Merge tag 'drm-msm-next-2022-07-10' of https://gitlab.freedesktop.org/drm/msm into drm-next

Next for v5.20

GPU:
- a619 support
- Fix for unclocked GMU register access
- Devcore dump enhancements

Core:

- client utilization via fdinfo support
- fix fence rollover issue
- gem: Lockdep false-positive warning fix
- gem: Switch to pfn mappings

DPU:

- constification of HW catalog
- support for using encoder as CRC source
- WB support on sc7180
- WB resolution fixes

DP:

- dropped custom bulk clock implementation
- made dp_bridge_mode_valid() return MODE_CLOCK_HIGH where applicable
- fix link retraining on resolution change

MDP5:

- MSM8953 perf data

HDMI:

- YAML'ification of schema
- dropped obsolete GPIO support
- misc cleanups

Signed-off-by: Dave Airlie <airlied@redhat.com>
From: Rob Clark <robdclark@gmail.com>
Link: https://patchwork.freedesktop.org/patch/msgid/CAF6AEGtuqswBGPw-kCYzJvckK2RR1XTeUEgaXwVG_mvpbv3gPA@mail.gmail.com

80 files changed, 1282 insertions, 1343 deletions

diff --git a/drivers/gpu/drm/msm/Makefile b/drivers/gpu/drm/msm/Makefile
index 66395ee0862a..7274c41228ed 100644
--- a/drivers/gpu/drm/msm/Makefile
+++ b/drivers/gpu/drm/msm/Makefile
@@ -119,7 +119,6 @@ msm-$(CONFIG_DRM_MSM_GPU_STATE)	+= adreno/a6xx_gpu_state.o
 
 msm-$(CONFIG_DRM_MSM_DP)+= dp/dp_aux.o \
 	dp/dp_catalog.o \
-	dp/dp_clk_util.o \
 	dp/dp_ctrl.o \
 	dp/dp_display.o \
 	dp/dp_drm.o \
diff --git a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
index c424e9a37669..3dcec7acb384 100644
--- a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
@@ -1666,18 +1666,10 @@ static u64 a5xx_gpu_busy(struct msm_gpu *gpu, unsigned long *out_sample_rate)
 {
 	u64 busy_cycles;
 
-	/* Only read the gpu busy if the hardware is already active */
-	if (pm_runtime_get_if_in_use(&gpu->pdev->dev) == 0) {
-		*out_sample_rate = 1;
-		return 0;
-	}
-
 	busy_cycles = gpu_read64(gpu, REG_A5XX_RBBM_PERFCTR_RBBM_0_LO,
 			REG_A5XX_RBBM_PERFCTR_RBBM_0_HI);
 	*out_sample_rate = clk_get_rate(gpu->core_clk);
 
-	pm_runtime_put(&gpu->pdev->dev);
-
 	return busy_cycles;
 }
 
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c
index 9f76f5b15759..310a317885a1 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c
@@ -102,7 +102,8 @@ bool a6xx_gmu_gx_is_on(struct a6xx_gmu *gmu)
 		A6XX_GMU_SPTPRAC_PWR_CLK_STATUS_GX_HM_CLK_OFF));
 }
 
-void a6xx_gmu_set_freq(struct msm_gpu *gpu, struct dev_pm_opp *opp)
+void a6xx_gmu_set_freq(struct msm_gpu *gpu, struct dev_pm_opp *opp,
+		       bool suspended)
 {
 	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
 	struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu);
@@ -127,15 +128,16 @@ void a6xx_gmu_set_freq(struct msm_gpu *gpu, struct dev_pm_opp *opp)
 
 	/*
 	 * This can get called from devfreq while the hardware is idle. Don't
-	 * bring up the power if it isn't already active
+	 * bring up the power if it isn't already active. All we're doing here
+	 * is updating the frequency so that when we come back online we're at
+	 * the right rate.
 	 */
-	if (pm_runtime_get_if_in_use(gmu->dev) == 0)
+	if (suspended)
 		return;
 
 	if (!gmu->legacy) {
 		a6xx_hfi_set_freq(gmu, perf_index);
 		dev_pm_opp_set_opp(&gpu->pdev->dev, opp);
-		pm_runtime_put(gmu->dev);
 		return;
 	}
 
