The Adreno GPU Management Unit (GMU) can also scale the ddr
bandwidth along the frequency and power domain level, but for
now we statically fill the bw_table with values from the
downstream driver.

Only the first entry is used, which is a disable vote, so we
currently rely on scaling via the linux interconnect paths.

Let's dynamically generate the bw_table with the vote values
previously calculated from the OPPs.

Those entried will then be used by the GMU when passing the
appropriate bandwidth level while voting for a gpu frequency.

Signed-off-by: Neil Armstrong <neil.armstrong@linaro.org>
---
 drivers/gpu/drm/msm/adreno/a6xx_hfi.c | 39 ++++++++++++++++++++++++++++++++---
 1 file changed, 36 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/msm/adreno/a6xx_hfi.c b/drivers/gpu/drm/msm/adreno/a6xx_hfi.c
index cb8844ed46b29c4569d05eb7a24f7b27e173190f..fe1946650425b749bad483dad1e630bc8be83abc 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_hfi.c
+++ b/drivers/gpu/drm/msm/adreno/a6xx_hfi.c
@@ -621,6 +621,35 @@ static void a740_build_bw_table(struct a6xx_hfi_msg_bw_table *msg)
 	msg->cnoc_cmds_data[1][0] = 0x60000001;
 }
 
+static void a740_generate_bw_table(const struct a6xx_info *info, struct a6xx_gmu *gmu,
+				   struct a6xx_hfi_msg_bw_table *msg)
+{
+	unsigned int i, j;
+
+	msg->ddr_wait_bitmask = 0x7;
+
+	for (i = 0; i < GMU_MAX_BCMS; i++) {
+		if (!info->bcms[i].name)
+			break;
+		msg->ddr_cmds_addrs[i] = cmd_db_read_addr(info->bcms[i].name);
+	}
+	msg->ddr_cmds_num = i;
+
+	for (i = 0; i < gmu->nr_gpu_bws; ++i)
+		for (j = 0; j < msg->ddr_cmds_num; j++)
+			msg->ddr_cmds_data[i][j] = gmu->gpu_ib_votes[i][j];
+	msg->bw_level_num = gmu->nr_gpu_bws;
+
+	/* TODO also generate CNOC commands */
+
+	msg->cnoc_cmds_num = 1;
+	msg->cnoc_wait_bitmask = 0x1;
+
+	msg->cnoc_cmds_addrs[0] = cmd_db_read_addr("CN0");
+	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 */
@@ -664,6 +693,7 @@ static int a6xx_hfi_send_bw_table(struct a6xx_gmu *gmu)
 	struct a6xx_hfi_msg_bw_table *msg;
 	struct a6xx_gpu *a6xx_gpu = container_of(gmu, struct a6xx_gpu, gmu);
 	struct adreno_gpu *adreno_gpu = &a6xx_gpu->base;
+	const struct a6xx_info *info = adreno_gpu->info->a6xx;
 
 	if (gmu->bw_table)
 		goto send;
@@ -690,9 +720,12 @@ static int a6xx_hfi_send_bw_table(struct a6xx_gmu *gmu)
 		a690_build_bw_table(msg);
 	else if (adreno_is_a730(adreno_gpu))
 		a730_build_bw_table(msg);
-	else if (adreno_is_a740_family(adreno_gpu))
-		a740_build_bw_table(msg);
-	else
+	else if (adreno_is_a740_family(adreno_gpu)) {
+		if (info->bcms && gmu->nr_gpu_bws > 1)
+			a740_generate_bw_table(info, gmu, msg);
+		else
+			a740_build_bw_table(msg);
+	} else
 		a6xx_build_bw_table(msg);
 
 	gmu->bw_table = msg;

-- 
2.34.1

On 28.11.2024 11:25 AM, Neil Armstrong wrote:
> The Adreno GPU Management Unit (GMU) can also scale the ddr
> bandwidth along the frequency and power domain level, but for
> now we statically fill the bw_table with values from the
> downstream driver.
> 
> Only the first entry is used, which is a disable vote, so we
> currently rely on scaling via the linux interconnect paths.
> 
> Let's dynamically generate the bw_table with the vote values
> previously calculated from the OPPs.
> 
> Those entried will then be used by the GMU when passing the

entries

> appropriate bandwidth level while voting for a gpu frequency.
> 
> Signed-off-by: Neil Armstrong <neil.armstrong@linaro.org>
> ---

[...]

