Skip to contentSkip to conversation

drm/msm/a6xx: Fix llcc configuration for a660 gpu

PATCH Superseded Akhil P Oommen 2 participants 4 messages Jul 23, 2021 – Jul 26, 2021

Subsystems (4)

v1 of 4 Superseded Latest is v4 →

lore
Share & tools
lore
#0 lore raw

PATCH 1/2 drm/msm/a6xx: Fix llcc configuration for a660 gpu

Add the missing scache_cntl0 register programing which is required for a660 gpu.

---
 drivers/gpu/drm/msm/adreno/a6xx_gpu.c | 46 ++++++++++++++++++++---------------
 1 file changed, 27 insertions(+), 19 deletions(-)
drivers/gpu/drm/msm/adreno/a6xx_gpu.c +27 -19
index 9c5e461..183b9f9 100644
@@ -1383,13 +1383,13 @@ static void a6xx_llc_activate(struct a6xx_gpu *a6xx_gpu)
 {
 	struct adreno_gpu *adreno_gpu = &a6xx_gpu->base;
 	struct msm_gpu *gpu = &adreno_gpu->base;
-	u32 cntl1_regval = 0;
+	u32 gpu_scid, cntl1_regval = 0;
 
 	if (IS_ERR(a6xx_gpu->llc_mmio))
 		return;
 
 	if (!llcc_slice_activate(a6xx_gpu->llc_slice)) {
-		u32 gpu_scid = llcc_get_slice_id(a6xx_gpu->llc_slice);
+		gpu_scid = llcc_get_slice_id(a6xx_gpu->llc_slice);
 
 		gpu_scid &= 0x1f;
 		cntl1_regval = (gpu_scid << 0) | (gpu_scid << 5) | (gpu_scid << 10) |
@@ -1409,26 +1409,34 @@ static void a6xx_llc_activate(struct a6xx_gpu *a6xx_gpu)
 		}
 	}
 
-	if (cntl1_regval) {
+	if (!cntl1_regval)
+		return;
+
+	/*
+	 * Program the slice IDs for the various GPU blocks and GPU MMU
+	 * pagetables
+	 */
+	if (!a6xx_gpu->have_mmu500) {
+		a6xx_llc_write(a6xx_gpu,
+			REG_A6XX_CX_MISC_SYSTEM_CACHE_CNTL_1, cntl1_regval);
+
 		/*
-		 * Program the slice IDs for the various GPU blocks and GPU MMU
-		 * pagetables
+		 * Program cacheability overrides to not allocate cache
+		 * lines on a write miss
 		 */
-		if (a6xx_gpu->have_mmu500)
-			gpu_rmw(gpu, REG_A6XX_GBIF_SCACHE_CNTL1, GENMASK(24, 0),
-				cntl1_regval);
-		else {
-			a6xx_llc_write(a6xx_gpu,
-				REG_A6XX_CX_MISC_SYSTEM_CACHE_CNTL_1, cntl1_regval);
-
-			/*
-			 * Program cacheability overrides to not allocate cache
-			 * lines on a write miss
-			 */
-			a6xx_llc_rmw(a6xx_gpu,
-				REG_A6XX_CX_MISC_SYSTEM_CACHE_CNTL_0, 0xF, 0x03);
-		}
+		a6xx_llc_rmw(a6xx_gpu,
+			REG_A6XX_CX_MISC_SYSTEM_CACHE_CNTL_0, 0xF, 0x03);
+		return;
 	}
+
+	gpu_rmw(gpu, REG_A6XX_GBIF_SCACHE_CNTL1, GENMASK(24, 0), cntl1_regval);
+
+	/* On A660, the SCID programming for UCHE traffic is done in
+	 * A6XX_GBIF_SCACHE_CNTL0[14:10]
+	 */
+	if (adreno_is_a660(adreno_gpu))
+		gpu_rmw(gpu, REG_A6XX_GBIF_SCACHE_CNTL0, (0x1f << 10) |
+			(1 << 8), (gpu_scid << 10) | (1 << 8));
 }
 
 static void a6xx_llc_slices_destroy(struct a6xx_gpu *a6xx_gpu)
Signature · 2 lines
QUALCOMM INDIA, on behalf of Qualcomm Innovation Center, Inc. is a member
of Code Aurora Forum, hosted by The Linux Foundation.
#1 lore raw

PATCH 2/2 drm/msm/a6xx: Add support for Adreno 7c Gen 3 gpu

This patch adds support for the gpu found in the Snapdragon 7c Gen 3 compute platform. This gpu is similar to the exisiting a660 gpu with minor delta in the programing sequence. As the Adreno GPUs are moving away from a numeric chipid based naming scheme to a string, it was decided to use 0x06030500 as the gpu id of this gpu to communicate to the userspace driver.

---
 drivers/gpu/drm/msm/adreno/a6xx_gmu.c      | 20 ++++++++++++++++++-
 drivers/gpu/drm/msm/adreno/a6xx_gmu.h      |  1 +
 drivers/gpu/drm/msm/adreno/a6xx_gmu.xml.h  |  2 ++
 drivers/gpu/drm/msm/adreno/a6xx_gpu.c      | 21 ++++++++++++++------
 drivers/gpu/drm/msm/adreno/a6xx_hfi.c      | 32 ++++++++++++++++++++++++++++++
 drivers/gpu/drm/msm/adreno/adreno_device.c | 12 +++++++++++
 drivers/gpu/drm/msm/adreno/adreno_gpu.h    | 11 ++++++++--
 7 files changed, 90 insertions(+), 9 deletions(-)
drivers/gpu/drm/msm/adreno/a6xx_gmu.c +19 -1
index b349692..332301f 100644
@@ -933,6 +933,7 @@ int a6xx_gmu_resume(struct a6xx_gpu *a6xx_gpu)
 
