Merge tag 'powerpc-4.6-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux

Pull powerpc updates from Michael Ellerman:
 "This was delayed a day or two by some build-breakage on old toolchains
  which we've now fixed.

  There's two PCI commits both acked by Bjorn.

  There's one commit to mm/hugepage.c which is (co)authored by Kirill.

  Highlights:
   - Restructure Linux PTE on Book3S/64 to Radix format from Paul
     Mackerras
   - Book3s 64 MMU cleanup in preparation for Radix MMU from Aneesh
     Kumar K.V
   - Add POWER9 cputable entry from Michael Neuling
   - FPU/Altivec/VSX save/restore optimisations from Cyril Bur
   - Add support for new ftrace ABI on ppc64le from Torsten Duwe

  Various cleanups & minor fixes from:
   - Adam Buchbinder, Andrew Donnellan, Balbir Singh, Christophe Leroy,
     Cyril Bur, Luis Henriques, Madhavan Srinivasan, Pan Xinhui, Russell
     Currey, Sukadev Bhattiprolu, Suraj Jitindar Singh.

  General:
   - atomics: Allow architectures to define their own __atomic_op_*
     helpers from Boqun Feng
   - Implement atomic{, 64}_*_return_* variants and acquire/release/
     relaxed variants for (cmp)xchg from Boqun Feng
   - Add powernv_defconfig from Jeremy Kerr
   - Fix BUG_ON() reporting in real mode from Balbir Singh
   - Add xmon command to dump OPAL msglog from Andrew Donnellan
   - Add xmon command to dump process/task similar to ps(1) from Douglas
     Miller
   - Clean up memory hotplug failure paths from David Gibson

  pci/eeh:
   - Redesign SR-IOV on PowerNV to give absolute isolation between VFs
     from Wei Yang.
   - EEH Support for SRIOV VFs from Wei Yang and Gavin Shan.
   - PCI/IOV: Rename and export virtfn_{add, remove} from Wei Yang
   - PCI: Add pcibios_bus_add_device() weak function from Wei Yang
   - MAINTAINERS: Update EEH details and maintainership from Russell
     Currey

  cxl:
   - Support added to the CXL driver for running on both bare-metal and
     hypervisor systems, from Christophe Lombard and Frederic Barrat.
   - Ignore probes for virtual afu pci devices from Vaibhav Jain

  perf:
   - Export Power8 generic and cache events to sysfs from Sukadev
     Bhattiprolu
   - hv-24x7: Fix usage with chip events, display change in counter
     values, display domain indices in sysfs, eliminate domain suffix in
     event names, from Sukadev Bhattiprolu

  Freescale:
   - Updates from Scott: "Highlights include 8xx optimizations, 32-bit
     checksum optimizations, 86xx consolidation, e5500/e6500 cpu
     hotplug, more fman and other dt bits, and minor fixes/cleanup"

* tag 'powerpc-4.6-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux: (179 commits)
  powerpc: Fix unrecoverable SLB miss during restore_math()
  powerpc/8xx: Fix do_mtspr_cpu6() build on older compilers
  powerpc/rcpm: Fix build break when SMP=n
  powerpc/book3e-64: Use hardcoded mttmr opcode
  powerpc/fsl/dts: Add "jedec,spi-nor" flash compatible
  powerpc/T104xRDB: add tdm riser card node to device tree
  powerpc32: PAGE_EXEC required for inittext
  powerpc/mpc85xx: Add pcsphy nodes to FManV3 device tree
  powerpc/mpc85xx: Add MDIO bus muxing support to the board device tree(s)
  powerpc/86xx: Introduce and use common dtsi
  powerpc/86xx: Update device tree
  powerpc/86xx: Move dts files to fsl directory
  powerpc/86xx: Switch to kconfig fragments approach
  powerpc/86xx: Update defconfigs
  powerpc/86xx: Consolidate common platform code
  powerpc32: Remove one insn in mulhdu
  powerpc32: small optimisation in flush_icache_range()
  powerpc: Simplify test in __dma_sync()
  powerpc32: move xxxxx_dcache_range() functions inline
  powerpc32: Remove clear_pages() and define clear_page() inline
  ...

