config PPC_4K_PAGES
bool "4k page size"
- select HAVE_ARCH_SOFT_DIRTY if CHECKPOINT_RESTORE && PPC_BOOK3S
+ select HAVE_ARCH_SOFT_DIRTY if PPC_BOOK3S_64
config PPC_16K_PAGES
bool "16k page size"
config PPC_64K_PAGES
bool "64k page size"
depends on !PPC_FSL_BOOK3E && (44x || PPC_STD_MMU_64 || PPC_BOOK3E_64)
- select HAVE_ARCH_SOFT_DIRTY if CHECKPOINT_RESTORE && PPC_BOOK3S
+ select HAVE_ARCH_SOFT_DIRTY if PPC_BOOK3S_64
config PPC_256K_PAGES
bool "256k page size"
extern void pmdp_invalidate(struct vm_area_struct *vma, unsigned long address,
pmd_t *pmdp);
+#define __HAVE_ARCH_PMDP_HUGE_SPLIT_PREPARE
+extern void pmdp_huge_split_prepare(struct vm_area_struct *vma,
+ unsigned long address, pmd_t *pmdp);
+
#define pmd_move_must_withdraw pmd_move_must_withdraw
struct spinlock;
static inline int pmd_move_must_withdraw(struct spinlock *new_pmd_ptl,
#define EEH_PE_KEEP (1 << 8) /* Keep PE on hotplug */
#define EEH_PE_CFG_RESTRICTED (1 << 9) /* Block config on error */
#define EEH_PE_REMOVED (1 << 10) /* Removed permanently */
+#define EEH_PE_PRI_BUS (1 << 11) /* Cached primary bus */
struct eeh_pe {
int type; /* PE type: PHB/Bus/Device */
extern void hcall_tracepoint_regfunc(void);
extern void hcall_tracepoint_unregfunc(void);
-TRACE_EVENT_FN(hcall_entry,
+TRACE_EVENT_FN_COND(hcall_entry,
TP_PROTO(unsigned long opcode, unsigned long *args),
TP_ARGS(opcode, args),
+ TP_CONDITION(cpu_online(raw_smp_processor_id())),
+
TP_STRUCT__entry(
__field(unsigned long, opcode)
),
hcall_tracepoint_regfunc, hcall_tracepoint_unregfunc
);
-TRACE_EVENT_FN(hcall_exit,
+TRACE_EVENT_FN_COND(hcall_exit,
TP_PROTO(unsigned long opcode, unsigned long retval,
unsigned long *retbuf),
TP_ARGS(opcode, retval, retbuf),
+ TP_CONDITION(cpu_online(raw_smp_processor_id())),
+
TP_STRUCT__entry(
__field(unsigned long, opcode)
__field(unsigned long, retval)
*/
eeh_pe_state_mark(pe, EEH_PE_KEEP);
if (bus) {
+ eeh_pe_state_clear(pe, EEH_PE_PRI_BUS);
pci_lock_rescan_remove();
pcibios_remove_pci_devices(bus);
pci_unlock_rescan_remove();
* the their PCI config any more.
*/
if (frozen_bus) {
+ eeh_pe_state_clear(pe, EEH_PE_PRI_BUS);
eeh_pe_dev_mode_mark(pe, EEH_DEV_REMOVED);
pci_lock_rescan_remove();
continue;
/* Notify all devices to be down */
+ eeh_pe_state_clear(pe, EEH_PE_PRI_BUS);
bus = eeh_pe_bus_get(phb_pe);
eeh_pe_dev_traverse(pe,
eeh_report_failure, NULL);
bus = pe->phb->bus;
} else if (pe->type & EEH_PE_BUS ||
pe->type & EEH_PE_DEVICE) {
- if (pe->bus) {
+ if (pe->state & EEH_PE_PRI_BUS) {
bus = pe->bus;
goto out;
}
if (name[0] == '.') {
if (strcmp(name+1, "TOC.") == 0)
syms[i].st_shndx = SHN_ABS;
- memmove(name, name+1, strlen(name));
+ syms[i].st_name++;
}
}
}
return pgtable;
}
+void pmdp_huge_split_prepare(struct vm_area_struct *vma,
+ unsigned long address, pmd_t *pmdp)
+{
+ VM_BUG_ON(address & ~HPAGE_PMD_MASK);
+ VM_BUG_ON(REGION_ID(address) != USER_REGION_ID);
+
+ /*
+ * We can't mark the pmd none here, because that will cause a race
+ * against exit_mmap. We need to continue mark pmd TRANS HUGE, while
+ * we spilt, but at the same time we wan't rest of the ppc64 code
+ * not to insert hash pte on this, because we will be modifying
+ * the deposited pgtable in the caller of this function. Hence
+ * clear the _PAGE_USER so that we move the fault handling to
+ * higher level function and that will serialize against ptl.
