diff options
48 files changed, 2904 insertions, 750 deletions
diff --git a/Documentation/devicetree/bindings/display/msm/dsi.txt b/Documentation/devicetree/bindings/display/msm/dsi.txt index fa00e62e1cf6..a6671bd2c85a 100644 --- a/Documentation/devicetree/bindings/display/msm/dsi.txt +++ b/Documentation/devicetree/bindings/display/msm/dsi.txt @@ -13,16 +13,16 @@ Required properties: - power-domains: Should be <&mmcc MDSS_GDSC>. - clocks: Phandles to device clocks. - clock-names: the following clocks are required: - * "mdp_core_clk" - * "iface_clk" - * "bus_clk" - * "core_mmss_clk" - * "byte_clk" - * "pixel_clk" - * "core_clk" + * "mdp_core" + * "iface" + * "bus" + * "core_mmss" + * "byte" + * "pixel" + * "core" For DSIv2, we need an additional clock: - * "src_clk" -- assigned-clocks: Parents of "byte_clk" and "pixel_clk" for the given platform. + * "src" +- assigned-clocks: Parents of "byte" and "pixel" for the given platform. - assigned-clock-parents: The Byte clock and Pixel clock PLL outputs provided by a DSI PHY block. See [1] for details on clock bindings. - vdd-supply: phandle to vdd regulator device node @@ -101,7 +101,7 @@ Required properties: - power-domains: Should be <&mmcc MDSS_GDSC>. - clocks: Phandles to device clocks. See [1] for details on clock bindings. - clock-names: the following clocks are required: - * "iface_clk" + * "iface" - vddio-supply: phandle to vdd-io regulator device node Optional properties: @@ -123,13 +123,13 @@ Example: reg = <0xfd922800 0x200>; power-domains = <&mmcc MDSS_GDSC>; clock-names = - "bus_clk", - "byte_clk", - "core_clk", - "core_mmss_clk", - "iface_clk", - "mdp_core_clk", - "pixel_clk"; + "bus", + "byte", + "core", + "core_mmss", + "iface", + "mdp_core", + "pixel"; clocks = <&mmcc MDSS_AXI_CLK>, <&mmcc MDSS_BYTE0_CLK>, @@ -207,7 +207,7 @@ Example: reg = <0xfd922a00 0xd4>, <0xfd922b00 0x2b0>, <0xfd922d80 0x7b>; - clock-names = "iface_clk"; + clock-names = "iface"; clocks = <&mmcc MDSS_AHB_CLK>; #clock-cells = <1>; vddio-supply = <&pma8084_l12>; diff --git a/Documentation/devicetree/bindings/display/msm/edp.txt b/Documentation/devicetree/bindings/display/msm/edp.txt index e63032be5401..95ce19ca7bc5 100644 --- a/Documentation/devicetree/bindings/display/msm/edp.txt +++ b/Documentation/devicetree/bindings/display/msm/edp.txt @@ -12,11 +12,11 @@ Required properties: - clocks: device clocks See Documentation/devicetree/bindings/clock/clock-bindings.txt for details. - clock-names: the following clocks are required: - * "core_clk" - * "iface_clk" - * "mdp_core_clk" - * "pixel_clk" - * "link_clk" + * "core" + * "iface" + * "mdp_core" + * "pixel" + * "link" - #clock-cells: The value should be 1. - vdda-supply: phandle to vdda regulator device node - lvl-vdd-supply: phandle to regulator device node which is used to supply power @@ -41,11 +41,11 @@ Example: interrupts = <12 0>; power-domains = <&mmcc MDSS_GDSC>; clock-names = - "core_clk", - "pixel_clk", - "iface_clk", - "link_clk", - "mdp_core_clk"; + "core", + "pixel", + "iface", + "link", + "mdp_core"; clocks = <&mmcc MDSS_EDPAUX_CLK>, <&mmcc MDSS_EDPPIXEL_CLK>, diff --git a/Documentation/devicetree/bindings/display/msm/hdmi.txt b/Documentation/devicetree/bindings/display/msm/hdmi.txt index 2d306f402d18..5f90a40da51b 100644 --- a/Documentation/devicetree/bindings/display/msm/hdmi.txt +++ b/Documentation/devicetree/bindings/display/msm/hdmi.txt @@ -64,9 +64,9 @@ Example: interrupts = <GIC_SPI 79 0>; power-domains = <&mmcc MDSS_GDSC>; clock-names = - "core_clk", - "master_iface_clk", - "slave_iface_clk"; + "core", + "master_iface", + "slave_iface"; clocks = <&mmcc HDMI_APP_CLK>, <&mmcc HDMI_M_AHB_CLK>, @@ -92,7 +92,7 @@ Example: <0x4a00500 0x100>; #phy-cells = <0>; power-domains = <&mmcc MDSS_GDSC>; - clock-names = "slave_iface_clk"; + clock-names = "slave_iface"; clocks = <&mmcc HDMI_S_AHB_CLK>; core-vdda-supply = <&pm8921_hdmi_mvs>; }; diff --git a/Documentation/devicetree/bindings/display/msm/mdp5.txt b/Documentation/devicetree/bindings/display/msm/mdp5.txt index 30c11ea83754..1b31977a68ba 100644 --- a/Documentation/devicetree/bindings/display/msm/mdp5.txt +++ b/Documentation/devicetree/bindings/display/msm/mdp5.txt @@ -22,16 +22,16 @@ Required properties: Documentation/devicetree/bindings/power/power_domain.txt - clocks: device clocks. See ../clocks/clock-bindings.txt for details. - clock-names: the following clocks are required. - * "iface_clk" - * "bus_clk" - * "vsync_clk" + * "iface" + * "bus" + * "vsync" - #address-cells: number of address cells for the MDSS children. Should be 1. - #size-cells: Should be 1. - ranges: parent bus address space is the same as the child bus address space. Optional properties: - clock-names: the following clocks are optional: - * "lut_clk" + * "lut" MDP5: Required properties: @@ -45,10 +45,10 @@ Required properties: through MDP block - clocks: device clocks. See ../clocks/clock-bindings.txt for details. - clock-names: the following clocks are required. -- * "bus_clk" -- * "iface_clk" -- * "core_clk" -- * "vsync_clk" +- * "bus" +- * "iface" +- * "core" +- * "vsync" - ports: contains the list of output ports from MDP. These connect to interfaces that are external to the MDP hardware, such as HDMI, DSI, EDP etc (LVDS is a special case since it is a part of the MDP block itself). @@ -77,7 +77,7 @@ Required properties: Optional properties: - clock-names: the following clocks are optional: - * "lut_clk" + * "lut" Example: @@ -95,9 +95,9 @@ Example: clocks = <&gcc GCC_MDSS_AHB_CLK>, <&gcc GCC_MDSS_AXI_CLK>, <&gcc GCC_MDSS_VSYNC_CLK>; - clock-names = "iface_clk", - "bus_clk", - "vsync_clk" + clock-names = "iface", + "bus", + "vsync" interrupts = <0 72 0>; @@ -120,10 +120,10 @@ Example: <&gcc GCC_MDSS_AXI_CLK>, <&gcc GCC_MDSS_MDP_CLK>, <&gcc GCC_MDSS_VSYNC_CLK>; - clock-names = "iface_clk", - "bus_clk", - "core_clk", - "vsync_clk"; + clock-names = "iface", + "bus", + "core", + "vsync"; ports { #address-cells = <1>; diff --git a/drivers/gpu/drm/msm/Makefile b/drivers/gpu/drm/msm/Makefile index 33008fa1be9b..d0b26dd80076 100644 --- a/drivers/gpu/drm/msm/Makefile +++ b/drivers/gpu/drm/msm/Makefile @@ -8,6 +8,7 @@ msm-y := \ adreno/a4xx_gpu.o \ adreno/a5xx_gpu.o \ adreno/a5xx_power.o \ + adreno/a5xx_preempt.o \ hdmi/hdmi.o \ hdmi/hdmi_audio.o \ hdmi/hdmi_bridge.o \ @@ -57,7 +58,8 @@ msm-y := \ msm_iommu.o \ msm_perf.o \ msm_rd.o \ - msm_ringbuffer.o + msm_ringbuffer.o \ + msm_submitqueue.o msm-$(CONFIG_DRM_FBDEV_EMULATION) += msm_fbdev.o msm-$(CONFIG_COMMON_CLK) += mdp/mdp4/mdp4_lvds_pll.o diff --git a/drivers/gpu/drm/msm/adreno/a3xx_gpu.c b/drivers/gpu/drm/msm/adreno/a3xx_gpu.c index 7791313405b5..4baef2738178 100644 --- a/drivers/gpu/drm/msm/adreno/a3xx_gpu.c +++ b/drivers/gpu/drm/msm/adreno/a3xx_gpu.c @@ -44,7 +44,7 @@ static bool a3xx_idle(struct msm_gpu *gpu); static bool a3xx_me_init(struct msm_gpu *gpu) { - struct msm_ringbuffer *ring = gpu->rb; + struct msm_ringbuffer *ring = gpu->rb[0]; OUT_PKT3(ring, CP_ME_INIT, 17); OUT_RING(ring, 0x000003f7); @@ -65,7 +65,7 @@ static bool a3xx_me_init(struct msm_gpu *gpu) OUT_RING(ring, 0x00000000); OUT_RING(ring, 0x00000000); - gpu->funcs->flush(gpu); + gpu->funcs->flush(gpu, ring); return a3xx_idle(gpu); } @@ -339,7 +339,7 @@ static void a3xx_destroy(struct msm_gpu *gpu) static bool a3xx_idle(struct msm_gpu *gpu) { /* wait for ringbuffer to drain: */ - if (!adreno_idle(gpu)) + if (!adreno_idle(gpu, gpu->rb[0])) return false; /* then wait for GPU to finish: */ @@ -444,9 +444,9 @@ static const struct adreno_gpu_funcs funcs = { .pm_suspend = msm_gpu_pm_suspend, .pm_resume = msm_gpu_pm_resume, .recover = a3xx_recover, - .last_fence = adreno_last_fence, .submit = adreno_submit, .flush = adreno_flush, + .active_ring = adreno_active_ring, .irq = a3xx_irq, .destroy = a3xx_destroy, #ifdef CONFIG_DEBUG_FS @@ -492,7 +492,7 @@ struct msm_gpu *a3xx_gpu_init(struct drm_device *dev) adreno_gpu->registers = a3xx_registers; adreno_gpu->reg_offsets = a3xx_register_offsets; - ret = adreno_gpu_init(dev, pdev, adreno_gpu, &funcs); + ret = adreno_gpu_init(dev, pdev, adreno_gpu, &funcs, 1); if (ret) goto fail; diff --git a/drivers/gpu/drm/msm/adreno/a4xx_gpu.c b/drivers/gpu/drm/msm/adreno/a4xx_gpu.c index 58341ef6f15b..8199a4b9f2fa 100644 --- a/drivers/gpu/drm/msm/adreno/a4xx_gpu.c +++ b/drivers/gpu/drm/msm/adreno/a4xx_gpu.c @@ -116,7 +116,7 @@ static void a4xx_enable_hwcg(struct msm_gpu *gpu) static bool a4xx_me_init(struct msm_gpu *gpu) { - struct msm_ringbuffer *ring = gpu->rb; + struct msm_ringbuffer *ring = gpu->rb[0]; OUT_PKT3(ring, CP_ME_INIT, 17); OUT_RING(ring, 0x000003f7); @@ -137,7 +137,7 @@ static bool a4xx_me_init(struct msm_gpu *gpu) OUT_RING(ring, 0x00000000); OUT_RING(ring, 0x00000000); - gpu->funcs->flush(gpu); + gpu->funcs->flush(gpu, ring); return a4xx_idle(gpu); } @@ -337,7 +337,7 @@ static void a4xx_destroy(struct msm_gpu *gpu) static bool a4xx_idle(struct msm_gpu *gpu) { /* wait for ringbuffer to drain: */ - if (!adreno_idle(gpu)) + if (!adreno_idle(gpu, gpu->rb[0])) return false; /* then wait for GPU to finish: */ @@ -532,9 +532,9 @@ static const struct adreno_gpu_funcs funcs = { .pm_suspend = a4xx_pm_suspend, .pm_resume = a4xx_pm_resume, .recover = a4xx_recover, - .last_fence = adreno_last_fence, .submit = adreno_submit, .flush = adreno_flush, + .active_ring = adreno_active_ring, .irq = a4xx_irq, .destroy = a4xx_destroy, #ifdef CONFIG_DEBUG_FS @@ -574,7 +574,7 @@ struct msm_gpu *a4xx_gpu_init(struct drm_device *dev) adreno_gpu->registers = a4xx_registers; adreno_gpu->reg_offsets = a4xx_register_offsets; - ret = adreno_gpu_init(dev, pdev, adreno_gpu, &funcs); + ret = adreno_gpu_init(dev, pdev, adreno_gpu, &funcs, 1); if (ret) goto fail; diff --git a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c index 17c59d839e6f..a1f4eeeb73e2 100644 --- a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c +++ b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c @@ -26,8 +26,9 @@ static void a5xx_dump(struct msm_gpu *gpu); #define GPU_PAS_ID 13 -static int zap_shader_load_mdt(struct device *dev, const char *fwname) +static int zap_shader_load_mdt(struct msm_gpu *gpu, const char *fwname) { + struct device *dev = &gpu->pdev->dev; const struct firmware *fw; struct device_node *np; struct resource r; @@ -55,10 +56,10 @@ static int zap_shader_load_mdt(struct device *dev, const char *fwname) mem_size = resource_size(&r); /* Request the MDT file for the firmware */ - ret = request_firmware(&fw, fwname, dev); - if (ret) { + fw = adreno_request_fw(to_adreno_gpu(gpu), fwname); + if (IS_ERR(fw)) { DRM_DEV_ERROR(dev, "Unable to load %s\n", fwname); - return ret; + return PTR_ERR(fw); } /* Figure out how much memory we need */ @@ -75,9 +76,26 @@ static int zap_shader_load_mdt(struct device *dev, const char *fwname) goto out; } - /* Load the rest of the MDT */ - ret = qcom_mdt_load(dev, fw, fwname, GPU_PAS_ID, mem_region, mem_phys, - mem_size); + /* + * Load the rest of the MDT + * + * Note that we could be dealing with two different paths, since + * with upstream linux-firmware it would be in a qcom/ subdir.. + * adreno_request_fw() handles this, but qcom_mdt_load() does + * not. But since we've already gotten thru adreno_request_fw() + * we know which of the two cases it is: + */ + if (to_adreno_gpu(gpu)->fwloc == FW_LOCATION_LEGACY) { + ret = qcom_mdt_load(dev, fw, fwname, GPU_PAS_ID, + mem_region, mem_phys, mem_size); + } else { + char newname[strlen("qcom/") + strlen(fwname) + 1]; + + sprintf(newname, "qcom/%s", fwname); + + ret = qcom_mdt_load(dev, fw, newname, GPU_PAS_ID, + mem_region, mem_phys, mem_size); + } if (ret) goto out; @@ -95,14 +113,65 @@ out: return ret; } +static void a5xx_flush(struct msm_gpu *gpu, struct msm_ringbuffer *ring) +{ + struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu); + struct a5xx_gpu *a5xx_gpu = to_a5xx_gpu(adreno_gpu); + uint32_t wptr; + unsigned long flags; + + spin_lock_irqsave(&ring->lock, flags); + + /* Copy the shadow to the actual register */ + ring->cur = ring->next; + + /* Make sure to wrap wptr if we need to */ + wptr = get_wptr(ring); + + spin_unlock_irqrestore(&ring->lock, flags); + + /* Make sure everything is posted before making a decision */ + mb(); + + /* Update HW if this is the current ring and we are not in preempt */ + if (a5xx_gpu->cur_ring == ring && !a5xx_in_preempt(a5xx_gpu)) + gpu_write(gpu, REG_A5XX_CP_RB_WPTR, wptr); +} + static void a5xx_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit, struct msm_file_private *ctx) { struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu); + struct a5xx_gpu *a5xx_gpu = to_a5xx_gpu(adreno_gpu); struct msm_drm_private *priv = gpu->dev->dev_private; - struct msm_ringbuffer *ring = gpu->rb; + struct msm_ringbuffer *ring = submit->ring; unsigned int i, ibs = 0; + OUT_PKT7(ring, CP_PREEMPT_ENABLE_GLOBAL, 1); + OUT_RING(ring, 0x02); + + /* Turn off protected mode to write to special registers */ + OUT_PKT7(ring, CP_SET_PROTECTED_MODE, 1); + OUT_RING(ring, 0); + + /* Set the save preemption record for the ring/command */ + OUT_PKT4(ring, REG_A5XX_CP_CONTEXT_SWITCH_SAVE_ADDR_LO, 2); + OUT_RING(ring, lower_32_bits(a5xx_gpu->preempt_iova[submit->ring->id])); + OUT_RING(ring, upper_32_bits(a5xx_gpu->preempt_iova[submit->ring->id])); + + /* Turn back on protected mode */ + OUT_PKT7(ring, CP_SET_PROTECTED_MODE, 1); + OUT_RING(ring, 1); + + /* Enable local preemption for finegrain preemption */ + OUT_PKT7(ring, CP_PREEMPT_ENABLE_GLOBAL, 1); + OUT_RING(ring, 0x02); + + /* Allow CP_CONTEXT_SWITCH_YIELD packets in the IB2 */ + OUT_PKT7(ring, CP_YIELD_ENABLE, 1); + OUT_RING(ring, 0x02); + + /* Submit the commands */ for (i = 0; i < submit->nr_cmds; i++) { switch (submit->cmd[i].type) { case MSM_SUBMIT_CMD_IB_TARGET_BUF: @@ -120,16 +189,54 @@ static void a5xx_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit, } } + /* + * Write the render mode to NULL (0) to indicate to the CP that the IBs + * are done rendering - otherwise a lucky preemption would start + * replaying from the last checkpoint + */ + OUT_PKT7(ring, CP_SET_RENDER_MODE, 5); + OUT_RING(ring, 0); + OUT_RING(ring, 0); + OUT_RING(ring, 0); + OUT_RING(ring, 0); + OUT_RING(ring, 0); + + /* Turn off IB level preemptions */ + OUT_PKT7(ring, CP_YIELD_ENABLE, 1); + OUT_RING(ring, 0x01); + + /* Write the fence to the scratch register */ OUT_PKT4(ring, REG_A5XX_CP_SCRATCH_REG(2), 1); - OUT_RING(ring, submit->fence->seqno); + OUT_RING(ring, submit->seqno); + /* + * Execute a CACHE_FLUSH_TS event. This will ensure that the + * timestamp is written to the memory and then triggers the interrupt + */ OUT_PKT7(ring, CP_EVENT_WRITE, 4); OUT_RING(ring, CACHE_FLUSH_TS | (1 << 