powernv/eeh: Use generic code to handle hot resets

When we reset PCI devices managed by a hotplug driver the reset may
generate spurious hotplug events that cause the PCI device we're resetting
to be torn down accidently. This is a problem for EEH (when the driver is
EEH aware) since we want to leave the OS PCI device state intact so that
the device can be re-set without losing any resources (network, disks,
etc) provided by the driver.

Generic PCI code provides the pci_bus_error_reset() function to handle
resetting a PCI Device (or bus) by using the reset method provided by the
hotplug slot driver. We can use this function if the EEH core has
requested a hot reset (common case) without tripping over the hotplug
driver.

Signed-off-by: Oliver O'Halloran <oohall@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20190903101605.2890-8-oohall@gmail.com

diff --git a/arch/powerpc/platforms/powernv/eeh-powernv.c b/arch/powerpc/platforms/powernv/eeh-powernv.c
index 94e26d56ecd2822a8821117905b6b1dfca01de2f..6bc24a47e9ef956e654ea022b4e6a9b52c0903df 100644 (file)
--- a/arch/powerpc/platforms/powernv/eeh-powernv.c
+++ b/arch/powerpc/platforms/powernv/eeh-powernv.c
@@ -34,6 +34,7 @@
 
 #include "powernv.h"
 #include "pci.h"
+#include "../../../../drivers/pci/pci.h"
 
 static int eeh_event_irq = -EINVAL;
 
@@ -849,7 +850,7 @@ static int __pnv_eeh_bridge_reset(struct pci_dev *dev, int option)
        int aer = edev ? edev->aer_cap : 0;
        u32 ctrl;
 
-       pr_debug("%s: Reset PCI bus %04x:%02x with option %d\n",
+       pr_debug("%s: Secondary Reset PCI bus %04x:%02x with option %d\n",
                 __func__, pci_domain_nr(dev->bus),
                 dev->bus->number, option);
 
@@ -907,6 +908,10 @@ static int pnv_eeh_bridge_reset(struct pci_dev *pdev, int option)
        if (!dn || !of_get_property(dn, "ibm,reset-by-firmware", NULL))
                return __pnv_eeh_bridge_reset(pdev, option);
 
+       pr_debug("%s: FW reset PCI bus %04x:%02x with option %d\n",
+                __func__, pci_domain_nr(pdev->bus),
+                pdev->bus->number, option);
+
        switch (option) {
        case EEH_RESET_FUNDAMENTAL:
                scope = OPAL_RESET_PCI_FUNDAMENTAL;
@@ -1125,10 +1130,37 @@ static int pnv_eeh_reset(struct eeh_pe *pe, int option)
                return -EIO;
        }
 
-       if (pci_is_root_bus(bus) ||
-           pci_is_root_bus(bus->parent))
+       if (pci_is_root_bus(bus))
                return pnv_eeh_root_reset(hose, option);
 
+       /*
+        * For hot resets try use the generic PCI error recovery reset
+        * functions. These correctly handles the case where the secondary
+        * bus is behind a hotplug slot and it will use the slot provided
+        * reset methods to prevent spurious hotplug events during the reset.
+        *
+        * Fundemental resets need to be handled internally to EEH since the
+        * PCI core doesn't really have a concept of a fundemental reset,
+        * mainly because there's no standard way to generate one. Only a
+        * few devices require an FRESET so it should be fine.
+        */
+       if (option != EEH_RESET_FUNDAMENTAL) {
+               /*
+                * NB: Skiboot and pnv_eeh_bridge_reset() also no-op the
+                *     de-assert step. It's like the OPAL reset API was
+                *     poorly designed or something...
+                */
+               if (option == EEH_RESET_DEACTIVATE)
+                       return 0;
+
+               rc = pci_bus_error_reset(bus->self);
+               if (!rc)
+                       return 0;
+       }
+
+       /* otherwise, use the generic bridge reset. this might call into FW */
+       if (pci_is_root_bus(bus->parent))
+               return pnv_eeh_root_reset(hose, option);
        return pnv_eeh_bridge_reset(bus->self, option);
 }