 	/* Use a known rate to bring up the GMU */
 	clk_set_rate(gmu->core_clk, 200000000);
+	clk_set_rate(gmu->hub_clk, 150000000);
 	ret = clk_bulk_prepare_enable(gmu->nr_clocks, gmu->clocks);
 	if (ret) {
 		pm_runtime_put(gmu->gxpd);
@@ -1094,6 +1095,7 @@ static void a6xx_gmu_shutdown(struct a6xx_gmu *gmu)
 
 int a6xx_gmu_stop(struct a6xx_gpu *a6xx_gpu)
 {
+	struct adreno_gpu *adreno_gpu = &a6xx_gpu->base;
 	struct a6xx_gmu *gmu = &a6xx_gpu->gmu;
 	struct msm_gpu *gpu = &a6xx_gpu->base.base;
 
@@ -1117,9 +1119,22 @@ int a6xx_gmu_stop(struct a6xx_gpu *a6xx_gpu)
 	 * domain. Usually the GMU does this but only if the shutdown sequence
 	 * was successful
 	 */
-	if (!IS_ERR_OR_NULL(gmu->gxpd))
+	if (!IS_ERR_OR_NULL(gmu->gxpd)) {
+		/*
+		 * Toggle the loop_en bit, across disabling the gx gdsc,
+		 * with a delay of 10 XO cycles before disabling gx
+		 * gdsc. This is to prevent CPR measurements from
+		 * failing.
+		 */
+		if (adreno_is_a660(adreno_gpu))
+			gmu_rmw(gmu, REG_A6XX_GPU_CPR_FSM_CTL, 1, 0);
+
 		pm_runtime_put_sync(gmu->gxpd);
 
+		if (adreno_is_a660(adreno_gpu))
+			gmu_rmw(gmu, REG_A6XX_GPU_CPR_FSM_CTL, 1, 1);
+	}
+
 	clk_bulk_disable_unprepare(gmu->nr_clocks, gmu->clocks);
 
 	pm_runtime_put_sync(gmu->dev);
@@ -1393,6 +1408,9 @@ static int a6xx_gmu_clocks_probe(struct a6xx_gmu *gmu)
 	gmu->core_clk = msm_clk_bulk_get_clock(gmu->clocks,
 		gmu->nr_clocks, "gmu");
 
+	gmu->hub_clk = msm_clk_bulk_get_clock(gmu->clocks,
+		gmu->nr_clocks, "hub");
+
 	return 0;
 }
 
drivers/gpu/drm/msm/adreno/a6xx_gmu.h +1 -0
index 71dfa600..3c74f64 100644
@@ -66,6 +66,7 @@ struct a6xx_gmu {
 	int nr_clocks;
 	struct clk_bulk_data *clocks;
 	struct clk *core_clk;
+	struct clk *hub_clk;
 
 	/* current performance index set externally */
 	int current_perf_index;
drivers/gpu/drm/msm/adreno/a6xx_gmu.xml.h +2 -0
index 8115892..d46733f 100644
@@ -479,5 +479,7 @@ static inline uint32_t A6XX_GMU_GPU_NAP_CTRL_SID(uint32_t val)
 
 #define REG_A6XX_RSCC_TCS3_DRV0_STATUS				0x0000053e
 
+#define REG_A6XX_GPU_CPR_FSM_CTL				0x0000c001
+
 
 #endif /* A6XX_GMU_XML */
drivers/gpu/drm/msm/adreno/a6xx_gpu.c +15 -6
index 183b9f9..c0882536 100644
@@ -694,6 +694,13 @@ static void a6xx_set_ubwc_config(struct msm_gpu *gpu)
 		uavflagprd_inv = 2;
 	}
 
+	if (adreno_is_7c3(adreno_gpu)) {
+		lower_bit = 1;
+		amsbc = 1;
+		rgb565_predicator = 1;
+		uavflagprd_inv = 2;
+	}
+
 	gpu_write(gpu, REG_A6XX_RB_NC_MODE_CNTL,
 		rgb565_predicator << 11 | amsbc << 4 | lower_bit << 1);
 	gpu_write(gpu, REG_A6XX_TPL1_NC_MODE_CNTL, lower_bit << 1);
@@ -950,10 +957,10 @@ static int a6xx_hw_init(struct msm_gpu *gpu)
 	/* Setting the primFifo thresholds default values,
 	 * and vccCacheSkipDis=1 bit (0x200) for A640 and newer
 	*/
-	if (adreno_is_a650(adreno_gpu) || adreno_is_a660(adreno_gpu))
-		gpu_write(gpu, REG_A6XX_PC_DBG_ECO_CNTL, 0x00300200);
-	else if (adreno_is_a640(adreno_gpu))
+	if (adreno_is_a640(adreno_gpu) || adreno_is_7c3(adreno_gpu))
 		gpu_write(gpu, REG_A6XX_PC_DBG_ECO_CNTL, 0x00200200);
+	else if (adreno_is_a650(adreno_gpu) || adreno_is_a660(adreno_gpu))
+		gpu_write(gpu, REG_A6XX_PC_DBG_ECO_CNTL, 0x00300200);
 	else
 		gpu_write(gpu, REG_A6XX_PC_DBG_ECO_CNTL, 0x00180000);
 
