1. Patchew
  2. linux
  3. [PATCH v5 0/7] drm/msm: adreno: add support for DDR bandwidth scaling via GMU
  4. View patch

[PATCH v5 3/7] drm/msm: adreno: dynamically generate GMU bw table

Neil Armstrong posted 7 patches 1 year ago
There is a newer version of this series
[PATCH v5 3/7] drm/msm: adreno: dynamically generate GMU bw table
Posted by Neil Armstrong 1 year ago 
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 entries 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 | 48 ++++++++++++++++++++++++++++++++++-
 1 file changed, 47 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/msm/adreno/a6xx_hfi.c b/drivers/gpu/drm/msm/adreno/a6xx_hfi.c
index cb8844ed46b29c4569d05eb7a24f7b27e173190f..995526620d678cd05020315f771213e4a6943bec 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_hfi.c
+++ b/drivers/gpu/drm/msm/adreno/a6xx_hfi.c
@@ -6,6 +6,7 @@
 #include <linux/list.h>
 
 #include <soc/qcom/cmd-db.h>
+#include <soc/qcom/tcs.h>
 
 #include "a6xx_gmu.h"
 #include "a6xx_gmu.xml.h"
@@ -259,6 +260,48 @@ static int a6xx_hfi_send_perf_table(struct a6xx_gmu *gmu)
 		NULL, 0);
 }
 
+static void a6xx_generate_bw_table(const struct a6xx_info *info, struct a6xx_gmu *gmu,
+				   struct a6xx_hfi_msg_bw_table *msg)
+{
+	unsigned int i, j;
+
+	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;
+
+	/* Compute the wait bitmask with each BCM having the commit bit */
+	msg->ddr_wait_bitmask = 0;
+	for (j = 0; j < msg->ddr_cmds_num; j++)
+		if (msg->ddr_cmds_data[0][j] & BCM_TCS_CMD_COMMIT_MASK)
+			msg->ddr_wait_bitmask |= BIT(j);
+
+	/*
+	 * These are the CX (CNOC) votes - these are used by the GMU
+	 * The 'CN0' BCM is used on all targets, and votes are basically
+	 * 'off' and 'on' states with first bit to enable the path.
+	 */
+
+	msg->cnoc_cmds_addrs[0] = cmd_db_read_addr("CN0");
+	msg->cnoc_cmds_num = 1;
+
+	msg->cnoc_cmds_data[0][0] = BCM_TCS_CMD(true, false, 0, 0);
+	msg->cnoc_cmds_data[1][0] = BCM_TCS_CMD(true, true, 0, BIT(0));
+
+	/* Compute the wait bitmask with each BCM having the commit bit */
+	msg->cnoc_wait_bitmask = 0;
+	for (j = 0; j < msg->cnoc_cmds_num; j++)
+		if (msg->cnoc_cmds_data[0][j] & BCM_TCS_CMD_COMMIT_MASK)
+			msg->cnoc_wait_bitmask |= BIT(j);
+}
+
 static void a618_build_bw_table(struct a6xx_hfi_msg_bw_table *msg)
 {
 	/* Send a single "off" entry since the 618 GMU doesn't do bus scaling */
@@ -664,6 +707,7 @@ 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;
@@ -672,7 +716,9 @@ static int a6xx_hfi_send_bw_table(struct a6xx_gmu *gmu)
 	if (!msg)
 		return -ENOMEM;
 
-	if (adreno_is_a618(adreno_gpu))
+	if (info->bcms && gmu->nr_gpu_bws > 1)
+		a6xx_generate_bw_table(info, gmu, msg);
+	else if (adreno_is_a618(adreno_gpu))
 		a618_build_bw_table(msg);
 	else if (adreno_is_a619(adreno_gpu))
 		a619_build_bw_table(msg);

-- 
2.34.1
Re: [PATCH v5 3/7] drm/msm: adreno: dynamically generate GMU bw table
Posted by Konrad Dybcio 1 year ago 
On 11.12.2024 9:29 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 entries 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 | 48 ++++++++++++++++++++++++++++++++++-
>  1 file changed, 47 insertions(+), 1 deletion(-)
> 
> diff --git a/drivers/gpu/drm/msm/adreno/a6xx_hfi.c b/drivers/gpu/drm/msm/adreno/a6xx_hfi.c
> index cb8844ed46b29c4569d05eb7a24f7b27e173190f..995526620d678cd05020315f771213e4a6943bec 100644
> --- a/drivers/gpu/drm/msm/adreno/a6xx_hfi.c
> +++ b/drivers/gpu/drm/msm/adreno/a6xx_hfi.c
> @@ -6,6 +6,7 @@
>  #include <linux/list.h>
>  
>  #include <soc/qcom/cmd-db.h>
> +#include <soc/qcom/tcs.h>
>  
>  #include "a6xx_gmu.h"
>  #include "a6xx_gmu.xml.h"
> @@ -259,6 +260,48 @@ static int a6xx_hfi_send_perf_table(struct a6xx_gmu *gmu)
>  		NULL, 0);
>  }
>  
> +static void a6xx_generate_bw_table(const struct a6xx_info *info, struct a6xx_gmu *gmu,
> +				   struct a6xx_hfi_msg_bw_table *msg)
> +{
> +	unsigned int i, j;
> +
> +	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;
> +
> +	/* Compute the wait bitmask with each BCM having the commit bit */
> +	msg->ddr_wait_bitmask = 0;
> +	for (j = 0; j < msg->ddr_cmds_num; j++)
> +		if (msg->ddr_cmds_data[0][j] & BCM_TCS_CMD_COMMIT_MASK)
> +			msg->ddr_wait_bitmask |= BIT(j);
> +
> +	/*
> +	 * These are the CX (CNOC) votes - these are used by the GMU
> +	 * The 'CN0' BCM is used on all targets, and votes are basically
> +	 * 'off' and 'on' states with first bit to enable the path.
> +	 */
> +

