Merge tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/cmarinas/linux-aarch64

Pull ARM64 updates from Catalin Marinas:
 "Main features:
   - KVM and Xen ports to AArch64
   - Hugetlbfs and transparent huge pages support for arm64
   - Applied Micro X-Gene Kconfig entry and dts file
   - Cache flushing improvements

  For arm64 huge pages support, there are x86 changes moving part of
  arch/x86/mm/hugetlbpage.c into mm/hugetlb.c to be re-used by arm64"

* tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/cmarinas/linux-aarch64: (66 commits)
  arm64: Add initial DTS for APM X-Gene Storm SOC and APM Mustang board
  arm64: Add defines for APM ARMv8 implementation
  arm64: Enable APM X-Gene SOC family in the defconfig
  arm64: Add Kconfig option for APM X-Gene SOC family
  arm64/Makefile: provide vdso_install target
  ARM64: mm: THP support.
  ARM64: mm: Raise MAX_ORDER for 64KB pages and THP.
  ARM64: mm: HugeTLB support.
  ARM64: mm: Move PTE_PROT_NONE bit.
  ARM64: mm: Make PAGE_NONE pages read only and no-execute.
  ARM64: mm: Restore memblock limit when map_mem finished.
  mm: thp: Correct the HPAGE_PMD_ORDER check.
  x86: mm: Remove general hugetlb code from x86.
  mm: hugetlb: Copy general hugetlb code from x86 to mm.
  x86: mm: Remove x86 version of huge_pmd_share.
  mm: hugetlb: Copy huge_pmd_share from x86 to mm.
  arm64: KVM: document kernel object mappings in HYP
  arm64: KVM: MAINTAINERS update
  arm64: KVM: userspace API documentation
  arm64: KVM: enable initialization of a 32bit vcpu
  ...

1 files changed, 210 insertions, 9 deletions

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 5cf99bf8cce2..aed085ad11a8 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -2948,15 +2948,6 @@ out_mutex:
         return ret;
 }
 
-/* Can be overriden by architectures */
-__attribute__((weak)) struct page *
-follow_huge_pud(struct mm_struct *mm, unsigned long address,
-               pud_t *pud, int write)
-{
-        BUG();
-        return NULL;
-}
-
 long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma,
                          struct page **pages, struct vm_area_struct **vmas,
                          unsigned long *position, unsigned long *nr_pages,
@@ -3186,6 +3177,216 @@ void hugetlb_unreserve_pages(struct inode *inode, long offset, long freed)
         hugetlb_acct_memory(h, -(chg - freed));
 }
 
