diff options
Diffstat (limited to 'drivers/gpu/drm')
143 files changed, 1830 insertions, 801 deletions
diff --git a/drivers/gpu/drm/amd/amdgpu/Makefile b/drivers/gpu/drm/amd/amdgpu/Makefile index 04c270757030..ca066018ea34 100644 --- a/drivers/gpu/drm/amd/amdgpu/Makefile +++ b/drivers/gpu/drm/amd/amdgpu/Makefile @@ -22,7 +22,7 @@ amdgpu-y += amdgpu_device.o amdgpu_kms.o \ amdgpu_ucode.o amdgpu_bo_list.o amdgpu_ctx.o amdgpu_sync.o # add asic specific block -amdgpu-$(CONFIG_DRM_AMDGPU_CIK)+= cik.o gmc_v7_0.o cik_ih.o kv_smc.o kv_dpm.o \ +amdgpu-$(CONFIG_DRM_AMDGPU_CIK)+= cik.o cik_ih.o kv_smc.o kv_dpm.o \ ci_smc.o ci_dpm.o dce_v8_0.o gfx_v7_0.o cik_sdma.o uvd_v4_2.o vce_v2_0.o \ amdgpu_amdkfd_gfx_v7.o @@ -31,6 +31,7 @@ amdgpu-y += \ # add GMC block amdgpu-y += \ + gmc_v7_0.o \ gmc_v8_0.o # add IH block diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h index 048cfe073dae..ff5566c69f7d 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h @@ -604,8 +604,6 @@ struct amdgpu_sa_manager { uint32_t align; }; -struct amdgpu_sa_bo; - /* sub-allocation buffer */ struct amdgpu_sa_bo { struct list_head olist; @@ -712,9 +710,9 @@ int amdgpu_gart_table_vram_pin(struct amdgpu_device *adev); void amdgpu_gart_table_vram_unpin(struct amdgpu_device *adev); int amdgpu_gart_init(struct amdgpu_device *adev); void amdgpu_gart_fini(struct amdgpu_device *adev); -void amdgpu_gart_unbind(struct amdgpu_device *adev, unsigned offset, +void amdgpu_gart_unbind(struct amdgpu_device *adev, uint64_t offset, int pages); -int amdgpu_gart_bind(struct amdgpu_device *adev, unsigned offset, +int amdgpu_gart_bind(struct amdgpu_device *adev, uint64_t offset, int pages, struct page **pagelist, dma_addr_t *dma_addr, uint32_t flags); @@ -1675,6 +1673,7 @@ struct amdgpu_uvd { struct amdgpu_bo *vcpu_bo; void *cpu_addr; uint64_t gpu_addr; + unsigned fw_version; atomic_t handles[AMDGPU_MAX_UVD_HANDLES]; struct drm_file *filp[AMDGPU_MAX_UVD_HANDLES]; struct delayed_work idle_work; @@ -2314,6 +2313,8 @@ bool amdgpu_ttm_bo_is_amdgpu_bo(struct ttm_buffer_object *bo); int amdgpu_ttm_tt_set_userptr(struct ttm_tt *ttm, uint64_t addr, uint32_t flags); bool amdgpu_ttm_tt_has_userptr(struct ttm_tt *ttm); +bool amdgpu_ttm_tt_affect_userptr(struct ttm_tt *ttm, unsigned long start, + unsigned long end); bool amdgpu_ttm_tt_is_readonly(struct ttm_tt *ttm); uint32_t amdgpu_ttm_tt_pte_flags(struct amdgpu_device *adev, struct ttm_tt *ttm, struct ttm_mem_reg *mem); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c index 9416e0f5c1db..51a9942cdb40 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c @@ -331,6 +331,19 @@ bool amdgpu_atombios_get_connector_info_from_object_table(struct amdgpu_device * (le16_to_cpu(path->usConnObjectId) & OBJECT_TYPE_MASK) >> OBJECT_TYPE_SHIFT; + /* Skip TV/CV support */ + if ((le16_to_cpu(path->usDeviceTag) == + ATOM_DEVICE_TV1_SUPPORT) || + (le16_to_cpu(path->usDeviceTag) == + ATOM_DEVICE_CV_SUPPORT)) + continue; + + if (con_obj_id >= ARRAY_SIZE(object_connector_convert)) { + DRM_ERROR("invalid con_obj_id %d for device tag 0x%04x\n", + con_obj_id, le16_to_cpu(path->usDeviceTag)); + continue; + } + connector_type = object_connector_convert[con_obj_id]; connector_object_id = con_obj_id; @@ -566,28 +579,19 @@ int amdgpu_atombios_get_clock_info(struct amdgpu_device *adev) le16_to_cpu(firmware_info->info.usReferenceClock); ppll->reference_div = 0; - if (crev < 2) - ppll->pll_out_min = - le16_to_cpu(firmware_info->info.usMinPixelClockPLL_Output); - else - ppll->pll_out_min = - le32_to_cpu(firmware_info->info_12.ulMinPixelClockPLL_Output); + ppll->pll_out_min = + le32_to_cpu(firmware_info->info_12.ulMinPixelClockPLL_Output); ppll->pll_out_max = le32_to_cpu(firmware_info->info.ulMaxPixelClockPLL_Output); - if (crev >= 4) { - ppll->lcd_pll_out_min = - le16_to_cpu(firmware_info->info_14.usLcdMinPixelClockPLL_Output) * 100; - if (ppll->lcd_pll_out_min == 0) - ppll->lcd_pll_out_min = ppll->pll_out_min; - ppll->lcd_pll_out_max = - le16_to_cpu(firmware_info->info_14.usLcdMaxPixelClockPLL_Output) * 100; - if (ppll->lcd_pll_out_max == 0) - ppll->lcd_pll_out_max = ppll->pll_out_max; - } else { + ppll->lcd_pll_out_min = + le16_to_cpu(firmware_info->info_14.usLcdMinPixelClockPLL_Output) * 100; + if (ppll->lcd_pll_out_min == 0) ppll->lcd_pll_out_min = ppll->pll_out_min; + ppll->lcd_pll_out_max = + le16_to_cpu(firmware_info->info_14.usLcdMaxPixelClockPLL_Output) * 100; + if (ppll->lcd_pll_out_max == 0) ppll->lcd_pll_out_max = ppll->pll_out_max; - } if (ppll->pll_out_min == 0) ppll->pll_out_min = 64800; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c index 5a8fbadbd27b..29adbbe225c4 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c @@ -10,6 +10,7 @@ #include <linux/slab.h> #include <linux/acpi.h> #include <linux/pci.h> +#include <linux/delay.h> #include "amdgpu_acpi.h" @@ -256,6 +257,10 @@ static int amdgpu_atpx_set_discrete_state(struct amdgpu_atpx *atpx, u8 state) if (!info) return -EIO; kfree(info); + + /* 200ms delay is required after off */ + if (state == 0) + msleep(200); } return 0; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c index 89c3dd62ba21..930083336968 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c @@ -77,7 +77,7 @@ void amdgpu_connector_hotplug(struct drm_connector *connector) } else if (amdgpu_atombios_dp_needs_link_train(amdgpu_connector)) { /* Don't try to start link training before we * have the dpcd */ - if (!amdgpu_atombios_dp_get_dpcd(amdgpu_connector)) + if (amdgpu_atombios_dp_get_dpcd(amdgpu_connector)) return; /* set it to OFF so that drm_helper_connector_dpms() @@ -194,12 +194,12 @@ int amdgpu_connector_get_monitor_bpc(struct drm_connector *connector) bpc = 8; DRM_DEBUG("%s: HDMI deep color 10 bpc exceeds max tmds clock. Using %d bpc.\n", connector->name, bpc); - } else if (bpc > 8) { - /* max_tmds_clock missing, but hdmi spec mandates it for deep color. */ - DRM_DEBUG("%s: Required max tmds clock for HDMI deep color missing. Using 8 bpc.\n", - connector->name); - bpc = 8; } + } else if (bpc > 8) { + /* max_tmds_clock missing, but hdmi spec mandates it for deep color. */ + DRM_DEBUG("%s: Required max tmds clock for HDMI deep color missing. Using 8 bpc.\n", + connector->name); + bpc = 8; } } @@ -1690,7 +1690,6 @@ amdgpu_connector_add(struct amdgpu_device *adev, DRM_MODE_SCALE_NONE); /* no HPD on analog connectors */ amdgpu_connector->hpd.hpd = AMDGPU_HPD_NONE; - connector->polled = DRM_CONNECTOR_POLL_CONNECT; connector->interlace_allowed = true; connector->doublescan_allowed = true; break; @@ -1893,8 +1892,10 @@ amdgpu_connector_add(struct amdgpu_device *adev, } if (amdgpu_connector->hpd.hpd == AMDGPU_HPD_NONE) { - if (i2c_bus->valid) - connector->polled = DRM_CONNECTOR_POLL_CONNECT; + if (i2c_bus->valid) { + connector->polled = DRM_CONNECTOR_POLL_CONNECT | + DRM_CONNECTOR_POLL_DISCONNECT; + } } else connector->polled = DRM_CONNECTOR_POLL_HPD; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index d5b421330145..16302f7d59f6 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -1744,15 +1744,20 @@ int amdgpu_resume_kms(struct drm_device *dev, bool resume, bool fbcon) } /* post card */ - amdgpu_atom_asic_init(adev->mode_info.atom_context); + if (!amdgpu_card_posted(adev)) + amdgpu_atom_asic_init(adev->mode_info.atom_context); r = amdgpu_resume(adev); + if (r) + DRM_ERROR("amdgpu_resume failed (%d).\n", r); amdgpu_fence_driver_resume(adev); - r = amdgpu_ib_ring_tests(adev); - if (r) - DRM_ERROR("ib ring test failed (%d).\n", r); + if (resume) { + r = amdgpu_ib_ring_tests(adev); + if (r) + DRM_ERROR("ib ring test failed (%d).\n", r); + } r = amdgpu_late_init(adev); if (r) @@ -1789,6 +1794,23 @@ int amdgpu_resume_kms(struct drm_device *dev, bool resume, bool fbcon) drm_kms_helper_poll_enable(dev); + /* + * Most of the connector probing functions try to acquire runtime pm + * refs to ensure that the GPU is powered on when connector polling is + * performed. Since we're calling this from a runtime PM callback, + * trying to acquire rpm refs will cause us to deadlock. + * + * Since we're guaranteed to be holding the rpm lock, it's safe to + * temporarily disable the rpm helpers so this doesn't deadlock us. + */ +#ifdef CONFIG_PM + dev->dev->power.disable_depth++; +#endif + drm_helper_hpd_irq_event(dev); +#ifdef CONFIG_PM + dev->dev->power.disable_depth--; +#endif + if (fbcon) { amdgpu_fbdev_set_suspend(adev, 0); console_unlock(); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c index 5580d3420c3a..82903ca78529 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c @@ -72,8 +72,8 @@ static void amdgpu_flip_work_func(struct work_struct *__work) struct drm_crtc *crtc = &amdgpuCrtc->base; unsigned long flags; - unsigned i; - int vpos, hpos, stat, min_udelay; + unsigned i, repcnt = 4; + int vpos, hpos, stat, min_udelay = 0; struct drm_vblank_crtc *vblank = &crtc->dev->vblank[work->crtc_id]; amdgpu_flip_wait_fence(adev, &work->excl); @@ -96,7 +96,7 @@ static void amdgpu_flip_work_func(struct work_struct *__work) * In practice this won't execute very often unless on very fast * machines because the time window for this to happen is very small. */ - for (;;) { + while (amdgpuCrtc->enabled && --repcnt) { /* GET_DISTANCE_TO_VBLANKSTART returns distance to real vblank * start in hpos, and to the "fudged earlier" vblank start in * vpos. @@ -112,12 +112,24 @@ static void amdgpu_flip_work_func(struct work_struct *__work) break; /* Sleep at least until estimated real start of hw vblank */ - spin_unlock_irqrestore(&crtc->dev->event_lock, flags); min_udelay = (-hpos + 1) * max(vblank->linedur_ns / 1000, 5); + if (min_udelay > vblank->framedur_ns / 2000) { + /* Don't wait ridiculously long - something is wrong */ + repcnt = 0; + break; + } + spin_unlock_irqrestore(&crtc->dev->event_lock, flags); usleep_range(min_udelay, 2 * min_udelay); spin_lock_irqsave(&crtc->dev->event_lock, flags); }; + if (!repcnt) + DRM_DEBUG_DRIVER("Delay problem on crtc %d: min_udelay %d, " + "framedur %d, linedur %d, stat %d, vpos %d, " + "hpos %d\n", work->crtc_id, min_udelay, + vblank->framedur_ns / 1000, + vblank->linedur_ns / 1000, stat, vpos, hpos); + /* do the flip (mmio) */ adev->mode_info.funcs->page_flip(adev, work->crtc_id, work->base); /* set the flip status */ diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_dpm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_dpm.c index 7b7f4aba60c0..fe36caf1b7d7 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_dpm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_dpm.c @@ -150,7 +150,7 @@ u32 amdgpu_dpm_get_vrefresh(struct amdgpu_device *adev) list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) { amdgpu_crtc = to_amdgpu_crtc(crtc); if (crtc->enabled && amdgpu_crtc->enabled && amdgpu_crtc->hw_mode.clock) { - vrefresh = amdgpu_crtc->hw_mode.vrefresh; + vrefresh = drm_mode_vrefresh(&amdgpu_crtc->hw_mode); break; } } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index 0508c5cd103a..8d6668cedf6d 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -250,11 +250,11 @@ static struct pci_device_id pciidlist[] = { {0x1002, 0x985F, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_MULLINS|AMD_IS_MOBILITY|AMD_IS_APU}, #endif /* topaz */ - {0x1002, 0x6900, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TOPAZ|AMD_EXP_HW_SUPPORT}, - {0x1002, 0x6901, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TOPAZ|AMD_EXP_HW_SUPPORT}, - {0x1002, 0x6902, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TOPAZ|AMD_EXP_HW_SUPPORT}, - {0x1002, 0x6903, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TOPAZ|AMD_EXP_HW_SUPPORT}, - {0x1002, 0x6907, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TOPAZ|AMD_EXP_HW_SUPPORT}, + {0x1002, 0x6900, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TOPAZ}, + {0x1002, 0x6901, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TOPAZ}, + {0x1002, 0x6902, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TOPAZ}, + {0x1002, 0x6903, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TOPAZ}, + {0x1002, 0x6907, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TOPAZ}, /* tonga */ {0x1002, 0x6920, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TONGA}, {0x1002, 0x6921, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TONGA}, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c index 7312d729d300..22a613a95bf0 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c @@ -221,7 +221,7 @@ void amdgpu_gart_table_vram_free(struct amdgpu_device *adev) * Unbinds the requested pages from the gart page table and * replaces them with the dummy page (all asics). */ -void amdgpu_gart_unbind(struct amdgpu_device *adev, unsigned offset, +void amdgpu_gart_unbind(struct amdgpu_device *adev, uint64_t offset, int pages) { unsigned t; @@ -269,7 +269,7 @@ void amdgpu_gart_unbind(struct amdgpu_device *adev, unsigned offset, * (all asics). * Returns 0 for success, -EINVAL for failure. */ -int amdgpu_gart_bind(struct amdgpu_device *adev, unsigned offset, +int amdgpu_gart_bind(struct amdgpu_device *adev, uint64_t offset, int pages, struct page **pagelist, dma_addr_t *dma_addr, uint32_t flags) { diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c index 9e25edafa721..c77a1ebfc632 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c @@ -288,7 +288,7 @@ void amdgpu_ib_pool_fini(struct amdgpu_device *adev) int amdgpu_ib_ring_tests(struct amdgpu_device *adev) { unsigned i; - int r; + int r, ret = 0; for (i = 0; i < AMDGPU_MAX_RINGS; ++i) { struct amdgpu_ring *ring = adev->rings[i]; @@ -309,10 +309,11 @@ int amdgpu_ib_ring_tests(struct amdgpu_device *adev) } else { /* still not good, but we can live with it */ DRM_ERROR("amdgpu: failed testing IB on ring %d (%d).\n", i, r); + ret = r; } } } - return 0; + return ret; } /* diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c index e23843f4d877..4488e82f87b0 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c @@ -303,7 +303,7 @@ static int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file fw_info.feature = adev->vce.fb_version; break; case AMDGPU_INFO_FW_UVD: - fw_info.ver = 0; + fw_info.ver = adev->uvd.fw_version; fw_info.feature = 0; break; case AMDGPU_INFO_FW_GMC: diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c index b1969f2b2038..d4e2780c0796 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c @@ -142,7 +142,8 @@ static void amdgpu_mn_invalidate_range_start(struct mmu_notifier *mn, list_for_each_entry(bo, &node->bos, mn_list) { - if (!bo->tbo.ttm || bo->tbo.ttm->state != tt_bound) + if (!amdgpu_ttm_tt_affect_userptr(bo->tbo.ttm, start, + end)) continue; r = amdgpu_bo_reserve(bo, true); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mode.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_mode.h index 064ebb347074..89df7871653d 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mode.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mode.h @@ -52,7 +52,7 @@ struct amdgpu_hpd; #define AMDGPU_MAX_HPD_PINS 6 #define AMDGPU_MAX_CRTCS 6 -#define AMDGPU_MAX_AFMT_BLOCKS 7 +#define AMDGPU_MAX_AFMT_BLOCKS 9 enum amdgpu_rmx_type { RMX_OFF, @@ -308,8 +308,8 @@ struct amdgpu_mode_info { struct atom_context *atom_context; struct card_info *atom_card_info; bool mode_config_initialized; - struct amdgpu_crtc *crtcs[6]; - struct amdgpu_afmt *afmt[7]; + struct amdgpu_crtc *crtcs[AMDGPU_MAX_CRTCS]; + struct amdgpu_afmt *afmt[AMDGPU_MAX_AFMT_BLOCKS]; /* DVI-I properties */ struct drm_property *coherent_mode_property; /* DAC enable load detect */ diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c index c3ce103b6a33..73628c7599e7 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c @@ -33,6 +33,7 @@ #include <linux/slab.h> #include <drm/drmP.h> #include <drm/amdgpu_drm.h> +#include <drm/drm_cache.h> #include "amdgpu.h" #include "amdgpu_trace.h" @@ -261,6 +262,13 @@ int amdgpu_bo_create_restricted(struct amdgpu_device *adev, AMDGPU_GEM_DOMAIN_OA); bo->flags = flags; + + /* For architectures that don't support WC memory, + * mask out the WC flag from the BO + */ + if (!drm_arch_can_wc_memory()) + bo->flags &= ~AMDGPU_GEM_CREATE_CPU_GTT_USWC; + amdgpu_fill_placement_to_bo(bo, placement); /* Kernel allocation are uninterruptible */ r = ttm_bo_init(&adev->mman.bdev, &bo->tbo, size, type, @@ -399,7 +407,8 @@ int amdgpu_bo_pin_restricted(struct amdgpu_bo *bo, u32 domain, } if (fpfn > bo->placements[i].fpfn) bo->placements[i].fpfn = fpfn; - if (lpfn && lpfn < bo->placements[i].lpfn) + if (!bo->placements[i].lpfn || + (lpfn && lpfn < bo->placements[i].lpfn)) bo->placements[i].lpfn = lpfn; bo->placements[i].flags |= TTM_PL_FLAG_NO_EVICT; } @@ -531,6 +540,7 @@ int amdgpu_bo_set_metadata (struct amdgpu_bo *bo, void *metadata, if (!metadata_size) { if (bo->metadata_size) { kfree(bo->metadata); + bo->metadata = NULL; bo->metadata_size = 0; } return 0; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c index 22a8c7d3a3ab..7ae15fad16ed 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c @@ -595,11 +595,6 @@ force: /* update display watermarks based on new power state */ amdgpu_display_bandwidth_update(adev); - /* update displays */ - amdgpu_dpm_display_configuration_changed(adev); - - adev->pm.dpm.current_active_crtcs = adev->pm.dpm.new_active_crtcs; - adev->pm.dpm.current_active_crtc_count = adev->pm.dpm.new_active_crtc_count; /* wait for the rings to drain */ for (i = 0; i < AMDGPU_MAX_RINGS; i++) { @@ -616,6 +611,12 @@ force: amdgpu_dpm_post_set_power_state(adev); + /* update displays */ + amdgpu_dpm_display_configuration_changed(adev); + + adev->pm.dpm.current_active_crtcs = adev->pm.dpm.new_active_crtcs; + adev->pm.dpm.current_active_crtc_count = adev->pm.dpm.new_active_crtc_count; + if (adev->pm.funcs->force_performance_level) { if (adev->pm.dpm.thermal_active) { enum amdgpu_dpm_forced_level level = adev->pm.dpm.forced_level; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_sa.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_sa.c index 8b88edb0434b..ca72a2e487b9 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_sa.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_sa.c @@ -354,12 +354,15 @@ int amdgpu_sa_bo_new(struct amdgpu_sa_manager *sa_manager, for (i = 0, count = 0; i < AMDGPU_MAX_RINGS; ++i) if (fences[i]) - fences[count++] = fences[i]; + fences[count++] = fence_get(fences[i]); if (count) { spin_unlock(&sa_manager->wq.lock); t = fence_wait_any_timeout(fences, count, false, MAX_SCHEDULE_TIMEOUT); + for (i = 0; i < count; ++i) + fence_put(fences[i]); + r = (t > 0) ? 0 : t; spin_lock(&sa_manager->wq.lock); } else { diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c index dd005c336c97..181ce39ef5e5 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c @@ -293,7 +293,8 @@ int amdgpu_sync_rings(struct amdgpu_sync *sync, fence = to_amdgpu_fence(sync->sync_to[i]); /* check if we really need to sync */ - if (!amdgpu_fence_need_sync(fence, ring)) + if (!amdgpu_enable_scheduler && + !amdgpu_fence_need_sync(fence, ring)) continue; /* prevent GPU deadlocks */ @@ -303,7 +304,7 @@ int amdgpu_sync_rings(struct amdgpu_sync *sync, } if (amdgpu_enable_scheduler || !amdgpu_enable_semaphores) { - r = fence_wait(&fence->base, true); + r = fence_wait(sync->sync_to[i], true); if (r) return r; continue; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c index 8a1752ff3d8e..475c38fe9245 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c @@ -233,8 +233,8 @@ static int amdgpu_move_blit(struct ttm_buffer_object *bo, adev = amdgpu_get_adev(bo->bdev); ring = adev->mman.buffer_funcs_ring; - old_start = old_mem->start << PAGE_SHIFT; - new_start = new_mem->start << PAGE_SHIFT; + old_start = (u64)old_mem->start << PAGE_SHIFT; + new_start = (u64)new_mem->start << PAGE_SHIFT; switch (old_mem->mem_type) { case TTM_PL_VRAM: @@ -712,7 +712,7 @@ static int amdgpu_ttm_tt_populate(struct ttm_tt *ttm) 0, PAGE_SIZE, PCI_DMA_BIDIRECTIONAL); if (pci_dma_mapping_error(adev->pdev, gtt->ttm.dma_address[i])) { - while (--i) { + while (i--) { pci_unmap_page(adev->pdev, gtt->ttm.dma_address[i], PAGE_SIZE, PCI_DMA_BIDIRECTIONAL); gtt->ttm.dma_address[i] = 0; @@ -783,6 +783,25 @@ bool amdgpu_ttm_tt_has_userptr(struct ttm_tt *ttm) return !!gtt->userptr; } +bool amdgpu_ttm_tt_affect_userptr(struct ttm_tt *ttm, unsigned long start, + unsigned long end) +{ + struct amdgpu_ttm_tt *gtt = (void *)ttm; + unsigned long size; + + if (gtt == NULL) + return false; + + if (gtt->ttm.ttm.state != tt_bound || !gtt->userptr) + return false; + + size = (unsigned long)gtt->ttm.ttm.num_pages * PAGE_SIZE; + if (gtt->userptr > end || gtt->userptr + size <= start) + return false; + + return true; +} + bool amdgpu_ttm_tt_is_readonly(struct ttm_tt *ttm) { struct amdgpu_ttm_tt *gtt = (void *)ttm; @@ -808,7 +827,7 @@ uint32_t amdgpu_ttm_tt_pte_flags(struct amdgpu_device *adev, struct ttm_tt *ttm, flags |= AMDGPU_PTE_SNOOPED; } - if (adev->asic_type >= CHIP_TOPAZ) + if (adev->asic_type >= CHIP_TONGA) flags |= AMDGPU_PTE_EXECUTABLE; flags |= AMDGPU_PTE_READABLE; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c index 53f987aeeacf..3b35ad83867c 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c @@ -156,6 +156,9 @@ int amdgpu_uvd_sw_init(struct amdgpu_device *adev) DRM_INFO("Found UVD firmware Version: %hu.%hu Family ID: %hu\n", version_major, version_minor, family_id); + adev->uvd.fw_version = ((version_major << 24) | (version_minor << 16) | + (family_id << 8)); + bo_size = AMDGPU_GPU_PAGE_ALIGN(le32_to_cpu(hdr->ucode_size_bytes) + 8) + AMDGPU_UVD_STACK_SIZE + AMDGPU_UVD_HEAP_SIZE; r = amdgpu_bo_create(adev, bo_size, PAGE_SIZE, true, @@ -273,6 +276,8 @@ int amdgpu_uvd_resume(struct amdgpu_device *adev) memcpy(adev->uvd.cpu_addr, (adev->uvd.fw->data) + offset, (adev->uvd.fw->size) - offset); + cancel_delayed_work_sync(&adev->uvd.idle_work); + size = amdgpu_bo_size(adev->uvd.vcpu_bo); size -= le32_to_cpu(hdr->ucode_size_bytes); ptr = adev->uvd.cpu_addr; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c index a745eeeb5d82..bb0da76051a1 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c @@ -220,6 +220,7 @@ int amdgpu_vce_suspend(struct amdgpu_device *adev) if (i == AMDGPU_MAX_VCE_HANDLES) return 0; + cancel_delayed_work_sync(&adev->vce.idle_work); /* TODO: suspending running encoding sessions isn't supported */ return -EINVAL; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c index b53d273eb7a1..8c5ec151ddac 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c @@ -1010,13 +1010,13 @@ int amdgpu_vm_bo_map(struct amdgpu_device *adev, return -EINVAL; /* make sure object fit at this offset */ - eaddr = saddr + size; + eaddr = saddr + size - 1; if ((saddr >= eaddr) || (offset + size > amdgpu_bo_size(bo_va->bo))) return -EINVAL; last_pfn = eaddr / AMDGPU_GPU_PAGE_SIZE; - if (last_pfn > adev->vm_manager.max_pfn) { - dev_err(adev->dev, "va above limit (0x%08X > 0x%08X)\n", + if (last_pfn >= adev->vm_manager.max_pfn) { + dev_err(adev->dev, "va above limit (0x%08X >= 0x%08X)\n", last_pfn, adev->vm_manager.max_pfn); return -EINVAL; } @@ -1025,7 +1025,7 @@ int amdgpu_vm_bo_map(struct amdgpu_device *adev, eaddr /= AMDGPU_GPU_PAGE_SIZE; spin_lock(&vm->it_lock); - it = interval_tree_iter_first(&vm->va, saddr, eaddr - 1); + it = interval_tree_iter_first(&vm->va, saddr, eaddr); spin_unlock(&vm->it_lock); if (it) { struct amdgpu_bo_va_mapping *tmp; @@ -1046,7 +1046,7 @@ int amdgpu_vm_bo_map(struct amdgpu_device *adev, INIT_LIST_HEAD(&mapping->list); mapping->it.start = saddr; - mapping->it.last = eaddr - 1; + mapping->it.last = eaddr; mapping->offset = offset; mapping->flags = flags; @@ -1248,7 +1248,7 @@ int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm) { const unsigned align = min(AMDGPU_VM_PTB_ALIGN_SIZE, AMDGPU_VM_PTE_COUNT * 8); - unsigned pd_size, pd_entries, pts_size; + unsigned pd_size, pd_entries; int i, r; for (i = 0; i < AMDGPU_MAX_RINGS; ++i) { @@ -1266,8 +1266,7 @@ int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm) pd_entries = amdgpu_vm_num_pdes(adev); /* allocate page table array */ - pts_size = pd_entries * sizeof(struct amdgpu_vm_pt); - vm->page_tables = kzalloc(pts_size, GFP_KERNEL); + vm->page_tables = drm_calloc_large(pd_entries, sizeof(struct amdgpu_vm_pt)); if (vm->page_tables == NULL) { DRM_ERROR("Cannot allocate memory for page table array\n"); return -ENOMEM; @@ -1327,7 +1326,7 @@ void amdgpu_vm_fini(struct amdgpu_device *adev, struct amdgpu_vm *vm) for (i = 0; i < amdgpu_vm_num_pdes(adev); i++) amdgpu_bo_unref(&vm->page_tables[i].bo); - kfree(vm->page_tables); + drm_free_large(vm->page_tables); amdgpu_bo_unref(&vm->page_directory); fence_put(vm->page_directory_fence); diff --git a/drivers/gpu/drm/amd/amdgpu/atombios_dp.c b/drivers/gpu/drm/amd/amdgpu/atombios_dp.c index 92b6acadfc52..21aacc1f45c1 100644 --- a/drivers/gpu/drm/amd/amdgpu/atombios_dp.c +++ b/drivers/gpu/drm/amd/amdgpu/atombios_dp.c @@ -243,7 +243,7 @@ static void amdgpu_atombios_dp_get_adjust_train(const u8 link_status[DP_LINK_STA /* convert bits per color to bits per pixel */ /* get bpc from the EDID */ -static int amdgpu_atombios_dp_convert_bpc_to_bpp(int bpc) +static unsigned amdgpu_atombios_dp_convert_bpc_to_bpp(int bpc) { if (bpc == 0) return 24; @@ -251,64 +251,32 @@ static int amdgpu_atombios_dp_convert_bpc_to_bpp(int bpc) return bpc * 3; } -/* get the max pix clock supported by the link rate and lane num */ -static int amdgpu_atombios_dp_get_max_dp_pix_clock(int link_rate, - int lane_num, - int bpp) -{ - return (link_rate * lane_num * 8) / bpp; -} - /***** amdgpu specific DP functions *****/ -/* First get the min lane# when low rate is used according to pixel clock - * (prefer low rate), second check max lane# supported by DP panel, - * if the max lane# < low rate lane# then use max lane# instead. - */ -static int amdgpu_atombios_dp_get_dp_lane_number(struct drm_connector *connector, +static int amdgpu_atombios_dp_get_dp_link_config(struct drm_connector *connector, const u8 dpcd[DP_DPCD_SIZE], - int pix_clock) -{ - int bpp = amdgpu_atombios_dp_convert_bpc_to_bpp(amdgpu_connector_get_monitor_bpc(connector)); - int max_link_rate = drm_dp_max_link_rate(dpcd); - int max_lane_num = drm_dp_max_lane_count(dpcd); - int lane_num; - int max_dp_pix_clock; - - for (lane_num = 1; lane_num < max_lane_num; lane_num <<= 1) { - max_dp_pix_clock = amdgpu_atombios_dp_get_max_dp_pix_clock(max_link_rate, lane_num, bpp); - if (pix_clock <= max_dp_pix_clock) - break; - } - - return lane_num; -} - -static int amdgpu_atombios_dp_get_dp_link_clock(struct drm_connector *connector, - const u8 dpcd[DP_DPCD_SIZE], - int pix_clock) + unsigned pix_clock, + unsigned *dp_lanes, unsigned *dp_rate) { - int bpp = amdgpu_atombios_dp_convert_bpc_to_bpp(amdgpu_connector_get_monitor_bpc(connector)); - int lane_num, max_pix_clock; - - if (amdgpu_connector_encoder_get_dp_bridge_encoder_id(connector) == - ENCODER_OBJECT_ID_NUTMEG) - return 270000; - - lane_num = amdgpu_atombios_dp_get_dp_lane_number(connector, dpcd, pix_clock); - max_pix_clock = amdgpu_atombios_dp_get_max_dp_pix_clock(162000, lane_num, bpp); - if (pix_clock <= max_pix_clock) - return 162000; - max_pix_clock = amdgpu_atombios_dp_get_max_dp_pix_clock(270000, lane_num, bpp); - if (pix_clock <= max_pix_clock) - return 270000; - if (amdgpu_connector_is_dp12_capable(connector)) { - max_pix_clock = amdgpu_atombios_dp_get_max_dp_pix_clock(540000, lane_num, bpp); - if (pix_clock <= max_pix_clock) - return 540000; + unsigned bpp = + amdgpu_atombios_dp_convert_bpc_to_bpp(amdgpu_connector_get_monitor_bpc(connector)); + static const unsigned link_rates[3] = { 162000, 270000, 540000 }; + unsigned max_link_rate = drm_dp_max_link_rate(dpcd); + unsigned max_lane_num = drm_dp_max_lane_count(dpcd); + unsigned lane_num, i, max_pix_clock; + + for (lane_num = 1; lane_num <= max_lane_num; lane_num <<= 1) { + for (i = 0; i < ARRAY_SIZE(link_rates) && link_rates[i] <= max_link_rate; i++) { + max_pix_clock = (lane_num * link_rates[i] * 8) / bpp; + if (max_pix_clock >= pix_clock) { + *dp_lanes = lane_num; + *dp_rate = link_rates[i]; + return 0; + } + } } - return drm_dp_max_link_rate(dpcd); + return -EINVAL; } static u8 amdgpu_atombios_dp_encoder_service(struct amdgpu_device *adev, @@ -422,6 +390,7 @@ void amdgpu_atombios_dp_set_link_config(struct drm_connector *connector, { struct amdgpu_connector *amdgpu_connector = to_amdgpu_connector(connector); struct amdgpu_connector_atom_dig *dig_connector; + int ret; if (!amdgpu_connector->con_priv) return; @@ -429,10 +398,14 @@ void amdgpu_atombios_dp_set_link_config(struct drm_connector *connector, if ((dig_connector->dp_sink_type == CONNECTOR_OBJECT_ID_DISPLAYPORT) || (dig_connector->dp_sink_type == CONNECTOR_OBJECT_ID_eDP)) { - dig_connector->dp_clock = - amdgpu_atombios_dp_get_dp_link_clock(connector, dig_connector->dpcd, mode->clock); - dig_connector->dp_lane_count = - amdgpu_atombios_dp_get_dp_lane_number(connector, dig_connector->dpcd, mode->clock); + ret = amdgpu_atombios_dp_get_dp_link_config(connector, dig_connector->dpcd, + mode->clock, + &dig_connector->dp_lane_count, + &dig_connector->dp_clock); + if (ret) { + dig_connector->dp_clock = 0; + dig_connector->dp_lane_count = 0; + } } } @@ -441,14 +414,17 @@ int amdgpu_atombios_dp_mode_valid_helper(struct drm_connector *connector, { struct amdgpu_connector *amdgpu_connector = to_amdgpu_connector(connector); struct amdgpu_connector_atom_dig *dig_connector; - int dp_clock; + unsigned dp_lanes, dp_clock; + int ret; if (!amdgpu_connector->con_priv) return MODE_CLOCK_HIGH; dig_connector = amdgpu_connector->con_priv; - dp_clock = - amdgpu_atombios_dp_get_dp_link_clock(connector, dig_connector->dpcd, mode->clock); + ret = amdgpu_atombios_dp_get_dp_link_config(connector, dig_connector->dpcd, + mode->clock, &dp_lanes, &dp_clock); + if (ret) + return MODE_CLOCK_HIGH; if ((dp_clock == 540000) && (!amdgpu_connector_is_dp12_capable(connector))) diff --git a/drivers/gpu/drm/amd/amdgpu/atombios_encoders.c b/drivers/gpu/drm/amd/amdgpu/atombios_encoders.c index 1e0bba29e167..542517d4e584 100644 --- a/drivers/gpu/drm/amd/amdgpu/atombios_encoders.c +++ b/drivers/gpu/drm/amd/amdgpu/atombios_encoders.c @@ -98,6 +98,7 @@ amdgpu_atombios_encoder_set_backlight_level(struct amdgpu_encoder *amdgpu_encode case ENCODER_OBJECT_ID_INTERNAL_KLDSCP_LVTMA: case ENCODER_OBJECT_ID_INTERNAL_UNIPHY1: case ENCODER_OBJECT_ID_INTERNAL_UNIPHY2: + case ENCODER_OBJECT_ID_INTERNAL_UNIPHY3: if (dig->backlight_level == 0) amdgpu_atombios_encoder_setup_dig_transmitter(encoder, ATOM_TRANSMITTER_ACTION_LCD_BLOFF, 0, 0); @@ -298,6 +299,10 @@ bool amdgpu_atombios_encoder_mode_fixup(struct drm_encoder *encoder, && (mode->crtc_vsync_start < (mode->crtc_vdisplay + 2))) adjusted_mode->crtc_vsync_start = adjusted_mode->crtc_vdisplay + 2; + /* vertical FP must be at least 1 */ + if (mode->crtc_vsync_start == mode->crtc_vdisplay) + adjusted_mode->crtc_vsync_start++; + /* get the native mode for scaling */ if (amdgpu_encoder->active_device & (ATOM_DEVICE_LCD_SUPPORT)) amdgpu_panel_mode_fixup(encoder, adjusted_mode); diff --git a/drivers/gpu/drm/amd/amdgpu/cik_sdma.c b/drivers/gpu/drm/amd/amdgpu/cik_sdma.c index 5f712ceddf08..c568293cb6c1 100644 --- a/drivers/gpu/drm/amd/amdgpu/cik_sdma.c +++ b/drivers/gpu/drm/amd/amdgpu/cik_sdma.c @@ -52,6 +52,7 @@ static void cik_sdma_set_ring_funcs(struct amdgpu_device *adev); static void cik_sdma_set_irq_funcs(struct amdgpu_device *adev); static void cik_sdma_set_buffer_funcs(struct amdgpu_device *adev); static void cik_sdma_set_vm_pte_funcs(struct amdgpu_device *adev); +static int cik_sdma_soft_reset(void *handle); MODULE_FIRMWARE("radeon/bonaire_sdma.bin"); MODULE_FIRMWARE("radeon/bonaire_sdma1.bin"); @@ -1030,6 +1031,8 @@ static int cik_sdma_resume(void *handle) { struct amdgpu_device *adev = (struct amdgpu_device *)handle; + cik_sdma_soft_reset(handle); + return cik_sdma_hw_init(adev); } diff --git a/drivers/gpu/drm/amd/amdgpu/cz_dpm.c b/drivers/gpu/drm/amd/amdgpu/cz_dpm.c index 8035d4d6a4f5..653917a3bcc2 100644 --- a/drivers/gpu/drm/amd/amdgpu/cz_dpm.c +++ b/drivers/gpu/drm/amd/amdgpu/cz_dpm.c @@ -1955,10 +1955,8 @@ static void cz_dpm_powergate_vce(struct amdgpu_device *adev, bool gate) } } else { /*pi->caps_vce_pg*/ cz_update_vce_dpm(adev); - cz_enable_vce_dpm(adev, true); + cz_enable_vce_dpm(adev, !gate); } - - return; } const struct amd_ip_funcs cz_dpm_ip_funcs = { diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c index 72793f93e2fc..b57fffc2d4af 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c @@ -3628,6 +3628,19 @@ static void gfx_v7_0_ring_emit_vm_flush(struct amdgpu_ring *ring, unsigned vm_id, uint64_t pd_addr) { int usepfp = (ring->type == AMDGPU_RING_TYPE_GFX); + uint32_t seq = ring->fence_drv.sync_seq[ring->idx]; + uint64_t addr = ring->fence_drv.gpu_addr; + + amdgpu_ring_write(ring, PACKET3(PACKET3_WAIT_REG_MEM, 5)); + amdgpu_ring_write(ring, (WAIT_REG_MEM_MEM_SPACE(1) | /* memory */ + WAIT_REG_MEM_FUNCTION(3) | /* equal */ + WAIT_REG_MEM_ENGINE(usepfp))); /* pfp or me */ + amdgpu_ring_write(ring, addr & 0xfffffffc); + amdgpu_ring_write(ring, upper_32_bits(addr) & 0xffffffff); + amdgpu_ring_write(ring, seq); + amdgpu_ring_write(ring, 0xffffffff); + amdgpu_ring_write(ring, 4); /* poll interval */ + if (usepfp) { /* synce CE with ME to prevent CE fetch CEIB before context switch done */ amdgpu_ring_write(ring, PACKET3(PACKET3_SWITCH_BUFFER, 0)); @@ -5450,7 +5463,7 @@ static int gfx_v7_0_eop_irq(struct amdgpu_device *adev, case 2: for (i = 0; i < adev->gfx.num_compute_rings; i++) { ring = &adev->gfx.compute_ring[i]; - if ((ring->me == me_id) & (ring->pipe == pipe_id)) + if ((ring->me == me_id) && (ring->pipe == pipe_id)) amdgpu_fence_process(ring); } break; diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c index e1dcab98e249..d1054034d14b 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c @@ -90,7 +90,6 @@ MODULE_FIRMWARE("amdgpu/topaz_ce.bin"); MODULE_FIRMWARE("amdgpu/topaz_pfp.bin"); MODULE_FIRMWARE("amdgpu/topaz_me.bin"); MODULE_FIRMWARE("amdgpu/topaz_mec.bin"); -MODULE_FIRMWARE("amdgpu/topaz_mec2.bin"); MODULE_FIRMWARE("amdgpu/topaz_rlc.bin"); MODULE_FIRMWARE("amdgpu/fiji_ce.bin"); @@ -807,7 +806,8 @@ static int gfx_v8_0_init_microcode(struct amdgpu_device *adev) adev->gfx.mec_fw_version = le32_to_cpu(cp_hdr->header.ucode_version); adev->gfx.mec_feature_version = le32_to_cpu(cp_hdr->ucode_feature_version); - if (adev->asic_type != CHIP_STONEY) { + if ((adev->asic_type != CHIP_STONEY) && + (adev->asic_type != CHIP_TOPAZ)) { snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_mec2.bin", chip_name); err = request_firmware(&adev->gfx.mec2_fw, fw_name, adev->dev); if (!err) { @@ -4681,7 +4681,8 @@ static void gfx_v8_0_ring_emit_vm_flush(struct amdgpu_ring *ring, amdgpu_ring_write(ring, PACKET3(PACKET3_WAIT_REG_MEM, 5)); amdgpu_ring_write(ring, (WAIT_REG_MEM_MEM_SPACE(1) | /* memory */ - WAIT_REG_MEM_FUNCTION(3))); /* equal */ + WAIT_REG_MEM_FUNCTION(3) | /* equal */ + WAIT_REG_MEM_ENGINE(usepfp))); /* pfp or me */ amdgpu_ring_write(ring, addr & 0xfffffffc); amdgpu_ring_write(ring, upper_32_bits(addr) & 0xffffffff); amdgpu_ring_write(ring, seq); diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c index ed8abb58a785..df17fababbd6 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c @@ -42,9 +42,39 @@ static void gmc_v7_0_set_irq_funcs(struct amdgpu_device *adev); MODULE_FIRMWARE("radeon/bonaire_mc.bin"); MODULE_FIRMWARE("radeon/hawaii_mc.bin"); +MODULE_FIRMWARE("amdgpu/topaz_mc.bin"); + +static const u32 golden_settings_iceland_a11[] = +{ + mmVM_PRT_APERTURE0_LOW_ADDR, 0x0fffffff, 0x0fffffff, + mmVM_PRT_APERTURE1_LOW_ADDR, 0x0fffffff, 0x0fffffff, + mmVM_PRT_APERTURE2_LOW_ADDR, 0x0fffffff, 0x0fffffff, + mmVM_PRT_APERTURE3_LOW_ADDR, 0x0fffffff, 0x0fffffff +}; + +static const u32 iceland_mgcg_cgcg_init[] = +{ + mmMC_MEM_POWER_LS, 0xffffffff, 0x00000104 +}; + +static void gmc_v7_0_init_golden_registers(struct amdgpu_device *adev) +{ + switch (adev->asic_type) { + case CHIP_TOPAZ: + amdgpu_program_register_sequence(adev, + iceland_mgcg_cgcg_init, + (const u32)ARRAY_SIZE(iceland_mgcg_cgcg_init)); + amdgpu_program_register_sequence(adev, + golden_settings_iceland_a11, + (const u32)ARRAY_SIZE(golden_settings_iceland_a11)); + break; + default: + break; + } +} /** - * gmc8_mc_wait_for_idle - wait for MC idle callback. + * gmc7_mc_wait_for_idle - wait for MC idle callback. * * @adev: amdgpu_device pointer * @@ -132,13 +162,21 @@ static int gmc_v7_0_init_microcode(struct amdgpu_device *adev) case CHIP_HAWAII: chip_name = "hawaii"; break; + case CHIP_TOPAZ: + chip_name = "topaz"; + break; case CHIP_KAVERI: case CHIP_KABINI: + case CHIP_MULLINS: return 0; default: BUG(); } - snprintf(fw_name, sizeof(fw_name), "radeon/%s_mc.bin", chip_name); + if (adev->asic_type == CHIP_TOPAZ) + snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_mc.bin", chip_name); + else + snprintf(fw_name, sizeof(fw_name), "radeon/%s_mc.bin", chip_name); + err = request_firmware(&adev->mc.fw, fw_name, adev->dev); if (err) goto out; @@ -861,14 +899,6 @@ static int gmc_v7_0_early_init(void *handle) gmc_v7_0_set_gart_funcs(adev); gmc_v7_0_set_irq_funcs(adev); - if (adev->flags & AMD_IS_APU) { - adev->mc.vram_type = AMDGPU_VRAM_TYPE_UNKNOWN; - } else { - u32 tmp = RREG32(mmMC_SEQ_MISC0); - tmp &= MC_SEQ_MISC0__MT__MASK; - adev->mc.vram_type = gmc_v7_0_convert_vram_type(tmp); - } - return 0; } @@ -889,6 +919,14 @@ static int gmc_v7_0_sw_init(void *handle) if (r) return r; + if (adev->flags & AMD_IS_APU) { + adev->mc.vram_type = AMDGPU_VRAM_TYPE_UNKNOWN; + } else { + u32 tmp = RREG32(mmMC_SEQ_MISC0); + tmp &= MC_SEQ_MISC0__MT__MASK; + adev->mc.vram_type = gmc_v7_0_convert_vram_type(tmp); + } + r = amdgpu_irq_add_id(adev, 146, &adev->mc.vm_fault); if (r) return r; @@ -980,6 +1018,8 @@ static int gmc_v7_0_hw_init(void *handle) int r; struct amdgpu_device *adev = (struct amdgpu_device *)handle; + gmc_v7_0_init_golden_registers(adev); + gmc_v7_0_mc_program(adev); if (!(adev->flags & AMD_IS_APU)) { diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c index d39028440814..08423089fb84 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c @@ -42,9 +42,7 @@ static void gmc_v8_0_set_gart_funcs(struct amdgpu_device *adev); static void gmc_v8_0_set_irq_funcs(struct amdgpu_device *adev); -MODULE_FIRMWARE("amdgpu/topaz_mc.bin"); MODULE_FIRMWARE("amdgpu/tonga_mc.bin"); -MODULE_FIRMWARE("amdgpu/fiji_mc.bin"); static const u32 golden_settings_tonga_a11[] = { @@ -75,19 +73,6 @@ static const u32 fiji_mgcg_cgcg_init[] = mmMC_MEM_POWER_LS, 0xffffffff, 0x00000104 }; -static const u32 golden_settings_iceland_a11[] = -{ - mmVM_PRT_APERTURE0_LOW_ADDR, 0x0fffffff, 0x0fffffff, - mmVM_PRT_APERTURE1_LOW_ADDR, 0x0fffffff, 0x0fffffff, - mmVM_PRT_APERTURE2_LOW_ADDR, 0x0fffffff, 0x0fffffff, - mmVM_PRT_APERTURE3_LOW_ADDR, 0x0fffffff, 0x0fffffff -}; - -static const u32 iceland_mgcg_cgcg_init[] = -{ - mmMC_MEM_POWER_LS, 0xffffffff, 0x00000104 -}; - static const u32 cz_mgcg_cgcg_init[] = { mmMC_MEM_POWER_LS, 0xffffffff, 0x00000104 @@ -102,14 +87,6 @@ static const u32 stoney_mgcg_cgcg_init[] = static void gmc_v8_0_init_golden_registers(struct amdgpu_device *adev) { switch (adev->asic_type) { - case CHIP_TOPAZ: - amdgpu_program_register_sequence(adev, - iceland_mgcg_cgcg_init, - (const u32)ARRAY_SIZE(iceland_mgcg_cgcg_init)); - amdgpu_program_register_sequence(adev, - golden_settings_iceland_a11, - (const u32)ARRAY_SIZE(golden_settings_iceland_a11)); - break; case CHIP_FIJI: amdgpu_program_register_sequence(adev, fiji_mgcg_cgcg_init, @@ -229,15 +206,10 @@ static int gmc_v8_0_init_microcode(struct amdgpu_device *adev) DRM_DEBUG("\n"); switch (adev->asic_type) { - case CHIP_TOPAZ: - chip_name = "topaz"; - break; case CHIP_TONGA: chip_name = "tonga"; break; case CHIP_FIJI: - chip_name = "fiji"; - break; case CHIP_CARRIZO: case CHIP_STONEY: return 0; @@ -880,14 +852,6 @@ static int gmc_v8_0_early_init(void *handle) gmc_v8_0_set_gart_funcs(adev); gmc_v8_0_set_irq_funcs(adev); - if (adev->flags & AMD_IS_APU) { - adev->mc.vram_type = AMDGPU_VRAM_TYPE_UNKNOWN; - } else { - u32 tmp = RREG32(mmMC_SEQ_MISC0); - tmp &= MC_SEQ_MISC0__MT__MASK; - adev->mc.vram_type = gmc_v8_0_convert_vram_type(tmp); - } - return 0; } @@ -898,6 +862,8 @@ static int gmc_v8_0_late_init(void *handle) return amdgpu_irq_get(adev, &adev->mc.vm_fault, 0); } +#define mmMC_SEQ_MISC0_FIJI 0xA71 + static int gmc_v8_0_sw_init(void *handle) { int r; @@ -908,6 +874,19 @@ static int gmc_v8_0_sw_init(void *handle) if (r) return r; + if (adev->flags & AMD_IS_APU) { + adev->mc.vram_type = AMDGPU_VRAM_TYPE_UNKNOWN; + } else { + u32 tmp; + + if (adev->asic_type == CHIP_FIJI) + tmp = RREG32(mmMC_SEQ_MISC0_FIJI); + else + tmp = RREG32(mmMC_SEQ_MISC0); + tmp &= MC_SEQ_MISC0__MT__MASK; + adev->mc.vram_type = gmc_v8_0_convert_vram_type(tmp); + } + r = amdgpu_irq_add_id(adev, 146, &adev->mc.vm_fault); if (r) return r; @@ -1003,7 +982,7 @@ static int gmc_v8_0_hw_init(void *handle) gmc_v8_0_mc_program(adev); - if (!(adev->flags & AMD_IS_APU)) { + if (adev->asic_type == CHIP_TONGA) { r = gmc_v8_0_mc_load_microcode(adev); if (r) { DRM_ERROR("Failed to load MC firmware!\n"); diff --git a/drivers/gpu/drm/amd/amdgpu/iceland_smc.c b/drivers/gpu/drm/amd/amdgpu/iceland_smc.c index 966d4b2ed9da..090486c18249 100644 --- a/drivers/gpu/drm/amd/amdgpu/iceland_smc.c +++ b/drivers/gpu/drm/amd/amdgpu/iceland_smc.c @@ -432,7 +432,7 @@ static uint32_t iceland_smu_get_mask_for_fw_type(uint32_t fw_type) case AMDGPU_UCODE_ID_CP_ME: return UCODE_ID_CP_ME_MASK; case AMDGPU_UCODE_ID_CP_MEC1: - return UCODE_ID_CP_MEC_MASK | UCODE_ID_CP_MEC_JT1_MASK | UCODE_ID_CP_MEC_JT2_MASK; + return UCODE_ID_CP_MEC_MASK | UCODE_ID_CP_MEC_JT1_MASK; case AMDGPU_UCODE_ID_CP_MEC2: return UCODE_ID_CP_MEC_MASK; case AMDGPU_UCODE_ID_RLC_G: @@ -522,12 +522,6 @@ static int iceland_smu_request_load_fw(struct amdgpu_device *adev) return -EINVAL; } - if (iceland_smu_populate_single_firmware_entry(adev, UCODE_ID_CP_MEC_JT2, - &toc->entry[toc->num_entries++])) { - DRM_ERROR("Failed to get firmware entry for MEC_JT2\n"); - return -EINVAL; - } - if (iceland_smu_populate_single_firmware_entry(adev, UCODE_ID_SDMA0, &toc->entry[toc->num_entries++])) { DRM_ERROR("Failed to get firmware entry for SDMA0\n"); @@ -550,8 +544,8 @@ static int iceland_smu_request_load_fw(struct amdgpu_device *adev) UCODE_ID_CP_ME_MASK | UCODE_ID_CP_PFP_MASK | UCODE_ID_CP_MEC_MASK | - UCODE_ID_CP_MEC_JT1_MASK | - UCODE_ID_CP_MEC_JT2_MASK; + UCODE_ID_CP_MEC_JT1_MASK; + if (iceland_send_msg_to_smc_with_parameter_without_waiting(adev, PPSMC_MSG_LoadUcodes, fw_to_load)) { DRM_ERROR("Fail to request SMU load ucode\n"); diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c b/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c index 2cf50180cc51..b1c7a9b3631b 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c @@ -32,8 +32,8 @@ #include "oss/oss_2_4_d.h" #include "oss/oss_2_4_sh_mask.h" -#include "gmc/gmc_8_1_d.h" -#include "gmc/gmc_8_1_sh_mask.h" +#include "gmc/gmc_7_1_d.h" +#include "gmc/gmc_7_1_sh_mask.h" #include "gca/gfx_8_0_d.h" #include "gca/gfx_8_0_enum.h" diff --git a/drivers/gpu/drm/amd/amdgpu/tonga_dpm.c b/drivers/gpu/drm/amd/amdgpu/tonga_dpm.c index 204903897b4f..63d6cb3c1110 100644 --- a/drivers/gpu/drm/amd/amdgpu/tonga_dpm.c +++ b/drivers/gpu/drm/amd/amdgpu/tonga_dpm.c @@ -122,25 +122,12 @@ static int tonga_dpm_hw_fini(void *handle) static int tonga_dpm_suspend(void *handle) { - return 0; + return tonga_dpm_hw_fini(handle); } static int tonga_dpm_resume(void *handle) { - int ret; - struct amdgpu_device *adev = (struct amdgpu_device *)handle; - - mutex_lock(&adev->pm.mutex); - - ret = tonga_smu_start(adev); - if (ret) { - DRM_ERROR("SMU start failed\n"); - goto fail; - } - -fail: - mutex_unlock(&adev->pm.mutex); - return ret; + return tonga_dpm_hw_init(handle); } static int tonga_dpm_set_clockgating_state(void *handle, diff --git a/drivers/gpu/drm/amd/amdgpu/vi.c b/drivers/gpu/drm/amd/amdgpu/vi.c index 2adc1c855e85..3e9cbe398151 100644 --- a/drivers/gpu/drm/amd/amdgpu/vi.c +++ b/drivers/gpu/drm/amd/amdgpu/vi.c @@ -60,6 +60,7 @@ #include "vi.h" #include "vi_dpm.h" #include "gmc_v8_0.h" +#include "gmc_v7_0.h" #include "gfx_v8_0.h" #include "sdma_v2_4.h" #include "sdma_v3_0.h" @@ -1081,10 +1082,10 @@ static const struct amdgpu_ip_block_version topaz_ip_blocks[] = }, { .type = AMD_IP_BLOCK_TYPE_GMC, - .major = 8, - .minor = 0, + .major = 7, + .minor = 4, .rev = 0, - .funcs = &gmc_v8_0_ip_funcs, + .funcs = &gmc_v7_0_ip_funcs, }, { .type = AMD_IP_BLOCK_TYPE_IH, diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_dbgdev.c b/drivers/gpu/drm/amd/amdkfd/kfd_dbgdev.c index c34c393e9aea..d5e19b5fbbfb 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_dbgdev.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_dbgdev.c @@ -513,7 +513,7 @@ static int dbgdev_wave_control_set_registers( union SQ_CMD_BITS *in_reg_sq_cmd, union GRBM_GFX_INDEX_BITS *in_reg_gfx_index) { - int status; + int status = 0; union SQ_CMD_BITS reg_sq_cmd; union GRBM_GFX_INDEX_BITS reg_gfx_index; struct HsaDbgWaveMsgAMDGen2 *pMsg; diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process.c b/drivers/gpu/drm/amd/amdkfd/kfd_process.c index 9be007081b72..eb1da83c9902 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_process.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_process.c @@ -242,13 +242,19 @@ static void kfd_process_notifier_release(struct mmu_notifier *mn, pqm_uninit(&p->pqm); /* Iterate over all process device data structure and check - * if we should reset all wavefronts */ - list_for_each_entry(pdd, &p->per_device_data, per_device_list) + * if we should delete debug managers and reset all wavefronts + */ + list_for_each_entry(pdd, &p->per_device_data, per_device_list) { + if ((pdd->dev->dbgmgr) && + (pdd->dev->dbgmgr->pasid == p->pasid)) + kfd_dbgmgr_destroy(pdd->dev->dbgmgr); + if (pdd->reset_wavefronts) { pr_warn("amdkfd: Resetting all wave fronts\n"); dbgdev_wave_reset_wavefronts(pdd->dev, p); pdd->reset_wavefronts = false; } + } mutex_unlock(&p->mutex); @@ -404,42 +410,52 @@ void kfd_unbind_process_from_device(struct kfd_dev *dev, unsigned int pasid) idx = srcu_read_lock(&kfd_processes_srcu); + /* + * Look for the process that matches the pasid. If there is no such + * process, we either released it in amdkfd's own notifier, or there + * is a bug. Unfortunately, there is no way to tell... + */ hash_for_each_rcu(kfd_processes_table, i, p, kfd_processes) - if (p->pasid == pasid) - break; + if (p->pasid == pasid) { - srcu_read_unlock(&kfd_processes_srcu, idx); + srcu_read_unlock(&kfd_processes_srcu, idx); - BUG_ON(p->pasid != pasid); + pr_debug("Unbinding process %d from IOMMU\n", pasid); - mutex_lock(&p->mutex); + mutex_lock(&p->mutex); - if ((dev->dbgmgr) && (dev->dbgmgr->pasid == p->pasid)) - kfd_dbgmgr_destroy(dev->dbgmgr); + if ((dev->dbgmgr) && (dev->dbgmgr->pasid == p->pasid)) + kfd_dbgmgr_destroy(dev->dbgmgr); - pqm_uninit(&p->pqm); + pqm_uninit(&p->pqm); - pdd = kfd_get_process_device_data(dev, p); + pdd = kfd_get_process_device_data(dev, p); - if (!pdd) { - mutex_unlock(&p->mutex); - return; - } + if (!pdd) { + mutex_unlock(&p->mutex); + return; + } - if (pdd->reset_wavefronts) { - dbgdev_wave_reset_wavefronts(pdd->dev, p); - pdd->reset_wavefronts = false; - } + if (pdd->reset_wavefronts) { + dbgdev_wave_reset_wavefronts(pdd->dev, p); + pdd->reset_wavefronts = false; + } - /* - * Just mark pdd as unbound, because we still need it to call - * amd_iommu_unbind_pasid() in when the process exits. - * We don't call amd_iommu_unbind_pasid() here - * because the IOMMU called us. - */ - pdd->bound = false; + /* + * Just mark pdd as unbound, because we still need it + * to call amd_iommu_unbind_pasid() in when the + * process exits. + * We don't call amd_iommu_unbind_pasid() here + * because the IOMMU called us. + */ + pdd->bound = false; - mutex_unlock(&p->mutex); + mutex_unlock(&p->mutex); + + return; + } + + srcu_read_unlock(&kfd_processes_srcu, idx); } struct kfd_process_device *kfd_get_first_process_device_data(struct kfd_process *p) diff --git a/drivers/gpu/drm/ast/ast_main.c b/drivers/gpu/drm/ast/ast_main.c index 541a610667ad..e0b4586a26fd 100644 --- a/drivers/gpu/drm/ast/ast_main.c +++ b/drivers/gpu/drm/ast/ast_main.c @@ -227,7 +227,7 @@ static int ast_get_dram_info(struct drm_device *dev) } while (ast_read32(ast, 0x10000) != 0x01); data = ast_read32(ast, 0x10004); - if (data & 0x400) + if (data & 0x40) ast->dram_bus_width = 16; else ast->dram_bus_width = 32; diff --git a/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_plane.c b/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_plane.c index d0299aed517e..e231176cb66b 100644 --- a/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_plane.c +++ b/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_plane.c @@ -316,25 +316,27 @@ atmel_hlcdc_plane_update_pos_and_size(struct atmel_hlcdc_plane *plane, u32 *coeff_tab = heo_upscaling_ycoef; u32 max_memsize; - if (state->crtc_w < state->src_w) + if (state->crtc_h < state->src_h) coeff_tab = heo_downscaling_ycoef; for (i = 0; i < ARRAY_SIZE(heo_upscaling_ycoef); i++) atmel_hlcdc_layer_update_cfg(&plane->layer, 33 + i, 0xffffffff, coeff_tab[i]); - factor = ((8 * 256 * state->src_w) - (256 * 4)) / - state->crtc_w; + factor = ((8 * 256 * state->src_h) - (256 * 4)) / + state->crtc_h; factor++; - max_memsize = ((factor * state->crtc_w) + (256 * 4)) / + max_memsize = ((factor * state->crtc_h) + (256 * 4)) / 2048; - if (max_memsize > state->src_w) + if (max_memsize > state->src_h) factor--; factor_reg |= (factor << 16) | 0x80000000; } atmel_hlcdc_layer_update_cfg(&plane->layer, 13, 0xffffffff, factor_reg); + } else { + atmel_hlcdc_layer_update_cfg(&plane->layer, 13, 0xffffffff, 0); } } diff --git a/drivers/gpu/drm/drm_atomic.c b/drivers/gpu/drm/drm_atomic.c index aeee083c7f95..6253775b8d9c 100644 --- a/drivers/gpu/drm/drm_atomic.c +++ b/drivers/gpu/drm/drm_atomic.c @@ -150,7 +150,7 @@ void drm_atomic_state_default_clear(struct drm_atomic_state *state) for (i = 0; i < state->num_connector; i++) { struct drm_connector *connector = state->connectors[i]; - if (!connector) + if (!connector || !connector->funcs) continue; /* @@ -367,6 +367,8 @@ int drm_atomic_set_mode_prop_for_crtc(struct drm_crtc_state *state, drm_property_unreference_blob(state->mode_blob); state->mode_blob = NULL; + memset(&state->mode, 