Re: [PATCH RFC v4 2/9] powerpc/powernv/pci: Suppress an EEH error when reading an empty slot
On 3/5/19 9:14 AM, Oliver wrote:
> On Sat, Mar 2, 2019 at 3:04 AM Sergey Miroshnichenko
> wrote:
>>
>> Reading an empty slot returns all ones, which triggers a false
>> EEH error event on PowerNV. This patch unfreezes the bus where
>> it has happened.
>>
>> Signed-off-by: Sergey Miroshnichenko
>> ---
>> arch/powerpc/include/asm/ppc-pci.h | 1 +
>> arch/powerpc/kernel/pci_dn.c | 2 +-
>> arch/powerpc/platforms/powernv/pci.c | 34
>> 3 files changed, 32 insertions(+), 5 deletions(-)
>>
>> diff --git a/arch/powerpc/include/asm/ppc-pci.h
>> b/arch/powerpc/include/asm/ppc-pci.h
>> index f67da277d652..737393c54f58 100644
>> --- a/arch/powerpc/include/asm/ppc-pci.h
>> +++ b/arch/powerpc/include/asm/ppc-pci.h
>> @@ -40,6 +40,7 @@ void *traverse_pci_dn(struct pci_dn *root,
>> void *(*fn)(struct pci_dn *, void *),
>> void *data);
>> extern void pci_devs_phb_init_dynamic(struct pci_controller *phb);
>> +struct pci_dn *pci_bus_to_pdn(struct pci_bus *bus);
>>
>> /* From rtas_pci.h */
>> extern void init_pci_config_tokens (void);
>> diff --git a/arch/powerpc/kernel/pci_dn.c b/arch/powerpc/kernel/pci_dn.c
>> index ab147a1909c8..341ed71250f1 100644
>> --- a/arch/powerpc/kernel/pci_dn.c
>> +++ b/arch/powerpc/kernel/pci_dn.c
>> @@ -40,7 +40,7 @@
>> * one of PF's bridge. For other devices, their firmware
>> * data is linked to that of their bridge.
>> */
>> -static struct pci_dn *pci_bus_to_pdn(struct pci_bus *bus)
>> +struct pci_dn *pci_bus_to_pdn(struct pci_bus *bus)
>> {
>> struct pci_bus *pbus;
>> struct device_node *dn;
>> diff --git a/arch/powerpc/platforms/powernv/pci.c
>> b/arch/powerpc/platforms/powernv/pci.c
>> index 3260250d2029..73c2d0aed996 100644
>> --- a/arch/powerpc/platforms/powernv/pci.c
>> +++ b/arch/powerpc/platforms/powernv/pci.c
>> @@ -761,6 +761,21 @@ static inline pnv_pci_cfg_check(struct pci_dn *pdn)
>> }
>> #endif /* CONFIG_EEH */
>>
>> +static int get_bus_pe_number(struct pci_bus *bus)
>> +{
>> + struct pci_dn *pdn = pci_bus_to_pdn(bus);
>> + struct pci_dn *child;
>> +
>> + if (!pdn)
>> + return IODA_INVALID_PE;
>> +
>> + list_for_each_entry(child, >child_list, list)
>> + if (child->pe_number != IODA_INVALID_PE)
>> + return child->pe_number;
>> +
>> + return IODA_INVALID_PE;
>> +}
>> +
>> static int pnv_pci_read_config(struct pci_bus *bus,
>>unsigned int devfn,
>>int where, int size, u32 *val)
>> @@ -769,12 +784,23 @@ static int pnv_pci_read_config(struct pci_bus *bus,
>> struct pci_controller *hose = pci_bus_to_host(bus);
>> struct pnv_phb *phb = hose->private_data;
>> int ret;
>> + u32 empty_val = 0x;
>>
>> - *val = 0x;
>> + *val = empty_val;
>> pdn = pci_get_pdn_by_devfn(bus, devfn);
>> - if (!pdn)
>> - return pnv_pci_cfg_read_raw(phb->opal_id, bus->number, devfn,
>> - where, size, val);
>> + if (!pdn) {
>> + int pe_number = get_bus_pe_number(bus);
>> +
>> + ret = pnv_pci_cfg_read_raw(phb->opal_id, bus->number, devfn,
>> + where, size, val);
>> +
>> + if (!ret && (*val == empty_val) && phb->unfreeze_pe)
>
> Do this empty val check work when using 1 or 2 byte cfg accesses?
>
That was intentional because 0xff and 0x are valid values, but the
0x is the only reliable sign of an empty slot. And the kernel
pokes a slot by the pci_bus_generic_read_dev_vendor_id() function, which
in turn tries to pci_bus_read_config_dword(PCI_VENDOR_ID).
But I haven't tried actually to read 1-2 bytes from an empty slot to
test if that triggers an EEH. If it does, I'll change that to
EEH_IO_ERROR_VALUE(size).
