Merge tag 'powerpc-4.7-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux

Pull powerpc updates from Michael Ellerman:
 "Highlights:
   - Support for Power ISA 3.0 (Power9) Radix Tree MMU from Aneesh Kumar K.V
   - Live patching support for ppc64le (also merged via livepatching.git)

  Various cleanups & minor fixes from:
   - Aaro Koskinen, Alexey Kardashevskiy, Andrew Donnellan, Aneesh Kumar K.V,
     Chris Smart, Daniel Axtens, Frederic Barrat, Gavin Shan, Ian Munsie,
     Lennart Sorensen, Madhavan Srinivasan, Mahesh Salgaonkar, Markus Elfring,
     Michael Ellerman, Oliver O'Halloran, Paul Gortmaker, Paul Mackerras,
     Rashmica Gupta, Russell Currey, Suraj Jitindar Singh, Thiago Jung
     Bauermann, Valentin Rothberg, Vipin K Parashar.

  General:
   - Update LMB associativity index during DLPAR add/remove from Nathan
     Fontenot
   - Fix branching to OOL handlers in relocatable kernel from Hari Bathini
   - Add support for userspace Power9 copy/paste from Chris Smart
   - Always use STRICT_MM_TYPECHECKS from Michael Ellerman
   - Add mask of possible MMU features from Michael Ellerman

  PCI:
   - Enable pass through of NVLink to guests from Alexey Kardashevskiy
   - Cleanups in preparation for powernv PCI hotplug from Gavin Shan
   - Don't report error in eeh_pe_reset_and_recover() from Gavin Shan
   - Restore initial state in eeh_pe_reset_and_recover() from Gavin Shan
   - Revert "powerpc/eeh: Fix crash in eeh_add_device_early() on Cell"
     from Guilherme G Piccoli
   - Remove the dependency on EEH struct in DDW mechanism from Guilherme
     G Piccoli

  selftests:
   - Test cp_abort during context switch from Chris Smart
   - Add several tests for transactional memory support from Rashmica
     Gupta

  perf:
   - Add support for sampling interrupt register state from Anju T
   - Add support for unwinding perf-stackdump from Chandan Kumar

  cxl:
   - Configure the PSL for two CAPI ports on POWER8NVL from Philippe
     Bergheaud
   - Allow initialization on timebase sync failures from Frederic Barrat
   - Increase timeout for detection of AFU mmio hang from Frederic
     Barrat
   - Handle num_of_processes larger than can fit in the SPA from Ian
     Munsie
   - Ensure PSL interrupt is configured for contexts with no AFU IRQs
     from Ian Munsie
   - Add kernel API to allow a context to operate with relocate disabled
     from Ian Munsie
   - Check periodically the coherent platform function's state from
     Christophe Lombard

  Freescale:
   - Updates from Scott: "Contains 86xx fixes, minor device tree fixes,
     an erratum workaround, and a kconfig dependency fix."

* tag 'powerpc-4.7-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux: (192 commits)
  powerpc/86xx: Fix PCI interrupt map definition
  powerpc/86xx: Move pci1 definition to the include file
  powerpc/fsl: Fix build of the dtb embedded kernel images
  powerpc/fsl: Fix rcpm compatible string
  powerpc/fsl: Remove FSL_SOC dependency from FSL_LBC
  powerpc/fsl-pci: Add a workaround for PCI 5 errata
  powerpc/fsl: Fix SPI compatible on t208xrdb and t1040rdb
  powerpc/powernv/npu: Add PE to PHB's list
  powerpc/powernv: Fix insufficient memory allocation
  powerpc/iommu: Remove the dependency on EEH struct in DDW mechanism
  Revert "powerpc/eeh: Fix crash in eeh_add_device_early() on Cell"
  powerpc/eeh: Drop unnecessary label in eeh_pe_change_owner()
  powerpc/eeh: Ignore handlers in eeh_pe_reset_and_recover()
  powerpc/eeh: Restore initial state in eeh_pe_reset_and_recover()
  powerpc/eeh: Don't report error in eeh_pe_reset_and_recover()
  Revert "powerpc/powernv: Exclude root bus in pnv_pci_reset_secondary_bus()"
  powerpc/powernv/npu: Enable NVLink pass through
  powerpc/powernv/npu: Rework TCE Kill handling
  powerpc/powernv/npu: Add set/unset window helpers
  powerpc/powernv/ioda2: Export debug helper pe_level_printk()
  ...

