linux/drivers/cpufreq/qcom-cpufreq-hw.c

801 lines
20 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0
/*
* Copyright (c) 2018, The Linux Foundation. All rights reserved.
*/
#include <linux/bitfield.h>
#include <linux/clk-provider.h>
#include <linux/cpufreq.h>
#include <linux/init.h>
#include <linux/interconnect.h>
#include <linux/interrupt.h>
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/of_address.h>
#include <linux/of_platform.h>
#include <linux/pm_opp.h>
#include <linux/pm_qos.h>
#include <linux/slab.h>
#include <linux/spinlock.h>
#include <linux/units.h>
#define LUT_MAX_ENTRIES 40U
#define LUT_SRC GENMASK(31, 30)
#define LUT_L_VAL GENMASK(7, 0)
#define LUT_CORE_COUNT GENMASK(18, 16)
#define LUT_VOLT GENMASK(11, 0)
#define CLK_HW_DIV 2
#define LUT_TURBO_IND 1
#define GT_IRQ_STATUS BIT(2)
struct qcom_cpufreq_soc_data {
u32 reg_enable;
u32 reg_domain_state;
u32 reg_dcvs_ctrl;
u32 reg_freq_lut;
u32 reg_volt_lut;
u32 reg_intr_clr;
u32 reg_current_vote;
u32 reg_perf_state;
u8 lut_row_size;
};
struct qcom_cpufreq_data {
void __iomem *base;
cpufreq: qcom-hw: drop devm_xxx() calls from init/exit hooks Commit f17b3e44320b ("cpufreq: qcom-hw: Use devm_platform_ioremap_resource() to simplify code") introduces a regression on platforms using the driver, by failing to initialise a policy, when one is created post hotplug. When all the CPUs of a policy are hoptplugged out, the call to .exit() and later to devm_iounmap() does not release the memory region that was requested during devm_platform_ioremap_resource(). Therefore, a subsequent call to .init() will result in the following error, which will prevent a new policy to be initialised: [ 3395.915416] CPU4: shutdown [ 3395.938185] psci: CPU4 killed (polled 0 ms) [ 3399.071424] CPU5: shutdown [ 3399.094316] psci: CPU5 killed (polled 0 ms) [ 3402.139358] CPU6: shutdown [ 3402.161705] psci: CPU6 killed (polled 0 ms) [ 3404.742939] CPU7: shutdown [ 3404.765592] psci: CPU7 killed (polled 0 ms) [ 3411.492274] Detected VIPT I-cache on CPU4 [ 3411.492337] GICv3: CPU4: found redistributor 400 region 0:0x0000000017ae0000 [ 3411.492448] CPU4: Booted secondary processor 0x0000000400 [0x516f802d] [ 3411.503654] qcom-cpufreq-hw 17d43000.cpufreq: can't request region for resource [mem 0x17d45800-0x17d46bff] With that being said, the original code was tricky and skipping memory region request intentionally to hide this issue. The true cause is that those devm_xxx() device managed functions shouldn't be used for cpufreq init/exit hooks, because &pdev->dev is alive across the hooks and will not trigger auto resource free-up. Let's drop the use of device managed functions and manually allocate/free resources, so that the issue can be fixed properly. Cc: v5.10+ <stable@vger.kernel.org> # v5.10+ Fixes: f17b3e44320b ("cpufreq: qcom-hw: Use devm_platform_ioremap_resource() to simplify code") Suggested-by: Bjorn Andersson <bjorn.andersson@linaro.org> Signed-off-by: Shawn Guo <shawn.guo@linaro.org> Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
2021-01-19 10:39:25 +08:00
struct resource *res;
/*
* Mutex to synchronize between de-init sequence and re-starting LMh
* polling/interrupts
*/
struct mutex throttle_lock;
int throttle_irq;
char irq_name[15];
bool cancel_throttle;
struct delayed_work throttle_work;
struct cpufreq_policy *policy;
struct clk_hw cpu_clk;
bool per_core_dcvs;
struct freq_qos_request throttle_freq_req;
};
static struct {
struct qcom_cpufreq_data *data;
const struct qcom_cpufreq_soc_data *soc_data;
} qcom_cpufreq;
static unsigned long cpu_hw_rate, xo_rate;
static bool icc_scaling_enabled;
static int qcom_cpufreq_set_bw(struct cpufreq_policy *policy,
unsigned long freq_khz)
{
unsigned long freq_hz = freq_khz * 1000;
struct dev_pm_opp *opp;
struct device *dev;
int ret;
dev = get_cpu_device(policy->cpu);
if (!dev)
return -ENODEV;
opp = dev_pm_opp_find_freq_exact(dev, freq_hz, true);
if (IS_ERR(opp))
return PTR_ERR(opp);
ret = dev_pm_opp_set_opp(dev, opp);
dev_pm_opp_put(opp);
return ret;
}
static int qcom_cpufreq_update_opp(struct device *cpu_dev,
unsigned long freq_khz,
unsigned long volt)
{
unsigned long freq_hz = freq_khz * 1000;
int ret;
/* Skip voltage update if the opp table is not available */
if (!icc_scaling_enabled)
return dev_pm_opp_add(cpu_dev, freq_hz, volt);
ret = dev_pm_opp_adjust_voltage(cpu_dev, freq_hz, volt, volt, volt);
if (ret) {
dev_err(cpu_dev, "Voltage update failed freq=%ld\n", freq_khz);
return ret;
}
return dev_pm_opp_enable(cpu_dev, freq_hz);
}
static int qcom_cpufreq_hw_target_index(struct cpufreq_policy *policy,
unsigned int index)
{
struct qcom_cpufreq_data *data = policy->driver_data;
const struct qcom_cpufreq_soc_data *soc_data = qcom_cpufreq.soc_data;
unsigned long freq = policy->freq_table[index].frequency;
unsigned int i;
writel_relaxed(index, data->base + soc_data->reg_perf_state);
if (data->per_core_dcvs)
for (i = 1; i < cpumask_weight(policy->related_cpus); i++)
writel_relaxed(index, data->base + soc_data->reg_perf_state + i * 4);
if (icc_scaling_enabled)
qcom_cpufreq_set_bw(policy, freq);
return 0;
}
static unsigned long qcom_lmh_get_throttle_freq(struct qcom_cpufreq_data *data)
{
unsigned int lval;
if (qcom_cpufreq.soc_data->reg_current_vote)
