diff options
Diffstat (limited to 'drivers/powercap')
| -rw-r--r-- | drivers/powercap/Kconfig | 11 | ||||
| -rw-r--r-- | drivers/powercap/Makefile | 3 | ||||
| -rw-r--r-- | drivers/powercap/intel_rapl_common.c (renamed from drivers/powercap/intel_rapl.c) | 836 | ||||
| -rw-r--r-- | drivers/powercap/intel_rapl_msr.c | 183 |
4 files changed, 510 insertions, 523 deletions
diff --git a/drivers/powercap/Kconfig b/drivers/powercap/Kconfig index 42d3798c88f0..dc1c1381d7fa 100644 --- a/drivers/powercap/Kconfig +++ b/drivers/powercap/Kconfig @@ -16,14 +16,17 @@ menuconfig POWERCAP if POWERCAP # Client driver configurations go here. +config INTEL_RAPL_CORE + tristate + config INTEL_RAPL - tristate "Intel RAPL Support" + tristate "Intel RAPL Support via MSR Interface" depends on X86 && IOSF_MBI - default n + select INTEL_RAPL_CORE ---help--- This enables support for the Intel Running Average Power Limit (RAPL) - technology which allows power limits to be enforced and monitored on - modern Intel processors (Sandy Bridge and later). + technology via MSR interface, which allows power limits to be enforced + and monitored on modern Intel processors (Sandy Bridge and later). In RAPL, the platform level settings are divided into domains for fine grained control. These domains include processor package, DRAM diff --git a/drivers/powercap/Makefile b/drivers/powercap/Makefile index 81c8ccaba6e7..7255c94ec61c 100644 --- a/drivers/powercap/Makefile +++ b/drivers/powercap/Makefile @@ -1,4 +1,5 @@ # SPDX-License-Identifier: GPL-2.0-only obj-$(CONFIG_POWERCAP) += powercap_sys.o -obj-$(CONFIG_INTEL_RAPL) += intel_rapl.o +obj-$(CONFIG_INTEL_RAPL_CORE) += intel_rapl_common.o +obj-$(CONFIG_INTEL_RAPL) += intel_rapl_msr.o obj-$(CONFIG_IDLE_INJECT) += idle_inject.o diff --git a/drivers/powercap/intel_rapl.c b/drivers/powercap/intel_rapl_common.c index f888117b0efc..9fd6dd342169 100644 --- a/drivers/powercap/intel_rapl.c +++ b/drivers/powercap/intel_rapl_common.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0-only /* - * Intel Running Average Power Limit (RAPL) Driver - * Copyright (c) 2013, Intel Corporation. + * Common code for Intel Running Average Power Limit (RAPL) support. + * Copyright (c) 2019, Intel Corporation. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt @@ -18,9 +18,11 @@ #include <linux/cpu.h> #include <linux/powercap.h> #include <linux/suspend.h> -#include <asm/iosf_mbi.h> +#include <linux/intel_rapl.h> +#include <linux/processor.h> +#include <linux/platform_device.h> -#include <asm/processor.h> +#include <asm/iosf_mbi.h> #include <asm/cpu_device_id.h> #include <asm/intel-family.h> @@ -37,8 +39,8 @@ #define POWER_LIMIT2_MASK (0x7FFFULL<<32) #define POWER_LIMIT2_ENABLE BIT_ULL(47) #define POWER_LIMIT2_CLAMP BIT_ULL(48) -#define POWER_PACKAGE_LOCK BIT_ULL(63) -#define POWER_PP_LOCK BIT(31) +#define POWER_HIGH_LOCK BIT_ULL(63) +#define POWER_LOW_LOCK BIT(31) #define TIME_WINDOW1_MASK (0x7FULL<<17) #define TIME_WINDOW2_MASK (0x7FULL<<49) @@ -61,139 +63,38 @@ #define PP_POLICY_MASK 0x1F /* Non HW constants */ -#define RAPL_PRIMITIVE_DERIVED BIT(1) /* not from raw data */ +#define RAPL_PRIMITIVE_DERIVED BIT(1) /* not from raw data */ #define RAPL_PRIMITIVE_DUMMY BIT(2) #define TIME_WINDOW_MAX_MSEC 40000 #define TIME_WINDOW_MIN_MSEC 250 -#define ENERGY_UNIT_SCALE 1000 /* scale from driver unit to powercap unit */ +#define ENERGY_UNIT_SCALE 1000 /* scale from driver unit to powercap unit */ enum unit_type { - ARBITRARY_UNIT, /* no translation */ + ARBITRARY_UNIT, /* no translation */ POWER_UNIT, ENERGY_UNIT, TIME_UNIT, }; -enum rapl_domain_type { - RAPL_DOMAIN_PACKAGE, /* entire package/socket */ - RAPL_DOMAIN_PP0, /* core power plane */ - RAPL_DOMAIN_PP1, /* graphics uncore */ - RAPL_DOMAIN_DRAM,/* DRAM control_type */ - RAPL_DOMAIN_PLATFORM, /* PSys control_type */ - RAPL_DOMAIN_MAX, -}; - -enum rapl_domain_msr_id { - RAPL_DOMAIN_MSR_LIMIT, - RAPL_DOMAIN_MSR_STATUS, - RAPL_DOMAIN_MSR_PERF, - RAPL_DOMAIN_MSR_POLICY, - RAPL_DOMAIN_MSR_INFO, - RAPL_DOMAIN_MSR_MAX, -}; - /* per domain data, some are optional */ -enum rapl_primitives { - ENERGY_COUNTER, - POWER_LIMIT1, - POWER_LIMIT2, - FW_LOCK, - - PL1_ENABLE, /* power limit 1, aka long term */ - PL1_CLAMP, /* allow frequency to go below OS request */ - PL2_ENABLE, /* power limit 2, aka short term, instantaneous */ - PL2_CLAMP, - - TIME_WINDOW1, /* long term */ - TIME_WINDOW2, /* short term */ - THERMAL_SPEC_POWER, - MAX_POWER, - - MIN_POWER, - MAX_TIME_WINDOW, - THROTTLED_TIME, - PRIORITY_LEVEL, - - /* below are not raw primitive data */ - AVERAGE_POWER, - NR_RAPL_PRIMITIVES, -}; - #define NR_RAW_PRIMITIVES (NR_RAPL_PRIMITIVES - 2) -/* Can be expanded to include events, etc.*/ -struct rapl_domain_data { - u64 primitives[NR_RAPL_PRIMITIVES]; - unsigned long timestamp; -}; - -struct msrl_action { - u32 msr_no; - u64 clear_mask; - u64 set_mask; - int err; -}; - #define DOMAIN_STATE_INACTIVE BIT(0) #define DOMAIN_STATE_POWER_LIMIT_SET BIT(1) #define DOMAIN_STATE_BIOS_LOCKED BIT(2) -#define NR_POWER_LIMITS (2) -struct rapl_power_limit { - struct powercap_zone_constraint *constraint; - int prim_id; /* primitive ID used to enable */ - struct rapl_domain *domain; - const char *name; - u64 last_power_limit; -}; - static const char pl1_name[] = "long_term"; static const char pl2_name[] = "short_term"; -struct rapl_package; -struct rapl_domain { - const char *name; - enum rapl_domain_type id; - int msrs[RAPL_DOMAIN_MSR_MAX]; - struct powercap_zone power_zone; - struct rapl_domain_data rdd; - struct rapl_power_limit rpl[NR_POWER_LIMITS]; - u64 attr_map; /* track capabilities */ - unsigned int state; - unsigned int domain_energy_unit; - struct rapl_package *rp; -}; #define power_zone_to_rapl_domain(_zone) \ container_of(_zone, struct rapl_domain, power_zone) - -/* Each physical package contains multiple domains, these are the common - * data across RAPL domains within a package. - */ -struct rapl_package { - unsigned int id; /* physical package/socket id */ - unsigned int nr_domains; - unsigned long domain_map; /* bit map of active domains */ - unsigned int power_unit; - unsigned int energy_unit; - unsigned int