powerpc/eeh: Enhance pcibios_set_pcie_reset_state()

Function pcibios_set_pcie_reset_state() is possibly called by
pci_reset_function(), on which VFIO infrastructure depends to
issue reset. pcibios_set_pcie_reset_state() is issuing reset
on the parent PE of the indicated PCI device. The reset causes
state lost on all PCI devices except the indicated one as the
argument to pcibios_set_pcie_reset_state(). Also, sideband
MMIO access from guest when issuing reset would cause unexpected
EEH error.

For above two issues, the patch applies following enhancements
to pcibios_set_pcie_reset_state():

   * For all PCI devices except the indicated one, save their
     state prior to reset and restore state after that.
   * Explicitly freeze PE prior to reset and unfreeze it after
     that, in order to avoid unexpected EEH error.

Tested-by: Priya M. A <priyama2@in.ibm.com>
Signed-off-by: Gavin Shan <gwshan@linux.vnet.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>

diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c
index 3b2252e7731b61ee47ac334ee4dce9c129727831..19a897c810bebb4dc4ea9d2180d5abac64e76235 100644 (file)
--- a/arch/powerpc/kernel/eeh.c
+++ b/arch/powerpc/kernel/eeh.c
@@ -667,6 +667,55 @@ int eeh_pci_enable(struct eeh_pe *pe, int function)
        return rc;
 }
 
+static void *eeh_disable_and_save_dev_state(void *data, void *userdata)
+{
+       struct eeh_dev *edev = data;
+       struct pci_dev *pdev = eeh_dev_to_pci_dev(edev);
+       struct pci_dev *dev = userdata;
+
+       /*
+        * The caller should have disabled and saved the
+        * state for the specified device
+        */
+       if (!pdev || pdev == dev)
+               return NULL;
+
+       /* Ensure we have D0 power state */
+       pci_set_power_state(pdev, PCI_D0);
+
+       /* Save device state */
+       pci_save_state(pdev);
+
+       /*
+        * Disable device to avoid any DMA traffic and
+        * interrupt from the device
+        */
+       pci_write_config_word(pdev, PCI_COMMAND, PCI_COMMAND_INTX_DISABLE);
+
+       return NULL;
+}
+
+static void *eeh_restore_dev_state(void *data, void *userdata)
+{
+       struct eeh_dev *edev = data;
+       struct device_node *dn = eeh_dev_to_of_node(edev);
+       struct pci_dev *pdev = eeh_dev_to_pci_dev(edev);
+       struct pci_dev *dev = userdata;
+
+       if (!pdev)
+               return NULL;
+
+       /* Apply customization from firmware */
+       if (dn && eeh_ops->restore_config)
+               eeh_ops->restore_config(dn);
+
+       /* The caller should restore state for the specified device */
+       if (pdev != dev)
+               pci_save_state(pdev);
+
+       return NULL;
+}
+
 /**
  * pcibios_set_pcie_slot_reset - Set PCI-E reset state
  * @dev: pci device struct
@@ -689,13 +738,19 @@ int pcibios_set_pcie_reset_state(struct pci_dev *dev, enum pcie_reset_state stat
        switch (state) {
        case pcie_deassert_reset:
                eeh_ops->reset(pe, EEH_RESET_DEACTIVATE);
+               eeh_unfreeze_pe(pe, false);
                eeh_pe_state_clear(pe, EEH_PE_CFG_BLOCKED);
+               eeh_pe_dev_traverse(pe, eeh_restore_dev_state, dev);
                break;
        case pcie_hot_reset:
+               eeh_ops->set_option(pe, EEH_OPT_FREEZE_PE);
+               eeh_pe_dev_traverse(pe, eeh_disable_and_save_dev_state, dev);
                eeh_pe_state_mark(pe, EEH_PE_CFG_BLOCKED);
                eeh_ops->reset(pe, EEH_RESET_HOT);
                break;
        case pcie_warm_reset:
+               eeh_ops->set_option(pe, EEH_OPT_FREEZE_PE);
+               eeh_pe_dev_traverse(pe, eeh_disable_and_save_dev_state, dev);
                eeh_pe_state_mark(pe, EEH_PE_CFG_BLOCKED);
                eeh_ops->reset(pe, EEH_RESET_FUNDAMENTAL);
                break;