diff options
Diffstat (limited to 'drivers/cpufreq/powernv-cpufreq.c')
| -rw-r--r-- | drivers/cpufreq/powernv-cpufreq.c | 364 |
1 files changed, 221 insertions, 143 deletions
diff --git a/drivers/cpufreq/powernv-cpufreq.c b/drivers/cpufreq/powernv-cpufreq.c index 3ff5160451b4..7d9a5f656de8 100644 --- a/drivers/cpufreq/powernv-cpufreq.c +++ b/drivers/cpufreq/powernv-cpufreq.c @@ -1,20 +1,10 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * POWERNV cpufreq driver for the IBM POWER processors * * (C) Copyright IBM 2014 * * Author: Vaidyanathan Srinivasan <svaidy at linux.vnet.ibm.com> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2, or (at your option) - * any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * */ #define pr_fmt(fmt) "powernv-cpufreq: " fmt @@ -28,8 +18,9 @@ #include <linux/of.h> #include <linux/reboot.h> #include <linux/slab.h> +#include <linux/string_choices.h> #include <linux/cpu.h> -#include <trace/events/power.h> +#include <linux/hashtable.h> #include <asm/cputhreads.h> #include <asm/firmware.h> @@ -38,14 +29,17 @@ #include <asm/opal.h> #include <linux/timer.h> -#define POWERNV_MAX_PSTATES 256 +#define CREATE_TRACE_POINTS +#include "powernv-trace.h" + +#define POWERNV_MAX_PSTATES_ORDER 8 +#define POWERNV_MAX_PSTATES (1UL << (POWERNV_MAX_PSTATES_ORDER)) #define PMSR_PSAFE_ENABLE (1UL << 30) #define PMSR_SPR_EM_DISABLE (1UL << 31) -#define PMSR_MAX(x) ((x >> 32) & 0xFF) +#define MAX_PSTATE_SHIFT 32 #define LPSTATE_SHIFT 48 #define GPSTATE_SHIFT 56 -#define GET_LPSTATE(x) (((x) >> LPSTATE_SHIFT) & 0xFF) -#define GET_GPSTATE(x) (((x) >> GPSTATE_SHIFT) & 0xFF) +#define MAX_NR_CHIPS 32 #define MAX_RAMP_DOWN_TIME 5120 /* @@ -74,13 +68,14 @@ * highest_lpstate_idx * @last_sampled_time: Time from boot in ms when global pstates were * last set - * @last_lpstate_idx, Last set value of local pstate and global - * last_gpstate_idx pstate in terms of cpufreq table index + * @last_lpstate_idx: Last set value of local pstate and global + * @last_gpstate_idx: pstate in terms of cpufreq table index * @timer: Is used for ramping down if cpu goes idle for * a long time with global pstate held high * @gpstate_lock: A spinlock to maintain synchronization between * routines called by the timer handler and * governer's target_index calls + * @policy: Associated CPUFreq policy */ struct global_pstate_info { int highest_lpstate_idx; @@ -90,9 +85,31 @@ struct global_pstate_info { int last_gpstate_idx; spinlock_t gpstate_lock; struct timer_list timer; + struct cpufreq_policy *policy; }; static struct cpufreq_frequency_table powernv_freqs[POWERNV_MAX_PSTATES+1]; + +static DEFINE_HASHTABLE(pstate_revmap, POWERNV_MAX_PSTATES_ORDER); +/** + * struct pstate_idx_revmap_data: Entry in the hashmap pstate_revmap + * indexed by a function of pstate id. + * + * @pstate_id: pstate id for this entry. + * + * @cpufreq_table_idx: Index into the powernv_freqs + * cpufreq_frequency_table for frequency + * corresponding to pstate_id. + * + * @hentry: hlist_node that hooks this entry into the pstate_revmap + * hashtable + */ +struct pstate_idx_revmap_data { + u8 pstate_id; + unsigned int cpufreq_table_idx; + struct hlist_node hentry; +}; + static bool rebooting, throttled, occ_reset; static const char * const