+ * We need to flush existing hash pte entries here even though,
+ * the translation is still valid, because we will withdraw
+ * pgtable_t after this.
+ */
+ pmd_hugepage_update(vma->vm_mm, address, pmdp, _PAGE_USER, 0);
+}
+
+
/*
* set a new huge pmd. We should not be called for updating
* an existing pmd entry. That should go via pmd_hugepage_update.
return set_pte_at(mm, addr, pmdp_ptep(pmdp), pmd_pte(pmd));
}
+/*
+ * We use this to invalidate a pmdp entry before switching from a
+ * hugepte to regular pmd entry.
+ */
void pmdp_invalidate(struct vm_area_struct *vma, unsigned long address,
pmd_t *pmdp)
{
pmd_hugepage_update(vma->vm_mm, address, pmdp, _PAGE_PRESENT, 0);
+
+ /*
+ * This ensures that generic code that rely on IRQ disabling
+ * to prevent a parallel THP split work as expected.
+ */
+ kick_all_cpus_sync();
}
/*
* PCI devices of the PE are expected to be removed prior
* to PE reset.
*/
- if (!edev->pe->bus)
+ if (!(edev->pe->state & EEH_PE_PRI_BUS)) {
edev->pe->bus = pci_find_bus(hose->global_number,
pdn->busno);
+ if (edev->pe->bus)
+ edev->pe->state |= EEH_PE_PRI_BUS;
+ }
/*
* Enable EEH explicitly so that we will do EEH check
static const struct pci_controller_ops pnv_pci_ioda_controller_ops = {
.dma_dev_setup = pnv_pci_dma_dev_setup,
+ .dma_bus_setup = pnv_pci_dma_bus_setup,
#ifdef CONFIG_PCI_MSI
.setup_msi_irqs = pnv_setup_msi_irqs,
.teardown_msi_irqs = pnv_teardown_msi_irqs,
u64 rpn = __pa(uaddr) >> tbl->it_page_shift;
long i;
+ if (proto_tce & TCE_PCI_WRITE)
+ proto_tce |= TCE_PCI_READ;
+
for (i = 0; i < npages; i++) {
unsigned long newtce = proto_tce |
((rpn + i) << tbl->it_page_shift);
BUG_ON(*hpa & ~IOMMU_PAGE_MASK(tbl));
+ if (newtce & TCE_PCI_WRITE)
+ newtce |= TCE_PCI_READ;
+
oldtce = xchg(pnv_tce(tbl, idx), cpu_to_be64(newtce));
*hpa = be64_to_cpu(oldtce) & ~(TCE_PCI_READ | TCE_PCI_WRITE);
*direction = iommu_tce_direction(oldtce);
phb->dma_dev_setup(phb, pdev);
}
+void pnv_pci_dma_bus_setup(struct pci_bus *bus)
+{
+ struct pci_controller *hose = bus->sysdata;
+ struct pnv_phb *phb = hose->private_data;
+ struct pnv_ioda_pe *pe;
+
+ list_for_each_entry(pe, &phb->ioda.pe_list, list) {
+ if (!(pe->flags & (PNV_IODA_PE_BUS | PNV_IODA_PE_BUS_ALL)))
+ continue;
+
+ if (!pe->pbus)
+ continue;
+
+ if (bus->number == ((pe->rid >> 8) & 0xFF)) {
+ pe->pbus = bus;
+ break;
+ }
+ }
+}
+
void pnv_pci_shutdown(void)
{
struct pci_controller *hose;
extern int pnv_eeh_phb_reset(struct pci_controller *hose, int option);
extern void pnv_pci_dma_dev_setup(struct pci_dev *pdev);
+extern void pnv_pci_dma_bus_setup(struct pci_bus *bus);
extern int pnv_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type);
extern void pnv_teardown_msi_irqs(struct pci_dev *pdev);
pmd_t *pmdp);
#endif
+#ifndef __HAVE_ARCH_PMDP_HUGE_SPLIT_PREPARE
+static inline void pmdp_huge_split_prepare(struct vm_area_struct *vma,
+ unsigned long address, pmd_t *pmdp)
+{
+
+}
+#endif
+
#ifndef __HAVE_ARCH_PTE_SAME
static inline int pte_same(pte_t pte_a, pte_t pte_b)
{
young = pmd_young(*pmd);
dirty = pmd_dirty(*pmd);
+ pmdp_huge_split_prepare(vma, haddr, pmd);
pgtable = pgtable_trans_huge_withdraw(mm, pmd);
pmd_populate(mm, &_pmd, pgtable);