0, sizeof(state->mode)); + if (blob) { if (blob->length != sizeof(struct drm_mode_modeinfo) || drm_mode_convert_umode(&state->mode, @@ -379,7 +381,6 @@ int drm_atomic_set_mode_prop_for_crtc(struct drm_crtc_state *state, DRM_DEBUG_ATOMIC("Set [MODE:%s] for CRTC state %p\n", state->mode.name, state); } else { - memset(&state->mode, 0, sizeof(state->mode)); state->enable = false; DRM_DEBUG_ATOMIC("Set [NOMODE] for CRTC state %p\n", state); diff --git a/drivers/gpu/drm/drm_atomic_helper.c b/drivers/gpu/drm/drm_atomic_helper.c index e5aec45bf985..1ac29d703c12 100644 --- a/drivers/gpu/drm/drm_atomic_helper.c +++ b/drivers/gpu/drm/drm_atomic_helper.c @@ -108,7 +108,6 @@ steal_encoder(struct drm_atomic_state *state, struct drm_crtc_state *crtc_state; struct drm_connector *connector; struct drm_connector_state *connector_state; - int ret; /* * We can only steal an encoder coming from a connector, which means we @@ -139,9 +138,6 @@ steal_encoder(struct drm_atomic_state *state, if (IS_ERR(connector_state)) return PTR_ERR(connector_state); - ret = drm_atomic_set_crtc_for_connector(connector_state, NULL); - if (ret) - return ret; connector_state->best_encoder = NULL; } diff --git a/drivers/gpu/drm/drm_cache.c b/drivers/gpu/drm/drm_cache.c index 6743ff7dccfa..7f4a6c550319 100644 --- a/drivers/gpu/drm/drm_cache.c +++ b/drivers/gpu/drm/drm_cache.c @@ -136,6 +136,7 @@ drm_clflush_virt_range(void *addr, unsigned long length) mb(); for (; addr < end; addr += size) clflushopt(addr); + clflushopt(end - 1); /* force serialisation */ mb(); return; } diff --git a/drivers/gpu/drm/drm_crtc.c b/drivers/gpu/drm/drm_crtc.c index 24c5434abd1c..5e4bb4837bae 100644 --- a/drivers/gpu/drm/drm_crtc.c +++ b/drivers/gpu/drm/drm_crtc.c @@ -2682,8 +2682,6 @@ int drm_mode_setcrtc(struct drm_device *dev, void *data, goto out; } - drm_mode_set_crtcinfo(mode, CRTC_INTERLACE_HALVE_V); - /* * Check whether the primary plane supports the fb pixel format. * Drivers not implementing the universal planes API use a @@ -3316,6 +3314,24 @@ int drm_mode_addfb2(struct drm_device *dev, return 0; } +struct drm_mode_rmfb_work { + struct work_struct work; + struct list_head fbs; +}; + +static void drm_mode_rmfb_work_fn(struct work_struct *w) +{ + struct drm_mode_rmfb_work *arg = container_of(w, typeof(*arg), work); + + while (!list_empty(&arg->fbs)) { + struct drm_framebuffer *fb = + list_first_entry(&arg->fbs, typeof(*fb), filp_head); + + list_del_init(&fb->filp_head); + drm_framebuffer_remove(fb); + } +} + /** * drm_mode_rmfb - remove an FB from the configuration * @dev: drm device for the ioctl @@ -3356,7 +3372,25 @@ int drm_mode_rmfb(struct drm_device *dev, mutex_unlock(&dev->mode_config.fb_lock); mutex_unlock(&file_priv->fbs_lock); - drm_framebuffer_unreference(fb); + /* + * we now own the reference that was stored in the fbs list + * + * drm_framebuffer_remove may fail with -EINTR on pending signals, + * so run this in a separate stack as there's no way to correctly + * handle this after the fb is already removed from the lookup table. + */ + if (atomic_read(&fb->refcount.refcount) > 1) { + struct drm_mode_rmfb_work arg; + + INIT_WORK_ONSTACK(&arg.work, drm_mode_rmfb_work_fn); + INIT_LIST_HEAD(&arg.fbs); + list_add_tail(&fb->filp_head, &arg.fbs); + + schedule_work(&arg.work); + flush_work(&arg.work); + destroy_work_on_stack(&arg.work); + } else + drm_framebuffer_unreference(fb); return 0; @@ -3509,7 +3543,6 @@ out_err1: return ret; } - /** * drm_fb_release - remove and free the FBs on this file * @priv: drm file for the ioctl @@ -3524,6 +3557,9 @@ out_err1: void drm_fb_release(struct drm_file *priv) { struct drm_framebuffer *fb, *tfb; + struct drm_mode_rmfb_work arg; + + INIT_LIST_HEAD(&arg.fbs); /* * When the file gets released that means no one else can access the fb @@ -3536,10 +3572,22 @@ void drm_fb_release(struct drm_file *priv) * at it any more. */ list_for_each_entry_safe(fb, tfb, &priv->fbs, filp_head) { - list_del_init(&fb->filp_head); + if (atomic_read(&fb->refcount.refcount) > 1) { + list_move_tail(&fb->filp_head, &arg.fbs); + } else { + list_del_init(&fb->filp_head); - /* This drops the fpriv->fbs reference. */ - drm_framebuffer_unreference(fb); + /* This drops the fpriv->fbs reference. */ + drm_framebuffer_unreference(fb); + } + } + + if (!list_empty(&arg.fbs)) { + INIT_WORK_ONSTACK(&arg.work, drm_mode_rmfb_work_fn); + + schedule_work(&arg.work); + flush_work(&arg.work); + destroy_work_on_stack(&arg.work); } } @@ -5183,6 +5231,9 @@ int drm_mode_page_flip_ioctl(struct drm_device *dev, unsigned long flags; int ret = -EINVAL; + if (!drm_core_check_feature(dev, DRIVER_MODESET)) + return -EINVAL; + if (page_flip->flags & ~DRM_MODE_PAGE_FLIP_FLAGS || page_flip->reserved != 0) return -EINVAL; diff --git a/drivers/gpu/drm/drm_dp_helper.c b/drivers/gpu/drm/drm_dp_helper.c index 9535c5b60387..7e5a97204051 100644 --- a/drivers/gpu/drm/drm_dp_helper.c +++ b/drivers/gpu/drm/drm_dp_helper.c @@ -178,7 +178,7 @@ static int drm_dp_dpcd_access(struct drm_dp_aux *aux, u8 request, { struct drm_dp_aux_msg msg; unsigned int retry; - int err; + int err = 0; memset(&msg, 0, sizeof(msg)); msg.address = offset; @@ -186,6 +186,8 @@ static int drm_dp_dpcd_access(struct drm_dp_aux *aux, u8 request, msg.buffer = buffer; msg.size = size; + mutex_lock(&aux->hw_mutex); + /* * The specification doesn't give any recommendation on how often to * retry native transactions. We used to retry 7 times like for @@ -194,25 +196,24 @@ static int drm_dp_dpcd_access(struct drm_dp_aux *aux, u8 request, */ for (retry = 0; retry < 32; retry++) { - mutex_lock(&aux->hw_mutex); err = aux->transfer(aux, &msg); - mutex_unlock(&aux->hw_mutex); if (err < 0) { if (err == -EBUSY) continue; - return err; + goto unlock; } switch (msg.reply & DP_AUX_NATIVE_REPLY_MASK) { case DP_AUX_NATIVE_REPLY_ACK: if (err < size) - return -EPROTO; - return err; + err = -EPROTO; + goto unlock; case DP_AUX_NATIVE_REPLY_NACK: - return -EIO; + err = -EIO; + goto unlock; case DP_AUX_NATIVE_REPLY_DEFER: usleep_range(AUX_RETRY_INTERVAL, AUX_RETRY_INTERVAL + 100); @@ -221,7 +222,11 @@ static int drm_dp_dpcd_access(struct drm_dp_aux *aux, u8 request, } DRM_DEBUG_KMS("too many retries, giving up\n"); - return -EIO; + err = -EIO; + +unlock: + mutex_unlock(&aux->hw_mutex); + return err; } /** @@ -543,9 +548,7 @@ static int drm_dp_i2c_do_msg(struct drm_dp_aux *aux, struct drm_dp_aux_msg *msg) int max_retries = max(7, drm_dp_i2c_retry_count(msg, dp_aux_i2c_speed_khz)); for (retry = 0, defer_i2c = 0; retry < (max_retries + defer_i2c); retry++) { - mutex_lock(&aux->hw_mutex); ret = aux->transfer(aux, msg); - mutex_unlock(&aux->hw_mutex); if (ret < 0) { if (ret == -EBUSY) continue; @@ -684,6 +687,8 @@ static int drm_dp_i2c_xfer(struct i2c_adapter *adapter, struct i2c_msg *msgs, memset(&msg, 0, sizeof(msg)); + mutex_lock(&aux->hw_mutex); + for (i = 0; i < num; i++) { msg.address = msgs[i].addr; drm_dp_i2c_msg_set_request(&msg, &msgs[i]); @@ -738,6 +743,8 @@ static int drm_dp_i2c_xfer(struct i2c_adapter *adapter, struct i2c_msg *msgs, msg.size = 0; (void)drm_dp_i2c_do_msg(aux, &msg); + mutex_unlock(&aux->hw_mutex); + return err; } diff --git a/drivers/gpu/drm/drm_dp_mst_topology.c b/drivers/gpu/drm/drm_dp_mst_topology.c index 809959d56d78..2485fb652716 100644 --- a/drivers/gpu/drm/drm_dp_mst_topology.c +++ b/drivers/gpu/drm/drm_dp_mst_topology.c @@ -798,6 +798,18 @@ static struct drm_dp_mst_branch *drm_dp_add_mst_branch_device(u8 lct, u8 *rad) return mstb; } +static void drm_dp_free_mst_port(struct kref *kref); + +static void drm_dp_free_mst_branch_device(struct kref *kref) +{ + struct drm_dp_mst_branch *mstb = container_of(kref, struct drm_dp_mst_branch, kref); + if (mstb->port_parent) { + if (list_empty(&mstb->port_parent->next)) + kref_put(&mstb->port_parent->kref, drm_dp_free_mst_port); + } + kfree(mstb); +} + static void drm_dp_destroy_mst_branch_device(struct kref *kref) { struct drm_dp_mst_branch *mstb = container_of(kref, struct drm_dp_mst_branch, kref); @@ -805,6 +817,15 @@ static void drm_dp_destroy_mst_branch_device(struct kref *kref) bool wake_tx = false; /* + * init kref again to be used by ports to remove mst branch when it is + * not needed anymore + */ + kref_init(kref); + + if (mstb->port_parent && list_empty(&mstb->port_parent->next)) + kref_get(&mstb->port_parent->kref); + + /* * destroy all ports - don't need lock * as there are no more references to the mst branch * device at this point. @@ -830,7 +851,8 @@ static void drm_dp_destroy_mst_branch_device(struct kref *kref) if (wake_tx) wake_up(&mstb->mgr->tx_waitq); - kfree(mstb); + + kref_put(kref, drm_dp_free_mst_branch_device); } static void drm_dp_put_mst_branch_device(struct drm_dp_mst_branch *mstb) @@ -878,6 +900,7 @@ static void drm_dp_destroy_port(struct kref *kref) * from an EDID retrieval */ mutex_lock(&mgr->destroy_connector_lock); + kref_get(&port->parent->kref); list_add(&port->next, &mgr->destroy_connector_list); mutex_unlock(&mgr->destroy_connector_lock); schedule_work(&mgr->destroy_connector_work); @@ -973,17 +996,17 @@ static struct drm_dp_mst_port *drm_dp_get_port(struct drm_dp_mst_branch *mstb, u static u8 drm_dp_calculate_rad(struct drm_dp_mst_port *port, u8 *rad) { - int lct = port->parent->lct; + int parent_lct = port->parent->lct; int shift = 4; - int idx = lct / 2; - if (lct > 1) { - memcpy(rad, port->parent->rad, idx); - shift = (lct % 2) ? 4 : 0; + int idx = (parent_lct - 1) / 2; + if (parent_lct > 1) { + memcpy(rad, port->parent->rad, idx + 1); + shift = (parent_lct % 2) ? 4 : 0; } else rad[0] = 0; rad[idx] |= port->port_num << shift; - return lct + 1; + return parent_lct + 1; } /* @@ -1013,18 +1036,27 @@ static bool drm_dp_port_setup_pdt(struct drm_dp_mst_port *port) return send_link; } -static void drm_dp_check_port_guid(struct drm_dp_mst_branch *mstb, - struct drm_dp_mst_port *port) +static void drm_dp_check_mstb_guid(struct drm_dp_mst_branch *mstb, u8 *guid) { int ret; - if (port->dpcd_rev >= 0x12) { - port->guid_valid = drm_dp_validate_guid(mstb->mgr, port->guid); - if (!port->guid_valid) { - ret = drm_dp_send_dpcd_write(mstb->mgr, - port, - DP_GUID, - 16, port->guid); - port->guid_valid = true; + + memcpy(mstb->guid, guid, 16); + + if (!drm_dp_validate_guid(mstb->mgr, mstb->guid)) { + if (mstb->port_parent) { + ret = drm_dp_send_dpcd_write( + mstb->mgr, + mstb->port_parent, + DP_GUID, + 16, + mstb->guid); + } else { + + ret = drm_dp_dpcd_write( + mstb->mgr->aux, + DP_GUID, + mstb->guid, + 16); } } } @@ -1039,7 +1071,7 @@ static void build_mst_prop_path(const struct drm_dp_mst_branch *mstb, snprintf(proppath, proppath_size, "mst:%d", mstb->mgr->conn_base_id); for (i = 0; i < (mstb->lct - 1); i++) { int shift = (i % 2) ? 0 : 4; - int port_num = mstb->rad[i / 2] >> shift; + int port_num = (mstb->rad[i / 2] >> shift) & 0xf; snprintf(temp, sizeof(temp), "-%d", port_num); strlcat(proppath, temp, proppath_size); } @@ -1081,7 +1113,6 @@ static void drm_dp_add_port(struct drm_dp_mst_branch *mstb, port->dpcd_rev = port_msg->dpcd_revision; port->num_sdp_streams = port_msg->num_sdp_streams; port->num_sdp_stream_sinks = port_msg->num_sdp_stream_sinks; - memcpy(port->guid, port_msg->peer_guid, 16); /* manage mstb port lists with mgr lock - take a reference for this list */ @@ -1094,11 +1125,9 @@ static void drm_dp_add_port(struct drm_dp_mst_branch *mstb, if (old_ddps != port->ddps) { if (port->ddps) { - drm_dp_check_port_guid(mstb, port); if (!port->input) drm_dp_send_enum_path_resources(mstb->mgr, mstb, port); } else { - port->guid_valid = false; port->available_pbn = 0; } } @@ -1157,10 +1186,8 @@ static void drm_dp_update_port(struct drm_dp_mst_branch *mstb, if (old_ddps != port->ddps) { if (port->ddps) { - drm_dp_check_port_guid(mstb, port); dowork = true; } else { - port->guid_valid = false; port->available_pbn = 0; } } @@ -1190,7 +1217,7 @@ static struct drm_dp_mst_branch *drm_dp_get_mst_branch_device(struct drm_dp_mst_ for (i = 0; i < lct - 1; i++) { int shift = (i % 2) ? 0 : 4; - int port_num = rad[i / 2] >> shift; + int port_num = (rad[i / 2] >> shift) & 0xf; list_for_each_entry(port, &mstb->ports, next) { if (port->port_num == port_num) { @@ -1210,6 +1237,48 @@ out: return mstb; } +static struct drm_dp_mst_branch *get_mst_branch_device_by_guid_helper( + struct drm_dp_mst_branch *mstb, + uint8_t *guid) +{ + struct drm_dp_mst_branch *found_mstb; + struct drm_dp_mst_port *port; + + if (memcmp(mstb->guid, guid, 16) == 0) + return mstb; + + + list_for_each_entry(port, &mstb->ports, next) { + if (!port->mstb) + continue; + + found_mstb = get_mst_branch_device_by_guid_helper(port->mstb, guid); + + if (found_mstb) + return found_mstb; + } + + return NULL; +} + +static struct drm_dp_mst_branch *drm_dp_get_mst_branch_device_by_guid( + struct drm_dp_mst_topology_mgr *mgr, + uint8_t *guid) +{ + struct drm_dp_mst_branch *mstb; + + /* find the port by iterating down */ + mutex_lock(&mgr->lock); + + mstb = get_mst_branch_device_by_guid_helper(mgr->mst_primary, guid); + + if (mstb) + kref_get(&mstb->kref); + + mutex_unlock(&mgr->lock); + return mstb; +} + static void drm_dp_check_and_send_link_address(struct drm_dp_mst_topology_mgr *mgr, struct drm_dp_mst_branch *mstb) { @@ -1320,6 +1389,7 @@ static int set_hdr_from_dst_qlock(struct drm_dp_sideband_msg_hdr *hdr, struct drm_dp_sideband_msg_tx *txmsg) { struct drm_dp_mst_branch *mstb = txmsg->dst; + u8 req_type; /* both msg slots are full */ if (txmsg->seqno == -1) { @@ -1336,7 +1406,13 @@ static int set_hdr_from_dst_qlock(struct drm_dp_sideband_msg_hdr *hdr, txmsg->seqno = 1; mstb->tx_slots[txmsg->seqno] = txmsg; } - hdr->broadcast = 0; + + req_type = txmsg->msg[0] & 0x7f; + if (req_type == DP_CONNECTION_STATUS_NOTIFY || + req_type == DP_RESOURCE_STATUS_NOTIFY) + hdr->broadcast = 1; + else + hdr->broadcast = 0; hdr->path_msg = txmsg->path_msg; hdr->lct = mstb->lct; hdr->lcr = mstb->lct - 1; @@ -1438,26 +1514,18 @@ static void process_single_down_tx_qlock(struct drm_dp_mst_topology_mgr *mgr) } /* called holding qlock */ -static void process_single_up_tx_qlock(struct drm_dp_mst_topology_mgr *mgr) +static void process_single_up_tx_qlock(struct drm_dp_mst_topology_mgr *mgr, + struct drm_dp_sideband_msg_tx *txmsg) { - struct drm_dp_sideband_msg_tx *txmsg; int ret; /* construct a chunk from the first msg in the tx_msg queue */ - if (list_empty(&mgr->tx_msg_upq)) { - mgr->tx_up_in_progress = false; - return; - } - - txmsg = list_first_entry(&mgr->tx_msg_upq, struct drm_dp_sideband_msg_tx, next); ret = process_single_tx_qlock(mgr, txmsg, true); - if (ret == 1) { - /* up txmsgs aren't put in slots - so free after we send it */ - list_del(&txmsg->next); - kfree(txmsg); - } else if (ret) + + if (ret != 1) DRM_DEBUG_KMS("failed to send msg in q %d\n", ret); - mgr->tx_up_in_progress = true; + + txmsg->dst->tx_slots[txmsg->seqno] = NULL; } static void drm_dp_queue_down_tx(struct drm_dp_mst_topology_mgr *mgr, @@ -1507,6 +1575,9 @@ static void drm_dp_send_link_address(struct drm_dp_mst_topology_mgr *mgr, txmsg->reply.u.link_addr.ports[i].num_sdp_streams, txmsg->reply.u.link_addr.ports[i].num_sdp_stream_sinks); } + + drm_dp_check_mstb_guid(mstb, txmsg->reply.u.link_addr.guid); + for (i = 0; i < txmsg->reply.u.link_addr.nports; i++) { drm_dp_add_port(mstb, mgr->dev, &txmsg->reply.u.link_addr.ports[i]); } @@ -1554,6 +1625,37 @@ static int drm_dp_send_enum_path_resources(struct drm_dp_mst_topology_mgr *mgr, return 0; } +static struct drm_dp_mst_port *drm_dp_get_last_connected_port_to_mstb(struct drm_dp_mst_branch *mstb) +{ + if (!mstb->port_parent) + return NULL; + + if (mstb->port_parent->mstb != mstb) + return mstb->port_parent; + + return drm_dp_get_last_connected_port_to_mstb(mstb->port_parent->parent); +} + +static struct drm_dp_mst_branch *drm_dp_get_last_connected_port_and_mstb(struct drm_dp_mst_topology_mgr *mgr, + struct drm_dp_mst_branch *mstb, + int *port_num) +{ + struct drm_dp_mst_branch *rmstb = NULL; + struct drm_dp_mst_port *found_port; + mutex_lock(&mgr->lock); + if (mgr->mst_primary) { + found_port = drm_dp_get_last_connected_port_to_mstb(mstb); + + if (found_port) { + rmstb = found_port->parent; + kref_get(&rmstb->kref); + *port_num = found_port->port_num; + } + } + mutex_unlock(&mgr->lock); + return rmstb; +} + static int drm_dp_payload_send_msg(struct drm_dp_mst_topology_mgr *mgr, struct drm_dp_mst_port *port, int id, @@ -1561,12 +1663,23 @@ static int drm_dp_payload_send_msg(struct drm_dp_mst_topology_mgr *mgr, { struct drm_dp_sideband_msg_tx *txmsg; struct drm_dp_mst_branch *mstb; - int len, ret; + int len, ret, port_num; - mstb = drm_dp_get_validated_mstb_ref(mgr, port->parent); - if (!mstb) + port = drm_dp_get_validated_port_ref(mgr, port); + if (!port) return -EINVAL; + port_num = port->port_num; + mstb = drm_dp_get_validated_mstb_ref(mgr, port->parent); + if (!mstb) { + mstb = drm_dp_get_last_connected_port_and_mstb(mgr, port->parent, &port_num); + + if (!mstb) { + drm_dp_put_port(port); + return -EINVAL; + } + } + txmsg = kzalloc(sizeof(*txmsg), GFP_KERNEL); if (!txmsg) { ret = -ENOMEM; @@ -1574,7 +1687,7 @@ static int drm_dp_payload_send_msg(struct drm_dp_mst_topology_mgr *mgr, } txmsg->dst = mstb; - len = build_allocate_payload(txmsg, port->port_num, + len = build_allocate_payload(txmsg, port_num, id, pbn); @@ -1590,6 +1703,7 @@ static int drm_dp_payload_send_msg(struct drm_dp_mst_topology_mgr *mgr, kfree(txmsg); fail_put: drm_dp_put_mst_branch_device(mstb); + drm_dp_put_port(port); return ret; } @@ -1672,6 +1786,11 @@ int drm_dp_update_payload_part1(struct drm_dp_mst_topology_mgr *mgr) req_payload.start_slot = cur_slots; if (mgr->proposed_vcpis[i]) { port = container_of(mgr->proposed_vcpis[i], struct drm_dp_mst_port, vcpi); + port = drm_dp_get_validated_port_ref(mgr, port); + if (!port) { + mutex_unlock(&mgr->payload_lock); + return -EINVAL; + } req_payload.num_slots = mgr->proposed_vcpis[i]->num_slots; } else { port = NULL; @@ -1697,6 +1816,9 @@ int drm_dp_update_payload_part1(struct drm_dp_mst_topology_mgr *mgr) mgr->payloads[i].payload_state = req_payload.payload_state; } cur_slots += req_payload.num_slots; + + if (port) + drm_dp_put_port(port); } for (i = 0; i < mgr->max_payloads; i++) { @@ -1844,11 +1966,12 @@ static int drm_dp_send_up_ack_reply(struct drm_dp_mst_topology_mgr *mgr, drm_dp_encode_up_ack_reply(txmsg, req_type); mutex_lock(&mgr->qlock); - list_add_tail(&txmsg->next, &mgr->tx_msg_upq); - if (!mgr->tx_up_in_progress) { - process_single_up_tx_qlock(mgr); - } + + process_single_up_tx_qlock(mgr, txmsg); + mutex_unlock(&mgr->qlock); + + kfree(txmsg); return 0; } @@ -1927,31 +2050,17 @@ int drm_dp_mst_topology_mgr_set_mst(struct drm_dp_mst_topology_mgr *mgr, bool ms mgr->mst_primary = mstb; kref_get(&mgr->mst_primary->kref); - { - struct drm_dp_payload reset_pay; - reset_pay.start_slot = 0; - reset_pay.num_slots = 0x3f; - drm_dp_dpcd_write_payload(mgr, 0, &reset_pay); - } - ret = drm_dp_dpcd_writeb(mgr->aux, DP_MSTM_CTRL, - DP_MST_EN | DP_UP_REQ_EN | DP_UPSTREAM_IS_SRC); + DP_MST_EN | DP_UP_REQ_EN | DP_UPSTREAM_IS_SRC); if (ret < 0) { goto out_unlock; } - - /* sort out guid */ - ret = drm_dp_dpcd_read(mgr->aux, DP_GUID, mgr->guid, 16); - if (ret != 16) { - DRM_DEBUG_KMS("failed to read DP GUID %d\n", ret); - goto out_unlock; - } - - mgr->guid_valid = drm_dp_validate_guid(mgr, mgr->guid); - if (!mgr->guid_valid) { - ret = drm_dp_dpcd_write(mgr->aux, DP_GUID, mgr->guid, 16); - mgr->guid_valid = true; + { + struct drm_dp_payload reset_pay; + reset_pay.start_slot = 0; + reset_pay.num_slots = 0x3f; + drm_dp_dpcd_write_payload(mgr, 0, &reset_pay); } queue_work(system_long_wq, &mgr->work); @@ -2015,6 +2124,8 @@ int drm_dp_mst_topology_mgr_resume(struct drm_dp_mst_topology_mgr *mgr) if (mgr->mst_primary) { int sret; + u8 guid[16]; + sret = drm_dp_dpcd_read(mgr->aux, DP_DPCD_REV, mgr->dpcd, DP_RECEIVER_CAP_SIZE); if (sret != DP_RECEIVER_CAP_SIZE) { DRM_DEBUG_KMS("dpcd read failed - undocked during suspend?\n"); @@ -2029,6 +2140,16 @@ int drm_dp_mst_topology_mgr_resume(struct drm_dp_mst_topology_mgr *mgr) ret = -1; goto out_unlock; } + + /* Some hubs forget their guids after they resume */ + sret = drm_dp_dpcd_read(mgr->aux, DP_GUID, guid, 16); + if (sret != 16) { + DRM_DEBUG_KMS("dpcd read failed - undocked during suspend?\n"); + ret = -1; + goto out_unlock; + } + drm_dp_check_mstb_guid(mgr->mst_primary, guid); + ret = 0; } else ret = -1; @@ -2145,28 +2266,51 @@ static int drm_dp_mst_handle_up_req(struct drm_dp_mst_topology_mgr *mgr) if (mgr->up_req_recv.have_eomt) { struct drm_dp_sideband_msg_req_body msg; - struct drm_dp_mst_branch *mstb; + struct drm_dp_mst_branch *mstb = NULL; bool seqno; - mstb = drm_dp_get_mst_branch_device(mgr, - mgr->up_req_recv.initial_hdr.lct, - mgr->up_req_recv.initial_hdr.rad); - if (!mstb) { - DRM_DEBUG_KMS("Got MST reply from unknown device %d\n", mgr->up_req_recv.initial_hdr.lct); - memset(&mgr->up_req_recv, 0, sizeof(struct drm_dp_sideband_msg_rx)); - return 0; + + if (!mgr->up_req_recv.initial_hdr.broadcast) { + mstb = drm_dp_get_mst_branch_device(mgr, + mgr->up_req_recv.initial_hdr.lct, + mgr->up_req_recv.initial_hdr.rad); + if (!mstb) { + DRM_DEBUG_KMS("Got MST reply from unknown device %d\n", mgr->up_req_recv.initial_hdr.lct); + memset(&mgr->up_req_recv, 0, sizeof(struct drm_dp_sideband_msg_rx)); + return 0; + } } seqno = mgr->up_req_recv.initial_hdr.seqno; drm_dp_sideband_parse_req(&mgr->up_req_recv, &msg); if (msg.req_type == DP_CONNECTION_STATUS_NOTIFY) { - drm_dp_send_up_ack_reply(mgr, mstb, msg.req_type, seqno, false); + drm_dp_send_up_ack_reply(mgr, mgr->mst_primary, msg.req_type, seqno, false); + + if (!mstb) + mstb = drm_dp_get_mst_branch_device_by_guid(mgr, msg.u.conn_stat.guid); + + if (!mstb) { + DRM_DEBUG_KMS("Got MST reply from unknown device %d\n", mgr->up_req_recv.initial_hdr.lct); + memset(&mgr->up_req_recv, 0, sizeof(struct drm_dp_sideband_msg_rx)); + return 0; + } + drm_dp_update_port(mstb, &msg.u.conn_stat); + DRM_DEBUG_KMS("Got CSN: pn: %d ldps:%d ddps: %d mcs: %d ip: %d pdt: %d\n", msg.u.conn_stat.port_number, msg.u.conn_stat.legacy_device_plug_status, msg.u.conn_stat.displayport_device_plug_status, msg.u.conn_stat.message_capability_status, msg.u.conn_stat.input_port, msg.u.conn_stat.peer_device_type); (*mgr->cbs->hotplug)(mgr); } else if (msg.req_type == DP_RESOURCE_STATUS_NOTIFY) { - drm_dp_send_up_ack_reply(mgr, mstb, msg.req_type, seqno, false); + drm_dp_send_up_ack_reply(mgr, mgr->mst_primary, msg.req_type, seqno, false); + if (!mstb) + mstb = drm_dp_get_mst_branch_device_by_guid(mgr, msg.u.resource_stat.guid); + + if (!mstb) { + DRM_DEBUG_KMS("Got MST reply from unknown device %d\n", mgr->up_req_recv.initial_hdr.lct); + memset(&mgr->up_req_recv, 0, sizeof(struct drm_dp_sideband_msg_rx)); + return 0; + } + DRM_DEBUG_KMS("Got RSN: pn: %d avail_pbn %d\n", msg.u.resource_stat.port_number, msg.u.resource_stat.available_pbn); } @@ -2346,6 +2490,7 @@ bool drm_dp_mst_allocate_vcpi(struct drm_dp_mst_topology_mgr *mgr, struct drm_dp DRM_DEBUG_KMS("payload: vcpi %d already allocated for pbn %d - requested pbn %d\n", port->vcpi.vcpi, port->vcpi.pbn, pbn); if (pbn == port->vcpi.pbn) { *slots = port->vcpi.num_slots; + drm_dp_put_port(port); return true; } } @@ -2505,32 +2650,31 @@ EXPORT_SYMBOL(drm_dp_check_act_status); */ int drm_dp_calc_pbn_mode(int clock, int bpp) { - fixed20_12 pix_bw; - fixed20_12 fbpp; - fixed20_12 result; - fixed20_12 margin, tmp; - u32 res; - - pix_bw.full = dfixed_const(clock); - fbpp.full = dfixed_const(bpp); - tmp.full = dfixed_const(8); - fbpp.full = dfixed_div(fbpp, tmp); - - result.full = dfixed_mul(pix_bw, fbpp); - margin.full = dfixed_const(54); - tmp.full = dfixed_const(64); - margin.full = dfixed_div(margin, tmp); - result.full = dfixed_div(result, margin); - - margin.full = dfixed_const(1006); - tmp.full = dfixed_const(1000); - margin.full = dfixed_div(margin, tmp); - result.full = dfixed_mul(result, margin); - - result.full = dfixed_div(result, tmp); - result.full = dfixed_ceil(result); - res = dfixed_trunc(result); - return res; + u64 kbps; + s64 peak_kbps; + u32 numerator; + u32 denominator; + + kbps = clock * bpp; + + /* + * margin 5300ppm + 300ppm ~ 0.6% as per spec, factor is 1.006 + * The unit of 54/64Mbytes/sec is an arbitrary unit chosen based on + * common multiplier to render an integer PBN for all link rate/lane + * counts combinations + * calculate + * peak_kbps *= (1006/1000) + * peak_kbps *= (64/54) + * peak_kbps *= 8 convert to bytes + */ + + numerator = 64 * 1006; + denominator = 54 * 8 * 1000 * 1000; + + kbps *= numerator; + peak_kbps = drm_fixp_from_fraction(kbps, denominator); + + return drm_fixp2int_ceil(peak_kbps); } EXPORT_SYMBOL(drm_dp_calc_pbn_mode); @@ -2538,11 +2682,23 @@ static int test_calc_pbn_mode(void) { int ret; ret = drm_dp_calc_pbn_mode(154000, 30); - if (ret != 689) + if (ret != 689) { + DRM_ERROR("PBN calculation test failed - clock %d, bpp %d, expected PBN %d, actual PBN %d.\n", + 154000, 30, 689, ret); return -EINVAL; + } ret = drm_dp_calc_pbn_mode(234000, 30); - if (ret != 1047) + if (ret != 1047) { + DRM_ERROR("PBN calculation test failed - clock %d, bpp %d, expected PBN %d, actual PBN %d.