1 files changed, 84 insertions, 217 deletions

diff --git a/drivers/gpu/drm/panthor/panthor_gpu.c b/drivers/gpu/drm/panthor/panthor_gpu.c
index 2d3529a0b156..06b231b2460a 100644
--- a/drivers/gpu/drm/panthor/panthor_gpu.c
+++ b/drivers/gpu/drm/panthor/panthor_gpu.c
@@ -15,9 +15,11 @@
 
 #include <drm/drm_drv.h>
 #include <drm/drm_managed.h>
+#include <drm/drm_print.h>
 
 #include "panthor_device.h"
 #include "panthor_gpu.h"
+#include "panthor_hw.h"
 #include "panthor_regs.h"
 
 /**
@@ -35,40 +37,9 @@ struct panthor_gpu {
 
 	/** @reqs_acked: GPU request wait queue. */
 	wait_queue_head_t reqs_acked;
-};
-
-/**
- * struct panthor_model - GPU model description
- */
-struct panthor_model {
-	/** @name: Model name. */
-	const char *name;
-
-	/** @arch_major: Major version number of architecture. */
-	u8 arch_major;
-
-	/** @product_major: Major version number of product. */
-	u8 product_major;
-};
-
-/**
- * GPU_MODEL() - Define a GPU model. A GPU product can be uniquely identified
- * by a combination of the major architecture version and the major product
- * version.
- * @_name: Name for the GPU model.
- * @_arch_major: Architecture major.
- * @_product_major: Product major.
- */
-#define GPU_MODEL(_name, _arch_major, _product_major) \
-{\
-	.name = __stringify(_name),				\
-	.arch_major = _arch_major,				\
-	.product_major = _product_major,			\
-}
 
-static const struct panthor_model gpu_models[] = {
-	GPU_MODEL(g610, 10, 7),
-	{},
+	/** @cache_flush_lock: Lock to serialize cache flushes */
+	struct mutex cache_flush_lock;
 };
 
 #define GPU_INTERRUPTS_MASK	\
@@ -77,77 +48,41 @@ static const struct panthor_model gpu_models[] = {
 	 GPU_IRQ_RESET_COMPLETED | \
 	 GPU_IRQ_CLEAN_CACHES_COMPLETED)
 
-static void panthor_gpu_init_info(struct panthor_device *ptdev)
+static void panthor_gpu_coherency_set(struct panthor_device *ptdev)
+{
+	gpu_write(ptdev, GPU_COHERENCY_PROTOCOL,
+		ptdev->coherent ? GPU_COHERENCY_PROT_BIT(ACE_LITE) : GPU_COHERENCY_NONE);
+}
+
+static void panthor_gpu_l2_config_set(struct panthor_device *ptdev)
 {
-	const struct panthor_model *model;
-	u32 arch_major, product_major;
-	u32 major, minor, status;
-	unsigned int i;
-
-	ptdev->gpu_info.gpu_id = gpu_read(ptdev, GPU_ID);
-	ptdev->gpu_info.csf_id = gpu_read(ptdev, GPU_CSF_ID);
-	ptdev->gpu_info.gpu_rev = gpu_read(ptdev, GPU_REVID);
-	ptdev->gpu_info.core_features = gpu_read(ptdev, GPU_CORE_FEATURES);
-	ptdev->gpu_info.l2_features = gpu_read(ptdev, GPU_L2_FEATURES);
-	ptdev->gpu_info.tiler_features = gpu_read(ptdev, GPU_TILER_FEATURES);
-	ptdev->gpu_info.mem_features = gpu_read(ptdev, GPU_MEM_FEATURES);
-	ptdev->gpu_info.mmu_features = gpu_read(ptdev, GPU_MMU_FEATURES);
-	ptdev->gpu_info.thread_features = gpu_read(ptdev, GPU_THREAD_FEATURES);
-	ptdev->gpu_info.max_threads = gpu_read(ptdev, GPU_THREAD_MAX_THREADS);
-	ptdev->gpu_info.thread_max_workgroup_size = gpu_read(ptdev, GPU_THREAD_MAX_WORKGROUP_SIZE);
-	ptdev->gpu_info.thread_max_barrier_size = gpu_read(ptdev, GPU_THREAD_MAX_BARRIER_SIZE);
-	ptdev->gpu_info.coherency_features = gpu_read(ptdev, GPU_COHERENCY_FEATURES);
-	for (i = 0; i < 4; i++)
-		ptdev->gpu_info.texture_features[i] = gpu_read(ptdev, GPU_TEXTURE_FEATURES(i));
-
-	ptdev->gpu_info.as_present = gpu_read(ptdev, GPU_AS_PRESENT);
-
-	ptdev->gpu_info.shader_present = gpu_read(ptdev, GPU_SHADER_PRESENT_LO);
-	ptdev->gpu_info.shader_present |= (u64)gpu_read(ptdev, GPU_SHADER_PRESENT_HI) << 32;
-
-	ptdev->gpu_info.tiler_present = gpu_read(ptdev, GPU_TILER_PRESENT_LO);
-	ptdev->gpu_info.tiler_present |= (u64)gpu_read(ptdev, GPU_TILER_PRESENT_HI) << 32;
-
-	ptdev->gpu_info.l2_present = gpu_read(ptdev, GPU_L2_PRESENT_LO);
-	ptdev->gpu_info.l2_present |= (u64)gpu_read(ptdev, GPU_L2_PRESENT_HI) << 32;
-
-	arch_major = GPU_ARCH_MAJOR(ptdev->gpu_info.gpu_id);
-	product_major = GPU_PROD_MAJOR(ptdev->gpu_info.gpu_id);
-	major = GPU_VER_MAJOR(ptdev->gpu_info.gpu_id);
-	minor = GPU_VER_MINOR(ptdev->gpu_info.gpu_id);
-	status = GPU_VER_STATUS(ptdev->gpu_info.gpu_id);
-
-	for (model = gpu_models; model->name; model++) {
-		if (model->arch_major == arch_major &&
-		    model->product_major == product_major)
-			break;
+	const struct panthor_soc_data *data = ptdev->soc_data;
+	u32 l2_config;
+	u32 i;
+
+	if (!data || !data->asn_hash_enable)
+		return;
+
+	if (GPU_ARCH_MAJOR(ptdev->gpu_info.gpu_id) < 11) {
+		drm_err(&ptdev->base, "Custom ASN hash not supported by the device");
+		return;
 	}
 