1 files changed, 342 insertions, 0 deletions

diff --git a/arch/powerpc/mm/pgtable-hash64.c b/arch/powerpc/mm/pgtable-hash64.c
new file mode 100644
index 0000000..c23e286
--- /dev/null
+++ b/arch/powerpc/mm/pgtable-hash64.c
@@ -0,0 +1,342 @@
+/*
+ * Copyright 2005, Paul Mackerras, IBM Corporation.
+ * Copyright 2009, Benjamin Herrenschmidt, IBM Corporation.
+ * Copyright 2015-2016, Aneesh Kumar K.V, IBM Corporation.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/sched.h>
+#include <asm/pgalloc.h>
+#include <asm/tlb.h>
+
+#include "mmu_decl.h"
+
+#define CREATE_TRACE_POINTS
+#include <trace/events/thp.h>
+
+#ifdef CONFIG_SPARSEMEM_VMEMMAP
+/*
+ * On hash-based CPUs, the vmemmap is bolted in the hash table.
+ *
+ */
+int __meminit hash__vmemmap_create_mapping(unsigned long start,
+				       unsigned long page_size,
+				       unsigned long phys)
+{
+	int rc = htab_bolt_mapping(start, start + page_size, phys,
+				   pgprot_val(PAGE_KERNEL),
+				   mmu_vmemmap_psize, mmu_kernel_ssize);
+	if (rc < 0) {
+		int rc2 = htab_remove_mapping(start, start + page_size,
+					      mmu_vmemmap_psize,
+					      mmu_kernel_ssize);
+		BUG_ON(rc2 && (rc2 != -ENOENT));
+	}
+	return rc;
+}
+
+#ifdef CONFIG_MEMORY_HOTPLUG
+void hash__vmemmap_remove_mapping(unsigned long start,
+			      unsigned long page_size)
+{
+	int rc = htab_remove_mapping(start, start + page_size,
+				     mmu_vmemmap_psize,
+				     mmu_kernel_ssize);
+	BUG_ON((rc < 0) && (rc != -ENOENT));
+	WARN_ON(rc == -ENOENT);
+}
+#endif
+#endif /* CONFIG_SPARSEMEM_VMEMMAP */
+
+/*
+ * map_kernel_page currently only called by __ioremap
+ * map_kernel_page adds an entry to the ioremap page table
+ * and adds an entry to the HPT, possibly bolting it
+ */
+int hash__map_kernel_page(unsigned long ea, unsigned long pa, unsigned long flags)
+{
+	pgd_t *pgdp;
+	pud_t *pudp;
+	pmd_t *pmdp;
+	pte_t *ptep;
+
+	BUILD_BUG_ON(TASK_SIZE_USER64 > H_PGTABLE_RANGE);
+	if (slab_is_available()) {
+		pgdp = pgd_offset_k(ea);
+		pudp = pud_alloc(&init_mm, pgdp, ea);
+		if (!pudp)
+			return -ENOMEM;
+		pmdp = pmd_alloc(&init_mm, pudp, ea);
+		if (!pmdp)
+			return -ENOMEM;
+		ptep = pte_alloc_kernel(pmdp, ea);
+		if (!ptep)
+			return -ENOMEM;
+		set_pte_at(&init_mm, ea, ptep, pfn_pte(pa >> PAGE_SHIFT,
+							  __pgprot(flags)));
+	} else {
+		/*
+		 * If the mm subsystem is not fully up, we cannot create a
+		 * linux page table entry for this mapping.  Simply bolt an
+		 * entry in the hardware page table.
+		 *
+		 */
+		if (htab_bolt_mapping(ea, ea + PAGE_SIZE, pa, flags,
+				      mmu_io_psize, mmu_kernel_ssize)) {
+			printk(KERN_ERR "Failed to do bolted mapping IO "
+			       "memory at %016lx !\n", pa);
+			return -ENOMEM;
+		}
+	}
+
+	smp_wmb();
+	return 0;
+}
+
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+
+unsigned long hash__pmd_hugepage_update(struct mm_struct *mm, unsigned long addr,
+				    pmd_t *pmdp, unsigned long clr,
+				    unsigned long set)
+{
+	__be64 old_be, tmp;
+	unsigned long old;
+
+#ifdef CONFIG_DEBUG_VM
+	WARN_ON(!pmd_trans_huge(*pmdp));
+	assert_spin_locked(&mm->page_table_lock);