1 files changed, 256 insertions, 42 deletions

diff --git a/arch/powerpc/platforms/powernv/eeh-powernv.c b/arch/powerpc/platforms/powernv/eeh-powernv.c
index 87f47e55aab6..950b3e539057 100644
--- a/arch/powerpc/platforms/powernv/eeh-powernv.c
+++ b/arch/powerpc/platforms/powernv/eeh-powernv.c
@@ -167,42 +167,26 @@ static int pnv_eeh_dbgfs_get(void *data, int offset, u64 *val)
 	return 0;
 }
 
-static int pnv_eeh_outb_dbgfs_set(void *data, u64 val)
-{
-	return pnv_eeh_dbgfs_set(data, 0xD10, val);
-}
-
-static int pnv_eeh_outb_dbgfs_get(void *data, u64 *val)
-{
-	return pnv_eeh_dbgfs_get(data, 0xD10, val);
-}
-
-static int pnv_eeh_inbA_dbgfs_set(void *data, u64 val)
-{
-	return pnv_eeh_dbgfs_set(data, 0xD90, val);
-}
-
-static int pnv_eeh_inbA_dbgfs_get(void *data, u64 *val)
-{
-	return pnv_eeh_dbgfs_get(data, 0xD90, val);
-}
-
-static int pnv_eeh_inbB_dbgfs_set(void *data, u64 val)
-{
-	return pnv_eeh_dbgfs_set(data, 0xE10, val);
-}
+#define PNV_EEH_DBGFS_ENTRY(name, reg)				\
+static int pnv_eeh_dbgfs_set_##name(void *data, u64 val)	\
+{								\
+	return pnv_eeh_dbgfs_set(data, reg, val);		\
+}								\
+								\
+static int pnv_eeh_dbgfs_get_##name(void *data, u64 *val)	\
+{								\
+	return pnv_eeh_dbgfs_get(data, reg, val);		\
+}								\
+								\
+DEFINE_SIMPLE_ATTRIBUTE(pnv_eeh_dbgfs_ops_##name,		\
+			pnv_eeh_dbgfs_get_##name,		\
+                        pnv_eeh_dbgfs_set_##name,		\
+			"0x%llx\n")
+
+PNV_EEH_DBGFS_ENTRY(outb, 0xD10);
+PNV_EEH_DBGFS_ENTRY(inbA, 0xD90);
+PNV_EEH_DBGFS_ENTRY(inbB, 0xE10);
 
-static int pnv_eeh_inbB_dbgfs_get(void *data, u64 *val)
-{
-	return pnv_eeh_dbgfs_get(data, 0xE10, val);
-}
-
-DEFINE_SIMPLE_ATTRIBUTE(pnv_eeh_outb_dbgfs_ops, pnv_eeh_outb_dbgfs_get,
-			pnv_eeh_outb_dbgfs_set, "0x%llx\n");
-DEFINE_SIMPLE_ATTRIBUTE(pnv_eeh_inbA_dbgfs_ops, pnv_eeh_inbA_dbgfs_get,
-			pnv_eeh_inbA_dbgfs_set, "0x%llx\n");
-DEFINE_SIMPLE_ATTRIBUTE(pnv_eeh_inbB_dbgfs_ops, pnv_eeh_inbB_dbgfs_get,
-			pnv_eeh_inbB_dbgfs_set, "0x%llx\n");
 #endif /* CONFIG_DEBUG_FS */
 
 /**
@@ -268,13 +252,13 @@ static int pnv_eeh_post_init(void)
 
 		debugfs_create_file("err_injct_outbound", 0600,
 				    phb->dbgfs, hose,
-				    &pnv_eeh_outb_dbgfs_ops);
+				    &pnv_eeh_dbgfs_ops_outb);
 		debugfs_create_file("err_injct_inboundA", 0600,
 				    phb->dbgfs, hose,
-				    &pnv_eeh_inbA_dbgfs_ops);
+				    &pnv_eeh_dbgfs_ops_inbA);
 		debugfs_create_file("err_injct_inboundB", 0600,
 				    phb->dbgfs, hose,
-				    &pnv_eeh_inbB_dbgfs_ops);
+				    &pnv_eeh_dbgfs_ops_inbB);
 #endif /* CONFIG_DEBUG_FS */
 	}
 