-	drm_info(&ptdev->base,
-		 "mali-%s id 0x%x major 0x%x minor 0x%x status 0x%x",
-		 model->name ?: "unknown", ptdev->gpu_info.gpu_id >> 16,
-		 major, minor, status);
-
-	drm_info(&ptdev->base,
-		 "Features: L2:%#x Tiler:%#x Mem:%#x MMU:%#x AS:%#x",
-		 ptdev->gpu_info.l2_features,
-		 ptdev->gpu_info.tiler_features,
-		 ptdev->gpu_info.mem_features,
-		 ptdev->gpu_info.mmu_features,
-		 ptdev->gpu_info.as_present);
-
-	drm_info(&ptdev->base,
-		 "shader_present=0x%0llx l2_present=0x%0llx tiler_present=0x%0llx",
-		 ptdev->gpu_info.shader_present, ptdev->gpu_info.l2_present,
-		 ptdev->gpu_info.tiler_present);
+	for (i = 0; i < ARRAY_SIZE(data->asn_hash); i++)
+		gpu_write(ptdev, GPU_ASN_HASH(i), data->asn_hash[i]);
+
+	l2_config = gpu_read(ptdev, GPU_L2_CONFIG);
+	l2_config |= GPU_L2_CONFIG_ASN_HASH_ENABLE;
+	gpu_write(ptdev, GPU_L2_CONFIG, l2_config);
 }
 
 static void panthor_gpu_irq_handler(struct panthor_device *ptdev, u32 status)
 {
+	gpu_write(ptdev, GPU_INT_CLEAR, status);
+
 	if (status & GPU_IRQ_FAULT) {
 		u32 fault_status = gpu_read(ptdev, GPU_FAULT_STATUS);
-		u64 address = ((u64)gpu_read(ptdev, GPU_FAULT_ADDR_HI) << 32) |
-			      gpu_read(ptdev, GPU_FAULT_ADDR_LO);
+		u64 address = gpu_read64(ptdev, GPU_FAULT_ADDR);
 
 		drm_warn(&ptdev->base, "GPU Fault 0x%08x (%s) at 0x%016llx\n",
 			 fault_status, panthor_exception_name(ptdev, fault_status & 0xFF),
@@ -174,7 +109,8 @@ void panthor_gpu_unplug(struct panthor_device *ptdev)
 	unsigned long flags;
 
 	/* Make sure the IRQ handler is not running after that point. */
-	panthor_gpu_irq_suspend(&ptdev->gpu->irq);
+	if (!IS_ENABLED(CONFIG_PM) || pm_runtime_active(ptdev->base.dev))
+		panthor_gpu_irq_suspend(&ptdev->gpu->irq);
 