throttle_reason[] = { @@ -147,39 +164,56 @@ static struct powernv_pstate_info { bool wof_enabled; } powernv_pstate_info; -/* Use following macros for conversions between pstate_id and index */ -static inline int idx_to_pstate(unsigned int i) +static inline u8 extract_pstate(u64 pmsr_val, unsigned int shift) +{ + return ((pmsr_val >> shift) & 0xFF); +} + +#define extract_local_pstate(x) extract_pstate(x, LPSTATE_SHIFT) +#define extract_global_pstate(x) extract_pstate(x, GPSTATE_SHIFT) +#define extract_max_pstate(x) extract_pstate(x, MAX_PSTATE_SHIFT) + +/* Use following functions for conversions between pstate_id and index */ + +/* + * idx_to_pstate : Returns the pstate id corresponding to the + * frequency in the cpufreq frequency table + * powernv_freqs indexed by @i. + * + * If @i is out of bound, this will return the pstate + * corresponding to the nominal frequency. + */ +static inline u8 idx_to_pstate(unsigned int i) { if (unlikely(i >= powernv_pstate_info.nr_pstates)) { - pr_warn_once("index %u is out of bound\n", i); + pr_warn_once("idx_to_pstate: index %u is out of bound\n", i); return powernv_freqs[powernv_pstate_info.nominal].driver_data; } return powernv_freqs[i].driver_data; } -static inline unsigned int pstate_to_idx(int pstate) +/* + * pstate_to_idx : Returns the index in the cpufreq frequencytable + * powernv_freqs for the frequency whose corresponding + * pstate id is @pstate. + * + * If no frequency corresponding to @pstate is found, + * this will return the index of the nominal + * frequency. + */ +static unsigned int pstate_to_idx(u8 pstate) { - int min = powernv_freqs[powernv_pstate_info.min].driver_data; - int max = powernv_freqs[powernv_pstate_info.max].driver_data; + unsigned int key = pstate % POWERNV_MAX_PSTATES; + struct pstate_idx_revmap_data *revmap_data; - if (min > 0) { - if (unlikely((pstate < max) || (pstate > min))) { - pr_warn_once("pstate %d is out of bound\n", pstate); - return powernv_pstate_info.nominal; - } - } else { - if (unlikely((pstate > max) || (pstate < min))) { - pr_warn_once("pstate %d is out of bound\n", pstate); - return powernv_pstate_info.nominal; - } + hash_for_each_possible(pstate_revmap, revmap_data, hentry, key) { + if (revmap_data->pstate_id == pstate) + return revmap_data->cpufreq_table_idx; } - /* - * abs() is deliberately used so that is works with - * both monotonically increasing and decreasing - * pstate values - */ - return abs(pstate - idx_to_pstate(powernv_pstate_info.max)); + + pr_warn_once("pstate_to_idx: pstate 0x%x not found\n", pstate); + return powernv_pstate_info.nominal; } static inline void reset_gpstates(struct cpufreq_policy *policy) @@ -205,6 +239,7 @@ static int init_powernv_pstates(void) u32 len_ids, len_freqs; u32 pstate_min, pstate_max, pstate_nominal; u32 pstate_turbo, pstate_ultra_turbo; + int rc = -ENODEV; power_mgt = of_find_node_by_path("/ibm,opal/power-mgt"); if (!power_mgt) { @@ -214,18 +249,18 @@ static int init_powernv_pstates(void) if (of_property_read_u32(power_mgt, "ibm,pstate-min", &pstate_min)) { pr_warn("ibm,pstate-min node not found\n"); - return -ENODEV; + goto out; } if (of_property_read_u32(power_mgt, "ibm,pstate-max", &pstate_max)) { pr_warn("ibm,pstate-max node not found\n"); - return -ENODEV; + goto