lval = readl_relaxed(data->base + qcom_cpufreq.soc_data->reg_current_vote) & 0x3ff;
else
lval = readl_relaxed(data->base + qcom_cpufreq.soc_data->reg_domain_state) & 0xff;
return lval * xo_rate;
}
/* Get the frequency requested by the cpufreq core for the CPU */
static unsigned int qcom_cpufreq_get_freq(unsigned int cpu)
{
struct qcom_cpufreq_data *data;
const struct qcom_cpufreq_soc_data *soc_data;
struct cpufreq_policy *policy;
unsigned int index;
policy = cpufreq_cpu_get_raw(cpu);
if (!policy)
return 0;
data = policy->driver_data;
soc_data = qcom_cpufreq.soc_data;
index = readl_relaxed(data->base + soc_data->reg_perf_state);
index = min(index, LUT_MAX_ENTRIES - 1);
return policy->freq_table[index].frequency;
}
static unsigned int qcom_cpufreq_hw_get(unsigned int cpu)
{
struct qcom_cpufreq_data *data;
struct cpufreq_policy *policy;
policy = cpufreq_cpu_get_raw(cpu);
if (!policy)
return 0;
data = policy->driver_data;
if (data->throttle_irq >= 0)
return qcom_lmh_get_throttle_freq(data) / HZ_PER_KHZ;
return qcom_cpufreq_get_freq(cpu);
}
static unsigned int qcom_cpufreq_hw_fast_switch(struct cpufreq_policy *policy,
unsigned int target_freq)
{
struct qcom_cpufreq_data *data = policy->driver_data;
const struct qcom_cpufreq_soc_data *soc_data = qcom_cpufreq.soc_data;
unsigned int index;
unsigned int i;
index = policy->cached_resolved_idx;
writel_relaxed(index, data->base + soc_data->reg_perf_state);
if (data->per_core_dcvs)
for (i = 1; i < cpumask_weight(policy->related_cpus); i++)
writel_relaxed(index, data->base + soc_data->reg_perf_state + i * 4);
cpufreq: move invariance setter calls in cpufreq core To properly scale its per-entity load-tracking signals, the task scheduler needs to be given a frequency scale factor, i.e. some image of the current frequency the CPU is running at. Currently, this scale can be computed either by using counters (APERF/MPERF on x86, AMU on arm64), or by piggy-backing on the frequency selection done by cpufreq. For the latter, drivers have to explicitly set the scale factor themselves, despite it being purely boiler-plate code: the required information depends entirely on the kind of frequency switch callback implemented by the driver, i.e. either of: target_index(), target(), fast_switch() and setpolicy(). The fitness of those callbacks with regard to driving the Frequency Invariance Engine (FIE) is studied below: target_index() ============== Documentation states that the chosen frequency "must be determined by freq_table[index].frequency". It isn't clear if it *has* to be that frequency, or if it can use that frequency value to do some computation that ultimately leads to a different frequency selection. All drivers go for the former, while the vexpress-spc-cpufreq has an atypical implementation which is handled separately. Therefore, the hook works on the assumption the core can use freq_table[index].frequency. target() ======= This has been flagged as deprecated since: commit 9c0ebcf78fde ("cpufreq: Implement light weight ->target_index() routine") It also doesn't have that many users: gx-suspmod.c:439: .target = cpufreq_gx_target, s3c24xx-cpufreq.c:428: .target = s3c_cpufreq_target, intel_pstate.c:2528: .target = intel_cpufreq_target, cppc_cpufreq.c:401: .target = cppc_cpufreq_set_target, cpufreq-nforce2.c:371: .target = nforce2_target, sh-cpufreq.c:163: .target = sh_cpufreq_target, pcc-cpufreq.c:573: .target = pcc_cpufreq_target, Similarly to the path taken for target_index() calls in the cpufreq core during a frequency change, all of the drivers above will mark the end of a frequency change by a call to cpufreq_freq_transition_end(). Therefore, cpufreq_freq_transition_end() can be used as the location for the arch_set_freq_scale() call to potentially inform the scheduler of the frequency change. This change maintains the previous functionality for the drivers that implement the target_index() callback, while also adding support for the few drivers that implement the deprecated target() callback. fast_switch() ============= This callback *has* to return the frequency that was selected. setpolicy() =========== This callback does not have any designated way of informing what was the end choice. But there are only two drivers using setpolicy(), and none of them have current FIE support: drivers/cpufreq/longrun.c:281: .setpolicy = longrun_set_policy, drivers/cpufreq/intel_pstate.c:2215: .setpolicy = intel_pstate_set_policy, The intel_pstate is known to use counter-driven frequency invariance. Conclusion ========== Given that the significant majority of current FIE enabled drivers use callbacks that lend themselves to triggering the setting of the FIE scale factor in a generic way, move the invariance setter calls to cpufreq core. As a result of setting the frequency scale factor in cpufreq core, after callbacks that lend themselves to trigger it, remove this functionality from the driver side. To be noted that despite marking a successful frequency change, many cpufreq drivers will consider the new frequency as the requested frequency, although this is might not be the one granted by the hardware. Therefore, the call to arch_set_freq_scale() is a "best effort" one, and it is up to the