>> + phb->unfreeze_pe(phb, (pe_number == IODA_INVALID_PE)
>> ?
>> +0xff : pe_number,
>
> Use phb->ioda.reserved_pe_idx rather than guessing that 0xff is safe
> to use. On P9 we have PHBs with 512 PEs and some older P8 firmware
> releases used 0 as the reserved PE rather than 0xff.
>
Thanks for the catch! I'll fix that in v5.
Best regards,
Serge
>> +OPAL_EEH_ACTION_CLEAR_FREEZE_ALL);
>> +
>> + return ret;
>> + }
>>
>> if (!pnv_pci_cfg_check(pdn))
>> return PCIBIOS_DEVICE_NOT_FOUND;
>> --
>> 2.20.1
>>
signature.asc
Description: OpenPGP digital signature
Re: [PATCH RFC v4 2/9] powerpc/powernv/pci: Suppress an EEH error when reading an empty slot
On Sat, Mar 2, 2019 at 3:04 AM Sergey Miroshnichenko
wrote:
>
> Reading an empty slot returns all ones, which triggers a false
> EEH error event on PowerNV. This patch unfreezes the bus where
> it has happened.
>
> Signed-off-by: Sergey Miroshnichenko
> ---
> arch/powerpc/include/asm/ppc-pci.h | 1 +
> arch/powerpc/kernel/pci_dn.c | 2 +-
> arch/powerpc/platforms/powernv/pci.c | 34
> 3 files changed, 32 insertions(+), 5 deletions(-)
>
> diff --git a/arch/powerpc/include/asm/ppc-pci.h
> b/arch/powerpc/include/asm/ppc-pci.h
> index f67da277d652..737393c54f58 100644
> --- a/arch/powerpc/include/asm/ppc-pci.h
> +++ b/arch/powerpc/include/asm/ppc-pci.h
> @@ -40,6 +40,7 @@ void *traverse_pci_dn(struct pci_dn *root,
> void *(*fn)(struct pci_dn *, void *),
> void *data);
> extern void pci_devs_phb_init_dynamic(struct pci_controller *phb);
> +struct pci_dn *pci_bus_to_pdn(struct pci_bus *bus);
>
> /* From rtas_pci.h */
> extern void init_pci_config_tokens (void);
> diff --git a/arch/powerpc/kernel/pci_dn.c b/arch/powerpc/kernel/pci_dn.c
> index ab147a1909c8..341ed71250f1 100644
> --- a/arch/powerpc/kernel/pci_dn.c
> +++ b/arch/powerpc/kernel/pci_dn.c
> @@ -40,7 +40,7 @@
> * one of PF's bridge. For other devices, their firmware
> * data is linked to that of their bridge.
> */
> -static struct pci_dn *pci_bus_to_pdn(struct pci_bus *bus)
> +struct pci_dn *pci_bus_to_pdn(struct pci_bus *bus)
> {
> struct pci_bus *pbus;
> struct device_node *dn;
> diff --git a/arch/powerpc/platforms/powernv/pci.c
> b/arch/powerpc/platforms/powernv/pci.c
> index 3260250d2029..73c2d0aed996 100644
> --- a/arch/powerpc/platforms/powernv/pci.c
> +++ b/arch/powerpc/platforms/powernv/pci.c
> @@ -761,6 +761,21 @@ static inline pnv_pci_cfg_check(struct pci_dn *pdn)
> }
> #endif /* CONFIG_EEH */
>
> +static int get_bus_pe_number(struct pci_bus *bus)
> +{
> + struct pci_dn *pdn = pci_bus_to_pdn(bus);
> + struct pci_dn *child;
> +
> + if (!pdn)
> + return IODA_INVALID_PE;
> +
> + list_for_each_entry(child, >child_list, list)
> + if (child->pe_number != IODA_INVALID_PE)
> + return child->pe_number;
> +
> + return IODA_INVALID_PE;
> +}
> +
> static int pnv_pci_read_config(struct pci_bus *bus,
>unsigned int devfn,
>int where, int size, u32 *val)
> @@ -769,12 +784,23 @@ static int pnv_pci_read_config(struct pci_bus *bus,
> struct pci_controller *hose = pci_bus_to_host(bus);
> struct pnv_phb *phb = hose->private_data;
> int ret;
> + u32 empty_val = 0x;
>
> - *val = 0x;
> + *val = empty_val;
> pdn = pci_get_pdn_by_devfn(bus, devfn);
> - if (!pdn)
> - return pnv_pci_cfg_read_raw(phb->opal_id, bus->number, devfn,
> - where, size, val);
> + if (!pdn) {
> + int pe_number = get_bus_pe_number(bus);
> +
> + ret = pnv_pci_cfg_read_raw(phb->opal_id, bus->number, devfn,
> + where, size, val);
> +
> + if (!ret && (*val == empty_val) && phb->unfreeze_pe)
Do this empty val check work when using 1 or 2 byte cfg accesses?
