diff options
| author | Maxime Ripard <maxime@cerno.tech> | 2020-11-02 11:17:54 +0100 |
|---|---|---|
| committer | Maxime Ripard <maxime@cerno.tech> | 2020-11-02 11:17:54 +0100 |
| commit | c489573b5b6ce6442ad4658d9d5ec77839b91622 (patch) | |
| tree | 6db35e19cfb4c1280033a5545c94e15ac9c7b863 /drivers/gpu | |
| parent | fbdev/sh_mobile: Drop unused include (diff) | |
| parent | Linux 5.10-rc2 (diff) | |
| download | linux-c489573b5b6ce6442ad4658d9d5ec77839b91622.tar.xz linux-c489573b5b6ce6442ad4658d9d5ec77839b91622.zip | |
Merge drm/drm-next into drm-misc-next
Daniel needs -rc2 in drm-misc-next to merge some patches
Signed-off-by: Maxime Ripard <maxime@cerno.tech>
Diffstat (limited to 'drivers/gpu')
510 files changed, 25157 insertions, 5951 deletions
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h index 4009d2e30727..87f095dc385c 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h @@ -49,6 +49,8 @@ #include <linux/rbtree.h> #include <linux/hashtable.h> #include <linux/dma-fence.h> +#include <linux/pci.h> +#include <linux/aer.h> #include <drm/ttm/ttm_bo_api.h> #include <drm/ttm/ttm_bo_driver.h> @@ -102,6 +104,7 @@ #include "amdgpu_mes.h" #include "amdgpu_umc.h" #include "amdgpu_mmhub.h" +#include "amdgpu_gfxhub.h" #include "amdgpu_df.h" #define MAX_GPU_INSTANCE 16 @@ -879,6 +882,9 @@ struct amdgpu_device { /* mmhub */ struct amdgpu_mmhub mmhub; + /* gfxhub */ + struct amdgpu_gfxhub gfxhub; + /* gfx */ struct amdgpu_gfx gfx; @@ -987,6 +993,9 @@ struct amdgpu_device { atomic_t throttling_logging_enabled; struct ratelimit_state throttling_logging_rs; uint32_t ras_features; + + bool in_pci_err_recovery; + struct pci_saved_state *pci_state; }; static inline struct amdgpu_device *drm_to_adev(struct drm_device *ddev) @@ -1011,18 +1020,32 @@ int amdgpu_gpu_wait_for_idle(struct amdgpu_device *adev); void amdgpu_device_vram_access(struct amdgpu_device *adev, loff_t pos, uint32_t *buf, size_t size, bool write); -uint32_t amdgpu_mm_rreg(struct amdgpu_device *adev, uint32_t reg, +uint32_t amdgpu_device_rreg(struct amdgpu_device *adev, + uint32_t reg, uint32_t acc_flags); +void amdgpu_device_wreg(struct amdgpu_device *adev, + uint32_t reg, uint32_t v, uint32_t acc_flags); -void amdgpu_mm_wreg(struct amdgpu_device *adev, uint32_t reg, uint32_t v, - uint32_t acc_flags); -void amdgpu_mm_wreg_mmio_rlc(struct amdgpu_device *adev, uint32_t reg, uint32_t v, - uint32_t acc_flags); +void amdgpu_mm_wreg_mmio_rlc(struct amdgpu_device *adev, + uint32_t reg, uint32_t v); void amdgpu_mm_wreg8(struct amdgpu_device *adev, uint32_t offset, uint8_t value); uint8_t amdgpu_mm_rreg8(struct amdgpu_device *adev, uint32_t offset); u32 amdgpu_io_rreg(struct amdgpu_device *adev, u32 reg); void amdgpu_io_wreg(struct amdgpu_device *adev, u32 reg, u32 v); +u32 amdgpu_device_indirect_rreg(struct amdgpu_device *adev, + u32 pcie_index, u32 pcie_data, + u32 reg_addr); +u64 amdgpu_device_indirect_rreg64(struct amdgpu_device *adev, + u32 pcie_index, u32 pcie_data, + u32 reg_addr); +void amdgpu_device_indirect_wreg(struct amdgpu_device *adev, + u32 pcie_index, u32 pcie_data, + u32 reg_addr, u32 reg_data); +void amdgpu_device_indirect_wreg64(struct amdgpu_device *adev, + u32 pcie_index, u32 pcie_data, + u32 reg_addr, u64 reg_data); + bool amdgpu_device_asic_has_dc_support(enum amd_asic_type asic_type); bool amdgpu_device_has_dc_support(struct amdgpu_device *adev); @@ -1033,8 +1056,8 @@ int emu_soc_asic_init(struct amdgpu_device *adev); */ #define AMDGPU_REGS_NO_KIQ (1<<1) -#define RREG32_NO_KIQ(reg) amdgpu_mm_rreg(adev, (reg), AMDGPU_REGS_NO_KIQ) -#define WREG32_NO_KIQ(reg, v) amdgpu_mm_wreg(adev, (reg), (v), AMDGPU_REGS_NO_KIQ) +#define RREG32_NO_KIQ(reg) amdgpu_device_rreg(adev, (reg), AMDGPU_REGS_NO_KIQ) +#define WREG32_NO_KIQ(reg, v) amdgpu_device_wreg(adev, (reg), (v), AMDGPU_REGS_NO_KIQ) #define RREG32_KIQ(reg) amdgpu_kiq_rreg(adev, (reg)) #define WREG32_KIQ(reg, v) amdgpu_kiq_wreg(adev, (reg), (v)) @@ -1042,9 +1065,9 @@ int emu_soc_asic_init(struct amdgpu_device *adev); #define RREG8(reg) amdgpu_mm_rreg8(adev, (reg)) #define WREG8(reg, v) amdgpu_mm_wreg8(adev, (reg), (v)) -#define RREG32(reg) amdgpu_mm_rreg(adev, (reg), 0) -#define DREG32(reg) printk(KERN_INFO "REGISTER: " #reg " : 0x%08X\n", amdgpu_mm_rreg(adev, (reg), 0)) -#define WREG32(reg, v) amdgpu_mm_wreg(adev, (reg), (v), 0) +#define RREG32(reg) amdgpu_device_rreg(adev, (reg), 0) +#define DREG32(reg) printk(KERN_INFO "REGISTER: " #reg " : 0x%08X\n", amdgpu_device_rreg(adev, (reg), 0)) +#define WREG32(reg, v) amdgpu_device_wreg(adev, (reg), (v), 0) #define REG_SET(FIELD, v) (((v) << FIELD##_SHIFT) & FIELD##_MASK) #define REG_GET(FIELD, v) (((v) << FIELD##_SHIFT) & FIELD##_MASK) #define RREG32_PCIE(reg) adev->pcie_rreg(adev, (reg)) @@ -1090,7 +1113,7 @@ int emu_soc_asic_init(struct amdgpu_device *adev); WREG32_SMC(_Reg, tmp); \ } while (0) -#define DREG32_SYS(sqf, adev, reg) seq_printf((sqf), #reg " : 0x%08X\n", amdgpu_mm_rreg((adev), (reg), false)) +#define DREG32_SYS(sqf, adev, reg) seq_printf((sqf), #reg " : 0x%08X\n", amdgpu_device_rreg((adev), (reg), false)) #define RREG32_IO(reg) amdgpu_io_rreg(adev, (reg)) #define WREG32_IO(reg, v) amdgpu_io_wreg(adev, (reg), (v)) @@ -1260,6 +1283,15 @@ static inline int amdgpu_dm_display_resume(struct amdgpu_device *adev) { return void amdgpu_register_gpu_instance(struct amdgpu_device *adev); void amdgpu_unregister_gpu_instance(struct amdgpu_device *adev); +pci_ers_result_t amdgpu_pci_error_detected(struct pci_dev *pdev, + pci_channel_state_t state); +pci_ers_result_t amdgpu_pci_mmio_enabled(struct pci_dev *pdev); +pci_ers_result_t amdgpu_pci_slot_reset(struct pci_dev *pdev); +void amdgpu_pci_resume(struct pci_dev *pdev); + +bool amdgpu_device_cache_pci_state(struct pci_dev *pdev); +bool amdgpu_device_load_pci_state(struct pci_dev *pdev); + #include "amdgpu_object.h" /* used by df_v3_6.c and amdgpu_pmu.c */ diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c index 4a93b880c6bf..165b02e267b0 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c @@ -806,8 +806,8 @@ int amdgpu_acpi_init(struct amdgpu_device *adev) } adev->atif = atif; - if (atif->notifications.brightness_change) { #if defined(CONFIG_BACKLIGHT_CLASS_DEVICE) || defined(CONFIG_BACKLIGHT_CLASS_DEVICE_MODULE) + if (atif->notifications.brightness_change) { if (amdgpu_device_has_dc_support(adev)) { #if defined(CONFIG_DRM_AMD_DC) struct amdgpu_display_manager *dm = &adev->dm; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c index edff1b7f282a..0544460653b9 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c @@ -36,6 +36,8 @@ */ uint64_t amdgpu_amdkfd_total_mem_size; +static bool kfd_initialized; + int amdgpu_amdkfd_init(void) { struct sysinfo si; @@ -51,19 +53,26 @@ int amdgpu_amdkfd_init(void) #else ret = -ENOENT; #endif + kfd_initialized = !ret; return ret; } void amdgpu_amdkfd_fini(void) { - kgd2kfd_exit(); + if (kfd_initialized) { + kgd2kfd_exit(); + kfd_initialized = false; + } } void amdgpu_amdkfd_device_probe(struct amdgpu_device *adev) { bool vf = amdgpu_sriov_vf(adev); + if (!kfd_initialized) + return; + adev->kfd.dev = kgd2kfd_probe((struct kgd_dev *)adev, adev->pdev, adev->asic_type, vf); @@ -572,6 +581,13 @@ uint32_t amdgpu_amdkfd_get_asic_rev_id(struct kgd_dev *kgd) return adev->rev_id; } +int amdgpu_amdkfd_get_noretry(struct kgd_dev *kgd) +{ + struct amdgpu_device *adev = (struct amdgpu_device *)kgd; + + return adev->gmc.noretry; +} + int amdgpu_amdkfd_submit_ib(struct kgd_dev *kgd, enum kgd_engine_type engine, uint32_t vmid, uint64_t gpu_addr, uint32_t *ib_cmd, uint32_t ib_len) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h index a10507ecb750..ea391ca7f2f1 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h @@ -181,6 +181,7 @@ uint64_t amdgpu_amdkfd_get_unique_id(struct kgd_dev *kgd); uint64_t amdgpu_amdkfd_get_mmio_remap_phys_addr(struct kgd_dev *kgd); uint32_t amdgpu_amdkfd_get_num_gws(struct kgd_dev *kgd); uint32_t amdgpu_amdkfd_get_asic_rev_id(struct kgd_dev *kgd); +int amdgpu_amdkfd_get_noretry(struct kgd_dev *kgd); uint8_t amdgpu_amdkfd_get_xgmi_hops_count(struct kgd_dev *dst, struct kgd_dev *src); /* Read user wptr from a specified user address space with page fault @@ -207,11 +208,11 @@ uint8_t amdgpu_amdkfd_get_xgmi_hops_count(struct kgd_dev *dst, struct kgd_dev *s }) /* GPUVM API */ -int amdgpu_amdkfd_gpuvm_create_process_vm(struct kgd_dev *kgd, unsigned int pasid, +int amdgpu_amdkfd_gpuvm_create_process_vm(struct kgd_dev *kgd, u32 pasid, void **vm, void **process_info, struct dma_fence **ef); int amdgpu_amdkfd_gpuvm_acquire_process_vm(struct kgd_dev *kgd, - struct file *filp, unsigned int pasid, + struct file *filp, u32 pasid, void **vm, void **process_info, struct dma_fence **ef); void amdgpu_amdkfd_gpuvm_destroy_cb(struct amdgpu_device *adev, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10.c index df0aab0fc67e..4763bab7a4d0 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10.c @@ -32,7 +32,6 @@ #include "v10_structs.h" #include "nv.h" #include "nvd.h" -#include "gfxhub_v2_0.h" enum hqd_dequeue_request_type { NO_ACTION = 0, @@ -105,7 +104,7 @@ static void kgd_program_sh_mem_settings(struct kgd_dev *kgd, uint32_t vmid, unlock_srbm(kgd); } -static int kgd_set_pasid_vmid_mapping(struct kgd_dev *kgd, unsigned int pasid, +static int kgd_set_pasid_vmid_mapping(struct kgd_dev *kgd, u32 pasid, unsigned int vmid) { struct amdgpu_device *adev = get_amdgpu_device(kgd); @@ -753,7 +752,7 @@ static void set_vm_context_page_table_base(struct kgd_dev *kgd, uint32_t vmid, } /* SDMA is on gfxhub as well for Navi1* series */ - gfxhub_v2_0_setup_vm_pt_regs(adev, vmid, page_table_base); + adev->gfxhub.funcs->setup_vm_pt_regs(adev, vmid, page_table_base); } const struct kfd2kgd_calls gfx_v10_kfd2kgd = { diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10_3.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10_3.c index 5b38f848b772..50016bf9c427 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10_3.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10_3.c @@ -31,7 +31,6 @@ #include "v10_structs.h" #include "nv.h" #include "nvd.h" -#include "gfxhub_v2_1.h" enum hqd_dequeue_request_type { NO_ACTION = 0, @@ -657,7 +656,7 @@ static void set_vm_context_page_table_base_v10_3(struct kgd_dev *kgd, uint32_t v struct amdgpu_device *adev = get_amdgpu_device(kgd); /* SDMA is on gfxhub as well for Navi1* series */ - gfxhub_v2_1_setup_vm_pt_regs(adev, vmid, page_table_base); + adev->gfxhub.funcs->setup_vm_pt_regs(adev, vmid, page_table_base); } #if 0 diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c index 275f20399373..b91d27e39bad 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c @@ -139,7 +139,7 @@ static void kgd_program_sh_mem_settings(struct kgd_dev *kgd, uint32_t vmid, unlock_srbm(kgd); } -static int kgd_set_pasid_vmid_mapping(struct kgd_dev *kgd, unsigned int pasid, +static int kgd_set_pasid_vmid_mapping(struct kgd_dev *kgd, u32 pasid, unsigned int vmid) { struct amdgpu_device *adev = get_amdgpu_device(kgd); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v8.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v8.c index 4997189d8b36..5ce0ce704a21 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v8.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v8.c @@ -96,7 +96,7 @@ static void kgd_program_sh_mem_settings(struct kgd_dev *kgd, uint32_t vmid, unlock_srbm(kgd); } -static int kgd_set_pasid_vmid_mapping(struct kgd_dev *kgd, unsigned int pasid, +static int kgd_set_pasid_vmid_mapping(struct kgd_dev *kgd, u32 pasid, unsigned int vmid) { struct amdgpu_device *adev = get_amdgpu_device(kgd); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c index e6aede725197..43b18863a8b8 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c @@ -36,9 +36,7 @@ #include "v9_structs.h" #include "soc15.h" #include "soc15d.h" -#include "mmhub_v1_0.h" -#include "gfxhub_v1_0.h" - +#include "gfx_v9_0.h" enum hqd_dequeue_request_type { NO_ACTION = 0, @@ -110,7 +108,7 @@ void kgd_gfx_v9_program_sh_mem_settings(struct kgd_dev *kgd, uint32_t vmid, unlock_srbm(kgd); } -int kgd_gfx_v9_set_pasid_vmid_mapping(struct kgd_dev *kgd, unsigned int pasid, +int kgd_gfx_v9_set_pasid_vmid_mapping(struct kgd_dev *kgd, u32 pasid, unsigned int vmid) { struct amdgpu_device *adev = get_amdgpu_device(kgd); @@ -703,7 +701,180 @@ void kgd_gfx_v9_set_vm_context_page_table_base(struct kgd_dev *kgd, adev->mmhub.funcs->setup_vm_pt_regs(adev, vmid, page_table_base); - gfxhub_v1_0_setup_vm_pt_regs(adev, vmid, page_table_base); + adev->gfxhub.funcs->setup_vm_pt_regs(adev, vmid, page_table_base); +} + +static void lock_spi_csq_mutexes(struct amdgpu_device *adev) +{ + mutex_lock(&adev->srbm_mutex); + mutex_lock(&adev->grbm_idx_mutex); + +} + +static void unlock_spi_csq_mutexes(struct amdgpu_device *adev) +{ + mutex_unlock(&adev->grbm_idx_mutex); + mutex_unlock(&adev->srbm_mutex); +} + +/** + * @get_wave_count: Read device registers to get number of waves in flight for + * a particular queue. The method also returns the VMID associated with the + * queue. + * + * @adev: Handle of device whose registers are to be read + * @queue_idx: Index of queue in the queue-map bit-field + * @wave_cnt: Output parameter updated with number of waves in flight + * @vmid: Output parameter updated with VMID of queue whose wave count + * is being collected + */ +static void get_wave_count(struct amdgpu_device *adev, int queue_idx, + int *wave_cnt, int *vmid) +{ + int pipe_idx; + int queue_slot; + unsigned int reg_val; + + /* + * Program GRBM with appropriate MEID, PIPEID, QUEUEID and VMID + * parameters to read out waves in flight. Get VMID if there are + * non-zero waves in flight. + */ + *vmid = 0xFF; + *wave_cnt = 0; + pipe_idx = queue_idx / adev->gfx.mec.num_queue_per_pipe; + queue_slot = queue_idx % adev->gfx.mec.num_queue_per_pipe; + soc15_grbm_select(adev, 1, pipe_idx, queue_slot, 0); + reg_val = RREG32(SOC15_REG_OFFSET(GC, 0, mmSPI_CSQ_WF_ACTIVE_COUNT_0) + + queue_slot); + *wave_cnt = reg_val & SPI_CSQ_WF_ACTIVE_COUNT_0__COUNT_MASK; + if (*wave_cnt != 0) + *vmid = (RREG32_SOC15(GC, 0, mmCP_HQD_VMID) & + CP_HQD_VMID__VMID_MASK) >> CP_HQD_VMID__VMID__SHIFT; +} + +/** + * @kgd_gfx_v9_get_cu_occupancy: Reads relevant registers associated with each + * shader engine and aggregates the number of waves that are in flight for the + * process whose pasid is provided as a parameter. The process could have ZERO + * or more queues running and submitting waves to compute units. + * + * @kgd: Handle of device from which to get number of waves in flight + * @pasid: Identifies the process for which this query call is invoked + * @wave_cnt: Output parameter updated with number of waves in flight that + * belong to process with given pasid + * @max_waves_per_cu: Output parameter updated with maximum number of waves + * possible per Compute Unit + * + * @note: It's possible that the device has too many queues (oversubscription) + * in which case a VMID could be remapped to a different PASID. This could lead + * to an iaccurate wave count. Following is a high-level sequence: + * Time T1: vmid = getVmid(); vmid is associated with Pasid P1 + * Time T2: passId = getPasId(vmid); vmid is associated with Pasid P2 + * In the sequence above wave count obtained from time T1 will be incorrectly + * lost or added to total wave count. + * + * The registers that provide the waves in flight are: + * + * SPI_CSQ_WF_ACTIVE_STATUS - bit-map of queues per pipe. The bit is ON if a + * queue is slotted, OFF if there is no queue. A process could have ZERO or + * more queues slotted and submitting waves to be run on compute units. Even + * when there is a queue it is possible there could be zero wave fronts, this + * can happen when queue is waiting on top-of-pipe events - e.g. waitRegMem + * command + * + * For each bit that is ON from above: + * + * Read (SPI_CSQ_WF_ACTIVE_COUNT_0 + queue_idx) register. It provides the + * number of waves that are in flight for the queue at specified index. The + * index ranges from 0 to 7. + * + * If non-zero waves are in flight, read CP_HQD_VMID register to obtain VMID + * of the wave(s). + * + * Determine if VMID from above step maps to pasid provided as parameter. If + * it matches agrregate the wave count. That the VMID will not match pasid is + * a normal condition i.e. a device is expected to support multiple queues + * from multiple proceses. + * + * Reading registers referenced above involves programming GRBM appropriately + */ +static void kgd_gfx_v9_get_cu_occupancy(struct kgd_dev *kgd, int pasid, + int *pasid_wave_cnt, int *max_waves_per_cu) +{ + int qidx; + int vmid; + int se_idx; + int sh_idx; + int se_cnt; + int sh_cnt; + int wave_cnt; + int queue_map; + int pasid_tmp; + int max_queue_cnt; + int vmid_wave_cnt = 0; + struct amdgpu_device *adev; + DECLARE_BITMAP(cp_queue_bitmap, KGD_MAX_QUEUES); + + adev = get_amdgpu_device(kgd); + lock_spi_csq_mutexes(adev); + soc15_grbm_select(adev, 1, 0, 0, 0); + + /* + * Iterate through the shader engines and arrays of the device + * to get number of waves in flight + */ + bitmap_complement(cp_queue_bitmap, adev->gfx.mec.queue_bitmap, + KGD_MAX_QUEUES); + max_queue_cnt = adev->gfx.mec.num_pipe_per_mec * + adev->gfx.mec.num_queue_per_pipe; + sh_cnt = adev->gfx.config.max_sh_per_se; + se_cnt = adev->gfx.config.max_shader_engines; + for (se_idx = 0; se_idx < se_cnt; se_idx++) { + for (sh_idx = 0; sh_idx < sh_cnt; sh_idx++) { + + gfx_v9_0_select_se_sh(adev, se_idx, sh_idx, 0xffffffff); + queue_map = RREG32(SOC15_REG_OFFSET(GC, 0, + mmSPI_CSQ_WF_ACTIVE_STATUS)); + + /* + * Assumption: queue map encodes following schema: four + * pipes per each micro-engine, with each pipe mapping + * eight queues. This schema is true for GFX9 devices + * and must be verified for newer device families + */ + for (qidx = 0; qidx < max_queue_cnt; qidx++) { + + /* Skip qeueus that are not associated with + * compute functions + */ + if (!test_bit(qidx, cp_queue_bitmap)) + continue; + + if (!(queue_map & (1 << qidx))) + continue; + + /* Get number of waves in flight and aggregate them */ + get_wave_count(adev, qidx, &wave_cnt, &vmid); + if (wave_cnt != 0) { + pasid_tmp = + RREG32(SOC15_REG_OFFSET(OSSSYS, 0, + mmIH_VMID_0_LUT) + vmid); + if (pasid_tmp == pasid) + vmid_wave_cnt += wave_cnt; + } + } + } + } + + gfx_v9_0_select_se_sh(adev, 0xffffffff, 0xffffffff, 0xffffffff); + soc15_grbm_select(adev, 0, 0, 0, 0); + unlock_spi_csq_mutexes(adev); + + /* Update the output parameters and return */ + *pasid_wave_cnt = vmid_wave_cnt; + *max_waves_per_cu = adev->gfx.cu_info.simd_per_cu * + adev->gfx.cu_info.max_waves_per_simd; } const struct kfd2kgd_calls gfx_v9_kfd2kgd = { @@ -726,4 +897,5 @@ const struct kfd2kgd_calls gfx_v9_kfd2kgd = { .get_atc_vmid_pasid_mapping_info = kgd_gfx_v9_get_atc_vmid_pasid_mapping_info, .set_vm_context_page_table_base = kgd_gfx_v9_set_vm_context_page_table_base, + .get_cu_occupancy = kgd_gfx_v9_get_cu_occupancy, }; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.h index f098e88d3a0d..fc8934b86d93 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.h @@ -26,7 +26,7 @@ void kgd_gfx_v9_program_sh_mem_settings(struct kgd_dev *kgd, uint32_t vmid, uint32_t sh_mem_config, uint32_t sh_mem_ape1_base, uint32_t sh_mem_ape1_limit, uint32_t sh_mem_bases); -int kgd_gfx_v9_set_pasid_vmid_mapping(struct kgd_dev *kgd, unsigned int pasid, +int kgd_gfx_v9_set_pasid_vmid_mapping(struct kgd_dev *kgd, u32 pasid, unsigned int vmid); int kgd_gfx_v9_init_interrupts(struct kgd_dev *kgd, uint32_t pipe_id); int kgd_gfx_v9_hqd_load(struct kgd_dev *kgd, void *mqd, uint32_t pipe_id, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c index 64d4b5ff95d6..054a1c2d5054 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c @@ -996,7 +996,7 @@ create_evict_fence_fail: return ret; } -int amdgpu_amdkfd_gpuvm_create_process_vm(struct kgd_dev *kgd, unsigned int pasid, +int amdgpu_amdkfd_gpuvm_create_process_vm(struct kgd_dev *kgd, u32 pasid, void **vm, void **process_info, struct dma_fence **ef) { @@ -1032,7 +1032,7 @@ amdgpu_vm_init_fail: } int amdgpu_amdkfd_gpuvm_acquire_process_vm(struct kgd_dev *kgd, - struct file *filp, unsigned int pasid, + struct file *filp, u32 pasid, void **vm, void **process_info, struct dma_fence **ef) { diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c index 17c010d0431f..b4df6460e45a 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c @@ -543,6 +543,7 @@ int amdgpu_mem_train_support(struct amdgpu_device *adev) case HW_REV(11, 0, 0): case HW_REV(11, 0, 5): case HW_REV(11, 0, 7): + case HW_REV(11, 0, 11): ret = 1; break; default: diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c index 3e35a8f2c5e5..7abe9500c0c6 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c @@ -616,7 +616,7 @@ static bool amdgpu_atpx_detect(void) while ((pdev = pci_get_class(PCI_CLASS_DISPLAY_VGA << 8, pdev)) != NULL) { vga_count++; - has_atpx |= (amdgpu_atpx_pci_probe_handle(pdev) == true); + has_atpx |= amdgpu_atpx_pci_probe_handle(pdev); parent_pdev = pci_upstream_bridge(pdev); d3_supported |= parent_pdev && parent_pdev->bridge_d3; @@ -626,7 +626,7 @@ static bool amdgpu_atpx_detect(void) while ((pdev = pci_get_class(PCI_CLASS_DISPLAY_OTHER << 8, pdev)) != NULL) { vga_count++; - has_atpx |= (amdgpu_atpx_pci_probe_handle(pdev) == true); + has_atpx |= amdgpu_atpx_pci_probe_handle(pdev); parent_pdev = pci_upstream_bridge(pdev); d3_supported |= parent_pdev && parent_pdev->bridge_d3; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c index a5e08dc54e4a..065937482239 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c @@ -267,7 +267,7 @@ static int amdgpu_debugfs_process_reg_op(bool read, struct file *f, } else { r = get_user(value, (uint32_t *)buf); if (!r) - amdgpu_mm_wreg_mmio_rlc(adev, *pos >> 2, value, 0); + amdgpu_mm_wreg_mmio_rlc(adev, *pos >> 2, value); } if (r) { result = r; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index f7307af76452..37da3537ba2e 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -80,8 +80,6 @@ MODULE_FIRMWARE("amdgpu/renoir_gpu_info.bin"); MODULE_FIRMWARE("amdgpu/navi10_gpu_info.bin"); MODULE_FIRMWARE("amdgpu/navi14_gpu_info.bin"); MODULE_FIRMWARE("amdgpu/navi12_gpu_info.bin"); -MODULE_FIRMWARE("amdgpu/sienna_cichlid_gpu_info.bin"); -MODULE_FIRMWARE("amdgpu/navy_flounder_gpu_info.bin"); #define AMDGPU_RESUME_MS 2000 @@ -303,10 +301,10 @@ void amdgpu_device_vram_access(struct amdgpu_device *adev, loff_t pos, } /* - * MMIO register access helper functions. + * register access helper functions. */ /** - * amdgpu_mm_rreg - read a memory mapped IO register + * amdgpu_device_rreg - read a memory mapped IO or indirect register * * @adev: amdgpu_device pointer * @reg: dword aligned register offset @@ -314,30 +312,29 @@ void amdgpu_device_vram_access(struct amdgpu_device *adev, loff_t pos, * * Returns the 32 bit value from the offset specified. */ -uint32_t amdgpu_mm_rreg(struct amdgpu_device *adev, uint32_t reg, - uint32_t acc_flags) +uint32_t amdgpu_device_rreg(struct amdgpu_device *adev, + uint32_t reg, uint32_t acc_flags) { uint32_t ret; - if (!(acc_flags & AMDGPU_REGS_NO_KIQ) && amdgpu_sriov_runtime(adev) && - down_read_trylock(&adev->reset_sem)) { - ret = amdgpu_kiq_rreg(adev, reg); - up_read(&adev->reset_sem); - return ret; - } - - if ((reg * 4) < adev->rmmio_size) - ret = readl(((void __iomem *)adev->rmmio) + (reg * 4)); - else { - unsigned long flags; + if (adev->in_pci_err_recovery) + return 0; - spin_lock_irqsave(&adev->mmio_idx_lock, flags); - writel((reg * 4), ((void __iomem *)adev->rmmio) + (mmMM_INDEX * 4)); - ret = readl(((void __iomem *)adev->rmmio) + (mmMM_DATA * 4)); - spin_unlock_irqrestore(&adev->mmio_idx_lock, flags); + if ((reg * 4) < adev->rmmio_size) { + if (!(acc_flags & AMDGPU_REGS_NO_KIQ) && + amdgpu_sriov_runtime(adev) && + down_read_trylock(&adev->reset_sem)) { + ret = amdgpu_kiq_rreg(adev, reg); + up_read(&adev->reset_sem); + } else { + ret = readl(((void __iomem *)adev->rmmio) + (reg * 4)); + } + } else { + ret = adev->pcie_rreg(adev, reg * 4); } - trace_amdgpu_mm_rreg(adev->pdev->device, reg, ret); + trace_amdgpu_device_rreg(adev->pdev->device, reg, ret); + return ret; } @@ -355,7 +352,11 @@ uint32_t amdgpu_mm_rreg(struct amdgpu_device *adev, uint32_t reg, * * Returns the 8 bit value from the offset specified. */ -uint8_t amdgpu_mm_rreg8(struct amdgpu_device *adev, uint32_t offset) { +uint8_t amdgpu_mm_rreg8(struct amdgpu_device *adev, uint32_t offset) +{ + if (adev->in_pci_err_recovery) + return 0; + if (offset < adev->rmmio_size) return (readb(adev->rmmio + offset)); BUG(); @@ -376,33 +377,19 @@ uint8_t amdgpu_mm_rreg8(struct amdgpu_device *adev, uint32_t offset) { * * Writes the value specified to the offset specified. */ -void amdgpu_mm_wreg8(struct amdgpu_device *adev, uint32_t offset, uint8_t value) { +void amdgpu_mm_wreg8(struct amdgpu_device *adev, uint32_t offset, uint8_t value) +{ + if (adev->in_pci_err_recovery) + return; + if (offset < adev->rmmio_size) writeb(value, adev->rmmio + offset); else BUG(); } -static inline void amdgpu_mm_wreg_mmio(struct amdgpu_device *adev, - uint32_t reg, uint32_t v, - uint32_t acc_flags) -{ - trace_amdgpu_mm_wreg(adev->pdev->device, reg, v); - - if ((reg * 4) < adev->rmmio_size) - writel(v, ((void __iomem *)adev->rmmio) + (reg * 4)); - else { - unsigned long flags; - - spin_lock_irqsave(&adev->mmio_idx_lock, flags); - writel((reg * 4), ((void __iomem *)adev->rmmio) + (mmMM_INDEX * 4)); - writel(v, ((void __iomem *)adev->rmmio) + (mmMM_DATA * 4)); - spin_unlock_irqrestore(&adev->mmio_idx_lock, flags); - } -} - /** - * amdgpu_mm_wreg - write to a memory mapped IO register + * amdgpu_device_wreg - write to a memory mapped IO or indirect register * * @adev: amdgpu_device pointer * @reg: dword aligned register offset @@ -411,17 +398,27 @@ static inline void amdgpu_mm_wreg_mmio(struct amdgpu_device *adev, * * Writes the value specified to the offset specified. */ -void amdgpu_mm_wreg(struct amdgpu_device *adev, uint32_t reg, uint32_t v, - uint32_t acc_flags) +void amdgpu_device_wreg(struct amdgpu_device *adev, + uint32_t reg, uint32_t v, + uint32_t acc_flags) { - if (!(acc_flags & AMDGPU_REGS_NO_KIQ) && amdgpu_sriov_runtime(adev) && - down_read_trylock(&adev->reset_sem)) { - amdgpu_kiq_wreg(adev, reg, v); - up_read(&adev->reset_sem); + if (adev->in_pci_err_recovery) return; + + if ((reg * 4) < adev->rmmio_size) { + if (!(acc_flags & AMDGPU_REGS_NO_KIQ) && + amdgpu_sriov_runtime(adev) && + down_read_trylock(&adev->reset_sem)) { + amdgpu_kiq_wreg(adev, reg, v); + up_read(&adev->reset_sem); + } else { + writel(v, ((void __iomem *)adev->rmmio) + (reg * 4)); + } + } else { + adev->pcie_wreg(adev, reg * 4, v); } - amdgpu_mm_wreg_mmio(adev, reg, v, acc_flags); + trace_amdgpu_device_wreg(adev->pdev->device, reg, v); } /* @@ -429,18 +426,20 @@ void amdgpu_mm_wreg(struct amdgpu_device *adev, uint32_t reg, uint32_t v, * * this function is invoked only the debugfs register access * */ -void amdgpu_mm_wreg_mmio_rlc(struct amdgpu_device *adev, uint32_t reg, uint32_t v, - uint32_t acc_flags) +void amdgpu_mm_wreg_mmio_rlc(struct amdgpu_device *adev, + uint32_t reg, uint32_t v) { - if (amdgpu_sriov_fullaccess(adev) && - adev->gfx.rlc.funcs && - adev->gfx.rlc.funcs->is_rlcg_access_range) { + if (adev->in_pci_err_recovery) + return; + if (amdgpu_sriov_fullaccess(adev) && + adev->gfx.rlc.funcs && + adev->gfx.rlc.funcs->is_rlcg_access_range) { if (adev->gfx.rlc.funcs->is_rlcg_access_range(adev, reg)) return adev->gfx.rlc.funcs->rlcg_wreg(adev, reg, v); + } else { + writel(v, ((void __iomem *)adev->rmmio) + (reg * 4)); } - - amdgpu_mm_wreg_mmio(adev, reg, v, acc_flags); } /** @@ -453,6 +452,9 @@ void amdgpu_mm_wreg_mmio_rlc(struct amdgpu_device *adev, uint32_t reg, uint32_t */ u32 amdgpu_io_rreg(struct amdgpu_device *adev, u32 reg) { + if (adev->in_pci_err_recovery) + return 0; + if ((reg * 4) < adev->rio_mem_size) return ioread32(adev->rio_mem + (reg * 4)); else { @@ -472,6 +474,9 @@ u32 amdgpu_io_rreg(struct amdgpu_device *adev, u32 reg) */ void amdgpu_io_wreg(struct amdgpu_device *adev, u32 reg, u32 v) { + if (adev->in_pci_err_recovery) + return; + if ((reg * 4) < adev->rio_mem_size) iowrite32(v, adev->rio_mem + (reg * 4)); else { @@ -491,6 +496,9 @@ void amdgpu_io_wreg(struct amdgpu_device *adev, u32 reg, u32 v) */ u32 amdgpu_mm_rdoorbell(struct amdgpu_device *adev, u32 index) { + if (adev->in_pci_err_recovery) + return 0; + if (index < adev->doorbell.num_doorbells) { return readl(adev->doorbell.ptr + index); } else { @@ -511,6 +519,9 @@ u32 amdgpu_mm_rdoorbell(struct amdgpu_device *adev, u32 index) */ void amdgpu_mm_wdoorbell(struct amdgpu_device *adev, u32 index, u32 v) { + if (adev->in_pci_err_recovery) + return; + if (index < adev->doorbell.num_doorbells) { writel(v, adev->doorbell.ptr + index); } else { @@ -529,6 +540,9 @@ void amdgpu_mm_wdoorbell(struct amdgpu_device *adev, u32 index, u32 v) */ u64 amdgpu_mm_rdoorbell64(struct amdgpu_device *adev, u32 index) { + if (adev->in_pci_err_recovery) + return 0; + if (index < adev->doorbell.num_doorbells) { return atomic64_read((atomic64_t *)(adev->doorbell.ptr + index)); } else { @@ -549,6 +563,9 @@ u64 amdgpu_mm_rdoorbell64(struct amdgpu_device *adev, u32 index) */ void amdgpu_mm_wdoorbell64(struct amdgpu_device *adev, u32 index, u64 v) { + if (adev->in_pci_err_recovery) + return; + if (index < adev->doorbell.num_doorbells) { atomic64_set((atomic64_t *)(adev->doorbell.ptr + index), v); } else { @@ -557,6 +574,135 @@ void amdgpu_mm_wdoorbell64(struct amdgpu_device *adev, u32 index, u64 v) } /** + * amdgpu_device_indirect_rreg - read an indirect register + * + * @adev: amdgpu_device pointer + * @pcie_index: mmio register offset + * @pcie_data: mmio register offset + * + * Returns the value of indirect register @reg_addr + */ +u32 amdgpu_device_indirect_rreg(struct amdgpu_device *adev, + u32 pcie_index, u32 pcie_data, + u32 reg_addr) +{ + unsigned long flags; + u32 r; + void __iomem *pcie_index_offset; + void __iomem *pcie_data_offset; + + spin_lock_irqsave(&adev->pcie_idx_lock, flags); + pcie_index_offset = (void __iomem *)adev->rmmio + pcie_index * 4; + pcie_data_offset = (void __iomem *)adev->rmmio + pcie_data * 4; + + writel(reg_addr, pcie_index_offset); + readl(pcie_index_offset); + r = readl(pcie_data_offset); + spin_unlock_irqrestore(&adev->pcie_idx_lock, flags); + + return r; +} + +/** + * amdgpu_device_indirect_rreg64 - read a 64bits indirect register + * + * @adev: amdgpu_device pointer + * @pcie_index: mmio register offset + * @pcie_data: mmio register offset + * + * Returns the value of indirect register @reg_addr + */ +u64 amdgpu_device_indirect_rreg64(struct amdgpu_device *adev, + u32 pcie_index, u32 pcie_data, + u32 reg_addr) +{ + unsigned long flags; + u64 r; + void __iomem *pcie_index_offset; + void __iomem *pcie_data_offset; + + spin_lock_irqsave(&adev->pcie_idx_lock, flags); + pcie_index_offset = (void __iomem *)adev->rmmio + pcie_index * 4; + pcie_data_offset = (void __iomem *)adev->rmmio + pcie_data * 4; + + /* read low 32 bits */ + writel(reg_addr, pcie_index_offset); + readl(pcie_index_offset); + r = readl(pcie_data_offset); + /* read high 32 bits */ + writel(reg_addr + 4, pcie_index_offset); + readl(pcie_index_offset); + r |= ((u64)readl(pcie_data_offset) << 32); + spin_unlock_irqrestore(&adev->pcie_idx_lock, flags); + + return r; +} + +/** + * amdgpu_device_indirect_wreg - write an indirect register address + * + * @adev: amdgpu_device pointer + * @pcie_index: mmio register offset + * @pcie_data: mmio register offset + * @reg_addr: indirect register offset + * @reg_data: indirect register data + * + */ +void amdgpu_device_indirect_wreg(struct amdgpu_device *adev, + u32 pcie_index, u32 pcie_data, + u32 reg_addr, u32 reg_data) +{ + unsigned long flags; + void __iomem *pcie_index_offset; + void __iomem *pcie_data_offset; + + spin_lock_irqsave(&adev->pcie_idx_lock, flags); + pcie_index_offset = (void __iomem *)adev->rmmio + pcie_index * 4; + pcie_data_offset = (void __iomem *)adev->rmmio + pcie_data * 4; + + writel(reg_addr, pcie_index_offset); + readl(pcie_index_offset); + writel(reg_data, pcie_data_offset); + readl(pcie_data_offset); + spin_unlock_irqrestore(&adev->pcie_idx_lock, flags); +} + +/** + * amdgpu_device_indirect_wreg64 - write a 64bits indirect register address + * + * @adev: amdgpu_device pointer + * @pcie_index: mmio register offset + * @pcie_data: mmio register offset + * @reg_addr: indirect register offset + * @reg_data: indirect register data + * + */ +void amdgpu_device_indirect_wreg64(struct amdgpu_device *adev, + u32 pcie_index, u32 pcie_data, + u32 reg_addr, u64 reg_data) +{ + unsigned long flags; + void __iomem *pcie_index_offset; + void __iomem *pcie_data_offset; + + spin_lock_irqsave(&adev->pcie_idx_lock, flags); + pcie_index_offset = (void __iomem *)adev->rmmio + pcie_index * 4; + pcie_data_offset = (void __iomem *)adev->rmmio + pcie_data * 4; + + /* write low 32 bits */ + writel(reg_addr, pcie_index_offset); + readl(pcie_index_offset); + writel((u32)(reg_data & 0xffffffffULL), pcie_data_offset); + readl(pcie_data_offset); + /* write high 32 bits */ + writel(reg_addr + 4, pcie_index_offset); + readl(pcie_index_offset); + writel((u32)(reg_data >> 32), pcie_data_offset); + readl(pcie_data_offset); + spin_unlock_irqrestore(&adev->pcie_idx_lock, flags); +} + +/** * amdgpu_invalid_rreg - dummy reg read function * * @adev: amdgpu device pointer @@ -1224,11 +1370,15 @@ static int amdgpu_device_check_arguments(struct amdgpu_device *adev) amdgpu_gmc_tmz_set(adev); - if (amdgpu_num_kcq > 8 || amdgpu_num_kcq < 0) { + if (amdgpu_num_kcq == -1) { + amdgpu_num_kcq = 8; + } else if (amdgpu_num_kcq > 8 || amdgpu_num_kcq < 0) { amdgpu_num_kcq = 8; dev_warn(adev->dev, "set kernel compute queue number to 8 due to invalid parameter provided by user\n"); } + amdgpu_gmc_noretry_set(adev); + return 0; } @@ -1256,7 +1406,7 @@ static void amdgpu_switcheroo_set_state(struct pci_dev *pdev, dev->switch_power_state = DRM_SWITCH_POWER_CHANGING; pci_set_power_state(dev->pdev, PCI_D0); - pci_restore_state(dev->pdev); + amdgpu_device_load_pci_state(dev->pdev); r = pci_enable_device(dev->pdev); if (r) DRM_WARN("pci_enable_device failed (%d)\n", r); @@ -1269,7 +1419,7 @@ static void amdgpu_switcheroo_set_state(struct pci_dev *pdev, drm_kms_helper_poll_disable(dev); dev->switch_power_state = DRM_SWITCH_POWER_CHANGING; amdgpu_device_suspend(dev, true); - pci_save_state(dev->pdev); + amdgpu_device_cache_pci_state(dev->pdev); /* Shut down the device */ pci_disable_device(dev->pdev); pci_set_power_state(dev->pdev, PCI_D3cold); @@ -1631,6 +1781,8 @@ static int amdgpu_device_parse_gpu_info_fw(struct amdgpu_device *adev) case CHIP_CARRIZO: case CHIP_STONEY: case CHIP_VEGA20: + case CHIP_SIENNA_CICHLID: + case CHIP_NAVY_FLOUNDER: default: return 0; case CHIP_VEGA10: @@ -1662,12 +1814,6 @@ static int amdgpu_device_parse_gpu_info_fw(struct amdgpu_device *adev) case CHIP_NAVI12: chip_name = "navi12"; break; - case CHIP_SIENNA_CICHLID: - chip_name = "sienna_cichlid"; - break; - case CHIP_NAVY_FLOUNDER: - chip_name = "navy_flounder"; - break; } snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_gpu_info.bin", chip_name); @@ -2999,6 +3145,7 @@ static const struct attribute *amdgpu_dev_attributes[] = { NULL }; + /** * amdgpu_device_init - initialize the driver * @@ -3170,13 +3317,13 @@ int amdgpu_device_init(struct amdgpu_device *adev, r = amdgpu_device_get_job_timeout_settings(adev); if (r) { dev_err(adev->dev, "invalid lockup_timeout parameter syntax\n"); - return r; + goto failed_unmap; } /* early init functions */ r = amdgpu_device_ip_early_init(adev); if (r) - return r; + goto failed_unmap; /* doorbell bar mapping and doorbell index init*/ amdgpu_device_doorbell_init(adev); @@ -3217,6 +3364,8 @@ int amdgpu_device_init(struct amdgpu_device *adev, } } + pci_enable_pcie_error_reporting(adev->ddev.pdev); + /* Post card if necessary */ if (amdgpu_device_need_post(adev)) { if (!adev->bios) { @@ -3359,16 +3508,18 @@ fence_driver_init: flush_delayed_work(&adev->delayed_init_work); r = sysfs_create_files(&adev->dev->kobj, amdgpu_dev_attributes); - if (r) { + if (r) dev_err(adev->dev, "Could not create amdgpu device attr\n"); - return r; - } if (IS_ENABLED(CONFIG_PERF_EVENTS)) r = amdgpu_pmu_init(adev); if (r) dev_err(adev->dev, "amdgpu_pmu_init failed\n"); + /* Have stored pci confspace at hand for restore in sudden PCI error */ + if (amdgpu_device_cache_pci_state(adev->pdev)) + pci_restore_state(pdev); + return 0; failed: @@ -3376,6 +3527,10 @@ failed: if (boco) vga_switcheroo_fini_domain_pm_ops(adev->dev); +failed_unmap: + iounmap(adev->rmmio); + adev->rmmio = NULL; + return r; } @@ -3393,11 +3548,15 @@ void amdgpu_device_fini(struct amdgpu_device *adev) flush_delayed_work(&adev->delayed_init_work); adev->shutdown = true; + kfree(adev->pci_state); + /* make sure IB test finished before entering exclusive mode * to avoid preemption on IB test * */ - if (amdgpu_sriov_vf(adev)) + if (amdgpu_sriov_vf(adev)) { amdgpu_virt_request_full_gpu(adev, false); + amdgpu_virt_fini_data_exchange(adev); + } /* disable all interrupts */ amdgpu_irq_disable_all(adev); @@ -4031,6 +4190,11 @@ static int amdgpu_device_pre_asic_reset(struct amdgpu_device *adev, amdgpu_debugfs_wait_dump(adev); + if (amdgpu_sriov_vf(adev)) { + /* stop the data exchange thread */ + amdgpu_virt_fini_data_exchange(adev); + } + /* block all schedulers and reset given job's ring */ for (i = 0; i < AMDGPU_MAX_RINGS; ++i) { struct amdgpu_ring *ring = adev->rings[i]; @@ -4072,7 +4236,8 @@ static int amdgpu_device_pre_asic_reset(struct amdgpu_device *adev, static int amdgpu_do_asic_reset(struct amdgpu_hive_info *hive, struct list_head *device_list_handle, - bool *need_full_reset_arg) + bool *need_full_reset_arg, + bool skip_hw_reset) { struct amdgpu_device *tmp_adev = NULL; bool need_full_reset = *need_full_reset_arg, vram_lost = false; @@ -4082,7 +4247,7 @@ static int amdgpu_do_asic_reset(struct amdgpu_hive_info *hive, * ASIC reset has to be done on all HGMI hive nodes ASAP * to allow proper links negotiation in FW (within 1 sec) */ - if (need_full_reset) { + if (!skip_hw_reset && need_full_reset) { list_for_each_entry(tmp_adev, device_list_handle, gmc.xgmi.head) { /* For XGMI run all resets in parallel to speed up the process */ if (tmp_adev->gmc.xgmi.num_physical_nodes > 1) { @@ -4460,7 +4625,7 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev, retry: /* Rest of adevs pre asic reset from XGMI hive. */ list_for_each_entry(tmp_adev, device_list_handle, gmc.xgmi.head) { r = amdgpu_device_pre_asic_reset(tmp_adev, - NULL, + (tmp_adev == adev) ? job : NULL, &need_full_reset); /*TODO Should we stop ?*/ if (r) { @@ -4477,7 +4642,7 @@ retry: /* Rest of adevs pre asic reset from XGMI hive. */ if (r) adev->asic_reset_res = r; } else { - r = amdgpu_do_asic_reset(hive, device_list_handle, &need_full_reset); + r = amdgpu_do_asic_reset(hive, device_list_handle, &need_full_reset, false); if (r && r == -EAGAIN) goto retry; } @@ -4705,3 +4870,235 @@ int amdgpu_device_baco_exit(struct drm_device *dev) return 0; } + +static void amdgpu_cancel_all_tdr(struct amdgpu_device *adev) +{ + int i; + + for (i = 0; i < AMDGPU_MAX_RINGS; ++i) { + struct amdgpu_ring *ring = adev->rings[i]; + + if (!ring || !ring->sched.thread) + continue; + + cancel_delayed_work_sync(&ring->sched.work_tdr); + } +} + +/** + * amdgpu_pci_error_detected - Called when a PCI error is detected. + * @pdev: PCI device struct + * @state: PCI channel state + * + * Description: Called when a PCI error is detected. + * + * Return: PCI_ERS_RESULT_NEED_RESET or PCI_ERS_RESULT_DISCONNECT. + */ +pci_ers_result_t amdgpu_pci_error_detected(struct pci_dev *pdev, pci_channel_state_t state) +{ + struct drm_device *dev = pci_get_drvdata(pdev); + struct amdgpu_device *adev = drm_to_adev(dev); + int i; + + DRM_INFO("PCI error: detected callback, state(%d)!!\n", state); + + if (adev->gmc.xgmi.num_physical_nodes > 1) { + DRM_WARN("No support for XGMI hive yet..."); + return PCI_ERS_RESULT_DISCONNECT; + } + + switch (state) { + case pci_channel_io_normal: + return PCI_ERS_RESULT_CAN_RECOVER; + /* Fatal error, prepare for slot reset */ + case pci_channel_io_frozen: + /* + * Cancel and wait for all TDRs in progress if failing to + * set adev->in_gpu_reset in amdgpu_device_lock_adev + * + * Locking adev->reset_sem will prevent any external access + * to GPU during PCI error recovery + */ + while (!amdgpu_device_lock_adev(adev, NULL)) + amdgpu_cancel_all_tdr(adev); + + /* + * Block any work scheduling as we do for regular GPU reset + * for the duration of the recovery + */ + for (i = 0; i < AMDGPU_MAX_RINGS; ++i) { + struct amdgpu_ring *ring = adev->rings[i]; + + if (!ring || !ring->sched.thread) + continue; + + drm_sched_stop(&ring->sched, NULL); + } + return PCI_ERS_RESULT_NEED_RESET; + case pci_channel_io_perm_failure: + /* Permanent error, prepare for device removal */ + return PCI_ERS_RESULT_DISCONNECT; + } + + return PCI_ERS_RESULT_NEED_RESET; +} + +/** + * amdgpu_pci_mmio_enabled - Enable MMIO and dump debug registers + * @pdev: pointer to PCI device + */ +pci_ers_result_t amdgpu_pci_mmio_enabled(struct pci_dev *pdev) +{ + + DRM_INFO("PCI error: mmio enabled callback!!\n"); + + /* TODO - dump whatever for debugging purposes */ + + /* This called only if amdgpu_pci_error_detected returns + * PCI_ERS_RESULT_CAN_RECOVER. Read/write to the device still + * works, no need to reset slot. + */ + + return PCI_ERS_RESULT_RECOVERED; +} + +/** + * amdgpu_pci_slot_reset - Called when PCI slot has been reset. + * @pdev: PCI device struct + * + * Description: This routine is called by the pci error recovery + * code after the PCI slot has been reset, just before we + * should resume normal operations. + */ +pci_ers_result_t amdgpu_pci_slot_reset(struct pci_dev *pdev) +{ + struct drm_device *dev = pci_get_drvdata(pdev); + struct amdgpu_device *adev = drm_to_adev(dev); + int r, i; + bool need_full_reset = true; + u32 memsize; + struct list_head device_list; + + DRM_INFO("PCI error: slot reset callback!!\n"); + + INIT_LIST_HEAD(&device_list); + list_add_tail(&adev->gmc.xgmi.head, &device_list); + + /* wait for asic to come out of reset */ + msleep(500); + + /* Restore PCI confspace */ + amdgpu_device_load_pci_state(pdev); + + /* confirm ASIC came out of reset */ + for (i = 0; i < adev->usec_timeout; i++) { + memsize = amdgpu_asic_get_config_memsize(adev); + + if (memsize != 0xffffffff) + break; + udelay(1); + } + if (memsize == 0xffffffff) { + r = -ETIME; + goto out; + } + + adev->in_pci_err_recovery = true; + r = amdgpu_device_pre_asic_reset(adev, NULL, &need_full_reset); + adev->in_pci_err_recovery = false; + if (r) + goto out; + + r = amdgpu_do_asic_reset(NULL, &device_list, &need_full_reset, true); + +out: + if (!r) { + if (amdgpu_device_cache_pci_state(adev->pdev)) + pci_restore_state(adev->pdev); + + DRM_INFO("PCIe error recovery succeeded\n"); + } else { + DRM_ERROR("PCIe error recovery failed, err:%d", r); + amdgpu_device_unlock_adev(adev); + } + + return r ? PCI_ERS_RESULT_DISCONNECT : PCI_ERS_RESULT_RECOVERED; +} + +/** + * amdgpu_pci_resume() - resume normal ops after PCI reset + * @pdev: pointer to PCI device + * + * Called when the error recovery driver tells us that its + * OK to resume normal operation. Use completion to allow + * halted scsi ops to resume. + */ +void amdgpu_pci_resume(struct pci_dev *pdev) +{ + struct drm_device *dev = pci_get_drvdata(pdev); + struct amdgpu_device *adev = drm_to_adev(dev); + int i; + + + DRM_INFO("PCI error: resume callback!!\n"); + + for (i = 0; i < AMDGPU_MAX_RINGS; ++i) { + struct amdgpu_ring *ring = adev->rings[i]; + + if (!ring || !ring->sched.thread) + continue; + + + drm_sched_resubmit_jobs(&ring->sched); + drm_sched_start(&ring->sched, true); + } + + amdgpu_device_unlock_adev(adev); +} + +bool amdgpu_device_cache_pci_state(struct pci_dev *pdev) +{ + struct drm_device *dev = pci_get_drvdata(pdev); + struct amdgpu_device *adev = drm_to_adev(dev); + int r; + + r = pci_save_state(pdev); + if (!r) { + kfree(adev->pci_state); + + adev->pci_state = pci_store_saved_state(pdev); + + if (!adev->pci_state) { + DRM_ERROR("Failed to store PCI saved state"); + return false; + } + } else { + DRM_WARN("Failed to save PCI state, err:%d\n", r); + return false; + } + + return true; +} + +bool amdgpu_device_load_pci_state(struct pci_dev *pdev) +{ + struct drm_device *dev = pci_get_drvdata(pdev); + struct amdgpu_device *adev = drm_to_adev(dev); + int r; + + if (!adev->pci_state) + return false; + + r = pci_load_saved_state(pdev, adev->pci_state); + + if (!r) { + pci_restore_state(pdev); + } else { + DRM_WARN("Failed to load PCI state, err:%d\n", r); + return false; + } + + return true; +} + + diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_df.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_df.h index 61a26c15c8dd..373cdebe0e2f 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_df.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_df.h @@ -44,9 +44,9 @@ struct amdgpu_df_funcs { void (*enable_ecc_force_par_wr_rmw)(struct amdgpu_device *adev, bool enable); int (*pmc_start)(struct amdgpu_device *adev, uint64_t config, - int is_enable); + int is_add); int (*pmc_stop)(struct amdgpu_device *adev, uint64_t config, - int is_disable); + int is_remove); void (*pmc_get_count)(struct amdgpu_device *adev, uint64_t config, uint64_t *count); uint64_t (*get_fica)(struct amdgpu_device *adev, uint32_t ficaa_val); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c index 4cba095b6c44..b25faaee6f0e 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c @@ -293,7 +293,7 @@ int amdgpu_display_crtc_set_config(struct drm_mode_set *set, take the current one */ if (active && !adev->have_disp_power_ref) { adev->have_disp_power_ref = true; - goto out; + return ret; } /* if we have no active crtcs, then drop the power ref we got before */ diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index f359ffb77aa5..8b30915aa972 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -32,7 +32,6 @@ #include <drm/drm_pciids.h> #include <linux/console.h> #include <linux/module.h> -#include <linux/pci.h> #include <linux/pm_runtime.h> #include <linux/vga_switcheroo.h> #include <drm/drm_probe_helper.h> @@ -148,7 +147,7 @@ int amdgpu_async_gfx_ring = 1; int amdgpu_mcbp = 0; int amdgpu_discovery = -1; int amdgpu_mes = 0; -int amdgpu_noretry; +int amdgpu_noretry = -1; int amdgpu_force_asic_type = -1; int amdgpu_tmz = 0; int amdgpu_reset_method = -1; /* auto */ @@ -597,8 +596,13 @@ MODULE_PARM_DESC(mes, "Enable Micro Engine Scheduler (0 = disabled (default), 1 = enabled)"); module_param_named(mes, amdgpu_mes, int, 0444); +/** + * DOC: noretry (int) + * Disable retry faults in the GPU memory controller. + * (0 = retry enabled, 1 = retry disabled, -1 auto (default)) + */ MODULE_PARM_DESC(noretry, - "Disable retry faults (0 = retry enabled (default), 1 = retry disabled)"); + "Disable retry faults (0 = retry enabled, 1 = retry disabled, -1 auto (default))"); module_param_named(noretry, amdgpu_noretry, int, 0644); /** @@ -1062,6 +1066,7 @@ static const struct pci_device_id pciidlist[] = { {0x1002, 0x7319, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI10}, {0x1002, 0x731A, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI10}, {0x1002, 0x731B, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI10}, + {0x1002, 0x731E, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI10}, {0x1002, 0x731F, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI10}, /* Navi14 */ {0x1002, 0x7340, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI14}, @@ -1073,8 +1078,16 @@ static const struct pci_device_id pciidlist[] = { {0x1002, 0x1636, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RENOIR|AMD_IS_APU}, /* Navi12 */ - {0x1002, 0x7360, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI12|AMD_EXP_HW_SUPPORT}, - {0x1002, 0x7362, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI12|AMD_EXP_HW_SUPPORT}, + {0x1002, 0x7360, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI12}, + {0x1002, 0x7362, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI12}, + + /* Sienna_Cichlid */ + {0x1002, 0x73A0, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SIENNA_CICHLID}, + {0x1002, 0x73A2, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SIENNA_CICHLID}, + {0x1002, 0x73A3, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SIENNA_CICHLID}, + {0x1002, 0x73AB, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SIENNA_CICHLID}, + {0x1002, 0x73AE, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SIENNA_CICHLID}, + {0x1002, 0x73BF, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SIENNA_CICHLID}, {0, 0, 0} }; @@ -1102,6 +1115,16 @@ static int amdgpu_pci_probe(struct pci_dev *pdev, return -ENODEV; } + /* Due to hardware bugs, S/G Display on raven requires a 1:1 IOMMU mapping, + * however, SME requires an indirect IOMMU mapping because the encryption + * bit is beyond the DMA mask of the chip. + */ + if (mem_encrypt_active() && ((flags & AMD_ASIC_MASK) == CHIP_RAVEN)) { + dev_info(&pdev->dev, + "SME is not compatible with RAVEN\n"); + return -ENOTSUPP; + } + #ifdef CONFIG_DRM_AMDGPU_SI if (!amdgpu_si_support) { switch (flags & AMD_ASIC_MASK) { @@ -1308,7 +1331,7 @@ static int amdgpu_pmops_runtime_suspend(struct device *dev) if (amdgpu_is_atpx_hybrid()) { pci_ignore_hotplug(pdev); } else { - pci_save_state(pdev); + amdgpu_device_cache_pci_state(pdev); pci_disable_device(pdev); pci_ignore_hotplug(pdev); pci_set_power_state(pdev, PCI_D3cold); @@ -1341,7 +1364,7 @@ static int amdgpu_pmops_runtime_resume(struct device *dev) pci_set_master(pdev); } else { pci_set_power_state(pdev, PCI_D0); - pci_restore_state(pdev); + amdgpu_device_load_pci_state(pdev); ret = pci_enable_device(pdev); if (ret) return ret; @@ -1514,6 +1537,13 @@ static struct drm_driver kms_driver = { .patchlevel = KMS_DRIVER_PATCHLEVEL, }; +static struct pci_error_handlers amdgpu_pci_err_handler = { + .error_detected = amdgpu_pci_error_detected, + .mmio_enabled = amdgpu_pci_mmio_enabled, + .slot_reset = amdgpu_pci_slot_reset, + .resume = amdgpu_pci_resume, +}; + static struct pci_driver amdgpu_kms_pci_driver = { .name = DRIVER_NAME, .id_table = pciidlist, @@ -1521,6 +1551,7 @@ static struct pci_driver amdgpu_kms_pci_driver = { .remove = amdgpu_pci_remove, .shutdown = amdgpu_pci_shutdown, .driver.pm = &amdgpu_pm_ops, + .err_handler = &amdgpu_pci_err_handler, }; static int __init amdgpu_init(void) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fru_eeprom.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fru_eeprom.c index e811fecc540f..8f4a8f8d8146 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fru_eeprom.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fru_eeprom.c @@ -34,18 +34,31 @@ static bool is_fru_eeprom_supported(struct amdgpu_device *adev) { - /* TODO: Gaming SKUs don't have the FRU EEPROM. - * Use this hack to address hangs on modprobe on gaming SKUs - * until a proper solution can be implemented by only supporting - * the explicit chip IDs for VG20 Server cards - * - * TODO: Add list of supported Arcturus DIDs once confirmed + /* Only server cards have the FRU EEPROM + * TODO: See if we can figure this out dynamically instead of + * having to parse VBIOS versions. */ - if ((adev->asic_type == CHIP_VEGA20 && adev->pdev->device == 0x66a0) || - (adev->asic_type == CHIP_VEGA20 && adev->pdev->device == 0x66a1) || - (adev->asic_type == CHIP_VEGA20 && adev->pdev->device == 0x66a4)) - return true; - return false; + struct atom_context *atom_ctx = adev->mode_info.atom_context; + + /* VBIOS is of the format ###-DXXXYY-##. For SKU identification, + * we can use just the "DXXX" portion. If there were more models, we + * could convert the 3 characters to a hex integer and use a switch + * for ease/speed/readability. For now, 2 string comparisons are + * reasonable and not too expensive + */ + switch (adev->asic_type) { + case CHIP_VEGA20: + /* D161 and D163 are the VG20 server SKUs */ + if (strnstr(atom_ctx->vbios_version, "D161", + sizeof(atom_ctx->vbios_version)) || + strnstr(atom_ctx->vbios_version, "D163", + sizeof(atom_ctx->vbios_version))) + return true; + else + return false; + default: + return false; + } } static int amdgpu_fru_read_eeprom(struct amdgpu_device *adev, uint32_t addrptr, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fru_eeprom.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_fru_eeprom.h index f29a8611d69b..1308d976d60e 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fru_eeprom.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fru_eeprom.h @@ -26,4 +26,4 @@ int amdgpu_fru_get_product_info(struct amdgpu_device *adev); -#endif // __AMDGPU_PRODINFO_H__ +#endif // __AMDGPU_FRU_EEPROM_H__ diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c index be08a63ef58c..8ea6fc745769 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c @@ -609,6 +609,7 @@ int amdgpu_gem_va_ioctl(struct drm_device *dev, void *data, struct ww_acquire_ctx ticket; struct list_head list, duplicates; uint64_t va_flags; + uint64_t vm_size; int r = 0; if (args->va_address < AMDGPU_VA_RESERVED_SIZE) { @@ -629,6 +630,15 @@ int amdgpu_gem_va_ioctl(struct drm_device *dev, void *data, args->va_address &= AMDGPU_GMC_HOLE_MASK; + vm_size = adev->vm_manager.max_pfn * AMDGPU_GPU_PAGE_SIZE; + vm_size -= AMDGPU_VA_RESERVED_SIZE; + if (args->va_address + args->map_size > vm_size) { + dev_dbg(&dev->pdev->dev, + "va_address 0x%llx is in top reserved area 0x%llx\n", + args->va_address + args->map_size, vm_size); + return -EINVAL; + } + if ((args->flags & ~valid_flags) && (args->flags & ~prt_flags)) { dev_dbg(&dev->pdev->dev, "invalid flags combination 0x%08X\n", args->flags); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c index d6981425ec51..8c9bacfdbc30 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c @@ -693,6 +693,9 @@ uint32_t amdgpu_kiq_rreg(struct amdgpu_device *adev, uint32_t reg) struct amdgpu_kiq *kiq = &adev->gfx.kiq; struct amdgpu_ring *ring = &kiq->ring; + if (adev->in_pci_err_recovery) + return 0; + BUG_ON(!ring->funcs->emit_rreg); spin_lock_irqsave(&kiq->ring_lock, flags); @@ -757,6 +760,9 @@ void amdgpu_kiq_wreg(struct amdgpu_device *adev, uint32_t reg, uint32_t v) BUG_ON(!ring->funcs->emit_wreg); + if (adev->in_pci_err_recovery) + return; + spin_lock_irqsave(&kiq->ring_lock, flags); amdgpu_ring_alloc(ring, 32); amdgpu_ring_emit_wreg(ring, reg, v); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h index a611e78dd4ba..258498cbf1eb 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h @@ -217,6 +217,7 @@ struct amdgpu_gfx_funcs { int (*query_ras_error_count) (struct amdgpu_device *adev, void *ras_error_status); void (*reset_ras_error_count) (struct amdgpu_device *adev); void (*init_spm_golden)(struct amdgpu_device *adev); + void (*query_ras_error_status) (struct amdgpu_device *adev); }; struct sq_work { diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfxhub.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfxhub.h new file mode 100644 index 000000000000..66ebc2e3b2ad --- /dev/null +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfxhub.h @@ -0,0 +1,43 @@ +/* + * Copyright 2020 Advanced Micro Devices, Inc. + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of this software and associated documentation files (the "Software"), + * to deal in the Software without restriction, including without limitation + * the rights to use, copy, modify, merge, publish, distribute, sublicense, + * and/or sell copies of the Software, and to permit persons to whom the + * Software is furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR + * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, + * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR + * OTHER DEALINGS IN THE SOFTWARE. + * + */ +#ifndef __AMDGPU_GFXHUB_H__ +#define __AMDGPU_GFXHUB_H__ + +struct amdgpu_gfxhub_funcs { + u64 (*get_fb_location)(struct amdgpu_device *adev); + u64 (*get_mc_fb_offset)(struct amdgpu_device *adev); + void (*setup_vm_pt_regs)(struct amdgpu_device *adev, uint32_t vmid, + uint64_t page_table_base); + int (*gart_enable)(struct amdgpu_device *adev); + + void (*gart_disable)(struct amdgpu_device *adev); + void (*set_fault_enable_default)(struct amdgpu_device *adev, bool value); + void (*init)(struct amdgpu_device *adev); + int (*get_xgmi_info)(struct amdgpu_device *adev); +}; + +struct amdgpu_gfxhub { + const struct amdgpu_gfxhub_funcs *funcs; +}; + +#endif diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c index 0e35023b5703..cc86f431a3d4 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c @@ -409,6 +409,44 @@ void amdgpu_gmc_tmz_set(struct amdgpu_device *adev) } } +/** + * amdgpu_noretry_set -- set per asic noretry defaults + * @adev: amdgpu_device pointer + * + * Set a per asic default for the no-retry parameter. + * + */ +void amdgpu_gmc_noretry_set(struct amdgpu_device *adev) +{ + struct amdgpu_gmc *gmc = &adev->gmc; + + switch (adev->asic_type) { + case CHIP_RAVEN: + /* Raven currently has issues with noretry + * regardless of what we decide for other + * asics, we should leave raven with + * noretry = 0 until we root cause the + * issues. + */ + if (amdgpu_noretry == -1) + gmc->noretry = 0; + else + gmc->noretry = amdgpu_noretry; + break; + default: + /* default this to 0 for now, but we may want + * to change this in the future for certain + * GPUs as it can increase performance in + * certain cases. + */ + if (amdgpu_noretry == -1) + gmc->noretry = 0; + else + gmc->noretry = amdgpu_noretry; + break; + } +} + void amdgpu_gmc_set_vm_fault_masks(struct amdgpu_device *adev, int hub_type, bool enable) { diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h index d61bbde4c7d2..aa0c83776ce0 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h @@ -239,6 +239,7 @@ struct amdgpu_gmc { struct amdgpu_xgmi xgmi; struct amdgpu_irq_src ecc_irq; + int noretry; }; #define amdgpu_gmc_flush_gpu_tlb(adev, vmid, vmhub, type) ((adev)->gmc.gmc_funcs->flush_gpu_tlb((adev), (vmid), (vmhub), (type))) @@ -300,6 +301,7 @@ void amdgpu_gmc_ras_fini(struct amdgpu_device *adev); int amdgpu_gmc_allocate_vm_inv_eng(struct amdgpu_device *adev); extern void amdgpu_gmc_tmz_set(struct amdgpu_device *adev); +extern void amdgpu_gmc_noretry_set(struct amdgpu_device *adev); extern void amdgpu_gmc_set_vm_fault_masks(struct amdgpu_device *adev, int hub_type, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c index 7521f4ab55de..6e9a9e5dbea0 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c @@ -43,7 +43,7 @@ static DEFINE_IDA(amdgpu_pasid_ida); /* Helper to free pasid from a fence callback */ struct amdgpu_pasid_cb { struct dma_fence_cb cb; - unsigned int pasid; + u32 pasid; }; /** @@ -79,7 +79,7 @@ int amdgpu_pasid_alloc(unsigned int bits) * amdgpu_pasid_free - Free a PASID * @pasid: PASID to free */ -void amdgpu_pasid_free(unsigned int pasid) +void amdgpu_pasid_free(u32 pasid) { trace_amdgpu_pasid_freed(pasid); ida_simple_remove(&amdgpu_pasid_ida, pasid); @@ -105,7 +105,7 @@ static void amdgpu_pasid_free_cb(struct dma_fence *fence, * Free the pasid only after all the fences in resv are signaled. */ void amdgpu_pasid_free_delayed(struct dma_resv *resv, - unsigned int pasid) + u32 pasid) { struct dma_fence *fence, **fences; struct amdgpu_pasid_cb *cb; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.h index 8e58325bbca2..0c3b4fa1f936 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.h @@ -71,9 +71,9 @@ struct amdgpu_vmid_mgr { }; int amdgpu_pasid_alloc(unsigned int bits); -void amdgpu_pasid_free(unsigned int pasid); +void amdgpu_pasid_free(u32 pasid); void amdgpu_pasid_free_delayed(struct dma_resv *resv, - unsigned int pasid); + u32 pasid); bool amdgpu_vmid_had_gpu_reset(struct amdgpu_device *adev, struct amdgpu_vmid *id); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c index 456a4a93b337..efda38349a03 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c @@ -177,7 +177,7 @@ int amdgpu_driver_load_kms(struct amdgpu_device *adev, unsigned long flags) break; case CHIP_VEGA10: /* turn runpm on if noretry=0 */ - if (!amdgpu_noretry) + if (!adev->gmc.noretry) adev->runpm = true; break; default: @@ -282,14 +282,25 @@ static int amdgpu_firmware_info(struct drm_amdgpu_info_firmware *fw_info, fw_info->feature = 0; break; case AMDGPU_INFO_FW_TA: - if (query_fw->index > 1) - return -EINVAL; - if (query_fw->index == 0) { + switch (query_fw->index) { + case 0: fw_info->ver = adev->psp.ta_fw_version; fw_info->feature = adev->psp.ta_xgmi_ucode_version; - } else { + break; + case 1: fw_info->ver = adev->psp.ta_fw_version; fw_info->feature = adev->psp.ta_ras_ucode_version; + break; + case 2: + fw_info->ver = adev->psp.ta_fw_version; + fw_info->feature = adev->psp.ta_hdcp_ucode_version; + break; + case 3: + fw_info->ver = adev->psp.ta_fw_version; + fw_info->feature = adev->psp.ta_dtm_ucode_version; + break; + default: + return -EINVAL; } break; case AMDGPU_INFO_FW_SDMA: @@ -1080,7 +1091,7 @@ void amdgpu_driver_postclose_kms(struct drm_device *dev, struct amdgpu_fpriv *fpriv = file_priv->driver_priv; struct amdgpu_bo_list *list; struct amdgpu_bo *pd; - unsigned int pasid; + u32 pasid; int handle; if (!fpriv) @@ -1385,13 +1396,31 @@ static int amdgpu_debugfs_firmware_info(struct seq_file *m, void *data) fw_info.feature, fw_info.ver); query_fw.fw_type = AMDGPU_INFO_FW_TA; - for (i = 0; i < 2; i++) { + for (i = 0; i < 4; i++) { query_fw.index = i; ret = amdgpu_firmware_info(&fw_info, &query_fw, adev); if (ret) continue; - seq_printf(m, "TA %s feature version: %u, firmware version: 0x%08x\n", - i ? "RAS" : "XGMI", fw_info.feature, fw_info.ver); + switch (query_fw.index) { + case 0: + seq_printf(m, "TA %s feature version: 0x%08x, firmware version: 0x%08x\n", + "RAS", fw_info.feature, fw_info.ver); + break; + case 1: + seq_printf(m, "TA %s feature version: 0x%08x, firmware version: 0x%08x\n", + "XGMI", fw_info.feature, fw_info.ver); + break; + case 2: + seq_printf(m, "TA %s feature version: 0x%08x, firmware version: 0x%08x\n", + "HDCP", fw_info.feature, fw_info.ver); + break; + case 3: + seq_printf(m, "TA %s feature version: 0x%08x, firmware version: 0x%08x\n", + "DTM", fw_info.feature, fw_info.ver); + break; + default: + return -EINVAL; + } } /* SMC */ diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mmhub.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_mmhub.h index 0c43d7fe893c..1ae9bdae7311 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mmhub.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mmhub.h @@ -40,6 +40,7 @@ struct amdgpu_mmhub_funcs { uint64_t page_table_base); void (*update_power_gating)(struct amdgpu_device *adev, bool enable); + void (*query_ras_error_status)(struct amdgpu_device *adev); }; struct amdgpu_mmhub { diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mode.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_mode.h index 04a430e0e2e1..a04decb934b0 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mode.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mode.h @@ -46,6 +46,7 @@ #include <drm/drm_dp_mst_helper.h> #include "modules/inc/mod_freesync.h" +#include "amdgpu_dm_irq_params.h" struct amdgpu_bo; struct amdgpu_device; @@ -404,7 +405,8 @@ struct amdgpu_crtc { struct amdgpu_flip_work *pflip_works; enum amdgpu_flip_status pflip_status; int deferred_flip_completion; - u32 last_flip_vblank; + /* parameters access from DM IRQ handler */ + struct dm_irq_params dm_irq_params; /* pll sharing */ struct amdgpu_atom_ss ss; bool ss_enabled; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c index d6c38e24f130..96a9699f87ba 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c @@ -161,10 +161,12 @@ static int psp_sw_init(void *handle) struct psp_context *psp = &adev->psp; int ret; - ret = psp_init_microcode(psp); - if (ret) { - DRM_ERROR("Failed to load psp firmware!\n"); - return ret; + if (!amdgpu_sriov_vf(adev)) { + ret = psp_init_microcode(psp); + if (ret) { + DRM_ERROR("Failed to load psp firmware!\n"); + return ret; + } } ret = psp_memory_training_init(psp); @@ -178,7 +180,7 @@ static int psp_sw_init(void *handle) return ret; } - if (adev->asic_type == CHIP_NAVI10) { + if (adev->asic_type == CHIP_NAVI10 || adev->asic_type == CHIP_SIENNA_CICHLID) { ret= psp_sysfs_init(adev); if (ret) { return ret; @@ -206,7 +208,8 @@ static int psp_sw_fini(void *handle) adev->psp.ta_fw = NULL; } - if (adev->asic_type == CHIP_NAVI10) + if (adev->asic_type == CHIP_NAVI10 || + adev->asic_type == CHIP_SIENNA_CICHLID) psp_sysfs_fini(adev); return 0; @@ -219,6 +222,9 @@ int psp_wait_for(struct psp_context *psp, uint32_t reg_index, int i; struct amdgpu_device *adev = psp->adev; + if (psp->adev->in_pci_err_recovery) + return 0; + for (i = 0; i < adev->usec_timeout; i++) { val = RREG32(reg_index); if (check_changed) { @@ -245,6 +251,9 @@ psp_cmd_submit_buf(struct psp_context *psp, bool ras_intr = false; bool skip_unsupport = false; + if (psp->adev->in_pci_err_recovery) + return 0; + mutex_lock(&psp->mutex); memset(psp->cmd_buf_mem, 0, PSP_CMD_BUFFER_SIZE); @@ -929,6 +938,7 @@ static int psp_ras_load(struct psp_context *psp) { int ret; struct psp_gfx_cmd_resp *cmd; + struct ta_ras_shared_memory *ras_cmd; /* * TODO: bypass the loading in sriov for now @@ -952,11 +962,20 @@ static int psp_ras_load(struct psp_context *psp) ret = psp_cmd_submit_buf(psp, NULL, cmd, psp->fence_buf_mc_addr); + ras_cmd = (struct ta_ras_shared_memory*)psp->ras.ras_shared_buf; + if (!ret) { - psp->ras.ras_initialized = true; psp->ras.session_id = cmd->resp.session_id; + + if (!ras_cmd->ras_status) + psp->ras.ras_initialized = true; + else + dev_warn(psp->adev->dev, "RAS Init Status: 0x%X\n", ras_cmd->ras_status); } + if (ret || ras_cmd->ras_status) + amdgpu_ras_fini(psp->adev); + kfree(cmd); return ret; @@ -1732,6 +1751,12 @@ static int psp_get_fw_type(struct amdgpu_firmware_info *ucode, case AMDGPU_UCODE_ID_RLC_RESTORE_LIST_SRM_MEM: *type = GFX_FW_TYPE_RLC_RESTORE_LIST_SRM_MEM; break; + case AMDGPU_UCODE_ID_RLC_IRAM: + *type = GFX_FW_TYPE_RLC_IRAM; + break; + case AMDGPU_UCODE_ID_RLC_DRAM: + *type = GFX_FW_TYPE_RLC_DRAM_BOOT; + break; case AMDGPU_UCODE_ID_SMC: *type = GFX_FW_TYPE_SMU; break; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c index e5ea14774c0c..4e36551ab50b 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c @@ -1027,58 +1027,6 @@ static ssize_t amdgpu_ras_sysfs_features_read(struct device *dev, return scnprintf(buf, PAGE_SIZE, "feature mask: 0x%x\n", con->features); } -static void amdgpu_ras_sysfs_add_bad_page_node(struct amdgpu_device *adev) -{ - struct amdgpu_ras *con = amdgpu_ras_get_context(adev); - struct attribute_group group; - struct bin_attribute *bin_attrs[] = { - &con->badpages_attr, - NULL, - }; - - con->badpages_attr = (struct bin_attribute) { - .attr = { - .name = "gpu_vram_bad_pages", - .mode = S_IRUGO, - }, - .size = 0, - .private = NULL, - .read = amdgpu_ras_sysfs_badpages_read, - }; - - group.name = RAS_FS_NAME; - group.bin_attrs = bin_attrs; - - sysfs_bin_attr_init(bin_attrs[0]); - - sysfs_update_group(&adev->dev->kobj, &group); -} - -static int amdgpu_ras_sysfs_create_feature_node(struct amdgpu_device *adev) -{ - struct amdgpu_ras *con = amdgpu_ras_get_context(adev); - struct attribute *attrs[] = { - &con->features_attr.attr, - NULL - }; - struct attribute_group group = { - .name = RAS_FS_NAME, - .attrs = attrs, - }; - - con->features_attr = (struct device_attribute) { - .attr = { - .name = "features", - .mode = S_IRUGO, - }, - .show = amdgpu_ras_sysfs_features_read, - }; - - sysfs_attr_init(attrs[0]); - - return sysfs_create_group(&adev->dev->kobj, &group); -} - static void amdgpu_ras_sysfs_remove_bad_page_node(struct amdgpu_device *adev) { struct amdgpu_ras *con = amdgpu_ras_get_context(adev); @@ -1300,13 +1248,43 @@ static void amdgpu_ras_debugfs_remove_all(struct amdgpu_device *adev) /* debugfs end */ /* ras fs */ - +static BIN_ATTR(gpu_vram_bad_pages, S_IRUGO, + amdgpu_ras_sysfs_badpages_read, NULL, 0); +static DEVICE_ATTR(features, S_IRUGO, + amdgpu_ras_sysfs_features_read, NULL); static int amdgpu_ras_fs_init(struct amdgpu_device *adev) { - amdgpu_ras_sysfs_create_feature_node(adev); + struct amdgpu_ras *con = amdgpu_ras_get_context(adev); + struct attribute_group group = { + .name = RAS_FS_NAME, + }; + struct attribute *attrs[] = { + &con->features_attr.attr, + NULL + }; + struct bin_attribute *bin_attrs[] = { + NULL, + NULL, + }; + int r; - if (amdgpu_bad_page_threshold != 0) - amdgpu_ras_sysfs_add_bad_page_node(adev); + /* add features entry */ + con->features_attr = dev_attr_features; + group.attrs = attrs; + sysfs_attr_init(attrs[0]); + + if (amdgpu_bad_page_threshold != 0) { + /* add bad_page_features entry */ + bin_attr_gpu_vram_bad_pages.private = NULL; + con->badpages_attr = bin_attr_gpu_vram_bad_pages; + bin_attrs[0] = &con->badpages_attr; + group.bin_attrs = bin_attrs; + sysfs_bin_attr_init(bin_attrs[0]); + } + + r = sysfs_create_group(&adev->dev->kobj, &group); + if (r) + dev_err(adev->dev, "Failed to create RAS sysfs group!"); return 0; } @@ -1498,6 +1476,45 @@ static void amdgpu_ras_log_on_err_counter(struct amdgpu_device *adev) } } +/* Parse RdRspStatus and WrRspStatus */ +void amdgpu_ras_error_status_query(struct amdgpu_device *adev, + struct ras_query_if *info) +{ + /* + * Only two block need to query read/write + * RspStatus at current state + */ + switch (info->head.block) { + case AMDGPU_RAS_BLOCK__GFX: + if (adev->gfx.funcs->query_ras_error_status) + adev->gfx.funcs->query_ras_error_status(adev); + break; + case AMDGPU_RAS_BLOCK__MMHUB: + if (adev->mmhub.funcs->query_ras_error_status) + adev->mmhub.funcs->query_ras_error_status(adev); + break; + default: + break; + } +} + +static void amdgpu_ras_query_err_status(struct amdgpu_device *adev) +{ + struct amdgpu_ras *con = amdgpu_ras_get_context(adev); + struct ras_manager *obj; + + if (!con) + return; + + list_for_each_entry(obj, &con->head, node) { + struct ras_query_if info = { + .head = obj->head, + }; + + amdgpu_ras_error_status_query(adev, &info); + } +} + /* recovery begin */ /* return 0 on success. @@ -1568,8 +1585,10 @@ static void amdgpu_ras_do_recovery(struct work_struct *work) } list_for_each_entry(remote_adev, - device_list_handle, gmc.xgmi.head) + device_list_handle, gmc.xgmi.head) { + amdgpu_ras_query_err_status(remote_adev); amdgpu_ras_log_on_err_counter(remote_adev); + } amdgpu_put_xgmi_hive(hive); } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_rlc.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_rlc.h index 60bb3e8b3118..aeaaae713c59 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_rlc.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_rlc.h @@ -168,12 +168,16 @@ struct amdgpu_rlc { u32 save_restore_list_cntl_size_bytes; u32 save_restore_list_gpm_size_bytes; u32 save_restore_list_srm_size_bytes; + u32 rlc_iram_ucode_size_bytes; + u32 rlc_dram_ucode_size_bytes; u32 *register_list_format; u32 *register_restore; u8 *save_restore_list_cntl; u8 *save_restore_list_gpm; u8 *save_restore_list_srm; + u8 *rlc_iram_ucode; + u8 *rlc_dram_ucode; bool is_rlc_v2_1; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h index 63e734a125fb..ee9480d14cbc 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h @@ -35,7 +35,7 @@ #define AMDGPU_JOB_GET_TIMELINE_NAME(job) \ job->base.s_fence->finished.ops->get_timeline_name(&job->base.s_fence->finished) -TRACE_EVENT(amdgpu_mm_rreg, +TRACE_EVENT(amdgpu_device_rreg, TP_PROTO(unsigned did, uint32_t reg, uint32_t value), TP_ARGS(did, reg, value), TP_STRUCT__entry( @@ -54,7 +54,7 @@ TRACE_EVENT(amdgpu_mm_rreg, (unsigned long)__entry->value) ); -TRACE_EVENT(amdgpu_mm_wreg, +TRACE_EVENT(amdgpu_device_wreg, TP_PROTO(unsigned did, uint32_t reg, uint32_t value), TP_ARGS(did, reg, value), TP_STRUCT__entry( @@ -321,6 +321,49 @@ DEFINE_EVENT(amdgpu_vm_mapping, amdgpu_vm_bo_cs, TP_ARGS(mapping) ); +TRACE_EVENT(amdgpu_vm_update_ptes, + TP_PROTO(struct amdgpu_vm_update_params *p, + uint64_t start, uint64_t end, + unsigned int nptes, uint64_t dst, + uint64_t incr, uint64_t flags, + pid_t pid, uint64_t vm_ctx), + TP_ARGS(p, start, end, nptes, dst, incr, flags, pid, vm_ctx), + TP_STRUCT__entry( + __field(u64, start) + __field(u64, end) + __field(u64, flags) + __field(unsigned int, nptes) + __field(u64, incr) + __field(pid_t, pid) + __field(u64, vm_ctx) + __dynamic_array(u64, dst, nptes) + ), + + TP_fast_assign( + unsigned int i; + + __entry->start = start; + __entry->end = end; + __entry->flags = flags; + __entry->incr = incr; + __entry->nptes = nptes; + __entry->pid = pid; + __entry->vm_ctx = vm_ctx; + for (i = 0; i < nptes; ++i) { + u64 addr = p->pages_addr ? amdgpu_vm_map_gart( + p->pages_addr, dst) : dst; + + ((u64 *)__get_dynamic_array(dst))[i] = addr; + dst += incr; + } + ), + TP_printk("pid:%u vm_ctx:0x%llx start:0x%010llx end:0x%010llx," + " flags:0x%llx, incr:%llu, dst:\n%s", __entry->pid, + __entry->vm_ctx, __entry->start, __entry->end, + __entry->flags, __entry->incr, __print_array( + __get_dynamic_array(dst), __entry->nptes, 8)) +); + TRACE_EVENT(amdgpu_vm_set_ptes, TP_PROTO(uint64_t pe, uint64_t addr, unsigned count, uint32_t incr, uint64_t flags, bool direct), diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c index f3416cc1bd04..bd6e6641c3fc 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c @@ -1043,6 +1043,7 @@ static int amdgpu_ttm_tt_pin_userptr(struct ttm_bo_device *bdev, release_sg: kfree(ttm->sg); + ttm->sg = NULL; return r; } @@ -1186,7 +1187,12 @@ static int amdgpu_ttm_backend_bind(struct ttm_bo_device *bdev, } /** - * amdgpu_ttm_alloc_gart - Allocate GART memory for buffer object + * amdgpu_ttm_alloc_gart - Make sure buffer object is accessible either + * through AGP or GART aperture. + * + * If bo is accessible through AGP aperture, then use AGP aperture + * to access bo; otherwise allocate logical space in GART aperture + * and map bo to GART aperture. */ int amdgpu_ttm_alloc_gart(struct ttm_buffer_object *bo) { diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c index 55fe19a2f332..b313ce4c3e97 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c @@ -500,6 +500,8 @@ static int amdgpu_ucode_init_single_fw(struct amdgpu_device *adev, ucode->ucode_id != AMDGPU_UCODE_ID_RLC_RESTORE_LIST_CNTL && ucode->ucode_id != AMDGPU_UCODE_ID_RLC_RESTORE_LIST_GPM_MEM && ucode->ucode_id != AMDGPU_UCODE_ID_RLC_RESTORE_LIST_SRM_MEM && + ucode->ucode_id != AMDGPU_UCODE_ID_RLC_IRAM && + ucode->ucode_id != AMDGPU_UCODE_ID_RLC_DRAM && ucode->ucode_id != AMDGPU_UCODE_ID_DMCU_ERAM && ucode->ucode_id != AMDGPU_UCODE_ID_DMCU_INTV && ucode->ucode_id != AMDGPU_UCODE_ID_DMCUB)) { @@ -556,6 +558,14 @@ static int amdgpu_ucode_init_single_fw(struct amdgpu_device *adev, ucode->ucode_size = adev->gfx.rlc.save_restore_list_srm_size_bytes; memcpy(ucode->kaddr, adev->gfx.rlc.save_restore_list_srm, ucode->ucode_size); + } else if (ucode->ucode_id == AMDGPU_UCODE_ID_RLC_IRAM) { + ucode->ucode_size = adev->gfx.rlc.rlc_iram_ucode_size_bytes; + memcpy(ucode->kaddr, adev->gfx.rlc.rlc_iram_ucode, + ucode->ucode_size); + } else if (ucode->ucode_id == AMDGPU_UCODE_ID_RLC_DRAM) { + ucode->ucode_size = adev->gfx.rlc.rlc_dram_ucode_size_bytes; + memcpy(ucode->kaddr, adev->gfx.rlc.rlc_dram_ucode, + ucode->ucode_size); } else if (ucode->ucode_id == AMDGPU_UCODE_ID_CP_MES) { ucode->ucode_size = le32_to_cpu(mes_hdr->mes_ucode_size_bytes); memcpy(ucode->kaddr, (void *)((uint8_t *)adev->mes.fw->data + diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.h index 3c23c6293ff9..0e43b46d3ab5 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.h @@ -222,6 +222,15 @@ struct rlc_firmware_header_v2_1 { uint32_t save_restore_list_srm_offset_bytes; }; +/* version_major=2, version_minor=1 */ +struct rlc_firmware_header_v2_2 { + struct rlc_firmware_header_v2_1 v2_1; + uint32_t rlc_iram_ucode_size_bytes; + uint32_t rlc_iram_ucode_offset_bytes; + uint32_t rlc_dram_ucode_size_bytes; + uint32_t rlc_dram_ucode_offset_bytes; +}; + /* version_major=1, version_minor=0 */ struct sdma_firmware_header_v1_0 { struct common_firmware_header header; @@ -339,6 +348,8 @@ enum AMDGPU_UCODE_ID { AMDGPU_UCODE_ID_RLC_RESTORE_LIST_CNTL, AMDGPU_UCODE_ID_RLC_RESTORE_LIST_GPM_MEM, AMDGPU_UCODE_ID_RLC_RESTORE_LIST_SRM_MEM, + AMDGPU_UCODE_ID_RLC_IRAM, + AMDGPU_UCODE_ID_RLC_DRAM, AMDGPU_UCODE_ID_RLC_G, AMDGPU_UCODE_ID_STORAGE, AMDGPU_UCODE_ID_SMC, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c index 495c3d7bb2b2..f3b7287e84c4 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c @@ -68,6 +68,7 @@ int amdgpu_vcn_sw_init(struct amdgpu_device *adev) INIT_DELAYED_WORK(&adev->vcn.idle_work, amdgpu_vcn_idle_work_handler); mutex_init(&adev->vcn.vcn_pg_lock); + mutex_init(&adev->vcn.vcn1_jpeg1_workaround); atomic_set(&adev->vcn.total_submission_cnt, 0); for (i = 0; i < adev->vcn.num_vcn_inst; i++) atomic_set(&adev->vcn.inst[i].dpg_enc_submission_cnt, 0); @@ -237,6 +238,7 @@ int amdgpu_vcn_sw_fini(struct amdgpu_device *adev) } release_firmware(adev->vcn.fw); + mutex_destroy(&adev->vcn.vcn1_jpeg1_workaround); mutex_destroy(&adev->vcn.vcn_pg_lock); return 0; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h index 7a9b804bc988..17691158f783 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h @@ -220,6 +220,7 @@ struct amdgpu_vcn { struct amdgpu_vcn_inst inst[AMDGPU_MAX_VCN_INSTANCES]; struct amdgpu_vcn_reg internal; struct mutex vcn_pg_lock; + struct mutex vcn1_jpeg1_workaround; atomic_t total_submission_cnt; unsigned harvest_config; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c index f76961d17246..d0aea5e39531 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c @@ -31,6 +31,12 @@ #include "soc15.h" #include "nv.h" +#define POPULATE_UCODE_INFO(vf2pf_info, ucode, ver) \ + do { \ + vf2pf_info->ucode_info[ucode].id = ucode; \ + vf2pf_info->ucode_info[ucode].version = ver; \ + } while (0) + bool amdgpu_virt_mmio_blocked(struct amdgpu_device *adev) { /* By now all MMIO pages except mailbox are blocked */ @@ -239,10 +245,10 @@ void amdgpu_virt_free_mm_table(struct amdgpu_device *adev) } -int amdgpu_virt_fw_reserve_get_checksum(void *obj, - unsigned long obj_size, - unsigned int key, - unsigned int chksum) +unsigned int amd_sriov_msg_checksum(void *obj, + unsigned long obj_size, + unsigned int key, + unsigned int checksum) { unsigned int ret = key; unsigned long i = 0; @@ -252,9 +258,9 @@ int amdgpu_virt_fw_reserve_get_checksum(void *obj, /* calculate checksum */ for (i = 0; i < obj_size; ++i) ret += *(pos + i); - /* minus the chksum itself */ - pos = (char *)&chksum; - for (i = 0; i < sizeof(chksum); ++i) + /* minus the checksum itself */ + pos = (char *)&checksum; + for (i = 0; i < sizeof(checksum); ++i) ret -= *(pos + i); return ret; } @@ -415,33 +421,188 @@ static void amdgpu_virt_add_bad_page(struct amdgpu_device *adev, } } -void amdgpu_virt_init_data_exchange(struct amdgpu_device *adev) +static int amdgpu_virt_read_pf2vf_data(struct amdgpu_device *adev) { - uint32_t pf2vf_size = 0; - uint32_t checksum = 0; + struct amd_sriov_msg_pf2vf_info_header *pf2vf_info = adev->virt.fw_reserve.p_pf2vf; + uint32_t checksum; uint32_t checkval; - char *str; + + if (adev->virt.fw_reserve.p_pf2vf == NULL) + return -EINVAL; + + if (pf2vf_info->size > 1024) { + DRM_ERROR("invalid pf2vf message size\n"); + return -EINVAL; + } + + switch (pf2vf_info->version) { + case 1: + checksum = ((struct amdgim_pf2vf_info_v1 *)pf2vf_info)->checksum; + checkval = amd_sriov_msg_checksum( + adev->virt.fw_reserve.p_pf2vf, pf2vf_info->size, + adev->virt.fw_reserve.checksum_key, checksum); + if (checksum != checkval) { + DRM_ERROR("invalid pf2vf message\n"); + return -EINVAL; + } + + adev->virt.gim_feature = + ((struct amdgim_pf2vf_info_v1 *)pf2vf_info)->feature_flags; + break; + case 2: + /* TODO: missing key, need to add it later */ + checksum = ((struct amd_sriov_msg_pf2vf_info *)pf2vf_info)->checksum; + checkval = amd_sriov_msg_checksum( + adev->virt.fw_reserve.p_pf2vf, pf2vf_info->size, + 0, checksum); + if (checksum != checkval) { + DRM_ERROR("invalid pf2vf message\n"); + return -EINVAL; + } + + adev->virt.vf2pf_update_interval_ms = + ((struct amd_sriov_msg_pf2vf_info *)pf2vf_info)->vf2pf_update_interval_ms; + adev->virt.gim_feature = + ((struct amd_sriov_msg_pf2vf_info *)pf2vf_info)->feature_flags.all; + + break; + default: + DRM_ERROR("invalid pf2vf version\n"); + return -EINVAL; + } + + /* correct too large or too little interval value */ + if (adev->virt.vf2pf_update_interval_ms < 200 || adev->virt.vf2pf_update_interval_ms > 10000) + adev->virt.vf2pf_update_interval_ms = 2000; + + return 0; +} + +static void amdgpu_virt_populate_vf2pf_ucode_info(struct amdgpu_device *adev) +{ + struct amd_sriov_msg_vf2pf_info *vf2pf_info; + vf2pf_info = (struct amd_sriov_msg_vf2pf_info *) adev->virt.fw_reserve.p_vf2pf; + + if (adev->virt.fw_reserve.p_vf2pf == NULL) + return; + + POPULATE_UCODE_INFO(vf2pf_info, AMD_SRIOV_UCODE_ID_VCE, adev->vce.fw_version); + POPULATE_UCODE_INFO(vf2pf_info, AMD_SRIOV_UCODE_ID_UVD, adev->uvd.fw_version); + POPULATE_UCODE_INFO(vf2pf_info, AMD_SRIOV_UCODE_ID_MC, adev->gmc.fw_version); + POPULATE_UCODE_INFO(vf2pf_info, AMD_SRIOV_UCODE_ID_ME, adev->gfx.me_fw_version); + POPULATE_UCODE_INFO(vf2pf_info, AMD_SRIOV_UCODE_ID_PFP, adev->gfx.pfp_fw_version); + POPULATE_UCODE_INFO(vf2pf_info, AMD_SRIOV_UCODE_ID_CE, adev->gfx.ce_fw_version); + POPULATE_UCODE_INFO(vf2pf_info, AMD_SRIOV_UCODE_ID_RLC, adev->gfx.rlc_fw_version); + POPULATE_UCODE_INFO(vf2pf_info, AMD_SRIOV_UCODE_ID_RLC_SRLC, adev->gfx.rlc_srlc_fw_version); + POPULATE_UCODE_INFO(vf2pf_info, AMD_SRIOV_UCODE_ID_RLC_SRLG, adev->gfx.rlc_srlg_fw_version); + POPULATE_UCODE_INFO(vf2pf_info, AMD_SRIOV_UCODE_ID_RLC_SRLS, adev->gfx.rlc_srls_fw_version); + POPULATE_UCODE_INFO(vf2pf_info, AMD_SRIOV_UCODE_ID_MEC, adev->gfx.mec_fw_version); + POPULATE_UCODE_INFO(vf2pf_info, AMD_SRIOV_UCODE_ID_MEC2, adev->gfx.mec2_fw_version); + POPULATE_UCODE_INFO(vf2pf_info, AMD_SRIOV_UCODE_ID_SOS, adev->psp.sos_fw_version); + POPULATE_UCODE_INFO(vf2pf_info, AMD_SRIOV_UCODE_ID_ASD, adev->psp.asd_fw_version); + POPULATE_UCODE_INFO(vf2pf_info, AMD_SRIOV_UCODE_ID_TA_RAS, adev->psp.ta_ras_ucode_version); + POPULATE_UCODE_INFO(vf2pf_info, AMD_SRIOV_UCODE_ID_TA_XGMI, adev->psp.ta_xgmi_ucode_version); + POPULATE_UCODE_INFO(vf2pf_info, AMD_SRIOV_UCODE_ID_SMC, adev->pm.fw_version); + POPULATE_UCODE_INFO(vf2pf_info, AMD_SRIOV_UCODE_ID_SDMA, adev->sdma.instance[0].fw_version); + POPULATE_UCODE_INFO(vf2pf_info, AMD_SRIOV_UCODE_ID_SDMA2, adev->sdma.instance[1].fw_version); + POPULATE_UCODE_INFO(vf2pf_info, AMD_SRIOV_UCODE_ID_VCN, adev->vcn.fw_version); + POPULATE_UCODE_INFO(vf2pf_info, AMD_SRIOV_UCODE_ID_DMCU, adev->dm.dmcu_fw_version); +} + +static int amdgpu_virt_write_vf2pf_data(struct amdgpu_device *adev) +{ + struct amd_sriov_msg_vf2pf_info *vf2pf_info; + struct ttm_resource_manager *vram_man = ttm_manager_type(&adev->mman.bdev, TTM_PL_VRAM); + + vf2pf_info = (struct amd_sriov_msg_vf2pf_info *) adev->virt.fw_reserve.p_vf2pf; + + if (adev->virt.fw_reserve.p_vf2pf == NULL) + return -EINVAL; + + memset(vf2pf_info, 0, sizeof(struct amd_sriov_msg_vf2pf_info)); + + vf2pf_info->header.size = sizeof(struct amd_sriov_msg_vf2pf_info); + vf2pf_info->header.version = AMD_SRIOV_MSG_FW_VRAM_VF2PF_VER; + +#ifdef MODULE + if (THIS_MODULE->version != NULL) + strcpy(vf2pf_info->driver_version, THIS_MODULE->version); + else +#endif + strcpy(vf2pf_info->driver_version, "N/A"); + + vf2pf_info->pf2vf_version_required = 0; // no requirement, guest understands all + vf2pf_info->driver_cert = 0; + vf2pf_info->os_info.all = 0; + + vf2pf_info->fb_usage = amdgpu_vram_mgr_usage(vram_man) >> 20; + vf2pf_info->fb_vis_usage = amdgpu_vram_mgr_vis_usage(vram_man) >> 20; + vf2pf_info->fb_size = adev->gmc.real_vram_size >> 20; + vf2pf_info->fb_vis_size = adev->gmc.visible_vram_size >> 20; + + amdgpu_virt_populate_vf2pf_ucode_info(adev); + + /* TODO: read dynamic info */ + vf2pf_info->gfx_usage = 0; + vf2pf_info->compute_usage = 0; + vf2pf_info->encode_usage = 0; + vf2pf_info->decode_usage = 0; + + vf2pf_info->checksum = + amd_sriov_msg_checksum( + vf2pf_info, vf2pf_info->header.size, 0, 0); + + return 0; +} + +void amdgpu_virt_update_vf2pf_work_item(struct work_struct *work) +{ + struct amdgpu_device *adev = container_of(work, struct amdgpu_device, virt.vf2pf_work.work); + + amdgpu_virt_read_pf2vf_data(adev); + amdgpu_virt_write_vf2pf_data(adev); + + schedule_delayed_work(&(adev->virt.vf2pf_work), adev->virt.vf2pf_update_interval_ms); +} + +void amdgpu_virt_fini_data_exchange(struct amdgpu_device *adev) +{ + if (adev->virt.vf2pf_update_interval_ms != 0) { + DRM_INFO("clean up the vf2pf work item\n"); + flush_delayed_work(&adev->virt.vf2pf_work); + cancel_delayed_work_sync(&adev->virt.vf2pf_work); + } +} + +void amdgpu_virt_init_data_exchange(struct amdgpu_device *adev) +{ uint64_t bp_block_offset = 0; uint32_t bp_block_size = 0; - struct amdgim_pf2vf_info_v2 *pf2vf_v2 = NULL; + struct amd_sriov_msg_pf2vf_info *pf2vf_v2 = NULL; adev->virt.fw_reserve.p_pf2vf = NULL; adev->virt.fw_reserve.p_vf2pf = NULL; + adev->virt.vf2pf_update_interval_ms = 0; if (adev->mman.fw_vram_usage_va != NULL) { + adev->virt.vf2pf_update_interval_ms = 2000; + adev->virt.fw_reserve.p_pf2vf = - (struct amd_sriov_msg_pf2vf_info_header *)( - adev->mman.fw_vram_usage_va + AMDGIM_DATAEXCHANGE_OFFSET); - AMDGPU_FW_VRAM_PF2VF_READ(adev, header.size, &pf2vf_size); - AMDGPU_FW_VRAM_PF2VF_READ(adev, checksum, &checksum); - AMDGPU_FW_VRAM_PF2VF_READ(adev, feature_flags, &adev->virt.gim_feature); - - /* pf2vf message must be in 4K */ - if (pf2vf_size > 0 && pf2vf_size < 4096) { - if (adev->virt.fw_reserve.p_pf2vf->version == 2) { - pf2vf_v2 = (struct amdgim_pf2vf_info_v2 *)adev->virt.fw_reserve.p_pf2vf; - bp_block_offset = ((uint64_t)pf2vf_v2->bp_block_offset_L & 0xFFFFFFFF) | - ((((uint64_t)pf2vf_v2->bp_block_offset_H) << 32) & 0xFFFFFFFF00000000); + (struct amd_sriov_msg_pf2vf_info_header *) + (adev->mman.fw_vram_usage_va + (AMD_SRIOV_MSG_PF2VF_OFFSET_KB << 10)); + adev->virt.fw_reserve.p_vf2pf = + (struct amd_sriov_msg_vf2pf_info_header *) + (adev->mman.fw_vram_usage_va + (AMD_SRIOV_MSG_VF2PF_OFFSET_KB << 10)); + + amdgpu_virt_read_pf2vf_data(adev); + amdgpu_virt_write_vf2pf_data(adev); + + /* bad page handling for version 2 */ + if (adev->virt.fw_reserve.p_pf2vf->version == 2) { + pf2vf_v2 = (struct amd_sriov_msg_pf2vf_info *)adev->virt.fw_reserve.p_pf2vf; + + bp_block_offset = ((uint64_t)pf2vf_v2->bp_block_offset_low & 0xFFFFFFFF) | + ((((uint64_t)pf2vf_v2->bp_block_offset_high) << 32) & 0xFFFFFFFF00000000); bp_block_size = pf2vf_v2->bp_block_size; if (bp_block_size && !adev->virt.ras_init_done) @@ -450,37 +611,11 @@ void amdgpu_virt_init_data_exchange(struct amdgpu_device *adev) if (adev->virt.ras_init_done) amdgpu_virt_add_bad_page(adev, bp_block_offset, bp_block_size); } + } - checkval = amdgpu_virt_fw_reserve_get_checksum( - adev->virt.fw_reserve.p_pf2vf, pf2vf_size, - adev->virt.fw_reserve.checksum_key, checksum); - if (checkval == checksum) { - adev->virt.fw_reserve.p_vf2pf = - ((void *)adev->virt.fw_reserve.p_pf2vf + - pf2vf_size); - memset((void *)adev->virt.fw_reserve.p_vf2pf, 0, - sizeof(amdgim_vf2pf_info)); - AMDGPU_FW_VRAM_VF2PF_WRITE(adev, header.version, - AMDGPU_FW_VRAM_VF2PF_VER); - AMDGPU_FW_VRAM_VF2PF_WRITE(adev, header.size, - sizeof(amdgim_vf2pf_info)); - AMDGPU_FW_VRAM_VF2PF_READ(adev, driver_version, - &str); -#ifdef MODULE - if (THIS_MODULE->version != NULL) - strcpy(str, THIS_MODULE->version); - else -#endif - strcpy(str, "N/A"); - AMDGPU_FW_VRAM_VF2PF_WRITE(adev, driver_cert, - 0); - AMDGPU_FW_VRAM_VF2PF_WRITE(adev, checksum, - amdgpu_virt_fw_reserve_get_checksum( - adev->virt.fw_reserve.p_vf2pf, - pf2vf_size, - adev->virt.fw_reserve.checksum_key, 0)); - } - } + if (adev->virt.vf2pf_update_interval_ms != 0) { + INIT_DELAYED_WORK(&adev->virt.vf2pf_work, amdgpu_virt_update_vf2pf_work_item); + schedule_delayed_work(&(adev->virt.vf2pf_work), adev->virt.vf2pf_update_interval_ms); } } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h index b2046c3a404d..8dd624c20f89 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h @@ -24,6 +24,8 @@ #ifndef AMDGPU_VIRT_H #define AMDGPU_VIRT_H +#include "amdgv_sriovmsg.h" + #define AMDGPU_SRIOV_CAPS_SRIOV_VBIOS (1 << 0) /* vBIOS is sr-iov ready */ #define AMDGPU_SRIOV_CAPS_ENABLE_IOV (1 << 1) /* sr-iov is enabled on this GPU */ #define AMDGPU_SRIOV_CAPS_IS_VF (1 << 2) /* this GPU is a virtual function */ @@ -79,7 +81,10 @@ struct amdgpu_virt_fw_reserve { struct amd_sriov_msg_vf2pf_info_header *p_vf2pf; unsigned int checksum_key; }; + /* + * Legacy GIM header + * * Defination between PF and VF * Structures forcibly aligned to 4 to keep the same style as PF. */ @@ -101,15 +106,7 @@ enum AMDGIM_FEATURE_FLAG { AMDGIM_FEATURE_PP_ONE_VF = (1 << 4), }; -struct amd_sriov_msg_pf2vf_info_header { - /* the total structure size in byte. */ - uint32_t size; - /* version of this structure, written by the GIM */ - uint32_t version; - /* reserved */ - uint32_t reserved[2]; -} __aligned(4); -struct amdgim_pf2vf_info_v1 { +struct amdgim_pf2vf_info_v1 { /* header contains size and version */ struct amd_sriov_msg_pf2vf_info_header header; /* max_width * max_height */ @@ -128,54 +125,6 @@ struct amdgim_pf2vf_info_v1 { unsigned int checksum; } __aligned(4); -struct amdgim_pf2vf_info_v2 { - /* header contains size and version */ - struct amd_sriov_msg_pf2vf_info_header header; - /* use private key from mailbox 2 to create chueksum */ - uint32_t checksum; - /* The features flags of the GIM driver supports. */ - uint32_t feature_flags; - /* max_width * max_height */ - uint32_t uvd_enc_max_pixels_count; - /* 16x16 pixels/sec, codec independent */ - uint32_t uvd_enc_max_bandwidth; - /* max_width * max_height */ - uint32_t vce_enc_max_pixels_count; - /* 16x16 pixels/sec, codec independent */ - uint32_t vce_enc_max_bandwidth; - /* Bad pages block position in BYTE */ - uint32_t bp_block_offset_L; - uint32_t bp_block_offset_H; - /* Bad pages block size in BYTE */ - uint32_t bp_block_size; - /* MEC FW position in kb from the start of VF visible frame buffer */ - uint32_t mecfw_kboffset_L; - uint32_t mecfw_kboffset_H; - /* MEC FW size in KB */ - uint32_t mecfw_ksize; - /* UVD FW position in kb from the start of VF visible frame buffer */ - uint32_t uvdfw_kboffset_L; - uint32_t uvdfw_kboffset_H; - /* UVD FW size in KB */ - uint32_t uvdfw_ksize; - /* VCE FW position in kb from the start of VF visible frame buffer */ - uint32_t vcefw_kboffset_L; - uint32_t vcefw_kboffset_H; - /* VCE FW size in KB */ - uint32_t vcefw_ksize; - uint32_t reserved[AMDGIM_GET_STRUCTURE_RESERVED_SIZE(256, 0, 0, (18 + sizeof(struct amd_sriov_msg_pf2vf_info_header)/sizeof(uint32_t)), 0)]; -} __aligned(4); - - -struct amd_sriov_msg_vf2pf_info_header { - /* the total structure size in byte. */ - uint32_t size; - /*version of this structure, written by the guest */ - uint32_t version; - /* reserved */ - uint32_t reserved[2]; -} __aligned(4); - struct amdgim_vf2pf_info_v1 { /* header contains size and version */ struct amd_sriov_msg_vf2pf_info_header header; @@ -237,31 +186,6 @@ struct amdgim_vf2pf_info_v2 { uint32_t reserved[AMDGIM_GET_STRUCTURE_RESERVED_SIZE(256, 64, 0, (12 + sizeof(struct amd_sriov_msg_vf2pf_info_header)/sizeof(uint32_t)), 0)]; } __aligned(4); -#define AMDGPU_FW_VRAM_VF2PF_VER 2 -typedef struct amdgim_vf2pf_info_v2 amdgim_vf2pf_info ; - -#define AMDGPU_FW_VRAM_VF2PF_WRITE(adev, field, val) \ - do { \ - ((amdgim_vf2pf_info *)adev->virt.fw_reserve.p_vf2pf)->field = (val); \ - } while (0) - -#define AMDGPU_FW_VRAM_VF2PF_READ(adev, field, val) \ - do { \ - (*val) = ((amdgim_vf2pf_info *)adev->virt.fw_reserve.p_vf2pf)->field; \ - } while (0) - -#define AMDGPU_FW_VRAM_PF2VF_READ(adev, field, val) \ - do { \ - if (!adev->virt.fw_reserve.p_pf2vf) \ - *(val) = 0; \ - else { \ - if (adev->virt.fw_reserve.p_pf2vf->version == 1) \ - *(val) = ((struct amdgim_pf2vf_info_v1 *)adev->virt.fw_reserve.p_pf2vf)->field; \ - if (adev->virt.fw_reserve.p_pf2vf->version == 2) \ - *(val) = ((struct amdgim_pf2vf_info_v2 *)adev->virt.fw_reserve.p_pf2vf)->field; \ - } \ - } while (0) - struct amdgpu_virt_ras_err_handler_data { /* point to bad page records array */ struct eeprom_table_record *bps; @@ -285,7 +209,7 @@ struct amdgpu_virt { struct work_struct flr_work; struct amdgpu_mm_table mm_table; const struct amdgpu_virt_ops *ops; - struct amdgpu_vf_error_buffer vf_errors; + struct amdgpu_vf_error_buffer vf_errors; struct amdgpu_virt_fw_reserve fw_reserve; uint32_t gim_feature; uint32_t reg_access_mode; @@ -293,6 +217,10 @@ struct amdgpu_virt { bool tdr_debug; struct amdgpu_virt_ras_err_handler_data *virt_eh_data; bool ras_init_done; + + /* vf2pf message */ + struct delayed_work vf2pf_work; + uint32_t vf2pf_update_interval_ms; }; #define amdgpu_sriov_enabled(adev) \ @@ -341,11 +269,9 @@ void amdgpu_virt_request_init_data(struct amdgpu_device *adev); int amdgpu_virt_wait_reset(struct amdgpu_device *adev); int amdgpu_virt_alloc_mm_table(struct amdgpu_device *adev); void amdgpu_virt_free_mm_table(struct amdgpu_device *adev); -int amdgpu_virt_fw_reserve_get_checksum(void *obj, unsigned long obj_size, - unsigned int key, - unsigned int chksum); void amdgpu_virt_release_ras_err_handler_data(struct amdgpu_device *adev); void amdgpu_virt_init_data_exchange(struct amdgpu_device *adev); +void amdgpu_virt_fini_data_exchange(struct amdgpu_device *adev); void amdgpu_detect_virtualization(struct amdgpu_device *adev); bool amdgpu_virt_can_access_debugfs(struct amdgpu_device *adev); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c index f0e6fafd0938..38b59a4fc04c 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c @@ -1502,6 +1502,8 @@ static int amdgpu_vm_update_ptes(struct amdgpu_vm_update_params *params, pt = cursor.entry->base.bo; shift = parent_shift; + frag_end = max(frag_end, ALIGN(frag_start + 1, + 1ULL << shift)); } /* Looks good so far, calculate parameters for the update */ @@ -1513,19 +1515,26 @@ static int amdgpu_vm_update_ptes(struct amdgpu_vm_update_params *params, entry_end = min(entry_end, end); do { + struct amdgpu_vm *vm = params->vm; uint64_t upd_end = min(entry_end, frag_end); unsigned nptes = (upd_end - frag_start) >> shift; + uint64_t upd_flags = flags | AMDGPU_PTE_FRAG(frag); /* This can happen when we set higher level PDs to * silent to stop fault floods. */ nptes = max(nptes, 1u); + + trace_amdgpu_vm_update_ptes(params, frag_start, upd_end, + nptes, dst, incr, upd_flags, + vm->task_info.pid, + vm->immediate.fence_context); amdgpu_vm_update_flags(params, pt, cursor.level, pe_start, dst, nptes, incr, - flags | AMDGPU_PTE_FRAG(frag)); + upd_flags); pe_start += nptes * 8; - dst += (uint64_t)nptes * AMDGPU_GPU_PAGE_SIZE << shift; + dst += nptes * incr; frag_start = upd_end; if (frag_start >= frag_end) { @@ -2795,7 +2804,7 @@ long amdgpu_vm_wait_idle(struct amdgpu_vm *vm, long timeout) * 0 for success, error for failure. */ int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm, - int vm_context, unsigned int pasid) + int vm_context, u32 pasid) { struct amdgpu_bo_param bp; struct amdgpu_bo *root; @@ -2966,7 +2975,7 @@ static int amdgpu_vm_check_clean_reserved(struct amdgpu_device *adev, * 0 for success, -errno for errors. */ int amdgpu_vm_make_compute(struct amdgpu_device *adev, struct amdgpu_vm *vm, - unsigned int pasid) + u32 pasid) { bool pte_support_ats = (adev->asic_type == CHIP_RAVEN); int r; @@ -3264,7 +3273,7 @@ int amdgpu_vm_ioctl(struct drm_device *dev, void *data, struct drm_file *filp) * @pasid: PASID identifier for VM * @task_info: task_info to fill. */ -void amdgpu_vm_get_task_info(struct amdgpu_device *adev, unsigned int pasid, +void amdgpu_vm_get_task_info(struct amdgpu_device *adev, u32 pasid, struct amdgpu_task_info *task_info) { struct amdgpu_vm *vm; @@ -3308,7 +3317,7 @@ void amdgpu_vm_set_task_info(struct amdgpu_vm *vm) * Try to gracefully handle a VM fault. Return true if the fault was handled and * shouldn't be reported any more. */ -bool amdgpu_vm_handle_fault(struct amdgpu_device *adev, unsigned int pasid, +bool amdgpu_vm_handle_fault(struct amdgpu_device *adev, u32 pasid, uint64_t addr) { struct amdgpu_bo *root; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h index 770025a5e500..58c83a7ad0fd 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h @@ -98,7 +98,7 @@ struct amdgpu_bo_list_entry; #define AMDGPU_PTE_MTYPE_NV10(a) ((uint64_t)(a) << 48) #define AMDGPU_PTE_MTYPE_NV10_MASK AMDGPU_PTE_MTYPE_NV10(7ULL) -/* How to programm VM fault handling */ +/* How to program VM fault handling */ #define AMDGPU_VM_FAULT_STOP_NEVER 0 #define AMDGPU_VM_FAULT_STOP_FIRST 1 #define AMDGPU_VM_FAULT_STOP_ALWAYS 2 @@ -112,8 +112,8 @@ struct amdgpu_bo_list_entry; #define AMDGPU_MMHUB_0 1 #define AMDGPU_MMHUB_1 2 -/* hardcode that limit for now */ -#define AMDGPU_VA_RESERVED_SIZE (1ULL << 20) +/* Reserve 2MB at top/bottom of address space for kernel use */ +#define AMDGPU_VA_RESERVED_SIZE (2ULL << 20) /* max vmids dedicated for process */ #define AMDGPU_VM_MAX_RESERVED_VMID 1 @@ -372,8 +372,8 @@ void amdgpu_vm_manager_fini(struct amdgpu_device *adev); long amdgpu_vm_wait_idle(struct amdgpu_vm *vm, long timeout); int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm, - int vm_context, unsigned int pasid); -int amdgpu_vm_make_compute(struct amdgpu_device *adev, struct amdgpu_vm *vm, unsigned int pasid); + int vm_context, u32 pasid); +int amdgpu_vm_make_compute(struct amdgpu_device *adev, struct amdgpu_vm *vm, u32 pasid); void amdgpu_vm_release_compute(struct amdgpu_device *adev, struct amdgpu_vm *vm); void amdgpu_vm_fini(struct amdgpu_device *adev, struct amdgpu_vm *vm); void amdgpu_vm_get_pd_bo(struct amdgpu_vm *vm, @@ -430,9 +430,9 @@ bool amdgpu_vm_need_pipeline_sync(struct amdgpu_ring *ring, struct amdgpu_job *job); void amdgpu_vm_check_compute_bug(struct amdgpu_device *adev); -void amdgpu_vm_get_task_info(struct amdgpu_device *adev, unsigned int pasid, +void amdgpu_vm_get_task_info(struct amdgpu_device *adev, u32 pasid, struct amdgpu_task_info *task_info); -bool amdgpu_vm_handle_fault(struct amdgpu_device *adev, unsigned int pasid, +bool amdgpu_vm_handle_fault(struct amdgpu_device *adev, u32 pasid, uint64_t addr); void amdgpu_vm_set_task_info(struct amdgpu_vm *vm); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_cpu.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_cpu.c index 39c704a1fb0e..0786e7555554 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_cpu.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_cpu.c @@ -59,7 +59,7 @@ static int amdgpu_vm_cpu_prepare(struct amdgpu_vm_update_params *p, * * @p: see amdgpu_vm_update_params definition * @bo: PD/PT to update - * @pe: kmap addr of the page entry + * @pe: byte offset of the PDE/PTE, relative to start of PDB/PTB * @addr: dst addr to write into pe * @count: number of page entries to update * @incr: increase next addr by incr bytes diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_sdma.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_sdma.c index 189d46ea603b..db790574dc2e 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_sdma.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_sdma.c @@ -155,7 +155,7 @@ static void amdgpu_vm_sdma_copy_ptes(struct amdgpu_vm_update_params *p, * * @p: see amdgpu_vm_update_params definition * @bo: PD/PT to update - * @pe: addr of the page entry + * @pe: byte offset of the PDE/PTE, relative to start of PDB/PTB * @addr: dst addr to write into pe * @count: number of page entries to update * @incr: increase next addr by incr bytes @@ -187,7 +187,7 @@ static void amdgpu_vm_sdma_set_ptes(struct amdgpu_vm_update_params *p, * * @p: see amdgpu_vm_update_params definition * @bo: PD/PT to update - * @pe: addr of the page entry + * @pe: byte offset of the PDE/PTE, relative to start of PDB/PTB * @addr: dst addr to write into pe * @count: number of page entries to update * @incr: increase next addr by incr bytes diff --git a/drivers/gpu/drm/amd/amdgpu/amdgv_sriovmsg.h b/drivers/gpu/drm/amd/amdgpu/amdgv_sriovmsg.h new file mode 100644 index 000000000000..5355827ed0ae --- /dev/null +++ b/drivers/gpu/drm/amd/amdgpu/amdgv_sriovmsg.h @@ -0,0 +1,276 @@ +/* + * Copyright 2018-2019 Advanced Micro Devices, Inc. + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of this software and associated documentation files (the "Software"), + * to deal in the Software without restriction, including without limitation + * the rights to use, copy, modify, merge, publish, distribute, sublicense, + * and/or sell copies of the Software, and to permit persons to whom the + * Software is furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR + * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, + * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR + * OTHER DEALINGS IN THE SOFTWARE. + * + */ + +#ifndef AMDGV_SRIOV_MSG__H_ +#define AMDGV_SRIOV_MSG__H_ + +/* unit in kilobytes */ +#define AMD_SRIOV_MSG_VBIOS_OFFSET 0 +#define AMD_SRIOV_MSG_VBIOS_SIZE_KB 64 +#define AMD_SRIOV_MSG_DATAEXCHANGE_OFFSET_KB AMD_SRIOV_MSG_VBIOS_SIZE_KB +#define AMD_SRIOV_MSG_DATAEXCHANGE_SIZE_KB 4 + +/* + * layout + * 0 64KB 65KB 66KB + * | VBIOS | PF2VF | VF2PF | Bad Page | ... + * | 64KB | 1KB | 1KB | + */ +#define AMD_SRIOV_MSG_SIZE_KB 1 +#define AMD_SRIOV_MSG_PF2VF_OFFSET_KB AMD_SRIOV_MSG_DATAEXCHANGE_OFFSET_KB +#define AMD_SRIOV_MSG_VF2PF_OFFSET_KB (AMD_SRIOV_MSG_PF2VF_OFFSET_KB + AMD_SRIOV_MSG_SIZE_KB) +#define AMD_SRIOV_MSG_BAD_PAGE_OFFSET_KB (AMD_SRIOV_MSG_VF2PF_OFFSET_KB + AMD_SRIOV_MSG_SIZE_KB) + +/* + * PF2VF history log: + * v1 defined in amdgim + * v2 current + * + * VF2PF history log: + * v1 defined in amdgim + * v2 defined in amdgim + * v3 current + */ +#define AMD_SRIOV_MSG_FW_VRAM_PF2VF_VER 2 +#define AMD_SRIOV_MSG_FW_VRAM_VF2PF_VER 3 + +#define AMD_SRIOV_MSG_RESERVE_UCODE 24 + +enum amd_sriov_ucode_engine_id { + AMD_SRIOV_UCODE_ID_VCE = 0, + AMD_SRIOV_UCODE_ID_UVD, + AMD_SRIOV_UCODE_ID_MC, + AMD_SRIOV_UCODE_ID_ME, + AMD_SRIOV_UCODE_ID_PFP, + AMD_SRIOV_UCODE_ID_CE, + AMD_SRIOV_UCODE_ID_RLC, + AMD_SRIOV_UCODE_ID_RLC_SRLC, + AMD_SRIOV_UCODE_ID_RLC_SRLG, + AMD_SRIOV_UCODE_ID_RLC_SRLS, + AMD_SRIOV_UCODE_ID_MEC, + AMD_SRIOV_UCODE_ID_MEC2, + AMD_SRIOV_UCODE_ID_SOS, + AMD_SRIOV_UCODE_ID_ASD, + AMD_SRIOV_UCODE_ID_TA_RAS, + AMD_SRIOV_UCODE_ID_TA_XGMI, + AMD_SRIOV_UCODE_ID_SMC, + AMD_SRIOV_UCODE_ID_SDMA, + AMD_SRIOV_UCODE_ID_SDMA2, + AMD_SRIOV_UCODE_ID_VCN, + AMD_SRIOV_UCODE_ID_DMCU, + AMD_SRIOV_UCODE_ID__MAX +}; + +#pragma pack(push, 1) // PF2VF / VF2PF data areas are byte packed + +union amd_sriov_msg_feature_flags { + struct { + uint32_t error_log_collect : 1; + uint32_t host_load_ucodes : 1; + uint32_t host_flr_vramlost : 1; + uint32_t mm_bw_management : 1; + uint32_t pp_one_vf_mode : 1; + uint32_t reserved : 27; + } flags; + uint32_t all; +}; + +union amd_sriov_msg_os_info { + struct { + uint32_t windows : 1; + uint32_t reserved : 31; + } info; + uint32_t all; +}; + +struct amd_sriov_msg_pf2vf_info_header { + /* the total structure size in byte */ + uint32_t size; + /* version of this structure, written by the HOST */ + uint32_t version; + /* reserved */ + uint32_t reserved[2]; +}; + +struct amd_sriov_msg_pf2vf_info { + /* header contains size and version */ + struct amd_sriov_msg_pf2vf_info_header header; + /* use private key from mailbox 2 to create checksum */ + uint32_t checksum; + /* The features flags of the HOST driver supports */ + union amd_sriov_msg_feature_flags feature_flags; + /* (max_width * max_height * fps) / (16 * 16) */ + uint32_t hevc_enc_max_mb_per_second; + /* (max_width * max_height) / (16 * 16) */ + uint32_t hevc_enc_max_mb_per_frame; + /* (max_width * max_height * fps) / (16 * 16) */ + uint32_t avc_enc_max_mb_per_second; + /* (max_width * max_height) / (16 * 16) */ + uint32_t avc_enc_max_mb_per_frame; + /* MEC FW position in BYTE from the start of VF visible frame buffer */ + uint64_t mecfw_offset; + /* MEC FW size in BYTE */ + uint32_t mecfw_size; + /* UVD FW position in BYTE from the start of VF visible frame buffer */ + uint64_t uvdfw_offset; + /* UVD FW size in BYTE */ + uint32_t uvdfw_size; + /* VCE FW position in BYTE from the start of VF visible frame buffer */ + uint64_t vcefw_offset; + /* VCE FW size in BYTE */ + uint32_t vcefw_size; + /* Bad pages block position in BYTE */ + uint32_t bp_block_offset_low; + uint32_t bp_block_offset_high; + /* Bad pages block size in BYTE */ + uint32_t bp_block_size; + /* frequency for VF to update the VF2PF area in msec, 0 = manual */ + uint32_t vf2pf_update_interval_ms; + /* identification in ROCm SMI */ + uint64_t uuid; + uint32_t fcn_idx; + /* reserved */ + uint32_t reserved[256-26]; +}; + +struct amd_sriov_msg_vf2pf_info_header { + /* the total structure size in byte */ + uint32_t size; + /* version of this structure, written by the guest */ + uint32_t version; + /* reserved */ + uint32_t reserved[2]; +}; + +struct amd_sriov_msg_vf2pf_info { + /* header contains size and version */ + struct amd_sriov_msg_vf2pf_info_header header; + uint32_t checksum; + /* driver version */ + uint8_t driver_version[64]; + /* driver certification, 1=WHQL, 0=None */ + uint32_t driver_cert; + /* guest OS type and version */ + union amd_sriov_msg_os_info os_info; + /* guest fb information in the unit of MB */ + uint32_t fb_usage; + /* guest gfx engine usage percentage */ + uint32_t gfx_usage; + /* guest gfx engine health percentage */ + uint32_t gfx_health; + /* guest compute engine usage percentage */ + uint32_t compute_usage; + /* guest compute engine health percentage */ + uint32_t compute_health; + /* guest avc engine usage percentage. 0xffff means N/A */ + uint32_t avc_enc_usage; + /* guest avc engine health percentage. 0xffff means N/A */ + uint32_t avc_enc_health; + /* guest hevc engine usage percentage. 0xffff means N/A */ + uint32_t hevc_enc_usage; + /* guest hevc engine usage percentage. 0xffff means N/A */ + uint32_t hevc_enc_health; + /* combined encode/decode usage */ + uint32_t encode_usage; + uint32_t decode_usage; + /* Version of PF2VF that VF understands */ + uint32_t pf2vf_version_required; + /* additional FB usage */ + uint32_t fb_vis_usage; + uint32_t fb_vis_size; + uint32_t fb_size; + /* guest ucode data, each one is 1.25 Dword */ + struct { + uint8_t id; + uint32_t version; + } ucode_info[AMD_SRIOV_MSG_RESERVE_UCODE]; + + /* reserved */ + uint32_t reserved[256-68]; +}; + +/* mailbox message send from guest to host */ +enum amd_sriov_mailbox_request_message { + MB_REQ_MSG_REQ_GPU_INIT_ACCESS = 1, + MB_REQ_MSG_REL_GPU_INIT_ACCESS, + MB_REQ_MSG_REQ_GPU_FINI_ACCESS, + MB_REQ_MSG_REL_GPU_FINI_ACCESS, + MB_REQ_MSG_REQ_GPU_RESET_ACCESS, + MB_REQ_MSG_REQ_GPU_INIT_DATA, + + MB_REQ_MSG_LOG_VF_ERROR = 200, +}; + +/* mailbox message send from host to guest */ +enum amd_sriov_mailbox_response_message { + MB_RES_MSG_CLR_MSG_BUF = 0, + MB_RES_MSG_READY_TO_ACCESS_GPU = 1, + MB_RES_MSG_FLR_NOTIFICATION, + MB_RES_MSG_FLR_NOTIFICATION_COMPLETION, + MB_RES_MSG_SUCCESS, + MB_RES_MSG_FAIL, + MB_RES_MSG_QUERY_ALIVE, + MB_RES_MSG_GPU_INIT_DATA_READY, + + MB_RES_MSG_TEXT_MESSAGE = 255 +}; + +/* version data stored in MAILBOX_MSGBUF_RCV_DW1 for future expansion */ +enum amd_sriov_gpu_init_data_version { + GPU_INIT_DATA_READY_V1 = 1, +}; + +#pragma pack(pop) // Restore previous packing option + +/* checksum function between host and guest */ +unsigned int amd_sriov_msg_checksum(void *obj, + unsigned long obj_size, + unsigned int key, + unsigned int checksum); + +/* assertion at compile time */ +#ifdef __linux__ +#define stringification(s) _stringification(s) +#define _stringification(s) #s + +_Static_assert( + sizeof(struct amd_sriov_msg_vf2pf_info) == AMD_SRIOV_MSG_SIZE_KB << 10, + "amd_sriov_msg_vf2pf_info must be " stringification(AMD_SRIOV_MSG_SIZE_KB) " KB"); + +_Static_assert( + sizeof(struct amd_sriov_msg_pf2vf_info) == AMD_SRIOV_MSG_SIZE_KB << 10, + "amd_sriov_msg_pf2vf_info must be " stringification(AMD_SRIOV_MSG_SIZE_KB) " KB"); + +_Static_assert( + AMD_SRIOV_MSG_RESERVE_UCODE % 4 == 0, + "AMD_SRIOV_MSG_RESERVE_UCODE must be multiple of 4"); + +_Static_assert( + AMD_SRIOV_MSG_RESERVE_UCODE > AMD_SRIOV_UCODE_ID__MAX, + "AMD_SRIOV_MSG_RESERVE_UCODE must be bigger than AMD_SRIOV_UCODE_ID__MAX"); + +#undef _stringification +#undef stringification +#endif + +#endif /* AMDGV_SRIOV_MSG__H_ */ diff --git a/drivers/gpu/drm/amd/amdgpu/cik_ih.c b/drivers/gpu/drm/amd/amdgpu/cik_ih.c index 401c99f0b2d0..db953e95f3d2 100644 --- a/drivers/gpu/drm/amd/amdgpu/cik_ih.c +++ b/drivers/gpu/drm/amd/amdgpu/cik_ih.c @@ -316,14 +316,9 @@ static int cik_ih_sw_fini(void *handle) static int cik_ih_hw_init(void *handle) { - int r; struct amdgpu_device *adev = (struct amdgpu_device *)handle; - r = cik_ih_irq_init(adev); - if (r) - return r; - - return 0; + return cik_ih_irq_init(adev); } static int cik_ih_hw_fini(void *handle) diff --git a/drivers/gpu/drm/amd/amdgpu/dce_virtual.c b/drivers/gpu/drm/amd/amdgpu/dce_virtual.c index cc93577dee03..b4d4b76538d2 100644 --- a/drivers/gpu/drm/amd/amdgpu/dce_virtual.c +++ b/drivers/gpu/drm/amd/amdgpu/dce_virtual.c @@ -47,6 +47,9 @@ static void dce_virtual_set_display_funcs(struct amdgpu_device *adev); static void dce_virtual_set_irq_funcs(struct amdgpu_device *adev); static int dce_virtual_connector_encoder_init(struct amdgpu_device *adev, int index); +static int dce_virtual_pageflip(struct amdgpu_device *adev, + unsigned crtc_id); +static enum hrtimer_restart dce_virtual_vblank_timer_handle(struct hrtimer *vblank_timer); static void dce_virtual_set_crtc_vblank_interrupt_state(struct amdgpu_device *adev, int crtc, enum amdgpu_interrupt_state state); @@ -171,8 +174,10 @@ static void dce_virtual_crtc_commit(struct drm_crtc *crtc) static void dce_virtual_crtc_disable(struct drm_crtc *crtc) { struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc); + struct drm_device *dev = crtc->dev; - drm_crtc_vblank_off(crtc); + if (dev->num_crtcs) + drm_crtc_vblank_off(crtc); amdgpu_crtc->enabled = false; amdgpu_crtc->pll_id = ATOM_PPLL_INVALID; @@ -247,6 +252,11 @@ static int dce_virtual_crtc_init(struct amdgpu_device *adev, int index) amdgpu_crtc->vsync_timer_enabled = AMDGPU_IRQ_STATE_DISABLE; drm_crtc_helper_add(&amdgpu_crtc->base, &dce_virtual_crtc_helper_funcs); + hrtimer_init(&amdgpu_crtc->vblank_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); + hrtimer_set_expires(&amdgpu_crtc->vblank_timer, DCE_VIRTUAL_VBLANK_PERIOD); + amdgpu_crtc->vblank_timer.function = dce_virtual_vblank_timer_handle; + hrtimer_start(&amdgpu_crtc->vblank_timer, + DCE_VIRTUAL_VBLANK_PERIOD, HRTIMER_MODE_REL); return 0; } @@ -476,7 +486,7 @@ static int dce_virtual_hw_fini(void *handle) for (i = 0; i<adev->mode_info.num_crtc; i++) if (adev->mode_info.crtcs[i]) - dce_virtual_set_crtc_vblank_interrupt_state(adev, i, AMDGPU_IRQ_STATE_DISABLE); + hrtimer_cancel(&adev->mode_info.crtcs[i]->vblank_timer); return 0; } @@ -698,9 +708,15 @@ static enum hrtimer_restart dce_virtual_vblank_timer_handle(struct hrtimer *vbla struct amdgpu_crtc, vblank_timer); struct drm_device *ddev = amdgpu_crtc->base.dev; struct amdgpu_device *adev = drm_to_adev(ddev); + struct amdgpu_irq_src *source = adev->irq.client[AMDGPU_IRQ_CLIENTID_LEGACY].sources + [VISLANDS30_IV_SRCID_SMU_DISP_TIMER2_TRIGGER]; + int irq_type = amdgpu_display_crtc_idx_to_irq_type(adev, + amdgpu_crtc->crtc_id); - drm_handle_vblank(ddev, amdgpu_crtc->crtc_id); - dce_virtual_pageflip(adev, amdgpu_crtc->crtc_id); + if (amdgpu_irq_enabled(adev, source, irq_type)) { + drm_handle_vblank(ddev, amdgpu_crtc->crtc_id); + dce_virtual_pageflip(adev, amdgpu_crtc->crtc_id); + } hrtimer_start(vblank_timer, DCE_VIRTUAL_VBLANK_PERIOD, HRTIMER_MODE_REL); @@ -716,21 +732,6 @@ static void dce_virtual_set_crtc_vblank_interrupt_state(struct amdgpu_device *ad return; } - if (state && !adev->mode_info.crtcs[crtc]->vsync_timer_enabled) { - DRM_DEBUG("Enable software vsync timer\n"); - hrtimer_init(&adev->mode_info.crtcs[crtc]->vblank_timer, - CLOCK_MONOTONIC, HRTIMER_MODE_REL); - hrtimer_set_expires(&adev->mode_info.crtcs[crtc]->vblank_timer, - DCE_VIRTUAL_VBLANK_PERIOD); - adev->mode_info.crtcs[crtc]->vblank_timer.function = - dce_virtual_vblank_timer_handle; - hrtimer_start(&adev->mode_info.crtcs[crtc]->vblank_timer, - DCE_VIRTUAL_VBLANK_PERIOD, HRTIMER_MODE_REL); - } else if (!state && adev->mode_info.crtcs[crtc]->vsync_timer_enabled) { - DRM_DEBUG("Disable software vsync timer\n"); - hrtimer_cancel(&adev->mode_info.crtcs[crtc]->vblank_timer); - } - adev->mode_info.crtcs[crtc]->vsync_timer_enabled = state; DRM_DEBUG("[FM]set crtc %d vblank interrupt state %d\n", crtc, state); } diff --git a/drivers/gpu/drm/amd/amdgpu/df_v3_6.c b/drivers/gpu/drm/amd/amdgpu/df_v3_6.c index 2eab808fffeb..7b89fd2aa44a 100644 --- a/drivers/gpu/drm/amd/amdgpu/df_v3_6.c +++ b/drivers/gpu/drm/amd/amdgpu/df_v3_6.c @@ -455,7 +455,8 @@ static int df_v3_6_pmc_get_ctrl_settings(struct amdgpu_device *adev, uint32_t *lo_base_addr, uint32_t *hi_base_addr, uint32_t *lo_val, - uint32_t *hi_val) + uint32_t *hi_val, + bool is_enable) { uint32_t eventsel, instance, unitmask; @@ -477,7 +478,8 @@ static int df_v3_6_pmc_get_ctrl_settings(struct amdgpu_device *adev, instance_5432 = (instance >> 2) & 0xf; instance_76 = (instance >> 6) & 0x3; - *lo_val = (unitmask << 8) | (instance_10 << 6) | eventsel | (1 << 22); + *lo_val = (unitmask << 8) | (instance_10 << 6) | eventsel; + *lo_val = is_enable ? *lo_val | (1 << 22) : *lo_val & ~(1 << 22); *hi_val = (instance_76 << 29) | instance_5432; DRM_DEBUG_DRIVER("config=%llx addr=%08x:%08x val=%08x:%08x", @@ -572,14 +574,14 @@ static void df_v3_6_reset_perfmon_cntr(struct amdgpu_device *adev, } static int df_v3_6_pmc_start(struct amdgpu_device *adev, uint64_t config, - int is_enable) + int is_add) { uint32_t lo_base_addr, hi_base_addr, lo_val, hi_val; int err = 0, ret = 0; switch (adev->asic_type) { case CHIP_VEGA20: - if (is_enable) + if (is_add) return df_v3_6_pmc_add_cntr(adev, config); df_v3_6_reset_perfmon_cntr(adev, config); @@ -589,7 +591,8 @@ static int df_v3_6_pmc_start(struct amdgpu_device *adev, uint64_t config, &lo_base_addr, &hi_base_addr, &lo_val, - &hi_val); + &hi_val, + true); if (ret) return ret; @@ -612,7 +615,7 @@ static int df_v3_6_pmc_start(struct amdgpu_device *adev, uint64_t config, } static int df_v3_6_pmc_stop(struct amdgpu_device *adev, uint64_t config, - int is_disable) + int is_remove) { uint32_t lo_base_addr, hi_base_addr, lo_val, hi_val; int ret = 0; @@ -624,15 +627,17 @@ static int df_v3_6_pmc_stop(struct amdgpu_device *adev, uint64_t config, &lo_base_addr, &hi_base_addr, &lo_val, - &hi_val); + &hi_val, + false); if (ret) return ret; - df_v3_6_reset_perfmon_cntr(adev, config); - if (is_disable) + if (is_remove) { + df_v3_6_reset_perfmon_cntr(adev, config); df_v3_6_pmc_release_cntr(adev, config); + } break; default: diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c index d502e30f67d9..56fdbe626d30 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c @@ -112,6 +112,22 @@ #define mmCP_HYP_ME_UCODE_DATA 0x5817 #define mmCP_HYP_ME_UCODE_DATA_BASE_IDX 1 +//CC_GC_SA_UNIT_DISABLE +#define mmCC_GC_SA_UNIT_DISABLE 0x0fe9 +#define mmCC_GC_SA_UNIT_DISABLE_BASE_IDX 0 +#define CC_GC_SA_UNIT_DISABLE__SA_DISABLE__SHIFT 0x8 +#define CC_GC_SA_UNIT_DISABLE__SA_DISABLE_MASK 0x0000FF00L +//GC_USER_SA_UNIT_DISABLE +#define mmGC_USER_SA_UNIT_DISABLE 0x0fea +#define mmGC_USER_SA_UNIT_DISABLE_BASE_IDX 0 +#define GC_USER_SA_UNIT_DISABLE__SA_DISABLE__SHIFT 0x8 +#define GC_USER_SA_UNIT_DISABLE__SA_DISABLE_MASK 0x0000FF00L +//PA_SC_ENHANCE_3 +#define mmPA_SC_ENHANCE_3 0x1085 +#define mmPA_SC_ENHANCE_3_BASE_IDX 0 +#define PA_SC_ENHANCE_3__FORCE_PBB_WORKLOAD_MODE_TO_ZERO__SHIFT 0x3 +#define PA_SC_ENHANCE_3__FORCE_PBB_WORKLOAD_MODE_TO_ZERO_MASK 0x00000008L + MODULE_FIRMWARE("amdgpu/navi10_ce.bin"); MODULE_FIRMWARE("amdgpu/navi10_pfp.bin"); MODULE_FIRMWARE("amdgpu/navi10_me.bin"); @@ -3091,6 +3107,7 @@ static const struct soc15_reg_golden golden_settings_gc_10_3[] = SOC15_REG_GOLDEN_VALUE(GC, 0, mmGL2C_ADDR_MATCH_MASK, 0xffffffff, 0xffffffcf), SOC15_REG_GOLDEN_VALUE(GC, 0, mmGL2C_CM_CTRL1, 0xff8fff0f, 0x580f1008), SOC15_REG_GOLDEN_VALUE(GC, 0, mmGL2C_CTRL3, 0xf7ffffff, 0x10f80988), + SOC15_REG_GOLDEN_VALUE(GC, 0, mmLDS_CONFIG, 0x00000020, 0x00000020), SOC15_REG_GOLDEN_VALUE(GC, 0, mmPA_CL_ENHANCE, 0xf17fffff, 0x01200007), SOC15_REG_GOLDEN_VALUE(GC, 0, mmPA_SC_BINNER_TIMEOUT_COUNTER, 0xffffffff, 0x00000800), SOC15_REG_GOLDEN_VALUE(GC, 0, mmPA_SC_ENHANCE_2, 0xffffffbf, 0x00000820), @@ -3188,6 +3205,8 @@ static int gfx_v10_0_wait_for_rlc_autoload_complete(struct amdgpu_device *adev); static void gfx_v10_0_ring_emit_ce_meta(struct amdgpu_ring *ring, bool resume); static void gfx_v10_0_ring_emit_de_meta(struct amdgpu_ring *ring, bool resume); static void gfx_v10_0_ring_emit_frame_cntl(struct amdgpu_ring *ring, bool start, bool secure); +static u32 gfx_v10_3_get_disabled_sa(struct amdgpu_device *adev); +static void gfx_v10_3_program_pbb_mode(struct amdgpu_device *adev); static void gfx10_kiq_set_resources(struct amdgpu_ring *kiq_ring, uint64_t queue_mask) { @@ -3560,7 +3579,7 @@ static void gfx_v10_0_check_fw_write_wait(struct amdgpu_device *adev) break; } - if (adev->gfx.cp_fw_write_wait == false) + if (!adev->gfx.cp_fw_write_wait) DRM_WARN_ONCE("CP firmware version too old, please update!"); } @@ -3586,6 +3605,17 @@ static void gfx_v10_0_init_rlc_ext_microcode(struct amdgpu_device *adev) le32_to_cpu(rlc_hdr->reg_list_format_direct_reg_list_length); } +static void gfx_v10_0_init_rlc_iram_dram_microcode(struct amdgpu_device *adev) +{ + const struct rlc_firmware_header_v2_2 *rlc_hdr; + + rlc_hdr = (const struct rlc_firmware_header_v2_2 *)adev->gfx.rlc_fw->data; + adev->gfx.rlc.rlc_iram_ucode_size_bytes = le32_to_cpu(rlc_hdr->rlc_iram_ucode_size_bytes); + adev->gfx.rlc.rlc_iram_ucode = (u8 *)rlc_hdr + le32_to_cpu(rlc_hdr->rlc_iram_ucode_offset_bytes); + adev->gfx.rlc.rlc_dram_ucode_size_bytes = le32_to_cpu(rlc_hdr->rlc_dram_ucode_size_bytes); + adev->gfx.rlc.rlc_dram_ucode = (u8 *)rlc_hdr + le32_to_cpu(rlc_hdr->rlc_dram_ucode_offset_bytes); +} + static bool gfx_v10_0_navi10_gfxoff_should_enable(struct amdgpu_device *adev) { bool ret = false; @@ -3610,6 +3640,9 @@ static void gfx_v10_0_check_gfxoff_flag(struct amdgpu_device *adev) if (!gfx_v10_0_navi10_gfxoff_should_enable(adev)) adev->pm.pp_feature &= ~PP_GFXOFF_MASK; break; + case CHIP_NAVY_FLOUNDER: + adev->pm.pp_feature &= ~PP_GFXOFF_MASK; + break; default: break; } @@ -3698,8 +3731,6 @@ static int gfx_v10_0_init_microcode(struct amdgpu_device *adev) rlc_hdr = (const struct rlc_firmware_header_v2_0 *)adev->gfx.rlc_fw->data; version_major = le16_to_cpu(rlc_hdr->header.header_version_major); version_minor = le16_to_cpu(rlc_hdr->header.header_version_minor); - if (version_major == 2 && version_minor == 1) - adev->gfx.rlc.is_rlc_v2_1 = true; adev->gfx.rlc_fw_version = le32_to_cpu(rlc_hdr->header.ucode_version); adev->gfx.rlc_feature_version = le32_to_cpu(rlc_hdr->ucode_feature_version); @@ -3741,8 +3772,12 @@ static int gfx_v10_0_init_microcode(struct amdgpu_device *adev) for (i = 0 ; i < (rlc_hdr->reg_list_size_bytes >> 2); i++) adev->gfx.rlc.register_restore[i] = le32_to_cpu(tmp[i]); - if (adev->gfx.rlc.is_rlc_v2_1) - gfx_v10_0_init_rlc_ext_microcode(adev); + if (version_major == 2) { + if (version_minor >= 1) + gfx_v10_0_init_rlc_ext_microcode(adev); + if (version_minor == 2) + gfx_v10_0_init_rlc_iram_dram_microcode(adev); + } } snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_mec%s.bin", chip_name, wks); @@ -3803,8 +3838,7 @@ static int gfx_v10_0_init_microcode(struct amdgpu_device *adev) adev->firmware.fw_size += ALIGN(le32_to_cpu(header->ucode_size_bytes), PAGE_SIZE); } - if (adev->gfx.rlc.is_rlc_v2_1 && - adev->gfx.rlc.save_restore_list_cntl_size_bytes && + if (adev->gfx.rlc.save_restore_list_cntl_size_bytes && adev->gfx.rlc.save_restore_list_gpm_size_bytes && adev->gfx.rlc.save_restore_list_srm_size_bytes) { info = &adev->firmware.ucode[AMDGPU_UCODE_ID_RLC_RESTORE_LIST_CNTL]; @@ -3824,6 +3858,21 @@ static int gfx_v10_0_init_microcode(struct amdgpu_device *adev) info->fw = adev->gfx.rlc_fw; adev->firmware.fw_size += ALIGN(adev->gfx.rlc.save_restore_list_srm_size_bytes, PAGE_SIZE); + + if (adev->gfx.rlc.rlc_iram_ucode_size_bytes && + adev->gfx.rlc.rlc_dram_ucode_size_bytes) { + info = &adev->firmware.ucode[AMDGPU_UCODE_ID_RLC_IRAM]; + info->ucode_id = AMDGPU_UCODE_ID_RLC_IRAM; + info->fw = adev->gfx.rlc_fw; + adev->firmware.fw_size += + ALIGN(adev->gfx.rlc.rlc_iram_ucode_size_bytes, PAGE_SIZE); + + info = &adev->firmware.ucode[AMDGPU_UCODE_ID_RLC_DRAM]; + info->ucode_id = AMDGPU_UCODE_ID_RLC_DRAM; + info->fw = adev->gfx.rlc_fw; + adev->firmware.fw_size += + ALIGN(adev->gfx.rlc.rlc_dram_ucode_size_bytes, PAGE_SIZE); + } } info = &adev->firmware.ucode[AMDGPU_UCODE_ID_CP_MEC1]; @@ -4533,12 +4582,17 @@ static void gfx_v10_0_setup_rb(struct amdgpu_device *adev) int i, j; u32 data; u32 active_rbs = 0; + u32 bitmap; u32 rb_bitmap_width_per_sh = adev->gfx.config.max_backends_per_se / adev->gfx.config.max_sh_per_se; mutex_lock(&adev->grbm_idx_mutex); for (i = 0; i < adev->gfx.config.max_shader_engines; i++) { for (j = 0; j < adev->gfx.config.max_sh_per_se; j++) { + bitmap = i * adev->gfx.config.max_sh_per_se + j; + if ((adev->asic_type == CHIP_SIENNA_CICHLID) && + ((gfx_v10_3_get_disabled_sa(adev) >> bitmap) & 1)) + continue; gfx_v10_0_select_se_sh(adev, i, j, 0xffffffff); data = gfx_v10_0_get_rb_active_bitmap(adev); active_rbs |= data << ((i * adev->gfx.config.max_sh_per_se + j) * @@ -6947,6 +7001,9 @@ static int gfx_v10_0_hw_init(void *handle) if (r) return r; + if (adev->asic_type == CHIP_SIENNA_CICHLID) + gfx_v10_3_program_pbb_mode(adev); + return r; } @@ -6980,15 +7037,19 @@ static int gfx_v10_0_hw_fini(void *handle) amdgpu_irq_put(adev, &adev->gfx.priv_reg_irq, 0); amdgpu_irq_put(adev, &adev->gfx.priv_inst_irq, 0); + + if (!adev->in_pci_err_recovery) { #ifndef BRING_UP_DEBUG - if (amdgpu_async_gfx_ring) { - r = gfx_v10_0_kiq_disable_kgq(adev); - if (r) - DRM_ERROR("KGQ disable failed\n"); - } + if (amdgpu_async_gfx_ring) { + r = gfx_v10_0_kiq_disable_kgq(adev); + if (r) + DRM_ERROR("KGQ disable failed\n"); + } #endif - if (amdgpu_gfx_disable_kcq(adev)) - DRM_ERROR("KCQ disable failed\n"); + if (amdgpu_gfx_disable_kcq(adev)) + DRM_ERROR("KCQ disable failed\n"); + } + if (amdgpu_sriov_vf(adev)) { gfx_v10_0_cp_gfx_enable(adev, false); /* Program KIQ position of RLC_CP_SCHEDULERS during destroy */ @@ -8756,6 +8817,10 @@ static int gfx_v10_0_get_cu_info(struct amdgpu_device *adev, mutex_lock(&adev->grbm_idx_mutex); for (i = 0; i < adev->gfx.config.max_shader_engines; i++) { for (j = 0; j < adev->gfx.config.max_sh_per_se; j++) { + bitmap = i * adev->gfx.config.max_sh_per_se + j; + if ((adev->asic_type == CHIP_SIENNA_CICHLID) && + ((gfx_v10_3_get_disabled_sa(adev) >> bitmap) & 1)) + continue; mask = 1; ao_bitmap = 0; counter = 0; @@ -8790,6 +8855,47 @@ static int gfx_v10_0_get_cu_info(struct amdgpu_device *adev, return 0; } +static u32 gfx_v10_3_get_disabled_sa(struct amdgpu_device *adev) +{ + uint32_t efuse_setting, vbios_setting, disabled_sa, max_sa_mask; + + efuse_setting = RREG32_SOC15(GC, 0, mmCC_GC_SA_UNIT_DISABLE); + efuse_setting &= CC_GC_SA_UNIT_DISABLE__SA_DISABLE_MASK; + efuse_setting >>= CC_GC_SA_UNIT_DISABLE__SA_DISABLE__SHIFT; + + vbios_setting = RREG32_SOC15(GC, 0, mmGC_USER_SA_UNIT_DISABLE); + vbios_setting &= GC_USER_SA_UNIT_DISABLE__SA_DISABLE_MASK; + vbios_setting >>= GC_USER_SA_UNIT_DISABLE__SA_DISABLE__SHIFT; + + max_sa_mask = amdgpu_gfx_create_bitmask(adev->gfx.config.max_sh_per_se * + adev->gfx.config.max_shader_engines); + disabled_sa = efuse_setting | vbios_setting; + disabled_sa &= max_sa_mask; + + return disabled_sa; +} + +static void gfx_v10_3_program_pbb_mode(struct amdgpu_device *adev) +{ + uint32_t max_sa_per_se, max_sa_per_se_mask, max_shader_engines; + uint32_t disabled_sa_mask, se_index, disabled_sa_per_se; + + disabled_sa_mask = gfx_v10_3_get_disabled_sa(adev); + + max_sa_per_se = adev->gfx.config.max_sh_per_se; + max_sa_per_se_mask = (1 << max_sa_per_se) - 1; + max_shader_engines = adev->gfx.config.max_shader_engines; + + for (se_index = 0; max_shader_engines > se_index; se_index++) { + disabled_sa_per_se = disabled_sa_mask >> (se_index * max_sa_per_se); + disabled_sa_per_se &= max_sa_per_se_mask; + if (disabled_sa_per_se == max_sa_per_se_mask) { + WREG32_FIELD15(GC, 0, PA_SC_ENHANCE_3, FORCE_PBB_WORKLOAD_MODE_TO_ZERO, 1); + break; + } + } +} + const struct amdgpu_ip_block_version gfx_v10_0_ip_block = { .type = AMD_IP_BLOCK_TYPE_GFX, diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c index 93c63ff3b35e..6959aebae6d4 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c @@ -49,6 +49,7 @@ #include "amdgpu_ras.h" #include "gfx_v9_4.h" +#include "gfx_v9_0.h" #include "asic_reg/pwr/pwr_10_0_offset.h" #include "asic_reg/pwr/pwr_10_0_sh_mask.h" @@ -788,7 +789,6 @@ static void gfx_v9_0_set_rlc_funcs(struct amdgpu_device *adev); static int gfx_v9_0_get_cu_info(struct amdgpu_device *adev, struct amdgpu_cu_info *cu_info); static uint64_t gfx_v9_0_get_gpu_clock_counter(struct amdgpu_device *adev); -static void gfx_v9_0_select_se_sh(struct amdgpu_device *adev, u32 se_num, u32 sh_num, u32 instance); static void gfx_v9_0_ring_emit_de_meta(struct amdgpu_ring *ring); static u64 gfx_v9_0_ring_get_rptr_compute(struct amdgpu_ring *ring); static int gfx_v9_0_query_ras_error_count(struct amdgpu_device *adev, @@ -2075,6 +2075,7 @@ static const struct amdgpu_gfx_funcs gfx_v9_4_gfx_funcs = { .ras_error_inject = &gfx_v9_4_ras_error_inject, .query_ras_error_count = &gfx_v9_4_query_ras_error_count, .reset_ras_error_count = &gfx_v9_4_reset_ras_error_count, + .query_ras_error_status = &gfx_v9_4_query_ras_error_status, }; static int gfx_v9_0_gpu_early_init(struct amdgpu_device *adev) @@ -2196,7 +2197,6 @@ static int gfx_v9_0_gpu_early_init(struct amdgpu_device *adev) static int gfx_v9_0_compute_ring_init(struct amdgpu_device *adev, int ring_id, int mec, int pipe, int queue) { - int r; unsigned irq_type; struct amdgpu_ring *ring = &adev->gfx.compute_ring[ring_id]; unsigned int hw_prio; @@ -2221,13 +2221,8 @@ static int gfx_v9_0_compute_ring_init(struct amdgpu_device *adev, int ring_id, hw_prio = amdgpu_gfx_is_high_priority_compute_queue(adev, ring->queue) ? AMDGPU_GFX_PIPE_PRIO_HIGH : AMDGPU_GFX_PIPE_PRIO_NORMAL; /* type-2 packets are deprecated on MEC, use type-3 instead */ - r = amdgpu_ring_init(adev, ring, 1024, - &adev->gfx.eop_irq, irq_type, hw_prio); - if (r) - return r; - - - return 0; + return amdgpu_ring_init(adev, ring, 1024, + &adev->gfx.eop_irq, irq_type, hw_prio); } static int gfx_v9_0_sw_init(void *handle) @@ -2402,7 +2397,8 @@ static void gfx_v9_0_tiling_mode_table_init(struct amdgpu_device *adev) /* TODO */ } -static void gfx_v9_0_select_se_sh(struct amdgpu_device *adev, u32 se_num, u32 sh_num, u32 instance) +void gfx_v9_0_select_se_sh(struct amdgpu_device *adev, u32 se_num, u32 sh_num, + u32 instance) { u32 data; @@ -2560,14 +2556,14 @@ static void gfx_v9_0_constants_init(struct amdgpu_device *adev) tmp = REG_SET_FIELD(0, SH_MEM_CONFIG, ALIGNMENT_MODE, SH_MEM_ALIGNMENT_MODE_UNALIGNED); tmp = REG_SET_FIELD(tmp, SH_MEM_CONFIG, RETRY_DISABLE, - !!amdgpu_noretry); + !!adev->gmc.noretry); WREG32_SOC15_RLC(GC, 0, mmSH_MEM_CONFIG, tmp); WREG32_SOC15_RLC(GC, 0, mmSH_MEM_BASES, 0); } else { tmp = REG_SET_FIELD(0, SH_MEM_CONFIG, ALIGNMENT_MODE, SH_MEM_ALIGNMENT_MODE_UNALIGNED); tmp = REG_SET_FIELD(tmp, SH_MEM_CONFIG, RETRY_DISABLE, - !!amdgpu_noretry); + !!adev->gmc.noretry); WREG32_SOC15_RLC(GC, 0, mmSH_MEM_CONFIG, tmp); tmp = REG_SET_FIELD(0, SH_MEM_BASES, PRIVATE_BASE, (adev->gmc.private_aperture_start >> 48)); @@ -2800,7 +2796,7 @@ static void pwr_10_0_gfxip_control_over_cgpg(struct amdgpu_device *adev, uint32_t default_data = 0; default_data = data = RREG32(SOC15_REG_OFFSET(PWR, 0, mmPWR_MISC_CNTL_STATUS)); - if (enable == true) { + if (enable) { /* enable GFXIP control over CGPG */ data |= PWR_MISC_CNTL_STATUS__PWR_GFX_RLC_CGPG_EN_MASK; if(default_data != data) diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.h b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.h index fa5a3fbaf6ab..dfe8d4841f58 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.h +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.h @@ -26,9 +26,7 @@ extern const struct amdgpu_ip_block_version gfx_v9_0_ip_block; -void gfx_v9_0_select_se_sh(struct amdgpu_device *adev, u32 se_num, u32 sh_num); - -uint64_t gfx_v9_0_get_gpu_clock_counter(struct amdgpu_device *adev); -int gfx_v9_0_get_cu_info(struct amdgpu_device *adev, struct amdgpu_cu_info *cu_info); +void gfx_v9_0_select_se_sh(struct amdgpu_device *adev, u32 se_num, u32 sh_num, + u32 instance); #endif diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_4.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_4.c index bd85aed3523a..bc699d680ce8 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_4.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_4.c @@ -992,3 +992,32 @@ int gfx_v9_4_ras_error_inject(struct amdgpu_device *adev, void *inject_if) return ret; } + +static const struct soc15_reg_entry gfx_v9_4_rdrsp_status_regs = + { SOC15_REG_ENTRY(GC, 0, mmGCEA_ERR_STATUS), 0, 1, 32 }; + +void gfx_v9_4_query_ras_error_status(struct amdgpu_device *adev) +{ + uint32_t i, j; + uint32_t reg_value; + + if (!amdgpu_ras_is_supported(adev, AMDGPU_RAS_BLOCK__GFX)) + return; + + mutex_lock(&adev->grbm_idx_mutex); + + for (i = 0; i < gfx_v9_4_rdrsp_status_regs.se_num; i++) { + for (j = 0; j < gfx_v9_4_rdrsp_status_regs.instance; + j++) { + gfx_v9_4_select_se_sh(adev, i, 0, j); + reg_value = RREG32(SOC15_REG_ENTRY_OFFSET( + gfx_v9_4_rdrsp_status_regs)); + if (reg_value) + dev_warn(adev->dev, "GCEA err detected at instance: %d, status: 0x%x!\n", + j, reg_value); + } + } + + gfx_v9_4_select_se_sh(adev, 0xffffffff, 0xffffffff, 0xffffffff); + mutex_unlock(&adev->grbm_idx_mutex); +} diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_4.h b/drivers/gpu/drm/amd/amdgpu/gfx_v9_4.h index 1ffecc5c0f0a..875f18473a98 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_4.h +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_4.h @@ -34,4 +34,6 @@ int gfx_v9_4_ras_error_inject(struct amdgpu_device *adev, void gfx_v9_4_reset_ras_error_count(struct amdgpu_device *adev); +void gfx_v9_4_query_ras_error_status(struct amdgpu_device *adev); + #endif /* __GFX_V9_4_H__ */ diff --git a/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.c b/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.c index 529e46386a50..fad887a66886 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.c @@ -245,7 +245,7 @@ static void gfxhub_v1_0_setup_vmid_config(struct amdgpu_device *adev) /* Send no-retry XNACK on fault to suppress VM fault storm. */ tmp = REG_SET_FIELD(tmp, VM_CONTEXT1_CNTL, RETRY_PERMISSION_OR_INVALID_PAGE_FAULT, - !amdgpu_noretry); + !adev->gmc.noretry); WREG32_SOC15_OFFSET(GC, 0, mmVM_CONTEXT1_CNTL, i * hub->ctx_distance, tmp); WREG32_SOC15_OFFSET(GC, 0, mmVM_CONTEXT1_PAGE_TABLE_START_ADDR_LO32, @@ -403,3 +403,13 @@ void gfxhub_v1_0_init(struct amdgpu_device *adev) hub->eng_addr_distance = mmVM_INVALIDATE_ENG1_ADDR_RANGE_LO32 - mmVM_INVALIDATE_ENG0_ADDR_RANGE_LO32; } + + +const struct amdgpu_gfxhub_funcs gfxhub_v1_0_funcs = { + .get_mc_fb_offset = gfxhub_v1_0_get_mc_fb_offset, + .setup_vm_pt_regs = gfxhub_v1_0_setup_vm_pt_regs, + .gart_enable = gfxhub_v1_0_gart_enable, + .gart_disable = gfxhub_v1_0_gart_disable, + .set_fault_enable_default = gfxhub_v1_0_set_fault_enable_default, + .init = gfxhub_v1_0_init, +}; diff --git a/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.h b/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.h index 92d3a70cd9b1..0c46672bbf49 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.h +++ b/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.h @@ -33,4 +33,5 @@ u64 gfxhub_v1_0_get_mc_fb_offset(struct amdgpu_device *adev); void gfxhub_v1_0_setup_vm_pt_regs(struct amdgpu_device *adev, uint32_t vmid, uint64_t page_table_base); +extern const struct amdgpu_gfxhub_funcs gfxhub_v1_0_funcs; #endif diff --git a/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_1.c b/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_1.c index c0ab71df0d90..1e24b6d51e41 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_1.c +++ b/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_1.c @@ -21,6 +21,7 @@ * */ #include "amdgpu.h" +#include "gfxhub_v1_0.h" #include "gfxhub_v1_1.h" #include "gc/gc_9_2_1_offset.h" @@ -28,7 +29,7 @@ #include "soc15_common.h" -int gfxhub_v1_1_get_xgmi_info(struct amdgpu_device *adev) +static int gfxhub_v1_1_get_xgmi_info(struct amdgpu_device *adev) { u32 xgmi_lfb_cntl = RREG32_SOC15(GC, 0, mmMC_VM_XGMI_LFB_CNTL); u32 max_region = @@ -66,3 +67,13 @@ int gfxhub_v1_1_get_xgmi_info(struct amdgpu_device *adev) return 0; } + +const struct amdgpu_gfxhub_funcs gfxhub_v1_1_funcs = { + .get_mc_fb_offset = gfxhub_v1_0_get_mc_fb_offset, + .setup_vm_pt_regs = gfxhub_v1_0_setup_vm_pt_regs, + .gart_enable = gfxhub_v1_0_gart_enable, + .gart_disable = gfxhub_v1_0_gart_disable, + .set_fault_enable_default = gfxhub_v1_0_set_fault_enable_default, + .init = gfxhub_v1_0_init, + .get_xgmi_info = gfxhub_v1_1_get_xgmi_info, +}; diff --git a/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_1.h b/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_1.h index d753cf28a0a6..ae5759ffbee3 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_1.h +++ b/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_1.h @@ -24,6 +24,6 @@ #ifndef __GFXHUB_V1_1_H__ #define __GFXHUB_V1_1_H__ -int gfxhub_v1_1_get_xgmi_info(struct amdgpu_device *adev); +extern const struct amdgpu_gfxhub_funcs gfxhub_v1_1_funcs; #endif diff --git a/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_0.c b/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_0.c index b882ac59879a..456360bf58fa 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_0.c @@ -102,7 +102,7 @@ gfxhub_v2_0_print_l2_protection_fault_status(struct amdgpu_device *adev, GCVM_L2_PROTECTION_FAULT_STATUS, RW)); } -u64 gfxhub_v2_0_get_fb_location(struct amdgpu_device *adev) +static u64 gfxhub_v2_0_get_fb_location(struct amdgpu_device *adev) { u64 base = RREG32_SOC15(GC, 0, mmGCMC_VM_FB_LOCATION_BASE); @@ -112,12 +112,12 @@ u64 gfxhub_v2_0_get_fb_location(struct amdgpu_device *adev) return base; } -u64 gfxhub_v2_0_get_mc_fb_offset(struct amdgpu_device *adev) +static u64 gfxhub_v2_0_get_mc_fb_offset(struct amdgpu_device *adev) { return (u64)RREG32_SOC15(GC, 0, mmGCMC_VM_FB_OFFSET) << 24; } -void gfxhub_v2_0_setup_vm_pt_regs(struct amdgpu_device *adev, uint32_t vmid, +static void gfxhub_v2_0_setup_vm_pt_regs(struct amdgpu_device *adev, uint32_t vmid, uint64_t page_table_base) { struct amdgpu_vmhub *hub = &adev->vmhub[AMDGPU_GFXHUB_0]; @@ -153,11 +153,6 @@ static void gfxhub_v2_0_init_system_aperture_regs(struct amdgpu_device *adev) uint64_t value; if (!amdgpu_sriov_vf(adev)) { - /* - * the new L1 policy will block SRIOV guest from writing - * these regs, and they will be programed at host. - * so skip programing these regs. - */ /* Disable AGP. */ WREG32_SOC15(GC, 0, mmGCMC_VM_AGP_BASE, 0); WREG32_SOC15(GC, 0, mmGCMC_VM_AGP_TOP, 0); @@ -318,7 +313,7 @@ static void gfxhub_v2_0_setup_vmid_config(struct amdgpu_device *adev) /* Send no-retry XNACK on fault to suppress VM fault storm. */ tmp = REG_SET_FIELD(tmp, GCVM_CONTEXT1_CNTL, RETRY_PERMISSION_OR_INVALID_PAGE_FAULT, - !amdgpu_noretry); + !adev->gmc.noretry); WREG32_SOC15_OFFSET(GC, 0, mmGCVM_CONTEXT1_CNTL, i * hub->ctx_distance, tmp); WREG32_SOC15_OFFSET(GC, 0, mmGCVM_CONTEXT1_PAGE_TABLE_START_ADDR_LO32, @@ -347,7 +342,7 @@ static void gfxhub_v2_0_program_invalidation(struct amdgpu_device *adev) } } -int gfxhub_v2_0_gart_enable(struct amdgpu_device *adev) +static int gfxhub_v2_0_gart_enable(struct amdgpu_device *adev) { /* GART Enable. */ gfxhub_v2_0_init_gart_aperture_regs(adev); @@ -363,7 +358,7 @@ int gfxhub_v2_0_gart_enable(struct amdgpu_device *adev) return 0; } -void gfxhub_v2_0_gart_disable(struct amdgpu_device *adev) +static void gfxhub_v2_0_gart_disable(struct amdgpu_device *adev) { struct amdgpu_vmhub *hub = &adev->vmhub[AMDGPU_GFXHUB_0]; u32 tmp; @@ -394,7 +389,7 @@ void gfxhub_v2_0_gart_disable(struct amdgpu_device *adev) * @adev: amdgpu_device pointer * @value: true redirects VM faults to the default page */ -void gfxhub_v2_0_set_fault_enable_default(struct amdgpu_device *adev, +static void gfxhub_v2_0_set_fault_enable_default(struct amdgpu_device *adev, bool value) { u32 tmp; @@ -436,7 +431,7 @@ static const struct amdgpu_vmhub_funcs gfxhub_v2_0_vmhub_funcs = { .get_invalidate_req = gfxhub_v2_0_get_invalidate_req, }; -void gfxhub_v2_0_init(struct amdgpu_device *adev) +static void gfxhub_v2_0_init(struct amdgpu_device *adev) { struct amdgpu_vmhub *hub = &adev->vmhub[AMDGPU_GFXHUB_0]; @@ -477,3 +472,13 @@ void gfxhub_v2_0_init(struct amdgpu_device *adev) hub->vmhub_funcs = &gfxhub_v2_0_vmhub_funcs; } + +const struct amdgpu_gfxhub_funcs gfxhub_v2_0_funcs = { + .get_fb_location = gfxhub_v2_0_get_fb_location, + .get_mc_fb_offset = gfxhub_v2_0_get_mc_fb_offset, + .setup_vm_pt_regs = gfxhub_v2_0_setup_vm_pt_regs, + .gart_enable = gfxhub_v2_0_gart_enable, + .gart_disable = gfxhub_v2_0_gart_disable, + .set_fault_enable_default = gfxhub_v2_0_set_fault_enable_default, + .init = gfxhub_v2_0_init, +}; diff --git a/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_0.h b/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_0.h index 392b8cd94fc0..9ddc35cd53d4 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_0.h +++ b/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_0.h @@ -24,14 +24,6 @@ #ifndef __GFXHUB_V2_0_H__ #define __GFXHUB_V2_0_H__ -u64 gfxhub_v2_0_get_fb_location(struct amdgpu_device *adev); -int gfxhub_v2_0_gart_enable(struct amdgpu_device *adev); -void gfxhub_v2_0_gart_disable(struct amdgpu_device *adev); -void gfxhub_v2_0_set_fault_enable_default(struct amdgpu_device *adev, - bool value); -void gfxhub_v2_0_init(struct amdgpu_device *adev); -u64 gfxhub_v2_0_get_mc_fb_offset(struct amdgpu_device *adev); -void gfxhub_v2_0_setup_vm_pt_regs(struct amdgpu_device *adev, uint32_t vmid, - uint64_t page_table_base); +extern const struct amdgpu_gfxhub_funcs gfxhub_v2_0_funcs; #endif diff --git a/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_1.c b/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_1.c index 237a9ff5afa0..724bb29e9bb4 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_1.c +++ b/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_1.c @@ -102,7 +102,7 @@ gfxhub_v2_1_print_l2_protection_fault_status(struct amdgpu_device *adev, GCVM_L2_PROTECTION_FAULT_STATUS, RW)); } -u64 gfxhub_v2_1_get_fb_location(struct amdgpu_device *adev) +static u64 gfxhub_v2_1_get_fb_location(struct amdgpu_device *adev) { u64 base = RREG32_SOC15(GC, 0, mmGCMC_VM_FB_LOCATION_BASE); @@ -112,12 +112,12 @@ u64 gfxhub_v2_1_get_fb_location(struct amdgpu_device *adev) return base; } -u64 gfxhub_v2_1_get_mc_fb_offset(struct amdgpu_device *adev) +static u64 gfxhub_v2_1_get_mc_fb_offset(struct amdgpu_device *adev) { return (u64)RREG32_SOC15(GC, 0, mmGCMC_VM_FB_OFFSET) << 24; } -void gfxhub_v2_1_setup_vm_pt_regs(struct amdgpu_device *adev, uint32_t vmid, +static void gfxhub_v2_1_setup_vm_pt_regs(struct amdgpu_device *adev, uint32_t vmid, uint64_t page_table_base) { struct amdgpu_vmhub *hub = &adev->vmhub[AMDGPU_GFXHUB_0]; @@ -319,7 +319,7 @@ static void gfxhub_v2_1_setup_vmid_config(struct amdgpu_device *adev) /* Send no-retry XNACK on fault to suppress VM fault storm. */ tmp = REG_SET_FIELD(tmp, GCVM_CONTEXT1_CNTL, RETRY_PERMISSION_OR_INVALID_PAGE_FAULT, - !amdgpu_noretry); + !adev->gmc.noretry); WREG32_SOC15_OFFSET(GC, 0, mmGCVM_CONTEXT1_CNTL, i * hub->ctx_distance, tmp); WREG32_SOC15_OFFSET(GC, 0, mmGCVM_CONTEXT1_PAGE_TABLE_START_ADDR_LO32, @@ -348,7 +348,7 @@ static void gfxhub_v2_1_program_invalidation(struct amdgpu_device *adev) } } -int gfxhub_v2_1_gart_enable(struct amdgpu_device *adev) +static int gfxhub_v2_1_gart_enable(struct amdgpu_device *adev) { if (amdgpu_sriov_vf(adev)) { /* @@ -376,7 +376,7 @@ int gfxhub_v2_1_gart_enable(struct amdgpu_device *adev) return 0; } -void gfxhub_v2_1_gart_disable(struct amdgpu_device *adev) +static void gfxhub_v2_1_gart_disable(struct amdgpu_device *adev) { struct amdgpu_vmhub *hub = &adev->vmhub[AMDGPU_GFXHUB_0]; u32 tmp; @@ -405,7 +405,7 @@ void gfxhub_v2_1_gart_disable(struct amdgpu_device *adev) * @adev: amdgpu_device pointer * @value: true redirects VM faults to the default page */ -void gfxhub_v2_1_set_fault_enable_default(struct amdgpu_device *adev, +static void gfxhub_v2_1_set_fault_enable_default(struct amdgpu_device *adev, bool value) { u32 tmp; @@ -454,7 +454,7 @@ static const struct amdgpu_vmhub_funcs gfxhub_v2_1_vmhub_funcs = { .get_invalidate_req = gfxhub_v2_1_get_invalidate_req, }; -void gfxhub_v2_1_init(struct amdgpu_device *adev) +static void gfxhub_v2_1_init(struct amdgpu_device *adev) { struct amdgpu_vmhub *hub = &adev->vmhub[AMDGPU_GFXHUB_0]; @@ -496,7 +496,7 @@ void gfxhub_v2_1_init(struct amdgpu_device *adev) hub->vmhub_funcs = &gfxhub_v2_1_vmhub_funcs; } -int gfxhub_v2_1_get_xgmi_info(struct amdgpu_device *adev) +static int gfxhub_v2_1_get_xgmi_info(struct amdgpu_device *adev) { u32 xgmi_lfb_cntl = RREG32_SOC15(GC, 0, mmGCMC_VM_XGMI_LFB_CNTL); u32 max_region = @@ -531,3 +531,14 @@ int gfxhub_v2_1_get_xgmi_info(struct amdgpu_device *adev) return 0; } + +const struct amdgpu_gfxhub_funcs gfxhub_v2_1_funcs = { + .get_fb_location = gfxhub_v2_1_get_fb_location, + .get_mc_fb_offset = gfxhub_v2_1_get_mc_fb_offset, + .setup_vm_pt_regs = gfxhub_v2_1_setup_vm_pt_regs, + .gart_enable = gfxhub_v2_1_gart_enable, + .gart_disable = gfxhub_v2_1_gart_disable, + .set_fault_enable_default = gfxhub_v2_1_set_fault_enable_default, + .init = gfxhub_v2_1_init, + .get_xgmi_info = gfxhub_v2_1_get_xgmi_info, +}; diff --git a/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_1.h b/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_1.h index 3452a4e9a3da..f75c2eccfad9 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_1.h +++ b/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_1.h @@ -24,16 +24,6 @@ #ifndef __GFXHUB_V2_1_H__ #define __GFXHUB_V2_1_H__ -u64 gfxhub_v2_1_get_fb_location(struct amdgpu_device *adev); -int gfxhub_v2_1_gart_enable(struct amdgpu_device *adev); -void gfxhub_v2_1_gart_disable(struct amdgpu_device *adev); -void gfxhub_v2_1_set_fault_enable_default(struct amdgpu_device *adev, - bool value); -void gfxhub_v2_1_init(struct amdgpu_device *adev); -u64 gfxhub_v2_1_get_mc_fb_offset(struct amdgpu_device *adev); -void gfxhub_v2_1_setup_vm_pt_regs(struct amdgpu_device *adev, uint32_t vmid, - uint64_t page_table_base); - -int gfxhub_v2_1_get_xgmi_info(struct amdgpu_device *adev); +extern const struct amdgpu_gfxhub_funcs gfxhub_v2_1_funcs; #endif diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c index 31359e519d69..dbc8b76b9b78 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c @@ -634,11 +634,26 @@ static void gmc_v10_0_set_mmhub_funcs(struct amdgpu_device *adev) adev->mmhub.funcs = &mmhub_v2_0_funcs; } +static void gmc_v10_0_set_gfxhub_funcs(struct amdgpu_device *adev) +{ + switch (adev->asic_type) { + case CHIP_SIENNA_CICHLID: + case CHIP_NAVY_FLOUNDER: + adev->gfxhub.funcs = &gfxhub_v2_1_funcs; + break; + default: + adev->gfxhub.funcs = &gfxhub_v2_0_funcs; + break; + } +} + + static int gmc_v10_0_early_init(void *handle) { struct amdgpu_device *adev = (struct amdgpu_device *)handle; gmc_v10_0_set_mmhub_funcs(adev); + gmc_v10_0_set_gfxhub_funcs(adev); gmc_v10_0_set_gmc_funcs(adev); gmc_v10_0_set_irq_funcs(adev); gmc_v10_0_set_umc_funcs(adev); @@ -676,11 +691,7 @@ static void gmc_v10_0_vram_gtt_location(struct amdgpu_device *adev, { u64 base = 0; - if (adev->asic_type == CHIP_SIENNA_CICHLID || - adev->asic_type == CHIP_NAVY_FLOUNDER) - base = gfxhub_v2_1_get_fb_location(adev); - else - base = gfxhub_v2_0_get_fb_location(adev); + base = adev->gfxhub.funcs->get_fb_location(adev); /* add the xgmi offset of the physical node */ base += adev->gmc.xgmi.physical_node_id * adev->gmc.xgmi.node_segment_size; @@ -689,11 +700,7 @@ static void gmc_v10_0_vram_gtt_location(struct amdgpu_device *adev, amdgpu_gmc_gart_location(adev, mc); /* base offset of vram pages */ - if (adev->asic_type == CHIP_SIENNA_CICHLID || - adev->asic_type == CHIP_NAVY_FLOUNDER) - adev->vm_manager.vram_base_offset = gfxhub_v2_1_get_mc_fb_offset(adev); - else - adev->vm_manager.vram_base_offset = gfxhub_v2_0_get_mc_fb_offset(adev); + adev->vm_manager.vram_base_offset = adev->gfxhub.funcs->get_mc_fb_offset(adev); /* add the xgmi offset of the physical node */ adev->vm_manager.vram_base_offset += @@ -777,11 +784,7 @@ static int gmc_v10_0_sw_init(void *handle) int r, vram_width = 0, vram_type = 0, vram_vendor = 0; struct amdgpu_device *adev = (struct amdgpu_device *)handle; - if (adev->asic_type == CHIP_SIENNA_CICHLID || - adev->asic_type == CHIP_NAVY_FLOUNDER) - gfxhub_v2_1_init(adev); - else - gfxhub_v2_0_init(adev); + adev->gfxhub.funcs->init(adev); adev->mmhub.funcs->init(adev); @@ -852,7 +855,7 @@ static int gmc_v10_0_sw_init(void *handle) } if (adev->gmc.xgmi.supported) { - r = gfxhub_v2_1_get_xgmi_info(adev); + r = adev->gfxhub.funcs->get_xgmi_info(adev); if (r) return r; } @@ -944,11 +947,7 @@ static int gmc_v10_0_gart_enable(struct amdgpu_device *adev) if (r) return r; - if (adev->asic_type == CHIP_SIENNA_CICHLID || - adev->asic_type == CHIP_NAVY_FLOUNDER) - r = gfxhub_v2_1_gart_enable(adev); - else - r = gfxhub_v2_0_gart_enable(adev); + r = adev->gfxhub.funcs->gart_enable(adev); if (r) return r; @@ -969,11 +968,7 @@ static int gmc_v10_0_gart_enable(struct amdgpu_device *adev) value = (amdgpu_vm_fault_stop == AMDGPU_VM_FAULT_STOP_ALWAYS) ? false : true; - if (adev->asic_type == CHIP_SIENNA_CICHLID || - adev->asic_type == CHIP_NAVY_FLOUNDER) - gfxhub_v2_1_set_fault_enable_default(adev, value); - else - gfxhub_v2_0_set_fault_enable_default(adev, value); + adev->gfxhub.funcs->set_fault_enable_default(adev, value); adev->mmhub.funcs->set_fault_enable_default(adev, value); gmc_v10_0_flush_gpu_tlb(adev, 0, AMDGPU_MMHUB_0, 0); gmc_v10_0_flush_gpu_tlb(adev, 0, AMDGPU_GFXHUB_0, 0); @@ -1014,11 +1009,7 @@ static int gmc_v10_0_hw_init(void *handle) */ static void gmc_v10_0_gart_disable(struct amdgpu_device *adev) { - if (adev->asic_type == CHIP_SIENNA_CICHLID || - adev->asic_type == CHIP_NAVY_FLOUNDER) - gfxhub_v2_1_gart_disable(adev); - else - gfxhub_v2_0_gart_disable(adev); + adev->gfxhub.funcs->gart_disable(adev); adev->mmhub.funcs->gart_disable(adev); amdgpu_gart_table_vram_unpin(adev); } diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c index 91629c2b1d5c..3ebbddb63705 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c @@ -269,7 +269,6 @@ static const char *mmhub_client_ids_arcturus[][2] = { [14][1] = "HDP", [15][1] = "SDMA0", [32+15][1] = "SDMA1", - [32+15][1] = "SDMA1", [64+15][1] = "SDMA2", [96+15][1] = "SDMA3", [128+15][1] = "SDMA4", @@ -1165,6 +1164,19 @@ static void gmc_v9_0_set_mmhub_funcs(struct amdgpu_device *adev) } } +static void gmc_v9_0_set_gfxhub_funcs(struct amdgpu_device *adev) +{ + switch (adev->asic_type) { + case CHIP_ARCTURUS: + case CHIP_VEGA20: + adev->gfxhub.funcs = &gfxhub_v1_1_funcs; + break; + default: + adev->gfxhub.funcs = &gfxhub_v1_0_funcs; + break; + } +} + static int gmc_v9_0_early_init(void *handle) { struct amdgpu_device *adev = (struct amdgpu_device *)handle; @@ -1173,6 +1185,7 @@ static int gmc_v9_0_early_init(void *handle) gmc_v9_0_set_irq_funcs(adev); gmc_v9_0_set_umc_funcs(adev); gmc_v9_0_set_mmhub_funcs(adev); + gmc_v9_0_set_gfxhub_funcs(adev); adev->gmc.shared_aperture_start = 0x2000000000000000ULL; adev->gmc.shared_aperture_end = @@ -1194,21 +1207,16 @@ static int gmc_v9_0_late_init(void *handle) r = amdgpu_gmc_allocate_vm_inv_eng(adev); if (r) return r; - /* Check if ecc is available */ + + /* + * Workaround performance drop issue with VBIOS enables partial + * writes, while disables HBM ECC for vega10. + */ if (!amdgpu_sriov_vf(adev) && (adev->asic_type == CHIP_VEGA10)) { - r = amdgpu_atomfirmware_mem_ecc_supported(adev); - if (!r) { - DRM_INFO("ECC is not present.\n"); + if (!(adev->ras_features & (1 << AMDGPU_RAS_BLOCK__UMC))) { if (adev->df.funcs->enable_ecc_force_par_wr_rmw) adev->df.funcs->enable_ecc_force_par_wr_rmw(adev, false); - } else - DRM_INFO("ECC is active.\n"); - - r = amdgpu_atomfirmware_sram_ecc_supported(adev); - if (!r) - DRM_INFO("SRAM ECC is not present.\n"); - else - DRM_INFO("SRAM ECC is active.\n"); + } } if (adev->mmhub.funcs && adev->mmhub.funcs->reset_ras_error_count) @@ -1235,7 +1243,7 @@ static void gmc_v9_0_vram_gtt_location(struct amdgpu_device *adev, amdgpu_gmc_gart_location(adev, mc); amdgpu_gmc_agp_location(adev, mc); /* base offset of vram pages */ - adev->vm_manager.vram_base_offset = gfxhub_v1_0_get_mc_fb_offset(adev); + adev->vm_manager.vram_base_offset = adev->gfxhub.funcs->get_mc_fb_offset(adev); /* XXX: add the xgmi offset of the physical node? */ adev->vm_manager.vram_base_offset += @@ -1270,7 +1278,7 @@ static int gmc_v9_0_mc_init(struct amdgpu_device *adev) #ifdef CONFIG_X86_64 if (adev->flags & AMD_IS_APU) { - adev->gmc.aper_base = gfxhub_v1_0_get_mc_fb_offset(adev); + adev->gmc.aper_base = adev->gfxhub.funcs->get_mc_fb_offset(adev); adev->gmc.aper_size = adev->gmc.real_vram_size; } #endif @@ -1340,7 +1348,7 @@ static int gmc_v9_0_sw_init(void *handle) int r, vram_width = 0, vram_type = 0, vram_vendor = 0; struct amdgpu_device *adev = (struct amdgpu_device *)handle; - gfxhub_v1_0_init(adev); + adev->gfxhub.funcs->init(adev); adev->mmhub.funcs->init(adev); @@ -1454,7 +1462,7 @@ static int gmc_v9_0_sw_init(void *handle) adev->need_swiotlb = drm_need_swiotlb(44); if (adev->gmc.xgmi.supported) { - r = gfxhub_v1_1_get_xgmi_info(adev); + r = adev->gfxhub.funcs->get_xgmi_info(adev); if (r) return r; } @@ -1546,8 +1554,11 @@ static void gmc_v9_0_init_golden_registers(struct amdgpu_device *adev) */ void gmc_v9_0_restore_registers(struct amdgpu_device *adev) { - if (adev->asic_type == CHIP_RAVEN) + if (adev->asic_type == CHIP_RAVEN) { WREG32_SOC15(DCE, 0, mmDCHUBBUB_SDPIF_MMIO_CNTRL_0, adev->gmc.sdpif_register); + WARN_ON(adev->gmc.sdpif_register != + RREG32_SOC15(DCE, 0, mmDCHUBBUB_SDPIF_MMIO_CNTRL_0)); + } } /** @@ -1567,7 +1578,7 @@ static int gmc_v9_0_gart_enable(struct amdgpu_device *adev) if (r) return r; - r = gfxhub_v1_0_gart_enable(adev); + r = adev->gfxhub.funcs->gart_enable(adev); if (r) return r; @@ -1634,7 +1645,7 @@ static int gmc_v9_0_hw_init(void *handle) value = true; if (!amdgpu_sriov_vf(adev)) { - gfxhub_v1_0_set_fault_enable_default(adev, value); + adev->gfxhub.funcs->set_fault_enable_default(adev, value); adev->mmhub.funcs->set_fault_enable_default(adev, value); } for (i = 0; i < adev->num_vmhubs; ++i) @@ -1657,7 +1668,7 @@ static int gmc_v9_0_hw_init(void *handle) */ static void gmc_v9_0_gart_disable(struct amdgpu_device *adev) { - gfxhub_v1_0_gart_disable(adev); + adev->gfxhub.funcs->gart_disable(adev); adev->mmhub.funcs->gart_disable(adev); amdgpu_gart_table_vram_unpin(adev); } @@ -1681,14 +1692,9 @@ static int gmc_v9_0_hw_fini(void *handle) static int gmc_v9_0_suspend(void *handle) { - int r; struct amdgpu_device *adev = (struct amdgpu_device *)handle; - r = gmc_v9_0_hw_fini(adev); - if (r) - return r; - - return 0; + return gmc_v9_0_hw_fini(adev); } static int gmc_v9_0_resume(void *handle) diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v1_0.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v1_0.c index bc300283b6ab..c600b61b5f45 100644 --- a/drivers/gpu/drm/amd/amdgpu/jpeg_v1_0.c +++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v1_0.c @@ -33,6 +33,7 @@ static void jpeg_v1_0_set_dec_ring_funcs(struct amdgpu_device *adev); static void jpeg_v1_0_set_irq_funcs(struct amdgpu_device *adev); +static void jpeg_v1_0_ring_begin_use(struct amdgpu_ring *ring); static void jpeg_v1_0_decode_ring_patch_wreg(struct amdgpu_ring *ring, uint32_t *ptr, uint32_t reg_offset, uint32_t val) { @@ -564,8 +565,8 @@ static const struct amdgpu_ring_funcs jpeg_v1_0_decode_ring_vm_funcs = { .insert_start = jpeg_v1_0_decode_ring_insert_start, .insert_end = jpeg_v1_0_decode_ring_insert_end, .pad_ib = amdgpu_ring_generic_pad_ib, - .begin_use = vcn_v1_0_ring_begin_use, - .end_use = amdgpu_vcn_ring_end_use, + .begin_use = jpeg_v1_0_ring_begin_use, + .end_use = vcn_v1_0_ring_end_use, .emit_wreg = jpeg_v1_0_decode_ring_emit_wreg, .emit_reg_wait = jpeg_v1_0_decode_ring_emit_reg_wait, .emit_reg_write_reg_wait = amdgpu_ring_emit_reg_write_reg_wait_helper, @@ -586,3 +587,22 @@ static void jpeg_v1_0_set_irq_funcs(struct amdgpu_device *adev) { adev->jpeg.inst->irq.funcs = &jpeg_v1_0_irq_funcs; } + +static void jpeg_v1_0_ring_begin_use(struct amdgpu_ring *ring) +{ + struct amdgpu_device *adev = ring->adev; + bool set_clocks = !cancel_delayed_work_sync(&adev->vcn.idle_work); + int cnt = 0; + + mutex_lock(&adev->vcn.vcn1_jpeg1_workaround); + + if (amdgpu_fence_wait_empty(&adev->vcn.inst->ring_dec)) + DRM_ERROR("JPEG dec: vcn dec ring may not be empty\n"); + + for (cnt = 0; cnt < adev->vcn.num_enc_rings; cnt++) { + if (amdgpu_fence_wait_empty(&adev->vcn.inst->ring_enc[cnt])) + DRM_ERROR("JPEG dec: vcn enc ring[%d] may not be empty\n", cnt); + } + + vcn_v1_0_set_pg_for_begin_use(ring, set_clocks); +} diff --git a/drivers/gpu/drm/amd/amdgpu/mes_v10_1.c b/drivers/gpu/drm/amd/amdgpu/mes_v10_1.c index 4b746584a797..1c22d8393b21 100644 --- a/drivers/gpu/drm/amd/amdgpu/mes_v10_1.c +++ b/drivers/gpu/drm/amd/amdgpu/mes_v10_1.c @@ -832,7 +832,6 @@ static int mes_v10_1_queue_init(struct amdgpu_device *adev) static int mes_v10_1_ring_init(struct amdgpu_device *adev) { struct amdgpu_ring *ring; - int r; ring = &adev->mes.ring; @@ -849,11 +848,7 @@ static int mes_v10_1_ring_init(struct amdgpu_device *adev) ring->no_scheduler = true; sprintf(ring->name, "mes_%d.%d.%d", ring->me, ring->pipe, ring->queue); - r = amdgpu_ring_init(adev, ring, 1024, NULL, 0, AMDGPU_RING_PRIO_DEFAULT); - if (r) - return r; - - return 0; + return amdgpu_ring_init(adev, ring, 1024, NULL, 0, AMDGPU_RING_PRIO_DEFAULT); } static int mes_v10_1_mqd_sw_init(struct amdgpu_device *adev) diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c index 45a902b1acb7..f84701c562bf 100644 --- a/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c +++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c @@ -268,7 +268,7 @@ static void mmhub_v1_0_setup_vmid_config(struct amdgpu_device *adev) /* Send no-retry XNACK on fault to suppress VM fault storm. */ tmp = REG_SET_FIELD(tmp, VM_CONTEXT1_CNTL, RETRY_PERMISSION_OR_INVALID_PAGE_FAULT, - !amdgpu_noretry); + !adev->gmc.noretry); WREG32_SOC15_OFFSET(MMHUB, 0, mmVM_CONTEXT1_CNTL, i * hub->ctx_distance, tmp); WREG32_SOC15_OFFSET(MMHUB, 0, mmVM_CONTEXT1_PAGE_TABLE_START_ADDR_LO32, diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c index 2d88278c50bf..2063700f0bc6 100644 --- a/drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c +++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c @@ -201,11 +201,6 @@ static void mmhub_v2_0_init_system_aperture_regs(struct amdgpu_device *adev) WREG32_SOC15(MMHUB, 0, mmMMMC_VM_AGP_BOT, 0x00FFFFFF); if (!amdgpu_sriov_vf(adev)) { - /* - * the new L1 policy will block SRIOV guest from writing - * these regs, and they will be programed at host. - * so skip programing these regs. - */ /* Program the system aperture low logical page number. */ WREG32_SOC15(MMHUB, 0, mmMMMC_VM_SYSTEM_APERTURE_LOW_ADDR, adev->gmc.vram_start >> 18); @@ -374,7 +369,7 @@ static void mmhub_v2_0_setup_vmid_config(struct amdgpu_device *adev) /* Send no-retry XNACK on fault to suppress VM fault storm. */ tmp = REG_SET_FIELD(tmp, MMVM_CONTEXT1_CNTL, RETRY_PERMISSION_OR_INVALID_PAGE_FAULT, - !amdgpu_noretry); + !adev->gmc.noretry); WREG32_SOC15_OFFSET(MMHUB, 0, mmMMVM_CONTEXT1_CNTL, i * hub->ctx_distance, tmp); WREG32_SOC15_OFFSET(MMHUB, 0, mmMMVM_CONTEXT1_PAGE_TABLE_START_ADDR_LO32, diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.c index 6c6ad529c65c..66748bb01b52 100644 --- a/drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.c +++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.c @@ -330,7 +330,7 @@ static void mmhub_v9_4_setup_vmid_config(struct amdgpu_device *adev, int hubid) /* Send no-retry XNACK on fault to suppress VM fault storm. */ tmp = REG_SET_FIELD(tmp, VML2VC0_VM_CONTEXT1_CNTL, RETRY_PERMISSION_OR_INVALID_PAGE_FAULT, - !amdgpu_noretry); + !adev->gmc.noretry); WREG32_SOC15_OFFSET(MMHUB, 0, mmVML2VC0_VM_CONTEXT1_CNTL, hubid * MMHUB_INSTANCE_REGISTER_OFFSET + i * hub->ctx_distance, tmp); @@ -1624,6 +1624,34 @@ static void mmhub_v9_4_reset_ras_error_count(struct amdgpu_device *adev) } } +static const struct soc15_reg_entry mmhub_v9_4_err_status_regs[] = { + { SOC15_REG_ENTRY(MMHUB, 0, mmMMEA0_ERR_STATUS), 0, 0, 0 }, + { SOC15_REG_ENTRY(MMHUB, 0, mmMMEA1_ERR_STATUS), 0, 0, 0 }, + { SOC15_REG_ENTRY(MMHUB, 0, mmMMEA2_ERR_STATUS), 0, 0, 0 }, + { SOC15_REG_ENTRY(MMHUB, 0, mmMMEA3_ERR_STATUS), 0, 0, 0 }, + { SOC15_REG_ENTRY(MMHUB, 0, mmMMEA4_ERR_STATUS), 0, 0, 0 }, + { SOC15_REG_ENTRY(MMHUB, 0, mmMMEA5_ERR_STATUS), 0, 0, 0 }, + { SOC15_REG_ENTRY(MMHUB, 0, mmMMEA6_ERR_STATUS), 0, 0, 0 }, + { SOC15_REG_ENTRY(MMHUB, 0, mmMMEA7_ERR_STATUS), 0, 0, 0 }, +}; + +static void mmhub_v9_4_query_ras_error_status(struct amdgpu_device *adev) +{ + int i; + uint32_t reg_value; + + if (!amdgpu_ras_is_supported(adev, AMDGPU_RAS_BLOCK__MMHUB)) + return; + + for (i = 0; i < ARRAY_SIZE(mmhub_v9_4_err_status_regs); i++) { + reg_value = + RREG32(SOC15_REG_ENTRY_OFFSET(mmhub_v9_4_err_status_regs[i])); + if (reg_value) + dev_warn(adev->dev, "MMHUB EA err detected at instance: %d, status: 0x%x!\n", + i, reg_value); + } +} + const struct amdgpu_mmhub_funcs mmhub_v9_4_funcs = { .ras_late_init = amdgpu_mmhub_ras_late_init, .query_ras_error_count = mmhub_v9_4_query_ras_error_count, @@ -1636,4 +1664,5 @@ const struct amdgpu_mmhub_funcs mmhub_v9_4_funcs = { .set_clockgating = mmhub_v9_4_set_clockgating, .get_clockgating = mmhub_v9_4_get_clockgating, .setup_vm_pt_regs = mmhub_v9_4_setup_vm_pt_regs, + .query_ras_error_status = mmhub_v9_4_query_ras_error_status, }; diff --git a/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c b/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c index 9c07014d9bd6..f5ce9a9f4cf5 100644 --- a/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c +++ b/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c @@ -262,7 +262,8 @@ flr_done: /* Trigger recovery for world switch failure if no TDR */ if (amdgpu_device_should_recover_gpu(adev) - && (amdgpu_device_has_job_running(adev) || adev->sdma_timeout == MAX_SCHEDULE_TIMEOUT)) + && (!amdgpu_device_has_job_running(adev) || + adev->sdma_timeout == MAX_SCHEDULE_TIMEOUT)) amdgpu_device_gpu_recover(adev, NULL); } diff --git a/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c b/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c index 9c23abf9b140..666ed99cc14b 100644 --- a/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c +++ b/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c @@ -283,7 +283,7 @@ flr_done: /* Trigger recovery for world switch failure if no TDR */ if (amdgpu_device_should_recover_gpu(adev) - && (amdgpu_device_has_job_running(adev) || + && (!amdgpu_device_has_job_running(adev) || adev->sdma_timeout == MAX_SCHEDULE_TIMEOUT || adev->gfx_timeout == MAX_SCHEDULE_TIMEOUT || adev->compute_timeout == MAX_SCHEDULE_TIMEOUT || diff --git a/drivers/gpu/drm/amd/amdgpu/nv.c b/drivers/gpu/drm/amd/amdgpu/nv.c index 4d1402356262..03462c857498 100644 --- a/drivers/gpu/drm/amd/amdgpu/nv.c +++ b/drivers/gpu/drm/amd/amdgpu/nv.c @@ -69,75 +69,40 @@ static const struct amd_ip_funcs nv_common_ip_funcs; */ static u32 nv_pcie_rreg(struct amdgpu_device *adev, u32 reg) { - unsigned long flags, address, data; - u32 r; + unsigned long address, data; address = adev->nbio.funcs->get_pcie_index_offset(adev); data = adev->nbio.funcs->get_pcie_data_offset(adev); - spin_lock_irqsave(&adev->pcie_idx_lock, flags); - WREG32(address, reg); - (void)RREG32(address); - r = RREG32(data); - spin_unlock_irqrestore(&adev->pcie_idx_lock, flags); - return r; + return amdgpu_device_indirect_rreg(adev, address, data, reg); } static void nv_pcie_wreg(struct amdgpu_device *adev, u32 reg, u32 v) { - unsigned long flags, address, data; + unsigned long address, data; address = adev->nbio.funcs->get_pcie_index_offset(adev); data = adev->nbio.funcs->get_pcie_data_offset(adev); - spin_lock_irqsave(&adev->pcie_idx_lock, flags); - WREG32(address, reg); - (void)RREG32(address); - WREG32(data, v); - (void)RREG32(data); - spin_unlock_irqrestore(&adev->pcie_idx_lock, flags); + amdgpu_device_indirect_wreg(adev, address, data, reg, v); } static u64 nv_pcie_rreg64(struct amdgpu_device *adev, u32 reg) { - unsigned long flags, address, data; - u64 r; + unsigned long address, data; address = adev->nbio.funcs->get_pcie_index_offset(adev); data = adev->nbio.funcs->get_pcie_data_offset(adev); - spin_lock_irqsave(&adev->pcie_idx_lock, flags); - /* read low 32 bit */ - WREG32(address, reg); - (void)RREG32(address); - r = RREG32(data); - - /* read high 32 bit*/ - WREG32(address, reg + 4); - (void)RREG32(address); - r |= ((u64)RREG32(data) << 32); - spin_unlock_irqrestore(&adev->pcie_idx_lock, flags); - return r; + return amdgpu_device_indirect_rreg64(adev, address, data, reg); } static void nv_pcie_wreg64(struct amdgpu_device *adev, u32 reg, u64 v) { - unsigned long flags, address, data; + unsigned long address, data; address = adev->nbio.funcs->get_pcie_index_offset(adev); data = adev->nbio.funcs->get_pcie_data_offset(adev); - spin_lock_irqsave(&adev->pcie_idx_lock, flags); - /* write low 32 bit */ - WREG32(address, reg); - (void)RREG32(address); - WREG32(data, (u32)(v & 0xffffffffULL)); - (void)RREG32(data); - - /* write high 32 bit */ - WREG32(address, reg + 4); - (void)RREG32(address); - WREG32(data, (u32)(v >> 32)); - (void)RREG32(data); - spin_unlock_irqrestore(&adev->pcie_idx_lock, flags); + amdgpu_device_indirect_wreg64(adev, address, data, reg, v); } static u32 nv_didt_rreg(struct amdgpu_device *adev, u32 reg) @@ -311,7 +276,7 @@ static int nv_asic_mode1_reset(struct amdgpu_device *adev) /* disable BM */ pci_clear_master(adev->pdev); - pci_save_state(adev->pdev); + amdgpu_device_cache_pci_state(adev->pdev); if (amdgpu_dpm_is_mode1_reset_supported(adev)) { dev_info(adev->dev, "GPU smu mode1 reset\n"); @@ -323,7 +288,7 @@ static int nv_asic_mode1_reset(struct amdgpu_device *adev) if (ret) dev_err(adev->dev, "GPU mode1 reset failed\n"); - pci_restore_state(adev->pdev); + amdgpu_device_load_pci_state(adev->pdev); /* wait for asic to come out of reset */ for (i = 0; i < adev->usec_timeout; i++) { @@ -490,6 +455,14 @@ void nv_set_virt_ops(struct amdgpu_device *adev) adev->virt.ops = &xgpu_nv_virt_ops; } +static bool nv_is_blockchain_sku(struct pci_dev *pdev) +{ + if (pdev->device == 0x731E && + (pdev->revision == 0xC6 || pdev->revision == 0xC7)) + return true; + return false; +} + int nv_set_ip_blocks(struct amdgpu_device *adev) { int r; @@ -518,7 +491,8 @@ int nv_set_ip_blocks(struct amdgpu_device *adev) if (adev->enable_virtual_display || amdgpu_sriov_vf(adev)) amdgpu_device_ip_block_add(adev, &dce_virtual_ip_block); #if defined(CONFIG_DRM_AMD_DC) - else if (amdgpu_device_has_dc_support(adev)) + else if (amdgpu_device_has_dc_support(adev) && + !nv_is_blockchain_sku(adev->pdev)) amdgpu_device_ip_block_add(adev, &dm_ip_block); #endif amdgpu_device_ip_block_add(adev, &gfx_v10_0_ip_block); @@ -526,7 +500,8 @@ int nv_set_ip_blocks(struct amdgpu_device *adev) if (adev->firmware.load_type == AMDGPU_FW_LOAD_DIRECT && !amdgpu_sriov_vf(adev)) amdgpu_device_ip_block_add(adev, &smu_v11_0_ip_block); - amdgpu_device_ip_block_add(adev, &vcn_v2_0_ip_block); + if (!nv_is_blockchain_sku(adev->pdev)) + amdgpu_device_ip_block_add(adev, &vcn_v2_0_ip_block); amdgpu_device_ip_block_add(adev, &jpeg_v2_0_ip_block); if (adev->enable_mes) amdgpu_device_ip_block_add(adev, &mes_v10_1_ip_block); @@ -621,7 +596,7 @@ static void nv_invalidate_hdp(struct amdgpu_device *adev, struct amdgpu_ring *ring) { if (!ring || !ring->funcs->emit_wreg) { - WREG32_SOC15_NO_KIQ(NBIO, 0, mmHDP_READ_CACHE_INVALIDATE, 1); + WREG32_SOC15_NO_KIQ(HDP, 0, mmHDP_READ_CACHE_INVALIDATE, 1); } else { amdgpu_ring_emit_wreg(ring, SOC15_REG_OFFSET( HDP, 0, mmHDP_READ_CACHE_INVALIDATE), 1); diff --git a/drivers/gpu/drm/amd/amdgpu/psp_gfx_if.h b/drivers/gpu/drm/amd/amdgpu/psp_gfx_if.h index cbc04a5c0fe1..4137dc710aaf 100644 --- a/drivers/gpu/drm/amd/amdgpu/psp_gfx_if.h +++ b/drivers/gpu/drm/amd/amdgpu/psp_gfx_if.h @@ -83,19 +83,6 @@ struct psp_gfx_ctrl */ #define GFX_FLAG_RESPONSE 0x80000000 -/* Gbr IH registers ID */ -enum ih_reg_id { - IH_RB = 0, // IH_RB_CNTL - IH_RB_RNG1 = 1, // IH_RB_CNTL_RING1 - IH_RB_RNG2 = 2, // IH_RB_CNTL_RING2 -}; - -/* Command to setup Gibraltar IH register */ -struct psp_gfx_cmd_gbr_ih_reg { - uint32_t reg_value; /* Value to be set to the IH_RB_CNTL... register*/ - enum ih_reg_id reg_id; /* ID of the register */ -}; - /* TEE Gfx Command IDs for the ring buffer interface. */ enum psp_gfx_cmd_id { @@ -214,7 +201,7 @@ enum psp_gfx_fw_type { GFX_FW_TYPE_UVD1 = 23, /* UVD1 VG-20 */ GFX_FW_TYPE_TOC = 24, /* TOC NV-10 */ GFX_FW_TYPE_RLC_P = 25, /* RLC P NV */ - GFX_FW_TYPE_RLX6 = 26, /* RLX6 NV */ + GFX_FW_TYPE_RLC_IRAM = 26, /* RLC_IRAM NV */ GFX_FW_TYPE_GLOBAL_TAP_DELAYS = 27, /* GLOBAL TAP DELAYS NV */ GFX_FW_TYPE_SE0_TAP_DELAYS = 28, /* SE0 TAP DELAYS NV */ GFX_FW_TYPE_SE1_TAP_DELAYS = 29, /* SE1 TAP DELAYS NV */ @@ -236,7 +223,7 @@ enum psp_gfx_fw_type { GFX_FW_TYPE_ACCUM_CTRL_RAM = 45, /* ACCUM CTRL RAM NV */ GFX_FW_TYPE_RLCP_CAM = 46, /* RLCP CAM NV */ GFX_FW_TYPE_RLC_SPP_CAM_EXT = 47, /* RLC SPP CAM EXT NV */ - GFX_FW_TYPE_RLX6_DRAM_BOOT = 48, /* RLX6 DRAM BOOT NV */ + GFX_FW_TYPE_RLC_DRAM_BOOT = 48, /* RLC DRAM BOOT NV */ GFX_FW_TYPE_VCN0_RAM = 49, /* VCN_RAM NV + RN */ GFX_FW_TYPE_VCN1_RAM = 50, /* VCN_RAM NV + RN */ GFX_FW_TYPE_DMUB = 51, /* DMUB RN */ diff --git a/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c b/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c index e16874f30d5d..6c5d9612abcb 100644 --- a/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c @@ -58,7 +58,7 @@ MODULE_FIRMWARE("amdgpu/arcturus_ta.bin"); MODULE_FIRMWARE("amdgpu/sienna_cichlid_sos.bin"); MODULE_FIRMWARE("amdgpu/sienna_cichlid_ta.bin"); MODULE_FIRMWARE("amdgpu/navy_flounder_sos.bin"); -MODULE_FIRMWARE("amdgpu/navy_flounder_asd.bin"); +MODULE_FIRMWARE("amdgpu/navy_flounder_ta.bin"); /* address block */ #define smnMP1_FIRMWARE_FLAGS 0x3010024 diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c index 856c50386c86..86fb1eddf5a6 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c @@ -592,6 +592,9 @@ static int sdma_v4_0_init_microcode(struct amdgpu_device *adev) struct amdgpu_firmware_info *info = NULL; const struct common_firmware_header *header = NULL; + if (amdgpu_sriov_vf(adev)) + return 0; + DRM_DEBUG("\n"); switch (adev->asic_type) { @@ -1000,7 +1003,7 @@ static void sdma_v4_0_page_stop(struct amdgpu_device *adev) sdma[i] = &adev->sdma.instance[i].page; if ((adev->mman.buffer_funcs_ring == sdma[i]) && - (unset == false)) { + (!unset)) { amdgpu_ttm_set_buffer_funcs_status(adev, false); unset = true; } @@ -1063,6 +1066,15 @@ static void sdma_v4_0_ctx_switch_enable(struct amdgpu_device *adev, bool enable) WREG32_SDMA(i, mmSDMA0_PHASE2_QUANTUM, phase_quantum); } WREG32_SDMA(i, mmSDMA0_CNTL, f32_cntl); + + /* + * Enable SDMA utilization. Its only supported on + * Arcturus for the moment and firmware version 14 + * and above. + */ + if (adev->asic_type == CHIP_ARCTURUS && + adev->sdma.instance[i].fw_version >= 14) + WREG32_SDMA(i, mmSDMA0_PUB_DUMMY_REG2, enable); } } @@ -1080,7 +1092,7 @@ static void sdma_v4_0_enable(struct amdgpu_device *adev, bool enable) u32 f32_cntl; int i; - if (enable == false) { + if (!enable) { sdma_v4_0_gfx_stop(adev); sdma_v4_0_rlc_stop(adev); if (adev->sdma.has_page_queue) diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c index e2232dd12d8e..9c72b95b7463 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c @@ -203,6 +203,9 @@ static int sdma_v5_0_init_microcode(struct amdgpu_device *adev) const struct common_firmware_header *header = NULL; const struct sdma_firmware_header_v1_0 *hdr; + if (amdgpu_sriov_vf(adev)) + return 0; + DRM_DEBUG("\n"); switch (adev->asic_type) { @@ -616,7 +619,7 @@ static void sdma_v5_0_enable(struct amdgpu_device *adev, bool enable) u32 f32_cntl; int i; - if (enable == false) { + if (!enable) { sdma_v5_0_gfx_stop(adev); sdma_v5_0_rlc_stop(adev); } diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c b/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c index 46a9617fee5f..9f3952723c63 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c @@ -148,6 +148,9 @@ static int sdma_v5_2_init_microcode(struct amdgpu_device *adev) struct amdgpu_firmware_info *info = NULL; const struct common_firmware_header *header = NULL; + if (amdgpu_sriov_vf(adev)) + return 0; + DRM_DEBUG("\n"); switch (adev->asic_type) { @@ -559,7 +562,7 @@ static void sdma_v5_2_enable(struct amdgpu_device *adev, bool enable) u32 f32_cntl; int i; - if (enable == false) { + if (!enable) { sdma_v5_2_gfx_stop(adev); sdma_v5_2_rlc_stop(adev); } diff --git a/drivers/gpu/drm/amd/amdgpu/si.c b/drivers/gpu/drm/amd/amdgpu/si.c index 455d5e366c69..e5e336fd9e94 100644 --- a/drivers/gpu/drm/amd/amdgpu/si.c +++ b/drivers/gpu/drm/amd/amdgpu/si.c @@ -1339,7 +1339,7 @@ static void si_vga_set_state(struct amdgpu_device *adev, bool state) uint32_t temp; temp = RREG32(CONFIG_CNTL); - if (state == false) { + if (!state) { temp &= ~(1<<0); temp |= (1<<1); } else { diff --git a/drivers/gpu/drm/amd/amdgpu/soc15.c b/drivers/gpu/drm/amd/amdgpu/soc15.c index 2f93c475d6d8..afcccc6c0fc6 100644 --- a/drivers/gpu/drm/amd/amdgpu/soc15.c +++ b/drivers/gpu/drm/amd/amdgpu/soc15.c @@ -101,75 +101,40 @@ */ static u32 soc15_pcie_rreg(struct amdgpu_device *adev, u32 reg) { - unsigned long flags, address, data; - u32 r; + unsigned long address, data; address = adev->nbio.funcs->get_pcie_index_offset(adev); data = adev->nbio.funcs->get_pcie_data_offset(adev); - spin_lock_irqsave(&adev->pcie_idx_lock, flags); - WREG32(address, reg); - (void)RREG32(address); - r = RREG32(data); - spin_unlock_irqrestore(&adev->pcie_idx_lock, flags); - return r; + return amdgpu_device_indirect_rreg(adev, address, data, reg); } static void soc15_pcie_wreg(struct amdgpu_device *adev, u32 reg, u32 v) { - unsigned long flags, address, data; + unsigned long address, data; address = adev->nbio.funcs->get_pcie_index_offset(adev); data = adev->nbio.funcs->get_pcie_data_offset(adev); - spin_lock_irqsave(&adev->pcie_idx_lock, flags); - WREG32(address, reg); - (void)RREG32(address); - WREG32(data, v); - (void)RREG32(data); - spin_unlock_irqrestore(&adev->pcie_idx_lock, flags); + amdgpu_device_indirect_wreg(adev, address, data, reg, v); } static u64 soc15_pcie_rreg64(struct amdgpu_device *adev, u32 reg) { - unsigned long flags, address, data; - u64 r; + unsigned long address, data; address = adev->nbio.funcs->get_pcie_index_offset(adev); data = adev->nbio.funcs->get_pcie_data_offset(adev); - spin_lock_irqsave(&adev->pcie_idx_lock, flags); - /* read low 32 bit */ - WREG32(address, reg); - (void)RREG32(address); - r = RREG32(data); - - /* read high 32 bit*/ - WREG32(address, reg + 4); - (void)RREG32(address); - r |= ((u64)RREG32(data) << 32); - spin_unlock_irqrestore(&adev->pcie_idx_lock, flags); - return r; + return amdgpu_device_indirect_rreg64(adev, address, data, reg); } static void soc15_pcie_wreg64(struct amdgpu_device *adev, u32 reg, u64 v) { - unsigned long flags, address, data; + unsigned long address, data; address = adev->nbio.funcs->get_pcie_index_offset(adev); data = adev->nbio.funcs->get_pcie_data_offset(adev); - spin_lock_irqsave(&adev->pcie_idx_lock, flags); - /* write low 32 bit */ - WREG32(address, reg); - (void)RREG32(address); - WREG32(data, (u32)(v & 0xffffffffULL)); - (void)RREG32(data); - - /* write high 32 bit */ - WREG32(address, reg + 4); - (void)RREG32(address); - WREG32(data, (u32)(v >> 32)); - (void)RREG32(data); - spin_unlock_irqrestore(&adev->pcie_idx_lock, flags); + amdgpu_device_indirect_wreg64(adev, address, data, reg, v); } static u32 soc15_uvd_ctx_rreg(struct amdgpu_device *adev, u32 reg) @@ -484,13 +449,13 @@ static int soc15_asic_mode1_reset(struct amdgpu_device *adev) /* disable BM */ pci_clear_master(adev->pdev); - pci_save_state(adev->pdev); + amdgpu_device_cache_pci_state(adev->pdev); ret = psp_gpu_reset(adev); if (ret) dev_err(adev->dev, "GPU mode1 reset failed\n"); - pci_restore_state(adev->pdev); + amdgpu_device_load_pci_state(adev->pdev); /* wait for asic to come out of reset */ for (i = 0; i < adev->usec_timeout; i++) { @@ -697,12 +662,12 @@ static void soc15_reg_base_init(struct amdgpu_device *adev) * it doesn't support SRIOV. */ if (amdgpu_discovery) { r = amdgpu_discovery_reg_base_init(adev); - if (r) { - DRM_WARN("failed to init reg base from ip discovery table, " - "fallback to legacy init method\n"); - vega10_reg_base_init(adev); - } + if (r == 0) + break; + DRM_WARN("failed to init reg base from ip discovery table, " + "fallback to legacy init method\n"); } + vega10_reg_base_init(adev); break; case CHIP_VEGA20: vega20_reg_base_init(adev); diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v4_2.c b/drivers/gpu/drm/amd/amdgpu/uvd_v4_2.c index 3cafba726587..b0c0c438fc93 100644 --- a/drivers/gpu/drm/amd/amdgpu/uvd_v4_2.c +++ b/drivers/gpu/drm/amd/amdgpu/uvd_v4_2.c @@ -348,7 +348,7 @@ static int uvd_v4_2_start(struct amdgpu_device *adev) /* Set the write pointer delay */ WREG32(mmUVD_RBC_RB_WPTR_CNTL, 0); - /* programm the 4GB memory segment for rptr and ring buffer */ + /* program the 4GB memory segment for rptr and ring buffer */ WREG32(mmUVD_LMI_EXT40_ADDR, upper_32_bits(ring->gpu_addr) | (0x7 << 16) | (0x1 << 31)); @@ -541,7 +541,7 @@ static void uvd_v4_2_mc_resume(struct amdgpu_device *adev) uint64_t addr; uint32_t size; - /* programm the VCPU memory controller bits 0-27 */ + /* program the VCPU memory controller bits 0-27 */ addr = (adev->uvd.inst->gpu_addr + AMDGPU_UVD_FIRMWARE_OFFSET) >> 3; size = AMDGPU_UVD_FIRMWARE_SIZE(adev) >> 3; WREG32(mmUVD_VCPU_CACHE_OFFSET0, addr); diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v5_0.c b/drivers/gpu/drm/amd/amdgpu/uvd_v5_0.c index a566ff926e90..6e57001f6d0a 100644 --- a/drivers/gpu/drm/amd/amdgpu/uvd_v5_0.c +++ b/drivers/gpu/drm/amd/amdgpu/uvd_v5_0.c @@ -253,7 +253,7 @@ static void uvd_v5_0_mc_resume(struct amdgpu_device *adev) uint64_t offset; uint32_t size; - /* programm memory controller bits 0-27 */ + /* program memory controller bits 0-27 */ WREG32(mmUVD_LMI_VCPU_CACHE_64BIT_BAR_LOW, lower_32_bits(adev->uvd.inst->gpu_addr)); WREG32(mmUVD_LMI_VCPU_CACHE_64BIT_BAR_HIGH, @@ -404,7 +404,7 @@ static int uvd_v5_0_start(struct amdgpu_device *adev) /* set the wb address */ WREG32(mmUVD_RBC_RB_RPTR_ADDR, (upper_32_bits(ring->gpu_addr) >> 2)); - /* programm the RB_BASE for ring buffer */ + /* program the RB_BASE for ring buffer */ WREG32(mmUVD_LMI_RBC_RB_64BIT_BAR_LOW, lower_32_bits(ring->gpu_addr)); WREG32(mmUVD_LMI_RBC_RB_64BIT_BAR_HIGH, diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c b/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c index 0a880bc101b8..666bfa4a0b8e 100644 --- a/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c +++ b/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c @@ -583,7 +583,7 @@ static void uvd_v6_0_mc_resume(struct amdgpu_device *adev) uint64_t offset; uint32_t size; - /* programm memory controller bits 0-27 */ + /* program memory controller bits 0-27 */ WREG32(mmUVD_LMI_VCPU_CACHE_64BIT_BAR_LOW, lower_32_bits(adev->uvd.inst->gpu_addr)); WREG32(mmUVD_LMI_VCPU_CACHE_64BIT_BAR_HIGH, @@ -825,7 +825,7 @@ static int uvd_v6_0_start(struct amdgpu_device *adev) /* set the wb address */ WREG32(mmUVD_RBC_RB_RPTR_ADDR, (upper_32_bits(ring->gpu_addr) >> 2)); - /* programm the RB_BASE for ring buffer */ + /* program the RB_BASE for ring buffer */ WREG32(mmUVD_LMI_RBC_RB_64BIT_BAR_LOW, lower_32_bits(ring->gpu_addr)); WREG32(mmUVD_LMI_RBC_RB_64BIT_BAR_HIGH, @@ -1240,8 +1240,8 @@ static int uvd_v6_0_process_interrupt(struct amdgpu_device *adev, break; } - if (false == int_handled) - DRM_ERROR("Unhandled interrupt: %d %d\n", + if (!int_handled) + DRM_ERROR("Unhandled interrupt: %d %d\n", entry->src_id, entry->src_data[0]); return 0; diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c b/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c index e07e3fae99b5..b44c8677ce8d 100644 --- a/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c +++ b/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c @@ -1073,7 +1073,7 @@ static int uvd_v7_0_start(struct amdgpu_device *adev) WREG32_SOC15(UVD, k, mmUVD_RBC_RB_RPTR_ADDR, (upper_32_bits(ring->gpu_addr) >> 2)); - /* programm the RB_BASE for ring buffer */ + /* program the RB_BASE for ring buffer */ WREG32_SOC15(UVD, k, mmUVD_LMI_RBC_RB_64BIT_BAR_LOW, lower_32_bits(ring->gpu_addr)); WREG32_SOC15(UVD, k, mmUVD_LMI_RBC_RB_64BIT_BAR_HIGH, diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c index 927c330fad21..86e1ef732ebe 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c @@ -54,6 +54,7 @@ static int vcn_v1_0_pause_dpg_mode(struct amdgpu_device *adev, int inst_idx, struct dpg_pause_state *new_state); static void vcn_v1_0_idle_work_handler(struct work_struct *work); +static void vcn_v1_0_ring_begin_use(struct amdgpu_ring *ring); /** * vcn_v1_0_early_init - set function pointers @@ -910,7 +911,7 @@ static int vcn_v1_0_start_spg_mode(struct amdgpu_device *adev) WREG32_SOC15(UVD, 0, mmUVD_RBC_RB_RPTR_ADDR, (upper_32_bits(ring->gpu_addr) >> 2)); - /* programm the RB_BASE for ring buffer */ + /* program the RB_BASE for ring buffer */ WREG32_SOC15(UVD, 0, mmUVD_LMI_RBC_RB_64BIT_BAR_LOW, lower_32_bits(ring->gpu_addr)); WREG32_SOC15(UVD, 0, mmUVD_LMI_RBC_RB_64BIT_BAR_HIGH, @@ -1068,7 +1069,7 @@ static int vcn_v1_0_start_dpg_mode(struct amdgpu_device *adev) WREG32_SOC15(UVD, 0, mmUVD_RBC_RB_RPTR_ADDR, (upper_32_bits(ring->gpu_addr) >> 2)); - /* programm the RB_BASE for ring buffer */ + /* program the RB_BASE for ring buffer */ WREG32_SOC15(UVD, 0, mmUVD_LMI_RBC_RB_64BIT_BAR_LOW, lower_32_bits(ring->gpu_addr)); WREG32_SOC15(UVD, 0, mmUVD_LMI_RBC_RB_64BIT_BAR_HIGH, @@ -1804,11 +1805,24 @@ static void vcn_v1_0_idle_work_handler(struct work_struct *work) } } -void vcn_v1_0_ring_begin_use(struct amdgpu_ring *ring) +static void vcn_v1_0_ring_begin_use(struct amdgpu_ring *ring) { - struct amdgpu_device *adev = ring->adev; + struct amdgpu_device *adev = ring->adev; bool set_clocks = !cancel_delayed_work_sync(&adev->vcn.idle_work); + mutex_lock(&adev->vcn.vcn1_jpeg1_workaround); + + if (amdgpu_fence_wait_empty(&ring->adev->jpeg.inst->ring_dec)) + DRM_ERROR("VCN dec: jpeg dec ring may not be empty\n"); + + vcn_v1_0_set_pg_for_begin_use(ring, set_clocks); + +} + +void vcn_v1_0_set_pg_for_begin_use(struct amdgpu_ring *ring, bool set_clocks) +{ + struct amdgpu_device *adev = ring->adev; + if (set_clocks) { amdgpu_gfx_off_ctrl(adev, false); if (adev->pm.dpm_enabled) @@ -1844,6 +1858,12 @@ void vcn_v1_0_ring_begin_use(struct amdgpu_ring *ring) } } +void vcn_v1_0_ring_end_use(struct amdgpu_ring *ring) +{ + schedule_delayed_work(&ring->adev->vcn.idle_work, VCN_IDLE_TIMEOUT); + mutex_unlock(&ring->adev->vcn.vcn1_jpeg1_workaround); +} + static const struct amd_ip_funcs vcn_v1_0_ip_funcs = { .name = "vcn_v1_0", .early_init = vcn_v1_0_early_init, @@ -1891,7 +1911,7 @@ static const struct amdgpu_ring_funcs vcn_v1_0_dec_ring_vm_funcs = { .insert_end = vcn_v1_0_dec_ring_insert_end, .pad_ib = amdgpu_ring_generic_pad_ib, .begin_use = vcn_v1_0_ring_begin_use, - .end_use = amdgpu_vcn_ring_end_use, + .end_use = vcn_v1_0_ring_end_use, .emit_wreg = vcn_v1_0_dec_ring_emit_wreg, .emit_reg_wait = vcn_v1_0_dec_ring_emit_reg_wait, .emit_reg_write_reg_wait = amdgpu_ring_emit_reg_write_reg_wait_helper, @@ -1923,7 +1943,7 @@ static const struct amdgpu_ring_funcs vcn_v1_0_enc_ring_vm_funcs = { .insert_end = vcn_v1_0_enc_ring_insert_end, .pad_ib = amdgpu_ring_generic_pad_ib, .begin_use = vcn_v1_0_ring_begin_use, - .end_use = amdgpu_vcn_ring_end_use, + .end_use = vcn_v1_0_ring_end_use, .emit_wreg = vcn_v1_0_enc_ring_emit_wreg, .emit_reg_wait = vcn_v1_0_enc_ring_emit_reg_wait, .emit_reg_write_reg_wait = amdgpu_ring_emit_reg_write_reg_wait_helper, diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.h b/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.h index f67d7391fc21..1f1cc7f0ece7 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.h +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.h @@ -24,7 +24,8 @@ #ifndef __VCN_V1_0_H__ #define __VCN_V1_0_H__ -void vcn_v1_0_ring_begin_use(struct amdgpu_ring *ring); +void vcn_v1_0_ring_end_use(struct amdgpu_ring *ring); +void vcn_v1_0_set_pg_for_begin_use(struct amdgpu_ring *ring, bool set_clocks); extern const struct amdgpu_ip_block_version vcn_v1_0_ip_block; diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c index 23a9eb5b2c8a..e5d29dee0c88 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c @@ -900,7 +900,7 @@ static int vcn_v2_0_start_dpg_mode(struct amdgpu_device *adev, bool indirect) WREG32_SOC15(UVD, 0, mmUVD_RBC_RB_RPTR_ADDR, (upper_32_bits(ring->gpu_addr) >> 2)); - /* programm the RB_BASE for ring buffer */ + /* program the RB_BASE for ring buffer */ WREG32_SOC15(UVD, 0, mmUVD_LMI_RBC_RB_64BIT_BAR_LOW, lower_32_bits(ring->gpu_addr)); WREG32_SOC15(UVD, 0, mmUVD_LMI_RBC_RB_64BIT_BAR_HIGH, @@ -1060,7 +1060,7 @@ static int vcn_v2_0_start(struct amdgpu_device *adev) WREG32_SOC15(UVD, 0, mmUVD_RBC_RB_CNTL, tmp); fw_shared->multi_queue.decode_queue_mode |= FW_QUEUE_RING_RESET; - /* programm the RB_BASE for ring buffer */ + /* program the RB_BASE for ring buffer */ WREG32_SOC15(UVD, 0, mmUVD_LMI_RBC_RB_64BIT_BAR_LOW, lower_32_bits(ring->gpu_addr)); WREG32_SOC15(UVD, 0, mmUVD_LMI_RBC_RB_64BIT_BAR_HIGH, diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c b/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c index 139fac0d8e76..0f1d3ef8baa7 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c @@ -882,7 +882,7 @@ static int vcn_v2_5_start_dpg_mode(struct amdgpu_device *adev, int inst_idx, boo WREG32_SOC15(VCN, inst_idx, mmUVD_RBC_RB_RPTR_ADDR, (upper_32_bits(ring->gpu_addr) >> 2)); - /* programm the RB_BASE for ring buffer */ + /* program the RB_BASE for ring buffer */ WREG32_SOC15(VCN, inst_idx, mmUVD_LMI_RBC_RB_64BIT_BAR_LOW, lower_32_bits(ring->gpu_addr)); WREG32_SOC15(VCN, inst_idx, mmUVD_LMI_RBC_RB_64BIT_BAR_HIGH, @@ -1062,7 +1062,7 @@ static int vcn_v2_5_start(struct amdgpu_device *adev) WREG32_SOC15(VCN, i, mmUVD_RBC_RB_CNTL, tmp); fw_shared->multi_queue.decode_queue_mode |= FW_QUEUE_RING_RESET; - /* programm the RB_BASE for ring buffer */ + /* program the RB_BASE for ring buffer */ WREG32_SOC15(VCN, i, mmUVD_LMI_RBC_RB_64BIT_BAR_LOW, lower_32_bits(ring->gpu_addr)); WREG32_SOC15(VCN, i, mmUVD_LMI_RBC_RB_64BIT_BAR_HIGH, diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c index 589d6cd8adec..e074f7ed388c 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c @@ -746,18 +746,18 @@ static void vcn_v3_0_disable_clock_gating(struct amdgpu_device *adev, int inst) | UVD_SUVD_CGC_GATE__IME_HEVC_MASK | UVD_SUVD_CGC_GATE__EFC_MASK | UVD_SUVD_CGC_GATE__SAOE_MASK - | 0x08000000 + | UVD_SUVD_CGC_GATE__SRE_AV1_MASK | UVD_SUVD_CGC_GATE__FBC_PCLK_MASK | UVD_SUVD_CGC_GATE__FBC_CCLK_MASK - | 0x40000000 + | UVD_SUVD_CGC_GATE__SCM_AV1_MASK | UVD_SUVD_CGC_GATE__SMPA_MASK); WREG32_SOC15(VCN, inst, mmUVD_SUVD_CGC_GATE, data); data = RREG32_SOC15(VCN, inst, mmUVD_SUVD_CGC_GATE2); data |= (UVD_SUVD_CGC_GATE2__MPBE0_MASK | UVD_SUVD_CGC_GATE2__MPBE1_MASK - | 0x00000004 - | 0x00000008 + | UVD_SUVD_CGC_GATE2__SIT_AV1_MASK + | UVD_SUVD_CGC_GATE2__SDB_AV1_MASK | UVD_SUVD_CGC_GATE2__MPC1_MASK); WREG32_SOC15(VCN, inst, mmUVD_SUVD_CGC_GATE2, data); @@ -776,8 +776,8 @@ static void vcn_v3_0_disable_clock_gating(struct amdgpu_device *adev, int inst) | UVD_SUVD_CGC_CTRL__SMPA_MODE_MASK | UVD_SUVD_CGC_CTRL__MPBE0_MODE_MASK | UVD_SUVD_CGC_CTRL__MPBE1_MODE_MASK - | 0x00008000 - | 0x00010000 + | UVD_SUVD_CGC_CTRL__SIT_AV1_MODE_MASK + | UVD_SUVD_CGC_CTRL__SDB_AV1_MODE_MASK | UVD_SUVD_CGC_CTRL__MPC1_MODE_MASK | UVD_SUVD_CGC_CTRL__FBC_PCLK_MASK | UVD_SUVD_CGC_CTRL__FBC_CCLK_MASK); @@ -892,8 +892,8 @@ static void vcn_v3_0_enable_clock_gating(struct amdgpu_device *adev, int inst) | UVD_SUVD_CGC_CTRL__SMPA_MODE_MASK | UVD_SUVD_CGC_CTRL__MPBE0_MODE_MASK | UVD_SUVD_CGC_CTRL__MPBE1_MODE_MASK - | 0x00008000 - | 0x00010000 + | UVD_SUVD_CGC_CTRL__SIT_AV1_MODE_MASK + | UVD_SUVD_CGC_CTRL__SDB_AV1_MODE_MASK | UVD_SUVD_CGC_CTRL__MPC1_MODE_MASK | UVD_SUVD_CGC_CTRL__FBC_PCLK_MASK | UVD_SUVD_CGC_CTRL__FBC_CCLK_MASK); diff --git a/drivers/gpu/drm/amd/amdkfd/cik_event_interrupt.c b/drivers/gpu/drm/amd/amdkfd/cik_event_interrupt.c index 24b471734117..dcb1d89d776e 100644 --- a/drivers/gpu/drm/amd/amdkfd/cik_event_interrupt.c +++ b/drivers/gpu/drm/amd/amdkfd/cik_event_interrupt.c @@ -91,7 +91,7 @@ static void cik_event_interrupt_wq(struct kfd_dev *dev, (const struct cik_ih_ring_entry *)ih_ring_entry; uint32_t context_id = ihre->data & 0xfffffff; unsigned int vmid = (ihre->ring_id & 0x0000ff00) >> 8; - unsigned int pasid = (ihre->ring_id & 0xffff0000) >> 16; + u32 pasid = (ihre->ring_id & 0xffff0000) >> 16; if (pasid == 0) return; diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c index b7b16adb0615..222f1df1a6b6 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c @@ -97,6 +97,7 @@ void kfd_chardev_exit(void) device_destroy(kfd_class, MKDEV(kfd_char_dev_major, 0)); class_destroy(kfd_class); unregister_chrdev(kfd_char_dev_major, kfd_dev_name); + kfd_device = NULL; } struct device *kfd_chardev(void) @@ -1290,18 +1291,6 @@ static int kfd_ioctl_alloc_memory_of_gpu(struct file *filep, return -EINVAL; } - if (flags & KFD_IOC_ALLOC_MEM_FLAGS_DOORBELL) { - if (args->size != kfd_doorbell_process_slice(dev)) - return -EINVAL; - offset = kfd_get_process_doorbells(dev, p); - } else if (flags & KFD_IOC_ALLOC_MEM_FLAGS_MMIO_REMAP) { - if (args->size != PAGE_SIZE) - return -EINVAL; - offset = amdgpu_amdkfd_get_mmio_remap_phys_addr(dev->kgd); - if (!offset) - return -ENOMEM; - } - mutex_lock(&p->mutex); pdd = kfd_bind_process_to_device(dev, p); @@ -1310,6 +1299,24 @@ static int kfd_ioctl_alloc_memory_of_gpu(struct file *filep, goto err_unlock; } + if (flags & KFD_IOC_ALLOC_MEM_FLAGS_DOORBELL) { + if (args->size != kfd_doorbell_process_slice(dev)) { + err = -EINVAL; + goto err_unlock; + } + offset = kfd_get_process_doorbells(pdd); + } else if (flags & KFD_IOC_ALLOC_MEM_FLAGS_MMIO_REMAP) { + if (args->size != PAGE_SIZE) { + err = -EINVAL; + goto err_unlock; + } + offset = amdgpu_amdkfd_get_mmio_remap_phys_addr(dev->kgd); + if (!offset) { + err = -ENOMEM; + goto err_unlock; + } + } + err = amdgpu_amdkfd_gpuvm_alloc_memory_of_gpu( dev->kgd, args->va_addr, args->size, pdd->vm, (struct kgd_mem **) &mem, &offset, diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_crat.c b/drivers/gpu/drm/amd/amdkfd/kfd_crat.c index 3fac06b281ce..5e2254b9e931 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_crat.