architecture if the new frequency is used in the new frequency scale factor setting (determined by the implementation of arch_set_freq_scale()) or eventually used by the scheduler (determined by the implementation of arch_scale_freq_capacity()). The architecture is in a better position to decide if it has better methods to obtain more accurate information regarding the current frequency and use that information instead (for example, the use of counters). Also, the implementation to arch_set_freq_scale() will now have to handle error conditions (current frequency == 0) in order to prevent the overhead in cpufreq core when the default arch_set_freq_scale() implementation is used. Signed-off-by: Ionela Voinescu <ionela.voinescu@arm.com> Suggested-by: Valentin Schneider <valentin.schneider@arm.com> Acked-by: Viresh Kumar <viresh.kumar@linaro.org> Acked-by: Sudeep Holla <sudeep.holla@arm.com> Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2020-09-02 04:55:46 +08:00
return policy->freq_table[index].frequency;
}
static int qcom_cpufreq_hw_read_lut(struct device *cpu_dev,
struct cpufreq_policy *policy)
{
u32 data, src, lval, i, core_count, prev_freq = 0, freq;
u32 volt;
struct cpufreq_frequency_table *table;
struct dev_pm_opp *opp;
unsigned long rate;
int ret;
struct qcom_cpufreq_data *drv_data = policy->driver_data;
const struct qcom_cpufreq_soc_data *soc_data = qcom_cpufreq.soc_data;
table = kcalloc(LUT_MAX_ENTRIES + 1, sizeof(*table), GFP_KERNEL);
if (!table)
return -ENOMEM;
ret = dev_pm_opp_of_add_table(cpu_dev);
if (!ret) {
/* Disable all opps and cross-validate against LUT later */
icc_scaling_enabled = true;
for (rate = 0; ; rate++) {
opp = dev_pm_opp_find_freq_ceil(cpu_dev, &rate);
if (IS_ERR(opp))
break;
dev_pm_opp_put(opp);
dev_pm_opp_disable(cpu_dev, rate);
}
} else if (ret != -ENODEV) {
dev_err(cpu_dev, "Invalid opp table in device tree\n");
kfree(table);
return ret;
} else {
policy->fast_switch_possible = true;
icc_scaling_enabled = false;
}
for (i = 0; i < LUT_MAX_ENTRIES; i++) {
data = readl_relaxed(drv_data->base + soc_data->reg_freq_lut +
i * soc_data->lut_row_size);
src = FIELD_GET(LUT_SRC, data);
lval = FIELD_GET(LUT_L_VAL, data);
core_count = FIELD_GET(LUT_CORE_COUNT, data);
data = readl_relaxed(drv_data->base + soc_data->reg_volt_lut +
i * soc_data->lut_row_size);
volt = FIELD_GET(LUT_VOLT, data) * 1000;
if (src)
freq = xo_rate * lval / 1000;
else
freq = cpu_hw_rate / 1000;
if (freq != prev_freq && core_count != LUT_TURBO_IND) {
if (!qcom_cpufreq_update_opp(cpu_dev, freq, volt)) {
table[i].frequency = freq;
dev_dbg(cpu_dev, "index=%d freq=%d, core_count %d\n", i,
freq, core_count);
} else {
dev_warn(cpu_dev, "failed to update OPP for freq=%d\n", freq);
table[i].frequency = CPUFREQ_ENTRY_INVALID;
}
} else if (core_count == LUT_TURBO_IND) {
table[i].frequency = CPUFREQ_ENTRY_INVALID;
}
/*
* Two of the same frequencies with the same core counts means
* end of table
*/
if (i > 0 && prev_freq == freq) {
struct cpufreq_frequency_table *prev = &table[i - 1];
/*
* Only treat the last frequency that might be a boost
* as the boost frequency
*/
if (prev->frequency == CPUFREQ_ENTRY_INVALID) {
if (!qcom_cpufreq_update_opp(cpu_dev, prev_freq, volt)) {
prev->frequency = prev_freq;
prev->flags = CPUFREQ_BOOST_FREQ;
} else {
dev_warn(cpu_dev, "failed to update OPP for freq=%d\n",
freq);
}
}
break;
}
prev_freq = freq;
}
table[i].frequency = CPUFREQ_TABLE_END;
policy->freq_table = table;
dev_pm_opp_set_sharing_cpus(cpu_dev, policy->cpus);
return 0;
}
static void qcom_get_related_cpus(int index, struct cpumask *m)
{
struct device_node *cpu_np;
struct of_phandle_args args;
int cpu, ret;
for_each_possible_cpu(cpu) {
cpu_np = of_cpu_device_node_get(cpu);
if (!cpu_np)
continue;
ret = of_parse_phandle_with_args(cpu_np, "qcom,freq-domain",
"#freq-domain-cells", 0,
&args);
of_node_put(cpu_np);
if (ret < 0)
continue;
if (index == args.args[0])
cpumask_set_cpu(cpu, m);
}
}
static void qcom_lmh_dcvs_notify(struct qcom_cpufreq_data *data)
{
struct cpufreq_policy *policy = data->policy;
cpufreq: qcom-hw: fix the race between LMH worker and cpuhp The driver would disable the worker when cpu is being put offline, but it happens closer to the end of cpufreq_offline(). The function qcom_lmh_dcvs_poll() can be running in parallel with this, when policy->cpus already has been updated. Read policy->related_cpus instead. [ 37.122433] ------------[ cut here ]------------ [ 37.127225] WARNING: CPU: 0 PID: 187 at drivers/base/arch_topology.c:180 topology_update_thermal_pressure+0xec/0x100 [ 37.138098] Modules linked in: [ 37.141279] CPU: 0 PID: 187 Comm: kworker/0:3 Tainted: G S 5.17.0-rc6-00389-g37c83d0b8710-dirty #713 [ 37.158306] Workqueue: events qcom_lmh_dcvs_poll [ 37.163095] pstate: 60400005 (nZCv daif +PAN -UAO -TCO -DIT -SSBS BTYPE=--) [ 37.170278] pc : topology_update_thermal_pressure+0xec/0x100 [ 37.176131] lr : topology_update_thermal_pressure+0x20/0x100 [ 37.181977] sp : ffff800009b6bce0 [ 37.185402] x29: ffff800009b6bce0 x28: ffffd87abe92b000 x27: ffff04bd7292e205 [ 37.192792] x26: ffffd87abe930af8 x25: ffffd87abe94e4c8 x24: 0000000000000000 [ 37.200180] x23: ffff04bb01177018 x22: ffff04bb011770c0 x21: ffff04bb01177000 [ 37.207567] x20: ffff04bb0a419000 x19: 00000000000c4e00 x18: 0000000000000000 [ 37.214954] x17: 000000040044ffff x16: 004000b2b5503510 x15: 0000006aaa1326d2 [ 37.222333] x14: 0000000000000232 x13: 0000000000000001 x12: 0000000000000040 [ 37.229718] x11: ffff04bb00400000 x10: 968f57bd39f701c8 x9 : ffff04bb0acc8674 [ 37.237095] x8 : fefefefefefefeff x7 : 0000000000000018 x6 : ffffd87abd90092c [ 37.244478] x5 : 0000000000000016 x4 : 0000000000000000 x3 : 0000000000000100 [ 37.251852] x2 : ffff04bb0a419020 x1 : 0000000000000100 x0 : 0000000000000100 [ 37.259235] Call trace: [ 37.261771] topology_update_thermal_pressure+0xec/0x100 [ 37.267266] qcom_lmh_dcvs_poll+0xbc/0x154 [ 37.271505] process_one_work+0x288/0x69c [ 37.275654] worker_thread+0x74/0x470 [ 37.279450] kthread+0xfc/0x100 [ 37.282712] ret_from_fork+0x10/0x20 [ 37.286417] irq event stamp: 74 [ 37.289664] hardirqs last enabled at (73): [<ffffd87abdd78af4>] _raw_spin_unlock_irq+0x44/0x80 [ 37.298632] hardirqs last disabled at (74): [<ffffd87abdd71fc0>] __schedule+0x710/0xa10 [ 37.306885] softirqs last enabled at (58): [<ffffd87abcc90410>] _stext+0x410/0x588 [ 37.314778] softirqs last disabled at (51): [<ffffd87abcd1bf68>] __irq_exit_rcu+0x158/0x174 [ 37.323386] ---[ end trace 0000000000000000 ]--- Fixes: 275157b367f4 ("cpufreq: qcom-cpufreq-hw: Add dcvs interrupt support") Signed-off-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org> Reviewed-by: Bjorn Andersson <bjorn.andersson@linaro.org> Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
2022-03-26 23:51:51 +08:00
int cpu = cpumask_first(policy->related_cpus);
struct device *dev = get_cpu_device(cpu);
cpufreq: qcom-cpufreq-hw: Use new thermal pressure update function Thermal pressure provides a new API, which allows to use CPU frequency as an argument. That removes the need of local conversion to capacity. Use this new API and remove old local conversion code. The new arch_update_thermal_pressure() also accepts boost frequencies, which solves issue in the driver code with wrong reduced capacity calculation. The reduced capacity was calculated wrongly due to 'policy->cpuinfo.max_freq' used as a divider. The value present there was actually the boost frequency. Thus, even a normal maximum frequency value which corresponds to max CPU capacity (arch_scale_cpu_capacity(cpu_id)) is not able to remove the capping. The second side effect which is solved is that the reduced frequency wasn't properly translated into the right reduced capacity, e.g. boost frequency = 3000MHz (stored in policy->cpuinfo.max_freq) max normal frequency = 2500MHz (which is 1024 capacity) 2nd highest frequency = 2000MHz (which translates to 819 capacity) Then in a scenario when the 'throttled_freq' max allowed frequency was 2000MHz the driver translated it into 682 capacity: capacity = 1024 * 2000 / 3000 = 682 Then set the pressure value bigger than actually applied by the HW: max_capacity - capacity => 1024 - 682 = 342 (<- thermal pressure) Which was causing higher throttling and misleading task scheduler about available CPU capacity. A proper calculation in such case should be: capacity = 1024 * 2000 / 2500 = 819 1024 - 819 = 205 (<- thermal pressure) This patch relies on the new arch_update_thermal_pressure() handling correctly such use case (with boost frequencies). Signed-off-by: Lukasz Luba <lukasz.luba@arm.com> Reviewed-by: Thara Gopinath <thara.gopinath@linaro.org> Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
2021-11-10 03:57:13 +08:00
unsigned long freq_hz, throttled_freq;
struct dev_pm_opp *opp;
/*
* Get the h/w throttled frequency, normalize it using the
* registered opp table and use it to calculate thermal pressure.
*/
freq_hz = qcom_lmh_get_throttle_freq(data);
opp = dev_pm_opp_find_freq_floor(dev, &freq_hz);
if (IS_ERR(opp) && PTR_ERR(opp) == -ERANGE)
cpufreq: qcom-hw: fix the opp entries refcounting The qcom_lmh_dcvs_notify() will get the dev_pm_opp instance for throttling, but will not put it, ending up with leaking a reference count and the following backtrace when putting the CPU offline. Correctly put the reference count of the returned opp instance. [ 84.418025] ------------[ cut here ]------------ [ 84.422770] WARNING: CPU: 7 PID: 43 at drivers/opp/core.c:1396 _opp_table_kref_release+0x188/0x190 [ 84.431966] Modules linked in: [ 84.435106] CPU: 7 PID: 43 Comm: cpuhp/7 Tainted: G S 5.17.0-rc6-00388-g7cf3c0d89c44-dirty #721 [ 84.451631] pstate: 82400005 (Nzcv daif +PAN -UAO +TCO -DIT -SSBS BTYPE=--) [ 84.458781] pc : _opp_table_kref_release+0x188/0x190 [ 84.463878] lr : _opp_table_kref_release+0x78/0x190 [ 84.468885] sp : ffff80000841bc70 [ 84.472294] x29: ffff80000841bc70 x28: ffff6664afe3d000 x27: ffff1db6729e5908 [ 84.479621] x26: 0000000000000000 x25: 0000000000000000 x24: ffff1db6729e58e0 [ 84.486946] x23: ffff8000080a5000 x22: ffff1db40aad80e0 x21: ffff1db4002fec80 [ 84.494277] x20: ffff1db40aad8000 x19: ffffb751c3186300 x18: ffffffffffffffff [ 84.501603] x17: 5300326563697665 x16: 645f676e696c6f6f x15: 00001186c1df5448 [ 84.508928] x14: 00000000000002e9 x13: 0000000000000000 x12: 0000000000000000 [ 84.516256] x11: ffffb751c3186368 x10: ffffb751c39a2a70 x9 : 0000000000000000 [ 84.523585] x8 : ffff1db4008edf00 x7 : ffffb751c328c000 