Re: [PATCH] aerdrv: Move cper_print_pcie() out of interrupt context
From: Rafael J. Wysocki
Date: Wed May 08 2013 - 17:53:04 EST
On Wednesday, May 08, 2013 11:15:19 AM Lance Ortiz wrote:
> The following warning was seen on 3.9 when a corrected PCIe error was being
> handled by the AER subsystem.
>
> WARNING: at .../drivers/pci/search.c:214 pci_get_dev_by_id+0x8a/0x90()
>
> This occurred because code was added to the function cper_print_pcie() that
> calls the pci_get_domain_bus_and_slot() function.
Do you know which commit added that code?
> cper_print_pcie() is called
> in an interrupt context and pci_get* functions are not supposed to be called
> in that context hence the warning.
>
> The solution is to move the call to cper_print_aer() out of the interrupt
> context and into aer_recover_queue() to avoid any warnings when calling
> pci_get* functions.
The way the changes are described here isn't particularly clear to me. I'd say
something like
If cper_print_aer() is called by aer_recover_work_func(), there won't be any
reason to call it from cper_print_pcie() any more, in which case all of the
problematic code needed only to prepare for the cper_print_aer() call,
including the invocation of pci_get_domain_bus_and_slot() causing the warning
to be printed, may be removed from there. Make that happen."
Also, since aer_recover_work_func() is going to be the only existing caller of
cper_print_aer() after this change, as far as I can say, and it doesn't use the
function's first argument, that argument should be dropped entirely.
Thanks,
Rafael
> Signed-off-by: Lance Ortiz <lance.ortiz@xxxxxx>
> ---
>
> drivers/acpi/apei/cper.c | 18 ------------------
> drivers/acpi/apei/ghes.c | 3 ++-
> drivers/pci/pcie/aer/aerdrv_core.c | 6 +++++-
> include/linux/aer.h | 2 +-
> 4 files changed, 8 insertions(+), 21 deletions(-)
>
> diff --git a/drivers/acpi/apei/cper.c b/drivers/acpi/apei/cper.c
> index 1e5d8a4..8713229 100644
> --- a/drivers/acpi/apei/cper.c
> +++ b/drivers/acpi/apei/cper.c
> @@ -250,10 +250,6 @@ static const char *cper_pcie_port_type_strs[] = {
> static void cper_print_pcie(const char *pfx, const struct cper_sec_pcie *pcie,
> const struct acpi_hest_generic_data *gdata)
> {
> -#ifdef CONFIG_ACPI_APEI_PCIEAER
> - struct pci_dev *dev;
> -#endif
> -
> if (pcie->validation_bits & CPER_PCIE_VALID_PORT_TYPE)
> printk("%s""port_type: %d, %s\n", pfx, pcie->port_type,
> pcie->port_type < ARRAY_SIZE(cper_pcie_port_type_strs) ?
> @@ -285,20 +281,6 @@ static void cper_print_pcie(const char *pfx, const struct cper_sec_pcie *pcie,
> printk(
> "%s""bridge: secondary_status: 0x%04x, control: 0x%04x\n",
> pfx, pcie->bridge.secondary_status, pcie->bridge.control);
> -#ifdef CONFIG_ACPI_APEI_PCIEAER
> - dev = pci_get_domain_bus_and_slot(pcie->device_id.segment,
> - pcie->device_id.bus, pcie->device_id.function);
> - if (!dev) {
> - pr_err("PCI AER Cannot get PCI device %04x:%02x:%02x.%d\n",
> - pcie->device_id.segment, pcie->device_id.bus,
> - pcie->device_id.slot, pcie->device_id.function);
> - return;
> - }
> - if (pcie->validation_bits & CPER_PCIE_VALID_AER_INFO)
> - cper_print_aer(pfx, dev, gdata->error_severity,
> - (struct aer_capability_regs *) pcie->aer_info);
> - pci_dev_put(dev);
> -#endif
> }
>
> static const char *apei_estatus_section_flag_strs[] = {
> diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c
> index d668a8a..f2084b5 100644
> --- a/drivers/acpi/apei/ghes.c
> +++ b/drivers/acpi/apei/ghes.c
> @@ -454,7 +454,8 @@ static void ghes_do_proc(struct ghes *ghes,
> aer_severity = cper_severity_to_aer(sev);
> aer_recover_queue(pcie_err->device_id.segment,
> pcie_err->device_id.bus,
> - devfn, aer_severity);
> + devfn, aer_severity,
> + pcie_err->aer_info);
> }
>
> }
> diff --git a/drivers/pci/pcie/aer/aerdrv_core.c b/drivers/pci/pcie/aer/aerdrv_core.c
> index 564d97f..26aec0f 100644
> --- a/drivers/pci/pcie/aer/aerdrv_core.c
> +++ b/drivers/pci/pcie/aer/aerdrv_core.c
> @@ -582,6 +582,7 @@ struct aer_recover_entry
> u8 devfn;
> u16 domain;
> int severity;
> + u8 *regs;
> };
>
> static DEFINE_KFIFO(aer_recover_ring, struct aer_recover_entry,
> @@ -595,7 +596,7 @@ static DEFINE_SPINLOCK(aer_recover_ring_lock);
> static DECLARE_WORK(aer_recover_work, aer_recover_work_func);
>
> void aer_recover_queue(int domain, unsigned int bus, unsigned int devfn,
> - int severity)
> + int severity, u8 *aer_regs)
> {
> unsigned long flags;
> struct aer_recover_entry entry = {
> @@ -603,6 +604,7 @@ void aer_recover_queue(int domain, unsigned int bus, unsigned int devfn,
> .devfn = devfn,
> .domain = domain,
> .severity = severity,
> + .regs = aer_regs,
> };
>
> spin_lock_irqsave(&aer_recover_ring_lock, flags);
> @@ -629,6 +631,8 @@ static void aer_recover_work_func(struct work_struct *work)
> PCI_SLOT(entry.devfn), PCI_FUNC(entry.devfn));
> continue;
> }
> + cper_print_aer("", pdev, entry.severity,
> + (struct aer_capability_regs *)entry.regs);
> do_recovery(pdev, entry.severity);
> pci_dev_put(pdev);
> }
> diff --git a/include/linux/aer.h b/include/linux/aer.h
> index ec10e1b..a5c1583 100644
> --- a/include/linux/aer.h
> +++ b/include/linux/aer.h
> @@ -53,6 +53,6 @@ extern void cper_print_aer(const char *prefix, struct pci_dev *dev,
> int cper_severity, struct aer_capability_regs *aer);
> extern int cper_severity_to_aer(int cper_severity);
> extern void aer_recover_queue(int domain, unsigned int bus, unsigned int devfn,
> - int severity);
> + int severity, u8 *aer_regs);
> #endif //_AER_H_
>
>
> --
> To unsubscribe from this list: send the line "unsubscribe linux-acpi" in
> the body of a message to majordomo@xxxxxxxxxxxxxxx
> More majordomo info at http://vger.kernel.org/majordomo-info.html
--
I speak only for myself.
Rafael J. Wysocki, Intel Open Source Technology Center.
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/