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_crat.c @@ -797,7 +797,8 @@ int kfd_create_crat_image_acpi(void **crat_image, size_t *size) return -ENODATA; } - pcrat_image = kmemdup(crat_table, crat_table->length, GFP_KERNEL); + pcrat_image = kvmalloc(crat_table->length, GFP_KERNEL); + memcpy(pcrat_image, crat_table, crat_table->length); if (!pcrat_image) return -ENOMEM; @@ -809,11 +810,10 @@ int kfd_create_crat_image_acpi(void **crat_image, size_t *size) /* Memory required to create Virtual CRAT. * Since there is no easy way to predict the amount of memory required, the - * following amount are allocated for CPU and GPU Virtual CRAT. This is + * following amount is allocated for GPU Virtual CRAT. This is * expected to cover all known conditions. But to be safe additional check * is put in the code to ensure we don't overwrite. */ -#define VCRAT_SIZE_FOR_CPU (2 * PAGE_SIZE) #define VCRAT_SIZE_FOR_GPU (4 * PAGE_SIZE) /* kfd_fill_cu_for_cpu - Fill in Compute info for the given CPU NUMA node @@ -964,7 +964,7 @@ static int kfd_create_vcrat_image_cpu(void *pcrat_image, size_t *size) #endif int ret = 0; - if (!pcrat_image || avail_size < VCRAT_SIZE_FOR_CPU) + if (!pcrat_image) return -EINVAL; /* Fill in CRAT Header. @@ -1364,30 +1364,37 @@ int kfd_create_crat_image_virtual(void **crat_image, size_t *size, uint32_t proximity_domain) { void *pcrat_image = NULL; - int ret = 0; + int ret = 0, num_nodes; + size_t dyn_size; if (!crat_image) return -EINVAL; *crat_image = NULL; - /* Allocate one VCRAT_SIZE_FOR_CPU for CPU virtual CRAT image and - * VCRAT_SIZE_FOR_GPU for GPU virtual CRAT image. This should cover - * all the current conditions. A check is put not to overwrite beyond - * allocated size + /* Allocate the CPU Virtual CRAT size based on the number of online + * nodes. Allocate VCRAT_SIZE_FOR_GPU for GPU virtual CRAT image. + * This should cover all the current conditions. A check is put not + * to overwrite beyond allocated size for GPUs */ switch (flags) { case COMPUTE_UNIT_CPU: - pcrat_image = kmalloc(VCRAT_SIZE_FOR_CPU, GFP_KERNEL); + num_nodes = num_online_nodes(); + dyn_size = sizeof(struct crat_header) + + num_nodes * (sizeof(struct crat_subtype_computeunit) + + sizeof(struct crat_subtype_memory) + + (num_nodes - 1) * sizeof(struct crat_subtype_iolink)); + pcrat_image = kvmalloc(dyn_size, GFP_KERNEL); if (!pcrat_image) return -ENOMEM; - *size = VCRAT_SIZE_FOR_CPU; + *size = dyn_size; + pr_debug("CRAT size is %ld", dyn_size); ret = kfd_create_vcrat_image_cpu(pcrat_image, size); break; case COMPUTE_UNIT_GPU: if (!kdev) return -EINVAL; - pcrat_image = kmalloc(VCRAT_SIZE_FOR_GPU, GFP_KERNEL); + pcrat_image = kvmalloc(VCRAT_SIZE_FOR_GPU, GFP_KERNEL); if (!pcrat_image) return -ENOMEM; *size = VCRAT_SIZE_FOR_GPU; @@ -1406,7 +1413,7 @@ int kfd_create_crat_image_virtual(void **crat_image, size_t *size, if (!ret) *crat_image = pcrat_image; else - kfree(pcrat_image); + kvfree(pcrat_image); return ret; } @@ -1419,5 +1426,5 @@ int kfd_create_crat_image_virtual(void **crat_image, size_t *size, */ void kfd_destroy_crat_image(void *crat_image) { - kfree(crat_image); + kvfree(crat_image); } diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_dbgdev.c b/drivers/gpu/drm/amd/amdkfd/kfd_dbgdev.c index 27bcc5b472f6..b258a3dae767 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_dbgdev.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_dbgdev.c @@ -45,7 +45,7 @@ static void dbgdev_address_watch_disable_nodiq(struct kfd_dev *dev) } static int dbgdev_diq_submit_ib(struct kfd_dbgdev *dbgdev, - unsigned int pasid, uint64_t vmid0_address, + u32 pasid, uint64_t vmid0_address, uint32_t *packet_buff, size_t size_in_bytes) { struct pm4__release_mem *rm_packet; diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_dbgmgr.h b/drivers/gpu/drm/amd/amdkfd/kfd_dbgmgr.h index a04a1fe1d0d9..f9c6df1fdc5c 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_dbgmgr.h +++ b/drivers/gpu/drm/amd/amdkfd/kfd_dbgmgr.h @@ -275,7 +275,7 @@ struct kfd_dbgdev { }; struct kfd_dbgmgr { - unsigned int pasid; + u32 pasid; struct kfd_dev *dev; struct kfd_dbgdev *dbgdev; }; diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device.c b/drivers/gpu/drm/amd/amdkfd/kfd_device.c index 0e71a0543f98..903170e59342 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device.c @@ -503,8 +503,8 @@ static const struct kfd_device_info *kfd_supported_devices[][2] = { #ifdef KFD_SUPPORT_IOMMU_V2 [CHIP_KAVERI] = {&kaveri_device_info, NULL}, [CHIP_CARRIZO] = {&carrizo_device_info, NULL}, - [CHIP_RAVEN] = {&raven_device_info, NULL}, #endif + [CHIP_RAVEN] = {&raven_device_info, NULL}, [CHIP_HAWAII] = {&hawaii_device_info, NULL}, [CHIP_TONGA] = {&tonga_device_info, NULL}, [CHIP_FIJI] = {&fiji_device_info, &fiji_vf_device_info}, @@ -583,6 +583,8 @@ struct kfd_dev *kgd2kfd_probe(struct kgd_dev *kgd, atomic_set(&kfd->sram_ecc_flag, 0); + ida_init(&kfd->doorbell_ida); + return kfd; } @@ -716,6 +718,8 @@ bool kgd2kfd_device_init(struct kfd_dev *kfd, kfd->unique_id = amdgpu_amdkfd_get_unique_id(kfd->kgd); + kfd->noretry = amdgpu_amdkfd_get_noretry(kfd->kgd); + if (kfd_interrupt_init(kfd)) { dev_err(kfd_device, "Error initializing interrupts\n"); goto kfd_interrupt_error; @@ -798,6 +802,7 @@ void kgd2kfd_device_exit(struct kfd_dev *kfd) kfd_interrupt_exit(kfd); kfd_topology_remove_device(kfd); kfd_doorbell_fini(kfd); + ida_destroy(&kfd->doorbell_ida); kfd_gtt_sa_fini(kfd); amdgpu_amdkfd_free_gtt_mem(kfd->kgd, kfd->gtt_mem); if (kfd->gws) diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c index 560adc57a050..c0ae04a08625 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c @@ -40,7 +40,7 @@ #define CIK_HPD_EOP_BYTES (1U << CIK_HPD_EOP_BYTES_LOG2) static int set_pasid_vmid_mapping(struct device_queue_manager *dqm, - unsigned int pasid, unsigned int vmid); + u32 pasid, unsigned int vmid); static int execute_queues_cpsch(struct device_queue_manager *dqm, enum kfd_unmap_queues_filter filter, @@ -191,9 +191,8 @@ static int allocate_doorbell(struct qcm_process_device *qpd, struct queue *q) } q->properties.doorbell_off = - kfd_get_doorbell_dw_offset_in_bar(dev, q->process, + kfd_get_doorbell_dw_offset_in_bar(dev, qpd_to_pdd(qpd), q->doorbell_id); - return 0; } @@ -650,9 +649,10 @@ static int evict_process_queues_nocpsch(struct device_queue_manager *dqm, goto out; pdd = qpd_to_pdd(qpd); - pr_info_ratelimited("Evicting PASID 0x%x queues\n", + pr_debug_ratelimited("Evicting PASID 0x%x queues\n", pdd->process->pasid); + pdd->last_evict_timestamp = get_jiffies_64(); /* Mark all queues as evicted. Deactivate all active queues on * the qpd. */ @@ -700,7 +700,7 @@ static int evict_process_queues_cpsch(struct device_queue_manager *dqm, goto out; pdd = qpd_to_pdd(qpd); - pr_info_ratelimited("Evicting PASID 0x%x queues\n", + pr_debug_ratelimited("Evicting PASID 0x%x queues\n", pdd->process->pasid); /* Mark all queues as evicted. Deactivate all active queues on @@ -714,6 +714,7 @@ static int evict_process_queues_cpsch(struct device_queue_manager *dqm, q->properties.is_active = false; decrement_queue_count(dqm, q->properties.type); } + pdd->last_evict_timestamp = get_jiffies_64(); retval = execute_queues_cpsch(dqm, qpd->is_debug ? KFD_UNMAP_QUEUES_FILTER_ALL_QUEUES : @@ -732,6 +733,7 @@ static int restore_process_queues_nocpsch(struct device_queue_manager *dqm, struct mqd_manager *mqd_mgr; struct kfd_process_device *pdd; uint64_t pd_base; + uint64_t eviction_duration; int retval, ret = 0; pdd = qpd_to_pdd(qpd); @@ -746,7 +748,7 @@ static int restore_process_queues_nocpsch(struct device_queue_manager *dqm, goto out; } - pr_info_ratelimited("Restoring PASID 0x%x queues\n", + pr_debug_ratelimited("Restoring PASID 0x%x queues\n", pdd->process->pasid); /* Update PD Base in QPD */ @@ -799,6 +801,8 @@ static int restore_process_queues_nocpsch(struct device_queue_manager *dqm, ret = retval; } qpd->evicted = 0; + eviction_duration = get_jiffies_64() - pdd->last_evict_timestamp; + atomic64_add(eviction_duration, &pdd->evict_duration_counter); out: if (mm) mmput(mm); @@ -812,6 +816,7 @@ static int restore_process_queues_cpsch(struct device_queue_manager *dqm, struct queue *q; struct kfd_process_device *pdd; uint64_t pd_base; + uint64_t eviction_duration; int retval = 0; pdd = qpd_to_pdd(qpd); @@ -826,7 +831,7 @@ static int restore_process_queues_cpsch(struct device_queue_manager *dqm, goto out; } - pr_info_ratelimited("Restoring PASID 0x%x queues\n", + pr_debug_ratelimited("Restoring PASID 0x%x queues\n", pdd->process->pasid); /* Update PD Base in QPD */ @@ -845,6 +850,8 @@ static int restore_process_queues_cpsch(struct device_queue_manager *dqm, retval = execute_queues_cpsch(dqm, KFD_UNMAP_QUEUES_FILTER_DYNAMIC_QUEUES, 0); qpd->evicted = 0; + eviction_duration = get_jiffies_64() - pdd->last_evict_timestamp; + atomic64_add(eviction_duration, &pdd->evict_duration_counter); out: dqm_unlock(dqm); return retval; @@ -924,7 +931,7 @@ out: } static int -set_pasid_vmid_mapping(struct device_queue_manager *dqm, unsigned int pasid, +set_pasid_vmid_mapping(struct device_queue_manager *dqm, u32 pasid, unsigned int vmid) { return dqm->dev->kfd2kgd->set_pasid_vmid_mapping( @@ -1192,6 +1199,8 @@ static int stop_cpsch(struct device_queue_manager *dqm) dqm->sched_running = false; dqm_unlock(dqm); + pm_release_ib(&dqm->packets); + kfd_gtt_sa_free(dqm->dev, dqm->fence_mem); pm_uninit(&dqm->packets, hanging); @@ -1302,7 +1311,7 @@ static int create_queue_cpsch(struct device_queue_manager *dqm, struct queue *q, if (q->properties.is_active) { increment_queue_count(dqm, q->properties.type); - retval = execute_queues_cpsch(dqm, + execute_queues_cpsch(dqm, KFD_UNMAP_QUEUES_FILTER_DYNAMIC_QUEUES, 0); } @@ -1955,8 +1964,7 @@ void device_queue_manager_uninit(struct device_queue_manager *dqm) kfree(dqm); } -int kfd_process_vm_fault(struct device_queue_manager *dqm, - unsigned int pasid) +int kfd_process_vm_fault(struct device_queue_manager *dqm, u32 pasid) { struct kfd_process_device *pdd; struct kfd_process *p = kfd_lookup_process_by_pasid(pasid); @@ -1964,6 +1972,7 @@ int kfd_process_vm_fault(struct device_queue_manager *dqm, if (!p) return -EINVAL; + WARN(debug_evictions, "Evicting pid %d", p->lead_thread->pid); pdd = kfd_get_process_device_data(dqm->dev, p); if (pdd) ret = dqm->ops.evict_process_queues(dqm, &pdd->qpd); diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_v10.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_v10.c index 72e4d61ac752..ad0593342333 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_v10.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_v10.c @@ -58,8 +58,9 @@ static int update_qpd_v10(struct device_queue_manager *dqm, /* check if sh_mem_config register already configured */ if (qpd->sh_mem_config == 0) { qpd->sh_mem_config = - SH_MEM_ALIGNMENT_MODE_UNALIGNED << - SH_MEM_CONFIG__ALIGNMENT_MODE__SHIFT; + (SH_MEM_ALIGNMENT_MODE_UNALIGNED << + SH_MEM_CONFIG__ALIGNMENT_MODE__SHIFT) | + (3 << SH_MEM_CONFIG__INITIAL_INST_PREFETCH__SHIFT); #if 0 /* TODO: * This shouldn't be an issue with Navi10. Verify. diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_v9.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_v9.c index 309f63a0b34a..eca6331efa94 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_v9.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_v9.c @@ -61,7 +61,7 @@ static int update_qpd_v9(struct device_queue_manager *dqm, qpd->sh_mem_config = SH_MEM_ALIGNMENT_MODE_UNALIGNED << SH_MEM_CONFIG__ALIGNMENT_MODE__SHIFT; - if (amdgpu_noretry && + if (dqm->dev->noretry && !dqm->dev->use_iommu_v2) qpd->sh_mem_config |= 1 << SH_MEM_CONFIG__RETRY_DISABLE__SHIFT; diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_doorbell.c b/drivers/gpu/drm/amd/amdkfd/kfd_doorbell.c index 8e0c00b9555e..768d153acff4 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_doorbell.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_doorbell.c @@ -31,9 +31,6 @@ * kernel queues using the first doorbell page reserved for the kernel. */ -static DEFINE_IDA(doorbell_ida); -static unsigned int max_doorbell_slices; - /* * Each device exposes a doorbell aperture, a PCI MMIO aperture that * receives 32-bit writes that are passed to queues as wptr values. @@ -84,9 +81,9 @@ int kfd_doorbell_init(struct kfd_dev *kfd) else return -ENOSPC; - if (!max_doorbell_slices || - doorbell_process_limit < max_doorbell_slices) - max_doorbell_slices = doorbell_process_limit; + if (!kfd->max_doorbell_slices || + doorbell_process_limit < kfd->max_doorbell_slices) + kfd->max_doorbell_slices = doorbell_process_limit; kfd->doorbell_base = kfd->shared_resources.doorbell_physical_address + doorbell_start_offset; @@ -130,6 +127,7 @@ int kfd_doorbell_mmap(struct kfd_dev *dev, struct kfd_process *process, struct vm_area_struct *vma) { phys_addr_t address; + struct kfd_process_device *pdd; /* * For simplicitly we only allow mapping of the entire doorbell @@ -138,9 +136,12 @@ int kfd_doorbell_mmap(struct kfd_dev *dev, struct kfd_process *process, if (vma->vm_end - vma->vm_start != kfd_doorbell_process_slice(dev)) return -EINVAL; - /* Calculate physical address of doorbell */ - address = kfd_get_process_doorbells(dev, process); + pdd = kfd_get_process_device_data(dev, process); + if (!pdd) + return -EINVAL; + /* Calculate physical address of doorbell */ + address = kfd_get_process_doorbells(pdd); vma->vm_flags |= VM_IO | VM_DONTCOPY | VM_DONTEXPAND | VM_NORESERVE | VM_DONTDUMP | VM_PFNMAP; @@ -226,7 +227,7 @@ void write_kernel_doorbell64(void __iomem *db, u64 value) } unsigned int kfd_get_doorbell_dw_offset_in_bar(struct kfd_dev *kfd, - struct kfd_process *process, + struct kfd_process_device *pdd, unsigned int doorbell_id) { /* @@ -236,7 +237,7 @@ unsigned int kfd_get_doorbell_dw_offset_in_bar(struct kfd_dev *kfd, * units regardless of the ASIC-dependent doorbell size. */ return kfd->doorbell_base_dw_offset + - process->doorbell_index + pdd->doorbell_index * kfd_doorbell_process_slice(kfd) / sizeof(u32) + doorbell_id * kfd->device_info->doorbell_size / sizeof(u32); } @@ -251,25 +252,24 @@ uint64_t kfd_get_number_elems(struct kfd_dev *kfd) } -phys_addr_t kfd_get_process_doorbells(struct kfd_dev *dev, - struct kfd_process *process) +phys_addr_t kfd_get_process_doorbells(struct kfd_process_device *pdd) { - return dev->doorbell_base + - process->doorbell_index * kfd_doorbell_process_slice(dev); + return pdd->dev->doorbell_base + + pdd->doorbell_index * kfd_doorbell_process_slice(pdd->dev); } -int kfd_alloc_process_doorbells(struct kfd_process *process) +int kfd_alloc_process_doorbells(struct kfd_dev *kfd, unsigned int *doorbell_index) { - int r = ida_simple_get(&doorbell_ida, 1, max_doorbell_slices, + int r = ida_simple_get(&kfd->doorbell_ida, 1, kfd->max_doorbell_slices, GFP_KERNEL); if (r > 0) - process->doorbell_index = r; + *doorbell_index = r; return r; } -void kfd_free_process_doorbells(struct kfd_process *process) +void kfd_free_process_doorbells(struct kfd_dev *kfd, unsigned int doorbell_index) { - if (process->doorbell_index) - ida_simple_remove(&doorbell_ida, process->doorbell_index); + if (doorbell_index) + ida_simple_remove(&kfd->doorbell_ida, doorbell_index); } diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_events.c b/drivers/gpu/drm/amd/amdkfd/kfd_events.c index a9583b95fcc1..ba2c2ce0c55a 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_events.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_events.c @@ -460,7 +460,7 @@ static void set_event_from_interrupt(struct kfd_process *p, } } -void kfd_signal_event_interrupt(unsigned int pasid, uint32_t partial_id, +void kfd_signal_event_interrupt(u32 pasid, uint32_t partial_id, uint32_t valid_id_bits) { struct kfd_event *ev = NULL; @@ -872,7 +872,7 @@ static void lookup_events_by_type_and_signal(struct kfd_process *p, } #ifdef KFD_SUPPORT_IOMMU_V2 -void kfd_signal_iommu_event(struct kfd_dev *dev, unsigned int pasid, +void kfd_signal_iommu_event(struct kfd_dev *dev, u32 pasid, unsigned long address, bool is_write_requested, bool is_execute_requested) { @@ -950,7 +950,7 @@ void kfd_signal_iommu_event(struct kfd_dev *dev, unsigned int pasid, } #endif /* KFD_SUPPORT_IOMMU_V2 */ -void kfd_signal_hw_exception_event(unsigned int pasid) +void kfd_signal_hw_exception_event(u32 pasid) { /* * Because we are called from arbitrary context (workqueue) as opposed @@ -971,7 +971,7 @@ void kfd_signal_hw_exception_event(unsigned int pasid) kfd_unref_process(p); } -void kfd_signal_vm_fault_event(struct kfd_dev *dev, unsigned int pasid, +void kfd_signal_vm_fault_event(struct kfd_dev *dev, u32 pasid, struct kfd_vm_fault_info *info) { struct kfd_event *ev; diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_events.h b/drivers/gpu/drm/amd/amdkfd/kfd_events.h index c7ac6c73af86..c8fe5dbdad55 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_events.h +++ b/drivers/gpu/drm/amd/amdkfd/kfd_events.h @@ -79,7 +79,7 @@ struct kfd_event { #define KFD_EVENT_TYPE_DEBUG 5 #define KFD_EVENT_TYPE_MEMORY 8 -extern void kfd_signal_event_interrupt(unsigned int pasid, uint32_t partial_id, - uint32_t valid_id_bits); +extern void kfd_signal_event_interrupt(u32 pasid, uint32_t partial_id, + uint32_t valid_id_bits); #endif diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_iommu.c b/drivers/gpu/drm/amd/amdkfd/kfd_iommu.c index 5a64915abaf7..66bbca61e3ef 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_iommu.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_iommu.c @@ -139,7 +139,7 @@ void kfd_iommu_unbind_process(struct kfd_process *p) } /* Callback for process shutdown invoked by the IOMMU driver */ -static void iommu_pasid_shutdown_callback(struct pci_dev *pdev, int pasid) +static void iommu_pasid_shutdown_callback(struct pci_dev *pdev, u32 pasid) { struct kfd_dev *dev = kfd_device_by_pci_dev(pdev); struct kfd_process *p; @@ -185,8 +185,8 @@ static void iommu_pasid_shutdown_callback(struct pci_dev *pdev, int pasid) } /* This function called by IOMMU driver on PPR failure */ -static int iommu_invalid_ppr_cb(struct pci_dev *pdev, int pasid, - unsigned long address, u16 flags) +static int iommu_invalid_ppr_cb(struct pci_dev *pdev, u32 pasid, + unsigned long address, u16 flags) { struct kfd_dev *dev; diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_module.c b/drivers/gpu/drm/amd/amdkfd/kfd_module.c index f4b7f7e6c40e..5e90fe642192 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_module.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_module.c @@ -70,6 +70,7 @@ err_create_wq: err_topology: kfd_chardev_exit(); err_ioctl: + pr_err("KFD is disabled due to module initialization failure\n"); return err; } diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_pasid.c b/drivers/gpu/drm/amd/amdkfd/kfd_pasid.c index 2a07c4f2cd0d..af5816f51e55 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_pasid.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_pasid.c @@ -51,7 +51,7 @@ unsigned int kfd_get_pasid_limit(void) return 1U << pasid_bits; } -unsigned int kfd_pasid_alloc(void) +u32 kfd_pasid_alloc(void) { int r = amdgpu_pasid_alloc(pasid_bits); @@ -63,7 +63,7 @@ unsigned int kfd_pasid_alloc(void) return 0; } -void kfd_pasid_free(unsigned int pasid) +void kfd_pasid_free(u32 pasid) { amdgpu_pasid_free(pasid); } diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h index 023629f28495..c77cf23032ac 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h +++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h @@ -314,6 +314,11 @@ struct kfd_dev { spinlock_t smi_lock; uint32_t reset_seq_num; + + struct ida doorbell_ida; + unsigned int max_doorbell_slices; + + int noretry; }; enum kfd_mempool { @@ -631,7 +636,7 @@ enum kfd_pdd_bound { PDD_BOUND_SUSPENDED, }; -#define MAX_SYSFS_FILENAME_LEN 11 +#define MAX_SYSFS_FILENAME_LEN 15 /* * SDMA counter runs at 100MHz frequency. @@ -692,6 +697,39 @@ struct kfd_process_device { uint64_t sdma_past_activity_counter; struct attribute attr_sdma; char sdma_filename[MAX_SYSFS_FILENAME_LEN]; + + /* Eviction activity tracking */ + uint64_t last_evict_timestamp; + atomic64_t evict_duration_counter; + struct attribute attr_evict; + + struct kobject *kobj_stats; + unsigned int doorbell_index; + + /* + * @cu_occupancy: Reports occupancy of Compute Units (CU) of a process + * that is associated with device encoded by "this" struct instance. The + * value reflects CU usage by all of the waves launched by this process + * on this device. A very important property of occupancy parameter is + * that its value is a snapshot of current use. + * + * Following is to be noted regarding how this parameter is reported: + * + * The number of waves that a CU can launch is limited by couple of + * parameters. These are encoded by struct amdgpu_cu_info instance + * that is part of every device definition. For GFX9 devices this + * translates to 40 waves (simd_per_cu * max_waves_per_simd) when waves + * do not use scratch memory and 32 waves (max_scratch_slots_per_cu) + * when they do use scratch memory. This could change for future + * devices and therefore this example should be considered as a guide. + * + * All CU's of a device are available for the process. This may not be true + * under certain conditions - e.g. CU masking. + * + * Finally number of CU's that are occupied by a process is affected by both + * number of CU's a device has along with number of other competing processes + */ + struct attribute attr_cu_occupancy; }; #define qpd_to_pdd(x) container_of(x, struct kfd_process_device, qpd) @@ -728,8 +766,7 @@ struct kfd_process { /* We want to receive a notification when the mm_struct is destroyed */ struct mmu_notifier mmu_notifier; - uint16_t pasid; - unsigned int doorbell_index; + u32 pasid; /* * List of kfd_process_device structures, @@ -805,7 +842,7 @@ int kfd_process_create_wq(void); void kfd_process_destroy_wq(void); struct kfd_process *kfd_create_process(struct file *filep); struct kfd_process *kfd_get_process(const struct task_struct *); -struct kfd_process *kfd_lookup_process_by_pasid(unsigned int pasid); +struct kfd_process *kfd_lookup_process_by_pasid(u32 pasid); struct kfd_process *kfd_lookup_process_by_mm(const struct mm_struct *mm); void kfd_unref_process(struct kfd_process *p); int kfd_process_evict_queues(struct kfd_process *p); @@ -846,8 +883,8 @@ int kfd_pasid_init(void); void kfd_pasid_exit(void); bool kfd_set_pasid_limit(unsigned int new_limit); unsigned int kfd_get_pasid_limit(void); -unsigned int kfd_pasid_alloc(void); -void kfd_pasid_free(unsigned int pasid); +u32 kfd_pasid_alloc(void); +void kfd_pasid_free(u32 pasid); /* Doorbells */ size_t kfd_doorbell_process_slice(struct kfd_dev *kfd); @@ -862,13 +899,13 @@ u32 read_kernel_doorbell(u32 __iomem *db); void write_kernel_doorbell(void __iomem *db, u32 value); void write_kernel_doorbell64(void __iomem *db, u64 value); unsigned int kfd_get_doorbell_dw_offset_in_bar(struct kfd_dev *kfd, - struct kfd_process *process, + struct kfd_process_device *pdd, unsigned int doorbell_id); -phys_addr_t kfd_get_process_doorbells(struct kfd_dev *dev, - struct kfd_process *process); -int kfd_alloc_process_doorbells(struct kfd_process *process); -void kfd_free_process_doorbells(struct kfd_process *process); - +phys_addr_t kfd_get_process_doorbells(struct kfd_process_device *pdd); +int kfd_alloc_process_doorbells(struct kfd_dev *kfd, + unsigned int *doorbell_index); +void kfd_free_process_doorbells(struct kfd_dev *kfd, + unsigned int doorbell_index); /* GTT Sub-Allocator */ int kfd_gtt_sa_allocate(struct kfd_dev *kfd, unsigned int size, @@ -933,7 +970,7 @@ void device_queue_manager_uninit(struct device_queue_manager *dqm); struct kernel_queue *kernel_queue_init(struct kfd_dev *dev, enum kfd_queue_type type); void kernel_queue_uninit(struct kernel_queue *kq, bool hanging); -int kfd_process_vm_fault(struct device_queue_manager *dqm, unsigned int pasid); +int kfd_process_vm_fault(struct device_queue_manager *dqm, u32 pasid); /* Process Queue Manager */ struct process_queue_node { @@ -1055,12 +1092,12 @@ int kfd_wait_on_events(struct kfd_process *p, uint32_t num_events, void __user *data, bool all, uint32_t user_timeout_ms, uint32_t *wait_result); -void kfd_signal_event_interrupt(unsigned int pasid, uint32_t partial_id, +void kfd_signal_event_interrupt(u32 pasid, uint32_t partial_id, uint32_t valid_id_bits); void kfd_signal_iommu_event(struct kfd_dev *dev, - unsigned int pasid, unsigned long address, - bool is_write_requested, bool is_execute_requested); -void kfd_signal_hw_exception_event(unsigned int pasid); + u32 pasid, unsigned long address, + bool is_write_requested, bool is_execute_requested); +void kfd_signal_hw_exception_event(u32 pasid); int kfd_set_event(struct kfd_process *p, uint32_t event_id); int kfd_reset_event(struct kfd_process *p, uint32_t event_id); int kfd_event_page_set(struct kfd_process *p, void *kernel_address, @@ -1071,7 +1108,7 @@ int kfd_event_create(struct file *devkfd, struct kfd_process *p, uint64_t *event_page_offset, uint32_t *event_slot_index); int kfd_event_destroy(struct kfd_process *p, uint32_t event_id); -void kfd_signal_vm_fault_event(struct kfd_dev *dev, unsigned int pasid, +void kfd_signal_vm_fault_event(struct kfd_dev *dev, u32 pasid, struct kfd_vm_fault_info *info); void kfd_signal_reset_event(struct kfd_dev *dev); diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process.c b/drivers/gpu/drm/amd/amdkfd/kfd_process.c index a0e12a79ab7d..65803e153a22 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_process.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_process.c @@ -249,6 +249,52 @@ cleanup: } } +/** + * @kfd_get_cu_occupancy() - Collect number of waves in-flight on this device + * by current process. Translates acquired wave count into number of compute units + * that are occupied. + * + * @atr: Handle of attribute that allows reporting of wave count. The attribute + * handle encapsulates GPU device it is associated with, thereby allowing collection + * of waves in flight, etc + * + * @buffer: Handle of user provided buffer updated with wave count + * + * Return: Number of bytes written to user buffer or an error value + */ +static int kfd_get_cu_occupancy(struct attribute *attr, char *buffer) +{ + int cu_cnt; + int wave_cnt; + int max_waves_per_cu; + struct kfd_dev *dev = NULL; + struct kfd_process *proc = NULL; + struct kfd_process_device *pdd = NULL; + + pdd = container_of(attr, struct kfd_process_device, attr_cu_occupancy); + dev = pdd->dev; + if (dev->kfd2kgd->get_cu_occupancy == NULL) + return -EINVAL; + + cu_cnt = 0; + proc = pdd->process; + if (pdd->qpd.queue_count == 0) { + pr_debug("Gpu-Id: %d has no active queues for process %d\n", + dev->id, proc->pasid); + return snprintf(buffer, PAGE_SIZE, "%d\n", cu_cnt); + } + + /* Collect wave count from device if it supports */ + wave_cnt = 0; + max_waves_per_cu = 0; + dev->kfd2kgd->get_cu_occupancy(dev->kgd, proc->pasid, &wave_cnt, + &max_waves_per_cu); + + /* Translate wave count to number of compute units */ + cu_cnt = (wave_cnt + (max_waves_per_cu - 1)) / max_waves_per_cu; + return snprintf(buffer, PAGE_SIZE, "%d\n", cu_cnt); +} + static ssize_t kfd_procfs_show(struct kobject *kobj, struct attribute *attr, char *buffer) { @@ -345,6 +391,32 @@ static ssize_t kfd_procfs_queue_show(struct kobject *kobj, return 0; } +static ssize_t kfd_procfs_stats_show(struct kobject *kobj, + struct attribute *attr, char *buffer) +{ + if (strcmp(attr->name, "evicted_ms") == 0) { + struct kfd_process_device *pdd = container_of(attr, + struct kfd_process_device, + attr_evict); + uint64_t evict_jiffies; + + evict_jiffies = atomic64_read(&pdd->evict_duration_counter); + + return snprintf(buffer, + PAGE_SIZE, + "%llu\n", + jiffies64_to_msecs(evict_jiffies)); + + /* Sysfs handle that gets CU occupancy is per device */ + } else if (strcmp(attr->name, "cu_occupancy") == 0) { + return kfd_get_cu_occupancy(attr, buffer); + } else { + pr_err("Invalid attribute"); + } + + return 0; +} + static struct attribute attr_queue_size = { .name = "size", .mode = KFD_SYSFS_FILE_MODE @@ -376,6 +448,19 @@ static struct kobj_type procfs_queue_type = { .default_attrs = procfs_queue_attrs, }; +static const struct sysfs_ops procfs_stats_ops = { + .show = kfd_procfs_stats_show, +}; + +static struct attribute *procfs_stats_attrs[] = { + NULL +}; + +static struct kobj_type procfs_stats_type = { + .sysfs_ops = &procfs_stats_ops, + .default_attrs = procfs_stats_attrs, +}; + int kfd_procfs_add_queue(struct queue *q) { struct kfd_process *proc; @@ -417,6 +502,72 @@ static int kfd_sysfs_create_file(struct kfd_process *p, struct attribute *attr, return ret; } +static int kfd_procfs_add_sysfs_stats(struct kfd_process *p) +{ + int ret = 0; + struct kfd_process_device *pdd; + char stats_dir_filename[MAX_SYSFS_FILENAME_LEN]; + + if (!p) + return -EINVAL; + + if (!p->kobj) + return -EFAULT; + + /* + * Create sysfs files for each GPU: + * - proc/<pid>/stats_<gpuid>/ + * - proc/<pid>/stats_<gpuid>/evicted_ms + * - proc/<pid>/stats_<gpuid>/cu_occupancy + */ + list_for_each_entry(pdd, &p->per_device_data, per_device_list) { + struct kobject *kobj_stats; + + snprintf(stats_dir_filename, MAX_SYSFS_FILENAME_LEN, + "stats_%u", pdd->dev->id); + kobj_stats = kfd_alloc_struct(kobj_stats); + if (!kobj_stats) + return -ENOMEM; + + ret = kobject_init_and_add(kobj_stats, + &procfs_stats_type, + p->kobj, + stats_dir_filename); + + if (ret) { + pr_warn("Creating KFD proc/stats_%s folder failed", + stats_dir_filename); + kobject_put(kobj_stats); + goto err; + } + + pdd->kobj_stats = kobj_stats; + pdd->attr_evict.name = "evicted_ms"; + pdd->attr_evict.mode = KFD_SYSFS_FILE_MODE; + sysfs_attr_init(&pdd->attr_evict); + ret = sysfs_create_file(kobj_stats, &pdd->attr_evict); + if (ret) + pr_warn("Creating eviction stats for gpuid %d failed", + (int)pdd->dev->id); + + /* Add sysfs file to report compute unit occupancy */ + if (pdd->dev->kfd2kgd->get_cu_occupancy != NULL) { + pdd->attr_cu_occupancy.name = "cu_occupancy"; + pdd->attr_cu_occupancy.mode = KFD_SYSFS_FILE_MODE; + sysfs_attr_init(&pdd->attr_cu_occupancy); + ret = sysfs_create_file(kobj_stats, + &pdd->attr_cu_occupancy); + if (ret) + pr_warn("Creating %s failed for gpuid: %d", + pdd->attr_cu_occupancy.name, + (int)pdd->dev->id); + } + } +err: + return ret; +} + + static int kfd_procfs_add_sysfs_files(struct kfd_process *p) { int ret = 0; @@ -452,7 +603,6 @@ static int kfd_procfs_add_sysfs_files(struct kfd_process *p) return ret; } - void kfd_procfs_del_queue(struct queue *q) { if (!q) @@ -660,6 +810,11 @@ struct kfd_process *kfd_create_process(struct file *filep) if (!process->kobj_queues) pr_warn("Creating KFD proc/queues folder failed"); + ret = kfd_procfs_add_sysfs_stats(process); + if (ret) + pr_warn("Creating sysfs stats dir for pid %d failed", + (int)process->lead_thread->pid); + ret = kfd_procfs_add_sysfs_files(process); if (ret) pr_warn("Creating sysfs usage file for pid %d failed", @@ -781,6 +936,8 @@ static void kfd_process_destroy_pdds(struct kfd_process *p) kfree(pdd->qpd.doorbell_bitmap); idr_destroy(&pdd->alloc_idr); + kfd_free_process_doorbells(pdd->dev, pdd->doorbell_index); + /* * before destroying pdd, make sure to report availability * for auto suspend @@ -816,6 +973,12 @@ static void kfd_process_wq_release(struct work_struct *work) list_for_each_entry(pdd, &p->per_device_data, per_device_list) { sysfs_remove_file(p->kobj, &pdd->attr_vram); sysfs_remove_file(p->kobj, &pdd->attr_sdma); + sysfs_remove_file(p->kobj, &pdd->attr_evict); + if (pdd->dev->kfd2kgd->get_cu_occupancy != NULL) + sysfs_remove_file(p->kobj, &pdd->attr_cu_occupancy); + kobject_del(pdd->kobj_stats); + kobject_put(pdd->kobj_stats); + pdd->kobj_stats = NULL; } kobject_del(p->kobj); @@ -833,8 +996,6 @@ static void kfd_process_wq_release(struct work_struct *work) kfd_event_free_process(p); kfd_pasid_free(p->pasid); - kfd_free_process_doorbells(p); - mutex_destroy(&p->mutex); put_task_struct(p->lead_thread); @@ -1012,9 +1173,6 @@ static struct kfd_process *create_process(const struct task_struct *thread) if (process->pasid == 0) goto err_alloc_pasid; - if (kfd_alloc_process_doorbells(process) < 0) - goto err_alloc_doorbells; - err = pqm_init(&process->pqm, process); if (err != 0) goto err_process_pqm_init; @@ -1042,8 +1200,6 @@ err_register_notifier: err_init_apertures: pqm_uninit(&process->pqm); err_process_pqm_init: - kfd_free_process_doorbells(process); -err_alloc_doorbells: kfd_pasid_free(process->pasid); err_alloc_pasid: mutex_destroy(&process->mutex); @@ -1106,10 +1262,14 @@ struct kfd_process_device *kfd_create_process_device_data(struct kfd_dev *dev, if (!pdd) return NULL; + if (kfd_alloc_process_doorbells(dev, &pdd->doorbell_index) < 0) { + pr_err("Failed to alloc doorbell for pdd\n"); + goto err_free_pdd; + } + if (init_doorbell_bitmap(&pdd->qpd, dev)) { pr_err("Failed to init doorbell for process\n"); - kfree(pdd); - return NULL; + goto err_free_pdd; } pdd->dev = dev; @@ -1125,12 +1285,17 @@ struct kfd_process_device *kfd_create_process_device_data(struct kfd_dev *dev, pdd->runtime_inuse = false; pdd->vram_usage = 0; pdd->sdma_past_activity_counter = 0; + atomic64_set(&pdd->evict_duration_counter, 0); list_add(&pdd->per_device_list, &p->per_device_data); /* Init idr used for memory handle translation */ idr_init(&pdd->alloc_idr); return pdd; + +err_free_pdd: + kfree(pdd); + return NULL; } /** @@ -1307,7 +1472,7 @@ void kfd_process_device_remove_obj_handle(struct kfd_process_device *pdd, } /* This increments the process->ref counter. */ -struct kfd_process *kfd_lookup_process_by_pasid(unsigned int pasid) +struct kfd_process *kfd_lookup_process_by_pasid(u32 pasid) { struct kfd_process *p, *ret_p = NULL; unsigned int temp; @@ -1488,6 +1653,7 @@ void kfd_suspend_all_processes(void) unsigned int temp; int idx = srcu_read_lock(&kfd_processes_srcu); + WARN(debug_evictions, "Evicting all processes"); hash_for_each_rcu(kfd_processes_table, temp, p, kfd_processes) { cancel_delayed_work_sync(&p->eviction_work); cancel_delayed_work_sync(&p->restore_work); diff --git a/drivers/gpu/drm/amd/display/Kconfig b/drivers/gpu/drm/amd/display/Kconfig index f24abf428534..60dfdd432aba 100644 --- a/drivers/gpu/drm/amd/display/Kconfig +++ b/drivers/gpu/drm/amd/display/Kconfig @@ -42,6 +42,7 @@ config DRM_AMD_DC_SI config DEBUG_KERNEL_DC bool "Enable kgdb break in DC" depends on DRM_AMD_DC + depends on KGDB help Choose this option if you want to hit kdgb_break in assert. diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index b24c14bfab31..e2b23486ba4c 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -228,17 +228,14 @@ static u32 dm_vblank_get_counter(struct amdgpu_device *adev, int crtc) return 0; else { struct amdgpu_crtc *acrtc = adev->mode_info.crtcs[crtc]; - struct dm_crtc_state *acrtc_state = to_dm_crtc_state( - acrtc->base.state); - - if (acrtc_state->stream == NULL) { + if (acrtc->dm_irq_params.stream == NULL) { DRM_ERROR("dc_stream_state is NULL for crtc '%d'!\n", crtc); return 0; } - return dc_stream_get_vblank_counter(acrtc_state->stream); + return dc_stream_get_vblank_counter(acrtc->dm_irq_params.stream); } } @@ -251,10 +248,8 @@ static int dm_crtc_get_scanoutpos(struct amdgpu_device *adev, int crtc, return -EINVAL; else { struct amdgpu_crtc *acrtc = adev->mode_info.crtcs[crtc]; - struct dm_crtc_state *acrtc_state = to_dm_crtc_state( - acrtc->base.state); - if (acrtc_state->stream == NULL) { + if (acrtc->dm_irq_params.stream == NULL) { DRM_ERROR("dc_stream_state is NULL for crtc '%d'!\n", crtc); return 0; @@ -264,7 +259,7 @@ static int dm_crtc_get_scanoutpos(struct amdgpu_device *adev, int crtc, * TODO rework base driver to use values directly. * for now parse it back into reg-format */ - dc_stream_get_scanoutpos(acrtc_state->stream, + dc_stream_get_scanoutpos(acrtc->dm_irq_params.stream, &v_blank_start, &v_blank_end, &h_position, @@ -323,6 +318,14 @@ get_crtc_by_otg_inst(struct amdgpu_device *adev, return NULL; } +static inline bool amdgpu_dm_vrr_active_irq(struct amdgpu_crtc *acrtc) +{ + return acrtc->dm_irq_params.freesync_config.state == + VRR_STATE_ACTIVE_VARIABLE || + acrtc->dm_irq_params.freesync_config.state == + VRR_STATE_ACTIVE_FIXED; +} + static inline bool amdgpu_dm_vrr_active(struct dm_crtc_state *dm_state) { return dm_state->freesync_config.state == VRR_STATE_ACTIVE_VARIABLE || @@ -343,7 +346,6 @@ static void dm_pflip_high_irq(void *interrupt_params) struct amdgpu_device *adev = irq_params->adev; unsigned long flags; struct drm_pending_vblank_event *e; - struct dm_crtc_state *acrtc_state; uint32_t vpos, hpos, v_blank_start, v_blank_end; bool vrr_active; @@ -375,12 +377,11 @@ static void dm_pflip_high_irq(void *interrupt_params) if (!e) WARN_ON(1); - acrtc_state = to_dm_crtc_state(amdgpu_crtc->base.state); - vrr_active = amdgpu_dm_vrr_active(acrtc_state); + vrr_active = amdgpu_dm_vrr_active_irq(amdgpu_crtc); /* Fixed refresh rate, or VRR scanout position outside front-porch? */ if (!vrr_active || - !dc_stream_get_scanoutpos(acrtc_state->stream, &v_blank_start, + !dc_stream_get_scanoutpos(amdgpu_crtc->dm_irq_params.stream, &v_blank_start, &v_blank_end, &hpos, &vpos) || (vpos < v_blank_start)) { /* Update to correct count and vblank timestamp if racing with @@ -425,7 +426,7 @@ static void dm_pflip_high_irq(void *interrupt_params) * of pageflip completion, so last_flip_vblank is the forbidden count * for queueing new pageflips if vsync + VRR is enabled. */ - amdgpu_crtc->last_flip_vblank = + amdgpu_crtc->dm_irq_params.last_flip_vblank = amdgpu_get_vblank_counter_kms(&amdgpu_crtc->base); amdgpu_crtc->pflip_status = AMDGPU_FLIP_NONE; @@ -441,17 +442,17 @@ static void dm_vupdate_high_irq(void *interrupt_params) struct common_irq_params *irq_params = interrupt_params; struct amdgpu_device *adev = irq_params->adev; struct amdgpu_crtc *acrtc; - struct dm_crtc_state *acrtc_state; unsigned long flags; + int vrr_active; acrtc = get_crtc_by_otg_inst(adev, irq_params->irq_src - IRQ_TYPE_VUPDATE); if (acrtc) { - acrtc_state = to_dm_crtc_state(acrtc->base.state); + vrr_active = amdgpu_dm_vrr_active_irq(acrtc); DRM_DEBUG_VBL("crtc:%d, vupdate-vrr:%d\n", acrtc->crtc_id, - amdgpu_dm_vrr_active(acrtc_state)); + vrr_active); /* Core vblank handling is done here after end of front-porch in * vrr mode, as vblank timestamping will give valid results @@ -459,22 +460,22 @@ static void dm_vupdate_high_irq(void *interrupt_params) * page-flip completion events that have been queued to us * if a pageflip happened inside front-porch. */ - if (amdgpu_dm_vrr_active(acrtc_state)) { + if (vrr_active) { drm_crtc_handle_vblank(&acrtc->base); /* BTR processing for pre-DCE12 ASICs */ - if (acrtc_state->stream && + if (acrtc->dm_irq_params.stream && adev->family < AMDGPU_FAMILY_AI) { spin_lock_irqsave(&adev_to_drm(adev)->event_lock, flags); mod_freesync_handle_v_update( adev->dm.freesync_module, - acrtc_state->stream, - &acrtc_state->vrr_params); + acrtc->dm_irq_params.stream, + &acrtc->dm_irq_params.vrr_params); dc_stream_adjust_vmin_vmax( adev->dm.dc, - acrtc_state->stream, - &acrtc_state->vrr_params.adjust); + acrtc->dm_irq_params.stream, + &acrtc->dm_irq_params.vrr_params.adjust); spin_unlock_irqrestore(&adev_to_drm(adev)->event_lock, flags); } } @@ -493,18 +494,17 @@ static void dm_crtc_high_irq(void *interrupt_params) struct common_irq_params *irq_params = interrupt_params; struct amdgpu_device *adev = irq_params->adev; struct amdgpu_crtc *acrtc; - struct dm_crtc_state *acrtc_state; unsigned long flags; + int vrr_active; acrtc = get_crtc_by_otg_inst(adev, irq_params->irq_src - IRQ_TYPE_VBLANK); if (!acrtc) return; - acrtc_state = to_dm_crtc_state(acrtc->base.state); + vrr_active = amdgpu_dm_vrr_active_irq(acrtc); DRM_DEBUG_VBL("crtc:%d, vupdate-vrr:%d, planes:%d\n", acrtc->crtc_id, - amdgpu_dm_vrr_active(acrtc_state), - acrtc_state->active_planes); + vrr_active, acrtc->dm_irq_params.active_planes); /** * Core vblank handling at start of front-porch is only possible @@ -512,7 +512,7 @@ static void dm_crtc_high_irq(void *interrupt_params) * valid results while done in front-porch. Otherwise defer it * to dm_vupdate_high_irq after end of front-porch. */ - if (!amdgpu_dm_vrr_active(acrtc_state)) + if (!vrr_active) drm_crtc_handle_vblank(&acrtc->base); /** @@ -527,14 +527,16 @@ static void dm_crtc_high_irq(void *interrupt_params) spin_lock_irqsave(&adev_to_drm(adev)->event_lock, flags); - if (acrtc_state->stream && acrtc_state->vrr_params.supported && - acrtc_state->freesync_config.state == VRR_STATE_ACTIVE_VARIABLE) { + if (acrtc->dm_irq_params.stream && + acrtc->dm_irq_params.vrr_params.supported && + acrtc->dm_irq_params.freesync_config.state == + VRR_STATE_ACTIVE_VARIABLE) { mod_freesync_handle_v_update(adev->dm.freesync_module, - acrtc_state->stream, - &acrtc_state->vrr_params); + acrtc->dm_irq_params.stream, + &acrtc->dm_irq_params.vrr_params); - dc_stream_adjust_vmin_vmax(adev->dm.dc, acrtc_state->stream, - &acrtc_state->vrr_params.adjust); + dc_stream_adjust_vmin_vmax(adev->dm.dc, acrtc->dm_irq_params.stream, + &acrtc->dm_irq_params.vrr_params.adjust); } /* @@ -549,7 +551,7 @@ static void dm_crtc_high_irq(void *interrupt_params) */ if (adev->family >= AMDGPU_FAMILY_RV && acrtc->pflip_status == AMDGPU_FLIP_SUBMITTED && - acrtc_state->active_planes == 0) { + acrtc->dm_irq_params.active_planes == 0) { if (acrtc->event) { drm_crtc_send_vblank_event(&acrtc->base, acrtc->event); acrtc->event = NULL; @@ -878,6 +880,45 @@ static int dm_dmub_hw_init(struct amdgpu_device *adev) return 0; } +static void amdgpu_check_debugfs_connector_property_change(struct amdgpu_device *adev, + struct drm_atomic_state *state) +{ + struct drm_connector *connector; + struct drm_crtc *crtc; + struct amdgpu_dm_connector *amdgpu_dm_connector; + struct drm_connector_state *conn_state; + struct dm_crtc_state *acrtc_state; + struct drm_crtc_state *crtc_state; + struct dc_stream_state *stream; + struct drm_device *dev = adev_to_drm(adev); + + list_for_each_entry(connector, &dev->mode_config.connector_list, head) { + + amdgpu_dm_connector = to_amdgpu_dm_connector(connector); + conn_state = connector->state; + + if (!(conn_state && conn_state->crtc)) + continue; + + crtc = conn_state->crtc; + acrtc_state = to_dm_crtc_state(crtc->state); + + if (!(acrtc_state && acrtc_state->stream)) + continue; + + stream = acrtc_state->stream; + + if (amdgpu_dm_connector->dsc_settings.dsc_force_enable || + amdgpu_dm_connector->dsc_settings.dsc_num_slices_v || + amdgpu_dm_connector->dsc_settings.dsc_num_slices_h || + amdgpu_dm_connector->dsc_settings.dsc_bits_per_pixel) { + conn_state = drm_atomic_get_connector_state(state, connector); + crtc_state = drm_atomic_get_crtc_state(state, crtc); + crtc_state->mode_changed = true; + } + } +} + static int amdgpu_dm_init(struct amdgpu_device *adev) { struct dc_init_data init_data; @@ -1425,9 +1466,6 @@ static int dm_late_init(void *handle) struct dmcu *dmcu = NULL; bool ret = true; - if (!adev->dm.fw_dmcu && !adev->dm.dmub_fw) - return detect_mst_link_for_all_connectors(adev_to_drm(adev)); - dmcu = adev->dm.dc->res_pool->dmcu; for (i = 0; i < 16; i++) @@ -3373,9 +3411,6 @@ static int amdgpu_dm_initialize_drm_device(struct amdgpu_device *adev) goto fail; } - /* No userspace support. */ - dm->dc->debug.disable_tri_buf = true; - return 0; fail: kfree(aencoder); @@ -4689,9 +4724,10 @@ create_stream_for_sink(struct amdgpu_dm_connector *aconnector, dc_link_get_link_cap(aconnector->dc_link)); #if defined(CONFIG_DRM_AMD_DC_DCN) - if (dsc_caps.is_dsc_supported) { + if (aconnector->dsc_settings.dsc_force_enable != DSC_CLK_FORCE_DISABLE && dsc_caps.is_dsc_supported) { /* Set DSC policy according to dsc_clock_en */ - dc_dsc_policy_set_enable_dsc_when_not_needed(aconnector->dsc_settings.dsc_clock_en); + dc_dsc_policy_set_enable_dsc_when_not_needed( + aconnector->dsc_settings.dsc_force_enable == DSC_CLK_FORCE_ENABLE); if (dc_dsc_compute_config(aconnector->dc_link->ctx->dc->res_pool->dscs[0], &dsc_caps, @@ -4701,16 +4737,14 @@ create_stream_for_sink(struct amdgpu_dm_connector *aconnector, &stream->timing.dsc_cfg)) stream->timing.flags.DSC = 1; /* Overwrite the stream flag if DSC is enabled through debugfs */ - if (aconnector->dsc_settings.dsc_clock_en) + if (aconnector->dsc_settings.dsc_force_enable == DSC_CLK_FORCE_ENABLE) stream->timing.flags.DSC = 1; - if (stream->timing.flags.DSC && aconnector->dsc_settings.dsc_slice_width) - stream->timing.dsc_cfg.num_slices_h = DIV_ROUND_UP(stream->timing.h_addressable, - aconnector->dsc_settings.dsc_slice_width); + if (stream->timing.flags.DSC && aconnector->dsc_settings.dsc_num_slices_h) + stream->timing.dsc_cfg.num_slices_h = aconnector->dsc_settings.dsc_num_slices_h; - if (stream->timing.flags.DSC && aconnector->dsc_settings.dsc_slice_height) - stream->timing.dsc_cfg.num_slices_v = DIV_ROUND_UP(stream->timing.v_addressable, - aconnector->dsc_settings.dsc_slice_height); + if (stream->timing.flags.DSC && aconnector->dsc_settings.dsc_num_slices_v) + stream->timing.dsc_cfg.num_slices_v = aconnector->dsc_settings.dsc_num_slices_v; if (stream->timing.flags.DSC && aconnector->dsc_settings.dsc_bits_per_pixel) stream->timing.dsc_cfg.bits_per_pixel = aconnector->dsc_settings.dsc_bits_per_pixel; @@ -4809,7 +4843,6 @@ dm_crtc_duplicate_state(struct drm_crtc *crtc) } state->active_planes = cur->active_planes; - state->vrr_params = cur->vrr_params; state->vrr_infopacket = cur->vrr_infopacket; state->abm_level = cur->abm_level; state->vrr_supported = cur->vrr_supported; @@ -5030,7 +5063,13 @@ static void amdgpu_dm_connector_destroy(struct drm_connector *connector) struct amdgpu_device *adev = drm_to_adev(connector->dev); struct amdgpu_display_manager *dm = &adev->dm; - drm_atomic_private_obj_fini(&aconnector->mst_mgr.base); + /* + * Call only if mst_mgr was iniitalized before since it's not done + * for all connector types. + */ + if (aconnector->mst_mgr.dev) + drm_dp_mst_topology_mgr_destroy(&aconnector->mst_mgr); + #if defined(CONFIG_BACKLIGHT_CLASS_DEVICE) ||\ defined(CONFIG_BACKLIGHT_CLASS_DEVICE_MODULE) @@ -5427,19 +5466,6 @@ static void dm_crtc_helper_disable(struct drm_crtc *crtc) { } -static bool does_crtc_have_active_cursor(struct drm_crtc_state *new_crtc_state) -{ - struct drm_device *dev = new_crtc_state->crtc->dev; - struct drm_plane *plane; - - drm_for_each_plane_mask(plane, dev, new_crtc_state->plane_mask) { - if (plane->type == DRM_PLANE_TYPE_CURSOR) - return true; - } - - return false; -} - static int count_crtc_active_planes(struct drm_crtc_state *new_crtc_state) { struct drm_atomic_state *state = new_crtc_state->state; @@ -5503,19 +5529,20 @@ static int dm_crtc_helper_atomic_check(struct drm_crtc *crtc, return ret; } - /* In some use cases, like reset, no stream is attached */ - if (!dm_crtc_state->stream) - return 0; - /* - * We want at least one hardware plane enabled to use - * the stream with a cursor enabled. + * We require the primary plane to be enabled whenever the CRTC is, otherwise + * drm_mode_cursor_universal may end up trying to enable the cursor plane while all other + * planes are disabled, which is not supported by the hardware. And there is legacy + * userspace which stops using the HW cursor altogether in response to the resulting EINVAL. */ - if (state->enable && state->active && - does_crtc_have_active_cursor(state) && - dm_crtc_state->active_planes == 0) + if (state->enable && + !(state->plane_mask & drm_plane_mask(crtc->primary))) return -EINVAL; + /* In some use cases, like reset, no stream is attached */ + if (!dm_crtc_state->stream) + return 0; + if (dc_validate_stream(dc, dm_crtc_state->stream) == DC_OK) return 0; @@ -6862,6 +6889,7 @@ static void update_freesync_state_on_stream( struct mod_vrr_params vrr_params; struct dc_info_packet vrr_infopacket = {0}; struct amdgpu_device *adev = dm->adev; + struct amdgpu_crtc *acrtc = to_amdgpu_crtc(new_crtc_state->base.crtc); unsigned long flags; if (!new_stream) @@ -6876,7 +6904,7 @@ static void update_freesync_state_on_stream( return; spin_lock_irqsave(&adev_to_drm(adev)->event_lock, flags); - vrr_params = new_crtc_state->vrr_params; + vrr_params = acrtc->dm_irq_params.vrr_params; if (surface) { mod_freesync_handle_preflip( @@ -6907,7 +6935,7 @@ static void update_freesync_state_on_stream( &vrr_infopacket); new_crtc_state->freesync_timing_changed |= - (memcmp(&new_crtc_state->vrr_params.adjust, + (memcmp(&acrtc->dm_irq_params.vrr_params.adjust, &vrr_params.adjust, sizeof(vrr_params.adjust)) != 0); @@ -6916,10 +6944,10 @@ static void update_freesync_state_on_stream( &vrr_infopacket, sizeof(vrr_infopacket)) != 0); - new_crtc_state->vrr_params = vrr_params; + acrtc->dm_irq_params.vrr_params = vrr_params; new_crtc_state->vrr_infopacket = vrr_infopacket; - new_stream->adjust = new_crtc_state->vrr_params.adjust; + new_stream->adjust = acrtc->dm_irq_params.vrr_params.adjust; new_stream->vrr_infopacket = vrr_infopacket; if (new_crtc_state->freesync_vrr_info_changed) @@ -6931,7 +6959,7 @@ static void update_freesync_state_on_stream( spin_unlock_irqrestore(&adev_to_drm(adev)->event_lock, flags); } -static void pre_update_freesync_state_on_stream( +static void update_stream_irq_parameters( struct amdgpu_display_manager *dm, struct dm_crtc_state *new_crtc_state) { @@ -6939,6 +6967,7 @@ static void pre_update_freesync_state_on_stream( struct mod_vrr_params vrr_params; struct mod_freesync_config config = new_crtc_state->freesync_config; struct amdgpu_device *adev = dm->adev; + struct amdgpu_crtc *acrtc = to_amdgpu_crtc(new_crtc_state->base.crtc); unsigned long flags; if (!new_stream) @@ -6952,7 +6981,7 @@ static void pre_update_freesync_state_on_stream( return; spin_lock_irqsave(&adev_to_drm(adev)->event_lock, flags); - vrr_params = new_crtc_state->vrr_params; + vrr_params = acrtc->dm_irq_params.vrr_params; if (new_crtc_state->vrr_supported && config.min_refresh_in_uhz && @@ -6969,11 +6998,14 @@ static void pre_update_freesync_state_on_stream( &config, &vrr_params); new_crtc_state->freesync_timing_changed |= - (memcmp(&new_crtc_state->vrr_params.adjust, - &vrr_params.adjust, - sizeof(vrr_params.adjust)) != 0); + (memcmp(&acrtc->dm_irq_params.vrr_params.adjust, + &vrr_params.adjust, sizeof(vrr_params.adjust)) != 0); - new_crtc_state->vrr_params = vrr_params; + new_crtc_state->freesync_config = config; + /* Copy state for access from DM IRQ handler */ + acrtc->dm_irq_params.freesync_config = config; + acrtc->dm_irq_params.active_planes = new_crtc_state->active_planes; + acrtc->dm_irq_params.vrr_params = vrr_params; spin_unlock_irqrestore(&adev_to_drm(adev)->event_lock, flags); } @@ -7197,7 +7229,7 @@ static void amdgpu_dm_commit_planes(struct drm_atomic_state *state, * on late submission of flips. */ spin_lock_irqsave(&pcrtc->dev->event_lock, flags); - last_flip_vblank = acrtc_attach->last_flip_vblank; + last_flip_vblank = acrtc_attach->dm_irq_params.last_flip_vblank; spin_unlock_irqrestore(&pcrtc->dev->event_lock, flags); } @@ -7281,7 +7313,7 @@ static void amdgpu_dm_commit_planes(struct drm_atomic_state *state, spin_lock_irqsave(&pcrtc->dev->event_lock, flags); dc_stream_adjust_vmin_vmax( dm->dc, acrtc_state->stream, - &acrtc_state->vrr_params.adjust); + &acrtc_attach->dm_irq_params.vrr_params.adjust); spin_unlock_irqrestore(&pcrtc->dev->event_lock, flags); } mutex_lock(&dm->dc_lock); @@ -7431,34 +7463,6 @@ static int amdgpu_dm_atomic_commit(struct drm_device *dev, struct drm_atomic_state *state, bool nonblock) { - struct drm_crtc *crtc; - struct drm_crtc_state *old_crtc_state, *new_crtc_state; - struct amdgpu_device *adev = drm_to_adev(dev); - int i; - - /* - * We evade vblank and pflip interrupts on CRTCs that are undergoing - * a modeset, being disabled, or have no active planes. - * - * It's done in atomic commit rather than commit tail for now since - * some of these interrupt handlers access the current CRTC state and - * potentially the stream pointer itself. - * - * Since the atomic state is swapped within atomic commit and not within - * commit tail this would leave to new state (that hasn't been committed yet) - * being accesssed from within the handlers. - * - * TODO: Fix this so we can do this in commit tail and not have to block - * in atomic check. - */ - for_each_oldnew_crtc_in_state(state, crtc, old_crtc_state, new_crtc_state, i) { - struct amdgpu_crtc *acrtc = to_amdgpu_crtc(crtc); - - if (old_crtc_state->active && - (!new_crtc_state->active || - drm_atomic_crtc_needs_modeset(new_crtc_state))) - manage_dm_interrupts(adev, acrtc, false); - } /* * Add check here for SoC's that support hardware cursor plane, to * unset legacy_cursor_update @@ -7509,6 +7513,20 @@ static void amdgpu_dm_atomic_commit_tail(struct drm_atomic_state *state) dc_resource_state_copy_construct_current(dm->dc, dc_state); } + for_each_oldnew_crtc_in_state (state, crtc, old_crtc_state, + new_crtc_state, i) { + struct amdgpu_crtc *acrtc = to_amdgpu_crtc(crtc); + + dm_old_crtc_state = to_dm_crtc_state(old_crtc_state); + + if (old_crtc_state->active && + (!new_crtc_state->active || + drm_atomic_crtc_needs_modeset(new_crtc_state))) { + manage_dm_interrupts(adev, acrtc, false); + dc_stream_release(dm_old_crtc_state->stream); + } + } + /* update changed items */ for_each_oldnew_crtc_in_state(state, crtc, old_crtc_state, new_crtc_state, i) { struct amdgpu_crtc *acrtc = to_amdgpu_crtc(crtc); @@ -7604,7 +7622,6 @@ static void amdgpu_dm_atomic_commit_tail(struct drm_atomic_state *state) if (!status) status = dc_stream_get_status_from_state(dc_state, dm_new_crtc_state->stream); - if (!status) DC_ERR("got no status for stream %p on acrtc%p\n", dm_new_crtc_state->stream, acrtc); else @@ -7730,8 +7747,8 @@ static void amdgpu_dm_atomic_commit_tail(struct drm_atomic_state *state) dm_new_crtc_state = to_dm_crtc_state(new_crtc_state); dm_old_crtc_state = to_dm_crtc_state(old_crtc_state); - /* Update freesync active state. */ - pre_update_freesync_state_on_stream(dm, dm_new_crtc_state); + /* For freesync config update on crtc state and params for irq */ + update_stream_irq_parameters(dm, dm_new_crtc_state); /* Handle vrr on->off / off->on transitions */ amdgpu_dm_handle_vrr_transition(dm_old_crtc_state, @@ -7747,10 +7764,15 @@ static void amdgpu_dm_atomic_commit_tail(struct drm_atomic_state *state) for_each_oldnew_crtc_in_state(state, crtc, old_crtc_state, new_crtc_state, i) { struct amdgpu_crtc *acrtc = to_amdgpu_crtc(crtc); + dm_new_crtc_state = to_dm_crtc_state(new_crtc_state); + if (new_crtc_state->active && (!old_crtc_state->active || drm_atomic_crtc_needs_modeset(new_crtc_state))) { + dc_stream_retain(dm_new_crtc_state->stream); + acrtc->dm_irq_params.stream = dm_new_crtc_state->stream; manage_dm_interrupts(adev, acrtc, true); + #ifdef CONFIG_DEBUG_FS /** * Frontend may have changed so reapply the CRC capture @@ -7994,8 +8016,6 @@ static void reset_freesync_config_for_crtc( { new_crtc_state->vrr_supported = false; - memset(&new_crtc_state->vrr_params, 0, - sizeof(new_crtc_state->vrr_params)); memset(&new_crtc_state->vrr_infopacket, 0, sizeof(new_crtc_state->vrr_infopacket)); } @@ -8566,6 +8586,8 @@ static int amdgpu_dm_atomic_check(struct drm_device *dev, int ret, i; bool lock_and_validation_needed = false; + amdgpu_check_debugfs_connector_property_change(adev, state); + ret = drm_atomic_helper_check_modeset(dev, state); if (ret) goto fail; diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h index a7856ae2e5f5..34f6369bf51f 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h @@ -149,6 +149,8 @@ struct amdgpu_dm_backlight_caps { * @cached_state: Caches device atomic state for suspend/resume * @cached_dc_state: Cached state of content streams * @compressor: Frame buffer compression buffer. See &struct dm_comressor_info + * @force_timing_sync: set via debugfs. When set, indicates that all connected + * displays will be forced to synchronize. */ struct amdgpu_display_manager { @@ -340,13 +342,19 @@ struct amdgpu_display_manager { * fake encoders used for DP MST. */ struct amdgpu_encoder mst_encoders[AMDGPU_DM_MAX_CRTC]; - bool force_timing_sync; + bool force_timing_sync; +}; + +enum dsc_clock_force_state { + DSC_CLK_FORCE_DEFAULT = 0, + DSC_CLK_FORCE_ENABLE, + DSC_CLK_FORCE_DISABLE, }; struct dsc_preferred_settings { - bool dsc_clock_en; - uint32_t dsc_slice_width; - uint32_t dsc_slice_height; + enum dsc_clock_force_state dsc_force_enable; + uint32_t dsc_num_slices_v; + uint32_t dsc_num_slices_h; uint32_t dsc_bits_per_pixel; }; @@ -434,7 +442,6 @@ struct dm_crtc_state { bool vrr_supported; struct mod_freesync_config freesync_config; - struct mod_vrr_params vrr_params; struct dc_info_packet vrr_infopacket; int abm_level; 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 94fcb086154c..8cd646eef096 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 @@ -111,7 +111,6 @@ static int parse_write_buffer_into_params(char *wr_buf, uint32_t wr_buf_size, if (*param_nums > max_param_num) *param_nums = max_param_num; -; wr_buf_ptr = wr_buf; /* reset buf pointer */ wr_buf_count = 0; /* number of char already checked */ @@ -265,7 +264,7 @@ static ssize_t dp_link_settings_write(struct file *f, const char __user *buf, if (!wr_buf) return -ENOSPC; - if (parse_write_buffer_into_params(wr_buf, wr_buf_size, + if (parse_write_buffer_into_params(wr_buf, size, (long *)param, buf, max_param_num, ¶m_nums)) { @@ -424,7 +423,7 @@ static ssize_t dp_phy_settings_write(struct file *f, const char __user *buf, if (!wr_buf) return -ENOSPC; - if (parse_write_buffer_into_params(wr_buf, wr_buf_size, + if (parse_write_buffer_into_params(wr_buf, size, (long *)param, buf, max_param_num, ¶m_nums)) { @@ -576,7 +575,7 @@ static ssize_t dp_phy_test_pattern_debugfs_write(struct file *f, const char __us if (!wr_buf) return -ENOSPC; - if (parse_write_buffer_into_params(wr_buf, wr_buf_size, + if (parse_write_buffer_into_params(wr_buf, size, (long *)param, buf, max_param_num, ¶m_nums)) { @@ -909,7 +908,7 @@ static ssize_t dp_dpcd_address_write(struct file *f, const char __user *buf, struct amdgpu_dm_connector *connector = file_inode(f)->i_private; if (size < sizeof(connector->debugfs_dpcd_address)) - return 0; + return -EINVAL; r = copy_from_user(&connector->debugfs_dpcd_address, buf, sizeof(connector->debugfs_dpcd_address)); @@ -924,7 +923,7 @@ static ssize_t dp_dpcd_size_write(struct file *f, const char __user *buf, struct amdgpu_dm_connector *connector = file_inode(f)->i_private; if (size < sizeof(connector->debugfs_dpcd_size)) - return 0; + return -EINVAL; r = copy_from_user(&connector->debugfs_dpcd_size, buf, sizeof(connector->debugfs_dpcd_size)); @@ -944,8 +943,8 @@ static ssize_t dp_dpcd_data_write(struct file *f, const char __user *buf, struct dc_link *link = connector->dc_link; uint32_t write_size = connector->debugfs_dpcd_size; - if (size < write_size) - return 0; + if (!write_size || size < write_size) + return -EINVAL; data = kzalloc(write_size, GFP_KERNEL); if (!data) @@ -968,7 +967,7 @@ static ssize_t dp_dpcd_data_read(struct file *f, char __user *buf, struct dc_link *link = connector->dc_link; uint32_t read_size = connector->debugfs_dpcd_size; - if (size < read_size) + if (!read_size || size < read_size) return 0; data = kzalloc(read_size, GFP_KERNEL); @@ -1059,12 +1058,17 @@ static int dp_dsc_fec_support_show(struct seq_file *m, void *data) * * echo 1 > /sys/kernel/debug/dri/0/DP-X/trigger_hotplug * + * This function can perform HPD unplug: + * + * echo 0 > /sys/kernel/debug/dri/0/DP-X/trigger_hotplug + * */ static ssize_t dp_trigger_hotplug(struct file *f, const char __user *buf, size_t size, loff_t *pos) { struct amdgpu_dm_connector *aconnector = file_inode(f)->i_private; struct drm_connector *connector = &aconnector->base; + struct dc_link *link = NULL; struct drm_device *dev = connector->dev; enum dc_connection_type new_connection_type = dc_connection_none; char *wr_buf = NULL; @@ -1086,11 +1090,13 @@ static ssize_t dp_trigger_hotplug(struct file *f, const char __user *buf, return -ENOSPC; } - if (parse_write_buffer_into_params(wr_buf, wr_buf_size, + if (parse_write_buffer_into_params(wr_buf, size, (long *)param, buf, max_param_num, - ¶m_nums)) + ¶m_nums)) { + kfree(wr_buf); return -EINVAL; + } if (param_nums <= 0) { DRM_DEBUG_DRIVER("user data not be read\n"); @@ -1115,11 +1121,33 @@ static ssize_t dp_trigger_hotplug(struct file *f, const char __user *buf, drm_modeset_unlock_all(dev); drm_kms_helper_hotplug_event(dev); + } else if (param[0] == 0) { + if (!aconnector->dc_link) + goto unlock; -unlock: - mutex_unlock(&aconnector->hpd_lock); + link = aconnector->dc_link; + + if (link->local_sink) { + dc_sink_release(link->local_sink); + link->local_sink = NULL; + } + + link->dpcd_sink_count = 0; + link->type = dc_connection_none; + link->dongle_max_pix_clk = 0; + + amdgpu_dm_update_connector_after_detect(aconnector); + + drm_modeset_lock_all(dev); + dm_restore_drm_connector_state(dev, connector); + drm_modeset_unlock_all(dev); + + drm_kms_helper_hotplug_event(dev); } +unlock: + mutex_unlock(&aconnector->hpd_lock); + kfree(wr_buf); return size; } @@ -1200,9 +1228,14 @@ static ssize_t dp_dsc_clock_en_read(struct file *f, char __user *buf, * * The write function: dp_dsc_clock_en_write * enables to force DSC on the connector. - * User can write to either force enable DSC + * User can write to either force enable or force disable DSC * on the next modeset or set it to driver default * + * Accepted inputs: + * 0 - default DSC enablement policy + * 1 - force enable DSC on the connector + * 2 - force disable DSC on the connector (might cause fail in atomic_check) + * * Writing DSC settings is done with the following command: * - To force enable DSC (you need to specify * connector like DP-1): @@ -1238,7 +1271,7 @@ static ssize_t dp_dsc_clock_en_write(struct file *f, const char __user *buf, return -ENOSPC; } - if (parse_write_buffer_into_params(wr_buf, wr_buf_size, + if (parse_write_buffer_into_params(wr_buf, size, (long *)param, buf, max_param_num, ¶m_nums)) { @@ -1262,7 +1295,12 @@ static ssize_t dp_dsc_clock_en_write(struct file *f, const char __user *buf, if (!pipe_ctx || !pipe_ctx->stream) goto done; - aconnector->dsc_settings.dsc_clock_en = param[0]; + if (param[0] == 1) + aconnector->dsc_settings.dsc_force_enable = DSC_CLK_FORCE_ENABLE; + else if (param[0] == 2) + aconnector->dsc_settings.dsc_force_enable = DSC_CLK_FORCE_DISABLE; + else + aconnector->dsc_settings.dsc_force_enable = DSC_CLK_FORCE_DEFAULT; done: kfree(wr_buf); @@ -1387,7 +1425,7 @@ static ssize_t dp_dsc_slice_width_write(struct file *f, const char __user *buf, return -ENOSPC; } - if (parse_write_buffer_into_params(wr_buf, wr_buf_size, + if (parse_write_buffer_into_params(wr_buf, size, (long *)param, buf, max_param_num, ¶m_nums)) { @@ -1411,7 +1449,12 @@ static ssize_t dp_dsc_slice_width_write(struct file *f, const char __user *buf, if (!pipe_ctx || !pipe_ctx->stream) goto done; - aconnector->dsc_settings.dsc_slice_width = param[0]; + if (param[0] > 0) + aconnector->dsc_settings.dsc_num_slices_h = DIV_ROUND_UP( + pipe_ctx->stream->timing.h_addressable, + param[0]); + else + aconnector->dsc_settings.dsc_num_slices_h = 0; done: kfree(wr_buf); @@ -1536,7 +1579,7 @@ static ssize_t dp_dsc_slice_height_write(struct file *f, const char __user *buf, return -ENOSPC; } - if (parse_write_buffer_into_params(wr_buf, wr_buf_size, + if (parse_write_buffer_into_params(wr_buf, size, (long *)param, buf, max_param_num, ¶m_nums)) { @@ -1560,7 +1603,12 @@ static ssize_t dp_dsc_slice_height_write(struct file *f, const char __user *buf, if (!pipe_ctx || !pipe_ctx->stream) goto done; - aconnector->dsc_settings.dsc_slice_height = param[0]; + if (param[0] > 0) + aconnector->dsc_settings.dsc_num_slices_v = DIV_ROUND_UP( + pipe_ctx->stream->timing.v_addressable, + param[0]); + else + aconnector->dsc_settings.dsc_num_slices_v = 0; done: kfree(wr_buf); @@ -1678,7 +1726,7 @@ static ssize_t dp_dsc_bits_per_pixel_write(struct file *f, const char __user *bu return -ENOSPC; } - if (parse_write_buffer_into_params(wr_buf, wr_buf_size, + if (parse_write_buffer_into_params(wr_buf, size, (long *)param, buf, max_param_num, ¶m_nums)) { @@ -2098,6 +2146,7 @@ static const struct { const struct file_operations *fops; } dp_debugfs_entries[] = { {"link_settings", &dp_link_settings_debugfs_fops}, + {"trigger_hotplug", &dp_trigger_hotplug_debugfs_fops}, {"phy_settings", &dp_phy_settings_debugfs_fop}, {"test_pattern", &dp_phy_test_pattern_fops}, #ifdef CONFIG_DRM_AMD_DC_HDCP diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.c index 694c5bc93665..c2cd184f0bbd 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.c @@ -604,7 +604,7 @@ struct hdcp_workqueue *hdcp_create_workqueue(struct amdgpu_device *adev, struct int i = 0; hdcp_work = kcalloc(max_caps, sizeof(*hdcp_work), GFP_KERNEL); - if (hdcp_work == NULL) + if (ZERO_OR_NULL_PTR(hdcp_work)) return NULL; hdcp_work->srm = kcalloc(PSP_HDCP_SRM_FIRST_GEN_MAX_SIZE, sizeof(*hdcp_work->srm), GFP_KERNEL); diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq_params.h b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq_params.h new file mode 100644 index 000000000000..45825a34f8eb --- /dev/null +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq_params.h @@ -0,0 +1,37 @@ +/* + * Copyright 2020 Advanced Micro Devices, Inc. + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of this software and associated documentation files (the "Software"), + * to deal in the Software without restriction, including without limitation + * the rights to use, copy, modify, merge, publish, distribute, sublicense, + * and/or sell copies of the Software, and to permit persons to whom the + * Software is furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR + * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, + * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR + * OTHER DEALINGS IN THE SOFTWARE. + * + * Authors: AMD + * + */ + +#ifndef __AMDGPU_DM_IRQ_PARAMS_H__ +#define __AMDGPU_DM_IRQ_PARAMS_H__ + +struct dm_irq_params { + u32 last_flip_vblank; + struct mod_vrr_params vrr_params; + struct dc_stream_state *stream; + int active_planes; + struct mod_freesync_config freesync_config; +}; + +#endif /* __AMDGPU_DM_IRQ_PARAMS_H__ */ diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c index adbb44822e94..eee19edeeee5 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c @@ -159,7 +159,20 @@ static bool validate_dsc_caps_on_connector(struct amdgpu_dm_connector *aconnecto u8 dsc_caps[16] = { 0 }; aconnector->dsc_aux = drm_dp_mst_dsc_aux_for_port(port); +#if defined(CONFIG_HP_HOOK_WORKAROUND) + /* + * drm_dp_mst_dsc_aux_for_port() will return NULL for certain configs + * because it only check the dsc/fec caps of the "port variable" and not the dock + * + * This case will return NULL: DSC capabe MST dock connected to a non fec/dsc capable display + * + * Workaround: explicitly check the use case above and use the mst dock's aux as dsc_aux + * + */ + if (!aconnector->dsc_aux && !port->parent->port_parent) + aconnector->dsc_aux = &aconnector->mst_port->dm_dp_aux.aux; +#endif if (!aconnector->dsc_aux) return false; @@ -453,9 +466,9 @@ struct dsc_mst_fairness_params { struct dc_dsc_bw_range bw_range; bool compression_possible; struct drm_dp_mst_port *port; - bool clock_overwrite; - uint32_t slice_width_overwrite; - uint32_t slice_height_overwrite; + enum dsc_clock_force_state clock_force_enable; + uint32_t num_slices_h; + uint32_t num_slices_v; uint32_t bpp_overwrite; }; @@ -496,15 +509,11 @@ static void set_dsc_configs_from_fairness_vars(struct dsc_mst_fairness_params *p else params[i].timing->dsc_cfg.bits_per_pixel = vars[i].bpp_x16; - if (params[i].slice_width_overwrite) - params[i].timing->dsc_cfg.num_slices_h = DIV_ROUND_UP( - params[i].timing->h_addressable, - params[i].slice_width_overwrite); + if (params[i].num_slices_h) + params[i].timing->dsc_cfg.num_slices_h = params[i].num_slices_h; - if (params[i].slice_height_overwrite) - params[i].timing->dsc_cfg.num_slices_v = DIV_ROUND_UP( - params[i].timing->v_addressable, - params[i].slice_height_overwrite); + if (params[i].num_slices_v) + params[i].timing->dsc_cfg.num_slices_v = params[i].num_slices_v; } else { params[i].timing->flags.DSC = 0; } @@ -638,7 +647,7 @@ static void try_disable_dsc(struct drm_atomic_state *state, for (i = 0; i < count; i++) { if (vars[i].dsc_enabled && vars[i].bpp_x16 == params[i].bw_range.max_target_bpp_x16 - && !params[i].clock_overwrite) { + && params[i].clock_force_enable == DSC_CLK_FORCE_DEFAULT) { kbps_increase[i] = params[i].bw_range.stream_kbps - params[i].bw_range.max_kbps; tried[i] = false; remaining_to_try += 1; @@ -718,11 +727,11 @@ static bool compute_mst_dsc_configs_for_link(struct drm_atomic_state *state, params[count].sink = stream->sink; aconnector = (struct amdgpu_dm_connector *)stream->dm_stream_context; params[count].port = aconnector->port; - params[count].clock_overwrite = aconnector->dsc_settings.dsc_clock_en; - if (params[count].clock_overwrite) + params[count].clock_force_enable = aconnector->dsc_settings.dsc_force_enable; + if (params[count].clock_force_enable == DSC_CLK_FORCE_ENABLE) debugfs_overwrite = true; - params[count].slice_width_overwrite = aconnector->dsc_settings.dsc_slice_width; - params[count].slice_height_overwrite = aconnector->dsc_settings.dsc_slice_height; + params[count].num_slices_h = aconnector->dsc_settings.dsc_num_slices_h; + params[count].num_slices_v = aconnector->dsc_settings.dsc_num_slices_v; params[count].bpp_overwrite = aconnector->dsc_settings.dsc_bits_per_pixel; params[count].compression_possible = stream->sink->dsc_caps.dsc_dec_caps.is_dsc_supported; dc_dsc_get_policy_for_timing(params[count].timing, &dsc_policy); @@ -756,7 +765,7 @@ static bool compute_mst_dsc_configs_for_link(struct drm_atomic_state *state, /* Try max compression */ for (i = 0; i < count; i++) { - if (params[i].compression_possible) { + if (params[i].compression_possible && params[i].clock_force_enable != DSC_CLK_FORCE_DISABLE) { vars[i].pbn = kbps_to_peak_pbn(params[i].bw_range.min_kbps); vars[i].dsc_enabled = true; vars[i].bpp_x16 = params[i].bw_range.min_target_bpp_x16; diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_pp_smu.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_pp_smu.c index c5f2216e59c4..6e575ffe34d0 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_pp_smu.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_pp_smu.c @@ -592,9 +592,6 @@ void pp_rv_set_wm_ranges(struct pp_smu *pp, if (pp_funcs && pp_funcs->set_watermarks_for_clocks_ranges) pp_funcs->set_watermarks_for_clocks_ranges(pp_handle, &wm_with_clock_ranges); - else if (adev->smu.ppt_funcs) - smu_set_watermarks_for_clock_ranges(&adev->smu, - &wm_with_clock_ranges); } void pp_rv_set_pme_wa_enable(struct pp_smu *pp) @@ -667,49 +664,8 @@ static enum pp_smu_status pp_nv_set_wm_ranges(struct pp_smu *pp, { const struct dc_context *ctx = pp->dm; struct amdgpu_device *adev = ctx->driver_context; - struct dm_pp_wm_sets_with_clock_ranges_soc15 wm_with_clock_ranges; - struct dm_pp_clock_range_for_dmif_wm_set_soc15 *wm_dce_clocks = - wm_with_clock_ranges.wm_dmif_clocks_ranges; - struct dm_pp_clock_range_for_mcif_wm_set_soc15 *wm_soc_clocks = - wm_with_clock_ranges.wm_mcif_clocks_ranges; - int32_t i; - wm_with_clock_ranges.num_wm_dmif_sets = ranges->num_reader_wm_sets; - wm_with_clock_ranges.num_wm_mcif_sets = ranges->num_writer_wm_sets; - - for (i = 0; i < wm_with_clock_ranges.num_wm_dmif_sets; i++) { - if (ranges->reader_wm_sets[i].wm_inst > 3) - wm_dce_clocks[i].wm_set_id = WM_SET_A; - else - wm_dce_clocks[i].wm_set_id = - ranges->reader_wm_sets[i].wm_inst; - wm_dce_clocks[i].wm_max_dcfclk_clk_in_khz = - ranges->reader_wm_sets[i].max_drain_clk_mhz * 1000; - wm_dce_clocks[i].wm_min_dcfclk_clk_in_khz = - ranges->reader_wm_sets[i].min_drain_clk_mhz * 1000; - wm_dce_clocks[i].wm_max_mem_clk_in_khz = - ranges->reader_wm_sets[i].max_fill_clk_mhz * 1000; - wm_dce_clocks[i].wm_min_mem_clk_in_khz = - ranges->reader_wm_sets[i].min_fill_clk_mhz * 1000; - } - - for (i = 0; i < wm_with_clock_ranges.num_wm_mcif_sets; i++) { - if (ranges->writer_wm_sets[i].wm_inst > 3) - wm_soc_clocks[i].wm_set_id = WM_SET_A; - else - wm_soc_clocks[i].wm_set_id = - ranges->writer_wm_sets[i].wm_inst; - wm_soc_clocks[i].wm_max_socclk_clk_in_khz = - ranges->writer_wm_sets[i].max_fill_clk_mhz * 1000; - wm_soc_clocks[i].wm_min_socclk_clk_in_khz = - ranges->writer_wm_sets[i].min_fill_clk_mhz * 1000; - wm_soc_clocks[i].wm_max_mem_clk_in_khz = - ranges->writer_wm_sets[i].max_drain_clk_mhz * 1000; - wm_soc_clocks[i].wm_min_mem_clk_in_khz = - ranges->writer_wm_sets[i].min_drain_clk_mhz * 1000; - } - - smu_set_watermarks_for_clock_ranges(&adev->smu, &wm_with_clock_ranges); + smu_set_watermarks_for_clock_ranges(&adev->smu, ranges); return PP_SMU_RESULT_OK; } @@ -810,7 +766,7 @@ pp_nv_set_hard_min_uclk_by_freq(struct pp_smu *pp, int mhz) } static enum pp_smu_status pp_nv_set_pstate_handshake_support( - struct pp_smu *pp, BOOLEAN pstate_handshake_supported) + struct pp_smu *pp, bool pstate_handshake_supported) { const struct dc_context *ctx = pp->dm; struct amdgpu_device *adev = ctx->driver_context; @@ -920,60 +876,8 @@ static enum pp_smu_status pp_rn_set_wm_ranges(struct pp_smu *pp, { const struct dc_context *ctx = pp->dm; struct amdgpu_device *adev = ctx->driver_context; - struct smu_context *smu = &adev->smu; - struct dm_pp_wm_sets_with_clock_ranges_soc15 wm_with_clock_ranges; - struct dm_pp_clock_range_for_dmif_wm_set_soc15 *wm_dce_clocks = - wm_with_clock_ranges.wm_dmif_clocks_ranges; - struct dm_pp_clock_range_for_mcif_wm_set_soc15 *wm_soc_clocks = - wm_with_clock_ranges.wm_mcif_clocks_ranges; - int32_t i; - - if (!smu->ppt_funcs) - return PP_SMU_RESULT_UNSUPPORTED; - - wm_with_clock_ranges.num_wm_dmif_sets = ranges->num_reader_wm_sets; - wm_with_clock_ranges.num_wm_mcif_sets = ranges->num_writer_wm_sets; - - for (i = 0; i < wm_with_clock_ranges.num_wm_dmif_sets; i++) { - if (ranges->reader_wm_sets[i].wm_inst > 3) - wm_dce_clocks[i].wm_set_id = WM_SET_A; - else - wm_dce_clocks[i].wm_set_id = - ranges->reader_wm_sets[i].wm_inst; - - wm_dce_clocks[i].wm_min_dcfclk_clk_in_khz = - ranges->reader_wm_sets[i].min_drain_clk_mhz; - - wm_dce_clocks[i].wm_max_dcfclk_clk_in_khz = - ranges->reader_wm_sets[i].max_drain_clk_mhz; - - wm_dce_clocks[i].wm_min_mem_clk_in_khz = - ranges->reader_wm_sets[i].min_fill_clk_mhz; - - wm_dce_clocks[i].wm_max_mem_clk_in_khz = - ranges->reader_wm_sets[i].max_fill_clk_mhz; - } - - for (i = 0; i < wm_with_clock_ranges.num_wm_mcif_sets; i++) { - if (ranges->writer_wm_sets[i].wm_inst > 3) - wm_soc_clocks[i].wm_set_id = WM_SET_A; - else - wm_soc_clocks[i].wm_set_id = - ranges->writer_wm_sets[i].wm_inst; - wm_soc_clocks[i].wm_min_socclk_clk_in_khz = - ranges->writer_wm_sets[i].min_fill_clk_mhz; - - wm_soc_clocks[i].wm_max_socclk_clk_in_khz = - ranges->writer_wm_sets[i].max_fill_clk_mhz; - - wm_soc_clocks[i].wm_min_mem_clk_in_khz = - ranges->writer_wm_sets[i].min_drain_clk_mhz; - - wm_soc_clocks[i].wm_max_mem_clk_in_khz = - ranges->writer_wm_sets[i].max_drain_clk_mhz; - } - smu_set_watermarks_for_clock_ranges(&adev->smu, &wm_with_clock_ranges); + smu_set_watermarks_for_clock_ranges(&adev->smu, ranges); return PP_SMU_RESULT_OK; } diff --git a/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c b/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c index 2d5c7daaee23..29d64e7e304f 100644 --- a/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c +++ b/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c @@ -847,6 +847,73 @@ static enum bp_result bios_parser_get_spread_spectrum_info( return result; } +static enum bp_result get_soc_bb_info_v4_4( + struct bios_parser *bp, + struct bp_soc_bb_info *soc_bb_info) +{ + enum bp_result result = BP_RESULT_OK; + struct atom_display_controller_info_v4_4 *disp_cntl_tbl = NULL; + + if (!soc_bb_info) + return BP_RESULT_BADINPUT; + + if (!DATA_TABLES(dce_info)) + return BP_RESULT_BADBIOSTABLE; + + if (!DATA_TABLES(smu_info)) + return BP_RESULT_BADBIOSTABLE; + + disp_cntl_tbl = GET_IMAGE(struct atom_display_controller_info_v4_4, + DATA_TABLES(dce_info)); + if (!disp_cntl_tbl) + return BP_RESULT_BADBIOSTABLE; + + soc_bb_info->dram_clock_change_latency_100ns = disp_cntl_tbl->max_mclk_chg_lat; + soc_bb_info->dram_sr_enter_exit_latency_100ns = disp_cntl_tbl->max_sr_enter_exit_lat; + soc_bb_info->dram_sr_exit_latency_100ns = disp_cntl_tbl->max_sr_exit_lat; + + return result; +} + +static enum bp_result bios_parser_get_soc_bb_info( + struct dc_bios *dcb, + struct bp_soc_bb_info *soc_bb_info) +{ + struct bios_parser *bp = BP_FROM_DCB(dcb); + enum bp_result result = BP_RESULT_UNSUPPORTED; + struct atom_common_table_header *header; + struct atom_data_revision tbl_revision; + + if (!soc_bb_info) /* check for bad input */ + return BP_RESULT_BADINPUT; + + if (!DATA_TABLES(dce_info)) + return BP_RESULT_UNSUPPORTED; + + header = GET_IMAGE(struct atom_common_table_header, + DATA_TABLES(dce_info)); + get_atom_data_table_revision(header, &tbl_revision); + + switch (tbl_revision.major) { + case 4: + switch (tbl_revision.minor) { + case 1: + case 2: + case 3: + break; + case 4: + result = get_soc_bb_info_v4_4(bp, soc_bb_info); + default: + break; + } + break; + default: + break; + } + + return result; +} + static enum bp_result get_embedded_panel_info_v2_1( struct bios_parser *bp, struct embedded_panel_info *info) @@ -2222,7 +2289,9 @@ static const struct dc_vbios_funcs vbios_funcs = { .get_atom_dc_golden_table = bios_get_atom_dc_golden_table, - .enable_lvtma_control = bios_parser_enable_lvtma_control + .enable_lvtma_control = bios_parser_enable_lvtma_control, + + .get_soc_bb_info = bios_parser_get_soc_bb_info, }; static bool bios_parser2_construct( diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dce112/dce112_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dce112/dce112_clk_mgr.c index d031bd3d3072..807dca8f7d7a 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dce112/dce112_clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dce112/dce112_clk_mgr.c @@ -79,8 +79,7 @@ int dce112_set_clock(struct clk_mgr *clk_mgr_base, int requested_clk_khz) memset(&dce_clk_params, 0, sizeof(dce_clk_params)); /* Make sure requested clock isn't lower than minimum threshold*/ - if (requested_clk_khz > 0) - requested_clk_khz = max(requested_clk_khz, + requested_clk_khz = max(requested_clk_khz, clk_mgr_dce->base.dentist_vco_freq_khz / 62); dce_clk_params.target_clock_frequency = requested_clk_khz; diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dce60/dce60_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dce60/dce60_clk_mgr.c index c11c6b3a787d..0267644717b2 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dce60/dce60_clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dce60/dce60_clk_mgr.c @@ -80,7 +80,7 @@ static const struct state_dependent_clocks dce60_max_clks_by_state[] = { /* ClocksStatePerformance */ { .display_clk_khz = 600000, .pixel_clk_khz = 400000 } }; -int dce60_get_dp_ref_freq_khz(struct clk_mgr *clk_mgr_base) +static int dce60_get_dp_ref_freq_khz(struct clk_mgr *clk_mgr_base) { struct clk_mgr_internal *clk_mgr = TO_CLK_MGR_INTERNAL(clk_mgr_base); int dprefclk_wdivider; diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.c index 543afa34d87a..2f8fee05547a 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.c @@ -761,6 +761,7 @@ void rn_clk_mgr_construct( { struct dc_debug_options *debug = &ctx->dc->debug; struct dpm_clocks clock_table = { 0 }; + enum pp_smu_status status = 0; clk_mgr->base.ctx = ctx; clk_mgr->base.funcs = &dcn21_funcs; @@ -783,7 +784,6 @@ void rn_clk_mgr_construct( } else { struct clk_log_info log_info = {0}; - clk_mgr->smu_ver = rn_vbios_smu_get_smu_version(clk_mgr); clk_mgr->periodic_retraining_disabled = rn_vbios_smu_is_periodic_retraining_disabled(clk_mgr); /* SMU Version 55.51.0 and up no longer have an issue @@ -818,8 +818,10 @@ void rn_clk_mgr_construct( clk_mgr->base.bw_params = &rn_bw_params; if (pp_smu && pp_smu->rn_funcs.get_dpm_clock_table) { - pp_smu->rn_funcs.get_dpm_clock_table(&pp_smu->rn_funcs.pp_smu, &clock_table); - if (ctx->dc_bios && ctx->dc_bios->integrated_info) { + status = pp_smu->rn_funcs.get_dpm_clock_table(&pp_smu->rn_funcs.pp_smu, &clock_table); + + if (status == PP_SMU_RESULT_OK && + ctx->dc_bios && ctx->dc_bios->integrated_info) { rn_clk_mgr_helper_populate_bw_params (clk_mgr->base.bw_params, &clock_table, ctx->dc_bios->integrated_info); } } diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c index dc463d99ef50..45ad05f6e03b 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc.c @@ -735,6 +735,8 @@ static bool dc_construct(struct dc *dc, dc->clk_mgr->force_smu_not_present = init_params->force_smu_not_present; #endif + dc->debug.force_ignore_link_settings = init_params->force_ignore_link_settings; + if (dc->res_pool->funcs->update_bw_bounding_box) dc->res_pool->funcs->update_bw_bounding_box(dc, dc->clk_mgr->bw_params); @@ -842,6 +844,60 @@ static void disable_dangling_plane(struct dc *dc, struct dc_state *context) dc_release_state(current_ctx); } +static void disable_vbios_mode_if_required( + struct dc *dc, + struct dc_state *context) +{ + unsigned int i, j; + + /* check if timing_changed, disable stream*/ + for (i = 0; i < dc->res_pool->pipe_count; i++) { + struct dc_stream_state *stream = NULL; + struct dc_link *link = NULL; + struct pipe_ctx *pipe = NULL; + + pipe = &context->res_ctx.pipe_ctx[i]; + stream = pipe->stream; + if (stream == NULL) + continue; + + if (stream->link->local_sink && + stream->link->local_sink->sink_signal == SIGNAL_TYPE_EDP) { + link = stream->link; + } + + if (link != NULL) { + unsigned int enc_inst, tg_inst = 0; + unsigned int pix_clk_100hz; + + enc_inst = link->link_enc->funcs->get_dig_frontend(link->link_enc); + if (enc_inst != ENGINE_ID_UNKNOWN) { + for (j = 0; j < dc->res_pool->stream_enc_count; j++) { + if (dc->res_pool->stream_enc[j]->id == enc_inst) { + tg_inst = dc->res_pool->stream_enc[j]->funcs->dig_source_otg( + dc->res_pool->stream_enc[j]); + break; + } + } + + dc->res_pool->dp_clock_source->funcs->get_pixel_clk_frequency_100hz( + dc->res_pool->dp_clock_source, + tg_inst, &pix_clk_100hz); + + if (link->link_status.link_active) { + uint32_t requested_pix_clk_100hz = + pipe->stream_res.pix_clk_params.requested_pix_clk_100hz; + + if (pix_clk_100hz != requested_pix_clk_100hz) { + core_link_disable_stream(pipe); + pipe->stream->dpms_off = false; + } + } + } + } + } +} + static void wait_for_no_pipes_pending(struct dc *dc, struct dc_state *context) { int i; @@ -1246,6 +1302,19 @@ void dc_trigger_sync(struct dc *dc, struct dc_state *context) } } +static uint8_t get_stream_mask(struct dc *dc, struct dc_state *context) +{ + int i; + unsigned int stream_mask = 0; + + for (i = 0; i < dc->res_pool->pipe_count; i++) { + if (context->res_ctx.pipe_ctx[i].stream) + stream_mask |= 1 << i; + } + + return stream_mask; +} + /* * Applies given context to HW and copy it into current context. * It's up to the user to release the src context afterwards. @@ -1265,15 +1334,17 @@ static enum dc_status dc_commit_state_no_check(struct dc *dc, struct dc_state *c for (i = 0; i < context->stream_count; i++) dc_streams[i] = context->streams[i]; - if (!dcb->funcs->is_accelerated_mode(dcb)) + if (!dcb->funcs->is_accelerated_mode(dcb)) { + disable_vbios_mode_if_required(dc, context); dc->hwss.enable_accelerated_mode(dc, context); + } - for (i = 0; i < context->stream_count; i++) { + for (i = 0; i < context->stream_count; i++) if (context->streams[i]->apply_seamless_boot_optimization) dc->optimize_seamless_boot_streams++; - } - if (dc->optimize_seamless_boot_streams == 0) + if (context->stream_count > dc->optimize_seamless_boot_streams || + context->stream_count == 0) dc->hwss.prepare_bandwidth(dc, context); disable_dangling_plane(dc, context); @@ -1355,13 +1426,19 @@ static enum dc_status dc_commit_state_no_check(struct dc *dc, struct dc_state *c dc_enable_stereo(dc, context, dc_streams, context->stream_count); - if (dc->optimize_seamless_boot_streams == 0) { + if (context->stream_count > dc->optimize_seamless_boot_streams || + context->stream_count == 0) { /* Must wait for no flips to be pending before doing optimize bw */ wait_for_no_pipes_pending(dc, context); /* pplib is notified if disp_num changed */ dc->hwss.optimize_bandwidth(dc, context); } + context->stream_mask = get_stream_mask(dc, context); + + if (context->stream_mask != dc->current_state->stream_mask) + dc_dmub_srv_notify_stream_mask(dc->ctx->dmub_srv, context->stream_mask); + for (i = 0; i < context->stream_count; i++) context->streams[i]->mode_changed = false; @@ -1481,13 +1558,8 @@ bool dc_post_update_surfaces_to_stream(struct dc *dc) return true; } -struct dc_state *dc_create_state(struct dc *dc) +static void init_state(struct dc *dc, struct dc_state *context) { - struct dc_state *context = kvzalloc(sizeof(struct dc_state), - GFP_KERNEL); - - if (!context) - return NULL; /* Each context must have their own instance of VBA and in order to * initialize and obtain IP and SOC the base DML instance from DC is * initially copied into every context @@ -1495,6 +1567,17 @@ struct dc_state *dc_create_state(struct dc *dc) #ifdef CONFIG_DRM_AMD_DC_DCN memcpy(&context->bw_ctx.dml, &dc->dml, sizeof(struct display_mode_lib)); #endif +} + +struct dc_state *dc_create_state(struct dc *dc) +{ + struct dc_state *context = kvzalloc(sizeof(struct dc_state), + GFP_KERNEL); + + if (!context) + return NULL; + + init_state(dc, context); kref_init(&context->refcount); @@ -2415,8 +2498,7 @@ static void commit_planes_for_stream(struct dc *dc, plane_state->triplebuffer_flips = false; if (update_type == UPDATE_TYPE_FAST && dc->hwss.program_triplebuffer != NULL && - !plane_state->flip_immediate && - !dc->debug.disable_tri_buf) { + !plane_state->flip_immediate && dc->debug.enable_tri_buf) { /*triple buffer for VUpdate only*/ plane_state->triplebuffer_flips = true; } @@ -2443,8 +2525,7 @@ static void commit_planes_for_stream(struct dc *dc, ASSERT(!pipe_ctx->plane_state->triplebuffer_flips); - if (dc->hwss.program_triplebuffer != NULL && - !dc->debug.disable_tri_buf) { + if (dc->hwss.program_triplebuffer != NULL && dc->debug.enable_tri_buf) { /*turn off triple buffer for full update*/ dc->hwss.program_triplebuffer( dc, pipe_ctx, pipe_ctx->plane_state->triplebuffer_flips); @@ -2509,8 +2590,7 @@ static void commit_planes_for_stream(struct dc *dc, if (pipe_ctx->plane_state != plane_state) continue; /*program triple buffer after lock based on flip type*/ - if (dc->hwss.program_triplebuffer != NULL && - !dc->debug.disable_tri_buf) { + if (dc->hwss.program_triplebuffer != NULL && dc->debug.enable_tri_buf) { /*only enable triplebuffer for fast_update*/ dc->hwss.program_triplebuffer( dc, pipe_ctx, plane_state->triplebuffer_flips); @@ -2965,7 +3045,7 @@ bool dc_set_psr_allow_active(struct dc *dc, bool enable) if (enable && !link->psr_settings.psr_allow_active) return dc_link_set_psr_allow_active(link, true, false); else if (!enable && link->psr_settings.psr_allow_active) - return dc_link_set_psr_allow_active(link, false, false); + return dc_link_set_psr_allow_active(link, false, true); } } @@ -3018,4 +3098,10 @@ void dc_lock_memory_clock_frequency(struct dc *dc) if (dc->current_state->res_ctx.pipe_ctx[i].plane_state) core_link_enable_stream(dc->current_state, &dc->current_state->res_ctx.pipe_ctx[i]); } + +bool dc_is_plane_eligible_for_idle_optimizaitons(struct dc *dc, + struct dc_plane_state *plane) +{ + return false; +} #endif diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/core/dc_hw_sequencer.c index c026b393f3c5..2a9080400bdd 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_hw_sequencer.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_hw_sequencer.c @@ -177,7 +177,7 @@ static bool is_ycbcr709_limited_type( ret = true; return ret; } -enum dc_color_space_type get_color_space_type(enum dc_color_space color_space) +static enum dc_color_space_type get_color_space_type(enum dc_color_space color_space) { enum dc_color_space_type type = COLOR_SPACE_RGB_TYPE; diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link.c b/drivers/gpu/drm/amd/display/dc/core/dc_link.c index 437d1a7a16fe..fec87a2e210c 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_link.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_link.c @@ -2441,7 +2441,7 @@ enum dc_status dc_link_validate_mode_timing( /* A hack to avoid failing any modes for EDID override feature on * topology change such as lower quality cable for DP or different dongle */ - if (link->remote_sinks[0]) + if (link->remote_sinks[0] && link->remote_sinks[0]->sink_signal == SIGNAL_TYPE_VIRTUAL) return DC_OK; /* Passive Dongle */ @@ -2566,7 +2566,7 @@ bool dc_link_set_psr_allow_active(struct dc_link *link, bool allow_active, bool link->psr_settings.psr_allow_active = allow_active; if (psr != NULL && link->psr_settings.psr_feature_enabled) - psr->funcs->psr_enable(psr, allow_active); + psr->funcs->psr_enable(psr, allow_active, wait); else if ((dmcu != NULL && dmcu->funcs->is_dmcu_initialized(dmcu)) && link->psr_settings.psr_feature_enabled) dmcu->funcs->set_psr_enable(dmcu, allow_active, wait); else @@ -2946,7 +2946,7 @@ enum dc_status dc_link_allocate_mst_payload(struct pipe_ctx *pipe_ctx) pbn = get_pbn_from_timing(pipe_ctx); avg_time_slots_per_mtp = dc_fixpt_div(pbn, pbn_per_slot); - stream_encoder->funcs->set_mst_bandwidth( + stream_encoder->funcs->set_throttled_vcp_size( stream_encoder, avg_time_slots_per_mtp); @@ -2974,7 +2974,7 @@ static enum dc_status deallocate_mst_payload(struct pipe_ctx *pipe_ctx) */ /* slot X.Y */ - stream_encoder->funcs->set_mst_bandwidth( + stream_encoder->funcs->set_throttled_vcp_size( stream_encoder, avg_time_slots_per_mtp); diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_ddc.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_ddc.c index b984eecca58b..dec12de37642 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_link_ddc.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_ddc.c @@ -148,14 +148,6 @@ static uint32_t dal_ddc_i2c_payloads_get_count(struct i2c_payloads *p) return p->payloads.count; } -static void dal_ddc_i2c_payloads_destroy(struct i2c_payloads *p) -{ - if (!p) - return; - - dal_vector_destruct(&p->payloads); -} - #define DDC_MIN(a, b) (((a) < (b)) ? (a) : (b)) void dal_ddc_i2c_payloads_add( @@ -582,7 +574,7 @@ bool dal_ddc_service_query_ddc_data( ddc->link, &command); - dal_ddc_i2c_payloads_destroy(&payloads); + dal_vector_destruct(&payloads.payloads); } return success; diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c index d1d95d3e248a..ff1e9963ec7a 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c @@ -49,14 +49,31 @@ static struct dc_link_settings get_common_supported_link_settings( struct dc_link_settings link_setting_a, struct dc_link_settings link_setting_b); -static uint32_t get_training_aux_rd_interval( - struct dc_link *link, - uint32_t default_wait_in_micro_secs) +static uint32_t get_cr_training_aux_rd_interval(struct dc_link *link, + const struct dc_link_settings *link_settings) { union training_aux_rd_interval training_rd_interval; + uint32_t wait_in_micro_secs = 100; memset(&training_rd_interval, 0, sizeof(training_rd_interval)); + core_link_read_dpcd( + link, + DP_TRAINING_AUX_RD_INTERVAL, + (uint8_t *)&training_rd_interval, + sizeof(training_rd_interval)); + if (training_rd_interval.bits.TRAINIG_AUX_RD_INTERVAL) + wait_in_micro_secs = training_rd_interval.bits.TRAINIG_AUX_RD_INTERVAL * 4000; + return wait_in_micro_secs; +} +static uint32_t get_eq_training_aux_rd_interval( + struct dc_link *link, + const struct dc_link_settings *link_settings) +{ + union training_aux_rd_interval training_rd_interval; + uint32_t wait_in_micro_secs = 400; + + memset(&training_rd_interval, 0, sizeof(training_rd_interval)); /* overwrite the delay if rev > 1.1*/ if (link->dpcd_caps.dpcd_rev.raw >= DPCD_REV_12) { /* DP 1.2 or later - retrieve delay through @@ -68,10 +85,10 @@ static uint32_t get_training_aux_rd_interval( sizeof(training_rd_interval)); if (training_rd_interval.bits.TRAINIG_AUX_RD_INTERVAL) - default_wait_in_micro_secs = training_rd_interval.bits.TRAINIG_AUX_RD_INTERVAL * 4000; + wait_in_micro_secs = training_rd_interval.bits.TRAINIG_AUX_RD_INTERVAL * 4000; } - return default_wait_in_micro_secs; + return wait_in_micro_secs; } static void wait_for_training_aux_rd_interval( @@ -101,7 +118,16 @@ static void dpcd_set_training_pattern( dpcd_pattern.v1_4.TRAINING_PATTERN_SET); } -static enum dc_dp_training_pattern get_supported_tp(struct dc_link *link) +static enum dc_dp_training_pattern decide_cr_training_pattern( + const struct dc_link_settings *link_settings) +{ + enum dc_dp_training_pattern pattern = DP_TRAINING_PATTERN_SEQUENCE_1; + + return pattern; +} + +static enum dc_dp_training_pattern decide_eq_training_pattern(struct dc_link *link, + const struct dc_link_settings *link_settings) { enum dc_dp_training_pattern highest_tp = DP_TRAINING_PATTERN_SEQUENCE_2; struct encoder_feature_support *features = &link->link_enc->features; @@ -132,7 +158,6 @@ static void dpcd_set_link_settings( union down_spread_ctrl downspread = { {0} }; union lane_count_set lane_count_set = { {0} }; - enum dc_dp_training_pattern dp_tr_pattern; downspread.raw = (uint8_t) (lt_settings->link_settings.link_spread); @@ -143,9 +168,8 @@ static void dpcd_set_link_settings( lane_count_set.bits.ENHANCED_FRAMING = lt_settings->enhanced_framing; lane_count_set.bits.POST_LT_ADJ_REQ_GRANTED = 0; - dp_tr_pattern = get_supported_tp(link); - if (dp_tr_pattern != DP_TRAINING_PATTERN_SEQUENCE_4) { + if (lt_settings->pattern_for_eq < DP_TRAINING_PATTERN_SEQUENCE_4) { lane_count_set.bits.POST_LT_ADJ_REQ_GRANTED = link->dpcd_caps.max_ln_count.bits.POST_LT_ADJ_REQ_SUPPORTED; } @@ -373,34 +397,30 @@ static void dpcd_set_lt_pattern_and_lane_settings( static bool is_cr_done(enum dc_lane_count ln_count, union lane_status *dpcd_lane_status) { - bool done = true; uint32_t lane; /*LANEx_CR_DONE bits All 1's?*/ for (lane = 0; lane < (uint32_t)(ln_count); lane++) { if (!dpcd_lane_status[lane].bits.CR_DONE_0) - done = false; + return false; } - return done; - + return true; } static bool is_ch_eq_done(enum dc_lane_count ln_count, union lane_status *dpcd_lane_status, union lane_align_status_updated *lane_status_updated) { - bool done = true; uint32_t lane; if (!lane_status_updated->bits.INTERLANE_ALIGN_DONE) - done = false; + return false; else { for (lane = 0; lane < (uint32_t)(ln_count); lane++) { if (!dpcd_lane_status[lane].bits.SYMBOL_LOCKED_0 || !dpcd_lane_status[lane].bits.CHANNEL_EQ_DONE_0) - done = false; + return false; } } - return done; - + return true; } static void update_drive_settings( @@ -979,7 +999,7 @@ static void start_clock_recovery_pattern_early(struct dc_link *link, { DC_LOG_HW_LINK_TRAINING("%s\n GPU sends TPS1. Wait 400us.\n", __func__); - dp_set_hw_training_pattern(link, DP_TRAINING_PATTERN_SEQUENCE_1, offset); + dp_set_hw_training_pattern(link, lt_settings->pattern_for_cr, offset); dp_set_hw_lane_settings(link, lt_settings, offset); udelay(400); } @@ -994,7 +1014,6 @@ static enum link_training_result perform_clock_recovery_sequence( uint32_t wait_time_microsec; struct link_training_settings req_settings; enum dc_lane_count lane_count = lt_settings->link_settings.lane_count; - enum dc_dp_training_pattern tr_pattern = DP_TRAINING_PATTERN_SEQUENCE_1; union lane_status dpcd_lane_status[LANE_COUNT_DP_MAX]; union lane_align_status_updated dpcd_lane_status_updated; @@ -1002,7 +1021,7 @@ static enum link_training_result perform_clock_recovery_sequence( retry_count = 0; if (!link->ctx->dc->work_arounds.lt_early_cr_pattern) - dp_set_hw_training_pattern(link, tr_pattern, offset); + dp_set_hw_training_pattern(link, lt_settings->pattern_for_cr, offset); /* najeeb - The synaptics MST hub can put the LT in * infinite loop by switching the VS @@ -1029,7 +1048,7 @@ static enum link_training_result perform_clock_recovery_sequence( dpcd_set_lt_pattern_and_lane_settings( link, lt_settings, - tr_pattern, + lt_settings->pattern_for_cr, offset); else dpcd_set_lane_settings( @@ -1113,7 +1132,7 @@ static inline enum link_training_result perform_link_training_int( * TPS4 must be used instead of POST_LT_ADJ_REQ. */ if (link->dpcd_caps.max_ln_count.bits.POST_LT_ADJ_REQ_SUPPORTED != 1 || - get_supported_tp(link) == DP_TRAINING_PATTERN_SEQUENCE_4) + lt_settings->pattern_for_eq == DP_TRAINING_PATTERN_SEQUENCE_4) return status; if (status == LINK_TRAINING_SUCCESS && @@ -1245,17 +1264,21 @@ static void initialize_training_settings( if (overrides->cr_pattern_time != NULL) lt_settings->cr_pattern_time = *overrides->cr_pattern_time; else - lt_settings->cr_pattern_time = get_training_aux_rd_interval(link, 100); + lt_settings->cr_pattern_time = get_cr_training_aux_rd_interval(link, link_setting); if (overrides->eq_pattern_time != NULL) lt_settings->eq_pattern_time = *overrides->eq_pattern_time; else - lt_settings->eq_pattern_time = get_training_aux_rd_interval(link, 400); + lt_settings->eq_pattern_time = get_eq_training_aux_rd_interval(link, link_setting); + if (overrides->pattern_for_cr != NULL) + lt_settings->pattern_for_cr = *overrides->pattern_for_cr; + else + lt_settings->pattern_for_cr = decide_cr_training_pattern(link_setting); if (overrides->pattern_for_eq != NULL) lt_settings->pattern_for_eq = *overrides->pattern_for_eq; else - lt_settings->pattern_for_eq = get_supported_tp(link); + lt_settings->pattern_for_eq = decide_eq_training_pattern(link, link_setting); if (overrides->enhanced_framing != NULL) lt_settings->enhanced_framing = *overrides->enhanced_framing; @@ -1457,7 +1480,6 @@ bool dc_link_dp_perform_link_training_skip_aux( const struct dc_link_settings *link_setting) { struct link_training_settings lt_settings; - enum dc_dp_training_pattern pattern_for_cr = DP_TRAINING_PATTERN_SEQUENCE_1; initialize_training_settings( link, @@ -1468,7 +1490,7 @@ bool dc_link_dp_perform_link_training_skip_aux( /* 1. Perform_clock_recovery_sequence. */ /* transmit training pattern for clock recovery */ - dp_set_hw_training_pattern(link, pattern_for_cr, DPRX); + dp_set_hw_training_pattern(link, lt_settings.pattern_for_cr, DPRX); /* call HWSS to set lane settings*/ dp_set_hw_lane_settings(link, <_settings, DPRX); @@ -1610,6 +1632,9 @@ bool perform_link_training_with_retries( for (j = 0; j < attempts; ++j) { + DC_LOG_HW_LINK_TRAINING("%s: Beginning link training attempt %u of %d\n", + __func__, (unsigned int)j + 1, attempts); + dp_enable_link_phy( link, signal, @@ -1638,6 +1663,9 @@ bool perform_link_training_with_retries( if (j == (attempts - 1)) break; + DC_LOG_WARNING("%s: Link training attempt %u of %d failed\n", + __func__, (unsigned int)j + 1, attempts); + dp_disable_link_phy(link, signal); msleep(delay_between_attempts); diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_hwss.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_hwss.c index dd88eb348dfa..11a619befb42 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_link_hwss.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_hwss.c @@ -104,6 +104,12 @@ void dp_enable_link_phy( struct clock_source *dp_cs = link->dc->res_pool->dp_clock_source; unsigned int i; + + if (link->connector_signal == SIGNAL_TYPE_EDP) { + link->dc->hwss.edp_power_control(link, true); + link->dc->hwss.edp_wait_for_hpd_ready(link, true); + } + /* If the current pixel clock source is not DTO(happens after * switching from HDMI passive dongle to DP on the same connector), * switch the pixel clock source to DTO. @@ -223,6 +229,8 @@ void dp_disable_link_phy(struct dc_link *link, enum signal_type signal) dp_receiver_power_ctrl(link, false); if (signal == SIGNAL_TYPE_EDP) { + if (link->dc->hwss.edp_backlight_control) + link->dc->hwss.edp_backlight_control(link, false); link->link_enc->funcs->disable_output(link->link_enc, signal); link->dc->hwss.edp_power_control(link, false); } else { @@ -485,13 +493,15 @@ void dp_set_dsc_on_stream(struct pipe_ctx *pipe_ctx, bool enable) OPTC_DSC_DISABLED, 0, 0); /* disable DSC in stream encoder */ - if (dc_is_dp_signal(stream->signal) && !IS_FPGA_MAXIMUS_DC(dc->ctx->dce_environment)) { - pipe_ctx->stream_res.stream_enc->funcs->dp_set_dsc_config( - pipe_ctx->stream_res.stream_enc, - OPTC_DSC_DISABLED, 0, 0); - - pipe_ctx->stream_res.stream_enc->funcs->dp_set_dsc_pps_info_packet( - pipe_ctx->stream_res.stream_enc, false, NULL); + if (dc_is_dp_signal(stream->signal)) { + + if (!IS_FPGA_MAXIMUS_DC(dc->ctx->dce_environment)) { + pipe_ctx->stream_res.stream_enc->funcs->dp_set_dsc_config( + pipe_ctx->stream_res.stream_enc, + OPTC_DSC_DISABLED, 0, 0); + pipe_ctx->stream_res.stream_enc->funcs->dp_set_dsc_pps_info_packet( + pipe_ctx->stream_res.stream_enc, false, NULL); + } } /* disable DSC block */ @@ -528,7 +538,6 @@ out: bool dp_set_dsc_pps_sdp(struct pipe_ctx *pipe_ctx, bool enable) { struct display_stream_compressor *dsc = pipe_ctx->stream_res.dsc; - struct dc *dc = pipe_ctx->stream->ctx->dc; struct dc_stream_state *stream = pipe_ctx->stream; if (!pipe_ctx->stream->timing.flags.DSC || !dsc) @@ -551,7 +560,7 @@ bool dp_set_dsc_pps_sdp(struct pipe_ctx *pipe_ctx, bool enable) DC_LOG_DSC(" "); dsc->funcs->dsc_get_packed_pps(dsc, &dsc_cfg, &dsc_packed_pps[0]); - if (dc_is_dp_signal(stream->signal) && !IS_FPGA_MAXIMUS_DC(dc->ctx->dce_environment)) { + if (dc_is_dp_signal(stream->signal)) { DC_LOG_DSC("Setting stream encoder DSC PPS SDP for engine %d\n", (int)pipe_ctx->stream_res.stream_enc->id); pipe_ctx->stream_res.stream_enc->funcs->dp_set_dsc_pps_info_packet( pipe_ctx->stream_res.stream_enc, @@ -560,7 +569,7 @@ bool dp_set_dsc_pps_sdp(struct pipe_ctx *pipe_ctx, bool enable) } } else { /* disable DSC PPS in stream encoder */ - if (dc_is_dp_signal(stream->signal) && !IS_FPGA_MAXIMUS_DC(dc->ctx->dce_environment)) { + if (dc_is_dp_signal(stream->signal)) { pipe_ctx->stream_res.stream_enc->funcs->dp_set_dsc_pps_info_packet( pipe_ctx->stream_res.stream_enc, false, NULL); } diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c index c6b737dd8425..e430148e47cf 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c @@ -782,11 +782,18 @@ static void calculate_recout(struct pipe_ctx *pipe_ctx) calculate_split_count_and_index(pipe_ctx, &split_count, &split_idx); - data->recout.x = stream->dst.x; - if (stream->src.x < surf_clip.x) - data->recout.x += (surf_clip.x - stream->src.x) * stream->dst.width + /* + * Only the leftmost ODM pipe should be offset by a nonzero distance + */ + if (!pipe_ctx->prev_odm_pipe) { + data->recout.x = stream->dst.x; + if (stream->src.x < surf_clip.x) + data->recout.x += (surf_clip.x - stream->src.x) * stream->dst.width / stream->src.width; + } else + data->recout.x = 0; + data->recout.width = surf_clip.width * stream->dst.width / stream->src.width; if (data->recout.width + data->recout.x > stream->dst.x + stream->dst.width) data->recout.width = stream->dst.x + stream->dst.width - data->recout.x; @@ -957,7 +964,7 @@ static void calculate_inits_and_adj_vp(struct pipe_ctx *pipe_ctx) { const struct dc_plane_state *plane_state = pipe_ctx->plane_state; const struct dc_stream_state *stream = pipe_ctx->stream; - struct pipe_ctx *odm_pipe = pipe_ctx->prev_odm_pipe; + struct pipe_ctx *odm_pipe = pipe_ctx; struct scaler_data *data = &pipe_ctx->plane_res.scl_data; struct rect src = pipe_ctx->plane_state->src_rect; int recout_skip_h, recout_skip_v, surf_size_h, surf_size_v; @@ -988,21 +995,24 @@ static void calculate_inits_and_adj_vp(struct pipe_ctx *pipe_ctx) swap(src.width, src.height); } + /*modified recout_skip_h calculation due to odm having no recout offset*/ + while (odm_pipe->prev_odm_pipe) { + odm_idx++; + odm_pipe = odm_pipe->prev_odm_pipe; + } + /*odm_pipe is the leftmost pipe in the ODM group*/ + recout_skip_h = odm_idx * data->recout.width; + /* Recout matching initial vp offset = recout_offset - (stream dst offset + * ((surf dst offset - stream src offset) * 1/ stream scaling ratio) * - (surf surf_src offset * 1/ full scl ratio)) */ - recout_skip_h = data->recout.x - (stream->dst.x + (plane_state->dst_rect.x - stream->src.x) + recout_skip_h += odm_pipe->plane_res.scl_data.recout.x + - (stream->dst.x + (plane_state->dst_rect.x - stream->src.x) * stream->dst.width / stream->src.width - src.x * plane_state->dst_rect.width / src.width * stream->dst.width / stream->src.width); - /*modified recout_skip_h calculation due to odm having no recout offset*/ - while (odm_pipe) { - odm_idx++; - odm_pipe = odm_pipe->prev_odm_pipe; - } - if (odm_idx) - recout_skip_h += odm_idx * data->recout.width; + recout_skip_v = data->recout.y - (stream->dst.y + (plane_state->dst_rect.y - stream->src.y) * stream->dst.height / stream->src.height - 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 f42a17d765e3..d48fd87d3b95 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_stream.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_stream.c @@ -123,7 +123,6 @@ static bool dc_stream_construct(struct dc_stream_state *stream, return false; } stream->out_transfer_func->type = TF_TYPE_BYPASS; - stream->out_transfer_func->ctx = stream->ctx; stream->stream_id = stream->ctx->dc_stream_id_count; stream->ctx->dc_stream_id_count++; @@ -298,7 +297,7 @@ bool dc_stream_set_cursor_attributes( #if defined(CONFIG_DRM_AMD_DC_DCN3_0) /* disable idle optimizations while updating cursor */ if (dc->idle_optimizations_allowed) { - dc->hwss.apply_idle_power_optimizations(dc, false); + dc_allow_idle_optimizations(dc, false); reset_idle_optimizations = true; } @@ -326,7 +325,7 @@ bool dc_stream_set_cursor_attributes( #if defined(CONFIG_DRM_AMD_DC_DCN3_0) /* re-enable idle optimizations if necessary */ if (reset_idle_optimizations) - dc->hwss.apply_idle_power_optimizations(dc, true); + dc_allow_idle_optimizations(dc, true); #endif return true; @@ -359,9 +358,8 @@ bool dc_stream_set_cursor_position( #if defined(CONFIG_DRM_AMD_DC_DCN3_0) /* disable idle optimizations if enabling cursor */ - if (dc->idle_optimizations_allowed && - !stream->cursor_position.enable && position->enable) { - dc->hwss.apply_idle_power_optimizations(dc, false); + if (dc->idle_optimizations_allowed && !stream->cursor_position.enable && position->enable) { + dc_allow_idle_optimizations(dc, false); reset_idle_optimizations = true; } @@ -392,7 +390,7 @@ bool dc_stream_set_cursor_position( #if defined(CONFIG_DRM_AMD_DC_DCN3_0) /* re-enable idle optimizations if necessary */ if (reset_idle_optimizations) - dc->hwss.apply_idle_power_optimizations(dc, true); + dc_allow_idle_optimizations(dc, true); #endif return true; diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_surface.c b/drivers/gpu/drm/amd/display/dc/core/dc_surface.c index ea1229a3e2b2..3d7d27435f15 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_surface.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_surface.c @@ -48,22 +48,17 @@ static void dc_plane_construct(struct dc_context *ctx, struct dc_plane_state *pl plane_state->in_transfer_func = dc_create_transfer_func(); if (plane_state->in_transfer_func != NULL) { plane_state->in_transfer_func->type = TF_TYPE_BYPASS; - plane_state->in_transfer_func->ctx = ctx; } plane_state->in_shaper_func = dc_create_transfer_func(); if (plane_state->in_shaper_func != NULL) { plane_state->in_shaper_func->type = TF_TYPE_BYPASS; - plane_state->in_shaper_func->ctx = ctx; } plane_state->lut3d_func = dc_create_3dlut_func(); - if (plane_state->lut3d_func != NULL) { - plane_state->lut3d_func->ctx = ctx; - } + plane_state->blend_tf = dc_create_transfer_func(); if (plane_state->blend_tf != NULL) { plane_state->blend_tf->type = TF_TYPE_BYPASS; - plane_state->blend_tf->ctx = ctx; } } diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h index 1d9c8e09c08b..82fe0ab56e3a 100644 --- a/drivers/gpu/drm/amd/display/dc/dc.h +++ b/drivers/gpu/drm/amd/display/dc/dc.h @@ -42,7 +42,7 @@ #include "inc/hw/dmcu.h" #include "dml/display_mode_lib.h" -#define DC_VER "3.2.99" +#define DC_VER "3.2.104" #define MAX_SURFACES 3 #define MAX_PLANES 6 @@ -476,7 +476,7 @@ struct dc_debug_options { unsigned int force_odm_combine_4to1; //bit vector based on otg inst #endif unsigned int force_fclk_khz; - bool disable_tri_buf; + bool enable_tri_buf; bool dmub_offload_enabled; bool dmcub_emulation; #if defined(CONFIG_DRM_AMD_DC_DCN3_0) @@ -503,6 +503,7 @@ struct dc_debug_options { bool usbc_combo_phy_reset_wa; bool disable_dsc; bool enable_dram_clock_change_one_display_vactive; + bool force_ignore_link_settings; }; struct dc_debug_data { @@ -660,6 +661,7 @@ struct dc_init_data { #if defined(CONFIG_DRM_AMD_DC_DCN3_0) bool force_smu_not_present; #endif + bool force_ignore_link_settings; }; struct dc_callback_init { @@ -745,7 +747,6 @@ struct dc_transfer_func { enum dc_transfer_func_predefined tf; /* FP16 1.0 reference level in nits, default is 80 nits, only for PQ*/ uint32_t sdr_ref_white_level; - struct dc_context *ctx; union { struct pwl_params pwl; struct dc_transfer_func_distributed_points tf_pts; @@ -772,7 +773,6 @@ struct dc_3dlut { struct tetrahedral_params lut_3d; struct fixed31_32 hdr_multiplier; union dc_3dlut_state state; - struct dc_context *ctx; }; /* * This structure is filled in by dc_surface_get_status and contains @@ -1250,6 +1250,9 @@ enum dc_status dc_set_clock(struct dc *dc, enum dc_clock_type clock_type, uint32 void dc_get_clock(struct dc *dc, enum dc_clock_type clock_type, struct dc_clock_config *clock_cfg); #if defined(CONFIG_DRM_AMD_DC_DCN3_0) +bool dc_is_plane_eligible_for_idle_optimizations(struct dc *dc, + struct dc_plane_state *plane); + void dc_allow_idle_optimizations(struct dc *dc, bool allow); /* diff --git a/drivers/gpu/drm/amd/display/dc/dc_bios_types.h b/drivers/gpu/drm/amd/display/dc/dc_bios_types.h index 0811f941f430..e146e3cba8eb 100644 --- a/drivers/gpu/drm/amd/display/dc/dc_bios_types.h +++ b/drivers/gpu/drm/amd/display/dc/dc_bios_types.h @@ -140,6 +140,10 @@ struct dc_vbios_funcs { enum bp_result (*enable_lvtma_control)( struct dc_bios *bios, uint8_t uc_pwr_on); + + enum bp_result (*get_soc_bb_info)( + struct dc_bios *dcb, + struct bp_soc_bb_info *soc_bb_info); }; struct bios_registers { 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 eea2429ac67d..b98754811977 100644 --- a/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.c +++ b/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.c @@ -132,3 +132,19 @@ void dc_dmub_srv_wait_phy_init(struct dc_dmub_srv *dc_dmub_srv) /* Continue spinning so we don't hang the ASIC. */ } } + +bool dc_dmub_srv_notify_stream_mask(struct dc_dmub_srv *dc_dmub_srv, + unsigned int stream_mask) +{ + struct dmub_srv *dmub; + const uint32_t timeout = 30; + + if (!dc_dmub_srv || !dc_dmub_srv->dmub) + return false; + + dmub = dc_dmub_srv->dmub; + + return dmub_srv_send_gpint_command( + dmub, DMUB_GPINT__IDLE_OPT_NOTIFY_STREAM_MASK, + stream_mask, timeout) == DMUB_STATUS_OK; +} diff --git a/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.h b/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.h index a3a09ccb6d26..bb4ab61887e4 100644 --- a/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.h +++ b/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.h @@ -56,4 +56,6 @@ void dc_dmub_srv_wait_idle(struct dc_dmub_srv *dc_dmub_srv); void dc_dmub_srv_wait_phy_init(struct dc_dmub_srv *dc_dmub_srv); +bool dc_dmub_srv_notify_stream_mask(struct dc_dmub_srv *dc_dmub_srv, + unsigned int stream_mask); #endif /* _DMUB_DC_SRV_H_ */ diff --git a/drivers/gpu/drm/amd/display/dc/dc_dp_types.h b/drivers/gpu/drm/amd/display/dc/dc_dp_types.h index a8a3b0643505..80a2191a3115 100644 --- a/drivers/gpu/drm/amd/display/dc/dc_dp_types.h +++ b/drivers/gpu/drm/amd/display/dc/dc_dp_types.h @@ -123,6 +123,7 @@ struct dc_link_training_overrides { uint16_t *cr_pattern_time; uint16_t *eq_pattern_time; + enum dc_dp_training_pattern *pattern_for_cr; enum dc_dp_training_pattern *pattern_for_eq; enum dc_link_spread *downspread; diff --git a/drivers/gpu/drm/amd/display/dc/dc_link.h b/drivers/gpu/drm/amd/display/dc/dc_link.h index e002ef706e1d..266b93a705d5 100644 --- a/drivers/gpu/drm/amd/display/dc/dc_link.h +++ b/drivers/gpu/drm/amd/display/dc/dc_link.h @@ -237,6 +237,8 @@ enum dc_detect_reason { DETECT_REASON_BOOT, DETECT_REASON_HPD, DETECT_REASON_HPDRX, + DETECT_REASON_FALLBACK, + DETECT_REASON_RETRAIN }; bool dc_link_detect(struct dc_link *dc_link, enum dc_detect_reason reason); diff --git a/drivers/gpu/drm/amd/display/dc/dc_types.h b/drivers/gpu/drm/amd/display/dc/dc_types.h index aa8e0955db48..c47a19719de2 100644 --- a/drivers/gpu/drm/amd/display/dc/dc_types.h +++ b/drivers/gpu/drm/amd/display/dc/dc_types.h @@ -122,7 +122,7 @@ struct dc_context { }; -#define DC_MAX_EDID_BUFFER_SIZE 1024 +#define DC_MAX_EDID_BUFFER_SIZE 1280 #define DC_EDID_BLOCK_SIZE 128 #define MAX_SURFACE_NUM 4 #define NUM_PIXEL_FORMATS 10 diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_clock_source.c b/drivers/gpu/drm/amd/display/dc/dce/dce_clock_source.c index 9cc65dc1970f..49ae5ff12da6 100644 --- a/drivers/gpu/drm/amd/display/dc/dce/dce_clock_source.c +++ b/drivers/gpu/drm/amd/display/dc/dce/dce_clock_source.c @@ -1149,7 +1149,8 @@ static uint32_t dcn3_get_pix_clk_dividers( static const struct clock_source_funcs dcn3_clk_src_funcs = { .cs_power_down = dce110_clock_source_power_down, .program_pix_clk = dcn3_program_pix_clk, - .get_pix_clk_dividers = dcn3_get_pix_clk_dividers + .get_pix_clk_dividers = dcn3_get_pix_clk_dividers, + .get_pixel_clk_frequency_100hz = get_pixel_clk_frequency_100hz }; #endif /*****************************************/ diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_panel_cntl.c b/drivers/gpu/drm/amd/display/dc/dce/dce_panel_cntl.c index df7f826eebd8..74f7619d4154 100644 --- a/drivers/gpu/drm/amd/display/dc/dce/dce_panel_cntl.c +++ b/drivers/gpu/drm/amd/display/dc/dce/dce_panel_cntl.c @@ -159,11 +159,15 @@ static uint32_t dce_panel_cntl_hw_init(struct panel_cntl *panel_cntl) static bool dce_is_panel_backlight_on(struct panel_cntl *panel_cntl) { struct dce_panel_cntl *dce_panel_cntl = TO_DCE_PANEL_CNTL(panel_cntl); - uint32_t value; + uint32_t blon, blon_ovrd, pwrseq_target_state; - REG_GET(PWRSEQ_CNTL, LVTMA_BLON, &value); + REG_GET_2(PWRSEQ_CNTL, LVTMA_BLON, &blon, LVTMA_BLON_OVRD, &blon_ovrd); + REG_GET(PWRSEQ_CNTL, LVTMA_PWRSEQ_TARGET_STATE, &pwrseq_target_state); - return value; + if (blon_ovrd) + return blon; + else + return pwrseq_target_state; } static bool dce_is_panel_powered_on(struct panel_cntl *panel_cntl) diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_panel_cntl.h b/drivers/gpu/drm/amd/display/dc/dce/dce_panel_cntl.h index 99c68ca9c7e0..6bd1196083a3 100644 --- a/drivers/gpu/drm/amd/display/dc/dce/dce_panel_cntl.h +++ b/drivers/gpu/drm/amd/display/dc/dce/dce_panel_cntl.h @@ -54,15 +54,17 @@ SR(BL_PWM_CNTL2), \ SR(BL_PWM_PERIOD_CNTL), \ SR(BL_PWM_GRP1_REG_LOCK), \ - SR(BIOS_SCRATCH_2) + NBIO_SR(BIOS_SCRATCH_2) #define DCE_PANEL_CNTL_SF(reg_name, field_name, post_fix)\ .field_name = reg_name ## __ ## field_name ## post_fix #define DCE_PANEL_CNTL_MASK_SH_LIST(mask_sh) \ DCE_PANEL_CNTL_SF(LVTMA_PWRSEQ_CNTL, LVTMA_BLON, mask_sh),\ + DCE_PANEL_CNTL_SF(LVTMA_PWRSEQ_CNTL, LVTMA_BLON_OVRD, mask_sh),\ DCE_PANEL_CNTL_SF(LVTMA_PWRSEQ_CNTL, LVTMA_DIGON, mask_sh),\ DCE_PANEL_CNTL_SF(LVTMA_PWRSEQ_CNTL, LVTMA_DIGON_OVRD, mask_sh),\ + DCE_PANEL_CNTL_SF(LVTMA_PWRSEQ_CNTL, LVTMA_PWRSEQ_TARGET_STATE, mask_sh), \ DCE_PANEL_CNTL_SF(LVTMA_PWRSEQ_STATE, LVTMA_PWRSEQ_TARGET_STATE_R, mask_sh), \ DCE_PANEL_CNTL_SF(LVTMA_PWRSEQ_REF_DIV, BL_PWM_REF_DIV, mask_sh), \ DCE_PANEL_CNTL_SF(BL_PWM_PERIOD_CNTL, BL_PWM_PERIOD, mask_sh), \ @@ -76,8 +78,10 @@ #define DCE_PANEL_CNTL_REG_FIELD_LIST(type) \ type LVTMA_BLON;\ + type LVTMA_BLON_OVRD;\ type LVTMA_DIGON;\ type LVTMA_DIGON_OVRD;\ + type LVTMA_PWRSEQ_TARGET_STATE; \ type LVTMA_PWRSEQ_TARGET_STATE_R; \ type BL_PWM_REF_DIV; \ type BL_PWM_EN; \ diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_stream_encoder.c b/drivers/gpu/drm/amd/display/dc/dce/dce_stream_encoder.c index 4cdaaf4d881c..5054bb567b74 100644 --- a/drivers/gpu/drm/amd/display/dc/dce/dce_stream_encoder.c +++ b/drivers/gpu/drm/amd/display/dc/dce/dce_stream_encoder.c @@ -710,7 +710,7 @@ static void dce110_stream_encoder_lvds_set_stream_attribute( ASSERT(crtc_timing->pixel_encoding == PIXEL_ENCODING_RGB); } -static void dce110_stream_encoder_set_mst_bandwidth( +static void dce110_stream_encoder_set_throttled_vcp_size( struct stream_encoder *enc, struct fixed31_32 avg_time_slots_per_mtp) { @@ -1621,8 +1621,8 @@ static const struct stream_encoder_funcs dce110_str_enc_funcs = { dce110_stream_encoder_dvi_set_stream_attribute, .lvds_set_stream_attribute = dce110_stream_encoder_lvds_set_stream_attribute, - .set_mst_bandwidth = - dce110_stream_encoder_set_mst_bandwidth, + .set_throttled_vcp_size = + dce110_stream_encoder_set_throttled_vcp_size, .update_hdmi_info_packets = dce110_stream_encoder_update_hdmi_info_packets, .stop_hdmi_info_packets = diff --git a/drivers/gpu/drm/amd/display/dc/dce/dmub_psr.c b/drivers/gpu/drm/amd/display/dc/dce/dmub_psr.c index 5167d6b8a48d..67af67ef2865 100644 --- a/drivers/gpu/drm/amd/display/dc/dce/dmub_psr.c +++ b/drivers/gpu/drm/amd/display/dc/dce/dmub_psr.c @@ -119,10 +119,11 @@ static bool dmub_psr_set_version(struct dmub_psr *dmub, struct dc_stream_state * /** * Enable/Disable PSR. */ -static void dmub_psr_enable(struct dmub_psr *dmub, bool enable) +static void dmub_psr_enable(struct dmub_psr *dmub, bool enable, bool wait) { union dmub_rb_cmd cmd; struct dc_context *dc = dmub->ctx; + uint32_t retry_count, psr_state = 0; cmd.psr_enable.header.type = DMUB_CMD__PSR; @@ -136,6 +137,30 @@ static void dmub_psr_enable(struct dmub_psr *dmub, bool enable) dc_dmub_srv_cmd_queue(dc->dmub_srv, &cmd); dc_dmub_srv_cmd_execute(dc->dmub_srv); dc_dmub_srv_wait_idle(dc->dmub_srv); + + /* Below loops 1000 x 500us = 500 ms. + * Exit PSR may need to wait 1-2 frames to power up. Timeout after at + * least a few frames. Should never hit the max retry assert below. + */ + if (wait) { + for (retry_count = 0; retry_count <= 1000; retry_count++) { + dmub_psr_get_state(dmub, &psr_state); + + if (enable) { + if (psr_state != 0) + break; + } else { + if (psr_state == 0) + break; + } + + udelay(500); + } + + /* assert if max retry hit */ + if (retry_count >= 1000) + ASSERT(0); + } } /** @@ -231,10 +256,11 @@ static bool dmub_psr_copy_settings(struct dmub_psr *dmub, copy_settings_data->smu_optimizations_en = psr_context->allow_smu_optimizations; copy_settings_data->frame_delay = psr_context->frame_delay; copy_settings_data->frame_cap_ind = psr_context->psrFrameCaptureIndicationReq; + copy_settings_data->init_sdp_deadline = psr_context->sdpTransmitLineNumDeadline; + copy_settings_data->debug.u32All = 0; copy_settings_data->debug.bitfields.visual_confirm = dc->dc->debug.visual_confirm == VISUAL_CONFIRM_PSR ? true : false; - copy_settings_data->debug.bitfields.use_hw_lock_mgr = 1; - copy_settings_data->init_sdp_deadline = psr_context->sdpTransmitLineNumDeadline; + copy_settings_data->debug.bitfields.use_hw_lock_mgr = 1; dc_dmub_srv_cmd_queue(dc->dmub_srv, &cmd); dc_dmub_srv_cmd_execute(dc->dmub_srv); diff --git a/drivers/gpu/drm/amd/display/dc/dce/dmub_psr.h b/drivers/gpu/drm/amd/display/dc/dce/dmub_psr.h index f404fecd6410..dc121ed92d2e 100644 --- a/drivers/gpu/drm/amd/display/dc/dce/dmub_psr.h +++ b/drivers/gpu/drm/amd/display/dc/dce/dmub_psr.h @@ -36,7 +36,7 @@ struct dmub_psr { struct dmub_psr_funcs { bool (*psr_copy_settings)(struct dmub_psr *dmub, struct dc_link *link, struct psr_context *psr_context); - void (*psr_enable)(struct dmub_psr *dmub, bool enable); + void (*psr_enable)(struct dmub_psr *dmub, bool enable, bool wait); void (*psr_get_state)(struct dmub_psr *dmub, uint32_t *psr_state); void (*psr_set_level)(struct dmub_psr *dmub, uint16_t psr_level); }; diff --git a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c index 0603ddca7bd0..3ac6c7b65a45 100644 --- a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c +++ b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c @@ -810,37 +810,66 @@ void dce110_edp_power_control( if (power_up != link->panel_cntl->funcs->is_panel_powered_on(link->panel_cntl)) { + + unsigned long long current_ts = dm_get_timestamp(ctx); + unsigned long long time_since_edp_poweroff_ms = + div64_u64(dm_get_elapse_time_in_ns( + ctx, + current_ts, + link->link_trace.time_stamp.edp_poweroff), 1000000); + unsigned long long time_since_edp_poweron_ms = + div64_u64(dm_get_elapse_time_in_ns( + ctx, + current_ts, + link->link_trace.time_stamp.edp_poweron), 1000000); + DC_LOG_HW_RESUME_S3( + "%s: transition: power_up=%d current_ts=%llu edp_poweroff=%llu edp_poweron=%llu time_since_edp_poweroff_ms=%llu time_since_edp_poweron_ms=%llu", + __func__, + power_up, + current_ts, + link->link_trace.time_stamp.edp_poweroff, + link->link_trace.time_stamp.edp_poweron, + time_since_edp_poweroff_ms, + time_since_edp_poweron_ms); + /* Send VBIOS command to prompt eDP panel power */ if (power_up) { - unsigned long long current_ts = dm_get_timestamp(ctx); - unsigned long long duration_in_ms = - div64_u64(dm_get_elapse_time_in_ns( - ctx, - current_ts, - link->link_trace.time_stamp.edp_poweroff), 1000000); - unsigned long long wait_time_ms = 0; - - /* max 500ms from LCDVDD off to on */ - unsigned long long edp_poweroff_time_ms = 500; + /* edp requires a min of 500ms from LCDVDD off to on */ + unsigned long long remaining_min_edp_poweroff_time_ms = 500; + /* add time defined by a patch, if any (usually patch extra_t12_ms is 0) */ if (link->local_sink != NULL) - edp_poweroff_time_ms = - 500 + link->local_sink->edid_caps.panel_patch.extra_t12_ms; - if (link->link_trace.time_stamp.edp_poweroff == 0) - wait_time_ms = edp_poweroff_time_ms; - else if (duration_in_ms < edp_poweroff_time_ms) - wait_time_ms = edp_poweroff_time_ms - duration_in_ms; - - if (wait_time_ms) { - msleep(wait_time_ms); - dm_output_to_console("%s: wait %lld ms to power on eDP.\n", - __func__, wait_time_ms); + remaining_min_edp_poweroff_time_ms += + link->local_sink->edid_caps.panel_patch.extra_t12_ms; + + /* Adjust remaining_min_edp_poweroff_time_ms if this is not the first time. */ + if (link->link_trace.time_stamp.edp_poweroff != 0) { + if (time_since_edp_poweroff_ms < remaining_min_edp_poweroff_time_ms) + remaining_min_edp_poweroff_time_ms = + remaining_min_edp_poweroff_time_ms - time_since_edp_poweroff_ms; + else + remaining_min_edp_poweroff_time_ms = 0; } + if (remaining_min_edp_poweroff_time_ms) { + DC_LOG_HW_RESUME_S3( + "%s: remaining_min_edp_poweroff_time_ms=%llu: begin wait.\n", + __func__, remaining_min_edp_poweroff_time_ms); + msleep(remaining_min_edp_poweroff_time_ms); + DC_LOG_HW_RESUME_S3( + "%s: remaining_min_edp_poweroff_time_ms=%llu: end wait.\n", + __func__, remaining_min_edp_poweroff_time_ms); + dm_output_to_console("%s: wait %lld ms to power on eDP.\n", + __func__, remaining_min_edp_poweroff_time_ms); + } else { + DC_LOG_HW_RESUME_S3( + "%s: remaining_min_edp_poweroff_time_ms=%llu: no wait required.\n", + __func__, remaining_min_edp_poweroff_time_ms); + } } DC_LOG_HW_RESUME_S3( - "%s: Panel Power action: %s\n", + "%s: BEGIN: Panel Power action: %s\n", __func__, (power_up ? "On":"Off")); cntl.action = power_up ? @@ -864,12 +893,23 @@ void dce110_edp_power_control( bp_result = link_transmitter_control(ctx->dc_bios, &cntl); + DC_LOG_HW_RESUME_S3( + "%s: END: Panel Power action: %s bp_result=%u\n", + __func__, (power_up ? "On":"Off"), + bp_result); + if (!power_up) /*save driver power off time stamp*/ link->link_trace.time_stamp.edp_poweroff = dm_get_timestamp(ctx); else link->link_trace.time_stamp.edp_poweron = dm_get_timestamp(ctx); + DC_LOG_HW_RESUME_S3( + "%s: updated values: edp_poweroff=%llu edp_poweron=%llu\n", + __func__, + link->link_trace.time_stamp.edp_poweroff, + link->link_trace.time_stamp.edp_poweron); + if (bp_result != BP_RESULT_OK) DC_LOG_ERROR( "%s: Panel Power bp_result: %d\n", @@ -1614,7 +1654,7 @@ void dce110_enable_accelerated_mode(struct dc *dc, struct dc_state *context) // enable fastboot if backend is enabled on eDP if (edp_link->link_enc->funcs->is_dig_enabled(edp_link->link_enc)) { /* Set optimization flag on eDP stream*/ - if (edp_stream) { + if (edp_stream && edp_link->link_status.link_active) { edp_stream->apply_edp_fast_boot_optimization = true; can_apply_edp_fast_boot = true; } @@ -2697,7 +2737,7 @@ static void program_output_csc(struct dc *dc, } } -void dce110_set_cursor_position(struct pipe_ctx *pipe_ctx) +static void dce110_set_cursor_position(struct pipe_ctx *pipe_ctx) { struct dc_cursor_position pos_cpy = pipe_ctx->stream->cursor_position; struct input_pixel_processor *ipp = pipe_ctx->plane_res.ipp; @@ -2742,7 +2782,7 @@ void dce110_set_cursor_position(struct pipe_ctx *pipe_ctx) mi->funcs->set_cursor_position(mi, &pos_cpy, ¶m); } -void dce110_set_cursor_attribute(struct pipe_ctx *pipe_ctx) +static void dce110_set_cursor_attribute(struct pipe_ctx *pipe_ctx) { struct dc_cursor_attributes *attributes = &pipe_ctx->stream->cursor_attributes; @@ -2850,6 +2890,7 @@ static const struct hw_sequencer_funcs dce110_funcs = { .setup_stereo = NULL, .set_avmute = dce110_set_avmute, .wait_for_mpcc_disconnect = dce110_wait_for_mpcc_disconnect, + .edp_backlight_control = dce110_edp_backlight_control, .edp_power_control = dce110_edp_power_control, .edp_wait_for_hpd_ready = dce110_edp_wait_for_hpd_ready, .set_cursor_position = dce110_set_cursor_position, diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_cm_common.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_cm_common.c index 47a39eb9400b..7a00fe525dfb 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_cm_common.c +++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_cm_common.c @@ -325,8 +325,6 @@ bool cm_helper_translate_curve_to_hw_format( if (output_tf == NULL || lut_params == NULL || output_tf->type == TF_TYPE_BYPASS) return false; - PERF_TRACE_CTX(output_tf->ctx); - corner_points = lut_params->corner_points; rgb_resulted = lut_params->rgb_resulted; hw_points = 0; @@ -524,8 +522,6 @@ bool cm_helper_translate_curve_to_degamma_hw_format( if (output_tf == NULL || lut_params == NULL || output_tf->type == TF_TYPE_BYPASS) return false; - PERF_TRACE_CTX(output_tf->ctx); - corner_points = lut_params->corner_points; rgb_resulted = lut_params->rgb_resulted; hw_points = 0; diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.c index cedf359a00f5..db5615a51fea 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.c +++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.c @@ -734,6 +734,9 @@ bool hubp1_is_flip_pending(struct hubp *hubp) struct dcn10_hubp *hubp1 = TO_DCN10_HUBP(hubp); struct dc_plane_address earliest_inuse_address; + if (hubp && hubp->power_gated) + return false; + REG_GET(DCSURF_FLIP_CONTROL, SURFACE_FLIP_PENDING, &flip_pending); diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c index 8ca94f506195..d0f3bf953d02 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c +++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c @@ -2765,7 +2765,7 @@ bool dcn10_disconnect_pipes( struct dc *dc, struct dc_state *context) { - bool found_stream = false; + bool found_pipe = false; int i, j; struct dce_hwseq *hws = dc->hwseq; struct dc_state *old_ctx = dc->current_state; @@ -2805,26 +2805,28 @@ bool dcn10_disconnect_pipes( old_ctx->res_ctx.pipe_ctx[i].top_pipe) { /* Find the top pipe in the new ctx for the bottom pipe that we - * want to remove by comparing the streams. If both pipes are being - * disabled then do it in the regular pipe programming sequence + * want to remove by comparing the streams and planes. If both + * pipes are being disabled then do it in the regular pipe + * programming sequence */ for (j = 0; j < dc->res_pool->pipe_count; j++) { if (old_ctx->res_ctx.pipe_ctx[i].top_pipe->stream == context->res_ctx.pipe_ctx[j].stream && + old_ctx->res_ctx.pipe_ctx[i].top_pipe->plane_state == context->res_ctx.pipe_ctx[j].plane_state && !context->res_ctx.pipe_ctx[j].top_pipe && !context->res_ctx.pipe_ctx[j].update_flags.bits.disable) { - found_stream = true; + found_pipe = true; break; } } // Disconnect if the top pipe lost it's pipe split - if (found_stream && !context->res_ctx.pipe_ctx[j].bottom_pipe) { + if (found_pipe && !context->res_ctx.pipe_ctx[j].bottom_pipe) { hws->funcs.plane_atomic_disconnect(dc, &dc->current_state->res_ctx.pipe_ctx[i]); DC_LOG_DC("Reset mpcc for pipe %d\n", dc->current_state->res_ctx.pipe_ctx[i].pipe_idx); mpcc_disconnected = true; } } - found_stream = false; + found_pipe = false; } } diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_init.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_init.c index a1d1559bb5d7..b24c8ae8b1ec 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_init.c +++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_init.c @@ -66,6 +66,7 @@ static const struct hw_sequencer_funcs dcn10_funcs = { .get_hw_state = dcn10_get_hw_state, .clear_status_bits = dcn10_clear_status_bits, .wait_for_mpcc_disconnect = dcn10_wait_for_mpcc_disconnect, + .edp_backlight_control = dce110_edp_backlight_control, .edp_power_control = dce110_edp_power_control, .edp_wait_for_hpd_ready = dce110_edp_wait_for_hpd_ready, .set_cursor_position = dcn10_set_cursor_position, diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.c index 2972392f9788..800be2693fac 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.c +++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.c @@ -288,6 +288,17 @@ void optc1_program_timing( if (optc1_is_two_pixels_per_containter(&patched_crtc_timing) || optc1->opp_count == 2) h_div = H_TIMING_DIV_BY2; + if (REG(OPTC_DATA_FORMAT_CONTROL)) { + uint32_t data_fmt = 0; + + if (patched_crtc_timing.pixel_encoding == PIXEL_ENCODING_YCBCR422) + data_fmt = 1; + else if (patched_crtc_timing.pixel_encoding == PIXEL_ENCODING_YCBCR420) + data_fmt = 2; + + REG_UPDATE(OPTC_DATA_FORMAT_CONTROL, OPTC_DATA_FORMAT, data_fmt); + } + #if defined(CONFIG_DRM_AMD_DC_DCN3_0) if (optc1->tg_mask->OTG_H_TIMING_DIV_MODE != 0) { if (optc1->opp_count == 4) diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c index 1abd81e17f09..a78712caf124 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c @@ -798,7 +798,7 @@ static const struct encoder_feature_support link_enc_feature = { .max_hdmi_deep_color = COLOR_DEPTH_121212, .max_hdmi_pixel_clock = 600000, .hdmi_ycbcr420_supported = true, - .dp_ycbcr420_supported = false, + .dp_ycbcr420_supported = true, .flags.bits.IS_HBR2_CAPABLE = true, .flags.bits.IS_HBR3_CAPABLE = true, .flags.bits.IS_TPS3_CAPABLE = true, diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_stream_encoder.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_stream_encoder.c index 842abb4c475b..f70fcadf1ee5 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_stream_encoder.c +++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_stream_encoder.c @@ -619,7 +619,7 @@ void enc1_stream_encoder_dvi_set_stream_attribute( enc1_stream_encoder_set_stream_attribute_helper(enc1, crtc_timing); } -void enc1_stream_encoder_set_mst_bandwidth( +void enc1_stream_encoder_set_throttled_vcp_size( struct stream_encoder *enc, struct fixed31_32 avg_time_slots_per_mtp) { @@ -896,10 +896,10 @@ void enc1_stream_encoder_dp_blank( */ REG_UPDATE(DP_VID_STREAM_CNTL, DP_VID_STREAM_DIS_DEFER, 2); /* Larger delay to wait until VBLANK - use max retry of - * 10us*5000=50ms. This covers 41.7ms of minimum 24 Hz mode + + * 10us*10200=102ms. This covers 100.0ms of minimum 10 Hz mode + * a little more because we may not trust delay accuracy. */ - max_retries = DP_BLANK_MAX_RETRY * 250; + max_retries = DP_BLANK_MAX_RETRY * 501; /* disable DP stream */ REG_UPDATE(DP_VID_STREAM_CNTL, DP_VID_STREAM_ENABLE, 0); @@ -1616,8 +1616,8 @@ static const struct stream_encoder_funcs dcn10_str_enc_funcs = { enc1_stream_encoder_hdmi_set_stream_attribute, .dvi_set_stream_attribute = enc1_stream_encoder_dvi_set_stream_attribute, - .set_mst_bandwidth = - enc1_stream_encoder_set_mst_bandwidth, + .set_throttled_vcp_size = + enc1_stream_encoder_set_throttled_vcp_size, .update_hdmi_info_packets = enc1_stream_encoder_update_hdmi_info_packets, .stop_hdmi_info_packets = diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_stream_encoder.h b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_stream_encoder.h index 30eae7459d50..b99d2527cf03 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_stream_encoder.h +++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_stream_encoder.h @@ -588,7 +588,7 @@ void enc1_stream_encoder_dvi_set_stream_attribute( struct dc_crtc_timing *crtc_timing, bool is_dual_link); -void enc1_stream_encoder_set_mst_bandwidth( +void enc1_stream_encoder_set_throttled_vcp_size( struct stream_encoder *enc, struct fixed31_32 avg_time_slots_per_mtp); diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubp.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubp.c index bb920d0e0b89..368818d2dfc6 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubp.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubp.c @@ -908,6 +908,9 @@ bool hubp2_is_flip_pending(struct hubp *hubp) struct dcn20_hubp *hubp2 = TO_DCN20_HUBP(hubp); struct dc_plane_address earliest_inuse_address; + if (hubp && hubp->power_gated) + return false; + REG_GET(DCSURF_FLIP_CONTROL, SURFACE_FLIP_PENDING, &flip_pending); diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c index c8cfd3ba1c15..01530e686f43 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c @@ -1251,6 +1251,11 @@ static void dcn20_detect_pipe_changes(struct pipe_ctx *old_pipe, struct pipe_ctx return; } + /* Detect plane change */ + if (old_pipe->plane_state != new_pipe->plane_state) { + new_pipe->update_flags.bits.plane_changed = true; + } + /* Detect top pipe only changes */ if (!new_pipe->top_pipe && !new_pipe->prev_odm_pipe) { /* Detect odm changes */ @@ -1392,6 +1397,7 @@ static void dcn20_update_dchubp_dpp( &pipe_ctx->ttu_regs); if (pipe_ctx->update_flags.bits.enable || + pipe_ctx->update_flags.bits.plane_changed || plane_state->update_flags.bits.bpp_change || plane_state->update_flags.bits.input_csc_change || plane_state->update_flags.bits.color_space_change || @@ -1414,6 +1420,7 @@ static void dcn20_update_dchubp_dpp( } if (pipe_ctx->update_flags.bits.mpcc + || pipe_ctx->update_flags.bits.plane_changed || plane_state->update_flags.bits.global_alpha_change || plane_state->update_flags.bits.per_pixel_alpha_change) { // MPCC inst is equal to pipe index in practice @@ -1515,6 +1522,7 @@ static void dcn20_update_dchubp_dpp( } if (pipe_ctx->update_flags.bits.enable || + pipe_ctx->update_flags.bits.plane_changed || pipe_ctx->update_flags.bits.opp_changed || plane_state->update_flags.bits.pixel_format_change || plane_state->update_flags.bits.horizontal_mirror_change || @@ -1539,7 +1547,9 @@ static void dcn20_update_dchubp_dpp( hubp->power_gated = false; } - if (pipe_ctx->update_flags.bits.enable || plane_state->update_flags.bits.addr_update) + if (pipe_ctx->update_flags.bits.enable || + pipe_ctx->update_flags.bits.plane_changed || + plane_state->update_flags.bits.addr_update) hws->funcs.update_plane_addr(dc, pipe_ctx); @@ -1632,16 +1642,26 @@ void dcn20_program_front_end_for_ctx( struct dce_hwseq *hws = dc->hwseq; DC_LOGGER_INIT(dc->ctx->logger); - for (i = 0; i < dc->res_pool->pipe_count; i++) { - struct pipe_ctx *pipe_ctx = &context->res_ctx.pipe_ctx[i]; + /* Carry over GSL groups in case the context is changing. */ + for (i = 0; i < dc->res_pool->pipe_count; i++) { + struct pipe_ctx *pipe_ctx = &context->res_ctx.pipe_ctx[i]; + struct pipe_ctx *old_pipe_ctx = + &dc->current_state->res_ctx.pipe_ctx[i]; + + if (pipe_ctx->stream == old_pipe_ctx->stream) + pipe_ctx->stream_res.gsl_group = + old_pipe_ctx->stream_res.gsl_group; + } + + if (dc->hwss.program_triplebuffer != NULL && dc->debug.enable_tri_buf) { + for (i = 0; i < dc->res_pool->pipe_count; i++) { + struct pipe_ctx *pipe_ctx = &context->res_ctx.pipe_ctx[i]; - if (!pipe_ctx->top_pipe && !pipe_ctx->prev_odm_pipe && pipe_ctx->plane_state) { - ASSERT(!pipe_ctx->plane_state->triplebuffer_flips); - if (dc->hwss.program_triplebuffer != NULL && - !dc->debug.disable_tri_buf) { + if (!pipe_ctx->top_pipe && !pipe_ctx->prev_odm_pipe && pipe_ctx->plane_state) { + ASSERT(!pipe_ctx->plane_state->triplebuffer_flips); /*turn off triple buffer for full update*/ dc->hwss.program_triplebuffer( - dc, pipe_ctx, pipe_ctx->plane_state->triplebuffer_flips); + dc, pipe_ctx, pipe_ctx->plane_state->triplebuffer_flips); } } } @@ -1909,9 +1929,9 @@ void dcn20_disable_stream_gating(struct dc *dc, struct pipe_ctx *pipe_ctx) if (pipe_ctx->stream_res.dsc) { struct pipe_ctx *odm_pipe = pipe_ctx->next_odm_pipe; - dcn20_dsc_pg_control(hws, pipe_ctx->stream_res.dsc->inst, true); + hws->funcs.dsc_pg_control(hws, pipe_ctx->stream_res.dsc->inst, true); while (odm_pipe) { - dcn20_dsc_pg_control(hws, odm_pipe->stream_res.dsc->inst, true); + hws->funcs.dsc_pg_control(hws, odm_pipe->stream_res.dsc->inst, true); odm_pipe = odm_pipe->next_odm_pipe; } } @@ -1924,9 +1944,9 @@ void dcn20_enable_stream_gating(struct dc *dc, struct pipe_ctx *pipe_ctx) if (pipe_ctx->stream_res.dsc) { struct pipe_ctx *odm_pipe = pipe_ctx->next_odm_pipe; - dcn20_dsc_pg_control(hws, pipe_ctx->stream_res.dsc->inst, false); + hws->funcs.dsc_pg_control(hws, pipe_ctx->stream_res.dsc->inst, false); while (odm_pipe) { - dcn20_dsc_pg_control(hws, odm_pipe->stream_res.dsc->inst, false); + hws->funcs.dsc_pg_control(hws, odm_pipe->stream_res.dsc->inst, false); odm_pipe = odm_pipe->next_odm_pipe; } } diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_init.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_init.c index 966e1790b9bf..072193c5ffe6 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_init.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_init.c @@ -68,6 +68,7 @@ static const struct hw_sequencer_funcs dcn20_funcs = { .get_hw_state = dcn10_get_hw_state, .clear_status_bits = dcn10_clear_status_bits, .wait_for_mpcc_disconnect = dcn10_wait_for_mpcc_disconnect, + .edp_backlight_control = dce110_edp_backlight_control, .edp_power_control = dce110_edp_power_control, .edp_wait_for_hpd_ready = dce110_edp_wait_for_hpd_ready, .set_cursor_position = dcn10_set_cursor_position, diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_optc.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_optc.c index 8c16967fe018..d8b18c515d06 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_optc.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_optc.c @@ -239,7 +239,6 @@ void optc2_set_odm_combine(struct timing_generator *optc, int *opp_id, int opp_c int mpcc_hactive = (timing->h_addressable + timing->h_border_left + timing->h_border_right) / opp_cnt; uint32_t memory_mask; - uint32_t data_fmt = 0; ASSERT(opp_cnt == 2); @@ -262,13 +261,6 @@ void optc2_set_odm_combine(struct timing_generator *optc, int *opp_id, int opp_c REG_SET(OPTC_MEMORY_CONFIG, 0, OPTC_MEM_SEL, memory_mask); - if (timing->pixel_encoding == PIXEL_ENCODING_YCBCR422) - data_fmt = 1; - else if (timing->pixel_encoding == PIXEL_ENCODING_YCBCR420) - data_fmt = 2; - - REG_UPDATE(OPTC_DATA_FORMAT_CONTROL, OPTC_DATA_FORMAT, data_fmt); - REG_SET_3(OPTC_DATA_SOURCE_SELECT, 0, OPTC_NUM_OF_INPUT_SEGMENT, 1, OPTC_SEG0_SRC_SEL, opp_id[0], diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c index 1b9874445134..d50a9c370637 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c @@ -150,7 +150,6 @@ struct _vcs_dpi_ip_params_st dcn2_0_ip = { .dispclk_delay_subtotal = 87, // .dcfclk_cstate_latency = 10, // SRExitTime .max_inter_dcn_tile_repeaters = 8, - .xfc_supported = true, .xfc_fill_bw_overhead_percent = 10.0, .xfc_fill_constant_bytes = 0, @@ -298,8 +297,8 @@ static struct _vcs_dpi_soc_bounding_box_st dcn2_0_soc = { }, }, .num_states = 5, - .sr_exit_time_us = 8.6, - .sr_enter_plus_exit_time_us = 10.9, + .sr_exit_time_us = 11.6, + .sr_enter_plus_exit_time_us = 13.9, .urgent_latency_us = 4.0, .urgent_latency_pixel_data_only_us = 4.0, .urgent_latency_pixel_mixed_with_vm_data_us = 4.0, @@ -409,8 +408,8 @@ static struct _vcs_dpi_soc_bounding_box_st dcn2_0_nv14_soc = { }, }, .num_states = 5, - .sr_exit_time_us = 8.6, - .sr_enter_plus_exit_time_us = 10.9, + .sr_exit_time_us = 11.6, + .sr_enter_plus_exit_time_us = 13.9, .urgent_latency_us = 4.0, .urgent_latency_pixel_data_only_us = 4.0, .urgent_latency_pixel_mixed_with_vm_data_us = 4.0, @@ -1075,7 +1074,6 @@ static const struct dc_debug_options debug_defaults_drv = { .disable_pplib_wm_range = false, .scl_reset_length10 = true, .sanity_checks = false, - .disable_tri_buf = true, .underflow_assert_delay_us = 0xFFFFFFFF, }; @@ -1092,6 +1090,7 @@ static const struct dc_debug_options debug_defaults_diags = { .disable_stutter = true, .scl_reset_length10 = true, .underflow_assert_delay_us = 0xFFFFFFFF, + .enable_tri_buf = true, }; void dcn20_dpp_destroy(struct dpp **dpp) @@ -2203,9 +2202,9 @@ int dcn20_populate_dml_pipes_from_context( /* todo: default max for now, until there is logic reflecting this in dc*/ pipes[pipe_cnt].dout.output_bpc = 12; #if defined(CONFIG_DRM_AMD_DC_DCN3_0) - /*fill up the audio sample rate*/ + /*fill up the audio sample rate (unit in kHz)*/ get_audio_check(&res_ctx->pipe_ctx[i].stream->audio_info, &aud_check); - pipes[pipe_cnt].dout.max_audio_sample_rate = aud_check.max_audiosample_rate; + pipes[pipe_cnt].dout.max_audio_sample_rate = aud_check.max_audiosample_rate / 1000; #endif /* * For graphic plane, cursor number is 1, nv12 is 0 diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_stream_encoder.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_stream_encoder.c index e3984f02b7b3..4075ae111530 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_stream_encoder.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_stream_encoder.c @@ -561,8 +561,8 @@ static const struct stream_encoder_funcs dcn20_str_enc_funcs = { enc1_stream_encoder_hdmi_set_stream_attribute, .dvi_set_stream_attribute = enc1_stream_encoder_dvi_set_stream_attribute, - .set_mst_bandwidth = - enc1_stream_encoder_set_mst_bandwidth, + .set_throttled_vcp_size = + enc1_stream_encoder_set_throttled_vcp_size, .update_hdmi_info_packets = enc2_stream_encoder_update_hdmi_info_packets, .stop_hdmi_info_packets = diff --git a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_init.c b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_init.c index 2ba880c3943c..2b7396c9fcb4 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_init.c +++ b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_init.c @@ -69,6 +69,7 @@ static const struct hw_sequencer_funcs dcn21_funcs = { .get_hw_state = dcn10_get_hw_state, .clear_status_bits = dcn10_clear_status_bits, .wait_for_mpcc_disconnect = dcn10_wait_for_mpcc_disconnect, + .edp_backlight_control = dce110_edp_backlight_control, .edp_power_control = dce110_edp_power_control, .edp_wait_for_hpd_ready = dce110_edp_wait_for_hpd_ready, .set_cursor_position = dcn10_set_cursor_position, diff --git a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c index 78743ae37851..e73785e74cba 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c @@ -894,6 +894,8 @@ static const struct dc_debug_options debug_defaults_diags = { .disable_pplib_wm_range = true, .disable_stutter = true, .disable_48mhz_pwrdwn = true, + .disable_psr = true, + .enable_tri_buf = true }; enum dcn20_clk_src_array_id { diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/Makefile b/drivers/gpu/drm/amd/display/dc/dcn30/Makefile index 025637a83c3b..bd2a068f9863 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn30/Makefile +++ b/drivers/gpu/drm/amd/display/dc/dcn30/Makefile @@ -31,9 +31,21 @@ DCN30 = dcn30_init.o dcn30_hubbub.o dcn30_hubp.o dcn30_dpp.o dcn30_optc.o \ dcn30_dio_link_encoder.o dcn30_resource.o -CFLAGS_$(AMDDALPATH)/dc/dcn30/dcn30_optc.o := -mhard-float -msse -mpreferred-stack-boundary=4 - +ifdef CONFIG_X86 CFLAGS_$(AMDDALPATH)/dc/dcn30/dcn30_resource.o := -mhard-float -msse +CFLAGS_$(AMDDALPATH)/dc/dcn30/dcn30_optc.o := -mhard-float -msse +endif + +ifdef CONFIG_PPC64 +CFLAGS_$(AMDDALPATH)/dc/dcn30/dcn30_resource.o := -mhard-float -maltivec +CFLAGS_$(AMDDALPATH)/dc/dcn30/dcn30_optc.o := -mhard-float -maltivec +endif + +ifdef CONFIG_ARM64 +CFLAGS_REMOVE_$(AMDDALPATH)/dc/dcn30/dcn30_resource.o := -mgeneral-regs-only +CFLAGS_REMOVE_$(AMDDALPATH)/dc/dcn30/dcn30_optc.o := -mgeneral-regs-only +endif + ifdef CONFIG_CC_IS_GCC ifeq ($(call cc-ifversion, -lt, 0701, y), y) IS_OLD_GCC = 1 @@ -45,8 +57,10 @@ ifdef IS_OLD_GCC # GCC < 7.1 cannot compile code using `double` and -mpreferred-stack-boundary=3 # (8B stack alignment). CFLAGS_$(AMDDALPATH)/dc/dcn30/dcn30_resource.o += -mpreferred-stack-boundary=4 +CFLAGS_$(AMDDALPATH)/dc/dcn30/dcn30_optc.o += -mpreferred-stack-boundary=4 else CFLAGS_$(AMDDALPATH)/dc/dcn30/dcn30_resource.o += -msse2 +CFLAGS_$(AMDDALPATH)/dc/dcn30/dcn30_optc.o += -msse2 endif AMD_DAL_DCN30 = $(addprefix $(AMDDALPATH)/dc/dcn30/,$(DCN30)) diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_cm_common.c b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_cm_common.c index a139a87a1a81..41a1d0e9b7e2 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_cm_common.c +++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_cm_common.c @@ -122,8 +122,6 @@ bool cm3_helper_translate_curve_to_hw_format( if (output_tf == NULL || lut_params == NULL || output_tf->type == TF_TYPE_BYPASS) return false; - PERF_TRACE_CTX(output_tf->ctx); - corner_points = lut_params->corner_points; rgb_resulted = lut_params->rgb_resulted; hw_points = 0; @@ -314,8 +312,6 @@ bool cm3_helper_translate_curve_to_degamma_hw_format( if (output_tf == NULL || lut_params == NULL || output_tf->type == TF_TYPE_BYPASS) return false; - PERF_TRACE_CTX(output_tf->ctx); - corner_points = lut_params->corner_points; rgb_resulted = lut_params->rgb_resulted; hw_points = 0; diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dio_stream_encoder.c b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dio_stream_encoder.c index f5e80a0db72b..6c0f7ef0a3df 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dio_stream_encoder.c +++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dio_stream_encoder.c @@ -790,8 +790,8 @@ static const struct stream_encoder_funcs dcn30_str_enc_funcs = { enc3_stream_encoder_hdmi_set_stream_attribute, .dvi_set_stream_attribute = enc3_stream_encoder_dvi_set_stream_attribute, - .set_mst_bandwidth = - enc1_stream_encoder_set_mst_bandwidth, + .set_throttled_vcp_size = + enc1_stream_encoder_set_throttled_vcp_size, .update_hdmi_info_packets = enc3_stream_encoder_update_hdmi_info_packets, .stop_hdmi_info_packets = diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c index a5d750ed569e..204773ffc376 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c @@ -35,7 +35,6 @@ #include "dcn30_dpp.h" #include "dcn10/dcn10_cm_common.h" #include "dcn30_cm_common.h" -#include "clk_mgr.h" #include "reg_helper.h" #include "abm.h" #include "clk_mgr.h" @@ -220,15 +219,13 @@ static void dcn30_set_writeback( struct dc_writeback_info *wb_info, struct dc_state *context) { - struct dwbc *dwb; struct mcif_wb *mcif_wb; struct mcif_buf_params *mcif_buf_params; ASSERT(wb_info->dwb_pipe_inst < MAX_DWB_PIPES); ASSERT(wb_info->wb_enabled); ASSERT(wb_info->mpcc_inst >= 0); - ASSERT(wb_info->mpcc_inst < 4); - dwb = dc->res_pool->dwbc[wb_info->dwb_pipe_inst]; + ASSERT(wb_info->mpcc_inst < dc->res_pool->mpcc_count); mcif_wb = dc->res_pool->mcif_wb[wb_info->dwb_pipe_inst]; mcif_buf_params = &wb_info->mcif_buf_params; @@ -692,26 +689,23 @@ void dcn30_program_dmdata_engine(struct pipe_ctx *pipe_ctx) bool dcn30_apply_idle_power_optimizations(struct dc *dc, bool enable) { - unsigned int surface_size; - if (!dc->ctx->dmub_srv) return false; if (enable) { - if (dc->current_state - && dc->current_state->stream_count == 1 // single display only - && dc->current_state->stream_status[0].plane_count == 1 // single surface only - && dc->current_state->stream_status[0].plane_states[0]->address.page_table_base.quad_part == 0 // no VM - // Only 8 and 16 bit formats - && dc->current_state->stream_status[0].plane_states[0]->format <= SURFACE_PIXEL_FORMAT_GRPH_ABGR16161616F - && dc->current_state->stream_status[0].plane_states[0]->format >= SURFACE_PIXEL_FORMAT_GRPH_ARGB8888) { - - surface_size = dc->current_state->stream_status[0].plane_states[0]->plane_size.surface_pitch * - dc->current_state->stream_status[0].plane_states[0]->plane_size.surface_size.height * - (dc->current_state->stream_status[0].plane_states[0]->format >= SURFACE_PIXEL_FORMAT_GRPH_ARGB16161616 ? 8 : 4); - + if (dc->current_state) { + int i; + + /* First, check no-memory-requests case */ + for (i = 0; i < dc->current_state->stream_count; i++) { + if (dc->current_state->stream_status[i] + .plane_count) + /* Fail eligibility on a visible stream */ + break; + } } + /* No applicable optimizations */ return false; } diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_init.c b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_init.c index 19daa456e3bf..7c90c2222506 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_init.c +++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_init.c @@ -69,6 +69,7 @@ static const struct hw_sequencer_funcs dcn30_funcs = { .get_hw_state = dcn10_get_hw_state, .clear_status_bits = dcn10_clear_status_bits, .wait_for_mpcc_disconnect = dcn10_wait_for_mpcc_disconnect, + .edp_backlight_control = dce110_edp_backlight_control, .edp_power_control = dce110_edp_power_control, .edp_wait_for_hpd_ready = dce110_edp_wait_for_hpd_ready, .set_cursor_position = dcn10_set_cursor_position, diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_optc.c b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_optc.c index 224c8d145eba..b1f228fc119a 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_optc.c +++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_optc.c @@ -179,8 +179,7 @@ void optc3_set_dsc_config(struct timing_generator *optc, } - -static void optc3_set_odm_bypass(struct timing_generator *optc, +void optc3_set_odm_bypass(struct timing_generator *optc, const struct dc_crtc_timing *dc_crtc_timing) { struct optc *optc1 = DCN10TG_FROM_TG(optc); @@ -210,7 +209,6 @@ static void optc3_set_odm_combine(struct timing_generator *optc, int *opp_id, in int mpcc_hactive = (timing->h_addressable + timing->h_border_left + timing->h_border_right) / opp_cnt; uint32_t memory_mask = 0; - uint32_t data_fmt = 0; /* TODO: In pseudocode but does not affect maximus, delete comment if we dont need on asic * REG_SET(OTG_GLOBAL_CONTROL2, 0, GLOBAL_UPDATE_LOCK_EN, 1); @@ -241,13 +239,6 @@ static void optc3_set_odm_combine(struct timing_generator *optc, int *opp_id, in REG_SET(OPTC_MEMORY_CONFIG, 0, OPTC_MEM_SEL, memory_mask); - if (timing->pixel_encoding == PIXEL_ENCODING_YCBCR422) - data_fmt = 1; - else if (timing->pixel_encoding == PIXEL_ENCODING_YCBCR420) - data_fmt = 2; - - REG_UPDATE(OPTC_DATA_FORMAT_CONTROL, OPTC_DATA_FORMAT, data_fmt); - if (opp_cnt == 2) { REG_SET_3(OPTC_DATA_SOURCE_SELECT, 0, OPTC_NUM_OF_INPUT_SEGMENT, 1, @@ -277,7 +268,7 @@ static void optc3_set_odm_combine(struct timing_generator *optc, int *opp_id, in * * Options: any time, start of frame, dp start of frame (range timing) */ -void optc3_set_timing_double_buffer(struct timing_generator *optc, bool enable) +static void optc3_set_timing_double_buffer(struct timing_generator *optc, bool enable) { struct optc *optc1 = DCN10TG_FROM_TG(optc); uint32_t mode = enable ? 2 : 0; diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_optc.h b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_optc.h index 33f13c1e7520..379616831636 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_optc.h +++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_optc.h @@ -339,4 +339,8 @@ void optc3_set_dsc_config(struct timing_generator *optc, void optc3_set_timing_db_mode(struct timing_generator *optc, bool enable); +void optc3_set_odm_bypass(struct timing_generator *optc, + const struct dc_crtc_timing *dc_crtc_timing); +void optc3_tg_init(struct timing_generator *optc); + #endif /* __DC_OPTC_DCN30_H__ */ diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.c b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.c index 8be4f21169d0..2455d210ccf6 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.c @@ -79,6 +79,7 @@ #include "reg_helper.h" #include "dce/dmub_abm.h" +#include "dce/dmub_psr.h" #include "dce/dce_aux.h" #include "dce/dce_i2c.h" @@ -832,7 +833,7 @@ static const struct dc_plane_cap plane_cap = { }; static const struct dc_debug_options debug_defaults_drv = { - .disable_dmcu = true, + .disable_dmcu = true, //No DMCU on DCN30 .force_abm_enable = false, .timing_trace = false, .clock_trace = true, @@ -849,10 +850,11 @@ static const struct dc_debug_options debug_defaults_drv = { .underflow_assert_delay_us = 0xFFFFFFFF, .dwb_fi_phase = -1, // -1 = disable, .dmub_command_table = true, + .disable_psr = false, }; static const struct dc_debug_options debug_defaults_diags = { - .disable_dmcu = true, + .disable_dmcu = true, //No dmcu on DCN30 .force_abm_enable = false, .timing_trace = true, .clock_trace = true, @@ -865,6 +867,8 @@ static const struct dc_debug_options debug_defaults_diags = { .scl_reset_length10 = true, .dwb_fi_phase = -1, // -1 = disable .dmub_command_table = true, + .disable_psr = true, + .enable_tri_buf = true, }; void dcn30_dpp_destroy(struct dpp **dpp) @@ -1312,6 +1316,9 @@ static void dcn30_resource_destruct(struct dcn30_resource_pool *pool) dce_abm_destroy(&pool->base.multiple_abms[i]); } + if (pool->base.psr != NULL) + dmub_psr_destroy(&pool->base.psr); + if (pool->base.dccg != NULL) dcn_dccg_destroy(&pool->base.dccg); } @@ -1821,6 +1828,22 @@ static bool init_soc_bounding_box(struct dc *dc, loaded_ip->max_num_dpp = pool->base.pipe_count; loaded_ip->clamp_min_dcfclk = dc->config.clamp_min_dcfclk; dcn20_patch_bounding_box(dc, loaded_bb); + + if (!bb && dc->ctx->dc_bios->funcs->get_soc_bb_info) { + struct bp_soc_bb_info bb_info = {0}; + + if (dc->ctx->dc_bios->funcs->get_soc_bb_info(dc->ctx->dc_bios, &bb_info) == BP_RESULT_OK) { + if (bb_info.dram_clock_change_latency_100ns > 0) + dcn3_0_soc.dram_clock_change_latency_us = bb_info.dram_clock_change_latency_100ns * 10; + + if (bb_info.dram_sr_enter_exit_latency_100ns > 0) + dcn3_0_soc.sr_enter_plus_exit_time_us = bb_info.dram_sr_enter_exit_latency_100ns * 10; + + if (bb_info.dram_sr_exit_latency_100ns > 0) + dcn3_0_soc.sr_exit_time_us = bb_info.dram_sr_exit_latency_100ns * 10; + } + } + return true; } @@ -1876,6 +1899,48 @@ static bool dcn30_split_stream_for_mpc_or_odm( return true; } +static struct pipe_ctx *dcn30_find_split_pipe( + struct dc *dc, + struct dc_state *context, + int old_index) +{ + struct pipe_ctx *pipe = NULL; + int i; + + if (old_index >= 0 && context->res_ctx.pipe_ctx[old_index].stream == NULL) { + pipe = &context->res_ctx.pipe_ctx[old_index]; + pipe->pipe_idx = old_index; + } + + if (!pipe) + for (i = dc->res_pool->pipe_count - 1; i >= 0; i--) { + if (dc->current_state->res_ctx.pipe_ctx[i].top_pipe == NULL + && dc->current_state->res_ctx.pipe_ctx[i].prev_odm_pipe == NULL) { + if (context->res_ctx.pipe_ctx[i].stream == NULL) { + pipe = &context->res_ctx.pipe_ctx[i]; + pipe->pipe_idx = i; + break; + } + } + } + + /* + * May need to fix pipes getting tossed from 1 opp to another on flip + * Add for debugging transient underflow during topology updates: + * ASSERT(pipe); + */ + if (!pipe) + for (i = dc->res_pool->pipe_count - 1; i >= 0; i--) { + if (context->res_ctx.pipe_ctx[i].stream == NULL) { + pipe = &context->res_ctx.pipe_ctx[i]; + pipe->pipe_idx = i; + break; + } + } + + return pipe; +} + static bool dcn30_internal_validate_bw( struct dc *dc, struct dc_state *context, @@ -2001,6 +2066,7 @@ static bool dcn30_internal_validate_bw( dcn20_release_dsc(&context->res_ctx, dc->res_pool, &pipe->stream_res.dsc); memset(&pipe->plane_res, 0, sizeof(pipe->plane_res)); memset(&pipe->stream_res, 0, sizeof(pipe->stream_res)); + repopulate_pipes = true; } else if (pipe->top_pipe && pipe->top_pipe->plane_state == pipe->plane_state) { struct pipe_ctx *top_pipe = pipe->top_pipe; struct pipe_ctx *bottom_pipe = pipe->bottom_pipe; @@ -2015,6 +2081,7 @@ static bool dcn30_internal_validate_bw( pipe->stream = NULL; memset(&pipe->plane_res, 0, sizeof(pipe->plane_res)); memset(&pipe->stream_res, 0, sizeof(pipe->stream_res)); + repopulate_pipes = true; } else ASSERT(0); /* Should never try to merge master pipe */ @@ -2022,8 +2089,10 @@ static bool dcn30_internal_validate_bw( for (i = 0, pipe_idx = -1; i < dc->res_pool->pipe_count; i++) { struct pipe_ctx *pipe = &context->res_ctx.pipe_ctx[i]; + struct pipe_ctx *old_pipe = &dc->current_state->res_ctx.pipe_ctx[i]; struct pipe_ctx *hsplit_pipe = NULL; bool odm; + int old_index = -1; if (!pipe->stream || newly_split[i]) continue; @@ -2035,7 +2104,20 @@ static bool dcn30_internal_validate_bw( continue; if (split[i]) { - hsplit_pipe = find_idle_secondary_pipe(&context->res_ctx, dc->res_pool, pipe); + if (odm) { + if (split[i] == 4 && old_pipe->next_odm_pipe && old_pipe->next_odm_pipe->next_odm_pipe) + old_index = old_pipe->next_odm_pipe->next_odm_pipe->pipe_idx; + else if (old_pipe->next_odm_pipe) + old_index = old_pipe->next_odm_pipe->pipe_idx; + } else { + if (split[i] == 4 && old_pipe->bottom_pipe && old_pipe->bottom_pipe->bottom_pipe && + old_pipe->bottom_pipe->bottom_pipe->plane_state == old_pipe->plane_state) + old_index = old_pipe->bottom_pipe->bottom_pipe->pipe_idx; + else if (old_pipe->bottom_pipe && + old_pipe->bottom_pipe->plane_state == old_pipe->plane_state) + old_index = old_pipe->bottom_pipe->pipe_idx; + } + hsplit_pipe = dcn30_find_split_pipe(dc, context, old_index); ASSERT(hsplit_pipe); if (!hsplit_pipe) goto validate_fail; @@ -2049,8 +2131,16 @@ static bool dcn30_internal_validate_bw( repopulate_pipes = true; } if (split[i] == 4) { - struct pipe_ctx *pipe_4to1 = find_idle_secondary_pipe(&context->res_ctx, dc->res_pool, pipe); + struct pipe_ctx *pipe_4to1; + if (odm && old_pipe->next_odm_pipe) + old_index = old_pipe->next_odm_pipe->pipe_idx; + else if (!odm && old_pipe->bottom_pipe && + old_pipe->bottom_pipe->plane_state == old_pipe->plane_state) + old_index = old_pipe->bottom_pipe->pipe_idx; + else + old_index = -1; + pipe_4to1 = dcn30_find_split_pipe(dc, context, old_index); ASSERT(pipe_4to1); if (!pipe_4to1) goto validate_fail; @@ -2060,7 +2150,16 @@ static bool dcn30_internal_validate_bw( goto validate_fail; newly_split[pipe_4to1->pipe_idx] = true; - pipe_4to1 = find_idle_secondary_pipe(&context->res_ctx, dc->res_pool, pipe); + if (odm && old_pipe->next_odm_pipe && old_pipe->next_odm_pipe->next_odm_pipe + && old_pipe->next_odm_pipe->next_odm_pipe->next_odm_pipe) + old_index = old_pipe->next_odm_pipe->next_odm_pipe->next_odm_pipe->pipe_idx; + else if (!odm && old_pipe->bottom_pipe && old_pipe->bottom_pipe->bottom_pipe && + old_pipe->bottom_pipe->bottom_pipe->bottom_pipe && + old_pipe->bottom_pipe->bottom_pipe->bottom_pipe->plane_state == old_pipe->plane_state) + old_index = old_pipe->bottom_pipe->bottom_pipe->bottom_pipe->pipe_idx; + else + old_index = -1; + pipe_4to1 = dcn30_find_split_pipe(dc, context, old_index); ASSERT(pipe_4to1); if (!pipe_4to1) goto validate_fail; @@ -2104,7 +2203,7 @@ validate_out: return out; } -static void dcn30_calculate_wm( +void dcn30_calculate_wm_and_dlg( struct dc *dc, struct dc_state *context, display_e2e_pipe_params_st *pipes, int pipe_cnt, @@ -2112,6 +2211,8 @@ static void dcn30_calculate_wm( { int i, pipe_idx; double dcfclk = context->bw_ctx.dml.vba.DCFCLKState[vlevel][context->bw_ctx.dml.vba.maxMpcComb]; + bool pstate_en = context->bw_ctx.dml.vba.DRAMClockChangeSupport[vlevel][context->bw_ctx.dml.vba.maxMpcComb] != + dm_dram_clock_change_unsupported; if (context->bw_ctx.dml.soc.min_dcfclk > dcfclk) dcfclk = context->bw_ctx.dml.soc.min_dcfclk; @@ -2145,30 +2246,12 @@ static void dcn30_calculate_wm( pipes[0].clks_cfg.voltage = vlevel; pipes[0].clks_cfg.dcfclk_mhz = dcfclk; - /* Set C: - * DCFCLK: Min Required - * FCLK(proportional to UCLK): 1GHz or Max - * pstate latency overriden to 5us - */ - if (dc->clk_mgr->bw_params->wm_table.nv_entries[WM_C].valid) { - context->bw_ctx.dml.soc.dram_clock_change_latency_us = dc->clk_mgr->bw_params->wm_table.nv_entries[WM_C].dml_input.pstate_latency_us; - context->bw_ctx.dml.soc.sr_enter_plus_exit_time_us = dc->clk_mgr->bw_params->wm_table.nv_entries[WM_C].dml_input.sr_enter_plus_exit_time_us; - context->bw_ctx.dml.soc.sr_exit_time_us = dc->clk_mgr->bw_params->wm_table.nv_entries[WM_C].dml_input.sr_exit_time_us; - } - context->bw_ctx.bw.dcn.watermarks.c.urgent_ns = get_wm_urgent(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; - context->bw_ctx.bw.dcn.watermarks.c.cstate_pstate.cstate_enter_plus_exit_ns = get_wm_stutter_enter_exit(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; - context->bw_ctx.bw.dcn.watermarks.c.cstate_pstate.cstate_exit_ns = get_wm_stutter_exit(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; - context->bw_ctx.bw.dcn.watermarks.c.cstate_pstate.pstate_change_ns = get_wm_dram_clock_change(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; - context->bw_ctx.bw.dcn.watermarks.c.pte_meta_urgent_ns = get_wm_memory_trip(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; - context->bw_ctx.bw.dcn.watermarks.c.frac_urg_bw_nom = get_fraction_of_urgent_bandwidth(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; - context->bw_ctx.bw.dcn.watermarks.c.frac_urg_bw_flip = get_fraction_of_urgent_bandwidth_imm_flip(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; - context->bw_ctx.bw.dcn.watermarks.c.urgent_latency_ns = get_urgent_latency(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; - /* Set D: * DCFCLK: Min Required * FCLK(proportional to UCLK): 1GHz or Max * sr_enter_exit = 4, sr_exit = 2us */ + /* if (dc->clk_mgr->bw_params->wm_table.nv_entries[WM_D].valid) { context->bw_ctx.dml.soc.dram_clock_change_latency_us = dc->clk_mgr->bw_params->wm_table.nv_entries[WM_D].dml_input.pstate_latency_us; context->bw_ctx.dml.soc.sr_enter_plus_exit_time_us = dc->clk_mgr->bw_params->wm_table.nv_entries[WM_D].dml_input.sr_enter_plus_exit_time_us; @@ -2182,26 +2265,72 @@ static void dcn30_calculate_wm( context->bw_ctx.bw.dcn.watermarks.d.frac_urg_bw_nom = get_fraction_of_urgent_bandwidth(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; context->bw_ctx.bw.dcn.watermarks.d.frac_urg_bw_flip = get_fraction_of_urgent_bandwidth_imm_flip(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; context->bw_ctx.bw.dcn.watermarks.d.urgent_latency_ns = get_urgent_latency(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; + */ - /* Set A: + /* Set C: * DCFCLK: Min Required * FCLK(proportional to UCLK): 1GHz or Max - * - * Set A calculated last so that following calculations are based on Set A + * pstate latency overridden to 5us */ - if (dc->clk_mgr->bw_params->wm_table.nv_entries[WM_A].valid) { - context->bw_ctx.dml.soc.dram_clock_change_latency_us = dc->clk_mgr->bw_params->wm_table.nv_entries[WM_A].dml_input.pstate_latency_us; - context->bw_ctx.dml.soc.sr_enter_plus_exit_time_us = dc->clk_mgr->bw_params->wm_table.nv_entries[WM_A].dml_input.sr_enter_plus_exit_time_us; - context->bw_ctx.dml.soc.sr_exit_time_us = dc->clk_mgr->bw_params->wm_table.nv_entries[WM_A].dml_input.sr_exit_time_us; + if (dc->clk_mgr->bw_params->wm_table.nv_entries[WM_C].valid) { + unsigned int min_dram_speed_mts = context->bw_ctx.dml.vba.DRAMSpeed; + unsigned int min_dram_speed_mts_margin = 160; + + context->bw_ctx.dml.soc.dram_clock_change_latency_us = dc->clk_mgr->bw_params->dummy_pstate_table[0].dummy_pstate_latency_us; + + if (context->bw_ctx.dml.vba.DRAMClockChangeSupport[vlevel][context->bw_ctx.dml.vba.maxMpcComb] == dm_dram_clock_change_unsupported) + min_dram_speed_mts = dc->clk_mgr->bw_params->clk_table.entries[dc->clk_mgr->bw_params->clk_table.num_entries - 1].memclk_mhz * 16; + + for (i = 3; i > 0; i--) { + if ((min_dram_speed_mts + min_dram_speed_mts_margin > dc->clk_mgr->bw_params->dummy_pstate_table[i].dram_speed_mts) && + (min_dram_speed_mts - min_dram_speed_mts_margin < dc->clk_mgr->bw_params->dummy_pstate_table[i].dram_speed_mts)) + context->bw_ctx.dml.soc.dram_clock_change_latency_us = dc->clk_mgr->bw_params->dummy_pstate_table[i].dummy_pstate_latency_us; + } + + context->bw_ctx.dml.soc.sr_enter_plus_exit_time_us = dc->clk_mgr->bw_params->wm_table.nv_entries[WM_C].dml_input.sr_enter_plus_exit_time_us; + context->bw_ctx.dml.soc.sr_exit_time_us = dc->clk_mgr->bw_params->wm_table.nv_entries[WM_C].dml_input.sr_exit_time_us; + } + context->bw_ctx.bw.dcn.watermarks.c.urgent_ns = get_wm_urgent(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; + context->bw_ctx.bw.dcn.watermarks.c.cstate_pstate.cstate_enter_plus_exit_ns = get_wm_stutter_enter_exit(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; + context->bw_ctx.bw.dcn.watermarks.c.cstate_pstate.cstate_exit_ns = get_wm_stutter_exit(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; + context->bw_ctx.bw.dcn.watermarks.c.cstate_pstate.pstate_change_ns = get_wm_dram_clock_change(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; + context->bw_ctx.bw.dcn.watermarks.c.pte_meta_urgent_ns = get_wm_memory_trip(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; + context->bw_ctx.bw.dcn.watermarks.c.frac_urg_bw_nom = get_fraction_of_urgent_bandwidth(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; + context->bw_ctx.bw.dcn.watermarks.c.frac_urg_bw_flip = get_fraction_of_urgent_bandwidth_imm_flip(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; + context->bw_ctx.bw.dcn.watermarks.c.urgent_latency_ns = get_urgent_latency(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; + + if (!pstate_en) { + /* The only difference between A and C is p-state latency, if p-state is not supported we want to + * calculate DLG based on dummy p-state latency, and max out the set A p-state watermark + */ + context->bw_ctx.bw.dcn.watermarks.a = context->bw_ctx.bw.dcn.watermarks.c; + context->bw_ctx.bw.dcn.watermarks.a.cstate_pstate.pstate_change_ns = 0x13FFFF; + } else { + /* Set A: + * DCFCLK: Min Required + * FCLK(proportional to UCLK): 1GHz or Max + * + * Set A calculated last so that following calculations are based on Set A + */ + if (dc->clk_mgr->bw_params->wm_table.nv_entries[WM_A].valid) { + context->bw_ctx.dml.soc.dram_clock_change_latency_us = dc->clk_mgr->bw_params->wm_table.nv_entries[WM_A].dml_input.pstate_latency_us; + context->bw_ctx.dml.soc.sr_enter_plus_exit_time_us = dc->clk_mgr->bw_params->wm_table.nv_entries[WM_A].dml_input.sr_enter_plus_exit_time_us; + context->bw_ctx.dml.soc.sr_exit_time_us = dc->clk_mgr->bw_params->wm_table.nv_entries[WM_A].dml_input.sr_exit_time_us; + } + context->bw_ctx.bw.dcn.watermarks.a.urgent_ns = get_wm_urgent(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; + context->bw_ctx.bw.dcn.watermarks.a.cstate_pstate.cstate_enter_plus_exit_ns = get_wm_stutter_enter_exit(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; + context->bw_ctx.bw.dcn.watermarks.a.cstate_pstate.cstate_exit_ns = get_wm_stutter_exit(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; + context->bw_ctx.bw.dcn.watermarks.a.cstate_pstate.pstate_change_ns = get_wm_dram_clock_change(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; + context->bw_ctx.bw.dcn.watermarks.a.pte_meta_urgent_ns = get_wm_memory_trip(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; + context->bw_ctx.bw.dcn.watermarks.a.frac_urg_bw_nom = get_fraction_of_urgent_bandwidth(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; + context->bw_ctx.bw.dcn.watermarks.a.frac_urg_bw_flip = get_fraction_of_urgent_bandwidth_imm_flip(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; + context->bw_ctx.bw.dcn.watermarks.a.urgent_latency_ns = get_urgent_latency(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; } - context->bw_ctx.bw.dcn.watermarks.a.urgent_ns = get_wm_urgent(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; - context->bw_ctx.bw.dcn.watermarks.a.cstate_pstate.cstate_enter_plus_exit_ns = get_wm_stutter_enter_exit(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; - context->bw_ctx.bw.dcn.watermarks.a.cstate_pstate.cstate_exit_ns = get_wm_stutter_exit(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; - context->bw_ctx.bw.dcn.watermarks.a.cstate_pstate.pstate_change_ns = get_wm_dram_clock_change(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; - context->bw_ctx.bw.dcn.watermarks.a.pte_meta_urgent_ns = get_wm_memory_trip(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; - context->bw_ctx.bw.dcn.watermarks.a.frac_urg_bw_nom = get_fraction_of_urgent_bandwidth(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; - context->bw_ctx.bw.dcn.watermarks.a.frac_urg_bw_flip = get_fraction_of_urgent_bandwidth_imm_flip(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; - context->bw_ctx.bw.dcn.watermarks.a.urgent_latency_ns = get_urgent_latency(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; + + context->perf_params.stutter_period_us = context->bw_ctx.dml.vba.StutterPeriod; + + /* Make set D = set A until set D is enabled */ + context->bw_ctx.bw.dcn.watermarks.d = context->bw_ctx.bw.dcn.watermarks.a; for (i = 0, pipe_idx = 0; i < dc->res_pool->pipe_count; i++) { if (!context->res_ctx.pipe_ctx[i].stream) @@ -2221,6 +2350,13 @@ static void dcn30_calculate_wm( pipe_idx++; } + + dcn20_calculate_dlg_params(dc, context, pipes, pipe_cnt, vlevel); + + if (!pstate_en) + /* Restore full p-state latency */ + context->bw_ctx.dml.soc.dram_clock_change_latency_us = + dc->clk_mgr->bw_params->wm_table.nv_entries[WM_A].dml_input.pstate_latency_us; } bool dcn30_validate_bandwidth(struct dc *dc, @@ -2253,8 +2389,7 @@ bool dcn30_validate_bandwidth(struct dc *dc, goto validate_out; } - dcn30_calculate_wm(dc, context, pipes, pipe_cnt, vlevel); - dcn20_calculate_dlg_params(dc, context, pipes, pipe_cnt, vlevel); + dc->res_pool->funcs->calculate_wm_and_dlg(dc, context, pipes, pipe_cnt, vlevel); BW_VAL_TRACE_END_WATERMARKS(); @@ -2422,6 +2557,7 @@ static const struct resource_funcs dcn30_res_pool_funcs = { .link_enc_create = dcn30_link_encoder_create, .panel_cntl_create = dcn30_panel_cntl_create, .validate_bandwidth = dcn30_validate_bandwidth, + .calculate_wm_and_dlg = dcn30_calculate_wm_and_dlg, .populate_dml_pipes = dcn30_populate_dml_pipes_from_context, .acquire_idle_pipe_for_layer = dcn20_acquire_idle_pipe_for_layer, .add_stream_to_ctx = dcn30_add_stream_to_ctx, @@ -2623,6 +2759,14 @@ static bool dcn30_resource_construct( } } pool->base.timing_generator_count = i; + /* PSR */ + pool->base.psr = dmub_psr_create(ctx); + + if (pool->base.psr == NULL) { + dm_error("DC: failed to create PSR obj!\n"); + BREAK_TO_DEBUGGER(); + goto create_fail; + } /* ABM */ for (i = 0; i < pool->base.res_cap->num_timing_generator; i++) { diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.h b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.h index c9d5f94092a0..d163812af858 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.h +++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.h @@ -55,6 +55,11 @@ unsigned int dcn30_calc_max_scaled_time( bool dcn30_validate_bandwidth(struct dc *dc, struct dc_state *context, bool fast_validate); +void dcn30_calculate_wm_and_dlg( + struct dc *dc, struct dc_state *context, + display_e2e_pipe_params_st *pipes, + int pipe_cnt, + int vlevel); void dcn30_populate_dml_writeback_from_context( struct dc *dc, struct resource_context *res_ctx, display_e2e_pipe_params_st *pipes); diff --git a/drivers/gpu/drm/amd/display/dc/dm_pp_smu.h b/drivers/gpu/drm/amd/display/dc/dm_pp_smu.h index ae608c329366..3586934df25f 100644 --- a/drivers/gpu/drm/amd/display/dc/dm_pp_smu.h +++ b/drivers/gpu/drm/amd/display/dc/dm_pp_smu.h @@ -30,8 +30,6 @@ * interface to PPLIB/SMU to setup clocks and pstate requirements on SoC */ -typedef bool BOOLEAN; - enum pp_smu_ver { /* * PP_SMU_INTERFACE_X should be interpreted as the interface defined @@ -240,7 +238,7 @@ struct pp_smu_funcs_nv { * DC hardware */ enum pp_smu_status (*set_pstate_handshake_support)(struct pp_smu *pp, - BOOLEAN pstate_handshake_supported); + bool pstate_handshake_supported); }; #define PP_SMU_NUM_SOCCLK_DPM_LEVELS 8 diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_mode_vba_20v2.c b/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_mode_vba_20v2.c index 80170f9721ce..860e72a51534 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_mode_vba_20v2.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_mode_vba_20v2.c @@ -2635,15 +2635,14 @@ static void dml20v2_DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndP } if (mode_lib->vba.DRAMClockChangeSupportsVActive && - mode_lib->vba.MinActiveDRAMClockChangeMargin > 60) { + mode_lib->vba.MinActiveDRAMClockChangeMargin > 60 && + mode_lib->vba.PrefetchMode[mode_lib->vba.VoltageLevel][mode_lib->vba.maxMpcComb] == 0) { mode_lib->vba.DRAMClockChangeWatermark += 25; for (k = 0; k < mode_lib->vba.NumberOfActivePlanes; ++k) { - if (mode_lib->vba.PrefetchMode[mode_lib->vba.VoltageLevel][mode_lib->vba.maxMpcComb] == 0) { - if (mode_lib->vba.DRAMClockChangeWatermark > - dml_max(mode_lib->vba.StutterEnterPlusExitWatermark, mode_lib->vba.UrgentWatermark)) - mode_lib->vba.MinTTUVBlank[k] += 25; - } + if (mode_lib->vba.DRAMClockChangeWatermark > + dml_max(mode_lib->vba.StutterEnterPlusExitWatermark, mode_lib->vba.UrgentWatermark)) + mode_lib->vba.MinTTUVBlank[k] += 25; } mode_lib->vba.DRAMClockChangeSupport[0][0] = dm_dram_clock_change_vactive; diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_rq_dlg_calc_20.h b/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_rq_dlg_calc_20.h index 1e557ddcb638..d0b90947f540 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_rq_dlg_calc_20.h +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_rq_dlg_calc_20.h @@ -33,7 +33,7 @@ struct display_mode_lib; // Function: dml_rq_dlg_get_rq_reg // Main entry point for test to get the register values out of this DML class. -// This function calls <get_rq_param> and <extract_rq_regs> fucntions to calculate +// This function calls <get_rq_param> and <extract_rq_regs> functions to calculate // and then populate the rq_regs struct // Input: // pipe_src_param - pipe source configuration (e.g. vp, pitch, etc.) diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_rq_dlg_calc_20v2.h b/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_rq_dlg_calc_20v2.h index 0d53e871a9d1..27cf8bed9376 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_rq_dlg_calc_20v2.h +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_rq_dlg_calc_20v2.h @@ -33,7 +33,7 @@ struct display_mode_lib; // Function: dml_rq_dlg_get_rq_reg // Main entry point for test to get the register values out of this DML class. -// This function calls <get_rq_param> and <extract_rq_regs> fucntions to calculate +// This function calls <get_rq_param> and <extract_rq_regs> functions to calculate // and then populate the rq_regs struct // Input: // pipe_src_param - pipe source configuration (e.g. vp, pitch, etc.) diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_mode_vba_21.c b/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_mode_vba_21.c index a576eed94d9b..367c82b5ab4c 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_mode_vba_21.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_mode_vba_21.c @@ -1294,7 +1294,7 @@ static unsigned int CalculateVMAndRowBytes( unsigned int MacroTileHeight; unsigned int ExtraDPDEBytesFrame; unsigned int PDEAndMetaPTEBytesFrame; - unsigned int PixelPTEReqHeightPTEs; + unsigned int PixelPTEReqHeightPTEs = 0; if (DCCEnable == true) { *MetaRequestHeight = 8 * BlockHeight256Bytes; 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 2beb284f89b0..9e0ae18e71fa 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 @@ -597,7 +597,8 @@ static void CalculateStutterEfficiency( double meta_row_bw[], double dpte_row_bw[], double *StutterEfficiencyNotIncludingVBlank, - double *StutterEfficiency); + double *StutterEfficiency, + double *StutterPeriodOut); static void CalculateSwathAndDETConfiguration( bool ForceSingleDPP, @@ -3134,7 +3135,8 @@ static void DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerforman v->meta_row_bw, v->dpte_row_bw, &v->StutterEfficiencyNotIncludingVBlank, - &v->StutterEfficiency); + &v->StutterEfficiency, + &v->StutterPeriod); } static void DisplayPipeConfiguration(struct display_mode_lib *mode_lib) @@ -3235,7 +3237,7 @@ static bool CalculateBytePerPixelAnd256BBlockSizes( *BytePerPixelDETC = 0; *BytePerPixelY = 4; *BytePerPixelC = 0; - } else if (SourcePixelFormat == dm_444_16 || SourcePixelFormat == dm_444_16) { + } else if (SourcePixelFormat == dm_444_16) { *BytePerPixelDETY = 2; *BytePerPixelDETC = 0; *BytePerPixelY = 2; @@ -5305,7 +5307,7 @@ void dml30_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l ViewportExceedsSurface = true; if (v->SourcePixelFormat[k] != dm_444_64 && v->SourcePixelFormat[k] != dm_444_32 && v->SourcePixelFormat[k] != dm_444_16 - && v->SourcePixelFormat[k] != dm_444_16 && v->SourcePixelFormat[k] != dm_444_8 && v->SourcePixelFormat[k] != dm_rgbe) { + && v->SourcePixelFormat[k] != dm_444_8 && v->SourcePixelFormat[k] != dm_rgbe) { if (v->ViewportWidthChroma[k] > v->SurfaceWidthC[k] || v->ViewportHeightChroma[k] > v->SurfaceHeightC[k]) { ViewportExceedsSurface = true; } @@ -5515,7 +5517,7 @@ static void CalculateWatermarksAndDRAMSpeedChangeSupport( if (WritebackPixelFormat[k] == dm_444_64) { WritebackDRAMClockChangeLatencyHiding = WritebackDRAMClockChangeLatencyHiding / 2; } - if (mode_lib->vba.WritebackConfiguration == dm_whole_buffer_for_single_stream_interleave || mode_lib->vba.WritebackConfiguration == dm_whole_buffer_for_single_stream_interleave) { + if (mode_lib->vba.WritebackConfiguration == dm_whole_buffer_for_single_stream_interleave) { WritebackDRAMClockChangeLatencyHiding = WritebackDRAMClockChangeLatencyHiding * 2; } WritebackDRAMClockChangeLatencyMargin = WritebackDRAMClockChangeLatencyHiding - mode_lib->vba.WritebackDRAMClockChangeWatermark; @@ -5556,7 +5558,7 @@ static void CalculateWatermarksAndDRAMSpeedChangeSupport( } } - if (mode_lib->vba.MinActiveDRAMClockChangeMargin > 0) { + if (mode_lib->vba.MinActiveDRAMClockChangeMargin > 0 && PrefetchMode == 0) { *DRAMClockChangeSupport = dm_dram_clock_change_vactive; } else if (((mode_lib->vba.SynchronizedVBlank == true || mode_lib->vba.TotalNumberOfActiveOTG == 1 || SecondMinActiveDRAMClockChangeMarginOneDisplayInVBLank > 0) && PrefetchMode == 0)) { *DRAMClockChangeSupport = dm_dram_clock_change_vblank; @@ -6151,7 +6153,8 @@ static void CalculateStutterEfficiency( double meta_row_bw[], double dpte_row_bw[], double *StutterEfficiencyNotIncludingVBlank, - double *StutterEfficiency) + double *StutterEfficiency, + double *StutterPeriodOut) { double FullDETBufferingTimeY[DC__NUM_DPP__MAX] = { 0 }; double FrameTimeForMinFullDETBufferingTime = 0; @@ -6262,6 +6265,9 @@ static void CalculateStutterEfficiency( } *StutterEfficiency = (*StutterEfficiencyNotIncludingVBlank / 100.0 * (FrameTimeForMinFullDETBufferingTime - SmallestVBlank) + SmallestVBlank) / FrameTimeForMinFullDETBufferingTime * 100; + + if (StutterPeriodOut) + *StutterPeriodOut = StutterPeriod; } static void CalculateSwathAndDETConfiguration( diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn30/display_rq_dlg_calc_30.c b/drivers/gpu/drm/amd/display/dc/dml/dcn30/display_rq_dlg_calc_30.c index 5bb10f6e300d..416bf6fb67bd 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn30/display_rq_dlg_calc_30.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn30/display_rq_dlg_calc_30.c @@ -279,7 +279,7 @@ static bool CalculateBytePerPixelAnd256BBlockSizes( *BytePerPixelDETC = 0; *BytePerPixelY = 4; *BytePerPixelC = 0; - } else if (SourcePixelFormat == dm_444_16 || SourcePixelFormat == dm_444_16) { + } else if (SourcePixelFormat == dm_444_16) { *BytePerPixelDETY = 2; *BytePerPixelDETC = 0; *BytePerPixelY = 2; diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn30/display_rq_dlg_calc_30.h b/drivers/gpu/drm/amd/display/dc/dml/dcn30/display_rq_dlg_calc_30.h index e5b17e1104c6..c04965cceff3 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn30/display_rq_dlg_calc_30.h +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn30/display_rq_dlg_calc_30.h @@ -32,7 +32,7 @@ struct display_mode_lib; // Function: dml_rq_dlg_get_rq_reg // Main entry point for test to get the register values out of this DML class. -// This function calls <get_rq_param> and <extract_rq_regs> fucntions to calculate +// This function calls <get_rq_param> and <extract_rq_regs> functions to calculate // and then populate the rq_regs struct // Input: // pipe_param - pipe source configuration (e.g. vp, pitch, scaling, dest, etc.) diff --git a/drivers/gpu/drm/amd/display/dc/gpio/dce120/hw_factory_dce120.c b/drivers/gpu/drm/amd/display/dc/gpio/dce120/hw_factory_dce120.c index cf98aa827a9a..e883864cff3c 100644 --- a/drivers/gpu/drm/amd/display/dc/gpio/dce120/hw_factory_dce120.c +++ b/drivers/gpu/drm/amd/display/dc/gpio/dce120/hw_factory_dce120.c @@ -162,7 +162,7 @@ static void define_hpd_registers(struct hw_gpio_pin *pin, uint32_t en) } -/* fucntion table */ +/* function table */ static const struct hw_factory_funcs funcs = { .init_ddc_data = dal_hw_ddc_init, .init_generic = NULL, diff --git a/drivers/gpu/drm/amd/display/dc/gpio/dcn10/hw_factory_dcn10.c b/drivers/gpu/drm/amd/display/dc/gpio/dcn10/hw_factory_dcn10.c index b38c96c9fed3..7d36b56346a6 100644 --- a/drivers/gpu/drm/amd/display/dc/gpio/dcn10/hw_factory_dcn10.c +++ b/drivers/gpu/drm/amd/display/dc/gpio/dcn10/hw_factory_dcn10.c @@ -194,7 +194,7 @@ static void define_hpd_registers(struct hw_gpio_pin *pin, uint32_t en) } -/* fucntion table */ +/* function table */ static const struct hw_factory_funcs funcs = { .init_ddc_data = dal_hw_ddc_init, .init_generic = dal_hw_generic_init, diff --git a/drivers/gpu/drm/amd/display/dc/gpio/dcn20/hw_factory_dcn20.c b/drivers/gpu/drm/amd/display/dc/gpio/dcn20/hw_factory_dcn20.c index 83f798cb8b21..9b63c6c0cc84 100644 --- a/drivers/gpu/drm/amd/display/dc/gpio/dcn20/hw_factory_dcn20.c +++ b/drivers/gpu/drm/amd/display/dc/gpio/dcn20/hw_factory_dcn20.c @@ -221,7 +221,7 @@ static void define_generic_registers(struct hw_gpio_pin *pin, uint32_t en) generic->base.regs = &generic_regs[en].gpio; } -/* fucntion table */ +/* function table */ static const struct hw_factory_funcs funcs = { .init_ddc_data = dal_hw_ddc_init, .init_generic = dal_hw_generic_init, diff --git a/drivers/gpu/drm/amd/display/dc/gpio/dcn21/hw_factory_dcn21.c b/drivers/gpu/drm/amd/display/dc/gpio/dcn21/hw_factory_dcn21.c index 907c5911eb9e..2f57ee6deabc 100644 --- a/drivers/gpu/drm/amd/display/dc/gpio/dcn21/hw_factory_dcn21.c +++ b/drivers/gpu/drm/amd/display/dc/gpio/dcn21/hw_factory_dcn21.c @@ -202,7 +202,7 @@ static void define_hpd_registers(struct hw_gpio_pin *pin, uint32_t en) } -/* fucntion table */ +/* function table */ static const struct hw_factory_funcs funcs = { .init_ddc_data = dal_hw_ddc_init, .init_generic = dal_hw_generic_init, diff --git a/drivers/gpu/drm/amd/display/dc/gpio/dcn30/hw_factory_dcn30.c b/drivers/gpu/drm/amd/display/dc/gpio/dcn30/hw_factory_dcn30.c index 7e7fb6572107..21583699f992 100644 --- a/drivers/gpu/drm/amd/display/dc/gpio/dcn30/hw_factory_dcn30.c +++ b/drivers/gpu/drm/amd/display/dc/gpio/dcn30/hw_factory_dcn30.c @@ -117,6 +117,12 @@ static const struct ddc_registers ddc_data_regs_dcn[] = { ddc_data_regs_dcn2(4), ddc_data_regs_dcn2(5), ddc_data_regs_dcn2(6), + { + DDC_GPIO_VGA_REG_LIST(DATA), + .ddc_setup = 0, + .phy_aux_cntl = 0, + .dc_gpio_aux_ctrl_5 = 0 + } }; static const struct ddc_registers ddc_clk_regs_dcn[] = { @@ -126,6 +132,12 @@ static const struct ddc_registers ddc_clk_regs_dcn[] = { ddc_clk_regs_dcn2(4), ddc_clk_regs_dcn2(5), ddc_clk_regs_dcn2(6), + { + DDC_GPIO_VGA_REG_LIST(CLK), + .ddc_setup = 0, + .phy_aux_cntl = 0, + .dc_gpio_aux_ctrl_5 = 0 + } }; static const struct ddc_sh_mask ddc_shift[] = { @@ -218,7 +230,7 @@ static void define_hpd_registers(struct hw_gpio_pin *pin, uint32_t en) } -/* fucntion table */ +/* function table */ static const struct hw_factory_funcs funcs = { .init_ddc_data = dal_hw_ddc_init, .init_generic = dal_hw_generic_init, diff --git a/drivers/gpu/drm/amd/display/dc/gpio/gpio_base.c b/drivers/gpu/drm/amd/display/dc/gpio/gpio_base.c index f67c18375bfd..dac427b68fd7 100644 --- a/drivers/gpu/drm/amd/display/dc/gpio/gpio_base.c +++ b/drivers/gpu/drm/amd/display/dc/gpio/gpio_base.c @@ -63,13 +63,13 @@ enum gpio_result dal_gpio_open_ex( enum gpio_mode mode) { if (gpio->pin) { - ASSERT_CRITICAL(false); + BREAK_TO_DEBUGGER(); return GPIO_RESULT_ALREADY_OPENED; } // No action if allocation failed during gpio construct if (!gpio->hw_container.ddc) { - ASSERT_CRITICAL(false); + BREAK_TO_DEBUGGER(); return GPIO_RESULT_NON_SPECIFIC_ERROR; } gpio->mode = mode; diff --git a/drivers/gpu/drm/amd/display/dc/inc/core_types.h b/drivers/gpu/drm/amd/display/dc/inc/core_types.h index 329395ee7461..6e6bc66e49f0 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/core_types.h +++ b/drivers/gpu/drm/amd/display/dc/inc/core_types.h @@ -101,7 +101,7 @@ struct resource_funcs { struct dc *dc, struct dc_state *context, bool fast_validate); - void (*calculate_wm)( + void (*calculate_wm_and_dlg)( struct dc *dc, struct dc_state *context, display_e2e_pipe_params_st *pipes, int pipe_cnt, @@ -300,6 +300,7 @@ union pipe_update_flags { uint32_t gamut_remap : 1; uint32_t scaler : 1; uint32_t viewport : 1; + uint32_t plane_changed : 1; } bits; uint32_t raw; }; @@ -396,6 +397,7 @@ struct dc_state { struct dc_stream_state *streams[MAX_PIPES]; struct dc_stream_status stream_status[MAX_PIPES]; uint8_t stream_count; + uint8_t stream_mask; struct resource_context res_ctx; @@ -410,6 +412,10 @@ struct dc_state { struct clk_mgr *clk_mgr; struct kref refcount; + + struct { + unsigned int stutter_period_us; + } perf_params; }; #endif /* _CORE_TYPES_H_ */ diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/stream_encoder.h b/drivers/gpu/drm/amd/display/dc/inc/hw/stream_encoder.h index 11ce06e69d3f..0184cefb083b 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/hw/stream_encoder.h +++ b/drivers/gpu/drm/amd/display/dc/inc/hw/stream_encoder.h @@ -143,7 +143,7 @@ struct stream_encoder_funcs { struct stream_encoder *enc, struct dc_crtc_timing *crtc_timing); - void (*set_mst_bandwidth)( + void (*set_throttled_vcp_size)( struct stream_encoder *enc, struct fixed31_32 avg_time_slots_per_mtp); diff --git a/drivers/gpu/drm/amd/display/dc/os_types.h b/drivers/gpu/drm/amd/display/dc/os_types.h index 330acaaed79a..95cb56929e79 100644 --- a/drivers/gpu/drm/amd/display/dc/os_types.h +++ b/drivers/gpu/drm/amd/display/dc/os_types.h @@ -94,36 +94,27 @@ * general debug capabilities * */ -#if defined(CONFIG_HAVE_KGDB) || defined(CONFIG_KGDB) -#define ASSERT_CRITICAL(expr) do { \ - if (WARN_ON(!