[PATCH V13 7/9] powerpc/powernv: Support EEH reset for VF PE

[Wei Yang <weiyang@linux.vnet.ibm.com>]

PEs for VFs don't have primary bus. So they have to have their own reset
backend, which is used during EEH recovery. The patch implements the reset
backend for VF's PE by issuing FLR or AF FLR to the VFs, which are contained
in the PE.

Signed-off-by: Wei Yang <weiyang@linux.vnet.ibm.com>
---
 arch/powerpc/include/asm/eeh.h               |   1 +
 arch/powerpc/kernel/eeh.c                    |   9 +-
 arch/powerpc/platforms/powernv/eeh-powernv.c | 133 ++++++++++++++++++++++++++-
 3 files changed, 139 insertions(+), 4 deletions(-)

diff --git a/arch/powerpc/include/asm/eeh.h b/arch/powerpc/include/asm/eeh.h
index ec21f8f..331c856 100644
--- a/arch/powerpc/include/asm/eeh.h
+++ b/arch/powerpc/include/asm/eeh.h
@@ -136,6 +136,7 @@ struct eeh_dev {
 	int pcix_cap;			/* Saved PCIx capability	*/
 	int pcie_cap;			/* Saved PCIe capability	*/
 	int aer_cap;			/* Saved AER capability		*/
+	int af_cap;			/* Saved AF capability		*/
 	struct eeh_pe *pe;		/* Associated PE		*/
 	struct list_head list;		/* Form link list in the PE	*/
 	struct pci_controller *phb;	/* Associated PHB		*/
diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c
index e968533..41a4b30 100644
--- a/arch/powerpc/kernel/eeh.c
+++ b/arch/powerpc/kernel/eeh.c
@@ -760,7 +760,8 @@ int pcibios_set_pcie_reset_state(struct pci_dev *dev, enum pcie_reset_state stat
 	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);
+		if (!(pe->type & EEH_PE_VF))
+			eeh_pe_state_clear(pe, EEH_PE_CFG_BLOCKED);
 		eeh_pe_dev_traverse(pe, eeh_restore_dev_state, dev);
 		eeh_pe_state_clear(pe, EEH_PE_ISOLATED);
 		break;
@@ -768,14 +769,16 @@ int pcibios_set_pcie_reset_state(struct pci_dev *dev, enum pcie_reset_state stat
 		eeh_pe_state_mark_with_cfg(pe, EEH_PE_ISOLATED);
 		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);
+		if (!(pe->type & EEH_PE_VF))
+			eeh_pe_state_mark(pe, EEH_PE_CFG_BLOCKED);
 		eeh_ops->reset(pe, EEH_RESET_HOT);
 		break;
 	case pcie_warm_reset:
 		eeh_pe_state_mark_with_cfg(pe, EEH_PE_ISOLATED);
 		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);
+		if (!(pe->type & EEH_PE_VF))
+			eeh_pe_state_mark(pe, EEH_PE_CFG_BLOCKED);
 		eeh_ops->reset(pe, EEH_RESET_FUNDAMENTAL);
 		break;
 	default:
diff --git a/arch/powerpc/platforms/powernv/eeh-powernv.c b/arch/powerpc/platforms/powernv/eeh-powernv.c
index 131c7d0..4de247a 100644
--- a/arch/powerpc/platforms/powernv/eeh-powernv.c
+++ b/arch/powerpc/platforms/powernv/eeh-powernv.c
@@ -404,6 +404,7 @@ static void *pnv_eeh_probe(struct pci_dn *pdn, void *data)
 	edev->pcix_cap = pnv_eeh_find_cap(pdn, PCI_CAP_ID_PCIX);
 	edev->pcie_cap = pnv_eeh_find_cap(pdn, PCI_CAP_ID_EXP);
 	edev->aer_cap  = pnv_eeh_find_ecap(pdn, PCI_EXT_CAP_ID_ERR);
+	edev->af_cap   = pnv_eeh_find_cap(pdn, PCI_CAP_ID_AF);
 	if ((edev->class_code >> 8) == PCI_CLASS_BRIDGE_PCI) {
 		edev->mode |= EEH_DEV_BRIDGE;
 		if (edev->pcie_cap) {
@@ -893,6 +894,126 @@ static int pnv_eeh_bridge_reset(struct pci_dev *dev, int option)
 	return 0;
 }
 