@@ -993,8 +1000,9 @@ static int a6xx_hw_init(struct msm_gpu *gpu)
 	if (adreno_is_a660(adreno_gpu)) {
 		gpu_write(gpu, REG_A6XX_CP_CHICKEN_DBG, 0x1);
 		gpu_write(gpu, REG_A6XX_RBBM_GBIF_CLIENT_QOS_CNTL, 0x0);
-		/* Set dualQ + disable afull for A660 GPU but not for A635 */
-		gpu_write(gpu, REG_A6XX_UCHE_CMDQ_CONFIG, 0x66906);
+		/* Set dualQ + disable afull for A660 GPU but not for 7c3 */
+		if (!adreno_is_7c3(adreno_gpu))
+			gpu_write(gpu, REG_A6XX_UCHE_CMDQ_CONFIG, 0x66906);
 	}
 
 	/* Enable expanded apriv for targets that support it */
@@ -1780,7 +1788,8 @@ struct msm_gpu *a6xx_gpu_init(struct drm_device *dev)
 	 */
 	info = adreno_info(config->rev);
 
-	if (info && (info->revn == 650 || info->revn == 660))
+	if (info && (info->revn == 650 || info->revn == 660
+			|| info->revn == ADRENO_REV_7C3))
 		adreno_gpu->base.hw_apriv = true;
 
 	a6xx_llc_slices_init(pdev, a6xx_gpu);
drivers/gpu/drm/msm/adreno/a6xx_hfi.c +32 -0
index 9194337..1451c2b 100644
@@ -382,6 +382,36 @@ static void a660_build_bw_table(struct a6xx_hfi_msg_bw_table *msg)
 	msg->cnoc_cmds_data[1][0] =  0x60000001;
 }
 
+static void adreno_7c3_build_bw_table(struct a6xx_hfi_msg_bw_table *msg)
+{
+	/*
+	 * Send a single "off" entry just to get things running
+	 * TODO: bus scaling
+	 */
+	msg->bw_level_num = 1;
+
+	msg->ddr_cmds_num = 3;
+	msg->ddr_wait_bitmask = 0x07;
+
+	msg->ddr_cmds_addrs[0] = 0x50004;
+	msg->ddr_cmds_addrs[1] = 0x50000;
+	msg->ddr_cmds_addrs[2] = 0x50088;
+
+	msg->ddr_cmds_data[0][0] =  0x40000000;
+	msg->ddr_cmds_data[0][1] =  0x40000000;
+	msg->ddr_cmds_data[0][2] =  0x40000000;
+
+	/*
+	 * These are the CX (CNOC) votes - these are used by the GMU but the
+	 * votes are known and fixed for the target
+	 */
+	msg->cnoc_cmds_num = 1;
+	msg->cnoc_wait_bitmask = 0x01;
+
+	msg->cnoc_cmds_addrs[0] = 0x5006c;
+	msg->cnoc_cmds_data[0][0] =  0x40000000;
+	msg->cnoc_cmds_data[1][0] =  0x60000001;
+}
 static void a6xx_build_bw_table(struct a6xx_hfi_msg_bw_table *msg)
 {
 	/* Send a single "off" entry since the 630 GMU doesn't do bus scaling */
@@ -432,6 +462,8 @@ static int a6xx_hfi_send_bw_table(struct a6xx_gmu *gmu)
 		a640_build_bw_table(&msg);
 	else if (adreno_is_a650(adreno_gpu))
 		a650_build_bw_table(&msg);
+	else if (adreno_is_7c3(adreno_gpu))
+		adreno_7c3_build_bw_table(&msg);
 	else if (adreno_is_a660(adreno_gpu))
 		a660_build_bw_table(&msg);
 	else
drivers/gpu/drm/msm/adreno/adreno_device.c +12 -0
index 6dad801..063b847 100644
@@ -300,6 +300,18 @@ static const struct adreno_info gpulist[] = {
 		.init = a6xx_gpu_init,
 		.zapfw = "a660_zap.mdt",
 		.hwcg = a660_hwcg,
+	}, {
+		.rev = ADRENO_REV(6, 3, 5, ANY_ID),
+		.revn = ADRENO_REV_7C3,
+		.name = "Adreno 7c Gen 3",
+		.fw = {
+			[ADRENO_FW_SQE] = "a660_sqe.fw",
+			[ADRENO_FW_GMU] = "a660_gmu.bin",
+		},
+		.gmem = SZ_512K,
+		.inactive_period = DRM_MSM_INACTIVE_PERIOD,
+		.init = a6xx_gpu_init,
+		.hwcg = a660_hwcg,
 	},
 };
 
drivers/gpu/drm/msm/adreno/adreno_gpu.h +9 -2
index 8dbe0d1..679bc59 100644
@@ -247,15 +247,22 @@ static inline int adreno_is_a650(struct adreno_gpu *gpu)
        return gpu->revn == 650;
 }
 
+#define ADRENO_REV_7C3	0x06030500
+static inline int adreno_is_7c3(struct adreno_gpu *gpu)
+{
+       return gpu->revn == ADRENO_REV_7C3;
+}
+
 static inline int adreno_is_a660(struct adreno_gpu *gpu)
 {
-       return gpu->revn == 660;
+       return gpu->revn == 660 || gpu->revn == ADRENO_REV_7C3;
 }
 
 /* check for a650, a660, or any derivatives */
 static inline int adreno_is_a650_family(struct adreno_gpu *gpu)
 {
-       return gpu->revn == 650 || gpu->revn == 620 || gpu->revn == 660;
+       return gpu->revn == 650 || gpu->revn == 620 || gpu->revn == 660
+	       || gpu->revn == ADRENO_REV_7C3;
 }
 
 int adreno_get_param(struct msm_gpu *gpu, uint32_t param, uint64_t *value);
Signature · 2 lines
QUALCOMM INDIA, on behalf of Qualcomm Innovation Center, Inc. is a member
of Code Aurora Forum, hosted by The Linux Foundation.
#2 lore raw

Re: [Freedreno] [PATCH 2/2] drm/msm/a6xx: Add support for Adreno 7c Gen 3 gpu

()

Quoted 48 lines · Akhil P Oommen

This patch adds support for the gpu found in the Snapdragon 7c Gen 3 compute platform. This gpu is similar to the exisiting a660 gpu with minor delta in the programing sequence. As the Adreno GPUs are moving away from a numeric chipid based naming scheme to a string, it was decided to use 0x06030500 as the gpu id of this gpu to communicate to the userspace driver.