>  drivers/gpu/drm/msm/adreno/a6xx_hfi.c | 39 ++++++++++++++++++++++++++++++++---
>  1 file changed, 36 insertions(+), 3 deletions(-)
> 
> diff --git a/drivers/gpu/drm/msm/adreno/a6xx_hfi.c b/drivers/gpu/drm/msm/adreno/a6xx_hfi.c
> index cb8844ed46b29c4569d05eb7a24f7b27e173190f..fe1946650425b749bad483dad1e630bc8be83abc 100644
> --- a/drivers/gpu/drm/msm/adreno/a6xx_hfi.c
> +++ b/drivers/gpu/drm/msm/adreno/a6xx_hfi.c
> @@ -621,6 +621,35 @@ static void a740_build_bw_table(struct a6xx_hfi_msg_bw_table *msg)
>  	msg->cnoc_cmds_data[1][0] = 0x60000001;
>  }
>  
> +static void a740_generate_bw_table(const struct a6xx_info *info, struct a6xx_gmu *gmu,
> +				   struct a6xx_hfi_msg_bw_table *msg)

This should work for all targets

> +{
> +	unsigned int i, j;
> +
> +	msg->ddr_wait_bitmask = 0x7;

GENMASK; also should be generated based on BCM data dynamically, there's
logic for it in bcm-voter.c : tcs_list_gen()

> +
> +	for (i = 0; i < GMU_MAX_BCMS; i++) {
> +		if (!info->bcms[i].name)
> +			break;
> +		msg->ddr_cmds_addrs[i] = cmd_db_read_addr(info->bcms[i].name);

A7xx share a common list of BCMs, the buswidth may differ per soc and it's
something already stored in ICC drivers

> +	}
> +	msg->ddr_cmds_num = i;
> +
> +	for (i = 0; i < gmu->nr_gpu_bws; ++i)
> +		for (j = 0; j < msg->ddr_cmds_num; j++)
> +			msg->ddr_cmds_data[i][j] = gmu->gpu_ib_votes[i][j];
> +	msg->bw_level_num = gmu->nr_gpu_bws;
> +
> +	/* TODO also generate CNOC commands */

We only do on/off (0/100 units - kbps?), it seems

> +
> +	msg->cnoc_cmds_num = 1;
> +	msg->cnoc_wait_bitmask = 0x1;
> +
> +	msg->cnoc_cmds_addrs[0] = cmd_db_read_addr("CN0");
> +	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 */
> @@ -664,6 +693,7 @@ static int a6xx_hfi_send_bw_table(struct a6xx_gmu *gmu)
>  	struct a6xx_hfi_msg_bw_table *msg;
>  	struct a6xx_gpu *a6xx_gpu = container_of(gmu, struct a6xx_gpu, gmu);
>  	struct adreno_gpu *adreno_gpu = &a6xx_gpu->base;
> +	const struct a6xx_info *info = adreno_gpu->info->a6xx;
>  
>  	if (gmu->bw_table)
>  		goto send;
> @@ -690,9 +720,12 @@ static int a6xx_hfi_send_bw_table(struct a6xx_gmu *gmu)
>  		a690_build_bw_table(msg);
>  	else if (adreno_is_a730(adreno_gpu))
>  		a730_build_bw_table(msg);
> -	else if (adreno_is_a740_family(adreno_gpu))
> -		a740_build_bw_table(msg);
> -	else
> +	else if (adreno_is_a740_family(adreno_gpu)) {
> +		if (info->bcms && gmu->nr_gpu_bws > 1)
> +			a740_generate_bw_table(info, gmu, msg);

This if should come before the hardcoded if-else chain, as it
applies to all platforms

Konrad