DML::%s: DSTXAfterScaler: %d\n", __func__, *DSTXAfterScaler); #endif - if (OutputFormat == dm_420 || (myPipe->InterlaceEnable && myPipe->ProgressiveToInterlaceUnitInOPP)) + if (v->OutputFormat[k] == dm_420 || (myPipe->InterlaceEnable && myPipe->ProgressiveToInterlaceUnitInOPP)) *DSTYAfterScaler = 1; else *DSTYAfterScaler = 0; @@ -3581,13 +3568,13 @@ bool dml32_CalculatePrefetchSchedule( Tr0_trips = trip_to_mem * (HostVMDynamicLevelsTrips + 1); - if (GPUVMEnable == true) { + if (v->GPUVMEnable == true) { Tvm_trips_rounded = dml_ceil(4.0 * Tvm_trips / LineTime, 1.0) / 4.0 * LineTime; Tr0_trips_rounded = dml_ceil(4.0 * Tr0_trips / LineTime, 1.0) / 4.0 * LineTime; - if (GPUVMPageTableLevels >= 3) { + if (v->GPUVMMaxPageTableLevels >= 3) { *Tno_bw = UrgentExtraLatency + trip_to_mem * - (double) ((GPUVMPageTableLevels - 2) * (HostVMDynamicLevelsTrips + 1) - 1); - } else if (GPUVMPageTableLevels == 1 && myPipe->DCCEnable != true) { + (double) ((v->GPUVMMaxPageTableLevels - 2) * (HostVMDynamicLevelsTrips + 1) - 1); + } else if (v->GPUVMMaxPageTableLevels == 1 && myPipe->DCCEnable != true) { Tr0_trips_rounded = dml_ceil(4.0 * UrgentExtraLatency / LineTime, 1.0) / 4.0 * LineTime; // VBA_ERROR *Tno_bw = UrgentExtraLatency; @@ -3622,7 +3609,7 @@ bool dml32_CalculatePrefetchSchedule( min_Lsw = dml_max(min_Lsw, 1.0); Lsw_oto = dml_ceil(4.0 * dml_max(prefetch_sw_bytes / prefetch_bw_oto / LineTime, min_Lsw), 1.0) / 4.0; - if (GPUVMEnable == true) { + if (v->GPUVMEnable == true) { Tvm_oto = dml_max3( Tvm_trips, *Tno_bw + PDEAndMetaPTEBytesFrame * HostVMInefficiencyFactor / prefetch_bw_oto, @@ -3630,7 +3617,7 @@ bool dml32_CalculatePrefetchSchedule( } else Tvm_oto = LineTime / 4.0; - if ((GPUVMEnable == true || myPipe->DCCEnable == true)) { + if ((v->GPUVMEnable == true || myPipe->DCCEnable == true)) { Tr0_oto = dml_max4( Tr0_trips, (MetaRowByte + PixelPTEBytesPerRow * HostVMInefficiencyFactor) / prefetch_bw_oto, @@ -3833,7 +3820,7 @@ bool dml32_CalculatePrefetchSchedule( #endif if (prefetch_bw_equ > 0) { - if (GPUVMEnable == true) { + if (v->GPUVMEnable == true) { Tvm_equ = dml_max3(*Tno_bw + PDEAndMetaPTEBytesFrame * HostVMInefficiencyFactor / prefetch_bw_equ, Tvm_trips, LineTime / 4); @@ -3841,7 +3828,7 @@ bool dml32_CalculatePrefetchSchedule( Tvm_equ = LineTime / 4; } - if ((GPUVMEnable == true || myPipe->DCCEnable == true)) { + if ((v->GPUVMEnable == true || myPipe->DCCEnable == true)) { Tr0_equ = dml_max4((MetaRowByte + PixelPTEBytesPerRow * HostVMInefficiencyFactor) / prefetch_bw_equ, Tr0_trips, (LineTime - Tvm_equ) / 2, LineTime / 4); @@ -4206,58 +4193,28 @@ void dml32_CalculateFlipSchedule( } // CalculateFlipSchedule void dml32_CalculateWatermarksMALLUseAndDRAMSpeedChangeSupport( - bool USRRetrainingRequiredFinal, - enum dm_use_mall_for_pstate_change_mode UseMALLForPStateChange[], + struct vba_vars_st *v, unsigned int PrefetchMode, - unsigned int NumberOfActiveSurfaces, - unsigned int MaxLineBufferLines, - unsigned int LineBufferSize, - unsigned int WritebackInterfaceBufferSize, double DCFCLK, double ReturnBW, - bool SynchronizeTimingsFinal, - bool SynchronizeDRRDisplaysForUCLKPStateChangeFinal, - bool DRRDisplay[], - unsigned int dpte_group_bytes[], - unsigned int meta_row_height[], - unsigned int meta_row_height_chroma[], SOCParametersList mmSOCParameters, - unsigned int WritebackChunkSize, double SOCCLK, double DCFClkDeepSleep, unsigned int DETBufferSizeY[], unsigned int DETBufferSizeC[], unsigned int SwathHeightY[], unsigned int SwathHeightC[], - unsigned int LBBitPerPixel[], double SwathWidthY[], double SwathWidthC[], - double HRatio[], - double HRatioChroma[], - unsigned int VTaps[], - unsigned int VTapsChroma[], - double VRatio[], - double VRatioChroma[], - unsigned int HTotal[], - unsigned int VTotal[], - unsigned int VActive[], - double PixelClock[], - unsigned int BlendingAndTiming[], unsigned int DPPPerSurface[], double BytePerPixelDETY[], double BytePerPixelDETC[], double DSTXAfterScaler[], double DSTYAfterScaler[], - bool WritebackEnable[], - enum source_format_class WritebackPixelFormat[], - double WritebackDestinationWidth[], - double WritebackDestinationHeight[], - double WritebackSourceHeight[], bool UnboundedRequestEnabled, unsigned int CompressedBufferSizeInkByte, /* Output */ - Watermarks *Watermark, enum clock_change_support *DRAMClockChangeSupport, double MaxActiveDRAMClockChangeLatencySupported[], unsigned int SubViewportLinesNeededInMALL[], @@ -4299,136 +4256,136 @@ void dml32_CalculateWatermarksMALLUseAndDRAMSpeedChangeSupport( unsigned int LBLatencyHidingSourceLinesY[DC__NUM_DPP__MAX]; unsigned int LBLatencyHidingSourceLinesC[DC__NUM_DPP__MAX]; - Watermark->UrgentWatermark = mmSOCParameters.UrgentLatency + mmSOCParameters.ExtraLatency; - Watermark->USRRetrainingWatermark = mmSOCParameters.UrgentLatency + mmSOCParameters.ExtraLatency + v->Watermark.UrgentWatermark = mmSOCParameters.UrgentLatency + mmSOCParameters.ExtraLatency; + v->Watermark.USRRetrainingWatermark = mmSOCParameters.UrgentLatency + mmSOCParameters.ExtraLatency + mmSOCParameters.USRRetrainingLatency + mmSOCParameters.SMNLatency; - Watermark->DRAMClockChangeWatermark = mmSOCParameters.DRAMClockChangeLatency + Watermark->UrgentWatermark; - Watermark->FCLKChangeWatermark = mmSOCParameters.FCLKChangeLatency + Watermark->UrgentWatermark; - Watermark->StutterExitWatermark = mmSOCParameters.SRExitTime + mmSOCParameters.ExtraLatency + v->Watermark.DRAMClockChangeWatermark = mmSOCParameters.DRAMClockChangeLatency + v->Watermark.UrgentWatermark; + v->Watermark.FCLKChangeWatermark = mmSOCParameters.FCLKChangeLatency + v->Watermark.UrgentWatermark; + v->Watermark.StutterExitWatermark = mmSOCParameters.SRExitTime + mmSOCParameters.ExtraLatency + 10 / DCFClkDeepSleep; - Watermark->StutterEnterPlusExitWatermark = mmSOCParameters.SREnterPlusExitTime + mmSOCParameters.ExtraLatency + v->Watermark.StutterEnterPlusExitWatermark = mmSOCParameters.SREnterPlusExitTime + mmSOCParameters.ExtraLatency + 10 / DCFClkDeepSleep; - Watermark->Z8StutterExitWatermark = mmSOCParameters.SRExitZ8Time + mmSOCParameters.ExtraLatency + v->Watermark.Z8StutterExitWatermark = mmSOCParameters.SRExitZ8Time + mmSOCParameters.ExtraLatency + 10 / DCFClkDeepSleep; - Watermark->Z8StutterEnterPlusExitWatermark = mmSOCParameters.SREnterPlusExitZ8Time + v->Watermark.Z8StutterEnterPlusExitWatermark = mmSOCParameters.SREnterPlusExitZ8Time + mmSOCParameters.ExtraLatency + 10 / DCFClkDeepSleep; #ifdef __DML_VBA_DEBUG__ dml_print("DML::%s: UrgentLatency = %f\n", __func__, mmSOCParameters.UrgentLatency); dml_print("DML::%s: ExtraLatency = %f\n", __func__, mmSOCParameters.ExtraLatency); dml_print("DML::%s: DRAMClockChangeLatency = %f\n", __func__, mmSOCParameters.DRAMClockChangeLatency); - dml_print("DML::%s: UrgentWatermark = %f\n", __func__, Watermark->UrgentWatermark); - dml_print("DML::%s: USRRetrainingWatermark = %f\n", __func__, Watermark->USRRetrainingWatermark); - dml_print("DML::%s: DRAMClockChangeWatermark = %f\n", __func__, Watermark->DRAMClockChangeWatermark); - dml_print("DML::%s: FCLKChangeWatermark = %f\n", __func__, Watermark->FCLKChangeWatermark); - dml_print("DML::%s: StutterExitWatermark = %f\n", __func__, Watermark->StutterExitWatermark); - dml_print("DML::%s: StutterEnterPlusExitWatermark = %f\n", __func__, Watermark->StutterEnterPlusExitWatermark); - dml_print("DML::%s: Z8StutterExitWatermark = %f\n", __func__, Watermark->Z8StutterExitWatermark); + dml_print("DML::%s: UrgentWatermark = %f\n", __func__, v->Watermark.UrgentWatermark); + dml_print("DML::%s: USRRetrainingWatermark = %f\n", __func__, v->Watermark.USRRetrainingWatermark); + dml_print("DML::%s: DRAMClockChangeWatermark = %f\n", __func__, v->Watermark.DRAMClockChangeWatermark); + dml_print("DML::%s: FCLKChangeWatermark = %f\n", __func__, v->Watermark.FCLKChangeWatermark); + dml_print("DML::%s: StutterExitWatermark = %f\n", __func__, v->Watermark.StutterExitWatermark); + dml_print("DML::%s: StutterEnterPlusExitWatermark = %f\n", __func__, v->Watermark.StutterEnterPlusExitWatermark); + dml_print("DML::%s: Z8StutterExitWatermark = %f\n", __func__, v->Watermark.Z8StutterExitWatermark); dml_print("DML::%s: Z8StutterEnterPlusExitWatermark = %f\n", - __func__, Watermark->Z8StutterEnterPlusExitWatermark); + __func__, v->Watermark.Z8StutterEnterPlusExitWatermark); #endif TotalActiveWriteback = 0; - for (k = 0; k < NumberOfActiveSurfaces; ++k) { - if (WritebackEnable[k] == true) + for (k = 0; k < v->NumberOfActiveSurfaces; ++k) { + if (v->WritebackEnable[k] == true) TotalActiveWriteback = TotalActiveWriteback + 1; } if (TotalActiveWriteback <= 1) { - Watermark->WritebackUrgentWatermark = mmSOCParameters.WritebackLatency; + v->Watermark.WritebackUrgentWatermark = mmSOCParameters.WritebackLatency; } else { - Watermark->WritebackUrgentWatermark = mmSOCParameters.WritebackLatency - + WritebackChunkSize * 1024.0 / 32.0 / SOCCLK; + v->Watermark.WritebackUrgentWatermark = mmSOCParameters.WritebackLatency + + v->WritebackChunkSize * 1024.0 / 32.0 / SOCCLK; } - if (USRRetrainingRequiredFinal) - Watermark->WritebackUrgentWatermark = Watermark->WritebackUrgentWatermark + if (v->USRRetrainingRequiredFinal) + v->Watermark.WritebackUrgentWatermark = v->Watermark.WritebackUrgentWatermark + mmSOCParameters.USRRetrainingLatency; if (TotalActiveWriteback <= 1) { - Watermark->WritebackDRAMClockChangeWatermark = mmSOCParameters.DRAMClockChangeLatency + v->Watermark.WritebackDRAMClockChangeWatermark = mmSOCParameters.DRAMClockChangeLatency + mmSOCParameters.WritebackLatency; - Watermark->WritebackFCLKChangeWatermark = mmSOCParameters.FCLKChangeLatency + v->Watermark.WritebackFCLKChangeWatermark = mmSOCParameters.FCLKChangeLatency + mmSOCParameters.WritebackLatency; } else { - Watermark->WritebackDRAMClockChangeWatermark = mmSOCParameters.DRAMClockChangeLatency - + mmSOCParameters.WritebackLatency + WritebackChunkSize * 1024.0 / 32.0 / SOCCLK; - Watermark->WritebackFCLKChangeWatermark = mmSOCParameters.FCLKChangeLatency - + mmSOCParameters.WritebackLatency + WritebackChunkSize * 1024 / 32 / SOCCLK; + v->Watermark.WritebackDRAMClockChangeWatermark = mmSOCParameters.DRAMClockChangeLatency + + mmSOCParameters.WritebackLatency + v->WritebackChunkSize * 1024.0 / 32.0 / SOCCLK; + v->Watermark.WritebackFCLKChangeWatermark = mmSOCParameters.FCLKChangeLatency + + mmSOCParameters.WritebackLatency + v->WritebackChunkSize * 1024 / 32 / SOCCLK; } - if (USRRetrainingRequiredFinal) - Watermark->WritebackDRAMClockChangeWatermark = Watermark->WritebackDRAMClockChangeWatermark + if (v->USRRetrainingRequiredFinal) + v->Watermark.WritebackDRAMClockChangeWatermark = v->Watermark.WritebackDRAMClockChangeWatermark + mmSOCParameters.USRRetrainingLatency; - if (USRRetrainingRequiredFinal) - Watermark->WritebackFCLKChangeWatermark = Watermark->WritebackFCLKChangeWatermark + if (v->USRRetrainingRequiredFinal) + v->Watermark.WritebackFCLKChangeWatermark = v->Watermark.WritebackFCLKChangeWatermark + mmSOCParameters.USRRetrainingLatency; #ifdef __DML_VBA_DEBUG__ dml_print("DML::%s: WritebackDRAMClockChangeWatermark = %f\n", - __func__, Watermark->WritebackDRAMClockChangeWatermark); - dml_print("DML::%s: WritebackFCLKChangeWatermark = %f\n", __func__, Watermark->WritebackFCLKChangeWatermark); - dml_print("DML::%s: WritebackUrgentWatermark = %f\n", __func__, Watermark->WritebackUrgentWatermark); - dml_print("DML::%s: USRRetrainingRequiredFinal = %d\n", __func__, USRRetrainingRequiredFinal); + __func__, v->Watermark.WritebackDRAMClockChangeWatermark); + dml_print("DML::%s: WritebackFCLKChangeWatermark = %f\n", __func__, v->Watermark.WritebackFCLKChangeWatermark); + dml_print("DML::%s: WritebackUrgentWatermark = %f\n", __func__, v->Watermark.WritebackUrgentWatermark); + dml_print("DML::%s: v->USRRetrainingRequiredFinal = %d\n", __func__, v->USRRetrainingRequiredFinal); dml_print("DML::%s: USRRetrainingLatency = %f\n", __func__, mmSOCParameters.USRRetrainingLatency); #endif - for (k = 0; k < NumberOfActiveSurfaces; ++k) { - TotalPixelBW = TotalPixelBW + DPPPerSurface[k] * (SwathWidthY[k] * BytePerPixelDETY[k] * VRatio[k] + - SwathWidthC[k] * BytePerPixelDETC[k] * VRatioChroma[k]) / (HTotal[k] / PixelClock[k]); + for (k = 0; k < v->NumberOfActiveSurfaces; ++k) { + TotalPixelBW = TotalPixelBW + DPPPerSurface[k] * (SwathWidthY[k] * BytePerPixelDETY[k] * v->VRatio[k] + + SwathWidthC[k] * BytePerPixelDETC[k] * v->VRatioChroma[k]) / (v->HTotal[k] / v->PixelClock[k]); } - for (k = 0; k < NumberOfActiveSurfaces; ++k) { + for (k = 0; k < v->NumberOfActiveSurfaces; ++k) { - LBLatencyHidingSourceLinesY[k] = dml_min((double) MaxLineBufferLines, dml_floor(LineBufferSize / LBBitPerPixel[k] / (SwathWidthY[k] / dml_max(HRatio[k], 1.0)), 1)) - (VTaps[k] - 1); - LBLatencyHidingSourceLinesC[k] = dml_min((double) MaxLineBufferLines, dml_floor(LineBufferSize / LBBitPerPixel[k] / (SwathWidthC[k] / dml_max(HRatioChroma[k], 1.0)), 1)) - (VTapsChroma[k] - 1); + LBLatencyHidingSourceLinesY[k] = dml_min((double) v->MaxLineBufferLines, dml_floor(v->LineBufferSizeFinal / v->LBBitPerPixel[k] / (SwathWidthY[k] / dml_max(v->HRatio[k], 1.0)), 1)) - (v->vtaps[k] - 1); + LBLatencyHidingSourceLinesC[k] = dml_min((double) v->MaxLineBufferLines, dml_floor(v->LineBufferSizeFinal / v->LBBitPerPixel[k] / (SwathWidthC[k] / dml_max(v->HRatioChroma[k], 1.0)), 1)) - (v->VTAPsChroma[k] - 1); #ifdef __DML_VBA_DEBUG__ - dml_print("DML::%s: k=%d, MaxLineBufferLines = %d\n", __func__, k, MaxLineBufferLines); - dml_print("DML::%s: k=%d, LineBufferSize = %d\n", __func__, k, LineBufferSize); - dml_print("DML::%s: k=%d, LBBitPerPixel = %d\n", __func__, k, LBBitPerPixel[k]); - dml_print("DML::%s: k=%d, HRatio = %f\n", __func__, k, HRatio[k]); - dml_print("DML::%s: k=%d, VTaps = %d\n", __func__, k, VTaps[k]); + dml_print("DML::%s: k=%d, v->MaxLineBufferLines = %d\n", __func__, k, v->MaxLineBufferLines); + dml_print("DML::%s: k=%d, v->LineBufferSizeFinal = %d\n", __func__, k, v->LineBufferSizeFinal); + dml_print("DML::%s: k=%d, v->LBBitPerPixel = %d\n", __func__, k, v->LBBitPerPixel[k]); + dml_print("DML::%s: k=%d, v->HRatio = %f\n", __func__, k, v->HRatio[k]); + dml_print("DML::%s: k=%d, v->vtaps = %d\n", __func__, k, v->vtaps[k]); #endif - EffectiveLBLatencyHidingY = LBLatencyHidingSourceLinesY[k] / VRatio[k] * (HTotal[k] / PixelClock[k]); - EffectiveLBLatencyHidingC = LBLatencyHidingSourceLinesC[k] / VRatioChroma[k] * (HTotal[k] / PixelClock[k]); + EffectiveLBLatencyHidingY = LBLatencyHidingSourceLinesY[k] / v->VRatio[k] * (v->HTotal[k] / v->PixelClock[k]); + EffectiveLBLatencyHidingC = LBLatencyHidingSourceLinesC[k] / v->VRatioChroma[k] * (v->HTotal[k] / v->PixelClock[k]); EffectiveDETBufferSizeY = DETBufferSizeY[k]; if (UnboundedRequestEnabled) { EffectiveDETBufferSizeY = EffectiveDETBufferSizeY + CompressedBufferSizeInkByte * 1024 - * (SwathWidthY[k] * BytePerPixelDETY[k] * VRatio[k]) - / (HTotal[k] / PixelClock[k]) / TotalPixelBW; + * (SwathWidthY[k] * BytePerPixelDETY[k] * v->VRatio[k]) + / (v->HTotal[k] / v->PixelClock[k]) / TotalPixelBW; } LinesInDETY[k] = (double) EffectiveDETBufferSizeY / BytePerPixelDETY[k] / SwathWidthY[k]; LinesInDETYRoundedDownToSwath[k] = dml_floor(LinesInDETY[k], SwathHeightY[k]); - FullDETBufferingTimeY = LinesInDETYRoundedDownToSwath[k] * (HTotal[k] / PixelClock[k]) / VRatio[k]; + FullDETBufferingTimeY = LinesInDETYRoundedDownToSwath[k] * (v->HTotal[k] / v->PixelClock[k]) / v->VRatio[k]; ActiveClockChangeLatencyHidingY = EffectiveLBLatencyHidingY + FullDETBufferingTimeY - - (DSTXAfterScaler[k] / HTotal[k] + DSTYAfterScaler[k]) * HTotal[k] / PixelClock[k]; + - (DSTXAfterScaler[k] / v->HTotal[k] + DSTYAfterScaler[k]) * v->HTotal[k] / v->PixelClock[k]; - if (NumberOfActiveSurfaces > 1) { + if (v->NumberOfActiveSurfaces > 1) { ActiveClockChangeLatencyHidingY = ActiveClockChangeLatencyHidingY - - (1 - 1 / NumberOfActiveSurfaces) * SwathHeightY[k] * HTotal[k] - / PixelClock[k] / VRatio[k]; + - (1 - 1 / v->NumberOfActiveSurfaces) * SwathHeightY[k] * v->HTotal[k] + / v->PixelClock[k] / v->VRatio[k]; } if (BytePerPixelDETC[k] > 0) { LinesInDETC[k] = DETBufferSizeC[k] / BytePerPixelDETC[k] / SwathWidthC[k]; LinesInDETCRoundedDownToSwath[k] = dml_floor(LinesInDETC[k], SwathHeightC[k]); - FullDETBufferingTimeC = LinesInDETCRoundedDownToSwath[k] * (HTotal[k] / PixelClock[k]) - / VRatioChroma[k]; + FullDETBufferingTimeC = LinesInDETCRoundedDownToSwath[k] * (v->HTotal[k] / v->PixelClock[k]) + / v->VRatioChroma[k]; ActiveClockChangeLatencyHidingC = EffectiveLBLatencyHidingC + FullDETBufferingTimeC - - (DSTXAfterScaler[k] / HTotal[k] + DSTYAfterScaler[k]) * HTotal[k] - / PixelClock[k]; - if (NumberOfActiveSurfaces > 1) { + - (DSTXAfterScaler[k] / v->HTotal[k] + DSTYAfterScaler[k]) * v->HTotal[k] + / v->PixelClock[k]; + if (v->NumberOfActiveSurfaces > 1) { ActiveClockChangeLatencyHidingC = ActiveClockChangeLatencyHidingC - - (1 - 1 / NumberOfActiveSurfaces) * SwathHeightC[k] * HTotal[k] - / PixelClock[k] / VRatioChroma[k]; + - (1 - 1 / v->NumberOfActiveSurfaces) * SwathHeightC[k] * v->HTotal[k] + / v->PixelClock[k] / v->VRatioChroma[k]; } ActiveClockChangeLatencyHiding = dml_min(ActiveClockChangeLatencyHidingY, ActiveClockChangeLatencyHidingC); @@ -4436,24 +4393,24 @@ void dml32_CalculateWatermarksMALLUseAndDRAMSpeedChangeSupport( ActiveClockChangeLatencyHiding = ActiveClockChangeLatencyHidingY; } - ActiveDRAMClockChangeLatencyMargin[k] = ActiveClockChangeLatencyHiding - Watermark->UrgentWatermark - - Watermark->DRAMClockChangeWatermark; - ActiveFCLKChangeLatencyMargin[k] = ActiveClockChangeLatencyHiding - Watermark->UrgentWatermark - - Watermark->FCLKChangeWatermark; - USRRetrainingLatencyMargin[k] = ActiveClockChangeLatencyHiding - Watermark->USRRetrainingWatermark; - - if (WritebackEnable[k]) { - WritebackLatencyHiding = WritebackInterfaceBufferSize * 1024 - / (WritebackDestinationWidth[k] * WritebackDestinationHeight[k] - / (WritebackSourceHeight[k] * HTotal[k] / PixelClock[k]) * 4); - if (WritebackPixelFormat[k] == dm_444_64) + ActiveDRAMClockChangeLatencyMargin[k] = ActiveClockChangeLatencyHiding - v->Watermark.UrgentWatermark + - v->Watermark.DRAMClockChangeWatermark; + ActiveFCLKChangeLatencyMargin[k] = ActiveClockChangeLatencyHiding - v->Watermark.UrgentWatermark + - v->Watermark.FCLKChangeWatermark; + USRRetrainingLatencyMargin[k] = ActiveClockChangeLatencyHiding - v->Watermark.USRRetrainingWatermark; + + if (v->WritebackEnable[k]) { + WritebackLatencyHiding = v->WritebackInterfaceBufferSize * 1024 + / (v->WritebackDestinationWidth[k] * v->WritebackDestinationHeight[k] + / (v->WritebackSourceHeight[k] * v->HTotal[k] / v->PixelClock[k]) * 4); + if (v->WritebackPixelFormat[k] == dm_444_64) WritebackLatencyHiding = WritebackLatencyHiding / 2; WritebackDRAMClockChangeLatencyMargin = WritebackLatencyHiding - - Watermark->WritebackDRAMClockChangeWatermark; + - v->Watermark.WritebackDRAMClockChangeWatermark; WritebackFCLKChangeLatencyMargin = WritebackLatencyHiding - - Watermark->WritebackFCLKChangeWatermark; + - v->Watermark.WritebackFCLKChangeWatermark; ActiveDRAMClockChangeLatencyMargin[k] = dml_min(ActiveDRAMClockChangeLatencyMargin[k], WritebackFCLKChangeLatencyMargin); @@ -4461,22 +4418,22 @@ void dml32_CalculateWatermarksMALLUseAndDRAMSpeedChangeSupport( WritebackDRAMClockChangeLatencyMargin); } MaxActiveDRAMClockChangeLatencySupported[k] = - (UseMALLForPStateChange[k] == dm_use_mall_pstate_change_phantom_pipe) ? + (v->UsesMALLForPStateChange[k] == dm_use_mall_pstate_change_phantom_pipe) ? 0 : (ActiveDRAMClockChangeLatencyMargin[k] + mmSOCParameters.DRAMClockChangeLatency); } - for (i = 0; i < NumberOfActiveSurfaces; ++i) { - for (j = 0; j < NumberOfActiveSurfaces; ++j) { + for (i = 0; i < v->NumberOfActiveSurfaces; ++i) { + for (j = 0; j < v->NumberOfActiveSurfaces; ++j) { if (i == j || - (BlendingAndTiming[i] == i && BlendingAndTiming[j] == i) || - (BlendingAndTiming[j] == j && BlendingAndTiming[i] == j) || - (BlendingAndTiming[i] == BlendingAndTiming[j] && BlendingAndTiming[i] != i) || - (SynchronizeTimingsFinal && PixelClock[i] == PixelClock[j] && - HTotal[i] == HTotal[j] && VTotal[i] == VTotal[j] && - VActive[i] == VActive[j]) || (SynchronizeDRRDisplaysForUCLKPStateChangeFinal && - (DRRDisplay[i] || DRRDisplay[j]))) { + (v->BlendingAndTiming[i] == i && v->BlendingAndTiming[j] == i) || + (v->BlendingAndTiming[j] == j && v->BlendingAndTiming[i] == j) || + (v->BlendingAndTiming[i] == v->BlendingAndTiming[j] && v->BlendingAndTiming[i] != i) || + (v->SynchronizeTimingsFinal && v->PixelClock[i] == v->PixelClock[j] && + v->HTotal[i] == v->HTotal[j] && v->VTotal[i] == v->VTotal[j] && + v->VActive[i] == v->VActive[j]) || (v->SynchronizeDRRDisplaysForUCLKPStateChangeFinal && + (v->DRRDisplay[i] || v->DRRDisplay[j]))) { SynchronizedSurfaces[i][j] = true; } else { SynchronizedSurfaces[i][j] = false; @@ -4484,8 +4441,8 @@ void dml32_CalculateWatermarksMALLUseAndDRAMSpeedChangeSupport( } } - for (k = 0; k < NumberOfActiveSurfaces; ++k) { - if ((UseMALLForPStateChange[k] != dm_use_mall_pstate_change_phantom_pipe) && + for (k = 0; k < v->NumberOfActiveSurfaces; ++k) { + if ((v->UsesMALLForPStateChange[k] != dm_use_mall_pstate_change_phantom_pipe) && (!FoundFirstSurfaceWithMinActiveFCLKChangeMargin || ActiveFCLKChangeLatencyMargin[k] < MinActiveFCLKChangeMargin)) { FoundFirstSurfaceWithMinActiveFCLKChangeMargin = true; @@ -4497,9 +4454,9 @@ void dml32_CalculateWatermarksMALLUseAndDRAMSpeedChangeSupport( *MinActiveFCLKChangeLatencySupported = MinActiveFCLKChangeMargin + mmSOCParameters.FCLKChangeLatency; SameTimingForFCLKChange = true; - for (k = 0; k < NumberOfActiveSurfaces; ++k) { + for (k = 0; k < v->NumberOfActiveSurfaces; ++k) { if (!SynchronizedSurfaces[k][SurfaceWithMinActiveFCLKChangeMargin]) { - if ((UseMALLForPStateChange[k] != dm_use_mall_pstate_change_phantom_pipe) && + if ((v->UsesMALLForPStateChange[k] != dm_use_mall_pstate_change_phantom_pipe) && (SameTimingForFCLKChange || ActiveFCLKChangeLatencyMargin[k] < SecondMinActiveFCLKChangeMarginOneDisplayInVBLank)) { @@ -4519,17 +4476,17 @@ void dml32_CalculateWatermarksMALLUseAndDRAMSpeedChangeSupport( } *USRRetrainingSupport = true; - for (k = 0; k < NumberOfActiveSurfaces; ++k) { - if ((UseMALLForPStateChange[k] != dm_use_mall_pstate_change_phantom_pipe) && + for (k = 0; k < v->NumberOfActiveSurfaces; ++k) { + if ((v->UsesMALLForPStateChange[k] != dm_use_mall_pstate_change_phantom_pipe) && (USRRetrainingLatencyMargin[k] < 0)) { *USRRetrainingSupport = false; } } - for (k = 0; k < NumberOfActiveSurfaces; ++k) { - if (UseMALLForPStateChange[k] != dm_use_mall_pstate_change_full_frame && - UseMALLForPStateChange[k] != dm_use_mall_pstate_change_sub_viewport && - UseMALLForPStateChange[k] != dm_use_mall_pstate_change_phantom_pipe && + for (k = 0; k < v->NumberOfActiveSurfaces; ++k) { + if (v->UsesMALLForPStateChange[k] != dm_use_mall_pstate_change_full_frame && + v->UsesMALLForPStateChange[k] != dm_use_mall_pstate_change_sub_viewport && + v->UsesMALLForPStateChange[k] != dm_use_mall_pstate_change_phantom_pipe && ActiveDRAMClockChangeLatencyMargin[k] < 0) { if (PrefetchMode > 0) { DRAMClockChangeSupportNumber = 2; @@ -4543,10 +4500,10 @@ void dml32_CalculateWatermarksMALLUseAndDRAMSpeedChangeSupport( } } - for (k = 0; k < NumberOfActiveSurfaces; ++k) { - if (UseMALLForPStateChange[k] == dm_use_mall_pstate_change_full_frame) + for (k = 0; k < v->NumberOfActiveSurfaces; ++k) { + if (v->UsesMALLForPStateChange[k] == dm_use_mall_pstate_change_full_frame) DRAMClockChangeMethod = 1; - else if (UseMALLForPStateChange[k] == dm_use_mall_pstate_change_sub_viewport) + else if (v->UsesMALLForPStateChange[k] == dm_use_mall_pstate_change_sub_viewport) DRAMClockChangeMethod = 2; } @@ -4573,16 +4530,16 @@ void dml32_CalculateWatermarksMALLUseAndDRAMSpeedChangeSupport( *DRAMClockChangeSupport = dm_dram_clock_change_unsupported; } - for (k = 0; k < NumberOfActiveSurfaces; ++k) { + for (k = 0; k < v->NumberOfActiveSurfaces; ++k) { unsigned int dst_y_pstate; unsigned int src_y_pstate_l; unsigned int src_y_pstate_c; unsigned int src_y_ahead_l, src_y_ahead_c, sub_vp_lines_l, sub_vp_lines_c; - dst_y_pstate = dml_ceil((mmSOCParameters.DRAMClockChangeLatency + mmSOCParameters.UrgentLatency) / (HTotal[k] / PixelClock[k]), 1); - src_y_pstate_l = dml_ceil(dst_y_pstate * VRatio[k], SwathHeightY[k]); + dst_y_pstate = dml_ceil((mmSOCParameters.DRAMClockChangeLatency + mmSOCParameters.UrgentLatency) / (v->HTotal[k] / v->PixelClock[k]), 1); + src_y_pstate_l = dml_ceil(dst_y_pstate * v->VRatio[k], SwathHeightY[k]); src_y_ahead_l = dml_floor(DETBufferSizeY[k] / BytePerPixelDETY[k] / SwathWidthY[k], SwathHeightY[k]) + LBLatencyHidingSourceLinesY[k]; - sub_vp_lines_l = src_y_pstate_l + src_y_ahead_l + meta_row_height[k]; + sub_vp_lines_l = src_y_pstate_l + src_y_ahead_l + v->meta_row_height[k]; #ifdef __DML_VBA_DEBUG__ dml_print("DML::%s: k=%d, DETBufferSizeY = %d\n", __func__, k, DETBufferSizeY[k]); @@ -4593,21 +4550,21 @@ dml_print("DML::%s: k=%d, LBLatencyHidingSourceLinesY = %d\n", __func__, k, LBL dml_print("DML::%s: k=%d, dst_y_pstate = %d\n", __func__, k, dst_y_pstate); dml_print("DML::%s: k=%d, src_y_pstate_l = %d\n", __func__, k, src_y_pstate_l); dml_print("DML::%s: k=%d, src_y_ahead_l = %d\n", __func__, k, src_y_ahead_l); -dml_print("DML::%s: k=%d, meta_row_height = %d\n", __func__, k, meta_row_height[k]); +dml_print("DML::%s: k=%d, v->meta_row_height = %d\n", __func__, k, v->meta_row_height[k]); dml_print("DML::%s: k=%d, sub_vp_lines_l = %d\n", __func__, k, sub_vp_lines_l); #endif SubViewportLinesNeededInMALL[k] = sub_vp_lines_l; if (BytePerPixelDETC[k] > 0) { - src_y_pstate_c = dml_ceil(dst_y_pstate * VRatioChroma[k], SwathHeightC[k]); + src_y_pstate_c = dml_ceil(dst_y_pstate * v->VRatioChroma[k], SwathHeightC[k]); src_y_ahead_c = dml_floor(DETBufferSizeC[k] / BytePerPixelDETC[k] / SwathWidthC[k], SwathHeightC[k]) + LBLatencyHidingSourceLinesC[k]; - sub_vp_lines_c = src_y_pstate_c + src_y_ahead_c + meta_row_height_chroma[k]; + sub_vp_lines_c = src_y_pstate_c + src_y_ahead_c + v->meta_row_height_chroma[k]; SubViewportLinesNeededInMALL[k] = dml_max(sub_vp_lines_l, sub_vp_lines_c); #ifdef __DML_VBA_DEBUG__ dml_print("DML::%s: k=%d, src_y_pstate_c = %d\n", __func__, k, src_y_pstate_c); dml_print("DML::%s: k=%d, src_y_ahead_c = %d\n", __func__, k, src_y_ahead_c); -dml_print("DML::%s: k=%d, meta_row_height_chroma = %d\n", __func__, k, meta_row_height_chroma[k]); +dml_print("DML::%s: k=%d, v->meta_row_height_chroma = %d\n", __func__, k, v->meta_row_height_chroma[k]); dml_print("DML::%s: k=%d, sub_vp_lines_c = %d\n", __func__, k, sub_vp_lines_c); #endif } diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_util_32.h b/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_util_32.h index d293856ba906..924e361ad243 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_util_32.h +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_util_32.h @@ -30,6 +30,7 @@ #include "os_types.h" #include "../dc_features.h" #include "../display_mode_structs.h" +#include "dml/display_mode_vba.h" unsigned int dml32_dscceComputeDelay( unsigned int bpc, @@ -712,28 +713,14 @@ double dml32_CalculateExtraLatency( unsigned int HostVMMaxNonCachedPageTableLevels); bool dml32_CalculatePrefetchSchedule( + struct vba_vars_st *v, + unsigned int k, double HostVMInefficiencyFactor, DmlPipe *myPipe, unsigned int DSCDelay, - double DPPCLKDelaySubtotalPlusCNVCFormater, - double DPPCLKDelaySCL, - double DPPCLKDelaySCLLBOnly, - double DPPCLKDelayCNVCCursor, - double DISPCLKDelaySubtotal, unsigned int DPP_RECOUT_WIDTH, - enum output_format_class OutputFormat, - unsigned int MaxInterDCNTileRepeaters, unsigned int VStartup, unsigned int MaxVStartup, - unsigned int GPUVMPageTableLevels, - bool GPUVMEnable, - bool HostVMEnable, - unsigned int HostVMMaxNonCachedPageTableLevels, - double HostVMMinPageSize, - bool DynamicMetadataEnable, - bool DynamicMetadataVMEnabled, - int DynamicMetadataLinesBeforeActiveRequired, - unsigned int DynamicMetadataTransmittedBytes, double UrgentLatency, double UrgentExtraLatency, double TCalc, @@ -807,58 +794,28 @@ void dml32_CalculateFlipSchedule( bool *ImmediateFlipSupportedForPipe); void dml32_CalculateWatermarksMALLUseAndDRAMSpeedChangeSupport( - bool USRRetrainingRequiredFinal, - enum dm_use_mall_for_pstate_change_mode UseMALLForPStateChange[], + struct vba_vars_st *v, unsigned int PrefetchMode, - unsigned int NumberOfActiveSurfaces, - unsigned int MaxLineBufferLines, - unsigned int LineBufferSize, - unsigned int WritebackInterfaceBufferSize, double DCFCLK, double ReturnBW, - bool SynchronizeTimingsFinal, - bool SynchronizeDRRDisplaysForUCLKPStateChangeFinal, - bool DRRDisplay[], - unsigned int dpte_group_bytes[], - unsigned int meta_row_height[], - unsigned int meta_row_height_chroma[], SOCParametersList mmSOCParameters, - unsigned int WritebackChunkSize, double SOCCLK, double