Files
Sumeet Pawnikar 9229916d59 powercap: intel_rapl_tpmi: Handle PMU registration failure during probe
intel_rapl_tpmi_probe() invokes rapl_package_add_pmu() but ignores its
return value, so a PMU registration failure would leave the driver
reporting probe success despite the PMU being absent, with no log
trace.

Since PMU registration is an optional auxiliary feature for perf energy
counters, its failure should not break the primary powercap functionality.
Check the return value and log a warning to ensure graceful degradation.

Fixes: 963a9ad3c5 ("powercap: intel_rapl_tpmi: Enable PMU support")
Signed-off-by: Sumeet Pawnikar <sumeet4linux@gmail.com>
[ rjw: Changed the log level of the new message to "info" ]
Link: https://patch.msgid.link/20260723172321.5960-1-sumeet4linux@gmail.com
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2026-07-27 16:29:16 +02:00

459 lines
13 KiB
C

// SPDX-License-Identifier: GPL-2.0-only
/*
* intel_rapl_tpmi: Intel RAPL driver via TPMI interface
*
* Copyright (c) 2023, Intel Corporation.
* All Rights Reserved.
*
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/auxiliary_bus.h>
#include <linux/bits.h>
#include <linux/intel_rapl.h>
#include <linux/intel_tpmi.h>
#include <linux/intel_vsec.h>
#include <linux/io.h>
#include <linux/module.h>
#include <linux/slab.h>
#include <linux/units.h>
#define TPMI_RAPL_MAJOR_VERSION 0
#define TPMI_RAPL_MINOR_VERSION 1
/* 1 header + 10 registers + 5 reserved. 8 bytes for each. */
#define TPMI_RAPL_DOMAIN_SIZE 128
enum tpmi_rapl_domain_type {
TPMI_RAPL_DOMAIN_INVALID,
TPMI_RAPL_DOMAIN_SYSTEM,
TPMI_RAPL_DOMAIN_PACKAGE,
TPMI_RAPL_DOMAIN_RESERVED,
TPMI_RAPL_DOMAIN_MEMORY,
TPMI_RAPL_DOMAIN_MAX,
};
enum tpmi_rapl_register {
TPMI_RAPL_REG_HEADER,
TPMI_RAPL_REG_UNIT,
TPMI_RAPL_REG_PL1,
TPMI_RAPL_REG_PL2,
TPMI_RAPL_REG_PL3,
TPMI_RAPL_REG_PL4,
TPMI_RAPL_REG_RESERVED,
TPMI_RAPL_REG_ENERGY_STATUS,
TPMI_RAPL_REG_PERF_STATUS,
TPMI_RAPL_REG_POWER_INFO,
TPMI_RAPL_REG_DOMAIN_INFO,
TPMI_RAPL_REG_INTERRUPT,
TPMI_RAPL_REG_MAX = 15,
};
struct tpmi_rapl_package {
struct rapl_if_priv priv;
struct oobmsm_plat_info *tpmi_info;
struct rapl_package *rp;
void __iomem *base;
struct list_head node;
};
static LIST_HEAD(tpmi_rapl_packages);
static DEFINE_MUTEX(tpmi_rapl_lock);
static struct powercap_control_type *tpmi_control_type;
/* bitmasks for RAPL TPMI, used by primitive access functions */
#define TPMI_POWER_LIMIT_MASK GENMASK_ULL(17, 0)
#define TPMI_POWER_LIMIT_ENABLE BIT_ULL(62)
#define TPMI_POWER_HIGH_LOCK BIT_ULL(63)
#define TPMI_TIME_WINDOW_MASK GENMASK_ULL(24, 18)
#define TPMI_INFO_SPEC_MASK GENMASK_ULL(17, 0)
#define TPMI_INFO_MIN_MASK GENMASK_ULL(35, 18)
#define TPMI_INFO_MAX_MASK GENMASK_ULL(53, 36)
