1 files changed, 266 insertions, 114 deletions

diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.c b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
index c8b4ac254bb5..de63ff26a062 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
@@ -17,13 +17,11 @@
  * this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
+#include <linux/pm_opp.h>
 #include "adreno_gpu.h"
 #include "msm_gem.h"
 #include "msm_mmu.h"
 
-#define RB_SIZE    SZ_32K
-#define RB_BLKSIZE 32
-
 int adreno_get_param(struct msm_gpu *gpu, uint32_t param, uint64_t *value)
 {
 	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
@@ -58,72 +56,181 @@ int adreno_get_param(struct msm_gpu *gpu, uint32_t param, uint64_t *value)
 			return ret;
 		}
 		return -EINVAL;
+	case MSM_PARAM_NR_RINGS:
+		*value = gpu->nr_rings;
+		return 0;
 	default:
 		DBG("%s: invalid param: %u", gpu->name, param);
 		return -EINVAL;
 	}
 }
 
+const struct firmware *
+adreno_request_fw(struct adreno_gpu *adreno_gpu, const char *fwname)
+{
+	struct drm_device *drm = adreno_gpu->base.dev;
+	const struct firmware *fw = NULL;
+	char newname[strlen("qcom/") + strlen(fwname) + 1];
+	int ret;
+
+	sprintf(newname, "qcom/%s", fwname);
+
+	/*
+	 * Try first to load from qcom/$fwfile using a direct load (to avoid
+	 * a potential timeout waiting for usermode helper)
+	 */
+	if ((adreno_gpu->fwloc == FW_LOCATION_UNKNOWN) ||
+	    (adreno_gpu->fwloc == FW_LOCATION_NEW)) {
+
+		ret = request_firmware_direct(&fw, newname, drm->dev);
+		if (!ret) {
+			dev_info(drm->dev, "loaded %s from new location\n",
+				newname);
+			adreno_gpu->fwloc = FW_LOCATION_NEW;
+			return fw;
+		} else if (adreno_gpu->fwloc != FW_LOCATION_UNKNOWN) {
+			dev_err(drm->dev, "failed to load %s: %d\n",
+				newname, ret);
+			return ERR_PTR(ret);
+		}
+	}
+
+	/*
+	 * Then try the legacy location without qcom/ prefix
+	 */
+	if ((adreno_gpu->fwloc == FW_LOCATION_UNKNOWN) ||
+	    (adreno_gpu->fwloc == FW_LOCATION_LEGACY)) {
+
+		ret = request_firmware_direct(&fw, fwname, drm->dev);
+		if (!ret) {
+			dev_info(drm->dev, "loaded %s from legacy location\n",
+				newname);
+			adreno_gpu->fwloc = FW_LOCATION_LEGACY;
+			return fw;
+		} else if (adreno_gpu->fwloc != FW_LOCATION_UNKNOWN) {
+			dev_err(drm->dev, "failed to load %s: %d\n",
+				fwname, ret);
+			return ERR_PTR(ret);
+		}
+	}
+
+	/*
+	 * Finally fall back to request_firmware() for cases where the
+	 * usermode helper is needed (I think mainly android)
+	 */
+	if ((adreno_gpu->fwloc == FW_LOCATION_UNKNOWN) ||
+	    (adreno_gpu->fwloc == FW_LOCATION_HELPER)) {
+
+		ret = request_firmware(&fw, newname, drm->dev);
+		if (!ret) {
+			dev_info(drm->dev, "loaded %s with helper\n",
+				newname);
+			adreno_gpu->fwloc = FW_LOCATION_HELPER;
+			return fw;
+		} else if (adreno_gpu->fwloc != FW_LOCATION_UNKNOWN) {
+			dev_err(drm->dev, "failed to load %s: %d\n",
+				newname, ret);
+			return ERR_PTR(ret);
+		}
+	}
+
+	dev_err(drm->dev, "failed to load %s\n", fwname);
+	return ERR_PTR(-ENOENT);
+}
+
+static int adreno_load_fw(struct adreno_gpu *adreno_gpu)
+{
+	const struct firmware *fw;
+
+	if (adreno_gpu->pm4)
+		return 0;
+
+	fw = adreno_request_fw(adreno_gpu, adreno_gpu->info->pm4fw);
+	if (IS_ERR(fw))
+		return PTR_ERR(fw);
+	adreno_gpu->pm4 = fw;
+
+	fw = adreno_request_fw(adreno_gpu, adreno_gpu->info->pfpfw);
+	if (IS_ERR(fw)) {
+		release_firmware(adreno_gpu->pm4);
+		adreno_gpu->pm4 = NULL;
+		return PTR_ERR(fw);
+	}
+	adreno_gpu->pfp = fw;
+
+	return 0;
+}
+
 int adreno_hw_init(struct msm_gpu *gpu)
 {
 	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
-	int ret;
+	int ret, i;
 