> + phb->unfreeze_pe(phb, (pe_number == IODA_INVALID_PE) ?
> +0xff : pe_number,
Use phb->ioda.reserved_pe_idx rather than guessing that 0xff is safe
to use. On P9 we have PHBs with 512 PEs and some older P8 firmware
releases used 0 as the reserved PE rather than 0xff.
> +OPAL_EEH_ACTION_CLEAR_FREEZE_ALL);
> +
> + return ret;
> + }
>
> if (!pnv_pci_cfg_check(pdn))
> return PCIBIOS_DEVICE_NOT_FOUND;
> --
> 2.20.1
>
[PATCH RFC v4 2/9] powerpc/powernv/pci: Suppress an EEH error when reading an empty slot
Reading an empty slot returns all ones, which triggers a false
EEH error event on PowerNV. This patch unfreezes the bus where
it has happened.
Signed-off-by: Sergey Miroshnichenko
---
arch/powerpc/include/asm/ppc-pci.h | 1 +
arch/powerpc/kernel/pci_dn.c | 2 +-
arch/powerpc/platforms/powernv/pci.c | 34
3 files changed, 32 insertions(+), 5 deletions(-)
diff --git a/arch/powerpc/include/asm/ppc-pci.h
b/arch/powerpc/include/asm/ppc-pci.h
index f67da277d652..737393c54f58 100644
--- a/arch/powerpc/include/asm/ppc-pci.h
+++ b/arch/powerpc/include/asm/ppc-pci.h
@@ -40,6 +40,7 @@ void *traverse_pci_dn(struct pci_dn *root,
void *(*fn)(struct pci_dn *, void *),
void *data);
extern void pci_devs_phb_init_dynamic(struct pci_controller *phb);
+struct pci_dn *pci_bus_to_pdn(struct pci_bus *bus);
/* From rtas_pci.h */
extern void init_pci_config_tokens (void);
diff --git a/arch/powerpc/kernel/pci_dn.c b/arch/powerpc/kernel/pci_dn.c
index ab147a1909c8..341ed71250f1 100644
--- a/arch/powerpc/kernel/pci_dn.c
+++ b/arch/powerpc/kernel/pci_dn.c
@@ -40,7 +40,7 @@
* one of PF's bridge. For other devices, their firmware
* data is linked to that of their bridge.
*/
-static struct pci_dn *pci_bus_to_pdn(struct pci_bus *bus)
+struct pci_dn *pci_bus_to_pdn(struct pci_bus *bus)
{
struct pci_bus *pbus;
struct device_node *dn;
diff --git a/arch/powerpc/platforms/powernv/pci.c
b/arch/powerpc/platforms/powernv/pci.c
index 3260250d2029..73c2d0aed996 100644
--- a/arch/powerpc/platforms/powernv/pci.c
+++ b/arch/powerpc/platforms/powernv/pci.c
@@ -761,6 +761,21 @@ static inline pnv_pci_cfg_check(struct pci_dn *pdn)
}
#endif /* CONFIG_EEH */
+static int get_bus_pe_number(struct pci_bus *bus)
+{
+ struct pci_dn *pdn = pci_bus_to_pdn(bus);
+ struct pci_dn *child;
+
+ if (!pdn)
+ return IODA_INVALID_PE;
+
+ list_for_each_entry(child, >child_list, list)
+ if (child->pe_number != IODA_INVALID_PE)
+ return child->pe_number;
+
+ return IODA_INVALID_PE;
+}
+
static int pnv_pci_read_config(struct pci_bus *bus,
unsigned int devfn,
int where, int size, u32 *val)
@@ -769,12 +784,23 @@ static int pnv_pci_read_config(struct pci_bus *bus,
struct pci_controller *hose = pci_bus_to_host(bus);
struct pnv_phb *phb = hose->private_data;
int ret;
+ u32 empty_val = 0x;
- *val = 0x;
+ *val = empty_val;
pdn = pci_get_pdn_by_devfn(bus, devfn);
- if (!pdn)
- return pnv_pci_cfg_read_raw(phb->opal_id, bus->number, devfn,
- where, size, val);
+ if (!pdn) {
+ int pe_number = get_bus_pe_number(bus);
+
+ ret = pnv_pci_cfg_read_raw(phb->opal_id, bus->number, devfn,
+ where, size, val);
+
+ if (!ret && (*val == empty_val) && phb->unfreeze_pe)
+ phb->unfreeze_pe(phb, (pe_number == IODA_INVALID_PE) ?
+0xff : pe_number,
+OPAL_EEH_ACTION_CLEAR_FREEZE_ALL);
+
+ return ret;
+ }
if (!pnv_pci_cfg_check(pdn))
return PCIBIOS_DEVICE_NOT_FOUND;
--
2.20.1