 	/* Wake-up all waiters. */
 	spin_lock_irqsave(&ptdev->gpu->reqs_lock, flags);
@@ -201,8 +137,8 @@ int panthor_gpu_init(struct panthor_device *ptdev)
 
 	spin_lock_init(&gpu->reqs_lock);
 	init_waitqueue_head(&gpu->reqs_acked);
+	mutex_init(&gpu->cache_flush_lock);
 	ptdev->gpu = gpu;
-	panthor_gpu_init_info(ptdev);
 
 	dma_set_max_seg_size(ptdev->base.dev, UINT_MAX);
 	pa_bits = GPU_MMU_FEATURES_PA_BITS(ptdev->gpu_info.mmu_features);
@@ -237,45 +173,27 @@ int panthor_gpu_block_power_off(struct panthor_device *ptdev,
 				u32 pwroff_reg, u32 pwrtrans_reg,
 				u64 mask, u32 timeout_us)
 {
-	u32 val, i;
+	u32 val;
 	int ret;
 
-	for (i = 0; i < 2; i++) {
-		u32 mask32 = mask >> (i * 32);
-
-		if (!mask32)
-			continue;
-
-		ret = readl_relaxed_poll_timeout(ptdev->iomem + pwrtrans_reg + (i * 4),
-						 val, !(mask32 & val),
-						 100, timeout_us);
-		if (ret) {
-			drm_err(&ptdev->base, "timeout waiting on %s:%llx power transition",
-				blk_name, mask);
-			return ret;
-		}
+	ret = gpu_read64_relaxed_poll_timeout(ptdev, pwrtrans_reg, val,
+					      !(mask & val), 100, timeout_us);
+	if (ret) {
+		drm_err(&ptdev->base,
+			"timeout waiting on %s:%llx power transition", blk_name,
+			mask);
+		return ret;
 	}
 
-	if (mask & GENMASK(31, 0))
-		gpu_write(ptdev, pwroff_reg, mask);
-
-	if (mask >> 32)
-		gpu_write(ptdev, pwroff_reg + 4, mask >> 32);
-
-	for (i = 0; i < 2; i++) {
-		u32 mask32 = mask >> (i * 32);
+	gpu_write64(ptdev, pwroff_reg, mask);
 
-		if (!mask32)
-			continue;
-
-		ret = readl_relaxed_poll_timeout(ptdev->iomem + pwrtrans_reg + (i * 4),
-						 val, !(mask32 & val),
-						 100, timeout_us);
-		if (ret) {
-			drm_err(&ptdev->base, "timeout waiting on %s:%llx power transition",
-				blk_name, mask);
-			return ret;
-		}
+	ret = gpu_read64_relaxed_poll_timeout(ptdev, pwrtrans_reg, val,
+					      !(mask & val), 100, timeout_us);
+	if (ret) {
+		drm_err(&ptdev->base,
+			"timeout waiting on %s:%llx power transition", blk_name,
+			mask);
+		return ret;
 	}
 
 	return 0;
@@ -298,50 +216,37 @@ int panthor_gpu_block_power_on(struct panthor_device *ptdev,
 			       u32 pwron_reg, u32 pwrtrans_reg,
 			       u32 rdy_reg, u64 mask, u32 timeout_us)
 {
-	u32 val, i;
+	u32 val;
 	int ret;
 
-	for (i = 0; i < 2; i++) {
-		u32 mask32 = mask >> (i * 32);
-
-		if (!mask32)
-			continue;
-
-		ret = readl_relaxed_poll_timeout(ptdev->iomem + pwrtrans_reg + (i * 4),
-						 val, !(mask32 & val),
-						 100, timeout_us);
-		if (ret) {
-			drm_err(&ptdev->base, "timeout waiting on %s:%llx power transition",
-				blk_name, mask);
-			return ret;
-		}
+	ret = gpu_read64_relaxed_poll_timeout(ptdev, pwrtrans_reg, val,
+					      !(mask & val), 100, timeout_us);
+	if (ret) {
+		drm_err(&ptdev->base,
+			"timeout waiting on %s:%llx power transition", blk_name,
+			mask);
+		return ret;
 	}
 
-	if (mask & GENMASK(31, 0))
-		gpu_write(ptdev, pwron_reg, mask);
-
-	if (mask >> 32)
-		gpu_write(ptdev, pwron_reg + 4, mask >> 32);
-
-	for (i = 0; i < 2; i++) {
-		u32 mask32 = mask >> (i * 32);
-
-		if (!mask32)
-			continue;
+	gpu_write64(ptdev, pwron_reg, mask);
 