 	DBG("%s", gpu->name);
 
-	ret = msm_gem_get_iova(gpu->rb->bo, gpu->aspace, &gpu->rb_iova);
-	if (ret) {
-		gpu->rb_iova = 0;
-		dev_err(gpu->dev->dev, "could not map ringbuffer: %d\n", ret);
+	ret = adreno_load_fw(adreno_gpu);
+	if (ret)
 		return ret;
-	}
 
-	/* reset ringbuffer: */
-	gpu->rb->cur = gpu->rb->start;
+	for (i = 0; i < gpu->nr_rings; i++) {
+		struct msm_ringbuffer *ring = gpu->rb[i];
+
+		if (!ring)
+			continue;
+
+		ret = msm_gem_get_iova(ring->bo, gpu->aspace, &ring->iova);
+		if (ret) {
+			ring->iova = 0;
+			dev_err(gpu->dev->dev,
+				"could not map ringbuffer %d: %d\n", i, ret);
+			return ret;
+		}
+
+		ring->cur = ring->start;
+		ring->next = ring->start;
 
-	/* reset completed fence seqno: */
-	adreno_gpu->memptrs->fence = gpu->fctx->completed_fence;
-	adreno_gpu->memptrs->rptr  = 0;
+		/* reset completed fence seqno: */
+		ring->memptrs->fence = ring->seqno;
+		ring->memptrs->rptr = 0;
+	}
 
-	/* Setup REG_CP_RB_CNTL: */
+	/*
+	 * Setup REG_CP_RB_CNTL.  The same value is used across targets (with
+	 * the excpetion of A430 that disables the RPTR shadow) - the cacluation
+	 * for the ringbuffer size and block size is moved to msm_gpu.h for the
+	 * pre-processor to deal with and the A430 variant is ORed in here
+	 */
 	adreno_gpu_write(adreno_gpu, REG_ADRENO_CP_RB_CNTL,
-			/* size is log2(quad-words): */
-			AXXX_CP_RB_CNTL_BUFSZ(ilog2(gpu->rb->size / 8)) |
-			AXXX_CP_RB_CNTL_BLKSZ(ilog2(RB_BLKSIZE / 8)) |
-			(adreno_is_a430(adreno_gpu) ? AXXX_CP_RB_CNTL_NO_UPDATE : 0));
+		MSM_GPU_RB_CNTL_DEFAULT |
+		(adreno_is_a430(adreno_gpu) ? AXXX_CP_RB_CNTL_NO_UPDATE : 0));
 
-	/* Setup ringbuffer address: */
+	/* Setup ringbuffer address - use ringbuffer[0] for GPU init */
 	adreno_gpu_write64(adreno_gpu, REG_ADRENO_CP_RB_BASE,
-		REG_ADRENO_CP_RB_BASE_HI, gpu->rb_iova);
+		REG_ADRENO_CP_RB_BASE_HI, gpu->rb[0]->iova);
 
 	if (!adreno_is_a430(adreno_gpu)) {
 		adreno_gpu_write64(adreno_gpu, REG_ADRENO_CP_RB_RPTR_ADDR,
 			REG_ADRENO_CP_RB_RPTR_ADDR_HI,
-			rbmemptr(adreno_gpu, rptr));
+			rbmemptr(gpu->rb[0], rptr));
 	}
 