x6 : 0000000000000001 [ 84.530916] x5 : 0000000000040000 x4 : 0000000000000001 x3 : ffff1db4008edf00 [ 84.538247] x2 : 0000000000000000 x1 : ffff1db400aa6100 x0 : ffff1db40aad80d0 [ 84.545579] Call trace: [ 84.548101] _opp_table_kref_release+0x188/0x190 [ 84.552842] dev_pm_opp_remove_all_dynamic+0x8c/0xc0 [ 84.557949] qcom_cpufreq_hw_cpu_exit+0x30/0xdc [ 84.562608] cpufreq_offline.isra.0+0x1b4/0x1d8 [ 84.567270] cpuhp_cpufreq_offline+0x10/0x6c [ 84.571663] cpuhp_invoke_callback+0x16c/0x2b0 [ 84.576231] cpuhp_thread_fun+0x190/0x250 [ 84.580353] smpboot_thread_fn+0x12c/0x230 [ 84.584568] kthread+0xfc/0x100 [ 84.587810] ret_from_fork+0x10/0x20 [ 84.591490] irq event stamp: 3482 [ 84.594901] hardirqs last enabled at (3481): [<ffffb751c13c3db0>] call_rcu+0x39c/0x50c [ 84.603119] hardirqs last disabled at (3482): [<ffffb751c236b518>] el1_dbg+0x24/0x8c [ 84.611074] softirqs last enabled at (310): [<ffffb751c1290410>] _stext+0x410/0x588 [ 84.619028] softirqs last disabled at (305): [<ffffb751c131bf68>] __irq_exit_rcu+0x158/0x174 [ 84.627691] ---[ end trace 0000000000000000 ]--- Fixes: 275157b367f4 ("cpufreq: qcom-cpufreq-hw: Add dcvs interrupt support") Reported-by: kernel test robot <lkp@intel.com> Tested-by: Vladimir Zapolskiy <vladimir.zapolskiy@linaro.org> Reviewed-by: Vladimir Zapolskiy <vladimir.zapolskiy@linaro.org> Reviewed-by: Bjorn Andersson <bjorn.andersson@linaro.org> Signed-off-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org> Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
2022-03-26 23:51:52 +08:00
opp = dev_pm_opp_find_freq_ceil(dev, &freq_hz);
cpufreq: qcom-hw: fix the opp entries refcounting The qcom_lmh_dcvs_notify() will get the dev_pm_opp instance for throttling, but will not put it, ending up with leaking a reference count and the following backtrace when putting the CPU offline. Correctly put the reference count of the returned opp instance. [ 84.418025] ------------[ cut here ]------------ [ 84.422770] WARNING: CPU: 7 PID: 43 at drivers/opp/core.c:1396 _opp_table_kref_release+0x188/0x190 [ 84.431966] Modules linked in: [ 84.435106] CPU: 7 PID: 43 Comm: cpuhp/7 Tainted: G S 5.17.0-rc6-00388-g7cf3c0d89c44-dirty #721 [ 84.451631] pstate: 82400005 (Nzcv daif +PAN -UAO +TCO -DIT -SSBS BTYPE=--) [ 84.458781] pc : _opp_table_kref_release+0x188/0x190 [ 84.463878] lr : _opp_table_kref_release+0x78/0x190 [ 84.468885] sp : ffff80000841bc70 [ 84.472294] x29: ffff80000841bc70 x28: ffff6664afe3d000 x27: ffff1db6729e5908 [ 84.479621] x26: 0000000000000000 x25: 0000000000000000 x24: ffff1db6729e58e0 [ 84.486946] x23: ffff8000080a5000 x22: ffff1db40aad80e0 x21: ffff1db4002fec80 [ 84.494277] x20: ffff1db40aad8000 x19: ffffb751c3186300 x18: ffffffffffffffff [ 84.501603] x17: 5300326563697665 x16: 645f676e696c6f6f x15: 00001186c1df5448 [ 84.508928] x14: 00000000000002e9 x13: 0000000000000000 x12: 0000000000000000 [ 84.516256] x11: ffffb751c3186368 x10: ffffb751c39a2a70 x9 : 0000000000000000 [ 84.523585] x8 : ffff1db4008edf00 x7 : ffffb751c328c000 x6 : 0000000000000001 [ 84.530916] x5 : 0000000000040000 x4 : 0000000000000001 x3 : ffff1db4008edf00 [ 84.538247] x2 : 0000000000000000 x1 : ffff1db400aa6100 x0 : ffff1db40aad80d0 [ 84.545579] Call trace: [ 84.548101] _opp_table_kref_release+0x188/0x190 [ 84.552842] dev_pm_opp_remove_all_dynamic+0x8c/0xc0 [ 84.557949] qcom_cpufreq_hw_cpu_exit+0x30/0xdc [ 84.562608] cpufreq_offline.isra.0+0x1b4/0x1d8 [ 84.567270] cpuhp_cpufreq_offline+0x10/0x6c [ 84.571663] cpuhp_invoke_callback+0x16c/0x2b0 [ 84.576231] cpuhp_thread_fun+0x190/0x250 [ 84.580353] smpboot_thread_fn+0x12c/0x230 [ 84.584568] kthread+0xfc/0x100 [ 84.587810] ret_from_fork+0x10/0x20 [ 84.591490] irq event stamp: 3482 [ 84.594901] hardirqs last enabled at (3481): [<ffffb751c13c3db0>] call_rcu+0x39c/0x50c [ 84.603119] hardirqs last disabled at (3482): [<ffffb751c236b518>] el1_dbg+0x24/0x8c [ 84.611074] softirqs last enabled at (310): [<ffffb751c1290410>] _stext+0x410/0x588 [ 84.619028] softirqs last disabled at (305): [<ffffb751c131bf68>] __irq_exit_rcu+0x158/0x174 [ 84.627691] ---[ end trace 0000000000000000 ]--- Fixes: 275157b367f4 ("cpufreq: qcom-cpufreq-hw: Add dcvs interrupt support") Reported-by: kernel test robot <lkp@intel.com> Tested-by: Vladimir Zapolskiy <vladimir.zapolskiy@linaro.org> Reviewed-by: Vladimir Zapolskiy <vladimir.zapolskiy@linaro.org> Reviewed-by: Bjorn Andersson <bjorn.andersson@linaro.org> Signed-off-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org> Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
2022-03-26 23:51:52 +08:00
if (IS_ERR(opp)) {
dev_warn(dev, "Can't find the OPP for throttling: %pe!\n", opp);
} else {
dev_pm_opp_put(opp);
}
throttled_freq = freq_hz / HZ_PER_KHZ;
freq_qos_update_request(&data->throttle_freq_req, throttled_freq);
/* Update thermal pressure (the boost frequencies are accepted) */
arch_update_thermal_pressure(policy->related_cpus, throttled_freq);
/*
* In the unlikely case policy is unregistered do not enable
* polling or h/w interrupt
*/
mutex_lock(&data->throttle_lock);
if (data->cancel_throttle)
goto out;
/*
* If h/w throttled frequency is higher than what cpufreq has requested
* for, then stop polling and switch back to interrupt mechanism.
