On Wed, 28 Aug 2024, Tero Kristo wrote:
> Add efficiency latency control support to the TPMI uncore driver. This
> defines two new threshold values for controlling uncore frequency, low
> threshold and high threshold. When CPU utilization is below low threshold,
> the user configurable floor latency control frequency can be used by the
> system. When CPU utilization is above high threshold, the uncore frequency
> is increased in 100MHz steps until power limit is reached.
>
> Signed-off-by: Tero Kristo <tero.kristo@xxxxxxxxxxxxxxx>
> ---
> v2:
> * Converted a long sequence of if (...)'s to a switch
>
> .../uncore-frequency-common.h | 4 +
> .../uncore-frequency/uncore-frequency-tpmi.c | 158 +++++++++++++++++-
> 2 files changed, 160 insertions(+), 2 deletions(-)
>
> diff --git a/drivers/platform/x86/intel/uncore-frequency/uncore-frequency-common.h b/drivers/platform/x86/intel/uncore-frequency/uncore-frequency-common.h
> index 4c245b945e4e..b5c7311bfa05 100644
> --- a/drivers/platform/x86/intel/uncore-frequency/uncore-frequency-common.h
> +++ b/drivers/platform/x86/intel/uncore-frequency/uncore-frequency-common.h
> @@ -70,6 +70,10 @@ enum uncore_index {
> UNCORE_INDEX_MIN_FREQ,
> UNCORE_INDEX_MAX_FREQ,
> UNCORE_INDEX_CURRENT_FREQ,
> + UNCORE_INDEX_EFF_LAT_CTRL_LOW_THRESHOLD,
> + UNCORE_INDEX_EFF_LAT_CTRL_HIGH_THRESHOLD,
> + UNCORE_INDEX_EFF_LAT_CTRL_HIGH_THRESHOLD_ENABLE,
> + UNCORE_INDEX_EFF_LAT_CTRL_FREQ,
> };
>
> int uncore_freq_common_init(int (*read)(struct uncore_data *data, unsigned int *value,
> diff --git a/drivers/platform/x86/intel/uncore-frequency/uncore-frequency-tpmi.c b/drivers/platform/x86/intel/uncore-frequency/uncore-frequency-tpmi.c
> index 9fa3037c03d1..50b28b4b1fc0 100644
> --- a/drivers/platform/x86/intel/uncore-frequency/uncore-frequency-tpmi.c
> +++ b/drivers/platform/x86/intel/uncore-frequency/uncore-frequency-tpmi.c
> @@ -30,6 +30,7 @@
>
> #define UNCORE_MAJOR_VERSION 0
> #define UNCORE_MINOR_VERSION 2
> +#define UNCORE_ELC_SUPPORTED_VERSION 2
> #define UNCORE_HEADER_INDEX 0
> #define UNCORE_FABRIC_CLUSTER_OFFSET 8
>
> @@ -46,6 +47,7 @@ struct tpmi_uncore_struct;
> /* Information for each cluster */
> struct tpmi_uncore_cluster_info {
> bool root_domain;
> + bool elc_supported;
> u8 __iomem *cluster_base;
> struct uncore_data uncore_data;
> struct tpmi_uncore_struct *uncore_root;
> @@ -75,6 +77,10 @@ struct tpmi_uncore_struct {
> /* Bit definitions for CONTROL register */
> #define UNCORE_MAX_RATIO_MASK GENMASK_ULL(14, 8)
> #define UNCORE_MIN_RATIO_MASK GENMASK_ULL(21, 15)
> +#define UNCORE_EFF_LAT_CTRL_RATIO_MASK GENMASK_ULL(28, 22)
> +#define UNCORE_EFF_LAT_CTRL_LOW_THRESHOLD_MASK GENMASK_ULL(38, 32)
> +#define UNCORE_EFF_LAT_CTRL_HIGH_THRESHOLD_ENABLE BIT(39)
> +#define UNCORE_EFF_LAT_CTRL_HIGH_THRESHOLD_MASK GENMASK_ULL(46, 40)
>
> /* Helper function to read MMIO offset for max/min control frequency */
> static void read_control_freq(struct tpmi_uncore_cluster_info *cluster_info,
> @@ -89,6 +95,48 @@ static void read_control_freq(struct tpmi_uncore_cluster_info *cluster_info,
> *value = FIELD_GET(UNCORE_MIN_RATIO_MASK, control) * UNCORE_FREQ_KHZ_MULTIPLIER;
> }
>
> +/* Helper function to read efficiency latency control values over MMIO */