 	return 0;
 }
 
-static uint32_t get_wptr(struct msm_ringbuffer *ring)
-{
-	return ring->cur - ring->start;
-}
-
 /* Use this helper to read rptr, since a430 doesn't update rptr in memory */
-static uint32_t get_rptr(struct adreno_gpu *adreno_gpu)
+static uint32_t get_rptr(struct adreno_gpu *adreno_gpu,
+		struct msm_ringbuffer *ring)
 {
 	if (adreno_is_a430(adreno_gpu))
-		return adreno_gpu->memptrs->rptr = adreno_gpu_read(
+		return ring->memptrs->rptr = adreno_gpu_read(
 			adreno_gpu, REG_ADRENO_CP_RB_RPTR);
 	else
-		return adreno_gpu->memptrs->rptr;
+		return ring->memptrs->rptr;
 }
 
-uint32_t adreno_last_fence(struct msm_gpu *gpu)
+struct msm_ringbuffer *adreno_active_ring(struct msm_gpu *gpu)
 {
-	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
-	return adreno_gpu->memptrs->fence;
+	return gpu->rb[0];
 }
 
 void adreno_recover(struct msm_gpu *gpu)
@@ -149,7 +256,7 @@ void adreno_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit,
 {
 	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
 	struct msm_drm_private *priv = gpu->dev->dev_private;
-	struct msm_ringbuffer *ring = gpu->rb;
+	struct msm_ringbuffer *ring = submit->ring;
 	unsigned i;
 
 	for (i = 0; i < submit->nr_cmds; i++) {
@@ -164,7 +271,7 @@ void adreno_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit,
 		case MSM_SUBMIT_CMD_BUF:
 			OUT_PKT3(ring, adreno_is_a430(adreno_gpu) ?
 				CP_INDIRECT_BUFFER_PFE : CP_INDIRECT_BUFFER_PFD, 2);
-			OUT_RING(ring, submit->cmd[i].iova);
+			OUT_RING(ring, lower_32_bits(submit->cmd[i].iova));
 			OUT_RING(ring, submit->cmd[i].size);
 			OUT_PKT2(ring);
 			break;
@@ -172,7 +279,7 @@ void adreno_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit,
 	}
 
 	OUT_PKT0(ring, REG_AXXX_CP_SCRATCH_REG2, 1);
-	OUT_RING(ring, submit->fence->seqno);
+	OUT_RING(ring, submit->seqno);
 
 	if (adreno_is_a3xx(adreno_gpu) || adreno_is_a4xx(adreno_gpu)) {
 		/* Flush HLSQ lazy updates to make sure there is nothing
@@ -188,8 +295,8 @@ void adreno_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit,
 
 	OUT_PKT3(ring, CP_EVENT_WRITE, 3);
 	OUT_RING(ring, CACHE_FLUSH_TS);
-	OUT_RING(ring, rbmemptr(adreno_gpu, fence));
-	OUT_RING(ring, submit->fence->seqno);
+	OUT_RING(ring, rbmemptr(ring, fence));
+	OUT_RING(ring, submit->seqno);
 
 	/* we could maybe be clever and only CP_COND_EXEC the interrupt: */
 	OUT_PKT3(ring, CP_INTERRUPT, 1);
@@ -215,20 +322,23 @@ void adreno_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit,
 	}
 #endif
 
-	gpu->funcs->flush(gpu);
+	gpu->funcs->flush(gpu, ring);
 }
 
-void adreno_flush(struct msm_gpu *gpu)
+void adreno_flush(struct msm_gpu *gpu, struct msm_ringbuffer *ring)
 {
 	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
 	uint32_t wptr;
 
+	/* Copy the shadow to the actual register */
+	ring->cur = ring->next;
+
 	/*
 	 * Mask wptr value that we calculate to fit in the HW range. This is
 	 * to account for the possibility that the last command fit exactly into
 	 * the ringbuffer and rb->next hasn't wrapped to zero yet
 	 */
-	wptr = get_wptr(gpu->rb) & ((gpu->rb->size / 4) - 1);
+	wptr = get_wptr(ring);
 