(expr))) { \ - kgdb_breakpoint(); \ - } \ -} while (0) +#ifdef CONFIG_DEBUG_KERNEL_DC +#define dc_breakpoint() kgdb_breakpoint() #else -#define ASSERT_CRITICAL(expr) do { \ - if (WARN_ON(!(expr))) { \ - ; \ - } \ -} while (0) +#define dc_breakpoint() do {} while (0) #endif -#if defined(CONFIG_DEBUG_KERNEL_DC) -#define ASSERT(expr) ASSERT_CRITICAL(expr) +#define ASSERT_CRITICAL(expr) do { \ + if (WARN_ON(!(expr))) \ + dc_breakpoint(); \ + } while (0) -#else -#define ASSERT(expr) WARN_ON_ONCE(!(expr)) -#endif +#define ASSERT(expr) do { \ + if (WARN_ON_ONCE(!(expr))) \ + dc_breakpoint(); \ + } while (0) -#if defined(CONFIG_DEBUG_KERNEL_DC) && (defined(CONFIG_HAVE_KGDB) || defined(CONFIG_KGDB)) #define BREAK_TO_DEBUGGER() \ do { \ DRM_DEBUG_DRIVER("%s():%d\n", __func__, __LINE__); \ - kgdb_breakpoint(); \ + dc_breakpoint(); \ } while (0) -#else -#define BREAK_TO_DEBUGGER() DRM_DEBUG_DRIVER("%s():%d\n", __func__, __LINE__) -#endif #define DC_ERR(...) do { \ dm_error(__VA_ARGS__); \ diff --git a/drivers/gpu/drm/amd/display/dc/virtual/virtual_stream_encoder.c b/drivers/gpu/drm/amd/display/dc/virtual/virtual_stream_encoder.c index 944c0327763c..1053b165c139 100644 --- a/drivers/gpu/drm/amd/display/dc/virtual/virtual_stream_encoder.c +++ b/drivers/gpu/drm/amd/display/dc/virtual/virtual_stream_encoder.c @@ -46,9 +46,10 @@ static void virtual_stream_encoder_dvi_set_stream_attribute( struct dc_crtc_timing *crtc_timing, bool is_dual_link) {} -static void virtual_stream_encoder_set_mst_bandwidth( +static void virtual_stream_encoder_set_throttled_vcp_size( struct stream_encoder *enc, - struct fixed31_32 avg_time_slots_per_mtp) {} + struct fixed31_32 avg_time_slots_per_mtp) +{} static void virtual_stream_encoder_update_hdmi_info_packets( struct stream_encoder *enc, @@ -98,6 +99,12 @@ static void virtual_setup_stereo_sync( bool enable) {} +static void virtual_stream_encoder_set_dsc_pps_info_packet( + struct stream_encoder *enc, + bool enable, + uint8_t *dsc_packed_pps) +{} + static const struct stream_encoder_funcs virtual_str_enc_funcs = { .dp_set_odm_combine = virtual_enc_dp_set_odm_combine, @@ -107,8 +114,8 @@ static const struct stream_encoder_funcs virtual_str_enc_funcs = { virtual_stream_encoder_hdmi_set_stream_attribute, .dvi_set_stream_attribute = virtual_stream_encoder_dvi_set_stream_attribute, - .set_mst_bandwidth = - virtual_stream_encoder_set_mst_bandwidth, + .set_throttled_vcp_size = + virtual_stream_encoder_set_throttled_vcp_size, .update_hdmi_info_packets = virtual_stream_encoder_update_hdmi_info_packets, .stop_hdmi_info_packets = @@ -127,6 +134,7 @@ static const struct stream_encoder_funcs virtual_str_enc_funcs = { .hdmi_reset_stream_attribute = virtual_stream_encoder_reset_hdmi_stream_attribute, .dig_connect_to_otg = virtual_dig_connect_to_otg, .setup_stereo_sync = virtual_setup_stereo_sync, + .dp_set_dsc_pps_info_packet = virtual_stream_encoder_set_dsc_pps_info_packet, }; bool virtual_stream_encoder_construct( diff --git a/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h b/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h index d7e7f2eda92f..d103ec1eaa73 100644 --- a/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h +++ b/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h @@ -36,10 +36,10 @@ /* Firmware versioning. */ #ifdef DMUB_EXPOSE_VERSION -#define DMUB_FW_VERSION_GIT_HASH 0x4e5b2f46f +#define DMUB_FW_VERSION_GIT_HASH 0x9cf8f05fe #define DMUB_FW_VERSION_MAJOR 0 #define DMUB_FW_VERSION_MINOR 0 -#define DMUB_FW_VERSION_REVISION 29 +#define DMUB_FW_VERSION_REVISION 35 #define DMUB_FW_VERSION_TEST 0 #define DMUB_FW_VERSION_VBIOS 0 #define DMUB_FW_VERSION_HOTFIX 0 @@ -57,6 +57,7 @@ #define SET_ABM_PIPE_GRADUALLY_DISABLE 0 #define SET_ABM_PIPE_IMMEDIATELY_DISABLE 255 +#define SET_ABM_PIPE_IMMEDIATE_KEEP_GAIN_DISABLE 254 #define SET_ABM_PIPE_NORMAL 1 /* Maximum number of streams on any ASIC. */ @@ -69,10 +70,6 @@ #define PHYSICAL_ADDRESS_LOC union large_integer #endif -#if defined(__cplusplus) -extern "C" { -#endif - #ifndef dmub_memcpy #define dmub_memcpy(dest, source, bytes) memcpy((dest), (source), (bytes)) #endif @@ -81,6 +78,10 @@ extern "C" { #define dmub_memset(dest, val, bytes) memset((dest), (val), (bytes)) #endif +#if defined(__cplusplus) +extern "C" { +#endif + #ifndef dmub_udelay #define dmub_udelay(microseconds) udelay(microseconds) #endif @@ -97,6 +98,7 @@ union dmub_psr_debug_flags { struct { uint32_t visual_confirm : 1; uint32_t use_hw_lock_mgr : 1; + uint32_t log_line_nums : 1; } bitfields; uint32_t u32All; @@ -169,7 +171,7 @@ union dmub_fw_boot_status { uint32_t dal_fw : 1; uint32_t mailbox_rdy : 1; uint32_t optimized_init_done : 1; - uint32_t reserved : 29; + uint32_t restore_required : 1; } bits; uint32_t all; }; @@ -178,6 +180,7 @@ enum dmub_fw_boot_status_bit { DMUB_FW_BOOT_STATUS_BIT_DAL_FIRMWARE = (1 << 0), DMUB_FW_BOOT_STATUS_BIT_MAILBOX_READY = (1 << 1), DMUB_FW_BOOT_STATUS_BIT_OPTIMIZED_INIT_DONE = (1 << 2), + DMUB_FW_BOOT_STATUS_BIT_RESTORE_REQUIRED = (1 << 3), }; /* Register bit definition for SCRATCH15 */ @@ -297,9 +300,17 @@ enum dmub_cmd_type { DMUB_CMD__PSR = 64, DMUB_CMD__ABM = 66, DMUB_CMD__HW_LOCK = 69, + DMUB_CMD__DP_AUX_ACCESS = 70, + DMUB_CMD__OUTBOX1_ENABLE = 71, DMUB_CMD__VBIOS = 128, }; +enum dmub_out_cmd_type { + DMUB_OUT_CMD__NULL = 0, + DMUB_OUT_CMD__DP_AUX_REPLY = 1, + DMUB_OUT_CMD__DP_HPD_NOTIFY = 2, +}; + #pragma pack(push, 1) struct dmub_cmd_header { @@ -455,6 +466,78 @@ struct dmub_rb_cmd_dpphy_init { uint8_t reserved[60]; }; +enum dp_aux_request_action { + DP_AUX_REQ_ACTION_I2C_WRITE = 0x00, + DP_AUX_REQ_ACTION_I2C_READ = 0x10, + DP_AUX_REQ_ACTION_I2C_STATUS_REQ = 0x20, + DP_AUX_REQ_ACTION_I2C_WRITE_MOT = 0x40, + DP_AUX_REQ_ACTION_I2C_READ_MOT = 0x50, + DP_AUX_REQ_ACTION_I2C_STATUS_REQ_MOT = 0x60, + DP_AUX_REQ_ACTION_DPCD_WRITE = 0x80, + DP_AUX_REQ_ACTION_DPCD_READ = 0x90 +}; + +/* DP AUX command */ +struct aux_transaction_parameters { + uint8_t is_i2c_over_aux; + uint8_t action; + uint8_t length; + uint8_t pad; + uint32_t address; + uint8_t data[16]; +}; + +struct dmub_cmd_dp_aux_control_data { + uint32_t handle; + uint8_t port_index; + uint8_t sw_crc_enabled; + uint16_t timeout; + struct aux_transaction_parameters dpaux; +}; + +struct dmub_rb_cmd_dp_aux_access { + struct dmub_cmd_header header; + struct dmub_cmd_dp_aux_control_data aux_control; +}; + +struct dmub_rb_cmd_outbox1_enable { + struct dmub_cmd_header header; + uint32_t enable; +}; + +/* DP AUX Reply command - OutBox Cmd */ +struct aux_reply_data { + uint8_t command; + uint8_t length; + uint8_t pad[2]; + uint8_t data[16]; +}; + +struct aux_reply_control_data { + uint32_t handle; + uint8_t phy_port_index; + uint8_t result; + uint16_t pad; +}; + +struct dmub_rb_cmd_dp_aux_reply { + struct dmub_cmd_header header; + struct aux_reply_control_data control; + struct aux_reply_data reply_data; +}; + +struct dp_hpd_data { + uint8_t phy_port_index; + uint8_t hpd_type; + uint8_t hpd_status; + uint8_t pad; +}; + +struct dmub_rb_cmd_dp_hpd_notify { + struct dmub_cmd_header header; + struct dp_hpd_data hpd_data; +}; + /* * Command IDs should be treated as stable ABI. * Do not reuse or modify IDs. @@ -684,8 +767,15 @@ union dmub_rb_cmd { struct dmub_rb_cmd_abm_set_ambient_level abm_set_ambient_level; struct dmub_rb_cmd_abm_set_pwm_frac abm_set_pwm_frac; struct dmub_rb_cmd_abm_init_config abm_init_config; + struct dmub_rb_cmd_dp_aux_access dp_aux_access; + struct dmub_rb_cmd_outbox1_enable outbox1_enable; }; +union dmub_rb_out_cmd { + struct dmub_rb_cmd_common cmd_common; + struct dmub_rb_cmd_dp_aux_reply dp_aux_reply; + struct dmub_rb_cmd_dp_hpd_notify dp_hpd_notify; +}; #pragma pack(pop) @@ -758,6 +848,25 @@ static inline bool dmub_rb_push_front(struct dmub_rb *rb, return true; } +static inline bool dmub_rb_out_push_front(struct dmub_rb *rb, + const union dmub_rb_out_cmd *cmd) +{ + uint8_t *dst = (uint8_t *)(rb->base_address) + rb->wrpt; + const uint8_t *src = (uint8_t *)cmd; + + if (dmub_rb_full(rb)) + return false; + + dmub_memcpy(dst, src, DMUB_RB_CMD_SIZE); + + rb->wrpt += DMUB_RB_CMD_SIZE; + + if (rb->wrpt >= rb->capacity) + rb->wrpt %= rb->capacity; + + return true; +} + static inline bool dmub_rb_front(struct dmub_rb *rb, union dmub_rb_cmd *cmd) { @@ -771,6 +880,23 @@ static inline bool dmub_rb_front(struct dmub_rb *rb, return true; } +static inline bool dmub_rb_out_front(struct dmub_rb *rb, + union dmub_rb_out_cmd *cmd) +{ + const uint64_t volatile *src = (const uint64_t volatile *)(rb->base_address) + rb->rptr / sizeof(uint64_t); + uint64_t *dst = (uint64_t *)cmd; + int i; + + if (dmub_rb_empty(rb)) + return false; + + // copying data + for (i = 0; i < DMUB_RB_CMD_SIZE / sizeof(uint64_t); i++) + *dst++ = *src++; + + return true; +} + static inline bool dmub_rb_pop_front(struct dmub_rb *rb) { if (dmub_rb_empty(rb)) @@ -791,12 +917,10 @@ static inline void dmub_rb_flush_pending(const struct dmub_rb *rb) while (rptr != wptr) { uint64_t volatile *data = (uint64_t volatile *)rb->base_address + rptr / sizeof(uint64_t); - //uint64_t volatile *p = (uint64_t volatile *)data; - uint64_t temp; int i; for (i = 0; i < DMUB_RB_CMD_SIZE / sizeof(uint64_t); i++) - temp = *data++; + *data++; rptr += DMUB_RB_CMD_SIZE; if (rptr >= rb->capacity) diff --git a/drivers/gpu/drm/amd/display/include/bios_parser_types.h b/drivers/gpu/drm/amd/display/include/bios_parser_types.h index 21011edea337..7c782924c941 100644 --- a/drivers/gpu/drm/amd/display/include/bios_parser_types.h +++ b/drivers/gpu/drm/amd/display/include/bios_parser_types.h @@ -318,4 +318,10 @@ struct bp_encoder_cap_info { uint32_t RESERVED:27; }; +struct bp_soc_bb_info { + uint32_t dram_clock_change_latency_100ns; + uint32_t dram_sr_exit_latency_100ns; + uint32_t dram_sr_enter_exit_latency_100ns; +}; + #endif /*__DAL_BIOS_PARSER_TYPES_H__ */ diff --git a/drivers/gpu/drm/amd/display/include/link_service_types.h b/drivers/gpu/drm/amd/display/include/link_service_types.h index 550f46e9b95f..7392a89e771f 100644 --- a/drivers/gpu/drm/amd/display/include/link_service_types.h +++ b/drivers/gpu/drm/amd/display/include/link_service_types.h @@ -80,6 +80,7 @@ struct link_training_settings { uint16_t cr_pattern_time; uint16_t eq_pattern_time; + enum dc_dp_training_pattern pattern_for_cr; enum dc_dp_training_pattern pattern_for_eq; bool enhanced_framing; diff --git a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp.c b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp.c index e9fbd94f8635..20e554e771d1 100644 --- a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp.c +++ b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp.c @@ -470,6 +470,14 @@ enum mod_hdcp_status mod_hdcp_process_event(struct mod_hdcp *hdcp, if (reset_status != MOD_HDCP_STATUS_SUCCESS) push_error_status(hdcp, reset_status); } + + /* Clear CP_IRQ status if needed */ + if (event_ctx.event == MOD_HDCP_EVENT_CPIRQ) { + status = mod_hdcp_clear_cp_irq_status(hdcp); + if (status != MOD_HDCP_STATUS_SUCCESS) + push_error_status(hdcp, status); + } + return status; } diff --git a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp.h b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp.h index b0cefed2eb02..6c678cfb82e3 100644 --- a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp.h +++ b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp.h @@ -386,6 +386,7 @@ enum mod_hdcp_status mod_hdcp_write_eks(struct mod_hdcp *hdcp); enum mod_hdcp_status mod_hdcp_write_repeater_auth_ack(struct mod_hdcp *hdcp); enum mod_hdcp_status mod_hdcp_write_stream_manage(struct mod_hdcp *hdcp); enum mod_hdcp_status mod_hdcp_write_content_type(struct mod_hdcp *hdcp); +enum mod_hdcp_status mod_hdcp_clear_cp_irq_status(struct mod_hdcp *hdcp); /* hdcp version helpers */ static inline uint8_t is_dp_hdcp(struct mod_hdcp *hdcp) diff --git a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_ddc.c b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_ddc.c index bb5130f4228d..f7b5583ee609 100644 --- a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_ddc.c +++ b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_ddc.c @@ -30,6 +30,8 @@ #define KSV_READ_SIZE 0xf /* 0x6803b - 0x6802c */ #define HDCP_MAX_AUX_TRANSACTION_SIZE 16 +#define DP_CP_IRQ (1 << 2) + enum mod_hdcp_ddc_message_id { MOD_HDCP_MESSAGE_ID_INVALID = -1, @@ -645,3 +647,18 @@ enum mod_hdcp_status mod_hdcp_write_content_type(struct mod_hdcp *hdcp) status = MOD_HDCP_STATUS_INVALID_OPERATION; return status; } + +enum mod_hdcp_status mod_hdcp_clear_cp_irq_status(struct mod_hdcp *hdcp) +{ + uint8_t clear_cp_irq_bit = DP_CP_IRQ; + uint32_t size = 1; + + if (is_dp_hdcp(hdcp)) { + uint32_t cp_irq_addrs = (hdcp->connection.link.dp.rev >= 0x14) + ? DP_DEVICE_SERVICE_IRQ_VECTOR_ESI0:DP_DEVICE_SERVICE_IRQ_VECTOR; + return hdcp->config.ddc.funcs.write_dpcd(hdcp->config.ddc.handle, cp_irq_addrs, + &clear_cp_irq_bit, size) ? MOD_HDCP_STATUS_SUCCESS : MOD_HDCP_STATUS_DDC_FAILURE; + } + + return MOD_HDCP_STATUS_INVALID_OPERATION; +} diff --git a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_log.h b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_log.h index d3192b9d0c3d..47f8ee2832ff 100644 --- a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_log.h +++ b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_log.h @@ -27,7 +27,7 @@ #define MOD_HDCP_LOG_H_ #ifdef CONFIG_DRM_AMD_DC_HDCP -#define HDCP_LOG_ERR(hdcp, ...) DRM_WARN(__VA_ARGS__) +#define HDCP_LOG_ERR(hdcp, ...) DRM_DEBUG_KMS(__VA_ARGS__) #define HDCP_LOG_VER(hdcp, ...) DRM_DEBUG_KMS(__VA_ARGS__) #define HDCP_LOG_FSM(hdcp, ...) DRM_DEBUG_KMS(__VA_ARGS__) #define HDCP_LOG_TOP(hdcp, ...) pr_debug("[HDCP_TOP]:"__VA_ARGS__) diff --git a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_psp.c b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_psp.c index fb1161dd7ea8..3a367a5968ae 100644 --- a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_psp.c +++ b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_psp.c @@ -88,7 +88,7 @@ enum mod_hdcp_status mod_hdcp_add_display_to_topology(struct mod_hdcp *hdcp, enum mod_hdcp_status status = MOD_HDCP_STATUS_SUCCESS; if (!psp->dtm_context.dtm_initialized) { - DRM_ERROR("Failed to add display topology, DTM TA is not initialized."); + DRM_INFO("Failed to add display topology, DTM TA is not initialized."); display->state = MOD_HDCP_DISPLAY_INACTIVE; return MOD_HDCP_STATUS_FAILURE; } diff --git a/drivers/gpu/drm/amd/include/amd_shared.h b/drivers/gpu/drm/amd/include/amd_shared.h index e98c84ef206f..10dc481ecbc4 100644 --- a/drivers/gpu/drm/amd/include/amd_shared.h +++ b/drivers/gpu/drm/amd/include/amd_shared.h @@ -47,6 +47,40 @@ enum amd_apu_flags { AMD_APU_IS_RENOIR = 0x00000008UL, }; +/** +* DOC: IP Blocks +* +* GPUs are composed of IP (intellectual property) blocks. These +* IP blocks provide various functionalities: display, graphics, +* video decode, etc. The IP blocks that comprise a particular GPU +* are listed in the GPU's respective SoC file. amdgpu_device.c +* acquires the list of IP blocks for the GPU in use on initialization. +* It can then operate on this list to perform standard driver operations +* such as: init, fini, suspend, resume, etc. +* +* +* IP block implementations are named using the following convention: +* <functionality>_v<version> (E.g.: gfx_v6_0). +*/ + +/** +* enum amd_ip_block_type - Used to classify IP blocks by functionality. +* +* @AMD_IP_BLOCK_TYPE_COMMON: GPU Family +* @AMD_IP_BLOCK_TYPE_GMC: Graphics Memory Controller +* @AMD_IP_BLOCK_TYPE_IH: Interrupt Handler +* @AMD_IP_BLOCK_TYPE_SMC: System Management Controller +* @AMD_IP_BLOCK_TYPE_PSP: Platform Security Processor +* @AMD_IP_BLOCK_TYPE_DCE: Display and Compositing Engine +* @AMD_IP_BLOCK_TYPE_GFX: Graphics and Compute Engine +* @AMD_IP_BLOCK_TYPE_SDMA: System DMA Engine +* @AMD_IP_BLOCK_TYPE_UVD: Unified Video Decoder +* @AMD_IP_BLOCK_TYPE_VCE: Video Compression Engine +* @AMD_IP_BLOCK_TYPE_ACP: Audio Co-Processor +* @AMD_IP_BLOCK_TYPE_VCN: Video Core/Codec Next +* @AMD_IP_BLOCK_TYPE_MES: Micro-Engine Scheduler +* @AMD_IP_BLOCK_TYPE_JPEG: JPEG Engine +*/ enum amd_ip_block_type { AMD_IP_BLOCK_TYPE_COMMON, AMD_IP_BLOCK_TYPE_GMC, @@ -128,6 +162,34 @@ enum amd_powergating_state { #define AMD_PG_SUPPORT_ATHUB (1 << 16) #define AMD_PG_SUPPORT_JPEG (1 << 17) +/** + * enum PP_FEATURE_MASK - Used to mask power play features. + * + * @PP_SCLK_DPM_MASK: Dynamic adjustment of the system (graphics) clock. + * @PP_MCLK_DPM_MASK: Dynamic adjustment of the memory clock. + * @PP_PCIE_DPM_MASK: Dynamic adjustment of PCIE clocks and lanes. + * @PP_SCLK_DEEP_SLEEP_MASK: System (graphics) clock deep sleep. + * @PP_POWER_CONTAINMENT_MASK: Power containment. + * @PP_UVD_HANDSHAKE_MASK: Unified video decoder handshake. + * @PP_SMC_VOLTAGE_CONTROL_MASK: Dynamic voltage control. + * @PP_VBI_TIME_SUPPORT_MASK: Vertical blank interval support. + * @PP_ULV_MASK: Ultra low voltage. + * @PP_ENABLE_GFX_CG_THRU_SMU: SMU control of GFX engine clockgating. + * @PP_CLOCK_STRETCH_MASK: Clock stretching. + * @PP_OD_FUZZY_FAN_CONTROL_MASK: Overdrive fuzzy fan control. + * @PP_SOCCLK_DPM_MASK: Dynamic adjustment of the SoC clock. + * @PP_DCEFCLK_DPM_MASK: Dynamic adjustment of the Display Controller Engine Fabric clock. + * @PP_OVERDRIVE_MASK: Over- and under-clocking support. + * @PP_GFXOFF_MASK: Dynamic graphics engine power control. + * @PP_ACG_MASK: Adaptive clock generator. + * @PP_STUTTER_MODE: Stutter mode. + * @PP_AVFS_MASK: Adaptive voltage and frequency scaling. + * + * To override these settings on boot, append amdgpu.ppfeaturemask=<mask> to + * the kernel's command line parameters. This is usually done through a system's + * boot loader (E.g. GRUB). If manually loading the driver, pass + * ppfeaturemask=<mask> as a modprobe parameter. + */ enum PP_FEATURE_MASK { PP_SCLK_DPM_MASK = 0x1, PP_MCLK_DPM_MASK = 0x2, @@ -165,56 +227,59 @@ enum DC_DEBUG_MASK { }; enum amd_dpm_forced_level; + /** * struct amd_ip_funcs - general hooks for managing amdgpu IP Blocks + * @name: Name of IP block + * @early_init: sets up early driver state (pre sw_init), + * does not configure hw - Optional + * @late_init: sets up late driver/hw state (post hw_init) - Optional + * @sw_init: sets up driver state, does not configure hw + * @sw_fini: tears down driver state, does not configure hw + * @hw_init: sets up the hw state + * @hw_fini: tears down the hw state + * @late_fini: final cleanup + * @suspend: handles IP specific hw/sw changes for suspend + * @resume: handles IP specific hw/sw changes for resume + * @is_idle: returns current IP block idle status + * @wait_for_idle: poll for idle + * @check_soft_reset: check soft reset the IP block + * @pre_soft_reset: pre soft reset the IP block + * @soft_reset: soft reset the IP block + * @post_soft_reset: post soft reset the IP block + * @set_clockgating_state: enable/disable cg for the IP block + * @set_powergating_state: enable/disable pg for the IP block + * @get_clockgating_state: get current clockgating status + * @enable_umd_pstate: enable UMD powerstate + * + * These hooks provide an interface for controlling the operational state + * of IP blocks. After acquiring a list of IP blocks for the GPU in use, + * the driver can make chip-wide state changes by walking this list and + * making calls to hooks from each IP block. This list is ordered to ensure + * that the driver initializes the IP blocks in a safe sequence. */ struct amd_ip_funcs { - /** @name: Name of IP block */ char *name; - /** - * @early_init: - * - * sets up early driver state (pre sw_init), - * does not configure hw - Optional - */ int (*early_init)(void *handle); - /** @late_init: sets up late driver/hw state (post hw_init) - Optional */ int (*late_init)(void *handle); - /** @sw_init: sets up driver state, does not configure hw */ int (*sw_init)(void *handle); - /** @sw_fini: tears down driver state, does not configure hw */ int (*sw_fini)(void *handle); - /** @hw_init: sets up the hw state */ int (*hw_init)(void *handle); - /** @hw_fini: tears down the hw state */ int (*hw_fini)(void *handle); - /** @late_fini: final cleanup */ void (*late_fini)(void *handle); - /** @suspend: handles IP specific hw/sw changes for suspend */ int (*suspend)(void *handle); - /** @resume: handles IP specific hw/sw changes for resume */ int (*resume)(void *handle); - /** @is_idle: returns current IP block idle status */ bool (*is_idle)(void *handle); - /** @wait_for_idle: poll for idle */ int (*wait_for_idle)(void *handle); - /** @check_soft_reset: check soft reset the IP block */ bool (*check_soft_reset)(void *handle); - /** @pre_soft_reset: pre soft reset the IP block */ int (*pre_soft_reset)(void *handle); - /** @soft_reset: soft reset the IP block */ int (*soft_reset)(void *handle); - /** @post_soft_reset: post soft reset the IP block */ int (*post_soft_reset)(void *handle); - /** @set_clockgating_state: enable/disable cg for the IP block */ int (*set_clockgating_state)(void *handle, enum amd_clockgating_state state); - /** @set_powergating_state: enable/disable pg for the IP block */ int (*set_powergating_state)(void *handle, enum amd_powergating_state state); - /** @get_clockgating_state: get current clockgating status */ void (*get_clockgating_state)(void *handle, u32 *flags); - /** @enable_umd_pstate: enable UMD powerstate */ int (*enable_umd_pstate)(void *handle, enum amd_dpm_forced_level *level); }; diff --git a/drivers/gpu/drm/amd/include/asic_reg/gc/gc_10_3_0_default.h b/drivers/gpu/drm/amd/include/asic_reg/gc/gc_10_3_0_default.h index 1116779252e6..e245e912535e 100644 --- a/drivers/gpu/drm/amd/include/asic_reg/gc/gc_10_3_0_default.h +++ b/drivers/gpu/drm/amd/include/asic_reg/gc/gc_10_3_0_default.h @@ -2727,6 +2727,7 @@ #define mmDB_STENCIL_WRITE_BASE_DEFAULT 0x00000000 #define mmDB_RESERVED_REG_1_DEFAULT 0x00000000 #define mmDB_RESERVED_REG_3_DEFAULT 0x00000000 +#define mmDB_VRS_OVERRIDE_CNTL_DEFAULT 0x00000000 #define mmDB_Z_READ_BASE_HI_DEFAULT 0x00000000 #define mmDB_STENCIL_READ_BASE_HI_DEFAULT 0x00000000 #define mmDB_Z_WRITE_BASE_HI_DEFAULT 0x00000000 @@ -3062,6 +3063,7 @@ #define mmPA_SU_OVER_RASTERIZATION_CNTL_DEFAULT 0x00000000 #define mmPA_STEREO_CNTL_DEFAULT 0x00000000 #define mmPA_STATE_STEREO_X_DEFAULT 0x00000000 +#define mmPA_CL_VRS_CNTL_DEFAULT 0x00000000 #define mmPA_SU_POINT_SIZE_DEFAULT 0x00000000 #define mmPA_SU_POINT_MINMAX_DEFAULT 0x00000000 #define mmPA_SU_LINE_CNTL_DEFAULT 0x00000000 diff --git a/drivers/gpu/drm/amd/include/asic_reg/gc/gc_10_3_0_offset.h b/drivers/gpu/drm/amd/include/asic_reg/gc/gc_10_3_0_offset.h index cbaad7d83194..66a4151fa676 100644 --- a/drivers/gpu/drm/amd/include/asic_reg/gc/gc_10_3_0_offset.h +++ b/drivers/gpu/drm/amd/include/asic_reg/gc/gc_10_3_0_offset.h @@ -5379,6 +5379,8 @@ #define mmDB_RESERVED_REG_1_BASE_IDX 1 #define mmDB_RESERVED_REG_3 0x0017 #define mmDB_RESERVED_REG_3_BASE_IDX 1 +#define mmDB_VRS_OVERRIDE_CNTL 0x0019 +#define mmDB_VRS_OVERRIDE_CNTL_BASE_IDX 1 #define mmDB_Z_READ_BASE_HI 0x001a #define mmDB_Z_READ_BASE_HI_BASE_IDX 1 #define mmDB_STENCIL_READ_BASE_HI 0x001b @@ -6049,6 +6051,8 @@ #define mmPA_STEREO_CNTL_BASE_IDX 1 #define mmPA_STATE_STEREO_X 0x0211 #define mmPA_STATE_STEREO_X_BASE_IDX 1 +#define mmPA_CL_VRS_CNTL 0x0212 +#define mmPA_CL_VRS_CNTL_BASE_IDX 1 #define mmPA_SU_POINT_SIZE 0x0280 #define mmPA_SU_POINT_SIZE_BASE_IDX 1 #define mmPA_SU_POINT_MINMAX 0x0281 diff --git a/drivers/gpu/drm/amd/include/asic_reg/gc/gc_10_3_0_sh_mask.h b/drivers/gpu/drm/amd/include/asic_reg/gc/gc_10_3_0_sh_mask.h index c2d035ef3e94..aed799d9a0e8 100644 --- a/drivers/gpu/drm/amd/include/asic_reg/gc/gc_10_3_0_sh_mask.h +++ b/drivers/gpu/drm/amd/include/asic_reg/gc/gc_10_3_0_sh_mask.h @@ -9777,6 +9777,7 @@ #define DB_EXCEPTION_CONTROL__AUTO_FLUSH_HTILE__SHIFT 0x3 #define DB_EXCEPTION_CONTROL__AUTO_FLUSH_QUAD__SHIFT 0x4 #define DB_EXCEPTION_CONTROL__FORCE_SUMMARIZE__SHIFT 0x8 +#define DB_EXCEPTION_CONTROL__FORCE_VRS_RATE_FINE__SHIFT 0x10 #define DB_EXCEPTION_CONTROL__DTAG_WATERMARK__SHIFT 0x18 #define DB_EXCEPTION_CONTROL__EARLY_Z_PANIC_DISABLE_MASK 0x00000001L #define DB_EXCEPTION_CONTROL__LATE_Z_PANIC_DISABLE_MASK 0x00000002L @@ -9784,6 +9785,7 @@ #define DB_EXCEPTION_CONTROL__AUTO_FLUSH_HTILE_MASK 0x00000008L #define DB_EXCEPTION_CONTROL__AUTO_FLUSH_QUAD_MASK 0x00000010L #define DB_EXCEPTION_CONTROL__FORCE_SUMMARIZE_MASK 0x00000F00L +#define DB_EXCEPTION_CONTROL__FORCE_VRS_RATE_FINE_MASK 0x00FF0000L #define DB_EXCEPTION_CONTROL__DTAG_WATERMARK_MASK 0x7F000000L //DB_DFSM_CONFIG #define DB_DFSM_CONFIG__BYPASS_DFSM__SHIFT 0x0 @@ -10076,6 +10078,7 @@ #define CB_HW_CONTROL_3__DISABLE_NACK_PROCESSING_CM__SHIFT 0x18 #define CB_HW_CONTROL_3__DISABLE_NACK_COLOR_RD_WR_OPT__SHIFT 0x19 #define CB_HW_CONTROL_3__DISABLE_BLENDER_CLOCK_GATING__SHIFT 0x1a +#define CB_HW_CONTROL_3__DISABLE_DCC_VRS_OPT__SHIFT 0x1c #define CB_HW_CONTROL_3__DISABLE_FMASK_NOFETCH_OPT__SHIFT 0x1e #define CB_HW_CONTROL_3__DISABLE_FMASK_NOFETCH_OPT_BC__SHIFT 0x1f #define CB_HW_CONTROL_3__DISABLE_SLOW_MODE_EMPTY_HALF_QUAD_KILL_MASK 0x00000001L @@ -10103,12 +10106,15 @@ #define CB_HW_CONTROL_3__DISABLE_NACK_PROCESSING_CM_MASK 0x01000000L #define CB_HW_CONTROL_3__DISABLE_NACK_COLOR_RD_WR_OPT_MASK 0x02000000L #define CB_HW_CONTROL_3__DISABLE_BLENDER_CLOCK_GATING_MASK 0x04000000L +#define CB_HW_CONTROL_3__DISABLE_DCC_VRS_OPT_MASK 0x10000000L #define CB_HW_CONTROL_3__DISABLE_FMASK_NOFETCH_OPT_MASK 0x40000000L #define CB_HW_CONTROL_3__DISABLE_FMASK_NOFETCH_OPT_BC_MASK 0x80000000L //CB_HW_CONTROL #define CB_HW_CONTROL__ALLOW_MRT_WITH_DUAL_SOURCE__SHIFT 0x0 +#define CB_HW_CONTROL__DISABLE_VRS_FILLRATE_OPTIMIZATION__SHIFT 0x1 #define CB_HW_CONTROL__DISABLE_FILLRATE_OPT_FIX_WITH_CFC__SHIFT 0x3 #define CB_HW_CONTROL__DISABLE_POST_DCC_WITH_CFC_FIX__SHIFT 0x4 +#define CB_HW_CONTROL__DISABLE_COMPRESS_1FRAG_WHEN_VRS_RATE_HINT_EN__SHIFT 0x5 #define CB_HW_CONTROL__RMI_CREDITS__SHIFT 0x6 #define CB_HW_CONTROL__CHICKEN_BITS__SHIFT 0xc #define CB_HW_CONTROL__DISABLE_FMASK_MULTI_MGCG_DOMAINS__SHIFT 0xf @@ -10129,8 +10135,10 @@ #define CB_HW_CONTROL__DISABLE_CC_IB_SERIALIZER_STATE_OPT__SHIFT 0x1e #define CB_HW_CONTROL__DISABLE_PIXEL_IN_QUAD_FIX_FOR_LINEAR_SURFACE__SHIFT 0x1f #define CB_HW_CONTROL__ALLOW_MRT_WITH_DUAL_SOURCE_MASK 0x00000001L +#define CB_HW_CONTROL__DISABLE_VRS_FILLRATE_OPTIMIZATION_MASK 0x00000002L #define CB_HW_CONTROL__DISABLE_FILLRATE_OPT_FIX_WITH_CFC_MASK 0x00000008L #define CB_HW_CONTROL__DISABLE_POST_DCC_WITH_CFC_FIX_MASK 0x00000010L +#define CB_HW_CONTROL__DISABLE_COMPRESS_1FRAG_WHEN_VRS_RATE_HINT_EN_MASK 0x00000020L #define CB_HW_CONTROL__RMI_CREDITS_MASK 0x00000FC0L #define CB_HW_CONTROL__CHICKEN_BITS_MASK 0x00007000L #define CB_HW_CONTROL__DISABLE_FMASK_MULTI_MGCG_DOMAINS_MASK 0x00008000L @@ -19881,6 +19889,7 @@ #define DB_RENDER_OVERRIDE2__PRESERVE_SRESULTS__SHIFT 0x16 #define DB_RENDER_OVERRIDE2__DISABLE_FAST_PASS__SHIFT 0x17 #define DB_RENDER_OVERRIDE2__ALLOW_PARTIAL_RES_HIER_KILL__SHIFT 0x19 +#define DB_RENDER_OVERRIDE2__FORCE_VRS_RATE_FINE__SHIFT 0x1a #define DB_RENDER_OVERRIDE2__CENTROID_COMPUTATION_MODE__SHIFT 0x1b #define DB_RENDER_OVERRIDE2__PARTIAL_SQUAD_LAUNCH_CONTROL_MASK 0x00000003L #define DB_RENDER_OVERRIDE2__PARTIAL_SQUAD_LAUNCH_COUNTDOWN_MASK 0x0000001CL @@ -19898,6 +19907,7 @@ #define DB_RENDER_OVERRIDE2__PRESERVE_SRESULTS_MASK 0x00400000L #define DB_RENDER_OVERRIDE2__DISABLE_FAST_PASS_MASK 0x00800000L #define DB_RENDER_OVERRIDE2__ALLOW_PARTIAL_RES_HIER_KILL_MASK 0x02000000L +#define DB_RENDER_OVERRIDE2__FORCE_VRS_RATE_FINE_MASK 0x04000000L #define DB_RENDER_OVERRIDE2__CENTROID_COMPUTATION_MODE_MASK 0x18000000L //DB_HTILE_DATA_BASE #define DB_HTILE_DATA_BASE__BASE_256B__SHIFT 0x0 @@ -20021,6 +20031,13 @@ //DB_RESERVED_REG_3 #define DB_RESERVED_REG_3__FIELD_1__SHIFT 0x0 #define DB_RESERVED_REG_3__FIELD_1_MASK 0x003FFFFFL +//DB_VRS_OVERRIDE_CNTL +#define DB_VRS_OVERRIDE_CNTL__VRS_OVERRIDE_RATE_COMBINER_MODE__SHIFT 0x0 +#define DB_VRS_OVERRIDE_CNTL__VRS_OVERRIDE_RATE_X__SHIFT 0x4 +#define DB_VRS_OVERRIDE_CNTL__VRS_OVERRIDE_RATE_Y__SHIFT 0x6 +#define DB_VRS_OVERRIDE_CNTL__VRS_OVERRIDE_RATE_COMBINER_MODE_MASK 0x00000007L +#define DB_VRS_OVERRIDE_CNTL__VRS_OVERRIDE_RATE_X_MASK 0x00000030L +#define DB_VRS_OVERRIDE_CNTL__VRS_OVERRIDE_RATE_Y_MASK 0x000000C0L //DB_Z_READ_BASE_HI #define DB_Z_READ_BASE_HI__BASE_HI__SHIFT 0x0 #define DB_Z_READ_BASE_HI__BASE_HI_MASK 0x000000FFL @@ -22598,6 +22615,7 @@ #define PA_CL_VS_OUT_CNTL__VS_OUT_MISC_SIDE_BUS_ENA__SHIFT 0x18 #define PA_CL_VS_OUT_CNTL__USE_VTX_GS_CUT_FLAG__SHIFT 0x19 #define PA_CL_VS_OUT_CNTL__USE_VTX_LINE_WIDTH__SHIFT 0x1b +#define PA_CL_VS_OUT_CNTL__USE_VTX_VRS_RATE__SHIFT 0x1c #define PA_CL_VS_OUT_CNTL__BYPASS_VTX_RATE_COMBINER__SHIFT 0x1d #define PA_CL_VS_OUT_CNTL__BYPASS_PRIM_RATE_COMBINER__SHIFT 0x1e #define PA_CL_VS_OUT_CNTL__CLIP_DIST_ENA_0_MASK 0x00000001L @@ -22627,6 +22645,7 @@ #define PA_CL_VS_OUT_CNTL__VS_OUT_MISC_SIDE_BUS_ENA_MASK 0x01000000L #define PA_CL_VS_OUT_CNTL__USE_VTX_GS_CUT_FLAG_MASK 0x02000000L #define PA_CL_VS_OUT_CNTL__USE_VTX_LINE_WIDTH_MASK 0x08000000L +#define PA_CL_VS_OUT_CNTL__USE_VTX_VRS_RATE_MASK 0x10000000L #define PA_CL_VS_OUT_CNTL__BYPASS_VTX_RATE_COMBINER_MASK 0x20000000L #define PA_CL_VS_OUT_CNTL__BYPASS_PRIM_RATE_COMBINER_MASK 0x40000000L //PA_CL_NANINF_CNTL @@ -22740,6 +22759,19 @@ //PA_STATE_STEREO_X #define PA_STATE_STEREO_X__STEREO_X_OFFSET__SHIFT 0x0 #define PA_STATE_STEREO_X__STEREO_X_OFFSET_MASK 0xFFFFFFFFL +//PA_CL_VRS_CNTL +#define PA_CL_VRS_CNTL__VERTEX_RATE_COMBINER_MODE__SHIFT 0x0 +#define PA_CL_VRS_CNTL__PRIMITIVE_RATE_COMBINER_MODE__SHIFT 0x3 +#define PA_CL_VRS_CNTL__HTILE_RATE_COMBINER_MODE__SHIFT 0x6 +#define PA_CL_VRS_CNTL__SAMPLE_ITER_COMBINER_MODE__SHIFT 0x9 +#define PA_CL_VRS_CNTL__EXPOSE_VRS_PIXELS_MASK__SHIFT 0xd +#define PA_CL_VRS_CNTL__CMASK_RATE_HINT_FORCE_ZERO__SHIFT 0xe +#define PA_CL_VRS_CNTL__VERTEX_RATE_COMBINER_MODE_MASK 0x00000007L +#define PA_CL_VRS_CNTL__PRIMITIVE_RATE_COMBINER_MODE_MASK 0x00000038L +#define PA_CL_VRS_CNTL__HTILE_RATE_COMBINER_MODE_MASK 0x000001C0L +#define PA_CL_VRS_CNTL__SAMPLE_ITER_COMBINER_MODE_MASK 0x00000E00L +#define PA_CL_VRS_CNTL__EXPOSE_VRS_PIXELS_MASK_MASK 0x00002000L +#define PA_CL_VRS_CNTL__CMASK_RATE_HINT_FORCE_ZERO_MASK 0x00004000L //PA_SU_POINT_SIZE #define PA_SU_POINT_SIZE__HEIGHT__SHIFT 0x0 #define PA_SU_POINT_SIZE__WIDTH__SHIFT 0x10 @@ -23088,6 +23120,7 @@ #define DB_HTILE_SURFACE__DST_OUTSIDE_ZERO_TO_ONE__SHIFT 0x10 #define DB_HTILE_SURFACE__RESERVED_FIELD_6__SHIFT 0x11 #define DB_HTILE_SURFACE__PIPE_ALIGNED__SHIFT 0x12 +#define DB_HTILE_SURFACE__VRS_HTILE_ENCODING__SHIFT 0x13 #define DB_HTILE_SURFACE__RESERVED_FIELD_1_MASK 0x00000001L #define DB_HTILE_SURFACE__FULL_CACHE_MASK 0x00000002L #define DB_HTILE_SURFACE__RESERVED_FIELD_2_MASK 0x00000004L @@ -23097,6 +23130,7 @@ #define DB_HTILE_SURFACE__DST_OUTSIDE_ZERO_TO_ONE_MASK 0x00010000L #define DB_HTILE_SURFACE__RESERVED_FIELD_6_MASK 0x00020000L #define DB_HTILE_SURFACE__PIPE_ALIGNED_MASK 0x00040000L +#define DB_HTILE_SURFACE__VRS_HTILE_ENCODING_MASK 0x00180000L //DB_SRESULTS_COMPARE_STATE0 #define DB_SRESULTS_COMPARE_STATE0__COMPAREFUNC0__SHIFT 0x0 #define DB_SRESULTS_COMPARE_STATE0__COMPAREVALUE0__SHIFT 0x4 @@ -24954,6 +24988,7 @@ #define CB_COLOR0_ATTRIB3__CMASK_PIPE_ALIGNED__SHIFT 0x1a #define CB_COLOR0_ATTRIB3__RESOURCE_LEVEL__SHIFT 0x1b #define CB_COLOR0_ATTRIB3__DCC_PIPE_ALIGNED__SHIFT 0x1e +#define CB_COLOR0_ATTRIB3__VRS_RATE_HINT_ENABLE__SHIFT 0x1f #define CB_COLOR0_ATTRIB3__MIP0_DEPTH_MASK 0x00001FFFL #define CB_COLOR0_ATTRIB3__META_LINEAR_MASK 0x00002000L #define CB_COLOR0_ATTRIB3__COLOR_SW_MODE_MASK 0x0007C000L @@ -24962,6 +24997,7 @@ #define CB_COLOR0_ATTRIB3__CMASK_PIPE_ALIGNED_MASK 0x04000000L #define CB_COLOR0_ATTRIB3__RESOURCE_LEVEL_MASK 0x38000000L #define CB_COLOR0_ATTRIB3__DCC_PIPE_ALIGNED_MASK 0x40000000L +#define CB_COLOR0_ATTRIB3__VRS_RATE_HINT_ENABLE_MASK 0x80000000L //CB_COLOR1_ATTRIB3 #define CB_COLOR1_ATTRIB3__MIP0_DEPTH__SHIFT 0x0 #define CB_COLOR1_ATTRIB3__META_LINEAR__SHIFT 0xd @@ -24971,6 +25007,7 @@ #define CB_COLOR1_ATTRIB3__CMASK_PIPE_ALIGNED__SHIFT 0x1a #define CB_COLOR1_ATTRIB3__RESOURCE_LEVEL__SHIFT 0x1b #define CB_COLOR1_ATTRIB3__DCC_PIPE_ALIGNED__SHIFT 0x1e +#define CB_COLOR1_ATTRIB3__VRS_RATE_HINT_ENABLE__SHIFT 0x1f #define CB_COLOR1_ATTRIB3__MIP0_DEPTH_MASK 0x00001FFFL #define CB_COLOR1_ATTRIB3__META_LINEAR_MASK 0x00002000L #define CB_COLOR1_ATTRIB3__COLOR_SW_MODE_MASK 0x0007C000L @@ -24979,6 +25016,7 @@ #define CB_COLOR1_ATTRIB3__CMASK_PIPE_ALIGNED_MASK 0x04000000L #define CB_COLOR1_ATTRIB3__RESOURCE_LEVEL_MASK 0x38000000L #define CB_COLOR1_ATTRIB3__DCC_PIPE_ALIGNED_MASK 0x40000000L +#define CB_COLOR1_ATTRIB3__VRS_RATE_HINT_ENABLE_MASK 0x80000000L //CB_COLOR2_ATTRIB3 #define CB_COLOR2_ATTRIB3__MIP0_DEPTH__SHIFT 0x0 #define CB_COLOR2_ATTRIB3__META_LINEAR__SHIFT 0xd @@ -24988,6 +25026,7 @@ #define CB_COLOR2_ATTRIB3__CMASK_PIPE_ALIGNED__SHIFT 0x1a #define CB_COLOR2_ATTRIB3__RESOURCE_LEVEL__SHIFT 0x1b #define CB_COLOR2_ATTRIB3__DCC_PIPE_ALIGNED__SHIFT 0x1e +#define CB_COLOR2_ATTRIB3__VRS_RATE_HINT_ENABLE__SHIFT 0x1f #define CB_COLOR2_ATTRIB3__MIP0_DEPTH_MASK 0x00001FFFL #define CB_COLOR2_ATTRIB3__META_LINEAR_MASK 0x00002000L #define CB_COLOR2_ATTRIB3__COLOR_SW_MODE_MASK 0x0007C000L @@ -24996,6 +25035,7 @@ #define CB_COLOR2_ATTRIB3__CMASK_PIPE_ALIGNED_MASK 0x04000000L #define CB_COLOR2_ATTRIB3__RESOURCE_LEVEL_MASK 0x38000000L #define CB_COLOR2_ATTRIB3__DCC_PIPE_ALIGNED_MASK 0x40000000L +#define CB_COLOR2_ATTRIB3__VRS_RATE_HINT_ENABLE_MASK 0x80000000L //CB_COLOR3_ATTRIB3 #define CB_COLOR3_ATTRIB3__MIP0_DEPTH__SHIFT 0x0 #define CB_COLOR3_ATTRIB3__META_LINEAR__SHIFT 0xd @@ -25005,6 +25045,7 @@ #define CB_COLOR3_ATTRIB3__CMASK_PIPE_ALIGNED__SHIFT 0x1a #define CB_COLOR3_ATTRIB3__RESOURCE_LEVEL__SHIFT 0x1b #define CB_COLOR3_ATTRIB3__DCC_PIPE_ALIGNED__SHIFT 0x1e +#define CB_COLOR3_ATTRIB3__VRS_RATE_HINT_ENABLE__SHIFT 0x1f #define CB_COLOR3_ATTRIB3__MIP0_DEPTH_MASK 0x00001FFFL #define CB_COLOR3_ATTRIB3__META_LINEAR_MASK 0x00002000L #define CB_COLOR3_ATTRIB3__COLOR_SW_MODE_MASK 0x0007C000L @@ -25013,6 +25054,7 @@ #define CB_COLOR3_ATTRIB3__CMASK_PIPE_ALIGNED_MASK 0x04000000L #define CB_COLOR3_ATTRIB3__RESOURCE_LEVEL_MASK 0x38000000L #define CB_COLOR3_ATTRIB3__DCC_PIPE_ALIGNED_MASK 0x40000000L +#define CB_COLOR3_ATTRIB3__VRS_RATE_HINT_ENABLE_MASK 0x80000000L //CB_COLOR4_ATTRIB3 #define CB_COLOR4_ATTRIB3__MIP0_DEPTH__SHIFT 0x0 #define CB_COLOR4_ATTRIB3__META_LINEAR__SHIFT 0xd @@ -25022,6 +25064,7 @@ #define CB_COLOR4_ATTRIB3__CMASK_PIPE_ALIGNED__SHIFT 0x1a #define CB_COLOR4_ATTRIB3__RESOURCE_LEVEL__SHIFT 0x1b #define CB_COLOR4_ATTRIB3__DCC_PIPE_ALIGNED__SHIFT 0x1e +#define CB_COLOR4_ATTRIB3__VRS_RATE_HINT_ENABLE__SHIFT 0x1f #define CB_COLOR4_ATTRIB3__MIP0_DEPTH_MASK 0x00001FFFL #define CB_COLOR4_ATTRIB3__META_LINEAR_MASK 0x00002000L #define CB_COLOR4_ATTRIB3__COLOR_SW_MODE_MASK 0x0007C000L @@ -25030,6 +25073,7 @@ #define CB_COLOR4_ATTRIB3__CMASK_PIPE_ALIGNED_MASK 0x04000000L #define CB_COLOR4_ATTRIB3__RESOURCE_LEVEL_MASK 0x38000000L #define CB_COLOR4_ATTRIB3__DCC_PIPE_ALIGNED_MASK 0x40000000L +#define CB_COLOR4_ATTRIB3__VRS_RATE_HINT_ENABLE_MASK 0x80000000L //CB_COLOR5_ATTRIB3 #define CB_COLOR5_ATTRIB3__MIP0_DEPTH__SHIFT 0x0 #define CB_COLOR5_ATTRIB3__META_LINEAR__SHIFT 0xd @@ -25039,6 +25083,7 @@ #define CB_COLOR5_ATTRIB3__CMASK_PIPE_ALIGNED__SHIFT 0x1a #define CB_COLOR5_ATTRIB3__RESOURCE_LEVEL__SHIFT 0x1b #define CB_COLOR5_ATTRIB3__DCC_PIPE_ALIGNED__SHIFT 0x1e +#define CB_COLOR5_ATTRIB3__VRS_RATE_HINT_ENABLE__SHIFT 0x1f #define CB_COLOR5_ATTRIB3__MIP0_DEPTH_MASK 0x00001FFFL #define CB_COLOR5_ATTRIB3__META_LINEAR_MASK 0x00002000L #define CB_COLOR5_ATTRIB3__COLOR_SW_MODE_MASK 0x0007C000L @@ -25047,6 +25092,7 @@ #define CB_COLOR5_ATTRIB3__CMASK_PIPE_ALIGNED_MASK 0x04000000L #define CB_COLOR5_ATTRIB3__RESOURCE_LEVEL_MASK 0x38000000L #define CB_COLOR5_ATTRIB3__DCC_PIPE_ALIGNED_MASK 0x40000000L +#define CB_COLOR5_ATTRIB3__VRS_RATE_HINT_ENABLE_MASK 0x80000000L //CB_COLOR6_ATTRIB3 #define CB_COLOR6_ATTRIB3__MIP0_DEPTH__SHIFT 0x0 #define CB_COLOR6_ATTRIB3__META_LINEAR__SHIFT 0xd @@ -25056,6 +25102,7 @@ #define CB_COLOR6_ATTRIB3__CMASK_PIPE_ALIGNED__SHIFT 0x1a #define CB_COLOR6_ATTRIB3__RESOURCE_LEVEL__SHIFT 0x1b #define CB_COLOR6_ATTRIB3__DCC_PIPE_ALIGNED__SHIFT 0x1e +#define CB_COLOR6_ATTRIB3__VRS_RATE_HINT_ENABLE__SHIFT 0x1f #define CB_COLOR6_ATTRIB3__MIP0_DEPTH_MASK 0x00001FFFL #define CB_COLOR6_ATTRIB3__META_LINEAR_MASK 0x00002000L #define CB_COLOR6_ATTRIB3__COLOR_SW_MODE_MASK 0x0007C000L @@ -25064,6 +25111,7 @@ #define CB_COLOR6_ATTRIB3__CMASK_PIPE_ALIGNED_MASK 0x04000000L #define CB_COLOR6_ATTRIB3__RESOURCE_LEVEL_MASK 0x38000000L #define CB_COLOR6_ATTRIB3__DCC_PIPE_ALIGNED_MASK 0x40000000L +#define CB_COLOR6_ATTRIB3__VRS_RATE_HINT_ENABLE_MASK 0x80000000L //CB_COLOR7_ATTRIB3 #define CB_COLOR7_ATTRIB3__MIP0_DEPTH__SHIFT 0x0 #define CB_COLOR7_ATTRIB3__META_LINEAR__SHIFT 0xd @@ -25073,6 +25121,7 @@ #define CB_COLOR7_ATTRIB3__CMASK_PIPE_ALIGNED__SHIFT 0x1a #define CB_COLOR7_ATTRIB3__RESOURCE_LEVEL__SHIFT 0x1b #define CB_COLOR7_ATTRIB3__DCC_PIPE_ALIGNED__SHIFT 0x1e +#define CB_COLOR7_ATTRIB3__VRS_RATE_HINT_ENABLE__SHIFT 0x1f #define CB_COLOR7_ATTRIB3__MIP0_DEPTH_MASK 0x00001FFFL #define CB_COLOR7_ATTRIB3__META_LINEAR_MASK 0x00002000L #define CB_COLOR7_ATTRIB3__COLOR_SW_MODE_MASK 0x0007C000L @@ -25081,6 +25130,7 @@ #define CB_COLOR7_ATTRIB3__CMASK_PIPE_ALIGNED_MASK 0x04000000L #define CB_COLOR7_ATTRIB3__RESOURCE_LEVEL_MASK 0x38000000L #define CB_COLOR7_ATTRIB3__DCC_PIPE_ALIGNED_MASK 0x40000000L +#define CB_COLOR7_ATTRIB3__VRS_RATE_HINT_ENABLE_MASK 0x80000000L // addressBlock: gc_gfxudec diff --git a/drivers/gpu/drm/amd/include/asic_reg/gc/gc_9_4_1_offset.h b/drivers/gpu/drm/amd/include/asic_reg/gc/gc_9_4_1_offset.h index f41556abfbbc..629a8a3b55e9 100644 --- a/drivers/gpu/drm/amd/include/asic_reg/gc/gc_9_4_1_offset.h +++ b/drivers/gpu/drm/amd/include/asic_reg/gc/gc_9_4_1_offset.h @@ -205,6 +205,8 @@ #define mmGCEA_EDC_CNT2_BASE_IDX 0 #define mmGCEA_EDC_CNT3 0x071b #define mmGCEA_EDC_CNT3_BASE_IDX 0 +#define mmGCEA_ERR_STATUS 0x0712 +#define mmGCEA_ERR_STATUS_BASE_IDX 0 // addressBlock: gc_gfxudec // base address: 0x30000 @@ -261,4 +263,4 @@ #define mmRLC_EDC_CNT2 0x4d41 #define mmRLC_EDC_CNT2_BASE_IDX 1 -#endif
\ No newline at end of file +#endif diff --git a/drivers/gpu/drm/amd/include/asic_reg/uvd/uvd_7_0_offset.h b/drivers/gpu/drm/amd/include/asic_reg/uvd/uvd_7_0_offset.h index 07aceffb108a..524ba4421c17 100644 --- a/drivers/gpu/drm/amd/include/asic_reg/uvd/uvd_7_0_offset.h +++ b/drivers/gpu/drm/amd/include/asic_reg/uvd/uvd_7_0_offset.h @@ -151,6 +151,8 @@ #define mmUVD_LMI_CTRL2_BASE_IDX 1 #define mmUVD_MASTINT_EN 0x0540 #define mmUVD_MASTINT_EN_BASE_IDX 1 +#define mmUVD_FW_STATUS 0x0557 +#define mmUVD_FW_STATUS_BASE_IDX 1 #define mmJPEG_CGC_CTRL 0x0565 #define mmJPEG_CGC_CTRL_BASE_IDX 1 #define mmUVD_LMI_CTRL 0x0566 @@ -219,4 +221,5 @@ #define mmUVD_CONTEXT_ID2_BASE_IDX 1 + #endif diff --git a/drivers/gpu/drm/amd/include/asic_reg/uvd/uvd_7_0_sh_mask.h b/drivers/gpu/drm/amd/include/asic_reg/uvd/uvd_7_0_sh_mask.h index b427f73bd536..919be1842bd5 100644 --- a/drivers/gpu/drm/amd/include/asic_reg/uvd/uvd_7_0_sh_mask.h +++ b/drivers/gpu/drm/amd/include/asic_reg/uvd/uvd_7_0_sh_mask.h @@ -807,5 +807,25 @@ #define UVD_CONTEXT_ID2__CONTEXT_ID2__SHIFT 0x0 #define UVD_CONTEXT_ID2__CONTEXT_ID2_MASK 0xFFFFFFFFL +//UVD_FW_STATUS +#define UVD_FW_STATUS__BUSY__SHIFT 0x0 +#define UVD_FW_STATUS__ACTIVE__SHIFT 0x1 +#define UVD_FW_STATUS__SEND_EFUSE_REQ__SHIFT 0x2 +#define UVD_FW_STATUS__DONE__SHIFT 0x8 +#define UVD_FW_STATUS__PASS__SHIFT 0x10 +#define UVD_FW_STATUS__FAIL__SHIFT 0x11 +#define UVD_FW_STATUS__INVALID_LEN__SHIFT 0x12 +#define UVD_FW_STATUS__INVALID_0_PADDING__SHIFT 0x13 +#define UVD_FW_STATUS__INVALID_NONCE__SHIFT 0x14 +#define UVD_FW_STATUS__BUSY_MASK 0x00000001L +#define UVD_FW_STATUS__ACTIVE_MASK 0x00000002L +#define UVD_FW_STATUS__SEND_EFUSE_REQ_MASK 0x00000004L +#define UVD_FW_STATUS__DONE_MASK 0x00000100L +#define UVD_FW_STATUS__PASS_MASK 0x00010000L +#define UVD_FW_STATUS__FAIL_MASK 0x00020000L +#define UVD_FW_STATUS__INVALID_LEN_MASK 0x00040000L +#define UVD_FW_STATUS__INVALID_0_PADDING_MASK 0x00080000L +#define UVD_FW_STATUS__INVALID_NONCE_MASK 0x00100000L + #endif diff --git a/drivers/gpu/drm/amd/include/asic_reg/vcn/vcn_3_0_0_sh_mask.h b/drivers/gpu/drm/amd/include/asic_reg/vcn/vcn_3_0_0_sh_mask.h index c0efd90808f2..58cf7adb9d54 100644 --- a/drivers/gpu/drm/amd/include/asic_reg/vcn/vcn_3_0_0_sh_mask.h +++ b/drivers/gpu/drm/amd/include/asic_reg/vcn/vcn_3_0_0_sh_mask.h @@ -2393,6 +2393,7 @@ #define VCN_FEATURES__HAS_MJPEG2_IDCT_DEC__SHIFT 0x7 #define VCN_FEATURES__HAS_SCLR_DEC__SHIFT 0x8 #define VCN_FEATURES__HAS_VP9_DEC__SHIFT 0x9 +#define VCN_FEATURES__HAS_AV1_DEC__SHIFT 0xa #define VCN_FEATURES__HAS_EFC_ENC__SHIFT 0xb #define VCN_FEATURES__HAS_EFC_HDR2SDR_ENC__SHIFT 0xc #define VCN_FEATURES__HAS_DUAL_MJPEG_DEC__SHIFT 0xd @@ -2407,6 +2408,7 @@ #define VCN_FEATURES__HAS_MJPEG2_IDCT_DEC_MASK 0x00000080L #define VCN_FEATURES__HAS_SCLR_DEC_MASK 0x00000100L #define VCN_FEATURES__HAS_VP9_DEC_MASK 0x00000200L +#define VCN_FEATURES__HAS_AV1_DEC_MASK 0x00000400L #define VCN_FEATURES__HAS_EFC_ENC_MASK 0x00000800L #define VCN_FEATURES__HAS_EFC_HDR2SDR_ENC_MASK 0x00001000L #define VCN_FEATURES__HAS_DUAL_MJPEG_DEC_MASK 0x00002000L @@ -2809,8 +2811,10 @@ #define UVD_SUVD_CGC_GATE__IME_HEVC__SHIFT 0x18 #define UVD_SUVD_CGC_GATE__EFC__SHIFT 0x19 #define UVD_SUVD_CGC_GATE__SAOE__SHIFT 0x1a +#define UVD_SUVD_CGC_GATE__SRE_AV1__SHIFT 0x1b #define UVD_SUVD_CGC_GATE__FBC_PCLK__SHIFT 0x1c #define UVD_SUVD_CGC_GATE__FBC_CCLK__SHIFT 0x1d +#define UVD_SUVD_CGC_GATE__SCM_AV1__SHIFT 0x1e #define UVD_SUVD_CGC_GATE__SMPA__SHIFT 0x1f #define UVD_SUVD_CGC_GATE__SRE_MASK 0x00000001L #define UVD_SUVD_CGC_GATE__SIT_MASK 0x00000002L @@ -2839,8 +2843,10 @@ #define UVD_SUVD_CGC_GATE__IME_HEVC_MASK 0x01000000L #define UVD_SUVD_CGC_GATE__EFC_MASK 0x02000000L #define UVD_SUVD_CGC_GATE__SAOE_MASK 0x04000000L +#define UVD_SUVD_CGC_GATE__SRE_AV1_MASK 0x08000000L #define UVD_SUVD_CGC_GATE__FBC_PCLK_MASK 0x10000000L #define UVD_SUVD_CGC_GATE__FBC_CCLK_MASK 0x20000000L +#define UVD_SUVD_CGC_GATE__SCM_AV1_MASK 0x40000000L #define UVD_SUVD_CGC_GATE__SMPA_MASK 0x80000000L //UVD_SUVD_CGC_STATUS #define UVD_SUVD_CGC_STATUS__SRE_VCLK__SHIFT 0x0 @@ -2873,6 +2879,8 @@ #define UVD_SUVD_CGC_STATUS__IME_HEVC_DCLK__SHIFT 0x1b #define UVD_SUVD_CGC_STATUS__EFC_DCLK__SHIFT 0x1c #define UVD_SUVD_CGC_STATUS__SAOE_DCLK__SHIFT 0x1d +#define UVD_SUVD_CGC_STATUS__SRE_AV1_VCLK__SHIFT 0x1e +#define UVD_SUVD_CGC_STATUS__SCM_AV1_DCLK__SHIFT 0x1f #define UVD_SUVD_CGC_STATUS__SRE_VCLK_MASK 0x00000001L #define UVD_SUVD_CGC_STATUS__SRE_DCLK_MASK 0x00000002L #define UVD_SUVD_CGC_STATUS__SIT_DCLK_MASK 0x00000004L @@ -2903,6 +2911,8 @@ #define UVD_SUVD_CGC_STATUS__IME_HEVC_DCLK_MASK 0x08000000L #define UVD_SUVD_CGC_STATUS__EFC_DCLK_MASK 0x10000000L #define UVD_SUVD_CGC_STATUS__SAOE_DCLK_MASK 0x20000000L +#define UVD_SUVD_CGC_STATUS__SRE_AV1_VCLK_MASK 0x40000000L +#define UVD_SUVD_CGC_STATUS__SCM_AV1_DCLK_MASK 0x80000000L //UVD_SUVD_CGC_CTRL #define UVD_SUVD_CGC_CTRL__SRE_MODE__SHIFT 0x0 #define UVD_SUVD_CGC_CTRL__SIT_MODE__SHIFT 0x1 @@ -2919,6 +2929,8 @@ #define UVD_SUVD_CGC_CTRL__SMPA_MODE__SHIFT 0xc #define UVD_SUVD_CGC_CTRL__MPBE0_MODE__SHIFT 0xd #define UVD_SUVD_CGC_CTRL__MPBE1_MODE__SHIFT 0xe +#define UVD_SUVD_CGC_CTRL__SIT_AV1_MODE__SHIFT 0xf +#define UVD_SUVD_CGC_CTRL__SDB_AV1_MODE__SHIFT 0x10 #define UVD_SUVD_CGC_CTRL__MPC1_MODE__SHIFT 0x11 #define UVD_SUVD_CGC_CTRL__FBC_PCLK__SHIFT 0x1c #define UVD_SUVD_CGC_CTRL__FBC_CCLK__SHIFT 0x1d @@ -2937,6 +2949,8 @@ #define UVD_SUVD_CGC_CTRL__SMPA_MODE_MASK 0x00001000L #define UVD_SUVD_CGC_CTRL__MPBE0_MODE_MASK 0x00002000L #define UVD_SUVD_CGC_CTRL__MPBE1_MODE_MASK 0x00004000L +#define UVD_SUVD_CGC_CTRL__SIT_AV1_MODE_MASK 0x00008000L +#define UVD_SUVD_CGC_CTRL__SDB_AV1_MODE_MASK 0x00010000L #define UVD_SUVD_CGC_CTRL__MPC1_MODE_MASK 0x00020000L #define UVD_SUVD_CGC_CTRL__FBC_PCLK_MASK 0x10000000L #define UVD_SUVD_CGC_CTRL__FBC_CCLK_MASK 0x20000000L @@ -3658,6 +3672,8 @@ #define UVD_SUVD_CGC_STATUS2__SMPA_VCLK__SHIFT 0x0 #define UVD_SUVD_CGC_STATUS2__SMPA_DCLK__SHIFT 0x1 #define UVD_SUVD_CGC_STATUS2__MPBE1_DCLK__SHIFT 0x3 +#define UVD_SUVD_CGC_STATUS2__SIT_AV1_DCLK__SHIFT 0x4 +#define UVD_SUVD_CGC_STATUS2__SDB_AV1_DCLK__SHIFT 0x5 #define UVD_SUVD_CGC_STATUS2__MPC1_DCLK__SHIFT 0x6 #define UVD_SUVD_CGC_STATUS2__MPC1_SCLK__SHIFT 0x7 #define UVD_SUVD_CGC_STATUS2__MPC1_VCLK__SHIFT 0x8 @@ -3666,6 +3682,8 @@ #define UVD_SUVD_CGC_STATUS2__SMPA_VCLK_MASK 0x00000001L #define UVD_SUVD_CGC_STATUS2__SMPA_DCLK_MASK 0x00000002L #define UVD_SUVD_CGC_STATUS2__MPBE1_DCLK_MASK 0x00000008L +#define UVD_SUVD_CGC_STATUS2__SIT_AV1_DCLK_MASK 0x00000010L +#define UVD_SUVD_CGC_STATUS2__SDB_AV1_DCLK_MASK 0x00000020L #define UVD_SUVD_CGC_STATUS2__MPC1_DCLK_MASK 0x00000040L #define UVD_SUVD_CGC_STATUS2__MPC1_SCLK_MASK 0x00000080L #define UVD_SUVD_CGC_STATUS2__MPC1_VCLK_MASK 0x00000100L @@ -3674,25 +3692,41 @@ //UVD_SUVD_CGC_GATE2 #define UVD_SUVD_CGC_GATE2__MPBE0__SHIFT 0x0 #define UVD_SUVD_CGC_GATE2__MPBE1__SHIFT 0x1 +#define UVD_SUVD_CGC_GATE2__SIT_AV1__SHIFT 0x2 +#define UVD_SUVD_CGC_GATE2__SDB_AV1__SHIFT 0x3 #define UVD_SUVD_CGC_GATE2__MPC1__SHIFT 0x4 #define UVD_SUVD_CGC_GATE2__MPBE0_MASK 0x00000001L #define UVD_SUVD_CGC_GATE2__MPBE1_MASK 0x00000002L +#define UVD_SUVD_CGC_GATE2__SIT_AV1_MASK 0x00000004L +#define UVD_SUVD_CGC_GATE2__SDB_AV1_MASK 0x00000008L #define UVD_SUVD_CGC_GATE2__MPC1_MASK 0x00000010L //UVD_SUVD_INT_STATUS2 #define UVD_SUVD_INT_STATUS2__SMPA_FUNC_INT__SHIFT 0x0 #define UVD_SUVD_INT_STATUS2__SMPA_ERR_INT__SHIFT 0x5 +#define UVD_SUVD_INT_STATUS2__SDB_AV1_FUNC_INT__SHIFT 0x6 +#define UVD_SUVD_INT_STATUS2__SDB_AV1_ERR_INT__SHIFT 0xb #define UVD_SUVD_INT_STATUS2__SMPA_FUNC_INT_MASK 0x0000001FL #define UVD_SUVD_INT_STATUS2__SMPA_ERR_INT_MASK 0x00000020L +#define UVD_SUVD_INT_STATUS2__SDB_AV1_FUNC_INT_MASK 0x000007C0L +#define UVD_SUVD_INT_STATUS2__SDB_AV1_ERR_INT_MASK 0x00000800L //UVD_SUVD_INT_EN2 #define UVD_SUVD_INT_EN2__SMPA_FUNC_INT_EN__SHIFT 0x0 #define UVD_SUVD_INT_EN2__SMPA_ERR_INT_EN__SHIFT 0x5 +#define UVD_SUVD_INT_EN2__SDB_AV1_FUNC_INT_EN__SHIFT 0x6 +#define UVD_SUVD_INT_EN2__SDB_AV1_ERR_INT_EN__SHIFT 0xb #define UVD_SUVD_INT_EN2__SMPA_FUNC_INT_EN_MASK 0x0000001FL #define UVD_SUVD_INT_EN2__SMPA_ERR_INT_EN_MASK 0x00000020L +#define UVD_SUVD_INT_EN2__SDB_AV1_FUNC_INT_EN_MASK 0x000007C0L +#define UVD_SUVD_INT_EN2__SDB_AV1_ERR_INT_EN_MASK 0x00000800L //UVD_SUVD_INT_ACK2 #define UVD_SUVD_INT_ACK2__SMPA_FUNC_INT_ACK__SHIFT 0x0 #define UVD_SUVD_INT_ACK2__SMPA_ERR_INT_ACK__SHIFT 0x5 +#define UVD_SUVD_INT_ACK2__SDB_AV1_FUNC_INT_ACK__SHIFT 0x6 +#define UVD_SUVD_INT_ACK2__SDB_AV1_ERR_INT_ACK__SHIFT 0xb #define UVD_SUVD_INT_ACK2__SMPA_FUNC_INT_ACK_MASK 0x0000001FL #define UVD_SUVD_INT_ACK2__SMPA_ERR_INT_ACK_MASK 0x00000020L +#define UVD_SUVD_INT_ACK2__SDB_AV1_FUNC_INT_ACK_MASK 0x000007C0L +#define UVD_SUVD_INT_ACK2__SDB_AV1_ERR_INT_ACK_MASK 0x00000800L // addressBlock: uvd0_ecpudec diff --git a/drivers/gpu/drm/amd/include/kgd_kfd_interface.h b/drivers/gpu/drm/amd/include/kgd_kfd_interface.h index fc592f60e6a0..95c656d205ed 100644 --- a/drivers/gpu/drm/amd/include/kgd_kfd_interface.h +++ b/drivers/gpu/drm/amd/include/kgd_kfd_interface.h @@ -212,6 +212,15 @@ struct tile_config { * IH ring entry. This function allows the KFD ISR to get the VMID * from the fault status register as early as possible. * + * @get_cu_occupancy: Function pointer that returns to caller the number + * of wave fronts that are in flight for all of the queues of a process + * as identified by its pasid. It is important to note that the value + * returned by this function is a snapshot of current moment and cannot + * guarantee any minimum for the number of waves in-flight. This function + * is defined for devices that belong to GFX9 and later GFX families. Care + * must be taken in calling this function as it is not defined for devices + * that belong to GFX8 and below GFX families. + * * This structure contains function pointers to services that the kgd driver * provides to amdkfd driver. * @@ -222,7 +231,7 @@ struct kfd2kgd_calls { uint32_t sh_mem_config, uint32_t sh_mem_ape1_base, uint32_t sh_mem_ape1_limit, uint32_t sh_mem_bases); - int (*set_pasid_vmid_mapping)(struct kgd_dev *kgd, unsigned int pasid, + int (*set_pasid_vmid_mapping)(struct kgd_dev *kgd, u32 pasid, unsigned int vmid); int (*init_interrupts)(struct kgd_dev *kgd, uint32_t pipe_id); @@ -286,6 +295,9 @@ struct kfd2kgd_calls { void (*set_vm_context_page_table_base)(struct kgd_dev *kgd, uint32_t vmid, uint64_t page_table_base); uint32_t (*read_vmid_from_vmfault_reg)(struct kgd_dev *kgd); + + void (*get_cu_occupancy)(struct kgd_dev *kgd, int pasid, int *wave_cnt, + int *max_waves_per_cu); }; #endif /* KGD_KFD_INTERFACE_H_INCLUDED */ diff --git a/drivers/gpu/drm/amd/include/kgd_pp_interface.h b/drivers/gpu/drm/amd/include/kgd_pp_interface.h index 0aec28fda058..94132c70d7af 100644 --- a/drivers/gpu/drm/amd/include/kgd_pp_interface.h +++ b/drivers/gpu/drm/amd/include/kgd_pp_interface.h @@ -281,6 +281,7 @@ struct amd_pm_funcs { int (*get_power_limit)(void *handle, uint32_t *limit, bool default_limit); int (*get_power_profile_mode)(void *handle, char *buf); int (*set_power_profile_mode)(void *handle, long *input, uint32_t size); + int (*set_fine_grain_clk_vol)(void *handle, uint32_t type, long *input, uint32_t size); int (*odn_edit_dpm_table)(void *handle, uint32_t type, long *input, uint32_t size); int (*set_mp1_state)(void *handle, enum pp_mp1_state mp1_state); int (*smu_i2c_bus_access)(void *handle, bool acquire); diff --git a/drivers/gpu/drm/amd/pm/amdgpu_pm.c b/drivers/gpu/drm/amd/pm/amdgpu_pm.c index 2d924e88a215..529816637c73 100644 --- a/drivers/gpu/drm/amd/pm/amdgpu_pm.c +++ b/drivers/gpu/drm/amd/pm/amdgpu_pm.c @@ -827,6 +827,18 @@ static ssize_t amdgpu_set_pp_od_clk_voltage(struct device *dev, return -EINVAL; } } else { + + if (adev->powerplay.pp_funcs->set_fine_grain_clk_vol) { + ret = amdgpu_dpm_set_fine_grain_clk_vol(adev, type, + parameter, + parameter_size); + if (ret) { + pm_runtime_mark_last_busy(ddev->dev); + pm_runtime_put_autosuspend(ddev->dev); + return -EINVAL; + } + } + if (adev->powerplay.pp_funcs->odn_edit_dpm_table) { ret = amdgpu_dpm_odn_edit_dpm_table(adev, type, parameter, parameter_size); diff --git a/drivers/gpu/drm/amd/pm/inc/amdgpu_dpm.h b/drivers/gpu/drm/amd/pm/inc/amdgpu_dpm.h index dff4a5f99bb0..f6e0e7d8a007 100644 --- a/drivers/gpu/drm/amd/pm/inc/amdgpu_dpm.h +++ b/drivers/gpu/drm/amd/pm/inc/amdgpu_dpm.h @@ -349,6 +349,10 @@ enum amdgpu_pcie_gen { ((adev)->powerplay.pp_funcs->set_power_profile_mode(\ (adev)->powerplay.pp_handle, parameter, size)) +#define amdgpu_dpm_set_fine_grain_clk_vol(adev, type, parameter, size) \ + ((adev)->powerplay.pp_funcs->set_fine_grain_clk_vol(\ + (adev)->powerplay.pp_handle, type, parameter, size)) + #define amdgpu_dpm_odn_edit_dpm_table(adev, type, parameter, size) \ ((adev)->powerplay.pp_funcs->odn_edit_dpm_table(\ (adev)->powerplay.pp_handle, type, parameter, size)) diff --git a/drivers/gpu/drm/amd/pm/inc/amdgpu_smu.h b/drivers/gpu/drm/amd/pm/inc/amdgpu_smu.h index d22a759b6b43..44fd0cd069de 100644 --- a/drivers/gpu/drm/amd/pm/inc/amdgpu_smu.h +++ b/drivers/gpu/drm/amd/pm/inc/amdgpu_smu.h @@ -270,6 +270,7 @@ struct smu_table_context */ struct smu_table driver_table; struct smu_table memory_pool; + struct smu_table dummy_read_1_table; uint8_t thermal_controller_type; void *overdrive_table; @@ -452,6 +453,7 @@ struct smu_context struct work_struct throttling_logging_work; atomic64_t throttle_int_counter; + struct work_struct interrupt_work; unsigned fan_max_rpm; unsigned manual_fan_speed_rpm; @@ -500,7 +502,7 @@ struct pptable_funcs { bool (*is_dpm_running)(struct smu_context *smu); int (*get_fan_speed_rpm)(struct smu_context *smu, uint32_t *speed); int (*set_watermarks_table)(struct smu_context *smu, - struct dm_pp_wm_sets_with_clock_ranges_soc15 *clock_ranges); + struct pp_smu_wm_range_sets *clock_ranges); int (*get_thermal_temperature_range)(struct smu_context *smu, struct smu_temperature_range *range); int (*get_uclk_dpm_states)(struct smu_context *smu, uint32_t *clocks_in_khz, uint32_t *num_states); int (*set_default_od_settings)(struct smu_context *smu); @@ -590,7 +592,6 @@ struct pptable_funcs { int (*mode2_reset)(struct smu_context *smu); int (*get_dpm_ultimate_freq)(struct smu_context *smu, enum smu_clk_type clk_type, uint32_t *min, uint32_t *max); int (*set_soft_freq_limited_range)(struct smu_context *smu, enum smu_clk_type clk_type, uint32_t min, uint32_t max); - int (*disable_umc_cdr_12gbps_workaround)(struct smu_context *smu); int (*set_power_source)(struct smu_context *smu, enum smu_power_src_type power_src); void (*log_thermal_throttling_event)(struct smu_context *smu); size_t (*get_pp_feature_mask)(struct smu_context *smu, char *buf); @@ -600,6 +601,8 @@ struct pptable_funcs { int (*gfx_ulv_control)(struct smu_context *smu, bool enablement); int (*deep_sleep_control)(struct smu_context *smu, bool enablement); int (*get_fan_parameters)(struct smu_context *smu); + int (*post_init)(struct smu_context *smu); + void (*interrupt_work)(struct smu_context *smu); }; typedef enum { @@ -703,7 +706,6 @@ int smu_set_fan_speed_percent(struct smu_context *smu, uint32_t speed); int smu_get_fan_speed_rpm(struct smu_context *smu, uint32_t *speed); int smu_set_deep_sleep_dcefclk(struct smu_context *smu, int clk); -int smu_set_active_display_count(struct smu_context *smu, uint32_t count); int smu_get_clock_by_type(struct smu_context *smu, enum amd_pp_clock_type type, @@ -755,7 +757,7 @@ enum amd_pm_state_type smu_get_current_power_state(struct smu_context *smu); int smu_write_watermarks_table(struct smu_context *smu); int smu_set_watermarks_for_clock_ranges( struct smu_context *smu, - struct dm_pp_wm_sets_with_clock_ranges_soc15 *clock_ranges); + struct pp_smu_wm_range_sets *clock_ranges); /* smu to display interface */ extern int smu_display_configuration_change(struct smu_context *smu, const diff --git a/drivers/gpu/drm/amd/pm/inc/hwmgr.h b/drivers/gpu/drm/amd/pm/inc/hwmgr.h index 1b3529efc91e..3898a95ec28b 100644 --- a/drivers/gpu/drm/amd/pm/inc/hwmgr.h +++ b/drivers/gpu/drm/amd/pm/inc/hwmgr.h @@ -340,6 +340,9 @@ struct pp_hwmgr_func { int (*odn_edit_dpm_table)(struct pp_hwmgr *hwmgr, enum PP_OD_DPM_TABLE_COMMAND type, long *input, uint32_t size); + int (*set_fine_grain_clk_vol)(struct pp_hwmgr *hwmgr, + enum PP_OD_DPM_TABLE_COMMAND type, + long *input, uint32_t size); int (*set_power_limit)(struct pp_hwmgr *hwmgr, uint32_t n); int (*powergate_mmhub)(struct pp_hwmgr *hwmgr); int (*smus_notify_pwe)(struct pp_hwmgr *hwmgr); @@ -347,6 +350,8 @@ struct pp_hwmgr_func { int (*enable_mgpu_fan_boost)(struct pp_hwmgr *hwmgr); int (*set_hard_min_dcefclk_by_freq)(struct pp_hwmgr *hwmgr, uint32_t clock); int (*set_hard_min_fclk_by_freq)(struct pp_hwmgr *hwmgr, uint32_t clock); + int (*set_hard_min_gfxclk_by_freq)(struct pp_hwmgr *hwmgr, uint32_t clock); + int (*set_soft_max_gfxclk_by_freq)(struct pp_hwmgr *hwmgr, uint32_t clock); int (*get_asic_baco_capability)(struct pp_hwmgr *hwmgr, bool *cap); int (*get_asic_baco_state)(struct pp_hwmgr *hwmgr, enum BACO_STATE *state); int (*set_asic_baco_state)(struct pp_hwmgr *hwmgr, enum BACO_STATE state); diff --git a/drivers/gpu/drm/amd/pm/inc/smu10_driver_if.h b/drivers/gpu/drm/amd/pm/inc/smu10_driver_if.h index dea8fe93da63..c498158771cc 100644 --- a/drivers/gpu/drm/amd/pm/inc/smu10_driver_if.h +++ b/drivers/gpu/drm/amd/pm/inc/smu10_driver_if.h @@ -54,7 +54,8 @@ typedef struct { uint16_t MaxMclk; uint8_t WmSetting; - uint8_t Padding[3]; + uint8_t WmType; + uint8_t Padding[2]; } WatermarkRowGeneric_t; #define NUM_WM_RANGES 4 diff --git a/drivers/gpu/drm/amd/pm/inc/smu11_driver_if_sienna_cichlid.h b/drivers/gpu/drm/amd/pm/inc/smu11_driver_if_sienna_cichlid.h index 5ef9c92f57c4..1275246769d9 100644 --- a/drivers/gpu/drm/amd/pm/inc/smu11_driver_if_sienna_cichlid.h +++ b/drivers/gpu/drm/amd/pm/inc/smu11_driver_if_sienna_cichlid.h @@ -27,9 +27,9 @@ // *** IMPORTANT *** // SMU TEAM: Always increment the interface version if // any structure is changed in this file -#define SMU11_DRIVER_IF_VERSION 0x35 +#define SMU11_DRIVER_IF_VERSION 0x39 -#define PPTABLE_Sienna_Cichlid_SMU_VERSION 5 +#define PPTABLE_Sienna_Cichlid_SMU_VERSION 6 #define NUM_GFXCLK_DPM_LEVELS 16 #define NUM_SMNCLK_DPM_LEVELS 2 @@ -169,7 +169,7 @@ typedef enum { #define DPM_OVERRIDE_DISABLE_DFLL_PLL_SHUTDOWN 0x00000200 #define DPM_OVERRIDE_DISABLE_MEMORY_TEMPERATURE_READ 0x00000400 #define DPM_OVERRIDE_DISABLE_VOLT_LINK_VCN_DCEFCLK 0x00000800 -#define DPM_OVERRIDE_ENABLE_FAST_FCLK_TIMER 0x00001000 +#define DPM_OVERRIDE_DISABLE_FAST_FCLK_TIMER 0x00001000 #define DPM_OVERRIDE_DISABLE_VCN_PG 0x00002000 #define DPM_OVERRIDE_DISABLE_FMAX_VMAX 0x00004000 @@ -793,8 +793,18 @@ typedef struct { // SECTION: Sku Reserved uint8_t CustomerVariant; - uint8_t Spare[3]; - uint32_t SkuReserved[14]; + + //VC BTC parameters are only applicable to VDD_GFX domain + uint8_t VcBtcEnabled; + uint16_t VcBtcVminT0; // T0_VMIN + uint16_t VcBtcFixedVminAgingOffset; // FIXED_VMIN_AGING_OFFSET + uint16_t VcBtcVmin2PsmDegrationGb; // VMIN_TO_PSM_DEGRADATION_GB + uint32_t VcBtcPsmA; // A_PSM + uint32_t VcBtcPsmB; // B_PSM + uint32_t VcBtcVminA; // A_VMIN + uint32_t VcBtcVminB; // B_VMIN + + uint32_t SkuReserved[9]; // MAJOR SECTION: BOARD PARAMETERS @@ -952,7 +962,7 @@ typedef struct { uint8_t FanLinearPwmPoints[NUM_OD_FAN_MAX_POINTS]; uint8_t FanLinearTempPoints[NUM_OD_FAN_MAX_POINTS]; uint16_t MaxOpTemp; // Degree Celcius - uint16_t Padding_16[1]; + int16_t VddGfxOffset; // in mV uint8_t FanZeroRpmEnable; uint8_t FanZeroRpmStopTemp; uint8_t FanMode; diff --git a/drivers/gpu/drm/amd/pm/inc/smu_11_0_cdr_table.h b/drivers/gpu/drm/amd/pm/inc/smu_11_0_cdr_table.h new file mode 100644 index 000000000000..beab6d7b28b7 --- /dev/null +++ b/drivers/gpu/drm/amd/pm/inc/smu_11_0_cdr_table.h @@ -0,0 +1,194 @@ +/* + * Copyright 2020 Advanced Micro Devices, Inc. + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of this software and associated documentation files (the "Software"), + * to deal in the Software without restriction, including without limitation + * the rights to use, copy, modify, merge, publish, distribute, sublicense, + * and/or sell copies of the Software, and to permit persons to whom the + * Software is furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR + * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, + * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR + * OTHER DEALINGS IN THE SOFTWARE. + * + */ + + +#ifndef SMU_11_0_CDR_TABLE +#define SMU_11_0_CDR_TABLE + + +#pragma pack(push, 1) + +/// CDR table : PRBS sequence for DQ toggles + +/*static unsigned int NoDbiPrbs7[] = +{ +//256 bytes, 256 byte aligned +0x0f0f0f0f, 0x0f0f0f0f, 0x0f0f0f0f, 0xf0f00f0f, 0x0f0f0f0f, 0x0f0f0f0f, 0xf0f0f0f0, 0x0f0f0f0f, 0x0f0f0f0f, 0xf0f00f0f, 0xf0f00f0f, 0x0f0f0f0f, 0xf0f0f0f0, 0xf0f0f0f0, 0x0f0f0f0f, 0xf0f00f0f, +0x0f0f0f0f, 0xf0f00f0f, 0xf0f0f0f0, 0x0f0f0f0f, 0xf0f0f0f0, 0xf0f00f0f, 0xf0f00f0f, 0xf0f00f0f, 0x0f0ff0f0, 0xf0f0f0f0, 0xf0f0f0f0, 0x0f0ff0f0, 0x0f0f0f0f, 0x0f0f0f0f, 0xf0f0f0f0, 0xf0f00f0f, +0x0f0f0f0f, 0xf0f00f0f, 0x0f0ff0f0, 0x0f0f0f0f, 0xf0f0f0f0, 0x0f0ff0f0, 0xf0f00f0f, 0xf0f00f0f, 0xf0f0f0f0, 0x0f0ff0f0, 0xf0f0f0f0, 0xf0f00f0f, 0xf0f0f0f0, 0x0f0f0f0f, 0x0f0ff0f0, 0xf0f00f0f, +0xf0f00f0f, 0x0f0ff0f0, 0x0f0ff0f0, 0xf0f0f0f0, 0x0f0ff0f0, 0xf0f0f0f0, 0x0f0f0f0f, 0xf0f0f0f0, 0x0f0f0f0f, 0xf0f00f0f, 0xf0f00f0f, 0xf0f00f0f, 0xf0f0f0f0, 0xf0f0f0f0, 0xf0f0f0f0, 0xf0f0ffff, +}; + + +static unsigned int DbiPrbs7[] = +{ +// 256 bytes, 256 byte aligned +0xffffffff, 0xffffffff, 0xffffffff, 0x0000ffff, 0xffffffff, 0xffffffff, 0x00000000, 0xffffffff, 0xffffffff, 0x0000ffff, 0x0000ffff, 0xffffffff, 0x00000000, 0x00000000, 0xffffffff, 0x0000ffff, +0xffffffff, 0x0000ffff, 0x00000000, 0xffffffff, 0x00000000, 0x0000ffff, 0x0000ffff, 0x0000ffff, 0xffff0000, 0x00000000, 0x00000000, 0xffff0000, 0xffffffff, 0xffffffff, 0x00000000, 0x0000ffff, +0xffffffff, 0x0000ffff, 0xffff0000, 0xffffffff, 0x00000000, 0xffff0000, 0x0000ffff, 0x0000ffff, 0x00000000, 0xffff0000, 0x00000000, 0x0000ffff, 0x00000000, 0xffffffff, 0xffff0000, 0x0000ffff, +0x0000ffff, 0xffff0000, 0xffff0000, 0x00000000, 0xffff0000, 0x00000000, 0xffffffff, 0x00000000, 0xffffffff, 0x0000ffff, 0x0000ffff, 0x0000ffff, 0x00000000, 0x00000000, 0x00000000, 0x0000ffff, +}; +*/ + + +//4096 bytes, 256 byte aligned +static unsigned int NoDbiPrbs7[] = +{ + 0x0f0f0f0f, 0x0f0f0f0f, 0x0f0f0f0f, 0xf0f00f0f, 0x0f0f0f0f, 0x0f0f0f0f, 0xf0f0f0f0, 0x0f0f0f0f, 0x0f0f0f0f, 0xf0f00f0f, 0xf0f00f0f, 0x0f0f0f0f, 0xf0f0f0f0, 0xf0f0f0f0, 0x0f0f0f0f, 0xf0f00f0f, + 0x0f0f0f0f, 0xf0f00f0f, 0xf0f0f0f0, 0x0f0f0f0f, 0xf0f0f0f0, 0xf0f00f0f, 0xf0f00f0f, 0xf0f00f0f, 0x0f0ff0f0, 0xf0f0f0f0, 0xf0f0f0f0, 0x0f0ff0f0, 0x0f0f0f0f, 0x0f0f0f0f, 0xf0f0f0f0, 0xf0f00f0f, + 0x0f0f0f0f, 0xf0f00f0f, 0x0f0ff0f0, 0x0f0f0f0f, 0xf0f0f0f0, 0x0f0ff0f0, 0xf0f00f0f, 0xf0f00f0f, 0xf0f0f0f0, 0x0f0ff0f0, 0xf0f0f0f0, 0xf0f00f0f, 0xf0f0f0f0, 0x0f0f0f0f, 0x0f0ff0f0, 0xf0f00f0f, + 0xf0f00f0f, 0x0f0ff0f0, 0x0f0ff0f0, 0xf0f0f0f0, 0x0f0ff0f0, 0xf0f0f0f0, 0x0f0f0f0f, 0xf0f0f0f0, 0x0f0f0f0f, 0xf0f00f0f, 0xf0f00f0f, 0xf0f00f0f, 0xf0f0f0f0, 0xf0f0f0f0, 0xf0f0f0f0, 0xf0f0ffff, + 0x0f0f0f0f, 0x0f0f0f0f, 0x0f0f0f0f, 0xf0f00f0f, 0x0f0f0f0f, 0x0f0f0f0f, 0xf0f0f0f0, 0x0f0f0f0f, 0x0f0f0f0f, 0xf0f00f0f, 0xf0f00f0f, 0x0f0f0f0f, 0xf0f0f0f0, 0xf0f0f0f0, 0x0f0f0f0f, 0xf0f00f0f, + 0x0f0f0f0f, 0xf0f00f0f, 0xf0f0f0f0, 0x0f0f0f0f, 0xf0f0f0f0, 0xf0f00f0f, 0xf0f00f0f, 0xf0f00f0f, 0x0f0ff0f0, 0xf0f0f0f0, 0xf0f0f0f0, 0x0f0ff0f0, 0x0f0f0f0f, 0x0f0f0f0f, 0xf0f0f0f0, 0xf0f00f0f, + 0x0f0f0f0f, 0xf0f00f0f, 0x0f0ff0f0, 0x0f0f0f0f, 0xf0f0f0f0, 0x0f0ff0f0, 0xf0f00f0f, 0xf0f00f0f, 0xf0f0f0f0, 0x0f0ff0f0, 0xf0f0f0f0, 0xf0f00f0f, 0xf0f0f0f0, 0x0f0f0f0f, 0x0f0ff0f0, 0xf0f00f0f, + 0xf0f00f0f, 0x0f0ff0f0, 0x0f0ff0f0, 0xf0f0f0f0, 0x0f0ff0f0, 0xf0f0f0f0, 0x0f0f0f0f, 0xf0f0f0f0, 0x0f0f0f0f, 0xf0f00f0f, 0xf0f00f0f, 0xf0f00f0f, 0xf0f0f0f0, 0xf0f0f0f0, 0xf0f0f0f0, 0xf0f0ffff, + 0x0f0f0f0f, 0x0f0f0f0f, 0x0f0f0f0f, 0xf0f00f0f, 0x0f0f0f0f, 0x0f0f0f0f, 0xf0f0f0f0, 0x0f0f0f0f, 0x0f0f0f0f, 0xf0f00f0f, 0xf0f00f0f, 0x0f0f0f0f, 0xf0f0f0f0, 0xf0f0f0f0, 0x0f0f0f0f, 0xf0f00f0f, + 0x0f0f0f0f, 0xf0f00f0f, 0xf0f0f0f0, 0x0f0f0f0f, 0xf0f0f0f0, 0xf0f00f0f, 0xf0f00f0f, 0xf0f00f0f, 0x0f0ff0f0, 0xf0f0f0f0, 0xf0f0f0f0, 0x0f0ff0f0, 0x0f0f0f0f, 0x0f0f0f0f, 0xf0f0f0f0, 0xf0f00f0f, + 0x0f0f0f0f, 0xf0f00f0f, 0x0f0ff0f0, 0x0f0f0f0f, 0xf0f0f0f0, 0x0f0ff0f0, 0xf0f00f0f, 0xf0f00f0f, 0xf0f0f0f0, 0x0f0ff0f0, 0xf0f0f0f0, 0xf0f00f0f, 0xf0f0f0f0, 0x0f0f0f0f, 0x0f0ff0f0, 0xf0f00f0f, + 0xf0f00f0f, 0x0f0ff0f0, 0x0f0ff0f0, 0xf0f0f0f0, 0x0f0ff0f0, 0xf0f0f0f0, 0x0f0f0f0f, 0xf0f0f0f0, 0x0f0f0f0f, 0xf0f00f0f, 0xf0f00f0f, 0xf0f00f0f, 0xf0f0f0f0, 0xf0f0f0f0, 0xf0f0f0f0, 0xf0f0ffff, + 0x0f0f0f0f, 0x0f0f0f0f, 0x0f0f0f0f, 0xf0f00f0f, 0x0f0f0f0f, 0x0f0f0f0f, 0xf0f0f0f0, 0x0f0f0f0f, 0x0f0f0f0f, 0xf0f00f0f, 0xf0f00f0f, 0x0f0f0f0f, 0xf0f0f0f0, 0xf0f0f0f0, 0x0f0f0f0f, 0xf0f00f0f, + 0x0f0f0f0f, 0xf0f00f0f, 0xf0f0f0f0, 0x0f0f0f0f, 0xf0f0f0f0, 0xf0f00f0f, 0xf0f00f0f, 0xf0f00f0f, 0x0f0ff0f0, 0xf0f0f0f0, 0xf0f0f0f0, 0x0f0ff0f0, 0x0f0f0f0f, 0x0f0f0f0f, 0xf0f0f0f0, 0xf0f00f0f, + 0x0f0f0f0f, 0xf0f00f0f, 0x0f0ff0f0, 0x0f0f0f0f, 0xf0f0f0f0, 0x0f0ff0f0, 0xf0f00f0f, 0xf0f00f0f, 0xf0f0f0f0, 0x0f0ff0f0, 0xf0f0f0f0, 0xf0f00f0f, 0xf0f0f0f0, 0x0f0f0f0f, 0x0f0ff0f0, 0xf0f00f0f, + 0xf0f00f0f, 0x0f0ff0f0, 0x0f0ff0f0, 0xf0f0f0f0, 0x0f0ff0f0, 0xf0f0f0f0, 0x0f0f0f0f, 0xf0f0f0f0, 0x0f0f0f0f, 0xf0f00f0f, 0xf0f00f0f, 0xf0f00f0f, 0xf0f0f0f0, 0xf0f0f0f0, 0xf0f0f0f0, 0xf0f0ffff, + 0x0f0f0f0f, 0x0f0f0f0f, 0x0f0f0f0f, 0xf0f00f0f, 0x0f0f0f0f, 0x0f0f0f0f, 0xf0f0f0f0, 0x0f0f0f0f, 0x0f0f0f0f, 0xf0f00f0f, 0xf0f00f0f, 0x0f0f0f0f, 0xf0f0f0f0, 0xf0f0f0f0, 0x0f0f0f0f, 0xf0f00f0f, + 0x0f0f0f0f, 0xf0f00f0f, 0xf0f0f0f0, 0x0f0f0f0f, 0xf0f0f0f0, 0xf0f00f0f, 0xf0f00f0f, 0xf0f00f0f, 0x0f0ff0f0, 0xf0f0f0f0, 0xf0f0f0f0, 0x0f0ff0f0, 0x0f0f0f0f, 0x0f0f0f0f, 0xf0f0f0f0, 0xf0f00f0f, + 0x0f0f0f0f, 0xf0f00f0f, 0x0f0ff0f0, 0x0f0f0f0f, 0xf0f0f0f0, 0x0f0ff0f0, 0xf0f00f0f, 0xf0f00f0f, 0xf0f0f0f0, 0x0f0ff0f0, 0xf0f0f0f0, 0xf0f00f0f, 0xf0f0f0f0, 0x0f0f0f0f, 0x0f0ff0f0, 0xf0f00f0f, + 0xf0f00f0f, 0x0f0ff0f0, 0x0f0ff0f0, 0xf0f0f0f0, 0x0f0ff0f0, 0xf0f0f0f0, 0x0f0f0f0f, 0xf0f0f0f0, 0x0f0f0f0f, 0xf0f00f0f, 0xf0f00f0f, 0xf0f00f0f, 0xf0f0f0f0, 0xf0f0f0f0, 0xf0f0f0f0, 0xf0f0ffff, + 0x0f0f0f0f, 0x0f0f0f0f, 0x0f0f0f0f, 0xf0f00f0f, 0x0f0f0f0f, 0x0f0f0f0f, 0xf0f0f0f0, 0x0f0f0f0f, 0x0f0f0f0f, 0xf0f00f0f, 0xf0f00f0f, 0x0f0f0f0f, 0xf0f0f0f0, 0xf0f0f0f0, 0x0f0f0f0f, 0xf0f00f0f, + 0x0f0f0f0f, 0xf0f00f0f, 0xf0f0f0f0, 0x0f0f0f0f, 0xf0f0f0f0, 0xf0f00f0f, 0xf0f00f0f, 0xf0f00f0f, 0x0f0ff0f0, 0xf0f0f0f0, 0xf0f0f0f0, 0x0f0ff0f0, 0x0f0f0f0f, 0x0f0f0f0f, 0xf0f0f0f0, 0xf0f00f0f, + 0x0f0f0f0f, 0xf0f00f0f, 0x0f0ff0f0, 0x0f0f0f0f, 0xf0f0f0f0, 0x0f0ff0f0, 0xf0f00f0f, 0xf0f00f0f, 0xf0f0f0f0, 0x0f0ff0f0, 0xf0f0f0f0, 0xf0f00f0f, 0xf0f0f0f0, 0x0f0f0f0f, 0x0f0ff0f0, 0xf0f00f0f, + 0xf0f00f0f, 0x0f0ff0f0, 0x0f0ff0f0, 0xf0f0f0f0, 0x0f0ff0f0, 0xf0f0f0f0, 0x0f0f0f0f, 0xf0f0f0f0, 0x0f0f0f0f, 0xf0f00f0f, 0xf0f00f0f, 0xf0f00f0f, 0xf0f0f0f0, 0xf0f0f0f0, 0xf0f0f0f0, 0xf0f0ffff, + 0x0f0f0f0f, 0x0f0f0f0f, 0x0f0f0f0f, 0xf0f00f0f, 0x0f0f0f0f, 0x0f0f0f0f, 0xf0f0f0f0, 0x0f0f0f0f, 0x0f0f0f0f, 0xf0f00f0f, 0xf0f00f0f, 0x0f0f0f0f, 0xf0f0f0f0, 0xf0f0f0f0, 0x0f0f0f0f, 0xf0f00f0f, + 0x0f0f0f0f, 0xf0f00f0f, 0xf0f0f0f0, 0x0f0f0f0f, 0xf0f0f0f0, 0xf0f00f0f, 0xf0f00f0f, 0xf0f00f0f, 0x0f0ff0f0, 0xf0f0f0f0, 0xf0f0f0f0, 0x0f0ff0f0, 0x0f0f0f0f, 0x0f0f0f0f, 0xf0f0f0f0, 0xf0f00f0f, + 0x0f0f0f0f, 0xf0f00f0f, 0x0f0ff0f0, 0x0f0f0f0f, 0xf0f0f0f0, 0x0f0ff0f0, 0xf0f00f0f, 0xf0f00f0f, 0xf0f0f0f0, 0x0f0ff0f0, 0xf0f0f0f0, 0xf0f00f0f, 0xf0f0f0f0, 0x0f0f0f0f, 0x0f0ff0f0, 0xf0f00f0f, + 0xf0f00f0f, 0x0f0ff0f0, 0x0f0ff0f0, 0xf0f0f0f0, 0x0f0ff0f0, 0xf0f0f0f0, 0x0f0f0f0f, 0xf0f0f0f0, 0x0f0f0f0f, 0xf0f00f0f, 0xf0f00f0f, 0xf0f00f0f, 0xf0f0f0f0, 0xf0f0f0f0, 0xf0f0f0f0, 0xf0f0ffff, + 0x0f0f0f0f, 0x0f0f0f0f, 0x0f0f0f0f, 0xf0f00f0f, 0x0f0f0f0f, 0x0f0f0f0f, 0xf0f0f0f0, 0x0f0f0f0f, 0x0f0f0f0f, 0xf0f00f0f, 0xf0f00f0f, 0x0f0f0f0f, 0xf0f0f0f0, 0xf0f0f0f0, 0x0f0f0f0f, 0xf0f00f0f, + 0x0f0f0f0f, 0xf0f00f0f, 0xf0f0f0f0, 0x0f0f0f0f, 0xf0f0f0f0, 0xf0f00f0f, 0xf0f00f0f, 0xf0f00f0f, 0x0f0ff0f0, 0xf0f0f0f0, 0xf0f0f0f0, 0x0f0ff0f0, 0x0f0f0f0f, 0x0f0f0f0f, 0xf0f0f0f0, 0xf0f00f0f, + 0x0f0f0f0f, 0xf0f00f0f, 0x0f0ff0f0, 0x0f0f0f0f, 0xf0f0f0f0, 0x0f0ff0f0, 0xf0f00f0f, 0xf0f00f0f, 0xf0f0f0f0, 0x0f0ff0f0, 0xf0f0f0f0, 0xf0f00f0f, 0xf0f0f0f0, 0x0f0f0f0f, 0x0f0ff0f0, 0xf0f00f0f, + 0xf0f00f0f, 0x0f0ff0f0, 0x0f0ff0f0, 0xf0f0f0f0, 0x0f0ff0f0, 0xf0f0f0f0, 0x0f0f0f0f, 0xf0f0f0f0, 0x0f0f0f0f, 0xf0f00f0f, 0xf0f00f0f, 0xf0f00f0f, 0xf0f0f0f0, 0xf0f0f0f0, 0xf0f0f0f0, 0xf0f0ffff, + 0x0f0f0f0f, 0x0f0f0f0f, 0x0f0f0f0f, 0xf0f00f0f, 0x0f0f0f0f, 0x0f0f0f0f, 0xf0f0f0f0, 0x0f0f0f0f, 0x0f0f0f0f, 0xf0f00f0f, 0xf0f00f0f, 0x0f0f0f0f, 0xf0f0f0f0, 0xf0f0f0f0, 0x0f0f0f0f, 0xf0f00f0f, + 0x0f0f0f0f, 0xf0f00f0f, 0xf0f0f0f0, 0x0f0f0f0f, 0xf0f0f0f0, 0xf0f00f0f, 0xf0f00f0f, 0xf0f00f0f, 0x0f0ff0f0, 0xf0f0f0f0, 0xf0f0f0f0, 0x0f0ff0f0, 0x0f0f0f0f, 0x0f0f0f0f, 0xf0f0f0f0, 0xf0f00f0f, + 0x0f0f0f0f, 0xf0f00f0f, 0x0f0ff0f0, 0x0f0f0f0f, 0xf0f0f0f0, 0x0f0ff0f0, 0xf0f00f0f, 0xf0f00f0f, 0xf0f0f0f0, 0x0f0ff0f0, 0xf0f0f0f0, 0xf0f00f0f, 0xf0f0f0f0, 0x0f0f0f0f, 0x0f0ff0f0, 0xf0f00f0f, + 0xf0f00f0f, 0x0f0ff0f0, 0x0f0ff0f0, 0xf0f0f0f0, 0x0f0ff0f0, 0xf0f0f0f0, 0x0f0f0f0f, 0xf0f0f0f0, 0x0f0f0f0f, 0xf0f00f0f, 0xf0f00f0f, 0xf0f00f0f, 0xf0f0f0f0, 0xf0f0f0f0, 0xf0f0f0f0, 0xf0f0ffff, + 0x0f0f0f0f, 0x0f0f0f0f, 0x0f0f0f0f, 0xf0f00f0f, 0x0f0f0f0f, 0x0f0f0f0f, 0xf0f0f0f0, 0x0f0f0f0f, 0x0f0f0f0f, 0xf0f00f0f, 0xf0f00f0f, 0x0f0f0f0f, 0xf0f0f0f0, 0xf0f0f0f0, 0x0f0f0f0f, 0xf0f00f0f, + 0x0f0f0f0f, 0xf0f00f0f, 0xf0f0f0f0, 0x0f0f0f0f, 0xf0f0f0f0, 0xf0f00f0f, 0xf0f00f0f, 0xf0f00f0f, 0x0f0ff0f0, 0xf0f0f0f0, 0xf0f0f0f0, 0x0f0ff0f0, 0x0f0f0f0f, 0x0f0f0f0f, 0xf0f0f0f0, 0xf0f00f0f, + 0x0f0f0f0f, 0xf0f00f0f, 0x0f0ff0f0, 0x0f0f0f0f, 0xf0f0f0f0, 0x0f0ff0f0, 0xf0f00f0f, 0xf0f00f0f, 0xf0f0f0f0, 0x0f0ff0f0, 0xf0f0f0f0, 0xf0f00f0f, 0xf0f0f0f0, 0x0f0f0f0f, 0x0f0ff0f0, 0xf0f00f0f, + 0xf0f00f0f, 0x0f0ff0f0, 0x0f0ff0f0, 0xf0f0f0f0, 0x0f0ff0f0, 0xf0f0f0f0, 0x0f0f0f0f, 0xf0f0f0f0, 0x0f0f0f0f, 0xf0f00f0f, 0xf0f00f0f, 0xf0f00f0f, 0xf0f0f0f0, 0xf0f0f0f0, 0xf0f0f0f0, 0xf0f0ffff, + 0x0f0f0f0f, 0x0f0f0f0f, 0x0f0f0f0f, 0xf0f00f0f, 0x0f0f0f0f, 0x0f0f0f0f, 0xf0f0f0f0, 0x0f0f0f0f, 0x0f0f0f0f, 0xf0f00f0f, 0xf0f00f0f, 0x0f0f0f0f, 0xf0f0f0f0, 0xf0f0f0f0, 0x0f0f0f0f, 0xf0f00f0f, + 0x0f0f0f0f, 0xf0f00f0f, 0xf0f0f0f0, 0x0f0f0f0f, 0xf0f0f0f0, 0xf0f00f0f, 0xf0f00f0f, 0xf0f00f0f, 0x0f0ff0f0, 0xf0f0f0f0, 0xf0f0f0f0, 0x0f0ff0f0, 0x0f0f0f0f, 0x0f0f0f0f, 0xf0f0f0f0, 0xf0f00f0f, + 0x0f0f0f0f, 0xf0f00f0f, 0x0f0ff0f0, 0x0f0f0f0f, 0xf0f0f0f0, 0x0f0ff0f0, 0xf0f00f0f, 0xf0f00f0f, 0xf0f0f0f0, 0x0f0ff0f0, 0xf0f0f0f0, 0xf0f00f0f, 0xf0f0f0f0, 0x0f0f0f0f, 0x0f0ff0f0, 0xf0f00f0f, + 0xf0f00f0f, 0x0f0ff0f0, 0x0f0ff0f0, 0xf0f0f0f0, 0x0f0ff0f0, 0xf0f0f0f0, 0x0f0f0f0f, 0xf0f0f0f0, 0x0f0f0f0f, 0xf0f00f0f, 0xf0f00f0f, 0xf0f00f0f, 0xf0f0f0f0, 0xf0f0f0f0, 0xf0f0f0f0, 0xf0f0ffff, + 0x0f0f0f0f, 0x0f0f0f0f, 0x0f0f0f0f, 0xf0f00f0f, 0x0f0f0f0f, 0x0f0f0f0f, 0xf0f0f0f0, 0x0f0f0f0f, 0x0f0f0f0f, 0xf0f00f0f, 0xf0f00f0f, 0x0f0f0f0f, 0xf0f0f0f0, 0xf0f0f0f0, 0x0f0f0f0f, 0xf0f00f0f, + 0x0f0f0f0f, 0xf0f00f0f, 0xf0f0f0f0, 0x0f0f0f0f, 0xf0f0f0f0, 0xf0f00f0f, 0xf0f00f0f, 0xf0f00f0f, 0x0f0ff0f0, 0xf0f0f0f0, 0xf0f0f0f0, 0x0f0ff0f0, 0x0f0f0f0f, 0x0f0f0f0f, 0xf0f0f0f0, 0xf0f00f0f, + 0x0f0f0f0f, 0xf0f00f0f, 0x0f0ff0f0, 0x0f0f0f0f, 0xf0f0f0f0, 0x0f0ff0f0, 0xf0f00f0f, 0xf0f00f0f, 0xf0f0f0f0, 0x0f0ff0f0, 0xf0f0f0f0, 0xf0f00f0f, 0xf0f0f0f0, 0x0f0f0f0f, 0x0f0ff0f0, 0xf0f00f0f, + 0xf0f00f0f, 0x0f0ff0f0, 0x0f0ff0f0, 0xf0f0f0f0, 0x0f0ff0f0, 0xf0f0f0f0, 0x0f0f0f0f, 0xf0f0f0f0, 0x0f0f0f0f, 0xf0f00f0f, 0xf0f00f0f, 0xf0f00f0f, 0xf0f0f0f0, 0xf0f0f0f0, 0xf0f0f0f0, 0xf0f0ffff, + 0x0f0f0f0f, 0x0f0f0f0f, 0x0f0f0f0f, 0xf0f00f0f, 0x0f0f0f0f, 0x0f0f0f0f, 0xf0f0f0f0, 0x0f0f0f0f, 0x0f0f0f0f, 0xf0f00f0f, 0xf0f00f0f, 0x0f0f0f0f, 0xf0f0f0f0, 0xf0f0f0f0, 0x0f0f0f0f, 0xf0f00f0f, + 0x0f0f0f0f, 0xf0f00f0f, 0xf0f0f0f0, 0x0f0f0f0f, 0xf0f0f0f0, 0xf0f00f0f, 0xf0f00f0f, 0xf0f00f0f, 0x0f0ff0f0, 0xf0f0f0f0, 0xf0f0f0f0, 0x0f0ff0f0, 0x0f0f0f0f, 0x0f0f0f0f, 0xf0f0f0f0, 0xf0f00f0f, + 0x0f0f0f0f, 0xf0f00f0f, 0x0f0ff0f0, 0x0f0f0f0f, 0xf0f0f0f0, 0x0f0ff0f0, 0xf0f00f0f, 0xf0f00f0f, 0xf0f0f0f0, 0x0f0ff0f0, 0xf0f0f0f0, 0xf0f00f0f, 0xf0f0f0f0, 0x0f0f0f0f, 0x0f0ff0f0, 0xf0f00f0f, + 0xf0f00f0f, 0x0f0ff0f0, 0x0f0ff0f0, 0xf0f0f0f0, 0x0f0ff0f0, 0xf0f0f0f0, 0x0f0f0f0f, 0xf0f0f0f0, 0x0f0f0f0f, 0xf0f00f0f, 0xf0f00f0f, 0xf0f00f0f, 0xf0f0f0f0, 0xf0f0f0f0, 0xf0f0f0f0, 0xf0f0ffff, + 0x0f0f0f0f, 0x0f0f0f0f, 0x0f0f0f0f, 0xf0f00f0f, 0x0f0f0f0f, 0x0f0f0f0f, 0xf0f0f0f0, 0x0f0f0f0f, 0x0f0f0f0f, 0xf0f00f0f, 0xf0f00f0f, 0x0f0f0f0f, 0xf0f0f0f0, 0xf0f0f0f0, 0x0f0f0f0f, 0xf0f00f0f, + 0x0f0f0f0f, 0xf0f00f0f, 0xf0f0f0f0, 0x0f0f0f0f, 0xf0f0f0f0, 0xf0f00f0f, 0xf0f00f0f, 0xf0f00f0f, 0x0f0ff0f0, 0xf0f0f0f0, 0xf0f0f0f0, 0x0f0ff0f0, 0x0f0f0f0f, 0x0f0f0f0f, 0xf0f0f0f0, 0xf0f00f0f, + 0x0f0f0f0f, 0xf0f00f0f, 0x0f0ff0f0, 0x0f0f0f0f, 0xf0f0f0f0, 0x0f0ff0f0, 0xf0f00f0f, 0xf0f00f0f, 0xf0f0f0f0, 0x0f0ff0f0, 0xf0f0f0f0, 0xf0f00f0f, 0xf0f0f0f0, 0x0f0f0f0f, 0x0f0ff0f0, 0xf0f00f0f, + 0xf0f00f0f, 0x0f0ff0f0, 0x0f0ff0f0, 0xf0f0f0f0, 0x0f0ff0f0, 0xf0f0f0f0, 0x0f0f0f0f, 0xf0f0f0f0, 0x0f0f0f0f, 0xf0f00f0f, 0xf0f00f0f, 0xf0f00f0f, 0xf0f0f0f0, 0xf0f0f0f0, 0xf0f0f0f0, 0xf0f0ffff, + 0x0f0f0f0f, 0x0f0f0f0f, 0x0f0f0f0f, 0xf0f00f0f, 0x0f0f0f0f, 0x0f0f0f0f, 0xf0f0f0f0, 0x0f0f0f0f, 0x0f0f0f0f, 0xf0f00f0f, 0xf0f00f0f, 0x0f0f0f0f, 0xf0f0f0f0, 0xf0f0f0f0, 0x0f0f0f0f, 0xf0f00f0f, + 0x0f0f0f0f, 0xf0f00f0f, 0xf0f0f0f0, 0x0f0f0f0f, 0xf0f0f0f0, 0xf0f00f0f, 0xf0f00f0f, 0xf0f00f0f, 0x0f0ff0f0, 0xf0f0f0f0, 0xf0f0f0f0, 0x0f0ff0f0, 0x0f0f0f0f, 0x0f0f0f0f, 0xf0f0f0f0, 0xf0f00f0f, + 0x0f0f0f0f, 0xf0f00f0f, 0x0f0ff0f0, 0x0f0f0f0f, 0xf0f0f0f0, 0x0f0ff0f0, 0xf0f00f0f, 0xf0f00f0f, 0xf0f0f0f0, 0x0f0ff0f0, 0xf0f0f0f0, 0xf0f00f0f, 0xf0f0f0f0, 0x0f0f0f0f, 0x0f0ff0f0, 0xf0f00f0f, + 0xf0f00f0f, 0x0f0ff0f0, 0x0f0ff0f0, 0xf0f0f0f0, 0x0f0ff0f0, 0xf0f0f0f0, 0x0f0f0f0f, 0xf0f0f0f0, 0x0f0f0f0f, 0xf0f00f0f, 0xf0f00f0f, 0xf0f00f0f, 0xf0f0f0f0, 0xf0f0f0f0, 0xf0f0f0f0, 0xf0f0ffff, + 0x0f0f0f0f, 0x0f0f0f0f, 0x0f0f0f0f, 0xf0f00f0f, 0x0f0f0f0f, 0x0f0f0f0f, 0xf0f0f0f0, 0x0f0f0f0f, 0x0f0f0f0f, 0xf0f00f0f, 0xf0f00f0f, 0x0f0f0f0f, 0xf0f0f0f0, 0xf0f0f0f0, 0x0f0f0f0f, 0xf0f00f0f, + 0x0f0f0f0f, 0xf0f00f0f, 0xf0f0f0f0, 0x0f0f0f0f, 0xf0f0f0f0, 0xf0f00f0f, 0xf0f00f0f, 0xf0f00f0f, 0x0f0ff0f0, 0xf0f0f0f0, 0xf0f0f0f0, 0x0f0ff0f0, 0x0f0f0f0f, 0x0f0f0f0f, 0xf0f0f0f0, 0xf0f00f0f, + 0x0f0f0f0f, 0xf0f00f0f, 0x0f0ff0f0, 0x0f0f0f0f, 0xf0f0f0f0, 0x0f0ff0f0, 0xf0f00f0f, 0xf0f00f0f, 0xf0f0f0f0, 0x0f0ff0f0, 0xf0f0f0f0, 0xf0f00f0f, 0xf0f0f0f0, 0x0f0f0f0f, 0x0f0ff0f0, 0xf0f00f0f, + 0xf0f00f0f, 0x0f0ff0f0, 0x0f0ff0f0, 0xf0f0f0f0, 0x0f0ff0f0, 0xf0f0f0f0, 0x0f0f0f0f, 0xf0f0f0f0, 0x0f0f0f0f, 0xf0f00f0f, 0xf0f00f0f, 0xf0f00f0f, 0xf0f0f0f0, 0xf0f0f0f0, 0xf0f0f0f0, 0xf0f0ffff, +}; + +// 4096 bytes, 256 byte aligned +static unsigned int DbiPrbs7[] = +{ + 0xffffffff, 0xffffffff, 0xffffffff, 0x0000ffff, 0xffffffff, 0xffffffff, 0x00000000, 0xffffffff, 0xffffffff, 0x0000ffff, 0x0000ffff, 0xffffffff, 0x00000000, 0x00000000, 0xffffffff, 0x0000ffff, + 0xffffffff, 0x0000ffff, 0x00000000, 0xffffffff, 0x00000000, 0x0000ffff, 0x0000ffff, 0x0000ffff, 0xffff0000, 0x00000000, 0x00000000, 0xffff0000, 0xffffffff, 0xffffffff, 0x00000000, 0x0000ffff, + 0xffffffff, 0x0000ffff, 0xffff0000, 0xffffffff, 0x00000000, 0xffff0000, 0x0000ffff, 0x0000ffff, 0x00000000, 0xffff0000, 0x00000000, 0x0000ffff, 0x00000000, 0xffffffff, 0xffff0000, 0x0000ffff, + 0x0000ffff, 0xffff0000, 0xffff0000, 0x00000000, 0xffff0000, 0x00000000, 0xffffffff, 0x00000000, 0xffffffff, 0x0000ffff, 0x0000ffff, 0x0000ffff, 0x00000000, 0x00000000, 0x00000000, 0x0000ffff, + 0xffffffff, 0xffffffff, 0xffffffff, 0x0000ffff, 0xffffffff, 0xffffffff, 0x00000000, 0xffffffff, 0xffffffff, 0x0000ffff, 0x0000ffff, 0xffffffff, 0x00000000, 0x00000000, 0xffffffff, 0x0000ffff, + 0xffffffff, 0x0000ffff, 0x00000000, 0xffffffff, 0x00000000, 0x0000ffff, 0x0000ffff, 0x0000ffff, 0xffff0000, 0x00000000, 0x00000000, 0xffff0000, 0xffffffff, 0xffffffff, 0x00000000, 0x0000ffff, + 0xffffffff, 0x0000ffff, 0xffff0000, 0xffffffff, 0x00000000, 0xffff0000, 0x0000ffff, 0x0000ffff, 0x00000000, 0xffff0000, 0x00000000, 0x0000ffff, 0x00000000, 0xffffffff, 0xffff0000, 0x0000ffff, + 0x0000ffff, 0xffff0000, 0xffff0000, 0x00000000, 0xffff0000, 0x00000000, 0xffffffff, 0x00000000, 0xffffffff, 0x0000ffff, 0x0000ffff, 0x0000ffff, 0x00000000, 0x00000000, 0x00000000, 0x0000ffff, + 0xffffffff, 0xffffffff, 0xffffffff, 0x0000ffff, 0xffffffff, 0xffffffff, 0x00000000, 0xffffffff, 0xffffffff, 0x0000ffff, 0x0000ffff, 0xffffffff, 0x00000000, 0x00000000, 0xffffffff, 0x0000ffff, + 0xffffffff, 0x0000ffff, 0x00000000, 0xffffffff, 0x00000000, 0x0000ffff, 0x0000ffff, 0x0000ffff, 0xffff0000, 0x00000000, 0x00000000, 0xffff0000, 0xffffffff, 0xffffffff, 0x00000000, 0x0000ffff, + 0xffffffff, 0x0000ffff, 0xffff0000, 0xffffffff, 0x00000000, 0xffff0000, 0x0000ffff, 0x0000ffff, 0x00000000, 0xffff0000, 0x00000000, 0x0000ffff, 0x00000000, 0xffffffff, 0xffff0000, 0x0000ffff, + 0x0000ffff, 0xffff0000, 0xffff0000, 0x00000000, 0xffff0000, 0x00000000, 0xffffffff, 0x00000000, 0xffffffff, 0x0000ffff, 0x0000ffff, 0x0000ffff, 0x00000000, 0x00000000, 0x00000000, 0x0000ffff, + 0xffffffff, 0xffffffff, 0xffffffff, 0x0000ffff, 0xffffffff, 0xffffffff, 0x00000000, 0xffffffff, 0xffffffff, 0x0000ffff, 0x0000ffff, 0xffffffff, 0x00000000, 0x00000000, 0xffffffff, 0x0000ffff, + 0xffffffff, 0x0000ffff, 0x00000000, 0xffffffff, 0x00000000, 0x0000ffff, 0x0000ffff, 0x0000ffff, 0xffff0000, 0x00000000, 0x00000000, 0xffff0000, 0xffffffff, 0xffffffff, 0x00000000, 0x0000ffff, + 0xffffffff, 0x0000ffff, 0xffff0000, 0xffffffff, 0x00000000, 0xffff0000, 0x0000ffff, 0x0000ffff, 0x00000000, 0xffff0000, 0x00000000, 0x0000ffff, 0x00000000, 0xffffffff, 0xffff0000, 0x0000ffff, + 0x0000ffff, 0xffff0000, 0xffff0000, 0x00000000, 0xffff0000, 0x00000000, 0xffffffff, 0x00000000, 0xffffffff, 0x0000ffff, 0x0000ffff, 0x0000ffff, 0x00000000, 0x00000000, 0x00000000, 0x0000ffff, + 0xffffffff, 0xffffffff, 0xffffffff, 0x0000ffff, 0xffffffff, 0xffffffff, 0x00000000, 0xffffffff, 0xffffffff, 0x0000ffff, 0x0000ffff, 0xffffffff, 0x00000000, 0x00000000, 0xffffffff, 0x0000ffff, + 0xffffffff, 0x0000ffff, 0x00000000, 0xffffffff, 0x00000000, 0x0000ffff, 0x0000ffff, 0x0000ffff, 0xffff0000, 0x00000000, 0x00000000, 0xffff0000, 0xffffffff, 0xffffffff, 0x00000000, 0x0000ffff, + 0xffffffff, 0x0000ffff, 0xffff0000, 0xffffffff, 0x00000000, 0xffff0000, 0x0000ffff, 0x0000ffff, 0x00000000, 0xffff0000, 0x00000000, 0x0000ffff, 0x00000000, 0xffffffff, 0xffff0000, 0x0000ffff, + 0x0000ffff, 0xffff0000, 0xffff0000, 0x00000000, 0xffff0000, 0x00000000, 0xffffffff, 0x00000000, 0xffffffff, 0x0000ffff, 0x0000ffff, 0x0000ffff, 0x00000000, 0x00000000, 0x00000000, 0x0000ffff, + 0xffffffff, 0xffffffff, 0xffffffff, 0x0000ffff, 0xffffffff, 0xffffffff, 0x00000000, 0xffffffff, 0xffffffff, 0x0000ffff, 0x0000ffff, 0xffffffff, 0x00000000, 0x00000000, 0xffffffff, 0x0000ffff, + 0xffffffff, 0x0000ffff, 0x00000000, 0xffffffff, 0x00000000, 0x0000ffff, 0x0000ffff, 0x0000ffff, 0xffff0000, 0x00000000, 0x00000000, 0xffff0000, 0xffffffff, 0xffffffff, 0x00000000, 0x0000ffff, + 0xffffffff, 0x0000ffff, 0xffff0000, 0xffffffff, 0x00000000, 0xffff0000, 0x0000ffff, 0x0000ffff, 0x00000000, 0xffff0000, 0x00000000, 0x0000ffff, 0x00000000, 0xffffffff, 0xffff0000, 0x0000ffff, + 0x0000ffff, 0xffff0000, 0xffff0000, 0x00000000, 0xffff0000, 0x00000000, 0xffffffff, 0x00000000, 0xffffffff, 0x0000ffff, 0x0000ffff, 0x0000ffff, 0x00000000, 0x00000000, 0x00000000, 0x0000ffff, + 0xffffffff, 0xffffffff, 0xffffffff, 0x0000ffff, 0xffffffff, 0xffffffff, 0x00000000, 0xffffffff, 0xffffffff, 0x0000ffff, 0x0000ffff, 0xffffffff, 0x00000000, 0x00000000, 0xffffffff, 0x0000ffff, + 0xffffffff, 0x0000ffff, 0x00000000, 0xffffffff, 0x00000000, 0x0000ffff, 0x0000ffff, 0x0000ffff, 0xffff0000, 0x00000000, 0x00000000, 0xffff0000, 0xffffffff, 0xffffffff, 0x00000000, 0x0000ffff, + 0xffffffff, 0x0000ffff, 0xffff0000, 0xffffffff, 0x00000000, 0xffff0000, 0x0000ffff, 0x0000ffff, 0x00000000, 0xffff0000, 0x00000000, 0x0000ffff, 0x00000000, 0xffffffff, 0xffff0000, 0x0000ffff, + 0x0000ffff, 0xffff0000, 0xffff0000, 0x00000000, 0xffff0000, 0x00000000, 0xffffffff, 0x00000000, 0xffffffff, 0x0000ffff, 0x0000ffff, 0x0000ffff, 0x00000000, 0x00000000, 0x00000000, 0x0000ffff, + 0xffffffff, 0xffffffff, 0xffffffff, 0x0000ffff, 0xffffffff, 0xffffffff, 0x00000000, 0xffffffff, 0xffffffff, 0x0000ffff, 0x0000ffff, 0xffffffff, 0x00000000, 0x00000000, 0xffffffff, 0x0000ffff, + 0xffffffff, 0x0000ffff, 0x00000000, 0xffffffff, 0x00000000, 0x0000ffff, 0x0000ffff, 0x0000ffff, 0xffff0000, 0x00000000, 0x00000000, 0xffff0000, 0xffffffff, 0xffffffff, 0x00000000, 0x0000ffff, + 0xffffffff, 0x0000ffff, 0xffff0000, 0xffffffff, 0x00000000, 0xffff0000, 0x0000ffff, 0x0000ffff, 0x00000000, 0xffff0000, 0x00000000, 0x0000ffff, 0x00000000, 0xffffffff, 0xffff0000, 0x0000ffff, + 0x0000ffff, 0xffff0000, 0xffff0000, 0x00000000, 0xffff0000, 0x00000000, 0xffffffff, 0x00000000, 0xffffffff, 0x0000ffff, 0x0000ffff, 0x0000ffff, 0x00000000, 0x00000000, 0x00000000, 0x0000ffff, + 0xffffffff, 0xffffffff, 0xffffffff, 0x0000ffff, 0xffffffff, 0xffffffff, 0x00000000, 0xffffffff, 0xffffffff, 0x0000ffff, 0x0000ffff, 0xffffffff, 0x00000000, 0x00000000, 0xffffffff, 0x0000ffff, + 0xffffffff, 0x0000ffff, 0x00000000, 0xffffffff, 0x00000000, 0x0000ffff, 0x0000ffff, 0x0000ffff, 0xffff0000, 0x00000000, 0x00000000, 0xffff0000, 0xffffffff, 0xffffffff, 0x00000000, 0x0000ffff, + 0xffffffff, 0x0000ffff, 0xffff0000, 0xffffffff, 0x00000000, 0xffff0000, 0x0000ffff, 0x0000ffff, 0x00000000, 0xffff0000, 0x00000000, 0x0000ffff, 0x00000000, 0xffffffff, 0xffff0000, 0x0000ffff, + 0x0000ffff, 0xffff0000, 0xffff0000, 0x00000000, 0xffff0000, 0x00000000, 0xffffffff, 0x00000000, 0xffffffff, 0x0000ffff, 0x0000ffff, 0x0000ffff, 0x00000000, 0x00000000, 0x00000000, 0x0000ffff, + 0xffffffff, 0xffffffff, 0xffffffff, 0x0000ffff, 0xffffffff, 0xffffffff, 0x00000000, 0xffffffff, 0xffffffff, 0x0000ffff, 0x0000ffff, 0xffffffff, 0x00000000, 0x00000000, 0xffffffff, 0x0000ffff, + 0xffffffff, 0x0000ffff, 0x00000000, 0xffffffff, 0x00000000, 0x0000ffff, 0x0000ffff, 0x0000ffff, 0xffff0000, 0x00000000, 0x00000000, 0xffff0000, 0xffffffff, 0xffffffff, 0x00000000, 0x0000ffff, + 0xffffffff, 0x0000ffff, 0xffff0000, 0xffffffff, 0x00000000, 0xffff0000, 0x0000ffff, 0x0000ffff, 0x00000000, 0xffff0000, 0x00000000, 0x0000ffff, 0x00000000, 0xffffffff, 0xffff0000, 0x0000ffff, + 0x0000ffff, 0xffff0000, 0xffff0000, 0x00000000, 0xffff0000, 0x00000000, 0xffffffff, 0x00000000, 0xffffffff, 0x0000ffff, 0x0000ffff, 0x0000ffff, 0x00000000, 0x00000000, 0x00000000, 0x0000ffff, + 0xffffffff, 0xffffffff, 0xffffffff, 0x0000ffff, 0xffffffff, 0xffffffff, 0x00000000, 0xffffffff, 0xffffffff, 0x0000ffff, 0x0000ffff, 0xffffffff, 0x00000000, 0x00000000, 0xffffffff, 0x0000ffff, + 0xffffffff, 0x0000ffff, 0x00000000, 0xffffffff, 0x00000000, 0x0000ffff, 0x0000ffff, 0x0000ffff, 0xffff0000, 0x00000000, 0x00000000, 0xffff0000, 0xffffffff, 0xffffffff, 0x00000000, 0x0000ffff, + 0xffffffff, 0x0000ffff, 0xffff0000, 0xffffffff, 0x00000000, 0xffff0000, 0x0000ffff, 0x0000ffff, 0x00000000, 0xffff0000, 0x00000000, 0x0000ffff, 0x00000000, 0xffffffff, 0xffff0000, 0x0000ffff, + 0x0000ffff, 0xffff0000, 0xffff0000, 0x00000000, 0xffff0000, 0x00000000, 0xffffffff, 0x00000000, 0xffffffff, 0x0000ffff, 0x0000ffff, 0x0000ffff, 0x00000000, 0x00000000, 0x00000000, 0x0000ffff, + 0xffffffff, 0xffffffff, 0xffffffff, 0x0000ffff, 0xffffffff, 0xffffffff, 0x00000000, 0xffffffff, 0xffffffff, 0x0000ffff, 0x0000ffff, 0xffffffff, 0x00000000, 0x00000000, 0xffffffff, 0x0000ffff, + 0xffffffff, 0x0000ffff, 0x00000000, 0xffffffff, 0x00000000, 0x0000ffff, 0x0000ffff, 0x0000ffff, 0xffff0000, 0x00000000, 0x00000000, 0xffff0000, 0xffffffff, 0xffffffff, 0x00000000, 0x0000ffff, + 0xffffffff, 0x0000ffff, 0xffff0000, 0xffffffff, 0x00000000, 0xffff0000, 0x0000ffff, 0x0000ffff, 0x00000000, 0xffff0000, 0x00000000, 0x0000ffff, 0x00000000, 0xffffffff, 0xffff0000, 0x0000ffff, + 0x0000ffff, 0xffff0000, 0xffff0000, 0x00000000, 0xffff0000, 0x00000000, 0xffffffff, 0x00000000, 0xffffffff, 0x0000ffff, 0x0000ffff, 0x0000ffff, 0x00000000, 0x00000000, 0x00000000, 0x0000ffff, + 0xffffffff, 0xffffffff, 0xffffffff, 0x0000ffff, 0xffffffff, 0xffffffff, 0x00000000, 0xffffffff, 0xffffffff, 0x0000ffff, 0x0000ffff, 0xffffffff, 0x00000000, 0x00000000, 0xffffffff, 0x0000ffff, + 0xffffffff, 0x0000ffff, 0x00000000, 0xffffffff, 0x00000000, 0x0000ffff, 0x0000ffff, 0x0000ffff, 0xffff0000, 0x00000000, 0x00000000, 0xffff0000, 0xffffffff, 0xffffffff, 0x00000000, 0x0000ffff, + 0xffffffff, 0x0000ffff, 0xffff0000, 0xffffffff, 0x00000000, 0xffff0000, 0x0000ffff, 0x0000ffff, 0x00000000, 0xffff0000, 0x00000000, 0x0000ffff, 0x00000000, 0xffffffff, 0xffff0000, 0x0000ffff, + 0x0000ffff, 0xffff0000, 0xffff0000, 0x00000000, 0xffff0000, 0x00000000, 0xffffffff, 0x00000000, 0xffffffff, 0x0000ffff, 0x0000ffff, 0x0000ffff, 0x00000000, 0x00000000, 0x00000000, 0x0000ffff, + 0xffffffff, 0xffffffff, 0xffffffff, 0x0000ffff, 0xffffffff, 0xffffffff, 0x00000000, 0xffffffff, 0xffffffff, 0x0000ffff, 0x0000ffff, 0xffffffff, 0x00000000, 0x00000000, 0xffffffff, 0x0000ffff, + 0xffffffff, 0x0000ffff, 0x00000000, 0xffffffff, 0x00000000, 0x0000ffff, 0x0000ffff, 0x0000ffff, 0xffff0000, 0x00000000, 0x00000000, 0xffff0000, 0xffffffff, 0xffffffff, 0x00000000, 0x0000ffff, + 0xffffffff, 0x0000ffff, 0xffff0000, 0xffffffff, 0x00000000, 0xffff0000, 0x0000ffff, 0x0000ffff, 0x00000000, 0xffff0000, 0x00000000, 0x0000ffff, 0x00000000, 0xffffffff, 0xffff0000, 0x0000ffff, + 0x0000ffff, 0xffff0000, 0xffff0000, 0x00000000, 0xffff0000, 0x00000000, 0xffffffff, 0x00000000, 0xffffffff, 0x0000ffff, 0x0000ffff, 0x0000ffff, 0x00000000, 0x00000000, 0x00000000, 0x0000ffff, + 0xffffffff, 0xffffffff, 0xffffffff, 0x0000ffff, 0xffffffff, 0xffffffff, 0x00000000, 0xffffffff, 0xffffffff, 0x0000ffff, 0x0000ffff, 0xffffffff, 0x00000000, 0x00000000, 0xffffffff, 0x0000ffff, + 0xffffffff, 0x0000ffff, 0x00000000, 0xffffffff, 0x00000000, 0x0000ffff, 0x0000ffff, 0x0000ffff, 0xffff0000, 0x00000000, 0x00000000, 0xffff0000, 0xffffffff, 0xffffffff, 0x00000000, 0x0000ffff, + 0xffffffff, 0x0000ffff, 0xffff0000, 0xffffffff, 0x00000000, 0xffff0000, 0x0000ffff, 0x0000ffff, 0x00000000, 0xffff0000, 0x00000000, 0x0000ffff, 0x00000000, 0xffffffff, 0xffff0000, 0x0000ffff, + 0x0000ffff, 0xffff0000, 0xffff0000, 0x00000000, 0xffff0000, 0x00000000, 0xffffffff, 0x00000000, 0xffffffff, 0x0000ffff, 0x0000ffff, 0x0000ffff, 0x00000000, 0x00000000, 0x00000000, 0x0000ffff, + 0xffffffff, 0xffffffff, 0xffffffff, 0x0000ffff, 0xffffffff, 0xffffffff, 0x00000000, 0xffffffff, 0xffffffff, 0x0000ffff, 0x0000ffff, 0xffffffff, 0x00000000, 0x00000000, 0xffffffff, 0x0000ffff, + 0xffffffff, 0x0000ffff, 0x00000000, 0xffffffff, 0x00000000, 0x0000ffff, 0x0000ffff, 0x0000ffff, 0xffff0000, 0x00000000, 0x00000000, 0xffff0000, 0xffffffff, 0xffffffff, 0x00000000, 0x0000ffff, + 0xffffffff, 0x0000ffff, 0xffff0000, 0xffffffff, 0x00000000, 0xffff0000, 0x0000ffff, 0x0000ffff, 0x00000000, 0xffff0000, 0x00000000, 0x0000ffff, 0x00000000, 0xffffffff, 0xffff0000, 0x0000ffff, + 0x0000ffff, 0xffff0000, 0xffff0000, 0x00000000, 0xffff0000, 0x00000000, 0xffffffff, 0x00000000, 0xffffffff, 0x0000ffff, 0x0000ffff, 0x0000ffff, 0x00000000, 0x00000000, 0x00000000, 0x0000ffff, +}; + +#pragma pack(pop) + +#endif diff --git a/drivers/gpu/drm/amd/pm/inc/smu_types.h b/drivers/gpu/drm/amd/pm/inc/smu_types.h index 7b585e205a5a..cbf4a58b77d9 100644 --- a/drivers/gpu/drm/amd/pm/inc/smu_types.h +++ b/drivers/gpu/drm/amd/pm/inc/smu_types.h @@ -173,6 +173,9 @@ __SMU_DUMMY_MAP(GmiPwrDnControl), \ __SMU_DUMMY_MAP(DAL_DISABLE_DUMMY_PSTATE_CHANGE), \ __SMU_DUMMY_MAP(DAL_ENABLE_DUMMY_PSTATE_CHANGE), \ + __SMU_DUMMY_MAP(SET_DRIVER_DUMMY_TABLE_DRAM_ADDR_HIGH), \ + __SMU_DUMMY_MAP(SET_DRIVER_DUMMY_TABLE_DRAM_ADDR_LOW), \ + __SMU_DUMMY_MAP(GET_UMC_FW_WA), \ __SMU_DUMMY_MAP(Mode1Reset), \ #undef __SMU_DUMMY_MAP @@ -217,6 +220,7 @@ enum smu_clk_type { __SMU_DUMMY_MAP(DPM_MP0CLK), \ __SMU_DUMMY_MAP(DPM_LINK), \ __SMU_DUMMY_MAP(DPM_DCEFCLK), \ + __SMU_DUMMY_MAP(DPM_XGMI), \ __SMU_DUMMY_MAP(DS_GFXCLK), \ __SMU_DUMMY_MAP(DS_SOCCLK), \ __SMU_DUMMY_MAP(DS_LCLK), \ diff --git a/drivers/gpu/drm/amd/pm/inc/smu_v11_0.h b/drivers/gpu/drm/amd/pm/inc/smu_v11_0.h index 1f9575a4dfe7..2d1c3babaa3a 100644 --- a/drivers/gpu/drm/amd/pm/inc/smu_v11_0.h +++ b/drivers/gpu/drm/amd/pm/inc/smu_v11_0.h @@ -30,8 +30,8 @@ #define SMU11_DRIVER_IF_VERSION_NV10 0x36 #define SMU11_DRIVER_IF_VERSION_NV12 0x36 #define SMU11_DRIVER_IF_VERSION_NV14 0x36 -#define SMU11_DRIVER_IF_VERSION_Sienna_Cichlid 0x35 -#define SMU11_DRIVER_IF_VERSION_Navy_Flounder 0x4 +#define SMU11_DRIVER_IF_VERSION_Sienna_Cichlid 0x39 +#define SMU11_DRIVER_IF_VERSION_Navy_Flounder 0x5 /* MP Apertures */ #define MP0_Public 0x03800000 @@ -280,5 +280,7 @@ int smu_v11_0_gfx_ulv_control(struct smu_context *smu, int smu_v11_0_deep_sleep_control(struct smu_context *smu, bool enablement); +void smu_v11_0_interrupt_work(struct smu_context *smu); + #endif #endif diff --git a/drivers/gpu/drm/amd/pm/inc/smu_v11_0_ppsmc.h b/drivers/gpu/drm/amd/pm/inc/smu_v11_0_ppsmc.h index fa0174dc7e0e..26181b679098 100644 --- a/drivers/gpu/drm/amd/pm/inc/smu_v11_0_ppsmc.h +++ b/drivers/gpu/drm/amd/pm/inc/smu_v11_0_ppsmc.h @@ -125,7 +125,12 @@ #define PPSMC_MSG_SetMGpuFanBoostLimitRpm 0x4C -#define PPSMC_Message_Count 0x4D +#define PPSMC_MSG_SetDriverDummyTableDramAddrHigh 0x4E +#define PPSMC_MSG_SetDriverDummyTableDramAddrLow 0x4F + +#define PPSMC_MSG_GetUMCFWWA 0x50 + +#define PPSMC_Message_Count 0x51 typedef uint32_t PPSMC_Result; typedef uint32_t PPSMC_Msg; diff --git a/drivers/gpu/drm/amd/pm/powerplay/amd_powerplay.c b/drivers/gpu/drm/amd/pm/powerplay/amd_powerplay.c index a6321f2063c1..eab9768029c1 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/amd_powerplay.c +++ b/drivers/gpu/drm/amd/pm/powerplay/amd_powerplay.c @@ -911,6 +911,19 @@ static int pp_set_power_profile_mode(void *handle, long *input, uint32_t size) return ret; } +static int pp_set_fine_grain_clk_vol(void *handle, uint32_t type, long *input, uint32_t size) +{ + struct pp_hwmgr *hwmgr = handle; + + if (!hwmgr || !hwmgr->pm_en) + return -EINVAL; + + if (hwmgr->hwmgr_func->set_fine_grain_clk_vol == NULL) + return 0; + + return hwmgr->hwmgr_func->set_fine_grain_clk_vol(hwmgr, type, input, size); +} + static int pp_odn_edit_dpm_table(void *handle, uint32_t type, long *input, uint32_t size) { struct pp_hwmgr *hwmgr = handle; @@ -920,7 +933,7 @@ static int pp_odn_edit_dpm_table(void *handle, uint32_t type, long *input, uint3 if (hwmgr->hwmgr_func->odn_edit_dpm_table == NULL) { pr_info_ratelimited("%s was not implemented.\n", __func__); - return -EINVAL; + return 0; } return hwmgr->hwmgr_func->odn_edit_dpm_table(hwmgr, type, input, size); @@ -1645,6 +1658,7 @@ static const struct amd_pm_funcs pp_dpm_funcs = { .set_powergating_by_smu = pp_set_powergating_by_smu, .get_power_profile_mode = pp_get_power_profile_mode, .set_power_profile_mode = pp_set_power_profile_mode, + .set_fine_grain_clk_vol = pp_set_fine_grain_clk_vol, .odn_edit_dpm_table = pp_odn_edit_dpm_table, .set_mp1_state = pp_dpm_set_mp1_state, .set_power_limit = pp_set_power_limit, diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu10_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu10_hwmgr.c index 9ee8cf8267c8..cf60f3992303 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu10_hwmgr.c +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu10_hwmgr.c @@ -242,6 +242,34 @@ static int smu10_set_hard_min_fclk_by_freq(struct pp_hwmgr *hwmgr, uint32_t cloc return 0; } +static int smu10_set_hard_min_gfxclk_by_freq(struct pp_hwmgr *hwmgr, uint32_t clock) +{ + struct smu10_hwmgr *smu10_data = (struct smu10_hwmgr *)(hwmgr->backend); + + if (clock && smu10_data->gfx_actual_soft_min_freq != clock) { + smu10_data->gfx_actual_soft_min_freq = clock; + smum_send_msg_to_smc_with_parameter(hwmgr, + PPSMC_MSG_SetHardMinGfxClk, + smu10_data->gfx_actual_soft_min_freq, + NULL); + } + return 0; +} + +static int smu10_set_soft_max_gfxclk_by_freq(struct pp_hwmgr *hwmgr, uint32_t clock) +{ + struct smu10_hwmgr *smu10_data = (struct smu10_hwmgr *)(hwmgr->backend); + + if (clock && smu10_data->gfx_max_freq_limit != (clock * 100)) { + smu10_data->gfx_max_freq_limit = clock * 100; + smum_send_msg_to_smc_with_parameter(hwmgr, + PPSMC_MSG_SetSoftMaxGfxClk, + clock, + NULL); + } + return 0; +} + static int smu10_set_active_display_count(struct pp_hwmgr *hwmgr, uint32_t count) { struct smu10_hwmgr *smu10_data = (struct smu10_hwmgr *)(hwmgr->backend); @@ -527,6 +555,9 @@ static int smu10_hwmgr_backend_init(struct pp_hwmgr *hwmgr) hwmgr->pstate_sclk = SMU10_UMD_PSTATE_GFXCLK * 100; hwmgr->pstate_mclk = SMU10_UMD_PSTATE_FCLK * 100; + /* enable the pp_od_clk_voltage sysfs file */ + hwmgr->od_enabled = 1; + return result; } @@ -563,6 +594,8 @@ static int smu10_dpm_force_dpm_level(struct pp_hwmgr *hwmgr, struct smu10_hwmgr *data = hwmgr->backend; uint32_t min_sclk = hwmgr->display_config->min_core_set_clock; uint32_t min_mclk = hwmgr->display_config->min_mem_set_clock/100; + uint32_t index_fclk = data->clock_vol_info.vdd_dep_on_fclk->count - 1; + uint32_t index_socclk = data->clock_vol_info.vdd_dep_on_socclk->count - 1; if (hwmgr->smu_version < 0x1E3700) { pr_info("smu firmware version too old, can not set dpm level\n"); @@ -648,7 +681,7 @@ static int smu10_dpm_force_dpm_level(struct pp_hwmgr *hwmgr, NULL); smum_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_SetHardMinVcn, - SMU10_UMD_PSTATE_VCE, + SMU10_UMD_PSTATE_PROFILE_VCE, NULL); smum_send_msg_to_smc_with_parameter(hwmgr, @@ -665,7 +698,7 @@ static int smu10_dpm_force_dpm_level(struct pp_hwmgr *hwmgr, NULL); smum_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_SetSoftMaxVcn, - SMU10_UMD_PSTATE_VCE, + SMU10_UMD_PSTATE_PROFILE_VCE, NULL); break; case AMD_DPM_FORCED_LEVEL_AUTO: @@ -676,13 +709,13 @@ static int smu10_dpm_force_dpm_level(struct pp_hwmgr *hwmgr, smum_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_SetHardMinFclkByFreq, hwmgr->display_config->num_display > 3 ? - SMU10_UMD_PSTATE_PEAK_FCLK : + data->clock_vol_info.vdd_dep_on_fclk->entries[0].clk : min_mclk, NULL); smum_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_SetHardMinSocclkByFreq, - SMU10_UMD_PSTATE_MIN_SOCCLK, + data->clock_vol_info.vdd_dep_on_socclk->entries[0].clk, NULL); smum_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_SetHardMinVcn, @@ -695,11 +728,11 @@ static int smu10_dpm_force_dpm_level(struct pp_hwmgr *hwmgr, NULL); smum_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_SetSoftMaxFclkByFreq, - SMU10_UMD_PSTATE_PEAK_FCLK, + data->clock_vol_info.vdd_dep_on_fclk->entries[index_fclk].clk, NULL); smum_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_SetSoftMaxSocclkByFreq, - SMU10_UMD_PSTATE_PEAK_SOCCLK, + data->clock_vol_info.vdd_dep_on_socclk->entries[index_socclk].clk, NULL); smum_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_SetSoftMaxVcn, @@ -947,6 +980,26 @@ static int smu10_print_clock_levels(struct pp_hwmgr *hwmgr, ((mclk_table->entries[i].clk / 100) == now) ? "*" : ""); break; + case OD_SCLK: + if (hwmgr->od_enabled) { + size = sprintf(buf, "%s:\n", "OD_SCLK"); + + size += sprintf(buf + size, "0: %10uMhz\n", + (data->gfx_actual_soft_min_freq > 0) ? data->gfx_actual_soft_min_freq : data->gfx_min_freq_limit/100); + size += sprintf(buf + size, "1: %10uMhz\n", data->gfx_max_freq_limit/100); + } + break; + case OD_RANGE: + if (hwmgr->od_enabled) { + uint32_t min_freq, max_freq = 0; + smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetMinGfxclkFrequency, &min_freq); + smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetMaxGfxclkFrequency, &max_freq); + + size = sprintf(buf, "%s:\n", "OD_RANGE"); + size += sprintf(buf + size, "SCLK: %7uMHz %10uMHz\n", + min_freq, max_freq); + } + break; default: break; } @@ -1181,8 +1234,19 @@ static int smu10_set_watermarks_for_clocks_ranges(struct pp_hwmgr *hwmgr, struct smu10_hwmgr *data = hwmgr->backend; struct dm_pp_wm_sets_with_clock_ranges_soc15 *wm_with_clock_ranges = clock_ranges; Watermarks_t *table = &(data->water_marks_table); + struct amdgpu_device *adev = hwmgr->adev; + int i; smu_set_watermarks_for_clocks_ranges(table,wm_with_clock_ranges); + + if (adev->apu_flags & AMD_APU_IS_RAVEN2) { + for (i = 0; i < NUM_WM_RANGES; i++) + table->WatermarkRow[WM_DCFCLK][i].WmType = (uint8_t)0; + + for (i = 0; i < NUM_WM_RANGES; i++) + table->WatermarkRow[WM_SOCCLK][i].WmType = (uint8_t)0; + } + smum_smc_table_manager(hwmgr, (uint8_t *)table, (uint16_t)SMU10_WMTABLE, false); data->water_marks_exist = true; return 0; @@ -1348,6 +1412,32 @@ static int smu10_asic_reset(struct pp_hwmgr *hwmgr, enum SMU_ASIC_RESET_MODE mod NULL); } +static int smu10_set_fine_grain_clk_vol(struct pp_hwmgr *hwmgr, + enum PP_OD_DPM_TABLE_COMMAND type, + long *input, uint32_t size) +{ + if (!hwmgr->od_enabled) { + pr_err("Fine grain not support\n"); + return -EINVAL; + } + + if (size != 2) { + pr_err("Input parameter number not correct\n"); + return -EINVAL; + } + + if (type == PP_OD_EDIT_SCLK_VDDC_TABLE) { + if (input[0] == 0) + smu10_set_hard_min_gfxclk_by_freq(hwmgr, input[1]); + else if (input[0] == 1) + smu10_set_soft_max_gfxclk_by_freq(hwmgr, input[1]); + else + return -EINVAL; + } + + return 0; +} + static const struct pp_hwmgr_func smu10_hwmgr_funcs = { .backend_init = smu10_hwmgr_backend_init, .backend_fini = smu10_hwmgr_backend_fini, @@ -1388,9 +1478,12 @@ static const struct pp_hwmgr_func smu10_hwmgr_funcs = { .powergate_sdma = smu10_powergate_sdma, .set_hard_min_dcefclk_by_freq = smu10_set_hard_min_dcefclk_by_freq, .set_hard_min_fclk_by_freq = smu10_set_hard_min_fclk_by_freq, + .set_hard_min_gfxclk_by_freq = smu10_set_hard_min_gfxclk_by_freq, + .set_soft_max_gfxclk_by_freq = smu10_set_soft_max_gfxclk_by_freq, .get_power_profile_mode = smu10_get_power_profile_mode, .set_power_profile_mode = smu10_set_power_profile_mode, .asic_reset = smu10_asic_reset, + .set_fine_grain_clk_vol = smu10_set_fine_grain_clk_vol, }; int smu10_init_function_pointers(struct pp_hwmgr *hwmgr) diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu10_hwmgr.h b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu10_hwmgr.h index 0f969de10fab..6c9b5f060902 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu10_hwmgr.h +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu10_hwmgr.h @@ -284,7 +284,7 @@ struct smu10_hwmgr { uint32_t dclk_soft_min; uint32_t gfx_actual_soft_min_freq; uint32_t gfx_min_freq_limit; - uint32_t gfx_max_freq_limit; + uint32_t gfx_max_freq_limit; /* in 10Khz*/ bool vcn_power_gated; bool vcn_dpg_mode; @@ -310,6 +310,7 @@ int smu10_init_function_pointers(struct pp_hwmgr *hwmgr); #define SMU10_UMD_PSTATE_SOCCLK 626 #define SMU10_UMD_PSTATE_FCLK 933 #define SMU10_UMD_PSTATE_VCE 0x03C00320 +#define SMU10_UMD_PSTATE_PROFILE_VCE 0x02AD0229 #define SMU10_UMD_PSTATE_PEAK_SOCCLK 757 #define SMU10_UMD_PSTATE_PEAK_FCLK 1200 diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c index 4a3b64aa21ce..1e8919b0acdb 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c @@ -1585,9 +1585,19 @@ static void smu7_init_dpm_defaults(struct pp_hwmgr *hwmgr) data->current_profile_setting.sclk_down_hyst = 100; data->current_profile_setting.sclk_activity = SMU7_SCLK_TARGETACTIVITY_DFLT; data->current_profile_setting.bupdate_mclk = 1; - data->current_profile_setting.mclk_up_hyst = 0; - data->current_profile_setting.mclk_down_hyst = 100; - data->current_profile_setting.mclk_activity = SMU7_MCLK_TARGETACTIVITY_DFLT; + if (adev->gmc.vram_width == 256) { + data->current_profile_setting.mclk_up_hyst = 10; + data->current_profile_setting.mclk_down_hyst = 60; + data->current_profile_setting.mclk_activity = 25; + } else if (adev->gmc.vram_width == 128) { + data->current_profile_setting.mclk_up_hyst = 5; + data->current_profile_setting.mclk_down_hyst = 16; + data->current_profile_setting.mclk_activity = 20; + } else if (adev->gmc.vram_width == 64) { + data->current_profile_setting.mclk_up_hyst = 3; + data->current_profile_setting.mclk_down_hyst = 16; + data->current_profile_setting.mclk_activity = 20; + } hwmgr->workload_mask = 1 << hwmgr->workload_prority[PP_SMC_POWER_PROFILE_FULLSCREEN3D]; hwmgr->power_profile_mode = PP_SMC_POWER_PROFILE_FULLSCREEN3D; hwmgr->default_power_profile_mode = PP_SMC_POWER_PROFILE_FULLSCREEN3D; @@ -2873,7 +2883,7 @@ static int smu7_vblank_too_short(struct pp_hwmgr *hwmgr, if (hwmgr->is_kicker) switch_limit_us = data->is_memory_gddr5 ? 450 : 150; else - switch_limit_us = data->is_memory_gddr5 ? 190 : 150; + switch_limit_us = data->is_memory_gddr5 ? 200 : 150; break; case CHIP_VEGAM: switch_limit_us = 30; diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_hwmgr.c index c378a000c934..7eada3098ffc 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_hwmgr.c +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_hwmgr.c @@ -4659,7 +4659,7 @@ static int vega10_display_configuration_changed_task(struct pp_hwmgr *hwmgr) if ((data->water_marks_bitmap & WaterMarksExist) && !(data->water_marks_bitmap & WaterMarksLoaded)) { result = smum_smc_table_manager(hwmgr, (uint8_t *)wm_table, WMTABLE, false); - PP_ASSERT_WITH_CODE(result, "Failed to update WMTABLE!", return EINVAL); + PP_ASSERT_WITH_CODE(result, "Failed to update WMTABLE!", return -EINVAL); data->water_marks_bitmap |= WaterMarksLoaded; } diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega12_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega12_hwmgr.c index f0680dd58508..dc206fa88c5e 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega12_hwmgr.c +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega12_hwmgr.c @@ -2444,7 +2444,7 @@ static int vega12_display_configuration_changed_task(struct pp_hwmgr *hwmgr) !(data->water_marks_bitmap & WaterMarksLoaded)) { result = smum_smc_table_manager(hwmgr, (uint8_t *)wm_table, TABLE_WATERMARKS, false); - PP_ASSERT_WITH_CODE(result, "Failed to update WMTABLE!", return EINVAL); + PP_ASSERT_WITH_CODE(result, "Failed to update WMTABLE!", return -EINVAL); data->water_marks_bitmap |= WaterMarksLoaded; } diff --git a/drivers/gpu/drm/amd/pm/powerplay/smumgr/smu9_smumgr.c b/drivers/gpu/drm/amd/pm/powerplay/smumgr/smu9_smumgr.c index adfbcbe5d113..8a9aee85043e 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/smumgr/smu9_smumgr.c +++ b/drivers/gpu/drm/amd/pm/powerplay/smumgr/smu9_smumgr.c @@ -61,9 +61,6 @@ static uint32_t smu9_wait_for_response(struct pp_hwmgr *hwmgr) uint32_t reg; uint32_t ret; - /* Due to the L1 policy problem under SRIOV, we have to use - * mmMP1_SMN_C2PMSG_103 as the driver response register - */ if (hwmgr->pp_one_vf) { reg = SOC15_REG_OFFSET(MP1, 0, mmMP1_SMN_C2PMSG_103); @@ -148,10 +145,6 @@ int smu9_send_msg_to_smc_with_parameter(struct pp_hwmgr *hwmgr, smu9_wait_for_response(hwmgr); - /* Due to the L1 policy problem under SRIOV, we have to use - * mmMP1_SMN_C2PMSG_101 as the driver message register and - * mmMP1_SMN_C2PMSG_102 as the driver parameter register. - */ if (hwmgr->pp_one_vf) { WREG32_SOC15(MP1, 0, mmMP1_SMN_C2PMSG_103, 0); WREG32_SOC15(MP1, 0, mmMP1_SMN_C2PMSG_102, parameter); diff --git a/drivers/gpu/drm/amd/pm/powerplay/smumgr/vega10_smumgr.c b/drivers/gpu/drm/amd/pm/powerplay/smumgr/vega10_smumgr.c index 1e222c5d91a4..daf122f24f23 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/smumgr/vega10_smumgr.c +++ b/drivers/gpu/drm/amd/pm/powerplay/smumgr/vega10_smumgr.c @@ -209,11 +209,13 @@ static int vega10_smu_init(struct pp_hwmgr *hwmgr) int ret; struct cgs_firmware_info info = {0}; - ret = cgs_get_firmware_info(hwmgr->device, - CGS_UCODE_ID_SMU, - &info); - if (ret || !info.kptr) - return -EINVAL; + if (!amdgpu_sriov_vf((struct amdgpu_device *)hwmgr->adev)) { + ret = cgs_get_firmware_info(hwmgr->device, + CGS_UCODE_ID_SMU, + &info); + if (ret || !info.kptr) + return -EINVAL; + } priv = kzalloc(sizeof(struct vega10_smumgr), GFP_KERNEL); diff --git a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c index 7a55ece1f124..fc4f95fa87cf 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c +++ b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c @@ -361,20 +361,16 @@ static int smu_get_driver_allowed_feature_mask(struct smu_context *smu) int ret = 0; uint32_t allowed_feature_mask[SMU_FEATURE_MAX/32]; - mutex_lock(&feature->mutex); bitmap_zero(feature->allowed, SMU_FEATURE_MAX); - mutex_unlock(&feature->mutex); ret = smu_get_allowed_feature_mask(smu, allowed_feature_mask, SMU_FEATURE_MAX/32); if (ret) return ret; - mutex_lock(&feature->mutex); bitmap_or(feature->allowed, feature->allowed, (unsigned long *)allowed_feature_mask, feature->feature_num); - mutex_unlock(&feature->mutex); return ret; } @@ -421,6 +417,9 @@ static int smu_early_init(void *handle) smu->pm_enabled = !!amdgpu_dpm; smu->is_apu = false; mutex_init(&smu->mutex); + mutex_init(&smu->smu_baco.mutex); + smu->smu_baco.state = SMU_BACO_STATE_EXIT; + smu->smu_baco.platform_support = false; return smu_set_funcs(adev); } @@ -473,20 +472,15 @@ static int smu_late_init(void *handle) if (!smu->pm_enabled) return 0; - ret = smu_set_default_od_settings(smu); + ret = smu_post_init(smu); if (ret) { - dev_err(adev->dev, "Failed to setup default OD settings!\n"); + dev_err(adev->dev, "Failed to post smu init!\n"); return ret; } - /* - * Set initialized values (get from vbios) to dpm tables context such as - * gfxclk, memclk, dcefclk, and etc. And enable the DPM feature for each - * type of clks. - */ - ret = smu_set_default_dpm_table(smu); + ret = smu_set_default_od_settings(smu); if (ret) { - dev_err(adev->dev, "Failed to setup default dpm clock tables!\n"); + dev_err(adev->dev, "Failed to setup default OD settings!\n"); return ret; } @@ -578,9 +572,6 @@ static int smu_fini_fb_allocations(struct smu_context *smu) struct smu_table *tables = smu_table->tables; struct smu_table *driver_table = &(smu_table->driver_table); - if (!tables) - return 0; - if (tables[SMU_TABLE_PMSTATUSLOG].mc_address) amdgpu_bo_free_kernel(&tables[SMU_TABLE_PMSTATUSLOG].bo, &tables[SMU_TABLE_PMSTATUSLOG].mc_address, @@ -657,6 +648,45 @@ static int smu_free_memory_pool(struct smu_context *smu) return 0; } +static int smu_alloc_dummy_read_table(struct smu_context *smu) +{ + struct smu_table_context *smu_table = &smu->smu_table; + struct smu_table *dummy_read_1_table = + &smu_table->dummy_read_1_table; + struct amdgpu_device *adev = smu->adev; + int ret = 0; + + dummy_read_1_table->size = 0x40000; + dummy_read_1_table->align = PAGE_SIZE; + dummy_read_1_table->domain = AMDGPU_GEM_DOMAIN_VRAM; + + ret = amdgpu_bo_create_kernel(adev, + dummy_read_1_table->size, + dummy_read_1_table->align, + dummy_read_1_table->domain, + &dummy_read_1_table->bo, + &dummy_read_1_table->mc_address, + &dummy_read_1_table->cpu_addr); + if (ret) + dev_err(adev->dev, "VRAM allocation for dummy read table failed!\n"); + + return ret; +} + +static void smu_free_dummy_read_table(struct smu_context *smu) +{ + struct smu_table_context *smu_table = &smu->smu_table; + struct smu_table *dummy_read_1_table = + &smu_table->dummy_read_1_table; + + + amdgpu_bo_free_kernel(&dummy_read_1_table->bo, + &dummy_read_1_table->mc_address, + &dummy_read_1_table->cpu_addr); + + memset(dummy_read_1_table, 0, sizeof(struct smu_table)); +} + static int smu_smc_table_sw_init(struct smu_context *smu) { int ret; @@ -692,6 +722,10 @@ static int smu_smc_table_sw_init(struct smu_context *smu) if (ret) return ret; + ret = smu_alloc_dummy_read_table(smu); + if (ret) + return ret; + ret = smu_i2c_init(smu, &smu->adev->pm.smu_i2c); if (ret) return ret; @@ -705,6 +739,8 @@ static int smu_smc_table_sw_fini(struct smu_context *smu) smu_i2c_fini(smu, &smu->adev->pm.smu_i2c); + smu_free_dummy_read_table(smu); + ret = smu_free_memory_pool(smu); if (ret) return ret; @@ -736,6 +772,19 @@ static void smu_throttling_logging_work_fn(struct work_struct *work) smu_log_thermal_throttling(smu); } +static void smu_interrupt_work_fn(struct work_struct *work) +{ + struct smu_context *smu = container_of(work, struct smu_context, + interrupt_work); + + mutex_lock(&smu->mutex); + + if (smu->ppt_funcs && smu->ppt_funcs->interrupt_work) + smu->ppt_funcs->interrupt_work(smu); + + mutex_unlock(&smu->mutex); +} + static int smu_sw_init(void *handle) { struct amdgpu_device *adev = (struct amdgpu_device *)handle; @@ -749,15 +798,12 @@ static int smu_sw_init(void *handle) bitmap_zero(smu->smu_feature.enabled, SMU_FEATURE_MAX); bitmap_zero(smu->smu_feature.allowed, SMU_FEATURE_MAX); - mutex_init(&smu->smu_baco.mutex); - smu->smu_baco.state = SMU_BACO_STATE_EXIT; - smu->smu_baco.platform_support = false; - mutex_init(&smu->sensor_lock); mutex_init(&smu->metrics_lock); mutex_init(&smu->message_lock); INIT_WORK(&smu->throttling_logging_work, smu_throttling_logging_work_fn); + INIT_WORK(&smu->interrupt_work, smu_interrupt_work_fn); atomic64_set(&smu->throttle_int_counter, 0); smu->watermarks_bitmap = 0; smu->power_profile_mode = PP_SMC_POWER_PROFILE_BOOTUP_DEFAULT; @@ -788,10 +834,13 @@ static int smu_sw_init(void *handle) smu->smu_dpm.dpm_level = AMD_DPM_FORCED_LEVEL_AUTO; smu->smu_dpm.requested_dpm_level = AMD_DPM_FORCED_LEVEL_AUTO; - ret = smu_init_microcode(smu); - if (ret) { - dev_err(adev->dev, "Failed to load smu firmware!\n"); - return ret; + + if (!amdgpu_sriov_vf(adev)) { + ret = smu_init_microcode(smu); + if (ret) { + dev_err(adev->dev, "Failed to load smu firmware!\n"); + return ret; + } } ret = smu_smc_table_sw_init(smu); @@ -969,21 +1018,25 @@ static int smu_smc_hw_setup(struct smu_context *smu) return ret; } - ret = smu_disable_umc_cdr_12gbps_workaround(smu); + /* + * Set initialized values (get from vbios) to dpm tables context such as + * gfxclk, memclk, dcefclk, and etc. And enable the DPM feature for each + * type of clks. + */ + ret = smu_set_default_dpm_table(smu); if (ret) { - dev_err(adev->dev, "Workaround failed to disable UMC CDR feature on 12Gbps SKU!\n"); + dev_err(adev->dev, "Failed to setup default dpm clock tables!\n"); return ret; } /* - * For Navi1X, manually switch it to AC mode as PMFW - * may boot it with DC mode. + * Set initialized values (get from vbios) to dpm tables context such as + * gfxclk, memclk, dcefclk, and etc. And enable the DPM feature for each + * type of clks. */ - ret = smu_set_power_source(smu, - adev->pm.ac_power ? SMU_POWER_SOURCE_AC : - SMU_POWER_SOURCE_DC); + ret = smu_set_default_dpm_table(smu); if (ret) { - dev_err(adev->dev, "Failed to switch to %s mode!\n", adev->pm.ac_power ? "AC" : "DC"); + dev_err(adev->dev, "Failed to setup default dpm clock tables!\n"); return ret; } @@ -1129,7 +1182,7 @@ static int smu_disable_dpms(struct smu_context *smu) */ if (smu->uploading_custom_pp_table && (adev->asic_type >= CHIP_NAVI10) && - (adev->asic_type <= CHIP_NAVI12)) + (adev->asic_type <= CHIP_NAVY_FLOUNDER)) return 0; /* @@ -1168,6 +1221,7 @@ static int smu_smc_hw_cleanup(struct smu_context *smu) int ret = 0; cancel_work_sync(&smu->throttling_logging_work); + cancel_work_sync(&smu->interrupt_work); ret = smu_disable_thermal_alert(smu); if (ret) { @@ -1188,7 +1242,6 @@ static int smu_hw_fini(void *handle) { struct amdgpu_device *adev = (struct amdgpu_device *)handle; struct smu_context *smu = &adev->smu; - int ret = 0; if (amdgpu_sriov_vf(adev)&& !amdgpu_sriov_is_pp_one_vf(adev)) return 0; @@ -1204,17 +1257,15 @@ static int smu_hw_fini(void *handle) adev->pm.dpm_enabled = false; - ret = smu_smc_hw_cleanup(smu); - if (ret) - return ret; - - return 0; + return smu_smc_hw_cleanup(smu); } int smu_reset(struct smu_context *smu) { struct amdgpu_device *adev = smu->adev; - int ret = 0; + int ret; + + amdgpu_gfx_off_ctrl(smu->adev, false); ret = smu_hw_fini(adev); if (ret) @@ -1225,8 +1276,12 @@ int smu_reset(struct smu_context *smu) return ret; ret = smu_late_init(adev); + if (ret) + return ret; - return ret; + amdgpu_gfx_off_ctrl(smu->adev, true); + + return 0; } static int smu_suspend(void *handle) @@ -1784,25 +1839,19 @@ int smu_write_watermarks_table(struct smu_context *smu) } int smu_set_watermarks_for_clock_ranges(struct smu_context *smu, - struct dm_pp_wm_sets_with_clock_ranges_soc15 *clock_ranges) + struct pp_smu_wm_range_sets *clock_ranges) { int ret = 0; if (!smu->pm_enabled || !smu->adev->pm.dpm_enabled) return -EOPNOTSUPP; + if (smu->disable_watermark) + return 0; + mutex_lock(&smu->mutex); - if (!smu->disable_watermark && - smu_feature_is_enabled(smu, SMU_FEATURE_DPM_DCEFCLK_BIT) && - smu_feature_is_enabled(smu, SMU_FEATURE_DPM_SOCCLK_BIT)) { - ret = smu_set_watermarks_table(smu, clock_ranges); - - if (!(smu->watermarks_bitmap & WATERMARKS_EXIST)) { - smu->watermarks_bitmap |= WATERMARKS_EXIST; - smu->watermarks_bitmap &= ~WATERMARKS_LOADED; - } - } + ret = smu_set_watermarks_table(smu, clock_ranges); mutex_unlock(&smu->mutex); @@ -2269,19 +2318,6 @@ int smu_set_deep_sleep_dcefclk(struct smu_context *smu, int clk) return ret; } -int smu_set_active_display_count(struct smu_context *smu, uint32_t count) -{ - int ret = 0; - - if (!smu->pm_enabled || !smu->adev->pm.dpm_enabled) - return -EOPNOTSUPP; - - if (smu->ppt_funcs->set_active_display_count) - ret = smu->ppt_funcs->set_active_display_count(smu, count); - - return ret; -} - int smu_get_clock_by_type(struct smu_context *smu, enum amd_pp_clock_type type, struct amd_pp_clocks *clocks) diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/arcturus_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/arcturus_ppt.c index 2ce6ad9c6609..fc376281e629 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu11/arcturus_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/arcturus_ppt.c @@ -386,11 +386,9 @@ static int arcturus_check_powerplay_table(struct smu_context *smu) table_context->power_play_table; struct smu_baco_context *smu_baco = &smu->smu_baco; - mutex_lock(&smu_baco->mutex); if (powerplay_table->platform_caps & SMU_11_0_PP_PLATFORM_CAP_BACO || powerplay_table->platform_caps & SMU_11_0_PP_PLATFORM_CAP_MACO) smu_baco->platform_support = true; - mutex_unlock(&smu_baco->mutex); table_context->thermal_controller_type = powerplay_table->thermal_controller_type; @@ -2390,6 +2388,7 @@ static const struct pptable_funcs arcturus_ppt_funcs = { .gfx_ulv_control = smu_v11_0_gfx_ulv_control, .deep_sleep_control = smu_v11_0_deep_sleep_control, .get_fan_parameters = arcturus_get_fan_parameters, + .interrupt_work = smu_v11_0_interrupt_work, }; void arcturus_set_ppt_funcs(struct smu_context *smu) diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c index 42d53cca7360..ef1a62e86a0e 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c @@ -45,6 +45,7 @@ #include "asic_reg/mp/mp_11_0_sh_mask.h" #include "smu_cmn.h" +#include "smu_11_0_cdr_table.h" /* * DO NOT use these for err/warn/info/debug messages. @@ -139,6 +140,9 @@ static struct cmn2asic_msg_mapping navi10_message_map[SMU_MSG_MAX_COUNT] = { MSG_MAP(GetVoltageByDpm, PPSMC_MSG_GetVoltageByDpm, 0), MSG_MAP(GetVoltageByDpmOverdrive, PPSMC_MSG_GetVoltageByDpmOverdrive, 0), MSG_MAP(SetMGpuFanBoostLimitRpm, PPSMC_MSG_SetMGpuFanBoostLimitRpm, 0), + MSG_MAP(SET_DRIVER_DUMMY_TABLE_DRAM_ADDR_HIGH, PPSMC_MSG_SetDriverDummyTableDramAddrHigh, 0), + MSG_MAP(SET_DRIVER_DUMMY_TABLE_DRAM_ADDR_LOW, PPSMC_MSG_SetDriverDummyTableDramAddrLow, 0), + MSG_MAP(GET_UMC_FW_WA, PPSMC_MSG_GetUMCFWWA, 0), }; static struct cmn2asic_mapping navi10_clk_map[SMU_CLK_COUNT] = { @@ -279,9 +283,6 @@ navi10_get_allowed_feature_mask(struct smu_context *smu, | FEATURE_MASK(FEATURE_FW_CTF_BIT) | FEATURE_MASK(FEATURE_OUT_OF_BAND_MONITOR_BIT); - if (adev->pm.pp_feature & PP_SOCCLK_DPM_MASK) - *(uint64_t *)feature_mask |= FEATURE_MASK(FEATURE_DPM_SOCCLK_BIT); - if (adev->pm.pp_feature & PP_SCLK_DPM_MASK) *(uint64_t *)feature_mask |= FEATURE_MASK(FEATURE_DPM_GFXCLK_BIT); @@ -291,11 +292,6 @@ navi10_get_allowed_feature_mask(struct smu_context *smu, if (adev->pm.pp_feature & PP_DCEFCLK_DPM_MASK) *(uint64_t *)feature_mask |= FEATURE_MASK(FEATURE_DPM_DCEFCLK_BIT); - if (adev->pm.pp_feature & PP_MCLK_DPM_MASK) - *(uint64_t *)feature_mask |= FEATURE_MASK(FEATURE_DPM_UCLK_BIT) - | FEATURE_MASK(FEATURE_MEM_VDDCI_SCALING_BIT) - | FEATURE_MASK(FEATURE_MEM_MVDD_SCALING_BIT); - if (adev->pm.pp_feature & PP_ULV_MASK) *(uint64_t *)feature_mask |= FEATURE_MASK(FEATURE_GFX_ULV_BIT); @@ -320,19 +316,24 @@ navi10_get_allowed_feature_mask(struct smu_context *smu, if (smu->dc_controlled_by_gpio) *(uint64_t *)feature_mask |= FEATURE_MASK(FEATURE_ACDC_BIT); - /* disable DPM UCLK and DS SOCCLK on navi10 A0 secure board */ - if (is_asic_secure(smu)) { - /* only for navi10 A0 */ - if ((adev->asic_type == CHIP_NAVI10) && - (adev->rev_id == 0)) { - *(uint64_t *)feature_mask &= - ~(FEATURE_MASK(FEATURE_DPM_UCLK_BIT) - | FEATURE_MASK(FEATURE_MEM_VDDCI_SCALING_BIT) - | FEATURE_MASK(FEATURE_MEM_MVDD_SCALING_BIT)); - *(uint64_t *)feature_mask &= - ~FEATURE_MASK(FEATURE_DS_SOCCLK_BIT); - } - } + if (adev->pm.pp_feature & PP_SOCCLK_DPM_MASK) + *(uint64_t *)feature_mask |= FEATURE_MASK(FEATURE_DPM_SOCCLK_BIT); + + /* DPM UCLK enablement should be skipped for navi10 A0 secure board */ + if (!(is_asic_secure(smu) && + (adev->asic_type == CHIP_NAVI10) && + (adev->rev_id == 0)) && + (adev->pm.pp_feature & PP_MCLK_DPM_MASK)) + *(uint64_t *)feature_mask |= FEATURE_MASK(FEATURE_DPM_UCLK_BIT) + | FEATURE_MASK(FEATURE_MEM_VDDCI_SCALING_BIT) + | FEATURE_MASK(FEATURE_MEM_MVDD_SCALING_BIT); + + /* DS SOCCLK enablement should be skipped for navi10 A0 secure board */ + if (is_asic_secure(smu) && + (adev->asic_type == CHIP_NAVI10) && + (adev->rev_id == 0)) + *(uint64_t *)feature_mask &= + ~FEATURE_MASK(FEATURE_DS_SOCCLK_BIT); return 0; } @@ -347,11 +348,9 @@ static int navi10_check_powerplay_table(struct smu_context *smu) if (powerplay_table->platform_caps & SMU_11_0_PP_PLATFORM_CAP_HARDWAREDC) smu->dc_controlled_by_gpio = true; - mutex_lock(&smu_baco->mutex); if (powerplay_table->platform_caps & SMU_11_0_PP_PLATFORM_CAP_BACO || powerplay_table->platform_caps & SMU_11_0_PP_PLATFORM_CAP_MACO) smu_baco->platform_support = true; - mutex_unlock(&smu_baco->mutex); table_context->thermal_controller_type = powerplay_table->thermal_controller_type; @@ -1362,14 +1361,9 @@ static int navi10_get_fan_speed_rpm(struct smu_context *smu, if (!speed) return -EINVAL; - switch (smu_v11_0_get_fan_control_mode(smu)) { - case AMD_FAN_CTRL_AUTO: - return navi10_get_smu_metrics_data(smu, - METRICS_CURR_FANSPEED, - speed); - default: - return smu_v11_0_get_fan_speed_rpm(smu, speed); - } + return navi10_get_smu_metrics_data(smu, + METRICS_CURR_FANSPEED, + speed); } static int navi10_get_fan_parameters(struct smu_context *smu) @@ -1602,57 +1596,43 @@ static int navi10_notify_smc_display_config(struct smu_context *smu) } static int navi10_set_watermarks_table(struct smu_context *smu, - struct dm_pp_wm_sets_with_clock_ranges_soc15 *clock_ranges) + struct pp_smu_wm_range_sets *clock_ranges) { Watermarks_t *table = smu->smu_table.watermarks_table; int ret = 0; int i; if (clock_ranges) { - if (clock_ranges->num_wm_dmif_sets > 4 || - clock_ranges->num_wm_mcif_sets > 4) + if (clock_ranges->num_reader_wm_sets > NUM_WM_RANGES || + clock_ranges->num_writer_wm_sets > NUM_WM_RANGES) return -EINVAL; - for (i = 0; i < clock_ranges->num_wm_dmif_sets; i++) { - table->WatermarkRow[1][i].MinClock = - cpu_to_le16((uint16_t) - (clock_ranges->wm_dmif_clocks_ranges[i].wm_min_dcfclk_clk_in_khz / - 1000)); - table->WatermarkRow[1][i].MaxClock = - cpu_to_le16((uint16_t) - (clock_ranges->wm_dmif_clocks_ranges[i].wm_max_dcfclk_clk_in_khz / - 1000)); - table->WatermarkRow[1][i].MinUclk = - cpu_to_le16((uint16_t) - (clock_ranges->wm_dmif_clocks_ranges[i].wm_min_mem_clk_in_khz / - 1000)); - table->WatermarkRow[1][i].MaxUclk = - cpu_to_le16((uint16_t) - (clock_ranges->wm_dmif_clocks_ranges[i].wm_max_mem_clk_in_khz / - 1000)); - table->WatermarkRow[1][i].WmSetting = (uint8_t) - clock_ranges->wm_dmif_clocks_ranges[i].wm_set_id; + for (i = 0; i < clock_ranges->num_reader_wm_sets; i++) { + table->WatermarkRow[WM_DCEFCLK][i].MinClock = + clock_ranges->reader_wm_sets[i].min_drain_clk_mhz; + table->WatermarkRow[WM_DCEFCLK][i].MaxClock = + clock_ranges->reader_wm_sets[i].max_drain_clk_mhz; + table->WatermarkRow[WM_DCEFCLK][i].MinUclk = + clock_ranges->reader_wm_sets[i].min_fill_clk_mhz; + table->WatermarkRow[WM_DCEFCLK][i].MaxUclk = + clock_ranges->reader_wm_sets[i].max_fill_clk_mhz; + + table->WatermarkRow[WM_DCEFCLK][i].WmSetting = + clock_ranges->reader_wm_sets[i].wm_inst; } - for (i = 0; i < clock_ranges->num_wm_mcif_sets; i++) { - table->WatermarkRow[0][i].MinClock = - cpu_to_le16((uint16_t) - (clock_ranges->wm_mcif_clocks_ranges[i].wm_min_socclk_clk_in_khz / - 1000)); - table->WatermarkRow[0][i].MaxClock = - cpu_to_le16((uint16_t) - (clock_ranges->wm_mcif_clocks_ranges[i].wm_max_socclk_clk_in_khz / - 1000)); - table->WatermarkRow[0][i].MinUclk = - cpu_to_le16((uint16_t) - (clock_ranges->wm_mcif_clocks_ranges[i].wm_min_mem_clk_in_khz / - 1000)); - table->WatermarkRow[0][i].MaxUclk = - cpu_to_le16((uint16_t) - (clock_ranges->wm_mcif_clocks_ranges[i].wm_max_mem_clk_in_khz / - 1000)); - table->WatermarkRow[0][i].WmSetting = (uint8_t) - clock_ranges->wm_mcif_clocks_ranges[i].wm_set_id; + for (i = 0; i < clock_ranges->num_writer_wm_sets; i++) { + table->WatermarkRow[WM_SOCCLK][i].MinClock = + clock_ranges->writer_wm_sets[i].min_fill_clk_mhz; + table->WatermarkRow[WM_SOCCLK][i].MaxClock = + clock_ranges->writer_wm_sets[i].max_fill_clk_mhz; + table->WatermarkRow[WM_SOCCLK][i].MinUclk = + clock_ranges->writer_wm_sets[i].min_drain_clk_mhz; + table->WatermarkRow[WM_SOCCLK][i].MaxUclk = + clock_ranges->writer_wm_sets[i].max_drain_clk_mhz; + + table->WatermarkRow[WM_SOCCLK][i].WmSetting = + clock_ranges->writer_wm_sets[i].wm_inst; } smu->watermarks_bitmap |= WATERMARKS_EXIST; @@ -2196,59 +2176,46 @@ static int navi10_run_btc(struct smu_context *smu) return ret; } -static int navi10_dummy_pstate_control(struct smu_context *smu, bool enable) +static bool navi10_need_umc_cdr_workaround(struct smu_context *smu) { - int result = 0; - - if (!enable) - result = smu_cmn_send_smc_msg(smu, SMU_MSG_DAL_DISABLE_DUMMY_PSTATE_CHANGE, NULL); - else - result = smu_cmn_send_smc_msg(smu, SMU_MSG_DAL_ENABLE_DUMMY_PSTATE_CHANGE, NULL); - - return result; -} + struct amdgpu_device *adev = smu->adev; -static inline bool navi10_need_umc_cdr_12gbps_workaround(struct amdgpu_device *adev) -{ - if (adev->asic_type != CHIP_NAVI10) + if (!smu_cmn_feature_is_enabled(smu, SMU_FEATURE_DPM_UCLK_BIT)) return false; - if (adev->pdev->device == 0x731f && - (adev->pdev->revision == 0xc2 || - adev->pdev->revision == 0xc3 || - adev->pdev->revision == 0xca || - adev->pdev->revision == 0xcb)) + if (adev->asic_type == CHIP_NAVI10 || + adev->asic_type == CHIP_NAVI14) return true; - else - return false; + + return false; } -static int navi10_disable_umc_cdr_12gbps_workaround(struct smu_context *smu) +static int navi10_umc_hybrid_cdr_workaround(struct smu_context *smu) { uint32_t uclk_count, uclk_min, uclk_max; - uint32_t smu_version; int ret = 0; - if (!navi10_need_umc_cdr_12gbps_workaround(smu->adev)) - return 0; - - ret = smu_cmn_get_smc_version(smu, NULL, &smu_version); - if (ret) - return ret; - - /* This workaround is available only for 42.50 or later SMC firmwares */ - if (smu_version < 0x2A3200) + /* This workaround can be applied only with uclk dpm enabled */ + if (!smu_cmn_feature_is_enabled(smu, SMU_FEATURE_DPM_UCLK_BIT)) return 0; ret = smu_v11_0_get_dpm_level_count(smu, SMU_UCLK, &uclk_count); if (ret) return ret; - ret = smu_v11_0_get_dpm_freq_by_index(smu, SMU_UCLK, (uint16_t)0, &uclk_min); + ret = smu_v11_0_get_dpm_freq_by_index(smu, SMU_UCLK, (uint16_t)(uclk_count - 1), &uclk_max); if (ret) return ret; - ret = smu_v11_0_get_dpm_freq_by_index(smu, SMU_UCLK, (uint16_t)(uclk_count - 1), &uclk_max); + /* + * The NAVI10_UMC_HYBRID_CDR_WORKAROUND_UCLK_THRESHOLD is 750Mhz. + * This workaround is needed only when the max uclk frequency + * not greater than that. + */ + if (uclk_max > 0x2EE) + return 0; + + ret = smu_v11_0_get_dpm_freq_by_index(smu, SMU_UCLK, (uint16_t)0, &uclk_min); if (ret) return ret; @@ -2265,8 +2232,97 @@ static int navi10_disable_umc_cdr_12gbps_workaround(struct smu_context *smu) /* * In this case, SMU already disabled dummy pstate during enablement * of UCLK DPM, we have to re-enabled it. - * */ - return navi10_dummy_pstate_control(smu, true); + */ + return smu_cmn_send_smc_msg(smu, SMU_MSG_DAL_ENABLE_DUMMY_PSTATE_CHANGE, NULL); +} + +static int navi10_set_dummy_pstates_table_location(struct smu_context *smu) +{ + struct smu_table_context *smu_table = &smu->smu_table; + struct smu_table *dummy_read_table = + &smu_table->dummy_read_1_table; + char *dummy_table = dummy_read_table->cpu_addr; + int ret = 0; + uint32_t i; + + for (i = 0; i < 0x40000; i += 0x1000 * 2) { + memcpy(dummy_table, &NoDbiPrbs7[0], 0x1000); + dummy_table += 0x1000; + memcpy(dummy_table, &DbiPrbs7[0], 0x1000); + dummy_table += 0x1000; + } + + amdgpu_asic_flush_hdp(smu->adev, NULL); + + ret = smu_cmn_send_smc_msg_with_param(smu, + SMU_MSG_SET_DRIVER_DUMMY_TABLE_DRAM_ADDR_HIGH, + upper_32_bits(dummy_read_table->mc_address), + NULL); + if (ret) + return ret; + + return smu_cmn_send_smc_msg_with_param(smu, + SMU_MSG_SET_DRIVER_DUMMY_TABLE_DRAM_ADDR_LOW, + lower_32_bits(dummy_read_table->mc_address), + NULL); +} + +static int navi10_run_umc_cdr_workaround(struct smu_context *smu) +{ + struct amdgpu_device *adev = smu->adev; + uint8_t umc_fw_greater_than_v136 = false; + uint8_t umc_fw_disable_cdr = false; + uint32_t pmfw_version; + uint32_t param; + int ret = 0; + + if (!navi10_need_umc_cdr_workaround(smu)) + return 0; + + ret = smu_cmn_get_smc_version(smu, NULL, &pmfw_version); + if (ret) { + dev_err(adev->dev, "Failed to get smu version!\n"); + return ret; + } + + /* + * The messages below are only supported by Navi10 42.53.0 and later + * PMFWs and Navi14 53.29.0 and later PMFWs. + * - PPSMC_MSG_SetDriverDummyTableDramAddrHigh + * - PPSMC_MSG_SetDriverDummyTableDramAddrLow + * - PPSMC_MSG_GetUMCFWWA + */ + if (((adev->asic_type == CHIP_NAVI10) && (pmfw_version >= 0x2a3500)) || + ((adev->asic_type == CHIP_NAVI14) && (pmfw_version >= 0x351D00))) { + ret = smu_cmn_send_smc_msg_with_param(smu, + SMU_MSG_GET_UMC_FW_WA, + 0, + ¶m); + if (ret) + return ret; + + /* First bit indicates if the UMC f/w is above v137 */ + umc_fw_greater_than_v136 = param & 0x1; + + /* Second bit indicates if hybrid-cdr is disabled */ + umc_fw_disable_cdr = param & 0x2; + + /* w/a only allowed if UMC f/w is <= 136 */ + if (umc_fw_greater_than_v136) + return 0; + + if (umc_fw_disable_cdr) { + if (adev->asic_type == CHIP_NAVI10) + return navi10_umc_hybrid_cdr_workaround(smu); + } else { + return navi10_set_dummy_pstates_table_location(smu); + } + } else { + if (adev->asic_type == CHIP_NAVI10) + return navi10_umc_hybrid_cdr_workaround(smu); + } + + return 0; } static void navi10_fill_i2c_req(SwI2cRequest_t *req, bool write, @@ -2275,8 +2331,6 @@ static void navi10_fill_i2c_req(SwI2cRequest_t *req, bool write, { int i; - BUG_ON(numbytes > MAX_SW_I2C_COMMANDS); - req->I2CcontrollerPort = 0; req->I2CSpeed = 2; req->SlaveAddress = address; @@ -2314,6 +2368,12 @@ static int navi10_i2c_read_data(struct i2c_adapter *control, struct smu_table_context *smu_table = &adev->smu.smu_table; struct smu_table *table = &smu_table->driver_table; + if (numbytes > MAX_SW_I2C_COMMANDS) { + dev_err(adev->dev, "numbytes requested %d is over max allowed %d\n", + numbytes, MAX_SW_I2C_COMMANDS); + return -EINVAL; + } + memset(&req, 0, sizeof(req)); navi10_fill_i2c_req(&req, false, address, numbytes, data); @@ -2350,6 +2410,12 @@ static int navi10_i2c_write_data(struct i2c_adapter *control, SwI2cRequest_t req; struct amdgpu_device *adev = to_amdgpu_device(control); + if (numbytes > MAX_SW_I2C_COMMANDS) { + dev_err(adev->dev, "numbytes requested %d is over max allowed %d\n", + numbytes, MAX_SW_I2C_COMMANDS); + return -EINVAL; + } + memset(&req, 0, sizeof(req)); navi10_fill_i2c_req(&req, true, address, numbytes, data); @@ -2463,29 +2529,6 @@ static const struct i2c_algorithm navi10_i2c_algo = { .functionality = navi10_i2c_func, }; -static int navi10_i2c_control_init(struct smu_context *smu, struct i2c_adapter *control) -{ - struct amdgpu_device *adev = to_amdgpu_device(control); - int res; - - control->owner = THIS_MODULE; - control->class = I2C_CLASS_SPD; - control->dev.parent = &adev->pdev->dev; - control->algo = &navi10_i2c_algo; - snprintf(control->name, sizeof(control->name), "AMDGPU SMU"); - - res = i2c_add_adapter(control); - if (res) - DRM_ERROR("Failed to register hw i2c, err: %d\n", res); - - return res; -} - -static void navi10_i2c_control_fini(struct smu_context *smu, struct i2c_adapter *control) -{ - i2c_del_adapter(control); -} - static ssize_t navi10_get_gpu_metrics(struct smu_context *smu, void **table) { @@ -2578,13 +2621,44 @@ static int navi10_enable_mgpu_fan_boost(struct smu_context *smu) NULL); } +static int navi10_post_smu_init(struct smu_context *smu) +{ + struct amdgpu_device *adev = smu->adev; + int ret = 0; + + if (amdgpu_sriov_vf(adev)) + return 0; + + ret = navi10_run_umc_cdr_workaround(smu); + if (ret) { + dev_err(adev->dev, "Failed to apply umc cdr workaround!\n"); + return ret; + } + + if (!smu->dc_controlled_by_gpio) { + /* + * For Navi1X, manually switch it to AC mode as PMFW + * may boot it with DC mode. + */ + ret = smu_v11_0_set_power_source(smu, + adev->pm.ac_power ? + SMU_POWER_SOURCE_AC : + SMU_POWER_SOURCE_DC); + if (ret) { + dev_err(adev->dev, "Failed to switch to %s mode!\n", + adev->pm.ac_power ? "AC" : "DC"); + return ret; + } + } + + return ret; +} + static const struct pptable_funcs navi10_ppt_funcs = { .get_allowed_feature_mask = navi10_get_allowed_feature_mask, .set_default_dpm_table = navi10_set_default_dpm_table, .dpm_set_vcn_enable = navi10_dpm_set_vcn_enable, .dpm_set_jpeg_enable = navi10_dpm_set_jpeg_enable, - .i2c_init = navi10_i2c_control_init, - .i2c_fini = navi10_i2c_control_fini, .print_clk_levels = navi10_print_clk_levels, .force_clk_levels = navi10_force_clk_levels, .populate_umd_state_clk = navi10_populate_umd_state_clk, @@ -2652,7 +2726,6 @@ static const struct pptable_funcs navi10_ppt_funcs = { .set_default_od_settings = navi10_set_default_od_settings, .od_edit_dpm_table = navi10_od_edit_dpm_table, .run_btc = navi10_run_btc, - .disable_umc_cdr_12gbps_workaround = navi10_disable_umc_cdr_12gbps_workaround, .set_power_source = smu_v11_0_set_power_source, .get_pp_feature_mask = smu_cmn_get_pp_feature_mask, .set_pp_feature_mask = smu_cmn_set_pp_feature_mask, @@ -2661,6 +2734,8 @@ static const struct pptable_funcs navi10_ppt_funcs = { .gfx_ulv_control = smu_v11_0_gfx_ulv_control, .deep_sleep_control = smu_v11_0_deep_sleep_control, .get_fan_parameters = navi10_get_fan_parameters, + .post_init = navi10_post_smu_init, + .interrupt_work = smu_v11_0_interrupt_work, }; void navi10_set_ppt_funcs(struct smu_context *smu) 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 5c22611d5878..895d89bea7fa 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 @@ -151,14 +151,17 @@ static struct cmn2asic_mapping sienna_cichlid_feature_mask_map[SMU_FEATURE_COUNT FEA_MAP(DPM_GFXCLK), FEA_MAP(DPM_GFX_GPO), FEA_MAP(DPM_UCLK), + FEA_MAP(DPM_FCLK), FEA_MAP(DPM_SOCCLK), FEA_MAP(DPM_MP0CLK), FEA_MAP(DPM_LINK), FEA_MAP(DPM_DCEFCLK), + FEA_MAP(DPM_XGMI), FEA_MAP(MEM_VDDCI_SCALING), FEA_MAP(MEM_MVDD_SCALING), FEA_MAP(DS_GFXCLK), FEA_MAP(DS_SOCCLK), + FEA_MAP(DS_FCLK), FEA_MAP(DS_LCLK), FEA_MAP(DS_DCEFCLK), FEA_MAP(DS_UCLK), @@ -298,11 +301,9 @@ static int sienna_cichlid_check_powerplay_table(struct smu_context *smu) table_context->power_play_table; struct smu_baco_context *smu_baco = &smu->smu_baco; - mutex_lock(&smu_baco->mutex); if (powerplay_table->platform_caps & SMU_11_0_7_PP_PLATFORM_CAP_BACO || powerplay_table->platform_caps & SMU_11_0_7_PP_PLATFORM_CAP_MACO) smu_baco->platform_support = true; - mutex_unlock(&smu_baco->mutex); table_context->thermal_controller_type = powerplay_table->thermal_controller_type; @@ -454,6 +455,9 @@ static int sienna_cichlid_get_smu_metrics_data(struct smu_context *smu, case METRICS_CURR_DCEFCLK: *value = metrics->CurrClock[PPCLK_DCEFCLK]; break; + case METRICS_CURR_FCLK: + *value = metrics->CurrClock[PPCLK_FCLK]; + break; case METRICS_AVERAGE_GFXCLK: if (metrics->AverageGfxActivity <= SMU_11_0_7_GFX_BUSY_THRESHOLD) *value = metrics->AverageGfxclkFrequencyPostDs; @@ -950,19 +954,23 @@ static int sienna_cichlid_print_clk_levels(struct smu_context *smu, freq_values[1] = cur_value; mark_index = cur_value == freq_values[0] ? 0 : cur_value == freq_values[2] ? 2 : 1; - if (mark_index != 1) - freq_values[1] = (freq_values[0] + freq_values[2]) / 2; - for (i = 0; i < 3; i++) { + count = 3; + if (mark_index != 1) { + count = 2; + freq_values[1] = freq_values[2]; + } + + for (i = 0; i < count; i++) { size += sprintf(buf + size, "%d: %uMhz %s\n", i, freq_values[i], - i == mark_index ? "*" : ""); + cur_value == freq_values[i] ? "*" : ""); } } break; case SMU_PCIE: - gen_speed = smu_v11_0_get_current_pcie_link_speed(smu); - lane_width = smu_v11_0_get_current_pcie_link_width(smu); + gen_speed = smu_v11_0_get_current_pcie_link_speed_level(smu); + lane_width = smu_v11_0_get_current_pcie_link_width_level(smu); for (i = 0; i < NUM_LINK_LEVELS; i++) size += sprintf(buf + size, "%d: %s %s %dMhz %s\n", i, (dpm_context->dpm_tables.pcie_table.pcie_gen[i] == 0) ? "2.5GT/s," : @@ -1169,14 +1177,9 @@ static int sienna_cichlid_get_fan_speed_rpm(struct smu_context *smu, if (!speed) return -EINVAL; - switch (smu_v11_0_get_fan_control_mode(smu)) { - case AMD_FAN_CTRL_AUTO: - return sienna_cichlid_get_smu_metrics_data(smu, - METRICS_CURR_FANSPEED, - speed); - default: - return smu_v11_0_get_fan_speed_rpm(smu, speed); - } + return sienna_cichlid_get_smu_metrics_data(smu, + METRICS_CURR_FANSPEED, + speed); } static int sienna_cichlid_get_fan_parameters(struct smu_context *smu) @@ -1409,58 +1412,43 @@ static int sienna_cichlid_notify_smc_display_config(struct smu_context *smu) } static int sienna_cichlid_set_watermarks_table(struct smu_context *smu, - struct dm_pp_wm_sets_with_clock_ranges_soc15 - *clock_ranges) + struct pp_smu_wm_range_sets *clock_ranges) { Watermarks_t *table = smu->smu_table.watermarks_table; int ret = 0; int i; if (clock_ranges) { - if (clock_ranges->num_wm_dmif_sets > 4 || - clock_ranges->num_wm_mcif_sets > 4) + if (clock_ranges->num_reader_wm_sets > NUM_WM_RANGES || + clock_ranges->num_writer_wm_sets > NUM_WM_RANGES) return -EINVAL; - for (i = 0; i < clock_ranges->num_wm_dmif_sets; i++) { - table->WatermarkRow[1][i].MinClock = - cpu_to_le16((uint16_t) - (clock_ranges->wm_dmif_clocks_ranges[i].wm_min_dcfclk_clk_in_khz / - 1000)); - table->WatermarkRow[1][i].MaxClock = - cpu_to_le16((uint16_t) - (clock_ranges->wm_dmif_clocks_ranges[i].wm_max_dcfclk_clk_in_khz / - 1000)); - table->WatermarkRow[1][i].MinUclk = - cpu_to_le16((uint16_t) - (clock_ranges->wm_dmif_clocks_ranges[i].wm_min_mem_clk_in_khz / - 1000)); - table->WatermarkRow[1][i].MaxUclk = - cpu_to_le16((uint16_t) - (clock_ranges->wm_dmif_clocks_ranges[i].wm_max_mem_clk_in_khz / - 1000)); - table->WatermarkRow[1][i].WmSetting = (uint8_t) - clock_ranges->wm_dmif_clocks_ranges[i].wm_set_id; + for (i = 0; i < clock_ranges->num_reader_wm_sets; i++) { + table->WatermarkRow[WM_DCEFCLK][i].MinClock = + clock_ranges->reader_wm_sets[i].min_drain_clk_mhz; + table->WatermarkRow[WM_DCEFCLK][i].MaxClock = + clock_ranges->reader_wm_sets[i].max_drain_clk_mhz; + table->WatermarkRow[WM_DCEFCLK][i].MinUclk = + clock_ranges->reader_wm_sets[i].min_fill_clk_mhz; + table->WatermarkRow[WM_DCEFCLK][i].MaxUclk = + clock_ranges->reader_wm_sets[i].max_fill_clk_mhz; + + table->WatermarkRow[WM_DCEFCLK][i].WmSetting = + clock_ranges->reader_wm_sets[i].wm_inst; } - for (i = 0; i < clock_ranges->num_wm_mcif_sets; i++) { - table->WatermarkRow[0][i].MinClock = - cpu_to_le16((uint16_t) - (clock_ranges->wm_mcif_clocks_ranges[i].wm_min_socclk_clk_in_khz / - 1000)); - table->WatermarkRow[0][i].MaxClock = - cpu_to_le16((uint16_t) - (clock_ranges->wm_mcif_clocks_ranges[i].wm_max_socclk_clk_in_khz / - 1000)); - table->WatermarkRow[0][i].MinUclk = - cpu_to_le16((uint16_t) - (clock_ranges->wm_mcif_clocks_ranges[i].wm_min_mem_clk_in_khz / - 1000)); - table->WatermarkRow[0][i].MaxUclk = - cpu_to_le16((uint16_t) - (clock_ranges->wm_mcif_clocks_ranges[i].wm_max_mem_clk_in_khz / - 1000)); - table->WatermarkRow[0][i].WmSetting = (uint8_t) - clock_ranges->wm_mcif_clocks_ranges[i].wm_set_id; + for (i = 0; i < clock_ranges->num_writer_wm_sets; i++) { + table->WatermarkRow[WM_SOCCLK][i].MinClock = + clock_ranges->writer_wm_sets[i].min_fill_clk_mhz; + table->WatermarkRow[WM_SOCCLK][i].MaxClock = + clock_ranges->writer_wm_sets[i].max_fill_clk_mhz; + table->WatermarkRow[WM_SOCCLK][i].MinUclk = + clock_ranges->writer_wm_sets[i].min_drain_clk_mhz; + table->WatermarkRow[WM_SOCCLK][i].MaxUclk = + clock_ranges->writer_wm_sets[i].max_drain_clk_mhz; + + table->WatermarkRow[WM_SOCCLK][i].WmSetting = + clock_ranges->writer_wm_sets[i].wm_inst; } smu->watermarks_bitmap |= WATERMARKS_EXIST; @@ -2291,11 +2279,6 @@ static void sienna_cichlid_dump_pptable(struct smu_context *smu) dev_info(smu->adev->dev, "SkuReserved[6] = 0x%x\n", pptable->SkuReserved[6]); dev_info(smu->adev->dev, "SkuReserved[7] = 0x%x\n", pptable->SkuReserved[7]); dev_info(smu->adev->dev, "SkuReserved[8] = 0x%x\n", pptable->SkuReserved[8]); - dev_info(smu->adev->dev, "SkuReserved[9] = 0x%x\n", pptable->SkuReserved[9]); - dev_info(smu->adev->dev, "SkuReserved[10] = 0x%x\n", pptable->SkuReserved[10]); - dev_info(smu->adev->dev, "SkuReserved[11] = 0x%x\n", pptable->SkuReserved[11]); - dev_info(smu->adev->dev, "SkuReserved[12] = 0x%x\n", pptable->SkuReserved[12]); - dev_info(smu->adev->dev, "SkuReserved[13] = 0x%x\n", pptable->SkuReserved[13]); dev_info(smu->adev->dev, "GamingClk[0] = 0x%x\n", pptable->GamingClk[0]); dev_info(smu->adev->dev, "GamingClk[1] = 0x%x\n", pptable->GamingClk[1]); @@ -2444,8 +2427,6 @@ static void sienna_cichlid_fill_i2c_req(SwI2cRequest_t *req, bool write, { int i; - BUG_ON(numbytes > MAX_SW_I2C_COMMANDS); - req->I2CcontrollerPort = 0; req->I2CSpeed = 2; req->SlaveAddress = address; @@ -2483,6 +2464,12 @@ static int sienna_cichlid_i2c_read_data(struct i2c_adapter *control, struct smu_table_context *smu_table = &adev->smu.smu_table; struct smu_table *table = &smu_table->driver_table; + if (numbytes > MAX_SW_I2C_COMMANDS) { + dev_err(adev->dev, "numbytes requested %d is over max allowed %d\n", + numbytes, MAX_SW_I2C_COMMANDS); + return -EINVAL; + } + memset(&req, 0, sizeof(req)); sienna_cichlid_fill_i2c_req(&req, false, address, numbytes, data); @@ -2519,6 +2506,12 @@ static int sienna_cichlid_i2c_write_data(struct i2c_adapter *control, SwI2cRequest_t req; struct amdgpu_device *adev = to_amdgpu_device(control); + if (numbytes > MAX_SW_I2C_COMMANDS) { + dev_err(adev->dev, "numbytes requested %d is over max allowed %d\n", + numbytes, MAX_SW_I2C_COMMANDS); + return -EINVAL; + } + memset(&req, 0, sizeof(req)); sienna_cichlid_fill_i2c_req(&req, true, address, numbytes, data); @@ -2806,6 +2799,7 @@ static const struct pptable_funcs sienna_cichlid_ppt_funcs = { .gfx_ulv_control = smu_v11_0_gfx_ulv_control, .deep_sleep_control = smu_v11_0_deep_sleep_control, .get_fan_parameters = sienna_cichlid_get_fan_parameters, + .interrupt_work = smu_v11_0_interrupt_work, }; void sienna_cichlid_set_ppt_funcs(struct smu_context *smu) diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c index f5aeb0b5cf97..2380759ddf48 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c @@ -322,39 +322,42 @@ int smu_v11_0_setup_pptable(struct smu_context *smu) void *table; uint16_t version_major, version_minor; - hdr = (const struct smc_firmware_header_v1_0 *) adev->pm.fw->data; - version_major = le16_to_cpu(hdr->header.header_version_major); - version_minor = le16_to_cpu(hdr->header.header_version_minor); - if ((version_major == 2 && smu->smu_table.boot_values.pp_table_id > 0) || - adev->asic_type == CHIP_NAVY_FLOUNDER) { - dev_info(adev->dev, "use driver provided pptable %d\n", smu->smu_table.boot_values.pp_table_id); - switch (version_minor) { - case 0: - ret = smu_v11_0_set_pptable_v2_0(smu, &table, &size); - break; - case 1: - ret = smu_v11_0_set_pptable_v2_1(smu, &table, &size, - smu->smu_table.boot_values.pp_table_id); - break; - default: - ret = -EINVAL; - break; + if (!amdgpu_sriov_vf(adev)) { + hdr = (const struct smc_firmware_header_v1_0 *) adev->pm.fw->data; + version_major = le16_to_cpu(hdr->header.header_version_major); + version_minor = le16_to_cpu(hdr->header.header_version_minor); + if ((version_major == 2 && smu->smu_table.boot_values.pp_table_id > 0) || + adev->asic_type == CHIP_NAVY_FLOUNDER) { + dev_info(adev->dev, "use driver provided pptable %d\n", smu->smu_table.boot_values.pp_table_id); + switch (version_minor) { + case 0: + ret = smu_v11_0_set_pptable_v2_0(smu, &table, &size); + break; + case 1: + ret = smu_v11_0_set_pptable_v2_1(smu, &table, &size, + smu->smu_table.boot_values.pp_table_id); + break; + default: + ret = -EINVAL; + break; + } + if (ret) + return ret; + goto out; } - if (ret) - return ret; + } - } else { - dev_info(adev->dev, "use vbios provided pptable\n"); - index = get_index_into_master_table(atom_master_list_of_data_tables_v2_1, - powerplayinfo); + dev_info(adev->dev, "use vbios provided pptable\n"); + index = get_index_into_master_table(atom_master_list_of_data_tables_v2_1, + powerplayinfo); - ret = amdgpu_atombios_get_data_table(adev, index, &atom_table_size, &frev, &crev, - (uint8_t **)&table); - if (ret) - return ret; - size = atom_table_size; - } + ret = amdgpu_atombios_get_data_table(adev, index, &atom_table_size, &frev, &crev, + (uint8_t **)&table); + if (ret) + return ret; + size = atom_table_size; +out: if (!smu->smu_table.power_play_table) smu->smu_table.power_play_table = table; if (!smu->smu_table.power_play_table_size) @@ -453,9 +456,6 @@ int smu_v11_0_init_power(struct smu_context *smu) { struct smu_power_context *smu_power = &smu->smu_power; - if (smu_power->power_context || smu_power->power_context_size != 0) - return -EINVAL; - smu_power->power_context = kzalloc(sizeof(struct smu_11_0_dpm_context), GFP_KERNEL); if (!smu_power->power_context) @@ -469,9 +469,6 @@ int smu_v11_0_fini_power(struct smu_context *smu) { struct smu_power_context *smu_power = &smu->smu_power; - if (!smu_power->power_context || smu_power->power_context_size == 0) - return -EINVAL; - kfree(smu_power->power_context); smu_power->power_context = NULL; smu_power->power_context_size = 0; @@ -700,18 +697,16 @@ int smu_v11_0_set_tool_table_location(struct smu_context *smu) int smu_v11_0_init_display_count(struct smu_context *smu, uint32_t count) { - int ret = 0; struct amdgpu_device *adev = smu->adev; /* Navy_Flounder do not support to change display num currently */ if (adev->asic_type == CHIP_NAVY_FLOUNDER) return 0; - if (!smu->pm_enabled) - return ret; - - ret = smu_cmn_send_smc_msg_with_param(smu, SMU_MSG_NumOfDisplays, count, NULL); - return ret; + return smu_cmn_send_smc_msg_with_param(smu, + SMU_MSG_NumOfDisplays, + count, + NULL); } @@ -721,7 +716,6 @@ int smu_v11_0_set_allowed_mask(struct smu_context *smu) int ret = 0; uint32_t feature_mask[2]; - mutex_lock(&feature->mutex); if (bitmap_empty(feature->allowed, SMU_FEATURE_MAX) || feature->feature_num < 64) goto failed; @@ -738,7 +732,6 @@ int smu_v11_0_set_allowed_mask(struct smu_context *smu) goto failed; failed: - mutex_unlock(&feature->mutex); return ret; } @@ -775,9 +768,6 @@ int smu_v11_0_notify_display_change(struct smu_context *smu) { int ret = 0; - if (!smu->pm_enabled) - return ret; - if (smu_cmn_feature_is_enabled(smu, SMU_FEATURE_DPM_UCLK_BIT) && smu->adev->gmc.vram_type == AMDGPU_VRAM_TYPE_HBM) ret = smu_cmn_send_smc_msg_with_param(smu, SMU_MSG_SetUclkFastSwitch, 1, NULL); @@ -947,12 +937,45 @@ int smu_v11_0_set_power_limit(struct smu_context *smu, uint32_t n) return 0; } +static int smu_v11_0_ack_ac_dc_interrupt(struct smu_context *smu) +{ + return smu_cmn_send_smc_msg(smu, + SMU_MSG_ReenableAcDcInterrupt, + NULL); +} + +static int smu_v11_0_process_pending_interrupt(struct smu_context *smu) +{ + int ret = 0; + + if (smu->dc_controlled_by_gpio && + smu_cmn_feature_is_enabled(smu, SMU_FEATURE_ACDC_BIT)) + ret = smu_v11_0_ack_ac_dc_interrupt(smu); + + return ret; +} + +void smu_v11_0_interrupt_work(struct smu_context *smu) +{ + if (smu_v11_0_ack_ac_dc_interrupt(smu)) + dev_err(smu->adev->dev, "Ack AC/DC interrupt Failed!\n"); +} + int smu_v11_0_enable_thermal_alert(struct smu_context *smu) { - if (smu->smu_table.thermal_controller_type) - return amdgpu_irq_get(smu->adev, &smu->irq_source, 0); + int ret = 0; - return 0; + if (smu->smu_table.thermal_controller_type) { + ret = amdgpu_irq_get(smu->adev, &smu->irq_source, 0); + if (ret) + return ret; + } + + /* + * After init there might have been missed interrupts triggered + * before driver registers for interrupt (Ex. AC/DC). + */ + return smu_v11_0_process_pending_interrupt(smu); } int smu_v11_0_disable_thermal_alert(struct smu_context *smu) @@ -1177,12 +1200,10 @@ int smu_v11_0_get_fan_speed_rpm(struct smu_context *smu, int smu_v11_0_set_xgmi_pstate(struct smu_context *smu, uint32_t pstate) { - int ret = 0; - ret = smu_cmn_send_smc_msg_with_param(smu, - SMU_MSG_SetXgmiMode, - pstate ? XGMI_MODE_PSTATE_D0 : XGMI_MODE_PSTATE_D3, + return smu_cmn_send_smc_msg_with_param(smu, + SMU_MSG_SetXgmiMode, + pstate ? XGMI_MODE_PSTATE_D0 : XGMI_MODE_PSTATE_D3, NULL); - return ret; } static int smu_v11_0_set_irq_state(struct amdgpu_device *adev, @@ -1250,13 +1271,6 @@ static int smu_v11_0_set_irq_state(struct amdgpu_device *adev, return 0; } -static int smu_v11_0_ack_ac_dc_interrupt(struct smu_context *smu) -{ - return smu_cmn_send_smc_msg(smu, - SMU_MSG_ReenableAcDcInterrupt, - NULL); -} - #define THM_11_0__SRCID__THM_DIG_THERM_L2H 0 /* ASIC_TEMP > CG_THERMAL_INT.DIG_THERM_INTH */ #define THM_11_0__SRCID__THM_DIG_THERM_H2L 1 /* ASIC_TEMP < CG_THERMAL_INT.DIG_THERM_INTL */ @@ -1312,11 +1326,11 @@ static int smu_v11_0_irq_process(struct amdgpu_device *adev, switch (ctxid) { case 0x3: dev_dbg(adev->dev, "Switched to AC mode!\n"); - smu_v11_0_ack_ac_dc_interrupt(&adev->smu); + schedule_work(&smu->interrupt_work); break; case 0x4: dev_dbg(adev->dev, "Switched to DC mode!\n"); - smu_v11_0_ack_ac_dc_interrupt(&adev->smu); + schedule_work(&smu->interrupt_work); break; case 0x7: /* @@ -1413,11 +1427,7 @@ int smu_v11_0_get_max_sustainable_clocks_by_dc(struct smu_context *smu, int smu_v11_0_set_azalia_d3_pme(struct smu_context *smu) { - int ret = 0; - - ret = smu_cmn_send_smc_msg(smu, SMU_MSG_BacoAudioD3PME, NULL); - - return ret; + return smu_cmn_send_smc_msg(smu, SMU_MSG_BacoAudioD3PME, NULL); } static int smu_v11_0_baco_set_armd3_sequence(struct smu_context *smu, enum smu_v11_0_baco_seq baco_seq) @@ -1428,13 +1438,8 @@ static int smu_v11_0_baco_set_armd3_sequence(struct smu_context *smu, enum smu_v bool smu_v11_0_baco_is_support(struct smu_context *smu) { struct smu_baco_context *smu_baco = &smu->smu_baco; - bool baco_support; - mutex_lock(&smu_baco->mutex); - baco_support = smu_baco->platform_support; - mutex_unlock(&smu_baco->mutex); - - if (!baco_support) + if (!smu_baco->platform_support) return false; /* Arcturus does not support this bit mask */ @@ -1521,13 +1526,7 @@ int smu_v11_0_baco_enter(struct smu_context *smu) int smu_v11_0_baco_exit(struct smu_context *smu) { - int ret = 0; - - ret = smu_v11_0_baco_set_state(smu, SMU_BACO_STATE_EXIT); - if (ret) - return ret; - - return ret; + return smu_v11_0_baco_set_state(smu, SMU_BACO_STATE_EXIT); } int smu_v11_0_mode1_reset(struct smu_context *smu) diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu12/renoir_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu12/renoir_ppt.c index 3b9ac72c7571..66c1026489be 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu12/renoir_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu12/renoir_ppt.c @@ -222,14 +222,16 @@ static int renoir_get_profiling_clk_mask(struct smu_context *smu, *sclk_mask = 0; } else if (level == AMD_DPM_FORCED_LEVEL_PROFILE_MIN_MCLK) { if (mclk_mask) - *mclk_mask = 0; + /* mclk levels are in reverse order */ + *mclk_mask = NUM_MEMCLK_DPM_LEVELS - 1; } else if (level == AMD_DPM_FORCED_LEVEL_PROFILE_PEAK) { if(sclk_mask) /* The sclk as gfxclk and has three level about max/min/current */ *sclk_mask = 3 - 1; if(mclk_mask) - *mclk_mask = NUM_MEMCLK_DPM_LEVELS - 1; + /* mclk levels are in reverse order */ + *mclk_mask = 0; if(soc_mask) *soc_mask = NUM_SOCCLK_DPM_LEVELS - 1; @@ -323,7 +325,7 @@ static int renoir_get_dpm_ultimate_freq(struct smu_context *smu, case SMU_UCLK: case SMU_FCLK: case SMU_MCLK: - ret = renoir_get_dpm_clk_limited(smu, clk_type, 0, min); + ret = renoir_get_dpm_clk_limited(smu, clk_type, NUM_MEMCLK_DPM_LEVELS - 1, min); if (ret) goto failed; break; @@ -832,9 +834,59 @@ static int renoir_set_performance_level(struct smu_context *smu, ret = renoir_force_dpm_limit_value(smu, false); break; case AMD_DPM_FORCED_LEVEL_AUTO: - case AMD_DPM_FORCED_LEVEL_PROFILE_STANDARD: ret = renoir_unforce_dpm_levels(smu); break; + case AMD_DPM_FORCED_LEVEL_PROFILE_STANDARD: + ret = smu_cmn_send_smc_msg_with_param(smu, + SMU_MSG_SetHardMinGfxClk, + RENOIR_UMD_PSTATE_GFXCLK, + NULL); + if (ret) + return ret; + ret = smu_cmn_send_smc_msg_with_param(smu, + SMU_MSG_SetHardMinFclkByFreq, + RENOIR_UMD_PSTATE_FCLK, + NULL); + if (ret) + return ret; + ret = smu_cmn_send_smc_msg_with_param(smu, + SMU_MSG_SetHardMinSocclkByFreq, + RENOIR_UMD_PSTATE_SOCCLK, + NULL); + if (ret) + return ret; + ret = smu_cmn_send_smc_msg_with_param(smu, + SMU_MSG_SetHardMinVcn, + RENOIR_UMD_PSTATE_VCNCLK, + NULL); + if (ret) + return ret; + + ret = smu_cmn_send_smc_msg_with_param(smu, + SMU_MSG_SetSoftMaxGfxClk, + RENOIR_UMD_PSTATE_GFXCLK, + NULL); + if (ret) + return ret; + ret = smu_cmn_send_smc_msg_with_param(smu, + SMU_MSG_SetSoftMaxFclkByFreq, + RENOIR_UMD_PSTATE_FCLK, + NULL); + if (ret) + return ret; + ret = smu_cmn_send_smc_msg_with_param(smu, + SMU_MSG_SetSoftMaxSocclkByFreq, + RENOIR_UMD_PSTATE_SOCCLK, + NULL); + if (ret) + return ret; + ret = smu_cmn_send_smc_msg_with_param(smu, + SMU_MSG_SetSoftMaxVcn, + RENOIR_UMD_PSTATE_VCNCLK, + NULL); + if (ret) + return ret; + break; case AMD_DPM_FORCED_LEVEL_PROFILE_MIN_SCLK: case AMD_DPM_FORCED_LEVEL_PROFILE_MIN_MCLK: ret = renoir_get_profiling_clk_mask(smu, level, @@ -863,50 +915,48 @@ static int renoir_set_performance_level(struct smu_context *smu, */ static int renoir_set_watermarks_table( struct smu_context *smu, - struct dm_pp_wm_sets_with_clock_ranges_soc15 *clock_ranges) + struct pp_smu_wm_range_sets *clock_ranges) { Watermarks_t *table = smu->smu_table.watermarks_table; int ret = 0; int i; if (clock_ranges) { - if (clock_ranges->num_wm_dmif_sets > 4 || - clock_ranges->num_wm_mcif_sets > 4) + if (clock_ranges->num_reader_wm_sets > NUM_WM_RANGES || + clock_ranges->num_writer_wm_sets > NUM_WM_RANGES) return -EINVAL; /* save into smu->smu_table.tables[SMU_TABLE_WATERMARKS]->cpu_addr*/ - for (i = 0; i < clock_ranges->num_wm_dmif_sets; i++) { + for (i = 0; i < clock_ranges->num_reader_wm_sets; i++) { table->WatermarkRow[WM_DCFCLK][i].MinClock = - cpu_to_le16((uint16_t) - (clock_ranges->wm_dmif_clocks_ranges[i].wm_min_dcfclk_clk_in_khz)); + clock_ranges->reader_wm_sets[i].min_drain_clk_mhz; table->WatermarkRow[WM_DCFCLK][i].MaxClock = - cpu_to_le16((uint16_t) - (clock_ranges->wm_dmif_clocks_ranges[i].wm_max_dcfclk_clk_in_khz)); + clock_ranges->reader_wm_sets[i].max_drain_clk_mhz; table->WatermarkRow[WM_DCFCLK][i].MinMclk = - cpu_to_le16((uint16_t) - (clock_ranges->wm_dmif_clocks_ranges[i].wm_min_mem_clk_in_khz)); + clock_ranges->reader_wm_sets[i].min_fill_clk_mhz; table->WatermarkRow[WM_DCFCLK][i].MaxMclk = - cpu_to_le16((uint16_t) - (clock_ranges->wm_dmif_clocks_ranges[i].wm_max_mem_clk_in_khz)); - table->WatermarkRow[WM_DCFCLK][i].WmSetting = (uint8_t) - clock_ranges->wm_dmif_clocks_ranges[i].wm_set_id; + clock_ranges->reader_wm_sets[i].max_fill_clk_mhz; + + table->WatermarkRow[WM_DCFCLK][i].WmSetting = + clock_ranges->reader_wm_sets[i].wm_inst; + table->WatermarkRow[WM_DCFCLK][i].WmType = + clock_ranges->reader_wm_sets[i].wm_type; } - for (i = 0; i < clock_ranges->num_wm_mcif_sets; i++) { + for (i = 0; i < clock_ranges->num_writer_wm_sets; i++) { table->WatermarkRow[WM_SOCCLK][i].MinClock = - cpu_to_le16((uint16_t) - (clock_ranges->wm_mcif_clocks_ranges[i].wm_min_socclk_clk_in_khz)); + clock_ranges->writer_wm_sets[i].min_fill_clk_mhz; table->WatermarkRow[WM_SOCCLK][i].MaxClock = - cpu_to_le16((uint16_t) - (clock_ranges->wm_mcif_clocks_ranges[i].wm_max_socclk_clk_in_khz)); + clock_ranges->writer_wm_sets[i].max_fill_clk_mhz; table->WatermarkRow[WM_SOCCLK][i].MinMclk = - cpu_to_le16((uint16_t) - (clock_ranges->wm_mcif_clocks_ranges[i].wm_min_mem_clk_in_khz)); + clock_ranges->writer_wm_sets[i].min_drain_clk_mhz; table->WatermarkRow[WM_SOCCLK][i].MaxMclk = - cpu_to_le16((uint16_t) - (clock_ranges->wm_mcif_clocks_ranges[i].wm_max_mem_clk_in_khz)); - table->WatermarkRow[WM_SOCCLK][i].WmSetting = (uint8_t) - clock_ranges->wm_mcif_clocks_ranges[i].wm_set_id; + clock_ranges->writer_wm_sets[i].max_drain_clk_mhz; + + table->WatermarkRow[WM_SOCCLK][i].WmSetting = + clock_ranges->writer_wm_sets[i].wm_inst; + table->WatermarkRow[WM_SOCCLK][i].WmType = + clock_ranges->writer_wm_sets[i].wm_type; } smu->watermarks_bitmap |= WATERMARKS_EXIST; diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu12/renoir_ppt.h b/drivers/gpu/drm/amd/pm/swsmu/smu12/renoir_ppt.h index 8c3f004cdf8d..11c3c22fecbe 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu12/renoir_ppt.h +++ b/drivers/gpu/drm/amd/pm/swsmu/smu12/renoir_ppt.h @@ -29,5 +29,6 @@ extern void renoir_set_ppt_funcs(struct smu_context *smu); #define RENOIR_UMD_PSTATE_GFXCLK 700 #define RENOIR_UMD_PSTATE_SOCCLK 678 #define RENOIR_UMD_PSTATE_FCLK 800 +#define RENOIR_UMD_PSTATE_VCNCLK 0x022D01D8 #endif diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c b/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c index a58ea08cd115..92b2ea4c197b 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c @@ -112,6 +112,9 @@ int smu_cmn_send_smc_msg_with_param(struct smu_context *smu, struct amdgpu_device *adev = smu->adev; int ret = 0, index = 0; + if (smu->adev->in_pci_err_recovery) + return 0; + index = smu_cmn_to_asic_specific_index(smu, CMN2ASIC_MAPPING_MSG, msg); @@ -343,9 +346,9 @@ int smu_cmn_get_enabled_mask(struct smu_context *smu, return ret; } -static int smu_cmn_feature_update_enable_state(struct smu_context *smu, - uint64_t feature_mask, - bool enabled) +int smu_cmn_feature_update_enable_state(struct smu_context *smu, + uint64_t feature_mask, + bool enabled) { struct smu_feature *feature = &smu->smu_feature; int ret = 0; @@ -428,10 +431,9 @@ size_t smu_cmn_get_pp_feature_mask(struct smu_context *smu, char *buf) { uint32_t feature_mask[2] = { 0 }; - int32_t feature_index = 0; + int feature_index = 0; uint32_t count = 0; - uint32_t sort_feature[SMU_FEATURE_COUNT]; - uint64_t hw_feature_count = 0; + int8_t sort_feature[SMU_FEATURE_COUNT]; size_t size = 0; int ret = 0, i; @@ -444,23 +446,31 @@ size_t smu_cmn_get_pp_feature_mask(struct smu_context *smu, size = sprintf(buf + size, "features high: 0x%08x low: 0x%08x\n", feature_mask[1], feature_mask[0]); + memset(sort_feature, -1, sizeof(sort_feature)); + for (i = 0; i < SMU_FEATURE_COUNT; i++) { feature_index = smu_cmn_to_asic_specific_index(smu, CMN2ASIC_MAPPING_FEATURE, i); if (feature_index < 0) continue; + sort_feature[feature_index] = i; - hw_feature_count++; } - for (i = 0; i < hw_feature_count; i++) { + size += sprintf(buf + size, "%-2s. %-20s %-3s : %-s\n", + "No", "Feature", "Bit", "State"); + + for (i = 0; i < SMU_FEATURE_COUNT; i++) { + if (sort_feature[i] < 0) + continue; + size += sprintf(buf + size, "%02d. %-20s (%2d) : %s\n", - count++, - smu_get_feature_name(smu, sort_feature[i]), - i, - !!smu_cmn_feature_is_enabled(smu, sort_feature[i]) ? - "enabled" : "disabled"); + count++, + smu_get_feature_name(smu, sort_feature[i]), + i, + !!smu_cmn_feature_is_enabled(smu, sort_feature[i]) ? + "enabled" : "disabled"); } return size; diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.h b/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.h index 6d00ad740c27..ab577be23c15 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.h +++ b/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.h @@ -52,6 +52,10 @@ int smu_cmn_get_enabled_mask(struct smu_context *smu, uint32_t *feature_mask, uint32_t num); +int smu_cmn_feature_update_enable_state(struct smu_context *smu, + uint64_t feature_mask, + bool enabled); + int smu_cmn_feature_set_enabled(struct smu_context *smu, enum smu_feature_mask mask, bool enable); diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu_internal.h b/drivers/gpu/drm/amd/pm/swsmu/smu_internal.h index 38c10177ed21..c5adbe46ba0d 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu_internal.h +++ b/drivers/gpu/drm/amd/pm/swsmu/smu_internal.h @@ -42,6 +42,7 @@ #define smu_check_fw_version(smu) smu_ppt_funcs(check_fw_version, 0, smu) #define smu_write_pptable(smu) smu_ppt_funcs(write_pptable, 0, smu) #define smu_set_min_dcef_deep_sleep(smu, clk) smu_ppt_funcs(set_min_dcef_deep_sleep, 0, smu, clk) +#define smu_set_active_display_count(smu, count) smu_ppt_funcs(set_active_display_count, 0, smu, count) #define smu_set_driver_table_location(smu) smu_ppt_funcs(set_driver_table_location, 0, smu) #define smu_set_tool_table_location(smu) smu_ppt_funcs(set_tool_table_location, 0, smu) #define smu_notify_memory_pool_location(smu) smu_ppt_funcs(notify_memory_pool_location, 0, smu) @@ -83,7 +84,6 @@ #define smu_asic_set_performance_level(smu, level) smu_ppt_funcs(set_performance_level, -EINVAL, smu, level) #define smu_dump_pptable(smu) smu_ppt_funcs(dump_pptable, 0, smu) #define smu_update_pcie_parameters(smu, pcie_gen_cap, pcie_width_cap) smu_ppt_funcs(update_pcie_parameters, 0, smu, pcie_gen_cap, pcie_width_cap) -#define smu_disable_umc_cdr_12gbps_workaround(smu) smu_ppt_funcs(disable_umc_cdr_12gbps_workaround, 0, smu) #define smu_set_power_source(smu, power_src) smu_ppt_funcs(set_power_source, 0, smu, power_src) #define smu_i2c_init(smu, control) smu_ppt_funcs(i2c_init, 0, smu, control) #define smu_i2c_fini(smu, control) smu_ppt_funcs(i2c_fini, 0, smu, control) @@ -95,6 +95,7 @@ #define smu_gfx_ulv_control(smu, enablement) smu_ppt_funcs(gfx_ulv_control, 0, smu, enablement) #define smu_deep_sleep_control(smu, enablement) smu_ppt_funcs(deep_sleep_control, 0, smu, enablement) #define smu_get_fan_parameters(smu) smu_ppt_funcs(get_fan_parameters, 0, smu) +#define smu_post_init(smu) smu_ppt_funcs(post_init, 0, smu) #endif #endif diff --git a/drivers/gpu/drm/armada/armada_gem.c b/drivers/gpu/drm/armada/armada_gem.c index c343fbefe47c..21909642ee4c 100644 --- a/drivers/gpu/drm/armada/armada_gem.c +++ b/drivers/gpu/drm/armada/armada_gem.c @@ -389,7 +389,7 @@ armada_gem_prime_map_dma_buf(struct dma_buf_attachment *attach, struct armada_gem_object *dobj = drm_to_armada_gem(obj); struct scatterlist *sg; struct sg_table *sgt; - int i, num; + int i; sgt = kmalloc(sizeof(*sgt), GFP_KERNEL); if (!sgt) @@ -405,22 +405,18 @@ armada_gem_prime_map_dma_buf(struct dma_buf_attachment *attach, mapping = dobj->obj.filp->f_mapping; - for_each_sg(sgt->sgl, sg, count, i) { + for_each_sgtable_sg(sgt, sg, i) { struct page *page; page = shmem_read_mapping_page(mapping, i); - if (IS_ERR(page)) { - num = i; + if (IS_ERR(page)) goto release; - } sg_set_page(sg, page, PAGE_SIZE, 0); } - if (dma_map_sg(attach->dev, sgt->sgl, sgt->nents, dir) == 0) { - num = sgt->nents; + if (dma_map_sgtable(attach->dev, sgt, dir, 0)) goto release; - } } else if (dobj->page) { /* Single contiguous page */ if (sg_alloc_table(sgt, 1, GFP_KERNEL)) @@ -428,7 +424,7 @@ armada_gem_prime_map_dma_buf(struct dma_buf_attachment *attach, sg_set_page(sgt->sgl, dobj->page, dobj->obj.size, 0); - if (dma_map_sg(attach->dev, sgt->sgl, sgt->nents, dir) == 0) + if (dma_map_sgtable(attach->dev, sgt, dir, 0)) goto free_table; } else if (dobj->linear) { /* Single contiguous physical region - no struct page */ @@ -442,8 +438,9 @@ armada_gem_prime_map_dma_buf(struct dma_buf_attachment *attach, return sgt; release: - for_each_sg(sgt->sgl, sg, num, i) - put_page(sg_page(sg)); + for_each_sgtable_sg(sgt, sg, i) + if (sg_page(sg)) + put_page(sg_page(sg)); free_table: sg_free_table(sgt); free_sgt: @@ -459,11 +456,12 @@ static void armada_gem_prime_unmap_dma_buf(struct dma_buf_attachment *attach, int i; if (!dobj->linear) - dma_unmap_sg(attach->dev, sgt->sgl, sgt->nents, dir); + dma_unmap_sgtable(attach->dev, sgt, dir, 0); if (dobj->obj.filp) { struct scatterlist *sg; - for_each_sg(sgt->sgl, sg, sgt->nents, i) + + for_each_sgtable_sg(sgt, sg, i) put_page(sg_page(sg)); } diff --git a/drivers/gpu/drm/bridge/Kconfig b/drivers/gpu/drm/bridge/Kconfig index 3e11af4e9f63..ef91646441b1 100644 --- a/drivers/gpu/drm/bridge/Kconfig +++ b/drivers/gpu/drm/bridge/Kconfig @@ -241,6 +241,8 @@ source "drivers/gpu/drm/bridge/analogix/Kconfig" source "drivers/gpu/drm/bridge/adv7511/Kconfig" +source "drivers/gpu/drm/bridge/cadence/Kconfig" + source "drivers/gpu/drm/bridge/synopsys/Kconfig" endmenu diff --git a/drivers/gpu/drm/bridge/Makefile b/drivers/gpu/drm/bridge/Makefile index c589a6a7cbe1..2b3aff104e46 100644 --- a/drivers/gpu/drm/bridge/Makefile +++ b/drivers/gpu/drm/bridge/Makefile @@ -25,4 +25,5 @@ obj-$(CONFIG_DRM_TI_TPD12S015) += ti-tpd12s015.o obj-$(CONFIG_DRM_NWL_MIPI_DSI) += nwl-dsi.o obj-y += analogix/ +obj-y += cadence/ obj-y += synopsys/ diff --git a/drivers/gpu/drm/bridge/cadence/Kconfig b/drivers/gpu/drm/bridge/cadence/Kconfig new file mode 100644 index 000000000000..511d67b16d14 --- /dev/null +++ b/drivers/gpu/drm/bridge/cadence/Kconfig @@ -0,0 +1,24 @@ +# SPDX-License-Identifier: GPL-2.0-only +config DRM_CDNS_MHDP8546 + tristate "Cadence DPI/DP bridge" + select DRM_KMS_HELPER + select DRM_PANEL_BRIDGE + depends on OF + help + Support Cadence DPI to DP bridge. This is an internal + bridge and is meant to be directly embedded in a SoC. + It takes a DPI stream as input and outputs it encoded + in DP format. + +if DRM_CDNS_MHDP8546 + +config DRM_CDNS_MHDP8546_J721E + depends on ARCH_K3_J721E_SOC || COMPILE_TEST + bool "J721E Cadence DPI/DP wrapper support" + default y + help + Support J721E Cadence DPI/DP wrapper. This is a wrapper + which adds support for J721E related platform ops. It + initializes the J721E Display Port and sets up the + clock and data muxes. +endif diff --git a/drivers/gpu/drm/bridge/cadence/Makefile b/drivers/gpu/drm/bridge/cadence/Makefile new file mode 100644 index 000000000000..8f647991b374 --- /dev/null +++ b/drivers/gpu/drm/bridge/cadence/Makefile @@ -0,0 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only +obj-$(CONFIG_DRM_CDNS_MHDP8546) += cdns-mhdp8546.o +cdns-mhdp8546-y := cdns-mhdp8546-core.o +cdns-mhdp8546-$(CONFIG_DRM_CDNS_MHDP8546_J721E) += cdns-mhdp8546-j721e.o diff --git a/drivers/gpu/drm/bridge/cadence/cdns-mhdp8546-core.c b/drivers/gpu/drm/bridge/cadence/cdns-mhdp8546-core.c new file mode 100644 index 000000000000..d0c65610ebb5 --- /dev/null +++ b/drivers/gpu/drm/bridge/cadence/cdns-mhdp8546-core.c @@ -0,0 +1,2532 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Cadence MHDP8546 DP bridge driver. + * + * Copyright (C) 2020 Cadence Design Systems, Inc. + * + * Authors: Quentin Schulz <quentin.schulz@free-electrons.com> + * Swapnil Jakhade <sjakhade@cadence.com> + * Yuti Amonkar <yamonkar@cadence.com> + * Tomi Valkeinen <tomi.valkeinen@ti.com> + * Jyri Sarha <jsarha@ti.com> + * + * TODO: + * - Implement optimized mailbox communication using mailbox interrupts + * - Add support for power management + * - Add support for features like audio, MST and fast link training + * - Implement request_fw_cancel to handle HW_STATE + * - Fix asynchronous loading of firmware implementation + * - Add DRM helper function for cdns_mhdp_lower_link_rate + */ + +#include <linux/clk.h> +#include <linux/delay.h> +#include <linux/err.h> +#include <linux/firmware.h> +#include <linux/io.h> +#include <linux/iopoll.h> +#include <linux/irq.h> +#include <linux/module.h> +#include <linux/of.h> +#include <linux/of_device.h> +#include <linux/phy/phy.h> +#include <linux/phy/phy-dp.h> +#include <linux/platform_device.h> +#include <linux/slab.h> +#include <linux/wait.h> + +#include <drm/drm_atomic.h> +#include <drm/drm_atomic_helper.h> +#include <drm/drm_atomic_state_helper.h> +#include <drm/drm_bridge.h> +#include <drm/drm_connector.h> +#include <drm/drm_crtc_helper.h> +#include <drm/drm_dp_helper.h> +#include <drm/drm_modeset_helper_vtables.h> +#include <drm/drm_print.h> +#include <drm/drm_probe_helper.h> + +#include <asm/unaligned.h> + +#include "cdns-mhdp8546-core.h" + +#include "cdns-mhdp8546-j721e.h" + +static int cdns_mhdp_mailbox_read(struct cdns_mhdp_device *mhdp) +{ + int ret, empty; + + WARN_ON(!mutex_is_locked(&mhdp->mbox_mutex)); + + ret = readx_poll_timeout(readl, mhdp->regs + CDNS_MAILBOX_EMPTY, + empty, !empty, MAILBOX_RETRY_US, + MAILBOX_TIMEOUT_US); + if (ret < 0) + return ret; + + return readl(mhdp->regs + CDNS_MAILBOX_RX_DATA) & 0xff; +} + +static int cdns_mhdp_mailbox_write(struct cdns_mhdp_device *mhdp, u8 val) +{ + int ret, full; + + WARN_ON(!mutex_is_locked(&mhdp->mbox_mutex)); + + ret = readx_poll_timeout(readl, mhdp->regs + CDNS_MAILBOX_FULL, + full, !full, MAILBOX_RETRY_US, + MAILBOX_TIMEOUT_US); + if (ret < 0) + return ret; + + writel(val, mhdp->regs + CDNS_MAILBOX_TX_DATA); + + return 0; +} + +static int cdns_mhdp_mailbox_recv_header(struct cdns_mhdp_device *mhdp, + u8 module_id, u8 opcode, + u16 req_size) +{ + u32 mbox_size, i; + u8 header[4]; + int ret; + + /* read the header of the message */ + for (i = 0; i < sizeof(header); i++) { + ret = cdns_mhdp_mailbox_read(mhdp); + if (ret < 0) + return ret; + + header[i] = ret; + } + + mbox_size = get_unaligned_be16(header + 2); + + if (opcode != header[0] || module_id != header[1] || + req_size != mbox_size) { + /* + * If the message in mailbox is not what we want, we need to + * clear the mailbox by reading its contents. + */ + for (i = 0; i < mbox_size; i++) + if (cdns_mhdp_mailbox_read(mhdp) < 0) + break; + + return -EINVAL; + } + + return 0; +} + +static int cdns_mhdp_mailbox_recv_data(struct cdns_mhdp_device *mhdp, + u8 *buff, u16 buff_size) +{ + u32 i; + int ret; + + for (i = 0; i < buff_size; i++) { + ret = cdns_mhdp_mailbox_read(mhdp); + if (ret < 0) + return ret; + + buff[i] = ret; + } + + return 0; +} + +static int cdns_mhdp_mailbox_send(struct cdns_mhdp_device *mhdp, u8 module_id, + u8 opcode, u16 size, u8 *message) +{ + u8 header[4]; + int ret, i; + + header[0] = opcode; + header[1] = module_id; + put_unaligned_be16(size, header + 2); + + for (i = 0; i < sizeof(header); i++) { + ret = cdns_mhdp_mailbox_write(mhdp, header[i]); + if (ret) + return ret; + } + + for (i = 0; i < size; i++) { + ret = cdns_mhdp_mailbox_write(mhdp, message[i]); + if (ret) + return ret; + } + + return 0; +} + +static +int cdns_mhdp_reg_read(struct cdns_mhdp_device *mhdp, u32 addr, u32 *value) +{ + u8 msg[4], resp[8]; + int ret; + + put_unaligned_be32(addr, msg); + + mutex_lock(&mhdp->mbox_mutex); + + ret = cdns_mhdp_mailbox_send(mhdp, MB_MODULE_ID_GENERAL, + GENERAL_REGISTER_READ, + sizeof(msg), msg); + if (ret) + goto out; + + ret = cdns_mhdp_mailbox_recv_header(mhdp, MB_MODULE_ID_GENERAL, + GENERAL_REGISTER_READ, + sizeof(resp)); + if (ret) + goto out; + + ret = cdns_mhdp_mailbox_recv_data(mhdp, resp, sizeof(resp)); + if (ret) + goto out; + + /* Returned address value should be the same as requested */ + if (memcmp(msg, resp, sizeof(msg))) { + ret = -EINVAL; + goto out; + } + + *value = get_unaligned_be32(resp + 4); + +out: + mutex_unlock(&mhdp->mbox_mutex); + if (ret) { + dev_err(mhdp->dev, "Failed to read register\n"); + *value = 0; + } + + return ret; +} + +static +int cdns_mhdp_reg_write(struct cdns_mhdp_device *mhdp, u16 addr, u32 val) +{ + u8 msg[6]; + int ret; + + put_unaligned_be16(addr, msg); + put_unaligned_be32(val, msg + 2); + + mutex_lock(&mhdp->mbox_mutex); + + ret = cdns_mhdp_mailbox_send(mhdp, MB_MODULE_ID_DP_TX, + DPTX_WRITE_REGISTER, sizeof(msg), msg); + + mutex_unlock(&mhdp->mbox_mutex); + + return ret; +} + +static +int cdns_mhdp_reg_write_bit(struct cdns_mhdp_device *mhdp, u16 addr, + u8 start_bit, u8 bits_no, u32 val) +{ + u8 field[8]; + int ret; + + put_unaligned_be16(addr, field); + field[2] = start_bit; + field[3] = bits_no; + put_unaligned_be32(val, field + 4); + + mutex_lock(&mhdp->mbox_mutex); + + ret = cdns_mhdp_mailbox_send(mhdp, MB_MODULE_ID_DP_TX, + DPTX_WRITE_FIELD, sizeof(field), field); + + mutex_unlock(&mhdp->mbox_mutex); + + return ret; +} + +static +int cdns_mhdp_dpcd_read(struct cdns_mhdp_device *mhdp, + u32 addr, u8 *data, u16 len) +{ + u8 msg[5], reg[5]; + int ret; + + put_unaligned_be16(len, msg); + put_unaligned_be24(addr, msg + 2); + + mutex_lock(&mhdp->mbox_mutex); + + ret = cdns_mhdp_mailbox_send(mhdp, MB_MODULE_ID_DP_TX, + DPTX_READ_DPCD, sizeof(msg), msg); + if (ret) + goto out; + + ret = cdns_mhdp_mailbox_recv_header(mhdp, MB_MODULE_ID_DP_TX, + DPTX_READ_DPCD, + sizeof(reg) + len); + if (ret) + goto out; + + ret = cdns_mhdp_mailbox_recv_data(mhdp, reg, sizeof(reg)); + if (ret) + goto out; + + ret = cdns_mhdp_mailbox_recv_data(mhdp, data, len); + +out: + mutex_unlock(&mhdp->mbox_mutex); + + return ret; +} + +static +int cdns_mhdp_dpcd_write(struct cdns_mhdp_device *mhdp, u32 addr, u8 value) +{ + u8 msg[6], reg[5]; + int ret; + + put_unaligned_be16(1, msg); + put_unaligned_be24(addr, msg + 2); + msg[5] = value; + + mutex_lock(&mhdp->mbox_mutex); + + ret = cdns_mhdp_mailbox_send(mhdp, MB_MODULE_ID_DP_TX, + DPTX_WRITE_DPCD, sizeof(msg), msg); + if (ret) + goto out; + + ret = cdns_mhdp_mailbox_recv_header(mhdp, MB_MODULE_ID_DP_TX, + DPTX_WRITE_DPCD, sizeof(reg)); + if (ret) + goto out; + + ret = cdns_mhdp_mailbox_recv_data(mhdp, reg, sizeof(reg)); + if (ret) + goto out; + + if (addr != get_unaligned_be24(reg + 2)) + ret = -EINVAL; + +out: + mutex_unlock(&mhdp->mbox_mutex); + + if (ret) + dev_err(mhdp->dev, "dpcd write failed: %d\n", ret); + return ret; +} + +static +int cdns_mhdp_set_firmware_active(struct cdns_mhdp_device *mhdp, bool enable) +{ + u8 msg[5]; + int ret, i; + + msg[0] = GENERAL_MAIN_CONTROL; + msg[1] = MB_MODULE_ID_GENERAL; + msg[2] = 0; + msg[3] = 1; + msg[4] = enable ? FW_ACTIVE : FW_STANDBY; + + mutex_lock(&mhdp->mbox_mutex); + + for (i = 0; i < sizeof(msg); i++) { + ret = cdns_mhdp_mailbox_write(mhdp, msg[i]); + if (ret) + goto out; + } + + /* read the firmware state */ + ret = cdns_mhdp_mailbox_recv_data(mhdp, msg, sizeof(msg)); + if (ret) + goto out; + + ret = 0; + +out: + mutex_unlock(&mhdp->mbox_mutex); + + if (ret < 0) + dev_err(mhdp->dev, "set firmware active failed\n"); + return ret; +} + +static +int cdns_mhdp_get_hpd_status(struct cdns_mhdp_device *mhdp) +{ + u8 status; + int ret; + + mutex_lock(&mhdp->mbox_mutex); + + ret = cdns_mhdp_mailbox_send(mhdp, MB_MODULE_ID_DP_TX, + DPTX_HPD_STATE, 0, NULL); + if (ret) + goto err_get_hpd; + + ret = cdns_mhdp_mailbox_recv_header(mhdp, MB_MODULE_ID_DP_TX, + DPTX_HPD_STATE, + sizeof(status)); + if (ret) + goto err_get_hpd; + + ret = cdns_mhdp_mailbox_recv_data(mhdp, &status, sizeof(status)); + if (ret) + goto err_get_hpd; + + mutex_unlock(&mhdp->mbox_mutex); + + dev_dbg(mhdp->dev, "%s: HPD %splugged\n", __func__, + status ? "" : "un"); + + return status; + +err_get_hpd: + mutex_unlock(&mhdp->mbox_mutex); + + return ret; +} + +static +int cdns_mhdp_get_edid_block(void *data, u8 *edid, + unsigned int block, size_t length) +{ + struct cdns_mhdp_device *mhdp = data; + u8 msg[2], reg[2], i; + int ret; + + mutex_lock(&mhdp->mbox_mutex); + + for (i = 0; i < 4; i++) { + msg[0] = block / 2; + msg[1] = block % 2; + + ret = cdns_mhdp_mailbox_send(mhdp, MB_MODULE_ID_DP_TX, + DPTX_GET_EDID, sizeof(msg), msg); + if (ret) + continue; + + ret = cdns_mhdp_mailbox_recv_header(mhdp, MB_MODULE_ID_DP_TX, + DPTX_GET_EDID, + sizeof(reg) + length); + if (ret) + continue; + + ret = cdns_mhdp_mailbox_recv_data(mhdp, reg, sizeof(reg)); + if (ret) + continue; + + ret = cdns_mhdp_mailbox_recv_data(mhdp, edid, length); + if (ret) + continue; + + if (reg[0] == length && reg[1] == block / 2) + break; + } + + mutex_unlock(&mhdp->mbox_mutex); + + if (ret) + dev_err(mhdp->dev, "get block[%d] edid failed: %d\n", + block, ret); + + return ret; +} + +static +int cdns_mhdp_read_hpd_event(struct cdns_mhdp_device *mhdp) +{ + u8 event = 0; + int ret; + + mutex_lock(&mhdp->mbox_mutex); + + ret = cdns_mhdp_mailbox_send(mhdp, MB_MODULE_ID_DP_TX, + DPTX_READ_EVENT, 0, NULL); + if (ret) + goto out; + + ret = cdns_mhdp_mailbox_recv_header(mhdp, MB_MODULE_ID_DP_TX, + DPTX_READ_EVENT, sizeof(event)); + if (ret < 0) + goto out; + + ret = cdns_mhdp_mailbox_recv_data(mhdp, &event, sizeof(event)); +out: + mutex_unlock(&mhdp->mbox_mutex); + + if (ret < 0) + return ret; + + dev_dbg(mhdp->dev, "%s: %s%s%s%s\n", __func__, + (event & DPTX_READ_EVENT_HPD_TO_HIGH) ? "TO_HIGH " : "", + (event & DPTX_READ_EVENT_HPD_TO_LOW) ? "TO_LOW " : "", + (event & DPTX_READ_EVENT_HPD_PULSE) ? "PULSE " : "", + (event & DPTX_READ_EVENT_HPD_STATE) ? "HPD_STATE " : ""); + + return event; +} + +static +int cdns_mhdp_adjust_lt(struct cdns_mhdp_device *mhdp, unsigned int nlanes, + unsigned int udelay, const u8 *lanes_data, + u8 link_status[DP_LINK_STATUS_SIZE]) +{ + u8 payload[7]; + u8 hdr[5]; /* For DPCD read response header */ + u32 addr; + int ret; + + if (nlanes != 4 && nlanes != 2 && nlanes != 1) { + dev_err(mhdp->dev, "invalid number of lanes: %u\n", nlanes); + ret = -EINVAL; + goto out; + } + + payload[0] = nlanes; + put_unaligned_be16(udelay, payload + 1); + memcpy(payload + 3, lanes_data, nlanes); + + mutex_lock(&mhdp->mbox_mutex); + + ret = cdns_mhdp_mailbox_send(mhdp, MB_MODULE_ID_DP_TX, + DPTX_ADJUST_LT, + sizeof(payload), payload); + if (ret) + goto out; + + /* Yes, read the DPCD read command response */ + ret = cdns_mhdp_mailbox_recv_header(mhdp, MB_MODULE_ID_DP_TX, + DPTX_READ_DPCD, + sizeof(hdr) + DP_LINK_STATUS_SIZE); + if (ret) + goto out; + + ret = cdns_mhdp_mailbox_recv_data(mhdp, hdr, sizeof(hdr)); + if (ret) + goto out; + + addr = get_unaligned_be24(hdr + 2); + if (addr != DP_LANE0_1_STATUS) + goto out; + + ret = cdns_mhdp_mailbox_recv_data(mhdp, link_status, + DP_LINK_STATUS_SIZE); + +out: + mutex_unlock(&mhdp->mbox_mutex); + + if (ret) + dev_err(mhdp->dev, "Failed to adjust Link Training.\n"); + + return ret; +} + +/** + * cdns_mhdp_link_power_up() - power up a DisplayPort link + * @aux: DisplayPort AUX channel + * @link: pointer to a structure containing the link configuration + * + * Returns 0 on success or a negative error code on failure. + */ +static +int cdns_mhdp_link_power_up(struct drm_dp_aux *aux, struct cdns_mhdp_link *link) +{ + u8 value; + int err; + + /* DP_SET_POWER register is only available on DPCD v1.1 and later */ + if (link->revision < 0x11) + return 0; + + err = drm_dp_dpcd_readb(aux, DP_SET_POWER, &value); + if (err < 0) + return err; + + value &= ~DP_SET_POWER_MASK; + value |= DP_SET_POWER_D0; + + err = drm_dp_dpcd_writeb(aux, DP_SET_POWER, value); + if (err < 0) + return err; + + /* + * According to the DP 1.1 specification, a "Sink Device must exit the + * power saving state within 1 ms" (Section 2.5.3.1, Table 5-52, "Sink + * Control Field" (register 0x600). + */ + usleep_range(1000, 2000); + + return 0; +} + +/** + * cdns_mhdp_link_power_down() - power down a DisplayPort link + * @aux: DisplayPort AUX channel + * @link: pointer to a structure containing the link configuration + * + * Returns 0 on success or a negative error code on failure. + */ +static +int cdns_mhdp_link_power_down(struct drm_dp_aux *aux, + struct cdns_mhdp_link *link) +{ + u8 value; + int err; + + /* DP_SET_POWER register is only available on DPCD v1.1 and later */ + if (link->revision < 0x11) + return 0; + + err = drm_dp_dpcd_readb(aux, DP_SET_POWER, &value); + if (err < 0) + return err; + + value &= ~DP_SET_POWER_MASK; + value |= DP_SET_POWER_D3; + + err = drm_dp_dpcd_writeb(aux, DP_SET_POWER, value); + if (err < 0) + return err; + + return 0; +} + +/** + * cdns_mhdp_link_configure() - configure a DisplayPort link + * @aux: DisplayPort AUX channel + * @link: pointer to a structure containing the link configuration + * + * Returns 0 on success or a negative error code on failure. + */ +static +int cdns_mhdp_link_configure(struct drm_dp_aux *aux, + struct cdns_mhdp_link *link) +{ + u8 values[2]; + int err; + + values[0] = drm_dp_link_rate_to_bw_code(link->rate); + values[1] = link->num_lanes; + + if (link->capabilities & DP_LINK_CAP_ENHANCED_FRAMING) + values[1] |= DP_LANE_COUNT_ENHANCED_FRAME_EN; + + err = drm_dp_dpcd_write(aux, DP_LINK_BW_SET, values, sizeof(values)); + if (err < 0) + return err; + + return 0; +} + +static unsigned int cdns_mhdp_max_link_rate(struct cdns_mhdp_device *mhdp) +{ + return min(mhdp->host.link_rate, mhdp->sink.link_rate); +} + +static u8 cdns_mhdp_max_num_lanes(struct cdns_mhdp_device *mhdp) +{ + return min(mhdp->sink.lanes_cnt, mhdp->host.lanes_cnt); +} + +static u8 cdns_mhdp_eq_training_pattern_supported(struct cdns_mhdp_device *mhdp) +{ + return fls(mhdp->host.pattern_supp & mhdp->sink.pattern_supp); +} + +static bool cdns_mhdp_get_ssc_supported(struct cdns_mhdp_device *mhdp) +{ + /* Check if SSC is supported by both sides */ + return mhdp->host.ssc && mhdp->sink.ssc; +} + +static enum drm_connector_status cdns_mhdp_detect(struct cdns_mhdp_device *mhdp) +{ + dev_dbg(mhdp->dev, "%s: %d\n", __func__, mhdp->plugged); + + if (mhdp->plugged) + return connector_status_connected; + else + return connector_status_disconnected; +} + +static int cdns_mhdp_check_fw_version(struct cdns_mhdp_device *mhdp) +{ + u32 major_num, minor_num, revision; + u32 fw_ver, lib_ver; + + fw_ver = (readl(mhdp->regs + CDNS_VER_H) << 8) + | readl(mhdp->regs + CDNS_VER_L); + + lib_ver = (readl(mhdp->regs + CDNS_LIB_H_ADDR) << 8) + | readl(mhdp->regs + CDNS_LIB_L_ADDR); + + if (lib_ver < 33984) { + /* + * Older FW versions with major number 1, used to store FW + * version information by storing repository revision number + * in registers. This is for identifying these FW versions. + */ + major_num = 1; + minor_num = 2; + if (fw_ver == 26098) { + revision = 15; + } else if (lib_ver == 0 && fw_ver == 0) { + revision = 17; + } else { + dev_err(mhdp->dev, "Unsupported FW version: fw_ver = %u, lib_ver = %u\n", + fw_ver, lib_ver); + return -ENODEV; + } + } else { + /* To identify newer FW versions with major number 2 onwards. */ + major_num = fw_ver / 10000; + minor_num = (fw_ver / 100) % 100; + revision = (fw_ver % 10000) % 100; + } + + dev_dbg(mhdp->dev, "FW version: v%u.%u.%u\n", major_num, minor_num, + revision); + return 0; +} + +static int cdns_mhdp_fw_activate(const struct firmware *fw, + struct cdns_mhdp_device *mhdp) +{ + unsigned int reg; + int ret; + + /* Release uCPU reset and stall it. */ + writel(CDNS_CPU_STALL, mhdp->regs + CDNS_APB_CTRL); + + memcpy_toio(mhdp->regs + CDNS_MHDP_IMEM, fw->data, fw->size); + + /* Leave debug mode, release stall */ + writel(0, mhdp->regs + CDNS_APB_CTRL); + + /* + * Wait for the KEEP_ALIVE "message" on the first 8 bits. + * Updated each sched "tick" (~2ms) + */ + ret = readl_poll_timeout(mhdp->regs + CDNS_KEEP_ALIVE, reg, + reg & CDNS_KEEP_ALIVE_MASK, 500, + CDNS_KEEP_ALIVE_TIMEOUT); + if (ret) { + dev_err(mhdp->dev, + "device didn't give any life sign: reg %d\n", reg); + return ret; + } + + ret = cdns_mhdp_check_fw_version(mhdp); + if (ret) + return ret; + + /* Init events to 0 as it's not cleared by FW at boot but on read */ + readl(mhdp->regs + CDNS_SW_EVENT0); + readl(mhdp->regs + CDNS_SW_EVENT1); + readl(mhdp->regs + CDNS_SW_EVENT2); + readl(mhdp->regs + CDNS_SW_EVENT3); + + /* Activate uCPU */ + ret = cdns_mhdp_set_firmware_active(mhdp, true); + if (ret) + return ret; + + spin_lock(&mhdp->start_lock); + + mhdp->hw_state = MHDP_HW_READY; + + /* + * Here we must keep the lock while enabling the interrupts + * since it would otherwise be possible that interrupt enable + * code is executed after the bridge is detached. The similar + * situation is not possible in attach()/detach() callbacks + * since the hw_state changes from MHDP_HW_READY to + * MHDP_HW_STOPPED happens only due to driver removal when + * bridge should already be detached. + */ + if (mhdp->bridge_attached) + writel(~(u32)CDNS_APB_INT_MASK_SW_EVENT_INT, + mhdp->regs + CDNS_APB_INT_MASK); + + spin_unlock(&mhdp->start_lock); + + wake_up(&mhdp->fw_load_wq); + dev_dbg(mhdp->dev, "DP FW activated\n"); + + return 0; +} + +static void cdns_mhdp_fw_cb(const struct firmware *fw, void *context) +{ + struct cdns_mhdp_device *mhdp = context; + bool bridge_attached; + int ret; + + dev_dbg(mhdp->dev, "firmware callback\n"); + + if (!fw || !fw->data) { + dev_err(mhdp->dev, "%s: No firmware.\n", __func__); + return; + } + + ret = cdns_mhdp_fw_activate(fw, mhdp); + + release_firmware(fw); + + if (ret) + return; + + /* + * XXX how to make sure the bridge is still attached when + * calling drm_kms_helper_hotplug_event() after releasing + * the lock? We should not hold the spin lock when + * calling drm_kms_helper_hotplug_event() since it may + * cause a dead lock. FB-dev console calls detect from the + * same thread just down the call stack started here. + */ + spin_lock(&mhdp->start_lock); + bridge_attached = mhdp->bridge_attached; + spin_unlock(&mhdp->start_lock); + if (bridge_attached) { + if (mhdp->connector.dev) + drm_kms_helper_hotplug_event(mhdp->bridge.dev); + else + drm_bridge_hpd_notify(&mhdp->bridge, cdns_mhdp_detect(mhdp)); + } +} + +static int cdns_mhdp_load_firmware(struct cdns_mhdp_device *mhdp) +{ + int ret; + + ret = request_firmware_nowait(THIS_MODULE, true, FW_NAME, mhdp->dev, + GFP_KERNEL, mhdp, cdns_mhdp_fw_cb); + if (ret) { + dev_err(mhdp->dev, "failed to load firmware (%s), ret: %d\n", + FW_NAME, ret); + return ret; + } + + return 0; +} + +static ssize_t cdns_mhdp_transfer(struct drm_dp_aux *aux, + struct drm_dp_aux_msg *msg) +{ + struct cdns_mhdp_device *mhdp = dev_get_drvdata(aux->dev); + int ret; + + if (msg->request != DP_AUX_NATIVE_WRITE && + msg->request != DP_AUX_NATIVE_READ) + return -EOPNOTSUPP; + + if (msg->request == DP_AUX_NATIVE_WRITE) { + const u8 *buf = msg->buffer; + unsigned int i; + + for (i = 0; i < msg->size; ++i) { + ret = cdns_mhdp_dpcd_write(mhdp, + msg->address + i, buf[i]); + if (!ret) + continue; + + dev_err(mhdp->dev, + "Failed to write DPCD addr %u\n", + msg->address + i); + + return ret; + } + } else { + ret = cdns_mhdp_dpcd_read(mhdp, msg->address, + msg->buffer, msg->size); + if (ret) { + dev_err(mhdp->dev, + "Failed to read DPCD addr %u\n", + msg->address); + + return ret; + } + } + + return msg->size; +} + +static int cdns_mhdp_link_training_init(struct cdns_mhdp_device *mhdp) +{ + union phy_configure_opts phy_cfg; + u32 reg32; + int ret; + + drm_dp_dpcd_writeb(&mhdp->aux, DP_TRAINING_PATTERN_SET, + DP_TRAINING_PATTERN_DISABLE); + + /* Reset PHY configuration */ + reg32 = CDNS_PHY_COMMON_CONFIG | CDNS_PHY_TRAINING_TYPE(1); + if (!mhdp->host.scrambler) + reg32 |= CDNS_PHY_SCRAMBLER_BYPASS; + + cdns_mhdp_reg_write(mhdp, CDNS_DPTX_PHY_CONFIG, reg32); + + cdns_mhdp_reg_write(mhdp, CDNS_DP_ENHNCD, + mhdp->sink.enhanced & mhdp->host.enhanced); + + cdns_mhdp_reg_write(mhdp, CDNS_DP_LANE_EN, + CDNS_DP_LANE_EN_LANES(mhdp->link.num_lanes)); + + cdns_mhdp_link_configure(&mhdp->aux, &mhdp->link); + phy_cfg.dp.link_rate = mhdp->link.rate / 100; + phy_cfg.dp.lanes = mhdp->link.num_lanes; + + memset(phy_cfg.dp.voltage, 0, sizeof(phy_cfg.dp.voltage)); + memset(phy_cfg.dp.pre, 0, sizeof(phy_cfg.dp.pre)); + + phy_cfg.dp.ssc = cdns_mhdp_get_ssc_supported(mhdp); + phy_cfg.dp.set_lanes = true; + phy_cfg.dp.set_rate = true; + phy_cfg.dp.set_voltages = true; + ret = phy_configure(mhdp->phy, &phy_cfg); + if (ret) { + dev_err(mhdp->dev, "%s: phy_configure() failed: %d\n", + __func__, ret); + return ret; + } + + cdns_mhdp_reg_write(mhdp, CDNS_DPTX_PHY_CONFIG, + CDNS_PHY_COMMON_CONFIG | + CDNS_PHY_TRAINING_EN | + CDNS_PHY_TRAINING_TYPE(1) | + CDNS_PHY_SCRAMBLER_BYPASS); + + drm_dp_dpcd_writeb(&mhdp->aux, DP_TRAINING_PATTERN_SET, + DP_TRAINING_PATTERN_1 | DP_LINK_SCRAMBLING_DISABLE); + + return 0; +} + +static void cdns_mhdp_get_adjust_train(struct cdns_mhdp_device *mhdp, + u8 link_status[DP_LINK_STATUS_SIZE], + u8 lanes_data[CDNS_DP_MAX_NUM_LANES], + union phy_configure_opts *phy_cfg) +{ + u8 adjust, max_pre_emph, max_volt_swing; + u8 set_volt, set_pre; + unsigned int i; + + max_pre_emph = CDNS_PRE_EMPHASIS(mhdp->host.pre_emphasis) + << DP_TRAIN_PRE_EMPHASIS_SHIFT; + max_volt_swing = CDNS_VOLT_SWING(mhdp->host.volt_swing); + + for (i = 0; i < mhdp->link.num_lanes; i++) { + /* Check if Voltage swing and pre-emphasis are within limits */ + adjust = drm_dp_get_adjust_request_voltage(link_status, i); + set_volt = min(adjust, max_volt_swing); + + adjust = drm_dp_get_adjust_request_pre_emphasis(link_status, i); + set_pre = min(adjust, max_pre_emph) + >> DP_TRAIN_PRE_EMPHASIS_SHIFT; + + /* + * Voltage swing level and pre-emphasis level combination is + * not allowed: leaving pre-emphasis as-is, and adjusting + * voltage swing. + */ + if (set_volt + set_pre > 3) + set_volt = 3 - set_pre; + + phy_cfg->dp.voltage[i] = set_volt; + lanes_data[i] = set_volt; + + if (set_volt == max_volt_swing) + lanes_data[i] |= DP_TRAIN_MAX_SWING_REACHED; + + phy_cfg->dp.pre[i] = set_pre; + lanes_data[i] |= (set_pre << DP_TRAIN_PRE_EMPHASIS_SHIFT); + + if (set_pre == (max_pre_emph >> DP_TRAIN_PRE_EMPHASIS_SHIFT)) + lanes_data[i] |= DP_TRAIN_MAX_PRE_EMPHASIS_REACHED; + } +} + +static +void cdns_mhdp_set_adjust_request_voltage(u8 link_status[DP_LINK_STATUS_SIZE], + unsigned int lane, u8 volt) +{ + unsigned int s = ((lane & 1) ? + DP_ADJUST_VOLTAGE_SWING_LANE1_SHIFT : + DP_ADJUST_VOLTAGE_SWING_LANE0_SHIFT); + unsigned int idx = DP_ADJUST_REQUEST_LANE0_1 - DP_LANE0_1_STATUS + (lane >> 1); + + link_status[idx] &= ~(DP_ADJUST_VOLTAGE_SWING_LANE0_MASK << s); + link_status[idx] |= volt << s; +} + +static +void cdns_mhdp_set_adjust_request_pre_emphasis(u8 link_status[DP_LINK_STATUS_SIZE], + unsigned int lane, u8 pre_emphasis) +{ + unsigned int s = ((lane & 1) ? + DP_ADJUST_PRE_EMPHASIS_LANE1_SHIFT : + DP_ADJUST_PRE_EMPHASIS_LANE0_SHIFT); + unsigned int idx = DP_ADJUST_REQUEST_LANE0_1 - DP_LANE0_1_STATUS + (lane >> 1); + + link_status[idx] &= ~(DP_ADJUST_PRE_EMPHASIS_LANE0_MASK << s); + link_status[idx] |= pre_emphasis << s; +} + +static void cdns_mhdp_adjust_requested_eq(struct cdns_mhdp_device *mhdp, + u8 link_status[DP_LINK_STATUS_SIZE]) +{ + u8 max_pre = CDNS_PRE_EMPHASIS(mhdp->host.pre_emphasis); + u8 max_volt = CDNS_VOLT_SWING(mhdp->host.volt_swing); + unsigned int i; + u8 volt, pre; + + for (i = 0; i < mhdp->link.num_lanes; i++) { + volt = drm_dp_get_adjust_request_voltage(link_status, i); + pre = drm_dp_get_adjust_request_pre_emphasis(link_status, i); + if (volt + pre > 3) + cdns_mhdp_set_adjust_request_voltage(link_status, i, + 3 - pre); + if (mhdp->host.volt_swing & CDNS_FORCE_VOLT_SWING) + cdns_mhdp_set_adjust_request_voltage(link_status, i, + max_volt); + if (mhdp->host.pre_emphasis & CDNS_FORCE_PRE_EMPHASIS) + cdns_mhdp_set_adjust_request_pre_emphasis(link_status, + i, max_pre); + } +} + +static void cdns_mhdp_print_lt_status(const char *prefix, + struct cdns_mhdp_device *mhdp, + union phy_configure_opts *phy_cfg) +{ + char vs[8] = "0/0/0/0"; + char pe[8] = "0/0/0/0"; + unsigned int i; + + for (i = 0; i < mhdp->link.num_lanes; i++) { + vs[i * 2] = '0' + phy_cfg->dp.voltage[i]; + pe[i * 2] = '0' + phy_cfg->dp.pre[i]; + } + + vs[i * 2 - 1] = '\0'; + pe[i * 2 - 1] = '\0'; + + dev_dbg(mhdp->dev, "%s, %u lanes, %u Mbps, vs %s, pe %s\n", + prefix, + mhdp->link.num_lanes, mhdp->link.rate / 100, + vs, pe); +} + +static bool cdns_mhdp_link_training_channel_eq(struct cdns_mhdp_device *mhdp, + u8 eq_tps, + unsigned int training_interval) +{ + u8 lanes_data[CDNS_DP_MAX_NUM_LANES], fail_counter_short = 0; + u8 link_status[DP_LINK_STATUS_SIZE]; + union phy_configure_opts phy_cfg; + u32 reg32; + int ret; + bool r; + + dev_dbg(mhdp->dev, "Starting EQ phase\n"); + + /* Enable link training TPS[eq_tps] in PHY */ + reg32 = CDNS_PHY_COMMON_CONFIG | CDNS_PHY_TRAINING_EN | + CDNS_PHY_TRAINING_TYPE(eq_tps); + if (eq_tps != 4) + reg32 |= CDNS_PHY_SCRAMBLER_BYPASS; + cdns_mhdp_reg_write(mhdp, CDNS_DPTX_PHY_CONFIG, reg32); + + drm_dp_dpcd_writeb(&mhdp->aux, DP_TRAINING_PATTERN_SET, + (eq_tps != 4) ? eq_tps | DP_LINK_SCRAMBLING_DISABLE : + CDNS_DP_TRAINING_PATTERN_4); + + drm_dp_dpcd_read_link_status(&mhdp->aux, link_status); + + do { + cdns_mhdp_get_adjust_train(mhdp, link_status, lanes_data, + &phy_cfg); + phy_cfg.dp.lanes = mhdp->link.num_lanes; + phy_cfg.dp.ssc = cdns_mhdp_get_ssc_supported(mhdp); + phy_cfg.dp.set_lanes = false; + phy_cfg.dp.set_rate = false; + phy_cfg.dp.set_voltages = true; + ret = phy_configure(mhdp->phy, &phy_cfg); + if (ret) { + dev_err(mhdp->dev, "%s: phy_configure() failed: %d\n", + __func__, ret); + goto err; + } + + cdns_mhdp_adjust_lt(mhdp, mhdp->link.num_lanes, + training_interval, lanes_data, link_status); + + r = drm_dp_clock_recovery_ok(link_status, mhdp->link.num_lanes); + if (!r) + goto err; + + if (drm_dp_channel_eq_ok(link_status, mhdp->link.num_lanes)) { + cdns_mhdp_print_lt_status("EQ phase ok", mhdp, + &phy_cfg); + return true; + } + + fail_counter_short++; + + cdns_mhdp_adjust_requested_eq(mhdp, link_status); + } while (fail_counter_short < 5); + +err: + cdns_mhdp_print_lt_status("EQ phase failed", mhdp, &phy_cfg); + + return false; +} + +static void cdns_mhdp_adjust_requested_cr(struct cdns_mhdp_device *mhdp, + u8 link_status[DP_LINK_STATUS_SIZE], + u8 *req_volt, u8 *req_pre) +{ + const u8 max_volt = CDNS_VOLT_SWING(mhdp->host.volt_swing); + const u8 max_pre = CDNS_PRE_EMPHASIS(mhdp->host.pre_emphasis); + unsigned int i; + + for (i = 0; i < mhdp->link.num_lanes; i++) { + u8 val; + + val = mhdp->host.volt_swing & CDNS_FORCE_VOLT_SWING ? + max_volt : req_volt[i]; + cdns_mhdp_set_adjust_request_voltage(link_status, i, val); + + val = mhdp->host.pre_emphasis & CDNS_FORCE_PRE_EMPHASIS ? + max_pre : req_pre[i]; + cdns_mhdp_set_adjust_request_pre_emphasis(link_status, i, val); + } +} + +static +void cdns_mhdp_validate_cr(struct cdns_mhdp_device *mhdp, bool *cr_done, + bool *same_before_adjust, bool *max_swing_reached, + u8 before_cr[CDNS_DP_MAX_NUM_LANES], + u8 after_cr[DP_LINK_STATUS_SIZE], u8 *req_volt, + u8 *req_pre) +{ + const u8 max_volt = CDNS_VOLT_SWING(mhdp->host.volt_swing); + const u8 max_pre = CDNS_PRE_EMPHASIS(mhdp->host.pre_emphasis); + bool same_pre, same_volt; + unsigned int i; + u8 adjust; + + *same_before_adjust = false; + *max_swing_reached = false; + *cr_done = drm_dp_clock_recovery_ok(after_cr, mhdp->link.num_lanes); + + for (i = 0; i < mhdp->link.num_lanes; i++) { + adjust = drm_dp_get_adjust_request_voltage(after_cr, i); + req_volt[i] = min(adjust, max_volt); + + adjust = drm_dp_get_adjust_request_pre_emphasis(after_cr, i) >> + DP_TRAIN_PRE_EMPHASIS_SHIFT; + req_pre[i] = min(adjust, max_pre); + + same_pre = (before_cr[i] & DP_TRAIN_PRE_EMPHASIS_MASK) == + req_pre[i] << DP_TRAIN_PRE_EMPHASIS_SHIFT; + same_volt = (before_cr[i] & DP_TRAIN_VOLTAGE_SWING_MASK) == + req_volt[i]; + if (same_pre && same_volt) + *same_before_adjust = true; + + /* 3.1.5.2 in DP Standard v1.4. Table 3-1 */ + if (!