/* The CNoC BCM only needs a simple off/on vote pair on all platforms */

> +	msg->cnoc_cmds_addrs[0] = cmd_db_read_addr("CN0");
> +	msg->cnoc_cmds_num = 1;
> +
> +	msg->cnoc_cmds_data[0][0] = BCM_TCS_CMD(true, false, 0, 0);
> +	msg->cnoc_cmds_data[1][0] = BCM_TCS_CMD(true, true, 0, BIT(0));

While it evaluates to the same, I think this is logically 1 (as in, one
unit of bus rate). The question of which bit that corresponds to is
handled by the macro.

Also, a7xx sets values in both x and y parts here, while a6xx only does
so in the y part.

> +
> +	/* Compute the wait bitmask with each BCM having the commit bit */
> +	msg->cnoc_wait_bitmask = 0;
> +	for (j = 0; j < msg->cnoc_cmds_num; j++)
> +		if (msg->cnoc_cmds_data[0][j] & BCM_TCS_CMD_COMMIT_MASK)
> +			msg->cnoc_wait_bitmask |= BIT(j);

This is a very fancy way to say msg->cnoc_wait_bitmask = BIT(0)

Konrad
Re: [PATCH v5 3/7] drm/msm: adreno: dynamically generate GMU bw table
Posted by Neil Armstrong 1 year ago 
On 12/12/2024 21:10, Konrad Dybcio wrote:
> On 11.12.2024 9:29 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 entries 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 | 48 ++++++++++++++++++++++++++++++++++-
>>   1 file changed, 47 insertions(+), 1 deletion(-)
>>
>> diff --git a/drivers/gpu/drm/msm/adreno/a6xx_hfi.c b/drivers/gpu/drm/msm/adreno/a6xx_hfi.c
>> index cb8844ed46b29c4569d05eb7a24f7b27e173190f..995526620d678cd05020315f771213e4a6943bec 100644
>> --- a/drivers/gpu/drm/msm/adreno/a6xx_hfi.c
>> +++ b/drivers/gpu/drm/msm/adreno/a6xx_hfi.c
>> @@ -6,6 +6,7 @@
>>   #include <linux/list.h>
>>   
>>   #include <soc/qcom/cmd-db.h>
>> +#include <soc/qcom/tcs.h>
>>   
>>   #include "a6xx_gmu.h"
>>   #include "a6xx_gmu.xml.h"
>> @@ -259,6 +260,48 @@ static int a6xx_hfi_send_perf_table(struct a6xx_gmu *gmu)
>>   		NULL, 0);
>>   }
>>   
>> +static void a6xx_generate_bw_table(const struct a6xx_info *info, struct a6xx_gmu *gmu,
>> +				   struct a6xx_hfi_msg_bw_table *msg)
>> +{
>> +	unsigned int i, j;
>> +
>> +	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;
>> +
>> +	/* Compute the wait bitmask with each BCM having the commit bit */
>> +	msg->ddr_wait_bitmask = 0;
>> +	for (j = 0; j < msg->ddr_cmds_num; j++)
>> +		if (msg->ddr_cmds_data[0][j] & BCM_TCS_CMD_COMMIT_MASK)
>> +			msg->ddr_wait_bitmask |= BIT(j);
>> +
>> +	/*
>> +	 * These are the CX (CNOC) votes - these are used by the GMU
>> +	 * The 'CN0' BCM is used on all targets, and votes are basically
>> +	 * 'off' and 'on' states with first bit to enable the path.
>> +	 */
>> +
> 
> /* The CNoC BCM only needs a simple off/on vote pair on all platforms */
> 
>> +	msg->cnoc_cmds_addrs[0] = cmd_db_read_addr("CN0");
>> +	msg->cnoc_cmds_num = 1;
>> +
>> +	msg->cnoc_cmds_data[0][0] = BCM_TCS_CMD(true, false, 0, 0);
>> +	msg->cnoc_cmds_data[1][0] = BCM_TCS_CMD(true, true, 0, BIT(0));
> 
> While it evaluates to the same, I think this is logically 1 (as in, one
> unit of bus rate). The question of which bit that corresponds to is
> handled by the macro.

"1" has not meaning, especially when we're supposed sending a bandwidth value, bit(0) means this bit has a special value

> 
> Also, a7xx sets values in both x and y parts here, while a6xx only does
> so in the y part.
> 
>> +
>> +	/* Compute the wait bitmask with each BCM having the commit bit */
>> +	msg->cnoc_wait_bitmask = 0;
>> +	for (j = 0; j < msg->cnoc_cmds_num; j++)
>> +		if (msg->cnoc_cmds_data[0][j] & BCM_TCS_CMD_COMMIT_MASK)
>> +			msg->cnoc_wait_bitmask |= BIT(j);
> 
> This is a very fancy way to say msg->cnoc_wait_bitmask = BIT(0)

Fancy but we know how it's calculated...

> 
> Konrad

Patchew 2.1-devel-b67e4c2

© 2016 - 2025 Red Hat, Inc.