\n", + 234000, 30, 1047, ret); return -EINVAL; + } + ret = drm_dp_calc_pbn_mode(297000, 24); + if (ret != 1063) { + DRM_ERROR("PBN calculation test failed - clock %d, bpp %d, expected PBN %d, actual PBN %d.\n", + 297000, 24, 1063, ret); + return -EINVAL; + } return 0; } @@ -2683,6 +2839,13 @@ static void drm_dp_tx_work(struct work_struct *work) mutex_unlock(&mgr->qlock); } +static void drm_dp_free_mst_port(struct kref *kref) +{ + struct drm_dp_mst_port *port = container_of(kref, struct drm_dp_mst_port, kref); + kref_put(&port->parent->kref, drm_dp_free_mst_branch_device); + kfree(port); +} + static void drm_dp_destroy_connector_work(struct work_struct *work) { struct drm_dp_mst_topology_mgr *mgr = container_of(work, struct drm_dp_mst_topology_mgr, destroy_connector_work); @@ -2703,13 +2866,20 @@ static void drm_dp_destroy_connector_work(struct work_struct *work) list_del(&port->next); mutex_unlock(&mgr->destroy_connector_lock); + kref_init(&port->kref); + INIT_LIST_HEAD(&port->next); + mgr->cbs->destroy_connector(mgr, port->connector); drm_dp_port_teardown_pdt(port, port->pdt); - if (!port->input && port->vcpi.vcpi > 0) + if (!port->input && port->vcpi.vcpi > 0) { + drm_dp_mst_reset_vcpi_slots(mgr, port); + drm_dp_update_payload_part1(mgr); drm_dp_mst_put_payload_id(mgr, port->vcpi.vcpi); - kfree(port); + } + + kref_put(&port->kref, drm_dp_free_mst_port); send_hotplug = true; } if (send_hotplug) @@ -2736,7 +2906,6 @@ int drm_dp_mst_topology_mgr_init(struct drm_dp_mst_topology_mgr *mgr, mutex_init(&mgr->qlock); mutex_init(&mgr->payload_lock); mutex_init(&mgr->destroy_connector_lock); - INIT_LIST_HEAD(&mgr->tx_msg_upq); INIT_LIST_HEAD(&mgr->tx_msg_downq); INIT_LIST_HEAD(&mgr->destroy_connector_list); INIT_WORK(&mgr->work, drm_dp_mst_link_probe_work); diff --git a/drivers/gpu/drm/drm_edid.c b/drivers/gpu/drm/drm_edid.c index d5d2c03fd136..8c9ac021608f 100644 --- a/drivers/gpu/drm/drm_edid.c +++ b/drivers/gpu/drm/drm_edid.c @@ -73,6 +73,8 @@ #define EDID_QUIRK_FORCE_8BPC (1 << 8) /* Force 12bpc */ #define EDID_QUIRK_FORCE_12BPC (1 << 9) +/* Force 6bpc */ +#define EDID_QUIRK_FORCE_6BPC (1 << 10) struct detailed_mode_closure { struct drm_connector *connector; @@ -99,6 +101,9 @@ static struct edid_quirk { /* Unknown Acer */ { "ACR", 2423, EDID_QUIRK_FIRST_DETAILED_PREFERRED }, + /* AEO model 0 reports 8 bpc, but is a 6 bpc panel */ + { "AEO", 0, EDID_QUIRK_FORCE_6BPC }, + /* Belinea 10 15 55 */ { "MAX", 1516, EDID_QUIRK_PREFER_LARGE_60 }, { "MAX", 0x77e, EDID_QUIRK_PREFER_LARGE_60 }, @@ -3820,6 +3825,9 @@ int drm_add_edid_modes(struct drm_connector *connector, struct edid *edid) drm_add_display_info(edid, &connector->display_info, connector); + if (quirks & EDID_QUIRK_FORCE_6BPC) + connector->display_info.bpc = 6; + if (quirks & EDID_QUIRK_FORCE_8BPC) connector->display_info.bpc = 8; diff --git a/drivers/gpu/drm/drm_fb_helper.c b/drivers/gpu/drm/drm_fb_helper.c index 69cbab5e5c81..5ad036741b99 100644 --- a/drivers/gpu/drm/drm_fb_helper.c +++ b/drivers/gpu/drm/drm_fb_helper.c @@ -1899,7 +1899,6 @@ static int drm_pick_crtcs(struct drm_fb_helper *fb_helper, int n, int width, int height) { int c, o; - struct drm_device *dev = fb_helper->dev; struct drm_connector *connector; const struct drm_connector_helper_funcs *connector_funcs; struct drm_encoder *encoder; @@ -1918,7 +1917,7 @@ static int drm_pick_crtcs(struct drm_fb_helper *fb_helper, if (modes[n] == NULL) return best_score; - crtcs = kzalloc(dev->mode_config.num_connector * + crtcs = kzalloc(fb_helper->connector_count * sizeof(struct drm_fb_helper_crtc *), GFP_KERNEL); if (!crtcs) return best_score; @@ -1964,7 +1963,7 @@ static int drm_pick_crtcs(struct drm_fb_helper *fb_helper, if (score > best_score) { best_score = score; memcpy(best_crtcs, crtcs, - dev->mode_config.num_connector * + fb_helper->connector_count * sizeof(struct drm_fb_helper_crtc *)); } } diff --git a/drivers/gpu/drm/drm_gem.c b/drivers/gpu/drm/drm_gem.c index c7de454e8e88..b205224f1a44 100644 --- a/drivers/gpu/drm/drm_gem.c +++ b/drivers/gpu/drm/drm_gem.c @@ -338,27 +338,32 @@ drm_gem_handle_create_tail(struct drm_file *file_priv, spin_unlock(&file_priv->table_lock); idr_preload_end(); mutex_unlock(&dev->object_name_lock); - if (ret < 0) { - drm_gem_object_handle_unreference_unlocked(obj); - return ret; - } + if (ret < 0) + goto err_unref; + *handlep = ret; ret = drm_vma_node_allow(&obj->vma_node, file_priv->filp); - if (ret) { - drm_gem_handle_delete(file_priv, *handlep); - return ret; - } + if (ret) + goto err_remove; if (dev->driver->gem_open_object) { ret = dev->driver->gem_open_object(obj, file_priv); - if (ret) { - drm_gem_handle_delete(file_priv, *handlep); - return ret; - } + if (ret) + goto err_revoke; } return 0; + +err_revoke: + drm_vma_node_revoke(&obj->vma_node, file_priv->filp); +err_remove: + spin_lock(&file_priv->table_lock); + idr_remove(&file_priv->object_idr, *handlep); + spin_unlock(&file_priv->table_lock); +err_unref: + drm_gem_object_handle_unreference_unlocked(obj); + return ret; } /** diff --git a/drivers/gpu/drm/drm_ioc32.c b/drivers/gpu/drm/drm_ioc32.c index 57676f8d7ecf..a6289752be16 100644 --- a/drivers/gpu/drm/drm_ioc32.c +++ b/drivers/gpu/drm/drm_ioc32.c @@ -1015,6 +1015,7 @@ static int compat_drm_wait_vblank(struct file *file, unsigned int cmd, return 0; } +#if defined(CONFIG_X86) || defined(CONFIG_IA64) typedef struct drm_mode_fb_cmd232 { u32 fb_id; u32 width; @@ -1071,6 +1072,7 @@ static int compat_drm_mode_addfb2(struct file *file, unsigned int cmd, return 0; } +#endif static drm_ioctl_compat_t *drm_compat_ioctls[] = { [DRM_IOCTL_NR(DRM_IOCTL_VERSION32)] = compat_drm_version, @@ -1104,7 +1106,9 @@ static drm_ioctl_compat_t *drm_compat_ioctls[] = { [DRM_IOCTL_NR(DRM_IOCTL_UPDATE_DRAW32)] = compat_drm_update_draw, #endif [DRM_IOCTL_NR(DRM_IOCTL_WAIT_VBLANK32)] = compat_drm_wait_vblank, +#if defined(CONFIG_X86) || defined(CONFIG_IA64) [DRM_IOCTL_NR(DRM_IOCTL_MODE_ADDFB232)] = compat_drm_mode_addfb2, +#endif }; /** diff --git a/drivers/gpu/drm/drm_irq.c b/drivers/gpu/drm/drm_irq.c index 607f493ae801..8090989185b2 100644 --- a/drivers/gpu/drm/drm_irq.c +++ b/drivers/gpu/drm/drm_irq.c @@ -221,6 +221,64 @@ static void drm_update_vblank_count(struct drm_device *dev, unsigned int pipe, diff = (flags & DRM_CALLED_FROM_VBLIRQ) != 0; } + /* + * Within a drm_vblank_pre_modeset - drm_vblank_post_modeset + * interval? If so then vblank irqs keep running and it will likely + * happen that the hardware vblank counter is not trustworthy as it + * might reset at some point in that interval and vblank timestamps + * are not trustworthy either in that interval. Iow. this can result + * in a bogus diff >> 1 which must be avoided as it would cause + * random large forward jumps of the software vblank counter. + */ + if (diff > 1 && (vblank->inmodeset & 0x2)) { + DRM_DEBUG_VBL("clamping vblank bump to 1 on crtc %u: diffr=%u" + " due to pre-modeset.\n", pipe, diff); + diff = 1; + } + + /* + * FIMXE: Need to replace this hack with proper seqlocks. + * + * Restrict the bump of the software vblank counter to a safe maximum + * value of +1 whenever there is the possibility that concurrent readers + * of vblank timestamps could be active at the moment, as the current + * implementation of the timestamp caching and updating is not safe + * against concurrent readers for calls to store_vblank() with a bump + * of anything but +1. A bump != 1 would very likely return corrupted + * timestamps to userspace, because the same slot in the cache could + * be concurrently written by store_vblank() and read by one of those + * readers without the read-retry logic detecting the collision. + * + * Concurrent readers can exist when we are called from the + * drm_vblank_off() or drm_vblank_on() functions and other non-vblank- + * irq callers. However, all those calls to us are happening with the + * vbl_lock locked to prevent drm_vblank_get(), so the vblank refcount + * can't increase while we are executing. Therefore a zero refcount at + * this point is safe for arbitrary counter bumps if we are called + * outside vblank irq, a non-zero count is not 100% safe. Unfortunately + * we must also accept a refcount of 1, as whenever we are called from + * drm_vblank_get() -> drm_vblank_enable() the refcount will be 1 and + * we must let that one pass through in order to not lose vblank counts + * during vblank irq off - which would completely defeat the whole + * point of this routine. + * + * Whenever we are called from vblank irq, we have to assume concurrent + * readers exist or can show up any time during our execution, even if + * the refcount is currently zero, as vblank irqs are usually only + * enabled due to the presence of readers, and because when we are called + * from vblank irq we can't hold the vbl_lock to protect us from sudden + * bumps in vblank refcount. Therefore also restrict bumps to +1 when + * called from vblank irq. + */ + if ((diff > 1) && (atomic_read(&vblank->refcount) > 1 || + (flags & DRM_CALLED_FROM_VBLIRQ))) { + DRM_DEBUG_VBL("clamping vblank bump to 1 on crtc %u: diffr=%u " + "refcount %u, vblirq %u\n", pipe, diff, + atomic_read(&vblank->refcount), + (flags & DRM_CALLED_FROM_VBLIRQ) != 0); + diff = 1; + } + DRM_DEBUG_VBL("updating vblank count on crtc %u:" " current=%u, diff=%u, hw=%u hw_last=%u\n", pipe, vblank->count, diff, cur_vblank, vblank->last); @@ -1313,7 +1371,13 @@ void drm_vblank_off(struct drm_device *dev, unsigned int pipe) spin_lock_irqsave(&dev->event_lock, irqflags); spin_lock(&dev->vbl_lock); - vblank_disable_and_save(dev, pipe); + DRM_DEBUG_VBL("crtc %d, vblank enabled %d, inmodeset %d\n", + pipe, vblank->enabled, vblank->inmodeset); + + /* Avoid redundant vblank disables without previous drm_vblank_on(). */ + if (drm_core_check_feature(dev, DRIVER_ATOMIC) || !vblank->inmodeset) + vblank_disable_and_save(dev, pipe); + wake_up(&vblank->queue); /* @@ -1415,6 +1479,9 @@ void drm_vblank_on(struct drm_device *dev, unsigned int pipe) return; spin_lock_irqsave(&dev->vbl_lock, irqflags); + DRM_DEBUG_VBL("crtc %d, vblank enabled %d, inmodeset %d\n", + pipe, vblank->enabled, vblank->inmodeset); + /* Drop our private "prevent drm_vblank_get" refcount */ if (vblank->inmodeset) { atomic_dec(&vblank->refcount); @@ -1427,8 +1494,7 @@ void drm_vblank_on(struct drm_device *dev, unsigned int pipe) * re-enable interrupts if there are users left, or the * user wishes vblank interrupts to be enabled all the time. */ - if (atomic_read(&vblank->refcount) != 0 || - (!dev->vblank_disable_immediate && drm_vblank_offdelay == 0)) + if (atomic_read(&vblank->refcount) != 0 || drm_vblank_offdelay == 0) WARN_ON(drm_vblank_enable(dev, pipe)); spin_unlock_irqrestore(&dev->vbl_lock, irqflags); } @@ -1523,6 +1589,7 @@ void drm_vblank_post_modeset(struct drm_device *dev, unsigned int pipe) if (vblank->inmodeset) { spin_lock_irqsave(&dev->vbl_lock, irqflags); dev->vblank_disable_allowed = true; + drm_reset_vblank_timestamp(dev, pipe); spin_unlock_irqrestore(&dev->vbl_lock, irqflags); if (vblank->inmodeset & 0x2) diff --git a/drivers/gpu/drm/drm_modes.c b/drivers/gpu/drm/drm_modes.c index cd74a0953f42..39e30abddf08 100644 --- a/drivers/gpu/drm/drm_modes.c +++ b/drivers/gpu/drm/drm_modes.c @@ -1487,6 +1487,8 @@ int drm_mode_convert_umode(struct drm_display_mode *out, if (out->status != MODE_OK) goto out; + drm_mode_set_crtcinfo(out, CRTC_INTERLACE_HALVE_V); + ret = 0; out: diff --git a/drivers/gpu/drm/gma500/cdv_intel_dp.c b/drivers/gpu/drm/gma500/cdv_intel_dp.c index 17cea400ae32..d3de377dc857 100644 --- a/drivers/gpu/drm/gma500/cdv_intel_dp.c +++ b/drivers/gpu/drm/gma500/cdv_intel_dp.c @@ -220,7 +220,7 @@ i2c_dp_aux_prepare_bus(struct i2c_adapter *adapter) * FIXME: This is the old dp aux helper, gma500 is the last driver that needs to * be ported over to the new helper code in drm_dp_helper.c like i915 or radeon. */ -static int __deprecated +static int i2c_dp_aux_add_bus(struct i2c_adapter *adapter) { int error; diff --git a/drivers/gpu/drm/gma500/gem.c b/drivers/gpu/drm/gma500/gem.c index c707fa6fca85..e3bdc8b1c32c 100644 --- a/drivers/gpu/drm/gma500/gem.c +++ b/drivers/gpu/drm/gma500/gem.c @@ -130,7 +130,7 @@ int psb_gem_create(struct drm_file *file, struct drm_device *dev, u64 size, return ret; } /* We have the initial and handle reference but need only one now */ - drm_gem_object_unreference(&r->gem); + drm_gem_object_unreference_unlocked(&r->gem); *handlep = handle; return 0; } diff --git a/drivers/gpu/drm/gma500/mdfld_dsi_pkg_sender.c b/drivers/gpu/drm/gma500/mdfld_dsi_pkg_sender.c index 6b43ae3ffd73..1616af209bfc 100644 --- a/drivers/gpu/drm/gma500/mdfld_dsi_pkg_sender.c +++ b/drivers/gpu/drm/gma500/mdfld_dsi_pkg_sender.c @@ -72,7 +72,7 @@ static const char *const dsi_errors[] = { "RX Prot Violation", "HS Generic Write FIFO Full", "LP Generic Write FIFO Full", - "Generic Read Data Avail" + "Generic Read Data Avail", "Special Packet Sent", "Tearing Effect", }; diff --git a/drivers/gpu/drm/i915/i915_dma.c b/drivers/gpu/drm/i915/i915_dma.c index b4741d121a74..61fcb3b22297 100644 --- a/drivers/gpu/drm/i915/i915_dma.c +++ b/drivers/gpu/drm/i915/i915_dma.c @@ -402,6 +402,8 @@ static int i915_load_modeset_init(struct drm_device *dev) if (ret) goto cleanup_gem_stolen; + intel_setup_gmbus(dev); + /* Important: The output setup functions called by modeset_init need * working irqs for e.g. gmbus and dp aux transfers. */ intel_modeset_init(dev); @@ -451,6 +453,7 @@ cleanup_gem: cleanup_irq: intel_guc_ucode_fini(dev); drm_irq_uninstall(dev); + intel_teardown_gmbus(dev); cleanup_gem_stolen: i915_gem_cleanup_stolen(dev); cleanup_vga_switcheroo: @@ -1028,7 +1031,6 @@ int i915_driver_load(struct drm_device *dev, unsigned long flags) /* Try to make sure MCHBAR is enabled before poking at it */ intel_setup_mchbar(dev); - intel_setup_gmbus(dev); intel_opregion_setup(dev); i915_gem_load(dev); @@ -1099,7 +1101,6 @@ out_gem_unload: if (dev->pdev->msi_enabled) pci_disable_msi(dev->pdev); - intel_teardown_gmbus(dev); intel_teardown_mchbar(dev); pm_qos_remove_request(&dev_priv->pm_qos); destroy_workqueue(dev_priv->gpu_error.hangcheck_wq); @@ -1198,7 +1199,6 @@ int i915_driver_unload(struct drm_device *dev) intel_csr_ucode_fini(dev); - intel_teardown_gmbus(dev); intel_teardown_mchbar(dev); destroy_workqueue(dev_priv->hotplug.dp_wq); diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c index 760e0ce4aa26..a6ad938f44a6 100644 --- a/drivers/gpu/drm/i915/i915_drv.c +++ b/drivers/gpu/drm/i915/i915_drv.c @@ -531,7 +531,10 @@ void intel_detect_pch(struct drm_device *dev) dev_priv->pch_type = PCH_SPT; DRM_DEBUG_KMS("Found SunrisePoint LP PCH\n"); WARN_ON(!IS_SKYLAKE(dev)); - } else if (id == INTEL_PCH_P2X_DEVICE_ID_TYPE) { + } else if ((id == INTEL_PCH_P2X_DEVICE_ID_TYPE) || + ((id == INTEL_PCH_QEMU_DEVICE_ID_TYPE) && + pch->subsystem_vendor == 0x1af4 && + pch->subsystem_device == 0x1100)) { dev_priv->pch_type = intel_virt_detect_pch(dev); } else continue; diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index f4af19a0d569..d400d6773bbb 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -2614,6 +2614,7 @@ struct drm_i915_cmd_table { #define INTEL_PCH_SPT_DEVICE_ID_TYPE 0xA100 #define INTEL_PCH_SPT_LP_DEVICE_ID_TYPE 0x9D00 #define INTEL_PCH_P2X_DEVICE_ID_TYPE 0x7100 +#define INTEL_PCH_QEMU_DEVICE_ID_TYPE 0x2900 /* qemu q35 has 2918 */ #define INTEL_PCH_TYPE(dev) (__I915__(dev)->pch_type) #define HAS_PCH_SPT(dev) (INTEL_PCH_TYPE(dev) == PCH_SPT) @@ -3312,6 +3313,9 @@ static inline bool intel_gmbus_is_forced_bit(struct i2c_adapter *adapter) } extern void intel_i2c_reset(struct drm_device *dev); +/* intel_bios.c */ +bool intel_bios_is_port_present(struct drm_i915_private *dev_priv, enum port port); + /* intel_opregion.c */ #ifdef CONFIG_ACPI extern int intel_opregion_setup(struct drm_device *dev); diff --git a/drivers/gpu/drm/i915/i915_gem_context.c b/drivers/gpu/drm/i915/i915_gem_context.c index 02ceb7a4b481..0433d25f9d23 100644 --- a/drivers/gpu/drm/i915/i915_gem_context.c +++ b/drivers/gpu/drm/i915/i915_gem_context.c @@ -340,6 +340,10 @@ void i915_gem_context_reset(struct drm_device *dev) i915_gem_context_unreference(lctx); ring->last_context = NULL; } + + /* Force the GPU state to be reinitialised on enabling */ + if (ring->default_context) + ring->default_context->legacy_hw_ctx.initialized = false; } } @@ -708,7 +712,7 @@ static int do_switch(struct drm_i915_gem_request *req) if (ret) goto unpin_out; - if (!to->legacy_hw_ctx.initialized) { + if (!to->legacy_hw_ctx.initialized || i915_gem_context_is_default(to)) { hw_flags |= MI_RESTORE_INHIBIT; /* NB: If we inhibit the restore, the context is not allowed to * die because future work may end up depending on valid address diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c index 86c7500454b4..b37fe0df743e 100644 --- a/drivers/gpu/drm/i915/i915_gem_gtt.c +++ b/drivers/gpu/drm/i915/i915_gem_gtt.c @@ -2747,6 +2747,7 @@ void i915_global_gtt_cleanup(struct drm_device *dev) struct i915_hw_ppgtt *ppgtt = dev_priv->mm.aliasing_ppgtt; ppgtt->base.cleanup(&ppgtt->base); + kfree(ppgtt); } if (drm_mm_initialized(&vm->mm)) { diff --git a/drivers/gpu/drm/i915/i915_gem_shrinker.c b/drivers/gpu/drm/i915/i915_gem_shrinker.c index f7df54a8ee2b..c0a96f1ee18e 100644 --- a/drivers/gpu/drm/i915/i915_gem_shrinker.c +++ b/drivers/gpu/drm/i915/i915_gem_shrinker.c @@ -39,7 +39,7 @@ 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_irq.c b/drivers/gpu/drm/i915/i915_irq.c index 0d228f909dcb..0f42a2782afc 100644 --- a/drivers/gpu/drm/i915/i915_irq.c +++ b/drivers/gpu/drm/i915/i915_irq.c @@ -2354,9 +2354,13 @@ static irqreturn_t gen8_irq_handler(int irq, void *arg) spt_irq_handler(dev, pch_iir); else cpt_irq_handler(dev, pch_iir); - } else - DRM_ERROR("The master control interrupt lied (SDE)!\n"); - + } else { + /* + * Like on previous PCH there seems to be something + * fishy going on with forwarding PCH interrupts. + */ + DRM_DEBUG_DRIVER("The master control interrupt lied (SDE)!\n"); + } } I915_WRITE_FW(GEN8_MASTER_IRQ, GEN8_MASTER_IRQ_CONTROL); diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index bc7b8faba84d..cace154bbdc0 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -2838,7 +2838,14 @@ enum skl_disp_power_wells { #define GEN6_RP_STATE_CAP (MCHBAR_MIRROR_BASE_SNB + 0x5998) #define BXT_RP_STATE_CAP 0x138170 -#define INTERVAL_1_28_US(us) (((us) * 100) >> 7) +/* + * Make these a multiple of magic 25 to avoid SNB (eg. Dell XPS + * 8300) freezing up around GPU hangs. Looks as if even + * scheduling/timer interrupts start misbehaving if the RPS + * EI/thresholds are "bad", leading to a very sluggish or even + * frozen machine. + */ +#define INTERVAL_1_28_US(us) roundup(((us) * 100) >> 7, 25) #define INTERVAL_1_33_US(us) (((us) * 3) >> 2) #define INTERVAL_0_833_US(us) (((us) * 6) / 5) #define GT_INTERVAL_FROM_US(dev_priv, us) (IS_GEN9(dev_priv) ? \ @@ -3233,19 +3240,20 @@ enum skl_disp_power_wells { #define PORT_HOTPLUG_STAT (dev_priv->info.display_mmio_offset + 0x61114) /* - * HDMI/DP bits are gen4+ + * HDMI/DP bits are g4x+ * * WARNING: Bspec for hpd status bits on gen4 seems to be completely confused. * Please check the detailed lore in the commit message for for experimental * evidence. */ -#define PORTD_HOTPLUG_LIVE_STATUS_G4X (1 << 29) +/* Bspec says GM45 should match G4X/VLV/CHV, but reality disagrees */ +#define PORTD_HOTPLUG_LIVE_STATUS_GM45 (1 << 29) +#define PORTC_HOTPLUG_LIVE_STATUS_GM45 (1 << 28) +#define PORTB_HOTPLUG_LIVE_STATUS_GM45 (1 << 27) +/* G4X/VLV/CHV DP/HDMI bits again match Bspec */ +#define PORTD_HOTPLUG_LIVE_STATUS_G4X (1 << 27) #define PORTC_HOTPLUG_LIVE_STATUS_G4X (1 << 28) -#define PORTB_HOTPLUG_LIVE_STATUS_G4X (1 << 27) -/* VLV DP/HDMI bits again match Bspec */ -#define PORTD_HOTPLUG_LIVE_STATUS_VLV (1 << 27) -#define PORTC_HOTPLUG_LIVE_STATUS_VLV (1 << 28) -#define PORTB_HOTPLUG_LIVE_STATUS_VLV (1 << 29) +#define PORTB_HOTPLUG_LIVE_STATUS_G4X (1 << 29) #define PORTD_HOTPLUG_INT_STATUS (3 << 21) #define PORTD_HOTPLUG_INT_LONG_PULSE (2 << 21) #define PORTD_HOTPLUG_INT_SHORT_PULSE (1 << 21) @@ -7350,6 +7358,8 @@ enum skl_disp_power_wells { #define TRANS_CLK_SEL_DISABLED (0x0<<29) #define TRANS_CLK_SEL_PORT(x) (((x)+1)<<29) +#define CDCLK_FREQ 0x46200 + #define TRANSA_MSA_MISC 0x60410 #define TRANSB_MSA_MISC 0x61410 #define TRANSC_MSA_MISC 0x62410 diff --git a/drivers/gpu/drm/i915/intel_bios.c b/drivers/gpu/drm/i915/intel_bios.c index ce82f9c7df24..d14bdc537587 100644 --- a/drivers/gpu/drm/i915/intel_bios.c +++ b/drivers/gpu/drm/i915/intel_bios.c @@ -1351,3 +1351,42 @@ intel_parse_bios(struct drm_device *dev) return 0; } + +/** + * intel_bios_is_port_present - is the specified digital port present + * @dev_priv: i915 device instance + * @port: port to check + * + * Return true if the device in %port is present. + */ +bool intel_bios_is_port_present(struct drm_i915_private *dev_priv, enum port port) +{ + static const struct { + u16 dp, hdmi; + } port_mapping[] = { + [PORT_B] = { DVO_PORT_DPB, DVO_PORT_HDMIB, }, + [PORT_C] = { DVO_PORT_DPC, DVO_PORT_HDMIC, }, + [PORT_D] = { DVO_PORT_DPD, DVO_PORT_HDMID, }, + [PORT_E] = { DVO_PORT_DPE, DVO_PORT_HDMIE, }, + }; + int i; + + /* FIXME maybe deal with port A as well? */ + if (WARN_ON(port == PORT_A) || port >= ARRAY_SIZE(port_mapping)) + return false; + + if (!dev_priv->vbt.child_dev_num) + return false; + + for (i = 0; i < dev_priv->vbt.child_dev_num; i++) { + const union child_device_config *p_child = + &dev_priv->vbt.child_dev[i]; + if ((p_child->common.dvo_port == port_mapping[port].dp || + p_child->common.dvo_port == port_mapping[port].hdmi) && + (p_child->common.device_type & (DEVICE_TYPE_TMDS_DVI_SIGNALING | + DEVICE_TYPE_DISPLAYPORT_OUTPUT))) + return true; + } + + return false; +} diff --git a/drivers/gpu/drm/i915/intel_crt.c b/drivers/gpu/drm/i915/intel_crt.c index 6a2c76e367a5..97d1ed20418b 100644 --- a/drivers/gpu/drm/i915/intel_crt.c +++ b/drivers/gpu/drm/i915/intel_crt.c @@ -248,8 +248,14 @@ static bool intel_crt_compute_config(struct intel_encoder *encoder, pipe_config->has_pch_encoder = true; /* LPT FDI RX only supports 8bpc. */ - if (HAS_PCH_LPT(dev)) + if (HAS_PCH_LPT(dev)) { + if (pipe_config->bw_constrained && pipe_config->pipe_bpp < 24) { + DRM_DEBUG_KMS("LPT only supports 24bpp\n"); + return false; + } + pipe_config->pipe_bpp = 24; + } /* FDI must always be 2.7 GHz */ if (HAS_DDI(dev)) { diff --git a/drivers/gpu/drm/i915/intel_csr.c b/drivers/gpu/drm/i915/intel_csr.c index 9e530a739354..fc28c512ece3 100644 --- a/drivers/gpu/drm/i915/intel_csr.c +++ b/drivers/gpu/drm/i915/intel_csr.c @@ -180,7 +180,8 @@ struct stepping_info { static const struct stepping_info skl_stepping_info[] = { {'A', '0'}, {'B', '0'}, {'C', '0'}, {'D', '0'}, {'E', '0'}, {'F', '0'}, - {'G', '0'}, {'H', '0'}, {'I', '0'} + {'G', '0'}, {'H', '0'}, {'I', '0'}, + {'J', '0'}, {'K', '0'} }; static struct stepping_info bxt_stepping_info[] = { diff --git a/drivers/gpu/drm/i915/intel_ddi.c b/drivers/gpu/drm/i915/intel_ddi.c index a6752a61d99f..3c6b07683bd9 100644 --- a/drivers/gpu/drm/i915/intel_ddi.c +++ b/drivers/gpu/drm/i915/intel_ddi.c @@ -464,9 +464,17 @@ static void intel_prepare_ddi_buffers(struct drm_device *dev, enum port port, } else if (IS_BROADWELL(dev)) { ddi_translations_fdi = bdw_ddi_translations_fdi; ddi_translations_dp = bdw_ddi_translations_dp; - ddi_translations_edp = bdw_ddi_translations_edp; + + if (dev_priv->edp_low_vswing) { + ddi_translations_edp = bdw_ddi_translations_edp; + n_edp_entries = ARRAY_SIZE(bdw_ddi_translations_edp); + } else { + ddi_translations_edp = bdw_ddi_translations_dp; + n_edp_entries = ARRAY_SIZE(bdw_ddi_translations_dp); + } + ddi_translations_hdmi = bdw_ddi_translations_hdmi; - n_edp_entries = ARRAY_SIZE(bdw_ddi_translations_edp); + n_dp_entries = ARRAY_SIZE(bdw_ddi_translations_dp); n_hdmi_entries = ARRAY_SIZE(bdw_ddi_translations_hdmi); hdmi_default_entry = 7; @@ -1582,7 +1590,8 @@ skl_ddi_pll_select(struct intel_crtc *intel_crtc, DPLL_CFGCR2_KDIV(wrpll_params.kdiv) | DPLL_CFGCR2_PDIV(wrpll_params.pdiv) | wrpll_params.central_freq; - } else if (intel_encoder->type == INTEL_OUTPUT_DISPLAYPORT) { + } else if (intel_encoder->type == INTEL_OUTPUT_DISPLAYPORT || + intel_encoder->type == INTEL_OUTPUT_DP_MST) { switch (crtc_state->port_clock / 2) { case 81000: ctrl1 |= DPLL_CTRL1_LINK_RATE(DPLL_CTRL1_LINK_RATE_810, 0); @@ -3187,12 +3196,6 @@ void intel_ddi_get_config(struct intel_encoder *encoder, intel_ddi_clock_get(encoder, pipe_config); } -static void intel_ddi_destroy(struct drm_encoder *encoder) -{ - /* HDMI has nothing special to destroy, so we can go with this. */ - intel_dp_encoder_destroy(encoder); -} - static bool intel_ddi_compute_config(struct intel_encoder *encoder, struct intel_crtc_state *pipe_config) { @@ -3211,7 +3214,8 @@ static bool intel_ddi_compute_config(struct intel_encoder *encoder, } static const struct drm_encoder_funcs intel_ddi_funcs = { - .destroy = intel_ddi_destroy, + .reset = intel_dp_encoder_reset, + .destroy = intel_dp_encoder_destroy, }; static struct intel_connector * @@ -3283,6 +3287,7 @@ void intel_ddi_init(struct drm_device *dev, enum port port) intel_encoder->post_disable = intel_ddi_post_disable; intel_encoder->get_hw_state = intel_ddi_get_hw_state; intel_encoder->get_config = intel_ddi_get_config; + intel_encoder->suspend = intel_dp_encoder_suspend; intel_dig_port->port = port; intel_dig_port->saved_port_bits = I915_READ(DDI_BUF_CTL(port)) & diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c index 32cf97346978..909d1d71d130 100644 --- a/drivers/gpu/drm/i915/intel_display.c +++ b/drivers/gpu/drm/i915/intel_display.c @@ -2950,13 +2950,13 @@ u32 intel_fb_stride_alignment(struct drm_device *dev, uint64_t fb_modifier, } } -unsigned long intel_plane_obj_offset(struct intel_plane *intel_plane, - struct drm_i915_gem_object *obj, - unsigned int plane) +u32 intel_plane_obj_offset(struct intel_plane *intel_plane, + struct drm_i915_gem_object *obj, + unsigned int plane) { const struct i915_ggtt_view *view = &i915_ggtt_view_normal; struct i915_vma *vma; - unsigned char *offset; + u64 offset; if (intel_rotation_90_or_270(intel_plane->base.state->rotation)) view = &i915_ggtt_view_rotated; @@ -2966,14 +2966,16 @@ unsigned long intel_plane_obj_offset(struct intel_plane *intel_plane, view->type)) return -1; - offset = (unsigned char *)vma->node.start; + offset = vma->node.start; if (plane == 1) { offset += vma->ggtt_view.rotation_info.uv_start_page * PAGE_SIZE; } - return (unsigned long)offset; + WARN_ON(upper_32_bits(offset)); + + return lower_32_bits(offset); } static void skl_detach_scaler(struct intel_crtc *intel_crtc, int id) @@ -3099,7 +3101,7 @@ static void skylake_update_primary_plane(struct drm_crtc *crtc, u32 tile_height, plane_offset, plane_size; unsigned int rotation; int x_offset, y_offset; - unsigned long surf_addr; + u32 surf_addr; struct intel_crtc_state *crtc_state = intel_crtc->config; struct intel_plane_state *plane_state; int src_x = 0, src_y = 0, src_w = 0, src_h = 0; @@ -4447,7 +4449,7 @@ int skl_update_scaler_crtc(struct intel_crtc_state *state) intel_crtc->base.base.id, intel_crtc->pipe, SKL_CRTC_INDEX); return skl_update_scaler(state, !state->base.active, SKL_CRTC_INDEX, - &state->scaler_state.scaler_id, DRM_ROTATE_0, + &state->scaler_state.scaler_id, BIT(DRM_ROTATE_0), state->pipe_src_w, state->pipe_src_h, adjusted_mode->crtc_hdisplay, adjusted_mode->crtc_vdisplay); } @@ -8228,12 +8230,14 @@ static void ironlake_init_pch_refclk(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; struct intel_encoder *encoder; + int i; u32 val, final; bool has_lvds = false; bool has_cpu_edp = false; bool has_panel = false; bool has_ck505 = false; bool can_ssc = false; + bool using_ssc_source = false; /* We need to take the global config into account */ for_each_intel_encoder(dev, encoder) { @@ -8260,8 +8264,22 @@ static void ironlake_init_pch_refclk(struct drm_device *dev) can_ssc = true; } - DRM_DEBUG_KMS("has_panel %d has_lvds %d has_ck505 %d\n", - has_panel, has_lvds, has_ck505); + /* Check if any DPLLs are using the SSC source */ + for (i = 0; i < dev_priv->num_shared_dpll; i++) { + u32 temp = I915_READ(PCH_DPLL(i)); + + if (!