powerpc fixes for 4.5 #3

- eeh: Fix partial hotplug criterion from Gavin Shan
  - mm: Clear the invalid slot information correctly from Aneesh Kumar K.V
 -----BEGIN PGP SIGNATURE-----
 Version: GnuPG v1
 
 iQIcBAABAgAGBQJWzXquAAoJEFHr6jzI4aWADHsP/2lbwqz/vS3Ep4zlySHNvStL
 /DrRN2TN35THZ59FPRxgEfeqPxTCXtbpD6zEXwD0gf6m39I2zArhaQMOHXMtVPvV
 p0nAtwR0PX/PxlQTJDpHlg074vVAD7s3iuvad6oNQObLcXhoZ7wYtbStZ9Ithm4R
 YfqZTelzsw+GfMuTYnvAQf5aoRYztUpy7OheaJbbDmSZgMFwF896ZPJnaG9rAOPE
 xcSsRaSfHiUR2NE2ua1K5yya+1ilZqrZhib7QxXgzGuxoVa2AAiPR7Hpx2kX1Wm+
 z0DqPXISzRbVf9zyLgWD3TpJ4OMHI/CYVW+t/Gx/yWCMfNcfavUrh0vPdHRVEPZu
 zxmIUoI6yv7jQ6bcfdzR5s0Mr5pYWlUj5MZg2r8aGqloYcLPk5DiENg+c0QmKI05
 kQPCBoQz2ezzJWAt1BYshkc+mlimv3ODaNWFP34Nc6kcDaSO6a0rhVOecvKuR6dv
 UBNpeh5np1rKq1wX0ri0yAmnm//yXqe+bK0I8Ctipi0++e73sVJGzfFdVvXwEhhW
 h+v1BkdgW8WK/xlH+JCPiXd5dfXrUeFI0D65Kgpb7IbFc9hcXDmp2Dv7+8zx/Wcl
 L2NpuucSDxi+LHkE10QiypgLWSKjn9OSi8PLocqABNXG8uHxIp54jRfyViBNALXF
 XlPveqTgpt7On3aa0qVh
 =bk3U
 -----END PGP SIGNATURE-----

Merge tag 'powerpc-4.5-4' into next

Pull in our current fixes from 4.5, in particular the "Fix Multi hit
ERAT" bug is causing folks some grief when testing next.

arch/powerpc/Kconfig

@@ -557,7 +557,7 @@ choice
 
 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"
@@ -566,7 +566,7 @@ config PPC_16K_PAGES
 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"

arch/powerpc/include/asm/book3s/64/pgtable.h

@@ -281,6 +281,10 @@ extern pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp);
 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,

arch/powerpc/include/asm/eeh.h

@@ -81,6 +81,7 @@ struct pci_dn;
 #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	*/

arch/powerpc/include/asm/trace.h

@@ -57,12 +57,14 @@ DEFINE_EVENT(ppc64_interrupt_class, timer_interrupt_exit,
 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)
 	),
@@ -76,13 +78,15 @@ TRACE_EVENT_FN(hcall_entry,
 	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)

arch/powerpc/kernel/eeh_driver.c

@@ -418,8 +418,7 @@ static void *eeh_rmv_device(void *data, void *userdata)
 		eeh_pcid_put(dev);
 		if (driver->err_handler &&
 		    driver->err_handler->error_detected &&
-		    driver->err_handler->slot_reset &&
-		    driver->err_handler->resume)
+		    driver->err_handler->slot_reset)
 			return NULL;
 	}
 