@@ -387,6 +371,7 @@ static void *pnv_eeh_probe(struct pci_dn *pdn, void *data)
 	edev->mode	&= 0xFFFFFF00;
 	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->af_cap   = pnv_eeh_find_cap(pdn, PCI_CAP_ID_AF);
 	edev->aer_cap  = pnv_eeh_find_ecap(pdn, PCI_EXT_CAP_ID_ERR);
 	if ((edev->class_code >> 8) == PCI_CLASS_BRIDGE_PCI) {
 		edev->mode |= EEH_DEV_BRIDGE;
@@ -895,6 +880,120 @@ void pnv_pci_reset_secondary_bus(struct pci_dev *dev)
 	}
 }
 
+static void pnv_eeh_wait_for_pending(struct pci_dn *pdn, const char *type,
+				     int pos, u16 mask)
+{
+	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 %sFLR to %04x:%02x:%02x.%01x\n",
+		__func__, 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, "AF",
+					 edev->af_cap + PCI_AF_CTRL,
+					 PCI_AF_STATUS_TP << 8);
+		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_pe(struct eeh_pe *pe, int option)
+{
+	struct eeh_dev *edev;
+	struct pci_dn *pdn;
+	int ret;
+
+	/* The VF PE should have only one child device */
+	edev = list_first_entry_or_null(&pe->edevs, struct eeh_dev, list);
+	pdn = eeh_dev_to_pdn(edev);
+	if (!pdn)
+		return -ENXIO;
+
+	ret = pnv_eeh_do_flr(pdn, option);
+	if (!ret)
+		return ret;
+
+	return pnv_eeh_do_af_flr(pdn, option);
+}
+
 /**
  * pnv_eeh_reset - Reset the specified PE
  * @pe: EEH PE
@@ -956,7 +1055,9 @@ 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_reset_vf_pe(pe, option);
+		else if (pci_is_root_bus(bus) ||
 			pci_is_root_bus(bus->parent))
 			ret = pnv_eeh_root_reset(hose, option);
 		else
@@ -1095,6 +1196,14 @@ 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;
 
@@ -1479,6 +1588,65 @@ static int pnv_eeh_next_error(struct eeh_pe **pe)
 	return ret;
 }
 
