diff options
Diffstat (limited to 'drivers/gpu')
33 files changed, 444 insertions, 126 deletions
diff --git a/drivers/gpu/drm/amd/amdgpu/atombios_i2c.c b/drivers/gpu/drm/amd/amdgpu/atombios_i2c.c index 13cdb01e9b45..bc56c8a181e6 100644 --- a/drivers/gpu/drm/amd/amdgpu/atombios_i2c.c +++ b/drivers/gpu/drm/amd/amdgpu/atombios_i2c.c @@ -156,3 +156,18 @@ u32 amdgpu_atombios_i2c_func(struct i2c_adapter *adap) return I2C_FUNC_I2C | I2C_FUNC_SMBUS_EMUL; } +void amdgpu_atombios_i2c_channel_trans(struct amdgpu_device* adev, u8 slave_addr, u8 line_number, u8 offset, u8 data) +{ + PROCESS_I2C_CHANNEL_TRANSACTION_PS_ALLOCATION args; + int index = GetIndexIntoMasterTable(COMMAND, ProcessI2cChannelTransaction); + + args.ucRegIndex = offset; + args.lpI2CDataOut = data; + args.ucFlag = 1; + args.ucI2CSpeed = TARGET_HW_I2C_CLOCK; + args.ucTransBytes = 1; + args.ucSlaveAddr = slave_addr; + args.ucLineNumber = line_number; + + amdgpu_atom_execute_table(adev->mode_info.atom_context, index, (uint32_t *)&args); +} diff --git a/drivers/gpu/drm/amd/amdgpu/atombios_i2c.h b/drivers/gpu/drm/amd/amdgpu/atombios_i2c.h index d6128d9de56e..251aaf41f65d 100644 --- a/drivers/gpu/drm/amd/amdgpu/atombios_i2c.h +++ b/drivers/gpu/drm/amd/amdgpu/atombios_i2c.h @@ -27,5 +27,7 @@ int amdgpu_atombios_i2c_xfer(struct i2c_adapter *i2c_adap, struct i2c_msg *msgs, int num); u32 amdgpu_atombios_i2c_func(struct i2c_adapter *adap); +void amdgpu_atombios_i2c_channel_trans(struct amdgpu_device* adev, + u8 slave_addr, u8 line_number, u8 offset, u8 data); #endif diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c index b2ebd4fef6cf..c2ef94511f70 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c @@ -28,6 +28,7 @@ #include "vid.h" #include "amdgpu_ucode.h" #include "amdgpu_atombios.h" +#include "atombios_i2c.h" #include "clearstate_vi.h" #include "gmc/gmc_8_2_d.h" @@ -284,6 +285,7 @@ static const u32 golden_settings_polaris11_a11[] = mmTCP_ADDR_CONFIG, 0x000003ff, 0x000000f3, mmTCP_CHAN_STEER_HI, 0xffffffff, 0x00000000, mmTCP_CHAN_STEER_LO, 0xffffffff, 0x00003210, + mmVGT_RESET_DEBUG, 0x00000004, 0x00000004, }; static const u32 polaris11_golden_common_all[] = @@ -314,6 +316,7 @@ static const u32 golden_settings_polaris10_a11[] = mmTCC_CTRL, 0x00100000, 0xf31fff7f, mmTCP_ADDR_CONFIG, 0x000003ff, 0x000000f7, mmTCP_CHAN_STEER_HI, 0xffffffff, 0x00000000, + mmVGT_RESET_DEBUG, 0x00000004, 0x00000004, }; static const u32 polaris10_golden_common_all[] = @@ -696,6 +699,10 @@ static void gfx_v8_0_init_golden_registers(struct amdgpu_device *adev) polaris10_golden_common_all, (const u32)ARRAY_SIZE(polaris10_golden_common_all)); WREG32_SMC(ixCG_ACLK_CNTL, 0x0000001C); + if (adev->pdev->revision == 0xc7) { + amdgpu_atombios_i2c_channel_trans(adev, 0x10, 0x96, 0x1E, 0xDD); + amdgpu_atombios_i2c_channel_trans(adev, 0x10, 0x96, 0x1F, 0xD0); + } break; case CHIP_CARRIZO: amdgpu_program_register_sequence(adev, diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/polaris10_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/polaris10_hwmgr.c index ec2a7ada346a..91e25f942d90 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/polaris10_hwmgr.c +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/polaris10_hwmgr.c @@ -98,7 +98,6 @@ #define PCIE_BUS_CLK 10000 #define TCLK (PCIE_BUS_CLK / 10) -#define CEILING_UCHAR(double) ((double-(uint8_t)(double)) > 0 ? (uint8_t)(double+1) : (uint8_t)(double)) static const uint16_t polaris10_clock_stretcher_lookup_table[2][4] = { {600, 1050, 3, 0}, {600, 1050, 6, 1} }; @@ -733,7 +732,7 @@ static int polaris10_populate_smc_mvdd_table(struct pp_hwmgr *hwmgr, table->Smio[level] |= data->mvdd_voltage_table.entries[level].smio_low; } - table->SmioMask2 = data->vddci_voltage_table.mask_low; + table->SmioMask2 = data->mvdd_voltage_table.mask_low; table->MvddLevelCount = (uint32_t) PP_HOST_TO_SMC_UL(count); } @@ -1807,27 +1806,25 @@ static int polaris10_populate_clock_stretcher_data_table(struct pp_hwmgr *hwmgr) ro = efuse * (max -min)/255 + min; - /* Populate Sclk_CKS_masterEn0_7 and Sclk_voltageOffset - * there is a little difference in calculating - * volt_with_cks with windows */ + /* Populate Sclk_CKS_masterEn0_7 and Sclk_voltageOffset */ for (i = 0; i < sclk_table->count; i++) { data->smc_state_table.Sclk_CKS_masterEn0_7 |= sclk_table->entries[i].cks_enable << i; if (hwmgr->chip_id == CHIP_POLARIS10) { - volt_without_cks = (uint32_t)((2753594000 + (sclk_table->entries[i].clk/100) * 136418 -(ro - 70) * 1000000) / \ + volt_without_cks = (uint32_t)((2753594000U + (sclk_table->entries[i].clk/100) * 136418 -(ro - 70) * 1000000) / \ (2424180 - (sclk_table->entries[i].clk/100) * 1132925/1000)); - volt_with_cks = (uint32_t)((279720200 + sclk_table->entries[i].clk * 3232 - (ro - 65) * 100000000) / \ - (252248000 - sclk_table->entries[i].clk/100 * 115764)); + volt_with_cks = (uint32_t)((2797202000U + sclk_table->entries[i].clk/100 * 3232 - (ro - 65) * 1000000) / \ + (2522480 - sclk_table->entries[i].clk/100 * 115764/100)); } else { - volt_without_cks = (uint32_t)((2416794800 + (sclk_table->entries[i].clk/100) * 1476925/10 -(ro - 50) * 1000000) / \ - (2625416 - (sclk_table->entries[i].clk/100) * 12586807/10000)); - volt_with_cks = (uint32_t)((2999656000 + sclk_table->entries[i].clk * 392803/100 - (ro - 44) * 1000000) / \ - (3422454 - sclk_table->entries[i].clk/100 * 18886376/10000)); + volt_without_cks = (uint32_t)((2416794800U + (sclk_table->entries[i].clk/100) * 1476925/10 -(ro - 50) * 1000000) / \ + (2625416 - (sclk_table->entries[i].clk/100) * (12586807/10000))); + volt_with_cks = (uint32_t)((2999656000U - sclk_table->entries[i].clk/100 * 392803 - (ro - 44) * 1000000) / \ + (3422454 - sclk_table->entries[i].clk/100 * (18886376/10000))); } if (volt_without_cks >= volt_with_cks) - volt_offset = (uint8_t)CEILING_UCHAR((volt_without_cks - volt_with_cks + - sclk_table->entries[i].cks_voffset) * 100 / 625); + volt_offset = (uint8_t)(((volt_without_cks - volt_with_cks + + sclk_table->entries[i].cks_voffset) * 100 + 624) / 625); data->smc_state_table.Sclk_voltageOffset[i] = volt_offset; } @@ -2685,7 +2682,7 @@ static int