diff options
Diffstat (limited to 'drivers/gpu/drm/radeon')
23 files changed, 699 insertions, 322 deletions
diff --git a/drivers/gpu/drm/radeon/atombios_crtc.c b/drivers/gpu/drm/radeon/atombios_crtc.c index 96184d02c8d9..3bce0299f64a 100644 --- a/drivers/gpu/drm/radeon/atombios_crtc.c +++ b/drivers/gpu/drm/radeon/atombios_crtc.c @@ -1690,41 +1690,49 @@ static int radeon_atom_pick_pll(struct drm_crtc *crtc) } /* all other cases */ pll_in_use = radeon_get_pll_use_mask(crtc); - if (!(pll_in_use & (1 << ATOM_PPLL2))) - return ATOM_PPLL2; if (!(pll_in_use & (1 << ATOM_PPLL1))) return ATOM_PPLL1; + if (!(pll_in_use & (1 << ATOM_PPLL2))) + return ATOM_PPLL2; DRM_ERROR("unable to allocate a PPLL\n"); return ATOM_PPLL_INVALID; - } else { - if (ASIC_IS_AVIVO(rdev)) { - /* in DP mode, the DP ref clock can come from either PPLL - * depending on the asic: - * DCE3: PPLL1 or PPLL2 - */ - if (ENCODER_MODE_IS_DP(atombios_get_encoder_mode(radeon_crtc->encoder))) { - /* use the same PPLL for all DP monitors */ - pll = radeon_get_shared_dp_ppll(crtc); - if (pll != ATOM_PPLL_INVALID) - return pll; - } else { - /* use the same PPLL for all monitors with the same clock */ - pll = radeon_get_shared_nondp_ppll(crtc); - if (pll != ATOM_PPLL_INVALID) - return pll; - } - /* all other cases */ - pll_in_use = radeon_get_pll_use_mask(crtc); + } else if (ASIC_IS_AVIVO(rdev)) { + /* in DP mode, the DP ref clock can come from either PPLL + * depending on the asic: + * DCE3: PPLL1 or PPLL2 + */ + if (ENCODER_MODE_IS_DP(atombios_get_encoder_mode(radeon_crtc->encoder))) { + /* use the same PPLL for all DP monitors */ + pll = radeon_get_shared_dp_ppll(crtc); + if (pll != ATOM_PPLL_INVALID) + return pll; + } else { + /* use the same PPLL for all monitors with the same clock */ + pll = radeon_get_shared_nondp_ppll(crtc); + if (pll != ATOM_PPLL_INVALID) + return pll; + } + /* all other cases */ + pll_in_use = radeon_get_pll_use_mask(crtc); + /* the order shouldn't matter here, but we probably + * need this until we have atomic modeset + */ + if (rdev->flags & RADEON_IS_IGP) { + if (!(pll_in_use & (1 << ATOM_PPLL1))) + return ATOM_PPLL1; + if (!(pll_in_use & (1 << ATOM_PPLL2))) + return ATOM_PPLL2; + } else { if (!(pll_in_use & (1 << ATOM_PPLL2))) return ATOM_PPLL2; if (!(pll_in_use & (1 << ATOM_PPLL1))) return ATOM_PPLL1; - DRM_ERROR("unable to allocate a PPLL\n"); - return ATOM_PPLL_INVALID; - } else { - /* on pre-R5xx asics, the crtc to pll mapping is hardcoded */ - return radeon_crtc->crtc_id; } + DRM_ERROR("unable to allocate a PPLL\n"); + return ATOM_PPLL_INVALID; + } else { + /* on pre-R5xx asics, the crtc to pll mapping is hardcoded */ + return radeon_crtc->crtc_id; } } diff --git a/drivers/gpu/drm/radeon/atombios_encoders.c b/drivers/gpu/drm/radeon/atombios_encoders.c index 49cbb3795a10..010bae19554a 100644 --- a/drivers/gpu/drm/radeon/atombios_encoders.c +++ b/drivers/gpu/drm/radeon/atombios_encoders.c @@ -184,6 +184,7 @@ void radeon_atom_backlight_init(struct radeon_encoder *radeon_encoder, struct radeon_backlight_privdata *pdata; struct radeon_encoder_atom_dig *dig; u8 backlight_level; + char bl_name[16]; if (!radeon_encoder->enc_priv) return; @@ -203,7 +204,9 @@ void radeon_atom_backlight_init(struct radeon_encoder *radeon_encoder, memset(&props, 0, sizeof(props)); props.max_brightness = RADEON_MAX_BL_LEVEL; props.type = BACKLIGHT_RAW; - bd = backlight_device_register("radeon_bl", &drm_connector->kdev, + snprintf(bl_name, sizeof(bl_name), + "radeon_bl%d", dev->primary->index); + bd = backlight_device_register(bl_name, &drm_connector->kdev, pdata, &radeon_atom_backlight_ops, &props); if (IS_ERR(bd)) { DRM_ERROR("Backlight registration failed\n"); @@ -1622,7 +1625,7 @@ radeon_atom_encoder_dpms_dig(struct drm_encoder *encoder, int mode) atombios_dig_transmitter_setup(encoder, ATOM_TRANSMITTER_ACTION_SETUP, 0, 0); atombios_dig_transmitter_setup(encoder, ATOM_TRANSMITTER_ACTION_ENABLE, 0, 0); /* some early dce3.2 boards have a bug in their transmitter control table */ - if ((rdev->family != CHIP_RV710) || (rdev->family != CHIP_RV730)) + if ((rdev->family != CHIP_RV710) && (rdev->family != CHIP_RV730)) atombios_dig_transmitter_setup(encoder, ATOM_TRANSMITTER_ACTION_ENABLE_OUTPUT, 0, 0); } if (ENCODER_MODE_IS_DP(atombios_get_encoder_mode(encoder)) && connector) { diff --git a/drivers/gpu/drm/radeon/evergreen.c b/drivers/gpu/drm/radeon/evergreen.c index a1f49c5fd74b..af31f829f4a8 100644 --- a/drivers/gpu/drm/radeon/evergreen.c +++ b/drivers/gpu/drm/radeon/evergreen.c @@ -1372,7 +1372,7 @@ void evergreen_mc_resume(struct radeon_device *rdev, struct evergreen_mc_save *s WREG32(BIF_FB_EN, FB_READ_EN | FB_WRITE_EN); for (i = 0; i < rdev->num_crtc; i++) { - if (save->crtc_enabled) { + if (save->crtc_enabled[i]) { if (ASIC_IS_DCE6(rdev)) { tmp = RREG32(EVERGREEN_CRTC_BLANK_CONTROL + crtc_offsets[i]); tmp |= EVERGREEN_CRTC_BLANK_DATA_EN; @@ -3431,9 +3431,14 @@ void evergreen_pcie_gen2_enable(struct radeon_device *rdev) if (!(mask & DRM_PCIE_SPEED_50)) return; + speed_cntl = RREG32_PCIE_P(PCIE_LC_SPEED_CNTL); + if (speed_cntl & LC_CURRENT_DATA_RATE) { + DRM_INFO("PCIE gen 2 link speeds already enabled\n"); + return; + } + DRM_INFO("enabling PCIE gen 2 link speeds, disable with radeon.pcie_gen2=0\n"); - speed_cntl = RREG32_PCIE_P(PCIE_LC_SPEED_CNTL); if ((speed_cntl & LC_OTHER_SIDE_EVER_SENT_GEN2) || (speed_cntl & LC_OTHER_SIDE_SUPPORTS_GEN2)) { diff --git a/drivers/gpu/drm/radeon/evergreen_cs.c b/drivers/gpu/drm/radeon/evergreen_cs.c index 573ed1bc6cf7..c042e497e450 100644 --- a/drivers/gpu/drm/radeon/evergreen_cs.c +++ b/drivers/gpu/drm/radeon/evergreen_cs.c @@ -264,7 +264,7 @@ static int evergreen_surface_check_2d(struct radeon_cs_parser *p, /* macro tile width & height */ palign = (8 * surf->bankw * track->npipes) * surf->mtilea; halign = (8 * surf->bankh * surf->nbanks) / surf->mtilea; - mtileb = (palign / 8) * (halign / 8) * tileb;; + mtileb = (palign / 8) * (halign / 8) * tileb; mtile_pr = surf->nbx / palign; mtile_ps = (mtile_pr * surf->nby) / halign; surf->layer_size = mtile_ps * mtileb * slice_pt; @@ -2725,6 +2725,9 @@ static bool evergreen_vm_reg_valid(u32 reg) /* check config regs */ switch (reg) { case GRBM_GFX_INDEX: + case CP_STRMOUT_CNTL: + case CP_COHER_CNTL: + case CP_COHER_SIZE: case VGT_VTX_VECT_EJECT_REG: case VGT_CACHE_INVALIDATION: case VGT_GS_VERTEX_REUSE: @@ -2829,6 +2832,7 @@ static bool evergreen_vm_reg_valid(u32 reg) case CAYMAN_SQ_EX_ALLOC_TABLE_SLOTS: return true; default: + DRM_ERROR("Invalid register 0x%x in CS\n", reg); return false; } } diff --git a/drivers/gpu/drm/radeon/evergreend.h b/drivers/gpu/drm/radeon/evergreend.h index df542f1a5dfb..2bc0f6a1b428 100644 --- a/drivers/gpu/drm/radeon/evergreend.h +++ b/drivers/gpu/drm/radeon/evergreend.h @@ -91,6 +91,10 @@ #define FB_READ_EN (1 << 0) #define FB_WRITE_EN (1 << 1) +#define CP_STRMOUT_CNTL 0x84FC + +#define CP_COHER_CNTL 0x85F0 +#define CP_COHER_SIZE 0x85F4 #define CP_COHER_BASE 0x85F8 #define CP_STALLED_STAT1 0x8674 #define CP_STALLED_STAT2 0x8678 diff --git a/drivers/gpu/drm/radeon/ni.c b/drivers/gpu/drm/radeon/ni.c index 8bcb554ea0c5..81e6a568c29d 100644 --- a/drivers/gpu/drm/radeon/ni.c +++ b/drivers/gpu/drm/radeon/ni.c @@ -770,9 +770,13 @@ static int cayman_pcie_gart_enable(struct radeon_device *rdev) WREG32(0x15DC, 0); /* empty context1-7 */ + /* Assign the pt base to