*cr_done && req_volt[i] + req_pre[i] >= 3) { + *max_swing_reached = true; + return; + } + } +} + +static bool cdns_mhdp_link_training_cr(struct cdns_mhdp_device *mhdp) +{ + u8 lanes_data[CDNS_DP_MAX_NUM_LANES], + fail_counter_short = 0, fail_counter_cr_long = 0; + u8 link_status[DP_LINK_STATUS_SIZE]; + bool cr_done; + union phy_configure_opts phy_cfg; + int ret; + + dev_dbg(mhdp->dev, "Starting CR phase\n"); + + ret = cdns_mhdp_link_training_init(mhdp); + if (ret) + goto err; + + drm_dp_dpcd_read_link_status(&mhdp->aux, link_status); + + do { + u8 requested_adjust_volt_swing[CDNS_DP_MAX_NUM_LANES] = {}; + u8 requested_adjust_pre_emphasis[CDNS_DP_MAX_NUM_LANES] = {}; + bool same_before_adjust, max_swing_reached; + + cdns_mhdp_get_adjust_train(mhdp, link_status, lanes_data, + &phy_cfg); + phy_cfg.dp.lanes = mhdp->link.num_lanes; + phy_cfg.dp.ssc = cdns_mhdp_get_ssc_supported(mhdp); + phy_cfg.dp.set_lanes = false; + phy_cfg.dp.set_rate = false; + phy_cfg.dp.set_voltages = true; + ret = phy_configure(mhdp->phy, &phy_cfg); + if (ret) { + dev_err(mhdp->dev, "%s: phy_configure() failed: %d\n", + __func__, ret); + goto err; + } + + cdns_mhdp_adjust_lt(mhdp, mhdp->link.num_lanes, 100, + lanes_data, link_status); + + cdns_mhdp_validate_cr(mhdp, &cr_done, &same_before_adjust, + &max_swing_reached, lanes_data, + link_status, + requested_adjust_volt_swing, + requested_adjust_pre_emphasis); + + if (max_swing_reached) { + dev_err(mhdp->dev, "CR: max swing reached\n"); + goto err; + } + + if (cr_done) { + cdns_mhdp_print_lt_status("CR phase ok", mhdp, + &phy_cfg); + return true; + } + + /* Not all CR_DONE bits set */ + fail_counter_cr_long++; + + if (same_before_adjust) { + fail_counter_short++; + continue; + } + + fail_counter_short = 0; + /* + * Voltage swing/pre-emphasis adjust requested + * during CR phase + */ + cdns_mhdp_adjust_requested_cr(mhdp, link_status, + requested_adjust_volt_swing, + requested_adjust_pre_emphasis); + } while (fail_counter_short < 5 && fail_counter_cr_long < 10); + +err: + cdns_mhdp_print_lt_status("CR phase failed", mhdp, &phy_cfg); + + return false; +} + +static void cdns_mhdp_lower_link_rate(struct cdns_mhdp_link *link) +{ + switch (drm_dp_link_rate_to_bw_code(link->rate)) { + case DP_LINK_BW_2_7: + link->rate = drm_dp_bw_code_to_link_rate(DP_LINK_BW_1_62); + break; + case DP_LINK_BW_5_4: + link->rate = drm_dp_bw_code_to_link_rate(DP_LINK_BW_2_7); + break; + case DP_LINK_BW_8_1: + link->rate = drm_dp_bw_code_to_link_rate(DP_LINK_BW_5_4); + break; + } +} + +static int cdns_mhdp_link_training(struct cdns_mhdp_device *mhdp, + unsigned int training_interval) +{ + u32 reg32; + const u8 eq_tps = cdns_mhdp_eq_training_pattern_supported(mhdp); + int ret; + + while (1) { + if (!cdns_mhdp_link_training_cr(mhdp)) { + if (drm_dp_link_rate_to_bw_code(mhdp->link.rate) != + DP_LINK_BW_1_62) { + dev_dbg(mhdp->dev, + "Reducing link rate during CR phase\n"); + cdns_mhdp_lower_link_rate(&mhdp->link); + + continue; + } else if (mhdp->link.num_lanes > 1) { + dev_dbg(mhdp->dev, + "Reducing lanes number during CR phase\n"); + mhdp->link.num_lanes >>= 1; + mhdp->link.rate = cdns_mhdp_max_link_rate(mhdp); + + continue; + } + + dev_err(mhdp->dev, + "Link training failed during CR phase\n"); + goto err; + } + + if (cdns_mhdp_link_training_channel_eq(mhdp, eq_tps, + training_interval)) + break; + + if (mhdp->link.num_lanes > 1) { + dev_dbg(mhdp->dev, + "Reducing lanes number during EQ phase\n"); + mhdp->link.num_lanes >>= 1; + + continue; + } else if (drm_dp_link_rate_to_bw_code(mhdp->link.rate) != + DP_LINK_BW_1_62) { + dev_dbg(mhdp->dev, + "Reducing link rate during EQ phase\n"); + cdns_mhdp_lower_link_rate(&mhdp->link); + mhdp->link.num_lanes = cdns_mhdp_max_num_lanes(mhdp); + + continue; + } + + dev_err(mhdp->dev, "Link training failed during EQ phase\n"); + goto err; + } + + dev_dbg(mhdp->dev, "Link training ok. Lanes: %u, Rate %u Mbps\n", + mhdp->link.num_lanes, mhdp->link.rate / 100); + + drm_dp_dpcd_writeb(&mhdp->aux, DP_TRAINING_PATTERN_SET, + mhdp->host.scrambler ? 0 : + DP_LINK_SCRAMBLING_DISABLE); + + ret = cdns_mhdp_reg_read(mhdp, CDNS_DP_FRAMER_GLOBAL_CONFIG, ®32); + if (ret < 0) { + dev_err(mhdp->dev, + "Failed to read CDNS_DP_FRAMER_GLOBAL_CONFIG %d\n", + ret); + return ret; + } + reg32 &= ~GENMASK(1, 0); + reg32 |= CDNS_DP_NUM_LANES(mhdp->link.num_lanes); + reg32 |= CDNS_DP_WR_FAILING_EDGE_VSYNC; + reg32 |= CDNS_DP_FRAMER_EN; + cdns_mhdp_reg_write(mhdp, CDNS_DP_FRAMER_GLOBAL_CONFIG, reg32); + + /* Reset PHY config */ + reg32 = CDNS_PHY_COMMON_CONFIG | CDNS_PHY_TRAINING_TYPE(1); + if (!mhdp->host.scrambler) + reg32 |= CDNS_PHY_SCRAMBLER_BYPASS; + cdns_mhdp_reg_write(mhdp, CDNS_DPTX_PHY_CONFIG, reg32); + + return 0; +err: + /* Reset PHY config */ + reg32 = CDNS_PHY_COMMON_CONFIG | CDNS_PHY_TRAINING_TYPE(1); + if (!mhdp->host.scrambler) + reg32 |= CDNS_PHY_SCRAMBLER_BYPASS; + cdns_mhdp_reg_write(mhdp, CDNS_DPTX_PHY_CONFIG, reg32); + + drm_dp_dpcd_writeb(&mhdp->aux, DP_TRAINING_PATTERN_SET, + DP_TRAINING_PATTERN_DISABLE); + + return -EIO; +} + +static u32 cdns_mhdp_get_training_interval_us(struct cdns_mhdp_device *mhdp, + u32 interval) +{ + if (interval == 0) + return 400; + if (interval < 5) + return 4000 << (interval - 1); + dev_err(mhdp->dev, + "wrong training interval returned by DPCD: %d\n", interval); + return 0; +} + +static void cdns_mhdp_fill_host_caps(struct cdns_mhdp_device *mhdp) +{ + unsigned int link_rate; + + /* Get source capabilities based on PHY attributes */ + + mhdp->host.lanes_cnt = mhdp->phy->attrs.bus_width; + if (!mhdp->host.lanes_cnt) + mhdp->host.lanes_cnt = 4; + + link_rate = mhdp->phy->attrs.max_link_rate; + if (!link_rate) + link_rate = drm_dp_bw_code_to_link_rate(DP_LINK_BW_8_1); + else + /* PHY uses Mb/s, DRM uses tens of kb/s. */ + link_rate *= 100; + + mhdp->host.link_rate = link_rate; + mhdp->host.volt_swing = CDNS_VOLT_SWING(3); + mhdp->host.pre_emphasis = CDNS_PRE_EMPHASIS(3); + mhdp->host.pattern_supp = CDNS_SUPPORT_TPS(1) | + CDNS_SUPPORT_TPS(2) | CDNS_SUPPORT_TPS(3) | + CDNS_SUPPORT_TPS(4); + mhdp->host.lane_mapping = CDNS_LANE_MAPPING_NORMAL; + mhdp->host.fast_link = false; + mhdp->host.enhanced = true; + mhdp->host.scrambler = true; + mhdp->host.ssc = false; +} + +static void cdns_mhdp_fill_sink_caps(struct cdns_mhdp_device *mhdp, + u8 dpcd[DP_RECEIVER_CAP_SIZE]) +{ + mhdp->sink.link_rate = mhdp->link.rate; + mhdp->sink.lanes_cnt = mhdp->link.num_lanes; + mhdp->sink.enhanced = !!(mhdp->link.capabilities & + DP_LINK_CAP_ENHANCED_FRAMING); + + /* Set SSC support */ + mhdp->sink.ssc = !!(dpcd[DP_MAX_DOWNSPREAD] & + DP_MAX_DOWNSPREAD_0_5); + + /* Set TPS support */ + mhdp->sink.pattern_supp = CDNS_SUPPORT_TPS(1) | CDNS_SUPPORT_TPS(2); + if (drm_dp_tps3_supported(dpcd)) + mhdp->sink.pattern_supp |= CDNS_SUPPORT_TPS(3); + if (drm_dp_tps4_supported(dpcd)) + mhdp->sink.pattern_supp |= CDNS_SUPPORT_TPS(4); + + /* Set fast link support */ + mhdp->sink.fast_link = !!(dpcd[DP_MAX_DOWNSPREAD] & + DP_NO_AUX_HANDSHAKE_LINK_TRAINING); +} + +static int cdns_mhdp_link_up(struct cdns_mhdp_device *mhdp) +{ + u8 dpcd[DP_RECEIVER_CAP_SIZE], amp[2]; + u32 resp, interval, interval_us; + u8 ext_cap_chk = 0; + unsigned int addr; + int err; + + WARN_ON(!mutex_is_locked(&mhdp->link_mutex)); + + drm_dp_dpcd_readb(&mhdp->aux, DP_TRAINING_AUX_RD_INTERVAL, + &ext_cap_chk); + + if (ext_cap_chk & DP_EXTENDED_RECEIVER_CAP_FIELD_PRESENT) + addr = DP_DP13_DPCD_REV; + else + addr = DP_DPCD_REV; + + err = drm_dp_dpcd_read(&mhdp->aux, addr, dpcd, DP_RECEIVER_CAP_SIZE); + if (err < 0) { + dev_err(mhdp->dev, "Failed to read receiver capabilities\n"); + return err; + } + + mhdp->link.revision = dpcd[0]; + mhdp->link.rate = drm_dp_bw_code_to_link_rate(dpcd[1]); + mhdp->link.num_lanes = dpcd[2] & DP_MAX_LANE_COUNT_MASK; + + if (dpcd[2] & DP_ENHANCED_FRAME_CAP) + mhdp->link.capabilities |= DP_LINK_CAP_ENHANCED_FRAMING; + + dev_dbg(mhdp->dev, "Set sink device power state via DPCD\n"); + cdns_mhdp_link_power_up(&mhdp->aux, &mhdp->link); + + cdns_mhdp_fill_sink_caps(mhdp, dpcd); + + mhdp->link.rate = cdns_mhdp_max_link_rate(mhdp); + mhdp->link.num_lanes = cdns_mhdp_max_num_lanes(mhdp); + + /* Disable framer for link training */ + err = cdns_mhdp_reg_read(mhdp, CDNS_DP_FRAMER_GLOBAL_CONFIG, &resp); + if (err < 0) { + dev_err(mhdp->dev, + "Failed to read CDNS_DP_FRAMER_GLOBAL_CONFIG %d\n", + err); + return err; + } + + resp &= ~CDNS_DP_FRAMER_EN; + cdns_mhdp_reg_write(mhdp, CDNS_DP_FRAMER_GLOBAL_CONFIG, resp); + + /* Spread AMP if required, enable 8b/10b coding */ + amp[0] = cdns_mhdp_get_ssc_supported(mhdp) ? DP_SPREAD_AMP_0_5 : 0; + amp[1] = DP_SET_ANSI_8B10B; + drm_dp_dpcd_write(&mhdp->aux, DP_DOWNSPREAD_CTRL, amp, 2); + + if (mhdp->host.fast_link & mhdp->sink.fast_link) { + dev_err(mhdp->dev, "fastlink not supported\n"); + return -EOPNOTSUPP; + } + + interval = dpcd[DP_TRAINING_AUX_RD_INTERVAL] & DP_TRAINING_AUX_RD_MASK; + interval_us = cdns_mhdp_get_training_interval_us(mhdp, interval); + if (!interval_us || + cdns_mhdp_link_training(mhdp, interval_us)) { + dev_err(mhdp->dev, "Link training failed. Exiting.\n"); + return -EIO; + } + + mhdp->link_up = true; + + return 0; +} + +static void cdns_mhdp_link_down(struct cdns_mhdp_device *mhdp) +{ + WARN_ON(!mutex_is_locked(&mhdp->link_mutex)); + + if (mhdp->plugged) + cdns_mhdp_link_power_down(&mhdp->aux, &mhdp->link); + + mhdp->link_up = false; +} + +static struct edid *cdns_mhdp_get_edid(struct cdns_mhdp_device *mhdp, + struct drm_connector *connector) +{ + if (!mhdp->plugged) + return NULL; + + return drm_do_get_edid(connector, cdns_mhdp_get_edid_block, mhdp); +} + +static int cdns_mhdp_get_modes(struct drm_connector *connector) +{ + struct cdns_mhdp_device *mhdp = connector_to_mhdp(connector); + struct edid *edid; + int num_modes; + + if (!mhdp->plugged) + return 0; + + edid = cdns_mhdp_get_edid(mhdp, connector); + if (!edid) { + dev_err(mhdp->dev, "Failed to read EDID\n"); + return 0; + } + + drm_connector_update_edid_property(connector, edid); + num_modes = drm_add_edid_modes(connector, edid); + kfree(edid); + + /* + * HACK: Warn about unsupported display formats until we deal + * with them correctly. + */ + if (connector->display_info.color_formats && + !(connector->display_info.color_formats & + mhdp->display_fmt.color_format)) + dev_warn(mhdp->dev, + "%s: No supported color_format found (0x%08x)\n", + __func__, connector->display_info.color_formats); + + if (connector->display_info.bpc && + connector->display_info.bpc < mhdp->display_fmt.bpc) + dev_warn(mhdp->dev, "%s: Display bpc only %d < %d\n", + __func__, connector->display_info.bpc, + mhdp->display_fmt.bpc); + + return num_modes; +} + +static int cdns_mhdp_connector_detect(struct drm_connector *conn, + struct drm_modeset_acquire_ctx *ctx, + bool force) +{ + struct cdns_mhdp_device *mhdp = connector_to_mhdp(conn); + + return cdns_mhdp_detect(mhdp); +} + +static u32 cdns_mhdp_get_bpp(struct cdns_mhdp_display_fmt *fmt) +{ + u32 bpp; + + if (fmt->y_only) + return fmt->bpc; + + switch (fmt->color_format) { + case DRM_COLOR_FORMAT_RGB444: + case DRM_COLOR_FORMAT_YCRCB444: + bpp = fmt->bpc * 3; + break; + case DRM_COLOR_FORMAT_YCRCB422: + bpp = fmt->bpc * 2; + break; + case DRM_COLOR_FORMAT_YCRCB420: + bpp = fmt->bpc * 3 / 2; + break; + default: + bpp = fmt->bpc * 3; + WARN_ON(1); + } + return bpp; +} + +static +bool cdns_mhdp_bandwidth_ok(struct cdns_mhdp_device *mhdp, + const struct drm_display_mode *mode, + unsigned int lanes, unsigned int rate) +{ + u32 max_bw, req_bw, bpp; + + /* + * mode->clock is expressed in kHz. Multiplying by bpp and dividing by 8 + * we get the number of kB/s. DisplayPort applies a 8b-10b encoding, the + * value thus equals the bandwidth in 10kb/s units, which matches the + * units of the rate parameter. + */ + + bpp = cdns_mhdp_get_bpp(&mhdp->display_fmt); + req_bw = mode->clock * bpp / 8; + max_bw = lanes * rate; + if (req_bw > max_bw) { + dev_dbg(mhdp->dev, + "Unsupported Mode: %s, Req BW: %u, Available Max BW:%u\n", + mode->name, req_bw, max_bw); + + return false; + } + + return true; +} + +static +enum drm_mode_status cdns_mhdp_mode_valid(struct drm_connector *conn, + struct drm_display_mode *mode) +{ + struct cdns_mhdp_device *mhdp = connector_to_mhdp(conn); + + mutex_lock(&mhdp->link_mutex); + + if (!cdns_mhdp_bandwidth_ok(mhdp, mode, mhdp->link.num_lanes, + mhdp->link.rate)) { + mutex_unlock(&mhdp->link_mutex); + return MODE_CLOCK_HIGH; + } + + mutex_unlock(&mhdp->link_mutex); + return MODE_OK; +} + +static const struct drm_connector_helper_funcs cdns_mhdp_conn_helper_funcs = { + .detect_ctx = cdns_mhdp_connector_detect, + .get_modes = cdns_mhdp_get_modes, + .mode_valid = cdns_mhdp_mode_valid, +}; + +static const struct drm_connector_funcs cdns_mhdp_conn_funcs = { + .fill_modes = drm_helper_probe_single_connector_modes, + .atomic_duplicate_state = drm_atomic_helper_connector_duplicate_state, + .atomic_destroy_state = drm_atomic_helper_connector_destroy_state, + .reset = drm_atomic_helper_connector_reset, + .destroy = drm_connector_cleanup, +}; + +static int cdns_mhdp_connector_init(struct cdns_mhdp_device *mhdp) +{ + u32 bus_format = MEDIA_BUS_FMT_RGB121212_1X36; + struct drm_connector *conn = &mhdp->connector; + struct drm_bridge *bridge = &mhdp->bridge; + int ret; + + if (!bridge->encoder) { + dev_err(mhdp->dev, "Parent encoder object not found"); + return -ENODEV; + } + + conn->polled = DRM_CONNECTOR_POLL_HPD; + + ret = drm_connector_init(bridge->dev, conn, &cdns_mhdp_conn_funcs, + DRM_MODE_CONNECTOR_DisplayPort); + if (ret) { + dev_err(mhdp->dev, "Failed to initialize connector with drm\n"); + return ret; + } + + drm_connector_helper_add(conn, &cdns_mhdp_conn_helper_funcs); + + ret = drm_display_info_set_bus_formats(&conn->display_info, + &bus_format, 1); + if (ret) + return ret; + + ret = drm_connector_attach_encoder(conn, bridge->encoder); + if (ret) { + dev_err(mhdp->dev, "Failed to attach connector to encoder\n"); + return ret; + } + + return 0; +} + +static int cdns_mhdp_attach(struct drm_bridge *bridge, + enum drm_bridge_attach_flags flags) +{ + struct cdns_mhdp_device *mhdp = bridge_to_mhdp(bridge); + bool hw_ready; + int ret; + + dev_dbg(mhdp->dev, "%s\n", __func__); + + if (!(flags & DRM_BRIDGE_ATTACH_NO_CONNECTOR)) { + ret = cdns_mhdp_connector_init(mhdp); + if (ret) + return ret; + } + + spin_lock(&mhdp->start_lock); + + mhdp->bridge_attached = true; + hw_ready = mhdp->hw_state == MHDP_HW_READY; + + spin_unlock(&mhdp->start_lock); + + /* Enable SW event interrupts */ + if (hw_ready) + writel(~(u32)CDNS_APB_INT_MASK_SW_EVENT_INT, + mhdp->regs + CDNS_APB_INT_MASK); + + return 0; +} + +static void cdns_mhdp_configure_video(struct cdns_mhdp_device *mhdp, + const struct drm_display_mode *mode) +{ + unsigned int dp_framer_sp = 0, msa_horizontal_1, + msa_vertical_1, bnd_hsync2vsync, hsync2vsync_pol_ctrl, + misc0 = 0, misc1 = 0, pxl_repr, + front_porch, back_porch, msa_h0, msa_v0, hsync, vsync, + dp_vertical_1; + u8 stream_id = mhdp->stream_id; + u32 bpp, bpc, pxlfmt, framer; + int ret; + + pxlfmt = mhdp->display_fmt.color_format; + bpc = mhdp->display_fmt.bpc; + + /* + * If YCBCR supported and stream not SD, use ITU709 + * Need to handle ITU version with YCBCR420 when supported + */ + if ((pxlfmt == DRM_COLOR_FORMAT_YCRCB444 || + pxlfmt == DRM_COLOR_FORMAT_YCRCB422) && mode->crtc_vdisplay >= 720) + misc0 = DP_YCBCR_COEFFICIENTS_ITU709; + + bpp = cdns_mhdp_get_bpp(&mhdp->display_fmt); + + switch (pxlfmt) { + case DRM_COLOR_FORMAT_RGB444: + pxl_repr = CDNS_DP_FRAMER_RGB << CDNS_DP_FRAMER_PXL_FORMAT; + misc0 |= DP_COLOR_FORMAT_RGB; + break; + case DRM_COLOR_FORMAT_YCRCB444: + pxl_repr = CDNS_DP_FRAMER_YCBCR444 << CDNS_DP_FRAMER_PXL_FORMAT; + misc0 |= DP_COLOR_FORMAT_YCbCr444 | DP_TEST_DYNAMIC_RANGE_CEA; + break; + case DRM_COLOR_FORMAT_YCRCB422: + pxl_repr = CDNS_DP_FRAMER_YCBCR422 << CDNS_DP_FRAMER_PXL_FORMAT; + misc0 |= DP_COLOR_FORMAT_YCbCr422 | DP_TEST_DYNAMIC_RANGE_CEA; + break; + case DRM_COLOR_FORMAT_YCRCB420: + pxl_repr = CDNS_DP_FRAMER_YCBCR420 << CDNS_DP_FRAMER_PXL_FORMAT; + break; + default: + pxl_repr = CDNS_DP_FRAMER_Y_ONLY << CDNS_DP_FRAMER_PXL_FORMAT; + } + + switch (bpc) { + case 6: + misc0 |= DP_TEST_BIT_DEPTH_6; + pxl_repr |= CDNS_DP_FRAMER_6_BPC; + break; + case 8: + misc0 |= DP_TEST_BIT_DEPTH_8; + pxl_repr |= CDNS_DP_FRAMER_8_BPC; + break; + case 10: + misc0 |= DP_TEST_BIT_DEPTH_10; + pxl_repr |= CDNS_DP_FRAMER_10_BPC; + break; + case 12: + misc0 |= DP_TEST_BIT_DEPTH_12; + pxl_repr |= CDNS_DP_FRAMER_12_BPC; + break; + case 16: + misc0 |= DP_TEST_BIT_DEPTH_16; + pxl_repr |= CDNS_DP_FRAMER_16_BPC; + break; + } + + bnd_hsync2vsync = CDNS_IP_BYPASS_V_INTERFACE; + if (mode->flags & DRM_MODE_FLAG_INTERLACE) + bnd_hsync2vsync |= CDNS_IP_DET_INTERLACE_FORMAT; + + cdns_mhdp_reg_write(mhdp, CDNS_BND_HSYNC2VSYNC(stream_id), + bnd_hsync2vsync); + + hsync2vsync_pol_ctrl = 0; + if (mode->flags & DRM_MODE_FLAG_NHSYNC) + hsync2vsync_pol_ctrl |= CDNS_H2V_HSYNC_POL_ACTIVE_LOW; + if (mode->flags & DRM_MODE_FLAG_NVSYNC) + hsync2vsync_pol_ctrl |= CDNS_H2V_VSYNC_POL_ACTIVE_LOW; + cdns_mhdp_reg_write(mhdp, CDNS_HSYNC2VSYNC_POL_CTRL(stream_id), + hsync2vsync_pol_ctrl); + + cdns_mhdp_reg_write(mhdp, CDNS_DP_FRAMER_PXL_REPR(stream_id), pxl_repr); + + if (mode->flags & DRM_MODE_FLAG_INTERLACE) + dp_framer_sp |= CDNS_DP_FRAMER_INTERLACE; + if (mode->flags & DRM_MODE_FLAG_NHSYNC) + dp_framer_sp |= CDNS_DP_FRAMER_HSYNC_POL_LOW; + if (mode->flags & DRM_MODE_FLAG_NVSYNC) + dp_framer_sp |= CDNS_DP_FRAMER_VSYNC_POL_LOW; + cdns_mhdp_reg_write(mhdp, CDNS_DP_FRAMER_SP(stream_id), dp_framer_sp); + + front_porch = mode->crtc_hsync_start - mode->crtc_hdisplay; + back_porch = mode->crtc_htotal - mode->crtc_hsync_end; + cdns_mhdp_reg_write(mhdp, CDNS_DP_FRONT_BACK_PORCH(stream_id), + CDNS_DP_FRONT_PORCH(front_porch) | + CDNS_DP_BACK_PORCH(back_porch)); + + cdns_mhdp_reg_write(mhdp, CDNS_DP_BYTE_COUNT(stream_id), + mode->crtc_hdisplay * bpp / 8); + + msa_h0 = mode->crtc_htotal - mode->crtc_hsync_start; + cdns_mhdp_reg_write(mhdp, CDNS_DP_MSA_HORIZONTAL_0(stream_id), + CDNS_DP_MSAH0_H_TOTAL(mode->crtc_htotal) | + CDNS_DP_MSAH0_HSYNC_START(msa_h0)); + + hsync = mode->crtc_hsync_end - mode->crtc_hsync_start; + msa_horizontal_1 = CDNS_DP_MSAH1_HSYNC_WIDTH(hsync) | + CDNS_DP_MSAH1_HDISP_WIDTH(mode->crtc_hdisplay); + if (mode->flags & DRM_MODE_FLAG_NHSYNC) + msa_horizontal_1 |= CDNS_DP_MSAH1_HSYNC_POL_LOW; + cdns_mhdp_reg_write(mhdp, CDNS_DP_MSA_HORIZONTAL_1(stream_id), + msa_horizontal_1); + + msa_v0 = mode->crtc_vtotal - mode->crtc_vsync_start; + cdns_mhdp_reg_write(mhdp, CDNS_DP_MSA_VERTICAL_0(stream_id), + CDNS_DP_MSAV0_V_TOTAL(mode->crtc_vtotal) | + CDNS_DP_MSAV0_VSYNC_START(msa_v0)); + + vsync = mode->crtc_vsync_end - mode->crtc_vsync_start; + msa_vertical_1 = CDNS_DP_MSAV1_VSYNC_WIDTH(vsync) | + CDNS_DP_MSAV1_VDISP_WIDTH(mode->crtc_vdisplay); + if (mode->flags & DRM_MODE_FLAG_NVSYNC) + msa_vertical_1 |= CDNS_DP_MSAV1_VSYNC_POL_LOW; + cdns_mhdp_reg_write(mhdp, CDNS_DP_MSA_VERTICAL_1(stream_id), + msa_vertical_1); + + if ((mode->flags & DRM_MODE_FLAG_INTERLACE) && + mode->crtc_vtotal % 2 == 0) + misc1 = DP_TEST_INTERLACED; + if (mhdp->display_fmt.y_only) + misc1 |= CDNS_DP_TEST_COLOR_FORMAT_RAW_Y_ONLY; + /* Use VSC SDP for Y420 */ + if (pxlfmt == DRM_COLOR_FORMAT_YCRCB420) + misc1 = CDNS_DP_TEST_VSC_SDP; + + cdns_mhdp_reg_write(mhdp, CDNS_DP_MSA_MISC(stream_id), + misc0 | (misc1 << 8)); + + cdns_mhdp_reg_write(mhdp, CDNS_DP_HORIZONTAL(stream_id), + CDNS_DP_H_HSYNC_WIDTH(hsync) | + CDNS_DP_H_H_TOTAL(mode->crtc_hdisplay)); + + cdns_mhdp_reg_write(mhdp, CDNS_DP_VERTICAL_0(stream_id), + CDNS_DP_V0_VHEIGHT(mode->crtc_vdisplay) | + CDNS_DP_V0_VSTART(msa_v0)); + + dp_vertical_1 = CDNS_DP_V1_VTOTAL(mode->crtc_vtotal); + if ((mode->flags & DRM_MODE_FLAG_INTERLACE) && + mode->crtc_vtotal % 2 == 0) + dp_vertical_1 |= CDNS_DP_V1_VTOTAL_EVEN; + + cdns_mhdp_reg_write(mhdp, CDNS_DP_VERTICAL_1(stream_id), dp_vertical_1); + + cdns_mhdp_reg_write_bit(mhdp, CDNS_DP_VB_ID(stream_id), 2, 1, + (mode->flags & DRM_MODE_FLAG_INTERLACE) ? + CDNS_DP_VB_ID_INTERLACED : 0); + + ret = cdns_mhdp_reg_read(mhdp, CDNS_DP_FRAMER_GLOBAL_CONFIG, &framer); + if (ret < 0) { + dev_err(mhdp->dev, + "Failed to read CDNS_DP_FRAMER_GLOBAL_CONFIG %d\n", + ret); + return; + } + framer |= CDNS_DP_FRAMER_EN; + framer &= ~CDNS_DP_NO_VIDEO_MODE; + cdns_mhdp_reg_write(mhdp, CDNS_DP_FRAMER_GLOBAL_CONFIG, framer); +} + +static void cdns_mhdp_sst_enable(struct cdns_mhdp_device *mhdp, + const struct drm_display_mode *mode) +{ + u32 rate, vs, required_bandwidth, available_bandwidth; + s32 line_thresh1, line_thresh2, line_thresh = 0; + int pxlclock = mode->crtc_clock; + u32 tu_size = 64; + u32 bpp; + + /* Get rate in MSymbols per second per lane */ + rate = mhdp->link.rate / 1000; + + bpp = cdns_mhdp_get_bpp(&mhdp->display_fmt); + + required_bandwidth = pxlclock * bpp / 8; + available_bandwidth = mhdp->link.num_lanes * rate; + + vs = tu_size * required_bandwidth / available_bandwidth; + vs /= 1000; + + if (vs == tu_size) + vs = tu_size - 1; + + line_thresh1 = ((vs + 1) << 5) * 8 / bpp; + line_thresh2 = (pxlclock << 5) / 1000 / rate * (vs + 1) - (1 << 5); + line_thresh = line_thresh1 - line_thresh2 / (s32)mhdp->link.num_lanes; + line_thresh = (line_thresh >> 5) + 2; + + mhdp->stream_id = 0; + + cdns_mhdp_reg_write(mhdp, CDNS_DP_FRAMER_TU, + CDNS_DP_FRAMER_TU_VS(vs) | + CDNS_DP_FRAMER_TU_SIZE(tu_size) | + CDNS_DP_FRAMER_TU_CNT_RST_EN); + + cdns_mhdp_reg_write(mhdp, CDNS_DP_LINE_THRESH(0), + line_thresh & GENMASK(5, 0)); + + cdns_mhdp_reg_write(mhdp, CDNS_DP_STREAM_CONFIG_2(0), + CDNS_DP_SC2_TU_VS_DIFF((tu_size - vs > 3) ? + 0 : tu_size - vs)); + + cdns_mhdp_configure_video(mhdp, mode); +} + +static void cdns_mhdp_atomic_enable(struct drm_bridge *bridge, + struct drm_bridge_state *bridge_state) +{ + struct cdns_mhdp_device *mhdp = bridge_to_mhdp(bridge); + struct drm_atomic_state *state = bridge_state->base.state; + struct cdns_mhdp_bridge_state *mhdp_state; + struct drm_crtc_state *crtc_state; + struct drm_connector *connector; + struct drm_connector_state *conn_state; + struct drm_bridge_state *new_state; + const struct drm_display_mode *mode; + u32 resp; + int ret; + + dev_dbg(mhdp->dev, "bridge enable\n"); + + mutex_lock(&mhdp->link_mutex); + + if (mhdp->plugged && !mhdp->link_up) { + ret = cdns_mhdp_link_up(mhdp); + if (ret < 0) + goto out; + } + + if (mhdp->info && mhdp->info->ops && mhdp->info->ops->enable) + mhdp->info->ops->enable(mhdp); + + /* Enable VIF clock for stream 0 */ + ret = cdns_mhdp_reg_read(mhdp, CDNS_DPTX_CAR, &resp); + if (ret < 0) { + dev_err(mhdp->dev, "Failed to read CDNS_DPTX_CAR %d\n", ret); + goto out; + } + + cdns_mhdp_reg_write(mhdp, CDNS_DPTX_CAR, + resp | CDNS_VIF_CLK_EN | CDNS_VIF_CLK_RSTN); + + connector = drm_atomic_get_new_connector_for_encoder(state, + bridge->encoder); + if (WARN_ON(!connector)) + goto out; + + conn_state = drm_atomic_get_new_connector_state(state, connector); + if (WARN_ON(!conn_state)) + goto out; + + crtc_state = drm_atomic_get_new_crtc_state(state, conn_state->crtc); + if (WARN_ON(!crtc_state)) + goto out; + + mode = &crtc_state->adjusted_mode; + + new_state = drm_atomic_get_new_bridge_state(state, bridge); + if (WARN_ON(!new_state)) + goto out; + + if (!cdns_mhdp_bandwidth_ok(mhdp, mode, mhdp->link.num_lanes, + mhdp->link.rate)) { + ret = -EINVAL; + goto out; + } + + cdns_mhdp_sst_enable(mhdp, mode); + + mhdp_state = to_cdns_mhdp_bridge_state(new_state); + + mhdp_state->current_mode = drm_mode_duplicate(bridge->dev, mode); + drm_mode_set_name(mhdp_state->current_mode); + + dev_dbg(mhdp->dev, "%s: Enabling mode %s\n", __func__, mode->name); + + mhdp->bridge_enabled = true; + +out: + mutex_unlock(&mhdp->link_mutex); + if (ret < 0) + schedule_work(&mhdp->modeset_retry_work); +} + +static void cdns_mhdp_atomic_disable(struct drm_bridge *bridge, + struct drm_bridge_state *bridge_state) +{ + struct cdns_mhdp_device *mhdp = bridge_to_mhdp(bridge); + u32 resp; + + dev_dbg(mhdp->dev, "%s\n", __func__); + + mutex_lock(&mhdp->link_mutex); + + mhdp->bridge_enabled = false; + cdns_mhdp_reg_read(mhdp, CDNS_DP_FRAMER_GLOBAL_CONFIG, &resp); + resp &= ~CDNS_DP_FRAMER_EN; + resp |= CDNS_DP_NO_VIDEO_MODE; + cdns_mhdp_reg_write(mhdp, CDNS_DP_FRAMER_GLOBAL_CONFIG, resp); + + cdns_mhdp_link_down(mhdp); + + /* Disable VIF clock for stream 0 */ + cdns_mhdp_reg_read(mhdp, CDNS_DPTX_CAR, &resp); + cdns_mhdp_reg_write(mhdp, CDNS_DPTX_CAR, + resp & ~(CDNS_VIF_CLK_EN | CDNS_VIF_CLK_RSTN)); + + if (mhdp->info && mhdp->info->ops && mhdp->info->ops->disable) + mhdp->info->ops->disable(mhdp); + + mutex_unlock(&mhdp->link_mutex); +} + +static void cdns_mhdp_detach(struct drm_bridge *bridge) +{ + struct cdns_mhdp_device *mhdp = bridge_to_mhdp(bridge); + + dev_dbg(mhdp->dev, "%s\n", __func__); + + spin_lock(&mhdp->start_lock); + + mhdp->bridge_attached = false; + + spin_unlock(&mhdp->start_lock); + + writel(~0, mhdp->regs + CDNS_APB_INT_MASK); +} + +static struct drm_bridge_state * +cdns_mhdp_bridge_atomic_duplicate_state(struct drm_bridge *bridge) +{ + struct cdns_mhdp_bridge_state *state; + + state = kzalloc(sizeof(*state), GFP_KERNEL); + if (!state) + return NULL; + + __drm_atomic_helper_bridge_duplicate_state(bridge, &state->base); + + return &state->base; +} + +static void +cdns_mhdp_bridge_atomic_destroy_state(struct drm_bridge *bridge, + struct drm_bridge_state *state) +{ + struct cdns_mhdp_bridge_state *cdns_mhdp_state; + + cdns_mhdp_state = to_cdns_mhdp_bridge_state(state); + + if (cdns_mhdp_state->current_mode) { + drm_mode_destroy(bridge->dev, cdns_mhdp_state->current_mode); + cdns_mhdp_state->current_mode = NULL; + } + + kfree(cdns_mhdp_state); +} + +static struct drm_bridge_state * +cdns_mhdp_bridge_atomic_reset(struct drm_bridge *bridge) +{ + struct cdns_mhdp_bridge_state *cdns_mhdp_state; + + cdns_mhdp_state = kzalloc(sizeof(*cdns_mhdp_state), GFP_KERNEL); + if (!cdns_mhdp_state) + return NULL; + + __drm_atomic_helper_bridge_reset(bridge, &cdns_mhdp_state->base); + + return &cdns_mhdp_state->base; +} + +static int cdns_mhdp_atomic_check(struct drm_bridge *bridge, + struct drm_bridge_state *bridge_state, + struct drm_crtc_state *crtc_state, + struct drm_connector_state *conn_state) +{ + struct cdns_mhdp_device *mhdp = bridge_to_mhdp(bridge); + const struct drm_display_mode *mode = &crtc_state->adjusted_mode; + + mutex_lock(&mhdp->link_mutex); + + if (!cdns_mhdp_bandwidth_ok(mhdp, mode, mhdp->link.num_lanes, + mhdp->link.rate)) { + dev_err(mhdp->dev, "%s: Not enough BW for %s (%u lanes at %u Mbps)\n", + __func__, mode->name, mhdp->link.num_lanes, + mhdp->link.rate / 100); + mutex_unlock(&mhdp->link_mutex); + return -EINVAL; + } + + mutex_unlock(&mhdp->link_mutex); + return 0; +} + +static enum drm_connector_status cdns_mhdp_bridge_detect(struct drm_bridge *bridge) +{ + struct cdns_mhdp_device *mhdp = bridge_to_mhdp(bridge); + + return cdns_mhdp_detect(mhdp); +} + +static struct edid *cdns_mhdp_bridge_get_edid(struct drm_bridge *bridge, + struct drm_connector *connector) +{ + struct cdns_mhdp_device *mhdp = bridge_to_mhdp(bridge); + + return cdns_mhdp_get_edid(mhdp, connector); +} + +static void cdns_mhdp_bridge_hpd_enable(struct drm_bridge *bridge) +{ + struct cdns_mhdp_device *mhdp = bridge_to_mhdp(bridge); + + /* Enable SW event interrupts */ + if (mhdp->bridge_attached) + writel(~(u32)CDNS_APB_INT_MASK_SW_EVENT_INT, + mhdp->regs + CDNS_APB_INT_MASK); +} + +static void cdns_mhdp_bridge_hpd_disable(struct drm_bridge *bridge) +{ + struct cdns_mhdp_device *mhdp = bridge_to_mhdp(bridge); + + writel(CDNS_APB_INT_MASK_SW_EVENT_INT, mhdp->regs + CDNS_APB_INT_MASK); +} + +static const struct drm_bridge_funcs cdns_mhdp_bridge_funcs = { + .atomic_enable = cdns_mhdp_atomic_enable, + .atomic_disable = cdns_mhdp_atomic_disable, + .atomic_check = cdns_mhdp_atomic_check, + .attach = cdns_mhdp_attach, + .detach = cdns_mhdp_detach, + .atomic_duplicate_state = cdns_mhdp_bridge_atomic_duplicate_state, + .atomic_destroy_state = cdns_mhdp_bridge_atomic_destroy_state, + .atomic_reset = cdns_mhdp_bridge_atomic_reset, + .detect = cdns_mhdp_bridge_detect, + .get_edid = cdns_mhdp_bridge_get_edid, + .hpd_enable = cdns_mhdp_bridge_hpd_enable, + .hpd_disable = cdns_mhdp_bridge_hpd_disable, +}; + +static bool cdns_mhdp_detect_hpd(struct cdns_mhdp_device *mhdp, bool *hpd_pulse) +{ + int hpd_event, hpd_status; + + *hpd_pulse = false; + + hpd_event = cdns_mhdp_read_hpd_event(mhdp); + + /* Getting event bits failed, bail out */ + if (hpd_event < 0) { + dev_warn(mhdp->dev, "%s: read event failed: %d\n", + __func__, hpd_event); + return false; + } + + hpd_status = cdns_mhdp_get_hpd_status(mhdp); + if (hpd_status < 0) { + dev_warn(mhdp->dev, "%s: get hpd status failed: %d\n", + __func__, hpd_status); + return false; + } + + if (hpd_event & DPTX_READ_EVENT_HPD_PULSE) + *hpd_pulse = true; + + return !!hpd_status; +} + +static int cdns_mhdp_update_link_status(struct cdns_mhdp_device *mhdp) +{ + struct cdns_mhdp_bridge_state *cdns_bridge_state; + struct drm_display_mode *current_mode; + bool old_plugged = mhdp->plugged; + struct drm_bridge_state *state; + u8 status[DP_LINK_STATUS_SIZE]; + bool hpd_pulse; + int ret = 0; + + mutex_lock(&mhdp->link_mutex); + + mhdp->plugged = cdns_mhdp_detect_hpd(mhdp, &hpd_pulse); + + if (!mhdp->plugged) { + cdns_mhdp_link_down(mhdp); + mhdp->link.rate = mhdp->host.link_rate; + mhdp->link.num_lanes = mhdp->host.lanes_cnt; + goto out; + } + + /* + * If we get a HPD pulse event and we were and still are connected, + * check the link status. If link status is ok, there's nothing to do + * as we don't handle DP interrupts. If link status is bad, continue + * with full link setup. + */ + if (hpd_pulse && old_plugged == mhdp->plugged) { + ret = drm_dp_dpcd_read_link_status(&mhdp->aux, status); + + /* + * If everything looks fine, just return, as we don't handle + * DP IRQs. + */ + if (ret > 0 && + drm_dp_channel_eq_ok(status, mhdp->link.num_lanes) && + drm_dp_clock_recovery_ok(status, mhdp->link.num_lanes)) + goto out; + + /* If link is bad, mark link as down so that we do a new LT */ + mhdp->link_up = false; + } + + if (!mhdp->link_up) { + ret = cdns_mhdp_link_up(mhdp); + if (ret < 0) + goto out; + } + + if (mhdp->bridge_enabled) { + state = drm_priv_to_bridge_state(mhdp->bridge.base.state); + if (!state) { + ret = -EINVAL; + goto out; + } + + cdns_bridge_state = to_cdns_mhdp_bridge_state(state); + if (!cdns_bridge_state) { + ret = -EINVAL; + goto out; + } + + current_mode = cdns_bridge_state->current_mode; + if (!current_mode) { + ret = -EINVAL; + goto out; + } + + if (!cdns_mhdp_bandwidth_ok(mhdp, current_mode, mhdp->link.num_lanes, + mhdp->link.rate)) { + ret = -EINVAL; + goto out; + } + + dev_dbg(mhdp->dev, "%s: Enabling mode %s\n", __func__, + current_mode->name); + + cdns_mhdp_sst_enable(mhdp, current_mode); + } +out: + mutex_unlock(&mhdp->link_mutex); + return ret; +} + +static void cdns_mhdp_modeset_retry_fn(struct work_struct *work) +{ + struct cdns_mhdp_device *mhdp; + struct drm_connector *conn; + + mhdp = container_of(work, typeof(*mhdp), modeset_retry_work); + + conn = &mhdp->connector; + + /* Grab the locks before changing connector property */ + mutex_lock(&conn->dev->mode_config.mutex); + + /* + * Set connector link status to BAD and send a Uevent to notify + * userspace to do a modeset. + */ + drm_connector_set_link_status_property(conn, DRM_MODE_LINK_STATUS_BAD); + mutex_unlock(&conn->dev->mode_config.mutex); + + /* Send Hotplug uevent so userspace can reprobe */ + drm_kms_helper_hotplug_event(mhdp->bridge.dev); +} + +static irqreturn_t cdns_mhdp_irq_handler(int irq, void *data) +{ + struct cdns_mhdp_device *mhdp = data; + u32 apb_stat, sw_ev0; + bool bridge_attached; + int ret; + + apb_stat = readl(mhdp->regs + CDNS_APB_INT_STATUS); + if (!(apb_stat & CDNS_APB_INT_MASK_SW_EVENT_INT)) + return IRQ_NONE; + + sw_ev0 = readl(mhdp->regs + CDNS_SW_EVENT0); + + /* + * Calling drm_kms_helper_hotplug_event() when not attached + * to drm device causes an oops because the drm_bridge->dev + * is NULL. See cdns_mhdp_fw_cb() comments for details about the + * problems related drm_kms_helper_hotplug_event() call. + */ + spin_lock(&mhdp->start_lock); + bridge_attached = mhdp->bridge_attached; + spin_unlock(&mhdp->start_lock); + + if (bridge_attached && (sw_ev0 & CDNS_DPTX_HPD)) { + ret = cdns_mhdp_update_link_status(mhdp); + if (mhdp->connector.dev) { + if (ret < 0) + schedule_work(&mhdp->modeset_retry_work); + else + drm_kms_helper_hotplug_event(mhdp->bridge.dev); + } else { + drm_bridge_hpd_notify(&mhdp->bridge, cdns_mhdp_detect(mhdp)); + } + } + + return IRQ_HANDLED; +} + +static int cdns_mhdp_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct cdns_mhdp_device *mhdp; + unsigned long rate; + struct clk *clk; + int ret; + int irq; + + mhdp = devm_kzalloc(dev, sizeof(*mhdp), GFP_KERNEL); + if (!mhdp) + return -ENOMEM; + + clk = devm_clk_get(dev, NULL); + if (IS_ERR(clk)) { + dev_err(dev, "couldn't get clk: %ld\n", PTR_ERR(clk)); + return PTR_ERR(clk); + } + + mhdp->clk = clk; + mhdp->dev = dev; + mutex_init(&mhdp->mbox_mutex); + mutex_init(&mhdp->link_mutex); + spin_lock_init(&mhdp->start_lock); + + drm_dp_aux_init(&mhdp->aux); + mhdp->aux.dev = dev; + mhdp->aux.transfer = cdns_mhdp_transfer; + + mhdp->regs = devm_platform_ioremap_resource(pdev, 0); + if (IS_ERR(mhdp->regs)) { + dev_err(dev, "Failed to get memory resource\n"); + return PTR_ERR(mhdp->regs); + } + + mhdp->phy = devm_of_phy_get_by_index(dev, pdev->dev.of_node, 0); + if (IS_ERR(mhdp->phy)) { + dev_err(dev, "no PHY configured\n"); + return PTR_ERR(mhdp->phy); + } + + platform_set_drvdata(pdev, mhdp); + + mhdp->info = of_device_get_match_data(dev); + + clk_prepare_enable(clk); + + pm_runtime_enable(dev); + ret = pm_runtime_get_sync(dev); + if (ret < 0) { + dev_err(dev, "pm_runtime_get_sync failed\n"); + pm_runtime_disable(dev); + goto clk_disable; + } + + if (mhdp->info && mhdp->info->ops && mhdp->info->ops->init) { + ret = mhdp->info->ops->init(mhdp); + if (ret != 0) { + dev_err(dev, "MHDP platform initialization failed: %d\n", + ret); + goto runtime_put; + } + } + + rate = clk_get_rate(clk); + writel(rate % 1000000, mhdp->regs + CDNS_SW_CLK_L); + writel(rate / 1000000, mhdp->regs + CDNS_SW_CLK_H); + + dev_dbg(dev, "func clk rate %lu Hz\n", rate); + + writel(~0, mhdp->regs + CDNS_APB_INT_MASK); + + irq = platform_get_irq(pdev, 0); + ret = devm_request_threaded_irq(mhdp->dev, irq, NULL, + cdns_mhdp_irq_handler, IRQF_ONESHOT, + "mhdp8546", mhdp); + if (ret) { + dev_err(dev, "cannot install IRQ %d\n", irq); + ret = -EIO; + goto plat_fini; + } + + cdns_mhdp_fill_host_caps(mhdp); + + /* Initialize link rate and num of lanes to host values */ + mhdp->link.rate = mhdp->host.link_rate; + mhdp->link.num_lanes = mhdp->host.lanes_cnt; + + /* The only currently supported format */ + mhdp->display_fmt.y_only = false; + mhdp->display_fmt.color_format = DRM_COLOR_FORMAT_RGB444; + mhdp->display_fmt.bpc = 8; + + mhdp->bridge.of_node = pdev->dev.of_node; + mhdp->bridge.funcs = &cdns_mhdp_bridge_funcs; + mhdp->bridge.ops = DRM_BRIDGE_OP_DETECT | DRM_BRIDGE_OP_EDID | + DRM_BRIDGE_OP_HPD; + mhdp->bridge.type = DRM_MODE_CONNECTOR_DisplayPort; + if (mhdp->info) + mhdp->bridge.timings = mhdp->info->timings; + + ret = phy_init(mhdp->phy); + if (ret) { + dev_err(mhdp->dev, "Failed to initialize PHY: %d\n", ret); + goto plat_fini; + } + + /* Initialize the work for modeset in case of link train failure */ + INIT_WORK(&mhdp->modeset_retry_work, cdns_mhdp_modeset_retry_fn); + + init_waitqueue_head(&mhdp->fw_load_wq); + + ret = cdns_mhdp_load_firmware(mhdp); + if (ret) + goto phy_exit; + + drm_bridge_add(&mhdp->bridge); + + return 0; + +phy_exit: + phy_exit(mhdp->phy); +plat_fini: + if (mhdp->info && mhdp->info->ops && mhdp->info->ops->exit) + mhdp->info->ops->exit(mhdp); +runtime_put: + pm_runtime_put_sync(dev); + pm_runtime_disable(dev); +clk_disable: + clk_disable_unprepare(mhdp->clk); + + return ret; +} + +static int cdns_mhdp_remove(struct platform_device *pdev) +{ + struct cdns_mhdp_device *mhdp = dev_get_drvdata(&pdev->dev); + unsigned long timeout = msecs_to_jiffies(100); + bool stop_fw = false; + int ret; + + drm_bridge_remove(&mhdp->bridge); + + ret = wait_event_timeout(mhdp->fw_load_wq, + mhdp->hw_state == MHDP_HW_READY, + timeout); + if (ret == 0) + dev_err(mhdp->dev, "%s: Timeout waiting for fw loading\n", + __func__); + else + stop_fw = true; + + spin_lock(&mhdp->start_lock); + mhdp->hw_state = MHDP_HW_STOPPED; + spin_unlock(&mhdp->start_lock); + + if (stop_fw) + ret = cdns_mhdp_set_firmware_active(mhdp, false); + + phy_exit(mhdp->phy); + + if (mhdp->info && mhdp->info->ops && mhdp->info->ops->exit) + mhdp->info->ops->exit(mhdp); + + pm_runtime_put_sync(&pdev->dev); + pm_runtime_disable(&pdev->dev); + + cancel_work_sync(&mhdp->modeset_retry_work); + flush_scheduled_work(); + + clk_disable_unprepare(mhdp->clk); + + return ret; +} + +static const struct of_device_id mhdp_ids[] = { + { .compatible = "cdns,mhdp8546", }, +#ifdef CONFIG_DRM_CDNS_MHDP8546_J721E + { .compatible = "ti,j721e-mhdp8546", + .data = &(const struct cdns_mhdp_platform_info) { + .timings = &mhdp_ti_j721e_bridge_timings, + .ops = &mhdp_ti_j721e_ops, + }, + }, +#endif + { /* sentinel */ } +}; +MODULE_DEVICE_TABLE(of, mhdp_ids); + +static struct platform_driver mhdp_driver = { + .driver = { + .name = "cdns-mhdp8546", + .of_match_table = of_match_ptr(mhdp_ids), + }, + .probe = cdns_mhdp_probe, + .remove = cdns_mhdp_remove, +}; +module_platform_driver(mhdp_driver); + +MODULE_FIRMWARE(FW_NAME); + +MODULE_AUTHOR("Quentin Schulz <quentin.schulz@free-electrons.com>"); +MODULE_AUTHOR("Swapnil Jakhade <sjakhade@cadence.com>"); +MODULE_AUTHOR("Yuti Amonkar <yamonkar@cadence.com>"); +MODULE_AUTHOR("Tomi Valkeinen <tomi.valkeinen@ti.com>"); +MODULE_AUTHOR("Jyri Sarha <jsarha@ti.com>"); +MODULE_DESCRIPTION("Cadence MHDP8546 DP bridge driver"); +MODULE_LICENSE("GPL"); +MODULE_ALIAS("platform:cdns-mhdp8546"); diff --git a/drivers/gpu/drm/bridge/cadence/cdns-mhdp8546-core.h b/drivers/gpu/drm/bridge/cadence/cdns-mhdp8546-core.h new file mode 100644 index 000000000000..5897a85e3159 --- /dev/null +++ b/drivers/gpu/drm/bridge/cadence/cdns-mhdp8546-core.h @@ -0,0 +1,400 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Cadence MHDP8546 DP bridge driver. + * + * Copyright (C) 2020 Cadence Design Systems, Inc. + * + * Author: Quentin Schulz <quentin.schulz@free-electrons.com> + * Swapnil Jakhade <sjakhade@cadence.com> + */ + +#ifndef CDNS_MHDP8546_CORE_H +#define CDNS_MHDP8546_CORE_H + +#include <linux/bits.h> +#include <linux/mutex.h> +#include <linux/spinlock.h> + +#include <drm/drm_bridge.h> +#include <drm/drm_connector.h> +#include <drm/drm_dp_helper.h> + +struct clk; +struct device; +struct phy; + +/* Register offsets */ +#define CDNS_APB_CTRL 0x00000 +#define CDNS_CPU_STALL BIT(3) + +#define CDNS_MAILBOX_FULL 0x00008 +#define CDNS_MAILBOX_EMPTY 0x0000c +#define CDNS_MAILBOX_TX_DATA 0x00010 +#define CDNS_MAILBOX_RX_DATA 0x00014 +#define CDNS_KEEP_ALIVE 0x00018 +#define CDNS_KEEP_ALIVE_MASK GENMASK(7, 0) + +#define CDNS_VER_L 0x0001C +#define CDNS_VER_H 0x00020 +#define CDNS_LIB_L_ADDR 0x00024 +#define CDNS_LIB_H_ADDR 0x00028 + +#define CDNS_MB_INT_MASK 0x00034 +#define CDNS_MB_INT_STATUS 0x00038 + +#define CDNS_SW_CLK_L 0x0003c +#define CDNS_SW_CLK_H 0x00040 + +#define CDNS_SW_EVENT0 0x00044 +#define CDNS_DPTX_HPD BIT(0) + +#define CDNS_SW_EVENT1 0x00048 +#define CDNS_SW_EVENT2 0x0004c +#define CDNS_SW_EVENT3 0x00050 + +#define CDNS_APB_INT_MASK 0x0006C +#define CDNS_APB_INT_MASK_MAILBOX_INT BIT(0) +#define CDNS_APB_INT_MASK_SW_EVENT_INT BIT(1) + +#define CDNS_APB_INT_STATUS 0x00070 + +#define CDNS_DPTX_CAR 0x00904 +#define CDNS_VIF_CLK_EN BIT(0) +#define CDNS_VIF_CLK_RSTN BIT(1) + +#define CDNS_SOURCE_VIDEO_IF(s) (0x00b00 + ((s) * 0x20)) +#define CDNS_BND_HSYNC2VSYNC(s) (CDNS_SOURCE_VIDEO_IF(s) + \ + 0x00) +#define CDNS_IP_DTCT_WIN GENMASK(11, 0) +#define CDNS_IP_DET_INTERLACE_FORMAT BIT(12) +#define CDNS_IP_BYPASS_V_INTERFACE BIT(13) + +#define CDNS_HSYNC2VSYNC_POL_CTRL(s) (CDNS_SOURCE_VIDEO_IF(s) + \ + 0x10) +#define CDNS_H2V_HSYNC_POL_ACTIVE_LOW BIT(1) +#define CDNS_H2V_VSYNC_POL_ACTIVE_LOW BIT(2) + +#define CDNS_DPTX_PHY_CONFIG 0x02000 +#define CDNS_PHY_TRAINING_EN BIT(0) +#define CDNS_PHY_TRAINING_TYPE(x) (((x) & GENMASK(3, 0)) << 1) +#define CDNS_PHY_SCRAMBLER_BYPASS BIT(5) +#define CDNS_PHY_ENCODER_BYPASS BIT(6) +#define CDNS_PHY_SKEW_BYPASS BIT(7) +#define CDNS_PHY_TRAINING_AUTO BIT(8) +#define CDNS_PHY_LANE0_SKEW(x) (((x) & GENMASK(2, 0)) << 9) +#define CDNS_PHY_LANE1_SKEW(x) (((x) & GENMASK(2, 0)) << 12) +#define CDNS_PHY_LANE2_SKEW(x) (((x) & GENMASK(2, 0)) << 15) +#define CDNS_PHY_LANE3_SKEW(x) (((x) & GENMASK(2, 0)) << 18) +#define CDNS_PHY_COMMON_CONFIG (CDNS_PHY_LANE1_SKEW(1) | \ + CDNS_PHY_LANE2_SKEW(2) | \ + CDNS_PHY_LANE3_SKEW(3)) +#define CDNS_PHY_10BIT_EN BIT(21) + +#define CDNS_DP_FRAMER_GLOBAL_CONFIG 0x02200 +#define CDNS_DP_NUM_LANES(x) ((x) - 1) +#define CDNS_DP_MST_EN BIT(2) +#define CDNS_DP_FRAMER_EN BIT(3) +#define CDNS_DP_RATE_GOVERNOR_EN BIT(4) +#define CDNS_DP_NO_VIDEO_MODE BIT(5) +#define CDNS_DP_DISABLE_PHY_RST BIT(6) +#define CDNS_DP_WR_FAILING_EDGE_VSYNC BIT(7) + +#define CDNS_DP_FRAMER_TU 0x02208 +#define CDNS_DP_FRAMER_TU_SIZE(x) (((x) & GENMASK(6, 0)) << 8) +#define CDNS_DP_FRAMER_TU_VS(x) ((x) & GENMASK(5, 0)) +#define CDNS_DP_FRAMER_TU_CNT_RST_EN BIT(15) + +#define CDNS_DP_MTPH_CONTROL 0x02264 +#define CDNS_DP_MTPH_ECF_EN BIT(0) +#define CDNS_DP_MTPH_ACT_EN BIT(1) +#define CDNS_DP_MTPH_LVP_EN BIT(2) + +#define CDNS_DP_MTPH_STATUS 0x0226C +#define CDNS_DP_MTPH_ACT_STATUS BIT(0) + +#define CDNS_DP_LANE_EN 0x02300 +#define CDNS_DP_LANE_EN_LANES(x) GENMASK((x) - 1, 0) + +#define CDNS_DP_ENHNCD 0x02304 + +#define CDNS_DPTX_STREAM(s) (0x03000 + (s) * 0x80) +#define CDNS_DP_MSA_HORIZONTAL_0(s) (CDNS_DPTX_STREAM(s) + 0x00) +#define CDNS_DP_MSAH0_H_TOTAL(x) (x) +#define CDNS_DP_MSAH0_HSYNC_START(x) ((x) << 16) + +#define CDNS_DP_MSA_HORIZONTAL_1(s) (CDNS_DPTX_STREAM(s) + 0x04) +#define CDNS_DP_MSAH1_HSYNC_WIDTH(x) (x) +#define CDNS_DP_MSAH1_HSYNC_POL_LOW BIT(15) +#define CDNS_DP_MSAH1_HDISP_WIDTH(x) ((x) << 16) + +#define CDNS_DP_MSA_VERTICAL_0(s) (CDNS_DPTX_STREAM(s) + 0x08) +#define CDNS_DP_MSAV0_V_TOTAL(x) (x) +#define CDNS_DP_MSAV0_VSYNC_START(x) ((x) << 16) + +#define CDNS_DP_MSA_VERTICAL_1(s) (CDNS_DPTX_STREAM(s) + 0x0c) +#define CDNS_DP_MSAV1_VSYNC_WIDTH(x) (x) +#define CDNS_DP_MSAV1_VSYNC_POL_LOW BIT(15) +#define CDNS_DP_MSAV1_VDISP_WIDTH(x) ((x) << 16) + +#define CDNS_DP_MSA_MISC(s) (CDNS_DPTX_STREAM(s) + 0x10) +#define CDNS_DP_STREAM_CONFIG(s) (CDNS_DPTX_STREAM(s) + 0x14) +#define CDNS_DP_STREAM_CONFIG_2(s) (CDNS_DPTX_STREAM(s) + 0x2c) +#define CDNS_DP_SC2_TU_VS_DIFF(x) ((x) << 8) + +#define CDNS_DP_HORIZONTAL(s) (CDNS_DPTX_STREAM(s) + 0x30) +#define CDNS_DP_H_HSYNC_WIDTH(x) (x) +#define CDNS_DP_H_H_TOTAL(x) ((x) << 16) + +#define CDNS_DP_VERTICAL_0(s) (CDNS_DPTX_STREAM(s) + 0x34) +#define CDNS_DP_V0_VHEIGHT(x) (x) +#define CDNS_DP_V0_VSTART(x) ((x) << 16) + +#define CDNS_DP_VERTICAL_1(s) (CDNS_DPTX_STREAM(s) + 0x38) +#define CDNS_DP_V1_VTOTAL(x) (x) +#define CDNS_DP_V1_VTOTAL_EVEN BIT(16) + +#define CDNS_DP_MST_SLOT_ALLOCATE(s) (CDNS_DPTX_STREAM(s) + 0x44) +#define CDNS_DP_S_ALLOC_START_SLOT(x) (x) +#define CDNS_DP_S_ALLOC_END_SLOT(x) ((x) << 8) + +#define CDNS_DP_RATE_GOVERNING(s) (CDNS_DPTX_STREAM(s) + 0x48) +#define CDNS_DP_RG_TARG_AV_SLOTS_Y(x) (x) +#define CDNS_DP_RG_TARG_AV_SLOTS_X(x) ((x) << 4) +#define CDNS_DP_RG_ENABLE BIT(10) + +#define CDNS_DP_FRAMER_PXL_REPR(s) (CDNS_DPTX_STREAM(s) + 0x4c) +#define CDNS_DP_FRAMER_6_BPC BIT(0) +#define CDNS_DP_FRAMER_8_BPC BIT(1) +#define CDNS_DP_FRAMER_10_BPC BIT(2) +#define CDNS_DP_FRAMER_12_BPC BIT(3) +#define CDNS_DP_FRAMER_16_BPC BIT(4) +#define CDNS_DP_FRAMER_PXL_FORMAT 0x8 +#define CDNS_DP_FRAMER_RGB BIT(0) +#define CDNS_DP_FRAMER_YCBCR444 BIT(1) +#define CDNS_DP_FRAMER_YCBCR422 BIT(2) +#define CDNS_DP_FRAMER_YCBCR420 BIT(3) +#define CDNS_DP_FRAMER_Y_ONLY BIT(4) + +#define CDNS_DP_FRAMER_SP(s) (CDNS_DPTX_STREAM(s) + 0x50) +#define CDNS_DP_FRAMER_VSYNC_POL_LOW BIT(0) +#define CDNS_DP_FRAMER_HSYNC_POL_LOW BIT(1) +#define CDNS_DP_FRAMER_INTERLACE BIT(2) + +#define CDNS_DP_LINE_THRESH(s) (CDNS_DPTX_STREAM(s) + 0x64) +#define CDNS_DP_ACTIVE_LINE_THRESH(x) (x) + +#define CDNS_DP_VB_ID(s) (CDNS_DPTX_STREAM(s) + 0x68) +#define CDNS_DP_VB_ID_INTERLACED BIT(2) +#define CDNS_DP_VB_ID_COMPRESSED BIT(6) + +#define CDNS_DP_FRONT_BACK_PORCH(s) (CDNS_DPTX_STREAM(s) + 0x78) +#define CDNS_DP_BACK_PORCH(x) (x) +#define CDNS_DP_FRONT_PORCH(x) ((x) << 16) + +#define CDNS_DP_BYTE_COUNT(s) (CDNS_DPTX_STREAM(s) + 0x7c) +#define CDNS_DP_BYTE_COUNT_BYTES_IN_CHUNK_SHIFT 16 + +/* mailbox */ +#define MAILBOX_RETRY_US 1000 +#define MAILBOX_TIMEOUT_US 2000000 + +#define MB_OPCODE_ID 0 +#define MB_MODULE_ID 1 +#define MB_SIZE_MSB_ID 2 +#define MB_SIZE_LSB_ID 3 +#define MB_DATA_ID 4 + +#define MB_MODULE_ID_DP_TX 0x01 +#define MB_MODULE_ID_HDCP_TX 0x07 +#define MB_MODULE_ID_HDCP_RX 0x08 +#define MB_MODULE_ID_HDCP_GENERAL 0x09 +#define MB_MODULE_ID_GENERAL 0x0a + +/* firmware and opcodes */ +#define FW_NAME "cadence/mhdp8546.bin" +#define CDNS_MHDP_IMEM 0x10000 + +#define GENERAL_MAIN_CONTROL 0x01 +#define GENERAL_TEST_ECHO 0x02 +#define GENERAL_BUS_SETTINGS 0x03 +#define GENERAL_TEST_ACCESS 0x04 +#define GENERAL_REGISTER_READ 0x07 + +#define DPTX_SET_POWER_MNG 0x00 +#define DPTX_GET_EDID 0x02 +#define DPTX_READ_DPCD 0x03 +#define DPTX_WRITE_DPCD 0x04 +#define DPTX_ENABLE_EVENT 0x05 +#define DPTX_WRITE_REGISTER 0x06 +#define DPTX_READ_REGISTER 0x07 +#define DPTX_WRITE_FIELD 0x08 +#define DPTX_READ_EVENT 0x0a +#define DPTX_GET_LAST_AUX_STAUS 0x0e +#define DPTX_HPD_STATE 0x11 +#define DPTX_ADJUST_LT 0x12 + +#define FW_STANDBY 0 +#define FW_ACTIVE 1 + +/* HPD */ +#define DPTX_READ_EVENT_HPD_TO_HIGH BIT(0) +#define DPTX_READ_EVENT_HPD_TO_LOW BIT(1) +#define DPTX_READ_EVENT_HPD_PULSE BIT(2) +#define DPTX_READ_EVENT_HPD_STATE BIT(3) + +/* general */ +#define CDNS_DP_TRAINING_PATTERN_4 0x7 + +#define CDNS_KEEP_ALIVE_TIMEOUT 2000 + +#define CDNS_VOLT_SWING(x) ((x) & GENMASK(1, 0)) +#define CDNS_FORCE_VOLT_SWING BIT(2) + +#define CDNS_PRE_EMPHASIS(x) ((x) & GENMASK(1, 0)) +#define CDNS_FORCE_PRE_EMPHASIS BIT(2) + +#define CDNS_SUPPORT_TPS(x) BIT((x) - 1) + +#define CDNS_FAST_LINK_TRAINING BIT(0) + +#define CDNS_LANE_MAPPING_TYPE_C_LANE_0(x) ((x) & GENMASK(1, 0)) +#define CDNS_LANE_MAPPING_TYPE_C_LANE_1(x) ((x) & GENMASK(3, 2)) +#define CDNS_LANE_MAPPING_TYPE_C_LANE_2(x) ((x) & GENMASK(5, 4)) +#define CDNS_LANE_MAPPING_TYPE_C_LANE_3(x) ((x) & GENMASK(7, 6)) +#define CDNS_LANE_MAPPING_NORMAL 0xe4 +#define CDNS_LANE_MAPPING_FLIPPED 0x1b + +#define CDNS_DP_MAX_NUM_LANES 4 +#define CDNS_DP_TEST_VSC_SDP BIT(6) /* 1.3+ */ +#define CDNS_DP_TEST_COLOR_FORMAT_RAW_Y_ONLY BIT(7) + +#define CDNS_MHDP_MAX_STREAMS 4 + +#define DP_LINK_CAP_ENHANCED_FRAMING BIT(0) + +struct cdns_mhdp_link { + unsigned char revision; + unsigned int rate; + unsigned int num_lanes; + unsigned long capabilities; +}; + +struct cdns_mhdp_host { + unsigned int link_rate; + u8 lanes_cnt; + u8 volt_swing; + u8 pre_emphasis; + u8 pattern_supp; + u8 lane_mapping; + bool fast_link; + bool enhanced; + bool scrambler; + bool ssc; +}; + +struct cdns_mhdp_sink { + unsigned int link_rate; + u8 lanes_cnt; + u8 pattern_supp; + bool fast_link; + bool enhanced; + bool ssc; +}; + +struct cdns_mhdp_display_fmt { + u32 color_format; + u32 bpc; + bool y_only; +}; + +/* + * These enums present MHDP hw initialization state + * Legal state transitions are: + * MHDP_HW_READY <-> MHDP_HW_STOPPED + */ +enum mhdp_hw_state { + MHDP_HW_READY = 1, /* HW ready, FW active */ + MHDP_HW_STOPPED /* Driver removal FW to be stopped */ +}; + +struct cdns_mhdp_device; + +struct mhdp_platform_ops { + int (*init)(struct cdns_mhdp_device *mhdp); + void (*exit)(struct cdns_mhdp_device *mhdp); + void (*enable)(struct cdns_mhdp_device *mhdp); + void (*disable)(struct cdns_mhdp_device *mhdp); +}; + +struct cdns_mhdp_bridge_state { + struct drm_bridge_state base; + struct drm_display_mode *current_mode; +}; + +struct cdns_mhdp_platform_info { + const struct drm_bridge_timings *timings; + const struct mhdp_platform_ops *ops; +}; + +#define to_cdns_mhdp_bridge_state(s) \ + container_of(s, struct cdns_mhdp_bridge_state, base) + +struct cdns_mhdp_device { + void __iomem *regs; + void __iomem *j721e_regs; + + struct device *dev; + struct clk *clk; + struct phy *phy; + + const struct cdns_mhdp_platform_info *info; + + /* This is to protect mailbox communications with the firmware */ + struct mutex mbox_mutex; + + /* + * "link_mutex" protects the access to all the link parameters + * including the link training process. Link training will be + * invoked both from threaded interrupt handler and from atomic + * callbacks when link_up is not set. So this mutex protects + * flags such as link_up, bridge_enabled, link.num_lanes, + * link.rate etc. + */ + struct mutex link_mutex; + + struct drm_connector connector; + struct drm_bridge bridge; + + struct cdns_mhdp_link link; + struct drm_dp_aux aux; + + struct cdns_mhdp_host host; + struct cdns_mhdp_sink sink; + struct cdns_mhdp_display_fmt display_fmt; + u8 stream_id; + + bool link_up; + bool plugged; + + /* + * "start_lock" protects the access to bridge_attached and + * hw_state data members that control the delayed firmware + * loading and attaching the bridge. They are accessed from + * both the DRM core and cdns_mhdp_fw_cb(). In most cases just + * protecting the data members is enough, but the irq mask + * setting needs to be protected when enabling the FW. + */ + spinlock_t start_lock; + bool bridge_attached; + bool bridge_enabled; + enum mhdp_hw_state hw_state; + wait_queue_head_t fw_load_wq; + + /* Work struct to schedule a uevent on link train failure */ + struct work_struct modeset_retry_work; +}; + +#define connector_to_mhdp(x) container_of(x, struct cdns_mhdp_device, connector) +#define bridge_to_mhdp(x) container_of(x, struct cdns_mhdp_device, bridge) + +#endif diff --git a/drivers/gpu/drm/bridge/cadence/cdns-mhdp8546-j721e.c b/drivers/gpu/drm/bridge/cadence/cdns-mhdp8546-j721e.c new file mode 100644 index 000000000000..dfe1b59514f7 --- /dev/null +++ b/drivers/gpu/drm/bridge/cadence/cdns-mhdp8546-j721e.c @@ -0,0 +1,78 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * TI j721e Cadence MHDP8546 DP wrapper + * + * Copyright (C) 2020 Texas Instruments Incorporated - http://www.ti.com/ + * Author: Jyri Sarha <jsarha@ti.com> + */ + +#include <linux/io.h> +#include <linux/platform_device.h> + +#include "cdns-mhdp8546-j721e.h" + +#define REVISION 0x00 +#define DPTX_IPCFG 0x04 +#define ECC_MEM_CFG 0x08 +#define DPTX_DSC_CFG 0x0c +#define DPTX_SRC_CFG 0x10 +#define DPTX_VIF_SECURE_MODE_CFG 0x14 +#define DPTX_VIF_CONN_STATUS 0x18 +#define PHY_CLK_STATUS 0x1c + +#define DPTX_SRC_AIF_EN BIT(16) +#define DPTX_SRC_VIF_3_IN30B BIT(11) +#define DPTX_SRC_VIF_2_IN30B BIT(10) +#define DPTX_SRC_VIF_1_IN30B BIT(9) +#define DPTX_SRC_VIF_0_IN30B BIT(8) +#define DPTX_SRC_VIF_3_SEL_DPI5 BIT(7) +#define DPTX_SRC_VIF_3_SEL_DPI3 0 +#define DPTX_SRC_VIF_2_SEL_DPI4 BIT(6) +#define DPTX_SRC_VIF_2_SEL_DPI2 0 +#define DPTX_SRC_VIF_1_SEL_DPI3 BIT(5) +#define DPTX_SRC_VIF_1_SEL_DPI1 0 +#define DPTX_SRC_VIF_0_SEL_DPI2 BIT(4) +#define DPTX_SRC_VIF_0_SEL_DPI0 0 +#define DPTX_SRC_VIF_3_EN BIT(3) +#define DPTX_SRC_VIF_2_EN BIT(2) +#define DPTX_SRC_VIF_1_EN BIT(1) +#define DPTX_SRC_VIF_0_EN BIT(0) + +/* TODO turn DPTX_IPCFG fw_mem_clk_en at pm_runtime_suspend. */ + +static int cdns_mhdp_j721e_init(struct cdns_mhdp_device *mhdp) +{ + struct platform_device *pdev = to_platform_device(mhdp->dev); + + mhdp->j721e_regs = devm_platform_ioremap_resource(pdev, 1); + return PTR_ERR_OR_ZERO(mhdp->j721e_regs); +} + +static void cdns_mhdp_j721e_enable(struct cdns_mhdp_device *mhdp) +{ + /* + * Enable VIF_0 and select DPI2 as its input. DSS0 DPI0 is connected + * to eDP DPI2. This is the only supported SST configuration on + * J721E. + */ + writel(DPTX_SRC_VIF_0_EN | DPTX_SRC_VIF_0_SEL_DPI2, + mhdp->j721e_regs + DPTX_SRC_CFG); +} + +static void cdns_mhdp_j721e_disable(struct cdns_mhdp_device *mhdp) +{ + /* Put everything to defaults */ + writel(0, mhdp->j721e_regs + DPTX_DSC_CFG); +} + +const struct mhdp_platform_ops mhdp_ti_j721e_ops = { + .init = cdns_mhdp_j721e_init, + .enable = cdns_mhdp_j721e_enable, + .disable = cdns_mhdp_j721e_disable, +}; + +const struct drm_bridge_timings mhdp_ti_j721e_bridge_timings = { + .input_bus_flags = DRM_BUS_FLAG_PIXDATA_SAMPLE_NEGEDGE | + DRM_BUS_FLAG_SYNC_SAMPLE_NEGEDGE | + DRM_BUS_FLAG_DE_HIGH, +}; diff --git a/drivers/gpu/drm/bridge/cadence/cdns-mhdp8546-j721e.h b/drivers/gpu/drm/bridge/cadence/cdns-mhdp8546-j721e.h new file mode 100644 index 000000000000..97d20d115a24 --- /dev/null +++ b/drivers/gpu/drm/bridge/cadence/cdns-mhdp8546-j721e.h @@ -0,0 +1,19 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * TI j721e Cadence MHDP8546 DP wrapper + * + * Copyright (C) 2020 Texas Instruments Incorporated - http://www.ti.com/ + * Author: Jyri Sarha <jsarha@ti.com> + */ + +#ifndef CDNS_MHDP8546_J721E_H +#define CDNS_MHDP8546_J721E_H + +#include "cdns-mhdp8546-core.h" + +struct mhdp_platform_ops; + +extern const struct mhdp_platform_ops mhdp_ti_j721e_ops; +extern const struct drm_bridge_timings mhdp_ti_j721e_bridge_timings; + +#endif /* !CDNS_MHDP8546_J721E_H */ diff --git a/drivers/gpu/drm/drm_cache.c b/drivers/gpu/drm/drm_cache.c index 03e01b000f7a..0fe3c496002a 100644 --- a/drivers/gpu/drm/drm_cache.c +++ b/drivers/gpu/drm/drm_cache.c @@ -127,7 +127,7 @@ drm_clflush_sg(struct sg_table *st) struct sg_page_iter sg_iter; mb(); /*CLFLUSH is ordered only by using memory barriers*/ - for_each_sg_page(st->sgl, &sg_iter, st->nents, 0) + for_each_sgtable_page(st, &sg_iter, 0) drm_clflush_page(sg_page_iter_page(&sg_iter)); mb(); /*Make sure that all cache line entry is flushed*/ diff --git a/drivers/gpu/drm/drm_dp_helper.c b/drivers/gpu/drm/drm_dp_helper.c index 1e7c638873c8..deeed73f4ed6 100644 --- a/drivers/gpu/drm/drm_dp_helper.c +++ b/drivers/gpu/drm/drm_dp_helper.c @@ -363,6 +363,70 @@ int drm_dp_dpcd_read_link_status(struct drm_dp_aux *aux, } EXPORT_SYMBOL(drm_dp_dpcd_read_link_status); +static bool is_edid_digital_input_dp(const struct edid *edid) +{ + return edid && edid->revision >= 4 && + edid->input & DRM_EDID_INPUT_DIGITAL && + (edid->input & DRM_EDID_DIGITAL_TYPE_MASK) == DRM_EDID_DIGITAL_TYPE_DP; +} + +/** + * drm_dp_downstream_is_type() - is the downstream facing port of certain type? + * @dpcd: DisplayPort configuration data + * @port_cap: port capabilities + * @type: port type to be checked. Can be: + * %DP_DS_PORT_TYPE_DP, %DP_DS_PORT_TYPE_VGA, %DP_DS_PORT_TYPE_DVI, + * %DP_DS_PORT_TYPE_HDMI, %DP_DS_PORT_TYPE_NON_EDID, + * %DP_DS_PORT_TYPE_DP_DUALMODE or %DP_DS_PORT_TYPE_WIRELESS. + * + * Caveat: Only works with DPCD 1.1+ port caps. + * + * Returns: whether the downstream facing port matches the type. + */ +bool drm_dp_downstream_is_type(const u8 dpcd[DP_RECEIVER_CAP_SIZE], + const u8 port_cap[4], u8 type) +{ + return drm_dp_is_branch(dpcd) && + dpcd[DP_DPCD_REV] >= 0x11 && + (port_cap[0] & DP_DS_PORT_TYPE_MASK) == type; +} +EXPORT_SYMBOL(drm_dp_downstream_is_type); + +/** + * drm_dp_downstream_is_tmds() - is the downstream facing port TMDS? + * @dpcd: DisplayPort configuration data + * @port_cap: port capabilities + * @edid: EDID + * + * Returns: whether the downstream facing port is TMDS (HDMI/DVI). + */ +bool drm_dp_downstream_is_tmds(const u8 dpcd[DP_RECEIVER_CAP_SIZE], + const u8 port_cap[4], + const struct edid *edid) +{ + if (dpcd[DP_DPCD_REV] < 0x11) { + switch (dpcd[DP_DOWNSTREAMPORT_PRESENT] & DP_DWN_STRM_PORT_TYPE_MASK) { + case DP_DWN_STRM_PORT_TYPE_TMDS: + return true; + default: + return false; + } + } + + switch (port_cap[0] & DP_DS_PORT_TYPE_MASK) { + case DP_DS_PORT_TYPE_DP_DUALMODE: + if (is_edid_digital_input_dp(edid)) + return false; + fallthrough; + case DP_DS_PORT_TYPE_DVI: + case DP_DS_PORT_TYPE_HDMI: + return true; + default: + return false; + } +} +EXPORT_SYMBOL(drm_dp_downstream_is_tmds); + /** * drm_dp_send_real_edid_checksum() - send back real edid checksum value * @aux: DisplayPort AUX channel @@ -545,79 +609,191 @@ int drm_dp_read_downstream_info(struct drm_dp_aux *aux, ret = drm_dp_dpcd_read(aux, DP_DOWNSTREAM_PORT_0, downstream_ports, len); if (ret < 0) return ret; + if (ret != len) + return -EIO; - return ret == len ? 0 : -EIO; + DRM_DEBUG_KMS("%s: DPCD DFP: %*ph\n", + aux->name, len, downstream_ports); + + return 0; } EXPORT_SYMBOL(drm_dp_read_downstream_info); /** - * drm_dp_downstream_max_clock() - extract branch device max - * pixel rate for legacy VGA - * converter or max TMDS clock - * rate for others + * drm_dp_downstream_max_dotclock() - extract downstream facing port max dot clock * @dpcd: DisplayPort configuration data * @port_cap: port capabilities * - * See also: - * drm_dp_read_downstream_info() - * drm_dp_downstream_max_bpc() - * - * Returns: Max clock in kHz on success or 0 if max clock not defined + * Returns: Downstream facing port max dot clock in kHz on success, + * or 0 if max clock not defined */ -int drm_dp_downstream_max_clock(const u8 dpcd[DP_RECEIVER_CAP_SIZE], - const u8 port_cap[4]) +int drm_dp_downstream_max_dotclock(const u8 dpcd[DP_RECEIVER_CAP_SIZE], + const u8 port_cap[4]) { - int type = port_cap[0] & DP_DS_PORT_TYPE_MASK; - bool detailed_cap_info = dpcd[DP_DOWNSTREAMPORT_PRESENT] & - DP_DETAILED_CAP_INFO_AVAILABLE; + if (!drm_dp_is_branch(dpcd)) + return 0; - if (!detailed_cap_info) + if (dpcd[DP_DPCD_REV] < 0x11) return 0; - switch (type) { + switch (port_cap[0] & DP_DS_PORT_TYPE_MASK) { case DP_DS_PORT_TYPE_VGA: - return port_cap[1] * 8 * 1000; - case DP_DS_PORT_TYPE_DVI: - case DP_DS_PORT_TYPE_HDMI: + if ((dpcd[DP_DOWNSTREAMPORT_PRESENT] & DP_DETAILED_CAP_INFO_AVAILABLE) == 0) + return 0; + return port_cap[1] * 8000; + default: + return 0; + } +} +EXPORT_SYMBOL(drm_dp_downstream_max_dotclock); + +/** + * drm_dp_downstream_max_tmds_clock() - extract downstream facing port max TMDS clock + * @dpcd: DisplayPort configuration data + * @port_cap: port capabilities + * @edid: EDID + * + * Returns: HDMI/DVI downstream facing port max TMDS clock in kHz on success, + * or 0 if max TMDS clock not defined + */ +int drm_dp_downstream_max_tmds_clock(const u8 dpcd[DP_RECEIVER_CAP_SIZE], + const u8 port_cap[4], + const struct edid *edid) +{ + if (!drm_dp_is_branch(dpcd)) + return 0; + + if (dpcd[DP_DPCD_REV] < 0x11) { + switch (dpcd[DP_DOWNSTREAMPORT_PRESENT] & DP_DWN_STRM_PORT_TYPE_MASK) { + case DP_DWN_STRM_PORT_TYPE_TMDS: + return 165000; + default: + return 0; + } + } + + switch (port_cap[0] & DP_DS_PORT_TYPE_MASK) { case DP_DS_PORT_TYPE_DP_DUALMODE: + if (is_edid_digital_input_dp(edid)) + return 0; + /* + * It's left up to the driver to check the + * DP dual mode adapter's max TMDS clock. + * + * Unfortunatley it looks like branch devices + * may not fordward that the DP dual mode i2c + * access so we just usually get i2c nak :( + */ + fallthrough; + case DP_DS_PORT_TYPE_HDMI: + /* + * We should perhaps assume 165 MHz when detailed cap + * info is not available. But looks like many typical + * branch devices fall into that category and so we'd + * probably end up with users complaining that they can't + * get high resolution modes with their favorite dongle. + * + * So let's limit to 300 MHz instead since DPCD 1.4 + * HDMI 2.0 DFPs are required to have the detailed cap + * info. So it's more likely we're dealing with a HDMI 1.4 + * compatible* device here. + */ + if ((dpcd[DP_DOWNSTREAMPORT_PRESENT] & DP_DETAILED_CAP_INFO_AVAILABLE) == 0) + return 300000; + return port_cap[1] * 2500; + case DP_DS_PORT_TYPE_DVI: + if ((dpcd[DP_DOWNSTREAMPORT_PRESENT] & DP_DETAILED_CAP_INFO_AVAILABLE) == 0) + return 165000; + /* FIXME what to do about DVI dual link? */ return port_cap[1] * 2500; default: return 0; } } -EXPORT_SYMBOL(drm_dp_downstream_max_clock); +EXPORT_SYMBOL(drm_dp_downstream_max_tmds_clock); /** - * drm_dp_downstream_max_bpc() - extract branch device max - * bits per component + * drm_dp_downstream_min_tmds_clock() - extract downstream facing port min TMDS clock * @dpcd: DisplayPort configuration data * @port_cap: port capabilities + * @edid: EDID * - * See also: - * drm_dp_read_downstream_info() - * drm_dp_downstream_max_clock() + * Returns: HDMI/DVI downstream facing port min TMDS clock in kHz on success, + * or 0 if max TMDS clock not defined + */ +int drm_dp_downstream_min_tmds_clock(const u8 dpcd[DP_RECEIVER_CAP_SIZE], + const u8 port_cap[4], + const struct edid *edid) +{ + if (!drm_dp_is_branch(dpcd)) + return 0; + + if (dpcd[DP_DPCD_REV] < 0x11) { + switch (dpcd[DP_DOWNSTREAMPORT_PRESENT] & DP_DWN_STRM_PORT_TYPE_MASK) { + case DP_DWN_STRM_PORT_TYPE_TMDS: + return 25000; + default: + return 0; + } + } + + switch (port_cap[0] & DP_DS_PORT_TYPE_MASK) { + case DP_DS_PORT_TYPE_DP_DUALMODE: + if (is_edid_digital_input_dp(edid)) + return 0; + fallthrough; + case DP_DS_PORT_TYPE_DVI: + case DP_DS_PORT_TYPE_HDMI: + /* + * Unclear whether the protocol converter could + * utilize pixel replication. Assume it won't. + */ + return 25000; + default: + return 0; + } +} +EXPORT_SYMBOL(drm_dp_downstream_min_tmds_clock); + +/** + * drm_dp_downstream_max_bpc() - extract downstream facing port max + * bits per component + * @dpcd: DisplayPort configuration data + * @port_cap: downstream facing port capabilities + * @edid: EDID * * Returns: Max bpc on success or 0 if max bpc not defined */ int drm_dp_downstream_max_bpc(const u8 dpcd[DP_RECEIVER_CAP_SIZE], - const u8 port_cap[4]) + const u8 port_cap[4], + const struct edid *edid) { - int type = port_cap[0] & DP_DS_PORT_TYPE_MASK; - bool detailed_cap_info = dpcd[DP_DOWNSTREAMPORT_PRESENT] & - DP_DETAILED_CAP_INFO_AVAILABLE; - int bpc; - - if (!detailed_cap_info) + if (!drm_dp_is_branch(dpcd)) return 0; - switch (type) { - case DP_DS_PORT_TYPE_VGA: - case DP_DS_PORT_TYPE_DVI: - case DP_DS_PORT_TYPE_HDMI: + if (dpcd[DP_DPCD_REV] < 0x11) { + switch (dpcd[DP_DOWNSTREAMPORT_PRESENT] & DP_DWN_STRM_PORT_TYPE_MASK) { + case DP_DWN_STRM_PORT_TYPE_DP: + return 0; + default: + return 8; + } + } + + switch (port_cap[0] & DP_DS_PORT_TYPE_MASK) { + case DP_DS_PORT_TYPE_DP: + return 0; case DP_DS_PORT_TYPE_DP_DUALMODE: - bpc = port_cap[2] & DP_DS_MAX_BPC_MASK; + if (is_edid_digital_input_dp(edid)) + return 0; + fallthrough; + case DP_DS_PORT_TYPE_HDMI: + case DP_DS_PORT_TYPE_DVI: + case DP_DS_PORT_TYPE_VGA: + if ((dpcd[DP_DOWNSTREAMPORT_PRESENT] & DP_DETAILED_CAP_INFO_AVAILABLE) == 0) + return 8; - switch (bpc) { + switch (port_cap[2] & DP_DS_MAX_BPC_MASK) { case DP_DS_8BPC: return 8; case DP_DS_10BPC: @@ -626,15 +802,132 @@ int drm_dp_downstream_max_bpc(const u8 dpcd[DP_RECEIVER_CAP_SIZE], return 12; case DP_DS_16BPC: return 16; + default: + return 8; } - fallthrough; + break; default: - return 0; + return 8; } } EXPORT_SYMBOL(drm_dp_downstream_max_bpc); /** + * drm_dp_downstream_420_passthrough() - determine downstream facing port + * YCbCr 4:2:0 pass-through capability + * @dpcd: DisplayPort configuration data + * @port_cap: downstream facing port capabilities + * + * Returns: whether the downstream facing port can pass through YCbCr 4:2:0 + */ +bool drm_dp_downstream_420_passthrough(const u8 dpcd[DP_RECEIVER_CAP_SIZE], + const u8 port_cap[4]) +{ + if (!drm_dp_is_branch(dpcd)) + return false; + + if (dpcd[DP_DPCD_REV] < 0x13) + return false; + + switch (port_cap[0] & DP_DS_PORT_TYPE_MASK) { + case DP_DS_PORT_TYPE_DP: + return true; + case DP_DS_PORT_TYPE_HDMI: + if ((dpcd[DP_DOWNSTREAMPORT_PRESENT] & DP_DETAILED_CAP_INFO_AVAILABLE) == 0) + return false; + + return port_cap[3] & DP_DS_HDMI_YCBCR420_PASS_THROUGH; + default: + return false; + } +} +EXPORT_SYMBOL(drm_dp_downstream_420_passthrough); + +/** + * drm_dp_downstream_444_to_420_conversion() - determine downstream facing port + * YCbCr 4:4:4->4:2:0 conversion capability + * @dpcd: DisplayPort configuration data + * @port_cap: downstream facing port capabilities + * + * Returns: whether the downstream facing port can convert YCbCr 4:4:4 to 4:2:0 + */ +bool drm_dp_downstream_444_to_420_conversion(const u8 dpcd[DP_RECEIVER_CAP_SIZE], + const u8 port_cap[4]) +{ + if (!drm_dp_is_branch(dpcd)) + return false; + + if (dpcd[DP_DPCD_REV] < 0x13) + return false; + + switch (port_cap[0] & DP_DS_PORT_TYPE_MASK) { + case DP_DS_PORT_TYPE_HDMI: + if ((dpcd[DP_DOWNSTREAMPORT_PRESENT] & DP_DETAILED_CAP_INFO_AVAILABLE) == 0) + return false; + + return port_cap[3] & DP_DS_HDMI_YCBCR444_TO_420_CONV; + default: + return false; + } +} +EXPORT_SYMBOL(drm_dp_downstream_444_to_420_conversion); + +/** + * drm_dp_downstream_mode() - return a mode for downstream facing port + * @dev: DRM device + * @dpcd: DisplayPort configuration data + * @port_cap: port capabilities + * + * Provides a suitable mode for downstream facing ports without EDID. + * + * Returns: A new drm_display_mode on success or NULL on failure + */ +struct drm_display_mode * +drm_dp_downstream_mode(struct drm_device *dev, + const u8 dpcd[DP_RECEIVER_CAP_SIZE], + const u8 port_cap[4]) + +{ + u8 vic; + + if (!drm_dp_is_branch(dpcd)) + return NULL; + + if (dpcd[DP_DPCD_REV] < 0x11) + return NULL; + + switch (port_cap[0] & DP_DS_PORT_TYPE_MASK) { + case DP_DS_PORT_TYPE_NON_EDID: + switch (port_cap[0] & DP_DS_NON_EDID_MASK) { + case DP_DS_NON_EDID_720x480i_60: + vic = 6; + break; + case DP_DS_NON_EDID_720x480i_50: + vic = 21; + break; + case DP_DS_NON_EDID_1920x1080i_60: + vic = 5; + break; + case DP_DS_NON_EDID_1920x1080i_50: + vic = 20; + break; + case DP_DS_NON_EDID_1280x720_60: + vic = 4; + break; + case DP_DS_NON_EDID_1280x720_50: + vic = 19; + break; + default: + return NULL; + } + return drm_display_mode_from_cea_vic(dev, vic); + default: + return NULL; + } +} +EXPORT_SYMBOL(drm_dp_downstream_mode); + +/** * drm_dp_downstream_id() - identify branch device * @aux: DisplayPort AUX channel * @id: DisplayPort branch device id @@ -652,12 +945,15 @@ EXPORT_SYMBOL(drm_dp_downstream_id); * @m: pointer for debugfs file * @dpcd: DisplayPort configuration data * @port_cap: port capabilities + * @edid: EDID * @aux: DisplayPort AUX channel * */ void drm_dp_downstream_debug(struct seq_file *m, const u8 dpcd[DP_RECEIVER_CAP_SIZE], - const u8 port_cap[4], struct drm_dp_aux *aux) + const u8 port_cap[4], + const struct edid *edid, + struct drm_dp_aux *aux) { bool detailed_cap_info = dpcd[DP_DOWNSTREAMPORT_PRESENT] & DP_DETAILED_CAP_INFO_AVAILABLE; @@ -715,16 +1011,19 @@ void drm_dp_downstream_debug(struct seq_file *m, seq_printf(m, "\t\tSW: %d.%d\n", rev[0], rev[1]); if (detailed_cap_info) { - clk = drm_dp_downstream_max_clock(dpcd, port_cap); + clk = drm_dp_downstream_max_dotclock(dpcd, port_cap); + if (clk > 0) + seq_printf(m, "\t\tMax dot clock: %d kHz\n", clk); - if (clk > 0) { - if (type == DP_DS_PORT_TYPE_VGA) - seq_printf(m, "\t\tMax dot clock: %d kHz\n", clk); - else - seq_printf(m, "\t\tMax TMDS clock: %d kHz\n", clk); - } + clk = drm_dp_downstream_max_tmds_clock(dpcd, port_cap, edid); + if (clk > 0) + seq_printf(m, "\t\tMax TMDS clock: %d kHz\n", clk); - bpc = drm_dp_downstream_max_bpc(dpcd, port_cap); + clk = drm_dp_downstream_min_tmds_clock(dpcd, port_cap, edid); + if (clk > 0) + seq_printf(m, "\t\tMin TMDS clock: %d kHz\n", clk); + + bpc = drm_dp_downstream_max_bpc(dpcd, port_cap, edid); if (bpc > 0) seq_printf(m, "\t\tMax bpc: %d\n", bpc); @@ -734,7 +1033,8 @@ EXPORT_SYMBOL(drm_dp_downstream_debug); /** * drm_dp_subconnector_type() - get DP branch device type - * + * @dpcd: DisplayPort configuration data + * @port_cap: port capabilities */ enum drm_mode_subconnector drm_dp_subconnector_type(const u8 dpcd[DP_RECEIVER_CAP_SIZE], @@ -785,6 +1085,10 @@ EXPORT_SYMBOL(drm_dp_subconnector_type); /** * drm_mode_set_dp_subconnector_property - set subconnector for DP connector + * @connector: connector to set property on + * @status: connector status + * @dpcd: DisplayPort configuration data + * @port_cap: port capabilities * * Called by a driver on every detect event. */ diff --git a/drivers/gpu/drm/drm_dp_mst_topology.c b/drivers/gpu/drm/drm_dp_mst_topology.c index b4a4bb340910..153b6065ba29 100644 --- a/drivers/gpu/drm/drm_dp_mst_topology.c +++ b/drivers/gpu/drm/drm_dp_mst_topology.c @@ -20,11 +20,13 @@ * OF THIS SOFTWARE. */ +#include <linux/bitfield.h> #include <linux/delay.h> #include <linux/errno.h> #include <linux/i2c.h> #include <linux/init.h> #include <linux/kernel.h> +#include <linux/random.h> #include <linux/sched.h> #include <linux/seq_file.h> #include <linux/iopoll.h> @@ -423,6 +425,22 @@ drm_dp_encode_sideband_req(const struct drm_dp_sideband_msg_req_body *req, memcpy(&buf[idx], req->u.i2c_write.bytes, req->u.i2c_write.num_bytes); idx += req->u.i2c_write.num_bytes; break; + case DP_QUERY_STREAM_ENC_STATUS: { + const struct drm_dp_query_stream_enc_status *msg; + + msg = &req->u.enc_status; + buf[idx] = msg->stream_id; + idx++; + memcpy(&buf[idx], msg->client_id, sizeof(msg->client_id)); + idx += sizeof(msg->client_id); + buf[idx] = 0; + buf[idx] |= FIELD_PREP(GENMASK(1, 0), msg->stream_event); + buf[idx] |= msg->valid_stream_event ? BIT(2) : 0; + buf[idx] |= FIELD_PREP(GENMASK(4, 3), msg->stream_behavior); + buf[idx] |= msg->valid_stream_behavior ? BIT(5) : 0; + idx++; + } + break; } raw->cur_len = idx; } @@ -551,6 +569,20 @@ drm_dp_decode_sideband_req(const struct drm_dp_sideband_msg_tx *raw, return -ENOMEM; } break; + case DP_QUERY_STREAM_ENC_STATUS: + req->u.enc_status.stream_id = buf[idx++]; + for (i = 0; i < sizeof(req->u.enc_status.client_id); i++) + req->u.enc_status.client_id[i] = buf[idx++]; + + req->u.enc_status.stream_event = FIELD_GET(GENMASK(1, 0), + buf[idx]); + req->u.enc_status.valid_stream_event = FIELD_GET(BIT(2), + buf[idx]); + req->u.enc_status.stream_behavior = FIELD_GET(GENMASK(4, 3), + buf[idx]); + req->u.enc_status.valid_stream_behavior = FIELD_GET(BIT(5), + buf[idx]); + break; } return 0; @@ -629,6 +661,16 @@ drm_dp_dump_sideband_msg_req_body(const struct drm_dp_sideband_msg_req_body *req req->u.i2c_write.num_bytes, req->u.i2c_write.num_bytes, req->u.i2c_write.bytes); break; + case DP_QUERY_STREAM_ENC_STATUS: + P("stream_id=%u client_id=%*ph stream_event=%x " + "valid_event=%d stream_behavior=%x valid_behavior=%d", + req->u.enc_status.stream_id, + (int)ARRAY_SIZE(req->u.enc_status.client_id), + req->u.enc_status.client_id, req->u.enc_status.stream_event, + req->u.enc_status.valid_stream_event, + req->u.enc_status.stream_behavior, + req->u.enc_status.valid_stream_behavior); + break; default: P("???\n"); break; @@ -936,6 +978,42 @@ static bool drm_dp_sideband_parse_power_updown_phy_ack(struct drm_dp_sideband_ms return true; } +static bool +drm_dp_sideband_parse_query_stream_enc_status( + struct drm_dp_sideband_msg_rx *raw, + struct drm_dp_sideband_msg_reply_body *repmsg) +{ + struct drm_dp_query_stream_enc_status_ack_reply *reply; + + reply = &repmsg->u.enc_status; + + reply->stream_id = raw->msg[3]; + + reply->reply_signed = raw->msg[2] & BIT(0); + + /* + * NOTE: It's my impression from reading the spec that the below parsing + * is correct. However I noticed while testing with an HDCP 1.4 display + * through an HDCP 2.2 hub that only bit 3 was set. In that case, I + * would expect both bits to be set. So keep the parsing following the + * spec, but beware reality might not match the spec (at least for some + * configurations). + */ + reply->hdcp_1x_device_present = raw->msg[2] & BIT(4); + reply->hdcp_2x_device_present = raw->msg[2] & BIT(3); + + reply->query_capable_device_present = raw->msg[2] & BIT(5); + reply->legacy_device_present = raw->msg[2] & BIT(6); + reply->unauthorizable_device_present = raw->msg[2] & BIT(7); + + reply->auth_completed = !!(raw->msg[1] & BIT(3)); + reply->encryption_enabled = !!(raw->msg[1] & BIT(4)); + reply->repeater_present = !!(raw->msg[1] & BIT(5)); + reply->state = (raw->msg[1] & GENMASK(7, 6)) >> 6; + + return true; +} + static bool drm_dp_sideband_parse_reply(struct drm_dp_sideband_msg_rx *raw, struct drm_dp_sideband_msg_reply_body *msg) { @@ -972,6 +1050,8 @@ static bool drm_dp_sideband_parse_reply(struct drm_dp_sideband_msg_rx *raw, return drm_dp_sideband_parse_power_updown_phy_ack(raw, msg); case DP_CLEAR_PAYLOAD_ID_TABLE: return true; /* since there's nothing to parse */ + case DP_QUERY_STREAM_ENC_STATUS: + return drm_dp_sideband_parse_query_stream_enc_status(raw, msg); default: DRM_ERROR("Got unknown reply 0x%02x (%s)\n", msg->req_type, drm_dp_mst_req_type_str(msg->req_type)); @@ -1123,6 +1203,25 @@ static void build_power_updown_phy(struct drm_dp_sideband_msg_tx *msg, msg->path_msg = true; } +static int +build_query_stream_enc_status(struct drm_dp_sideband_msg_tx *msg, u8 stream_id, + u8 *q_id) +{ + struct drm_dp_sideband_msg_req_body req; + + req.req_type = DP_QUERY_STREAM_ENC_STATUS; + req.u.enc_status.stream_id = stream_id; + memcpy(req.u.enc_status.client_id, q_id, + sizeof(req.u.enc_status.client_id)); + req.u.enc_status.stream_event = 0; + req.u.enc_status.valid_stream_event = false; + req.u.enc_status.stream_behavior = 0; + req.u.enc_status.valid_stream_behavior = false; + + drm_dp_encode_sideband_req(&req, msg); + return 0; +} + static int drm_dp_mst_assign_payload_id(struct drm_dp_mst_topology_mgr *mgr, struct drm_dp_vcpi *vcpi) { @@ -3155,6 +3254,57 @@ int drm_dp_send_power_updown_phy(struct drm_dp_mst_topology_mgr *mgr, } EXPORT_SYMBOL(drm_dp_send_power_updown_phy); +int drm_dp_send_query_stream_enc_status(struct drm_dp_mst_topology_mgr *mgr, + struct drm_dp_mst_port *port, + struct drm_dp_query_stream_enc_status_ack_reply *status) +{ + struct drm_dp_sideband_msg_tx *txmsg; + u8 nonce[7]; + int len, ret; + + txmsg = kzalloc(sizeof(*txmsg), GFP_KERNEL); + if (!txmsg) + return -ENOMEM; + + port = drm_dp_mst_topology_get_port_validated(mgr, port); + if (!port) { + ret = -EINVAL; + goto out_get_port; + } + + get_random_bytes(nonce, sizeof(nonce)); + + /* + * "Source device targets the QUERY_STREAM_ENCRYPTION_STATUS message + * transaction at the MST Branch device directly connected to the + * Source" + */ + txmsg->dst = mgr->mst_primary; + + len = build_query_stream_enc_status(txmsg, port->vcpi.vcpi, nonce); + + drm_dp_queue_down_tx(mgr, txmsg); + + ret = drm_dp_mst_wait_tx_reply(mgr->mst_primary, txmsg); + if (ret < 0) { + goto out; + } else if (txmsg->reply.reply_type == DP_SIDEBAND_REPLY_NAK) { + drm_dbg_kms(mgr->dev, "query encryption status nak received\n"); + ret = -ENXIO; + goto out; + } + + ret = 0; + memcpy(status, &txmsg->reply.u.enc_status, sizeof(*status)); + +out: + drm_dp_mst_topology_put_port(port); +out_get_port: + kfree(txmsg); + return ret; +} +EXPORT_SYMBOL(drm_dp_send_query_stream_enc_status); + static int drm_dp_create_payload_step1(struct drm_dp_mst_topology_mgr *mgr, int id, struct drm_dp_payload *payload) diff --git a/drivers/gpu/drm/drm_edid.c b/drivers/gpu/drm/drm_edid.c index 7060152a5daa..c7363af731b4 100644 --- a/drivers/gpu/drm/drm_edid.c +++ b/drivers/gpu/drm/drm_edid.c @@ -3738,6 +3738,34 @@ drm_add_cmdb_modes(struct drm_connector *connector, u8 svd) bitmap_set(hdmi->y420_cmdb_modes, vic, 1); } +/** + * drm_display_mode_from_cea_vic() - return a mode for CEA VIC + * @dev: DRM device + * @video_code: CEA VIC of the mode + * + * Creates a new mode matching the specified CEA VIC. + * + * Returns: A new drm_display_mode on success or NULL on failure + */ +struct drm_display_mode * +drm_display_mode_from_cea_vic(struct drm_device *dev, + u8 video_code) +{ + const struct drm_display_mode *cea_mode; + struct drm_display_mode *newmode; + + cea_mode = cea_mode_for_vic(video_code); + if (!cea_mode) + return NULL; + + newmode = drm_mode_duplicate(dev, cea_mode); + if (!newmode) + return NULL; + + return newmode; +} +EXPORT_SYMBOL(drm_display_mode_from_cea_vic); + static int do_cea_modes(struct drm_connector *connector, const u8 *db, u8 len) { diff --git a/drivers/gpu/drm/drm_fb_helper.c b/drivers/gpu/drm/drm_fb_helper.c index c2f72bb6afb1..92e0db30fdf7 100644 --- a/drivers/gpu/drm/drm_fb_helper.c +++ b/drivers/gpu/drm/drm_fb_helper.c @@ -309,7 +309,7 @@ static void drm_fb_helper_sysrq(int dummy1) static const struct sysrq_key_op sysrq_drm_fb_helper_restore_op = { .handler = drm_fb_helper_sysrq, - .help_msg = "force-fb(V)", + .help_msg = "force-fb(v)", .action_msg = "Restore framebuffer console", }; #else diff --git a/drivers/gpu/drm/drm_gem.c b/drivers/gpu/drm/drm_gem.c index 1da67d34e55d..d586068f5509 100644 --- a/drivers/gpu/drm/drm_gem.c +++ b/drivers/gpu/drm/drm_gem.c @@ -1076,6 +1076,8 @@ int drm_gem_mmap_obj(struct drm_gem_object *obj, unsigned long obj_size, */ drm_gem_object_get(obj); + vma->vm_private_data = obj; + if (obj->funcs->mmap) { ret = obj->funcs->mmap(obj, vma); if (ret) { @@ -1096,8 +1098,6 @@ int drm_gem_mmap_obj(struct drm_gem_object *obj, unsigned long obj_size, vma->vm_page_prot = pgprot_decrypted(vma->vm_page_prot); } - vma->vm_private_data = obj; - return 0; } EXPORT_SYMBOL(drm_gem_mmap_obj); diff --git a/drivers/gpu/drm/drm_gem_cma_helper.c b/drivers/gpu/drm/drm_gem_cma_helper.c index 5e9d29961307..2165633c9b9e 100644 --- a/drivers/gpu/drm/drm_gem_cma_helper.c +++ b/drivers/gpu/drm/drm_gem_cma_helper.c @@ -470,26 +470,9 @@ drm_gem_cma_prime_import_sg_table(struct drm_device *dev, { struct drm_gem_cma_object *cma_obj; - if (sgt->nents != 1) { - /* check if the entries in the sg_table are contiguous */ - dma_addr_t next_addr = sg_dma_address(sgt->sgl); - struct scatterlist *s; - unsigned int i; - - for_each_sg(sgt->sgl, s, sgt->nents, i) { - /* - * sg_dma_address(s) is only valid for entries - * that have sg_dma_len(s) != 0 - */ - if (!sg_dma_len(s)) - continue; - - if (sg_dma_address(s) != next_addr) - return ERR_PTR(-EINVAL); - - next_addr = sg_dma_address(s) + sg_dma_len(s); - } - } + /* check if the entries in the sg_table are contiguous */ + if (drm_prime_get_contiguous_size(sgt) < attach->dmabuf->size) + return ERR_PTR(-EINVAL); /* Create a CMA GEM buffer. */ cma_obj = __drm_gem_cma_create(dev, attach->dmabuf->size); diff --git a/drivers/gpu/drm/drm_gem_shmem_helper.c b/drivers/gpu/drm/drm_gem_shmem_helper.c index 3c2e8cde69a8..8233bda4692f 100644 --- a/drivers/gpu/drm/drm_gem_shmem_helper.c +++ b/drivers/gpu/drm/drm_gem_shmem_helper.c @@ -126,8 +126,8 @@ void drm_gem_shmem_free_object(struct drm_gem_object *obj) drm_prime_gem_destroy(obj, shmem->sgt); } else { if (shmem->sgt) { - dma_unmap_sg(obj->dev->dev, shmem->sgt->sgl, - shmem->sgt->nents, DMA_BIDIRECTIONAL); + dma_unmap_sgtable(obj->dev->dev, shmem->sgt, + DMA_BIDIRECTIONAL, 0); sg_free_table(shmem->sgt); kfree(shmem->sgt); } @@ -429,8 +429,7 @@ void drm_gem_shmem_purge_locked(struct drm_gem_object *obj) WARN_ON(!drm_gem_shmem_is_purgeable(shmem)); - dma_unmap_sg(obj->dev->dev, shmem->sgt->sgl, - shmem->sgt->nents, DMA_BIDIRECTIONAL); + dma_unmap_sgtable(obj->dev->dev, shmem->sgt, DMA_BIDIRECTIONAL, 0); sg_free_table(shmem->sgt); kfree(shmem->sgt); shmem->sgt = NULL; @@ -599,8 +598,13 @@ int drm_gem_shmem_mmap(struct drm_gem_object *obj, struct vm_area_struct *vma) /* Remove the fake offset */ vma->vm_pgoff -= drm_vma_node_start(&obj->vma_node); - if (obj->import_attach) + if (obj->import_attach) { + /* Drop the reference drm_gem_mmap_obj() acquired.*/ + drm_gem_object_put(obj); + vma->vm_private_data = NULL; + return dma_buf_mmap(obj->dma_buf, vma, 0); + } shmem = to_drm_gem_shmem_obj(obj); @@ -702,12 +706,17 @@ struct sg_table *drm_gem_shmem_get_pages_sgt(struct drm_gem_object *obj) goto err_put_pages; } /* Map the pages for use by the h/w. */ - dma_map_sg(obj->dev->dev, sgt->sgl, sgt->nents, DMA_BIDIRECTIONAL); + ret = dma_map_sgtable(obj->dev->dev, sgt, DMA_BIDIRECTIONAL, 0); + if (ret) + goto err_free_sgt; shmem->sgt = sgt; return sgt; +err_free_sgt: + sg_free_table(sgt); + kfree(sgt); err_put_pages: drm_gem_shmem_put_pages(shmem); return ERR_PTR(ret); diff --git a/drivers/gpu/drm/drm_prime.c b/drivers/gpu/drm/drm_prime.c index 4910c446db83..187b55ede62e 100644 --- a/drivers/gpu/drm/drm_prime.c +++ b/drivers/gpu/drm/drm_prime.c @@ -615,6 +615,7 @@ struct sg_table *drm_gem_map_dma_buf(struct dma_buf_attachment *attach, { struct drm_gem_object *obj = attach->dmabuf->priv; struct sg_table *sgt; + int ret; if (WARN_ON(dir == DMA_NONE)) return ERR_PTR(-EINVAL); @@ -626,11 +627,12 @@ struct sg_table *drm_gem_map_dma_buf(struct dma_buf_attachment *attach, if (IS_ERR(sgt)) return sgt; - if (!dma_map_sg_attrs(attach->dev, sgt->sgl, sgt->nents, dir, - DMA_ATTR_SKIP_CPU_SYNC)) { + ret = dma_map_sgtable(attach->dev, sgt, dir, + DMA_ATTR_SKIP_CPU_SYNC); + if (ret) { sg_free_table(sgt); kfree(sgt); - sgt = ERR_PTR(-ENOMEM); + sgt = ERR_PTR(ret); } return sgt; @@ -652,8 +654,7 @@ void drm_gem_unmap_dma_buf(struct dma_buf_attachment *attach, if (!sgt) return; - dma_unmap_sg_attrs(attach->dev, sgt->sgl, sgt->nents, dir, - DMA_ATTR_SKIP_CPU_SYNC); + dma_unmap_sgtable(attach->dev, sgt, dir, DMA_ATTR_SKIP_CPU_SYNC); sg_free_table(sgt); kfree(sgt); } @@ -796,6 +797,7 @@ static const struct dma_buf_ops drm_gem_prime_dmabuf_ops = { /** * drm_prime_pages_to_sg - converts a page array into an sg list + * @dev: DRM device * @pages: pointer to the array of page pointers to convert * @nr_pages: length of the page vector * @@ -808,34 +810,62 @@ static const struct dma_buf_ops drm_gem_prime_dmabuf_ops = { struct sg_table *drm_prime_pages_to_sg(struct drm_device *dev, struct page **pages, unsigned int nr_pages) { - struct sg_table *sg = NULL; + struct sg_table *sg; + struct scatterlist *sge; size_t max_segment = 0; - int ret; sg = kmalloc(sizeof(struct sg_table), GFP_KERNEL); - if (!sg) { - ret = -ENOMEM; - goto out; - } + if (!sg) + return ERR_PTR(-ENOMEM); if (dev) max_segment = dma_max_mapping_size(dev->dev); if (max_segment == 0 || max_segment > SCATTERLIST_MAX_SEGMENT) max_segment = SCATTERLIST_MAX_SEGMENT; - ret = __sg_alloc_table_from_pages(sg, pages, nr_pages, 0, + sge = __sg_alloc_table_from_pages(sg, pages, nr_pages, 0, nr_pages << PAGE_SHIFT, - max_segment, GFP_KERNEL); - if (ret) - goto out; - + max_segment, + NULL, 0, GFP_KERNEL); + if (IS_ERR(sge)) { + kfree(sg); + sg = ERR_CAST(sge); + } return sg; -out: - kfree(sg); - return ERR_PTR(ret); } EXPORT_SYMBOL(drm_prime_pages_to_sg); /** + * drm_prime_get_contiguous_size - returns the contiguous size of the buffer + * @sgt: sg_table describing the buffer to check + * + * This helper calculates the contiguous size in the DMA address space + * of the the buffer described by the provided sg_table. + * + * This is useful for implementing + * &drm_gem_object_funcs.gem_prime_import_sg_table. + */ +unsigned long drm_prime_get_contiguous_size(struct sg_table *sgt) +{ + dma_addr_t expected = sg_dma_address(sgt->sgl); + struct scatterlist *sg; + unsigned long size = 0; + int i; + + for_each_sgtable_dma_sg(sgt, sg, i) { + unsigned int len = sg_dma_len(sg); + + if (!len) + break; + if (sg_dma_address(sg) != expected) + break; + expected += len; + size += len; + } + return size; +} +EXPORT_SYMBOL(drm_prime_get_contiguous_size); + +/** * drm_gem_prime_export - helper library implementation of the export callback * @obj: GEM object to export * @flags: flags like DRM_CLOEXEC and DRM_RDWR @@ -969,45 +999,26 @@ EXPORT_SYMBOL(drm_gem_prime_import); int drm_prime_sg_to_page_addr_arrays(struct sg_table *sgt, struct page **pages, dma_addr_t *addrs, int max_entries) { - unsigned count; - struct scatterlist *sg; - struct page *page; - u32 page_len, page_index; - dma_addr_t addr; - u32 dma_len, dma_index; - - /* - * Scatterlist elements contains both pages and DMA addresses, but - * one shoud not assume 1:1 relation between them. The sg->length is - * the size of the physical memory chunk described by the sg->page, - * while sg_dma_len(sg) is the size of the DMA (IO virtual) chunk - * described by the sg_dma_address(sg). - */ - page_index = 0; - dma_index = 0; - for_each_sg(sgt->sgl, sg, sgt->nents, count) { - page_len = sg->length; - page = sg_page(sg); - dma_len = sg_dma_len(sg); - addr = sg_dma_address(sg); - - while (pages && page_len > 0) { - if (WARN_ON(page_index >= max_entries)) + struct sg_dma_page_iter dma_iter; + struct sg_page_iter page_iter; + struct page **p = pages; + dma_addr_t *a = addrs; + + if (pages) { + for_each_sgtable_page(sgt, &page_iter, 0) { + if (WARN_ON(p - pages >= max_entries)) return -1; - pages[page_index] = page; - page++; - page_len -= PAGE_SIZE; - page_index++; + *p++ = sg_page_iter_page(&page_iter); } - while (addrs && dma_len > 0) { - if (WARN_ON(dma_index >= max_entries)) + } + if (addrs) { + for_each_sgtable_dma_page(sgt, &dma_iter, 0) { + if (WARN_ON(a - addrs >= max_entries)) return -1; - addrs[dma_index] = addr; - addr += PAGE_SIZE; - dma_len -= PAGE_SIZE; - dma_index++; + *a++ = sg_page_iter_dma_address(&dma_iter); } } + return 0; } EXPORT_SYMBOL(drm_prime_sg_to_page_addr_arrays); diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gem.c b/drivers/gpu/drm/etnaviv/etnaviv_gem.c index 312e9d58d5a7..67d9a2b9ea6a 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_gem.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_gem.c @@ -27,7 +27,7 @@ static void etnaviv_gem_scatter_map(struct etnaviv_gem_object *etnaviv_obj) * because display controller, GPU, etc. are not coherent. */ if (etnaviv_obj->flags & ETNA_BO_CACHE_MASK) - dma_map_sg(dev->dev, sgt->sgl, sgt->nents, DMA_BIDIRECTIONAL); + dma_map_sgtable(dev->dev, sgt, DMA_BIDIRECTIONAL, 0); } static void etnaviv_gem_scatterlist_unmap(struct etnaviv_gem_object *etnaviv_obj) @@ -51,7 +51,7 @@ static void etnaviv_gem_scatterlist_unmap(struct etnaviv_gem_object *etnaviv_obj * discard those writes. */ if (etnaviv_obj->flags & ETNA_BO_CACHE_MASK) - dma_unmap_sg(dev->dev, sgt->sgl, sgt->nents, DMA_BIDIRECTIONAL); + dma_unmap_sgtable(dev->dev, sgt, DMA_BIDIRECTIONAL, 0); } /* called with etnaviv_obj->lock held */ @@ -405,9 +405,8 @@ int etnaviv_gem_cpu_prep(struct drm_gem_object *obj, u32 op, } if (etnaviv_obj->flags & ETNA_BO_CACHED) { - dma_sync_sg_for_cpu(dev->dev, etnaviv_obj->sgt->sgl, - etnaviv_obj->sgt->nents, - etnaviv_op_to_dma_dir(op)); + dma_sync_sgtable_for_cpu(dev->dev, etnaviv_obj->sgt, + etnaviv_op_to_dma_dir(op)); etnaviv_obj->last_cpu_prep_op = op; } @@ -422,8 +421,7 @@ int etnaviv_gem_cpu_fini(struct drm_gem_object *obj) if (etnaviv_obj->flags & ETNA_BO_CACHED) { /* fini without a prep is almost certainly a userspace error */ WARN_ON(etnaviv_obj->last_cpu_prep_op == 0); - dma_sync_sg_for_device(dev->dev, etnaviv_obj->sgt->sgl, - etnaviv_obj->sgt->nents, + dma_sync_sgtable_for_device(dev->dev, etnaviv_obj->sgt, etnaviv_op_to_dma_dir(etnaviv_obj->last_cpu_prep_op)); etnaviv_obj->last_cpu_prep_op = 0; } diff --git a/drivers/gpu/drm/etnaviv/etnaviv_mmu.c b/drivers/gpu/drm/etnaviv/etnaviv_mmu.c index 3607d348c298..15d9fa3879e5 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_mmu.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_mmu.c @@ -73,13 +73,13 @@ static int etnaviv_iommu_map(struct etnaviv_iommu_context *context, u32 iova, struct sg_table *sgt, unsigned len, int prot) { struct scatterlist *sg; unsigned int da = iova; - unsigned int i, j; + unsigned int i; int ret; if (!context || !sgt) return -EINVAL; - for_each_sg(sgt->sgl, sg, sgt->nents, i) { + for_each_sgtable_dma_sg(sgt, sg, i) { u32 pa = sg_dma_address(sg) - sg->offset; size_t bytes = sg_dma_len(sg) + sg->offset; @@ -95,14 +95,7 @@ static int etnaviv_iommu_map(struct etnaviv_iommu_context *context, u32 iova, return 0; fail: - da = iova; - - for_each_sg(sgt->sgl, sg, i, j) { - size_t bytes = sg_dma_len(sg) + sg->offset; - - etnaviv_context_unmap(context, da, bytes); - da += bytes; - } + etnaviv_context_unmap(context, iova, da - iova); return ret; } @@ -113,7 +106,7 @@ static void etnaviv_iommu_unmap(struct etnaviv_iommu_context *context, u32 iova, unsigned int da = iova; int i; - for_each_sg(sgt->sgl, sg, sgt->nents, i) { + for_each_sgtable_dma_sg(sgt, sg, i) { size_t bytes = sg_dma_len(sg) + sg->offset; etnaviv_context_unmap(context, da, bytes); diff --git a/drivers/gpu/drm/exynos/exynos_drm_dma.c b/drivers/gpu/drm/exynos/exynos_drm_dma.c index 58b89ec11b0e..0644936afee2 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_dma.c +++ b/drivers/gpu/drm/exynos/exynos_drm_dma.c @@ -5,7 +5,7 @@ // Author: Andrzej Hajda <a.hajda@samsung.com> #include <linux/dma-iommu.h> -#include <linux/dma-mapping.h> +#include <linux/dma-map-ops.h> #include <linux/iommu.h> #include <linux/platform_device.h> @@ -31,23 +31,6 @@ #define EXYNOS_DEV_ADDR_START 0x20000000 #define EXYNOS_DEV_ADDR_SIZE 0x40000000 -static inline int configure_dma_max_seg_size(struct device *dev) -{ - if (!dev->dma_parms) - dev->dma_parms = kzalloc(sizeof(*dev->dma_parms), GFP_KERNEL); - if (!dev->dma_parms) - return -ENOMEM; - - dma_set_max_seg_size(dev, DMA_BIT_MASK(32)); - return 0; -} - -static inline void clear_dma_max_seg_size(struct device *dev) -{ - kfree(dev->dma_parms); - dev->dma_parms = NULL; -} - /* * drm_iommu_attach_device- attach device to iommu mapping * @@ -69,10 +52,7 @@ static int drm_iommu_attach_device(struct drm_device *drm_dev, return -EINVAL; } - ret = configure_dma_max_seg_size(subdrv_dev); - if (ret) - return ret; - + dma_set_max_seg_size(subdrv_dev, DMA_BIT_MASK(32)); if (IS_ENABLED(CONFIG_ARM_DMA_USE_IOMMU)) { /* * Keep the original DMA mapping of the sub-device and @@ -89,9 +69,6 @@ static int drm_iommu_attach_device(struct drm_device *drm_dev, ret = iommu_attach_device(priv->mapping, subdrv_dev); } - if (ret) - clear_dma_max_seg_size(subdrv_dev); - return ret; } @@ -114,8 +91,6 @@ static void drm_iommu_detach_device(struct drm_device *drm_dev, arm_iommu_attach_device(subdrv_dev, *dma_priv); } else if (IS_ENABLED(CONFIG_IOMMU_DMA)) iommu_detach_device(priv->mapping, subdrv_dev); - - clear_dma_max_seg_size(subdrv_dev); } int exynos_drm_register_dma(struct drm_device *drm, struct device *dev, diff --git a/drivers/gpu/drm/exynos/exynos_drm_dsi.c b/drivers/gpu/drm/exynos/exynos_drm_dsi.c index 1a1a2853a842..5b9666fc7af1 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_dsi.c +++ b/drivers/gpu/drm/exynos/exynos_drm_dsi.c @@ -1760,11 +1760,8 @@ static int exynos_dsi_probe(struct platform_device *pdev) dsi->supplies[1].supply = "vddio"; ret = devm_regulator_bulk_get(dev, ARRAY_SIZE(dsi->supplies), dsi->supplies); - if (ret) { - if (ret != -EPROBE_DEFER) - dev_info(dev, "failed to get regulators: %d\n", ret); - return ret; - } + if (ret) + return dev_err_probe(dev, ret, "failed to get regulators\n"); dsi->clks = devm_kcalloc(dev, dsi->driver_data->num_clks, sizeof(*dsi->clks), diff --git a/drivers/gpu/drm/exynos/exynos_drm_g2d.c b/drivers/gpu/drm/exynos/exynos_drm_g2d.c index 03be31427181..967a5cdc120e 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_g2d.c +++ b/drivers/gpu/drm/exynos/exynos_drm_g2d.c @@ -395,8 +395,8 @@ static void g2d_userptr_put_dma_addr(struct g2d_data *g2d, return; out: - dma_unmap_sg(to_dma_dev(g2d->drm_dev), g2d_userptr->sgt->sgl, - g2d_userptr->sgt->nents, DMA_BIDIRECTIONAL); + dma_unmap_sgtable(to_dma_dev(g2d->drm_dev), g2d_userptr->sgt, + DMA_BIDIRECTIONAL, 0); pages = frame_vector_pages(g2d_userptr->vec); if (!IS_ERR(pages)) { @@ -511,10 +511,10 @@ static dma_addr_t *g2d_userptr_get_dma_addr(struct g2d_data *g2d, g2d_userptr->sgt = sgt; - if (!dma_map_sg(to_dma_dev(g2d->drm_dev), sgt->sgl, sgt->nents, - DMA_BIDIRECTIONAL)) { + ret = dma_map_sgtable(to_dma_dev(g2d->drm_dev), sgt, + DMA_BIDIRECTIONAL, 0); + if (ret) { DRM_DEV_ERROR(g2d->dev, "failed to map sgt with dma region.\n"); - ret = -ENOMEM; goto err_sg_free_table; } diff --git a/drivers/gpu/drm/exynos/exynos_drm_gem.c b/drivers/gpu/drm/exynos/exynos_drm_gem.c index 69a5cf28b4ae..4afbf5109cbf 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_gem.c +++ b/drivers/gpu/drm/exynos/exynos_drm_gem.c @@ -42,8 +42,6 @@ static int exynos_drm_alloc_buf(struct exynos_drm_gem *exynos_gem, bool kvmap) if (exynos_gem->flags & EXYNOS_BO_WC || !(exynos_gem->flags & EXYNOS_BO_CACHABLE)) attr |= DMA_ATTR_WRITE_COMBINE; - else - attr |= DMA_ATTR_NON_CONSISTENT; /* FBDev emulation requires kernel mapping */ if (!kvmap) @@ -446,27 +444,10 @@ exynos_drm_gem_prime_import_sg_table(struct drm_device *dev, { struct exynos_drm_gem *exynos_gem; - if (sgt->nents < 1) + /* check if the entries in the sg_table are contiguous */ + if (drm_prime_get_contiguous_size(sgt) < attach->dmabuf->size) { + DRM_ERROR("buffer chunks must be mapped contiguously"); return ERR_PTR(-EINVAL); - - /* - * Check if the provided buffer has been mapped as contiguous - * into DMA address space. - */ - if (sgt->nents > 1) { - dma_addr_t next_addr = sg_dma_address(sgt->sgl); - struct scatterlist *s; - unsigned int i; - - for_each_sg(sgt->sgl, s, sgt->nents, i) { - if (!sg_dma_len(s)) - break; - if (sg_dma_address(s) != next_addr) { - DRM_ERROR("buffer chunks must be mapped contiguously"); - return ERR_PTR(-EINVAL); - } - next_addr = sg_dma_address(s) + sg_dma_len(s); - } } exynos_gem = exynos_drm_gem_init(dev, attach->dmabuf->size); diff --git a/drivers/gpu/drm/exynos/exynos_hdmi.c b/drivers/gpu/drm/exynos/exynos_hdmi.c index c5ba32fca5f3..dc01c188c0e0 100644 --- a/drivers/gpu/drm/exynos/exynos_hdmi.c +++ b/drivers/gpu/drm/exynos/exynos_hdmi.c @@ -1797,11 +1797,8 @@ static int hdmi_resources_init(struct hdmi_context *hdata) hdata->regul_bulk[i].supply = supply[i]; ret = devm_regulator_bulk_get(dev, ARRAY_SIZE(supply), hdata->regul_bulk); - if (ret) { - if (ret != -EPROBE_DEFER) - DRM_DEV_ERROR(dev, "failed to get regulators\n"); - return ret; - } + if (ret) + return dev_err_probe(dev, ret, "failed to get regulators\n"); hdata->reg_hdmi_en = devm_regulator_get_optional(dev, "hdmi-en"); diff --git a/drivers/gpu/drm/i915/Kconfig b/drivers/gpu/drm/i915/Kconfig index 9afa5c4a6bf0..1e1cb245fca7 100644 --- a/drivers/gpu/drm/i915/Kconfig +++ b/drivers/gpu/drm/i915/Kconfig @@ -25,6 +25,7 @@ config DRM_I915 select CRC32 select SND_HDA_I915 if SND_HDA_CORE select CEC_CORE if CEC_NOTIFIER + select VMAP_PFN help Choose this option if you have a system that has "Intel Graphics Media Accelerator" or "HD Graphics" integrated graphics, diff --git a/drivers/gpu/drm/i915/Kconfig.debug b/drivers/gpu/drm/i915/Kconfig.debug index 1cb28c20807c..25cd9788a4d5 100644 --- a/drivers/gpu/drm/i915/Kconfig.debug +++ b/drivers/gpu/drm/i915/Kconfig.debug @@ -153,6 +153,7 @@ config DRM_I915_SELFTEST select DRM_EXPORT_FOR_TESTS if m select FAULT_INJECTION select PRIME_NUMBERS + select CRC32 help Choose this option to allow the driver to perform selftests upon loading; also requires the i915.selftest=1 module parameter. To diff --git a/drivers/gpu/drm/i915/Makefile b/drivers/gpu/drm/i915/Makefile index bda4c0e408f8..e5574e506a5c 100644 --- a/drivers/gpu/drm/i915/Makefile +++ b/drivers/gpu/drm/i915/Makefile @@ -234,6 +234,7 @@ i915-y += \ display/intel_ddi.o \ display/intel_dp.o \ display/intel_dp_aux_backlight.o \ + display/intel_dp_hdcp.o \ display/intel_dp_link_training.o \ display/intel_dp_mst.o \ display/intel_dsi.o \ diff --git a/drivers/gpu/drm/i915/display/icl_dsi.c b/drivers/gpu/drm/i915/display/icl_dsi.c index f4053dd6bde9..520715b7d5b5 100644 --- a/drivers/gpu/drm/i915/display/icl_dsi.c +++ b/drivers/gpu/drm/i915/display/icl_dsi.c @@ -1646,6 +1646,7 @@ static const struct drm_encoder_funcs gen11_dsi_encoder_funcs = { }; static const struct drm_connector_funcs gen11_dsi_connector_funcs = { + .detect = intel_panel_detect, .late_register = intel_connector_register, .early_unregister = intel_connector_unregister, .destroy = intel_connector_destroy, diff --git a/drivers/gpu/drm/i915/display/intel_atomic.c b/drivers/gpu/drm/i915/display/intel_atomic.c index 630f49b7aa01..86be032bcf96 100644 --- a/drivers/gpu/drm/i915/display/intel_atomic.c +++ b/drivers/gpu/drm/i915/display/intel_atomic.c @@ -527,8 +527,6 @@ void intel_atomic_state_clear(struct drm_atomic_state *s) intel_atomic_clear_global_state(state); state->dpll_set = state->modeset = false; - state->global_state_changed = false; - state->active_pipes = 0; } struct intel_crtc_state * @@ -542,40 +540,3 @@ intel_atomic_get_crtc_state(struct drm_atomic_state *state, return to_intel_crtc_state(crtc_state); } - -int _intel_atomic_lock_global_state(struct intel_atomic_state *state) -{ - struct drm_i915_private *dev_priv = to_i915(state->base.dev); - struct intel_crtc *crtc; - - state->global_state_changed = true; - - for_each_intel_crtc(&dev_priv->drm, crtc) { - int ret; - - ret = drm_modeset_lock(&crtc->base.mutex, - state->base.acquire_ctx); - if (ret) - return ret; - } - - return 0; -} - -int _intel_atomic_serialize_global_state(struct intel_atomic_state *state) -{ - struct drm_i915_private *dev_priv = to_i915(state->base.dev); - struct intel_crtc *crtc; - - state->global_state_changed = true; - - for_each_intel_crtc(&dev_priv->drm, crtc) { - struct intel_crtc_state *crtc_state; - - crtc_state = intel_atomic_get_crtc_state(&state->base, crtc); - if (IS_ERR(crtc_state)) - return PTR_ERR(crtc_state); - } - - return 0; -} diff --git a/drivers/gpu/drm/i915/display/intel_atomic.h b/drivers/gpu/drm/i915/display/intel_atomic.h index 11146292b06f..285de07011dc 100644 --- a/drivers/gpu/drm/i915/display/intel_atomic.h +++ b/drivers/gpu/drm/i915/display/intel_atomic.h @@ -56,8 +56,4 @@ int intel_atomic_setup_scalers(struct drm_i915_private *dev_priv, struct intel_crtc *intel_crtc, struct intel_crtc_state *crtc_state); -int _intel_atomic_lock_global_state(struct intel_atomic_state *state); - -int _intel_atomic_serialize_global_state(struct intel_atomic_state *state); - #endif /* __INTEL_ATOMIC_H__ */ diff --git a/drivers/gpu/drm/i915/display/intel_audio.c b/drivers/gpu/drm/i915/display/intel_audio.c index ad4aa66fd676..f7de55707746 100644 --- a/drivers/gpu/drm/i915/display/intel_audio.c +++ b/drivers/gpu/drm/i915/display/intel_audio.c @@ -958,13 +958,8 @@ static int glk_force_audio_cdclk_commit(struct intel_atomic_state *state, if (IS_ERR(cdclk_state)) return PTR_ERR(cdclk_state); - cdclk_state->force_min_cdclk_changed = true; cdclk_state->force_min_cdclk = enable ? 2 * 96000 : 0; - ret = intel_atomic_lock_global_state(&cdclk_state->base); - if (ret) - return ret; - return drm_atomic_commit(&state->base); } diff --git a/drivers/gpu/drm/i915/display/intel_bios.c b/drivers/gpu/drm/i915/display/intel_bios.c index a0a41ec5c341..4716484af62d 100644 --- a/drivers/gpu/drm/i915/display/intel_bios.c +++ b/drivers/gpu/drm/i915/display/intel_bios.c @@ -1656,6 +1656,8 @@ static enum port dvo_port_to_port(struct drm_i915_private *dev_priv, [PORT_E] = { DVO_PORT_HDMIE, DVO_PORT_DPE, DVO_PORT_CRT }, [PORT_F] = { DVO_PORT_HDMIF, DVO_PORT_DPF, -1 }, [PORT_G] = { DVO_PORT_HDMIG, DVO_PORT_DPG, -1 }, + [PORT_H] = { DVO_PORT_HDMIH, DVO_PORT_DPH, -1 }, + [PORT_I] = { DVO_PORT_HDMII, DVO_PORT_DPI, -1 }, }; /* * Bspec lists the ports as A, B, C, D - however internally in our @@ -2133,7 +2135,7 @@ void intel_bios_init(struct drm_i915_private *dev_priv) INIT_LIST_HEAD(&dev_priv->vbt.display_devices); - if (!HAS_DISPLAY(dev_priv) || !INTEL_DISPLAY_ENABLED(dev_priv)) { + if (!HAS_DISPLAY(dev_priv)) { drm_dbg_kms(&dev_priv->drm, "Skipping VBT init due to disabled display.\n"); return; @@ -2650,6 +2652,12 @@ enum aux_ch intel_bios_port_aux_ch(struct drm_i915_private *dev_priv, case DP_AUX_G: aux_ch = AUX_CH_G; break; + case DP_AUX_H: + aux_ch = AUX_CH_H; + break; + case DP_AUX_I: + aux_ch = AUX_CH_I; + break; default: MISSING_CASE(info->alternate_aux_channel); aux_ch = AUX_CH_A; diff --git a/drivers/gpu/drm/i915/display/intel_cdclk.c b/drivers/gpu/drm/i915/display/intel_cdclk.c index 577c4441f32d..cb93f6cf6d37 100644 --- a/drivers/gpu/drm/i915/display/intel_cdclk.c +++ b/drivers/gpu/drm/i915/display/intel_cdclk.c @@ -2426,7 +2426,6 @@ static struct intel_global_state *intel_cdclk_duplicate_state(struct intel_globa if (!cdclk_state) return NULL; - cdclk_state->force_min_cdclk_changed = false; cdclk_state->pipe = INVALID_PIPE; return &cdclk_state->base; @@ -2501,6 +2500,7 @@ int intel_modeset_calc_cdclk(struct intel_atomic_state *state) if (ret) return ret; } else if (old_cdclk_state->active_pipes != new_cdclk_state->active_pipes || + old_cdclk_state->force_min_cdclk != new_cdclk_state->force_min_cdclk || intel_cdclk_changed(&old_cdclk_state->logical, &new_cdclk_state->logical)) { ret = intel_atomic_lock_global_state(&new_cdclk_state->base); diff --git a/drivers/gpu/drm/i915/display/intel_cdclk.h b/drivers/gpu/drm/i915/display/intel_cdclk.h index 6b31fde4be16..b34eb00fb327 100644 --- a/drivers/gpu/drm/i915/display/intel_cdclk.h +++ b/drivers/gpu/drm/i915/display/intel_cdclk.h @@ -49,7 +49,6 @@ struct intel_cdclk_state { /* forced minimum cdclk for glk+ audio w/a */ int force_min_cdclk; - bool force_min_cdclk_changed; /* bitmask of active pipes */ u8 active_pipes; diff --git a/drivers/gpu/drm/i915/display/intel_crt.c b/drivers/gpu/drm/i915/display/intel_crt.c index 5b4510ce5693..4934edd51cb0 100644 --- a/drivers/gpu/drm/i915/display/intel_crt.c +++ b/drivers/gpu/drm/i915/display/intel_crt.c @@ -833,6 +833,9 @@ intel_crt_detect(struct drm_connector *connector, connector->base.id, connector->name, force); + if (!INTEL_DISPLAY_ENABLED(dev_priv)) + return connector_status_disconnected; + if (dev_priv->params.load_detect_test) { wakeref = intel_display_power_get(dev_priv, intel_encoder->power_domain); diff --git a/drivers/gpu/drm/i915/display/intel_ddi.c b/drivers/gpu/drm/i915/display/intel_ddi.c index 19ac6b2a664c..cdcb7b1034ae 100644 --- a/drivers/gpu/drm/i915/display/intel_ddi.c +++ b/drivers/gpu/drm/i915/display/intel_ddi.c @@ -572,13 +572,13 @@ static const struct cnl_ddi_buf_trans ehl_combo_phy_ddi_translations_dp[] = { /* NT mV Trans mV db */ { 0xA, 0x33, 0x3F, 0x00, 0x00 }, /* 350 350 0.0 */ { 0xA, 0x47, 0x36, 0x00, 0x09 }, /* 350 500 3.1 */ - { 0xC, 0x64, 0x30, 0x00, 0x0F }, /* 350 700 6.0 */ - { 0x6, 0x7F, 0x2C, 0x00, 0x13 }, /* 350 900 8.2 */ + { 0xC, 0x64, 0x34, 0x00, 0x0B }, /* 350 700 6.0 */ + { 0x6, 0x7F, 0x30, 0x00, 0x0F }, /* 350 900 8.2 */ { 0xA, 0x46, 0x3F, 0x00, 0x00 }, /* 500 500 0.0 */ - { 0xC, 0x64, 0x36, 0x00, 0x09 }, /* 500 700 2.9 */ - { 0x6, 0x7F, 0x30, 0x00, 0x0F }, /* 500 900 5.1 */ + { 0xC, 0x64, 0x38, 0x00, 0x07 }, /* 500 700 2.9 */ + { 0x6, 0x7F, 0x32, 0x00, 0x0D }, /* 500 900 5.1 */ { 0xC, 0x61, 0x3F, 0x00, 0x00 }, /* 650 700 0.6 */ - { 0x6, 0x7F, 0x37, 0x00, 0x08 }, /* 600 900 3.5 */ + { 0x6, 0x7F, 0x38, 0x00, 0x07 }, /* 600 900 3.5 */ { 0x6, 0x7F, 0x3F, 0x00, 0x00 }, /* 900 900 0.0 */ }; @@ -1074,12 +1074,28 @@ static const struct cnl_ddi_buf_trans * ehl_get_combo_buf_trans(struct intel_encoder *encoder, int type, int rate, int *n_entries) { - if (type != INTEL_OUTPUT_HDMI && type != INTEL_OUTPUT_EDP) { + struct drm_i915_private *dev_priv = to_i915(encoder->base.dev); + + switch (type) { + case INTEL_OUTPUT_HDMI: + *n_entries = ARRAY_SIZE(icl_combo_phy_ddi_translations_hdmi); + return icl_combo_phy_ddi_translations_hdmi; + case INTEL_OUTPUT_EDP: + if (dev_priv->vbt.edp.low_vswing) { + if (rate > 540000) { + *n_entries = ARRAY_SIZE(icl_combo_phy_ddi_translations_edp_hbr3); + return icl_combo_phy_ddi_translations_edp_hbr3; + } else { + *n_entries = ARRAY_SIZE(icl_combo_phy_ddi_translations_edp_hbr2); + return icl_combo_phy_ddi_translations_edp_hbr2; + } + } + /* fall through */ + default: + /* All combo DP and eDP ports that do not support low_vswing */ *n_entries = ARRAY_SIZE(ehl_combo_phy_ddi_translations_dp); return ehl_combo_phy_ddi_translations_dp; } - - return icl_get_combo_buf_trans(encoder, type, rate, n_entries); } static const struct cnl_ddi_buf_trans * @@ -1088,30 +1104,44 @@ tgl_get_combo_buf_trans(struct intel_encoder *encoder, int type, int rate, { struct drm_i915_private *dev_priv = to_i915(encoder->base.dev); - if (type == INTEL_OUTPUT_EDP && dev_priv->vbt.edp.hobl) { - struct intel_dp *intel_dp = enc_to_intel_dp(encoder); - - if (!intel_dp->hobl_failed && rate <= 540000) { - /* Same table applies to TGL, RKL and DG1 */ - *n_entries = ARRAY_SIZE(tgl_combo_phy_ddi_translations_edp_hbr2_hobl); - return tgl_combo_phy_ddi_translations_edp_hbr2_hobl; + switch (type) { + case INTEL_OUTPUT_HDMI: + *n_entries = ARRAY_SIZE(icl_combo_phy_ddi_translations_hdmi); + return icl_combo_phy_ddi_translations_hdmi; + case INTEL_OUTPUT_EDP: + if (dev_priv->vbt.edp.hobl) { + struct intel_dp *intel_dp = enc_to_intel_dp(encoder); + + if (!intel_dp->hobl_failed && rate <= 540000) { + /* Same table applies to TGL, RKL and DG1 */ + *n_entries = ARRAY_SIZE(tgl_combo_phy_ddi_translations_edp_hbr2_hobl); + return tgl_combo_phy_ddi_translations_edp_hbr2_hobl; + } } - } - if (type == INTEL_OUTPUT_HDMI || type == INTEL_OUTPUT_EDP) { - return icl_get_combo_buf_trans(encoder, type, rate, n_entries); - } else if (rate > 270000) { - if (IS_TGL_U(dev_priv) || IS_TGL_Y(dev_priv)) { - *n_entries = ARRAY_SIZE(tgl_uy_combo_phy_ddi_translations_dp_hbr2); - return tgl_uy_combo_phy_ddi_translations_dp_hbr2; + if (rate > 540000) { + *n_entries = ARRAY_SIZE(icl_combo_phy_ddi_translations_edp_hbr3); + return icl_combo_phy_ddi_translations_edp_hbr3; + } else if (dev_priv->vbt.edp.low_vswing) { + *n_entries = ARRAY_SIZE(icl_combo_phy_ddi_translations_edp_hbr2); + return icl_combo_phy_ddi_translations_edp_hbr2; + } + /* fall through */ + default: + /* All combo DP and eDP ports that do not support low_vswing */ + if (rate > 270000) { + if (IS_TGL_U(dev_priv) || IS_TGL_Y(dev_priv)) { + *n_entries = ARRAY_SIZE(tgl_uy_combo_phy_ddi_translations_dp_hbr2); + return tgl_uy_combo_phy_ddi_translations_dp_hbr2; + } + + *n_entries = ARRAY_SIZE(tgl_combo_phy_ddi_translations_dp_hbr2); + return tgl_combo_phy_ddi_translations_dp_hbr2; } - *n_entries = ARRAY_SIZE(tgl_combo_phy_ddi_translations_dp_hbr2); - return tgl_combo_phy_ddi_translations_dp_hbr2; + *n_entries = ARRAY_SIZE(tgl_combo_phy_ddi_translations_dp_hbr); + return tgl_combo_phy_ddi_translations_dp_hbr; } - - *n_entries = ARRAY_SIZE(tgl_combo_phy_ddi_translations_dp_hbr); - return tgl_combo_phy_ddi_translations_dp_hbr; } static const struct tgl_dkl_phy_ddi_buf_trans * @@ -1791,6 +1821,8 @@ void intel_ddi_disable_transcoder_func(const struct intel_crtc_state *crtc_state ctl = intel_de_read(dev_priv, TRANS_DDI_FUNC_CTL(cpu_transcoder)); + drm_WARN_ON(crtc->base.dev, ctl & TRANS_DDI_HDCP_SIGNALLING); + ctl &= ~TRANS_DDI_FUNC_ENABLE; if (IS_GEN_RANGE(dev_priv, 8, 10)) @@ -1818,12 +1850,12 @@ void intel_ddi_disable_transcoder_func(const struct intel_crtc_state *crtc_state } int intel_ddi_toggle_hdcp_signalling(struct intel_encoder *intel_encoder, + enum transcoder cpu_transcoder, bool enable) { struct drm_device *dev = intel_encoder->base.dev; struct drm_i915_private *dev_priv = to_i915(dev); intel_wakeref_t wakeref; - enum pipe pipe = 0; int ret = 0; u32 tmp; @@ -1832,19 +1864,12 @@ int intel_ddi_toggle_hdcp_signalling(struct intel_encoder *intel_encoder, if (drm_WARN_ON(dev, !wakeref)) return -ENXIO; - if (drm_WARN_ON(dev, - !intel_encoder->get_hw_state(intel_encoder, &pipe))) { - ret = -EIO; - goto out; - } - - tmp = intel_de_read(dev_priv, TRANS_DDI_FUNC_CTL(pipe)); + tmp = intel_de_read(dev_priv, TRANS_DDI_FUNC_CTL(cpu_transcoder)); if (enable) tmp |= TRANS_DDI_HDCP_SIGNALLING; else tmp &= ~TRANS_DDI_HDCP_SIGNALLING; - intel_de_write(dev_priv, TRANS_DDI_FUNC_CTL(pipe), tmp); -out: + intel_de_write(dev_priv, TRANS_DDI_FUNC_CTL(cpu_transcoder), tmp); intel_display_power_put(dev_priv, intel_encoder->power_domain, wakeref); return ret; } @@ -2717,7 +2742,7 @@ tgl_dkl_phy_ddi_vswing_sequence(struct intel_encoder *encoder, int link_clock, u32 n_entries, val, ln, dpcnt_mask, dpcnt_val; int rate = 0; - if (type == INTEL_OUTPUT_HDMI) { + if (type != INTEL_OUTPUT_HDMI) { struct intel_dp *intel_dp = enc_to_intel_dp(encoder); rate = intel_dp->link_rate; @@ -3445,6 +3470,7 @@ static void hsw_ddi_pre_enable_dp(struct intel_atomic_state *state, intel_ddi_init_dp_buf_reg(encoder); if (!is_mst) intel_dp_sink_dpms(intel_dp, DRM_MODE_DPMS_ON); + intel_dp_configure_protocol_converter(intel_dp); intel_dp_sink_set_decompression_state(intel_dp, crtc_state, true); intel_dp_sink_set_fec_ready(intel_dp, crtc_state); @@ -3556,19 +3582,17 @@ static void intel_ddi_pre_enable(struct intel_atomic_state *state, intel_ddi_pre_enable_hdmi(state, encoder, crtc_state, conn_state); } else { - struct intel_lspcon *lspcon = - enc_to_intel_lspcon(encoder); + struct intel_digital_port *dig_port = enc_to_dig_port(encoder); intel_ddi_pre_enable_dp(state, encoder, crtc_state, conn_state); - if (lspcon->active) { - struct intel_digital_port *dig_port = - enc_to_dig_port(encoder); + /* FIXME precompute everything properly */ + /* FIXME how do we turn infoframes off again? */ + if (dig_port->lspcon.active && dig_port->dp.has_hdmi_sink) dig_port->set_infoframes(encoder, crtc_state->has_infoframe, crtc_state, conn_state); - } } } @@ -4012,18 +4036,19 @@ static void intel_ddi_update_pipe_dp(struct intel_atomic_state *state, intel_psr_update(intel_dp, crtc_state, conn_state); intel_dp_set_infoframes(encoder, true, crtc_state, conn_state); - intel_edp_drrs_enable(intel_dp, crtc_state); + intel_edp_drrs_update(intel_dp, crtc_state); intel_panel_update_backlight(state, encoder, crtc_state, conn_state); } -static void intel_ddi_update_pipe(struct intel_atomic_state *state, - struct intel_encoder *encoder, - const struct intel_crtc_state *crtc_state, - const struct drm_connector_state *conn_state) +void intel_ddi_update_pipe(struct intel_atomic_state *state, + struct intel_encoder *encoder, + const struct intel_crtc_state *crtc_state, + const struct drm_connector_state *conn_state) { - if (!intel_crtc_has_type(crtc_state, INTEL_OUTPUT_HDMI)) + if (!intel_crtc_has_type(crtc_state, INTEL_OUTPUT_HDMI) && + !intel_encoder_is_mst(encoder)) intel_ddi_update_pipe_dp(state, encoder, crtc_state, conn_state); @@ -4949,6 +4974,57 @@ static bool hti_uses_phy(struct drm_i915_private *i915, enum phy phy) i915->hti_state & HDPORT_PHY_USED_HDMI(phy)); } +static enum hpd_pin tgl_hpd_pin(struct drm_i915_private *dev_priv, + enum port port) +{ + if (port >= PORT_D) + return HPD_PORT_TC1 + port - PORT_D; + else + return HPD_PORT_A + port - PORT_A; +} + +static enum hpd_pin rkl_hpd_pin(struct drm_i915_private *dev_priv, + enum port port) +{ + if (HAS_PCH_TGP(dev_priv)) + return tgl_hpd_pin(dev_priv, port); + + if (port >= PORT_D) + return HPD_PORT_C + port - PORT_D; + else + return HPD_PORT_A + port - PORT_A; +} + +static enum hpd_pin icl_hpd_pin(struct drm_i915_private *dev_priv, + enum port port) +{ + if (port >= PORT_C) + return HPD_PORT_TC1 + port - PORT_C; + else + return HPD_PORT_A + port - PORT_A; +} + +static enum hpd_pin ehl_hpd_pin(struct drm_i915_private *dev_priv, + enum port port) +{ + if (port == PORT_D) + return HPD_PORT_A; + + if (HAS_PCH_MCC(dev_priv)) + return icl_hpd_pin(dev_priv, port); + + return HPD_PORT_A + port - PORT_A; +} + +static enum hpd_pin cnl_hpd_pin(struct drm_i915_private *dev_priv, + enum port port) +{ + if (port == PORT_F) + return HPD_PORT_E; + + return HPD_PORT_A + port - PORT_A; +} + void intel_ddi_init(struct drm_i915_private *dev_priv, enum port port) { struct intel_digital_port *dig_port; @@ -5001,6 +5077,9 @@ void intel_ddi_init(struct drm_i915_private *dev_priv, enum port port) drm_encoder_init(&dev_priv->drm, &encoder->base, &intel_ddi_funcs, DRM_MODE_ENCODER_TMDS, "DDI %c", port_name(port)); + mutex_init(&dig_port->hdcp_mutex); + dig_port->num_hdcp_streams = 0; + encoder->hotplug = intel_ddi_hotplug; encoder->compute_output_type = intel_ddi_compute_output_type; encoder->compute_config = intel_ddi_compute_config; @@ -5022,6 +5101,19 @@ void intel_ddi_init(struct drm_i915_private *dev_priv, enum port port) encoder->cloneable = 0; encoder->pipe_mask = ~0; + if (IS_ROCKETLAKE(dev_priv)) + encoder->hpd_pin = rkl_hpd_pin(dev_priv, port); + else if (INTEL_GEN(dev_priv) >= 12) + encoder->hpd_pin = tgl_hpd_pin(dev_priv, port); + else if (IS_ELKHARTLAKE(dev_priv)) + encoder->hpd_pin = ehl_hpd_pin(dev_priv, port); + else if (IS_GEN(dev_priv, 11)) + encoder->hpd_pin = icl_hpd_pin(dev_priv, port); + else if (IS_GEN(dev_priv, 10)) + encoder->hpd_pin = cnl_hpd_pin(dev_priv, port); + else + encoder->hpd_pin = intel_hpd_pin_default(dev_priv, port); + if (INTEL_GEN(dev_priv) >= 11) dig_port->saved_port_bits = intel_de_read(dev_priv, DDI_BUF_CTL(port)) diff --git a/drivers/gpu/drm/i915/display/intel_ddi.h b/drivers/gpu/drm/i915/display/intel_ddi.h index 077e9dbbe367..f5fb62fc9400 100644 --- a/drivers/gpu/drm/i915/display/intel_ddi.h +++ b/drivers/gpu/drm/i915/display/intel_ddi.h @@ -16,6 +16,7 @@ struct intel_crtc_state; struct intel_dp; struct intel_dpll_hw_state; struct intel_encoder; +enum transcoder; void intel_ddi_fdi_post_disable(struct intel_atomic_state *state, struct intel_encoder *intel_encoder, @@ -43,6 +44,7 @@ void intel_ddi_compute_min_voltage_level(struct drm_i915_private *dev_priv, u32 bxt_signal_levels(struct intel_dp *intel_dp); u32 ddi_signal_levels(struct intel_dp *intel_dp); int intel_ddi_toggle_hdcp_signalling(struct intel_encoder *intel_encoder, + enum transcoder cpu_transcoder, bool enable); void icl_sanitize_encoder_pll_mapping(struct intel_encoder *encoder); diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c index 345eceec24fe..31337d2a2cde 100644 --- a/drivers/gpu/drm/i915/display/intel_display.c +++ b/drivers/gpu/drm/i915/display/intel_display.c @@ -67,6 +67,7 @@ #include "intel_bw.h" #include "intel_cdclk.h" #include "intel_color.h" +#include "intel_csr.h" #include "intel_display_types.h" #include "intel_dp_link_training.h" #include "intel_fbc.h" @@ -3433,6 +3434,14 @@ initial_plane_vma(struct drm_i915_private *i915, if (IS_ERR(obj)) return NULL; + /* + * Mark it WT ahead of time to avoid changing the + * cache_level during fbdev initialization. The + * unbind there would get stuck waiting for rcu. + */ + i915_gem_object_set_cache_coherency(obj, HAS_WT(i915) ? + I915_CACHE_WT : I915_CACHE_NONE); + switch (plane_config->tiling) { case I915_TILING_NONE: break; @@ -4092,8 +4101,7 @@ static int skl_check_ccs_aux_surface(struct intel_plane_state *plane_state) int skl_check_plane_surface(struct intel_plane_state *plane_state) { const struct drm_framebuffer *fb = plane_state->hw.fb; - int ret; - bool needs_aux = false; + int ret, i; ret = intel_plane_compute_gtt(plane_state); if (ret) @@ -4107,7 +4115,6 @@ int skl_check_plane_surface(struct intel_plane_state *plane_state) * it. */ if (is_ccs_modifier(fb->modifier)) { - needs_aux = true; ret = skl_check_ccs_aux_surface(plane_state); if (ret) return ret; @@ -4115,20 +4122,15 @@ int skl_check_plane_surface(struct intel_plane_state *plane_state) if (intel_format_info_is_yuv_semiplanar(fb->format, fb->modifier)) { - needs_aux = true; ret = skl_check_nv12_aux_surface(plane_state); if (ret) return ret; } - if (!needs_aux) { - int i; - - for (i = 1; i < fb->format->num_planes; i++) { - plane_state->color_plane[i].offset = ~0xfff; - plane_state->color_plane[i].x = 0; - plane_state->color_plane[i].y = 0; - } + for (i = fb->format->num_planes; i < ARRAY_SIZE(plane_state->color_plane); i++) { + plane_state->color_plane[i].offset = ~0xfff; + plane_state->color_plane[i].x = 0; + plane_state->color_plane[i].y = 0; } ret = skl_check_main_surface(plane_state); @@ -7331,6 +7333,10 @@ enum intel_display_power_domain intel_port_to_power_domain(enum port port) return POWER_DOMAIN_PORT_DDI_F_LANES; case PORT_G: return POWER_DOMAIN_PORT_DDI_G_LANES; + case PORT_H: + return POWER_DOMAIN_PORT_DDI_H_LANES; + case PORT_I: + return POWER_DOMAIN_PORT_DDI_I_LANES; default: MISSING_CASE(port); return POWER_DOMAIN_PORT_OTHER; @@ -7356,6 +7362,10 @@ intel_aux_power_domain(struct intel_digital_port *dig_port) return POWER_DOMAIN_AUX_F_TBT; case AUX_CH_G: return POWER_DOMAIN_AUX_G_TBT; + case AUX_CH_H: + return POWER_DOMAIN_AUX_H_TBT; + case AUX_CH_I: + return POWER_DOMAIN_AUX_I_TBT; default: MISSING_CASE(dig_port->aux_ch); return POWER_DOMAIN_AUX_C_TBT; @@ -7387,6 +7397,10 @@ intel_legacy_aux_to_power_domain(enum aux_ch aux_ch) return POWER_DOMAIN_AUX_F; case AUX_CH_G: return POWER_DOMAIN_AUX_G; + case AUX_CH_H: + return POWER_DOMAIN_AUX_H; + case AUX_CH_I: + return POWER_DOMAIN_AUX_I; default: MISSING_CASE(aux_ch); return POWER_DOMAIN_AUX_A; @@ -8155,7 +8169,7 @@ static void compute_m_n(unsigned int m, unsigned int n, * which the devices expect also in synchronous clock mode. */ if (constant_n) - *ret_n = 0x8000; + *ret_n = DP_LINK_CONSTANT_N_VALUE; else *ret_n = min_t(unsigned int, roundup_pow_of_two(n), DATA_LINK_N_MAX); @@ -10622,6 +10636,10 @@ skl_get_initial_plane_config(struct intel_crtc *crtc, val & PLANE_CTL_FLIP_HORIZONTAL) plane_config->rotation |= DRM_MODE_REFLECT_X; + /* 90/270 degree rotation would require extra work */ + if (drm_rotation_90_or_270(plane_config->rotation)) + goto error; + base = intel_de_read(dev_priv, PLANE_SURF(pipe, plane_id)) & 0xfffff000; plane_config->base = base; @@ -14291,7 +14309,6 @@ verify_crtc_state(struct intel_crtc *crtc, struct intel_encoder *encoder; struct intel_crtc_state *pipe_config = old_crtc_state; struct drm_atomic_state *state = old_crtc_state->uapi.state; - bool active; __drm_atomic_helper_crtc_destroy_state(&old_crtc_state->uapi); intel_crtc_free_hw_state(old_crtc_state); @@ -14301,16 +14318,19 @@ verify_crtc_state(struct intel_crtc *crtc, drm_dbg_kms(&dev_priv->drm, "[CRTC:%d:%s]\n", crtc->base.base.id, crtc->base.name); - active = dev_priv->display.get_pipe_config(crtc, pipe_config); + pipe_config->hw.enable = new_crtc_state->hw.enable; + + pipe_config->hw.active = + dev_priv->display.get_pipe_config(crtc, pipe_config); /* we keep both pipes enabled on 830 */ - if (IS_I830(dev_priv)) - active = new_crtc_state->hw.active; + if (IS_I830(dev_priv) && pipe_config->hw.active) + pipe_config->hw.active = new_crtc_state->hw.active; - I915_STATE_WARN(new_crtc_state->hw.active != active, + I915_STATE_WARN(new_crtc_state->hw.active != pipe_config->hw.active, "crtc active state doesn't match with hw state " "(expected %i, found %i)\n", - new_crtc_state->hw.active, active); + new_crtc_state->hw.active, pipe_config->hw.active); I915_STATE_WARN(crtc->active != new_crtc_state->hw.active, "transitional active state does not match atomic hw state " @@ -14319,6 +14339,7 @@ verify_crtc_state(struct intel_crtc *crtc, for_each_encoder_on_crtc(dev, &crtc->base, encoder) { enum pipe pipe; + bool active; active = encoder->get_hw_state(encoder, &pipe); I915_STATE_WARN(active != new_crtc_state->hw.active, @@ -14630,16 +14651,8 @@ u8 intel_calc_active_pipes(struct intel_atomic_state *state, static int intel_modeset_checks(struct intel_atomic_state *state) { struct drm_i915_private *dev_priv = to_i915(state->base.dev); - int ret; state->modeset = true; - state->active_pipes = intel_calc_active_pipes(state, dev_priv->active_pipes); - - if (state->active_pipes != dev_priv->active_pipes) { - ret = _intel_atomic_lock_global_state(state); - if (ret) - return ret; - } if (IS_HASWELL(dev_priv)) return hsw_mode_set_planes_workaround(state); @@ -14783,7 +14796,8 @@ static int intel_atomic_check_cdclk(struct intel_atomic_state *state, bool *need_cdclk_calc) { struct drm_i915_private *dev_priv = to_i915(state->base.dev); - struct intel_cdclk_state *new_cdclk_state; + const struct intel_cdclk_state *old_cdclk_state; + const struct intel_cdclk_state *new_cdclk_state; struct intel_plane_state *plane_state; struct intel_bw_state *new_bw_state; struct intel_plane *plane; @@ -14802,9 +14816,11 @@ static int intel_atomic_check_cdclk(struct intel_atomic_state *state, return ret; } + old_cdclk_state = intel_atomic_get_old_cdclk_state(state); new_cdclk_state = intel_atomic_get_new_cdclk_state(state); - if (new_cdclk_state && new_cdclk_state->force_min_cdclk_changed) + if (new_cdclk_state && + old_cdclk_state->force_min_cdclk != new_cdclk_state->force_min_cdclk) *need_cdclk_calc = true; ret = dev_priv->display.bw_calc_min_cdclk(state); @@ -15751,14 +15767,6 @@ static void intel_atomic_track_fbs(struct intel_atomic_state *state) plane->frontbuffer_bit); } -static void assert_global_state_locked(struct drm_i915_private *dev_priv) -{ - struct intel_crtc *crtc; - - for_each_intel_crtc(&dev_priv->drm, crtc) - drm_modeset_lock_assert_held(&crtc->base.mutex); -} - static int intel_atomic_commit(struct drm_device *dev, struct drm_atomic_state *_state, bool nonblock) @@ -15834,12 +15842,6 @@ static int intel_atomic_commit(struct drm_device *dev, intel_shared_dpll_swap_state(state); intel_atomic_track_fbs(state); - if (state->global_state_changed) { - assert_global_state_locked(dev_priv); - - dev_priv->active_pipes = state->active_pipes; - } - drm_atomic_state_get(&state->base); INIT_WORK(&state->base.commit_work, intel_atomic_commit_work); @@ -16886,7 +16888,7 @@ static void intel_setup_outputs(struct drm_i915_private *dev_priv) intel_pps_init(dev_priv); - if (!HAS_DISPLAY(dev_priv) || !INTEL_DISPLAY_ENABLED(dev_priv)) + if (!HAS_DISPLAY(dev_priv)) return; if (IS_ROCKETLAKE(dev_priv)) { @@ -17872,6 +17874,27 @@ int intel_modeset_init_noirq(struct drm_i915_private *i915) { int ret; + if (i915_inject_probe_failure(i915)) + return -ENODEV; + + if (HAS_DISPLAY(i915)) { + ret = drm_vblank_init(&i915->drm, + INTEL_NUM_PIPES(i915)); + if (ret) + return ret; + } + + intel_bios_init(i915); + + ret = intel_vga_register(i915); + if (ret) + goto cleanup_bios; + + /* FIXME: completely on the wrong abstraction layer */ + intel_power_domains_init_hw(i915, false); + + intel_csr_ucode_init(i915); + i915->modeset_wq = alloc_ordered_workqueue("i915_modeset", 0); i915->flip_wq = alloc_workqueue("i915_flip", WQ_HIGHPRI | WQ_UNBOUND, WQ_UNBOUND_MAX_ACTIVE); @@ -17880,15 +17903,15 @@ int intel_modeset_init_noirq(struct drm_i915_private *i915) ret = intel_cdclk_init(i915); if (ret) - return ret; + goto cleanup_vga_client_pw_domain_csr; ret = intel_dbuf_init(i915); if (ret) - return ret; + goto cleanup_vga_client_pw_domain_csr; ret = intel_bw_init(i915); if (ret) - return ret; + goto cleanup_vga_client_pw_domain_csr; init_llist_head(&i915->atomic_helper.free_list); INIT_WORK(&i915->atomic_helper.free_work, @@ -17899,10 +17922,19 @@ int intel_modeset_init_noirq(struct drm_i915_private *i915) intel_fbc_init(i915); return 0; + +cleanup_vga_client_pw_domain_csr: + intel_csr_ucode_fini(i915); + intel_power_domains_driver_remove(i915); + intel_vga_unregister(i915); +cleanup_bios: + intel_bios_driver_remove(i915); + + return ret; } -/* part #2: call after irq install */ -int intel_modeset_init(struct drm_i915_private *i915) +/* part #2: call after irq install, but before gem init */ +int intel_modeset_init_nogem(struct drm_i915_private *i915) { struct drm_device *dev = &i915->drm; enum pipe pipe; @@ -17919,7 +17951,7 @@ int intel_modeset_init(struct drm_i915_private *i915) INTEL_NUM_PIPES(i915), INTEL_NUM_PIPES(i915) > 1 ? "s" : ""); - if (HAS_DISPLAY(i915) && INTEL_DISPLAY_ENABLED(i915)) { + if (HAS_DISPLAY(i915)) { for_each_pipe(i915, pipe) { ret = intel_crtc_init(i915, pipe); if (ret) { @@ -18001,6 +18033,30 @@ int intel_modeset_init(struct drm_i915_private *i915) return 0; } +/* part #3: call after gem init */ +int intel_modeset_init(struct drm_i915_private *i915) +{ + int ret; + + intel_overlay_setup(i915); + + if (!HAS_DISPLAY(i915)) + return 0; + + ret = intel_fbdev_init(&i915->drm); + if (ret) + return ret; + + /* Only enable hotplug handling once the fbdev is fully set up. */ + intel_hpd_init(i915); + + intel_init_ipc(i915); + + intel_psr_set_force_mode_changed(i915->psr.dp); + + return 0; +} + void i830_enable_pipe(struct drm_i915_private *dev_priv, enum pipe pipe) { struct intel_crtc *crtc = intel_get_crtc_for_pipe(dev_priv, pipe); @@ -18885,6 +18941,18 @@ void intel_modeset_driver_remove_noirq(struct drm_i915_private *i915) intel_fbc_cleanup_cfb(i915); } +/* part #3: call after gem init */ +void intel_modeset_driver_remove_nogem(struct drm_i915_private *i915) +{ + intel_csr_ucode_fini(i915); + + intel_power_domains_driver_remove(i915); + + intel_vga_unregister(i915); + + intel_bios_driver_remove(i915); +} + #if IS_ENABLED(CONFIG_DRM_I915_CAPTURE_ERROR) struct intel_display_error_state { @@ -18945,7 +19013,7 @@ intel_display_capture_error_state(struct drm_i915_private *dev_priv) BUILD_BUG_ON(ARRAY_SIZE(transcoders) != ARRAY_SIZE(error->transcoder)); - if (!HAS_DISPLAY(dev_priv) || !INTEL_DISPLAY_ENABLED(dev_priv)) + if (!HAS_DISPLAY(dev_priv)) return NULL; error = kzalloc(sizeof(*error), GFP_ATOMIC); diff --git a/drivers/gpu/drm/i915/display/intel_display.h b/drivers/gpu/drm/i915/display/intel_display.h index e890c8fb779b..d10b7c8cde3f 100644 --- a/drivers/gpu/drm/i915/display/intel_display.h +++ b/drivers/gpu/drm/i915/display/intel_display.h @@ -272,8 +272,6 @@ enum dpio_phy { DPIO_PHY2, }; -#define I915_NUM_PHYS_VLV 2 - enum aux_ch { AUX_CH_A, AUX_CH_B, @@ -282,6 +280,8 @@ enum aux_ch { AUX_CH_E, /* ICL+ */ AUX_CH_F, AUX_CH_G, + AUX_CH_H, + AUX_CH_I, }; #define aux_ch_name(a) ((a) + 'A') @@ -629,9 +629,11 @@ intel_format_info_is_yuv_semiplanar(const struct drm_format_info *info, /* modesetting */ void intel_modeset_init_hw(struct drm_i915_private *i915); int intel_modeset_init_noirq(struct drm_i915_private *i915); +int intel_modeset_init_nogem(struct drm_i915_private *i915); int intel_modeset_init(struct drm_i915_private *i915); void intel_modeset_driver_remove(struct drm_i915_private *i915); void intel_modeset_driver_remove_noirq(struct drm_i915_private *i915); +void intel_modeset_driver_remove_nogem(struct drm_i915_private *i915); void intel_display_resume(struct drm_device *dev); void intel_init_pch_refclk(struct drm_i915_private *dev_priv); diff --git a/drivers/gpu/drm/i915/display/intel_display_debugfs.c b/drivers/gpu/drm/i915/display/intel_display_debugfs.c index f549381048b3..0bf31f9a8af5 100644 --- a/drivers/gpu/drm/i915/display/intel_display_debugfs.c +++ b/drivers/gpu/drm/i915/display/intel_display_debugfs.c @@ -601,6 +601,11 @@ static void intel_hdcp_info(struct seq_file *m, { bool hdcp_cap, hdcp2_cap; + if (!intel_connector->hdcp.shim) { + seq_puts(m, "No Connector Support"); + goto out; + } + hdcp_cap = intel_hdcp_capable(intel_connector); hdcp2_cap = intel_hdcp2_capable(intel_connector); @@ -612,6 +617,7 @@ static void intel_hdcp_info(struct seq_file *m, if (!hdcp_cap && !hdcp2_cap) seq_puts(m, "None"); +out: seq_puts(m, "\n"); } @@ -620,6 +626,7 @@ static void intel_dp_info(struct seq_file *m, { struct intel_encoder *intel_encoder = intel_attached_encoder(intel_connector); struct intel_dp *intel_dp = enc_to_intel_dp(intel_encoder); + const struct drm_property_blob *edid = intel_connector->base.edid_blob_ptr; seq_printf(m, "\tDPCD rev: %x\n", intel_dp->dpcd[DP_DPCD_REV]); seq_printf(m, "\taudio support: %s\n", yesno(intel_dp->has_audio)); @@ -627,11 +634,7 @@ static void intel_dp_info(struct seq_file *m, intel_panel_info(m, &intel_connector->panel); drm_dp_downstream_debug(m, intel_dp->dpcd, intel_dp->downstream_ports, - &intel_dp->aux); - if (intel_connector->hdcp.shim) { - seq_puts(m, "\tHDCP version: "); - intel_hdcp_info(m, intel_connector); - } + edid ? edid->data : NULL, &intel_dp->aux); } static void intel_dp_mst_info(struct seq_file *m, @@ -649,10 +652,6 @@ static void intel_hdmi_info(struct seq_file *m, struct intel_hdmi *intel_hdmi = enc_to_intel_hdmi(intel_encoder); seq_printf(m, "\taudio support: %s\n", yesno(intel_hdmi->has_audio)); - if (intel_connector->hdcp.shim) { - seq_puts(m, "\tHDCP version: "); - intel_hdcp_info(m, intel_connector); - } } static void intel_lvds_info(struct seq_file *m, @@ -708,6 +707,9 @@ static void intel_connector_info(struct seq_file *m, break; } + seq_puts(m, "\tHDCP version: "); + intel_hdcp_info(m, intel_connector); + seq_printf(m, "\tmodes:\n"); list_for_each_entry(mode, &connector->modes, head) intel_seq_print_mode(m, 2, mode); @@ -1069,10 +1071,18 @@ static void drrs_status_per_crtc(struct seq_file *m, drm_connector_list_iter_begin(dev, &conn_iter); drm_for_each_connector_iter(connector, &conn_iter) { + bool supported = false; + if (connector->state->crtc != &intel_crtc->base) continue; seq_printf(m, "%s:\n", connector->name); + + if (connector->connector_type == DRM_MODE_CONNECTOR_eDP && + drrs->type == SEAMLESS_DRRS_SUPPORT) + supported = true; + + seq_printf(m, "\tDRRS Supported: %s\n", yesno(supported)); } drm_connector_list_iter_end(&conn_iter); @@ -1083,7 +1093,7 @@ static void drrs_status_per_crtc(struct seq_file *m, mutex_lock(&drrs->mutex); /* DRRS Supported */ - seq_puts(m, "\tDRRS Supported: Yes\n"); + seq_puts(m, "\tDRRS Enabled: Yes\n"); /* disable_drrs() will make drrs->dp NULL */ if (!drrs->dp) { @@ -1118,7 +1128,7 @@ static void drrs_status_per_crtc(struct seq_file *m, mutex_unlock(&drrs->mutex); } else { /* DRRS not supported. Print the VBT parameter*/ - seq_puts(m, "\tDRRS Supported : No"); + seq_puts(m, "\tDRRS Enabled : No"); } seq_puts(m, "\n"); } @@ -2029,10 +2039,6 @@ static int i915_hdcp_sink_capability_show(struct seq_file *m, void *data) if (connector->status != connector_status_connected) return -ENODEV; - /* HDCP is supported by connector */ - if (!intel_connector->hdcp.shim) - return -EINVAL; - seq_printf(m, "%s:%d HDCP version: ", connector->name, connector->base.id); intel_hdcp_info(m, intel_connector); diff --git a/drivers/gpu/drm/i915/display/intel_display_power.c b/drivers/gpu/drm/i915/display/intel_display_power.c index 7946c6af4b1e..7277e58b01f1 100644 --- a/drivers/gpu/drm/i915/display/intel_display_power.c +++ b/drivers/gpu/drm/i915/display/intel_display_power.c @@ -5263,7 +5263,7 @@ static void tgl_bw_buddy_init(struct drm_i915_private *dev_priv) unsigned long abox_mask = INTEL_INFO(dev_priv)->abox_mask; int config, i; - if (IS_TGL_REVID(dev_priv, TGL_REVID_A0, TGL_REVID_B0)) + if (IS_TGL_DISP_REVID(dev_priv, TGL_REVID_A0, TGL_REVID_B0)) /* Wa_1409767108: tgl */ table = wa_1409767108_buddy_page_masks; else diff --git a/drivers/gpu/drm/i915/display/intel_display_types.h b/drivers/gpu/drm/i915/display/intel_display_types.h index 9349b15afff6..3d4bf9b6a0a2 100644 --- a/drivers/gpu/drm/i915/display/intel_display_types.h +++ b/drivers/gpu/drm/i915/display/intel_display_types.h @@ -28,6 +28,7 @@ #include <linux/async.h> #include <linux/i2c.h> +#include <linux/pwm.h> #include <linux/sched/clock.h> #include <drm/drm_atomic.h> @@ -223,6 +224,7 @@ struct intel_panel { bool util_pin_active_low; /* bxt+ */ u8 controller; /* bxt+ only */ struct pwm_device *pwm; + struct pwm_state pwm_state; /* DPCD backlight */ u8 pwmgen_bit_count; @@ -314,10 +316,12 @@ struct intel_hdcp_shim { /* Enables HDCP signalling on the port */ int (*toggle_signalling)(struct intel_digital_port *dig_port, + enum transcoder cpu_transcoder, bool enable); /* Ensures the link is still protected */ - bool (*check_link)(struct intel_digital_port *dig_port); + bool (*check_link)(struct intel_digital_port *dig_port, + struct intel_connector *connector); /* Detects panel's hdcp capability. This is optional for HDMI. */ int (*hdcp_capable)(struct intel_digital_port *dig_port, @@ -479,8 +483,6 @@ struct intel_atomic_state { bool dpll_set, modeset; - u8 active_pipes; - struct intel_shared_dpll_state shared_dpll[I915_NUM_PLLS]; /* @@ -491,11 +493,6 @@ struct intel_atomic_state { bool rps_interactive; - /* - * active_pipes - */ - bool global_state_changed; - struct i915_sw_fence commit_ready; struct llist_node freed; @@ -1275,6 +1272,7 @@ struct intel_dp { u8 sink_count; bool link_mst; bool link_trained; + bool has_hdmi_sink; bool has_audio; bool reset_link_params; u8 dpcd[DP_RECEIVER_CAP_SIZE]; @@ -1376,6 +1374,14 @@ struct intel_dp { /* Displayport compliance testing */ struct intel_dp_compliance compliance; + /* Downstream facing port caps */ + struct { + int min_tmds_clock, max_tmds_clock; + int max_dotclock; + u8 max_bpc; + bool ycbcr_444_to_420; + } dfp; + /* Display stream compression testing */ bool force_dsc_en; @@ -1415,6 +1421,11 @@ struct intel_digital_port { enum phy_fia tc_phy_fia; u8 tc_phy_fia_idx; + /* protects num_hdcp_streams reference count */ + struct mutex hdcp_mutex; + /* the number of pipes using HDCP signalling out of this port */ + unsigned int num_hdcp_streams; + void (*write_infoframe)(struct intel_encoder *encoder, const struct intel_crtc_state *crtc_state, unsigned int type, @@ -1525,6 +1536,18 @@ static inline bool intel_encoder_is_dig_port(struct intel_encoder *encoder) } } +static inline bool intel_encoder_is_mst(struct intel_encoder *encoder) +{ + return encoder->type == INTEL_OUTPUT_DP_MST; +} + +static inline struct intel_dp_mst_encoder * +enc_to_mst(struct intel_encoder *encoder) +{ + return container_of(&encoder->base, struct intel_dp_mst_encoder, + base.base); +} + static inline struct intel_digital_port * enc_to_dig_port(struct intel_encoder *encoder) { @@ -1533,6 +1556,8 @@ enc_to_dig_port(struct intel_encoder *encoder) if (intel_encoder_is_dig_port(intel_encoder)) return container_of(&encoder->base, struct intel_digital_port, base.base); + else if (intel_encoder_is_mst(intel_encoder)) + return enc_to_mst(encoder)->primary; else return NULL; } @@ -1543,13 +1568,6 @@ intel_attached_dig_port(struct intel_connector *connector) return enc_to_dig_port(intel_attached_encoder(connector)); } -static inline struct intel_dp_mst_encoder * -enc_to_mst(struct intel_encoder *encoder) -{ - return container_of(&encoder->base, struct intel_dp_mst_encoder, - base.base); -} - static inline struct intel_dp *enc_to_intel_dp(struct intel_encoder *encoder) { return &enc_to_dig_port(encoder)->dp; diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c index 284b15f84592..bf1e9cf1c0f3 100644 --- a/drivers/gpu/drm/i915/display/intel_dp.c +++ b/drivers/gpu/drm/i915/display/intel_dp.c @@ -38,7 +38,6 @@ #include <drm/drm_crtc.h> #include <drm/drm_dp_helper.h> #include <drm/drm_edid.h> -#include <drm/drm_hdcp.h> #include <drm/drm_probe_helper.h> #include "i915_debugfs.h" @@ -248,29 +247,6 @@ intel_dp_max_data_rate(int max_link_clock, int max_lanes) return max_link_clock * max_lanes; } -static int -intel_dp_downstream_max_dotclock(struct intel_dp *intel_dp) -{ - struct intel_digital_port *dig_port = dp_to_dig_port(intel_dp); - struct intel_encoder *encoder = &dig_port->base; - struct drm_i915_private *dev_priv = to_i915(encoder->base.dev); - int max_dotclk = dev_priv->max_dotclk_freq; - int ds_max_dotclk; - - int type = intel_dp->downstream_ports[0] & DP_DS_PORT_TYPE_MASK; - - if (type != DP_DS_PORT_TYPE_VGA) - return max_dotclk; - - ds_max_dotclk = drm_dp_downstream_max_clock(intel_dp->dpcd, - intel_dp->downstream_ports); - - if (ds_max_dotclk != 0) - max_dotclk = min(max_dotclk, ds_max_dotclk); - - return max_dotclk; -} - static int cnl_max_source_rate(struct intel_dp *intel_dp) { struct intel_digital_port *dig_port = dp_to_dig_port(intel_dp); @@ -636,6 +612,34 @@ static bool intel_dp_hdisplay_bad(struct drm_i915_private *dev_priv, } static enum drm_mode_status +intel_dp_mode_valid_downstream(struct intel_connector *connector, + const struct drm_display_mode *mode, + int target_clock) +{ + struct intel_dp *intel_dp = intel_attached_dp(connector); + const struct drm_display_info *info = &connector->base.display_info; + int tmds_clock; + + if (intel_dp->dfp.max_dotclock && + target_clock > intel_dp->dfp.max_dotclock) + return MODE_CLOCK_HIGH; + + /* Assume 8bpc for the DP++/HDMI/DVI TMDS clock check */ + tmds_clock = target_clock; + if (drm_mode_is_420_only(info, mode)) + tmds_clock /= 2; + + if (intel_dp->dfp.min_tmds_clock && + tmds_clock < intel_dp->dfp.min_tmds_clock) + return MODE_CLOCK_LOW; + if (intel_dp->dfp.max_tmds_clock && + tmds_clock > intel_dp->dfp.max_tmds_clock) + return MODE_CLOCK_HIGH; + + return MODE_OK; +} + +static enum drm_mode_status intel_dp_mode_valid(struct drm_connector *connector, struct drm_display_mode *mode) { @@ -645,15 +649,14 @@ intel_dp_mode_valid(struct drm_connector *connector, struct drm_i915_private *dev_priv = to_i915(connector->dev); int target_clock = mode->clock; int max_rate, mode_rate, max_lanes, max_link_clock; - int max_dotclk; + int max_dotclk = dev_priv->max_dotclk_freq; u16 dsc_max_output_bpp = 0; u8 dsc_slice_count = 0; + enum drm_mode_status status; if (mode->flags & DRM_MODE_FLAG_DBLSCAN) return MODE_NO_DBLESCAN; - max_dotclk = intel_dp_downstream_max_dotclock(intel_dp); - if (intel_dp_is_edp(intel_dp) && fixed_mode) { if (mode->hdisplay > fixed_mode->hdisplay) return MODE_PANEL; @@ -709,6 +712,11 @@ intel_dp_mode_valid(struct drm_connector *connector, if (mode->flags & DRM_MODE_FLAG_DBLCLK) return MODE_H_ILLEGAL; + status = intel_dp_mode_valid_downstream(intel_connector, + mode, target_clock); + if (status != MODE_OK) + return status; + return intel_mode_valid_max_plane_size(dev_priv, mode); } @@ -1563,6 +1571,20 @@ intel_dp_aux_header(u8 txbuf[HEADER_SIZE], txbuf[3] = msg->size - 1; } +static u32 intel_dp_aux_xfer_flags(const struct drm_dp_aux_msg *msg) +{ + /* + * If we're trying to send the HDCP Aksv, we need to set a the Aksv + * select bit to inform the hardware to send the Aksv after our header + * since we can't access that data from software. + */ + if ((msg->request & ~DP_AUX_I2C_MOT) == DP_AUX_NATIVE_WRITE && + msg->address == DP_AUX_HDCP_AKSV) + return DP_AUX_CH_CTL_AUX_AKSV_SELECT; + + return 0; +} + static ssize_t intel_dp_aux_transfer(struct drm_dp_aux *aux, struct drm_dp_aux_msg *msg) { @@ -1570,6 +1592,7 @@ intel_dp_aux_transfer(struct drm_dp_aux *aux, struct drm_dp_aux_msg *msg) struct drm_i915_private *i915 = dp_to_i915(intel_dp); u8 txbuf[20], rxbuf[20]; size_t txsize, rxsize; + u32 flags = intel_dp_aux_xfer_flags(msg); int ret; intel_dp_aux_header(txbuf, msg); @@ -1590,7 +1613,7 @@ intel_dp_aux_transfer(struct drm_dp_aux *aux, struct drm_dp_aux_msg *msg) memcpy(txbuf + HEADER_SIZE, msg->buffer, msg->size); ret = intel_dp_aux_xfer(intel_dp, txbuf, txsize, - rxbuf, rxsize, 0); + rxbuf, rxsize, flags); if (ret > 0) { msg->reply = rxbuf[0] >> 4; @@ -1613,7 +1636,7 @@ intel_dp_aux_transfer(struct drm_dp_aux *aux, struct drm_dp_aux_msg *msg) return -E2BIG; ret = intel_dp_aux_xfer(intel_dp, txbuf, txsize, - rxbuf, rxsize, 0); + rxbuf, rxsize, flags); if (ret > 0) { msg->reply = rxbuf[0] >> 4; /* @@ -1954,19 +1977,72 @@ static bool intel_dp_supports_dsc(struct intel_dp *intel_dp, drm_dp_sink_supports_dsc(intel_dp->dsc_dpcd); } -static int intel_dp_compute_bpp(struct intel_dp *intel_dp, - struct intel_crtc_state *pipe_config) +static bool intel_dp_hdmi_ycbcr420(struct intel_dp *intel_dp, + const struct intel_crtc_state *crtc_state) +{ + return crtc_state->output_format == INTEL_OUTPUT_FORMAT_YCBCR420 || + (crtc_state->output_format == INTEL_OUTPUT_FORMAT_YCBCR444 && + intel_dp->dfp.ycbcr_444_to_420); +} + +static int intel_dp_hdmi_tmds_clock(struct intel_dp *intel_dp, + const struct intel_crtc_state *crtc_state, int bpc) +{ + int clock = crtc_state->hw.adjusted_mode.crtc_clock * bpc / 8; + + if (intel_dp_hdmi_ycbcr420(intel_dp, crtc_state)) + clock /= 2; + + return clock; +} + +static bool intel_dp_hdmi_tmds_clock_valid(struct intel_dp *intel_dp, + const struct intel_crtc_state *crtc_state, int bpc) +{ + int tmds_clock = intel_dp_hdmi_tmds_clock(intel_dp, crtc_state, bpc); + + if (intel_dp->dfp.min_tmds_clock && + tmds_clock < intel_dp->dfp.min_tmds_clock) + return false; + + if (intel_dp->dfp.max_tmds_clock && + tmds_clock > intel_dp->dfp.max_tmds_clock) + return false; + + return true; +} + +static bool intel_dp_hdmi_deep_color_possible(struct intel_dp *intel_dp, + const struct intel_crtc_state *crtc_state, + int bpc) +{ + + return intel_hdmi_deep_color_possible(crtc_state, bpc, + intel_dp->has_hdmi_sink, + intel_dp_hdmi_ycbcr420(intel_dp, crtc_state)) && + intel_dp_hdmi_tmds_clock_valid(intel_dp, crtc_state, bpc); +} + +static int intel_dp_max_bpp(struct intel_dp *intel_dp, + const struct intel_crtc_state *crtc_state) { struct drm_i915_private *dev_priv = dp_to_i915(intel_dp); struct intel_connector *intel_connector = intel_dp->attached_connector; int bpp, bpc; - bpp = pipe_config->pipe_bpp; - bpc = drm_dp_downstream_max_bpc(intel_dp->dpcd, intel_dp->downstream_ports); + bpc = crtc_state->pipe_bpp / 3; - if (bpc > 0) - bpp = min(bpp, 3*bpc); + if (intel_dp->dfp.max_bpc) + bpc = min_t(int, bpc, intel_dp->dfp.max_bpc); + if (intel_dp->dfp.min_tmds_clock) { + for (; bpc >= 10; bpc -= 2) { + if (intel_dp_hdmi_deep_color_possible(intel_dp, crtc_state, bpc)) + break; + } + } + + bpp = bpc * 3; if (intel_dp_is_edp(intel_dp)) { /* Get bpp from vbt only for panels that dont have bpp in edid */ if (intel_connector->base.display_info.bpc == 0 && @@ -2288,7 +2364,7 @@ intel_dp_compute_link_config(struct intel_encoder *encoder, limits.max_lane_count = intel_dp_max_lane_count(intel_dp); limits.min_bpp = intel_dp_min_bpp(pipe_config); - limits.max_bpp = intel_dp_compute_bpp(intel_dp, pipe_config); + limits.max_bpp = intel_dp_max_bpp(intel_dp, pipe_config); if (intel_dp_is_edp(intel_dp)) { /* @@ -2363,10 +2439,16 @@ intel_dp_ycbcr420_config(struct intel_dp *intel_dp, const struct drm_display_mode *adjusted_mode = &crtc_state->hw.adjusted_mode; - if (!drm_mode_is_420_only(info, adjusted_mode) || - !intel_dp_get_colorimetry_status(intel_dp) || - !connector->ycbcr_420_allowed) + if (!connector->ycbcr_420_allowed) + return 0; + + if (!drm_mode_is_420_only(info, adjusted_mode)) + return 0; + + if (intel_dp->dfp.ycbcr_444_to_420) { + crtc_state->output_format = INTEL_OUTPUT_FORMAT_YCBCR444; return 0; + } crtc_state->output_format = INTEL_OUTPUT_FORMAT_YCBCR420; @@ -2575,6 +2657,34 @@ intel_dp_compute_hdr_metadata_infoframe_sdp(struct intel_dp *intel_dp, intel_hdmi_infoframe_enable(HDMI_PACKET_TYPE_GAMUT_METADATA); } +static void +intel_dp_drrs_compute_config(struct intel_dp *intel_dp, + struct intel_crtc_state *pipe_config, + int output_bpp, bool constant_n) +{ + struct intel_connector *intel_connector = intel_dp->attached_connector; + struct drm_i915_private *dev_priv = dp_to_i915(intel_dp); + + /* + * DRRS and PSR can't be enable together, so giving preference to PSR + * as it allows more power-savings by complete shutting down display, + * so to guarantee this, intel_dp_drrs_compute_config() must be called + * after intel_psr_compute_config(). + */ + if (pipe_config->has_psr) + return; + + if (!intel_connector->panel.downclock_mode || + dev_priv->drrs.type != SEAMLESS_DRRS_SUPPORT) + return; + + pipe_config->has_drrs = true; + intel_link_compute_m_n(output_bpp, pipe_config->lane_count, + intel_connector->panel.downclock_mode->clock, + pipe_config->port_clock, &pipe_config->dp_m2_n2, + constant_n, pipe_config->fec_enable); +} + int intel_dp_compute_config(struct intel_encoder *encoder, struct intel_crtc_state *pipe_config, @@ -2605,7 +2715,6 @@ intel_dp_compute_config(struct intel_encoder *encoder, if (ret) return ret; - pipe_config->has_drrs = false; if (!intel_dp_port_has_audio(dev_priv, port)) pipe_config->has_audio = false; else if (intel_conn_state->force_audio == HDMI_AUDIO_AUTO) @@ -2657,21 +2766,12 @@ intel_dp_compute_config(struct intel_encoder *encoder, &pipe_config->dp_m_n, constant_n, pipe_config->fec_enable); - if (intel_connector->panel.downclock_mode != NULL && - dev_priv->drrs.type == SEAMLESS_DRRS_SUPPORT) { - pipe_config->has_drrs = true; - intel_link_compute_m_n(output_bpp, - pipe_config->lane_count, - intel_connector->panel.downclock_mode->clock, - pipe_config->port_clock, - &pipe_config->dp_m2_n2, - constant_n, pipe_config->fec_enable); - } - if (!HAS_DDI(dev_priv)) intel_dp_set_clock(encoder, pipe_config); intel_psr_compute_config(intel_dp, pipe_config); + intel_dp_drrs_compute_config(intel_dp, pipe_config, output_bpp, + constant_n); intel_dp_compute_vsc_sdp(intel_dp, pipe_config, conn_state); intel_dp_compute_hdr_metadata_infoframe_sdp(intel_dp, pipe_config, conn_state); @@ -3752,6 +3852,43 @@ static void intel_dp_enable_port(struct intel_dp *intel_dp, intel_de_posting_read(dev_priv, intel_dp->output_reg); } +void intel_dp_configure_protocol_converter(struct intel_dp *intel_dp) +{ + struct drm_i915_private *i915 = dp_to_i915(intel_dp); + u8 tmp; + + if (intel_dp->dpcd[DP_DPCD_REV] < 0x13) + return; + + if (!drm_dp_is_branch(intel_dp->dpcd)) + return; + + tmp = intel_dp->has_hdmi_sink ? + DP_HDMI_DVI_OUTPUT_CONFIG : 0; + + if (drm_dp_dpcd_writeb(&intel_dp->aux, + DP_PROTOCOL_CONVERTER_CONTROL_0, tmp) != 1) + drm_dbg_kms(&i915->drm, "Failed to set protocol converter HDMI mode to %s\n", + enableddisabled(intel_dp->has_hdmi_sink)); + + tmp = intel_dp->dfp.ycbcr_444_to_420 ? + DP_CONVERSION_TO_YCBCR420_ENABLE : 0; + + if (drm_dp_dpcd_writeb(&intel_dp->aux, + DP_PROTOCOL_CONVERTER_CONTROL_1, tmp) != 1) + drm_dbg_kms(&i915->drm, + "Failed to set protocol converter YCbCr 4:2:0 conversion mode to %s\n", + enableddisabled(intel_dp->dfp.ycbcr_444_to_420)); + + tmp = 0; + + if (drm_dp_dpcd_writeb(&intel_dp->aux, + DP_PROTOCOL_CONVERTER_CONTROL_2, tmp) <= 0) + drm_dbg_kms(&i915->drm, + "Failed to set protocol converter YCbCr 4:2:2 conversion mode to %s\n", + enableddisabled(false)); +} + static void intel_enable_dp(struct intel_atomic_state *state, struct intel_encoder *encoder, const struct intel_crtc_state *pipe_config, @@ -3789,6 +3926,7 @@ static void intel_enable_dp(struct intel_atomic_state *state, } intel_dp_sink_dpms(intel_dp, DRM_MODE_DPMS_ON); + intel_dp_configure_protocol_converter(intel_dp); intel_dp_start_link_train(intel_dp); intel_dp_stop_link_train(intel_dp); @@ -6028,16 +6166,103 @@ intel_dp_get_edid(struct intel_dp *intel_dp) } static void +intel_dp_update_dfp(struct intel_dp *intel_dp, + const struct edid *edid) +{ + struct drm_i915_private *i915 = dp_to_i915(intel_dp); + struct intel_connector *connector = intel_dp->attached_connector; + + intel_dp->dfp.max_bpc = + drm_dp_downstream_max_bpc(intel_dp->dpcd, + intel_dp->downstream_ports, edid); + + intel_dp->dfp.max_dotclock = + drm_dp_downstream_max_dotclock(intel_dp->dpcd, + intel_dp->downstream_ports); + + intel_dp->dfp.min_tmds_clock = + drm_dp_downstream_min_tmds_clock(intel_dp->dpcd, + intel_dp->downstream_ports, + edid); + intel_dp->dfp.max_tmds_clock = + drm_dp_downstream_max_tmds_clock(intel_dp->dpcd, + intel_dp->downstream_ports, + edid); + + drm_dbg_kms(&i915->drm, + "[CONNECTOR:%d:%s] DFP max bpc %d, max dotclock %d, TMDS clock %d-%d\n", + connector->base.base.id, connector->base.name, + intel_dp->dfp.max_bpc, + intel_dp->dfp.max_dotclock, + intel_dp->dfp.min_tmds_clock, + intel_dp->dfp.max_tmds_clock); +} + +static void +intel_dp_update_420(struct intel_dp *intel_dp) +{ + struct drm_i915_private *i915 = dp_to_i915(intel_dp); + struct intel_connector *connector = intel_dp->attached_connector; + bool is_branch, ycbcr_420_passthrough, ycbcr_444_to_420; + + /* No YCbCr output support on gmch platforms */ + if (HAS_GMCH(i915)) + return; + + /* + * ILK doesn't seem capable of DP YCbCr output. The + * displayed image is severly corrupted. SNB+ is fine. + */ + if (IS_GEN(i915, 5)) + return; + + is_branch = drm_dp_is_branch(intel_dp->dpcd); + ycbcr_420_passthrough = + drm_dp_downstream_420_passthrough(intel_dp->dpcd, + intel_dp->downstream_ports); + ycbcr_444_to_420 = + drm_dp_downstream_444_to_420_conversion(intel_dp->dpcd, + intel_dp->downstream_ports); + + if (INTEL_GEN(i915) >= 11) { + /* Prefer 4:2:0 passthrough over 4:4:4->4:2:0 conversion */ + intel_dp->dfp.ycbcr_444_to_420 = + ycbcr_444_to_420 && !ycbcr_420_passthrough; + + connector->base.ycbcr_420_allowed = + !is_branch || ycbcr_444_to_420 || ycbcr_420_passthrough; + } else { + /* 4:4:4->4:2:0 conversion is the only way */ + intel_dp->dfp.ycbcr_444_to_420 = ycbcr_444_to_420; + + connector->base.ycbcr_420_allowed = ycbcr_444_to_420; + } + + drm_dbg_kms(&i915->drm, + "[CONNECTOR:%d:%s] YCbCr 4:2:0 allowed? %s, YCbCr 4:4:4->4:2:0 conversion? %s\n", + connector->base.base.id, connector->base.name, + yesno(connector->base.ycbcr_420_allowed), + yesno(intel_dp->dfp.ycbcr_444_to_420)); +} + +static void intel_dp_set_edid(struct intel_dp *intel_dp) { - struct intel_connector *intel_connector = intel_dp->attached_connector; + struct intel_connector *connector = intel_dp->attached_connector; struct edid *edid; intel_dp_unset_edid(intel_dp); edid = intel_dp_get_edid(intel_dp); - intel_connector->detect_edid = edid; + connector->detect_edid = edid; + + intel_dp_update_dfp(intel_dp, edid); + intel_dp_update_420(intel_dp); + + if (edid && edid->input & DRM_EDID_INPUT_DIGITAL) { + intel_dp->has_hdmi_sink = drm_detect_hdmi_monitor(edid); + intel_dp->has_audio = drm_detect_monitor_audio(edid); + } - intel_dp->has_audio = drm_detect_monitor_audio(edid); drm_dp_cec_set_edid(&intel_dp->aux, edid); intel_dp->edid_quirks = drm_dp_get_edid_quirks(edid); } @@ -6045,14 +6270,23 @@ intel_dp_set_edid(struct intel_dp *intel_dp) static void intel_dp_unset_edid(struct intel_dp *intel_dp) { - struct intel_connector *intel_connector = intel_dp->attached_connector; + struct intel_connector *connector = intel_dp->attached_connector; drm_dp_cec_unset_edid(&intel_dp->aux); - kfree(intel_connector->detect_edid); - intel_connector->detect_edid = NULL; + kfree(connector->detect_edid); + connector->detect_edid = NULL; + intel_dp->has_hdmi_sink = false; intel_dp->has_audio = false; intel_dp->edid_quirks = 0; + + intel_dp->dfp.max_bpc = 0; + intel_dp->dfp.max_dotclock = 0; + intel_dp->dfp.min_tmds_clock = 0; + intel_dp->dfp.max_tmds_clock = 0; + + intel_dp->dfp.ycbcr_444_to_420 = false; + connector->base.ycbcr_420_allowed = false; } static int @@ -6071,6 +6305,9 @@ intel_dp_detect(struct drm_connector *connector, drm_WARN_ON(&dev_priv->drm, !drm_modeset_is_locked(&dev_priv->drm.mode_config.connection_mutex)); + if (!INTEL_DISPLAY_ENABLED(dev_priv)) + return connector_status_disconnected; + /* Can't disconnect eDP */ if (intel_dp_is_edp(intel_dp)) status = edp_detect(intel_dp); @@ -6211,7 +6448,7 @@ static int intel_dp_get_modes(struct drm_connector *connector) } /* if eDP has no EDID, fall back to fixed mode */ - if (intel_dp_is_edp(intel_attached_dp(to_intel_connector(connector))) && + if (intel_dp_is_edp(intel_attached_dp(intel_connector)) && intel_connector->panel.fixed_mode) { struct drm_display_mode *mode; @@ -6223,6 +6460,19 @@ static int intel_dp_get_modes(struct drm_connector *connector) } } + if (!edid) { + struct intel_dp *intel_dp = intel_attached_dp(intel_connector); + struct drm_display_mode *mode; + + mode = drm_dp_downstream_mode(connector->dev, + intel_dp->dpcd, + intel_dp->downstream_ports); + if (mode) { + drm_mode_probed_add(connector, mode); + return 1; + } + } + return 0; } @@ -6308,628 +6558,6 @@ void intel_dp_encoder_suspend(struct intel_encoder *intel_encoder) edp_panel_vdd_off_sync(intel_dp); } -static void intel_dp_hdcp_wait_for_cp_irq(struct intel_hdcp *hdcp, int timeout) -{ - long ret; - -#define C (hdcp->cp_irq_count_cached != atomic_read(&hdcp->cp_irq_count)) - ret = wait_event_interruptible_timeout(hdcp->cp_irq_queue, C, - msecs_to_jiffies(timeout)); - - if (!ret) - DRM_DEBUG_KMS("Timedout at waiting for CP_IRQ\n"); -} - -static -int intel_dp_hdcp_write_an_aksv(struct intel_digital_port *dig_port, - u8 *an) -{ - struct drm_i915_private *i915 = to_i915(dig_port->base.base.dev); - struct intel_dp *intel_dp = enc_to_intel_dp(to_intel_encoder(&dig_port->base.base)); - static const struct drm_dp_aux_msg msg = { - .request = DP_AUX_NATIVE_WRITE, - .address = DP_AUX_HDCP_AKSV, - .size = DRM_HDCP_KSV_LEN, - }; - u8 txbuf[HEADER_SIZE + DRM_HDCP_KSV_LEN] = {}, rxbuf[2], reply = 0; - ssize_t dpcd_ret; - int ret; - - /* Output An first, that's easy */ - dpcd_ret = drm_dp_dpcd_write(&dig_port->dp.aux, DP_AUX_HDCP_AN, - an, DRM_HDCP_AN_LEN); - if (dpcd_ret != DRM_HDCP_AN_LEN) { - drm_dbg_kms(&i915->drm, - "Failed to write An over DP/AUX (%zd)\n", - dpcd_ret); - return dpcd_ret >= 0 ? -EIO : dpcd_ret; - } - - /* - * Since Aksv is Oh-So-Secret, we can't access it in software. So in - * order to get it on the wire, we need to create the AUX header as if - * we were writing the data, and then tickle the hardware to output the - * data once the header is sent out. - */ - intel_dp_aux_header(txbuf, &msg); - - ret = intel_dp_aux_xfer(intel_dp, txbuf, HEADER_SIZE + msg.size, - rxbuf, sizeof(rxbuf), - DP_AUX_CH_CTL_AUX_AKSV_SELECT); - if (ret < 0) { - drm_dbg_kms(&i915->drm, - "Write Aksv over DP/AUX failed (%d)\n", ret); - return ret; - } else if (ret == 0) { - drm_dbg_kms(&i915->drm, "Aksv write over DP/AUX was empty\n"); - return -EIO; - } - - reply = (rxbuf[0] >> 4) & DP_AUX_NATIVE_REPLY_MASK; - if (reply != DP_AUX_NATIVE_REPLY_ACK) { - drm_dbg_kms(&i915->drm, - "Aksv write: no DP_AUX_NATIVE_REPLY_ACK %x\n", - reply); - return -EIO; - } - return 0; -} - -static int intel_dp_hdcp_read_bksv(struct intel_digital_port *dig_port, - u8 *bksv) -{ - struct drm_i915_private *i915 = to_i915(dig_port->base.base.dev); - ssize_t ret; - - ret = drm_dp_dpcd_read(&dig_port->dp.aux, DP_AUX_HDCP_BKSV, bksv, - DRM_HDCP_KSV_LEN); - if (ret != DRM_HDCP_KSV_LEN) { - drm_dbg_kms(&i915->drm, - "Read Bksv from DP/AUX failed (%zd)\n", ret); - return ret >= 0 ? -EIO : ret; - } - return 0; -} - -static int intel_dp_hdcp_read_bstatus(struct intel_digital_port *dig_port, - u8 *bstatus) -{ - struct drm_i915_private *i915 = to_i915(dig_port->base.base.dev); - ssize_t ret; - - /* - * For some reason the HDMI and DP HDCP specs call this register - * definition by different names. In the HDMI spec, it's called BSTATUS, - * but in DP it's called BINFO. - */ - ret = drm_dp_dpcd_read(&dig_port->dp.aux, DP_AUX_HDCP_BINFO, - bstatus, DRM_HDCP_BSTATUS_LEN); - if (ret != DRM_HDCP_BSTATUS_LEN) { - drm_dbg_kms(&i915->drm, - "Read bstatus from DP/AUX failed (%zd)\n", ret); - return ret >= 0 ? -EIO : ret; - } - return 0; -} - -static -int intel_dp_hdcp_read_bcaps(struct intel_digital_port *dig_port, - u8 *bcaps) -{ - struct drm_i915_private *i915 = to_i915(dig_port->base.base.dev); - ssize_t ret; - - ret = drm_dp_dpcd_read(&dig_port->dp.aux, DP_AUX_HDCP_BCAPS, - bcaps, 1); - if (ret != 1) { - drm_dbg_kms(&i915->drm, - "Read bcaps from DP/AUX failed (%zd)\n", ret); - return ret >= 0 ? -EIO : ret; - } - - return 0; -} - -static -int intel_dp_hdcp_repeater_present(struct intel_digital_port *dig_port, - bool *repeater_present) -{ - ssize_t ret; - u8 bcaps; - - ret = intel_dp_hdcp_read_bcaps(dig_port, &bcaps); - if (ret) - return ret; - - *repeater_present = bcaps & DP_BCAPS_REPEATER_PRESENT; - return 0; -} - -static -int intel_dp_hdcp_read_ri_prime(struct intel_digital_port *dig_port, - u8 *ri_prime) -{ - struct drm_i915_private *i915 = to_i915(dig_port->base.base.dev); - ssize_t ret; - - ret = drm_dp_dpcd_read(&dig_port->dp.aux, DP_AUX_HDCP_RI_PRIME, - ri_prime, DRM_HDCP_RI_LEN); - if (ret != DRM_HDCP_RI_LEN) { - drm_dbg_kms(&i915->drm, "Read Ri' from DP/AUX failed (%zd)\n", - ret); - return ret >= 0 ? -EIO : ret; - } - return 0; -} - -static -int intel_dp_hdcp_read_ksv_ready(struct intel_digital_port *dig_port, - bool *ksv_ready) -{ - struct drm_i915_private *i915 = to_i915(dig_port->base.base.dev); - ssize_t ret; - u8 bstatus; - - ret = drm_dp_dpcd_read(&dig_port->dp.aux, DP_AUX_HDCP_BSTATUS, - &bstatus, 1); - if (ret != 1) { - drm_dbg_kms(&i915->drm, - "Read bstatus from DP/AUX failed (%zd)\n", ret); - return ret >= 0 ? -EIO : ret; - } - *ksv_ready = bstatus & DP_BSTATUS_READY; - return 0; -} - -static -int intel_dp_hdcp_read_ksv_fifo(struct intel_digital_port *dig_port, - int num_downstream, u8 *ksv_fifo) -{ - struct drm_i915_private *i915 = to_i915(dig_port->base.base.dev); - ssize_t ret; - int i; - - /* KSV list is read via 15 byte window (3 entries @ 5 bytes each) */ - for (i = 0; i < num_downstream; i += 3) { - size_t len = min(num_downstream - i, 3) * DRM_HDCP_KSV_LEN; - ret = drm_dp_dpcd_read(&dig_port->dp.aux, - DP_AUX_HDCP_KSV_FIFO, - ksv_fifo + i * DRM_HDCP_KSV_LEN, - len); - if (ret != len) { - drm_dbg_kms(&i915->drm, - "Read ksv[%d] from DP/AUX failed (%zd)\n", - i, ret); - return ret >= 0 ? -EIO : ret; - } - } - return 0; -} - -static -int intel_dp_hdcp_read_v_prime_part(struct intel_digital_port *dig_port, - int i, u32 *part) -{ - struct drm_i915_private *i915 = to_i915(dig_port->base.base.dev); - ssize_t ret; - - if (i >= DRM_HDCP_V_PRIME_NUM_PARTS) - return -EINVAL; - - ret = drm_dp_dpcd_read(&dig_port->dp.aux, - DP_AUX_HDCP_V_PRIME(i), part, - DRM_HDCP_V_PRIME_PART_LEN); - if (ret != DRM_HDCP_V_PRIME_PART_LEN) { - drm_dbg_kms(&i915->drm, - "Read v'[%d] from DP/AUX failed (%zd)\n", i, ret); - return ret >= 0 ? -EIO : ret; - } - return 0; -} - -static -int intel_dp_hdcp_toggle_signalling(struct intel_digital_port *dig_port, - bool enable) -{ - /* Not used for single stream DisplayPort setups */ - return 0; -} - -static -bool intel_dp_hdcp_check_link(struct intel_digital_port *dig_port) -{ - struct drm_i915_private *i915 = to_i915(dig_port->base.base.dev); - ssize_t ret; - u8 bstatus; - - ret = drm_dp_dpcd_read(&dig_port->dp.aux, DP_AUX_HDCP_BSTATUS, - &bstatus, 1); - if (ret != 1) { - drm_dbg_kms(&i915->drm, - "Read bstatus from DP/AUX failed (%zd)\n", ret); - return false; - } - - return !(bstatus & (DP_BSTATUS_LINK_FAILURE | DP_BSTATUS_REAUTH_REQ)); -} - -static -int intel_dp_hdcp_capable(struct intel_digital_port *dig_port, - bool *hdcp_capable) -{ - ssize_t ret; - u8 bcaps; - - ret = intel_dp_hdcp_read_bcaps(dig_port, &bcaps); - if (ret) - return ret; - - *hdcp_capable = bcaps & DP_BCAPS_HDCP_CAPABLE; - return 0; -} - -struct hdcp2_dp_errata_stream_type { - u8 msg_id; - u8 stream_type; -} __packed; - -struct hdcp2_dp_msg_data { - u8 msg_id; - u32 offset; - bool msg_detectable; - u32 timeout; - u32 timeout2; /* Added for non_paired situation */ -}; - -static const struct hdcp2_dp_msg_data hdcp2_dp_msg_data[] = { - { HDCP_2_2_AKE_INIT, DP_HDCP_2_2_AKE_INIT_OFFSET, false, 0, 0 }, - { HDCP_2_2_AKE_SEND_CERT, DP_HDCP_2_2_AKE_SEND_CERT_OFFSET, - false, HDCP_2_2_CERT_TIMEOUT_MS, 0 }, - { HDCP_2_2_AKE_NO_STORED_KM, DP_HDCP_2_2_AKE_NO_STORED_KM_OFFSET, - false, 0, 0 }, - { HDCP_2_2_AKE_STORED_KM, DP_HDCP_2_2_AKE_STORED_KM_OFFSET, - false, 0, 0 }, - { HDCP_2_2_AKE_SEND_HPRIME, DP_HDCP_2_2_AKE_SEND_HPRIME_OFFSET, - true, HDCP_2_2_HPRIME_PAIRED_TIMEOUT_MS, - HDCP_2_2_HPRIME_NO_PAIRED_TIMEOUT_MS }, - { HDCP_2_2_AKE_SEND_PAIRING_INFO, - DP_HDCP_2_2_AKE_SEND_PAIRING_INFO_OFFSET, true, - HDCP_2_2_PAIRING_TIMEOUT_MS, 0 }, - { HDCP_2_2_LC_INIT, DP_HDCP_2_2_LC_INIT_OFFSET, false, 0, 0 }, - { HDCP_2_2_LC_SEND_LPRIME, DP_HDCP_2_2_LC_SEND_LPRIME_OFFSET, - false, HDCP_2_2_DP_LPRIME_TIMEOUT_MS, 0 }, - { HDCP_2_2_SKE_SEND_EKS, DP_HDCP_2_2_SKE_SEND_EKS_OFFSET, false, - 0, 0 }, - { HDCP_2_2_REP_SEND_RECVID_LIST, - DP_HDCP_2_2_REP_SEND_RECVID_LIST_OFFSET, true, - HDCP_2_2_RECVID_LIST_TIMEOUT_MS, 0 }, - { HDCP_2_2_REP_SEND_ACK, DP_HDCP_2_2_REP_SEND_ACK_OFFSET, false, - 0, 0 }, - { HDCP_2_2_REP_STREAM_MANAGE, - DP_HDCP_2_2_REP_STREAM_MANAGE_OFFSET, false, - 0, 0 }, - { HDCP_2_2_REP_STREAM_READY, DP_HDCP_2_2_REP_STREAM_READY_OFFSET, - false, HDCP_2_2_STREAM_READY_TIMEOUT_MS, 0 }, -/* local define to shovel this through the write_2_2 interface */ -#define HDCP_2_2_ERRATA_DP_STREAM_TYPE 50 - { HDCP_2_2_ERRATA_DP_STREAM_TYPE, - DP_HDCP_2_2_REG_STREAM_TYPE_OFFSET, false, - 0, 0 }, -}; - -static int -intel_dp_hdcp2_read_rx_status(struct intel_digital_port *dig_port, - u8 *rx_status) -{ - struct drm_i915_private *i915 = to_i915(dig_port->base.base.dev); - ssize_t ret; - - ret = drm_dp_dpcd_read(&dig_port->dp.aux, - DP_HDCP_2_2_REG_RXSTATUS_OFFSET, rx_status, - HDCP_2_2_DP_RXSTATUS_LEN); - if (ret != HDCP_2_2_DP_RXSTATUS_LEN) { - drm_dbg_kms(&i915->drm, - "Read bstatus from DP/AUX failed (%zd)\n", ret); - return ret >= 0 ? -EIO : ret; - } - - return 0; -} - -static -int hdcp2_detect_msg_availability(struct intel_digital_port *dig_port, - u8 msg_id, bool *msg_ready) -{ - u8 rx_status; - int ret; - - *msg_ready = false; - ret = intel_dp_hdcp2_read_rx_status(dig_port, &rx_status); - if (ret < 0) - return ret; - - switch (msg_id) { - case HDCP_2_2_AKE_SEND_HPRIME: - if (HDCP_2_2_DP_RXSTATUS_H_PRIME(rx_status)) - *msg_ready = true; - break; - case HDCP_2_2_AKE_SEND_PAIRING_INFO: - if (HDCP_2_2_DP_RXSTATUS_PAIRING(rx_status)) - *msg_ready = true; - break; - case HDCP_2_2_REP_SEND_RECVID_LIST: - if (HDCP_2_2_DP_RXSTATUS_READY(rx_status)) - *msg_ready = true; - break; - default: - DRM_ERROR("Unidentified msg_id: %d\n", msg_id); - return -EINVAL; - } - - return 0; -} - -static ssize_t -intel_dp_hdcp2_wait_for_msg(struct intel_digital_port *dig_port, - const struct hdcp2_dp_msg_data *hdcp2_msg_data) -{ - struct drm_i915_private *i915 = to_i915(dig_port->base.base.dev); - struct intel_dp *dp = &dig_port->dp; - struct intel_hdcp *hdcp = &dp->attached_connector->hdcp; - u8 msg_id = hdcp2_msg_data->msg_id; - int ret, timeout; - bool msg_ready = false; - - if (msg_id == HDCP_2_2_AKE_SEND_HPRIME && !hdcp->is_paired) - timeout = hdcp2_msg_data->timeout2; - else - timeout = hdcp2_msg_data->timeout; - - /* - * There is no way to detect the CERT, LPRIME and STREAM_READY - * availability. So Wait for timeout and read the msg. - */ - if (!hdcp2_msg_data->msg_detectable) { - mdelay(timeout); - ret = 0; - } else { - /* - * As we want to check the msg availability at timeout, Ignoring - * the timeout at wait for CP_IRQ. - */ - intel_dp_hdcp_wait_for_cp_irq(hdcp, timeout); - ret = hdcp2_detect_msg_availability(dig_port, - msg_id, &msg_ready); - if (!msg_ready) - ret = -ETIMEDOUT; - } - - if (ret) - drm_dbg_kms(&i915->drm, - "msg_id %d, ret %d, timeout(mSec): %d\n", - hdcp2_msg_data->msg_id, ret, timeout); - - return ret; -} - -static const struct hdcp2_dp_msg_data *get_hdcp2_dp_msg_data(u8 msg_id) -{ - int i; - - for (i = 0; i < ARRAY_SIZE(hdcp2_dp_msg_data); i++) - if (hdcp2_dp_msg_data[i].msg_id == msg_id) - return &hdcp2_dp_msg_data[i]; - - return NULL; -} - -static -int intel_dp_hdcp2_write_msg(struct intel_digital_port *dig_port, - void *buf, size_t size) -{ - struct intel_dp *dp = &dig_port->dp; - struct intel_hdcp *hdcp = &dp->attached_connector->hdcp; - unsigned int offset; - u8 *byte = buf; - ssize_t ret, bytes_to_write, len; - const struct hdcp2_dp_msg_data *hdcp2_msg_data; - - hdcp2_msg_data = get_hdcp2_dp_msg_data(*byte); - if (!hdcp2_msg_data) - return -EINVAL; - - offset = hdcp2_msg_data->offset; - - /* No msg_id in DP HDCP2.2 msgs */ - bytes_to_write = size - 1; - byte++; - - hdcp->cp_irq_count_cached = atomic_read(&hdcp->cp_irq_count); - - while (bytes_to_write) { - len = bytes_to_write > DP_AUX_MAX_PAYLOAD_BYTES ? - DP_AUX_MAX_PAYLOAD_BYTES : bytes_to_write; - - ret = drm_dp_dpcd_write(&dig_port->dp.aux, - offset, (void *)byte, len); - if (ret < 0) - return ret; - - bytes_to_write -= ret; - byte += ret; - offset += ret; - } - - return size; -} - -static -ssize_t get_receiver_id_list_size(struct intel_digital_port *dig_port) -{ - u8 rx_info[HDCP_2_2_RXINFO_LEN]; - u32 dev_cnt; - ssize_t ret; - - ret = drm_dp_dpcd_read(&dig_port->dp.aux, - DP_HDCP_2_2_REG_RXINFO_OFFSET, - (void *)rx_info, HDCP_2_2_RXINFO_LEN); - if (ret != HDCP_2_2_RXINFO_LEN) - return ret >= 0 ? -EIO : ret; - - dev_cnt = (HDCP_2_2_DEV_COUNT_HI(rx_info[0]) << 4 | - HDCP_2_2_DEV_COUNT_LO(rx_info[1])); - - if (dev_cnt > HDCP_2_2_MAX_DEVICE_COUNT) - dev_cnt = HDCP_2_2_MAX_DEVICE_COUNT; - - ret = sizeof(struct hdcp2_rep_send_receiverid_list) - - HDCP_2_2_RECEIVER_IDS_MAX_LEN + - (dev_cnt * HDCP_2_2_RECEIVER_ID_LEN); - - return ret; -} - -static -int intel_dp_hdcp2_read_msg(struct intel_digital_port *dig_port, - u8 msg_id, void *buf, size_t size) -{ - struct drm_i915_private *i915 = to_i915(dig_port->base.base.dev); - unsigned int offset; - u8 *byte = buf; - ssize_t ret, bytes_to_recv, len; - const struct hdcp2_dp_msg_data *hdcp2_msg_data; - - hdcp2_msg_data = get_hdcp2_dp_msg_data(msg_id); - if (!hdcp2_msg_data) - return -EINVAL; - offset = hdcp2_msg_data->offset; - - ret = intel_dp_hdcp2_wait_for_msg(dig_port, hdcp2_msg_data); - if (ret < 0) - return ret; - - if (msg_id == HDCP_2_2_REP_SEND_RECVID_LIST) { - ret = get_receiver_id_list_size(dig_port); - if (ret < 0) - return ret; - - size = ret; - } - bytes_to_recv = size - 1; - - /* DP adaptation msgs has no msg_id */ - byte++; - - while (bytes_to_recv) { - len = bytes_to_recv > DP_AUX_MAX_PAYLOAD_BYTES ? - DP_AUX_MAX_PAYLOAD_BYTES : bytes_to_recv; - - ret = drm_dp_dpcd_read(&dig_port->dp.aux, offset, - (void *)byte, len); - if (ret < 0) { - drm_dbg_kms(&i915->drm, "msg_id %d, ret %zd\n", - msg_id, ret); - return ret; - } - - bytes_to_recv -= ret; - byte += ret; - offset += ret; - } - byte = buf; - *byte = msg_id; - - return size; -} - -static -int intel_dp_hdcp2_config_stream_type(struct intel_digital_port *dig_port, - bool is_repeater, u8 content_type) -{ - int ret; - struct hdcp2_dp_errata_stream_type stream_type_msg; - - if (is_repeater) - return 0; - - /* - * Errata for DP: As Stream type is used for encryption, Receiver - * should be communicated with stream type for the decryption of the - * content. - * Repeater will be communicated with stream type as a part of it's - * auth later in time. - */ - stream_type_msg.msg_id = HDCP_2_2_ERRATA_DP_STREAM_TYPE; - stream_type_msg.stream_type = content_type; - - ret = intel_dp_hdcp2_write_msg(dig_port, &stream_type_msg, - sizeof(stream_type_msg)); - - return ret < 0 ? ret : 0; - -} - -static -int intel_dp_hdcp2_check_link(struct intel_digital_port *dig_port) -{ - u8 rx_status; - int ret; - - ret = intel_dp_hdcp2_read_rx_status(dig_port, &rx_status); - if (ret) - return ret; - - if (HDCP_2_2_DP_RXSTATUS_REAUTH_REQ(rx_status)) - ret = HDCP_REAUTH_REQUEST; - else if (HDCP_2_2_DP_RXSTATUS_LINK_FAILED(rx_status)) - ret = HDCP_LINK_INTEGRITY_FAILURE; - else if (HDCP_2_2_DP_RXSTATUS_READY(rx_status)) - ret = HDCP_TOPOLOGY_CHANGE; - - return ret; -} - -static -int intel_dp_hdcp2_capable(struct intel_digital_port *dig_port, - bool *capable) -{ - u8 rx_caps[3]; - int ret; - - *capable = false; - ret = drm_dp_dpcd_read(&dig_port->dp.aux, - DP_HDCP_2_2_REG_RX_CAPS_OFFSET, - rx_caps, HDCP_2_2_RXCAPS_LEN); - if (ret != HDCP_2_2_RXCAPS_LEN) - return ret >= 0 ? -EIO : ret; - - if (rx_caps[0] == HDCP_2_2_RX_CAPS_VERSION_VAL && - HDCP_2_2_DP_HDCP_CAPABLE(rx_caps[2])) - *capable = true; - - return 0; -} - -static const struct intel_hdcp_shim intel_dp_hdcp_shim = { - .write_an_aksv = intel_dp_hdcp_write_an_aksv, - .read_bksv = intel_dp_hdcp_read_bksv, - .read_bstatus = intel_dp_hdcp_read_bstatus, - .repeater_present = intel_dp_hdcp_repeater_present, - .read_ri_prime = intel_dp_hdcp_read_ri_prime, - .read_ksv_ready = intel_dp_hdcp_read_ksv_ready, - .read_ksv_fifo = intel_dp_hdcp_read_ksv_fifo, - .read_v_prime_part = intel_dp_hdcp_read_v_prime_part, - .toggle_signalling = intel_dp_hdcp_toggle_signalling, - .check_link = intel_dp_hdcp_check_link, - .hdcp_capable = intel_dp_hdcp_capable, - .write_2_2_msg = intel_dp_hdcp2_write_msg, - .read_2_2_msg = intel_dp_hdcp2_read_msg, - .config_stream_type = intel_dp_hdcp2_config_stream_type, - .check_2_2_link = intel_dp_hdcp2_check_link, - .hdcp_2_2_capable = intel_dp_hdcp2_capable, - .protocol = HDCP_PROTOCOL_DP, -}; - static void intel_edp_panel_vdd_sanitize(struct intel_dp *intel_dp) { struct drm_i915_private *dev_priv = dp_to_i915(intel_dp); @@ -7640,6 +7268,15 @@ static void intel_dp_set_drrs_state(struct drm_i915_private *dev_priv, refresh_rate); } +static void +intel_edp_drrs_enable_locked(struct intel_dp *intel_dp) +{ + struct drm_i915_private *dev_priv = dp_to_i915(intel_dp); + + dev_priv->drrs.busy_frontbuffer_bits = 0; + dev_priv->drrs.dp = intel_dp; +} + /** * intel_edp_drrs_enable - init drrs struct if supported * @intel_dp: DP struct @@ -7652,31 +7289,40 @@ void intel_edp_drrs_enable(struct intel_dp *intel_dp, { struct drm_i915_private *dev_priv = dp_to_i915(intel_dp); - if (!crtc_state->has_drrs) { - drm_dbg_kms(&dev_priv->drm, "Panel doesn't support DRRS\n"); + if (!crtc_state->has_drrs) return; - } - if (dev_priv->psr.enabled) { - drm_dbg_kms(&dev_priv->drm, - "PSR enabled. Not enabling DRRS.\n"); - return; - } + drm_dbg_kms(&dev_priv->drm, "Enabling DRRS\n"); mutex_lock(&dev_priv->drrs.mutex); + if (dev_priv->drrs.dp) { - drm_dbg_kms(&dev_priv->drm, "DRRS already enabled\n"); + drm_warn(&dev_priv->drm, "DRRS already enabled\n"); goto unlock; } - dev_priv->drrs.busy_frontbuffer_bits = 0; - - dev_priv->drrs.dp = intel_dp; + intel_edp_drrs_enable_locked(intel_dp); unlock: mutex_unlock(&dev_priv->drrs.mutex); } +static void +intel_edp_drrs_disable_locked(struct intel_dp *intel_dp, + const struct intel_crtc_state *crtc_state) +{ + struct drm_i915_private *dev_priv = dp_to_i915(intel_dp); + + if (dev_priv->drrs.refresh_rate_type == DRRS_LOW_RR) { + int refresh; + + refresh = drm_mode_vrefresh(intel_dp->attached_connector->panel.fixed_mode); + intel_dp_set_drrs_state(dev_priv, crtc_state, refresh); + } + + dev_priv->drrs.dp = NULL; +} + /** * intel_edp_drrs_disable - Disable DRRS * @intel_dp: DP struct @@ -7697,16 +7343,45 @@ void intel_edp_drrs_disable(struct intel_dp *intel_dp, return; } - if (dev_priv->drrs.refresh_rate_type == DRRS_LOW_RR) - intel_dp_set_drrs_state(dev_priv, old_crtc_state, - drm_mode_vrefresh(intel_dp->attached_connector->panel.fixed_mode)); - - dev_priv->drrs.dp = NULL; + intel_edp_drrs_disable_locked(intel_dp, old_crtc_state); mutex_unlock(&dev_priv->drrs.mutex); cancel_delayed_work_sync(&dev_priv->drrs.work); } +/** + * intel_edp_drrs_update - Update DRRS state + * @intel_dp: Intel DP + * @crtc_state: new CRTC state + * + * This function will update DRRS states, disabling or enabling DRRS when + * executing fastsets. For full modeset, intel_edp_drrs_disable() and + * intel_edp_drrs_enable() should be called instead. + */ +void +intel_edp_drrs_update(struct intel_dp *intel_dp, + const struct intel_crtc_state *crtc_state) +{ + struct drm_i915_private *dev_priv = dp_to_i915(intel_dp); + + if (dev_priv->drrs.type != SEAMLESS_DRRS_SUPPORT) + return; + + mutex_lock(&dev_priv->drrs.mutex); + + /* New state matches current one? */ + if (crtc_state->has_drrs == !!dev_priv->drrs.dp) + goto unlock; + + if (crtc_state->has_drrs) + intel_edp_drrs_enable_locked(intel_dp); + else + intel_edp_drrs_disable_locked(intel_dp, crtc_state); + +unlock: + mutex_unlock(&dev_priv->drrs.mutex); +} + static void intel_edp_drrs_downclock_work(struct work_struct *work) { struct drm_i915_private *dev_priv = @@ -8138,10 +7813,6 @@ intel_dp_init_connector(struct intel_digital_port *dig_port, connector->interlace_allowed = true; connector->doublescan_allowed = 0; - if (INTEL_GEN(dev_priv) >= 11) - connector->ycbcr_420_allowed = true; - - intel_encoder->hpd_pin = intel_hpd_pin_default(dev_priv, port); intel_connector->polled = DRM_CONNECTOR_POLL_HPD; intel_dp_aux_init(intel_dp); @@ -8166,7 +7837,7 @@ intel_dp_init_connector(struct intel_digital_port *dig_port, intel_dp_add_properties(intel_dp, connector); if (is_hdcp_supported(dev_priv, port) && !intel_dp_is_edp(intel_dp)) { - int ret = intel_hdcp_init(intel_connector, &intel_dp_hdcp_shim); + int ret = intel_dp_init_hdcp(dig_port, intel_connector); if (ret) drm_dbg_kms(&dev_priv->drm, "HDCP init failed, skipping.\n"); @@ -8210,6 +7881,8 @@ bool intel_dp_init(struct drm_i915_private *dev_priv, intel_encoder = &dig_port->base; encoder = &intel_encoder->base; + mutex_init(&dig_port->hdcp_mutex); + if (drm_encoder_init(&dev_priv->drm, &intel_encoder->base, &intel_dp_enc_funcs, DRM_MODE_ENCODER_TMDS, "DP %c", port_name(port))) @@ -8284,6 +7957,7 @@ bool intel_dp_init(struct drm_i915_private *dev_priv, } intel_encoder->cloneable = 0; intel_encoder->port = port; + intel_encoder->hpd_pin = intel_hpd_pin_default(dev_priv, port); dig_port->hpd_pulse = intel_dp_hpd_pulse; diff --git a/drivers/gpu/drm/i915/display/intel_dp.h b/drivers/gpu/drm/i915/display/intel_dp.h index 0a3af3410d52..08a1c0aa8b94 100644 --- a/drivers/gpu/drm/i915/display/intel_dp.h +++ b/drivers/gpu/drm/i915/display/intel_dp.h @@ -17,6 +17,7 @@ struct drm_encoder; struct drm_i915_private; struct drm_modeset_acquire_ctx; struct drm_dp_vsc_sdp; +struct intel_atomic_state; struct intel_connector; struct intel_crtc_state; struct intel_digital_port; @@ -50,6 +51,7 @@ int intel_dp_get_link_train_fallback_values(struct intel_dp *intel_dp, int intel_dp_retrain_link(struct intel_encoder *encoder, struct drm_modeset_acquire_ctx *ctx); void intel_dp_sink_dpms(struct intel_dp *intel_dp, int mode); +void intel_dp_configure_protocol_converter(struct intel_dp *intel_dp); void intel_dp_sink_set_decompression_state(struct intel_dp *intel_dp, const struct intel_crtc_state *crtc_state, bool enable); @@ -81,6 +83,8 @@ void intel_edp_drrs_enable(struct intel_dp *intel_dp, const struct intel_crtc_state *crtc_state); void intel_edp_drrs_disable(struct intel_dp *intel_dp, const struct intel_crtc_state *crtc_state); +void intel_edp_drrs_update(struct intel_dp *intel_dp, + const struct intel_crtc_state *crtc_state); void intel_edp_drrs_invalidate(struct drm_i915_private *dev_priv, unsigned int frontbuffer_bits); void intel_edp_drrs_flush(struct drm_i915_private *dev_priv, @@ -127,4 +131,12 @@ static inline unsigned int intel_dp_unused_lane_mask(int lane_count) u32 intel_dp_mode_to_fec_clock(u32 mode_clock); +void intel_ddi_update_pipe(struct intel_atomic_state *state, + struct intel_encoder *encoder, + const struct intel_crtc_state *crtc_state, + const struct drm_connector_state *conn_state); + +int intel_dp_init_hdcp(struct intel_digital_port *dig_port, + struct intel_connector *intel_connector); + #endif /* __INTEL_DP_H__ */ diff --git a/drivers/gpu/drm/i915/display/intel_dp_aux_backlight.c b/drivers/gpu/drm/i915/display/intel_dp_aux_backlight.c index acbd7eb66cbe..036f504ac7db 100644 --- a/drivers/gpu/drm/i915/display/intel_dp_aux_backlight.c +++ b/drivers/gpu/drm/i915/display/intel_dp_aux_backlight.c @@ -52,17 +52,11 @@ static void set_aux_backlight_enable(struct intel_dp *intel_dp, bool enable) } } -/* - * Read the current backlight value from DPCD register(s) based - * on if 8-bit(MSB) or 16-bit(MSB and LSB) values are supported - */ -static u32 intel_dp_aux_get_backlight(struct intel_connector *connector) +static bool intel_dp_aux_backlight_dpcd_mode(struct intel_connector *connector) { struct intel_dp *intel_dp = intel_attached_dp(connector); struct drm_i915_private *i915 = dp_to_i915(intel_dp); - u8 read_val[2] = { 0x0 }; u8 mode_reg; - u16 level = 0; if (drm_dp_dpcd_readb(&intel_dp->aux, DP_EDP_BACKLIGHT_MODE_SET_REGISTER, @@ -70,15 +64,29 @@ static u32 intel_dp_aux_get_backlight(struct intel_connector *connector) drm_dbg_kms(&i915->drm, "Failed to read the DPCD register 0x%x\n", DP_EDP_BACKLIGHT_MODE_SET_REGISTER); - return 0; + return false; } + return (mode_reg & DP_EDP_BACKLIGHT_CONTROL_MODE_MASK) == + DP_EDP_BACKLIGHT_CONTROL_MODE_DPCD; +} + +/* + * Read the current backlight value from DPCD register(s) based + * on if 8-bit(MSB) or 16-bit(MSB and LSB) values are supported + */ +static u32 intel_dp_aux_get_backlight(struct intel_connector *connector) +{ + struct intel_dp *intel_dp = intel_attached_dp(connector); + struct drm_i915_private *i915 = dp_to_i915(intel_dp); + u8 read_val[2] = { 0x0 }; + u16 level = 0; + /* * If we're not in DPCD control mode yet, the programmed brightness * value is meaningless and we should assume max brightness */ - if ((mode_reg & DP_EDP_BACKLIGHT_CONTROL_MODE_MASK) != - DP_EDP_BACKLIGHT_CONTROL_MODE_DPCD) + if (!intel_dp_aux_backlight_dpcd_mode(connector)) return connector->panel.backlight.max; if (drm_dp_dpcd_read(&intel_dp->aux, DP_EDP_BACKLIGHT_BRIGHTNESS_MSB, @@ -319,7 +327,8 @@ static int intel_dp_aux_setup_backlight(struct intel_connector *connector, panel->backlight.min = 0; panel->backlight.level = intel_dp_aux_get_backlight(connector); - panel->backlight.enabled = panel->backlight.level != 0; + panel->backlight.enabled = intel_dp_aux_backlight_dpcd_mode(connector) && + panel->backlight.level != 0; return 0; } diff --git a/drivers/gpu/drm/i915/display/intel_dp_hdcp.c b/drivers/gpu/drm/i915/display/intel_dp_hdcp.c new file mode 100644 index 000000000000..03424d20e9f7 --- /dev/null +++ b/drivers/gpu/drm/i915/display/intel_dp_hdcp.c @@ -0,0 +1,703 @@ +/* SPDX-License-Identifier: MIT */ +/* + * Copyright (C) 2020 Google, Inc. + * + * Authors: + * Sean Paul <seanpaul@chromium.org> + */ + +#include <drm/drm_dp_helper.h> +#include <drm/drm_dp_mst_helper.h> +#include <drm/drm_hdcp.h> +#include <drm/drm_print.h> + +#include "intel_display_types.h" +#include "intel_ddi.h" +#include "intel_dp.h" +#include "intel_hdcp.h" + +static void intel_dp_hdcp_wait_for_cp_irq(struct intel_hdcp *hdcp, int timeout) +{ + long ret; + +#define C (hdcp->cp_irq_count_cached != atomic_read(&hdcp->cp_irq_count)) + ret = wait_event_interruptible_timeout(hdcp->cp_irq_queue, C, + msecs_to_jiffies(timeout)); + + if (!ret) + DRM_DEBUG_KMS("Timedout at waiting for CP_IRQ\n"); +} + +static +int intel_dp_hdcp_write_an_aksv(struct intel_digital_port *dig_port, + u8 *an) +{ + struct drm_i915_private *i915 = to_i915(dig_port->base.base.dev); + u8 aksv[DRM_HDCP_KSV_LEN] = {}; + ssize_t dpcd_ret; + + /* Output An first, that's easy */ + dpcd_ret = drm_dp_dpcd_write(&dig_port->dp.aux, DP_AUX_HDCP_AN, + an, DRM_HDCP_AN_LEN); + if (dpcd_ret != DRM_HDCP_AN_LEN) { + drm_dbg_kms(&i915->drm, + "Failed to write An over DP/AUX (%zd)\n", + dpcd_ret); + return dpcd_ret >= 0 ? -EIO : dpcd_ret; + } + + /* + * Since Aksv is Oh-So-Secret, we can't access it in software. So we + * send an empty buffer of the correct length through the DP helpers. On + * the other side, in the transfer hook, we'll generate a flag based on + * the destination address which will tickle the hardware to output the + * Aksv on our behalf after the header is sent. + */ + dpcd_ret = drm_dp_dpcd_write(&dig_port->dp.aux, DP_AUX_HDCP_AKSV, + aksv, DRM_HDCP_KSV_LEN); + if (dpcd_ret != DRM_HDCP_KSV_LEN) { + drm_dbg_kms(&i915->drm, + "Failed to write Aksv over DP/AUX (%zd)\n", + dpcd_ret); + return dpcd_ret >= 0 ? -EIO : dpcd_ret; + } + return 0; +} + +static int intel_dp_hdcp_read_bksv(struct intel_digital_port *dig_port, + u8 *bksv) +{ + struct drm_i915_private *i915 = to_i915(dig_port->base.base.dev); + ssize_t ret; + + ret = drm_dp_dpcd_read(&dig_port->dp.aux, DP_AUX_HDCP_BKSV, bksv, + DRM_HDCP_KSV_LEN); + if (ret != DRM_HDCP_KSV_LEN) { + drm_dbg_kms(&i915->drm, + "Read Bksv from DP/AUX failed (%zd)\n", ret); + return ret >= 0 ? -EIO : ret; + } + return 0; +} + +static int intel_dp_hdcp_read_bstatus(struct intel_digital_port *dig_port, + u8 *bstatus) +{ + struct drm_i915_private *i915 = to_i915(dig_port->base.base.dev); + ssize_t ret; + + /* + * For some reason the HDMI and DP HDCP specs call this register + * definition by different names. In the HDMI spec, it's called BSTATUS, + * but in DP it's called BINFO. + */ + ret = drm_dp_dpcd_read(&dig_port->dp.aux, DP_AUX_HDCP_BINFO, + bstatus, DRM_HDCP_BSTATUS_LEN); + if (ret != DRM_HDCP_BSTATUS_LEN) { + drm_dbg_kms(&i915->drm, + "Read bstatus from DP/AUX failed (%zd)\n", ret); + return ret >= 0 ? -EIO : ret; + } + return 0; +} + +static +int intel_dp_hdcp_read_bcaps(struct intel_digital_port *dig_port, + u8 *bcaps) +{ + struct drm_i915_private *i915 = to_i915(dig_port->base.base.dev); + ssize_t ret; + + ret = drm_dp_dpcd_read(&dig_port->dp.aux, DP_AUX_HDCP_BCAPS, + bcaps, 1); + if (ret != 1) { + drm_dbg_kms(&i915->drm, + "Read bcaps from DP/AUX failed (%zd)\n", ret); + return ret >= 0 ? -EIO : ret; + } + + return 0; +} + +static +int intel_dp_hdcp_repeater_present(struct intel_digital_port *dig_port, + bool *repeater_present) +{ + ssize_t ret; + u8 bcaps; + + ret = intel_dp_hdcp_read_bcaps(dig_port, &bcaps); + if (ret) + return ret; + + *repeater_present = bcaps & DP_BCAPS_REPEATER_PRESENT; + return 0; +} + +static +int intel_dp_hdcp_read_ri_prime(struct intel_digital_port *dig_port, + u8 *ri_prime) +{ + struct drm_i915_private *i915 = to_i915(dig_port->base.base.dev); + ssize_t ret; + + ret = drm_dp_dpcd_read(&dig_port->dp.aux, DP_AUX_HDCP_RI_PRIME, + ri_prime, DRM_HDCP_RI_LEN); + if (ret != DRM_HDCP_RI_LEN) { + drm_dbg_kms(&i915->drm, "Read Ri' from DP/AUX failed (%zd)\n", + ret); + return ret >= 0 ? -EIO : ret; + } + return 0; +} + +static +int intel_dp_hdcp_read_ksv_ready(struct intel_digital_port *dig_port, + bool *ksv_ready) +{ + struct drm_i915_private *i915 = to_i915(dig_port->base.base.dev); + ssize_t ret; + u8 bstatus; + + ret = drm_dp_dpcd_read(&dig_port->dp.aux, DP_AUX_HDCP_BSTATUS, + &bstatus, 1); + if (ret != 1) { + drm_dbg_kms(&i915->drm, + "Read bstatus from DP/AUX failed (%zd)\n", ret); + return ret >= 0 ? -EIO : ret; + } + *ksv_ready = bstatus & DP_BSTATUS_READY; + return 0; +} + +static +int intel_dp_hdcp_read_ksv_fifo(struct intel_digital_port *dig_port, + int num_downstream, u8 *ksv_fifo) +{ + struct drm_i915_private *i915 = to_i915(dig_port->base.base.dev); + ssize_t ret; + int i; + + /* KSV list is read via 15 byte window (3 entries @ 5 bytes each) */ + for (i = 0; i < num_downstream; i += 3) { + size_t len = min(num_downstream - i, 3) * DRM_HDCP_KSV_LEN; + ret = drm_dp_dpcd_read(&dig_port->dp.aux, + DP_AUX_HDCP_KSV_FIFO, + ksv_fifo + i * DRM_HDCP_KSV_LEN, + len); + if (ret != len) { + drm_dbg_kms(&i915->drm, + "Read ksv[%d] from DP/AUX failed (%zd)\n", + i, ret); + return ret >= 0 ? -EIO : ret; + } + } + return 0; +} + +static +int intel_dp_hdcp_read_v_prime_part(struct intel_digital_port *dig_port, + int i, u32 *part) +{ + struct drm_i915_private *i915 = to_i915(dig_port->base.base.dev); + ssize_t ret; + + if (i >= DRM_HDCP_V_PRIME_NUM_PARTS) + return -EINVAL; + + ret = drm_dp_dpcd_read(&dig_port->dp.aux, + DP_AUX_HDCP_V_PRIME(i), part, + DRM_HDCP_V_PRIME_PART_LEN); + if (ret != DRM_HDCP_V_PRIME_PART_LEN) { + drm_dbg_kms(&i915->drm, + "Read v'[%d] from DP/AUX failed (%zd)\n", i, ret); + return ret >= 0 ? -EIO : ret; + } + return 0; +} + +static +int intel_dp_hdcp_toggle_signalling(struct intel_digital_port *dig_port, + enum transcoder cpu_transcoder, + bool enable) +{ + /* Not used for single stream DisplayPort setups */ + return 0; +} + +static +bool intel_dp_hdcp_check_link(struct intel_digital_port *dig_port, + struct intel_connector *connector) +{ + struct drm_i915_private *i915 = to_i915(dig_port->base.base.dev); + ssize_t ret; + u8 bstatus; + + ret = drm_dp_dpcd_read(&dig_port->dp.aux, DP_AUX_HDCP_BSTATUS, + &bstatus, 1); + if (ret != 1) { + drm_dbg_kms(&i915->drm, + "Read bstatus from DP/AUX failed (%zd)\n", ret); + return false; + } + + return !