31)); - OUT_RING(ring, lower_32_bits(rbmemptr(adreno_gpu, fence))); - OUT_RING(ring, upper_32_bits(rbmemptr(adreno_gpu, fence))); - OUT_RING(ring, submit->fence->seqno); + OUT_RING(ring, lower_32_bits(rbmemptr(ring, fence))); + OUT_RING(ring, upper_32_bits(rbmemptr(ring, fence))); + OUT_RING(ring, submit->seqno); - gpu->funcs->flush(gpu); + /* Yield the floor on command completion */ + OUT_PKT7(ring, CP_CONTEXT_SWITCH_YIELD, 4); + /* + * If dword[2:1] are non zero, they specify an address for the CP to + * write the value of dword[3] to on preemption complete. Write 0 to + * skip the write + */ + OUT_RING(ring, 0x00); + OUT_RING(ring, 0x00); + /* Data value - not used if the address above is 0 */ + OUT_RING(ring, 0x01); + /* Set bit 0 to trigger an interrupt on preempt complete */ + OUT_RING(ring, 0x01); + + a5xx_flush(gpu, ring); + + /* Check to see if we need to start preemption */ + a5xx_preempt_trigger(gpu); } static const struct { @@ -245,7 +352,7 @@ void a5xx_set_hwcg(struct msm_gpu *gpu, bool state) static int a5xx_me_init(struct msm_gpu *gpu) { struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu); - struct msm_ringbuffer *ring = gpu->rb; + struct msm_ringbuffer *ring = gpu->rb[0]; OUT_PKT7(ring, CP_ME_INIT, 8); @@ -276,11 +383,54 @@ static int a5xx_me_init(struct msm_gpu *gpu) OUT_RING(ring, 0x00000000); OUT_RING(ring, 0x00000000); - gpu->funcs->flush(gpu); + gpu->funcs->flush(gpu, ring); + return a5xx_idle(gpu, ring) ? 0 : -EINVAL; +} + +static int a5xx_preempt_start(struct msm_gpu *gpu) +{ + struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu); + struct a5xx_gpu *a5xx_gpu = to_a5xx_gpu(adreno_gpu); + struct msm_ringbuffer *ring = gpu->rb[0]; + + if (gpu->nr_rings == 1) + return 0; + + /* Turn off protected mode to write to special registers */ + OUT_PKT7(ring, CP_SET_PROTECTED_MODE, 1); + OUT_RING(ring, 0); + + /* Set the save preemption record for the ring/command */ + OUT_PKT4(ring, REG_A5XX_CP_CONTEXT_SWITCH_SAVE_ADDR_LO, 2); + OUT_RING(ring, lower_32_bits(a5xx_gpu->preempt_iova[ring->id])); + OUT_RING(ring, upper_32_bits(a5xx_gpu->preempt_iova[ring->id])); + + /* Turn back on protected mode */ + OUT_PKT7(ring, CP_SET_PROTECTED_MODE, 1); + OUT_RING(ring, 1); + + OUT_PKT7(ring, CP_PREEMPT_ENABLE_GLOBAL, 1); + OUT_RING(ring, 0x00); + + OUT_PKT7(ring, CP_PREEMPT_ENABLE_LOCAL, 1); + OUT_RING(ring, 0x01); - return a5xx_idle(gpu) ? 0 : -EINVAL; + OUT_PKT7(ring, CP_YIELD_ENABLE, 1); + OUT_RING(ring, 0x01); + + /* Yield the floor on command completion */ + OUT_PKT7(ring, CP_CONTEXT_SWITCH_YIELD, 4); + OUT_RING(ring, 0x00); + OUT_RING(ring, 0x00); + OUT_RING(ring, 0x01); + OUT_RING(ring, 0x01); + + gpu->funcs->flush(gpu, ring); + + return a5xx_idle(gpu, ring) ? 