+#endif
+
+	__asm__ __volatile__(
+	"1:	ldarx	%0,0,%3\n\
+		and.	%1,%0,%6\n\
+		bne-	1b \n\
+		andc	%1,%0,%4 \n\
+		or	%1,%1,%7\n\
+		stdcx.	%1,0,%3 \n\
+		bne-	1b"
+	: "=&r" (old_be), "=&r" (tmp), "=m" (*pmdp)
+	: "r" (pmdp), "r" (cpu_to_be64(clr)), "m" (*pmdp),
+	  "r" (cpu_to_be64(H_PAGE_BUSY)), "r" (cpu_to_be64(set))
+	: "cc" );
+
+	old = be64_to_cpu(old_be);
+
+	trace_hugepage_update(addr, old, clr, set);
+	if (old & H_PAGE_HASHPTE)
+		hpte_do_hugepage_flush(mm, addr, pmdp, old);
+	return old;
+}
+
+pmd_t hash__pmdp_collapse_flush(struct vm_area_struct *vma, unsigned long address,
+			    pmd_t *pmdp)
+{
+	pmd_t pmd;
+
+	VM_BUG_ON(address & ~HPAGE_PMD_MASK);
+	VM_BUG_ON(pmd_trans_huge(*pmdp));
+
+	pmd = *pmdp;
+	pmd_clear(pmdp);
+	/*
+	 * Wait for all pending hash_page to finish. This is needed
+	 * in case of subpage collapse. When we collapse normal pages
+	 * to hugepage, we first clear the pmd, then invalidate all
+	 * the PTE entries. The assumption here is that any low level
+	 * page fault will see a none pmd and take the slow path that
+	 * will wait on mmap_sem. But we could very well be in a
+	 * hash_page with local ptep pointer value. Such a hash page
+	 * can result in adding new HPTE entries for normal subpages.
+	 * That means we could be modifying the page content as we
+	 * copy them to a huge page. So wait for parallel hash_page
+	 * to finish before invalidating HPTE entries. We can do this
+	 * by sending an IPI to all the cpus and executing a dummy
+	 * function there.
+	 */
+	kick_all_cpus_sync();
+	/*
+	 * Now invalidate the hpte entries in the range
+	 * covered by pmd. This make sure we take a
+	 * fault and will find the pmd as none, which will
+	 * result in a major fault which takes mmap_sem and
+	 * hence wait for collapse to complete. Without this
+	 * the __collapse_huge_page_copy can result in copying
+	 * the old content.
+	 */
+	flush_tlb_pmd_range(vma->vm_mm, &pmd, address);
+	return pmd;
+}
+
+/*
+ * We want to put the pgtable in pmd and use pgtable for tracking
+ * the base page size hptes
+ */
+void hash__pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp,
+				  pgtable_t pgtable)
+{
+	pgtable_t *pgtable_slot;
+	assert_spin_locked(&mm->page_table_lock);
+	/*
+	 * we store the pgtable in the second half of PMD
+	 */
+	pgtable_slot = (pgtable_t *)pmdp + PTRS_PER_PMD;
+	*pgtable_slot = pgtable;
+	/*
+	 * expose the deposited pgtable to other cpus.
+	 * before we set the hugepage PTE at pmd level
+	 * hash fault code looks at the deposted pgtable
+	 * to store hash index values.
+	 */
+	smp_wmb();
+}
+
+pgtable_t hash__pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp)
+{
+	pgtable_t pgtable;
+	pgtable_t *pgtable_slot;
+
+	assert_spin_locked(&mm->page_table_lock);
+	pgtable_slot = (pgtable_t *)pmdp + PTRS_PER_PMD;
+	pgtable = *pgtable_slot;
+	/*
+	 * Once we withdraw, mark the entry NULL.
+	 */
+	*pgtable_slot = NULL;
+	/*
+	 * We store HPTE information in the deposited PTE fragment.
+	 * zero out the content on withdraw.
+	 */
+	memset(pgtable, 0, PTE_FRAG_SIZE);
+	return pgtable;