time_unit; - struct rapl_domain *domains; /* array of domains, sized at runtime */ - struct powercap_zone *power_zone; /* keep track of parent zone */ - unsigned long power_limit_irq; /* keep track of package power limit - * notify interrupt enable status. - */ - struct list_head plist; - int lead_cpu; /* one active cpu per package for access */ - /* Track active cpus */ - struct cpumask cpumask; -}; - struct rapl_defaults { u8 floor_freq_reg_addr; int (*check_unit)(struct rapl_package *rp, int cpu); void (*set_floor_freq)(struct rapl_domain *rd, bool mode); u64 (*compute_time_window)(struct rapl_package *rp, u64 val, - bool to_raw); + bool to_raw); unsigned int dram_domain_energy_unit; }; static struct rapl_defaults *rapl_defaults; @@ -212,7 +113,7 @@ struct rapl_primitive_info { const char *name; u64 mask; int shift; - enum rapl_domain_msr_id id; + enum rapl_domain_reg_id id; enum unit_type unit; u32 flag; }; @@ -228,19 +129,18 @@ struct rapl_primitive_info { static void rapl_init_domains(struct rapl_package *rp); static int rapl_read_data_raw(struct rapl_domain *rd, - enum rapl_primitives prim, - bool xlate, u64 *data); + enum rapl_primitives prim, + bool xlate, u64 *data); static int rapl_write_data_raw(struct rapl_domain *rd, - enum rapl_primitives prim, - unsigned long long value); + enum rapl_primitives prim, + unsigned long long value); static u64 rapl_unit_xlate(struct rapl_domain *rd, - enum unit_type type, u64 value, - int to_raw); + enum unit_type type, u64 value, int to_raw); static void package_power_limit_irq_save(struct rapl_package *rp); -static LIST_HEAD(rapl_packages); /* guarded by CPU hotplug lock */ +static LIST_HEAD(rapl_packages); /* guarded by CPU hotplug lock */ -static const char * const rapl_domain_names[] = { +static const char *const rapl_domain_names[] = { "package", "core", "uncore", @@ -248,23 +148,8 @@ static const char * const rapl_domain_names[] = { "psys", }; -static struct powercap_control_type *control_type; /* PowerCap Controller */ -static struct rapl_domain *platform_rapl_domain; /* Platform (PSys) domain */ - -/* caller to ensure CPU hotplug lock is held */ -static struct rapl_package *find_package_by_id(int id) -{ - struct rapl_package *rp; - - list_for_each_entry(rp, &rapl_packages, plist) { - if (rp->id == id) - return rp; - } - - return NULL; -} - -static int get_energy_counter(struct powercap_zone *power_zone, u64 *energy_raw) +static int get_energy_counter(struct powercap_zone *power_zone, + u64 *energy_raw) { struct rapl_domain *rd; u64 energy_now; @@ -363,50 +248,49 @@ static int get_domain_enable(struct powercap_zone *power_zone, bool *mode) static const struct powercap_zone_ops zone_ops[] = { /* RAPL_DOMAIN_PACKAGE */ { - .get_energy_uj = get_energy_counter, - .get_max_energy_range_uj = get_max_energy_counter, - .release = release_zone, - .set_enable = set_domain_enable, - .get_enable = get_domain_enable, - }, + .get_energy_uj = get_energy_counter, + .get_max_energy_range_uj = get_max_energy_counter, + .release = release_zone, + .set_enable = set_domain_enable, + .get_enable = get_domain_enable, + }, /* RAPL_DOMAIN_PP0 */ { - .get_energy_uj = get_energy_counter, - .get_max_energy_range_uj = get_max_energy_counter, - .release = release_zone, - .set_enable = set_domain_enable, - .get_enable = get_domain_enable, - }, + .get_energy_uj = get_energy_counter, + .get_max_energy_range_uj = get_max_energy_counter, + .release = release_zone, + .set_enable = set_domain_enable, + .get_enable = get_domain_enable, + }, /* RAPL_DOMAIN_PP1 */ { - .get_energy_uj = get_energy_counter, - .get_max_energy_range_uj = get_max_energy_counter, - .release = release_zone, - .set_enable = set_domain_enable, - .get_enable = get_domain_enable, - }, + .get_energy_uj = get_energy_counter, + .get_max_energy_range_uj = get_max_energy_counter, + .release = release_zone, + .set_enable = set_domain_enable, + .get_enable = get_domain_enable, + }, /* RAPL_DOMAIN_DRAM */ { - .get_energy_uj = get_energy_counter, - .get_max_energy_range_uj = get_max_energy_counter, - .release = release_zone, - .set_enable = set_domain_enable, - .get_enable = get_domain_enable, - }, + .get_energy_uj = get_energy_counter, + .get_max_energy_range_uj = get_max_energy_counter, + .release = release_zone, + .set_enable = set_domain_enable, + .get_enable = get_domain_enable, + }, /* RAPL_DOMAIN_PLATFORM */ { - .get_energy_uj = get_energy_counter, - .get_max_energy_range_uj = get_max_energy_counter, - .release = release_zone, - .set_enable = set_domain_enable, - .get_enable = get_domain_enable, - }, + .get_energy_uj = get_energy_counter, + .get_max_energy_range_uj = get_max_energy_counter, + .release = release_zone, + .set_enable = set_domain_enable, + .get_enable = get_domain_enable, + }, }; - /* * Constraint index used by powercap can be different than power limit (PL) - * index in that some PLs maybe missing due to non-existant MSRs. So we + * index in that some PLs maybe missing due to non-existent MSRs. So we * need to convert here by finding the valid PLs only (name populated). */ static int contraint_to_pl(struct rapl_domain *rd, int cid) @@ -425,7 +309,7 @@ static int contraint_to_pl(struct rapl_domain *rd, int cid) } static int set_power_limit(struct powercap_zone *power_zone, int cid, - u64 power_limit) + u64 power_limit) { struct rapl_domain *rd; struct rapl_package *rp; @@ -443,8 +327,8 @@ static int set_power_limit(struct powercap_zone *power_zone, int cid, rp = rd->rp; if (rd->state & DOMAIN_STATE_BIOS_LOCKED) { - dev_warn(&power_zone->dev, "%s locked by BIOS, monitoring only\n", - rd->name); + dev_warn(&power_zone->dev, + "%s locked by BIOS, monitoring only\n", rd->name); ret = -EACCES; goto set_exit; } @@ -467,7 +351,7 @@ set_exit: } static int get_current_power_limit(struct powercap_zone *power_zone, int cid, - u64 *data) + u64 *data) { struct rapl_domain *rd; u64 val; @@ -506,7 +390,7 @@ get_exit: } static int set_time_window(struct powercap_zone *power_zone, int cid, - u64 window) + u64 window) { struct rapl_domain *rd; int ret = 0; @@ -536,7 +420,8 @@ set_time_exit: return ret; } -static int get_time_window(struct powercap_zone *power_zone, int cid, u64 *data) +static int get_time_window(struct powercap_zone *power_zone, int cid, + u64 *data) { struct rapl_domain *rd; u64 val; @@ -571,7 +456,8 @@ get_time_exit: return ret; } -static const char *get_constraint_name(struct powercap_zone *power_zone, int cid) +static const char *get_constraint_name(struct powercap_zone *power_zone, + int cid) { struct rapl_domain *rd; int id; @@ -584,9 +470,7 @@ static const char *get_constraint_name(struct powercap_zone *power_zone, int cid return NULL; } - -static int get_max_power(struct powercap_zone *power_zone, int id, - u64 *data) +static int get_max_power(struct powercap_zone *power_zone, int id, u64 *data) { struct rapl_domain *rd; u64 val; @@ -628,73 +512,43 @@ static const struct powercap_zone_constraint_ops constraint_ops = { /* called after domain detection and package level data are set */ static void rapl_init_domains(struct rapl_package *rp) { - int i; + enum rapl_domain_type i; + enum rapl_domain_reg_id j; struct rapl_domain *rd = rp->domains; for (i = 0; i < RAPL_DOMAIN_MAX; i++) { unsigned int mask = rp->domain_map & (1 << i); - switch (mask) { - case BIT(RAPL_DOMAIN_PACKAGE): - rd->name = rapl_domain_names[RAPL_DOMAIN_PACKAGE]; - rd->id = RAPL_DOMAIN_PACKAGE; - rd->msrs[0] = MSR_PKG_POWER_LIMIT; - rd->msrs[1] = MSR_PKG_ENERGY_STATUS; - rd->msrs[2] = MSR_PKG_PERF_STATUS; - rd->msrs[3] = 0; - rd->msrs[4] = MSR_PKG_POWER_INFO; - rd->rpl[0].prim_id = PL1_ENABLE; - rd->rpl[0].name = pl1_name; + + if (!mask) + continue; + + rd->rp = rp; + rd->name = rapl_domain_names[i]; + rd->id = i; + rd->rpl[0].prim_id = PL1_ENABLE; + rd->rpl[0].name = pl1_name; + /* some domain may support two power limits */ + if (rp->priv->limits[i] == 2) { rd->rpl[1].prim_id = PL2_ENABLE; rd->rpl[1].name = pl2_name; - break; - case BIT(RAPL_DOMAIN_PP0): - rd->name = rapl_domain_names[RAPL_DOMAIN_PP0]; - rd->id = RAPL_DOMAIN_PP0; - rd->msrs[0] = MSR_PP0_POWER_LIMIT; - rd->msrs[1] = MSR_PP0_ENERGY_STATUS; - rd->msrs[2] = 0; - rd->msrs[3] = MSR_PP0_POLICY; - rd->msrs[4] = 0; - rd->rpl[0].prim_id = PL1_ENABLE; - rd->rpl[0].name = pl1_name; - break; - case BIT(RAPL_DOMAIN_PP1): - rd->name = rapl_domain_names[RAPL_DOMAIN_PP1]; - rd->id = RAPL_DOMAIN_PP1; - rd->msrs[0] = MSR_PP1_POWER_LIMIT; - rd->msrs[1] = MSR_PP1_ENERGY_STATUS; - rd->msrs[2] = 0; - rd->msrs[3] = MSR_PP1_POLICY; - rd->msrs[4] = 0; - rd->rpl[0].prim_id = PL1_ENABLE; - rd->rpl[0].name = pl1_name; - break; - case BIT(RAPL_DOMAIN_DRAM): - rd->name = rapl_domain_names[RAPL_DOMAIN_DRAM]; - rd->id = RAPL_DOMAIN_DRAM; - rd->msrs[0] = MSR_DRAM_POWER_LIMIT; - rd->msrs[1] = MSR_DRAM_ENERGY_STATUS; - rd->msrs[2] = MSR_DRAM_PERF_STATUS; - rd->msrs[3] = 0; - rd->msrs[4] = MSR_DRAM_POWER_INFO; - rd->rpl[0].prim_id = PL1_ENABLE; - rd->rpl[0].name = pl1_name; + } + + for (j = 0; j < RAPL_DOMAIN_REG_MAX; j++) + rd->regs[j] = rp->priv->regs[i][j]; + + if (i == RAPL_DOMAIN_DRAM) { rd->domain_energy_unit = - rapl_defaults->dram_domain_energy_unit; + rapl_defaults->dram_domain_energy_unit; if (rd->domain_energy_unit) pr_info("DRAM domain energy unit %dpj\n", rd->domain_energy_unit); - break; - } - if (mask) { - rd->rp = rp; - rd++; } + rd++; } } static u64 rapl_unit_xlate(struct rapl_domain *rd, enum unit_type type, - u64 value, int to_raw) + u64 value, int to_raw) { u64 units = 1; struct rapl_package *rp = rd->rp; @@ -731,40 +585,40 @@ static u64 rapl_unit_xlate(struct rapl_domain *rd, enum unit_type type, static struct rapl_primitive_info rpi[] = { /* name, mask, shift, msr index, unit divisor */ PRIMITIVE_INFO_INIT(ENERGY_COUNTER, ENERGY_STATUS_MASK, 0, - RAPL_DOMAIN_MSR_STATUS, ENERGY_UNIT, 0), + RAPL_DOMAIN_REG_STATUS, ENERGY_UNIT, 0), PRIMITIVE_INFO_INIT(POWER_LIMIT1, POWER_LIMIT1_MASK, 0, - RAPL_DOMAIN_MSR_LIMIT, POWER_UNIT, 0), + RAPL_DOMAIN_REG_LIMIT, POWER_UNIT, 0), PRIMITIVE_INFO_INIT(POWER_LIMIT2, POWER_LIMIT2_MASK, 32, - RAPL_DOMAIN_MSR_LIMIT, POWER_UNIT, 0), - PRIMITIVE_INFO_INIT(FW_LOCK, POWER_PP_LOCK, 31, - RAPL_DOMAIN_MSR_LIMIT, ARBITRARY_UNIT, 0), + RAPL_DOMAIN_REG_LIMIT, POWER_UNIT, 0), + PRIMITIVE_INFO_INIT(FW_LOCK, POWER_LOW_LOCK, 31, + RAPL_DOMAIN_REG_LIMIT, ARBITRARY_UNIT, 0), PRIMITIVE_INFO_INIT(PL1_ENABLE, POWER_LIMIT1_ENABLE, 15, - RAPL_DOMAIN_MSR_LIMIT, ARBITRARY_UNIT, 0), + RAPL_DOMAIN_REG_LIMIT, ARBITRARY_UNIT, 0), PRIMITIVE_INFO_INIT(PL1_CLAMP, POWER_LIMIT1_CLAMP, 16, - RAPL_DOMAIN_MSR_LIMIT, ARBITRARY_UNIT, 0), + RAPL_DOMAIN_REG_LIMIT, ARBITRARY_UNIT, 0), PRIMITIVE_INFO_INIT(PL2_ENABLE, POWER_LIMIT2_ENABLE, 47, - RAPL_DOMAIN_MSR_LIMIT, ARBITRARY_UNIT, 0), + RAPL_DOMAIN_REG_LIMIT, ARBITRARY_UNIT, 0), PRIMITIVE_INFO_INIT(PL2_CLAMP, POWER_LIMIT2_CLAMP, 48, - RAPL_DOMAIN_MSR_LIMIT, ARBITRARY_UNIT, 0), + RAPL_DOMAIN_REG_LIMIT, ARBITRARY_UNIT, 0), PRIMITIVE_INFO_INIT(TIME_WINDOW1, TIME_WINDOW1_MASK, 17, - RAPL_DOMAIN_MSR_LIMIT, TIME_UNIT, 0), + RAPL_DOMAIN_REG_LIMIT, TIME_UNIT, 0), PRIMITIVE_INFO_INIT(TIME_WINDOW2, TIME_WINDOW2_MASK, 49, - RAPL_DOMAIN_MSR_LIMIT, TIME_UNIT, 0), + RAPL_DOMAIN_REG_LIMIT, TIME_UNIT, 0), PRIMITIVE_INFO_INIT(THERMAL_SPEC_POWER, POWER_INFO_THERMAL_SPEC_MASK, - 0, RAPL_DOMAIN_MSR_INFO, POWER_UNIT, 0), + 0, RAPL_DOMAIN_REG_INFO, POWER_UNIT, 0), PRIMITIVE_INFO_INIT(MAX_POWER, POWER_INFO_MAX_MASK, 32, - RAPL_DOMAIN_MSR_INFO, POWER_UNIT, 0), + RAPL_DOMAIN_REG_INFO, POWER_UNIT, 0), PRIMITIVE_INFO_INIT(MIN_POWER, POWER_INFO_MIN_MASK, 16, - RAPL_DOMAIN_MSR_INFO, POWER_UNIT, 0), + RAPL_DOMAIN_REG_INFO, POWER_UNIT, 0), PRIMITIVE_INFO_INIT(MAX_TIME_WINDOW, POWER_INFO_MAX_TIME_WIN_MASK, 48, - RAPL_DOMAIN_MSR_INFO, TIME_UNIT, 0), + RAPL_DOMAIN_REG_INFO, TIME_UNIT, 0), PRIMITIVE_INFO_INIT(THROTTLED_TIME, PERF_STATUS_THROTTLE_TIME_MASK, 0, - RAPL_DOMAIN_MSR_PERF, TIME_UNIT, 0), + RAPL_DOMAIN_REG_PERF, TIME_UNIT, 0), PRIMITIVE_INFO_INIT(PRIORITY_LEVEL, PP_POLICY_MASK, 0, - RAPL_DOMAIN_MSR_POLICY, ARBITRARY_UNIT, 0), + RAPL_DOMAIN_REG_POLICY, ARBITRARY_UNIT, 0), /* non-hardware */ PRIMITIVE_INFO_INIT(AVERAGE_POWER, 0, 0, 0, POWER_UNIT, - RAPL_PRIMITIVE_DERIVED), + RAPL_PRIMITIVE_DERIVED), {NULL, 0, 0, 0}, }; @@ -782,26 +636,25 @@ static struct rapl_primitive_info rpi[] = { * 63-------------------------- 31--------------------------- 