#define TPMI_INFO_MAX_TIME_WIN_MASK GENMASK_ULL(60, 54)
#define TPMI_ENERGY_STATUS_MASK GENMASK(31, 0)
#define TPMI_PERF_STATUS_THROTTLE_TIME_MASK GENMASK(31, 0)
/* RAPL primitives for TPMI I/F */
static struct rapl_primitive_info rpi_tpmi[NR_RAPL_PRIMITIVES] = {
/* name, mask, shift, msr index, unit divisor */
[POWER_LIMIT1] = PRIMITIVE_INFO_INIT(POWER_LIMIT1, TPMI_POWER_LIMIT_MASK, 0,
RAPL_DOMAIN_REG_LIMIT, POWER_UNIT, 0),
[POWER_LIMIT2] = PRIMITIVE_INFO_INIT(POWER_LIMIT2, TPMI_POWER_LIMIT_MASK, 0,
RAPL_DOMAIN_REG_PL2, POWER_UNIT, 0),
[POWER_LIMIT4] = PRIMITIVE_INFO_INIT(POWER_LIMIT4, TPMI_POWER_LIMIT_MASK, 0,
RAPL_DOMAIN_REG_PL4, POWER_UNIT, 0),
[ENERGY_COUNTER] = PRIMITIVE_INFO_INIT(ENERGY_COUNTER, TPMI_ENERGY_STATUS_MASK, 0,
RAPL_DOMAIN_REG_STATUS, ENERGY_UNIT, 0),
[PL1_LOCK] = PRIMITIVE_INFO_INIT(PL1_LOCK, TPMI_POWER_HIGH_LOCK, 63,
RAPL_DOMAIN_REG_LIMIT, ARBITRARY_UNIT, 0),
[PL2_LOCK] = PRIMITIVE_INFO_INIT(PL2_LOCK, TPMI_POWER_HIGH_LOCK, 63,
RAPL_DOMAIN_REG_PL2, ARBITRARY_UNIT, 0),
[PL4_LOCK] = PRIMITIVE_INFO_INIT(PL4_LOCK, TPMI_POWER_HIGH_LOCK, 63,
RAPL_DOMAIN_REG_PL4, ARBITRARY_UNIT, 0),
[PL1_ENABLE] = PRIMITIVE_INFO_INIT(PL1_ENABLE, TPMI_POWER_LIMIT_ENABLE, 62,
RAPL_DOMAIN_REG_LIMIT, ARBITRARY_UNIT, 0),
[PL2_ENABLE] = PRIMITIVE_INFO_INIT(PL2_ENABLE, TPMI_POWER_LIMIT_ENABLE, 62,
RAPL_DOMAIN_REG_PL2, ARBITRARY_UNIT, 0),
[PL4_ENABLE] = PRIMITIVE_INFO_INIT(PL4_ENABLE, TPMI_POWER_LIMIT_ENABLE, 62,
RAPL_DOMAIN_REG_PL4, ARBITRARY_UNIT, 0),
[TIME_WINDOW1] = PRIMITIVE_INFO_INIT(TIME_WINDOW1, TPMI_TIME_WINDOW_MASK, 18,
RAPL_DOMAIN_REG_LIMIT, TIME_UNIT, 0),
[TIME_WINDOW2] = PRIMITIVE_INFO_INIT(TIME_WINDOW2, TPMI_TIME_WINDOW_MASK, 18,
RAPL_DOMAIN_REG_PL2, TIME_UNIT, 0),
[THERMAL_SPEC_POWER] = PRIMITIVE_INFO_INIT(THERMAL_SPEC_POWER, TPMI_INFO_SPEC_MASK, 0,
RAPL_DOMAIN_REG_INFO, POWER_UNIT, 0),
[MAX_POWER] = PRIMITIVE_INFO_INIT(MAX_POWER, TPMI_INFO_MAX_MASK, 36,
RAPL_DOMAIN_REG_INFO, POWER_UNIT, 0),
[MIN_POWER] = PRIMITIVE_INFO_INIT(MIN_POWER, TPMI_INFO_MIN_MASK, 18,
RAPL_DOMAIN_REG_INFO, POWER_UNIT, 0),
[MAX_TIME_WINDOW] = PRIMITIVE_INFO_INIT(MAX_TIME_WINDOW, TPMI_INFO_MAX_TIME_WIN_MASK,
54, RAPL_DOMAIN_REG_INFO, TIME_UNIT, 0),
[THROTTLED_TIME] = PRIMITIVE_INFO_INIT(THROTTLED_TIME,
TPMI_PERF_STATUS_THROTTLE_TIME_MASK,
0, RAPL_DOMAIN_REG_PERF, TIME_UNIT, 0),
};
static int tpmi_rapl_read_raw(int id, struct reg_action *ra, bool atomic)
{
if (!ra->reg.mmio)
return -EINVAL;
ra->value = readq(ra->reg.mmio);
ra->value &= ra->mask;
return 0;
}
static int tpmi_rapl_write_raw(int id, struct reg_action *ra)
{
u64 val;
if (!ra->reg.mmio)
return -EINVAL;
val = readq(ra->reg.mmio);
val &= ~ra->mask;
val |= ra->value;
writeq(val, ra->reg.mmio);
return 0;
}
static struct tpmi_rapl_package *trp_alloc(int pkg_id)
{