DCFClkDeepSleep, unsigned int DETBufferSizeY[], unsigned int DETBufferSizeC[], unsigned int SwathHeightY[], unsigned int SwathHeightC[], - unsigned int LBBitPerPixel[], double SwathWidthY[], double SwathWidthC[], - double HRatio[], - double HRatioChroma[], - unsigned int VTaps[], - unsigned int VTapsChroma[], - double VRatio[], - double VRatioChroma[], - unsigned int HTotal[], - unsigned int VTotal[], - unsigned int VActive[], - double PixelClock[], - unsigned int BlendingAndTiming[], unsigned int DPPPerSurface[], double BytePerPixelDETY[], double BytePerPixelDETC[], double DSTXAfterScaler[], double DSTYAfterScaler[], - bool WritebackEnable[], - enum source_format_class WritebackPixelFormat[], - double WritebackDestinationWidth[], - double WritebackDestinationHeight[], - double WritebackSourceHeight[], bool UnboundedRequestEnabled, unsigned int CompressedBufferSizeInkByte, /* Output */ - Watermarks *Watermark, enum clock_change_support *DRAMClockChangeSupport, double MaxActiveDRAMClockChangeLatencySupported[], unsigned int SubViewportLinesNeededInMALL[], diff --git a/drivers/gpu/drm/amd/display/dc/dml/display_mode_lib.c b/drivers/gpu/drm/amd/display/dc/dml/display_mode_lib.c index 5d27ff0ebb5f..f5400eda07a5 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/display_mode_lib.c +++ b/drivers/gpu/drm/amd/display/dc/dml/display_mode_lib.c @@ -35,6 +35,8 @@ #include "dcn30/display_rq_dlg_calc_30.h" #include "dcn31/display_mode_vba_31.h" #include "dcn31/display_rq_dlg_calc_31.h" +#include "dcn314/display_mode_vba_314.h" +#include "dcn314/display_rq_dlg_calc_314.h" #include "dcn32/display_mode_vba_32.h" #include "dcn32/display_rq_dlg_calc_32.h" #include "dml_logger.h" @@ -74,6 +76,13 @@ const struct dml_funcs dml31_funcs = { .rq_dlg_get_rq_reg = dml31_rq_dlg_get_rq_reg }; +const struct dml_funcs dml314_funcs = { + .validate = dml314_ModeSupportAndSystemConfigurationFull, + .recalculate = dml314_recalculate, + .rq_dlg_get_dlg_reg = dml314_rq_dlg_get_dlg_reg, + .rq_dlg_get_rq_reg = dml314_rq_dlg_get_rq_reg +}; + const struct dml_funcs dml32_funcs = { .validate = dml32_ModeSupportAndSystemConfigurationFull, .recalculate = dml32_recalculate, @@ -107,6 +116,9 @@ void dml_init_instance(struct display_mode_lib *lib, case DML_PROJECT_DCN31_FPGA: lib->funcs = dml31_funcs; break; + case DML_PROJECT_DCN314: + lib->funcs = dml314_funcs; + break; case DML_PROJECT_DCN32: lib->funcs = dml32_funcs; break; diff --git a/drivers/gpu/drm/amd/display/dc/dml/display_mode_lib.h b/drivers/gpu/drm/amd/display/dc/dml/display_mode_lib.h index 2bdd6ed22611..b1878a1440e2 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/display_mode_lib.h +++ b/drivers/gpu/drm/amd/display/dc/dml/display_mode_lib.h @@ -41,6 +41,7 @@ enum dml_project { DML_PROJECT_DCN30, DML_PROJECT_DCN31, DML_PROJECT_DCN31_FPGA, + DML_PROJECT_DCN314, DML_PROJECT_DCN32, }; diff --git a/drivers/gpu/drm/amd/display/dc/dml/display_mode_vba.h b/drivers/gpu/drm/amd/display/dc/dml/display_mode_vba.h index 492aec634b68..2051ddaa641a 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/display_mode_vba.h +++ b/drivers/gpu/drm/amd/display/dc/dml/display_mode_vba.h @@ -651,10 +651,10 @@ struct vba_vars_st { unsigned int OutputTypeAndRatePerState[DC__VOLTAGE_STATES][DC__NUM_DPP__MAX]; double RequiredDISPCLKPerSurface[DC__VOLTAGE_STATES][2][DC__NUM_DPP__MAX]; - unsigned int MicroTileHeightY[DC__NUM_DPP__MAX]; - unsigned int MicroTileHeightC[DC__NUM_DPP__MAX]; - unsigned int MicroTileWidthY[DC__NUM_DPP__MAX]; - unsigned int MicroTileWidthC[DC__NUM_DPP__MAX]; + unsigned int MacroTileHeightY[DC__NUM_DPP__MAX]; + unsigned int MacroTileHeightC[DC__NUM_DPP__MAX]; + unsigned int MacroTileWidthY[DC__NUM_DPP__MAX]; + unsigned int MacroTileWidthC[DC__NUM_DPP__MAX]; bool ImmediateFlipRequiredFinal; bool DCCProgrammingAssumesScanDirectionUnknownFinal; bool EnoughWritebackUnits; @@ -800,8 +800,6 @@ struct vba_vars_st { double PSCL_FACTOR[DC__NUM_DPP__MAX]; double PSCL_FACTOR_CHROMA[DC__NUM_DPP__MAX]; double MaximumVStartup[DC__VOLTAGE_STATES][2][DC__NUM_DPP__MAX]; - unsigned int MacroTileWidthY[DC__NUM_DPP__MAX]; - unsigned int MacroTileWidthC[DC__NUM_DPP__MAX]; double AlignedDCCMetaPitch[DC__NUM_DPP__MAX]; double AlignedYPitch[DC__NUM_DPP__MAX]; double AlignedCPitch[DC__NUM_DPP__MAX]; diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/clk_mgr.h b/drivers/gpu/drm/amd/display/dc/inc/hw/clk_mgr.h index 5d2b028e5dad..d9f1b0a4fbd4 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/hw/clk_mgr.h +++ b/drivers/gpu/drm/amd/display/dc/inc/hw/clk_mgr.h @@ -214,6 +214,7 @@ struct dummy_pstate_entry { struct clk_bw_params { unsigned int vram_type; unsigned int num_channels; + unsigned int dram_channel_width_bytes; unsigned int dispclk_vco_khz; unsigned int dc_mode_softmax_memclk; struct clk_limit_table clk_table; diff --git a/drivers/gpu/drm/amd/display/modules/color/color_gamma.c b/drivers/gpu/drm/amd/display/modules/color/color_gamma.c index 859ffd8725c5..04f7656906ca 100644 --- a/drivers/gpu/drm/amd/display/modules/color/color_gamma.c +++ b/drivers/gpu/drm/amd/display/modules/color/color_gamma.c @@ -1600,6 +1600,7 @@ static void interpolate_user_regamma(uint32_t hw_points_num, struct fixed31_32 lut2; struct fixed31_32 delta_lut; struct fixed31_32 delta_index; + const struct fixed31_32 one = dc_fixpt_from_int(1); i = 0; /* fixed_pt library has problems handling too small values */ @@ -1628,6 +1629,9 @@ static void interpolate_user_regamma(uint32_t hw_points_num, } else hw_x = coordinates_x[i].x; + if (dc_fixpt_le(one, hw_x)) + hw_x = one; + norm_x = dc_fixpt_mul(norm_factor, hw_x); index = dc_fixpt_floor(norm_x); if (index < 0 || index > 255) diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c index 6db67f082d91..644ea150e075 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c @@ -368,6 +368,17 @@ static void sienna_cichlid_check_bxco_support(struct smu_context *smu) smu_baco->platform_support = (val & RCC_BIF_STRAP0__STRAP_PX_CAPABLE_MASK) ? true : false; + + /* + * Disable BACO entry/exit completely on below SKUs to + * avoid hardware intermittent failures. + */ + if (((adev->pdev->device == 0x73A1) && + (adev->pdev->revision == 0x00)) || + ((adev->pdev->device == 0x73BF) && + (adev->pdev->revision == 0xCF))) + smu_baco->platform_support = false; + } } diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c index fcf24c540859..c422bf8a09b1 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c @@ -120,6 +120,7 @@ static struct cmn2asic_msg_mapping smu_v13_0_7_message_map[SMU_MSG_MAX_COUNT] = MSG_MAP(DisallowGfxOff, PPSMC_MSG_DisallowGfxOff, 0), MSG_MAP(Mode1Reset, PPSMC_MSG_Mode1Reset, 0), MSG_MAP(PrepareMp1ForUnload, PPSMC_MSG_PrepareMp1ForUnload, 0), + MSG_MAP(SetMGpuFanBoostLimitRpm, PPSMC_MSG_SetMGpuFanBoostLimitRpm, 0), }; static struct cmn2asic_mapping smu_v13_0_7_clk_map[SMU_CLK_COUNT] = { diff --git a/drivers/gpu/drm/drm_debugfs.c b/drivers/gpu/drm/drm_debugfs.c index 493922069c90..01ee3febb813 100644 --- a/drivers/gpu/drm/drm_debugfs.c +++ b/drivers/gpu/drm/drm_debugfs.c @@ -377,8 +377,8 @@ static int vrr_range_show(struct seq_file *m, void *data) if (connector->status != connector_status_connected) return -ENODEV; - seq_printf(m, "Min: %u\n", (u8)connector->display_info.monitor_range.min_vfreq); - seq_printf(m, "Max: %u\n", (u8)connector->display_info.monitor_range.max_vfreq); + seq_printf(m, "Min: %u\n", connector->display_info.monitor_range.min_vfreq); + seq_printf(m, "Max: %u\n", connector->display_info.monitor_range.max_vfreq); return 0; } diff --git a/drivers/gpu/drm/drm_edid.c b/drivers/gpu/drm/drm_edid.c index bbc25e3b7220..eaa819381281 100644 --- a/drivers/gpu/drm/drm_edid.c +++ b/drivers/gpu/drm/drm_edid.c @@ -5971,12 +5971,14 @@ static void drm_parse_cea_ext(struct drm_connector *connector, } static -void get_monitor_range(const struct detailed_timing *timing, - void *info_monitor_range) +void get_monitor_range(const struct detailed_timing *timing, void *c) { - struct drm_monitor_range_info *monitor_range = info_monitor_range; + struct detailed_mode_closure *closure = c; + struct drm_display_info *info = &closure->connector->display_info; + struct drm_monitor_range_info *monitor_range = &info->monitor_range; const struct detailed_non_pixel *data = &timing->data.other_data; const struct detailed_data_monitor_range *range = &data->data.range; + const struct edid *edid = closure->drm_edid->edid; if (!is_display_descriptor(timing, EDID_DETAIL_MONITOR_RANGE)) return; @@ -5992,18 +5994,28 @@ void get_monitor_range(const struct detailed_timing *timing, monitor_range->min_vfreq = range->min_vfreq; monitor_range->max_vfreq = range->max_vfreq; + + if (edid->revision >= 4) { + if (data->pad2 & DRM_EDID_RANGE_OFFSET_MIN_VFREQ) + monitor_range->min_vfreq += 255; + if (data->pad2 & DRM_EDID_RANGE_OFFSET_MAX_VFREQ) + monitor_range->max_vfreq += 255; + } } static void drm_get_monitor_range(struct drm_connector *connector, const struct drm_edid *drm_edid) { - struct drm_display_info *info = &connector->display_info; + const struct drm_display_info *info = &connector->display_info; + struct detailed_mode_closure closure = { + .connector = connector, + .drm_edid = drm_edid, + }; if (!version_greater(drm_edid, 1, 1)) return; - drm_for_each_detailed_block(drm_edid, get_monitor_range, - &info->monitor_range); + drm_for_each_detailed_block(drm_edid, get_monitor_range, &closure); DRM_DEBUG_KMS("Supported Monitor Refresh rate range is %d Hz - %d Hz\n", info->monitor_range.min_vfreq, diff --git a/drivers/gpu/drm/gma500/cdv_device.c b/drivers/gpu/drm/gma500/cdv_device.c index dd32b484dd82..ce96234f3df2 100644 --- a/drivers/gpu/drm/gma500/cdv_device.c +++ b/drivers/gpu/drm/gma500/cdv_device.c @@ -581,11 +581,9 @@ static const struct psb_offset cdv_regmap[2] = { static int cdv_chip_setup(struct drm_device *dev) { struct drm_psb_private *dev_priv = to_drm_psb_private(dev); - struct pci_dev *pdev = to_pci_dev(dev->dev); INIT_WORK(&dev_priv->hotplug_work, cdv_hotplug_work_func); - if (pci_enable_msi(pdev)) - dev_warn(dev->dev, "Enabling MSI failed!\n"); + dev_priv->use_msi = true; dev_priv->regmap = cdv_regmap; gma_get_core_freq(dev); psb_intel_opregion_init(dev); diff --git a/drivers/gpu/drm/gma500/gem.c b/drivers/gpu/drm/gma500/gem.c index dffe37490206..4b7627a72637 100644 --- a/drivers/gpu/drm/gma500/gem.c +++ b/drivers/gpu/drm/gma500/gem.c @@ -112,12 +112,12 @@ static void psb_gem_free_object(struct drm_gem_object *obj) { struct psb_gem_object *pobj = to_psb_gem_object(obj); - drm_gem_object_release(obj); - /* Undo the mmap pin if we are destroying the object */ if (pobj->mmapping) psb_gem_unpin(pobj); + drm_gem_object_release(obj); + WARN_ON(pobj->in_gart && !pobj->stolen); release_resource(&pobj->resource); diff --git a/drivers/gpu/drm/gma500/gma_display.c b/drivers/gpu/drm/gma500/gma_display.c index bd40c040a2c9..2f52eceda3a1 100644 --- a/drivers/gpu/drm/gma500/gma_display.c +++ b/drivers/gpu/drm/gma500/gma_display.c @@ -532,15 +532,18 @@ int gma_crtc_page_flip(struct drm_crtc *crtc, WARN_ON(drm_crtc_vblank_get(crtc) != 0); gma_crtc->page_flip_event = event; + spin_unlock_irqrestore(&dev->event_lock, flags); /* Call this locked if we want an event at vblank interrupt. */ ret = crtc_funcs->mode_set_base(crtc, crtc->x, crtc->y, old_fb); if (ret) { - gma_crtc->page_flip_event = NULL; - drm_crtc_vblank_put(crtc); + spin_lock_irqsave(&dev->event_lock, flags); + if (gma_crtc->page_flip_event) { + gma_crtc->page_flip_event = NULL; + drm_crtc_vblank_put(crtc); + } + spin_unlock_irqrestore(&dev->event_lock, flags); } - - spin_unlock_irqrestore(&dev->event_lock, flags); } else { ret = crtc_funcs->mode_set_base(crtc, crtc->x, crtc->y, old_fb); } diff --git a/drivers/gpu/drm/gma500/oaktrail_device.c b/drivers/gpu/drm/gma500/oaktrail_device.c index 5923a9c89312..f90e628cb482 100644 --- a/drivers/gpu/drm/gma500/oaktrail_device.c +++ b/drivers/gpu/drm/gma500/oaktrail_device.c @@ -501,12 +501,9 @@ static const struct psb_offset oaktrail_regmap[2] = { static int oaktrail_chip_setup(struct drm_device *dev) { struct drm_psb_private *dev_priv = to_drm_psb_private(dev); - struct pci_dev *pdev = to_pci_dev(dev->dev); int ret; - if (pci_enable_msi(pdev)) - dev_warn(dev->dev, "Enabling MSI failed!\n"); - + dev_priv->use_msi = true; dev_priv->regmap = oaktrail_regmap; ret = mid_chip_setup(dev); diff --git a/drivers/gpu/drm/gma500/power.c b/drivers/gpu/drm/gma500/power.c index b91de6d36e41..66873085d450 100644 --- a/drivers/gpu/drm/gma500/power.c +++ b/drivers/gpu/drm/gma500/power.c @@ -139,8 +139,6 @@ static void gma_suspend_pci(struct pci_dev *pdev) dev_priv->regs.saveBSM = bsm; pci_read_config_dword(pdev, 0xFC, &vbt); dev_priv->regs.saveVBT = vbt; - pci_read_config_dword(pdev, PSB_PCIx_MSI_ADDR_LOC, &dev_priv->msi_addr); - pci_read_config_dword(pdev, PSB_PCIx_MSI_DATA_LOC, &dev_priv->msi_data); pci_disable_device(pdev); pci_set_power_state(pdev, PCI_D3hot); @@ -168,9 +166,6 @@ static bool gma_resume_pci(struct pci_dev *pdev) pci_restore_state(pdev); pci_write_config_dword(pdev, 0x5c, dev_priv->regs.saveBSM); pci_write_config_dword(pdev, 0xFC, dev_priv->regs.saveVBT); - /* restoring MSI address and data in PCIx space */ - pci_write_config_dword(pdev, PSB_PCIx_MSI_ADDR_LOC, dev_priv->msi_addr); - pci_write_config_dword(pdev, PSB_PCIx_MSI_DATA_LOC, dev_priv->msi_data); ret = pci_enable_device(pdev); if (ret != 0) @@ -223,8 +218,7 @@ int gma_power_resume(struct device *_dev) mutex_lock(&power_mutex); gma_resume_pci(pdev); gma_resume_display(pdev); - gma_irq_preinstall(dev); - gma_irq_postinstall(dev); + gma_irq_install(dev); mutex_unlock(&power_mutex); return 0; } diff --git a/drivers/gpu/drm/gma500/psb_drv.c b/drivers/gpu/drm/gma500/psb_drv.c index 1d8744f3e702..54e756b48606 100644 --- a/drivers/gpu/drm/gma500/psb_drv.c +++ b/drivers/gpu/drm/gma500/psb_drv.c @@ -383,7 +383,7 @@ static int psb_driver_load(struct drm_device *dev, unsigned long flags) PSB_WVDC32(0xFFFFFFFF, PSB_INT_MASK_R); spin_unlock_irqrestore(&dev_priv->irqmask_lock, irqflags); - gma_irq_install(dev, pdev->irq); + gma_irq_install(dev); dev->max_vblank_count = 0xffffff; /* only 24 bits of frame count */ diff --git a/drivers/gpu/drm/gma500/psb_drv.h b/drivers/gpu/drm/gma500/psb_drv.h index 0ea3d23575f3..731cc356c07a 100644 --- a/drivers/gpu/drm/gma500/psb_drv.h +++ b/drivers/gpu/drm/gma500/psb_drv.h @@ -490,6 +490,7 @@ struct drm_psb_private { int rpm_enabled; /* MID specific */ + bool use_msi; bool has_gct; struct oaktrail_gct_data gct_data; @@ -499,10 +500,6 @@ struct drm_psb_private { /* Register state */ struct psb_save_area regs; - /* MSI reg save */ - uint32_t msi_addr; - uint32_t msi_data; - /* Hotplug handling */ struct work_struct hotplug_work; diff --git a/drivers/gpu/drm/gma500/psb_irq.c b/drivers/gpu/drm/gma500/psb_irq.c index e6e6d61bbeab..038f18ed0a95 100644 --- a/drivers/gpu/drm/gma500/psb_irq.c +++ b/drivers/gpu/drm/gma500/psb_irq.c @@ -316,17 +316,24 @@ void gma_irq_postinstall(struct drm_device *dev) spin_unlock_irqrestore(&dev_priv->irqmask_lock, irqflags); } -int gma_irq_install(struct drm_device *dev, unsigned int irq) +int gma_irq_install(struct drm_device *dev) { + struct drm_psb_private *dev_priv = to_drm_psb_private(dev); + struct pci_dev *pdev = to_pci_dev(dev->dev); int ret; - if (irq == IRQ_NOTCONNECTED) + if (dev_priv->use_msi && pci_enable_msi(pdev)) { + dev_warn(dev->dev, "Enabling MSI failed!\n"); + dev_priv->use_msi = false; + } + + if (pdev->irq == IRQ_NOTCONNECTED) return -ENOTCONN; gma_irq_preinstall(dev); /* PCI devices require shared interrupts. */ - ret = request_irq(irq, gma_irq_handler, IRQF_SHARED, dev->driver->name, dev); + ret = request_irq(pdev->irq, gma_irq_handler, IRQF_SHARED, dev->driver->name, dev); if (ret) return ret; @@ -369,6 +376,8 @@ void gma_irq_uninstall(struct drm_device *dev) spin_unlock_irqrestore(&dev_priv->irqmask_lock, irqflags); free_irq(pdev->irq, dev); + if (dev_priv->use_msi) + pci_disable_msi(pdev); } int gma_crtc_enable_vblank(struct drm_crtc *crtc) diff --git a/drivers/gpu/drm/gma500/psb_irq.h b/drivers/gpu/drm/gma500/psb_irq.h index b51e395194ff..7648f69824a5 100644 --- a/drivers/gpu/drm/gma500/psb_irq.h +++ b/drivers/gpu/drm/gma500/psb_irq.h @@ -17,7 +17,7 @@ struct drm_device; void gma_irq_preinstall(struct drm_device *dev); void gma_irq_postinstall(struct drm_device *dev); -int gma_irq_install(struct drm_device *dev, unsigned int irq); +int gma_irq_install(struct drm_device *dev); void gma_irq_uninstall(struct drm_device *dev); int gma_crtc_enable_vblank(struct drm_crtc *crtc); diff --git a/drivers/gpu/drm/hyperv/hyperv_drm_drv.c b/drivers/gpu/drm/hyperv/hyperv_drm_drv.c index 6d11e7938c83..f84d39762a72 100644 --- a/drivers/gpu/drm/hyperv/hyperv_drm_drv.c +++ b/drivers/gpu/drm/hyperv/hyperv_drm_drv.c @@ -23,9 +23,6 @@ #define DRIVER_MAJOR 1 #define DRIVER_MINOR 0 -#define PCI_VENDOR_ID_MICROSOFT 0x1414 -#define PCI_DEVICE_ID_HYPERV_VIDEO 0x5353 - DEFINE_DRM_GEM_FOPS(hv_fops); static struct drm_driver hyperv_driver = { @@ -133,7 +130,6 @@ static int hyperv_vmbus_probe(struct hv_device *hdev, } ret = hyperv_setup_vram(hv, hdev); - if (ret) goto err_vmbus_close; @@ -150,18 +146,20 @@ static int hyperv_vmbus_probe(struct hv_device *hdev, ret = hyperv_mode_config_init(hv); if (ret) - goto err_vmbus_close; + goto err_free_mmio; ret = drm_dev_register(dev, 0); if (ret) { drm_err(dev, "Failed to register drm driver.\n"); - goto err_vmbus_close; + goto err_free_mmio; } drm_fbdev_generic_setup(dev, 0); return 0; +err_free_mmio: + vmbus_free_mmio(hv->mem->start, hv->fb_size); err_vmbus_close: vmbus_close(hdev->channel); err_hv_set_drv_data: diff --git a/drivers/gpu/drm/i915/display/icl_dsi.c b/drivers/gpu/drm/i915/display/icl_dsi.c index 885c74f60366..1390729401a0 100644 --- a/drivers/gpu/drm/i915/display/icl_dsi.c +++ b/drivers/gpu/drm/i915/display/icl_dsi.c @@ -1629,6 +1629,8 @@ static int gen11_dsi_dsc_compute_config(struct intel_encoder *encoder, /* FIXME: initialize from VBT */ vdsc_cfg->rc_model_size = DSC_RC_MODEL_SIZE_CONST; + vdsc_cfg->pic_height = crtc_state->hw.adjusted_mode.crtc_vdisplay; + ret = intel_dsc_compute_params(crtc_state); if (ret) return ret; diff --git a/drivers/gpu/drm/i915/display/intel_bios.c b/drivers/gpu/drm/i915/display/intel_bios.c index 198a2f4920cc..7d6eb9ad7a02 100644 --- a/drivers/gpu/drm/i915/display/intel_bios.c +++ b/drivers/gpu/drm/i915/display/intel_bios.c @@ -479,6 +479,13 @@ init_bdb_block(struct drm_i915_private *i915, block_size = get_blocksize(block); + /* + * Version number and new block size are considered + * part of the header for MIPI sequenece block v3+. + */ + if (section_id == BDB_MIPI_SEQUENCE && *(const u8 *)block >= 3) + block_size += 5; + entry = kzalloc(struct_size(entry, data, max(min_size, block_size) + 3), GFP_KERNEL); if (!entry) { diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c index ac90d455a7c7..3ed7eeacc706 100644 --- a/drivers/gpu/drm/i915/display/intel_dp.c +++ b/drivers/gpu/drm/i915/display/intel_dp.c @@ -389,23 +389,13 @@ static int dg2_max_source_rate(struct intel_dp *intel_dp) return intel_dp_is_edp(intel_dp) ? 810000 : 1350000; } -static bool is_low_voltage_sku(struct drm_i915_private *i915, enum phy phy) -{ - u32 voltage; - - voltage = intel_de_read(i915, ICL_PORT_COMP_DW3(phy)) & VOLTAGE_INFO_MASK; - - return voltage == VOLTAGE_INFO_0_85V; -} - static int icl_max_source_rate(struct intel_dp *intel_dp) { struct intel_digital_port *dig_port = dp_to_dig_port(intel_dp); struct drm_i915_private *dev_priv = to_i915(dig_port->base.base.dev); enum phy phy = intel_port_to_phy(dev_priv, dig_port->base.port); - if (intel_phy_is_combo(dev_priv, phy) && - (is_low_voltage_sku(dev_priv, phy) || !intel_dp_is_edp(intel_dp))) + if (intel_phy_is_combo(dev_priv, phy) && !intel_dp_is_edp(intel_dp)) return 540000; return 810000; @@ -413,23 +403,7 @@ static int icl_max_source_rate(struct intel_dp *intel_dp) static int ehl_max_source_rate(struct intel_dp *intel_dp) { - struct intel_digital_port *dig_port = dp_to_dig_port(intel_dp); - struct drm_i915_private *dev_priv = to_i915(dig_port->base.base.dev); - enum phy phy = intel_port_to_phy(dev_priv, dig_port->base.port); - - if (intel_dp_is_edp(intel_dp) || is_low_voltage_sku(dev_priv, phy)) - return 540000; - - return 810000; -} - -static int dg1_max_source_rate(struct intel_dp *intel_dp) -{ - struct intel_digital_port *dig_port = dp_to_dig_port(intel_dp); - struct drm_i915_private *i915 = to_i915(dig_port->base.base.dev); - enum phy phy = intel_port_to_phy(i915, dig_port->base.port); - - if (intel_phy_is_combo(i915, phy) && is_low_voltage_sku(i915, phy)) + if (intel_dp_is_edp(intel_dp)) return 540000; return 810000; @@ -491,7 +465,7 @@ intel_dp_set_source_rates(struct intel_dp *intel_dp) max_rate = dg2_max_source_rate(intel_dp); else if (IS_ALDERLAKE_P(dev_priv) || IS_ALDERLAKE_S(dev_priv) || IS_DG1(dev_priv) || IS_ROCKETLAKE(dev_priv)) - max_rate = dg1_max_source_rate(intel_dp); + max_rate = 810000; else if (IS_JSL_EHL(dev_priv)) max_rate = ehl_max_source_rate(intel_dp); else @@ -1395,6 +1369,7 @@ static int intel_dp_dsc_compute_params(struct intel_encoder *encoder, * DP_DSC_RC_BUF_SIZE for this. */ vdsc_cfg->rc_model_size = DSC_RC_MODEL_SIZE_CONST; + vdsc_cfg->pic_height = crtc_state->hw.adjusted_mode.crtc_vdisplay; /* * Slice Height of 8 works for all currently available panels. So start diff --git a/drivers/gpu/drm/i915/display/intel_dp_link_training.c b/drivers/gpu/drm/i915/display/intel_dp_link_training.c index 9feaf1a589f3..d213d8ad1ea5 100644 --- a/drivers/gpu/drm/i915/display/intel_dp_link_training.c +++ b/drivers/gpu/drm/i915/display/intel_dp_link_training.c @@ -671,6 +671,28 @@ intel_dp_prepare_link_train(struct intel_dp *intel_dp, intel_dp_compute_rate(intel_dp, crtc_state->port_clock, &link_bw, &rate_select); + /* + * WaEdpLinkRateDataReload + * + * Parade PS8461E MUX (used on varius TGL+ laptops) needs + * to snoop the link rates reported by the sink when we + * use LINK_RATE_SET in order to operate in jitter cleaning + * mode (as opposed to redriver mode). Unfortunately it + * loses track of the snooped link rates when powered down, + * so we need to make it re-snoop often. Without this high + * link rates are not stable. + */ + if (!link_bw) { + struct intel_connector *connector = intel_dp->attached_connector; + __le16 sink_rates[DP_MAX_SUPPORTED_RATES]; + + drm_dbg_kms(&i915->drm, "[CONNECTOR:%d:%s] Reloading eDP link rates\n", + connector->base.base.id, connector->base.name); + + drm_dp_dpcd_read(&intel_dp->aux, DP_SUPPORTED_LINK_RATES, + sink_rates, sizeof(sink_rates)); + } + if (link_bw) drm_dbg_kms(&i915->drm, "[ENCODER:%d:%s] Using LINK_BW_SET value %02x\n", diff --git a/drivers/gpu/drm/i915/display/intel_vdsc.c b/drivers/gpu/drm/i915/display/intel_vdsc.c index 43e1bbc1e303..ca530f0733e0 100644 --- a/drivers/gpu/drm/i915/display/intel_vdsc.c +++ b/drivers/gpu/drm/i915/display/intel_vdsc.c @@ -460,7 +460,6 @@ int intel_dsc_compute_params(struct intel_crtc_state *pipe_config) u8 i = 0; vdsc_cfg->pic_width = pipe_config->hw.adjusted_mode.crtc_hdisplay; - vdsc_cfg->pic_height = pipe_config->hw.adjusted_mode.crtc_vdisplay; vdsc_cfg->slice_width = DIV_ROUND_UP(vdsc_cfg->pic_width, pipe_config->dsc.slice_count); diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object.c b/drivers/gpu/drm/i915/gem/i915_gem_object.c index 389e9f157ca5..85482a04d158 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_object.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_object.c @@ -723,6 +723,9 @@ bool i915_gem_object_needs_ccs_pages(struct drm_i915_gem_object *obj) bool lmem_placement = false; int i; + if (!HAS_FLAT_CCS(to_i915(obj->base.dev))) + return false; + for (i = 0; i < obj->mm.n_placements; i++) { /* Compression is not allowed for the objects with smem placement */ if (obj->mm.placements[i]->type == INTEL_MEMORY_SYSTEM) diff --git a/drivers/gpu/drm/i915/gem/i915_gem_ttm.c b/drivers/gpu/drm/i915/gem/i915_gem_ttm.c index f131dc065f47..6f3ab7ade41a 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_ttm.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_ttm.c @@ -297,7 +297,7 @@ static struct ttm_tt *i915_ttm_tt_create(struct ttm_buffer_object *bo, i915_tt->is_shmem = true; } - if (HAS_FLAT_CCS(i915) && i915_gem_object_needs_ccs_pages(obj)) + if (i915_gem_object_needs_ccs_pages(obj)) ccs_pages = DIV_ROUND_UP(DIV_ROUND_UP(bo->base.size, NUM_BYTES_PER_CCS_BYTE), PAGE_SIZE); diff --git a/drivers/gpu/drm/i915/gt/intel_llc.c b/drivers/gpu/drm/i915/gt/intel_llc.c index 14fe65812e42..1d19c073ba2e 100644 --- a/drivers/gpu/drm/i915/gt/intel_llc.c +++ b/drivers/gpu/drm/i915/gt/intel_llc.c @@ -12,6 +12,7 @@ #include "intel_llc.h" #include "intel_mchbar_regs.h" #include "intel_pcode.h" +#include "intel_rps.h" struct ia_constants { unsigned int min_gpu_freq; @@ -55,9 +56,6 @@ static bool get_ia_constants(struct intel_llc *llc, if (!HAS_LLC(i915) || IS_DGFX(i915)) return false; - if (rps->max_freq <= rps->min_freq) - return false; - consts->max_ia_freq = cpu_max_MHz(); consts->min_ring_freq = @@ -65,13 +63,8 @@ static bool get_ia_constants(struct intel_llc *llc, /* convert DDR frequency from units of 266.6MHz to bandwidth */ consts->min_ring_freq = mult_frac(consts->min_ring_freq, 8, 3); - consts->min_gpu_freq = rps->min_freq; - consts->max_gpu_freq = rps->max_freq; - if (GRAPHICS_VER(i915) >= 9) { - /* Convert GT frequency to 50 HZ units */ - consts->min_gpu_freq /= GEN9_FREQ_SCALER; - consts->max_gpu_freq /= GEN9_FREQ_SCALER; - } + consts->min_gpu_freq = intel_rps_get_min_raw_freq(rps); + consts->max_gpu_freq = intel_rps_get_max_raw_freq(rps); return true; } @@ -131,6 +124,12 @@ static void gen6_update_ring_freq(struct intel_llc *llc) return; /* + * Although this is unlikely on any platform during initialization, + * let's ensure we don't get accidentally into infinite loop + */ + if (consts.max_gpu_freq <= consts.min_gpu_freq) + return; + /* * For each potential GPU frequency, load a ring frequency we'd like * to use for memory access. We do this by specifying the IA frequency * the PCU should use as a reference to determine the ring frequency. diff --git a/drivers/gpu/drm/i915/gt/intel_rps.c b/drivers/gpu/drm/i915/gt/intel_rps.c index fb3f57ee450b..7bb967034679 100644 --- a/drivers/gpu/drm/i915/gt/intel_rps.c +++ b/drivers/gpu/drm/i915/gt/intel_rps.c @@ -2126,6 +2126,31 @@ u32 intel_rps_get_max_frequency(struct intel_rps *rps) return intel_gpu_freq(rps, rps->max_freq_softlimit); } +/** + * intel_rps_get_max_raw_freq - returns the max frequency in some raw format. + * @rps: the intel_rps structure + * + * Returns the max frequency in a raw format. In newer platforms raw is in + * units of 50 MHz. + */ +u32 intel_rps_get_max_raw_freq(struct intel_rps *rps) +{ + struct intel_guc_slpc *slpc = rps_to_slpc(rps); + u32 freq; + + if (rps_uses_slpc(rps)) { + return DIV_ROUND_CLOSEST(slpc->rp0_freq, + GT_FREQUENCY_MULTIPLIER); + } else { + freq = rps->max_freq; + if (GRAPHICS_VER(rps_to_i915(rps)) >= 9) { + /* Convert GT frequency to 50 MHz units */ + freq /= GEN9_FREQ_SCALER; + } + return freq; + } +} + u32 intel_rps_get_rp0_frequency(struct intel_rps *rps) { struct intel_guc_slpc *slpc = rps_to_slpc(rps); @@ -2214,6 +2239,31 @@ u32 intel_rps_get_min_frequency(struct intel_rps *rps) return intel_gpu_freq(rps, rps->min_freq_softlimit); } +/** + * intel_rps_get_min_raw_freq - returns the min frequency in some raw format. + * @rps: the intel_rps structure + * + * Returns the min frequency in a raw format. In newer platforms raw is in + * units of 50 MHz. + */ +u32 intel_rps_get_min_raw_freq(struct intel_rps *rps) +{ + struct intel_guc_slpc *slpc = rps_to_slpc(rps); + u32 freq; + + if (rps_uses_slpc(rps)) { + return DIV_ROUND_CLOSEST(slpc->min_freq, + GT_FREQUENCY_MULTIPLIER); + } else { + freq = rps->min_freq; + if (GRAPHICS_VER(rps_to_i915(rps)) >= 9) { + /* Convert GT frequency to 50 MHz units */ + freq /= GEN9_FREQ_SCALER; + } + return freq; + } +} + static int set_min_freq(struct intel_rps *rps, u32 val) { int ret = 0; diff --git a/drivers/gpu/drm/i915/gt/intel_rps.h b/drivers/gpu/drm/i915/gt/intel_rps.h index 1e8d56491308..4509dfdc52e0 100644 --- a/drivers/gpu/drm/i915/gt/intel_rps.h +++ b/drivers/gpu/drm/i915/gt/intel_rps.h @@ -37,8 +37,10 @@ u32 intel_rps_get_cagf(struct intel_rps *rps, u32 rpstat1); u32 intel_rps_read_actual_frequency(struct intel_rps *rps); u32 intel_rps_get_requested_frequency(struct intel_rps *rps); u32 intel_rps_get_min_frequency(struct intel_rps *rps); +u32 intel_rps_get_min_raw_freq(struct intel_rps *rps); int intel_rps_set_min_frequency(struct intel_rps *rps, u32 val); u32 intel_rps_get_max_frequency(struct intel_rps *rps); +u32 intel_rps_get_max_raw_freq(struct intel_rps *rps); int intel_rps_set_max_frequency(struct intel_rps *rps, u32 val); u32 intel_rps_get_rp0_frequency(struct intel_rps *rps); u32 intel_rps_get_rp1_frequency(struct intel_rps *rps); diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c index 834c707d1877..3e91f44829e9 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c @@ -1438,7 +1438,12 @@ void intel_guc_busyness_park(struct intel_gt *gt) if (!guc_submission_initialized(guc)) return; - cancel_delayed_work(&guc->timestamp.work); + /* + * There is a race with suspend flow where the worker runs after suspend + * and causes an unclaimed register access warning. Cancel the worker + * synchronously here. + */ + cancel_delayed_work_sync(&guc->timestamp.work); /* * Before parking, we should sample engine busyness stats if we need to. diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index 3168d7007e10..135d04c2d41c 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -1857,14 +1857,14 @@ #define GT0_PERF_LIMIT_REASONS _MMIO(0x1381a8) #define GT0_PERF_LIMIT_REASONS_MASK 0xde3 -#define PROCHOT_MASK REG_BIT(1) -#define THERMAL_LIMIT_MASK REG_BIT(2) -#define RATL_MASK REG_BIT(6) -#define VR_THERMALERT_MASK REG_BIT(7) -#define VR_TDC_MASK REG_BIT(8) -#define POWER_LIMIT_4_MASK REG_BIT(9) -#define POWER_LIMIT_1_MASK REG_BIT(11) -#define POWER_LIMIT_2_MASK REG_BIT(12) +#define PROCHOT_MASK REG_BIT(0) +#define THERMAL_LIMIT_MASK REG_BIT(1) +#define RATL_MASK REG_BIT(5) +#define VR_THERMALERT_MASK REG_BIT(6) +#define VR_TDC_MASK REG_BIT(7) +#define POWER_LIMIT_4_MASK REG_BIT(8) +#define POWER_LIMIT_1_MASK REG_BIT(10) +#define POWER_LIMIT_2_MASK REG_BIT(11) #define CHV_CLK_CTL1 _MMIO(0x101100) #define VLV_CLK_CTL2 _MMIO(0x101104) diff --git a/drivers/gpu/drm/i915/i915_vma.c b/drivers/gpu/drm/i915/i915_vma.c index 260371716490..373582cfd8f3 100644 --- a/drivers/gpu/drm/i915/i915_vma.c +++ b/drivers/gpu/drm/i915/i915_vma.c @@ -1882,12 +1882,13 @@ int _i915_vma_move_to_active(struct i915_vma *vma, enum dma_resv_usage usage; int idx; - obj->read_domains = 0; if (flags & EXEC_OBJECT_WRITE) { usage = DMA_RESV_USAGE_WRITE; obj->write_domain = I915_GEM_DOMAIN_RENDER; + obj->read_domains = 0; } else { usage = DMA_RESV_USAGE_READ; + obj->write_domain = 0; } dma_fence_array_for_each(curr, idx, fence) diff --git a/drivers/gpu/drm/meson/meson_plane.c b/drivers/gpu/drm/meson/meson_plane.c index b9ac932af8d0..03acc68abf2c 100644 --- a/drivers/gpu/drm/meson/meson_plane.c +++ b/drivers/gpu/drm/meson/meson_plane.c @@ -170,7 +170,7 @@ static void meson_plane_atomic_update(struct drm_plane *plane, /* Enable OSD and BLK0, set max global alpha */ priv->viu.osd1_ctrl_stat = OSD_ENABLE | - (0xFF << OSD_GLOBAL_ALPHA_SHIFT) | + (0x100 << OSD_GLOBAL_ALPHA_SHIFT) | OSD_BLK0_ENABLE; priv->viu.osd1_ctrl_stat2 = readl(priv->io_base + diff --git a/drivers/gpu/drm/meson/meson_viu.c b/drivers/gpu/drm/meson/meson_viu.c index bb7e109534de..d4b907889a21 100644 --- a/drivers/gpu/drm/meson/meson_viu.c +++ b/drivers/gpu/drm/meson/meson_viu.c @@ -94,7 +94,7 @@ static void meson_viu_set_g12a_osd1_matrix(struct meson_drm *priv, priv->io_base + _REG(VPP_WRAP_OSD1_MATRIX_COEF11_12)); writel(((m[9] & 0x1fff) << 16) | (m[10] & 0x1fff), priv->io_base + _REG(VPP_WRAP_OSD1_MATRIX_COEF20_21)); - writel((m[11] & 0x1fff) << 16, + writel((m[11] & 0x1fff), priv->io_base + _REG(VPP_WRAP_OSD1_MATRIX_COEF22)); writel(((m[18] & 0xfff) << 16) | (m[19] & 0xfff), diff --git a/drivers/gpu/drm/panel/panel-edp.c b/drivers/gpu/drm/panel/panel-edp.c index cdb154c8b866..b75c690bb0cc 100644 --- a/drivers/gpu/drm/panel/panel-edp.c +++ b/drivers/gpu/drm/panel/panel-edp.c @@ -1295,7 +1295,8 @@ static const struct panel_desc innolux_n116bca_ea1 = { }, .delay = { .hpd_absent = 200, - .prepare_to_enable = 80, + .enable = 80, + .disable = 50, .unprepare = 500, }, }; diff --git a/drivers/gpu/drm/panfrost/panfrost_devfreq.c b/drivers/gpu/drm/panfrost/panfrost_devfreq.c index 5110cd9b2425..fe5f12f16a63 100644 --- a/drivers/gpu/drm/panfrost/panfrost_devfreq.c +++ b/drivers/gpu/drm/panfrost/panfrost_devfreq.c @@ -131,6 +131,17 @@ int panfrost_devfreq_init(struct panfrost_device *pfdev) return PTR_ERR(opp); panfrost_devfreq_profile.initial_freq = cur_freq; + + /* + * Set the recommend OPP this will enable and configure the regulator + * if any and will avoid a switch off by regulator_late_cleanup() + */ + ret = dev_pm_opp_set_opp(dev, opp); + if (ret) { + DRM_DEV_ERROR(dev, "Couldn't set recommended OPP\n"); + return ret; + } + dev_pm_opp_put(opp); /* diff --git a/drivers/gpu/drm/rockchip/cdn-dp-core.c b/drivers/gpu/drm/rockchip/cdn-dp-core.c index c204e9b95c1f..518ee13b1d6f 100644 --- a/drivers/gpu/drm/rockchip/cdn-dp-core.c +++ b/drivers/gpu/drm/rockchip/cdn-dp-core.c @@ -283,8 +283,9 @@ static int cdn_dp_connector_get_modes(struct drm_connector *connector) return ret; } -static int cdn_dp_connector_mode_valid(struct drm_connector *connector, - struct drm_display_mode *mode) +static enum drm_mode_status +cdn_dp_connector_mode_valid(struct drm_connector *connector, + struct drm_display_mode *mode) { struct cdn_dp_device *dp = connector_to_dp(connector); struct drm_display_info *display_info = &dp->connector.display_info; diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_vop2.c b/drivers/gpu/drm/rockchip/rockchip_drm_vop2.c index e4631f515ba4..f9aa8b96c695 100644 --- a/drivers/gpu/drm/rockchip/rockchip_drm_vop2.c +++ b/drivers/gpu/drm/rockchip/rockchip_drm_vop2.c @@ -1439,11 +1439,15 @@ static void rk3568_set_intf_mux(struct vop2_video_port *vp, int id, die &= ~RK3568_SYS_DSP_INFACE_EN_HDMI_MUX; die |= RK3568_SYS_DSP_INFACE_EN_HDMI | FIELD_PREP(RK3568_SYS_DSP_INFACE_EN_HDMI_MUX, vp->id); + dip &= ~RK3568_DSP_IF_POL__HDMI_PIN_POL; + dip |= FIELD_PREP(RK3568_DSP_IF_POL__HDMI_PIN_POL, polflags); break; case ROCKCHIP_VOP2_EP_EDP0: die &= ~RK3568_SYS_DSP_INFACE_EN_EDP_MUX; die |= RK3568_SYS_DSP_INFACE_EN_EDP | FIELD_PREP(RK3568_SYS_DSP_INFACE_EN_EDP_MUX, vp->id); + dip &= ~RK3568_DSP_IF_POL__EDP_PIN_POL; + dip |= FIELD_PREP(RK3568_DSP_IF_POL__EDP_PIN_POL, polflags); break; case ROCKCHIP_VOP2_EP_MIPI0: die &= ~RK3568_SYS_DSP_INFACE_EN_MIPI0_MUX; diff --git a/drivers/gpu/drm/ttm/ttm_bo_util.c b/drivers/gpu/drm/ttm/ttm_bo_util.c index 1cbfb00c1d65..911141d16e95 100644 --- a/drivers/gpu/drm/ttm/ttm_bo_util.c +++ b/drivers/gpu/drm/ttm/ttm_bo_util.c @@ -236,16 +236,19 @@ static int ttm_buffer_object_transfer(struct ttm_buffer_object *bo, if (bo->type != ttm_bo_type_sg) fbo->base.base.resv = &fbo->base.base._resv; - if (fbo->base.resource) { - ttm_resource_set_bo(fbo->base.resource, &fbo->base); - bo->resource = NULL; - } - dma_resv_init(&fbo->base.base._resv); fbo->base.base.dev = NULL; ret = dma_resv_trylock(&fbo->base.base._resv); WARN_ON(!ret); + if (fbo->base.resource) { + ttm_resource_set_bo(fbo->base.resource, &fbo->base); + bo->resource = NULL; + ttm_bo_set_bulk_move(&fbo->base, NULL); + } else { + fbo->base.bulk_move = NULL; + } + ret = dma_resv_reserve_fences(&fbo->base.base._resv, 1); if (ret) { kfree(fbo); diff --git a/drivers/hv/hv_fcopy.c b/drivers/hv/hv_fcopy.c index 660036da7449..922d83eb7ddf 100644 --- a/drivers/hv/hv_fcopy.c +++ b/drivers/hv/hv_fcopy.c @@ -129,7 +129,7 @@ static void fcopy_send_data(struct work_struct *dummy) /* * The strings sent from the host are encoded in - * in utf16; convert it to utf8 strings. + * utf16; convert it to utf8 strings. * The host assures us that the utf16 strings will not exceed * the max lengths specified. We will however, reserve room * for the string terminating character - in the utf16s_utf8s() diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c index 23c680d1a0f5..3c833ea60db6 100644 --- a/drivers/hv/vmbus_drv.c +++ b/drivers/hv/vmbus_drv.c @@ -35,6 +35,7 @@ #include <linux/kernel.h> #include <linux/syscore_ops.h> #include <linux/dma-map-ops.h> +#include <linux/pci.h> #include <clocksource/hyperv_timer.h> #include "hyperv_vmbus.h" @@ -2262,26 +2263,43 @@ static int vmbus_acpi_remove(struct acpi_device *device) static void vmbus_reserve_fb(void) { - int size; + resource_size_t start = 0, size; + struct pci_dev *pdev; + + if (efi_enabled(EFI_BOOT)) { + /* Gen2 VM: get FB base from EFI framebuffer */ + start = screen_info.lfb_base; + size = max_t(__u32, screen_info.lfb_size, 0x800000); + } else { + /* Gen1 VM: get FB base from PCI */ + pdev = pci_get_device(PCI_VENDOR_ID_MICROSOFT, + PCI_DEVICE_ID_HYPERV_VIDEO, NULL); + if (!pdev) + return; + + if (pdev->resource[0].flags & IORESOURCE_MEM) { + start = pci_resource_start(pdev, 0); + size = pci_resource_len(pdev, 0); + } + + /* + * Release the PCI device so hyperv_drm or hyperv_fb driver can + * grab it later. + */ + pci_dev_put(pdev); + } + + if (!start) + return; + /* * Make a claim for the frame buffer in the resource tree under the * first node, which will be the one below 4GB. The length seems to * be underreported, particularly in a Generation 1 VM. So start out * reserving a larger area and make it smaller until it succeeds. */ - - if (screen_info.lfb_base) { - if (efi_enabled(EFI_BOOT)) - size = max_t(__u32, screen_info.lfb_size, 0x800000); - else - size = max_t(__u32, screen_info.lfb_size, 0x4000000); - - for (; !fb_mmio && (size >= 0x100000); size >>= 1) { - fb_mmio = __request_region(hyperv_mmio, - screen_info.lfb_base, size, - fb_mmio_name, 0); - } - } + for (; !fb_mmio && (size >= 0x100000); size >>= 1) + fb_mmio = __request_region(hyperv_mmio, start, size, fb_mmio_name, 0); } /** @@ -2313,7 +2331,7 @@ int vmbus_allocate_mmio(struct resource **new, struct hv_device *device_obj, bool fb_overlap_ok) { struct resource *iter, *shadow; - resource_size_t range_min, range_max, start; + resource_size_t range_min, range_max, start, end; const char *dev_n = dev_name(&device_obj->device); int retval; @@ -2348,6 +2366,14 @@ int vmbus_allocate_mmio(struct resource **new, struct hv_device *device_obj, range_max = iter->end; start = (range_min + align - 1) & ~(align - 1); for (; start + size - 1 <= range_max; start += align) { + end = start + size - 1; + + /* Skip the whole fb_mmio region if not fb_overlap_ok */ + if (!fb_overlap_ok && fb_mmio && + (((start >= fb_mmio->start) && (start <= fb_mmio->end)) || + ((end >= fb_mmio->start) && (end <= fb_mmio->end)))) + continue; + shadow = __request_region(iter, start, size, NULL, IORESOURCE_BUSY); if (!shadow) diff --git a/drivers/hwmon/asus-ec-sensors.c b/drivers/hwmon/asus-ec-sensors.c index 61a4684fc020..81e688975c6a 100644 --- a/drivers/hwmon/asus-ec-sensors.c +++ b/drivers/hwmon/asus-ec-sensors.c @@ -266,9 +266,7 @@ static const struct ec_sensor_info sensors_family_intel_600[] = { #define SENSOR_SET_WATER_BLOCK \ (SENSOR_TEMP_WATER_BLOCK_IN | SENSOR_TEMP_WATER_BLOCK_OUT) - struct ec_board_info { - const char *board_names[MAX_IDENTICAL_BOARD_VARIATIONS]; unsigned long sensors; /* * Defines which mutex to use for guarding access to the state and the @@ -281,152 +279,194 @@ struct ec_board_info { enum board_family family; }; -static const struct ec_board_info board_info[] = { - { - .board_names = {"PRIME X470-PRO"}, - .sensors = SENSOR_SET_TEMP_CHIPSET_CPU_MB | - SENSOR_TEMP_T_SENSOR | SENSOR_TEMP_VRM | - SENSOR_FAN_CPU_OPT | - SENSOR_CURR_CPU | SENSOR_IN_CPU_CORE, - .mutex_path = ACPI_GLOBAL_LOCK_PSEUDO_PATH, - .family = family_amd_400_series, - }, - { - .board_names = {"PRIME X570-PRO"}, - .sensors = SENSOR_SET_TEMP_CHIPSET_CPU_MB | SENSOR_TEMP_VRM | - SENSOR_TEMP_T_SENSOR | SENSOR_FAN_CHIPSET, - .mutex_path = ASUS_HW_ACCESS_MUTEX_ASMX, - .family = family_amd_500_series, - }, - { - .board_names = {"ProArt X570-CREATOR WIFI"}, - .sensors = SENSOR_SET_TEMP_CHIPSET_CPU_MB | SENSOR_TEMP_VRM | - SENSOR_TEMP_T_SENSOR | SENSOR_FAN_CPU_OPT | - SENSOR_CURR_CPU | SENSOR_IN_CPU_CORE, - }, - { - .board_names = {"Pro WS X570-ACE"}, - .sensors = SENSOR_SET_TEMP_CHIPSET_CPU_MB | SENSOR_TEMP_VRM | - SENSOR_TEMP_T_SENSOR | SENSOR_FAN_CHIPSET | - SENSOR_CURR_CPU | SENSOR_IN_CPU_CORE, - .mutex_path = ASUS_HW_ACCESS_MUTEX_ASMX, - .family = family_amd_500_series, - }, - { - .board_names = {"ROG CROSSHAIR VIII DARK HERO"}, - .sensors = SENSOR_SET_TEMP_CHIPSET_CPU_MB | - SENSOR_TEMP_T_SENSOR | - SENSOR_TEMP_VRM | SENSOR_SET_TEMP_WATER | - SENSOR_FAN_CPU_OPT | SENSOR_FAN_WATER_FLOW | - SENSOR_CURR_CPU | SENSOR_IN_CPU_CORE, - .mutex_path = ASUS_HW_ACCESS_MUTEX_ASMX, - .family = family_amd_500_series, - }, - { - .board_names = { - "ROG CROSSHAIR VIII FORMULA", - "ROG CROSSHAIR VIII HERO", - "ROG CROSSHAIR VIII HERO (WI-FI)", - }, - .sensors = SENSOR_SET_TEMP_CHIPSET_CPU_MB | - SENSOR_TEMP_T_SENSOR | - SENSOR_TEMP_VRM | SENSOR_SET_TEMP_WATER | - SENSOR_FAN_CPU_OPT | SENSOR_FAN_CHIPSET | - SENSOR_FAN_WATER_FLOW | SENSOR_CURR_CPU | - SENSOR_IN_CPU_CORE, - .mutex_path = ASUS_HW_ACCESS_MUTEX_ASMX, - .family = family_amd_500_series, - }, - { - .board_names = { - "ROG MAXIMUS XI HERO", - "ROG MAXIMUS XI HERO (WI-FI)", - }, - .sensors = SENSOR_SET_TEMP_CHIPSET_CPU_MB | - SENSOR_TEMP_T_SENSOR | - SENSOR_TEMP_VRM | SENSOR_SET_TEMP_WATER | - SENSOR_FAN_CPU_OPT | SENSOR_FAN_WATER_FLOW, - .mutex_path = ASUS_HW_ACCESS_MUTEX_ASMX, - .family = family_intel_300_series, - }, - { - .board_names = {"ROG CROSSHAIR VIII IMPACT"}, - .sensors = SENSOR_SET_TEMP_CHIPSET_CPU_MB | - SENSOR_TEMP_T_SENSOR | SENSOR_TEMP_VRM | - SENSOR_FAN_CHIPSET | SENSOR_CURR_CPU | - SENSOR_IN_CPU_CORE, - .mutex_path = ASUS_HW_ACCESS_MUTEX_ASMX, - .family = family_amd_500_series, - }, - { - .board_names = {"ROG STRIX B550-E GAMING"}, - .sensors = SENSOR_SET_TEMP_CHIPSET_CPU_MB | - SENSOR_TEMP_T_SENSOR | SENSOR_TEMP_VRM | - SENSOR_FAN_CPU_OPT, - .mutex_path = ASUS_HW_ACCESS_MUTEX_ASMX, - .family = family_amd_500_series, - }, - { - .board_names = {"ROG STRIX B550-I GAMING"}, - .sensors = SENSOR_SET_TEMP_CHIPSET_CPU_MB | - SENSOR_TEMP_T_SENSOR | SENSOR_TEMP_VRM | - SENSOR_FAN_VRM_HS | SENSOR_CURR_CPU | - SENSOR_IN_CPU_CORE, - .mutex_path = ASUS_HW_ACCESS_MUTEX_ASMX, - .family = family_amd_500_series, - }, - { - .board_names = {"ROG STRIX X570-E GAMING"}, - .sensors = SENSOR_SET_TEMP_CHIPSET_CPU_MB | - SENSOR_TEMP_T_SENSOR | SENSOR_TEMP_VRM | - SENSOR_FAN_CHIPSET | SENSOR_CURR_CPU | - SENSOR_IN_CPU_CORE, - .mutex_path = ASUS_HW_ACCESS_MUTEX_ASMX, - .family = family_amd_500_series, - }, - { - .board_names = {"ROG STRIX X570-E GAMING WIFI II"}, - .sensors = SENSOR_SET_TEMP_CHIPSET_CPU_MB | - SENSOR_TEMP_T_SENSOR | SENSOR_CURR_CPU | - SENSOR_IN_CPU_CORE, - .mutex_path = ASUS_HW_ACCESS_MUTEX_ASMX, - .family = family_amd_500_series, - }, - { - .board_names = {"ROG STRIX X570-F GAMING"}, - .sensors = SENSOR_SET_TEMP_CHIPSET_CPU_MB | - SENSOR_TEMP_T_SENSOR | SENSOR_FAN_CHIPSET, - .mutex_path = ASUS_HW_ACCESS_MUTEX_ASMX, - .family = family_amd_500_series, - }, - { - .board_names = {"ROG STRIX X570-I GAMING"}, - .sensors = SENSOR_TEMP_CHIPSET | SENSOR_TEMP_VRM | - SENSOR_TEMP_T_SENSOR | - SENSOR_FAN_VRM_HS | SENSOR_FAN_CHIPSET | - SENSOR_CURR_CPU | SENSOR_IN_CPU_CORE, - .mutex_path = ASUS_HW_ACCESS_MUTEX_ASMX, - .family = family_amd_500_series, - }, - { - .board_names = {"ROG STRIX Z690-A GAMING WIFI D4"}, - .sensors = SENSOR_TEMP_T_SENSOR | SENSOR_TEMP_VRM, - .mutex_path = ASUS_HW_ACCESS_MUTEX_RMTW_ASMX, - .family = family_intel_600_series, - }, - { - .board_names = {"ROG ZENITH II EXTREME"}, - .sensors = SENSOR_SET_TEMP_CHIPSET_CPU_MB | SENSOR_TEMP_T_SENSOR | - SENSOR_TEMP_VRM | SENSOR_SET_TEMP_WATER | - SENSOR_FAN_CPU_OPT | SENSOR_FAN_CHIPSET | SENSOR_FAN_VRM_HS | - SENSOR_FAN_WATER_FLOW | SENSOR_CURR_CPU | SENSOR_IN_CPU_CORE | - SENSOR_SET_WATER_BLOCK | - SENSOR_TEMP_T_SENSOR_2 | SENSOR_TEMP_SENSOR_EXTRA_1 | - SENSOR_TEMP_SENSOR_EXTRA_2 | SENSOR_TEMP_SENSOR_EXTRA_3, - .mutex_path = ASUS_HW_ACCESS_MUTEX_SB_PCI0_SBRG_SIO1_MUT0, - .family = family_amd_500_series, - }, - {} +static const struct ec_board_info board_info_prime_x470_pro = { + .sensors = SENSOR_SET_TEMP_CHIPSET_CPU_MB | + SENSOR_TEMP_T_SENSOR | SENSOR_TEMP_VRM | + SENSOR_FAN_CPU_OPT | + SENSOR_CURR_CPU | SENSOR_IN_CPU_CORE, + .mutex_path = ACPI_GLOBAL_LOCK_PSEUDO_PATH, + .family = family_amd_400_series, +}; + +static const struct ec_board_info board_info_prime_x570_pro = { + .sensors = SENSOR_SET_TEMP_CHIPSET_CPU_MB | SENSOR_TEMP_VRM | + SENSOR_TEMP_T_SENSOR | SENSOR_FAN_CHIPSET, + .mutex_path = ASUS_HW_ACCESS_MUTEX_ASMX, + .family = family_amd_500_series, +}; + +static const struct ec_board_info board_info_pro_art_x570_creator_wifi = { + .sensors = SENSOR_SET_TEMP_CHIPSET_CPU_MB | SENSOR_TEMP_VRM | + SENSOR_TEMP_T_SENSOR | SENSOR_FAN_CPU_OPT | + SENSOR_CURR_CPU | SENSOR_IN_CPU_CORE, + .family = family_amd_500_series, +}; + +static const struct ec_board_info board_info_pro_ws_x570_ace = { + .sensors = SENSOR_SET_TEMP_CHIPSET_CPU_MB | SENSOR_TEMP_VRM | + SENSOR_TEMP_T_SENSOR | SENSOR_FAN_CHIPSET | + SENSOR_CURR_CPU | SENSOR_IN_CPU_CORE, + .mutex_path = ASUS_HW_ACCESS_MUTEX_ASMX, + .family = family_amd_500_series, +}; + +static const struct ec_board_info board_info_crosshair_viii_dark_hero = { + .sensors = SENSOR_SET_TEMP_CHIPSET_CPU_MB | + SENSOR_TEMP_T_SENSOR | + SENSOR_TEMP_VRM | SENSOR_SET_TEMP_WATER | + SENSOR_FAN_CPU_OPT | SENSOR_FAN_WATER_FLOW | + SENSOR_CURR_CPU | SENSOR_IN_CPU_CORE, + .mutex_path = ASUS_HW_ACCESS_MUTEX_ASMX, + .family = family_amd_500_series, +}; + +static const struct ec_board_info board_info_crosshair_viii_hero = { + .sensors = SENSOR_SET_TEMP_CHIPSET_CPU_MB | + SENSOR_TEMP_T_SENSOR | + SENSOR_TEMP_VRM | SENSOR_SET_TEMP_WATER | + SENSOR_FAN_CPU_OPT | SENSOR_FAN_CHIPSET | + SENSOR_FAN_WATER_FLOW | SENSOR_CURR_CPU | + SENSOR_IN_CPU_CORE, + .mutex_path = ASUS_HW_ACCESS_MUTEX_ASMX, + .family = family_amd_500_series, +}; + +static const struct ec_board_info board_info_maximus_xi_hero = { + .sensors = SENSOR_SET_TEMP_CHIPSET_CPU_MB | + SENSOR_TEMP_T_SENSOR | + SENSOR_TEMP_VRM | SENSOR_SET_TEMP_WATER | + SENSOR_FAN_CPU_OPT | SENSOR_FAN_WATER_FLOW, + .mutex_path = ASUS_HW_ACCESS_MUTEX_ASMX, + .family = family_intel_300_series, +}; + +static const struct ec_board_info board_info_crosshair_viii_impact = { + .sensors = SENSOR_SET_TEMP_CHIPSET_CPU_MB | + SENSOR_TEMP_T_SENSOR | SENSOR_TEMP_VRM | + SENSOR_FAN_CHIPSET | SENSOR_CURR_CPU | + SENSOR_IN_CPU_CORE, + .mutex_path = ASUS_HW_ACCESS_MUTEX_ASMX, + .family = family_amd_500_series, +}; + +static const struct ec_board_info board_info_strix_b550_e_gaming = { + .sensors = SENSOR_SET_TEMP_CHIPSET_CPU_MB | + SENSOR_TEMP_T_SENSOR | SENSOR_TEMP_VRM | + SENSOR_FAN_CPU_OPT, + .mutex_path = ASUS_HW_ACCESS_MUTEX_ASMX, + .family = family_amd_500_series, +}; + +static const struct ec_board_info board_info_strix_b550_i_gaming = { + .sensors = SENSOR_SET_TEMP_CHIPSET_CPU_MB | + SENSOR_TEMP_T_SENSOR | SENSOR_TEMP_VRM | + SENSOR_FAN_VRM_HS | SENSOR_CURR_CPU | + SENSOR_IN_CPU_CORE, + .mutex_path = ASUS_HW_ACCESS_MUTEX_ASMX, + .family = family_amd_500_series, +}; + +static const struct ec_board_info board_info_strix_x570_e_gaming = { + .sensors = SENSOR_SET_TEMP_CHIPSET_CPU_MB | + SENSOR_TEMP_T_SENSOR | SENSOR_TEMP_VRM | + SENSOR_FAN_CHIPSET | SENSOR_CURR_CPU | + SENSOR_IN_CPU_CORE, + .mutex_path = ASUS_HW_ACCESS_MUTEX_ASMX, + .family = family_amd_500_series, +}; + +static const struct ec_board_info board_info_strix_x570_e_gaming_wifi_ii = { + .sensors = SENSOR_SET_TEMP_CHIPSET_CPU_MB | + SENSOR_TEMP_T_SENSOR | SENSOR_CURR_CPU | + SENSOR_IN_CPU_CORE, + .mutex_path = ASUS_HW_ACCESS_MUTEX_ASMX, + .family = family_amd_500_series, +}; + +static const struct ec_board_info board_info_strix_x570_f_gaming = { + .sensors = SENSOR_SET_TEMP_CHIPSET_CPU_MB | + SENSOR_TEMP_T_SENSOR | SENSOR_FAN_CHIPSET, + .mutex_path = ASUS_HW_ACCESS_MUTEX_ASMX, + .family = family_amd_500_series, +}; + +static const struct ec_board_info board_info_strix_x570_i_gaming = { + .sensors = SENSOR_TEMP_CHIPSET | SENSOR_TEMP_VRM | + SENSOR_TEMP_T_SENSOR | + SENSOR_FAN_VRM_HS | SENSOR_FAN_CHIPSET | + SENSOR_CURR_CPU | SENSOR_IN_CPU_CORE, + .mutex_path = ASUS_HW_ACCESS_MUTEX_ASMX, + .family = family_amd_500_series, +}; + +static const struct ec_board_info board_info_strix_z690_a_gaming_wifi_d4 = { + .sensors = SENSOR_TEMP_T_SENSOR | SENSOR_TEMP_VRM, + .mutex_path = ASUS_HW_ACCESS_MUTEX_RMTW_ASMX, + .family = family_intel_600_series, +}; + +static const struct ec_board_info board_info_zenith_ii_extreme = { + .sensors = SENSOR_SET_TEMP_CHIPSET_CPU_MB | SENSOR_TEMP_T_SENSOR | + SENSOR_TEMP_VRM | SENSOR_SET_TEMP_WATER | + SENSOR_FAN_CPU_OPT | SENSOR_FAN_CHIPSET | SENSOR_FAN_VRM_HS | + SENSOR_FAN_WATER_FLOW | SENSOR_CURR_CPU | SENSOR_IN_CPU_CORE | + SENSOR_SET_WATER_BLOCK | + SENSOR_TEMP_T_SENSOR_2 | SENSOR_TEMP_SENSOR_EXTRA_1 | + SENSOR_TEMP_SENSOR_EXTRA_2 | SENSOR_TEMP_SENSOR_EXTRA_3, + .mutex_path = ASUS_HW_ACCESS_MUTEX_SB_PCI0_SBRG_SIO1_MUT0, + .family = family_amd_500_series, +}; + +#define DMI_EXACT_MATCH_ASUS_BOARD_NAME(name, board_info) \ + { \ + .matches = { \ + DMI_EXACT_MATCH(DMI_BOARD_VENDOR, \ + "ASUSTeK COMPUTER INC."), \ + DMI_EXACT_MATCH(DMI_BOARD_NAME, name), \ + }, \ + .driver_data = (void *)board_info, \ + } + +static const struct dmi_system_id dmi_table[] = { + DMI_EXACT_MATCH_ASUS_BOARD_NAME("PRIME X470-PRO", + &board_info_prime_x470_pro), + DMI_EXACT_MATCH_ASUS_BOARD_NAME("PRIME X570-PRO", + &board_info_prime_x570_pro), + DMI_EXACT_MATCH_ASUS_BOARD_NAME("ProArt X570-CREATOR WIFI", + &board_info_pro_art_x570_creator_wifi), + DMI_EXACT_MATCH_ASUS_BOARD_NAME("Pro WS X570-ACE", + &board_info_pro_ws_x570_ace), + DMI_EXACT_MATCH_ASUS_BOARD_NAME("ROG CROSSHAIR VIII DARK HERO", + &board_info_crosshair_viii_dark_hero), + DMI_EXACT_MATCH_ASUS_BOARD_NAME("ROG CROSSHAIR VIII FORMULA", + &board_info_crosshair_viii_hero), + DMI_EXACT_MATCH_ASUS_BOARD_NAME("ROG CROSSHAIR VIII HERO", + &board_info_crosshair_viii_hero), + DMI_EXACT_MATCH_ASUS_BOARD_NAME("ROG CROSSHAIR VIII HERO (WI-FI)", + &board_info_crosshair_viii_hero), + DMI_EXACT_MATCH_ASUS_BOARD_NAME("ROG MAXIMUS XI HERO", + &board_info_maximus_xi_hero), + DMI_EXACT_MATCH_ASUS_BOARD_NAME("ROG MAXIMUS XI HERO (WI-FI)", + &board_info_maximus_xi_hero), + DMI_EXACT_MATCH_ASUS_BOARD_NAME("ROG CROSSHAIR VIII IMPACT", + &board_info_crosshair_viii_impact), + DMI_EXACT_MATCH_ASUS_BOARD_NAME("ROG STRIX B550-E GAMING", + &board_info_strix_b550_e_gaming), + DMI_EXACT_MATCH_ASUS_BOARD_NAME("ROG STRIX B550-I GAMING", + &board_info_strix_b550_i_gaming), + DMI_EXACT_MATCH_ASUS_BOARD_NAME("ROG STRIX X570-E GAMING", + &board_info_strix_x570_e_gaming), + DMI_EXACT_MATCH_ASUS_BOARD_NAME("ROG STRIX X570-E GAMING WIFI II", + &board_info_strix_x570_e_gaming_wifi_ii), + DMI_EXACT_MATCH_ASUS_BOARD_NAME("ROG STRIX X570-F GAMING", + &board_info_strix_x570_f_gaming), + DMI_EXACT_MATCH_ASUS_BOARD_NAME("ROG STRIX X570-I GAMING", + &board_info_strix_x570_i_gaming), + DMI_EXACT_MATCH_ASUS_BOARD_NAME("ROG STRIX Z690-A GAMING WIFI D4", + &board_info_strix_z690_a_gaming_wifi_d4), + DMI_EXACT_MATCH_ASUS_BOARD_NAME("ROG ZENITH II EXTREME", + &board_info_zenith_ii_extreme), + {}, }; struct ec_sensor { @@ -537,12 +577,12 @@ static int find_ec_sensor_index(const struct ec_sensors_data *ec, return -ENOENT; } -static int __init bank_compare(const void *a, const void *b) +static int bank_compare(const void *a, const void *b) { return *((const s8 *)a) - *((const s8 *)b); } -static void __init setup_sensor_data(struct ec_sensors_data *ec) +static void setup_sensor_data(struct ec_sensors_data *ec) { struct ec_sensor *s = ec->sensors; bool bank_found; @@ -574,7 +614,7 @@ static void __init setup_sensor_data(struct ec_sensors_data *ec) sort(ec->banks, ec->nr_banks, 1, bank_compare, NULL); } -static void __init fill_ec_registers(struct ec_sensors_data *ec) +static void fill_ec_registers(struct ec_sensors_data *ec) { const struct ec_sensor_info *si; unsigned int i, j, register_idx = 0; @@ -589,7 +629,7 @@ static void __init fill_ec_registers(struct ec_sensors_data *ec) } } -static int __init setup_lock_data(struct device *dev) +static int setup_lock_data(struct device *dev) { const char *mutex_path; int status; @@ -812,7 +852,7 @@ static umode_t asus_ec_hwmon_is_visible(const void *drvdata, return find_ec_sensor_index(state, type, channel) >= 0 ? S_IRUGO : 0; } -static int __init +static int asus_ec_hwmon_add_chan_info(struct hwmon_channel_info *asus_ec_hwmon_chan, struct device *dev, int num, enum hwmon_sensor_types type, u32 config) @@ -841,27 +881,15 @@ static struct hwmon_chip_info asus_ec_chip_info = { .ops = &asus_ec_hwmon_ops, }; -static const struct ec_board_info * __init get_board_info(void) +static const struct ec_board_info *get_board_info(void) { - const char *dmi_board_vendor = dmi_get_system_info(DMI_BOARD_VENDOR); - const char *dmi_board_name = dmi_get_system_info(DMI_BOARD_NAME); - const struct ec_board_info *board; - - if (!dmi_board_vendor || !dmi_board_name || - strcasecmp(dmi_board_vendor, "ASUSTeK COMPUTER INC.")) - return NULL; - - for (board = board_info; board->sensors; board++) { - if (match_string(board->board_names, - MAX_IDENTICAL_BOARD_VARIATIONS, - dmi_board_name) >= 0) - return board; - } + const struct dmi_system_id *dmi_entry; - return NULL; + dmi_entry = dmi_first_match(dmi_table); + return dmi_entry ? dmi_entry->driver_data : NULL; } -static int __init asus_ec_probe(struct platform_device *pdev) +static int asus_ec_probe(struct platform_device *pdev) { const struct hwmon_channel_info **ptr_asus_ec_ci; int nr_count[hwmon_max] = { 0 }, nr_types = 0; @@ -970,29 +998,37 @@ static int __init asus_ec_probe(struct platform_device *pdev) return PTR_ERR_OR_ZERO(hwdev); } - -static const struct acpi_device_id acpi_ec_ids[] = { - /* Embedded Controller Device */ - { "PNP0C09", 0 }, - {} -}; +MODULE_DEVICE_TABLE(dmi, dmi_table); static struct platform_driver asus_ec_sensors_platform_driver = { .driver = { .name = "asus-ec-sensors", - .acpi_match_table = acpi_ec_ids, }, + .probe = asus_ec_probe, }; -MODULE_DEVICE_TABLE(acpi, acpi_ec_ids); -/* - * we use module_platform_driver_probe() rather than module_platform_driver() - * because the probe function (and its dependants) are marked with __init, which - * means we can't put it into the .probe member of the platform_driver struct - * above, and we can't mark the asus_ec_sensors_platform_driver object as __init - * because the object is referenced from the module exit code. - */ -module_platform_driver_probe(asus_ec_sensors_platform_driver, asus_ec_probe); +static struct platform_device *asus_ec_sensors_platform_device; + +static int __init asus_ec_init(void) +{ + asus_ec_sensors_platform_device = + platform_create_bundle(&asus_ec_sensors_platform_driver, + asus_ec_probe, NULL, 0, NULL, 0); + + if (IS_ERR(asus_ec_sensors_platform_device)) + return PTR_ERR(asus_ec_sensors_platform_device); + + return 0; +} + +static void __exit asus_ec_exit(void) +{ + platform_device_unregister(asus_ec_sensors_platform_device); + platform_driver_unregister(&asus_ec_sensors_platform_driver); +} + +module_init(asus_ec_init); +module_exit(asus_ec_exit); module_param_named(mutex_path, mutex_path_override, charp, 0); MODULE_PARM_DESC(mutex_path, diff --git a/drivers/hwmon/mr75203.c b/drivers/hwmon/mr75203.c index 26278b0f17a9..9259779cc2df 100644 --- a/drivers/hwmon/mr75203.c +++ b/drivers/hwmon/mr75203.c @@ -68,8 +68,9 @@ /* VM Individual Macro Register */ #define VM_COM_REG_SIZE 0x200 -#define VM_SDIF_DONE(n) (VM_COM_REG_SIZE + 0x34 + 0x200 * (n)) -#define VM_SDIF_DATA(n) (VM_COM_REG_SIZE + 0x40 + 0x200 * (n)) +#define VM_SDIF_DONE(vm) (VM_COM_REG_SIZE + 0x34 + 0x200 * (vm)) +#define VM_SDIF_DATA(vm, ch) \ + (VM_COM_REG_SIZE + 0x40 + 0x200 * (vm) + 0x4 * (ch)) /* SDA Slave Register */ #define IP_CTRL 0x00 @@ -115,6 +116,7 @@ struct pvt_device { u32 t_num; u32 p_num; u32 v_num; + u32 c_num; u32 ip_freq; u8 *vm_idx; }; @@ -178,14 +180,15 @@ static int pvt_read_in(struct device *dev, u32 attr, int channel, long *val) { struct pvt_device *pvt = dev_get_drvdata(dev); struct regmap *v_map = pvt->v_map; + u8 vm_idx, ch_idx; u32 n, stat; - u8 vm_idx; int ret; - if (channel >= pvt->v_num) + if (channel >= pvt->v_num * pvt->c_num) return -EINVAL; - vm_idx = pvt->vm_idx[channel]; + vm_idx = pvt->vm_idx[channel / pvt->c_num]; + ch_idx = channel % pvt->c_num; switch (attr) { case hwmon_in_input: @@ -196,13 +199,23 @@ static int pvt_read_in(struct device *dev, u32 attr, int channel, long *val) if (ret) return ret; - ret = regmap_read(v_map, VM_SDIF_DATA(vm_idx), &n); + ret = regmap_read(v_map, VM_SDIF_DATA(vm_idx, ch_idx), &n); if(ret < 0) return ret; n &= SAMPLE_DATA_MSK; - /* Convert the N bitstream count into voltage */ - *val = (PVT_N_CONST * n - PVT_R_CONST) >> PVT_CONV_BITS; + /* + * Convert the N bitstream count into voltage. + * To support negative voltage calculation for 64bit machines + * n must be cast to long, since n and *val differ both in + * signedness and in size. + * Division is used instead of right shift, because for signed + * numbers, the sign bit is used to fill the vacated bit + * positions, and if the number is negative, 1 is used. + * BIT(x) may not be used instead of (1 << x) because it's + * unsigned. + */ + *val = (PVT_N_CONST * (long)n - PVT_R_CONST) / (1 << PVT_CONV_BITS); return 0; default: @@ -375,6 +388,19 @@ static int pvt_init(struct pvt_device *pvt) if (ret) return ret; + val = (BIT(pvt->c_num) - 1) | VM_CH_INIT | + IP_POLL << SDIF_ADDR_SFT | SDIF_WRN_W | SDIF_PROG; + ret = regmap_write(v_map, SDIF_W, val); + if (ret < 0) + return ret; + + ret = regmap_read_poll_timeout(v_map, SDIF_STAT, + val, !