 	/* ensure writes to ringbuffer have hit system memory: */
 	mb();
@@ -236,17 +346,19 @@ void adreno_flush(struct msm_gpu *gpu)
 	adreno_gpu_write(adreno_gpu, REG_ADRENO_CP_RB_WPTR, wptr);
 }
 
-bool adreno_idle(struct msm_gpu *gpu)
+bool adreno_idle(struct msm_gpu *gpu, struct msm_ringbuffer *ring)
 {
 	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
-	uint32_t wptr = get_wptr(gpu->rb);
+	uint32_t wptr = get_wptr(ring);
 
 	/* wait for CP to drain ringbuffer: */
-	if (!spin_until(get_rptr(adreno_gpu) == wptr))
+	if (!spin_until(get_rptr(adreno_gpu, ring) == wptr))
 		return true;
 
 	/* TODO maybe we need to reset GPU here to recover from hang? */
-	DRM_ERROR("%s: timeout waiting to drain ringbuffer!\n", gpu->name);
+	DRM_ERROR("%s: timeout waiting to drain ringbuffer %d rptr/wptr = %X/%X\n",
+		gpu->name, ring->id, get_rptr(adreno_gpu, ring), wptr);
+
 	return false;
 }
 
@@ -261,10 +373,16 @@ void adreno_show(struct msm_gpu *gpu, struct seq_file *m)
 			adreno_gpu->rev.major, adreno_gpu->rev.minor,
 			adreno_gpu->rev.patchid);
 
-	seq_printf(m, "fence:    %d/%d\n", adreno_gpu->memptrs->fence,
-			gpu->fctx->last_fence);
-	seq_printf(m, "rptr:     %d\n", get_rptr(adreno_gpu));
-	seq_printf(m, "rb wptr:  %d\n", get_wptr(gpu->rb));
+	for (i = 0; i < gpu->nr_rings; i++) {
+		struct msm_ringbuffer *ring = gpu->rb[i];
+
+		seq_printf(m, "rb %d: fence:    %d/%d\n", i,
+			ring->memptrs->fence, ring->seqno);
+
+		seq_printf(m, "      rptr:     %d\n",
+			get_rptr(adreno_gpu, ring));
+		seq_printf(m, "rb wptr:  %d\n", get_wptr(ring));
+	}
 
 	/* dump these out in a form that can be parsed by demsm: */
 	seq_printf(m, "IO:region %s 00000000 00020000\n", gpu->name);
@@ -290,16 +408,23 @@ void adreno_show(struct msm_gpu *gpu, struct seq_file *m)
 void adreno_dump_info(struct msm_gpu *gpu)
 {
 	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
+	int i;
 
 	printk("revision: %d (%d.%d.%d.%d)\n",
 			adreno_gpu->info->revn, adreno_gpu->rev.core,
 			adreno_gpu->rev.major, adreno_gpu->rev.minor,
 			adreno_gpu->rev.patchid);
 
-	printk("fence:    %d/%d\n", adreno_gpu->memptrs->fence,
-			gpu->fctx->last_fence);
-	printk("rptr:     %d\n", get_rptr(adreno_gpu));
-	printk("rb wptr:  %d\n", get_wptr(gpu->rb));
+	for (i = 0; i < gpu->nr_rings; i++) {
+		struct msm_ringbuffer *ring = gpu->rb[i];
+
+		printk("rb %d: fence:    %d/%d\n", i,
+			ring->memptrs->fence,
+			ring->seqno);
+
+		printk("rptr:     %d\n", get_rptr(adreno_gpu, ring));
+		printk("rb wptr:  %d\n", get_wptr(ring));
+	}
 }
 
 /* would be nice to not have to duplicate the _show() stuff with printk(): */
@@ -322,28 +447,101 @@ void adreno_dump(struct msm_gpu *gpu)
 	}
 }
 
