diff options
| author | Prarit Bhargava <prarit@redhat.com> | 2011-01-11 23:34:35 +0300 |
|---|---|---|
| committer | Jesse Barnes <jbarnes@virtuousgeek.org> | 2011-03-04 21:41:02 +0300 |
| commit | 457d9d088b026e26dbab98cad9d299c1faf4c343 (patch) | |
| tree | 654406ce3724d90fe784446ef38c12605adb692e /drivers/pci/pcie/aer | |
| parent | 3449248c8731e8474980856d76bbf9bac9b0682f (diff) | |
| download | linux-457d9d088b026e26dbab98cad9d299c1faf4c343.tar.xz | |
PCI: aer-inject: Override PCIe AER Mask Registers
I have several systems which have the same problem: The PCIe AER
corrected and uncorrected masks have all the error bits set. This
results in the inablility to test with the aer_inject module & utility
on those systems.
Add the 'aer_mask_override' module parameter which will override the
corrected or uncorrected masks for a PCI device. The mask will have the
bit corresponding to the status passed into the aer_inject() function.
After this patch it is possible to successfully use the aer_inject
utility on those PCI slots.
Successfully tested by me on a Dell and Intel whitebox which exhibited
the mask problem.
Signed-off-by: Prarit Bhargava <prarit@redhat.com>
Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
Diffstat (limited to 'drivers/pci/pcie/aer')
| -rw-r--r-- | drivers/pci/pcie/aer/aer_inject.c | 31 |
1 files changed, 28 insertions, 3 deletions
diff --git a/drivers/pci/pcie/aer/aer_inject.c b/drivers/pci/pcie/aer/aer_inject.c index b3cf6223f63a..f62079ff06dd 100644 --- a/drivers/pci/pcie/aer/aer_inject.c +++ b/drivers/pci/pcie/aer/aer_inject.c @@ -27,6 +27,10 @@ #include <linux/stddef.h> #include "aerdrv.h" +/* Override the existing corrected and uncorrected error masks */ +static int aer_mask_override; +module_param(aer_mask_override, bool, 0); + struct aer_error_inj { u8 bus; u8 dev; @@ -322,7 +326,7 @@ static int aer_inject(struct aer_error_inj *einj) unsigned long flags; unsigned int devfn = PCI_DEVFN(einj->dev, einj->fn); int pos_cap_err, rp_pos_cap_err; - u32 sever, cor_mask, uncor_mask; + u32 sever, cor_mask, uncor_mask, cor_mask_orig, uncor_mask_orig; int ret = 0; dev = pci_get_domain_bus_and_slot((int)einj->domain, einj->bus, devfn); @@ -361,6 +365,18 @@ static int aer_inject(struct aer_error_inj *einj) goto out_put; } + if (aer_mask_override) { + cor_mask_orig = cor_mask; + cor_mask &= !(einj->cor_status); + pci_write_config_dword(dev, pos_cap_err + PCI_ERR_COR_MASK, + cor_mask); + + uncor_mask_orig = uncor_mask; + uncor_mask &= !(einj->uncor_status); + pci_write_config_dword(dev, pos_cap_err + PCI_ERR_UNCOR_MASK, + uncor_mask); + } + spin_lock_irqsave(&inject_lock, flags); err = __find_aer_error_by_dev(dev); @@ -378,14 +394,16 @@ static int aer_inject(struct aer_error_inj *einj) err->header_log2 = einj->header_log2; err->header_log3 = einj->header_log3; - if (einj->cor_status && !(einj->cor_status & ~cor_mask)) { + if (!aer_mask_override && einj->cor_status && + !(einj->cor_status & ~cor_mask)) { ret = -EINVAL; printk(KERN_WARNING "The correctable error(s) is masked " "by device\n"); spin_unlock_irqrestore(&inject_lock, flags); goto out_put; } - if (einj->uncor_status && !(einj->uncor_status & ~uncor_mask)) { + if (!aer_mask_override && einj->uncor_status && + !(einj->uncor_status & ~uncor_mask)) { ret = -EINVAL; printk(KERN_WARNING "The uncorrectable error(s) is masked " "by device\n"); @@ -425,6 +443,13 @@ static int aer_inject(struct aer_error_inj *einj) } spin_unlock_irqrestore(&inject_lock, flags); + if (aer_mask_override) { + pci_write_config_dword(dev, pos_cap_err + PCI_ERR_COR_MASK, + cor_mask_orig); + pci_write_config_dword(dev, pos_cap_err + PCI_ERR_UNCOR_MASK, + uncor_mask_orig); + } + ret = pci_bus_set_aer_ops(dev->bus); if (ret) goto out_put; |