---
 drivers/gpu/drm/msm/adreno/a6xx_gmu.c      | 20 ++++++++++++++++++-
 drivers/gpu/drm/msm/adreno/a6xx_gmu.h      |  1 +
 drivers/gpu/drm/msm/adreno/a6xx_gmu.xml.h  |  2 ++
 drivers/gpu/drm/msm/adreno/a6xx_gpu.c      | 21 ++++++++++++++------
 drivers/gpu/drm/msm/adreno/a6xx_hfi.c      | 32 ++++++++++++++++++++++++++++++
 drivers/gpu/drm/msm/adreno/adreno_device.c | 12 +++++++++++
 drivers/gpu/drm/msm/adreno/adreno_gpu.h    | 11 ++++++++--
 7 files changed, 90 insertions(+), 9 deletions(-)
drivers/gpu/drm/msm/adreno/a6xx_gmu.c +6 -1
index b349692..332301f 100644
@@ -933,6 +933,7 @@ int a6xx_gmu_resume(struct a6xx_gpu *a6xx_gpu)
 
        /* Use a known rate to bring up the GMU */
        clk_set_rate(gmu->core_clk, 200000000);
+       clk_set_rate(gmu->hub_clk, 150000000);
        ret = clk_bulk_prepare_enable(gmu->nr_clocks, gmu->clocks);
        if (ret) {
                pm_runtime_put(gmu->gxpd);
@@ -1094,6 +1095,7 @@ static void a6xx_gmu_shutdown(struct a6xx_gmu *gmu)
 
 int a6xx_gmu_stop(struct a6xx_gpu *a6xx_gpu)
 {
+       struct adreno_gpu *adreno_gpu = &a6xx_gpu->base;
        struct a6xx_gmu *gmu = &a6xx_gpu->gmu;
        struct msm_gpu *gpu = &a6xx_gpu->base.base;
 
@@ -1117,9 +1119,22 @@ int a6xx_gmu_stop(struct a6xx_gpu *a6xx_gpu)
         * domain. Usually the GMU does this but only if the shutdown sequence
         * was successful
         */
-       if (!IS_ERR_OR_NULL(gmu->gxpd))
+       if (!IS_ERR_OR_NULL(gmu->gxpd)) {
+               /*
+                * Toggle the loop_en bit, across disabling the gx gdsc,
+                * with a delay of 10 XO cycles before disabling gx

drivers/gpu/drm/msm/adreno/a6xx_gmu.c int a6xx_gmu_stop(struct a6xx_gpu *a6xx_gpu) · line 1135

Quoted 10 lines
drivers/gpu/drm/msm/adreno/a6xx_gmu.c +8 -0
+                * gdsc. This is to prevent CPR measurements from
+                * failing.
+                */
+               if (adreno_is_a660(adreno_gpu))
+                       gmu_rmw(gmu, REG_A6XX_GPU_CPR_FSM_CTL, 1, 0);
+
                pm_runtime_put_sync(gmu->gxpd);
 
+               if (adreno_is_a660(adreno_gpu))
+                       gmu_rmw(gmu, REG_A6XX_GPU_CPR_FSM_CTL, 1, 1);

This kinda seems like it should be a separate patch.. but I noticed you silently turned adreno_is_a660() into what should probably be adreno_is_a660_family()

I'd suggest to break this out into it's own patch, so it is clear that it effects a660 as well, and then a next patch to rename adreno_is_a660_family()

Longer term, we might want to think about refactoring all the if(adreno_is_xyz()) into a features table (see i915_pci.c for ideas)

Quoted 148 lines
drivers/gpu/drm/msm/adreno/a6xx_gmu.c +5 -0
+       }
+
        clk_bulk_disable_unprepare(gmu->nr_clocks, gmu->clocks);
 
        pm_runtime_put_sync(gmu->dev);
@@ -1393,6 +1408,9 @@ static int a6xx_gmu_clocks_probe(struct a6xx_gmu *gmu)
        gmu->core_clk = msm_clk_bulk_get_clock(gmu->clocks,
                gmu->nr_clocks, "gmu");
 
+       gmu->hub_clk = msm_clk_bulk_get_clock(gmu->clocks,
+               gmu->nr_clocks, "hub");
+
        return 0;
 }
 
drivers/gpu/drm/msm/adreno/a6xx_gmu.h +1 -0
index 71dfa600..3c74f64 100644
@@ -66,6 +66,7 @@ struct a6xx_gmu {
        int nr_clocks;
        struct clk_bulk_data *clocks;
        struct clk *core_clk;
+       struct clk *hub_clk;
 
        /* current performance index set externally */
        int current_perf_index;
drivers/gpu/drm/msm/adreno/a6xx_gmu.xml.h +2 -0
index 8115892..d46733f 100644
@@ -479,5 +479,7 @@ static inline uint32_t A6XX_GMU_GPU_NAP_CTRL_SID(uint32_t val)
 
 #define REG_A6XX_RSCC_TCS3_DRV0_STATUS                         0x0000053e
 
+#define REG_A6XX_GPU_CPR_FSM_CTL                               0x0000c001
+
 
 #endif /* A6XX_GMU_XML */
drivers/gpu/drm/msm/adreno/a6xx_gpu.c +15 -6
index 183b9f9..c0882536 100644
@@ -694,6 +694,13 @@ static void a6xx_set_ubwc_config(struct msm_gpu *gpu)
                uavflagprd_inv = 2;
        }
 