0 */ static int rapl_read_data_raw(struct rapl_domain *rd, - enum rapl_primitives prim, - bool xlate, u64 *data) + enum rapl_primitives prim, bool xlate, u64 *data) { - u64 value, final; - u32 msr; + u64 value; struct rapl_primitive_info *rp = &rpi[prim]; + struct reg_action ra; int cpu; if (!rp->name || rp->flag & RAPL_PRIMITIVE_DUMMY) return -EINVAL; - msr = rd->msrs[rp->id]; - if (!msr) + ra.reg = rd->regs[rp->id]; + if (!ra.reg) return -EINVAL; cpu = rd->rp->lead_cpu; - /* special-case package domain, which uses a different bit*/ - if (prim == FW_LOCK && rd->id == RAPL_DOMAIN_PACKAGE) { - rp->mask = POWER_PACKAGE_LOCK; + /* domain with 2 limits has different bit */ + if (prim == FW_LOCK && rd->rp->priv->limits[rd->id] == 2) { + rp->mask = POWER_HIGH_LOCK; rp->shift = 63; } /* non-hardware data are collected by the polling thread */ @@ -810,56 +663,32 @@ static int rapl_read_data_raw(struct rapl_domain *rd, return 0; } - if (rdmsrl_safe_on_cpu(cpu, msr, &value)) { - pr_debug("failed to read msr 0x%x on cpu %d\n", msr, cpu); + ra.mask = rp->mask; + + if (rd->rp->priv->read_raw(cpu, &ra)) { + pr_debug("failed to read reg 0x%llx on cpu %d\n", ra.reg, cpu); return -EIO; } - final = value & rp->mask; - final = final >> rp->shift; + value = ra.value >> rp->shift; + if (xlate) - *data = rapl_unit_xlate(rd, rp->unit, final, 0); + *data = rapl_unit_xlate(rd, rp->unit, value, 0); else - *data = final; + *data = value; return 0; } - -static int msrl_update_safe(u32 msr_no, u64 clear_mask, u64 set_mask) -{ - int err; - u64 val; - - err = rdmsrl_safe(msr_no, &val); - if (err) - goto out; - - val &= ~clear_mask; - val |= set_mask; - - err = wrmsrl_safe(msr_no, val); - -out: - return err; -} - -static void msrl_update_func(void *info) -{ - struct msrl_action *ma = info; - - ma->err = msrl_update_safe(ma->msr_no, ma->clear_mask, ma->set_mask); -} - /* Similar use of primitive info in the read counterpart */ static int rapl_write_data_raw(struct rapl_domain *rd, - enum rapl_primitives prim, - unsigned long long value) + enum rapl_primitives prim, + unsigned long long value) { struct rapl_primitive_info *rp = &rpi[prim]; int cpu; u64 bits; - struct msrl_action ma; + struct reg_action ra; int ret; cpu = rd->rp->lead_cpu; @@ -867,17 +696,13 @@ static int rapl_write_data_raw(struct rapl_domain *rd, bits <<= rp->shift; bits &= rp->mask; - memset(&ma, 0, sizeof(ma)); + memset(&ra, 0, sizeof(ra)); - ma.msr_no = rd->msrs[rp->id]; - ma.clear_mask = rp->mask; - ma.set_mask = bits; + ra.reg = rd->regs[rp->id]; + ra.mask = rp->mask; + ra.value = bits; - ret = smp_call_function_single(cpu, msrl_update_func, &ma, 1); - if (ret) - WARN_ON_ONCE(ret); - else - ret = ma.err; + ret = rd->rp->priv->write_raw(cpu, &ra); return ret; } @@ -895,51 +720,56 @@ static int rapl_write_data_raw(struct rapl_domain *rd, */ static int rapl_check_unit_core(struct rapl_package *rp, int cpu) { - u64 msr_val; + struct reg_action ra; u32 value; - if (rdmsrl_safe_on_cpu(cpu, MSR_RAPL_POWER_UNIT, &msr_val)) { - pr_err("Failed to read power unit MSR 0x%x on CPU %d, exit.\n", - MSR_RAPL_POWER_UNIT, cpu); + ra.reg = rp->priv->reg_unit; + ra.mask = ~0; + if (rp->priv->read_raw(cpu, &ra)) { + pr_err("Failed to read power unit REG 0x%llx on CPU %d, exit.\n", + rp->priv->reg_unit, cpu); return -ENODEV; } - value = (msr_val & ENERGY_UNIT_MASK) >> ENERGY_UNIT_OFFSET; + value = (ra.value & ENERGY_UNIT_MASK) >> ENERGY_UNIT_OFFSET; rp->energy_unit = ENERGY_UNIT_SCALE * 1000000 / (1 << value); - value = (msr_val & POWER_UNIT_MASK) >> POWER_UNIT_OFFSET; + value = (ra.value & POWER_UNIT_MASK) >> POWER_UNIT_OFFSET; rp->power_unit = 1000000 / (1 << value); - value = (msr_val & TIME_UNIT_MASK) >> TIME_UNIT_OFFSET; + value = (ra.value & TIME_UNIT_MASK) >> TIME_UNIT_OFFSET; rp->time_unit = 1000000 / (1 << value); - pr_debug("Core CPU package %d energy=%dpJ, time=%dus, power=%duW\n", - rp->id, rp->energy_unit, rp->time_unit, rp->power_unit); + pr_debug("Core CPU %s energy=%dpJ, time=%dus, power=%duW\n", + rp->name, rp->energy_unit, rp->time_unit, rp->power_unit); return 0; } static int rapl_check_unit_atom(struct rapl_package *rp, int cpu) { - u64 msr_val; + struct reg_action ra; u32 value; - if (rdmsrl_safe_on_cpu(cpu, MSR_RAPL_POWER_UNIT, &msr_val)) { - pr_err("Failed to read power unit MSR 0x%x on CPU %d, exit.\n", - MSR_RAPL_POWER_UNIT, cpu); + ra.reg = rp->priv->reg_unit; + ra.mask = ~0; + if (rp->priv->read_raw(cpu, &ra)) { + pr_err("Failed to read power unit REG 0x%llx on CPU %d, exit.\n", + rp->priv->reg_unit, cpu); return -ENODEV; } - value = (msr_val & ENERGY_UNIT_MASK) >> ENERGY_UNIT_OFFSET; + + value = (ra.value & ENERGY_UNIT_MASK) >> ENERGY_UNIT_OFFSET; rp->energy_unit = ENERGY_UNIT_SCALE * 1 << value; - value = (msr_val & POWER_UNIT_MASK) >> POWER_UNIT_OFFSET; + value = (ra.value & POWER_UNIT_MASK) >> POWER_UNIT_OFFSET; rp->power_unit = (1 << value) * 1000; - value = (msr_val & TIME_UNIT_MASK) >> TIME_UNIT_OFFSET; + value = (ra.value & TIME_UNIT_MASK) >> TIME_UNIT_OFFSET; rp->time_unit = 1000000 / (1 << value); - pr_debug("Atom package %d energy=%dpJ, time=%dus, power=%duW\n", - rp->id, rp->energy_unit, rp->time_unit, rp->power_unit); + pr_debug("Atom %s energy=%dpJ, time=%dus, power=%duW\n", + rp->name, rp->energy_unit, rp->time_unit, rp->power_unit); return 0; } @@ -959,7 +789,6 @@ static void power_limit_irq_save_cpu(void *info) wrmsr_safe(MSR_IA32_PACKAGE_THERM_INTERRUPT, l, h); } - /* REVISIT: * When package power limit is set artificially low by RAPL, LVT * thermal interrupt for package power limit should be ignored @@ -1043,9 +872,9 @@ static void set_floor_freq_atom(struct rapl_domain *rd, bool enable) } static u64 rapl_compute_time_window_core(struct rapl_package *rp, u64 value, - bool to_raw) + bool to_raw) { - u64 f, y; /* fraction and exp. used for time unit */ + u64 f, y; /* fraction and exp. used for time unit */ /* * Special processing based on 2^Y*(1+F/4), refer @@ -1065,7 +894,7 @@ static u64 rapl_compute_time_window_core(struct rapl_package *rp, u64 value, } static u64 rapl_compute_time_window_atom(struct rapl_package *rp, u64 value, - bool to_raw) + bool to_raw) { /* * Atom