-		ret = readl_relaxed_poll_timeout(ptdev->iomem + rdy_reg + (i * 4),
-						 val, (mask32 & val) == mask32,
-						 100, timeout_us);
-		if (ret) {
-			drm_err(&ptdev->base, "timeout waiting on %s:%llx readiness",
-				blk_name, mask);
-			return ret;
-		}
+	ret = gpu_read64_relaxed_poll_timeout(ptdev, rdy_reg, val,
+					      (mask & val) == val,
+					      100, timeout_us);
+	if (ret) {
+		drm_err(&ptdev->base, "timeout waiting on %s:%llx readiness",
+			blk_name, mask);
+		return ret;
 	}
 
 	return 0;
 }
 
+void panthor_gpu_l2_power_off(struct panthor_device *ptdev)
+{
+	panthor_gpu_power_off(ptdev, L2, ptdev->gpu_info.l2_present, 20000);
+}
+
 /**
  * panthor_gpu_l2_power_on() - Power-on the L2-cache
  * @ptdev: Device.
@@ -365,6 +270,10 @@ int panthor_gpu_l2_power_on(struct panthor_device *ptdev)
 			      hweight64(ptdev->gpu_info.shader_present));
 	}
 
+	/* Set the desired coherency mode and L2 config before the power up of L2 */
+	panthor_gpu_coherency_set(ptdev);
+	panthor_gpu_l2_config_set(ptdev);
+
 	return panthor_gpu_power_on(ptdev, L2, 1, 20000);
 }
 
@@ -383,6 +292,9 @@ int panthor_gpu_flush_caches(struct panthor_device *ptdev,
 	bool timedout = false;
 	unsigned long flags;
 
+	/* Serialize cache flush operations. */
+	guard(mutex)(&ptdev->gpu->cache_flush_lock);
+
 	spin_lock_irqsave(&ptdev->gpu->reqs_lock, flags);
 	if (!drm_WARN_ON(&ptdev->base,
 			 ptdev->gpu->pending_reqs & GPU_IRQ_CLEAN_CACHES_COMPLETED)) {
@@ -460,11 +372,12 @@ int panthor_gpu_soft_reset(struct panthor_device *ptdev)
  */
 void panthor_gpu_suspend(struct panthor_device *ptdev)
 {
-	/*
-	 * It may be preferable to simply power down the L2, but for now just
-	 * soft-reset which will leave the L2 powered down.
-	 */
-	panthor_gpu_soft_reset(ptdev);
+	/* On a fast reset, simply power down the L2. */
+	if (!ptdev->reset.fast)
+		panthor_hw_soft_reset(ptdev);
+	else
+		panthor_hw_l2_power_off(ptdev);
+
 	panthor_gpu_irq_suspend(&ptdev->gpu->irq);
 }
 
@@ -478,52 +391,6 @@ void panthor_gpu_suspend(struct panthor_device *ptdev)
 void panthor_gpu_resume(struct panthor_device *ptdev)
 {
 	panthor_gpu_irq_resume(&ptdev->gpu->irq, GPU_INTERRUPTS_MASK);
-	panthor_gpu_l2_power_on(ptdev);
-}
-
-/**
- * panthor_gpu_read_64bit_counter() - Read a 64-bit counter at a given offset.
- * @ptdev: Device.
- * @reg: The offset of the register to read.
- *
- * Return: The counter value.
- */
-static u64
-panthor_gpu_read_64bit_counter(struct panthor_device *ptdev, u32 reg)
-{
-	u32 hi, lo;
-
-	do {
-		hi = gpu_read(ptdev, reg + 0x4);
-		lo = gpu_read(ptdev, reg);
-	} while (hi != gpu_read(ptdev, reg + 0x4));
-
-	return ((u64)hi << 32) | lo;
+	panthor_hw_l2_power_on(ptdev);
 }
 
-/**
- * panthor_gpu_read_timestamp() - Read the timestamp register.
- * @ptdev: Device.
- *
- * Return: The GPU timestamp value.
- */
-u64 panthor_gpu_read_timestamp(struct panthor_device *ptdev)
-{
-	return panthor_gpu_read_64bit_counter(ptdev, GPU_TIMESTAMP_LO);
-}
-
-/**
- * panthor_gpu_read_timestamp_offset() - Read the timestamp offset register.
- * @ptdev: Device.
- *
- * Return: The GPU timestamp offset value.
- */
-u64 panthor_gpu_read_timestamp_offset(struct panthor_device *ptdev)
-{
-	u32 hi, lo;
-
-	hi = gpu_read(ptdev, GPU_TIMESTAMP_OFFSET_HI);
-	lo = gpu_read(ptdev, GPU_TIMESTAMP_OFFSET_LO);
-
-	return ((u64)hi << 32) | lo;
-}