something valid for now; the pts used for + * the VMs are determined by the application and setup and assigned + * on the fly in the vm part of radeon_gart.c + */ for (i = 1; i < 8; i++) { WREG32(VM_CONTEXT0_PAGE_TABLE_START_ADDR + (i << 2), 0); - WREG32(VM_CONTEXT0_PAGE_TABLE_END_ADDR + (i << 2), 0); + WREG32(VM_CONTEXT0_PAGE_TABLE_END_ADDR + (i << 2), rdev->vm_manager.max_pfn); WREG32(VM_CONTEXT0_PAGE_TABLE_BASE_ADDR + (i << 2), rdev->gart.table_addr >> 12); } @@ -1534,26 +1538,31 @@ void cayman_vm_set_page(struct radeon_device *rdev, uint64_t pe, { struct radeon_ring *ring = &rdev->ring[rdev->asic->vm.pt_ring_index]; uint32_t r600_flags = cayman_vm_page_flags(rdev, flags); - int i; - radeon_ring_write(ring, PACKET3(PACKET3_ME_WRITE, 1 + count * 2)); - radeon_ring_write(ring, pe); - radeon_ring_write(ring, upper_32_bits(pe) & 0xff); - for (i = 0; i < count; ++i) { - uint64_t value = 0; - if (flags & RADEON_VM_PAGE_SYSTEM) { - value = radeon_vm_map_gart(rdev, addr); - value &= 0xFFFFFFFFFFFFF000ULL; - addr += incr; - - } else if (flags & RADEON_VM_PAGE_VALID) { - value = addr; - addr += incr; - } + while (count) { + unsigned ndw = 1 + count * 2; + if (ndw > 0x3FFF) + ndw = 0x3FFF; + + radeon_ring_write(ring, PACKET3(PACKET3_ME_WRITE, ndw)); + radeon_ring_write(ring, pe); + radeon_ring_write(ring, upper_32_bits(pe) & 0xff); + for (; ndw > 1; ndw -= 2, --count, pe += 8) { + uint64_t value = 0; + if (flags & RADEON_VM_PAGE_SYSTEM) { + value = radeon_vm_map_gart(rdev, addr); + value &= 0xFFFFFFFFFFFFF000ULL; + addr += incr; + + } else if (flags & RADEON_VM_PAGE_VALID) { + value = addr; + addr += incr; + } - value |= r600_flags; - radeon_ring_write(ring, value); - radeon_ring_write(ring, upper_32_bits(value)); + value |= r600_flags; + radeon_ring_write(ring, value); + radeon_ring_write(ring, upper_32_bits(value)); + } } } @@ -1572,12 +1581,6 @@ void cayman_vm_flush(struct radeon_device *rdev, int ridx, struct radeon_vm *vm) if (vm == NULL) return; - radeon_ring_write(ring, PACKET0(VM_CONTEXT0_PAGE_TABLE_START_ADDR + (vm->id << 2), 0)); - radeon_ring_write(ring, 0); - - radeon_ring_write(ring, PACKET0(VM_CONTEXT0_PAGE_TABLE_END_ADDR + (vm->id << 2), 0)); - radeon_ring_write(ring, vm->last_pfn); - radeon_ring_write(ring, PACKET0(VM_CONTEXT0_PAGE_TABLE_BASE_ADDR + (vm->id << 2), 0)); radeon_ring_write(ring, vm->pd_gpu_addr >> 12); @@ -1588,4 +1591,8 @@ void cayman_vm_flush(struct radeon_device *rdev, int ridx, struct radeon_vm *vm) /* bits 0-7 are the VM contexts0-7 */ radeon_ring_write(ring, PACKET0(VM_INVALIDATE_REQUEST, 0)); radeon_ring_write(ring, 1 << vm->id); + + /* sync PFP to ME, otherwise we might get invalid PFP reads */ + radeon_ring_write(ring, PACKET3(PACKET3_PFP_SYNC_ME, 0)); + radeon_ring_write(ring, 0x0); } diff --git a/drivers/gpu/drm/radeon/nid.h b/drivers/gpu/drm/radeon/nid.h index 2423d1b5d385..cbef6815907a 100644 --- a/drivers/gpu/drm/radeon/nid.h +++ b/drivers/gpu/drm/radeon/nid.h @@ -502,6 +502,7 @@ #define PACKET3_MPEG_INDEX 0x3A #define PACKET3_WAIT_REG_MEM 0x3C #define PACKET3_MEM_WRITE 0x3D +#define PACKET3_PFP_SYNC_ME 0x42 #define PACKET3_SURFACE_SYNC 0x43 # define PACKET3_CB0_DEST_BASE_ENA (1 << 6) # define PACKET3_CB1_DEST_BASE_ENA (1 << 7) diff --git a/drivers/gpu/drm/radeon/r600.c b/drivers/gpu/drm/radeon/r600.c index 70c800ff6190..cda280d157da 100644 --- a/drivers/gpu/drm/radeon/r600.c +++ b/drivers/gpu/drm/radeon/r600.c @@ -3703,6 +3703,12 @@ static void r600_pcie_gen2_enable(struct radeon_device *rdev) if (!(mask & DRM_PCIE_SPEED_50)) return; + speed_cntl = RREG32_PCIE_P(PCIE_LC_SPEED_CNTL); + if (speed_cntl & LC_CURRENT_DATA_RATE) { + DRM_INFO("PCIE gen 2 link speeds already enabled\n"); + return; + } + DRM_INFO("enabling PCIE gen 2 link speeds, disable with radeon.pcie_gen2=0\n"); /* 55 nm r6xx asics */ diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h index b04c06444d8b..8c42d54c2e26 100644 --- a/drivers/gpu/drm/radeon/radeon.h +++ b/drivers/gpu/drm/radeon/radeon.h @@ -663,9 +663,14 @@ struct radeon_vm { struct list_head list; struct list_head va; unsigned id; - unsigned last_pfn; - u64 pd_gpu_addr; - struct radeon_sa_bo *sa_bo; + + /* contains the page directory */ + struct radeon_sa_bo *page_directory; + uint64_t pd_gpu_addr; + + /* array of page tables, one for each page directory entry */ + struct radeon_sa_bo **page_tables; + struct mutex mutex; /* last fence for cs using this vm */ struct radeon_fence *fence; @@ -1843,9 +1848,10 @@ extern void radeon_ttm_set_active_vram_size(struct radeon_device *rdev, u64 size */ int radeon_vm_manager_init(struct radeon_device *rdev); void radeon_vm_manager_fini(struct radeon_device *rdev); -int radeon_vm_init(struct radeon_device *rdev, struct radeon_vm *vm); +void radeon_vm_init(struct radeon_device *rdev, struct radeon_vm *vm); void radeon_vm_fini(struct radeon_device *rdev, struct radeon_vm *vm); int radeon_vm_alloc_pt(struct radeon_device *rdev, struct radeon_vm *vm); +void radeon_vm_add_to_lru(struct radeon_device *rdev, struct radeon_vm *vm); struct radeon_fence *radeon_vm_grab_id(struct radeon_device *rdev, struct radeon_vm *vm, int ring); void radeon_vm_fence(struct radeon_device *rdev, diff --git a/drivers/gpu/drm/radeon/radeon_acpi.c b/drivers/gpu/drm/radeon/radeon_acpi.c index b0a5688c67f8..196d28d99570 100644 --- a/drivers/gpu/drm/radeon/radeon_acpi.c +++ b/drivers/gpu/drm/radeon/radeon_acpi.c @@ -201,7 +201,7 @@ static int radeon_atif_verify_interface(acpi_handle handle, size = *(u16 *) info->buffer.pointer; if (size < 12) { - DRM_INFO("ATIF buffer is too small: %lu\n", size); + DRM_INFO("ATIF buffer is too small: %zu\n", size); err = -EINVAL; goto out; } @@ -370,6 +370,7 @@ int radeon_atif_handler(struct radeon_device *rdev, radeon_set_backlight_level(rdev, enc, req.backlight_level); +#if defined(CONFIG_BACKLIGHT_CLASS_DEVICE) || defined(CONFIG_BACKLIGHT_CLASS_DEVICE_MODULE) if (rdev->is_atom_bios) { struct radeon_encoder_atom_dig *dig = enc->enc_priv; backlight_force_update(dig->bl_dev, @@ -379,6 +380,7 @@ int radeon_atif_handler(struct radeon_device *rdev, backlight_force_update(dig->bl_dev, BACKLIGHT_UPDATE_HOTKEY); } +#endif } } /* TODO: check other events */ @@ -485,7 +487,7 @@ static int radeon_atcs_verify_interface(acpi_handle handle, size = *(u16 *) info->buffer.pointer; if (size < 8) { - DRM_INFO("ATCS buffer is too small: %lu\n", size); + DRM_INFO("ATCS buffer is too small: %zu\n", size); err = -EINVAL; goto out; } diff --git a/drivers/gpu/drm/radeon/radeon_atpx_handler.c b/drivers/gpu/drm/radeon/radeon_atpx_handler.c index 582e99449c12..15f5ded65e0c 100644 --- a/drivers/gpu/drm/radeon/radeon_atpx_handler.c +++ b/drivers/gpu/drm/radeon/radeon_atpx_handler.c @@ -87,7 +87,7 @@ static union acpi_object *radeon_atpx_call(acpi_handle handle, int function, atpx_arg_elements[1].integer.value = 0; } - status = acpi_evaluate_object(handle, "ATPX", &atpx_arg, &buffer); + status = acpi_evaluate_object(handle, NULL, &atpx_arg, &buffer); /* Fail only if calling the method fails and ATPX is supported */ if (ACPI_FAILURE(status) && status != AE_NOT_FOUND) { @@ -148,7 +148,7 @@ static int radeon_atpx_verify_interface(struct radeon_atpx *atpx) size = *(u16 *) info->buffer.pointer; if (size < 8) { - printk("ATPX buffer is too small: %lu\n", size); + printk("ATPX buffer is too small: %zu\n", size); err = -EINVAL; goto out; } @@ -352,9 +352,9 @@ static int radeon_atpx_switchto(enum vga_switcheroo_client_id id) } /** - * radeon_atpx_switchto - switch to the requested GPU + * radeon_atpx_power_state - power down/up the requested GPU * - * @id: GPU to switch to + * @id: GPU to power down/up * @state: requested power state (0 = off, 1 = on) * * Execute the necessary ATPX function to power down/up the discrete GPU @@ -373,11 +373,11 @@ static int radeon_atpx_power_state(enum vga_switcheroo_client_id id, } /** - * radeon_atpx_pci_probe_handle - look up the ATRM and ATPX handles + * radeon_atpx_pci_probe_handle - look up the ATPX handle * * @pdev: pci device * - * Look up the ATPX and ATRM handles (all asics). + * Look up the ATPX handles (all asics). * Returns true if the handles are found, false if not. */ static bool radeon_atpx_pci_probe_handle(struct pci_dev *pdev) diff --git a/drivers/gpu/drm/radeon/radeon_connectors.c b/drivers/gpu/drm/radeon/radeon_connectors.c index 67cfc1795ecd..b884c362a8c2 100644 --- a/drivers/gpu/drm/radeon/radeon_connectors.c +++ b/drivers/gpu/drm/radeon/radeon_connectors.c @@ -941,7 +941,7 @@ radeon_dvi_detect(struct drm_connector *connector, bool force) struct drm_mode_object *obj; int i; enum drm_connector_status ret = connector_status_disconnected; - bool dret = false; + bool dret = false, broken_edid = false; if (!force && radeon_check_hpd_status_unchanged(connector)) return connector->status; @@ -965,6 +965,9 @@ radeon_dvi_detect(struct drm_connector *connector, bool force) ret = connector_status_disconnected; DRM_ERROR("%s: detected RS690 floating bus bug, stopping ddc detect\n", drm_get_connector_name(connector)); radeon_connector->ddc_bus = NULL; + } else { + ret = connector_status_connected; + broken_edid = true; /* defer use_digital to later */ } } else { radeon_connector->use_digital = !!(radeon_connector->edid->input & DRM_EDID_INPUT_DIGITAL); @@ -1047,13 +1050,24 @@ radeon_dvi_detect(struct drm_connector *connector, bool force) encoder_funcs = encoder->helper_private; if (encoder_funcs->detect) { - if (ret != connector_status_connected) { - ret = encoder_funcs->detect(encoder, connector); - if (ret == connector_status_connected) { - radeon_connector->use_digital = false; + if (!broken_edid) { + if (ret != connector_status_connected) { + /* deal with analog monitors without DDC */ + ret = encoder_funcs->detect(encoder, connector); + if (ret == connector_status_connected) { + radeon_connector->use_digital = false; + } + if (ret != connector_status_disconnected) + radeon_connector->detected_by_load = true; } - if (ret != connector_status_disconnected) - radeon_connector->detected_by_load = true; + } else { + enum drm_connector_status lret; + /* assume digital unless load detected otherwise */ + radeon_connector->use_digital = true; + lret = encoder_funcs->detect(encoder, connector); + DRM_DEBUG_KMS("load_detect %x returned: %x\n",encoder->encoder_type,lret); + if (lret == connector_status_connected) + radeon_connector->use_digital = false; } break; } diff --git a/drivers/gpu/drm/radeon/radeon_cs.c b/drivers/gpu/drm/radeon/radeon_cs.c index cb7b7c062fef..41672cc563fb 100644 --- a/drivers/gpu/drm/radeon/radeon_cs.c +++ b/drivers/gpu/drm/radeon/radeon_cs.c @@ -478,6 +478,7 @@ static int radeon_cs_ib_vm_chunk(struct radeon_device *rdev, } out: + radeon_vm_add_to_lru(rdev, vm); mutex_unlock(&vm->mutex); mutex_unlock(&rdev->vm_manager.lock); return r; diff --git a/drivers/gpu/drm/radeon/radeon_device.c b/drivers/gpu/drm/radeon/radeon_device.c index 64a42647f08a..e2f5f888c374 100644 --- a/drivers/gpu/drm/radeon/radeon_device.c +++ b/drivers/gpu/drm/radeon/radeon_device.c @@ -355,6 +355,8 @@ int radeon_wb_init(struct radeon_device *rdev) */ void radeon_vram_location(struct radeon_device *rdev, struct radeon_mc *mc, u64 base) { + uint64_t limit = (uint64_t)radeon_vram_limit << 20; + mc->vram_start = base; if (mc->mc_vram_size > (0xFFFFFFFF - base + 1)) { dev_warn(rdev->dev, "limiting VRAM to PCI aperture size\n"); @@ -368,8 +370,8 @@ void radeon_vram_location(struct radeon_device *rdev, struct radeon_mc *mc, u64 mc->mc_vram_size = mc->aper_size; } mc->vram_end = mc->vram_start + mc->mc_vram_size - 1; - if (radeon_vram_limit && radeon_vram_limit < mc->real_vram_size) - mc->real_vram_size = radeon_vram_limit; + if (limit && limit < mc->real_vram_size) + mc->real_vram_size = limit; dev_info(rdev->dev, "VRAM: %lluM 0x%016llX - 0x%016llX (%lluM used)\n", mc->mc_vram_size >> 20, mc->vram_start, mc->vram_end, mc->real_vram_size >> 20); @@ -835,6 +837,19 @@ static unsigned int radeon_vga_set_decode(void *cookie, bool state) } /** + * radeon_check_pot_argument - check that argument is a power of two + * + * @arg: value to check + * + * Validates that a certain argument is a power of two (all asics). + * Returns true if argument is valid. + */ +static bool radeon_check_pot_argument(int arg) +{ + return (arg & (arg - 1)) == 0; +} + +/** * radeon_check_arguments - validate module params * * @rdev: radeon_device pointer @@ -845,52 +860,25 @@ static unsigned int radeon_vga_set_decode(void *cookie, bool state) static void radeon_check_arguments(struct radeon_device *rdev) { /* vramlimit must be a power of two */ - switch (radeon_vram_limit) { - case 0: - case 4: - case 8: - case 16: - case 32: - case 64: - case 128: - case 256: - case 512: - case 1024: - case 2048: - case 4096: - break; - default: + if (!radeon_check_pot_argument(radeon_vram_limit)) { dev_warn(rdev->dev, "vram limit (%d) must be a power of 2\n", radeon_vram_limit); radeon_vram_limit = 0; - break; } - radeon_vram_limit = radeon_vram_limit << 20; + /* gtt size must be power of two and greater or equal to 32M */ - switch (radeon_gart_size) { - case 4: - case 8: - case 16: + if (radeon_gart_size < 32) { dev_warn(rdev->dev, "gart size (%d) too small forcing to 512M\n", radeon_gart_size); radeon_gart_size = 512; - break; - case 32: - case 64: - case 128: - case 256: - case 512: - case 1024: - case 2048: - case 4096: - break; - default: + + } else if (!radeon_check_pot_argument(radeon_gart_size)) { dev_warn(rdev->dev, "gart size (%d) must be a power of 2\n", radeon_gart_size); radeon_gart_size = 512; - break; } - rdev->mc.gtt_size = radeon_gart_size * 1024 * 1024; + rdev->mc.gtt_size = (uint64_t)radeon_gart_size << 20; + /* AGP mode can only be -1, 1, 2, 4, 8 */ switch (radeon_agpmode) { case -1: @@ -1018,6 +1006,10 @@ int radeon_device_init(struct radeon_device *rdev, return r; /* initialize vm here */ mutex_init(&rdev->vm_manager.lock); + /* Adjust VM size here. + * Currently set to 4GB ((1 << 20) 4k pages). + * Max GPUVM size for cayman and SI is 40 bits. + */ rdev->vm_manager.max_pfn = 1 << 20; INIT_LIST_HEAD(&rdev->vm_manager.lru_vm); diff --git a/drivers/gpu/drm/radeon/radeon_gart.c b/drivers/gpu/drm/radeon/radeon_gart.c index f0c06d196b75..4debd60e5aa6 100644 --- a/drivers/gpu/drm/radeon/radeon_gart.c +++ b/drivers/gpu/drm/radeon/radeon_gart.c @@ -355,14 +355,13 @@ int radeon_gart_init(struct radeon_device *rdev) DRM_INFO("GART: num cpu pages %u, num gpu pages %u\n", rdev->gart.num_cpu_pages, rdev->gart.num_gpu_pages); /* Allocate pages table */ - rdev->gart.pages = kzalloc(sizeof(void *) * rdev->gart.num_cpu_pages, - GFP_KERNEL); + rdev->gart.pages = vzalloc(sizeof(void *) * rdev->gart.num_cpu_pages); if (rdev->gart.pages == NULL) { radeon_gart_fini(rdev); return -ENOMEM; } - rdev->gart.pages_addr = kzalloc(sizeof(dma_addr_t) * - rdev->gart.num_cpu_pages, GFP_KERNEL); + rdev->gart.pages_addr = vzalloc(sizeof(dma_addr_t) * + rdev->gart.num_cpu_pages); if (rdev->gart.pages_addr == NULL) { radeon_gart_fini(rdev); return -ENOMEM; @@ -388,8 +387,8 @@ void radeon_gart_fini(struct radeon_device *rdev) radeon_gart_unbind(rdev, 0, rdev->gart.num_cpu_pages); } rdev->gart.ready = false; - kfree(rdev->gart.pages); - kfree(rdev->gart.pages_addr); + vfree(rdev->gart.pages); + vfree(rdev->gart.pages_addr); rdev->gart.pages = NULL; rdev->gart.pages_addr = NULL; @@ -423,6 +422,18 @@ void radeon_gart_fini(struct radeon_device *rdev) */ /** + * radeon_vm_num_pde - return the number of page directory entries + * + * @rdev: radeon_device pointer + * + * Calculate the number of page directory entries (cayman+). + */ +static unsigned radeon_vm_num_pdes(struct radeon_device *rdev) +{ + return rdev->vm_manager.max_pfn >> RADEON_VM_BLOCK_SIZE; +} + +/** * radeon_vm_directory_size - returns the size of the page directory in bytes * * @rdev: radeon_device pointer @@ -431,7 +442,7 @@ void radeon_gart_fini(struct radeon_device *rdev) */ static unsigned radeon_vm_directory_size(struct radeon_device *rdev) { - return (rdev->vm_manager.max_pfn >> RADEON_VM_BLOCK_SIZE) * 8; + return RADEON_GPU_PAGE_ALIGN(radeon_vm_num_pdes(rdev) * 8); } /** @@ -451,11 +462,11 @@ int radeon_vm_manager_init(struct radeon_device *rdev) if (!rdev->vm_manager.enabled) { /* allocate enough for 2 full VM pts */ - size = RADEON_GPU_PAGE_ALIGN(radeon_vm_directory_size(rdev)); - size += RADEON_GPU_PAGE_ALIGN(rdev->vm_manager.max_pfn * 8); + size = radeon_vm_directory_size(rdev); + size += rdev->vm_manager.max_pfn * 8; size *= 2; r = radeon_sa_bo_manager_init(rdev, &rdev->vm_manager.sa_manager, - size, + RADEON_GPU_PAGE_ALIGN(size), RADEON_GEM_DOMAIN_VRAM); if (r) { dev_err(rdev->dev, "failed to allocate vm bo (%dKB)\n", @@ -476,7 +487,7 @@ int radeon_vm_manager_init(struct radeon_device *rdev) /* restore page table */ list_for_each_entry(vm, &rdev->vm_manager.lru_vm, list) { - if (vm->sa_bo == NULL) + if (vm->page_directory == NULL) continue; list_for_each_entry(bo_va, &vm->va, vm_list) { @@ -500,16 +511,25 @@ static void radeon_vm_free_pt(struct radeon_device *rdev, struct radeon_vm *vm) { struct radeon_bo_va *bo_va; + int i; - if (!vm->sa_bo) + if (!vm->page_directory) return; list_del_init(&vm->list); - radeon_sa_bo_free(rdev, &vm->sa_bo, vm->fence); + radeon_sa_bo_free(rdev, &vm->page_directory, vm->fence); list_for_each_entry(bo_va, &vm->va, vm_list) { bo_va->valid = false; } + + if (vm->page_tables == NULL) + return; + + for (i = 0; i < radeon_vm_num_pdes(rdev); i++) + radeon_sa_bo_free(rdev, &vm->page_tables[i], vm->fence); + + kfree(vm->page_tables); } /** @@ -546,63 +566,106 @@ void radeon_vm_manager_fini(struct radeon_device *rdev) } /** + * radeon_vm_evict - evict page table to make room for new one + * + * @rdev: radeon_device pointer + * @vm: VM we want to allocate something for + * + * Evict a VM from the lru, making sure that it isn't @vm. (cayman+). + * Returns 0 for success, -ENOMEM for failure. + * + * Global and local mutex must be locked! + */ +static int radeon_vm_evict(struct radeon_device *rdev, struct radeon_vm *vm) +{ + struct radeon_vm *vm_evict; + + if (list_empty(&rdev->vm_manager.lru_vm)) + return -ENOMEM; + + vm_evict = list_first_entry(&rdev->vm_manager.lru_vm, + struct radeon_vm, list); + if (vm_evict == vm) + return -ENOMEM; + + mutex_lock(&vm_evict->mutex); + radeon_vm_free_pt(rdev, vm_evict); + mutex_unlock(&vm_evict->mutex); + return 0; +} + +/** * radeon_vm_alloc_pt - allocates a page table for a VM * * @rdev: radeon_device pointer * @vm: vm to bind * * Allocate a page table for the requested vm (cayman+). - * Also starts to populate the page table. * Returns 0 for success, error for failure. * * Global and local mutex must be locked! */ int radeon_vm_alloc_pt(struct radeon_device *rdev, struct radeon_vm *vm) { - struct radeon_vm *vm_evict; - int r; + unsigned pd_size, pts_size; u64 *pd_addr; - int tables_size; + int r; if (vm == NULL) { return -EINVAL; } - /* allocate enough to cover the current VM size */ - tables_size = RADEON_GPU_PAGE_ALIGN(radeon_vm_directory_size(rdev)); - tables_size += RADEON_GPU_PAGE_ALIGN(vm->last_pfn * 8); - - if (vm->sa_bo != NULL) { - /* update lru */ - list_del_init(&vm->list); - list_add_tail(&vm->list, &rdev->vm_manager.lru_vm); + if (vm->page_directory != NULL) { return 0; } retry: - r = radeon_sa_bo_new(rdev, &rdev->vm_manager.sa_manager, &vm->sa_bo, - tables_size, RADEON_GPU_PAGE_SIZE, false); + pd_size = RADEON_GPU_PAGE_ALIGN(radeon_vm_directory_size(rdev)); + r = radeon_sa_bo_new(rdev, &rdev->vm_manager.sa_manager, + &vm->page_directory, pd_size, + RADEON_GPU_PAGE_SIZE, false); if (r == -ENOMEM) { - if (list_empty(&rdev->vm_manager.lru_vm)) { + r = radeon_vm_evict(rdev, vm); + if (r) return r; - } - vm_evict = list_first_entry(&rdev->vm_manager.lru_vm, struct radeon_vm, list); - mutex_lock(&vm_evict->mutex); - radeon_vm_free_pt(rdev, vm_evict); - mutex_unlock(&vm_evict->mutex); goto retry; } else if (r) { return r; } - pd_addr = radeon_sa_bo_cpu_addr(vm->sa_bo); - vm->pd_gpu_addr = radeon_sa_bo_gpu_addr(vm->sa_bo); - memset(pd_addr, 0, tables_size); + vm->pd_gpu_addr = radeon_sa_bo_gpu_addr(vm->page_directory); + + /* Initially clear the page directory */ + pd_addr = radeon_sa_bo_cpu_addr(vm->page_directory); + memset(pd_addr, 0, pd_size); + + pts_size = radeon_vm_num_pdes(rdev) * sizeof(struct radeon_sa_bo *); + vm->page_tables = kzalloc(pts_size, GFP_KERNEL); + + if (vm->page_tables == NULL) { + DRM_ERROR("Cannot allocate memory for page table array\n"); + radeon_sa_bo_free(rdev, &vm->page_directory, vm->fence); + return -ENOMEM; + } + + return 0; +} +/** + * radeon_vm_add_to_lru - add VMs page table to LRU list + * + * @rdev: radeon_device pointer + * @vm: vm to add to LRU + * + * Add the allocated page table to the LRU list (cayman+). + * + * Global mutex must be locked! + */ +void radeon_vm_add_to_lru(struct radeon_device *rdev, struct radeon_vm *vm) +{ + list_del_init(&vm->list); list_add_tail(&vm->list, &rdev->vm_manager.lru_vm); - return radeon_vm_bo_update_pte(rdev, vm, rdev->ring_tmp_bo.bo, - &rdev->ring_tmp_bo.bo->tbo.mem); } /** @@ -793,20 +856,6 @@ int radeon_vm_bo_set_addr(struct radeon_device *rdev, } mutex_lock(&vm->mutex); - if (last_pfn > vm->last_pfn) { - /* release mutex and lock in right order */ - mutex_unlock(&vm->mutex); - mutex_lock(&rdev->vm_manager.lock); - mutex_lock(&vm->mutex); - /* and check again */ - if (last_pfn > vm->last_pfn) { - /* grow va space 32M by 32M */ - unsigned align = ((32 << 20) >> 12) - 1; - radeon_vm_free_pt(rdev, vm); - vm->last_pfn = (last_pfn + align) & ~align; - } - mutex_unlock(&rdev->vm_manager.lock); - } head = &vm->va; last_offset = 0; list_for_each_entry(tmp, &vm->va, vm_list) { @@ -865,6 +914,154 @@ uint64_t radeon_vm_map_gart(struct radeon_device *rdev, uint64_t addr) } /** + * radeon_vm_update_pdes - make sure that page directory is valid + * + * @rdev: radeon_device pointer + * @vm: requested vm + * @start: start of GPU address range + * @end: end of GPU address range + * + * Allocates new page tables if necessary + * and updates the page directory (cayman+). + * Returns 0 for success, error for failure. + * + * Global