+static void pnv_eeh_wait_for_pending(struct pci_dn *pdn, int pos,
+				     u16 mask, const char *reset_type)
+{
+	struct eeh_dev *edev = pdn_to_eeh_dev(pdn);
+	int i, status = 0;
+
+	/* Wait for Transaction Pending bit to be cleared */
+	for (i = 0; i < 4; i++) {
+		eeh_ops->read_config(pdn, pos, 2, &status);
+		if (!(status & mask))
+			return;
+
+		msleep((1 << i) * 100);
+	}
+
+	pr_warn("%s: Pending transaction while issuing %s FLR to %04x:%02x:%02x.%01x\n",
+		__func__, reset_type,
+		edev->phb->global_number, pdn->busno,
+		PCI_SLOT(pdn->devfn), PCI_FUNC(pdn->devfn));
+}
+
+static int pnv_eeh_do_flr(struct pci_dn *pdn, int option)
+{
+	struct eeh_dev *edev = pdn_to_eeh_dev(pdn);
+	u32 reg = 0;
+
+	if (WARN_ON(!edev->pcie_cap))
+		return -ENOTTY;
+
+	eeh_ops->read_config(pdn, edev->pcie_cap + PCI_EXP_DEVCAP, 4, &reg);
+	if (!(reg & PCI_EXP_DEVCAP_FLR))
+		return -ENOTTY;
+
+	switch (option) {
+	case EEH_RESET_HOT:
+	case EEH_RESET_FUNDAMENTAL:
+		pnv_eeh_wait_for_pending(pdn, edev->pcie_cap + PCI_EXP_DEVSTA,
+					 PCI_EXP_DEVSTA_TRPND, "");
+		eeh_ops->read_config(pdn, edev->pcie_cap + PCI_EXP_DEVCTL,
+				     4, &reg);
+		reg |= PCI_EXP_DEVCTL_BCR_FLR;
+		eeh_ops->write_config(pdn, edev->pcie_cap + PCI_EXP_DEVCTL,
+				      4, reg);
+		msleep(EEH_PE_RST_HOLD_TIME);
+		break;
+	case EEH_RESET_DEACTIVATE:
+		eeh_ops->read_config(pdn, edev->pcie_cap + PCI_EXP_DEVCTL,
+				     4, &reg);
+		reg &= ~PCI_EXP_DEVCTL_BCR_FLR;
+		eeh_ops->write_config(pdn, edev->pcie_cap + PCI_EXP_DEVCTL,
+				      4, reg);
+		msleep(EEH_PE_RST_SETTLE_TIME);
+		break;
+	}
+
+	return 0;
+}
+
+static int pnv_eeh_do_af_flr(struct pci_dn *pdn, int option)
+{
+	struct eeh_dev *edev = pdn_to_eeh_dev(pdn);
+	u32 cap = 0;
+
+	if (WARN_ON(!edev->af_cap))
+		return -ENOTTY;
+
+	eeh_ops->read_config(pdn, edev->af_cap + PCI_AF_CAP, 1, &cap);
+	if (!(cap & PCI_AF_CAP_TP) || !(cap & PCI_AF_CAP_FLR))
+		return -ENOTTY;
+
+	switch (option) {
+	case EEH_RESET_HOT:
+	case EEH_RESET_FUNDAMENTAL:
+		/*
+		 * Wait for Transaction Pending bit to clear. A word-aligned
+		 * test is used, so we use the conrol offset rather than status
+		 * and shift the test bit to match.
+		 */
+		pnv_eeh_wait_for_pending(pdn, edev->af_cap + PCI_AF_CTRL,
+					 PCI_AF_STATUS_TP << 8, "AF");
+		eeh_ops->write_config(pdn, edev->af_cap + PCI_AF_CTRL,
+				      1, PCI_AF_CTRL_FLR);
+		msleep(EEH_PE_RST_HOLD_TIME);
+		break;
+	case EEH_RESET_DEACTIVATE:
+		eeh_ops->write_config(pdn, edev->af_cap + PCI_AF_CTRL, 1, 0);
+		msleep(EEH_PE_RST_SETTLE_TIME);
+		break;
+	}
+
+	return 0;
+}
+
+static int pnv_eeh_reset_vf(struct pci_dn *pdn, int option)
+{
+	int ret;
+
+	ret = pnv_eeh_do_flr(pdn, option);
+	if (ret != -ENOTTY)
+		return ret;
+
+	return pnv_eeh_do_af_flr(pdn, option);
+}
+
+static int pnv_eeh_vf_pe_reset(struct eeh_pe *pe, int option)
+{
+	struct eeh_dev *edev, *tmp;
+	struct pci_dn *pdn;
+	int ret;
+
+	eeh_pe_for_each_dev(pe, edev, tmp) {
+		pdn = eeh_dev_to_pdn(edev);
+		ret = pnv_eeh_reset_vf(pdn, option);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
 void pnv_pci_reset_secondary_bus(struct pci_dev *dev)
 {
 	struct pci_controller *hose;
@@ -968,7 +1089,9 @@ static int pnv_eeh_reset(struct eeh_pe *pe, int option)
 		}
 
 		bus = eeh_pe_bus_get(pe);
-		if (pci_is_root_bus(bus) ||
+		if (pe->type & EEH_PE_VF)
+			ret = pnv_eeh_vf_pe_reset(pe, option);
+		else if (pci_is_root_bus(bus) ||
 			pci_is_root_bus(bus->parent))
 			ret = pnv_eeh_root_reset(hose, option);
 		else
@@ -1108,6 +1231,14 @@ static inline bool pnv_eeh_cfg_blocked(struct pci_dn *pdn)
 	if (!edev || !edev->pe)
 		return false;
 
+	/*
+	 * We will issue FLR or AF FLR to all VFs, which are contained
+	 * in VF PE. It relies on the EEH PCI config accessors. So we
+	 * can't block them during the window.
+	 */
+	if (edev->physfn && (edev->pe->state & EEH_PE_RESET))
+		return false;
+
 	if (edev->pe->state & EEH_PE_CFG_BLOCKED)
 		return true;
 
-- 
2.5.0