(bstatus & (DP_BSTATUS_LINK_FAILURE | DP_BSTATUS_REAUTH_REQ)); +} + +static +int intel_dp_hdcp_capable(struct intel_digital_port *dig_port, + bool *hdcp_capable) +{ + ssize_t ret; + u8 bcaps; + + ret = intel_dp_hdcp_read_bcaps(dig_port, &bcaps); + if (ret) + return ret; + + *hdcp_capable = bcaps & DP_BCAPS_HDCP_CAPABLE; + return 0; +} + +struct hdcp2_dp_errata_stream_type { + u8 msg_id; + u8 stream_type; +} __packed; + +struct hdcp2_dp_msg_data { + u8 msg_id; + u32 offset; + bool msg_detectable; + u32 timeout; + u32 timeout2; /* Added for non_paired situation */ +}; + +static const struct hdcp2_dp_msg_data hdcp2_dp_msg_data[] = { + { HDCP_2_2_AKE_INIT, DP_HDCP_2_2_AKE_INIT_OFFSET, false, 0, 0 }, + { HDCP_2_2_AKE_SEND_CERT, DP_HDCP_2_2_AKE_SEND_CERT_OFFSET, + false, HDCP_2_2_CERT_TIMEOUT_MS, 0 }, + { HDCP_2_2_AKE_NO_STORED_KM, DP_HDCP_2_2_AKE_NO_STORED_KM_OFFSET, + false, 0, 0 }, + { HDCP_2_2_AKE_STORED_KM, DP_HDCP_2_2_AKE_STORED_KM_OFFSET, + false, 0, 0 }, + { HDCP_2_2_AKE_SEND_HPRIME, DP_HDCP_2_2_AKE_SEND_HPRIME_OFFSET, + true, HDCP_2_2_HPRIME_PAIRED_TIMEOUT_MS, + HDCP_2_2_HPRIME_NO_PAIRED_TIMEOUT_MS }, + { HDCP_2_2_AKE_SEND_PAIRING_INFO, + DP_HDCP_2_2_AKE_SEND_PAIRING_INFO_OFFSET, true, + HDCP_2_2_PAIRING_TIMEOUT_MS, 0 }, + { HDCP_2_2_LC_INIT, DP_HDCP_2_2_LC_INIT_OFFSET, false, 0, 0 }, + { HDCP_2_2_LC_SEND_LPRIME, DP_HDCP_2_2_LC_SEND_LPRIME_OFFSET, + false, HDCP_2_2_DP_LPRIME_TIMEOUT_MS, 0 }, + { HDCP_2_2_SKE_SEND_EKS, DP_HDCP_2_2_SKE_SEND_EKS_OFFSET, false, + 0, 0 }, + { HDCP_2_2_REP_SEND_RECVID_LIST, + DP_HDCP_2_2_REP_SEND_RECVID_LIST_OFFSET, true, + HDCP_2_2_RECVID_LIST_TIMEOUT_MS, 0 }, + { HDCP_2_2_REP_SEND_ACK, DP_HDCP_2_2_REP_SEND_ACK_OFFSET, false, + 0, 0 }, + { HDCP_2_2_REP_STREAM_MANAGE, + DP_HDCP_2_2_REP_STREAM_MANAGE_OFFSET, false, + 0, 0 }, + { HDCP_2_2_REP_STREAM_READY, DP_HDCP_2_2_REP_STREAM_READY_OFFSET, + false, HDCP_2_2_STREAM_READY_TIMEOUT_MS, 0 }, +/* local define to shovel this through the write_2_2 interface */ +#define HDCP_2_2_ERRATA_DP_STREAM_TYPE 50 + { HDCP_2_2_ERRATA_DP_STREAM_TYPE, + DP_HDCP_2_2_REG_STREAM_TYPE_OFFSET, false, + 0, 0 }, +}; + +static int +intel_dp_hdcp2_read_rx_status(struct intel_digital_port *dig_port, + u8 *rx_status) +{ + struct drm_i915_private *i915 = to_i915(dig_port->base.base.dev); + ssize_t ret; + + ret = drm_dp_dpcd_read(&dig_port->dp.aux, + DP_HDCP_2_2_REG_RXSTATUS_OFFSET, rx_status, + HDCP_2_2_DP_RXSTATUS_LEN); + if (ret != HDCP_2_2_DP_RXSTATUS_LEN) { + drm_dbg_kms(&i915->drm, + "Read bstatus from DP/AUX failed (%zd)\n", ret); + return ret >= 0 ? -EIO : ret; + } + + return 0; +} + +static +int hdcp2_detect_msg_availability(struct intel_digital_port *dig_port, + u8 msg_id, bool *msg_ready) +{ + u8 rx_status; + int ret; + + *msg_ready = false; + ret = intel_dp_hdcp2_read_rx_status(dig_port, &rx_status); + if (ret < 0) + return ret; + + switch (msg_id) { + case HDCP_2_2_AKE_SEND_HPRIME: + if (HDCP_2_2_DP_RXSTATUS_H_PRIME(rx_status)) + *msg_ready = true; + break; + case HDCP_2_2_AKE_SEND_PAIRING_INFO: + if (HDCP_2_2_DP_RXSTATUS_PAIRING(rx_status)) + *msg_ready = true; + break; + case HDCP_2_2_REP_SEND_RECVID_LIST: + if (HDCP_2_2_DP_RXSTATUS_READY(rx_status)) + *msg_ready = true; + break; + default: + DRM_ERROR("Unidentified msg_id: %d\n", msg_id); + return -EINVAL; + } + + return 0; +} + +static ssize_t +intel_dp_hdcp2_wait_for_msg(struct intel_digital_port *dig_port, + const struct hdcp2_dp_msg_data *hdcp2_msg_data) +{ + struct drm_i915_private *i915 = to_i915(dig_port->base.base.dev); + struct intel_dp *dp = &dig_port->dp; + struct intel_hdcp *hdcp = &dp->attached_connector->hdcp; + u8 msg_id = hdcp2_msg_data->msg_id; + int ret, timeout; + bool msg_ready = false; + + if (msg_id == HDCP_2_2_AKE_SEND_HPRIME && !hdcp->is_paired) + timeout = hdcp2_msg_data->timeout2; + else + timeout = hdcp2_msg_data->timeout; + + /* + * There is no way to detect the CERT, LPRIME and STREAM_READY + * availability. So Wait for timeout and read the msg. + */ + if (!hdcp2_msg_data->msg_detectable) { + mdelay(timeout); + ret = 0; + } else { + /* + * As we want to check the msg availability at timeout, Ignoring + * the timeout at wait for CP_IRQ. + */ + intel_dp_hdcp_wait_for_cp_irq(hdcp, timeout); + ret = hdcp2_detect_msg_availability(dig_port, + msg_id, &msg_ready); + if (!msg_ready) + ret = -ETIMEDOUT; + } + + if (ret) + drm_dbg_kms(&i915->drm, + "msg_id %d, ret %d, timeout(mSec): %d\n", + hdcp2_msg_data->msg_id, ret, timeout); + + return ret; +} + +static const struct hdcp2_dp_msg_data *get_hdcp2_dp_msg_data(u8 msg_id) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(hdcp2_dp_msg_data); i++) + if (hdcp2_dp_msg_data[i].msg_id == msg_id) + return &hdcp2_dp_msg_data[i]; + + return NULL; +} + +static +int intel_dp_hdcp2_write_msg(struct intel_digital_port *dig_port, + void *buf, size_t size) +{ + struct intel_dp *dp = &dig_port->dp; + struct intel_hdcp *hdcp = &dp->attached_connector->hdcp; + unsigned int offset; + u8 *byte = buf; + ssize_t ret, bytes_to_write, len; + const struct hdcp2_dp_msg_data *hdcp2_msg_data; + + hdcp2_msg_data = get_hdcp2_dp_msg_data(*byte); + if (!hdcp2_msg_data) + return -EINVAL; + + offset = hdcp2_msg_data->offset; + + /* No msg_id in DP HDCP2.2 msgs */ + bytes_to_write = size - 1; + byte++; + + hdcp->cp_irq_count_cached = atomic_read(&hdcp->cp_irq_count); + + while (bytes_to_write) { + len = bytes_to_write > DP_AUX_MAX_PAYLOAD_BYTES ? + DP_AUX_MAX_PAYLOAD_BYTES : bytes_to_write; + + ret = drm_dp_dpcd_write(&dig_port->dp.aux, + offset, (void *)byte, len); + if (ret < 0) + return ret; + + bytes_to_write -= ret; + byte += ret; + offset += ret; + } + + return size; +} + +static +ssize_t get_receiver_id_list_size(struct intel_digital_port *dig_port) +{ + u8 rx_info[HDCP_2_2_RXINFO_LEN]; + u32 dev_cnt; + ssize_t ret; + + ret = drm_dp_dpcd_read(&dig_port->dp.aux, + DP_HDCP_2_2_REG_RXINFO_OFFSET, + (void *)rx_info, HDCP_2_2_RXINFO_LEN); + if (ret != HDCP_2_2_RXINFO_LEN) + return ret >= 0 ? -EIO : ret; + + dev_cnt = (HDCP_2_2_DEV_COUNT_HI(rx_info[0]) << 4 | + HDCP_2_2_DEV_COUNT_LO(rx_info[1])); + + if (dev_cnt > HDCP_2_2_MAX_DEVICE_COUNT) + dev_cnt = HDCP_2_2_MAX_DEVICE_COUNT; + + ret = sizeof(struct hdcp2_rep_send_receiverid_list) - + HDCP_2_2_RECEIVER_IDS_MAX_LEN + + (dev_cnt * HDCP_2_2_RECEIVER_ID_LEN); + + return ret; +} + +static +int intel_dp_hdcp2_read_msg(struct intel_digital_port *dig_port, + u8 msg_id, void *buf, size_t size) +{ + struct drm_i915_private *i915 = to_i915(dig_port->base.base.dev); + unsigned int offset; + u8 *byte = buf; + ssize_t ret, bytes_to_recv, len; + const struct hdcp2_dp_msg_data *hdcp2_msg_data; + + hdcp2_msg_data = get_hdcp2_dp_msg_data(msg_id); + if (!hdcp2_msg_data) + return -EINVAL; + offset = hdcp2_msg_data->offset; + + ret = intel_dp_hdcp2_wait_for_msg(dig_port, hdcp2_msg_data); + if (ret < 0) + return ret; + + if (msg_id == HDCP_2_2_REP_SEND_RECVID_LIST) { + ret = get_receiver_id_list_size(dig_port); + if (ret < 0) + return ret; + + size = ret; + } + bytes_to_recv = size - 1; + + /* DP adaptation msgs has no msg_id */ + byte++; + + while (bytes_to_recv) { + len = bytes_to_recv > DP_AUX_MAX_PAYLOAD_BYTES ? + DP_AUX_MAX_PAYLOAD_BYTES : bytes_to_recv; + + ret = drm_dp_dpcd_read(&dig_port->dp.aux, offset, + (void *)byte, len); + if (ret < 0) { + drm_dbg_kms(&i915->drm, "msg_id %d, ret %zd\n", + msg_id, ret); + return ret; + } + + bytes_to_recv -= ret; + byte += ret; + offset += ret; + } + byte = buf; + *byte = msg_id; + + return size; +} + +static +int intel_dp_hdcp2_config_stream_type(struct intel_digital_port *dig_port, + bool is_repeater, u8 content_type) +{ + int ret; + struct hdcp2_dp_errata_stream_type stream_type_msg; + + if (is_repeater) + return 0; + + /* + * Errata for DP: As Stream type is used for encryption, Receiver + * should be communicated with stream type for the decryption of the + * content. + * Repeater will be communicated with stream type as a part of it's + * auth later in time. + */ + stream_type_msg.msg_id = HDCP_2_2_ERRATA_DP_STREAM_TYPE; + stream_type_msg.stream_type = content_type; + + ret = intel_dp_hdcp2_write_msg(dig_port, &stream_type_msg, + sizeof(stream_type_msg)); + + return ret < 0 ? ret : 0; + +} + +static +int intel_dp_hdcp2_check_link(struct intel_digital_port *dig_port) +{ + u8 rx_status; + int ret; + + ret = intel_dp_hdcp2_read_rx_status(dig_port, &rx_status); + if (ret) + return ret; + + if (HDCP_2_2_DP_RXSTATUS_REAUTH_REQ(rx_status)) + ret = HDCP_REAUTH_REQUEST; + else if (HDCP_2_2_DP_RXSTATUS_LINK_FAILED(rx_status)) + ret = HDCP_LINK_INTEGRITY_FAILURE; + else if (HDCP_2_2_DP_RXSTATUS_READY(rx_status)) + ret = HDCP_TOPOLOGY_CHANGE; + + return ret; +} + +static +int intel_dp_hdcp2_capable(struct intel_digital_port *dig_port, + bool *capable) +{ + u8 rx_caps[3]; + int ret; + + *capable = false; + ret = drm_dp_dpcd_read(&dig_port->dp.aux, + DP_HDCP_2_2_REG_RX_CAPS_OFFSET, + rx_caps, HDCP_2_2_RXCAPS_LEN); + if (ret != HDCP_2_2_RXCAPS_LEN) + return ret >= 0 ? -EIO : ret; + + if (rx_caps[0] == HDCP_2_2_RX_CAPS_VERSION_VAL && + HDCP_2_2_DP_HDCP_CAPABLE(rx_caps[2])) + *capable = true; + + return 0; +} + +static const struct intel_hdcp_shim intel_dp_hdcp_shim = { + .write_an_aksv = intel_dp_hdcp_write_an_aksv, + .read_bksv = intel_dp_hdcp_read_bksv, + .read_bstatus = intel_dp_hdcp_read_bstatus, + .repeater_present = intel_dp_hdcp_repeater_present, + .read_ri_prime = intel_dp_hdcp_read_ri_prime, + .read_ksv_ready = intel_dp_hdcp_read_ksv_ready, + .read_ksv_fifo = intel_dp_hdcp_read_ksv_fifo, + .read_v_prime_part = intel_dp_hdcp_read_v_prime_part, + .toggle_signalling = intel_dp_hdcp_toggle_signalling, + .check_link = intel_dp_hdcp_check_link, + .hdcp_capable = intel_dp_hdcp_capable, + .write_2_2_msg = intel_dp_hdcp2_write_msg, + .read_2_2_msg = intel_dp_hdcp2_read_msg, + .config_stream_type = intel_dp_hdcp2_config_stream_type, + .check_2_2_link = intel_dp_hdcp2_check_link, + .hdcp_2_2_capable = intel_dp_hdcp2_capable, + .protocol = HDCP_PROTOCOL_DP, +}; + +static int +intel_dp_mst_hdcp_toggle_signalling(struct intel_digital_port *dig_port, + enum transcoder cpu_transcoder, + bool enable) +{ + struct drm_i915_private *i915 = to_i915(dig_port->base.base.dev); + int ret; + + if (!enable) + usleep_range(6, 60); /* Bspec says >= 6us */ + + ret = intel_ddi_toggle_hdcp_signalling(&dig_port->base, + cpu_transcoder, enable); + if (ret) + drm_dbg_kms(&i915->drm, "%s HDCP signalling failed (%d)\n", + enable ? "Enable" : "Disable", ret); + return ret; +} + +static +bool intel_dp_mst_hdcp_check_link(struct intel_digital_port *dig_port, + struct intel_connector *connector) +{ + struct drm_i915_private *i915 = to_i915(dig_port->base.base.dev); + struct intel_dp *intel_dp = &dig_port->dp; + struct drm_dp_query_stream_enc_status_ack_reply reply; + int ret; + + if (!intel_dp_hdcp_check_link(dig_port, connector)) + return false; + + ret = drm_dp_send_query_stream_enc_status(&intel_dp->mst_mgr, + connector->port, &reply); + if (ret) { + drm_dbg_kms(&i915->drm, + "[CONNECTOR:%d:%s] failed QSES ret=%d\n", + connector->base.base.id, connector->base.name, ret); + return false; + } + + return reply.auth_completed && reply.encryption_enabled; +} + +static const struct intel_hdcp_shim intel_dp_mst_hdcp_shim = { + .write_an_aksv = intel_dp_hdcp_write_an_aksv, + .read_bksv = intel_dp_hdcp_read_bksv, + .read_bstatus = intel_dp_hdcp_read_bstatus, + .repeater_present = intel_dp_hdcp_repeater_present, + .read_ri_prime = intel_dp_hdcp_read_ri_prime, + .read_ksv_ready = intel_dp_hdcp_read_ksv_ready, + .read_ksv_fifo = intel_dp_hdcp_read_ksv_fifo, + .read_v_prime_part = intel_dp_hdcp_read_v_prime_part, + .toggle_signalling = intel_dp_mst_hdcp_toggle_signalling, + .check_link = intel_dp_mst_hdcp_check_link, + .hdcp_capable = intel_dp_hdcp_capable, + + .protocol = HDCP_PROTOCOL_DP, +}; + +int intel_dp_init_hdcp(struct intel_digital_port *dig_port, + struct intel_connector *intel_connector) +{ + struct drm_device *dev = intel_connector->base.dev; + struct drm_i915_private *dev_priv = to_i915(dev); + struct intel_encoder *intel_encoder = &dig_port->base; + enum port port = intel_encoder->port; + struct intel_dp *intel_dp = &dig_port->dp; + + if (!is_hdcp_supported(dev_priv, port)) + return 0; + + if (intel_connector->mst_port) + return intel_hdcp_init(intel_connector, port, + &intel_dp_mst_hdcp_shim); + else if (!intel_dp_is_edp(intel_dp)) + return intel_hdcp_init(intel_connector, port, + &intel_dp_hdcp_shim); + + return 0; +} diff --git a/drivers/gpu/drm/i915/display/intel_dp_mst.c b/drivers/gpu/drm/i915/display/intel_dp_mst.c index a2d91a499700..64d885539e94 100644 --- a/drivers/gpu/drm/i915/display/intel_dp_mst.c +++ b/drivers/gpu/drm/i915/display/intel_dp_mst.c @@ -37,6 +37,7 @@ #include "intel_dp.h" #include "intel_dp_mst.h" #include "intel_dpio_phy.h" +#include "intel_hdcp.h" static int intel_dp_mst_compute_link_config(struct intel_encoder *encoder, struct intel_crtc_state *crtc_state, @@ -352,6 +353,8 @@ static void intel_mst_disable_dp(struct intel_atomic_state *state, drm_dbg_kms(&i915->drm, "active links %d\n", intel_dp->active_mst_links); + intel_hdcp_disable(intel_mst->connector); + drm_dp_mst_reset_vcpi_slots(&intel_dp->mst_mgr, connector->port); ret = drm_dp_update_payload_part1(&intel_dp->mst_mgr); @@ -556,6 +559,13 @@ static void intel_mst_enable_dp(struct intel_atomic_state *state, if (pipe_config->has_audio) intel_audio_codec_enable(encoder, pipe_config, conn_state); + + /* Enable hdcp if it's desired */ + if (conn_state->content_protection == + DRM_MODE_CONTENT_PROTECTION_DESIRED) + intel_hdcp_enable(to_intel_connector(conn_state->connector), + pipe_config->cpu_transcoder, + (u8)conn_state->hdcp_content_type); } static bool intel_dp_mst_enc_get_hw_state(struct intel_encoder *encoder, @@ -709,9 +719,13 @@ static int intel_dp_mst_detect(struct drm_connector *connector, struct drm_modeset_acquire_ctx *ctx, bool force) { + struct drm_i915_private *i915 = to_i915(connector->dev); struct intel_connector *intel_connector = to_intel_connector(connector); struct intel_dp *intel_dp = intel_connector->mst_port; + if (!INTEL_DISPLAY_ENABLED(i915)) + return connector_status_disconnected; + if (drm_connector_is_unregistered(connector)) return connector_status_disconnected; @@ -799,6 +813,14 @@ static struct drm_connector *intel_dp_add_mst_connector(struct drm_dp_mst_topolo intel_attach_force_audio_property(connector); intel_attach_broadcast_rgb_property(connector); + + /* TODO: Figure out how to make HDCP work on GEN12+ */ + if (INTEL_GEN(dev_priv) < 12) { + ret = intel_dp_init_hdcp(dig_port, intel_connector); + if (ret) + DRM_DEBUG_KMS("HDCP init failed, skipping.\n"); + } + /* * Reuse the prop from the SST connector because we're * not allowed to create new props after device registration. @@ -865,6 +887,7 @@ intel_dp_create_fake_mst_encoder(struct intel_digital_port *dig_port, enum pipe intel_encoder->compute_config_late = intel_dp_mst_compute_config_late; intel_encoder->disable = intel_mst_disable_dp; intel_encoder->post_disable = intel_mst_post_disable_dp; + intel_encoder->update_pipe = intel_ddi_update_pipe; intel_encoder->pre_pll_enable = intel_mst_pre_pll_enable_dp; intel_encoder->pre_enable = intel_mst_pre_enable_dp; intel_encoder->enable = intel_mst_enable_dp; diff --git a/drivers/gpu/drm/i915/display/intel_dpll_mgr.c b/drivers/gpu/drm/i915/display/intel_dpll_mgr.c index c9013f8f766f..e08684e34078 100644 --- a/drivers/gpu/drm/i915/display/intel_dpll_mgr.c +++ b/drivers/gpu/drm/i915/display/intel_dpll_mgr.c @@ -147,6 +147,18 @@ void assert_shared_dpll(struct drm_i915_private *dev_priv, pll->info->name, onoff(state), onoff(cur_state)); } +static i915_reg_t +intel_combo_pll_enable_reg(struct drm_i915_private *i915, + struct intel_shared_dpll *pll) +{ + + if (IS_ELKHARTLAKE(i915) && (pll->info->id == DPLL_ID_EHL_DPLL4)) + return MG_PLL_ENABLE(0); + + return CNL_DPLL_ENABLE(pll->info->id); + + +} /** * intel_prepare_shared_dpll - call a dpll's prepare hook * @crtc_state: CRTC, and its state, which has a shared dpll @@ -3842,12 +3854,7 @@ static bool combo_pll_get_hw_state(struct drm_i915_private *dev_priv, struct intel_shared_dpll *pll, struct intel_dpll_hw_state *hw_state) { - i915_reg_t enable_reg = CNL_DPLL_ENABLE(pll->info->id); - - if (IS_ELKHARTLAKE(dev_priv) && - pll->info->id == DPLL_ID_EHL_DPLL4) { - enable_reg = MG_PLL_ENABLE(0); - } + i915_reg_t enable_reg = intel_combo_pll_enable_reg(dev_priv, pll); return icl_pll_get_hw_state(dev_priv, pll, hw_state, enable_reg); } @@ -4045,11 +4052,10 @@ static void icl_pll_enable(struct drm_i915_private *dev_priv, static void combo_pll_enable(struct drm_i915_private *dev_priv, struct intel_shared_dpll *pll) { - i915_reg_t enable_reg = CNL_DPLL_ENABLE(pll->info->id); + i915_reg_t enable_reg = intel_combo_pll_enable_reg(dev_priv, pll); if (IS_ELKHARTLAKE(dev_priv) && pll->info->id == DPLL_ID_EHL_DPLL4) { - enable_reg = MG_PLL_ENABLE(0); /* * We need to disable DC states when this DPLL is enabled. @@ -4157,19 +4163,14 @@ static void icl_pll_disable(struct drm_i915_private *dev_priv, static void combo_pll_disable(struct drm_i915_private *dev_priv, struct intel_shared_dpll *pll) { - i915_reg_t enable_reg = CNL_DPLL_ENABLE(pll->info->id); + i915_reg_t enable_reg = intel_combo_pll_enable_reg(dev_priv, pll); - if (IS_ELKHARTLAKE(dev_priv) && - pll->info->id == DPLL_ID_EHL_DPLL4) { - enable_reg = MG_PLL_ENABLE(0); - icl_pll_disable(dev_priv, pll, enable_reg); + icl_pll_disable(dev_priv, pll, enable_reg); + if (IS_ELKHARTLAKE(dev_priv) && + pll->info->id == DPLL_ID_EHL_DPLL4) intel_display_power_put(dev_priv, POWER_DOMAIN_DPLL_DC_OFF, pll->wakeref); - return; - } - - icl_pll_disable(dev_priv, pll, enable_reg); } static void tbt_pll_disable(struct drm_i915_private *dev_priv, diff --git a/drivers/gpu/drm/i915/display/intel_dvo.c b/drivers/gpu/drm/i915/display/intel_dvo.c index 307ed8ae9a19..237dbb1ba0ee 100644 --- a/drivers/gpu/drm/i915/display/intel_dvo.c +++ b/drivers/gpu/drm/i915/display/intel_dvo.c @@ -313,9 +313,15 @@ static void intel_dvo_pre_enable(struct intel_atomic_state *state, static enum drm_connector_status intel_dvo_detect(struct drm_connector *connector, bool force) { + struct drm_i915_private *i915 = to_i915(connector->dev); struct intel_dvo *intel_dvo = intel_attached_dvo(to_intel_connector(connector)); + DRM_DEBUG_KMS("[CONNECTOR:%d:%s]\n", connector->base.id, connector->name); + + if (!INTEL_DISPLAY_ENABLED(i915)) + return connector_status_disconnected; + return intel_dvo->dev.dev_ops->detect(&intel_dvo->dev); } diff --git a/drivers/gpu/drm/i915/display/intel_fbdev.c b/drivers/gpu/drm/i915/display/intel_fbdev.c index bd39eb6a21b8..842c04e63214 100644 --- a/drivers/gpu/drm/i915/display/intel_fbdev.c +++ b/drivers/gpu/drm/i915/display/intel_fbdev.c @@ -451,8 +451,7 @@ int intel_fbdev_init(struct drm_device *dev) struct intel_fbdev *ifbdev; int ret; - if (drm_WARN_ON(dev, !HAS_DISPLAY(dev_priv) || - !INTEL_DISPLAY_ENABLED(dev_priv))) + if (drm_WARN_ON(dev, !HAS_DISPLAY(dev_priv))) return -ENODEV; ifbdev = kzalloc(sizeof(struct intel_fbdev), GFP_KERNEL); diff --git a/drivers/gpu/drm/i915/display/intel_gmbus.c b/drivers/gpu/drm/i915/display/intel_gmbus.c index a8d119b6b45c..e6b8d6dfb598 100644 --- a/drivers/gpu/drm/i915/display/intel_gmbus.c +++ b/drivers/gpu/drm/i915/display/intel_gmbus.c @@ -834,7 +834,7 @@ int intel_gmbus_setup(struct drm_i915_private *dev_priv) unsigned int pin; int ret; - if (!HAS_DISPLAY(dev_priv) || !INTEL_DISPLAY_ENABLED(dev_priv)) + if (!HAS_DISPLAY(dev_priv)) return 0; if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) diff --git a/drivers/gpu/drm/i915/display/intel_hdcp.c b/drivers/gpu/drm/i915/display/intel_hdcp.c index 1a0d49af2a08..5492076d1ae0 100644 --- a/drivers/gpu/drm/i915/display/intel_hdcp.c +++ b/drivers/gpu/drm/i915/display/intel_hdcp.c @@ -148,9 +148,8 @@ static int intel_hdcp_poll_ksv_fifo(struct intel_digital_port *dig_port, static bool hdcp_key_loadable(struct drm_i915_private *dev_priv) { - struct i915_power_domains *power_domains = &dev_priv->power_domains; - struct i915_power_well *power_well; enum i915_power_well_id id; + intel_wakeref_t wakeref; bool enabled = false; /* @@ -162,17 +161,9 @@ static bool hdcp_key_loadable(struct drm_i915_private *dev_priv) else id = SKL_DISP_PW_1; - mutex_lock(&power_domains->lock); - /* PG1 (power well #1) needs to be enabled */ - for_each_power_well(dev_priv, power_well) { - if (power_well->desc->id == id) { - enabled = power_well->desc->ops->is_enabled(dev_priv, - power_well); - break; - } - } - mutex_unlock(&power_domains->lock); + with_intel_runtime_pm(&dev_priv->runtime_pm, wakeref) + enabled = intel_display_power_well_is_enabled(dev_priv, id); /* * Another req for hdcp key loadability is enabled state of pll for @@ -713,7 +704,7 @@ static int intel_hdcp_auth(struct intel_connector *connector) intel_de_write(dev_priv, HDCP_REP_CTL, intel_hdcp_get_repeater_ctl(dev_priv, cpu_transcoder, port)); - ret = shim->toggle_signalling(dig_port, true); + ret = shim->toggle_signalling(dig_port, cpu_transcoder, true); if (ret) return ret; @@ -801,6 +792,19 @@ static int _intel_hdcp_disable(struct intel_connector *connector) drm_dbg_kms(&dev_priv->drm, "[%s:%d] HDCP is being disabled...\n", connector->base.name, connector->base.base.id); + /* + * If there are other connectors on this port using HDCP, don't disable + * it. Instead, toggle the HDCP signalling off on that particular + * connector/pipe and exit. + */ + if (dig_port->num_hdcp_streams > 0) { + ret = hdcp->shim->toggle_signalling(dig_port, + cpu_transcoder, false); + if (ret) + DRM_ERROR("Failed to disable HDCP signalling\n"); + return ret; + } + hdcp->hdcp_encrypted = false; intel_de_write(dev_priv, HDCP_CONF(dev_priv, cpu_transcoder, port), 0); if (intel_de_wait_for_clear(dev_priv, @@ -816,7 +820,7 @@ static int _intel_hdcp_disable(struct intel_connector *connector) intel_de_write(dev_priv, HDCP_REP_CTL, intel_de_read(dev_priv, HDCP_REP_CTL) & ~repeater_ctl); - ret = hdcp->shim->toggle_signalling(dig_port, false); + ret = hdcp->shim->toggle_signalling(dig_port, cpu_transcoder, false); if (ret) { drm_err(&dev_priv->drm, "Failed to disable HDCP signalling\n"); return ret; @@ -876,6 +880,34 @@ static struct intel_connector *intel_hdcp_to_connector(struct intel_hdcp *hdcp) return container_of(hdcp, struct intel_connector, hdcp); } +static void intel_hdcp_update_value(struct intel_connector *connector, + u64 value, bool update_property) +{ + struct drm_device *dev = connector->base.dev; + struct intel_digital_port *dig_port = intel_attached_dig_port(connector); + struct intel_hdcp *hdcp = &connector->hdcp; + + drm_WARN_ON(connector->base.dev, !mutex_is_locked(&hdcp->mutex)); + + if (hdcp->value == value) + return; + + drm_WARN_ON(dev, !mutex_is_locked(&dig_port->hdcp_mutex)); + + if (hdcp->value == DRM_MODE_CONTENT_PROTECTION_ENABLED) { + if (!drm_WARN_ON(dev, dig_port->num_hdcp_streams == 0)) + dig_port->num_hdcp_streams--; + } else if (value == DRM_MODE_CONTENT_PROTECTION_ENABLED) { + dig_port->num_hdcp_streams++; + } + + hdcp->value = value; + if (update_property) { + drm_connector_get(&connector->base); + schedule_work(&hdcp->prop_work); + } +} + /* Implements Part 3 of the HDCP authorization procedure */ static int intel_hdcp_check_link(struct intel_connector *connector) { @@ -887,6 +919,8 @@ static int intel_hdcp_check_link(struct intel_connector *connector) int ret = 0; mutex_lock(&hdcp->mutex); + mutex_lock(&dig_port->hdcp_mutex); + cpu_transcoder = hdcp->cpu_transcoder; /* Check_link valid only when HDCP1.4 is enabled */ @@ -903,15 +937,16 @@ static int intel_hdcp_check_link(struct intel_connector *connector) connector->base.name, connector->base.base.id, intel_de_read(dev_priv, HDCP_STATUS(dev_priv, cpu_transcoder, port))); ret = -ENXIO; - hdcp->value = DRM_MODE_CONTENT_PROTECTION_DESIRED; - schedule_work(&hdcp->prop_work); + intel_hdcp_update_value(connector, + DRM_MODE_CONTENT_PROTECTION_DESIRED, + true); goto out; } - if (hdcp->shim->check_link(dig_port)) { + if (hdcp->shim->check_link(dig_port, connector)) { if (hdcp->value != DRM_MODE_CONTENT_PROTECTION_UNDESIRED) { - hdcp->value = DRM_MODE_CONTENT_PROTECTION_ENABLED; - schedule_work(&hdcp->prop_work); + intel_hdcp_update_value(connector, + DRM_MODE_CONTENT_PROTECTION_ENABLED, true); } goto out; } @@ -923,20 +958,23 @@ static int intel_hdcp_check_link(struct intel_connector *connector) ret = _intel_hdcp_disable(connector); if (ret) { drm_err(&dev_priv->drm, "Failed to disable hdcp (%d)\n", ret); - hdcp->value = DRM_MODE_CONTENT_PROTECTION_DESIRED; - schedule_work(&hdcp->prop_work); + intel_hdcp_update_value(connector, + DRM_MODE_CONTENT_PROTECTION_DESIRED, + true); goto out; } ret = _intel_hdcp_enable(connector); if (ret) { drm_err(&dev_priv->drm, "Failed to enable hdcp (%d)\n", ret); - hdcp->value = DRM_MODE_CONTENT_PROTECTION_DESIRED; - schedule_work(&hdcp->prop_work); + intel_hdcp_update_value(connector, + DRM_MODE_CONTENT_PROTECTION_DESIRED, + true); goto out; } out: + mutex_unlock(&dig_port->hdcp_mutex); mutex_unlock(&hdcp->mutex); return ret; } @@ -962,6 +1000,8 @@ static void intel_hdcp_prop_work(struct work_struct *work) mutex_unlock(&hdcp->mutex); drm_modeset_unlock(&dev_priv->drm.mode_config.connection_mutex); + + drm_connector_put(&connector->base); } bool is_hdcp_supported(struct drm_i915_private *dev_priv, enum port port) @@ -1600,7 +1640,8 @@ static int hdcp2_enable_encryption(struct intel_connector *connector) intel_de_read(dev_priv, HDCP2_STATUS(dev_priv, cpu_transcoder, port)) & LINK_ENCRYPTION_STATUS); if (hdcp->shim->toggle_signalling) { - ret = hdcp->shim->toggle_signalling(dig_port, true); + ret = hdcp->shim->toggle_signalling(dig_port, cpu_transcoder, + true); if (ret) { drm_err(&dev_priv->drm, "Failed to enable HDCP signalling. %d\n", @@ -1650,7 +1691,8 @@ static int hdcp2_disable_encryption(struct intel_connector *connector) drm_dbg_kms(&dev_priv->drm, "Disable Encryption Timedout"); if (hdcp->shim->toggle_signalling) { - ret = hdcp->shim->toggle_signalling(dig_port, false); + ret = hdcp->shim->toggle_signalling(dig_port, cpu_transcoder, + false); if (ret) { drm_err(&dev_priv->drm, "Failed to disable HDCP signalling. %d\n", @@ -1766,16 +1808,18 @@ static int intel_hdcp2_check_link(struct intel_connector *connector) "HDCP2.2 link stopped the encryption, %x\n", intel_de_read(dev_priv, HDCP2_STATUS(dev_priv, cpu_transcoder, port))); ret = -ENXIO; - hdcp->value = DRM_MODE_CONTENT_PROTECTION_DESIRED; - schedule_work(&hdcp->prop_work); + intel_hdcp_update_value(connector, + DRM_MODE_CONTENT_PROTECTION_DESIRED, + true); goto out; } ret = hdcp->shim->check_2_2_link(dig_port); if (ret == HDCP_LINK_PROTECTED) { if (hdcp->value != DRM_MODE_CONTENT_PROTECTION_UNDESIRED) { - hdcp->value = DRM_MODE_CONTENT_PROTECTION_ENABLED; - schedule_work(&hdcp->prop_work); + intel_hdcp_update_value(connector, + DRM_MODE_CONTENT_PROTECTION_ENABLED, + true); } goto out; } @@ -1788,8 +1832,9 @@ static int intel_hdcp2_check_link(struct intel_connector *connector) "HDCP2.2 Downstream topology change\n"); ret = hdcp2_authenticate_repeater_topology(connector); if (!ret) { - hdcp->value = DRM_MODE_CONTENT_PROTECTION_ENABLED; - schedule_work(&hdcp->prop_work); + intel_hdcp_update_value(connector, + DRM_MODE_CONTENT_PROTECTION_ENABLED, + true); goto out; } drm_dbg_kms(&dev_priv->drm, @@ -1807,8 +1852,8 @@ static int intel_hdcp2_check_link(struct intel_connector *connector) drm_err(&dev_priv->drm, "[%s:%d] Failed to disable hdcp2.2 (%d)\n", connector->base.name, connector->base.base.id, ret); - hdcp->value = DRM_MODE_CONTENT_PROTECTION_DESIRED; - schedule_work(&hdcp->prop_work); + intel_hdcp_update_value(connector, + DRM_MODE_CONTENT_PROTECTION_DESIRED, true); goto out; } @@ -1818,8 +1863,9 @@ static int intel_hdcp2_check_link(struct intel_connector *connector) "[%s:%d] Failed to enable hdcp2.2 (%d)\n", connector->base.name, connector->base.base.id, ret); - hdcp->value = DRM_MODE_CONTENT_PROTECTION_DESIRED; - schedule_work(&hdcp->prop_work); + intel_hdcp_update_value(connector, + DRM_MODE_CONTENT_PROTECTION_DESIRED, + true); goto out; } @@ -1835,6 +1881,9 @@ static void intel_hdcp_check_work(struct work_struct *work) check_work); struct intel_connector *connector = intel_hdcp_to_connector(hdcp); + if (drm_connector_is_unregistered(&connector->base)) + return; + if (!intel_hdcp2_check_link(connector)) schedule_delayed_work(&hdcp->check_work, DRM_HDCP2_CHECK_PERIOD_MS); @@ -1896,6 +1945,7 @@ static enum mei_fw_tc intel_get_mei_fw_tc(enum transcoder cpu_transcoder) } static int initialize_hdcp_port_data(struct intel_connector *connector, + enum port port, const struct intel_hdcp_shim *shim) { struct drm_i915_private *dev_priv = to_i915(connector->base.dev); @@ -1903,8 +1953,7 @@ static int initialize_hdcp_port_data(struct intel_connector *connector, struct hdcp_port_data *data = &hdcp->port_data; if (INTEL_GEN(dev_priv) < 12) - data->fw_ddi = - intel_get_mei_fw_ddi_index(intel_attached_encoder(connector)->port); + data->fw_ddi = intel_get_mei_fw_ddi_index(port); else /* * As per ME FW API expectation, for GEN 12+, fw_ddi is filled @@ -1974,14 +2023,14 @@ void intel_hdcp_component_init(struct drm_i915_private *dev_priv) } } -static void intel_hdcp2_init(struct intel_connector *connector, +static void intel_hdcp2_init(struct intel_connector *connector, enum port port, const struct intel_hdcp_shim *shim) { struct drm_i915_private *i915 = to_i915(connector->base.dev); struct intel_hdcp *hdcp = &connector->hdcp; int ret; - ret = initialize_hdcp_port_data(connector, shim); + ret = initialize_hdcp_port_data(connector, port, shim); if (ret) { drm_dbg_kms(&i915->drm, "Mei hdcp data init failed\n"); return; @@ -1991,6 +2040,7 @@ static void intel_hdcp2_init(struct intel_connector *connector, } int intel_hdcp_init(struct intel_connector *connector, + enum port port, const struct intel_hdcp_shim *shim) { struct drm_i915_private *dev_priv = to_i915(connector->base.dev); @@ -2000,8 +2050,8 @@ int intel_hdcp_init(struct intel_connector *connector, if (!shim) return -EINVAL; - if (is_hdcp2_supported(dev_priv)) - intel_hdcp2_init(connector, shim); + if (is_hdcp2_supported(dev_priv) && !connector->mst_port) + intel_hdcp2_init(connector, port, shim); ret = drm_connector_attach_content_protection_property(&connector->base, @@ -2025,6 +2075,7 @@ int intel_hdcp_enable(struct intel_connector *connector, enum transcoder cpu_transcoder, u8 content_type) { struct drm_i915_private *dev_priv = to_i915(connector->base.dev); + struct intel_digital_port *dig_port = intel_attached_dig_port(connector); struct intel_hdcp *hdcp = &connector->hdcp; unsigned long check_link_interval = DRM_HDCP_CHECK_PERIOD_MS; int ret = -EINVAL; @@ -2033,14 +2084,14 @@ int intel_hdcp_enable(struct intel_connector *connector, return -ENOENT; mutex_lock(&hdcp->mutex); + mutex_lock(&dig_port->hdcp_mutex); drm_WARN_ON(&dev_priv->drm, hdcp->value == DRM_MODE_CONTENT_PROTECTION_ENABLED); hdcp->content_type = content_type; + hdcp->cpu_transcoder = cpu_transcoder; - if (INTEL_GEN(dev_priv) >= 12) { - hdcp->cpu_transcoder = cpu_transcoder; + if (INTEL_GEN(dev_priv) >= 12) hdcp->port_data.fw_tc = intel_get_mei_fw_tc(cpu_transcoder); - } /* * Considering that HDCP2.2 is more secure than HDCP1.4, If the setup @@ -2063,16 +2114,19 @@ int intel_hdcp_enable(struct intel_connector *connector, if (!ret) { schedule_delayed_work(&hdcp->check_work, check_link_interval); - hdcp->value = DRM_MODE_CONTENT_PROTECTION_ENABLED; - schedule_work(&hdcp->prop_work); + intel_hdcp_update_value(connector, + DRM_MODE_CONTENT_PROTECTION_ENABLED, + true); } + mutex_unlock(&dig_port->hdcp_mutex); mutex_unlock(&hdcp->mutex); return ret; } int intel_hdcp_disable(struct intel_connector *connector) { + struct intel_digital_port *dig_port = intel_attached_dig_port(connector); struct intel_hdcp *hdcp = &connector->hdcp; int ret = 0; @@ -2080,15 +2134,20 @@ int intel_hdcp_disable(struct intel_connector *connector) return -ENOENT; mutex_lock(&hdcp->mutex); + mutex_lock(&dig_port->hdcp_mutex); - if (hdcp->value != DRM_MODE_CONTENT_PROTECTION_UNDESIRED) { - hdcp->value = DRM_MODE_CONTENT_PROTECTION_UNDESIRED; - if (hdcp->hdcp2_encrypted) - ret = _intel_hdcp2_disable(connector); - else if (hdcp->hdcp_encrypted) - ret = _intel_hdcp_disable(connector); - } + if (hdcp->value == DRM_MODE_CONTENT_PROTECTION_UNDESIRED) + goto out; + + intel_hdcp_update_value(connector, + DRM_MODE_CONTENT_PROTECTION_UNDESIRED, false); + if (hdcp->hdcp2_encrypted) + ret = _intel_hdcp2_disable(connector); + else if (hdcp->hdcp_encrypted) + ret = _intel_hdcp_disable(connector); +out: + mutex_unlock(&dig_port->hdcp_mutex); mutex_unlock(&hdcp->mutex); cancel_delayed_work_sync(&hdcp->check_work); return ret; @@ -2102,11 +2161,15 @@ void intel_hdcp_update_pipe(struct intel_atomic_state *state, struct intel_connector *connector = to_intel_connector(conn_state->connector); struct intel_hdcp *hdcp = &connector->hdcp; - bool content_protection_type_changed = + bool content_protection_type_changed, desired_and_not_enabled = false; + + if (!connector->hdcp.shim) + return; + + content_protection_type_changed = (conn_state->hdcp_content_type != hdcp->content_type && conn_state->content_protection != DRM_MODE_CONTENT_PROTECTION_UNDESIRED); - bool desired_and_not_enabled = false; /* * During the HDCP encryption session if Type change is requested, @@ -2159,12 +2222,39 @@ void intel_hdcp_component_fini(struct drm_i915_private *dev_priv) void intel_hdcp_cleanup(struct intel_connector *connector) { - if (!connector->hdcp.shim) + struct intel_hdcp *hdcp = &connector->hdcp; + + if (!hdcp->shim) return; - mutex_lock(&connector->hdcp.mutex); - kfree(connector->hdcp.port_data.streams); - mutex_unlock(&connector->hdcp.mutex); + /* + * If the connector is registered, it's possible userspace could kick + * off another HDCP enable, which would re-spawn the workers. + */ + drm_WARN_ON(connector->base.dev, + connector->base.registration_state == DRM_CONNECTOR_REGISTERED); + + /* + * Now that the connector is not registered, check_work won't be run, + * but cancel any outstanding instances of it + */ + cancel_delayed_work_sync(&hdcp->check_work); + + /* + * We don't cancel prop_work in the same way as check_work since it + * requires connection_mutex which could be held while calling this + * function. Instead, we rely on the connector references grabbed before + * scheduling prop_work to ensure the connector is alive when prop_work + * is run. So if we're in the destroy path (which is where this + * function should be called), we're "guaranteed" that prop_work is not + * active (tl;dr This Should Never Happen). + */ + drm_WARN_ON(connector->base.dev, work_pending(&hdcp->prop_work)); + + mutex_lock(&hdcp->mutex); + kfree(hdcp->port_data.streams); + hdcp->shim = NULL; + mutex_unlock(&hdcp->mutex); } void intel_hdcp_atomic_check(struct drm_connector *connector, diff --git a/drivers/gpu/drm/i915/display/intel_hdcp.h b/drivers/gpu/drm/i915/display/intel_hdcp.h index 86bbaec120cc..1bbf5b67ed0a 100644 --- a/drivers/gpu/drm/i915/display/intel_hdcp.h +++ b/drivers/gpu/drm/i915/display/intel_hdcp.h @@ -22,7 +22,7 @@ enum transcoder; void intel_hdcp_atomic_check(struct drm_connector *connector, struct drm_connector_state *old_state, struct drm_connector_state *new_state); -int intel_hdcp_init(struct intel_connector *connector, +int intel_hdcp_init(struct intel_connector *connector, enum port port, const struct intel_hdcp_shim *hdcp_shim); int intel_hdcp_enable(struct intel_connector *connector, enum transcoder cpu_transcoder, u8 content_type); diff --git a/drivers/gpu/drm/i915/display/intel_hdmi.c b/drivers/gpu/drm/i915/display/intel_hdmi.c index de2ce5632b94..3f2008d845c2 100644 --- a/drivers/gpu/drm/i915/display/intel_hdmi.c +++ b/drivers/gpu/drm/i915/display/intel_hdmi.c @@ -1477,7 +1477,8 @@ int intel_hdmi_hdcp_read_v_prime_part(struct intel_digital_port *dig_port, return ret; } -static int kbl_repositioning_enc_en_signal(struct intel_connector *connector) +static int kbl_repositioning_enc_en_signal(struct intel_connector *connector, + enum transcoder cpu_transcoder) { struct drm_i915_private *dev_priv = to_i915(connector->base.dev); struct intel_digital_port *dig_port = intel_attached_dig_port(connector); @@ -1494,13 +1495,15 @@ static int kbl_repositioning_enc_en_signal(struct intel_connector *connector) usleep_range(25, 50); } - ret = intel_ddi_toggle_hdcp_signalling(&dig_port->base, false); + ret = intel_ddi_toggle_hdcp_signalling(&dig_port->base, cpu_transcoder, + false); if (ret) { drm_err(&dev_priv->drm, "Disable HDCP signalling failed (%d)\n", ret); return ret; } - ret = intel_ddi_toggle_hdcp_signalling(&dig_port->base, true); + ret = intel_ddi_toggle_hdcp_signalling(&dig_port->base, cpu_transcoder, + true); if (ret) { drm_err(&dev_priv->drm, "Enable HDCP signalling failed (%d)\n", ret); @@ -1512,6 +1515,7 @@ static int kbl_repositioning_enc_en_signal(struct intel_connector *connector) static int intel_hdmi_hdcp_toggle_signalling(struct intel_digital_port *dig_port, + enum transcoder cpu_transcoder, bool enable) { struct intel_hdmi *hdmi = &dig_port->hdmi; @@ -1522,7 +1526,8 @@ int intel_hdmi_hdcp_toggle_signalling(struct intel_digital_port *dig_port, if (!enable) usleep_range(6, 60); /* Bspec says >= 6us */ - ret = intel_ddi_toggle_hdcp_signalling(&dig_port->base, enable); + ret = intel_ddi_toggle_hdcp_signalling(&dig_port->base, cpu_transcoder, + enable); if (ret) { drm_err(&dev_priv->drm, "%s HDCP signalling failed (%d)\n", enable ? "Enable" : "Disable", ret); @@ -1534,17 +1539,17 @@ int intel_hdmi_hdcp_toggle_signalling(struct intel_digital_port *dig_port, * opportunity and enc_en signalling in KABYLAKE. */ if (IS_KABYLAKE(dev_priv) && enable) - return kbl_repositioning_enc_en_signal(connector); + return kbl_repositioning_enc_en_signal(connector, + cpu_transcoder); return 0; } static -bool intel_hdmi_hdcp_check_link_once(struct intel_digital_port *dig_port) +bool intel_hdmi_hdcp_check_link_once(struct intel_digital_port *dig_port, + struct intel_connector *connector) { struct drm_i915_private *i915 = to_i915(dig_port->base.base.dev); - struct intel_connector *connector = - dig_port->hdmi.attached_connector; enum port port = dig_port->base.port; enum transcoder cpu_transcoder = connector->hdcp.cpu_transcoder; int ret; @@ -1572,13 +1577,14 @@ bool intel_hdmi_hdcp_check_link_once(struct intel_digital_port *dig_port) } static -bool intel_hdmi_hdcp_check_link(struct intel_digital_port *dig_port) +bool intel_hdmi_hdcp_check_link(struct intel_digital_port *dig_port, + struct intel_connector *connector) { struct drm_i915_private *i915 = to_i915(dig_port->base.base.dev); int retry; for (retry = 0; retry < 3; retry++) - if (intel_hdmi_hdcp_check_link_once(dig_port)) + if (intel_hdmi_hdcp_check_link_once(dig_port, connector)) return true; drm_err(&i915->drm, "Link check failed\n"); @@ -2271,35 +2277,18 @@ intel_hdmi_mode_valid(struct drm_connector *connector, return intel_mode_valid_max_plane_size(dev_priv, mode); } -static bool hdmi_deep_color_possible(const struct intel_crtc_state *crtc_state, - int bpc) +bool intel_hdmi_deep_color_possible(const struct intel_crtc_state *crtc_state, + int bpc, bool has_hdmi_sink, bool ycbcr420_output) { - struct drm_i915_private *dev_priv = - to_i915(crtc_state->uapi.crtc->dev); struct drm_atomic_state *state = crtc_state->uapi.state; struct drm_connector_state *connector_state; struct drm_connector *connector; - const struct drm_display_mode *adjusted_mode = - &crtc_state->hw.adjusted_mode; int i; - if (HAS_GMCH(dev_priv)) - return false; - - if (bpc == 10 && INTEL_GEN(dev_priv) < 11) - return false; - if (crtc_state->pipe_bpp < bpc * 3) return false; - if (!crtc_state->has_hdmi_sink) - return false; - - /* - * HDMI deep color affects the clocks, so it's only possible - * when not cloning with other encoder types. - */ - if (crtc_state->output_types != 1 << INTEL_OUTPUT_HDMI) + if (!has_hdmi_sink) return false; for_each_new_connector_in_state(state, connector, connector_state, i) { @@ -2308,7 +2297,7 @@ static bool hdmi_deep_color_possible(const struct intel_crtc_state *crtc_state, if (connector_state->crtc != crtc_state->uapi.crtc) continue; - if (crtc_state->output_format == INTEL_OUTPUT_FORMAT_YCBCR420) { + if (ycbcr420_output) { const struct drm_hdmi_info *hdmi = &info->hdmi; if (bpc == 12 && !(hdmi->y420_dc_modes & @@ -2327,6 +2316,30 @@ static bool hdmi_deep_color_possible(const struct intel_crtc_state *crtc_state, } } + return true; +} + +static bool hdmi_deep_color_possible(const struct intel_crtc_state *crtc_state, + int bpc) +{ + struct drm_i915_private *dev_priv = + to_i915(crtc_state->uapi.crtc->dev); + const struct drm_display_mode *adjusted_mode = + &crtc_state->hw.adjusted_mode; + + if (HAS_GMCH(dev_priv)) + return false; + + if (bpc == 10 && INTEL_GEN(dev_priv) < 11) + return false; + + /* + * HDMI deep color affects the clocks, so it's only possible + * when not cloning with other encoder types. + */ + if (crtc_state->output_types != BIT(INTEL_OUTPUT_HDMI)) + return false; + /* Display Wa_1405510057:icl,ehl */ if (crtc_state->output_format == INTEL_OUTPUT_FORMAT_YCBCR420 && bpc == 10 && IS_GEN(dev_priv, 11) && @@ -2334,7 +2347,10 @@ static bool hdmi_deep_color_possible(const struct intel_crtc_state *crtc_state, adjusted_mode->crtc_hblank_start) % 8 == 2) return false; - return true; + return intel_hdmi_deep_color_possible(crtc_state, bpc, + crtc_state->has_hdmi_sink, + crtc_state->output_format == + INTEL_OUTPUT_FORMAT_YCBCR420); } static int @@ -2459,6 +2475,23 @@ bool intel_hdmi_limited_color_range(const struct intel_crtc_state *crtc_state, } } +static bool intel_hdmi_has_audio(struct intel_encoder *encoder, + const struct intel_crtc_state *crtc_state, + const struct drm_connector_state *conn_state) +{ + struct intel_hdmi *intel_hdmi = enc_to_intel_hdmi(encoder); + const struct intel_digital_connector_state *intel_conn_state = + to_intel_digital_connector_state(conn_state); + + if (!crtc_state->has_hdmi_sink) + return false; + + if (intel_conn_state->force_audio == HDMI_AUDIO_AUTO) + return intel_hdmi->has_audio; + else + return intel_conn_state->force_audio == HDMI_AUDIO_ON; +} + int intel_hdmi_compute_config(struct intel_encoder *encoder, struct intel_crtc_state *pipe_config, struct drm_connector_state *conn_state) @@ -2468,8 +2501,6 @@ int intel_hdmi_compute_config(struct intel_encoder *encoder, struct drm_display_mode *adjusted_mode = &pipe_config->hw.adjusted_mode; struct drm_connector *connector = conn_state->connector; struct drm_scdc *scdc = &connector->display_info.hdmi.scdc; - struct intel_digital_connector_state *intel_conn_state = - to_intel_digital_connector_state(conn_state); int ret; if (adjusted_mode->flags & DRM_MODE_FLAG_DBLSCAN) @@ -2495,13 +2526,8 @@ int intel_hdmi_compute_config(struct intel_encoder *encoder, if (HAS_PCH_SPLIT(dev_priv) && !HAS_DDI(dev_priv)) pipe_config->has_pch_encoder = true; - if (pipe_config->has_hdmi_sink) { - if (intel_conn_state->force_audio == HDMI_AUDIO_AUTO) - pipe_config->has_audio = intel_hdmi->has_audio; - else - pipe_config->has_audio = - intel_conn_state->force_audio == HDMI_AUDIO_ON; - } + pipe_config->has_audio = + intel_hdmi_has_audio(encoder, pipe_config, conn_state); ret = intel_hdmi_compute_clock(encoder, pipe_config); if (ret) @@ -2667,6 +2693,9 @@ intel_hdmi_detect(struct drm_connector *connector, bool force) drm_dbg_kms(&dev_priv->drm, "[CONNECTOR:%d:%s]\n", connector->base.id, connector->name); + if (!INTEL_DISPLAY_ENABLED(dev_priv)) + return connector_status_disconnected; + wakeref = intel_display_power_get(dev_priv, POWER_DOMAIN_GMBUS); if (INTEL_GEN(dev_priv) >= 11 && @@ -3250,7 +3279,6 @@ void intel_hdmi_init_connector(struct intel_digital_port *dig_port, if (INTEL_GEN(dev_priv) >= 10 || IS_GEMINILAKE(dev_priv)) connector->ycbcr_420_allowed = true; - intel_encoder->hpd_pin = intel_hpd_pin_default(dev_priv, port); intel_connector->polled = DRM_CONNECTOR_POLL_HPD; if (HAS_DDI(dev_priv)) @@ -3264,7 +3292,7 @@ void intel_hdmi_init_connector(struct intel_digital_port *dig_port, intel_hdmi->attached_connector = intel_connector; if (is_hdcp_supported(dev_priv, port)) { - int ret = intel_hdcp_init(intel_connector, + int ret = intel_hdcp_init(intel_connector, port, &intel_hdmi_hdcp_shim); if (ret) drm_dbg_kms(&dev_priv->drm, @@ -3335,6 +3363,8 @@ void intel_hdmi_init(struct drm_i915_private *dev_priv, intel_encoder = &dig_port->base; + mutex_init(&dig_port->hdcp_mutex); + drm_encoder_init(&dev_priv->drm, &intel_encoder->base, &intel_hdmi_enc_funcs, DRM_MODE_ENCODER_TMDS, "HDMI %c", port_name(port)); @@ -3382,6 +3412,7 @@ void intel_hdmi_init(struct drm_i915_private *dev_priv, intel_encoder->pipe_mask = ~0; } intel_encoder->cloneable = 1 << INTEL_OUTPUT_ANALOG; + intel_encoder->hpd_pin = intel_hpd_pin_default(dev_priv, port); /* * BSpec is unclear about HDMI+HDMI cloning on g4x, but it seems * to work on real hardware. And since g4x can send infoframes to diff --git a/drivers/gpu/drm/i915/display/intel_hdmi.h b/drivers/gpu/drm/i915/display/intel_hdmi.h index 5b348dcab77a..15eb0ccde76e 100644 --- a/drivers/gpu/drm/i915/display/intel_hdmi.h +++ b/drivers/gpu/drm/i915/display/intel_hdmi.h @@ -48,5 +48,7 @@ void intel_read_infoframe(struct intel_encoder *encoder, union hdmi_infoframe *frame); bool intel_hdmi_limited_color_range(const struct intel_crtc_state *crtc_state, const struct drm_connector_state *conn_state); +bool intel_hdmi_deep_color_possible(const struct intel_crtc_state *crtc_state, int bpc, + bool has_hdmi_sink, bool ycbcr420_output); #endif /* __INTEL_HDMI_H__ */ diff --git a/drivers/gpu/drm/i915/display/intel_hotplug.c b/drivers/gpu/drm/i915/display/intel_hotplug.c index 3f1d7b804a66..5c58c1ed6493 100644 --- a/drivers/gpu/drm/i915/display/intel_hotplug.c +++ b/drivers/gpu/drm/i915/display/intel_hotplug.c @@ -81,33 +81,12 @@ * * It is only valid and used by digital port encoder. * - * Return pin that is associatade with @port and HDP_NONE if no pin is - * hard associated with that @port. + * Return pin that is associatade with @port. */ enum hpd_pin intel_hpd_pin_default(struct drm_i915_private *dev_priv, enum port port) { - enum phy phy = intel_port_to_phy(dev_priv, port); - - /* - * RKL + TGP PCH is a special case; we effectively choose the hpd_pin - * based on the DDI rather than the PHY (i.e., the last two outputs - * shold be HPD_PORT_{D,E} rather than {C,D}. Note that this differs - * from the behavior of both TGL+TGP and RKL+CMP. - */ - if (IS_ROCKETLAKE(dev_priv) && HAS_PCH_TGP(dev_priv)) - return HPD_PORT_A + port - PORT_A; - - switch (phy) { - case PHY_F: - return IS_CNL_WITH_PORT_F(dev_priv) ? HPD_PORT_E : HPD_PORT_F; - case PHY_A ... PHY_E: - case PHY_G ... PHY_I: - return HPD_PORT_A + phy - PHY_A; - default: - MISSING_CASE(phy); - return HPD_NONE; - } + return HPD_PORT_A + port - PORT_A; } #define HPD_STORM_DETECT_PERIOD 1000 @@ -503,7 +482,6 @@ void intel_hpd_irq_handler(struct drm_i915_private *dev_priv, * only the one of them (DP) will have ->hpd_pulse(). */ for_each_intel_encoder(&dev_priv->drm, encoder) { - bool has_hpd_pulse = intel_encoder_has_hpd_pulse(encoder); enum port port = encoder->port; bool long_hpd; @@ -511,7 +489,7 @@ void intel_hpd_irq_handler(struct drm_i915_private *dev_priv, if (!(BIT(pin) & pin_mask)) continue; - if (!has_hpd_pulse) + if (!intel_encoder_has_hpd_pulse(encoder)) continue; long_hpd = long_mask & BIT(pin); diff --git a/drivers/gpu/drm/i915/display/intel_lvds.c b/drivers/gpu/drm/i915/display/intel_lvds.c index 1888611244db..e65c2de522c3 100644 --- a/drivers/gpu/drm/i915/display/intel_lvds.c +++ b/drivers/gpu/drm/i915/display/intel_lvds.c @@ -456,12 +456,6 @@ static int intel_lvds_compute_config(struct intel_encoder *intel_encoder, return 0; } -static enum drm_connector_status -intel_lvds_detect(struct drm_connector *connector, bool force) -{ - return connector_status_connected; -} - /* * Return the list of DDC modes if available, or the BIOS fixed mode otherwise. */ @@ -490,7 +484,7 @@ static const struct drm_connector_helper_funcs intel_lvds_connector_helper_funcs }; static const struct drm_connector_funcs intel_lvds_connector_funcs = { - .detect = intel_lvds_detect, + .detect = intel_panel_detect, .fill_modes = drm_helper_probe_single_connector_modes, .atomic_get_property = intel_digital_connector_atomic_get_property, .atomic_set_property = intel_digital_connector_atomic_set_property, diff --git a/drivers/gpu/drm/i915/display/intel_panel.c b/drivers/gpu/drm/i915/display/intel_panel.c index 4072d7062efd..9f23bac0d792 100644 --- a/drivers/gpu/drm/i915/display/intel_panel.c +++ b/drivers/gpu/drm/i915/display/intel_panel.c @@ -40,8 +40,6 @@ #include "intel_dsi_dcs_backlight.h" #include "intel_panel.h" -#define CRC_PMIC_PWM_PERIOD_NS 21333 - void intel_fixed_panel_mode(const struct drm_display_mode *fixed_mode, struct drm_display_mode *adjusted_mode) @@ -594,10 +592,10 @@ static u32 bxt_get_backlight(struct intel_connector *connector) static u32 pwm_get_backlight(struct intel_connector *connector) { struct intel_panel *panel = &connector->panel; - int duty_ns; + struct pwm_state state; - duty_ns = pwm_get_duty_cycle(panel->backlight.pwm); - return DIV_ROUND_UP(duty_ns * 100, CRC_PMIC_PWM_PERIOD_NS); + pwm_get_state(panel->backlight.pwm, &state); + return pwm_get_relative_duty_cycle(&state, 100); } static void lpt_set_backlight(const struct drm_connector_state *conn_state, u32 level) @@ -671,9 +669,9 @@ static void bxt_set_backlight(const struct drm_connector_state *conn_state, u32 static void pwm_set_backlight(const struct drm_connector_state *conn_state, u32 level) { struct intel_panel *panel = &to_intel_connector(conn_state->connector)->panel; - int duty_ns = DIV_ROUND_UP(level * CRC_PMIC_PWM_PERIOD_NS, 100); - pwm_config(panel->backlight.pwm, duty_ns, CRC_PMIC_PWM_PERIOD_NS); + pwm_set_relative_duty_cycle(&panel->backlight.pwm_state, level, 100); + pwm_apply_state(panel->backlight.pwm, &panel->backlight.pwm_state); } static void @@ -842,10 +840,8 @@ static void pwm_disable_backlight(const struct drm_connector_state *old_conn_sta struct intel_connector *connector = to_intel_connector(old_conn_state->connector); struct intel_panel *panel = &connector->panel; - /* Disable the backlight */ - intel_panel_actually_set_backlight(old_conn_state, 0); - usleep_range(2000, 3000); - pwm_disable(panel->backlight.pwm); + panel->backlight.pwm_state.enabled = false; + pwm_apply_state(panel->backlight.pwm, &panel->backlight.pwm_state); } void intel_panel_disable_backlight(const struct drm_connector_state *old_conn_state) @@ -1177,9 +1173,12 @@ static void pwm_enable_backlight(const struct intel_crtc_state *crtc_state, { struct intel_connector *connector = to_intel_connector(conn_state->connector); struct intel_panel *panel = &connector->panel; + int level = panel->backlight.level; - pwm_enable(panel->backlight.pwm); - intel_panel_actually_set_backlight(conn_state, panel->backlight.level); + level = intel_panel_compute_brightness(connector, level); + pwm_set_relative_duty_cycle(&panel->backlight.pwm_state, level, 100); + panel->backlight.pwm_state.enabled = true; + pwm_apply_state(panel->backlight.pwm, &panel->backlight.pwm_state); } static void __intel_panel_enable_backlight(const struct intel_crtc_state *crtc_state, @@ -1543,18 +1542,9 @@ static u32 vlv_hz_to_pwm(struct intel_connector *connector, u32 pwm_freq_hz) return DIV_ROUND_CLOSEST(clock, pwm_freq_hz * mul); } -static u32 get_backlight_max_vbt(struct intel_connector *connector) +static u16 get_vbt_pwm_freq(struct drm_i915_private *dev_priv) { - struct drm_i915_private *dev_priv = to_i915(connector->base.dev); - struct intel_panel *panel = &connector->panel; u16 pwm_freq_hz = dev_priv->vbt.backlight.pwm_freq_hz; - u32 pwm; - - if (!panel->backlight.hz_to_pwm) { - drm_dbg_kms(&dev_priv->drm, - "backlight frequency conversion not supported\n"); - return 0; - } if (pwm_freq_hz) { drm_dbg_kms(&dev_priv->drm, @@ -1567,6 +1557,22 @@ static u32 get_backlight_max_vbt(struct intel_connector *connector) pwm_freq_hz); } + return pwm_freq_hz; +} + +static u32 get_backlight_max_vbt(struct intel_connector *connector) +{ + struct drm_i915_private *dev_priv = to_i915(connector->base.dev); + struct intel_panel *panel = &connector->panel; + u16 pwm_freq_hz = get_vbt_pwm_freq(dev_priv); + u32 pwm; + + if (!panel->backlight.hz_to_pwm) { + drm_dbg_kms(&dev_priv->drm, + "backlight frequency conversion not supported\n"); + return 0; + } + pwm = panel->backlight.hz_to_pwm(connector, pwm_freq_hz); if (!pwm) { drm_dbg_kms(&dev_priv->drm, @@ -1891,8 +1897,7 @@ static int pwm_setup_backlight(struct intel_connector *connector, struct drm_i915_private *dev_priv = to_i915(dev); struct intel_panel *panel = &connector->panel; const char *desc; - u32 level, ns; - int retval; + u32 level; /* Get the right PWM chip for DSI backlight according to VBT */ if (dev_priv->vbt.dsi.config->pwm_blc == PPS_BLC_PMIC) { @@ -1910,30 +1915,28 @@ static int pwm_setup_backlight(struct intel_connector *connector, return -ENODEV; } - /* - * FIXME: pwm_apply_args() should be removed when switching to - * the atomic PWM API. - */ - pwm_apply_args(panel->backlight.pwm); - - panel->backlight.min = 0; /* 0% */ panel->backlight.max = 100; /* 100% */ - level = intel_panel_compute_brightness(connector, 100); - ns = DIV_ROUND_UP(level * CRC_PMIC_PWM_PERIOD_NS, 100); + panel->backlight.min = get_backlight_min_vbt(connector); - retval = pwm_config(panel->backlight.pwm, ns, CRC_PMIC_PWM_PERIOD_NS); - if (retval < 0) { - drm_err(&dev_priv->drm, "Failed to configure the pwm chip\n"); - pwm_put(panel->backlight.pwm); - panel->backlight.pwm = NULL; - return retval; - } + if (pwm_is_enabled(panel->backlight.pwm)) { + /* PWM is already enabled, use existing settings */ + pwm_get_state(panel->backlight.pwm, &panel->backlight.pwm_state); + + level = pwm_get_relative_duty_cycle(&panel->backlight.pwm_state, + 100); + level = intel_panel_compute_brightness(connector, level); + panel->backlight.level = clamp(level, panel->backlight.min, + panel->backlight.max); + panel->backlight.enabled = true; - level = DIV_ROUND_UP_ULL(pwm_get_duty_cycle(panel->backlight.pwm) * 100, - CRC_PMIC_PWM_PERIOD_NS); - panel->backlight.level = - intel_panel_compute_brightness(connector, level); - panel->backlight.enabled = panel->backlight.level != 0; + drm_dbg_kms(&dev_priv->drm, "PWM already enabled at freq %ld, VBT freq %d, level %d\n", + NSEC_PER_SEC / (unsigned long)panel->backlight.pwm_state.period, + get_vbt_pwm_freq(dev_priv), level); + } else { + /* Set period from VBT frequency, leave other settings at 0. */ + panel->backlight.pwm_state.period = + NSEC_PER_SEC / get_vbt_pwm_freq(dev_priv); + } drm_info(&dev_priv->drm, "Using %s PWM for LCD backlight control\n", desc); @@ -2092,6 +2095,17 @@ intel_panel_init_backlight_funcs(struct intel_panel *panel) } } +enum drm_connector_status +intel_panel_detect(struct drm_connector *connector, bool force) +{ + struct drm_i915_private *i915 = to_i915(connector->dev); + + if (!INTEL_DISPLAY_ENABLED(i915)) + return connector_status_disconnected; + + return connector_status_connected; +} + int intel_panel_init(struct intel_panel *panel, struct drm_display_mode *fixed_mode, struct drm_display_mode *downclock_mode) diff --git a/drivers/gpu/drm/i915/display/intel_panel.h b/drivers/gpu/drm/i915/display/intel_panel.h index 968b95281cb4..5b813fe90557 100644 --- a/drivers/gpu/drm/i915/display/intel_panel.h +++ b/drivers/gpu/drm/i915/display/intel_panel.h @@ -23,6 +23,8 @@ int intel_panel_init(struct intel_panel *panel, struct drm_display_mode *fixed_mode, struct drm_display_mode *downclock_mode); void intel_panel_fini(struct intel_panel *panel); +enum drm_connector_status +intel_panel_detect(struct drm_connector *connector, bool force); void intel_fixed_panel_mode(const struct drm_display_mode *fixed_mode, struct drm_display_mode *adjusted_mode); int intel_pch_panel_fitting(struct intel_crtc_state *crtc_state, diff --git a/drivers/gpu/drm/i915/display/intel_psr.c b/drivers/gpu/drm/i915/display/intel_psr.c index 2b004ee9619c..8a9d0bdde1bf 100644 --- a/drivers/gpu/drm/i915/display/intel_psr.c +++ b/drivers/gpu/drm/i915/display/intel_psr.c @@ -555,7 +555,7 @@ static void hsw_activate_psr2(struct intel_dp *intel_dp) if (dev_priv->psr.psr2_sel_fetch_enabled) { /* WA 1408330847 */ - if (IS_TGL_REVID(dev_priv, TGL_REVID_A0, TGL_REVID_A0) || + if (IS_TGL_DISP_REVID(dev_priv, TGL_REVID_A0, TGL_REVID_A0) || IS_RKL_REVID(dev_priv, RKL_REVID_A0, RKL_REVID_A0)) intel_de_rmw(dev_priv, CHICKEN_PAR1_1, DIS_RAM_BYPASS_PSR2_MAN_TRACK, @@ -1109,7 +1109,7 @@ static void intel_psr_disable_locked(struct intel_dp *intel_dp) /* WA 1408330847 */ if (dev_priv->psr.psr2_sel_fetch_enabled && - (IS_TGL_REVID(dev_priv, TGL_REVID_A0, TGL_REVID_A0) || + (IS_TGL_DISP_REVID(dev_priv, TGL_REVID_A0, TGL_REVID_A0) || IS_RKL_REVID(dev_priv, RKL_REVID_A0, RKL_REVID_A0))) intel_de_rmw(dev_priv, CHICKEN_PAR1_1, DIS_RAM_BYPASS_PSR2_MAN_TRACK, 0); diff --git a/drivers/gpu/drm/i915/display/intel_sdvo.c b/drivers/gpu/drm/i915/display/intel_sdvo.c index 5e9fb349c829..4eaa4aa86ecd 100644 --- a/drivers/gpu/drm/i915/display/intel_sdvo.c +++ b/drivers/gpu/drm/i915/display/intel_sdvo.c @@ -2084,14 +2084,18 @@ intel_sdvo_connector_matches_edid(struct intel_sdvo_connector *sdvo, static enum drm_connector_status intel_sdvo_detect(struct drm_connector *connector, bool force) { - u16 response; + struct drm_i915_private *i915 = to_i915(connector->dev); struct intel_sdvo *intel_sdvo = intel_attached_sdvo(to_intel_connector(connector)); struct intel_sdvo_connector *intel_sdvo_connector = to_intel_sdvo_connector(connector); enum drm_connector_status ret; + u16 response; DRM_DEBUG_KMS("[CONNECTOR:%d:%s]\n", connector->base.id, connector->name); + if (!INTEL_DISPLAY_ENABLED(i915)) + return connector_status_disconnected; + if (!intel_sdvo_get_value(intel_sdvo, SDVO_CMD_GET_ATTACHED_DISPLAYS, &response, 2)) diff --git a/drivers/gpu/drm/i915/display/intel_sprite.c b/drivers/gpu/drm/i915/display/intel_sprite.c index 6b72223981be..63040cb0d4e1 100644 --- a/drivers/gpu/drm/i915/display/intel_sprite.c +++ b/drivers/gpu/drm/i915/display/intel_sprite.c @@ -1626,8 +1626,7 @@ static int g4x_sprite_min_cdclk(const struct intel_crtc_state *crtc_state, hscale = drm_rect_calc_hscale(&plane_state->uapi.src, &plane_state->uapi.dst, 0, INT_MAX); - if (hscale < 0x10000) - return pixel_rate; + hscale = max(hscale, 0x10000u); /* Decimation steps at 2x,4x,8x,16x */ decimate = ilog2(hscale >> 16); @@ -1640,8 +1639,8 @@ static int g4x_sprite_min_cdclk(const struct intel_crtc_state *crtc_state, limit -= decimate; /* -10% for RGB */ - if (fb->format->cpp[0] >= 4) - limit--; /* -10% for RGB */ + if (!fb->format->is_yuv) + limit--; /* * We should also do -10% if sprite scaling is enabled @@ -2845,7 +2844,7 @@ static bool gen12_plane_supports_mc_ccs(struct drm_i915_private *dev_priv, { /* Wa_14010477008:tgl[a0..c0],rkl[all] */ if (IS_ROCKETLAKE(dev_priv) || - IS_TGL_REVID(dev_priv, TGL_REVID_A0, TGL_REVID_C0)) + IS_TGL_DISP_REVID(dev_priv, TGL_REVID_A0, TGL_REVID_C0)) return false; return plane_id < PLANE_SPRITE4; diff --git a/drivers/gpu/drm/i915/display/intel_tv.c b/drivers/gpu/drm/i915/display/intel_tv.c index 777032d9697b..7a7b99b015a5 100644 --- a/drivers/gpu/drm/i915/display/intel_tv.c +++ b/drivers/gpu/drm/i915/display/intel_tv.c @@ -1706,6 +1706,9 @@ intel_tv_detect(struct drm_connector *connector, drm_dbg_kms(&i915->drm, "[CONNECTOR:%d:%s] force=%d\n", connector->base.id, connector->name, force); + if (!INTEL_DISPLAY_ENABLED(i915)) + return connector_status_disconnected; + if (force) { struct intel_load_detect_pipe tmp; int ret; diff --git a/drivers/gpu/drm/i915/display/intel_vbt_defs.h b/drivers/gpu/drm/i915/display/intel_vbt_defs.h index 6faabd4f6d49..54bcc6a6947c 100644 --- a/drivers/gpu/drm/i915/display/intel_vbt_defs.h +++ b/drivers/gpu/drm/i915/display/intel_vbt_defs.h @@ -293,8 +293,12 @@ struct bdb_general_features { #define DVO_PORT_HDMIE 12 /* 193 */ #define DVO_PORT_DPF 13 /* N/A */ #define DVO_PORT_HDMIF 14 /* N/A */ -#define DVO_PORT_DPG 15 -#define DVO_PORT_HDMIG 16 +#define DVO_PORT_DPG 15 /* 217 */ +#define DVO_PORT_HDMIG 16 /* 217 */ +#define DVO_PORT_DPH 17 /* 217 */ +#define DVO_PORT_HDMIH 18 /* 217 */ +#define DVO_PORT_DPI 19 /* 217 */ +#define DVO_PORT_HDMII 20 /* 217 */ #define DVO_PORT_MIPIA 21 /* 171 */ #define DVO_PORT_MIPIB 22 /* 171 */ #define DVO_PORT_MIPIC 23 /* 171 */ @@ -330,6 +334,8 @@ enum vbt_gmbus_ddi { #define DP_AUX_E 0x50 #define DP_AUX_F 0x60 #define DP_AUX_G 0x70 +#define DP_AUX_H 0x80 +#define DP_AUX_I 0x90 #define VBT_DP_MAX_LINK_RATE_HBR3 0 #define VBT_DP_MAX_LINK_RATE_HBR2 1 diff --git a/drivers/gpu/drm/i915/display/vlv_dsi.c b/drivers/gpu/drm/i915/display/vlv_dsi.c index 052e0b31a2da..5e5522923b1e 100644 --- a/drivers/gpu/drm/i915/display/vlv_dsi.c +++ b/drivers/gpu/drm/i915/display/vlv_dsi.c @@ -1585,6 +1585,7 @@ static const struct drm_connector_helper_funcs intel_dsi_connector_helper_funcs }; static const struct drm_connector_funcs intel_dsi_connector_funcs = { + .detect = intel_panel_detect, .late_register = intel_connector_register, .early_unregister = intel_connector_unregister, .destroy = intel_connector_destroy, diff --git a/drivers/gpu/drm/i915/display/vlv_dsi_pll.c b/drivers/gpu/drm/i915/display/vlv_dsi_pll.c index d0a514301575..4070b00c3690 100644 --- a/drivers/gpu/drm/i915/display/vlv_dsi_pll.c +++ b/drivers/gpu/drm/i915/display/vlv_dsi_pll.c @@ -483,7 +483,7 @@ int bxt_dsi_pll_compute(struct intel_encoder *encoder, if (dsi_ratio < dsi_ratio_min || dsi_ratio > dsi_ratio_max) { drm_err(&dev_priv->drm, - "Cant get a suitable ratio from DSI PLL ratios\n"); + "Can't get a suitable ratio from DSI PLL ratios\n"); return -ECHRNG; } else drm_dbg_kms(&dev_priv->drm, "DSI PLL calculation is Done!!\n"); diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context.c b/drivers/gpu/drm/i915/gem/i915_gem_context.c index cf5ecbde9e06..4fd38101bb56 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_context.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_context.c @@ -390,24 +390,6 @@ __context_engines_static(const struct i915_gem_context *ctx) return rcu_dereference_protected(ctx->engines, true); } -static bool __reset_engine(struct intel_engine_cs *engine) -{ - struct intel_gt *gt = engine->gt; - bool success = false; - - if (!intel_has_reset_engine(gt)) - return false; - - if (!test_and_set_bit(I915_RESET_ENGINE + engine->id, - >->reset.flags)) { - success = intel_engine_reset(engine, NULL) == 0; - clear_and_wake_up_bit(I915_RESET_ENGINE + engine->id, - >->reset.flags); - } - - return success; -} - static void __reset_context(struct i915_gem_context *ctx, struct intel_engine_cs *engine) { @@ -431,12 +413,7 @@ static bool __cancel_engine(struct intel_engine_cs *engine) * kill the banned context, we fallback to doing a local reset * instead. */ - if (IS_ACTIVE(CONFIG_DRM_I915_PREEMPT_TIMEOUT) && - !intel_engine_pulse(engine)) - return true; - - /* If we are unable to send a pulse, try resetting this engine. */ - return __reset_engine(engine); + return intel_engine_pulse(engine) == 0; } static bool @@ -460,8 +437,8 @@ __active_engine(struct i915_request *rq, struct intel_engine_cs **active) spin_lock(&locked->active.lock); } - if (!i915_request_completed(rq)) { - if (i915_request_is_active(rq) && rq->fence.error != -EIO) + if (i915_request_is_active(rq)) { + if (!i915_request_completed(rq)) *active = locked; ret = true; } @@ -479,13 +456,26 @@ static struct intel_engine_cs *active_engine(struct intel_context *ce) if (!ce->timeline) return NULL; + /* + * rq->link is only SLAB_TYPESAFE_BY_RCU, we need to hold a reference + * to the request to prevent it being transferred to a new timeline + * (and onto a new timeline->requests list). + */ rcu_read_lock(); - list_for_each_entry_rcu(rq, &ce->timeline->requests, link) { - if (i915_request_is_active(rq) && i915_request_completed(rq)) - continue; + list_for_each_entry_reverse(rq, &ce->timeline->requests, link) { + bool found; + + /* timeline is already completed upto this point? */ + if (!i915_request_get_rcu(rq)) + break; /* Check with the backend if the request is inflight */ - if (__active_engine(rq, &engine)) + found = true; + if (likely(rcu_access_pointer(rq->timeline) == ce->timeline)) + found = __active_engine(rq, &engine); + + i915_request_put(rq); + if (found) break; } rcu_read_unlock(); @@ -493,7 +483,7 @@ static struct intel_engine_cs *active_engine(struct intel_context *ce) return engine; } -static void kill_engines(struct i915_gem_engines *engines) +static void kill_engines(struct i915_gem_engines *engines, bool ban) { struct i915_gem_engines_iter it; struct intel_context *ce; @@ -508,7 +498,7 @@ static void kill_engines(struct i915_gem_engines *engines) for_each_gem_engine(ce, engines, it) { struct intel_engine_cs *engine; - if (intel_context_set_banned(ce)) + if (ban && intel_context_set_banned(ce)) continue; /* @@ -521,7 +511,7 @@ static void kill_engines(struct i915_gem_engines *engines) engine = active_engine(ce); /* First attempt to gracefully cancel the context */ - if (engine && !__cancel_engine(engine)) + if (engine && !__cancel_engine(engine) && ban) /* * If we are unable to send a preemptive pulse to bump * the context from the GPU, we have to resort to a full @@ -531,8 +521,10 @@ static void kill_engines(struct i915_gem_engines *engines) } } -static void kill_stale_engines(struct i915_gem_context *ctx) +static void kill_context(struct i915_gem_context *ctx) { + bool ban = (!i915_gem_context_is_persistent(ctx) || + !ctx->i915->params.enable_hangcheck); struct i915_gem_engines *pos, *next; spin_lock_irq(&ctx->stale.lock); @@ -545,7 +537,7 @@ static void kill_stale_engines(struct i915_gem_context *ctx) spin_unlock_irq(&ctx->stale.lock); - kill_engines(pos); + kill_engines(pos, ban); spin_lock_irq(&ctx->stale.lock); GEM_BUG_ON(i915_sw_fence_signaled(&pos->fence)); @@ -557,11 +549,6 @@ static void kill_stale_engines(struct i915_gem_context *ctx) spin_unlock_irq(&ctx->stale.lock); } -static void kill_context(struct i915_gem_context *ctx) -{ - kill_stale_engines(ctx); -} - static void engines_idle_release(struct i915_gem_context *ctx, struct i915_gem_engines *engines) { @@ -596,7 +583,7 @@ static void engines_idle_release(struct i915_gem_context *ctx, kill: if (list_empty(&engines->link)) /* raced, already closed */ - kill_engines(engines); + kill_engines(engines, true); i915_sw_fence_commit(&engines->fence); } @@ -654,9 +641,7 @@ static void context_close(struct i915_gem_context *ctx) * case we opt to forcibly kill off all remaining requests on * context close. */ - if (!i915_gem_context_is_persistent(ctx) || - !ctx->i915->params.enable_hangcheck) - kill_context(ctx); + kill_context(ctx); i915_gem_context_put(ctx); } diff --git a/drivers/gpu/drm/i915/gem/i915_gem_dmabuf.c b/drivers/gpu/drm/i915/gem/i915_gem_dmabuf.c index fec0e1e3dc3e..0dd477e56573 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_dmabuf.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_dmabuf.c @@ -48,12 +48,9 @@ static struct sg_table *i915_gem_map_dma_buf(struct dma_buf_attachment *attachme src = sg_next(src); } - if (!dma_map_sg_attrs(attachment->dev, - st->sgl, st->nents, dir, - DMA_ATTR_SKIP_CPU_SYNC)) { - ret = -ENOMEM; + ret = dma_map_sgtable(attachment->dev, st, dir, DMA_ATTR_SKIP_CPU_SYNC); + if (ret) goto err_free_sg; - } return st; @@ -73,9 +70,7 @@ static void i915_gem_unmap_dma_buf(struct dma_buf_attachment *attachment, { struct drm_i915_gem_object *obj = dma_buf_to_obj(attachment->dmabuf); - dma_unmap_sg_attrs(attachment->dev, - sg->sgl, sg->nents, dir, - DMA_ATTR_SKIP_CPU_SYNC); + dma_unmap_sgtable(attachment->dev, sg, dir, DMA_ATTR_SKIP_CPU_SYNC); sg_free_table(sg); kfree(sg); diff --git a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c index 5509946f1a1d..1904e6e5ea64 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c @@ -287,8 +287,8 @@ struct i915_execbuffer { u64 invalid_flags; /** Set of execobj.flags that are invalid */ u32 context_flags; /** Set of execobj.flags to insert from the ctx */ + u64 batch_len; /** Length of batch within object */ u32 batch_start_offset; /** Location within object of batch */ - u32 batch_len; /** Length of batch within object */ u32 batch_flags; /** Flags composed for emit_bb_start() */ struct intel_gt_buffer_pool_node *batch_pool; /** pool node for batch buffer */ @@ -871,6 +871,10 @@ static int eb_lookup_vmas(struct i915_execbuffer *eb) if (eb->batch_len == 0) eb->batch_len = eb->batch->vma->size - eb->batch_start_offset; + if (unlikely(eb->batch_len == 0)) { /* impossible! */ + drm_dbg(&i915->drm, "Invalid batch length\n"); + return -EINVAL; + } return 0; @@ -2267,8 +2271,8 @@ struct eb_parse_work { struct i915_vma *batch; struct i915_vma *shadow; struct i915_vma *trampoline; - unsigned int batch_offset; - unsigned int batch_length; + unsigned long batch_offset; + unsigned long batch_length; }; static int __eb_parse(struct dma_fence_work *work) @@ -2338,6 +2342,9 @@ static int eb_parse_pipeline(struct i915_execbuffer *eb, struct eb_parse_work *pw; int err; + GEM_BUG_ON(overflows_type(eb->batch_start_offset, pw->batch_offset)); + GEM_BUG_ON(overflows_type(eb->batch_len, pw->batch_length)); + pw = kzalloc(sizeof(*pw), GFP_KERNEL); if (!pw) return -ENOMEM; @@ -2421,7 +2428,7 @@ static int eb_parse(struct i915_execbuffer *eb) struct drm_i915_private *i915 = eb->i915; struct intel_gt_buffer_pool_node *pool = eb->batch_pool; struct i915_vma *shadow, *trampoline, *batch; - unsigned int len; + unsigned long len; int err; if (!eb_use_cmdparser(eb)) { @@ -2446,6 +2453,8 @@ static int eb_parse(struct i915_execbuffer *eb) } else { len += I915_CMD_PARSER_TRAMPOLINE_SIZE; } + if (unlikely(len < eb->batch_len)) /* last paranoid check of overflow */ + return -EINVAL; if (!pool) { pool = intel_gt_get_buffer_pool(eb->engine->gt, len); diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object_blt.c b/drivers/gpu/drm/i915/gem/i915_gem_object_blt.c index d93eb36160c9..aee7ad3cc3c6 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_object_blt.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_object_blt.c @@ -364,7 +364,7 @@ int i915_gem_object_copy_blt(struct drm_i915_gem_object *src, vma[1] = i915_vma_instance(dst, vm, NULL); if (IS_ERR(vma[1])) - return PTR_ERR(vma); + return PTR_ERR(vma[1]); i915_gem_ww_ctx_init(&ww, true); intel_engine_pm_get(ce->engine); diff --git a/drivers/gpu/drm/i915/gem/i915_gem_pages.c b/drivers/gpu/drm/i915/gem/i915_gem_pages.c index e8a083743e09..f60ca6dc911f 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_pages.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_pages.c @@ -162,8 +162,6 @@ static void unmap_object(struct drm_i915_gem_object *obj, void *ptr) { if (is_vmalloc_addr(ptr)) vunmap(ptr); - else - kunmap(kmap_to_page(ptr)); } struct sg_table * @@ -234,50 +232,40 @@ unlock: return err; } -static inline pte_t iomap_pte(resource_size_t base, - dma_addr_t offset, - pgprot_t prot) -{ - return pte_mkspecial(pfn_pte((base + offset) >> PAGE_SHIFT, prot)); -} - /* The 'mapping' part of i915_gem_object_pin_map() below */ -static void *i915_gem_object_map(struct drm_i915_gem_object *obj, - enum i915_map_type type) +static void *i915_gem_object_map_page(struct drm_i915_gem_object *obj, + enum i915_map_type type) { - unsigned long n_pte = obj->base.size >> PAGE_SHIFT; - struct sg_table *sgt = obj->mm.pages; - pte_t *stack[32], **mem; - struct vm_struct *area; + unsigned long n_pages = obj->base.size >> PAGE_SHIFT, i; + struct page *stack[32], **pages = stack, *page; + struct sgt_iter iter; pgprot_t pgprot; - - if (!i915_gem_object_has_struct_page(obj) && type != I915_MAP_WC) - return NULL; - - /* A single page can always be kmapped */ - if (n_pte == 1 && type == I915_MAP_WB) - return kmap(sg_page(sgt->sgl)); - - mem = stack; - if (n_pte > ARRAY_SIZE(stack)) { - /* Too big for stack -- allocate temporary array instead */ - mem = kvmalloc_array(n_pte, sizeof(*mem), GFP_KERNEL); - if (!mem) - return NULL; - } - - area = alloc_vm_area(obj->base.size, mem); - if (!area) { - if (mem != stack) - kvfree(mem); - return NULL; - } + void *vaddr; switch (type) { default: MISSING_CASE(type); fallthrough; /* to use PAGE_KERNEL anyway */ case I915_MAP_WB: + /* + * On 32b, highmem using a finite set of indirect PTE (i.e. + * vmap) to provide virtual mappings of the high pages. + * As these are finite, map_new_virtual() must wait for some + * other kmap() to finish when it runs out. If we map a large + * number of objects, there is no method for it to tell us + * to release the mappings, and we deadlock. + * + * However, if we make an explicit vmap of the page, that + * uses a larger vmalloc arena, and also has the ability + * to tell us to release unwanted mappings. Most importantly, + * it will fail and propagate an error instead of waiting + * forever. + * + * So if the page is beyond the 32b boundary, make an explicit + * vmap. + */ + if (n_pages == 1 && !PageHighMem(sg_page(obj->mm.pages->sgl))) + return page_address(sg_page(obj->mm.pages->sgl)); pgprot = PAGE_KERNEL; break; case I915_MAP_WC: @@ -285,30 +273,50 @@ static void *i915_gem_object_map(struct drm_i915_gem_object *obj, break; } - if (i915_gem_object_has_struct_page(obj)) { - struct sgt_iter iter; - struct page *page; - pte_t **ptes = mem; + if (n_pages > ARRAY_SIZE(stack)) { + /* Too big for stack -- allocate temporary array instead */ + pages = kvmalloc_array(n_pages, sizeof(*pages), GFP_KERNEL); + if (!pages) + return NULL; + } - for_each_sgt_page(page, iter, sgt) - **ptes++ = mk_pte(page, pgprot); - } else { - resource_size_t iomap; - struct sgt_iter iter; - pte_t **ptes = mem; - dma_addr_t addr; + i = 0; + for_each_sgt_page(page, iter, obj->mm.pages) + pages[i++] = page; + vaddr = vmap(pages, n_pages, 0, pgprot); + if (pages != stack) + kvfree(pages); + return vaddr; +} - iomap = obj->mm.region->iomap.base; - iomap -= obj->mm.region->region.start; +static void *i915_gem_object_map_pfn(struct drm_i915_gem_object *obj, + enum i915_map_type type) +{ + resource_size_t iomap = obj->mm.region->iomap.base - + obj->mm.region->region.start; + unsigned long n_pfn = obj->base.size >> PAGE_SHIFT; + unsigned long stack[32], *pfns = stack, i; + struct sgt_iter iter; + dma_addr_t addr; + void *vaddr; + + if (type != I915_MAP_WC) + return NULL; - for_each_sgt_daddr(addr, iter, sgt) - **ptes++ = iomap_pte(iomap, addr, pgprot); + if (n_pfn > ARRAY_SIZE(stack)) { + /* Too big for stack -- allocate temporary array instead */ + pfns = kvmalloc_array(n_pfn, sizeof(*pfns), GFP_KERNEL); + if (!pfns) + return NULL; } - if (mem != stack) - kvfree(mem); - - return area->addr; + i = 0; + for_each_sgt_daddr(addr, iter, obj->mm.pages) + pfns[i++] = (iomap + addr) >> PAGE_SHIFT; + vaddr = vmap_pfn(pfns, n_pfn, pgprot_writecombine(PAGE_KERNEL_IO)); + if (pfns != stack) + kvfree(pfns); + return vaddr; } /* get, pin, and map the pages of the object into kernel space */ @@ -360,7 +368,13 @@ void *i915_gem_object_pin_map(struct drm_i915_gem_object *obj, } if (!ptr) { - ptr = i915_gem_object_map(obj, type); + if (GEM_WARN_ON(type == I915_MAP_WC && + !static_cpu_has(X86_FEATURE_PAT))) + ptr = NULL; + else if (i915_gem_object_has_struct_page(obj)) + ptr = i915_gem_object_map_page(obj, type); + else + ptr = i915_gem_object_map_pfn(obj, type); if (!ptr) { err = -ENOMEM; goto err_unpin; diff --git a/drivers/gpu/drm/i915/gem/i915_gem_shmem.c b/drivers/gpu/drm/i915/gem/i915_gem_shmem.c index 38113d3c0138..75e8b71c18b9 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_shmem.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_shmem.c @@ -258,8 +258,8 @@ shmem_writeback(struct drm_i915_gem_object *obj) for (i = 0; i < obj->base.size >> PAGE_SHIFT; i++) { struct page *page; - page = find_lock_entry(mapping, i); - if (!page || xa_is_value(page)) + page = find_lock_page(mapping, i); + if (!page) continue; if (!page_mapped(page) && clear_page_dirty_for_io(page)) { diff --git a/drivers/gpu/drm/i915/gem/i915_gem_stolen.c b/drivers/gpu/drm/i915/gem/i915_gem_stolen.c index 0be5e8683337..84b2707d8b17 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_stolen.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_stolen.c @@ -53,8 +53,10 @@ int i915_gem_stolen_insert_node(struct drm_i915_private *i915, struct drm_mm_node *node, u64 size, unsigned alignment) { - return i915_gem_stolen_insert_node_in_range(i915, node, size, - alignment, 0, U64_MAX); + return i915_gem_stolen_insert_node_in_range(i915, node, + size, alignment, + I915_GEM_STOLEN_BIAS, + U64_MAX); } void i915_gem_stolen_remove_node(struct drm_i915_private *i915, diff --git a/drivers/gpu/drm/i915/gem/i915_gem_stolen.h b/drivers/gpu/drm/i915/gem/i915_gem_stolen.h index e15c0adad8af..61e028063f9f 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_stolen.h +++ b/drivers/gpu/drm/i915/gem/i915_gem_stolen.h @@ -30,4 +30,6 @@ i915_gem_object_create_stolen_for_preallocated(struct drm_i915_private *dev_priv resource_size_t stolen_offset, resource_size_t size); +#define I915_GEM_STOLEN_BIAS SZ_128K + #endif /* __I915_GEM_STOLEN_H__ */ diff --git a/drivers/gpu/drm/i915/gem/i915_gem_userptr.c b/drivers/gpu/drm/i915/gem/i915_gem_userptr.c index 12b30075134a..f2eaed6aca3d 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_userptr.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_userptr.c @@ -403,6 +403,7 @@ __i915_gem_userptr_alloc_pages(struct drm_i915_gem_object *obj, unsigned int max_segment = i915_sg_segment_size(); struct sg_table *st; unsigned int sg_page_sizes; + struct scatterlist *sg; int ret; st = kmalloc(sizeof(*st), GFP_KERNEL); @@ -410,13 +411,12 @@ __i915_gem_userptr_alloc_pages(struct drm_i915_gem_object *obj, return ERR_PTR(-ENOMEM); alloc_table: - ret = __sg_alloc_table_from_pages(st, pvec, num_pages, - 0, num_pages << PAGE_SHIFT, - max_segment, - GFP_KERNEL); - if (ret) { + sg = __sg_alloc_table_from_pages(st, pvec, num_pages, 0, + num_pages << PAGE_SHIFT, max_segment, + NULL, 0, GFP_KERNEL); + if (IS_ERR(sg)) { kfree(st); - return ERR_PTR(ret); + return ERR_CAST(sg); } ret = i915_gem_gtt_prepare_pages(obj, st); diff --git a/drivers/gpu/drm/i915/gem/selftests/mock_dmabuf.c b/drivers/gpu/drm/i915/gem/selftests/mock_dmabuf.c index 7dfef531f6d4..2855d11c7a51 100644 --- a/drivers/gpu/drm/i915/gem/selftests/mock_dmabuf.c +++ b/drivers/gpu/drm/i915/gem/selftests/mock_dmabuf.c @@ -28,10 +28,9 @@ static struct sg_table *mock_map_dma_buf(struct dma_buf_attachment *attachment, sg = sg_next(sg); } - if (!dma_map_sg(attachment->dev, st->sgl, st->nents, dir)) { - err = -ENOMEM; + err = dma_map_sgtable(attachment->dev, st, dir, 0); + if (err) goto err_st; - } return st; @@ -46,7 +45,7 @@ static void mock_unmap_dma_buf(struct dma_buf_attachment *attachment, struct sg_table *st, enum dma_data_direction dir) { - dma_unmap_sg(attachment->dev, st->sgl, st->nents, dir); + dma_unmap_sgtable(attachment->dev, st, dir, 0); sg_free_table(st); kfree(st); } diff --git a/drivers/gpu/drm/i915/gt/gen6_ppgtt.c b/drivers/gpu/drm/i915/gt/gen6_ppgtt.c index fd0d24d28763..c30adc05fa98 100644 --- a/drivers/gpu/drm/i915/gt/gen6_ppgtt.c +++ b/drivers/gpu/drm/i915/gt/gen6_ppgtt.c @@ -239,18 +239,24 @@ static int gen6_ppgtt_init_scratch(struct gen6_ppgtt *ppgtt) I915_CACHE_NONE, PTE_READ_ONLY); vm->scratch[1] = vm->alloc_pt_dma(vm, I915_GTT_PAGE_SIZE_4K); - if (IS_ERR(vm->scratch[1])) - return PTR_ERR(vm->scratch[1]); + if (IS_ERR(vm->scratch[1])) { + ret = PTR_ERR(vm->scratch[1]); + goto err_scratch0; + } ret = pin_pt_dma(vm, vm->scratch[1]); - if (ret) { - i915_gem_object_put(vm->scratch[1]); - return ret; - } + if (ret) + goto err_scratch1; fill32_px(vm->scratch[1], vm->scratch[0]->encode); return 0; + +err_scratch1: + i915_gem_object_put(vm->scratch[1]); +err_scratch0: + i915_gem_object_put(vm->scratch[0]); + return ret; } static void gen6_ppgtt_free_pd(struct gen6_ppgtt *ppgtt) diff --git a/drivers/gpu/drm/i915/gt/gen8_ppgtt.c b/drivers/gpu/drm/i915/gt/gen8_ppgtt.c index eb64f474a78c..38c7069b7749 100644 --- a/drivers/gpu/drm/i915/gt/gen8_ppgtt.c +++ b/drivers/gpu/drm/i915/gt/gen8_ppgtt.c @@ -604,7 +604,8 @@ static int gen8_init_scratch(struct i915_address_space *vm) return 0; free_scratch: - free_scratch(vm); + while (i--) + i915_gem_object_put(vm->scratch[i]); return -ENOMEM; } diff --git a/drivers/gpu/drm/i915/gt/intel_context.c b/drivers/gpu/drm/i915/gt/intel_context.c index d301dda1b261..92a3f25c4006 100644 --- a/drivers/gpu/drm/i915/gt/intel_context.c +++ b/drivers/gpu/drm/i915/gt/intel_context.c @@ -472,6 +472,7 @@ retry: err = i915_gem_ww_ctx_backoff(&ww); if (!err) goto retry; + rq = ERR_PTR(err); } else { rq = ERR_PTR(err); } diff --git a/drivers/gpu/drm/i915/gt/intel_engine.h b/drivers/gpu/drm/i915/gt/intel_engine.h index 08e2c000dcc3..7c3a1012e702 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine.h +++ b/drivers/gpu/drm/i915/gt/intel_engine.h @@ -337,4 +337,13 @@ intel_engine_has_preempt_reset(const struct intel_engine_cs *engine) return intel_engine_has_preemption(engine); } +static inline bool +intel_engine_has_heartbeat(const struct intel_engine_cs *engine) +{ + if (!IS_ACTIVE(CONFIG_DRM_I915_HEARTBEAT_INTERVAL)) + return false; + + return READ_ONCE(engine->props.heartbeat_interval_ms); +} + #endif /* _INTEL_RINGBUFFER_H_ */ diff --git a/drivers/gpu/drm/i915/gt/intel_engine_heartbeat.c b/drivers/gpu/drm/i915/gt/intel_engine_heartbeat.c index 8ffdf676c0a0..5067d0524d4b 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine_heartbeat.c +++ b/drivers/gpu/drm/i915/gt/intel_engine_heartbeat.c @@ -177,36 +177,82 @@ void intel_engine_init_heartbeat(struct intel_engine_cs *engine) INIT_DELAYED_WORK(&engine->heartbeat.work, heartbeat); } +static int __intel_engine_pulse(struct intel_engine_cs *engine) +{ + struct i915_sched_attr attr = { .priority = I915_PRIORITY_BARRIER }; + struct intel_context *ce = engine->kernel_context; + struct i915_request *rq; + + lockdep_assert_held(&ce->timeline->mutex); + GEM_BUG_ON(!intel_engine_has_preemption(engine)); + GEM_BUG_ON(!intel_engine_pm_is_awake(engine)); + + intel_context_enter(ce); + rq = __i915_request_create(ce, GFP_NOWAIT | __GFP_NOWARN); + intel_context_exit(ce); + if (IS_ERR(rq)) + return PTR_ERR(rq); + + __set_bit(I915_FENCE_FLAG_SENTINEL, &rq->fence.flags); + idle_pulse(engine, rq); + + __i915_request_commit(rq); + __i915_request_queue(rq, &attr); + GEM_BUG_ON(rq->sched.attr.priority < I915_PRIORITY_BARRIER); + + return 0; +} + +static unsigned long set_heartbeat(struct intel_engine_cs *engine, + unsigned long delay) +{ + unsigned long old; + + old = xchg(&engine->props.heartbeat_interval_ms, delay); + if (delay) + intel_engine_unpark_heartbeat(engine); + else + intel_engine_park_heartbeat(engine); + + return old; +} + int intel_engine_set_heartbeat(struct intel_engine_cs *engine, unsigned long delay) { - int err; + struct intel_context *ce = engine->kernel_context; + int err = 0; - /* Send one last pulse before to cleanup persistent hogs */ - if (!delay && IS_ACTIVE(CONFIG_DRM_I915_PREEMPT_TIMEOUT)) { - err = intel_engine_pulse(engine); - if (err) - return err; - } + if (!delay && !intel_engine_has_preempt_reset(engine)) + return -ENODEV; + + intel_engine_pm_get(engine); + + err = mutex_lock_interruptible(&ce->timeline->mutex); + if (err) + goto out_rpm; - WRITE_ONCE(engine->props.heartbeat_interval_ms, delay); + if (delay != engine->props.heartbeat_interval_ms) { + unsigned long saved = set_heartbeat(engine, delay); - if (intel_engine_pm_get_if_awake(engine)) { - if (delay) - intel_engine_unpark_heartbeat(engine); - else - intel_engine_park_heartbeat(engine); - intel_engine_pm_put(engine); + /* recheck current execution */ + if (intel_engine_has_preemption(engine)) { + err = __intel_engine_pulse(engine); + if (err) + set_heartbeat(engine, saved); + } } - return 0; + mutex_unlock(&ce->timeline->mutex); + +out_rpm: + intel_engine_pm_put(engine); + return err; } int intel_engine_pulse(struct intel_engine_cs *engine) { - struct i915_sched_attr attr = { .priority = I915_PRIORITY_BARRIER }; struct intel_context *ce = engine->kernel_context; - struct i915_request *rq; int err; if (!intel_engine_has_preemption(engine)) @@ -215,30 +261,12 @@ int intel_engine_pulse(struct intel_engine_cs *engine) if (!intel_engine_pm_get_if_awake(engine)) return 0; - if (mutex_lock_interruptible(&ce->timeline->mutex)) { - err = -EINTR; - goto out_rpm; - } - - intel_context_enter(ce); - rq = __i915_request_create(ce, GFP_NOWAIT | __GFP_NOWARN); - intel_context_exit(ce); - if (IS_ERR(rq)) { - err = PTR_ERR(rq); - goto out_unlock; + err = -EINTR; + if (!mutex_lock_interruptible(&ce->timeline->mutex)) { + err = __intel_engine_pulse(engine); + mutex_unlock(&ce->timeline->mutex); } - __set_bit(I915_FENCE_FLAG_SENTINEL, &rq->fence.flags); - idle_pulse(engine, rq); - - __i915_request_commit(rq); - __i915_request_queue(rq, &attr); - GEM_BUG_ON(rq->sched.attr.priority < I915_PRIORITY_BARRIER); - err = 0; - -out_unlock: - mutex_unlock(&ce->timeline->mutex); -out_rpm: intel_engine_pm_put(engine); return err; } diff --git a/drivers/gpu/drm/i915/gt/intel_engine_types.h b/drivers/gpu/drm/i915/gt/intel_engine_types.h index c400aaa2287b..ee6312601c56 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine_types.h +++ b/drivers/gpu/drm/i915/gt/intel_engine_types.h @@ -278,7 +278,7 @@ struct intel_engine_execlists { * * Note these register may be either mmio or HWSP shadow. */ - u32 *csb_status; + u64 *csb_status; /** * @csb_size: context status buffer FIFO size diff --git a/drivers/gpu/drm/i915/gt/intel_gt_buffer_pool.c b/drivers/gpu/drm/i915/gt/intel_gt_buffer_pool.c index 4b7671ac5dca..104cb30e8c13 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt_buffer_pool.c +++ b/drivers/gpu/drm/i915/gt/intel_gt_buffer_pool.c @@ -134,6 +134,7 @@ static void pool_retire(struct i915_active *ref) /* Return this object to the shrinker pool */ i915_gem_object_make_purgeable(node->obj); + GEM_BUG_ON(node->age); spin_lock_irqsave(&pool->lock, flags); list_add_rcu(&node->link, list); WRITE_ONCE(node->age, jiffies ?: 1); /* 0 reserved for active nodes */ @@ -155,6 +156,7 @@ node_create(struct intel_gt_buffer_pool *pool, size_t sz) if (!node) return ERR_PTR(-ENOMEM); + node->age = 0; node->pool = pool; i915_active_init(&node->active, pool_active, pool_retire); diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c index 0412a44f25f2..a32aabce7901 100644 --- a/drivers/gpu/drm/i915/gt/intel_lrc.c +++ b/drivers/gpu/drm/i915/gt/intel_lrc.c @@ -1140,9 +1140,8 @@ __unwind_incomplete_requests(struct intel_engine_cs *engine) /* Check in case we rollback so far we wrap [size/2] */ if (intel_ring_direction(rq->ring, - intel_ring_wrap(rq->ring, - rq->tail), - rq->ring->tail) > 0) + rq->tail, + rq->ring->tail + 8) > 0) rq->context->lrc.desc |= CTX_DESC_FORCE_RESTORE; active = rq; @@ -2464,7 +2463,7 @@ cancel_port_requests(struct intel_engine_execlists * const execlists) } static inline void -invalidate_csb_entries(const u32 *first, const u32 *last) +invalidate_csb_entries(const u64 *first, const u64 *last) { clflush((void *)first); clflush((void *)last); @@ -2496,14 +2495,25 @@ invalidate_csb_entries(const u32 *first, const u32 *last) * bits 47-57: sw context id of the lrc the GT switched away from * bits 58-63: sw counter of the lrc the GT switched away from */ -static inline bool -gen12_csb_parse(const struct intel_engine_execlists *execlists, const u32 *csb) -{ - u32 lower_dw = csb[0]; - u32 upper_dw = csb[1]; - bool ctx_to_valid = GEN12_CSB_CTX_VALID(lower_dw); - bool ctx_away_valid = GEN12_CSB_CTX_VALID(upper_dw); - bool new_queue = lower_dw & GEN12_CTX_STATUS_SWITCHED_TO_NEW_QUEUE; +static inline bool gen12_csb_parse(const u64 *csb) +{ + bool ctx_away_valid; + bool new_queue; + u64 entry; + + /* HSD#22011248461 */ + entry = READ_ONCE(*csb); + if (unlikely(entry == -1)) { + preempt_disable(); + if (wait_for_atomic_us((entry = READ_ONCE(*csb)) != -1, 50)) + GEM_WARN_ON("50us CSB timeout"); + preempt_enable(); + } + WRITE_ONCE(*(u64 *)csb, -1); + + ctx_away_valid = GEN12_CSB_CTX_VALID(upper_32_bits(entry)); + new_queue = + lower_32_bits(entry) & GEN12_CTX_STATUS_SWITCHED_TO_NEW_QUEUE; /* * The context switch detail is not guaranteed to be 5 when a preemption @@ -2513,7 +2523,7 @@ gen12_csb_parse(const struct intel_engine_execlists *execlists, const u32 *csb) * would require some extra handling, but we don't support that. */ if (!ctx_away_valid || new_queue) { - GEM_BUG_ON(!ctx_to_valid); + GEM_BUG_ON(!GEN12_CSB_CTX_VALID(lower_32_bits(entry))); return true; } @@ -2522,12 +2532,11 @@ gen12_csb_parse(const struct intel_engine_execlists *execlists, const u32 *csb) * context switch on an unsuccessful wait instruction since we always * use polling mode. */ - GEM_BUG_ON(GEN12_CTX_SWITCH_DETAIL(upper_dw)); + GEM_BUG_ON(GEN12_CTX_SWITCH_DETAIL(upper_32_bits(entry))); return false; } -static inline bool -gen8_csb_parse(const struct intel_engine_execlists *execlists, const u32 *csb) +static inline bool gen8_csb_parse(const u64 *csb) { return *csb & (GEN8_CTX_STATUS_IDLE_ACTIVE | GEN8_CTX_STATUS_PREEMPTED); } @@ -2535,7 +2544,7 @@ gen8_csb_parse(const struct intel_engine_execlists *execlists, const u32 *csb) static void process_csb(struct intel_engine_cs *engine) { struct intel_engine_execlists * const execlists = &engine->execlists; - const u32 * const buf = execlists->csb_status; + const u64 * const buf = execlists->csb_status; const u8 num_entries = execlists->csb_size; u8 head, tail; @@ -2616,12 +2625,14 @@ static void process_csb(struct intel_engine_cs *engine) */ ENGINE_TRACE(engine, "csb[%d]: status=0x%08x:0x%08x\n", - head, buf[2 * head + 0], buf[2 * head + 1]); + head, + upper_32_bits(buf[head]), + lower_32_bits(buf[head])); if (INTEL_GEN(engine->i915) >= 12) - promote = gen12_csb_parse(execlists, buf + 2 * head); + promote = gen12_csb_parse(buf + head); else - promote = gen8_csb_parse(execlists, buf + 2 * head); + promote = gen8_csb_parse(buf + head); if (promote) { struct i915_request * const *old = execlists->active; @@ -2649,6 +2660,9 @@ static void process_csb(struct intel_engine_cs *engine) smp_wmb(); /* complete the seqlock */ WRITE_ONCE(execlists->active, execlists->inflight); + /* XXX Magic delay for tgl */ + ENGINE_POSTING_READ(engine, RING_CONTEXT_STATUS_PTR); + WRITE_ONCE(execlists->pending[0], NULL); } else { if (GEM_WARN_ON(!*execlists->active)) { @@ -4005,6 +4019,8 @@ static void reset_csb_pointers(struct intel_engine_cs *engine) WRITE_ONCE(*execlists->csb_write, reset_value); wmb(); /* Make sure this is visible to HW (paranoia?) */ + /* Check that the GPU does indeed update the CSB entries! */ + memset(execlists->csb_status, -1, (reset_value + 1) * sizeof(u64)); invalidate_csb_entries(&execlists->csb_status[0], &execlists->csb_status[reset_value]); @@ -5157,7 +5173,7 @@ int intel_execlists_submission_setup(struct intel_engine_cs *engine) } execlists->csb_status = - &engine->status_page.addr[I915_HWS_CSB_BUF0_INDEX]; + (u64 *)&engine->status_page.addr[I915_HWS_CSB_BUF0_INDEX]; execlists->csb_write = &engine->status_page.addr[intel_hws_csb_write_index(i915)]; diff --git a/drivers/gpu/drm/i915/gt/intel_mocs.c b/drivers/gpu/drm/i915/gt/intel_mocs.c index 632e08a4592b..b8f56e62158e 100644 --- a/drivers/gpu/drm/i915/gt/intel_mocs.c +++ b/drivers/gpu/drm/i915/gt/intel_mocs.c @@ -234,11 +234,17 @@ static const struct drm_i915_mocs_entry broxton_mocs_table[] = { L3_1_UC) static const struct drm_i915_mocs_entry tgl_mocs_table[] = { - /* Base - Error (Reserved for Non-Use) */ - MOCS_ENTRY(0, 0x0, 0x0), - /* Base - Reserved */ - MOCS_ENTRY(1, 0x0, 0x0), - + /* + * NOTE: + * Reserved and unspecified MOCS indices have been set to (L3 + LCC). + * These reserved entries should never be used, they may be changed + * to low performant variants with better coherency in the future if + * more entries are needed. We are programming index I915_MOCS_PTE(1) + * only, __init_mocs_table() take care to program unused index with + * this entry. + */ + MOCS_ENTRY(1, LE_3_WB | LE_TC_1_LLC | LE_LRUM(3), + L3_3_WB), GEN11_MOCS_ENTRIES, /* Implicitly enable L1 - HDC:L1 + L3 + LLC */ diff --git a/drivers/gpu/drm/i915/gt/intel_workarounds.c b/drivers/gpu/drm/i915/gt/intel_workarounds.c index a3f72b75c61e..6c580d0d9ea8 100644 --- a/drivers/gpu/drm/i915/gt/intel_workarounds.c +++ b/drivers/gpu/drm/i915/gt/intel_workarounds.c @@ -70,6 +70,19 @@ const struct i915_rev_steppings kbl_revids[] = { [7] = { .gt_stepping = KBL_REVID_G0, .disp_stepping = KBL_REVID_C0 }, }; +const struct i915_rev_steppings tgl_uy_revids[] = { + [0] = { .gt_stepping = TGL_REVID_A0, .disp_stepping = TGL_REVID_A0 }, + [1] = { .gt_stepping = TGL_REVID_B0, .disp_stepping = TGL_REVID_C0 }, + [2] = { .gt_stepping = TGL_REVID_B1, .disp_stepping = TGL_REVID_C0 }, + [3] = { .gt_stepping = TGL_REVID_C0, .disp_stepping = TGL_REVID_D0 }, +}; + +/* Same GT stepping between tgl_uy_revids and tgl_revids don't mean the same HW */ +const struct i915_rev_steppings tgl_revids[] = { + [0] = { .gt_stepping = TGL_REVID_A0, .disp_stepping = TGL_REVID_B0 }, + [1] = { .gt_stepping = TGL_REVID_B0, .disp_stepping = TGL_REVID_D0 }, +}; + static void wa_init_start(struct i915_wa_list *wal, const char *name, const char *engine_name) { wal->name = name; @@ -1219,13 +1232,13 @@ tgl_gt_workarounds_init(struct drm_i915_private *i915, struct i915_wa_list *wal) gen12_gt_workarounds_init(i915, wal); /* Wa_1409420604:tgl */ - if (IS_TGL_REVID(i915, TGL_REVID_A0, TGL_REVID_A0)) + if (IS_TGL_UY_GT_REVID(i915, TGL_REVID_A0, TGL_REVID_A0)) wa_write_or(wal, SUBSLICE_UNIT_LEVEL_CLKGATE2, CPSSUNIT_CLKGATE_DIS); /* Wa_1607087056:tgl also know as BUG:1409180338 */ - if (IS_TGL_REVID(i915, TGL_REVID_A0, TGL_REVID_A0)) + if (IS_TGL_UY_GT_REVID(i915, TGL_REVID_A0, TGL_REVID_A0)) wa_write_or(wal, SLICE_UNIT_LEVEL_CLKGATE, L3_CLKGATE_DIS | L3_CR2X_CLKGATE_DIS); @@ -1660,7 +1673,7 @@ rcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal) { struct drm_i915_private *i915 = engine->i915; - if (IS_TGL_REVID(i915, TGL_REVID_A0, TGL_REVID_A0)) { + if (IS_TGL_UY_GT_REVID(i915, TGL_REVID_A0, TGL_REVID_A0)) { /* * Wa_1607138336:tgl * Wa_1607063988:tgl @@ -1700,7 +1713,7 @@ rcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal) * Wa_1407928979:tgl A* * Wa_18011464164:tgl B0+ * Wa_22010931296:tgl B0+ - * Wa_14010919138:rkl + * Wa_14010919138:rkl,tgl */ wa_write_or(wal, GEN7_FF_THREAD_MODE, GEN12_FF_TESSELATION_DOP_GATE_DISABLE); @@ -1716,15 +1729,23 @@ rcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal) GEN6_RC_SLEEP_PSMI_CONTROL, GEN12_WAIT_FOR_EVENT_POWER_DOWN_DISABLE | GEN8_RC_SEMA_IDLE_MSG_DISABLE); - } - if (IS_TIGERLAKE(i915)) { - /* Wa_1606700617:tgl */ + /* + * Wa_1606700617:tgl + * Wa_22010271021:tgl,rkl + */ wa_masked_en(wal, GEN9_CS_DEBUG_MODE1, FF_DOP_CLOCK_GATE_DISABLE); } + if (IS_GEN(i915, 12)) { + /* Wa_1406941453:gen12 */ + wa_masked_en(wal, + GEN10_SAMPLER_MODE, + ENABLE_SMALLPL); + } + if (IS_GEN(i915, 11)) { /* This is not an Wa. Enable for better image quality */ wa_masked_en(wal, diff --git a/drivers/gpu/drm/i915/gt/selftest_reset.c b/drivers/gpu/drm/i915/gt/selftest_reset.c index 35406ecdf0b2..ef5aeebbeeb0 100644 --- a/drivers/gpu/drm/i915/gt/selftest_reset.c +++ b/drivers/gpu/drm/i915/gt/selftest_reset.c @@ -3,9 +3,203 @@ * Copyright © 2018 Intel Corporation */ +#include <linux/crc32.h> + +#include "gem/i915_gem_stolen.h" + +#include "i915_memcpy.h" #include "i915_selftest.h" #include "selftests/igt_reset.h" #include "selftests/igt_atomic.h" +#include "selftests/igt_spinner.h" + +static int +__igt_reset_stolen(struct intel_gt *gt, + intel_engine_mask_t mask, + const char *msg) +{ + struct i915_ggtt *ggtt = >->i915->ggtt; + const struct resource *dsm = >->i915->dsm; + resource_size_t num_pages, page; + struct intel_engine_cs *engine; + intel_wakeref_t wakeref; + enum intel_engine_id id; + struct igt_spinner spin; + long max, count; + void *tmp; + u32 *crc; + int err; + + if (!drm_mm_node_allocated(&ggtt->error_capture)) + return 0; + + num_pages = resource_size(dsm) >> PAGE_SHIFT; + if (!num_pages) + return 0; + + crc = kmalloc_array(num_pages, sizeof(u32), GFP_KERNEL); + if (!crc) + return -ENOMEM; + + tmp = kmalloc(PAGE_SIZE, GFP_KERNEL); + if (!tmp) { + err = -ENOMEM; + goto err_crc; + } + + igt_global_reset_lock(gt); + wakeref = intel_runtime_pm_get(gt->uncore->rpm); + + err = igt_spinner_init(&spin, gt); + if (err) + goto err_lock; + + for_each_engine(engine, gt, id) { + struct intel_context *ce; + struct i915_request *rq; + + if (!(mask & engine->mask)) + continue; + + if (!intel_engine_can_store_dword(engine)) + continue; + + ce = intel_context_create(engine); + if (IS_ERR(ce)) { + err = PTR_ERR(ce); + goto err_spin; + } + rq = igt_spinner_create_request(&spin, ce, MI_ARB_CHECK); + intel_context_put(ce); + if (IS_ERR(rq)) { + err = PTR_ERR(rq); + goto err_spin; + } + i915_request_add(rq); + } + + for (page = 0; page < num_pages; page++) { + dma_addr_t dma = (dma_addr_t)dsm->start + (page << PAGE_SHIFT); + void __iomem *s; + void *in; + + ggtt->vm.insert_page(&ggtt->vm, dma, + ggtt->error_capture.start, + I915_CACHE_NONE, 0); + mb(); + + s = io_mapping_map_wc(&ggtt->iomap, + ggtt->error_capture.start, + PAGE_SIZE); + + if (!__drm_mm_interval_first(>->i915->mm.stolen, + page << PAGE_SHIFT, + ((page + 1) << PAGE_SHIFT) - 1)) + memset32(s, STACK_MAGIC, PAGE_SIZE / sizeof(u32)); + + in = s; + if (i915_memcpy_from_wc(tmp, s, PAGE_SIZE)) + in = tmp; + crc[page] = crc32_le(0, in, PAGE_SIZE); + + io_mapping_unmap(s); + } + mb(); + ggtt->vm.clear_range(&ggtt->vm, ggtt->error_capture.start, PAGE_SIZE); + + if (mask == ALL_ENGINES) { + intel_gt_reset(gt, mask, NULL); + } else { + for_each_engine(engine, gt, id) { + if (mask & engine->mask) + intel_engine_reset(engine, NULL); + } + } + + max = -1; + count = 0; + for (page = 0; page < num_pages; page++) { + dma_addr_t dma = (dma_addr_t)dsm->start + (page << PAGE_SHIFT); + void __iomem *s; + void *in; + u32 x; + + ggtt->vm.insert_page(&ggtt->vm, dma, + ggtt->error_capture.start, + I915_CACHE_NONE, 0); + mb(); + + s = io_mapping_map_wc(&ggtt->iomap, + ggtt->error_capture.start, + PAGE_SIZE); + + in = s; + if (i915_memcpy_from_wc(tmp, s, PAGE_SIZE)) + in = tmp; + x = crc32_le(0, in, PAGE_SIZE); + + if (x != crc[page] && + !__drm_mm_interval_first(>->i915->mm.stolen, + page << PAGE_SHIFT, + ((page + 1) << PAGE_SHIFT) - 1)) { + pr_debug("unused stolen page %pa modified by GPU reset\n", + &page); + if (count++ == 0) + igt_hexdump(in, PAGE_SIZE); + max = page; + } + + io_mapping_unmap(s); + } + mb(); + ggtt->vm.clear_range(&ggtt->vm, ggtt->error_capture.start, PAGE_SIZE); + + if (count > 0) { + pr_info("%s reset clobbered %ld pages of stolen, last clobber at page %ld\n", + msg, count, max); + } + if (max >= I915_GEM_STOLEN_BIAS >> PAGE_SHIFT) { + pr_err("%s reset clobbered unreserved area [above %x] of stolen; may cause severe faults\n", + msg, I915_GEM_STOLEN_BIAS); + err = -EINVAL; + } + +err_spin: + igt_spinner_fini(&spin); + +err_lock: + intel_runtime_pm_put(gt->uncore->rpm, wakeref); + igt_global_reset_unlock(gt); + + kfree(tmp); +err_crc: + kfree(crc); + return err; +} + +static int igt_reset_device_stolen(void *arg) +{ + return __igt_reset_stolen(arg, ALL_ENGINES, "device"); +} + +static int igt_reset_engines_stolen(void *arg) +{ + struct intel_gt *gt = arg; + struct intel_engine_cs *engine; + enum intel_engine_id id; + int err; + + if (!intel_has_reset_engine(gt)) + return 0; + + for_each_engine(engine, gt, id) { + err = __igt_reset_stolen(gt, engine->mask, engine->name); + if (err) + return err; + } + + return 0; +} static int igt_global_reset(void *arg) { @@ -164,6 +358,8 @@ int intel_reset_live_selftests(struct drm_i915_private *i915) { static const struct i915_subtest tests[] = { SUBTEST(igt_global_reset), /* attempt to recover GPU first */ + SUBTEST(igt_reset_device_stolen), + SUBTEST(igt_reset_engines_stolen), SUBTEST(igt_wedged_reset), SUBTEST(igt_atomic_reset), SUBTEST(igt_atomic_engine_reset), diff --git a/drivers/gpu/drm/i915/gt/shmem_utils.c b/drivers/gpu/drm/i915/gt/shmem_utils.c index 43c7acbdc79d..f011ea42487e 100644 --- a/drivers/gpu/drm/i915/gt/shmem_utils.c +++ b/drivers/gpu/drm/i915/gt/shmem_utils.c @@ -49,80 +49,40 @@ struct file *shmem_create_from_object(struct drm_i915_gem_object *obj) return file; } -static size_t shmem_npte(struct file *file) -{ - return file->f_mapping->host->i_size >> PAGE_SHIFT; -} - -static void __shmem_unpin_map(struct file *file, void *ptr, size_t n_pte) -{ - unsigned long pfn; - - vunmap(ptr); - - for (pfn = 0; pfn < n_pte; pfn++) { - struct page *page; - - page = shmem_read_mapping_page_gfp(file->f_mapping, pfn, - GFP_KERNEL); - if (!WARN_ON(IS_ERR(page))) { - put_page(page); - put_page(page); - } - } -} - void *shmem_pin_map(struct file *file) { - const size_t n_pte = shmem_npte(file); - pte_t *stack[32], **ptes, **mem; - struct vm_struct *area; - unsigned long pfn; - - mem = stack; - if (n_pte > ARRAY_SIZE(stack)) { - mem = kvmalloc_array(n_pte, sizeof(*mem), GFP_KERNEL); - if (!mem) - return NULL; - } + struct page **pages; + size_t n_pages, i; + void *vaddr; - area = alloc_vm_area(n_pte << PAGE_SHIFT, mem); - if (!area) { - if (mem != stack) - kvfree(mem); + n_pages = file->f_mapping->host->i_size >> PAGE_SHIFT; + pages = kvmalloc_array(n_pages, sizeof(*pages), GFP_KERNEL); + if (!pages) return NULL; - } - ptes = mem; - for (pfn = 0; pfn < n_pte; pfn++) { - struct page *page; - - page = shmem_read_mapping_page_gfp(file->f_mapping, pfn, - GFP_KERNEL); - if (IS_ERR(page)) + for (i = 0; i < n_pages; i++) { + pages[i] = shmem_read_mapping_page_gfp(file->f_mapping, i, + GFP_KERNEL); + if (IS_ERR(pages[i])) goto err_page; - - **ptes++ = mk_pte(page, PAGE_KERNEL); } - if (mem != stack) - kvfree(mem); - + vaddr = vmap(pages, n_pages, VM_MAP_PUT_PAGES, PAGE_KERNEL); + if (!vaddr) + goto err_page; mapping_set_unevictable(file->f_mapping); - return area->addr; - + return vaddr; err_page: - if (mem != stack) - kvfree(mem); - - __shmem_unpin_map(file, area->addr, pfn); + while (--i >= 0) + put_page(pages[i]); + kvfree(pages); return NULL; } void shmem_unpin_map(struct file *file, void *ptr) { mapping_clear_unevictable(file->f_mapping); - __shmem_unpin_map(file, ptr, shmem_npte(file)); + vfree(ptr); } static int __shmem_rw(struct file *file, loff_t off, diff --git a/drivers/gpu/drm/i915/gvt/cmd_parser.c b/drivers/gpu/drm/i915/gvt/cmd_parser.c index d0a599b51bfe..16b582cb97ed 100644 --- a/drivers/gpu/drm/i915/gvt/cmd_parser.c +++ b/drivers/gpu/drm/i915/gvt/cmd_parser.c @@ -936,7 +936,7 @@ static int cmd_reg_handler(struct parser_exec_state *s, return -EFAULT; } - if (!intel_gvt_mmio_is_cmd_access(gvt, offset)) { + if (!intel_gvt_mmio_is_cmd_accessible(gvt, offset)) { gvt_vgpu_err("%s access to non-render register (%x)\n", cmd, offset); return -EBADRQC; @@ -976,7 +976,7 @@ static int cmd_reg_handler(struct parser_exec_state *s, * inhibit context will restore with correct values */ if (IS_GEN(s->engine->i915, 9) && - intel_gvt_mmio_is_in_ctx(gvt, offset) && + intel_gvt_mmio_is_sr_in_ctx(gvt, offset) && !strncmp(cmd, "lri", 3)) { intel_gvt_hypervisor_read_gpa(s->vgpu, s->workload->ring_context_gpa + 12, &ctx_sr_ctl, 4); @@ -992,8 +992,6 @@ static int cmd_reg_handler(struct parser_exec_state *s, } } - /* TODO: Update the global mask if this MMIO is a masked-MMIO */ - intel_gvt_mmio_set_cmd_accessed(gvt, offset); return 0; } diff --git a/drivers/gpu/drm/i915/gvt/gvt.h b/drivers/gpu/drm/i915/gvt/gvt.h index ff7f2515a6fe..9831361f181e 100644 --- a/drivers/gpu/drm/i915/gvt/gvt.h +++ b/drivers/gpu/drm/i915/gvt/gvt.h @@ -256,11 +256,11 @@ struct intel_gvt_mmio { /* This reg has been accessed by a VM */ #define F_ACCESSED (1 << 4) /* This reg has been accessed through GPU commands */ -#define F_CMD_ACCESSED (1 << 5) -/* This reg could be accessed by unaligned address */ #define F_UNALIGN (1 << 6) -/* This reg is saved/restored in context */ -#define F_IN_CTX (1 << 7) +/* This reg is in GVT's mmio save-restor list and in hardware + * logical context image + */ +#define F_SR_IN_CTX (1 << 7) struct gvt_mmio_block *mmio_block; unsigned int num_mmio_block; @@ -597,39 +597,42 @@ static inline void intel_gvt_mmio_set_accessed( } /** - * intel_gvt_mmio_is_cmd_accessed - mark a MMIO could be accessed by command + * intel_gvt_mmio_is_cmd_accessible - if a MMIO could be accessed by command * @gvt: a GVT device * @offset: register offset * + * Returns: + * True if an MMIO is able to be accessed by GPU commands */ -static inline bool intel_gvt_mmio_is_cmd_access( +static inline bool intel_gvt_mmio_is_cmd_accessible( struct intel_gvt *gvt, unsigned int offset) { return gvt->mmio.mmio_attribute[offset >> 2] & F_CMD_ACCESS; } /** - * intel_gvt_mmio_is_unalign - mark a MMIO could be accessed unaligned + * intel_gvt_mmio_set_cmd_accessible - + * mark a MMIO could be accessible by command * @gvt: a GVT device * @offset: register offset * */ -static inline bool intel_gvt_mmio_is_unalign( +static inline void intel_gvt_mmio_set_cmd_accessible( struct intel_gvt *gvt, unsigned int offset) { - return gvt->mmio.mmio_attribute[offset >> 2] & F_UNALIGN; + gvt->mmio.mmio_attribute[offset >> 2] |= F_CMD_ACCESS; } /** - * intel_gvt_mmio_set_cmd_accessed - mark a MMIO has been accessed by command + * intel_gvt_mmio_is_unalign - mark a MMIO could be accessed unaligned * @gvt: a GVT device * @offset: register offset * */ -static inline void intel_gvt_mmio_set_cmd_accessed( +static inline bool intel_gvt_mmio_is_unalign( struct intel_gvt *gvt, unsigned int offset) { - gvt->mmio.mmio_attribute[offset >> 2] |= F_CMD_ACCESSED; + return gvt->mmio.mmio_attribute[offset >> 2] & F_UNALIGN; } /** @@ -648,30 +651,33 @@ static inline bool intel_gvt_mmio_has_mode_mask( } /** - * intel_gvt_mmio_is_in_ctx - check if a MMIO has in-ctx mask + * intel_gvt_mmio_is_sr_in_ctx - + * check if an MMIO has F_SR_IN_CTX mask * @gvt: a GVT device * @offset: register offset * * Returns: - * True if a MMIO has a in-context mask, false if it isn't. + * True if an MMIO has an F_SR_IN_CTX mask, false if it isn't. * */ -static inline bool intel_gvt_mmio_is_in_ctx( +static inline bool intel_gvt_mmio_is_sr_in_ctx( struct intel_gvt *gvt, unsigned int offset) { - return gvt->mmio.mmio_attribute[offset >> 2] & F_IN_CTX; + return gvt->mmio.mmio_attribute[offset >> 2] & F_SR_IN_CTX; } /** - * intel_gvt_mmio_set_in_ctx - mask a MMIO in logical context + * intel_gvt_mmio_set_sr_in_ctx - + * mask an MMIO in GVT's mmio save-restore list and also + * in hardware logical context image * @gvt: a GVT device * @offset: register offset * */ -static inline void intel_gvt_mmio_set_in_ctx( +static inline void intel_gvt_mmio_set_sr_in_ctx( struct intel_gvt *gvt, unsigned int offset) { - gvt->mmio.mmio_attribute[offset >> 2] |= F_IN_CTX; + gvt->mmio.mmio_attribute[offset >> 2] |= F_SR_IN_CTX; } void intel_gvt_debugfs_add_vgpu(struct intel_vgpu *vgpu); diff --git a/drivers/gpu/drm/i915/gvt/handlers.c b/drivers/gpu/drm/i915/gvt/handlers.c index 05f3bc98d242..3be37e6fe33d 100644 --- a/drivers/gpu/drm/i915/gvt/handlers.c +++ b/drivers/gpu/drm/i915/gvt/handlers.c @@ -1892,7 +1892,7 @@ static int init_generic_mmio_info(struct intel_gvt *gvt) struct drm_i915_private *dev_priv = gvt->gt->i915; int ret; - MMIO_RING_DFH(RING_IMR, D_ALL, F_CMD_ACCESS, NULL, + MMIO_RING_DFH(RING_IMR, D_ALL, 0, NULL, intel_vgpu_reg_imr_handler); MMIO_DFH(SDEIMR, D_ALL, 0, NULL, intel_vgpu_reg_imr_handler); @@ -1900,7 +1900,8 @@ static int init_generic_mmio_info(struct intel_gvt *gvt) MMIO_DFH(SDEIIR, D_ALL, 0, NULL, intel_vgpu_reg_iir_handler); MMIO_D(SDEISR, D_ALL); - MMIO_RING_DFH(RING_HWSTAM, D_ALL, F_CMD_ACCESS, NULL, NULL); + MMIO_RING_DFH(RING_HWSTAM, D_ALL, 0, NULL, NULL); + MMIO_DH(GEN8_GAMW_ECO_DEV_RW_IA, D_BDW_PLUS, NULL, gamw_echo_dev_rw_ia_write); @@ -1927,11 +1928,11 @@ static int init_generic_mmio_info(struct intel_gvt *gvt) MMIO_GM_RDR(_MMIO(0x12198), D_ALL, NULL, NULL); MMIO_D(GEN7_CXT_SIZE, D_ALL); - MMIO_RING_DFH(RING_TAIL, D_ALL, F_CMD_ACCESS, NULL, NULL); - MMIO_RING_DFH(RING_HEAD, D_ALL, F_CMD_ACCESS, NULL, NULL); - MMIO_RING_DFH(RING_CTL, D_ALL, F_CMD_ACCESS, NULL, NULL); - MMIO_RING_DFH(RING_ACTHD, D_ALL, F_CMD_ACCESS, mmio_read_from_hw, NULL); - MMIO_RING_GM_RDR(RING_START, D_ALL, NULL, NULL); + MMIO_RING_DFH(RING_TAIL, D_ALL, 0, NULL, NULL); + MMIO_RING_DFH(RING_HEAD, D_ALL, 0, NULL, NULL); + MMIO_RING_DFH(RING_CTL, D_ALL, 0, NULL, NULL); + MMIO_RING_DFH(RING_ACTHD, D_ALL, 0, mmio_read_from_hw, NULL); + MMIO_RING_GM(RING_START, D_ALL, NULL, NULL); /* RING MODE */ #define RING_REG(base) _MMIO((base) + 0x29c) @@ -2686,7 +2687,7 @@ static int init_generic_mmio_info(struct intel_gvt *gvt) MMIO_DFH(_MMIO(0x4094), D_BDW_PLUS, F_CMD_ACCESS, NULL, NULL); MMIO_DFH(ARB_MODE, D_ALL, F_MODE_MASK | F_CMD_ACCESS, NULL, NULL); - MMIO_RING_GM_RDR(RING_BBADDR, D_ALL, NULL, NULL); + MMIO_RING_GM(RING_BBADDR, D_ALL, NULL, NULL); MMIO_DFH(_MMIO(0x2220), D_ALL, F_CMD_ACCESS, NULL, NULL); MMIO_DFH(_MMIO(0x12220), D_ALL, F_CMD_ACCESS, NULL, NULL); MMIO_DFH(_MMIO(0x22220), D_ALL, F_CMD_ACCESS, NULL, NULL); @@ -2771,7 +2772,7 @@ static int init_bdw_mmio_info(struct intel_gvt *gvt) MMIO_DH(GEN8_MASTER_IRQ, D_BDW_PLUS, NULL, intel_vgpu_reg_master_irq_handler); - MMIO_RING_DFH(RING_ACTHD_UDW, D_BDW_PLUS, F_CMD_ACCESS, + MMIO_RING_DFH(RING_ACTHD_UDW, D_BDW_PLUS, 0, mmio_read_from_hw, NULL); #define RING_REG(base) _MMIO((base) + 0xd0) @@ -2785,7 +2786,7 @@ static int init_bdw_mmio_info(struct intel_gvt *gvt) #undef RING_REG #define RING_REG(base) _MMIO((base) + 0x234) - MMIO_RING_F(RING_REG, 8, F_RO | F_CMD_ACCESS, 0, ~0, D_BDW_PLUS, + MMIO_RING_F(RING_REG, 8, F_RO, 0, ~0, D_BDW_PLUS, NULL, NULL); #undef RING_REG @@ -2820,7 +2821,7 @@ static int init_bdw_mmio_info(struct intel_gvt *gvt) MMIO_RING_F(RING_REG, 32, F_CMD_ACCESS, 0, 0, D_BDW_PLUS, NULL, NULL); #undef RING_REG - MMIO_RING_GM_RDR(RING_HWS_PGA, D_BDW_PLUS, NULL, hws_pga_write); + MMIO_RING_GM(RING_HWS_PGA, D_BDW_PLUS, NULL, hws_pga_write); MMIO_DFH(HDC_CHICKEN0, D_BDW_PLUS, F_MODE_MASK | F_CMD_ACCESS, NULL, NULL); @@ -2921,7 +2922,7 @@ static int init_skl_mmio_info(struct intel_gvt *gvt) MMIO_D(GEN9_MEDIA_PG_IDLE_HYSTERESIS, D_SKL_PLUS); MMIO_D(GEN9_RENDER_PG_IDLE_HYSTERESIS, D_SKL_PLUS); MMIO_DFH(GEN9_GAMT_ECO_REG_RW_IA, D_SKL_PLUS, F_CMD_ACCESS, NULL, NULL); - MMIO_DH(MMCD_MISC_CTRL, D_SKL_PLUS, NULL, NULL); + MMIO_DFH(MMCD_MISC_CTRL, D_SKL_PLUS, F_CMD_ACCESS, NULL, NULL); MMIO_DH(CHICKEN_PAR1_1, D_SKL_PLUS, NULL, NULL); MMIO_D(DC_STATE_EN, D_SKL_PLUS); MMIO_D(DC_STATE_DEBUG, D_SKL_PLUS); @@ -3137,7 +3138,7 @@ static int init_skl_mmio_info(struct intel_gvt *gvt) MMIO_DFH(GEN9_WM_CHICKEN3, D_SKL_PLUS, F_MODE_MASK | F_CMD_ACCESS, NULL, NULL); - MMIO_D(GAMT_CHKN_BIT_REG, D_KBL | D_CFL); + MMIO_DFH(GAMT_CHKN_BIT_REG, D_KBL | D_CFL, F_CMD_ACCESS, NULL, NULL); MMIO_D(GEN9_CTX_PREEMPT_REG, D_SKL_PLUS); return 0; @@ -3357,7 +3358,10 @@ void intel_gvt_clean_mmio_info(struct intel_gvt *gvt) gvt->mmio.mmio_attribute = NULL; } -/* Special MMIO blocks. */ +/* Special MMIO blocks. registers in MMIO block ranges should not be command + * accessible (should have no F_CMD_ACCESS flag). + * otherwise, need to update cmd_reg_handler in cmd_parser.c + */ static struct gvt_mmio_block mmio_blocks[] = { {D_SKL_PLUS, _MMIO(CSR_MMIO_START_RANGE), 0x3000, NULL, NULL}, {D_ALL, _MMIO(MCHBAR_MIRROR_BASE_SNB), 0x40000, NULL, NULL}, diff --git a/drivers/gpu/drm/i915/gvt/mmio.c b/drivers/gpu/drm/i915/gvt/mmio.c index 291993615af9..b6811f6a230d 100644 --- a/drivers/gpu/drm/i915/gvt/mmio.c +++ b/drivers/gpu/drm/i915/gvt/mmio.c @@ -251,6 +251,9 @@ void intel_vgpu_reset_mmio(struct intel_vgpu *vgpu, bool dmlr) /* set the bit 0:2(Core C-State ) to C0 */ vgpu_vreg_t(vgpu, GEN6_GT_CORE_STATUS) = 0; + /* uc reset hw expect GS_MIA_IN_RESET */ + vgpu_vreg_t(vgpu, GUC_STATUS) |= GS_MIA_IN_RESET; + if (IS_BROXTON(vgpu->gvt->gt->i915)) { vgpu_vreg_t(vgpu, BXT_P_CR_GT_DISP_PWRON) &= ~(BIT(0) | BIT(1)); diff --git a/drivers/gpu/drm/i915/gvt/mmio_context.c b/drivers/gpu/drm/i915/gvt/mmio_context.c index 86a60bdf0818..afe574d6b3b5 100644 --- a/drivers/gpu/drm/i915/gvt/mmio_context.c +++ b/drivers/gpu/drm/i915/gvt/mmio_context.c @@ -595,7 +595,7 @@ void intel_gvt_init_engine_mmio_context(struct intel_gvt *gvt) i915_mmio_reg_valid(mmio->reg); mmio++) { if (mmio->in_context) { gvt->engine_mmio_list.ctx_mmio_count[mmio->id]++; - intel_gvt_mmio_set_in_ctx(gvt, mmio->reg.reg); + intel_gvt_mmio_set_sr_in_ctx(gvt, mmio->reg.reg); } } } diff --git a/drivers/gpu/drm/i915/gvt/vgpu.c b/drivers/gpu/drm/i915/gvt/vgpu.c index 8fa9b31a2484..f6d7e33c7099 100644 --- a/drivers/gpu/drm/i915/gvt/vgpu.c +++ b/drivers/gpu/drm/i915/gvt/vgpu.c @@ -368,6 +368,7 @@ void intel_gvt_destroy_idle_vgpu(struct intel_vgpu *vgpu) static struct intel_vgpu *__intel_gvt_create_vgpu(struct intel_gvt *gvt, struct intel_vgpu_creation_params *param) { + struct drm_i915_private *dev_priv = gvt->gt->i915; struct intel_vgpu *vgpu; int ret; @@ -436,7 +437,10 @@ static struct intel_vgpu *__intel_gvt_create_vgpu(struct intel_gvt *gvt, if (ret) goto out_clean_sched_policy; - ret = intel_gvt_hypervisor_set_edid(vgpu, PORT_D); + if (IS_BROADWELL(dev_priv)) + ret = intel_gvt_hypervisor_set_edid(vgpu, PORT_B); + else + ret = intel_gvt_hypervisor_set_edid(vgpu, PORT_D); if (ret) goto out_clean_sched_policy; diff --git a/drivers/gpu/drm/i915/i915_active.c b/drivers/gpu/drm/i915/i915_active.c index b0a6522be3d1..10a865f3dc09 100644 --- a/drivers/gpu/drm/i915/i915_active.c +++ b/drivers/gpu/drm/i915/i915_active.c @@ -83,7 +83,7 @@ static void *active_debug_hint(void *addr) return (void *)ref->active ?: (void *)ref->retire ?: (void *)ref; } -static struct debug_obj_descr active_debug_desc = { +static const struct debug_obj_descr active_debug_desc = { .name = "i915_active", .debug_hint = active_debug_hint, }; diff --git a/drivers/gpu/drm/i915/i915_cmd_parser.c b/drivers/gpu/drm/i915/i915_cmd_parser.c index 5ac4a999f05a..e88970256e8e 100644 --- a/drivers/gpu/drm/i915/i915_cmd_parser.c +++ b/drivers/gpu/drm/i915/i915_cmd_parser.c @@ -1136,7 +1136,7 @@ find_reg(const struct intel_engine_cs *engine, u32 addr) /* Returns a vmap'd pointer to dst_obj, which the caller must unmap */ static u32 *copy_batch(struct drm_i915_gem_object *dst_obj, struct drm_i915_gem_object *src_obj, - u32 offset, u32 length) + unsigned long offset, unsigned long length) { bool needs_clflush; void *dst, *src; @@ -1166,8 +1166,8 @@ static u32 *copy_batch(struct drm_i915_gem_object *dst_obj, } } if (IS_ERR(src)) { + unsigned long x, n; void *ptr; - int x, n; /* * We can avoid clflushing partial cachelines before the write @@ -1184,7 +1184,7 @@ static u32 *copy_batch(struct drm_i915_gem_object *dst_obj, ptr = dst; x = offset_in_page(offset); for (n = offset >> PAGE_SHIFT; length; n++) { - int len = min_t(int, length, PAGE_SIZE - x); + int len = min(length, PAGE_SIZE - x); src = kmap_atomic(i915_gem_object_get_page(src_obj, n)); if (needs_clflush) @@ -1414,8 +1414,8 @@ static bool shadow_needs_clflush(struct drm_i915_gem_object *obj) */ int intel_engine_cmd_parser(struct intel_engine_cs *engine, struct i915_vma *batch, - u32 batch_offset, - u32 batch_length, + unsigned long batch_offset, + unsigned long batch_length, struct i915_vma *shadow, bool trampoline) { diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c index 784219962193..ea469168cd44 100644 --- a/drivers/gpu/drm/i915/i915_debugfs.c +++ b/drivers/gpu/drm/i915/i915_debugfs.c @@ -326,6 +326,7 @@ static void print_context_stats(struct seq_file *m, } i915_gem_context_unlock_engines(ctx); + mutex_lock(&ctx->mutex); if (!IS_ERR_OR_NULL(ctx->file_priv)) { struct file_stats stats = { .vm = rcu_access_pointer(ctx->vm), @@ -346,6 +347,7 @@ static void print_context_stats(struct seq_file *m, print_file_stats(m, name, stats); } + mutex_unlock(&ctx->mutex); spin_lock(&i915->gem.contexts.lock); list_safe_reset_next(ctx, cn, link); diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c index d580d86a75d4..45e719c79183 100644 --- a/drivers/gpu/drm/i915/i915_drv.c +++ b/drivers/gpu/drm/i915/i915_drv.c @@ -58,7 +58,6 @@ #include "display/intel_hotplug.h" #include "display/intel_overlay.h" #include "display/intel_pipe_crc.h" -#include "display/intel_psr.h" #include "display/intel_sprite.h" #include "display/intel_vga.h" @@ -216,125 +215,6 @@ intel_teardown_mchbar(struct drm_i915_private *dev_priv) release_resource(&dev_priv->mch_res); } -/* part #1: call before irq install */ -static int i915_driver_modeset_probe_noirq(struct drm_i915_private *i915) -{ - int ret; - - if (i915_inject_probe_failure(i915)) - return -ENODEV; - - if (HAS_DISPLAY(i915) && INTEL_DISPLAY_ENABLED(i915)) { - ret = drm_vblank_init(&i915->drm, - INTEL_NUM_PIPES(i915)); - if (ret) - return ret; - } - - intel_bios_init(i915); - - ret = intel_vga_register(i915); - if (ret) - goto cleanup_bios; - - intel_power_domains_init_hw(i915, false); - - intel_csr_ucode_init(i915); - - ret = intel_modeset_init_noirq(i915); - if (ret) - goto cleanup_vga_client_pw_domain_csr; - - return 0; - -cleanup_vga_client_pw_domain_csr: - intel_csr_ucode_fini(i915); - intel_power_domains_driver_remove(i915); - intel_vga_unregister(i915); -cleanup_bios: - intel_bios_driver_remove(i915); - return ret; -} - -/* part #2: call after irq install */ -static int i915_driver_modeset_probe(struct drm_i915_private *i915) -{ - int ret; - - /* Important: The output setup functions called by modeset_init need - * working irqs for e.g. gmbus and dp aux transfers. */ - ret = intel_modeset_init(i915); - if (ret) - goto out; - - ret = i915_gem_init(i915); - if (ret) - goto cleanup_modeset; - - intel_overlay_setup(i915); - - if (!HAS_DISPLAY(i915) || !INTEL_DISPLAY_ENABLED(i915)) - return 0; - - ret = intel_fbdev_init(&i915->drm); - if (ret) - goto cleanup_gem; - - /* Only enable hotplug handling once the fbdev is fully set up. */ - intel_hpd_init(i915); - - intel_init_ipc(i915); - - intel_psr_set_force_mode_changed(i915->psr.dp); - - return 0; - -cleanup_gem: - i915_gem_suspend(i915); - i915_gem_driver_remove(i915); - i915_gem_driver_release(i915); -cleanup_modeset: - /* FIXME */ - intel_modeset_driver_remove(i915); - intel_irq_uninstall(i915); - intel_modeset_driver_remove_noirq(i915); -out: - return ret; -} - -/* part #1: call before irq uninstall */ -static void i915_driver_modeset_remove(struct drm_i915_private *i915) -{ - intel_modeset_driver_remove(i915); -} - -/* part #2: call after irq uninstall */ -static void i915_driver_modeset_remove_noirq(struct drm_i915_private *i915) -{ - intel_csr_ucode_fini(i915); - - intel_power_domains_driver_remove(i915); - - intel_vga_unregister(i915); - - intel_bios_driver_remove(i915); -} - -static void intel_init_dpio(struct drm_i915_private *dev_priv) -{ - /* - * IOSF_PORT_DPIO is used for VLV x2 PHY (DP/HDMI B and C), - * CHV x1 PHY (DP/HDMI D) - * IOSF_PORT_DPIO_2 is used for CHV x2 PHY (DP/HDMI B and C) - */ - if (IS_CHERRYVIEW(dev_priv)) { - DPIO_PHY_IOSF_PORT(DPIO_PHY0) = IOSF_PORT_DPIO_2; - DPIO_PHY_IOSF_PORT(DPIO_PHY1) = IOSF_PORT_DPIO; - } else if (IS_VALLEYVIEW(dev_priv)) { - DPIO_PHY_IOSF_PORT(DPIO_PHY0) = IOSF_PORT_DPIO; - } -} - static int i915_workqueues_init(struct drm_i915_private *dev_priv) { /* @@ -463,7 +343,6 @@ static int i915_driver_early_probe(struct drm_i915_private *dev_priv) intel_detect_pch(dev_priv); intel_pm_setup(dev_priv); - intel_init_dpio(dev_priv); ret = intel_power_domains_init(dev_priv); if (ret < 0) goto err_gem; @@ -798,7 +677,7 @@ static void i915_driver_register(struct drm_i915_private *dev_priv) drm_err(&dev_priv->drm, "Failed to register driver for userspace access!\n"); - if (HAS_DISPLAY(dev_priv) && INTEL_DISPLAY_ENABLED(dev_priv)) { + if (HAS_DISPLAY(dev_priv)) { /* Must be done after probing outputs */ intel_opregion_register(dev_priv); acpi_video_register(); @@ -821,7 +700,7 @@ static void i915_driver_register(struct drm_i915_private *dev_priv) * We need to coordinate the hotplugs with the asynchronous fbdev * configuration, for which we use the fbdev->async_cookie. */ - if (HAS_DISPLAY(dev_priv) && INTEL_DISPLAY_ENABLED(dev_priv)) + if (HAS_DISPLAY(dev_priv)) drm_kms_helper_poll_init(dev); intel_power_domains_enable(dev_priv); @@ -988,7 +867,7 @@ int i915_driver_probe(struct pci_dev *pdev, const struct pci_device_id *ent) if (ret < 0) goto out_cleanup_mmio; - ret = i915_driver_modeset_probe_noirq(i915); + ret = intel_modeset_init_noirq(i915); if (ret < 0) goto out_cleanup_hw; @@ -996,10 +875,18 @@ int i915_driver_probe(struct pci_dev *pdev, const struct pci_device_id *ent) if (ret) goto out_cleanup_modeset; - ret = i915_driver_modeset_probe(i915); - if (ret < 0) + ret = intel_modeset_init_nogem(i915); + if (ret) goto out_cleanup_irq; + ret = i915_gem_init(i915); + if (ret) + goto out_cleanup_modeset2; + + ret = intel_modeset_init(i915); + if (ret) + goto out_cleanup_gem; + i915_driver_register(i915); enable_rpm_wakeref_asserts(&i915->runtime_pm); @@ -1010,10 +897,20 @@ int i915_driver_probe(struct pci_dev *pdev, const struct pci_device_id *ent) return 0; +out_cleanup_gem: + i915_gem_suspend(i915); + i915_gem_driver_remove(i915); + i915_gem_driver_release(i915); +out_cleanup_modeset2: + /* FIXME clean up the error path */ + intel_modeset_driver_remove(i915); + intel_irq_uninstall(i915); + intel_modeset_driver_remove_noirq(i915); + goto out_cleanup_modeset; out_cleanup_irq: intel_irq_uninstall(i915); out_cleanup_modeset: - i915_driver_modeset_remove_noirq(i915); + intel_modeset_driver_remove_nogem(i915); out_cleanup_hw: i915_driver_hw_remove(i915); intel_memory_regions_driver_release(i915); @@ -1045,7 +942,7 @@ void i915_driver_remove(struct drm_i915_private *i915) intel_gvt_driver_remove(i915); - i915_driver_modeset_remove(i915); + intel_modeset_driver_remove(i915); intel_irq_uninstall(i915); @@ -1054,7 +951,7 @@ void i915_driver_remove(struct drm_i915_private *i915) i915_reset_error_state(i915); i915_gem_driver_remove(i915); - i915_driver_modeset_remove_noirq(i915); + intel_modeset_driver_remove_nogem(i915); i915_driver_hw_remove(i915); diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index ab17084af0ff..8426d5974669 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -33,6 +33,8 @@ #include <uapi/drm/i915_drm.h> #include <uapi/drm/drm_fourcc.h> +#include <asm/hypervisor.h> + #include <linux/io-mapping.h> #include <linux/i2c.h> #include <linux/i2c-algo-bit.h> @@ -108,18 +110,11 @@ #define DRIVER_NAME "i915" #define DRIVER_DESC "Intel Graphics" -#define DRIVER_DATE "20200824" -#define DRIVER_TIMESTAMP 1598293597 +#define DRIVER_DATE "20200917" +#define DRIVER_TIMESTAMP 1600375437 struct drm_i915_gem_object; -/* - * The code assumes that the hpd_pins below have consecutive values and - * starting with HPD_PORT_A, the HPD pin associated with any port can be - * retrieved by adding the corresponding port (or phy) enum value to - * HPD_PORT_A in most cases. For example: - * HPD_PORT_C = HPD_PORT_A + PHY_C - PHY_A - */ enum hpd_pin { HPD_NONE = 0, HPD_TV = HPD_NONE, /* TV is known to be unreliable */ @@ -131,10 +126,12 @@ enum hpd_pin { HPD_PORT_C, HPD_PORT_D, HPD_PORT_E, - HPD_PORT_F, - HPD_PORT_G, - HPD_PORT_H, - HPD_PORT_I, + HPD_PORT_TC1, + HPD_PORT_TC2, + HPD_PORT_TC3, + HPD_PORT_TC4, + HPD_PORT_TC5, + HPD_PORT_TC6, HPD_NUM_PINS }; @@ -537,13 +534,9 @@ struct intel_gmbus { struct i915_suspend_saved_registers { u32 saveDSPARB; - u32 saveFBC_CONTROL; - u32 saveCACHE_MODE_0; - u32 saveMI_ARB_STATE; u32 saveSWF0[16]; u32 saveSWF1[16]; u32 saveSWF3[3]; - u32 savePCH_PORT_HOTPLUG; u16 saveGCDGMBUS; }; @@ -1020,8 +1013,6 @@ struct drm_i915_private { */ u8 active_pipes; - int dpio_phy_iosf_port[I915_NUM_PHYS_VLV]; - struct i915_wa_list gt_wa_list; struct i915_frontbuffer_tracking fb_tracking; @@ -1572,12 +1563,41 @@ extern const struct i915_rev_steppings kbl_revids[]; #define IS_EHL_REVID(p, since, until) \ (IS_ELKHARTLAKE(p) && IS_REVID(p, since, until)) -#define TGL_REVID_A0 0x0 -#define TGL_REVID_B0 0x1 -#define TGL_REVID_C0 0x2 +enum { + TGL_REVID_A0, + TGL_REVID_B0, + TGL_REVID_B1, + TGL_REVID_C0, + TGL_REVID_D0, +}; -#define IS_TGL_REVID(p, since, until) \ - (IS_TIGERLAKE(p) && IS_REVID(p, since, until)) +extern const struct i915_rev_steppings tgl_uy_revids[]; +extern const struct i915_rev_steppings tgl_revids[]; + +static inline const struct i915_rev_steppings * +tgl_revids_get(struct drm_i915_private *dev_priv) +{ + if (IS_TGL_U(dev_priv) || IS_TGL_Y(dev_priv)) + return tgl_uy_revids; + else + return tgl_revids; +} + +#define IS_TGL_DISP_REVID(p, since, until) \ + (IS_TIGERLAKE(p) && \ + tgl_revids_get(p)->disp_stepping >= (since) && \ + tgl_revids_get(p)->disp_stepping <= (until)) + +#define IS_TGL_UY_GT_REVID(p, since, until) \ + ((IS_TGL_U(p) || IS_TGL_Y(p)) && \ + tgl_uy_revids->gt_stepping >= (since) && \ + tgl_uy_revids->gt_stepping <= (until)) + +#define IS_TGL_GT_REVID(p, since, until) \ + (IS_TIGERLAKE(p) && \ + !(IS_TGL_U(p) || IS_TGL_Y(p)) && \ + tgl_revids->gt_stepping >= (since) && \ + tgl_revids->gt_stepping <= (until)) #define RKL_REVID_A0 0x0 #define RKL_REVID_B0 0x1 @@ -1742,7 +1762,9 @@ static inline bool intel_vtd_active(void) if (intel_iommu_gfx_mapped) return true; #endif - return false; + + /* Running as a guest, we assume the host is enforcing VT'd */ + return !hypervisor_is_type(X86_HYPER_NATIVE); } static inline bool intel_scanout_needs_vtd_wa(struct drm_i915_private *dev_priv) @@ -1931,8 +1953,8 @@ void intel_engine_init_cmd_parser(struct intel_engine_cs *engine); void intel_engine_cleanup_cmd_parser(struct intel_engine_cs *engine); int intel_engine_cmd_parser(struct intel_engine_cs *engine, struct i915_vma *batch, - u32 batch_offset, - u32 batch_length, + unsigned long batch_offset, + unsigned long batch_length, struct i915_vma *shadow, bool trampoline); #define I915_CMD_PARSER_TRAMPOLINE_SIZE 8 diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c index 3e6cbb0d1150..cf6e47adfde6 100644 --- a/drivers/gpu/drm/i915/i915_gpu_error.c +++ b/drivers/gpu/drm/i915/i915_gpu_error.c @@ -311,6 +311,8 @@ static int compress_page(struct i915_vma_compress *c, if (zlib_deflate(zstream, Z_NO_FLUSH) != Z_OK) return -EIO; + + cond_resched(); } while (zstream->avail_in); /* Fallback to uncompressed if we increase size? */ @@ -397,6 +399,7 @@ static int compress_page(struct i915_vma_compress *c, if (!(wc && i915_memcpy_from_wc(ptr, src, PAGE_SIZE))) memcpy(ptr, src, PAGE_SIZE); dst->pages[dst->page_count++] = ptr; + cond_resched(); return 0; } @@ -1309,7 +1312,7 @@ capture_vma(struct intel_engine_capture_vma *next, } strcpy(c->name, name); - c->vma = i915_vma_get(vma); + c->vma = vma; /* reference held while active */ c->next = next; return c; @@ -1399,7 +1402,6 @@ intel_engine_coredump_add_vma(struct intel_engine_coredump *ee, compress)); i915_active_release(&vma->active); - i915_vma_put(vma); capture = this->next; kfree(this); diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c index f113fe44572b..759f523c6a6b 100644 --- a/drivers/gpu/drm/i915/i915_irq.c +++ b/drivers/gpu/drm/i915/i915_irq.c @@ -132,40 +132,24 @@ static const u32 hpd_bxt[HPD_NUM_PINS] = { }; static const u32 hpd_gen11[HPD_NUM_PINS] = { - [HPD_PORT_C] = GEN11_TC1_HOTPLUG | GEN11_TBT1_HOTPLUG, - [HPD_PORT_D] = GEN11_TC2_HOTPLUG | GEN11_TBT2_HOTPLUG, - [HPD_PORT_E] = GEN11_TC3_HOTPLUG | GEN11_TBT3_HOTPLUG, - [HPD_PORT_F] = GEN11_TC4_HOTPLUG | GEN11_TBT4_HOTPLUG, -}; - -static const u32 hpd_gen12[HPD_NUM_PINS] = { - [HPD_PORT_D] = GEN11_TC1_HOTPLUG | GEN11_TBT1_HOTPLUG, - [HPD_PORT_E] = GEN11_TC2_HOTPLUG | GEN11_TBT2_HOTPLUG, - [HPD_PORT_F] = GEN11_TC3_HOTPLUG | GEN11_TBT3_HOTPLUG, - [HPD_PORT_G] = GEN11_TC4_HOTPLUG | GEN11_TBT4_HOTPLUG, - [HPD_PORT_H] = GEN12_TC5_HOTPLUG | GEN12_TBT5_HOTPLUG, - [HPD_PORT_I] = GEN12_TC6_HOTPLUG | GEN12_TBT6_HOTPLUG, + [HPD_PORT_TC1] = GEN11_TC_HOTPLUG(PORT_TC1) | GEN11_TBT_HOTPLUG(PORT_TC1), + [HPD_PORT_TC2] = GEN11_TC_HOTPLUG(PORT_TC2) | GEN11_TBT_HOTPLUG(PORT_TC2), + [HPD_PORT_TC3] = GEN11_TC_HOTPLUG(PORT_TC3) | GEN11_TBT_HOTPLUG(PORT_TC3), + [HPD_PORT_TC4] = GEN11_TC_HOTPLUG(PORT_TC4) | GEN11_TBT_HOTPLUG(PORT_TC4), + [HPD_PORT_TC5] = GEN11_TC_HOTPLUG(PORT_TC5) | GEN11_TBT_HOTPLUG(PORT_TC5), + [HPD_PORT_TC6] = GEN11_TC_HOTPLUG(PORT_TC6) | GEN11_TBT_HOTPLUG(PORT_TC6), }; static const u32 hpd_icp[HPD_NUM_PINS] = { [HPD_PORT_A] = SDE_DDI_HOTPLUG_ICP(PORT_A), [HPD_PORT_B] = SDE_DDI_HOTPLUG_ICP(PORT_B), - [HPD_PORT_C] = SDE_TC_HOTPLUG_ICP(PORT_TC1), - [HPD_PORT_D] = SDE_TC_HOTPLUG_ICP(PORT_TC2), - [HPD_PORT_E] = SDE_TC_HOTPLUG_ICP(PORT_TC3), - [HPD_PORT_F] = SDE_TC_HOTPLUG_ICP(PORT_TC4), -}; - -static const u32 hpd_tgp[HPD_NUM_PINS] = { - [HPD_PORT_A] = SDE_DDI_HOTPLUG_ICP(PORT_A), - [HPD_PORT_B] = SDE_DDI_HOTPLUG_ICP(PORT_B), [HPD_PORT_C] = SDE_DDI_HOTPLUG_ICP(PORT_C), - [HPD_PORT_D] = SDE_TC_HOTPLUG_ICP(PORT_TC1), - [HPD_PORT_E] = SDE_TC_HOTPLUG_ICP(PORT_TC2), - [HPD_PORT_F] = SDE_TC_HOTPLUG_ICP(PORT_TC3), - [HPD_PORT_G] = SDE_TC_HOTPLUG_ICP(PORT_TC4), - [HPD_PORT_H] = SDE_TC_HOTPLUG_ICP(PORT_TC5), - [HPD_PORT_I] = SDE_TC_HOTPLUG_ICP(PORT_TC6), + [HPD_PORT_TC1] = SDE_TC_HOTPLUG_ICP(PORT_TC1), + [HPD_PORT_TC2] = SDE_TC_HOTPLUG_ICP(PORT_TC2), + [HPD_PORT_TC3] = SDE_TC_HOTPLUG_ICP(PORT_TC3), + [HPD_PORT_TC4] = SDE_TC_HOTPLUG_ICP(PORT_TC4), + [HPD_PORT_TC5] = SDE_TC_HOTPLUG_ICP(PORT_TC5), + [HPD_PORT_TC6] = SDE_TC_HOTPLUG_ICP(PORT_TC6), }; static void intel_hpd_init_pins(struct drm_i915_private *dev_priv) @@ -181,9 +165,7 @@ static void intel_hpd_init_pins(struct drm_i915_private *dev_priv) return; } - if (INTEL_GEN(dev_priv) >= 12) - hpd->hpd = hpd_gen12; - else if (INTEL_GEN(dev_priv) >= 11) + if (INTEL_GEN(dev_priv) >= 11) hpd->hpd = hpd_gen11; else if (IS_GEN9_LP(dev_priv)) hpd->hpd = hpd_bxt; @@ -197,9 +179,8 @@ static void intel_hpd_init_pins(struct drm_i915_private *dev_priv) if (!HAS_PCH_SPLIT(dev_priv) || HAS_PCH_NOP(dev_priv)) return; - if (HAS_PCH_TGP(dev_priv) || HAS_PCH_JSP(dev_priv)) - hpd->pch_hpd = hpd_tgp; - else if (HAS_PCH_ICP(dev_priv) || HAS_PCH_MCC(dev_priv)) + if (HAS_PCH_TGP(dev_priv) || HAS_PCH_JSP(dev_priv) || + HAS_PCH_ICP(dev_priv) || HAS_PCH_MCC(dev_priv)) hpd->pch_hpd = hpd_icp; else if (HAS_PCH_CNP(dev_priv) || HAS_PCH_SPT(dev_priv)) hpd->pch_hpd = hpd_spt; @@ -1049,33 +1030,17 @@ out: static bool gen11_port_hotplug_long_detect(enum hpd_pin pin, u32 val) { switch (pin) { - case HPD_PORT_C: - return val & GEN11_HOTPLUG_CTL_LONG_DETECT(PORT_TC1); - case HPD_PORT_D: - return val & GEN11_HOTPLUG_CTL_LONG_DETECT(PORT_TC2); - case HPD_PORT_E: - return val & GEN11_HOTPLUG_CTL_LONG_DETECT(PORT_TC3); - case HPD_PORT_F: - return val & GEN11_HOTPLUG_CTL_LONG_DETECT(PORT_TC4); - default: - return false; - } -} - -static bool gen12_port_hotplug_long_detect(enum hpd_pin pin, u32 val) -{ - switch (pin) { - case HPD_PORT_D: + case HPD_PORT_TC1: return val & GEN11_HOTPLUG_CTL_LONG_DETECT(PORT_TC1); - case HPD_PORT_E: + case HPD_PORT_TC2: return val & GEN11_HOTPLUG_CTL_LONG_DETECT(PORT_TC2); - case HPD_PORT_F: + case HPD_PORT_TC3: return val & GEN11_HOTPLUG_CTL_LONG_DETECT(PORT_TC3); - case HPD_PORT_G: + case HPD_PORT_TC4: return val & GEN11_HOTPLUG_CTL_LONG_DETECT(PORT_TC4); - case HPD_PORT_H: + case HPD_PORT_TC5: return val & GEN11_HOTPLUG_CTL_LONG_DETECT(PORT_TC5); - case HPD_PORT_I: + case HPD_PORT_TC6: return val & GEN11_HOTPLUG_CTL_LONG_DETECT(PORT_TC6); default: return false; @@ -1113,33 +1078,17 @@ static bool icp_ddi_port_hotplug_long_detect(enum hpd_pin pin, u32 val) static bool icp_tc_port_hotplug_long_detect(enum hpd_pin pin, u32 val) { switch (pin) { - case HPD_PORT_C: - return val & ICP_TC_HPD_LONG_DETECT(PORT_TC1); - case HPD_PORT_D: - return val & ICP_TC_HPD_LONG_DETECT(PORT_TC2); - case HPD_PORT_E: - return val & ICP_TC_HPD_LONG_DETECT(PORT_TC3); - case HPD_PORT_F: - return val & ICP_TC_HPD_LONG_DETECT(PORT_TC4); - default: - return false; - } -} - -static bool tgp_tc_port_hotplug_long_detect(enum hpd_pin pin, u32 val) -{ - switch (pin) { - case HPD_PORT_D: + case HPD_PORT_TC1: return val & ICP_TC_HPD_LONG_DETECT(PORT_TC1); - case HPD_PORT_E: + case HPD_PORT_TC2: return val & ICP_TC_HPD_LONG_DETECT(PORT_TC2); - case HPD_PORT_F: + case HPD_PORT_TC3: return val & ICP_TC_HPD_LONG_DETECT(PORT_TC3); - case HPD_PORT_G: + case HPD_PORT_TC4: return val & ICP_TC_HPD_LONG_DETECT(PORT_TC4); - case HPD_PORT_H: + case HPD_PORT_TC5: return val & ICP_TC_HPD_LONG_DETECT(PORT_TC5); - case HPD_PORT_I: + case HPD_PORT_TC6: return val & ICP_TC_HPD_LONG_DETECT(PORT_TC6); default: return false; @@ -1893,19 +1842,16 @@ static void icp_irq_handler(struct drm_i915_private *dev_priv, u32 pch_iir) { u32 ddi_hotplug_trigger, tc_hotplug_trigger; u32 pin_mask = 0, long_mask = 0; - bool (*tc_port_hotplug_long_detect)(enum hpd_pin pin, u32 val); if (HAS_PCH_TGP(dev_priv)) { ddi_hotplug_trigger = pch_iir & SDE_DDI_MASK_TGP; tc_hotplug_trigger = pch_iir & SDE_TC_MASK_TGP; - tc_port_hotplug_long_detect = tgp_tc_port_hotplug_long_detect; } else if (HAS_PCH_JSP(dev_priv)) { ddi_hotplug_trigger = pch_iir & SDE_DDI_MASK_TGP; tc_hotplug_trigger = 0; } else if (HAS_PCH_MCC(dev_priv)) { ddi_hotplug_trigger = pch_iir & SDE_DDI_MASK_ICP; tc_hotplug_trigger = pch_iir & SDE_TC_HOTPLUG_ICP(PORT_TC1); - tc_port_hotplug_long_detect = icp_tc_port_hotplug_long_detect; } else { drm_WARN(&dev_priv->drm, !HAS_PCH_ICP(dev_priv), "Unrecognized PCH type 0x%x\n", @@ -1913,7 +1859,6 @@ static void icp_irq_handler(struct drm_i915_private *dev_priv, u32 pch_iir) ddi_hotplug_trigger = pch_iir & SDE_DDI_MASK_ICP; tc_hotplug_trigger = pch_iir & SDE_TC_MASK_ICP; - tc_port_hotplug_long_detect = icp_tc_port_hotplug_long_detect; } if (ddi_hotplug_trigger) { @@ -1937,7 +1882,7 @@ static void icp_irq_handler(struct drm_i915_private *dev_priv, u32 pch_iir) intel_get_hpd_pins(dev_priv, &pin_mask, &long_mask, tc_hotplug_trigger, dig_hotplug_reg, dev_priv->hotplug.pch_hpd, - tc_port_hotplug_long_detect); + icp_tc_port_hotplug_long_detect); } if (pin_mask) @@ -2185,12 +2130,6 @@ static void gen11_hpd_irq_handler(struct drm_i915_private *dev_priv, u32 iir) u32 pin_mask = 0, long_mask = 0; u32 trigger_tc = iir & GEN11_DE_TC_HOTPLUG_MASK; u32 trigger_tbt = iir & GEN11_DE_TBT_HOTPLUG_MASK; - long_pulse_detect_func long_pulse_detect; - - if (INTEL_GEN(dev_priv) >= 12) - long_pulse_detect = gen12_port_hotplug_long_detect; - else - long_pulse_detect = gen11_port_hotplug_long_detect; if (trigger_tc) { u32 dig_hotplug_reg; @@ -2201,7 +2140,7 @@ static void gen11_hpd_irq_handler(struct drm_i915_private *dev_priv, u32 iir) intel_get_hpd_pins(dev_priv, &pin_mask, &long_mask, trigger_tc, dig_hotplug_reg, dev_priv->hotplug.hpd, - long_pulse_detect); + gen11_port_hotplug_long_detect); } if (trigger_tbt) { @@ -2213,7 +2152,7 @@ static void gen11_hpd_irq_handler(struct drm_i915_private *dev_priv, u32 iir) intel_get_hpd_pins(dev_priv, &pin_mask, &long_mask, trigger_tbt, dig_hotplug_reg, dev_priv->hotplug.hpd, - long_pulse_detect); + gen11_port_hotplug_long_detect); } if (pin_mask) @@ -3048,6 +2987,18 @@ static u32 intel_hpd_enabled_irqs(struct drm_i915_private *dev_priv, return enabled_irqs; } +static u32 intel_hpd_hotplug_irqs(struct drm_i915_private *dev_priv, + const u32 hpd[HPD_NUM_PINS]) +{ + struct intel_encoder *encoder; + u32 hotplug_irqs = 0; + + for_each_intel_encoder(&dev_priv->drm, encoder) + hotplug_irqs |= hpd[encoder->hpd_pin]; + + return hotplug_irqs; +} + static void ibx_hpd_detection_setup(struct drm_i915_private *dev_priv) { u32 hotplug; @@ -3077,50 +3028,50 @@ static void ibx_hpd_irq_setup(struct drm_i915_private *dev_priv) { u32 hotplug_irqs, enabled_irqs; - if (HAS_PCH_IBX(dev_priv)) - hotplug_irqs = SDE_HOTPLUG_MASK; - else - hotplug_irqs = SDE_HOTPLUG_MASK_CPT; - enabled_irqs = intel_hpd_enabled_irqs(dev_priv, dev_priv->hotplug.pch_hpd); + hotplug_irqs = intel_hpd_hotplug_irqs(dev_priv, dev_priv->hotplug.pch_hpd); ibx_display_interrupt_update(dev_priv, hotplug_irqs, enabled_irqs); ibx_hpd_detection_setup(dev_priv); } -static void icp_hpd_detection_setup(struct drm_i915_private *dev_priv, - u32 ddi_hotplug_enable_mask, - u32 tc_hotplug_enable_mask) +static void icp_ddi_hpd_detection_setup(struct drm_i915_private *dev_priv, + u32 enable_mask) { u32 hotplug; hotplug = I915_READ(SHOTPLUG_CTL_DDI); - hotplug |= ddi_hotplug_enable_mask; + hotplug |= enable_mask; I915_WRITE(SHOTPLUG_CTL_DDI, hotplug); +} - if (tc_hotplug_enable_mask) { - hotplug = I915_READ(SHOTPLUG_CTL_TC); - hotplug |= tc_hotplug_enable_mask; - I915_WRITE(SHOTPLUG_CTL_TC, hotplug); - } +static void icp_tc_hpd_detection_setup(struct drm_i915_private *dev_priv, + u32 enable_mask) +{ + u32 hotplug; + + hotplug = I915_READ(SHOTPLUG_CTL_TC); + hotplug |= enable_mask; + I915_WRITE(SHOTPLUG_CTL_TC, hotplug); } static void icp_hpd_irq_setup(struct drm_i915_private *dev_priv, - u32 sde_ddi_mask, u32 sde_tc_mask, u32 ddi_enable_mask, u32 tc_enable_mask) { u32 hotplug_irqs, enabled_irqs; - hotplug_irqs = sde_ddi_mask | sde_tc_mask; enabled_irqs = intel_hpd_enabled_irqs(dev_priv, dev_priv->hotplug.pch_hpd); + hotplug_irqs = intel_hpd_hotplug_irqs(dev_priv, dev_priv->hotplug.pch_hpd); if (INTEL_PCH_TYPE(dev_priv) <= PCH_TGP) I915_WRITE(SHPD_FILTER_CNT, SHPD_FILTER_CNT_500_ADJ); ibx_display_interrupt_update(dev_priv, hotplug_irqs, enabled_irqs); - icp_hpd_detection_setup(dev_priv, ddi_enable_mask, tc_enable_mask); + icp_ddi_hpd_detection_setup(dev_priv, ddi_enable_mask); + if (tc_enable_mask) + icp_tc_hpd_detection_setup(dev_priv, tc_enable_mask); } /* @@ -3130,7 +3081,6 @@ static void icp_hpd_irq_setup(struct drm_i915_private *dev_priv, static void mcc_hpd_irq_setup(struct drm_i915_private *dev_priv) { icp_hpd_irq_setup(dev_priv, - SDE_DDI_MASK_ICP, SDE_TC_HOTPLUG_ICP(PORT_TC1), ICP_DDI_HPD_ENABLE_MASK, ICP_TC_HPD_ENABLE(PORT_TC1)); } @@ -3142,7 +3092,6 @@ static void mcc_hpd_irq_setup(struct drm_i915_private *dev_priv) static void jsp_hpd_irq_setup(struct drm_i915_private *dev_priv) { icp_hpd_irq_setup(dev_priv, - SDE_DDI_MASK_TGP, 0, TGP_DDI_HPD_ENABLE_MASK, 0); } @@ -3154,14 +3103,18 @@ static void gen11_hpd_detection_setup(struct drm_i915_private *dev_priv) hotplug |= GEN11_HOTPLUG_CTL_ENABLE(PORT_TC1) | GEN11_HOTPLUG_CTL_ENABLE(PORT_TC2) | GEN11_HOTPLUG_CTL_ENABLE(PORT_TC3) | - GEN11_HOTPLUG_CTL_ENABLE(PORT_TC4); + GEN11_HOTPLUG_CTL_ENABLE(PORT_TC4) | + GEN11_HOTPLUG_CTL_ENABLE(PORT_TC5) | + GEN11_HOTPLUG_CTL_ENABLE(PORT_TC6); I915_WRITE(GEN11_TC_HOTPLUG_CTL, hotplug); hotplug = I915_READ(GEN11_TBT_HOTPLUG_CTL); hotplug |= GEN11_HOTPLUG_CTL_ENABLE(PORT_TC1) | GEN11_HOTPLUG_CTL_ENABLE(PORT_TC2) | GEN11_HOTPLUG_CTL_ENABLE(PORT_TC3) | - GEN11_HOTPLUG_CTL_ENABLE(PORT_TC4); + GEN11_HOTPLUG_CTL_ENABLE(PORT_TC4) | + GEN11_HOTPLUG_CTL_ENABLE(PORT_TC5) | + GEN11_HOTPLUG_CTL_ENABLE(PORT_TC6); I915_WRITE(GEN11_TBT_HOTPLUG_CTL, hotplug); } @@ -3171,7 +3124,7 @@ static void gen11_hpd_irq_setup(struct drm_i915_private *dev_priv) u32 val; enabled_irqs = intel_hpd_enabled_irqs(dev_priv, dev_priv->hotplug.hpd); - hotplug_irqs = GEN11_DE_TC_HOTPLUG_MASK | GEN11_DE_TBT_HOTPLUG_MASK; + hotplug_irqs = intel_hpd_hotplug_irqs(dev_priv, dev_priv->hotplug.hpd); val = I915_READ(GEN11_DE_HPD_IMR); val &= ~hotplug_irqs; @@ -3182,10 +3135,10 @@ static void gen11_hpd_irq_setup(struct drm_i915_private *dev_priv) gen11_hpd_detection_setup(dev_priv); if (INTEL_PCH_TYPE(dev_priv) >= PCH_TGP) - icp_hpd_irq_setup(dev_priv, SDE_DDI_MASK_TGP, SDE_TC_MASK_TGP, + icp_hpd_irq_setup(dev_priv, TGP_DDI_HPD_ENABLE_MASK, TGP_TC_HPD_ENABLE_MASK); else if (INTEL_PCH_TYPE(dev_priv) >= PCH_ICP) - icp_hpd_irq_setup(dev_priv, SDE_DDI_MASK_ICP, SDE_TC_MASK_ICP, + icp_hpd_irq_setup(dev_priv, ICP_DDI_HPD_ENABLE_MASK, ICP_TC_HPD_ENABLE_MASK); } @@ -3221,8 +3174,8 @@ static void spt_hpd_irq_setup(struct drm_i915_private *dev_priv) if (INTEL_PCH_TYPE(dev_priv) >= PCH_CNP) I915_WRITE(SHPD_FILTER_CNT, SHPD_FILTER_CNT_500_ADJ); - hotplug_irqs = SDE_HOTPLUG_MASK_SPT; enabled_irqs = intel_hpd_enabled_irqs(dev_priv, dev_priv->hotplug.pch_hpd); + hotplug_irqs = intel_hpd_hotplug_irqs(dev_priv, dev_priv->hotplug.pch_hpd); ibx_display_interrupt_update(dev_priv, hotplug_irqs, enabled_irqs); @@ -3249,22 +3202,13 @@ static void ilk_hpd_irq_setup(struct drm_i915_private *dev_priv) { u32 hotplug_irqs, enabled_irqs; - if (INTEL_GEN(dev_priv) >= 8) { - hotplug_irqs = GEN8_PORT_DP_A_HOTPLUG; - enabled_irqs = intel_hpd_enabled_irqs(dev_priv, dev_priv->hotplug.hpd); + enabled_irqs = intel_hpd_enabled_irqs(dev_priv, dev_priv->hotplug.hpd); + hotplug_irqs = intel_hpd_hotplug_irqs(dev_priv, dev_priv->hotplug.hpd); + if (INTEL_GEN(dev_priv) >= 8) bdw_update_port_irq(dev_priv, hotplug_irqs, enabled_irqs); - } else if (INTEL_GEN(dev_priv) >= 7) { - hotplug_irqs = DE_DP_A_HOTPLUG_IVB; - enabled_irqs = intel_hpd_enabled_irqs(dev_priv, dev_priv->hotplug.hpd); - - ilk_update_display_irq(dev_priv, hotplug_irqs, enabled_irqs); - } else { - hotplug_irqs = DE_DP_A_HOTPLUG; - enabled_irqs = intel_hpd_enabled_irqs(dev_priv, dev_priv->hotplug.hpd); - + else ilk_update_display_irq(dev_priv, hotplug_irqs, enabled_irqs); - } ilk_hpd_detection_setup(dev_priv); @@ -3313,7 +3257,7 @@ static void bxt_hpd_irq_setup(struct drm_i915_private *dev_priv) u32 hotplug_irqs, enabled_irqs; enabled_irqs = intel_hpd_enabled_irqs(dev_priv, dev_priv->hotplug.hpd); - hotplug_irqs = BXT_DE_PORT_HOTPLUG_MASK; + hotplug_irqs = intel_hpd_hotplug_irqs(dev_priv, dev_priv->hotplug.hpd); bdw_update_port_irq(dev_priv, hotplug_irqs, enabled_irqs); @@ -3534,17 +3478,18 @@ static void icp_irq_postinstall(struct drm_i915_private *dev_priv) gen3_assert_iir_is_zero(&dev_priv->uncore, SDEIIR); I915_WRITE(SDEIMR, ~mask); - if (HAS_PCH_TGP(dev_priv)) - icp_hpd_detection_setup(dev_priv, TGP_DDI_HPD_ENABLE_MASK, - TGP_TC_HPD_ENABLE_MASK); - else if (HAS_PCH_JSP(dev_priv)) - icp_hpd_detection_setup(dev_priv, TGP_DDI_HPD_ENABLE_MASK, 0); - else if (HAS_PCH_MCC(dev_priv)) - icp_hpd_detection_setup(dev_priv, ICP_DDI_HPD_ENABLE_MASK, - ICP_TC_HPD_ENABLE(PORT_TC1)); - else - icp_hpd_detection_setup(dev_priv, ICP_DDI_HPD_ENABLE_MASK, - ICP_TC_HPD_ENABLE_MASK); + if (HAS_PCH_TGP(dev_priv)) { + icp_ddi_hpd_detection_setup(dev_priv, TGP_DDI_HPD_ENABLE_MASK); + icp_tc_hpd_detection_setup(dev_priv, TGP_TC_HPD_ENABLE_MASK); + } else if (HAS_PCH_JSP(dev_priv)) { + icp_ddi_hpd_detection_setup(dev_priv, TGP_DDI_HPD_ENABLE_MASK); + } else if (HAS_PCH_MCC(dev_priv)) { + icp_ddi_hpd_detection_setup(dev_priv, ICP_DDI_HPD_ENABLE_MASK); + icp_tc_hpd_detection_setup(dev_priv, ICP_TC_HPD_ENABLE(PORT_TC1)); + } else { + icp_ddi_hpd_detection_setup(dev_priv, ICP_DDI_HPD_ENABLE_MASK); + icp_tc_hpd_detection_setup(dev_priv, ICP_TC_HPD_ENABLE_MASK); + } } static void gen11_irq_postinstall(struct drm_i915_private *dev_priv) diff --git a/drivers/gpu/drm/i915/i915_pci.c b/drivers/gpu/drm/i915/i915_pci.c index 366ddfc8df6b..fb5e30de78c2 100644 --- a/drivers/gpu/drm/i915/i915_pci.c +++ b/drivers/gpu/drm/i915/i915_pci.c @@ -389,6 +389,7 @@ static const struct intel_device_info ilk_m_info = { GEN5_FEATURES, PLATFORM(INTEL_IRONLAKE), .is_mobile = 1, + .has_rps = true, .display.has_fbc = 1, }; diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index ac691927e29d..d805d4da6181 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -1382,7 +1382,6 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg) #define DPIO_CMNRST (1 << 0) #define DPIO_PHY(pipe) ((pipe) >> 1) -#define DPIO_PHY_IOSF_PORT(phy) (dev_priv->dpio_phy_iosf_port[phy]) /* * Per pipe/PLL DPIO regs @@ -7760,32 +7759,20 @@ enum { #define GEN11_DE_HPD_IMR _MMIO(0x44474) #define GEN11_DE_HPD_IIR _MMIO(0x44478) #define GEN11_DE_HPD_IER _MMIO(0x4447c) -#define GEN12_TC6_HOTPLUG (1 << 21) -#define GEN12_TC5_HOTPLUG (1 << 20) -#define GEN11_TC4_HOTPLUG (1 << 19) -#define GEN11_TC3_HOTPLUG (1 << 18) -#define GEN11_TC2_HOTPLUG (1 << 17) -#define GEN11_TC1_HOTPLUG (1 << 16) #define GEN11_TC_HOTPLUG(tc_port) (1 << ((tc_port) + 16)) -#define GEN11_DE_TC_HOTPLUG_MASK (GEN12_TC6_HOTPLUG | \ - GEN12_TC5_HOTPLUG | \ - GEN11_TC4_HOTPLUG | \ - GEN11_TC3_HOTPLUG | \ - GEN11_TC2_HOTPLUG | \ - GEN11_TC1_HOTPLUG) -#define GEN12_TBT6_HOTPLUG (1 << 5) -#define GEN12_TBT5_HOTPLUG (1 << 4) -#define GEN11_TBT4_HOTPLUG (1 << 3) -#define GEN11_TBT3_HOTPLUG (1 << 2) -#define GEN11_TBT2_HOTPLUG (1 << 1) -#define GEN11_TBT1_HOTPLUG (1 << 0) +#define GEN11_DE_TC_HOTPLUG_MASK (GEN11_TC_HOTPLUG(PORT_TC6) | \ + GEN11_TC_HOTPLUG(PORT_TC5) | \ + GEN11_TC_HOTPLUG(PORT_TC4) | \ + GEN11_TC_HOTPLUG(PORT_TC3) | \ + GEN11_TC_HOTPLUG(PORT_TC2) | \ + GEN11_TC_HOTPLUG(PORT_TC1)) #define GEN11_TBT_HOTPLUG(tc_port) (1 << (tc_port)) -#define GEN11_DE_TBT_HOTPLUG_MASK (GEN12_TBT6_HOTPLUG | \ - GEN12_TBT5_HOTPLUG | \ - GEN11_TBT4_HOTPLUG | \ - GEN11_TBT3_HOTPLUG | \ - GEN11_TBT2_HOTPLUG | \ - GEN11_TBT1_HOTPLUG) +#define GEN11_DE_TBT_HOTPLUG_MASK (GEN11_TBT_HOTPLUG(PORT_TC6) | \ + GEN11_TBT_HOTPLUG(PORT_TC5) | \ + GEN11_TBT_HOTPLUG(PORT_TC4) | \ + GEN11_TBT_HOTPLUG(PORT_TC3) | \ + GEN11_TBT_HOTPLUG(PORT_TC2) | \ + GEN11_TBT_HOTPLUG(PORT_TC1)) #define GEN11_TBT_HOTPLUG_CTL _MMIO(0x44030) #define GEN11_TC_HOTPLUG_CTL _MMIO(0x44038) @@ -9315,6 +9302,7 @@ enum { #define GEN11_LSN_UNSLCVC_GAFS_HALF_SF_MAXALLOC (1 << 7) #define GEN10_SAMPLER_MODE _MMIO(0xE18C) +#define ENABLE_SMALLPL REG_BIT(15) #define GEN11_SAMPLER_ENABLE_HEADLESS_MSG REG_BIT(5) /* IVYBRIDGE DPF */ diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c index 11e272422fb7..0e813819b041 100644 --- a/drivers/gpu/drm/i915/i915_request.c +++ b/drivers/gpu/drm/i915/i915_request.c @@ -542,8 +542,13 @@ bool __i915_request_submit(struct i915_request *request) if (i915_request_completed(request)) goto xfer; + if (unlikely(intel_context_is_closed(request->context) && + !intel_engine_has_heartbeat(engine))) + intel_context_set_banned(request->context); + if (unlikely(intel_context_is_banned(request->context))) i915_request_set_error_once(request, -EIO); + if (unlikely(fatal_error(request->fence.error))) __i915_request_skip(request); @@ -593,16 +598,8 @@ xfer: __notify_execute_cb_irq(request); /* We may be recursing from the signal callback of another i915 fence */ - if (!i915_request_signaled(request)) { - spin_lock_nested(&request->lock, SINGLE_DEPTH_NESTING); - - if (test_bit(DMA_FENCE_FLAG_ENABLE_SIGNAL_BIT, - &request->fence.flags) && - !i915_request_enable_breadcrumb(request)) - intel_engine_signal_breadcrumbs(engine); - - spin_unlock(&request->lock); - } + if (test_bit(DMA_FENCE_FLAG_ENABLE_SIGNAL_BIT, &request->fence.flags)) + i915_request_enable_breadcrumb(request); return result; } diff --git a/drivers/gpu/drm/i915/i915_suspend.c b/drivers/gpu/drm/i915/i915_suspend.c index ed2be3489f8e..7b64e7137270 100644 --- a/drivers/gpu/drm/i915/i915_suspend.c +++ b/drivers/gpu/drm/i915/i915_suspend.c @@ -34,17 +34,25 @@ static void i915_save_display(struct drm_i915_private *dev_priv) { + struct pci_dev *pdev = dev_priv->drm.pdev; + /* Display arbitration control */ if (INTEL_GEN(dev_priv) <= 4) dev_priv->regfile.saveDSPARB = I915_READ(DSPARB); - /* save FBC interval */ - if (HAS_FBC(dev_priv) && INTEL_GEN(dev_priv) <= 4 && !IS_G4X(dev_priv)) - dev_priv->regfile.saveFBC_CONTROL = I915_READ(FBC_CONTROL); + if (IS_GEN(dev_priv, 4)) + pci_read_config_word(pdev, GCDGMBUS, + &dev_priv->regfile.saveGCDGMBUS); } static void i915_restore_display(struct drm_i915_private *dev_priv) { + struct pci_dev *pdev = dev_priv->drm.pdev; + + if (IS_GEN(dev_priv, 4)) + pci_write_config_word(pdev, GCDGMBUS, + dev_priv->regfile.saveGCDGMBUS); + /* Display arbitration */ if (INTEL_GEN(dev_priv) <= 4) I915_WRITE(DSPARB, dev_priv->regfile.saveDSPARB); @@ -52,31 +60,17 @@ static void i915_restore_display(struct drm_i915_private *dev_priv) /* only restore FBC info on the platform that supports FBC*/ intel_fbc_global_disable(dev_priv); - /* restore FBC interval */ - if (HAS_FBC(dev_priv) && INTEL_GEN(dev_priv) <= 4 && !IS_G4X(dev_priv)) - I915_WRITE(FBC_CONTROL, dev_priv->regfile.saveFBC_CONTROL); - intel_vga_redisable(dev_priv); + + intel_gmbus_reset(dev_priv); } int i915_save_state(struct drm_i915_private *dev_priv) { - struct pci_dev *pdev = dev_priv->drm.pdev; int i; i915_save_display(dev_priv); - if (IS_GEN(dev_priv, 4)) - pci_read_config_word(pdev, GCDGMBUS, - &dev_priv->regfile.saveGCDGMBUS); - - /* Cache mode state */ - if (INTEL_GEN(dev_priv) < 7) - dev_priv->regfile.saveCACHE_MODE_0 = I915_READ(CACHE_MODE_0); - - /* Memory Arbitration state */ - dev_priv->regfile.saveMI_ARB_STATE = I915_READ(MI_ARB_STATE); - /* Scratch space */ if (IS_GEN(dev_priv, 2) && IS_MOBILE(dev_priv)) { for (i = 0; i < 7; i++) { @@ -102,22 +96,10 @@ int i915_save_state(struct drm_i915_private *dev_priv) int i915_restore_state(struct drm_i915_private *dev_priv) { - struct pci_dev *pdev = dev_priv->drm.pdev; int i; - if (IS_GEN(dev_priv, 4)) - pci_write_config_word(pdev, GCDGMBUS, - dev_priv->regfile.saveGCDGMBUS); i915_restore_display(dev_priv); - /* Cache mode state */ - if (INTEL_GEN(dev_priv) < 7) - I915_WRITE(CACHE_MODE_0, dev_priv->regfile.saveCACHE_MODE_0 | - 0xffff0000); - - /* Memory arbitration state */ - I915_WRITE(MI_ARB_STATE, dev_priv->regfile.saveMI_ARB_STATE | 0xffff0000); - /* Scratch space */ if (IS_GEN(dev_priv, 2) && IS_MOBILE(dev_priv)) { for (i = 0; i < 7; i++) { @@ -138,7 +120,5 @@ int i915_restore_state(struct drm_i915_private *dev_priv) I915_WRITE(SWF3(i), dev_priv->regfile.saveSWF3[i]); } - intel_gmbus_reset(dev_priv); - return 0; } diff --git a/drivers/gpu/drm/i915/i915_sw_fence.c b/drivers/gpu/drm/i915/i915_sw_fence.c index 4cd2038cbe35..038d4c6884c5 100644 --- a/drivers/gpu/drm/i915/i915_sw_fence.c +++ b/drivers/gpu/drm/i915/i915_sw_fence.c @@ -34,7 +34,7 @@ static void *i915_sw_fence_debug_hint(void *addr) #ifdef CONFIG_DRM_I915_SW_FENCE_DEBUG_OBJECTS -static struct debug_obj_descr i915_sw_fence_debug_descr = { +static const struct debug_obj_descr i915_sw_fence_debug_descr = { .name = "i915_sw_fence", .debug_hint = i915_sw_fence_debug_hint, }; diff --git a/drivers/gpu/drm/i915/i915_vma.c b/drivers/gpu/drm/i915/i915_vma.c index 495d28f6d160..ffb5287e055a 100644 --- a/drivers/gpu/drm/i915/i915_vma.c +++ b/drivers/gpu/drm/i915/i915_vma.c @@ -892,9 +892,11 @@ int i915_vma_pin_ww(struct i915_vma *vma, struct i915_gem_ww_ctx *ww, /* Allocate enough page directories to used PTE */ if (vma->vm->allocate_va_range) { - i915_vm_alloc_pt_stash(vma->vm, - &work->stash, - vma->size); + err = i915_vm_alloc_pt_stash(vma->vm, + &work->stash, + vma->size); + if (err) + goto err_fence; err = i915_vm_pin_pt_stash(vma->vm, &work->stash); diff --git a/drivers/gpu/drm/i915/intel_device_info.c b/drivers/gpu/drm/i915/intel_device_info.c index e2aa5bc3a6e0..adc836f15fde 100644 --- a/drivers/gpu/drm/i915/intel_device_info.c +++ b/drivers/gpu/drm/i915/intel_device_info.c @@ -516,6 +516,14 @@ void intel_device_info_runtime_init(struct drm_i915_private *dev_priv) S32_MAX), USEC_PER_SEC)); } + + if (!HAS_DISPLAY(dev_priv)) { + dev_priv->drm.driver_features &= ~(DRIVER_MODESET | + DRIVER_ATOMIC); + memset(&info->display, 0, sizeof(info->display)); + memset(runtime->num_sprites, 0, sizeof(runtime->num_sprites)); + memset(runtime->num_scalers, 0, sizeof(runtime->num_scalers)); + } } void intel_driver_caps_print(const struct intel_driver_caps *caps, diff --git a/drivers/gpu/drm/i915/intel_memory_region.c b/drivers/gpu/drm/i915/intel_memory_region.c index 6b5e9d88646d..180e1078ef7c 100644 --- a/drivers/gpu/drm/i915/intel_memory_region.c +++ b/drivers/gpu/drm/i915/intel_memory_region.c @@ -87,7 +87,7 @@ __intel_memory_region_get_pages_buddy(struct intel_memory_region *mem, min_order = ilog2(size) - ilog2(mem->mm.chunk_size); } - if (size > BIT(mem->mm.max_order) * mem->mm.chunk_size) + if (size > mem->mm.size) return -E2BIG; n_pages = size >> ilog2(mem->mm.chunk_size); diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c index b4bd19266b8c..34e0d22d456b 100644 --- a/drivers/gpu/drm/i915/intel_pm.c +++ b/drivers/gpu/drm/i915/intel_pm.c @@ -7136,7 +7136,7 @@ static void tgl_init_clock_gating(struct drm_i915_private *dev_priv) I915_READ(POWERGATE_ENABLE) | vd_pg_enable); /* Wa_1409825376:tgl (pre-prod)*/ - if (IS_TGL_REVID(dev_priv, TGL_REVID_A0, TGL_REVID_A0)) + if (IS_TGL_DISP_REVID(dev_priv, TGL_REVID_A0, TGL_REVID_B1)) I915_WRITE(GEN9_CLKGATE_DIS_3, I915_READ(GEN9_CLKGATE_DIS_3) | TGL_VRH_GATING_DIS); diff --git a/drivers/gpu/drm/i915/intel_sideband.c b/drivers/gpu/drm/i915/intel_sideband.c index 916ccd1c0e96..5b3279262123 100644 --- a/drivers/gpu/drm/i915/intel_sideband.c +++ b/drivers/gpu/drm/i915/intel_sideband.c @@ -231,9 +231,21 @@ void vlv_ccu_write(struct drm_i915_private *i915, u32 reg, u32 val) SB_CRWRDA_NP, reg, &val); } +static u32 vlv_dpio_phy_iosf_port(struct drm_i915_private *i915, enum dpio_phy phy) +{ + /* + * IOSF_PORT_DPIO: VLV x2 PHY (DP/HDMI B and C), CHV x1 PHY (DP/HDMI D) + * IOSF_PORT_DPIO_2: CHV x2 PHY (DP/HDMI B and C) + */ + if (IS_CHERRYVIEW(i915)) + return phy == DPIO_PHY0 ? IOSF_PORT_DPIO_2 : IOSF_PORT_DPIO; + else + return IOSF_PORT_DPIO; +} + u32 vlv_dpio_read(struct drm_i915_private *i915, enum pipe pipe, int reg) { - int port = i915->dpio_phy_iosf_port[DPIO_PHY(pipe)]; + u32 port = vlv_dpio_phy_iosf_port(i915, DPIO_PHY(pipe)); u32 val = 0; vlv_sideband_rw(i915, DPIO_DEVFN, port, SB_MRD_NP, reg, &val); @@ -252,7 +264,7 @@ u32 vlv_dpio_read(struct drm_i915_private *i915, enum pipe pipe, int reg) void vlv_dpio_write(struct drm_i915_private *i915, enum pipe pipe, int reg, u32 val) { - int port = i915->dpio_phy_iosf_port[DPIO_PHY(pipe)]; + u32 port = vlv_dpio_phy_iosf_port(i915, DPIO_PHY(pipe)); vlv_sideband_rw(i915, DPIO_DEVFN, port, SB_MWR_NP, reg, &val); } diff --git a/drivers/gpu/drm/i915/intel_uncore.c b/drivers/gpu/drm/i915/intel_uncore.c index 8d5a933e6af6..97ded2a59cf4 100644 --- a/drivers/gpu/drm/i915/intel_uncore.c +++ b/drivers/gpu/drm/i915/intel_uncore.c @@ -1209,6 +1209,18 @@ unclaimed_reg_debug(struct intel_uncore *uncore, spin_unlock(&uncore->debug->lock); } +#define __vgpu_read(x) \ +static u##x \ +vgpu_read##x(struct intel_uncore *uncore, i915_reg_t reg, bool trace) { \ + u##x val = __raw_uncore_read##x(uncore, reg); \ + trace_i915_reg_rw(false, reg, val, sizeof(val), trace); \ + return val; \ +} +__vgpu_read(8) +__vgpu_read(16) +__vgpu_read(32) +__vgpu_read(64) + #define GEN2_READ_HEADER(x) \ u##x val = 0; \ assert_rpm_wakelock_held(uncore->rpm); @@ -1414,6 +1426,16 @@ __gen_reg_write_funcs(gen8); #undef GEN6_WRITE_FOOTER #undef GEN6_WRITE_HEADER +#define __vgpu_write(x) \ +static void \ +vgpu_write##x(struct intel_uncore *uncore, i915_reg_t reg, u##x val, bool trace) { \ + trace_i915_reg_rw(true, reg, val, sizeof(val), trace); \ + __raw_uncore_write##x(uncore, reg, val); \ +} +__vgpu_write(8) +__vgpu_write(16) +__vgpu_write(32) + #define ASSIGN_RAW_WRITE_MMIO_VFUNCS(uncore, x) \ do { \ (uncore)->funcs.mmio_writeb = x##_write8; \ @@ -1735,7 +1757,10 @@ static void uncore_raw_init(struct intel_uncore *uncore) { GEM_BUG_ON(intel_uncore_has_forcewake(uncore)); - if (IS_GEN(uncore->i915, 5)) { + if (intel_vgpu_active(uncore->i915)) { + ASSIGN_RAW_WRITE_MMIO_VFUNCS(uncore, vgpu); + ASSIGN_RAW_READ_MMIO_VFUNCS(uncore, vgpu); + } else if (IS_GEN(uncore->i915, 5)) { ASSIGN_RAW_WRITE_MMIO_VFUNCS(uncore, gen5); ASSIGN_RAW_READ_MMIO_VFUNCS(uncore, gen5); } else { @@ -1993,13 +2018,14 @@ int __intel_wait_for_register_fw(struct intel_uncore *uncore, unsigned int slow_timeout_ms, u32 *out_value) { - u32 reg_value; + u32 reg_value = 0; #define done (((reg_value = intel_uncore_read_fw(uncore, reg)) & mask) == value) int ret; /* Catch any overuse of this function */ might_sleep_if(slow_timeout_ms); GEM_BUG_ON(fast_timeout_us > 20000); + GEM_BUG_ON(!fast_timeout_us && !slow_timeout_ms); ret = -ETIMEDOUT; if (fast_timeout_us && fast_timeout_us <= 20000) diff --git a/drivers/gpu/drm/i915/selftests/intel_memory_region.c b/drivers/gpu/drm/i915/selftests/intel_memory_region.c index 334b0648e253..0aeba8e3af28 100644 --- a/drivers/gpu/drm/i915/selftests/intel_memory_region.c +++ b/drivers/gpu/drm/i915/selftests/intel_memory_region.c @@ -261,6 +261,82 @@ err_close_objects: return err; } +static int igt_mock_splintered_region(void *arg) +{ + struct intel_memory_region *mem = arg; + struct drm_i915_private *i915 = mem->i915; + struct drm_i915_gem_object *obj; + unsigned int expected_order; + LIST_HEAD(objects); + u64 size; + int err = 0; + + /* + * Sanity check we can still allocate everything even if the + * mm.max_order != mm.size. i.e our starting address space size is not a + * power-of-two. + */ + + size = (SZ_4G - 1) & PAGE_MASK; + mem = mock_region_create(i915, 0, size, PAGE_SIZE, 0); + if (IS_ERR(mem)) + return PTR_ERR(mem); + + if (mem->mm.size != size) { + pr_err("%s size mismatch(%llu != %llu)\n", + __func__, mem->mm.size, size); + err = -EINVAL; + goto out_put; + } + + expected_order = get_order(rounddown_pow_of_two(size)); + if (mem->mm.max_order != expected_order) { + pr_err("%s order mismatch(%u != %u)\n", + __func__, mem->mm.max_order, expected_order); + err = -EINVAL; + goto out_put; + } + + obj = igt_object_create(mem, &objects, size, 0); + if (IS_ERR(obj)) { + err = PTR_ERR(obj); + goto out_close; + } + + close_objects(mem, &objects); + + /* + * While we should be able allocate everything without any flag + * restrictions, if we consider I915_BO_ALLOC_CONTIGUOUS then we are + * actually limited to the largest power-of-two for the region size i.e + * max_order, due to the inner workings of the buddy allocator. So make + * sure that does indeed hold true. + */ + + obj = igt_object_create(mem, &objects, size, I915_BO_ALLOC_CONTIGUOUS); + if (!IS_ERR(obj)) { + pr_err("%s too large contiguous allocation was not rejected\n", + __func__); + err = -EINVAL; + goto out_close; + } + + obj = igt_object_create(mem, &objects, rounddown_pow_of_two(size), + I915_BO_ALLOC_CONTIGUOUS); + if (IS_ERR(obj)) { + pr_err("%s largest possible contiguous allocation failed\n", + __func__); + err = PTR_ERR(obj); + goto out_close; + } + +out_close: + close_objects(mem, &objects); +out_put: + intel_memory_region_put(mem); + return err; +} + static int igt_gpu_write_dw(struct intel_context *ce, struct i915_vma *vma, u32 dword, @@ -771,6 +847,7 @@ int intel_memory_region_mock_selftests(void) static const struct i915_subtest tests[] = { SUBTEST(igt_mock_fill), SUBTEST(igt_mock_contiguous), + SUBTEST(igt_mock_splintered_region), }; struct intel_memory_region *mem; struct drm_i915_private *i915; diff --git a/drivers/gpu/drm/i915/selftests/mock_gem_device.c b/drivers/gpu/drm/i915/selftests/mock_gem_device.c index cf81ba84ae0b..9220c9d1a4b7 100644 --- a/drivers/gpu/drm/i915/selftests/mock_gem_device.c +++ b/drivers/gpu/drm/i915/selftests/mock_gem_device.c @@ -113,11 +113,11 @@ static struct dev_pm_domain pm_domain = { struct drm_i915_private *mock_gem_device(void) { - struct drm_i915_private *i915; - struct pci_dev *pdev; #if IS_ENABLED(CONFIG_IOMMU_API) && defined(CONFIG_INTEL_IOMMU) - struct dev_iommu iommu; + static struct dev_iommu fake_iommu = { .priv = (void *)-1 }; #endif + struct drm_i915_private *i915; + struct pci_dev *pdev; pdev = kzalloc(sizeof(*pdev), GFP_KERNEL); if (!pdev) @@ -129,10 +129,8 @@ struct drm_i915_private *mock_gem_device(void) dma_coerce_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64)); #if IS_ENABLED(CONFIG_IOMMU_API) && defined(CONFIG_INTEL_IOMMU) - /* HACK HACK HACK to disable iommu for the fake device; force identity mapping */ - memset(&iommu, 0, sizeof(iommu)); - iommu.priv = (void *)-1; - pdev->dev.iommu = &iommu; + /* HACK to disable iommu for the fake device; force identity mapping */ + pdev->dev.iommu = &fake_iommu; #endif if (!devres_open_group(&pdev->dev, NULL, GFP_KERNEL)) { put_device(&pdev->dev); diff --git a/drivers/gpu/drm/i915/selftests/mock_region.c b/drivers/gpu/drm/i915/selftests/mock_region.c index 09660f5a0a4c..979d96f27c43 100644 --- a/drivers/gpu/drm/i915/selftests/mock_region.c +++ b/drivers/gpu/drm/i915/selftests/mock_region.c @@ -24,7 +24,7 @@ mock_object_create(struct intel_memory_region *mem, struct drm_i915_private *i915 = mem->i915; struct drm_i915_gem_object *obj; - if (size > BIT(mem->mm.max_order) * mem->mm.chunk_size) + if (size > mem->mm.size) return ERR_PTR(-E2BIG); obj = i915_gem_object_alloc(); diff --git a/drivers/gpu/drm/lima/lima_gem.c b/drivers/gpu/drm/lima/lima_gem.c index 155f2b4b4030..11223fe348df 100644 --- a/drivers/gpu/drm/lima/lima_gem.c +++ b/drivers/gpu/drm/lima/lima_gem.c @@ -69,8 +69,7 @@ int lima_heap_alloc(struct lima_bo *bo, struct lima_vm *vm) return ret; if (bo->base.sgt) { - dma_unmap_sg(dev, bo->base.sgt->sgl, - bo->base.sgt->nents, DMA_BIDIRECTIONAL); + dma_unmap_sgtable(dev, bo->base.sgt, DMA_BIDIRECTIONAL, 0); sg_free_table(bo->base.sgt); } else { bo->base.sgt = kmalloc(sizeof(*bo->base.sgt), GFP_KERNEL); @@ -80,7 +79,13 @@ int lima_heap_alloc(struct lima_bo *bo, struct lima_vm *vm) } } - dma_map_sg(dev, sgt.sgl, sgt.nents, DMA_BIDIRECTIONAL); + ret = dma_map_sgtable(dev, &sgt, DMA_BIDIRECTIONAL, 0); + if (ret) { + sg_free_table(&sgt); + kfree(bo->base.sgt); + bo->base.sgt = NULL; + return ret; + } *bo->base.sgt = sgt; diff --git a/drivers/gpu/drm/lima/lima_vm.c b/drivers/gpu/drm/lima/lima_vm.c index 5b92fb82674a..2b2739adc7f5 100644 --- a/drivers/gpu/drm/lima/lima_vm.c +++ b/drivers/gpu/drm/lima/lima_vm.c @@ -124,7 +124,7 @@ int lima_vm_bo_add(struct lima_vm *vm, struct lima_bo *bo, bool create) if (err) goto err_out1; - for_each_sg_dma_page(bo->base.sgt->sgl, &sg_iter, bo->base.sgt->nents, 0) { + for_each_sgtable_dma_page(bo->base.sgt, &sg_iter, 0) { err = lima_vm_map_page(vm, sg_page_iter_dma_address(&sg_iter), bo_va->node.start + offset); if (err) @@ -298,8 +298,7 @@ int lima_vm_map_bo(struct lima_vm *vm, struct lima_bo *bo, int pageoff) mutex_lock(&vm->lock); base = bo_va->node.start + (pageoff << PAGE_SHIFT); - for_each_sg_dma_page(bo->base.sgt->sgl, &sg_iter, - bo->base.sgt->nents, pageoff) { + for_each_sgtable_dma_page(bo->base.sgt, &sg_iter, pageoff) { err = lima_vm_map_page(vm, sg_page_iter_dma_address(&sg_iter), base + offset); if (err) diff --git a/drivers/gpu/drm/mediatek/Kconfig b/drivers/gpu/drm/mediatek/Kconfig index aa74aac3cbcc..65cd03a4be29 100644 --- a/drivers/gpu/drm/mediatek/Kconfig +++ b/drivers/gpu/drm/mediatek/Kconfig @@ -24,6 +24,6 @@ config DRM_MEDIATEK_HDMI tristate "DRM HDMI Support for Mediatek SoCs" depends on DRM_MEDIATEK select SND_SOC_HDMI_CODEC if SND_SOC - select GENERIC_PHY + select PHY_MTK_HDMI help DRM/KMS HDMI driver for Mediatek SoCs diff --git a/drivers/gpu/drm/mediatek/Makefile b/drivers/gpu/drm/mediatek/Makefile index b7a82ed5788f..77b0fd86063d 100644 --- a/drivers/gpu/drm/mediatek/Makefile +++ b/drivers/gpu/drm/mediatek/Makefile @@ -19,9 +19,6 @@ obj-$(CONFIG_DRM_MEDIATEK) += mediatek-drm.o mediatek-drm-hdmi-objs := mtk_cec.o \ mtk_hdmi.o \ - mtk_hdmi_ddc.o \ - mtk_mt2701_hdmi_phy.o \ - mtk_mt8173_hdmi_phy.o \ - mtk_hdmi_phy.o + mtk_hdmi_ddc.o obj-$(CONFIG_DRM_MEDIATEK_HDMI) += mediatek-drm-hdmi.o diff --git a/drivers/gpu/drm/mediatek/mtk_dpi.c b/drivers/gpu/drm/mediatek/mtk_dpi.c index d4f0fb7ad312..cf11c4850b40 100644 --- a/drivers/gpu/drm/mediatek/mtk_dpi.c +++ b/drivers/gpu/drm/mediatek/mtk_dpi.c @@ -64,7 +64,8 @@ enum mtk_dpi_out_color_format { struct mtk_dpi { struct mtk_ddp_comp ddp_comp; struct drm_encoder encoder; - struct drm_bridge *bridge; + struct drm_bridge bridge; + struct drm_bridge *next_bridge; void __iomem *regs; struct device *dev; struct clk *engine_clk; @@ -83,9 +84,9 @@ struct mtk_dpi { int refcount; }; -static inline struct mtk_dpi *mtk_dpi_from_encoder(struct drm_encoder *e) +static inline struct mtk_dpi *bridge_to_dpi(struct drm_bridge *b) { - return container_of(e, struct mtk_dpi, encoder); + return container_of(b, struct mtk_dpi, bridge); } enum mtk_dpi_polarity { @@ -521,50 +522,53 @@ static int mtk_dpi_set_display_mode(struct mtk_dpi *dpi, return 0; } -static bool mtk_dpi_encoder_mode_fixup(struct drm_encoder *encoder, - const struct drm_display_mode *mode, - struct drm_display_mode *adjusted_mode) +static void mtk_dpi_encoder_destroy(struct drm_encoder *encoder) { - return true; + drm_encoder_cleanup(encoder); } -static void mtk_dpi_encoder_mode_set(struct drm_encoder *encoder, - struct drm_display_mode *mode, - struct drm_display_mode *adjusted_mode) +static const struct drm_encoder_funcs mtk_dpi_encoder_funcs = { + .destroy = mtk_dpi_encoder_destroy, +}; + +static int mtk_dpi_bridge_attach(struct drm_bridge *bridge, + enum drm_bridge_attach_flags flags) { - struct mtk_dpi *dpi = mtk_dpi_from_encoder(encoder); + struct mtk_dpi *dpi = bridge_to_dpi(bridge); + + return drm_bridge_attach(bridge->encoder, dpi->next_bridge, + &dpi->bridge, flags); +} + +static void mtk_dpi_bridge_mode_set(struct drm_bridge *bridge, + const struct drm_display_mode *mode, + const struct drm_display_mode *adjusted_mode) +{ + struct mtk_dpi *dpi = bridge_to_dpi(bridge); drm_mode_copy(&dpi->mode, adjusted_mode); } -static void mtk_dpi_encoder_disable(struct drm_encoder *encoder) +static void mtk_dpi_bridge_disable(struct drm_bridge *bridge) { - struct mtk_dpi *dpi = mtk_dpi_from_encoder(encoder); + struct mtk_dpi *dpi = bridge_to_dpi(bridge); mtk_dpi_power_off(dpi); } -static void mtk_dpi_encoder_enable(struct drm_encoder *encoder) +static void mtk_dpi_bridge_enable(struct drm_bridge *bridge) { - struct mtk_dpi *dpi = mtk_dpi_from_encoder(encoder); + struct mtk_dpi *dpi = bridge_to_dpi(bridge); mtk_dpi_power_on(dpi); mtk_dpi_set_display_mode(dpi, &dpi->mode); } -static int mtk_dpi_atomic_check(struct drm_encoder *encoder, - struct drm_crtc_state *crtc_state, - struct drm_connector_state *conn_state) -{ - return 0; -} - -static const struct drm_encoder_helper_funcs mtk_dpi_encoder_helper_funcs = { - .mode_fixup = mtk_dpi_encoder_mode_fixup, - .mode_set = mtk_dpi_encoder_mode_set, - .disable = mtk_dpi_encoder_disable, - .enable = mtk_dpi_encoder_enable, - .atomic_check = mtk_dpi_atomic_check, +static const struct drm_bridge_funcs mtk_dpi_bridge_funcs = { + .attach = mtk_dpi_bridge_attach, + .mode_set = mtk_dpi_bridge_mode_set, + .disable = mtk_dpi_bridge_disable, + .enable = mtk_dpi_bridge_enable, }; static void mtk_dpi_start(struct mtk_ddp_comp *comp) @@ -605,12 +609,10 @@ static int mtk_dpi_bind(struct device *dev, struct device *master, void *data) dev_err(dev, "Failed to initialize decoder: %d\n", ret); goto err_unregister; } - drm_encoder_helper_add(&dpi->encoder, &mtk_dpi_encoder_helper_funcs); - /* Currently DPI0 is fixed to be driven by OVL1 */ - dpi->encoder.possible_crtcs = BIT(1); + dpi->encoder.possible_crtcs = mtk_drm_find_possible_crtc_by_comp(drm_dev, dpi->ddp_comp); - ret = drm_bridge_attach(&dpi->encoder, dpi->bridge, NULL, 0); + ret = drm_bridge_attach(&dpi->encoder, &dpi->bridge, NULL, 0); if (ret) { dev_err(dev, "Failed to attach bridge: %d\n", ret); goto err_cleanup; @@ -770,11 +772,11 @@ static int mtk_dpi_probe(struct platform_device *pdev) } ret = drm_of_find_panel_or_bridge(dev->of_node, 0, 0, - NULL, &dpi->bridge); + NULL, &dpi->next_bridge); if (ret) return ret; - dev_info(dev, "Found bridge node: %pOF\n", dpi->bridge->of_node); + dev_info(dev, "Found bridge node: %pOF\n", dpi->next_bridge->of_node); comp_id = mtk_ddp_comp_get_id(dev->of_node, MTK_DPI); if (comp_id < 0) { @@ -791,8 +793,15 @@ static int mtk_dpi_probe(struct platform_device *pdev) platform_set_drvdata(pdev, dpi); + dpi->bridge.funcs = &mtk_dpi_bridge_funcs; + dpi->bridge.of_node = dev->of_node; + dpi->bridge.type = DRM_MODE_CONNECTOR_DPI; + + drm_bridge_add(&dpi->bridge); + ret = component_add(dev, &mtk_dpi_component_ops); if (ret) { + drm_bridge_remove(&dpi->bridge); dev_err(dev, "Failed to add component: %d\n", ret); return ret; } @@ -802,7 +811,10 @@ static int mtk_dpi_probe(struct platform_device *pdev) static int mtk_dpi_remove(struct platform_device *pdev) { + struct mtk_dpi *dpi = platform_get_drvdata(pdev); + component_del(&pdev->dev, &mtk_dpi_component_ops); + drm_bridge_remove(&dpi->bridge); return 0; } diff --git a/drivers/gpu/drm/mediatek/mtk_drm_crtc.c b/drivers/gpu/drm/mediatek/mtk_drm_crtc.c index 6fc818049f2d..c28f5d7aac1a 100644 --- a/drivers/gpu/drm/mediatek/mtk_drm_crtc.c +++ b/drivers/gpu/drm/mediatek/mtk_drm_crtc.c @@ -481,7 +481,7 @@ static void mtk_drm_crtc_hw_config(struct mtk_drm_crtc *mtk_crtc) mbox_flush(mtk_crtc->cmdq_client->chan, 2000); cmdq_handle = cmdq_pkt_create(mtk_crtc->cmdq_client, PAGE_SIZE); cmdq_pkt_clear_event(cmdq_handle, mtk_crtc->cmdq_event); - cmdq_pkt_wfe(cmdq_handle, mtk_crtc->cmdq_event); + cmdq_pkt_wfe(cmdq_handle, mtk_crtc->cmdq_event, false); mtk_crtc_ddp_config(crtc, cmdq_handle); cmdq_pkt_finalize(cmdq_handle); cmdq_pkt_flush_async(cmdq_handle, ddp_cmdq_cb, cmdq_handle); @@ -831,13 +831,19 @@ int mtk_drm_crtc_create(struct drm_device *drm_dev, drm_crtc_index(&mtk_crtc->base)); mtk_crtc->cmdq_client = NULL; } - ret = of_property_read_u32_index(priv->mutex_node, - "mediatek,gce-events", - drm_crtc_index(&mtk_crtc->base), - &mtk_crtc->cmdq_event); - if (ret) - dev_dbg(dev, "mtk_crtc %d failed to get mediatek,gce-events property\n", - drm_crtc_index(&mtk_crtc->base)); + + if (mtk_crtc->cmdq_client) { + ret = of_property_read_u32_index(priv->mutex_node, + "mediatek,gce-events", + drm_crtc_index(&mtk_crtc->base), + &mtk_crtc->cmdq_event); + if (ret) { + dev_dbg(dev, "mtk_crtc %d failed to get mediatek,gce-events property\n", + drm_crtc_index(&mtk_crtc->base)); + cmdq_mbox_destroy(mtk_crtc->cmdq_client); + mtk_crtc->cmdq_client = NULL; + } + } #endif return 0; } diff --git a/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.c b/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.c index 57c88de9a329..8eba44be3a8a 100644 --- a/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.c +++ b/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.c @@ -13,6 +13,8 @@ #include <linux/of_platform.h> #include <linux/platform_device.h> #include <linux/soc/mediatek/mtk-cmdq.h> +#include <drm/drm_print.h> + #include "mtk_drm_drv.h" #include "mtk_drm_plane.h" #include "mtk_drm_ddp_comp.h" @@ -412,6 +414,22 @@ static const struct mtk_ddp_comp_match mtk_ddp_matches[DDP_COMPONENT_ID_MAX] = { [DDP_COMPONENT_WDMA1] = { MTK_DISP_WDMA, 1, NULL }, }; +static bool mtk_drm_find_comp_in_ddp(struct mtk_ddp_comp ddp_comp, + const enum mtk_ddp_comp_id *path, + unsigned int path_len) +{ + unsigned int i; + + if (path == NULL) + return false; + + for (i = 0U; i < path_len; i++) + if (ddp_comp.id == path[i]) + return true; + + return false; +} + int mtk_ddp_comp_get_id(struct device_node *node, enum mtk_ddp_comp_type comp_type) { @@ -427,6 +445,26 @@ int mtk_ddp_comp_get_id(struct device_node *node, return -EINVAL; } +unsigned int mtk_drm_find_possible_crtc_by_comp(struct drm_device *drm, + struct mtk_ddp_comp ddp_comp) +{ + struct mtk_drm_private *private = drm->dev_private; + unsigned int ret = 0; + + if (mtk_drm_find_comp_in_ddp(ddp_comp, private->data->main_path, private->data->main_len)) + ret = BIT(0); + else if (mtk_drm_find_comp_in_ddp(ddp_comp, private->data->ext_path, + private->data->ext_len)) + ret = BIT(1); + else if (mtk_drm_find_comp_in_ddp(ddp_comp, private->data->third_path, + private->data->third_len)) + ret = BIT(2); + else + DRM_INFO("Failed to find comp in ddp table\n"); + + return ret; +} + int mtk_ddp_comp_init(struct device *dev, struct device_node *node, struct mtk_ddp_comp *comp, enum mtk_ddp_comp_id comp_id, const struct mtk_ddp_comp_funcs *funcs) @@ -496,6 +534,7 @@ int mtk_ddp_comp_init(struct device *dev, struct device_node *node, #if IS_REACHABLE(CONFIG_MTK_CMDQ) if (of_address_to_resource(node, 0, &res) != 0) { dev_err(dev, "Missing reg in %s node\n", node->full_name); + put_device(&larb_pdev->dev); return -EINVAL; } comp->regs_pa = res.start; diff --git a/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.h b/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.h index debe36395fe7..1d9e00b69462 100644 --- a/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.h +++ b/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.h @@ -202,6 +202,8 @@ static inline void mtk_ddp_ctm_set(struct mtk_ddp_comp *comp, int mtk_ddp_comp_get_id(struct device_node *node, enum mtk_ddp_comp_type comp_type); +unsigned int mtk_drm_find_possible_crtc_by_comp(struct drm_device *drm, + struct mtk_ddp_comp ddp_comp); int mtk_ddp_comp_init(struct device *dev, struct device_node *comp_node, struct mtk_ddp_comp *comp, enum mtk_ddp_comp_id comp_id, const struct mtk_ddp_comp_funcs *funcs); diff --git a/drivers/gpu/drm/mediatek/mtk_drm_drv.c b/drivers/gpu/drm/mediatek/mtk_drm_drv.c index 2f8d0043fca7..7f3398a7c2b0 100644 --- a/drivers/gpu/drm/mediatek/mtk_drm_drv.c +++ b/drivers/gpu/drm/mediatek/mtk_drm_drv.c @@ -27,7 +27,6 @@ #include "mtk_drm_crtc.h" #include "mtk_drm_ddp.h" -#include "mtk_drm_ddp.h" #include "mtk_drm_ddp_comp.h" #include "mtk_drm_drv.h" #include "mtk_drm_gem.h" @@ -74,6 +73,19 @@ static const enum mtk_ddp_comp_id mt2701_mtk_ddp_ext[] = { DDP_COMPONENT_DPI0, }; +static const enum mtk_ddp_comp_id mt7623_mtk_ddp_main[] = { + DDP_COMPONENT_OVL0, + DDP_COMPONENT_RDMA0, + DDP_COMPONENT_COLOR0, + DDP_COMPONENT_BLS, + DDP_COMPONENT_DPI0, +}; + +static const enum mtk_ddp_comp_id mt7623_mtk_ddp_ext[] = { + DDP_COMPONENT_RDMA1, + DDP_COMPONENT_DSI0, +}; + static const enum mtk_ddp_comp_id mt2712_mtk_ddp_main[] = { DDP_COMPONENT_OVL0, DDP_COMPONENT_COLOR0, @@ -127,6 +139,14 @@ static const struct mtk_mmsys_driver_data mt2701_mmsys_driver_data = { .shadow_register = true, }; +static const struct mtk_mmsys_driver_data mt7623_mmsys_driver_data = { + .main_path = mt7623_mtk_ddp_main, + .main_len = ARRAY_SIZE(mt7623_mtk_ddp_main), + .ext_path = mt7623_mtk_ddp_ext, + .ext_len = ARRAY_SIZE(mt7623_mtk_ddp_ext), + .shadow_register = true, +}; + static const struct mtk_mmsys_driver_data mt2712_mmsys_driver_data = { .main_path = mt2712_mtk_ddp_main, .main_len = ARRAY_SIZE(mt2712_mtk_ddp_main), @@ -165,7 +185,7 @@ static int mtk_drm_kms_init(struct drm_device *drm) ret = drmm_mode_config_init(drm); if (ret) - return ret; + goto put_mutex_dev; drm->mode_config.min_width = 64; drm->mode_config.min_height = 64; @@ -182,7 +202,7 @@ static int mtk_drm_kms_init(struct drm_device *drm) ret = component_bind_all(drm->dev, drm); if (ret) - return ret; + goto put_mutex_dev; /* * We currently support two fixed data streams, each optional, @@ -229,7 +249,7 @@ static int mtk_drm_kms_init(struct drm_device *drm) } if (!dma_dev->dma_parms) { ret = -ENOMEM; - goto err_component_unbind; + goto put_dma_dev; } ret = dma_set_max_seg_size(dma_dev, (unsigned int)DMA_BIT_MASK(32)); @@ -256,9 +276,12 @@ static int mtk_drm_kms_init(struct drm_device *drm) err_unset_dma_parms: if (private->dma_parms_allocated) dma_dev->dma_parms = NULL; +put_dma_dev: + put_device(private->dma_dev); err_component_unbind: component_unbind_all(drm->dev, drm); - +put_mutex_dev: + put_device(private->mutex_dev); return ret; } @@ -417,6 +440,8 @@ static const struct of_device_id mtk_ddp_comp_dt_ids[] = { static const struct of_device_id mtk_drm_of_ids[] = { { .compatible = "mediatek,mt2701-mmsys", .data = &mt2701_mmsys_driver_data}, + { .compatible = "mediatek,mt7623-mmsys", + .data = &mt7623_mmsys_driver_data}, { .compatible = "mediatek,mt2712-mmsys", .data = &mt2712_mmsys_driver_data}, { .compatible = "mediatek,mt8173-mmsys", @@ -539,8 +564,13 @@ err_pm: pm_runtime_disable(dev); err_node: of_node_put(private->mutex_node); - for (i = 0; i < DDP_COMPONENT_ID_MAX; i++) + for (i = 0; i < DDP_COMPONENT_ID_MAX; i++) { of_node_put(private->comp_node[i]); + if (private->ddp_comp[i]) { + put_device(private->ddp_comp[i]->larb_dev); + private->ddp_comp[i] = NULL; + } + } return ret; } diff --git a/drivers/gpu/drm/mediatek/mtk_drm_gem.c b/drivers/gpu/drm/mediatek/mtk_drm_gem.c index 591b90410e4a..cdd1a6e61564 100644 --- a/drivers/gpu/drm/mediatek/mtk_drm_gem.c +++ b/drivers/gpu/drm/mediatek/mtk_drm_gem.c @@ -223,46 +223,28 @@ struct drm_gem_object *mtk_gem_prime_import_sg_table(struct drm_device *dev, struct dma_buf_attachment *attach, struct sg_table *sg) { struct mtk_drm_gem_obj *mtk_gem; - int ret; - struct scatterlist *s; - unsigned int i; - dma_addr_t expected; - mtk_gem = mtk_drm_gem_init(dev, attach->dmabuf->size); + /* check if the entries in the sg_table are contiguous */ + if (drm_prime_get_contiguous_size(sg) < attach->dmabuf->size) { + DRM_ERROR("sg_table is not contiguous"); + return ERR_PTR(-EINVAL); + } + mtk_gem = mtk_drm_gem_init(dev, attach->dmabuf->size); if (IS_ERR(mtk_gem)) return ERR_CAST(mtk_gem); - expected = sg_dma_address(sg->sgl); - for_each_sg(sg->sgl, s, sg->nents, i) { - if (!sg_dma_len(s)) - break; - - if (sg_dma_address(s) != expected) { - DRM_ERROR("sg_table is not contiguous"); - ret = -EINVAL; - goto err_gem_free; - } - expected = sg_dma_address(s) + sg_dma_len(s); - } - mtk_gem->dma_addr = sg_dma_address(sg->sgl); mtk_gem->sg = sg; return &mtk_gem->base; - -err_gem_free: - kfree(mtk_gem); - return ERR_PTR(ret); } void *mtk_drm_gem_prime_vmap(struct drm_gem_object *obj) { struct mtk_drm_gem_obj *mtk_gem = to_mtk_gem_obj(obj); struct sg_table *sgt; - struct sg_page_iter iter; unsigned int npages; - unsigned int i = 0; if (mtk_gem->kvaddr) return mtk_gem->kvaddr; @@ -276,11 +258,8 @@ void *mtk_drm_gem_prime_vmap(struct drm_gem_object *obj) if (!mtk_gem->pages) goto out; - for_each_sg_page(sgt->sgl, &iter, sgt->orig_nents, 0) { - mtk_gem->pages[i++] = sg_page_iter_page(&iter); - if (i > npages) - break; - } + drm_prime_sg_to_page_addr_arrays(sgt, mtk_gem->pages, NULL, npages); + mtk_gem->kvaddr = vmap(mtk_gem->pages, npages, VM_MAP, pgprot_writecombine(PAGE_KERNEL)); diff --git a/drivers/gpu/drm/mediatek/mtk_dsi.c b/drivers/gpu/drm/mediatek/mtk_dsi.c index 16fd99dcdacf..4a188a942c38 100644 --- a/drivers/gpu/drm/mediatek/mtk_dsi.c +++ b/drivers/gpu/drm/mediatek/mtk_dsi.c @@ -466,14 +466,13 @@ static void mtk_dsi_config_vdo_timing(struct mtk_dsi *dsi) horizontal_sync_active_byte = (vm->hsync_len * dsi_tmp_buf_bpp - 10); if (dsi->mode_flags & MIPI_DSI_MODE_VIDEO_SYNC_PULSE) - horizontal_backporch_byte = - (vm->hback_porch * dsi_tmp_buf_bpp - 10); + horizontal_backporch_byte = vm->hback_porch * dsi_tmp_buf_bpp; else - horizontal_backporch_byte = ((vm->hback_porch + vm->hsync_len) * - dsi_tmp_buf_bpp - 10); + horizontal_backporch_byte = (vm->hback_porch + vm->hsync_len) * + dsi_tmp_buf_bpp; data_phy_cycles = timing->lpx + timing->da_hs_prepare + - timing->da_hs_zero + timing->da_hs_exit + 3; + timing->da_hs_zero + timing->da_hs_exit; if (dsi->mode_flags & MIPI_DSI_MODE_VIDEO_BURST) { if ((vm->hfront_porch + vm->hback_porch) * dsi_tmp_buf_bpp > @@ -970,11 +969,7 @@ static int mtk_dsi_encoder_init(struct drm_device *drm, struct mtk_dsi *dsi) return ret; } - /* - * Currently display data paths are statically assigned to a crtc each. - * crtc 0 is OVL0 -> COLOR0 -> AAL -> OD -> RDMA0 -> UFOE -> DSI0 - */ - dsi->encoder.possible_crtcs = 1; + dsi->encoder.possible_crtcs = mtk_drm_find_possible_crtc_by_comp(drm, dsi->ddp_comp); ret = drm_bridge_attach(&dsi->encoder, &dsi->bridge, NULL, DRM_BRIDGE_ATTACH_NO_CONNECTOR); diff --git a/drivers/gpu/drm/mediatek/mtk_hdmi.c b/drivers/gpu/drm/mediatek/mtk_hdmi.c index f2e9b429960b..97a1ff529a1d 100644 --- a/drivers/gpu/drm/mediatek/mtk_hdmi.c +++ b/drivers/gpu/drm/mediatek/mtk_hdmi.c @@ -12,6 +12,7 @@ #include <linux/io.h> #include <linux/kernel.h> #include <linux/mfd/syscon.h> +#include <linux/module.h> #include <linux/mutex.h> #include <linux/of_platform.h> #include <linux/of.h> @@ -145,11 +146,16 @@ struct hdmi_audio_param { struct hdmi_codec_params codec_params; }; +struct mtk_hdmi_conf { + bool tz_disabled; +}; + struct mtk_hdmi { struct drm_bridge bridge; struct drm_bridge *next_bridge; struct drm_connector conn; struct device *dev; + const struct mtk_hdmi_conf *conf; struct phy *phy; struct device *cec_dev; struct i2c_adapter *ddc_adpt; @@ -234,7 +240,6 @@ static void mtk_hdmi_hw_vid_black(struct mtk_hdmi *hdmi, bool black) static void mtk_hdmi_hw_make_reg_writable(struct mtk_hdmi *hdmi, bool enable) { struct arm_smccc_res res; - struct mtk_hdmi_phy *hdmi_phy = phy_get_drvdata(hdmi->phy); /* * MT8173 HDMI hardware has an output control bit to enable/disable HDMI @@ -242,7 +247,7 @@ static void mtk_hdmi_hw_make_reg_writable(struct mtk_hdmi *hdmi, bool enable) * The ARM trusted firmware provides an API for the HDMI driver to set * this control bit to enable HDMI output in supervisor mode. */ - if (hdmi_phy->conf && hdmi_phy->conf->tz_disabled) + if (hdmi->conf && hdmi->conf->tz_disabled) regmap_update_bits(hdmi->sys_regmap, hdmi->sys_offset + HDMI_SYS_CFG20, 0x80008005, enable ? 