out; } if (of_property_read_u32(power_mgt, "ibm,pstate-nominal", &pstate_nominal)) { pr_warn("ibm,pstate-nominal not found\n"); - return -ENODEV; + goto out; } if (of_property_read_u32(power_mgt, "ibm,pstate-ultra-turbo", @@ -246,22 +281,22 @@ static int init_powernv_pstates(void) powernv_pstate_info.wof_enabled = true; next: - pr_info("cpufreq pstate min %d nominal %d max %d\n", pstate_min, + pr_info("cpufreq pstate min 0x%x nominal 0x%x max 0x%x\n", pstate_min, pstate_nominal, pstate_max); pr_info("Workload Optimized Frequency is %s in the platform\n", - (powernv_pstate_info.wof_enabled) ? "enabled" : "disabled"); + str_enabled_disabled(powernv_pstate_info.wof_enabled)); pstate_ids = of_get_property(power_mgt, "ibm,pstate-ids", &len_ids); if (!pstate_ids) { pr_warn("ibm,pstate-ids not found\n"); - return -ENODEV; + goto out; } pstate_freqs = of_get_property(power_mgt, "ibm,pstate-frequencies-mhz", &len_freqs); if (!pstate_freqs) { pr_warn("ibm,pstate-frequencies-mhz not found\n"); - return -ENODEV; + goto out; } if (len_ids != len_freqs) { @@ -272,24 +307,38 @@ next: nr_pstates = min(len_ids, len_freqs) / sizeof(u32); if (!nr_pstates) { pr_warn("No PStates found\n"); - return -ENODEV; + goto out; } powernv_pstate_info.nr_pstates = nr_pstates; pr_debug("NR PStates %d\n", nr_pstates); + for (i = 0; i < nr_pstates; i++) { u32 id = be32_to_cpu(pstate_ids[i]); u32 freq = be32_to_cpu(pstate_freqs[i]); + struct pstate_idx_revmap_data *revmap_data; + unsigned int key; pr_debug("PState id %d freq %d MHz\n", id, freq); powernv_freqs[i].frequency = freq * 1000; /* kHz */ - powernv_freqs[i].driver_data = id; + powernv_freqs[i].driver_data = id & 0xFF; + + revmap_data = kmalloc(sizeof(*revmap_data), GFP_KERNEL); + if (!revmap_data) { + rc = -ENOMEM; + goto out; + } + + revmap_data->pstate_id = id & 0xFF; + revmap_data->cpufreq_table_idx = i; + key = (revmap_data->pstate_id) % POWERNV_MAX_PSTATES; + hash_add(pstate_revmap, &revmap_data->hentry, key); if (id == pstate_max) powernv_pstate_info.max = i; - else if (id == pstate_nominal) + if (id == pstate_nominal) powernv_pstate_info.nominal = i; - else if (id == pstate_min) + if (id == pstate_min) powernv_pstate_info.min = i; if (powernv_pstate_info.wof_enabled && id == pstate_turbo) { @@ -302,18 +351,22 @@ next: /* End of list marker entry */ powernv_freqs[i].frequency = CPUFREQ_TABLE_END; + + of_node_put(power_mgt); return 0; +out: + of_node_put(power_mgt); + return rc; } /* Returns the CPU frequency corresponding to the pstate_id. */ -static unsigned int pstate_id_to_freq(int pstate_id) +static unsigned int pstate_id_to_freq(u8 pstate_id) { int i; i = pstate_to_idx(pstate_id); if (i >= powernv_pstate_info.nr_pstates || i < 0) { - pr_warn("PState id %d outside of PState table, " - "reporting nominal id %d instead\n", + pr_warn("PState id 0x%x outside of PState table, reporting nominal id 0x%x instead\n", pstate_id, idx_to_pstate(powernv_pstate_info.nominal)); i = powernv_pstate_info.nominal; } @@ -332,15 +385,11 @@ static ssize_t cpuinfo_nominal_freq_show(struct cpufreq_policy *policy, powernv_freqs[powernv_pstate_info.nominal].frequency); } -struct freq_attr cpufreq_freq_attr_cpuinfo_nominal_freq = +static struct freq_attr cpufreq_freq_attr_cpuinfo_nominal_freq = __ATTR_RO(cpuinfo_nominal_freq); -#define SCALING_BOOST_FREQS_ATTR_INDEX 2 - static struct freq_attr *powernv_cpu_freq_attr[] = { - &cpufreq_freq_attr_scaling_available_freqs, &cpufreq_freq_attr_cpuinfo_nominal_freq, - &cpufreq_freq_attr_scaling_boost_freqs, NULL, }; @@ -419,8 +468,8 @@ static inline void set_pmspr(unsigned long sprn, unsigned long val) */ struct powernv_smp_call_data { unsigned int freq; - int pstate_id; - int gpstate_id; + u8 pstate_id; + u8 gpstate_id; }; /* @@ -437,22 +486,15 @@ struct powernv_smp_call_data { static void powernv_read_cpu_freq(void *arg) { unsigned long pmspr_val; - s8 local_pstate_id; struct powernv_smp_call_data *freq_data = arg; pmspr_val = get_pmspr(SPRN_PMSR); - - /* - * The local pstate id corresponds bits 48..55 in the PMSR. - * Note: Watch out for the sign! - */ - local_pstate_id = (pmspr_val >> 48) & 0xFF; - freq_data->pstate_id = local_pstate_id; + freq_data->pstate_id = extract_local_pstate(pmspr_val); freq_data->freq = pstate_id_to_freq(freq_data->pstate_id); - pr_debug("cpu %d pmsr %016lX pstate_id %d frequency %d kHz\n", - raw_smp_processor_id(), pmspr_val, freq_data->pstate_id, - freq_data->freq); + pr_debug("cpu %d pmsr %016lX pstate_id 0x%x frequency %d kHz\n", + raw_smp_processor_id(), pmspr_val, freq_data->pstate_id, + freq_data->freq); } /* @@ -514,21 +556,21 @@ static void powernv_cpufreq_throttle_check(void *data) struct chip *chip; unsigned int cpu = smp_processor_id(); unsigned long pmsr; - int pmsr_pmax; + u8 pmsr_pmax; unsigned int pmsr_pmax_idx; pmsr = get_pmspr(SPRN_PMSR); chip = this_cpu_read(chip_info); /* Check for Pmax Capping */ - pmsr_pmax = (s8)PMSR_MAX(pmsr); + pmsr_pmax = extract_max_pstate(pmsr); pmsr_pmax_idx = pstate_to_idx(pmsr_pmax); if (pmsr_pmax_idx != powernv_pstate_info.max) { if (chip->throttled) goto next; chip->throttled = true; if (pmsr_pmax_idx > powernv_pstate_info.nominal) { - pr_warn_once("CPU %d on Chip %u has Pmax(%d) reduced below nominal frequency(%d)\n", + pr_warn_once("CPU %d on Chip %u has Pmax(0x%x) reduced below that of nominal frequency(0x%x)\n", cpu, chip->id, pmsr_pmax, idx_to_pstate(powernv_pstate_info.nominal)); chip->throttle_sub_turbo++; @@ -619,16 +661,17 @@ static inline void queue_gpstate_timer(struct global_pstate_info *gpstates) /** * gpstate_timer_handler * - * @data: pointer to cpufreq_policy on which timer was queued + * @t: Timer context used to fetch global pstate info struct * * This handler brings down the global pstate closer to the local pstate * according quadratic equation. Queues a new timer if it is still not equal * to local pstate */ -void gpstate_timer_handler(unsigned long data) +static void gpstate_timer_handler(struct timer_list *t) { - struct cpufreq_policy *policy = (struct cpufreq_policy *)data; - struct global_pstate_info *gpstates = policy->driver_data; + struct global_pstate_info *gpstates = timer_container_of(gpstates, t, + timer); + struct cpufreq_policy *policy = gpstates->policy; int gpstate_idx, lpstate_idx; unsigned long val; unsigned int time_diff = jiffies_to_msecs(jiffies) @@ -637,15 +680,25 @@ void gpstate_timer_handler(unsigned long data) if (!spin_trylock(&gpstates->gpstate_lock)) return; + /* + * If the timer has migrated to the different