polaris10_get_evv_voltages(struct pp_hwmgr *hwmgr) { struct polaris10_hwmgr *data = (struct polaris10_hwmgr *)(hwmgr->backend); uint16_t vv_id; - uint16_t vddc = 0; + uint32_t vddc = 0; uint16_t i, j; uint32_t sclk = 0; struct phm_ppt_v1_information *table_info = @@ -2716,8 +2713,9 @@ static int polaris10_get_evv_voltages(struct pp_hwmgr *hwmgr) continue); - /* need to make sure vddc is less than 2v or else, it could burn the ASIC. */ - PP_ASSERT_WITH_CODE((vddc < 2000 && vddc != 0), + /* need to make sure vddc is less than 2v or else, it could burn the ASIC. + * real voltage level in unit of 0.01mv */ + PP_ASSERT_WITH_CODE((vddc < 200000 && vddc != 0), "Invalid VDDC value", result = -EINVAL;); /* the voltage should not be zero nor equal to leakage ID */ diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomctrl.c b/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomctrl.c index bf4e18fd3872..90b35c5c10a4 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomctrl.c +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomctrl.c @@ -1256,7 +1256,7 @@ int atomctrl_set_ac_timing_ai(struct pp_hwmgr *hwmgr, uint32_t memory_clock, } int atomctrl_get_voltage_evv_on_sclk_ai(struct pp_hwmgr *hwmgr, uint8_t voltage_type, - uint32_t sclk, uint16_t virtual_voltage_Id, uint16_t *voltage) + uint32_t sclk, uint16_t virtual_voltage_Id, uint32_t *voltage) { int result; @@ -1274,7 +1274,7 @@ int atomctrl_get_voltage_evv_on_sclk_ai(struct pp_hwmgr *hwmgr, uint8_t voltage_ if (0 != result) return result; - *voltage = get_voltage_info_param_space.usVoltageLevel; + *voltage = ((GET_EVV_VOLTAGE_INFO_OUTPUT_PARAMETER_V1_3 *)(&get_voltage_info_param_space))->ulVoltageLevel; return result; } diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomctrl.h b/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomctrl.h index 248c5db5f380..1e35a9625baf 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomctrl.h +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomctrl.h @@ -305,7 +305,7 @@ extern int atomctrl_get_engine_pll_dividers_ai(struct pp_hwmgr *hwmgr, uint32_t extern int atomctrl_set_ac_timing_ai(struct pp_hwmgr *hwmgr, uint32_t memory_clock, uint8_t level); extern int atomctrl_get_voltage_evv_on_sclk_ai(struct pp_hwmgr *hwmgr, uint8_t voltage_type, - uint32_t sclk, uint16_t virtual_voltage_Id, uint16_t *voltage); + uint32_t sclk, uint16_t virtual_voltage_Id, uint32_t *voltage); extern int atomctrl_get_smc_sclk_range_table(struct pp_hwmgr *hwmgr, struct pp_atom_ctrl_sclk_range_table *table); extern int atomctrl_get_avfs_information(struct pp_hwmgr *hwmgr, struct pp_atom_ctrl__avfs_parameters *param); diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/tonga_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/tonga_hwmgr.c index 233eb7f36c1d..5d0f655bf160 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/tonga_hwmgr.c +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/tonga_hwmgr.c @@ -1302,7 +1302,7 @@ static int tonga_populate_smc_mvdd_table(struct pp_hwmgr *hwmgr, table->Smio[count] |= data->mvdd_voltage_table.entries[count].smio_low; } - table->SmioMask2 = data->vddci_voltage_table.mask_low; + table->SmioMask2 = data->mvdd_voltage_table.mask_low; CONVERT_FROM_HOST_TO_SMC_UL(table->MvddLevelCount); } diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/tonga_processpptables.c b/drivers/gpu/drm/amd/powerplay/hwmgr/tonga_processpptables.c index 671fdb4d615a..dccc859f638c 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/tonga_processpptables.c +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/tonga_processpptables.c @@ -302,7 +302,7 @@ static int init_dpm_2_parameters( (((unsigned long)powerplay_table) + le16_to_cpu(powerplay_table->usPPMTableOffset)); if (0 != powerplay_table->usPPMTableOffset) { - if (1 == get_platform_power_management_table(hwmgr, atom_ppm_table)) { + if (get_platform_power_management_table(hwmgr, atom_ppm_table) == 0) { phm_cap_set(hwmgr->platform_descriptor.platformCaps, PHM_PlatformCaps_EnablePlatformPowerManagement); } diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c index f313b4d8344f..85c4debf47e0 100644 --- a/drivers/gpu/drm/i915/i915_drv.c +++ b/drivers/gpu/drm/i915/i915_drv.c @@ -512,6 +512,10 @@ void intel_detect_pch(struct drm_device *dev) DRM_DEBUG_KMS("Found SunrisePoint LP PCH\n"); WARN_ON(!IS_SKYLAKE(dev) && !IS_KABYLAKE(dev)); + } else if (id == INTEL_PCH_KBP_DEVICE_ID_TYPE) { + dev_priv->pch_type = PCH_KBP; + DRM_DEBUG_KMS("Found KabyPoint PCH\n"); + WARN_ON(!IS_KABYLAKE(dev)); } else if ((id == INTEL_PCH_P2X_DEVICE_ID_TYPE) || (id == INTEL_PCH_P3X_DEVICE_ID_TYPE) || ((id == INTEL_PCH_QEMU_DEVICE_ID_TYPE) && diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index 7c334e902266..bc3f2e6842e7 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -990,6 +990,7 @@ enum intel_pch { PCH_CPT, /* Cougarpoint PCH */ PCH_LPT, /* Lynxpoint PCH */ PCH_SPT, /* Sunrisepoint PCH */ + PCH_KBP, /* Kabypoint PCH */ PCH_NOP, }; @@ -2600,6 +2601,15 @@ struct drm_i915_cmd_table { #define IS_BXT_REVID(p, since, until) (IS_BROXTON(p) && IS_REVID(p, since, until)) +#define KBL_REVID_A0 0x0 +#define KBL_REVID_B0 0x1 +#define KBL_REVID_C0 0x2 +#define KBL_REVID_D0 0x3 +#define KBL_REVID_E0 0x4 + +#define IS_KBL_REVID(p, since, until) \ + (IS_KABYLAKE(p) && IS_REVID(p, since, until)) + /* * The genX designation typically refers to the render engine, so render * capability related checks should use IS_GEN, while display and other checks @@ -2708,11 +2718,13 @@ struct drm_i915_cmd_table { #define INTEL_PCH_LPT_LP_DEVICE_ID_TYPE 0x9c00 #define INTEL_PCH_SPT_DEVICE_ID_TYPE 0xA100 #define INTEL_PCH_SPT_LP_DEVICE_ID_TYPE 0x9D00 +#define INTEL_PCH_KBP_DEVICE_ID_TYPE 0xA200 #define INTEL_PCH_P2X_DEVICE_ID_TYPE 0x7100 #define INTEL_PCH_P3X_DEVICE_ID_TYPE 0x7000 #define INTEL_PCH_QEMU_DEVICE_ID_TYPE 0x2900 /* qemu q35 has 2918 */ #define INTEL_PCH_TYPE(dev) (__I915__(dev)->pch_type) +#define HAS_PCH_KBP(dev) (INTEL_PCH_TYPE(dev) == PCH_KBP) #define HAS_PCH_SPT(dev) (INTEL_PCH_TYPE(dev) == PCH_SPT) #define HAS_PCH_LPT(dev) (INTEL_PCH_TYPE(dev) == PCH_LPT) #define