and local mutex must be locked! + */ +static int radeon_vm_update_pdes(struct radeon_device *rdev, + struct radeon_vm *vm, + uint64_t start, uint64_t end) +{ + static const uint32_t incr = RADEON_VM_PTE_COUNT * 8; + + uint64_t last_pde = ~0, last_pt = ~0; + unsigned count = 0; + uint64_t pt_idx; + int r; + + start = (start / RADEON_GPU_PAGE_SIZE) >> RADEON_VM_BLOCK_SIZE; + end = (end / RADEON_GPU_PAGE_SIZE) >> RADEON_VM_BLOCK_SIZE; + + /* walk over the address space and update the page directory */ + for (pt_idx = start; pt_idx <= end; ++pt_idx) { + uint64_t pde, pt; + + if (vm->page_tables[pt_idx]) + continue; + +retry: + r = radeon_sa_bo_new(rdev, &rdev->vm_manager.sa_manager, + &vm->page_tables[pt_idx], + RADEON_VM_PTE_COUNT * 8, + RADEON_GPU_PAGE_SIZE, false); + + if (r == -ENOMEM) { + r = radeon_vm_evict(rdev, vm); + if (r) + return r; + goto retry; + } else if (r) { + return r; + } + + pde = vm->pd_gpu_addr + pt_idx * 8; + + pt = radeon_sa_bo_gpu_addr(vm->page_tables[pt_idx]); + + if (((last_pde + 8 * count) != pde) || + ((last_pt + incr * count) != pt)) { + + if (count) { + radeon_asic_vm_set_page(rdev, last_pde, + last_pt, count, incr, + RADEON_VM_PAGE_VALID); + } + + count = 1; + last_pde = pde; + last_pt = pt; + } else { + ++count; + } + } + + if (count) { + radeon_asic_vm_set_page(rdev, last_pde, last_pt, count, + incr, RADEON_VM_PAGE_VALID); + + } + + return 0; +} + +/** + * radeon_vm_update_ptes - make sure that page tables are valid + * + * @rdev: radeon_device pointer + * @vm: requested vm + * @start: start of GPU address range + * @end: end of GPU address range + * @dst: destination address to map to + * @flags: mapping flags + * + * Update the page tables in the range @start - @end (cayman+). + * + * Global and local mutex must be locked! + */ +static void radeon_vm_update_ptes(struct radeon_device *rdev, + struct radeon_vm *vm, + uint64_t start, uint64_t end, + uint64_t dst, uint32_t flags) +{ + static const uint64_t mask = RADEON_VM_PTE_COUNT - 1; + + uint64_t last_pte = ~0, last_dst = ~0; + unsigned count = 0; + uint64_t addr; + + start = start / RADEON_GPU_PAGE_SIZE; + end = end / RADEON_GPU_PAGE_SIZE; + + /* walk over the address space and update the page tables */ + for (addr = start; addr < end; ) { + uint64_t pt_idx = addr >> RADEON_VM_BLOCK_SIZE; + unsigned nptes; + uint64_t pte; + + if ((addr & ~mask) == (end & ~mask)) + nptes = end - addr; + else + nptes = RADEON_VM_PTE_COUNT - (addr & mask); + + pte = radeon_sa_bo_gpu_addr(vm->page_tables[pt_idx]); + pte += (addr & mask) * 8; + + if ((last_pte + 8 * count) != pte) { + + if (count) { + radeon_asic_vm_set_page(rdev, last_pte, + last_dst, count, + RADEON_GPU_PAGE_SIZE, + flags); + } + + count = nptes; + last_pte = pte; + last_dst = dst; + } else { + count += nptes; + } + + addr += nptes; + dst += nptes * RADEON_GPU_PAGE_SIZE; + } + + if (count) { + radeon_asic_vm_set_page(rdev, last_pte, last_dst, count, + RADEON_GPU_PAGE_SIZE, flags); + } +} + +/** * radeon_vm_bo_update_pte - map a bo into the vm page table * * @rdev: radeon_device pointer @@ -887,12 +1084,11 @@ int radeon_vm_bo_update_pte(struct radeon_device *rdev, struct radeon_semaphore *sem = NULL; struct radeon_bo_va *bo_va; unsigned nptes, npdes, ndw; - uint64_t pe, addr; - uint64_t pfn; + uint64_t addr; int r; /* nothing to do if vm isn't bound */ - if (vm->sa_bo == NULL) + if (vm->page_directory == NULL) return 0; bo_va = radeon_vm_bo_find(vm, bo); @@ -939,25 +1135,29 @@ int radeon_vm_bo_update_pte(struct radeon_device *rdev, } } - /* estimate number of dw needed */ - /* reserve space for 32-bit padding */ - ndw = 32; - nptes = radeon_bo_ngpu_pages(bo); - pfn = (bo_va->soffset / RADEON_GPU_PAGE_SIZE); + /* assume two extra pdes in case the mapping overlaps the borders */ + npdes = (nptes >> RADEON_VM_BLOCK_SIZE) + 2; - /* handle cases where a bo spans several pdes */ - npdes = (ALIGN(pfn + nptes, RADEON_VM_PTE_COUNT) - - (pfn & ~(RADEON_VM_PTE_COUNT - 1))) >> RADEON_VM_BLOCK_SIZE; + /* estimate number of dw needed */ + /* semaphore, fence and padding */ + ndw = 32; + + if (RADEON_VM_BLOCK_SIZE > 11) + /* reserve space for one header for every 2k dwords */ + ndw += (nptes >> 11) * 4; + else + /* reserve space for one header for + every (1 << BLOCK_SIZE) entries */ + ndw += (nptes >> RADEON_VM_BLOCK_SIZE) * 4; - /* reserve space for one header for every 2k dwords */ - ndw += (nptes >> 11) * 3; /* reserve space for pte addresses */ ndw += nptes * 2; /* reserve space for one header for every 2k dwords */ - ndw += (npdes >> 11) * 3; + ndw += (npdes >> 11) * 4; + /* reserve space for pde addresses */ ndw += npdes * 2; @@ -971,22 +1171,14 @@ int radeon_vm_bo_update_pte(struct radeon_device *rdev, radeon_fence_note_sync(vm->fence, ridx); } - /* update page table entries */ - pe = vm->pd_gpu_addr; - pe += radeon_vm_directory_size(rdev); - pe += (bo_va->soffset / RADEON_GPU_PAGE_SIZE) * 8; - - radeon_asic_vm_set_page(rdev, pe, addr, nptes, - RADEON_GPU_PAGE_SIZE, bo_va->flags); - - /* update page directory entries */ - addr = pe; - - pe = vm->pd_gpu_addr; - pe += ((bo_va->soffset / RADEON_GPU_PAGE_SIZE) >> RADEON_VM_BLOCK_SIZE) * 8; + r = radeon_vm_update_pdes(rdev, vm, bo_va->soffset, bo_va->eoffset); + if (r) { + radeon_ring_unlock_undo(rdev, ring); + return r; + } - radeon_asic_vm_set_page(rdev, pe, addr, npdes, - RADEON_VM_PTE_COUNT * 8, RADEON_VM_PAGE_VALID); + radeon_vm_update_ptes(rdev, vm, bo_va->soffset, bo_va->eoffset, + addr, bo_va->flags); radeon_fence_unref(&vm->fence); r = radeon_fence_emit(rdev, &vm->fence, ridx); @@ -997,6 +1189,7 @@ int radeon_vm_bo_update_pte(struct radeon_device *rdev, radeon_ring_unlock_commit(rdev, ring); radeon_semaphore_free(rdev, &sem, vm->fence); radeon_fence_unref(&vm->last_flush); + return 0; } @@ -1056,31 +1249,15 @@ void radeon_vm_bo_invalidate(struct radeon_device *rdev, * @rdev: radeon_device pointer * @vm: requested vm * - * Init @vm (cayman+). - * Map the IB pool and any other shared objects into the VM - * by default as it's used by all VMs. - * Returns 0 for success, error for failure. + * Init @vm fields (cayman+). */ -int radeon_vm_init(struct radeon_device *rdev, struct radeon_vm *vm) +void radeon_vm_init(struct radeon_device *rdev, struct radeon_vm *vm) { - struct radeon_bo_va *bo_va; - int r; - vm->id = 0; vm->fence = NULL; - vm->last_pfn = 0; mutex_init(&vm->mutex); INIT_LIST_HEAD(&vm->list); INIT_LIST_HEAD(&vm->va); - - /* map the ib pool buffer at 0 in virtual address space, set - * read only - */ - bo_va = radeon_vm_bo_add(rdev, vm, rdev->ring_tmp_bo.bo); - r = radeon_vm_bo_set_addr(rdev, bo_va, RADEON_VA_IB_OFFSET, - RADEON_VM_PAGE_READABLE | - RADEON_VM_PAGE_SNOOPED); - return r; } /** @@ -1102,17 +1279,6 @@ void radeon_vm_fini(struct radeon_device *rdev, struct radeon_vm *vm) radeon_vm_free_pt(rdev, vm); mutex_unlock(&rdev->vm_manager.lock); - /* remove all bo at this point non are busy any more because unbind - * waited for the last vm fence to signal - */ - r = radeon_bo_reserve(rdev->ring_tmp_bo.bo, false); - if (!r) { - bo_va = radeon_vm_bo_find(vm, rdev->ring_tmp_bo.bo); - list_del_init(&bo_va->bo_list); - list_del_init(&bo_va->vm_list); - radeon_bo_unreserve(rdev->ring_tmp_bo.bo); - kfree(bo_va); - } if (!list_empty(&vm->va)) { dev_err(rdev->dev, "still active bo inside vm\n"); } diff --git a/drivers/gpu/drm/radeon/radeon_gem.c