@@ -564,6 +563,7 @@ static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus)
 	 */
 	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();
@@ -803,6 +803,7 @@ perm_error:
 	 * 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();
@@ -886,6 +887,7 @@ static void eeh_handle_special_event(void)
 					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);

arch/powerpc/kernel/eeh_pe.c

@@ -928,7 +928,7 @@ struct pci_bus *eeh_pe_bus_get(struct eeh_pe *pe)
 		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;
 		}

arch/powerpc/kernel/module_64.c

@@ -340,7 +340,7 @@ static void dedotify(Elf64_Sym *syms, unsigned int numsyms, char *strtab)
 			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++;
 			}
 		}
 	}

arch/powerpc/mm/hash64_64k.c

@@ -111,7 +111,13 @@ int __hash_page_4K(unsigned long ea, unsigned long access, unsigned long vsid,
 	 */
 	if (!(old_pte & _PAGE_COMBO)) {
 		flush_hash_page(vpn, rpte, MMU_PAGE_64K, ssize, flags);
-		old_pte &= ~_PAGE_HASHPTE | _PAGE_F_GIX | _PAGE_F_SECOND;
+		/*
+		 * clear the old slot details from the old and new pte.
+		 * On hash insert failure we use old pte value and we don't
+		 * want slot information there if we have a insert failure.
+		 */
+		old_pte &= ~(_PAGE_HASHPTE | _PAGE_F_GIX | _PAGE_F_SECOND);
+		new_pte &= ~(_PAGE_HASHPTE | _PAGE_F_GIX | _PAGE_F_SECOND);
 		goto htab_insert_hpte;
 	}
 	/*

arch/powerpc/mm/hugepage-hash64.c

@@ -78,9 +78,19 @@ int __hash_page_thp(unsigned long ea, unsigned long access, unsigned long vsid,
 		 * base page size. This is because demote_segment won't flush
 		 * hash page table entries.
 		 */
-		if ((old_pmd & _PAGE_HASHPTE) && !(old_pmd & _PAGE_COMBO))
+		if ((old_pmd & _PAGE_HASHPTE) && !(old_pmd & _PAGE_COMBO)) {
 			flush_hash_hugepage(vsid, ea, pmdp, MMU_PAGE_64K,
 					    ssize, flags);
+			/*
+			 * With THP, we also clear the slot information with
+			 * respect to all the 64K hash pte mapping the 16MB
+			 * page. They are all invalid now. This make sure we
+			 * don't find the slot valid when we fault with 4k
+			 * base page size.
+			 *
+			 */
+			memset(hpte_slot_array, 0, PTE_FRAG_SIZE);
+		}
 	}
 
 	valid = hpte_valid(hpte_slot_array, index);

arch/powerpc/mm/pgtable_64.c

@@ -646,6 +646,28 @@ pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp)
 	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.
@@ -663,10 +685,20 @@ void set_pmd_at(struct mm_struct *mm, unsigned long addr,
 	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();
 }
 
 /*

arch/powerpc/platforms/powernv/eeh-powernv.c

@@ -428,9 +428,12 @@ static void *pnv_eeh_probe(struct pci_dn *pdn, void *data)
 	 * 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

arch/powerpc/platforms/powernv/pci-ioda.c

@@ -3211,6 +3211,7 @@ static void pnv_pci_ioda_shutdown(struct pci_controller *hose)
 
 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,

arch/powerpc/platforms/powernv/pci.c

@@ -596,6 +596,9 @@ int pnv_tce_build(struct iommu_table *tbl, long index, long npages,
 	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);
@@ -617,6 +620,9 @@ int pnv_tce_xchg(struct iommu_table *tbl, long index,
 
 	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);
@@ -757,6 +763,26 @@ void pnv_pci_dma_dev_setup(struct pci_dev *pdev)
 		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;

arch/powerpc/platforms/powernv/pci.h

@@ -232,6 +232,7 @@ extern void pnv_pci_reset_secondary_bus(struct pci_dev *dev);
 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);
 

include/asm-generic/pgtable.h

@@ -239,6 +239,14 @@ extern void pmdp_invalidate(struct vm_area_struct *vma, unsigned long address,
 			    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)
 {

mm/huge_memory.c

@@ -2860,6 +2860,7 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd,
 	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);