struct tpmi_rapl_package *trp;
int ret;
mutex_lock(&tpmi_rapl_lock);
if (list_empty(&tpmi_rapl_packages)) {
tpmi_control_type = powercap_register_control_type(NULL, "intel-rapl", NULL);
if (IS_ERR(tpmi_control_type)) {
ret = PTR_ERR(tpmi_control_type);
goto err_unlock;
}
}
trp = kzalloc_obj(*trp);
if (!trp) {
ret = -ENOMEM;
goto err_del_powercap;
}
list_add(&trp->node, &tpmi_rapl_packages);
mutex_unlock(&tpmi_rapl_lock);
return trp;
err_del_powercap:
if (list_empty(&tpmi_rapl_packages))
powercap_unregister_control_type(tpmi_control_type);
err_unlock:
mutex_unlock(&tpmi_rapl_lock);
return ERR_PTR(ret);
}
static void trp_release(struct tpmi_rapl_package *trp)
{
mutex_lock(&tpmi_rapl_lock);
list_del(&trp->node);
if (list_empty(&tpmi_rapl_packages))
powercap_unregister_control_type(tpmi_control_type);
kfree(trp);
mutex_unlock(&tpmi_rapl_lock);
}
/*
* Bit 0 of TPMI_RAPL_REG_DOMAIN_INFO indicates if the current package is a domain
* root or not. Only domain root packages can enumerate System (Psys) Domain.
*/
#define TPMI_RAPL_DOMAIN_ROOT BIT(0)
static int parse_one_domain(struct tpmi_rapl_package *trp, u32 offset)
{
u8 tpmi_domain_version;
enum rapl_domain_type domain_type;
enum tpmi_rapl_domain_type tpmi_domain_type;
enum tpmi_rapl_register reg_index;
enum rapl_domain_reg_id reg_id;
int tpmi_domain_size, tpmi_domain_flags;
u64 tpmi_domain_header = readq(trp->base + offset);
u64 tpmi_domain_info;
/* Domain Parent bits are ignored for now */
tpmi_domain_version = tpmi_domain_header & 0xff;
tpmi_domain_type = tpmi_domain_header >> 8 & 0xff;
tpmi_domain_size = tpmi_domain_header >> 16 & 0xff;
tpmi_domain_flags = tpmi_domain_header >> 32 & 0xffff;
if (tpmi_domain_version == TPMI_VERSION_INVALID) {
pr_debug("Invalid version, other instances may be valid\n");
return -ENODEV;
}
if (TPMI_MAJOR_VERSION(tpmi_domain_version) != TPMI_RAPL_MAJOR_VERSION) {
pr_warn(FW_BUG "Unsupported major version:%ld\n",
TPMI_MAJOR_VERSION(tpmi_domain_version));
return -ENODEV;
}
if (TPMI_MINOR_VERSION(tpmi_domain_version) > TPMI_RAPL_MINOR_VERSION)
pr_info("Ignore: Unsupported minor version:%ld\n",
TPMI_MINOR_VERSION(tpmi_domain_version));
/* Domain size: in unit of 128 Bytes */
if (tpmi_domain_size != 1) {
pr_warn(FW_BUG "Invalid Domain size %d\n", tpmi_domain_size);
return -EINVAL;
}
/* Unit register and Energy Status register are mandatory for each domain */
if (!(tpmi_domain_flags & BIT(TPMI_RAPL_REG_UNIT)) ||
!(tpmi_domain_flags & BIT(TPMI_RAPL_REG_ENERGY_STATUS))) {
pr_warn(FW_BUG "Invalid Domain flag 0x%x\n", tpmi_domain_flags);
return -EINVAL;
}
switch (tpmi_domain_type) {
case TPMI_RAPL_DOMAIN_PACKAGE:
domain_type = RAPL_DOMAIN_PACKAGE;
break;
case TPMI_RAPL_DOMAIN_SYSTEM:
if (!(tpmi_domain_flags & BIT(TPMI_RAPL_REG_DOMAIN_INFO))) {