b/drivers/gpu/drm/radeon/radeon_gem.c index f38fbcc46935..fe5c1f6b7957 100644 --- a/drivers/gpu/drm/radeon/radeon_gem.c +++ b/drivers/gpu/drm/radeon/radeon_gem.c @@ -53,6 +53,7 @@ int radeon_gem_object_create(struct radeon_device *rdev, int size, struct drm_gem_object **obj) { struct radeon_bo *robj; + unsigned long max_size; int r; *obj = NULL; @@ -60,11 +61,26 @@ int radeon_gem_object_create(struct radeon_device *rdev, int size, if (alignment < PAGE_SIZE) { alignment = PAGE_SIZE; } + + /* maximun bo size is the minimun btw visible vram and gtt size */ + max_size = min(rdev->mc.visible_vram_size, rdev->mc.gtt_size); + if (size > max_size) { + printk(KERN_WARNING "%s:%d alloc size %dMb bigger than %ldMb limit\n", + __func__, __LINE__, size >> 20, max_size >> 20); + return -ENOMEM; + } + +retry: r = radeon_bo_create(rdev, size, alignment, kernel, initial_domain, NULL, &robj); if (r) { - if (r != -ERESTARTSYS) + if (r != -ERESTARTSYS) { + if (initial_domain == RADEON_GEM_DOMAIN_VRAM) { + initial_domain |= RADEON_GEM_DOMAIN_GTT; + goto retry; + } DRM_ERROR("Failed to allocate GEM object (%d, %d, %u, %d)\n", size, initial_domain, alignment, r); + } return r; } *obj = &robj->gem_base; diff --git a/drivers/gpu/drm/radeon/radeon_kms.c b/drivers/gpu/drm/radeon/radeon_kms.c index 83b8d8aa71c0..dc781c49b96b 100644 --- a/drivers/gpu/drm/radeon/radeon_kms.c +++ b/drivers/gpu/drm/radeon/radeon_kms.c @@ -419,6 +419,7 @@ int radeon_driver_open_kms(struct drm_device *dev, struct drm_file *file_priv) /* new gpu have virtual address space support */ if (rdev->family >= CHIP_CAYMAN) { struct radeon_fpriv *fpriv; + struct radeon_bo_va *bo_va; int r; fpriv = kzalloc(sizeof(*fpriv), GFP_KERNEL); @@ -426,7 +427,15 @@ int radeon_driver_open_kms(struct drm_device *dev, struct drm_file *file_priv) return -ENOMEM; } - r = radeon_vm_init(rdev, &fpriv->vm); + radeon_vm_init(rdev, &fpriv->vm); + + /* map the ib pool buffer read only into + * virtual address space */ + bo_va = radeon_vm_bo_add(rdev, &fpriv->vm, + rdev->ring_tmp_bo.bo); + r = radeon_vm_bo_set_addr(rdev, bo_va, RADEON_VA_IB_OFFSET, + RADEON_VM_PAGE_READABLE | + RADEON_VM_PAGE_SNOOPED); if (r) { radeon_vm_fini(rdev, &fpriv->vm); kfree(fpriv); @@ -454,6 +463,17 @@ void radeon_driver_postclose_kms(struct drm_device *dev, /* new gpu have virtual address space support */ if (rdev->family >= CHIP_CAYMAN && file_priv->driver_priv) { struct radeon_fpriv *fpriv = file_priv->driver_priv; + struct radeon_bo_va *bo_va; + int r; + + r = radeon_bo_reserve(rdev->ring_tmp_bo.bo, false); + if (!r) { + bo_va = radeon_vm_bo_find(&fpriv->vm, + rdev->ring_tmp_bo.bo); + if (bo_va) + radeon_vm_bo_rmv(rdev, bo_va); + radeon_bo_unreserve(rdev->ring_tmp_bo.bo); + } radeon_vm_fini(rdev, &fpriv->vm); kfree(fpriv); diff --git a/drivers/gpu/drm/radeon/radeon_legacy_crtc.c b/drivers/gpu/drm/radeon/radeon_legacy_crtc.c index 5677a424b585..6857cb4efb76 100644 --- a/drivers/gpu/drm/radeon/radeon_legacy_crtc.c +++ b/drivers/gpu/drm/radeon/radeon_legacy_crtc.c @@ -295,6 +295,7 @@ static void radeon_crtc_dpms(struct drm_crtc *crtc, int mode) struct radeon_crtc *radeon_crtc = to_radeon_crtc(crtc); struct drm_device *dev = crtc->dev; struct radeon_device *rdev = dev->dev_private; + uint32_t crtc_ext_cntl = 0; uint32_t mask; if (radeon_crtc->crtc_id) @@ -307,6 +308,16 @@ static void radeon_crtc_dpms(struct drm_crtc *crtc, int mode) RADEON_CRTC_VSYNC_DIS | RADEON_CRTC_HSYNC_DIS); + /* + * On all dual CRTC GPUs this bit controls the CRTC of the primary DAC. + * Therefore it is set in the DAC DMPS function. + * This is different for GPU's with a single CRTC but a primary and a + * TV DAC: here it controls the single CRTC no matter where it is + * routed. Therefore we set it here. + */ + if (rdev->flags & RADEON_SINGLE_CRTC) + crtc_ext_cntl = RADEON_CRTC_CRT_ON; + switch (mode) { case DRM_MODE_DPMS_ON: radeon_crtc->enabled = true; @@ -317,7 +328,7 @@ static void radeon_crtc_dpms(struct drm_crtc *crtc, int mode) else { WREG32_P(RADEON_CRTC_GEN_CNTL, RADEON_CRTC_EN, ~(RADEON_CRTC_EN | RADEON_CRTC_DISP_REQ_EN_B)); - WREG32_P(RADEON_CRTC_EXT_CNTL, 0, ~mask); + WREG32_P(RADEON_CRTC_EXT_CNTL, crtc_ext_cntl, ~(mask | crtc_ext_cntl)); } drm_vblank_post_modeset(dev, radeon_crtc->crtc_id); radeon_crtc_load_lut(crtc); @@ -331,7 +342,7 @@ static void radeon_crtc_dpms(struct drm_crtc *crtc, int mode) else { WREG32_P(RADEON_CRTC_GEN_CNTL, RADEON_CRTC_DISP_REQ_EN_B, ~(RADEON_CRTC_EN | RADEON_CRTC_DISP_REQ_EN_B)); - WREG32_P(RADEON_CRTC_EXT_CNTL, mask, ~mask); + WREG32_P(RADEON_CRTC_EXT_CNTL, mask, ~(mask | crtc_ext_cntl)); } radeon_crtc->enabled = false; /* adjust pm to dpms changes AFTER disabling crtcs */ diff --git a/drivers/gpu/drm/radeon/radeon_legacy_encoders.c b/drivers/gpu/drm/radeon/radeon_legacy_encoders.c index 92487e614778..f5ba2241dacc 100644 --- a/drivers/gpu/drm/radeon/radeon_legacy_encoders.c +++ b/drivers/gpu/drm/radeon/radeon_legacy_encoders.c @@ -269,27 +269,6 @@ static const struct drm_encoder_helper_funcs radeon_legacy_lvds_helper_funcs = { .disable = radeon_legacy_encoder_disable, }; -#if defined(CONFIG_BACKLIGHT_CLASS_DEVICE) || defined(CONFIG_BACKLIGHT_CLASS_DEVICE_MODULE) - -static uint8_t radeon_legacy_lvds_level(struct backlight_device *bd) -{ - struct radeon_backlight_privdata *pdata = bl_get_data(bd); - uint8_t level; - - /* Convert brightness to hardware level */ - if (bd->props.brightness < 0) - level = 0; - else if (bd->props.brightness > RADEON_MAX_BL_LEVEL) - level = RADEON_MAX_BL_LEVEL; - else - level = bd->props.brightness; - - if (pdata->negative) - level = RADEON_MAX_BL_LEVEL - level; - - return level; -} - u8 radeon_legacy_get_backlight_level(struct radeon_encoder *radeon_encoder) { @@ -331,6 +310,27 @@ radeon_legacy_set_backlight_level(struct radeon_encoder *radeon_encoder, u8 leve radeon_legacy_lvds_update(&radeon_encoder->base, dpms_mode); } +#if defined(CONFIG_BACKLIGHT_CLASS_DEVICE) || defined(CONFIG_BACKLIGHT_CLASS_DEVICE_MODULE) + +static uint8_t radeon_legacy_lvds_level(struct backlight_device *bd) +{ + struct radeon_backlight_privdata *pdata = bl_get_data(bd); + uint8_t level; + + /* Convert brightness to hardware level */ + if (bd->props.brightness < 0) + level = 0; + else if (bd->props.brightness > RADEON_MAX_BL_LEVEL) + level = RADEON_MAX_BL_LEVEL; + else + level = bd->props.brightness; + + if (pdata->negative) + level = RADEON_MAX_BL_LEVEL - level; + + return level; +} + static int radeon_legacy_backlight_update_status(struct backlight_device *bd) { struct radeon_backlight_privdata *pdata = bl_get_data(bd); @@ -370,6 +370,7 @@ void radeon_legacy_backlight_init(struct radeon_encoder *radeon_encoder, struct backlight_properties props; struct radeon_backlight_privdata *pdata; uint8_t backlight_level; + char bl_name[16]; if (!radeon_encoder->enc_priv) return; @@ -389,7 +390,9 @@ void radeon_legacy_backlight_init(struct radeon_encoder *radeon_encoder, memset(&props, 0, sizeof(props)); props.max_brightness = RADEON_MAX_BL_LEVEL; props.type = BACKLIGHT_RAW; - bd = backlight_device_register("radeon_bl", &drm_connector->kdev, + snprintf(bl_name, sizeof(bl_name), + "radeon_bl%d", dev->primary->index); + bd = backlight_device_register(bl_name, &drm_connector->kdev, pdata, &radeon_backlight_ops, &props); if (IS_ERR(bd)) { DRM_ERROR("Backlight registration failed\n"); @@ -534,7 +537,9 @@ static void radeon_legacy_primary_dac_dpms(struct drm_encoder *encoder, int mode break; } - WREG32(RADEON_CRTC_EXT_CNTL, crtc_ext_cntl); + /* handled in radeon_crtc_dpms() */ + if (!