[PATCH v3] powerpc/pseries/eeh: Fix pseries_eeh_err_inject

From: Narayana Murty N
Date: Mon Sep 09 2024 - 10:03:28 EST


VFIO_EEH_PE_INJECT_ERR ioctl is currently failing on pseries
due to missing implementation of err_inject eeh_ops for pseries.
This patch implements pseries_eeh_err_inject in eeh_ops/pseries
eeh_ops. Implements support for injecting MMIO load/store error
for testing from user space.

The check on PCI error type (bus type) code is moved to platform
code, since the eeh_pe_inject_err can be allowed to more error
types depending on platform requirement. Removal of the check for
'type' in eeh_pe_inject_err() doesn't impact PowerNV as
pnv_eeh_err_inject() already has an equivalent check in place.

Signed-off-by: Narayana Murty N <nnmlinux@xxxxxxxxxxxxx>
Reviewed-by: Vaibhav Jain <vaibhav@xxxxxxxxxxxxx>

---

Testing:
========
vfio-test [1] by Alex Willamson, was forked and updated to add
support inject error on pSeries guest and used to test this
patch[2].

References:
===========
[1] https://github.com/awilliam/tests
[2] https://github.com/nnmwebmin/vfio-ppc-tests/tree/vfio-ppc-ex

================
Changelog:
V2: https://lore.kernel.org/all/20240823151158.92602-1-nnmlinux@xxxxxxxxxxxxx/
- Updated patch description explicitly mentioning about similar checks
in place for PoweRNV as suggested.
- eeh_pe_inject_mmio_error wrapper function removed because CONFIG_EEH
is always enabled built for PPC_PSERIES when PPC_PSERIES=y.
V1: https://lore.kernel.org/all/20240822082713.529982-1-nnmlinux@xxxxxxxxxxxxx/
- Resolved build issues for ppc64|le_defconfig by moving the
pseries_eeh_err_inject() definition outside of the CONFIG_PCI_IOV
code block.
- New eeh_pe_inject_mmio_error wrapper function added to avoid
CONFIG_EEH is not set.
---
arch/powerpc/include/asm/eeh.h | 2 +-
arch/powerpc/kernel/eeh.c | 9 +++--
arch/powerpc/platforms/pseries/eeh_pseries.c | 39 +++++++++++++++++++-
3 files changed, 44 insertions(+), 6 deletions(-)

diff --git a/arch/powerpc/include/asm/eeh.h b/arch/powerpc/include/asm/eeh.h
index 91a9fd53254f..317b12fc1fe4 100644
--- a/arch/powerpc/include/asm/eeh.h
+++ b/arch/powerpc/include/asm/eeh.h
@@ -308,7 +308,7 @@ int eeh_pe_reset(struct eeh_pe *pe, int option, bool include_passed);
int eeh_pe_configure(struct eeh_pe *pe);
int eeh_pe_inject_err(struct eeh_pe *pe, int type, int func,
unsigned long addr, unsigned long mask);
-
+int eeh_pe_inject_mmio_error(struct pci_dev *pdev);
/**
* EEH_POSSIBLE_ERROR() -- test for possible MMIO failure.
*
diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c
index d03f17987fca..49ab11a287a3 100644
--- a/arch/powerpc/kernel/eeh.c
+++ b/arch/powerpc/kernel/eeh.c
@@ -1537,10 +1537,6 @@ int eeh_pe_inject_err(struct eeh_pe *pe, int type, int func,
if (!eeh_ops || !eeh_ops->err_inject)
return -ENOENT;

- /* Check on PCI error type */
- if (type != EEH_ERR_TYPE_32 && type != EEH_ERR_TYPE_64)
- return -EINVAL;
-
/* Check on PCI error function */
if (func < EEH_ERR_FUNC_MIN || func > EEH_ERR_FUNC_MAX)
return -EINVAL;
@@ -1851,6 +1847,11 @@ static const struct file_operations eeh_dev_break_fops = {
.read = eeh_debugfs_dev_usage,
};

+int eeh_pe_inject_mmio_error(struct pci_dev *pdev)
+{
+ return eeh_debugfs_break_device(pdev);
+}
+
static ssize_t eeh_dev_can_recover(struct file *filp,
const char __user *user_buf,
size_t count, loff_t *ppos)
diff --git a/arch/powerpc/platforms/pseries/eeh_pseries.c b/arch/powerpc/platforms/pseries/eeh_pseries.c
index b1ae0c0d1187..1893f66371fa 100644
--- a/arch/powerpc/platforms/pseries/eeh_pseries.c
+++ b/arch/powerpc/platforms/pseries/eeh_pseries.c
@@ -784,6 +784,43 @@ static int pseries_notify_resume(struct eeh_dev *edev)
}
#endif

+/**
+ * pseries_eeh_err_inject - Inject specified error to the indicated PE
+ * @pe: the indicated PE
+ * @type: error type
+ * @func: specific error type
+ * @addr: address
+ * @mask: address mask
+ * The routine is called to inject specified error, which is
+ * determined by @type and @func, to the indicated PE
+ */
+static int pseries_eeh_err_inject(struct eeh_pe *pe, int type, int func,
+ unsigned long addr, unsigned long mask)
+{
+ struct eeh_dev *pdev;
+
+ /* Check on PCI error type */
+ if (type != EEH_ERR_TYPE_32 && type != EEH_ERR_TYPE_64)
+ return -EINVAL;
+
+ switch (func) {
+ case EEH_ERR_FUNC_LD_MEM_ADDR:
+ case EEH_ERR_FUNC_LD_MEM_DATA:
+ case EEH_ERR_FUNC_ST_MEM_ADDR:
+ case EEH_ERR_FUNC_ST_MEM_DATA:
+ /* injects a MMIO error for all pdev's belonging to PE */
+ pci_lock_rescan_remove();
+ list_for_each_entry(pdev, &pe->edevs, entry)
+ eeh_pe_inject_mmio_error(pdev->pdev);
+ pci_unlock_rescan_remove();
+ break;
+ default:
+ return -ERANGE;
+ }
+
+ return 0;
+}
+
static struct eeh_ops pseries_eeh_ops = {
.name = "pseries",
.probe = pseries_eeh_probe,
@@ -792,7 +829,7 @@ static struct eeh_ops pseries_eeh_ops = {
.reset = pseries_eeh_reset,
.get_log = pseries_eeh_get_log,
.configure_bridge = pseries_eeh_configure_bridge,
- .err_inject = NULL,
+ .err_inject = pseries_eeh_err_inject,
.read_config = pseries_eeh_read_config,
.write_config = pseries_eeh_write_config,
.next_error = NULL,
--
2.45.2