0 : -EINVAL; } + static struct drm_gem_object *a5xx_ucode_load_bo(struct msm_gpu *gpu, const struct firmware *fw, u64 *iova) { @@ -381,7 +531,7 @@ static int a5xx_zap_shader_init(struct msm_gpu *gpu) return -ENODEV; } - ret = zap_shader_load_mdt(&pdev->dev, adreno_gpu->info->zapfw); + ret = zap_shader_load_mdt(gpu, adreno_gpu->info->zapfw); loaded = !ret; @@ -396,6 +546,7 @@ static int a5xx_zap_shader_init(struct msm_gpu *gpu) A5XX_RBBM_INT_0_MASK_RBBM_ATB_ASYNC_OVERFLOW | \ A5XX_RBBM_INT_0_MASK_CP_HW_ERROR | \ A5XX_RBBM_INT_0_MASK_MISC_HANG_DETECT | \ + A5XX_RBBM_INT_0_MASK_CP_SW | \ A5XX_RBBM_INT_0_MASK_CP_CACHE_FLUSH_TS | \ A5XX_RBBM_INT_0_MASK_UCHE_OOB_ACCESS | \ A5XX_RBBM_INT_0_MASK_GPMU_VOLTAGE_DROOP) @@ -536,13 +687,14 @@ static int a5xx_hw_init(struct msm_gpu *gpu) REG_A5XX_RBBM_SECVID_TSB_TRUSTED_BASE_HI, 0x00000000); gpu_write(gpu, REG_A5XX_RBBM_SECVID_TSB_TRUSTED_SIZE, 0x00000000); - /* Load the GPMU firmware before starting the HW init */ - a5xx_gpmu_ucode_init(gpu); - ret = adreno_hw_init(gpu); if (ret) return ret; + a5xx_preempt_hw_init(gpu); + + a5xx_gpmu_ucode_init(gpu); + ret = a5xx_ucode_init(gpu); if (ret) return ret; @@ -565,11 +717,11 @@ static int a5xx_hw_init(struct msm_gpu *gpu) * ticking correctly */ if (adreno_is_a530(adreno_gpu)) { - OUT_PKT7(gpu->rb, CP_EVENT_WRITE, 1); - OUT_RING(gpu->rb, 0x0F); + OUT_PKT7(gpu->rb[0], CP_EVENT_WRITE, 1); + OUT_RING(gpu->rb[0], 0x0F); - gpu->funcs->flush(gpu); - if (!a5xx_idle(gpu)) + gpu->funcs->flush(gpu, gpu->rb[0]); + if (!a5xx_idle(gpu, gpu->rb[0])) return -EINVAL; } @@ -582,11 +734,11 @@ static int a5xx_hw_init(struct msm_gpu *gpu) */ ret = a5xx_zap_shader_init(gpu); if (!ret) { - OUT_PKT7(gpu->rb, CP_SET_SECURE_MODE, 1); - OUT_RING(gpu->rb, 0x00000000); + OUT_PKT7(gpu->rb[0], CP_SET_SECURE_MODE, 1); + OUT_RING(gpu->rb[0], 0x00000000); - gpu->funcs->flush(gpu); - if (!a5xx_idle(gpu)) + gpu->funcs->flush(gpu, gpu->rb[0]); + if (!a5xx_idle(gpu, gpu->rb[0])) return -EINVAL; } else { /* Print a warning so if we die, we know why */ @@ -595,6 +747,9 @@ static int a5xx_hw_init(struct msm_gpu *gpu) gpu_write(gpu, REG_A5XX_RBBM_SECVID_TRUST_CNTL, 0x0); } + /* Last step - yield the ringbuffer */ + a5xx_preempt_start(gpu); + return 0; } @@ -625,6 +780,8 @@ static void a5xx_destroy(struct msm_gpu *gpu) DBG("%s", gpu->name); + a5xx_preempt_fini(gpu); + if (a5xx_gpu->pm4_bo) { if (a5xx_gpu->pm4_iova) msm_gem_put_iova(a5xx_gpu->pm4_bo, gpu->aspace); @@ -660,18 +817,27 @@ static inline bool _a5xx_check_idle(struct msm_gpu *gpu) A5XX_RBBM_INT_0_MASK_MISC_HANG_DETECT); } -bool a5xx_idle(struct msm_gpu *gpu) +bool a5xx_idle(struct msm_gpu *gpu, struct msm_ringbuffer *ring) { + struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu); + struct a5xx_gpu *a5xx_gpu = to_a5xx_gpu(adreno_gpu); + + if (ring != a5xx_gpu->cur_ring) { + WARN(1, "Tried to idle a non-current ringbuffer\n"); + return false; + } + /* wait for CP to drain ringbuffer: */ - if (!adreno_idle(gpu)) + if (!adreno_idle(gpu, ring)) return false; if (spin_until(_a5xx_check_idle(gpu))) { - DRM_ERROR("%s: %ps: timeout waiting for GPU to idle: status %8.8X irq %8.8X\n", + DRM_ERROR("%s: %ps: timeout |