+       if (adreno_is_7c3(adreno_gpu)) {
+               lower_bit = 1;
+               amsbc = 1;
+               rgb565_predicator = 1;
+               uavflagprd_inv = 2;
+       }
+
        gpu_write(gpu, REG_A6XX_RB_NC_MODE_CNTL,
                rgb565_predicator << 11 | amsbc << 4 | lower_bit << 1);
        gpu_write(gpu, REG_A6XX_TPL1_NC_MODE_CNTL, lower_bit << 1);
@@ -950,10 +957,10 @@ static int a6xx_hw_init(struct msm_gpu *gpu)
        /* Setting the primFifo thresholds default values,
         * and vccCacheSkipDis=1 bit (0x200) for A640 and newer
        */
-       if (adreno_is_a650(adreno_gpu) || adreno_is_a660(adreno_gpu))
-               gpu_write(gpu, REG_A6XX_PC_DBG_ECO_CNTL, 0x00300200);
-       else if (adreno_is_a640(adreno_gpu))
+       if (adreno_is_a640(adreno_gpu) || adreno_is_7c3(adreno_gpu))
                gpu_write(gpu, REG_A6XX_PC_DBG_ECO_CNTL, 0x00200200);
+       else if (adreno_is_a650(adreno_gpu) || adreno_is_a660(adreno_gpu))
+               gpu_write(gpu, REG_A6XX_PC_DBG_ECO_CNTL, 0x00300200);
        else
                gpu_write(gpu, REG_A6XX_PC_DBG_ECO_CNTL, 0x00180000);
 
@@ -993,8 +1000,9 @@ static int a6xx_hw_init(struct msm_gpu *gpu)
        if (adreno_is_a660(adreno_gpu)) {
                gpu_write(gpu, REG_A6XX_CP_CHICKEN_DBG, 0x1);
                gpu_write(gpu, REG_A6XX_RBBM_GBIF_CLIENT_QOS_CNTL, 0x0);
-               /* Set dualQ + disable afull for A660 GPU but not for A635 */
-               gpu_write(gpu, REG_A6XX_UCHE_CMDQ_CONFIG, 0x66906);
+               /* Set dualQ + disable afull for A660 GPU but not for 7c3 */
+               if (!adreno_is_7c3(adreno_gpu))
+                       gpu_write(gpu, REG_A6XX_UCHE_CMDQ_CONFIG, 0x66906);
        }
 
        /* Enable expanded apriv for targets that support it */
@@ -1780,7 +1788,8 @@ struct msm_gpu *a6xx_gpu_init(struct drm_device *dev)
         */
        info = adreno_info(config->rev);
 
-       if (info && (info->revn == 650 || info->revn == 660))
+       if (info && (info->revn == 650 || info->revn == 660
+                       || info->revn == ADRENO_REV_7C3))
                adreno_gpu->base.hw_apriv = true;
 
        a6xx_llc_slices_init(pdev, a6xx_gpu);
drivers/gpu/drm/msm/adreno/a6xx_hfi.c +32 -0
index 9194337..1451c2b 100644
@@ -382,6 +382,36 @@ static void a660_build_bw_table(struct a6xx_hfi_msg_bw_table *msg)
        msg->cnoc_cmds_data[1][0] =  0x60000001;
 }
 
+static void adreno_7c3_build_bw_table(struct a6xx_hfi_msg_bw_table *msg)
+{
+       /*
+        * Send a single "off" entry just to get things running
+        * TODO: bus scaling
+        */
+       msg->bw_level_num = 1;
+
+       msg->ddr_cmds_num = 3;
+       msg->ddr_wait_bitmask = 0x07;
+
+       msg->ddr_cmds_addrs[0] = 0x50004;
+       msg->ddr_cmds_addrs[1] = 0x50000;
+       msg->ddr_cmds_addrs[2] = 0x50088;
+
+       msg->ddr_cmds_data[0][0] =  0x40000000;
+       msg->ddr_cmds_data[0][1] =  0x40000000;
+       msg->ddr_cmds_data[0][2] =  0x40000000;
+
+       /*
+        * These are the CX (CNOC) votes - these are used by the GMU but the
+        * votes are known and fixed for the target
+        */
+       msg->cnoc_cmds_num = 1;
+       msg->cnoc_wait_bitmask = 0x01;
+
+       msg->cnoc_cmds_addrs[0] = 0x5006c;
+       msg->cnoc_cmds_data[0][0] =  0x40000000;
+       msg->cnoc_cmds_data[1][0] =  0x60000001;
+}
 static void a6xx_build_bw_table(struct a6xx_hfi_msg_bw_table *msg)
 {
        /* Send a single "off" entry since the 630 GMU doesn't do bus scaling */
@@ -432,6 +462,8 @@ static int a6xx_hfi_send_bw_table(struct a6xx_gmu *gmu)
                a640_build_bw_table(&msg);
        else if (adreno_is_a650(adreno_gpu))
                a650_build_bw_table(&msg);
+       else if (adreno_is_7c3(adreno_gpu))
+               adreno_7c3_build_bw_table(&msg);
        else if (adreno_is_a660(adreno_gpu))
                a660_build_bw_table(&msg);
        else
drivers/gpu/drm/msm/adreno/adreno_device.c +0 -0
index 6dad801..063b847 100644

drivers/gpu/drm/msm/adreno/adreno_device.c static const struct adreno_info gpulist[] = { · line 305

Quoted 6 lines
drivers/gpu/drm/msm/adreno/adreno_device.c +3 -0
@@ -300,6 +300,18 @@ static const struct adreno_info gpulist[] = {
                .init = a6xx_gpu_init,
                .zapfw = "a660_zap.mdt",
                .hwcg = a660_hwcg,
+       }, {
+               .rev = ADRENO_REV(6, 3, 5, ANY_ID),
+               .revn = ADRENO_REV_7C3,

So rather than adding an ARENO_REV_7C3 define, I was thinking to just not set .revn (leave it zero) and identify based on .rev .. that (ie. GPU_ID being zero) would also be the signal to userspace to identify the GPU via CHIP_ID instead

You could extract out the version comparison in adreno_info() into a helper that can be re-used in things like adreno_is_a660_family() and adreno_is_7c3().