time unit encoding is straight forward val * time_unit, @@ -1073,8 +902,8 @@ static u64 rapl_compute_time_window_atom(struct rapl_package *rp, u64 value, */ if (!to_raw) return (value) ? value *= rp->time_unit : rp->time_unit; - else - value = div64_u64(value, rp->time_unit); + + value = div64_u64(value, rp->time_unit); return value; } @@ -1122,43 +951,48 @@ static const struct rapl_defaults rapl_defaults_cht = { }; static const struct x86_cpu_id rapl_ids[] __initconst = { - INTEL_CPU_FAM6(SANDYBRIDGE, rapl_defaults_core), - INTEL_CPU_FAM6(SANDYBRIDGE_X, rapl_defaults_core), - - INTEL_CPU_FAM6(IVYBRIDGE, rapl_defaults_core), - INTEL_CPU_FAM6(IVYBRIDGE_X, rapl_defaults_core), - - INTEL_CPU_FAM6(HASWELL_CORE, rapl_defaults_core), - INTEL_CPU_FAM6(HASWELL_ULT, rapl_defaults_core), - INTEL_CPU_FAM6(HASWELL_GT3E, rapl_defaults_core), - INTEL_CPU_FAM6(HASWELL_X, rapl_defaults_hsw_server), - - INTEL_CPU_FAM6(BROADWELL_CORE, rapl_defaults_core), - INTEL_CPU_FAM6(BROADWELL_GT3E, rapl_defaults_core), - INTEL_CPU_FAM6(BROADWELL_XEON_D, rapl_defaults_core), - INTEL_CPU_FAM6(BROADWELL_X, rapl_defaults_hsw_server), - - INTEL_CPU_FAM6(SKYLAKE_DESKTOP, rapl_defaults_core), - INTEL_CPU_FAM6(SKYLAKE_MOBILE, rapl_defaults_core), - INTEL_CPU_FAM6(SKYLAKE_X, rapl_defaults_hsw_server), - INTEL_CPU_FAM6(KABYLAKE_MOBILE, rapl_defaults_core), - INTEL_CPU_FAM6(KABYLAKE_DESKTOP, rapl_defaults_core), - INTEL_CPU_FAM6(CANNONLAKE_MOBILE, rapl_defaults_core), - INTEL_CPU_FAM6(ICELAKE_MOBILE, rapl_defaults_core), - - INTEL_CPU_FAM6(ATOM_SILVERMONT, rapl_defaults_byt), - INTEL_CPU_FAM6(ATOM_AIRMONT, rapl_defaults_cht), - INTEL_CPU_FAM6(ATOM_SILVERMONT_MID, rapl_defaults_tng), - INTEL_CPU_FAM6(ATOM_AIRMONT_MID, rapl_defaults_ann), - INTEL_CPU_FAM6(ATOM_GOLDMONT, rapl_defaults_core), - INTEL_CPU_FAM6(ATOM_GOLDMONT_PLUS, rapl_defaults_core), - INTEL_CPU_FAM6(ATOM_GOLDMONT_X, rapl_defaults_core), - INTEL_CPU_FAM6(ATOM_TREMONT_X, rapl_defaults_core), - - INTEL_CPU_FAM6(XEON_PHI_KNL, rapl_defaults_hsw_server), - INTEL_CPU_FAM6(XEON_PHI_KNM, rapl_defaults_hsw_server), + INTEL_CPU_FAM6(SANDYBRIDGE, rapl_defaults_core), + INTEL_CPU_FAM6(SANDYBRIDGE_X, rapl_defaults_core), + + INTEL_CPU_FAM6(IVYBRIDGE, rapl_defaults_core), + INTEL_CPU_FAM6(IVYBRIDGE_X, rapl_defaults_core), + + INTEL_CPU_FAM6(HASWELL_CORE, rapl_defaults_core), + INTEL_CPU_FAM6(HASWELL_ULT, rapl_defaults_core), + INTEL_CPU_FAM6(HASWELL_GT3E, rapl_defaults_core), + INTEL_CPU_FAM6(HASWELL_X, rapl_defaults_hsw_server), + + INTEL_CPU_FAM6(BROADWELL_CORE, rapl_defaults_core), + INTEL_CPU_FAM6(BROADWELL_GT3E, rapl_defaults_core), + INTEL_CPU_FAM6(BROADWELL_XEON_D, rapl_defaults_core), + INTEL_CPU_FAM6(BROADWELL_X, rapl_defaults_hsw_server), + + INTEL_CPU_FAM6(SKYLAKE_DESKTOP, rapl_defaults_core), + INTEL_CPU_FAM6(SKYLAKE_MOBILE, rapl_defaults_core), + INTEL_CPU_FAM6(SKYLAKE_X, rapl_defaults_hsw_server), + INTEL_CPU_FAM6(KABYLAKE_MOBILE, rapl_defaults_core), + INTEL_CPU_FAM6(KABYLAKE_DESKTOP, rapl_defaults_core), + INTEL_CPU_FAM6(CANNONLAKE_MOBILE, rapl_defaults_core), + INTEL_CPU_FAM6(ICELAKE_MOBILE, rapl_defaults_core), + INTEL_CPU_FAM6(ICELAKE_DESKTOP, rapl_defaults_core), + INTEL_CPU_FAM6(ICELAKE_NNPI, rapl_defaults_core), + INTEL_CPU_FAM6(ICELAKE_X, rapl_defaults_hsw_server), + INTEL_CPU_FAM6(ICELAKE_XEON_D, rapl_defaults_hsw_server), + + INTEL_CPU_FAM6(ATOM_SILVERMONT, rapl_defaults_byt), + INTEL_CPU_FAM6(ATOM_AIRMONT, rapl_defaults_cht), + INTEL_CPU_FAM6(ATOM_SILVERMONT_MID, rapl_defaults_tng), + INTEL_CPU_FAM6(ATOM_AIRMONT_MID, rapl_defaults_ann), + INTEL_CPU_FAM6(ATOM_GOLDMONT, rapl_defaults_core), + INTEL_CPU_FAM6(ATOM_GOLDMONT_PLUS, rapl_defaults_core), + INTEL_CPU_FAM6(ATOM_GOLDMONT_X, rapl_defaults_core), + INTEL_CPU_FAM6(ATOM_TREMONT_X, rapl_defaults_core), + + INTEL_CPU_FAM6(XEON_PHI_KNL, rapl_defaults_hsw_server), + INTEL_CPU_FAM6(XEON_PHI_KNM, rapl_defaults_hsw_server), {} }; + MODULE_DEVICE_TABLE(x86cpu, rapl_ids); /* Read once for all raw primitive data for domains */ @@ -1168,56 +1002,39 @@ static void rapl_update_domain_data(struct rapl_package *rp) u64 val; for (dmn = 0; dmn < rp->nr_domains; dmn++) { - pr_debug("update package %d domain %s data\n", rp->id, + pr_debug("update %s domain %s data\n", rp->name, rp->domains[dmn].name); /* exclude non-raw primitives */ for (prim = 0; prim < NR_RAW_PRIMITIVES; prim++) { if (!rapl_read_data_raw(&rp->domains[dmn], prim, rpi[prim].unit, &val)) - rp->domains[dmn].rdd.primitives[prim] = val; + rp->domains[dmn].rdd.primitives[prim] = val; } } } -static void rapl_unregister_powercap(void) -{ - if (platform_rapl_domain) { - powercap_unregister_zone(control_type, - &platform_rapl_domain->power_zone); - kfree(platform_rapl_domain); - } - powercap_unregister_control_type(control_type); -} - static int rapl_package_register_powercap(struct rapl_package *rp) { struct rapl_domain *rd; - char dev_name[17]; /* max domain name = 7 + 1 + 8 for int + 1 for null*/ struct powercap_zone *power_zone = NULL; int nr_pl, ret; /* Update the domain data of the new package */ rapl_update_domain_data(rp); - /* first we register package domain as the parent zone*/ + /* first we register package domain as the parent zone */ for (rd = rp->domains; rd < rp->domains + rp->nr_domains; rd++) { if (rd->id == RAPL_DOMAIN_PACKAGE) { nr_pl = find_nr_power_limit(rd); - pr_debug("register socket %d package domain %s\n", - rp->id, rd->name); - memset(dev_name, 0, sizeof(dev_name)); - snprintf(dev_name, sizeof(dev_name), "%s-%d", - rd->name, rp->id); + pr_debug("register package domain %s\n", rp->name); power_zone = powercap_register_zone(&rd->power_zone, - control_type, - dev_name, NULL, - &zone_ops[rd->id], - nr_pl, - &constraint_ops); + rp->priv->control_type, rp->name, + NULL, &zone_ops[rd->id], nr_pl, + &constraint_ops); if (IS_ERR(power_zone)) { - pr_debug("failed to register package, %d\n", - rp->id); + pr_debug("failed to register power zone %s\n", + rp->name); return PTR_ERR(power_zone); } /* track parent zone in per package/socket data */ @@ -1230,21 +1047,21 @@ static int rapl_package_register_powercap(struct rapl_package *rp) pr_err("no package domain found, unknown topology!