0x80000005 : 0x8000); @@ -1507,25 +1512,30 @@ static int mtk_hdmi_dt_parse_pdata(struct mtk_hdmi *hdmi, dev_err(dev, "Failed to get system configuration registers: %d\n", ret); - return ret; + goto put_device; } hdmi->sys_regmap = regmap; mem = platform_get_resource(pdev, IORESOURCE_MEM, 0); hdmi->regs = devm_ioremap_resource(dev, mem); - if (IS_ERR(hdmi->regs)) - return PTR_ERR(hdmi->regs); + if (IS_ERR(hdmi->regs)) { + ret = PTR_ERR(hdmi->regs); + goto put_device; + } remote = of_graph_get_remote_node(np, 1, 0); - if (!remote) - return -EINVAL; + if (!remote) { + ret = -EINVAL; + goto put_device; + } if (!of_device_is_compatible(remote, "hdmi-connector")) { hdmi->next_bridge = of_drm_find_bridge(remote); if (!hdmi->next_bridge) { dev_err(dev, "Waiting for external bridge\n"); of_node_put(remote); - return -EPROBE_DEFER; + ret = -EPROBE_DEFER; + goto put_device; } } @@ -1534,7 +1544,8 @@ static int mtk_hdmi_dt_parse_pdata(struct mtk_hdmi *hdmi, dev_err(dev, "Failed to find ddc-i2c-bus node in %pOF\n", remote); of_node_put(remote); - return -EINVAL; + ret = -EINVAL; + goto put_device; } of_node_put(remote); @@ -1542,10 +1553,14 @@ static int mtk_hdmi_dt_parse_pdata(struct mtk_hdmi *hdmi, of_node_put(i2c_np); if (!hdmi->ddc_adpt) { dev_err(dev, "Failed to get ddc i2c adapter by node\n"); - return -EINVAL; + ret = -EINVAL; + goto put_device; } return 0; +put_device: + put_device(hdmi->cec_dev); + return ret; } /* @@ -1723,6 +1738,7 @@ static int mtk_drm_hdmi_probe(struct platform_device *pdev) return -ENOMEM; hdmi->dev = dev; + hdmi->conf = of_device_get_match_data(dev); ret = mtk_hdmi_dt_parse_pdata(hdmi, pdev); if (ret) @@ -1803,8 +1819,16 @@ static int mtk_hdmi_resume(struct device *dev) static SIMPLE_DEV_PM_OPS(mtk_hdmi_pm_ops, mtk_hdmi_suspend, mtk_hdmi_resume); +static const struct mtk_hdmi_conf mtk_hdmi_conf_mt2701 = { + .tz_disabled = true, +}; + static const struct of_device_id mtk_drm_hdmi_of_ids[] = { - { .compatible = "mediatek,mt8173-hdmi", }, + { .compatible = "mediatek,mt2701-hdmi", + .data = &mtk_hdmi_conf_mt2701, + }, + { .compatible = "mediatek,mt8173-hdmi", + }, {} }; @@ -1819,7 +1843,6 @@ static struct platform_driver mtk_hdmi_driver = { }; static struct platform_driver * const mtk_hdmi_drivers[] = { - &mtk_hdmi_phy_driver, &mtk_hdmi_ddc_driver, &mtk_cec_driver, &mtk_hdmi_driver, diff --git a/drivers/gpu/drm/mediatek/mtk_hdmi.h b/drivers/gpu/drm/mediatek/mtk_hdmi.h index bb3653de6bd1..472bf141c92b 100644 --- a/drivers/gpu/drm/mediatek/mtk_hdmi.h +++ b/drivers/gpu/drm/mediatek/mtk_hdmi.h @@ -5,7 +5,6 @@ */ #ifndef _MTK_HDMI_CTRL_H #define _MTK_HDMI_CTRL_H -#include "mtk_hdmi_phy.h" struct platform_driver; diff --git a/drivers/gpu/drm/mediatek/mtk_hdmi_phy.c b/drivers/gpu/drm/mediatek/mtk_hdmi_phy.c deleted file mode 100644 index 5223498502c4..000000000000 --- a/drivers/gpu/drm/mediatek/mtk_hdmi_phy.c +++ /dev/null @@ -1,210 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * Copyright (c) 2018 MediaTek Inc. - * Author: Jie Qiu <jie.qiu@mediatek.com> - */ - -#include "mtk_hdmi_phy.h" - -static int mtk_hdmi_phy_power_on(struct phy *phy); -static int mtk_hdmi_phy_power_off(struct phy *phy); - -static const struct phy_ops mtk_hdmi_phy_dev_ops = { - .power_on = mtk_hdmi_phy_power_on, - .power_off = mtk_hdmi_phy_power_off, - .owner = THIS_MODULE, -}; - -void mtk_hdmi_phy_clear_bits(struct mtk_hdmi_phy *hdmi_phy, u32 offset, - u32 bits) -{ - void __iomem *reg = hdmi_phy->regs + offset; - u32 tmp; - - tmp = readl(reg); - tmp &= ~bits; - writel(tmp, reg); -} - -void mtk_hdmi_phy_set_bits(struct mtk_hdmi_phy *hdmi_phy, u32 offset, - u32 bits) -{ - void __iomem *reg = hdmi_phy->regs + offset; - u32 tmp; - - tmp = readl(reg); - tmp |= bits; - writel(tmp, reg); -} - -void mtk_hdmi_phy_mask(struct mtk_hdmi_phy *hdmi_phy, u32 offset, - u32 val, u32 mask) -{ - void __iomem *reg = hdmi_phy->regs + offset; - u32 tmp; - - tmp = readl(reg); - tmp = (tmp & ~mask) | (val & mask); - writel(tmp, reg); -} - -inline struct mtk_hdmi_phy *to_mtk_hdmi_phy(struct clk_hw *hw) -{ - return container_of(hw, struct mtk_hdmi_phy, pll_hw); -} - -static int mtk_hdmi_phy_power_on(struct phy *phy) -{ - struct mtk_hdmi_phy *hdmi_phy = phy_get_drvdata(phy); - int ret; - - ret = clk_prepare_enable(hdmi_phy->pll); - if (ret < 0) - return ret; - - hdmi_phy->conf->hdmi_phy_enable_tmds(hdmi_phy); - return 0; -} - -static int mtk_hdmi_phy_power_off(struct phy *phy) -{ - struct mtk_hdmi_phy *hdmi_phy = phy_get_drvdata(phy); - - hdmi_phy->conf->hdmi_phy_disable_tmds(hdmi_phy); - clk_disable_unprepare(hdmi_phy->pll); - - return 0; -} - -static const struct phy_ops * -mtk_hdmi_phy_dev_get_ops(const struct mtk_hdmi_phy *hdmi_phy) -{ - if (hdmi_phy && hdmi_phy->conf && - hdmi_phy->conf->hdmi_phy_enable_tmds && - hdmi_phy->conf->hdmi_phy_disable_tmds) - return &mtk_hdmi_phy_dev_ops; - - dev_err(hdmi_phy->dev, "Failed to get dev ops of phy\n"); - return NULL; -} - -static void mtk_hdmi_phy_clk_get_data(struct mtk_hdmi_phy *hdmi_phy, - struct clk_init_data *clk_init) -{ - clk_init->flags = hdmi_phy->conf->flags; - clk_init->ops = hdmi_phy->conf->hdmi_phy_clk_ops; -} - -static int mtk_hdmi_phy_probe(struct platform_device *pdev) -{ - struct device *dev = &pdev->dev; - struct mtk_hdmi_phy *hdmi_phy; - struct resource *mem; - struct clk *ref_clk; - const char *ref_clk_name; - struct clk_init_data clk_init = { - .num_parents = 1, - .parent_names = (const char * const *)&ref_clk_name, - }; - - struct phy *phy; - struct phy_provider *phy_provider; - int ret; - - hdmi_phy = devm_kzalloc(dev, sizeof(*hdmi_phy), GFP_KERNEL); - if (!hdmi_phy) - return -ENOMEM; - - mem = platform_get_resource(pdev, IORESOURCE_MEM, 0); - hdmi_phy->regs = devm_ioremap_resource(dev, mem); - if (IS_ERR(hdmi_phy->regs)) { - ret = PTR_ERR(hdmi_phy->regs); - dev_err(dev, "Failed to get memory resource: %d\n", ret); - return ret; - } - - ref_clk = devm_clk_get(dev, "pll_ref"); - if (IS_ERR(ref_clk)) { - ret = PTR_ERR(ref_clk); - dev_err(&pdev->dev, "Failed to get PLL reference clock: %d\n", - ret); - return ret; - } - ref_clk_name = __clk_get_name(ref_clk); - - ret = of_property_read_string(dev->of_node, "clock-output-names", - &clk_init.name); - if (ret < 0) { - dev_err(dev, "Failed to read clock-output-names: %d\n", ret); - return ret; - } - - hdmi_phy->dev = dev; - hdmi_phy->conf = - (struct mtk_hdmi_phy_conf *)of_device_get_match_data(dev); - mtk_hdmi_phy_clk_get_data(hdmi_phy, &clk_init); - hdmi_phy->pll_hw.init = &clk_init; - hdmi_phy->pll = devm_clk_register(dev, &hdmi_phy->pll_hw); - if (IS_ERR(hdmi_phy->pll)) { - ret = PTR_ERR(hdmi_phy->pll); - dev_err(dev, "Failed to register PLL: %d\n", ret); - return ret; - } - - ret = of_property_read_u32(dev->of_node, "mediatek,ibias", - &hdmi_phy->ibias); - if (ret < 0) { - dev_err(&pdev->dev, "Failed to get ibias: %d\n", ret); - return ret; - } - - ret = of_property_read_u32(dev->of_node, "mediatek,ibias_up", - &hdmi_phy->ibias_up); - if (ret < 0) { - dev_err(&pdev->dev, "Failed to get ibias up: %d\n", ret); - return ret; - } - - dev_info(dev, "Using default TX DRV impedance: 4.2k/36\n"); - hdmi_phy->drv_imp_clk = 0x30; - hdmi_phy->drv_imp_d2 = 0x30; - hdmi_phy->drv_imp_d1 = 0x30; - hdmi_phy->drv_imp_d0 = 0x30; - - phy = devm_phy_create(dev, NULL, mtk_hdmi_phy_dev_get_ops(hdmi_phy)); - if (IS_ERR(phy)) { - dev_err(dev, "Failed to create HDMI PHY\n"); - return PTR_ERR(phy); - } - phy_set_drvdata(phy, hdmi_phy); - - phy_provider = devm_of_phy_provider_register(dev, of_phy_simple_xlate); - if (IS_ERR(phy_provider)) { - dev_err(dev, "Failed to register HDMI PHY\n"); - return PTR_ERR(phy_provider); - } - - return of_clk_add_provider(dev->of_node, of_clk_src_simple_get, - hdmi_phy->pll); -} - -static const struct of_device_id mtk_hdmi_phy_match[] = { - { .compatible = "mediatek,mt2701-hdmi-phy", - .data = &mtk_hdmi_phy_2701_conf, - }, - { .compatible = "mediatek,mt8173-hdmi-phy", - .data = &mtk_hdmi_phy_8173_conf, - }, - {}, -}; - -struct platform_driver mtk_hdmi_phy_driver = { - .probe = mtk_hdmi_phy_probe, - .driver = { - .name = "mediatek-hdmi-phy", - .of_match_table = mtk_hdmi_phy_match, - }, -}; - -MODULE_DESCRIPTION("MediaTek HDMI PHY Driver"); -MODULE_LICENSE("GPL v2"); diff --git a/drivers/gpu/drm/mediatek/mtk_hdmi_phy.h b/drivers/gpu/drm/mediatek/mtk_hdmi_phy.h deleted file mode 100644 index 2d8b3182470d..000000000000 --- a/drivers/gpu/drm/mediatek/mtk_hdmi_phy.h +++ /dev/null @@ -1,57 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * Copyright (c) 2018 MediaTek Inc. - * Author: Chunhui Dai <chunhui.dai@mediatek.com> - */ - -#ifndef _MTK_HDMI_PHY_H -#define _MTK_HDMI_PHY_H -#include <linux/clk.h> -#include <linux/clk-provider.h> -#include <linux/delay.h> -#include <linux/io.h> -#include <linux/mfd/syscon.h> -#include <linux/module.h> -#include <linux/of_device.h> -#include <linux/phy/phy.h> -#include <linux/platform_device.h> -#include <linux/types.h> - -struct mtk_hdmi_phy; - -struct mtk_hdmi_phy_conf { - bool tz_disabled; - unsigned long flags; - const struct clk_ops *hdmi_phy_clk_ops; - void (*hdmi_phy_enable_tmds)(struct mtk_hdmi_phy *hdmi_phy); - void (*hdmi_phy_disable_tmds)(struct mtk_hdmi_phy *hdmi_phy); -}; - -struct mtk_hdmi_phy { - void __iomem *regs; - struct device *dev; - struct mtk_hdmi_phy_conf *conf; - struct clk *pll; - struct clk_hw pll_hw; - unsigned long pll_rate; - unsigned char drv_imp_clk; - unsigned char drv_imp_d2; - unsigned char drv_imp_d1; - unsigned char drv_imp_d0; - unsigned int ibias; - unsigned int ibias_up; -}; - -void mtk_hdmi_phy_clear_bits(struct mtk_hdmi_phy *hdmi_phy, u32 offset, - u32 bits); -void mtk_hdmi_phy_set_bits(struct mtk_hdmi_phy *hdmi_phy, u32 offset, - u32 bits); -void mtk_hdmi_phy_mask(struct mtk_hdmi_phy *hdmi_phy, u32 offset, - u32 val, u32 mask); -struct mtk_hdmi_phy *to_mtk_hdmi_phy(struct clk_hw *hw); - -extern struct platform_driver mtk_hdmi_phy_driver; -extern struct mtk_hdmi_phy_conf mtk_hdmi_phy_8173_conf; -extern struct mtk_hdmi_phy_conf mtk_hdmi_phy_2701_conf; - -#endif /* _MTK_HDMI_PHY_H */ diff --git a/drivers/gpu/drm/mediatek/mtk_mt2701_hdmi_phy.c b/drivers/gpu/drm/mediatek/mtk_mt2701_hdmi_phy.c deleted file mode 100644 index d3cc4022e988..000000000000 --- a/drivers/gpu/drm/mediatek/mtk_mt2701_hdmi_phy.c +++ /dev/null @@ -1,249 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * Copyright (c) 2018 MediaTek Inc. - * Author: Chunhui Dai <chunhui.dai@mediatek.com> - */ - -#include "mtk_hdmi_phy.h" - -#define HDMI_CON0 0x00 -#define RG_HDMITX_DRV_IBIAS 0 -#define RG_HDMITX_DRV_IBIAS_MASK (0x3f << 0) -#define RG_HDMITX_EN_SER 12 -#define RG_HDMITX_EN_SER_MASK (0x0f << 12) -#define RG_HDMITX_EN_SLDO 16 -#define RG_HDMITX_EN_SLDO_MASK (0x0f << 16) -#define RG_HDMITX_EN_PRED 20 -#define RG_HDMITX_EN_PRED_MASK (0x0f << 20) -#define RG_HDMITX_EN_IMP 24 -#define RG_HDMITX_EN_IMP_MASK (0x0f << 24) -#define RG_HDMITX_EN_DRV 28 -#define RG_HDMITX_EN_DRV_MASK (0x0f << 28) - -#define HDMI_CON1 0x04 -#define RG_HDMITX_PRED_IBIAS 18 -#define RG_HDMITX_PRED_IBIAS_MASK (0x0f << 18) -#define RG_HDMITX_PRED_IMP (0x01 << 22) -#define RG_HDMITX_DRV_IMP 26 -#define RG_HDMITX_DRV_IMP_MASK (0x3f << 26) - -#define HDMI_CON2 0x08 -#define RG_HDMITX_EN_TX_CKLDO (0x01 << 0) -#define RG_HDMITX_EN_TX_POSDIV (0x01 << 1) -#define RG_HDMITX_TX_POSDIV 3 -#define RG_HDMITX_TX_POSDIV_MASK (0x03 << 3) -#define RG_HDMITX_EN_MBIAS (0x01 << 6) -#define RG_HDMITX_MBIAS_LPF_EN (0x01 << 7) - -#define HDMI_CON4 0x10 -#define RG_HDMITX_RESERVE_MASK (0xffffffff << 0) - -#define HDMI_CON6 0x18 -#define RG_HTPLL_BR 0 -#define RG_HTPLL_BR_MASK (0x03 << 0) -#define RG_HTPLL_BC 2 -#define RG_HTPLL_BC_MASK (0x03 << 2) -#define RG_HTPLL_BP 4 -#define RG_HTPLL_BP_MASK (0x0f << 4) -#define RG_HTPLL_IR 8 -#define RG_HTPLL_IR_MASK (0x0f << 8) -#define RG_HTPLL_IC 12 -#define RG_HTPLL_IC_MASK (0x0f << 12) -#define RG_HTPLL_POSDIV 16 -#define RG_HTPLL_POSDIV_MASK (0x03 << 16) -#define RG_HTPLL_PREDIV 18 -#define RG_HTPLL_PREDIV_MASK (0x03 << 18) -#define RG_HTPLL_FBKSEL 20 -#define RG_HTPLL_FBKSEL_MASK (0x03 << 20) -#define RG_HTPLL_RLH_EN (0x01 << 22) -#define RG_HTPLL_FBKDIV 24 -#define RG_HTPLL_FBKDIV_MASK (0x7f << 24) -#define RG_HTPLL_EN (0x01 << 31) - -#define HDMI_CON7 0x1c -#define RG_HTPLL_AUTOK_EN (0x01 << 23) -#define RG_HTPLL_DIVEN 28 -#define RG_HTPLL_DIVEN_MASK (0x07 << 28) - -static int mtk_hdmi_pll_prepare(struct clk_hw *hw) -{ - struct mtk_hdmi_phy *hdmi_phy = to_mtk_hdmi_phy(hw); - - mtk_hdmi_phy_set_bits(hdmi_phy, HDMI_CON7, RG_HTPLL_AUTOK_EN); - mtk_hdmi_phy_clear_bits(hdmi_phy, HDMI_CON6, RG_HTPLL_RLH_EN); - mtk_hdmi_phy_set_bits(hdmi_phy, HDMI_CON6, RG_HTPLL_POSDIV_MASK); - mtk_hdmi_phy_set_bits(hdmi_phy, HDMI_CON2, RG_HDMITX_EN_MBIAS); - usleep_range(80, 100); - mtk_hdmi_phy_set_bits(hdmi_phy, HDMI_CON6, RG_HTPLL_EN); - mtk_hdmi_phy_set_bits(hdmi_phy, HDMI_CON2, RG_HDMITX_EN_TX_CKLDO); - mtk_hdmi_phy_set_bits(hdmi_phy, HDMI_CON0, RG_HDMITX_EN_SLDO_MASK); - usleep_range(80, 100); - mtk_hdmi_phy_set_bits(hdmi_phy, HDMI_CON2, RG_HDMITX_MBIAS_LPF_EN); - mtk_hdmi_phy_set_bits(hdmi_phy, HDMI_CON0, RG_HDMITX_EN_SER_MASK); - mtk_hdmi_phy_set_bits(hdmi_phy, HDMI_CON0, RG_HDMITX_EN_PRED_MASK); - mtk_hdmi_phy_set_bits(hdmi_phy, HDMI_CON0, RG_HDMITX_EN_DRV_MASK); - usleep_range(80, 100); - return 0; -} - -static void mtk_hdmi_pll_unprepare(struct clk_hw *hw) -{ - struct mtk_hdmi_phy *hdmi_phy = to_mtk_hdmi_phy(hw); - - mtk_hdmi_phy_clear_bits(hdmi_phy, HDMI_CON0, RG_HDMITX_EN_DRV_MASK); - mtk_hdmi_phy_clear_bits(hdmi_phy, HDMI_CON0, RG_HDMITX_EN_PRED_MASK); - mtk_hdmi_phy_clear_bits(hdmi_phy, HDMI_CON0, RG_HDMITX_EN_SER_MASK); - mtk_hdmi_phy_clear_bits(hdmi_phy, HDMI_CON2, RG_HDMITX_MBIAS_LPF_EN); - usleep_range(80, 100); - mtk_hdmi_phy_clear_bits(hdmi_phy, HDMI_CON0, RG_HDMITX_EN_SLDO_MASK); - mtk_hdmi_phy_clear_bits(hdmi_phy, HDMI_CON2, RG_HDMITX_EN_TX_CKLDO); - mtk_hdmi_phy_clear_bits(hdmi_phy, HDMI_CON6, RG_HTPLL_EN); - usleep_range(80, 100); - mtk_hdmi_phy_clear_bits(hdmi_phy, HDMI_CON2, RG_HDMITX_EN_MBIAS); - mtk_hdmi_phy_clear_bits(hdmi_phy, HDMI_CON6, RG_HTPLL_POSDIV_MASK); - mtk_hdmi_phy_clear_bits(hdmi_phy, HDMI_CON6, RG_HTPLL_RLH_EN); - mtk_hdmi_phy_clear_bits(hdmi_phy, HDMI_CON7, RG_HTPLL_AUTOK_EN); - usleep_range(80, 100); -} - -static long mtk_hdmi_pll_round_rate(struct clk_hw *hw, unsigned long rate, - unsigned long *parent_rate) -{ - return rate; -} - -static int mtk_hdmi_pll_set_rate(struct clk_hw *hw, unsigned long rate, - unsigned long parent_rate) -{ - struct mtk_hdmi_phy *hdmi_phy = to_mtk_hdmi_phy(hw); - u32 pos_div; - - if (rate <= 64000000) - pos_div = 3; - else if (rate <= 128000000) - pos_div = 2; - else - pos_div = 1; - - mtk_hdmi_phy_set_bits(hdmi_phy, HDMI_CON6, RG_HTPLL_PREDIV_MASK); - mtk_hdmi_phy_set_bits(hdmi_phy, HDMI_CON6, RG_HTPLL_POSDIV_MASK); - mtk_hdmi_phy_set_bits(hdmi_phy, HDMI_CON2, RG_HDMITX_EN_TX_POSDIV); - mtk_hdmi_phy_mask(hdmi_phy, HDMI_CON6, (0x1 << RG_HTPLL_IC), - RG_HTPLL_IC_MASK); - mtk_hdmi_phy_mask(hdmi_phy, HDMI_CON6, (0x1 << RG_HTPLL_IR), - RG_HTPLL_IR_MASK); - mtk_hdmi_phy_mask(hdmi_phy, HDMI_CON2, (pos_div << RG_HDMITX_TX_POSDIV), - RG_HDMITX_TX_POSDIV_MASK); - mtk_hdmi_phy_mask(hdmi_phy, HDMI_CON6, (1 << RG_HTPLL_FBKSEL), - RG_HTPLL_FBKSEL_MASK); - mtk_hdmi_phy_mask(hdmi_phy, HDMI_CON6, (19 << RG_HTPLL_FBKDIV), - RG_HTPLL_FBKDIV_MASK); - mtk_hdmi_phy_mask(hdmi_phy, HDMI_CON7, (0x2 << RG_HTPLL_DIVEN), - RG_HTPLL_DIVEN_MASK); - mtk_hdmi_phy_mask(hdmi_phy, HDMI_CON6, (0xc << RG_HTPLL_BP), - RG_HTPLL_BP_MASK); - mtk_hdmi_phy_mask(hdmi_phy, HDMI_CON6, (0x2 << RG_HTPLL_BC), - RG_HTPLL_BC_MASK); - mtk_hdmi_phy_mask(hdmi_phy, HDMI_CON6, (0x1 << RG_HTPLL_BR), - RG_HTPLL_BR_MASK); - - mtk_hdmi_phy_clear_bits(hdmi_phy, HDMI_CON1, RG_HDMITX_PRED_IMP); - mtk_hdmi_phy_mask(hdmi_phy, HDMI_CON1, (0x3 << RG_HDMITX_PRED_IBIAS), - RG_HDMITX_PRED_IBIAS_MASK); - mtk_hdmi_phy_clear_bits(hdmi_phy, HDMI_CON0, RG_HDMITX_EN_IMP_MASK); - mtk_hdmi_phy_mask(hdmi_phy, HDMI_CON1, (0x28 << RG_HDMITX_DRV_IMP), - RG_HDMITX_DRV_IMP_MASK); - mtk_hdmi_phy_mask(hdmi_phy, HDMI_CON4, 0x28, RG_HDMITX_RESERVE_MASK); - mtk_hdmi_phy_mask(hdmi_phy, HDMI_CON0, (0xa << RG_HDMITX_DRV_IBIAS), - RG_HDMITX_DRV_IBIAS_MASK); - return 0; -} - -static unsigned long mtk_hdmi_pll_recalc_rate(struct clk_hw *hw, - unsigned long parent_rate) -{ - struct mtk_hdmi_phy *hdmi_phy = to_mtk_hdmi_phy(hw); - unsigned long out_rate, val; - - val = (readl(hdmi_phy->regs + HDMI_CON6) - & RG_HTPLL_PREDIV_MASK) >> RG_HTPLL_PREDIV; - switch (val) { - case 0x00: - out_rate = parent_rate; - break; - case 0x01: - out_rate = parent_rate / 2; - break; - default: - out_rate = parent_rate / 4; - break; - } - - val = (readl(hdmi_phy->regs + HDMI_CON6) - & RG_HTPLL_FBKDIV_MASK) >> RG_HTPLL_FBKDIV; - out_rate *= (val + 1) * 2; - val = (readl(hdmi_phy->regs + HDMI_CON2) - & RG_HDMITX_TX_POSDIV_MASK); - out_rate >>= (val >> RG_HDMITX_TX_POSDIV); - - if (readl(hdmi_phy->regs + HDMI_CON2) & RG_HDMITX_EN_TX_POSDIV) - out_rate /= 5; - - return out_rate; -} - -static const struct clk_ops mtk_hdmi_phy_pll_ops = { - .prepare = mtk_hdmi_pll_prepare, - .unprepare = mtk_hdmi_pll_unprepare, - .set_rate = mtk_hdmi_pll_set_rate, - .round_rate = mtk_hdmi_pll_round_rate, - .recalc_rate = mtk_hdmi_pll_recalc_rate, -}; - -static void mtk_hdmi_phy_enable_tmds(struct mtk_hdmi_phy *hdmi_phy) -{ - mtk_hdmi_phy_set_bits(hdmi_phy, HDMI_CON7, RG_HTPLL_AUTOK_EN); - mtk_hdmi_phy_clear_bits(hdmi_phy, HDMI_CON6, RG_HTPLL_RLH_EN); - mtk_hdmi_phy_set_bits(hdmi_phy, HDMI_CON6, RG_HTPLL_POSDIV_MASK); - mtk_hdmi_phy_set_bits(hdmi_phy, HDMI_CON2, RG_HDMITX_EN_MBIAS); - usleep_range(80, 100); - mtk_hdmi_phy_set_bits(hdmi_phy, HDMI_CON6, RG_HTPLL_EN); - mtk_hdmi_phy_set_bits(hdmi_phy, HDMI_CON2, RG_HDMITX_EN_TX_CKLDO); - mtk_hdmi_phy_set_bits(hdmi_phy, HDMI_CON0, RG_HDMITX_EN_SLDO_MASK); - usleep_range(80, 100); - mtk_hdmi_phy_set_bits(hdmi_phy, HDMI_CON2, RG_HDMITX_MBIAS_LPF_EN); - mtk_hdmi_phy_set_bits(hdmi_phy, HDMI_CON0, RG_HDMITX_EN_SER_MASK); - mtk_hdmi_phy_set_bits(hdmi_phy, HDMI_CON0, RG_HDMITX_EN_PRED_MASK); - mtk_hdmi_phy_set_bits(hdmi_phy, HDMI_CON0, RG_HDMITX_EN_DRV_MASK); - usleep_range(80, 100); -} - -static void mtk_hdmi_phy_disable_tmds(struct mtk_hdmi_phy *hdmi_phy) -{ - mtk_hdmi_phy_clear_bits(hdmi_phy, HDMI_CON0, RG_HDMITX_EN_DRV_MASK); - mtk_hdmi_phy_clear_bits(hdmi_phy, HDMI_CON0, RG_HDMITX_EN_PRED_MASK); - mtk_hdmi_phy_clear_bits(hdmi_phy, HDMI_CON0, RG_HDMITX_EN_SER_MASK); - mtk_hdmi_phy_clear_bits(hdmi_phy, HDMI_CON2, RG_HDMITX_MBIAS_LPF_EN); - usleep_range(80, 100); - mtk_hdmi_phy_clear_bits(hdmi_phy, HDMI_CON0, RG_HDMITX_EN_SLDO_MASK); - mtk_hdmi_phy_clear_bits(hdmi_phy, HDMI_CON2, RG_HDMITX_EN_TX_CKLDO); - mtk_hdmi_phy_clear_bits(hdmi_phy, HDMI_CON6, RG_HTPLL_EN); - usleep_range(80, 100); - mtk_hdmi_phy_clear_bits(hdmi_phy, HDMI_CON2, RG_HDMITX_EN_MBIAS); - mtk_hdmi_phy_clear_bits(hdmi_phy, HDMI_CON6, RG_HTPLL_POSDIV_MASK); - mtk_hdmi_phy_clear_bits(hdmi_phy, HDMI_CON6, RG_HTPLL_RLH_EN); - mtk_hdmi_phy_clear_bits(hdmi_phy, HDMI_CON7, RG_HTPLL_AUTOK_EN); - usleep_range(80, 100); -} - -struct mtk_hdmi_phy_conf mtk_hdmi_phy_2701_conf = { - .tz_disabled = true, - .flags = CLK_SET_RATE_GATE, - .hdmi_phy_clk_ops = &mtk_hdmi_phy_pll_ops, - .hdmi_phy_enable_tmds = mtk_hdmi_phy_enable_tmds, - .hdmi_phy_disable_tmds = mtk_hdmi_phy_disable_tmds, -}; - -MODULE_AUTHOR("Chunhui Dai <chunhui.dai@mediatek.com>"); -MODULE_DESCRIPTION("MediaTek HDMI PHY Driver"); -MODULE_LICENSE("GPL v2"); diff --git a/drivers/gpu/drm/mediatek/mtk_mt8173_hdmi_phy.c b/drivers/gpu/drm/mediatek/mtk_mt8173_hdmi_phy.c deleted file mode 100644 index 827b93786fac..000000000000 --- a/drivers/gpu/drm/mediatek/mtk_mt8173_hdmi_phy.c +++ /dev/null @@ -1,282 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * Copyright (c) 2014 MediaTek Inc. - * Author: Jie Qiu <jie.qiu@mediatek.com> - */ - -#include "mtk_hdmi_phy.h" - -#define HDMI_CON0 0x00 -#define RG_HDMITX_PLL_EN BIT(31) -#define RG_HDMITX_PLL_FBKDIV (0x7f << 24) -#define PLL_FBKDIV_SHIFT 24 -#define RG_HDMITX_PLL_FBKSEL (0x3 << 22) -#define PLL_FBKSEL_SHIFT 22 -#define RG_HDMITX_PLL_PREDIV (0x3 << 20) -#define PREDIV_SHIFT 20 -#define RG_HDMITX_PLL_POSDIV (0x3 << 18) -#define POSDIV_SHIFT 18 -#define RG_HDMITX_PLL_RST_DLY (0x3 << 16) -#define RG_HDMITX_PLL_IR (0xf << 12) -#define PLL_IR_SHIFT 12 -#define RG_HDMITX_PLL_IC (0xf << 8) -#define PLL_IC_SHIFT 8 -#define RG_HDMITX_PLL_BP (0xf << 4) -#define PLL_BP_SHIFT 4 -#define RG_HDMITX_PLL_BR (0x3 << 2) -#define PLL_BR_SHIFT 2 -#define RG_HDMITX_PLL_BC (0x3 << 0) -#define PLL_BC_SHIFT 0 -#define HDMI_CON1 0x04 -#define RG_HDMITX_PLL_DIVEN (0x7 << 29) -#define PLL_DIVEN_SHIFT 29 -#define RG_HDMITX_PLL_AUTOK_EN BIT(28) -#define RG_HDMITX_PLL_AUTOK_KF (0x3 << 26) -#define RG_HDMITX_PLL_AUTOK_KS (0x3 << 24) -#define RG_HDMITX_PLL_AUTOK_LOAD BIT(23) -#define RG_HDMITX_PLL_BAND (0x3f << 16) -#define RG_HDMITX_PLL_REF_SEL BIT(15) -#define RG_HDMITX_PLL_BIAS_EN BIT(14) -#define RG_HDMITX_PLL_BIAS_LPF_EN BIT(13) -#define RG_HDMITX_PLL_TXDIV_EN BIT(12) -#define RG_HDMITX_PLL_TXDIV (0x3 << 10) -#define PLL_TXDIV_SHIFT 10 -#define RG_HDMITX_PLL_LVROD_EN BIT(9) -#define RG_HDMITX_PLL_MONVC_EN BIT(8) -#define RG_HDMITX_PLL_MONCK_EN BIT(7) -#define RG_HDMITX_PLL_MONREF_EN BIT(6) -#define RG_HDMITX_PLL_TST_EN BIT(5) -#define RG_HDMITX_PLL_TST_CK_EN BIT(4) -#define RG_HDMITX_PLL_TST_SEL (0xf << 0) -#define HDMI_CON2 0x08 -#define RGS_HDMITX_PLL_AUTOK_BAND (0x7f << 8) -#define RGS_HDMITX_PLL_AUTOK_FAIL BIT(1) -#define RG_HDMITX_EN_TX_CKLDO BIT(0) -#define HDMI_CON3 0x0c -#define RG_HDMITX_SER_EN (0xf << 28) -#define RG_HDMITX_PRD_EN (0xf << 24) -#define RG_HDMITX_PRD_IMP_EN (0xf << 20) -#define RG_HDMITX_DRV_EN (0xf << 16) -#define RG_HDMITX_DRV_IMP_EN (0xf << 12) -#define DRV_IMP_EN_SHIFT 12 -#define RG_HDMITX_MHLCK_FORCE BIT(10) -#define RG_HDMITX_MHLCK_PPIX_EN BIT(9) -#define RG_HDMITX_MHLCK_EN BIT(8) -#define RG_HDMITX_SER_DIN_SEL (0xf << 4) -#define RG_HDMITX_SER_5T1_BIST_EN BIT(3) -#define RG_HDMITX_SER_BIST_TOG BIT(2) -#define RG_HDMITX_SER_DIN_TOG BIT(1) -#define RG_HDMITX_SER_CLKDIG_INV BIT(0) -#define HDMI_CON4 0x10 -#define RG_HDMITX_PRD_IBIAS_CLK (0xf << 24) -#define RG_HDMITX_PRD_IBIAS_D2 (0xf << 16) -#define RG_HDMITX_PRD_IBIAS_D1 (0xf << 8) -#define RG_HDMITX_PRD_IBIAS_D0 (0xf << 0) -#define PRD_IBIAS_CLK_SHIFT 24 -#define PRD_IBIAS_D2_SHIFT 16 -#define PRD_IBIAS_D1_SHIFT 8 -#define PRD_IBIAS_D0_SHIFT 0 -#define HDMI_CON5 0x14 -#define RG_HDMITX_DRV_IBIAS_CLK (0x3f << 24) -#define RG_HDMITX_DRV_IBIAS_D2 (0x3f << 16) -#define RG_HDMITX_DRV_IBIAS_D1 (0x3f << 8) -#define RG_HDMITX_DRV_IBIAS_D0 (0x3f << 0) -#define DRV_IBIAS_CLK_SHIFT 24 -#define DRV_IBIAS_D2_SHIFT 16 -#define DRV_IBIAS_D1_SHIFT 8 -#define DRV_IBIAS_D0_SHIFT 0 -#define HDMI_CON6 0x18 -#define RG_HDMITX_DRV_IMP_CLK (0x3f << 24) -#define RG_HDMITX_DRV_IMP_D2 (0x3f << 16) -#define RG_HDMITX_DRV_IMP_D1 (0x3f << 8) -#define RG_HDMITX_DRV_IMP_D0 (0x3f << 0) -#define DRV_IMP_CLK_SHIFT 24 -#define DRV_IMP_D2_SHIFT 16 -#define DRV_IMP_D1_SHIFT 8 -#define DRV_IMP_D0_SHIFT 0 -#define HDMI_CON7 0x1c -#define RG_HDMITX_MHLCK_DRV_IBIAS (0x1f << 27) -#define RG_HDMITX_SER_DIN (0x3ff << 16) -#define RG_HDMITX_CHLDC_TST (0xf << 12) -#define RG_HDMITX_CHLCK_TST (0xf << 8) -#define RG_HDMITX_RESERVE (0xff << 0) -#define HDMI_CON8 0x20 -#define RGS_HDMITX_2T1_LEV (0xf << 16) -#define RGS_HDMITX_2T1_EDG (0xf << 12) -#define RGS_HDMITX_5T1_LEV (0xf << 8) -#define RGS_HDMITX_5T1_EDG (0xf << 4) -#define RGS_HDMITX_PLUG_TST BIT(0) - -static int mtk_hdmi_pll_prepare(struct clk_hw *hw) -{ - struct mtk_hdmi_phy *hdmi_phy = to_mtk_hdmi_phy(hw); - - mtk_hdmi_phy_set_bits(hdmi_phy, HDMI_CON1, RG_HDMITX_PLL_AUTOK_EN); - mtk_hdmi_phy_set_bits(hdmi_phy, HDMI_CON0, RG_HDMITX_PLL_POSDIV); - mtk_hdmi_phy_clear_bits(hdmi_phy, HDMI_CON3, RG_HDMITX_MHLCK_EN); - mtk_hdmi_phy_set_bits(hdmi_phy, HDMI_CON1, RG_HDMITX_PLL_BIAS_EN); - usleep_range(100, 150); - mtk_hdmi_phy_set_bits(hdmi_phy, HDMI_CON0, RG_HDMITX_PLL_EN); - usleep_range(100, 150); - mtk_hdmi_phy_set_bits(hdmi_phy, HDMI_CON1, RG_HDMITX_PLL_BIAS_LPF_EN); - mtk_hdmi_phy_set_bits(hdmi_phy, HDMI_CON1, RG_HDMITX_PLL_TXDIV_EN); - - return 0; -} - -static void mtk_hdmi_pll_unprepare(struct clk_hw *hw) -{ - struct mtk_hdmi_phy *hdmi_phy = to_mtk_hdmi_phy(hw); - - mtk_hdmi_phy_clear_bits(hdmi_phy, HDMI_CON1, RG_HDMITX_PLL_TXDIV_EN); - mtk_hdmi_phy_clear_bits(hdmi_phy, HDMI_CON1, RG_HDMITX_PLL_BIAS_LPF_EN); - usleep_range(100, 150); - mtk_hdmi_phy_clear_bits(hdmi_phy, HDMI_CON0, RG_HDMITX_PLL_EN); - usleep_range(100, 150); - mtk_hdmi_phy_clear_bits(hdmi_phy, HDMI_CON1, RG_HDMITX_PLL_BIAS_EN); - mtk_hdmi_phy_clear_bits(hdmi_phy, HDMI_CON0, RG_HDMITX_PLL_POSDIV); - mtk_hdmi_phy_clear_bits(hdmi_phy, HDMI_CON1, RG_HDMITX_PLL_AUTOK_EN); - usleep_range(100, 150); -} - -static long mtk_hdmi_pll_round_rate(struct clk_hw *hw, unsigned long rate, - unsigned long *parent_rate) -{ - struct mtk_hdmi_phy *hdmi_phy = to_mtk_hdmi_phy(hw); - - hdmi_phy->pll_rate = rate; - if (rate <= 74250000) - *parent_rate = rate; - else - *parent_rate = rate / 2; - - return rate; -} - -static int mtk_hdmi_pll_set_rate(struct clk_hw *hw, unsigned long rate, - unsigned long parent_rate) -{ - struct mtk_hdmi_phy *hdmi_phy = to_mtk_hdmi_phy(hw); - unsigned int pre_div; - unsigned int div; - unsigned int pre_ibias; - unsigned int hdmi_ibias; - unsigned int imp_en; - - dev_dbg(hdmi_phy->dev, "%s: %lu Hz, parent: %lu Hz\n", __func__, - rate, parent_rate); - - if (rate <= 27000000) { - pre_div = 0; - div = 3; - } else if (rate <= 74250000) { - pre_div = 1; - div = 2; - } else { - pre_div = 1; - div = 1; - } - - mtk_hdmi_phy_mask(hdmi_phy, HDMI_CON0, - (pre_div << PREDIV_SHIFT), RG_HDMITX_PLL_PREDIV); - mtk_hdmi_phy_set_bits(hdmi_phy, HDMI_CON0, RG_HDMITX_PLL_POSDIV); - mtk_hdmi_phy_mask(hdmi_phy, HDMI_CON0, - (0x1 << PLL_IC_SHIFT) | (0x1 << PLL_IR_SHIFT), - RG_HDMITX_PLL_IC | RG_HDMITX_PLL_IR); - mtk_hdmi_phy_mask(hdmi_phy, HDMI_CON1, - (div << PLL_TXDIV_SHIFT), RG_HDMITX_PLL_TXDIV); - mtk_hdmi_phy_mask(hdmi_phy, HDMI_CON0, - (0x1 << PLL_FBKSEL_SHIFT) | (19 << PLL_FBKDIV_SHIFT), - RG_HDMITX_PLL_FBKSEL | RG_HDMITX_PLL_FBKDIV); - mtk_hdmi_phy_mask(hdmi_phy, HDMI_CON1, - (0x2 << PLL_DIVEN_SHIFT), RG_HDMITX_PLL_DIVEN); - mtk_hdmi_phy_mask(hdmi_phy, HDMI_CON0, - (0xc << PLL_BP_SHIFT) | (0x2 << PLL_BC_SHIFT) | - (0x1 << PLL_BR_SHIFT), - RG_HDMITX_PLL_BP | RG_HDMITX_PLL_BC | - RG_HDMITX_PLL_BR); - if (rate < 165000000) { - mtk_hdmi_phy_clear_bits(hdmi_phy, HDMI_CON3, - RG_HDMITX_PRD_IMP_EN); - pre_ibias = 0x3; - imp_en = 0x0; - hdmi_ibias = hdmi_phy->ibias; - } else { - mtk_hdmi_phy_set_bits(hdmi_phy, HDMI_CON3, - RG_HDMITX_PRD_IMP_EN); - pre_ibias = 0x6; - imp_en = 0xf; - hdmi_ibias = hdmi_phy->ibias_up; - } - mtk_hdmi_phy_mask(hdmi_phy, HDMI_CON4, - (pre_ibias << PRD_IBIAS_CLK_SHIFT) | - (pre_ibias << PRD_IBIAS_D2_SHIFT) | - (pre_ibias << PRD_IBIAS_D1_SHIFT) | - (pre_ibias << PRD_IBIAS_D0_SHIFT), - RG_HDMITX_PRD_IBIAS_CLK | - RG_HDMITX_PRD_IBIAS_D2 | - RG_HDMITX_PRD_IBIAS_D1 | - RG_HDMITX_PRD_IBIAS_D0); - mtk_hdmi_phy_mask(hdmi_phy, HDMI_CON3, - (imp_en << DRV_IMP_EN_SHIFT), - RG_HDMITX_DRV_IMP_EN); - mtk_hdmi_phy_mask(hdmi_phy, HDMI_CON6, - (hdmi_phy->drv_imp_clk << DRV_IMP_CLK_SHIFT) | - (hdmi_phy->drv_imp_d2 << DRV_IMP_D2_SHIFT) | - (hdmi_phy->drv_imp_d1 << DRV_IMP_D1_SHIFT) | - (hdmi_phy->drv_imp_d0 << DRV_IMP_D0_SHIFT), - RG_HDMITX_DRV_IMP_CLK | RG_HDMITX_DRV_IMP_D2 | - RG_HDMITX_DRV_IMP_D1 | RG_HDMITX_DRV_IMP_D0); - mtk_hdmi_phy_mask(hdmi_phy, HDMI_CON5, - (hdmi_ibias << DRV_IBIAS_CLK_SHIFT) | - (hdmi_ibias << DRV_IBIAS_D2_SHIFT) | - (hdmi_ibias << DRV_IBIAS_D1_SHIFT) | - (hdmi_ibias << DRV_IBIAS_D0_SHIFT), - RG_HDMITX_DRV_IBIAS_CLK | - RG_HDMITX_DRV_IBIAS_D2 | - RG_HDMITX_DRV_IBIAS_D1 | - RG_HDMITX_DRV_IBIAS_D0); - return 0; -} - -static unsigned long mtk_hdmi_pll_recalc_rate(struct clk_hw *hw, - unsigned long parent_rate) -{ - struct mtk_hdmi_phy *hdmi_phy = to_mtk_hdmi_phy(hw); - - return hdmi_phy->pll_rate; -} - -static const struct clk_ops mtk_hdmi_phy_pll_ops = { - .prepare = mtk_hdmi_pll_prepare, - .unprepare = mtk_hdmi_pll_unprepare, - .set_rate = mtk_hdmi_pll_set_rate, - .round_rate = mtk_hdmi_pll_round_rate, - .recalc_rate = mtk_hdmi_pll_recalc_rate, -}; - -static void mtk_hdmi_phy_enable_tmds(struct mtk_hdmi_phy *hdmi_phy) -{ - mtk_hdmi_phy_set_bits(hdmi_phy, HDMI_CON3, - RG_HDMITX_SER_EN | RG_HDMITX_PRD_EN | - RG_HDMITX_DRV_EN); - usleep_range(100, 150); -} - -static void mtk_hdmi_phy_disable_tmds(struct mtk_hdmi_phy *hdmi_phy) -{ - mtk_hdmi_phy_clear_bits(hdmi_phy, HDMI_CON3, - RG_HDMITX_DRV_EN | RG_HDMITX_PRD_EN | - RG_HDMITX_SER_EN); -} - -struct mtk_hdmi_phy_conf mtk_hdmi_phy_8173_conf = { - .flags = CLK_SET_RATE_PARENT | CLK_SET_RATE_GATE, - .hdmi_phy_clk_ops = &mtk_hdmi_phy_pll_ops, - .hdmi_phy_enable_tmds = mtk_hdmi_phy_enable_tmds, - .hdmi_phy_disable_tmds = mtk_hdmi_phy_disable_tmds, -}; - -MODULE_AUTHOR("Jie Qiu <jie.qiu@mediatek.com>"); -MODULE_DESCRIPTION("MediaTek MT8173 HDMI PHY Driver"); -MODULE_LICENSE("GPL v2"); diff --git a/drivers/gpu/drm/msm/Kconfig b/drivers/gpu/drm/msm/Kconfig index 6deaa7d01654..e5816b498494 100644 --- a/drivers/gpu/drm/msm/Kconfig +++ b/drivers/gpu/drm/msm/Kconfig @@ -6,8 +6,8 @@ config DRM_MSM depends on ARCH_QCOM || SOC_IMX5 || (ARM && COMPILE_TEST) depends on OF && COMMON_CLK depends on MMU - depends on INTERCONNECT || !INTERCONNECT depends on QCOM_OCMEM || QCOM_OCMEM=n + select IOMMU_IO_PGTABLE select QCOM_MDT_LOADER if ARCH_QCOM select REGULATOR select DRM_KMS_HELPER @@ -57,6 +57,15 @@ config DRM_MSM_HDMI_HDCP help Choose this option to enable HDCP state machine +config DRM_MSM_DP + bool "Enable DisplayPort support in MSM DRM driver" + depends on DRM_MSM + default y + help + Compile in support for DP driver in MSM DRM driver. DP external + display support is enabled through this config option. It can + be primary or secondary display on device. + config DRM_MSM_DSI bool "Enable DSI support in MSM DRM driver" depends on DRM_MSM @@ -110,3 +119,11 @@ config DRM_MSM_DSI_10NM_PHY default y help Choose this option if DSI PHY on SDM845 is used on the platform. + +config DRM_MSM_DSI_7NM_PHY + bool "Enable DSI 7nm PHY driver in MSM DRM (used by SM8150/SM8250)" + depends on DRM_MSM_DSI + default y + help + Choose this option if DSI PHY on SM8150/SM8250 is used on the + platform. diff --git a/drivers/gpu/drm/msm/Makefile b/drivers/gpu/drm/msm/Makefile index 42f8aae28b31..340682cd0f32 100644 --- a/drivers/gpu/drm/msm/Makefile +++ b/drivers/gpu/drm/msm/Makefile @@ -2,6 +2,7 @@ ccflags-y := -I $(srctree)/$(src) ccflags-y += -I $(srctree)/$(src)/disp/dpu1 ccflags-$(CONFIG_DRM_MSM_DSI) += -I $(srctree)/$(src)/dsi +ccflags-$(CONFIG_DRM_MSM_DP) += -I $(srctree)/$(src)/dp msm-y := \ adreno/adreno_device.o \ @@ -95,10 +96,23 @@ msm-y := \ msm_gpu_tracepoints.o \ msm_gpummu.o -msm-$(CONFIG_DEBUG_FS) += adreno/a5xx_debugfs.o +msm-$(CONFIG_DEBUG_FS) += adreno/a5xx_debugfs.o \ + dp/dp_debug.o msm-$(CONFIG_DRM_MSM_GPU_STATE) += adreno/a6xx_gpu_state.o +msm-$(CONFIG_DRM_MSM_DP)+= dp/dp_aux.o \ + dp/dp_catalog.o \ + dp/dp_ctrl.o \ + dp/dp_display.o \ + dp/dp_drm.o \ + dp/dp_hpd.o \ + dp/dp_link.o \ + dp/dp_panel.o \ + dp/dp_parser.o \ + dp/dp_power.o \ + dp/dp_audio.o + msm-$(CONFIG_DRM_FBDEV_EMULATION) += msm_fbdev.o msm-$(CONFIG_COMMON_CLK) += disp/mdp4/mdp4_lvds_pll.o msm-$(CONFIG_COMMON_CLK) += hdmi/hdmi_pll_8960.o @@ -119,6 +133,7 @@ msm-$(CONFIG_DRM_MSM_DSI_20NM_PHY) += dsi/phy/dsi_phy_20nm.o msm-$(CONFIG_DRM_MSM_DSI_28NM_8960_PHY) += dsi/phy/dsi_phy_28nm_8960.o msm-$(CONFIG_DRM_MSM_DSI_14NM_PHY) += dsi/phy/dsi_phy_14nm.o msm-$(CONFIG_DRM_MSM_DSI_10NM_PHY) += dsi/phy/dsi_phy_10nm.o +msm-$(CONFIG_DRM_MSM_DSI_7NM_PHY) += dsi/phy/dsi_phy_7nm.o ifeq ($(CONFIG_DRM_MSM_DSI_PLL),y) msm-y += dsi/pll/dsi_pll.o @@ -126,6 +141,7 @@ msm-$(CONFIG_DRM_MSM_DSI_28NM_PHY) += dsi/pll/dsi_pll_28nm.o msm-$(CONFIG_DRM_MSM_DSI_28NM_8960_PHY) += dsi/pll/dsi_pll_28nm_8960.o msm-$(CONFIG_DRM_MSM_DSI_14NM_PHY) += dsi/pll/dsi_pll_14nm.o msm-$(CONFIG_DRM_MSM_DSI_10NM_PHY) += dsi/pll/dsi_pll_10nm.o +msm-$(CONFIG_DRM_MSM_DSI_7NM_PHY) += dsi/pll/dsi_pll_7nm.o endif obj-$(CONFIG_DRM_MSM) += msm.o diff --git a/drivers/gpu/drm/msm/adreno/a2xx_gpu.c b/drivers/gpu/drm/msm/adreno/a2xx_gpu.c index 48fa49f69d6d..7e82c41a85f1 100644 --- a/drivers/gpu/drm/msm/adreno/a2xx_gpu.c +++ b/drivers/gpu/drm/msm/adreno/a2xx_gpu.c @@ -10,6 +10,48 @@ extern bool hang_debug; static void a2xx_dump(struct msm_gpu *gpu); static bool a2xx_idle(struct msm_gpu *gpu); +static void a2xx_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit) +{ + struct msm_drm_private *priv = gpu->dev->dev_private; + struct msm_ringbuffer *ring = submit->ring; + unsigned int i; + + for (i = 0; i < submit->nr_cmds; i++) { + switch (submit->cmd[i].type) { + case MSM_SUBMIT_CMD_IB_TARGET_BUF: + /* ignore IB-targets */ + break; + case MSM_SUBMIT_CMD_CTX_RESTORE_BUF: + /* ignore if there has not been a ctx switch: */ + if (priv->lastctx == submit->queue->ctx) + break; + fallthrough; + case MSM_SUBMIT_CMD_BUF: + OUT_PKT3(ring, CP_INDIRECT_BUFFER_PFD, 2); + OUT_RING(ring, lower_32_bits(submit->cmd[i].iova)); + OUT_RING(ring, submit->cmd[i].size); + OUT_PKT2(ring); + break; + } + } + + OUT_PKT0(ring, REG_AXXX_CP_SCRATCH_REG2, 1); + OUT_RING(ring, submit->seqno); + + /* wait for idle before cache flush/interrupt */ + OUT_PKT3(ring, CP_WAIT_FOR_IDLE, 1); + OUT_RING(ring, 0x00000000); + + OUT_PKT3(ring, CP_EVENT_WRITE, 3); + OUT_RING(ring, CACHE_FLUSH_TS); + OUT_RING(ring, rbmemptr(ring, fence)); + OUT_RING(ring, submit->seqno); + OUT_PKT3(ring, CP_INTERRUPT, 1); + OUT_RING(ring, 0x80000000); + + adreno_flush(gpu, ring, REG_AXXX_CP_RB_WPTR); +} + static bool a2xx_me_init(struct msm_gpu *gpu) { struct msm_ringbuffer *ring = gpu->rb[0]; @@ -53,7 +95,7 @@ static bool a2xx_me_init(struct msm_gpu *gpu) OUT_PKT3(ring, CP_SET_PROTECTED_MODE, 1); OUT_RING(ring, 1); - gpu->funcs->flush(gpu, ring); + adreno_flush(gpu, ring, REG_AXXX_CP_RB_WPTR); return a2xx_idle(gpu); } @@ -421,16 +463,11 @@ a2xx_create_address_space(struct msm_gpu *gpu, struct platform_device *pdev) return aspace; } -/* Register offset defines for A2XX - copy of A3XX */ -static const unsigned int a2xx_register_offsets[REG_ADRENO_REGISTER_MAX] = { - REG_ADRENO_DEFINE(REG_ADRENO_CP_RB_BASE, REG_AXXX_CP_RB_BASE), - REG_ADRENO_SKIP(REG_ADRENO_CP_RB_BASE_HI), - REG_ADRENO_DEFINE(REG_ADRENO_CP_RB_RPTR_ADDR, REG_AXXX_CP_RB_RPTR_ADDR), - REG_ADRENO_SKIP(REG_ADRENO_CP_RB_RPTR_ADDR_HI), - REG_ADRENO_DEFINE(REG_ADRENO_CP_RB_RPTR, REG_AXXX_CP_RB_RPTR), - REG_ADRENO_DEFINE(REG_ADRENO_CP_RB_WPTR, REG_AXXX_CP_RB_WPTR), - REG_ADRENO_DEFINE(REG_ADRENO_CP_RB_CNTL, REG_AXXX_CP_RB_CNTL), -}; +static u32 a2xx_get_rptr(struct msm_gpu *gpu, struct msm_ringbuffer *ring) +{ + ring->memptrs->rptr = gpu_read(gpu, REG_AXXX_CP_RB_RPTR); + return ring->memptrs->rptr; +} static const struct adreno_gpu_funcs funcs = { .base = { @@ -439,8 +476,7 @@ static const struct adreno_gpu_funcs funcs = { .pm_suspend = msm_gpu_pm_suspend, .pm_resume = msm_gpu_pm_resume, .recover = a2xx_recover, - .submit = adreno_submit, - .flush = adreno_flush, + .submit = a2xx_submit, .active_ring = adreno_active_ring, .irq = a2xx_irq, .destroy = a2xx_destroy, @@ -450,6 +486,7 @@ static const struct adreno_gpu_funcs funcs = { .gpu_state_get = a2xx_gpu_state_get, .gpu_state_put = adreno_gpu_state_put, .create_address_space = a2xx_create_address_space, + .get_rptr = a2xx_get_rptr, }, }; @@ -491,8 +528,6 @@ struct msm_gpu *a2xx_gpu_init(struct drm_device *dev) else adreno_gpu->registers = a220_registers; - adreno_gpu->reg_offsets = a2xx_register_offsets; - ret = adreno_gpu_init(dev, pdev, adreno_gpu, &funcs, 1); if (ret) goto fail; diff --git a/drivers/gpu/drm/msm/adreno/a3xx_gpu.c b/drivers/gpu/drm/msm/adreno/a3xx_gpu.c index f6471145a7a6..f29c77d9cd42 100644 --- a/drivers/gpu/drm/msm/adreno/a3xx_gpu.c +++ b/drivers/gpu/drm/msm/adreno/a3xx_gpu.c @@ -28,6 +28,61 @@ extern bool hang_debug; static void a3xx_dump(struct msm_gpu *gpu); static bool a3xx_idle(struct msm_gpu *gpu); +static void a3xx_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit) +{ + struct msm_drm_private *priv = gpu->dev->dev_private; + struct msm_ringbuffer *ring = submit->ring; + unsigned int i; + + for (i = 0; i < submit->nr_cmds; i++) { + switch (submit->cmd[i].type) { + case MSM_SUBMIT_CMD_IB_TARGET_BUF: + /* ignore IB-targets */ + break; + case MSM_SUBMIT_CMD_CTX_RESTORE_BUF: + /* ignore if there has not been a ctx switch: */ + if (priv->lastctx == submit->queue->ctx) + break; + fallthrough; + case MSM_SUBMIT_CMD_BUF: + OUT_PKT3(ring, CP_INDIRECT_BUFFER_PFD, 2); + OUT_RING(ring, lower_32_bits(submit->cmd[i].iova)); + OUT_RING(ring, submit->cmd[i].size); + OUT_PKT2(ring); + break; + } + } + + OUT_PKT0(ring, REG_AXXX_CP_SCRATCH_REG2, 1); + OUT_RING(ring, submit->seqno); + + /* Flush HLSQ lazy updates to make sure there is nothing + * pending for indirect loads after the timestamp has + * passed: + */ + OUT_PKT3(ring, CP_EVENT_WRITE, 1); + OUT_RING(ring, HLSQ_FLUSH); + + /* wait for idle before cache flush/interrupt */ + OUT_PKT3(ring, CP_WAIT_FOR_IDLE, 1); + OUT_RING(ring, 0x00000000); + + /* BIT(31) of CACHE_FLUSH_TS triggers CACHE_FLUSH_TS IRQ from GPU */ + OUT_PKT3(ring, CP_EVENT_WRITE, 3); + OUT_RING(ring, CACHE_FLUSH_TS | BIT(31)); + OUT_RING(ring, rbmemptr(ring, fence)); + OUT_RING(ring, submit->seqno); + +#if 0 + /* Dummy set-constant to trigger context rollover */ + OUT_PKT3(ring, CP_SET_CONSTANT, 2); + OUT_RING(ring, CP_REG(REG_A3XX_HLSQ_CL_KERNEL_GROUP_X_REG)); + OUT_RING(ring, 0x00000000); +#endif + + adreno_flush(gpu, ring, REG_AXXX_CP_RB_WPTR); +} + static bool a3xx_me_init(struct msm_gpu *gpu) { struct msm_ringbuffer *ring = gpu->rb[0]; @@ -51,7 +106,7 @@ static bool a3xx_me_init(struct msm_gpu *gpu) OUT_RING(ring, 0x00000000); OUT_RING(ring, 0x00000000); - gpu->funcs->flush(gpu, ring); + adreno_flush(gpu, ring, REG_AXXX_CP_RB_WPTR); return a3xx_idle(gpu); } @@ -423,16 +478,11 @@ static struct msm_gpu_state *a3xx_gpu_state_get(struct msm_gpu *gpu) return state; } -/* Register offset defines for A3XX */ -static const unsigned int a3xx_register_offsets[REG_ADRENO_REGISTER_MAX] = { - REG_ADRENO_DEFINE(REG_ADRENO_CP_RB_BASE, REG_AXXX_CP_RB_BASE), - REG_ADRENO_SKIP(REG_ADRENO_CP_RB_BASE_HI), - REG_ADRENO_DEFINE(REG_ADRENO_CP_RB_RPTR_ADDR, REG_AXXX_CP_RB_RPTR_ADDR), - REG_ADRENO_SKIP(REG_ADRENO_CP_RB_RPTR_ADDR_HI), - REG_ADRENO_DEFINE(REG_ADRENO_CP_RB_RPTR, REG_AXXX_CP_RB_RPTR), - REG_ADRENO_DEFINE(REG_ADRENO_CP_RB_WPTR, REG_AXXX_CP_RB_WPTR), - REG_ADRENO_DEFINE(REG_ADRENO_CP_RB_CNTL, REG_AXXX_CP_RB_CNTL), -}; +static u32 a3xx_get_rptr(struct msm_gpu *gpu, struct msm_ringbuffer *ring) +{ + ring->memptrs->rptr = gpu_read(gpu, REG_AXXX_CP_RB_RPTR); + return ring->memptrs->rptr; +} static const struct adreno_gpu_funcs funcs = { .base = { @@ -441,8 +491,7 @@ static const struct adreno_gpu_funcs funcs = { .pm_suspend = msm_gpu_pm_suspend, .pm_resume = msm_gpu_pm_resume, .recover = a3xx_recover, - .submit = adreno_submit, - .flush = adreno_flush, + .submit = a3xx_submit, .active_ring = adreno_active_ring, .irq = a3xx_irq, .destroy = a3xx_destroy, @@ -452,6 +501,7 @@ static const struct adreno_gpu_funcs funcs = { .gpu_state_get = a3xx_gpu_state_get, .gpu_state_put = adreno_gpu_state_put, .create_address_space = adreno_iommu_create_address_space, + .get_rptr = a3xx_get_rptr, }, }; @@ -490,7 +540,6 @@ struct msm_gpu *a3xx_gpu_init(struct drm_device *dev) gpu->num_perfcntrs = ARRAY_SIZE(perfcntrs); adreno_gpu->registers = a3xx_registers; - adreno_gpu->reg_offsets = a3xx_register_offsets; ret = adreno_gpu_init(dev, pdev, adreno_gpu, &funcs, 1); if (ret) diff --git a/drivers/gpu/drm/msm/adreno/a4xx_gpu.c b/drivers/gpu/drm/msm/adreno/a4xx_gpu.c index 954753600625..2b93b33b05e4 100644 --- a/drivers/gpu/drm/msm/adreno/a4xx_gpu.c +++ b/drivers/gpu/drm/msm/adreno/a4xx_gpu.c @@ -22,6 +22,54 @@ extern bool hang_debug; static void a4xx_dump(struct msm_gpu *gpu); static bool a4xx_idle(struct msm_gpu *gpu); +static void a4xx_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit) +{ + struct msm_drm_private *priv = gpu->dev->dev_private; + struct msm_ringbuffer *ring = submit->ring; + unsigned int i; + + for (i = 0; i < submit->nr_cmds; i++) { + switch (submit->cmd[i].type) { + case MSM_SUBMIT_CMD_IB_TARGET_BUF: + /* ignore IB-targets */ + break; + case MSM_SUBMIT_CMD_CTX_RESTORE_BUF: + /* ignore if there has not been a ctx switch: */ + if (priv->lastctx == submit->queue->ctx) + break; + fallthrough; + case MSM_SUBMIT_CMD_BUF: + OUT_PKT3(ring, CP_INDIRECT_BUFFER_PFE, 2); + OUT_RING(ring, lower_32_bits(submit->cmd[i].iova)); + OUT_RING(ring, submit->cmd[i].size); + OUT_PKT2(ring); + break; + } + } + + OUT_PKT0(ring, REG_AXXX_CP_SCRATCH_REG2, 1); + OUT_RING(ring, submit->seqno); + + /* Flush HLSQ lazy updates to make sure there is nothing + * pending for indirect loads after the timestamp has + * passed: + */ + OUT_PKT3(ring, CP_EVENT_WRITE, 1); + OUT_RING(ring, HLSQ_FLUSH); + + /* wait for idle before cache flush/interrupt */ + OUT_PKT3(ring, CP_WAIT_FOR_IDLE, 1); + OUT_RING(ring, 0x00000000); + + /* BIT(31) of CACHE_FLUSH_TS triggers CACHE_FLUSH_TS IRQ from GPU */ + OUT_PKT3(ring, CP_EVENT_WRITE, 3); + OUT_RING(ring, CACHE_FLUSH_TS | BIT(31)); + OUT_RING(ring, rbmemptr(ring, fence)); + OUT_RING(ring, submit->seqno); + + adreno_flush(gpu, ring, REG_A4XX_CP_RB_WPTR); +} + /* * a4xx_enable_hwcg() - Program the clock control registers * @device: The adreno device pointer @@ -129,7 +177,7 @@ static bool a4xx_me_init(struct msm_gpu *gpu) OUT_RING(ring, 0x00000000); OUT_RING(ring, 0x00000000); - gpu->funcs->flush(gpu, ring); + adreno_flush(gpu, ring, REG_A4XX_CP_RB_WPTR); return a4xx_idle(gpu); } @@ -515,17 +563,6 @@ static struct msm_gpu_state *a4xx_gpu_state_get(struct msm_gpu *gpu) return state; } -/* Register offset defines for A4XX, in order of enum adreno_regs */ -static const unsigned int a4xx_register_offsets[REG_ADRENO_REGISTER_MAX] = { - REG_ADRENO_DEFINE(REG_ADRENO_CP_RB_BASE, REG_A4XX_CP_RB_BASE), - REG_ADRENO_SKIP(REG_ADRENO_CP_RB_BASE_HI), - REG_ADRENO_DEFINE(REG_ADRENO_CP_RB_RPTR_ADDR, REG_A4XX_CP_RB_RPTR_ADDR), - REG_ADRENO_SKIP(REG_ADRENO_CP_RB_RPTR_ADDR_HI), - REG_ADRENO_DEFINE(REG_ADRENO_CP_RB_RPTR, REG_A4XX_CP_RB_RPTR), - REG_ADRENO_DEFINE(REG_ADRENO_CP_RB_WPTR, REG_A4XX_CP_RB_WPTR), - REG_ADRENO_DEFINE(REG_ADRENO_CP_RB_CNTL, REG_A4XX_CP_RB_CNTL), -}; - static void a4xx_dump(struct msm_gpu *gpu) { printk("status: %08x\n", @@ -576,6 +613,12 @@ static int a4xx_get_timestamp(struct msm_gpu *gpu, uint64_t *value) return 0; } +static u32 a4xx_get_rptr(struct msm_gpu *gpu, struct msm_ringbuffer *ring) +{ + ring->memptrs->rptr = gpu_read(gpu, REG_A4XX_CP_RB_RPTR); + return ring->memptrs->rptr; +} + static const struct adreno_gpu_funcs funcs = { .base = { .get_param = adreno_get_param, @@ -583,8 +626,7 @@ static const struct adreno_gpu_funcs funcs = { .pm_suspend = a4xx_pm_suspend, .pm_resume = a4xx_pm_resume, .recover = a4xx_recover, - .submit = adreno_submit, - .flush = adreno_flush, + .submit = a4xx_submit, .active_ring = adreno_active_ring, .irq = a4xx_irq, .destroy = a4xx_destroy, @@ -594,6 +636,7 @@ static const struct adreno_gpu_funcs funcs = { .gpu_state_get = a4xx_gpu_state_get, .gpu_state_put = adreno_gpu_state_put, .create_address_space = adreno_iommu_create_address_space, + .get_rptr = a4xx_get_rptr, }, .get_timestamp = a4xx_get_timestamp, }; @@ -631,15 +674,12 @@ struct msm_gpu *a4xx_gpu_init(struct drm_device *dev) adreno_gpu->registers = adreno_is_a405(adreno_gpu) ? a405_registers : a4xx_registers; - adreno_gpu->reg_offsets = a4xx_register_offsets; /* if needed, allocate gmem: */ - if (adreno_is_a4xx(adreno_gpu)) { - ret = adreno_gpu_ocmem_init(dev->dev, adreno_gpu, - &a4xx_gpu->ocmem); - if (ret) - goto fail; - } + ret = adreno_gpu_ocmem_init(dev->dev, adreno_gpu, + &a4xx_gpu->ocmem); + if (ret) + goto fail; if (!gpu->aspace) { /* TODO we think it is possible to configure the GPU to diff --git a/drivers/gpu/drm/msm/adreno/a5xx_debugfs.c b/drivers/gpu/drm/msm/adreno/a5xx_debugfs.c index 68eddac7771c..fc2c905b6c9e 100644 --- a/drivers/gpu/drm/msm/adreno/a5xx_debugfs.c +++ b/drivers/gpu/drm/msm/adreno/a5xx_debugfs.c @@ -11,7 +11,7 @@ #include "a5xx_gpu.h" -static int pfp_print(struct msm_gpu *gpu, struct drm_printer *p) +static void pfp_print(struct msm_gpu *gpu, struct drm_printer *p) { int i; @@ -22,11 +22,9 @@ static int pfp_print(struct msm_gpu *gpu, struct drm_printer *p) drm_printf(p, " %02x: %08x\n", i, gpu_read(gpu, REG_A5XX_CP_PFP_STAT_DATA)); } - - return 0; } -static int me_print(struct msm_gpu *gpu, struct drm_printer *p) +static void me_print(struct msm_gpu *gpu, struct drm_printer *p) { int i; @@ -37,11 +35,9 @@ static int me_print(struct msm_gpu *gpu, struct drm_printer *p) drm_printf(p, " %02x: %08x\n", i, gpu_read(gpu, REG_A5XX_CP_ME_STAT_DATA)); } - - return 0; } -static int meq_print(struct msm_gpu *gpu, struct drm_printer *p) +static void meq_print(struct msm_gpu *gpu, struct drm_printer *p) { int i; @@ -52,11 +48,9 @@ static int meq_print(struct msm_gpu *gpu, struct drm_printer *p) drm_printf(p, " %02x: %08x\n", i, gpu_read(gpu, REG_A5XX_CP_MEQ_DBG_DATA)); } - - return 0; } -static int roq_print(struct msm_gpu *gpu, struct drm_printer *p) +static void roq_print(struct msm_gpu *gpu, struct drm_printer *p) { int i; @@ -71,8 +65,6 @@ static int roq_print(struct msm_gpu *gpu, struct drm_printer *p) drm_printf(p, " %02x: %08x %08x %08x %08x\n", i, val[0], val[1], val[2], val[3]); } - - return 0; } static int show(struct seq_file *m, void *arg) @@ -81,10 +73,11 @@ static int show(struct seq_file *m, void *arg) struct drm_device *dev = node->minor->dev; struct msm_drm_private *priv = dev->dev_private; struct drm_printer p = drm_seq_file_printer(m); - int (*show)(struct msm_gpu *gpu, struct drm_printer *p) = + void (*show)(struct msm_gpu *gpu, struct drm_printer *p) = node->info_ent->data; - return show(priv->gpu, &p); + show(priv->gpu, &p); + return 0; } #define ENT(n) { .name = #n, .show = show, .data = n ##_print } diff --git a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c index 91726da82ed6..d6804a802355 100644 --- a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c +++ b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c @@ -18,13 +18,24 @@ static void a5xx_dump(struct msm_gpu *gpu); #define GPU_PAS_ID 13 -static void a5xx_flush(struct msm_gpu *gpu, struct msm_ringbuffer *ring) +void a5xx_flush(struct msm_gpu *gpu, struct msm_ringbuffer *ring, + bool sync) { struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu); struct a5xx_gpu *a5xx_gpu = to_a5xx_gpu(adreno_gpu); uint32_t wptr; unsigned long flags; + /* + * Most flush operations need to issue a WHERE_AM_I opcode to sync up + * the rptr shadow + */ + if (a5xx_gpu->has_whereami && sync) { + OUT_PKT7(ring, CP_WHERE_AM_I, 2); + OUT_RING(ring, lower_32_bits(shadowptr(a5xx_gpu, ring))); + OUT_RING(ring, upper_32_bits(shadowptr(a5xx_gpu, ring))); + } + spin_lock_irqsave(&ring->lock, flags); /* Copy the shadow to the actual register */ @@ -43,8 +54,7 @@ static void a5xx_flush(struct msm_gpu *gpu, struct msm_ringbuffer *ring) gpu_write(gpu, REG_A5XX_CP_RB_WPTR, wptr); } -static void a5xx_submit_in_rb(struct msm_gpu *gpu, struct msm_gem_submit *submit, - struct msm_file_private *ctx) +static void a5xx_submit_in_rb(struct msm_gpu *gpu, struct msm_gem_submit *submit) { struct msm_drm_private *priv = gpu->dev->dev_private; struct msm_ringbuffer *ring = submit->ring; @@ -57,7 +67,7 @@ static void a5xx_submit_in_rb(struct msm_gpu *gpu, struct msm_gem_submit *submit case MSM_SUBMIT_CMD_IB_TARGET_BUF: break; case MSM_SUBMIT_CMD_CTX_RESTORE_BUF: - if (priv->lastctx == ctx) + if (priv->lastctx == submit->queue->ctx) break; fallthrough; case MSM_SUBMIT_CMD_BUF: @@ -91,7 +101,7 @@ static void a5xx_submit_in_rb(struct msm_gpu *gpu, struct msm_gem_submit *submit } } - a5xx_flush(gpu, ring); + a5xx_flush(gpu, ring, true); a5xx_preempt_trigger(gpu); /* we might not necessarily have a cmd from userspace to @@ -103,8 +113,7 @@ static void a5xx_submit_in_rb(struct msm_gpu *gpu, struct msm_gem_submit *submit msm_gpu_retire(gpu); } -static void a5xx_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit, - struct msm_file_private *ctx) +static void a5xx_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit) { struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu); struct a5xx_gpu *a5xx_gpu = to_a5xx_gpu(adreno_gpu); @@ -114,7 +123,7 @@ static void a5xx_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit, if (IS_ENABLED(CONFIG_DRM_MSM_GPU_SUDO) && submit->in_rb) { priv->lastctx = NULL; - a5xx_submit_in_rb(gpu, submit, ctx); + a5xx_submit_in_rb(gpu, submit); return; } @@ -148,7 +157,7 @@ static void a5xx_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit, case MSM_SUBMIT_CMD_IB_TARGET_BUF: break; case MSM_SUBMIT_CMD_CTX_RESTORE_BUF: - if (priv->lastctx == ctx) + if (priv->lastctx == submit->queue->ctx) break; fallthrough; case MSM_SUBMIT_CMD_BUF: @@ -206,7 +215,8 @@ static void a5xx_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit, /* Set bit 0 to trigger an interrupt on preempt complete */ OUT_RING(ring, 0x01); - a5xx_flush(gpu, ring); + /* A WHERE_AM_I packet is not needed after a YIELD */ + a5xx_flush(gpu, ring, false); /* Check to see if we need to start preemption */ a5xx_preempt_trigger(gpu); @@ -365,7 +375,7 @@ static int a5xx_me_init(struct msm_gpu *gpu) OUT_RING(ring, 0x00000000); OUT_RING(ring, 0x00000000); - gpu->funcs->flush(gpu, ring); + a5xx_flush(gpu, ring, true); return a5xx_idle(gpu, ring) ? 0 : -EINVAL; } @@ -407,11 +417,31 @@ static int a5xx_preempt_start(struct msm_gpu *gpu) OUT_RING(ring, 0x01); OUT_RING(ring, 0x01); - gpu->funcs->flush(gpu, ring); + /* The WHERE_AMI_I packet is not needed after a YIELD is issued */ + a5xx_flush(gpu, ring, false); return a5xx_idle(gpu, ring) ? 0 : -EINVAL; } +static void a5xx_ucode_check_version(struct a5xx_gpu *a5xx_gpu, + struct drm_gem_object *obj) +{ + u32 *buf = msm_gem_get_vaddr_active(obj); + + if (IS_ERR(buf)) + return; + + /* + * If the lowest nibble is 0xa that is an indication that this microcode + * has been patched. The actual version is in dword [3] but we only care + * about the patchlevel which is the lowest nibble of dword [3] + */ + if (((buf[0] & 0xf) == 0xa) && (buf[2] & 0xf) >= 1) + a5xx_gpu->has_whereami = true; + + msm_gem_put_vaddr(obj); +} + static int a5xx_ucode_init(struct msm_gpu *gpu) { struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu); @@ -447,6 +477,7 @@ static int a5xx_ucode_init(struct msm_gpu *gpu) } msm_gem_object_set_name(a5xx_gpu->pfp_bo, "pfpfw"); + a5xx_ucode_check_version(a5xx_gpu, a5xx_gpu->pfp_bo); } gpu_write64(gpu, REG_A5XX_CP_ME_INSTR_BASE_LO, @@ -506,6 +537,7 @@ static int a5xx_zap_shader_init(struct msm_gpu *gpu) static int a5xx_hw_init(struct msm_gpu *gpu) { struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu); + struct a5xx_gpu *a5xx_gpu = to_a5xx_gpu(adreno_gpu); int ret; gpu_write(gpu, REG_A5XX_VBIF_ROUND_ROBIN_QOS_ARB, 0x00000003); @@ -714,9 +746,36 @@ static int a5xx_hw_init(struct msm_gpu *gpu) gpu_write64(gpu, REG_A5XX_CP_RB_BASE, REG_A5XX_CP_RB_BASE_HI, gpu->rb[0]->iova); + /* + * If the microcode supports the WHERE_AM_I opcode then we can use that + * in lieu of the RPTR shadow and enable preemption. Otherwise, we + * can't safely use the RPTR shadow or preemption. In either case, the + * RPTR shadow should be disabled in hardware. + */ gpu_write(gpu, REG_A5XX_CP_RB_CNTL, MSM_GPU_RB_CNTL_DEFAULT | AXXX_CP_RB_CNTL_NO_UPDATE); + /* Disable preemption if WHERE_AM_I isn't available */ + if (!a5xx_gpu->has_whereami && gpu->nr_rings > 1) { + a5xx_preempt_fini(gpu); + gpu->nr_rings = 1; + } else { + /* Create a privileged buffer for the RPTR shadow */ + if (!a5xx_gpu->shadow_bo) { + a5xx_gpu->shadow = msm_gem_kernel_new(gpu->dev, + sizeof(u32) * gpu->nr_rings, + MSM_BO_UNCACHED | MSM_BO_MAP_PRIV, + gpu->aspace, &a5xx_gpu->shadow_bo, + &a5xx_gpu->shadow_iova); + + if (IS_ERR(a5xx_gpu->shadow)) + return PTR_ERR(a5xx_gpu->shadow); + } + + gpu_write64(gpu, REG_A5XX_CP_RB_RPTR_ADDR, + REG_A5XX_CP_RB_RPTR_ADDR_HI, shadowptr(a5xx_gpu, gpu->rb[0])); + } + a5xx_preempt_hw_init(gpu); /* Disable the interrupts through the initial bringup stage */ @@ -740,7 +799,7 @@ static int a5xx_hw_init(struct msm_gpu *gpu) OUT_PKT7(gpu->rb[0], CP_EVENT_WRITE, 1); OUT_RING(gpu->rb[0], CP_EVENT_WRITE_0_EVENT(STAT_EVENT)); - gpu->funcs->flush(gpu, gpu->rb[0]); + a5xx_flush(gpu, gpu->rb[0], true); if (!a5xx_idle(gpu, gpu->rb[0])) return -EINVAL; } @@ -758,7 +817,7 @@ static int a5xx_hw_init(struct msm_gpu *gpu) OUT_PKT7(gpu->rb[0], CP_SET_SECURE_MODE, 1); OUT_RING(gpu->rb[0], 0x00000000); - gpu->funcs->flush(gpu, gpu->rb[0]); + a5xx_flush(gpu, gpu->rb[0], true); if (!a5xx_idle(gpu, gpu->rb[0])) return -EINVAL; } else if (ret == -ENODEV) { @@ -825,6 +884,11 @@ static void a5xx_destroy(struct msm_gpu *gpu) drm_gem_object_put(a5xx_gpu->gpmu_bo); } + if (a5xx_gpu->shadow_bo) { + msm_gem_unpin_iova(a5xx_gpu->shadow_bo, gpu->aspace); + drm_gem_object_put(a5xx_gpu->shadow_bo); + } + adreno_gpu_cleanup(adreno_gpu); kfree(a5xx_gpu); } @@ -1057,17 +1121,6 @@ static irqreturn_t a5xx_irq(struct msm_gpu *gpu) return IRQ_HANDLED; } -static const u32 a5xx_register_offsets[REG_ADRENO_REGISTER_MAX] = { - REG_ADRENO_DEFINE(REG_ADRENO_CP_RB_BASE, REG_A5XX_CP_RB_BASE), - REG_ADRENO_DEFINE(REG_ADRENO_CP_RB_BASE_HI, REG_A5XX_CP_RB_BASE_HI), - REG_ADRENO_DEFINE(REG_ADRENO_CP_RB_RPTR_ADDR, REG_A5XX_CP_RB_RPTR_ADDR), - REG_ADRENO_DEFINE(REG_ADRENO_CP_RB_RPTR_ADDR_HI, - REG_A5XX_CP_RB_RPTR_ADDR_HI), - REG_ADRENO_DEFINE(REG_ADRENO_CP_RB_RPTR, REG_A5XX_CP_RB_RPTR), - REG_ADRENO_DEFINE(REG_ADRENO_CP_RB_WPTR, REG_A5XX_CP_RB_WPTR), - REG_ADRENO_DEFINE(REG_ADRENO_CP_RB_CNTL, REG_A5XX_CP_RB_CNTL), -}; - static const u32 a5xx_registers[] = { 0x0000, 0x0002, 0x0004, 0x0020, 0x0022, 0x0026, 0x0029, 0x002B, 0x002E, 0x0035, 0x0038, 0x0042, 0x0044, 0x0044, 0x0047, 0x0095, @@ -1432,6 +1485,17 @@ static unsigned long a5xx_gpu_busy(struct msm_gpu *gpu) return (unsigned long)busy_time; } +static uint32_t a5xx_get_rptr(struct msm_gpu *gpu, struct msm_ringbuffer *ring) +{ + struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu); + struct a5xx_gpu *a5xx_gpu = to_a5xx_gpu(adreno_gpu); + + if (a5xx_gpu->has_whereami) + return a5xx_gpu->shadow[ring->id]; + + return ring->memptrs->rptr = gpu_read(gpu, REG_A5XX_CP_RB_RPTR); +} + static const struct adreno_gpu_funcs funcs = { .base = { .get_param = adreno_get_param, @@ -1440,7 +1504,6 @@ static const struct adreno_gpu_funcs funcs = { .pm_resume = a5xx_pm_resume, .recover = a5xx_recover, .submit = a5xx_submit, - .flush = a5xx_flush, .active_ring = a5xx_active_ring, .irq = a5xx_irq, .destroy = a5xx_destroy, @@ -1454,6 +1517,7 @@ static const struct adreno_gpu_funcs funcs = { .gpu_state_get = a5xx_gpu_state_get, .gpu_state_put = a5xx_gpu_state_put, .create_address_space = adreno_iommu_create_address_space, + .get_rptr = a5xx_get_rptr, }, .get_timestamp = a5xx_get_timestamp, }; @@ -1512,14 +1576,12 @@ struct msm_gpu *a5xx_gpu_init(struct drm_device *dev) gpu = &adreno_gpu->base; adreno_gpu->registers = a5xx_registers; - adreno_gpu->reg_offsets = a5xx_register_offsets; a5xx_gpu->lm_leakage = 0x4E001A; check_speed_bin(&pdev->dev); - /* Restricting nr_rings to 1 to temporarily disable preemption */ - ret = adreno_gpu_init(dev, pdev, adreno_gpu, &funcs, 1); + ret = adreno_gpu_init(dev, pdev, adreno_gpu, &funcs, 4); if (ret) { a5xx_destroy(&(a5xx_gpu->base.base)); return ERR_PTR(ret); diff --git a/drivers/gpu/drm/msm/adreno/a5xx_gpu.h b/drivers/gpu/drm/msm/adreno/a5xx_gpu.h index 1e5b1a15a70f..c7187bcc5e90 100644 --- a/drivers/gpu/drm/msm/adreno/a5xx_gpu.h +++ b/drivers/gpu/drm/msm/adreno/a5xx_gpu.h @@ -37,6 +37,13 @@ struct a5xx_gpu { atomic_t preempt_state; struct timer_list preempt_timer; + + struct drm_gem_object *shadow_bo; + uint64_t shadow_iova; + uint32_t *shadow; + + /* True if the microcode supports the WHERE_AM_I opcode */ + bool has_whereami; }; #define to_a5xx_gpu(x) container_of(x, struct a5xx_gpu, base) @@ -141,6 +148,9 @@ static inline int spin_usecs(struct msm_gpu *gpu, uint32_t usecs, return -ETIMEDOUT; } +#define shadowptr(a5xx_gpu, ring) ((a5xx_gpu)->shadow_iova + \ + ((ring)->id * sizeof(uint32_t))) + bool a5xx_idle(struct msm_gpu *gpu, struct msm_ringbuffer *ring); void a5xx_set_hwcg(struct msm_gpu *gpu, bool state); @@ -150,6 +160,8 @@ void a5xx_preempt_trigger(struct msm_gpu *gpu); void a5xx_preempt_irq(struct msm_gpu *gpu); void a5xx_preempt_fini(struct msm_gpu *gpu); +void a5xx_flush(struct msm_gpu *gpu, struct msm_ringbuffer *ring, bool sync); + /* Return true if we are in a preempt state */ static inline bool a5xx_in_preempt(struct a5xx_gpu *a5xx_gpu) { diff --git a/drivers/gpu/drm/msm/adreno/a5xx_power.c b/drivers/gpu/drm/msm/adreno/a5xx_power.c index 321a8061fd32..f176a6f3eff6 100644 --- a/drivers/gpu/drm/msm/adreno/a5xx_power.c +++ b/drivers/gpu/drm/msm/adreno/a5xx_power.c @@ -240,7 +240,7 @@ static int a5xx_gpmu_init(struct msm_gpu *gpu) OUT_PKT7(ring, CP_SET_PROTECTED_MODE, 1); OUT_RING(ring, 1); - gpu->funcs->flush(gpu, ring); + a5xx_flush(gpu, ring, true); if (!a5xx_idle(gpu, ring)) { DRM_ERROR("%s: Unable to load GPMU firmware. GPMU will not be active\n", diff --git a/drivers/gpu/drm/msm/adreno/a5xx_preempt.c b/drivers/gpu/drm/msm/adreno/a5xx_preempt.c index 9f3fe177b00e..7e04509c4e1f 100644 --- a/drivers/gpu/drm/msm/adreno/a5xx_preempt.c +++ b/drivers/gpu/drm/msm/adreno/a5xx_preempt.c @@ -259,8 +259,9 @@ static int preempt_init_ring(struct a5xx_gpu *a5xx_gpu, ptr->magic = A5XX_PREEMPT_RECORD_MAGIC; ptr->info = 0; ptr->data = 0; - ptr->cntl = MSM_GPU_RB_CNTL_DEFAULT; - ptr->rptr_addr = rbmemptr(ring, rptr); + ptr->cntl = MSM_GPU_RB_CNTL_DEFAULT | AXXX_CP_RB_CNTL_NO_UPDATE; + + ptr->rptr_addr = shadowptr(a5xx_gpu, ring); ptr->counter = counters_iova; return 0; diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c index e1c7bcd1b1eb..491fee410daf 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c +++ b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c @@ -11,6 +11,7 @@ #include "a6xx_gpu.h" #include "a6xx_gmu.xml.h" #include "msm_gem.h" +#include "msm_gpu_trace.h" #include "msm_mmu.h" static void a6xx_gmu_fault(struct a6xx_gmu *gmu) @@ -124,6 +125,8 @@ void a6xx_gmu_set_freq(struct msm_gpu *gpu, struct dev_pm_opp *opp) gmu->current_perf_index = perf_index; gmu->freq = gmu->gpu_freqs[perf_index]; + trace_msm_gmu_freq_change(gmu->freq, perf_index); + /* * This can get called from devfreq while the hardware is idle. Don't * bring up the power if it isn't already active diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c index 66a95e22b7b3..948f3656c20c 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c +++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c @@ -51,9 +51,20 @@ bool a6xx_idle(struct msm_gpu *gpu, struct msm_ringbuffer *ring) static void a6xx_flush(struct msm_gpu *gpu, struct msm_ringbuffer *ring) { + struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu); + struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu); uint32_t wptr; unsigned long flags; + /* Expanded APRIV doesn't need to issue the WHERE_AM_I opcode */ + if (a6xx_gpu->has_whereami && !adreno_gpu->base.hw_apriv) { + struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu); + + OUT_PKT7(ring, CP_WHERE_AM_I, 2); + OUT_RING(ring, lower_32_bits(shadowptr(a6xx_gpu, ring))); + OUT_RING(ring, upper_32_bits(shadowptr(a6xx_gpu, ring))); + } + spin_lock_irqsave(&ring->lock, flags); /* Copy the shadow to the actual register */ @@ -81,8 +92,50 @@ static void get_stats_counter(struct msm_ringbuffer *ring, u32 counter, OUT_RING(ring, upper_32_bits(iova)); } -static void a6xx_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit, - struct msm_file_private *ctx) +static void a6xx_set_pagetable(struct a6xx_gpu *a6xx_gpu, + struct msm_ringbuffer *ring, struct msm_file_private *ctx) +{ + phys_addr_t ttbr; + u32 asid; + u64 memptr = rbmemptr(ring, ttbr0); + + if (ctx == a6xx_gpu->cur_ctx) + return; + + if (msm_iommu_pagetable_params(ctx->aspace->mmu, &ttbr, &asid)) + return; + + /* Execute the table update */ + OUT_PKT7(ring, CP_SMMU_TABLE_UPDATE, 4); + OUT_RING(ring, CP_SMMU_TABLE_UPDATE_0_TTBR0_LO(lower_32_bits(ttbr))); + + OUT_RING(ring, + CP_SMMU_TABLE_UPDATE_1_TTBR0_HI(upper_32_bits(ttbr)) | + CP_SMMU_TABLE_UPDATE_1_ASID(asid)); + OUT_RING(ring, CP_SMMU_TABLE_UPDATE_2_CONTEXTIDR(0)); + OUT_RING(ring, CP_SMMU_TABLE_UPDATE_3_CONTEXTBANK(0)); + + /* + * Write the new TTBR0 to the memstore. This is good for debugging. + */ + OUT_PKT7(ring, CP_MEM_WRITE, 4); + OUT_RING(ring, CP_MEM_WRITE_0_ADDR_LO(lower_32_bits(memptr))); + OUT_RING(ring, CP_MEM_WRITE_1_ADDR_HI(upper_32_bits(memptr))); + OUT_RING(ring, lower_32_bits(ttbr)); + OUT_RING(ring, (asid << 16) | upper_32_bits(ttbr)); + + /* + * And finally, trigger a uche flush to be sure there isn't anything + * lingering in that part of the GPU + */ + + OUT_PKT7(ring, CP_EVENT_WRITE, 1); + OUT_RING(ring, 0x31); + + a6xx_gpu->cur_ctx = ctx; +} + +static void a6xx_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit) { unsigned int index = submit->seqno % MSM_GPU_SUBMIT_STATS_COUNT; struct msm_drm_private *priv = gpu->dev->dev_private; @@ -91,6 +144,8 @@ static void a6xx_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit, struct msm_ringbuffer *ring = submit->ring; unsigned int i; + a6xx_set_pagetable(a6xx_gpu, ring, submit->queue->ctx); + get_stats_counter(ring, REG_A6XX_RBBM_PERFCTR_CP_0_LO, rbmemptr_stats(ring, index, cpcycles_start)); @@ -115,7 +170,7 @@ static void a6xx_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit, case MSM_SUBMIT_CMD_IB_TARGET_BUF: break; case MSM_SUBMIT_CMD_CTX_RESTORE_BUF: - if (priv->lastctx == ctx) + if (priv->lastctx == submit->queue->ctx) break; fallthrough; case MSM_SUBMIT_CMD_BUF: @@ -464,6 +519,30 @@ static int a6xx_cp_init(struct msm_gpu *gpu) return a6xx_idle(gpu, ring) ? 0 : -EINVAL; } +static void a6xx_ucode_check_version(struct a6xx_gpu *a6xx_gpu, + struct drm_gem_object *obj) +{ + u32 *buf = msm_gem_get_vaddr_active(obj); + + if (IS_ERR(buf)) + return; + + /* + * If the lowest nibble is 0xa that is an indication that this microcode + * has been patched. The actual version is in dword [3] but we only care + * about the patchlevel which is the lowest nibble of dword [3] + * + * Otherwise check that the firmware is greater than or equal to 1.90 + * which was the first version that had this fix built in + */ + if (((buf[0] & 0xf) == 0xa) && (buf[2] & 0xf) >= 1) + a6xx_gpu->has_whereami = true; + else if ((buf[0] & 0xfff) > 0x190) + a6xx_gpu->has_whereami = true; + + msm_gem_put_vaddr(obj); +} + static int a6xx_ucode_init(struct msm_gpu *gpu) { struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu); @@ -484,6 +563,7 @@ static int a6xx_ucode_init(struct msm_gpu *gpu) } msm_gem_object_set_name(a6xx_gpu->sqe_bo, "sqefw"); + a6xx_ucode_check_version(a6xx_gpu, a6xx_gpu->sqe_bo); } gpu_write64(gpu, REG_A6XX_CP_SQE_INSTR_BASE_LO, @@ -699,12 +779,43 @@ static int a6xx_hw_init(struct msm_gpu *gpu) gpu_write64(gpu, REG_A6XX_CP_RB_BASE, REG_A6XX_CP_RB_BASE_HI, gpu->rb[0]->iova); - gpu_write(gpu, REG_A6XX_CP_RB_CNTL, - MSM_GPU_RB_CNTL_DEFAULT | AXXX_CP_RB_CNTL_NO_UPDATE); + /* Targets that support extended APRIV can use the RPTR shadow from + * hardware but all the other ones need to disable the feature. Targets + * that support the WHERE_AM_I opcode can use that instead + */ + if (adreno_gpu->base.hw_apriv) + gpu_write(gpu, REG_A6XX_CP_RB_CNTL, MSM_GPU_RB_CNTL_DEFAULT); + else + gpu_write(gpu, REG_A6XX_CP_RB_CNTL, + MSM_GPU_RB_CNTL_DEFAULT | AXXX_CP_RB_CNTL_NO_UPDATE); + + /* + * Expanded APRIV and targets that support WHERE_AM_I both need a + * privileged buffer to store the RPTR shadow + */ + + if (adreno_gpu->base.hw_apriv || a6xx_gpu->has_whereami) { + if (!a6xx_gpu->shadow_bo) { + a6xx_gpu->shadow = msm_gem_kernel_new_locked(gpu->dev, + sizeof(u32) * gpu->nr_rings, + MSM_BO_UNCACHED | MSM_BO_MAP_PRIV, + gpu->aspace, &a6xx_gpu->shadow_bo, + &a6xx_gpu->shadow_iova); + + if (IS_ERR(a6xx_gpu->shadow)) + return PTR_ERR(a6xx_gpu->shadow); + } + + gpu_write64(gpu, REG_A6XX_CP_RB_RPTR_ADDR_LO, + REG_A6XX_CP_RB_RPTR_ADDR_HI, + shadowptr(a6xx_gpu, gpu->rb[0])); + } /* Always come up on rb 0 */ a6xx_gpu->cur_ring = gpu->rb[0]; + a6xx_gpu->cur_ctx = NULL; + /* Enable the SQE_to start the CP engine */ gpu_write(gpu, REG_A6XX_CP_SQE_CNTL, 1); @@ -911,18 +1022,6 @@ static irqreturn_t a6xx_irq(struct msm_gpu *gpu) return IRQ_HANDLED; } -static const u32 a6xx_register_offsets[REG_ADRENO_REGISTER_MAX] = { - REG_ADRENO_DEFINE(REG_ADRENO_CP_RB_BASE, REG_A6XX_CP_RB_BASE), - REG_ADRENO_DEFINE(REG_ADRENO_CP_RB_BASE_HI, REG_A6XX_CP_RB_BASE_HI), - REG_ADRENO_DEFINE(REG_ADRENO_CP_RB_RPTR_ADDR, - REG_A6XX_CP_RB_RPTR_ADDR_LO), - REG_ADRENO_DEFINE(REG_ADRENO_CP_RB_RPTR_ADDR_HI, - REG_A6XX_CP_RB_RPTR_ADDR_HI), - REG_ADRENO_DEFINE(REG_ADRENO_CP_RB_RPTR, REG_A6XX_CP_RB_RPTR), - REG_ADRENO_DEFINE(REG_ADRENO_CP_RB_WPTR, REG_A6XX_CP_RB_WPTR), - REG_ADRENO_DEFINE(REG_ADRENO_CP_RB_CNTL, REG_A6XX_CP_RB_CNTL), -}; - static int a6xx_pm_resume(struct msm_gpu *gpu) { struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu); @@ -931,6 +1030,8 @@ static int a6xx_pm_resume(struct msm_gpu *gpu) gpu->needs_hw_init = true; + trace_msm_gpu_resume(0); + ret = a6xx_gmu_resume(a6xx_gpu); if (ret) return ret; @@ -945,6 +1046,8 @@ static int a6xx_pm_suspend(struct msm_gpu *gpu) struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu); struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu); + trace_msm_gpu_suspend(0); + devfreq_suspend_device(gpu->devfreq.devfreq); return a6xx_gmu_stop(a6xx_gpu); @@ -983,6 +1086,11 @@ static void a6xx_destroy(struct msm_gpu *gpu) drm_gem_object_put(a6xx_gpu->sqe_bo); } + if (a6xx_gpu->shadow_bo) { + msm_gem_unpin_iova(a6xx_gpu->shadow_bo, gpu->aspace); + drm_gem_object_put(a6xx_gpu->shadow_bo); + } + a6xx_gmu_remove(a6xx_gpu); adreno_gpu_cleanup(adreno_gpu); @@ -1017,6 +1125,31 @@ static unsigned long a6xx_gpu_busy(struct msm_gpu *gpu) return (unsigned long)busy_time; } +static struct msm_gem_address_space * +a6xx_create_private_address_space(struct msm_gpu *gpu) +{ + struct msm_mmu *mmu; + + mmu = msm_iommu_pagetable_create(gpu->aspace->mmu); + + if (IS_ERR(mmu)) + return ERR_CAST(mmu); + + return msm_gem_address_space_create(mmu, + "gpu", 0x100000000ULL, 0x1ffffffffULL); +} + +static uint32_t a6xx_get_rptr(struct msm_gpu *gpu, struct msm_ringbuffer *ring) +{ + struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu); + struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu); + + if (adreno_gpu->base.hw_apriv || a6xx_gpu->has_whereami) + return a6xx_gpu->shadow[ring->id]; + + return ring->memptrs->rptr = gpu_read(gpu, REG_A6XX_CP_RB_RPTR); +} + static const struct adreno_gpu_funcs funcs = { .base = { .get_param = adreno_get_param, @@ -1025,7 +1158,6 @@ static const struct adreno_gpu_funcs funcs = { .pm_resume = a6xx_pm_resume, .recover = a6xx_recover, .submit = a6xx_submit, - .flush = a6xx_flush, .active_ring = a6xx_active_ring, .irq = a6xx_irq, .destroy = a6xx_destroy, @@ -1040,6 +1172,8 @@ static const struct adreno_gpu_funcs funcs = { .gpu_state_put = a6xx_gpu_state_put, #endif .create_address_space = adreno_iommu_create_address_space, + .create_private_address_space = a6xx_create_private_address_space, + .get_rptr = a6xx_get_rptr, }, .get_timestamp = a6xx_get_timestamp, }; @@ -1048,6 +1182,8 @@ struct msm_gpu *a6xx_gpu_init(struct drm_device *dev) { struct msm_drm_private *priv = dev->dev_private; struct platform_device *pdev = priv->gpu_pdev; + struct adreno_platform_config *config = pdev->dev.platform_data; + const struct adreno_info *info; struct device_node *node; struct a6xx_gpu *a6xx_gpu; struct adreno_gpu *adreno_gpu; @@ -1062,9 +1198,15 @@ struct msm_gpu *a6xx_gpu_init(struct drm_device *dev) gpu = &adreno_gpu->base; adreno_gpu->registers = NULL; - adreno_gpu->reg_offsets = a6xx_register_offsets; - if (adreno_is_a650(adreno_gpu)) + /* + * We need to know the platform type before calling into adreno_gpu_init + * so that the hw_apriv flag can be correctly set. Snoop into the info + * and grab the revision number + */ + info = adreno_info(config->rev); + + if (info && info->revn == 650) adreno_gpu->base.hw_apriv = true; ret = adreno_gpu_init(dev, pdev, adreno_gpu, &funcs, 1); diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.h b/drivers/gpu/drm/msm/adreno/a6xx_gpu.h index 03ba60d5b07f..3eeebf6a754b 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.h +++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.h @@ -19,8 +19,15 @@ struct a6xx_gpu { uint64_t sqe_iova; struct msm_ringbuffer *cur_ring; + struct msm_file_private *cur_ctx; struct a6xx_gmu gmu; + + struct drm_gem_object *shadow_bo; + uint64_t shadow_iova; + uint32_t *shadow; + + bool has_whereami; }; #define to_a6xx_gpu(x) container_of(x, struct a6xx_gpu, base) @@ -50,6 +57,9 @@ static inline bool a6xx_has_gbif(struct adreno_gpu *gpu) return true; } +#define shadowptr(_a6xx_gpu, _ring) ((_a6xx_gpu)->shadow_iova + \ + ((_ring)->id * sizeof(uint32_t))) + int a6xx_gmu_resume(struct a6xx_gpu *gpu); int a6xx_gmu_stop(struct a6xx_gpu *gpu); diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c index b12f5b4a1bea..e9ede19193b0 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c +++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c @@ -875,7 +875,7 @@ static void a6xx_get_indexed_registers(struct msm_gpu *gpu, int i; a6xx_state->indexed_regs = state_kcalloc(a6xx_state, count, - sizeof(a6xx_state->indexed_regs)); + sizeof(*a6xx_state->indexed_regs)); if (!a6xx_state->indexed_regs) return; diff --git a/drivers/gpu/drm/msm/adreno/adreno_device.c b/drivers/gpu/drm/msm/adreno/adreno_device.c index 9eeb46bf2a5d..58e03b20e1c7 100644 --- a/drivers/gpu/drm/msm/adreno/adreno_device.c +++ b/drivers/gpu/drm/msm/adreno/adreno_device.c @@ -282,7 +282,7 @@ struct msm_gpu *adreno_load_gpu(struct drm_device *dev) int ret; if (pdev) - gpu = platform_get_drvdata(pdev); + gpu = dev_to_gpu(&pdev->dev); if (!gpu) { dev_err_once(dev->dev, "no GPU device was found\n"); @@ -417,15 +417,13 @@ static int adreno_bind(struct device *dev, struct device *master, void *data) return PTR_ERR(gpu); } - dev_set_drvdata(dev, gpu); - return 0; } static void adreno_unbind(struct device *dev, struct device *master, void *data) { - struct msm_gpu *gpu = dev_get_drvdata(dev); + struct msm_gpu *gpu = dev_to_gpu(dev); pm_runtime_force_suspend(dev); gpu->funcs->destroy(gpu); @@ -490,16 +488,14 @@ static const struct of_device_id dt_match[] = { #ifdef CONFIG_PM static int adreno_resume(struct device *dev) { - struct platform_device *pdev = to_platform_device(dev); - struct msm_gpu *gpu = platform_get_drvdata(pdev); + struct msm_gpu *gpu = dev_to_gpu(dev); return gpu->funcs->pm_resume(gpu); } static int adreno_suspend(struct device *dev) { - struct platform_device *pdev = to_platform_device(dev); - struct msm_gpu *gpu = platform_get_drvdata(pdev); + struct msm_gpu *gpu = dev_to_gpu(dev); return gpu->funcs->pm_suspend(gpu); } diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.c b/drivers/gpu/drm/msm/adreno/adreno_gpu.c index 862dd35b27d3..458b5b26d3c2 100644 --- a/drivers/gpu/drm/msm/adreno/adreno_gpu.c +++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.c @@ -189,12 +189,27 @@ struct msm_gem_address_space * adreno_iommu_create_address_space(struct msm_gpu *gpu, struct platform_device *pdev) { - struct iommu_domain *iommu = iommu_domain_alloc(&platform_bus_type); - struct msm_mmu *mmu = msm_iommu_new(&pdev->dev, iommu); + struct iommu_domain *iommu; + struct msm_mmu *mmu; struct msm_gem_address_space *aspace; + u64 start, size; - aspace = msm_gem_address_space_create(mmu, "gpu", SZ_16M, - 0xffffffff - SZ_16M); + iommu = iommu_domain_alloc(&platform_bus_type); + if (!iommu) + return NULL; + + mmu = msm_iommu_new(&pdev->dev, iommu); + + /* + * Use the aperture start or SZ_16M, whichever is greater. This will + * ensure that we align with the allocated pagetable range while still + * allowing room in the lower 32 bits for GMEM and whatnot + */ + start = max_t(u64, SZ_16M, iommu->geometry.aperture_start); + size = iommu->geometry.aperture_end - start + 1; + + aspace = msm_gem_address_space_create(mmu, "gpu", + start & GENMASK_ULL(48, 0), size); if (IS_ERR(aspace) && !IS_ERR(mmu)) mmu->funcs->destroy(mmu); @@ -407,8 +422,9 @@ int adreno_hw_init(struct msm_gpu *gpu) static uint32_t get_rptr(struct adreno_gpu *adreno_gpu, struct msm_ringbuffer *ring) { - return ring->memptrs->rptr = adreno_gpu_read( - adreno_gpu, REG_ADRENO_CP_RB_RPTR); + struct msm_gpu *gpu = &adreno_gpu->base; + + return gpu->funcs->get_rptr(gpu, ring); } struct msm_ringbuffer *adreno_active_ring(struct msm_gpu *gpu) @@ -434,81 +450,8 @@ void adreno_recover(struct msm_gpu *gpu) } } -void adreno_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit, - struct msm_file_private *ctx) -{ - struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu); - struct msm_drm_private *priv = gpu->dev->dev_private; - struct msm_ringbuffer *ring = submit->ring; - unsigned i; - - for (i = 0; i < submit->nr_cmds; i++) { - switch (submit->cmd[i].type) { - case MSM_SUBMIT_CMD_IB_TARGET_BUF: - /* ignore IB-targets */ - break; - case MSM_SUBMIT_CMD_CTX_RESTORE_BUF: - /* ignore if there has not been a ctx switch: */ - if (priv->lastctx == ctx) - break; - fallthrough; - case MSM_SUBMIT_CMD_BUF: - OUT_PKT3(ring, adreno_is_a4xx(adreno_gpu) ? - CP_INDIRECT_BUFFER_PFE : CP_INDIRECT_BUFFER_PFD, 2); - OUT_RING(ring, lower_32_bits(submit->cmd[i].iova)); - OUT_RING(ring, submit->cmd[i].size); - OUT_PKT2(ring); - break; - } - } - - OUT_PKT0(ring, REG_AXXX_CP_SCRATCH_REG2, 1); - OUT_RING(ring, submit->seqno); - - if (adreno_is_a3xx(adreno_gpu) || adreno_is_a4xx(adreno_gpu)) { - /* Flush HLSQ lazy updates to make sure there is nothing - * pending for indirect loads after the timestamp has - * passed: - */ - OUT_PKT3(ring, CP_EVENT_WRITE, 1); - OUT_RING(ring, HLSQ_FLUSH); - } - - /* wait for idle before cache flush/interrupt */ - OUT_PKT3(ring, CP_WAIT_FOR_IDLE, 1); - OUT_RING(ring, 0x00000000); - - if (!adreno_is_a2xx(adreno_gpu)) { - /* BIT(31) of CACHE_FLUSH_TS triggers CACHE_FLUSH_TS IRQ from GPU */ - OUT_PKT3(ring, CP_EVENT_WRITE, 3); - OUT_RING(ring, CACHE_FLUSH_TS | BIT(31)); - OUT_RING(ring, rbmemptr(ring, fence)); - OUT_RING(ring, submit->seqno); - } else { - /* BIT(31) means something else on a2xx */ - OUT_PKT3(ring, CP_EVENT_WRITE, 3); - OUT_RING(ring, CACHE_FLUSH_TS); - OUT_RING(ring, rbmemptr(ring, fence)); - OUT_RING(ring, submit->seqno); - OUT_PKT3(ring, CP_INTERRUPT, 1); - OUT_RING(ring, 0x80000000); - } - -#if 0 - if (adreno_is_a3xx(adreno_gpu)) { - /* Dummy set-constant to trigger context rollover */ - OUT_PKT3(ring, CP_SET_CONSTANT, 2); - OUT_RING(ring, CP_REG(REG_A3XX_HLSQ_CL_KERNEL_GROUP_X_REG)); - OUT_RING(ring, 0x00000000); - } -#endif - - gpu->funcs->flush(gpu, ring); -} - -void adreno_flush(struct msm_gpu *gpu, struct msm_ringbuffer *ring) +void adreno_flush(struct msm_gpu *gpu, struct msm_ringbuffer *ring, u32 reg) { - struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu); uint32_t wptr; /* Copy the shadow to the actual register */ @@ -524,7 +467,7 @@ void adreno_flush(struct msm_gpu *gpu, struct msm_ringbuffer *ring) /* ensure writes to ringbuffer have hit system memory: */ mb(); - adreno_gpu_write(adreno_gpu, REG_ADRENO_CP_RB_WPTR, wptr); + gpu_write(gpu, reg, wptr); } bool adreno_idle(struct msm_gpu *gpu, struct msm_ringbuffer *ring) diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.h b/drivers/gpu/drm/msm/adreno/adreno_gpu.h index e55abae365b5..c3775f79525a 100644 --- a/drivers/gpu/drm/msm/adreno/adreno_gpu.h +++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.h @@ -17,29 +17,8 @@ #include "adreno_common.xml.h" #include "adreno_pm4.xml.h" -#define REG_ADRENO_DEFINE(_offset, _reg) [_offset] = (_reg) + 1 -#define REG_SKIP ~0 -#define REG_ADRENO_SKIP(_offset) [_offset] = REG_SKIP - extern bool snapshot_debugbus; -/** - * adreno_regs: List of registers that are used in across all - * 3D devices. Each device type has different offset value for the same - * register, so an array of register offsets are declared for every device - * and are indexed by the enumeration values defined in this enum - */ -enum adreno_regs { - REG_ADRENO_CP_RB_BASE, - REG_ADRENO_CP_RB_BASE_HI, - REG_ADRENO_CP_RB_RPTR_ADDR, - REG_ADRENO_CP_RB_RPTR_ADDR_HI, - REG_ADRENO_CP_RB_RPTR, - REG_ADRENO_CP_RB_WPTR, - REG_ADRENO_CP_RB_CNTL, - REG_ADRENO_REGISTER_MAX, -}; - enum { ADRENO_FW_PM4 = 0, ADRENO_FW_SQE = 0, /* a6xx */ @@ -176,11 +155,6 @@ static inline bool adreno_is_a225(struct adreno_gpu *gpu) return gpu->revn == 225; } -static inline bool adreno_is_a3xx(struct adreno_gpu *gpu) -{ - return (gpu->revn >= 300) && (gpu->revn < 400); -} - static inline bool adreno_is_a305(struct adreno_gpu *gpu) { return gpu->revn == 305; @@ -207,11 +181,6 @@ static inline bool adreno_is_a330v2(struct adreno_gpu *gpu) return adreno_is_a330(gpu) && (gpu->rev.patchid > 0); } -static inline bool adreno_is_a4xx(struct adreno_gpu *gpu) -{ - return (gpu->revn >= 400) && (gpu->revn < 500); -} - static inline int adreno_is_a405(struct adreno_gpu *gpu) { return gpu->revn == 405; @@ -269,9 +238,7 @@ struct drm_gem_object *adreno_fw_create_bo(struct msm_gpu *gpu, const struct firmware *fw, u64 *iova); int adreno_hw_init(struct msm_gpu *gpu); void adreno_recover(struct msm_gpu *gpu); -void adreno_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit, - struct msm_file_private *ctx); -void adreno_flush(struct msm_gpu *gpu, struct msm_ringbuffer *ring); +void adreno_flush(struct msm_gpu *gpu, struct msm_ringbuffer *ring, u32 reg); bool adreno_idle(struct msm_gpu *gpu, struct msm_ringbuffer *ring); #if defined(CONFIG_DEBUG_FS) || defined(CONFIG_DEV_COREDUMP) void adreno_show(struct msm_gpu *gpu, struct msm_gpu_state *state, @@ -365,59 +332,12 @@ OUT_PKT7(struct msm_ringbuffer *ring, uint8_t opcode, uint16_t cnt) ((opcode & 0x7F) << 16) | (PM4_PARITY(opcode) << 23)); } -/* - * adreno_reg_check() - Checks the validity of a register enum - * @gpu: Pointer to struct adreno_gpu - * @offset_name: The register enum that is checked - */ -static inline bool adreno_reg_check(struct adreno_gpu *gpu, - enum adreno_regs offset_name) -{ - BUG_ON(offset_name >= REG_ADRENO_REGISTER_MAX || !gpu->reg_offsets[offset_name]); - - /* - * REG_SKIP is a special value that tell us that the register in - * question isn't implemented on target but don't trigger a BUG(). This - * is used to cleanly implement adreno_gpu_write64() and - * adreno_gpu_read64() in a generic fashion - */ - if (gpu->reg_offsets[offset_name] == REG_SKIP) - return false; - - return true; -} - -static inline u32 adreno_gpu_read(struct adreno_gpu *gpu, - enum adreno_regs offset_name) -{ - u32 reg = gpu->reg_offsets[offset_name]; - u32 val = 0; - if(adreno_reg_check(gpu,offset_name)) - val = gpu_read(&gpu->base, reg - 1); - return val; -} - -static inline void adreno_gpu_write(struct adreno_gpu *gpu, - enum adreno_regs offset_name, u32 data) -{ - u32 reg = gpu->reg_offsets[offset_name]; - if(adreno_reg_check(gpu, offset_name)) - gpu_write(&gpu->base, reg - 1, data); -} - struct msm_gpu *a2xx_gpu_init(struct drm_device *dev); struct msm_gpu *a3xx_gpu_init(struct drm_device *dev); struct msm_gpu *a4xx_gpu_init(struct drm_device *dev); struct msm_gpu *a5xx_gpu_init(struct drm_device *dev); struct msm_gpu *a6xx_gpu_init(struct drm_device *dev); -static inline void adreno_gpu_write64(struct adreno_gpu *gpu, - enum adreno_regs lo, enum adreno_regs hi, u64 data) -{ - adreno_gpu_write(gpu, lo, lower_32_bits(data)); - adreno_gpu_write(gpu, hi, upper_32_bits(data)); -} - static inline uint32_t get_wptr(struct msm_ringbuffer *ring) { return (ring->cur - ring->start) % (MSM_GPU_RINGBUFFER_SZ >> 2); diff --git a/drivers/gpu/drm/msm/adreno/adreno_pm4.xml.h b/drivers/gpu/drm/msm/adreno/adreno_pm4.xml.h index 3931eecadaff..59bb8c1ffce6 100644 --- a/drivers/gpu/drm/msm/adreno/adreno_pm4.xml.h +++ b/drivers/gpu/drm/msm/adreno/adreno_pm4.xml.h @@ -298,6 +298,7 @@ enum adreno_pm4_type3_packets { CP_SET_BIN_DATA5_OFFSET = 46, CP_SET_CTXSWITCH_IB = 85, CP_REG_WRITE = 109, + CP_WHERE_AM_I = 98, }; enum adreno_state_block { diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_core_irq.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_core_irq.c index f1bc6a1af7a7..84ea09d9692f 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_core_irq.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_core_irq.c @@ -288,19 +288,6 @@ static void dpu_disable_all_irqs(struct dpu_kms *dpu_kms) } #ifdef CONFIG_DEBUG_FS -#define DEFINE_DPU_DEBUGFS_SEQ_FOPS(__prefix) \ -static int __prefix ## _open(struct inode *inode, struct file *file) \ -{ \ - return single_open(file, __prefix ## _show, inode->i_private); \ -} \ -static const struct file_operations __prefix ## _fops = { \ - .owner = THIS_MODULE, \ - .open = __prefix ## _open, \ - .release = single_release, \ - .read = seq_read, \ - .llseek = seq_lseek, \ -} - static int dpu_debugfs_core_irq_show(struct seq_file *s, void *v) { struct dpu_irq *irq_obj = s->private; @@ -328,7 +315,7 @@ static int dpu_debugfs_core_irq_show(struct seq_file *s, void *v) return 0; } -DEFINE_DPU_DEBUGFS_SEQ_FOPS(dpu_debugfs_core_irq); +DEFINE_SHOW_ATTRIBUTE(dpu_debugfs_core_irq); void dpu_debugfs_core_irq_init(struct dpu_kms *dpu_kms, struct dentry *parent) diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c index b36919d95362..393858ef8a83 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c @@ -30,6 +30,74 @@ enum dpu_perf_mode { DPU_PERF_MODE_MAX }; +/** + * @_dpu_core_perf_calc_bw() - to calculate BW per crtc + * @kms - pointer to the dpu_kms + * @crtc - pointer to a crtc + * Return: returns aggregated BW for all planes in crtc. + */ +static u64 _dpu_core_perf_calc_bw(struct dpu_kms *kms, + struct drm_crtc *crtc) +{ + struct drm_plane *plane; + struct dpu_plane_state *pstate; + u64 crtc_plane_bw = 0; + u32 bw_factor; + + drm_atomic_crtc_for_each_plane(plane, crtc) { + pstate = to_dpu_plane_state(plane->state); + if (!pstate) + continue; + + crtc_plane_bw += pstate->plane_fetch_bw; + } + + bw_factor = kms->catalog->perf.bw_inefficiency_factor; + if (bw_factor) { + crtc_plane_bw *= bw_factor; + do_div(crtc_plane_bw, 100); + } + + return crtc_plane_bw; +} + +/** + * _dpu_core_perf_calc_clk() - to calculate clock per crtc + * @kms - pointer to the dpu_kms + * @crtc - pointer to a crtc + * @state - pointer to a crtc state + * Return: returns max clk for all planes in crtc. + */ +static u64 _dpu_core_perf_calc_clk(struct dpu_kms *kms, + struct drm_crtc *crtc, struct drm_crtc_state *state) +{ + struct drm_plane *plane; + struct dpu_plane_state *pstate; + struct drm_display_mode *mode; + u64 crtc_clk; + u32 clk_factor; + + mode = &state->adjusted_mode; + + crtc_clk = mode->vtotal * mode->hdisplay * drm_mode_vrefresh(mode); + + drm_atomic_crtc_for_each_plane(plane, crtc) { + pstate = to_dpu_plane_state(plane->state); + if (!pstate) + continue; + + crtc_clk = max(pstate->plane_clk, crtc_clk); + } + + clk_factor = kms->catalog->perf.clk_inefficiency_factor; + if (clk_factor) { + crtc_clk *= clk_factor; + do_div(crtc_clk, 100); + } + + return crtc_clk; +} + static struct dpu_kms *_dpu_crtc_get_kms(struct drm_crtc *crtc) { struct msm_drm_private *priv; @@ -52,12 +120,7 @@ static void _dpu_core_perf_calc_crtc(struct dpu_kms *kms, dpu_cstate = to_dpu_crtc_state(state); memset(perf, 0, sizeof(struct dpu_core_perf_params)); - if (!dpu_cstate->bw_control) { - perf->bw_ctl = kms->catalog->perf.max_bw_high * - 1000ULL; - perf->max_per_pipe_ib = perf->bw_ctl; - perf->core_clk_rate = kms->perf.max_core_clk_rate; - } else if (kms->perf.perf_tune.mode == DPU_PERF_MODE_MINIMUM) { + if (kms->perf.perf_tune.mode == DPU_PERF_MODE_MINIMUM) { perf->bw_ctl = 0; perf->max_per_pipe_ib = 0; perf->core_clk_rate = 0; @@ -65,6 +128,10 @@ static void _dpu_core_perf_calc_crtc(struct dpu_kms *kms, perf->bw_ctl = kms->perf.fix_core_ab_vote; perf->max_per_pipe_ib = kms->perf.fix_core_ib_vote; perf->core_clk_rate = kms->perf.fix_core_clk_rate; + } else { + perf->bw_ctl = _dpu_core_perf_calc_bw(kms, crtc); + perf->max_per_pipe_ib = kms->catalog->perf.min_dram_ib; + perf->core_clk_rate = _dpu_core_perf_calc_clk(kms, crtc, state); } DPU_DEBUG( @@ -116,11 +183,7 @@ int dpu_core_perf_crtc_check(struct drm_crtc *crtc, DPU_DEBUG("crtc:%d bw:%llu ctrl:%d\n", tmp_crtc->base.id, tmp_cstate->new_perf.bw_ctl, tmp_cstate->bw_control); - /* - * For bw check only use the bw if the - * atomic property has been already set - */ - if (tmp_cstate->bw_control) + bw_sum_of_intfs += tmp_cstate->new_perf.bw_ctl; } @@ -132,9 +195,7 @@ int dpu_core_perf_crtc_check(struct drm_crtc *crtc, DPU_DEBUG("final threshold bw limit = %d\n", threshold); - if (!dpu_cstate->bw_control) { - DPU_DEBUG("bypass bandwidth check\n"); - } else if (!threshold) { + if (!threshold) { DPU_ERROR("no bandwidth limits specified\n"); return -E2BIG; } else if (bw > threshold) { @@ -155,7 +216,11 @@ static int _dpu_core_perf_crtc_update_bus(struct dpu_kms *kms, = dpu_crtc_get_client_type(crtc); struct drm_crtc *tmp_crtc; struct dpu_crtc_state *dpu_cstate; - int ret = 0; + int i, ret = 0; + u64 avg_bw; + + if (!kms->num_paths) + return -EINVAL; drm_for_each_crtc(tmp_crtc, crtc->dev) { if (tmp_crtc->enabled && @@ -166,10 +231,20 @@ static int _dpu_core_perf_crtc_update_bus(struct dpu_kms *kms, perf.max_per_pipe_ib = max(perf.max_per_pipe_ib, dpu_cstate->new_perf.max_per_pipe_ib); - DPU_DEBUG("crtc=%d bw=%llu\n", tmp_crtc->base.id, - dpu_cstate->new_perf.bw_ctl); + perf.bw_ctl += dpu_cstate->new_perf.bw_ctl; + + DPU_DEBUG("crtc=%d bw=%llu paths:%d\n", + tmp_crtc->base.id, + dpu_cstate->new_perf.bw_ctl, kms->num_paths); } } + + avg_bw = perf.bw_ctl; + do_div(avg_bw, (kms->num_paths * 1000)); /*Bps_to_icc*/ + + for (i = 0; i < kms->num_paths; i++) + icc_set_bw(kms->path[i], avg_bw, perf.max_per_pipe_ib); + return ret; } diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c index 5ba9b49dfa7a..6a24ce245a37 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c @@ -266,11 +266,6 @@ enum dpu_intf_mode dpu_crtc_get_intf_mode(struct drm_crtc *crtc) { struct drm_encoder *encoder; - if (!crtc) { - DPU_ERROR("invalid crtc\n"); - return INTF_MODE_NONE; - } - /* * TODO: This function is called from dpu debugfs and as part of atomic * check. When called from debugfs, the crtc->mutex must be held to @@ -298,7 +293,6 @@ void dpu_crtc_vblank_callback(struct drm_crtc *crtc) dpu_crtc->vblank_cb_time = ktime_get(); else dpu_crtc->vblank_cb_count++; - _dpu_crtc_complete_flip(crtc); drm_crtc_handle_vblank(crtc); trace_dpu_crtc_vblank_cb(DRMID(crtc)); } @@ -403,6 +397,7 @@ static void dpu_crtc_frame_event_cb(void *data, u32 event) void dpu_crtc_complete_commit(struct drm_crtc *crtc) { trace_dpu_crtc_complete_commit(DRMID(crtc)); + _dpu_crtc_complete_flip(crtc); } static void _dpu_crtc_setup_lm_bounds(struct drm_crtc *crtc, @@ -422,8 +417,6 @@ static void _dpu_crtc_setup_lm_bounds(struct drm_crtc *crtc, trace_dpu_crtc_setup_lm_bounds(DRMID(crtc), i, r); } - - drm_mode_debug_printmodeline(adj_mode); } static void _dpu_crtc_get_pcc_coeff(struct drm_crtc_state *state, @@ -458,7 +451,6 @@ static void _dpu_crtc_setup_cp_blocks(struct drm_crtc *crtc) struct dpu_crtc_mixer *mixer = cstate->mixers; struct dpu_hw_pcc_cfg cfg; struct dpu_hw_ctl *ctl; - struct dpu_hw_mixer *lm; struct dpu_hw_dspp *dspp; int i; @@ -468,7 +460,6 @@ static void _dpu_crtc_setup_cp_blocks(struct drm_crtc *crtc) for (i = 0; i < cstate->num_mixers; i++) { ctl = mixer[i].lm_ctl; - lm = mixer[i].hw_lm; dspp = mixer[i].hw_dspp; if (!dspp || !dspp->ops.setup_pcc) @@ -497,16 +488,8 @@ static void _dpu_crtc_setup_cp_blocks(struct drm_crtc *crtc) static void dpu_crtc_atomic_begin(struct drm_crtc *crtc, struct drm_crtc_state *old_state) { - struct dpu_crtc *dpu_crtc; - struct dpu_crtc_state *cstate; + struct dpu_crtc_state *cstate = to_dpu_crtc_state(crtc->state); struct drm_encoder *encoder; - struct drm_device *dev; - unsigned long flags; - - if (!crtc) { - DPU_ERROR("invalid crtc\n"); - return; - } if (!crtc->state->enable) { DPU_DEBUG("crtc%d -> enable %d, skip atomic_begin\n", @@ -516,21 +499,8 @@ static void dpu_crtc_atomic_begin(struct drm_crtc *crtc, DPU_DEBUG("crtc%d\n", crtc->base.id); - dpu_crtc = to_dpu_crtc(crtc); - cstate = to_dpu_crtc_state(crtc->state); - dev = crtc->dev; - _dpu_crtc_setup_lm_bounds(crtc, crtc->state); - if (dpu_crtc->event) { - WARN_ON(dpu_crtc->event); - } else { - spin_lock_irqsave(&dev->event_lock, flags); - dpu_crtc->event = crtc->state->event; - crtc->state->event = NULL; - spin_unlock_irqrestore(&dev->event_lock, flags); - } - /* encoder will trigger pending mask now */ drm_for_each_encoder_mask(encoder, crtc->dev, crtc->state->encoder_mask) dpu_encoder_trigger_kickoff_pending(encoder); @@ -584,14 +554,11 @@ static void dpu_crtc_atomic_flush(struct drm_crtc *crtc, return; } - if (dpu_crtc->event) { - DPU_DEBUG("already received dpu_crtc->event\n"); - } else { - spin_lock_irqsave(&dev->event_lock, flags); - dpu_crtc->event = crtc->state->event; - crtc->state->event = NULL; - spin_unlock_irqrestore(&dev->event_lock, flags); - } + WARN_ON(dpu_crtc->event); + spin_lock_irqsave(&dev->event_lock, flags); + dpu_crtc->event = crtc->state->event; + crtc->state->event = NULL; + spin_unlock_irqrestore(&dev->event_lock, flags); /* * If no mixers has been allocated in dpu_crtc_atomic_check(), @@ -636,14 +603,7 @@ static void dpu_crtc_atomic_flush(struct drm_crtc *crtc, static void dpu_crtc_destroy_state(struct drm_crtc *crtc, struct drm_crtc_state *state) { - struct dpu_crtc_state *cstate; - - if (!crtc || !state) { - DPU_ERROR("invalid argument(s)\n"); - return; - } - - cstate = to_dpu_crtc_state(state); + struct dpu_crtc_state *cstate = to_dpu_crtc_state(state); DPU_DEBUG("crtc%d\n", crtc->base.id); @@ -732,14 +692,8 @@ static void dpu_crtc_reset(struct drm_crtc *crtc) */ static struct drm_crtc_state *dpu_crtc_duplicate_state(struct drm_crtc *crtc) { - struct dpu_crtc_state *cstate, *old_cstate; + struct dpu_crtc_state *cstate, *old_cstate = to_dpu_crtc_state(crtc->state); - if (!crtc || !crtc->state) { - DPU_ERROR("invalid argument(s)\n"); - return NULL; - } - - old_cstate = to_dpu_crtc_state(crtc->state); cstate = kmemdup(old_cstate, sizeof(*old_cstate), GFP_KERNEL); if (!cstate) { DPU_ERROR("failed to allocate state\n"); @@ -757,19 +711,12 @@ static void dpu_crtc_disable(struct drm_crtc *crtc, { struct drm_crtc_state *old_crtc_state = drm_atomic_get_old_crtc_state(state, crtc); - struct dpu_crtc *dpu_crtc; - struct dpu_crtc_state *cstate; + struct dpu_crtc *dpu_crtc = to_dpu_crtc(crtc); + struct dpu_crtc_state *cstate = to_dpu_crtc_state(crtc->state); struct drm_encoder *encoder; unsigned long flags; bool release_bandwidth = false; - if (!crtc || !crtc->state) { - DPU_ERROR("invalid crtc\n"); - return; - } - dpu_crtc = to_dpu_crtc(crtc); - cstate = to_dpu_crtc_state(crtc->state); - DRM_DEBUG_KMS("crtc%d\n", crtc->base.id); /* Disable/save vblank irq handling */ @@ -828,19 +775,13 @@ static void dpu_crtc_disable(struct drm_crtc *crtc, static void dpu_crtc_enable(struct drm_crtc *crtc, struct drm_atomic_state *state) { - struct dpu_crtc *dpu_crtc; + struct dpu_crtc *dpu_crtc = to_dpu_crtc(crtc); struct drm_encoder *encoder; bool request_bandwidth = false; - if (!crtc) { - DPU_ERROR("invalid crtc\n"); - return; - } - pm_runtime_get_sync(crtc->dev->dev); DRM_DEBUG_KMS("crtc%d\n", crtc->base.id); - dpu_crtc = to_dpu_crtc(crtc); drm_for_each_encoder_mask(encoder, crtc->dev, crtc->state->encoder_mask) { /* in video mode, we hold an extra bandwidth reference @@ -876,15 +817,15 @@ struct plane_state { static int dpu_crtc_atomic_check(struct drm_crtc *crtc, struct drm_crtc_state *state) { - struct dpu_crtc *dpu_crtc; + struct dpu_crtc *dpu_crtc = to_dpu_crtc(crtc); + struct dpu_crtc_state *cstate = to_dpu_crtc_state(state); struct plane_state *pstates; - struct dpu_crtc_state *cstate; const struct drm_plane_state *pstate; struct drm_plane *plane; struct drm_display_mode *mode; - int cnt = 0, rc = 0, mixer_width, i, z_pos; + int cnt = 0, rc = 0, mixer_width = 0, i, z_pos; struct dpu_multirect_plane_states multirect_plane[DPU_STAGE_MAX * 2]; int multirect_count = 0; @@ -892,16 +833,8 @@ static int dpu_crtc_atomic_check(struct drm_crtc *crtc, int left_zpos_cnt = 0, right_zpos_cnt = 0; struct drm_rect crtc_rect = { 0 }; - if (!crtc) { - DPU_ERROR("invalid crtc\n"); - return -EINVAL; - } - pstates = kzalloc(sizeof(*pstates) * DPU_STAGE_MAX * 4, GFP_KERNEL); - dpu_crtc = to_dpu_crtc(crtc); - cstate = to_dpu_crtc_state(state); - if (!state->enable || !state->active) { DPU_DEBUG("crtc%d -> enable %d, active %d, skip atomic_check\n", crtc->base.id, state->enable, state->active); @@ -917,9 +850,11 @@ static int dpu_crtc_atomic_check(struct drm_crtc *crtc, memset(pipe_staged, 0, sizeof(pipe_staged)); - mixer_width = mode->hdisplay / cstate->num_mixers; + if (cstate->num_mixers) { + mixer_width = mode->hdisplay / cstate->num_mixers; - _dpu_crtc_setup_lm_bounds(crtc, state); + _dpu_crtc_setup_lm_bounds(crtc, state); + } crtc_rect.x2 = mode->hdisplay; crtc_rect.y2 = mode->vdisplay; @@ -1245,23 +1180,7 @@ static int _dpu_debugfs_status_show(struct seq_file *s, void *data) return 0; } -static int _dpu_debugfs_status_open(struct inode *inode, struct file *file) -{ - return single_open(file, _dpu_debugfs_status_show, inode->i_private); -} - -#define DEFINE_DPU_DEBUGFS_SEQ_FOPS(__prefix) \ -static int __prefix ## _open(struct inode *inode, struct file *file) \ -{ \ - return single_open(file, __prefix ## _show, inode->i_private); \ -} \ -static const struct file_operations __prefix ## _fops = { \ - .owner = THIS_MODULE, \ - .open = __prefix ## _open, \ - .release = single_release, \ - .read = seq_read, \ - .llseek = seq_lseek, \ -} +DEFINE_SHOW_ATTRIBUTE(_dpu_debugfs_status); static int dpu_crtc_debugfs_state_show(struct seq_file *s, void *v) { @@ -1278,25 +1197,18 @@ static int dpu_crtc_debugfs_state_show(struct seq_file *s, void *v) return 0; } -DEFINE_DPU_DEBUGFS_SEQ_FOPS(dpu_crtc_debugfs_state); +DEFINE_SHOW_ATTRIBUTE(dpu_crtc_debugfs_state); static int _dpu_crtc_init_debugfs(struct drm_crtc *crtc) { struct dpu_crtc *dpu_crtc = to_dpu_crtc(crtc); - static const struct file_operations debugfs_status_fops = { - .open = _dpu_debugfs_status_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, - }; - dpu_crtc->debugfs_root = debugfs_create_dir(dpu_crtc->name, crtc->dev->primary->debugfs_root); debugfs_create_file("status", 0400, dpu_crtc->debugfs_root, - dpu_crtc, &debugfs_status_fops); + dpu_crtc, &_dpu_debugfs_status_fops); debugfs_create_file("state", 0600, dpu_crtc->debugfs_root, &dpu_crtc->base, diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c index bd6def436c65..f7f5c258b553 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c @@ -1001,6 +1001,9 @@ static void dpu_encoder_virt_mode_set(struct drm_encoder *drm_enc, trace_dpu_enc_mode_set(DRMID(drm_enc)); + if (drm_enc->encoder_type == DRM_MODE_ENCODER_TMDS && priv->dp) + msm_dp_display_mode_set(priv->dp, drm_enc, mode, adj_mode); + list_for_each_entry(conn_iter, connector_list, head) if (conn_iter->encoder == drm_enc) conn = conn_iter; @@ -1109,6 +1112,13 @@ static void _dpu_encoder_virt_enable_helper(struct drm_encoder *drm_enc) return; } + + if (dpu_enc->disp_info.intf_type == DRM_MODE_CONNECTOR_DisplayPort && + dpu_enc->cur_master->hw_mdptop && + dpu_enc->cur_master->hw_mdptop->ops.intf_audio_select) + dpu_enc->cur_master->hw_mdptop->ops.intf_audio_select( + dpu_enc->cur_master->hw_mdptop); + _dpu_encoder_update_vsync_source(dpu_enc, &dpu_enc->disp_info); if (dpu_enc->disp_info.intf_type == DRM_MODE_ENCODER_DSI && @@ -1146,6 +1156,7 @@ static void dpu_encoder_virt_enable(struct drm_encoder *drm_enc) { struct dpu_encoder_virt *dpu_enc = NULL; int ret = 0; + struct msm_drm_private *priv; struct drm_display_mode *cur_mode = NULL; if (!drm_enc) { @@ -1156,6 +1167,7 @@ static void dpu_encoder_virt_enable(struct drm_encoder *drm_enc) mutex_lock(&dpu_enc->enc_lock); cur_mode = &dpu_enc->base.crtc->state->adjusted_mode; + priv = drm_enc->dev->dev_private; trace_dpu_enc_enable(DRMID(drm_enc), cur_mode->hdisplay, cur_mode->vdisplay); @@ -1176,6 +1188,15 @@ static void dpu_encoder_virt_enable(struct drm_encoder *drm_enc) _dpu_encoder_virt_enable_helper(drm_enc); + if (drm_enc->encoder_type == DRM_MODE_ENCODER_TMDS && priv->dp) { + ret = msm_dp_display_enable(priv->dp, + drm_enc); + if (ret) { + DPU_ERROR_ENC(dpu_enc, "dp display enable failed: %d\n", + ret); + goto out; + } + } dpu_enc->enabled = true; out: @@ -1211,6 +1232,11 @@ static void dpu_encoder_virt_disable(struct drm_encoder *drm_enc) /* wait for idle */ dpu_encoder_wait_for_event(drm_enc, MSM_ENC_TX_COMPLETE); + if (drm_enc->encoder_type == DRM_MODE_ENCODER_TMDS && priv->dp) { + if (msm_dp_display_pre_disable(priv->dp, drm_enc)) + DPU_ERROR_ENC(dpu_enc, "dp display push idle failed\n"); + } + dpu_encoder_resource_control(drm_enc, DPU_ENC_RC_EVENT_PRE_STOP); for (i = 0; i < dpu_enc->num_phys_encs; i++) { @@ -1220,6 +1246,7 @@ static void dpu_encoder_virt_disable(struct drm_encoder *drm_enc) phys->ops.disable(phys); } + /* after phys waits for frame-done, should be no more frames pending */ if (atomic_xchg(&dpu_enc->frame_done_timeout_ms, 0)) { DPU_ERROR("enc%d timeout pending\n", drm_enc->base.id); @@ -1234,6 +1261,11 @@ static void dpu_encoder_virt_disable(struct drm_encoder *drm_enc) DPU_DEBUG_ENC(dpu_enc, "encoder disabled\n"); + if (drm_enc->encoder_type == DRM_MODE_ENCODER_TMDS && priv->dp) { + if (msm_dp_display_disable(priv->dp, drm_enc)) + DPU_ERROR_ENC(dpu_enc, "dp display disable failed\n"); + } + mutex_unlock(&dpu_enc->enc_lock); } @@ -1880,24 +1912,13 @@ static int _dpu_encoder_status_show(struct seq_file *s, void *data) return 0; } -static int _dpu_encoder_debugfs_status_open(struct inode *inode, - struct file *file) -{ - return single_open(file, _dpu_encoder_status_show, inode->i_private); -} +DEFINE_SHOW_ATTRIBUTE(_dpu_encoder_status); static int _dpu_encoder_init_debugfs(struct drm_encoder *drm_enc) { struct dpu_encoder_virt *dpu_enc = to_dpu_encoder_virt(drm_enc); int i; - static const struct file_operations debugfs_status_fops = { - .open = _dpu_encoder_debugfs_status_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, - }; - char name[DPU_NAME_SIZE]; if (!drm_enc->dev) { @@ -1913,7 +1934,7 @@ static int _dpu_encoder_init_debugfs(struct drm_encoder *drm_enc) /* don't error check these */ debugfs_create_file("status", 0600, - dpu_enc->debugfs_root, dpu_enc, &debugfs_status_fops); + dpu_enc->debugfs_root, dpu_enc, &_dpu_encoder_status_fops); for (i = 0; i < dpu_enc->num_phys_encs; i++) if (dpu_enc->phys_encs[i]->ops.late_register) @@ -2008,7 +2029,7 @@ static int dpu_encoder_setup_display(struct dpu_encoder_virt *dpu_enc, { int ret = 0; int i = 0; - enum dpu_intf_type intf_type; + enum dpu_intf_type intf_type = INTF_NONE; struct dpu_enc_phys_init_params phys_params; if (!dpu_enc) { @@ -2030,9 +2051,9 @@ static int dpu_encoder_setup_display(struct dpu_encoder_virt *dpu_enc, case DRM_MODE_ENCODER_DSI: intf_type = INTF_DSI; break; - default: - DPU_ERROR_ENC(dpu_enc, "unsupported display interface type\n"); - return -EINVAL; + case DRM_MODE_ENCODER_TMDS: + intf_type = INTF_DP; + break; } WARN_ON(disp_info->num_of_h_tiles < 1); diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_vid.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_vid.c index b5a49050d131..805e059b50b7 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_vid.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_vid.c @@ -100,6 +100,14 @@ static void drm_mode_to_intf_timing_params( * display_v_end -= mode->hsync_start - mode->hdisplay; * } */ + /* for DP/EDP, Shift timings to align it to bottom right */ + if ((phys_enc->hw_intf->cap->type == INTF_DP) || + (phys_enc->hw_intf->cap->type == INTF_EDP)) { + timing->h_back_porch += timing->h_front_porch; + timing->h_front_porch = 0; + timing->v_back_porch += timing->v_front_porch; + timing->v_front_porch = 0; + } } static u32 get_horizontal_total(const struct intf_timing_params *timing) @@ -298,7 +306,6 @@ static void dpu_encoder_phys_vid_vblank_irq(void *arg, int irq_idx) struct dpu_hw_ctl *hw_ctl; unsigned long lock_flags; u32 flush_register = 0; - int new_cnt = -1, old_cnt = -1; hw_ctl = phys_enc->hw_ctl; @@ -308,7 +315,7 @@ static void dpu_encoder_phys_vid_vblank_irq(void *arg, int irq_idx) phys_enc->parent_ops->handle_vblank_virt(phys_enc->parent, phys_enc); - old_cnt = atomic_read(&phys_enc->pending_kickoff_cnt); + atomic_read(&phys_enc->pending_kickoff_cnt); /* * only decrement the pending flush count if we've actually flushed @@ -320,8 +327,7 @@ static void dpu_encoder_phys_vid_vblank_irq(void *arg, int irq_idx) flush_register = hw_ctl->ops.get_flush_register(hw_ctl); if (!(flush_register & hw_ctl->ops.get_pending_flush(hw_ctl))) - new_cnt = atomic_add_unless(&phys_enc->pending_kickoff_cnt, - -1, 0); + atomic_add_unless(&phys_enc->pending_kickoff_cnt, -1, 0); spin_unlock_irqrestore(phys_enc->enc_spinlock, lock_flags); /* Signal any waiting atomic commit thread */ diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c index 97d122eee96d..60b304b72b7c 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c @@ -684,7 +684,8 @@ static const struct dpu_perf_cfg sc7180_perf_data = { .max_bw_high = 6800000, .min_core_ib = 2400000, .min_llcc_ib = 800000, - .min_dram_ib = 800000, + .min_dram_ib = 1600000, + .min_prefill_lines = 24, .danger_lut_tbl = {0xff, 0xffff, 0x0}, .qos_lut_tbl = { {.nentry = ARRAY_SIZE(sc7180_qos_linear), @@ -701,6 +702,8 @@ static const struct dpu_perf_cfg sc7180_perf_data = { {.rd_enable = 1, .wr_enable = 1}, {.rd_enable = 1, .wr_enable = 0} }, + .clk_inefficiency_factor = 105, + .bw_inefficiency_factor = 120, }; static const struct dpu_perf_cfg sm8150_perf_data = { diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.h index 1b7a9213a756..3544af1a45c5 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.h +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.h @@ -659,6 +659,8 @@ struct dpu_perf_cdp_cfg { * @downscaling_prefill_lines downscaling latency in lines * @amortizable_theshold minimum y position for traffic shaping prefill * @min_prefill_lines minimum pipeline latency in lines + * @clk_inefficiency_factor DPU src clock inefficiency factor + * @bw_inefficiency_factor DPU axi bus bw inefficiency factor * @safe_lut_tbl: LUT tables for safe signals * @danger_lut_tbl: LUT tables for danger signals * @qos_lut_tbl: LUT tables for QoS signals @@ -683,6 +685,8 @@ struct dpu_perf_cfg { u32 downscaling_prefill_lines; u32 amortizable_threshold; u32 min_prefill_lines; + u32 clk_inefficiency_factor; + u32 bw_inefficiency_factor; u32 safe_lut_tbl[DPU_QOS_LUT_USAGE_MAX]; u32 danger_lut_tbl[DPU_QOS_LUT_USAGE_MAX]; struct dpu_qos_lut_tbl qos_lut_tbl[DPU_QOS_LUT_USAGE_MAX]; diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c index c0a4d4e16d82..d93c44f6996d 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c @@ -85,30 +85,17 @@ static int _dpu_danger_signal_status(struct seq_file *s, return 0; } -#define DEFINE_DPU_DEBUGFS_SEQ_FOPS(__prefix) \ -static int __prefix ## _open(struct inode *inode, struct file *file) \ -{ \ - return single_open(file, __prefix ## _show, inode->i_private); \ -} \ -static const struct file_operations __prefix ## _fops = { \ - .owner = THIS_MODULE, \ - .open = __prefix ## _open, \ - .release = single_release, \ - .read = seq_read, \ - .llseek = seq_lseek, \ -} - static int dpu_debugfs_danger_stats_show(struct seq_file *s, void *v) { return _dpu_danger_signal_status(s, true); } -DEFINE_DPU_DEBUGFS_SEQ_FOPS(dpu_debugfs_danger_stats); +DEFINE_SHOW_ATTRIBUTE(dpu_debugfs_danger_stats); static int dpu_debugfs_safe_stats_show(struct seq_file *s, void *v) { return _dpu_danger_signal_status(s, false); } -DEFINE_DPU_DEBUGFS_SEQ_FOPS(dpu_debugfs_safe_stats); +DEFINE_SHOW_ATTRIBUTE(dpu_debugfs_safe_stats); static void dpu_debugfs_danger_init(struct dpu_kms *dpu_kms, struct dentry *parent) @@ -195,10 +182,15 @@ static int dpu_kms_debugfs_init(struct msm_kms *kms, struct drm_minor *minor) struct dpu_kms *dpu_kms = to_dpu_kms(kms); void *p = dpu_hw_util_get_log_mask_ptr(); struct dentry *entry; + struct drm_device *dev; + struct msm_drm_private *priv; if (!p) return -EINVAL; + dev = dpu_kms->dev; + priv = dev->dev_private; + entry = debugfs_create_dir("debug", minor->debugfs_root); debugfs_create_x32(DPU_DEBUGFS_HWMASKNAME, 0600, entry, p); @@ -207,6 +199,9 @@ static int dpu_kms_debugfs_init(struct msm_kms *kms, struct drm_minor *minor) dpu_debugfs_vbif_init(dpu_kms, entry); dpu_debugfs_core_irq_init(dpu_kms, entry); + if (priv->dp) + msm_dp_debugfs_init(priv->dp, minor); + return dpu_core_perf_debugfs_init(dpu_kms, entry); } #endif @@ -290,6 +285,28 @@ static int dpu_kms_global_obj_init(struct dpu_kms *dpu_kms) return 0; } +static int dpu_kms_parse_data_bus_icc_path(struct dpu_kms *dpu_kms) +{ + struct icc_path *path0; + struct icc_path *path1; + struct drm_device *dev = dpu_kms->dev; + + path0 = of_icc_get(dev->dev, "mdp0-mem"); + path1 = of_icc_get(dev->dev, "mdp1-mem"); + + if (IS_ERR_OR_NULL(path0)) + return PTR_ERR_OR_ZERO(path0); + + dpu_kms->path[0] = path0; + dpu_kms->num_paths = 1; + + if (!IS_ERR_OR_NULL(path1)) { + dpu_kms->path[1] = path1; + dpu_kms->num_paths++; + } + return 0; +} + static int dpu_kms_enable_vblank(struct msm_kms *kms, struct drm_crtc *crtc) { return dpu_crtc_vblank(crtc, true); @@ -479,6 +496,33 @@ static int _dpu_kms_initialize_dsi(struct drm_device *dev, return rc; } +static int _dpu_kms_initialize_displayport(struct drm_device *dev, + struct msm_drm_private *priv, + struct dpu_kms *dpu_kms) +{ + struct drm_encoder *encoder = NULL; + int rc = 0; + + if (!priv->dp) + return rc; + + encoder = dpu_encoder_init(dev, DRM_MODE_ENCODER_TMDS); + if (IS_ERR(encoder)) { + DPU_ERROR("encoder init failed for dsi display\n"); + return PTR_ERR(encoder); + } + + rc = msm_dp_modeset_init(priv->dp, dev, encoder); + if (rc) { + DPU_ERROR("modeset_init failed for DP, rc = %d\n", rc); + drm_encoder_cleanup(encoder); + return rc; + } + + priv->encoders[priv->num_encoders++] = encoder; + return rc; +} + /** * _dpu_kms_setup_displays - create encoders, bridges and connectors * for underlying displays @@ -491,12 +535,21 @@ static int _dpu_kms_setup_displays(struct drm_device *dev, struct msm_drm_private *priv, struct dpu_kms *dpu_kms) { - /** - * Extend this function to initialize other - * types of displays - */ + int rc = 0; - return _dpu_kms_initialize_dsi(dev, priv, dpu_kms); + rc = _dpu_kms_initialize_dsi(dev, priv, dpu_kms); + if (rc) { + DPU_ERROR("initialize_dsi failed, rc = %d\n", rc); + return rc; + } + + rc = _dpu_kms_initialize_displayport(dev, priv, dpu_kms); + if (rc) { + DPU_ERROR("initialize_DP failed, rc = %d\n", rc); + return rc; + } + + return rc; } static void _dpu_kms_drm_obj_destroy(struct dpu_kms *dpu_kms) @@ -681,13 +734,20 @@ static void _dpu_kms_set_encoder_mode(struct msm_kms *kms, info.capabilities = cmd_mode ? MSM_DISPLAY_CAP_CMD_MODE : MSM_DISPLAY_CAP_VID_MODE; - /* TODO: No support for DSI swap */ - for (i = 0; i < ARRAY_SIZE(priv->dsi); i++) { - if (priv->dsi[i]) { - info.h_tile_instance[info.num_of_h_tiles] = i; - info.num_of_h_tiles++; + switch (info.intf_type) { + case DRM_MODE_ENCODER_DSI: + /* TODO: No support for DSI swap */ + for (i = 0; i < ARRAY_SIZE(priv->dsi); i++) { + if (priv->dsi[i]) { + info.h_tile_instance[info.num_of_h_tiles] = i; + info.num_of_h_tiles++; + } } - } + break; + case DRM_MODE_ENCODER_TMDS: + info.num_of_h_tiles = 1; + break; + }; rc = dpu_encoder_setup(encoder->dev, encoder, &info); if (rc) @@ -709,6 +769,23 @@ static void dpu_irq_preinstall(struct msm_kms *kms) dpu_core_irq_preinstall(dpu_kms); } +static int dpu_irq_postinstall(struct msm_kms *kms) +{ + struct msm_drm_private *priv; + struct dpu_kms *dpu_kms = to_dpu_kms(kms); + + if (!dpu_kms || !dpu_kms->dev) + return -EINVAL; + + priv = dpu_kms->dev->dev_private; + if (!priv) + return -EINVAL; + + msm_dp_irq_postinstall(priv->dp); + + return 0; +} + static void dpu_irq_uninstall(struct msm_kms *kms) { struct dpu_kms *dpu_kms = to_dpu_kms(kms); @@ -719,6 +796,7 @@ static void dpu_irq_uninstall(struct msm_kms *kms) static const struct msm_kms_funcs kms_funcs = { .hw_init = dpu_kms_hw_init, .irq_preinstall = dpu_irq_preinstall, + .irq_postinstall = dpu_irq_postinstall, .irq_uninstall = dpu_irq_uninstall, .irq = dpu_irq, .enable_commit = dpu_kms_enable_commit, @@ -952,6 +1030,9 @@ static int dpu_kms_hw_init(struct msm_kms *kms) dpu_vbif_init_memtypes(dpu_kms); + if (of_device_is_compatible(dev->dev->of_node, "qcom,sc7180-mdss")) + dpu_kms_parse_data_bus_icc_path(dpu_kms); + pm_runtime_put_sync(&dpu_kms->pdev->dev); return 0; @@ -1079,7 +1160,7 @@ static int dpu_dev_remove(struct platform_device *pdev) static int __maybe_unused dpu_runtime_suspend(struct device *dev) { - int rc = -1; + int i, rc = -1; struct platform_device *pdev = to_platform_device(dev); struct dpu_kms *dpu_kms = platform_get_drvdata(pdev); struct dss_module_power *mp = &dpu_kms->mp; @@ -1090,6 +1171,9 @@ static int __maybe_unused dpu_runtime_suspend(struct device *dev) if (rc) DPU_ERROR("clock disable failed rc:%d\n", rc); + for (i = 0; i < dpu_kms->num_paths; i++) + icc_set_bw(dpu_kms->path[i], 0, 0); + return rc; } @@ -1101,8 +1185,15 @@ static int __maybe_unused dpu_runtime_resume(struct device *dev) struct drm_encoder *encoder; struct drm_device *ddev; struct dss_module_power *mp = &dpu_kms->mp; + int i; ddev = dpu_kms->dev; + + /* Min vote of BW is required before turning on AXI clk */ + for (i = 0; i < dpu_kms->num_paths; i++) + icc_set_bw(dpu_kms->path[i], 0, + dpu_kms->catalog->perf.min_dram_ib); + rc = msm_dss_enable_clk(mp->clk_config, mp->num_clk, true); if (rc) { DPU_ERROR("clock enable failed rc:%d\n", rc); diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.h index e140cd633071..1c0e4c0c9ffb 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.h +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.h @@ -8,6 +8,8 @@ #ifndef __DPU_KMS_H__ #define __DPU_KMS_H__ +#include <linux/interconnect.h> + #include <drm/drm_drv.h> #include "msm_drv.h" @@ -140,6 +142,8 @@ struct dpu_kms { * when disabled. */ atomic_t bandwidth_ref; + struct icc_path *path[2]; + u32 num_paths; }; struct vsync_info { diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_mdss.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_mdss.c index 7d3fdbb00e7e..cd4078807db1 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_mdss.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_mdss.c @@ -8,7 +8,6 @@ #include <linux/irqdesc.h> #include <linux/irqchip/chained_irq.h> #include "dpu_kms.h" -#include <linux/interconnect.h> #define to_dpu_mdss(x) container_of(x, struct dpu_mdss, base) @@ -277,9 +276,11 @@ int dpu_mdss_init(struct drm_device *dev) DRM_DEBUG("mapped mdss address space @%pK\n", dpu_mdss->mmio); - ret = dpu_mdss_parse_data_bus_icc_path(dev, dpu_mdss); - if (ret) - return ret; + if (!of_device_is_compatible(dev->dev->of_node, "qcom,sc7180-mdss")) { + ret = dpu_mdss_parse_data_bus_icc_path(dev, dpu_mdss); + if (ret) + return ret; + } mp = &dpu_mdss->mp; ret = msm_dss_parse_clock(pdev, mp); diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c index 29e373d2e7b5..7ea90d25a3b6 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c @@ -132,6 +132,86 @@ static struct dpu_kms *_dpu_plane_get_kms(struct drm_plane *plane) } /** + * _dpu_plane_calc_bw - calculate bandwidth required for a plane + * @Plane: Pointer to drm plane. + * Result: Updates calculated bandwidth in the plane state. + * BW Equation: src_w * src_h * bpp * fps * (v_total / v_dest) + * Prefill BW Equation: line src bytes * line_time + */ +static void _dpu_plane_calc_bw(struct drm_plane *plane, + struct drm_framebuffer *fb) +{ + struct dpu_plane *pdpu = to_dpu_plane(plane); + struct dpu_plane_state *pstate; + struct drm_display_mode *mode; + const struct dpu_format *fmt = NULL; + struct dpu_kms *dpu_kms = _dpu_plane_get_kms(plane); + int src_width, src_height, dst_height, fps; + u64 plane_prefill_bw; + u64 plane_bw; + u32 hw_latency_lines; + u64 scale_factor; + int vbp, vpw; + + pstate = to_dpu_plane_state(plane->state); + mode = &plane->state->crtc->mode; + + fmt = dpu_get_dpu_format_ext(fb->format->format, fb->modifier); + + src_width = drm_rect_width(&pdpu->pipe_cfg.src_rect); + src_height = drm_rect_height(&pdpu->pipe_cfg.src_rect); + dst_height = drm_rect_height(&pdpu->pipe_cfg.dst_rect); + fps = drm_mode_vrefresh(mode); + vbp = mode->vtotal - mode->vsync_end; + vpw = mode->vsync_end - mode->vsync_start; + hw_latency_lines = dpu_kms->catalog->perf.min_prefill_lines; + scale_factor = src_height > dst_height ? + mult_frac(src_height, 1, dst_height) : 1; + + plane_bw = + src_width * mode->vtotal * fps * fmt->bpp * + scale_factor; + + plane_prefill_bw = + src_width * hw_latency_lines * fps * fmt->bpp * + scale_factor * mode->vtotal; + + do_div(plane_prefill_bw, (vbp+vpw)); + + pstate->plane_fetch_bw = max(plane_bw, plane_prefill_bw); +} + +/** + * _dpu_plane_calc_clk - calculate clock required for a plane + * @Plane: Pointer to drm plane. + * Result: Updates calculated clock in the plane state. + * Clock equation: dst_w * v_total * fps * (src_h / dst_h) + */ +static void _dpu_plane_calc_clk(struct drm_plane *plane) +{ + struct dpu_plane *pdpu = to_dpu_plane(plane); + struct dpu_plane_state *pstate; + struct drm_display_mode *mode; + int dst_width, src_height, dst_height, fps; + + pstate = to_dpu_plane_state(plane->state); + mode = &plane->state->crtc->mode; + + src_height = drm_rect_height(&pdpu->pipe_cfg.src_rect); + dst_width = drm_rect_width(&pdpu->pipe_cfg.dst_rect); + dst_height = drm_rect_height(&pdpu->pipe_cfg.dst_rect); + fps = drm_mode_vrefresh(mode); + + pstate->plane_clk = + dst_width * mode->vtotal * fps; + + if (src_height > dst_height) { + pstate->plane_clk *= src_height; + do_div(pstate->plane_clk, dst_height); + } +} + +/** * _dpu_plane_calc_fill_level - calculate fill level of the given source format * @plane: Pointer to drm plane * @fmt: Pointer to source buffer format @@ -1102,6 +1182,10 @@ static void dpu_plane_sspp_atomic_update(struct drm_plane *plane) } _dpu_plane_set_qos_remap(plane); + + _dpu_plane_calc_bw(plane, fb); + + _dpu_plane_calc_clk(plane); } static void _dpu_plane_atomic_disable(struct drm_plane *plane) diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.h index 456949713e90..ca83b8753d59 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.h +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.h @@ -25,6 +25,8 @@ * @scaler3_cfg: configuration data for scaler3 * @pixel_ext: configuration data for pixel extensions * @cdp_cfg: CDP configuration + * @plane_fetch_bw: calculated BW per plane + * @plane_clk: calculated clk per plane */ struct dpu_plane_state { struct drm_plane_state base; @@ -39,6 +41,8 @@ struct dpu_plane_state { struct dpu_hw_pixel_ext pixel_ext; struct dpu_hw_pipe_cdp_cfg cdp_cfg; + u64 plane_fetch_bw; + u64 plane_clk; }; /** diff --git a/drivers/gpu/drm/msm/disp/mdp4/mdp4_dtv_encoder.c b/drivers/gpu/drm/msm/disp/mdp4/mdp4_dtv_encoder.c index 5d8956055286..88645dbc3785 100644 --- a/drivers/gpu/drm/msm/disp/mdp4/mdp4_dtv_encoder.c +++ b/drivers/gpu/drm/msm/disp/mdp4/mdp4_dtv_encoder.c @@ -25,54 +25,9 @@ static struct mdp4_kms *get_kms(struct drm_encoder *encoder) return to_mdp4_kms(to_mdp_kms(priv->kms)); } -#ifdef DOWNSTREAM_CONFIG_MSM_BUS_SCALING -#include <mach/board.h> -/* not ironically named at all.. no, really.. */ -static void bs_init(struct mdp4_dtv_encoder *mdp4_dtv_encoder) -{ - struct drm_device *dev = mdp4_dtv_encoder->base.dev; - struct lcdc_platform_data *dtv_pdata = mdp4_find_pdata("dtv.0"); - - if (!dtv_pdata) { - DRM_DEV_ERROR(dev->dev, "could not find dtv pdata\n"); - return; - } - - if (dtv_pdata->bus_scale_table) { - mdp4_dtv_encoder->bsc = msm_bus_scale_register_client( - dtv_pdata->bus_scale_table); - DBG("bus scale client: %08x", mdp4_dtv_encoder->bsc); - DBG("lcdc_power_save: %p", dtv_pdata->lcdc_power_save); - if (dtv_pdata->lcdc_power_save) - dtv_pdata->lcdc_power_save(1); - } -} - -static void bs_fini(struct mdp4_dtv_encoder *mdp4_dtv_encoder) -{ - if (mdp4_dtv_encoder->bsc) { - msm_bus_scale_unregister_client(mdp4_dtv_encoder->bsc); - mdp4_dtv_encoder->bsc = 0; - } -} - -static void bs_set(struct mdp4_dtv_encoder *mdp4_dtv_encoder, int idx) -{ - if (mdp4_dtv_encoder->bsc) { - DBG("set bus scaling: %d", idx); - msm_bus_scale_client_update_request(mdp4_dtv_encoder->bsc, idx); - } -} -#else -static void bs_init(struct mdp4_dtv_encoder *mdp4_dtv_encoder) {} -static void bs_fini(struct mdp4_dtv_encoder *mdp4_dtv_encoder) {} -static void bs_set(struct mdp4_dtv_encoder *mdp4_dtv_encoder, int idx) {} -#endif - static void mdp4_dtv_encoder_destroy(struct drm_encoder *encoder) { struct mdp4_dtv_encoder *mdp4_dtv_encoder = to_mdp4_dtv_encoder(encoder); - bs_fini(mdp4_dtv_encoder); drm_encoder_cleanup(encoder); kfree(mdp4_dtv_encoder); } @@ -162,8 +117,6 @@ static void mdp4_dtv_encoder_disable(struct drm_encoder *encoder) clk_disable_unprepare(mdp4_dtv_encoder->hdmi_clk); clk_disable_unprepare(mdp4_dtv_encoder->mdp_clk); - bs_set(mdp4_dtv_encoder, 0); - mdp4_dtv_encoder->enabled = false; } @@ -185,8 +138,6 @@ static void mdp4_dtv_encoder_enable(struct drm_encoder *encoder) MDP4_DMA_CONFIG_PACK(0x21)); mdp4_crtc_set_intf(encoder->crtc, INTF_LCDC_DTV, 1); - bs_set(mdp4_dtv_encoder, 1); - DBG("setting mdp_clk=%lu", pc); ret = clk_set_rate(mdp4_dtv_encoder->mdp_clk, pc); @@ -252,8 +203,6 @@ struct drm_encoder *mdp4_dtv_encoder_init(struct drm_device *dev) goto fail; } - bs_init(mdp4_dtv_encoder); - return encoder; fail: diff --git a/drivers/gpu/drm/msm/disp/mdp4/mdp4_kms.h b/drivers/gpu/drm/msm/disp/mdp4/mdp4_kms.h index 18933bd81c77..e8ee92ab7956 100644 --- a/drivers/gpu/drm/msm/disp/mdp4/mdp4_kms.h +++ b/drivers/gpu/drm/msm/disp/mdp4/mdp4_kms.h @@ -222,17 +222,4 @@ static inline struct clk *mpd4_lvds_pll_init(struct drm_device *dev) } #endif -#ifdef DOWNSTREAM_CONFIG_MSM_BUS_SCALING -/* bus scaling data is associated with extra pointless platform devices, - * "dtv", etc.. this is a bit of a hack, but we need a way for encoders - * to find their pdata to make the bus-scaling stuff work. - */ -static inline void *mdp4_find_pdata(const char *devname) -{ - struct device *dev; - dev = bus_find_device_by_name(&platform_bus_type, NULL, devname); - return dev ? dev->platform_data : NULL; -} -#endif - #endif /* __MDP4_KMS_H__ */ diff --git a/drivers/gpu/drm/msm/disp/mdp4/mdp4_lcdc_encoder.c b/drivers/gpu/drm/msm/disp/mdp4/mdp4_lcdc_encoder.c index 871f3514ef69..10eb3e5b218e 100644 --- a/drivers/gpu/drm/msm/disp/mdp4/mdp4_lcdc_encoder.c +++ b/drivers/gpu/drm/msm/disp/mdp4/mdp4_lcdc_encoder.c @@ -30,51 +30,10 @@ static struct mdp4_kms *get_kms(struct drm_encoder *encoder) return to_mdp4_kms(to_mdp_kms(priv->kms)); } -#ifdef DOWNSTREAM_CONFIG_MSM_BUS_SCALING -#include <mach/board.h> -static void bs_init(struct mdp4_lcdc_encoder *mdp4_lcdc_encoder) -{ - struct drm_device *dev = mdp4_lcdc_encoder->base.dev; - struct lcdc_platform_data *lcdc_pdata = mdp4_find_pdata("lvds.0"); - - if (!lcdc_pdata) { - DRM_DEV_ERROR(dev->dev, "could not find lvds pdata\n"); - return; - } - - if (lcdc_pdata->bus_scale_table) { - mdp4_lcdc_encoder->bsc = msm_bus_scale_register_client( - lcdc_pdata->bus_scale_table); - DBG("lvds : bus scale client: %08x", mdp4_lcdc_encoder->bsc); - } -} - -static void bs_fini(struct mdp4_lcdc_encoder *mdp4_lcdc_encoder) -{ - if (mdp4_lcdc_encoder->bsc) { - msm_bus_scale_unregister_client(mdp4_lcdc_encoder->bsc); - mdp4_lcdc_encoder->bsc = 0; - } -} - -static void bs_set(struct mdp4_lcdc_encoder *mdp4_lcdc_encoder, int idx) -{ - if (mdp4_lcdc_encoder->bsc) { - DBG("set bus scaling: %d", idx); - msm_bus_scale_client_update_request(mdp4_lcdc_encoder->bsc, idx); - } -} -#else -static void bs_init(struct mdp4_lcdc_encoder *mdp4_lcdc_encoder) {} -static void bs_fini(struct mdp4_lcdc_encoder *mdp4_lcdc_encoder) {} -static void bs_set(struct mdp4_lcdc_encoder *mdp4_lcdc_encoder, int idx) {} -#endif - static void mdp4_lcdc_encoder_destroy(struct drm_encoder *encoder) { struct mdp4_lcdc_encoder *mdp4_lcdc_encoder = to_mdp4_lcdc_encoder(encoder); - bs_fini(mdp4_lcdc_encoder); drm_encoder_cleanup(encoder); kfree(mdp4_lcdc_encoder); } @@ -348,8 +307,6 @@ static void mdp4_lcdc_encoder_disable(struct drm_encoder *encoder) DRM_DEV_ERROR(dev->dev, "failed to disable regulator: %d\n", ret); } - bs_set(mdp4_lcdc_encoder, 0); - mdp4_lcdc_encoder->enabled = false; } @@ -382,8 +339,6 @@ static void mdp4_lcdc_encoder_enable(struct drm_encoder *encoder) mdp4_crtc_set_config(encoder->crtc, config); mdp4_crtc_set_intf(encoder->crtc, INTF_LCDC_DTV, 0); - bs_set(mdp4_lcdc_encoder, 1); - for (i = 0; i < ARRAY_SIZE(mdp4_lcdc_encoder->regs); i++) { ret = regulator_enable(mdp4_lcdc_encoder->regs[i]); if (ret) @@ -480,8 +435,6 @@ struct drm_encoder *mdp4_lcdc_encoder_init(struct drm_device *dev, } mdp4_lcdc_encoder->regs[2] = reg; - bs_init(mdp4_lcdc_encoder); - return encoder; fail: diff --git a/drivers/gpu/drm/msm/disp/mdp5/mdp5_cmd_encoder.c b/drivers/gpu/drm/msm/disp/mdp5/mdp5_cmd_encoder.c index eeef41fcd4e1..ff2c1d583c79 100644 --- a/drivers/gpu/drm/msm/disp/mdp5/mdp5_cmd_encoder.c +++ b/drivers/gpu/drm/msm/disp/mdp5/mdp5_cmd_encoder.c @@ -14,27 +14,6 @@ static struct mdp5_kms *get_kms(struct drm_encoder *encoder) return to_mdp5_kms(to_mdp_kms(priv->kms)); } -#ifdef DOWNSTREAM_CONFIG_MSM_BUS_SCALING -#include <mach/board.h> -#include <linux/msm-bus.h> -#include <linux/msm-bus-board.h> - -static void bs_set(struct mdp5_encoder *mdp5_cmd_enc, int idx) -{ - if (mdp5_cmd_enc->bsc) { - DBG("set bus scaling: %d", idx); - /* HACK: scaling down, and then immediately back up - * seems to leave things broken (underflow).. so - * never disable: - */ - idx = 1; - msm_bus_scale_client_update_request(mdp5_cmd_enc->bsc, idx); - } -} -#else -static void bs_set(struct mdp5_encoder *mdp5_cmd_enc, int idx) {} -#endif - #define VSYNC_CLK_RATE 19200000 static int pingpong_tearcheck_setup(struct drm_encoder *encoder, struct drm_display_mode *mode) @@ -146,8 +125,6 @@ void mdp5_cmd_encoder_disable(struct drm_encoder *encoder) mdp5_ctl_set_encoder_state(ctl, pipeline, false); mdp5_ctl_commit(ctl, pipeline, mdp_ctl_flush_mask_encoder(intf), true); - bs_set(mdp5_cmd_enc, 0); - mdp5_cmd_enc->enabled = false; } @@ -161,7 +138,6 @@ void mdp5_cmd_encoder_enable(struct drm_encoder *encoder) if (WARN_ON(mdp5_cmd_enc->enabled)) return; - bs_set(mdp5_cmd_enc, 1); if (pingpong_tearcheck_enable(encoder)) return; diff --git a/drivers/gpu/drm/msm/disp/mdp5/mdp5_encoder.c b/drivers/gpu/drm/msm/disp/mdp5/mdp5_encoder.c index f48827283c2b..79d67c495780 100644 --- a/drivers/gpu/drm/msm/disp/mdp5/mdp5_encoder.c +++ b/drivers/gpu/drm/msm/disp/mdp5/mdp5_encoder.c @@ -16,72 +16,9 @@ static struct mdp5_kms *get_kms(struct drm_encoder *encoder) return to_mdp5_kms(to_mdp_kms(priv->kms)); } -#ifdef DOWNSTREAM_CONFIG_MSM_BUS_SCALING -#include <mach/board.h> -#include <mach/msm_bus.h> -#include <mach/msm_bus_board.h> -#define MDP_BUS_VECTOR_ENTRY(ab_val, ib_val) \ - { \ - .src = MSM_BUS_MASTER_MDP_PORT0, \ - .dst = MSM_BUS_SLAVE_EBI_CH0, \ - .ab = (ab_val), \ - .ib = (ib_val), \ - } - -static struct msm_bus_vectors mdp_bus_vectors[] = { - MDP_BUS_VECTOR_ENTRY(0, 0), - MDP_BUS_VECTOR_ENTRY(2000000000, 2000000000), -}; -static struct msm_bus_paths mdp_bus_usecases[] = { { - .num_paths = 1, - .vectors = &mdp_bus_vectors[0], -}, { - .num_paths = 1, - .vectors = &mdp_bus_vectors[1], -} }; -static struct msm_bus_scale_pdata mdp_bus_scale_table = { - .usecase = mdp_bus_usecases, - .num_usecases = ARRAY_SIZE(mdp_bus_usecases), - .name = "mdss_mdp", -}; - -static void bs_init(struct mdp5_encoder *mdp5_encoder) -{ - mdp5_encoder->bsc = msm_bus_scale_register_client( - &mdp_bus_scale_table); - DBG("bus scale client: %08x", mdp5_encoder->bsc); -} - -static void bs_fini(struct mdp5_encoder *mdp5_encoder) -{ - if (mdp5_encoder->bsc) { - msm_bus_scale_unregister_client(mdp5_encoder->bsc); - mdp5_encoder->bsc = 0; - } -} - -static void bs_set(struct mdp5_encoder *mdp5_encoder, int idx) -{ - if (mdp5_encoder->bsc) { - DBG("set bus scaling: %d", idx); - /* HACK: scaling down, and then immediately back up - * seems to leave things broken (underflow).. so - * never disable: - */ - idx = 1; - msm_bus_scale_client_update_request(mdp5_encoder->bsc, idx); - } -} -#else -static void bs_init(struct mdp5_encoder *mdp5_encoder) {} -static void bs_fini(struct mdp5_encoder *mdp5_encoder) {} -static void bs_set(struct mdp5_encoder *mdp5_encoder, int idx) {} -#endif - static void mdp5_encoder_destroy(struct drm_encoder *encoder) { struct mdp5_encoder *mdp5_encoder = to_mdp5_encoder(encoder); - bs_fini(mdp5_encoder); drm_encoder_cleanup(encoder); kfree(mdp5_encoder); } @@ -222,8 +159,6 @@ static void mdp5_vid_encoder_disable(struct drm_encoder *encoder) */ mdp_irq_wait(&mdp5_kms->base, intf2vblank(mixer, intf)); - bs_set(mdp5_encoder, 0); - mdp5_encoder->enabled = false; } @@ -240,7 +175,6 @@ static void mdp5_vid_encoder_enable(struct drm_encoder *encoder) if (WARN_ON(mdp5_encoder->enabled)) return; - bs_set(mdp5_encoder, 1); spin_lock_irqsave(&mdp5_encoder->intf_lock, flags); mdp5_write(mdp5_kms, REG_MDP5_INTF_TIMING_ENGINE_EN(intfn), 1); spin_unlock_irqrestore(&mdp5_encoder->intf_lock, flags); @@ -426,8 +360,6 @@ struct drm_encoder *mdp5_encoder_init(struct drm_device *dev, drm_encoder_helper_add(encoder, &mdp5_encoder_helper_funcs); - bs_init(mdp5_encoder); - return encoder; fail: diff --git a/drivers/gpu/drm/msm/dp/dp_audio.c b/drivers/gpu/drm/msm/dp/dp_audio.c new file mode 100644 index 000000000000..82a8673ab8da --- /dev/null +++ b/drivers/gpu/drm/msm/dp/dp_audio.c @@ -0,0 +1,638 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (c) 2016-2020, The Linux Foundation. All rights reserved. + */ + + +#define pr_fmt(fmt) "[drm-dp] %s: " fmt, __func__ + +#include <linux/of_platform.h> + +#include <drm/drm_dp_helper.h> +#include <drm/drm_edid.h> + +#include "dp_catalog.h" +#include "dp_audio.h" +#include "dp_panel.h" +#include "dp_display.h" + +#define HEADER_BYTE_2_BIT 0 +#define PARITY_BYTE_2_BIT 8 +#define HEADER_BYTE_1_BIT 16 +#define PARITY_BYTE_1_BIT 24 +#define HEADER_BYTE_3_BIT 16 +#define PARITY_BYTE_3_BIT 24 + +struct dp_audio_private { + struct platform_device *audio_pdev; + struct platform_device *pdev; + struct dp_catalog *catalog; + struct dp_panel *panel; + + bool engine_on; + u32 channels; + + struct dp_audio dp_audio; +}; + +static u8 dp_audio_get_g0_value(u8 data) +{ + u8 c[4]; + u8 g[4]; + u8 ret_data = 0; + u8 i; + + for (i = 0; i < 4; i++) + c[i] = (data >> i) & 0x01; + + g[0] = c[3]; + g[1] = c[0] ^ c[3]; + g[2] = c[1]; + g[3] = c[2]; + + for (i = 0; i < 4; i++) + ret_data = ((g[i] & 0x01) << i) | ret_data; + + return ret_data; +} + +static u8 dp_audio_get_g1_value(u8 data) +{ + u8 c[4]; + u8 g[4]; + u8 ret_data = 0; + u8 i; + + for (i = 0; i < 4; i++) + c[i] = (data >> i) & 0x01; + + g[0] = c[0] ^ c[3]; + g[1] = c[0] ^ c[1] ^ c[3]; + g[2] = c[1] ^ c[2]; + g[3] = c[2] ^ c[3]; + + for (i = 0; i < 4; i++) + ret_data = ((g[i] & 0x01) << i) | ret_data; + + return ret_data; +} + +static u8 dp_audio_calculate_parity(u32 data) +{ + u8 x0 = 0; + u8 x1 = 0; + u8 ci = 0; + u8 iData = 0; + u8 i = 0; + u8 parity_byte; + u8 num_byte = (data & 0xFF00) > 0 ? 8 : 2; + + for (i = 0; i < num_byte; i++) { + iData = (data >> i*4) & 0xF; + + ci = iData ^ x1; + x1 = x0 ^ dp_audio_get_g1_value(ci); + x0 = dp_audio_get_g0_value(ci); + } + + parity_byte = x1 | (x0 << 4); + + return parity_byte; +} + +static u32 dp_audio_get_header(struct dp_catalog *catalog, + enum dp_catalog_audio_sdp_type sdp, + enum dp_catalog_audio_header_type header) +{ + catalog->sdp_type = sdp; + catalog->sdp_header = header; + dp_catalog_audio_get_header(catalog); + + return catalog->audio_data; +} + +static void dp_audio_set_header(struct dp_catalog *catalog, + u32 data, + enum dp_catalog_audio_sdp_type sdp, + enum dp_catalog_audio_header_type header) +{ + catalog->sdp_type = sdp; + catalog->sdp_header = header; + catalog->audio_data = data; + dp_catalog_audio_set_header(catalog); +} + +static void dp_audio_stream_sdp(struct dp_audio_private *audio) +{ + struct dp_catalog *catalog = audio->catalog; + u32 value, new_value; + u8 parity_byte; + + /* Config header and parity byte 1 */ + value = dp_audio_get_header(catalog, + DP_AUDIO_SDP_STREAM, DP_AUDIO_SDP_HEADER_1); + + new_value = 0x02; + parity_byte = dp_audio_calculate_parity(new_value); + value |= ((new_value << HEADER_BYTE_1_BIT) + | (parity_byte << PARITY_BYTE_1_BIT)); + DRM_DEBUG_DP("Header Byte 1: value = 0x%x, parity_byte = 0x%x\n", + value, parity_byte); + dp_audio_set_header(catalog, value, + DP_AUDIO_SDP_STREAM, DP_AUDIO_SDP_HEADER_1); + + /* Config header and parity byte 2 */ + value = dp_audio_get_header(catalog, + DP_AUDIO_SDP_STREAM, DP_AUDIO_SDP_HEADER_2); + new_value = value; + parity_byte = dp_audio_calculate_parity(new_value); + value |= ((new_value << HEADER_BYTE_2_BIT) + | (parity_byte << PARITY_BYTE_2_BIT)); + DRM_DEBUG_DP("Header Byte 2: value = 0x%x, parity_byte = 0x%x\n", + value, parity_byte); + + dp_audio_set_header(catalog, value, + DP_AUDIO_SDP_STREAM, DP_AUDIO_SDP_HEADER_2); + + /* Config header and parity byte 3 */ + value = dp_audio_get_header(catalog, + DP_AUDIO_SDP_STREAM, DP_AUDIO_SDP_HEADER_3); + + new_value = audio->channels - 1; + parity_byte = dp_audio_calculate_parity(new_value); + value |= ((new_value << HEADER_BYTE_3_BIT) + | (parity_byte << PARITY_BYTE_3_BIT)); + DRM_DEBUG_DP("Header Byte 3: value = 0x%x, parity_byte = 0x%x\n", + value, parity_byte); + + dp_audio_set_header(catalog, value, + DP_AUDIO_SDP_STREAM, DP_AUDIO_SDP_HEADER_3); +} + +static void dp_audio_timestamp_sdp(struct dp_audio_private *audio) +{ + struct dp_catalog *catalog = audio->catalog; + u32 value, new_value; + u8 parity_byte; + + /* Config header and parity byte 1 */ + value = dp_audio_get_header(catalog, + DP_AUDIO_SDP_TIMESTAMP, DP_AUDIO_SDP_HEADER_1); + + new_value = 0x1; + parity_byte = dp_audio_calculate_parity(new_value); + value |= ((new_value << HEADER_BYTE_1_BIT) + | (parity_byte << PARITY_BYTE_1_BIT)); + DRM_DEBUG_DP("Header Byte 1: value = 0x%x, parity_byte = 0x%x\n", + value, parity_byte); + dp_audio_set_header(catalog, value, + DP_AUDIO_SDP_TIMESTAMP, DP_AUDIO_SDP_HEADER_1); + + /* Config header and parity byte 2 */ + value = dp_audio_get_header(catalog, + DP_AUDIO_SDP_TIMESTAMP, DP_AUDIO_SDP_HEADER_2); + + new_value = 0x17; + parity_byte = dp_audio_calculate_parity(new_value); + value |= ((new_value << HEADER_BYTE_2_BIT) + | (parity_byte << PARITY_BYTE_2_BIT)); + DRM_DEBUG_DP("Header Byte 2: value = 0x%x, parity_byte = 0x%x\n", + value, parity_byte); + dp_audio_set_header(catalog, value, + DP_AUDIO_SDP_TIMESTAMP, DP_AUDIO_SDP_HEADER_2); + + /* Config header and parity byte 3 */ + value = dp_audio_get_header(catalog, + DP_AUDIO_SDP_TIMESTAMP, DP_AUDIO_SDP_HEADER_3); + + new_value = (0x0 | (0x11 << 2)); + parity_byte = dp_audio_calculate_parity(new_value); + value |= ((new_value << HEADER_BYTE_3_BIT) + | (parity_byte << PARITY_BYTE_3_BIT)); + DRM_DEBUG_DP("Header Byte 3: value = 0x%x, parity_byte = 0x%x\n", + value, parity_byte); + dp_audio_set_header(catalog, value, + DP_AUDIO_SDP_TIMESTAMP, DP_AUDIO_SDP_HEADER_3); +} + +static void dp_audio_infoframe_sdp(struct dp_audio_private *audio) +{ + struct dp_catalog *catalog = audio->catalog; + u32 value, new_value; + u8 parity_byte; + + /* Config header and parity byte 1 */ + value = dp_audio_get_header(catalog, + DP_AUDIO_SDP_INFOFRAME, DP_AUDIO_SDP_HEADER_1); + + new_value = 0x84; + parity_byte = dp_audio_calculate_parity(new_value); + value |= ((new_value << HEADER_BYTE_1_BIT) + | (parity_byte << PARITY_BYTE_1_BIT)); + DRM_DEBUG_DP("Header Byte 1: value = 0x%x, parity_byte = 0x%x\n", + value, parity_byte); + dp_audio_set_header(catalog, value, + DP_AUDIO_SDP_INFOFRAME, DP_AUDIO_SDP_HEADER_1); + + /* Config header and parity byte 2 */ + value = dp_audio_get_header(catalog, + DP_AUDIO_SDP_INFOFRAME, DP_AUDIO_SDP_HEADER_2); + + new_value = 0x1b; + parity_byte = dp_audio_calculate_parity(new_value); + value |= ((new_value << HEADER_BYTE_2_BIT) + | (parity_byte << PARITY_BYTE_2_BIT)); + DRM_DEBUG_DP("Header Byte 2: value = 0x%x, parity_byte = 0x%x\n", + value, parity_byte); + dp_audio_set_header(catalog, value, + DP_AUDIO_SDP_INFOFRAME, DP_AUDIO_SDP_HEADER_2); + + /* Config header and parity byte 3 */ + value = dp_audio_get_header(catalog, + DP_AUDIO_SDP_INFOFRAME, DP_AUDIO_SDP_HEADER_3); + + new_value = (0x0 | (0x11 << 2)); + parity_byte = dp_audio_calculate_parity(new_value); + value |= ((new_value << HEADER_BYTE_3_BIT) + | (parity_byte << PARITY_BYTE_3_BIT)); + DRM_DEBUG_DP("Header Byte 3: value = 0x%x, parity_byte = 0x%x\n", + new_value, parity_byte); + dp_audio_set_header(catalog, value, + DP_AUDIO_SDP_INFOFRAME, DP_AUDIO_SDP_HEADER_3); +} + +static void dp_audio_copy_management_sdp(struct dp_audio_private *audio) +{ + struct dp_catalog *catalog = audio->catalog; + u32 value, new_value; + u8 parity_byte; + + /* Config header and parity byte 1 */ + value = dp_audio_get_header(catalog, + DP_AUDIO_SDP_COPYMANAGEMENT, DP_AUDIO_SDP_HEADER_1); + + new_value = 0x05; + parity_byte = dp_audio_calculate_parity(new_value); + value |= ((new_value << HEADER_BYTE_1_BIT) + | (parity_byte << PARITY_BYTE_1_BIT)); + DRM_DEBUG_DP("Header Byte 1: value = 0x%x, parity_byte = 0x%x\n", + value, parity_byte); + dp_audio_set_header(catalog, value, + DP_AUDIO_SDP_COPYMANAGEMENT, DP_AUDIO_SDP_HEADER_1); + + /* Config header and parity byte 2 */ + value = dp_audio_get_header(catalog, + DP_AUDIO_SDP_COPYMANAGEMENT, DP_AUDIO_SDP_HEADER_2); + + new_value = 0x0F; + parity_byte = dp_audio_calculate_parity(new_value); + value |= ((new_value << HEADER_BYTE_2_BIT) + | (parity_byte << PARITY_BYTE_2_BIT)); + DRM_DEBUG_DP("Header Byte 2: value = 0x%x, parity_byte = 0x%x\n", + value, parity_byte); + dp_audio_set_header(catalog, value, + DP_AUDIO_SDP_COPYMANAGEMENT, DP_AUDIO_SDP_HEADER_2); + + /* Config header and parity byte 3 */ + value = dp_audio_get_header(catalog, + DP_AUDIO_SDP_COPYMANAGEMENT, DP_AUDIO_SDP_HEADER_3); + + new_value = 0x0; + parity_byte = dp_audio_calculate_parity(new_value); + value |= ((new_value << HEADER_BYTE_3_BIT) + | (parity_byte << PARITY_BYTE_3_BIT)); + DRM_DEBUG_DP("Header Byte 3: value = 0x%x, parity_byte = 0x%x\n", + value, parity_byte); + dp_audio_set_header(catalog, value, + DP_AUDIO_SDP_COPYMANAGEMENT, DP_AUDIO_SDP_HEADER_3); +} + +static void dp_audio_isrc_sdp(struct dp_audio_private *audio) +{ + struct dp_catalog *catalog = audio->catalog; + u32 value, new_value; + u8 parity_byte; + + /* Config header and parity byte 1 */ + value = dp_audio_get_header(catalog, + DP_AUDIO_SDP_ISRC, DP_AUDIO_SDP_HEADER_1); + + new_value = 0x06; + parity_byte = dp_audio_calculate_parity(new_value); + value |= ((new_value << HEADER_BYTE_1_BIT) + | (parity_byte << PARITY_BYTE_1_BIT)); + DRM_DEBUG_DP("Header Byte 1: value = 0x%x, parity_byte = 0x%x\n", + value, parity_byte); + dp_audio_set_header(catalog, value, + DP_AUDIO_SDP_ISRC, DP_AUDIO_SDP_HEADER_1); + + /* Config header and parity byte 2 */ + value = dp_audio_get_header(catalog, + DP_AUDIO_SDP_ISRC, DP_AUDIO_SDP_HEADER_2); + + new_value = 0x0F; + parity_byte = dp_audio_calculate_parity(new_value); + value |= ((new_value << HEADER_BYTE_2_BIT) + | (parity_byte << PARITY_BYTE_2_BIT)); + DRM_DEBUG_DP("Header Byte 2: value = 0x%x, parity_byte = 0x%x\n", + value, parity_byte); + dp_audio_set_header(catalog, value, + DP_AUDIO_SDP_ISRC, DP_AUDIO_SDP_HEADER_2); +} + +static void dp_audio_setup_sdp(struct dp_audio_private *audio) +{ + dp_catalog_audio_config_sdp(audio->catalog); + + dp_audio_stream_sdp(audio); + dp_audio_timestamp_sdp(audio); + dp_audio_infoframe_sdp(audio); + dp_audio_copy_management_sdp(audio); + dp_audio_isrc_sdp(audio); +} + +static void dp_audio_setup_acr(struct dp_audio_private *audio) +{ + u32 select = 0; + struct dp_catalog *catalog = audio->catalog; + + switch (audio->dp_audio.bw_code) { + case DP_LINK_BW_1_62: + select = 0; + break; + case DP_LINK_BW_2_7: + select = 1; + break; + case DP_LINK_BW_5_4: + select = 2; + break; + case DP_LINK_BW_8_1: + select = 3; + break; + default: + DRM_DEBUG_DP("Unknown link rate\n"); + select = 0; + break; + } + + catalog->audio_data = select; + dp_catalog_audio_config_acr(catalog); +} + +static void dp_audio_safe_to_exit_level(struct dp_audio_private *audio) +{ + struct dp_catalog *catalog = audio->catalog; + u32 safe_to_exit_level = 0; + + switch (audio->dp_audio.lane_count) { + case 1: + safe_to_exit_level = 14; + break; + case 2: + safe_to_exit_level = 8; + break; + case 4: + safe_to_exit_level = 5; + break; + default: + DRM_DEBUG_DP("setting the default safe_to_exit_level = %u\n", + safe_to_exit_level); + safe_to_exit_level = 14; + break; + } + + catalog->audio_data = safe_to_exit_level; + dp_catalog_audio_sfe_level(catalog); +} + +static void dp_audio_enable(struct dp_audio_private *audio, bool enable) +{ + struct dp_catalog *catalog = audio->catalog; + + catalog->audio_data = enable; + dp_catalog_audio_enable(catalog); + + audio->engine_on = enable; +} + +static struct dp_audio_private *dp_audio_get_data(struct platform_device *pdev) +{ + struct dp_audio *dp_audio; + struct msm_dp *dp_display; + + if (!pdev) { + DRM_ERROR("invalid input\n"); + return ERR_PTR(-ENODEV); + } + + dp_display = platform_get_drvdata(pdev); + if (!dp_display) { + DRM_ERROR("invalid input\n"); + return ERR_PTR(-ENODEV); + } + + dp_audio = dp_display->dp_audio; + + if (!dp_audio) { + DRM_ERROR("invalid dp_audio data\n"); + return ERR_PTR(-EINVAL); + } + + return container_of(dp_audio, struct dp_audio_private, dp_audio); +} + +static int dp_audio_hook_plugged_cb(struct device *dev, void *data, + hdmi_codec_plugged_cb fn, + struct device *codec_dev) +{ + + struct platform_device *pdev; + struct msm_dp *dp_display; + + pdev = to_platform_device(dev); + if (!pdev) { + pr_err("invalid input\n"); + return -ENODEV; + } + + dp_display = platform_get_drvdata(pdev); + if (!dp_display) { + pr_err("invalid input\n"); + return -ENODEV; + } + + return dp_display_set_plugged_cb(dp_display, fn, codec_dev); +} + +static int dp_audio_get_eld(struct device *dev, + void *data, uint8_t *buf, size_t len) +{ + struct platform_device *pdev; + struct msm_dp *dp_display; + + pdev = to_platform_device(dev); + + if (!pdev) { + DRM_ERROR("invalid input\n"); + return -ENODEV; + } + + dp_display = platform_get_drvdata(pdev); + if (!dp_display) { + DRM_ERROR("invalid input\n"); + return -ENODEV; + } + + memcpy(buf, dp_display->connector->eld, + min(sizeof(dp_display->connector->eld), len)); + + return 0; +} + +int dp_audio_hw_params(struct device *dev, + void *data, + struct hdmi_codec_daifmt *daifmt, + struct hdmi_codec_params *params) +{ + int rc = 0; + struct dp_audio_private *audio; + struct platform_device *pdev; + struct msm_dp *dp_display; + + pdev = to_platform_device(dev); + dp_display = platform_get_drvdata(pdev); + + /* + * there could be cases where sound card can be opened even + * before OR even when DP is not connected . This can cause + * unclocked access as the audio subsystem relies on the DP + * driver to maintain the correct state of clocks. To protect + * such cases check for connection status and bail out if not + * connected. + */ + if (!dp_display->power_on) { + rc = -EINVAL; + goto end; + } + + audio = dp_audio_get_data(pdev); + if (IS_ERR(audio)) { + rc = PTR_ERR(audio); + goto end; + } + + audio->channels = params->channels; + + dp_audio_setup_sdp(audio); + dp_audio_setup_acr(audio); + dp_audio_safe_to_exit_level(audio); + dp_audio_enable(audio, true); + dp_display->audio_enabled = true; + +end: + return rc; +} + +static void dp_audio_shutdown(struct device *dev, void *data) +{ + struct dp_audio_private *audio; + struct platform_device *pdev; + struct msm_dp *dp_display; + + pdev = to_platform_device(dev); + dp_display = platform_get_drvdata(pdev); + audio = dp_audio_get_data(pdev); + if (IS_ERR(audio)) { + DRM_ERROR("failed to get audio data\n"); + return; + } + + /* + * if audio was not enabled there is no need + * to execute the shutdown and we can bail out early. + * This also makes sure that we dont cause an unclocked + * access when audio subsystem calls this without DP being + * connected. is_connected cannot be used here as its set + * to false earlier than this call + */ + if (!dp_display->audio_enabled) + return; + + dp_audio_enable(audio, false); + /* signal the dp display to safely shutdown clocks */ + dp_display_signal_audio_complete(dp_display); +} + +static const struct hdmi_codec_ops dp_audio_codec_ops = { + .hw_params = dp_audio_hw_params, + .audio_shutdown = dp_audio_shutdown, + .get_eld = dp_audio_get_eld, + .hook_plugged_cb = dp_audio_hook_plugged_cb, +}; + +static struct hdmi_codec_pdata codec_data = { + .ops = &dp_audio_codec_ops, + .max_i2s_channels = 8, + .i2s = 1, +}; + +int dp_register_audio_driver(struct device *dev, + struct dp_audio *dp_audio) +{ + struct dp_audio_private *audio_priv; + + audio_priv = container_of(dp_audio, + struct dp_audio_private, dp_audio); + + audio_priv->audio_pdev = platform_device_register_data(dev, + HDMI_CODEC_DRV_NAME, + PLATFORM_DEVID_AUTO, + &codec_data, + sizeof(codec_data)); + return PTR_ERR_OR_ZERO(audio_priv->audio_pdev); +} + +struct dp_audio *dp_audio_get(struct platform_device *pdev, + struct dp_panel *panel, + struct dp_catalog *catalog) +{ + int rc = 0; + struct dp_audio_private *audio; + struct dp_audio *dp_audio; + + if (!pdev || !panel || !catalog) { + DRM_ERROR("invalid input\n"); + rc = -EINVAL; + goto error; + } + + audio = devm_kzalloc(&pdev->dev, sizeof(*audio), GFP_KERNEL); + if (!audio) { + rc = -ENOMEM; + goto error; + } + + audio->pdev = pdev; + audio->panel = panel; + audio->catalog = catalog; + + dp_audio = &audio->dp_audio; + + dp_catalog_audio_init(catalog); + + return dp_audio; +error: + return ERR_PTR(rc); +} + +void dp_audio_put(struct dp_audio *dp_audio) +{ + struct dp_audio_private *audio; + + if (!dp_audio) + return; + + audio = container_of(dp_audio, struct dp_audio_private, dp_audio); + + devm_kfree(&audio->pdev->dev, audio); +} diff --git a/drivers/gpu/drm/msm/dp/dp_audio.h b/drivers/gpu/drm/msm/dp/dp_audio.h new file mode 100644 index 000000000000..84e5f4a5d26b --- /dev/null +++ b/drivers/gpu/drm/msm/dp/dp_audio.h @@ -0,0 +1,72 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (c) 2017-2020, The Linux Foundation. All rights reserved. + */ + +#ifndef _DP_AUDIO_H_ +#define _DP_AUDIO_H_ + +#include <linux/platform_device.h> + +#include "dp_panel.h" +#include "dp_catalog.h" +#include <sound/hdmi-codec.h> + +/** + * struct dp_audio + * @lane_count: number of lanes configured in current session + * @bw_code: link rate's bandwidth code for current session + */ +struct dp_audio { + u32 lane_count; + u32 bw_code; +}; + +/** + * dp_audio_get() + * + * Creates and instance of dp audio. + * + * @pdev: caller's platform device instance. + * @panel: an instance of dp_panel module. + * @catalog: an instance of dp_catalog module. + * + * Returns the error code in case of failure, otherwize + * an instance of newly created dp_module. + */ +struct dp_audio *dp_audio_get(struct platform_device *pdev, + struct dp_panel *panel, + struct dp_catalog *catalog); + +/** + * dp_register_audio_driver() + * + * Registers DP device with hdmi_codec interface. + * + * @dev: DP device instance. + * @dp_audio: an instance of dp_audio module. + * + * + * Returns the error code in case of failure, otherwise + * zero on success. + */ +int dp_register_audio_driver(struct device *dev, + struct dp_audio *dp_audio); + +/** + * dp_audio_put() + * + * Cleans the dp_audio instance. + * + * @dp_audio: an instance of dp_audio. + */ +void dp_audio_put(struct dp_audio *dp_audio); + +int dp_audio_hw_params(struct device *dev, + void *data, + struct hdmi_codec_daifmt *daifmt, + struct hdmi_codec_params *params); + +#endif /* _DP_AUDIO_H_ */ + + diff --git a/drivers/gpu/drm/msm/dp/dp_aux.c b/drivers/gpu/drm/msm/dp/dp_aux.c new file mode 100644 index 000000000000..19b35ae3e927 --- /dev/null +++ b/drivers/gpu/drm/msm/dp/dp_aux.c @@ -0,0 +1,535 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (c) 2012-2020, The Linux Foundation. All rights reserved. + */ + +#include <linux/delay.h> +#include <drm/drm_print.h> + +#include "dp_reg.h" +#include "dp_aux.h" + +#define DP_AUX_ENUM_STR(x) #x + +struct dp_aux_private { + struct device *dev; + struct dp_catalog *catalog; + + struct mutex mutex; + struct completion comp; + + u32 aux_error_num; + u32 retry_cnt; + bool cmd_busy; + bool native; + bool read; + bool no_send_addr; + bool no_send_stop; + u32 offset; + u32 segment; + u32 isr; + + struct drm_dp_aux dp_aux; +}; + +static const char *dp_aux_get_error(u32 aux_error) +{ + switch (aux_error) { + case DP_AUX_ERR_NONE: + return DP_AUX_ENUM_STR(DP_AUX_ERR_NONE); + case DP_AUX_ERR_ADDR: + return DP_AUX_ENUM_STR(DP_AUX_ERR_ADDR); + case DP_AUX_ERR_TOUT: + return DP_AUX_ENUM_STR(DP_AUX_ERR_TOUT); + case DP_AUX_ERR_NACK: + return DP_AUX_ENUM_STR(DP_AUX_ERR_NACK); + case DP_AUX_ERR_DEFER: + return DP_AUX_ENUM_STR(DP_AUX_ERR_DEFER); + case DP_AUX_ERR_NACK_DEFER: + return DP_AUX_ENUM_STR(DP_AUX_ERR_NACK_DEFER); + default: + return "unknown"; + } +} + +static u32 dp_aux_write(struct dp_aux_private *aux, + struct drm_dp_aux_msg *msg) +{ + u32 data[4], reg, len; + u8 *msgdata = msg->buffer; + int const AUX_CMD_FIFO_LEN = 128; + int i = 0; + + if (aux->read) + len = 4; + else + len = msg->size + 4; + + /* + * cmd fifo only has depth of 144 bytes + * limit buf length to 128 bytes here + */ + if (len > AUX_CMD_FIFO_LEN) { + DRM_ERROR("buf size greater than allowed size of 128 bytes\n"); + return 0; + } + + /* Pack cmd and write to HW */ + data[0] = (msg->address >> 16) & 0xf; /* addr[19:16] */ + if (aux->read) + data[0] |= BIT(4); /* R/W */ + + data[1] = (msg->address >> 8) & 0xff; /* addr[15:8] */ + data[2] = msg->address & 0xff; /* addr[7:0] */ + data[3] = (msg->size - 1) & 0xff; /* len[7:0] */ + + for (i = 0; i < len; i++) { + reg = (i < 4) ? data[i] : msgdata[i - 4]; + /* index = 0, write */ + reg = (((reg) << DP_AUX_DATA_OFFSET) + & DP_AUX_DATA_MASK) | DP_AUX_DATA_WRITE; + if (i == 0) + reg |= DP_AUX_DATA_INDEX_WRITE; + aux->catalog->aux_data = reg; + dp_catalog_aux_write_data(aux->catalog); + } + + dp_catalog_aux_clear_trans(aux->catalog, false); + dp_catalog_aux_clear_hw_interrupts(aux->catalog); + + reg = 0; /* Transaction number == 1 */ + if (!aux->native) { /* i2c */ + reg |= DP_AUX_TRANS_CTRL_I2C; + + if (aux->no_send_addr) + reg |= DP_AUX_TRANS_CTRL_NO_SEND_ADDR; + + if (aux->no_send_stop) + reg |= DP_AUX_TRANS_CTRL_NO_SEND_STOP; + } + + reg |= DP_AUX_TRANS_CTRL_GO; + aux->catalog->aux_data = reg; + dp_catalog_aux_write_trans(aux->catalog); + + return len; +} + +static int dp_aux_cmd_fifo_tx(struct dp_aux_private *aux, + struct drm_dp_aux_msg *msg) +{ + u32 ret, len, timeout; + int aux_timeout_ms = HZ/4; + + reinit_completion(&aux->comp); + + len = dp_aux_write(aux, msg); + if (len == 0) { + DRM_ERROR("DP AUX write failed\n"); + return -EINVAL; + } + + timeout = wait_for_completion_timeout(&aux->comp, aux_timeout_ms); + if (!timeout) { + DRM_ERROR("aux %s timeout\n", (aux->read ? "read" : "write")); + return -ETIMEDOUT; + } + + if (aux->aux_error_num == DP_AUX_ERR_NONE) { + ret = len; + } else { + DRM_ERROR_RATELIMITED("aux err: %s\n", + dp_aux_get_error(aux->aux_error_num)); + + ret = -EINVAL; + } + + return ret; +} + +static void dp_aux_cmd_fifo_rx(struct dp_aux_private *aux, + struct drm_dp_aux_msg *msg) +{ + u32 data; + u8 *dp; + u32 i, actual_i; + u32 len = msg->size; + + dp_catalog_aux_clear_trans(aux->catalog, true); + + data = DP_AUX_DATA_INDEX_WRITE; /* INDEX_WRITE */ + data |= DP_AUX_DATA_READ; /* read */ + + aux->catalog->aux_data = data; + dp_catalog_aux_write_data(aux->catalog); + + dp = msg->buffer; + + /* discard first byte */ + data = dp_catalog_aux_read_data(aux->catalog); + + for (i = 0; i < len; i++) { + data = dp_catalog_aux_read_data(aux->catalog); + *dp++ = (u8)((data >> DP_AUX_DATA_OFFSET) & 0xff); + + actual_i = (data >> DP_AUX_DATA_INDEX_OFFSET) & 0xFF; + if (i != actual_i) + DRM_ERROR("Index mismatch: expected %d, found %d\n", + i, actual_i); + } +} + +static void dp_aux_native_handler(struct dp_aux_private *aux) +{ + u32 isr = aux->isr; + + if (isr & DP_INTR_AUX_I2C_DONE) + aux->aux_error_num = DP_AUX_ERR_NONE; + else if (isr & DP_INTR_WRONG_ADDR) + aux->aux_error_num = DP_AUX_ERR_ADDR; + else if (isr & DP_INTR_TIMEOUT) + aux->aux_error_num = DP_AUX_ERR_TOUT; + if (isr & DP_INTR_NACK_DEFER) + aux->aux_error_num = DP_AUX_ERR_NACK; + if (isr & DP_INTR_AUX_ERROR) { + aux->aux_error_num = DP_AUX_ERR_PHY; + dp_catalog_aux_clear_hw_interrupts(aux->catalog); + } + + complete(&aux->comp); +} + +static void dp_aux_i2c_handler(struct dp_aux_private *aux) +{ + u32 isr = aux->isr; + + if (isr & DP_INTR_AUX_I2C_DONE) { + if (isr & (DP_INTR_I2C_NACK | DP_INTR_I2C_DEFER)) + aux->aux_error_num = DP_AUX_ERR_NACK; + else + aux->aux_error_num = DP_AUX_ERR_NONE; + } else { + if (isr & DP_INTR_WRONG_ADDR) + aux->aux_error_num = DP_AUX_ERR_ADDR; + else if (isr & DP_INTR_TIMEOUT) + aux->aux_error_num = DP_AUX_ERR_TOUT; + if (isr & DP_INTR_NACK_DEFER) + aux->aux_error_num = DP_AUX_ERR_NACK_DEFER; + if (isr & DP_INTR_I2C_NACK) + aux->aux_error_num = DP_AUX_ERR_NACK; + if (isr & DP_INTR_I2C_DEFER) + aux->aux_error_num = DP_AUX_ERR_DEFER; + if (isr & DP_INTR_AUX_ERROR) { + aux->aux_error_num = DP_AUX_ERR_PHY; + dp_catalog_aux_clear_hw_interrupts(aux->catalog); + } + } + + complete(&aux->comp); +} + +static void dp_aux_update_offset_and_segment(struct dp_aux_private *aux, + struct drm_dp_aux_msg *input_msg) +{ + u32 edid_address = 0x50; + u32 segment_address = 0x30; + bool i2c_read = input_msg->request & + (DP_AUX_I2C_READ & DP_AUX_NATIVE_READ); + u8 *data; + + if (aux->native || i2c_read || ((input_msg->address != edid_address) && + (input_msg->address != segment_address))) + return; + + + data = input_msg->buffer; + if (input_msg->address == segment_address) + aux->segment = *data; + else + aux->offset = *data; +} + +/** + * dp_aux_transfer_helper() - helper function for EDID read transactions + * + * @aux: DP AUX private structure + * @input_msg: input message from DRM upstream APIs + * @send_seg: send the segment to sink + * + * return: void + * + * This helper function is used to fix EDID reads for non-compliant + * sinks that do not handle the i2c middle-of-transaction flag correctly. + */ +static void dp_aux_transfer_helper(struct dp_aux_private *aux, + struct drm_dp_aux_msg *input_msg, + bool send_seg) +{ + struct drm_dp_aux_msg helper_msg; + u32 message_size = 0x10; + u32 segment_address = 0x30; + u32 const edid_block_length = 0x80; + bool i2c_mot = input_msg->request & DP_AUX_I2C_MOT; + bool i2c_read = input_msg->request & + (DP_AUX_I2C_READ & DP_AUX_NATIVE_READ); + + if (!i2c_mot || !i2c_read || (input_msg->size == 0)) + return; + + /* + * Sending the segment value and EDID offset will be performed + * from the DRM upstream EDID driver for each block. Avoid + * duplicate AUX transactions related to this while reading the + * first 16 bytes of each block. + */ + if (!(aux->offset % edid_block_length) || !send_seg) + goto end; + + aux->read = false; + aux->cmd_busy = true; + aux->no_send_addr = true; + aux->no_send_stop = true; + + /* + * Send the segment address for every i2c read in which the + * middle-of-tranaction flag is set. This is required to support EDID + * reads of more than 2 blocks as the segment address is reset to 0 + * since we are overriding the middle-of-transaction flag for read + * transactions. + */ + + if (aux->segment) { + memset(&helper_msg, 0, sizeof(helper_msg)); + helper_msg.address = segment_address; + helper_msg.buffer = &aux->segment; + helper_msg.size = 1; + dp_aux_cmd_fifo_tx(aux, &helper_msg); + } + + /* + * Send the offset address for every i2c read in which the + * middle-of-transaction flag is set. This will ensure that the sink + * will update its read pointer and return the correct portion of the + * EDID buffer in the subsequent i2c read trasntion triggered in the + * native AUX transfer function. + */ + memset(&helper_msg, 0, sizeof(helper_msg)); + helper_msg.address = input_msg->address; + helper_msg.buffer = &aux->offset; + helper_msg.size = 1; + dp_aux_cmd_fifo_tx(aux, &helper_msg); + +end: + aux->offset += message_size; + if (aux->offset == 0x80 || aux->offset == 0x100) + aux->segment = 0x0; /* reset segment at end of block */ +} + +/* + * This function does the real job to process an AUX transaction. + * It will call aux_reset() function to reset the AUX channel, + * if the waiting is timeout. + */ +static ssize_t dp_aux_transfer(struct drm_dp_aux *dp_aux, + struct drm_dp_aux_msg *msg) +{ + ssize_t ret; + int const aux_cmd_native_max = 16; + int const aux_cmd_i2c_max = 128; + int const retry_count = 5; + struct dp_aux_private *aux = container_of(dp_aux, + struct dp_aux_private, dp_aux); + + mutex_lock(&aux->mutex); + + aux->native = msg->request & (DP_AUX_NATIVE_WRITE & DP_AUX_NATIVE_READ); + + /* Ignore address only message */ + if ((msg->size == 0) || (msg->buffer == NULL)) { + msg->reply = aux->native ? + DP_AUX_NATIVE_REPLY_ACK : DP_AUX_I2C_REPLY_ACK; + ret = msg->size; + goto unlock_exit; + } + + /* msg sanity check */ + if ((aux->native && (msg->size > aux_cmd_native_max)) || + (msg->size > aux_cmd_i2c_max)) { + DRM_ERROR("%s: invalid msg: size(%zu), request(%x)\n", + __func__, msg->size, msg->request); + ret = -EINVAL; + goto unlock_exit; + } + + dp_aux_update_offset_and_segment(aux, msg); + dp_aux_transfer_helper(aux, msg, true); + + aux->read = msg->request & (DP_AUX_I2C_READ & DP_AUX_NATIVE_READ); + aux->cmd_busy = true; + + if (aux->read) { + aux->no_send_addr = true; + aux->no_send_stop = false; + } else { + aux->no_send_addr = true; + aux->no_send_stop = true; + } + + ret = dp_aux_cmd_fifo_tx(aux, msg); + + if (ret < 0) { + if (aux->native) { + aux->retry_cnt++; + if (!(aux->retry_cnt % retry_count)) + dp_catalog_aux_update_cfg(aux->catalog); + dp_catalog_aux_reset(aux->catalog); + } + usleep_range(400, 500); /* at least 400us to next try */ + goto unlock_exit; + } + + if (aux->aux_error_num == DP_AUX_ERR_NONE) { + if (aux->read) + dp_aux_cmd_fifo_rx(aux, msg); + + msg->reply = aux->native ? + DP_AUX_NATIVE_REPLY_ACK : DP_AUX_I2C_REPLY_ACK; + } else { + /* Reply defer to retry */ + msg->reply = aux->native ? + DP_AUX_NATIVE_REPLY_DEFER : DP_AUX_I2C_REPLY_DEFER; + } + + /* Return requested size for success or retry */ + ret = msg->size; + aux->retry_cnt = 0; + +unlock_exit: + aux->cmd_busy = false; + mutex_unlock(&aux->mutex); + return ret; +} + +void dp_aux_isr(struct drm_dp_aux *dp_aux) +{ + struct dp_aux_private *aux; + + if (!dp_aux) { + DRM_ERROR("invalid input\n"); + return; + } + + aux = container_of(dp_aux, struct dp_aux_private, dp_aux); + + aux->isr = dp_catalog_aux_get_irq(aux->catalog); + + if (!aux->cmd_busy) + return; + + if (aux->native) + dp_aux_native_handler(aux); + else + dp_aux_i2c_handler(aux); +} + +void dp_aux_reconfig(struct drm_dp_aux *dp_aux) +{ + struct dp_aux_private *aux; + + aux = container_of(dp_aux, struct dp_aux_private, dp_aux); + + dp_catalog_aux_update_cfg(aux->catalog); + dp_catalog_aux_reset(aux->catalog); +} + +void dp_aux_init(struct drm_dp_aux *dp_aux) +{ + struct dp_aux_private *aux; + + if (!dp_aux) { + DRM_ERROR("invalid input\n"); + return; + } + + aux = container_of(dp_aux, struct dp_aux_private, dp_aux); + + dp_catalog_aux_enable(aux->catalog, true); + aux->retry_cnt = 0; +} + +void dp_aux_deinit(struct drm_dp_aux *dp_aux) +{ + struct dp_aux_private *aux; + + aux = container_of(dp_aux, struct dp_aux_private, dp_aux); + + dp_catalog_aux_enable(aux->catalog, false); +} + +int dp_aux_register(struct drm_dp_aux *dp_aux) +{ + struct dp_aux_private *aux; + int ret; + + if (!dp_aux) { + DRM_ERROR("invalid input\n"); + return -EINVAL; + } + + aux = container_of(dp_aux, struct dp_aux_private, dp_aux); + + aux->dp_aux.name = "dpu_dp_aux"; + aux->dp_aux.dev = aux->dev; + aux->dp_aux.transfer = dp_aux_transfer; + ret = drm_dp_aux_register(&aux->dp_aux); + if (ret) { + DRM_ERROR("%s: failed to register drm aux: %d\n", __func__, + ret); + return ret; + } + + return 0; +} + +void dp_aux_unregister(struct drm_dp_aux *dp_aux) +{ + drm_dp_aux_unregister(dp_aux); +} + +struct drm_dp_aux *dp_aux_get(struct device *dev, struct dp_catalog *catalog) +{ + struct dp_aux_private *aux; + + if (!catalog) { + DRM_ERROR("invalid input\n"); + return ERR_PTR(-ENODEV); + } + + aux = devm_kzalloc(dev, sizeof(*aux), GFP_KERNEL); + if (!aux) + return ERR_PTR(-ENOMEM); + + init_completion(&aux->comp); + aux->cmd_busy = false; + mutex_init(&aux->mutex); + + aux->dev = dev; + aux->catalog = catalog; + aux->retry_cnt = 0; + + return &aux->dp_aux; +} + +void dp_aux_put(struct drm_dp_aux *dp_aux) +{ + struct dp_aux_private *aux; + + if (!dp_aux) + return; + + aux = container_of(dp_aux, struct dp_aux_private, dp_aux); + + mutex_destroy(&aux->mutex); + + devm_kfree(aux->dev, aux); +} diff --git a/drivers/gpu/drm/msm/dp/dp_aux.h b/drivers/gpu/drm/msm/dp/dp_aux.h new file mode 100644 index 000000000000..f8b8ba919465 --- /dev/null +++ b/drivers/gpu/drm/msm/dp/dp_aux.h @@ -0,0 +1,30 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (c) 2012-2020, The Linux Foundation. All rights reserved. + */ + +#ifndef _DP_AUX_H_ +#define _DP_AUX_H_ + +#include "dp_catalog.h" +#include <drm/drm_dp_helper.h> + +#define DP_AUX_ERR_NONE 0 +#define DP_AUX_ERR_ADDR -1 +#define DP_AUX_ERR_TOUT -2 +#define DP_AUX_ERR_NACK -3 +#define DP_AUX_ERR_DEFER -4 +#define DP_AUX_ERR_NACK_DEFER -5 +#define DP_AUX_ERR_PHY -6 + +int dp_aux_register(struct drm_dp_aux *dp_aux); +void dp_aux_unregister(struct drm_dp_aux *dp_aux); +void dp_aux_isr(struct drm_dp_aux *dp_aux); +void dp_aux_init(struct drm_dp_aux *dp_aux); +void dp_aux_deinit(struct drm_dp_aux *dp_aux); +void dp_aux_reconfig(struct drm_dp_aux *dp_aux); + +struct drm_dp_aux *dp_aux_get(struct device *dev, struct dp_catalog *catalog); +void dp_aux_put(struct drm_dp_aux *aux); + +#endif /*__DP_AUX_H_*/ diff --git a/drivers/gpu/drm/msm/dp/dp_catalog.c b/drivers/gpu/drm/msm/dp/dp_catalog.c new file mode 100644 index 000000000000..b15b4ce4ba35 --- /dev/null +++ b/drivers/gpu/drm/msm/dp/dp_catalog.c @@ -0,0 +1,1019 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (c) 2017-2020, The Linux Foundation. All rights reserved. + */ + +#define pr_fmt(fmt) "[drm-dp] %s: " fmt, __func__ + +#include <linux/rational.h> +#include <linux/delay.h> +#include <linux/iopoll.h> +#include <linux/phy/phy.h> +#include <linux/phy/phy-dp.h> +#include <linux/rational.h> +#include <drm/drm_dp_helper.h> +#include <drm/drm_print.h> + +#include "dp_catalog.h" +#include "dp_reg.h" + +#define POLLING_SLEEP_US 1000 +#define POLLING_TIMEOUT_US 10000 + +#define SCRAMBLER_RESET_COUNT_VALUE 0xFC + +#define DP_INTERRUPT_STATUS_ACK_SHIFT 1 +#define DP_INTERRUPT_STATUS_MASK_SHIFT 2 + +#define MSM_DP_CONTROLLER_AHB_OFFSET 0x0000 +#define MSM_DP_CONTROLLER_AHB_SIZE 0x0200 +#define MSM_DP_CONTROLLER_AUX_OFFSET 0x0200 +#define MSM_DP_CONTROLLER_AUX_SIZE 0x0200 +#define MSM_DP_CONTROLLER_LINK_OFFSET 0x0400 +#define MSM_DP_CONTROLLER_LINK_SIZE 0x0C00 +#define MSM_DP_CONTROLLER_P0_OFFSET 0x1000 +#define MSM_DP_CONTROLLER_P0_SIZE 0x0400 + +#define DP_INTERRUPT_STATUS1 \ + (DP_INTR_AUX_I2C_DONE| \ + DP_INTR_WRONG_ADDR | DP_INTR_TIMEOUT | \ + DP_INTR_NACK_DEFER | DP_INTR_WRONG_DATA_CNT | \ + DP_INTR_I2C_NACK | DP_INTR_I2C_DEFER | \ + DP_INTR_PLL_UNLOCKED | DP_INTR_AUX_ERROR) + +#define DP_INTERRUPT_STATUS1_ACK \ + (DP_INTERRUPT_STATUS1 << DP_INTERRUPT_STATUS_ACK_SHIFT) +#define DP_INTERRUPT_STATUS1_MASK \ + (DP_INTERRUPT_STATUS1 << DP_INTERRUPT_STATUS_MASK_SHIFT) + +#define DP_INTERRUPT_STATUS2 \ + (DP_INTR_READY_FOR_VIDEO | DP_INTR_IDLE_PATTERN_SENT | \ + DP_INTR_FRAME_END | DP_INTR_CRC_UPDATED) + +#define DP_INTERRUPT_STATUS2_ACK \ + (DP_INTERRUPT_STATUS2 << DP_INTERRUPT_STATUS_ACK_SHIFT) +#define DP_INTERRUPT_STATUS2_MASK \ + (DP_INTERRUPT_STATUS2 << DP_INTERRUPT_STATUS_MASK_SHIFT) + +struct dp_catalog_private { + struct device *dev; + struct dp_io *io; + u32 (*audio_map)[DP_AUDIO_SDP_HEADER_MAX]; + struct dp_catalog dp_catalog; + u8 aux_lut_cfg_index[PHY_AUX_CFG_MAX]; +}; + +static inline u32 dp_read_aux(struct dp_catalog_private *catalog, u32 offset) +{ + offset += MSM_DP_CONTROLLER_AUX_OFFSET; + return readl_relaxed(catalog->io->dp_controller.base + offset); +} + +static inline void dp_write_aux(struct dp_catalog_private *catalog, + u32 offset, u32 data) +{ + offset += MSM_DP_CONTROLLER_AUX_OFFSET; + /* + * To make sure aux reg writes happens before any other operation, + * this function uses writel() instread of writel_relaxed() + */ + writel(data, catalog->io->dp_controller.base + offset); +} + +static inline u32 dp_read_ahb(struct dp_catalog_private *catalog, u32 offset) +{ + offset += MSM_DP_CONTROLLER_AHB_OFFSET; + return readl_relaxed(catalog->io->dp_controller.base + offset); +} + +static inline void dp_write_ahb(struct dp_catalog_private *catalog, + u32 offset, u32 data) +{ + offset += MSM_DP_CONTROLLER_AHB_OFFSET; + /* + * To make sure phy reg writes happens before any other operation, + * this function uses writel() instread of writel_relaxed() + */ + writel(data, catalog->io->dp_controller.base + offset); +} + +static inline void dp_write_p0(struct dp_catalog_private *catalog, + u32 offset, u32 data) +{ + offset += MSM_DP_CONTROLLER_P0_OFFSET; + /* + * To make sure interface reg writes happens before any other operation, + * this function uses writel() instread of writel_relaxed() + */ + writel(data, catalog->io->dp_controller.base + offset); +} + +static inline u32 dp_read_p0(struct dp_catalog_private *catalog, + u32 offset) +{ + offset += MSM_DP_CONTROLLER_P0_OFFSET; + /* + * To make sure interface reg writes happens before any other operation, + * this function uses writel() instread of writel_relaxed() + */ + return readl_relaxed(catalog->io->dp_controller.base + offset); +} + +static inline u32 dp_read_link(struct dp_catalog_private *catalog, u32 offset) +{ + offset += MSM_DP_CONTROLLER_LINK_OFFSET; + return readl_relaxed(catalog->io->dp_controller.base + offset); +} + +static inline void dp_write_link(struct dp_catalog_private *catalog, + u32 offset, u32 data) +{ + offset += MSM_DP_CONTROLLER_LINK_OFFSET; + /* + * To make sure link reg writes happens before any other operation, + * this function uses writel() instread of writel_relaxed() + */ + writel(data, catalog->io->dp_controller.base + offset); +} + +/* aux related catalog functions */ +u32 dp_catalog_aux_read_data(struct dp_catalog *dp_catalog) +{ + struct dp_catalog_private *catalog = container_of(dp_catalog, + struct dp_catalog_private, dp_catalog); + + return dp_read_aux(catalog, REG_DP_AUX_DATA); +} + +int dp_catalog_aux_write_data(struct dp_catalog *dp_catalog) +{ + struct dp_catalog_private *catalog = container_of(dp_catalog, + struct dp_catalog_private, dp_catalog); + + dp_write_aux(catalog, REG_DP_AUX_DATA, dp_catalog->aux_data); + return 0; +} + +int dp_catalog_aux_write_trans(struct dp_catalog *dp_catalog) +{ + struct dp_catalog_private *catalog = container_of(dp_catalog, + struct dp_catalog_private, dp_catalog); + + dp_write_aux(catalog, REG_DP_AUX_TRANS_CTRL, dp_catalog->aux_data); + return 0; +} + +int dp_catalog_aux_clear_trans(struct dp_catalog *dp_catalog, bool read) +{ + u32 data; + struct dp_catalog_private *catalog = container_of(dp_catalog, + struct dp_catalog_private, dp_catalog); + + if (read) { + data = dp_read_aux(catalog, REG_DP_AUX_TRANS_CTRL); + data &= ~DP_AUX_TRANS_CTRL_GO; + dp_write_aux(catalog, REG_DP_AUX_TRANS_CTRL, data); + } else { + dp_write_aux(catalog, REG_DP_AUX_TRANS_CTRL, 0); + } + return 0; +} + +int dp_catalog_aux_clear_hw_interrupts(struct dp_catalog *dp_catalog) +{ + struct dp_catalog_private *catalog = container_of(dp_catalog, + struct dp_catalog_private, dp_catalog); + + dp_read_aux(catalog, REG_DP_PHY_AUX_INTERRUPT_STATUS); + dp_write_aux(catalog, REG_DP_PHY_AUX_INTERRUPT_CLEAR, 0x1f); + dp_write_aux(catalog, REG_DP_PHY_AUX_INTERRUPT_CLEAR, 0x9f); + dp_write_aux(catalog, REG_DP_PHY_AUX_INTERRUPT_CLEAR, 0); + return 0; +} + +void dp_catalog_aux_reset(struct dp_catalog *dp_catalog) +{ + u32 aux_ctrl; + struct dp_catalog_private *catalog = container_of(dp_catalog, + struct dp_catalog_private, dp_catalog); + + aux_ctrl = dp_read_aux(catalog, REG_DP_AUX_CTRL); + + aux_ctrl |= DP_AUX_CTRL_RESET; + dp_write_aux(catalog, REG_DP_AUX_CTRL, aux_ctrl); + usleep_range(1000, 1100); /* h/w recommended delay */ + + aux_ctrl &= ~DP_AUX_CTRL_RESET; + dp_write_aux(catalog, REG_DP_AUX_CTRL, aux_ctrl); +} + +void dp_catalog_aux_enable(struct dp_catalog *dp_catalog, bool enable) +{ + u32 aux_ctrl; + struct dp_catalog_private *catalog = container_of(dp_catalog, + struct dp_catalog_private, dp_catalog); + + aux_ctrl = dp_read_aux(catalog, REG_DP_AUX_CTRL); + + if (enable) { + dp_write_aux(catalog, REG_DP_TIMEOUT_COUNT, 0xffff); + dp_write_aux(catalog, REG_DP_AUX_LIMITS, 0xffff); + aux_ctrl |= DP_AUX_CTRL_ENABLE; + } else { + aux_ctrl &= ~DP_AUX_CTRL_ENABLE; + } + + dp_write_aux(catalog, REG_DP_AUX_CTRL, aux_ctrl); +} + +void dp_catalog_aux_update_cfg(struct dp_catalog *dp_catalog) +{ + struct dp_catalog_private *catalog = container_of(dp_catalog, + struct dp_catalog_private, dp_catalog); + struct dp_io *dp_io = catalog->io; + struct phy *phy = dp_io->phy; + + phy_calibrate(phy); +} + +static void dump_regs(void __iomem *base, int len) +{ + int i; + u32 x0, x4, x8, xc; + u32 addr_off = 0; + + len = DIV_ROUND_UP(len, 16); + for (i = 0; i < len; i++) { + x0 = readl_relaxed(base + addr_off); + x4 = readl_relaxed(base + addr_off + 0x04); + x8 = readl_relaxed(base + addr_off + 0x08); + xc = readl_relaxed(base + addr_off + 0x0c); + + pr_info("%08x: %08x %08x %08x %08x", addr_off, x0, x4, x8, xc); + addr_off += 16; + } +} + +void dp_catalog_dump_regs(struct dp_catalog *dp_catalog) +{ + u32 offset, len; + struct dp_catalog_private *catalog = container_of(dp_catalog, + struct dp_catalog_private, dp_catalog); + + pr_info("AHB regs\n"); + offset = MSM_DP_CONTROLLER_AHB_OFFSET; + len = MSM_DP_CONTROLLER_AHB_SIZE; + dump_regs(catalog->io->dp_controller.base + offset, len); + + pr_info("AUXCLK regs\n"); + offset = MSM_DP_CONTROLLER_AUX_OFFSET; + len = MSM_DP_CONTROLLER_AUX_SIZE; + dump_regs(catalog->io->dp_controller.base + offset, len); + + pr_info("LCLK regs\n"); + offset = MSM_DP_CONTROLLER_LINK_OFFSET; + len = MSM_DP_CONTROLLER_LINK_SIZE; + dump_regs(catalog->io->dp_controller.base + offset, len); + + pr_info("P0CLK regs\n"); + offset = MSM_DP_CONTROLLER_P0_OFFSET; + len = MSM_DP_CONTROLLER_P0_SIZE; + dump_regs(catalog->io->dp_controller.base + offset, len); +} + +int dp_catalog_aux_get_irq(struct dp_catalog *dp_catalog) +{ + struct dp_catalog_private *catalog = container_of(dp_catalog, + struct dp_catalog_private, dp_catalog); + u32 intr, intr_ack; + + intr = dp_read_ahb(catalog, REG_DP_INTR_STATUS); + intr &= ~DP_INTERRUPT_STATUS1_MASK; + intr_ack = (intr & DP_INTERRUPT_STATUS1) + << DP_INTERRUPT_STATUS_ACK_SHIFT; + dp_write_ahb(catalog, REG_DP_INTR_STATUS, intr_ack | + DP_INTERRUPT_STATUS1_MASK); + + return intr; + +} + +/* controller related catalog functions */ +void dp_catalog_ctrl_update_transfer_unit(struct dp_catalog *dp_catalog, + u32 dp_tu, u32 valid_boundary, + u32 valid_boundary2) +{ + struct dp_catalog_private *catalog = container_of(dp_catalog, + struct dp_catalog_private, dp_catalog); + + dp_write_link(catalog, REG_DP_VALID_BOUNDARY, valid_boundary); + dp_write_link(catalog, REG_DP_TU, dp_tu); + dp_write_link(catalog, REG_DP_VALID_BOUNDARY_2, valid_boundary2); +} + +void dp_catalog_ctrl_state_ctrl(struct dp_catalog *dp_catalog, u32 state) +{ + struct dp_catalog_private *catalog = container_of(dp_catalog, + struct dp_catalog_private, dp_catalog); + + dp_write_link(catalog, REG_DP_STATE_CTRL, state); +} + +void dp_catalog_ctrl_config_ctrl(struct dp_catalog *dp_catalog, u32 cfg) +{ + struct dp_catalog_private *catalog = container_of(dp_catalog, + struct dp_catalog_private, dp_catalog); + + DRM_DEBUG_DP("DP_CONFIGURATION_CTRL=0x%x\n", cfg); + + dp_write_link(catalog, REG_DP_CONFIGURATION_CTRL, cfg); +} + +void dp_catalog_ctrl_lane_mapping(struct dp_catalog *dp_catalog) +{ + struct dp_catalog_private *catalog = container_of(dp_catalog, + struct dp_catalog_private, dp_catalog); + u32 ln_0 = 0, ln_1 = 1, ln_2 = 2, ln_3 = 3; /* One-to-One mapping */ + u32 ln_mapping; + + ln_mapping = ln_0 << LANE0_MAPPING_SHIFT; + ln_mapping |= ln_1 << LANE1_MAPPING_SHIFT; + ln_mapping |= ln_2 << LANE2_MAPPING_SHIFT; + ln_mapping |= ln_3 << LANE3_MAPPING_SHIFT; + + dp_write_link(catalog, REG_DP_LOGICAL2PHYSICAL_LANE_MAPPING, + ln_mapping); +} + +void dp_catalog_ctrl_mainlink_ctrl(struct dp_catalog *dp_catalog, + bool enable) +{ + u32 mainlink_ctrl; + struct dp_catalog_private *catalog = container_of(dp_catalog, + struct dp_catalog_private, dp_catalog); + + if (enable) { + /* + * To make sure link reg writes happens before other operation, + * dp_write_link() function uses writel() + */ + mainlink_ctrl = dp_read_link(catalog, REG_DP_MAINLINK_CTRL); + + mainlink_ctrl &= ~(DP_MAINLINK_CTRL_RESET | + DP_MAINLINK_CTRL_ENABLE); + dp_write_link(catalog, REG_DP_MAINLINK_CTRL, mainlink_ctrl); + + mainlink_ctrl |= DP_MAINLINK_CTRL_RESET; + dp_write_link(catalog, REG_DP_MAINLINK_CTRL, mainlink_ctrl); + + mainlink_ctrl &= ~DP_MAINLINK_CTRL_RESET; + dp_write_link(catalog, REG_DP_MAINLINK_CTRL, mainlink_ctrl); + + mainlink_ctrl |= (DP_MAINLINK_CTRL_ENABLE | + DP_MAINLINK_FB_BOUNDARY_SEL); + dp_write_link(catalog, REG_DP_MAINLINK_CTRL, mainlink_ctrl); + } else { + mainlink_ctrl = dp_read_link(catalog, REG_DP_MAINLINK_CTRL); + mainlink_ctrl &= ~DP_MAINLINK_CTRL_ENABLE; + dp_write_link(catalog, REG_DP_MAINLINK_CTRL, mainlink_ctrl); + } +} + +void dp_catalog_ctrl_config_misc(struct dp_catalog *dp_catalog, + u32 colorimetry_cfg, + u32 test_bits_depth) +{ + u32 misc_val; + struct dp_catalog_private *catalog = container_of(dp_catalog, + struct dp_catalog_private, dp_catalog); + + misc_val = dp_read_link(catalog, REG_DP_MISC1_MISC0); + + /* clear bpp bits */ + misc_val &= ~(0x07 << DP_MISC0_TEST_BITS_DEPTH_SHIFT); + misc_val |= colorimetry_cfg << DP_MISC0_COLORIMETRY_CFG_SHIFT; + misc_val |= test_bits_depth << DP_MISC0_TEST_BITS_DEPTH_SHIFT; + /* Configure clock to synchronous mode */ + misc_val |= DP_MISC0_SYNCHRONOUS_CLK; + + DRM_DEBUG_DP("misc settings = 0x%x\n", misc_val); + dp_write_link(catalog, REG_DP_MISC1_MISC0, misc_val); +} + +void dp_catalog_ctrl_config_msa(struct dp_catalog *dp_catalog, + u32 rate, u32 stream_rate_khz, + bool fixed_nvid) +{ + u32 pixel_m, pixel_n; + u32 mvid, nvid, pixel_div = 0, dispcc_input_rate; + u32 const nvid_fixed = DP_LINK_CONSTANT_N_VALUE; + u32 const link_rate_hbr2 = 540000; + u32 const link_rate_hbr3 = 810000; + unsigned long den, num; + + struct dp_catalog_private *catalog = container_of(dp_catalog, + struct dp_catalog_private, dp_catalog); + + if (rate == link_rate_hbr3) + pixel_div = 6; + else if (rate == 1620000 || rate == 270000) + pixel_div = 2; + else if (rate == link_rate_hbr2) + pixel_div = 4; + else + DRM_ERROR("Invalid pixel mux divider\n"); + + dispcc_input_rate = (rate * 10) / pixel_div; + + rational_best_approximation(dispcc_input_rate, stream_rate_khz, + (unsigned long)(1 << 16) - 1, + (unsigned long)(1 << 16) - 1, &den, &num); + + den = ~(den - num); + den = den & 0xFFFF; + pixel_m = num; + pixel_n = den; + + mvid = (pixel_m & 0xFFFF) * 5; + nvid = (0xFFFF & (~pixel_n)) + (pixel_m & 0xFFFF); + + if (nvid < nvid_fixed) { + u32 temp; + + temp = (nvid_fixed / nvid) * nvid; + mvid = (nvid_fixed / nvid) * mvid; + nvid = temp; + } + + if (link_rate_hbr2 == rate) + nvid *= 2; + + if (link_rate_hbr3 == rate) + nvid *= 3; + + DRM_DEBUG_DP("mvid=0x%x, nvid=0x%x\n", mvid, nvid); + dp_write_link(catalog, REG_DP_SOFTWARE_MVID, mvid); + dp_write_link(catalog, REG_DP_SOFTWARE_NVID, nvid); + dp_write_p0(catalog, MMSS_DP_DSC_DTO, 0x0); +} + +int dp_catalog_ctrl_set_pattern(struct dp_catalog *dp_catalog, + u32 pattern) +{ + int bit, ret; + u32 data; + struct dp_catalog_private *catalog = container_of(dp_catalog, + struct dp_catalog_private, dp_catalog); + + bit = BIT(pattern - 1); + DRM_DEBUG_DP("hw: bit=%d train=%d\n", bit, pattern); + dp_catalog_ctrl_state_ctrl(dp_catalog, bit); + + bit = BIT(pattern - 1) << DP_MAINLINK_READY_LINK_TRAINING_SHIFT; + + /* Poll for mainlink ready status */ + ret = readx_poll_timeout(readl, catalog->io->dp_controller.base + + MSM_DP_CONTROLLER_LINK_OFFSET + + REG_DP_MAINLINK_READY, + data, data & bit, + POLLING_SLEEP_US, POLLING_TIMEOUT_US); + if (ret < 0) { + DRM_ERROR("set pattern for link_train=%d failed\n", pattern); + return ret; + } + return 0; +} + +void dp_catalog_ctrl_reset(struct dp_catalog *dp_catalog) +{ + u32 sw_reset; + struct dp_catalog_private *catalog = container_of(dp_catalog, + struct dp_catalog_private, dp_catalog); + + sw_reset = dp_read_ahb(catalog, REG_DP_SW_RESET); + + sw_reset |= DP_SW_RESET; + dp_write_ahb(catalog, REG_DP_SW_RESET, sw_reset); + usleep_range(1000, 1100); /* h/w recommended delay */ + + sw_reset &= ~DP_SW_RESET; + dp_write_ahb(catalog, REG_DP_SW_RESET, sw_reset); +} + +bool dp_catalog_ctrl_mainlink_ready(struct dp_catalog *dp_catalog) +{ + u32 data; + int ret; + struct dp_catalog_private *catalog = container_of(dp_catalog, + struct dp_catalog_private, dp_catalog); + + /* Poll for mainlink ready status */ + ret = readl_poll_timeout(catalog->io->dp_controller.base + + MSM_DP_CONTROLLER_LINK_OFFSET + + REG_DP_MAINLINK_READY, + data, data & DP_MAINLINK_READY_FOR_VIDEO, + POLLING_SLEEP_US, POLLING_TIMEOUT_US); + if (ret < 0) { + DRM_ERROR("mainlink not ready\n"); + return false; + } + + return true; +} + +void dp_catalog_ctrl_enable_irq(struct dp_catalog *dp_catalog, + bool enable) +{ + struct dp_catalog_private *catalog = container_of(dp_catalog, + struct dp_catalog_private, dp_catalog); + + if (enable) { + dp_write_ahb(catalog, REG_DP_INTR_STATUS, + DP_INTERRUPT_STATUS1_MASK); + dp_write_ahb(catalog, REG_DP_INTR_STATUS2, + DP_INTERRUPT_STATUS2_MASK); + } else { + dp_write_ahb(catalog, REG_DP_INTR_STATUS, 0x00); + dp_write_ahb(catalog, REG_DP_INTR_STATUS2, 0x00); + } +} + +void dp_catalog_hpd_config_intr(struct dp_catalog *dp_catalog, + u32 intr_mask, bool en) +{ + struct dp_catalog_private *catalog = container_of(dp_catalog, + struct dp_catalog_private, dp_catalog); + + u32 config = dp_read_aux(catalog, REG_DP_DP_HPD_INT_MASK); + + config = (en ? config | intr_mask : config & ~intr_mask); + + dp_write_aux(catalog, REG_DP_DP_HPD_INT_MASK, + config & DP_DP_HPD_INT_MASK); +} + +void dp_catalog_ctrl_hpd_config(struct dp_catalog *dp_catalog) +{ + struct dp_catalog_private *catalog = container_of(dp_catalog, + struct dp_catalog_private, dp_catalog); + + u32 reftimer = dp_read_aux(catalog, REG_DP_DP_HPD_REFTIMER); + + /* enable HPD interrupts */ + dp_catalog_hpd_config_intr(dp_catalog, + DP_DP_HPD_PLUG_INT_MASK | DP_DP_IRQ_HPD_INT_MASK + | DP_DP_HPD_UNPLUG_INT_MASK | DP_DP_HPD_REPLUG_INT_MASK, true); + + /* Configure REFTIMER and enable it */ + reftimer |= DP_DP_HPD_REFTIMER_ENABLE; + dp_write_aux(catalog, REG_DP_DP_HPD_REFTIMER, reftimer); + + /* Enable HPD */ + dp_write_aux(catalog, REG_DP_DP_HPD_CTRL, DP_DP_HPD_CTRL_HPD_EN); +} + +u32 dp_catalog_hpd_get_intr_status(struct dp_catalog *dp_catalog) +{ + struct dp_catalog_private *catalog = container_of(dp_catalog, + struct dp_catalog_private, dp_catalog); + int isr = 0; + + isr = dp_read_aux(catalog, REG_DP_DP_HPD_INT_STATUS); + dp_write_aux(catalog, REG_DP_DP_HPD_INT_ACK, + (isr & DP_DP_HPD_INT_MASK)); + + return isr; +} + +int dp_catalog_ctrl_get_interrupt(struct dp_catalog *dp_catalog) +{ + struct dp_catalog_private *catalog = container_of(dp_catalog, + struct dp_catalog_private, dp_catalog); + u32 intr, intr_ack; + + intr = dp_read_ahb(catalog, REG_DP_INTR_STATUS2); + intr &= ~DP_INTERRUPT_STATUS2_MASK; + intr_ack = (intr & DP_INTERRUPT_STATUS2) + << DP_INTERRUPT_STATUS_ACK_SHIFT; + dp_write_ahb(catalog, REG_DP_INTR_STATUS2, + intr_ack | DP_INTERRUPT_STATUS2_MASK); + + return intr; +} + +void dp_catalog_ctrl_phy_reset(struct dp_catalog *dp_catalog) +{ + struct dp_catalog_private *catalog = container_of(dp_catalog, + struct dp_catalog_private, dp_catalog); + + dp_write_ahb(catalog, REG_DP_PHY_CTRL, + DP_PHY_CTRL_SW_RESET | DP_PHY_CTRL_SW_RESET_PLL); + usleep_range(1000, 1100); /* h/w recommended delay */ + dp_write_ahb(catalog, REG_DP_PHY_CTRL, 0x0); +} + +int dp_catalog_ctrl_update_vx_px(struct dp_catalog *dp_catalog, + u8 v_level, u8 p_level) +{ + struct dp_catalog_private *catalog = container_of(dp_catalog, + struct dp_catalog_private, dp_catalog); + struct dp_io *dp_io = catalog->io; + struct phy *phy = dp_io->phy; + struct phy_configure_opts_dp *opts_dp = &dp_io->phy_opts.dp; + + /* TODO: Update for all lanes instead of just first one */ + opts_dp->voltage[0] = v_level; + opts_dp->pre[0] = p_level; + opts_dp->set_voltages = 1; + phy_configure(phy, &dp_io->phy_opts); + opts_dp->set_voltages = 0; + + return 0; +} + +void dp_catalog_ctrl_send_phy_pattern(struct dp_catalog *dp_catalog, + u32 pattern) +{ + struct dp_catalog_private *catalog = container_of(dp_catalog, + struct dp_catalog_private, dp_catalog); + u32 value = 0x0; + + /* Make sure to clear the current pattern before starting a new one */ + dp_write_link(catalog, REG_DP_STATE_CTRL, 0x0); + + switch (pattern) { + case DP_PHY_TEST_PATTERN_D10_2: + dp_write_link(catalog, REG_DP_STATE_CTRL, + DP_STATE_CTRL_LINK_TRAINING_PATTERN1); + break; + case DP_PHY_TEST_PATTERN_ERROR_COUNT: + value &= ~(1 << 16); + dp_write_link(catalog, REG_DP_HBR2_COMPLIANCE_SCRAMBLER_RESET, + value); + value |= SCRAMBLER_RESET_COUNT_VALUE; + dp_write_link(catalog, REG_DP_HBR2_COMPLIANCE_SCRAMBLER_RESET, + value); + dp_write_link(catalog, REG_DP_MAINLINK_LEVELS, + DP_MAINLINK_SAFE_TO_EXIT_LEVEL_2); + dp_write_link(catalog, REG_DP_STATE_CTRL, + DP_STATE_CTRL_LINK_SYMBOL_ERR_MEASURE); + break; + case DP_PHY_TEST_PATTERN_PRBS7: + dp_write_link(catalog, REG_DP_STATE_CTRL, + DP_STATE_CTRL_LINK_PRBS7); + break; + case DP_PHY_TEST_PATTERN_80BIT_CUSTOM: + dp_write_link(catalog, REG_DP_STATE_CTRL, + DP_STATE_CTRL_LINK_TEST_CUSTOM_PATTERN); + /* 00111110000011111000001111100000 */ + dp_write_link(catalog, REG_DP_TEST_80BIT_CUSTOM_PATTERN_REG0, + 0x3E0F83E0); + /* 00001111100000111110000011111000 */ + dp_write_link(catalog, REG_DP_TEST_80BIT_CUSTOM_PATTERN_REG1, + 0x0F83E0F8); + /* 1111100000111110 */ + dp_write_link(catalog, REG_DP_TEST_80BIT_CUSTOM_PATTERN_REG2, + 0x0000F83E); + break; + case DP_PHY_TEST_PATTERN_CP2520: + value = dp_read_link(catalog, REG_DP_MAINLINK_CTRL); + value &= ~DP_MAINLINK_CTRL_SW_BYPASS_SCRAMBLER; + dp_write_link(catalog, REG_DP_MAINLINK_CTRL, value); + + value = DP_HBR2_ERM_PATTERN; + dp_write_link(catalog, REG_DP_HBR2_COMPLIANCE_SCRAMBLER_RESET, + value); + value |= SCRAMBLER_RESET_COUNT_VALUE; + dp_write_link(catalog, REG_DP_HBR2_COMPLIANCE_SCRAMBLER_RESET, + value); + dp_write_link(catalog, REG_DP_MAINLINK_LEVELS, + DP_MAINLINK_SAFE_TO_EXIT_LEVEL_2); + dp_write_link(catalog, REG_DP_STATE_CTRL, + DP_STATE_CTRL_LINK_SYMBOL_ERR_MEASURE); + value = dp_read_link(catalog, REG_DP_MAINLINK_CTRL); + value |= DP_MAINLINK_CTRL_ENABLE; + dp_write_link(catalog, REG_DP_MAINLINK_CTRL, value); + break; + case DP_PHY_TEST_PATTERN_SEL_MASK: + dp_write_link(catalog, REG_DP_MAINLINK_CTRL, + DP_MAINLINK_CTRL_ENABLE); + dp_write_link(catalog, REG_DP_STATE_CTRL, + DP_STATE_CTRL_LINK_TRAINING_PATTERN4); + break; + default: + DRM_DEBUG_DP("No valid test pattern requested:0x%x\n", pattern); + break; + } +} + +u32 dp_catalog_ctrl_read_phy_pattern(struct dp_catalog *dp_catalog) +{ + struct dp_catalog_private *catalog = container_of(dp_catalog, + struct dp_catalog_private, dp_catalog); + + return dp_read_link(catalog, REG_DP_MAINLINK_READY); +} + +/* panel related catalog functions */ +int dp_catalog_panel_timing_cfg(struct dp_catalog *dp_catalog) +{ + struct dp_catalog_private *catalog = container_of(dp_catalog, + struct dp_catalog_private, dp_catalog); + + dp_write_link(catalog, REG_DP_TOTAL_HOR_VER, + dp_catalog->total); + dp_write_link(catalog, REG_DP_START_HOR_VER_FROM_SYNC, + dp_catalog->sync_start); + dp_write_link(catalog, REG_DP_HSYNC_VSYNC_WIDTH_POLARITY, + dp_catalog->width_blanking); + dp_write_link(catalog, REG_DP_ACTIVE_HOR_VER, dp_catalog->dp_active); + return 0; +} + +void dp_catalog_panel_tpg_enable(struct dp_catalog *dp_catalog, + struct drm_display_mode *drm_mode) +{ + struct dp_catalog_private *catalog = container_of(dp_catalog, + struct dp_catalog_private, dp_catalog); + u32 hsync_period, vsync_period; + u32 display_v_start, display_v_end; + u32 hsync_start_x, hsync_end_x; + u32 v_sync_width; + u32 hsync_ctl; + u32 display_hctl; + + /* TPG config parameters*/ + hsync_period = drm_mode->htotal; + vsync_period = drm_mode->vtotal; + + display_v_start = ((drm_mode->vtotal - drm_mode->vsync_start) * + hsync_period); + display_v_end = ((vsync_period - (drm_mode->vsync_start - + drm_mode->vdisplay)) + * hsync_period) - 1; + + display_v_start += drm_mode->htotal - drm_mode->hsync_start; + display_v_end -= (drm_mode->hsync_start - drm_mode->hdisplay); + + hsync_start_x = drm_mode->htotal - drm_mode->hsync_start; + hsync_end_x = hsync_period - (drm_mode->hsync_start - + drm_mode->hdisplay) - 1; + + v_sync_width = drm_mode->vsync_end - drm_mode->vsync_start; + + hsync_ctl = (hsync_period << 16) | + (drm_mode->hsync_end - drm_mode->hsync_start); + display_hctl = (hsync_end_x << 16) | hsync_start_x; + + + dp_write_p0(catalog, MMSS_DP_INTF_CONFIG, 0x0); + dp_write_p0(catalog, MMSS_DP_INTF_HSYNC_CTL, hsync_ctl); + dp_write_p0(catalog, MMSS_DP_INTF_VSYNC_PERIOD_F0, vsync_period * + hsync_period); + dp_write_p0(catalog, MMSS_DP_INTF_VSYNC_PULSE_WIDTH_F0, v_sync_width * + hsync_period); + dp_write_p0(catalog, MMSS_DP_INTF_VSYNC_PERIOD_F1, 0); + dp_write_p0(catalog, MMSS_DP_INTF_VSYNC_PULSE_WIDTH_F1, 0); + dp_write_p0(catalog, MMSS_DP_INTF_DISPLAY_HCTL, display_hctl); + dp_write_p0(catalog, MMSS_DP_INTF_ACTIVE_HCTL, 0); + dp_write_p0(catalog, MMSS_INTF_DISPLAY_V_START_F0, display_v_start); + dp_write_p0(catalog, MMSS_DP_INTF_DISPLAY_V_END_F0, display_v_end); + dp_write_p0(catalog, MMSS_INTF_DISPLAY_V_START_F1, 0); + dp_write_p0(catalog, MMSS_DP_INTF_DISPLAY_V_END_F1, 0); + dp_write_p0(catalog, MMSS_DP_INTF_ACTIVE_V_START_F0, 0); + dp_write_p0(catalog, MMSS_DP_INTF_ACTIVE_V_END_F0, 0); + dp_write_p0(catalog, MMSS_DP_INTF_ACTIVE_V_START_F1, 0); + dp_write_p0(catalog, MMSS_DP_INTF_ACTIVE_V_END_F1, 0); + dp_write_p0(catalog, MMSS_DP_INTF_POLARITY_CTL, 0); + + dp_write_p0(catalog, MMSS_DP_TPG_MAIN_CONTROL, + DP_TPG_CHECKERED_RECT_PATTERN); + dp_write_p0(catalog, MMSS_DP_TPG_VIDEO_CONFIG, + DP_TPG_VIDEO_CONFIG_BPP_8BIT | + DP_TPG_VIDEO_CONFIG_RGB); + dp_write_p0(catalog, MMSS_DP_BIST_ENABLE, + DP_BIST_ENABLE_DPBIST_EN); + dp_write_p0(catalog, MMSS_DP_TIMING_ENGINE_EN, + DP_TIMING_ENGINE_EN_EN); + DRM_DEBUG_DP("%s: enabled tpg\n", __func__); +} + +void dp_catalog_panel_tpg_disable(struct dp_catalog *dp_catalog) +{ + struct dp_catalog_private *catalog = container_of(dp_catalog, + struct dp_catalog_private, dp_catalog); + + dp_write_p0(catalog, MMSS_DP_TPG_MAIN_CONTROL, 0x0); + dp_write_p0(catalog, MMSS_DP_BIST_ENABLE, 0x0); + dp_write_p0(catalog, MMSS_DP_TIMING_ENGINE_EN, 0x0); +} + +struct dp_catalog *dp_catalog_get(struct device *dev, struct dp_io *io) +{ + struct dp_catalog_private *catalog; + + if (!io) { + DRM_ERROR("invalid input\n"); + return ERR_PTR(-EINVAL); + } + + catalog = devm_kzalloc(dev, sizeof(*catalog), GFP_KERNEL); + if (!catalog) + return ERR_PTR(-ENOMEM); + + catalog->dev = dev; + catalog->io = io; + + return &catalog->dp_catalog; +} + +void dp_catalog_audio_get_header(struct dp_catalog *dp_catalog) +{ + struct dp_catalog_private *catalog; + u32 (*sdp_map)[DP_AUDIO_SDP_HEADER_MAX]; + enum dp_catalog_audio_sdp_type sdp; + enum dp_catalog_audio_header_type header; + + if (!dp_catalog) + return; + + catalog = container_of(dp_catalog, + struct dp_catalog_private, dp_catalog); + + sdp_map = catalog->audio_map; + sdp = dp_catalog->sdp_type; + header = dp_catalog->sdp_header; + + dp_catalog->audio_data = dp_read_link(catalog, + sdp_map[sdp][header]); +} + +void dp_catalog_audio_set_header(struct dp_catalog *dp_catalog) +{ + struct dp_catalog_private *catalog; + u32 (*sdp_map)[DP_AUDIO_SDP_HEADER_MAX]; + enum dp_catalog_audio_sdp_type sdp; + enum dp_catalog_audio_header_type header; + u32 data; + + if (!dp_catalog) + return; + + catalog = container_of(dp_catalog, + struct dp_catalog_private, dp_catalog); + + sdp_map = catalog->audio_map; + sdp = dp_catalog->sdp_type; + header = dp_catalog->sdp_header; + data = dp_catalog->audio_data; + + dp_write_link(catalog, sdp_map[sdp][header], data); +} + +void dp_catalog_audio_config_acr(struct dp_catalog *dp_catalog) +{ + struct dp_catalog_private *catalog; + u32 acr_ctrl, select; + + if (!dp_catalog) + return; + + catalog = container_of(dp_catalog, + struct dp_catalog_private, dp_catalog); + + select = dp_catalog->audio_data; + acr_ctrl = select << 4 | BIT(31) | BIT(8) | BIT(14); + + DRM_DEBUG_DP("select = 0x%x, acr_ctrl = 0x%x\n", select, acr_ctrl); + + dp_write_link(catalog, MMSS_DP_AUDIO_ACR_CTRL, acr_ctrl); +} + +void dp_catalog_audio_enable(struct dp_catalog *dp_catalog) +{ + struct dp_catalog_private *catalog; + bool enable; + u32 audio_ctrl; + + if (!dp_catalog) + return; + + catalog = container_of(dp_catalog, + struct dp_catalog_private, dp_catalog); + + enable = !!dp_catalog->audio_data; + audio_ctrl = dp_read_link(catalog, MMSS_DP_AUDIO_CFG); + + if (enable) + audio_ctrl |= BIT(0); + else + audio_ctrl &= ~BIT(0); + + DRM_DEBUG_DP("dp_audio_cfg = 0x%x\n", audio_ctrl); + + dp_write_link(catalog, MMSS_DP_AUDIO_CFG, audio_ctrl); + /* make sure audio engine is disabled */ + wmb(); +} + +void dp_catalog_audio_config_sdp(struct dp_catalog *dp_catalog) +{ + struct dp_catalog_private *catalog; + u32 sdp_cfg = 0; + u32 sdp_cfg2 = 0; + + if (!dp_catalog) + return; + + catalog = container_of(dp_catalog, + struct dp_catalog_private, dp_catalog); + + sdp_cfg = dp_read_link(catalog, MMSS_DP_SDP_CFG); + /* AUDIO_TIMESTAMP_SDP_EN */ + sdp_cfg |= BIT(1); + /* AUDIO_STREAM_SDP_EN */ + sdp_cfg |= BIT(2); + /* AUDIO_COPY_MANAGEMENT_SDP_EN */ + sdp_cfg |= BIT(5); + /* AUDIO_ISRC_SDP_EN */ + sdp_cfg |= BIT(6); + /* AUDIO_INFOFRAME_SDP_EN */ + sdp_cfg |= BIT(20); + + DRM_DEBUG_DP("sdp_cfg = 0x%x\n", sdp_cfg); + + dp_write_link(catalog, MMSS_DP_SDP_CFG, sdp_cfg); + + sdp_cfg2 = dp_read_link(catalog, MMSS_DP_SDP_CFG2); + /* IFRM_REGSRC -> Do not use reg values */ + sdp_cfg2 &= ~BIT(0); + /* AUDIO_STREAM_HB3_REGSRC-> Do not use reg values */ + sdp_cfg2 &= ~BIT(1); + + DRM_DEBUG_DP("sdp_cfg2 = 0x%x\n", sdp_cfg2); + + dp_write_link(catalog, MMSS_DP_SDP_CFG2, sdp_cfg2); +} + +void dp_catalog_audio_init(struct dp_catalog *dp_catalog) +{ + struct dp_catalog_private *catalog; + + static u32 sdp_map[][DP_AUDIO_SDP_HEADER_MAX] = { + { + MMSS_DP_AUDIO_STREAM_0, + MMSS_DP_AUDIO_STREAM_1, + MMSS_DP_AUDIO_STREAM_1, + }, + { + MMSS_DP_AUDIO_TIMESTAMP_0, + MMSS_DP_AUDIO_TIMESTAMP_1, + MMSS_DP_AUDIO_TIMESTAMP_1, + }, + { + MMSS_DP_AUDIO_INFOFRAME_0, + MMSS_DP_AUDIO_INFOFRAME_1, + MMSS_DP_AUDIO_INFOFRAME_1, + }, + { + MMSS_DP_AUDIO_COPYMANAGEMENT_0, + MMSS_DP_AUDIO_COPYMANAGEMENT_1, + MMSS_DP_AUDIO_COPYMANAGEMENT_1, + }, + { + MMSS_DP_AUDIO_ISRC_0, + MMSS_DP_AUDIO_ISRC_1, + MMSS_DP_AUDIO_ISRC_1, + }, + }; + + if (!dp_catalog) + return; + + catalog = container_of(dp_catalog, + struct dp_catalog_private, dp_catalog); + + catalog->audio_map = sdp_map; +} + +void dp_catalog_audio_sfe_level(struct dp_catalog *dp_catalog) +{ + struct dp_catalog_private *catalog; + u32 mainlink_levels, safe_to_exit_level; + + if (!dp_catalog) + return; + + catalog = container_of(dp_catalog, + struct dp_catalog_private, dp_catalog); + + safe_to_exit_level = dp_catalog->audio_data; + mainlink_levels = dp_read_link(catalog, REG_DP_MAINLINK_LEVELS); + mainlink_levels &= 0xFE0; + mainlink_levels |= safe_to_exit_level; + + DRM_DEBUG_DP("mainlink_level = 0x%x, safe_to_exit_level = 0x%x\n", + mainlink_levels, safe_to_exit_level); + + dp_write_link(catalog, REG_DP_MAINLINK_LEVELS, mainlink_levels); +} diff --git a/drivers/gpu/drm/msm/dp/dp_catalog.h b/drivers/gpu/drm/msm/dp/dp_catalog.h new file mode 100644 index 000000000000..4b7666f1fe6f --- /dev/null +++ b/drivers/gpu/drm/msm/dp/dp_catalog.h @@ -0,0 +1,131 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (c) 2017-2020, The Linux Foundation. All rights reserved. + */ + +#ifndef _DP_CATALOG_H_ +#define _DP_CATALOG_H_ + +#include <drm/drm_modes.h> + +#include "dp_parser.h" + +/* interrupts */ +#define DP_INTR_HPD BIT(0) +#define DP_INTR_AUX_I2C_DONE BIT(3) +#define DP_INTR_WRONG_ADDR BIT(6) +#define DP_INTR_TIMEOUT BIT(9) +#define DP_INTR_NACK_DEFER BIT(12) +#define DP_INTR_WRONG_DATA_CNT BIT(15) +#define DP_INTR_I2C_NACK BIT(18) +#define DP_INTR_I2C_DEFER BIT(21) +#define DP_INTR_PLL_UNLOCKED BIT(24) +#define DP_INTR_AUX_ERROR BIT(27) + +#define DP_INTR_READY_FOR_VIDEO BIT(0) +#define DP_INTR_IDLE_PATTERN_SENT BIT(3) +#define DP_INTR_FRAME_END BIT(6) +#define DP_INTR_CRC_UPDATED BIT(9) + +#define DP_AUX_CFG_MAX_VALUE_CNT 3 + +/* PHY AUX config registers */ +enum dp_phy_aux_config_type { + PHY_AUX_CFG0, + PHY_AUX_CFG1, + PHY_AUX_CFG2, + PHY_AUX_CFG3, + PHY_AUX_CFG4, + PHY_AUX_CFG5, + PHY_AUX_CFG6, + PHY_AUX_CFG7, + PHY_AUX_CFG8, + PHY_AUX_CFG9, + PHY_AUX_CFG_MAX, +}; + +enum dp_catalog_audio_sdp_type { + DP_AUDIO_SDP_STREAM, + DP_AUDIO_SDP_TIMESTAMP, + DP_AUDIO_SDP_INFOFRAME, + DP_AUDIO_SDP_COPYMANAGEMENT, + DP_AUDIO_SDP_ISRC, + DP_AUDIO_SDP_MAX, +}; + +enum dp_catalog_audio_header_type { + DP_AUDIO_SDP_HEADER_1, + DP_AUDIO_SDP_HEADER_2, + DP_AUDIO_SDP_HEADER_3, + DP_AUDIO_SDP_HEADER_MAX, +}; + +struct dp_catalog { + u32 aux_data; + u32 total; + u32 sync_start; + u32 width_blanking; + u32 dp_active; + enum dp_catalog_audio_sdp_type sdp_type; + enum dp_catalog_audio_header_type sdp_header; + u32 audio_data; +}; + +/* AUX APIs */ +u32 dp_catalog_aux_read_data(struct dp_catalog *dp_catalog); +int dp_catalog_aux_write_data(struct dp_catalog *dp_catalog); +int dp_catalog_aux_write_trans(struct dp_catalog *dp_catalog); +int dp_catalog_aux_clear_trans(struct dp_catalog *dp_catalog, bool read); +int dp_catalog_aux_clear_hw_interrupts(struct dp_catalog *dp_catalog); +void dp_catalog_aux_reset(struct dp_catalog *dp_catalog); +void dp_catalog_aux_enable(struct dp_catalog *dp_catalog, bool enable); +void dp_catalog_aux_update_cfg(struct dp_catalog *dp_catalog); +int dp_catalog_aux_get_irq(struct dp_catalog *dp_catalog); + +/* DP Controller APIs */ +void dp_catalog_ctrl_state_ctrl(struct dp_catalog *dp_catalog, u32 state); +void dp_catalog_ctrl_config_ctrl(struct dp_catalog *dp_catalog, u32 config); +void dp_catalog_ctrl_lane_mapping(struct dp_catalog *dp_catalog); +void dp_catalog_ctrl_mainlink_ctrl(struct dp_catalog *dp_catalog, bool enable); +void dp_catalog_ctrl_config_misc(struct dp_catalog *dp_catalog, u32 cc, u32 tb); +void dp_catalog_ctrl_config_msa(struct dp_catalog *dp_catalog, u32 rate, + u32 stream_rate_khz, bool fixed_nvid); +int dp_catalog_ctrl_set_pattern(struct dp_catalog *dp_catalog, u32 pattern); +void dp_catalog_ctrl_reset(struct dp_catalog *dp_catalog); +bool dp_catalog_ctrl_mainlink_ready(struct dp_catalog *dp_catalog); +void dp_catalog_ctrl_enable_irq(struct dp_catalog *dp_catalog, bool enable); +void dp_catalog_hpd_config_intr(struct dp_catalog *dp_catalog, + u32 intr_mask, bool en); +void dp_catalog_ctrl_hpd_config(struct dp_catalog *dp_catalog); +u32 dp_catalog_hpd_get_intr_status(struct dp_catalog *dp_catalog); +void dp_catalog_ctrl_phy_reset(struct dp_catalog *dp_catalog); +int dp_catalog_ctrl_update_vx_px(struct dp_catalog *dp_catalog, u8 v_level, + u8 p_level); +int dp_catalog_ctrl_get_interrupt(struct dp_catalog *dp_catalog); +void dp_catalog_ctrl_update_transfer_unit(struct dp_catalog *dp_catalog, + u32 dp_tu, u32 valid_boundary, + u32 valid_boundary2); +void dp_catalog_ctrl_send_phy_pattern(struct dp_catalog *dp_catalog, + u32 pattern); +u32 dp_catalog_ctrl_read_phy_pattern(struct dp_catalog *dp_catalog); + +/* DP Panel APIs */ +int dp_catalog_panel_timing_cfg(struct dp_catalog *dp_catalog); +void dp_catalog_dump_regs(struct dp_catalog *dp_catalog); +void dp_catalog_panel_tpg_enable(struct dp_catalog *dp_catalog, + struct drm_display_mode *drm_mode); +void dp_catalog_panel_tpg_disable(struct dp_catalog *dp_catalog); + +struct dp_catalog *dp_catalog_get(struct device *dev, struct dp_io *io); + +/* DP Audio APIs */ +void dp_catalog_audio_get_header(struct dp_catalog *catalog); +void dp_catalog_audio_set_header(struct dp_catalog *catalog); +void dp_catalog_audio_config_acr(struct dp_catalog *catalog); +void dp_catalog_audio_enable(struct dp_catalog *catalog); +void dp_catalog_audio_enable(struct dp_catalog *catalog); +void dp_catalog_audio_config_sdp(struct dp_catalog *catalog); +void dp_catalog_audio_init(struct dp_catalog *catalog); +void dp_catalog_audio_sfe_level(struct dp_catalog *catalog); + +#endif /* _DP_CATALOG_H_ */ diff --git a/drivers/gpu/drm/msm/dp/dp_ctrl.c b/drivers/gpu/drm/msm/dp/dp_ctrl.c new file mode 100644 index 000000000000..2e3e1917351f --- /dev/null +++ b/drivers/gpu/drm/msm/dp/dp_ctrl.c @@ -0,0 +1,1869 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (c) 2012-2020, The Linux Foundation. All rights reserved. + */ + +#define pr_fmt(fmt) "[drm-dp] %s: " fmt, __func__ + +#include <linux/types.h> +#include <linux/completion.h> +#include <linux/delay.h> +#include <linux/phy/phy.h> +#include <linux/phy/phy-dp.h> +#include <drm/drm_fixed.h> +#include <drm/drm_dp_helper.h> +#include <drm/drm_print.h> + +#include "dp_reg.h" +#include "dp_ctrl.h" +#include "dp_link.h" + +#define DP_KHZ_TO_HZ 1000 +#define IDLE_PATTERN_COMPLETION_TIMEOUT_JIFFIES (30 * HZ / 1000) /* 30 ms */ +#define WAIT_FOR_VIDEO_READY_TIMEOUT_JIFFIES (HZ / 2) + +#define DP_CTRL_INTR_READY_FOR_VIDEO BIT(0) +#define DP_CTRL_INTR_IDLE_PATTERN_SENT BIT(3) + +#define MR_LINK_TRAINING1 0x8 +#define MR_LINK_SYMBOL_ERM 0x80 +#define MR_LINK_PRBS7 0x100 +#define MR_LINK_CUSTOM80 0x200 +#define MR_LINK_TRAINING4 0x40 + +enum { + DP_TRAINING_NONE, + DP_TRAINING_1, + DP_TRAINING_2, +}; + +struct dp_tu_calc_input { + u64 lclk; /* 162, 270, 540 and 810 */ + u64 pclk_khz; /* in KHz */ + u64 hactive; /* active h-width */ + u64 hporch; /* bp + fp + pulse */ + int nlanes; /* no.of.lanes */ + int bpp; /* bits */ + int pixel_enc; /* 444, 420, 422 */ + int dsc_en; /* dsc on/off */ + int async_en; /* async mode */ + int fec_en; /* fec */ + int compress_ratio; /* 2:1 = 200, 3:1 = 300, 3.75:1 = 375 */ + int num_of_dsc_slices; /* number of slices per line */ +}; + +struct dp_vc_tu_mapping_table { + u32 vic; + u8 lanes; + u8 lrate; /* DP_LINK_RATE -> 162(6), 270(10), 540(20), 810 (30) */ + u8 bpp; + u8 valid_boundary_link; + u16 delay_start_link; + bool boundary_moderation_en; + u8 valid_lower_boundary_link; + u8 upper_boundary_count; + u8 lower_boundary_count; + u8 tu_size_minus1; +}; + +struct dp_ctrl_private { + struct dp_ctrl dp_ctrl; + struct device *dev; + struct drm_dp_aux *aux; + struct dp_panel *panel; + struct dp_link *link; + struct dp_power *power; + struct dp_parser *parser; + struct dp_catalog *catalog; + + struct completion idle_comp; + struct completion video_comp; +}; + +struct dp_cr_status { + u8 lane_0_1; + u8 lane_2_3; +}; + +#define DP_LANE0_1_CR_DONE 0x11 + +static int dp_aux_link_configure(struct drm_dp_aux *aux, + struct dp_link_info *link) +{ + u8 values[2]; + int err; + + values[0] = drm_dp_link_rate_to_bw_code(link->rate); + values[1] = link->num_lanes; + + if (link->capabilities & DP_LINK_CAP_ENHANCED_FRAMING) + values[1] |= DP_LANE_COUNT_ENHANCED_FRAME_EN; + + err = drm_dp_dpcd_write(aux, DP_LINK_BW_SET, values, sizeof(values)); + if (err < 0) + return err; + + return 0; +} + +void dp_ctrl_push_idle(struct dp_ctrl *dp_ctrl) +{ + struct dp_ctrl_private *ctrl; + + ctrl = container_of(dp_ctrl, struct dp_ctrl_private, dp_ctrl); + + reinit_completion(&ctrl->idle_comp); + dp_catalog_ctrl_state_ctrl(ctrl->catalog, DP_STATE_CTRL_PUSH_IDLE); + + if (!wait_for_completion_timeout(&ctrl->idle_comp, + IDLE_PATTERN_COMPLETION_TIMEOUT_JIFFIES)) + pr_warn("PUSH_IDLE pattern timedout\n"); + + pr_debug("mainlink off done\n"); +} + +static void dp_ctrl_config_ctrl(struct dp_ctrl_private *ctrl) +{ + u32 config = 0, tbd; + u8 *dpcd = ctrl->panel->dpcd; + + /* Default-> LSCLK DIV: 1/4 LCLK */ + config |= (2 << DP_CONFIGURATION_CTRL_LSCLK_DIV_SHIFT); + + /* Scrambler reset enable */ + if (dpcd[DP_EDP_CONFIGURATION_CAP] & DP_ALTERNATE_SCRAMBLER_RESET_CAP) + config |= DP_CONFIGURATION_CTRL_ASSR; + + tbd = dp_link_get_test_bits_depth(ctrl->link, + ctrl->panel->dp_mode.bpp); + + if (tbd == DP_TEST_BIT_DEPTH_UNKNOWN) { + pr_debug("BIT_DEPTH not set. Configure default\n"); + tbd = DP_TEST_BIT_DEPTH_8; + } + + config |= tbd << DP_CONFIGURATION_CTRL_BPC_SHIFT; + + /* Num of Lanes */ + config |= ((ctrl->link->link_params.num_lanes - 1) + << DP_CONFIGURATION_CTRL_NUM_OF_LANES_SHIFT); + + if (drm_dp_enhanced_frame_cap(dpcd)) + config |= DP_CONFIGURATION_CTRL_ENHANCED_FRAMING; + + config |= DP_CONFIGURATION_CTRL_P_INTERLACED; /* progressive video */ + + /* sync clock & static Mvid */ + config |= DP_CONFIGURATION_CTRL_STATIC_DYNAMIC_CN; + config |= DP_CONFIGURATION_CTRL_SYNC_ASYNC_CLK; + + dp_catalog_ctrl_config_ctrl(ctrl->catalog, config); +} + +static void dp_ctrl_configure_source_params(struct dp_ctrl_private *ctrl) +{ + u32 cc, tb; + + dp_catalog_ctrl_lane_mapping(ctrl->catalog); + dp_catalog_ctrl_mainlink_ctrl(ctrl->catalog, true); + + dp_ctrl_config_ctrl(ctrl); + + tb = dp_link_get_test_bits_depth(ctrl->link, + ctrl->panel->dp_mode.bpp); + cc = dp_link_get_colorimetry_config(ctrl->link); + dp_catalog_ctrl_config_misc(ctrl->catalog, cc, tb); + dp_panel_timing_cfg(ctrl->panel); +} + +/* + * The structure and few functions present below are IP/Hardware + * specific implementation. Most of the implementation will not + * have coding comments + */ +struct tu_algo_data { + s64 lclk_fp; + s64 pclk_fp; + s64 lwidth; + s64 lwidth_fp; + s64 hbp_relative_to_pclk; + s64 hbp_relative_to_pclk_fp; + int nlanes; + int bpp; + int pixelEnc; + int dsc_en; + int async_en; + int bpc; + + uint delay_start_link_extra_pixclk; + int extra_buffer_margin; + s64 ratio_fp; + s64 original_ratio_fp; + + s64 err_fp; + s64 n_err_fp; + s64 n_n_err_fp; + int tu_size; + int tu_size_desired; + int tu_size_minus1; + + int valid_boundary_link; + s64 resulting_valid_fp; + s64 total_valid_fp; + s64 effective_valid_fp; + s64 effective_valid_recorded_fp; + int n_tus; + int n_tus_per_lane; + int paired_tus; + int remainder_tus; + int remainder_tus_upper; + int remainder_tus_lower; + int extra_bytes; + int filler_size; + int delay_start_link; + + int extra_pclk_cycles; + int extra_pclk_cycles_in_link_clk; + s64 ratio_by_tu_fp; + s64 average_valid2_fp; + int new_valid_boundary_link; + int remainder_symbols_exist; + int n_symbols; + s64 n_remainder_symbols_per_lane_fp; + s64 last_partial_tu_fp; + s64 TU_ratio_err_fp; + + int n_tus_incl_last_incomplete_tu; + int extra_pclk_cycles_tmp; + int extra_pclk_cycles_in_link_clk_tmp; + int extra_required_bytes_new_tmp; + int filler_size_tmp; + int lower_filler_size_tmp; + int delay_start_link_tmp; + + bool boundary_moderation_en; + int boundary_mod_lower_err; + int upper_boundary_count; + int lower_boundary_count; + int i_upper_boundary_count; + int i_lower_boundary_count; + int valid_lower_boundary_link; + int even_distribution_BF; + int even_distribution_legacy; + int even_distribution; + int min_hblank_violated; + s64 delay_start_time_fp; + s64 hbp_time_fp; + s64 hactive_time_fp; + s64 diff_abs_fp; + + s64 ratio; +}; + +static int _tu_param_compare(s64 a, s64 b) +{ + u32 a_sign; + u32 b_sign; + s64 a_temp, b_temp, minus_1; + + if (a == b) + return 0; + + minus_1 = drm_fixp_from_fraction(-1, 1); + + a_sign = (a >> 32) & 0x80000000 ? 