@@ -159,7 +161,6 @@ void a6xx_gmu_set_freq(struct msm_gpu *gpu, struct dev_pm_opp *opp)
 		dev_err(gmu->dev, "GMU set GPU frequency error: %d\n", ret);
 
 	dev_pm_opp_set_opp(&gpu->pdev->dev, opp);
-	pm_runtime_put(gmu->dev);
 }
 
 unsigned long a6xx_gmu_get_freq(struct msm_gpu *gpu)
@@ -504,7 +505,7 @@ static void a6xx_rpmh_stop(struct a6xx_gmu *gmu)
 
 static inline void pdc_write(void __iomem *ptr, u32 offset, u32 value)
 {
-	return msm_writel(value, ptr + (offset << 2));
+	msm_writel(value, ptr + (offset << 2));
 }
 
 static void __iomem *a6xx_gmu_get_mmio(struct platform_device *pdev,
@@ -527,6 +528,8 @@ static void a6xx_gmu_rpmh_init(struct a6xx_gmu *gmu)
 		pdc_in_aop = true;
 	else if (adreno_is_a618(adreno_gpu) || adreno_is_a640_family(adreno_gpu))
 		pdc_address_offset = 0x30090;
+	else if (adreno_is_a619(adreno_gpu))
+		pdc_address_offset = 0x300a0;
 	else
 		pdc_address_offset = 0x30080;
 
@@ -601,7 +604,8 @@ static void a6xx_gmu_rpmh_init(struct a6xx_gmu *gmu)
 
 	pdc_write(pdcptr, REG_A6XX_PDC_GPU_TCS3_CMD0_MSGID + 4, 0x10108);
 	pdc_write(pdcptr, REG_A6XX_PDC_GPU_TCS3_CMD0_ADDR + 4, 0x30000);
-	if (adreno_is_a618(adreno_gpu) || adreno_is_a650_family(adreno_gpu))
+	if (adreno_is_a618(adreno_gpu) || adreno_is_a619(adreno_gpu) ||
+			adreno_is_a650_family(adreno_gpu))
 		pdc_write(pdcptr, REG_A6XX_PDC_GPU_TCS3_CMD0_DATA + 4, 0x2);
 	else
 		pdc_write(pdcptr, REG_A6XX_PDC_GPU_TCS3_CMD0_DATA + 4, 0x3);
@@ -895,7 +899,7 @@ static void a6xx_gmu_set_initial_freq(struct msm_gpu *gpu, struct a6xx_gmu *gmu)
 		return;
 
 	gmu->freq = 0; /* so a6xx_gmu_set_freq() doesn't exit early */
-	a6xx_gmu_set_freq(gpu, gpu_opp);
+	a6xx_gmu_set_freq(gpu, gpu_opp, false);
 	dev_pm_opp_put(gpu_opp);
 }
 
@@ -1537,6 +1541,12 @@ int a6xx_gmu_init(struct a6xx_gpu *a6xx_gpu, struct device_node *node)
 			SZ_16M - SZ_16K, 0x04000, "icache");
 		if (ret)
 			goto err_memory;
+	/*
+	 * NOTE: when porting legacy ("pre-650-family") GPUs you may be tempted to add a condition
+	 * to allocate icache/dcache here, as per downstream code flow, but it may not actually be
+	 * necessary. If you omit this step and you don't get random pagefaults, you are likely
+	 * good to go without this!
+	 */
 	} else if (adreno_is_a640_family(adreno_gpu)) {
 		ret = a6xx_gmu_memory_alloc(gmu, &gmu->icache,
 			SZ_256K - SZ_16K, 0x04000, "icache");
@@ -1547,9 +1557,7 @@ int a6xx_gmu_init(struct a6xx_gpu *a6xx_gpu, struct device_node *node)
 			SZ_256K - SZ_16K, 0x44000, "dcache");
 		if (ret)
 			goto err_memory;
-	} else {
-		BUG_ON(adreno_is_a660_family(adreno_gpu));
-
+	} else if (adreno_is_a630(adreno_gpu) || adreno_is_a615_family(adreno_gpu)) {
 		/* HFI v1, has sptprac */
 		gmu->legacy = true;
 