(val & SDIF_BUSY), + PVT_POLL_DELAY_US, + PVT_POLL_TIMEOUT_US); + if (ret) + return ret; + val = CFG1_VOL_MEAS_MODE | CFG1_PARALLEL_OUT | CFG1_14_BIT | IP_CFG << SDIF_ADDR_SFT | SDIF_WRN_W | SDIF_PROG; @@ -489,8 +515,8 @@ static int pvt_reset_control_deassert(struct device *dev, struct pvt_device *pvt static int mr75203_probe(struct platform_device *pdev) { + u32 ts_num, vm_num, pd_num, ch_num, val, index, i; const struct hwmon_channel_info **pvt_info; - u32 ts_num, vm_num, pd_num, val, index, i; struct device *dev = &pdev->dev; u32 *temp_config, *in_config; struct device *hwmon_dev; @@ -531,9 +557,11 @@ static int mr75203_probe(struct platform_device *pdev) ts_num = (val & TS_NUM_MSK) >> TS_NUM_SFT; pd_num = (val & PD_NUM_MSK) >> PD_NUM_SFT; vm_num = (val & VM_NUM_MSK) >> VM_NUM_SFT; + ch_num = (val & CH_NUM_MSK) >> CH_NUM_SFT; pvt->t_num = ts_num; pvt->p_num = pd_num; pvt->v_num = vm_num; + pvt->c_num = ch_num; val = 0; if (ts_num) val++; @@ -570,7 +598,7 @@ static int mr75203_probe(struct platform_device *pdev) } if (vm_num) { - u32 num = vm_num; + u32 total_ch; ret = pvt_get_regmap(pdev, "vm", pvt); if (ret) @@ -584,30 +612,30 @@ static int mr75203_probe(struct platform_device *pdev) ret = device_property_read_u8_array(dev, "intel,vm-map", pvt->vm_idx, vm_num); if (ret) { - num = 0; + /* + * Incase intel,vm-map property is not defined, we + * assume incremental channel numbers. + */ + for (i = 0; i < vm_num; i++) + pvt->vm_idx[i] = i; } else { for (i = 0; i < vm_num; i++) if (pvt->vm_idx[i] >= vm_num || pvt->vm_idx[i] == 0xff) { - num = i; + pvt->v_num = i; + vm_num = i; break; } } - /* - * Incase intel,vm-map property is not defined, we assume - * incremental channel numbers. - */ - for (i = num; i < vm_num; i++) - pvt->vm_idx[i] = i; - - in_config = devm_kcalloc(dev, num + 1, + total_ch = ch_num * vm_num; + in_config = devm_kcalloc(dev, total_ch + 1, sizeof(*in_config), GFP_KERNEL); if (!in_config) return -ENOMEM; - memset32(in_config, HWMON_I_INPUT, num); - in_config[num] = 0; + memset32(in_config, HWMON_I_INPUT, total_ch); + in_config[total_ch] = 0; pvt_in.config = in_config; pvt_info[index++] = &pvt_in; diff --git a/drivers/hwmon/tps23861.c b/drivers/hwmon/tps23861.c index 42762e87b014..f7c59ff7ae8e 100644 --- a/drivers/hwmon/tps23861.c +++ b/drivers/hwmon/tps23861.c @@ -493,18 +493,20 @@ static char *tps23861_port_poe_plus_status(struct tps23861_data *data, int port) static int tps23861_port_resistance(struct tps23861_data *data, int port) { - u16 regval; + unsigned int raw_val; + __le16 regval; regmap_bulk_read(data->regmap, PORT_1_RESISTANCE_LSB + PORT_N_RESISTANCE_LSB_OFFSET * (port - 1), ®val, 2); - switch (FIELD_GET(PORT_RESISTANCE_RSN_MASK, regval)) { + raw_val = le16_to_cpu(regval); + switch (FIELD_GET(PORT_RESISTANCE_RSN_MASK, raw_val)) { case PORT_RESISTANCE_RSN_OTHER: - return (FIELD_GET(PORT_RESISTANCE_MASK, regval) * RESISTANCE_LSB) / 10000; + return (FIELD_GET(PORT_RESISTANCE_MASK, raw_val) * RESISTANCE_LSB) / 10000; case PORT_RESISTANCE_RSN_LOW: - return (FIELD_GET(PORT_RESISTANCE_MASK, regval) * RESISTANCE_LSB_LOW) / 10000; + return (FIELD_GET(PORT_RESISTANCE_MASK, raw_val) * RESISTANCE_LSB_LOW) / 10000; case PORT_RESISTANCE_RSN_SHORT: case PORT_RESISTANCE_RSN_OPEN: default: diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c index 46d06678dfbe..be317f2665a9 100644 --- a/drivers/infiniband/core/cma.c +++ b/drivers/infiniband/core/cma.c @@ -1841,8 +1841,8 @@ cma_ib_id_from_event(struct ib_cm_id *cm_id, } if (!validate_net_dev(*net_dev, - (struct sockaddr *)&req->listen_addr_storage, - (struct sockaddr *)&req->src_addr_storage)) { + (struct sockaddr *)&req->src_addr_storage, + (struct sockaddr *)&req->listen_addr_storage)) { id_priv = ERR_PTR(-EHOSTUNREACH); goto err; } diff --git a/drivers/infiniband/core/umem_odp.c b/drivers/infiniband/core/umem_odp.c index 186ed8859920..d39e16c211e8 100644 --- a/drivers/infiniband/core/umem_odp.c +++ b/drivers/infiniband/core/umem_odp.c @@ -462,7 +462,7 @@ retry: mutex_unlock(&umem_odp->umem_mutex); out_put_mm: - mmput(owning_mm); + mmput_async(owning_mm); out_put_task: if (owning_process) put_task_struct(owning_process); diff --git a/drivers/infiniband/hw/hns/hns_roce_device.h b/drivers/infiniband/hw/hns/hns_roce_device.h index f848eedc6a23..d24996526c4d 100644 --- a/drivers/infiniband/hw/hns/hns_roce_device.h +++ b/drivers/infiniband/hw/hns/hns_roce_device.h @@ -730,7 +730,6 @@ struct hns_roce_caps { u32 num_qps; u32 num_pi_qps; u32 reserved_qps; - int num_qpc_timer; u32 num_srqs; u32 max_wqes; u32 max_srq_wrs; diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c index cbdafaac678a..c780646bd60a 100644 --- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c +++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c @@ -1977,7 +1977,7 @@ static void set_default_caps(struct hns_roce_dev *hr_dev) caps->num_mtpts = HNS_ROCE_V2_MAX_MTPT_NUM; caps->num_pds = HNS_ROCE_V2_MAX_PD_NUM; - caps->num_qpc_timer = HNS_ROCE_V2_MAX_QPC_TIMER_NUM; + caps->qpc_timer_bt_num = HNS_ROCE_V2_MAX_QPC_TIMER_BT_NUM; caps->cqc_timer_bt_num = HNS_ROCE_V2_MAX_CQC_TIMER_BT_NUM; caps->max_qp_init_rdma = HNS_ROCE_V2_MAX_QP_INIT_RDMA; @@ -2273,7 +2273,6 @@ static int hns_roce_query_pf_caps(struct hns_roce_dev *hr_dev) caps->max_rq_sg = le16_to_cpu(resp_a->max_rq_sg); caps->max_rq_sg = roundup_pow_of_two(caps->max_rq_sg); caps->max_extend_sg = le32_to_cpu(resp_a->max_extend_sg); - caps->num_qpc_timer = le16_to_cpu(resp_a->num_qpc_timer); caps->max_srq_sges = le16_to_cpu(resp_a->max_srq_sges); caps->max_srq_sges = roundup_pow_of_two(caps->max_srq_sges); caps->num_aeq_vectors = resp_a->num_aeq_vectors; diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.h b/drivers/infiniband/hw/hns/hns_roce_hw_v2.h index f96debac30fe..64797109bab6 100644 --- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.h +++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.h @@ -36,11 +36,11 @@ #include <linux/bitops.h> #define HNS_ROCE_V2_MAX_QP_NUM 0x1000 -#define HNS_ROCE_V2_MAX_QPC_TIMER_NUM 0x200 #define HNS_ROCE_V2_MAX_WQE_NUM 0x8000 #define HNS_ROCE_V2_MAX_SRQ_WR 0x8000 #define HNS_ROCE_V2_MAX_SRQ_SGE 64 #define HNS_ROCE_V2_MAX_CQ_NUM 0x100000 +#define HNS_ROCE_V2_MAX_QPC_TIMER_BT_NUM 0x100 #define HNS_ROCE_V2_MAX_CQC_TIMER_BT_NUM 0x100 #define HNS_ROCE_V2_MAX_SRQ_NUM 0x100000 #define HNS_ROCE_V2_MAX_CQE_NUM 0x400000 @@ -83,7 +83,7 @@ #define HNS_ROCE_V2_QPC_TIMER_ENTRY_SZ PAGE_SIZE #define HNS_ROCE_V2_CQC_TIMER_ENTRY_SZ PAGE_SIZE -#define HNS_ROCE_V2_PAGE_SIZE_SUPPORTED 0xFFFFF000 +#define HNS_ROCE_V2_PAGE_SIZE_SUPPORTED 0xFFFF000 #define HNS_ROCE_V2_MAX_INNER_MTPT_NUM 2 #define HNS_ROCE_INVALID_LKEY 0x0 #define HNS_ROCE_INVALID_SGE_LENGTH 0x80000000 diff --git a/drivers/infiniband/hw/hns/hns_roce_main.c b/drivers/infiniband/hw/hns/hns_roce_main.c index c8af4ebd7cbd..4ccb217b2841 100644 --- a/drivers/infiniband/hw/hns/hns_roce_main.c +++ b/drivers/infiniband/hw/hns/hns_roce_main.c @@ -725,7 +725,7 @@ static int hns_roce_init_hem(struct hns_roce_dev *hr_dev) ret = hns_roce_init_hem_table(hr_dev, &hr_dev->qpc_timer_table, HEM_TYPE_QPC_TIMER, hr_dev->caps.qpc_timer_entry_sz, - hr_dev->caps.num_qpc_timer, 1); + hr_dev->caps.qpc_timer_bt_num, 1); if (ret) { dev_err(dev, "Failed to init QPC timer memory, aborting.\n"); diff --git a/drivers/infiniband/hw/hns/hns_roce_qp.c b/drivers/infiniband/hw/hns/hns_roce_qp.c index 48d3616a6d71..7bee7f6c5e70 100644 --- a/drivers/infiniband/hw/hns/hns_roce_qp.c +++ b/drivers/infiniband/hw/hns/hns_roce_qp.c @@ -462,11 +462,8 @@ static int set_rq_size(struct hns_roce_dev *hr_dev, struct ib_qp_cap *cap, hr_qp->rq.max_gs = roundup_pow_of_two(max(1U, cap->max_recv_sge) + hr_qp->rq.rsv_sge); - if (hr_dev->caps.max_rq_sg <= HNS_ROCE_SGE_IN_WQE) - hr_qp->rq.wqe_shift = ilog2(hr_dev->caps.max_rq_desc_sz); - else - hr_qp->rq.wqe_shift = ilog2(hr_dev->caps.max_rq_desc_sz * - hr_qp->rq.max_gs); + hr_qp->rq.wqe_shift = ilog2(hr_dev->caps.max_rq_desc_sz * + hr_qp->rq.max_gs); hr_qp->rq.wqe_cnt = cnt; if (hr_dev->caps.flags & HNS_ROCE_CAP_FLAG_RQ_INLINE && diff --git a/drivers/infiniband/hw/irdma/uk.c b/drivers/infiniband/hw/irdma/uk.c index daeab5daed5b..a6e5d350a94c 100644 --- a/drivers/infiniband/hw/irdma/uk.c +++ b/drivers/infiniband/hw/irdma/uk.c @@ -497,7 +497,8 @@ int irdma_uk_send(struct irdma_qp_uk *qp, struct irdma_post_sq_info *info, FIELD_PREP(IRDMAQPSQ_IMMDATA, info->imm_data)); i = 0; } else { - qp->wqe_ops.iw_set_fragment(wqe, 0, op_info->sg_list, + qp->wqe_ops.iw_set_fragment(wqe, 0, + frag_cnt ? op_info->sg_list : NULL, qp->swqe_polarity); i = 1; } @@ -1005,6 +1006,7 @@ int irdma_uk_cq_poll_cmpl(struct irdma_cq_uk *cq, int ret_code; bool move_cq_head = true; u8 polarity; + u8 op_type; bool ext_valid; __le64 *ext_cqe; @@ -1187,7 +1189,6 @@ int irdma_uk_cq_poll_cmpl(struct irdma_cq_uk *cq, do { __le64 *sw_wqe; u64 wqe_qword; - u8 op_type; u32 tail; tail = qp->sq_ring.tail; @@ -1204,6 +1205,8 @@ int irdma_uk_cq_poll_cmpl(struct irdma_cq_uk *cq, break; } } while (1); + if (op_type == IRDMA_OP_TYPE_BIND_MW && info->minor_err == FLUSH_PROT_ERR) + info->minor_err = FLUSH_MW_BIND_ERR; qp->sq_flush_seen = true; if (!IRDMA_RING_MORE_WORK(qp->sq_ring)) qp->sq_flush_complete = true; diff --git a/drivers/infiniband/hw/irdma/utils.c b/drivers/infiniband/hw/irdma/utils.c index fdf4cc88cb91..075defaabee5 100644 --- a/drivers/infiniband/hw/irdma/utils.c +++ b/drivers/infiniband/hw/irdma/utils.c @@ -590,11 +590,14 @@ static int irdma_wait_event(struct irdma_pci_f *rf, cqp_error = cqp_request->compl_info.error; if (cqp_error) { err_code = -EIO; - if (cqp_request->compl_info.maj_err_code == 0xFFFF && - cqp_request->compl_info.min_err_code == 0x8029) { - if (!rf->reset) { - rf->reset = true; - rf->gen_ops.request_reset(rf); + if (cqp_request->compl_info.maj_err_code == 0xFFFF) { + if (cqp_request->compl_info.min_err_code == 0x8002) + err_code = -EBUSY; + else if (cqp_request->compl_info.min_err_code == 0x8029) { + if (!rf->reset) { + rf->reset = true; + rf->gen_ops.request_reset(rf); + } } } } @@ -2598,7 +2601,7 @@ void irdma_generate_flush_completions(struct irdma_qp *iwqp) spin_unlock_irqrestore(&iwqp->lock, flags2); spin_unlock_irqrestore(&iwqp->iwscq->lock, flags1); if (compl_generated) - irdma_comp_handler(iwqp->iwrcq); + irdma_comp_handler(iwqp->iwscq); } else { spin_unlock_irqrestore(&iwqp->iwscq->lock, flags1); mod_delayed_work(iwqp->iwdev->cleanup_wq, &iwqp->dwork_flush, diff --git a/drivers/infiniband/hw/irdma/verbs.c b/drivers/infiniband/hw/irdma/verbs.c index 9b07b8af2997..9b207f5084eb 100644 --- a/drivers/infiniband/hw/irdma/verbs.c +++ b/drivers/infiniband/hw/irdma/verbs.c @@ -39,15 +39,18 @@ static int irdma_query_device(struct ib_device *ibdev, props->max_send_sge = hw_attrs->uk_attrs.max_hw_wq_frags; props->max_recv_sge = hw_attrs->uk_attrs.max_hw_wq_frags; props->max_cq = rf->max_cq - rf->used_cqs; - props->max_cqe = rf->max_cqe; + props->max_cqe = rf->max_cqe - 1; props->max_mr = rf->max_mr - rf->used_mrs; props->max_mw = props->max_mr; props->max_pd = rf->max_pd - rf->used_pds; props->max_sge_rd = hw_attrs->uk_attrs.max_hw_read_sges; props->max_qp_rd_atom = hw_attrs->max_hw_ird; props->max_qp_init_rd_atom = hw_attrs->max_hw_ord; - if (rdma_protocol_roce(ibdev, 1)) + if (rdma_protocol_roce(ibdev, 1)) { + props->device_cap_flags |= IB_DEVICE_RC_RNR_NAK_GEN; props->max_pkeys = IRDMA_PKEY_TBL_SZ; + } + props->max_ah = rf->max_ah; props->max_mcast_grp = rf->max_mcg; props->max_mcast_qp_attach = IRDMA_MAX_MGS_PER_CTX; @@ -3009,6 +3012,7 @@ static int irdma_dereg_mr(struct ib_mr *ib_mr, struct ib_udata *udata) struct irdma_pble_alloc *palloc = &iwpbl->pble_alloc; struct irdma_cqp_request *cqp_request; struct cqp_cmds_info *cqp_info; + int status; if (iwmr->type != IRDMA_MEMREG_TYPE_MEM) { if (iwmr->region) { @@ -3039,8 +3043,11 @@ static int irdma_dereg_mr(struct ib_mr *ib_mr, struct ib_udata *udata) cqp_info->post_sq = 1; cqp_info->in.u.dealloc_stag.dev = &iwdev->rf->sc_dev; cqp_info->in.u.dealloc_stag.scratch = (uintptr_t)cqp_request; - irdma_handle_cqp_op(iwdev->rf, cqp_request); + status = irdma_handle_cqp_op(iwdev->rf, cqp_request); irdma_put_cqp_request(&iwdev->rf->cqp, cqp_request); + if (status) + return status; + irdma_free_stag(iwdev, iwmr->stag); done: if (iwpbl->pbl_allocated) diff --git a/drivers/infiniband/hw/mlx5/mad.c b/drivers/infiniband/hw/mlx5/mad.c index 293ed709e5ed..b4dc52392275 100644 --- a/drivers/infiniband/hw/mlx5/mad.c +++ b/drivers/infiniband/hw/mlx5/mad.c @@ -166,6 +166,12 @@ static int process_pma_cmd(struct mlx5_ib_dev *dev, u32 port_num, mdev = dev->mdev; mdev_port_num = 1; } + if (MLX5_CAP_GEN(dev->mdev, num_ports) == 1) { + /* set local port to one for Function-Per-Port HCA. */ + mdev = dev->mdev; + mdev_port_num = 1; + } + /* Declaring support of extended counters */ if (in_mad->mad_hdr.attr_id == IB_PMA_CLASS_PORT_INFO) { struct ib_class_port_info cpi = {}; diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c index fc94a1b25485..883d7c60143e 100644 --- a/drivers/infiniband/hw/mlx5/main.c +++ b/drivers/infiniband/hw/mlx5/main.c @@ -4336,7 +4336,7 @@ static int mlx5r_probe(struct auxiliary_device *adev, dev->mdev = mdev; dev->num_ports = num_ports; - if (ll == IB_LINK_LAYER_ETHERNET && !mlx5_is_roce_init_enabled(mdev)) + if (ll == IB_LINK_LAYER_ETHERNET && !mlx5_get_roce_state(mdev)) profile = &raw_eth_profile; else profile = &pf_profile; diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h index 2e2ad3918385..e66bf72f1f04 100644 --- a/drivers/infiniband/hw/mlx5/mlx5_ib.h +++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h @@ -708,6 +708,7 @@ struct mlx5_ib_umr_context { }; enum { + MLX5_UMR_STATE_UNINIT, MLX5_UMR_STATE_ACTIVE, MLX5_UMR_STATE_RECOVER, MLX5_UMR_STATE_ERR, diff --git a/drivers/infiniband/hw/mlx5/umr.c b/drivers/infiniband/hw/mlx5/umr.c index e00b94d1b1ea..d5105b5c9979 100644 --- a/drivers/infiniband/hw/mlx5/umr.c +++ b/drivers/infiniband/hw/mlx5/umr.c @@ -177,6 +177,7 @@ int mlx5r_umr_resource_init(struct mlx5_ib_dev *dev) sema_init(&dev->umrc.sem, MAX_UMR_WR); mutex_init(&dev->umrc.lock); + dev->umrc.state = MLX5_UMR_STATE_ACTIVE; return 0; @@ -191,6 +192,8 @@ destroy_pd: void mlx5r_umr_resource_cleanup(struct mlx5_ib_dev *dev) { + if (dev->umrc.state == MLX5_UMR_STATE_UNINIT) + return; ib_destroy_qp(dev->umrc.qp); ib_free_cq(dev->umrc.cq); ib_dealloc_pd(dev->umrc.pd); diff --git a/drivers/infiniband/sw/siw/siw_qp_tx.c b/drivers/infiniband/sw/siw/siw_qp_tx.c index 1f4e60257700..7d47b521070b 100644 --- a/drivers/infiniband/sw/siw/siw_qp_tx.c +++ b/drivers/infiniband/sw/siw/siw_qp_tx.c @@ -29,7 +29,7 @@ static struct page *siw_get_pblpage(struct siw_mem *mem, u64 addr, int *idx) dma_addr_t paddr = siw_pbl_get_buffer(pbl, offset, NULL, idx); if (paddr) - return virt_to_page(paddr); + return virt_to_page((void *)paddr); return NULL; } @@ -533,13 +533,23 @@ static int siw_tx_hdt(struct siw_iwarp_tx *c_tx, struct socket *s) kunmap_local(kaddr); } } else { - u64 va = sge->laddr + sge_off; + /* + * Cast to an uintptr_t to preserve all 64 bits + * in sge->laddr. + */ + uintptr_t va = (uintptr_t)(sge->laddr + sge_off); - page_array[seg] = virt_to_page(va & PAGE_MASK); + /* + * virt_to_page() takes a (void *) pointer + * so cast to a (void *) meaning it will be 64 + * bits on a 64 bit platform and 32 bits on a + * 32 bit platform. + */ + page_array[seg] = virt_to_page((void *)(va & PAGE_MASK)); if (do_crc) crypto_shash_update( c_tx->mpa_crc_hd, - (void *)(uintptr_t)va, + (void *)va, plen); } diff --git a/drivers/infiniband/ulp/rtrs/rtrs-clt.c b/drivers/infiniband/ulp/rtrs/rtrs-clt.c index baecde41d126..449904dac0a9 100644 --- a/drivers/infiniband/ulp/rtrs/rtrs-clt.c +++ b/drivers/infiniband/ulp/rtrs/rtrs-clt.c @@ -1004,7 +1004,8 @@ rtrs_clt_get_copy_req(struct rtrs_clt_path *alive_path, static int rtrs_post_rdma_write_sg(struct rtrs_clt_con *con, struct rtrs_clt_io_req *req, struct rtrs_rbuf *rbuf, bool fr_en, - u32 size, u32 imm, struct ib_send_wr *wr, + u32 count, u32 size, u32 imm, + struct ib_send_wr *wr, struct ib_send_wr *tail) { struct rtrs_clt_path *clt_path = to_clt_path(con->c.path); @@ -1024,12 +1025,12 @@ static int rtrs_post_rdma_write_sg(struct rtrs_clt_con *con, num_sge = 2; ptail = tail; } else { - for_each_sg(req->sglist, sg, req->sg_cnt, i) { + for_each_sg(req->sglist, sg, count, i) { sge[i].addr = sg_dma_address(sg); sge[i].length = sg_dma_len(sg); sge[i].lkey = clt_path->s.dev->ib_pd->local_dma_lkey; } - num_sge = 1 + req->sg_cnt; + num_sge = 1 + count; } sge[i].addr = req->iu->dma_addr; sge[i].length = size; @@ -1142,7 +1143,7 @@ static int rtrs_clt_write_req(struct rtrs_clt_io_req *req) */ rtrs_clt_update_all_stats(req, WRITE); - ret = rtrs_post_rdma_write_sg(req->con, req, rbuf, fr_en, + ret = rtrs_post_rdma_write_sg(req->con, req, rbuf, fr_en, count, req->usr_len + sizeof(*msg), imm, wr, &inv_wr); if (ret) { diff --git a/drivers/infiniband/ulp/rtrs/rtrs-srv.c b/drivers/infiniband/ulp/rtrs/rtrs-srv.c index 34c03bde5064..4894e7329d88 100644 --- a/drivers/infiniband/ulp/rtrs/rtrs-srv.c +++ b/drivers/infiniband/ulp/rtrs/rtrs-srv.c @@ -595,7 +595,7 @@ static int map_cont_bufs(struct rtrs_srv_path *srv_path) struct sg_table *sgt = &srv_mr->sgt; struct scatterlist *s; struct ib_mr *mr; - int nr, chunks; + int nr, nr_sgt, chunks; chunks = chunks_per_mr * mri; if (!always_invalidate) @@ -610,19 +610,19 @@ static int map_cont_bufs(struct rtrs_srv_path *srv_path) sg_set_page(s, srv->chunks[chunks + i], max_chunk_size, 0); - nr = ib_dma_map_sg(srv_path->s.dev->ib_dev, sgt->sgl, + nr_sgt = ib_dma_map_sg(srv_path->s.dev->ib_dev, sgt->sgl, sgt->nents, DMA_BIDIRECTIONAL); - if (nr < sgt->nents) { - err = nr < 0 ? nr : -EINVAL; + if (!nr_sgt) { + err = -EINVAL; goto free_sg; } mr = ib_alloc_mr(srv_path->s.dev->ib_pd, IB_MR_TYPE_MEM_REG, - sgt->nents); + nr_sgt); if (IS_ERR(mr)) { err = PTR_ERR(mr); goto unmap_sg; } - nr = ib_map_mr_sg(mr, sgt->sgl, sgt->nents, + nr = ib_map_mr_sg(mr, sgt->sgl, nr_sgt, NULL, max_chunk_size); if (nr < 0 || nr < sgt->nents) { err = nr < 0 ? nr : -EINVAL; @@ -641,7 +641,7 @@ static int map_cont_bufs(struct rtrs_srv_path *srv_path) } } /* Eventually dma addr for each chunk can be cached */ - for_each_sg(sgt->sgl, s, sgt->orig_nents, i) + for_each_sg(sgt->sgl, s, nr_sgt, i) srv_path->dma_addr[chunks + i] = sg_dma_address(s); ib_update_fast_reg_key(mr, ib_inc_rkey(mr->rkey)); diff --git a/drivers/infiniband/ulp/srp/ib_srp.c b/drivers/infiniband/ulp/srp/ib_srp.c index 7720ea270ed8..d7f69e593a63 100644 --- a/drivers/infiniband/ulp/srp/ib_srp.c +++ b/drivers/infiniband/ulp/srp/ib_srp.c @@ -1961,7 +1961,8 @@ static void srp_process_rsp(struct srp_rdma_ch *ch, struct srp_rsp *rsp) if (scmnd) { req = scsi_cmd_priv(scmnd); scmnd = srp_claim_req(ch, req, NULL, scmnd); - } else { + } + if (!scmnd) { shost_printk(KERN_ERR, target->scsi_host, "Null scmnd for RSP w/tag %#016llx received on ch %td / QP %#x\n", rsp->tag, ch - target->ch, ch->qp->qp_num); diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c index 65b8e4fd8217..828672a46a3d 100644 --- a/drivers/iommu/amd/iommu.c +++ b/drivers/iommu/amd/iommu.c @@ -939,7 +939,8 @@ static void build_completion_wait(struct iommu_cmd *cmd, memset(cmd, 0, sizeof(*cmd)); cmd->data[0] = lower_32_bits(paddr) | CMD_COMPL_WAIT_STORE_MASK; cmd->data[1] = upper_32_bits(paddr); - cmd->data[2] = data; + cmd->data[2] = lower_32_bits(data); + cmd->data[3] = upper_32_bits(data); CMD_SET_TYPE(cmd, CMD_COMPL_WAIT); } diff --git a/drivers/iommu/amd/iommu_v2.c b/drivers/iommu/amd/iommu_v2.c index 696d5555be57..6a1f02c62dff 100644 --- a/drivers/iommu/amd/iommu_v2.c +++ b/drivers/iommu/amd/iommu_v2.c @@ -777,6 +777,8 @@ int amd_iommu_init_device(struct pci_dev *pdev, int pasids) if (dev_state->domain == NULL) goto out_free_states; + /* See iommu_is_default_domain() */ + dev_state->domain->type = IOMMU_DOMAIN_IDENTITY; amd_iommu_domain_direct_map(dev_state->domain); ret = amd_iommu_domain_enable_v2(dev_state->domain, pasids); diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c index 7cca030a508e..31bc50e538a3 100644 --- a/drivers/iommu/intel/iommu.c +++ b/drivers/iommu/intel/iommu.c @@ -163,38 +163,6 @@ static phys_addr_t root_entry_uctp(struct root_entry *re) return re->hi & VTD_PAGE_MASK; } -static inline void context_clear_pasid_enable(struct context_entry *context) -{ - context->lo &= ~(1ULL << 11); -} - -static inline bool context_pasid_enabled(struct context_entry *context) -{ - return !!(context->lo & (1ULL << 11)); -} - -static inline void context_set_copied(struct context_entry *context) -{ - context->hi |= (1ull << 3); -} - -static inline bool context_copied(struct context_entry *context) -{ - return !!(context->hi & (1ULL << 3)); -} - -static inline bool __context_present(struct context_entry *context) -{ - return (context->lo & 1); -} - -bool context_present(struct context_entry *context) -{ - return context_pasid_enabled(context) ? - __context_present(context) : - __context_present(context) && !context_copied(context); -} - static inline void context_set_present(struct context_entry *context) { context->lo |= 1; @@ -242,6 +210,26 @@ static inline void context_clear_entry(struct context_entry *context) context->hi = 0; } +static inline bool context_copied(struct intel_iommu *iommu, u8 bus, u8 devfn) +{ + if (!iommu->copied_tables) + return false; + + return test_bit(((long)bus << 8) | devfn, iommu->copied_tables); +} + +static inline void +set_context_copied(struct intel_iommu *iommu, u8 bus, u8 devfn) +{ + set_bit(((long)bus << 8) | devfn, iommu->copied_tables); +} + +static inline void +clear_context_copied(struct intel_iommu *iommu, u8 bus, u8 devfn) +{ + clear_bit(((long)bus << 8) | devfn, iommu->copied_tables); +} + /* * This domain is a statically identity mapping domain. * 1. This domain creats a static 1:1 mapping to all usable memory. @@ -402,14 +390,36 @@ static inline int domain_pfn_supported(struct dmar_domain *domain, return !(addr_width < BITS_PER_LONG && pfn >> addr_width); } +/* + * Calculate the Supported Adjusted Guest Address Widths of an IOMMU. + * Refer to 11.4.2 of the VT-d spec for the encoding of each bit of + * the returned SAGAW. + */ +static unsigned long __iommu_calculate_sagaw(struct intel_iommu *iommu) +{ + unsigned long fl_sagaw, sl_sagaw; + + fl_sagaw = BIT(2) | (cap_5lp_support(iommu->cap) ? BIT(3) : 0); + sl_sagaw = cap_sagaw(iommu->cap); + + /* Second level only. */ + if (!sm_supported(iommu) || !ecap_flts(iommu->ecap)) + return sl_sagaw; + + /* First level only. */ + if (!ecap_slts(iommu->ecap)) + return fl_sagaw; + + return fl_sagaw & sl_sagaw; +} + static int __iommu_calculate_agaw(struct intel_iommu *iommu, int max_gaw) { unsigned long sagaw; int agaw; - sagaw = cap_sagaw(iommu->cap); - for (agaw = width_to_agaw(max_gaw); - agaw >= 0; agaw--) { + sagaw = __iommu_calculate_sagaw(iommu); + for (agaw = width_to_agaw(max_gaw); agaw >= 0; agaw--) { if (test_bit(agaw, &sagaw)) break; } @@ -505,8 +515,9 @@ static int domain_update_device_node(struct dmar_domain *domain) { struct device_domain_info *info; int nid = NUMA_NO_NODE; + unsigned long flags; - spin_lock(&domain->lock); + spin_lock_irqsave(&domain->lock, flags); list_for_each_entry(info, &domain->devices, link) { /* * There could possibly be multiple device numa nodes as devices @@ -518,7 +529,7 @@ static int domain_update_device_node(struct dmar_domain *domain) if (nid != NUMA_NO_NODE) break; } - spin_unlock(&domain->lock); + spin_unlock_irqrestore(&domain->lock, flags); return nid; } @@ -578,6 +589,13 @@ struct context_entry *iommu_context_addr(struct intel_iommu *iommu, u8 bus, struct context_entry *context; u64 *entry; + /* + * Except that the caller requested to allocate a new entry, + * returning a copied context entry makes no sense. + */ + if (!alloc && context_copied(iommu, bus, devfn)) + return NULL; + entry = &root->lo; if (sm_supported(iommu)) { if (devfn >= 0x80) { @@ -795,32 +813,11 @@ static void free_context_table(struct intel_iommu *iommu) } #ifdef CONFIG_DMAR_DEBUG -static void pgtable_walk(struct intel_iommu *iommu, unsigned long pfn, u8 bus, u8 devfn) +static void pgtable_walk(struct intel_iommu *iommu, unsigned long pfn, + u8 bus, u8 devfn, struct dma_pte *parent, int level) { - struct device_domain_info *info; - struct dma_pte *parent, *pte; - struct dmar_domain *domain; - struct pci_dev *pdev; - int offset, level; - - pdev = pci_get_domain_bus_and_slot(iommu->segment, bus, devfn); - if (!pdev) - return; - - info = dev_iommu_priv_get(&pdev->dev); - if (!info || !info->domain) { - pr_info("device [%02x:%02x.%d] not probed\n", - bus, PCI_SLOT(devfn), PCI_FUNC(devfn)); - return; - } - - domain = info->domain; - level = agaw_to_level(domain->agaw); - parent = domain->pgd; - if (!parent) { - pr_info("no page table setup\n"); - return; - } + struct dma_pte *pte; + int offset; while (1) { offset = pfn_level_offset(pfn, level); @@ -847,9 +844,10 @@ void dmar_fault_dump_ptes(struct intel_iommu *iommu, u16 source_id, struct pasid_entry *entries, *pte; struct context_entry *ctx_entry; struct root_entry *rt_entry; + int i, dir_index, index, level; u8 devfn = source_id & 0xff; u8 bus = source_id >> 8; - int i, dir_index, index; + struct dma_pte *pgtable; pr_info("Dump %s table entries for IOVA 0x%llx\n", iommu->name, addr); @@ -877,8 +875,11 @@ void dmar_fault_dump_ptes(struct intel_iommu *iommu, u16 source_id, ctx_entry->hi, ctx_entry->lo); /* legacy mode does not require PASID entries */ - if (!sm_supported(iommu)) + if (!sm_supported(iommu)) { + level = agaw_to_level(ctx_entry->hi & 7); + pgtable = phys_to_virt(ctx_entry->lo & VTD_PAGE_MASK); goto pgtable_walk; + } /* get the pointer to pasid directory entry */ dir = phys_to_virt(ctx_entry->lo & VTD_PAGE_MASK); @@ -905,8 +906,16 @@ void dmar_fault_dump_ptes(struct intel_iommu *iommu, u16 source_id, for (i = 0; i < ARRAY_SIZE(pte->val); i++) pr_info("pasid table entry[%d]: 0x%016llx\n", i, pte->val[i]); + if (pasid_pte_get_pgtt(pte) == PASID_ENTRY_PGTT_FL_ONLY) { + level = pte->val[2] & BIT_ULL(2) ? 5 : 4; + pgtable = phys_to_virt(pte->val[2] & VTD_PAGE_MASK); + } else { + level = agaw_to_level((pte->val[0] >> 2) & 0x7); + pgtable = phys_to_virt(pte->val[0] & VTD_PAGE_MASK); + } + pgtable_walk: - pgtable_walk(iommu, addr >> VTD_PAGE_SHIFT, bus, devfn); + pgtable_walk(iommu, addr >> VTD_PAGE_SHIFT, bus, devfn, pgtable, level); } #endif @@ -1345,19 +1354,20 @@ iommu_support_dev_iotlb(struct dmar_domain *domain, struct intel_iommu *iommu, u8 bus, u8 devfn) { struct device_domain_info *info; + unsigned long flags; if (!iommu->qi) return NULL; - spin_lock(&domain->lock); + spin_lock_irqsave(&domain->lock, flags); list_for_each_entry(info, &domain->devices, link) { if (info->iommu == iommu && info->bus == bus && info->devfn == devfn) { - spin_unlock(&domain->lock); + spin_unlock_irqrestore(&domain->lock, flags); return info->ats_supported ? info : NULL; } } - spin_unlock(&domain->lock); + spin_unlock_irqrestore(&domain->lock, flags); return NULL; } @@ -1366,8 +1376,9 @@ static void domain_update_iotlb(struct dmar_domain *domain) { struct device_domain_info *info; bool has_iotlb_device = false; + unsigned long flags; - spin_lock(&domain->lock); + spin_lock_irqsave(&domain->lock, flags); list_for_each_entry(info, &domain->devices, link) { if (info->ats_enabled) { has_iotlb_device = true; @@ -1375,7 +1386,7 @@ static void domain_update_iotlb(struct dmar_domain *domain) } } domain->has_iotlb_device = has_iotlb_device; - spin_unlock(&domain->lock); + spin_unlock_irqrestore(&domain->lock, flags); } static void iommu_enable_dev_iotlb(struct device_domain_info *info) @@ -1467,14 +1478,15 @@ static void iommu_flush_dev_iotlb(struct dmar_domain *domain, u64 addr, unsigned mask) { struct device_domain_info *info; + unsigned long flags; if (!domain->has_iotlb_device) return; - spin_lock(&domain->lock); + spin_lock_irqsave(&domain->lock, flags); list_for_each_entry(info, &domain->devices, link) __iommu_flush_dev_iotlb(info, addr, mask); - spin_unlock(&domain->lock); + spin_unlock_irqrestore(&domain->lock, flags); } static void iommu_flush_iotlb_psi(struct intel_iommu *iommu, @@ -1688,6 +1700,11 @@ static void free_dmar_iommu(struct intel_iommu *iommu) iommu->domain_ids = NULL; } + if (iommu->copied_tables) { + bitmap_free(iommu->copied_tables); + iommu->copied_tables = NULL; + } + /* free context mapping */ free_context_table(iommu); @@ -1913,7 +1930,7 @@ static int domain_context_mapping_one(struct dmar_domain *domain, goto out_unlock; ret = 0; - if (context_present(context)) + if (context_present(context) && !context_copied(iommu, bus, devfn)) goto out_unlock; /* @@ -1925,7 +1942,7 @@ static int domain_context_mapping_one(struct dmar_domain *domain, * in-flight DMA will exist, and we don't need to worry anymore * hereafter. */ - if (context_copied(context)) { + if (context_copied(iommu, bus, devfn)) { u16 did_old = context_domain_id(context); if (did_old < cap_ndoms(iommu->cap)) { @@ -1936,6 +1953,8 @@ static int domain_context_mapping_one(struct dmar_domain *domain, iommu->flush.flush_iotlb(iommu, did_old, 0, 0, DMA_TLB_DSI_FLUSH); } + + clear_context_copied(iommu, bus, devfn); } context_clear_entry(context); @@ -2429,6 +2448,7 @@ static int domain_add_dev_info(struct dmar_domain *domain, struct device *dev) { struct device_domain_info *info = dev_iommu_priv_get(dev); struct intel_iommu *iommu; + unsigned long flags; u8 bus, devfn; int ret; @@ -2440,9 +2460,9 @@ static int domain_add_dev_info(struct dmar_domain *domain, struct device *dev) if (ret) return ret; info->domain = domain; - spin_lock(&domain->lock); + spin_lock_irqsave(&domain->lock, flags); list_add(&info->link, &domain->devices); - spin_unlock(&domain->lock); + spin_unlock_irqrestore(&domain->lock, flags); /* PASID table is mandatory for a PCI device in scalable mode. */ if (sm_supported(iommu) && !dev_is_real_dma_subdevice(dev)) { @@ -2684,32 +2704,14 @@ static int copy_context_table(struct intel_iommu *iommu, /* Now copy the context entry */ memcpy(&ce, old_ce + idx, sizeof(ce)); - if (!