1 : 0; + + b_sign = (b >> 32) & 0x80000000 ? 1 : 0; + + if (a_sign > b_sign) + return 2; + else if (b_sign > a_sign) + return 1; + + if (!a_sign && !b_sign) { /* positive */ + if (a > b) + return 1; + else + return 2; + } else { /* negative */ + a_temp = drm_fixp_mul(a, minus_1); + b_temp = drm_fixp_mul(b, minus_1); + + if (a_temp > b_temp) + return 2; + else + return 1; + } +} + +static void dp_panel_update_tu_timings(struct dp_tu_calc_input *in, + struct tu_algo_data *tu) +{ + int nlanes = in->nlanes; + int dsc_num_slices = in->num_of_dsc_slices; + int dsc_num_bytes = 0; + int numerator; + s64 pclk_dsc_fp; + s64 dwidth_dsc_fp; + s64 hbp_dsc_fp; + + int tot_num_eoc_symbols = 0; + int tot_num_hor_bytes = 0; + int tot_num_dummy_bytes = 0; + int dwidth_dsc_bytes = 0; + int eoc_bytes = 0; + + s64 temp1_fp, temp2_fp, temp3_fp; + + tu->lclk_fp = drm_fixp_from_fraction(in->lclk, 1); + tu->pclk_fp = drm_fixp_from_fraction(in->pclk_khz, 1000); + tu->lwidth = in->hactive; + tu->hbp_relative_to_pclk = in->hporch; + tu->nlanes = in->nlanes; + tu->bpp = in->bpp; + tu->pixelEnc = in->pixel_enc; + tu->dsc_en = in->dsc_en; + tu->async_en = in->async_en; + tu->lwidth_fp = drm_fixp_from_fraction(in->hactive, 1); + tu->hbp_relative_to_pclk_fp = drm_fixp_from_fraction(in->hporch, 1); + + if (tu->pixelEnc == 420) { + temp1_fp = drm_fixp_from_fraction(2, 1); + tu->pclk_fp = drm_fixp_div(tu->pclk_fp, temp1_fp); + tu->lwidth_fp = drm_fixp_div(tu->lwidth_fp, temp1_fp); + tu->hbp_relative_to_pclk_fp = + drm_fixp_div(tu->hbp_relative_to_pclk_fp, 2); + } + + if (tu->pixelEnc == 422) { + switch (tu->bpp) { + case 24: + tu->bpp = 16; + tu->bpc = 8; + break; + case 30: + tu->bpp = 20; + tu->bpc = 10; + break; + default: + tu->bpp = 16; + tu->bpc = 8; + break; + } + } else { + tu->bpc = tu->bpp/3; + } + + if (!in->dsc_en) + goto fec_check; + + temp1_fp = drm_fixp_from_fraction(in->compress_ratio, 100); + temp2_fp = drm_fixp_from_fraction(in->bpp, 1); + temp3_fp = drm_fixp_div(temp2_fp, temp1_fp); + temp2_fp = drm_fixp_mul(tu->lwidth_fp, temp3_fp); + + temp1_fp = drm_fixp_from_fraction(8, 1); + temp3_fp = drm_fixp_div(temp2_fp, temp1_fp); + + numerator = drm_fixp2int(temp3_fp); + + dsc_num_bytes = numerator / dsc_num_slices; + eoc_bytes = dsc_num_bytes % nlanes; + tot_num_eoc_symbols = nlanes * dsc_num_slices; + tot_num_hor_bytes = dsc_num_bytes * dsc_num_slices; + tot_num_dummy_bytes = (nlanes - eoc_bytes) * dsc_num_slices; + + if (dsc_num_bytes == 0) + pr_info("incorrect no of bytes per slice=%d\n", dsc_num_bytes); + + dwidth_dsc_bytes = (tot_num_hor_bytes + + tot_num_eoc_symbols + + (eoc_bytes == 0 ? 0 : tot_num_dummy_bytes)); + + dwidth_dsc_fp = drm_fixp_from_fraction(dwidth_dsc_bytes, 3); + + temp2_fp = drm_fixp_mul(tu->pclk_fp, dwidth_dsc_fp); + temp1_fp = drm_fixp_div(temp2_fp, tu->lwidth_fp); + pclk_dsc_fp = temp1_fp; + + temp1_fp = drm_fixp_div(pclk_dsc_fp, tu->pclk_fp); + temp2_fp = drm_fixp_mul(tu->hbp_relative_to_pclk_fp, temp1_fp); + hbp_dsc_fp = temp2_fp; + + /* output */ + tu->pclk_fp = pclk_dsc_fp; + tu->lwidth_fp = dwidth_dsc_fp; + tu->hbp_relative_to_pclk_fp = hbp_dsc_fp; + +fec_check: + if (in->fec_en) { + temp1_fp = drm_fixp_from_fraction(976, 1000); /* 0.976 */ + tu->lclk_fp = drm_fixp_mul(tu->lclk_fp, temp1_fp); + } +} + +static void _tu_valid_boundary_calc(struct tu_algo_data *tu) +{ + s64 temp1_fp, temp2_fp, temp, temp1, temp2; + int compare_result_1, compare_result_2, compare_result_3; + + temp1_fp = drm_fixp_from_fraction(tu->tu_size, 1); + temp2_fp = drm_fixp_mul(tu->ratio_fp, temp1_fp); + + tu->new_valid_boundary_link = drm_fixp2int_ceil(temp2_fp); + + temp = (tu->i_upper_boundary_count * + tu->new_valid_boundary_link + + tu->i_lower_boundary_count * + (tu->new_valid_boundary_link-1)); + tu->average_valid2_fp = drm_fixp_from_fraction(temp, + (tu->i_upper_boundary_count + + tu->i_lower_boundary_count)); + + temp1_fp = drm_fixp_from_fraction(tu->bpp, 8); + temp2_fp = tu->lwidth_fp; + temp1_fp = drm_fixp_mul(temp2_fp, temp1_fp); + temp2_fp = drm_fixp_div(temp1_fp, tu->average_valid2_fp); + tu->n_tus = drm_fixp2int(temp2_fp); + if ((temp2_fp & 0xFFFFFFFF) > 0xFFFFF000) + tu->n_tus += 1; + + temp1_fp = drm_fixp_from_fraction(tu->n_tus, 1); + temp2_fp = drm_fixp_mul(temp1_fp, tu->average_valid2_fp); + temp1_fp = drm_fixp_from_fraction(tu->n_symbols, 1); + temp2_fp = temp1_fp - temp2_fp; + temp1_fp = drm_fixp_from_fraction(tu->nlanes, 1); + temp2_fp = drm_fixp_div(temp2_fp, temp1_fp); + tu->n_remainder_symbols_per_lane_fp = temp2_fp; + + temp1_fp = drm_fixp_from_fraction(tu->tu_size, 1); + tu->last_partial_tu_fp = + drm_fixp_div(tu->n_remainder_symbols_per_lane_fp, + temp1_fp); + + if (tu->n_remainder_symbols_per_lane_fp != 0) + tu->remainder_symbols_exist = 1; + else + tu->remainder_symbols_exist = 0; + + temp1_fp = drm_fixp_from_fraction(tu->n_tus, tu->nlanes); + tu->n_tus_per_lane = drm_fixp2int(temp1_fp); + + tu->paired_tus = (int)((tu->n_tus_per_lane) / + (tu->i_upper_boundary_count + + tu->i_lower_boundary_count)); + + tu->remainder_tus = tu->n_tus_per_lane - tu->paired_tus * + (tu->i_upper_boundary_count + + tu->i_lower_boundary_count); + + if ((tu->remainder_tus - tu->i_upper_boundary_count) > 0) { + tu->remainder_tus_upper = tu->i_upper_boundary_count; + tu->remainder_tus_lower = tu->remainder_tus - + tu->i_upper_boundary_count; + } else { + tu->remainder_tus_upper = tu->remainder_tus; + tu->remainder_tus_lower = 0; + } + + temp = tu->paired_tus * (tu->i_upper_boundary_count * + tu->new_valid_boundary_link + + tu->i_lower_boundary_count * + (tu->new_valid_boundary_link - 1)) + + (tu->remainder_tus_upper * + tu->new_valid_boundary_link) + + (tu->remainder_tus_lower * + (tu->new_valid_boundary_link - 1)); + tu->total_valid_fp = drm_fixp_from_fraction(temp, 1); + + if (tu->remainder_symbols_exist) { + temp1_fp = tu->total_valid_fp + + tu->n_remainder_symbols_per_lane_fp; + temp2_fp = drm_fixp_from_fraction(tu->n_tus_per_lane, 1); + temp2_fp = temp2_fp + tu->last_partial_tu_fp; + temp1_fp = drm_fixp_div(temp1_fp, temp2_fp); + } else { + temp2_fp = drm_fixp_from_fraction(tu->n_tus_per_lane, 1); + temp1_fp = drm_fixp_div(tu->total_valid_fp, temp2_fp); + } + tu->effective_valid_fp = temp1_fp; + + temp1_fp = drm_fixp_from_fraction(tu->tu_size, 1); + temp2_fp = drm_fixp_mul(tu->ratio_fp, temp1_fp); + tu->n_n_err_fp = tu->effective_valid_fp - temp2_fp; + + temp1_fp = drm_fixp_from_fraction(tu->tu_size, 1); + temp2_fp = drm_fixp_mul(tu->ratio_fp, temp1_fp); + tu->n_err_fp = tu->average_valid2_fp - temp2_fp; + + tu->even_distribution = tu->n_tus % tu->nlanes == 0 ? 1 : 0; + + temp1_fp = drm_fixp_from_fraction(tu->bpp, 8); + temp2_fp = tu->lwidth_fp; + temp1_fp = drm_fixp_mul(temp2_fp, temp1_fp); + temp2_fp = drm_fixp_div(temp1_fp, tu->average_valid2_fp); + + if (temp2_fp) + tu->n_tus_incl_last_incomplete_tu = drm_fixp2int_ceil(temp2_fp); + else + tu->n_tus_incl_last_incomplete_tu = 0; + + temp1 = 0; + temp1_fp = drm_fixp_from_fraction(tu->tu_size, 1); + temp2_fp = drm_fixp_mul(tu->original_ratio_fp, temp1_fp); + temp1_fp = tu->average_valid2_fp - temp2_fp; + temp2_fp = drm_fixp_from_fraction(tu->n_tus_incl_last_incomplete_tu, 1); + temp1_fp = drm_fixp_mul(temp2_fp, temp1_fp); + + if (temp1_fp) + temp1 = drm_fixp2int_ceil(temp1_fp); + + temp = tu->i_upper_boundary_count * tu->nlanes; + temp1_fp = drm_fixp_from_fraction(tu->tu_size, 1); + temp2_fp = drm_fixp_mul(tu->original_ratio_fp, temp1_fp); + temp1_fp = drm_fixp_from_fraction(tu->new_valid_boundary_link, 1); + temp2_fp = temp1_fp - temp2_fp; + temp1_fp = drm_fixp_from_fraction(temp, 1); + temp2_fp = drm_fixp_mul(temp1_fp, temp2_fp); + + if (temp2_fp) + temp2 = drm_fixp2int_ceil(temp2_fp); + else + temp2 = 0; + tu->extra_required_bytes_new_tmp = (int)(temp1 + temp2); + + temp1_fp = drm_fixp_from_fraction(8, tu->bpp); + temp2_fp = drm_fixp_from_fraction( + tu->extra_required_bytes_new_tmp, 1); + temp1_fp = drm_fixp_mul(temp2_fp, temp1_fp); + + if (temp1_fp) + tu->extra_pclk_cycles_tmp = drm_fixp2int_ceil(temp1_fp); + else + tu->extra_pclk_cycles_tmp = 0; + + temp1_fp = drm_fixp_from_fraction(tu->extra_pclk_cycles_tmp, 1); + temp2_fp = drm_fixp_div(tu->lclk_fp, tu->pclk_fp); + temp1_fp = drm_fixp_mul(temp1_fp, temp2_fp); + + if (temp1_fp) + tu->extra_pclk_cycles_in_link_clk_tmp = + drm_fixp2int_ceil(temp1_fp); + else + tu->extra_pclk_cycles_in_link_clk_tmp = 0; + + tu->filler_size_tmp = tu->tu_size - tu->new_valid_boundary_link; + + tu->lower_filler_size_tmp = tu->filler_size_tmp + 1; + + tu->delay_start_link_tmp = tu->extra_pclk_cycles_in_link_clk_tmp + + tu->lower_filler_size_tmp + + tu->extra_buffer_margin; + + temp1_fp = drm_fixp_from_fraction(tu->delay_start_link_tmp, 1); + tu->delay_start_time_fp = drm_fixp_div(temp1_fp, tu->lclk_fp); + + compare_result_1 = _tu_param_compare(tu->n_n_err_fp, tu->diff_abs_fp); + if (compare_result_1 == 2) + compare_result_1 = 1; + else + compare_result_1 = 0; + + compare_result_2 = _tu_param_compare(tu->n_n_err_fp, tu->err_fp); + if (compare_result_2 == 2) + compare_result_2 = 1; + else + compare_result_2 = 0; + + compare_result_3 = _tu_param_compare(tu->hbp_time_fp, + tu->delay_start_time_fp); + if (compare_result_3 == 2) + compare_result_3 = 0; + else + compare_result_3 = 1; + + if (((tu->even_distribution == 1) || + ((tu->even_distribution_BF == 0) && + (tu->even_distribution_legacy == 0))) && + tu->n_err_fp >= 0 && tu->n_n_err_fp >= 0 && + compare_result_2 && + (compare_result_1 || (tu->min_hblank_violated == 1)) && + (tu->new_valid_boundary_link - 1) > 0 && + compare_result_3 && + (tu->delay_start_link_tmp <= 1023)) { + tu->upper_boundary_count = tu->i_upper_boundary_count; + tu->lower_boundary_count = tu->i_lower_boundary_count; + tu->err_fp = tu->n_n_err_fp; + tu->boundary_moderation_en = true; + tu->tu_size_desired = tu->tu_size; + tu->valid_boundary_link = tu->new_valid_boundary_link; + tu->effective_valid_recorded_fp = tu->effective_valid_fp; + tu->even_distribution_BF = 1; + tu->delay_start_link = tu->delay_start_link_tmp; + } else if (tu->boundary_mod_lower_err == 0) { + compare_result_1 = _tu_param_compare(tu->n_n_err_fp, + tu->diff_abs_fp); + if (compare_result_1 == 2) + tu->boundary_mod_lower_err = 1; + } +} + +static void _dp_ctrl_calc_tu(struct dp_tu_calc_input *in, + struct dp_vc_tu_mapping_table *tu_table) +{ + struct tu_algo_data tu; + int compare_result_1, compare_result_2; + u64 temp = 0; + s64 temp_fp = 0, temp1_fp = 0, temp2_fp = 0; + + s64 LCLK_FAST_SKEW_fp = drm_fixp_from_fraction(6, 10000); /* 0.0006 */ + s64 const_p49_fp = drm_fixp_from_fraction(49, 100); /* 0.49 */ + s64 const_p56_fp = drm_fixp_from_fraction(56, 100); /* 0.56 */ + s64 RATIO_SCALE_fp = drm_fixp_from_fraction(1001, 1000); + + u8 DP_BRUTE_FORCE = 1; + s64 BRUTE_FORCE_THRESHOLD_fp = drm_fixp_from_fraction(1, 10); /* 0.1 */ + uint EXTRA_PIXCLK_CYCLE_DELAY = 4; + uint HBLANK_MARGIN = 4; + + memset(&tu, 0, sizeof(tu)); + + dp_panel_update_tu_timings(in, &tu); + + tu.err_fp = drm_fixp_from_fraction(1000, 1); /* 1000 */ + + temp1_fp = drm_fixp_from_fraction(4, 1); + temp2_fp = drm_fixp_mul(temp1_fp, tu.lclk_fp); + temp_fp = drm_fixp_div(temp2_fp, tu.pclk_fp); + tu.extra_buffer_margin = drm_fixp2int_ceil(temp_fp); + + temp1_fp = drm_fixp_from_fraction(tu.bpp, 8); + temp2_fp = drm_fixp_mul(tu.pclk_fp, temp1_fp); + temp1_fp = drm_fixp_from_fraction(tu.nlanes, 1); + temp2_fp = drm_fixp_div(temp2_fp, temp1_fp); + tu.ratio_fp = drm_fixp_div(temp2_fp, tu.lclk_fp); + + tu.original_ratio_fp = tu.ratio_fp; + tu.boundary_moderation_en = false; + tu.upper_boundary_count = 0; + tu.lower_boundary_count = 0; + tu.i_upper_boundary_count = 0; + tu.i_lower_boundary_count = 0; + tu.valid_lower_boundary_link = 0; + tu.even_distribution_BF = 0; + tu.even_distribution_legacy = 0; + tu.even_distribution = 0; + tu.delay_start_time_fp = 0; + + tu.err_fp = drm_fixp_from_fraction(1000, 1); + tu.n_err_fp = 0; + tu.n_n_err_fp = 0; + + tu.ratio = drm_fixp2int(tu.ratio_fp); + temp1_fp = drm_fixp_from_fraction(tu.nlanes, 1); + div64_u64_rem(tu.lwidth_fp, temp1_fp, &temp2_fp); + if (temp2_fp != 0 && + !tu.ratio && tu.dsc_en == 0) { + tu.ratio_fp = drm_fixp_mul(tu.ratio_fp, RATIO_SCALE_fp); + tu.ratio = drm_fixp2int(tu.ratio_fp); + if (tu.ratio) + tu.ratio_fp = drm_fixp_from_fraction(1, 1); + } + + if (tu.ratio > 1) + tu.ratio = 1; + + if (tu.ratio == 1) + goto tu_size_calc; + + compare_result_1 = _tu_param_compare(tu.ratio_fp, const_p49_fp); + if (!compare_result_1 || compare_result_1 == 1) + compare_result_1 = 1; + else + compare_result_1 = 0; + + compare_result_2 = _tu_param_compare(tu.ratio_fp, const_p56_fp); + if (!compare_result_2 || compare_result_2 == 2) + compare_result_2 = 1; + else + compare_result_2 = 0; + + if (tu.dsc_en && compare_result_1 && compare_result_2) { + HBLANK_MARGIN += 4; + DRM_DEBUG_DP("Info: increase HBLANK_MARGIN to %d\n", + HBLANK_MARGIN); + } + +tu_size_calc: + for (tu.tu_size = 32; tu.tu_size <= 64; tu.tu_size++) { + temp1_fp = drm_fixp_from_fraction(tu.tu_size, 1); + temp2_fp = drm_fixp_mul(tu.ratio_fp, temp1_fp); + temp = drm_fixp2int_ceil(temp2_fp); + temp1_fp = drm_fixp_from_fraction(temp, 1); + tu.n_err_fp = temp1_fp - temp2_fp; + + if (tu.n_err_fp < tu.err_fp) { + tu.err_fp = tu.n_err_fp; + tu.tu_size_desired = tu.tu_size; + } + } + + tu.tu_size_minus1 = tu.tu_size_desired - 1; + + temp1_fp = drm_fixp_from_fraction(tu.tu_size_desired, 1); + temp2_fp = drm_fixp_mul(tu.ratio_fp, temp1_fp); + tu.valid_boundary_link = drm_fixp2int_ceil(temp2_fp); + + temp1_fp = drm_fixp_from_fraction(tu.bpp, 8); + temp2_fp = tu.lwidth_fp; + temp2_fp = drm_fixp_mul(temp2_fp, temp1_fp); + + temp1_fp = drm_fixp_from_fraction(tu.valid_boundary_link, 1); + temp2_fp = drm_fixp_div(temp2_fp, temp1_fp); + tu.n_tus = drm_fixp2int(temp2_fp); + if ((temp2_fp & 0xFFFFFFFF) > 0xFFFFF000) + tu.n_tus += 1; + + tu.even_distribution_legacy = tu.n_tus % tu.nlanes == 0 ? 1 : 0; + DRM_DEBUG_DP("Info: n_sym = %d, num_of_tus = %d\n", + tu.valid_boundary_link, tu.n_tus); + + temp1_fp = drm_fixp_from_fraction(tu.tu_size_desired, 1); + temp2_fp = drm_fixp_mul(tu.original_ratio_fp, temp1_fp); + temp1_fp = drm_fixp_from_fraction(tu.valid_boundary_link, 1); + temp2_fp = temp1_fp - temp2_fp; + temp1_fp = drm_fixp_from_fraction(tu.n_tus + 1, 1); + temp2_fp = drm_fixp_mul(temp1_fp, temp2_fp); + + temp = drm_fixp2int(temp2_fp); + if (temp && temp2_fp) + tu.extra_bytes = drm_fixp2int_ceil(temp2_fp); + else + tu.extra_bytes = 0; + + temp1_fp = drm_fixp_from_fraction(tu.extra_bytes, 1); + temp2_fp = drm_fixp_from_fraction(8, tu.bpp); + temp1_fp = drm_fixp_mul(temp1_fp, temp2_fp); + + if (temp && temp1_fp) + tu.extra_pclk_cycles = drm_fixp2int_ceil(temp1_fp); + else + tu.extra_pclk_cycles = drm_fixp2int(temp1_fp); + + temp1_fp = drm_fixp_div(tu.lclk_fp, tu.pclk_fp); + temp2_fp = drm_fixp_from_fraction(tu.extra_pclk_cycles, 1); + temp1_fp = drm_fixp_mul(temp2_fp, temp1_fp); + + if (temp1_fp) + tu.extra_pclk_cycles_in_link_clk = drm_fixp2int_ceil(temp1_fp); + else + tu.extra_pclk_cycles_in_link_clk = drm_fixp2int(temp1_fp); + + tu.filler_size = tu.tu_size_desired - tu.valid_boundary_link; + + temp1_fp = drm_fixp_from_fraction(tu.tu_size_desired, 1); + tu.ratio_by_tu_fp = drm_fixp_mul(tu.ratio_fp, temp1_fp); + + tu.delay_start_link = tu.extra_pclk_cycles_in_link_clk + + tu.filler_size + tu.extra_buffer_margin; + + tu.resulting_valid_fp = + drm_fixp_from_fraction(tu.valid_boundary_link, 1); + + temp1_fp = drm_fixp_from_fraction(tu.tu_size_desired, 1); + temp2_fp = drm_fixp_div(tu.resulting_valid_fp, temp1_fp); + tu.TU_ratio_err_fp = temp2_fp - tu.original_ratio_fp; + + temp1_fp = drm_fixp_from_fraction(HBLANK_MARGIN, 1); + temp1_fp = tu.hbp_relative_to_pclk_fp - temp1_fp; + tu.hbp_time_fp = drm_fixp_div(temp1_fp, tu.pclk_fp); + + temp1_fp = drm_fixp_from_fraction(tu.delay_start_link, 1); + tu.delay_start_time_fp = drm_fixp_div(temp1_fp, tu.lclk_fp); + + compare_result_1 = _tu_param_compare(tu.hbp_time_fp, + tu.delay_start_time_fp); + if (compare_result_1 == 2) /* if (hbp_time_fp < delay_start_time_fp) */ + tu.min_hblank_violated = 1; + + tu.hactive_time_fp = drm_fixp_div(tu.lwidth_fp, tu.pclk_fp); + + compare_result_2 = _tu_param_compare(tu.hactive_time_fp, + tu.delay_start_time_fp); + if (compare_result_2 == 2) + tu.min_hblank_violated = 1; + + tu.delay_start_time_fp = 0; + + /* brute force */ + + tu.delay_start_link_extra_pixclk = EXTRA_PIXCLK_CYCLE_DELAY; + tu.diff_abs_fp = tu.resulting_valid_fp - tu.ratio_by_tu_fp; + + temp = drm_fixp2int(tu.diff_abs_fp); + if (!temp && tu.diff_abs_fp <= 0xffff) + tu.diff_abs_fp = 0; + + /* if(diff_abs < 0) diff_abs *= -1 */ + if (tu.diff_abs_fp < 0) + tu.diff_abs_fp = drm_fixp_mul(tu.diff_abs_fp, -1); + + tu.boundary_mod_lower_err = 0; + if ((tu.diff_abs_fp != 0 && + ((tu.diff_abs_fp > BRUTE_FORCE_THRESHOLD_fp) || + (tu.even_distribution_legacy == 0) || + (DP_BRUTE_FORCE == 1))) || + (tu.min_hblank_violated == 1)) { + do { + tu.err_fp = drm_fixp_from_fraction(1000, 1); + + temp1_fp = drm_fixp_div(tu.lclk_fp, tu.pclk_fp); + temp2_fp = drm_fixp_from_fraction( + tu.delay_start_link_extra_pixclk, 1); + temp1_fp = drm_fixp_mul(temp2_fp, temp1_fp); + + if (temp1_fp) + tu.extra_buffer_margin = + drm_fixp2int_ceil(temp1_fp); + else + tu.extra_buffer_margin = 0; + + temp1_fp = drm_fixp_from_fraction(tu.bpp, 8); + temp1_fp = drm_fixp_mul(tu.lwidth_fp, temp1_fp); + + if (temp1_fp) + tu.n_symbols = drm_fixp2int_ceil(temp1_fp); + else + tu.n_symbols = 0; + + for (tu.tu_size = 32; tu.tu_size <= 64; tu.tu_size++) { + for (tu.i_upper_boundary_count = 1; + tu.i_upper_boundary_count <= 15; + tu.i_upper_boundary_count++) { + for (tu.i_lower_boundary_count = 1; + tu.i_lower_boundary_count <= 15; + tu.i_lower_boundary_count++) { + _tu_valid_boundary_calc(&tu); + } + } + } + tu.delay_start_link_extra_pixclk--; + } while (tu.boundary_moderation_en != true && + tu.boundary_mod_lower_err == 1 && + tu.delay_start_link_extra_pixclk != 0); + + if (tu.boundary_moderation_en == true) { + temp1_fp = drm_fixp_from_fraction( + (tu.upper_boundary_count * + tu.valid_boundary_link + + tu.lower_boundary_count * + (tu.valid_boundary_link - 1)), 1); + temp2_fp = drm_fixp_from_fraction( + (tu.upper_boundary_count + + tu.lower_boundary_count), 1); + tu.resulting_valid_fp = + drm_fixp_div(temp1_fp, temp2_fp); + + temp1_fp = drm_fixp_from_fraction( + tu.tu_size_desired, 1); + tu.ratio_by_tu_fp = + drm_fixp_mul(tu.original_ratio_fp, temp1_fp); + + tu.valid_lower_boundary_link = + tu.valid_boundary_link - 1; + + temp1_fp = drm_fixp_from_fraction(tu.bpp, 8); + temp1_fp = drm_fixp_mul(tu.lwidth_fp, temp1_fp); + temp2_fp = drm_fixp_div(temp1_fp, + tu.resulting_valid_fp); + tu.n_tus = drm_fixp2int(temp2_fp); + + tu.tu_size_minus1 = tu.tu_size_desired - 1; + tu.even_distribution_BF = 1; + + temp1_fp = + drm_fixp_from_fraction(tu.tu_size_desired, 1); + temp2_fp = + drm_fixp_div(tu.resulting_valid_fp, temp1_fp); + tu.TU_ratio_err_fp = temp2_fp - tu.original_ratio_fp; + } + } + + temp2_fp = drm_fixp_mul(LCLK_FAST_SKEW_fp, tu.lwidth_fp); + + if (temp2_fp) + temp = drm_fixp2int_ceil(temp2_fp); + else + temp = 0; + + temp1_fp = drm_fixp_from_fraction(tu.nlanes, 1); + temp2_fp = drm_fixp_mul(tu.original_ratio_fp, temp1_fp); + temp1_fp = drm_fixp_from_fraction(tu.bpp, 8); + temp2_fp = drm_fixp_div(temp1_fp, temp2_fp); + temp1_fp = drm_fixp_from_fraction(temp, 1); + temp2_fp = drm_fixp_mul(temp1_fp, temp2_fp); + temp = drm_fixp2int(temp2_fp); + + if (tu.async_en) + tu.delay_start_link += (int)temp; + + temp1_fp = drm_fixp_from_fraction(tu.delay_start_link, 1); + tu.delay_start_time_fp = drm_fixp_div(temp1_fp, tu.lclk_fp); + + /* OUTPUTS */ + tu_table->valid_boundary_link = tu.valid_boundary_link; + tu_table->delay_start_link = tu.delay_start_link; + tu_table->boundary_moderation_en = tu.boundary_moderation_en; + tu_table->valid_lower_boundary_link = tu.valid_lower_boundary_link; + tu_table->upper_boundary_count = tu.upper_boundary_count; + tu_table->lower_boundary_count = tu.lower_boundary_count; + tu_table->tu_size_minus1 = tu.tu_size_minus1; + + DRM_DEBUG_DP("TU: valid_boundary_link: %d\n", + tu_table->valid_boundary_link); + DRM_DEBUG_DP("TU: delay_start_link: %d\n", + tu_table->delay_start_link); + DRM_DEBUG_DP("TU: boundary_moderation_en: %d\n", + tu_table->boundary_moderation_en); + DRM_DEBUG_DP("TU: valid_lower_boundary_link: %d\n", + tu_table->valid_lower_boundary_link); + DRM_DEBUG_DP("TU: upper_boundary_count: %d\n", + tu_table->upper_boundary_count); + DRM_DEBUG_DP("TU: lower_boundary_count: %d\n", + tu_table->lower_boundary_count); + DRM_DEBUG_DP("TU: tu_size_minus1: %d\n", tu_table->tu_size_minus1); +} + +static void dp_ctrl_calc_tu_parameters(struct dp_ctrl_private *ctrl, + struct dp_vc_tu_mapping_table *tu_table) +{ + struct dp_tu_calc_input in; + struct drm_display_mode *drm_mode; + + drm_mode = &ctrl->panel->dp_mode.drm_mode; + + in.lclk = ctrl->link->link_params.rate / 1000; + in.pclk_khz = drm_mode->clock; + in.hactive = drm_mode->hdisplay; + in.hporch = drm_mode->htotal - drm_mode->hdisplay; + in.nlanes = ctrl->link->link_params.num_lanes; + in.bpp = ctrl->panel->dp_mode.bpp; + in.pixel_enc = 444; + in.dsc_en = 0; + in.async_en = 0; + in.fec_en = 0; + in.num_of_dsc_slices = 0; + in.compress_ratio = 100; + + _dp_ctrl_calc_tu(&in, tu_table); +} + +static void dp_ctrl_setup_tr_unit(struct dp_ctrl_private *ctrl) +{ + u32 dp_tu = 0x0; + u32 valid_boundary = 0x0; + u32 valid_boundary2 = 0x0; + struct dp_vc_tu_mapping_table tu_calc_table; + + dp_ctrl_calc_tu_parameters(ctrl, &tu_calc_table); + + dp_tu |= tu_calc_table.tu_size_minus1; + valid_boundary |= tu_calc_table.valid_boundary_link; + valid_boundary |= (tu_calc_table.delay_start_link << 16); + + valid_boundary2 |= (tu_calc_table.valid_lower_boundary_link << 1); + valid_boundary2 |= (tu_calc_table.upper_boundary_count << 16); + valid_boundary2 |= (tu_calc_table.lower_boundary_count << 20); + + if (tu_calc_table.boundary_moderation_en) + valid_boundary2 |= BIT(0); + + pr_debug("dp_tu=0x%x, valid_boundary=0x%x, valid_boundary2=0x%x\n", + dp_tu, valid_boundary, valid_boundary2); + + dp_catalog_ctrl_update_transfer_unit(ctrl->catalog, + dp_tu, valid_boundary, valid_boundary2); +} + +static int dp_ctrl_wait4video_ready(struct dp_ctrl_private *ctrl) +{ + int ret = 0; + + if (!wait_for_completion_timeout(&ctrl->video_comp, + WAIT_FOR_VIDEO_READY_TIMEOUT_JIFFIES)) { + DRM_ERROR("wait4video timedout\n"); + ret = -ETIMEDOUT; + } + return ret; +} + +static int dp_ctrl_update_vx_px(struct dp_ctrl_private *ctrl) +{ + struct dp_link *link = ctrl->link; + int ret = 0, lane, lane_cnt; + u8 buf[4]; + u32 max_level_reached = 0; + u32 voltage_swing_level = link->phy_params.v_level; + u32 pre_emphasis_level = link->phy_params.p_level; + + ret = dp_catalog_ctrl_update_vx_px(ctrl->catalog, + voltage_swing_level, pre_emphasis_level); + + if (ret) + return ret; + + if (voltage_swing_level >= DP_TRAIN_VOLTAGE_SWING_MAX) { + DRM_DEBUG_DP("max. voltage swing level reached %d\n", + voltage_swing_level); + max_level_reached |= DP_TRAIN_MAX_SWING_REACHED; + } + + if (pre_emphasis_level >= DP_TRAIN_PRE_EMPHASIS_MAX) { + DRM_DEBUG_DP("max. pre-emphasis level reached %d\n", + pre_emphasis_level); + max_level_reached |= DP_TRAIN_MAX_PRE_EMPHASIS_REACHED; + } + + pre_emphasis_level <<= DP_TRAIN_PRE_EMPHASIS_SHIFT; + + lane_cnt = ctrl->link->link_params.num_lanes; + for (lane = 0; lane < lane_cnt; lane++) + buf[lane] = voltage_swing_level | pre_emphasis_level + | max_level_reached; + + DRM_DEBUG_DP("sink: p|v=0x%x\n", voltage_swing_level + | pre_emphasis_level); + ret = drm_dp_dpcd_write(ctrl->aux, DP_TRAINING_LANE0_SET, + buf, lane_cnt); + if (ret == lane_cnt) + ret = 0; + + return ret; +} + +static bool dp_ctrl_train_pattern_set(struct dp_ctrl_private *ctrl, + u8 pattern) +{ + u8 buf; + int ret = 0; + + DRM_DEBUG_DP("sink: pattern=%x\n", pattern); + + buf = pattern; + + if (pattern && pattern != DP_TRAINING_PATTERN_4) + buf |= DP_LINK_SCRAMBLING_DISABLE; + + ret = drm_dp_dpcd_writeb(ctrl->aux, DP_TRAINING_PATTERN_SET, buf); + return ret == 1; +} + +static int dp_ctrl_read_link_status(struct dp_ctrl_private *ctrl, + u8 *link_status) +{ + int len = 0; + u32 const offset = DP_LANE_ALIGN_STATUS_UPDATED - DP_LANE0_1_STATUS; + u32 link_status_read_max_retries = 100; + + while (--link_status_read_max_retries) { + len = drm_dp_dpcd_read_link_status(ctrl->aux, + link_status); + if (len != DP_LINK_STATUS_SIZE) { + DRM_ERROR("DP link status read failed, err: %d\n", len); + return len; + } + + if (!(link_status[offset] & DP_LINK_STATUS_UPDATED)) + return 0; + } + + return -ETIMEDOUT; +} + +static int dp_ctrl_link_train_1(struct dp_ctrl_private *ctrl, + struct dp_cr_status *cr, int *training_step) +{ + int tries, old_v_level, ret = 0; + u8 link_status[DP_LINK_STATUS_SIZE]; + int const maximum_retries = 4; + + dp_catalog_ctrl_state_ctrl(ctrl->catalog, 0); + + *training_step = DP_TRAINING_1; + + ret = dp_catalog_ctrl_set_pattern(ctrl->catalog, DP_TRAINING_PATTERN_1); + if (ret) + return ret; + dp_ctrl_train_pattern_set(ctrl, DP_TRAINING_PATTERN_1 | + DP_LINK_SCRAMBLING_DISABLE); + + ret = dp_ctrl_update_vx_px(ctrl); + if (ret) + return ret; + + tries = 0; + old_v_level = ctrl->link->phy_params.v_level; + for (tries = 0; tries < maximum_retries; tries++) { + drm_dp_link_train_clock_recovery_delay(ctrl->panel->dpcd); + + ret = dp_ctrl_read_link_status(ctrl, link_status); + if (ret) + return ret; + + cr->lane_0_1 = link_status[0]; + cr->lane_2_3 = link_status[1]; + + if (drm_dp_clock_recovery_ok(link_status, + ctrl->link->link_params.num_lanes)) { + return 0; + } + + if (ctrl->link->phy_params.v_level >= + DP_TRAIN_VOLTAGE_SWING_MAX) { + DRM_ERROR_RATELIMITED("max v_level reached\n"); + return -EAGAIN; + } + + if (old_v_level != ctrl->link->phy_params.v_level) { + tries = 0; + old_v_level = ctrl->link->phy_params.v_level; + } + + DRM_DEBUG_DP("clock recovery not done, adjusting vx px\n"); + + dp_link_adjust_levels(ctrl->link, link_status); + ret = dp_ctrl_update_vx_px(ctrl); + if (ret) + return ret; + } + + DRM_ERROR("max tries reached\n"); + return -ETIMEDOUT; +} + +static int dp_ctrl_link_rate_down_shift(struct dp_ctrl_private *ctrl) +{ + int ret = 0; + + switch (ctrl->link->link_params.rate) { + case 810000: + ctrl->link->link_params.rate = 540000; + break; + case 540000: + ctrl->link->link_params.rate = 270000; + break; + case 270000: + ctrl->link->link_params.rate = 162000; + break; + case 162000: + default: + ret = -EINVAL; + break; + }; + + if (!ret) + DRM_DEBUG_DP("new rate=0x%x\n", ctrl->link->link_params.rate); + + return ret; +} + +static int dp_ctrl_link_lane_down_shift(struct dp_ctrl_private *ctrl) +{ + + if (ctrl->link->link_params.num_lanes == 1) + return -1; + + ctrl->link->link_params.num_lanes /= 2; + ctrl->link->link_params.rate = ctrl->panel->link_info.rate; + + ctrl->link->phy_params.p_level = 0; + ctrl->link->phy_params.v_level = 0; + + return 0; +} + +static void dp_ctrl_clear_training_pattern(struct dp_ctrl_private *ctrl) +{ + dp_ctrl_train_pattern_set(ctrl, DP_TRAINING_PATTERN_DISABLE); + drm_dp_link_train_channel_eq_delay(ctrl->panel->dpcd); +} + +static int dp_ctrl_link_train_2(struct dp_ctrl_private *ctrl, + struct dp_cr_status *cr, int *training_step) +{ + int tries = 0, ret = 0; + char pattern; + int const maximum_retries = 5; + u8 link_status[DP_LINK_STATUS_SIZE]; + + dp_catalog_ctrl_state_ctrl(ctrl->catalog, 0); + + *training_step = DP_TRAINING_2; + + if (drm_dp_tps3_supported(ctrl->panel->dpcd)) + pattern = DP_TRAINING_PATTERN_3; + else + pattern = DP_TRAINING_PATTERN_2; + + ret = dp_ctrl_update_vx_px(ctrl); + if (ret) + return ret; + + ret = dp_catalog_ctrl_set_pattern(ctrl->catalog, pattern); + if (ret) + return ret; + + dp_ctrl_train_pattern_set(ctrl, pattern | DP_RECOVERED_CLOCK_OUT_EN); + + for (tries = 0; tries <= maximum_retries; tries++) { + drm_dp_link_train_channel_eq_delay(ctrl->panel->dpcd); + + ret = dp_ctrl_read_link_status(ctrl, link_status); + if (ret) + return ret; + cr->lane_0_1 = link_status[0]; + cr->lane_2_3 = link_status[1]; + + if (drm_dp_channel_eq_ok(link_status, + ctrl->link->link_params.num_lanes)) { + return 0; + } + + dp_link_adjust_levels(ctrl->link, link_status); + ret = dp_ctrl_update_vx_px(ctrl); + if (ret) + return ret; + + } + + return -ETIMEDOUT; +} + +static int dp_ctrl_reinitialize_mainlink(struct dp_ctrl_private *ctrl); + +static int dp_ctrl_link_train(struct dp_ctrl_private *ctrl, + struct dp_cr_status *cr, int *training_step) +{ + int ret = 0; + u8 encoding = DP_SET_ANSI_8B10B; + struct dp_link_info link_info = {0}; + + dp_ctrl_config_ctrl(ctrl); + + link_info.num_lanes = ctrl->link->link_params.num_lanes; + link_info.rate = ctrl->link->link_params.rate; + link_info.capabilities = DP_LINK_CAP_ENHANCED_FRAMING; + + dp_aux_link_configure(ctrl->aux, &link_info); + drm_dp_dpcd_write(ctrl->aux, DP_MAIN_LINK_CHANNEL_CODING_SET, + &encoding, 1); + + ret = dp_ctrl_link_train_1(ctrl, cr, training_step); + if (ret) { + DRM_ERROR("link training #1 failed. ret=%d\n", ret); + goto end; + } + + /* print success info as this is a result of user initiated action */ + DRM_DEBUG_DP("link training #1 successful\n"); + + ret = dp_ctrl_link_train_2(ctrl, cr, training_step); + if (ret) { + DRM_ERROR("link training #2 failed. ret=%d\n", ret); + goto end; + } + + /* print success info as this is a result of user initiated action */ + DRM_DEBUG_DP("link training #2 successful\n"); + +end: + dp_catalog_ctrl_state_ctrl(ctrl->catalog, 0); + + return ret; +} + +static int dp_ctrl_setup_main_link(struct dp_ctrl_private *ctrl, + struct dp_cr_status *cr, int *training_step) +{ + int ret = 0; + + dp_catalog_ctrl_mainlink_ctrl(ctrl->catalog, true); + + if (ctrl->link->sink_request & DP_TEST_LINK_PHY_TEST_PATTERN) + return ret; + + /* + * As part of previous calls, DP controller state might have + * transitioned to PUSH_IDLE. In order to start transmitting + * a link training pattern, we have to first do soft reset. + */ + dp_catalog_ctrl_reset(ctrl->catalog); + + ret = dp_ctrl_link_train(ctrl, cr, training_step); + + return ret; +} + +static void dp_ctrl_set_clock_rate(struct dp_ctrl_private *ctrl, + enum dp_pm_type module, char *name, unsigned long rate) +{ + u32 num = ctrl->parser->mp[module].num_clk; + struct dss_clk *cfg = ctrl->parser->mp[module].clk_config; + + while (num && strcmp(cfg->clk_name, name)) { + num--; + cfg++; + } + + DRM_DEBUG_DP("setting rate=%lu on clk=%s\n", rate, name); + + if (num) + cfg->rate = rate; + else + DRM_ERROR("%s clock doesn't exit to set rate %lu\n", + name, rate); +} + +static int dp_ctrl_enable_mainlink_clocks(struct dp_ctrl_private *ctrl) +{ + int ret = 0; + struct dp_io *dp_io = &ctrl->parser->io; + struct phy *phy = dp_io->phy; + struct phy_configure_opts_dp *opts_dp = &dp_io->phy_opts.dp; + + opts_dp->lanes = ctrl->link->link_params.num_lanes; + opts_dp->link_rate = ctrl->link->link_params.rate / 100; + dp_ctrl_set_clock_rate(ctrl, DP_CTRL_PM, "ctrl_link", + ctrl->link->link_params.rate * 1000); + + phy_configure(phy, &dp_io->phy_opts); + phy_power_on(phy); + + ret = dp_power_clk_enable(ctrl->power, DP_CTRL_PM, true); + if (ret) + DRM_ERROR("Unable to start link clocks. ret=%d\n", ret); + + DRM_DEBUG_DP("link rate=%d pixel_clk=%d\n", + ctrl->link->link_params.rate, ctrl->dp_ctrl.pixel_rate); + + return ret; +} + +static int dp_ctrl_enable_stream_clocks(struct dp_ctrl_private *ctrl) +{ + int ret = 0; + + dp_ctrl_set_clock_rate(ctrl, DP_STREAM_PM, "stream_pixel", + ctrl->dp_ctrl.pixel_rate * 1000); + + ret = dp_power_clk_enable(ctrl->power, DP_STREAM_PM, true); + if (ret) + DRM_ERROR("Unabled to start pixel clocks. ret=%d\n", ret); + + DRM_DEBUG_DP("link rate=%d pixel_clk=%d\n", + ctrl->link->link_params.rate, ctrl->dp_ctrl.pixel_rate); + + return ret; +} + +int dp_ctrl_host_init(struct dp_ctrl *dp_ctrl, bool flip) +{ + struct dp_ctrl_private *ctrl; + struct dp_io *dp_io; + struct phy *phy; + + if (!dp_ctrl) { + DRM_ERROR("Invalid input data\n"); + return -EINVAL; + } + + ctrl = container_of(dp_ctrl, struct dp_ctrl_private, dp_ctrl); + dp_io = &ctrl->parser->io; + phy = dp_io->phy; + + ctrl->dp_ctrl.orientation = flip; + + dp_catalog_ctrl_phy_reset(ctrl->catalog); + phy_init(phy); + dp_catalog_ctrl_enable_irq(ctrl->catalog, true); + + return 0; +} + +/** + * dp_ctrl_host_deinit() - Uninitialize DP controller + * @dp_ctrl: Display Port Driver data + * + * Perform required steps to uninitialize DP controller + * and its resources. + */ +void dp_ctrl_host_deinit(struct dp_ctrl *dp_ctrl) +{ + struct dp_ctrl_private *ctrl; + + if (!dp_ctrl) { + DRM_ERROR("Invalid input data\n"); + return; + } + + ctrl = container_of(dp_ctrl, struct dp_ctrl_private, dp_ctrl); + + dp_catalog_ctrl_enable_irq(ctrl->catalog, false); + + DRM_DEBUG_DP("Host deinitialized successfully\n"); +} + +static bool dp_ctrl_use_fixed_nvid(struct dp_ctrl_private *ctrl) +{ + u8 *dpcd = ctrl->panel->dpcd; + u32 edid_quirks = 0; + + edid_quirks = drm_dp_get_edid_quirks(ctrl->panel->edid); + /* + * For better interop experience, used a fixed NVID=0x8000 + * whenever connected to a VGA dongle downstream. + */ + if (drm_dp_is_branch(dpcd)) + return (drm_dp_has_quirk(&ctrl->panel->desc, edid_quirks, + DP_DPCD_QUIRK_CONSTANT_N)); + + return false; +} + +static int dp_ctrl_reinitialize_mainlink(struct dp_ctrl_private *ctrl) +{ + int ret = 0; + struct dp_io *dp_io = &ctrl->parser->io; + struct phy *phy = dp_io->phy; + struct phy_configure_opts_dp *opts_dp = &dp_io->phy_opts.dp; + + dp_catalog_ctrl_mainlink_ctrl(ctrl->catalog, false); + opts_dp->lanes = ctrl->link->link_params.num_lanes; + phy_configure(phy, &dp_io->phy_opts); + /* + * Disable and re-enable the mainlink clock since the + * link clock might have been adjusted as part of the + * link maintenance. + */ + ret = dp_power_clk_enable(ctrl->power, DP_CTRL_PM, false); + if (ret) { + DRM_ERROR("Failed to disable clocks. ret=%d\n", ret); + return ret; + } + phy_power_off(phy); + /* hw recommended delay before re-enabling clocks */ + msleep(20); + + ret = dp_ctrl_enable_mainlink_clocks(ctrl); + if (ret) { + DRM_ERROR("Failed to enable mainlink clks. ret=%d\n", ret); + return ret; + } + + return ret; +} + +static int dp_ctrl_link_maintenance(struct dp_ctrl_private *ctrl) +{ + int ret = 0; + struct dp_cr_status cr; + int training_step = DP_TRAINING_NONE; + + dp_ctrl_push_idle(&ctrl->dp_ctrl); + dp_catalog_ctrl_reset(ctrl->catalog); + + ctrl->dp_ctrl.pixel_rate = ctrl->panel->dp_mode.drm_mode.clock; + + ret = dp_ctrl_setup_main_link(ctrl, &cr, &training_step); + if (ret) + goto end; + + dp_ctrl_clear_training_pattern(ctrl); + + dp_catalog_ctrl_state_ctrl(ctrl->catalog, DP_STATE_CTRL_SEND_VIDEO); + + ret = dp_ctrl_wait4video_ready(ctrl); +end: + return ret; +} + +static int dp_ctrl_process_phy_test_request(struct dp_ctrl_private *ctrl) +{ + int ret = 0; + + if (!ctrl->link->phy_params.phy_test_pattern_sel) { + DRM_DEBUG_DP("no test pattern selected by sink\n"); + return ret; + } + + /* + * The global reset will need DP link related clocks to be + * running. Add the global reset just before disabling the + * link clocks and core clocks. + */ + ret = dp_ctrl_off(&ctrl->dp_ctrl); + if (ret) { + DRM_ERROR("failed to disable DP controller\n"); + return ret; + } + + ret = dp_ctrl_on_link(&ctrl->dp_ctrl); + if (!ret) + ret = dp_ctrl_on_stream(&ctrl->dp_ctrl); + else + DRM_ERROR("failed to enable DP link controller\n"); + + return ret; +} + +static bool dp_ctrl_send_phy_test_pattern(struct dp_ctrl_private *ctrl) +{ + bool success = false; + u32 pattern_sent = 0x0; + u32 pattern_requested = ctrl->link->phy_params.phy_test_pattern_sel; + + DRM_DEBUG_DP("request: 0x%x\n", pattern_requested); + + if (dp_catalog_ctrl_update_vx_px(ctrl->catalog, + ctrl->link->phy_params.v_level, + ctrl->link->phy_params.p_level)) { + DRM_ERROR("Failed to set v/p levels\n"); + return false; + } + dp_catalog_ctrl_send_phy_pattern(ctrl->catalog, pattern_requested); + dp_ctrl_update_vx_px(ctrl); + dp_link_send_test_response(ctrl->link); + + pattern_sent = dp_catalog_ctrl_read_phy_pattern(ctrl->catalog); + + switch (pattern_sent) { + case MR_LINK_TRAINING1: + success = (pattern_requested == + DP_PHY_TEST_PATTERN_D10_2); + break; + case MR_LINK_SYMBOL_ERM: + success = ((pattern_requested == + DP_PHY_TEST_PATTERN_ERROR_COUNT) || + (pattern_requested == + DP_PHY_TEST_PATTERN_CP2520)); + break; + case MR_LINK_PRBS7: + success = (pattern_requested == + DP_PHY_TEST_PATTERN_PRBS7); + break; + case MR_LINK_CUSTOM80: + success = (pattern_requested == + DP_PHY_TEST_PATTERN_80BIT_CUSTOM); + break; + case MR_LINK_TRAINING4: + success = (pattern_requested == + DP_PHY_TEST_PATTERN_SEL_MASK); + break; + default: + success = false; + } + + DRM_DEBUG_DP("%s: test->0x%x\n", success ? "success" : "failed", + pattern_requested); + return success; +} + +void dp_ctrl_handle_sink_request(struct dp_ctrl *dp_ctrl) +{ + struct dp_ctrl_private *ctrl; + u32 sink_request = 0x0; + + if (!dp_ctrl) { + DRM_ERROR("invalid input\n"); + return; + } + + ctrl = container_of(dp_ctrl, struct dp_ctrl_private, dp_ctrl); + sink_request = ctrl->link->sink_request; + + if (sink_request & DP_TEST_LINK_PHY_TEST_PATTERN) { + DRM_DEBUG_DP("PHY_TEST_PATTERN request\n"); + if (dp_ctrl_process_phy_test_request(ctrl)) { + DRM_ERROR("process phy_test_req failed\n"); + return; + } + } + + if (sink_request & DP_LINK_STATUS_UPDATED) { + if (dp_ctrl_link_maintenance(ctrl)) { + DRM_ERROR("LM failed: TEST_LINK_TRAINING\n"); + return; + } + } + + if (sink_request & DP_TEST_LINK_TRAINING) { + dp_link_send_test_response(ctrl->link); + if (dp_ctrl_link_maintenance(ctrl)) { + DRM_ERROR("LM failed: TEST_LINK_TRAINING\n"); + return; + } + } +} + +int dp_ctrl_on_link(struct dp_ctrl *dp_ctrl) +{ + int rc = 0; + struct dp_ctrl_private *ctrl; + u32 rate = 0; + int link_train_max_retries = 5; + u32 const phy_cts_pixel_clk_khz = 148500; + struct dp_cr_status cr; + unsigned int training_step; + + if (!dp_ctrl) + return -EINVAL; + + ctrl = container_of(dp_ctrl, struct dp_ctrl_private, dp_ctrl); + + rate = ctrl->panel->link_info.rate; + + dp_power_clk_enable(ctrl->power, DP_CORE_PM, true); + + if (ctrl->link->sink_request & DP_TEST_LINK_PHY_TEST_PATTERN) { + DRM_DEBUG_DP("using phy test link parameters\n"); + if (!ctrl->panel->dp_mode.drm_mode.clock) + ctrl->dp_ctrl.pixel_rate = phy_cts_pixel_clk_khz; + } else { + ctrl->link->link_params.rate = rate; + ctrl->link->link_params.num_lanes = + ctrl->panel->link_info.num_lanes; + ctrl->dp_ctrl.pixel_rate = ctrl->panel->dp_mode.drm_mode.clock; + } + + DRM_DEBUG_DP("rate=%d, num_lanes=%d, pixel_rate=%d\n", + ctrl->link->link_params.rate, + ctrl->link->link_params.num_lanes, ctrl->dp_ctrl.pixel_rate); + + rc = dp_ctrl_enable_mainlink_clocks(ctrl); + if (rc) + return rc; + + ctrl->link->phy_params.p_level = 0; + ctrl->link->phy_params.v_level = 0; + + while (--link_train_max_retries && + !atomic_read(&ctrl->dp_ctrl.aborted)) { + rc = dp_ctrl_reinitialize_mainlink(ctrl); + if (rc) { + DRM_ERROR("Failed to reinitialize mainlink. rc=%d\n", + rc); + break; + } + + training_step = DP_TRAINING_NONE; + rc = dp_ctrl_setup_main_link(ctrl, &cr, &training_step); + if (rc == 0) { + /* training completed successfully */ + break; + } else if (training_step == DP_TRAINING_1) { + /* link train_1 failed */ + rc = dp_ctrl_link_rate_down_shift(ctrl); + if (rc < 0) { /* already in RBR = 1.6G */ + if (cr.lane_0_1 & DP_LANE0_1_CR_DONE) { + /* + * some lanes are ready, + * reduce lane number + */ + rc = dp_ctrl_link_lane_down_shift(ctrl); + if (rc < 0) { /* lane == 1 already */ + /* end with failure */ + break; + } + } else { + /* end with failure */ + break; /* lane == 1 already */ + } + } + } else if (training_step == DP_TRAINING_2) { + /* link train_2 failed, lower lane rate */ + rc = dp_ctrl_link_lane_down_shift(ctrl); + if (rc < 0) { + /* end with failure */ + break; /* lane == 1 already */ + } + } + } + + if (ctrl->link->sink_request & DP_TEST_LINK_PHY_TEST_PATTERN) + return rc; + + /* stop txing train pattern */ + dp_ctrl_clear_training_pattern(ctrl); + + /* + * keep transmitting idle pattern until video ready + * to avoid main link from loss of sync + */ + if (rc == 0) /* link train successfully */ + dp_ctrl_push_idle(dp_ctrl); + + return rc; +} + +int dp_ctrl_on_stream(struct dp_ctrl *dp_ctrl) +{ + u32 rate = 0; + int ret = 0; + bool mainlink_ready = false; + struct dp_ctrl_private *ctrl; + + if (!dp_ctrl) + return -EINVAL; + + ctrl = container_of(dp_ctrl, struct dp_ctrl_private, dp_ctrl); + + rate = ctrl->panel->link_info.rate; + + ctrl->link->link_params.rate = rate; + ctrl->link->link_params.num_lanes = ctrl->panel->link_info.num_lanes; + ctrl->dp_ctrl.pixel_rate = ctrl->panel->dp_mode.drm_mode.clock; + + DRM_DEBUG_DP("rate=%d, num_lanes=%d, pixel_rate=%d\n", + ctrl->link->link_params.rate, + ctrl->link->link_params.num_lanes, ctrl->dp_ctrl.pixel_rate); + + if (!dp_power_clk_status(ctrl->power, DP_CTRL_PM)) { /* link clk is off */ + ret = dp_ctrl_enable_mainlink_clocks(ctrl); + if (ret) { + DRM_ERROR("Failed to start link clocks. ret=%d\n", ret); + goto end; + } + } + + ret = dp_ctrl_enable_stream_clocks(ctrl); + if (ret) { + DRM_ERROR("Failed to start pixel clocks. ret=%d\n", ret); + goto end; + } + + if (ctrl->link->sink_request & DP_TEST_LINK_PHY_TEST_PATTERN) { + dp_ctrl_send_phy_test_pattern(ctrl); + return 0; + } + + /* + * Set up transfer unit values and set controller state to send + * video. + */ + dp_ctrl_configure_source_params(ctrl); + + dp_catalog_ctrl_config_msa(ctrl->catalog, + ctrl->link->link_params.rate, + ctrl->dp_ctrl.pixel_rate, dp_ctrl_use_fixed_nvid(ctrl)); + + reinit_completion(&ctrl->video_comp); + + dp_ctrl_setup_tr_unit(ctrl); + + dp_catalog_ctrl_state_ctrl(ctrl->catalog, DP_STATE_CTRL_SEND_VIDEO); + + ret = dp_ctrl_wait4video_ready(ctrl); + if (ret) + return ret; + + mainlink_ready = dp_catalog_ctrl_mainlink_ready(ctrl->catalog); + DRM_DEBUG_DP("mainlink %s\n", mainlink_ready ? "READY" : "NOT READY"); + +end: + return ret; +} + +int dp_ctrl_off(struct dp_ctrl *dp_ctrl) +{ + struct dp_ctrl_private *ctrl; + struct dp_io *dp_io; + struct phy *phy; + int ret = 0; + + if (!dp_ctrl) + return -EINVAL; + + ctrl = container_of(dp_ctrl, struct dp_ctrl_private, dp_ctrl); + dp_io = &ctrl->parser->io; + phy = dp_io->phy; + + dp_catalog_ctrl_mainlink_ctrl(ctrl->catalog, false); + + dp_catalog_ctrl_reset(ctrl->catalog); + + ret = dp_power_clk_enable(ctrl->power, DP_STREAM_PM, false); + if (ret) + DRM_ERROR("Failed to disable pixel clocks. ret=%d\n", ret); + + ret = dp_power_clk_enable(ctrl->power, DP_CTRL_PM, false); + if (ret) { + DRM_ERROR("Failed to disable link clocks. ret=%d\n", ret); + } + + phy_power_off(phy); + phy_exit(phy); + + DRM_DEBUG_DP("DP off done\n"); + return ret; +} + +void dp_ctrl_isr(struct dp_ctrl *dp_ctrl) +{ + struct dp_ctrl_private *ctrl; + u32 isr; + + if (!dp_ctrl) + return; + + ctrl = container_of(dp_ctrl, struct dp_ctrl_private, dp_ctrl); + + isr = dp_catalog_ctrl_get_interrupt(ctrl->catalog); + + if (isr & DP_CTRL_INTR_READY_FOR_VIDEO) { + DRM_DEBUG_DP("dp_video_ready\n"); + complete(&ctrl->video_comp); + } + + if (isr & DP_CTRL_INTR_IDLE_PATTERN_SENT) { + DRM_DEBUG_DP("idle_patterns_sent\n"); + complete(&ctrl->idle_comp); + } +} + +struct dp_ctrl *dp_ctrl_get(struct device *dev, struct dp_link *link, + struct dp_panel *panel, struct drm_dp_aux *aux, + struct dp_power *power, struct dp_catalog *catalog, + struct dp_parser *parser) +{ + struct dp_ctrl_private *ctrl; + + if (!dev || !panel || !aux || + !link || !catalog) { + DRM_ERROR("invalid input\n"); + return ERR_PTR(-EINVAL); + } + + ctrl = devm_kzalloc(dev, sizeof(*ctrl), GFP_KERNEL); + if (!ctrl) { + DRM_ERROR("Mem allocation failure\n"); + return ERR_PTR(-ENOMEM); + } + + init_completion(&ctrl->idle_comp); + init_completion(&ctrl->video_comp); + + /* in parameters */ + ctrl->parser = parser; + ctrl->panel = panel; + ctrl->power = power; + ctrl->aux = aux; + ctrl->link = link; + ctrl->catalog = catalog; + ctrl->dev = dev; + + return &ctrl->dp_ctrl; +} + +void dp_ctrl_put(struct dp_ctrl *dp_ctrl) +{ +} diff --git a/drivers/gpu/drm/msm/dp/dp_ctrl.h b/drivers/gpu/drm/msm/dp/dp_ctrl.h new file mode 100644 index 000000000000..f60ba93c8678 --- /dev/null +++ b/drivers/gpu/drm/msm/dp/dp_ctrl.h @@ -0,0 +1,36 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (c) 2012-2020, The Linux Foundation. All rights reserved. + */ + +#ifndef _DP_CTRL_H_ +#define _DP_CTRL_H_ + +#include "dp_aux.h" +#include "dp_panel.h" +#include "dp_link.h" +#include "dp_parser.h" +#include "dp_power.h" +#include "dp_catalog.h" + +struct dp_ctrl { + bool orientation; + atomic_t aborted; + u32 pixel_rate; +}; + +int dp_ctrl_host_init(struct dp_ctrl *dp_ctrl, bool flip); +void dp_ctrl_host_deinit(struct dp_ctrl *dp_ctrl); +int dp_ctrl_on_link(struct dp_ctrl *dp_ctrl); +int dp_ctrl_on_stream(struct dp_ctrl *dp_ctrl); +int dp_ctrl_off(struct dp_ctrl *dp_ctrl); +void dp_ctrl_push_idle(struct dp_ctrl *dp_ctrl); +void dp_ctrl_isr(struct dp_ctrl *dp_ctrl); +void dp_ctrl_handle_sink_request(struct dp_ctrl *dp_ctrl); +struct dp_ctrl *dp_ctrl_get(struct device *dev, struct dp_link *link, + struct dp_panel *panel, struct drm_dp_aux *aux, + struct dp_power *power, struct dp_catalog *catalog, + struct dp_parser *parser); +void dp_ctrl_put(struct dp_ctrl *dp_ctrl); + +#endif /* _DP_CTRL_H_ */ diff --git a/drivers/gpu/drm/msm/dp/dp_debug.c b/drivers/gpu/drm/msm/dp/dp_debug.c new file mode 100644 index 000000000000..84670bcdcfea --- /dev/null +++ b/drivers/gpu/drm/msm/dp/dp_debug.c @@ -0,0 +1,485 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (c) 2017-2020, The Linux Foundation. All rights reserved. + */ + +#define pr_fmt(fmt)"[drm-dp] %s: " fmt, __func__ + +#include <linux/debugfs.h> +#include <drm/drm_connector.h> +#include <drm/drm_file.h> + +#include "dp_parser.h" +#include "dp_catalog.h" +#include "dp_aux.h" +#include "dp_ctrl.h" +#include "dp_debug.h" +#include "dp_display.h" + +#define DEBUG_NAME "msm_dp" + +struct dp_debug_private { + struct dentry *root; + + struct dp_usbpd *usbpd; + struct dp_link *link; + struct dp_panel *panel; + struct drm_connector **connector; + struct device *dev; + struct drm_device *drm_dev; + + struct dp_debug dp_debug; +}; + +static int dp_debug_check_buffer_overflow(int rc, int *max_size, int *len) +{ + if (rc >= *max_size) { + DRM_ERROR("buffer overflow\n"); + return -EINVAL; + } + *len += rc; + *max_size = SZ_4K - *len; + + return 0; +} + +static ssize_t dp_debug_read_info(struct file *file, char __user *user_buff, + size_t count, loff_t *ppos) +{ + struct dp_debug_private *debug = file->private_data; + char *buf; + u32 len = 0, rc = 0; + u64 lclk = 0; + u32 max_size = SZ_4K; + u32 link_params_rate; + struct drm_display_mode *drm_mode; + + if (!debug) + return -ENODEV; + + if (*ppos) + return 0; + + buf = kzalloc(SZ_4K, GFP_KERNEL); + if (!buf) + return -ENOMEM; + + drm_mode = &debug->panel->dp_mode.drm_mode; + + rc = snprintf(buf + len, max_size, "\tname = %s\n", DEBUG_NAME); + if (dp_debug_check_buffer_overflow(rc, &max_size, &len)) + goto error; + + rc = snprintf(buf + len, max_size, + "\tdp_panel\n\t\tmax_pclk_khz = %d\n", + debug->panel->max_pclk_khz); + if (dp_debug_check_buffer_overflow(rc, &max_size, &len)) + goto error; + + rc = snprintf(buf + len, max_size, + "\tdrm_dp_link\n\t\trate = %u\n", + debug->panel->link_info.rate); + if (dp_debug_check_buffer_overflow(rc, &max_size, &len)) + goto error; + + rc = snprintf(buf + len, max_size, + "\t\tnum_lanes = %u\n", + debug->panel->link_info.num_lanes); + if (dp_debug_check_buffer_overflow(rc, &max_size, &len)) + goto error; + + rc = snprintf(buf + len, max_size, + "\t\tcapabilities = %lu\n", + debug->panel->link_info.capabilities); + if (dp_debug_check_buffer_overflow(rc, &max_size, &len)) + goto error; + + rc = snprintf(buf + len, max_size, + "\tdp_panel_info:\n\t\tactive = %dx%d\n", + drm_mode->hdisplay, + drm_mode->vdisplay); + if (dp_debug_check_buffer_overflow(rc, &max_size, &len)) + goto error; + + rc = snprintf(buf + len, max_size, + "\t\tback_porch = %dx%d\n", + drm_mode->htotal - drm_mode->hsync_end, + drm_mode->vtotal - drm_mode->vsync_end); + if (dp_debug_check_buffer_overflow(rc, &max_size, &len)) + goto error; + + rc = snprintf(buf + len, max_size, + "\t\tfront_porch = %dx%d\n", + drm_mode->hsync_start - drm_mode->hdisplay, + drm_mode->vsync_start - drm_mode->vdisplay); + if (dp_debug_check_buffer_overflow(rc, &max_size, &len)) + goto error; + + rc = snprintf(buf + len, max_size, + "\t\tsync_width = %dx%d\n", + drm_mode->hsync_end - drm_mode->hsync_start, + drm_mode->vsync_end - drm_mode->vsync_start); + if (dp_debug_check_buffer_overflow(rc, &max_size, &len)) + goto error; + + rc = snprintf(buf + len, max_size, + "\t\tactive_low = %dx%d\n", + debug->panel->dp_mode.h_active_low, + debug->panel->dp_mode.v_active_low); + if (dp_debug_check_buffer_overflow(rc, &max_size, &len)) + goto error; + + rc = snprintf(buf + len, max_size, + "\t\th_skew = %d\n", + drm_mode->hskew); + if (dp_debug_check_buffer_overflow(rc, &max_size, &len)) + goto error; + + rc = snprintf(buf + len, max_size, + "\t\trefresh rate = %d\n", + drm_mode_vrefresh(drm_mode)); + if (dp_debug_check_buffer_overflow(rc, &max_size, &len)) + goto error; + + rc = snprintf(buf + len, max_size, + "\t\tpixel clock khz = %d\n", + drm_mode->clock); + if (dp_debug_check_buffer_overflow(rc, &max_size, &len)) + goto error; + + rc = snprintf(buf + len, max_size, + "\t\tbpp = %d\n", + debug->panel->dp_mode.bpp); + if (dp_debug_check_buffer_overflow(rc, &max_size, &len)) + goto error; + + /* Link Information */ + rc = snprintf(buf + len, max_size, + "\tdp_link:\n\t\ttest_requested = %d\n", + debug->link->sink_request); + if (dp_debug_check_buffer_overflow(rc, &max_size, &len)) + goto error; + + rc = snprintf(buf + len, max_size, + "\t\tnum_lanes = %d\n", + debug->link->link_params.num_lanes); + if (dp_debug_check_buffer_overflow(rc, &max_size, &len)) + goto error; + + link_params_rate = debug->link->link_params.rate; + rc = snprintf(buf + len, max_size, + "\t\tbw_code = %d\n", + drm_dp_link_rate_to_bw_code(link_params_rate)); + if (dp_debug_check_buffer_overflow(rc, &max_size, &len)) + goto error; + + lclk = debug->link->link_params.rate * 1000; + rc = snprintf(buf + len, max_size, + "\t\tlclk = %lld\n", lclk); + if (dp_debug_check_buffer_overflow(rc, &max_size, &len)) + goto error; + + rc = snprintf(buf + len, max_size, + "\t\tv_level = %d\n", + debug->link->phy_params.v_level); + if (dp_debug_check_buffer_overflow(rc, &max_size, &len)) + goto error; + + rc = snprintf(buf + len, max_size, + "\t\tp_level = %d\n", + debug->link->phy_params.p_level); + if (dp_debug_check_buffer_overflow(rc, &max_size, &len)) + goto error; + + if (copy_to_user(user_buff, buf, len)) + goto error; + + *ppos += len; + + kfree(buf); + return len; + error: + kfree(buf); + return -EINVAL; +} + +static int dp_test_data_show(struct seq_file *m, void *data) +{ + struct drm_device *dev; + struct dp_debug_private *debug; + struct drm_connector *connector; + struct drm_connector_list_iter conn_iter; + u32 bpc; + + debug = m->private; + dev = debug->drm_dev; + drm_connector_list_iter_begin(dev, &conn_iter); + drm_for_each_connector_iter(connector, &conn_iter) { + + if (connector->connector_type != + DRM_MODE_CONNECTOR_DisplayPort) + continue; + + if (connector->status == connector_status_connected) { + bpc = debug->link->test_video.test_bit_depth; + seq_printf(m, "hdisplay: %d\n", + debug->link->test_video.test_h_width); + seq_printf(m, "vdisplay: %d\n", + debug->link->test_video.test_v_height); + seq_printf(m, "bpc: %u\n", + dp_link_bit_depth_to_bpc(bpc)); + } else + seq_puts(m, "0"); + } + + drm_connector_list_iter_end(&conn_iter); + + return 0; +} +DEFINE_SHOW_ATTRIBUTE(dp_test_data); + +static int dp_test_type_show(struct seq_file *m, void *data) +{ + struct dp_debug_private *debug = m->private; + struct drm_device *dev = debug->drm_dev; + struct drm_connector *connector; + struct drm_connector_list_iter conn_iter; + + drm_connector_list_iter_begin(dev, &conn_iter); + drm_for_each_connector_iter(connector, &conn_iter) { + + if (connector->connector_type != + DRM_MODE_CONNECTOR_DisplayPort) + continue; + + if (connector->status == connector_status_connected) + seq_printf(m, "%02x", DP_TEST_LINK_VIDEO_PATTERN); + else + seq_puts(m, "0"); + } + drm_connector_list_iter_end(&conn_iter); + + return 0; +} +DEFINE_SHOW_ATTRIBUTE(dp_test_type); + +static ssize_t dp_test_active_write(struct file *file, + const char __user *ubuf, + size_t len, loff_t *offp) +{ + char *input_buffer; + int status = 0; + struct dp_debug_private *debug; + struct drm_device *dev; + struct drm_connector *connector; + struct drm_connector_list_iter conn_iter; + int val = 0; + + debug = ((struct seq_file *)file->private_data)->private; + dev = debug->drm_dev; + + if (len == 0) + return 0; + + input_buffer = memdup_user_nul(ubuf, len); + if (IS_ERR(input_buffer)) + return PTR_ERR(input_buffer); + + DRM_DEBUG_DRIVER("Copied %d bytes from user\n", (unsigned int)len); + + drm_connector_list_iter_begin(dev, &conn_iter); + drm_for_each_connector_iter(connector, &conn_iter) { + if (connector->connector_type != + DRM_MODE_CONNECTOR_DisplayPort) + continue; + + if (connector->status == connector_status_connected) { + status = kstrtoint(input_buffer, 10, &val); + if (status < 0) + break; + DRM_DEBUG_DRIVER("Got %d for test active\n", val); + /* To prevent erroneous activation of the compliance + * testing code, only accept an actual value of 1 here + */ + if (val == 1) + debug->panel->video_test = true; + else + debug->panel->video_test = false; + } + } + drm_connector_list_iter_end(&conn_iter); + kfree(input_buffer); + if (status < 0) + return status; + + *offp += len; + return len; +} + +static int dp_test_active_show(struct seq_file *m, void *data) +{ + struct dp_debug_private *debug = m->private; + struct drm_device *dev = debug->drm_dev; + struct drm_connector *connector; + struct drm_connector_list_iter conn_iter; + + drm_connector_list_iter_begin(dev, &conn_iter); + drm_for_each_connector_iter(connector, &conn_iter) { + if (connector->connector_type != + DRM_MODE_CONNECTOR_DisplayPort) + continue; + + if (connector->status == connector_status_connected) { + if (debug->panel->video_test) + seq_puts(m, "1"); + else + seq_puts(m, "0"); + } else + seq_puts(m, "0"); + } + drm_connector_list_iter_end(&conn_iter); + + return 0; +} + +static int dp_test_active_open(struct inode *inode, + struct file *file) +{ + return single_open(file, dp_test_active_show, + inode->i_private); +} + +static const struct file_operations dp_debug_fops = { + .open = simple_open, + .read = dp_debug_read_info, +}; + +static const struct file_operations test_active_fops = { + .owner = THIS_MODULE, + .open = dp_test_active_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, + .write = dp_test_active_write +}; + +static int dp_debug_init(struct dp_debug *dp_debug, struct drm_minor *minor) +{ + int rc = 0; + struct dp_debug_private *debug = container_of(dp_debug, + struct dp_debug_private, dp_debug); + struct dentry *file; + struct dentry *test_active; + struct dentry *test_data, *test_type; + + file = debugfs_create_file("dp_debug", 0444, minor->debugfs_root, + debug, &dp_debug_fops); + if (IS_ERR_OR_NULL(file)) { + rc = PTR_ERR(file); + DRM_ERROR("[%s] debugfs create file failed, rc=%d\n", + DEBUG_NAME, rc); + } + + test_active = debugfs_create_file("msm_dp_test_active", 0444, + minor->debugfs_root, + debug, &test_active_fops); + if (IS_ERR_OR_NULL(test_active)) { + rc = PTR_ERR(test_active); + DRM_ERROR("[%s] debugfs test_active failed, rc=%d\n", + DEBUG_NAME, rc); + } + + test_data = debugfs_create_file("msm_dp_test_data", 0444, + minor->debugfs_root, + debug, &dp_test_data_fops); + if (IS_ERR_OR_NULL(test_data)) { + rc = PTR_ERR(test_data); + DRM_ERROR("[%s] debugfs test_data failed, rc=%d\n", + DEBUG_NAME, rc); + } + + test_type = debugfs_create_file("msm_dp_test_type", 0444, + minor->debugfs_root, + debug, &dp_test_type_fops); + if (IS_ERR_OR_NULL(test_type)) { + rc = PTR_ERR(test_type); + DRM_ERROR("[%s] debugfs test_type failed, rc=%d\n", + DEBUG_NAME, rc); + } + + debug->root = minor->debugfs_root; + + return rc; +} + +struct dp_debug *dp_debug_get(struct device *dev, struct dp_panel *panel, + struct dp_usbpd *usbpd, struct dp_link *link, + struct drm_connector **connector, struct drm_minor *minor) +{ + int rc = 0; + struct dp_debug_private *debug; + struct dp_debug *dp_debug; + + if (!dev || !panel || !usbpd || !link) { + DRM_ERROR("invalid input\n"); + rc = -EINVAL; + goto error; + } + + debug = devm_kzalloc(dev, sizeof(*debug), GFP_KERNEL); + if (!debug) { + rc = -ENOMEM; + goto error; + } + + debug->dp_debug.debug_en = false; + debug->usbpd = usbpd; + debug->link = link; + debug->panel = panel; + debug->dev = dev; + debug->drm_dev = minor->dev; + debug->connector = connector; + + dp_debug = &debug->dp_debug; + dp_debug->vdisplay = 0; + dp_debug->hdisplay = 0; + dp_debug->vrefresh = 0; + + rc = dp_debug_init(dp_debug, minor); + if (rc) { + devm_kfree(dev, debug); + goto error; + } + + return dp_debug; + error: + return ERR_PTR(rc); +} + +static int dp_debug_deinit(struct dp_debug *dp_debug) +{ + struct dp_debug_private *debug; + + if (!dp_debug) + return -EINVAL; + + debug = container_of(dp_debug, struct dp_debug_private, dp_debug); + + debugfs_remove_recursive(debug->root); + + return 0; +} + +void dp_debug_put(struct dp_debug *dp_debug) +{ + struct dp_debug_private *debug; + + if (!dp_debug) + return; + + debug = container_of(dp_debug, struct dp_debug_private, dp_debug); + + dp_debug_deinit(dp_debug); + + devm_kfree(debug->dev, debug); +} diff --git a/drivers/gpu/drm/msm/dp/dp_debug.h b/drivers/gpu/drm/msm/dp/dp_debug.h new file mode 100644 index 000000000000..7eaedfbb149c --- /dev/null +++ b/drivers/gpu/drm/msm/dp/dp_debug.h @@ -0,0 +1,74 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (c) 2017-2020, The Linux Foundation. All rights reserved. + */ + +#ifndef _DP_DEBUG_H_ +#define _DP_DEBUG_H_ + +#include "dp_panel.h" +#include "dp_link.h" + +/** + * struct dp_debug + * @debug_en: specifies whether debug mode enabled + * @vdisplay: used to filter out vdisplay value + * @hdisplay: used to filter out hdisplay value + * @vrefresh: used to filter out vrefresh value + * @tpg_state: specifies whether tpg feature is enabled + */ +struct dp_debug { + bool debug_en; + int aspect_ratio; + int vdisplay; + int hdisplay; + int vrefresh; +}; + +#if defined(CONFIG_DEBUG_FS) + +/** + * dp_debug_get() - configure and get the DisplayPlot debug module data + * + * @dev: device instance of the caller + * @panel: instance of panel module + * @usbpd: instance of usbpd module + * @link: instance of link module + * @connector: double pointer to display connector + * @minor: pointer to drm minor number after device registration + * return: pointer to allocated debug module data + * + * This function sets up the debug module and provides a way + * for debugfs input to be communicated with existing modules + */ +struct dp_debug *dp_debug_get(struct device *dev, struct dp_panel *panel, + struct dp_usbpd *usbpd, struct dp_link *link, + struct drm_connector **connector, + struct drm_minor *minor); + +/** + * dp_debug_put() + * + * Cleans up dp_debug instance + * + * @dp_debug: instance of dp_debug + */ +void dp_debug_put(struct dp_debug *dp_debug); + +#else + +static inline +struct dp_debug *dp_debug_get(struct device *dev, struct dp_panel *panel, + struct dp_usbpd *usbpd, struct dp_link *link, + struct drm_connector **connector, struct drm_minor *minor) +{ + return ERR_PTR(-EINVAL); +} + +static inline void dp_debug_put(struct dp_debug *dp_debug) +{ +} + +#endif /* defined(CONFIG_DEBUG_FS) */ + +#endif /* _DP_DEBUG_H_ */ diff --git a/drivers/gpu/drm/msm/dp/dp_display.c b/drivers/gpu/drm/msm/dp/dp_display.c new file mode 100644 index 000000000000..e175aa3fd3a9 --- /dev/null +++ b/drivers/gpu/drm/msm/dp/dp_display.c @@ -0,0 +1,1463 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (c) 2017-2020, The Linux Foundation. All rights reserved. + */ + +#include <linux/module.h> +#include <linux/slab.h> +#include <linux/uaccess.h> +#include <linux/debugfs.h> +#include <linux/component.h> +#include <linux/of_irq.h> +#include <linux/delay.h> + +#include "msm_drv.h" +#include "msm_kms.h" +#include "dp_hpd.h" +#include "dp_parser.h" +#include "dp_power.h" +#include "dp_catalog.h" +#include "dp_aux.h" +#include "dp_reg.h" +#include "dp_link.h" +#include "dp_panel.h" +#include "dp_ctrl.h" +#include "dp_display.h" +#include "dp_drm.h" +#include "dp_audio.h" +#include "dp_debug.h" + +static struct msm_dp *g_dp_display; +#define HPD_STRING_SIZE 30 + +enum { + ISR_DISCONNECTED, + ISR_CONNECT_PENDING, + ISR_CONNECTED, + ISR_HPD_REPLUG_COUNT, + ISR_IRQ_HPD_PULSE_COUNT, + ISR_HPD_LO_GLITH_COUNT, +}; + +/* event thread connection state */ +enum { + ST_DISCONNECTED, + ST_CONNECT_PENDING, + ST_CONNECTED, + ST_DISCONNECT_PENDING, + ST_SUSPEND_PENDING, + ST_SUSPENDED, +}; + +enum { + EV_NO_EVENT, + /* hpd events */ + EV_HPD_INIT_SETUP, + EV_HPD_PLUG_INT, + EV_IRQ_HPD_INT, + EV_HPD_REPLUG_INT, + EV_HPD_UNPLUG_INT, + EV_USER_NOTIFICATION, + EV_CONNECT_PENDING_TIMEOUT, + EV_DISCONNECT_PENDING_TIMEOUT, +}; + +#define EVENT_TIMEOUT (HZ/10) /* 100ms */ +#define DP_EVENT_Q_MAX 8 + +#define DP_TIMEOUT_5_SECOND (5000/EVENT_TIMEOUT) +#define DP_TIMEOUT_NONE 0 + +#define WAIT_FOR_RESUME_TIMEOUT_JIFFIES (HZ / 2) + +struct dp_event { + u32 event_id; + u32 data; + u32 delay; +}; + +struct dp_display_private { + char *name; + int irq; + + /* state variables */ + bool core_initialized; + bool hpd_irq_on; + bool audio_supported; + + struct platform_device *pdev; + struct dentry *root; + + struct dp_usbpd *usbpd; + struct dp_parser *parser; + struct dp_power *power; + struct dp_catalog *catalog; + struct drm_dp_aux *aux; + struct dp_link *link; + struct dp_panel *panel; + struct dp_ctrl *ctrl; + struct dp_debug *debug; + + struct dp_usbpd_cb usbpd_cb; + struct dp_display_mode dp_mode; + struct msm_dp dp_display; + + /* wait for audio signaling */ + struct completion audio_comp; + + /* event related only access by event thread */ + struct mutex event_mutex; + wait_queue_head_t event_q; + atomic_t hpd_state; + u32 event_pndx; + u32 event_gndx; + struct dp_event event_list[DP_EVENT_Q_MAX]; + spinlock_t event_lock; + + struct completion resume_comp; + + struct dp_audio *audio; +}; + +static const struct of_device_id dp_dt_match[] = { + {.compatible = "qcom,sc7180-dp"}, + {} +}; + +static int dp_add_event(struct dp_display_private *dp_priv, u32 event, + u32 data, u32 delay) +{ + unsigned long flag; + struct dp_event *todo; + int pndx; + + spin_lock_irqsave(&dp_priv->event_lock, flag); + pndx = dp_priv->event_pndx + 1; + pndx %= DP_EVENT_Q_MAX; + if (pndx == dp_priv->event_gndx) { + pr_err("event_q is full: pndx=%d gndx=%d\n", + dp_priv->event_pndx, dp_priv->event_gndx); + spin_unlock_irqrestore(&dp_priv->event_lock, flag); + return -EPERM; + } + todo = &dp_priv->event_list[dp_priv->event_pndx++]; + dp_priv->event_pndx %= DP_EVENT_Q_MAX; + todo->event_id = event; + todo->data = data; + todo->delay = delay; + wake_up(&dp_priv->event_q); + spin_unlock_irqrestore(&dp_priv->event_lock, flag); + + return 0; +} + +static int dp_del_event(struct dp_display_private *dp_priv, u32 event) +{ + unsigned long flag; + struct dp_event *todo; + u32 gndx; + + spin_lock_irqsave(&dp_priv->event_lock, flag); + if (dp_priv->event_pndx == dp_priv->event_gndx) { + spin_unlock_irqrestore(&dp_priv->event_lock, flag); + return -ENOENT; + } + + gndx = dp_priv->event_gndx; + while (dp_priv->event_pndx != gndx) { + todo = &dp_priv->event_list[gndx]; + if (todo->event_id == event) { + todo->event_id = EV_NO_EVENT; /* deleted */ + todo->delay = 0; + } + gndx++; + gndx %= DP_EVENT_Q_MAX; + } + spin_unlock_irqrestore(&dp_priv->event_lock, flag); + + return 0; +} + +void dp_display_signal_audio_complete(struct msm_dp *dp_display) +{ + struct dp_display_private *dp; + + dp = container_of(dp_display, struct dp_display_private, dp_display); + + complete_all(&dp->audio_comp); +} + +static int dp_display_bind(struct device *dev, struct device *master, + void *data) +{ + int rc = 0; + struct dp_display_private *dp; + struct drm_device *drm; + struct msm_drm_private *priv; + + drm = dev_get_drvdata(master); + + dp = container_of(g_dp_display, + struct dp_display_private, dp_display); + if (!dp) { + DRM_ERROR("DP driver bind failed. Invalid driver data\n"); + return -EINVAL; + } + + dp->dp_display.drm_dev = drm; + priv = drm->dev_private; + priv->dp = &(dp->dp_display); + + rc = dp->parser->parse(dp->parser); + if (rc) { + DRM_ERROR("device tree parsing failed\n"); + goto end; + } + + rc = dp_aux_register(dp->aux); + if (rc) { + DRM_ERROR("DRM DP AUX register failed\n"); + goto end; + } + + rc = dp_power_client_init(dp->power); + if (rc) { + DRM_ERROR("Power client create failed\n"); + goto end; + } + + rc = dp_register_audio_driver(dev, dp->audio); + if (rc) + DRM_ERROR("Audio registration Dp failed\n"); + +end: + return rc; +} + +static void dp_display_unbind(struct device *dev, struct device *master, + void *data) +{ + struct dp_display_private *dp; + struct drm_device *drm = dev_get_drvdata(master); + struct msm_drm_private *priv = drm->dev_private; + + dp = container_of(g_dp_display, + struct dp_display_private, dp_display); + if (!dp) { + DRM_ERROR("Invalid DP driver data\n"); + return; + } + + dp_power_client_deinit(dp->power); + dp_aux_unregister(dp->aux); + priv->dp = NULL; +} + +static const struct component_ops dp_display_comp_ops = { + .bind = dp_display_bind, + .unbind = dp_display_unbind, +}; + +static bool dp_display_is_ds_bridge(struct dp_panel *panel) +{ + return (panel->dpcd[DP_DOWNSTREAMPORT_PRESENT] & + DP_DWN_STRM_PORT_PRESENT); +} + +static bool dp_display_is_sink_count_zero(struct dp_display_private *dp) +{ + return dp_display_is_ds_bridge(dp->panel) && + (dp->link->sink_count == 0); +} + +static void dp_display_send_hpd_event(struct msm_dp *dp_display) +{ + struct dp_display_private *dp; + struct drm_connector *connector; + + dp = container_of(dp_display, struct dp_display_private, dp_display); + + connector = dp->dp_display.connector; + drm_helper_hpd_irq_event(connector->dev); +} + +static int dp_display_send_hpd_notification(struct dp_display_private *dp, + bool hpd) +{ + static bool encoder_mode_set; + struct msm_drm_private *priv = dp->dp_display.drm_dev->dev_private; + struct msm_kms *kms = priv->kms; + + if ((hpd && dp->dp_display.is_connected) || + (!hpd && !dp->dp_display.is_connected)) { + DRM_DEBUG_DP("HPD already %s\n", (hpd ? "on" : "off")); + return 0; + } + + /* reset video pattern flag on disconnect */ + if (!hpd) + dp->panel->video_test = false; + + dp->dp_display.is_connected = hpd; + + if (dp->dp_display.is_connected && dp->dp_display.encoder + && !encoder_mode_set + && kms->funcs->set_encoder_mode) { + kms->funcs->set_encoder_mode(kms, + dp->dp_display.encoder, false); + DRM_DEBUG_DP("set_encoder_mode() Completed\n"); + encoder_mode_set = true; + } + + dp_display_send_hpd_event(&dp->dp_display); + + return 0; +} + +static int dp_display_process_hpd_high(struct dp_display_private *dp) +{ + int rc = 0; + struct edid *edid; + + dp->panel->max_dp_lanes = dp->parser->max_dp_lanes; + + rc = dp_panel_read_sink_caps(dp->panel, dp->dp_display.connector); + if (rc) + goto end; + + dp_link_process_request(dp->link); + + edid = dp->panel->edid; + + dp->audio_supported = drm_detect_monitor_audio(edid); + dp_panel_handle_sink_request(dp->panel); + + dp->dp_display.max_pclk_khz = DP_MAX_PIXEL_CLK_KHZ; + dp->dp_display.max_dp_lanes = dp->parser->max_dp_lanes; + + rc = dp_ctrl_on_link(dp->ctrl); + if (rc) { + DRM_ERROR("failed to complete DP link training\n"); + goto end; + } + + dp_add_event(dp, EV_USER_NOTIFICATION, true, 0); + + +end: + return rc; +} + +static void dp_display_host_init(struct dp_display_private *dp) +{ + bool flip = false; + + if (dp->core_initialized) { + DRM_DEBUG_DP("DP core already initialized\n"); + return; + } + + if (dp->usbpd->orientation == ORIENTATION_CC2) + flip = true; + + dp_power_init(dp->power, flip); + dp_ctrl_host_init(dp->ctrl, flip); + dp_aux_init(dp->aux); + dp->core_initialized = true; +} + +static int dp_display_usbpd_configure_cb(struct device *dev) +{ + int rc = 0; + struct dp_display_private *dp; + + if (!dev) { + DRM_ERROR("invalid dev\n"); + rc = -EINVAL; + goto end; + } + + dp = container_of(g_dp_display, + struct dp_display_private, dp_display); + if (!dp) { + DRM_ERROR("no driver data found\n"); + rc = -ENODEV; + goto end; + } + + dp_display_host_init(dp); + + /* + * set sink to normal operation mode -- D0 + * before dpcd read + */ + dp_link_psm_config(dp->link, &dp->panel->link_info, false); + rc = dp_display_process_hpd_high(dp); +end: + return rc; +} + +static int dp_display_usbpd_disconnect_cb(struct device *dev) +{ + int rc = 0; + struct dp_display_private *dp; + + if (!dev) { + DRM_ERROR("invalid dev\n"); + rc = -EINVAL; + return rc; + } + + dp = container_of(g_dp_display, + struct dp_display_private, dp_display); + if (!dp) { + DRM_ERROR("no driver data found\n"); + rc = -ENODEV; + return rc; + } + + dp_add_event(dp, EV_USER_NOTIFICATION, false, 0); + + return rc; +} + +static void dp_display_handle_video_request(struct dp_display_private *dp) +{ + if (dp->link->sink_request & DP_TEST_LINK_VIDEO_PATTERN) { + dp->panel->video_test = true; + dp_link_send_test_response(dp->link); + } +} + +static int dp_display_handle_irq_hpd(struct dp_display_private *dp) +{ + u32 sink_request; + + sink_request = dp->link->sink_request; + + if (sink_request & DS_PORT_STATUS_CHANGED) { + dp_add_event(dp, EV_USER_NOTIFICATION, false, 0); + if (dp_display_is_sink_count_zero(dp)) { + DRM_DEBUG_DP("sink count is zero, nothing to do\n"); + return 0; + } + + return dp_display_process_hpd_high(dp); + } + + dp_ctrl_handle_sink_request(dp->ctrl); + + if (dp->link->sink_request & DP_TEST_LINK_VIDEO_PATTERN) + dp_display_handle_video_request(dp); + + return 0; +} + +static int dp_display_usbpd_attention_cb(struct device *dev) +{ + int rc = 0; + struct dp_display_private *dp; + + if (!dev) { + DRM_ERROR("invalid dev\n"); + return -EINVAL; + } + + dp = container_of(g_dp_display, + struct dp_display_private, dp_display); + if (!dp) { + DRM_ERROR("no driver data found\n"); + return -ENODEV; + } + + /* check for any test request issued by sink */ + rc = dp_link_process_request(dp->link); + if (!rc) + dp_display_handle_irq_hpd(dp); + + return rc; +} + +static int dp_hpd_plug_handle(struct dp_display_private *dp, u32 data) +{ + struct dp_usbpd *hpd = dp->usbpd; + u32 state; + u32 tout = DP_TIMEOUT_5_SECOND; + int ret; + + if (!hpd) + return 0; + + mutex_lock(&dp->event_mutex); + + state = atomic_read(&dp->hpd_state); + if (state == ST_SUSPEND_PENDING) { + mutex_unlock(&dp->event_mutex); + return 0; + } + + if (state == ST_CONNECT_PENDING || state == ST_CONNECTED) { + mutex_unlock(&dp->event_mutex); + return 0; + } + + if (state == ST_DISCONNECT_PENDING) { + /* wait until ST_DISCONNECTED */ + dp_add_event(dp, EV_HPD_PLUG_INT, 0, 1); /* delay = 1 */ + mutex_unlock(&dp->event_mutex); + return 0; + } + + if (state == ST_SUSPENDED) + tout = DP_TIMEOUT_NONE; + + atomic_set(&dp->hpd_state, ST_CONNECT_PENDING); + + hpd->hpd_high = 1; + + ret = dp_display_usbpd_configure_cb(&dp->pdev->dev); + if (ret) { /* failed */ + hpd->hpd_high = 0; + atomic_set(&dp->hpd_state, ST_DISCONNECTED); + } + + /* start sanity checking */ + dp_add_event(dp, EV_CONNECT_PENDING_TIMEOUT, 0, tout); + + mutex_unlock(&dp->event_mutex); + + /* uevent will complete connection part */ + return 0; +}; + +static int dp_display_enable(struct dp_display_private *dp, u32 data); +static int dp_display_disable(struct dp_display_private *dp, u32 data); + +static int dp_connect_pending_timeout(struct dp_display_private *dp, u32 data) +{ + u32 state; + + mutex_lock(&dp->event_mutex); + + state = atomic_read(&dp->hpd_state); + if (state == ST_CONNECT_PENDING) { + dp_display_enable(dp, 0); + atomic_set(&dp->hpd_state, ST_CONNECTED); + } + + mutex_unlock(&dp->event_mutex); + + return 0; +} + +static void dp_display_handle_plugged_change(struct msm_dp *dp_display, + bool plugged) +{ + if (dp_display->plugged_cb && dp_display->codec_dev) + dp_display->plugged_cb(dp_display->codec_dev, plugged); +} + +static int dp_hpd_unplug_handle(struct dp_display_private *dp, u32 data) +{ + struct dp_usbpd *hpd = dp->usbpd; + u32 state; + + if (!hpd) + return 0; + + mutex_lock(&dp->event_mutex); + + state = atomic_read(&dp->hpd_state); + if (state == ST_SUSPEND_PENDING) { + mutex_unlock(&dp->event_mutex); + return 0; + } + + if (state == ST_DISCONNECT_PENDING || state == ST_DISCONNECTED) { + mutex_unlock(&dp->event_mutex); + return 0; + } + + if (state == ST_CONNECT_PENDING) { + /* wait until CONNECTED */ + dp_add_event(dp, EV_HPD_UNPLUG_INT, 0, 1); /* delay = 1 */ + mutex_unlock(&dp->event_mutex); + return 0; + } + + atomic_set(&dp->hpd_state, ST_DISCONNECT_PENDING); + + /* disable HPD plug interrupt until disconnect is done */ + dp_catalog_hpd_config_intr(dp->catalog, DP_DP_HPD_PLUG_INT_MASK + | DP_DP_IRQ_HPD_INT_MASK, false); + + hpd->hpd_high = 0; + + /* + * We don't need separate work for disconnect as + * connect/attention interrupts are disabled + */ + dp_display_usbpd_disconnect_cb(&dp->pdev->dev); + + /* start sanity checking */ + dp_add_event(dp, EV_DISCONNECT_PENDING_TIMEOUT, 0, DP_TIMEOUT_5_SECOND); + + /* signal the disconnect event early to ensure proper teardown */ + dp_display_handle_plugged_change(g_dp_display, false); + reinit_completion(&dp->audio_comp); + + dp_catalog_hpd_config_intr(dp->catalog, DP_DP_HPD_PLUG_INT_MASK | + DP_DP_IRQ_HPD_INT_MASK, true); + + /* uevent will complete disconnection part */ + mutex_unlock(&dp->event_mutex); + return 0; +} + +static int dp_disconnect_pending_timeout(struct dp_display_private *dp, u32 data) +{ + u32 state; + + mutex_lock(&dp->event_mutex); + + state = atomic_read(&dp->hpd_state); + if (state == ST_DISCONNECT_PENDING) { + dp_display_disable(dp, 0); + atomic_set(&dp->hpd_state, ST_DISCONNECTED); + } + + mutex_unlock(&dp->event_mutex); + + return 0; +} + +static int dp_irq_hpd_handle(struct dp_display_private *dp, u32 data) +{ + u32 state; + + mutex_lock(&dp->event_mutex); + + /* irq_hpd can happen at either connected or disconnected state */ + state = atomic_read(&dp->hpd_state); + if (state == ST_SUSPEND_PENDING) { + mutex_unlock(&dp->event_mutex); + return 0; + } + + dp_display_usbpd_attention_cb(&dp->pdev->dev); + + mutex_unlock(&dp->event_mutex); + + return 0; +} + +static void dp_display_deinit_sub_modules(struct dp_display_private *dp) +{ + dp_debug_put(dp->debug); + dp_ctrl_put(dp->ctrl); + dp_panel_put(dp->panel); + dp_aux_put(dp->aux); + dp_audio_put(dp->audio); +} + +static int dp_init_sub_modules(struct dp_display_private *dp) +{ + int rc = 0; + struct device *dev = &dp->pdev->dev; + struct dp_usbpd_cb *cb = &dp->usbpd_cb; + struct dp_panel_in panel_in = { + .dev = dev, + }; + + /* Callback APIs used for cable status change event */ + cb->configure = dp_display_usbpd_configure_cb; + cb->disconnect = dp_display_usbpd_disconnect_cb; + cb->attention = dp_display_usbpd_attention_cb; + + dp->usbpd = dp_hpd_get(dev, cb); + if (IS_ERR(dp->usbpd)) { + rc = PTR_ERR(dp->usbpd); + DRM_ERROR("failed to initialize hpd, rc = %d\n", rc); + dp->usbpd = NULL; + goto error; + } + + dp->parser = dp_parser_get(dp->pdev); + if (IS_ERR(dp->parser)) { + rc = PTR_ERR(dp->parser); + DRM_ERROR("failed to initialize parser, rc = %d\n", rc); + dp->parser = NULL; + goto error; + } + + dp->catalog = dp_catalog_get(dev, &dp->parser->io); + if (IS_ERR(dp->catalog)) { + rc = PTR_ERR(dp->catalog); + DRM_ERROR("failed to initialize catalog, rc = %d\n", rc); + dp->catalog = NULL; + goto error; + } + + dp->power = dp_power_get(dp->parser); + if (IS_ERR(dp->power)) { + rc = PTR_ERR(dp->power); + DRM_ERROR("failed to initialize power, rc = %d\n", rc); + dp->power = NULL; + goto error; + } + + dp->aux = dp_aux_get(dev, dp->catalog); + if (IS_ERR(dp->aux)) { + rc = PTR_ERR(dp->aux); + DRM_ERROR("failed to initialize aux, rc = %d\n", rc); + dp->aux = NULL; + goto error; + } + + dp->link = dp_link_get(dev, dp->aux); + if (IS_ERR(dp->link)) { + rc = PTR_ERR(dp->link); + DRM_ERROR("failed to initialize link, rc = %d\n", rc); + dp->link = NULL; + goto error_link; + } + + panel_in.aux = dp->aux; + panel_in.catalog = dp->catalog; + panel_in.link = dp->link; + + dp->panel = dp_panel_get(&panel_in); + if (IS_ERR(dp->panel)) { + rc = PTR_ERR(dp->panel); + DRM_ERROR("failed to initialize panel, rc = %d\n", rc); + dp->panel = NULL; + goto error_link; + } + + dp->ctrl = dp_ctrl_get(dev, dp->link, dp->panel, dp->aux, + dp->power, dp->catalog, dp->parser); + if (IS_ERR(dp->ctrl)) { + rc = PTR_ERR(dp->ctrl); + DRM_ERROR("failed to initialize ctrl, rc = %d\n", rc); + dp->ctrl = NULL; + goto error_ctrl; + } + + dp->audio = dp_audio_get(dp->pdev, dp->panel, dp->catalog); + if (IS_ERR(dp->audio)) { + rc = PTR_ERR(dp->audio); + pr_err("failed to initialize audio, rc = %d\n", rc); + dp->audio = NULL; + goto error_audio; + } + + return rc; + +error_audio: + dp_ctrl_put(dp->ctrl); +error_ctrl: + dp_panel_put(dp->panel); +error_link: + dp_aux_put(dp->aux); +error: + return rc; +} + +static int dp_display_set_mode(struct msm_dp *dp_display, + struct dp_display_mode *mode) +{ + struct dp_display_private *dp; + + dp = container_of(dp_display, struct dp_display_private, dp_display); + + dp->panel->dp_mode.drm_mode = mode->drm_mode; + dp->panel->dp_mode.bpp = mode->bpp; + dp->panel->dp_mode.capabilities = mode->capabilities; + dp_panel_init_panel_info(dp->panel); + return 0; +} + +static int dp_display_prepare(struct msm_dp *dp) +{ + return 0; +} + +static int dp_display_enable(struct dp_display_private *dp, u32 data) +{ + int rc = 0; + struct msm_dp *dp_display; + + dp_display = g_dp_display; + + if (dp_display->power_on) { + DRM_DEBUG_DP("Link already setup, return\n"); + return 0; + } + + rc = dp_ctrl_on_stream(dp->ctrl); + if (!rc) + dp_display->power_on = true; + + /* complete resume_comp regardless it is armed or not */ + complete(&dp->resume_comp); + return rc; +} + +static int dp_display_post_enable(struct msm_dp *dp_display) +{ + struct dp_display_private *dp; + u32 rate; + + dp = container_of(dp_display, struct dp_display_private, dp_display); + + rate = dp->link->link_params.rate; + + if (dp->audio_supported) { + dp->audio->bw_code = drm_dp_link_rate_to_bw_code(rate); + dp->audio->lane_count = dp->link->link_params.num_lanes; + } + + /* signal the connect event late to synchronize video and display */ + dp_display_handle_plugged_change(dp_display, true); + return 0; +} + +static int dp_display_disable(struct dp_display_private *dp, u32 data) +{ + struct msm_dp *dp_display; + + dp_display = g_dp_display; + + if (!dp_display->power_on) + return -EINVAL; + + /* wait only if audio was enabled */ + if (dp_display->audio_enabled) { + if (!wait_for_completion_timeout(&dp->audio_comp, + HZ * 5)) + DRM_ERROR("audio comp timeout\n"); + } + + dp_display->audio_enabled = false; + + dp_ctrl_off(dp->ctrl); + + dp->core_initialized = false; + + dp_display->power_on = false; + + return 0; +} + +static int dp_display_unprepare(struct msm_dp *dp) +{ + return 0; +} + +int dp_display_set_plugged_cb(struct msm_dp *dp_display, + hdmi_codec_plugged_cb fn, struct device *codec_dev) +{ + bool plugged; + + dp_display->plugged_cb = fn; + dp_display->codec_dev = codec_dev; + plugged = dp_display->is_connected; + dp_display_handle_plugged_change(dp_display, plugged); + + return 0; +} + +int dp_display_validate_mode(struct msm_dp *dp, u32 mode_pclk_khz) +{ + const u32 num_components = 3, default_bpp = 24; + struct dp_display_private *dp_display; + struct dp_link_info *link_info; + u32 mode_rate_khz = 0, supported_rate_khz = 0, mode_bpp = 0; + + if (!dp || !mode_pclk_khz || !dp->connector) { + DRM_ERROR("invalid params\n"); + return -EINVAL; + } + + dp_display = container_of(dp, struct dp_display_private, dp_display); + link_info = &dp_display->panel->link_info; + + mode_bpp = dp->connector->display_info.bpc * num_components; + if (!mode_bpp) + mode_bpp = default_bpp; + + mode_bpp = dp_panel_get_mode_bpp(dp_display->panel, + mode_bpp, mode_pclk_khz); + + mode_rate_khz = mode_pclk_khz * mode_bpp; + supported_rate_khz = link_info->num_lanes * link_info->rate * 8; + + if (mode_rate_khz > supported_rate_khz) + return MODE_BAD; + + return MODE_OK; +} + +int dp_display_get_modes(struct msm_dp *dp, + struct dp_display_mode *dp_mode) +{ + struct dp_display_private *dp_display; + int ret = 0; + + if (!dp) { + DRM_ERROR("invalid params\n"); + return 0; + } + + dp_display = container_of(dp, struct dp_display_private, dp_display); + + ret = dp_panel_get_modes(dp_display->panel, + dp->connector, dp_mode); + if (dp_mode->drm_mode.clock) + dp->max_pclk_khz = dp_mode->drm_mode.clock; + return ret; +} + +bool dp_display_check_video_test(struct msm_dp *dp) +{ + struct dp_display_private *dp_display; + + dp_display = container_of(dp, struct dp_display_private, dp_display); + + return dp_display->panel->video_test; +} + +int dp_display_get_test_bpp(struct msm_dp *dp) +{ + struct dp_display_private *dp_display; + + if (!dp) { + DRM_ERROR("invalid params\n"); + return 0; + } + + dp_display = container_of(dp, struct dp_display_private, dp_display); + + return dp_link_bit_depth_to_bpp( + dp_display->link->test_video.test_bit_depth); +} + +static void dp_display_config_hpd(struct dp_display_private *dp) +{ + + dp_display_host_init(dp); + dp_catalog_ctrl_hpd_config(dp->catalog); + + /* Enable interrupt first time + * we are leaving dp clocks on during disconnect + * and never disable interrupt + */ + enable_irq(dp->irq); +} + +static int hpd_event_thread(void *data) +{ + struct dp_display_private *dp_priv; + unsigned long flag; + struct dp_event *todo; + int timeout_mode = 0; + + dp_priv = (struct dp_display_private *)data; + + while (1) { + if (timeout_mode) { + wait_event_timeout(dp_priv->event_q, + (dp_priv->event_pndx == dp_priv->event_gndx), + EVENT_TIMEOUT); + } else { + wait_event_interruptible(dp_priv->event_q, + (dp_priv->event_pndx != dp_priv->event_gndx)); + } + spin_lock_irqsave(&dp_priv->event_lock, flag); + todo = &dp_priv->event_list[dp_priv->event_gndx]; + if (todo->delay) { + struct dp_event *todo_next; + + dp_priv->event_gndx++; + dp_priv->event_gndx %= DP_EVENT_Q_MAX; + + /* re enter delay event into q */ + todo_next = &dp_priv->event_list[dp_priv->event_pndx++]; + dp_priv->event_pndx %= DP_EVENT_Q_MAX; + todo_next->event_id = todo->event_id; + todo_next->data = todo->data; + todo_next->delay = todo->delay - 1; + + /* clean up older event */ + todo->event_id = EV_NO_EVENT; + todo->delay = 0; + + /* switch to timeout mode */ + timeout_mode = 1; + spin_unlock_irqrestore(&dp_priv->event_lock, flag); + continue; + } + + /* timeout with no events in q */ + if (dp_priv->event_pndx == dp_priv->event_gndx) { + spin_unlock_irqrestore(&dp_priv->event_lock, flag); + continue; + } + + dp_priv->event_gndx++; + dp_priv->event_gndx %= DP_EVENT_Q_MAX; + timeout_mode = 0; + spin_unlock_irqrestore(&dp_priv->event_lock, flag); + + switch (todo->event_id) { + case EV_HPD_INIT_SETUP: + dp_display_config_hpd(dp_priv); + break; + case EV_HPD_PLUG_INT: + dp_hpd_plug_handle(dp_priv, todo->data); + break; + case EV_HPD_UNPLUG_INT: + dp_hpd_unplug_handle(dp_priv, todo->data); + break; + case EV_IRQ_HPD_INT: + dp_irq_hpd_handle(dp_priv, todo->data); + break; + case EV_HPD_REPLUG_INT: + /* do nothing */ + break; + case EV_USER_NOTIFICATION: + dp_display_send_hpd_notification(dp_priv, + todo->data); + break; + case EV_CONNECT_PENDING_TIMEOUT: + dp_connect_pending_timeout(dp_priv, + todo->data); + break; + case EV_DISCONNECT_PENDING_TIMEOUT: + dp_disconnect_pending_timeout(dp_priv, + todo->data); + break; + default: + break; + } + } + + return 0; +} + +static void dp_hpd_event_setup(struct dp_display_private *dp_priv) +{ + init_waitqueue_head(&dp_priv->event_q); + spin_lock_init(&dp_priv->event_lock); + + kthread_run(hpd_event_thread, dp_priv, "dp_hpd_handler"); +} + +static irqreturn_t dp_display_irq_handler(int irq, void *dev_id) +{ + struct dp_display_private *dp = dev_id; + irqreturn_t ret = IRQ_HANDLED; + u32 hpd_isr_status; + + if (!dp) { + DRM_ERROR("invalid data\n"); + return IRQ_NONE; + } + + hpd_isr_status = dp_catalog_hpd_get_intr_status(dp->catalog); + + if (hpd_isr_status & 0x0F) { + /* hpd related interrupts */ + if (hpd_isr_status & DP_DP_HPD_PLUG_INT_MASK || + hpd_isr_status & DP_DP_HPD_REPLUG_INT_MASK) { + dp_add_event(dp, EV_HPD_PLUG_INT, 0, 0); + } + + if (hpd_isr_status & DP_DP_IRQ_HPD_INT_MASK) { + /* delete connect pending event first */ + dp_del_event(dp, EV_CONNECT_PENDING_TIMEOUT); + dp_add_event(dp, EV_IRQ_HPD_INT, 0, 0); + } + + if (hpd_isr_status & DP_DP_HPD_REPLUG_INT_MASK) + dp_add_event(dp, EV_HPD_REPLUG_INT, 0, 0); + + if (hpd_isr_status & DP_DP_HPD_UNPLUG_INT_MASK) + dp_add_event(dp, EV_HPD_UNPLUG_INT, 0, 0); + } + + /* DP controller isr */ + dp_ctrl_isr(dp->ctrl); + + /* DP aux isr */ + dp_aux_isr(dp->aux); + + return ret; +} + +int dp_display_request_irq(struct msm_dp *dp_display) +{ + int rc = 0; + struct dp_display_private *dp; + + if (!dp_display) { + DRM_ERROR("invalid input\n"); + return -EINVAL; + } + + dp = container_of(dp_display, struct dp_display_private, dp_display); + + dp->irq = irq_of_parse_and_map(dp->pdev->dev.of_node, 0); + if (dp->irq < 0) { + rc = dp->irq; + DRM_ERROR("failed to get irq: %d\n", rc); + return rc; + } + + rc = devm_request_irq(&dp->pdev->dev, dp->irq, + dp_display_irq_handler, + IRQF_TRIGGER_HIGH, "dp_display_isr", dp); + if (rc < 0) { + DRM_ERROR("failed to request IRQ%u: %d\n", + dp->irq, rc); + return rc; + } + disable_irq(dp->irq); + + return 0; +} + +static int dp_display_probe(struct platform_device *pdev) +{ + int rc = 0; + struct dp_display_private *dp; + + if (!pdev || !pdev->dev.of_node) { + DRM_ERROR("pdev not found\n"); + return -ENODEV; + } + + dp = devm_kzalloc(&pdev->dev, sizeof(*dp), GFP_KERNEL); + if (!dp) + return -ENOMEM; + + dp->pdev = pdev; + dp->name = "drm_dp"; + + rc = dp_init_sub_modules(dp); + if (rc) { + DRM_ERROR("init sub module failed\n"); + return -EPROBE_DEFER; + } + + mutex_init(&dp->event_mutex); + + init_completion(&dp->resume_comp); + + g_dp_display = &dp->dp_display; + + /* Store DP audio handle inside DP display */ + g_dp_display->dp_audio = dp->audio; + + init_completion(&dp->audio_comp); + + platform_set_drvdata(pdev, g_dp_display); + + rc = component_add(&pdev->dev, &dp_display_comp_ops); + if (rc) { + DRM_ERROR("component add failed, rc=%d\n", rc); + dp_display_deinit_sub_modules(dp); + } + + return rc; +} + +static int dp_display_remove(struct platform_device *pdev) +{ + struct dp_display_private *dp; + + dp = container_of(g_dp_display, + struct dp_display_private, dp_display); + + dp_display_deinit_sub_modules(dp); + + component_del(&pdev->dev, &dp_display_comp_ops); + platform_set_drvdata(pdev, NULL); + + return 0; +} + +static int dp_pm_resume(struct device *dev) +{ + return 0; +} + +static int dp_pm_suspend(struct device *dev) +{ + struct platform_device *pdev = to_platform_device(dev); + struct dp_display_private *dp = platform_get_drvdata(pdev); + + if (!dp) { + DRM_ERROR("DP driver bind failed. Invalid driver data\n"); + return -EINVAL; + } + + atomic_set(&dp->hpd_state, ST_SUSPENDED); + + return 0; +} + +static int dp_pm_prepare(struct device *dev) +{ + return 0; +} + +static void dp_pm_complete(struct device *dev) +{ + +} + +static const struct dev_pm_ops dp_pm_ops = { + .suspend = dp_pm_suspend, + .resume = dp_pm_resume, + .prepare = dp_pm_prepare, + .complete = dp_pm_complete, +}; + +static struct platform_driver dp_display_driver = { + .probe = dp_display_probe, + .remove = dp_display_remove, + .driver = { + .name = "msm-dp-display", + .of_match_table = dp_dt_match, + .suppress_bind_attrs = true, + .pm = &dp_pm_ops, + }, +}; + +int __init msm_dp_register(void) +{ + int ret; + + ret = platform_driver_register(&dp_display_driver); + if (ret) + DRM_ERROR("Dp display driver register failed"); + + return ret; +} + +void __exit msm_dp_unregister(void) +{ + platform_driver_unregister(&dp_display_driver); +} + +void msm_dp_irq_postinstall(struct msm_dp *dp_display) +{ + struct dp_display_private *dp; + + if (!dp_display) + return; + + dp = container_of(dp_display, struct dp_display_private, dp_display); + + dp_hpd_event_setup(dp); + + dp_add_event(dp, EV_HPD_INIT_SETUP, 0, 100); +} + +void msm_dp_debugfs_init(struct msm_dp *dp_display, struct drm_minor *minor) +{ + struct dp_display_private *dp; + struct device *dev; + int rc; + + dp = container_of(dp_display, struct dp_display_private, dp_display); + dev = &dp->pdev->dev; + + dp->debug = dp_debug_get(dev, dp->panel, dp->usbpd, + dp->link, &dp->dp_display.connector, + minor); + if (IS_ERR(dp->debug)) { + rc = PTR_ERR(dp->debug); + DRM_ERROR("failed to initialize debug, rc = %d\n", rc); + dp->debug = NULL; + } +} + +int msm_dp_modeset_init(struct msm_dp *dp_display, struct drm_device *dev, + struct drm_encoder *encoder) +{ + struct msm_drm_private *priv; + int ret; + + if (WARN_ON(!encoder) || WARN_ON(!dp_display) || WARN_ON(!dev)) + return -EINVAL; + + priv = dev->dev_private; + dp_display->drm_dev = dev; + + ret = dp_display_request_irq(dp_display); + if (ret) { + DRM_ERROR("request_irq failed, ret=%d\n", ret); + return ret; + } + + dp_display->encoder = encoder; + + dp_display->connector = dp_drm_connector_init(dp_display); + if (IS_ERR(dp_display->connector)) { + ret = PTR_ERR(dp_display->connector); + DRM_DEV_ERROR(dev->dev, + "failed to create dp connector: %d\n", ret); + dp_display->connector = NULL; + return ret; + } + + priv->connectors[priv->num_connectors++] = dp_display->connector; + return 0; +} + +static int dp_display_wait4resume_done(struct dp_display_private *dp) +{ + int ret = 0; + + reinit_completion(&dp->resume_comp); + if (!wait_for_completion_timeout(&dp->resume_comp, + WAIT_FOR_RESUME_TIMEOUT_JIFFIES)) { + DRM_ERROR("wait4resume_done timedout\n"); + ret = -ETIMEDOUT; + } + return ret; +} + +int msm_dp_display_enable(struct msm_dp *dp, struct drm_encoder *encoder) +{ + int rc = 0; + struct dp_display_private *dp_display; + u32 state; + + dp_display = container_of(dp, struct dp_display_private, dp_display); + if (!dp_display->dp_mode.drm_mode.clock) { + DRM_ERROR("invalid params\n"); + return -EINVAL; + } + + mutex_lock(&dp_display->event_mutex); + + rc = dp_display_set_mode(dp, &dp_display->dp_mode); + if (rc) { + DRM_ERROR("Failed to perform a mode set, rc=%d\n", rc); + mutex_unlock(&dp_display->event_mutex); + return rc; + } + + rc = dp_display_prepare(dp); + if (rc) { + DRM_ERROR("DP display prepare failed, rc=%d\n", rc); + mutex_unlock(&dp_display->event_mutex); + return rc; + } + + state = atomic_read(&dp_display->hpd_state); + if (state == ST_SUSPENDED) { + /* start link training */ + dp_add_event(dp_display, EV_HPD_PLUG_INT, 0, 0); + mutex_unlock(&dp_display->event_mutex); + + /* wait until dp interface is up */ + goto resume_done; + } + + dp_display_enable(dp_display, 0); + + rc = dp_display_post_enable(dp); + if (rc) { + DRM_ERROR("DP display post enable failed, rc=%d\n", rc); + dp_display_disable(dp_display, 0); + dp_display_unprepare(dp); + } + + dp_del_event(dp_display, EV_CONNECT_PENDING_TIMEOUT); + + if (state == ST_SUSPEND_PENDING) + dp_add_event(dp_display, EV_IRQ_HPD_INT, 0, 0); + + /* completed connection */ + atomic_set(&dp_display->hpd_state, ST_CONNECTED); + + mutex_unlock(&dp_display->event_mutex); + + return rc; + +resume_done: + dp_display_wait4resume_done(dp_display); + return rc; +} + +int msm_dp_display_pre_disable(struct msm_dp *dp, struct drm_encoder *encoder) +{ + struct dp_display_private *dp_display; + + dp_display = container_of(dp, struct dp_display_private, dp_display); + + dp_ctrl_push_idle(dp_display->ctrl); + + return 0; +} + +int msm_dp_display_disable(struct msm_dp *dp, struct drm_encoder *encoder) +{ + int rc = 0; + u32 state; + struct dp_display_private *dp_display; + + dp_display = container_of(dp, struct dp_display_private, dp_display); + + mutex_lock(&dp_display->event_mutex); + + dp_display_disable(dp_display, 0); + + rc = dp_display_unprepare(dp); + if (rc) + DRM_ERROR("DP display unprepare failed, rc=%d\n", rc); + + dp_del_event(dp_display, EV_DISCONNECT_PENDING_TIMEOUT); + + state = atomic_read(&dp_display->hpd_state); + if (state == ST_DISCONNECT_PENDING) { + /* completed disconnection */ + atomic_set(&dp_display->hpd_state, ST_DISCONNECTED); + } else { + atomic_set(&dp_display->hpd_state, ST_SUSPEND_PENDING); + } + + mutex_unlock(&dp_display->event_mutex); + return rc; +} + +void msm_dp_display_mode_set(struct msm_dp *dp, struct drm_encoder *encoder, + struct drm_display_mode *mode, + struct drm_display_mode *adjusted_mode) +{ + struct dp_display_private *dp_display; + + dp_display = container_of(dp, struct dp_display_private, dp_display); + + memset(&dp_display->dp_mode, 0x0, sizeof(struct dp_display_mode)); + + if (dp_display_check_video_test(dp)) + dp_display->dp_mode.bpp = dp_display_get_test_bpp(dp); + else /* Default num_components per pixel = 3 */ + dp_display->dp_mode.bpp = dp->connector->display_info.bpc * 3; + + if (!dp_display->dp_mode.bpp) + dp_display->dp_mode.bpp = 24; /* Default bpp */ + + drm_mode_copy(&dp_display->dp_mode.drm_mode, adjusted_mode); + + dp_display->dp_mode.v_active_low = + !!(dp_display->dp_mode.drm_mode.flags & DRM_MODE_FLAG_NVSYNC); + + dp_display->dp_mode.h_active_low = + !!(dp_display->dp_mode.drm_mode.flags & DRM_MODE_FLAG_NHSYNC); +} diff --git a/drivers/gpu/drm/msm/dp/dp_display.h b/drivers/gpu/drm/msm/dp/dp_display.h new file mode 100644 index 000000000000..6092ba1ed85e --- /dev/null +++ b/drivers/gpu/drm/msm/dp/dp_display.h @@ -0,0 +1,39 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (c) 2017-2020, The Linux Foundation. All rights reserved. + */ + +#ifndef _DP_DISPLAY_H_ +#define _DP_DISPLAY_H_ + +#include "dp_panel.h" +#include <sound/hdmi-codec.h> + +struct msm_dp { + struct drm_device *drm_dev; + struct device *codec_dev; + struct drm_connector *connector; + struct drm_encoder *encoder; + bool is_connected; + bool audio_enabled; + bool power_on; + + hdmi_codec_plugged_cb plugged_cb; + + u32 max_pclk_khz; + + u32 max_dp_lanes; + struct dp_audio *dp_audio; +}; + +int dp_display_set_plugged_cb(struct msm_dp *dp_display, + hdmi_codec_plugged_cb fn, struct device *codec_dev); +int dp_display_validate_mode(struct msm_dp *dp_display, u32 mode_pclk_khz); +int dp_display_get_modes(struct msm_dp *dp_display, + struct dp_display_mode *dp_mode); +int dp_display_request_irq(struct msm_dp *dp_display); +bool dp_display_check_video_test(struct msm_dp *dp_display); +int dp_display_get_test_bpp(struct msm_dp *dp_display); +void dp_display_signal_audio_complete(struct msm_dp *dp_display); + +#endif /* _DP_DISPLAY_H_ */ diff --git a/drivers/gpu/drm/msm/dp/dp_drm.c b/drivers/gpu/drm/msm/dp/dp_drm.c new file mode 100644 index 000000000000..764f4b81017e --- /dev/null +++ b/drivers/gpu/drm/msm/dp/dp_drm.c @@ -0,0 +1,164 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (c) 2017-2020, The Linux Foundation. All rights reserved. + */ + +#include <drm/drm_atomic_helper.h> +#include <drm/drm_atomic.h> +#include <drm/drm_crtc.h> + +#include "msm_drv.h" +#include "msm_kms.h" +#include "dp_drm.h" + +struct dp_connector { + struct drm_connector base; + struct msm_dp *dp_display; +}; +#define to_dp_connector(x) container_of(x, struct dp_connector, base) + +/** + * dp_connector_detect - callback to determine if connector is connected + * @conn: Pointer to drm connector structure + * @force: Force detect setting from drm framework + * Returns: Connector 'is connected' status + */ +static enum drm_connector_status dp_connector_detect(struct drm_connector *conn, + bool force) +{ + struct msm_dp *dp; + + dp = to_dp_connector(conn)->dp_display; + + DRM_DEBUG_DP("is_connected = %s\n", + (dp->is_connected) ? "true" : "false"); + + return (dp->is_connected) ? connector_status_connected : + connector_status_disconnected; +} + +/** + * dp_connector_get_modes - callback to add drm modes via drm_mode_probed_add() + * @connector: Pointer to drm connector structure + * Returns: Number of modes added + */ +static int dp_connector_get_modes(struct drm_connector *connector) +{ + int rc = 0; + struct msm_dp *dp; + struct dp_display_mode *dp_mode = NULL; + struct drm_display_mode *m, drm_mode; + + if (!connector) + return 0; + + dp = to_dp_connector(connector)->dp_display; + + dp_mode = kzalloc(sizeof(*dp_mode), GFP_KERNEL); + if (!dp_mode) + return 0; + + /* pluggable case assumes EDID is read when HPD */ + if (dp->is_connected) { + /* + *The get_modes() function might return one mode that is stored + * in dp_mode when compliance test is in progress. If not, the + * return value is equal to the total number of modes supported + * by the sink + */ + rc = dp_display_get_modes(dp, dp_mode); + if (rc <= 0) { + DRM_ERROR("failed to get DP sink modes, rc=%d\n", rc); + kfree(dp_mode); + return rc; + } + if (dp_mode->drm_mode.clock) { /* valid DP mode */ + memset(&drm_mode, 0x0, sizeof(drm_mode)); + drm_mode_copy(&drm_mode, &dp_mode->drm_mode); + m = drm_mode_duplicate(connector->dev, &drm_mode); + if (!m) { + DRM_ERROR("failed to add mode %ux%u\n", + drm_mode.hdisplay, + drm_mode.vdisplay); + kfree(dp_mode); + return 0; + } + drm_mode_probed_add(connector, m); + } + } else { + DRM_DEBUG_DP("No sink connected\n"); + } + kfree(dp_mode); + return rc; +} + +/** + * dp_connector_mode_valid - callback to determine if specified mode is valid + * @connector: Pointer to drm connector structure + * @mode: Pointer to drm mode structure + * Returns: Validity status for specified mode + */ +static enum drm_mode_status dp_connector_mode_valid( + struct drm_connector *connector, + struct drm_display_mode *mode) +{ + struct msm_dp *dp_disp; + + dp_disp = to_dp_connector(connector)->dp_display; + + if ((dp_disp->max_pclk_khz <= 0) || + (dp_disp->max_pclk_khz > DP_MAX_PIXEL_CLK_KHZ) || + (mode->clock > dp_disp->max_pclk_khz)) + return MODE_BAD; + + return dp_display_validate_mode(dp_disp, mode->clock); +} + +static const struct drm_connector_funcs dp_connector_funcs = { + .detect = dp_connector_detect, + .fill_modes = drm_helper_probe_single_connector_modes, + .destroy = drm_connector_cleanup, + .reset = drm_atomic_helper_connector_reset, + .atomic_duplicate_state = drm_atomic_helper_connector_duplicate_state, + .atomic_destroy_state = drm_atomic_helper_connector_destroy_state, +}; + +static const struct drm_connector_helper_funcs dp_connector_helper_funcs = { + .get_modes = dp_connector_get_modes, + .mode_valid = dp_connector_mode_valid, +}; + +/* connector initialization */ +struct drm_connector *dp_drm_connector_init(struct msm_dp *dp_display) +{ + struct drm_connector *connector = NULL; + struct dp_connector *dp_connector; + int ret; + + dp_connector = devm_kzalloc(dp_display->drm_dev->dev, + sizeof(*dp_connector), + GFP_KERNEL); + if (!dp_connector) + return ERR_PTR(-ENOMEM); + + dp_connector->dp_display = dp_display; + + connector = &dp_connector->base; + + ret = drm_connector_init(dp_display->drm_dev, connector, + &dp_connector_funcs, + DRM_MODE_CONNECTOR_DisplayPort); + if (ret) + return ERR_PTR(ret); + + drm_connector_helper_add(connector, &dp_connector_helper_funcs); + + /* + * Enable HPD to let hpd event is handled when cable is connected. + */ + connector->polled = DRM_CONNECTOR_POLL_HPD; + + drm_connector_attach_encoder(connector, dp_display->encoder); + + return connector; +} diff --git a/drivers/gpu/drm/msm/dp/dp_drm.h b/drivers/gpu/drm/msm/dp/dp_drm.h new file mode 100644 index 000000000000..c27bfceefdf0 --- /dev/null +++ b/drivers/gpu/drm/msm/dp/dp_drm.h @@ -0,0 +1,18 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (c) 2017-2020, The Linux Foundation. All rights reserved. + */ + +#ifndef _DP_DRM_H_ +#define _DP_DRM_H_ + +#include <linux/types.h> +#include <drm/drm_crtc.h> +#include <drm/drm_crtc_helper.h> + +#include "msm_drv.h" +#include "dp_display.h" + +struct drm_connector *dp_drm_connector_init(struct msm_dp *dp_display); + +#endif /* _DP_DRM_H_ */ diff --git a/drivers/gpu/drm/msm/dp/dp_hpd.c b/drivers/gpu/drm/msm/dp/dp_hpd.c new file mode 100644 index 000000000000..5b8fe32022b5 --- /dev/null +++ b/drivers/gpu/drm/msm/dp/dp_hpd.c @@ -0,0 +1,69 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (c) 2012-2020, The Linux Foundation. All rights reserved. + */ + +#define pr_fmt(fmt) "[drm-dp] %s: " fmt, __func__ + +#include <linux/slab.h> +#include <linux/device.h> + +#include "dp_hpd.h" + +/* DP specific VDM commands */ +#define DP_USBPD_VDM_STATUS 0x10 +#define DP_USBPD_VDM_CONFIGURE 0x11 + +/* USBPD-TypeC specific Macros */ +#define VDM_VERSION 0x0 +#define USB_C_DP_SID 0xFF01 + +struct dp_hpd_private { + struct device *dev; + struct dp_usbpd_cb *dp_cb; + struct dp_usbpd dp_usbpd; +}; + +int dp_hpd_connect(struct dp_usbpd *dp_usbpd, bool hpd) +{ + int rc = 0; + struct dp_hpd_private *hpd_priv; + + hpd_priv = container_of(dp_usbpd, struct dp_hpd_private, + dp_usbpd); + + dp_usbpd->hpd_high = hpd; + + if (!hpd_priv->dp_cb && !hpd_priv->dp_cb->configure + && !hpd_priv->dp_cb->disconnect) { + pr_err("hpd dp_cb not initialized\n"); + return -EINVAL; + } + if (hpd) + hpd_priv->dp_cb->configure(hpd_priv->dev); + else + hpd_priv->dp_cb->disconnect(hpd_priv->dev); + + return rc; +} + +struct dp_usbpd *dp_hpd_get(struct device *dev, struct dp_usbpd_cb *cb) +{ + struct dp_hpd_private *dp_hpd; + + if (!cb) { + pr_err("invalid cb data\n"); + return ERR_PTR(-EINVAL); + } + + dp_hpd = devm_kzalloc(dev, sizeof(*dp_hpd), GFP_KERNEL); + if (!dp_hpd) + return ERR_PTR(-ENOMEM); + + dp_hpd->dev = dev; + dp_hpd->dp_cb = cb; + + dp_hpd->dp_usbpd.connect = dp_hpd_connect; + + return &dp_hpd->dp_usbpd; +} diff --git a/drivers/gpu/drm/msm/dp/dp_hpd.h b/drivers/gpu/drm/msm/dp/dp_hpd.h new file mode 100644 index 000000000000..5bc5bb64680f --- /dev/null +++ b/drivers/gpu/drm/msm/dp/dp_hpd.h @@ -0,0 +1,80 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (c) 2012-2020, The Linux Foundation. All rights reserved. + */ + +#ifndef _DP_HPD_H_ +#define _DP_HPD_H_ + +//#include <linux/usb/usbpd.h> + +#include <linux/types.h> +#include <linux/device.h> + +enum plug_orientation { + ORIENTATION_NONE, + ORIENTATION_CC1, + ORIENTATION_CC2, +}; + +/** + * struct dp_usbpd - DisplayPort status + * + * @orientation: plug orientation configuration + * @low_pow_st: low power state + * @adaptor_dp_en: adaptor functionality enabled + * @multi_func: multi-function preferred + * @usb_config_req: request to switch to usb + * @exit_dp_mode: request exit from displayport mode + * @hpd_high: Hot Plug Detect signal is high. + * @hpd_irq: Change in the status since last message + * @alt_mode_cfg_done: bool to specify alt mode status + * @debug_en: bool to specify debug mode + * @connect: simulate disconnect or connect for debug mode + */ +struct dp_usbpd { + enum plug_orientation orientation; + bool low_pow_st; + bool adaptor_dp_en; + bool multi_func; + bool usb_config_req; + bool exit_dp_mode; + bool hpd_high; + bool hpd_irq; + bool alt_mode_cfg_done; + bool debug_en; + + int (*connect)(struct dp_usbpd *dp_usbpd, bool hpd); +}; + +/** + * struct dp_usbpd_cb - callback functions provided by the client + * + * @configure: called by usbpd module when PD communication has + * been completed and the usb peripheral has been configured on + * dp mode. + * @disconnect: notify the cable disconnect issued by usb. + * @attention: notify any attention message issued by usb. + */ +struct dp_usbpd_cb { + int (*configure)(struct device *dev); + int (*disconnect)(struct device *dev); + int (*attention)(struct device *dev); +}; + +/** + * dp_hpd_get() - setup hpd module + * + * @dev: device instance of the caller + * @cb: struct containing callback function pointers. + * + * This function allows the client to initialize the usbpd + * module. The module will communicate with HPD module. + */ +struct dp_usbpd *dp_hpd_get(struct device *dev, struct dp_usbpd_cb *cb); + +int dp_hpd_register(struct dp_usbpd *dp_usbpd); +void dp_hpd_unregister(struct dp_usbpd *dp_usbpd); +int dp_hpd_connect(struct dp_usbpd *dp_usbpd, bool hpd); + +#endif /* _DP_HPD_H_ */ diff --git a/drivers/gpu/drm/msm/dp/dp_link.c b/drivers/gpu/drm/msm/dp/dp_link.c new file mode 100644 index 000000000000..c811da515fb3 --- /dev/null +++ b/drivers/gpu/drm/msm/dp/dp_link.c @@ -0,0 +1,1210 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (c) 2012-2020, The Linux Foundation. All rights reserved. + */ + +#define pr_fmt(fmt) "[drm-dp] %s: " fmt, __func__ + +#include <drm/drm_print.h> + +#include "dp_link.h" +#include "dp_panel.h" + +#define DP_TEST_REQUEST_MASK 0x7F + +enum audio_sample_rate { + AUDIO_SAMPLE_RATE_32_KHZ = 0x00, + AUDIO_SAMPLE_RATE_44_1_KHZ = 0x01, + AUDIO_SAMPLE_RATE_48_KHZ = 0x02, + AUDIO_SAMPLE_RATE_88_2_KHZ = 0x03, + AUDIO_SAMPLE_RATE_96_KHZ = 0x04, + AUDIO_SAMPLE_RATE_176_4_KHZ = 0x05, + AUDIO_SAMPLE_RATE_192_KHZ = 0x06, +}; + +enum audio_pattern_type { + AUDIO_TEST_PATTERN_OPERATOR_DEFINED = 0x00, + AUDIO_TEST_PATTERN_SAWTOOTH = 0x01, +}; + +struct dp_link_request { + u32 test_requested; + u32 test_link_rate; + u32 test_lane_count; +}; + +struct dp_link_private { + u32 prev_sink_count; + struct device *dev; + struct drm_dp_aux *aux; + struct dp_link dp_link; + + struct dp_link_request request; + struct mutex psm_mutex; + u8 link_status[DP_LINK_STATUS_SIZE]; +}; + +static int dp_aux_link_power_up(struct drm_dp_aux *aux, + struct dp_link_info *link) +{ + u8 value; + int err; + + if (link->revision < 0x11) + return 0; + + err = drm_dp_dpcd_readb(aux, DP_SET_POWER, &value); + if (err < 0) + return err; + + value &= ~DP_SET_POWER_MASK; + value |= DP_SET_POWER_D0; + + err = drm_dp_dpcd_writeb(aux, DP_SET_POWER, value); + if (err < 0) + return err; + + usleep_range(1000, 2000); + + return 0; +} + +static int dp_aux_link_power_down(struct drm_dp_aux *aux, + struct dp_link_info *link) +{ + u8 value; + int err; + + if (link->revision < 0x11) + return 0; + + err = drm_dp_dpcd_readb(aux, DP_SET_POWER, &value); + if (err < 0) + return err; + + value &= ~DP_SET_POWER_MASK; + value |= DP_SET_POWER_D3; + + err = drm_dp_dpcd_writeb(aux, DP_SET_POWER, value); + if (err < 0) + return err; + + return 0; +} + +static int dp_link_get_period(struct dp_link_private *link, int const addr) +{ + int ret = 0; + u8 data; + u32 const max_audio_period = 0xA; + + /* TEST_AUDIO_PERIOD_CH_XX */ + if (drm_dp_dpcd_readb(link->aux, addr, &data) < 0) { + DRM_ERROR("failed to read test_audio_period (0x%x)\n", addr); + ret = -EINVAL; + goto exit; + } + + /* Period - Bits 3:0 */ + data = data & 0xF; + if ((int)data > max_audio_period) { + DRM_ERROR("invalid test_audio_period_ch_1 = 0x%x\n", data); + ret = -EINVAL; + goto exit; + } + + ret = data; +exit: + return ret; +} + +static int dp_link_parse_audio_channel_period(struct dp_link_private *link) +{ + int ret = 0; + struct dp_link_test_audio *req = &link->dp_link.test_audio; + + ret = dp_link_get_period(link, DP_TEST_AUDIO_PERIOD_CH1); + if (ret == -EINVAL) + goto exit; + + req->test_audio_period_ch_1 = ret; + DRM_DEBUG_DP("test_audio_period_ch_1 = 0x%x\n", ret); + + ret = dp_link_get_period(link, DP_TEST_AUDIO_PERIOD_CH2); + if (ret == -EINVAL) + goto exit; + + req->test_audio_period_ch_2 = ret; + DRM_DEBUG_DP("test_audio_period_ch_2 = 0x%x\n", ret); + + /* TEST_AUDIO_PERIOD_CH_3 (Byte 0x275) */ + ret = dp_link_get_period(link, DP_TEST_AUDIO_PERIOD_CH3); + if (ret == -EINVAL) + goto exit; + + req->test_audio_period_ch_3 = ret; + DRM_DEBUG_DP("test_audio_period_ch_3 = 0x%x\n", ret); + + ret = dp_link_get_period(link, DP_TEST_AUDIO_PERIOD_CH4); + if (ret == -EINVAL) + goto exit; + + req->test_audio_period_ch_4 = ret; + DRM_DEBUG_DP("test_audio_period_ch_4 = 0x%x\n", ret); + + ret = dp_link_get_period(link, DP_TEST_AUDIO_PERIOD_CH5); + if (ret == -EINVAL) + goto exit; + + req->test_audio_period_ch_5 = ret; + DRM_DEBUG_DP("test_audio_period_ch_5 = 0x%x\n", ret); + + ret = dp_link_get_period(link, DP_TEST_AUDIO_PERIOD_CH6); + if (ret == -EINVAL) + goto exit; + + req->test_audio_period_ch_6 = ret; + DRM_DEBUG_DP("test_audio_period_ch_6 = 0x%x\n", ret); + + ret = dp_link_get_period(link, DP_TEST_AUDIO_PERIOD_CH7); + if (ret == -EINVAL) + goto exit; + + req->test_audio_period_ch_7 = ret; + DRM_DEBUG_DP("test_audio_period_ch_7 = 0x%x\n", ret); + + ret = dp_link_get_period(link, DP_TEST_AUDIO_PERIOD_CH8); + if (ret == -EINVAL) + goto exit; + + req->test_audio_period_ch_8 = ret; + DRM_DEBUG_DP("test_audio_period_ch_8 = 0x%x\n", ret); +exit: + return ret; +} + +static int dp_link_parse_audio_pattern_type(struct dp_link_private *link) +{ + int ret = 0; + u8 data; + ssize_t rlen; + int const max_audio_pattern_type = 0x1; + + rlen = drm_dp_dpcd_readb(link->aux, + DP_TEST_AUDIO_PATTERN_TYPE, &data); + if (rlen < 0) { + DRM_ERROR("failed to read link audio mode. rlen=%zd\n", rlen); + return rlen; + } + + /* Audio Pattern Type - Bits 7:0 */ + if ((int)data > max_audio_pattern_type) { + DRM_ERROR("invalid audio pattern type = 0x%x\n", data); + ret = -EINVAL; + goto exit; + } + + link->dp_link.test_audio.test_audio_pattern_type = data; + DRM_DEBUG_DP("audio pattern type = 0x%x\n", data); +exit: + return ret; +} + +static int dp_link_parse_audio_mode(struct dp_link_private *link) +{ + int ret = 0; + u8 data; + ssize_t rlen; + int const max_audio_sampling_rate = 0x6; + int const max_audio_channel_count = 0x8; + int sampling_rate = 0x0; + int channel_count = 0x0; + + rlen = drm_dp_dpcd_readb(link->aux, DP_TEST_AUDIO_MODE, &data); + if (rlen < 0) { + DRM_ERROR("failed to read link audio mode. rlen=%zd\n", rlen); + return rlen; + } + + /* Sampling Rate - Bits 3:0 */ + sampling_rate = data & 0xF; + if (sampling_rate > max_audio_sampling_rate) { + DRM_ERROR("sampling rate (0x%x) greater than max (0x%x)\n", + sampling_rate, max_audio_sampling_rate); + ret = -EINVAL; + goto exit; + } + + /* Channel Count - Bits 7:4 */ + channel_count = ((data & 0xF0) >> 4) + 1; + if (channel_count > max_audio_channel_count) { + DRM_ERROR("channel_count (0x%x) greater than max (0x%x)\n", + channel_count, max_audio_channel_count); + ret = -EINVAL; + goto exit; + } + + link->dp_link.test_audio.test_audio_sampling_rate = sampling_rate; + link->dp_link.test_audio.test_audio_channel_count = channel_count; + DRM_DEBUG_DP("sampling_rate = 0x%x, channel_count = 0x%x\n", + sampling_rate, channel_count); +exit: + return ret; +} + +static int dp_link_parse_audio_pattern_params(struct dp_link_private *link) +{ + int ret = 0; + + ret = dp_link_parse_audio_mode(link); + if (ret) + goto exit; + + ret = dp_link_parse_audio_pattern_type(link); + if (ret) + goto exit; + + ret = dp_link_parse_audio_channel_period(link); + +exit: + return ret; +} + +static bool dp_link_is_video_pattern_valid(u32 pattern) +{ + switch (pattern) { + case DP_NO_TEST_PATTERN: + case DP_COLOR_RAMP: + case DP_BLACK_AND_WHITE_VERTICAL_LINES: + case DP_COLOR_SQUARE: + return true; + default: + return false; + } +} + +/** + * dp_link_is_bit_depth_valid() - validates the bit depth requested + * @tbd: bit depth requested by the sink + * + * Returns true if the requested bit depth is supported. + */ +static bool dp_link_is_bit_depth_valid(u32 tbd) +{ + /* DP_TEST_VIDEO_PATTERN_NONE is treated as invalid */ + switch (tbd) { + case DP_TEST_BIT_DEPTH_6: + case DP_TEST_BIT_DEPTH_8: + case DP_TEST_BIT_DEPTH_10: + return true; + default: + return false; + } +} + +static int dp_link_parse_timing_params1(struct dp_link_private *link, + int addr, int len, u32 *val) +{ + u8 bp[2]; + int rlen; + + if (len != 2) + return -EINVAL; + + /* Read the requested video link pattern (Byte 0x221). */ + rlen = drm_dp_dpcd_read(link->aux, addr, bp, len); + if (rlen < len) { + DRM_ERROR("failed to read 0x%x\n", addr); + return -EINVAL; + } + + *val = bp[1] | (bp[0] << 8); + + return 0; +} + +static int dp_link_parse_timing_params2(struct dp_link_private *link, + int addr, int len, + u32 *val1, u32 *val2) +{ + u8 bp[2]; + int rlen; + + if (len != 2) + return -EINVAL; + + /* Read the requested video link pattern (Byte 0x221). */ + rlen = drm_dp_dpcd_read(link->aux, addr, bp, len); + if (rlen < len) { + DRM_ERROR("failed to read 0x%x\n", addr); + return -EINVAL; + } + + *val1 = (bp[0] & BIT(7)) >> 7; + *val2 = bp[1] | ((bp[0] & 0x7F) << 8); + + return 0; +} + +static int dp_link_parse_timing_params3(struct dp_link_private *link, + int addr, u32 *val) +{ + u8 bp; + u32 len = 1; + int rlen; + + rlen = drm_dp_dpcd_read(link->aux, addr, &bp, len); + if (rlen < 1) { + DRM_ERROR("failed to read 0x%x\n", addr); + return -EINVAL; + } + *val = bp; + + return 0; +} + +/** + * dp_parse_video_pattern_params() - parses video pattern parameters from DPCD + * @link: Display Port Driver data + * + * Returns 0 if it successfully parses the video link pattern and the link + * bit depth requested by the sink and, and if the values parsed are valid. + */ +static int dp_link_parse_video_pattern_params(struct dp_link_private *link) +{ + int ret = 0; + ssize_t rlen; + u8 bp; + + rlen = drm_dp_dpcd_readb(link->aux, DP_TEST_PATTERN, &bp); + if (rlen < 0) { + DRM_ERROR("failed to read link video pattern. rlen=%zd\n", + rlen); + return rlen; + } + + if (!dp_link_is_video_pattern_valid(bp)) { + DRM_ERROR("invalid link video pattern = 0x%x\n", bp); + ret = -EINVAL; + return ret; + } + + link->dp_link.test_video.test_video_pattern = bp; + + /* Read the requested color bit depth and dynamic range (Byte 0x232) */ + rlen = drm_dp_dpcd_readb(link->aux, DP_TEST_MISC0, &bp); + if (rlen < 0) { + DRM_ERROR("failed to read link bit depth. rlen=%zd\n", rlen); + return rlen; + } + + /* Dynamic Range */ + link->dp_link.test_video.test_dyn_range = + (bp & DP_TEST_DYNAMIC_RANGE_CEA); + + /* Color bit depth */ + bp &= DP_TEST_BIT_DEPTH_MASK; + if (!dp_link_is_bit_depth_valid(bp)) { + DRM_ERROR("invalid link bit depth = 0x%x\n", bp); + ret = -EINVAL; + return ret; + } + + link->dp_link.test_video.test_bit_depth = bp; + + /* resolution timing params */ + ret = dp_link_parse_timing_params1(link, DP_TEST_H_TOTAL_HI, 2, + &link->dp_link.test_video.test_h_total); + if (ret) { + DRM_ERROR("failed to parse test_htotal(DP_TEST_H_TOTAL_HI)\n"); + return ret; + } + + ret = dp_link_parse_timing_params1(link, DP_TEST_V_TOTAL_HI, 2, + &link->dp_link.test_video.test_v_total); + if (ret) { + DRM_ERROR("failed to parse test_v_total(DP_TEST_V_TOTAL_HI)\n"); + return ret; + } + + ret = dp_link_parse_timing_params1(link, DP_TEST_H_START_HI, 2, + &link->dp_link.test_video.test_h_start); + if (ret) { + DRM_ERROR("failed to parse test_h_start(DP_TEST_H_START_HI)\n"); + return ret; + } + + ret = dp_link_parse_timing_params1(link, DP_TEST_V_START_HI, 2, + &link->dp_link.test_video.test_v_start); + if (ret) { + DRM_ERROR("failed to parse test_v_start(DP_TEST_V_START_HI)\n"); + return ret; + } + + ret = dp_link_parse_timing_params2(link, DP_TEST_HSYNC_HI, 2, + &link->dp_link.test_video.test_hsync_pol, + &link->dp_link.test_video.test_hsync_width); + if (ret) { + DRM_ERROR("failed to parse (DP_TEST_HSYNC_HI)\n"); + return ret; + } + + ret = dp_link_parse_timing_params2(link, DP_TEST_VSYNC_HI, 2, + &link->dp_link.test_video.test_vsync_pol, + &link->dp_link.test_video.test_vsync_width); + if (ret) { + DRM_ERROR("failed to parse (DP_TEST_VSYNC_HI)\n"); + return ret; + } + + ret = dp_link_parse_timing_params1(link, DP_TEST_H_WIDTH_HI, 2, + &link->dp_link.test_video.test_h_width); + if (ret) { + DRM_ERROR("failed to parse test_h_width(DP_TEST_H_WIDTH_HI)\n"); + return ret; + } + + ret = dp_link_parse_timing_params1(link, DP_TEST_V_HEIGHT_HI, 2, + &link->dp_link.test_video.test_v_height); + if (ret) { + DRM_ERROR("failed to parse test_v_height\n"); + return ret; + } + + ret = dp_link_parse_timing_params3(link, DP_TEST_MISC1, + &link->dp_link.test_video.test_rr_d); + link->dp_link.test_video.test_rr_d &= DP_TEST_REFRESH_DENOMINATOR; + if (ret) { + DRM_ERROR("failed to parse test_rr_d (DP_TEST_MISC1)\n"); + return ret; + } + + ret = dp_link_parse_timing_params3(link, DP_TEST_REFRESH_RATE_NUMERATOR, + &link->dp_link.test_video.test_rr_n); + if (ret) { + DRM_ERROR("failed to parse test_rr_n\n"); + return ret; + } + + DRM_DEBUG_DP("link video pattern = 0x%x\n" + "link dynamic range = 0x%x\n" + "link bit depth = 0x%x\n" + "TEST_H_TOTAL = %d, TEST_V_TOTAL = %d\n" + "TEST_H_START = %d, TEST_V_START = %d\n" + "TEST_HSYNC_POL = %d\n" + "TEST_HSYNC_WIDTH = %d\n" + "TEST_VSYNC_POL = %d\n" + "TEST_VSYNC_WIDTH = %d\n" + "TEST_H_WIDTH = %d\n" + "TEST_V_HEIGHT = %d\n" + "TEST_REFRESH_DENOMINATOR = %d\n" + "TEST_REFRESH_NUMERATOR = %d\n", + link->dp_link.test_video.test_video_pattern, + link->dp_link.test_video.test_dyn_range, + link->dp_link.test_video.test_bit_depth, + link->dp_link.test_video.test_h_total, + link->dp_link.test_video.test_v_total, + link->dp_link.test_video.test_h_start, + link->dp_link.test_video.test_v_start, + link->dp_link.test_video.test_hsync_pol, + link->dp_link.test_video.test_hsync_width, + link->dp_link.test_video.test_vsync_pol, + link->dp_link.test_video.test_vsync_width, + link->dp_link.test_video.test_h_width, + link->dp_link.test_video.test_v_height, + link->dp_link.test_video.test_rr_d, + link->dp_link.test_video.test_rr_n); + + return ret; +} + +/** + * dp_link_parse_link_training_params() - parses link training parameters from + * DPCD + * @link: Display Port Driver data + * + * Returns 0 if it successfully parses the link rate (Byte 0x219) and lane + * count (Byte 0x220), and if these values parse are valid. + */ +static int dp_link_parse_link_training_params(struct dp_link_private *link) +{ + u8 bp; + ssize_t rlen; + + rlen = drm_dp_dpcd_readb(link->aux, DP_TEST_LINK_RATE, &bp); + if (rlen < 0) { + DRM_ERROR("failed to read link rate. rlen=%zd\n", rlen); + return rlen; + } + + if (!is_link_rate_valid(bp)) { + DRM_ERROR("invalid link rate = 0x%x\n", bp); + return -EINVAL; + } + + link->request.test_link_rate = bp; + DRM_DEBUG_DP("link rate = 0x%x\n", link->request.test_link_rate); + + rlen = drm_dp_dpcd_readb(link->aux, DP_TEST_LANE_COUNT, &bp); + if (rlen < 0) { + DRM_ERROR("failed to read lane count. rlen=%zd\n", rlen); + return rlen; + } + bp &= DP_MAX_LANE_COUNT_MASK; + + if (!is_lane_count_valid(bp)) { + DRM_ERROR("invalid lane count = 0x%x\n", bp); + return -EINVAL; + } + + link->request.test_lane_count = bp; + DRM_DEBUG_DP("lane count = 0x%x\n", link->request.test_lane_count); + return 0; +} + +/** + * dp_parse_phy_test_params() - parses the phy link parameters + * @link: Display Port Driver data + * + * Parses the DPCD (Byte 0x248) for the DP PHY link pattern that is being + * requested. + */ +static int dp_link_parse_phy_test_params(struct dp_link_private *link) +{ + u8 data; + ssize_t rlen; + + rlen = drm_dp_dpcd_readb(link->aux, DP_PHY_TEST_PATTERN, + &data); + if (rlen < 0) { + DRM_ERROR("failed to read phy link pattern. rlen=%zd\n", rlen); + return rlen; + } + + link->dp_link.phy_params.phy_test_pattern_sel = data & 0x07; + + DRM_DEBUG_DP("phy_test_pattern_sel = 0x%x\n", data); + + switch (data) { + case DP_PHY_TEST_PATTERN_SEL_MASK: + case DP_PHY_TEST_PATTERN_NONE: + case DP_PHY_TEST_PATTERN_D10_2: + case DP_PHY_TEST_PATTERN_ERROR_COUNT: + case DP_PHY_TEST_PATTERN_PRBS7: + case DP_PHY_TEST_PATTERN_80BIT_CUSTOM: + case DP_PHY_TEST_PATTERN_CP2520: + return 0; + default: + return -EINVAL; + } +} + +/** + * dp_link_is_video_audio_test_requested() - checks for audio/video link request + * @link: link requested by the sink + * + * Returns true if the requested link is a permitted audio/video link. + */ +static bool dp_link_is_video_audio_test_requested(u32 link) +{ + u8 video_audio_test = (DP_TEST_LINK_VIDEO_PATTERN | + DP_TEST_LINK_AUDIO_PATTERN | + DP_TEST_LINK_AUDIO_DISABLED_VIDEO); + + return ((link & video_audio_test) && + !(link & ~video_audio_test)); +} + +/** + * dp_link_parse_request() - parses link request parameters from sink + * @link: Display Port Driver data + * + * Parses the DPCD to check if an automated link is requested (Byte 0x201), + * and what type of link automation is being requested (Byte 0x218). + */ +static int dp_link_parse_request(struct dp_link_private *link) +{ + int ret = 0; + u8 data; + ssize_t rlen; + + /** + * Read the device service IRQ vector (Byte 0x201) to determine + * whether an automated link has been requested by the sink. + */ + rlen = drm_dp_dpcd_readb(link->aux, + DP_DEVICE_SERVICE_IRQ_VECTOR, &data); + if (rlen < 0) { + DRM_ERROR("aux read failed. rlen=%zd\n", rlen); + return rlen; + } + + DRM_DEBUG_DP("device service irq vector = 0x%x\n", data); + + if (!(data & DP_AUTOMATED_TEST_REQUEST)) { + DRM_DEBUG_DP("no test requested\n"); + return 0; + } + + /** + * Read the link request byte (Byte 0x218) to determine what type + * of automated link has been requested by the sink. + */ + rlen = drm_dp_dpcd_readb(link->aux, DP_TEST_REQUEST, &data); + if (rlen < 0) { + DRM_ERROR("aux read failed. rlen=%zd\n", rlen); + return rlen; + } + + if (!data || (data == DP_TEST_LINK_FAUX_PATTERN)) { + DRM_DEBUG_DP("link 0x%x not supported\n", data); + goto end; + } + + DRM_DEBUG_DP("Test:(0x%x) requested\n", data); + link->request.test_requested = data; + if (link->request.test_requested == DP_TEST_LINK_PHY_TEST_PATTERN) { + ret = dp_link_parse_phy_test_params(link); + if (ret) + goto end; + ret = dp_link_parse_link_training_params(link); + if (ret) + goto end; + } + + if (link->request.test_requested == DP_TEST_LINK_TRAINING) { + ret = dp_link_parse_link_training_params(link); + if (ret) + goto end; + } + + if (dp_link_is_video_audio_test_requested( + link->request.test_requested)) { + ret = dp_link_parse_video_pattern_params(link); + if (ret) + goto end; + + ret = dp_link_parse_audio_pattern_params(link); + } +end: + /* + * Send a DP_TEST_ACK if all link parameters are valid, otherwise send + * a DP_TEST_NAK. + */ + if (ret) { + link->dp_link.test_response = DP_TEST_NAK; + } else { + if (link->request.test_requested != DP_TEST_LINK_EDID_READ) + link->dp_link.test_response = DP_TEST_ACK; + else + link->dp_link.test_response = + DP_TEST_EDID_CHECKSUM_WRITE; + } + + return ret; +} + +/** + * dp_link_parse_sink_count() - parses the sink count + * @dp_link: pointer to link module data + * + * Parses the DPCD to check if there is an update to the sink count + * (Byte 0x200), and whether all the sink devices connected have Content + * Protection enabled. + */ +static int dp_link_parse_sink_count(struct dp_link *dp_link) +{ + ssize_t rlen; + bool cp_ready; + + struct dp_link_private *link = container_of(dp_link, + struct dp_link_private, dp_link); + + rlen = drm_dp_dpcd_readb(link->aux, DP_SINK_COUNT, + &link->dp_link.sink_count); + if (rlen < 0) { + DRM_ERROR("sink count read failed. rlen=%zd\n", rlen); + return rlen; + } + + cp_ready = link->dp_link.sink_count & DP_SINK_CP_READY; + + link->dp_link.sink_count = + DP_GET_SINK_COUNT(link->dp_link.sink_count); + + DRM_DEBUG_DP("sink_count = 0x%x, cp_ready = 0x%x\n", + link->dp_link.sink_count, cp_ready); + return 0; +} + +static void dp_link_parse_sink_status_field(struct dp_link_private *link) +{ + int len = 0; + + link->prev_sink_count = link->dp_link.sink_count; + dp_link_parse_sink_count(&link->dp_link); + + len = drm_dp_dpcd_read_link_status(link->aux, + link->link_status); + if (len < DP_LINK_STATUS_SIZE) + DRM_ERROR("DP link status read failed\n"); + dp_link_parse_request(link); +} + +/** + * dp_link_process_link_training_request() - processes new training requests + * @link: Display Port link data + * + * This function will handle new link training requests that are initiated by + * the sink. In particular, it will update the requested lane count and link + * rate, and then trigger the link retraining procedure. + * + * The function will return 0 if a link training request has been processed, + * otherwise it will return -EINVAL. + */ +static int dp_link_process_link_training_request(struct dp_link_private *link) +{ + if (link->request.test_requested != DP_TEST_LINK_TRAINING) + return -EINVAL; + + DRM_DEBUG_DP("Test:0x%x link rate = 0x%x, lane count = 0x%x\n", + DP_TEST_LINK_TRAINING, + link->request.test_link_rate, + link->request.test_lane_count); + + link->dp_link.link_params.num_lanes = link->request.test_lane_count; + link->dp_link.link_params.rate = link->request.test_link_rate; + + return 0; +} + +bool dp_link_send_test_response(struct dp_link *dp_link) +{ + struct dp_link_private *link = NULL; + int ret = 0; + + if (!dp_link) { + DRM_ERROR("invalid input\n"); + return false; + } + + link = container_of(dp_link, struct dp_link_private, dp_link); + + ret = drm_dp_dpcd_writeb(link->aux, DP_TEST_RESPONSE, + dp_link->test_response); + + return ret == 1; +} + +int dp_link_psm_config(struct dp_link *dp_link, + struct dp_link_info *link_info, bool enable) +{ + struct dp_link_private *link = NULL; + int ret = 0; + + if (!dp_link) { + DRM_ERROR("invalid params\n"); + return -EINVAL; + } + + link = container_of(dp_link, struct dp_link_private, dp_link); + + mutex_lock(&link->psm_mutex); + if (enable) + ret = dp_aux_link_power_down(link->aux, link_info); + else + ret = dp_aux_link_power_up(link->aux, link_info); + + if (ret) + DRM_ERROR("Failed to %s low power mode\n", enable ? + "enter" : "exit"); + else + dp_link->psm_enabled = enable; + + mutex_unlock(&link->psm_mutex); + return ret; +} + +bool dp_link_send_edid_checksum(struct dp_link *dp_link, u8 checksum) +{ + struct dp_link_private *link = NULL; + int ret = 0; + + if (!dp_link) { + DRM_ERROR("invalid input\n"); + return false; + } + + link = container_of(dp_link, struct dp_link_private, dp_link); + + ret = drm_dp_dpcd_writeb(link->aux, DP_TEST_EDID_CHECKSUM, + checksum); + return ret == 1; +} + +static int dp_link_parse_vx_px(struct dp_link_private *link) +{ + int ret = 0; + + DRM_DEBUG_DP("vx: 0=%d, 1=%d, 2=%d, 3=%d\n", + drm_dp_get_adjust_request_voltage(link->link_status, 0), + drm_dp_get_adjust_request_voltage(link->link_status, 1), + drm_dp_get_adjust_request_voltage(link->link_status, 2), + drm_dp_get_adjust_request_voltage(link->link_status, 3)); + + DRM_DEBUG_DP("px: 0=%d, 1=%d, 2=%d, 3=%d\n", + drm_dp_get_adjust_request_pre_emphasis(link->link_status, 0), + drm_dp_get_adjust_request_pre_emphasis(link->link_status, 1), + drm_dp_get_adjust_request_pre_emphasis(link->link_status, 2), + drm_dp_get_adjust_request_pre_emphasis(link->link_status, 3)); + + /** + * Update the voltage and pre-emphasis levels as per DPCD request + * vector. + */ + DRM_DEBUG_DP("Current: v_level = 0x%x, p_level = 0x%x\n", + link->dp_link.phy_params.v_level, + link->dp_link.phy_params.p_level); + link->dp_link.phy_params.v_level = + drm_dp_get_adjust_request_voltage(link->link_status, 0); + link->dp_link.phy_params.p_level = + drm_dp_get_adjust_request_pre_emphasis(link->link_status, 0); + DRM_DEBUG_DP("Requested: v_level = 0x%x, p_level = 0x%x\n", + link->dp_link.phy_params.v_level, + link->dp_link.phy_params.p_level); + + return ret; +} + +/** + * dp_link_process_phy_test_pattern_request() - process new phy link requests + * @link: Display Port Driver data + * + * This function will handle new phy link pattern requests that are initiated + * by the sink. The function will return 0 if a phy link pattern has been + * processed, otherwise it will return -EINVAL. + */ +static int dp_link_process_phy_test_pattern_request( + struct dp_link_private *link) +{ + int ret = 0; + + if (!(link->request.test_requested & DP_TEST_LINK_PHY_TEST_PATTERN)) { + DRM_DEBUG_DP("no phy test\n"); + return -EINVAL; + } + + if (!is_link_rate_valid(link->request.test_link_rate) || + !is_lane_count_valid(link->request.test_lane_count)) { + DRM_ERROR("Invalid: link rate = 0x%x,lane count = 0x%x\n", + link->request.test_link_rate, + link->request.test_lane_count); + return -EINVAL; + } + + DRM_DEBUG_DP("Current: rate = 0x%x, lane count = 0x%x\n", + link->dp_link.link_params.rate, + link->dp_link.link_params.num_lanes); + + DRM_DEBUG_DP("Requested: rate = 0x%x, lane count = 0x%x\n", + link->request.test_link_rate, + link->request.test_lane_count); + + link->dp_link.link_params.num_lanes = link->request.test_lane_count; + link->dp_link.link_params.rate = link->request.test_link_rate; + + ret = dp_link_parse_vx_px(link); + + if (ret) + DRM_ERROR("parse_vx_px failed. ret=%d\n", ret); + + return ret; +} + +static u8 get_link_status(const u8 link_status[DP_LINK_STATUS_SIZE], int r) +{ + return link_status[r - DP_LANE0_1_STATUS]; +} + +/** + * dp_link_process_link_status_update() - processes link status updates + * @link: Display Port link module data + * + * This function will check for changes in the link status, e.g. clock + * recovery done on all lanes, and trigger link training if there is a + * failure/error on the link. + * + * The function will return 0 if the a link status update has been processed, + * otherwise it will return -EINVAL. + */ +static int dp_link_process_link_status_update(struct dp_link_private *link) +{ + if (!(get_link_status(link->link_status, + DP_LANE_ALIGN_STATUS_UPDATED) & + DP_LINK_STATUS_UPDATED) || + (drm_dp_clock_recovery_ok(link->link_status, + link->dp_link.link_params.num_lanes) && + drm_dp_channel_eq_ok(link->link_status, + link->dp_link.link_params.num_lanes))) + return -EINVAL; + + DRM_DEBUG_DP("channel_eq_done = %d, clock_recovery_done = %d\n", + drm_dp_clock_recovery_ok(link->link_status, + link->dp_link.link_params.num_lanes), + drm_dp_clock_recovery_ok(link->link_status, + link->dp_link.link_params.num_lanes)); + + return 0; +} + +/** + * dp_link_process_downstream_port_status_change() - process port status changes + * @link: Display Port Driver data + * + * This function will handle downstream port updates that are initiated by + * the sink. If the downstream port status has changed, the EDID is read via + * AUX. + * + * The function will return 0 if a downstream port update has been + * processed, otherwise it will return -EINVAL. + */ +static int dp_link_process_ds_port_status_change(struct dp_link_private *link) +{ + if (get_link_status(link->link_status, DP_LANE_ALIGN_STATUS_UPDATED) & + DP_DOWNSTREAM_PORT_STATUS_CHANGED) + goto reset; + + if (link->prev_sink_count == link->dp_link.sink_count) + return -EINVAL; + +reset: + /* reset prev_sink_count */ + link->prev_sink_count = link->dp_link.sink_count; + + return 0; +} + +static bool dp_link_is_video_pattern_requested(struct dp_link_private *link) +{ + return (link->request.test_requested & DP_TEST_LINK_VIDEO_PATTERN) + && !(link->request.test_requested & + DP_TEST_LINK_AUDIO_DISABLED_VIDEO); +} + +static bool dp_link_is_audio_pattern_requested(struct dp_link_private *link) +{ + return (link->request.test_requested & DP_TEST_LINK_AUDIO_PATTERN); +} + +static void dp_link_reset_data(struct dp_link_private *link) +{ + link->request = (const struct dp_link_request){ 0 }; + link->dp_link.test_video = (const struct dp_link_test_video){ 0 }; + link->dp_link.test_video.test_bit_depth = DP_TEST_BIT_DEPTH_UNKNOWN; + link->dp_link.test_audio = (const struct dp_link_test_audio){ 0 }; + link->dp_link.phy_params.phy_test_pattern_sel = 0; + link->dp_link.sink_request = 0; + link->dp_link.test_response = 0; +} + +/** + * dp_link_process_request() - handle HPD IRQ transition to HIGH + * @dp_link: pointer to link module data + * + * This function will handle the HPD IRQ state transitions from LOW to HIGH + * (including cases when there are back to back HPD IRQ HIGH) indicating + * the start of a new link training request or sink status update. + */ +int dp_link_process_request(struct dp_link *dp_link) +{ + int ret = 0; + struct dp_link_private *link; + + if (!dp_link) { + DRM_ERROR("invalid input\n"); + return -EINVAL; + } + + link = container_of(dp_link, struct dp_link_private, dp_link); + + dp_link_reset_data(link); + + dp_link_parse_sink_status_field(link); + + if (link->request.test_requested == DP_TEST_LINK_EDID_READ) { + dp_link->sink_request |= DP_TEST_LINK_EDID_READ; + return ret; + } + + ret = dp_link_process_ds_port_status_change(link); + if (!ret) { + dp_link->sink_request |= DS_PORT_STATUS_CHANGED; + return ret; + } + + ret = dp_link_process_link_training_request(link); + if (!ret) { + dp_link->sink_request |= DP_TEST_LINK_TRAINING; + return ret; + } + + ret = dp_link_process_phy_test_pattern_request(link); + if (!ret) { + dp_link->sink_request |= DP_TEST_LINK_PHY_TEST_PATTERN; + return ret; + } + + ret = dp_link_process_link_status_update(link); + if (!ret) { + dp_link->sink_request |= DP_LINK_STATUS_UPDATED; + return ret; + } + + if (dp_link_is_video_pattern_requested(link)) { + ret = 0; + dp_link->sink_request |= DP_TEST_LINK_VIDEO_PATTERN; + } + + if (dp_link_is_audio_pattern_requested(link)) { + dp_link->sink_request |= DP_TEST_LINK_AUDIO_PATTERN; + return -EINVAL; + } + + return ret; +} + +int dp_link_get_colorimetry_config(struct dp_link *dp_link) +{ + u32 cc; + struct dp_link_private *link; + + if (!dp_link) { + DRM_ERROR("invalid input\n"); + return -EINVAL; + } + + link = container_of(dp_link, struct dp_link_private, dp_link); + + /* + * Unless a video pattern CTS test is ongoing, use RGB_VESA + * Only RGB_VESA and RGB_CEA supported for now + */ + if (dp_link_is_video_pattern_requested(link)) + cc = link->dp_link.test_video.test_dyn_range; + else + cc = DP_TEST_DYNAMIC_RANGE_VESA; + + return cc; +} + +int dp_link_adjust_levels(struct dp_link *dp_link, u8 *link_status) +{ + int i; + int v_max = 0, p_max = 0; + + if (!dp_link) { + DRM_ERROR("invalid input\n"); + return -EINVAL; + } + + /* use the max level across lanes */ + for (i = 0; i < dp_link->link_params.num_lanes; i++) { + u8 data_v = drm_dp_get_adjust_request_voltage(link_status, i); + u8 data_p = drm_dp_get_adjust_request_pre_emphasis(link_status, + i); + DRM_DEBUG_DP("lane=%d req_vol_swing=%d req_pre_emphasis=%d\n", + i, data_v, data_p); + if (v_max < data_v) + v_max = data_v; + if (p_max < data_p) + p_max = data_p; + } + + dp_link->phy_params.v_level = v_max >> DP_TRAIN_VOLTAGE_SWING_SHIFT; + dp_link->phy_params.p_level = p_max >> DP_TRAIN_PRE_EMPHASIS_SHIFT; + + /** + * Adjust the voltage swing and pre-emphasis level combination to within + * the allowable range. + */ + if (dp_link->phy_params.v_level > DP_TRAIN_VOLTAGE_SWING_MAX) { + DRM_DEBUG_DP("Requested vSwingLevel=%d, change to %d\n", + dp_link->phy_params.v_level, + DP_TRAIN_VOLTAGE_SWING_MAX); + dp_link->phy_params.v_level = DP_TRAIN_VOLTAGE_SWING_MAX; + } + + if (dp_link->phy_params.p_level > DP_TRAIN_PRE_EMPHASIS_MAX) { + DRM_DEBUG_DP("Requested preEmphasisLevel=%d, change to %d\n", + dp_link->phy_params.p_level, + DP_TRAIN_PRE_EMPHASIS_MAX); + dp_link->phy_params.p_level = DP_TRAIN_PRE_EMPHASIS_MAX; + } + + if ((dp_link->phy_params.p_level > DP_TRAIN_PRE_EMPHASIS_LVL_1) + && (dp_link->phy_params.v_level == + DP_TRAIN_VOLTAGE_SWING_LVL_2)) { + DRM_DEBUG_DP("Requested preEmphasisLevel=%d, change to %d\n", + dp_link->phy_params.p_level, + DP_TRAIN_PRE_EMPHASIS_LVL_1); + dp_link->phy_params.p_level = DP_TRAIN_PRE_EMPHASIS_LVL_1; + } + + DRM_DEBUG_DP("adjusted: v_level=%d, p_level=%d\n", + dp_link->phy_params.v_level, dp_link->phy_params.p_level); + + return 0; +} + +u32 dp_link_get_test_bits_depth(struct dp_link *dp_link, u32 bpp) +{ + u32 tbd; + + /* + * Few simplistic rules and assumptions made here: + * 1. Test bit depth is bit depth per color component + * 2. Assume 3 color components + */ + switch (bpp) { + case 18: + tbd = DP_TEST_BIT_DEPTH_6; + break; + case 24: + tbd = DP_TEST_BIT_DEPTH_8; + break; + case 30: + tbd = DP_TEST_BIT_DEPTH_10; + break; + default: + tbd = DP_TEST_BIT_DEPTH_UNKNOWN; + break; + } + + if (tbd != DP_TEST_BIT_DEPTH_UNKNOWN) + tbd = (tbd >> DP_TEST_BIT_DEPTH_SHIFT); + + return tbd; +} + +struct dp_link *dp_link_get(struct device *dev, struct drm_dp_aux *aux) +{ + struct dp_link_private *link; + struct dp_link *dp_link; + + if (!dev || !aux) { + DRM_ERROR("invalid input\n"); + return ERR_PTR(-EINVAL); + } + + link = devm_kzalloc(dev, sizeof(*link), GFP_KERNEL); + if (!link) + return ERR_PTR(-ENOMEM); + + link->dev = dev; + link->aux = aux; + + mutex_init(&link->psm_mutex); + dp_link = &link->dp_link; + + return dp_link; +} diff --git a/drivers/gpu/drm/msm/dp/dp_link.h b/drivers/gpu/drm/msm/dp/dp_link.h new file mode 100644 index 000000000000..49811b6221e5 --- /dev/null +++ b/drivers/gpu/drm/msm/dp/dp_link.h @@ -0,0 +1,155 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (c) 2012-2020, The Linux Foundation. All rights reserved. + */ + +#ifndef _DP_LINK_H_ +#define _DP_LINK_H_ + +#include "dp_aux.h" + +#define DS_PORT_STATUS_CHANGED 0x200 +#define DP_TEST_BIT_DEPTH_UNKNOWN 0xFFFFFFFF +#define DP_LINK_CAP_ENHANCED_FRAMING (1 << 0) + +struct dp_link_info { + unsigned char revision; + unsigned int rate; + unsigned int num_lanes; + unsigned long capabilities; +}; + +enum dp_link_voltage_level { + DP_TRAIN_VOLTAGE_SWING_LVL_0 = 0, + DP_TRAIN_VOLTAGE_SWING_LVL_1 = 1, + DP_TRAIN_VOLTAGE_SWING_LVL_2 = 2, + DP_TRAIN_VOLTAGE_SWING_MAX = DP_TRAIN_VOLTAGE_SWING_LVL_2, +}; + +enum dp_link_preemaphasis_level { + DP_TRAIN_PRE_EMPHASIS_LVL_0 = 0, + DP_TRAIN_PRE_EMPHASIS_LVL_1 = 1, + DP_TRAIN_PRE_EMPHASIS_LVL_2 = 2, + DP_TRAIN_PRE_EMPHASIS_MAX = DP_TRAIN_PRE_EMPHASIS_LVL_2, +}; + +struct dp_link_test_video { + u32 test_video_pattern; + u32 test_bit_depth; + u32 test_dyn_range; + u32 test_h_total; + u32 test_v_total; + u32 test_h_start; + u32 test_v_start; + u32 test_hsync_pol; + u32 test_hsync_width; + u32 test_vsync_pol; + u32 test_vsync_width; + u32 test_h_width; + u32 test_v_height; + u32 test_rr_d; + u32 test_rr_n; +}; + +struct dp_link_test_audio { + u32 test_audio_sampling_rate; + u32 test_audio_channel_count; + u32 test_audio_pattern_type; + u32 test_audio_period_ch_1; + u32 test_audio_period_ch_2; + u32 test_audio_period_ch_3; + u32 test_audio_period_ch_4; + u32 test_audio_period_ch_5; + u32 test_audio_period_ch_6; + u32 test_audio_period_ch_7; + u32 test_audio_period_ch_8; +}; + +struct dp_link_phy_params { + u32 phy_test_pattern_sel; + u8 v_level; + u8 p_level; +}; + +struct dp_link { + u32 sink_request; + u32 test_response; + bool psm_enabled; + + u8 sink_count; + struct dp_link_test_video test_video; + struct dp_link_test_audio test_audio; + struct dp_link_phy_params phy_params; + struct dp_link_info link_params; +}; + +/** + * mdss_dp_test_bit_depth_to_bpp() - convert test bit depth to bpp + * @tbd: test bit depth + * + * Returns the bits per pixel (bpp) to be used corresponding to the + * git bit depth value. This function assumes that bit depth has + * already been validated. + */ +static inline u32 dp_link_bit_depth_to_bpp(u32 tbd) +{ + /* + * Few simplistic rules and assumptions made here: + * 1. Bit depth is per color component + * 2. If bit depth is unknown return 0 + * 3. Assume 3 color components + */ + switch (tbd) { + case DP_TEST_BIT_DEPTH_6: + return 18; + case DP_TEST_BIT_DEPTH_8: + return 24; + case DP_TEST_BIT_DEPTH_10: + return 30; + case DP_TEST_BIT_DEPTH_UNKNOWN: + default: + return 0; + } +} + +/** + * dp_test_bit_depth_to_bpc() - convert test bit depth to bpc + * @tbd: test bit depth + * + * Returns the bits per comp (bpc) to be used corresponding to the + * bit depth value. This function assumes that bit depth has + * already been validated. + */ +static inline u32 dp_link_bit_depth_to_bpc(u32 tbd) +{ + switch (tbd) { + case DP_TEST_BIT_DEPTH_6: + return 6; + case DP_TEST_BIT_DEPTH_8: + return 8; + case DP_TEST_BIT_DEPTH_10: + return 10; + case DP_TEST_BIT_DEPTH_UNKNOWN: + default: + return 0; + } +} + +u32 dp_link_get_test_bits_depth(struct dp_link *dp_link, u32 bpp); +int dp_link_process_request(struct dp_link *dp_link); +int dp_link_get_colorimetry_config(struct dp_link *dp_link); +int dp_link_adjust_levels(struct dp_link *dp_link, u8 *link_status); +bool dp_link_send_test_response(struct dp_link *dp_link); +int dp_link_psm_config(struct dp_link *dp_link, + struct dp_link_info *link_info, bool enable); +bool dp_link_send_edid_checksum(struct dp_link *dp_link, u8 checksum); + +/** + * dp_link_get() - get the functionalities of dp test module + * + * + * return: a pointer to dp_link struct + */ +struct dp_link *dp_link_get(struct device *dev, struct drm_dp_aux *aux); + +#endif /* _DP_LINK_H_ */ diff --git a/drivers/gpu/drm/msm/dp/dp_panel.c b/drivers/gpu/drm/msm/dp/dp_panel.c new file mode 100644 index 000000000000..18cec4fc5e0b --- /dev/null +++ b/drivers/gpu/drm/msm/dp/dp_panel.c @@ -0,0 +1,463 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (c) 2012-2020, The Linux Foundation. All rights reserved. + */ + +#include "dp_panel.h" + +#include <drm/drm_connector.h> +#include <drm/drm_edid.h> +#include <drm/drm_print.h> + +struct dp_panel_private { + struct device *dev; + struct dp_panel dp_panel; + struct drm_dp_aux *aux; + struct dp_link *link; + struct dp_catalog *catalog; + bool panel_on; + bool aux_cfg_update_done; +}; + +static int dp_panel_read_dpcd(struct dp_panel *dp_panel) +{ + int rc = 0; + size_t len; + ssize_t rlen; + struct dp_panel_private *panel; + struct dp_link_info *link_info; + u8 *dpcd, major = 0, minor = 0, temp; + u32 offset = DP_DPCD_REV; + + dpcd = dp_panel->dpcd; + + panel = container_of(dp_panel, struct dp_panel_private, dp_panel); + link_info = &dp_panel->link_info; + + rlen = drm_dp_dpcd_read(panel->aux, offset, + dpcd, (DP_RECEIVER_CAP_SIZE + 1)); + if (rlen < (DP_RECEIVER_CAP_SIZE + 1)) { + DRM_ERROR("dpcd read failed, rlen=%zd\n", rlen); + if (rlen == -ETIMEDOUT) + rc = rlen; + else + rc = -EINVAL; + + goto end; + } + + temp = dpcd[DP_TRAINING_AUX_RD_INTERVAL]; + + /* check for EXTENDED_RECEIVER_CAPABILITY_FIELD_PRESENT */ + if (temp & BIT(7)) { + DRM_DEBUG_DP("using EXTENDED_RECEIVER_CAPABILITY_FIELD\n"); + offset = DPRX_EXTENDED_DPCD_FIELD; + } + + rlen = drm_dp_dpcd_read(panel->aux, offset, + dpcd, (DP_RECEIVER_CAP_SIZE + 1)); + if (rlen < (DP_RECEIVER_CAP_SIZE + 1)) { + DRM_ERROR("dpcd read failed, rlen=%zd\n", rlen); + if (rlen == -ETIMEDOUT) + rc = rlen; + else + rc = -EINVAL; + + goto end; + } + + link_info->revision = dpcd[DP_DPCD_REV]; + major = (link_info->revision >> 4) & 0x0f; + minor = link_info->revision & 0x0f; + + link_info->rate = drm_dp_bw_code_to_link_rate(dpcd[DP_MAX_LINK_RATE]); + link_info->num_lanes = dpcd[DP_MAX_LANE_COUNT] & DP_MAX_LANE_COUNT_MASK; + + if (link_info->num_lanes > dp_panel->max_dp_lanes) + link_info->num_lanes = dp_panel->max_dp_lanes; + + /* Limit support upto HBR2 until HBR3 support is added */ + if (link_info->rate >= (drm_dp_bw_code_to_link_rate(DP_LINK_BW_5_4))) + link_info->rate = drm_dp_bw_code_to_link_rate(DP_LINK_BW_5_4); + + DRM_DEBUG_DP("version: %d.%d\n", major, minor); + DRM_DEBUG_DP("link_rate=%d\n", link_info->rate); + DRM_DEBUG_DP("lane_count=%d\n", link_info->num_lanes); + + if (drm_dp_enhanced_frame_cap(dpcd)) + link_info->capabilities |= DP_LINK_CAP_ENHANCED_FRAMING; + + dp_panel->dfp_present = dpcd[DP_DOWNSTREAMPORT_PRESENT]; + dp_panel->dfp_present &= DP_DWN_STRM_PORT_PRESENT; + + if (dp_panel->dfp_present && (dpcd[DP_DPCD_REV] > 0x10)) { + dp_panel->ds_port_cnt = dpcd[DP_DOWN_STREAM_PORT_COUNT]; + dp_panel->ds_port_cnt &= DP_PORT_COUNT_MASK; + len = DP_DOWNSTREAM_PORTS * DP_DOWNSTREAM_CAP_SIZE; + + rlen = drm_dp_dpcd_read(panel->aux, + DP_DOWNSTREAM_PORT_0, dp_panel->ds_cap_info, len); + if (rlen < len) { + DRM_ERROR("ds port status failed, rlen=%zd\n", rlen); + rc = -EINVAL; + goto end; + } + } + +end: + return rc; +} + +static u32 dp_panel_get_supported_bpp(struct dp_panel *dp_panel, + u32 mode_edid_bpp, u32 mode_pclk_khz) +{ + struct dp_link_info *link_info; + const u32 max_supported_bpp = 30, min_supported_bpp = 18; + u32 bpp = 0, data_rate_khz = 0; + + bpp = min_t(u32, mode_edid_bpp, max_supported_bpp); + + link_info = &dp_panel->link_info; + data_rate_khz = link_info->num_lanes * link_info->rate * 8; + + while (bpp > min_supported_bpp) { + if (mode_pclk_khz * bpp <= data_rate_khz) + break; + bpp -= 6; + } + + return bpp; +} + +static int dp_panel_update_modes(struct drm_connector *connector, + struct edid *edid) +{ + int rc = 0; + + if (edid) { + rc = drm_connector_update_edid_property(connector, edid); + if (rc) { + DRM_ERROR("failed to update edid property %d\n", rc); + return rc; + } + rc = drm_add_edid_modes(connector, edid); + DRM_DEBUG_DP("%s -", __func__); + return rc; + } + + rc = drm_connector_update_edid_property(connector, NULL); + if (rc) + DRM_ERROR("failed to update edid property %d\n", rc); + + return rc; +} + +int dp_panel_read_sink_caps(struct dp_panel *dp_panel, + struct drm_connector *connector) +{ + int rc = 0, bw_code; + int rlen, count; + struct dp_panel_private *panel; + + if (!dp_panel || !connector) { + DRM_ERROR("invalid input\n"); + return -EINVAL; + } + + panel = container_of(dp_panel, struct dp_panel_private, dp_panel); + + rc = dp_panel_read_dpcd(dp_panel); + bw_code = drm_dp_link_rate_to_bw_code(dp_panel->link_info.rate); + if (rc || !is_link_rate_valid(bw_code) || + !is_lane_count_valid(dp_panel->link_info.num_lanes) || + (bw_code > dp_panel->max_bw_code)) { + DRM_ERROR("read dpcd failed %d\n", rc); + return rc; + } + + if (dp_panel->dfp_present) { + rlen = drm_dp_dpcd_read(panel->aux, DP_SINK_COUNT, + &count, 1); + if (rlen == 1) { + count = DP_GET_SINK_COUNT(count); + if (!count) { + DRM_ERROR("no downstream ports connected\n"); + panel->link->sink_count = 0; + rc = -ENOTCONN; + goto end; + } + } + } + + kfree(dp_panel->edid); + dp_panel->edid = NULL; + + dp_panel->edid = drm_get_edid(connector, + &panel->aux->ddc); + if (!dp_panel->edid) { + DRM_ERROR("panel edid read failed\n"); + + /* fail safe edid */ + mutex_lock(&connector->dev->mode_config.mutex); + if (drm_add_modes_noedid(connector, 640, 480)) + drm_set_preferred_mode(connector, 640, 480); + mutex_unlock(&connector->dev->mode_config.mutex); + } + + if (panel->aux_cfg_update_done) { + DRM_DEBUG_DP("read DPCD with updated AUX config\n"); + rc = dp_panel_read_dpcd(dp_panel); + bw_code = drm_dp_link_rate_to_bw_code(dp_panel->link_info.rate); + if (rc || !is_link_rate_valid(bw_code) || + !is_lane_count_valid(dp_panel->link_info.num_lanes) + || (bw_code > dp_panel->max_bw_code)) { + DRM_ERROR("read dpcd failed %d\n", rc); + return rc; + } + panel->aux_cfg_update_done = false; + } +end: + return rc; +} + +u32 dp_panel_get_mode_bpp(struct dp_panel *dp_panel, + u32 mode_edid_bpp, u32 mode_pclk_khz) +{ + struct dp_panel_private *panel; + u32 bpp = mode_edid_bpp; + + if (!dp_panel || !mode_edid_bpp || !mode_pclk_khz) { + DRM_ERROR("invalid input\n"); + return 0; + } + + panel = container_of(dp_panel, struct dp_panel_private, dp_panel); + + if (dp_panel->video_test) + bpp = dp_link_bit_depth_to_bpp( + panel->link->test_video.test_bit_depth); + else + bpp = dp_panel_get_supported_bpp(dp_panel, mode_edid_bpp, + mode_pclk_khz); + + return bpp; +} + +int dp_panel_get_modes(struct dp_panel *dp_panel, + struct drm_connector *connector, struct dp_display_mode *mode) +{ + if (!dp_panel) { + DRM_ERROR("invalid input\n"); + return -EINVAL; + } + + if (dp_panel->edid) + return dp_panel_update_modes(connector, dp_panel->edid); + + return 0; +} + +static u8 dp_panel_get_edid_checksum(struct edid *edid) +{ + struct edid *last_block; + u8 *raw_edid; + bool is_edid_corrupt; + + if (!edid) { + DRM_ERROR("invalid edid input\n"); + return 0; + } + + raw_edid = (u8 *)edid; + raw_edid += (edid->extensions * EDID_LENGTH); + last_block = (struct edid *)raw_edid; + + /* block type extension */ + drm_edid_block_valid(raw_edid, 1, false, &is_edid_corrupt); + if (!is_edid_corrupt) + return last_block->checksum; + + DRM_ERROR("Invalid block, no checksum\n"); + return 0; +} + +void dp_panel_handle_sink_request(struct dp_panel *dp_panel) +{ + struct dp_panel_private *panel; + + if (!dp_panel) { + DRM_ERROR("invalid input\n"); + return; + } + + panel = container_of(dp_panel, struct dp_panel_private, dp_panel); + + if (panel->link->sink_request & DP_TEST_LINK_EDID_READ) { + u8 checksum = dp_panel_get_edid_checksum(dp_panel->edid); + + dp_link_send_edid_checksum(panel->link, checksum); + dp_link_send_test_response(panel->link); + } +} + +void dp_panel_tpg_config(struct dp_panel *dp_panel, bool enable) +{ + struct dp_catalog *catalog; + struct dp_panel_private *panel; + + if (!dp_panel) { + DRM_ERROR("invalid input\n"); + return; + } + + panel = container_of(dp_panel, struct dp_panel_private, dp_panel); + catalog = panel->catalog; + + if (!panel->panel_on) { + DRM_DEBUG_DP("DP panel not enabled, handle TPG on next on\n"); + return; + } + + if (!enable) { + dp_catalog_panel_tpg_disable(catalog); + return; + } + + DRM_DEBUG_DP("%s: calling catalog tpg_enable\n", __func__); + dp_catalog_panel_tpg_enable(catalog, &panel->dp_panel.dp_mode.drm_mode); +} + +void dp_panel_dump_regs(struct dp_panel *dp_panel) +{ + struct dp_catalog *catalog; + struct dp_panel_private *panel; + + panel = container_of(dp_panel, struct dp_panel_private, dp_panel); + catalog = panel->catalog; + + dp_catalog_dump_regs(catalog); +} + +int dp_panel_timing_cfg(struct dp_panel *dp_panel) +{ + int rc = 0; + u32 data, total_ver, total_hor; + struct dp_catalog *catalog; + struct dp_panel_private *panel; + struct drm_display_mode *drm_mode; + + panel = container_of(dp_panel, struct dp_panel_private, dp_panel); + catalog = panel->catalog; + drm_mode = &panel->dp_panel.dp_mode.drm_mode; + + DRM_DEBUG_DP("width=%d hporch= %d %d %d\n", + drm_mode->hdisplay, drm_mode->htotal - drm_mode->hsync_end, + drm_mode->hsync_start - drm_mode->hdisplay, + drm_mode->hsync_end - drm_mode->hsync_start); + + DRM_DEBUG_DP("height=%d vporch= %d %d %d\n", + drm_mode->vdisplay, drm_mode->vtotal - drm_mode->vsync_end, + drm_mode->vsync_start - drm_mode->vdisplay, + drm_mode->vsync_end - drm_mode->vsync_start); + + total_hor = drm_mode->htotal; + + total_ver = drm_mode->vtotal; + + data = total_ver; + data <<= 16; + data |= total_hor; + + catalog->total = data; + + data = (drm_mode->vtotal - drm_mode->vsync_start); + data <<= 16; + data |= (drm_mode->htotal - drm_mode->hsync_start); + + catalog->sync_start = data; + + data = drm_mode->vsync_end - drm_mode->vsync_start; + data <<= 16; + data |= (panel->dp_panel.dp_mode.v_active_low << 31); + data |= drm_mode->hsync_end - drm_mode->hsync_start; + data |= (panel->dp_panel.dp_mode.h_active_low << 15); + + catalog->width_blanking = data; + + data = drm_mode->vdisplay; + data <<= 16; + data |= drm_mode->hdisplay; + + catalog->dp_active = data; + + dp_catalog_panel_timing_cfg(catalog); + panel->panel_on = true; + + return rc; +} + +int dp_panel_init_panel_info(struct dp_panel *dp_panel) +{ + int rc = 0; + struct drm_display_mode *drm_mode; + + drm_mode = &dp_panel->dp_mode.drm_mode; + + /* + * print resolution info as this is a result + * of user initiated action of cable connection + */ + DRM_DEBUG_DP("SET NEW RESOLUTION:\n"); + DRM_DEBUG_DP("%dx%d@%dfps\n", drm_mode->hdisplay, + drm_mode->vdisplay, drm_mode_vrefresh(drm_mode)); + DRM_DEBUG_DP("h_porches(back|front|width) = (%d|%d|%d)\n", + drm_mode->htotal - drm_mode->hsync_end, + drm_mode->hsync_start - drm_mode->hdisplay, + drm_mode->hsync_end - drm_mode->hsync_start); + DRM_DEBUG_DP("v_porches(back|front|width) = (%d|%d|%d)\n", + drm_mode->vtotal - drm_mode->vsync_end, + drm_mode->vsync_start - drm_mode->vdisplay, + drm_mode->vsync_end - drm_mode->vsync_start); + DRM_DEBUG_DP("pixel clock (KHz)=(%d)\n", drm_mode->clock); + DRM_DEBUG_DP("bpp = %d\n", dp_panel->dp_mode.bpp); + + dp_panel->dp_mode.bpp = max_t(u32, 18, + min_t(u32, dp_panel->dp_mode.bpp, 30)); + DRM_DEBUG_DP("updated bpp = %d\n", dp_panel->dp_mode.bpp); + + return rc; +} + +struct dp_panel *dp_panel_get(struct dp_panel_in *in) +{ + struct dp_panel_private *panel; + struct dp_panel *dp_panel; + + if (!in->dev || !in->catalog || !in->aux || !in->link) { + DRM_ERROR("invalid input\n"); + return ERR_PTR(-EINVAL); + } + + panel = devm_kzalloc(in->dev, sizeof(*panel), GFP_KERNEL); + if (!panel) + return ERR_PTR(-ENOMEM); + + panel->dev = in->dev; + panel->aux = in->aux; + panel->catalog = in->catalog; + panel->link = in->link; + + dp_panel = &panel->dp_panel; + dp_panel->max_bw_code = DP_LINK_BW_8_1; + panel->aux_cfg_update_done = false; + + return dp_panel; +} + +void dp_panel_put(struct dp_panel *dp_panel) +{ + if (!dp_panel) + return; + + kfree(dp_panel->edid); +} diff --git a/drivers/gpu/drm/msm/dp/dp_panel.h b/drivers/gpu/drm/msm/dp/dp_panel.h new file mode 100644 index 000000000000..9023e5bb4b8b --- /dev/null +++ b/drivers/gpu/drm/msm/dp/dp_panel.h @@ -0,0 +1,100 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (c) 2012-2020, The Linux Foundation. All rights reserved. + */ + +#ifndef _DP_PANEL_H_ +#define _DP_PANEL_H_ + +#include <drm/msm_drm.h> + +#include "dp_aux.h" +#include "dp_link.h" +#include "dp_hpd.h" + +struct edid; + +#define DPRX_EXTENDED_DPCD_FIELD 0x2200 + +#define DP_DOWNSTREAM_PORTS 4 +#define DP_DOWNSTREAM_CAP_SIZE 4 + +struct dp_display_mode { + struct drm_display_mode drm_mode; + u32 capabilities; + u32 bpp; + u32 h_active_low; + u32 v_active_low; +}; + +struct dp_panel_in { + struct device *dev; + struct drm_dp_aux *aux; + struct dp_link *link; + struct dp_catalog *catalog; +}; + +struct dp_panel { + /* dpcd raw data */ + u8 dpcd[DP_RECEIVER_CAP_SIZE + 1]; + u8 ds_cap_info[DP_DOWNSTREAM_PORTS * DP_DOWNSTREAM_CAP_SIZE]; + u32 ds_port_cnt; + u32 dfp_present; + + struct dp_link_info link_info; + struct drm_dp_desc desc; + struct edid *edid; + struct drm_connector *connector; + struct dp_display_mode dp_mode; + bool video_test; + + u32 vic; + u32 max_pclk_khz; + u32 max_dp_lanes; + + u32 max_bw_code; +}; + +int dp_panel_init_panel_info(struct dp_panel *dp_panel); +int dp_panel_deinit(struct dp_panel *dp_panel); +int dp_panel_timing_cfg(struct dp_panel *dp_panel); +void dp_panel_dump_regs(struct dp_panel *dp_panel); +int dp_panel_read_sink_caps(struct dp_panel *dp_panel, + struct drm_connector *connector); +u32 dp_panel_get_mode_bpp(struct dp_panel *dp_panel, u32 mode_max_bpp, + u32 mode_pclk_khz); +int dp_panel_get_modes(struct dp_panel *dp_panel, + struct drm_connector *connector, struct dp_display_mode *mode); +void dp_panel_handle_sink_request(struct dp_panel *dp_panel); +void dp_panel_tpg_config(struct dp_panel *dp_panel, bool enable); + +/** + * is_link_rate_valid() - validates the link rate + * @lane_rate: link rate requested by the sink + * + * Returns true if the requested link rate is supported. + */ +static inline bool is_link_rate_valid(u32 bw_code) +{ + return (bw_code == DP_LINK_BW_1_62 || + bw_code == DP_LINK_BW_2_7 || + bw_code == DP_LINK_BW_5_4 || + bw_code == DP_LINK_BW_8_1); +} + +/** + * dp_link_is_lane_count_valid() - validates the lane count + * @lane_count: lane count requested by the sink + * + * Returns true if the requested lane count is supported. + */ +static inline bool is_lane_count_valid(u32 lane_count) +{ + return (lane_count == 1 || + lane_count == 2 || + lane_count == 4); +} + +struct dp_panel *dp_panel_get(struct dp_panel_in *in); +void dp_panel_put(struct dp_panel *dp_panel); +#endif /* _DP_PANEL_H_ */ diff --git a/drivers/gpu/drm/msm/dp/dp_parser.c b/drivers/gpu/drm/msm/dp/dp_parser.c new file mode 100644 index 000000000000..0519dd3ac3c3 --- /dev/null +++ b/drivers/gpu/drm/msm/dp/dp_parser.c @@ -0,0 +1,293 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (c) 2012-2020, The Linux Foundation. All rights reserved. + */ + +#include <linux/of_gpio.h> +#include <linux/phy/phy.h> + +#include <drm/drm_print.h> + +#include "dp_parser.h" +#include "dp_reg.h" + +static const struct dp_regulator_cfg sdm845_dp_reg_cfg = { + .num = 2, + .regs = { + {"vdda-1p2", 21800, 4 }, /* 1.2 V */ + {"vdda-0p9", 36000, 32 }, /* 0.9 V */ + }, +}; + +static int msm_dss_ioremap(struct platform_device *pdev, + struct dss_io_data *io_data) +{ + struct resource *res = NULL; + + res = platform_get_resource(pdev, IORESOURCE_MEM, 0); + if (!res) { + DRM_ERROR("%pS->%s: msm_dss_get_res failed\n", + __builtin_return_address(0), __func__); + return -ENODEV; + } + + io_data->len = (u32)resource_size(res); + io_data->base = ioremap(res->start, io_data->len); + if (!io_data->base) { + DRM_ERROR("%pS->%s: ioremap failed\n", + __builtin_return_address(0), __func__); + return -EIO; + } + + return 0; +} + +static void msm_dss_iounmap(struct dss_io_data *io_data) +{ + if (io_data->base) { + iounmap(io_data->base); + io_data->base = NULL; + } + io_data->len = 0; +} + +static void dp_parser_unmap_io_resources(struct dp_parser *parser) +{ + struct dp_io *io = &parser->io; + + msm_dss_iounmap(&io->dp_controller); +} + +static int dp_parser_ctrl_res(struct dp_parser *parser) +{ + int rc = 0; + struct platform_device *pdev = parser->pdev; + struct dp_io *io = &parser->io; + + rc = msm_dss_ioremap(pdev, &io->dp_controller); + if (rc) { + DRM_ERROR("unable to remap dp io resources, rc=%d\n", rc); + goto err; + } + + io->phy = devm_phy_get(&pdev->dev, "dp"); + if (IS_ERR(io->phy)) { + rc = PTR_ERR(io->phy); + goto err; + } + + return 0; +err: + dp_parser_unmap_io_resources(parser); + return rc; +} + +static int dp_parser_misc(struct dp_parser *parser) +{ + struct device_node *of_node = parser->pdev->dev.of_node; + int len = 0; + const char *data_lane_property = "data-lanes"; + + len = of_property_count_elems_of_size(of_node, + data_lane_property, sizeof(u32)); + if (len < 0) { + DRM_WARN("Invalid property %s, default max DP lanes = %d\n", + data_lane_property, DP_MAX_NUM_DP_LANES); + len = DP_MAX_NUM_DP_LANES; + } + + parser->max_dp_lanes = len; + return 0; +} + +static inline bool dp_parser_check_prefix(const char *clk_prefix, + const char *clk_name) +{ + return !strncmp(clk_prefix, clk_name, strlen(clk_prefix)); +} + +static int dp_parser_init_clk_data(struct dp_parser *parser) +{ + int num_clk, i, rc; + int core_clk_count = 0, ctrl_clk_count = 0, stream_clk_count = 0; + const char *clk_name; + struct device *dev = &parser->pdev->dev; + struct dss_module_power *core_power = &parser->mp[DP_CORE_PM]; + struct dss_module_power *ctrl_power = &parser->mp[DP_CTRL_PM]; + struct dss_module_power *stream_power = &parser->mp[DP_STREAM_PM]; + + num_clk = of_property_count_strings(dev->of_node, "clock-names"); + if (num_clk <= 0) { + DRM_ERROR("no clocks are defined\n"); + return -EINVAL; + } + + for (i = 0; i < num_clk; i++) { + rc = of_property_read_string_index(dev->of_node, + "clock-names", i, &clk_name); + if (rc < 0) + return rc; + + if (dp_parser_check_prefix("core", clk_name)) + core_clk_count++; + + if (dp_parser_check_prefix("ctrl", clk_name)) + ctrl_clk_count++; + + if (dp_parser_check_prefix("stream", clk_name)) + stream_clk_count++; + } + + /* Initialize the CORE power module */ + if (core_clk_count == 0) { + DRM_ERROR("no core clocks are defined\n"); + return -EINVAL; + } + + core_power->num_clk = core_clk_count; + core_power->clk_config = devm_kzalloc(dev, + sizeof(struct dss_clk) * core_power->num_clk, + GFP_KERNEL); + if (!core_power->clk_config) + return -EINVAL; + + /* Initialize the CTRL power module */ + if (ctrl_clk_count == 0) { + DRM_ERROR("no ctrl clocks are defined\n"); + return -EINVAL; + } + + ctrl_power->num_clk = ctrl_clk_count; + ctrl_power->clk_config = devm_kzalloc(dev, + sizeof(struct dss_clk) * ctrl_power->num_clk, + GFP_KERNEL); + if (!ctrl_power->clk_config) { + ctrl_power->num_clk = 0; + return -EINVAL; + } + + /* Initialize the STREAM power module */ + if (stream_clk_count == 0) { + DRM_ERROR("no stream (pixel) clocks are defined\n"); + return -EINVAL; + } + + stream_power->num_clk = stream_clk_count; + stream_power->clk_config = devm_kzalloc(dev, + sizeof(struct dss_clk) * stream_power->num_clk, + GFP_KERNEL); + if (!stream_power->clk_config) { + stream_power->num_clk = 0; + return -EINVAL; + } + + return 0; +} + +static int dp_parser_clock(struct dp_parser *parser) +{ + int rc = 0, i = 0; + int num_clk = 0; + int core_clk_index = 0, ctrl_clk_index = 0, stream_clk_index = 0; + int core_clk_count = 0, ctrl_clk_count = 0, stream_clk_count = 0; + const char *clk_name; + struct device *dev = &parser->pdev->dev; + struct dss_module_power *core_power = &parser->mp[DP_CORE_PM]; + struct dss_module_power *ctrl_power = &parser->mp[DP_CTRL_PM]; + struct dss_module_power *stream_power = &parser->mp[DP_STREAM_PM]; + + rc = dp_parser_init_clk_data(parser); + if (rc) { + DRM_ERROR("failed to initialize power data %d\n", rc); + return -EINVAL; + } + + core_clk_count = core_power->num_clk; + ctrl_clk_count = ctrl_power->num_clk; + stream_clk_count = stream_power->num_clk; + + num_clk = core_clk_count + ctrl_clk_count + stream_clk_count; + + for (i = 0; i < num_clk; i++) { + rc = of_property_read_string_index(dev->of_node, "clock-names", + i, &clk_name); + if (rc) { + DRM_ERROR("error reading clock-names %d\n", rc); + return rc; + } + if (dp_parser_check_prefix("core", clk_name) && + core_clk_index < core_clk_count) { + struct dss_clk *clk = + &core_power->clk_config[core_clk_index]; + strlcpy(clk->clk_name, clk_name, sizeof(clk->clk_name)); + clk->type = DSS_CLK_AHB; + core_clk_index++; + } else if (dp_parser_check_prefix("stream", clk_name) && + stream_clk_index < stream_clk_count) { + struct dss_clk *clk = + &stream_power->clk_config[stream_clk_index]; + strlcpy(clk->clk_name, clk_name, sizeof(clk->clk_name)); + clk->type = DSS_CLK_PCLK; + stream_clk_index++; + } else if (dp_parser_check_prefix("ctrl", clk_name) && + ctrl_clk_index < ctrl_clk_count) { + struct dss_clk *clk = + &ctrl_power->clk_config[ctrl_clk_index]; + strlcpy(clk->clk_name, clk_name, sizeof(clk->clk_name)); + ctrl_clk_index++; + if (dp_parser_check_prefix("ctrl_link", clk_name) || + dp_parser_check_prefix("stream_pixel", clk_name)) + clk->type = DSS_CLK_PCLK; + else + clk->type = DSS_CLK_AHB; + } + } + + DRM_DEBUG_DP("clock parsing successful\n"); + + return 0; +} + +static int dp_parser_parse(struct dp_parser *parser) +{ + int rc = 0; + + if (!parser) { + DRM_ERROR("invalid input\n"); + return -EINVAL; + } + + rc = dp_parser_ctrl_res(parser); + if (rc) + return rc; + + rc = dp_parser_misc(parser); + if (rc) + return rc; + + rc = dp_parser_clock(parser); + if (rc) + return rc; + + /* Map the corresponding regulator information according to + * version. Currently, since we only have one supported platform, + * mapping the regulator directly. + */ + parser->regulator_cfg = &sdm845_dp_reg_cfg; + + return 0; +} + +struct dp_parser *dp_parser_get(struct platform_device *pdev) +{ + struct dp_parser *parser; + + parser = devm_kzalloc(&pdev->dev, sizeof(*parser), GFP_KERNEL); + if (!parser) + return ERR_PTR(-ENOMEM); + + parser->parse = dp_parser_parse; + parser->pdev = pdev; + + return parser; +} diff --git a/drivers/gpu/drm/msm/dp/dp_parser.h b/drivers/gpu/drm/msm/dp/dp_parser.h new file mode 100644 index 000000000000..34b49628bbaf --- /dev/null +++ b/drivers/gpu/drm/msm/dp/dp_parser.h @@ -0,0 +1,136 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (c) 2012-2020, The Linux Foundation. All rights reserved. + */ + +#ifndef _DP_PARSER_H_ +#define _DP_PARSER_H_ + +#include <linux/platform_device.h> +#include <linux/phy/phy.h> +#include <linux/phy/phy-dp.h> + +#include "dpu_io_util.h" +#include "msm_drv.h" + +#define DP_LABEL "MDSS DP DISPLAY" +#define DP_MAX_PIXEL_CLK_KHZ 675000 +#define DP_MAX_NUM_DP_LANES 4 + +enum dp_pm_type { + DP_CORE_PM, + DP_CTRL_PM, + DP_STREAM_PM, + DP_PHY_PM, + DP_MAX_PM +}; + +struct dss_io_data { + u32 len; + void __iomem *base; +}; + +static inline const char *dp_parser_pm_name(enum dp_pm_type module) +{ + switch (module) { + case DP_CORE_PM: return "DP_CORE_PM"; + case DP_CTRL_PM: return "DP_CTRL_PM"; + case DP_STREAM_PM: return "DP_STREAM_PM"; + case DP_PHY_PM: return "DP_PHY_PM"; + default: return "???"; + } +} + +/** + * struct dp_display_data - display related device tree data. + * + * @ctrl_node: referece to controller device + * @phy_node: reference to phy device + * @is_active: is the controller currently active + * @name: name of the display + * @display_type: type of the display + */ +struct dp_display_data { + struct device_node *ctrl_node; + struct device_node *phy_node; + bool is_active; + const char *name; + const char *display_type; +}; + +/** + * struct dp_ctrl_resource - controller's IO related data + * + * @dp_controller: Display Port controller mapped memory address + * @phy_io: phy's mapped memory address + */ +struct dp_io { + struct dss_io_data dp_controller; + struct phy *phy; + union phy_configure_opts phy_opts; +}; + +/** + * struct dp_pinctrl - DP's pin control + * + * @pin: pin-controller's instance + * @state_active: active state pin control + * @state_hpd_active: hpd active state pin control + * @state_suspend: suspend state pin control + */ +struct dp_pinctrl { + struct pinctrl *pin; + struct pinctrl_state *state_active; + struct pinctrl_state *state_hpd_active; + struct pinctrl_state *state_suspend; +}; + +#define DP_DEV_REGULATOR_MAX 4 + +/* Regulators for DP devices */ +struct dp_reg_entry { + char name[32]; + int enable_load; + int disable_load; +}; + +struct dp_regulator_cfg { + int num; + struct dp_reg_entry regs[DP_DEV_REGULATOR_MAX]; +}; + +/** + * struct dp_parser - DP parser's data exposed to clients + * + * @pdev: platform data of the client + * @mp: gpio, regulator and clock related data + * @pinctrl: pin-control related data + * @disp_data: controller's display related data + * @parse: function to be called by client to parse device tree. + */ +struct dp_parser { + struct platform_device *pdev; + struct dss_module_power mp[DP_MAX_PM]; + struct dp_pinctrl pinctrl; + struct dp_io io; + struct dp_display_data disp_data; + const struct dp_regulator_cfg *regulator_cfg; + u32 max_dp_lanes; + + int (*parse)(struct dp_parser *parser); +}; + +/** + * dp_parser_get() - get the DP's device tree parser module + * + * @pdev: platform data of the client + * return: pointer to dp_parser structure. + * + * This function provides client capability to parse the + * device tree and populate the data structures. The data + * related to clock, regulators, pin-control and other + * can be parsed using this module. + */ +struct dp_parser *dp_parser_get(struct platform_device *pdev); + +#endif diff --git a/drivers/gpu/drm/msm/dp/dp_power.c b/drivers/gpu/drm/msm/dp/dp_power.c new file mode 100644 index 000000000000..17c1fc6a2d44 --- /dev/null +++ b/drivers/gpu/drm/msm/dp/dp_power.c @@ -0,0 +1,372 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (c) 2012-2020, The Linux Foundation. All rights reserved. + */ + +#define pr_fmt(fmt) "[drm-dp] %s: " fmt, __func__ + +#include <linux/clk.h> +#include <linux/clk-provider.h> +#include <linux/regulator/consumer.h> +#include "dp_power.h" +#include "msm_drv.h" + +struct dp_power_private { + struct dp_parser *parser; + struct platform_device *pdev; + struct clk *link_clk_src; + struct clk *pixel_provider; + struct clk *link_provider; + struct regulator_bulk_data supplies[DP_DEV_REGULATOR_MAX]; + + struct dp_power dp_power; +}; + +static void dp_power_regulator_disable(struct dp_power_private *power) +{ + struct regulator_bulk_data *s = power->supplies; + const struct dp_reg_entry *regs = power->parser->regulator_cfg->regs; + int num = power->parser->regulator_cfg->num; + int i; + + DBG(""); + for (i = num - 1; i >= 0; i--) + if (regs[i].disable_load >= 0) + regulator_set_load(s[i].consumer, + regs[i].disable_load); + + regulator_bulk_disable(num, s); +} + +static int dp_power_regulator_enable(struct dp_power_private *power) +{ + struct regulator_bulk_data *s = power->supplies; + const struct dp_reg_entry *regs = power->parser->regulator_cfg->regs; + int num = power->parser->regulator_cfg->num; + int ret, i; + + DBG(""); + for (i = 0; i < num; i++) { + if (regs[i].enable_load >= 0) { + ret = regulator_set_load(s[i].consumer, + regs[i].enable_load); + if (ret < 0) { + pr_err("regulator %d set op mode failed, %d\n", + i, ret); + goto fail; + } + } + } + + ret = regulator_bulk_enable(num, s); + if (ret < 0) { + pr_err("regulator enable failed, %d\n", ret); + goto fail; + } + + return 0; + +fail: + for (i--; i >= 0; i--) + regulator_set_load(s[i].consumer, regs[i].disable_load); + return ret; +} + +static int dp_power_regulator_init(struct dp_power_private *power) +{ + struct regulator_bulk_data *s = power->supplies; + const struct dp_reg_entry *regs = power->parser->regulator_cfg->regs; + struct platform_device *pdev = power->pdev; + int num = power->parser->regulator_cfg->num; + int i, ret; + + for (i = 0; i < num; i++) + s[i].supply = regs[i].name; + + ret = devm_regulator_bulk_get(&pdev->dev, num, s); + if (ret < 0) { + pr_err("%s: failed to init regulator, ret=%d\n", + __func__, ret); + return ret; + } + + return 0; +} + +static int dp_power_clk_init(struct dp_power_private *power) +{ + int rc = 0; + struct dss_module_power *core, *ctrl, *stream; + struct device *dev = &power->pdev->dev; + + core = &power->parser->mp[DP_CORE_PM]; + ctrl = &power->parser->mp[DP_CTRL_PM]; + stream = &power->parser->mp[DP_STREAM_PM]; + + rc = msm_dss_get_clk(dev, core->clk_config, core->num_clk); + if (rc) { + DRM_ERROR("failed to get %s clk. err=%d\n", + dp_parser_pm_name(DP_CORE_PM), rc); + return rc; + } + + rc = msm_dss_get_clk(dev, ctrl->clk_config, ctrl->num_clk); + if (rc) { + DRM_ERROR("failed to get %s clk. err=%d\n", + dp_parser_pm_name(DP_CTRL_PM), rc); + msm_dss_put_clk(core->clk_config, core->num_clk); + return -ENODEV; + } + + rc = msm_dss_get_clk(dev, stream->clk_config, stream->num_clk); + if (rc) { + DRM_ERROR("failed to get %s clk. err=%d\n", + dp_parser_pm_name(DP_CTRL_PM), rc); + msm_dss_put_clk(core->clk_config, core->num_clk); + return -ENODEV; + } + + return 0; +} + +static int dp_power_clk_deinit(struct dp_power_private *power) +{ + struct dss_module_power *core, *ctrl, *stream; + + core = &power->parser->mp[DP_CORE_PM]; + ctrl = &power->parser->mp[DP_CTRL_PM]; + stream = &power->parser->mp[DP_STREAM_PM]; + + if (!core || !ctrl || !stream) { + DRM_ERROR("invalid power_data\n"); + return -EINVAL; + } + + msm_dss_put_clk(ctrl->clk_config, ctrl->num_clk); + msm_dss_put_clk(core->clk_config, core->num_clk); + msm_dss_put_clk(stream->clk_config, stream->num_clk); + return 0; +} + +static int dp_power_clk_set_rate(struct dp_power_private *power, + enum dp_pm_type module, bool enable) +{ + int rc = 0; + struct dss_module_power *mp = &power->parser->mp[module]; + + if (enable) { + rc = msm_dss_clk_set_rate(mp->clk_config, mp->num_clk); + if (rc) { + DRM_ERROR("failed to set clks rate.