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gmu.h b/drivers/gpu/drm/msm/adreno/a6xx_gmu.h
index 84bd516f01e8..e034935b3986 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gmu.h
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gmu.h
@@ -98,7 +98,7 @@ static inline u32 gmu_read(struct a6xx_gmu *gmu, u32 offset)
 
 static inline void gmu_write(struct a6xx_gmu *gmu, u32 offset, u32 value)
 {
-	return msm_writel(value, gmu->mmio + (offset << 2));
+	msm_writel(value, gmu->mmio + (offset << 2));
 }
 
 static inline void
@@ -138,7 +138,7 @@ static inline u32 gmu_read_rscc(struct a6xx_gmu *gmu, u32 offset)
 
 static inline void gmu_write_rscc(struct a6xx_gmu *gmu, u32 offset, u32 value)
 {
-	return msm_writel(value, gmu->rscc + (offset << 2));
+	msm_writel(value, gmu->rscc + (offset << 2));
 }
 
 #define gmu_poll_timeout_rscc(gmu, addr, val, cond, interval, timeout) \
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
index 42ed9a3c4905..4d501100b9e4 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
@@ -252,6 +252,74 @@ static void a6xx_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit)
 	a6xx_flush(gpu, ring);
 }
 
+/* For a615 family (a615, a616, a618 and a619) */
+const struct adreno_reglist a615_hwcg[] = {
+	{REG_A6XX_RBBM_CLOCK_CNTL_SP0,  0x02222222},
+	{REG_A6XX_RBBM_CLOCK_CNTL2_SP0, 0x02222220},
+	{REG_A6XX_RBBM_CLOCK_DELAY_SP0, 0x00000080},
+	{REG_A6XX_RBBM_CLOCK_HYST_SP0,  0x0000F3CF},
+	{REG_A6XX_RBBM_CLOCK_CNTL_TP0,  0x02222222},
+	{REG_A6XX_RBBM_CLOCK_CNTL_TP1,  0x02222222},
+	{REG_A6XX_RBBM_CLOCK_CNTL2_TP0, 0x22222222},
+	{REG_A6XX_RBBM_CLOCK_CNTL2_TP1, 0x22222222},
+	{REG_A6XX_RBBM_CLOCK_CNTL3_TP0, 0x22222222},
+	{REG_A6XX_RBBM_CLOCK_CNTL3_TP1, 0x22222222},
+	{REG_A6XX_RBBM_CLOCK_CNTL4_TP0, 0x00022222},
+	{REG_A6XX_RBBM_CLOCK_CNTL4_TP1, 0x00022222},
+	{REG_A6XX_RBBM_CLOCK_HYST_TP0,  0x77777777},
+	{REG_A6XX_RBBM_CLOCK_HYST_TP1,  0x77777777},
+	{REG_A6XX_RBBM_CLOCK_HYST2_TP0, 0x77777777},
+	{REG_A6XX_RBBM_CLOCK_HYST2_TP1, 0x77777777},
+	{REG_A6XX_RBBM_CLOCK_HYST3_TP0, 0x77777777},
+	{REG_A6XX_RBBM_CLOCK_HYST3_TP1, 0x77777777},
+	{REG_A6XX_RBBM_CLOCK_HYST4_TP0, 0x00077777},
+	{REG_A6XX_RBBM_CLOCK_HYST4_TP1, 0x00077777},
+	{REG_A6XX_RBBM_CLOCK_DELAY_TP0, 0x11111111},
+	{REG_A6XX_RBBM_CLOCK_DELAY_TP1, 0x11111111},