__context_present(&ce)) + if (!context_present(&ce)) continue; did = context_domain_id(&ce); if (did >= 0 && did < cap_ndoms(iommu->cap)) set_bit(did, iommu->domain_ids); - /* - * We need a marker for copied context entries. This - * marker needs to work for the old format as well as - * for extended context entries. - * - * Bit 67 of the context entry is used. In the old - * format this bit is available to software, in the - * extended format it is the PGE bit, but PGE is ignored - * by HW if PASIDs are disabled (and thus still - * available). - * - * So disable PASIDs first and then mark the entry - * copied. This means that we don't copy PASID - * translations from the old kernel, but this is fine as - * faults there are not fatal. - */ - context_clear_pasid_enable(&ce); - context_set_copied(&ce); - + set_context_copied(iommu, bus, devfn); new_ce[idx] = ce; } @@ -2735,8 +2737,8 @@ static int copy_translation_tables(struct intel_iommu *iommu) bool new_ext, ext; rtaddr_reg = dmar_readq(iommu->reg + DMAR_RTADDR_REG); - ext = !!(rtaddr_reg & DMA_RTADDR_RTT); - new_ext = !!ecap_ecs(iommu->ecap); + ext = !!(rtaddr_reg & DMA_RTADDR_SMT); + new_ext = !!sm_supported(iommu); /* * The RTT bit can only be changed when translation is disabled, @@ -2747,6 +2749,10 @@ static int copy_translation_tables(struct intel_iommu *iommu) if (new_ext != ext) return -EINVAL; + iommu->copied_tables = bitmap_zalloc(BIT_ULL(16), GFP_KERNEL); + if (!iommu->copied_tables) + return -ENOMEM; + old_rt_phys = rtaddr_reg & VTD_PAGE_MASK; if (!old_rt_phys) return -EINVAL; @@ -4080,6 +4086,7 @@ static void dmar_remove_one_dev_info(struct device *dev) struct device_domain_info *info = dev_iommu_priv_get(dev); struct dmar_domain *domain = info->domain; struct intel_iommu *iommu = info->iommu; + unsigned long flags; if (!dev_is_real_dma_subdevice(info->dev)) { if (dev_is_pci(info->dev) && sm_supported(iommu)) @@ -4091,9 +4098,9 @@ static void dmar_remove_one_dev_info(struct device *dev) intel_pasid_free_table(info->dev); } - spin_lock(&domain->lock); + spin_lock_irqsave(&domain->lock, flags); list_del(&info->link); - spin_unlock(&domain->lock); + spin_unlock_irqrestore(&domain->lock, flags); domain_detach_iommu(domain, iommu); info->domain = NULL; @@ -4412,19 +4419,20 @@ static void domain_set_force_snooping(struct dmar_domain *domain) static bool intel_iommu_enforce_cache_coherency(struct iommu_domain *domain) { struct dmar_domain *dmar_domain = to_dmar_domain(domain); + unsigned long flags; if (dmar_domain->force_snooping) return true; - spin_lock(&dmar_domain->lock); + spin_lock_irqsave(&dmar_domain->lock, flags); if (!domain_support_force_snooping(dmar_domain)) { - spin_unlock(&dmar_domain->lock); + spin_unlock_irqrestore(&dmar_domain->lock, flags); return false; } domain_set_force_snooping(dmar_domain); dmar_domain->force_snooping = true; - spin_unlock(&dmar_domain->lock); + spin_unlock_irqrestore(&dmar_domain->lock, flags); return true; } diff --git a/drivers/iommu/intel/iommu.h b/drivers/iommu/intel/iommu.h index fae45bbb0c7f..74b0e19e23ee 100644 --- a/drivers/iommu/intel/iommu.h +++ b/drivers/iommu/intel/iommu.h @@ -197,7 +197,6 @@ #define ecap_dis(e) (((e) >> 27) & 0x1) #define ecap_nest(e) (((e) >> 26) & 0x1) #define ecap_mts(e) (((e) >> 25) & 0x1) -#define ecap_ecs(e) (((e) >> 24) & 0x1) #define ecap_iotlb_offset(e) ((((e) >> 8) & 0x3ff) * 16) #define ecap_max_iotlb_offset(e) (ecap_iotlb_offset(e) + 16) #define ecap_coherent(e) ((e) & 0x1) @@ -265,7 +264,6 @@ #define DMA_GSTS_CFIS (((u32)1) << 23) /* DMA_RTADDR_REG */ -#define DMA_RTADDR_RTT (((u64)1) << 11) #define DMA_RTADDR_SMT (((u64)1) << 10) /* CCMD_REG */ @@ -579,6 +577,7 @@ struct intel_iommu { #ifdef CONFIG_INTEL_IOMMU unsigned long *domain_ids; /* bitmap of domains */ + unsigned long *copied_tables; /* bitmap of copied tables */ spinlock_t lock; /* protect context, domain ids */ struct root_entry *root_entry; /* virtual address */ @@ -701,6 +700,11 @@ static inline int nr_pte_to_next_page(struct dma_pte *pte) (struct dma_pte *)ALIGN((unsigned long)pte, VTD_PAGE_SIZE) - pte; } +static inline bool context_present(struct context_entry *context) +{ + return (context->lo & 1); +} + extern struct dmar_drhd_unit * dmar_find_matched_drhd_unit(struct pci_dev *dev); extern int dmar_enable_qi(struct intel_iommu *iommu); @@ -784,7 +788,6 @@ static inline void intel_iommu_debugfs_init(void) {} #endif /* CONFIG_INTEL_IOMMU_DEBUGFS */ extern const struct attribute_group *intel_iommu_groups[]; -bool context_present(struct context_entry *context); struct context_entry *iommu_context_addr(struct intel_iommu *iommu, u8 bus, u8 devfn, int alloc); diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c index 780fb7071577..3a808146b50f 100644 --- a/drivers/iommu/iommu.c +++ b/drivers/iommu/iommu.c @@ -3076,6 +3076,24 @@ out: return ret; } +static bool iommu_is_default_domain(struct iommu_group *group) +{ + if (group->domain == group->default_domain) + return true; + + /* + * If the default domain was set to identity and it is still an identity + * domain then we consider this a pass. This happens because of + * amd_iommu_init_device() replacing the default idenytity domain with an + * identity domain that has a different configuration for AMDGPU. + */ + if (group->default_domain && + group->default_domain->type == IOMMU_DOMAIN_IDENTITY && + group->domain && group->domain->type == IOMMU_DOMAIN_IDENTITY) + return true; + return false; +} + /** * iommu_device_use_default_domain() - Device driver wants to handle device * DMA through the kernel DMA API. @@ -3094,8 +3112,7 @@ int iommu_device_use_default_domain(struct device *dev) mutex_lock(&group->mutex); if (group->owner_cnt) { - if (group->domain != group->default_domain || - group->owner) { + if (group->owner || !iommu_is_default_domain(group)) { ret = -EBUSY; goto unlock_out; } diff --git a/drivers/iommu/virtio-iommu.c b/drivers/iommu/virtio-iommu.c index 08eeafc9529f..80151176ba12 100644 --- a/drivers/iommu/virtio-iommu.c +++ b/drivers/iommu/virtio-iommu.c @@ -1006,7 +1006,18 @@ static int viommu_of_xlate(struct device *dev, struct of_phandle_args *args) return iommu_fwspec_add_ids(dev, args->args, 1); } +static bool viommu_capable(enum iommu_cap cap) +{ + switch (cap) { + case IOMMU_CAP_CACHE_COHERENCY: + return true; + default: + return false; + } +} + static struct iommu_ops viommu_ops = { + .capable = viommu_capable, .domain_alloc = viommu_domain_alloc, .probe_device = viommu_probe_device, .probe_finalize = viommu_probe_finalize, diff --git a/drivers/net/bonding/bond_3ad.c b/drivers/net/bonding/bond_3ad.c index 184608bd8999..e58a1e0cadd2 100644 --- a/drivers/net/bonding/bond_3ad.c +++ b/drivers/net/bonding/bond_3ad.c @@ -88,8 +88,9 @@ static const u8 null_mac_addr[ETH_ALEN + 2] __long_aligned = { static const u16 ad_ticks_per_sec = 1000 / AD_TIMER_INTERVAL; static const int ad_delta_in_ticks = (AD_TIMER_INTERVAL * HZ) / 1000; -static const u8 lacpdu_mcast_addr[ETH_ALEN + 2] __long_aligned = - MULTICAST_LACPDU_ADDR; +const u8 lacpdu_mcast_addr[ETH_ALEN + 2] __long_aligned = { + 0x01, 0x80, 0xC2, 0x00, 0x00, 0x02 +}; /* ================= main 802.3ad protocol functions ================== */ static int ad_lacpdu_send(struct port *port); diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index ddd07395827a..24bb50dfd362 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -865,12 +865,8 @@ static void bond_hw_addr_flush(struct net_device *bond_dev, dev_uc_unsync(slave_dev, bond_dev); dev_mc_unsync(slave_dev, bond_dev); - if (BOND_MODE(bond) == BOND_MODE_8023AD) { - /* del lacpdu mc addr from mc list */ - u8 lacpdu_multicast[ETH_ALEN] = MULTICAST_LACPDU_ADDR; - - dev_mc_del(slave_dev, lacpdu_multicast); - } + if (BOND_MODE(bond) == BOND_MODE_8023AD) + dev_mc_del(slave_dev, lacpdu_mcast_addr); } /*--------------------------- Active slave change ---------------------------*/ @@ -890,7 +886,8 @@ static void bond_hw_addr_swap(struct bonding *bond, struct slave *new_active, if (bond->dev->flags & IFF_ALLMULTI) dev_set_allmulti(old_active->dev, -1); - bond_hw_addr_flush(bond->dev, old_active->dev); + if (bond->dev->flags & IFF_UP) + bond_hw_addr_flush(bond->dev, old_active->dev); } if (new_active) { @@ -901,10 +898,12 @@ static void bond_hw_addr_swap(struct bonding *bond, struct slave *new_active, if (bond->dev->flags & IFF_ALLMULTI) dev_set_allmulti(new_active->dev, 1); - netif_addr_lock_bh(bond->dev); - dev_uc_sync(new_active->dev, bond->dev); - dev_mc_sync(new_active->dev, bond->dev); - netif_addr_unlock_bh(bond->dev); + if (bond->dev->flags & IFF_UP) { + netif_addr_lock_bh(bond->dev); + dev_uc_sync(new_active->dev, bond->dev); + dev_mc_sync(new_active->dev, bond->dev); + netif_addr_unlock_bh(bond->dev); + } } } @@ -2166,16 +2165,14 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev, } } - netif_addr_lock_bh(bond_dev); - dev_mc_sync_multiple(slave_dev, bond_dev); - dev_uc_sync_multiple(slave_dev, bond_dev); - netif_addr_unlock_bh(bond_dev); - - if (BOND_MODE(bond) == BOND_MODE_8023AD) { - /* add lacpdu mc addr to mc list */ - u8 lacpdu_multicast[ETH_ALEN] = MULTICAST_LACPDU_ADDR; + if (bond_dev->flags & IFF_UP) { + netif_addr_lock_bh(bond_dev); + dev_mc_sync_multiple(slave_dev, bond_dev); + dev_uc_sync_multiple(slave_dev, bond_dev); + netif_addr_unlock_bh(bond_dev); - dev_mc_add(slave_dev, lacpdu_multicast); + if (BOND_MODE(bond) == BOND_MODE_8023AD) + dev_mc_add(slave_dev, lacpdu_mcast_addr); } } @@ -2447,7 +2444,8 @@ static int __bond_release_one(struct net_device *bond_dev, if (old_flags & IFF_ALLMULTI) dev_set_allmulti(slave_dev, -1); - bond_hw_addr_flush(bond_dev, slave_dev); + if (old_flags & IFF_UP) + bond_hw_addr_flush(bond_dev, slave_dev); } slave_disable_netpoll(slave); @@ -4184,6 +4182,12 @@ static int bond_open(struct net_device *bond_dev) struct list_head *iter; struct slave *slave; + if (BOND_MODE(bond) == BOND_MODE_ROUNDROBIN && !bond->rr_tx_counter) { + bond->rr_tx_counter = alloc_percpu(u32); + if (!bond->rr_tx_counter) + return -ENOMEM; + } + /* reset slave->backup and slave->inactive */ if (bond_has_slaves(bond)) { bond_for_each_slave(bond, slave, iter) { @@ -4221,6 +4225,9 @@ static int bond_open(struct net_device *bond_dev) /* register to receive LACPDUs */ bond->recv_probe = bond_3ad_lacpdu_recv; bond_3ad_initiate_agg_selection(bond, 1); + + bond_for_each_slave(bond, slave, iter) + dev_mc_add(slave->dev, lacpdu_mcast_addr); } if (bond_mode_can_use_xmit_hash(bond)) @@ -4232,6 +4239,7 @@ static int bond_open(struct net_device *bond_dev) static int bond_close(struct net_device *bond_dev) { struct bonding *bond = netdev_priv(bond_dev); + struct slave *slave; bond_work_cancel_all(bond); bond->send_peer_notif = 0; @@ -4239,6 +4247,19 @@ static int bond_close(struct net_device *bond_dev) bond_alb_deinitialize(bond); bond->recv_probe = NULL; + if (bond_uses_primary(bond)) { + rcu_read_lock(); + slave = rcu_dereference(bond->curr_active_slave); + if (slave) + bond_hw_addr_flush(bond_dev, slave->dev); + rcu_read_unlock(); + } else { + struct list_head *iter; + + bond_for_each_slave(bond, slave, iter) + bond_hw_addr_flush(bond_dev, slave->dev); + } + return 0; } @@ -6228,15 +6249,6 @@ static int bond_init(struct net_device *bond_dev) if (!bond->wq) return -ENOMEM; - if (BOND_MODE(bond) == BOND_MODE_ROUNDROBIN) { - bond->rr_tx_counter = alloc_percpu(u32); - if (!bond->rr_tx_counter) { - destroy_workqueue(bond->wq); - bond->wq = NULL; - return -ENOMEM; - } - } - spin_lock_init(&bond->stats_lock); netdev_lockdep_set_classes(bond_dev); diff --git a/drivers/net/can/flexcan/flexcan-core.c b/drivers/net/can/flexcan/flexcan-core.c index 5e27944b8a21..5ee38e586fd8 100644 --- a/drivers/net/can/flexcan/flexcan-core.c +++ b/drivers/net/can/flexcan/flexcan-core.c @@ -941,11 +941,6 @@ static struct sk_buff *flexcan_mailbox_read(struct can_rx_offload *offload, u32 reg_ctrl, reg_id, reg_iflag1; int i; - if (unlikely(drop)) { - skb = ERR_PTR(-ENOBUFS); - goto mark_as_read; - } - mb = flexcan_get_mb(priv, n); if (priv->devtype_data.quirks & FLEXCAN_QUIRK_USE_RX_MAILBOX) { @@ -974,6 +969,11 @@ static struct sk_buff *flexcan_mailbox_read(struct can_rx_offload *offload, reg_ctrl = priv->read(&mb->can_ctrl); } + if (unlikely(drop)) { + skb = ERR_PTR(-ENOBUFS); + goto mark_as_read; + } + if (reg_ctrl & FLEXCAN_MB_CNT_EDL) skb = alloc_canfd_skb(offload->dev, &cfd); else diff --git a/drivers/net/can/usb/gs_usb.c b/drivers/net/can/usb/gs_usb.c index cc363f1935ce..5e0d280b0cd3 100644 --- a/drivers/net/can/usb/gs_usb.c +++ b/drivers/net/can/usb/gs_usb.c @@ -961,6 +961,7 @@ static int gs_can_open(struct net_device *netdev) flags |= GS_CAN_MODE_HW_TIMESTAMP; /* finally start device */ + dev->can.state = CAN_STATE_ERROR_ACTIVE; dm->mode = cpu_to_le32(GS_CAN_MODE_START); dm->flags = cpu_to_le32(flags); rc = usb_control_msg(interface_to_usbdev(dev->iface), @@ -972,6 +973,7 @@ static int gs_can_open(struct net_device *netdev) if (rc < 0) { netdev_err(netdev, "Couldn't start device (err=%d)\n", rc); kfree(dm); + dev->can.state = CAN_STATE_STOPPED; return rc; } @@ -981,8 +983,6 @@ static int gs_can_open(struct net_device *netdev) if (dev->feature & GS_CAN_FEATURE_HW_TIMESTAMP) gs_usb_timestamp_init(dev); - dev->can.state = CAN_STATE_ERROR_ACTIVE; - parent->active_channels++; if (!(dev->can.ctrlmode & CAN_CTRLMODE_LISTENONLY)) netif_start_queue(netdev); @@ -1081,17 +1081,21 @@ static int gs_usb_set_identify(struct net_device *netdev, bool do_identify) } /* blink LED's for finding the this interface */ -static int gs_usb_set_phys_id(struct net_device *dev, +static int gs_usb_set_phys_id(struct net_device *netdev, enum ethtool_phys_id_state state) { + const struct gs_can *dev = netdev_priv(netdev); int rc = 0; + if (!(dev->feature & GS_CAN_FEATURE_IDENTIFY)) + return -EOPNOTSUPP; + switch (state) { case ETHTOOL_ID_ACTIVE: - rc = gs_usb_set_identify(dev, GS_CAN_IDENTIFY_ON); + rc = gs_usb_set_identify(netdev, GS_CAN_IDENTIFY_ON); break; case ETHTOOL_ID_INACTIVE: - rc = gs_usb_set_identify(dev, GS_CAN_IDENTIFY_OFF); + rc = gs_usb_set_identify(netdev, GS_CAN_IDENTIFY_OFF); break; default: break; @@ -1240,9 +1244,10 @@ static struct gs_can *gs_make_candev(unsigned int channel, dev->feature |= GS_CAN_FEATURE_REQ_USB_QUIRK_LPC546XX | GS_CAN_FEATURE_QUIRK_BREQ_CANTACT_PRO; - if (le32_to_cpu(dconf->sw_version) > 1) - if (feature & GS_CAN_FEATURE_IDENTIFY) - netdev->ethtool_ops = &gs_usb_ethtool_ops; + /* GS_CAN_FEATURE_IDENTIFY is only supported for sw_version > 1 */ + if (!(le32_to_cpu(dconf->sw_version) > 1 && + feature & GS_CAN_FEATURE_IDENTIFY)) + dev->feature &= ~GS_CAN_FEATURE_IDENTIFY; kfree(bt_const); diff --git a/drivers/net/dsa/microchip/lan937x_main.c b/drivers/net/dsa/microchip/lan937x_main.c index 3e83f8ca0f09..cefe8517629a 100644 --- a/drivers/net/dsa/microchip/lan937x_main.c +++ b/drivers/net/dsa/microchip/lan937x_main.c @@ -298,10 +298,6 @@ void lan937x_port_setup(struct ksz_device *dev, int port, bool cpu_port) lan937x_port_cfg(dev, port, REG_PORT_CTRL_0, PORT_TAIL_TAG_ENABLE, true); - /* disable frame check length field */ - lan937x_port_cfg(dev, port, REG_PORT_MAC_CTRL_0, PORT_CHECK_LENGTH, - false); - /* set back pressure for half duplex */ lan937x_port_cfg(dev, port, REG_PORT_MAC_CTRL_1, PORT_BACK_PRESSURE, true); diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_main.c b/drivers/net/ethernet/aquantia/atlantic/aq_main.c index 88595863d8bc..8a0af371e7dc 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_main.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_main.c @@ -94,11 +94,8 @@ static int aq_ndev_close(struct net_device *ndev) int err = 0; err = aq_nic_stop(aq_nic); - if (err < 0) - goto err_exit; aq_nic_deinit(aq_nic, true); -err_exit: return err; } diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index f46eefb5a029..96da0ba3d507 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -659,7 +659,6 @@ static void bnxt_tx_int(struct bnxt *bp, struct bnxt_napi *bnapi, int nr_pkts) for (i = 0; i < nr_pkts; i++) { struct bnxt_sw_tx_bd *tx_buf; - bool compl_deferred = false; struct sk_buff *skb; int j, last; @@ -668,6 +667,8 @@ static void bnxt_tx_int(struct bnxt *bp, struct bnxt_napi *bnapi, int nr_pkts) skb = tx_buf->skb; tx_buf->skb = NULL; + tx_bytes += skb->len; + if (tx_buf->is_push) { tx_buf->is_push = 0; goto next_tx_int; @@ -688,8 +689,9 @@ static void bnxt_tx_int(struct bnxt *bp, struct bnxt_napi *bnapi, int nr_pkts) } if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_IN_PROGRESS)) { if (bp->flags & BNXT_FLAG_CHIP_P5) { + /* PTP worker takes ownership of the skb */ if (!bnxt_get_tx_ts_p5(bp, skb)) - compl_deferred = true; + skb = NULL; else atomic_inc(&bp->ptp_cfg->tx_avail); } @@ -698,9 +700,7 @@ static void bnxt_tx_int(struct bnxt *bp, struct bnxt_napi *bnapi, int nr_pkts) next_tx_int: cons = NEXT_TX(cons); - tx_bytes += skb->len; - if (!compl_deferred) - dev_kfree_skb_any(skb); + dev_kfree_skb_any(skb); } netdev_tx_completed_queue(txq, nr_pkts, tx_bytes); diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c index 7f3c0875b6f5..8e316367f6ce 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c @@ -317,9 +317,9 @@ void bnxt_ptp_cfg_tstamp_filters(struct bnxt *bp) if (!(bp->fw_cap & BNXT_FW_CAP_RX_ALL_PKT_TS) && (ptp->tstamp_filters & (PORT_MAC_CFG_REQ_FLAGS_ALL_RX_TS_CAPTURE_ENABLE | - PORT_MAC_CFG_REQ_FLAGS_PTP_RX_TS_CAPTURE_DISABLE))) { + PORT_MAC_CFG_REQ_FLAGS_ALL_RX_TS_CAPTURE_DISABLE))) { ptp->tstamp_filters &= ~(PORT_MAC_CFG_REQ_FLAGS_ALL_RX_TS_CAPTURE_ENABLE | - PORT_MAC_CFG_REQ_FLAGS_PTP_RX_TS_CAPTURE_DISABLE); + PORT_MAC_CFG_REQ_FLAGS_ALL_RX_TS_CAPTURE_DISABLE); netdev_warn(bp->dev, "Unsupported FW for all RX pkts timestamp filter\n"); } diff --git a/drivers/net/ethernet/freescale/enetc/Makefile b/drivers/net/ethernet/freescale/enetc/Makefile index a139f2e9d59f..e0e8dfd13793 100644 --- a/drivers/net/ethernet/freescale/enetc/Makefile +++ b/drivers/net/ethernet/freescale/enetc/Makefile @@ -9,7 +9,6 @@ fsl-enetc-$(CONFIG_FSL_ENETC_QOS) += enetc_qos.o obj-$(CONFIG_FSL_ENETC_VF) += fsl-enetc-vf.o fsl-enetc-vf-y := enetc_vf.o $(common-objs) -fsl-enetc-vf-$(CONFIG_FSL_ENETC_QOS) += enetc_qos.o obj-$(CONFIG_FSL_ENETC_IERB) += fsl-enetc-ierb.o fsl-enetc-ierb-y := enetc_ierb.o diff --git a/drivers/net/ethernet/freescale/enetc/enetc.c b/drivers/net/ethernet/freescale/enetc/enetc.c index 4470a4a3e4c3..9f5b921039bd 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc.c +++ b/drivers/net/ethernet/freescale/enetc/enetc.c @@ -2432,7 +2432,7 @@ int enetc_close(struct net_device *ndev) return 0; } -static int enetc_setup_tc_mqprio(struct net_device *ndev, void *type_data) +int enetc_setup_tc_mqprio(struct net_device *ndev, void *type_data) { struct enetc_ndev_priv *priv = netdev_priv(ndev); struct tc_mqprio_qopt *mqprio = type_data; @@ -2486,25 +2486,6 @@ static int enetc_setup_tc_mqprio(struct net_device *ndev, void *type_data) return 0; } -int enetc_setup_tc(struct net_device *ndev, enum tc_setup_type type, - void *type_data) -{ - switch (type) { - case TC_SETUP_QDISC_MQPRIO: - return enetc_setup_tc_mqprio(ndev, type_data); - case TC_SETUP_QDISC_TAPRIO: - return enetc_setup_tc_taprio(ndev, type_data); - case TC_SETUP_QDISC_CBS: - return enetc_setup_tc_cbs(ndev, type_data); - case TC_SETUP_QDISC_ETF: - return enetc_setup_tc_txtime(ndev, type_data); - case TC_SETUP_BLOCK: - return enetc_setup_tc_psfp(ndev, type_data); - default: - return -EOPNOTSUPP; - } -} - static int enetc_setup_xdp_prog(struct net_device *dev, struct bpf_prog *prog, struct netlink_ext_ack *extack) { @@ -2600,29 +2581,6 @@ static int enetc_set_rss(struct net_device *ndev, int en) return 0; } -static int enetc_set_psfp(struct net_device *ndev, int en) -{ - struct enetc_ndev_priv *priv = netdev_priv(ndev); - int err; - - if (en) { - err = enetc_psfp_enable(priv); - if (err) - return err; - - priv->active_offloads |= ENETC_F_QCI; - return 0; - } - - err = enetc_psfp_disable(priv); - if (err) - return err; - - priv->active_offloads &= ~ENETC_F_QCI; - - return 0; -} - static void enetc_enable_rxvlan(struct net_device *ndev, bool en) { struct enetc_ndev_priv *priv = netdev_priv(ndev); @@ -2641,11 +2599,9 @@ static void enetc_enable_txvlan(struct net_device *ndev, bool en) enetc_bdr_enable_txvlan(&priv->si->hw, i, en); } -int enetc_set_features(struct net_device *ndev, - netdev_features_t features) +void enetc_set_features(struct net_device *ndev, netdev_features_t features) { netdev_features_t changed = ndev->features ^ features; - int err = 0; if (changed & NETIF_F_RXHASH) enetc_set_rss(ndev, !!(features & NETIF_F_RXHASH)); @@ -2657,11 +2613,6 @@ int enetc_set_features(struct net_device *ndev, if (changed & NETIF_F_HW_VLAN_CTAG_TX) enetc_enable_txvlan(ndev, !!(features & NETIF_F_HW_VLAN_CTAG_TX)); - - if (changed & NETIF_F_HW_TC) - err = enetc_set_psfp(ndev, !!(features & NETIF_F_HW_TC)); - - return err; } #ifdef CONFIG_FSL_ENETC_PTP_CLOCK diff --git a/drivers/net/ethernet/freescale/enetc/enetc.h b/drivers/net/ethernet/freescale/enetc/enetc.h index 29922c20531f..2cfe6944ebd3 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc.h +++ b/drivers/net/ethernet/freescale/enetc/enetc.h @@ -393,11 +393,9 @@ void enetc_start(struct net_device *ndev); void enetc_stop(struct net_device *ndev); netdev_tx_t enetc_xmit(struct sk_buff *skb, struct net_device *ndev); struct net_device_stats *enetc_get_stats(struct net_device *ndev); -int enetc_set_features(struct net_device *ndev, - netdev_features_t features); +void enetc_set_features(struct net_device *ndev, netdev_features_t features); int enetc_ioctl(struct net_device *ndev, struct ifreq *rq, int cmd); -int enetc_setup_tc(struct net_device *ndev, enum tc_setup_type type, - void *type_data); +int enetc_setup_tc_mqprio(struct net_device *ndev, void *type_data); int enetc_setup_bpf(struct net_device *dev, struct netdev_bpf *xdp); int enetc_xdp_xmit(struct net_device *ndev, int num_frames, struct xdp_frame **frames, u32 flags); @@ -465,6 +463,7 @@ int enetc_setup_tc_block_cb(enum tc_setup_type type, void *type_data, int enetc_setup_tc_psfp(struct net_device *ndev, void *type_data); int enetc_psfp_init(struct enetc_ndev_priv *priv); int enetc_psfp_clean(struct enetc_ndev_priv *priv); +int enetc_set_psfp(struct net_device *ndev, bool en); static inline void enetc_get_max_cap(struct enetc_ndev_priv *priv) { @@ -540,4 +539,9 @@ static inline int enetc_psfp_disable(struct enetc_ndev_priv *priv) { return 0; } + +static inline int enetc_set_psfp(struct net_device *ndev, bool en) +{ + return 0; +} #endif diff --git a/drivers/net/ethernet/freescale/enetc/enetc_pf.c b/drivers/net/ethernet/freescale/enetc/enetc_pf.c index c4a0e836d4f0..bb7750222691 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc_pf.c +++ b/drivers/net/ethernet/freescale/enetc/enetc_pf.c @@ -709,6 +709,13 @@ static int enetc_pf_set_features(struct net_device *ndev, { netdev_features_t changed = ndev->features ^ features; struct enetc_ndev_priv *priv = netdev_priv(ndev); + int err; + + if (changed & NETIF_F_HW_TC) { + err = enetc_set_psfp(ndev, !!(features & NETIF_F_HW_TC)); + if (err) + return err; + } if (changed & NETIF_F_HW_VLAN_CTAG_FILTER) { struct enetc_pf *pf = enetc_si_priv(priv->si); @@ -722,7 +729,28 @@ static int enetc_pf_set_features(struct net_device *ndev, if (changed & NETIF_F_LOOPBACK) enetc_set_loopback(ndev, !!(features & NETIF_F_LOOPBACK)); - return enetc_set_features(ndev, features); + enetc_set_features(ndev, features); + + return 0; +} + +static int enetc_pf_setup_tc(struct net_device *ndev, enum tc_setup_type type, + void *type_data) +{ + switch (type) { + case TC_SETUP_QDISC_MQPRIO: + return enetc_setup_tc_mqprio(ndev, type_data); + case TC_SETUP_QDISC_TAPRIO: + return enetc_setup_tc_taprio(ndev, type_data); + case TC_SETUP_QDISC_CBS: + return enetc_setup_tc_cbs(ndev, type_data); + case TC_SETUP_QDISC_ETF: + return enetc_setup_tc_txtime(ndev, type_data); + case TC_SETUP_BLOCK: + return enetc_setup_tc_psfp(ndev, type_data); + default: + return -EOPNOTSUPP; + } } static const struct net_device_ops enetc_ndev_ops = { @@ -739,7 +767,7 @@ static const struct net_device_ops enetc_ndev_ops = { .ndo_set_vf_spoofchk = enetc_pf_set_vf_spoofchk, .ndo_set_features = enetc_pf_set_features, .ndo_eth_ioctl = enetc_ioctl, - .ndo_setup_tc = enetc_setup_tc, + .ndo_setup_tc = enetc_pf_setup_tc, .ndo_bpf = enetc_setup_bpf, .ndo_xdp_xmit = enetc_xdp_xmit, }; diff --git a/drivers/net/ethernet/freescale/enetc/enetc_qos.c b/drivers/net/ethernet/freescale/enetc/enetc_qos.c index 582a663ed0ba..f8a2f02ce22d 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc_qos.c +++ b/drivers/net/ethernet/freescale/enetc/enetc_qos.c @@ -1517,6 +1517,29 @@ int enetc_setup_tc_block_cb(enum tc_setup_type type, void *type_data, } } +int enetc_set_psfp(struct net_device *ndev, bool en) +{ + struct enetc_ndev_priv *priv = netdev_priv(ndev); + int err; + + if (en) { + err = enetc_psfp_enable(priv); + if (err) + return err; + + priv->active_offloads |= ENETC_F_QCI; + return 0; + } + + err = enetc_psfp_disable(priv); + if (err) + return err; + + priv->active_offloads &= ~ENETC_F_QCI; + + return 0; +} + int enetc_psfp_init(struct enetc_ndev_priv *priv) { if (epsfp.psfp_sfi_bitmap) diff --git a/drivers/net/ethernet/freescale/enetc/enetc_vf.c b/drivers/net/ethernet/freescale/enetc/enetc_vf.c index 17924305afa2..dfcaac302e24 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc_vf.c +++ b/drivers/net/ethernet/freescale/enetc/enetc_vf.c @@ -88,7 +88,20 @@ static int enetc_vf_set_mac_addr(struct net_device *ndev, void *addr) static int enetc_vf_set_features(struct net_device *ndev, netdev_features_t features) { - return enetc_set_features(ndev, features); + enetc_set_features(ndev, features); + + return 0; +} + +static int enetc_vf_setup_tc(struct net_device *ndev, enum tc_setup_type type, + void *type_data) +{ + switch (type) { + case TC_SETUP_QDISC_MQPRIO: + return enetc_setup_tc_mqprio(ndev, type_data); + default: + return -EOPNOTSUPP; + } } /* Probing/ Init */ @@ -100,7 +113,7 @@ static const struct net_device_ops enetc_ndev_ops = { .ndo_set_mac_address = enetc_vf_set_mac_addr, .ndo_set_features = enetc_vf_set_features, .ndo_eth_ioctl = enetc_ioctl, - .ndo_setup_tc = enetc_setup_tc, + .ndo_setup_tc = enetc_vf_setup_tc, }; static void enetc_vf_netdev_setup(struct enetc_si *si, struct net_device *ndev, diff --git a/drivers/net/ethernet/freescale/fec.h b/drivers/net/ethernet/freescale/fec.h index dd055d734363..b0100fe3c9e4 100644 --- a/drivers/net/ethernet/freescale/fec.h +++ b/drivers/net/ethernet/freescale/fec.h @@ -563,6 +563,7 @@ struct fec_enet_private { struct clk *clk_2x_txclk; bool ptp_clk_on; + struct mutex ptp_clk_mutex; unsigned int num_tx_queues; unsigned int num_rx_queues; @@ -641,13 +642,6 @@ struct fec_enet_private { int pps_enable; unsigned int next_counter; - struct { - struct timespec64 ts_phc; - u64 ns_sys; - u32 at_corr; - u8 at_inc_corr; - } ptp_saved_state; - struct imx_sc_ipc *ipc_handle; u64 ethtool_stats[]; @@ -660,8 +654,5 @@ void fec_ptp_disable_hwts(struct net_device *ndev); int fec_ptp_set(struct net_device *ndev, struct ifreq *ifr); int fec_ptp_get(struct net_device *ndev, struct ifreq *ifr); -void fec_ptp_save_state(struct fec_enet_private *fep); -int fec_ptp_restore_state(struct fec_enet_private *fep); - /****************************************************************************/ #endif /* FEC_H */ diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index d8b487f5c1ca..59921218a8a4 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -298,11 +298,8 @@ MODULE_PARM_DESC(macaddr, "FEC Ethernet MAC address"); #define FEC_MMFR_TA (2 << 16) #define FEC_MMFR_DATA(v) (v & 0xffff) /* FEC ECR bits definition */ -#define FEC_ECR_RESET BIT(0) -#define FEC_ECR_ETHEREN BIT(1) -#define FEC_ECR_MAGICEN BIT(2) -#define FEC_ECR_SLEEP BIT(3) -#define FEC_ECR_EN1588 BIT(4) +#define FEC_ECR_MAGICEN (1 << 2) +#define FEC_ECR_SLEEP (1 << 3) #define FEC_MII_TIMEOUT 30000 /* us */ @@ -998,9 +995,6 @@ fec_restart(struct net_device *ndev) u32 temp_mac[2]; u32 rcntl = OPT_FRAME_SIZE | 0x04; u32 ecntl = 0x2; /* ETHEREN */ - struct ptp_clock_request ptp_rq = { .type = PTP_CLK_REQ_PPS }; - - fec_ptp_save_state(fep); /* Whack a reset. We should wait for this. * For i.MX6SX SOC, enet use AXI bus, we use disable MAC @@ -1154,7 +1148,7 @@ fec_restart(struct net_device *ndev) } if (fep->bufdesc_ex) - ecntl |= FEC_ECR_EN1588; + ecntl |= (1 << 4); if (fep->quirks & FEC_QUIRK_DELAYED_CLKS_SUPPORT && fep->rgmii_txc_dly) @@ -1175,14 +1169,6 @@ fec_restart(struct net_device *ndev) if (fep->bufdesc_ex) fec_ptp_start_cyclecounter(ndev); - /* Restart PPS if needed */ - if (fep->pps_enable) { - /* Clear flag so fec_ptp_enable_pps() doesn't return immediately */ - fep->pps_enable = 0; - fec_ptp_restore_state(fep); - fep->ptp_caps.enable(&fep->ptp_caps, &ptp_rq, 1); - } - /* Enable interrupts we wish to service */ if (fep->link) writel(FEC_DEFAULT_IMASK, fep->hwp + FEC_IMASK); @@ -1263,8 +1249,6 @@ fec_stop(struct net_device *ndev) struct fec_enet_private *fep = netdev_priv(ndev); u32 rmii_mode = readl(fep->hwp + FEC_R_CNTRL) & (1 << 8); u32 val; - struct ptp_clock_request ptp_rq = { .type = PTP_CLK_REQ_PPS }; - u32 ecntl = 0; /* We cannot expect a graceful transmit stop without link !!! */ if (fep->link) { @@ -1274,8 +1258,6 @@ fec_stop(struct net_device *ndev) netdev_err(ndev, "Graceful transmit stop did not complete!