(temp & DPLL_VCO_ENABLE)) + continue; + + if ((temp & PLL_REF_INPUT_MASK) == + PLLB_REF_INPUT_SPREADSPECTRUMIN) { + using_ssc_source = true; + break; + } + } + + DRM_DEBUG_KMS("has_panel %d has_lvds %d has_ck505 %d using_ssc_source %d\n", + has_panel, has_lvds, has_ck505, using_ssc_source); /* Ironlake: try to setup display ref clock before DPLL * enabling. This is only under driver's control after @@ -8298,9 +8316,9 @@ static void ironlake_init_pch_refclk(struct drm_device *dev) final |= DREF_CPU_SOURCE_OUTPUT_NONSPREAD; } else final |= DREF_CPU_SOURCE_OUTPUT_DISABLE; - } else { - final |= DREF_SSC_SOURCE_DISABLE; - final |= DREF_CPU_SOURCE_OUTPUT_DISABLE; + } else if (using_ssc_source) { + final |= DREF_SSC_SOURCE_ENABLE; + final |= DREF_SSC1_ENABLE; } if (final == val) @@ -8346,7 +8364,7 @@ static void ironlake_init_pch_refclk(struct drm_device *dev) POSTING_READ(PCH_DREF_CONTROL); udelay(200); } else { - DRM_DEBUG_KMS("Disabling SSC entirely\n"); + DRM_DEBUG_KMS("Disabling CPU source output\n"); val &= ~DREF_CPU_SOURCE_OUTPUT_MASK; @@ -8357,16 +8375,20 @@ static void ironlake_init_pch_refclk(struct drm_device *dev) POSTING_READ(PCH_DREF_CONTROL); udelay(200); - /* Turn off the SSC source */ - val &= ~DREF_SSC_SOURCE_MASK; - val |= DREF_SSC_SOURCE_DISABLE; + if (!using_ssc_source) { + DRM_DEBUG_KMS("Disabling SSC source\n"); - /* Turn off SSC1 */ - val &= ~DREF_SSC1_ENABLE; + /* Turn off the SSC source */ + val &= ~DREF_SSC_SOURCE_MASK; + val |= DREF_SSC_SOURCE_DISABLE; - I915_WRITE(PCH_DREF_CONTROL, val); - POSTING_READ(PCH_DREF_CONTROL); - udelay(200); + /* Turn off SSC1 */ + val &= ~DREF_SSC1_ENABLE; + + I915_WRITE(PCH_DREF_CONTROL, val); + POSTING_READ(PCH_DREF_CONTROL); + udelay(200); + } } BUG_ON(val != final); @@ -9669,6 +9691,8 @@ static void broadwell_set_cdclk(struct drm_device *dev, int cdclk) sandybridge_pcode_write(dev_priv, HSW_PCODE_DE_WRITE_FREQ_REQ, data); mutex_unlock(&dev_priv->rps.hw_lock); + I915_WRITE(CDCLK_FREQ, DIV_ROUND_CLOSEST(cdclk, 1000) - 1); + intel_update_cdclk(dev); WARN(cdclk != dev_priv->cdclk_freq, @@ -13537,11 +13561,12 @@ intel_check_primary_plane(struct drm_plane *plane, int max_scale = DRM_PLANE_HELPER_NO_SCALING; bool can_position = false; - /* use scaler when colorkey is not required */ - if (INTEL_INFO(plane->dev)->gen >= 9 && - state->ckey.flags == I915_SET_COLORKEY_NONE) { - min_scale = 1; - max_scale = skl_max_scale(to_intel_crtc(crtc), crtc_state); + if (INTEL_INFO(plane->dev)->gen >= 9) { + /* use scaler when colorkey is not required */ + if (state->ckey.flags == I915_SET_COLORKEY_NONE) { + min_scale = 1; + max_scale = skl_max_scale(to_intel_crtc(crtc), crtc_state); + } can_position = true; } @@ -14137,6 +14162,8 @@ static void intel_setup_outputs(struct drm_device *dev) if (I915_READ(PCH_DP_D) & DP_DETECTED) intel_dp_init(dev, PCH_DP_D, PORT_D); } else if (IS_VALLEYVIEW(dev)) { + bool has_edp, has_port; + /* * The DP_DETECTED bit is the latched state of the DDC * SDA pin at boot. However since eDP doesn't require DDC @@ -14145,27 +14172,37 @@ static void intel_setup_outputs(struct drm_device *dev) * Thus we can't rely on the DP_DETECTED bit alone to detect * eDP ports. Consult the VBT as well as DP_DETECTED to * detect eDP ports. + * + * Sadly the straps seem to be missing sometimes even for HDMI + * ports (eg. on Voyo V3 - CHT x7-Z8700), so check both strap + * and VBT for the presence of the port. Additionally we can't + * trust the port type the VBT declares as we've seen at least + * HDMI ports that the VBT claim are DP or eDP. */ - if (I915_READ(VLV_HDMIB) & SDVO_DETECTED && - !intel_dp_is_edp(dev, PORT_B)) + has_edp = intel_dp_is_edp(dev, PORT_B); + has_port = intel_bios_is_port_present(dev_priv, PORT_B); + if (I915_READ(VLV_DP_B) & DP_DETECTED || has_port) + has_edp &= intel_dp_init(dev, VLV_DP_B, PORT_B); + if ((I915_READ(VLV_HDMIB) & SDVO_DETECTED || has_port) && !has_edp) intel_hdmi_init(dev, VLV_HDMIB, PORT_B); - if (I915_READ(VLV_DP_B) & DP_DETECTED || - intel_dp_is_edp(dev, PORT_B)) - intel_dp_init(dev, VLV_DP_B, PORT_B); - if (I915_READ(VLV_HDMIC) & SDVO_DETECTED && - !intel_dp_is_edp(dev, PORT_C)) + has_edp = intel_dp_is_edp(dev, PORT_C); + has_port = intel_bios_is_port_present(dev_priv, PORT_C); + if (I915_READ(VLV_DP_C) & DP_DETECTED || has_port) + has_edp &= intel_dp_init(dev, VLV_DP_C, PORT_C); + if ((I915_READ(VLV_HDMIC) & SDVO_DETECTED || has_port) && !has_edp) intel_hdmi_init(dev, VLV_HDMIC, PORT_C); - if (I915_READ(VLV_DP_C) & DP_DETECTED || - intel_dp_is_edp(dev, PORT_C)) - intel_dp_init(dev, VLV_DP_C, PORT_C); if (IS_CHERRYVIEW(dev)) { - /* eDP not supported on port D, so don't check VBT */ - if (I915_READ(CHV_HDMID) & SDVO_DETECTED) - intel_hdmi_init(dev, CHV_HDMID, PORT_D); - if (I915_READ(CHV_DP_D) & DP_DETECTED) + /* + * eDP not supported on port D, + * so no need to worry about it + */ + has_port = intel_bios_is_port_present(dev_priv, PORT_D); + if (I915_READ(CHV_DP_D) & DP_DETECTED || has_port) intel_dp_init(dev, CHV_DP_D, PORT_D); + if (I915_READ(CHV_HDMID) & SDVO_DETECTED || has_port) + intel_hdmi_init(dev, CHV_HDMID, PORT_D); } intel_dsi_init(dev); @@ -15565,6 +15602,8 @@ void intel_modeset_cleanup(struct drm_device *dev) mutex_lock(&dev->struct_mutex); intel_cleanup_gt_powersave(dev); mutex_unlock(&dev->struct_mutex); + + intel_teardown_gmbus(dev); } /* diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c index 78b8ec84d576..ebbd23407a80 100644 --- a/drivers/gpu/drm/i915/intel_dp.c +++ b/drivers/gpu/drm/i915/intel_dp.c @@ -3628,8 +3628,7 @@ static bool intel_dp_reset_link_train(struct intel_dp *intel_dp, uint32_t *DP, uint8_t dp_train_pat) { - if (!intel_dp->train_set_valid) - memset(intel_dp->train_set, 0, sizeof(intel_dp->train_set)); + memset(intel_dp->train_set, 0, sizeof(intel_dp->train_set)); intel_dp_set_signal_levels(intel_dp, DP); return intel_dp_set_link_train(intel_dp, DP, dp_train_pat); } @@ -3746,22 +3745,6 @@ intel_dp_link_training_clock_recovery(struct intel_dp *intel_dp) break; } - /* - * if we used previously trained voltage and pre-emphasis values - * and we don't get clock recovery, reset link training values - */ - if (intel_dp->train_set_valid) { - DRM_DEBUG_KMS("clock recovery not ok, reset"); - /* clear the flag as we are not reusing train set */ - intel_dp->train_set_valid = false; - if (!intel_dp_reset_link_train(intel_dp, &DP, - DP_TRAINING_PATTERN_1 | - DP_LINK_SCRAMBLING_DISABLE)) { - DRM_ERROR("failed to enable link training\n"); - return; - } - continue; - } /* Check to see if we've tried the max voltage */ for (i = 0; i < intel_dp->lane_count; i++) @@ -3854,7 +3837,6 @@ intel_dp_link_training_channel_equalization(struct intel_dp *intel_dp) /* Make sure clock is still ok */ if (!drm_dp_clock_recovery_ok(link_status, intel_dp->lane_count)) { - intel_dp->train_set_valid = false; intel_dp_link_training_clock_recovery(intel_dp); intel_dp_set_link_train(intel_dp, &DP, training_pattern | @@ -3871,7 +3853,6 @@ intel_dp_link_training_channel_equalization(struct intel_dp *intel_dp) /* Try 5 times, then try clock recovery if that fails */ if (tries > 5) { - intel_dp->train_set_valid = false; intel_dp_link_training_clock_recovery(intel_dp); intel_dp_set_link_train(intel_dp, &DP, training_pattern | @@ -3893,10 +3874,8 @@ intel_dp_link_training_channel_equalization(struct intel_dp *intel_dp) intel_dp->DP = DP; - if (channel_eq) { - intel_dp->train_set_valid = true; + if (channel_eq) DRM_DEBUG_KMS("Channel EQ done. DP Training successful\n"); - } } void intel_dp_stop_link_train(struct intel_dp *intel_dp) @@ -4613,20 +4592,20 @@ static bool g4x_digital_port_connected(struct drm_i915_private *dev_priv, return I915_READ(PORT_HOTPLUG_STAT) & bit; } -static bool vlv_digital_port_connected(struct drm_i915_private *dev_priv, - struct intel_digital_port *port) +static bool gm45_digital_port_connected(struct drm_i915_private *dev_priv, + struct intel_digital_port *port) { u32 bit; switch (port->port) { case PORT_B: - bit = PORTB_HOTPLUG_LIVE_STATUS_VLV; + bit = PORTB_HOTPLUG_LIVE_STATUS_GM45; break; case PORT_C: - bit = PORTC_HOTPLUG_LIVE_STATUS_VLV; + bit = PORTC_HOTPLUG_LIVE_STATUS_GM45; break; case PORT_D: - bit = PORTD_HOTPLUG_LIVE_STATUS_VLV; + bit = PORTD_HOTPLUG_LIVE_STATUS_GM45; break; default: MISSING_CASE(port->port); @@ -4678,8 +4657,8 @@ bool intel_digital_port_connected(struct drm_i915_private *dev_priv, return cpt_digital_port_connected(dev_priv, port); else if (IS_BROXTON(dev_priv)) return bxt_digital_port_connected(dev_priv, port); - else if (IS_VALLEYVIEW(dev_priv)) - return vlv_digital_port_connected(dev_priv, port); + else if (IS_GM45(dev_priv)) + return gm45_digital_port_connected(dev_priv, port); else return g4x_digital_port_connected(dev_priv, port); } @@ -5035,7 +5014,7 @@ void intel_dp_encoder_destroy(struct drm_encoder *encoder) kfree(intel_dig_port); } -static void intel_dp_encoder_suspend(struct intel_encoder *intel_encoder) +void intel_dp_encoder_suspend(struct intel_encoder *intel_encoder) { struct intel_dp *intel_dp = enc_to_intel_dp(&intel_encoder->base); @@ -5077,15 +5056,17 @@ static void intel_edp_panel_vdd_sanitize(struct intel_dp *intel_dp) edp_panel_vdd_schedule_off(intel_dp); } -static void intel_dp_encoder_reset(struct drm_encoder *encoder) +void intel_dp_encoder_reset(struct drm_encoder *encoder) { - struct intel_dp *intel_dp; + struct drm_i915_private *dev_priv = to_i915(encoder->dev); + struct intel_dp *intel_dp = enc_to_intel_dp(encoder); + + if (!HAS_DDI(dev_priv)) + intel_dp->DP = I915_READ(intel_dp->output_reg); if (to_intel_encoder(encoder)->type != INTEL_OUTPUT_EDP) return; - intel_dp = enc_to_intel_dp(encoder); - pps_lock(intel_dp); /* @@ -5157,9 +5138,6 @@ intel_dp_hpd_pulse(struct intel_digital_port *intel_dig_port, bool long_hpd) intel_display_power_get(dev_priv, power_domain); if (long_hpd) { - /* indicate that we need to restart link training */ - intel_dp->train_set_valid = false; - if (!intel_digital_port_connected(dev_priv, intel_dig_port)) goto mst_fail; @@ -6135,8 +6113,9 @@ intel_dp_init_connector(struct intel_digital_port *intel_dig_port, return true; } -void -intel_dp_init(struct drm_device *dev, int output_reg, enum port port) +bool intel_dp_init(struct drm_device *dev, + int output_reg, + enum port port) { struct drm_i915_private *dev_priv = dev->dev_private; struct intel_digital_port *intel_dig_port; @@ -6146,7 +6125,7 @@ intel_dp_init(struct drm_device *dev, int output_reg, enum port port) intel_dig_port = kzalloc(sizeof(*intel_dig_port), GFP_KERNEL); if (!intel_dig_port) - return; + return false; intel_connector = intel_connector_alloc(); if (!intel_connector) @@ -6201,15 +6180,14 @@ intel_dp_init(struct drm_device *dev, int output_reg, enum port port) if (!intel_dp_init_connector(intel_dig_port, intel_connector)) goto err_init_connector; - return; + return true; err_init_connector: drm_encoder_cleanup(encoder); kfree(intel_connector); err_connector_alloc: kfree(intel_dig_port); - - return; + return false; } void intel_dp_mst_suspend(struct drm_device *dev) diff --git a/drivers/gpu/drm/i915/intel_dp_mst.c b/drivers/gpu/drm/i915/intel_dp_mst.c index 0639275fc471..06bd9257acdc 100644 --- a/drivers/gpu/drm/i915/intel_dp_mst.c +++ b/drivers/gpu/drm/i915/intel_dp_mst.c @@ -477,6 +477,8 @@ static void intel_dp_destroy_mst_connector(struct drm_dp_mst_topology_mgr *mgr, struct intel_connector *intel_connector = to_intel_connector(connector); struct drm_device *dev = connector->dev; + intel_connector->unregister(intel_connector); + /* need to nuke the connector */ drm_modeset_lock_all(dev); if (connector->state->crtc) { @@ -490,11 +492,7 @@ static void intel_dp_destroy_mst_connector(struct drm_dp_mst_topology_mgr *mgr, WARN(ret, "Disabling mst crtc failed with %i\n", ret); } - drm_modeset_unlock_all(dev); - intel_connector->unregister(intel_connector); - - drm_modeset_lock_all(dev); intel_connector_remove_from_fbdev(intel_connector); drm_connector_cleanup(connector); drm_modeset_unlock_all(dev); diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h index 0d00f07b7163..41442e619595 100644 --- a/drivers/gpu/drm/i915/intel_drv.h +++ b/drivers/gpu/drm/i915/intel_drv.h @@ -783,7 +783,6 @@ struct intel_dp { bool has_aux_irq, int send_bytes, uint32_t aux_clock_divider); - bool train_set_valid; /* Displayport compliance testing */ unsigned long compliance_test_type; @@ -1178,9 +1177,9 @@ void intel_modeset_preclose(struct drm_device *dev, struct drm_file *file); int skl_update_scaler_crtc(struct intel_crtc_state *crtc_state); int skl_max_scale(struct intel_crtc *crtc, struct intel_crtc_state *crtc_state); -unsigned long intel_plane_obj_offset(struct intel_plane *intel_plane, - struct drm_i915_gem_object *obj, - unsigned int plane); +u32 intel_plane_obj_offset(struct intel_plane *intel_plane, + struct drm_i915_gem_object *obj, + unsigned int plane); u32 skl_plane_ctl_format(uint32_t pixel_format); u32 skl_plane_ctl_tiling(uint64_t fb_modifier); @@ -1196,7 +1195,7 @@ void intel_csr_ucode_fini(struct drm_device *dev); void assert_csr_loaded(struct drm_i915_private *dev_priv); /* intel_dp.c */ -void intel_dp_init(struct drm_device *dev, int output_reg, enum port port); +bool intel_dp_init(struct drm_device *dev, int output_reg, enum port port); bool intel_dp_init_connector(struct intel_digital_port *intel_dig_port, struct intel_connector *intel_connector); void intel_dp_set_link_params(struct intel_dp *intel_dp, @@ -1204,6 +1203,8 @@ void intel_dp_set_link_params(struct intel_dp *intel_dp, void intel_dp_start_link_train(struct intel_dp *intel_dp); void intel_dp_stop_link_train(struct intel_dp *intel_dp); void intel_dp_sink_dpms(struct intel_dp *intel_dp, int mode); +void intel_dp_encoder_reset(struct drm_encoder *encoder); +void intel_dp_encoder_suspend(struct intel_encoder *intel_encoder); void intel_dp_encoder_destroy(struct drm_encoder *encoder); int intel_dp_sink_crc(struct intel_dp *intel_dp, u8 *crc); bool intel_dp_compute_config(struct intel_encoder *encoder, diff --git a/drivers/gpu/drm/i915/intel_dsi_panel_vbt.c b/drivers/gpu/drm/i915/intel_dsi_panel_vbt.c index a5e99ac305da..a8912aecc31f 100644 --- a/drivers/gpu/drm/i915/intel_dsi_panel_vbt.c +++ b/drivers/gpu/drm/i915/intel_dsi_panel_vbt.c @@ -207,7 +207,12 @@ static const u8 *mipi_exec_gpio(struct intel_dsi *intel_dsi, const u8 *data) gpio = *data++; /* pull up/down */ - action = *data++; + action = *data++ & 1; + + if (gpio >= ARRAY_SIZE(gtable)) { + DRM_DEBUG_KMS("unknown gpio %u\n", gpio); + goto out; + } function = gtable[gpio].function_reg; pad = gtable[gpio].pad_reg; @@ -226,6 +231,7 @@ static const u8 *mipi_exec_gpio(struct intel_dsi *intel_dsi, const u8 *data) vlv_gpio_nc_write(dev_priv, pad, val); mutex_unlock(&dev_priv->sb_lock); +out: return data; } diff --git a/drivers/gpu/drm/i915/intel_fbdev.c b/drivers/gpu/drm/i915/intel_fbdev.c index 4fd5fdfef6bd..c0c094d5b822 100644 --- a/drivers/gpu/drm/i915/intel_fbdev.c +++ b/drivers/gpu/drm/i915/intel_fbdev.c @@ -362,12 +362,12 @@ static bool intel_fb_initial_config(struct drm_fb_helper *fb_helper, uint64_t conn_configured = 0, mask; int pass = 0; - save_enabled = kcalloc(dev->mode_config.num_connector, sizeof(bool), + save_enabled = kcalloc(fb_helper->connector_count, sizeof(bool), GFP_KERNEL); if (!save_enabled) return false; - memcpy(save_enabled, enabled, dev->mode_config.num_connector); + memcpy(save_enabled, enabled, fb_helper->connector_count); mask = (1 << fb_helper->connector_count) - 1; retry: for (i = 0; i < fb_helper->connector_count; i++) { @@ -501,7 +501,7 @@ retry: if (fallback) { bail: DRM_DEBUG_KMS("Not using firmware configuration\n"); - memcpy(enabled, save_enabled, dev->mode_config.num_connector); + memcpy(enabled, save_enabled, fb_helper->connector_count); kfree(save_enabled); return false; } diff --git a/drivers/gpu/drm/i915/intel_hdmi.c b/drivers/gpu/drm/i915/intel_hdmi.c index e6c035b0fc1c..dff69fef47e0 100644 --- a/drivers/gpu/drm/i915/intel_hdmi.c +++ b/drivers/gpu/drm/i915/intel_hdmi.c @@ -1388,8 +1388,16 @@ intel_hdmi_detect(struct drm_connector *connector, bool force) hdmi_to_dig_port(intel_hdmi)); } - if (!live_status) - DRM_DEBUG_KMS("Live status not up!"); + if (!live_status) { + DRM_DEBUG_KMS("HDMI live status down\n"); + /* + * Live status register is not reliable on all intel platforms. + * So consider live_status only for certain platforms, for + * others, read EDID to determine presence of sink. + */ + if (INTEL_INFO(dev_priv)->gen < 7 || IS_IVYBRIDGE(dev_priv)) + live_status = true; + } intel_hdmi_unset_edid(connector); @@ -2022,6 +2030,9 @@ void intel_hdmi_init_connector(struct intel_digital_port *intel_dig_port, enum port port = intel_dig_port->port; uint8_t alternate_ddc_pin; + DRM_DEBUG_KMS("Adding HDMI connector on port %c\n", + port_name(port)); + drm_connector_init(dev, connector, &intel_hdmi_connector_funcs, DRM_MODE_CONNECTOR_HDMIA); drm_connector_helper_add(connector, &intel_hdmi_connector_helper_funcs); diff --git a/drivers/gpu/drm/i915/intel_hotplug.c b/drivers/gpu/drm/i915/intel_hotplug.c index b17785719598..d7a6437d9da2 100644 --- a/drivers/gpu/drm/i915/intel_hotplug.c +++ b/drivers/gpu/drm/i915/intel_hotplug.c @@ -468,9 +468,14 @@ void intel_hpd_init(struct drm_i915_private *dev_priv) list_for_each_entry(connector, &mode_config->connector_list, head) { struct intel_connector *intel_connector = to_intel_connector(connector); connector->polled = intel_connector->polled; - if (connector->encoder && !connector->polled && I915_HAS_HOTPLUG(dev) && intel_connector->encoder->hpd_pin > HPD_NONE) - connector->polled = DRM_CONNECTOR_POLL_HPD; + + /* MST has a dynamic intel_connector->encoder and it's reprobing + * is all handled by the MST helpers. */ if (intel_connector->mst_port) + continue; + + if (!connector->polled && I915_HAS_HOTPLUG(dev) && + intel_connector->encoder->hpd_pin > HPD_NONE) connector->polled = DRM_CONNECTOR_POLL_HPD; } diff --git a/drivers/gpu/drm/i915/intel_i2c.c b/drivers/gpu/drm/i915/intel_i2c.c index 8324654037b6..f3bee54c414f 100644 --- a/drivers/gpu/drm/i915/intel_i2c.c +++ b/drivers/gpu/drm/i915/intel_i2c.c @@ -675,7 +675,7 @@ int intel_setup_gmbus(struct drm_device *dev) return 0; err: - while (--pin) { + while (pin--) { if (!intel_gmbus_is_valid_pin(dev_priv, pin)) continue; diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c index 88e12bdf79e2..7058f75c7b42 100644 --- a/drivers/gpu/drm/i915/intel_lrc.c +++ b/drivers/gpu/drm/i915/intel_lrc.c @@ -776,11 +776,11 @@ static int logical_ring_prepare(struct drm_i915_gem_request *req, int bytes) if (unlikely(total_bytes > remain_usable)) { /* * The base request will fit but the reserved space - * falls off the end. So only need to to wait for the - * reserved size after flushing out the remainder. + * falls off the end. So don't need an immediate wrap + * and only need to effectively wait for the reserved + * size space from the start of ringbuffer. */ wait_bytes = remain_actual + ringbuf->reserved_size; - need_wrap = true; } else if (total_bytes > ringbuf->space) { /* No wrapping required, just waiting. */ wait_bytes = total_bytes; @@ -1706,6 +1706,7 @@ static int gen8_emit_flush_render(struct drm_i915_gem_request *request, if (flush_domains) { flags |= PIPE_CONTROL_RENDER_TARGET_CACHE_FLUSH; flags |= PIPE_CONTROL_DEPTH_CACHE_FLUSH; + flags |= PIPE_CONTROL_DC_FLUSH_ENABLE; flags |= PIPE_CONTROL_FLUSH_ENABLE; } diff --git a/drivers/gpu/drm/i915/intel_opregion.c b/drivers/gpu/drm/i915/intel_opregion.c index 6dc13c02c28e..e362a30776fa 100644 --- a/drivers/gpu/drm/i915/intel_opregion.c +++ b/drivers/gpu/drm/i915/intel_opregion.c @@ -682,7 +682,7 @@ static void intel_didl_outputs(struct drm_device *dev) } if (!acpi_video_bus) { - DRM_ERROR("No ACPI video bus found\n"); + DRM_DEBUG_KMS("No ACPI video bus found\n"); return; } diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c index f091ad12d694..1e851e037c29 100644 --- a/drivers/gpu/drm/i915/intel_pm.c +++ b/drivers/gpu/drm/i915/intel_pm.c @@ -1789,16 +1789,20 @@ static uint32_t ilk_compute_cur_wm(const struct intel_crtc_state *cstate, const struct intel_plane_state *pstate, uint32_t mem_value) { - int bpp = pstate->base.fb ? pstate->base.fb->bits_per_pixel / 8 : 0; + /* + * We treat the cursor plane as always-on for the purposes of watermark + * calculation. Until we have two-stage watermark programming merged, + * this is necessary to avoid flickering. + */ + int cpp = 4; + int width = pstate->visible ? pstate->base.crtc_w : 64; - if (!cstate->base.active || !pstate->visible) + if (!cstate->base.active) return 0; return ilk_wm_method2(ilk_pipe_pixel_rate(cstate), cstate->base.adjusted_mode.crtc_htotal, - drm_rect_width(&pstate->dst), - bpp, - mem_value); + width, cpp, mem_value); } /* Only for WM_LP. */ @@ -3880,6 +3884,8 @@ static void ilk_pipe_wm_get_hw_state(struct drm_crtc *crtc) if (IS_HASWELL(dev) || IS_BROADWELL(dev)) hw->wm_linetime[pipe] = I915_READ(PIPE_WM_LINETIME(pipe)); + memset(active, 0, sizeof(*active)); + active->pipe_enabled = intel_crtc->active; if (active->pipe_enabled) { @@ -4520,7 +4526,8 @@ void gen6_rps_idle(struct drm_i915_private *dev_priv) else gen6_set_rps(dev_priv->dev, dev_priv->rps.idle_freq); dev_priv->rps.last_adj = 0; - I915_WRITE(GEN6_PMINTRMSK, 0xffffffff); + I915_WRITE(GEN6_PMINTRMSK, + gen6_sanitize_rps_pm_mask(dev_priv, ~0)); } mutex_unlock(&dev_priv->rps.hw_lock); @@ -6620,6 +6627,12 @@ static void broadwell_init_clock_gating(struct drm_device *dev) misccpctl = I915_READ(GEN7_MISCCPCTL); I915_WRITE(GEN7_MISCCPCTL, misccpctl & ~GEN7_DOP_CLOCK_GATE_ENABLE); I915_WRITE(GEN8_L3SQCREG1, BDW_WA_L3SQCREG1_DEFAULT); + /* + * Wait at least 100 clocks before re-enabling clock gating. See + * the definition of L3SQCREG1 in BSpec. + */ + POSTING_READ(GEN8_L3SQCREG1); + udelay(1); I915_WRITE(GEN7_MISCCPCTL, misccpctl); /* diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c index 9461a238f5d5..9d48443bca2e 100644 --- a/drivers/gpu/drm/i915/intel_ringbuffer.c +++ b/drivers/gpu/drm/i915/intel_ringbuffer.c @@ -347,6 +347,7 @@ gen7_render_ring_flush(struct drm_i915_gem_request *req, if (flush_domains) { flags |= PIPE_CONTROL_RENDER_TARGET_CACHE_FLUSH; flags |= PIPE_CONTROL_DEPTH_CACHE_FLUSH; + flags |= PIPE_CONTROL_DC_FLUSH_ENABLE; flags |= PIPE_CONTROL_FLUSH_ENABLE; } if (invalidate_domains) { @@ -419,6 +420,7 @@ gen8_render_ring_flush(struct drm_i915_gem_request *req, if (flush_domains) { flags |= PIPE_CONTROL_RENDER_TARGET_CACHE_FLUSH; flags |= PIPE_CONTROL_DEPTH_CACHE_FLUSH; + flags |= PIPE_CONTROL_DC_FLUSH_ENABLE; flags |= PIPE_CONTROL_FLUSH_ENABLE; } if (invalidate_domains) { @@ -1920,6 +1922,17 @@ i915_dispatch_execbuffer(struct drm_i915_gem_request *req, return 0; } +static void cleanup_phys_status_page(struct intel_engine_cs *ring) +{ + struct drm_i915_private *dev_priv = to_i915(ring->dev); + + if (!dev_priv->status_page_dmah) + return; + + drm_pci_free(ring->dev, dev_priv->status_page_dmah); + ring->status_page.page_addr = NULL; +} + static void cleanup_status_page(struct intel_engine_cs *ring) { struct drm_i915_gem_object *obj; @@ -1936,9 +1949,9 @@ static void cleanup_status_page(struct intel_engine_cs *ring) static int init_status_page(struct intel_engine_cs *ring) { - struct drm_i915_gem_object *obj; + struct drm_i915_gem_object *obj = ring->status_page.obj; - if ((obj = ring->status_page.obj) == NULL) { + if (obj == NULL) { unsigned flags; int ret; @@ -2132,7 +2145,7 @@ static int intel_init_ring_buffer(struct drm_device *dev, if (ret) goto error; } else { - BUG_ON(ring->id != RCS); + WARN_ON(ring->id != RCS); ret = init_phys_status_page(ring); if (ret) goto error; @@ -2177,7 +2190,12 @@ void intel_cleanup_ring_buffer(struct intel_engine_cs *ring) if (ring->cleanup) ring->cleanup(ring); - cleanup_status_page(ring); + if (I915_NEED_GFX_HWS(ring->dev)) { + cleanup_status_page(ring); + } else { + WARN_ON(ring->id != RCS); + cleanup_phys_status_page(ring); + } i915_cmd_parser_fini_ring(ring); i915_gem_batch_pool_fini(&ring->batch_pool); @@ -2339,11 +2357,11 @@ static int __intel_ring_prepare(struct intel_engine_cs *ring, int bytes) if (unlikely(total_bytes > remain_usable)) { /* * The base request will fit but the reserved space - * falls off the end. So only need to to wait for the - * reserved size after flushing out the remainder. + * falls off the end. So don't need an immediate wrap + * and only need to effectively wait for the reserved + * size space from the start of ringbuffer. */ wait_bytes = remain_actual + ringbuf->reserved_size; - need_wrap = true; } else if (total_bytes > ringbuf->space) { /* No wrapping required, just waiting. */ wait_bytes = total_bytes; diff --git a/drivers/gpu/drm/i915/intel_sprite.c b/drivers/gpu/drm/i915/intel_sprite.c index 56dc132e8e20..2cc6aa072f4c 100644 --- a/drivers/gpu/drm/i915/intel_sprite.c +++ b/drivers/gpu/drm/i915/intel_sprite.c @@ -195,7 +195,7 @@ skl_update_plane(struct drm_plane *drm_plane, struct drm_crtc *crtc, int pixel_size = drm_format_plane_cpp(fb->pixel_format, 0); const struct drm_intel_sprite_colorkey *key = &to_intel_plane_state(drm_plane->state)->ckey; - unsigned long surf_addr; + u32 surf_addr; u32 tile_height, plane_offset, plane_size; unsigned int rotation; int x_offset, y_offset; diff --git a/drivers/gpu/drm/i915/intel_uncore.c b/drivers/gpu/drm/i915/intel_uncore.c index 43cba129a0c0..cc91ae832ffb 100644 --- a/drivers/gpu/drm/i915/intel_uncore.c +++ b/drivers/gpu/drm/i915/intel_uncore.c @@ -1132,7 +1132,11 @@ static void intel_uncore_fw_domains_init(struct drm_device *dev) } else if (IS_HASWELL(dev) || IS_BROADWELL(dev)) { dev_priv->uncore.funcs.force_wake_get = fw_domains_get_with_thread_status; - dev_priv->uncore.funcs.force_wake_put = fw_domains_put; + if (IS_HASWELL(dev)) + dev_priv->uncore.funcs.force_wake_put = + fw_domains_put_with_fifo; + else + dev_priv->uncore.funcs.force_wake_put = fw_domains_put; fw_domain_init(dev_priv, FW_DOMAIN_ID_RENDER, FORCEWAKE_MT, FORCEWAKE_ACK_HSW); } else if (IS_IVYBRIDGE(dev)) { diff --git a/drivers/gpu/drm/imx/imx-drm-core.c b/drivers/gpu/drm/imx/imx-drm-core.c index 7b990b4e96d2..5378bdc3bbf9 100644 --- a/drivers/gpu/drm/imx/imx-drm-core.c +++ b/drivers/gpu/drm/imx/imx-drm-core.c @@ -26,6 +26,7 @@ #include <drm/drm_fb_cma_helper.h> #include <drm/drm_plane_helper.h> #include <drm/drm_of.h> +#include <video/imx-ipu-v3.h> #include "imx-drm.h" @@ -504,6 +505,13 @@ static int compare_of(struct device *dev, void *data) { struct device_node *np = data; + /* Special case for DI, dev->of_node may not be set yet */ + if (strcmp(dev->driver->name, "imx-ipuv3-crtc") == 0) { + struct ipu_client_platformdata *pdata = dev->platform_data; + + return pdata->of_node == np; + } + /* Special case for LDB, one device for two channels */ if (of_node_cmp(np->name, "lvds-channel") == 0) { np = of_get_parent(np); diff --git a/drivers/gpu/drm/imx/ipuv3-crtc.c b/drivers/gpu/drm/imx/ipuv3-crtc.c index 4ab841eebee1..9b0abd44b751 100644 --- a/drivers/gpu/drm/imx/ipuv3-crtc.c +++ b/drivers/gpu/drm/imx/ipuv3-crtc.c @@ -369,7 +369,7 @@ static int ipu_crtc_init(struct ipu_crtc *ipu_crtc, ret = imx_drm_add_crtc(drm, &ipu_crtc->base, &ipu_crtc->imx_crtc, &ipu_crtc->plane[0]->base, &ipu_crtc_helper_funcs, - ipu_crtc->dev->of_node); + pdata->of_node); if (ret) { dev_err(ipu_crtc->dev, "adding crtc failed with %d.\n", ret); goto err_put_resources; diff --git a/drivers/gpu/drm/mgag200/mgag200_mode.c b/drivers/gpu/drm/mgag200/mgag200_mode.c index c99d3fe12881..e5bb40e58020 100644 --- a/drivers/gpu/drm/mgag200/mgag200_mode.c +++ b/drivers/gpu/drm/mgag200/mgag200_mode.c @@ -194,7 +194,7 @@ static int mga_g200se_set_plls(struct mga_device *mdev, long clock) } } - fvv = pllreffreq * testn / testm; + fvv = pllreffreq * (n + 1) / (m + 1); fvv = (fvv - 800000) / 50000; if (fvv > 15) @@ -214,6 +214,14 @@ static int mga_g200se_set_plls(struct mga_device *mdev, long clock) WREG_DAC(MGA1064_PIX_PLLC_M, m); WREG_DAC(MGA1064_PIX_PLLC_N, n); WREG_DAC(MGA1064_PIX_PLLC_P, p); + + if (mdev->unique_rev_id >= 0x04) { + WREG_DAC(0x1a, 0x09); + msleep(20); + WREG_DAC(0x1a, 0x01); + + } + return 0; } diff --git a/drivers/gpu/drm/msm/msm_gem_submit.c b/drivers/gpu/drm/msm/msm_gem_submit.c index 6d7cd3fe21e7..1847f83b1e33 100644 --- a/drivers/gpu/drm/msm/msm_gem_submit.c +++ b/drivers/gpu/drm/msm/msm_gem_submit.c @@ -55,6 +55,14 @@ static struct msm_gem_submit *submit_create(struct drm_device *dev, return submit; } +static inline unsigned long __must_check +copy_from_user_inatomic(void *to, const void __user *from, unsigned long n) +{ + if (access_ok(VERIFY_READ, from, n)) + return __copy_from_user_inatomic(to, from, n); + return -EFAULT; +} + static int submit_lookup_objects(struct msm_gem_submit *submit, struct drm_msm_gem_submit *args, struct drm_file *file) { @@ -62,6 +70,7 @@ static int submit_lookup_objects(struct msm_gem_submit *submit, int ret = 0; spin_lock(&file->table_lock); + pagefault_disable(); for (i = 0; i < args->nr_bos; i++) { struct drm_msm_gem_submit_bo submit_bo; @@ -70,10 +79,15 @@ static int submit_lookup_objects(struct msm_gem_submit *submit, void __user *userptr = to_user_ptr(args->bos + (i * sizeof(submit_bo))); - ret = copy_from_user(&submit_bo, userptr, sizeof(submit_bo)); - if (ret) { - ret = -EFAULT; - goto out_unlock; + ret = copy_from_user_inatomic(&submit_bo, userptr, sizeof(submit_bo)); + if (unlikely(ret)) { + pagefault_enable(); + spin_unlock(&file->table_lock); + ret = copy_from_user(&submit_bo, userptr, sizeof(submit_bo)); + if (ret) + goto out; + spin_lock(&file->table_lock); + pagefault_disable(); } if (submit_bo.flags & ~MSM_SUBMIT_BO_FLAGS) { @@ -113,9 +127,12 @@ static int submit_lookup_objects(struct msm_gem_submit *submit, } out_unlock: - submit->nr_bos = i; + pagefault_enable(); spin_unlock(&file->table_lock); +out: + submit->nr_bos = i; + return ret; } diff --git a/drivers/gpu/drm/nouveau/nouveau_connector.c b/drivers/gpu/drm/nouveau/nouveau_connector.c index 2e7cbe933533..2a5ed7460354 100644 --- a/drivers/gpu/drm/nouveau/nouveau_connector.c +++ b/drivers/gpu/drm/nouveau/nouveau_connector.c @@ -969,10 +969,13 @@ nouveau_connector_hotplug(struct nvif_notify *notify) NV_DEBUG(drm, "%splugged %s\n", plugged ? "" : "un", name); + mutex_lock(&drm->dev->mode_config.mutex); if (plugged) drm_helper_connector_dpms(connector, DRM_MODE_DPMS_ON); else drm_helper_connector_dpms(connector, DRM_MODE_DPMS_OFF); + mutex_unlock(&drm->dev->mode_config.mutex); + drm_helper_hpd_irq_event(connector->dev); } diff --git a/drivers/gpu/drm/nouveau/nouveau_display.c b/drivers/gpu/drm/nouveau/nouveau_display.c index 64c8d932d5f1..58a3f7cf2fb3 100644 --- a/drivers/gpu/drm/nouveau/nouveau_display.c +++ b/drivers/gpu/drm/nouveau/nouveau_display.c @@ -634,10 +634,6 @@ nouveau_display_resume(struct drm_device *dev, bool runtime) nv_crtc->lut.depth = 0; } - /* Make sure that drm and hw vblank irqs get resumed if needed. */ - for (head = 0; head < dev->mode_config.num_crtc; head++) - drm_vblank_on(dev, head); - /* This should ensure we don't hit a locking problem when someone * wakes us up via a connector. We should never go into suspend * while the display is on anyways. @@ -647,6 +643,10 @@ nouveau_display_resume(struct drm_device *dev, bool runtime) drm_helper_resume_force_mode(dev); + /* Make sure that drm and hw vblank irqs get resumed if needed. */ + for (head = 0; head < dev->mode_config.num_crtc; head++) + drm_vblank_on(dev, head); + list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) { struct nouveau_crtc *nv_crtc = nouveau_crtc(crtc); diff --git a/drivers/gpu/drm/nouveau/nouveau_drm.c b/drivers/gpu/drm/nouveau/nouveau_drm.c index 1d3ee5179ab8..d236fc7c425b 100644 --- a/drivers/gpu/drm/nouveau/nouveau_drm.c +++ b/drivers/gpu/drm/nouveau/nouveau_drm.c @@ -308,7 +308,16 @@ static int nouveau_drm_probe(struct pci_dev *pdev, bool boot = false; int ret; - /* remove conflicting drivers (vesafb, efifb etc) */ + /* We need to check that the chipset is supported before booting + * fbdev off the hardware, as there's no way to put it back. + */ + ret = nvkm_device_pci_new(pdev, NULL, "error", true, false, 0, &device); + if (ret) + return ret; + + nvkm_device_del(&device); + + /* Remove conflicting drivers (vesafb, efifb etc). */ aper = alloc_apertures(3); if (!aper) return -ENOMEM; diff --git a/drivers/gpu/drm/nouveau/nouveau_fbcon.c b/drivers/gpu/drm/nouveau/nouveau_fbcon.c index 59f27e774acb..e40a1b07a014 100644 --- a/drivers/gpu/drm/nouveau/nouveau_fbcon.c +++ b/drivers/gpu/drm/nouveau/nouveau_fbcon.c @@ -557,6 +557,8 @@ nouveau_fbcon_init(struct drm_device *dev) if (ret) goto fini; + if (fbcon->helper.fbdev) + fbcon->helper.fbdev->pixmap.buf_align = 4; return 0; fini: diff --git a/drivers/gpu/drm/nouveau/nouveau_platform.c b/drivers/gpu/drm/nouveau/nouveau_platform.c index 60e32c4e4e49..35ecc0d0458f 100644 --- a/drivers/gpu/drm/nouveau/nouveau_platform.c +++ b/drivers/gpu/drm/nouveau/nouveau_platform.c @@ -24,7 +24,7 @@ static int nouveau_platform_probe(struct platform_device *pdev) { const struct nvkm_device_tegra_func *func; - struct nvkm_device *device; + struct nvkm_device *device = NULL; struct drm_device *drm; int ret; diff --git a/drivers/gpu/drm/nouveau/nv04_fbcon.c b/drivers/gpu/drm/nouveau/nv04_fbcon.c index 789dc2993b0d..f90568327468 100644 --- a/drivers/gpu/drm/nouveau/nv04_fbcon.c +++ b/drivers/gpu/drm/nouveau/nv04_fbcon.c @@ -82,7 +82,6 @@ nv04_fbcon_imageblit(struct fb_info *info, const struct fb_image *image) uint32_t fg; uint32_t bg; uint32_t dsize; - uint32_t width; uint32_t *data = (uint32_t *)image->data; int ret; @@ -93,9 +92,6 @@ nv04_fbcon_imageblit(struct fb_info *info, const struct fb_image *image) if (ret) return ret; - width = ALIGN(image->width, 8); - dsize = ALIGN(width * image->height, 32) >> 5; - if (info->fix.visual == FB_VISUAL_TRUECOLOR || info->fix.visual == FB_VISUAL_DIRECTCOLOR) { fg = ((uint32_t *) info->pseudo_palette)[image->fg_color]; @@ -111,10 +107,11 @@ nv04_fbcon_imageblit(struct fb_info *info, const struct fb_image *image) ((image->dx + image->width) & 0xffff)); OUT_RING(chan, bg); OUT_RING(chan, fg); - OUT_RING(chan, (image->height << 16) | width); + OUT_RING(chan, (image->height << 16) | ALIGN(image->width, 8)); OUT_RING(chan, (image->height << 16) | image->width); OUT_RING(chan, (image->dy << 16) | (image->dx & 0xffff)); + dsize = ALIGN(ALIGN(image->width, 8) * image->height, 32) >> 5; while (dsize) { int iter_len = dsize > 128 ? 128 : dsize; diff --git a/drivers/gpu/drm/nouveau/nv50_fbcon.c b/drivers/gpu/drm/nouveau/nv50_fbcon.c index e05499d6ed83..c8e096533f60 100644 --- a/drivers/gpu/drm/nouveau/nv50_fbcon.c +++ b/drivers/gpu/drm/nouveau/nv50_fbcon.c @@ -95,7 +95,7 @@ nv50_fbcon_imageblit(struct fb_info *info, const struct fb_image *image) struct nouveau_fbdev *nfbdev = info->par; struct nouveau_drm *drm = nouveau_drm(nfbdev->dev); struct nouveau_channel *chan = drm->channel; - uint32_t width, dwords, *data = (uint32_t *)image->data; + uint32_t dwords, *data = (uint32_t *)image->data; uint32_t mask = ~(~0 >> (32 - info->var.bits_per_pixel)); uint32_t *palette = info->pseudo_palette; int ret; @@ -107,9 +107,6 @@ nv50_fbcon_imageblit(struct fb_info *info, const struct fb_image *image) if (ret) return ret; - width = ALIGN(image->width, 32); - dwords = (width * image->height) >> 5; - BEGIN_NV04(chan, NvSub2D, 0x0814, 2); if (info->fix.visual == FB_VISUAL_TRUECOLOR || info->fix.visual == FB_VISUAL_DIRECTCOLOR) { @@ -128,6 +125,7 @@ nv50_fbcon_imageblit(struct fb_info *info, const struct fb_image *image) OUT_RING(chan, 0); OUT_RING(chan, image->dy); + dwords = ALIGN(ALIGN(image->width, 8) * image->height, 32) >> 5; while (dwords) { int push = dwords > 2047 ? 2047 : dwords; diff --git a/drivers/gpu/drm/nouveau/nvc0_fbcon.c b/drivers/gpu/drm/nouveau/nvc0_fbcon.c index c97395b4a312..22d32578dafd 100644 --- a/drivers/gpu/drm/nouveau/nvc0_fbcon.c +++ b/drivers/gpu/drm/nouveau/nvc0_fbcon.c @@ -95,7 +95,7 @@ nvc0_fbcon_imageblit(struct fb_info *info, const struct fb_image *image) struct nouveau_fbdev *nfbdev = info->par; struct nouveau_drm *drm = nouveau_drm(nfbdev->dev); struct nouveau_channel *chan = drm->channel; - uint32_t width, dwords, *data = (uint32_t *)image->data; + uint32_t dwords, *data = (uint32_t *)image->data; uint32_t mask = ~(~0 >> (32 - info->var.bits_per_pixel)); uint32_t *palette = info->pseudo_palette; int ret; @@ -107,9 +107,6 @@ nvc0_fbcon_imageblit(struct fb_info *info, const struct fb_image *image) if (ret) return ret; - width = ALIGN(image->width, 32); - dwords = (width * image->height) >> 5; - BEGIN_NVC0(chan, NvSub2D, 0x0814, 2); if (info->fix.visual == FB_VISUAL_TRUECOLOR || info->fix.visual == FB_VISUAL_DIRECTCOLOR) { @@ -128,6 +125,7 @@ nvc0_fbcon_imageblit(struct fb_info *info, const struct fb_image *image) OUT_RING (chan, 0); OUT_RING (chan, image->dy); + dwords = ALIGN(ALIGN(image->width, 8) * image->height, 32) >> 5; while (dwords) { int push = dwords > 2047 ? 2047 : dwords; diff --git a/drivers/gpu/drm/nouveau/nvkm/core/ramht.c b/drivers/gpu/drm/nouveau/nvkm/core/ramht.c index 3216e157a8a0..89da47234016 100644 --- a/drivers/gpu/drm/nouveau/nvkm/core/ramht.c +++ b/drivers/gpu/drm/nouveau/nvkm/core/ramht.c @@ -131,7 +131,7 @@ nvkm_ramht_del(struct nvkm_ramht **pramht) struct nvkm_ramht *ramht = *pramht; if (ramht) { nvkm_gpuobj_del(&ramht->gpuobj); - kfree(*pramht); + vfree(*pramht); *pramht = NULL; } } @@ -143,8 +143,8 @@ nvkm_ramht_new(struct nvkm_device *device, u32 size, u32 align, struct nvkm_ramht *ramht; int ret, i; - if (!(ramht = *pramht = kzalloc(sizeof(*ramht) + (size >> 3) * - sizeof(*ramht->data), GFP_KERNEL))) + if (!(ramht = *pramht = vzalloc(sizeof(*ramht) + + (size >> 3) * sizeof(*ramht->data)))) return -ENOMEM; ramht->device = device; diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/device/tegra.c b/drivers/gpu/drm/nouveau/nvkm/engine/device/tegra.c index 7f8a42721eb2..e7e581d6a8ff 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/device/tegra.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/device/tegra.c @@ -252,32 +252,40 @@ nvkm_device_tegra_new(const struct nvkm_device_tegra_func *func, if (!(tdev = kzalloc(sizeof(*tdev), GFP_KERNEL))) return -ENOMEM; - *pdevice = &tdev->device; + tdev->func = func; tdev->pdev = pdev; tdev->irq = -1; tdev->vdd = devm_regulator_get(&pdev->dev, "vdd"); - if (IS_ERR(tdev->vdd)) - return PTR_ERR(tdev->vdd); + if (IS_ERR(tdev->vdd)) { + ret = PTR_ERR(tdev->vdd); + goto free; + } tdev->rst = devm_reset_control_get(&pdev->dev, "gpu"); - if (IS_ERR(tdev->rst)) - return PTR_ERR(tdev->rst); + if (IS_ERR(tdev->rst)) { + ret = PTR_ERR(tdev->rst); + goto free; + } tdev->clk = devm_clk_get(&pdev->dev, "gpu"); - if (IS_ERR(tdev->clk)) - return PTR_ERR(tdev->clk); + if (IS_ERR(tdev->clk)) { + ret = PTR_ERR(tdev->clk); + goto free; + } tdev->clk_pwr = devm_clk_get(&pdev->dev, "pwr"); - if (IS_ERR(tdev->clk_pwr)) - return PTR_ERR(tdev->clk_pwr); + if (IS_ERR(tdev->clk_pwr)) { + ret = PTR_ERR(tdev->clk_pwr); + goto free; + } nvkm_device_tegra_probe_iommu(tdev); ret = nvkm_device_tegra_power_up(tdev); if (ret) - return ret; + goto remove; tdev->gpu_speedo = tegra_sku_info.gpu_speedo_value; ret = nvkm_device_ctor(&nvkm_device_tegra_func, NULL, &pdev->dev, @@ -285,9 +293,19 @@ nvkm_device_tegra_new(const struct nvkm_device_tegra_func *func, cfg, dbg, detect, mmio, subdev_mask, &tdev->device); if (ret) - return ret; + goto powerdown; + + *pdevice = &tdev->device; return 0; + +powerdown: + nvkm_device_tegra_power_down(tdev); +remove: + nvkm_device_tegra_remove_iommu(tdev); +free: + kfree(tdev); + return ret; } #else int diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/dport.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/dport.c index 74e2f7c6c07e..9688970eca47 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/dport.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/dport.c @@ -328,6 +328,7 @@ nvkm_dp_train(struct work_struct *w) .outp = outp, }, *dp = &_dp; u32 datarate = 0; + u8 pwr; int ret; if (!outp->base.info.location && disp->func->sor.magic) @@ -355,6 +356,15 @@ nvkm_dp_train(struct work_struct *w) /* disable link interrupt handling during link training */ nvkm_notify_put(&outp->irq); + /* ensure sink is not in a low-power state */ + if (!nvkm_rdaux(outp->aux, DPCD_SC00, &pwr, 1)) { + if ((pwr & DPCD_SC00_SET_POWER) != DPCD_SC00_SET_POWER_D0) { + pwr &= ~DPCD_SC00_SET_POWER; + pwr |= DPCD_SC00_SET_POWER_D0; + nvkm_wraux(outp->aux, DPCD_SC00, &pwr, 1); + } + } + /* enable down-spreading and execute pre-train script from vbios */ dp_link_train_init(dp, outp->dpcd[3] & 0x01); diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/dport.h b/drivers/gpu/drm/nouveau/nvkm/engine/disp/dport.h index 9596290329c7..6e10c5e0ef11 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/dport.h +++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/dport.h @@ -71,5 +71,11 @@ #define DPCD_LS0C_LANE1_POST_CURSOR2 0x0c #define DPCD_LS0C_LANE0_POST_CURSOR2 0x03 +/* DPCD Sink Control */ +#define DPCD_SC00 0x00600 +#define DPCD_SC00_SET_POWER 0x03 +#define DPCD_SC00_SET_POWER_D0 0x01 +#define DPCD_SC00_SET_POWER_D3 0x03 + void nvkm_dp_train(struct work_struct *); #endif diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/sorgf119.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/sorgf119.c index b4b41b135643..2aaf0dd19a55 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/sorgf119.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/sorgf119.c @@ -40,8 +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; - const u32 loff = gf119_sor_loff(outp); - nvkm_mask(device, 0x61c110 + loff, 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/nouveau/nvkm/engine/fifo/dmanv04.c b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/dmanv04.c index bfcc6408a772..b7f4b826febe 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/dmanv04.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/dmanv04.c @@ -36,7 +36,10 @@ nv04_fifo_dma_object_dtor(struct nvkm_fifo_chan *base, int cookie) { struct nv04_fifo_chan *chan = nv04_fifo_chan(base); struct nvkm_instmem *imem = chan->fifo->base.engine.subdev.device->imem; + + mutex_lock(&chan->fifo->base.engine.subdev.mutex); nvkm_ramht_remove(imem->ramht, cookie); + mutex_unlock(&chan->fifo->base.engine.subdev.mutex); } static int diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.c index 9f5dfc85147a..eeeea1c2ca23 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.c @@ -874,22 +874,41 @@ gf100_gr_trap_gpc_rop(struct gf100_gr *gr, int gpc) } static const struct nvkm_enum gf100_mp_warp_error[] = { - { 0x00, "NO_ERROR" }, - { 0x01, "STACK_MISMATCH" }, + { 0x01, "STACK_ERROR" }, + { 0x02, "API_STACK_ERROR" }, + { 0x03, "RET_EMPTY_STACK_ERROR" }, + { 0x04, "PC_WRAP" }, { 0x05, "MISALIGNED_PC" }, - { 0x08, "MISALIGNED_GPR" }, - { 0x09, "INVALID_OPCODE" }, - { 0x0d, "GPR_OUT_OF_BOUNDS" }, - { 0x0e, "MEM_OUT_OF_BOUNDS" }, - { 0x0f, "UNALIGNED_MEM_ACCESS" }, + { 0x06, "PC_OVERFLOW" }, + { 0x07, "MISALIGNED_IMMC_ADDR" }, + { 0x08, "MISALIGNED_REG" }, + { 0x09, "ILLEGAL_INSTR_ENCODING" }, + { 0x0a, "ILLEGAL_SPH_INSTR_COMBO" }, + { 0x0b, "ILLEGAL_INSTR_PARAM" }, + { 0x0c, "INVALID_CONST_ADDR" }, + { 0x0d, "OOR_REG" }, + { 0x0e, "OOR_ADDR" }, + { 0x0f, "MISALIGNED_ADDR" }, { 0x10, "INVALID_ADDR_SPACE" }, - { 0x11, "INVALID_PARAM" }, + { 0x11, "ILLEGAL_INSTR_PARAM2" }, + { 0x12, "INVALID_CONST_ADDR_LDC" }, + { 0x13, "GEOMETRY_SM_ERROR" }, + { 0x14, "DIVERGENT" }, + { 0x15, "WARP_EXIT" }, {} }; static const struct nvkm_bitfield gf100_mp_global_error[] = { + { 0x00000001, "SM_TO_SM_FAULT" }, + { 0x00000002, "L1_ERROR" }, { 0x00000004, "MULTIPLE_WARP_ERRORS" }, - { 0x00000008, "OUT_OF_STACK_SPACE" }, + { 0x00000008, "PHYSICAL_STACK_OVERFLOW" }, + { 0x00000010, "BPT_INT" }, + { 0x00000020, "BPT_PAUSE" }, + { 0x00000040, "SINGLE_STEP_COMPLETE" }, + { 0x20000000, "ECC_SEC_ERROR" }, + { 0x40000000, "ECC_DED_ERROR" }, + { 0x80000000, "TIMEOUT" }, {} }; @@ -1717,6 +1736,8 @@ gf100_gr_init(struct gf100_gr *gr) gf100_gr_mmio(gr, gr->func->mmio); + nvkm_mask(device, TPC_UNIT(0, 0, 0x05c), 0x00000001, 0x00000001); + memcpy(tpcnr, gr->tpc_nr, sizeof(gr->tpc_nr)); for (i = 0, gpc = -1; i < gr->tpc_total; i++) { do { diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/nv30.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/nv30.c index 69de8c6259fe..f1e15a4d4f64 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/nv30.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/nv30.c @@ -76,8 +76,8 @@ nv30_gr_chan_new(struct nvkm_gr *base, struct nvkm_fifo_chan *fifoch, nvkm_wo32(chan->inst, i, 0x00040004); for (i = 0x1f18; i <= 0x3088 ; i += 16) { nvkm_wo32(chan->inst, i + 0, 0x10700ff9); - nvkm_wo32(chan->inst, i + 1, 0x0436086c); - nvkm_wo32(chan->inst, i + 2, 0x000c001b); + nvkm_wo32(chan->inst, i + 4, 0x0436086c); + nvkm_wo32(chan->inst, i + 8, 0x000c001b); } for (i = 0x30b8; i < 0x30c8; i += 4) nvkm_wo32(chan->inst, i, 0x0000ffff); diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/nv34.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/nv34.c index 2207dac23981..300f5ed5de0b 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/nv34.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/nv34.c @@ -75,8 +75,8 @@ nv34_gr_chan_new(struct nvkm_gr *base, struct nvkm_fifo_chan *fifoch, nvkm_wo32(chan->inst, i, 0x00040004); for (i = 0x15ac; i <= 0x271c ; i += 16) { nvkm_wo32(chan->inst, i + 0, 0x10700ff9); - nvkm_wo32(chan->inst, i + 1, 0x0436086c); - nvkm_wo32(chan->inst, i + 2, 0x000c001b); + nvkm_wo32(chan->inst, i + 4, 0x0436086c); + nvkm_wo32(chan->inst, i + 8, 0x000c001b); } for (i = 0x274c; i < 0x275c; i += 4) nvkm_wo32(chan->inst, i, 0x0000ffff); diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/pm/nv40.c b/drivers/gpu/drm/nouveau/nvkm/engine/pm/nv40.c index 4bef72a9d106..3fda594700e0 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/pm/nv40.