+}
+
+void hash__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, 0, _PAGE_PRIVILEGED);
+}
+
+/*
+ * A linux hugepage PMD was changed and the corresponding hash table entries
+ * neesd to be flushed.
+ */
+void hpte_do_hugepage_flush(struct mm_struct *mm, unsigned long addr,
+			    pmd_t *pmdp, unsigned long old_pmd)
+{
+	int ssize;
+	unsigned int psize;
+	unsigned long vsid;
+	unsigned long flags = 0;
+	const struct cpumask *tmp;
+
+	/* get the base page size,vsid and segment size */
+#ifdef CONFIG_DEBUG_VM
+	psize = get_slice_psize(mm, addr);
+	BUG_ON(psize == MMU_PAGE_16M);
+#endif
+	if (old_pmd & H_PAGE_COMBO)
+		psize = MMU_PAGE_4K;
+	else
+		psize = MMU_PAGE_64K;
+
+	if (!is_kernel_addr(addr)) {
+		ssize = user_segment_size(addr);
+		vsid = get_vsid(mm->context.id, addr, ssize);
+		WARN_ON(vsid == 0);
+	} else {
+		vsid = get_kernel_vsid(addr, mmu_kernel_ssize);
+		ssize = mmu_kernel_ssize;
+	}
+
+	tmp = cpumask_of(smp_processor_id());
+	if (cpumask_equal(mm_cpumask(mm), tmp))
+		flags |= HPTE_LOCAL_UPDATE;
+
+	return flush_hash_hugepage(vsid, addr, pmdp, psize, ssize, flags);
+}
+
+pmd_t hash__pmdp_huge_get_and_clear(struct mm_struct *mm,
+				unsigned long addr, pmd_t *pmdp)
+{
+	pmd_t old_pmd;
+	pgtable_t pgtable;
+	unsigned long old;
+	pgtable_t *pgtable_slot;
+
+	old = pmd_hugepage_update(mm, addr, pmdp, ~0UL, 0);
+	old_pmd = __pmd(old);
+	/*
+	 * We have pmd == none and we are holding page_table_lock.
+	 * So we can safely go and clear the pgtable hash
+	 * index info.
+	 */
+	pgtable_slot = (pgtable_t *)pmdp + PTRS_PER_PMD;
+	pgtable = *pgtable_slot;
+	/*
+	 * Let's zero out old valid and hash index details
+	 * hash fault look at them.
+	 */
+	memset(pgtable, 0, PTE_FRAG_SIZE);
+	/*
+	 * Serialize against find_linux_pte_or_hugepte which does lock-less
+	 * lookup in page tables with local interrupts disabled. For huge pages
+	 * it casts pmd_t to pte_t. Since format of pte_t is different from
+	 * pmd_t we want to prevent transit from pmd pointing to page table
+	 * to pmd pointing to huge page (and back) while interrupts are disabled.
+	 * We clear pmd to possibly replace it with page table pointer in
+	 * different code paths. So make sure we wait for the parallel
+	 * find_linux_pte_or_hugepage to finish.
+	 */
+	kick_all_cpus_sync();
+	return old_pmd;
+}
+
+int hash__has_transparent_hugepage(void)
+{
+
+	if (!mmu_has_feature(MMU_FTR_16M_PAGE))
+		return 0;
+	/*
+	 * We support THP only if PMD_SIZE is 16MB.
+	 */
+	if (mmu_psize_defs[MMU_PAGE_16M].shift != PMD_SHIFT)
+		return 0;
+	/*
+	 * We need to make sure that we support 16MB hugepage in a segement
+	 * with base page size 64K or 4K. We only enable THP with a PAGE_SIZE
+	 * of 64K.
+	 */
+	/*
+	 * If we have 64K HPTE, we will be using that by default
+	 */
+	if (mmu_psize_defs[MMU_PAGE_64K].shift &&
+	    (mmu_psize_defs[MMU_PAGE_64K].penc[MMU_PAGE_16M] == -1))
+		return 0;
+	/*
+	 * Ok we only have 4K HPTE
+	 */
+	if (mmu_psize_defs[MMU_PAGE_4K].penc[MMU_PAGE_16M] == -1)
+		return 0;
+
+	return 1;
+}
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE */