Merge branch 'next' of git://git.kernel.org/pub/scm/linux/kernel/git/benh/powerpc

Pull powerpc updates from Ben Herrenschmidt:
 "This is the powerpc changes for the 3.11 merge window.  In addition to
  the usual bug fixes and small updates, the main highlights are:

   - Support for transparent huge pages by Aneesh Kumar for 64-bit
     server processors.  This allows the use of 16M pages as transparent
     huge pages on kernels compiled with a 64K base page size.

   - Base VFIO support for KVM on power by Alexey Kardashevskiy

   - Wiring up of our nvram to the pstore infrastructure, including
     putting compressed oopses in there by Aruna Balakrishnaiah

   - Move, rework and improve our "EEH" (basically PCI error handling
     and recovery) infrastructure.  It is no longer specific to pseries
     but is now usable by the new "powernv" platform as well (no
     hypervisor) by Gavin Shan.

   - I fixed some bugs in our math-emu instruction decoding and made it
     usable to emulate some optional FP instructions on processors with
     hard FP that lack them (such as fsqrt on Freescale embedded
     processors).

   - Support for Power8 "Event Based Branch" facility by Michael
     Ellerman.  This facility allows what is basically "userspace
     interrupts" for performance monitor events.

   - A bunch of Transactional Memory vs.  Signals bug fixes and HW
     breakpoint/watchpoint fixes by Michael Neuling.

  And more ...  I appologize in advance if I've failed to highlight
  something that somebody deemed worth it."

* 'next' of git://git.kernel.org/pub/scm/linux/kernel/git/benh/powerpc: (156 commits)
  pstore: Add hsize argument in write_buf call of pstore_ftrace_call
  powerpc/fsl: add MPIC timer wakeup support
  powerpc/mpic: create mpic subsystem object
  powerpc/mpic: add global timer support
  powerpc/mpic: add irq_set_wake support
  powerpc/85xx: enable coreint for all the 64bit boards
  powerpc/8xx: Erroneous double irq_eoi() on CPM IRQ in MPC8xx
  powerpc/fsl: Enable CONFIG_E1000E in mpc85xx_smp_defconfig
  powerpc/mpic: Add get_version API both for internal and external use
  powerpc: Handle both new style and old style reserve maps
  powerpc/hw_brk: Fix off by one error when validating DAWR region end
  powerpc/pseries: Support compression of oops text via pstore
  powerpc/pseries: Re-organise the oops compression code
  pstore: Pass header size in the pstore write callback
  powerpc/powernv: Fix iommu initialization again
  powerpc/pseries: Inform the hypervisor we are using EBB regs
  powerpc/perf: Add power8 EBB support
  powerpc/perf: Core EBB support for 64-bit book3s
  powerpc/perf: Drop MMCRA from thread_struct
  powerpc/perf: Don't enable if we have zero events
  ...

1 files changed, 103 insertions, 36 deletions

diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c
index 277343c..a28d3b5 100644
--- a/arch/powerpc/platforms/powernv/pci.c
+++ b/arch/powerpc/platforms/powernv/pci.c
@@ -20,6 +20,7 @@
 #include <linux/irq.h>
 #include <linux/io.h>
 #include <linux/msi.h>
+#include <linux/iommu.h>
 
 #include <asm/sections.h>
 #include <asm/io.h>
@@ -32,6 +33,8 @@
 #include <asm/iommu.h>
 #include <asm/tce.h>
 #include <asm/firmware.h>
+#include <asm/eeh_event.h>
+#include <asm/eeh.h>
 
 #include "powernv.h"
 #include "pci.h"
@@ -202,7 +205,8 @@ static void pnv_pci_handle_eeh_config(struct pnv_phb *phb, u32 pe_no)
 
 	spin_lock_irqsave(&phb->lock, flags);
 
-	rc = opal_pci_get_phb_diag_data(phb->opal_id, phb->diag.blob, PNV_PCI_DIAG_BUF_SIZE);
+	rc = opal_pci_get_phb_diag_data2(phb->opal_id, phb->diag.blob,
+					 PNV_PCI_DIAG_BUF_SIZE);
 	has_diag = (rc == OPAL_SUCCESS);
 
 	rc = opal_pci_eeh_freeze_clear(phb->opal_id, pe_no,
@@ -227,43 +231,50 @@ static void pnv_pci_handle_eeh_config(struct pnv_phb *phb, u32 pe_no)
 	spin_unlock_irqrestore(&phb->lock, flags);
 }
 