+#ifdef CONFIG_ARCH_WANT_HUGE_PMD_SHARE
+static unsigned long page_table_shareable(struct vm_area_struct *svma,
+                                struct vm_area_struct *vma,
+                                unsigned long addr, pgoff_t idx)
+{
+        unsigned long saddr = ((idx - svma->vm_pgoff) << PAGE_SHIFT) +
+                                svma->vm_start;
+        unsigned long sbase = saddr & PUD_MASK;
+        unsigned long s_end = sbase + PUD_SIZE;
+
+        /* Allow segments to share if only one is marked locked */
+        unsigned long vm_flags = vma->vm_flags & ~VM_LOCKED;
+        unsigned long svm_flags = svma->vm_flags & ~VM_LOCKED;
+
+        /*
+         * match the virtual addresses, permission and the alignment of the
+         * page table page.
+         */
+        if (pmd_index(addr) != pmd_index(saddr) ||
+            vm_flags != svm_flags ||
+            sbase < svma->vm_start || svma->vm_end < s_end)
+                return 0;
+
+        return saddr;
+}
+
+static int vma_shareable(struct vm_area_struct *vma, unsigned long addr)
+{
+        unsigned long base = addr & PUD_MASK;
+        unsigned long end = base + PUD_SIZE;
+
+        /*
+         * check on proper vm_flags and page table alignment
+         */
+        if (vma->vm_flags & VM_MAYSHARE &&
+            vma->vm_start <= base && end <= vma->vm_end)
+                return 1;
+        return 0;
+}
+
+/*
+ * Search for a shareable pmd page for hugetlb. In any case calls pmd_alloc()
+ * and returns the corresponding pte. While this is not necessary for the
+ * !shared pmd case because we can allocate the pmd later as well, it makes the
+ * code much cleaner. pmd allocation is essential for the shared case because
+ * pud has to be populated inside the same i_mmap_mutex section - otherwise
+ * racing tasks could either miss the sharing (see huge_pte_offset) or select a
+ * bad pmd for sharing.
+ */
+pte_t *huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud)
+{
+        struct vm_area_struct *vma = find_vma(mm, addr);
+        struct address_space *mapping = vma->vm_file->f_mapping;
+        pgoff_t idx = ((addr - vma->vm_start) >> PAGE_SHIFT) +
+                        vma->vm_pgoff;
+        struct vm_area_struct *svma;
+        unsigned long saddr;
+        pte_t *spte = NULL;
+        pte_t *pte;
+
+        if (!vma_shareable(vma, addr))
+                return (pte_t *)pmd_alloc(mm, pud, addr);
+
+        mutex_lock(&mapping->i_mmap_mutex);
+        vma_interval_tree_foreach(svma, &mapping->i_mmap, idx, idx) {
+                if (svma == vma)
+                        continue;
+
+                saddr = page_table_shareable(svma, vma, addr, idx);
+                if (saddr) {
+                        spte = huge_pte_offset(svma->vm_mm, saddr);
+                        if (spte) {
+                                get_page(virt_to_page(spte));
+                                break;
+                        }
+                }
+        }
+
+        if (!spte)
+                goto out;
+
+        spin_lock(&mm->page_table_lock);
+        if (pud_none(*pud))
+                pud_populate(mm, pud,
+                                (pmd_t *)((unsigned long)spte & PAGE_MASK));
+        else
+                put_page(virt_to_page(spte));
+        spin_unlock(&mm->page_table_lock);
+out:
+        pte = (pte_t *)pmd_alloc(mm, pud, addr);
+        mutex_unlock(&mapping->i_mmap_mutex);
+        return pte;
+}
+
+/*
+ * unmap huge page backed by shared pte.
+ *
+ * Hugetlb pte page is ref counted at the time of mapping.  If pte is shared
+ * indicated by page_count > 1, unmap is achieved by clearing pud and
+ * decrementing the ref count. If count == 1, the pte page is not shared.
+ *
+ * called with vma->vm_mm->page_table_lock held.
+ *
+ * returns: 1 successfully unmapped a shared pte page
+ *          0 the underlying pte page is not shared, or it is the last user
+ */
+int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep)
+{
+        pgd_t *pgd = pgd_offset(mm, *addr);
+        pud_t *pud = pud_offset(pgd, *addr);
+
+        BUG_ON(page_count(virt_to_page(ptep)) == 0);
+        if (page_count(virt_to_page(ptep)) == 1)
+                return 0;
+
+        pud_clear(pud);
+        put_page(virt_to_page(ptep));
+        *addr = ALIGN(*addr, HPAGE_SIZE * PTRS_PER_PTE) - HPAGE_SIZE;
+        return 1;
+}
+#define want_pmd_share()        (1)
+#else /* !CONFIG_ARCH_WANT_HUGE_PMD_SHARE */
+pte_t *huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud)
+{
+        return NULL;
+}
+#define want_pmd_share()        (0)
+#endif /* CONFIG_ARCH_WANT_HUGE_PMD_SHARE */
+
+#ifdef CONFIG_ARCH_WANT_GENERAL_HUGETLB
+pte_t *huge_pte_alloc(struct mm_struct *mm,
+                        unsigned long addr, unsigned long sz)
+{
+        pgd_t *pgd;
+        pud_t *pud;
+        pte_t *pte = NULL;
+
+        pgd = pgd_offset(mm, addr);
+        pud = pud_alloc(mm, pgd, addr);
+        if (pud) {
+                if (sz == PUD_SIZE) {
+                        pte = (pte_t *)pud;
+                } else {
+                        BUG_ON(sz != PMD_SIZE);
+                        if (want_pmd_share() && pud_none(*pud))
+                                pte = huge_pmd_share(mm, addr, pud);
+                        else
+                                pte = (pte_t *)pmd_alloc(mm, pud, addr);
+                }
+        }
+        BUG_ON(pte && !pte_none(*pte) && !pte_huge(*pte));
+
+        return pte;
+}
+
+pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr)
+{
+        pgd_t *pgd;
+        pud_t *pud;
+        pmd_t *pmd = NULL;
+
+        pgd = pgd_offset(mm, addr);
+        if (pgd_present(*pgd)) {
+                pud = pud_offset(pgd, addr);
+                if (pud_present(*pud)) {
+                        if (pud_huge(*pud))
+                                return (pte_t *)pud;
+                        pmd = pmd_offset(pud, addr);
+                }
+        }
+        return (pte_t *) pmd;
+}
+
+struct page *
+follow_huge_pmd(struct mm_struct *mm, unsigned long address,
+                pmd_t *pmd, int write)
+{
+        struct page *page;
+
+        page = pte_page(*(pte_t *)pmd);
+        if (page)
+                page += ((address & ~PMD_MASK) >> PAGE_SHIFT);
+        return page;
+}
+
+struct page *
+follow_huge_pud(struct mm_struct *mm, unsigned long address,
+                pud_t *pud, int write)
+{
+        struct page *page;
+
+        page = pte_page(*(pte_t *)pud);
+        if (page)
+                page += ((address & ~PUD_MASK) >> PAGE_SHIFT);
+        return page;
+}
+
+#else /* !CONFIG_ARCH_WANT_GENERAL_HUGETLB */
+
+/* Can be overriden by architectures */
+__attribute__((weak)) struct page *
+follow_huge_pud(struct mm_struct *mm, unsigned long address,
+               pud_t *pud, int write)
+{
+        BUG();
+        return NULL;
+}
+
+#endif /* CONFIG_ARCH_WANT_GENERAL_HUGETLB */
+
 #ifdef CONFIG_MEMORY_FAILURE
 
 /* Should be called in hugetlb_lock */