HAS_PCH_LPT_LP(dev) (__I915__(dev)->pch_id == INTEL_PCH_LPT_LP_DEVICE_ID_TYPE) diff --git a/drivers/gpu/drm/i915/i915_gem_shrinker.c b/drivers/gpu/drm/i915/i915_gem_shrinker.c index 425e721aac58..66571466e9a8 100644 --- a/drivers/gpu/drm/i915/i915_gem_shrinker.c +++ b/drivers/gpu/drm/i915/i915_gem_shrinker.c @@ -40,7 +40,7 @@ static bool mutex_is_locked_by(struct mutex *mutex, struct task_struct *task) if (!mutex_is_locked(mutex)) return false; -#if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_MUTEXES) +#if defined(CONFIG_DEBUG_MUTEXES) || defined(CONFIG_MUTEX_SPIN_ON_OWNER) return mutex->owner == task; #else /* Since UP may be pre-empted, we cannot assume that we own the lock */ diff --git a/drivers/gpu/drm/i915/i915_gem_stolen.c b/drivers/gpu/drm/i915/i915_gem_stolen.c index b7ce963fb8f8..44004e3f09e4 100644 --- a/drivers/gpu/drm/i915/i915_gem_stolen.c +++ b/drivers/gpu/drm/i915/i915_gem_stolen.c @@ -55,8 +55,10 @@ int i915_gem_stolen_insert_node_in_range(struct drm_i915_private *dev_priv, return -ENODEV; /* See the comment at the drm_mm_init() call for more about this check. - * WaSkipStolenMemoryFirstPage:bdw,chv (incomplete) */ - if (INTEL_INFO(dev_priv)->gen == 8 && start < 4096) + * WaSkipStolenMemoryFirstPage:bdw,chv,kbl (incomplete) + */ + if (start < 4096 && (IS_GEN8(dev_priv) || + IS_KBL_REVID(dev_priv, 0, KBL_REVID_A0))) start = 4096; mutex_lock(&dev_priv->mm.stolen_lock); diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c index 2f6fd33c07ba..aab47f7bb61b 100644 --- a/drivers/gpu/drm/i915/i915_irq.c +++ b/drivers/gpu/drm/i915/i915_irq.c @@ -2471,7 +2471,7 @@ gen8_de_irq_handler(struct drm_i915_private *dev_priv, u32 master_ctl) I915_WRITE(SDEIIR, iir); ret = IRQ_HANDLED; - if (HAS_PCH_SPT(dev_priv)) + if (HAS_PCH_SPT(dev_priv) || HAS_PCH_KBP(dev_priv)) spt_irq_handler(dev, iir); else cpt_irq_handler(dev, iir); @@ -4661,7 +4661,7 @@ void intel_irq_init(struct drm_i915_private *dev_priv) dev->driver->disable_vblank = gen8_disable_vblank; if (IS_BROXTON(dev)) dev_priv->display.hpd_irq_setup = bxt_hpd_irq_setup; - else if (HAS_PCH_SPT(dev)) + else if (HAS_PCH_SPT(dev) || HAS_PCH_KBP(dev)) dev_priv->display.hpd_irq_setup = spt_hpd_irq_setup; else dev_priv->display.hpd_irq_setup = ilk_hpd_irq_setup; diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index b407411e31ba..3fcf7dd5b6ca 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -220,6 +220,9 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg) #define ECOCHK_PPGTT_WT_HSW (0x2<<3) #define ECOCHK_PPGTT_WB_HSW (0x3<<3) +#define GEN8_CONFIG0 _MMIO(0xD00) +#define GEN9_DEFAULT_FIXES (1 << 3 | 1 << 2 | 1 << 1) + #define GAC_ECO_BITS _MMIO(0x14090) #define ECOBITS_SNB_BIT (1<<13) #define ECOBITS_PPGTT_CACHE64B (3<<8) @@ -1669,6 +1672,9 @@ enum skl_disp_power_wells { #define GEN7_TLB_RD_ADDR _MMIO(0x4700) +#define GAMT_CHKN_BIT_REG _MMIO(0x4ab8) +#define GAMT_CHKN_DISABLE_DYNAMIC_CREDIT_SHARING (1<<28) + #if 0 #define PRB0_TAIL _MMIO(0x2030) #define PRB0_HEAD _MMIO(0x2034) @@ -1804,6 +1810,10 @@ enum skl_disp_power_wells { #define GEN9_IZ_HASHING_MASK(slice) (0x3 << ((slice) * 2)) #define GEN9_IZ_HASHING(slice, val) ((val) << ((slice) * 2)) +/* chicken reg for WaConextSwitchWithConcurrentTLBInvalidate */ +#define GEN9_CSFE_CHICKEN1_RCS _MMIO(0x20D4) +#define GEN9_PREEMPT_GPGPU_SYNC_SWITCH_DISABLE (1 << 2) + /* WaClearTdlStateAckDirtyBits */ #define GEN8_STATE_ACK _MMIO(0x20F0) #define GEN9_STATE_ACK_SLICE1 _MMIO(0x20F8) @@ -2200,6 +2210,8 @@ enum skl_disp_power_wells { #define ILK_DPFC_STATUS _MMIO(0x43210) #define ILK_DPFC_FENCE_YOFF _MMIO(0x43218) #define ILK_DPFC_CHICKEN _MMIO(0x43224) +#define ILK_DPFC_DISABLE_DUMMY0 (1<<8) +#define ILK_DPFC_NUKE_ON_ANY_MODIFICATION (1<<23) #define ILK_FBC_RT_BASE _MMIO(0x2128) #define ILK_FBC_RT_VALID (1<<0) #define SNB_FBC_FRONT_BUFFER (1<<1) @@ -6031,6 +6043,7 @@ enum skl_disp_power_wells { #define CHICKEN_PAR1_1 _MMIO(0x42080) #define DPA_MASK_VBLANK_SRD (1 << 15) #define FORCE_ARB_IDLE_PLANES (1 << 14) +#define SKL_EDP_PSR_FIX_RDWRAP (1 << 3) #define _CHICKEN_PIPESL_1_A 0x420b0 #define _CHICKEN_PIPESL_1_B 0x420b4 @@ -6039,6 +6052,7 @@ enum skl_disp_power_wells { #define CHICKEN_PIPESL_1(pipe) _MMIO_PIPE(pipe, _CHICKEN_PIPESL_1_A, _CHICKEN_PIPESL_1_B) #define DISP_ARB_CTL _MMIO(0x45000) +#define DISP_FBC_MEMORY_WAKE (1<<31) #define DISP_TILE_SURFACE_SWIZZLING (1<<13) #define DISP_FBC_WM_DIS (1<<15) #define DISP_ARB_CTL2 _MMIO(0x45004) @@ -6052,6 +6066,9 @@ enum skl_disp_power_wells { #define HSW_NDE_RSTWRN_OPT _MMIO(0x46408) #define RESET_PCH_HANDSHAKE_ENABLE (1<<4) +#define GEN8_CHICKEN_DCPR_1 _MMIO(0x46430) +#define MASK_WAKEMEM (1<<13) + #define SKL_DFSM _MMIO(0x51000) #define SKL_DFSM_CDCLK_LIMIT_MASK (3 << 23) #define SKL_DFSM_CDCLK_LIMIT_675 (0 << 23) @@ -6069,6 +6086,7 @@ enum skl_disp_power_wells { #define GEN9_TSG_BARRIER_ACK_DISABLE (1<<8) #define GEN9_CS_DEBUG_MODE1 _MMIO(0x20ec) +#define GEN9_CTX_PREEMPT_REG _MMIO(0x2248) #define GEN8_CS_CHICKEN1 _MMIO(0x2580) /* GEN7 chicken */ @@ -6076,6 +6094,7 @@ enum skl_disp_power_wells { # define GEN7_CSC1_RHWO_OPT_DISABLE_IN_RCC ((1<<10) | (1<<26)) # define GEN9_RHWO_OPTIMIZATION_DISABLE (1<<14) #define COMMON_SLICE_CHICKEN2 _MMIO(0x7014) +# define GEN8_SBE_DISABLE_REPLAY_BUF_OPTIMIZATION (1<<8) # define GEN8_CSC2_SBE_VUE_CACHE_CONSERVATIVE (1<<0) #define HIZ_CHICKEN _MMIO(0x7018) @@ -6921,6 +6940,7 @@ enum skl_disp_power_wells { #define EDRAM_SETS_IDX(cap) (((cap) >> 8) & 0x3) #define GEN6_UCGCTL1 _MMIO(0x9400) +# define GEN6_GAMUNIT_CLOCK_GATE_DISABLE (1 << 22) # define GEN6_EU_TCUNIT_CLOCK_GATE_DISABLE (1 << 16) # define GEN6_BLBUNIT_CLOCK_GATE_DISABLE (1 << 5) # define GEN6_CSUNIT_CLOCK_GATE_DISABLE (1 << 7) @@ -6937,6 +6957,7 @@ enum skl_disp_power_wells { #define GEN7_UCGCTL4 _MMIO(0x940c) #define GEN7_L3BANK2X_CLOCK_GATE_DISABLE (1<<25) +#define GEN8_EU_GAUNIT_CLOCK_GATE_DISABLE (1<<14) #define GEN6_RCGCTL1 _MMIO(0x9410) #define GEN6_RCGCTL2 _MMIO(0x9414) diff --git a/drivers/gpu/drm/i915/intel_csr.c b/drivers/gpu/drm/i915/intel_csr.c index a34c23eceba0..2b3b428d9cd2 100644 --- a/drivers/gpu/drm/i915/intel_csr.c +++ b/drivers/gpu/drm/i915/intel_csr.c @@ -41,16 +41,22 @@ * be moved to FW_FAILED. */ +#define I915_CSR_KBL "i915/kbl_dmc_ver1.bin" +MODULE_FIRMWARE(I915_CSR_KBL); +#define KBL_CSR_VERSION_REQUIRED CSR_VERSION(1, 1) + #define I915_CSR_SKL "i915/skl_dmc_ver1.bin" +MODULE_FIRMWARE(I915_CSR_SKL); +#define SKL_CSR_VERSION_REQUIRED CSR_VERSION(1, 23) + #define I915_CSR_BXT "i915/bxt_dmc_ver1.bin" +MODULE_FIRMWARE(I915_CSR_BXT); +#define BXT_CSR_VERSION_REQUIRED CSR_VERSION(1, 7) #define FIRMWARE_URL "https://01.org/linuxgraphics/intel-linux-graphics-firmwares" -MODULE_FIRMWARE(I915_CSR_SKL); -MODULE_FIRMWARE(I915_CSR_BXT); -#define SKL_CSR_VERSION_REQUIRED CSR_VERSION(1, 23) -#define BXT_CSR_VERSION_REQUIRED CSR_VERSION(1, 7) + #define CSR_MAX_FW_SIZE 0x2FFF #define CSR_DEFAULT_FW_OFFSET 0xFFFFFFFF @@ -169,12 +175,10 @@ struct stepping_info { char substepping; }; -/* - * Kabylake derivated from Skylake H0, so SKL H0 - * is the right firmware for KBL A0 (revid 0). - */ static const struct stepping_info kbl_stepping_info[] = { - {'H', '0'}, {'I', '0'} + {'A', '0'}, {'B', '0'}, {'C', '0'}, + {'D', '0'}, {'E', '0'}, {'F', '0'}, + {'G', '0'}, {'H', '0'}, {'I', '0'}, }; static const struct stepping_info skl_stepping_info[] = { @@ -298,7 +302,9 @@ static uint32_t *parse_csr_fw(struct drm_i915_private *dev_priv, csr->version = css_header->version; - if (IS_SKYLAKE(dev_priv) || IS_KABYLAKE(dev_priv)) { + if (IS_KABYLAKE(dev_priv)) { + required_min_version = KBL_CSR_VERSION_REQUIRED; + } else if (IS_SKYLAKE(dev_priv)) { required_min_version = SKL_CSR_VERSION_REQUIRED; } else if (IS_BROXTON(dev_priv)) { required_min_version = BXT_CSR_VERSION_REQUIRED; @@ -446,7 +452,9 @@ void intel_csr_ucode_init(struct drm_i915_private *dev_priv) if (!HAS_CSR(dev_priv)) return; - if (IS_SKYLAKE(dev_priv) || IS_KABYLAKE(dev_priv)) + if (IS_KABYLAKE(dev_priv)) + csr->fw_path = I915_CSR_KBL; + else if (IS_SKYLAKE(dev_priv)) csr->fw_path = I915_CSR_SKL; else if (IS_BROXTON(dev_priv)) csr->fw_path = I915_CSR_BXT; diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c index 04452cf3eae8..3074c56a643d 100644 --- a/drivers/gpu/drm/i915/intel_display.c +++ b/drivers/gpu/drm/i915/intel_display.c @@ -11997,6 +11997,12 @@ static int intel_crtc_atomic_check(struct drm_crtc *crtc, ret = intel_color_check(crtc, crtc_state); if (ret) return ret; + + /* + * Changing color management on Intel hardware is + * handled as part of planes update. + */ + crtc_state->planes_changed = true; } ret = 0; diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c index 40745e38d438..891107f92d9f 100644 --- a/drivers/gpu/drm/i915/intel_dp.c +++ b/drivers/gpu/drm/i915/intel_dp.c @@ -4645,7 +4645,7 @@ intel_dp_detect(struct drm_connector *connector, bool force) intel_dp->detect_done = false; - if (intel_connector->detect_edid) + if (is_edp(intel_dp) || intel_connector->detect_edid) return connector_status_connected; else return connector_status_disconnected; diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c index 42eac37de047..7f2d8415ed8b 100644 --- a/drivers/gpu/drm/i915/intel_lrc.c +++ b/drivers/gpu/drm/i915/intel_lrc.c @@ -1103,15 +1103,17 @@ static inline int gen8_emit_flush_coherentl3_wa(struct intel_engine_cs *engine, uint32_t *const batch, uint32_t index) { + struct drm_i915_private *dev_priv = engine->dev->dev_private; uint32_t l3sqc4_flush = (0x40400000 | GEN8_LQSC_FLUSH_COHERENT_LINES); /* - * WaDisableLSQCROPERFforOCL:skl + * WaDisableLSQCROPERFforOCL:skl,kbl * This WA is implemented in skl_init_clock_gating() but since * this batch updates GEN8_L3SQCREG4 with default value we need to * set this bit here to retain the WA during flush. */ - if (IS_SKL_REVID(engine->dev, 0, SKL_REVID_E0)) + if (IS_SKL_REVID(dev_priv, 0, SKL_REVID_E0) || + IS_KBL_REVID(dev_priv, 0, KBL_REVID_E0)) l3sqc4_flush |= GEN8_LQSC_RO_PERF_DIS; wa_ctx_emit(batch, index, (MI_STORE_REGISTER_MEM_GEN8 | @@ -1273,6 +1275,7 @@ static int gen9_init_indirectctx_bb(struct intel_engine_cs *engine, { int ret; struct drm_device *dev = engine->dev; + struct drm_i915_private *dev_priv = dev->dev_private; uint32_t index = wa_ctx_start(wa_ctx, *offset, CACHELINE_DWORDS); /* WaDisableCtxRestoreArbitration:skl,bxt */ @@ -1286,6 +1289,22 @@ static int gen9_init_indirectctx_bb(struct intel_engine_cs *engine, return ret; index = ret; + /* WaClearSlmSpaceAtContextSwitch:kbl */ + /* Actual scratch location is at 128 bytes offset */ + if (IS_KBL_REVID(dev_priv, 0, KBL_REVID_A0)) { + uint32_t scratch_addr + = engine->scratch.gtt_offset + 2*CACHELINE_BYTES; + + wa_ctx_emit(batch, index, GFX_OP_PIPE_CONTROL(6)); + wa_ctx_emit(batch, index, (PIPE_CONTROL_FLUSH_L3 | + PIPE_CONTROL_GLOBAL_GTT_IVB | + PIPE_CONTROL_CS_STALL | + PIPE_CONTROL_QW_WRITE)); + wa_ctx_emit(batch, index, scratch_addr); + wa_ctx_emit(batch, index, 0); + wa_ctx_emit(batch, index, 0); + wa_ctx_emit(batch, index, 0); + } /* Pad to end of cacheline */ while (index % CACHELINE_DWORDS) wa_ctx_emit(batch, index, MI_NOOP); @@ -1687,9 +1706,10 @@ static int gen8_emit_flush_render(struct drm_i915_gem_request *request, struct intel_ringbuffer *ringbuf = request->ringbuf; struct intel_engine_cs *engine = ringbuf->engine; u32 scratch_addr = engine->scratch.gtt_offset + 2 * CACHELINE_BYTES; - bool vf_flush_wa = false; + bool vf_flush_wa = false, dc_flush_wa = false; u32 flags = 0; int ret; + int len; flags |= PIPE_CONTROL_CS_STALL; @@ -1716,9 +1736,21 @@ static int gen8_emit_flush_render(struct drm_i915_gem_request *request, */ if (IS_GEN9(engine->dev)) vf_flush_wa = true; + + /* WaForGAMHang:kbl */ + if (IS_KBL_REVID(request->i915, 0, KBL_REVID_B0)) + dc_flush_wa = true; } - ret = intel_ring_begin(request, vf_flush_wa ? 