> +static int read_eff_lat_ctrl(struct uncore_data *data, unsigned int *val, enum uncore_index index)
> +{
> + struct tpmi_uncore_cluster_info *cluster_info;
> + u64 ctrl;
> +
> + cluster_info = container_of(data, struct tpmi_uncore_cluster_info, uncore_data);
> + if (cluster_info->root_domain)
> + return -ENODATA;
> +
> + if (!cluster_info->elc_supported)
> + return -EOPNOTSUPP;
> +
> + ctrl = readq(cluster_info->cluster_base + UNCORE_CONTROL_INDEX);
> +
> + switch (index) {
> + case UNCORE_INDEX_EFF_LAT_CTRL_LOW_THRESHOLD:
> + *val = FIELD_GET(UNCORE_EFF_LAT_CTRL_LOW_THRESHOLD_MASK, ctrl);
> + *val *= 100;
> + *val = DIV_ROUND_UP(*val, FIELD_MAX(UNCORE_EFF_LAT_CTRL_LOW_THRESHOLD_MASK));
> + break;
> +
> + case UNCORE_INDEX_EFF_LAT_CTRL_HIGH_THRESHOLD:
> + *val = FIELD_GET(UNCORE_EFF_LAT_CTRL_HIGH_THRESHOLD_MASK, ctrl);
> + *val *= 100;
> + *val = DIV_ROUND_UP(*val, FIELD_MAX(UNCORE_EFF_LAT_CTRL_HIGH_THRESHOLD_MASK));
I wonder if DIV_ROUND_CLOSEST() would be more appropriate in these two
cases, rounding up isn't well justified as I think this wants to round it
back to the original number to deal with the minor divergences due to
precision loss during conversions?
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@xxxxxxxxxxxxxxx>
--
i.
> + break;
> +
> + case UNCORE_INDEX_EFF_LAT_CTRL_HIGH_THRESHOLD_ENABLE:
> + *val = FIELD_GET(UNCORE_EFF_LAT_CTRL_HIGH_THRESHOLD_ENABLE, ctrl);
> + break;
> + case UNCORE_INDEX_EFF_LAT_CTRL_FREQ:
> + *val = FIELD_GET(UNCORE_EFF_LAT_CTRL_RATIO_MASK, ctrl) * UNCORE_FREQ_KHZ_MULTIPLIER;
> + break;
> +
> + default:
> + return -EOPNOTSUPP;
> + }
> +
> + return 0;
> +}
> +
> #define UNCORE_MAX_RATIO FIELD_MAX(UNCORE_MAX_RATIO_MASK)
>
> /* Helper for sysfs read for max/min frequencies. Called under mutex locks */
> @@ -137,6 +185,82 @@ static int uncore_read_control_freq(struct uncore_data *data, unsigned int *valu
> return 0;
> }
>
> +/* Helper function for writing efficiency latency control values over MMIO */
> +static int write_eff_lat_ctrl(struct uncore_data *data, unsigned int val, enum uncore_index index)
> +{
> + struct tpmi_uncore_cluster_info *cluster_info;
> + u64 control;
> +
> + cluster_info = container_of(data, struct tpmi_uncore_cluster_info, uncore_data);
> +
> + if (cluster_info->root_domain)
> + return -ENODATA;
> +
> + if (!cluster_info->elc_supported)
> + return -EOPNOTSUPP;
> +
> + switch (index) {
> + case UNCORE_INDEX_EFF_LAT_CTRL_LOW_THRESHOLD:
> + if (val > 100)
> + return -EINVAL;
> + break;
> +
> + case UNCORE_INDEX_EFF_LAT_CTRL_HIGH_THRESHOLD:
> + if (val > 100)
> + return -EINVAL;
> + break;
> +
> + case UNCORE_INDEX_EFF_LAT_CTRL_HIGH_THRESHOLD_ENABLE:
> + if (val > 1)
> + return -EINVAL;
> + break;
> +
> + case UNCORE_INDEX_EFF_LAT_CTRL_FREQ:
> + val /= UNCORE_FREQ_KHZ_MULTIPLIER;
> + if (val > FIELD_MAX(UNCORE_EFF_LAT_CTRL_RATIO_MASK))
> + return -EINVAL;
> + break;
> +
> + default:
> + return -EOPNOTSUPP;
> + }
> +
> + control = readq(cluster_info->cluster_base + UNCORE_CONTROL_INDEX);
> +
> + switch (index) {
> + case UNCORE_INDEX_EFF_LAT_CTRL_LOW_THRESHOLD:
> + val *= FIELD_MAX(UNCORE_EFF_LAT_CTRL_LOW_THRESHOLD_MASK);
> + val /= 100;
> + control &= ~UNCORE_EFF_LAT_CTRL_LOW_THRESHOLD_MASK;
> + control |= FIELD_PREP(UNCORE_EFF_LAT_CTRL_LOW_THRESHOLD_MASK, val);
> + break;
> +