-static uint32_t ring_freewords(struct msm_gpu *gpu)
+static uint32_t ring_freewords(struct msm_ringbuffer *ring)
 {
-	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
-	uint32_t size = gpu->rb->size / 4;
-	uint32_t wptr = get_wptr(gpu->rb);
-	uint32_t rptr = get_rptr(adreno_gpu);
+	struct adreno_gpu *adreno_gpu = to_adreno_gpu(ring->gpu);
+	uint32_t size = MSM_GPU_RINGBUFFER_SZ >> 2;
+	/* Use ring->next to calculate free size */
+	uint32_t wptr = ring->next - ring->start;
+	uint32_t rptr = get_rptr(adreno_gpu, ring);
 	return (rptr + (size - 1) - wptr) % size;
 }
 
-void adreno_wait_ring(struct msm_gpu *gpu, uint32_t ndwords)
+void adreno_wait_ring(struct msm_ringbuffer *ring, uint32_t ndwords)
 {
-	if (spin_until(ring_freewords(gpu) >= ndwords))
-		DRM_ERROR("%s: timeout waiting for ringbuffer space\n", gpu->name);
+	if (spin_until(ring_freewords(ring) >= ndwords))
+		DRM_DEV_ERROR(ring->gpu->dev->dev,
+			"timeout waiting for space in ringbuffer %d\n",
+			ring->id);
+}
+
+/* Get legacy powerlevels from qcom,gpu-pwrlevels and populate the opp table */
+static int adreno_get_legacy_pwrlevels(struct device *dev)
+{
+	struct device_node *child, *node;
+	int ret;
+
+	node = of_find_compatible_node(dev->of_node, NULL,
+		"qcom,gpu-pwrlevels");
+	if (!node) {
+		dev_err(dev, "Could not find the GPU powerlevels\n");
+		return -ENXIO;
+	}
+
+	for_each_child_of_node(node, child) {
+		unsigned int val;
+
+		ret = of_property_read_u32(child, "qcom,gpu-freq", &val);
+		if (ret)
+			continue;
+
+		/*
+		 * Skip the intentionally bogus clock value found at the bottom
+		 * of most legacy frequency tables
+		 */
+		if (val != 27000000)
+			dev_pm_opp_add(dev, val, 0);
+	}
+
+	return 0;
+}
+
+static int adreno_get_pwrlevels(struct device *dev,
+		struct msm_gpu *gpu)
+{
+	unsigned long freq = ULONG_MAX;
+	struct dev_pm_opp *opp;
+	int ret;
+
+	gpu->fast_rate = 0;
+
+	/* You down with OPP? */
+	if (!of_find_property(dev->of_node, "operating-points-v2", NULL))
+		ret = adreno_get_legacy_pwrlevels(dev);
+	else {
+		ret = dev_pm_opp_of_add_table(dev);
+		if (ret)
+			dev_err(dev, "Unable to set the OPP table\n");
+	}
+
+	if (!ret) {
+		/* Find the fastest defined rate */
+		opp = dev_pm_opp_find_freq_floor(dev, &freq);
+		if (!IS_ERR(opp)) {
+			gpu->fast_rate = freq;
+			dev_pm_opp_put(opp);
+		}
+	}
+
+	if (!gpu->fast_rate) {
+		dev_warn(dev,
+			"Could not find a clock rate. Using a reasonable default\n");
+		/* Pick a suitably safe clock speed for any target */
+		gpu->fast_rate = 200000000;
+	}
+
+	DBG("fast_rate=%u, slow_rate=27000000", gpu->fast_rate);
+
+	return 0;
 }
 
 int adreno_gpu_init(struct drm_device *drm, struct platform_device *pdev,
-		struct adreno_gpu *adreno_gpu, const struct adreno_gpu_funcs *funcs)
+		struct adreno_gpu *adreno_gpu,
+		const struct adreno_gpu_funcs *funcs, int nr_rings)
 {
 	struct adreno_platform_config *config = pdev->dev.platform_data;
 	struct msm_gpu_config adreno_gpu_config  = { 0 };
 	struct msm_gpu *gpu = &adreno_gpu->base;
-	int ret;
 
 	adreno_gpu->funcs = funcs;
 	adreno_gpu->info = adreno_info(config->rev);
@@ -351,74 +549,28 @@ int adreno_gpu_init(struct drm_device *drm, struct platform_device *pdev,
 	adreno_gpu->revn = adreno_gpu->info->revn;
 	adreno_gpu->rev = config->rev;
 