(rdev->flags & RADEON_SINGLE_CRTC)) + WREG32(RADEON_CRTC_EXT_CNTL, crtc_ext_cntl); WREG32(RADEON_DAC_CNTL, dac_cntl); WREG32(RADEON_DAC_MACRO_CNTL, dac_macro_cntl); @@ -659,6 +664,8 @@ static enum drm_connector_status radeon_legacy_primary_dac_detect(struct drm_enc if (ASIC_IS_R300(rdev)) tmp |= (0x1b6 << RADEON_DAC_FORCE_DATA_SHIFT); + else if (ASIC_IS_RV100(rdev)) + tmp |= (0x1ac << RADEON_DAC_FORCE_DATA_SHIFT); else tmp |= (0x180 << RADEON_DAC_FORCE_DATA_SHIFT); @@ -668,6 +675,7 @@ static enum drm_connector_status radeon_legacy_primary_dac_detect(struct drm_enc tmp |= RADEON_DAC_RANGE_CNTL_PS2 | RADEON_DAC_CMP_EN; WREG32(RADEON_DAC_CNTL, tmp); + tmp = dac_macro_cntl; tmp &= ~(RADEON_DAC_PDWN_R | RADEON_DAC_PDWN_G | RADEON_DAC_PDWN_B); @@ -991,11 +999,7 @@ static void radeon_legacy_tmds_ext_mode_set(struct drm_encoder *encoder, static void radeon_ext_tmds_enc_destroy(struct drm_encoder *encoder) { struct radeon_encoder *radeon_encoder = to_radeon_encoder(encoder); - struct radeon_encoder_ext_tmds *tmds = radeon_encoder->enc_priv; - if (tmds) { - if (tmds->i2c_bus) - radeon_i2c_destroy(tmds->i2c_bus); - } + /* don't destroy the i2c bus record here, this will be done in radeon_i2c_fini */ kfree(radeon_encoder->enc_priv); drm_encoder_cleanup(encoder); kfree(radeon_encoder); @@ -1093,7 +1097,8 @@ static void radeon_legacy_tv_dac_dpms(struct drm_encoder *encoder, int mode) } else { if (is_tv) WREG32(RADEON_TV_MASTER_CNTL, tv_master_cntl); - else + /* handled in radeon_crtc_dpms() */ + else if (!(rdev->flags & RADEON_SINGLE_CRTC)) WREG32(RADEON_CRTC2_GEN_CNTL, crtc2_gen_cntl); WREG32(RADEON_TV_DAC_CNTL, tv_dac_cntl); } @@ -1417,13 +1422,104 @@ static bool radeon_legacy_tv_detect(struct drm_encoder *encoder, return found; } +static bool radeon_legacy_ext_dac_detect(struct drm_encoder *encoder, + struct drm_connector *connector) +{ + struct drm_device *dev = encoder->dev; + struct radeon_device *rdev = dev->dev_private; + uint32_t gpio_monid, fp2_gen_cntl, disp_output_cntl, crtc2_gen_cntl; + uint32_t disp_lin_trans_grph_a, disp_lin_trans_grph_b, disp_lin_trans_grph_c; + uint32_t disp_lin_trans_grph_d, disp_lin_trans_grph_e, disp_lin_trans_grph_f; + uint32_t tmp, crtc2_h_total_disp, crtc2_v_total_disp; + uint32_t crtc2_h_sync_strt_wid, crtc2_v_sync_strt_wid; + bool found = false; + int i; + + /* save the regs we need */ + gpio_monid = RREG32(RADEON_GPIO_MONID); + fp2_gen_cntl = RREG32(RADEON_FP2_GEN_CNTL); + disp_output_cntl = RREG32(RADEON_DISP_OUTPUT_CNTL); + crtc2_gen_cntl = RREG32(RADEON_CRTC2_GEN_CNTL); + disp_lin_trans_grph_a = RREG32(RADEON_DISP_LIN_TRANS_GRPH_A); + disp_lin_trans_grph_b = RREG32(RADEON_DISP_LIN_TRANS_GRPH_B); + disp_lin_trans_grph_c = RREG32(RADEON_DISP_LIN_TRANS_GRPH_C); + disp_lin_trans_grph_d = RREG32(RADEON_DISP_LIN_TRANS_GRPH_D); + disp_lin_trans_grph_e = RREG32(RADEON_DISP_LIN_TRANS_GRPH_E); + disp_lin_trans_grph_f = RREG32(RADEON_DISP_LIN_TRANS_GRPH_F); + crtc2_h_total_disp = RREG32(RADEON_CRTC2_H_TOTAL_DISP); + crtc2_v_total_disp = RREG32(RADEON_CRTC2_V_TOTAL_DISP); + crtc2_h_sync_strt_wid = RREG32(RADEON_CRTC2_H_SYNC_STRT_WID); + crtc2_v_sync_strt_wid = RREG32(RADEON_CRTC2_V_SYNC_STRT_WID); + + tmp = RREG32(RADEON_GPIO_MONID); + tmp &= ~RADEON_GPIO_A_0; + WREG32(RADEON_GPIO_MONID, tmp); + + WREG32(RADEON_FP2_GEN_CNTL, (RADEON_FP2_ON | + RADEON_FP2_PANEL_FORMAT | + R200_FP2_SOURCE_SEL_TRANS_UNIT | + RADEON_FP2_DVO_EN | + R200_FP2_DVO_RATE_SEL_SDR)); + + WREG32(RADEON_DISP_OUTPUT_CNTL, (RADEON_DISP_DAC_SOURCE_RMX | + RADEON_DISP_TRANS_MATRIX_GRAPHICS)); + + WREG32(RADEON_CRTC2_GEN_CNTL, (RADEON_CRTC2_EN | + RADEON_CRTC2_DISP_REQ_EN_B)); + + WREG32(RADEON_DISP_LIN_TRANS_GRPH_A, 0x00000000); + WREG32(RADEON_DISP_LIN_TRANS_GRPH_B, 0x000003f0); + WREG32(RADEON_DISP_LIN_TRANS_GRPH_C, 0x00000000); + WREG32(RADEON_DISP_LIN_TRANS_GRPH_D, 0x000003f0); + WREG32(RADEON_DISP_LIN_TRANS_GRPH_E, 0x00000000); + WREG32(RADEON_DISP_LIN_TRANS_GRPH_F, 0x000003f0); + + WREG32(RADEON_CRTC2_H_TOTAL_DISP, 0x01000008); + WREG32(RADEON_CRTC2_H_SYNC_STRT_WID, 0x00000800); + WREG32(RADEON_CRTC2_V_TOTAL_DISP, 0x00080001); + WREG32(RADEON_CRTC2_V_SYNC_STRT_WID, 0x00000080); + + for (i = 0; i < 200; i++) { + tmp = RREG32(RADEON_GPIO_MONID); + if (tmp & RADEON_GPIO_Y_0) + found = true; + + if (found) + break; + + if (!drm_can_sleep()) + mdelay(1); + else + msleep(1); + } + + /* restore the regs we used */ + WREG32(RADEON_DISP_LIN_TRANS_GRPH_A, disp_lin_trans_grph_a); + WREG32(RADEON_DISP_LIN_TRANS_GRPH_B, disp_lin_trans_grph_b); + WREG32(RADEON_DISP_LIN_TRANS_GRPH_C, disp_lin_trans_grph_c); + WREG32(RADEON_DISP_LIN_TRANS_GRPH_D, disp_lin_trans_grph_d); + WREG32(RADEON_DISP_LIN_TRANS_GRPH_E, disp_lin_trans_grph_e); + WREG32(RADEON_DISP_LIN_TRANS_GRPH_F, disp_lin_trans_grph_f); + WREG32(RADEON_CRTC2_H_TOTAL_DISP, crtc2_h_total_disp); + WREG32(RADEON_CRTC2_V_TOTAL_DISP, crtc2_v_total_disp); + WREG32(RADEON_CRTC2_H_SYNC_STRT_WID, crtc2_h_sync_strt_wid); + WREG32(RADEON_CRTC2_V_SYNC_STRT_WID, crtc2_v_sync_strt_wid); + WREG32(RADEON_CRTC2_GEN_CNTL, crtc2_gen_cntl); + WREG32(RADEON_DISP_OUTPUT_CNTL, disp_output_cntl); + WREG32(RADEON_FP2_GEN_CNTL, fp2_gen_cntl); + WREG32(RADEON_GPIO_MONID, gpio_monid); + + return found; +} + static enum drm_connector_status radeon_legacy_tv_dac_detect(struct drm_encoder *encoder, struct drm_connector *connector) { struct drm_device *dev = encoder->dev; struct radeon_device *rdev = dev->dev_private; - uint32_t crtc2_gen_cntl, tv_dac_cntl, dac_cntl2, dac_ext_cntl; - uint32_t disp_hw_debug, disp_output_cntl, gpiopad_a, pixclks_cntl, tmp; + uint32_t crtc2_gen_cntl = 0, tv_dac_cntl, dac_cntl2, dac_ext_cntl; + uint32_t gpiopad_a = 0, pixclks_cntl, tmp; + uint32_t disp_output_cntl = 0, disp_hw_debug = 0, crtc_ext_cntl = 0; enum drm_connector_status found = connector_status_disconnected; struct radeon_encoder *radeon_encoder = to_radeon_encoder(encoder); struct radeon_encoder_tv_dac *tv_dac = radeon_encoder->enc_priv; @@ -1460,12 +1556,27 @@ static enum drm_connector_status radeon_legacy_tv_dac_detect(struct drm_encoder return connector_status_disconnected; } + /* R200 uses an external DAC for secondary DAC */ + if (rdev->family == CHIP_R200) { + if (radeon_legacy_ext_dac_detect(encoder, connector)) + found = connector_status_connected; + return found; + } + /* save the regs we need */ pixclks_cntl = RREG32_PLL(RADEON_PIXCLKS_CNTL); - gpiopad_a = ASIC_IS_R300(rdev) ? RREG32(RADEON_GPIOPAD_A) : 0; - disp_output_cntl = ASIC_IS_R300(rdev) ? RREG32(RADEON_DISP_OUTPUT_CNTL) : 0; - disp_hw_debug = ASIC_IS_R300(rdev) ? 