BR,
-R

Quoted 49 lines
drivers/gpu/drm/msm/adreno/adreno_device.c +9 -0
+               .name = "Adreno 7c Gen 3",
+               .fw = {
+                       [ADRENO_FW_SQE] = "a660_sqe.fw",
+                       [ADRENO_FW_GMU] = "a660_gmu.bin",
+               },
+               .gmem = SZ_512K,
+               .inactive_period = DRM_MSM_INACTIVE_PERIOD,
+               .init = a6xx_gpu_init,
+               .hwcg = a660_hwcg,
        },
 };
 
drivers/gpu/drm/msm/adreno/adreno_gpu.h +9 -3
index 8dbe0d1..679bc59 100644
@@ -247,15 +247,22 @@ static inline int adreno_is_a650(struct adreno_gpu *gpu)
        return gpu->revn == 650;
 }
 
+#define ADRENO_REV_7C3 0x06030500
+static inline int adreno_is_7c3(struct adreno_gpu *gpu)
+{
+       return gpu->revn == ADRENO_REV_7C3;
+}
+
 static inline int adreno_is_a660(struct adreno_gpu *gpu)
 {
-       return gpu->revn == 660;
+       return gpu->revn == 660 || gpu->revn == ADRENO_REV_7C3;
 }
 
 /* check for a650, a660, or any derivatives */
 static inline int adreno_is_a650_family(struct adreno_gpu *gpu)
 {
-       return gpu->revn == 650 || gpu->revn == 620 || gpu->revn == 660;
+       return gpu->revn == 650 || gpu->revn == 620 || gpu->revn == 660
+              || gpu->revn == ADRENO_REV_7C3;
 }
 
 int adreno_get_param(struct msm_gpu *gpu, uint32_t param, uint64_t *value);
--

QUALCOMM INDIA, on behalf of Qualcomm Innovation Center, Inc. is a member of Code Aurora Forum, hosted by The Linux Foundation.

_______________________________________________
Freedreno mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/freedreno

#3 lore raw

Re: [Freedreno] [PATCH 2/2] drm/msm/a6xx: Add support for Adreno 7c Gen 3 gpu

Quoted 66 lines · Rob Clark

()

Quoted 48 lines · Akhil P Oommen

This patch adds support for the gpu found in the Snapdragon 7c Gen 3 compute platform. This gpu is similar to the exisiting a660 gpu with minor delta in the programing sequence. As the Adreno GPUs are moving away from a numeric chipid based naming scheme to a string, it was decided to use 0x06030500 as the gpu id of this gpu to communicate to the userspace driver.

---
  drivers/gpu/drm/msm/adreno/a6xx_gmu.c      | 20 ++++++++++++++++++-
  drivers/gpu/drm/msm/adreno/a6xx_gmu.h      |  1 +
  drivers/gpu/drm/msm/adreno/a6xx_gmu.xml.h  |  2 ++
  drivers/gpu/drm/msm/adreno/a6xx_gpu.c      | 21 ++++++++++++++------
  drivers/gpu/drm/msm/adreno/a6xx_hfi.c      | 32 ++++++++++++++++++++++++++++++
  drivers/gpu/drm/msm/adreno/adreno_device.c | 12 +++++++++++
  drivers/gpu/drm/msm/adreno/adreno_gpu.h    | 11 ++++++++--
  7 files changed, 90 insertions(+), 9 deletions(-)
drivers/gpu/drm/msm/adreno/a6xx_gmu.c +6 -1
index b349692..332301f 100644
@@ -933,6 +933,7 @@ int a6xx_gmu_resume(struct a6xx_gpu *a6xx_gpu)
 
         /* Use a known rate to bring up the GMU */
         clk_set_rate(gmu->core_clk, 200000000);
+       clk_set_rate(gmu->hub_clk, 150000000);
         ret = clk_bulk_prepare_enable(gmu->nr_clocks, gmu->clocks);
         if (ret) {
                 pm_runtime_put(gmu->gxpd);
@@ -1094,6 +1095,7 @@ static void a6xx_gmu_shutdown(struct a6xx_gmu *gmu)
 
  int a6xx_gmu_stop(struct a6xx_gpu *a6xx_gpu)
  {
+       struct adreno_gpu *adreno_gpu = &a6xx_gpu->base;
         struct a6xx_gmu *gmu = &a6xx_gpu->gmu;
         struct msm_gpu *gpu = &a6xx_gpu->base.base;
 
@@ -1117,9 +1119,22 @@ int a6xx_gmu_stop(struct a6xx_gpu *a6xx_gpu)
          * domain. Usually the GMU does this but only if the shutdown sequence
          * was successful
          */
-       if (!IS_ERR_OR_NULL(gmu->gxpd))
+       if (!IS_ERR_OR_NULL(gmu->gxpd)) {
+               /*
+                * Toggle the loop_en bit, across disabling the gx gdsc,
+                * with a delay of 10 XO cycles before disabling gx

drivers/gpu/drm/msm/adreno/a6xx_gmu.c int a6xx_gmu_stop(struct a6xx_gpu *a6xx_gpu) · line 1135