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/pm/nv40.c @@ -59,9 +59,11 @@ static void nv40_perfctr_next(struct nvkm_pm *pm, struct nvkm_perfdom *dom) { struct nvkm_device *device = pm->engine.subdev.device; - if (pm->sequence != pm->sequence) { + struct nv40_pm *nv40pm = container_of(pm, struct nv40_pm, base); + + if (nv40pm->sequence != pm->sequence) { nvkm_wr32(device, 0x400084, 0x00000020); - pm->sequence = pm->sequence; + nv40pm->sequence = pm->sequence; } } diff --git a/drivers/gpu/drm/qxl/qxl_display.c b/drivers/gpu/drm/qxl/qxl_display.c index 183aea1abebc..5edebf495c07 100644 --- a/drivers/gpu/drm/qxl/qxl_display.c +++ b/drivers/gpu/drm/qxl/qxl_display.c @@ -375,10 +375,15 @@ static int qxl_crtc_cursor_set2(struct drm_crtc *crtc, qxl_bo_kunmap(user_bo); + qcrtc->cur_x += qcrtc->hot_spot_x - hot_x; + qcrtc->cur_y += qcrtc->hot_spot_y - hot_y; + qcrtc->hot_spot_x = hot_x; + qcrtc->hot_spot_y = hot_y; + cmd = (struct qxl_cursor_cmd *)qxl_release_map(qdev, release); cmd->type = QXL_CURSOR_SET; - cmd->u.set.position.x = qcrtc->cur_x; - cmd->u.set.position.y = qcrtc->cur_y; + cmd->u.set.position.x = qcrtc->cur_x + qcrtc->hot_spot_x; + cmd->u.set.position.y = qcrtc->cur_y + qcrtc->hot_spot_y; cmd->u.set.shape = qxl_bo_physical_address(qdev, cursor_bo, 0); @@ -441,8 +446,8 @@ static int qxl_crtc_cursor_move(struct drm_crtc *crtc, cmd = (struct qxl_cursor_cmd *)qxl_release_map(qdev, release); cmd->type = QXL_CURSOR_MOVE; - cmd->u.position.x = qcrtc->cur_x; - cmd->u.position.y = qcrtc->cur_y; + cmd->u.position.x = qcrtc->cur_x + qcrtc->hot_spot_x; + cmd->u.position.y = qcrtc->cur_y + qcrtc->hot_spot_y; qxl_release_unmap(qdev, release, &cmd->release_info); qxl_push_cursor_ring_release(qdev, release, QXL_CMD_CURSOR, false); diff --git a/drivers/gpu/drm/qxl/qxl_draw.c b/drivers/gpu/drm/qxl/qxl_draw.c index 56e1d633875e..6e6c76080d6a 100644 --- a/drivers/gpu/drm/qxl/qxl_draw.c +++ b/drivers/gpu/drm/qxl/qxl_draw.c @@ -136,6 +136,8 @@ static int qxl_palette_create_1bit(struct qxl_bo *palette_bo, * correctly globaly, since that would require * tracking all of our palettes. */ ret = qxl_bo_kmap(palette_bo, (void **)&pal); + if (ret) + return ret; pal->num_ents = 2; pal->unique = unique++; if (visual == FB_VISUAL_TRUECOLOR || visual == FB_VISUAL_DIRECTCOLOR) { diff --git a/drivers/gpu/drm/qxl/qxl_drv.h b/drivers/gpu/drm/qxl/qxl_drv.h index 01a86948eb8c..3ab90179e9ab 100644 --- a/drivers/gpu/drm/qxl/qxl_drv.h +++ b/drivers/gpu/drm/qxl/qxl_drv.h @@ -135,6 +135,8 @@ struct qxl_crtc { int index; int cur_x; int cur_y; + int hot_spot_x; + int hot_spot_y; }; struct qxl_output { diff --git a/drivers/gpu/drm/qxl/qxl_ioctl.c b/drivers/gpu/drm/qxl/qxl_ioctl.c index 2ae8577497ca..7c2e78201ead 100644 --- a/drivers/gpu/drm/qxl/qxl_ioctl.c +++ b/drivers/gpu/drm/qxl/qxl_ioctl.c @@ -168,7 +168,8 @@ static int qxl_process_single_command(struct qxl_device *qdev, cmd->command_size)) return -EFAULT; - reloc_info = kmalloc(sizeof(struct qxl_reloc_info) * cmd->relocs_num, GFP_KERNEL); + reloc_info = kmalloc_array(cmd->relocs_num, + sizeof(struct qxl_reloc_info), GFP_KERNEL); if (!reloc_info) return -ENOMEM; diff --git a/drivers/gpu/drm/radeon/atombios_crtc.c b/drivers/gpu/drm/radeon/atombios_crtc.c index dac78ad24b31..79bab6fd76bb 100644 --- a/drivers/gpu/drm/radeon/atombios_crtc.c +++ b/drivers/gpu/drm/radeon/atombios_crtc.c @@ -1739,6 +1739,7 @@ static u32 radeon_get_pll_use_mask(struct drm_crtc *crtc) static int radeon_get_shared_dp_ppll(struct drm_crtc *crtc) { struct drm_device *dev = crtc->dev; + struct radeon_device *rdev = dev->dev_private; struct drm_crtc *test_crtc; struct radeon_crtc *test_radeon_crtc; @@ -1748,6 +1749,10 @@ static int radeon_get_shared_dp_ppll(struct drm_crtc *crtc) test_radeon_crtc = to_radeon_crtc(test_crtc); if (test_radeon_crtc->encoder && ENCODER_MODE_IS_DP(atombios_get_encoder_mode(test_radeon_crtc->encoder))) { + /* PPLL2 is exclusive to UNIPHYA on DCE61 */ + if (ASIC_IS_DCE61(rdev) && !ASIC_IS_DCE8(rdev) && + test_radeon_crtc->pll_id == ATOM_PPLL2) + continue; /* for DP use the same PLL for all */ if (test_radeon_crtc->pll_id != ATOM_PPLL_INVALID) return test_radeon_crtc->pll_id; @@ -1769,6 +1774,7 @@ static int radeon_get_shared_nondp_ppll(struct drm_crtc *crtc) { struct radeon_crtc *radeon_crtc = to_radeon_crtc(crtc); struct drm_device *dev = crtc->dev; + struct radeon_device *rdev = dev->dev_private; struct drm_crtc *test_crtc; struct radeon_crtc *test_radeon_crtc; u32 adjusted_clock, test_adjusted_clock; @@ -1784,6 +1790,10 @@ static int radeon_get_shared_nondp_ppll(struct drm_crtc *crtc) test_radeon_crtc = to_radeon_crtc(test_crtc); if (test_radeon_crtc->encoder && !ENCODER_MODE_IS_DP(atombios_get_encoder_mode(test_radeon_crtc->encoder))) { + /* PPLL2 is exclusive to UNIPHYA on DCE61 */ + if (ASIC_IS_DCE61(rdev) && !ASIC_IS_DCE8(rdev) && + test_radeon_crtc->pll_id == ATOM_PPLL2) + continue; /* check if we are already driving this connector with another crtc */ if (test_radeon_crtc->connector == radeon_crtc->connector) { /* if we are, return that pll */ diff --git a/drivers/gpu/drm/radeon/atombios_dp.c b/drivers/gpu/drm/radeon/atombios_dp.c index bd73b4069069..44ee72e04df9 100644 --- a/drivers/gpu/drm/radeon/atombios_dp.c +++ b/drivers/gpu/drm/radeon/atombios_dp.c @@ -302,77 +302,31 @@ static int convert_bpc_to_bpp(int bpc) return bpc * 3; } -/* get the max pix clock supported by the link rate and lane num */ -static int dp_get_max_dp_pix_clock(int link_rate, - int lane_num, - int bpp) -{ - return (link_rate * lane_num * 8) / bpp; -} - /***** radeon specific DP functions *****/ -int radeon_dp_get_max_link_rate(struct drm_connector *connector, - const u8 dpcd[DP_DPCD_SIZE]) -{ - int max_link_rate; - - if (radeon_connector_is_dp12_capable(connector)) - max_link_rate = min(drm_dp_max_link_rate(dpcd), 540000); - else - max_link_rate = min(drm_dp_max_link_rate(dpcd), 270000); - - return max_link_rate; -} - -/* First get the min lane# when low rate is used according to pixel clock - * (prefer low rate), second check max lane# supported by DP panel, - * if the max lane# < low rate lane# then use max lane# instead. - */ -static int radeon_dp_get_dp_lane_number(struct drm_connector *connector, - const u8 dpcd[DP_DPCD_SIZE], - int pix_clock) -{ - int bpp = convert_bpc_to_bpp(radeon_get_monitor_bpc(connector)); - int max_link_rate = radeon_dp_get_max_link_rate(connector, dpcd); - int max_lane_num = drm_dp_max_lane_count(dpcd); - int lane_num; - int max_dp_pix_clock; - - for (lane_num = 1; lane_num < max_lane_num; lane_num <<= 1) { - max_dp_pix_clock = dp_get_max_dp_pix_clock(max_link_rate, lane_num, bpp); - if (pix_clock <= max_dp_pix_clock) - break; - } - - return lane_num; -} - -static int radeon_dp_get_dp_link_clock(struct drm_connector *connector, - const u8 dpcd[DP_DPCD_SIZE], - int pix_clock) +int radeon_dp_get_dp_link_config(struct drm_connector *connector, + const u8 dpcd[DP_DPCD_SIZE], + unsigned pix_clock, + unsigned *dp_lanes, unsigned *dp_rate) { int bpp = convert_bpc_to_bpp(radeon_get_monitor_bpc(connector)); - int lane_num, max_pix_clock; - - if (radeon_connector_encoder_get_dp_bridge_encoder_id(connector) == - ENCODER_OBJECT_ID_NUTMEG) - return 270000; - - lane_num = radeon_dp_get_dp_lane_number(connector, dpcd, pix_clock); - max_pix_clock = dp_get_max_dp_pix_clock(162000, lane_num, bpp); - if (pix_clock <= max_pix_clock) - return 162000; - max_pix_clock = dp_get_max_dp_pix_clock(270000, lane_num, bpp); - if (pix_clock <= max_pix_clock) - return 270000; - if (radeon_connector_is_dp12_capable(connector)) { - max_pix_clock = dp_get_max_dp_pix_clock(540000, lane_num, bpp); - if (pix_clock <= max_pix_clock) - return 540000; + static const unsigned link_rates[3] = { 162000, 270000, 540000 }; + unsigned max_link_rate = drm_dp_max_link_rate(dpcd); + unsigned max_lane_num = drm_dp_max_lane_count(dpcd); + unsigned lane_num, i, max_pix_clock; + + for (lane_num = 1; lane_num <= max_lane_num; lane_num <<= 1) { + for (i = 0; i < ARRAY_SIZE(link_rates) && link_rates[i] <= max_link_rate; i++) { + max_pix_clock = (lane_num * link_rates[i] * 8) / bpp; + if (max_pix_clock >= pix_clock) { + *dp_lanes = lane_num; + *dp_rate = link_rates[i]; + return 0; + } + } } - return radeon_dp_get_max_link_rate(connector, dpcd); + return -EINVAL; } static u8 radeon_dp_encoder_service(struct radeon_device *rdev, @@ -491,6 +445,7 @@ void radeon_dp_set_link_config(struct drm_connector *connector, { struct radeon_connector *radeon_connector = to_radeon_connector(connector); struct radeon_connector_atom_dig *dig_connector; + int ret; if (!radeon_connector->con_priv) return; @@ -498,10 +453,14 @@ void radeon_dp_set_link_config(struct drm_connector *connector, if ((dig_connector->dp_sink_type == CONNECTOR_OBJECT_ID_DISPLAYPORT) || (dig_connector->dp_sink_type == CONNECTOR_OBJECT_ID_eDP)) { - dig_connector->dp_clock = - radeon_dp_get_dp_link_clock(connector, dig_connector->dpcd, mode->clock); - dig_connector->dp_lane_count = - radeon_dp_get_dp_lane_number(connector, dig_connector->dpcd, mode->clock); + ret = radeon_dp_get_dp_link_config(connector, dig_connector->dpcd, + mode->clock, + &dig_connector->dp_lane_count, + &dig_connector->dp_clock); + if (ret) { + dig_connector->dp_clock = 0; + dig_connector->dp_lane_count = 0; + } } } @@ -510,7 +469,8 @@ int radeon_dp_mode_valid_helper(struct drm_connector *connector, { struct radeon_connector *radeon_connector = to_radeon_connector(connector); struct radeon_connector_atom_dig *dig_connector; - int dp_clock; + unsigned dp_clock, dp_lanes; + int ret; if ((mode->clock > 340000) && (!radeon_connector_is_dp12_capable(connector))) @@ -520,8 +480,12 @@ int radeon_dp_mode_valid_helper(struct drm_connector *connector, return MODE_CLOCK_HIGH; dig_connector = radeon_connector->con_priv; - dp_clock = - radeon_dp_get_dp_link_clock(connector, dig_connector->dpcd, mode->clock); + ret = radeon_dp_get_dp_link_config(connector, dig_connector->dpcd, + mode->clock, + &dp_lanes, + &dp_clock); + if (ret) + return MODE_CLOCK_HIGH; if ((dp_clock == 540000) && (!radeon_connector_is_dp12_capable(connector))) diff --git a/drivers/gpu/drm/radeon/atombios_encoders.c b/drivers/gpu/drm/radeon/atombios_encoders.c index bb292143997e..d4ac8c837314 100644 --- a/drivers/gpu/drm/radeon/atombios_encoders.c +++ b/drivers/gpu/drm/radeon/atombios_encoders.c @@ -120,6 +120,7 @@ atombios_set_backlight_level(struct radeon_encoder *radeon_encoder, u8 level) case ENCODER_OBJECT_ID_INTERNAL_KLDSCP_LVTMA: case ENCODER_OBJECT_ID_INTERNAL_UNIPHY1: case ENCODER_OBJECT_ID_INTERNAL_UNIPHY2: + case ENCODER_OBJECT_ID_INTERNAL_UNIPHY3: if (dig->backlight_level == 0) atombios_dig_transmitter_setup(encoder, ATOM_TRANSMITTER_ACTION_LCD_BLOFF, 0, 0); else { @@ -310,6 +311,10 @@ static bool radeon_atom_mode_fixup(struct drm_encoder *encoder, && (mode->crtc_vsync_start < (mode->crtc_vdisplay + 2))) adjusted_mode->crtc_vsync_start = adjusted_mode->crtc_vdisplay + 2; + /* vertical FP must be at least 1 */ + if (mode->crtc_vsync_start == mode->crtc_vdisplay) + adjusted_mode->crtc_vsync_start++; + /* get the native mode for scaling */ if (radeon_encoder->active_device & (ATOM_DEVICE_LCD_SUPPORT)) { radeon_panel_mode_fixup(encoder, adjusted_mode); @@ -892,8 +897,6 @@ atombios_dig_encoder_setup2(struct drm_encoder *encoder, int action, int panel_m else args.v1.ucLaneNum = 4; - if (ENCODER_MODE_IS_DP(args.v1.ucEncoderMode) && (dp_clock == 270000)) - args.v1.ucConfig |= ATOM_ENCODER_CONFIG_DPLINKRATE_2_70GHZ; switch (radeon_encoder->encoder_id) { case ENCODER_OBJECT_ID_INTERNAL_UNIPHY: args.v1.ucConfig = ATOM_ENCODER_CONFIG_V2_TRANSMITTER1; @@ -910,6 +913,10 @@ atombios_dig_encoder_setup2(struct drm_encoder *encoder, int action, int panel_m args.v1.ucConfig |= ATOM_ENCODER_CONFIG_LINKB; else args.v1.ucConfig |= ATOM_ENCODER_CONFIG_LINKA; + + if (ENCODER_MODE_IS_DP(args.v1.ucEncoderMode) && (dp_clock == 270000)) + args.v1.ucConfig |= ATOM_ENCODER_CONFIG_DPLINKRATE_2_70GHZ; + break; case 2: case 3: diff --git a/drivers/gpu/drm/radeon/dce6_afmt.c b/drivers/gpu/drm/radeon/dce6_afmt.c index 752072771388..367a916f364e 100644 --- a/drivers/gpu/drm/radeon/dce6_afmt.c +++ b/drivers/gpu/drm/radeon/dce6_afmt.c @@ -301,6 +301,14 @@ void dce6_dp_audio_set_dto(struct radeon_device *rdev, * is the numerator, DCCG_AUDIO_DTOx_MODULE is the denominator */ if (ASIC_IS_DCE8(rdev)) { + unsigned int div = (RREG32(DENTIST_DISPCLK_CNTL) & + DENTIST_DPREFCLK_WDIVIDER_MASK) >> + DENTIST_DPREFCLK_WDIVIDER_SHIFT; + div = radeon_audio_decode_dfs_div(div); + + if (div) + clock = clock * 100 / div; + WREG32(DCE8_DCCG_AUDIO_DTO1_PHASE, 24000); WREG32(DCE8_DCCG_AUDIO_DTO1_MODULE, clock); } else { diff --git a/drivers/gpu/drm/radeon/evergreen.c b/drivers/gpu/drm/radeon/evergreen.c index 2ad462896896..32491355a1d4 100644 --- a/drivers/gpu/drm/radeon/evergreen.c +++ b/drivers/gpu/drm/radeon/evergreen.c @@ -2608,10 +2608,152 @@ static void evergreen_agp_enable(struct radeon_device *rdev) WREG32(VM_CONTEXT1_CNTL, 0); } +static const unsigned ni_dig_offsets[] = +{ + NI_DIG0_REGISTER_OFFSET, + NI_DIG1_REGISTER_OFFSET, + NI_DIG2_REGISTER_OFFSET, + NI_DIG3_REGISTER_OFFSET, + NI_DIG4_REGISTER_OFFSET, + NI_DIG5_REGISTER_OFFSET +}; + +static const unsigned ni_tx_offsets[] = +{ + NI_DCIO_UNIPHY0_UNIPHY_TX_CONTROL1, + NI_DCIO_UNIPHY1_UNIPHY_TX_CONTROL1, + NI_DCIO_UNIPHY2_UNIPHY_TX_CONTROL1, + NI_DCIO_UNIPHY3_UNIPHY_TX_CONTROL1, + NI_DCIO_UNIPHY4_UNIPHY_TX_CONTROL1, + NI_DCIO_UNIPHY5_UNIPHY_TX_CONTROL1 +}; + +static const unsigned evergreen_dp_offsets[] = +{ + EVERGREEN_DP0_REGISTER_OFFSET, + EVERGREEN_DP1_REGISTER_OFFSET, + EVERGREEN_DP2_REGISTER_OFFSET, + EVERGREEN_DP3_REGISTER_OFFSET, + EVERGREEN_DP4_REGISTER_OFFSET, + EVERGREEN_DP5_REGISTER_OFFSET +}; + + +/* + * Assumption is that EVERGREEN_CRTC_MASTER_EN enable for requested crtc + * We go from crtc to connector and it is not relible since it + * should be an opposite direction .If crtc is enable then + * find the dig_fe which selects this crtc and insure that it enable. + * if such dig_fe is found then find dig_be which selects found dig_be and + * insure that it enable and in DP_SST mode. + * if UNIPHY_PLL_CONTROL1.enable then we should disconnect timing + * from dp symbols clocks . + */ +static bool evergreen_is_dp_sst_stream_enabled(struct radeon_device *rdev, + unsigned crtc_id, unsigned *ret_dig_fe) +{ + unsigned i; + unsigned dig_fe; + unsigned dig_be; + unsigned dig_en_be; + unsigned uniphy_pll; + unsigned digs_fe_selected; + unsigned dig_be_mode; + unsigned dig_fe_mask; + bool is_enabled = false; + bool found_crtc = false; + + /* loop through all running dig_fe to find selected crtc */ + for (i = 0; i < ARRAY_SIZE(ni_dig_offsets); i++) { + dig_fe = RREG32(NI_DIG_FE_CNTL + ni_dig_offsets[i]); + if (dig_fe & NI_DIG_FE_CNTL_SYMCLK_FE_ON && + crtc_id == NI_DIG_FE_CNTL_SOURCE_SELECT(dig_fe)) { + /* found running pipe */ + found_crtc = true; + dig_fe_mask = 1 << i; + dig_fe = i; + break; + } + } + + if (found_crtc) { + /* loop through all running dig_be to find selected dig_fe */ + for (i = 0; i < ARRAY_SIZE(ni_dig_offsets); i++) { + dig_be = RREG32(NI_DIG_BE_CNTL + ni_dig_offsets[i]); + /* if dig_fe_selected by dig_be? */ + digs_fe_selected = NI_DIG_BE_CNTL_FE_SOURCE_SELECT(dig_be); + dig_be_mode = NI_DIG_FE_CNTL_MODE(dig_be); + if (dig_fe_mask & digs_fe_selected && + /* if dig_be in sst mode? */ + dig_be_mode == NI_DIG_BE_DPSST) { + dig_en_be = RREG32(NI_DIG_BE_EN_CNTL + + ni_dig_offsets[i]); + uniphy_pll = RREG32(NI_DCIO_UNIPHY0_PLL_CONTROL1 + + ni_tx_offsets[i]); + /* dig_be enable and tx is running */ + if (dig_en_be & NI_DIG_BE_EN_CNTL_ENABLE && + dig_en_be & NI_DIG_BE_EN_CNTL_SYMBCLK_ON && + uniphy_pll & NI_DCIO_UNIPHY0_PLL_CONTROL1_ENABLE) { + is_enabled = true; + *ret_dig_fe = dig_fe; + break; + } + } + } + } + + return is_enabled; +} + +/* + * Blank dig when in dp sst mode + * Dig ignores crtc timing + */ +static void evergreen_blank_dp_output(struct radeon_device *rdev, + unsigned dig_fe) +{ + unsigned stream_ctrl; + unsigned fifo_ctrl; + unsigned counter = 0; + + if (dig_fe >= ARRAY_SIZE(evergreen_dp_offsets)) { + DRM_ERROR("invalid dig_fe %d\n", dig_fe); + return; + } + + stream_ctrl = RREG32(EVERGREEN_DP_VID_STREAM_CNTL + + evergreen_dp_offsets[dig_fe]); + if (!(stream_ctrl & EVERGREEN_DP_VID_STREAM_CNTL_ENABLE)) { + DRM_ERROR("dig %d , should be enable\n", dig_fe); + return; + } + + stream_ctrl &=~EVERGREEN_DP_VID_STREAM_CNTL_ENABLE; + WREG32(EVERGREEN_DP_VID_STREAM_CNTL + + evergreen_dp_offsets[dig_fe], stream_ctrl); + + stream_ctrl = RREG32(EVERGREEN_DP_VID_STREAM_CNTL + + evergreen_dp_offsets[dig_fe]); + while (counter < 32 && stream_ctrl & EVERGREEN_DP_VID_STREAM_STATUS) { + msleep(1); + counter++; + stream_ctrl = RREG32(EVERGREEN_DP_VID_STREAM_CNTL + + evergreen_dp_offsets[dig_fe]); + } + if (counter >= 32 ) + DRM_ERROR("counter exceeds %d\n", counter); + + fifo_ctrl = RREG32(EVERGREEN_DP_STEER_FIFO + evergreen_dp_offsets[dig_fe]); + fifo_ctrl |= EVERGREEN_DP_STEER_FIFO_RESET; + WREG32(EVERGREEN_DP_STEER_FIFO + evergreen_dp_offsets[dig_fe], fifo_ctrl); + +} + void evergreen_mc_stop(struct radeon_device *rdev, struct evergreen_mc_save *save) { u32 crtc_enabled, tmp, frame_count, blackout; int i, j; + unsigned dig_fe; if (!ASIC_IS_NODCE(rdev)) { save->vga_render_control = RREG32(VGA_RENDER_CONTROL); @@ -2651,7 +2793,17 @@ void evergreen_mc_stop(struct radeon_device *rdev, struct evergreen_mc_save *sav break; udelay(1); } - + /*we should disable dig if it drives dp sst*/ + /*but we are in radeon_device_init and the topology is unknown*/ + /*and it is available after radeon_modeset_init*/ + /*the following method radeon_atom_encoder_dpms_dig*/ + /*does the job if we initialize it properly*/ + /*for now we do it this manually*/ + /**/ + if (ASIC_IS_DCE5(rdev) && + evergreen_is_dp_sst_stream_enabled(rdev, i ,&dig_fe)) + evergreen_blank_dp_output(rdev, dig_fe); + /*we could remove 6 lines below*/ /* XXX this is a hack to avoid strange behavior with EFI on certain systems */ WREG32(EVERGREEN_CRTC_UPDATE_LOCK + crtc_offsets[i], 1); tmp = RREG32(EVERGREEN_CRTC_CONTROL + crtc_offsets[i]); diff --git a/drivers/gpu/drm/radeon/evergreen_hdmi.c b/drivers/gpu/drm/radeon/evergreen_hdmi.c index 9953356fe263..3cf04a2f44bb 100644 --- a/drivers/gpu/drm/radeon/evergreen_hdmi.c +++ b/drivers/gpu/drm/radeon/evergreen_hdmi.c @@ -289,6 +289,16 @@ void dce4_dp_audio_set_dto(struct radeon_device *rdev, * number (coefficient of two integer numbers. DCCG_AUDIO_DTOx_PHASE * is the numerator, DCCG_AUDIO_DTOx_MODULE is the denominator */ + if (ASIC_IS_DCE41(rdev)) { + unsigned int div = (RREG32(DCE41_DENTIST_DISPCLK_CNTL) & + DENTIST_DPREFCLK_WDIVIDER_MASK) >> + DENTIST_DPREFCLK_WDIVIDER_SHIFT; + div = radeon_audio_decode_dfs_div(div); + + if (div) + clock = 100 * clock / div; + } + WREG32(DCCG_AUDIO_DTO1_PHASE, 24000); WREG32(DCCG_AUDIO_DTO1_MODULE, clock); } diff --git a/drivers/gpu/drm/radeon/evergreen_reg.h b/drivers/gpu/drm/radeon/evergreen_reg.h index aa939dfed3a3..b436badf9efa 100644 --- a/drivers/gpu/drm/radeon/evergreen_reg.h +++ b/drivers/gpu/drm/radeon/evergreen_reg.h @@ -250,8 +250,43 @@ /* HDMI blocks at 0x7030, 0x7c30, 0x10830, 0x11430, 0x12030, 0x12c30 */ #define EVERGREEN_HDMI_BASE 0x7030 +/*DIG block*/ +#define NI_DIG0_REGISTER_OFFSET (0x7000 - 0x7000) +#define NI_DIG1_REGISTER_OFFSET (0x7C00 - 0x7000) +#define NI_DIG2_REGISTER_OFFSET (0x10800 - 0x7000) +#define NI_DIG3_REGISTER_OFFSET (0x11400 - 0x7000) +#define NI_DIG4_REGISTER_OFFSET (0x12000 - 0x7000) +#define NI_DIG5_REGISTER_OFFSET (0x12C00 - 0x7000) + + +#define NI_DIG_FE_CNTL 0x7000 +# define NI_DIG_FE_CNTL_SOURCE_SELECT(x) ((x) & 0x3) +# define NI_DIG_FE_CNTL_SYMCLK_FE_ON (1<<24) + + +#define NI_DIG_BE_CNTL 0x7140 +# define NI_DIG_BE_CNTL_FE_SOURCE_SELECT(x) (((x) >> 8 ) & 0x3F) +# define NI_DIG_FE_CNTL_MODE(x) (((x) >> 16) & 0x7 ) + +#define NI_DIG_BE_EN_CNTL 0x7144 +# define NI_DIG_BE_EN_CNTL_ENABLE (1 << 0) +# define NI_DIG_BE_EN_CNTL_SYMBCLK_ON (1 << 8) +# define NI_DIG_BE_DPSST 0 /* Display Port block */ +#define EVERGREEN_DP0_REGISTER_OFFSET (0x730C - 0x730C) +#define EVERGREEN_DP1_REGISTER_OFFSET (0x7F0C - 0x730C) +#define EVERGREEN_DP2_REGISTER_OFFSET (0x10B0C - 0x730C) +#define EVERGREEN_DP3_REGISTER_OFFSET (0x1170C - 0x730C) +#define EVERGREEN_DP4_REGISTER_OFFSET (0x1230C - 0x730C) +#define EVERGREEN_DP5_REGISTER_OFFSET (0x12F0C - 0x730C) + + +#define EVERGREEN_DP_VID_STREAM_CNTL 0x730C +# define EVERGREEN_DP_VID_STREAM_CNTL_ENABLE (1 << 0) +# define EVERGREEN_DP_VID_STREAM_STATUS (1 <<16) +#define EVERGREEN_DP_STEER_FIFO 0x7310 +# define EVERGREEN_DP_STEER_FIFO_RESET (1 << 0) #define EVERGREEN_DP_SEC_CNTL 0x7280 # define EVERGREEN_DP_SEC_STREAM_ENABLE (1 << 0) # define EVERGREEN_DP_SEC_ASP_ENABLE (1 << 4) @@ -266,4 +301,15 @@ # define EVERGREEN_DP_SEC_N_BASE_MULTIPLE(x) (((x) & 0xf) << 24) # define EVERGREEN_DP_SEC_SS_EN (1 << 28) +/*DCIO_UNIPHY block*/ +#define NI_DCIO_UNIPHY0_UNIPHY_TX_CONTROL1 (0x6600 -0x6600) +#define NI_DCIO_UNIPHY1_UNIPHY_TX_CONTROL1 (0x6640 -0x6600) +#define NI_DCIO_UNIPHY2_UNIPHY_TX_CONTROL1 (0x6680 - 0x6600) +#define NI_DCIO_UNIPHY3_UNIPHY_TX_CONTROL1 (0x66C0 - 0x6600) +#define NI_DCIO_UNIPHY4_UNIPHY_TX_CONTROL1 (0x6700 - 0x6600) +#define NI_DCIO_UNIPHY5_UNIPHY_TX_CONTROL1 (0x6740 - 0x6600) + +#define NI_DCIO_UNIPHY0_PLL_CONTROL1 0x6618 +# define NI_DCIO_UNIPHY0_PLL_CONTROL1_ENABLE (1 << 0) + #endif diff --git a/drivers/gpu/drm/radeon/evergreend.h b/drivers/gpu/drm/radeon/evergreend.h index 4aa5f755572b..13b6029d65cc 100644 --- a/drivers/gpu/drm/radeon/evergreend.h +++ b/drivers/gpu/drm/radeon/evergreend.h @@ -511,6 +511,11 @@ #define DCCG_AUDIO_DTO1_CNTL 0x05cc # define DCCG_AUDIO_DTO1_USE_512FBR_DTO (1 << 3) +#define DCE41_DENTIST_DISPCLK_CNTL 0x049c +# define DENTIST_DPREFCLK_WDIVIDER(x) (((x) & 0x7f) << 24) +# define DENTIST_DPREFCLK_WDIVIDER_MASK (0x7f << 24) +# define DENTIST_DPREFCLK_WDIVIDER_SHIFT 24 + /* DCE 4.0 AFMT */ #define HDMI_CONTROL 0x7030 # define HDMI_KEEPOUT_MODE (1 << 0) diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h index 87db64983ea8..5580568088bb 100644 --- a/drivers/gpu/drm/radeon/radeon.h +++ b/drivers/gpu/drm/radeon/radeon.h @@ -268,6 +268,7 @@ struct radeon_clock { uint32_t current_dispclk; uint32_t dp_extclk; uint32_t max_pixel_clock; + uint32_t vco_freq; }; /* diff --git a/drivers/gpu/drm/radeon/radeon_atombios.c b/drivers/gpu/drm/radeon/radeon_atombios.c index 8f285244c839..0c5b3eeff82d 100644 --- a/drivers/gpu/drm/radeon/radeon_atombios.c +++ b/drivers/gpu/drm/radeon/radeon_atombios.c @@ -437,7 +437,9 @@ static bool radeon_atom_apply_quirks(struct drm_device *dev, } /* Fujitsu D3003-S2 board lists DVI-I as DVI-D and VGA */ - if (((dev->pdev->device == 0x9802) || (dev->pdev->device == 0x9806)) && + if (((dev->pdev->device == 0x9802) || + (dev->pdev->device == 0x9805) || + (dev->pdev->device == 0x9806)) && (dev->pdev->subsystem_vendor == 0x1734) && (dev->pdev->subsystem_device == 0x11bd)) { if (*connector_type == DRM_MODE_CONNECTOR_VGA) { @@ -448,14 +450,6 @@ static bool radeon_atom_apply_quirks(struct drm_device *dev, } } - /* Fujitsu D3003-S2 board lists DVI-I as DVI-I and VGA */ - if ((dev->pdev->device == 0x9805) && - (dev->pdev->subsystem_vendor == 0x1734) && - (dev->pdev->subsystem_device == 0x11bd)) { - if (*connector_type == DRM_MODE_CONNECTOR_VGA) - return false; - } - return true; } @@ -1112,6 +1106,31 @@ union firmware_info { ATOM_FIRMWARE_INFO_V2_2 info_22; }; +union igp_info { + struct _ATOM_INTEGRATED_SYSTEM_INFO info; + struct _ATOM_INTEGRATED_SYSTEM_INFO_V2 info_2; + struct _ATOM_INTEGRATED_SYSTEM_INFO_V6 info_6; + struct _ATOM_INTEGRATED_SYSTEM_INFO_V1_7 info_7; + struct _ATOM_INTEGRATED_SYSTEM_INFO_V1_8 info_8; +}; + +static void radeon_atombios_get_dentist_vco_freq(struct radeon_device *rdev) +{ + struct radeon_mode_info *mode_info = &rdev->mode_info; + int index = GetIndexIntoMasterTable(DATA, IntegratedSystemInfo); + union igp_info *igp_info; + u8 frev, crev; + u16 data_offset; + + if (atom_parse_data_header(mode_info->atom_context, index, NULL, + &frev, &crev, &data_offset)) { + igp_info = (union igp_info *)(mode_info->atom_context->bios + + data_offset); + rdev->clock.vco_freq = + le32_to_cpu(igp_info->info_6.ulDentistVCOFreq); + } +} + bool radeon_atom_get_clock_info(struct drm_device *dev) { struct radeon_device *rdev = dev->dev_private; @@ -1136,7 +1155,7 @@ bool radeon_atom_get_clock_info(struct drm_device *dev) le16_to_cpu(firmware_info->info.usReferenceClock); p1pll->reference_div = 0; - if (crev < 2) + if ((frev < 2) && (crev < 2)) p1pll->pll_out_min = le16_to_cpu(firmware_info->info.usMinPixelClockPLL_Output); else @@ -1145,7 +1164,7 @@ bool radeon_atom_get_clock_info(struct drm_device *dev) p1pll->pll_out_max = le32_to_cpu(firmware_info->info.ulMaxPixelClockPLL_Output); - if (crev >= 4) { + if (((frev < 2) && (crev >= 4)) || (frev >= 2)) { p1pll->lcd_pll_out_min = le16_to_cpu(firmware_info->info_14.usLcdMinPixelClockPLL_Output) * 100; if (p1pll->lcd_pll_out_min == 0) @@ -1263,20 +1282,25 @@ bool radeon_atom_get_clock_info(struct drm_device *dev) rdev->mode_info.firmware_flags = le16_to_cpu(firmware_info->info.usFirmwareCapability.susAccess); + if (ASIC_IS_DCE8(rdev)) + rdev->clock.vco_freq = + le32_to_cpu(firmware_info->info_22.ulGPUPLL_OutputFreq); + else if (ASIC_IS_DCE5(rdev)) + rdev->clock.vco_freq = rdev->clock.current_dispclk; + else if (ASIC_IS_DCE41(rdev)) + radeon_atombios_get_dentist_vco_freq(rdev); + else + rdev->clock.vco_freq = rdev->clock.current_dispclk; + + if (rdev->clock.vco_freq == 0) + rdev->clock.vco_freq = 360000; /* 3.6 GHz */ + return true; } return false; } -union igp_info { - struct _ATOM_INTEGRATED_SYSTEM_INFO info; - struct _ATOM_INTEGRATED_SYSTEM_INFO_V2 info_2; - struct _ATOM_INTEGRATED_SYSTEM_INFO_V6 info_6; - struct _ATOM_INTEGRATED_SYSTEM_INFO_V1_7 info_7; - struct _ATOM_INTEGRATED_SYSTEM_INFO_V1_8 info_8; -}; - bool radeon_atombios_sideport_present(struct radeon_device *rdev) { struct radeon_mode_info *mode_info = &rdev->mode_info; diff --git a/drivers/gpu/drm/radeon/radeon_atpx_handler.c b/drivers/gpu/drm/radeon/radeon_atpx_handler.c index c4b4f298a283..69ce95571136 100644 --- a/drivers/gpu/drm/radeon/radeon_atpx_handler.c +++ b/drivers/gpu/drm/radeon/radeon_atpx_handler.c @@ -10,6 +10,7 @@ #include <linux/slab.h> #include <linux/acpi.h> #include <linux/pci.h> +#include <linux/delay.h> #include "radeon_acpi.h" @@ -255,6 +256,10 @@ static int radeon_atpx_set_discrete_state(struct radeon_atpx *atpx, u8 state) if (!info) return -EIO; kfree(info); + + /* 200ms delay is required after off */ + if (state == 0) + msleep(200); } return 