+	{REG_A6XX_RBBM_CLOCK_DELAY2_TP0, 0x11111111},
+	{REG_A6XX_RBBM_CLOCK_DELAY2_TP1, 0x11111111},
+	{REG_A6XX_RBBM_CLOCK_DELAY3_TP0, 0x11111111},
+	{REG_A6XX_RBBM_CLOCK_DELAY3_TP1, 0x11111111},
+	{REG_A6XX_RBBM_CLOCK_DELAY4_TP0, 0x00011111},
+	{REG_A6XX_RBBM_CLOCK_DELAY4_TP1, 0x00011111},
+	{REG_A6XX_RBBM_CLOCK_CNTL_UCHE,  0x22222222},
+	{REG_A6XX_RBBM_CLOCK_CNTL2_UCHE, 0x22222222},
+	{REG_A6XX_RBBM_CLOCK_CNTL3_UCHE, 0x22222222},
+	{REG_A6XX_RBBM_CLOCK_CNTL4_UCHE, 0x00222222},
+	{REG_A6XX_RBBM_CLOCK_HYST_UCHE,  0x00000004},
+	{REG_A6XX_RBBM_CLOCK_DELAY_UCHE, 0x00000002},
+	{REG_A6XX_RBBM_CLOCK_CNTL_RB0, 0x22222222},
+	{REG_A6XX_RBBM_CLOCK_CNTL2_RB0, 0x00002222},
+	{REG_A6XX_RBBM_CLOCK_CNTL_CCU0, 0x00002020},
+	{REG_A6XX_RBBM_CLOCK_CNTL_CCU1, 0x00002220},
+	{REG_A6XX_RBBM_CLOCK_CNTL_CCU2, 0x00002220},
+	{REG_A6XX_RBBM_CLOCK_CNTL_CCU3, 0x00002220},
+	{REG_A6XX_RBBM_CLOCK_HYST_RB_CCU0, 0x00040F00},
+	{REG_A6XX_RBBM_CLOCK_HYST_RB_CCU1, 0x00040F00},
+	{REG_A6XX_RBBM_CLOCK_HYST_RB_CCU2, 0x00040F00},
+	{REG_A6XX_RBBM_CLOCK_HYST_RB_CCU3, 0x00040F00},
+	{REG_A6XX_RBBM_CLOCK_CNTL_RAC, 0x05022022},
+	{REG_A6XX_RBBM_CLOCK_CNTL2_RAC, 0x00005555},
+	{REG_A6XX_RBBM_CLOCK_DELAY_RAC, 0x00000011},
+	{REG_A6XX_RBBM_CLOCK_HYST_RAC, 0x00445044},
+	{REG_A6XX_RBBM_CLOCK_CNTL_TSE_RAS_RBBM, 0x04222222},
+	{REG_A6XX_RBBM_CLOCK_MODE_GPC, 0x00222222},
+	{REG_A6XX_RBBM_CLOCK_MODE_VFD, 0x00002222},
+	{REG_A6XX_RBBM_CLOCK_HYST_TSE_RAS_RBBM, 0x00000000},
+	{REG_A6XX_RBBM_CLOCK_HYST_GPC, 0x04104004},
+	{REG_A6XX_RBBM_CLOCK_HYST_VFD, 0x00000000},
+	{REG_A6XX_RBBM_CLOCK_DELAY_HLSQ, 0x00000000},
+	{REG_A6XX_RBBM_CLOCK_DELAY_TSE_RAS_RBBM, 0x00004000},
+	{REG_A6XX_RBBM_CLOCK_DELAY_GPC, 0x00000200},
+	{REG_A6XX_RBBM_CLOCK_DELAY_VFD, 0x00002222},
+	{REG_A6XX_RBBM_CLOCK_DELAY_HLSQ_2, 0x00000002},
+	{REG_A6XX_RBBM_CLOCK_MODE_HLSQ, 0x00002222},
+	{REG_A6XX_RBBM_CLOCK_CNTL_GMU_GX, 0x00000222},
+	{REG_A6XX_RBBM_CLOCK_DELAY_GMU_GX, 0x00000111},
+	{REG_A6XX_RBBM_CLOCK_HYST_GMU_GX, 0x00000555},
+	{},
+};
+
 const struct adreno_reglist a630_hwcg[] = {
 	{REG_A6XX_RBBM_CLOCK_CNTL_SP0, 0x22222222},
 	{REG_A6XX_RBBM_CLOCK_CNTL_SP1, 0x22222222},
@@ -555,7 +623,7 @@ static void a6xx_set_hwcg(struct msm_gpu *gpu, bool state)
 	gpu_write(gpu, REG_A6XX_RBBM_CLOCK_CNTL, state ? clock_cntl_on : 0);
 }
 