> + case UNCORE_INDEX_EFF_LAT_CTRL_HIGH_THRESHOLD:
> + val *= FIELD_MAX(UNCORE_EFF_LAT_CTRL_HIGH_THRESHOLD_MASK);
> + val /= 100;
> + control &= ~UNCORE_EFF_LAT_CTRL_HIGH_THRESHOLD_MASK;
> + control |= FIELD_PREP(UNCORE_EFF_LAT_CTRL_HIGH_THRESHOLD_MASK, val);
> + break;
> +
> + case UNCORE_INDEX_EFF_LAT_CTRL_HIGH_THRESHOLD_ENABLE:
> + control &= ~UNCORE_EFF_LAT_CTRL_HIGH_THRESHOLD_ENABLE;
> + control |= FIELD_PREP(UNCORE_EFF_LAT_CTRL_HIGH_THRESHOLD_ENABLE, val);
> + break;
> +
> + case UNCORE_INDEX_EFF_LAT_CTRL_FREQ:
> + control &= ~UNCORE_EFF_LAT_CTRL_RATIO_MASK;
> + control |= FIELD_PREP(UNCORE_EFF_LAT_CTRL_RATIO_MASK, val);
> + break;
> +
> + default:
> + break;
> + }
> +
> + writeq(control, cluster_info->cluster_base + UNCORE_CONTROL_INDEX);
> +
> + return 0;
> +}
> +
> /* Helper function to write MMIO offset for max/min control frequency */
> static void write_control_freq(struct tpmi_uncore_cluster_info *cluster_info, unsigned int input,
> unsigned int index)
> @@ -156,7 +280,7 @@ static void write_control_freq(struct tpmi_uncore_cluster_info *cluster_info, un
> writeq(control, (cluster_info->cluster_base + UNCORE_CONTROL_INDEX));
> }
>
> -/* Callback for sysfs write for max/min frequencies. Called under mutex locks */
> +/* Helper for sysfs write for max/min frequencies. Called under mutex locks */
> static int uncore_write_control_freq(struct uncore_data *data, unsigned int input,
> enum uncore_index index)
> {
> @@ -234,6 +358,33 @@ static int uncore_read(struct uncore_data *data, unsigned int *value, enum uncor
> case UNCORE_INDEX_CURRENT_FREQ:
> return uncore_read_freq(data, value);
>
> + case UNCORE_INDEX_EFF_LAT_CTRL_LOW_THRESHOLD:
> + case UNCORE_INDEX_EFF_LAT_CTRL_HIGH_THRESHOLD:
> + case UNCORE_INDEX_EFF_LAT_CTRL_HIGH_THRESHOLD_ENABLE:
> + case UNCORE_INDEX_EFF_LAT_CTRL_FREQ:
> + return read_eff_lat_ctrl(data, value, index);
> +
> + default:
> + break;
> + }
> +
> + return -EOPNOTSUPP;
> +}
> +
> +/* Callback for sysfs write for TPMI uncore data. Called under mutex locks. */
> +static int uncore_write(struct uncore_data *data, unsigned int value, enum uncore_index index)
> +{
> + switch (index) {
> + case UNCORE_INDEX_EFF_LAT_CTRL_LOW_THRESHOLD:
> + case UNCORE_INDEX_EFF_LAT_CTRL_HIGH_THRESHOLD:
> + case UNCORE_INDEX_EFF_LAT_CTRL_HIGH_THRESHOLD_ENABLE:
> + case UNCORE_INDEX_EFF_LAT_CTRL_FREQ:
> + return write_eff_lat_ctrl(data, value, index);
> +
> + case UNCORE_INDEX_MIN_FREQ:
> + case UNCORE_INDEX_MAX_FREQ:
> + return uncore_write_control_freq(data, value, index);
> +
> default:
> break;
> }
> @@ -291,7 +442,7 @@ static int uncore_probe(struct auxiliary_device *auxdev, const struct auxiliary_
> return -EINVAL;
>
> /* Register callbacks to uncore core */
> - ret = uncore_freq_common_init(uncore_read, uncore_write_control_freq);
> + ret = uncore_freq_common_init(uncore_read, uncore_write);
> if (ret)
> return ret;
>
> @@ -409,6 +560,9 @@ static int uncore_probe(struct auxiliary_device *auxdev, const struct auxiliary_
>
> cluster_info->uncore_root = tpmi_uncore;
>
> + if (TPMI_MINOR_VERSION(pd_info->ufs_header_ver) >= UNCORE_ELC_SUPPORTED_VERSION)
> + cluster_info->elc_supported = true;
> +
> ret = uncore_freq_add_entry(&cluster_info->uncore_data, 0);
> if (ret) {
> cluster_info->cluster_base = NULL;
>