0 : RREG32(RADEON_DISP_HW_DEBUG); - crtc2_gen_cntl = RREG32(RADEON_CRTC2_GEN_CNTL); + + if (rdev->flags & RADEON_SINGLE_CRTC) { + crtc_ext_cntl = RREG32(RADEON_CRTC_EXT_CNTL); + } else { + if (ASIC_IS_R300(rdev)) { + gpiopad_a = RREG32(RADEON_GPIOPAD_A); + disp_output_cntl = RREG32(RADEON_DISP_OUTPUT_CNTL); + } else { + disp_hw_debug = RREG32(RADEON_DISP_HW_DEBUG); + } + crtc2_gen_cntl = RREG32(RADEON_CRTC2_GEN_CNTL); + } tv_dac_cntl = RREG32(RADEON_TV_DAC_CNTL); dac_ext_cntl = RREG32(RADEON_DAC_EXT_CNTL); dac_cntl2 = RREG32(RADEON_DAC_CNTL2); @@ -1474,22 +1585,24 @@ static enum drm_connector_status radeon_legacy_tv_dac_detect(struct drm_encoder | RADEON_PIX2CLK_DAC_ALWAYS_ONb); WREG32_PLL(RADEON_PIXCLKS_CNTL, tmp); - if (ASIC_IS_R300(rdev)) - WREG32_P(RADEON_GPIOPAD_A, 1, ~1); - - tmp = crtc2_gen_cntl & ~RADEON_CRTC2_PIX_WIDTH_MASK; - tmp |= RADEON_CRTC2_CRT2_ON | - (2 << RADEON_CRTC2_PIX_WIDTH_SHIFT); - - WREG32(RADEON_CRTC2_GEN_CNTL, tmp); - - if (ASIC_IS_R300(rdev)) { - tmp = disp_output_cntl & ~RADEON_DISP_TVDAC_SOURCE_MASK; - tmp |= RADEON_DISP_TVDAC_SOURCE_CRTC2; - WREG32(RADEON_DISP_OUTPUT_CNTL, tmp); + if (rdev->flags & RADEON_SINGLE_CRTC) { + tmp = crtc_ext_cntl | RADEON_CRTC_CRT_ON; + WREG32(RADEON_CRTC_EXT_CNTL, tmp); } else { - tmp = disp_hw_debug & ~RADEON_CRT2_DISP1_SEL; - WREG32(RADEON_DISP_HW_DEBUG, tmp); + tmp = crtc2_gen_cntl & ~RADEON_CRTC2_PIX_WIDTH_MASK; + tmp |= RADEON_CRTC2_CRT2_ON | + (2 << RADEON_CRTC2_PIX_WIDTH_SHIFT); + WREG32(RADEON_CRTC2_GEN_CNTL, tmp); + + if (ASIC_IS_R300(rdev)) { + WREG32_P(RADEON_GPIOPAD_A, 1, ~1); + tmp = disp_output_cntl & ~RADEON_DISP_TVDAC_SOURCE_MASK; + tmp |= RADEON_DISP_TVDAC_SOURCE_CRTC2; + WREG32(RADEON_DISP_OUTPUT_CNTL, tmp); + } else { + tmp = disp_hw_debug & ~RADEON_CRT2_DISP1_SEL; + WREG32(RADEON_DISP_HW_DEBUG, tmp); + } } tmp = RADEON_TV_DAC_NBLANK | @@ -1531,14 +1644,19 @@ static enum drm_connector_status radeon_legacy_tv_dac_detect(struct drm_encoder WREG32(RADEON_DAC_CNTL2, dac_cntl2); WREG32(RADEON_DAC_EXT_CNTL, dac_ext_cntl); WREG32(RADEON_TV_DAC_CNTL, tv_dac_cntl); - WREG32(RADEON_CRTC2_GEN_CNTL, crtc2_gen_cntl); - if (ASIC_IS_R300(rdev)) { - WREG32(RADEON_DISP_OUTPUT_CNTL, disp_output_cntl); - WREG32_P(RADEON_GPIOPAD_A, gpiopad_a, ~1); + if (rdev->flags & RADEON_SINGLE_CRTC) { + WREG32(RADEON_CRTC_EXT_CNTL, crtc_ext_cntl); } else { - WREG32(RADEON_DISP_HW_DEBUG, disp_hw_debug); + WREG32(RADEON_CRTC2_GEN_CNTL, crtc2_gen_cntl); + if (ASIC_IS_R300(rdev)) { + WREG32(RADEON_DISP_OUTPUT_CNTL, disp_output_cntl); + WREG32_P(RADEON_GPIOPAD_A, gpiopad_a, ~1); + } else { + WREG32(RADEON_DISP_HW_DEBUG, disp_hw_debug); + } } + WREG32_PLL(RADEON_PIXCLKS_CNTL, pixclks_cntl); return found; diff --git a/drivers/gpu/drm/radeon/radeon_object.c b/drivers/gpu/drm/radeon/radeon_object.c index 8b27dd6e3144..b91118ccef86 100644 --- a/drivers/gpu/drm/radeon/radeon_object.c +++ b/drivers/gpu/drm/radeon/radeon_object.c @@ -105,7 +105,6 @@ int radeon_bo_create(struct radeon_device *rdev, struct radeon_bo *bo; enum ttm_bo_type type; unsigned long page_align = roundup(byte_align, PAGE_SIZE) >> PAGE_SHIFT; - unsigned long max_size = 0; size_t acc_size; int r; @@ -121,18 +120,9 @@ int radeon_bo_create(struct radeon_device *rdev, } *bo_ptr = NULL; - /* maximun bo size is the minimun btw visible vram and gtt size */ - max_size = min(rdev->mc.visible_vram_size, rdev->mc.gtt_size); - if ((page_align << PAGE_SHIFT) >= max_size) { - printk(KERN_WARNING "%s:%d alloc size %ldM bigger than %ldMb limit\n", - __func__, __LINE__, page_align >> (20 - PAGE_SHIFT), max_size >> 20); - return -ENOMEM; - } - acc_size = ttm_bo_dma_acc_size(&rdev->mman.bdev, size, sizeof(struct radeon_bo)); -retry: bo = kzalloc(sizeof(struct radeon_bo), GFP_KERNEL); if (bo == NULL) return -ENOMEM; @@ -154,15 +144,6 @@ retry: acc_size, sg, &radeon_ttm_bo_destroy); up_read(&rdev->pm.mclk_lock); if (unlikely(r != 0)) { - if (r != -ERESTARTSYS) { - if (domain == RADEON_GEM_DOMAIN_VRAM) { - domain |= RADEON_GEM_DOMAIN_GTT; - goto retry; - } - dev_err(rdev->dev, - "object_init failed for (%lu, 0x%08X)\n", - size, domain); - } return r; } *bo_ptr = bo; diff --git a/drivers/gpu/drm/radeon/radeon_ring.c b/drivers/gpu/drm/radeon/radeon_ring.c index bba66902c83b..47634f27f2e5 100644 --- a/drivers/gpu/drm/radeon/radeon_ring.c +++ b/drivers/gpu/drm/radeon/radeon_ring.c @@ -305,7 +305,7 @@ void radeon_ring_write(struct radeon_ring *ring, uint32_t v) { #if DRM_DEBUG_CODE if (ring->count_dw <= 0) { - DRM_ERROR("radeon: writting more dword to ring than expected !\n"); + DRM_ERROR("radeon: writing more dwords to the ring than expected!\n"); } #endif ring->ring[ring->wptr++] = v; diff --git a/drivers/gpu/drm/radeon/si.c b/drivers/gpu/drm/radeon/si.c index f79633a036c3..4422d630b33b 100644 --- a/drivers/gpu/drm/radeon/si.c +++ b/drivers/gpu/drm/radeon/si.c @@ -2407,12 +2407,13 @@ static int si_pcie_gart_enable(struct radeon_device *rdev) WREG32(0x15DC, 0); /* empty context1-15 */ - /* FIXME start with 4G, once using 2 level pt switch to full - * vm size space - */ /* set vm size, must be a multiple of 4 */ WREG32(VM_CONTEXT1_PAGE_TABLE_START_ADDR, 0); WREG32(VM_CONTEXT1_PAGE_TABLE_END_ADDR, rdev->vm_manager.max_pfn); + /* Assign the pt base to something valid for now; the pts used for + * the VMs are determined by the application and setup and assigned + * on the fly in the vm part of radeon_gart.c + */ for (i = 1; i < 16; i++) { if (i < 8) WREG32(VM_CONTEXT0_PAGE_TABLE_BASE_ADDR + (i << 2), @@ -2473,6 +2474,7 @@ static bool si_vm_reg_valid(u32 reg) /* check config regs */ switch (reg) { case GRBM_GFX_INDEX: + case CP_STRMOUT_CNTL: case VGT_VTX_VECT_EJECT_REG: case VGT_CACHE_INVALIDATION: case VGT_ESGS_RING_SIZE: @@ -2807,26 +2809,31 @@ void si_vm_set_page(struct radeon_device *rdev, uint64_t pe, { struct radeon_ring *ring = &rdev->ring[rdev->asic->vm.pt_ring_index]; uint32_t r600_flags = cayman_vm_page_flags(rdev, flags); - int i; - uint64_t value; - radeon_ring_write(ring, PACKET3(PACKET3_WRITE_DATA, 2 + count * 2)); - radeon_ring_write(ring, (WRITE_DATA_ENGINE_SEL(0) | - WRITE_DATA_DST_SEL(1))); - radeon_ring_write(ring, pe); - radeon_ring_write(ring, upper_32_bits(pe)); - for (i = 0; i < count; ++i) { - if (flags & RADEON_VM_PAGE_SYSTEM) { - value = radeon_vm_map_gart(rdev, addr); - value &= 0xFFFFFFFFFFFFF000ULL; - } else if (flags & RADEON_VM_PAGE_VALID) - value = addr; - else - value = 0; - addr += incr; - value |= r600_flags; - radeon_ring_write(ring, value); - radeon_ring_write(ring, upper_32_bits(value)); + while (count) { + unsigned ndw = 2 + count * 2; + if (ndw > 0x3FFE) + ndw = 0x3FFE; + + radeon_ring_write(ring, PACKET3(PACKET3_WRITE_DATA, ndw)); + radeon_ring_write(ring, (WRITE_DATA_ENGINE_SEL(0) | + WRITE_DATA_DST_SEL(1))); + radeon_ring_write(ring, pe); + radeon_ring_write(ring, upper_32_bits(pe)); + for (; ndw > 2; ndw -= 2, --count, pe += 8) { + uint64_t value; + if (flags & RADEON_VM_PAGE_SYSTEM) { + value = radeon_vm_map_gart(rdev, addr); + value &= 0xFFFFFFFFFFFFF000ULL; + } else if (flags & RADEON_VM_PAGE_VALID) + value = addr; + else + value = 0; + addr += incr; + value |= r600_flags; + radeon_ring_write(ring, value); + radeon_ring_write(ring, upper_32_bits(value)); + } } } @@ -2867,6 +2874,10 @@ void si_vm_flush(struct radeon_device *rdev, int ridx, struct radeon_vm *vm) radeon_ring_write(ring, VM_INVALIDATE_REQUEST >> 2); radeon_ring_write(ring, 0); radeon_ring_write(ring, 1 << vm->id); + + /* sync PFP to ME, otherwise we might get invalid PFP reads */ + radeon_ring_write(ring, PACKET3(PACKET3_PFP_SYNC_ME, 0)); + radeon_ring_write(ring, 0x0); } /* diff --git a/drivers/gpu/drm/radeon/sid.h b/drivers/gpu/drm/radeon/sid.h index 7d2a20e56577..a8871afc5b4e 100644 --- a/drivers/gpu/drm/radeon/sid.h +++ b/drivers/gpu/drm/radeon/sid.h @@ -424,6 +424,7 @@ # define RDERR_INT_ENABLE (1 << 0) # define GUI_IDLE_INT_ENABLE (1 << 19) +#define CP_STRMOUT_CNTL 0x84FC #define SCRATCH_REG0 0x8500 #define SCRATCH_REG1 0x8504 #define SCRATCH_REG2 0x8508 |