\n"); return -ENODEV; } - /* now register domains as children of the socket/package*/ + /* now register domains as children of the socket/package */ for (rd = rp->domains; rd < rp->domains + rp->nr_domains; rd++) { if (rd->id == RAPL_DOMAIN_PACKAGE) continue; /* number of power limits per domain varies */ nr_pl = find_nr_power_limit(rd); power_zone = powercap_register_zone(&rd->power_zone, - control_type, rd->name, - rp->power_zone, - &zone_ops[rd->id], nr_pl, - &constraint_ops); + rp->priv->control_type, + rd->name, rp->power_zone, + &zone_ops[rd->id], nr_pl, + &constraint_ops); if (IS_ERR(power_zone)) { - pr_debug("failed to register power_zone, %d:%s:%s\n", - rp->id, rd->name, dev_name); + pr_debug("failed to register power_zone, %s:%s\n", + rp->name, rd->name); ret = PTR_ERR(power_zone); goto err_cleanup; } @@ -1257,23 +1074,31 @@ err_cleanup: * failed after the first domain setup. */ while (--rd >= rp->domains) { - pr_debug("unregister package %d domain %s\n", rp->id, rd->name); - powercap_unregister_zone(control_type, &rd->power_zone); + pr_debug("unregister %s domain %s\n", rp->name, rd->name); + powercap_unregister_zone(rp->priv->control_type, + &rd->power_zone); } return ret; } -static int __init rapl_register_psys(void) +int rapl_add_platform_domain(struct rapl_if_priv *priv) { struct rapl_domain *rd; struct powercap_zone *power_zone; - u64 val; + struct reg_action ra; + int ret; - if (rdmsrl_safe_on_cpu(0, MSR_PLATFORM_ENERGY_STATUS, &val) || !val) + ra.reg = priv->regs[RAPL_DOMAIN_PLATFORM][RAPL_DOMAIN_REG_STATUS]; + ra.mask = ~0; + ret = priv->read_raw(0, &ra); + if (ret || !ra.value) return -ENODEV; - if (rdmsrl_safe_on_cpu(0, MSR_PLATFORM_POWER_LIMIT, &val) || !val) + ra.reg = priv->regs[RAPL_DOMAIN_PLATFORM][RAPL_DOMAIN_REG_LIMIT]; + ra.mask = ~0; + ret = priv->read_raw(0, &ra); + if (ret || !ra.value) return -ENODEV; rd = kzalloc(sizeof(*rd), GFP_KERNEL); @@ -1282,15 +1107,17 @@ static int __init rapl_register_psys(void) rd->name = rapl_domain_names[RAPL_DOMAIN_PLATFORM]; rd->id = RAPL_DOMAIN_PLATFORM; - rd->msrs[0] = MSR_PLATFORM_POWER_LIMIT; - rd->msrs[1] = MSR_PLATFORM_ENERGY_STATUS; + rd->regs[RAPL_DOMAIN_REG_LIMIT] = + priv->regs[RAPL_DOMAIN_PLATFORM][RAPL_DOMAIN_REG_LIMIT]; + rd->regs[RAPL_DOMAIN_REG_STATUS] = + priv->regs[RAPL_DOMAIN_PLATFORM][RAPL_DOMAIN_REG_STATUS]; rd->rpl[0].prim_id = PL1_ENABLE; rd->rpl[0].name = pl1_name; rd->rpl[1].prim_id = PL2_ENABLE; rd->rpl[1].name = pl2_name; - rd->rp = find_package_by_id(0); + rd->rp = rapl_find_package_domain(0, priv); - power_zone = powercap_register_zone(&rd->power_zone, control_type, + power_zone = powercap_register_zone(&rd->power_zone, priv->control_type, "psys", NULL, &zone_ops[RAPL_DOMAIN_PLATFORM], 2, &constraint_ops); @@ -1300,38 +1127,32 @@ static int __init rapl_register_psys(void) return PTR_ERR(power_zone); } - platform_rapl_domain = rd; + priv->platform_rapl_domain = rd; return 0; } +EXPORT_SYMBOL_GPL(rapl_add_platform_domain); -static int __init rapl_register_powercap(void) +void rapl_remove_platform_domain(struct rapl_if_priv *priv) { - control_type = powercap_register_control_type(NULL, "intel-rapl", NULL); - if (IS_ERR(control_type)) { - pr_debug("failed to register powercap control_type.\n"); - return PTR_ERR(control_type); + if (priv->platform_rapl_domain) { + powercap_unregister_zone(priv->control_type, + &priv->platform_rapl_domain->power_zone); + kfree(priv->platform_rapl_domain); } - return 0; } +EXPORT_SYMBOL_GPL(rapl_remove_platform_domain); -static int rapl_check_domain(int cpu, int domain) +static int rapl_check_domain(int cpu, int domain, struct rapl_package *rp) { - unsigned msr; - u64 val = 0; + struct reg_action ra; switch (domain) { case RAPL_DOMAIN_PACKAGE: - msr = MSR_PKG_ENERGY_STATUS; - break; case RAPL_DOMAIN_PP0: - msr = MSR_PP0_ENERGY_STATUS; - break; case RAPL_DOMAIN_PP1: - msr = MSR_PP1_ENERGY_STATUS; - break; case RAPL_DOMAIN_DRAM: - msr = MSR_DRAM_ENERGY_STATUS; + ra.reg = rp->priv->regs[domain][RAPL_DOMAIN_REG_STATUS]; break; case RAPL_DOMAIN_PLATFORM: /* PSYS(PLATFORM) is not a CPU domain, so avoid printng error */ @@ -1343,19 +1164,20 @@ static int rapl_check_domain(int cpu, int domain) /* make sure domain counters are available and contains non-zero * values, otherwise skip it. */ - if (rdmsrl_safe_on_cpu(cpu, msr, &val) || !val) + + ra.mask = ~0; + if (rp->priv->read_raw(cpu, &ra) || !ra.value) return -ENODEV; return 0; } - /* * Check if power limits are available. Two cases when they are not available: * 1. Locked by BIOS, in this case we still provide read-only access so that * users can see what limit is set by the BIOS. * 2. Some CPUs make some domains monitoring only which means PLx MSRs may not - * exist at all. In this case, we do not show the contraints in powercap. + * exist at all. In this case, we do not show the constraints in powercap. * * Called after domains are detected and initialized. */ @@ -1367,14 +1189,15 @@ static void rapl_detect_powerlimit(struct rapl_domain *rd) /* check if the domain is locked by BIOS, ignore if MSR doesn't exist */ if (!rapl_read_data_raw(rd, FW_LOCK, false, &val64)) { if (val64) { - pr_info("RAPL package %d domain %s locked by BIOS\n", - rd->rp->id, rd->name); + pr_info("RAPL %s domain %s locked by BIOS\n", + rd->rp->name, rd->name); rd->state |= DOMAIN_STATE_BIOS_LOCKED; } } - /* check if power limit MSRs exists, otherwise domain is monitoring only */ + /* check if power limit MSR exists, otherwise domain is monitoring only */ for (i = 0; i < NR_POWER_LIMITS; i++) { int prim = rd->rpl[i].prim_id; + if (rapl_read_data_raw(rd, prim, false, &val64)) rd->rpl[i].name = NULL; } @@ -1390,20 +1213,20 @@ static int rapl_detect_domains(struct rapl_package *rp, int cpu) for (i = 0; i < RAPL_DOMAIN_MAX; i++) { /* use physical package id to read counters */ - if (!rapl_check_domain(cpu, i)) { + if (!rapl_check_domain(cpu, i, rp)) { rp->domain_map |= 1 << i; pr_info("Found RAPL domain %s\n", rapl_domain_names[i]); } } - rp->nr_domains = bitmap_weight(&rp->domain_map, RAPL_DOMAIN_MAX); + rp->nr_domains = bitmap_weight(&rp->domain_map, RAPL_DOMAIN_MAX); if (!rp->nr_domains) { - pr_debug("no valid rapl