Quoted 10 lines
drivers/gpu/drm/msm/adreno/a6xx_gmu.c +8 -0
+                * gdsc. This is to prevent CPR measurements from
+                * failing.
+                */
+               if (adreno_is_a660(adreno_gpu))
+                       gmu_rmw(gmu, REG_A6XX_GPU_CPR_FSM_CTL, 1, 0);
+
                 pm_runtime_put_sync(gmu->gxpd);
 
+               if (adreno_is_a660(adreno_gpu))
+                       gmu_rmw(gmu, REG_A6XX_GPU_CPR_FSM_CTL, 1, 1);

This kinda seems like it should be a separate patch.. but I noticed you silently turned adreno_is_a660() into what should probably be adreno_is_a660_family()

Quoted 6 lines

I'd suggest to break this out into it's own patch, so it is clear that it effects a660 as well, and then a next patch to rename adreno_is_a660_family()

Longer term, we might want to think about refactoring all the if(adreno_is_xyz()) into a features table (see i915_pci.c for ideas)

I agree. This should have been a seperate patch.

Quoted 161 lines
Quoted 149 lines
drivers/gpu/drm/msm/adreno/a6xx_gmu.c +5 -0
+       }
+
         clk_bulk_disable_unprepare(gmu->nr_clocks, gmu->clocks);
 
         pm_runtime_put_sync(gmu->dev);
@@ -1393,6 +1408,9 @@ static int a6xx_gmu_clocks_probe(struct a6xx_gmu *gmu)
         gmu->core_clk = msm_clk_bulk_get_clock(gmu->clocks,
                 gmu->nr_clocks, "gmu");
 
+       gmu->hub_clk = msm_clk_bulk_get_clock(gmu->clocks,
+               gmu->nr_clocks, "hub");
+
         return 0;
  }
 
drivers/gpu/drm/msm/adreno/a6xx_gmu.h +1 -0
index 71dfa600..3c74f64 100644
@@ -66,6 +66,7 @@ struct a6xx_gmu {
         int nr_clocks;
         struct clk_bulk_data *clocks;
         struct clk *core_clk;
+       struct clk *hub_clk;
 
         /* current performance index set externally */
         int current_perf_index;
drivers/gpu/drm/msm/adreno/a6xx_gmu.xml.h +2 -0
index 8115892..d46733f 100644
@@ -479,5 +479,7 @@ static inline uint32_t A6XX_GMU_GPU_NAP_CTRL_SID(uint32_t val)
 
  #define REG_A6XX_RSCC_TCS3_DRV0_STATUS                         0x0000053e
 
+#define REG_A6XX_GPU_CPR_FSM_CTL                               0x0000c001
+
 
  #endif /* A6XX_GMU_XML */
drivers/gpu/drm/msm/adreno/a6xx_gpu.c +15 -6
index 183b9f9..c0882536 100644
@@ -694,6 +694,13 @@ static void a6xx_set_ubwc_config(struct msm_gpu *gpu)
                 uavflagprd_inv = 2;
         }
 
+       if (adreno_is_7c3(adreno_gpu)) {
+               lower_bit = 1;
+               amsbc = 1;
+               rgb565_predicator = 1;
+               uavflagprd_inv = 2;
+       }
+
         gpu_write(gpu, REG_A6XX_RB_NC_MODE_CNTL,
                 rgb565_predicator << 11 | amsbc << 4 | lower_bit << 1);
         gpu_write(gpu, REG_A6XX_TPL1_NC_MODE_CNTL, lower_bit << 1);
@@ -950,10 +957,10 @@ static int a6xx_hw_init(struct msm_gpu *gpu)
         /* Setting the primFifo thresholds default values,
          * and vccCacheSkipDis=1 bit (0x200) for A640 and newer
         */
-       if (adreno_is_a650(adreno_gpu) || adreno_is_a660(adreno_gpu))
-               gpu_write(gpu, REG_A6XX_PC_DBG_ECO_CNTL, 0x00300200);
-       else if (adreno_is_a640(adreno_gpu))
+       if (adreno_is_a640(adreno_gpu) || adreno_is_7c3(adreno_gpu))
                 gpu_write(gpu, REG_A6XX_PC_DBG_ECO_CNTL, 0x00200200);
+       else if (adreno_is_a650(adreno_gpu) || adreno_is_a660(adreno_gpu))
+               gpu_write(gpu, REG_A6XX_PC_DBG_ECO_CNTL, 0x00300200);
         else
                 gpu_write(gpu, REG_A6XX_PC_DBG_ECO_CNTL, 0x00180000);
 
@@ -993,8 +1000,9 @@ static int a6xx_hw_init(struct msm_gpu *gpu)
         if (adreno_is_a660(adreno_gpu)) {
                 gpu_write(gpu, REG_A6XX_CP_CHICKEN_DBG, 0x1);
                 gpu_write(gpu, REG_A6XX_RBBM_GBIF_CLIENT_QOS_CNTL, 0x0);
-               /* Set dualQ + disable afull for A660 GPU but not for A635 */
-               gpu_write(gpu, REG_A6XX_UCHE_CMDQ_CONFIG, 0x66906);
+               /* Set dualQ + disable afull for A660 GPU but not for 7c3 */
+               if (!adreno_is_7c3(adreno_gpu))
+                       gpu_write(gpu, REG_A6XX_UCHE_CMDQ_CONFIG, 0x66906);
         }
 
         /* Enable expanded apriv for targets that support it */
@@ -1780,7 +1788,8 @@ struct msm_gpu *a6xx_gpu_init(struct drm_device *dev)
          */
         info = adreno_info(config->rev);
 