\n"); } - fec_ptp_save_state(fep); - /* Whack a reset. We should wait for this. * For i.MX6SX SOC, enet use AXI bus, we use disable MAC * instead of reset MAC itself. @@ -1295,28 +1277,12 @@ fec_stop(struct net_device *ndev) writel(fep->phy_speed, fep->hwp + FEC_MII_SPEED); writel(FEC_DEFAULT_IMASK, fep->hwp + FEC_IMASK); - if (fep->bufdesc_ex) - ecntl |= FEC_ECR_EN1588; - /* We have to keep ENET enabled to have MII interrupt stay working */ if (fep->quirks & FEC_QUIRK_ENET_MAC && !(fep->wol_flag & FEC_WOL_FLAG_SLEEP_ON)) { - ecntl |= FEC_ECR_ETHEREN; + writel(2, fep->hwp + FEC_ECNTRL); writel(rmii_mode, fep->hwp + FEC_R_CNTRL); } - - writel(ecntl, fep->hwp + FEC_ECNTRL); - - if (fep->bufdesc_ex) - fec_ptp_start_cyclecounter(ndev); - - /* Restart PPS if needed */ - if (fep->pps_enable) { - /* Clear flag so fec_ptp_enable_pps() doesn't return immediately */ - fep->pps_enable = 0; - fec_ptp_restore_state(fep); - fep->ptp_caps.enable(&fep->ptp_caps, &ptp_rq, 1); - } } @@ -2071,7 +2037,6 @@ static void fec_enet_phy_reset_after_clk_enable(struct net_device *ndev) static int fec_enet_clk_enable(struct net_device *ndev, bool enable) { struct fec_enet_private *fep = netdev_priv(ndev); - unsigned long flags; int ret; if (enable) { @@ -2080,15 +2045,15 @@ static int fec_enet_clk_enable(struct net_device *ndev, bool enable) return ret; if (fep->clk_ptp) { - spin_lock_irqsave(&fep->tmreg_lock, flags); + mutex_lock(&fep->ptp_clk_mutex); ret = clk_prepare_enable(fep->clk_ptp); if (ret) { - spin_unlock_irqrestore(&fep->tmreg_lock, flags); + mutex_unlock(&fep->ptp_clk_mutex); goto failed_clk_ptp; } else { fep->ptp_clk_on = true; } - spin_unlock_irqrestore(&fep->tmreg_lock, flags); + mutex_unlock(&fep->ptp_clk_mutex); } ret = clk_prepare_enable(fep->clk_ref); @@ -2103,10 +2068,10 @@ static int fec_enet_clk_enable(struct net_device *ndev, bool enable) } else { clk_disable_unprepare(fep->clk_enet_out); if (fep->clk_ptp) { - spin_lock_irqsave(&fep->tmreg_lock, flags); + mutex_lock(&fep->ptp_clk_mutex); clk_disable_unprepare(fep->clk_ptp); fep->ptp_clk_on = false; - spin_unlock_irqrestore(&fep->tmreg_lock, flags); + mutex_unlock(&fep->ptp_clk_mutex); } clk_disable_unprepare(fep->clk_ref); clk_disable_unprepare(fep->clk_2x_txclk); @@ -2119,10 +2084,10 @@ failed_clk_2x_txclk: clk_disable_unprepare(fep->clk_ref); failed_clk_ref: if (fep->clk_ptp) { - spin_lock_irqsave(&fep->tmreg_lock, flags); + mutex_lock(&fep->ptp_clk_mutex); clk_disable_unprepare(fep->clk_ptp); fep->ptp_clk_on = false; - spin_unlock_irqrestore(&fep->tmreg_lock, flags); + mutex_unlock(&fep->ptp_clk_mutex); } failed_clk_ptp: clk_disable_unprepare(fep->clk_enet_out); @@ -3961,7 +3926,7 @@ fec_probe(struct platform_device *pdev) } fep->ptp_clk_on = false; - spin_lock_init(&fep->tmreg_lock); + mutex_init(&fep->ptp_clk_mutex); /* clk_ref is optional, depends on board */ fep->clk_ref = devm_clk_get_optional(&pdev->dev, "enet_clk_ref"); diff --git a/drivers/net/ethernet/freescale/fec_ptp.c b/drivers/net/ethernet/freescale/fec_ptp.c index 7be97ab84e50..cffd9ad499dd 100644 --- a/drivers/net/ethernet/freescale/fec_ptp.c +++ b/drivers/net/ethernet/freescale/fec_ptp.c @@ -365,19 +365,21 @@ static int fec_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta) */ static int fec_ptp_gettime(struct ptp_clock_info *ptp, struct timespec64 *ts) { - struct fec_enet_private *fep = + struct fec_enet_private *adapter = container_of(ptp, struct fec_enet_private, ptp_caps); u64 ns; unsigned long flags; - spin_lock_irqsave(&fep->tmreg_lock, flags); + mutex_lock(&adapter->ptp_clk_mutex); /* Check the ptp clock */ - if (!fep->ptp_clk_on) { - spin_unlock_irqrestore(&fep->tmreg_lock, flags); + if (!adapter->ptp_clk_on) { + mutex_unlock(&adapter->ptp_clk_mutex); return -EINVAL; } - ns = timecounter_read(&fep->tc); - spin_unlock_irqrestore(&fep->tmreg_lock, flags); + spin_lock_irqsave(&adapter->tmreg_lock, flags); + ns = timecounter_read(&adapter->tc); + spin_unlock_irqrestore(&adapter->tmreg_lock, flags); + mutex_unlock(&adapter->ptp_clk_mutex); *ts = ns_to_timespec64(ns); @@ -402,10 +404,10 @@ static int fec_ptp_settime(struct ptp_clock_info *ptp, unsigned long flags; u32 counter; - spin_lock_irqsave(&fep->tmreg_lock, flags); + mutex_lock(&fep->ptp_clk_mutex); /* Check the ptp clock */ if (!fep->ptp_clk_on) { - spin_unlock_irqrestore(&fep->tmreg_lock, flags); + mutex_unlock(&fep->ptp_clk_mutex); return -EINVAL; } @@ -415,9 +417,11 @@ static int fec_ptp_settime(struct ptp_clock_info *ptp, */ counter = ns & fep->cc.mask; + spin_lock_irqsave(&fep->tmreg_lock, flags); writel(counter, fep->hwp + FEC_ATIME); timecounter_init(&fep->tc, &fep->cc, ns); spin_unlock_irqrestore(&fep->tmreg_lock, flags); + mutex_unlock(&fep->ptp_clk_mutex); return 0; } @@ -514,11 +518,13 @@ static void fec_time_keep(struct work_struct *work) struct fec_enet_private *fep = container_of(dwork, struct fec_enet_private, time_keep); unsigned long flags; - spin_lock_irqsave(&fep->tmreg_lock, flags); + mutex_lock(&fep->ptp_clk_mutex); if (fep->ptp_clk_on) { + spin_lock_irqsave(&fep->tmreg_lock, flags); timecounter_read(&fep->tc); + spin_unlock_irqrestore(&fep->tmreg_lock, flags); } - spin_unlock_irqrestore(&fep->tmreg_lock, flags); + mutex_unlock(&fep->ptp_clk_mutex); schedule_delayed_work(&fep->time_keep, HZ); } @@ -593,6 +599,8 @@ void fec_ptp_init(struct platform_device *pdev, int irq_idx) } fep->ptp_inc = NSEC_PER_SEC / fep->cycle_speed; + spin_lock_init(&fep->tmreg_lock); + fec_ptp_start_cyclecounter(ndev); INIT_DELAYED_WORK(&fep->time_keep, fec_time_keep); @@ -625,36 +633,7 @@ void fec_ptp_stop(struct platform_device *pdev) struct net_device *ndev = platform_get_drvdata(pdev); struct fec_enet_private *fep = netdev_priv(ndev); - if (fep->pps_enable) - fec_ptp_enable_pps(fep, 0); - cancel_delayed_work_sync(&fep->time_keep); if (fep->ptp_clock) ptp_clock_unregister(fep->ptp_clock); } - -void fec_ptp_save_state(struct fec_enet_private *fep) -{ - u32 atime_inc_corr; - - fec_ptp_gettime(&fep->ptp_caps, &fep->ptp_saved_state.ts_phc); - fep->ptp_saved_state.ns_sys = ktime_get_ns(); - - fep->ptp_saved_state.at_corr = readl(fep->hwp + FEC_ATIME_CORR); - atime_inc_corr = readl(fep->hwp + FEC_ATIME_INC) & FEC_T_INC_CORR_MASK; - fep->ptp_saved_state.at_inc_corr = (u8)(atime_inc_corr >> FEC_T_INC_CORR_OFFSET); -} - -int fec_ptp_restore_state(struct fec_enet_private *fep) -{ - u32 atime_inc = readl(fep->hwp + FEC_ATIME_INC) & FEC_T_INC_MASK; - u64 ns_sys; - - writel(fep->ptp_saved_state.at_corr, fep->hwp + FEC_ATIME_CORR); - atime_inc |= ((u32)fep->ptp_saved_state.at_inc_corr) << FEC_T_INC_CORR_OFFSET; - writel(atime_inc, fep->hwp + FEC_ATIME_INC); - - ns_sys = ktime_get_ns() - fep->ptp_saved_state.ns_sys; - timespec64_add_ns(&fep->ptp_saved_state.ts_phc, ns_sys); - return fec_ptp_settime(&fep->ptp_caps, &fep->ptp_saved_state.ts_phc); -} diff --git a/drivers/net/ethernet/google/gve/gve_rx_dqo.c b/drivers/net/ethernet/google/gve/gve_rx_dqo.c index 8c939628e2d8..2e6461b0ea8b 100644 --- a/drivers/net/ethernet/google/gve/gve_rx_dqo.c +++ b/drivers/net/ethernet/google/gve/gve_rx_dqo.c @@ -157,7 +157,7 @@ static int gve_alloc_page_dqo(struct gve_priv *priv, int err; err = gve_alloc_page(priv, &priv->pdev->dev, &buf_state->page_info.page, - &buf_state->addr, DMA_FROM_DEVICE, GFP_KERNEL); + &buf_state->addr, DMA_FROM_DEVICE, GFP_ATOMIC); if (err) return err; diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 5e60ff79450d..3c8b70d31232 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -5902,6 +5902,26 @@ static int i40e_get_link_speed(struct i40e_vsi *vsi) } /** + * i40e_bw_bytes_to_mbits - Convert max_tx_rate from bytes to mbits + * @vsi: Pointer to vsi structure + * @max_tx_rate: max TX rate in bytes to be converted into Mbits + * + * Helper function to convert units before send to set BW limit + **/ +static u64 i40e_bw_bytes_to_mbits(struct i40e_vsi *vsi, u64 max_tx_rate) +{ + if (max_tx_rate < I40E_BW_MBPS_DIVISOR) { + dev_warn(&vsi->back->pdev->dev, + "Setting max tx rate to minimum usable value of 50Mbps.\n"); + max_tx_rate = I40E_BW_CREDIT_DIVISOR; + } else { + do_div(max_tx_rate, I40E_BW_MBPS_DIVISOR); + } + + return max_tx_rate; +} + +/** * i40e_set_bw_limit - setup BW limit for Tx traffic based on max_tx_rate * @vsi: VSI to be configured * @seid: seid of the channel/VSI @@ -5923,10 +5943,10 @@ int i40e_set_bw_limit(struct i40e_vsi *vsi, u16 seid, u64 max_tx_rate) max_tx_rate, seid); return -EINVAL; } - if (max_tx_rate && max_tx_rate < 50) { + if (max_tx_rate && max_tx_rate < I40E_BW_CREDIT_DIVISOR) { dev_warn(&pf->pdev->dev, "Setting max tx rate to minimum usable value of 50Mbps.\n"); - max_tx_rate = 50; + max_tx_rate = I40E_BW_CREDIT_DIVISOR; } /* Tx rate credits are in values of 50Mbps, 0 is disabled */ @@ -8217,9 +8237,9 @@ config_tc: if (i40e_is_tc_mqprio_enabled(pf)) { if (vsi->mqprio_qopt.max_rate[0]) { - u64 max_tx_rate = vsi->mqprio_qopt.max_rate[0]; + u64 max_tx_rate = i40e_bw_bytes_to_mbits(vsi, + vsi->mqprio_qopt.max_rate[0]); - do_div(max_tx_rate, I40E_BW_MBPS_DIVISOR); ret = i40e_set_bw_limit(vsi, vsi->seid, max_tx_rate); if (!ret) { u64 credits = max_tx_rate; @@ -10964,10 +10984,10 @@ static void i40e_rebuild(struct i40e_pf *pf, bool reinit, bool lock_acquired) } if (vsi->mqprio_qopt.max_rate[0]) { - u64 max_tx_rate = vsi->mqprio_qopt.max_rate[0]; + u64 max_tx_rate = i40e_bw_bytes_to_mbits(vsi, + vsi->mqprio_qopt.max_rate[0]); u64 credits = 0; - do_div(max_tx_rate, I40E_BW_MBPS_DIVISOR); ret = i40e_set_bw_limit(vsi, vsi->seid, max_tx_rate); if (ret) goto end_unlock; diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c index 4f184c50f6e8..7e9f6a69eb10 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c @@ -2039,6 +2039,25 @@ static void i40e_del_qch(struct i40e_vf *vf) } /** + * i40e_vc_get_max_frame_size + * @vf: pointer to the VF + * + * Max frame size is determined based on the current port's max frame size and + * whether a port VLAN is configured on this VF. The VF is not aware whether + * it's in a port VLAN so the PF needs to account for this in max frame size + * checks and sending the max frame size to the VF. + **/ +static u16 i40e_vc_get_max_frame_size(struct i40e_vf *vf) +{ + u16 max_frame_size = vf->pf->hw.phy.link_info.max_frame_size; + + if (vf->port_vlan_id) + max_frame_size -= VLAN_HLEN; + + return max_frame_size; +} + +/** * i40e_vc_get_vf_resources_msg * @vf: pointer to the VF info * @msg: pointer to the msg buffer @@ -2139,6 +2158,7 @@ static int i40e_vc_get_vf_resources_msg(struct i40e_vf *vf, u8 *msg) vfres->max_vectors = pf->hw.func_caps.num_msix_vectors_vf; vfres->rss_key_size = I40E_HKEY_ARRAY_SIZE; vfres->rss_lut_size = I40E_VF_HLUT_ARRAY_SIZE; + vfres->max_mtu = i40e_vc_get_max_frame_size(vf); if (vf->lan_vsi_idx) { vfres->vsi_res[0].vsi_id = vf->lan_vsi_id; diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c index 1671e52b6ba2..79fef8c59d65 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_main.c +++ b/drivers/net/ethernet/intel/iavf/iavf_main.c @@ -1077,7 +1077,6 @@ static int iavf_set_mac(struct net_device *netdev, void *p) { struct iavf_adapter *adapter = netdev_priv(netdev); struct sockaddr *addr = p; - bool handle_mac = iavf_is_mac_set_handled(netdev, addr->sa_data); int ret; if (!is_valid_ether_addr(addr->sa_data)) @@ -1094,10 +1093,9 @@ static int iavf_set_mac(struct net_device *netdev, void *p) return 0; } - if (handle_mac) - goto done; - - ret = wait_event_interruptible_timeout(adapter->vc_waitqueue, false, msecs_to_jiffies(2500)); + ret = wait_event_interruptible_timeout(adapter->vc_waitqueue, + iavf_is_mac_set_handled(netdev, addr->sa_data), + msecs_to_jiffies(2500)); /* If ret < 0 then it means wait was interrupted. * If ret == 0 then it means we got a timeout. @@ -1111,7 +1109,6 @@ static int iavf_set_mac(struct net_device *netdev, void *p) if (!ret) return -EAGAIN; -done: if (!ether_addr_equal(netdev->dev_addr, addr->sa_data)) return -EACCES; diff --git a/drivers/net/ethernet/intel/iavf/iavf_txrx.c b/drivers/net/ethernet/intel/iavf/iavf_txrx.c index 06d18797d25a..18b6a702a1d6 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_txrx.c +++ b/drivers/net/ethernet/intel/iavf/iavf_txrx.c @@ -114,8 +114,11 @@ u32 iavf_get_tx_pending(struct iavf_ring *ring, bool in_sw) { u32 head, tail; + /* underlying hardware might not allow access and/or always return + * 0 for the head/tail registers so just use the cached values + */ head = ring->next_to_clean; - tail = readl(ring->tail); + tail = ring->next_to_use; if (head != tail) return (head < tail) ? @@ -1390,7 +1393,7 @@ static struct sk_buff *iavf_build_skb(struct iavf_ring *rx_ring, #endif struct sk_buff *skb; - if (!rx_buffer) + if (!rx_buffer || !size) return NULL; /* prefetch first cache line of first page */ va = page_address(rx_buffer->page) + rx_buffer->page_offset; @@ -1548,7 +1551,7 @@ static int iavf_clean_rx_irq(struct iavf_ring *rx_ring, int budget) /* exit if we failed to retrieve a buffer */ if (!skb) { rx_ring->rx_stats.alloc_buff_failed++; - if (rx_buffer) + if (rx_buffer && size) rx_buffer->pagecnt_bias++; break; } diff --git a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c index 15ee85dc33bd..5a9e6563923e 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c +++ b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c @@ -269,11 +269,14 @@ int iavf_get_vf_vlan_v2_caps(struct iavf_adapter *adapter) void iavf_configure_queues(struct iavf_adapter *adapter) { struct virtchnl_vsi_queue_config_info *vqci; - struct virtchnl_queue_pair_info *vqpi; + int i, max_frame = adapter->vf_res->max_mtu; int pairs = adapter->num_active_queues; - int i, max_frame = IAVF_MAX_RXBUFFER; + struct virtchnl_queue_pair_info *vqpi; size_t len; + if (max_frame > IAVF_MAX_RXBUFFER || !max_frame) + max_frame = IAVF_MAX_RXBUFFER; + if (adapter->current_op != VIRTCHNL_OP_UNKNOWN) { /* bail because we already have a command pending */ dev_err(&adapter->pdev->dev, "Cannot configure queues, command %d pending\n", diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c index d126f4cb3ba8..8a80da8e910e 100644 --- a/drivers/net/ethernet/intel/ice/ice_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_lib.c @@ -914,7 +914,7 @@ static void ice_set_dflt_vsi_ctx(struct ice_hw *hw, struct ice_vsi_ctx *ctxt) */ static int ice_vsi_setup_q_map(struct ice_vsi *vsi, struct ice_vsi_ctx *ctxt) { - u16 offset = 0, qmap = 0, tx_count = 0, pow = 0; + u16 offset = 0, qmap = 0, tx_count = 0, rx_count = 0, pow = 0; u16 num_txq_per_tc, num_rxq_per_tc; u16 qcount_tx = vsi->alloc_txq; u16 qcount_rx = vsi->alloc_rxq; @@ -981,23 +981,25 @@ static int ice_vsi_setup_q_map(struct ice_vsi *vsi, struct ice_vsi_ctx *ctxt) * at least 1) */ if (offset) - vsi->num_rxq = offset; + rx_count = offset; else - vsi->num_rxq = num_rxq_per_tc; + rx_count = num_rxq_per_tc; - if (vsi->num_rxq > vsi->alloc_rxq) { + if (rx_count > vsi->alloc_rxq) { dev_err(ice_pf_to_dev(vsi->back), "Trying to use more Rx queues (%u), than were allocated (%u)!\n", - vsi->num_rxq, vsi->alloc_rxq); + rx_count, vsi->alloc_rxq); return -EINVAL; } - vsi->num_txq = tx_count; - if (vsi->num_txq > vsi->alloc_txq) { + if (tx_count > vsi->alloc_txq) { dev_err(ice_pf_to_dev(vsi->back), "Trying to use more Tx queues (%u), than were allocated (%u)!\n", - vsi->num_txq, vsi->alloc_txq); + tx_count, vsi->alloc_txq); return -EINVAL; } + vsi->num_txq = tx_count; + vsi->num_rxq = rx_count; + if (vsi->type == ICE_VSI_VF && vsi->num_txq != vsi->num_rxq) { dev_dbg(ice_pf_to_dev(vsi->back), "VF VSI should have same number of Tx and Rx queues. Hence making them equal\n"); /* since there is a chance that num_rxq could have been changed @@ -3513,6 +3515,7 @@ ice_vsi_setup_q_map_mqprio(struct ice_vsi *vsi, struct ice_vsi_ctx *ctxt, u16 pow, offset = 0, qcount_tx = 0, qcount_rx = 0, qmap; u16 tc0_offset = vsi->mqprio_qopt.qopt.offset[0]; int tc0_qcount = vsi->mqprio_qopt.qopt.count[0]; + u16 new_txq, new_rxq; u8 netdev_tc = 0; int i; @@ -3553,21 +3556,24 @@ ice_vsi_setup_q_map_mqprio(struct ice_vsi *vsi, struct ice_vsi_ctx *ctxt, } } - /* Set actual Tx/Rx queue pairs */ - vsi->num_txq = offset + qcount_tx; - if (vsi->num_txq > vsi->alloc_txq) { + new_txq = offset + qcount_tx; + if (new_txq > vsi->alloc_txq) { dev_err(ice_pf_to_dev(vsi->back), "Trying to use more Tx queues (%u), than were allocated (%u)!\n", - vsi->num_txq, vsi->alloc_txq); + new_txq, vsi->alloc_txq); return -EINVAL; } - vsi->num_rxq = offset + qcount_rx; - if (vsi->num_rxq > vsi->alloc_rxq) { + new_rxq = offset + qcount_rx; + if (new_rxq > vsi->alloc_rxq) { dev_err(ice_pf_to_dev(vsi->back), "Trying to use more Rx queues (%u), than were allocated (%u)!\n", - vsi->num_rxq, vsi->alloc_rxq); + new_rxq, vsi->alloc_rxq); return -EINVAL; } + /* Set actual Tx/Rx queue pairs */ + vsi->num_txq = new_txq; + vsi->num_rxq = new_rxq; + /* Setup queue TC[0].qmap for given VSI context */ ctxt->info.tc_mapping[0] = cpu_to_le16(qmap); ctxt->info.q_mapping[0] = cpu_to_le16(vsi->rxq_map[0]); @@ -3599,6 +3605,7 @@ int ice_vsi_cfg_tc(struct ice_vsi *vsi, u8 ena_tc) { u16 max_txqs[ICE_MAX_TRAFFIC_CLASS] = { 0 }; struct ice_pf *pf = vsi->back; + struct ice_tc_cfg old_tc_cfg; struct ice_vsi_ctx *ctx; struct device *dev; int i, ret = 0; @@ -3623,6 +3630,7 @@ int ice_vsi_cfg_tc(struct ice_vsi *vsi, u8 ena_tc) max_txqs[i] = vsi->num_txq; } + memcpy(&old_tc_cfg, &vsi->tc_cfg, sizeof(old_tc_cfg)); vsi->tc_cfg.ena_tc = ena_tc; vsi->tc_cfg.numtc = num_tc; @@ -3639,8 +3647,10 @@ int ice_vsi_cfg_tc(struct ice_vsi *vsi, u8 ena_tc) else ret = ice_vsi_setup_q_map(vsi, ctx); - if (ret) + if (ret) { + memcpy(&vsi->tc_cfg, &old_tc_cfg, sizeof(vsi->tc_cfg)); goto out; + } /* must to indicate which section of VSI context are being modified */ ctx->info.valid_sections = cpu_to_le16(ICE_AQ_VSI_PROP_RXQ_MAP_VALID); diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index aa26672b7205..0ccc8a750374 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -2399,8 +2399,6 @@ int ice_schedule_reset(struct ice_pf *pf, enum ice_reset_req reset) return -EBUSY; } - ice_unplug_aux_dev(pf); - switch (reset) { case ICE_RESET_PFR: set_bit(ICE_PFR_REQ, pf->state); @@ -6726,7 +6724,7 @@ static void ice_napi_disable_all(struct ice_vsi *vsi) */ int ice_down(struct ice_vsi *vsi) { - int i, tx_err, rx_err, link_err = 0, vlan_err = 0; + int i, tx_err, rx_err, vlan_err = 0; WARN_ON(!test_bit(ICE_VSI_DOWN, vsi->state)); @@ -6760,20 +6758,13 @@ int ice_down(struct ice_vsi *vsi) ice_napi_disable_all(vsi); - if (test_bit(ICE_FLAG_LINK_DOWN_ON_CLOSE_ENA, vsi->back->flags)) { - link_err = ice_force_phys_link_state(vsi, false); - if (link_err) - netdev_err(vsi->netdev, "Failed to set physical link down, VSI %d error %d\n", - vsi->vsi_num, link_err); - } - ice_for_each_txq(vsi, i) ice_clean_tx_ring(vsi->tx_rings[i]); ice_for_each_rxq(vsi, i) ice_clean_rx_ring(vsi->rx_rings[i]); - if (tx_err || rx_err || link_err || vlan_err) { + if (tx_err || rx_err || vlan_err) { netdev_err(vsi->netdev, "Failed to close VSI 0x%04X on switch 0x%04X\n", vsi->vsi_num, vsi->vsw->sw_id); return -EIO; @@ -6960,6 +6951,8 @@ int ice_vsi_open(struct ice_vsi *vsi) if (err) goto err_setup_rx; + ice_vsi_cfg_netdev_tc(vsi, vsi->tc_cfg.ena_tc); + if (vsi->type == ICE_VSI_PF) { /* Notify the stack of the actual queue counts. */ err = netif_set_real_num_tx_queues(vsi->netdev, vsi->num_txq); @@ -8992,6 +8985,16 @@ int ice_stop(struct net_device *netdev) return -EBUSY; } + if (test_bit(ICE_FLAG_LINK_DOWN_ON_CLOSE_ENA, vsi->back->flags)) { + int link_err = ice_force_phys_link_state(vsi, false); + + if (link_err) { + netdev_err(vsi->netdev, "Failed to set physical link down, VSI %d error %d\n", + vsi->vsi_num, link_err); + return -EIO; + } + } + ice_vsi_close(vsi); return 0; diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c index 42b42f4b21ef..a5a0c9706b5a 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx.c +++ b/drivers/net/ethernet/intel/ice/ice_txrx.c @@ -610,7 +610,7 @@ ice_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames, if (test_bit(ICE_VSI_DOWN, vsi->state)) return -ENETDOWN; - if (!ice_is_xdp_ena_vsi(vsi) || queue_index >= vsi->num_xdp_txq) + if (!ice_is_xdp_ena_vsi(vsi)) return -ENXIO; if (unlikely(flags & ~XDP_XMIT_FLAGS_MASK)) @@ -621,6 +621,9 @@ ice_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames, xdp_ring = vsi->xdp_rings[queue_index]; spin_lock(&xdp_ring->tx_lock); } else { + /* Generally, should not happen */ + if (unlikely(queue_index >= vsi->num_xdp_txq)) + return -ENXIO; xdp_ring = vsi->xdp_rings[queue_index]; } diff --git a/drivers/net/ethernet/marvell/prestera/prestera_main.c b/drivers/net/ethernet/marvell/prestera/prestera_main.c index 3956d6d5df3c..639d3e940a88 100644 --- a/drivers/net/ethernet/marvell/prestera/prestera_main.c +++ b/drivers/net/ethernet/marvell/prestera/prestera_main.c @@ -373,6 +373,7 @@ static int prestera_port_sfp_bind(struct prestera_port *port) if (!sw->np) return 0; + of_node_get(sw->np); ports = of_find_node_by_name(sw->np, "ports"); for_each_child_of_node(ports, node) { @@ -422,6 +423,7 @@ static int prestera_port_sfp_bind(struct prestera_port *port) } out: + of_node_put(node); of_node_put(ports); return err; } diff --git a/drivers/net/ethernet/marvell/prestera/prestera_pci.c b/drivers/net/ethernet/marvell/prestera/prestera_pci.c index f538a749ebd4..59470d99f522 100644 --- a/drivers/net/ethernet/marvell/prestera/prestera_pci.c +++ b/drivers/net/ethernet/marvell/prestera/prestera_pci.c @@ -872,6 +872,7 @@ static void prestera_pci_remove(struct pci_dev *pdev) static const struct pci_device_id prestera_pci_devices[] = { { PCI_DEVICE(PCI_VENDOR_ID_MARVELL, 0xC804) }, { PCI_DEVICE(PCI_VENDOR_ID_MARVELL, 0xC80C) }, + { PCI_DEVICE(PCI_VENDOR_ID_MARVELL, 0xCC1E) }, { } }; MODULE_DEVICE_TABLE(pci, prestera_pci_devices); diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c index 516875cd698f..49b7e8c1f4bd 100644 --- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c +++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c @@ -1470,7 +1470,7 @@ static void mtk_update_rx_cpu_idx(struct mtk_eth *eth) static bool mtk_page_pool_enabled(struct mtk_eth *eth) { - return !eth->hwlro; + return MTK_HAS_CAPS(eth->soc->caps, MTK_NETSYS_V2); } static struct page_pool *mtk_create_page_pool(struct mtk_eth *eth, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index 1986f1c715b5..b45cef89370e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -494,6 +494,24 @@ static int max_uc_list_get_devlink_param(struct mlx5_core_dev *dev) return err; } +bool mlx5_is_roce_on(struct mlx5_core_dev *dev) +{ + struct devlink *devlink = priv_to_devlink(dev); + union devlink_param_value val; + int err; + + err = devlink_param_driverinit_value_get(devlink, + DEVLINK_PARAM_GENERIC_ID_ENABLE_ROCE, + &val); + + if (!err) + return val.vbool; + + mlx5_core_dbg(dev, "Failed to get param. err = %d\n", err); + return MLX5_CAP_GEN(dev, roce); +} +EXPORT_SYMBOL(mlx5_is_roce_on); + static int handle_hca_cap_2(struct mlx5_core_dev *dev, void *set_ctx) { void *set_hca_cap; @@ -597,7 +615,8 @@ static int handle_hca_cap(struct mlx5_core_dev *dev, void *set_ctx) MLX5_CAP_GEN_MAX(dev, num_total_dynamic_vf_msix)); if (MLX5_CAP_GEN(dev, roce_rw_supported)) - MLX5_SET(cmd_hca_cap, set_hca_cap, roce, mlx5_is_roce_init_enabled(dev)); + MLX5_SET(cmd_hca_cap, set_hca_cap, roce, + mlx5_is_roce_on(dev)); max_uc_list = max_uc_list_get_devlink_param(dev); if (max_uc_list > 0) @@ -623,7 +642,7 @@ static int handle_hca_cap(struct mlx5_core_dev *dev, void *set_ctx) */ static bool is_roce_fw_disabled(struct mlx5_core_dev *dev) { - return (MLX5_CAP_GEN(dev, roce_rw_supported) && !mlx5_is_roce_init_enabled(dev)) || + return (MLX5_CAP_GEN(dev, roce_rw_supported) && !mlx5_is_roce_on(dev)) || (!MLX5_CAP_GEN(dev, roce_rw_supported) && !MLX5_CAP_GEN(dev, roce)); } diff --git a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_mdio.c b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_mdio.c index 85155cd9405c..4aeb927c3715 100644 --- a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_mdio.c +++ b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_mdio.c @@ -179,6 +179,9 @@ static int mlxbf_gige_mdio_read(struct mii_bus *bus, int phy_add, int phy_reg) /* Only return ad bits of the gw register */ ret &= MLXBF_GIGE_MDIO_GW_AD_MASK; + /* The MDIO lock is set on read. To release it, clear gw register */ + writel(0, priv->mdio_io + MLXBF_GIGE_MDIO_GW_OFFSET); + return ret; } @@ -203,6 +206,9 @@ static int mlxbf_gige_mdio_write(struct mii_bus *bus, int phy_add, temp, !(temp & MLXBF_GIGE_MDIO_GW_BUSY_MASK), 5, 1000000); + /* The MDIO lock is set on read. To release it, clear gw register */ + writel(0, priv->mdio_io + MLXBF_GIGE_MDIO_GW_OFFSET); + return ret; } diff --git a/drivers/net/ethernet/microsoft/mana/gdma_main.c b/drivers/net/ethernet/microsoft/mana/gdma_main.c index 5f9240182351..a6f99b4344d9 100644 --- a/drivers/net/ethernet/microsoft/mana/gdma_main.c +++ b/drivers/net/ethernet/microsoft/mana/gdma_main.c @@ -397,6 +397,11 @@ static void mana_gd_process_eq_events(void *arg) break; } + /* Per GDMA spec, rmb is necessary after checking owner_bits, before + * reading eqe. + */ + rmb(); + mana_gd_process_eqe(eq); eq->head++; @@ -1134,6 +1139,11 @@ static int mana_gd_read_cqe(struct gdma_queue *cq, struct gdma_comp *comp) if (WARN_ON_ONCE(owner_bits != new_bits)) return -1; + /* Per GDMA spec, rmb is necessary after checking owner_bits, before + * reading completion info + */ + rmb(); + comp->wq_num = cqe->cqe_info.wq_num; comp->is_sq = cqe->cqe_info.is_sq; memcpy(comp->cqe_data, cqe->cqe_data, GDMA_COMP_DATA_SIZE); @@ -1465,10 +1475,6 @@ static void mana_gd_shutdown(struct pci_dev *pdev) pci_disable_device(pdev); } -#ifndef PCI_VENDOR_ID_MICROSOFT -#define PCI_VENDOR_ID_MICROSOFT 0x1414 -#endif - static const struct pci_device_id mana_id_table[] = { { PCI_DEVICE(PCI_VENDOR_ID_MICROSOFT, MANA_PF_DEVICE_ID) }, { PCI_DEVICE(PCI_VENDOR_ID_MICROSOFT, MANA_VF_DEVICE_ID) }, diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c index a550ffec9000..c992bf1c711e 100644 --- a/drivers/net/ethernet/renesas/ravb_main.c +++ b/drivers/net/ethernet/renesas/ravb_main.c @@ -1455,6 +1455,8 @@ static int ravb_phy_init(struct net_device *ndev) phy_remove_link_mode(phydev, ETHTOOL_LINK_MODE_100baseT_Half_BIT); } + /* Indicate that the MAC is responsible for managing PHY PM */ + phydev->mac_managed_pm = true; phy_attached_info(phydev); return 0; diff --git a/drivers/net/ethernet/renesas/sh_eth.c b/drivers/net/ethernet/renesas/sh_eth.c index 67ade78fb767..7fd8828d3a84 100644 --- a/drivers/net/ethernet/renesas/sh_eth.c +++ b/drivers/net/ethernet/renesas/sh_eth.c @@ -2029,6 +2029,8 @@ static int sh_eth_phy_init(struct net_device *ndev) if (mdp->cd->register_type != SH_ETH_REG_GIGABIT) phy_set_max_speed(phydev, SPEED_100); + /* Indicate that the MAC is responsible for managing PHY PM */ + phydev->mac_managed_pm = true; phy_attached_info(phydev); return 0; diff --git a/drivers/net/ethernet/sfc/efx_channels.c b/drivers/net/ethernet/sfc/efx_channels.c index 032b8c0bd788..5b4d661ab986 100644 --- a/drivers/net/ethernet/sfc/efx_channels.c +++ b/drivers/net/ethernet/sfc/efx_channels.c @@ -319,7 +319,7 @@ int efx_probe_interrupts(struct efx_nic *efx) efx->n_channels = 1 + (efx_separate_tx_channels ? 