pr_warn(FW_BUG "System domain must support Domain Info register\n");
return -ENODEV;
}
tpmi_domain_info = readq(trp->base + offset + TPMI_RAPL_REG_DOMAIN_INFO * 8);
if (!(tpmi_domain_info & TPMI_RAPL_DOMAIN_ROOT))
return 0;
domain_type = RAPL_DOMAIN_PLATFORM;
break;
case TPMI_RAPL_DOMAIN_MEMORY:
domain_type = RAPL_DOMAIN_DRAM;
break;
default:
pr_warn(FW_BUG "Unsupported Domain type %d\n", tpmi_domain_type);
return -EINVAL;
}
if (trp->priv.regs[domain_type][RAPL_DOMAIN_REG_UNIT].mmio) {
pr_warn(FW_BUG "Duplicate Domain type %d\n", tpmi_domain_type);
return -EINVAL;
}
reg_index = TPMI_RAPL_REG_HEADER;
while (++reg_index != TPMI_RAPL_REG_MAX) {
if (!(tpmi_domain_flags & BIT(reg_index)))
continue;
switch (reg_index) {
case TPMI_RAPL_REG_UNIT:
reg_id = RAPL_DOMAIN_REG_UNIT;
break;
case TPMI_RAPL_REG_PL1:
reg_id = RAPL_DOMAIN_REG_LIMIT;
trp->priv.limits[domain_type] |= BIT(POWER_LIMIT1);
break;
case TPMI_RAPL_REG_PL2:
reg_id = RAPL_DOMAIN_REG_PL2;
trp->priv.limits[domain_type] |= BIT(POWER_LIMIT2);
break;
case TPMI_RAPL_REG_PL4:
reg_id = RAPL_DOMAIN_REG_PL4;
trp->priv.limits[domain_type] |= BIT(POWER_LIMIT4);
break;
case TPMI_RAPL_REG_ENERGY_STATUS:
reg_id = RAPL_DOMAIN_REG_STATUS;
break;
case TPMI_RAPL_REG_PERF_STATUS:
reg_id = RAPL_DOMAIN_REG_PERF;
break;
case TPMI_RAPL_REG_POWER_INFO:
reg_id = RAPL_DOMAIN_REG_INFO;
break;
default:
continue;
}
trp->priv.regs[domain_type][reg_id].mmio = trp->base + offset + reg_index * 8;
}
return 0;
}
/* TPMI Unit register has different layout */
#define TPMI_ENERGY_UNIT_SCALE 1000
#define TPMI_POWER_UNIT_OFFSET 0x00
#define TPMI_POWER_UNIT_MASK GENMASK(3, 0)
#define TPMI_ENERGY_UNIT_OFFSET 0x06
#define TPMI_ENERGY_UNIT_MASK GENMASK_ULL(10, 6)
#define TPMI_TIME_UNIT_OFFSET 0x0C
#define TPMI_TIME_UNIT_MASK GENMASK_ULL(15, 12)
static int rapl_check_unit_tpmi(struct rapl_domain *rd)
{
struct reg_action ra;
u32 value;
ra.reg = rd->regs[RAPL_DOMAIN_REG_UNIT];
ra.mask = ~0;
if (tpmi_rapl_read_raw(rd->rp->id, &ra, false)) {
pr_err("Failed to read power unit REG 0x%llx on %s:%s, exit.\n",
ra.reg.val, rd->rp->name, rd->name);
return -ENODEV;
}
value = (ra.value & TPMI_ENERGY_UNIT_MASK) >> TPMI_ENERGY_UNIT_OFFSET;
rd->energy_unit = (TPMI_ENERGY_UNIT_SCALE * MICROJOULE_PER_JOULE) >> value;
value = (ra.value & TPMI_POWER_UNIT_MASK) >> TPMI_POWER_UNIT_OFFSET;
rd->power_unit = MICROWATT_PER_WATT >> value;
value = (ra.value & TPMI_TIME_UNIT_MASK) >> TPMI_TIME_UNIT_OFFSET;
rd->time_unit = USEC_PER_SEC >> value;
pr_debug("Core CPU %s:%s energy=%dpJ, time=%dus, power=%duW\n",
rd->rp->name, rd->name, rd->energy_unit, rd->time_unit, rd->power_unit);
return 0;
}
static const struct rapl_defaults defaults_tpmi = {
.check_unit = rapl_check_unit_tpmi,