-       if (info && (info->revn == 650 || info->revn == 660))
+       if (info && (info->revn == 650 || info->revn == 660
+                       || info->revn == ADRENO_REV_7C3))
                 adreno_gpu->base.hw_apriv = true;
 
         a6xx_llc_slices_init(pdev, a6xx_gpu);
drivers/gpu/drm/msm/adreno/a6xx_hfi.c +32 -0
index 9194337..1451c2b 100644
@@ -382,6 +382,36 @@ static void a660_build_bw_table(struct a6xx_hfi_msg_bw_table *msg)
         msg->cnoc_cmds_data[1][0] =  0x60000001;
  }
 
+static void adreno_7c3_build_bw_table(struct a6xx_hfi_msg_bw_table *msg)
+{
+       /*
+        * Send a single "off" entry just to get things running
+        * TODO: bus scaling
+        */
+       msg->bw_level_num = 1;
+
+       msg->ddr_cmds_num = 3;
+       msg->ddr_wait_bitmask = 0x07;
+
+       msg->ddr_cmds_addrs[0] = 0x50004;
+       msg->ddr_cmds_addrs[1] = 0x50000;
+       msg->ddr_cmds_addrs[2] = 0x50088;
+
+       msg->ddr_cmds_data[0][0] =  0x40000000;
+       msg->ddr_cmds_data[0][1] =  0x40000000;
+       msg->ddr_cmds_data[0][2] =  0x40000000;
+
+       /*
+        * These are the CX (CNOC) votes - these are used by the GMU but the
+        * votes are known and fixed for the target
+        */
+       msg->cnoc_cmds_num = 1;
+       msg->cnoc_wait_bitmask = 0x01;
+
+       msg->cnoc_cmds_addrs[0] = 0x5006c;
+       msg->cnoc_cmds_data[0][0] =  0x40000000;
+       msg->cnoc_cmds_data[1][0] =  0x60000001;
+}
  static void a6xx_build_bw_table(struct a6xx_hfi_msg_bw_table *msg)
  {
         /* Send a single "off" entry since the 630 GMU doesn't do bus scaling */
@@ -432,6 +462,8 @@ static int a6xx_hfi_send_bw_table(struct a6xx_gmu *gmu)
                 a640_build_bw_table(&msg);
         else if (adreno_is_a650(adreno_gpu))
                 a650_build_bw_table(&msg);
+       else if (adreno_is_7c3(adreno_gpu))
+               adreno_7c3_build_bw_table(&msg);
         else if (adreno_is_a660(adreno_gpu))
                 a660_build_bw_table(&msg);
         else
drivers/gpu/drm/msm/adreno/adreno_device.c +0 -0
index 6dad801..063b847 100644

drivers/gpu/drm/msm/adreno/adreno_device.c static const struct adreno_info gpulist[] = { · line 305

Quoted 6 lines
drivers/gpu/drm/msm/adreno/adreno_device.c +3 -0
@@ -300,6 +300,18 @@ static const struct adreno_info gpulist[] = {
                 .init = a6xx_gpu_init,
                 .zapfw = "a660_zap.mdt",
                 .hwcg = a660_hwcg,
+       }, {
+               .rev = ADRENO_REV(6, 3, 5, ANY_ID),
+               .revn = ADRENO_REV_7C3,

So rather than adding an ARENO_REV_7C3 define, I was thinking to just not set .revn (leave it zero) and identify based on .rev .. that (ie. GPU_ID being zero) would also be the signal to userspace to identify the GPU via CHIP_ID instead

Quoted 6 lines

You could extract out the version comparison in adreno_info() into a helper that can be re-used in things like adreno_is_a660_family() and adreno_is_7c3().

BR,
-R

Sure. Will update this patch.

-Akhil.

Quoted 50 lines
Quoted 50 lines
drivers/gpu/drm/msm/adreno/adreno_device.c +9 -0
+               .name = "Adreno 7c Gen 3",
+               .fw = {
+                       [ADRENO_FW_SQE] = "a660_sqe.fw",
+                       [ADRENO_FW_GMU] = "a660_gmu.bin",
+               },
+               .gmem = SZ_512K,
+               .inactive_period = DRM_MSM_INACTIVE_PERIOD,
+               .init = a6xx_gpu_init,
+               .hwcg = a660_hwcg,
         },
  };
 
drivers/gpu/drm/msm/adreno/adreno_gpu.h +9 -3
index 8dbe0d1..679bc59 100644
@@ -247,15 +247,22 @@ static inline int adreno_is_a650(struct adreno_gpu *gpu)
         return gpu->revn == 650;
  }
 
+#define ADRENO_REV_7C3 0x06030500
+static inline int adreno_is_7c3(struct adreno_gpu *gpu)
+{
+       return gpu->revn == ADRENO_REV_7C3;
+}
+
  static inline int adreno_is_a660(struct adreno_gpu *gpu)
  {
-       return gpu->revn == 660;
+       return gpu->revn == 660 || gpu->revn == ADRENO_REV_7C3;
  }
 
  /* check for a650, a660, or any derivatives */
  static inline int adreno_is_a650_family(struct adreno_gpu *gpu)
  {
-       return gpu->revn == 650 || gpu->revn == 620 || gpu->revn == 660;
+       return gpu->revn == 650 || gpu->revn == 620 || gpu->revn == 660
+              || gpu->revn == ADRENO_REV_7C3;
  }
 
  int adreno_get_param(struct msm_gpu *gpu, uint32_t param, uint64_t *value);
--

QUALCOMM INDIA, on behalf of Qualcomm Innovation Center, Inc. is a member of Code Aurora Forum, hosted by The Linux Foundation.

_______________________________________________
Freedreno mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/freedreno