12 : 6); + len = 6; + + if (vf_flush_wa) + len += 6; + + if (dc_flush_wa) + len += 12; + + ret = intel_ring_begin(request, len); if (ret) return ret; @@ -1731,12 +1763,31 @@ static int gen8_emit_flush_render(struct drm_i915_gem_request *request, intel_logical_ring_emit(ringbuf, 0); } + if (dc_flush_wa) { + intel_logical_ring_emit(ringbuf, GFX_OP_PIPE_CONTROL(6)); + intel_logical_ring_emit(ringbuf, PIPE_CONTROL_DC_FLUSH_ENABLE); + intel_logical_ring_emit(ringbuf, 0); + intel_logical_ring_emit(ringbuf, 0); + intel_logical_ring_emit(ringbuf, 0); + intel_logical_ring_emit(ringbuf, 0); + } + intel_logical_ring_emit(ringbuf, GFX_OP_PIPE_CONTROL(6)); intel_logical_ring_emit(ringbuf, flags); intel_logical_ring_emit(ringbuf, scratch_addr); intel_logical_ring_emit(ringbuf, 0); intel_logical_ring_emit(ringbuf, 0); intel_logical_ring_emit(ringbuf, 0); + + if (dc_flush_wa) { + intel_logical_ring_emit(ringbuf, GFX_OP_PIPE_CONTROL(6)); + intel_logical_ring_emit(ringbuf, PIPE_CONTROL_CS_STALL); + intel_logical_ring_emit(ringbuf, 0); + intel_logical_ring_emit(ringbuf, 0); + intel_logical_ring_emit(ringbuf, 0); + intel_logical_ring_emit(ringbuf, 0); + } + intel_logical_ring_advance(ringbuf); return 0; diff --git a/drivers/gpu/drm/i915/intel_opregion.c b/drivers/gpu/drm/i915/intel_opregion.c index 99e26034ae8d..16e209d326b6 100644 --- a/drivers/gpu/drm/i915/intel_opregion.c +++ b/drivers/gpu/drm/i915/intel_opregion.c @@ -1038,5 +1038,16 @@ intel_opregion_get_panel_type(struct drm_device *dev) return -ENODEV; } + /* + * FIXME On Dell XPS 13 9350 the OpRegion panel type (0) gives us + * low vswing for eDP, whereas the VBT panel type (2) gives us normal + * vswing instead. Low vswing results in some display flickers, so + * let's simply ignore the OpRegion panel type on SKL for now. + */ + if (IS_SKYLAKE(dev)) { + DRM_DEBUG_KMS("Ignoring OpRegion panel type (%d)\n", ret - 1); + return -ENODEV; + } + return ret - 1; } diff --git a/drivers/gpu/drm/i915/intel_panel.c b/drivers/gpu/drm/i915/intel_panel.c index 8357d571553a..aba94099886b 100644 --- a/drivers/gpu/drm/i915/intel_panel.c +++ b/drivers/gpu/drm/i915/intel_panel.c @@ -1731,7 +1731,8 @@ intel_panel_init_backlight_funcs(struct intel_panel *panel) panel->backlight.set = bxt_set_backlight; panel->backlight.get = bxt_get_backlight; panel->backlight.hz_to_pwm = bxt_hz_to_pwm; - } else if (HAS_PCH_LPT(dev_priv) || HAS_PCH_SPT(dev_priv)) { + } else if (HAS_PCH_LPT(dev_priv) || HAS_PCH_SPT(dev_priv) || + HAS_PCH_KBP(dev_priv)) { panel->backlight.setup = lpt_setup_backlight; panel->backlight.enable = lpt_enable_backlight; panel->backlight.disable = lpt_disable_backlight; diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c index a7ef45da0a9e..2863b92c9da6 100644 --- a/drivers/gpu/drm/i915/intel_pm.c +++ b/drivers/gpu/drm/i915/intel_pm.c @@ -54,10 +54,38 @@ #define INTEL_RC6p_ENABLE (1<<1) #define INTEL_RC6pp_ENABLE (1<<2) +static void gen9_init_clock_gating(struct drm_device *dev) +{ + struct drm_i915_private *dev_priv = dev->dev_private; + + /* See Bspec note for PSR2_CTL bit 31, Wa#828:skl,bxt,kbl */ + I915_WRITE(CHICKEN_PAR1_1, + I915_READ(CHICKEN_PAR1_1) | SKL_EDP_PSR_FIX_RDWRAP); + + I915_WRITE(GEN8_CONFIG0, + I915_READ(GEN8_CONFIG0) | GEN9_DEFAULT_FIXES); + + /* WaEnableChickenDCPR:skl,bxt,kbl */ + I915_WRITE(GEN8_CHICKEN_DCPR_1, + I915_READ(GEN8_CHICKEN_DCPR_1) | MASK_WAKEMEM); + + /* WaFbcTurnOffFbcWatermark:skl,bxt,kbl */ + /* WaFbcWakeMemOn:skl,bxt,kbl */ + I915_WRITE(DISP_ARB_CTL, I915_READ(DISP_ARB_CTL) | + DISP_FBC_WM_DIS | + DISP_FBC_MEMORY_WAKE); + + /* WaFbcHighMemBwCorruptionAvoidance:skl,bxt,kbl */ + I915_WRITE(ILK_DPFC_CHICKEN, I915_READ(ILK_DPFC_CHICKEN) | + ILK_DPFC_DISABLE_DUMMY0); +} + static void bxt_init_clock_gating(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; + gen9_init_clock_gating(dev); + /* WaDisableSDEUnitClockGating:bxt */ I915_WRITE(GEN8_UCGCTL6, I915_READ(GEN8_UCGCTL6) | GEN8_SDEUNIT_CLOCK_GATE_DISABLE); @@ -6698,6 +6726,38 @@ static void lpt_suspend_hw(struct drm_device *dev) } } +static void kabylake_init_clock_gating(struct drm_device *dev) +{ + struct drm_i915_private *dev_priv = dev->dev_private; + + gen9_init_clock_gating(dev); + + /* WaDisableSDEUnitClockGating:kbl */ + if (IS_KBL_REVID(dev_priv, 0, KBL_REVID_B0)) + I915_WRITE(GEN8_UCGCTL6, I915_READ(GEN8_UCGCTL6) | + GEN8_SDEUNIT_CLOCK_GATE_DISABLE); + + /* WaDisableGamClockGating:kbl */ + if (IS_KBL_REVID(dev_priv, 0, KBL_REVID_B0)) + I915_WRITE(GEN6_UCGCTL1, I915_READ(GEN6_UCGCTL1) | + GEN6_GAMUNIT_CLOCK_GATE_DISABLE); + + /* WaFbcNukeOnHostModify:kbl */ + I915_WRITE(ILK_DPFC_CHICKEN, I915_READ(ILK_DPFC_CHICKEN) | + ILK_DPFC_NUKE_ON_ANY_MODIFICATION); +} + +static void skylake_init_clock_gating(struct drm_device *dev) +{ + struct drm_i915_private *dev_priv = dev->dev_private; + + gen9_init_clock_gating(dev); + + /* WaFbcNukeOnHostModify:skl */ + I915_WRITE(ILK_DPFC_CHICKEN, I915_READ(ILK_DPFC_CHICKEN) | + ILK_DPFC_NUKE_ON_ANY_MODIFICATION); +} + static void broadwell_init_clock_gating(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; @@ -7163,9 +7223,9 @@ static void nop_init_clock_gating(struct drm_device *dev) void intel_init_clock_gating_hooks(struct drm_i915_private *dev_priv) { if (IS_SKYLAKE(dev_priv)) - dev_priv->display.init_clock_gating = nop_init_clock_gating; + dev_priv->display.init_clock_gating = skylake_init_clock_gating; else if (IS_KABYLAKE(dev_priv)) - dev_priv->display.init_clock_gating = nop_init_clock_gating; + dev_priv->display.init_clock_gating = kabylake_init_clock_gating; else if (IS_BROXTON(dev_priv)) dev_priv->display.init_clock_gating = bxt_init_clock_gating; else if (IS_BROADWELL(dev_priv)) diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c index 04402bb9d26b..68c5af079ef8 100644 --- a/drivers/gpu/drm/i915/intel_ringbuffer.c +++ b/drivers/gpu/drm/i915/intel_ringbuffer.c @@ -913,24 +913,26 @@ static int gen9_init_workarounds(struct intel_engine_cs *engine) { struct drm_device *dev = engine->dev; struct drm_i915_private *dev_priv = dev->dev_private; - uint32_t tmp; int ret; - /* WaEnableLbsSlaRetryTimerDecrement:skl */ + /* WaConextSwitchWithConcurrentTLBInvalidate:skl,bxt,kbl */ + I915_WRITE(GEN9_CSFE_CHICKEN1_RCS, _MASKED_BIT_ENABLE(GEN9_PREEMPT_GPGPU_SYNC_SWITCH_DISABLE)); + + /* WaEnableLbsSlaRetryTimerDecrement:skl,bxt,kbl */ I915_WRITE(BDW_SCRATCH1, I915_READ(BDW_SCRATCH1) | GEN9_LBS_SLA_RETRY_TIMER_DECREMENT_ENABLE); - /* WaDisableKillLogic:bxt,skl */ + /* WaDisableKillLogic:bxt,skl,kbl */ I915_WRITE(GAM_ECOCHK, I915_READ(GAM_ECOCHK) | ECOCHK_DIS_TLB); - /* WaClearFlowControlGpgpuContextSave:skl,bxt */ - /* WaDisablePartialInstShootdown:skl,bxt */ + /* WaClearFlowControlGpgpuContextSave:skl,bxt,kbl */ + /* WaDisablePartialInstShootdown:skl,bxt,kbl */ WA_SET_BIT_MASKED(GEN8_ROW_CHICKEN, FLOW_CONTROL_ENABLE | PARTIAL_INSTRUCTION_SHOOTDOWN_DISABLE); - /* Syncing dependencies between camera and graphics:skl,bxt */ + /* Syncing dependencies between camera and graphics:skl,bxt,kbl */ WA_SET_BIT_MASKED(HALF_SLICE_CHICKEN3, GEN9_DISABLE_OCL_OOB_SUPPRESS_LOGIC); @@ -952,18 +954,18 @@ static int gen9_init_workarounds(struct intel_engine_cs *engine) */ } - /* WaEnableYV12BugFixInHalfSliceChicken7:skl,bxt */ - /* WaEnableSamplerGPGPUPreemptionSupport:skl,bxt */ + /* WaEnableYV12BugFixInHalfSliceChicken7:skl,bxt,kbl */ + /* WaEnableSamplerGPGPUPreemptionSupport:skl,bxt,kbl */ WA_SET_BIT_MASKED(GEN9_HALF_SLICE_CHICKEN7, GEN9_ENABLE_YV12_BUGFIX | GEN9_ENABLE_GPGPU_PREEMPTION); - /* Wa4x4STCOptimizationDisable:skl,bxt */ - /* WaDisablePartialResolveInVc:skl,bxt */ + /* Wa4x4STCOptimizationDisable:skl,bxt,kbl */ + /* WaDisablePartialResolveInVc:skl,bxt,kbl */ WA_SET_BIT_MASKED(CACHE_MODE_1, (GEN8_4x4_STC_OPTIMIZATION_DISABLE | GEN9_PARTIAL_RESOLVE_IN_VC_DISABLE)); - /* WaCcsTlbPrefetchDisable:skl,bxt */ + /* WaCcsTlbPrefetchDisable:skl,bxt,kbl */ WA_CLR_BIT_MASKED(GEN9_HALF_SLICE_CHICKEN5, GEN9_CCS_TLB_PREFETCH_ENABLE); @@ -973,31 +975,57 @@ static int gen9_init_workarounds(struct intel_engine_cs *engine) WA_SET_BIT_MASKED(SLICE_ECO_CHICKEN0, PIXEL_MASK_CAMMING_DISABLE); - /* WaForceContextSaveRestoreNonCoherent:skl,bxt */ - tmp = HDC_FORCE_CONTEXT_SAVE_RESTORE_NON_COHERENT; - if (IS_SKL_REVID(dev, SKL_REVID_F0, REVID_FOREVER) || - IS_BXT_REVID(dev, BXT_REVID_B0, REVID_FOREVER)) - tmp |= HDC_FORCE_CSR_NON_COHERENT_OVR_DISABLE; - WA_SET_BIT_MASKED(HDC_CHICKEN0, tmp); + /* WaForceContextSaveRestoreNonCoherent:skl,bxt,kbl */ + WA_SET_BIT_MASKED(HDC_CHICKEN0, + HDC_FORCE_CONTEXT_SAVE_RESTORE_NON_COHERENT | + HDC_FORCE_CSR_NON_COHERENT_OVR_DISABLE); + + /* WaForceEnableNonCoherent and WaDisableHDCInvalidation are + * both tied to WaForceContextSaveRestoreNonCoherent + * in some hsds for skl. We keep the tie for all gen9. The + * documentation is a bit hazy and so we want to get common behaviour, + * even though there is no clear evidence we would need both on kbl/bxt. + * This area has been source of system hangs so we play it safe + * and mimic the skl regardless of what bspec says. + * + * Use Force Non-Coherent whenever executing a 3D context. This + * is a workaround for a possible hang in the unlikely event + * a TLB invalidation occurs during a PSD flush. + */ - /* WaDisableSamplerPowerBypassForSOPingPong:skl,bxt */ - if (IS_SKYLAKE(dev) || IS_BXT_REVID(dev, 0, BXT_REVID_B0)) + /* WaForceEnableNonCoherent:skl,bxt,kbl */ + WA_SET_BIT_MASKED(HDC_CHICKEN0, + HDC_FORCE_NON_COHERENT); + + /* WaDisableHDCInvalidation:skl,bxt,kbl */ + I915_WRITE(GAM_ECOCHK, I915_READ(GAM_ECOCHK) | + BDW_DISABLE_HDC_INVALIDATION); + + /* WaDisableSamplerPowerBypassForSOPingPong:skl,bxt,kbl */ + if (IS_SKYLAKE(dev_priv) || + IS_KABYLAKE(dev_priv) || + IS_BXT_REVID(dev_priv, 0, BXT_REVID_B0)) WA_SET_BIT_MASKED(HALF_SLICE_CHICKEN3, GEN8_SAMPLER_POWER_BYPASS_DIS); - /* WaDisableSTUnitPowerOptimization:skl,bxt */ + /* WaDisableSTUnitPowerOptimization:skl,bxt,kbl */ WA_SET_BIT_MASKED(HALF_SLICE_CHICKEN2, GEN8_ST_PO_DISABLE); - /* WaOCLCoherentLineFlush:skl,bxt */ + /* WaOCLCoherentLineFlush:skl,bxt,kbl */ I915_WRITE(GEN8_L3SQCREG4, (I915_READ(GEN8_L3SQCREG4) | GEN8_LQSC_FLUSH_COHERENT_LINES)); - /* WaEnablePreemptionGranularityControlByUMD:skl,bxt */ + /* WaVFEStateAfterPipeControlwithMediaStateClear:skl,bxt */ + ret = wa_ring_whitelist_reg(engine, GEN9_CTX_PREEMPT_REG); + if (ret) + return ret; + + /* WaEnablePreemptionGranularityControlByUMD:skl,bxt,kbl */ ret= wa_ring_whitelist_reg(engine, GEN8_CS_CHICKEN1); if (ret) return ret; - /* WaAllowUMDToModifyHDCChicken1:skl,bxt */ + /* WaAllowUMDToModifyHDCChicken1:skl,bxt,kbl */ ret = wa_ring_whitelist_reg(engine, GEN8_HDC_CHICKEN1); if (ret) return ret; @@ -1092,22 +1120,6 @@ static int skl_init_workarounds(struct intel_engine_cs *engine) WA_SET_BIT_MASKED(HIZ_CHICKEN, BDW_HIZ_POWER_COMPILER_CLOCK_GATING_DISABLE); - /* This is tied to WaForceContextSaveRestoreNonCoherent */ - if (IS_SKL_REVID(dev, 0, REVID_FOREVER)) { - /* - *Use Force Non-Coherent whenever executing a 3D context. This - * is a workaround for a possible hang in the unlikely event - * a TLB invalidation occurs during a PSD flush. - */ - /* WaForceEnableNonCoherent:skl */ - WA_SET_BIT_MASKED(HDC_CHICKEN0, - HDC_FORCE_NON_COHERENT); - - /* WaDisableHDCInvalidation:skl */ - I915_WRITE(GAM_ECOCHK, I915_READ(GAM_ECOCHK) | - BDW_DISABLE_HDC_INVALIDATION); - } - /* WaBarrierPerformanceFixDisable:skl */ if (IS_SKL_REVID(dev, SKL_REVID_C0, SKL_REVID_D0)) WA_SET_BIT_MASKED(HDC_CHICKEN0, @@ -1120,6 +1132,9 @@ static int skl_init_workarounds(struct intel_engine_cs *engine) GEN7_HALF_SLICE_CHICKEN1, GEN7_SBE_SS_CACHE_DISPATCH_PORT_SHARING_DISABLE); + /* WaDisableGafsUnitClkGating:skl */ + WA_SET_BIT(GEN7_UCGCTL4, GEN8_EU_GAUNIT_CLOCK_GATE_DISABLE); + /* WaDisableLSQCROPERFforOCL:skl */ ret = wa_ring_whitelist_reg(engine, GEN8_L3SQCREG4); if (ret) @@ -1174,6 +1189,63 @@ static int bxt_init_workarounds(struct intel_engine_cs *engine) return ret; } + /* WaInsertDummyPushConstPs:bxt */ + if (IS_BXT_REVID(dev_priv, 0, BXT_REVID_B0)) + WA_SET_BIT_MASKED(COMMON_SLICE_CHICKEN2, + GEN8_SBE_DISABLE_REPLAY_BUF_OPTIMIZATION); + + return 0; +} + +static int kbl_init_workarounds(struct intel_engine_cs *engine) +{ + struct drm_i915_private *dev_priv = engine->dev->dev_private; + int ret; + + ret = gen9_init_workarounds(engine); + if (ret) + return ret; + + /* WaEnableGapsTsvCreditFix:kbl */ + I915_WRITE(GEN8_GARBCNTL, (I915_READ(GEN8_GARBCNTL) | + GEN9_GAPS_TSV_CREDIT_DISABLE)); + + /* WaDisableDynamicCreditSharing:kbl */ + if (IS_KBL_REVID(dev_priv, 0, KBL_REVID_B0)) + WA_SET_BIT(GAMT_CHKN_BIT_REG, + GAMT_CHKN_DISABLE_DYNAMIC_CREDIT_SHARING); + + /* WaDisableFenceDestinationToSLM:kbl (pre-prod) */ + if (IS_KBL_REVID(dev_priv, KBL_REVID_A0, KBL_REVID_A0)) + WA_SET_BIT_MASKED(HDC_CHICKEN0, + HDC_FENCE_DEST_SLM_DISABLE); + + /* GEN8_L3SQCREG4 has a dependency with WA batch so any new changes + * involving this register should also be added to WA batch as required. + */ + if (IS_KBL_REVID(dev_priv, 0, KBL_REVID_E0)) + /* WaDisableLSQCROPERFforOCL:kbl */ + I915_WRITE(GEN8_L3SQCREG4, I915_READ(GEN8_L3SQCREG4) | + GEN8_LQSC_RO_PERF_DIS); + + /* WaInsertDummyPushConstPs:kbl */ + if (IS_KBL_REVID(dev_priv, 0, KBL_REVID_B0)) + WA_SET_BIT_MASKED(COMMON_SLICE_CHICKEN2, + GEN8_SBE_DISABLE_REPLAY_BUF_OPTIMIZATION); + + /* WaDisableGafsUnitClkGating:kbl */ + WA_SET_BIT(GEN7_UCGCTL4, GEN8_EU_GAUNIT_CLOCK_GATE_DISABLE); + + /* WaDisableSbeCacheDispatchPortSharing:kbl */ + WA_SET_BIT_MASKED( + GEN7_HALF_SLICE_CHICKEN1, + GEN7_SBE_SS_CACHE_DISPATCH_PORT_SHARING_DISABLE); + + /* WaDisableLSQCROPERFforOCL:kbl */ + ret = wa_ring_whitelist_reg(engine, GEN8_L3SQCREG4); + if (ret) + return ret; + return 0; } @@ -1199,6 +1271,9 @@ int init_workarounds_ring(struct intel_engine_cs *engine) if (IS_BROXTON(dev)) return bxt_init_workarounds(engine); + if (IS_KABYLAKE(dev_priv)) + return kbl_init_workarounds(engine); + return 0; } diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/sorgf119.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/sorgf119.c index 22706c0a54b5..49bd5da194e1 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/sorgf119.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/sorgf119.c @@ -40,7 +40,8 @@ static int gf119_sor_dp_pattern(struct nvkm_output_dp *outp, int pattern) { struct nvkm_device *device = outp->base.disp->engine.subdev.device; - nvkm_mask(device, 0x61c110, 0x0f0f0f0f, 0x01010101 * pattern); + const u32 soff = gf119_sor_soff(outp); + nvkm_mask(device, 0x61c110 + soff, 0x0f0f0f0f, 0x01010101 * pattern); return 0; } diff --git a/drivers/gpu/drm/sun4i/sun4i_crtc.c b/drivers/gpu/drm/sun4i/sun4i_crtc.c index 4182a21f5923..41cacecbea9a 100644 --- a/drivers/gpu/drm/sun4i/sun4i_crtc.c +++ b/drivers/gpu/drm/sun4i/sun4i_crtc.c @@ -65,6 +65,14 @@ static void sun4i_crtc_disable(struct drm_crtc *crtc) DRM_DEBUG_DRIVER("Disabling the CRTC\n"); sun4i_tcon_disable(drv->tcon); + + if (crtc->state->event && !crtc->state->active) { + spin_lock_irq(&crtc->dev->event_lock); + drm_crtc_send_vblank_event(crtc, crtc->state->event); + spin_unlock_irq(&crtc->dev->event_lock); + + crtc->state->event = NULL; + } } static void sun4i_crtc_enable(struct drm_crtc *crtc) diff --git a/drivers/gpu/drm/sun4i/sun4i_drv.c b/drivers/gpu/drm/sun4i/sun4i_drv.c index 257d2b4f3645..937394cbc241 100644 --- a/drivers/gpu/drm/sun4i/sun4i_drv.c +++ b/drivers/gpu/drm/sun4i/sun4i_drv.c @@ -92,7 +92,7 @@ static struct drm_driver sun4i_drv_driver = { /* Frame Buffer Operations */ /* VBlank Operations */ - .get_vblank_counter = drm_vblank_count, + .get_vblank_counter = drm_vblank_no_hw_counter, .enable_vblank = sun4i_drv_enable_vblank, .disable_vblank = sun4i_drv_disable_vblank, }; @@ -310,6 +310,7 @@ static int sun4i_drv_probe(struct platform_device *pdev) count += sun4i_drv_add_endpoints(&pdev->dev, &match, pipeline); + of_node_put(pipeline); DRM_DEBUG_DRIVER("Queued %d outputs on pipeline %d\n", count, i); diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c index 39386f50af87..a71cf98c655f 100644 --- a/drivers/gpu/drm/ttm/ttm_bo.c +++ b/drivers/gpu/drm/ttm/ttm_bo.c @@ -1034,9 +1034,9 @@ out_unlock: return ret; } -static bool ttm_bo_mem_compat(struct ttm_placement *placement, - struct ttm_mem_reg *mem, - uint32_t *new_flags) +bool ttm_bo_mem_compat(struct ttm_placement *placement, + struct ttm_mem_reg *mem, + uint32_t *new_flags) { int i; @@ -1068,6 +1068,7 @@ static bool ttm_bo_mem_compat(struct ttm_placement *placement, return false; } +EXPORT_SYMBOL(ttm_bo_mem_compat); int ttm_bo_validate(struct ttm_buffer_object *bo, struct ttm_placement *placement, diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_dmabuf.c b/drivers/gpu/drm/vmwgfx/vmwgfx_dmabuf.c index 9b078a493996..0cd889015dc5 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_dmabuf.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_dmabuf.c @@ -49,6 +49,7 @@ int vmw_dmabuf_pin_in_placement(struct vmw_private *dev_priv, { struct ttm_buffer_object *bo = &buf->base; int ret; + uint32_t new_flags; ret = ttm_write_lock(&dev_priv->reservation_sem, interruptible); if (unlikely(ret != 0)) @@ -60,7 +61,12 @@ int vmw_dmabuf_pin_in_placement(struct vmw_private *dev_priv, if (unlikely(ret != 0)) goto err; - ret = ttm_bo_validate(bo, placement, interruptible, false); + if (buf->pin_count > 0) + ret = ttm_bo_mem_compat(placement, &bo->mem, + &new_flags) == true ? 0 : -EINVAL; + else + ret = ttm_bo_validate(bo, placement, interruptible, false); + if (!ret) vmw_bo_pin_reserved(buf, true); @@ -91,6 +97,7 @@ int vmw_dmabuf_pin_in_vram_or_gmr(struct vmw_private *dev_priv, { struct ttm_buffer_object *bo = &buf->base; int ret; + uint32_t new_flags; ret = ttm_write_lock(&dev_priv->reservation_sem, interruptible); if (unlikely(ret != 0)) @@ -102,6 +109,12 @@ int vmw_dmabuf_pin_in_vram_or_gmr(struct vmw_private *dev_priv, if (unlikely(ret != 0)) goto err; + if (buf->pin_count > 0) { + ret = ttm_bo_mem_compat(&vmw_vram_gmr_placement, &bo->mem, + &new_flags) == true ? 0 : -EINVAL; + goto out_unreserve; + } + ret = ttm_bo_validate(bo, &vmw_vram_gmr_placement, interruptible, false); if (likely(ret == 0) || ret == -ERESTARTSYS) @@ -161,6 +174,7 @@ int vmw_dmabuf_pin_in_start_of_vram(struct vmw_private *dev_priv, struct ttm_placement placement; struct ttm_place place; int ret = 0; + uint32_t new_flags; place = vmw_vram_placement.placement[0]; place.lpfn = bo->num_pages; @@ -185,10 +199,15 @@ int vmw_dmabuf_pin_in_start_of_vram(struct vmw_private *dev_priv, */ if (bo->mem.mem_type == TTM_PL_VRAM && bo->mem.start < bo->num_pages && - bo->mem.start > 0) + bo->mem.start > 0 && + buf->pin_count == 0) (void) ttm_bo_validate(bo, &vmw_sys_placement, false, false); - ret = ttm_bo_validate(bo, &placement, interruptible, false); + if (buf->pin_count > 0) + ret = ttm_bo_mem_compat(&placement, &bo->mem, + &new_flags) == true ? 