0; } diff --git a/drivers/gpu/drm/radeon/radeon_audio.c b/drivers/gpu/drm/radeon/radeon_audio.c index 2c02e99b5f95..b214663b370d 100644 --- a/drivers/gpu/drm/radeon/radeon_audio.c +++ b/drivers/gpu/drm/radeon/radeon_audio.c @@ -739,9 +739,6 @@ static void radeon_audio_dp_mode_set(struct drm_encoder *encoder, struct radeon_encoder *radeon_encoder = to_radeon_encoder(encoder); struct radeon_encoder_atom_dig *dig = radeon_encoder->enc_priv; struct drm_connector *connector = radeon_get_connector_for_encoder(encoder); - struct radeon_connector *radeon_connector = to_radeon_connector(connector); - struct radeon_connector_atom_dig *dig_connector = - radeon_connector->con_priv; if (!dig || !dig->afmt) return; @@ -753,10 +750,7 @@ static void radeon_audio_dp_mode_set(struct drm_encoder *encoder, radeon_audio_write_speaker_allocation(encoder); radeon_audio_write_sad_regs(encoder); radeon_audio_write_latency_fields(encoder, mode); - if (rdev->clock.dp_extclk || ASIC_IS_DCE5(rdev)) - radeon_audio_set_dto(encoder, rdev->clock.default_dispclk * 10); - else - radeon_audio_set_dto(encoder, dig_connector->dp_clock); + radeon_audio_set_dto(encoder, rdev->clock.vco_freq * 10); radeon_audio_set_audio_packet(encoder); radeon_audio_select_pin(encoder); @@ -781,3 +775,15 @@ void radeon_audio_dpms(struct drm_encoder *encoder, int mode) if (radeon_encoder->audio && radeon_encoder->audio->dpms) radeon_encoder->audio->dpms(encoder, mode == DRM_MODE_DPMS_ON); } + +unsigned int radeon_audio_decode_dfs_div(unsigned int div) +{ + if (div >= 8 && div < 64) + return (div - 8) * 25 + 200; + else if (div >= 64 && div < 96) + return (div - 64) * 50 + 1600; + else if (div >= 96 && div < 128) + return (div - 96) * 100 + 3200; + else + return 0; +} diff --git a/drivers/gpu/drm/radeon/radeon_audio.h b/drivers/gpu/drm/radeon/radeon_audio.h index 059cc3012062..5c70cceaa4a6 100644 --- a/drivers/gpu/drm/radeon/radeon_audio.h +++ b/drivers/gpu/drm/radeon/radeon_audio.h @@ -79,5 +79,6 @@ void radeon_audio_fini(struct radeon_device *rdev); void radeon_audio_mode_set(struct drm_encoder *encoder, struct drm_display_mode *mode); void radeon_audio_dpms(struct drm_encoder *encoder, int mode); +unsigned int radeon_audio_decode_dfs_div(unsigned int div); #endif diff --git a/drivers/gpu/drm/radeon/radeon_connectors.c b/drivers/gpu/drm/radeon/radeon_connectors.c index 340f3f549f29..30f00748ed37 100644 --- a/drivers/gpu/drm/radeon/radeon_connectors.c +++ b/drivers/gpu/drm/radeon/radeon_connectors.c @@ -1996,10 +1996,12 @@ radeon_add_atom_connector(struct drm_device *dev, rdev->mode_info.dither_property, RADEON_FMT_DITHER_DISABLE); - if (radeon_audio != 0) + if (radeon_audio != 0) { drm_object_attach_property(&radeon_connector->base.base, rdev->mode_info.audio_property, RADEON_AUDIO_AUTO); + radeon_connector->audio = RADEON_AUDIO_AUTO; + } if (ASIC_IS_DCE5(rdev)) drm_object_attach_property(&radeon_connector->base.base, rdev->mode_info.output_csc_property, @@ -2056,7 +2058,6 @@ radeon_add_atom_connector(struct drm_device *dev, RADEON_OUTPUT_CSC_BYPASS); /* no HPD on analog connectors */ radeon_connector->hpd.hpd = RADEON_HPD_NONE; - connector->polled = DRM_CONNECTOR_POLL_CONNECT; connector->interlace_allowed = true; connector->doublescan_allowed = true; break; @@ -2124,6 +2125,7 @@ radeon_add_atom_connector(struct drm_device *dev, drm_object_attach_property(&radeon_connector->base.base, rdev->mode_info.audio_property, RADEON_AUDIO_AUTO); + radeon_connector->audio = RADEON_AUDIO_AUTO; } if (connector_type == DRM_MODE_CONNECTOR_DVII) { radeon_connector->dac_load_detect = true; @@ -2179,6 +2181,7 @@ radeon_add_atom_connector(struct drm_device *dev, drm_object_attach_property(&radeon_connector->base.base, rdev->mode_info.audio_property, RADEON_AUDIO_AUTO); + radeon_connector->audio = RADEON_AUDIO_AUTO; } if (ASIC_IS_DCE5(rdev)) drm_object_attach_property(&radeon_connector->base.base, @@ -2231,6 +2234,7 @@ radeon_add_atom_connector(struct drm_device *dev, drm_object_attach_property(&radeon_connector->base.base, rdev->mode_info.audio_property, RADEON_AUDIO_AUTO); + radeon_connector->audio = RADEON_AUDIO_AUTO; } if (ASIC_IS_DCE5(rdev)) drm_object_attach_property(&radeon_connector->base.base, @@ -2303,8 +2307,10 @@ radeon_add_atom_connector(struct drm_device *dev, } if (radeon_connector->hpd.hpd == RADEON_HPD_NONE) { - if (i2c_bus->valid) - connector->polled = DRM_CONNECTOR_POLL_CONNECT; + if (i2c_bus->valid) { + connector->polled = DRM_CONNECTOR_POLL_CONNECT | + DRM_CONNECTOR_POLL_DISCONNECT; + } } else connector->polled = DRM_CONNECTOR_POLL_HPD; @@ -2380,7 +2386,6 @@ radeon_add_legacy_connector(struct drm_device *dev, 1); /* no HPD on analog connectors */ radeon_connector->hpd.hpd = RADEON_HPD_NONE; - connector->polled = DRM_CONNECTOR_POLL_CONNECT; connector->interlace_allowed = true; connector->doublescan_allowed = true; break; @@ -2465,10 +2470,13 @@ radeon_add_legacy_connector(struct drm_device *dev, } if (radeon_connector->hpd.hpd == RADEON_HPD_NONE) { - if (i2c_bus->valid) - connector->polled = DRM_CONNECTOR_POLL_CONNECT; + if (i2c_bus->valid) { + connector->polled = DRM_CONNECTOR_POLL_CONNECT | + DRM_CONNECTOR_POLL_DISCONNECT; + } } else connector->polled = DRM_CONNECTOR_POLL_HPD; + connector->display_info.subpixel_order = subpixel_order; drm_connector_register(connector); } diff --git a/drivers/gpu/drm/radeon/radeon_device.c b/drivers/gpu/drm/radeon/radeon_device.c index c566993a2ec3..e2dd5d19c32c 100644 --- a/drivers/gpu/drm/radeon/radeon_device.c +++ b/drivers/gpu/drm/radeon/radeon_device.c @@ -630,6 +630,23 @@ void radeon_gtt_location(struct radeon_device *rdev, struct radeon_mc *mc) /* * GPU helpers function. */ + +/** + * radeon_device_is_virtual - check if we are running is a virtual environment + * + * Check if the asic has been passed through to a VM (all asics). + * Used at driver startup. + * Returns true if virtual or false if not. + */ +static bool radeon_device_is_virtual(void) +{ +#ifdef CONFIG_X86 + return boot_cpu_has(X86_FEATURE_HYPERVISOR); +#else + return false; +#endif +} + /** * radeon_card_posted - check if the hw has already been initialized * @@ -643,6 +660,10 @@ bool radeon_card_posted(struct radeon_device *rdev) { uint32_t reg; + /* for pass through, always force asic_init */ + if (radeon_device_is_virtual()) + return false; + /* required for EFI mode on macbook2,1 which uses an r5xx asic */ if (efi_enabled(EFI_BOOT) && (rdev->pdev->subsystem_vendor == PCI_VENDOR_ID_APPLE) && diff --git a/drivers/gpu/drm/radeon/radeon_display.c b/drivers/gpu/drm/radeon/radeon_display.c index 1eca0acac016..3645b223aa37 100644 --- a/drivers/gpu/drm/radeon/radeon_display.c +++ b/drivers/gpu/drm/radeon/radeon_display.c @@ -403,7 +403,8 @@ static void radeon_flip_work_func(struct work_struct *__work) struct drm_crtc *crtc = &radeon_crtc->base; unsigned long flags; int r; - int vpos, hpos, stat, min_udelay; + int vpos, hpos, stat, min_udelay = 0; + unsigned repcnt = 4; struct drm_vblank_crtc *vblank = &crtc->dev->vblank[work->crtc_id]; down_read(&rdev->exclusive_lock); @@ -454,7 +455,7 @@ static void radeon_flip_work_func(struct work_struct *__work) * In practice this won't execute very often unless on very fast * machines because the time window for this to happen is very small. */ - for (;;) { + while (radeon_crtc->enabled && --repcnt) { /* GET_DISTANCE_TO_VBLANKSTART returns distance to real vblank * start in hpos, and to the "fudged earlier" vblank start in * vpos. @@ -470,12 +471,24 @@ static void radeon_flip_work_func(struct work_struct *__work) break; /* Sleep at least until estimated real start of hw vblank */ - spin_unlock_irqrestore(&crtc->dev->event_lock, flags); min_udelay = (-hpos + 1) * max(vblank->linedur_ns / 1000, 5); + if (min_udelay > vblank->framedur_ns / 2000) { + /* Don't wait ridiculously long - something is wrong */ + repcnt = 0; + break; + } + spin_unlock_irqrestore(&crtc->dev->event_lock, flags); usleep_range(min_udelay, 2 * min_udelay); spin_lock_irqsave(&crtc->dev->event_lock, flags); }; + if (!repcnt) + DRM_DEBUG_DRIVER("Delay problem on crtc %d: min_udelay %d, " + "framedur %d, linedur %d, stat %d, vpos %d, " + "hpos %d\n", work->crtc_id, min_udelay, + vblank->framedur_ns / 1000, + vblank->linedur_ns / 1000, stat, vpos, hpos); + /* do the flip (mmio) */ radeon_page_flip(rdev, radeon_crtc->crtc_id, work->base); diff --git a/drivers/gpu/drm/radeon/radeon_dp_auxch.c b/drivers/gpu/drm/radeon/radeon_dp_auxch.c index 3b0c229d7dcd..db64e0062689 100644 --- a/drivers/gpu/drm/radeon/radeon_dp_auxch.c +++ b/drivers/gpu/drm/radeon/radeon_dp_auxch.c @@ -105,7 +105,7 @@ radeon_dp_aux_transfer_native(struct drm_dp_aux *aux, struct drm_dp_aux_msg *msg tmp &= AUX_HPD_SEL(0x7); tmp |= AUX_HPD_SEL(chan->rec.hpd); - tmp |= AUX_EN | AUX_LS_READ_EN; + tmp |= AUX_EN | AUX_LS_READ_EN | AUX_HPD_DISCON(0x1); WREG32(AUX_CONTROL + aux_offset[instance], tmp); diff --git a/drivers/gpu/drm/radeon/radeon_dp_mst.c b/drivers/gpu/drm/radeon/radeon_dp_mst.c index 744f5c49c664..6dd39bdedb97 100644 --- a/drivers/gpu/drm/radeon/radeon_dp_mst.c +++ b/drivers/gpu/drm/radeon/radeon_dp_mst.c @@ -525,11 +525,9 @@ static bool radeon_mst_mode_fixup(struct drm_encoder *encoder, drm_mode_set_crtcinfo(adjusted_mode, 0); { struct radeon_connector_atom_dig *dig_connector; - dig_connector = mst_enc->connector->con_priv; dig_connector->dp_lane_count = drm_dp_max_lane_count(dig_connector->dpcd); - dig_connector->dp_clock = radeon_dp_get_max_link_rate(&mst_enc->connector->base, - dig_connector->dpcd); + dig_connector->dp_clock = drm_dp_max_link_rate(dig_connector->dpcd); DRM_DEBUG_KMS("dig clock %p %d %d\n", dig_connector, dig_connector->dp_lane_count, dig_connector->dp_clock); } diff --git a/drivers/gpu/drm/radeon/radeon_mode.h b/drivers/gpu/drm/radeon/radeon_mode.h index bba112628b47..7a0666ac4e23 100644 --- a/drivers/gpu/drm/radeon/radeon_mode.h +++ b/drivers/gpu/drm/radeon/radeon_mode.h @@ -757,8 +757,10 @@ extern u8 radeon_dp_getsinktype(struct radeon_connector *radeon_connector); extern bool radeon_dp_getdpcd(struct radeon_connector *radeon_connector); extern int radeon_dp_get_panel_mode(struct drm_encoder *encoder, struct drm_connector *connector); -int radeon_dp_get_max_link_rate(struct drm_connector *connector, - const u8 *dpcd); +extern int radeon_dp_get_dp_link_config(struct drm_connector *connector, + const u8 *dpcd, + unsigned pix_clock, + unsigned *dp_lanes, unsigned *dp_rate); extern void radeon_dp_set_rx_power_state(struct drm_connector *connector, u8 power_state); extern void radeon_dp_aux_init(struct radeon_connector *radeon_connector); diff --git a/drivers/gpu/drm/radeon/radeon_object.c b/drivers/gpu/drm/radeon/radeon_object.c index 84d45633d28c..fb6ad143873f 100644 --- a/drivers/gpu/drm/radeon/radeon_object.c +++ b/drivers/gpu/drm/radeon/radeon_object.c @@ -33,6 +33,7 @@ #include <linux/slab.h> #include <drm/drmP.h> #include <drm/radeon_drm.h> +#include <drm/drm_cache.h> #include "radeon.h" #include "radeon_trace.h" @@ -245,6 +246,12 @@ int radeon_bo_create(struct radeon_device *rdev, DRM_INFO_ONCE("Please enable CONFIG_MTRR and CONFIG_X86_PAT for " "better performance thanks to write-combining\n"); bo->flags &= ~(RADEON_GEM_GTT_WC | RADEON_GEM_GTT_UC); +#else + /* For architectures that don't support WC memory, + * mask out the WC flag from the BO + */ + if (!drm_arch_can_wc_memory()) + bo->flags &= ~RADEON_GEM_GTT_WC; #endif radeon_ttm_placement_from_domain(bo, domain); diff --git a/drivers/gpu/drm/radeon/radeon_pm.c b/drivers/gpu/drm/radeon/radeon_pm.c index 59abebd6b5dc..60ab31517153 100644 --- a/drivers/gpu/drm/radeon/radeon_pm.c +++ b/drivers/gpu/drm/radeon/radeon_pm.c @@ -1078,10 +1078,6 @@ force: /* update displays */ radeon_dpm_display_configuration_changed(rdev); - rdev->pm.dpm.current_active_crtcs = rdev->pm.dpm.new_active_crtcs; - rdev->pm.dpm.current_active_crtc_count = rdev->pm.dpm.new_active_crtc_count; - rdev->pm.dpm.single_display = single_display; - /* wait for the rings to drain */ for (i = 0; i < RADEON_NUM_RINGS; i++) { struct radeon_ring *ring = &rdev->ring[i]; @@ -1097,6 +1093,10 @@ force: radeon_dpm_post_set_power_state(rdev); + rdev->pm.dpm.current_active_crtcs = rdev->pm.dpm.new_active_crtcs; + rdev->pm.dpm.current_active_crtc_count = rdev->pm.dpm.new_active_crtc_count; + rdev->pm.dpm.single_display = single_display; + if (rdev->asic->dpm.force_performance_level) { if (rdev->pm.dpm.thermal_active) { enum radeon_dpm_forced_level level = rdev->pm.dpm.forced_level; diff --git a/drivers/gpu/drm/radeon/radeon_sa.c b/drivers/gpu/drm/radeon/radeon_sa.c index c507896aca45..197b157b73d0 100644 --- a/drivers/gpu/drm/radeon/radeon_sa.c +++ b/drivers/gpu/drm/radeon/radeon_sa.c @@ -349,8 +349,13 @@ int radeon_sa_bo_new(struct radeon_device *rdev, /* see if we can skip over some allocations */ } while (radeon_sa_bo_next_hole(sa_manager, fences, tries)); + for (i = 0; i < RADEON_NUM_RINGS; ++i) + radeon_fence_ref(fences[i]); + spin_unlock(&sa_manager->wq.lock); r = radeon_fence_wait_any(rdev, fences, false); + for (i = 0; i < RADEON_NUM_RINGS; ++i) + radeon_fence_unref(&fences[i]); spin_lock(&sa_manager->wq.lock); /* if we have nothing to wait for block */ if (r == -ENOENT) { diff --git a/drivers/gpu/drm/radeon/radeon_ttm.c b/drivers/gpu/drm/radeon/radeon_ttm.c index e34307459e50..35310336dd0a 100644 --- a/drivers/gpu/drm/radeon/radeon_ttm.c +++ b/drivers/gpu/drm/radeon/radeon_ttm.c @@ -235,6 +235,8 @@ static int radeon_verify_access(struct ttm_buffer_object *bo, struct file *filp) { struct radeon_bo *rbo = container_of(bo, struct radeon_bo, tbo); + if (radeon_ttm_tt_has_userptr(bo->ttm)) + return -EPERM; return drm_vma_node_verify_access(&rbo->gem_base.vma_node, filp); } @@ -261,8 +263,8 @@ static int radeon_move_blit(struct ttm_buffer_object *bo, rdev = radeon_get_rdev(bo->bdev); ridx = radeon_copy_ring_index(rdev); - old_start = old_mem->start << PAGE_SHIFT; - new_start = new_mem->start << PAGE_SHIFT; + old_start = (u64)old_mem->start << PAGE_SHIFT; + new_start = (u64)new_mem->start << PAGE_SHIFT; switch (old_mem->mem_type) { case TTM_PL_VRAM: @@ -758,7 +760,7 @@ static int radeon_ttm_tt_populate(struct ttm_tt *ttm) 0, PAGE_SIZE, PCI_DMA_BIDIRECTIONAL); if (pci_dma_mapping_error(rdev->pdev, gtt->ttm.dma_address[i])) { - while (--i) { + while (i--) { pci_unmap_page(rdev->pdev, gtt->ttm.dma_address[i], PAGE_SIZE, PCI_DMA_BIDIRECTIONAL); gtt->ttm.dma_address[i] = 0; diff --git a/drivers/gpu/drm/radeon/radeon_vm.c b/drivers/gpu/drm/radeon/radeon_vm.c index 48d97c040f49..3979632b9225 100644 --- a/drivers/gpu/drm/radeon/radeon_vm.c +++ b/drivers/gpu/drm/radeon/radeon_vm.c @@ -455,15 +455,15 @@ int radeon_vm_bo_set_addr(struct radeon_device *rdev, if (soffset) { /* make sure object fit at this offset */ - eoffset = soffset + size; + eoffset = soffset + size - 1; if (soffset >= eoffset) { r = -EINVAL; goto error_unreserve; } last_pfn = eoffset / RADEON_GPU_PAGE_SIZE; - if (last_pfn > rdev->vm_manager.max_pfn) { - dev_err(rdev->dev, "va above limit (0x%08X > 0x%08X)\n", + if (last_pfn >= rdev->vm_manager.max_pfn) { + dev_err(rdev->dev, "va above limit (0x%08X >= 0x%08X)\n", last_pfn, rdev->vm_manager.max_pfn); r = -EINVAL; goto error_unreserve; @@ -478,7 +478,7 @@ int radeon_vm_bo_set_addr(struct radeon_device *rdev, eoffset /= RADEON_GPU_PAGE_SIZE; if (soffset || eoffset) { struct interval_tree_node *it; - it = interval_tree_iter_first(&vm->va, soffset, eoffset - 1); + it = interval_tree_iter_first(&vm->va, soffset, eoffset); if (it && it != &bo_va->it) { struct radeon_bo_va *tmp; tmp = container_of(it, struct radeon_bo_va, it); @@ -518,7 +518,7 @@ int radeon_vm_bo_set_addr(struct radeon_device *rdev, if (soffset || eoffset) { spin_lock(&vm->status_lock); bo_va->it.start = soffset; - bo_va->it.last = eoffset - 1; + bo_va->it.last = eoffset; list_add(&bo_va->vm_status, &vm->cleared); spin_unlock(&vm->status_lock); interval_tree_insert(&bo_va->it, &vm->va); @@ -888,7 +888,7 @@ static void radeon_vm_fence_pts(struct radeon_vm *vm, unsigned i; start >>= radeon_vm_block_size; - end >>= radeon_vm_block_size; + end = (end - 1) >> radeon_vm_block_size; for (i = start; i <= end; ++i) radeon_bo_fence(vm->page_tables[i].bo, fence, true); diff --git a/drivers/gpu/drm/radeon/si_dpm.c b/drivers/gpu/drm/radeon/si_dpm.c index a82b891ae1fe..3aaa07dafc00 100644 --- a/drivers/gpu/drm/radeon/si_dpm.c +++ b/drivers/gpu/drm/radeon/si_dpm.c @@ -2926,9 +2926,12 @@ static struct si_dpm_quirk si_dpm_quirk_list[] = { /* PITCAIRN - https://bugs.freedesktop.org/show_bug.cgi?id=76490 */ { PCI_VENDOR_ID_ATI, 0x6810, 0x1462, 0x3036, 0, 120000 }, { PCI_VENDOR_ID_ATI, 0x6811, 0x174b, 0xe271, 0, 120000 }, + { PCI_VENDOR_ID_ATI, 0x6811, 0x174b, 0x2015, 0, 120000 }, { PCI_VENDOR_ID_ATI, 0x6810, 0x174b, 0xe271, 85000, 90000 }, { PCI_VENDOR_ID_ATI, 0x6811, 0x1462, 0x2015, 0, 120000 }, { PCI_VENDOR_ID_ATI, 0x6811, 0x1043, 0x2015, 0, 120000 }, + { PCI_VENDOR_ID_ATI, 0x6811, 0x148c, 0x2015, 0, 120000 }, + { PCI_VENDOR_ID_ATI, 0x6810, 0x1682, 0x9275, 0, 120000 }, { 0, 0, 0, 0 }, }; @@ -3008,6 +3011,16 @@ static void si_apply_state_adjust_rules(struct radeon_device *rdev, } ++p; } + /* limit mclk on all R7 370 parts for stability */ + if (rdev->pdev->device == 0x6811 && + rdev->pdev->revision == 0x81) + max_mclk = 120000; + /* limit sclk/mclk on Jet parts for stability */ + if (rdev->pdev->device == 0x6665 && + rdev->pdev->revision == 0xc3) { + max_sclk = 75000; + max_mclk = 80000; + } if (rps->vce_active) { rps->evclk = rdev->pm.dpm.vce_states[rdev->pm.dpm.vce_level].evclk; diff --git a/drivers/gpu/drm/radeon/sid.h b/drivers/gpu/drm/radeon/sid.h index 4c4a7218a3bd..d1a7b58dd291 100644 --- a/drivers/gpu/drm/radeon/sid.h +++ b/drivers/gpu/drm/radeon/sid.h @@ -915,6 +915,11 @@ #define DCCG_AUDIO_DTO1_PHASE 0x05c0 #define DCCG_AUDIO_DTO1_MODULE 0x05c4 +#define DENTIST_DISPCLK_CNTL 0x0490 +# define DENTIST_DPREFCLK_WDIVIDER(x) (((x) & 0x7f) << 24) +# define DENTIST_DPREFCLK_WDIVIDER_MASK (0x7f << 24) +# define DENTIST_DPREFCLK_WDIVIDER_SHIFT 24 + #define AFMT_AUDIO_SRC_CONTROL 0x713c #define AFMT_AUDIO_SRC_SELECT(x) (((x) & 7) << 0) /* AFMT_AUDIO_SRC_SELECT diff --git a/drivers/gpu/drm/radeon/vce_v1_0.c b/drivers/gpu/drm/radeon/vce_v1_0.c index 07a0d378e122..a01efe39a820 100644 --- a/drivers/gpu/drm/radeon/vce_v1_0.c +++ b/drivers/gpu/drm/radeon/vce_v1_0.c @@ -178,12 +178,12 @@ int vce_v1_0_load_fw(struct radeon_device *rdev, uint32_t *data) return -EINVAL; } - for (i = 0; i < sign->num; ++i) { - if (sign->val[i].chip_id == chip_id) + for (i = 0; i < le32_to_cpu(sign->num); ++i) { + if (le32_to_cpu(sign->val[i].chip_id) == chip_id) break; } - if (i == sign->num) + if (i == le32_to_cpu(sign->num)) return -EINVAL; data += (256 - 64) / 4; @@ -191,18 +191,18 @@ int vce_v1_0_load_fw(struct radeon_device *rdev, uint32_t *data) data[1] = sign->val[i].nonce[1]; data[2] = sign->val[i].nonce[2]; data[3] = sign->val[i].nonce[3]; - data[4] = sign->len + 64; + data[4] = cpu_to_le32(le32_to_cpu(sign->len) + 64); memset(&data[5], 0, 44); memcpy(&data[16], &sign[1], rdev->vce_fw->size - sizeof(*sign)); - data += data[4] / 4; + data += le32_to_cpu(data[4]) / 4; data[0] = sign->val[i].sigval[0]; data[1] = sign->val[i].sigval[1]; data[2] = sign->val[i].sigval[2]; data[3] = sign->val[i].sigval[3]; - rdev->vce.keyselect = sign->val[i].keyselect; + rdev->vce.keyselect = le32_to_cpu(sign->val[i].keyselect); return 0; } diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c index 745e996d2dbc..4ae8b56b1847 100644 --- a/drivers/gpu/drm/ttm/ttm_bo.c +++ b/drivers/gpu/drm/ttm/ttm_bo.c @@ -1004,9 +1004,9 @@ 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; @@ -1038,6 +1038,7 @@ 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/udl/udl_fb.c b/drivers/gpu/drm/udl/udl_fb.c index 62c7b1dafaa4..73e41a8613da 100644 --- a/drivers/gpu/drm/udl/udl_fb.c +++ b/drivers/gpu/drm/udl/udl_fb.c @@ -539,7 +539,7 @@ static int udlfb_create(struct drm_fb_helper *helper, out_destroy_fbi: drm_fb_helper_release_fbi(helper); out_gfree: - drm_gem_object_unreference(&ufbdev->ufb.obj->base); + drm_gem_object_unreference_unlocked(&ufbdev->ufb.obj->base); out: return ret; } diff --git a/drivers/gpu/drm/udl/udl_gem.c b/drivers/gpu/drm/udl/udl_gem.c index 2a0a784ab6ee..d7528e0d8442 100644 --- a/drivers/gpu/drm/udl/udl_gem.c +++ b/drivers/gpu/drm/udl/udl_gem.c @@ -52,7 +52,7 @@ udl_gem_create(struct drm_file *file, return ret; } - drm_gem_object_unreference(&obj->base); + drm_gem_object_unreference_unlocked(&obj->base); *handle_p = handle; return 0; } diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_cmdbuf.c b/drivers/gpu/drm/vmwgfx/vmwgfx_cmdbuf.c index 6377e8151000..67cebb23c940 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_cmdbuf.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_cmdbuf.c @@ -247,7 +247,7 @@ static void __vmw_cmdbuf_header_free(struct vmw_cmdbuf_header *header) { struct vmw_cmdbuf_man *man = header->man; - BUG_ON(!spin_is_locked(&man->lock)); + lockdep_assert_held_once(&man->lock); if (header->inline_space) { vmw_cmdbuf_header_inline_free(header); diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_dmabuf.c b/drivers/gpu/drm/vmwgfx/vmwgfx_dmabuf.c index 299925a1f6c6..eadc981ee79a 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 c49812b80dd0..f3f31f995878 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c @@ -25,6 +25,7 @@ * **************************************************************************/ #include <linux/module.h> +#include <linux/console.h> #include <drm/drmP.h> #include "vmwgfx_drv.h" @@ -226,6 +227,7 @@ 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 *); @@ -242,6 +244,8 @@ 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) @@ -651,6 +655,8 @@ 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); @@ -697,6 +703,13 @@ 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, @@ -1538,6 +1551,12 @@ static int vmw_probe(struct pci_dev *pdev, const struct pci_device_id *ent) static int __init vmwgfx_init(void) { int ret; + +#ifdef CONFIG_VGA_CONSOLE + if (vgacon_text_force()) + return -EINVAL; +#endif + ret = drm_pci_init(&driver, &vmw_pci_driver); if (ret) DRM_ERROR("Failed initializing DRM.\n"); diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h index 469cdd520615..2e94fe27b3f6 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h @@ -387,6 +387,7 @@ 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_execbuf.c b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c index 5da5de0cb522..4948c1529836 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c @@ -3273,19 +3273,19 @@ static const struct vmw_cmd_entry vmw_cmd_entries[SVGA_3D_CMD_MAX] = { &vmw_cmd_dx_cid_check, true, false, true), VMW_CMD_DEF(SVGA_3D_CMD_DX_DEFINE_QUERY, &vmw_cmd_dx_define_query, true, false, true), - VMW_CMD_DEF(SVGA_3D_CMD_DX_DESTROY_QUERY, &vmw_cmd_ok, + VMW_CMD_DEF(SVGA_3D_CMD_DX_DESTROY_QUERY, &vmw_cmd_dx_cid_check, true, false, true), VMW_CMD_DEF(SVGA_3D_CMD_DX_BIND_QUERY, &vmw_cmd_dx_bind_query, true, false, true), VMW_CMD_DEF(SVGA_3D_CMD_DX_SET_QUERY_OFFSET, - &vmw_cmd_ok, true, false, true), - VMW_CMD_DEF(SVGA_3D_CMD_DX_BEGIN_QUERY, &vmw_cmd_ok, + &vmw_cmd_dx_cid_check, true, false, true), + VMW_CMD_DEF(SVGA_3D_CMD_DX_BEGIN_QUERY, &vmw_cmd_dx_cid_check, true, false, true), - VMW_CMD_DEF(SVGA_3D_CMD_DX_END_QUERY, &vmw_cmd_ok, + VMW_CMD_DEF(SVGA_3D_CMD_DX_END_QUERY, &vmw_cmd_dx_cid_check, true, false, true), VMW_CMD_DEF(SVGA_3D_CMD_DX_READBACK_QUERY, &vmw_cmd_invalid, true, false, true), - VMW_CMD_DEF(SVGA_3D_CMD_DX_SET_PREDICATION, &vmw_cmd_invalid, + VMW_CMD_DEF(SVGA_3D_CMD_DX_SET_PREDICATION, &vmw_cmd_dx_cid_check, true, false, true), VMW_CMD_DEF(SVGA_3D_CMD_DX_SET_VIEWPORTS, &vmw_cmd_dx_cid_check, true, false, true), diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_fb.c b/drivers/gpu/drm/vmwgfx/vmwgfx_fb.c index 3b1faf7862a5..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; } @@ -573,9 +551,9 @@ static int vmw_fb_set_par(struct fb_info *info) mode = old_mode; old_mode = NULL; } else if (!vmw_kms_validate_mode_vram(vmw_priv, - mode->hdisplay * - (var->bits_per_pixel + 7) / 8, - mode->vdisplay)) { + mode->hdisplay * + DIV_ROUND_UP(var->bits_per_pixel, 8), + mode->vdisplay)) { drm_mode_destroy(vmw_priv->dev, mode); return -EINVAL; } @@ -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 9b4bb9e74d73..060e5c6f4446 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c @@ -763,21 +763,25 @@ static int vmw_create_dmabuf_proxy(struct drm_device *dev, uint32_t format; struct drm_vmw_size content_base_size; struct vmw_resource *res; + unsigned int bytes_pp; int ret; switch (mode_cmd->depth) { case 32: case 24: format = SVGA3D_X8R8G8B8; + bytes_pp = 4; break; case 16: case 15: format = SVGA3D_R5G6B5; + bytes_pp = 2; break; case 8: format = SVGA3D_P8; + bytes_pp = 1; break; default: @@ -785,7 +789,7 @@ static int vmw_create_dmabuf_proxy(struct drm_device *dev, return -EINVAL; } - content_base_size.width = mode_cmd->width; + content_base_size.width = mode_cmd->pitch / bytes_pp; content_base_size.height = mode_cmd->height; content_base_size.depth = 1; @@ -1534,14 +1538,10 @@ 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); |