domains found in package %d\n", rp->id); + pr_debug("no valid rapl domains found in %s\n", rp->name); return -ENODEV; } - pr_debug("found %d domains on package %d\n", rp->nr_domains, rp->id); + pr_debug("found %d domains on %s\n", rp->nr_domains, rp->name); rp->domains = kcalloc(rp->nr_domains + 1, sizeof(struct rapl_domain), - GFP_KERNEL); + GFP_KERNEL); if (!rp->domains) return -ENOMEM; @@ -1416,7 +1239,7 @@ static int rapl_detect_domains(struct rapl_package *rp, int cpu) } /* called from CPU hotplug notifier, hotplug lock held */ -static void rapl_remove_package(struct rapl_package *rp) +void rapl_remove_package(struct rapl_package *rp) { struct rapl_domain *rd, *rd_package = NULL; @@ -1433,20 +1256,41 @@ static void rapl_remove_package(struct rapl_package *rp) rd_package = rd; continue; } - pr_debug("remove package, undo power limit on %d: %s\n", - rp->id, rd->name); - powercap_unregister_zone(control_type, &rd->power_zone); + pr_debug("remove package, undo power limit on %s: %s\n", + rp->name, rd->name); + powercap_unregister_zone(rp->priv->control_type, + &rd->power_zone); } /* do parent zone last */ - powercap_unregister_zone(control_type, &rd_package->power_zone); + powercap_unregister_zone(rp->priv->control_type, + &rd_package->power_zone); list_del(&rp->plist); kfree(rp); } +EXPORT_SYMBOL_GPL(rapl_remove_package); + +/* caller to ensure CPU hotplug lock is held */ +struct rapl_package *rapl_find_package_domain(int cpu, struct rapl_if_priv *priv) +{ + int id = topology_logical_die_id(cpu); + struct rapl_package *rp; + + list_for_each_entry(rp, &rapl_packages, plist) { + if (rp->id == id + && rp->priv->control_type == priv->control_type) + return rp; + } + + return NULL; +} +EXPORT_SYMBOL_GPL(rapl_find_package_domain); /* called from CPU hotplug notifier, hotplug lock held */ -static struct rapl_package *rapl_add_package(int cpu, int pkgid) +struct rapl_package *rapl_add_package(int cpu, struct rapl_if_priv *priv) { + int id = topology_logical_die_id(cpu); struct rapl_package *rp; + struct cpuinfo_x86 *c = &cpu_data(cpu); int ret; rp = kzalloc(sizeof(struct rapl_package), GFP_KERNEL); @@ -1454,12 +1298,19 @@ static struct rapl_package *rapl_add_package(int cpu, int pkgid) return ERR_PTR(-ENOMEM); /* add the new package to the list */ - rp->id = pkgid; + rp->id = id; rp->lead_cpu = cpu; + rp->priv = priv; + + if (topology_max_die_per_package() > 1) + snprintf(rp->name, PACKAGE_DOMAIN_NAME_LENGTH, + "package-%d-die-%d", c->phys_proc_id, c->cpu_die_id); + else + snprintf(rp->name, PACKAGE_DOMAIN_NAME_LENGTH, "package-%d", + c->phys_proc_id); /* check if the package contains valid domains */ - if (rapl_detect_domains(rp, cpu) || - rapl_defaults->check_unit(rp, cpu)) { + if (rapl_detect_domains(rp, cpu) || rapl_defaults->check_unit(rp, cpu)) { ret = -ENODEV; goto err_free_package; } @@ -1475,49 +1326,7 @@ err_free_package: kfree(rp); return ERR_PTR(ret); } - -/* Handles CPU hotplug on multi-socket systems. - * If a CPU goes online as the first CPU of the physical package - * we add the RAPL package to the system. Similarly, when the last - * CPU of the package is removed, we remove the RAPL package and its - * associated domains. Cooling devices are handled accordingly at - * per-domain level. - */ -static int rapl_cpu_online(unsigned int cpu) -{ - int pkgid = topology_physical_package_id(cpu); - struct rapl_package *rp; - - rp = find_package_by_id(pkgid); - if (!rp) { - rp = rapl_add_package(cpu, pkgid); - if (IS_ERR(rp)) - return PTR_ERR(rp); - } - cpumask_set_cpu(cpu, &rp->cpumask); - return 0; -} - -static int rapl_cpu_down_prep(unsigned int cpu) -{ - int pkgid = topology_physical_package_id(cpu); - struct rapl_package *rp; - int lead_cpu; - - rp = find_package_by_id(pkgid); - if (!rp) - return 0; - - cpumask_clear_cpu(cpu, &rp->cpumask); - lead_cpu = cpumask_first(&rp->cpumask); - if (lead_cpu >= nr_cpu_ids) - rapl_remove_package(rp); - else if (rp->lead_cpu == cpu) - rp->lead_cpu = lead_cpu; - return 0; -} - -static enum cpuhp_state pcap_rapl_online; +EXPORT_SYMBOL_GPL(rapl_add_package); static void power_limit_state_save(void) { @@ -1535,17 +1344,15 @@ static void power_limit_state_save(void) switch (rd->rpl[i].prim_id) { case PL1_ENABLE: ret = rapl_read_data_raw(rd, - POWER_LIMIT1, - true, - &rd->rpl[i].last_power_limit); + POWER_LIMIT1, true, + &rd->rpl[i].last_power_limit); if (ret) rd->rpl[i].last_power_limit = 0; break; case PL2_ENABLE: ret = rapl_read_data_raw(rd, - POWER_LIMIT2, - true, - &rd->rpl[i].last_power_limit); + POWER_LIMIT2, true, + &rd->rpl[i].last_power_limit); if (ret) rd->rpl[i].last_power_limit = 0; break; @@ -1571,15 +1378,13 @@ static void power_limit_state_restore(void) switch (rd->rpl[i].prim_id) { case PL1_ENABLE: if (rd->rpl[i].last_power_limit) - rapl_write_data_raw(rd, - POWER_LIMIT1, - rd->rpl[i].last_power_limit); + rapl_write_data_raw(rd, POWER_LIMIT1, + rd->rpl[i].last_power_limit); break; case PL2_ENABLE: if (rd->rpl[i].last_power_limit) - rapl_write_data_raw(rd, - POWER_LIMIT2, - rd->rpl[i].last_power_limit); + rapl_write_data_raw(rd, POWER_LIMIT2, + rd->rpl[i].last_power_limit); break; } } @@ -1588,7 +1393,7 @@ static void power_limit_state_restore(void) } static int rapl_pm_callback(struct notifier_block *nb, - unsigned long mode, void *_unused) + unsigned long mode, void *_unused) { switch (mode) { case PM_SUSPEND_PREPARE: @@ -1605,6 +1410,8 @@ static struct notifier_block rapl_pm_notifier = { .notifier_call = rapl_pm_callback, }; +static struct platform_device *rapl_msr_platdev; + static int __init rapl_init(void) { const struct x86_cpu_id *id; @@ -1613,50 +1420,43 @@ static int __init rapl_init(void) id = x86_match_cpu(rapl_ids); if (!id) { pr_err("driver does not support CPU family %d model %d\n", - boot_cpu_data.x86, boot_cpu_data.x86_model); + boot_cpu_data.x86, boot_cpu_data.x86_model); return -ENODEV; } rapl_defaults = (struct rapl_defaults *)id->driver_data; - ret = rapl_register_powercap(); + ret = register_pm_notifier(&rapl_pm_notifier); if (ret) return ret; - ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "powercap/rapl:online", - rapl_cpu_online, rapl_cpu_down_prep); - if (ret < 0) - goto err_unreg; - pcap_rapl_online = ret; - - /* Don't bail out if PSys is not supported */ - rapl_register_psys(); + rapl_msr_platdev = platform_device_alloc("intel_rapl_msr", 0); + if (!rapl_msr_platdev) { + ret = -ENOMEM; + goto end; + } - ret = register_pm_notifier(&rapl_pm_notifier); + ret = platform_device_add(rapl_msr_platdev); if (ret) - goto err_unreg_all; + platform_device_put(rapl_msr_platdev); - return 0; - -err_unreg_all: - cpuhp_remove_state(pcap_rapl_online); +end: + if (ret) + unregister_pm_notifier(&rapl_pm_notifier); -err_unreg: - rapl_unregister_powercap(); return ret; } static void __exit rapl_exit(void) { + platform_device_unregister(rapl_msr_platdev); unregister_pm_notifier(&rapl_pm_notifier); - cpuhp_remove_state(pcap_rapl_online); - rapl_unregister_powercap(); } module_init(rapl_init); module_exit(rapl_exit); -MODULE_DESCRIPTION("Driver for Intel RAPL (Running Average Power Limit)"); +MODULE_DESCRIPTION("Intel Runtime Average Power Limit (RAPL) common code"); MODULE_AUTHOR("Jacob Pan <jacob.jun.pan@intel.com>"); MODULE_LICENSE("GPL v2"); diff --git a/drivers/powercap/intel_rapl_msr.c b/drivers/powercap/intel_rapl_msr.c new file mode 100644 index 000000000000..d5487965bdfe --- /dev/null +++ b/drivers/powercap/intel_rapl_msr.c @@ -0,0 +1,183 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Intel Running Average Power Limit (RAPL) Driver via MSR interface + * Copyright (c) 2019, Intel Corporation. + */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/list.h> +#include <linux/types.h> +#include <linux/device.h> +#include <linux/slab.h> +#include <linux/log2.h> +#include <linux/bitmap.h> +#include <linux/delay.h> +#include <linux/sysfs.h> +#include <linux/cpu.h> +#include <linux/powercap.h> +#include <linux/suspend.h> +#include <linux/intel_rapl.h> +#include <linux/processor.h> +#include <linux/platform_device.h> + +#include <asm/iosf_mbi.h> +#include <asm/cpu_device_id.h> +#include <asm/intel-family.h> + +/* Local defines */ +#define MSR_PLATFORM_POWER_LIMIT 0x0000065C + +/* private data for RAPL MSR Interface */ +static struct rapl_if_priv rapl_msr_priv = { + .reg_unit = MSR_RAPL_POWER_UNIT, + .regs[RAPL_DOMAIN_PACKAGE] = { + MSR_PKG_POWER_LIMIT, MSR_PKG_ENERGY_STATUS, MSR_PKG_PERF_STATUS, 0, MSR_PKG_POWER_INFO }, + .regs[RAPL_DOMAIN_PP0] = { + MSR_PP0_POWER_LIMIT, MSR_PP0_ENERGY_STATUS, 0, MSR_PP0_POLICY, 0 }, + .regs[RAPL_DOMAIN_PP1] = { + MSR_PP1_POWER_LIMIT, MSR_PP1_ENERGY_STATUS, 0, MSR_PP1_POLICY, 0 }, + .regs[RAPL_DOMAIN_DRAM] = { + MSR_DRAM_POWER_LIMIT, MSR_DRAM_ENERGY_STATUS, MSR_DRAM_PERF_STATUS, 0, MSR_DRAM_POWER_INFO }, + .regs[RAPL_DOMAIN_PLATFORM] = { + MSR_PLATFORM_POWER_LIMIT, MSR_PLATFORM_ENERGY_STATUS, 0, 0, 0}, + .limits[RAPL_DOMAIN_PACKAGE] = 2, +}; + +/* Handles CPU hotplug on multi-socket systems. + * If a CPU goes online as the first CPU of the physical package + * we add the RAPL package to the system. Similarly, when the last + * CPU of the package is removed, we remove the RAPL package and its + * associated domains. Cooling devices are handled accordingly at + * per-domain level. + */ +static int rapl_cpu_online(unsigned int cpu) +{ + struct rapl_package *rp; + + rp = rapl_find_package_domain(cpu, &rapl_msr_priv); + if (!rp) { + rp = rapl_add_package(cpu, &rapl_msr_priv); + if (IS_ERR(rp)) + return PTR_ERR(rp); + } + cpumask_set_cpu(cpu, &rp->cpumask); + return 0; +} + +static int rapl_cpu_down_prep(unsigned int cpu) +{ + struct rapl_package *rp; + int lead_cpu; + + rp = rapl_find_package_domain(cpu, &rapl_msr_priv); + if (!rp) + return 0; + + cpumask_clear_cpu(cpu, &rp->cpumask); + lead_cpu = cpumask_first(&rp->cpumask); + if (lead_cpu >= nr_cpu_ids) + rapl_remove_package(rp); + else if (rp->lead_cpu == cpu) + rp->lead_cpu = lead_cpu; + return 0; +} + +static int rapl_msr_read_raw(int cpu, struct reg_action *ra) +{ + u32 msr = (u32)ra->reg; + + if (rdmsrl_safe_on_cpu(cpu, msr, &ra->value)) { + pr_debug("failed to read msr 0x%x on cpu %d\n", msr, cpu); + return -EIO; + } + ra->value &= ra->mask; + return 0; +} + +static void rapl_msr_update_func(void *info) +{ + struct reg_action *ra = info; + u32 msr = (u32)ra->reg; + u64 val; + + ra->err = rdmsrl_safe(msr, &val); + if (ra->err) + return; + + val &= ~ra->mask; + val |= ra->value; + + ra->err = wrmsrl_safe(msr, val); +} + +static int rapl_msr_write_raw(int cpu, struct reg_action *ra) +{ + int ret; + + ret = smp_call_function_single(cpu, rapl_msr_update_func, ra, 1); + if (WARN_ON_ONCE(ret)) + return ret; + + return ra->err; +} + +static int rapl_msr_probe(struct platform_device *pdev) +{ + int ret; + + rapl_msr_priv.read_raw = rapl_msr_read_raw; + rapl_msr_priv.write_raw = rapl_msr_write_raw; + + rapl_msr_priv.control_type = powercap_register_control_type(NULL, "intel-rapl", NULL); + if (IS_ERR(rapl_msr_priv.control_type)) { + pr_debug("failed to register powercap control_type.\n"); + return PTR_ERR(rapl_msr_priv.control_type); + } + + ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "powercap/rapl:online", + rapl_cpu_online, rapl_cpu_down_prep); + if (ret < 0) + goto out; + rapl_msr_priv.pcap_rapl_online = ret; + + /* Don't bail out if PSys is not supported */ + rapl_add_platform_domain(&rapl_msr_priv); + + return 0; + +out: + if (ret) + powercap_unregister_control_type(rapl_msr_priv.control_type); + return ret; +} + +static int rapl_msr_remove(struct platform_device *pdev) +{ + cpuhp_remove_state(rapl_msr_priv.pcap_rapl_online); + rapl_remove_platform_domain(&rapl_msr_priv); + powercap_unregister_control_type(rapl_msr_priv.control_type); + return 0; +} + +static const struct platform_device_id rapl_msr_ids[] = { + { .name = "intel_rapl_msr", }, + {} +}; +MODULE_DEVICE_TABLE(platform, rapl_msr_ids); + +static struct platform_driver intel_rapl_msr_driver = { + .probe = rapl_msr_probe, + .remove = rapl_msr_remove, + .id_table = rapl_msr_ids, + .driver = { + .name = "intel_rapl_msr", + }, +}; + +module_platform_driver(intel_rapl_msr_driver); + +MODULE_DESCRIPTION("Driver for Intel RAPL (Running Average Power Limit) control via MSR interface"); +MODULE_AUTHOR("Zhang Rui <rui.zhang@intel.com>"); +MODULE_LICENSE("GPL v2"); |