-/* For a615, a616, a618, A619, a630, a640 and a680 */
+/* For a615, a616, a618, a619, a630, a640 and a680 */
 static const u32 a6xx_protect[] = {
 	A6XX_PROTECT_RDONLY(0x00000, 0x04ff),
 	A6XX_PROTECT_RDONLY(0x00501, 0x0005),
@@ -1446,7 +1514,7 @@ static void a6xx_llc_rmw(struct a6xx_gpu *a6xx_gpu, u32 reg, u32 mask, u32 or)
 
 static void a6xx_llc_write(struct a6xx_gpu *a6xx_gpu, u32 reg, u32 value)
 {
-	return msm_writel(value, a6xx_gpu->llc_mmio + (reg << 2));
+	msm_writel(value, a6xx_gpu->llc_mmio + (reg << 2));
 }
 
 static void a6xx_llc_deactivate(struct a6xx_gpu *a6xx_gpu)
@@ -1658,27 +1726,21 @@ static u64 a6xx_gpu_busy(struct msm_gpu *gpu, unsigned long *out_sample_rate)
 	/* 19.2MHz */
 	*out_sample_rate = 19200000;
 
-	/* Only read the gpu busy if the hardware is already active */
-	if (pm_runtime_get_if_in_use(a6xx_gpu->gmu.dev) == 0)
-		return 0;
-
 	busy_cycles = gmu_read64(&a6xx_gpu->gmu,
 			REG_A6XX_GMU_CX_GMU_POWER_COUNTER_XOCLK_0_L,
 			REG_A6XX_GMU_CX_GMU_POWER_COUNTER_XOCLK_0_H);
 
-
-	pm_runtime_put(a6xx_gpu->gmu.dev);
-
 	return busy_cycles;
 }
 
-static void a6xx_gpu_set_freq(struct msm_gpu *gpu, struct dev_pm_opp *opp)
+static void a6xx_gpu_set_freq(struct msm_gpu *gpu, struct dev_pm_opp *opp,
+			      bool suspended)
 {
 	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
 	struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu);
 
 	mutex_lock(&a6xx_gpu->gmu.lock);
-	a6xx_gmu_set_freq(gpu, opp);
+	a6xx_gmu_set_freq(gpu, opp, suspended);
 	mutex_unlock(&a6xx_gpu->gmu.lock);
 }
 
@@ -1737,7 +1799,8 @@ a6xx_create_private_address_space(struct msm_gpu *gpu)
 		return ERR_CAST(mmu);
 
 	return msm_gem_address_space_create(mmu,
-		"gpu", 0x100000000ULL, SZ_4G);
+		"gpu", 0x100000000ULL,
+		adreno_private_address_space_size(gpu));
 }
 
 static uint32_t a6xx_get_rptr(struct msm_gpu *gpu, struct msm_ringbuffer *ring)
@@ -1763,6 +1826,22 @@ static u32 a618_get_speed_bin(u32 fuse)
 	return UINT_MAX;
 }
 
+static u32 a619_get_speed_bin(u32 fuse)
+{
+	if (fuse == 0)
+		return 0;
+	else if (fuse == 120)
+		return 4;
+	else if (fuse == 138)
+		return 3;
+	else if (fuse == 169)
+		return 2;
+	else if (fuse == 180)
+		return 1;
+
+	return UINT_MAX;
+}
+
 static u32 adreno_7c3_get_speed_bin(u32 fuse)
 {
 	if (fuse == 0)
@@ -1782,6 +1861,9 @@ static u32 fuse_to_supp_hw(struct device *dev, struct adreno_rev rev, u32 fuse)
 	if (adreno_cmp_rev(ADRENO_REV(6, 1, 8, ANY_ID), rev))
 		val = a618_get_speed_bin(fuse);
 
+	if (adreno_cmp_rev(ADRENO_REV(6, 1, 9, ANY_ID), rev))
+		val = a619_get_speed_bin(fuse);
+
 	if (adreno_cmp_rev(ADRENO_REV(6, 3, 5, ANY_ID), rev))
 		val = adreno_7c3_get_speed_bin(fuse);
 
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.h b/drivers/gpu/drm/msm/adreno/a6xx_gpu.h
index 86e0a7c3fe6d..ab853f61db63 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.h
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.h
@@ -77,7 +77,8 @@ void a6xx_gmu_clear_oob(struct a6xx_gmu *gmu, enum a6xx_gmu_oob_state state);
 int a6xx_gmu_init(struct a6xx_gpu *a6xx_gpu, struct device_node *node);
 void a6xx_gmu_remove(struct a6xx_gpu *a6xx_gpu);
 
-void a6xx_gmu_set_freq(struct msm_gpu *gpu, struct dev_pm_opp *opp);
+void a6xx_gmu_set_freq(struct msm_gpu *gpu, struct dev_pm_opp *opp,
+