0 : -EINVAL; + else + ret = ttm_bo_validate(bo, &placement, interruptible, false); /* For some reason we didn't end up at the start of vram */ WARN_ON(ret == 0 && bo->offset != 0); diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c index 9fcd8200d485..8d528fcf6e96 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c @@ -233,6 +233,7 @@ static int vmw_force_iommu; static int vmw_restrict_iommu; static int vmw_force_coherent; static int vmw_restrict_dma_mask; +static int vmw_assume_16bpp; static int vmw_probe(struct pci_dev *, const struct pci_device_id *); static void vmw_master_init(struct vmw_master *); @@ -249,6 +250,8 @@ MODULE_PARM_DESC(force_coherent, "Force coherent TTM pages"); module_param_named(force_coherent, vmw_force_coherent, int, 0600); MODULE_PARM_DESC(restrict_dma_mask, "Restrict DMA mask to 44 bits with IOMMU"); module_param_named(restrict_dma_mask, vmw_restrict_dma_mask, int, 0600); +MODULE_PARM_DESC(assume_16bpp, "Assume 16-bpp when filtering modes"); +module_param_named(assume_16bpp, vmw_assume_16bpp, int, 0600); static void vmw_print_capabilities(uint32_t capabilities) @@ -660,6 +663,8 @@ static int vmw_driver_load(struct drm_device *dev, unsigned long chipset) dev_priv->vram_start = pci_resource_start(dev->pdev, 1); dev_priv->mmio_start = pci_resource_start(dev->pdev, 2); + dev_priv->assume_16bpp = !!vmw_assume_16bpp; + dev_priv->enable_fb = enable_fbdev; vmw_write(dev_priv, SVGA_REG_ID, SVGA_ID_2); @@ -706,6 +711,13 @@ static int vmw_driver_load(struct drm_device *dev, unsigned long chipset) vmw_read(dev_priv, SVGA_REG_SUGGESTED_GBOBJECT_MEM_SIZE_KB); + /* + * Workaround for low memory 2D VMs to compensate for the + * allocation taken by fbdev + */ + if (!(dev_priv->capabilities & SVGA_CAP_3D)) + mem_size *= 2; + dev_priv->max_mob_pages = mem_size * 1024 / PAGE_SIZE; dev_priv->prim_bb_mem = vmw_read(dev_priv, diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h index 1980e2a28265..89fb19443a3f 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h @@ -386,6 +386,7 @@ struct vmw_private { spinlock_t hw_lock; spinlock_t cap_lock; bool has_dx; + bool assume_16bpp; /* * VGA registers. diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_fb.c b/drivers/gpu/drm/vmwgfx/vmwgfx_fb.c index 679a4cb98ee3..d2d93959b119 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_fb.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_fb.c @@ -517,28 +517,6 @@ static int vmw_fb_kms_framebuffer(struct fb_info *info) par->set_fb = &vfb->base; - if (!par->bo_ptr) { - /* - * Pin before mapping. Since we don't know in what placement - * to pin, call into KMS to do it for us. - */ - ret = vfb->pin(vfb); - if (ret) { - DRM_ERROR("Could not pin the fbdev framebuffer.\n"); - return ret; - } - - ret = ttm_bo_kmap(&par->vmw_bo->base, 0, - par->vmw_bo->base.num_pages, &par->map); - if (ret) { - vfb->unpin(vfb); - DRM_ERROR("Could not map the fbdev framebuffer.\n"); - return ret; - } - - par->bo_ptr = ttm_kmap_obj_virtual(&par->map, &par->bo_iowrite); - } - return 0; } @@ -601,6 +579,31 @@ static int vmw_fb_set_par(struct fb_info *info) if (ret) goto out_unlock; + if (!par->bo_ptr) { + struct vmw_framebuffer *vfb = vmw_framebuffer_to_vfb(set.fb); + + /* + * Pin before mapping. Since we don't know in what placement + * to pin, call into KMS to do it for us. + */ + ret = vfb->pin(vfb); + if (ret) { + DRM_ERROR("Could not pin the fbdev framebuffer.\n"); + goto out_unlock; + } + + ret = ttm_bo_kmap(&par->vmw_bo->base, 0, + par->vmw_bo->base.num_pages, &par->map); + if (ret) { + vfb->unpin(vfb); + DRM_ERROR("Could not map the fbdev framebuffer.\n"); + goto out_unlock; + } + + par->bo_ptr = ttm_kmap_obj_virtual(&par->map, &par->bo_iowrite); + } + + vmw_fb_dirty_mark(par, par->fb_x, par->fb_y, par->set_fb->width, par->set_fb->height); diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c index 55231cce73a0..e29da45a2847 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c @@ -1553,14 +1553,10 @@ int vmw_du_connector_fill_modes(struct drm_connector *connector, DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_PVSYNC) }; int i; - u32 assumed_bpp = 2; + u32 assumed_bpp = 4; - /* - * If using screen objects, then assume 32-bpp because that's what the - * SVGA device is assuming - */ - if (dev_priv->active_display_unit == vmw_du_screen_object) - assumed_bpp = 4; + if (dev_priv->assume_16bpp) + assumed_bpp = 2; if (dev_priv->active_display_unit == vmw_du_screen_target) { max_width = min(max_width, dev_priv->stdu_max_width); diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c b/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c index f0374f9b56ca..e57a0bad7a62 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c @@ -300,6 +300,9 @@ static int vmw_recv_msg(struct rpc_channel *channel, void **msg, break; } + if (retries == RETRIES) + return -EINVAL; + *msg_len = reply_len; *msg = reply; diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c b/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c index 9ca818fb034c..41932a7c4f79 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c @@ -399,8 +399,10 @@ static int vmw_stdu_bind_fb(struct vmw_private *dev_priv, WARN_ON_ONCE(!stdu->defined); - if (!vfb->dmabuf && new_fb->width == mode->hdisplay && - new_fb->height == mode->vdisplay) + new_vfbs = (vfb->dmabuf) ? NULL : vmw_framebuffer_to_vfbs(new_fb); + + if (new_vfbs && new_vfbs->surface->base_size.width == mode->hdisplay && + new_vfbs->surface->base_size.height == mode->vdisplay) new_content_type = SAME_AS_DISPLAY; else if (vfb->dmabuf) new_content_type = SEPARATE_DMA; @@ -444,7 +446,6 @@ static int vmw_stdu_bind_fb(struct vmw_private *dev_priv, content_srf.mip_levels[0] = 1; content_srf.multisample_count = 0; } else { - new_vfbs = vmw_framebuffer_to_vfbs(new_fb); content_srf = *new_vfbs->surface; } @@ -464,7 +465,6 @@ static int vmw_stdu_bind_fb(struct vmw_private *dev_priv, return ret; } } else if (new_content_type == SAME_AS_DISPLAY) { - new_vfbs = vmw_framebuffer_to_vfbs(new_fb); new_display_srf = vmw_surface_reference(new_vfbs->surface); } |