Re: [PATCH 2/2] hwmon: (k10temp) Use API function to access System Management Network

[Guenter Roeck]

On 04/28/2018 06:54 PM, Guenter Roeck wrote:
> The SMN (System Management Network) on Family 17h AMD CPUs is also accessed
> from other drivers, specifically EDAC. Accessing it directly is racy.
> On top of that, accessing the SMN through root bridge 00:00 is wrong on
> multi-die CPUs and may result in reading the temperature from the wrong
> die. Use available API functions to fix the problem.
>
> For this to work, also change the Raven Ridge PCI device ID to point to
> Data Fabric Function 3, since this ID is used by the API functions to
> find the CPU node.
>
> Signed-off-by: Guenter Roeck <linux@xxxxxxxxxxxx>
> ---
>   drivers/hwmon/k10temp.c | 11 ++++++-----
>   1 file changed, 6 insertions(+), 5 deletions(-)
>
> diff --git a/drivers/hwmon/k10temp.c b/drivers/hwmon/k10temp.c
> index b06bb1f90853..00e785afae0d 100644
> --- a/drivers/hwmon/k10temp.c
> +++ b/drivers/hwmon/k10temp.c
> @@ -23,6 +23,7 @@
>   #include <linux/init.h>
>   #include <linux/module.h>
>   #include <linux/pci.h>
> +#include <asm/amd_nb.h>
>   #include <asm/processor.h>
>   
>   MODULE_DESCRIPTION("AMD Family 10h+ CPU core temperature monitor");
> @@ -40,8 +41,8 @@ static DEFINE_MUTEX(nb_smu_ind_mutex);
>   #define PCI_DEVICE_ID_AMD_17H_DF_F3	0x1463
>   #endif
>   
> -#ifndef PCI_DEVICE_ID_AMD_17H_RR_NB
> -#define PCI_DEVICE_ID_AMD_17H_RR_NB	0x15d0
> +#ifndef PCI_DEVICE_ID_AMD_17H_RR_DF_F3
> +#define PCI_DEVICE_ID_AMD_17H_RR_DF_F3	0x14eb

This should have been 0x15eb. I'll resend after a week or so, waiting for more feedback.

Guenter

>   #endif
>   
>   /* CPUID function 0x80000001, ebx */
> @@ -136,8 +137,8 @@ static void read_tempreg_nb_f15(struct pci_dev *pdev, u32 *regval)
>   
>   static void read_tempreg_nb_f17(struct pci_dev *pdev, u32 *regval)
>   {
> -	amd_nb_index_read(pdev, PCI_DEVFN(0, 0), 0x60,
> -			  F17H_M01H_REPORTED_TEMP_CTRL_OFFSET, regval);
> +	amd_smn_read(amd_pci_dev_to_node_id(pdev),
> +		     F17H_M01H_REPORTED_TEMP_CTRL_OFFSET, regval);
>   }
>   
>   static ssize_t temp1_input_show(struct device *dev,
> @@ -323,7 +324,7 @@ static const struct pci_device_id k10temp_id_table[] = {
>   	{ PCI_VDEVICE(AMD, PCI_DEVICE_ID_AMD_16H_NB_F3) },
>   	{ PCI_VDEVICE(AMD, PCI_DEVICE_ID_AMD_16H_M30H_NB_F3) },
>   	{ PCI_VDEVICE(AMD, PCI_DEVICE_ID_AMD_17H_DF_F3) },
> -	{ PCI_VDEVICE(AMD, PCI_DEVICE_ID_AMD_17H_RR_NB) },
> +	{ PCI_VDEVICE(AMD, PCI_DEVICE_ID_AMD_17H_RR_DF_F3) },
>   	{}
>   };
>   MODULE_DEVICE_TABLE(pci, k10temp_id_table);