Re: [PATCH] hwmon: (coretemp) remove duplicated coretemp for same core id

From: Guenter Roeck
Date: Tue Oct 17 2017 - 11:25:59 EST


On Tue, Oct 17, 2017 at 04:44:50PM +0800, shuwang@xxxxxxxxxx wrote:
> From: Shu Wang <shuwang@xxxxxxxxxx>
>
> Fix kernel warning on my 4cpus 2core_id system. The cpu0 and cpu1 have
> same core_id 0, so both cpu0 and cpu1 will try to create file temp2_label
> when it's online.
>
What system/cpu is that ?

Normally I would assume that each CPU (package) instantiates
a separate instance of the driver.

> - coretemp_cpu_online(cpu=0)
> - create_core_data(cpu=0, attr_no=2)
> - create_core_attrs(attr_no=2)
> - coretemp_cpu_online(cpu=1)
> - create_core_data(cpu=1, attr_no=2)
> - create_core_attrs(attr_no=2)
>
> $ grep -e processor -e 'core id' /proc/cpuinfo
> processor : 0
> core id : 0
> processor : 1
> core id : 0
> processor : 2
> core id : 1
> processor : 3
> core id : 1

Complete output of /proc/cpuinfo might be helpful.

>
> dmesg:
> sysfs: cannot create duplicate filename '/devices/platform/coretemp.0/hwmon/hwmon3/temp2_label'
> sysfs: cannot create duplicate filename '/devices/platform/coretemp.0/hwmon/hwmon3/temp3_label'
> WARNING: CPU: 3 PID: 27 at fs/sysfs/dir.c:31 sysfs_warn_dup+0x58/0x70
> Call Trace:
> sysfs_add_file_mode_ns+0x170/0x180
> internal_create_group+0xe3/0x2c0
> sysfs_create_group+0x13/0x20
> create_core_data+0x3ab/0x5e0 [coretemp]
> coretemp_cpu_online+0x14b/0x1f7 [coretemp]
> ? create_core_data+0x5e0/0x5e0 [coretemp]
> cpuhp_invoke_callback+0xae/0x5c0
> ? __schedule+0x295/0x880
> cpuhp_thread_fun+0xcb/0x170
> smpboot_thread_fn+0x110/0x160
>
> Signed-off-by: Shu Wang <shuwang@xxxxxxxxxx>
> ---
> drivers/hwmon/coretemp.c | 26 +++++++++++++++-----------
> 1 file changed, 15 insertions(+), 11 deletions(-)
>
> diff --git a/drivers/hwmon/coretemp.c b/drivers/hwmon/coretemp.c
> index c13a4fd86b3c..2fb29ab1080b 100644
> --- a/drivers/hwmon/coretemp.c
> +++ b/drivers/hwmon/coretemp.c
> @@ -459,6 +459,17 @@ static struct temp_data *init_temp_data(unsigned int cpu, int pkg_flag)
> return tdata;
> }
>
> +static void coretemp_remove_core(struct platform_data *pdata, int indx)
> +{
> + struct temp_data *tdata = pdata->core_data[indx];
> +
> + /* Remove the sysfs attributes */
> + sysfs_remove_group(&pdata->hwmon_dev->kobj, &tdata->attr_group);
> +
> + kfree(pdata->core_data[indx]);
> + pdata->core_data[indx] = NULL;
> +}
> +
> static int create_core_data(struct platform_device *pdev, unsigned int cpu,
> int pkg_flag)
> {
> @@ -479,6 +490,10 @@ static int create_core_data(struct platform_device *pdev, unsigned int cpu,
> if (attr_no > MAX_CORE_DATA - 1)
> return -ERANGE;
>
> + tdata = pdata->core_data[attr_no];
> + if (tdata != NULL)
> + coretemp_remove_core(pdata, attr_no);
> +

That looks more like a hack than a fix. Presumably the other cpu/core
is still online ?

> tdata = init_temp_data(cpu, pkg_flag);
> if (!tdata)
> return -ENOMEM;
> @@ -527,17 +542,6 @@ coretemp_add_core(struct platform_device *pdev, unsigned int cpu, int pkg_flag)
> dev_err(&pdev->dev, "Adding Core %u failed\n", cpu);
> }
>
> -static void coretemp_remove_core(struct platform_data *pdata, int indx)
> -{
> - struct temp_data *tdata = pdata->core_data[indx];
> -
> - /* Remove the sysfs attributes */
> - sysfs_remove_group(&pdata->hwmon_dev->kobj, &tdata->attr_group);
> -
> - kfree(pdata->core_data[indx]);
> - pdata->core_data[indx] = NULL;
> -}
> -
> static int coretemp_probe(struct platform_device *pdev)
> {
> struct device *dev = &pdev->dev;
> --
> 2.13.5
>