*/
if (throttled_freq >= qcom_cpufreq_get_freq(cpu))
enable_irq(data->throttle_irq);
else
mod_delayed_work(system_highpri_wq, &data->throttle_work,
msecs_to_jiffies(10));
out:
mutex_unlock(&data->throttle_lock);
}
static void qcom_lmh_dcvs_poll(struct work_struct *work)
{
struct qcom_cpufreq_data *data;
data = container_of(work, struct qcom_cpufreq_data, throttle_work.work);
qcom_lmh_dcvs_notify(data);
}
static irqreturn_t qcom_lmh_dcvs_handle_irq(int irq, void *data)
{
struct qcom_cpufreq_data *c_data = data;
/* Disable interrupt and enable polling */
disable_irq_nosync(c_data->throttle_irq);
schedule_delayed_work(&c_data->throttle_work, 0);
if (qcom_cpufreq.soc_data->reg_intr_clr)
writel_relaxed(GT_IRQ_STATUS,
c_data->base + qcom_cpufreq.soc_data->reg_intr_clr);
return IRQ_HANDLED;
}
static const struct qcom_cpufreq_soc_data qcom_soc_data = {
.reg_enable = 0x0,
.reg_dcvs_ctrl = 0xbc,
.reg_freq_lut = 0x110,
.reg_volt_lut = 0x114,
.reg_current_vote = 0x704,
.reg_perf_state = 0x920,
.lut_row_size = 32,
};
static const struct qcom_cpufreq_soc_data epss_soc_data = {
.reg_enable = 0x0,
.reg_domain_state = 0x20,
.reg_dcvs_ctrl = 0xb0,
.reg_freq_lut = 0x100,
.reg_volt_lut = 0x200,
.reg_intr_clr = 0x308,
.reg_perf_state = 0x320,
.lut_row_size = 4,
};
static const struct of_device_id qcom_cpufreq_hw_match[] = {
{ .compatible = "qcom,cpufreq-hw", .data = &qcom_soc_data },
{ .compatible = "qcom,cpufreq-epss", .data = &epss_soc_data },
{}
};
MODULE_DEVICE_TABLE(of, qcom_cpufreq_hw_match);
static int qcom_cpufreq_hw_lmh_init(struct cpufreq_policy *policy, int index)
{
struct qcom_cpufreq_data *data = policy->driver_data;
struct platform_device *pdev = cpufreq_get_driver_data();
int ret;
/*
* Look for LMh interrupt. If no interrupt line is specified /
* if there is an error, allow cpufreq to be enabled as usual.
*/
data->throttle_irq = platform_get_irq_optional(pdev, index);
if (data->throttle_irq == -ENXIO)
return 0;
if (data->throttle_irq < 0)
return data->throttle_irq;
ret = freq_qos_add_request(&policy->constraints,
&data->throttle_freq_req, FREQ_QOS_MAX,
FREQ_QOS_MAX_DEFAULT_VALUE);
if (ret < 0) {
dev_err(&pdev->dev, "Failed to add freq constraint (%d)\n", ret);
return ret;
}
data->cancel_throttle = false;
data->policy = policy;
mutex_init(&data->throttle_lock);
INIT_DEFERRABLE_WORK(&data->throttle_work, qcom_lmh_dcvs_poll);
snprintf(data->irq_name, sizeof(data->irq_name), "dcvsh-irq-%u", policy->cpu);
ret = request_threaded_irq(data->throttle_irq, NULL, qcom_lmh_dcvs_handle_irq,
IRQF_ONESHOT | IRQF_NO_AUTOEN, data->irq_name, data);
if (ret) {
dev_err(&pdev->dev, "Error registering %s: %d\n", data->irq_name, ret);
return 0;
}
ret = irq_set_affinity_and_hint(data->throttle_irq, policy->cpus);
if (ret)
dev_err(&pdev->dev, "Failed to set CPU affinity of %s[%d]\n",
data->irq_name, data->throttle_irq);
return 0;
}
static int qcom_cpufreq_hw_cpu_online(struct cpufreq_policy *policy)
{
struct qcom_cpufreq_data *data = policy->driver_data;
struct platform_device *pdev = cpufreq_get_driver_data();
int ret;
if (data->throttle_irq <= 0)
return 0;
mutex_lock(&data->throttle_lock);
data->cancel_throttle = false;
mutex_unlock(&data->throttle_lock);
ret = irq_set_affinity_and_hint(data->throttle_irq, policy->cpus);
if (ret)
dev_err(&pdev->dev, "Failed to set CPU affinity of %s[%d]\n",
data->irq_name, data->throttle_irq);
return ret;
}
static int qcom_cpufreq_hw_cpu_offline(struct cpufreq_policy *policy)
{
struct qcom_cpufreq_data *data = policy->driver_data;
if (data->throttle_irq <= 0)
return 0;
mutex_lock(&data->throttle_lock);
data->cancel_throttle = true;
mutex_unlock(&data->throttle_lock);
cancel_delayed_work_sync(&data->throttle_work);
irq_set_affinity_and_hint(data->throttle_irq, NULL);
disable_irq_nosync(data->throttle_irq);
return 0;
}
static void qcom_cpufreq_hw_lmh_exit(struct qcom_cpufreq_data *data)
{
if (data->throttle_irq <= 0)
return;
freq_qos_remove_request(&data->throttle_freq_req);
free_irq(data->throttle_irq, data);
}
static int qcom_cpufreq_hw_cpu_init(struct cpufreq_policy *policy)
{
struct platform_device *pdev = cpufreq_get_driver_data();
struct device *dev = &pdev->dev;
struct of_phandle_args args;
struct device_node *cpu_np;
struct device *cpu_dev;
struct qcom_cpufreq_data *data;
int ret, index;
cpu_dev = get_cpu_device(policy->cpu);
if (!cpu_dev) {
pr_err("%s: failed to get cpu%d device\n", __func__,
policy->cpu);
return -ENODEV;
}
cpu_np = of_cpu_device_node_get(policy->cpu);
if (!cpu_np)
return -EINVAL;
ret = of_parse_phandle_with_args(cpu_np, "qcom,freq-domain",
"#freq-domain-cells", 0, &args);
of_node_put(cpu_np);
if (ret)
return ret;
index = args.args[0];
data = &qcom_cpufreq.data[index];
/* HW should be in enabled state to proceed */
if (!(readl_relaxed(data->base + qcom_cpufreq.soc_data->reg_enable) & 0x1)) {
dev_err(dev, "Domain-%d cpufreq hardware not enabled\n", index);
return -ENODEV;
}
if (readl_relaxed(data->base + qcom_cpufreq.soc_data->reg_dcvs_ctrl) & 0x1)
data->per_core_dcvs = true;
qcom_get_related_cpus(index, policy->cpus);
policy->driver_data = data;
policy->dvfs_possible_from_any_cpu = true;
ret = qcom_cpufreq_hw_read_lut(cpu_dev, policy);
if (ret) {
dev_err(dev, "Domain-%d failed to read LUT\n", index);
return ret;
}
ret = dev_pm_opp_get_opp_count(cpu_dev);
if (ret <= 0) {
dev_err(cpu_dev, "Failed to add OPPs\n");
return -ENODEV;
}
if (policy_has_boost_freq(policy)) {
ret = cpufreq_enable_boost_support();
if (ret)
dev_warn(cpu_dev, "failed to enable boost: %d\n", ret);