cpu then bring + * it back to one of the policy->cpus + */ + if (!cpumask_test_cpu(raw_smp_processor_id(), policy->cpus)) { + gpstates->timer.expires = jiffies + msecs_to_jiffies(1); + add_timer_on(&gpstates->timer, cpumask_first(policy->cpus)); + spin_unlock(&gpstates->gpstate_lock); + return; + } /* - * If PMCR was last updated was using fast_swtich then + * If PMCR was last updated was using fast_switch then * We may have wrong in gpstate->last_lpstate_idx * value. Hence, read from PMCR to get correct data. */ val = get_pmspr(SPRN_PMCR); - freq_data.gpstate_id = (s8)GET_GPSTATE(val); - freq_data.pstate_id = (s8)GET_LPSTATE(val); + freq_data.gpstate_id = extract_global_pstate(val); + freq_data.pstate_id = extract_local_pstate(val); if (freq_data.gpstate_id == freq_data.pstate_id) { reset_gpstates(policy); spin_unlock(&gpstates->gpstate_lock); @@ -676,10 +729,8 @@ void gpstate_timer_handler(unsigned long data) if (gpstate_idx != gpstates->last_lpstate_idx) queue_gpstate_timer(gpstates); + set_pstate(&freq_data); spin_unlock(&gpstates->gpstate_lock); - - /* Timer may get migrated to a different cpu on cpu hot unplug */ - smp_call_function_any(policy->cpus, set_pstate, &freq_data, 1); } /* @@ -708,8 +759,13 @@ static int powernv_cpufreq_target_index(struct cpufreq_policy *policy, cur_msec = jiffies_to_msecs(get_jiffies_64()); - spin_lock(&gpstates->gpstate_lock); freq_data.pstate_id = idx_to_pstate(new_index); + if (!gpstates) { + freq_data.gpstate_id = freq_data.pstate_id; + goto no_gpstate; + } + + spin_lock(&gpstates->gpstate_lock); if (!gpstates->last_sampled_time) { gpstate_idx = new_index; @@ -749,7 +805,7 @@ static int powernv_cpufreq_target_index(struct cpufreq_policy *policy, if (gpstate_idx != new_index) queue_gpstate_timer(gpstates); else - del_timer_sync(&gpstates->timer); + timer_delete_sync(&gpstates->timer); gpstates_done: freq_data.gpstate_id = idx_to_pstate(gpstate_idx); @@ -759,6 +815,7 @@ gpstates_done: spin_unlock(&gpstates->gpstate_lock); +no_gpstate: /* * Use smp_call_function to send IPI and execute the * mtspr on target CPU. We could do that without IPI @@ -770,7 +827,7 @@ gpstates_done: static int powernv_cpufreq_cpu_init(struct cpufreq_policy *policy) { - int base, i, ret; + int base, i; struct kernfs_node *kn; struct global_pstate_info *gpstates; @@ -793,6 +850,13 @@ static int powernv_cpufreq_cpu_init(struct cpufreq_policy *policy) kernfs_put(kn); } + policy->freq_table = powernv_freqs; + policy->fast_switch_possible = true; + + if (pvr_version_is(PVR_POWER9)) + return 0; + + /* Initialise Gpstate ramp-down timer only on POWER8 */ gpstates = kzalloc(sizeof(*gpstates), GFP_KERNEL); if (!gpstates) return -ENOMEM; @@ -800,41 +864,43 @@ static int powernv_cpufreq_cpu_init(struct cpufreq_policy *policy) policy->driver_data = gpstates; /* initialize timer */ - init_timer_pinned_deferrable(&gpstates->timer); - gpstates->timer.data = (unsigned long)policy; - gpstates->timer.function = gpstate_timer_handler; + gpstates->policy = policy; + timer_setup(&gpstates->timer, gpstate_timer_handler, + TIMER_PINNED | TIMER_DEFERRABLE); gpstates->timer.expires = jiffies + msecs_to_jiffies(GPSTATE_TIMER_INTERVAL); spin_lock_init(&gpstates->gpstate_lock); - ret = cpufreq_table_validate_and_show(policy, powernv_freqs); - if (ret < 0) { - kfree(policy->driver_data); - return ret; - } - - policy->fast_switch_possible = true; - return ret; + return 0; } -static int powernv_cpufreq_cpu_exit(struct cpufreq_policy *policy) +static void powernv_cpufreq_cpu_exit(struct cpufreq_policy *policy) { - /* timer is deleted in cpufreq_cpu_stop() */ - kfree(policy->driver_data); + struct powernv_smp_call_data freq_data; + struct global_pstate_info *gpstates = policy->driver_data; - return 0; + freq_data.pstate_id = idx_to_pstate(powernv_pstate_info.min); + freq_data.gpstate_id = idx_to_pstate(powernv_pstate_info.min); + smp_call_function_single(policy->cpu, set_pstate, &freq_data, 1); + if (gpstates) + timer_delete_sync(&gpstates->timer); + + kfree(policy->driver_data); } static int powernv_cpufreq_reboot_notifier(struct notifier_block *nb, unsigned long action, void *unused) { int cpu; - struct cpufreq_policy cpu_policy; + struct cpufreq_policy *cpu_policy; rebooting = true; for_each_online_cpu(cpu) { - cpufreq_get_policy(&cpu_policy, cpu); - powernv_cpufreq_target_index(&cpu_policy, get_nominal_index()); + cpu_policy = cpufreq_cpu_get(cpu); + if (!cpu_policy) + continue; + powernv_cpufreq_target_index(cpu_policy, get_nominal_index()); + cpufreq_cpu_put(cpu_policy); } return NOTIFY_DONE; @@ -844,13 +910,14 @@ static struct notifier_block powernv_cpufreq_reboot_nb = { .notifier_call = powernv_cpufreq_reboot_notifier, }; -void powernv_cpufreq_work_fn(struct work_struct *work) +static void powernv_cpufreq_work_fn(struct work_struct *work) { struct chip *chip = container_of(work, struct chip, throttle); + struct cpufreq_policy *policy; unsigned int cpu; cpumask_t mask; - get_online_cpus(); + cpus_read_lock(); cpumask_and(&mask, &chip->mask, cpu_online_mask); smp_call_function_any(&mask, powernv_cpufreq_throttle_check, NULL, 0); @@ -861,15 +928,17 @@ void powernv_cpufreq_work_fn(struct work_struct *work) chip->restore = false; for_each_cpu(cpu, &mask) { int index; - struct cpufreq_policy policy; - cpufreq_get_policy(&policy, cpu); - index = cpufreq_table_find_index_c(&policy, policy.cur); - powernv_cpufreq_target_index(&policy, index); - cpumask_andnot(&mask, &mask, policy.cpus); + policy = cpufreq_cpu_get(cpu); + if (!policy) + continue; + index = cpufreq_table_find_index_c(policy, policy->cur, false); + powernv_cpufreq_target_index(policy, index); + cpumask_andnot(&mask, &mask, policy->cpus); + cpufreq_cpu_put(policy); } out: - put_online_cpus(); + cpus_read_unlock(); } static int powernv_cpufreq_occ_msg(struct notifier_block *nb, @@ -945,24 +1014,13 @@ static struct notifier_block powernv_cpufreq_opal_nb = { .priority = 0, }; -static void powernv_cpufreq_stop_cpu(struct cpufreq_policy *policy) -{ - struct powernv_smp_call_data freq_data; - struct global_pstate_info *gpstates = policy->driver_data; - - freq_data.pstate_id = idx_to_pstate(powernv_pstate_info.min); - freq_data.gpstate_id = idx_to_pstate(powernv_pstate_info.min); - smp_call_function_single(policy->cpu, set_pstate, &freq_data, 1); - del_timer_sync(&gpstates->timer); -} - static unsigned int powernv_fast_switch(struct cpufreq_policy *policy, unsigned int target_freq) { int index; struct powernv_smp_call_data freq_data; - index = cpufreq_table_find_index_dl(policy, target_freq); + index = cpufreq_table_find_index_dl(policy, target_freq, false); freq_data.pstate_id = powernv_freqs[index].driver_data; freq_data.gpstate_id = powernv_freqs[index].driver_data; set_pstate(&freq_data); @@ -979,15 +1037,27 @@ static struct cpufreq_driver powernv_cpufreq_driver = { .target_index = powernv_cpufreq_target_index, .fast_switch = powernv_fast_switch, .get = powernv_cpufreq_get, - .stop_cpu = powernv_cpufreq_stop_cpu, .attr = powernv_cpu_freq_attr, }; static int init_chip_info(void) { - unsigned int chip[256]; + unsigned int *chip; unsigned int cpu, i; unsigned int prev_chip_id = UINT_MAX; + cpumask_t *chip_cpu_mask; + int ret = 0; + + chip = kcalloc(num_possible_cpus(), sizeof(*chip), GFP_KERNEL); + if (!chip) + return -ENOMEM; + + /* Allocate a chip cpu mask large enough to fit mask for all chips */ + chip_cpu_mask = kcalloc(MAX_NR_CHIPS, sizeof(cpumask_t), GFP_KERNEL); + if (!chip_cpu_mask) { + ret = -ENOMEM; + goto free_and_return; + } for_each_possible_cpu(cpu) { unsigned int id = cpu_to_chip_id(cpu); @@ -996,25 +1066,38 @@ static int init_chip_info(void) prev_chip_id = id; chip[nr_chips++] = id; } + cpumask_set_cpu(cpu, &chip_cpu_mask[nr_chips-1]); } chips = kcalloc(nr_chips, sizeof(struct chip), GFP_KERNEL); - if (!chips) - return -ENOMEM; + if (!chips) { + ret = -ENOMEM; + goto out_free_chip_cpu_mask; + } for (i = 0; i < nr_chips; i++) { chips[i].id = chip[i]; - cpumask_copy(&chips[i].mask, cpumask_of_node(chip[i])); + cpumask_copy(&chips[i].mask, &chip_cpu_mask[i]); INIT_WORK(&chips[i].throttle, powernv_cpufreq_work_fn); for_each_cpu(cpu, &chips[i].mask) per_cpu(chip_info, cpu) = &chips[i]; } - return 0; +out_free_chip_cpu_mask: + kfree(chip_cpu_mask); +free_and_return: + kfree(chip); + return ret; } static inline void clean_chip_info(void) { + int i; + + /* flush any pending work items */ + if (chips) + for (i = 0; i < nr_chips; i++) + cancel_work_sync(&chips[i].throttle); kfree(chips); } @@ -1043,26 +1126,20 @@ static int __init powernv_cpufreq_init(void) if (rc) goto out; - register_reboot_notifier(&powernv_cpufreq_reboot_nb); - opal_message_notifier_register(OPAL_MSG_OCC, &powernv_cpufreq_opal_nb); - if (powernv_pstate_info.wof_enabled) - powernv_cpufreq_driver.boost_enabled = true; - else - powernv_cpu_freq_attr[SCALING_BOOST_FREQS_ATTR_INDEX] = NULL; + powernv_cpufreq_driver.set_boost = cpufreq_boost_set_sw; rc = cpufreq_register_driver(&powernv_cpufreq_driver); if (rc) { pr_info("Failed to register the cpufreq driver (%d)\n", rc); - goto cleanup_notifiers; + goto cleanup; } - if (powernv_pstate_info.wof_enabled) - cpufreq_enable_boost_support(); + register_reboot_notifier(&powernv_cpufreq_reboot_nb); + opal_message_notifier_register(OPAL_MSG_OCC, &powernv_cpufreq_opal_nb); return 0; -cleanup_notifiers: - unregister_all_notifiers(); +cleanup: clean_chip_info(); out: pr_info("Platform driver disabled. System does not support PState control\n"); @@ -1078,5 +1155,6 @@ static void __exit powernv_cpufreq_exit(void) } module_exit(powernv_cpufreq_exit); +MODULE_DESCRIPTION("cpufreq driver for IBM/OpenPOWER powernv systems"); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Vaidyanathan Srinivasan <svaidy at linux.vnet.ibm.com>"); |