\n"); + return rc; + } + } + + rc = msm_dss_enable_clk(mp->clk_config, mp->num_clk, enable); + if (rc) { + DRM_ERROR("failed to %d clks, err: %d\n", enable, rc); + return rc; + } + + return 0; +} + +int dp_power_clk_status(struct dp_power *dp_power, enum dp_pm_type pm_type) +{ + if (pm_type == DP_CORE_PM) + return dp_power->core_clks_on; + + if (pm_type == DP_CTRL_PM) + return dp_power->link_clks_on; + + if (pm_type == DP_STREAM_PM) + return dp_power->stream_clks_on; + + return 0; +} + +int dp_power_clk_enable(struct dp_power *dp_power, + enum dp_pm_type pm_type, bool enable) +{ + int rc = 0; + struct dp_power_private *power; + + power = container_of(dp_power, struct dp_power_private, dp_power); + + if (pm_type != DP_CORE_PM && pm_type != DP_CTRL_PM && + pm_type != DP_STREAM_PM) { + DRM_ERROR("unsupported power module: %s\n", + dp_parser_pm_name(pm_type)); + return -EINVAL; + } + + if (enable) { + if (pm_type == DP_CORE_PM && dp_power->core_clks_on) { + DRM_DEBUG_DP("core clks already enabled\n"); + return 0; + } + + if (pm_type == DP_CTRL_PM && dp_power->link_clks_on) { + DRM_DEBUG_DP("links clks already enabled\n"); + return 0; + } + + if (pm_type == DP_STREAM_PM && dp_power->stream_clks_on) { + DRM_DEBUG_DP("pixel clks already enabled\n"); + return 0; + } + + if ((pm_type == DP_CTRL_PM) && (!dp_power->core_clks_on)) { + DRM_DEBUG_DP("Enable core clks before link clks\n"); + + rc = dp_power_clk_set_rate(power, DP_CORE_PM, enable); + if (rc) { + DRM_ERROR("fail to enable clks: %s. err=%d\n", + dp_parser_pm_name(DP_CORE_PM), rc); + return rc; + } + dp_power->core_clks_on = true; + } + } + + rc = dp_power_clk_set_rate(power, pm_type, enable); + if (rc) { + DRM_ERROR("failed to '%s' clks for: %s. err=%d\n", + enable ? "enable" : "disable", + dp_parser_pm_name(pm_type), rc); + return rc; + } + + if (pm_type == DP_CORE_PM) + dp_power->core_clks_on = enable; + else if (pm_type == DP_STREAM_PM) + dp_power->stream_clks_on = enable; + else + dp_power->link_clks_on = enable; + + DRM_DEBUG_DP("%s clocks for %s\n", + enable ? "enable" : "disable", + dp_parser_pm_name(pm_type)); + DRM_DEBUG_DP("strem_clks:%s link_clks:%s core_clks:%s\n", + dp_power->stream_clks_on ? "on" : "off", + dp_power->link_clks_on ? "on" : "off", + dp_power->core_clks_on ? "on" : "off"); + + return 0; +} + +int dp_power_client_init(struct dp_power *dp_power) +{ + int rc = 0; + struct dp_power_private *power; + + if (!dp_power) { + DRM_ERROR("invalid power data\n"); + return -EINVAL; + } + + power = container_of(dp_power, struct dp_power_private, dp_power); + + pm_runtime_enable(&power->pdev->dev); + + rc = dp_power_regulator_init(power); + if (rc) { + DRM_ERROR("failed to init regulators %d\n", rc); + goto error; + } + + rc = dp_power_clk_init(power); + if (rc) { + DRM_ERROR("failed to init clocks %d\n", rc); + goto error; + } + return 0; + +error: + pm_runtime_disable(&power->pdev->dev); + return rc; +} + +void dp_power_client_deinit(struct dp_power *dp_power) +{ + struct dp_power_private *power; + + if (!dp_power) { + DRM_ERROR("invalid power data\n"); + return; + } + + power = container_of(dp_power, struct dp_power_private, dp_power); + + dp_power_clk_deinit(power); + pm_runtime_disable(&power->pdev->dev); + +} + +int dp_power_init(struct dp_power *dp_power, bool flip) +{ + int rc = 0; + struct dp_power_private *power = NULL; + + if (!dp_power) { + DRM_ERROR("invalid power data\n"); + return -EINVAL; + } + + power = container_of(dp_power, struct dp_power_private, dp_power); + + pm_runtime_get_sync(&power->pdev->dev); + rc = dp_power_regulator_enable(power); + if (rc) { + DRM_ERROR("failed to enable regulators, %d\n", rc); + goto exit; + } + + rc = dp_power_clk_enable(dp_power, DP_CORE_PM, true); + if (rc) { + DRM_ERROR("failed to enable DP core clocks, %d\n", rc); + goto err_clk; + } + + return 0; + +err_clk: + dp_power_regulator_disable(power); +exit: + pm_runtime_put_sync(&power->pdev->dev); + return rc; +} + +int dp_power_deinit(struct dp_power *dp_power) +{ + struct dp_power_private *power; + + power = container_of(dp_power, struct dp_power_private, dp_power); + + dp_power_clk_enable(dp_power, DP_CORE_PM, false); + dp_power_regulator_disable(power); + pm_runtime_put_sync(&power->pdev->dev); + return 0; +} + +struct dp_power *dp_power_get(struct dp_parser *parser) +{ + struct dp_power_private *power; + struct dp_power *dp_power; + + if (!parser) { + DRM_ERROR("invalid input\n"); + return ERR_PTR(-EINVAL); + } + + power = devm_kzalloc(&parser->pdev->dev, sizeof(*power), GFP_KERNEL); + if (!power) + return ERR_PTR(-ENOMEM); + + power->parser = parser; + power->pdev = parser->pdev; + + dp_power = &power->dp_power; + + return dp_power; +} diff --git a/drivers/gpu/drm/msm/dp/dp_power.h b/drivers/gpu/drm/msm/dp/dp_power.h new file mode 100644 index 000000000000..76743d755833 --- /dev/null +++ b/drivers/gpu/drm/msm/dp/dp_power.h @@ -0,0 +1,107 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (c) 2012-2020, The Linux Foundation. All rights reserved. + */ + +#ifndef _DP_POWER_H_ +#define _DP_POWER_H_ + +#include "dp_parser.h" + +/** + * sruct dp_power - DisplayPort's power related data + * + * @init: initializes the regulators/core clocks/GPIOs/pinctrl + * @deinit: turns off the regulators/core clocks/GPIOs/pinctrl + * @clk_enable: enable/disable the DP clocks + * @set_pixel_clk_parent: set the parent of DP pixel clock + */ +struct dp_power { + bool core_clks_on; + bool link_clks_on; + bool stream_clks_on; +}; + +/** + * dp_power_init() - enable power supplies for display controller + * + * @power: instance of power module + * @flip: bool for flipping gpio direction + * return: 0 if success or error if failure. + * + * This API will turn on the regulators and configures gpio's + * aux/hpd. + */ +int dp_power_init(struct dp_power *power, bool flip); + +/** + * dp_power_deinit() - turn off regulators and gpios. + * + * @power: instance of power module + * return: 0 for success + * + * This API turns off power and regulators. + */ +int dp_power_deinit(struct dp_power *power); + +/** + * dp_power_clk_status() - display controller clocks status + * + * @power: instance of power module + * @pm_type: type of pm, core/ctrl/phy + * return: status of power clocks + * + * This API return status of DP clocks + */ + +int dp_power_clk_status(struct dp_power *dp_power, enum dp_pm_type pm_type); + +/** + * dp_power_clk_enable() - enable display controller clocks + * + * @power: instance of power module + * @pm_type: type of pm, core/ctrl/phy + * @enable: enables or disables + * return: pointer to allocated power module data + * + * This API will call setrate and enable for DP clocks + */ + +int dp_power_clk_enable(struct dp_power *power, enum dp_pm_type pm_type, + bool enable); + +/** + * dp_power_client_init() - initialize clock and regulator modules + * + * @power: instance of power module + * return: 0 for success, error for failure. + * + * This API will configure the DisplayPort's clocks and regulator + * modules. + */ +int dp_power_client_init(struct dp_power *power); + +/** + * dp_power_clinet_deinit() - de-initialize clock and regulator modules + * + * @power: instance of power module + * return: 0 for success, error for failure. + * + * This API will de-initialize the DisplayPort's clocks and regulator + * modueles. + */ +void dp_power_client_deinit(struct dp_power *power); + +/** + * dp_power_get() - configure and get the DisplayPort power module data + * + * @parser: instance of parser module + * return: pointer to allocated power module data + * + * This API will configure the DisplayPort's power module and provides + * methods to be called by the client to configure the power related + * modueles. + */ +struct dp_power *dp_power_get(struct dp_parser *parser); + +#endif /* _DP_POWER_H_ */ diff --git a/drivers/gpu/drm/msm/dp/dp_reg.h b/drivers/gpu/drm/msm/dp/dp_reg.h new file mode 100644 index 000000000000..43042ff90a19 --- /dev/null +++ b/drivers/gpu/drm/msm/dp/dp_reg.h @@ -0,0 +1,306 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (c) 2017-2020, The Linux Foundation. All rights reserved. + */ + +#ifndef _DP_REG_H_ +#define _DP_REG_H_ + +/* DP_TX Registers */ +#define REG_DP_HW_VERSION (0x00000000) + +#define REG_DP_SW_RESET (0x00000010) +#define DP_SW_RESET (0x00000001) + +#define REG_DP_PHY_CTRL (0x00000014) +#define DP_PHY_CTRL_SW_RESET_PLL (0x00000001) +#define DP_PHY_CTRL_SW_RESET (0x00000004) + +#define REG_DP_CLK_CTRL (0x00000018) +#define REG_DP_CLK_ACTIVE (0x0000001C) +#define REG_DP_INTR_STATUS (0x00000020) +#define REG_DP_INTR_STATUS2 (0x00000024) +#define REG_DP_INTR_STATUS3 (0x00000028) + +#define REG_DP_DP_HPD_CTRL (0x00000000) +#define DP_DP_HPD_CTRL_HPD_EN (0x00000001) + +#define REG_DP_DP_HPD_INT_STATUS (0x00000004) + +#define REG_DP_DP_HPD_INT_ACK (0x00000008) +#define DP_DP_HPD_PLUG_INT_ACK (0x00000001) +#define DP_DP_IRQ_HPD_INT_ACK (0x00000002) +#define DP_DP_HPD_REPLUG_INT_ACK (0x00000004) +#define DP_DP_HPD_UNPLUG_INT_ACK (0x00000008) + +#define REG_DP_DP_HPD_INT_MASK (0x0000000C) +#define DP_DP_HPD_PLUG_INT_MASK (0x00000001) +#define DP_DP_IRQ_HPD_INT_MASK (0x00000002) +#define DP_DP_HPD_REPLUG_INT_MASK (0x00000004) +#define DP_DP_HPD_UNPLUG_INT_MASK (0x00000008) +#define DP_DP_HPD_INT_MASK (DP_DP_HPD_PLUG_INT_MASK | \ + DP_DP_IRQ_HPD_INT_MASK | \ + DP_DP_HPD_REPLUG_INT_MASK | \ + DP_DP_HPD_UNPLUG_INT_MASK) +#define DP_DP_HPD_STATE_STATUS_CONNECTED (0x40000000) +#define DP_DP_HPD_STATE_STATUS_PENDING (0x20000000) +#define DP_DP_HPD_STATE_STATUS_DISCONNECTED (0x00000000) +#define DP_DP_HPD_STATE_STATUS_MASK (0xE0000000) + +#define REG_DP_DP_HPD_REFTIMER (0x00000018) +#define DP_DP_HPD_REFTIMER_ENABLE (1 << 16) + +#define REG_DP_DP_HPD_EVENT_TIME_0 (0x0000001C) +#define REG_DP_DP_HPD_EVENT_TIME_1 (0x00000020) +#define DP_DP_HPD_EVENT_TIME_0_VAL (0x3E800FA) +#define DP_DP_HPD_EVENT_TIME_1_VAL (0x1F407D0) + +#define REG_DP_AUX_CTRL (0x00000030) +#define DP_AUX_CTRL_ENABLE (0x00000001) +#define DP_AUX_CTRL_RESET (0x00000002) + +#define REG_DP_AUX_DATA (0x00000034) +#define DP_AUX_DATA_READ (0x00000001) +#define DP_AUX_DATA_WRITE (0x00000000) +#define DP_AUX_DATA_OFFSET (0x00000008) +#define DP_AUX_DATA_INDEX_OFFSET (0x00000010) +#define DP_AUX_DATA_MASK (0x0000ff00) +#define DP_AUX_DATA_INDEX_WRITE (0x80000000) + +#define REG_DP_AUX_TRANS_CTRL (0x00000038) +#define DP_AUX_TRANS_CTRL_I2C (0x00000100) +#define DP_AUX_TRANS_CTRL_GO (0x00000200) +#define DP_AUX_TRANS_CTRL_NO_SEND_ADDR (0x00000400) +#define DP_AUX_TRANS_CTRL_NO_SEND_STOP (0x00000800) + +#define REG_DP_TIMEOUT_COUNT (0x0000003C) +#define REG_DP_AUX_LIMITS (0x00000040) +#define REG_DP_AUX_STATUS (0x00000044) + +#define DP_DPCD_CP_IRQ (0x201) +#define DP_DPCD_RXSTATUS (0x69493) + +#define DP_INTERRUPT_TRANS_NUM (0x000000A0) + +#define REG_DP_MAINLINK_CTRL (0x00000000) +#define DP_MAINLINK_CTRL_ENABLE (0x00000001) +#define DP_MAINLINK_CTRL_RESET (0x00000002) +#define DP_MAINLINK_CTRL_SW_BYPASS_SCRAMBLER (0x00000010) +#define DP_MAINLINK_FB_BOUNDARY_SEL (0x02000000) + +#define REG_DP_STATE_CTRL (0x00000004) +#define DP_STATE_CTRL_LINK_TRAINING_PATTERN1 (0x00000001) +#define DP_STATE_CTRL_LINK_TRAINING_PATTERN2 (0x00000002) +#define DP_STATE_CTRL_LINK_TRAINING_PATTERN3 (0x00000004) +#define DP_STATE_CTRL_LINK_TRAINING_PATTERN4 (0x00000008) +#define DP_STATE_CTRL_LINK_SYMBOL_ERR_MEASURE (0x00000010) +#define DP_STATE_CTRL_LINK_PRBS7 (0x00000020) +#define DP_STATE_CTRL_LINK_TEST_CUSTOM_PATTERN (0x00000040) +#define DP_STATE_CTRL_SEND_VIDEO (0x00000080) +#define DP_STATE_CTRL_PUSH_IDLE (0x00000100) + +#define REG_DP_CONFIGURATION_CTRL (0x00000008) +#define DP_CONFIGURATION_CTRL_SYNC_ASYNC_CLK (0x00000001) +#define DP_CONFIGURATION_CTRL_STATIC_DYNAMIC_CN (0x00000002) +#define DP_CONFIGURATION_CTRL_P_INTERLACED (0x00000004) +#define DP_CONFIGURATION_CTRL_INTERLACED_BTF (0x00000008) +#define DP_CONFIGURATION_CTRL_NUM_OF_LANES (0x00000010) +#define DP_CONFIGURATION_CTRL_ENHANCED_FRAMING (0x00000040) +#define DP_CONFIGURATION_CTRL_SEND_VSC (0x00000080) +#define DP_CONFIGURATION_CTRL_BPC (0x00000100) +#define DP_CONFIGURATION_CTRL_ASSR (0x00000400) +#define DP_CONFIGURATION_CTRL_RGB_YUV (0x00000800) +#define DP_CONFIGURATION_CTRL_LSCLK_DIV (0x00002000) +#define DP_CONFIGURATION_CTRL_NUM_OF_LANES_SHIFT (0x04) +#define DP_CONFIGURATION_CTRL_BPC_SHIFT (0x08) +#define DP_CONFIGURATION_CTRL_LSCLK_DIV_SHIFT (0x0D) + +#define REG_DP_SOFTWARE_MVID (0x00000010) +#define REG_DP_SOFTWARE_NVID (0x00000018) +#define REG_DP_TOTAL_HOR_VER (0x0000001C) +#define REG_DP_START_HOR_VER_FROM_SYNC (0x00000020) +#define REG_DP_HSYNC_VSYNC_WIDTH_POLARITY (0x00000024) +#define REG_DP_ACTIVE_HOR_VER (0x00000028) + +#define REG_DP_MISC1_MISC0 (0x0000002C) +#define DP_MISC0_SYNCHRONOUS_CLK (0x00000001) +#define DP_MISC0_COLORIMETRY_CFG_SHIFT (0x00000001) +#define DP_MISC0_TEST_BITS_DEPTH_SHIFT (0x00000005) + +#define REG_DP_VALID_BOUNDARY (0x00000030) +#define REG_DP_VALID_BOUNDARY_2 (0x00000034) + +#define REG_DP_LOGICAL2PHYSICAL_LANE_MAPPING (0x00000038) +#define LANE0_MAPPING_SHIFT (0x00000000) +#define LANE1_MAPPING_SHIFT (0x00000002) +#define LANE2_MAPPING_SHIFT (0x00000004) +#define LANE3_MAPPING_SHIFT (0x00000006) + +#define REG_DP_MAINLINK_READY (0x00000040) +#define DP_MAINLINK_READY_FOR_VIDEO (0x00000001) +#define DP_MAINLINK_READY_LINK_TRAINING_SHIFT (0x00000003) + +#define REG_DP_MAINLINK_LEVELS (0x00000044) +#define DP_MAINLINK_SAFE_TO_EXIT_LEVEL_2 (0x00000002) + + +#define REG_DP_TU (0x0000004C) + +#define REG_DP_HBR2_COMPLIANCE_SCRAMBLER_RESET (0x00000054) +#define DP_HBR2_ERM_PATTERN (0x00010000) + +#define REG_DP_TEST_80BIT_CUSTOM_PATTERN_REG0 (0x000000C0) +#define REG_DP_TEST_80BIT_CUSTOM_PATTERN_REG1 (0x000000C4) +#define REG_DP_TEST_80BIT_CUSTOM_PATTERN_REG2 (0x000000C8) + +#define MMSS_DP_MISC1_MISC0 (0x0000002C) +#define MMSS_DP_AUDIO_TIMING_GEN (0x00000080) +#define MMSS_DP_AUDIO_TIMING_RBR_32 (0x00000084) +#define MMSS_DP_AUDIO_TIMING_HBR_32 (0x00000088) +#define MMSS_DP_AUDIO_TIMING_RBR_44 (0x0000008C) +#define MMSS_DP_AUDIO_TIMING_HBR_44 (0x00000090) +#define MMSS_DP_AUDIO_TIMING_RBR_48 (0x00000094) +#define MMSS_DP_AUDIO_TIMING_HBR_48 (0x00000098) + +#define MMSS_DP_PSR_CRC_RG (0x00000154) +#define MMSS_DP_PSR_CRC_B (0x00000158) + +#define REG_DP_COMPRESSION_MODE_CTRL (0x00000180) + +#define MMSS_DP_AUDIO_CFG (0x00000200) +#define MMSS_DP_AUDIO_STATUS (0x00000204) +#define MMSS_DP_AUDIO_PKT_CTRL (0x00000208) +#define MMSS_DP_AUDIO_PKT_CTRL2 (0x0000020C) +#define MMSS_DP_AUDIO_ACR_CTRL (0x00000210) +#define MMSS_DP_AUDIO_CTRL_RESET (0x00000214) + +#define MMSS_DP_SDP_CFG (0x00000228) +#define MMSS_DP_SDP_CFG2 (0x0000022C) +#define MMSS_DP_AUDIO_TIMESTAMP_0 (0x00000230) +#define MMSS_DP_AUDIO_TIMESTAMP_1 (0x00000234) + +#define MMSS_DP_AUDIO_STREAM_0 (0x00000240) +#define MMSS_DP_AUDIO_STREAM_1 (0x00000244) + +#define MMSS_DP_EXTENSION_0 (0x00000250) +#define MMSS_DP_EXTENSION_1 (0x00000254) +#define MMSS_DP_EXTENSION_2 (0x00000258) +#define MMSS_DP_EXTENSION_3 (0x0000025C) +#define MMSS_DP_EXTENSION_4 (0x00000260) +#define MMSS_DP_EXTENSION_5 (0x00000264) +#define MMSS_DP_EXTENSION_6 (0x00000268) +#define MMSS_DP_EXTENSION_7 (0x0000026C) +#define MMSS_DP_EXTENSION_8 (0x00000270) +#define MMSS_DP_EXTENSION_9 (0x00000274) +#define MMSS_DP_AUDIO_COPYMANAGEMENT_0 (0x00000278) +#define MMSS_DP_AUDIO_COPYMANAGEMENT_1 (0x0000027C) +#define MMSS_DP_AUDIO_COPYMANAGEMENT_2 (0x00000280) +#define MMSS_DP_AUDIO_COPYMANAGEMENT_3 (0x00000284) +#define MMSS_DP_AUDIO_COPYMANAGEMENT_4 (0x00000288) +#define MMSS_DP_AUDIO_COPYMANAGEMENT_5 (0x0000028C) +#define MMSS_DP_AUDIO_ISRC_0 (0x00000290) +#define MMSS_DP_AUDIO_ISRC_1 (0x00000294) +#define MMSS_DP_AUDIO_ISRC_2 (0x00000298) +#define MMSS_DP_AUDIO_ISRC_3 (0x0000029C) +#define MMSS_DP_AUDIO_ISRC_4 (0x000002A0) +#define MMSS_DP_AUDIO_ISRC_5 (0x000002A4) +#define MMSS_DP_AUDIO_INFOFRAME_0 (0x000002A8) +#define MMSS_DP_AUDIO_INFOFRAME_1 (0x000002AC) +#define MMSS_DP_AUDIO_INFOFRAME_2 (0x000002B0) + +#define MMSS_DP_GENERIC0_0 (0x00000300) +#define MMSS_DP_GENERIC0_1 (0x00000304) +#define MMSS_DP_GENERIC0_2 (0x00000308) +#define MMSS_DP_GENERIC0_3 (0x0000030C) +#define MMSS_DP_GENERIC0_4 (0x00000310) +#define MMSS_DP_GENERIC0_5 (0x00000314) +#define MMSS_DP_GENERIC0_6 (0x00000318) +#define MMSS_DP_GENERIC0_7 (0x0000031C) +#define MMSS_DP_GENERIC0_8 (0x00000320) +#define MMSS_DP_GENERIC0_9 (0x00000324) +#define MMSS_DP_GENERIC1_0 (0x00000328) +#define MMSS_DP_GENERIC1_1 (0x0000032C) +#define MMSS_DP_GENERIC1_2 (0x00000330) +#define MMSS_DP_GENERIC1_3 (0x00000334) +#define MMSS_DP_GENERIC1_4 (0x00000338) +#define MMSS_DP_GENERIC1_5 (0x0000033C) +#define MMSS_DP_GENERIC1_6 (0x00000340) +#define MMSS_DP_GENERIC1_7 (0x00000344) +#define MMSS_DP_GENERIC1_8 (0x00000348) +#define MMSS_DP_GENERIC1_9 (0x0000034C) + +#define MMSS_DP_VSCEXT_0 (0x000002D0) +#define MMSS_DP_VSCEXT_1 (0x000002D4) +#define MMSS_DP_VSCEXT_2 (0x000002D8) +#define MMSS_DP_VSCEXT_3 (0x000002DC) +#define MMSS_DP_VSCEXT_4 (0x000002E0) +#define MMSS_DP_VSCEXT_5 (0x000002E4) +#define MMSS_DP_VSCEXT_6 (0x000002E8) +#define MMSS_DP_VSCEXT_7 (0x000002EC) +#define MMSS_DP_VSCEXT_8 (0x000002F0) +#define MMSS_DP_VSCEXT_9 (0x000002F4) + +#define MMSS_DP_BIST_ENABLE (0x00000000) +#define DP_BIST_ENABLE_DPBIST_EN (0x00000001) + +#define MMSS_DP_TIMING_ENGINE_EN (0x00000010) +#define DP_TIMING_ENGINE_EN_EN (0x00000001) + +#define MMSS_DP_INTF_CONFIG (0x00000014) +#define MMSS_DP_INTF_HSYNC_CTL (0x00000018) +#define MMSS_DP_INTF_VSYNC_PERIOD_F0 (0x0000001C) +#define MMSS_DP_INTF_VSYNC_PERIOD_F1 (0x00000020) +#define MMSS_DP_INTF_VSYNC_PULSE_WIDTH_F0 (0x00000024) +#define MMSS_DP_INTF_VSYNC_PULSE_WIDTH_F1 (0x00000028) +#define MMSS_INTF_DISPLAY_V_START_F0 (0x0000002C) +#define MMSS_INTF_DISPLAY_V_START_F1 (0x00000030) +#define MMSS_DP_INTF_DISPLAY_V_END_F0 (0x00000034) +#define MMSS_DP_INTF_DISPLAY_V_END_F1 (0x00000038) +#define MMSS_DP_INTF_ACTIVE_V_START_F0 (0x0000003C) +#define MMSS_DP_INTF_ACTIVE_V_START_F1 (0x00000040) +#define MMSS_DP_INTF_ACTIVE_V_END_F0 (0x00000044) +#define MMSS_DP_INTF_ACTIVE_V_END_F1 (0x00000048) +#define MMSS_DP_INTF_DISPLAY_HCTL (0x0000004C) +#define MMSS_DP_INTF_ACTIVE_HCTL (0x00000050) +#define MMSS_DP_INTF_POLARITY_CTL (0x00000058) + +#define MMSS_DP_TPG_MAIN_CONTROL (0x00000060) +#define MMSS_DP_DSC_DTO (0x0000007C) +#define DP_TPG_CHECKERED_RECT_PATTERN (0x00000100) + +#define MMSS_DP_TPG_VIDEO_CONFIG (0x00000064) +#define DP_TPG_VIDEO_CONFIG_BPP_8BIT (0x00000001) +#define DP_TPG_VIDEO_CONFIG_RGB (0x00000004) + +#define MMSS_DP_ASYNC_FIFO_CONFIG (0x00000088) + +#define REG_DP_PHY_AUX_INTERRUPT_CLEAR (0x0000004C) +#define REG_DP_PHY_AUX_BIST_CFG (0x00000050) +#define REG_DP_PHY_AUX_INTERRUPT_STATUS (0x000000BC) + +/* DP HDCP 1.3 registers */ +#define DP_HDCP_CTRL (0x0A0) +#define DP_HDCP_STATUS (0x0A4) +#define DP_HDCP_SW_UPPER_AKSV (0x098) +#define DP_HDCP_SW_LOWER_AKSV (0x09C) +#define DP_HDCP_ENTROPY_CTRL0 (0x350) +#define DP_HDCP_ENTROPY_CTRL1 (0x35C) +#define DP_HDCP_SHA_STATUS (0x0C8) +#define DP_HDCP_RCVPORT_DATA2_0 (0x0B0) +#define DP_HDCP_RCVPORT_DATA3 (0x0A4) +#define DP_HDCP_RCVPORT_DATA4 (0x0A8) +#define DP_HDCP_RCVPORT_DATA5 (0x0C0) +#define DP_HDCP_RCVPORT_DATA6 (0x0C4) + +#define HDCP_SEC_DP_TZ_HV_HLOS_HDCP_SHA_CTRL (0x024) +#define HDCP_SEC_DP_TZ_HV_HLOS_HDCP_SHA_DATA (0x028) +#define HDCP_SEC_DP_TZ_HV_HLOS_HDCP_RCVPORT_DATA0 (0x004) +#define HDCP_SEC_DP_TZ_HV_HLOS_HDCP_RCVPORT_DATA1 (0x008) +#define HDCP_SEC_DP_TZ_HV_HLOS_HDCP_RCVPORT_DATA7 (0x00C) +#define HDCP_SEC_DP_TZ_HV_HLOS_HDCP_RCVPORT_DATA8 (0x010) +#define HDCP_SEC_DP_TZ_HV_HLOS_HDCP_RCVPORT_DATA9 (0x014) +#define HDCP_SEC_DP_TZ_HV_HLOS_HDCP_RCVPORT_DATA10 (0x018) +#define HDCP_SEC_DP_TZ_HV_HLOS_HDCP_RCVPORT_DATA11 (0x01C) +#define HDCP_SEC_DP_TZ_HV_HLOS_HDCP_RCVPORT_DATA12 (0x020) + +#endif /* _DP_REG_H_ */ diff --git a/drivers/gpu/drm/msm/dsi/dsi.h b/drivers/gpu/drm/msm/dsi/dsi.h index 4de771d6f0be..78ef5d4ed922 100644 --- a/drivers/gpu/drm/msm/dsi/dsi.h +++ b/drivers/gpu/drm/msm/dsi/dsi.h @@ -30,6 +30,8 @@ enum msm_dsi_phy_type { MSM_DSI_PHY_28NM_8960, MSM_DSI_PHY_14NM, MSM_DSI_PHY_10NM, + MSM_DSI_PHY_7NM, + MSM_DSI_PHY_7NM_V4_1, MSM_DSI_PHY_MAX }; diff --git a/drivers/gpu/drm/msm/dsi/dsi.xml.h b/drivers/gpu/drm/msm/dsi/dsi.xml.h index 8e536e060070..50eb4d1b8fdd 100644 --- a/drivers/gpu/drm/msm/dsi/dsi.xml.h +++ b/drivers/gpu/drm/msm/dsi/dsi.xml.h @@ -1886,5 +1886,428 @@ static inline uint32_t REG_DSI_10nm_PHY_LN_TX_DCTRL(uint32_t i0) { return 0x0000 #define REG_DSI_10nm_PHY_PLL_COMMON_STATUS_ONE 0x000001a0 +#define REG_DSI_7nm_PHY_CMN_REVISION_ID0 0x00000000 + +#define REG_DSI_7nm_PHY_CMN_REVISION_ID1 0x00000004 + +#define REG_DSI_7nm_PHY_CMN_REVISION_ID2 0x00000008 + +#define REG_DSI_7nm_PHY_CMN_REVISION_ID3 0x0000000c + +#define REG_DSI_7nm_PHY_CMN_CLK_CFG0 0x00000010 + +#define REG_DSI_7nm_PHY_CMN_CLK_CFG1 0x00000014 + +#define REG_DSI_7nm_PHY_CMN_GLBL_CTRL 0x00000018 + +#define REG_DSI_7nm_PHY_CMN_RBUF_CTRL 0x0000001c + +#define REG_DSI_7nm_PHY_CMN_VREG_CTRL_0 0x00000020 + +#define REG_DSI_7nm_PHY_CMN_CTRL_0 0x00000024 + +#define REG_DSI_7nm_PHY_CMN_CTRL_1 0x00000028 + +#define REG_DSI_7nm_PHY_CMN_CTRL_2 0x0000002c + +#define REG_DSI_7nm_PHY_CMN_CTRL_3 0x00000030 + +#define REG_DSI_7nm_PHY_CMN_LANE_CFG0 0x00000034 + +#define REG_DSI_7nm_PHY_CMN_LANE_CFG1 0x00000038 + +#define REG_DSI_7nm_PHY_CMN_PLL_CNTRL 0x0000003c + +#define REG_DSI_7nm_PHY_CMN_DPHY_SOT 0x00000040 + +#define REG_DSI_7nm_PHY_CMN_LANE_CTRL0 0x000000a0 + +#define REG_DSI_7nm_PHY_CMN_LANE_CTRL1 0x000000a4 + +#define REG_DSI_7nm_PHY_CMN_LANE_CTRL2 0x000000a8 + +#define REG_DSI_7nm_PHY_CMN_LANE_CTRL3 0x000000ac + +#define REG_DSI_7nm_PHY_CMN_LANE_CTRL4 0x000000b0 + +#define REG_DSI_7nm_PHY_CMN_TIMING_CTRL_0 0x000000b4 + +#define REG_DSI_7nm_PHY_CMN_TIMING_CTRL_1 0x000000b8 + +#define REG_DSI_7nm_PHY_CMN_TIMING_CTRL_2 0x000000bc + +#define REG_DSI_7nm_PHY_CMN_TIMING_CTRL_3 0x000000c0 + +#define REG_DSI_7nm_PHY_CMN_TIMING_CTRL_4 0x000000c4 + +#define REG_DSI_7nm_PHY_CMN_TIMING_CTRL_5 0x000000c8 + +#define REG_DSI_7nm_PHY_CMN_TIMING_CTRL_6 0x000000cc + +#define REG_DSI_7nm_PHY_CMN_TIMING_CTRL_7 0x000000d0 + +#define REG_DSI_7nm_PHY_CMN_TIMING_CTRL_8 0x000000d4 + +#define REG_DSI_7nm_PHY_CMN_TIMING_CTRL_9 0x000000d8 + +#define REG_DSI_7nm_PHY_CMN_TIMING_CTRL_10 0x000000dc + +#define REG_DSI_7nm_PHY_CMN_TIMING_CTRL_11 0x000000e0 + +#define REG_DSI_7nm_PHY_CMN_TIMING_CTRL_12 0x000000e4 + +#define REG_DSI_7nm_PHY_CMN_TIMING_CTRL_13 0x000000e8 + +#define REG_DSI_7nm_PHY_CMN_GLBL_HSTX_STR_CTRL_0 0x000000ec + +#define REG_DSI_7nm_PHY_CMN_GLBL_HSTX_STR_CTRL_1 0x000000f0 + +#define REG_DSI_7nm_PHY_CMN_GLBL_RESCODE_OFFSET_TOP_CTRL 0x000000f4 + +#define REG_DSI_7nm_PHY_CMN_GLBL_RESCODE_OFFSET_BOT_CTRL 0x000000f8 + +#define REG_DSI_7nm_PHY_CMN_GLBL_RESCODE_OFFSET_MID_CTRL 0x000000fc + +#define REG_DSI_7nm_PHY_CMN_GLBL_LPTX_STR_CTRL 0x00000100 + +#define REG_DSI_7nm_PHY_CMN_GLBL_PEMPH_CTRL_0 0x00000104 + +#define REG_DSI_7nm_PHY_CMN_GLBL_PEMPH_CTRL_1 0x00000108 + +#define REG_DSI_7nm_PHY_CMN_GLBL_STR_SWI_CAL_SEL_CTRL 0x0000010c + +#define REG_DSI_7nm_PHY_CMN_VREG_CTRL_1 0x00000110 + +#define REG_DSI_7nm_PHY_CMN_CTRL_4 0x00000114 + +#define REG_DSI_7nm_PHY_CMN_GLBL_DIGTOP_SPARE4 0x00000128 + +#define REG_DSI_7nm_PHY_CMN_PHY_STATUS 0x00000140 + +#define REG_DSI_7nm_PHY_CMN_LANE_STATUS0 0x00000148 + +#define REG_DSI_7nm_PHY_CMN_LANE_STATUS1 0x0000014c + +static inline uint32_t REG_DSI_7nm_PHY_LN(uint32_t i0) { return 0x00000000 + 0x80*i0; } + +static inline uint32_t REG_DSI_7nm_PHY_LN_CFG0(uint32_t i0) { return 0x00000000 + 0x80*i0; } + +static inline uint32_t REG_DSI_7nm_PHY_LN_CFG1(uint32_t i0) { return 0x00000004 + 0x80*i0; } + +static inline uint32_t REG_DSI_7nm_PHY_LN_CFG2(uint32_t i0) { return 0x00000008 + 0x80*i0; } + +static inline uint32_t REG_DSI_7nm_PHY_LN_TEST_DATAPATH(uint32_t i0) { return 0x0000000c + 0x80*i0; } + +static inline uint32_t REG_DSI_7nm_PHY_LN_PIN_SWAP(uint32_t i0) { return 0x00000010 + 0x80*i0; } + +static inline uint32_t REG_DSI_7nm_PHY_LN_LPRX_CTRL(uint32_t i0) { return 0x00000014 + 0x80*i0; } + +static inline uint32_t REG_DSI_7nm_PHY_LN_TX_DCTRL(uint32_t i0) { return 0x00000018 + 0x80*i0; } + +#define REG_DSI_7nm_PHY_PLL_ANALOG_CONTROLS_ONE 0x00000000 + +#define REG_DSI_7nm_PHY_PLL_ANALOG_CONTROLS_TWO 0x00000004 + +#define REG_DSI_7nm_PHY_PLL_INT_LOOP_SETTINGS 0x00000008 + +#define REG_DSI_7nm_PHY_PLL_INT_LOOP_SETTINGS_TWO 0x0000000c + +#define REG_DSI_7nm_PHY_PLL_ANALOG_CONTROLS_THREE 0x00000010 + +#define REG_DSI_7nm_PHY_PLL_ANALOG_CONTROLS_FOUR 0x00000014 + +#define REG_DSI_7nm_PHY_PLL_ANALOG_CONTROLS_FIVE 0x00000018 + +#define REG_DSI_7nm_PHY_PLL_INT_LOOP_CONTROLS 0x0000001c + +#define REG_DSI_7nm_PHY_PLL_DSM_DIVIDER 0x00000020 + +#define REG_DSI_7nm_PHY_PLL_FEEDBACK_DIVIDER 0x00000024 + +#define REG_DSI_7nm_PHY_PLL_SYSTEM_MUXES 0x00000028 + +#define REG_DSI_7nm_PHY_PLL_FREQ_UPDATE_CONTROL_OVERRIDES 0x0000002c + +#define REG_DSI_7nm_PHY_PLL_CMODE 0x00000030 + +#define REG_DSI_7nm_PHY_PLL_PSM_CTRL 0x00000034 + +#define REG_DSI_7nm_PHY_PLL_RSM_CTRL 0x00000038 + +#define REG_DSI_7nm_PHY_PLL_VCO_TUNE_MAP 0x0000003c + +#define REG_DSI_7nm_PHY_PLL_PLL_CNTRL 0x00000040 + +#define REG_DSI_7nm_PHY_PLL_CALIBRATION_SETTINGS 0x00000044 + +#define REG_DSI_7nm_PHY_PLL_BAND_SEL_CAL_TIMER_LOW 0x00000048 + +#define REG_DSI_7nm_PHY_PLL_BAND_SEL_CAL_TIMER_HIGH 0x0000004c + +#define REG_DSI_7nm_PHY_PLL_BAND_SEL_CAL_SETTINGS 0x00000050 + +#define REG_DSI_7nm_PHY_PLL_BAND_SEL_MIN 0x00000054 + +#define REG_DSI_7nm_PHY_PLL_BAND_SEL_MAX 0x00000058 + +#define REG_DSI_7nm_PHY_PLL_BAND_SEL_PFILT 0x0000005c + +#define REG_DSI_7nm_PHY_PLL_BAND_SEL_IFILT 0x00000060 + +#define REG_DSI_7nm_PHY_PLL_BAND_SEL_CAL_SETTINGS_TWO 0x00000064 + +#define REG_DSI_7nm_PHY_PLL_BAND_SEL_CAL_SETTINGS_THREE 0x00000068 + +#define REG_DSI_7nm_PHY_PLL_BAND_SEL_CAL_SETTINGS_FOUR 0x0000006c + +#define REG_DSI_7nm_PHY_PLL_BAND_SEL_ICODE_HIGH 0x00000070 + +#define REG_DSI_7nm_PHY_PLL_BAND_SEL_ICODE_LOW 0x00000074 + +#define REG_DSI_7nm_PHY_PLL_FREQ_DETECT_SETTINGS_ONE 0x00000078 + +#define REG_DSI_7nm_PHY_PLL_FREQ_DETECT_THRESH 0x0000007c + +#define REG_DSI_7nm_PHY_PLL_FREQ_DET_REFCLK_HIGH 0x00000080 + +#define REG_DSI_7nm_PHY_PLL_FREQ_DET_REFCLK_LOW 0x00000084 + +#define REG_DSI_7nm_PHY_PLL_FREQ_DET_PLLCLK_HIGH 0x00000088 + +#define REG_DSI_7nm_PHY_PLL_FREQ_DET_PLLCLK_LOW 0x0000008c + +#define REG_DSI_7nm_PHY_PLL_PFILT 0x00000090 + +#define REG_DSI_7nm_PHY_PLL_IFILT 0x00000094 + +#define REG_DSI_7nm_PHY_PLL_PLL_GAIN 0x00000098 + +#define REG_DSI_7nm_PHY_PLL_ICODE_LOW 0x0000009c + +#define REG_DSI_7nm_PHY_PLL_ICODE_HIGH 0x000000a0 + +#define REG_DSI_7nm_PHY_PLL_LOCKDET 0x000000a4 + +#define REG_DSI_7nm_PHY_PLL_OUTDIV 0x000000a8 + +#define REG_DSI_7nm_PHY_PLL_FASTLOCK_CONTROL 0x000000ac + +#define REG_DSI_7nm_PHY_PLL_PASS_OUT_OVERRIDE_ONE 0x000000b0 + +#define REG_DSI_7nm_PHY_PLL_PASS_OUT_OVERRIDE_TWO 0x000000b4 + +#define REG_DSI_7nm_PHY_PLL_CORE_OVERRIDE 0x000000b8 + +#define REG_DSI_7nm_PHY_PLL_CORE_INPUT_OVERRIDE 0x000000bc + +#define REG_DSI_7nm_PHY_PLL_RATE_CHANGE 0x000000c0 + +#define REG_DSI_7nm_PHY_PLL_PLL_DIGITAL_TIMERS 0x000000c4 + +#define REG_DSI_7nm_PHY_PLL_PLL_DIGITAL_TIMERS_TWO 0x000000c8 + +#define REG_DSI_7nm_PHY_PLL_DECIMAL_DIV_START 0x000000cc + +#define REG_DSI_7nm_PHY_PLL_FRAC_DIV_START_LOW 0x000000d0 + +#define REG_DSI_7nm_PHY_PLL_FRAC_DIV_START_MID 0x000000d4 + +#define REG_DSI_7nm_PHY_PLL_FRAC_DIV_START_HIGH 0x000000d8 + +#define REG_DSI_7nm_PHY_PLL_DEC_FRAC_MUXES 0x000000dc + +#define REG_DSI_7nm_PHY_PLL_DECIMAL_DIV_START_1 0x000000e0 + +#define REG_DSI_7nm_PHY_PLL_FRAC_DIV_START_LOW_1 0x000000e4 + +#define REG_DSI_7nm_PHY_PLL_FRAC_DIV_START_MID_1 0x000000e8 + +#define REG_DSI_7nm_PHY_PLL_FRAC_DIV_START_HIGH_1 0x000000ec + +#define REG_DSI_7nm_PHY_PLL_DECIMAL_DIV_START_2 0x000000f0 + +#define REG_DSI_7nm_PHY_PLL_FRAC_DIV_START_LOW_2 0x000000f4 + +#define REG_DSI_7nm_PHY_PLL_FRAC_DIV_START_MID_2 0x000000f8 + +#define REG_DSI_7nm_PHY_PLL_FRAC_DIV_START_HIGH_2 0x000000fc + +#define REG_DSI_7nm_PHY_PLL_MASH_CONTROL 0x00000100 + +#define REG_DSI_7nm_PHY_PLL_SSC_STEPSIZE_LOW 0x00000104 + +#define REG_DSI_7nm_PHY_PLL_SSC_STEPSIZE_HIGH 0x00000108 + +#define REG_DSI_7nm_PHY_PLL_SSC_DIV_PER_LOW 0x0000010c + +#define REG_DSI_7nm_PHY_PLL_SSC_DIV_PER_HIGH 0x00000110 + +#define REG_DSI_7nm_PHY_PLL_SSC_ADJPER_LOW 0x00000114 + +#define REG_DSI_7nm_PHY_PLL_SSC_ADJPER_HIGH 0x00000118 + +#define REG_DSI_7nm_PHY_PLL_SSC_MUX_CONTROL 0x0000011c + +#define REG_DSI_7nm_PHY_PLL_SSC_STEPSIZE_LOW_1 0x00000120 + +#define REG_DSI_7nm_PHY_PLL_SSC_STEPSIZE_HIGH_1 0x00000124 + +#define REG_DSI_7nm_PHY_PLL_SSC_DIV_PER_LOW_1 0x00000128 + +#define REG_DSI_7nm_PHY_PLL_SSC_DIV_PER_HIGH_1 0x0000012c + +#define REG_DSI_7nm_PHY_PLL_SSC_ADJPER_LOW_1 0x00000130 + +#define REG_DSI_7nm_PHY_PLL_SSC_ADJPER_HIGH_1 0x00000134 + +#define REG_DSI_7nm_PHY_PLL_SSC_STEPSIZE_LOW_2 0x00000138 + +#define REG_DSI_7nm_PHY_PLL_SSC_STEPSIZE_HIGH_2 0x0000013c + +#define REG_DSI_7nm_PHY_PLL_SSC_DIV_PER_LOW_2 0x00000140 + +#define REG_DSI_7nm_PHY_PLL_SSC_DIV_PER_HIGH_2 0x00000144 + +#define REG_DSI_7nm_PHY_PLL_SSC_ADJPER_LOW_2 0x00000148 + +#define REG_DSI_7nm_PHY_PLL_SSC_ADJPER_HIGH_2 0x0000014c + +#define REG_DSI_7nm_PHY_PLL_SSC_CONTROL 0x00000150 + +#define REG_DSI_7nm_PHY_PLL_PLL_OUTDIV_RATE 0x00000154 + +#define REG_DSI_7nm_PHY_PLL_PLL_LOCKDET_RATE_1 0x00000158 + +#define REG_DSI_7nm_PHY_PLL_PLL_LOCKDET_RATE_2 0x0000015c + +#define REG_DSI_7nm_PHY_PLL_PLL_PROP_GAIN_RATE_1 0x00000160 + +#define REG_DSI_7nm_PHY_PLL_PLL_PROP_GAIN_RATE_2 0x00000164 + +#define REG_DSI_7nm_PHY_PLL_PLL_BAND_SEL_RATE_1 0x00000168 + +#define REG_DSI_7nm_PHY_PLL_PLL_BAND_SEL_RATE_2 0x0000016c + +#define REG_DSI_7nm_PHY_PLL_PLL_INT_GAIN_IFILT_BAND_1 0x00000170 + +#define REG_DSI_7nm_PHY_PLL_PLL_INT_GAIN_IFILT_BAND_2 0x00000174 + +#define REG_DSI_7nm_PHY_PLL_PLL_FL_INT_GAIN_PFILT_BAND_1 0x00000178 + +#define REG_DSI_7nm_PHY_PLL_PLL_FL_INT_GAIN_PFILT_BAND_2 0x0000017c + +#define REG_DSI_7nm_PHY_PLL_PLL_FASTLOCK_EN_BAND 0x00000180 + +#define REG_DSI_7nm_PHY_PLL_FREQ_TUNE_ACCUM_INIT_MID 0x00000184 + +#define REG_DSI_7nm_PHY_PLL_FREQ_TUNE_ACCUM_INIT_HIGH 0x00000188 + +#define REG_DSI_7nm_PHY_PLL_FREQ_TUNE_ACCUM_INIT_MUX 0x0000018c + +#define REG_DSI_7nm_PHY_PLL_PLL_LOCK_OVERRIDE 0x00000190 + +#define REG_DSI_7nm_PHY_PLL_PLL_LOCK_DELAY 0x00000194 + +#define REG_DSI_7nm_PHY_PLL_PLL_LOCK_MIN_DELAY 0x00000198 + +#define REG_DSI_7nm_PHY_PLL_CLOCK_INVERTERS 0x0000019c + +#define REG_DSI_7nm_PHY_PLL_SPARE_AND_JPC_OVERRIDES 0x000001a0 + +#define REG_DSI_7nm_PHY_PLL_BIAS_CONTROL_1 0x000001a4 + +#define REG_DSI_7nm_PHY_PLL_BIAS_CONTROL_2 0x000001a8 + +#define REG_DSI_7nm_PHY_PLL_ALOG_OBSV_BUS_CTRL_1 0x000001ac + +#define REG_DSI_7nm_PHY_PLL_COMMON_STATUS_ONE 0x000001b0 + +#define REG_DSI_7nm_PHY_PLL_COMMON_STATUS_TWO 0x000001b4 + +#define REG_DSI_7nm_PHY_PLL_BAND_SEL_CAL 0x000001b8 + +#define REG_DSI_7nm_PHY_PLL_ICODE_ACCUM_STATUS_LOW 0x000001bc + +#define REG_DSI_7nm_PHY_PLL_ICODE_ACCUM_STATUS_HIGH 0x000001c0 + +#define REG_DSI_7nm_PHY_PLL_FD_OUT_LOW 0x000001c4 + +#define REG_DSI_7nm_PHY_PLL_FD_OUT_HIGH 0x000001c8 + +#define REG_DSI_7nm_PHY_PLL_ALOG_OBSV_BUS_STATUS_1 0x000001cc + +#define REG_DSI_7nm_PHY_PLL_PLL_MISC_CONFIG 0x000001d0 + +#define REG_DSI_7nm_PHY_PLL_FLL_CONFIG 0x000001d4 + +#define REG_DSI_7nm_PHY_PLL_FLL_FREQ_ACQ_TIME 0x000001d8 + +#define REG_DSI_7nm_PHY_PLL_FLL_CODE0 0x000001dc + +#define REG_DSI_7nm_PHY_PLL_FLL_CODE1 0x000001e0 + +#define REG_DSI_7nm_PHY_PLL_FLL_GAIN0 0x000001e4 + +#define REG_DSI_7nm_PHY_PLL_FLL_GAIN1 0x000001e8 + +#define REG_DSI_7nm_PHY_PLL_SW_RESET 0x000001ec + +#define REG_DSI_7nm_PHY_PLL_FAST_PWRUP 0x000001f0 + +#define REG_DSI_7nm_PHY_PLL_LOCKTIME0 0x000001f4 + +#define REG_DSI_7nm_PHY_PLL_LOCKTIME1 0x000001f8 + +#define REG_DSI_7nm_PHY_PLL_DEBUG_BUS_SEL 0x000001fc + +#define REG_DSI_7nm_PHY_PLL_DEBUG_BUS0 0x00000200 + +#define REG_DSI_7nm_PHY_PLL_DEBUG_BUS1 0x00000204 + +#define REG_DSI_7nm_PHY_PLL_DEBUG_BUS2 0x00000208 + +#define REG_DSI_7nm_PHY_PLL_DEBUG_BUS3 0x0000020c + +#define REG_DSI_7nm_PHY_PLL_ANALOG_FLL_CONTROL_OVERRIDES 0x00000210 + +#define REG_DSI_7nm_PHY_PLL_VCO_CONFIG 0x00000214 + +#define REG_DSI_7nm_PHY_PLL_VCO_CAL_CODE1_MODE0_STATUS 0x00000218 + +#define REG_DSI_7nm_PHY_PLL_VCO_CAL_CODE1_MODE1_STATUS 0x0000021c + +#define REG_DSI_7nm_PHY_PLL_RESET_SM_STATUS 0x00000220 + +#define REG_DSI_7nm_PHY_PLL_TDC_OFFSET 0x00000224 + +#define REG_DSI_7nm_PHY_PLL_PS3_PWRDOWN_CONTROLS 0x00000228 + +#define REG_DSI_7nm_PHY_PLL_PS4_PWRDOWN_CONTROLS 0x0000022c + +#define REG_DSI_7nm_PHY_PLL_PLL_RST_CONTROLS 0x00000230 + +#define REG_DSI_7nm_PHY_PLL_GEAR_BAND_SELECT_CONTROLS 0x00000234 + +#define REG_DSI_7nm_PHY_PLL_PSM_CLK_CONTROLS 0x00000238 + +#define REG_DSI_7nm_PHY_PLL_SYSTEM_MUXES_2 0x0000023c + +#define REG_DSI_7nm_PHY_PLL_VCO_CONFIG_1 0x00000240 + +#define REG_DSI_7nm_PHY_PLL_VCO_CONFIG_2 0x00000244 + +#define REG_DSI_7nm_PHY_PLL_CLOCK_INVERTERS_1 0x00000248 + +#define REG_DSI_7nm_PHY_PLL_CLOCK_INVERTERS_2 0x0000024c + +#define REG_DSI_7nm_PHY_PLL_CMODE_1 0x00000250 + +#define REG_DSI_7nm_PHY_PLL_CMODE_2 0x00000254 + +#define REG_DSI_7nm_PHY_PLL_ANALOG_CONTROLS_FIVE_1 0x00000258 + +#define REG_DSI_7nm_PHY_PLL_ANALOG_CONTROLS_FIVE_2 0x0000025c + +#define REG_DSI_7nm_PHY_PLL_PERF_OPTIMIZE 0x00000260 #endif /* DSI_XML */ diff --git a/drivers/gpu/drm/msm/dsi/dsi_cfg.c b/drivers/gpu/drm/msm/dsi/dsi_cfg.c index f892f2cbe8bb..b2ff68a15791 100644 --- a/drivers/gpu/drm/msm/dsi/dsi_cfg.c +++ b/drivers/gpu/drm/msm/dsi/dsi_cfg.c @@ -265,9 +265,12 @@ static const struct msm_dsi_cfg_handler dsi_cfg_handlers[] = { &msm8998_dsi_cfg, &msm_dsi_6g_v2_host_ops}, {MSM_DSI_VER_MAJOR_6G, MSM_DSI_6G_VER_MINOR_V2_2_1, &sdm845_dsi_cfg, &msm_dsi_6g_v2_host_ops}, + {MSM_DSI_VER_MAJOR_6G, MSM_DSI_6G_VER_MINOR_V2_3_0, + &sdm845_dsi_cfg, &msm_dsi_6g_v2_host_ops}, + {MSM_DSI_VER_MAJOR_6G, MSM_DSI_6G_VER_MINOR_V2_4_0, + &sdm845_dsi_cfg, &msm_dsi_6g_v2_host_ops}, {MSM_DSI_VER_MAJOR_6G, MSM_DSI_6G_VER_MINOR_V2_4_1, &sc7180_dsi_cfg, &msm_dsi_6g_v2_host_ops}, - }; const struct msm_dsi_cfg_handler *msm_dsi_cfg_get(u32 major, u32 minor) diff --git a/drivers/gpu/drm/msm/dsi/dsi_cfg.h b/drivers/gpu/drm/msm/dsi/dsi_cfg.h index efd469d1db45..ade9b609c7d9 100644 --- a/drivers/gpu/drm/msm/dsi/dsi_cfg.h +++ b/drivers/gpu/drm/msm/dsi/dsi_cfg.h @@ -21,6 +21,8 @@ #define MSM_DSI_6G_VER_MINOR_V2_1_0 0x20010000 #define MSM_DSI_6G_VER_MINOR_V2_2_0 0x20000000 #define MSM_DSI_6G_VER_MINOR_V2_2_1 0x20020001 +#define MSM_DSI_6G_VER_MINOR_V2_3_0 0x20030000 +#define MSM_DSI_6G_VER_MINOR_V2_4_0 0x20040000 #define MSM_DSI_6G_VER_MINOR_V2_4_1 0x20040001 #define MSM_DSI_V2_VER_MINOR_8064 0x0 diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c b/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c index 009f5b843dd1..e8c1a727179c 100644 --- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c +++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c @@ -364,6 +364,102 @@ int msm_dsi_dphy_timing_calc_v3(struct msm_dsi_dphy_timing *timing, return 0; } +int msm_dsi_dphy_timing_calc_v4(struct msm_dsi_dphy_timing *timing, + struct msm_dsi_phy_clk_request *clk_req) +{ + const unsigned long bit_rate = clk_req->bitclk_rate; + const unsigned long esc_rate = clk_req->escclk_rate; + s32 ui, ui_x8; + s32 tmax, tmin; + s32 pcnt_clk_prep = 50; + s32 pcnt_clk_zero = 2; + s32 pcnt_clk_trail = 30; + s32 pcnt_hs_prep = 50; + s32 pcnt_hs_zero = 10; + s32 pcnt_hs_trail = 30; + s32 pcnt_hs_exit = 10; + s32 coeff = 1000; /* Precision, should avoid overflow */ + s32 hb_en; + s32 temp; + + if (!bit_rate || !esc_rate) + return -EINVAL; + + hb_en = 0; + + ui = mult_frac(NSEC_PER_MSEC, coeff, bit_rate / 1000); + ui_x8 = ui << 3; + + /* TODO: verify these calculations against latest downstream driver + * everything except clk_post/clk_pre uses calculations from v3 based + * on the downstream driver having the same calculations for v3 and v4 + */ + + temp = S_DIV_ROUND_UP(38 * coeff, ui_x8); + tmin = max_t(s32, temp, 0); + temp = (95 * coeff) / ui_x8; + tmax = max_t(s32, temp, 0); + timing->clk_prepare = linear_inter(tmax, tmin, pcnt_clk_prep, 0, false); + + temp = 300 * coeff - (timing->clk_prepare << 3) * ui; + tmin = S_DIV_ROUND_UP(temp, ui_x8) - 1; + tmax = (tmin > 255) ? 511 : 255; + timing->clk_zero = linear_inter(tmax, tmin, pcnt_clk_zero, 0, false); + + tmin = DIV_ROUND_UP(60 * coeff + 3 * ui, ui_x8); + temp = 105 * coeff + 12 * ui - 20 * coeff; + tmax = (temp + 3 * ui) / ui_x8; + timing->clk_trail = linear_inter(tmax, tmin, pcnt_clk_trail, 0, false); + + temp = S_DIV_ROUND_UP(40 * coeff + 4 * ui, ui_x8); + tmin = max_t(s32, temp, 0); + temp = (85 * coeff + 6 * ui) / ui_x8; + tmax = max_t(s32, temp, 0); + timing->hs_prepare = linear_inter(tmax, tmin, pcnt_hs_prep, 0, false); + + temp = 145 * coeff + 10 * ui - (timing->hs_prepare << 3) * ui; + tmin = S_DIV_ROUND_UP(temp, ui_x8) - 1; + tmax = 255; + timing->hs_zero = linear_inter(tmax, tmin, pcnt_hs_zero, 0, false); + + tmin = DIV_ROUND_UP(60 * coeff + 4 * ui, ui_x8) - 1; + temp = 105 * coeff + 12 * ui - 20 * coeff; + tmax = (temp / ui_x8) - 1; + timing->hs_trail = linear_inter(tmax, tmin, pcnt_hs_trail, 0, false); + + temp = 50 * coeff + ((hb_en << 2) - 8) * ui; + timing->hs_rqst = S_DIV_ROUND_UP(temp, ui_x8); + + tmin = DIV_ROUND_UP(100 * coeff, ui_x8) - 1; + tmax = 255; + timing->hs_exit = linear_inter(tmax, tmin, pcnt_hs_exit, 0, false); + + /* recommended min + * = roundup((mipi_min_ns + t_hs_trail_ns)/(16*bit_clk_ns), 0) - 1 + */ + temp = 60 * coeff + 52 * ui + + (timing->hs_trail + 1) * ui_x8; + tmin = DIV_ROUND_UP(temp, 16 * ui) - 1; + tmax = 255; + timing->shared_timings.clk_post = linear_inter(tmax, tmin, 5, 0, false); + + /* recommended min + * val1 = (tlpx_ns + clk_prepare_ns + clk_zero_ns + hs_rqst_ns) + * val2 = (16 * bit_clk_ns) + * final = roundup(val1/val2, 0) - 1 + */ + temp = 52 * coeff + (timing->clk_prepare + timing->clk_zero + 1) * ui_x8 + 54 * coeff; + tmin = DIV_ROUND_UP(temp, 16 * ui) - 1; + tmax = 255; + timing->shared_timings.clk_pre = DIV_ROUND_UP((tmax - tmin) * 125, 10000) + tmin; + + DBG("%d, %d, %d, %d, %d, %d, %d, %d, %d, %d", + timing->shared_timings.clk_pre, timing->shared_timings.clk_post, + timing->clk_zero, timing->clk_trail, timing->clk_prepare, timing->hs_exit, + timing->hs_zero, timing->hs_prepare, timing->hs_trail, timing->hs_rqst); + + return 0; +} + void msm_dsi_phy_set_src_pll(struct msm_dsi_phy *phy, int pll_id, u32 reg, u32 bit_mask) { @@ -508,6 +604,12 @@ static const struct of_device_id dsi_phy_dt_match[] = { { .compatible = "qcom,dsi-phy-10nm-8998", .data = &dsi_phy_10nm_8998_cfgs }, #endif +#ifdef CONFIG_DRM_MSM_DSI_7NM_PHY + { .compatible = "qcom,dsi-phy-7nm", + .data = &dsi_phy_7nm_cfgs }, + { .compatible = "qcom,dsi-phy-7nm-8150", + .data = &dsi_phy_7nm_8150_cfgs }, +#endif {} }; diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy.h b/drivers/gpu/drm/msm/dsi/phy/dsi_phy.h index ef8672d7b123..d2bd74b6f357 100644 --- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy.h +++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy.h @@ -48,10 +48,10 @@ extern const struct msm_dsi_phy_cfg dsi_phy_14nm_cfgs; extern const struct msm_dsi_phy_cfg dsi_phy_14nm_660_cfgs; extern const struct msm_dsi_phy_cfg dsi_phy_10nm_cfgs; extern const struct msm_dsi_phy_cfg dsi_phy_10nm_8998_cfgs; +extern const struct msm_dsi_phy_cfg dsi_phy_7nm_cfgs; +extern const struct msm_dsi_phy_cfg dsi_phy_7nm_8150_cfgs; struct msm_dsi_dphy_timing { - u32 clk_pre; - u32 clk_post; u32 clk_zero; u32 clk_trail; u32 clk_prepare; @@ -102,6 +102,8 @@ int msm_dsi_dphy_timing_calc_v2(struct msm_dsi_dphy_timing *timing, struct msm_dsi_phy_clk_request *clk_req); int msm_dsi_dphy_timing_calc_v3(struct msm_dsi_dphy_timing *timing, struct msm_dsi_phy_clk_request *clk_req); +int msm_dsi_dphy_timing_calc_v4(struct msm_dsi_dphy_timing *timing, + struct msm_dsi_phy_clk_request *clk_req); void msm_dsi_phy_set_src_pll(struct msm_dsi_phy *phy, int pll_id, u32 reg, u32 bit_mask); int msm_dsi_phy_init_common(struct msm_dsi_phy *phy); diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_7nm.c b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_7nm.c new file mode 100644 index 000000000000..255b5f5ab2ce --- /dev/null +++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_7nm.c @@ -0,0 +1,255 @@ +/* + * SPDX-License-Identifier: GPL-2.0 + * Copyright (c) 2018, The Linux Foundation + */ + +#include <linux/iopoll.h> + +#include "dsi_phy.h" +#include "dsi.xml.h" + +static int dsi_phy_hw_v4_0_is_pll_on(struct msm_dsi_phy *phy) +{ + void __iomem *base = phy->base; + u32 data = 0; + + data = dsi_phy_read(base + REG_DSI_7nm_PHY_CMN_PLL_CNTRL); + mb(); /* make sure read happened */ + + return (data & BIT(0)); +} + +static void dsi_phy_hw_v4_0_config_lpcdrx(struct msm_dsi_phy *phy, bool enable) +{ + void __iomem *lane_base = phy->lane_base; + int phy_lane_0 = 0; /* TODO: Support all lane swap configs */ + + /* + * LPRX and CDRX need to enabled only for physical data lane + * corresponding to the logical data lane 0 + */ + if (enable) + dsi_phy_write(lane_base + + REG_DSI_7nm_PHY_LN_LPRX_CTRL(phy_lane_0), 0x3); + else + dsi_phy_write(lane_base + + REG_DSI_7nm_PHY_LN_LPRX_CTRL(phy_lane_0), 0); +} + +static void dsi_phy_hw_v4_0_lane_settings(struct msm_dsi_phy *phy) +{ + int i; + const u8 tx_dctrl_0[] = { 0x00, 0x00, 0x00, 0x04, 0x01 }; + const u8 tx_dctrl_1[] = { 0x40, 0x40, 0x40, 0x46, 0x41 }; + const u8 *tx_dctrl = tx_dctrl_0; + void __iomem *lane_base = phy->lane_base; + + if (phy->cfg->type == MSM_DSI_PHY_7NM_V4_1) + tx_dctrl = tx_dctrl_1; + + /* Strength ctrl settings */ + for (i = 0; i < 5; i++) { + /* + * Disable LPRX and CDRX for all lanes. And later on, it will + * be only enabled for the physical data lane corresponding + * to the logical data lane 0 + */ + dsi_phy_write(lane_base + REG_DSI_7nm_PHY_LN_LPRX_CTRL(i), 0); + dsi_phy_write(lane_base + REG_DSI_7nm_PHY_LN_PIN_SWAP(i), 0x0); + } + + dsi_phy_hw_v4_0_config_lpcdrx(phy, true); + + /* other settings */ + for (i = 0; i < 5; i++) { + dsi_phy_write(lane_base + REG_DSI_7nm_PHY_LN_CFG0(i), 0x0); + dsi_phy_write(lane_base + REG_DSI_7nm_PHY_LN_CFG1(i), 0x0); + dsi_phy_write(lane_base + REG_DSI_7nm_PHY_LN_CFG2(i), i == 4 ? 0x8a : 0xa); + dsi_phy_write(lane_base + REG_DSI_7nm_PHY_LN_TX_DCTRL(i), tx_dctrl[i]); + } +} + +static int dsi_7nm_phy_enable(struct msm_dsi_phy *phy, int src_pll_id, + struct msm_dsi_phy_clk_request *clk_req) +{ + int ret; + u32 status; + u32 const delay_us = 5; + u32 const timeout_us = 1000; + struct msm_dsi_dphy_timing *timing = &phy->timing; + void __iomem *base = phy->base; + bool less_than_1500_mhz; + u32 vreg_ctrl_0, glbl_str_swi_cal_sel_ctrl, glbl_hstx_str_ctrl_0; + u32 glbl_rescode_top_ctrl, glbl_rescode_bot_ctrl; + u32 data; + + DBG(""); + + if (msm_dsi_dphy_timing_calc_v4(timing, clk_req)) { + DRM_DEV_ERROR(&phy->pdev->dev, + "%s: D-PHY timing calculation failed\n", __func__); + return -EINVAL; + } + + if (dsi_phy_hw_v4_0_is_pll_on(phy)) + pr_warn("PLL turned on before configuring PHY\n"); + + /* wait for REFGEN READY */ + ret = readl_poll_timeout_atomic(base + REG_DSI_7nm_PHY_CMN_PHY_STATUS, + status, (status & BIT(0)), + delay_us, timeout_us); + if (ret) { + pr_err("Ref gen not ready. Aborting\n"); + return -EINVAL; + } + + /* TODO: CPHY enable path (this is for DPHY only) */ + + /* Alter PHY configurations if data rate less than 1.5GHZ*/ + less_than_1500_mhz = (clk_req->bitclk_rate <= 1500000000); + + if (phy->cfg->type == MSM_DSI_PHY_7NM_V4_1) { + vreg_ctrl_0 = less_than_1500_mhz ? 0x53 : 0x52; + glbl_rescode_top_ctrl = less_than_1500_mhz ? 0x3d : 0x00; + glbl_rescode_bot_ctrl = less_than_1500_mhz ? 0x39 : 0x3c; + glbl_str_swi_cal_sel_ctrl = 0x00; + glbl_hstx_str_ctrl_0 = 0x88; + } else { + vreg_ctrl_0 = less_than_1500_mhz ? 0x5B : 0x59; + glbl_str_swi_cal_sel_ctrl = less_than_1500_mhz ? 0x03 : 0x00; + glbl_hstx_str_ctrl_0 = less_than_1500_mhz ? 0x66 : 0x88; + glbl_rescode_top_ctrl = 0x03; + glbl_rescode_bot_ctrl = 0x3c; + } + + /* de-assert digital and pll power down */ + data = BIT(6) | BIT(5); + dsi_phy_write(base + REG_DSI_7nm_PHY_CMN_CTRL_0, data); + + /* Assert PLL core reset */ + dsi_phy_write(base + REG_DSI_7nm_PHY_CMN_PLL_CNTRL, 0x00); + + /* turn off resync FIFO */ + dsi_phy_write(base + REG_DSI_7nm_PHY_CMN_RBUF_CTRL, 0x00); + + /* program CMN_CTRL_4 for minor_ver 2 chipsets*/ + data = dsi_phy_read(base + REG_DSI_7nm_PHY_CMN_REVISION_ID0); + data = data & (0xf0); + if (data == 0x20) + dsi_phy_write(base + REG_DSI_7nm_PHY_CMN_CTRL_4, 0x04); + + /* Configure PHY lane swap (TODO: we need to calculate this) */ + dsi_phy_write(base + REG_DSI_7nm_PHY_CMN_LANE_CFG0, 0x21); + dsi_phy_write(base + REG_DSI_7nm_PHY_CMN_LANE_CFG1, 0x84); + + /* Enable LDO */ + dsi_phy_write(base + REG_DSI_7nm_PHY_CMN_VREG_CTRL_0, vreg_ctrl_0); + dsi_phy_write(base + REG_DSI_7nm_PHY_CMN_VREG_CTRL_1, 0x5c); + dsi_phy_write(base + REG_DSI_7nm_PHY_CMN_CTRL_3, 0x00); + dsi_phy_write(base + REG_DSI_7nm_PHY_CMN_GLBL_STR_SWI_CAL_SEL_CTRL, + glbl_str_swi_cal_sel_ctrl); + dsi_phy_write(base + REG_DSI_7nm_PHY_CMN_GLBL_HSTX_STR_CTRL_0, + glbl_hstx_str_ctrl_0); + dsi_phy_write(base + REG_DSI_7nm_PHY_CMN_GLBL_PEMPH_CTRL_0, 0x00); + dsi_phy_write(base + REG_DSI_7nm_PHY_CMN_GLBL_RESCODE_OFFSET_TOP_CTRL, + glbl_rescode_top_ctrl); + dsi_phy_write(base + REG_DSI_7nm_PHY_CMN_GLBL_RESCODE_OFFSET_BOT_CTRL, + glbl_rescode_bot_ctrl); + dsi_phy_write(base + REG_DSI_7nm_PHY_CMN_GLBL_LPTX_STR_CTRL, 0x55); + + /* Remove power down from all blocks */ + dsi_phy_write(base + REG_DSI_7nm_PHY_CMN_CTRL_0, 0x7f); + + dsi_phy_write(base + REG_DSI_7nm_PHY_CMN_LANE_CTRL0, 0x1f); + + /* Select full-rate mode */ + dsi_phy_write(base + REG_DSI_7nm_PHY_CMN_CTRL_2, 0x40); + + ret = msm_dsi_pll_set_usecase(phy->pll, phy->usecase); + if (ret) { + DRM_DEV_ERROR(&phy->pdev->dev, "%s: set pll usecase failed, %d\n", + __func__, ret); + return ret; + } + + /* DSI PHY timings */ + dsi_phy_write(base + REG_DSI_7nm_PHY_CMN_TIMING_CTRL_0, 0x00); + dsi_phy_write(base + REG_DSI_7nm_PHY_CMN_TIMING_CTRL_1, timing->clk_zero); + dsi_phy_write(base + REG_DSI_7nm_PHY_CMN_TIMING_CTRL_2, timing->clk_prepare); + dsi_phy_write(base + REG_DSI_7nm_PHY_CMN_TIMING_CTRL_3, timing->clk_trail); + dsi_phy_write(base + REG_DSI_7nm_PHY_CMN_TIMING_CTRL_4, timing->hs_exit); + dsi_phy_write(base + REG_DSI_7nm_PHY_CMN_TIMING_CTRL_5, timing->hs_zero); + dsi_phy_write(base + REG_DSI_7nm_PHY_CMN_TIMING_CTRL_6, timing->hs_prepare); + dsi_phy_write(base + REG_DSI_7nm_PHY_CMN_TIMING_CTRL_7, timing->hs_trail); + dsi_phy_write(base + REG_DSI_7nm_PHY_CMN_TIMING_CTRL_8, timing->hs_rqst); + dsi_phy_write(base + REG_DSI_7nm_PHY_CMN_TIMING_CTRL_9, 0x02); + dsi_phy_write(base + REG_DSI_7nm_PHY_CMN_TIMING_CTRL_10, 0x04); + dsi_phy_write(base + REG_DSI_7nm_PHY_CMN_TIMING_CTRL_11, 0x00); + dsi_phy_write(base + REG_DSI_7nm_PHY_CMN_TIMING_CTRL_12, + timing->shared_timings.clk_pre); + dsi_phy_write(base + REG_DSI_7nm_PHY_CMN_TIMING_CTRL_13, + timing->shared_timings.clk_post); + + /* DSI lane settings */ + dsi_phy_hw_v4_0_lane_settings(phy); + + DBG("DSI%d PHY enabled", phy->id); + + return 0; +} + +static void dsi_7nm_phy_disable(struct msm_dsi_phy *phy) +{ + /* TODO */ +} + +static int dsi_7nm_phy_init(struct msm_dsi_phy *phy) +{ + struct platform_device *pdev = phy->pdev; + + phy->lane_base = msm_ioremap(pdev, "dsi_phy_lane", + "DSI_PHY_LANE"); + if (IS_ERR(phy->lane_base)) { + DRM_DEV_ERROR(&pdev->dev, "%s: failed to map phy lane base\n", + __func__); + return -ENOMEM; + } + + return 0; +} + +const struct msm_dsi_phy_cfg dsi_phy_7nm_cfgs = { + .type = MSM_DSI_PHY_7NM_V4_1, + .src_pll_truthtable = { {false, false}, {true, false} }, + .reg_cfg = { + .num = 1, + .regs = { + {"vdds", 36000, 32}, + }, + }, + .ops = { + .enable = dsi_7nm_phy_enable, + .disable = dsi_7nm_phy_disable, + .init = dsi_7nm_phy_init, + }, + .io_start = { 0xae94400, 0xae96400 }, + .num_dsi_phy = 2, +}; + +const struct msm_dsi_phy_cfg dsi_phy_7nm_8150_cfgs = { + .type = MSM_DSI_PHY_7NM, + .src_pll_truthtable = { {false, false}, {true, false} }, + .reg_cfg = { + .num = 1, + .regs = { + {"vdds", 36000, 32}, + }, + }, + .ops = { + .enable = dsi_7nm_phy_enable, + .disable = dsi_7nm_phy_disable, + .init = dsi_7nm_phy_init, + }, + .io_start = { 0xae94400, 0xae96400 }, + .num_dsi_phy = 2, +}; diff --git a/drivers/gpu/drm/msm/dsi/pll/dsi_pll.c b/drivers/gpu/drm/msm/dsi/pll/dsi_pll.c index 4a4aa3c61d71..a45fe95aff49 100644 --- a/drivers/gpu/drm/msm/dsi/pll/dsi_pll.c +++ b/drivers/gpu/drm/msm/dsi/pll/dsi_pll.c @@ -161,6 +161,10 @@ struct msm_dsi_pll *msm_dsi_pll_init(struct platform_device *pdev, case MSM_DSI_PHY_10NM: pll = msm_dsi_pll_10nm_init(pdev, id); break; + case MSM_DSI_PHY_7NM: + case MSM_DSI_PHY_7NM_V4_1: + pll = msm_dsi_pll_7nm_init(pdev, id); + break; default: pll = ERR_PTR(-ENXIO); break; diff --git a/drivers/gpu/drm/msm/dsi/pll/dsi_pll.h b/drivers/gpu/drm/msm/dsi/pll/dsi_pll.h index c6a3623f905d..3405982a092c 100644 --- a/drivers/gpu/drm/msm/dsi/pll/dsi_pll.h +++ b/drivers/gpu/drm/msm/dsi/pll/dsi_pll.h @@ -116,5 +116,15 @@ msm_dsi_pll_10nm_init(struct platform_device *pdev, int id) return ERR_PTR(-ENODEV); } #endif +#ifdef CONFIG_DRM_MSM_DSI_7NM_PHY +struct msm_dsi_pll *msm_dsi_pll_7nm_init(struct platform_device *pdev, int id); +#else +static inline struct msm_dsi_pll * +msm_dsi_pll_7nm_init(struct platform_device *pdev, int id) +{ + return ERR_PTR(-ENODEV); +} +#endif + #endif /* __DSI_PLL_H__ */ diff --git a/drivers/gpu/drm/msm/dsi/pll/dsi_pll_7nm.c b/drivers/gpu/drm/msm/dsi/pll/dsi_pll_7nm.c new file mode 100644 index 000000000000..de0dfb815125 --- /dev/null +++ b/drivers/gpu/drm/msm/dsi/pll/dsi_pll_7nm.c @@ -0,0 +1,904 @@ +/* + * SPDX-License-Identifier: GPL-2.0 + * Copyright (c) 2018, The Linux Foundation + */ + +#include <linux/clk.h> +#include <linux/clk-provider.h> +#include <linux/iopoll.h> + +#include "dsi_pll.h" +#include "dsi.xml.h" + +/* + * DSI PLL 7nm - clock diagram (eg: DSI0): TODO: updated CPHY diagram + * + * dsi0_pll_out_div_clk dsi0_pll_bit_clk + * | | + * | | + * +---------+ | +----------+ | +----+ + * dsi0vco_clk ---| out_div |--o--| divl_3_0 |--o--| /8 |-- dsi0_phy_pll_out_byteclk + * +---------+ | +----------+ | +----+ + * | | + * | | dsi0_pll_by_2_bit_clk + * | | | + * | | +----+ | |\ dsi0_pclk_mux + * | |--| /2 |--o--| \ | + * | | +----+ | \ | +---------+ + * | --------------| |--o--| div_7_4 |-- dsi0_phy_pll_out_dsiclk + * |------------------------------| / +---------+ + * | +-----+ | / + * -----------| /4? |--o----------|/ + * +-----+ | | + * | |dsiclk_sel + * | + * dsi0_pll_post_out_div_clk + */ + +#define DSI_BYTE_PLL_CLK 0 +#define DSI_PIXEL_PLL_CLK 1 +#define NUM_PROVIDED_CLKS 2 + +#define VCO_REF_CLK_RATE 19200000 + +struct dsi_pll_regs { + u32 pll_prop_gain_rate; + u32 pll_lockdet_rate; + u32 decimal_div_start; + u32 frac_div_start_low; + u32 frac_div_start_mid; + u32 frac_div_start_high; + u32 pll_clock_inverters; + u32 ssc_stepsize_low; + u32 ssc_stepsize_high; + u32 ssc_div_per_low; + u32 ssc_div_per_high; + u32 ssc_adjper_low; + u32 ssc_adjper_high; + u32 ssc_control; +}; + +struct dsi_pll_config { + u32 ref_freq; + bool div_override; + u32 output_div; + bool ignore_frac; + bool disable_prescaler; + bool enable_ssc; + bool ssc_center; + u32 dec_bits; + u32 frac_bits; + u32 lock_timer; + u32 ssc_freq; + u32 ssc_offset; + u32 ssc_adj_per; + u32 thresh_cycles; + u32 refclk_cycles; +}; + +struct pll_7nm_cached_state { + unsigned long vco_rate; + u8 bit_clk_div; + u8 pix_clk_div; + u8 pll_out_div; + u8 pll_mux; +}; + +struct dsi_pll_7nm { + struct msm_dsi_pll base; + + int id; + struct platform_device *pdev; + + void __iomem *phy_cmn_mmio; + void __iomem *mmio; + + u64 vco_ref_clk_rate; + u64 vco_current_rate; + + /* protects REG_DSI_7nm_PHY_CMN_CLK_CFG0 register */ + spinlock_t postdiv_lock; + + int vco_delay; + struct dsi_pll_config pll_configuration; + struct dsi_pll_regs reg_setup; + + /* private clocks: */ + struct clk_hw *out_div_clk_hw; + struct clk_hw *bit_clk_hw; + struct clk_hw *byte_clk_hw; + struct clk_hw *by_2_bit_clk_hw; + struct clk_hw *post_out_div_clk_hw; + struct clk_hw *pclk_mux_hw; + struct clk_hw *out_dsiclk_hw; + + /* clock-provider: */ + struct clk_hw_onecell_data *hw_data; + + struct pll_7nm_cached_state cached_state; + + enum msm_dsi_phy_usecase uc; + struct dsi_pll_7nm *slave; +}; + +#define to_pll_7nm(x) container_of(x, struct dsi_pll_7nm, base) + +/* + * Global list of private DSI PLL struct pointers. We need this for Dual DSI + * mode, where the master PLL's clk_ops needs access the slave's private data + */ +static struct dsi_pll_7nm *pll_7nm_list[DSI_MAX]; + +static void dsi_pll_setup_config(struct dsi_pll_7nm *pll) +{ + struct dsi_pll_config *config = &pll->pll_configuration; + + config->ref_freq = pll->vco_ref_clk_rate; + config->output_div = 1; + config->dec_bits = 8; + config->frac_bits = 18; + config->lock_timer = 64; + config->ssc_freq = 31500; + config->ssc_offset = 4800; + config->ssc_adj_per = 2; + config->thresh_cycles = 32; + config->refclk_cycles = 256; + + config->div_override = false; + config->ignore_frac = false; + config->disable_prescaler = false; + + /* TODO: ssc enable */ + config->enable_ssc = false; + config->ssc_center = 0; +} + +static void dsi_pll_calc_dec_frac(struct dsi_pll_7nm *pll) +{ + struct dsi_pll_config *config = &pll->pll_configuration; + struct dsi_pll_regs *regs = &pll->reg_setup; + u64 fref = pll->vco_ref_clk_rate; + u64 pll_freq; + u64 divider; + u64 dec, dec_multiple; + u32 frac; + u64 multiplier; + + pll_freq = pll->vco_current_rate; + + if (config->disable_prescaler) + divider = fref; + else + divider = fref * 2; + + multiplier = 1 << config->frac_bits; + dec_multiple = div_u64(pll_freq * multiplier, divider); + div_u64_rem(dec_multiple, multiplier, &frac); + + dec = div_u64(dec_multiple, multiplier); + + if (pll->base.type != MSM_DSI_PHY_7NM_V4_1) + regs->pll_clock_inverters = 0x28; + else if (pll_freq <= 1000000000ULL) + regs->pll_clock_inverters = 0xa0; + else if (pll_freq <= 2500000000ULL) + regs->pll_clock_inverters = 0x20; + else if (pll_freq <= 3020000000ULL) + regs->pll_clock_inverters = 0x00; + else + regs->pll_clock_inverters = 0x40; + + regs->pll_lockdet_rate = config->lock_timer; + regs->decimal_div_start = dec; + regs->frac_div_start_low = (frac & 0xff); + regs->frac_div_start_mid = (frac & 0xff00) >> 8; + regs->frac_div_start_high = (frac & 0x30000) >> 16; +} + +#define SSC_CENTER BIT(0) +#define SSC_EN BIT(1) + +static void dsi_pll_calc_ssc(struct dsi_pll_7nm *pll) +{ + struct dsi_pll_config *config = &pll->pll_configuration; + struct dsi_pll_regs *regs = &pll->reg_setup; + u32 ssc_per; + u32 ssc_mod; + u64 ssc_step_size; + u64 frac; + + if (!config->enable_ssc) { + DBG("SSC not enabled\n"); + return; + } + + ssc_per = DIV_ROUND_CLOSEST(config->ref_freq, config->ssc_freq) / 2 - 1; + ssc_mod = (ssc_per + 1) % (config->ssc_adj_per + 1); + ssc_per -= ssc_mod; + + frac = regs->frac_div_start_low | + (regs->frac_div_start_mid << 8) | + (regs->frac_div_start_high << 16); + ssc_step_size = regs->decimal_div_start; + ssc_step_size *= (1 << config->frac_bits); + ssc_step_size += frac; + ssc_step_size *= config->ssc_offset; + ssc_step_size *= (config->ssc_adj_per + 1); + ssc_step_size = div_u64(ssc_step_size, (ssc_per + 1)); + ssc_step_size = DIV_ROUND_CLOSEST_ULL(ssc_step_size, 1000000); + + regs->ssc_div_per_low = ssc_per & 0xFF; + regs->ssc_div_per_high = (ssc_per & 0xFF00) >> 8; + regs->ssc_stepsize_low = (u32)(ssc_step_size & 0xFF); + regs->ssc_stepsize_high = (u32)((ssc_step_size & 0xFF00) >> 8); + regs->ssc_adjper_low = config->ssc_adj_per & 0xFF; + regs->ssc_adjper_high = (config->ssc_adj_per & 0xFF00) >> 8; + + regs->ssc_control = config->ssc_center ? SSC_CENTER : 0; + + pr_debug("SCC: Dec:%d, frac:%llu, frac_bits:%d\n", + regs->decimal_div_start, frac, config->frac_bits); + pr_debug("SSC: div_per:0x%X, stepsize:0x%X, adjper:0x%X\n", + ssc_per, (u32)ssc_step_size, config->ssc_adj_per); +} + +static void dsi_pll_ssc_commit(struct dsi_pll_7nm *pll) +{ + void __iomem *base = pll->mmio; + struct dsi_pll_regs *regs = &pll->reg_setup; + + if (pll->pll_configuration.enable_ssc) { + pr_debug("SSC is enabled\n"); + + pll_write(base + REG_DSI_7nm_PHY_PLL_SSC_STEPSIZE_LOW_1, + regs->ssc_stepsize_low); + pll_write(base + REG_DSI_7nm_PHY_PLL_SSC_STEPSIZE_HIGH_1, + regs->ssc_stepsize_high); + pll_write(base + REG_DSI_7nm_PHY_PLL_SSC_DIV_PER_LOW_1, + regs->ssc_div_per_low); + pll_write(base + REG_DSI_7nm_PHY_PLL_SSC_DIV_PER_HIGH_1, + regs->ssc_div_per_high); + pll_write(base + REG_DSI_7nm_PHY_PLL_SSC_ADJPER_LOW_1, + regs->ssc_adjper_low); + pll_write(base + REG_DSI_7nm_PHY_PLL_SSC_ADJPER_HIGH_1, + regs->ssc_adjper_high); + pll_write(base + REG_DSI_7nm_PHY_PLL_SSC_CONTROL, + SSC_EN | regs->ssc_control); + } +} + +static void dsi_pll_config_hzindep_reg(struct dsi_pll_7nm *pll) +{ + void __iomem *base = pll->mmio; + u8 analog_controls_five_1 = 0x01, vco_config_1 = 0x00; + + if (pll->base.type == MSM_DSI_PHY_7NM_V4_1) { + if (pll->vco_current_rate >= 3100000000ULL) + analog_controls_five_1 = 0x03; + + if (pll->vco_current_rate < 1520000000ULL) + vco_config_1 = 0x08; + else if (pll->vco_current_rate < 2990000000ULL) + vco_config_1 = 0x01; + } + + pll_write(base + REG_DSI_7nm_PHY_PLL_ANALOG_CONTROLS_FIVE_1, + analog_controls_five_1); + pll_write(base + REG_DSI_7nm_PHY_PLL_VCO_CONFIG_1, vco_config_1); + pll_write(base + REG_DSI_7nm_PHY_PLL_ANALOG_CONTROLS_FIVE, 0x01); + pll_write(base + REG_DSI_7nm_PHY_PLL_ANALOG_CONTROLS_TWO, 0x03); + pll_write(base + REG_DSI_7nm_PHY_PLL_ANALOG_CONTROLS_THREE, 0x00); + pll_write(base + REG_DSI_7nm_PHY_PLL_DSM_DIVIDER, 0x00); + pll_write(base + REG_DSI_7nm_PHY_PLL_FEEDBACK_DIVIDER, 0x4e); + pll_write(base + REG_DSI_7nm_PHY_PLL_CALIBRATION_SETTINGS, 0x40); + pll_write(base + REG_DSI_7nm_PHY_PLL_BAND_SEL_CAL_SETTINGS_THREE, 0xba); + pll_write(base + REG_DSI_7nm_PHY_PLL_FREQ_DETECT_SETTINGS_ONE, 0x0c); + pll_write(base + REG_DSI_7nm_PHY_PLL_OUTDIV, 0x00); + pll_write(base + REG_DSI_7nm_PHY_PLL_CORE_OVERRIDE, 0x00); + pll_write(base + REG_DSI_7nm_PHY_PLL_PLL_DIGITAL_TIMERS_TWO, 0x08); + pll_write(base + REG_DSI_7nm_PHY_PLL_PLL_PROP_GAIN_RATE_1, 0x0a); + pll_write(base + REG_DSI_7nm_PHY_PLL_PLL_BAND_SEL_RATE_1, 0xc0); + pll_write(base + REG_DSI_7nm_PHY_PLL_PLL_INT_GAIN_IFILT_BAND_1, 0x84); + pll_write(base + REG_DSI_7nm_PHY_PLL_PLL_INT_GAIN_IFILT_BAND_1, 0x82); + pll_write(base + REG_DSI_7nm_PHY_PLL_PLL_FL_INT_GAIN_PFILT_BAND_1, 0x4c); + pll_write(base + REG_DSI_7nm_PHY_PLL_PLL_LOCK_OVERRIDE, 0x80); + pll_write(base + REG_DSI_7nm_PHY_PLL_PFILT, 0x29); + pll_write(base + REG_DSI_7nm_PHY_PLL_PFILT, 0x2f); + pll_write(base + REG_DSI_7nm_PHY_PLL_IFILT, 0x2a); + pll_write(base + REG_DSI_7nm_PHY_PLL_IFILT, + pll->base.type == MSM_DSI_PHY_7NM_V4_1 ? 0x3f : 0x22); + + if (pll->base.type == MSM_DSI_PHY_7NM_V4_1) { + pll_write(base + REG_DSI_7nm_PHY_PLL_PERF_OPTIMIZE, 0x22); + if (pll->slave) + pll_write(pll->slave->mmio + REG_DSI_7nm_PHY_PLL_PERF_OPTIMIZE, 0x22); + } +} + +static void dsi_pll_commit(struct dsi_pll_7nm *pll) +{ + void __iomem *base = pll->mmio; + struct dsi_pll_regs *reg = &pll->reg_setup; + + pll_write(base + REG_DSI_7nm_PHY_PLL_CORE_INPUT_OVERRIDE, 0x12); + pll_write(base + REG_DSI_7nm_PHY_PLL_DECIMAL_DIV_START_1, reg->decimal_div_start); + pll_write(base + REG_DSI_7nm_PHY_PLL_FRAC_DIV_START_LOW_1, reg->frac_div_start_low); + pll_write(base + REG_DSI_7nm_PHY_PLL_FRAC_DIV_START_MID_1, reg->frac_div_start_mid); + pll_write(base + REG_DSI_7nm_PHY_PLL_FRAC_DIV_START_HIGH_1, reg->frac_div_start_high); + pll_write(base + REG_DSI_7nm_PHY_PLL_PLL_LOCKDET_RATE_1, 0x40); + pll_write(base + REG_DSI_7nm_PHY_PLL_PLL_LOCK_DELAY, 0x06); + pll_write(base + REG_DSI_7nm_PHY_PLL_CMODE_1, 0x10); /* TODO: 0x00 for CPHY */ + pll_write(base + REG_DSI_7nm_PHY_PLL_CLOCK_INVERTERS, reg->pll_clock_inverters); +} + +static int dsi_pll_7nm_vco_set_rate(struct clk_hw *hw, unsigned long rate, + unsigned long parent_rate) +{ + struct msm_dsi_pll *pll = hw_clk_to_pll(hw); + struct dsi_pll_7nm *pll_7nm = to_pll_7nm(pll); + + DBG("DSI PLL%d rate=%lu, parent's=%lu", pll_7nm->id, rate, + parent_rate); + + pll_7nm->vco_current_rate = rate; + pll_7nm->vco_ref_clk_rate = VCO_REF_CLK_RATE; + + dsi_pll_setup_config(pll_7nm); + + dsi_pll_calc_dec_frac(pll_7nm); + + dsi_pll_calc_ssc(pll_7nm); + + dsi_pll_commit(pll_7nm); + + dsi_pll_config_hzindep_reg(pll_7nm); + + dsi_pll_ssc_commit(pll_7nm); + + /* flush, ensure all register writes are done*/ + wmb(); + + return 0; +} + +static int dsi_pll_7nm_lock_status(struct dsi_pll_7nm *pll) +{ + int rc; + u32 status = 0; + u32 const delay_us = 100; + u32 const timeout_us = 5000; + + rc = readl_poll_timeout_atomic(pll->mmio + + REG_DSI_7nm_PHY_PLL_COMMON_STATUS_ONE, + status, + ((status & BIT(0)) > 0), + delay_us, + timeout_us); + if (rc) + pr_err("DSI PLL(%d) lock failed, status=0x%08x\n", + pll->id, status); + + return rc; +} + +static void dsi_pll_disable_pll_bias(struct dsi_pll_7nm *pll) +{ + u32 data = pll_read(pll->phy_cmn_mmio + REG_DSI_7nm_PHY_CMN_CTRL_0); + + pll_write(pll->mmio + REG_DSI_7nm_PHY_PLL_SYSTEM_MUXES, 0); + pll_write(pll->phy_cmn_mmio + REG_DSI_7nm_PHY_CMN_CTRL_0, data & ~BIT(5)); + ndelay(250); +} + +static void dsi_pll_enable_pll_bias(struct dsi_pll_7nm *pll) +{ + u32 data = pll_read(pll->phy_cmn_mmio + REG_DSI_7nm_PHY_CMN_CTRL_0); + + pll_write(pll->phy_cmn_mmio + REG_DSI_7nm_PHY_CMN_CTRL_0, data | BIT(5)); + pll_write(pll->mmio + REG_DSI_7nm_PHY_PLL_SYSTEM_MUXES, 0xc0); + ndelay(250); +} + +static void dsi_pll_disable_global_clk(struct dsi_pll_7nm *pll) +{ + u32 data; + + data = pll_read(pll->phy_cmn_mmio + REG_DSI_7nm_PHY_CMN_CLK_CFG1); + pll_write(pll->phy_cmn_mmio + REG_DSI_7nm_PHY_CMN_CLK_CFG1, data & ~BIT(5)); +} + +static void dsi_pll_enable_global_clk(struct dsi_pll_7nm *pll) +{ + u32 data; + + pll_write(pll->phy_cmn_mmio + REG_DSI_7nm_PHY_CMN_CTRL_3, 0x04); + + data = pll_read(pll->phy_cmn_mmio + REG_DSI_7nm_PHY_CMN_CLK_CFG1); + pll_write(pll->phy_cmn_mmio + REG_DSI_7nm_PHY_CMN_CLK_CFG1, + data | BIT(5) | BIT(4)); +} + +static void dsi_pll_phy_dig_reset(struct dsi_pll_7nm *pll) +{ + /* + * Reset the PHY digital domain. This would be needed when + * coming out of a CX or analog rail power collapse while + * ensuring that the pads maintain LP00 or LP11 state + */ + pll_write(pll->phy_cmn_mmio + REG_DSI_7nm_PHY_CMN_GLBL_DIGTOP_SPARE4, BIT(0)); + wmb(); /* Ensure that the reset is deasserted */ + pll_write(pll->phy_cmn_mmio + REG_DSI_7nm_PHY_CMN_GLBL_DIGTOP_SPARE4, 0x0); + wmb(); /* Ensure that the reset is deasserted */ +} + +static int dsi_pll_7nm_vco_prepare(struct clk_hw *hw) +{ + struct msm_dsi_pll *pll = hw_clk_to_pll(hw); + struct dsi_pll_7nm *pll_7nm = to_pll_7nm(pll); + int rc; + + dsi_pll_enable_pll_bias(pll_7nm); + if (pll_7nm->slave) + dsi_pll_enable_pll_bias(pll_7nm->slave); + + /* Start PLL */ + pll_write(pll_7nm->phy_cmn_mmio + REG_DSI_7nm_PHY_CMN_PLL_CNTRL, 0x01); + + /* + * ensure all PLL configurations are written prior to checking + * for PLL lock. + */ + wmb(); + + /* Check for PLL lock */ + rc = dsi_pll_7nm_lock_status(pll_7nm); + if (rc) { + pr_err("PLL(%d) lock failed\n", pll_7nm->id); + goto error; + } + + pll->pll_on = true; + + /* + * assert power on reset for PHY digital in case the PLL is + * enabled after CX of analog domain power collapse. This needs + * to be done before enabling the global clk. + */ + dsi_pll_phy_dig_reset(pll_7nm); + if (pll_7nm->slave) + dsi_pll_phy_dig_reset(pll_7nm->slave); + + dsi_pll_enable_global_clk(pll_7nm); + if (pll_7nm->slave) + dsi_pll_enable_global_clk(pll_7nm->slave); + +error: + return rc; +} + +static void dsi_pll_disable_sub(struct dsi_pll_7nm *pll) +{ + pll_write(pll->phy_cmn_mmio + REG_DSI_7nm_PHY_CMN_RBUF_CTRL, 0); + dsi_pll_disable_pll_bias(pll); +} + +static void dsi_pll_7nm_vco_unprepare(struct clk_hw *hw) +{ + struct msm_dsi_pll *pll = hw_clk_to_pll(hw); + struct dsi_pll_7nm *pll_7nm = to_pll_7nm(pll); + + /* + * To avoid any stray glitches while abruptly powering down the PLL + * make sure to gate the clock using the clock enable bit before + * powering down the PLL + */ + dsi_pll_disable_global_clk(pll_7nm); + pll_write(pll_7nm->phy_cmn_mmio + REG_DSI_7nm_PHY_CMN_PLL_CNTRL, 0); + dsi_pll_disable_sub(pll_7nm); + if (pll_7nm->slave) { + dsi_pll_disable_global_clk(pll_7nm->slave); + dsi_pll_disable_sub(pll_7nm->slave); + } + /* flush, ensure all register writes are done */ + wmb(); + pll->pll_on = false; +} + +static unsigned long dsi_pll_7nm_vco_recalc_rate(struct clk_hw *hw, + unsigned long parent_rate) +{ + struct msm_dsi_pll *pll = hw_clk_to_pll(hw); + struct dsi_pll_7nm *pll_7nm = to_pll_7nm(pll); + void __iomem *base = pll_7nm->mmio; + u64 ref_clk = pll_7nm->vco_ref_clk_rate; + u64 vco_rate = 0x0; + u64 multiplier; + u32 frac; + u32 dec; + u64 pll_freq, tmp64; + + dec = pll_read(base + REG_DSI_7nm_PHY_PLL_DECIMAL_DIV_START_1); + dec &= 0xff; + + frac = pll_read(base + REG_DSI_7nm_PHY_PLL_FRAC_DIV_START_LOW_1); + frac |= ((pll_read(base + REG_DSI_7nm_PHY_PLL_FRAC_DIV_START_MID_1) & + 0xff) << 8); + frac |= ((pll_read(base + REG_DSI_7nm_PHY_PLL_FRAC_DIV_START_HIGH_1) & + 0x3) << 16); + + /* + * TODO: + * 1. Assumes prescaler is disabled + * 2. Multiplier is 2^18. it should be 2^(num_of_frac_bits) + */ + multiplier = 1 << 18; + pll_freq = dec * (ref_clk * 2); + tmp64 = (ref_clk * 2 * frac); + pll_freq += div_u64(tmp64, multiplier); + + vco_rate = pll_freq; + + DBG("DSI PLL%d returning vco rate = %lu, dec = %x, frac = %x", + pll_7nm->id, (unsigned long)vco_rate, dec, frac); + + return (unsigned long)vco_rate; +} + +static const struct clk_ops clk_ops_dsi_pll_7nm_vco = { + .round_rate = msm_dsi_pll_helper_clk_round_rate, + .set_rate = dsi_pll_7nm_vco_set_rate, + .recalc_rate = dsi_pll_7nm_vco_recalc_rate, + .prepare = dsi_pll_7nm_vco_prepare, + .unprepare = dsi_pll_7nm_vco_unprepare, +}; + +/* + * PLL Callbacks + */ + +static void dsi_pll_7nm_save_state(struct msm_dsi_pll *pll) +{ + struct dsi_pll_7nm *pll_7nm = to_pll_7nm(pll); + struct pll_7nm_cached_state *cached = &pll_7nm->cached_state; + void __iomem *phy_base = pll_7nm->phy_cmn_mmio; + u32 cmn_clk_cfg0, cmn_clk_cfg1; + + cached->pll_out_div = pll_read(pll_7nm->mmio + + REG_DSI_7nm_PHY_PLL_PLL_OUTDIV_RATE); + cached->pll_out_div &= 0x3; + + cmn_clk_cfg0 = pll_read(phy_base + REG_DSI_7nm_PHY_CMN_CLK_CFG0); + cached->bit_clk_div = cmn_clk_cfg0 & 0xf; + cached->pix_clk_div = (cmn_clk_cfg0 & 0xf0) >> 4; + + cmn_clk_cfg1 = pll_read(phy_base + REG_DSI_7nm_PHY_CMN_CLK_CFG1); + cached->pll_mux = cmn_clk_cfg1 & 0x3; + + DBG("DSI PLL%d outdiv %x bit_clk_div %x pix_clk_div %x pll_mux %x", + pll_7nm->id, cached->pll_out_div, cached->bit_clk_div, + cached->pix_clk_div, cached->pll_mux); +} + +static int dsi_pll_7nm_restore_state(struct msm_dsi_pll *pll) +{ + struct dsi_pll_7nm *pll_7nm = to_pll_7nm(pll); + struct pll_7nm_cached_state *cached = &pll_7nm->cached_state; + void __iomem *phy_base = pll_7nm->phy_cmn_mmio; + u32 val; + + val = pll_read(pll_7nm->mmio + REG_DSI_7nm_PHY_PLL_PLL_OUTDIV_RATE); + val &= ~0x3; + val |= cached->pll_out_div; + pll_write(pll_7nm->mmio + REG_DSI_7nm_PHY_PLL_PLL_OUTDIV_RATE, val); + + pll_write(phy_base + REG_DSI_7nm_PHY_CMN_CLK_CFG0, + cached->bit_clk_div | (cached->pix_clk_div << 4)); + + val = pll_read(phy_base + REG_DSI_7nm_PHY_CMN_CLK_CFG1); + val &= ~0x3; + val |= cached->pll_mux; + pll_write(phy_base + REG_DSI_7nm_PHY_CMN_CLK_CFG1, val); + + DBG("DSI PLL%d", pll_7nm->id); + + return 0; +} + +static int dsi_pll_7nm_set_usecase(struct msm_dsi_pll *pll, + enum msm_dsi_phy_usecase uc) +{ + struct dsi_pll_7nm *pll_7nm = to_pll_7nm(pll); + void __iomem *base = pll_7nm->phy_cmn_mmio; + u32 data = 0x0; /* internal PLL */ + + DBG("DSI PLL%d", pll_7nm->id); + + switch (uc) { + case MSM_DSI_PHY_STANDALONE: + break; + case MSM_DSI_PHY_MASTER: + pll_7nm->slave = pll_7nm_list[(pll_7nm->id + 1) % DSI_MAX]; + break; + case MSM_DSI_PHY_SLAVE: + data = 0x1; /* external PLL */ + break; + default: + return -EINVAL; + } + + /* set PLL src */ + pll_write(base + REG_DSI_7nm_PHY_CMN_CLK_CFG1, (data << 2)); + + pll_7nm->uc = uc; + + return 0; +} + +static int dsi_pll_7nm_get_provider(struct msm_dsi_pll *pll, + struct clk **byte_clk_provider, + struct clk **pixel_clk_provider) +{ + struct dsi_pll_7nm *pll_7nm = to_pll_7nm(pll); + struct clk_hw_onecell_data *hw_data = pll_7nm->hw_data; + + DBG("DSI PLL%d", pll_7nm->id); + + if (byte_clk_provider) + *byte_clk_provider = hw_data->hws[DSI_BYTE_PLL_CLK]->clk; + if (pixel_clk_provider) + *pixel_clk_provider = hw_data->hws[DSI_PIXEL_PLL_CLK]->clk; + + return 0; +} + +static void dsi_pll_7nm_destroy(struct msm_dsi_pll *pll) +{ + struct dsi_pll_7nm *pll_7nm = to_pll_7nm(pll); + struct device *dev = &pll_7nm->pdev->dev; + + DBG("DSI PLL%d", pll_7nm->id); + of_clk_del_provider(dev->of_node); + + clk_hw_unregister_divider(pll_7nm->out_dsiclk_hw); + clk_hw_unregister_mux(pll_7nm->pclk_mux_hw); + clk_hw_unregister_fixed_factor(pll_7nm->post_out_div_clk_hw); + clk_hw_unregister_fixed_factor(pll_7nm->by_2_bit_clk_hw); + clk_hw_unregister_fixed_factor(pll_7nm->byte_clk_hw); + clk_hw_unregister_divider(pll_7nm->bit_clk_hw); + clk_hw_unregister_divider(pll_7nm->out_div_clk_hw); + clk_hw_unregister(&pll_7nm->base.clk_hw); +} + +/* + * The post dividers and mux clocks are created using the standard divider and + * mux API. Unlike the 14nm PHY, the slave PLL doesn't need its dividers/mux + * state to follow the master PLL's divider/mux state. Therefore, we don't + * require special clock ops that also configure the slave PLL registers + */ +static int pll_7nm_register(struct dsi_pll_7nm *pll_7nm) +{ + char clk_name[32], parent[32], vco_name[32]; + char parent2[32], parent3[32], parent4[32]; + struct clk_init_data vco_init = { + .parent_names = (const char *[]){ "bi_tcxo" }, + .num_parents = 1, + .name = vco_name, + .flags = CLK_IGNORE_UNUSED, + .ops = &clk_ops_dsi_pll_7nm_vco, + }; + struct device *dev = &pll_7nm->pdev->dev; + struct clk_hw_onecell_data *hw_data; + struct clk_hw *hw; + int ret; + + DBG("DSI%d", pll_7nm->id); + + hw_data = devm_kzalloc(dev, sizeof(*hw_data) + + NUM_PROVIDED_CLKS * sizeof(struct clk_hw *), + GFP_KERNEL); + if (!hw_data) + return -ENOMEM; + + snprintf(vco_name, 32, "dsi%dvco_clk", pll_7nm->id); + pll_7nm->base.clk_hw.init = &vco_init; + + ret = clk_hw_register(dev, &pll_7nm->base.clk_hw); + if (ret) + return ret; + + snprintf(clk_name, 32, "dsi%d_pll_out_div_clk", pll_7nm->id); + snprintf(parent, 32, "dsi%dvco_clk", pll_7nm->id); + + hw = clk_hw_register_divider(dev, clk_name, + parent, CLK_SET_RATE_PARENT, + pll_7nm->mmio + + REG_DSI_7nm_PHY_PLL_PLL_OUTDIV_RATE, + 0, 2, CLK_DIVIDER_POWER_OF_TWO, NULL); + if (IS_ERR(hw)) { + ret = PTR_ERR(hw); + goto err_base_clk_hw; + } + + pll_7nm->out_div_clk_hw = hw; + + snprintf(clk_name, 32, "dsi%d_pll_bit_clk", pll_7nm->id); + snprintf(parent, 32, "dsi%d_pll_out_div_clk", pll_7nm->id); + + /* BIT CLK: DIV_CTRL_3_0 */ + hw = clk_hw_register_divider(dev, clk_name, parent, + CLK_SET_RATE_PARENT, + pll_7nm->phy_cmn_mmio + + REG_DSI_7nm_PHY_CMN_CLK_CFG0, + 0, 4, CLK_DIVIDER_ONE_BASED, + &pll_7nm->postdiv_lock); + if (IS_ERR(hw)) { + ret = PTR_ERR(hw); + goto err_out_div_clk_hw; + } + + pll_7nm->bit_clk_hw = hw; + + snprintf(clk_name, 32, "dsi%d_phy_pll_out_byteclk", pll_7nm->id); + snprintf(parent, 32, "dsi%d_pll_bit_clk", pll_7nm->id); + + /* DSI Byte clock = VCO_CLK / OUT_DIV / BIT_DIV / 8 */ + hw = clk_hw_register_fixed_factor(dev, clk_name, parent, + CLK_SET_RATE_PARENT, 1, 8); + if (IS_ERR(hw)) { + ret = PTR_ERR(hw); + goto err_bit_clk_hw; + } + + pll_7nm->byte_clk_hw = hw; + hw_data->hws[DSI_BYTE_PLL_CLK] = hw; + + snprintf(clk_name, 32, "dsi%d_pll_by_2_bit_clk", pll_7nm->id); + snprintf(parent, 32, "dsi%d_pll_bit_clk", pll_7nm->id); + + hw = clk_hw_register_fixed_factor(dev, clk_name, parent, + 0, 1, 2); + if (IS_ERR(hw)) { + ret = PTR_ERR(hw); + goto err_byte_clk_hw; + } + + pll_7nm->by_2_bit_clk_hw = hw; + + snprintf(clk_name, 32, "dsi%d_pll_post_out_div_clk", pll_7nm->id); + snprintf(parent, 32, "dsi%d_pll_out_div_clk", pll_7nm->id); + + hw = clk_hw_register_fixed_factor(dev, clk_name, parent, + 0, 1, 4); + if (IS_ERR(hw)) { + ret = PTR_ERR(hw); + goto err_by_2_bit_clk_hw; + } + + pll_7nm->post_out_div_clk_hw = hw; + + snprintf(clk_name, 32, "dsi%d_pclk_mux", pll_7nm->id); + snprintf(parent, 32, "dsi%d_pll_bit_clk", pll_7nm->id); + snprintf(parent2, 32, "dsi%d_pll_by_2_bit_clk", pll_7nm->id); + snprintf(parent3, 32, "dsi%d_pll_out_div_clk", pll_7nm->id); + snprintf(parent4, 32, "dsi%d_pll_post_out_div_clk", pll_7nm->id); + + hw = clk_hw_register_mux(dev, clk_name, + ((const char *[]){ + parent, parent2, parent3, parent4 + }), 4, 0, pll_7nm->phy_cmn_mmio + + REG_DSI_7nm_PHY_CMN_CLK_CFG1, + 0, 2, 0, NULL); + if (IS_ERR(hw)) { + ret = PTR_ERR(hw); + goto err_post_out_div_clk_hw; + } + + pll_7nm->pclk_mux_hw = hw; + + snprintf(clk_name, 32, "dsi%d_phy_pll_out_dsiclk", pll_7nm->id); + snprintf(parent, 32, "dsi%d_pclk_mux", pll_7nm->id); + + /* PIX CLK DIV : DIV_CTRL_7_4*/ + hw = clk_hw_register_divider(dev, clk_name, parent, + 0, pll_7nm->phy_cmn_mmio + + REG_DSI_7nm_PHY_CMN_CLK_CFG0, + 4, 4, CLK_DIVIDER_ONE_BASED, + &pll_7nm->postdiv_lock); + if (IS_ERR(hw)) { + ret = PTR_ERR(hw); + goto err_pclk_mux_hw; + } + + pll_7nm->out_dsiclk_hw = hw; + hw_data->hws[DSI_PIXEL_PLL_CLK] = hw; + + hw_data->num = NUM_PROVIDED_CLKS; + pll_7nm->hw_data = hw_data; + + ret = of_clk_add_hw_provider(dev->of_node, of_clk_hw_onecell_get, + pll_7nm->hw_data); + if (ret) { + DRM_DEV_ERROR(dev, "failed to register clk provider: %d\n", ret); + goto err_dsiclk_hw; + } + + return 0; + +err_dsiclk_hw: + clk_hw_unregister_divider(pll_7nm->out_dsiclk_hw); +err_pclk_mux_hw: + clk_hw_unregister_mux(pll_7nm->pclk_mux_hw); +err_post_out_div_clk_hw: + clk_hw_unregister_fixed_factor(pll_7nm->post_out_div_clk_hw); +err_by_2_bit_clk_hw: + clk_hw_unregister_fixed_factor(pll_7nm->by_2_bit_clk_hw); +err_byte_clk_hw: + clk_hw_unregister_fixed_factor(pll_7nm->byte_clk_hw); +err_bit_clk_hw: + clk_hw_unregister_divider(pll_7nm->bit_clk_hw); +err_out_div_clk_hw: + clk_hw_unregister_divider(pll_7nm->out_div_clk_hw); +err_base_clk_hw: + clk_hw_unregister(&pll_7nm->base.clk_hw); + + return ret; +} + +struct msm_dsi_pll *msm_dsi_pll_7nm_init(struct platform_device *pdev, int id) +{ + struct dsi_pll_7nm *pll_7nm; + struct msm_dsi_pll *pll; + int ret; + + pll_7nm = devm_kzalloc(&pdev->dev, sizeof(*pll_7nm), GFP_KERNEL); + if (!pll_7nm) + return ERR_PTR(-ENOMEM); + + DBG("DSI PLL%d", id); + + pll_7nm->pdev = pdev; + pll_7nm->id = id; + pll_7nm_list[id] = pll_7nm; + + pll_7nm->phy_cmn_mmio = msm_ioremap(pdev, "dsi_phy", "DSI_PHY"); + if (IS_ERR_OR_NULL(pll_7nm->phy_cmn_mmio)) { + DRM_DEV_ERROR(&pdev->dev, "failed to map CMN PHY base\n"); + return ERR_PTR(-ENOMEM); + } + + pll_7nm->mmio = msm_ioremap(pdev, "dsi_pll", "DSI_PLL"); + if (IS_ERR_OR_NULL(pll_7nm->mmio)) { + DRM_DEV_ERROR(&pdev->dev, "failed to map PLL base\n"); + return ERR_PTR(-ENOMEM); + } + + spin_lock_init(&pll_7nm->postdiv_lock); + + pll = &pll_7nm->base; + pll->min_rate = 1000000000UL; + pll->max_rate = 3500000000UL; + if (pll->type == MSM_DSI_PHY_7NM_V4_1) { + pll->min_rate = 600000000UL; + pll->max_rate = (unsigned long)5000000000ULL; + /* workaround for max rate overflowing on 32-bit builds: */ + pll->max_rate = max(pll->max_rate, 0xffffffffUL); + } + pll->get_provider = dsi_pll_7nm_get_provider; + pll->destroy = dsi_pll_7nm_destroy; + pll->save_state = dsi_pll_7nm_save_state; + pll->restore_state = dsi_pll_7nm_restore_state; + pll->set_usecase = dsi_pll_7nm_set_usecase; + + pll_7nm->vco_delay = 1; + + ret = pll_7nm_register(pll_7nm); + if (ret) { + DRM_DEV_ERROR(&pdev->dev, "failed to register PLL: %d\n", ret); + return ERR_PTR(ret); + } + + /* TODO: Remove this when we have proper display handover support */ + msm_dsi_pll_save_state(pll); + + return pll; +} diff --git a/drivers/gpu/drm/msm/msm_drv.c b/drivers/gpu/drm/msm/msm_drv.c index 5952767ea478..aa4509766d64 100644 --- a/drivers/gpu/drm/msm/msm_drv.c +++ b/drivers/gpu/drm/msm/msm_drv.c @@ -453,15 +453,7 @@ static int msm_drm_init(struct device *dev, struct drm_driver *drv) if (ret) goto err_msm_uninit; - if (!dev->dma_parms) { - dev->dma_parms = devm_kzalloc(dev, sizeof(*dev->dma_parms), - GFP_KERNEL); - if (!dev->dma_parms) { - ret = -ENOMEM; - goto err_msm_uninit; - } - } - dma_set_max_seg_size(dev, DMA_BIT_MASK(32)); + dma_set_max_seg_size(dev, UINT_MAX); msm_gem_shrinker_init(ddev); @@ -594,9 +586,10 @@ static int context_init(struct drm_device *dev, struct drm_file *file) if (!ctx) return -ENOMEM; + kref_init(&ctx->ref); msm_submitqueue_init(dev, ctx); - ctx->aspace = priv->gpu ? priv->gpu->aspace : NULL; + ctx->aspace = msm_gpu_create_private_address_space(priv->gpu, current); file->driver_priv = ctx; return 0; @@ -615,7 +608,7 @@ static int msm_open(struct drm_device *dev, struct drm_file *file) static void context_close(struct msm_file_private *ctx) { msm_submitqueue_close(ctx); - kfree(ctx); + msm_file_private_put(ctx); } static void msm_postclose(struct drm_device *dev, struct drm_file *file) @@ -779,18 +772,19 @@ static int msm_ioctl_gem_cpu_fini(struct drm_device *dev, void *data, } static int msm_ioctl_gem_info_iova(struct drm_device *dev, - struct drm_gem_object *obj, uint64_t *iova) + struct drm_file *file, struct drm_gem_object *obj, + uint64_t *iova) { - struct msm_drm_private *priv = dev->dev_private; + struct msm_file_private *ctx = file->driver_priv; - if (!priv->gpu) + if (!ctx->aspace) return -EINVAL; /* * Don't pin the memory here - just get an address so that userspace can * be productive */ - return msm_gem_get_iova(obj, priv->gpu->aspace, iova); + return msm_gem_get_iova(obj, ctx->aspace, iova); } static int msm_ioctl_gem_info(struct drm_device *dev, void *data, @@ -829,7 +823,7 @@ static int msm_ioctl_gem_info(struct drm_device *dev, void *data, args->value = msm_gem_mmap_offset(obj); break; case MSM_INFO_GET_IOVA: - ret = msm_ioctl_gem_info_iova(dev, obj, &args->value); + ret = msm_ioctl_gem_info_iova(dev, file, obj, &args->value); break; case MSM_INFO_SET_NAME: /* length check should leave room for terminating null: */ @@ -1345,6 +1339,7 @@ static int __init msm_drm_register(void) msm_dsi_register(); msm_edp_register(); msm_hdmi_register(); + msm_dp_register(); adreno_register(); return platform_driver_register(&msm_platform_driver); } @@ -1353,6 +1348,7 @@ static void __exit msm_drm_unregister(void) { DBG("fini"); platform_driver_unregister(&msm_platform_driver); + msm_dp_unregister(); msm_hdmi_unregister(); adreno_unregister(); msm_edp_unregister(); diff --git a/drivers/gpu/drm/msm/msm_drv.h b/drivers/gpu/drm/msm/msm_drv.h index 7bcea10be81f..c45789f36e48 100644 --- a/drivers/gpu/drm/msm/msm_drv.h +++ b/drivers/gpu/drm/msm/msm_drv.h @@ -57,6 +57,7 @@ struct msm_file_private { struct list_head submitqueues; int queueid; struct msm_gem_address_space *aspace; + struct kref ref; }; enum msm_mdp_plane_property { @@ -159,6 +160,8 @@ struct msm_drm_private { /* DSI is shared by mdp4 and mdp5 */ struct msm_dsi *dsi[2]; + struct msm_dp *dp; + /* when we have more than one 'msm_gpu' these need to be an array: */ struct msm_gpu *gpu; struct msm_file_private *lastctx; @@ -248,6 +251,10 @@ int msm_gem_map_vma(struct msm_gem_address_space *aspace, void msm_gem_close_vma(struct msm_gem_address_space *aspace, struct msm_gem_vma *vma); + +struct msm_gem_address_space * +msm_gem_address_space_get(struct msm_gem_address_space *aspace); + void msm_gem_address_space_put(struct msm_gem_address_space *aspace); struct msm_gem_address_space * @@ -301,9 +308,8 @@ void msm_gem_put_vaddr(struct drm_gem_object *obj); int msm_gem_madvise(struct drm_gem_object *obj, unsigned madv); int msm_gem_sync_object(struct drm_gem_object *obj, struct msm_fence_context *fctx, bool exclusive); -void msm_gem_move_to_active(struct drm_gem_object *obj, - struct msm_gpu *gpu, bool exclusive, struct dma_fence *fence); -void msm_gem_move_to_inactive(struct drm_gem_object *obj); +void msm_gem_active_get(struct drm_gem_object *obj, struct msm_gpu *gpu); +void msm_gem_active_put(struct drm_gem_object *obj); int msm_gem_cpu_prep(struct drm_gem_object *obj, uint32_t op, ktime_t *timeout); int msm_gem_cpu_fini(struct drm_gem_object *obj); void msm_gem_free_object(struct drm_gem_object *obj); @@ -377,6 +383,63 @@ static inline int msm_dsi_modeset_init(struct msm_dsi *msm_dsi, } #endif +#ifdef CONFIG_DRM_MSM_DP +int __init msm_dp_register(void); +void __exit msm_dp_unregister(void); +int msm_dp_modeset_init(struct msm_dp *dp_display, struct drm_device *dev, + struct drm_encoder *encoder); +int msm_dp_display_enable(struct msm_dp *dp, struct drm_encoder *encoder); +int msm_dp_display_disable(struct msm_dp *dp, struct drm_encoder *encoder); +int msm_dp_display_pre_disable(struct msm_dp *dp, struct drm_encoder *encoder); +void msm_dp_display_mode_set(struct msm_dp *dp, struct drm_encoder *encoder, + struct drm_display_mode *mode, + struct drm_display_mode *adjusted_mode); +void msm_dp_irq_postinstall(struct msm_dp *dp_display); + +void msm_dp_debugfs_init(struct msm_dp *dp_display, struct drm_minor *minor); + +#else +static inline int __init msm_dp_register(void) +{ + return -EINVAL; +} +static inline void __exit msm_dp_unregister(void) +{ +} +static inline int msm_dp_modeset_init(struct msm_dp *dp_display, + struct drm_device *dev, + struct drm_encoder *encoder) +{ + return -EINVAL; +} +static inline int msm_dp_display_enable(struct msm_dp *dp, + struct drm_encoder *encoder) +{ + return -EINVAL; +} +static inline int msm_dp_display_disable(struct msm_dp *dp, + struct drm_encoder *encoder) +{ + return -EINVAL; +} +static inline void msm_dp_display_mode_set(struct msm_dp *dp, + struct drm_encoder *encoder, + struct drm_display_mode *mode, + struct drm_display_mode *adjusted_mode) +{ +} + +static inline void msm_dp_irq_postinstall(struct msm_dp *dp_display) +{ +} + +static inline void msm_dp_debugfs_init(struct msm_dp *dp_display, + struct drm_minor *minor) +{ +} + +#endif + void __init msm_mdp_register(void); void __exit msm_mdp_unregister(void); void __init msm_dpu_register(void); @@ -397,8 +460,9 @@ void msm_perf_debugfs_cleanup(struct msm_drm_private *priv); #else static inline int msm_debugfs_late_init(struct drm_device *dev) { return 0; } __printf(3, 4) -static inline void msm_rd_dump_submit(struct msm_rd_state *rd, struct msm_gem_submit *submit, - const char *fmt, ...) {} +static inline void msm_rd_dump_submit(struct msm_rd_state *rd, + struct msm_gem_submit *submit, + const char *fmt, ...) {} static inline void msm_rd_debugfs_cleanup(struct msm_drm_private *priv) {} static inline void msm_perf_debugfs_cleanup(struct msm_drm_private *priv) {} #endif @@ -418,7 +482,8 @@ struct msm_gpu_submitqueue; int msm_submitqueue_init(struct drm_device *drm, struct msm_file_private *ctx); struct msm_gpu_submitqueue *msm_submitqueue_get(struct msm_file_private *ctx, u32 id); -int msm_submitqueue_create(struct drm_device *drm, struct msm_file_private *ctx, +int msm_submitqueue_create(struct drm_device *drm, + struct msm_file_private *ctx, u32 prio, u32 flags, u32 *id); int msm_submitqueue_query(struct drm_device *drm, struct msm_file_private *ctx, struct drm_msm_submitqueue_query *args); @@ -427,6 +492,26 @@ void msm_submitqueue_close(struct msm_file_private *ctx); void msm_submitqueue_destroy(struct kref *kref); +static inline void __msm_file_private_destroy(struct kref *kref) +{ + struct msm_file_private *ctx = container_of(kref, + struct msm_file_private, ref); + + msm_gem_address_space_put(ctx->aspace); + kfree(ctx); +} + +static inline void msm_file_private_put(struct msm_file_private *ctx) +{ + kref_put(&ctx->ref, __msm_file_private_destroy); +} + +static inline struct msm_file_private *msm_file_private_get( + struct msm_file_private *ctx) +{ + kref_get(&ctx->ref); + return ctx; +} #define DBG(fmt, ...) DRM_DEBUG_DRIVER(fmt"\n", ##__VA_ARGS__) #define VERB(fmt, ...) if (0) DRM_DEBUG_DRIVER(fmt"\n", ##__VA_ARGS__) diff --git a/drivers/gpu/drm/msm/msm_gem.c b/drivers/gpu/drm/msm/msm_gem.c index de915ff6f4b4..2e1bce7c0b19 100644 --- a/drivers/gpu/drm/msm/msm_gem.c +++ b/drivers/gpu/drm/msm/msm_gem.c @@ -4,6 +4,7 @@ * Author: Rob Clark <robdclark@gmail.com> */ +#include <linux/dma-map-ops.h> #include <linux/spinlock.h> #include <linux/shmem_fs.h> #include <linux/dma-buf.h> @@ -52,26 +53,14 @@ static void sync_for_device(struct msm_gem_object *msm_obj) { struct device *dev = msm_obj->base.dev->dev; - if (get_dma_ops(dev) && IS_ENABLED(CONFIG_ARM64)) { - dma_sync_sg_for_device(dev, msm_obj->sgt->sgl, - msm_obj->sgt->nents, DMA_BIDIRECTIONAL); - } else { - dma_map_sg(dev, msm_obj->sgt->sgl, - msm_obj->sgt->nents, DMA_BIDIRECTIONAL); - } + dma_map_sgtable(dev, msm_obj->sgt, DMA_BIDIRECTIONAL, 0); } static void sync_for_cpu(struct msm_gem_object *msm_obj) { struct device *dev = msm_obj->base.dev->dev; - if (get_dma_ops(dev) && IS_ENABLED(CONFIG_ARM64)) { - dma_sync_sg_for_cpu(dev, msm_obj->sgt->sgl, - msm_obj->sgt->nents, DMA_BIDIRECTIONAL); - } else { - dma_unmap_sg(dev, msm_obj->sgt->sgl, - msm_obj->sgt->nents, DMA_BIDIRECTIONAL); - } + dma_unmap_sgtable(dev, msm_obj->sgt, DMA_BIDIRECTIONAL, 0); } /* allocate pages from VRAM carveout, used when no IOMMU: */ @@ -753,31 +742,31 @@ int msm_gem_sync_object(struct drm_gem_object *obj, return 0; } -void msm_gem_move_to_active(struct drm_gem_object *obj, - struct msm_gpu *gpu, bool exclusive, struct dma_fence *fence) +void msm_gem_active_get(struct drm_gem_object *obj, struct msm_gpu *gpu) { struct msm_gem_object *msm_obj = to_msm_bo(obj); + WARN_ON(!mutex_is_locked(&obj->dev->struct_mutex)); WARN_ON(msm_obj->madv != MSM_MADV_WILLNEED); - msm_obj->gpu = gpu; - if (exclusive) - dma_resv_add_excl_fence(obj->resv, fence); - else - dma_resv_add_shared_fence(obj->resv, fence); - list_del_init(&msm_obj->mm_list); - list_add_tail(&msm_obj->mm_list, &gpu->active_list); + + if (!atomic_fetch_inc(&msm_obj->active_count)) { + msm_obj->gpu = gpu; + list_del_init(&msm_obj->mm_list); + list_add_tail(&msm_obj->mm_list, &gpu->active_list); + } } -void msm_gem_move_to_inactive(struct drm_gem_object *obj) +void msm_gem_active_put(struct drm_gem_object *obj) { - struct drm_device *dev = obj->dev; - struct msm_drm_private *priv = dev->dev_private; struct msm_gem_object *msm_obj = to_msm_bo(obj); + struct msm_drm_private *priv = obj->dev->dev_private; - WARN_ON(!mutex_is_locked(&dev->struct_mutex)); + WARN_ON(!mutex_is_locked(&obj->dev->struct_mutex)); - msm_obj->gpu = NULL; - list_del_init(&msm_obj->mm_list); - list_add_tail(&msm_obj->mm_list, &priv->inactive_list); + if (!atomic_dec_return(&msm_obj->active_count)) { + msm_obj->gpu = NULL; + list_del_init(&msm_obj->mm_list); + list_add_tail(&msm_obj->mm_list, &priv->inactive_list); + } } int msm_gem_cpu_prep(struct drm_gem_object *obj, uint32_t op, ktime_t *timeout) @@ -852,11 +841,28 @@ void msm_gem_describe(struct drm_gem_object *obj, struct seq_file *m) seq_puts(m, " vmas:"); - list_for_each_entry(vma, &msm_obj->vmas, list) - seq_printf(m, " [%s: %08llx,%s,inuse=%d]", - vma->aspace != NULL ? vma->aspace->name : NULL, - vma->iova, vma->mapped ? "mapped" : "unmapped", + list_for_each_entry(vma, &msm_obj->vmas, list) { + const char *name, *comm; + if (vma->aspace) { + struct msm_gem_address_space *aspace = vma->aspace; + struct task_struct *task = + get_pid_task(aspace->pid, PIDTYPE_PID); + if (task) { + comm = kstrdup(task->comm, GFP_KERNEL); + } else { + comm = NULL; + } + name = aspace->name; + } else { + name = comm = NULL; + } + seq_printf(m, " [%s%s%s: aspace=%p, %08llx,%s,inuse=%d]", + name, comm ? ":" : "", comm ? comm : "", + vma->aspace, vma->iova, + vma->mapped ? "mapped" : "unmapped", vma->inuse); + kfree(comm); + } seq_puts(m, "\n"); } diff --git a/drivers/gpu/drm/msm/msm_gem.h b/drivers/gpu/drm/msm/msm_gem.h index 972490b14ba5..a1bf741b9b89 100644 --- a/drivers/gpu/drm/msm/msm_gem.h +++ b/drivers/gpu/drm/msm/msm_gem.h @@ -24,6 +24,11 @@ struct msm_gem_address_space { spinlock_t lock; /* Protects drm_mm node allocation/removal */ struct msm_mmu *mmu; struct kref kref; + + /* For address spaces associated with a specific process, this + * will be non-NULL: + */ + struct pid *pid; }; struct msm_gem_vma { @@ -83,12 +88,14 @@ struct msm_gem_object { struct mutex lock; /* Protects resources associated with bo */ char name[32]; /* Identifier to print for the debugfs files */ + + atomic_t active_count; }; #define to_msm_bo(x) container_of(x, struct msm_gem_object, base) static inline bool is_active(struct msm_gem_object *msm_obj) { - return msm_obj->gpu != NULL; + return atomic_read(&msm_obj->active_count); } static inline bool is_purgeable(struct msm_gem_object *msm_obj) @@ -142,6 +149,7 @@ struct msm_gem_submit { bool valid; /* true if no cmdstream patching needed */ bool in_rb; /* "sudo" mode, copy cmds into RB */ struct msm_ringbuffer *ring; + struct msm_file_private *ctx; unsigned int nr_cmds; unsigned int nr_bos; u32 ident; /* A "identifier" for the submit for logging */ diff --git a/drivers/gpu/drm/msm/msm_gem_shrinker.c b/drivers/gpu/drm/msm/msm_gem_shrinker.c index 722d61668a97..482576d7a39a 100644 --- a/drivers/gpu/drm/msm/msm_gem_shrinker.c +++ b/drivers/gpu/drm/msm/msm_gem_shrinker.c @@ -6,6 +6,7 @@ #include "msm_drv.h" #include "msm_gem.h" +#include "msm_gpu_trace.h" static bool msm_gem_shrinker_lock(struct drm_device *dev, bool *unlock) { @@ -87,7 +88,7 @@ msm_gem_shrinker_scan(struct shrinker *shrinker, struct shrink_control *sc) mutex_unlock(&dev->struct_mutex); if (freed > 0) - pr_info_ratelimited("Purging %lu bytes\n", freed << PAGE_SHIFT); + trace_msm_gem_purge(freed << PAGE_SHIFT); return freed; } @@ -123,7 +124,7 @@ msm_gem_shrinker_vmap(struct notifier_block *nb, unsigned long event, void *ptr) *(unsigned long *)ptr += unmapped; if (unmapped > 0) - pr_info_ratelimited("Purging %u vmaps\n", unmapped); + trace_msm_gem_purge_vmaps(unmapped); return NOTIFY_DONE; } diff --git a/drivers/gpu/drm/msm/msm_gem_submit.c b/drivers/gpu/drm/msm/msm_gem_submit.c index 8cb9aa15ff90..aa5c60a7132d 100644 --- a/drivers/gpu/drm/msm/msm_gem_submit.c +++ b/drivers/gpu/drm/msm/msm_gem_submit.c @@ -27,7 +27,7 @@ #define BO_PINNED 0x2000 static struct msm_gem_submit *submit_create(struct drm_device *dev, - struct msm_gpu *gpu, struct msm_gem_address_space *aspace, + struct msm_gpu *gpu, struct msm_gpu_submitqueue *queue, uint32_t nr_bos, uint32_t nr_cmds) { @@ -43,7 +43,7 @@ static struct msm_gem_submit *submit_create(struct drm_device *dev, return NULL; submit->dev = dev; - submit->aspace = aspace; + submit->aspace = queue->ctx->aspace; submit->gpu = gpu; submit->fence = NULL; submit->cmd = (void *)&submit->bos[nr_bos]; @@ -677,7 +677,7 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data, } } - submit = submit_create(dev, gpu, ctx->aspace, queue, args->nr_bos, + submit = submit_create(dev, gpu, queue, args->nr_bos, args->nr_cmds); if (!submit) { ret = -ENOMEM; @@ -785,7 +785,7 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data, } } - msm_gpu_submit(gpu, submit, ctx); + msm_gpu_submit(gpu, submit); args->fence = submit->fence->seqno; diff --git a/drivers/gpu/drm/msm/msm_gem_vma.c b/drivers/gpu/drm/msm/msm_gem_vma.c index 5f6a11211b64..f914ddbaea89 100644 --- a/drivers/gpu/drm/msm/msm_gem_vma.c +++ b/drivers/gpu/drm/msm/msm_gem_vma.c @@ -17,6 +17,7 @@ msm_gem_address_space_destroy(struct kref *kref) drm_mm_takedown(&aspace->mm); if (aspace->mmu) aspace->mmu->funcs->destroy(aspace->mmu); + put_pid(aspace->pid); kfree(aspace); } @@ -27,6 +28,15 @@ void msm_gem_address_space_put(struct msm_gem_address_space *aspace) kref_put(&aspace->kref, msm_gem_address_space_destroy); } +struct msm_gem_address_space * +msm_gem_address_space_get(struct msm_gem_address_space *aspace) +{ + if (!IS_ERR_OR_NULL(aspace)) + kref_get(&aspace->kref); + + return aspace; +} + /* Actually unmap memory for the vma */ void msm_gem_purge_vma(struct msm_gem_address_space *aspace, struct msm_gem_vma *vma) @@ -78,8 +88,10 @@ msm_gem_map_vma(struct msm_gem_address_space *aspace, ret = aspace->mmu->funcs->map(aspace->mmu, vma->iova, sgt, size, prot); - if (ret) + if (ret) { vma->mapped = false; + vma->inuse--; + } return ret; } diff --git a/drivers/gpu/drm/msm/msm_gpu.c b/drivers/gpu/drm/msm/msm_gpu.c index 57ddc9438351..55d16489d0f3 100644 --- a/drivers/gpu/drm/msm/msm_gpu.c +++ b/drivers/gpu/drm/msm/msm_gpu.c @@ -24,7 +24,7 @@ static int msm_devfreq_target(struct device *dev, unsigned long *freq, u32 flags) { - struct msm_gpu *gpu = platform_get_drvdata(to_platform_device(dev)); + struct msm_gpu *gpu = dev_to_gpu(dev); struct dev_pm_opp *opp; opp = devfreq_recommended_opp(dev, freq, flags); @@ -32,6 +32,8 @@ static int msm_devfreq_target(struct device *dev, unsigned long *freq, if (IS_ERR(opp)) return PTR_ERR(opp); + trace_msm_gpu_freq_change(dev_pm_opp_get_freq(opp)); + if (gpu->funcs->gpu_set_freq) gpu->funcs->gpu_set_freq(gpu, opp); else @@ -45,7 +47,7 @@ static int msm_devfreq_target(struct device *dev, unsigned long *freq, static int msm_devfreq_get_dev_status(struct device *dev, struct devfreq_dev_status *status) { - struct msm_gpu *gpu = platform_get_drvdata(to_platform_device(dev)); + struct msm_gpu *gpu = dev_to_gpu(dev); ktime_t time; if (gpu->funcs->gpu_get_freq) @@ -64,7 +66,7 @@ static int msm_devfreq_get_dev_status(struct device *dev, static int msm_devfreq_get_cur_freq(struct device *dev, unsigned long *freq) { - struct msm_gpu *gpu = platform_get_drvdata(to_platform_device(dev)); + struct msm_gpu *gpu = dev_to_gpu(dev); if (gpu->funcs->gpu_get_freq) *freq = gpu->funcs->gpu_get_freq(gpu); @@ -200,6 +202,7 @@ int msm_gpu_pm_resume(struct msm_gpu *gpu) int ret; DBG("%s", gpu->name); + trace_msm_gpu_resume(0); ret = enable_pwrrail(gpu); if (ret) @@ -225,6 +228,7 @@ int msm_gpu_pm_suspend(struct msm_gpu *gpu) int ret; DBG("%s", gpu->name); + trace_msm_gpu_suspend(0); devfreq_suspend_device(gpu->devfreq.devfreq); @@ -520,7 +524,7 @@ static void recover_worker(struct work_struct *work) struct msm_ringbuffer *ring = gpu->rb[i]; list_for_each_entry(submit, &ring->submits, node) - gpu->funcs->submit(gpu, submit, NULL); + gpu->funcs->submit(gpu, submit); } } @@ -694,8 +698,8 @@ static void retire_submit(struct msm_gpu *gpu, struct msm_ringbuffer *ring, for (i = 0; i < submit->nr_bos; i++) { struct msm_gem_object *msm_obj = submit->bos[i].obj; - /* move to inactive: */ - msm_gem_move_to_inactive(&msm_obj->base); + + msm_gem_active_put(&msm_obj->base); msm_gem_unpin_iova(&msm_obj->base, submit->aspace); drm_gem_object_put_locked(&msm_obj->base); } @@ -747,8 +751,7 @@ void msm_gpu_retire(struct msm_gpu *gpu) } /* add bo's to gpu's ring, and kick gpu: */ -void msm_gpu_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit, - struct msm_file_private *ctx) +void msm_gpu_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit) { struct drm_device *dev = gpu->dev; struct msm_drm_private *priv = dev->dev_private; @@ -771,6 +774,7 @@ void msm_gpu_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit, for (i = 0; i < submit->nr_bos; i++) { struct msm_gem_object *msm_obj = submit->bos[i].obj; + struct drm_gem_object *drm_obj = &msm_obj->base; uint64_t iova; /* can't happen yet.. but when we add 2d support we'll have @@ -783,13 +787,15 @@ void msm_gpu_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit, msm_gem_get_and_pin_iova(&msm_obj->base, submit->aspace, &iova); if (submit->bos[i].flags & MSM_SUBMIT_BO_WRITE) - msm_gem_move_to_active(&msm_obj->base, gpu, true, submit->fence); + dma_resv_add_excl_fence(drm_obj->resv, submit->fence); else if (submit->bos[i].flags & MSM_SUBMIT_BO_READ) - msm_gem_move_to_active(&msm_obj->base, gpu, false, submit->fence); + dma_resv_add_shared_fence(drm_obj->resv, submit->fence); + + msm_gem_active_get(drm_obj, gpu); } - gpu->funcs->submit(gpu, submit, ctx); - priv->lastctx = ctx; + gpu->funcs->submit(gpu, submit); + priv->lastctx = submit->queue->ctx; hangcheck_timer_reset(gpu); } @@ -824,6 +830,30 @@ static int get_clocks(struct platform_device *pdev, struct msm_gpu *gpu) return 0; } +/* Return a new address space for a msm_drm_private instance */ +struct msm_gem_address_space * +msm_gpu_create_private_address_space(struct msm_gpu *gpu, struct task_struct *task) +{ + struct msm_gem_address_space *aspace = NULL; + if (!gpu) + return NULL; + + /* + * If the target doesn't support private address spaces then return + * the global one + */ + if (gpu->funcs->create_private_address_space) { + aspace = gpu->funcs->create_private_address_space(gpu); + if (!IS_ERR(aspace)) + aspace->pid = get_pid(task_pid(task)); + } + + if (IS_ERR_OR_NULL(aspace)) + aspace = msm_gem_address_space_get(gpu->aspace); + + return aspace; +} + int msm_gpu_init(struct drm_device *drm, struct platform_device *pdev, struct msm_gpu *gpu, const struct msm_gpu_funcs *funcs, const char *name, struct msm_gpu_config *config) @@ -892,7 +922,7 @@ int msm_gpu_init(struct drm_device *drm, struct platform_device *pdev, gpu->gpu_cx = NULL; gpu->pdev = pdev; - platform_set_drvdata(pdev, gpu); + platform_set_drvdata(pdev, &gpu->adreno_smmu); msm_devfreq_init(gpu); diff --git a/drivers/gpu/drm/msm/msm_gpu.h b/drivers/gpu/drm/msm/msm_gpu.h index 37cffac4cbe3..6c9e1fdc1a76 100644 --- a/drivers/gpu/drm/msm/msm_gpu.h +++ b/drivers/gpu/drm/msm/msm_gpu.h @@ -7,6 +7,7 @@ #ifndef __MSM_GPU_H__ #define __MSM_GPU_H__ +#include <linux/adreno-smmu-priv.h> #include <linux/clk.h> #include <linux/interconnect.h> #include <linux/pm_opp.h> @@ -45,8 +46,7 @@ struct msm_gpu_funcs { int (*hw_init)(struct msm_gpu *gpu); int (*pm_suspend)(struct msm_gpu *gpu); int (*pm_resume)(struct msm_gpu *gpu); - void (*submit)(struct msm_gpu *gpu, struct msm_gem_submit *submit, - struct msm_file_private *ctx); + void (*submit)(struct msm_gpu *gpu, struct msm_gem_submit *submit); void (*flush)(struct msm_gpu *gpu, struct msm_ringbuffer *ring); irqreturn_t (*irq)(struct msm_gpu *irq); struct msm_ringbuffer *(*active_ring)(struct msm_gpu *gpu); @@ -66,6 +66,9 @@ struct msm_gpu_funcs { void (*gpu_set_freq)(struct msm_gpu *gpu, struct dev_pm_opp *opp); struct msm_gem_address_space *(*create_address_space) (struct msm_gpu *gpu, struct platform_device *pdev); + struct msm_gem_address_space *(*create_private_address_space) + (struct msm_gpu *gpu); + uint32_t (*get_rptr)(struct msm_gpu *gpu, struct msm_ringbuffer *ring); }; struct msm_gpu { @@ -74,6 +77,8 @@ struct msm_gpu { struct platform_device *pdev; const struct msm_gpu_funcs *funcs; + struct adreno_smmu_priv adreno_smmu; + /* performance counters (hw & sw): */ spinlock_t perf_lock; bool perfcntr_active; @@ -144,6 +149,12 @@ struct msm_gpu { bool hw_apriv; }; +static inline struct msm_gpu *dev_to_gpu(struct device *dev) +{ + struct adreno_smmu_priv *adreno_smmu = dev_get_drvdata(dev); + return container_of(adreno_smmu, struct msm_gpu, adreno_smmu); +} + /* It turns out that all targets use the same ringbuffer size */ #define MSM_GPU_RINGBUFFER_SZ SZ_32K #define MSM_GPU_RINGBUFFER_BLKSIZE 32 @@ -184,6 +195,7 @@ struct msm_gpu_submitqueue { u32 flags; u32 prio; int faults; + struct msm_file_private *ctx; struct list_head node; struct kref ref; }; @@ -283,13 +295,15 @@ int msm_gpu_perfcntr_sample(struct msm_gpu *gpu, uint32_t *activetime, uint32_t *totaltime, uint32_t ncntrs, uint32_t *cntrs); void msm_gpu_retire(struct msm_gpu *gpu); -void msm_gpu_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit, - struct msm_file_private *ctx); +void msm_gpu_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit); int msm_gpu_init(struct drm_device *drm, struct platform_device *pdev, struct msm_gpu *gpu, const struct msm_gpu_funcs *funcs, const char *name, struct msm_gpu_config *config); +struct msm_gem_address_space * +msm_gpu_create_private_address_space(struct msm_gpu *gpu, struct task_struct *task); + void msm_gpu_cleanup(struct msm_gpu *gpu); struct msm_gpu *adreno_load_gpu(struct drm_device *dev); diff --git a/drivers/gpu/drm/msm/msm_gpu_trace.h b/drivers/gpu/drm/msm/msm_gpu_trace.h index 122b84789238..03e0c2536b94 100644 --- a/drivers/gpu/drm/msm/msm_gpu_trace.h +++ b/drivers/gpu/drm/msm/msm_gpu_trace.h @@ -83,6 +83,89 @@ TRACE_EVENT(msm_gpu_submit_retired, __entry->start_ticks, __entry->end_ticks) ); + +TRACE_EVENT(msm_gpu_freq_change, + TP_PROTO(u32 freq), + TP_ARGS(freq), + TP_STRUCT__entry( + __field(u32, freq) + ), + TP_fast_assign( + /* trace freq in MHz to match intel_gpu_freq_change, to make life easier + * for userspace + */ + __entry->freq = DIV_ROUND_UP(freq, 1000000); + ), + TP_printk("new_freq=%u", __entry->freq) +); + + +TRACE_EVENT(msm_gmu_freq_change, + TP_PROTO(u32 freq, u32 perf_index), + TP_ARGS(freq, perf_index), + TP_STRUCT__entry( + __field(u32, freq) + __field(u32, perf_index) + ), + TP_fast_assign( + __entry->freq = freq; + __entry->perf_index = perf_index; + ), + TP_printk("freq=%u, perf_index=%u", __entry->freq, __entry->perf_index) +); + + +TRACE_EVENT(msm_gem_purge, + TP_PROTO(u32 bytes), + TP_ARGS(bytes), + TP_STRUCT__entry( + __field(u32, bytes) + ), + TP_fast_assign( + __entry->bytes = bytes; + ), + TP_printk("Purging %u bytes", __entry->bytes) +); + + +TRACE_EVENT(msm_gem_purge_vmaps, + TP_PROTO(u32 unmapped), + TP_ARGS(unmapped), + TP_STRUCT__entry( + __field(u32, unmapped) + ), + TP_fast_assign( + __entry->unmapped = unmapped; + ), + TP_printk("Purging %u vmaps", __entry->unmapped) +); + + +TRACE_EVENT(msm_gpu_suspend, + TP_PROTO(int dummy), + TP_ARGS(dummy), + TP_STRUCT__entry( + __field(u32, dummy) + ), + TP_fast_assign( + __entry->dummy = dummy; + ), + TP_printk("%u", __entry->dummy) +); + + +TRACE_EVENT(msm_gpu_resume, + TP_PROTO(int dummy), + TP_ARGS(dummy), + TP_STRUCT__entry( + __field(u32, dummy) + ), + TP_fast_assign( + __entry->dummy = dummy; + ), + TP_printk("%u", __entry->dummy) +); + #endif #undef TRACE_INCLUDE_PATH diff --git a/drivers/gpu/drm/msm/msm_gpummu.c b/drivers/gpu/drm/msm/msm_gpummu.c index 310a31b05faa..379496186c7f 100644 --- a/drivers/gpu/drm/msm/msm_gpummu.c +++ b/drivers/gpu/drm/msm/msm_gpummu.c @@ -30,21 +30,20 @@ static int msm_gpummu_map(struct msm_mmu *mmu, uint64_t iova, { struct msm_gpummu *gpummu = to_msm_gpummu(mmu); unsigned idx = (iova - GPUMMU_VA_START) / GPUMMU_PAGE_SIZE; - struct scatterlist *sg; + struct sg_dma_page_iter dma_iter; unsigned prot_bits = 0; - unsigned i, j; if (prot & IOMMU_WRITE) prot_bits |= 1; if (prot & IOMMU_READ) prot_bits |= 2; - for_each_sg(sgt->sgl, sg, sgt->nents, i) { - dma_addr_t addr = sg->dma_address; - for (j = 0; j < sg->length / GPUMMU_PAGE_SIZE; j++, idx++) { - gpummu->table[idx] = addr | prot_bits; - addr += GPUMMU_PAGE_SIZE; - } + for_each_sgtable_dma_page(sgt, &dma_iter, 0) { + dma_addr_t addr = sg_page_iter_dma_address(&dma_iter); + int i; + + for (i = 0; i < PAGE_SIZE; i += GPUMMU_PAGE_SIZE) + gpummu->table[idx++] = (addr + i) | prot_bits; } /* we can improve by deferring flush for multiple map() */ @@ -102,7 +101,7 @@ struct msm_mmu *msm_gpummu_new(struct device *dev, struct msm_gpu *gpu) } gpummu->gpu = gpu; - msm_mmu_init(&gpummu->base, dev, &funcs); + msm_mmu_init(&gpummu->base, dev, &funcs, MSM_MMU_GPUMMU); return &gpummu->base; } diff --git a/drivers/gpu/drm/msm/msm_iommu.c b/drivers/gpu/drm/msm/msm_iommu.c index 3a381a9674c9..22ac7c692a81 100644 --- a/drivers/gpu/drm/msm/msm_iommu.c +++ b/drivers/gpu/drm/msm/msm_iommu.c @@ -4,15 +4,210 @@ * Author: Rob Clark <robdclark@gmail.com> */ +#include <linux/adreno-smmu-priv.h> +#include <linux/io-pgtable.h> #include "msm_drv.h" #include "msm_mmu.h" struct msm_iommu { struct msm_mmu base; struct iommu_domain *domain; + atomic_t pagetables; }; + #define to_msm_iommu(x) container_of(x, struct msm_iommu, base) +struct msm_iommu_pagetable { + struct msm_mmu base; + struct msm_mmu *parent; + struct io_pgtable_ops *pgtbl_ops; + phys_addr_t ttbr; + u32 asid; +}; +static struct msm_iommu_pagetable *to_pagetable(struct msm_mmu *mmu) +{ + return container_of(mmu, struct msm_iommu_pagetable, base); +} + +static int msm_iommu_pagetable_unmap(struct msm_mmu *mmu, u64 iova, + size_t size) +{ + struct msm_iommu_pagetable *pagetable = to_pagetable(mmu); + struct io_pgtable_ops *ops = pagetable->pgtbl_ops; + size_t unmapped = 0; + + /* Unmap the block one page at a time */ + while (size) { + unmapped += ops->unmap(ops, iova, 4096, NULL); + iova += 4096; + size -= 4096; + } + + iommu_flush_iotlb_all(to_msm_iommu(pagetable->parent)->domain); + + return (unmapped == size) ? 0 : -EINVAL; +} + +static int msm_iommu_pagetable_map(struct msm_mmu *mmu, u64 iova, + struct sg_table *sgt, size_t len, int prot) +{ + struct msm_iommu_pagetable *pagetable = to_pagetable(mmu); + struct io_pgtable_ops *ops = pagetable->pgtbl_ops; + struct scatterlist *sg; + size_t mapped = 0; + u64 addr = iova; + unsigned int i; + + for_each_sg(sgt->sgl, sg, sgt->nents, i) { + size_t size = sg->length; + phys_addr_t phys = sg_phys(sg); + + /* Map the block one page at a time */ + while (size) { + if (ops->map(ops, addr, phys, 4096, prot, GFP_KERNEL)) { + msm_iommu_pagetable_unmap(mmu, iova, mapped); + return -EINVAL; + } + + phys += 4096; + addr += 4096; + size -= 4096; + mapped += 4096; + } + } + + return 0; +} + +static void msm_iommu_pagetable_destroy(struct msm_mmu *mmu) +{ + struct msm_iommu_pagetable *pagetable = to_pagetable(mmu); + struct msm_iommu *iommu = to_msm_iommu(pagetable->parent); + struct adreno_smmu_priv *adreno_smmu = + dev_get_drvdata(pagetable->parent->dev); + + /* + * If this is the last attached pagetable for the parent, + * disable TTBR0 in the arm-smmu driver + */ + if (atomic_dec_return(&iommu->pagetables) == 0) + adreno_smmu->set_ttbr0_cfg(adreno_smmu->cookie, NULL); + + free_io_pgtable_ops(pagetable->pgtbl_ops); + kfree(pagetable); +} + +int msm_iommu_pagetable_params(struct msm_mmu *mmu, + phys_addr_t *ttbr, int *asid) +{ + struct msm_iommu_pagetable *pagetable; + + if (mmu->type != MSM_MMU_IOMMU_PAGETABLE) + return -EINVAL; + + pagetable = to_pagetable(mmu); + + if (ttbr) + *ttbr = pagetable->ttbr; + + if (asid) + *asid = pagetable->asid; + + return 0; +} + +static const struct msm_mmu_funcs pagetable_funcs = { + .map = msm_iommu_pagetable_map, + .unmap = msm_iommu_pagetable_unmap, + .destroy = msm_iommu_pagetable_destroy, +}; + +static void msm_iommu_tlb_flush_all(void *cookie) +{ +} + +static void msm_iommu_tlb_flush_walk(unsigned long iova, size_t size, + size_t granule, void *cookie) +{ +} + +static void msm_iommu_tlb_add_page(struct iommu_iotlb_gather *gather, + unsigned long iova, size_t granule, void *cookie) +{ +} + +static const struct iommu_flush_ops null_tlb_ops = { + .tlb_flush_all = msm_iommu_tlb_flush_all, + .tlb_flush_walk = msm_iommu_tlb_flush_walk, + .tlb_flush_leaf = msm_iommu_tlb_flush_walk, + .tlb_add_page = msm_iommu_tlb_add_page, +}; + +struct msm_mmu *msm_iommu_pagetable_create(struct msm_mmu *parent) +{ + struct adreno_smmu_priv *adreno_smmu = dev_get_drvdata(parent->dev); + struct msm_iommu *iommu = to_msm_iommu(parent); + struct msm_iommu_pagetable *pagetable; + const struct io_pgtable_cfg *ttbr1_cfg = NULL; + struct io_pgtable_cfg ttbr0_cfg; + int ret; + + /* Get the pagetable configuration from the domain */ + if (adreno_smmu->cookie) + ttbr1_cfg = adreno_smmu->get_ttbr1_cfg(adreno_smmu->cookie); + if (!ttbr1_cfg) + return ERR_PTR(-ENODEV); + + pagetable = kzalloc(sizeof(*pagetable), GFP_KERNEL); + if (!pagetable) + return ERR_PTR(-ENOMEM); + + msm_mmu_init(&pagetable->base, parent->dev, &pagetable_funcs, + MSM_MMU_IOMMU_PAGETABLE); + + /* Clone the TTBR1 cfg as starting point for TTBR0 cfg: */ + ttbr0_cfg = *ttbr1_cfg; + + /* The incoming cfg will have the TTBR1 quirk enabled */ + ttbr0_cfg.quirks &= ~IO_PGTABLE_QUIRK_ARM_TTBR1; + ttbr0_cfg.tlb = &null_tlb_ops; + + pagetable->pgtbl_ops = alloc_io_pgtable_ops(ARM_64_LPAE_S1, + &ttbr0_cfg, iommu->domain); + + if (!pagetable->pgtbl_ops) { + kfree(pagetable); + return ERR_PTR(-ENOMEM); + } + + /* + * If this is the first pagetable that we've allocated, send it back to + * the arm-smmu driver as a trigger to set up TTBR0 + */ + if (atomic_inc_return(&iommu->pagetables) == 1) { + ret = adreno_smmu->set_ttbr0_cfg(adreno_smmu->cookie, &ttbr0_cfg); + if (ret) { + free_io_pgtable_ops(pagetable->pgtbl_ops); + kfree(pagetable); + return ERR_PTR(ret); + } + } + + /* Needed later for TLB flush */ + pagetable->parent = parent; + pagetable->ttbr = ttbr0_cfg.arm_lpae_s1_cfg.ttbr; + + /* + * TODO we would like each set of page tables to have a unique ASID + * to optimize TLB invalidation. But iommu_flush_iotlb_all() will + * end up flushing the ASID used for TTBR1 pagetables, which is not + * what we want. So for now just use the same ASID as TTBR1. + */ + pagetable->asid = 0; + + return &pagetable->base; +} + static int msm_fault_handler(struct iommu_domain *domain, struct device *dev, unsigned long iova, int flags, void *arg) { @@ -36,7 +231,11 @@ static int msm_iommu_map(struct msm_mmu *mmu, uint64_t iova, struct msm_iommu *iommu = to_msm_iommu(mmu); size_t ret; - ret = iommu_map_sg(iommu->domain, iova, sgt->sgl, sgt->nents, prot); + /* The arm-smmu driver expects the addresses to be sign extended */ + if (iova & BIT_ULL(48)) + iova |= GENMASK_ULL(63, 49); + + ret = iommu_map_sgtable(iommu->domain, iova, sgt, prot); WARN_ON(!ret); return (ret == len) ? 0 : -EINVAL; @@ -46,6 +245,9 @@ static int msm_iommu_unmap(struct msm_mmu *mmu, uint64_t iova, size_t len) { struct msm_iommu *iommu = to_msm_iommu(mmu); + if (iova & BIT_ULL(48)) + iova |= GENMASK_ULL(63, 49); + iommu_unmap(iommu->domain, iova, len); return 0; @@ -78,9 +280,11 @@ struct msm_mmu *msm_iommu_new(struct device *dev, struct iommu_domain *domain) return ERR_PTR(-ENOMEM); iommu->domain = domain; - msm_mmu_init(&iommu->base, dev, &funcs); + msm_mmu_init(&iommu->base, dev, &funcs, MSM_MMU_IOMMU); iommu_set_fault_handler(domain, msm_fault_handler, iommu); + atomic_set(&iommu->pagetables, 0); + ret = iommu_attach_device(iommu->domain, dev); if (ret) { kfree(iommu); diff --git a/drivers/gpu/drm/msm/msm_mmu.h b/drivers/gpu/drm/msm/msm_mmu.h index 3a534ee59bf6..61ade89d9e48 100644 --- a/drivers/gpu/drm/msm/msm_mmu.h +++ b/drivers/gpu/drm/msm/msm_mmu.h @@ -17,18 +17,26 @@ struct msm_mmu_funcs { void (*destroy)(struct msm_mmu *mmu); }; +enum msm_mmu_type { + MSM_MMU_GPUMMU, + MSM_MMU_IOMMU, + MSM_MMU_IOMMU_PAGETABLE, +}; + struct msm_mmu { const struct msm_mmu_funcs *funcs; struct device *dev; int (*handler)(void *arg, unsigned long iova, int flags); void *arg; + enum msm_mmu_type type; }; static inline void msm_mmu_init(struct msm_mmu *mmu, struct device *dev, - const struct msm_mmu_funcs *funcs) + const struct msm_mmu_funcs *funcs, enum msm_mmu_type type) { mmu->dev = dev; mmu->funcs = funcs; + mmu->type = type; } struct msm_mmu *msm_iommu_new(struct device *dev, struct iommu_domain *domain); @@ -41,7 +49,13 @@ static inline void msm_mmu_set_fault_handler(struct msm_mmu *mmu, void *arg, mmu->handler = handler; } +struct msm_mmu *msm_iommu_pagetable_create(struct msm_mmu *parent); + void msm_gpummu_params(struct msm_mmu *mmu, dma_addr_t *pt_base, dma_addr_t *tran_error); + +int msm_iommu_pagetable_params(struct msm_mmu *mmu, phys_addr_t *ttbr, + int *asid); + #endif /* __MSM_MMU_H__ */ diff --git a/drivers/gpu/drm/msm/msm_ringbuffer.h b/drivers/gpu/drm/msm/msm_ringbuffer.h index 7764373d0ed2..0987d6bf848c 100644 --- a/drivers/gpu/drm/msm/msm_ringbuffer.h +++ b/drivers/gpu/drm/msm/msm_ringbuffer.h @@ -31,6 +31,7 @@ struct msm_rbmemptrs { volatile uint32_t fence; volatile struct msm_gpu_submit_stats stats[MSM_GPU_SUBMIT_STATS_COUNT]; + volatile u64 ttbr0; }; struct msm_ringbuffer { diff --git a/drivers/gpu/drm/msm/msm_submitqueue.c b/drivers/gpu/drm/msm/msm_submitqueue.c index a1d94be7883a..c3d206105d28 100644 --- a/drivers/gpu/drm/msm/msm_submitqueue.c +++ b/drivers/gpu/drm/msm/msm_submitqueue.c @@ -12,6 +12,8 @@ void msm_submitqueue_destroy(struct kref *kref) struct msm_gpu_submitqueue *queue = container_of(kref, struct msm_gpu_submitqueue, ref); + msm_file_private_put(queue->ctx); + kfree(queue); } @@ -49,8 +51,10 @@ void msm_submitqueue_close(struct msm_file_private *ctx) * No lock needed in close and there won't * be any more user ioctls coming our way */ - list_for_each_entry_safe(entry, tmp, &ctx->submitqueues, node) + list_for_each_entry_safe(entry, tmp, &ctx->submitqueues, node) { + list_del(&entry->node); msm_submitqueue_put(entry); + } } int msm_submitqueue_create(struct drm_device *drm, struct msm_file_private *ctx, @@ -81,6 +85,7 @@ int msm_submitqueue_create(struct drm_device *drm, struct msm_file_private *ctx, write_lock(&ctx->queuelock); + queue->ctx = msm_file_private_get(ctx); queue->id = ctx->queueid++; if (id) diff --git a/drivers/gpu/drm/nouveau/dispnv50/core.h b/drivers/gpu/drm/nouveau/dispnv50/core.h index 498622c0c670..f75088186fba 100644 --- a/drivers/gpu/drm/nouveau/dispnv50/core.h +++ b/drivers/gpu/drm/nouveau/dispnv50/core.h @@ -44,6 +44,7 @@ int core507d_new_(const struct nv50_core_func *, struct nouveau_drm *, s32, struct nv50_core **); int core507d_init(struct nv50_core *); void core507d_ntfy_init(struct nouveau_bo *, u32); +int core507d_read_caps(struct nv50_disp *disp); int core507d_caps_init(struct nouveau_drm *, struct nv50_disp *); int core507d_ntfy_wait_done(struct nouveau_bo *, u32, struct nvif_device *); int core507d_update(struct nv50_core *, u32 *, bool); @@ -55,6 +56,7 @@ extern const struct nv50_outp_func pior507d; int core827d_new(struct nouveau_drm *, s32, struct nv50_core **); int core907d_new(struct nouveau_drm *, s32, struct nv50_core **); +int core907d_caps_init(struct nouveau_drm *drm, struct nv50_disp *disp); extern const struct nv50_outp_func dac907d; extern const struct nv50_outp_func sor907d; diff --git a/drivers/gpu/drm/nouveau/dispnv50/core507d.c b/drivers/gpu/drm/nouveau/dispnv50/core507d.c index 248edf69e168..e6f16a7750f0 100644 --- a/drivers/gpu/drm/nouveau/dispnv50/core507d.c +++ b/drivers/gpu/drm/nouveau/dispnv50/core507d.c @@ -78,19 +78,56 @@ core507d_ntfy_init(struct nouveau_bo *bo, u32 offset) } int -core507d_caps_init(struct nouveau_drm *drm, struct nv50_disp *disp) +core507d_read_caps(struct nv50_disp *disp) { struct nvif_push *push = disp->core->chan.push; int ret; - if ((ret = PUSH_WAIT(push, 2))) + ret = PUSH_WAIT(push, 6); + if (ret) return ret; + PUSH_MTHD(push, NV507D, SET_NOTIFIER_CONTROL, + NVDEF(NV507D, SET_NOTIFIER_CONTROL, MODE, WRITE) | + NVVAL(NV507D, SET_NOTIFIER_CONTROL, OFFSET, NV50_DISP_CORE_NTFY >> 2) | + NVDEF(NV507D, SET_NOTIFIER_CONTROL, NOTIFY, ENABLE)); + PUSH_MTHD(push, NV507D, GET_CAPABILITIES, 0x00000000); + + PUSH_MTHD(push, NV507D, SET_NOTIFIER_CONTROL, + NVDEF(NV507D, SET_NOTIFIER_CONTROL, NOTIFY, DISABLE)); + return PUSH_KICK(push); } int +core507d_caps_init(struct nouveau_drm *drm, struct nv50_disp *disp) +{ + struct nv50_core *core = disp->core; + struct nouveau_bo *bo = disp->sync; + s64 time; + int ret; + + NVBO_WR32(bo, NV50_DISP_CORE_NTFY, NV_DISP_CORE_NOTIFIER_1, CAPABILITIES_1, + NVDEF(NV_DISP_CORE_NOTIFIER_1, CAPABILITIES_1, DONE, FALSE)); + + ret = core507d_read_caps(disp); + if (ret < 0) + return ret; + + time = nvif_msec(core->chan.base.device, 2000ULL, + if (NVBO_TD32(bo, NV50_DISP_CORE_NTFY, + NV_DISP_CORE_NOTIFIER_1, CAPABILITIES_1, DONE, ==, TRUE)) + break; + usleep_range(1, 2); + ); + if (time < 0) + NV_ERROR(drm, "core caps notifier timeout\n"); + + return 0; +} + +int core507d_init(struct nv50_core *core) { struct nvif_push *push = core->chan.push; diff --git a/drivers/gpu/drm/nouveau/dispnv50/core907d.c b/drivers/gpu/drm/nouveau/dispnv50/core907d.c index b17c03529c78..8564d4dffaff 100644 --- a/drivers/gpu/drm/nouveau/dispnv50/core907d.c +++ b/drivers/gpu/drm/nouveau/dispnv50/core907d.c @@ -22,11 +22,45 @@ #include "core.h" #include "head.h" +#include <nvif/push507c.h> +#include <nvif/timer.h> + +#include <nvhw/class/cl907d.h> + +#include "nouveau_bo.h" + +int +core907d_caps_init(struct nouveau_drm *drm, struct nv50_disp *disp) +{ + struct nv50_core *core = disp->core; + struct nouveau_bo *bo = disp->sync; + s64 time; + int ret; + + NVBO_WR32(bo, NV50_DISP_CORE_NTFY, NV907D_CORE_NOTIFIER_3, CAPABILITIES_4, + NVDEF(NV907D_CORE_NOTIFIER_3, CAPABILITIES_4, DONE, FALSE)); + + ret = core507d_read_caps(disp); + if (ret < 0) + return ret; + + time = nvif_msec(core->chan.base.device, 2000ULL, + if (NVBO_TD32(bo, NV50_DISP_CORE_NTFY, + NV907D_CORE_NOTIFIER_3, CAPABILITIES_4, DONE, ==, TRUE)) + break; + usleep_range(1, 2); + ); + if (time < 0) + NV_ERROR(drm, "core caps notifier timeout\n"); + + return 0; +} + static const struct nv50_core_func core907d = { .init = core507d_init, .ntfy_init = core507d_ntfy_init, - .caps_init = core507d_caps_init, + .caps_init = core907d_caps_init, .ntfy_wait_done = core507d_ntfy_wait_done, .update = core507d_update, .head = &head907d, diff --git a/drivers/gpu/drm/nouveau/dispnv50/core917d.c b/drivers/gpu/drm/nouveau/dispnv50/core917d.c index 66846f372080..1cd3a2a35dfb 100644 --- a/drivers/gpu/drm/nouveau/dispnv50/core917d.c +++ b/drivers/gpu/drm/nouveau/dispnv50/core917d.c @@ -26,7 +26,7 @@ static const struct nv50_core_func core917d = { .init = core507d_init, .ntfy_init = core507d_ntfy_init, - .caps_init = core507d_caps_init, + .caps_init = core907d_caps_init, .ntfy_wait_done = core507d_ntfy_wait_done, .update = core507d_update, .head = &head917d, diff --git a/drivers/gpu/drm/nouveau/include/nvhw/class/cl507d.h b/drivers/gpu/drm/nouveau/include/nvhw/class/cl507d.h index 2e444bac701d..6a463f308b64 100644 --- a/drivers/gpu/drm/nouveau/include/nvhw/class/cl507d.h +++ b/drivers/gpu/drm/nouveau/include/nvhw/class/cl507d.h @@ -32,7 +32,10 @@ #define NV_DISP_CORE_NOTIFIER_1_COMPLETION_0_DONE_TRUE 0x00000001 #define NV_DISP_CORE_NOTIFIER_1_COMPLETION_0_R0 15:1 #define NV_DISP_CORE_NOTIFIER_1_COMPLETION_0_TIMESTAMP 29:16 - +#define NV_DISP_CORE_NOTIFIER_1_CAPABILITIES_1 0x00000001 +#define NV_DISP_CORE_NOTIFIER_1_CAPABILITIES_1_DONE 0:0 +#define NV_DISP_CORE_NOTIFIER_1_CAPABILITIES_1_DONE_FALSE 0x00000000 +#define NV_DISP_CORE_NOTIFIER_1_CAPABILITIES_1_DONE_TRUE 0x00000001 // class methods #define NV507D_UPDATE (0x00000080) diff --git a/drivers/gpu/drm/nouveau/include/nvhw/class/cl907d.h b/drivers/gpu/drm/nouveau/include/nvhw/class/cl907d.h index 34bc3eafac7d..79aff6ff3138 100644 --- a/drivers/gpu/drm/nouveau/include/nvhw/class/cl907d.h +++ b/drivers/gpu/drm/nouveau/include/nvhw/class/cl907d.h @@ -24,6 +24,10 @@ #ifndef _cl907d_h_ #define _cl907d_h_ +#define NV907D_CORE_NOTIFIER_3_CAPABILITIES_4 0x00000004 +#define NV907D_CORE_NOTIFIER_3_CAPABILITIES_4_DONE 0:0 +#define NV907D_CORE_NOTIFIER_3_CAPABILITIES_4_DONE_FALSE 0x00000000 +#define NV907D_CORE_NOTIFIER_3_CAPABILITIES_4_DONE_TRUE 0x00000001 #define NV907D_CORE_NOTIFIER_3_CAPABILITIES_CAP_SOR0_20 0x00000014 #define NV907D_CORE_NOTIFIER_3_CAPABILITIES_CAP_SOR0_20_SINGLE_LVDS18 0:0 #define NV907D_CORE_NOTIFIER_3_CAPABILITIES_CAP_SOR0_20_SINGLE_LVDS18_FALSE 0x00000000 diff --git a/drivers/gpu/drm/nouveau/nouveau_connector.c b/drivers/gpu/drm/nouveau/nouveau_connector.c index 49dd0cbc332f..6f21f36719fc 100644 --- a/drivers/gpu/drm/nouveau/nouveau_connector.c +++ b/drivers/gpu/drm/nouveau/nouveau_connector.c @@ -1023,29 +1023,6 @@ get_tmds_link_bandwidth(struct drm_connector *connector) return 112000 * duallink_scale; } -enum drm_mode_status -nouveau_conn_mode_clock_valid(const struct drm_display_mode *mode, - const unsigned min_clock, - const unsigned max_clock, - unsigned int *clock_out) -{ - unsigned int clock = mode->clock; - - if ((mode->flags & DRM_MODE_FLAG_3D_MASK) == - DRM_MODE_FLAG_3D_FRAME_PACKING) - clock *= 2; - - if (clock < min_clock) - return MODE_CLOCK_LOW; - if (clock > max_clock) - return MODE_CLOCK_HIGH; - - if (clock_out) - *clock_out = clock; - - return MODE_OK; -} - static enum drm_mode_status nouveau_connector_mode_valid(struct drm_connector *connector, struct drm_display_mode *mode) @@ -1053,7 +1030,7 @@ nouveau_connector_mode_valid(struct drm_connector *connector, struct nouveau_connector *nv_connector = nouveau_connector(connector); struct nouveau_encoder *nv_encoder = nv_connector->detected_encoder; struct drm_encoder *encoder = to_drm_encoder(nv_encoder); - unsigned min_clock = 25000, max_clock = min_clock; + unsigned int min_clock = 25000, max_clock = min_clock, clock = mode->clock; switch (nv_encoder->dcb->type) { case DCB_OUTPUT_LVDS: @@ -1082,8 +1059,15 @@ nouveau_connector_mode_valid(struct drm_connector *connector, return MODE_BAD; } - return nouveau_conn_mode_clock_valid(mode, min_clock, max_clock, - NULL); + if ((mode->flags & DRM_MODE_FLAG_3D_MASK) == DRM_MODE_FLAG_3D_FRAME_PACKING) + clock *= 2; + + if (clock < min_clock) + return MODE_CLOCK_LOW; + if (clock > max_clock) + return MODE_CLOCK_HIGH; + + return MODE_OK; } static struct drm_encoder * diff --git a/drivers/gpu/drm/nouveau/nouveau_dmem.c b/drivers/gpu/drm/nouveau/nouveau_dmem.c index af70ef8e5471..92987daa5e17 100644 --- a/drivers/gpu/drm/nouveau/nouveau_dmem.c +++ b/drivers/gpu/drm/nouveau/nouveau_dmem.c @@ -101,7 +101,7 @@ unsigned long nouveau_dmem_page_addr(struct page *page) { struct nouveau_dmem_chunk *chunk = nouveau_page_to_chunk(page); unsigned long off = (page_to_pfn(page) << PAGE_SHIFT) - - chunk->pagemap.res.start; + chunk->pagemap.range.start; return chunk->bo->offset + off; } @@ -249,7 +249,9 @@ nouveau_dmem_chunk_alloc(struct nouveau_drm *drm, struct page **ppage) chunk->drm = drm; chunk->pagemap.type = MEMORY_DEVICE_PRIVATE; - chunk->pagemap.res = *res; + chunk->pagemap.range.start = res->start; + chunk->pagemap.range.end = res->end; + chunk->pagemap.nr_range = 1; chunk->pagemap.ops = &nouveau_dmem_pagemap_ops; chunk->pagemap.owner = drm->dev; @@ -273,7 +275,7 @@ nouveau_dmem_chunk_alloc(struct nouveau_drm *drm, struct page **ppage) list_add(&chunk->list, &drm->dmem->chunks); mutex_unlock(&drm->dmem->mutex); - pfn_first = chunk->pagemap.res.start >> PAGE_SHIFT; + pfn_first = chunk->pagemap.range.start >> PAGE_SHIFT; page = pfn_to_page(pfn_first); spin_lock(&drm->dmem->lock); for (i = 0; i < DMEM_CHUNK_NPAGES - 1; ++i, ++page) { @@ -294,8 +296,7 @@ out_bo_unpin: out_bo_free: nouveau_bo_ref(NULL, &chunk->bo); out_release: - release_mem_region(chunk->pagemap.res.start, - resource_size(&chunk->pagemap.res)); + release_mem_region(chunk->pagemap.range.start, range_len(&chunk->pagemap.range)); out_free: kfree(chunk); out: @@ -382,8 +383,8 @@ nouveau_dmem_fini(struct nouveau_drm *drm) nouveau_bo_ref(NULL, &chunk->bo); list_del(&chunk->list); memunmap_pages(&chunk->pagemap); - release_mem_region(chunk->pagemap.res.start, - resource_size(&chunk->pagemap.res)); + release_mem_region(chunk->pagemap.range.start, + range_len(&chunk->pagemap.range)); kfree(chunk); } diff --git a/drivers/gpu/drm/nouveau/nouveau_dp.c b/drivers/gpu/drm/nouveau/nouveau_dp.c index 810bf6956568..040ed88d362d 100644 --- a/drivers/gpu/drm/nouveau/nouveau_dp.c +++ b/drivers/gpu/drm/nouveau/nouveau_dp.c @@ -231,23 +231,30 @@ nv50_dp_mode_valid(struct drm_connector *connector, const struct drm_display_mode *mode, unsigned *out_clock) { - const unsigned min_clock = 25000; - unsigned max_clock, ds_clock, clock; - enum drm_mode_status ret; + const unsigned int min_clock = 25000; + unsigned int max_rate, mode_rate, ds_max_dotclock, clock = mode->clock; + const u8 bpp = connector->display_info.bpc * 3; if (mode->flags & DRM_MODE_FLAG_INTERLACE && !outp->caps.dp_interlace) return MODE_NO_INTERLACE; - max_clock = outp->dp.link_nr * outp->dp.link_bw; - ds_clock = drm_dp_downstream_max_clock(outp->dp.dpcd, - outp->dp.downstream_ports); - if (ds_clock) - max_clock = min(max_clock, ds_clock); + if ((mode->flags & DRM_MODE_FLAG_3D_MASK) == DRM_MODE_FLAG_3D_FRAME_PACKING) + clock *= 2; + + max_rate = outp->dp.link_nr * outp->dp.link_bw; + mode_rate = DIV_ROUND_UP(clock * bpp, 8); + if (mode_rate > max_rate) + return MODE_CLOCK_HIGH; + + ds_max_dotclock = drm_dp_downstream_max_dotclock(outp->dp.dpcd, outp->dp.downstream_ports); + if (ds_max_dotclock && clock > ds_max_dotclock) + return MODE_CLOCK_HIGH; + + if (clock < min_clock) + return MODE_CLOCK_LOW; - clock = mode->clock * (connector->display_info.bpc * 3) / 10; - ret = nouveau_conn_mode_clock_valid(mode, min_clock, max_clock, - &clock); if (out_clock) *out_clock = clock; - return ret; + + return MODE_OK; } diff --git a/drivers/gpu/drm/nouveau/nouveau_gem.c b/drivers/gpu/drm/nouveau/nouveau_gem.c index 9a421c3949de..dd51cd0ae20c 100644 --- a/drivers/gpu/drm/nouveau/nouveau_gem.c +++ b/drivers/gpu/drm/nouveau/nouveau_gem.c @@ -203,7 +203,8 @@ nouveau_gem_new(struct nouveau_cli *cli, u64 size, int align, uint32_t domain, * to the caller, instead of a normal nouveau_bo ttm reference. */ ret = drm_gem_object_init(drm->dev, &nvbo->bo.base, size); if (ret) { - nouveau_bo_ref(NULL, &nvbo); + drm_gem_object_release(&nvbo->bo.base); + kfree(nvbo); return ret; } diff --git a/drivers/gpu/drm/nouveau/nouveau_mem.c b/drivers/gpu/drm/nouveau/nouveau_mem.c index 0a4c04aaad30..a1049e9feee1 100644 --- a/drivers/gpu/drm/nouveau/nouveau_mem.c +++ b/drivers/gpu/drm/nouveau/nouveau_mem.c @@ -178,6 +178,8 @@ void nouveau_mem_del(struct ttm_resource *reg) { struct nouveau_mem *mem = nouveau_mem(reg); + if (!mem) + return; nouveau_mem_fini(mem); kfree(reg->mm_node); reg->mm_node = NULL; diff --git a/drivers/gpu/drm/nouveau/nouveau_svm.c b/drivers/gpu/drm/nouveau/nouveau_svm.c index 2df1c0460559..4f69e4c3dafd 100644 --- a/drivers/gpu/drm/nouveau/nouveau_svm.c +++ b/drivers/gpu/drm/nouveau/nouveau_svm.c @@ -105,11 +105,11 @@ nouveau_svmm_bind(struct drm_device *dev, void *data, struct nouveau_cli *cli = nouveau_cli(file_priv); struct drm_nouveau_svm_bind *args = data; unsigned target, cmd, priority; - unsigned long addr, end, size; + unsigned long addr, end; struct mm_struct *mm; args->va_start &= PAGE_MASK; - args->va_end &= PAGE_MASK; + args->va_end = ALIGN(args->va_end, PAGE_SIZE); /* Sanity check arguments */ if (args->reserved0 || args->reserved1) @@ -118,8 +118,6 @@ nouveau_svmm_bind(struct drm_device *dev, void *data, return -EINVAL; if (args->va_start >= args->va_end) return -EINVAL; - if (!args->npages) - return -EINVAL; cmd = args->header >> NOUVEAU_SVM_BIND_COMMAND_SHIFT; cmd &= NOUVEAU_SVM_BIND_COMMAND_MASK; @@ -151,12 +149,6 @@ nouveau_svmm_bind(struct drm_device *dev, void *data, if (args->stride) return -EINVAL; - size = ((unsigned long)args->npages) << PAGE_SHIFT; - if ((args->va_start + size) <= args->va_start) - return -EINVAL; - if ((args->va_start + size) > args->va_end) - return -EINVAL; - /* * Ok we are ask to do something sane, for now we only support migrate * commands but we will add things like memory policy (what to do on @@ -171,7 +163,7 @@ nouveau_svmm_bind(struct drm_device *dev, void *data, return -EINVAL; } - for (addr = args->va_start, end = args->va_start + size; addr < end;) { + for (addr = args->va_start, end = args->va_end; addr < end;) { struct vm_area_struct *vma; unsigned long next; diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c b/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c index 9f4ac2672cf2..7851bec5f0e5 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c @@ -2924,17 +2924,34 @@ nvkm_device_del(struct nvkm_device **pdevice) } } +/* returns true if the GPU is in the CPU native byte order */ static inline bool nvkm_device_endianness(struct nvkm_device *device) { - u32 boot1 = nvkm_rd32(device, 0x000004) & 0x01000001; #ifdef __BIG_ENDIAN - if (!boot1) - return false; + const bool big_endian = true; #else - if (boot1) - return false; + const bool big_endian = false; #endif + + /* Read NV_PMC_BOOT_1, and assume non-functional endian switch if it + * doesn't contain the expected values. + */ + u32 pmc_boot_1 = nvkm_rd32(device, 0x000004); + if (pmc_boot_1 && pmc_boot_1 != 0x01000001) + return !big_endian; /* Assume GPU is LE in this case. */ + + /* 0 means LE and 0x01000001 means BE GPU. Condition is true when + * GPU/CPU endianness don't match. + */ + if (big_endian == !pmc_boot_1) { + nvkm_wr32(device, 0x000004, 0x01000001); + nvkm_rd32(device, 0x000000); + if (nvkm_rd32(device, 0x000004) != (big_endian ? 0x01000001 : 0x00000000)) + return !big_endian; /* Assume GPU is LE on any unexpected read-back. */ + } + + /* CPU/GPU endianness should (hopefully) match. */ return true; } @@ -2987,14 +3004,10 @@ nvkm_device_ctor(const struct nvkm_device_func *func, if (detect) { /* switch mmio to cpu's native endianness */ if (!nvkm_device_endianness(device)) { - nvkm_wr32(device, 0x000004, 0x01000001); - nvkm_rd32(device, 0x000000); - if (!nvkm_device_endianness(device)) { - nvdev_error(device, - "GPU not supported on big-endian\n"); - ret = -ENOSYS; - goto done; - } + nvdev_error(device, + "Couldn't switch GPU to CPUs endianess\n"); + ret = -ENOSYS; + goto done; } boot0 = nvkm_rd32(device, 0x000000); @@ -3149,6 +3162,7 @@ nvkm_device_ctor(const struct nvkm_device_func *func, case 0x168: device->chip = &nv168_chipset; break; default: nvdev_error(device, "unknown chipset (%08x)\n", boot0); + ret = -ENODEV; goto done; } diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/instmem/gk20a.c b/drivers/gpu/drm/nouveau/nvkm/subdev/instmem/gk20a.c index 985f2990ab0d..13d4d7ac0697 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/instmem/gk20a.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/instmem/gk20a.c @@ -594,8 +594,7 @@ gk20a_instmem_new(struct nvkm_device *device, int index, nvkm_info(&imem->base.subdev, "using IOMMU\n"); } else { - imem->attrs = DMA_ATTR_NON_CONSISTENT | - DMA_ATTR_WEAK_ORDERING | + imem->attrs = DMA_ATTR_WEAK_ORDERING | DMA_ATTR_WRITE_COMBINE; nvkm_info(&imem->base.subdev, "using DMA API\n"); diff --git a/drivers/gpu/drm/omapdrm/omap_gem.c b/drivers/gpu/drm/omapdrm/omap_gem.c index 979d53a93c2b..d8e09792793a 100644 --- a/drivers/gpu/drm/omapdrm/omap_gem.c +++ b/drivers/gpu/drm/omapdrm/omap_gem.c @@ -1311,10 +1311,9 @@ struct drm_gem_object *omap_gem_new_dmabuf(struct drm_device *dev, size_t size, omap_obj->dma_addr = sg_dma_address(sgt->sgl); } else { /* Create pages list from sgt */ - struct sg_page_iter iter; struct page **pages; unsigned int npages; - unsigned int i = 0; + unsigned int ret; npages = DIV_ROUND_UP(size, PAGE_SIZE); pages = kcalloc(npages, sizeof(*pages), GFP_KERNEL); @@ -1325,14 +1324,9 @@ struct drm_gem_object *omap_gem_new_dmabuf(struct drm_device *dev, size_t size, } omap_obj->pages = pages; - - for_each_sg_page(sgt->sgl, &iter, sgt->orig_nents, 0) { - pages[i++] = sg_page_iter_page(&iter); - if (i > npages) - break; - } - - if (WARN_ON(i != npages)) { + ret = drm_prime_sg_to_page_addr_arrays(sgt, pages, NULL, + npages); + if (ret) { omap_gem_free_object(obj); obj = ERR_PTR(-ENOMEM); goto done; diff --git a/drivers/gpu/drm/panfrost/panfrost_gem.c b/drivers/gpu/drm/panfrost/panfrost_gem.c index cdf1a8754eba..fb9f7334ce18 100644 --- a/drivers/gpu/drm/panfrost/panfrost_gem.c +++ b/drivers/gpu/drm/panfrost/panfrost_gem.c @@ -41,8 +41,8 @@ static void panfrost_gem_free_object(struct drm_gem_object *obj) for (i = 0; i < n_sgt; i++) { if (bo->sgts[i].sgl) { - dma_unmap_sg(pfdev->dev, bo->sgts[i].sgl, - bo->sgts[i].nents, DMA_BIDIRECTIONAL); + dma_unmap_sgtable(pfdev->dev, &bo->sgts[i], + DMA_BIDIRECTIONAL, 0); sg_free_table(&bo->sgts[i]); } } diff --git a/drivers/gpu/drm/panfrost/panfrost_gpu.c b/drivers/gpu/drm/panfrost/panfrost_gpu.c index e1b2a3376624..2aae636f1cf5 100644 --- a/drivers/gpu/drm/panfrost/panfrost_gpu.c +++ b/drivers/gpu/drm/panfrost/panfrost_gpu.c @@ -325,13 +325,13 @@ void panfrost_gpu_power_on(struct panfrost_device *pfdev) /* Just turn on everything for now */ gpu_write(pfdev, L2_PWRON_LO, pfdev->features.l2_present); ret = readl_relaxed_poll_timeout(pfdev->iomem + L2_READY_LO, - val, val == pfdev->features.l2_present, 100, 1000); + val, val == pfdev->features.l2_present, 100, 20000); if (ret) dev_err(pfdev->dev, "error powering up gpu L2"); gpu_write(pfdev, SHADER_PWRON_LO, pfdev->features.shader_present); ret = readl_relaxed_poll_timeout(pfdev->iomem + SHADER_READY_LO, - val, val == pfdev->features.shader_present, 100, 1000); + val, val == pfdev->features.shader_present, 100, 20000); if (ret) dev_err(pfdev->dev, "error powering up gpu shader"); diff --git a/drivers/gpu/drm/panfrost/panfrost_mmu.c b/drivers/gpu/drm/panfrost/panfrost_mmu.c index 8852fd378f7a..be8d68fb0e11 100644 --- a/drivers/gpu/drm/panfrost/panfrost_mmu.c +++ b/drivers/gpu/drm/panfrost/panfrost_mmu.c @@ -253,7 +253,7 @@ static int mmu_map_sg(struct panfrost_device *pfdev, struct panfrost_mmu *mmu, struct io_pgtable_ops *ops = mmu->pgtbl_ops; u64 start_iova = iova; - for_each_sg(sgt->sgl, sgl, sgt->nents, count) { + for_each_sgtable_dma_sg(sgt, sgl, count) { unsigned long paddr = sg_dma_address(sgl); size_t len = sg_dma_len(sgl); @@ -518,10 +518,9 @@ static int panfrost_mmu_map_fault_addr(struct panfrost_device *pfdev, int as, if (ret) goto err_pages; - if (!dma_map_sg(pfdev->dev, sgt->sgl, sgt->nents, DMA_BIDIRECTIONAL)) { - ret = -EINVAL; + ret = dma_map_sgtable(pfdev->dev, sgt, DMA_BIDIRECTIONAL, 0); + if (ret) goto err_map; - } mmu_map_sg(pfdev, bomapping->mmu, addr, IOMMU_WRITE | IOMMU_READ | IOMMU_NOEXEC, sgt); diff --git a/drivers/gpu/drm/radeon/radeon_display.c b/drivers/gpu/drm/radeon/radeon_display.c index 3eacf33bbe48..b79686cf8bdb 100644 --- a/drivers/gpu/drm/radeon/radeon_display.c +++ b/drivers/gpu/drm/radeon/radeon_display.c @@ -928,7 +928,7 @@ static void avivo_get_fb_ref_div(unsigned nom, unsigned den, unsigned post_div, /* get matching reference and feedback divider */ *ref_div = min(max(den/post_div, 1u), ref_div_max); - *fb_div = max(nom * *ref_div * post_div / den, 1u); + *fb_div = DIV_ROUND_CLOSEST(nom * *ref_div * post_div, den); /* limit fb divider to its maximum */ if (*fb_div > fb_div_max) { diff --git a/drivers/gpu/drm/radeon/radeon_pm.c b/drivers/gpu/drm/radeon/radeon_pm.c index 8c5d6fda0d75..05c4196a8212 100644 --- a/drivers/gpu/drm/radeon/radeon_pm.c +++ b/drivers/gpu/drm/radeon/radeon_pm.c @@ -712,6 +712,31 @@ static SENSOR_DEVICE_ATTR(pwm1_enable, S_IRUGO | S_IWUSR, radeon_hwmon_get_pwm1_ static SENSOR_DEVICE_ATTR(pwm1_min, S_IRUGO, radeon_hwmon_get_pwm1_min, NULL, 0); static SENSOR_DEVICE_ATTR(pwm1_max, S_IRUGO, radeon_hwmon_get_pwm1_max, NULL, 0); +static ssize_t radeon_hwmon_show_sclk(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct radeon_device *rdev = dev_get_drvdata(dev); + struct drm_device *ddev = rdev->ddev; + u32 sclk = 0; + + /* Can't get clock frequency when the card is off */ + if ((rdev->flags & RADEON_IS_PX) && + (ddev->switch_power_state != DRM_SWITCH_POWER_ON)) + return -EINVAL; + + if (rdev->asic->dpm.get_current_sclk) + sclk = radeon_dpm_get_current_sclk(rdev); + + /* Value returned by dpm is in 10 KHz units, need to convert it into Hz + for hwmon */ + sclk *= 10000; + + return snprintf(buf, PAGE_SIZE, "%u\n", sclk); +} + +static SENSOR_DEVICE_ATTR(freq1_input, S_IRUGO, radeon_hwmon_show_sclk, NULL, + 0); + static struct attribute *hwmon_attributes[] = { &sensor_dev_attr_temp1_input.dev_attr.attr, @@ -721,6 +746,7 @@ static struct attribute *hwmon_attributes[] = { &sensor_dev_attr_pwm1_enable.dev_attr.attr, &sensor_dev_attr_pwm1_min.dev_attr.attr, &sensor_dev_attr_pwm1_max.dev_attr.attr, + &sensor_dev_attr_freq1_input.dev_attr.attr, NULL }; @@ -738,7 +764,8 @@ static umode_t hwmon_attributes_visible(struct kobject *kobj, attr == &sensor_dev_attr_pwm1.dev_attr.attr || attr == &sensor_dev_attr_pwm1_enable.dev_attr.attr || attr == &sensor_dev_attr_pwm1_max.dev_attr.attr || - attr == &sensor_dev_attr_pwm1_min.dev_attr.attr)) + attr == &sensor_dev_attr_pwm1_min.dev_attr.attr || + attr == &sensor_dev_attr_freq1_input.dev_attr.attr)) return 0; /* Skip fan attributes if fan is not present */ diff --git a/drivers/gpu/drm/radeon/radeon_vm.c b/drivers/gpu/drm/radeon/radeon_vm.c index ebad27c91a0d..27b14eff532c 100644 --- a/drivers/gpu/drm/radeon/radeon_vm.c +++ b/drivers/gpu/drm/radeon/radeon_vm.c @@ -188,7 +188,7 @@ struct radeon_fence *radeon_vm_grab_id(struct radeon_device *rdev, vm_id->last_id_use == rdev->vm_manager.active[vm_id->id]) return NULL; - /* we definately need to flush */ + /* we definitely need to flush */ vm_id->pd_gpu_addr = ~0ll; /* skip over VMID 0, since it is the system VM */ diff --git a/drivers/gpu/drm/radeon/uvd_v1_0.c b/drivers/gpu/drm/radeon/uvd_v1_0.c index 800721153d51..58557c2263a7 100644 --- a/drivers/gpu/drm/radeon/uvd_v1_0.c +++ b/drivers/gpu/drm/radeon/uvd_v1_0.c @@ -117,7 +117,7 @@ int uvd_v1_0_resume(struct radeon_device *rdev) if (r) return r; - /* programm the VCPU memory controller bits 0-27 */ + /* program the VCPU memory controller bits 0-27 */ addr = (rdev->uvd.gpu_addr >> 3) + 16; size = RADEON_GPU_PAGE_ALIGN(rdev->uvd_fw->size) >> 3; WREG32(UVD_VCPU_CACHE_OFFSET0, addr); @@ -360,7 +360,7 @@ int uvd_v1_0_start(struct radeon_device *rdev) /* Set the write pointer delay */ WREG32(UVD_RBC_RB_WPTR_CNTL, 0); - /* programm the 4GB memory segment for rptr and ring buffer */ + /* program the 4GB memory segment for rptr and ring buffer */ WREG32(UVD_LMI_EXT40_ADDR, upper_32_bits(ring->gpu_addr) | (0x7 << 16) | (0x1 << 31)); diff --git a/drivers/gpu/drm/radeon/uvd_v2_2.c b/drivers/gpu/drm/radeon/uvd_v2_2.c index 23b18edda20e..6266167886d9 100644 --- a/drivers/gpu/drm/radeon/uvd_v2_2.c +++ b/drivers/gpu/drm/radeon/uvd_v2_2.c @@ -109,7 +109,7 @@ int uvd_v2_2_resume(struct radeon_device *rdev) if (r) return r; - /* programm the VCPU memory controller bits 0-27 */ + /* program the VCPU memory controller bits 0-27 */ addr = rdev->uvd.gpu_addr >> 3; size = RADEON_GPU_PAGE_ALIGN(rdev->uvd_fw->size + 4) >> 3; WREG32(UVD_VCPU_CACHE_OFFSET0, addr); diff --git a/drivers/gpu/drm/radeon/uvd_v4_2.c b/drivers/gpu/drm/radeon/uvd_v4_2.c index dc54fa4aaea8..f9e97fa63674 100644 --- a/drivers/gpu/drm/radeon/uvd_v4_2.c +++ b/drivers/gpu/drm/radeon/uvd_v4_2.c @@ -40,7 +40,7 @@ int uvd_v4_2_resume(struct radeon_device *rdev) uint64_t addr; uint32_t size; - /* programm the VCPU memory controller bits 0-27 */ + /* program the VCPU memory controller bits 0-27 */ /* skip over the header of the new firmware format */ if (rdev->uvd.fw_header_present) diff --git a/drivers/gpu/drm/rcar-du/Kconfig b/drivers/gpu/drm/rcar-du/Kconfig index f65d1489dc50..b47e74421e34 100644 --- a/drivers/gpu/drm/rcar-du/Kconfig +++ b/drivers/gpu/drm/rcar-du/Kconfig @@ -22,11 +22,11 @@ config DRM_RCAR_CMM Enable support for R-Car Color Management Module (CMM). config DRM_RCAR_DW_HDMI - tristate "R-Car DU Gen3 HDMI Encoder Support" + tristate "R-Car Gen3 and RZ/G2 DU HDMI Encoder Support" depends on DRM && OF select DRM_DW_HDMI help - Enable support for R-Car Gen3 internal HDMI encoder. + Enable support for R-Car Gen3 or RZ/G2 internal HDMI encoder. config DRM_RCAR_LVDS tristate "R-Car DU LVDS Encoder Support" @@ -49,3 +49,4 @@ config DRM_RCAR_VSP config DRM_RCAR_WRITEBACK bool default y if ARM64 + depends on DRM_RCAR_DU diff --git a/drivers/gpu/drm/rcar-du/rcar_du_drv.c b/drivers/gpu/drm/rcar-du/rcar_du_drv.c index f53b0ec71085..447be991fa25 100644 --- a/drivers/gpu/drm/rcar-du/rcar_du_drv.c +++ b/drivers/gpu/drm/rcar-du/rcar_du_drv.c @@ -186,6 +186,35 @@ static const struct rcar_du_device_info rcar_du_r8a774c0_info = { .lvds_clk_mask = BIT(1) | BIT(0), }; +static const struct rcar_du_device_info rcar_du_r8a774e1_info = { + .gen = 3, + .features = RCAR_DU_FEATURE_CRTC_IRQ_CLOCK + | RCAR_DU_FEATURE_VSP1_SOURCE + | RCAR_DU_FEATURE_INTERLACED + | RCAR_DU_FEATURE_TVM_SYNC, + .channels_mask = BIT(3) | BIT(1) | BIT(0), + .routes = { + /* + * R8A774E1 has one RGB output, one LVDS output and one HDMI + * output. + */ + [RCAR_DU_OUTPUT_DPAD0] = { + .possible_crtcs = BIT(2), + .port = 0, + }, + [RCAR_DU_OUTPUT_HDMI0] = { + .possible_crtcs = BIT(1), + .port = 1, + }, + [RCAR_DU_OUTPUT_LVDS0] = { + .possible_crtcs = BIT(0), + .port = 2, + }, + }, + .num_lvds = 1, + .dpll_mask = BIT(1), +}; + static const struct rcar_du_device_info rcar_du_r8a7779_info = { .gen = 1, .features = RCAR_DU_FEATURE_INTERLACED @@ -216,8 +245,9 @@ static const struct rcar_du_device_info rcar_du_r8a7790_info = { .channels_mask = BIT(2) | BIT(1) | BIT(0), .routes = { /* - * R8A7790 has one RGB output, two LVDS outputs and one - * (currently unsupported) TCON output. + * R8A7742 and R8A7790 each have one RGB output and two LVDS + * outputs. Additionally R8A7790 supports one TCON output + * (currently unsupported by the driver). */ [RCAR_DU_OUTPUT_DPAD0] = { .possible_crtcs = BIT(2) | BIT(1) | BIT(0), @@ -443,6 +473,7 @@ static const struct rcar_du_device_info rcar_du_r8a7799x_info = { }; static const struct of_device_id rcar_du_of_table[] = { + { .compatible = "renesas,du-r8a7742", .data = &rcar_du_r8a7790_info }, { .compatible = "renesas,du-r8a7743", .data = &rzg1_du_r8a7743_info }, { .compatible = "renesas,du-r8a7744", .data = &rzg1_du_r8a7743_info }, { .compatible = "renesas,du-r8a7745", .data = &rzg1_du_r8a7745_info }, @@ -450,6 +481,7 @@ static const struct of_device_id rcar_du_of_table[] = { { .compatible = "renesas,du-r8a774a1", .data = &rcar_du_r8a774a1_info }, { .compatible = "renesas,du-r8a774b1", .data = &rcar_du_r8a774b1_info }, { .compatible = "renesas,du-r8a774c0", .data = &rcar_du_r8a774c0_info }, + { .compatible = "renesas,du-r8a774e1", .data = &rcar_du_r8a774e1_info }, { .compatible = "renesas,du-r8a7779", .data = &rcar_du_r8a7779_info }, { .compatible = "renesas,du-r8a7790", .data = &rcar_du_r8a7790_info }, { .compatible = "renesas,du-r8a7791", .data = &rcar_du_r8a7791_info }, @@ -458,6 +490,7 @@ static const struct of_device_id rcar_du_of_table[] = { { .compatible = "renesas,du-r8a7794", .data = &rcar_du_r8a7794_info }, { .compatible = "renesas,du-r8a7795", .data = &rcar_du_r8a7795_info }, { .compatible = "renesas,du-r8a7796", .data = &rcar_du_r8a7796_info }, + { .compatible = "renesas,du-r8a77961", .data = &rcar_du_r8a7796_info }, { .compatible = "renesas,du-r8a77965", .data = &rcar_du_r8a77965_info }, { .compatible = "renesas,du-r8a77970", .data = &rcar_du_r8a77970_info }, { .compatible = "renesas,du-r8a77980", .data = &rcar_du_r8a77970_info }, diff --git a/drivers/gpu/drm/rcar-du/rcar_du_kms.c b/drivers/gpu/drm/rcar-du/rcar_du_kms.c index 482329102f19..72dda446355f 100644 --- a/drivers/gpu/drm/rcar-du/rcar_du_kms.c +++ b/drivers/gpu/drm/rcar-du/rcar_du_kms.c @@ -40,6 +40,7 @@ static const struct rcar_du_format_info rcar_du_format_infos[] = { .v4l2 = V4L2_PIX_FMT_RGB565, .bpp = 16, .planes = 1, + .hsub = 1, .pnmr = PnMR_SPIM_TP | PnMR_DDDF_16BPP, .edf = PnDDCR4_EDF_NONE, }, { @@ -47,6 +48,7 @@ static const struct rcar_du_format_info rcar_du_format_infos[] = { .v4l2 = V4L2_PIX_FMT_ARGB555, .bpp = 16, .planes = 1, + .hsub = 1, .pnmr = PnMR_SPIM_ALP | PnMR_DDDF_ARGB, .edf = PnDDCR4_EDF_NONE, }, { @@ -61,6 +63,7 @@ static const struct rcar_du_format_info rcar_du_format_infos[] = { .v4l2 = V4L2_PIX_FMT_XBGR32, .bpp = 32, .planes = 1, + .hsub = 1, .pnmr = PnMR_SPIM_TP | PnMR_DDDF_16BPP, .edf = PnDDCR4_EDF_RGB888, }, { @@ -68,6 +71,7 @@ static const struct rcar_du_format_info rcar_du_format_infos[] = { .v4l2 = V4L2_PIX_FMT_ABGR32, .bpp = 32, .planes = 1, + .hsub = 1, .pnmr = PnMR_SPIM_ALP | PnMR_DDDF_16BPP, .edf = PnDDCR4_EDF_ARGB8888, }, { @@ -75,6 +79,7 @@ static const struct rcar_du_format_info rcar_du_format_infos[] = { .v4l2 = V4L2_PIX_FMT_UYVY, .bpp = 16, .planes = 1, + .hsub = 2, .pnmr = PnMR_SPIM_TP_OFF | PnMR_DDDF_YC, .edf = PnDDCR4_EDF_NONE, }, { @@ -82,6 +87,7 @@ static const struct rcar_du_format_info rcar_du_format_infos[] = { .v4l2 = V4L2_PIX_FMT_YUYV, .bpp = 16, .planes = 1, + .hsub = 2, .pnmr = PnMR_SPIM_TP_OFF | PnMR_DDDF_YC, .edf = PnDDCR4_EDF_NONE, }, { @@ -89,6 +95,7 @@ static const struct rcar_du_format_info rcar_du_format_infos[] = { .v4l2 = V4L2_PIX_FMT_NV12M, .bpp = 12, .planes = 2, + .hsub = 2, .pnmr = PnMR_SPIM_TP_OFF | PnMR_DDDF_YC, .edf = PnDDCR4_EDF_NONE, }, { @@ -96,6 +103,7 @@ static const struct rcar_du_format_info rcar_du_format_infos[] = { .v4l2 = V4L2_PIX_FMT_NV21M, .bpp = 12, .planes = 2, + .hsub = 2, .pnmr = PnMR_SPIM_TP_OFF | PnMR_DDDF_YC, .edf = PnDDCR4_EDF_NONE, }, { @@ -103,6 +111,7 @@ static const struct rcar_du_format_info rcar_du_format_infos[] = { .v4l2 = V4L2_PIX_FMT_NV16M, .bpp = 16, .planes = 2, + .hsub = 2, .pnmr = PnMR_SPIM_TP_OFF | PnMR_DDDF_YC, .edf = PnDDCR4_EDF_NONE, }, @@ -115,156 +124,187 @@ static const struct rcar_du_format_info rcar_du_format_infos[] = { .v4l2 = V4L2_PIX_FMT_RGB332, .bpp = 8, .planes = 1, + .hsub = 1, }, { .fourcc = DRM_FORMAT_ARGB4444, .v4l2 = V4L2_PIX_FMT_ARGB444, .bpp = 16, .planes = 1, + .hsub = 1, }, { .fourcc = DRM_FORMAT_XRGB4444, .v4l2 = V4L2_PIX_FMT_XRGB444, .bpp = 16, .planes = 1, + .hsub = 1, }, { .fourcc = DRM_FORMAT_RGBA4444, .v4l2 = V4L2_PIX_FMT_RGBA444, .bpp = 16, .planes = 1, + .hsub = 1, }, { .fourcc = DRM_FORMAT_RGBX4444, .v4l2 = V4L2_PIX_FMT_RGBX444, .bpp = 16, .planes = 1, + .hsub = 1, }, { .fourcc = DRM_FORMAT_ABGR4444, .v4l2 = V4L2_PIX_FMT_ABGR444, .bpp = 16, .planes = 1, + .hsub = 1, }, { .fourcc = DRM_FORMAT_XBGR4444, .v4l2 = V4L2_PIX_FMT_XBGR444, .bpp = 16, .planes = 1, + .hsub = 1, }, { .fourcc = DRM_FORMAT_BGRA4444, .v4l2 = V4L2_PIX_FMT_BGRA444, .bpp = 16, .planes = 1, + .hsub = 1, }, { .fourcc = DRM_FORMAT_BGRX4444, .v4l2 = V4L2_PIX_FMT_BGRX444, .bpp = 16, .planes = 1, + .hsub = 1, }, { .fourcc = DRM_FORMAT_RGBA5551, .v4l2 = V4L2_PIX_FMT_RGBA555, .bpp = 16, .planes = 1, + .hsub = 1, }, { .fourcc = DRM_FORMAT_RGBX5551, .v4l2 = V4L2_PIX_FMT_RGBX555, .bpp = 16, .planes = 1, + .hsub = 1, }, { .fourcc = DRM_FORMAT_ABGR1555, .v4l2 = V4L2_PIX_FMT_ABGR555, .bpp = 16, .planes = 1, + .hsub = 1, }, { .fourcc = DRM_FORMAT_XBGR1555, .v4l2 = V4L2_PIX_FMT_XBGR555, .bpp = 16, .planes = 1, + .hsub = 1, }, { .fourcc = DRM_FORMAT_BGRA5551, .v4l2 = V4L2_PIX_FMT_BGRA555, .bpp = 16, .planes = 1, + .hsub = 1, }, { .fourcc = DRM_FORMAT_BGRX5551, .v4l2 = V4L2_PIX_FMT_BGRX555, .bpp = 16, .planes = 1, + .hsub = 1, }, { .fourcc = DRM_FORMAT_BGR888, .v4l2 = V4L2_PIX_FMT_RGB24, .bpp = 24, .planes = 1, + .hsub = 1, }, { .fourcc = DRM_FORMAT_RGB888, .v4l2 = V4L2_PIX_FMT_BGR24, .bpp = 24, .planes = 1, + .hsub = 1, }, { .fourcc = DRM_FORMAT_RGBA8888, .v4l2 = V4L2_PIX_FMT_BGRA32, .bpp = 32, .planes = 1, + .hsub = 1, }, { .fourcc = DRM_FORMAT_RGBX8888, .v4l2 = V4L2_PIX_FMT_BGRX32, .bpp = 32, .planes = 1, + .hsub = 1, }, { .fourcc = DRM_FORMAT_ABGR8888, .v4l2 = V4L2_PIX_FMT_RGBA32, .bpp = 32, .planes = 1, + .hsub = 1, }, { .fourcc = DRM_FORMAT_XBGR8888, .v4l2 = V4L2_PIX_FMT_RGBX32, .bpp = 32, .planes = 1, + .hsub = 1, }, { .fourcc = DRM_FORMAT_BGRA8888, .v4l2 = V4L2_PIX_FMT_ARGB32, .bpp = 32, .planes = 1, + .hsub = 1, }, { .fourcc = DRM_FORMAT_BGRX8888, .v4l2 = V4L2_PIX_FMT_XRGB32, .bpp = 32, .planes = 1, + .hsub = 1, }, { .fourcc = DRM_FORMAT_YVYU, .v4l2 = V4L2_PIX_FMT_YVYU, .bpp = 16, .planes = 1, + .hsub = 2, }, { .fourcc = DRM_FORMAT_NV61, .v4l2 = V4L2_PIX_FMT_NV61M, .bpp = 16, .planes = 2, + .hsub = 2, }, { .fourcc = DRM_FORMAT_YUV420, .v4l2 = V4L2_PIX_FMT_YUV420M, .bpp = 12, .planes = 3, + .hsub = 2, }, { .fourcc = DRM_FORMAT_YVU420, .v4l2 = V4L2_PIX_FMT_YVU420M, .bpp = 12, .planes = 3, + .hsub = 2, }, { .fourcc = DRM_FORMAT_YUV422, .v4l2 = V4L2_PIX_FMT_YUV422M, .bpp = 16, .planes = 3, + .hsub = 2, }, { .fourcc = DRM_FORMAT_YVU422, .v4l2 = V4L2_PIX_FMT_YVU422M, .bpp = 16, .planes = 3, + .hsub = 2, }, { .fourcc = DRM_FORMAT_YUV444, .v4l2 = V4L2_PIX_FMT_YUV444M, .bpp = 24, .planes = 3, + .hsub = 1, }, { .fourcc = DRM_FORMAT_YVU444, .v4l2 = V4L2_PIX_FMT_YVU444M, .bpp = 24, .planes = 3, + .hsub = 1, }, }; @@ -311,6 +351,7 @@ rcar_du_fb_create(struct drm_device *dev, struct drm_file *file_priv, { struct rcar_du_device *rcdu = dev->dev_private; const struct rcar_du_format_info *format; + unsigned int chroma_pitch; unsigned int max_pitch; unsigned int align; unsigned int i; @@ -353,10 +394,19 @@ rcar_du_fb_create(struct drm_device *dev, struct drm_file *file_priv, return ERR_PTR(-EINVAL); } + /* + * Calculate the chroma plane(s) pitch using the horizontal subsampling + * factor. For semi-planar formats, the U and V planes are combined, the + * pitch must thus be doubled. + */ + chroma_pitch = mode_cmd->pitches[0] / format->hsub; + if (format->planes == 2) + chroma_pitch *= 2; + for (i = 1; i < format->planes; ++i) { - if (mode_cmd->pitches[i] != mode_cmd->pitches[0]) { + if (mode_cmd->pitches[i] != chroma_pitch) { dev_dbg(dev->dev, - "luma and chroma pitches do not match\n"); + "luma and chroma pitches are not compatible\n"); return ERR_PTR(-EINVAL); } } diff --git a/drivers/gpu/drm/rcar-du/rcar_du_kms.h b/drivers/gpu/drm/rcar-du/rcar_du_kms.h index 0346504d8c59..8f5fff176754 100644 --- a/drivers/gpu/drm/rcar-du/rcar_du_kms.h +++ b/drivers/gpu/drm/rcar-du/rcar_du_kms.h @@ -22,6 +22,7 @@ struct rcar_du_format_info { u32 v4l2; unsigned int bpp; unsigned int planes; + unsigned int hsub; unsigned int pnmr; unsigned int edf; }; diff --git a/drivers/gpu/drm/rcar-du/rcar_du_vsp.c b/drivers/gpu/drm/rcar-du/rcar_du_vsp.c index f1a81c9b184d..f6a69aa116e6 100644 --- a/drivers/gpu/drm/rcar-du/rcar_du_vsp.c +++ b/drivers/gpu/drm/rcar-du/rcar_du_vsp.c @@ -13,6 +13,7 @@ #include <drm/drm_fourcc.h> #include <drm/drm_gem_cma_helper.h> #include <drm/drm_gem_framebuffer_helper.h> +#include <drm/drm_managed.h> #include <drm/drm_plane_helper.h> #include <drm/drm_vblank.h> @@ -197,9 +198,8 @@ int rcar_du_vsp_map_fb(struct rcar_du_vsp *vsp, struct drm_framebuffer *fb, goto fail; ret = vsp1_du_map_sg(vsp->vsp, sgt); - if (!ret) { + if (ret) { sg_free_table(sgt); - ret = -ENOMEM; goto fail; } } @@ -279,7 +279,7 @@ static void rcar_du_vsp_plane_atomic_update(struct drm_plane *plane, if (plane->state->visible) rcar_du_vsp_plane_setup(rplane); - else + else if (old_state->crtc) vsp1_du_atomic_update(rplane->vsp->vsp, crtc->vsp_pipe, rplane->index, NULL); } @@ -341,6 +341,13 @@ static const struct drm_plane_funcs rcar_du_vsp_plane_funcs = { .atomic_destroy_state = rcar_du_vsp_plane_atomic_destroy_state, }; +static void rcar_du_vsp_cleanup(struct drm_device *dev, void *res) +{ + struct rcar_du_vsp *vsp = res; + + put_device(vsp->vsp); +} + int rcar_du_vsp_init(struct rcar_du_vsp *vsp, struct device_node *np, unsigned int crtcs) { @@ -357,6 +364,10 @@ int rcar_du_vsp_init(struct rcar_du_vsp *vsp, struct device_node *np, vsp->vsp = &pdev->dev; + ret = drmm_add_action(rcdu->ddev, rcar_du_vsp_cleanup, vsp); + if (ret < 0) + return ret; + ret = vsp1_du_init(vsp->vsp); if (ret < 0) return ret; diff --git a/drivers/gpu/drm/rcar-du/rcar_lvds.c b/drivers/gpu/drm/rcar-du/rcar_lvds.c index bced729a96fe..70dbbe44bb23 100644 --- a/drivers/gpu/drm/rcar-du/rcar_lvds.c +++ b/drivers/gpu/drm/rcar-du/rcar_lvds.c @@ -978,11 +978,13 @@ static const struct rcar_lvds_device_info rcar_lvds_r8a77995_info = { }; static const struct of_device_id rcar_lvds_of_table[] = { + { .compatible = "renesas,r8a7742-lvds", .data = &rcar_lvds_gen2_info }, { .compatible = "renesas,r8a7743-lvds", .data = &rcar_lvds_gen2_info }, { .compatible = "renesas,r8a7744-lvds", .data = &rcar_lvds_gen2_info }, { .compatible = "renesas,r8a774a1-lvds", .data = &rcar_lvds_gen3_info }, { .compatible = "renesas,r8a774b1-lvds", .data = &rcar_lvds_gen3_info }, { .compatible = "renesas,r8a774c0-lvds", .data = &rcar_lvds_r8a77990_info }, + { .compatible = "renesas,r8a774e1-lvds", .data = &rcar_lvds_gen3_info }, { .compatible = "renesas,r8a7790-lvds", .data = &rcar_lvds_gen2_info }, { .compatible = "renesas,r8a7791-lvds", .data = &rcar_lvds_gen2_info }, { .compatible = "renesas,r8a7793-lvds", .data = &rcar_lvds_gen2_info }, diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_gem.c b/drivers/gpu/drm/rockchip/rockchip_drm_gem.c index 6da15faf0192..7d5ebb10323b 100644 --- a/drivers/gpu/drm/rockchip/rockchip_drm_gem.c +++ b/drivers/gpu/drm/rockchip/rockchip_drm_gem.c @@ -37,8 +37,8 @@ static int rockchip_gem_iommu_map(struct rockchip_gem_object *rk_obj) rk_obj->dma_addr = rk_obj->mm.start; - ret = iommu_map_sg(private->domain, rk_obj->dma_addr, rk_obj->sgt->sgl, - rk_obj->sgt->nents, prot); + ret = iommu_map_sgtable(private->domain, rk_obj->dma_addr, rk_obj->sgt, + prot); if (ret < rk_obj->base.size) { DRM_ERROR("failed to map buffer: size=%zd request_size=%zd\n", ret, rk_obj->base.size); @@ -100,11 +100,10 @@ static int rockchip_gem_get_pages(struct rockchip_gem_object *rk_obj) * TODO: Replace this by drm_clflush_sg() once it can be implemented * without relying on symbols that are not exported. */ - for_each_sg(rk_obj->sgt->sgl, s, rk_obj->sgt->nents, i) + for_each_sgtable_sg(rk_obj->sgt, s, i) sg_dma_address(s) = sg_phys(s); - dma_sync_sg_for_device(drm->dev, rk_obj->sgt->sgl, rk_obj->sgt->nents, - DMA_TO_DEVICE); + dma_sync_sgtable_for_device(drm->dev, rk_obj->sgt, DMA_TO_DEVICE); return 0; @@ -362,8 +361,8 @@ void rockchip_gem_free_object(struct drm_gem_object *obj) if (private->domain) { rockchip_gem_iommu_unmap(rk_obj); } else { - dma_unmap_sg(drm->dev, rk_obj->sgt->sgl, - rk_obj->sgt->nents, DMA_BIDIRECTIONAL); + dma_unmap_sgtable(drm->dev, rk_obj->sgt, + DMA_BIDIRECTIONAL, 0); } drm_prime_gem_destroy(obj, rk_obj->sgt); } else { @@ -472,23 +471,6 @@ struct sg_table *rockchip_gem_prime_get_sg_table(struct drm_gem_object *obj) return sgt; } -static unsigned long rockchip_sg_get_contiguous_size(struct sg_table *sgt, - int count) -{ - struct scatterlist *s; - dma_addr_t expected = sg_dma_address(sgt->sgl); - unsigned int i; - unsigned long size = 0; - - for_each_sg(sgt->sgl, s, count, i) { - if (sg_dma_address(s) != expected) - break; - expected = sg_dma_address(s) + sg_dma_len(s); - size += sg_dma_len(s); - } - return size; -} - static int rockchip_gem_iommu_map_sg(struct drm_device *drm, struct dma_buf_attachment *attach, @@ -505,15 +487,13 @@ rockchip_gem_dma_map_sg(struct drm_device *drm, struct sg_table *sg, struct rockchip_gem_object *rk_obj) { - int count = dma_map_sg(drm->dev, sg->sgl, sg->nents, - DMA_BIDIRECTIONAL); - if (!count) - return -EINVAL; + int err = dma_map_sgtable(drm->dev, sg, DMA_BIDIRECTIONAL, 0); + if (err) + return err; - if (rockchip_sg_get_contiguous_size(sg, count) < attach->dmabuf->size) { + if (drm_prime_get_contiguous_size(sg) < attach->dmabuf->size) { DRM_ERROR("failed to map sg_table to contiguous linear address.\n"); - dma_unmap_sg(drm->dev, sg->sgl, sg->nents, - DMA_BIDIRECTIONAL); + dma_unmap_sgtable(drm->dev, sg, DMA_BIDIRECTIONAL, 0); return -EINVAL; } diff --git a/drivers/gpu/drm/scheduler/sched_fence.c b/drivers/gpu/drm/scheduler/sched_fence.c index 8b45c3a1b84e..69de2c76731f 100644 --- a/drivers/gpu/drm/scheduler/sched_fence.c +++ b/drivers/gpu/drm/scheduler/sched_fence.c @@ -101,7 +101,7 @@ static void drm_sched_fence_free(struct rcu_head *rcu) /** * drm_sched_fence_release_scheduled - callback that fence can be freed * - * @fence: fence + * @f: fence * * This function is called when the reference count becomes zero. * It just RCU schedules freeing up the fence. diff --git a/drivers/gpu/drm/selftests/test-drm_dp_mst_helper.c b/drivers/gpu/drm/selftests/test-drm_dp_mst_helper.c index bd990d178765..1d696ec001cf 100644 --- a/drivers/gpu/drm/selftests/test-drm_dp_mst_helper.c +++ b/drivers/gpu/drm/selftests/test-drm_dp_mst_helper.c @@ -5,6 +5,8 @@ #define PREFIX_STR "[drm_dp_mst_helper]" +#include <linux/random.h> + #include <drm/drm_dp_mst_helper.h> #include <drm/drm_print.h> @@ -237,6 +239,21 @@ int igt_dp_mst_sideband_msg_req_decode(void *unused) in.u.i2c_write.bytes = data; DO_TEST(); + in.req_type = DP_QUERY_STREAM_ENC_STATUS; + in.u.enc_status.stream_id = 1; + DO_TEST(); + get_random_bytes(in.u.enc_status.client_id, + sizeof(in.u.enc_status.client_id)); + DO_TEST(); + in.u.enc_status.stream_event = 3; + DO_TEST(); + in.u.enc_status.valid_stream_event = 0; + DO_TEST(); + in.u.enc_status.stream_behavior = 3; + DO_TEST(); + in.u.enc_status.valid_stream_behavior = 1; + DO_TEST(); + #undef DO_TEST return 0; } diff --git a/drivers/gpu/drm/sun4i/sun4i_backend.c b/drivers/gpu/drm/sun4i/sun4i_backend.c index 2f26f85ef538..77497b45f9a2 100644 --- a/drivers/gpu/drm/sun4i/sun4i_backend.c +++ b/drivers/gpu/drm/sun4i/sun4i_backend.c @@ -11,6 +11,7 @@ #include <linux/module.h> #include <linux/of_device.h> #include <linux/of_graph.h> +#include <linux/dma-mapping.h> #include <linux/platform_device.h> #include <linux/reset.h> @@ -810,8 +811,13 @@ static int sun4i_backend_bind(struct device *dev, struct device *master, * because of an old DT, we need to set the DMA offset by hand * on our device since the RAM mapping is at 0 for the DMA bus, * unlike the CPU. + * + * XXX(hch): this has no business in a driver and needs to move + * to the device tree. */ - drm->dev->dma_pfn_offset = PHYS_PFN_OFFSET; + ret = dma_direct_set_offset(drm->dev, PHYS_OFFSET, 0, SZ_4G); + if (ret) + return ret; } backend->engine.node = dev->of_node; diff --git a/drivers/gpu/drm/sun4i/sun4i_frontend.c b/drivers/gpu/drm/sun4i/sun4i_frontend.c index b51cc685c13a..edb60ae0a9b7 100644 --- a/drivers/gpu/drm/sun4i/sun4i_frontend.c +++ b/drivers/gpu/drm/sun4i/sun4i_frontend.c @@ -407,6 +407,7 @@ int sun4i_frontend_update_formats(struct sun4i_frontend *frontend, struct drm_framebuffer *fb = state->fb; const struct drm_format_info *format = fb->format; uint64_t modifier = fb->modifier; + unsigned int ch1_phase_idx; u32 out_fmt_val; u32 in_fmt_val, in_mod_val, in_ps_val; unsigned int i; @@ -442,18 +443,19 @@ int sun4i_frontend_update_formats(struct sun4i_frontend *frontend, * I have no idea what this does exactly, but it seems to be * related to the scaler FIR filter phase parameters. */ + ch1_phase_idx = (format->num_planes > 1) ? 1 : 0; regmap_write(frontend->regs, SUN4I_FRONTEND_CH0_HORZPHASE_REG, - frontend->data->ch_phase[0].horzphase); + frontend->data->ch_phase[0]); regmap_write(frontend->regs, SUN4I_FRONTEND_CH1_HORZPHASE_REG, - frontend->data->ch_phase[1].horzphase); + frontend->data->ch_phase[ch1_phase_idx]); regmap_write(frontend->regs, SUN4I_FRONTEND_CH0_VERTPHASE0_REG, - frontend->data->ch_phase[0].vertphase[0]); + frontend->data->ch_phase[0]); regmap_write(frontend->regs, SUN4I_FRONTEND_CH1_VERTPHASE0_REG, - frontend->data->ch_phase[1].vertphase[0]); + frontend->data->ch_phase[ch1_phase_idx]); regmap_write(frontend->regs, SUN4I_FRONTEND_CH0_VERTPHASE1_REG, - frontend->data->ch_phase[0].vertphase[1]); + frontend->data->ch_phase[0]); regmap_write(frontend->regs, SUN4I_FRONTEND_CH1_VERTPHASE1_REG, - frontend->data->ch_phase[1].vertphase[1]); + frontend->data->ch_phase[ch1_phase_idx]); /* * Checking the input format is sufficient since we currently only @@ -687,30 +689,12 @@ static const struct dev_pm_ops sun4i_frontend_pm_ops = { }; static const struct sun4i_frontend_data sun4i_a10_frontend = { - .ch_phase = { - { - .horzphase = 0, - .vertphase = { 0, 0 }, - }, - { - .horzphase = 0xfc000, - .vertphase = { 0xfc000, 0xfc000 }, - }, - }, + .ch_phase = { 0x000, 0xfc000 }, .has_coef_rdy = true, }; static const struct sun4i_frontend_data sun8i_a33_frontend = { - .ch_phase = { - { - .horzphase = 0x400, - .vertphase = { 0x400, 0x400 }, - }, - { - .horzphase = 0x400, - .vertphase = { 0x400, 0x400 }, - }, - }, + .ch_phase = { 0x400, 0xfc400 }, .has_coef_access_ctrl = true, }; diff --git a/drivers/gpu/drm/sun4i/sun4i_frontend.h b/drivers/gpu/drm/sun4i/sun4i_frontend.h index 0c382c1ddb0f..2e7b76e50c2b 100644 --- a/drivers/gpu/drm/sun4i/sun4i_frontend.h +++ b/drivers/gpu/drm/sun4i/sun4i_frontend.h @@ -115,11 +115,7 @@ struct reset_control; struct sun4i_frontend_data { bool has_coef_access_ctrl; bool has_coef_rdy; - - struct { - u32 horzphase; - u32 vertphase[2]; - } ch_phase[2]; + u32 ch_phase[2]; }; struct sun4i_frontend { diff --git a/drivers/gpu/drm/sun4i/sun8i_csc.h b/drivers/gpu/drm/sun4i/sun8i_csc.h index f42441b1b14d..a55a38ad849c 100644 --- a/drivers/gpu/drm/sun4i/sun8i_csc.h +++ b/drivers/gpu/drm/sun4i/sun8i_csc.h @@ -12,7 +12,7 @@ struct sun8i_mixer; /* VI channel CSC units offsets */ #define CCSC00_OFFSET 0xAA050 -#define CCSC01_OFFSET 0xFA000 +#define CCSC01_OFFSET 0xFA050 #define CCSC10_OFFSET 0xA0000 #define CCSC11_OFFSET 0xF0000 diff --git a/drivers/gpu/drm/sun4i/sun8i_mixer.c b/drivers/gpu/drm/sun4i/sun8i_mixer.c index 4b59806b30df..5b42cf25cc86 100644 --- a/drivers/gpu/drm/sun4i/sun8i_mixer.c +++ b/drivers/gpu/drm/sun4i/sun8i_mixer.c @@ -307,7 +307,7 @@ static const struct regmap_config sun8i_mixer_regmap_config = { .reg_bits = 32, .val_bits = 32, .reg_stride = 4, - .max_register = 0xbfffc, /* guessed */ + .max_register = 0xffffc, /* guessed */ }; static int sun8i_mixer_of_get_id(struct device_node *node) diff --git a/drivers/gpu/drm/tegra/drm.h b/drivers/gpu/drm/tegra/drm.h index b25443255be6..f38de08e0c95 100644 --- a/drivers/gpu/drm/tegra/drm.h +++ b/drivers/gpu/drm/tegra/drm.h @@ -12,6 +12,7 @@ #include <linux/gpio/consumer.h> #include <drm/drm_atomic.h> +#include <drm/drm_bridge.h> #include <drm/drm_edid.h> #include <drm/drm_encoder.h> #include <drm/drm_fb_helper.h> @@ -116,6 +117,7 @@ struct tegra_output { struct device_node *of_node; struct device *dev; + struct drm_bridge *bridge; struct drm_panel *panel; struct i2c_adapter *ddc; const struct edid *edid; diff --git a/drivers/gpu/drm/tegra/dsi.c b/drivers/gpu/drm/tegra/dsi.c index 3387de79718b..5691ef1b0e58 100644 --- a/drivers/gpu/drm/tegra/dsi.c +++ b/drivers/gpu/drm/tegra/dsi.c @@ -694,11 +694,11 @@ static int tegra_dsi_pad_calibrate(struct tegra_dsi *dsi) DSI_PAD_PREEMP_PD(0x03) | DSI_PAD_PREEMP_PU(0x3); tegra_dsi_writel(dsi, value, DSI_PAD_CONTROL_3); - err = tegra_mipi_calibrate(dsi->mipi); + err = tegra_mipi_start_calibration(dsi->mipi); if (err < 0) return err; - return tegra_mipi_wait(dsi->mipi); + return tegra_mipi_finish_calibration(dsi->mipi); } static void tegra_dsi_set_timeout(struct tegra_dsi *dsi, unsigned long bclk, diff --git a/drivers/gpu/drm/tegra/gem.c b/drivers/gpu/drm/tegra/gem.c index 5df577682878..26af8daa9a16 100644 --- a/drivers/gpu/drm/tegra/gem.c +++ b/drivers/gpu/drm/tegra/gem.c @@ -98,8 +98,8 @@ static struct sg_table *tegra_bo_pin(struct device *dev, struct host1x_bo *bo, * the SG table needs to be copied to avoid overwriting any * other potential users of the original SG table. */ - err = sg_alloc_table_from_sg(sgt, obj->sgt->sgl, obj->sgt->nents, - GFP_KERNEL); + err = sg_alloc_table_from_sg(sgt, obj->sgt->sgl, + obj->sgt->orig_nents, GFP_KERNEL); if (err < 0) goto free; } else { @@ -201,8 +201,7 @@ static int tegra_bo_iommu_map(struct tegra_drm *tegra, struct tegra_bo *bo) bo->iova = bo->mm->start; - bo->size = iommu_map_sg(tegra->domain, bo->iova, bo->sgt->sgl, - bo->sgt->nents, prot); + bo->size = iommu_map_sgtable(tegra->domain, bo->iova, bo->sgt, prot); if (!bo->size) { dev_err(tegra->drm->dev, "failed to map buffer\n"); err = -ENOMEM; @@ -277,8 +276,7 @@ free: static void tegra_bo_free(struct drm_device *drm, struct tegra_bo *bo) { if (bo->pages) { - dma_unmap_sg(drm->dev, bo->sgt->sgl, bo->sgt->nents, - DMA_FROM_DEVICE); + dma_unmap_sgtable(drm->dev, bo->sgt, DMA_FROM_DEVICE, 0); drm_gem_put_pages(&bo->gem, bo->pages, true, true); sg_free_table(bo->sgt); kfree(bo->sgt); @@ -303,12 +301,9 @@ static int tegra_bo_get_pages(struct drm_device *drm, struct tegra_bo *bo) goto put_pages; } - err = dma_map_sg(drm->dev, bo->sgt->sgl, bo->sgt->nents, - DMA_FROM_DEVICE); - if (err == 0) { - err = -EFAULT; + err = dma_map_sgtable(drm->dev, bo->sgt, DMA_FROM_DEVICE, 0); + if (err) goto free_sgt; - } return 0; @@ -584,7 +579,7 @@ tegra_gem_prime_map_dma_buf(struct dma_buf_attachment *attach, goto free; } - if (dma_map_sg(attach->dev, sgt->sgl, sgt->nents, dir) == 0) + if (dma_map_sgtable(attach->dev, sgt, dir, 0)) goto free; return sgt; @@ -603,7 +598,7 @@ static void tegra_gem_prime_unmap_dma_buf(struct dma_buf_attachment *attach, struct tegra_bo *bo = to_tegra_bo(gem); if (bo->pages) - dma_unmap_sg(attach->dev, sgt->sgl, sgt->nents, dir); + dma_unmap_sgtable(attach->dev, sgt, dir, 0); sg_free_table(sgt); kfree(sgt); @@ -622,8 +617,7 @@ static int tegra_gem_prime_begin_cpu_access(struct dma_buf *buf, struct drm_device *drm = gem->dev; if (bo->pages) - dma_sync_sg_for_cpu(drm->dev, bo->sgt->sgl, bo->sgt->nents, - DMA_FROM_DEVICE); + dma_sync_sgtable_for_cpu(drm->dev, bo->sgt, DMA_FROM_DEVICE); return 0; } @@ -636,8 +630,7 @@ static int tegra_gem_prime_end_cpu_access(struct dma_buf *buf, struct drm_device *drm = gem->dev; if (bo->pages) - dma_sync_sg_for_device(drm->dev, bo->sgt->sgl, bo->sgt->nents, - DMA_TO_DEVICE); + dma_sync_sgtable_for_device(drm->dev, bo->sgt, DMA_TO_DEVICE); return 0; } diff --git a/drivers/gpu/drm/tegra/output.c b/drivers/gpu/drm/tegra/output.c index a3adb9e4debf..5a4fd0dbf4cf 100644 --- a/drivers/gpu/drm/tegra/output.c +++ b/drivers/gpu/drm/tegra/output.c @@ -5,6 +5,7 @@ */ #include <drm/drm_atomic_helper.h> +#include <drm/drm_of.h> #include <drm/drm_panel.h> #include <drm/drm_simple_kms_helper.h> @@ -99,27 +100,38 @@ int tegra_output_probe(struct tegra_output *output) if (!output->of_node) output->of_node = output->dev->of_node; + err = drm_of_find_panel_or_bridge(output->of_node, -1, -1, + &output->panel, &output->bridge); + if (err && err != -ENODEV) + return err; + panel = of_parse_phandle(output->of_node, "nvidia,panel", 0); if (panel) { + /* + * Don't mix nvidia,panel phandle with the graph in a + * device-tree. + */ + WARN_ON(output->panel || output->bridge); + output->panel = of_drm_find_panel(panel); + of_node_put(panel); + if (IS_ERR(output->panel)) return PTR_ERR(output->panel); - - of_node_put(panel); } output->edid = of_get_property(output->of_node, "nvidia,edid", &size); ddc = of_parse_phandle(output->of_node, "nvidia,ddc-i2c-bus", 0); if (ddc) { - output->ddc = of_find_i2c_adapter_by_node(ddc); + output->ddc = of_get_i2c_adapter_by_node(ddc); + of_node_put(ddc); + if (!output->ddc) { err = -EPROBE_DEFER; of_node_put(ddc); return err; } - - of_node_put(ddc); } output->hpd_gpio = devm_gpiod_get_from_of_node(output->dev, @@ -173,7 +185,7 @@ void tegra_output_remove(struct tegra_output *output) free_irq(output->hpd_irq, output); if (output->ddc) - put_device(&output->ddc->dev); + i2c_put_adapter(output->ddc); } int tegra_output_init(struct drm_device *drm, struct tegra_output *output) diff --git a/drivers/gpu/drm/tegra/plane.c b/drivers/gpu/drm/tegra/plane.c index 4cd0461cc508..539d14935728 100644 --- a/drivers/gpu/drm/tegra/plane.c +++ b/drivers/gpu/drm/tegra/plane.c @@ -131,12 +131,9 @@ static int tegra_dc_pin(struct tegra_dc *dc, struct tegra_plane_state *state) } if (sgt) { - err = dma_map_sg(dc->dev, sgt->sgl, sgt->nents, - DMA_TO_DEVICE); - if (err == 0) { - err = -ENOMEM; + err = dma_map_sgtable(dc->dev, sgt, DMA_TO_DEVICE, 0); + if (err) goto unpin; - } /* * The display controller needs contiguous memory, so @@ -144,7 +141,7 @@ static int tegra_dc_pin(struct tegra_dc *dc, struct tegra_plane_state *state) * map its SG table to a single contiguous chunk of * I/O virtual memory. */ - if (err > 1) { + if (sgt->nents > 1) { err = -EINVAL; goto unpin; } @@ -166,8 +163,7 @@ unpin: struct sg_table *sgt = state->sgt[i]; if (sgt) - dma_unmap_sg(dc->dev, sgt->sgl, sgt->nents, - DMA_TO_DEVICE); + dma_unmap_sgtable(dc->dev, sgt, DMA_TO_DEVICE, 0); host1x_bo_unpin(dc->dev, &bo->base, sgt); state->iova[i] = DMA_MAPPING_ERROR; @@ -186,8 +182,7 @@ static void tegra_dc_unpin(struct tegra_dc *dc, struct tegra_plane_state *state) struct sg_table *sgt = state->sgt[i]; if (sgt) - dma_unmap_sg(dc->dev, sgt->sgl, sgt->nents, - DMA_TO_DEVICE); + dma_unmap_sgtable(dc->dev, sgt, DMA_TO_DEVICE, 0); host1x_bo_unpin(dc->dev, &bo->base, sgt); state->iova[i] = DMA_MAPPING_ERROR; diff --git a/drivers/gpu/drm/tegra/rgb.c b/drivers/gpu/drm/tegra/rgb.c index 0562a7eb793f..4142a56ca764 100644 --- a/drivers/gpu/drm/tegra/rgb.c +++ b/drivers/gpu/drm/tegra/rgb.c @@ -7,7 +7,7 @@ #include <linux/clk.h> #include <drm/drm_atomic_helper.h> -#include <drm/drm_panel.h> +#include <drm/drm_bridge_connector.h> #include <drm/drm_simple_kms_helper.h> #include "drm.h" @@ -85,45 +85,13 @@ static void tegra_dc_write_regs(struct tegra_dc *dc, tegra_dc_writel(dc, table[i].value, table[i].offset); } -static const struct drm_connector_funcs tegra_rgb_connector_funcs = { - .reset = drm_atomic_helper_connector_reset, - .detect = tegra_output_connector_detect, - .fill_modes = drm_helper_probe_single_connector_modes, - .destroy = tegra_output_connector_destroy, - .atomic_duplicate_state = drm_atomic_helper_connector_duplicate_state, - .atomic_destroy_state = drm_atomic_helper_connector_destroy_state, -}; - -static enum drm_mode_status -tegra_rgb_connector_mode_valid(struct drm_connector *connector, - struct drm_display_mode *mode) -{ - /* - * FIXME: For now, always assume that the mode is okay. There are - * unresolved issues with clk_round_rate(), which doesn't always - * reliably report whether a frequency can be set or not. - */ - return MODE_OK; -} - -static const struct drm_connector_helper_funcs tegra_rgb_connector_helper_funcs = { - .get_modes = tegra_output_connector_get_modes, - .mode_valid = tegra_rgb_connector_mode_valid, -}; - static void tegra_rgb_encoder_disable(struct drm_encoder *encoder) { struct tegra_output *output = encoder_to_output(encoder); struct tegra_rgb *rgb = to_rgb(output); - if (output->panel) - drm_panel_disable(output->panel); - tegra_dc_write_regs(rgb->dc, rgb_disable, ARRAY_SIZE(rgb_disable)); tegra_dc_commit(rgb->dc); - - if (output->panel) - drm_panel_unprepare(output->panel); } static void tegra_rgb_encoder_enable(struct drm_encoder *encoder) @@ -132,9 +100,6 @@ static void tegra_rgb_encoder_enable(struct drm_encoder *encoder) struct tegra_rgb *rgb = to_rgb(output); u32 value; - if (output->panel) - drm_panel_prepare(output->panel); - tegra_dc_write_regs(rgb->dc, rgb_enable, ARRAY_SIZE(rgb_enable)); value = DE_SELECT_ACTIVE | DE_CONTROL_NORMAL; @@ -156,9 +121,6 @@ static void tegra_rgb_encoder_enable(struct drm_encoder *encoder) tegra_dc_writel(rgb->dc, value, DC_DISP_SHIFT_CLOCK_OPTIONS); tegra_dc_commit(rgb->dc); - - if (output->panel) - drm_panel_enable(output->panel); } static int @@ -267,24 +229,68 @@ int tegra_dc_rgb_remove(struct tegra_dc *dc) int tegra_dc_rgb_init(struct drm_device *drm, struct tegra_dc *dc) { struct tegra_output *output = dc->rgb; + struct drm_connector *connector; int err; if (!dc->rgb) return -ENODEV; - drm_connector_init(drm, &output->connector, &tegra_rgb_connector_funcs, - DRM_MODE_CONNECTOR_LVDS); - drm_connector_helper_add(&output->connector, - &tegra_rgb_connector_helper_funcs); - output->connector.dpms = DRM_MODE_DPMS_OFF; - drm_simple_encoder_init(drm, &output->encoder, DRM_MODE_ENCODER_LVDS); drm_encoder_helper_add(&output->encoder, &tegra_rgb_encoder_helper_funcs); - drm_connector_attach_encoder(&output->connector, - &output->encoder); - drm_connector_register(&output->connector); + /* + * Wrap directly-connected panel into DRM bridge in order to let + * DRM core to handle panel for us. + */ + if (output->panel) { + output->bridge = devm_drm_panel_bridge_add(output->dev, + output->panel); + if (IS_ERR(output->bridge)) { + dev_err(output->dev, + "failed to wrap panel into bridge: %pe\n", + output->bridge); + return PTR_ERR(output->bridge); + } + + output->panel = NULL; + } + + /* + * Tegra devices that have LVDS panel utilize LVDS encoder bridge + * for converting up to 28 LCD LVTTL lanes into 5/4 LVDS lanes that + * go to display panel's receiver. + * + * Encoder usually have a power-down control which needs to be enabled + * in order to transmit data to the panel. Historically devices that + * use an older device-tree version didn't model the bridge, assuming + * that encoder is turned ON by default, while today's DRM allows us + * to model LVDS encoder properly. + * + * Newer device-trees utilize LVDS encoder bridge, which provides + * us with a connector and handles the display panel. + * + * For older device-trees we wrapped panel into the panel-bridge. + */ + if (output->bridge) { + err = drm_bridge_attach(&output->encoder, output->bridge, + NULL, DRM_BRIDGE_ATTACH_NO_CONNECTOR); + if (err) { + dev_err(output->dev, "failed to attach bridge: %d\n", + err); + return err; + } + + connector = drm_bridge_connector_init(drm, &output->encoder); + if (IS_ERR(connector)) { + dev_err(output->dev, + "failed to initialize bridge connector: %pe\n", + connector); + return PTR_ERR(connector); + } + + drm_connector_attach_encoder(connector, &output->encoder); + } err = tegra_output_init(drm, output); if (err < 0) { diff --git a/drivers/gpu/drm/tegra/sor.c b/drivers/gpu/drm/tegra/sor.c index 45b5258c77a2..e88a17c2937f 100644 --- a/drivers/gpu/drm/tegra/sor.c +++ b/drivers/gpu/drm/tegra/sor.c @@ -3728,7 +3728,12 @@ static int tegra_sor_probe(struct platform_device *pdev) if (!sor->aux) return -EPROBE_DEFER; - sor->output.ddc = &sor->aux->ddc; + if (get_device(&sor->aux->ddc.dev)) { + if (try_module_get(sor->aux->ddc.owner)) + sor->output.ddc = &sor->aux->ddc; + else + put_device(&sor->aux->ddc.dev); + } } if (!sor->aux) { diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c index 530c9a4af09f..c63b7ea1cd5d 100644 --- a/drivers/gpu/drm/ttm/ttm_bo.c +++ b/drivers/gpu/drm/ttm/ttm_bo.c @@ -612,7 +612,7 @@ bool ttm_bo_eviction_valuable(struct ttm_buffer_object *bo, /* Don't evict this BO if it's outside of the * requested placement range */ - if (place->fpfn >= (bo->mem.start + bo->mem.size) || + if (place->fpfn >= (bo->mem.start + bo->mem.num_pages) || (place->lpfn && place->lpfn <= bo->mem.start)) return false; diff --git a/drivers/gpu/drm/v3d/v3d_gem.c b/drivers/gpu/drm/v3d/v3d_gem.c index 915f8bfdb58c..182c586525eb 100644 --- a/drivers/gpu/drm/v3d/v3d_gem.c +++ b/drivers/gpu/drm/v3d/v3d_gem.c @@ -568,7 +568,6 @@ v3d_submit_cl_ioctl(struct drm_device *dev, void *data, ret = v3d_job_init(v3d, file_priv, &bin->base, v3d_job_free, args->in_sync_bcl); if (ret) { - kfree(bin); v3d_job_put(&render->base); kfree(bin); return ret; diff --git a/drivers/gpu/drm/v3d/v3d_mmu.c b/drivers/gpu/drm/v3d/v3d_mmu.c index 3b81ea28c0bb..5a453532901f 100644 --- a/drivers/gpu/drm/v3d/v3d_mmu.c +++ b/drivers/gpu/drm/v3d/v3d_mmu.c @@ -90,18 +90,17 @@ void v3d_mmu_insert_ptes(struct v3d_bo *bo) struct v3d_dev *v3d = to_v3d_dev(shmem_obj->base.dev); u32 page = bo->node.start; u32 page_prot = V3D_PTE_WRITEABLE | V3D_PTE_VALID; - unsigned int count; - struct scatterlist *sgl; + struct sg_dma_page_iter dma_iter; - for_each_sg(shmem_obj->sgt->sgl, sgl, shmem_obj->sgt->nents, count) { - u32 page_address = sg_dma_address(sgl) >> V3D_MMU_PAGE_SHIFT; + for_each_sgtable_dma_page(shmem_obj->sgt, &dma_iter, 0) { + dma_addr_t dma_addr = sg_page_iter_dma_address(&dma_iter); + u32 page_address = dma_addr >> V3D_MMU_PAGE_SHIFT; u32 pte = page_prot | page_address; u32 i; - BUG_ON(page_address + (sg_dma_len(sgl) >> V3D_MMU_PAGE_SHIFT) >= + BUG_ON(page_address + (PAGE_SIZE >> V3D_MMU_PAGE_SHIFT) >= BIT(24)); - - for (i = 0; i < sg_dma_len(sgl) >> V3D_MMU_PAGE_SHIFT; i++) + for (i = 0; i < PAGE_SIZE >> V3D_MMU_PAGE_SHIFT; i++) v3d->pt[page++] = pte + i; } diff --git a/drivers/gpu/drm/vc4/vc4_crtc.c b/drivers/gpu/drm/vc4/vc4_crtc.c index 72141bb24aa5..f04f5cc8c839 100644 --- a/drivers/gpu/drm/vc4/vc4_crtc.c +++ b/drivers/gpu/drm/vc4/vc4_crtc.c @@ -856,11 +856,19 @@ void vc4_crtc_destroy_state(struct drm_crtc *crtc, void vc4_crtc_reset(struct drm_crtc *crtc) { + struct vc4_crtc_state *vc4_crtc_state; + if (crtc->state) vc4_crtc_destroy_state(crtc, crtc->state); - crtc->state = kzalloc(sizeof(struct vc4_crtc_state), GFP_KERNEL); - if (crtc->state) - __drm_atomic_helper_crtc_reset(crtc, crtc->state); + + vc4_crtc_state = kzalloc(sizeof(*vc4_crtc_state), GFP_KERNEL); + if (!vc4_crtc_state) { + crtc->state = NULL; + return; + } + + vc4_crtc_state->assigned_channel = VC4_HVS_CHANNEL_DISABLED; + __drm_atomic_helper_crtc_reset(crtc, &vc4_crtc_state->base); } static const struct drm_crtc_funcs vc4_crtc_funcs = { diff --git a/drivers/gpu/drm/vc4/vc4_drv.c b/drivers/gpu/drm/vc4/vc4_drv.c index d27eaa2d0cfe..8f10f609e4f8 100644 --- a/drivers/gpu/drm/vc4/vc4_drv.c +++ b/drivers/gpu/drm/vc4/vc4_drv.c @@ -302,6 +302,7 @@ unbind_all: component_unbind_all(dev, drm); gem_destroy: vc4_gem_destroy(drm); + drm_mode_config_cleanup(drm); vc4_bo_cache_destroy(drm); dev_put: drm_dev_put(drm); diff --git a/drivers/gpu/drm/vc4/vc4_drv.h b/drivers/gpu/drm/vc4/vc4_drv.h index a22478a35199..7003e7f14a48 100644 --- a/drivers/gpu/drm/vc4/vc4_drv.h +++ b/drivers/gpu/drm/vc4/vc4_drv.h @@ -287,7 +287,7 @@ struct vc4_bo { static inline struct vc4_bo * to_vc4_bo(struct drm_gem_object *bo) { - return (struct vc4_bo *)bo; + return container_of(to_drm_gem_cma_obj(bo), struct vc4_bo, base); } struct vc4_fence { @@ -300,7 +300,7 @@ struct vc4_fence { static inline struct vc4_fence * to_vc4_fence(struct dma_fence *fence) { - return (struct vc4_fence *)fence; + return container_of(fence, struct vc4_fence, base); } struct vc4_seqno_cb { @@ -347,7 +347,7 @@ struct vc4_plane { static inline struct vc4_plane * to_vc4_plane(struct drm_plane *plane) { - return (struct vc4_plane *)plane; + return container_of(plane, struct vc4_plane, base); } enum vc4_scaling_mode { @@ -423,7 +423,7 @@ struct vc4_plane_state { static inline struct vc4_plane_state * to_vc4_plane_state(struct drm_plane_state *state) { - return (struct vc4_plane_state *)state; + return container_of(state, struct vc4_plane_state, base); } enum vc4_encoder_type { @@ -499,7 +499,7 @@ struct vc4_crtc { static inline struct vc4_crtc * to_vc4_crtc(struct drm_crtc *crtc) { - return (struct vc4_crtc *)crtc; + return container_of(crtc, struct vc4_crtc, base); } static inline const struct vc4_crtc_data * @@ -532,10 +532,12 @@ struct vc4_crtc_state { } margins; }; +#define VC4_HVS_CHANNEL_DISABLED ((unsigned int)-1) + static inline struct vc4_crtc_state * to_vc4_crtc_state(struct drm_crtc_state *crtc_state) { - return (struct vc4_crtc_state *)crtc_state; + return container_of(crtc_state, struct vc4_crtc_state, base); } #define V3D_READ(offset) readl(vc4->v3d->regs + offset) diff --git a/drivers/gpu/drm/vc4/vc4_hdmi.c b/drivers/gpu/drm/vc4/vc4_hdmi.c index 03825596a308..95779d50cca0 100644 --- a/drivers/gpu/drm/vc4/vc4_hdmi.c +++ b/drivers/gpu/drm/vc4/vc4_hdmi.c @@ -922,6 +922,7 @@ static int vc4_hdmi_audio_hw_params(struct snd_pcm_substream *substream, struct snd_soc_dai *dai) { struct vc4_hdmi *vc4_hdmi = dai_to_hdmi(dai); + struct drm_encoder *encoder = &vc4_hdmi->encoder.base.base; struct device *dev = &vc4_hdmi->pdev->dev; u32 audio_packet_config, channel_mask; u32 channel_map; @@ -981,6 +982,8 @@ static int vc4_hdmi_audio_hw_params(struct snd_pcm_substream *substream, HDMI_WRITE(HDMI_AUDIO_PACKET_CONFIG, audio_packet_config); vc4_hdmi_set_n_cts(vc4_hdmi); + vc4_hdmi_set_audio_infoframe(encoder); + return 0; } @@ -988,11 +991,9 @@ static int vc4_hdmi_audio_trigger(struct snd_pcm_substream *substream, int cmd, struct snd_soc_dai *dai) { struct vc4_hdmi *vc4_hdmi = dai_to_hdmi(dai); - struct drm_encoder *encoder = &vc4_hdmi->encoder.base.base; switch (cmd) { case SNDRV_PCM_TRIGGER_START: - vc4_hdmi_set_audio_infoframe(encoder); vc4_hdmi->audio.streaming = true; if (vc4_hdmi->variant->phy_rng_enable) @@ -1076,6 +1077,7 @@ static const struct snd_soc_dapm_route vc4_hdmi_audio_routes[] = { }; static const struct snd_soc_component_driver vc4_hdmi_audio_component_drv = { + .name = "vc4-hdmi-codec-dai-component", .controls = vc4_hdmi_audio_controls, .num_controls = ARRAY_SIZE(vc4_hdmi_audio_controls), .dapm_widgets = vc4_hdmi_audio_widgets, @@ -1224,6 +1226,7 @@ static int vc4_hdmi_audio_init(struct vc4_hdmi *vc4_hdmi) card->num_links = 1; card->name = vc4_hdmi->variant->card_name; card->dev = dev; + card->owner = THIS_MODULE; /* * Be careful, snd_soc_register_card() calls dev_set_drvdata() and diff --git a/drivers/gpu/drm/vc4/vc4_kms.c b/drivers/gpu/drm/vc4/vc4_kms.c index af3ee3dcdab6..149825ff5df8 100644 --- a/drivers/gpu/drm/vc4/vc4_kms.c +++ b/drivers/gpu/drm/vc4/vc4_kms.c @@ -616,7 +616,7 @@ static int vc4_atomic_check(struct drm_device *dev, struct drm_atomic_state *state) { unsigned long unassigned_channels = GENMASK(NUM_CHANNELS - 1, 0); - struct drm_crtc_state *crtc_state; + struct drm_crtc_state *old_crtc_state, *new_crtc_state; struct drm_crtc *crtc; int i, ret; @@ -629,6 +629,8 @@ vc4_atomic_check(struct drm_device *dev, struct drm_atomic_state *state) * modified. */ list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) { + struct drm_crtc_state *crtc_state; + if (!crtc->state->enable) continue; @@ -637,15 +639,23 @@ vc4_atomic_check(struct drm_device *dev, struct drm_atomic_state *state) return PTR_ERR(crtc_state); } - for_each_new_crtc_in_state(state, crtc, crtc_state, i) { - struct vc4_crtc_state *vc4_crtc_state = - to_vc4_crtc_state(crtc_state); + for_each_oldnew_crtc_in_state(state, crtc, old_crtc_state, new_crtc_state, i) { + struct vc4_crtc_state *new_vc4_crtc_state = + to_vc4_crtc_state(new_crtc_state); struct vc4_crtc *vc4_crtc = to_vc4_crtc(crtc); unsigned int matching_channels; - if (!crtc_state->active) + if (old_crtc_state->enable && !new_crtc_state->enable) + new_vc4_crtc_state->assigned_channel = VC4_HVS_CHANNEL_DISABLED; + + if (!new_crtc_state->enable) continue; + if (new_vc4_crtc_state->assigned_channel != VC4_HVS_CHANNEL_DISABLED) { + unassigned_channels &= ~BIT(new_vc4_crtc_state->assigned_channel); + continue; + } + /* * The problem we have to solve here is that we have * up to 7 encoders, connected to up to 6 CRTCs. @@ -674,7 +684,7 @@ vc4_atomic_check(struct drm_device *dev, struct drm_atomic_state *state) if (matching_channels) { unsigned int channel = ffs(matching_channels) - 1; - vc4_crtc_state->assigned_channel = channel; + new_vc4_crtc_state->assigned_channel = channel; unassigned_channels &= ~BIT(channel); } else { return -EINVAL; diff --git a/drivers/gpu/drm/virtio/virtgpu_object.c b/drivers/gpu/drm/virtio/virtgpu_object.c index 50cbc36c3b82..2d3aa7baffe4 100644 --- a/drivers/gpu/drm/virtio/virtgpu_object.c +++ b/drivers/gpu/drm/virtio/virtgpu_object.c @@ -71,9 +71,8 @@ void virtio_gpu_cleanup_object(struct virtio_gpu_object *bo) if (shmem->pages) { if (shmem->mapped) { - dma_unmap_sg(vgdev->vdev->dev.parent, - shmem->pages->sgl, shmem->mapped, - DMA_TO_DEVICE); + dma_unmap_sgtable(vgdev->vdev->dev.parent, + shmem->pages, DMA_TO_DEVICE, 0); shmem->mapped = 0; } @@ -176,13 +175,13 @@ static int virtio_gpu_object_shmem_init(struct virtio_gpu_device *vgdev, } if (use_dma_api) { - shmem->mapped = dma_map_sg(vgdev->vdev->dev.parent, - shmem->pages->sgl, - shmem->pages->nents, - DMA_TO_DEVICE); - *nents = shmem->mapped; + ret = dma_map_sgtable(vgdev->vdev->dev.parent, + shmem->pages, DMA_TO_DEVICE, 0); + if (ret) + return ret; + *nents = shmem->mapped = shmem->pages->nents; } else { - *nents = shmem->pages->nents; + *nents = shmem->pages->orig_nents; } *ents = kmalloc_array(*nents, sizeof(struct virtio_gpu_mem_entry), @@ -192,13 +191,20 @@ static int virtio_gpu_object_shmem_init(struct virtio_gpu_device *vgdev, return -ENOMEM; } - for_each_sg(shmem->pages->sgl, sg, *nents, si) { - (*ents)[si].addr = cpu_to_le64(use_dma_api - ? sg_dma_address(sg) - : sg_phys(sg)); - (*ents)[si].length = cpu_to_le32(sg->length); - (*ents)[si].padding = 0; + if (use_dma_api) { + for_each_sgtable_dma_sg(shmem->pages, sg, si) { + (*ents)[si].addr = cpu_to_le64(sg_dma_address(sg)); + (*ents)[si].length = cpu_to_le32(sg_dma_len(sg)); + (*ents)[si].padding = 0; + } + } else { + for_each_sgtable_sg(shmem->pages, sg, si) { + (*ents)[si].addr = cpu_to_le64(sg_phys(sg)); + (*ents)[si].length = cpu_to_le32(sg->length); + (*ents)[si].padding = 0; + } } + return 0; } diff --git a/drivers/gpu/drm/virtio/virtgpu_vq.c b/drivers/gpu/drm/virtio/virtgpu_vq.c index c1824f536936..857f730747b6 100644 --- a/drivers/gpu/drm/virtio/virtgpu_vq.c +++ b/drivers/gpu/drm/virtio/virtgpu_vq.c @@ -302,7 +302,7 @@ static struct sg_table *vmalloc_to_sgt(char *data, uint32_t size, int *sg_ents) return NULL; } - for_each_sg(sgt->sgl, sg, *sg_ents, i) { + for_each_sgtable_sg(sgt, sg, i) { pg = vmalloc_to_page(data); if (!pg) { sg_free_table(sgt); @@ -608,9 +608,8 @@ void virtio_gpu_cmd_transfer_to_host_2d(struct virtio_gpu_device *vgdev, struct virtio_gpu_object_shmem *shmem = to_virtio_gpu_shmem(bo); if (use_dma_api) - dma_sync_sg_for_device(vgdev->vdev->dev.parent, - shmem->pages->sgl, shmem->pages->nents, - DMA_TO_DEVICE); + dma_sync_sgtable_for_device(vgdev->vdev->dev.parent, + shmem->pages, DMA_TO_DEVICE); cmd_p = virtio_gpu_alloc_cmd(vgdev, &vbuf, sizeof(*cmd_p)); memset(cmd_p, 0, sizeof(*cmd_p)); @@ -1030,10 +1029,8 @@ void virtio_gpu_cmd_transfer_to_host_3d(struct virtio_gpu_device *vgdev, if (virtio_gpu_is_shmem(bo) && use_dma_api) { struct virtio_gpu_object_shmem *shmem = to_virtio_gpu_shmem(bo); - - dma_sync_sg_for_device(vgdev->vdev->dev.parent, - shmem->pages->sgl, shmem->pages->nents, - DMA_TO_DEVICE); + dma_sync_sgtable_for_device(vgdev->vdev->dev.parent, + shmem->pages, DMA_TO_DEVICE); } cmd_p = virtio_gpu_alloc_cmd(vgdev, &vbuf, sizeof(*cmd_p)); diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_gmrid_manager.c b/drivers/gpu/drm/vmwgfx/vmwgfx_gmrid_manager.c index 9e8a3e337b96..be325a62c178 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_gmrid_manager.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_gmrid_manager.c @@ -60,7 +60,7 @@ static int vmw_gmrid_man_get_node(struct ttm_resource_manager *man, id = ida_alloc_max(&gman->gmr_ida, gman->max_gmr_ids - 1, GFP_KERNEL); if (id < 0) - return (id != -ENOMEM ? 0 : id); + return id; spin_lock(&gman->lock); diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c b/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c index e9f448a5ebb3..15b5bde69324 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c @@ -24,7 +24,7 @@ * */ -#include <linux/frame.h> +#include <linux/objtool.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/slab.h> @@ -599,4 +599,3 @@ out_open: return -EINVAL; } - diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_thp.c b/drivers/gpu/drm/vmwgfx/vmwgfx_thp.c index 328d332a55e2..155ca3a5c7e5 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_thp.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_thp.c @@ -26,6 +26,8 @@ static struct vmw_thp_manager *to_thp_manager(struct ttm_resource_manager *man) return container_of(man, struct vmw_thp_manager, manager); } +static const struct ttm_resource_manager_func vmw_thp_func; + static int vmw_thp_insert_aligned(struct drm_mm *mm, struct drm_mm_node *node, unsigned long align_pages, const struct ttm_place *place, @@ -101,7 +103,7 @@ found_unlock: mem->start = node->start; } - return 0; + return ret; } @@ -132,6 +134,7 @@ int vmw_thp_init(struct vmw_private *dev_priv) ttm_resource_manager_init(&rman->manager, dev_priv->vram_size >> PAGE_SHIFT); + rman->manager.func = &vmw_thp_func; drm_mm_init(&rman->mm, 0, rman->manager.size); spin_lock_init(&rman->lock); @@ -171,7 +174,7 @@ static void vmw_thp_debug(struct ttm_resource_manager *man, spin_unlock(&rman->lock); } -const struct ttm_resource_manager_func vmw_thp_func = { +static const struct ttm_resource_manager_func vmw_thp_func = { .alloc = vmw_thp_get_node, .free = vmw_thp_put_node, .debug = vmw_thp_debug diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c b/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c index aa0cdf476a53..51f70bea41cc 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c @@ -311,8 +311,7 @@ static void vmw_ttm_unmap_from_dma(struct vmw_ttm_tt *vmw_tt) { struct device *dev = vmw_tt->dev_priv->dev->dev; - dma_unmap_sg(dev, vmw_tt->sgt.sgl, vmw_tt->sgt.nents, - DMA_BIDIRECTIONAL); + dma_unmap_sgtable(dev, &vmw_tt->sgt, DMA_BIDIRECTIONAL, 0); vmw_tt->sgt.nents = vmw_tt->sgt.orig_nents; } @@ -332,16 +331,8 @@ static void vmw_ttm_unmap_from_dma(struct vmw_ttm_tt *vmw_tt) static int vmw_ttm_map_for_dma(struct vmw_ttm_tt *vmw_tt) { struct device *dev = vmw_tt->dev_priv->dev->dev; - int ret; - - ret = dma_map_sg(dev, vmw_tt->sgt.sgl, vmw_tt->sgt.orig_nents, - DMA_BIDIRECTIONAL); - if (unlikely(ret == 0)) - return -ENOMEM; - - vmw_tt->sgt.nents = ret; - return 0; + return dma_map_sgtable(dev, &vmw_tt->sgt, DMA_BIDIRECTIONAL, 0); } /** @@ -368,6 +359,7 @@ static int vmw_ttm_map_dma(struct vmw_ttm_tt *vmw_tt) int ret = 0; static size_t sgl_size; static size_t sgt_size; + struct scatterlist *sg; if (vmw_tt->mapped) return 0; @@ -390,18 +382,20 @@ static int vmw_ttm_map_dma(struct vmw_ttm_tt *vmw_tt) if (unlikely(ret != 0)) return ret; - ret = __sg_alloc_table_from_pages - (&vmw_tt->sgt, vsgt->pages, vsgt->num_pages, 0, - (unsigned long) vsgt->num_pages << PAGE_SHIFT, - dma_get_max_seg_size(dev_priv->dev->dev), - GFP_KERNEL); - if (unlikely(ret != 0)) + sg = __sg_alloc_table_from_pages(&vmw_tt->sgt, vsgt->pages, + vsgt->num_pages, 0, + (unsigned long) vsgt->num_pages << PAGE_SHIFT, + dma_get_max_seg_size(dev_priv->dev->dev), + NULL, 0, GFP_KERNEL); + if (IS_ERR(sg)) { + ret = PTR_ERR(sg); goto out_sg_alloc_fail; + } - if (vsgt->num_pages > vmw_tt->sgt.nents) { + if (vsgt->num_pages > vmw_tt->sgt.orig_nents) { uint64_t over_alloc = sgl_size * (vsgt->num_pages - - vmw_tt->sgt.nents); + vmw_tt->sgt.orig_nents); ttm_mem_global_free(glob, over_alloc); vmw_tt->sg_alloc_size -= over_alloc; diff --git a/drivers/gpu/drm/xen/xen_drm_front_gem.c b/drivers/gpu/drm/xen/xen_drm_front_gem.c index f3830a0d1808..4f34ef34ba60 100644 --- a/drivers/gpu/drm/xen/xen_drm_front_gem.c +++ b/drivers/gpu/drm/xen/xen_drm_front_gem.c @@ -233,7 +233,7 @@ xen_drm_front_gem_import_sg_table(struct drm_device *dev, return ERR_PTR(ret); DRM_DEBUG("Imported buffer of size %zu with nents %u\n", - size, sgt->nents); + size, sgt->orig_nents); return &xen_obj->base; } diff --git a/drivers/gpu/host1x/job.c b/drivers/gpu/host1x/job.c index 89b6c14b7392..82d0a60ba3f7 100644 --- a/drivers/gpu/host1x/job.c +++ b/drivers/gpu/host1x/job.c @@ -170,11 +170,9 @@ static unsigned int pin_job(struct host1x *host, struct host1x_job *job) goto unpin; } - err = dma_map_sg(dev, sgt->sgl, sgt->nents, dir); - if (!err) { - err = -ENOMEM; + err = dma_map_sgtable(dev, sgt, dir, 0); + if (err) goto unpin; - } job->unpins[job->num_unpins].dev = dev; job->unpins[job->num_unpins].dir = dir; @@ -228,7 +226,7 @@ static unsigned int pin_job(struct host1x *host, struct host1x_job *job) } if (host->domain) { - for_each_sg(sgt->sgl, sg, sgt->nents, j) + for_each_sgtable_sg(sgt, sg, j) gather_size += sg->length; gather_size = iova_align(&host->iova, gather_size); @@ -240,9 +238,9 @@ static unsigned int pin_job(struct host1x *host, struct host1x_job *job) goto put; } - err = iommu_map_sg(host->domain, + err = iommu_map_sgtable(host->domain, iova_dma_addr(&host->iova, alloc), - sgt->sgl, sgt->nents, IOMMU_READ); + sgt, IOMMU_READ); if (err == 0) { __free_iova(&host->iova, alloc); err = -EINVAL; @@ -252,12 +250,9 @@ static unsigned int pin_job(struct host1x *host, struct host1x_job *job) job->unpins[job->num_unpins].size = gather_size; phys_addr = iova_dma_addr(&host->iova, alloc); } else if (sgt) { - err = dma_map_sg(host->dev, sgt->sgl, sgt->nents, - DMA_TO_DEVICE); - if (!err) { - err = -ENOMEM; + err = dma_map_sgtable(host->dev, sgt, DMA_TO_DEVICE, 0); + if (err) goto put; - } job->unpins[job->num_unpins].dir = DMA_TO_DEVICE; job->unpins[job->num_unpins].dev = host->dev; @@ -660,8 +655,7 @@ void host1x_job_unpin(struct host1x_job *job) } if (unpin->dev && sgt) - dma_unmap_sg(unpin->dev, sgt->sgl, sgt->nents, - unpin->dir); + dma_unmap_sgtable(unpin->dev, sgt, unpin->dir, 0); host1x_bo_unpin(dev, unpin->bo, sgt); host1x_bo_put(unpin->bo); diff --git a/drivers/gpu/host1x/mipi.c b/drivers/gpu/host1x/mipi.c index e606464aa43c..2efe12dde8bc 100644 --- a/drivers/gpu/host1x/mipi.c +++ b/drivers/gpu/host1x/mipi.c @@ -293,19 +293,13 @@ int tegra_mipi_disable(struct tegra_mipi_device *dev) } EXPORT_SYMBOL(tegra_mipi_disable); -int tegra_mipi_wait(struct tegra_mipi_device *device) +int tegra_mipi_finish_calibration(struct tegra_mipi_device *device) { struct tegra_mipi *mipi = device->mipi; void __iomem *status_reg = mipi->regs + (MIPI_CAL_STATUS << 2); u32 value; int err; - err = clk_enable(device->mipi->clk); - if (err < 0) - return err; - - mutex_lock(&device->mipi->lock); - err = readl_relaxed_poll_timeout(status_reg, value, !(value & MIPI_CAL_STATUS_ACTIVE) && (value & MIPI_CAL_STATUS_DONE), 50, @@ -315,9 +309,9 @@ int tegra_mipi_wait(struct tegra_mipi_device *device) return err; } -EXPORT_SYMBOL(tegra_mipi_wait); +EXPORT_SYMBOL(tegra_mipi_finish_calibration); -int tegra_mipi_calibrate(struct tegra_mipi_device *device) +int tegra_mipi_start_calibration(struct tegra_mipi_device *device) { const struct tegra_mipi_soc *soc = device->mipi->soc; unsigned int i; @@ -381,12 +375,16 @@ int tegra_mipi_calibrate(struct tegra_mipi_device *device) value |= MIPI_CAL_CTRL_START; tegra_mipi_writel(device->mipi, value, MIPI_CAL_CTRL); - mutex_unlock(&device->mipi->lock); - clk_disable(device->mipi->clk); + /* + * Wait for min 72uS to let calibration logic finish calibration + * sequence codes before waiting for pads idle state to apply the + * results. + */ + usleep_range(75, 80); return 0; } -EXPORT_SYMBOL(tegra_mipi_calibrate); +EXPORT_SYMBOL(tegra_mipi_start_calibration); static const struct tegra_mipi_pad tegra114_mipi_pads[] = { { .data = MIPI_CAL_CONFIG_CSIA }, |