}
return qcom_cpufreq_hw_lmh_init(policy, index);
}
static int qcom_cpufreq_hw_cpu_exit(struct cpufreq_policy *policy)
{
struct device *cpu_dev = get_cpu_device(policy->cpu);
struct qcom_cpufreq_data *data = policy->driver_data;
cpufreq: qcom-hw: drop devm_xxx() calls from init/exit hooks Commit f17b3e44320b ("cpufreq: qcom-hw: Use devm_platform_ioremap_resource() to simplify code") introduces a regression on platforms using the driver, by failing to initialise a policy, when one is created post hotplug. When all the CPUs of a policy are hoptplugged out, the call to .exit() and later to devm_iounmap() does not release the memory region that was requested during devm_platform_ioremap_resource(). Therefore, a subsequent call to .init() will result in the following error, which will prevent a new policy to be initialised: [ 3395.915416] CPU4: shutdown [ 3395.938185] psci: CPU4 killed (polled 0 ms) [ 3399.071424] CPU5: shutdown [ 3399.094316] psci: CPU5 killed (polled 0 ms) [ 3402.139358] CPU6: shutdown [ 3402.161705] psci: CPU6 killed (polled 0 ms) [ 3404.742939] CPU7: shutdown [ 3404.765592] psci: CPU7 killed (polled 0 ms) [ 3411.492274] Detected VIPT I-cache on CPU4 [ 3411.492337] GICv3: CPU4: found redistributor 400 region 0:0x0000000017ae0000 [ 3411.492448] CPU4: Booted secondary processor 0x0000000400 [0x516f802d] [ 3411.503654] qcom-cpufreq-hw 17d43000.cpufreq: can't request region for resource [mem 0x17d45800-0x17d46bff] With that being said, the original code was tricky and skipping memory region request intentionally to hide this issue. The true cause is that those devm_xxx() device managed functions shouldn't be used for cpufreq init/exit hooks, because &pdev->dev is alive across the hooks and will not trigger auto resource free-up. Let's drop the use of device managed functions and manually allocate/free resources, so that the issue can be fixed properly. Cc: v5.10+ <stable@vger.kernel.org> # v5.10+ Fixes: f17b3e44320b ("cpufreq: qcom-hw: Use devm_platform_ioremap_resource() to simplify code") Suggested-by: Bjorn Andersson <bjorn.andersson@linaro.org> Signed-off-by: Shawn Guo <shawn.guo@linaro.org> Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
2021-01-19 10:39:25 +08:00
struct resource *res = data->res;
void __iomem *base = data->base;
dev_pm_opp_remove_all_dynamic(cpu_dev);
dev_pm_opp_of_cpumask_remove_table(policy->related_cpus);
qcom_cpufreq_hw_lmh_exit(data);
kfree(policy->freq_table);
cpufreq: qcom-hw: drop devm_xxx() calls from init/exit hooks Commit f17b3e44320b ("cpufreq: qcom-hw: Use devm_platform_ioremap_resource() to simplify code") introduces a regression on platforms using the driver, by failing to initialise a policy, when one is created post hotplug. When all the CPUs of a policy are hoptplugged out, the call to .exit() and later to devm_iounmap() does not release the memory region that was requested during devm_platform_ioremap_resource(). Therefore, a subsequent call to .init() will result in the following error, which will prevent a new policy to be initialised: [ 3395.915416] CPU4: shutdown [ 3395.938185] psci: CPU4 killed (polled 0 ms) [ 3399.071424] CPU5: shutdown [ 3399.094316] psci: CPU5 killed (polled 0 ms) [ 3402.139358] CPU6: shutdown [ 3402.161705] psci: CPU6 killed (polled 0 ms) [ 3404.742939] CPU7: shutdown [ 3404.765592] psci: CPU7 killed (polled 0 ms) [ 3411.492274] Detected VIPT I-cache on CPU4 [ 3411.492337] GICv3: CPU4: found redistributor 400 region 0:0x0000000017ae0000 [ 3411.492448] CPU4: Booted secondary processor 0x0000000400 [0x516f802d] [ 3411.503654] qcom-cpufreq-hw 17d43000.cpufreq: can't request region for resource [mem 0x17d45800-0x17d46bff] With that being said, the original code was tricky and skipping memory region request intentionally to hide this issue. The true cause is that those devm_xxx() device managed functions shouldn't be used for cpufreq init/exit hooks, because &pdev->dev is alive across the hooks and will not trigger auto resource free-up. Let's drop the use of device managed functions and manually allocate/free resources, so that the issue can be fixed properly. Cc: v5.10+ <stable@vger.kernel.org> # v5.10+ Fixes: f17b3e44320b ("cpufreq: qcom-hw: Use devm_platform_ioremap_resource() to simplify code") Suggested-by: Bjorn Andersson <bjorn.andersson@linaro.org> Signed-off-by: Shawn Guo <shawn.guo@linaro.org> Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
2021-01-19 10:39:25 +08:00
kfree(data);
iounmap(base);
release_mem_region(res->start, resource_size(res));
return 0;
}
static void qcom_cpufreq_ready(struct cpufreq_policy *policy)
{
struct qcom_cpufreq_data *data = policy->driver_data;
if (data->throttle_irq >= 0)
enable_irq(data->throttle_irq);
}
static struct freq_attr *qcom_cpufreq_hw_attr[] = {
&cpufreq_freq_attr_scaling_available_freqs,
&cpufreq_freq_attr_scaling_boost_freqs,
NULL
};
static struct cpufreq_driver cpufreq_qcom_hw_driver = {