+static int pnv_eeh_restore_vf_config(struct pci_dn *pdn)
+{
+	struct eeh_dev *edev = pdn_to_eeh_dev(pdn);
+	u32 devctl, cmd, cap2, aer_capctl;
+	int old_mps;
+
+	if (edev->pcie_cap) {
+		/* Restore MPS */
+		old_mps = (ffs(pdn->mps) - 8) << 5;
+		eeh_ops->read_config(pdn, edev->pcie_cap + PCI_EXP_DEVCTL,
+				     2, &devctl);
+		devctl &= ~PCI_EXP_DEVCTL_PAYLOAD;
+		devctl |= old_mps;
+		eeh_ops->write_config(pdn, edev->pcie_cap + PCI_EXP_DEVCTL,
+				      2, devctl);
+
+		/* Disable Completion Timeout */
+		eeh_ops->read_config(pdn, edev->pcie_cap + PCI_EXP_DEVCAP2,
+				     4, &cap2);
+		if (cap2 & 0x10) {
+			eeh_ops->read_config(pdn,
+					     edev->pcie_cap + PCI_EXP_DEVCTL2,
+					     4, &cap2);
+			cap2 |= 0x10;
+			eeh_ops->write_config(pdn,
+					      edev->pcie_cap + PCI_EXP_DEVCTL2,
+					      4, cap2);
+		}
+	}
+
+	/* Enable SERR and parity checking */
+	eeh_ops->read_config(pdn, PCI_COMMAND, 2, &cmd);
+	cmd |= (PCI_COMMAND_PARITY | PCI_COMMAND_SERR);
+	eeh_ops->write_config(pdn, PCI_COMMAND, 2, cmd);
+
+	/* Enable report various errors */
+	if (edev->pcie_cap) {
+		eeh_ops->read_config(pdn, edev->pcie_cap + PCI_EXP_DEVCTL,
+				     2, &devctl);
+		devctl &= ~PCI_EXP_DEVCTL_CERE;
+		devctl |= (PCI_EXP_DEVCTL_NFERE |
+			   PCI_EXP_DEVCTL_FERE |
+			   PCI_EXP_DEVCTL_URRE);
+		eeh_ops->write_config(pdn, edev->pcie_cap + PCI_EXP_DEVCTL,
+				      2, devctl);
+	}
+
+	/* Enable ECRC generation and check */
+	if (edev->pcie_cap && edev->aer_cap) {
+		eeh_ops->read_config(pdn, edev->aer_cap + PCI_ERR_CAP,
+				     4, &aer_capctl);
+		aer_capctl |= (PCI_ERR_CAP_ECRC_GENE | PCI_ERR_CAP_ECRC_CHKE);
+		eeh_ops->write_config(pdn, edev->aer_cap + PCI_ERR_CAP,
+				      4, aer_capctl);
+	}
+
+	return 0;
+}
+
 static int pnv_eeh_restore_config(struct pci_dn *pdn)
 {
 	struct eeh_dev *edev = pdn_to_eeh_dev(pdn);
@@ -1488,9 +1656,21 @@ static int pnv_eeh_restore_config(struct pci_dn *pdn)
 	if (!edev)
 		return -EEXIST;
 
-	phb = edev->phb->private_data;
-	ret = opal_pci_reinit(phb->opal_id,
-			      OPAL_REINIT_PCI_DEV, edev->config_addr);
+	/*
+	 * We have to restore the PCI config space after reset since the
+	 * firmware can't see SRIOV VFs.
+	 *
+	 * FIXME: The MPS, error routing rules, timeout setting are worthy
+	 * to be exported by firmware in extendible way.
+	 */
+	if (edev->physfn) {
+		ret = pnv_eeh_restore_vf_config(pdn);
+	} else {
+		phb = edev->phb->private_data;
+		ret = opal_pci_reinit(phb->opal_id,
+				      OPAL_REINIT_PCI_DEV, edev->config_addr);
+	}
+
 	if (ret) {
 		pr_warn("%s: Can't reinit PCI dev 0x%x (%lld)\n",
 			__func__, edev->config_addr, ret);
@@ -1519,6 +1699,40 @@ static struct eeh_ops pnv_eeh_ops = {
 	.restore_config		= pnv_eeh_restore_config
 };
 
+void pcibios_bus_add_device(struct pci_dev *pdev)
+{
+	struct pci_dn *pdn = pci_get_pdn(pdev);
+
+	if (!pdev->is_virtfn)
+		return;
+
+	/*
+	 * The following operations will fail if VF's sysfs files
+	 * aren't created or its resources aren't finalized.
+	 */
+	eeh_add_device_early(pdn);
+	eeh_add_device_late(pdev);
+	eeh_sysfs_add_device(pdev);
+}
+
+#ifdef CONFIG_PCI_IOV
+static void pnv_pci_fixup_vf_mps(struct pci_dev *pdev)
+{
+	struct pci_dn *pdn = pci_get_pdn(pdev);
+	int parent_mps;
+
+	if (!pdev->is_virtfn)
+		return;
+
+	/* Synchronize MPS for VF and PF */
+	parent_mps = pcie_get_mps(pdev->physfn);
+	if ((128 << pdev->pcie_mpss) >= parent_mps)
+		pcie_set_mps(pdev, parent_mps);
+	pdn->mps = pcie_get_mps(pdev);
+}
+DECLARE_PCI_FIXUP_HEADER(PCI_ANY_ID, PCI_ANY_ID, pnv_pci_fixup_vf_mps);
+#endif /* CONFIG_PCI_IOV */
+
 /**
  * eeh_powernv_init - Register platform dependent EEH operations
  *