1 : 0); efx->n_rx_channels = 1; efx->n_tx_channels = 1; - efx->tx_channel_offset = 1; + efx->tx_channel_offset = efx_separate_tx_channels ? 1 : 0; efx->n_xdp_channels = 0; efx->xdp_channel_offset = efx->n_channels; efx->legacy_irq = efx->pci_dev->irq; diff --git a/drivers/net/ethernet/sfc/siena/efx_channels.c b/drivers/net/ethernet/sfc/siena/efx_channels.c index 017212a40df3..f54ebd007286 100644 --- a/drivers/net/ethernet/sfc/siena/efx_channels.c +++ b/drivers/net/ethernet/sfc/siena/efx_channels.c @@ -320,7 +320,7 @@ int efx_siena_probe_interrupts(struct efx_nic *efx) efx->n_channels = 1 + (efx_siena_separate_tx_channels ? 1 : 0); efx->n_rx_channels = 1; efx->n_tx_channels = 1; - efx->tx_channel_offset = 1; + efx->tx_channel_offset = efx_siena_separate_tx_channels ? 1 : 0; efx->n_xdp_channels = 0; efx->xdp_channel_offset = efx->n_channels; efx->legacy_irq = efx->pci_dev->irq; diff --git a/drivers/net/ethernet/sfc/siena/tx.c b/drivers/net/ethernet/sfc/siena/tx.c index e166dcb9b99c..91e87594ed1e 100644 --- a/drivers/net/ethernet/sfc/siena/tx.c +++ b/drivers/net/ethernet/sfc/siena/tx.c @@ -336,7 +336,7 @@ netdev_tx_t efx_siena_hard_start_xmit(struct sk_buff *skb, * previous packets out. */ if (!netdev_xmit_more()) - efx_tx_send_pending(tx_queue->channel); + efx_tx_send_pending(efx_get_tx_channel(efx, index)); return NETDEV_TX_OK; } diff --git a/drivers/net/ethernet/sfc/tx.c b/drivers/net/ethernet/sfc/tx.c index d12474042c84..c5f88f7a7a04 100644 --- a/drivers/net/ethernet/sfc/tx.c +++ b/drivers/net/ethernet/sfc/tx.c @@ -549,7 +549,7 @@ netdev_tx_t efx_hard_start_xmit(struct sk_buff *skb, * previous packets out. */ if (!netdev_xmit_more()) - efx_tx_send_pending(tx_queue->channel); + efx_tx_send_pending(efx_get_tx_channel(efx, index)); return NETDEV_TX_OK; } diff --git a/drivers/net/ethernet/sun/sunhme.c b/drivers/net/ethernet/sun/sunhme.c index 1921054b7f7d..e660902cfdf7 100644 --- a/drivers/net/ethernet/sun/sunhme.c +++ b/drivers/net/ethernet/sun/sunhme.c @@ -2020,9 +2020,9 @@ static void happy_meal_rx(struct happy_meal *hp, struct net_device *dev) skb_reserve(copy_skb, 2); skb_put(copy_skb, len); - dma_sync_single_for_cpu(hp->dma_dev, dma_addr, len, DMA_FROM_DEVICE); + dma_sync_single_for_cpu(hp->dma_dev, dma_addr, len + 2, DMA_FROM_DEVICE); skb_copy_from_linear_data(skb, copy_skb->data, len); - dma_sync_single_for_device(hp->dma_dev, dma_addr, len, DMA_FROM_DEVICE); + dma_sync_single_for_device(hp->dma_dev, dma_addr, len + 2, DMA_FROM_DEVICE); /* Reuse original ring buffer. */ hme_write_rxd(hp, this, (RXFLAG_OWN|((RX_BUF_ALLOC_SIZE-RX_OFFSET)<<16)), diff --git a/drivers/net/ipa/ipa_qmi.c b/drivers/net/ipa/ipa_qmi.c index ec010cf2e816..6f874f99b910 100644 --- a/drivers/net/ipa/ipa_qmi.c +++ b/drivers/net/ipa/ipa_qmi.c @@ -308,12 +308,12 @@ init_modem_driver_req(struct ipa_qmi *ipa_qmi) mem = ipa_mem_find(ipa, IPA_MEM_V4_ROUTE); req.v4_route_tbl_info_valid = 1; req.v4_route_tbl_info.start = ipa->mem_offset + mem->offset; - req.v4_route_tbl_info.count = mem->size / sizeof(__le64); + req.v4_route_tbl_info.end = IPA_ROUTE_MODEM_COUNT - 1; mem = ipa_mem_find(ipa, IPA_MEM_V6_ROUTE); req.v6_route_tbl_info_valid = 1; req.v6_route_tbl_info.start = ipa->mem_offset + mem->offset; - req.v6_route_tbl_info.count = mem->size / sizeof(__le64); + req.v6_route_tbl_info.end = IPA_ROUTE_MODEM_COUNT - 1; mem = ipa_mem_find(ipa, IPA_MEM_V4_FILTER); req.v4_filter_tbl_start_valid = 1; @@ -352,7 +352,7 @@ init_modem_driver_req(struct ipa_qmi *ipa_qmi) req.v4_hash_route_tbl_info_valid = 1; req.v4_hash_route_tbl_info.start = ipa->mem_offset + mem->offset; - req.v4_hash_route_tbl_info.count = mem->size / sizeof(__le64); + req.v4_hash_route_tbl_info.end = IPA_ROUTE_MODEM_COUNT - 1; } mem = ipa_mem_find(ipa, IPA_MEM_V6_ROUTE_HASHED); @@ -360,7 +360,7 @@ init_modem_driver_req(struct ipa_qmi *ipa_qmi) req.v6_hash_route_tbl_info_valid = 1; req.v6_hash_route_tbl_info.start = ipa->mem_offset + mem->offset; - req.v6_hash_route_tbl_info.count = mem->size / sizeof(__le64); + req.v6_hash_route_tbl_info.end = IPA_ROUTE_MODEM_COUNT - 1; } mem = ipa_mem_find(ipa, IPA_MEM_V4_FILTER_HASHED); diff --git a/drivers/net/ipa/ipa_qmi_msg.c b/drivers/net/ipa/ipa_qmi_msg.c index 6838e8065072..75d3fc0092e9 100644 --- a/drivers/net/ipa/ipa_qmi_msg.c +++ b/drivers/net/ipa/ipa_qmi_msg.c @@ -311,7 +311,7 @@ struct qmi_elem_info ipa_init_modem_driver_req_ei[] = { .tlv_type = 0x12, .offset = offsetof(struct ipa_init_modem_driver_req, v4_route_tbl_info), - .ei_array = ipa_mem_array_ei, + .ei_array = ipa_mem_bounds_ei, }, { .data_type = QMI_OPT_FLAG, @@ -332,7 +332,7 @@ struct qmi_elem_info ipa_init_modem_driver_req_ei[] = { .tlv_type = 0x13, .offset = offsetof(struct ipa_init_modem_driver_req, v6_route_tbl_info), - .ei_array = ipa_mem_array_ei, + .ei_array = ipa_mem_bounds_ei, }, { .data_type = QMI_OPT_FLAG, @@ -496,7 +496,7 @@ struct qmi_elem_info ipa_init_modem_driver_req_ei[] = { .tlv_type = 0x1b, .offset = offsetof(struct ipa_init_modem_driver_req, v4_hash_route_tbl_info), - .ei_array = ipa_mem_array_ei, + .ei_array = ipa_mem_bounds_ei, }, { .data_type = QMI_OPT_FLAG, @@ -517,7 +517,7 @@ struct qmi_elem_info ipa_init_modem_driver_req_ei[] = { .tlv_type = 0x1c, .offset = offsetof(struct ipa_init_modem_driver_req, v6_hash_route_tbl_info), - .ei_array = ipa_mem_array_ei, + .ei_array = ipa_mem_bounds_ei, }, { .data_type = QMI_OPT_FLAG, diff --git a/drivers/net/ipa/ipa_qmi_msg.h b/drivers/net/ipa/ipa_qmi_msg.h index 495e85abe50b..9651aa59b596 100644 --- a/drivers/net/ipa/ipa_qmi_msg.h +++ b/drivers/net/ipa/ipa_qmi_msg.h @@ -86,9 +86,11 @@ enum ipa_platform_type { IPA_QMI_PLATFORM_TYPE_MSM_QNX_V01 = 0x5, /* QNX MSM */ }; -/* This defines the start and end offset of a range of memory. Both - * fields are offsets relative to the start of IPA shared memory. - * The end value is the last addressable byte *within* the range. +/* This defines the start and end offset of a range of memory. The start + * value is a byte offset relative to the start of IPA shared memory. The + * end value is the last addressable unit *within* the range. Typically + * the end value is in units of bytes, however it can also be a maximum + * array index value. */ struct ipa_mem_bounds { u32 start; @@ -129,18 +131,19 @@ struct ipa_init_modem_driver_req { u8 hdr_tbl_info_valid; struct ipa_mem_bounds hdr_tbl_info; - /* Routing table information. These define the location and size of - * non-hashable IPv4 and IPv6 filter tables. The start values are - * offsets relative to the start of IPA shared memory. + /* Routing table information. These define the location and maximum + * *index* (not byte) for the modem portion of non-hashable IPv4 and + * IPv6 routing tables. The start values are byte offsets relative + * to the start of IPA shared memory. */ u8 v4_route_tbl_info_valid; - struct ipa_mem_array v4_route_tbl_info; + struct ipa_mem_bounds v4_route_tbl_info; u8 v6_route_tbl_info_valid; - struct ipa_mem_array v6_route_tbl_info; + struct ipa_mem_bounds v6_route_tbl_info; /* Filter table information. These define the location of the * non-hashable IPv4 and IPv6 filter tables. The start values are - * offsets relative to the start of IPA shared memory. + * byte offsets relative to the start of IPA shared memory. */ u8 v4_filter_tbl_start_valid; u32 v4_filter_tbl_start; @@ -181,18 +184,20 @@ struct ipa_init_modem_driver_req { u8 zip_tbl_info_valid; struct ipa_mem_bounds zip_tbl_info; - /* Routing table information. These define the location and size - * of hashable IPv4 and IPv6 filter tables. The start values are - * offsets relative to the start of IPA shared memory. + /* Routing table information. These define the location and maximum + * *index* (not byte) for the modem portion of hashable IPv4 and IPv6 + * routing tables (if supported by hardware). The start values are + * byte offsets relative to the start of IPA shared memory. */ u8 v4_hash_route_tbl_info_valid; - struct ipa_mem_array v4_hash_route_tbl_info; + struct ipa_mem_bounds v4_hash_route_tbl_info; u8 v6_hash_route_tbl_info_valid; - struct ipa_mem_array v6_hash_route_tbl_info; + struct ipa_mem_bounds v6_hash_route_tbl_info; /* Filter table information. These define the location and size - * of hashable IPv4 and IPv6 filter tables. The start values are - * offsets relative to the start of IPA shared memory. + * of hashable IPv4 and IPv6 filter tables (if supported by hardware). + * The start values are byte offsets relative to the start of IPA + * shared memory. */ u8 v4_hash_filter_tbl_start_valid; u32 v4_hash_filter_tbl_start; diff --git a/drivers/net/ipa/ipa_table.c b/drivers/net/ipa/ipa_table.c index 2f5a58bfc529..69efe672ca52 100644 --- a/drivers/net/ipa/ipa_table.c +++ b/drivers/net/ipa/ipa_table.c @@ -108,8 +108,6 @@ /* Assignment of route table entries to the modem and AP */ #define IPA_ROUTE_MODEM_MIN 0 -#define IPA_ROUTE_MODEM_COUNT 8 - #define IPA_ROUTE_AP_MIN IPA_ROUTE_MODEM_COUNT #define IPA_ROUTE_AP_COUNT \ (IPA_ROUTE_COUNT_MAX - IPA_ROUTE_MODEM_COUNT) diff --git a/drivers/net/ipa/ipa_table.h b/drivers/net/ipa/ipa_table.h index b6a9a0d79d68..1538e2e1732f 100644 --- a/drivers/net/ipa/ipa_table.h +++ b/drivers/net/ipa/ipa_table.h @@ -13,6 +13,9 @@ struct ipa; /* The maximum number of filter table entries (IPv4, IPv6; hashed or not) */ #define IPA_FILTER_COUNT_MAX 14 +/* The number of route table entries allotted to the modem */ +#define IPA_ROUTE_MODEM_COUNT 8 + /* The maximum number of route table entries (IPv4, IPv6; hashed or not) */ #define IPA_ROUTE_COUNT_MAX 15 diff --git a/drivers/net/ipvlan/ipvlan_core.c b/drivers/net/ipvlan/ipvlan_core.c index dfeb5b392e64..bb1c298c1e78 100644 --- a/drivers/net/ipvlan/ipvlan_core.c +++ b/drivers/net/ipvlan/ipvlan_core.c @@ -495,7 +495,6 @@ static int ipvlan_process_v6_outbound(struct sk_buff *skb) static int ipvlan_process_outbound(struct sk_buff *skb) { - struct ethhdr *ethh = eth_hdr(skb); int ret = NET_XMIT_DROP; /* The ipvlan is a pseudo-L2 device, so the packets that we receive @@ -505,6 +504,8 @@ static int ipvlan_process_outbound(struct sk_buff *skb) if (skb_mac_header_was_set(skb)) { /* In this mode we dont care about * multicast and broadcast traffic */ + struct ethhdr *ethh = eth_hdr(skb); + if (is_multicast_ether_addr(ethh->h_dest)) { pr_debug_ratelimited( "Dropped {multi|broad}cast of type=[%x]\n", @@ -589,7 +590,7 @@ out: static int ipvlan_xmit_mode_l2(struct sk_buff *skb, struct net_device *dev) { const struct ipvl_dev *ipvlan = netdev_priv(dev); - struct ethhdr *eth = eth_hdr(skb); + struct ethhdr *eth = skb_eth_hdr(skb); struct ipvl_addr *addr; void *lyr3h; int addr_type; @@ -619,6 +620,7 @@ static int ipvlan_xmit_mode_l2(struct sk_buff *skb, struct net_device *dev) return dev_forward_skb(ipvlan->phy_dev, skb); } else if (is_multicast_ether_addr(eth->h_dest)) { + skb_reset_mac_header(skb); ipvlan_skb_crossing_ns(skb, NULL); ipvlan_multicast_enqueue(ipvlan->port, skb, true); return NET_XMIT_SUCCESS; diff --git a/drivers/net/mdio/of_mdio.c b/drivers/net/mdio/of_mdio.c index 9e3c815a070f..796e9c7857d0 100644 --- a/drivers/net/mdio/of_mdio.c +++ b/drivers/net/mdio/of_mdio.c @@ -231,6 +231,7 @@ int of_mdiobus_register(struct mii_bus *mdio, struct device_node *np) return 0; unregister: + of_node_put(child); mdiobus_unregister(mdio); return rc; } diff --git a/drivers/net/netdevsim/hwstats.c b/drivers/net/netdevsim/hwstats.c index 605a38e16db0..0e58aa7f0374 100644 --- a/drivers/net/netdevsim/hwstats.c +++ b/drivers/net/netdevsim/hwstats.c @@ -433,11 +433,11 @@ int nsim_dev_hwstats_init(struct nsim_dev *nsim_dev) goto err_remove_hwstats_recursive; } - debugfs_create_file("enable_ifindex", 0600, hwstats->l3_ddir, hwstats, + debugfs_create_file("enable_ifindex", 0200, hwstats->l3_ddir, hwstats, &nsim_dev_hwstats_l3_enable_fops.fops); - debugfs_create_file("disable_ifindex", 0600, hwstats->l3_ddir, hwstats, + debugfs_create_file("disable_ifindex", 0200, hwstats->l3_ddir, hwstats, &nsim_dev_hwstats_l3_disable_fops.fops); - debugfs_create_file("fail_next_enable", 0600, hwstats->l3_ddir, hwstats, + debugfs_create_file("fail_next_enable", 0200, hwstats->l3_ddir, hwstats, &nsim_dev_hwstats_l3_fail_fops.fops); INIT_DELAYED_WORK(&hwstats->traffic_dw, diff --git a/drivers/net/phy/aquantia_main.c b/drivers/net/phy/aquantia_main.c index 8b7a46db30e0..7111e2e958e9 100644 --- a/drivers/net/phy/aquantia_main.c +++ b/drivers/net/phy/aquantia_main.c @@ -91,6 +91,9 @@ #define VEND1_GLOBAL_FW_ID_MAJOR GENMASK(15, 8) #define VEND1_GLOBAL_FW_ID_MINOR GENMASK(7, 0) +#define VEND1_GLOBAL_GEN_STAT2 0xc831 +#define VEND1_GLOBAL_GEN_STAT2_OP_IN_PROG BIT(15) + #define VEND1_GLOBAL_RSVD_STAT1 0xc885 #define VEND1_GLOBAL_RSVD_STAT1_FW_BUILD_ID GENMASK(7, 4) #define VEND1_GLOBAL_RSVD_STAT1_PROV_ID GENMASK(3, 0) @@ -125,6 +128,12 @@ #define VEND1_GLOBAL_INT_VEND_MASK_GLOBAL2 BIT(1) #define VEND1_GLOBAL_INT_VEND_MASK_GLOBAL3 BIT(0) +/* Sleep and timeout for checking if the Processor-Intensive + * MDIO operation is finished + */ +#define AQR107_OP_IN_PROG_SLEEP 1000 +#define AQR107_OP_IN_PROG_TIMEOUT 100000 + struct aqr107_hw_stat { const char *name; int reg; @@ -597,16 +606,52 @@ static void aqr107_link_change_notify(struct phy_device *phydev) phydev_info(phydev, "Aquantia 1000Base-T2 mode active\n"); } +static int aqr107_wait_processor_intensive_op(struct phy_device *phydev) +{ + int val, err; + + /* The datasheet notes to wait at least 1ms after issuing a + * processor intensive operation before checking. + * We cannot use the 'sleep_before_read' parameter of read_poll_timeout + * because that just determines the maximum time slept, not the minimum. + */ + usleep_range(1000, 5000); + + err = phy_read_mmd_poll_timeout(phydev, MDIO_MMD_VEND1, + VEND1_GLOBAL_GEN_STAT2, val, + !(val & VEND1_GLOBAL_GEN_STAT2_OP_IN_PROG), + AQR107_OP_IN_PROG_SLEEP, + AQR107_OP_IN_PROG_TIMEOUT, false); + if (err) { + phydev_err(phydev, "timeout: processor-intensive MDIO operation\n"); + return err; + } + + return 0; +} + static int aqr107_suspend(struct phy_device *phydev) { - return phy_set_bits_mmd(phydev, MDIO_MMD_VEND1, MDIO_CTRL1, - MDIO_CTRL1_LPOWER); + int err; + + err = phy_set_bits_mmd(phydev, MDIO_MMD_VEND1, MDIO_CTRL1, + MDIO_CTRL1_LPOWER); + if (err) + return err; + + return aqr107_wait_processor_intensive_op(phydev); } static int aqr107_resume(struct phy_device *phydev) { - return phy_clear_bits_mmd(phydev, MDIO_MMD_VEND1, MDIO_CTRL1, - MDIO_CTRL1_LPOWER); + int err; + + err = phy_clear_bits_mmd(phydev, MDIO_MMD_VEND1, MDIO_CTRL1, + MDIO_CTRL1_LPOWER); + if (err) + return err; + + return aqr107_wait_processor_intensive_op(phydev); } static int aqr107_probe(struct phy_device *phydev) diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c index f5c3c5c2fe11..6a8c740dce65 100644 --- a/drivers/net/phy/micrel.c +++ b/drivers/net/phy/micrel.c @@ -2824,16 +2824,19 @@ static int lan8804_config_intr(struct phy_device *phydev) static irqreturn_t lan8814_handle_interrupt(struct phy_device *phydev) { int irq_status, tsu_irq_status; + int ret = IRQ_NONE; irq_status = phy_read(phydev, LAN8814_INTS); - if (irq_status > 0 && (irq_status & LAN8814_INT_LINK)) - phy_trigger_machine(phydev); - if (irq_status < 0) { phy_error(phydev); return IRQ_NONE; } + if (irq_status & LAN8814_INT_LINK) { + phy_trigger_machine(phydev); + ret = IRQ_HANDLED; + } + while (1) { tsu_irq_status = lanphy_read_page_reg(phydev, 4, LAN8814_INTR_STS_REG); @@ -2842,12 +2845,15 @@ static irqreturn_t lan8814_handle_interrupt(struct phy_device *phydev) (tsu_irq_status & (LAN8814_INTR_STS_REG_1588_TSU0_ | LAN8814_INTR_STS_REG_1588_TSU1_ | LAN8814_INTR_STS_REG_1588_TSU2_ | - LAN8814_INTR_STS_REG_1588_TSU3_))) + LAN8814_INTR_STS_REG_1588_TSU3_))) { lan8814_handle_ptp_interrupt(phydev); - else + ret = IRQ_HANDLED; + } else { break; + } } - return IRQ_HANDLED; + + return ret; } static int lan8814_ack_interrupt(struct phy_device *phydev) diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c index ab92416d861f..62ade69295a9 100644 --- a/drivers/net/team/team.c +++ b/drivers/net/team/team.c @@ -1275,10 +1275,12 @@ static int team_port_add(struct team *team, struct net_device *port_dev, } } - netif_addr_lock_bh(dev); - dev_uc_sync_multiple(port_dev, dev); - dev_mc_sync_multiple(port_dev, dev); - netif_addr_unlock_bh(dev); + if (dev->flags & IFF_UP) { + netif_addr_lock_bh(dev); + dev_uc_sync_multiple(port_dev, dev); + dev_mc_sync_multiple(port_dev, dev); + netif_addr_unlock_bh(dev); + } port->index = -1; list_add_tail_rcu(&port->list, &team->port_list); @@ -1349,8 +1351,10 @@ static int team_port_del(struct team *team, struct net_device *port_dev) netdev_rx_handler_unregister(port_dev); team_port_disable_netpoll(port); vlan_vids_del_by_dev(port_dev, dev); - dev_uc_unsync(port_dev, dev); - dev_mc_unsync(port_dev, dev); + if (dev->flags & IFF_UP) { + dev_uc_unsync(port_dev, dev); + dev_mc_unsync(port_dev, dev); + } dev_close(port_dev); team_port_leave(team, port); @@ -1700,6 +1704,14 @@ static int team_open(struct net_device *dev) static int team_close(struct net_device *dev) { + struct team *team = netdev_priv(dev); + struct team_port *port; + + list_for_each_entry(port, &team->port_list, list) { + dev_uc_unsync(port->dev, dev); + dev_mc_unsync(port->dev, dev); + } + return 0; } diff --git a/drivers/net/wireguard/netlink.c b/drivers/net/wireguard/netlink.c index 0c0644e762e5..43c8c84e7ea8 100644 --- a/drivers/net/wireguard/netlink.c +++ b/drivers/net/wireguard/netlink.c @@ -436,14 +436,13 @@ static int set_peer(struct wg_device *wg, struct nlattr **attrs) if (attrs[WGPEER_A_ENDPOINT]) { struct sockaddr *addr = nla_data(attrs[WGPEER_A_ENDPOINT]); size_t len = nla_len(attrs[WGPEER_A_ENDPOINT]); + struct endpoint endpoint = { { { 0 } } }; - if ((len == sizeof(struct sockaddr_in) && - addr->sa_family == AF_INET) || - (len == sizeof(struct sockaddr_in6) && - addr->sa_family == AF_INET6)) { - struct endpoint endpoint = { { { 0 } } }; - - memcpy(&endpoint.addr, addr, len); + if (len == sizeof(struct sockaddr_in) && addr->sa_family == AF_INET) { + endpoint.addr4 = *(struct sockaddr_in *)addr; + wg_socket_set_peer_endpoint(peer, &endpoint); + } else if (len == sizeof(struct sockaddr_in6) && addr->sa_family == AF_INET6) { + endpoint.addr6 = *(struct sockaddr_in6 *)addr; wg_socket_set_peer_endpoint(peer, &endpoint); } } diff --git a/drivers/net/wireguard/selftest/ratelimiter.c b/drivers/net/wireguard/selftest/ratelimiter.c index ba87d294604f..d4bb40a695ab 100644 --- a/drivers/net/wireguard/selftest/ratelimiter.c +++ b/drivers/net/wireguard/selftest/ratelimiter.c @@ -6,29 +6,28 @@ #ifdef DEBUG #include <linux/jiffies.h> -#include <linux/hrtimer.h> static const struct { bool result; - u64 nsec_to_sleep_before; + unsigned int msec_to_sleep_before; } expected_results[] __initconst = { [0 ... PACKETS_BURSTABLE - 1] = { true, 0 }, [PACKETS_BURSTABLE] = { false, 0 }, - [PACKETS_BURSTABLE + 1] = { true, NSEC_PER_SEC / PACKETS_PER_SECOND }, + [PACKETS_BURSTABLE + 1] = { true, MSEC_PER_SEC / PACKETS_PER_SECOND }, [PACKETS_BURSTABLE + 2] = { false, 0 }, - [PACKETS_BURSTABLE + 3] = { true, (NSEC_PER_SEC / PACKETS_PER_SECOND) * 2 }, + [PACKETS_BURSTABLE + 3] = { true, (MSEC_PER_SEC / PACKETS_PER_SECOND) * 2 }, [PACKETS_BURSTABLE + 4] = { true, 0 }, [PACKETS_BURSTABLE + 5] = { false, 0 } }; static __init unsigned int maximum_jiffies_at_index(int index) { - u64 total_nsecs = 2 * NSEC_PER_SEC / PACKETS_PER_SECOND / 3; + unsigned int total_msecs = 2 * MSEC_PER_SEC / PACKETS_PER_SECOND / 3; int i; for (i = 0; i <= index; ++i) - total_nsecs += expected_results[i].nsec_to_sleep_before; - return nsecs_to_jiffies(total_nsecs); + total_msecs += expected_results[i].msec_to_sleep_before; + return msecs_to_jiffies(total_msecs); } static __init int timings_test(struct sk_buff *skb4, struct iphdr *hdr4, @@ -43,12 +42,8 @@ static __init int timings_test(struct sk_buff *skb4, struct iphdr *hdr4, loop_start_time = jiffies; for (i = 0; i < ARRAY_SIZE(expected_results); ++i) { - if (expected_results[i].nsec_to_sleep_before) { - ktime_t timeout = ktime_add(ktime_add_ns(ktime_get_coarse_boottime(), TICK_NSEC * 4 / 3), - ns_to_ktime(expected_results[i].nsec_to_sleep_before)); - set_current_state(TASK_UNINTERRUPTIBLE); - schedule_hrtimeout_range_clock(&timeout, 0, HRTIMER_MODE_ABS, CLOCK_BOOTTIME); - } + if (expected_results[i].msec_to_sleep_before) + msleep(expected_results[i].msec_to_sleep_before); if (time_is_before_jiffies(loop_start_time + maximum_jiffies_at_index(i))) @@ -132,7 +127,7 @@ bool __init wg_ratelimiter_selftest(void) if (IS_ENABLED(CONFIG_KASAN) || IS_ENABLED(CONFIG_UBSAN)) return true; - BUILD_BUG_ON(NSEC_PER_SEC % PACKETS_PER_SECOND != 0); + BUILD_BUG_ON(MSEC_PER_SEC % PACKETS_PER_SECOND != 0); if (wg_ratelimiter_init()) goto out; @@ -172,7 +167,7 @@ bool __init wg_ratelimiter_selftest(void) ++test; #endif - for (trials = TRIALS_BEFORE_GIVING_UP;;) { + for (trials = TRIALS_BEFORE_GIVING_UP; IS_ENABLED(DEBUG_RATELIMITER_TIMINGS);) { int test_count = 0, ret; ret = timings_test(skb4, hdr4, skb6, hdr6, &test_count); diff --git a/drivers/net/wireless/intel/iwlwifi/Kconfig b/drivers/net/wireless/intel/iwlwifi/Kconfig index a647a406b87b..b20409f8c13a 100644 --- a/drivers/net/wireless/intel/iwlwifi/Kconfig +++ b/drivers/net/wireless/intel/iwlwifi/Kconfig @@ -140,6 +140,7 @@ config IWLMEI depends on INTEL_MEI depends on PM depends on CFG80211 + depends on BROKEN help Enables the iwlmei kernel module. diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c index 5eb28f8ee87e..11536f115198 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c @@ -1833,8 +1833,8 @@ static void iwl_mvm_parse_ppe(struct iwl_mvm *mvm, * If nss < MAX: we can set zeros in other streams */ if (nss > MAX_HE_SUPP_NSS) { - IWL_INFO(mvm, "Got NSS = %d - trimming to %d\n", nss, - MAX_HE_SUPP_NSS); + IWL_DEBUG_INFO(mvm, "Got NSS = %d - trimming to %d\n", nss, + MAX_HE_SUPP_NSS); nss = MAX_HE_SUPP_NSS; } diff --git a/drivers/net/wireless/mediatek/mt76/mac80211.c b/drivers/net/wireless/mediatek/mt76/mac80211.c index 253cbc1956d1..6de13d641438 100644 --- a/drivers/net/wireless/mediatek/mt76/mac80211.c +++ b/drivers/net/wireless/mediatek/mt76/mac80211.c @@ -267,7 +267,8 @@ static void mt76_init_stream_cap(struct mt76_phy *phy, } vht_cap->vht_mcs.rx_mcs_map = cpu_to_le16(mcs_map); vht_cap->vht_mcs.tx_mcs_map = cpu_to_le16(mcs_map); - vht_cap->vht_mcs.tx_highest |= + if (ieee80211_hw_check(phy->hw, SUPPORTS_VHT_EXT_NSS_BW)) + vht_cap->vht_mcs.tx_highest |= cpu_to_le16(IEEE80211_VHT_EXT_NSS_BW_CAPABLE); } diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/mac.c b/drivers/net/wireless/mediatek/mt76/mt7615/mac.c index ad6c7d632eed..d6aae60c440d 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7615/mac.c +++ b/drivers/net/wireless/mediatek/mt76/mt7615/mac.c @@ -1088,7 +1088,7 @@ u32 mt7615_mac_get_sta_tid_sn(struct mt7615_dev *dev, int wcid, u8 tid) offset %= 32; val = mt76_rr(dev, addr); - val >>= (tid % 32); + val >>= offset; if (offset > 20) { addr += 4; diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index af367b22871b..66446f1e06cf 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -4703,6 +4703,8 @@ static void nvme_fw_act_work(struct work_struct *work) nvme_start_queues(ctrl); /* read FW slot information to clear the AER */ nvme_get_fw_slot_info(ctrl); + + queue_work(nvme_wq, &ctrl->async_event_work); } static u32 nvme_aer_type(u32 result) @@ -4715,9 +4717,10 @@ static u32 nvme_aer_subtype(u32 result) return (result & 0xff00) >> 8; } -static void nvme_handle_aen_notice(struct nvme_ctrl *ctrl, u32 result) +static bool nvme_handle_aen_notice(struct nvme_ctrl *ctrl, u32 result) { u32 aer_notice_type = nvme_aer_subtype(result); + bool requeue = true; trace_nvme_async_event(ctrl, aer_notice_type); @@ -4734,6 +4737,7 @@ static void nvme_handle_aen_notice(struct nvme_ctrl *ctrl, u32 result) */ if (nvme_change_ctrl_state(ctrl, NVME_CTRL_RESETTING)) { nvme_auth_stop(ctrl); + requeue = false; queue_work(nvme_wq, &ctrl->fw_act_work); } break; @@ -4750,6 +4754,7 @@ static void nvme_handle_aen_notice(struct nvme_ctrl *ctrl, u32 result) default: dev_warn(ctrl->device, "async event result %08x\n", result); } + return requeue; } static void nvme_handle_aer_persistent_error(struct nvme_ctrl *ctrl) @@ -4765,13 +4770,14 @@ void nvme_complete_async_event(struct nvme_ctrl *ctrl, __le16 status, u32 result = le32_to_cpu(res->u32); u32 aer_type = nvme_aer_type(result); u32 aer_subtype = nvme_aer_subtype(result); + bool requeue = true; if (le16_to_cpu(status) >> 1 != NVME_SC_SUCCESS) return; switch (aer_type) { case NVME_AER_NOTICE: - nvme_handle_aen_notice(ctrl, result); + requeue = nvme_handle_aen_notice(ctrl, result); break; case NVME_AER_ERROR: /* @@ -4792,7 +4798,9 @@ void nvme_complete_async_event(struct nvme_ctrl *ctrl, __le16 status, default: break; } - queue_work(nvme_wq, &ctrl->async_event_work); + + if (requeue) + queue_work(nvme_wq, &ctrl->async_event_work); } EXPORT_SYMBOL_GPL(nvme_complete_async_event); diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c index 044da18c06f5..d5871fd6f769 100644 --- a/drivers/nvme/host/tcp.c +++ b/drivers/nvme/host/tcp.c @@ -121,7 +121,6 @@ struct nvme_tcp_queue { struct mutex send_mutex; struct llist_head req_list; struct list_head send_list; - bool more_requests; /* recv state */ void *pdu; @@ -320,7 +319,7 @@ static inline void nvme_tcp_send_all(struct nvme_tcp_queue *queue) static inline bool nvme_tcp_queue_more(struct nvme_tcp_queue *queue) { return !list_empty(&queue->send_list) || - !llist_empty(&queue->req_list) || queue->more_requests; + !llist_empty(&queue->req_list); } static inline void nvme_tcp_queue_request(struct nvme_tcp_request *req, @@ -339,9 +338,7 @@ static inline void nvme_tcp_queue_request(struct nvme_tcp_request *req, */ if (queue->io_cpu == raw_smp_processor_id() && sync && empty && mutex_trylock(&queue->send_mutex)) { - queue->more_requests = !last; nvme_tcp_send_all(queue); - queue->more_requests = false; mutex_unlock(&queue->send_mutex); } @@ -1229,7 +1226,7 @@ static void nvme_tcp_io_work(struct work_struct *w) else if (unlikely(result < 0)) return; - if (!pending) + if (!pending || !queue->rd_enabled) return; } while (!time_after(jiffies, deadline)); /* quota is exhausted */ diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c index a1345790005f..7f4083cf953a 100644 --- a/drivers/nvme/target/core.c +++ b/drivers/nvme/target/core.c @@ -735,6 +735,8 @@ static void nvmet_set_error(struct nvmet_req *req, u16 status) static void __nvmet_req_complete(struct nvmet_req *req, u16 status) { + struct nvmet_ns *ns = req->ns; + if (!req->sq->sqhd_disabled) nvmet_update_sq_head(req); req->cqe->sq_id = cpu_to_le16(req->sq->qid); @@ -745,9 +747,9 @@ static void __nvmet_req_complete(struct nvmet_req *req, u16 status) trace_nvmet_req_complete(req); - if (req->ns) - nvmet_put_namespace(req->ns); req->ops->queue_response(req); + if (ns) + nvmet_put_namespace(ns); } void nvmet_req_complete(struct nvmet_req *req, u16 status) diff --git a/drivers/nvme/target/zns.c b/drivers/nvme/target/zns.c index c7ef69f29fe4..835bfda86fcf 100644 --- a/drivers/nvme/target/zns.c +++ b/drivers/nvme/target/zns.c @@ -100,6 +100,7 @@ void nvmet_execute_identify_cns_cs_ns(struct nvmet_req *req) struct nvme_id_ns_zns *id_zns; u64 zsze; u16 status; + u32 mar, mor; if (le32_to_cpu(req->cmd->identify.nsid) == NVME_NSID_ALL) { req->error_loc = offsetof(struct nvme_identify, nsid); @@ -130,8 +131,20 @@ void nvmet_execute_identify_cns_cs_ns(struct nvmet_req *req) zsze = (bdev_zone_sectors(req->ns->bdev) << 9) >> req->ns->blksize_shift; id_zns->lbafe[0].zsze = cpu_to_le64(zsze); - id_zns->mor = cpu_to_le32(bdev_max_open_zones(req->ns->bdev)); - id_zns->mar = cpu_to_le32(bdev_max_active_zones(req->ns->bdev)); + + mor = bdev_max_open_zones(req->ns->bdev); + if (!mor) + mor = U32_MAX; + else + mor--; + id_zns->mor = cpu_to_le32(mor); + + mar = bdev_max_active_zones(req->ns->bdev); + if (!mar) + mar = U32_MAX; + else + mar--; + id_zns->mar = cpu_to_le32(mar); done: status = nvmet_copy_to_sgl(req, 0, id_zns, sizeof(*id_zns)); diff --git a/drivers/of/fdt.c b/drivers/of/fdt.c index 7bc92923104c..1c573e7a60bc 100644 --- a/drivers/of/fdt.c +++ b/drivers/of/fdt.c @@ -314,7 +314,7 @@ static int unflatten_dt_nodes(const void *blob, for (offset = 0; offset >= 0 && depth >= initial_depth; offset = fdt_next_node(blob, offset, &depth)) { - if (WARN_ON_ONCE(depth >= FDT_MAX_DEPTH)) + if (WARN_ON_ONCE(depth >= FDT_MAX_DEPTH - 1)) continue; if (!IS_ENABLED(CONFIG_OF_KOBJ) && diff --git a/drivers/parisc/ccio-dma.c b/drivers/parisc/ccio-dma.c index f223afe47d10..a66386043aa6 100644 --- a/drivers/parisc/ccio-dma.c +++ b/drivers/parisc/ccio-dma.c @@ -1546,6 +1546,7 @@ static int __init ccio_probe(struct parisc_device *dev) } ccio_ioc_init(ioc); if (ccio_init_resources(ioc)) { + iounmap(ioc->ioc_regs); kfree(ioc); return -ENOMEM; } diff --git a/drivers/parisc/iosapic.c b/drivers/parisc/iosapic.c index 3a8c98615634..bdef7a8d6ab8 100644 --- a/drivers/parisc/iosapic.c +++ b/drivers/parisc/iosapic.c @@ -221,16 +221,7 @@ static size_t irt_num_entry; static struct irt_entry *iosapic_alloc_irt(int num_entries) { - unsigned long a; - - /* The IRT needs to be 8-byte aligned for the PDC call. - * Normally kmalloc would guarantee larger alignment, but - * if CONFIG_DEBUG_SLAB is enabled, then we can get only - * 4-byte alignment on 32-bit kernels - */ - a = (unsigned long)kmalloc(sizeof(struct irt_entry) * num_entries + 8, GFP_KERNEL); - a = (a + 7UL) & ~7UL; - return (struct irt_entry *)a; + return kcalloc(num_entries, sizeof(struct irt_entry), GFP_KERNEL); } /** diff --git a/drivers/perf/riscv_pmu_sbi.c b/drivers/perf/riscv_pmu_sbi.c index 6f6681bbfd36..8de4ca2fef21 100644 --- a/drivers/perf/riscv_pmu_sbi.c +++ b/drivers/perf/riscv_pmu_sbi.c @@ -473,7 +473,7 @@ static int pmu_sbi_get_ctrinfo(int nctr) if (!pmu_ctr_list) return -ENOMEM; - for (i = 0; i <= nctr; i++) { + for (i = 0; i < nctr; i++) { ret = sbi_ecall(SBI_EXT_PMU, SBI_EXT_PMU_COUNTER_GET_INFO, i, 0, 0, 0, 0, 0); if (ret.error) /* The logical counter ids are not expected to be contiguous */ diff --git a/drivers/pinctrl/pinctrl-ocelot.c b/drivers/pinctrl/pinctrl-ocelot.c index 340ca2373429..83464e0bf4e6 100644 --- a/drivers/pinctrl/pinctrl-ocelot.c +++ b/drivers/pinctrl/pinctrl-ocelot.c @@ -332,6 +332,7 @@ struct ocelot_pinctrl { const struct ocelot_pincfg_data *pincfg_data; struct ocelot_pmx_func func[FUNC_MAX]; u8 stride; + struct workqueue_struct *wq; }; struct ocelot_match_data { @@ -339,6 +340,11 @@ struct ocelot_match_data { struct ocelot_pincfg_data pincfg_data; }; +struct ocelot_irq_work { + struct work_struct irq_work; + struct irq_desc *irq_desc; +}; + #define LUTON_P(p, f0, f1) \ static struct ocelot_pin_caps luton_pin_##p = { \ .pin = p, \ @@ -1814,6 +1820,75 @@ static void ocelot_irq_mask(struct irq_data *data) gpiochip_disable_irq(chip, gpio); } +static void ocelot_irq_work(struct work_struct *work) +{ + struct ocelot_irq_work *w = container_of(work, struct ocelot_irq_work, irq_work); + struct irq_chip *parent_chip = irq_desc_get_chip(w->irq_desc); + struct gpio_chip *chip = irq_desc_get_chip_data(w->irq_desc); + struct irq_data *data = irq_desc_get_irq_data(w->irq_desc); + unsigned int gpio = irqd_to_hwirq(data); + + local_irq_disable(); + chained_irq_enter(parent_chip, w->irq_desc); + generic_handle_domain_irq(chip->irq.domain, gpio); + chained_irq_exit(parent_chip, w->irq_desc); + local_irq_enable(); + + kfree(w); +} + +static void ocelot_irq_unmask_level(struct irq_data *data) +{ + struct gpio_chip *chip = irq_data_get_irq_chip_data(data); + struct ocelot_pinctrl *info = gpiochip_get_data(chip); + struct irq_desc *desc = irq_data_to_desc(data); + unsigned int gpio = irqd_to_hwirq(data); + unsigned int bit = BIT(gpio % 32); + bool ack = false, active = false; + u8 trigger_level; + int val; + + trigger_level = irqd_get_trigger_type(data); + + /* Check if the interrupt line is still active. */ + regmap_read(info->map, REG(OCELOT_GPIO_IN, info, gpio), &val); + if ((!