cpufreq: Remove CPUFREQ_STICKY flag During cpufreq driver's registration, if the ->init() callback for all the CPUs fail then there is not much point in keeping the driver around as it will only account for more of unnecessary noise, for example cpufreq core will try to suspend/resume the driver which never got registered properly. The removal of such a driver is avoided if the driver carries the CPUFREQ_STICKY flag. This was added way back [1] in 2004 and perhaps no one should ever need it now. A lot of drivers do set this flag, probably because they just copied it from other drivers. This was added earlier for some platforms [2] because their cpufreq drivers were getting registered before the CPUs were registered with subsys framework. And hence they used to fail. The same isn't true anymore though. The current code flow in the kernel is: start_kernel() -> kernel_init() -> kernel_init_freeable() -> do_basic_setup() -> driver_init() -> cpu_dev_init() -> subsys_system_register() //For CPUs -> do_initcalls() -> cpufreq_register_driver() Clearly, the CPUs will always get registered with subsys framework before any cpufreq driver can get probed. Remove the flag and update the relevant drivers. Link: https://git.kernel.org/pub/scm/linux/kernel/git/tglx/history.git/commit/include/linux/cpufreq.h?id=7cc9f0d9a1ab04cedc60d64fd8dcf7df224a3b4d # [1] Link: https://git.kernel.org/pub/scm/linux/kernel/git/tglx/history.git/commit/arch/arm/mach-sa1100/cpu-sa1100.c?id=f59d3bbe35f6268d729f51be82af8325d62f20f5 # [2] Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org> Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2021-02-02 12:55:11 +08:00
.flags = CPUFREQ_NEED_INITIAL_FREQ_CHECK |
CPUFREQ_HAVE_GOVERNOR_PER_POLICY |
CPUFREQ_IS_COOLING_DEV,
.verify = cpufreq_generic_frequency_table_verify,
.target_index = qcom_cpufreq_hw_target_index,
.get = qcom_cpufreq_hw_get,
.init = qcom_cpufreq_hw_cpu_init,
.exit = qcom_cpufreq_hw_cpu_exit,
.online = qcom_cpufreq_hw_cpu_online,
.offline = qcom_cpufreq_hw_cpu_offline,
.register_em = cpufreq_register_em_with_opp,
.fast_switch = qcom_cpufreq_hw_fast_switch,
.name = "qcom-cpufreq-hw",
.attr = qcom_cpufreq_hw_attr,
.ready = qcom_cpufreq_ready,
};
static unsigned long qcom_cpufreq_hw_recalc_rate(struct clk_hw *hw, unsigned long parent_rate)
{
struct qcom_cpufreq_data *data = container_of(hw, struct qcom_cpufreq_data, cpu_clk);
return qcom_lmh_get_throttle_freq(data);
}
static const struct clk_ops qcom_cpufreq_hw_clk_ops = {
.recalc_rate = qcom_cpufreq_hw_recalc_rate,
};
static int qcom_cpufreq_hw_driver_probe(struct platform_device *pdev)
{
struct clk_hw_onecell_data *clk_data;
struct device *dev = &pdev->dev;
struct device_node *soc_node;
struct device *cpu_dev;
struct clk *clk;
int ret, i, num_domains, reg_sz;
clk = clk_get(dev, "xo");
if (IS_ERR(clk))
return PTR_ERR(clk);
xo_rate = clk_get_rate(clk);
clk_put(clk);
clk = clk_get(dev, "alternate");
if (IS_ERR(clk))
return PTR_ERR(clk);
cpu_hw_rate = clk_get_rate(clk) / CLK_HW_DIV;
clk_put(clk);
cpufreq_qcom_hw_driver.driver_data = pdev;
/* Check for optional interconnect paths on CPU0 */
cpu_dev = get_cpu_device(0);
if (!cpu_dev)
return -EPROBE_DEFER;
ret = dev_pm_opp_of_find_icc_paths(cpu_dev, NULL);
if (ret)
return ret;
/* Allocate qcom_cpufreq_data based on the available frequency domains in DT */
soc_node = of_get_parent(dev->of_node);
if (!soc_node)
return -EINVAL;
ret = of_property_read_u32(soc_node, "#address-cells", &reg_sz);
if (ret)
goto of_exit;
ret = of_property_read_u32(soc_node, "#size-cells", &i);
if (ret)
goto of_exit;
reg_sz += i;
num_domains = of_property_count_elems_of_size(dev->of_node, "reg", sizeof(u32) * reg_sz);
if (num_domains <= 0)
return num_domains;
qcom_cpufreq.data = devm_kzalloc(dev, sizeof(struct qcom_cpufreq_data) * num_domains,
GFP_KERNEL);
if (!qcom_cpufreq.data)
return -ENOMEM;
qcom_cpufreq.soc_data = of_device_get_match_data(dev);
if (!qcom_cpufreq.soc_data)
return -ENODEV;
clk_data = devm_kzalloc(dev, struct_size(clk_data, hws, num_domains), GFP_KERNEL);
if (!clk_data)
return -ENOMEM;
clk_data->num = num_domains;
for (i = 0; i < num_domains; i++) {
struct qcom_cpufreq_data *data = &qcom_cpufreq.data[i];
struct clk_init_data clk_init = {};
struct resource *res;
void __iomem *base;
base = devm_platform_get_and_ioremap_resource(pdev, i, &res);
if (IS_ERR(base)) {
dev_err(dev, "Failed to map resource %pR\n", res);
return PTR_ERR(base);
}
data->base = base;
data->res = res;
/* Register CPU clock for each frequency domain */
clk_init.name = kasprintf(GFP_KERNEL, "qcom_cpufreq%d", i);
if (!clk_init.name)
return -ENOMEM;
clk_init.flags = CLK_GET_RATE_NOCACHE;
clk_init.ops = &qcom_cpufreq_hw_clk_ops;
data->cpu_clk.init = &clk_init;
ret = devm_clk_hw_register(dev, &data->cpu_clk);
if (ret < 0) {
dev_err(dev, "Failed to register clock %d: %d\n", i, ret);
kfree(clk_init.name);
return ret;
}
clk_data->hws[i] = &data->cpu_clk;
kfree(clk_init.name);
}
ret = devm_of_clk_add_hw_provider(dev, of_clk_hw_onecell_get, clk_data);
if (ret < 0) {
dev_err(dev, "Failed to add clock provider\n");
return ret;
}
ret = cpufreq_register_driver(&cpufreq_qcom_hw_driver);
if (ret)
dev_err(dev, "CPUFreq HW driver failed to register\n");
else
dev_dbg(dev, "QCOM CPUFreq HW driver initialized\n");
of_exit:
of_node_put(soc_node);
return ret;
}
static int qcom_cpufreq_hw_driver_remove(struct platform_device *pdev)
{
cpufreq_unregister_driver(&cpufreq_qcom_hw_driver);
return 0;
}
static struct platform_driver qcom_cpufreq_hw_driver = {
.probe = qcom_cpufreq_hw_driver_probe,
.remove = qcom_cpufreq_hw_driver_remove,
.driver = {
.name = "qcom-cpufreq-hw",
.of_match_table = qcom_cpufreq_hw_match,
},
};
static int __init qcom_cpufreq_hw_init(void)
{
return platform_driver_register(&qcom_cpufreq_hw_driver);
}
postcore_initcall(qcom_cpufreq_hw_init);
static void __exit qcom_cpufreq_hw_exit(void)
{
platform_driver_unregister(&qcom_cpufreq_hw_driver);
}
module_exit(qcom_cpufreq_hw_exit);
MODULE_DESCRIPTION("QCOM CPUFREQ HW Driver");
MODULE_LICENSE("GPL v2");