-	gpu->fast_rate = config->fast_rate;
-	gpu->bus_freq  = config->bus_freq;
-#ifdef DOWNSTREAM_CONFIG_MSM_BUS_SCALING
-	gpu->bus_scale_table = config->bus_scale_table;
-#endif
-
-	DBG("fast_rate=%u, slow_rate=27000000, bus_freq=%u",
-			gpu->fast_rate, gpu->bus_freq);
-
 	adreno_gpu_config.ioname = "kgsl_3d0_reg_memory";
 	adreno_gpu_config.irqname = "kgsl_3d0_irq";
 
 	adreno_gpu_config.va_start = SZ_16M;
 	adreno_gpu_config.va_end = 0xffffffff;
 
-	adreno_gpu_config.ringsz = RB_SIZE;
+	adreno_gpu_config.nr_rings = nr_rings;
+
+	adreno_get_pwrlevels(&pdev->dev, gpu);
 
 	pm_runtime_set_autosuspend_delay(&pdev->dev, DRM_MSM_INACTIVE_PERIOD);
 	pm_runtime_use_autosuspend(&pdev->dev);
 	pm_runtime_enable(&pdev->dev);
 
-	ret = msm_gpu_init(drm, pdev, &adreno_gpu->base, &funcs->base,
+	return msm_gpu_init(drm, pdev, &adreno_gpu->base, &funcs->base,
 			adreno_gpu->info->name, &adreno_gpu_config);
-	if (ret)
-		return ret;
-
-	ret = request_firmware(&adreno_gpu->pm4, adreno_gpu->info->pm4fw, drm->dev);
-	if (ret) {
-		dev_err(drm->dev, "failed to load %s PM4 firmware: %d\n",
-				adreno_gpu->info->pm4fw, ret);
-		return ret;
-	}
-
-	ret = request_firmware(&adreno_gpu->pfp, adreno_gpu->info->pfpfw, drm->dev);
-	if (ret) {
-		dev_err(drm->dev, "failed to load %s PFP firmware: %d\n",
-				adreno_gpu->info->pfpfw, ret);
-		return ret;
-	}
-
-	adreno_gpu->memptrs = msm_gem_kernel_new(drm,
-		sizeof(*adreno_gpu->memptrs), MSM_BO_UNCACHED, gpu->aspace,
-		&adreno_gpu->memptrs_bo, &adreno_gpu->memptrs_iova);
-
-	if (IS_ERR(adreno_gpu->memptrs)) {
-		ret = PTR_ERR(adreno_gpu->memptrs);
-		adreno_gpu->memptrs = NULL;
-		dev_err(drm->dev, "could not allocate memptrs: %d\n", ret);
-	}
-
-	return ret;
 }
 
 void adreno_gpu_cleanup(struct adreno_gpu *adreno_gpu)
 {
-	struct msm_gpu *gpu = &adreno_gpu->base;
-
-	if (adreno_gpu->memptrs_bo) {
-		if (adreno_gpu->memptrs)
-			msm_gem_put_vaddr(adreno_gpu->memptrs_bo);
-
-		if (adreno_gpu->memptrs_iova)
-			msm_gem_put_iova(adreno_gpu->memptrs_bo, gpu->aspace);
-
-		drm_gem_object_unreference_unlocked(adreno_gpu->memptrs_bo);
-	}
 	release_firmware(adreno_gpu->pm4);
 	release_firmware(adreno_gpu->pfp);
 
-	msm_gpu_cleanup(gpu);
+	msm_gpu_cleanup(&adreno_gpu->base);
 }