/* Reuse existing logic, ignore the PL_CLAMP failures and enable all Power Limits */
.set_floor_freq = rapl_default_set_floor_freq,
.compute_time_window = rapl_default_compute_time_window,
};
static int intel_rapl_tpmi_probe(struct auxiliary_device *auxdev,
const struct auxiliary_device_id *id)
{
struct tpmi_rapl_package *trp;
struct oobmsm_plat_info *info;
struct resource *res;
u32 offset;
int ret;
info = tpmi_get_platform_data(auxdev);
if (!info)
return -ENODEV;
trp = trp_alloc(info->package_id);
if (IS_ERR(trp))
return PTR_ERR(trp);
if (tpmi_get_resource_count(auxdev) > 1) {
dev_err(&auxdev->dev, "does not support multiple resources\n");
ret = -EINVAL;
goto err;
}
res = tpmi_get_resource_at_index(auxdev, 0);
if (!res) {
dev_err(&auxdev->dev, "can't fetch device resource info\n");
ret = -EIO;
goto err;
}
trp->base = devm_ioremap_resource(&auxdev->dev, res);
if (IS_ERR(trp->base)) {
ret = PTR_ERR(trp->base);
goto err;
}
for (offset = 0; offset < resource_size(res); offset += TPMI_RAPL_DOMAIN_SIZE) {
ret = parse_one_domain(trp, offset);
if (ret)
goto err;
}
trp->tpmi_info = info;
trp->priv.type = RAPL_IF_TPMI;
trp->priv.read_raw = tpmi_rapl_read_raw;
trp->priv.write_raw = tpmi_rapl_write_raw;
trp->priv.control_type = tpmi_control_type;
trp->priv.defaults = &defaults_tpmi;
trp->priv.rpi = rpi_tpmi;
/* RAPL TPMI I/F is per physical package */
trp->rp = rapl_find_package_domain(info->package_id, &trp->priv, false);
if (trp->rp) {
dev_err(&auxdev->dev, "Domain for Package%d already exists\n", info->package_id);
ret = -EEXIST;
goto err;
}
trp->rp = rapl_add_package(info->package_id, &trp->priv, false);
if (IS_ERR(trp->rp)) {
dev_err(&auxdev->dev, "Failed to add RAPL Domain for Package%d, %ld\n",
info->package_id, PTR_ERR(trp->rp));
ret = PTR_ERR(trp->rp);
goto err;
}
ret = rapl_package_add_pmu(trp->rp);
if (ret)
dev_info(&auxdev->dev, "Failed to add RAPL PMU for Package%d, %d\n",
info->package_id, ret);
auxiliary_set_drvdata(auxdev, trp);
return 0;
err:
trp_release(trp);
return ret;
}
static void intel_rapl_tpmi_remove(struct auxiliary_device *auxdev)
{
struct tpmi_rapl_package *trp = auxiliary_get_drvdata(auxdev);
rapl_package_remove_pmu(trp->rp);
rapl_remove_package(trp->rp);
trp_release(trp);
}
static const struct auxiliary_device_id intel_rapl_tpmi_ids[] = {
{.name = "intel_vsec.tpmi-rapl" },
{ }
};
MODULE_DEVICE_TABLE(auxiliary, intel_rapl_tpmi_ids);
static struct auxiliary_driver intel_rapl_tpmi_driver = {
.probe = intel_rapl_tpmi_probe,
.remove = intel_rapl_tpmi_remove,
.id_table = intel_rapl_tpmi_ids,
};
module_auxiliary_driver(intel_rapl_tpmi_driver)
MODULE_IMPORT_NS("INTEL_RAPL");
MODULE_IMPORT_NS("INTEL_TPMI");
MODULE_DESCRIPTION("Intel RAPL TPMI Driver");
MODULE_LICENSE("GPL");