-static void pnv_pci_config_check_eeh(struct pnv_phb *phb, struct pci_bus *bus,
-				     u32 bdfn)
+static void pnv_pci_config_check_eeh(struct pnv_phb *phb,
+				     struct device_node *dn)
 {
 	s64	rc;
 	u8	fstate;
 	u16	pcierr;
 	u32	pe_no;
 
-	/* Get PE# if we support IODA */
-	pe_no = phb->bdfn_to_pe ? phb->bdfn_to_pe(phb, bus, bdfn & 0xff) : 0;
+	/*
+	 * Get the PE#. During the PCI probe stage, we might not
+	 * setup that yet. So all ER errors should be mapped to
+	 * PE#0
+	 */
+	pe_no = PCI_DN(dn)->pe_number;
+	if (pe_no == IODA_INVALID_PE)
+		pe_no = 0;
 
 	/* Read freeze status */
 	rc = opal_pci_eeh_freeze_status(phb->opal_id, pe_no, &fstate, &pcierr,
 					NULL);
 	if (rc) {
-		pr_warning("PCI %d: Failed to read EEH status for PE#%d,"
-			   " err %lld\n", phb->hose->global_number, pe_no, rc);
+		pr_warning("%s: Can't read EEH status (PE#%d) for "
+			   "%s, err %lld\n",
+			   __func__, pe_no, dn->full_name, rc);
 		return;
 	}
-	cfg_dbg(" -> EEH check, bdfn=%04x PE%d fstate=%x\n",
-		bdfn, pe_no, fstate);
+	cfg_dbg(" -> EEH check, bdfn=%04x PE#%d fstate=%x\n",
+		(PCI_DN(dn)->busno << 8) | (PCI_DN(dn)->devfn),
+		pe_no, fstate);
 	if (fstate != 0)
 		pnv_pci_handle_eeh_config(phb, pe_no);
 }
 
-static int pnv_pci_read_config(struct pci_bus *bus,
-			       unsigned int devfn,
-			       int where, int size, u32 *val)
+int pnv_pci_cfg_read(struct device_node *dn,
+		     int where, int size, u32 *val)
 {
-	struct pci_controller *hose = pci_bus_to_host(bus);
-	struct pnv_phb *phb = hose->private_data;
-	u32 bdfn = (((uint64_t)bus->number) << 8) | devfn;
+	struct pci_dn *pdn = PCI_DN(dn);
+	struct pnv_phb *phb = pdn->phb->private_data;
+	u32 bdfn = (pdn->busno << 8) | pdn->devfn;
+#ifdef CONFIG_EEH
+	struct eeh_pe *phb_pe = NULL;
+#endif
 	s64 rc;
 
-	if (hose == NULL)
-		return PCIBIOS_DEVICE_NOT_FOUND;
-
 	switch (size) {
 	case 1: {
 		u8 v8;
@@ -287,28 +298,43 @@ static int pnv_pci_read_config(struct pci_bus *bus,
 	default:
 		return PCIBIOS_FUNC_NOT_SUPPORTED;
 	}
-	cfg_dbg("pnv_pci_read_config bus: %x devfn: %x +%x/%x -> %08x\n",
-		bus->number, devfn, where, size, *val);
-
-	/* Check if the PHB got frozen due to an error (no response) */
-	pnv_pci_config_check_eeh(phb, bus, bdfn);
+	cfg_dbg("%s: bus: %x devfn: %x +%x/%x -> %08x\n",
+		__func__, pdn->busno, pdn->devfn, where, size, *val);
+
+	/*
+	 * Check if the specified PE has been put into frozen
+	 * state. On the other hand, we needn't do that while
+	 * the PHB has been put into frozen state because of
+	 * PHB-fatal errors.
+	 */
+#ifdef CONFIG_EEH
+	phb_pe = eeh_phb_pe_get(pdn->phb);
+	if (phb_pe && (phb_pe->state & EEH_PE_ISOLATED))
+		return PCIBIOS_SUCCESSFUL;
+
+	if (phb->eeh_state & PNV_EEH_STATE_ENABLED) {
+		if (*val == EEH_IO_ERROR_VALUE(size) &&
+		    eeh_dev_check_failure(of_node_to_eeh_dev(dn)))
+			return PCIBIOS_DEVICE_NOT_FOUND;
+	} else {
+		pnv_pci_config_check_eeh(phb, dn);
+	}
+#else
+	pnv_pci_config_check_eeh(phb, dn);
+#endif
 
 	return PCIBIOS_SUCCESSFUL;
 }
 
-static int pnv_pci_write_config(struct pci_bus *bus,
-				unsigned int devfn,
-				int where, int size, u32 val)
+int pnv_pci_cfg_write(struct device_node *dn,
+		      int where, int size, u32 val)
 {
-	struct pci_controller *hose = pci_bus_to_host(bus);
-	struct pnv_phb *phb = hose->private_data;
-	u32 bdfn = (((uint64_t)bus->number) << 8) | devfn;
-
-	if (hose == NULL)
-		return PCIBIOS_DEVICE_NOT_FOUND;
+	struct pci_dn *pdn = PCI_DN(dn);
+	struct pnv_phb *phb = pdn->phb->private_data;
+	u32 bdfn = (pdn->busno << 8) | pdn->devfn;
 
-	cfg_dbg("pnv_pci_write_config bus: %x devfn: %x +%x/%x -> %08x\n",
-		bus->number, devfn, where, size, val);
+	cfg_dbg("%s: bus: %x devfn: %x +%x/%x -> %08x\n",
+		pdn->busno, pdn->devfn, where, size, val);
 	switch (size) {
 	case 1:
 		opal_pci_config_write_byte(phb->opal_id, bdfn, where, val);
@@ -322,14 +348,54 @@ static int pnv_pci_write_config(struct pci_bus *bus,
 	default:
 		return PCIBIOS_FUNC_NOT_SUPPORTED;
 	}
+
 	/* Check if the PHB got frozen due to an error (no response) */
-	pnv_pci_config_check_eeh(phb, bus, bdfn);
+#ifdef CONFIG_EEH
+	if (!(phb->eeh_state & PNV_EEH_STATE_ENABLED))
+		pnv_pci_config_check_eeh(phb, dn);
+#else
+	pnv_pci_config_check_eeh(phb, dn);
+#endif
 
 	return PCIBIOS_SUCCESSFUL;
 }
 
+static int pnv_pci_read_config(struct pci_bus *bus,
+			       unsigned int devfn,
+			       int where, int size, u32 *val)
+{
+	struct device_node *dn, *busdn = pci_bus_to_OF_node(bus);
+	struct pci_dn *pdn;
+
+	for (dn = busdn->child; dn; dn = dn->sibling) {
+		pdn = PCI_DN(dn);
+		if (pdn && pdn->devfn == devfn)
+			return pnv_pci_cfg_read(dn, where, size, val);
+	}
+
+	*val = 0xFFFFFFFF;
+	return PCIBIOS_DEVICE_NOT_FOUND;
+
+}
+
+static int pnv_pci_write_config(struct pci_bus *bus,
+				unsigned int devfn,
+				int where, int size, u32 val)
+{
+	struct device_node *dn, *busdn = pci_bus_to_OF_node(bus);
+	struct pci_dn *pdn;
+
+	for (dn = busdn->child; dn; dn = dn->sibling) {
+		pdn = PCI_DN(dn);
+		if (pdn && pdn->devfn == devfn)
+			return pnv_pci_cfg_write(dn, where, size, val);
+	}
+
+	return PCIBIOS_DEVICE_NOT_FOUND;
+}
+
 struct pci_ops pnv_pci_ops = {
-	.read = pnv_pci_read_config,
+	.read  = pnv_pci_read_config,
 	.write = pnv_pci_write_config,
 };
 
@@ -412,6 +478,7 @@ static struct iommu_table *pnv_pci_setup_bml_iommu(struct pci_controller *hose)
 	pnv_pci_setup_iommu_table(tbl, __va(be64_to_cpup(basep)),
 				  be32_to_cpup(sizep), 0);
 	iommu_init_table(tbl, hose->node);
+	iommu_register_group(tbl, pci_domain_nr(hose->bus), 0);
 
 	/* Deal with SW invalidated TCEs when needed (BML way) */
 	swinvp = of_get_property(hose->dn, "linux,tce-sw-invalidate-info",