(val & bit) && trigger_level == IRQ_TYPE_LEVEL_LOW) || + (val & bit && trigger_level == IRQ_TYPE_LEVEL_HIGH)) + active = true; + + /* + * Check if the interrupt controller has seen any changes in the + * interrupt line. + */ + regmap_read(info->map, REG(OCELOT_GPIO_INTR, info, gpio), &val); + if (val & bit) + ack = true; + + /* Enable the interrupt now */ + gpiochip_enable_irq(chip, gpio); + regmap_update_bits(info->map, REG(OCELOT_GPIO_INTR_ENA, info, gpio), + bit, bit); + + /* + * In case the interrupt line is still active and the interrupt + * controller has not seen any changes in the interrupt line, then it + * means that there happen another interrupt while the line was active. + * So we missed that one, so we need to kick the interrupt again + * handler. + */ + if (active && !ack) { + struct ocelot_irq_work *work; + + work = kmalloc(sizeof(*work), GFP_ATOMIC); + if (!work) + return; + + work->irq_desc = desc; + INIT_WORK(&work->irq_work, ocelot_irq_work); + queue_work(info->wq, &work->irq_work); + } +} + static void ocelot_irq_unmask(struct irq_data *data) { struct gpio_chip *chip = irq_data_get_irq_chip_data(data); @@ -1837,13 +1912,12 @@ static void ocelot_irq_ack(struct irq_data *data) static int ocelot_irq_set_type(struct irq_data *data, unsigned int type); -static struct irq_chip ocelot_eoi_irqchip = { +static struct irq_chip ocelot_level_irqchip = { .name = "gpio", .irq_mask = ocelot_irq_mask, - .irq_eoi = ocelot_irq_ack, - .irq_unmask = ocelot_irq_unmask, - .flags = IRQCHIP_EOI_THREADED | IRQCHIP_EOI_IF_HANDLED | - IRQCHIP_IMMUTABLE, + .irq_ack = ocelot_irq_ack, + .irq_unmask = ocelot_irq_unmask_level, + .flags = IRQCHIP_IMMUTABLE, .irq_set_type = ocelot_irq_set_type, GPIOCHIP_IRQ_RESOURCE_HELPERS }; @@ -1860,14 +1934,9 @@ static struct irq_chip ocelot_irqchip = { static int ocelot_irq_set_type(struct irq_data *data, unsigned int type) { - type &= IRQ_TYPE_SENSE_MASK; - - if (!(type & (IRQ_TYPE_EDGE_BOTH | IRQ_TYPE_LEVEL_HIGH))) - return -EINVAL; - - if (type & IRQ_TYPE_LEVEL_HIGH) - irq_set_chip_handler_name_locked(data, &ocelot_eoi_irqchip, - handle_fasteoi_irq, NULL); + if (type & (IRQ_TYPE_LEVEL_HIGH | IRQ_TYPE_LEVEL_LOW)) + irq_set_chip_handler_name_locked(data, &ocelot_level_irqchip, + handle_level_irq, NULL); if (type & IRQ_TYPE_EDGE_BOTH) irq_set_chip_handler_name_locked(data, &ocelot_irqchip, handle_edge_irq, NULL); @@ -1996,6 +2065,10 @@ static int ocelot_pinctrl_probe(struct platform_device *pdev) if (!info->desc) return -ENOMEM; + info->wq = alloc_ordered_workqueue("ocelot_ordered", 0); + if (!info->wq) + return -ENOMEM; + info->pincfg_data = &data->pincfg_data; reset = devm_reset_control_get_optional_shared(dev, "switch"); @@ -2012,7 +2085,7 @@ static int ocelot_pinctrl_probe(struct platform_device *pdev) if (IS_ERR(info->map)) return dev_err_probe(dev, PTR_ERR(info->map), "Failed to create regmap\n"); - dev_set_drvdata(dev, info->map); + dev_set_drvdata(dev, info); info->dev = dev; /* Pinconf registers */ @@ -2037,6 +2110,15 @@ static int ocelot_pinctrl_probe(struct platform_device *pdev) return 0; } +static int ocelot_pinctrl_remove(struct platform_device *pdev) +{ + struct ocelot_pinctrl *info = platform_get_drvdata(pdev); + + destroy_workqueue(info->wq); + + return 0; +} + static struct platform_driver ocelot_pinctrl_driver = { .driver = { .name = "pinctrl-ocelot", @@ -2044,6 +2126,7 @@ static struct platform_driver ocelot_pinctrl_driver = { .suppress_bind_attrs = true, }, .probe = ocelot_pinctrl_probe, + .remove = ocelot_pinctrl_remove, }; module_platform_driver(ocelot_pinctrl_driver); MODULE_LICENSE("Dual MIT/GPL"); diff --git a/drivers/pinctrl/qcom/pinctrl-sc8180x.c b/drivers/pinctrl/qcom/pinctrl-sc8180x.c index 6bec7f143134..704a99d2f93c 100644 --- a/drivers/pinctrl/qcom/pinctrl-sc8180x.c +++ b/drivers/pinctrl/qcom/pinctrl-sc8180x.c @@ -530,10 +530,10 @@ DECLARE_MSM_GPIO_PINS(187); DECLARE_MSM_GPIO_PINS(188); DECLARE_MSM_GPIO_PINS(189); -static const unsigned int sdc2_clk_pins[] = { 190 }; -static const unsigned int sdc2_cmd_pins[] = { 191 }; -static const unsigned int sdc2_data_pins[] = { 192 }; -static const unsigned int ufs_reset_pins[] = { 193 }; +static const unsigned int ufs_reset_pins[] = { 190 }; +static const unsigned int sdc2_clk_pins[] = { 191 }; +static const unsigned int sdc2_cmd_pins[] = { 192 }; +static const unsigned int sdc2_data_pins[] = { 193 }; enum sc8180x_functions { msm_mux_adsp_ext, @@ -1582,7 +1582,7 @@ static const int sc8180x_acpi_reserved_gpios[] = { static const struct msm_gpio_wakeirq_map sc8180x_pdc_map[] = { { 3, 31 }, { 5, 32 }, { 8, 33 }, { 9, 34 }, { 10, 100 }, { 12, 104 }, { 24, 37 }, { 26, 38 }, { 27, 41 }, { 28, 42 }, { 30, 39 }, { 36, 43 }, - { 37, 43 }, { 38, 45 }, { 39, 118 }, { 39, 125 }, { 41, 47 }, + { 37, 44 }, { 38, 45 }, { 39, 118 }, { 39, 125 }, { 41, 47 }, { 42, 48 }, { 46, 50 }, { 47, 49 }, { 48, 51 }, { 49, 53 }, { 50, 52 }, { 51, 116 }, { 51, 123 }, { 53, 54 }, { 54, 55 }, { 55, 56 }, { 56, 57 }, { 58, 58 }, { 60, 60 }, { 68, 62 }, { 70, 63 }, { 76, 86 }, diff --git a/drivers/pinctrl/sunxi/pinctrl-sun50i-a100-r.c b/drivers/pinctrl/sunxi/pinctrl-sun50i-a100-r.c index afc1f5df7545..b82ad135bf2a 100644 --- a/drivers/pinctrl/sunxi/pinctrl-sun50i-a100-r.c +++ b/drivers/pinctrl/sunxi/pinctrl-sun50i-a100-r.c @@ -99,7 +99,7 @@ MODULE_DEVICE_TABLE(of, a100_r_pinctrl_match); static struct platform_driver a100_r_pinctrl_driver = { .probe = a100_r_pinctrl_probe, .driver = { - .name = "sun50iw10p1-r-pinctrl", + .name = "sun50i-a100-r-pinctrl", .of_match_table = a100_r_pinctrl_match, }, }; diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c index d8373cb04f90..d3e8dc32832d 100644 --- a/drivers/regulator/core.c +++ b/drivers/regulator/core.c @@ -2733,13 +2733,18 @@ static int _regulator_do_enable(struct regulator_dev *rdev) */ static int _regulator_handle_consumer_enable(struct regulator *regulator) { + int ret; struct regulator_dev *rdev = regulator->rdev; lockdep_assert_held_once(&rdev->mutex.base); regulator->enable_count++; - if (regulator->uA_load && regulator->enable_count == 1) - return drms_uA_update(rdev); + if (regulator->uA_load && regulator->enable_count == 1) { + ret = drms_uA_update(rdev); + if (ret) + regulator->enable_count--; + return ret; + } return 0; } diff --git a/drivers/regulator/pfuze100-regulator.c b/drivers/regulator/pfuze100-regulator.c index 6b617024a67d..d899d6e98fb8 100644 --- a/drivers/regulator/pfuze100-regulator.c +++ b/drivers/regulator/pfuze100-regulator.c @@ -766,7 +766,7 @@ static int pfuze100_regulator_probe(struct i2c_client *client, ((pfuze_chip->chip_id == PFUZE3000) ? "3000" : "3001")))); memcpy(pfuze_chip->regulator_descs, pfuze_chip->pfuze_regulators, - sizeof(pfuze_chip->regulator_descs)); + regulator_num * sizeof(struct pfuze_regulator)); ret = pfuze_parse_regulators_dt(pfuze_chip); if (ret) diff --git a/drivers/scsi/hosts.c b/drivers/scsi/hosts.c index 0738238ed6cc..9857dba09c95 100644 --- a/drivers/scsi/hosts.c +++ b/drivers/scsi/hosts.c @@ -182,6 +182,15 @@ void scsi_remove_host(struct Scsi_Host *shost) mutex_unlock(&shost->scan_mutex); scsi_proc_host_rm(shost); + /* + * New SCSI devices cannot be attached anymore because of the SCSI host + * state so drop the tag set refcnt. Wait until the tag set refcnt drops + * to zero because .exit_cmd_priv implementations may need the host + * pointer. + */ + kref_put(&shost->tagset_refcnt, scsi_mq_free_tags); + wait_for_completion(&shost->tagset_freed); + spin_lock_irqsave(shost->host_lock, flags); if (scsi_host_set_state(shost, SHOST_DEL)) BUG_ON(scsi_host_set_state(shost, SHOST_DEL_RECOVERY)); @@ -190,15 +199,6 @@ void scsi_remove_host(struct Scsi_Host *shost) transport_unregister_device(&shost->shost_gendev); device_unregister(&shost->shost_dev); device_del(&shost->shost_gendev); - - /* - * After scsi_remove_host() has returned the scsi LLD module can be - * unloaded and/or the host resources can be released. Hence wait until - * the dependent SCSI targets and devices are gone before returning. - */ - wait_event(shost->targets_wq, atomic_read(&shost->target_count) == 0); - - scsi_mq_destroy_tags(shost); } EXPORT_SYMBOL(scsi_remove_host); @@ -254,6 +254,9 @@ int scsi_add_host_with_dma(struct Scsi_Host *shost, struct device *dev, if (error) goto fail; + kref_init(&shost->tagset_refcnt); + init_completion(&shost->tagset_freed); + /* * Increase usage count temporarily here so that calling * scsi_autopm_put_host() will trigger runtime idle if there is @@ -309,8 +312,8 @@ int scsi_add_host_with_dma(struct Scsi_Host *shost, struct device *dev, return error; /* - * Any resources associated with the SCSI host in this function except - * the tag set will be freed by scsi_host_dev_release(). + * Any host allocation in this function will be freed in + * scsi_host_dev_release(). */ out_del_dev: device_del(&shost->shost_dev); @@ -326,7 +329,7 @@ int scsi_add_host_with_dma(struct Scsi_Host *shost, struct device *dev, pm_runtime_disable(&shost->shost_gendev); pm_runtime_set_suspended(&shost->shost_gendev); pm_runtime_put_noidle(&shost->shost_gendev); - scsi_mq_destroy_tags(shost); + kref_put(&shost->tagset_refcnt, scsi_mq_free_tags); fail: return error; } @@ -406,7 +409,6 @@ struct Scsi_Host *scsi_host_alloc(struct scsi_host_template *sht, int privsize) INIT_LIST_HEAD(&shost->starved_list); init_waitqueue_head(&shost->host_wait); mutex_init(&shost->scan_mutex); - init_waitqueue_head(&shost->targets_wq); index = ida_alloc(&host_index_ida, GFP_KERNEL); if (index < 0) { diff --git a/drivers/scsi/lpfc/lpfc_init.c b/drivers/scsi/lpfc/lpfc_init.c index c69c5a0979ec..55a1ad6eed03 100644 --- a/drivers/scsi/lpfc/lpfc_init.c +++ b/drivers/scsi/lpfc/lpfc_init.c @@ -8053,7 +8053,7 @@ lpfc_sli4_driver_resource_setup(struct lpfc_hba *phba) /* Allocate device driver memory */ rc = lpfc_mem_alloc(phba, SGL_ALIGN_SZ); if (rc) - return -ENOMEM; + goto out_destroy_workqueue; /* IF Type 2 ports get initialized now. */ if (bf_get(lpfc_sli_intf_if_type, &phba->sli4_hba.sli_intf) >= @@ -8481,6 +8481,9 @@ out_free_bsmbx: lpfc_destroy_bootstrap_mbox(phba); out_free_mem: lpfc_mem_free(phba); +out_destroy_workqueue: + destroy_workqueue(phba->wq); + phba->wq = NULL; return rc; } diff --git a/drivers/scsi/lpfc/lpfc_scsi.c b/drivers/scsi/lpfc/lpfc_scsi.c index 084c0f9fdc3a..938a5e435943 100644 --- a/drivers/scsi/lpfc/lpfc_scsi.c +++ b/drivers/scsi/lpfc/lpfc_scsi.c @@ -4272,7 +4272,7 @@ lpfc_fcp_io_cmd_wqe_cmpl(struct lpfc_hba *phba, struct lpfc_iocbq *pwqeIn, lpfc_cmd->result == IOERR_ABORT_REQUESTED || lpfc_cmd->result == IOERR_RPI_SUSPENDED || lpfc_cmd->result == IOERR_SLER_CMD_RCV_FAILURE) { - cmd->result = DID_REQUEUE << 16; + cmd->result = DID_TRANSPORT_DISRUPTED << 16; break; } if ((lpfc_cmd->result == IOERR_RX_DMA_FAILED || @@ -4562,7 +4562,7 @@ lpfc_scsi_cmd_iocb_cmpl(struct lpfc_hba *phba, struct lpfc_iocbq *pIocbIn, lpfc_cmd->result == IOERR_NO_RESOURCES || lpfc_cmd->result == IOERR_ABORT_REQUESTED || lpfc_cmd->result == IOERR_SLER_CMD_RCV_FAILURE) { - cmd->result = DID_REQUEUE << 16; + cmd->result = DID_TRANSPORT_DISRUPTED << 16; break; } if ((lpfc_cmd->result == IOERR_RX_DMA_FAILED || diff --git a/drivers/scsi/mpt3sas/mpt3sas_scsih.c b/drivers/scsi/mpt3sas/mpt3sas_scsih.c index def37a7e5980..bd6a5f1bd532 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_scsih.c +++ b/drivers/scsi/mpt3sas/mpt3sas_scsih.c @@ -3670,6 +3670,7 @@ static struct fw_event_work *dequeue_next_fw_event(struct MPT3SAS_ADAPTER *ioc) fw_event = list_first_entry(&ioc->fw_event_list, struct fw_event_work, list); list_del_init(&fw_event->list); + fw_event_work_put(fw_event); } spin_unlock_irqrestore(&ioc->fw_event_lock, flags); @@ -3751,7 +3752,6 @@ _scsih_fw_event_cleanup_queue(struct MPT3SAS_ADAPTER *ioc) if (cancel_work_sync(&fw_event->work)) fw_event_work_put(fw_event); - fw_event_work_put(fw_event); } ioc->fw_events_cleanup = 0; } diff --git a/drivers/scsi/scsi.c b/drivers/scsi/scsi.c index 086ec5b5862d..c59eac7a32f2 100644 --- a/drivers/scsi/scsi.c +++ b/drivers/scsi/scsi.c @@ -586,13 +586,10 @@ EXPORT_SYMBOL(scsi_device_get); */ void scsi_device_put(struct scsi_device *sdev) { - /* - * Decreasing the module reference count before the device reference - * count is safe since scsi_remove_host() only returns after all - * devices have been removed. - */ - module_put(sdev->host->hostt->module); + struct module *mod = sdev->host->hostt->module; + put_device(&sdev->sdev_gendev); + module_put(mod); } EXPORT_SYMBOL(scsi_device_put); diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c index ef08029a0079..96e7e3eaca29 100644 --- a/drivers/scsi/scsi_lib.c +++ b/drivers/scsi/scsi_lib.c @@ -1983,9 +1983,13 @@ int scsi_mq_setup_tags(struct Scsi_Host *shost) return blk_mq_alloc_tag_set(tag_set); } -void scsi_mq_destroy_tags(struct Scsi_Host *shost) +void scsi_mq_free_tags(struct kref *kref) { + struct Scsi_Host *shost = container_of(kref, typeof(*shost), + tagset_refcnt); + blk_mq_free_tag_set(&shost->tag_set); + complete(&shost->tagset_freed); } /** diff --git a/drivers/scsi/scsi_priv.h b/drivers/scsi/scsi_priv.h index 429663bd78ec..f385b3f04d6e 100644 --- a/drivers/scsi/scsi_priv.h +++ b/drivers/scsi/scsi_priv.h @@ -94,7 +94,7 @@ extern void scsi_run_host_queues(struct Scsi_Host *shost); extern void scsi_requeue_run_queue(struct work_struct *work); extern void scsi_start_queue(struct scsi_device *sdev); extern int scsi_mq_setup_tags(struct Scsi_Host *shost); -extern void scsi_mq_destroy_tags(struct Scsi_Host *shost); +extern void scsi_mq_free_tags(struct kref *kref); extern void scsi_exit_queue(void); extern void scsi_evt_thread(struct work_struct *work); diff --git a/drivers/scsi/scsi_scan.c b/drivers/scsi/scsi_scan.c index ac6059702d13..5d27f5196de6 100644 --- a/drivers/scsi/scsi_scan.c +++ b/drivers/scsi/scsi_scan.c @@ -340,6 +340,7 @@ static struct scsi_device *scsi_alloc_sdev(struct scsi_target *starget, kfree(sdev); goto out; } + kref_get(&sdev->host->tagset_refcnt); sdev->request_queue = q; q->queuedata = sdev; __scsi_init_queue(sdev->host, q); @@ -406,14 +407,9 @@ static void scsi_target_destroy(struct scsi_target *starget) static void scsi_target_dev_release(struct device *dev) { struct device *parent = dev->parent; - struct Scsi_Host *shost = dev_to_shost(parent); struct scsi_target *starget = to_scsi_target(dev); kfree(starget); - - if (atomic_dec_return(&shost->target_count) == 0) - wake_up(&shost->targets_wq); - put_device(parent); } @@ -526,10 +522,6 @@ static struct scsi_target *scsi_alloc_target(struct device *parent, starget->state = STARGET_CREATED; starget->scsi_level = SCSI_2; starget->max_target_blocked = SCSI_DEFAULT_TARGET_BLOCKED; - init_waitqueue_head(&starget->sdev_wq); - - atomic_inc(&shost->target_count); - retry: spin_lock_irqsave(shost->host_lock, flags); diff --git a/drivers/scsi/scsi_sysfs.c b/drivers/scsi/scsi_sysfs.c index 9dad2fd5297f..5d61f58399dc 100644 --- a/drivers/scsi/scsi_sysfs.c +++ b/drivers/scsi/scsi_sysfs.c @@ -443,15 +443,18 @@ static void scsi_device_cls_release(struct device *class_dev) static void scsi_device_dev_release_usercontext(struct work_struct *work) { - struct scsi_device *sdev = container_of(work, struct scsi_device, - ew.work); - struct scsi_target *starget = sdev->sdev_target; + struct scsi_device *sdev; struct device *parent; struct list_head *this, *tmp; struct scsi_vpd *vpd_pg80 = NULL, *vpd_pg83 = NULL; struct scsi_vpd *vpd_pg0 = NULL, *vpd_pg89 = NULL; struct scsi_vpd *vpd_pgb0 = NULL, *vpd_pgb1 = NULL, *vpd_pgb2 = NULL; unsigned long flags; + struct module *mod; + + sdev = container_of(work, struct scsi_device, ew.work); + + mod = sdev->host->hostt->module; scsi_dh_release_device(sdev); @@ -513,16 +516,19 @@ static void scsi_device_dev_release_usercontext(struct work_struct *work) kfree(sdev->inquiry); kfree(sdev); - if (starget && atomic_dec_return(&starget->sdev_count) == 0) - wake_up(&starget->sdev_wq); - if (parent) put_device(parent); + module_put(mod); } static void scsi_device_dev_release(struct device *dev) { struct scsi_device *sdp = to_scsi_device(dev); + + /* Set module pointer as NULL in case of module unloading */ + if (!try_module_get(sdp->host->hostt->module)) + sdp->host->hostt->module = NULL; + execute_in_process_context(scsi_device_dev_release_usercontext, &sdp->ew); } @@ -1470,6 +1476,7 @@ void __scsi_remove_device(struct scsi_device *sdev) mutex_unlock(&sdev->state_mutex); blk_mq_destroy_queue(sdev->request_queue); + kref_put(&sdev->host->tagset_refcnt, scsi_mq_free_tags); cancel_work_sync(&sdev->requeue_work); if (sdev->host->hostt->slave_destroy) @@ -1529,14 +1536,6 @@ static void __scsi_remove_target(struct scsi_target *starget) goto restart; } spin_unlock_irqrestore(shost->host_lock, flags); - - /* - * After scsi_remove_target() returns its caller can remove resources - * associated with @starget, e.g. an rport or session. Wait until all - * devices associated with @starget have been removed to prevent that - * a SCSI error handling callback function triggers a use-after-free. - */ - wait_event(starget->sdev_wq, atomic_read(&starget->sdev_count) == 0); } /** @@ -1647,9 +1646,6 @@ void scsi_sysfs_device_initialize(struct scsi_device *sdev) list_add_tail(&sdev->same_target_siblings, &starget->devices); list_add_tail(&sdev->siblings, &shost->__devices); spin_unlock_irqrestore(shost->host_lock, flags); - - atomic_inc(&starget->sdev_count); - /* * device can now only be removed via __scsi_remove_device() so hold * the target. Target will be held in CREATED state until something diff --git a/drivers/spi/spi-bitbang-txrx.h b/drivers/spi/spi-bitbang-txrx.h index 267342dfa738..2dcbe166df63 100644 --- a/drivers/spi/spi-bitbang-txrx.h +++ b/drivers/spi/spi-bitbang-txrx.h @@ -116,6 +116,7 @@ bitbang_txrx_le_cpha0(struct spi_device *spi, { /* if (cpol == 0) this is SPI_MODE_0; else this is SPI_MODE_2 */ + u8 rxbit = bits - 1; u32 oldbit = !(word & 1); /* clock starts at inactive polarity */ for (; likely(bits); bits--) { @@ -135,7 +136,7 @@ bitbang_txrx_le_cpha0(struct spi_device *spi, /* sample LSB (from slave) on leading edge */ word >>= 1; if ((flags & SPI_MASTER_NO_RX) == 0) - word |= getmiso(spi) << (bits - 1); + word |= getmiso(spi) << rxbit; setsck(spi, cpol); } return word; @@ -148,6 +149,7 @@ bitbang_txrx_le_cpha1(struct spi_device *spi, { /* if (cpol == 0) this is SPI_MODE_1; else this is SPI_MODE_3 */ + u8 rxbit = bits - 1; u32 oldbit = !(word & 1); /* clock starts at inactive polarity */ for (; likely(bits); bits--) { @@ -168,7 +170,7 @@ bitbang_txrx_le_cpha1(struct spi_device *spi, /* sample LSB (from slave) on trailing edge */ word >>= 1; if ((flags & SPI_MASTER_NO_RX) == 0) - word |= getmiso(spi) << (bits - 1); + word |= getmiso(spi) << rxbit; } return word; } diff --git a/drivers/spi/spi-cadence-quadspi.c b/drivers/spi/spi-cadence-quadspi.c index 72b1a5a2298c..e12ab5b43f34 100644 --- a/drivers/spi/spi-cadence-quadspi.c +++ b/drivers/spi/spi-cadence-quadspi.c @@ -39,6 +39,7 @@ #define CQSPI_DISABLE_DAC_MODE BIT(1) #define CQSPI_SUPPORT_EXTERNAL_DMA BIT(2) #define CQSPI_NO_SUPPORT_WR_COMPLETION BIT(3) +#define CQSPI_SLOW_SRAM BIT(4) /* Capabilities */ #define CQSPI_SUPPORTS_OCTAL BIT(0) @@ -87,6 +88,7 @@ struct cqspi_st { bool use_dma_read; u32 pd_dev_id; bool wr_completion; + bool slow_sram; }; struct cqspi_driver_platdata { @@ -333,7 +335,10 @@ static irqreturn_t cqspi_irq_handler(int this_irq, void *dev) } } - irq_status &= CQSPI_IRQ_MASK_RD | CQSPI_IRQ_MASK_WR; + else if (!cqspi->slow_sram) + irq_status &= CQSPI_IRQ_MASK_RD | CQSPI_IRQ_MASK_WR; + else + irq_status &= CQSPI_REG_IRQ_WATERMARK | CQSPI_IRQ_MASK_WR; if (irq_status) complete(&cqspi->transfer_complete); @@ -673,7 +678,18 @@ static int cqspi_indirect_read_execute(struct cqspi_flash_pdata *f_pdata, /* Clear all interrupts. */ writel(CQSPI_IRQ_STATUS_MASK, reg_base + CQSPI_REG_IRQSTATUS); - writel(CQSPI_IRQ_MASK_RD, reg_base + CQSPI_REG_IRQMASK); + /* + * On SoCFPGA platform reading the SRAM is slow due to + * hardware limitation and causing read interrupt storm to CPU, + * so enabling only watermark interrupt to disable all read + * interrupts later as we want to run "bytes to read" loop with + * all the read interrupts disabled for max performance. + */ + + if (!cqspi->slow_sram) + writel(CQSPI_IRQ_MASK_RD, reg_base + CQSPI_REG_IRQMASK); + else + writel(CQSPI_REG_IRQ_WATERMARK, reg_base + CQSPI_REG_IRQMASK); reinit_completion(&cqspi->transfer_complete); writel(CQSPI_REG_INDIRECTRD_START_MASK, @@ -684,6 +700,13 @@ static int cqspi_indirect_read_execute(struct cqspi_flash_pdata *f_pdata, msecs_to_jiffies(CQSPI_READ_TIMEOUT_MS))) ret = -ETIMEDOUT; + /* + * Disable all read interrupts until + * we are out of "bytes to read" + */ + if (cqspi->slow_sram) + writel(0x0, reg_base + CQSPI_REG_IRQMASK); + bytes_to_read = cqspi_get_rd_sram_level(cqspi); if (ret && bytes_to_read == 0) { @@ -715,8 +738,11 @@ static int cqspi_indirect_read_execute(struct cqspi_flash_pdata *f_pdata, bytes_to_read = cqspi_get_rd_sram_level(cqspi); } - if (remaining > 0) + if (remaining > 0) { reinit_completion(&cqspi->transfer_complete); + if (cqspi->slow_sram) + writel(CQSPI_REG_IRQ_WATERMARK, reg_base + CQSPI_REG_IRQMASK); + } } /* Check indirect done status */ @@ -1667,6 +1693,8 @@ static int cqspi_probe(struct platform_device *pdev) cqspi->use_dma_read = true; if (ddata->quirks & CQSPI_NO_SUPPORT_WR_COMPLETION) cqspi->wr_completion = false; + if (ddata->quirks & CQSPI_SLOW_SRAM) + cqspi->slow_sram = true; if (of_device_is_compatible(pdev->dev.of_node, "xlnx,versal-ospi-1.0")) @@ -1779,7 +1807,9 @@ static const struct cqspi_driver_platdata intel_lgm_qspi = { }; static const struct cqspi_driver_platdata socfpga_qspi = { - .quirks = CQSPI_DISABLE_DAC_MODE | CQSPI_NO_SUPPORT_WR_COMPLETION, + .quirks = CQSPI_DISABLE_DAC_MODE + | CQSPI_NO_SUPPORT_WR_COMPLETION + | CQSPI_SLOW_SRAM, }; static const struct cqspi_driver_platdata versal_ospi = { diff --git a/drivers/spi/spi-mux.c b/drivers/spi/spi-mux.c index f5d32ec4634e..0709e987bd5a 100644 --- a/drivers/spi/spi-mux.c +++ b/drivers/spi/spi-mux.c @@ -161,6 +161,7 @@ static int spi_mux_probe(struct spi_device *spi) ctlr->num_chipselect = mux_control_states(priv->mux); ctlr->bus_num = -1; ctlr->dev.of_node = spi->dev.of_node; + ctlr->must_async = true; ret = devm_spi_register_controller(&spi->dev, ctlr); if (ret) diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c index 83da8862b8f2..32c01e684af3 100644 --- a/drivers/spi/spi.c +++ b/drivers/spi/spi.c @@ -1727,8 +1727,7 @@ static void __spi_pump_messages(struct spi_controller *ctlr, bool in_kthread) spin_unlock_irqrestore(&ctlr->queue_lock, flags); ret = __spi_pump_transfer_message(ctlr, msg, was_busy); - if (!ret) - kthread_queue_work(ctlr->kworker, &ctlr->pump_messages); + kthread_queue_work(ctlr->kworker, &ctlr->pump_messages); ctlr->cur_msg = NULL; ctlr->fallback = false; @@ -4033,7 +4032,7 @@ static int __spi_sync(struct spi_device *spi, struct spi_message *message) * guard against reentrancy from a different context. The io_mutex * will catch those cases. */ - if (READ_ONCE(ctlr->queue_empty)) { + if (READ_ONCE(ctlr->queue_empty) && !ctlr->must_async) { message->actual_length = 0; message->status = -EINPROGRESS; diff --git a/drivers/thunderbolt/Kconfig b/drivers/thunderbolt/Kconfig index e76a6c173637..f12d0a3ee3e2 100644 --- a/drivers/thunderbolt/Kconfig +++ b/drivers/thunderbolt/Kconfig @@ -29,8 +29,7 @@ config USB4_DEBUGFS_WRITE config USB4_KUNIT_TEST bool "KUnit tests" if !KUNIT_ALL_TESTS - depends on (USB4=m || KUNIT=y) - depends on KUNIT + depends on USB4 && KUNIT=y default KUNIT_ALL_TESTS config USB4_DMA_TEST diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c index db516c90a977..8706482665d1 100644 --- a/drivers/vfio/vfio_iommu_type1.c +++ b/drivers/vfio/vfio_iommu_type1.c @@ -558,6 +558,18 @@ static int vaddr_get_pfns(struct mm_struct *mm, unsigned long vaddr, ret = pin_user_pages_remote(mm, vaddr, npages, flags | FOLL_LONGTERM, pages, NULL, NULL); if (ret > 0) { + int i; + + /* + * The zero page is always resident, we don't need to pin it + * and it falls into our invalid/reserved test so we don't + * unpin in put_pfn(). Unpin all zero pages in the batch here. + */ + for (i = 0 ; i < ret; i++) { + if (unlikely(is_zero_pfn(page_to_pfn(pages[i])))) + unpin_user_page(pages[i]); + } + *pfn = page_to_pfn(pages[0]); goto done; } diff --git a/drivers/video/fbdev/hyperv_fb.c b/drivers/video/fbdev/hyperv_fb.c index 886c564787f1..b58b445bb529 100644 --- a/drivers/video/fbdev/hyperv_fb.c +++ b/drivers/video/fbdev/hyperv_fb.c @@ -74,10 +74,6 @@ #define SYNTHVID_DEPTH_WIN8 32 #define SYNTHVID_FB_SIZE_WIN8 (8 * 1024 * 1024) -#define PCI_VENDOR_ID_MICROSOFT 0x1414 -#define PCI_DEVICE_ID_HYPERV_VIDEO 0x5353 - - enum pipe_msg_type { PIPE_MSG_INVALID, PIPE_MSG_DATA, diff --git a/drivers/virt/nitro_enclaves/Kconfig b/drivers/virt/nitro_enclaves/Kconfig index ce91add81401..dc4d25c26256 100644 --- a/drivers/virt/nitro_enclaves/Kconfig +++ b/drivers/virt/nitro_enclaves/Kconfig @@ -17,7 +17,7 @@ config NITRO_ENCLAVES config NITRO_ENCLAVES_MISC_DEV_TEST bool "Tests for the misc device functionality of the Nitro Enclaves" if !KUNIT_ALL_TESTS - depends on NITRO_ENCLAVES && KUNIT + depends on NITRO_ENCLAVES && KUNIT=y default KUNIT_ALL_TESTS help Enable KUnit tests for the misc device functionality of the Nitro |