#include <linux/swap.h>
#include <linux/shrinker.h>
#include <linux/mm_inline.h>
+#include <linux/dax.h>
#include <linux/kthread.h>
#include <linux/khugepaged.h>
#include <linux/freezer.h>
static atomic_t huge_zero_refcount;
struct page *huge_zero_page __read_mostly;
-static inline bool is_huge_zero_pmd(pmd_t pmd)
-{
- return is_huge_zero_page(pmd_page(pmd));
-}
-
-static struct page *get_huge_zero_page(void)
+struct page *get_huge_zero_page(void)
{
struct page *zero_page;
retry:
static int __do_huge_pmd_anonymous_page(struct mm_struct *mm,
struct vm_area_struct *vma,
- unsigned long haddr, pmd_t *pmd,
+ unsigned long address, pmd_t *pmd,
struct page *page, gfp_t gfp,
unsigned int flags)
{
struct mem_cgroup *memcg;
pgtable_t pgtable;
spinlock_t *ptl;
+ unsigned long haddr = address & HPAGE_PMD_MASK;
VM_BUG_ON_PAGE(!PageCompound(page), page);
mem_cgroup_cancel_charge(page, memcg);
put_page(page);
pte_free(mm, pgtable);
- ret = handle_userfault(vma, haddr, flags,
+ ret = handle_userfault(vma, address, flags,
VM_UFFD_MISSING);
VM_BUG_ON(ret & VM_FAULT_FALLBACK);
return ret;
}
/* Caller must hold page table lock. */
-static void set_huge_zero_page(pgtable_t pgtable, struct mm_struct *mm,
+bool set_huge_zero_page(pgtable_t pgtable, struct mm_struct *mm,
struct vm_area_struct *vma, unsigned long haddr, pmd_t *pmd,
struct page *zero_page)
{
pmd_t entry;
+ if (!pmd_none(*pmd))
+ return false;
entry = mk_pmd(zero_page, vma->vm_page_prot);
entry = pmd_mkhuge(entry);
pgtable_trans_huge_deposit(mm, pmd, pgtable);
set_pmd_at(mm, haddr, pmd, entry);
atomic_long_inc(&mm->nr_ptes);
+ return true;
}
int do_huge_pmd_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma,
if (pmd_none(*pmd)) {
if (userfaultfd_missing(vma)) {
spin_unlock(ptl);
- ret = handle_userfault(vma, haddr, flags,
+ ret = handle_userfault(vma, address, flags,
VM_UFFD_MISSING);
VM_BUG_ON(ret & VM_FAULT_FALLBACK);
} else {
count_vm_event(THP_FAULT_FALLBACK);
return VM_FAULT_FALLBACK;
}
- return __do_huge_pmd_anonymous_page(mm, vma, haddr, pmd, page, gfp, flags);
+ return __do_huge_pmd_anonymous_page(mm, vma, address, pmd, page, gfp,
+ flags);
+}
+
+static void insert_pfn_pmd(struct vm_area_struct *vma, unsigned long addr,
+ pmd_t *pmd, unsigned long pfn, pgprot_t prot, bool write)
+{
+ struct mm_struct *mm = vma->vm_mm;
+ pmd_t entry;
+ spinlock_t *ptl;
+
+ ptl = pmd_lock(mm, pmd);
+ if (pmd_none(*pmd)) {
+ entry = pmd_mkhuge(pfn_pmd(pfn, prot));
+ if (write) {
+ entry = pmd_mkyoung(pmd_mkdirty(entry));
+ entry = maybe_pmd_mkwrite(entry, vma);
+ }
+ set_pmd_at(mm, addr, pmd, entry);
+ update_mmu_cache_pmd(vma, addr, pmd);
+ }
+ spin_unlock(ptl);
+}
+
+int vmf_insert_pfn_pmd(struct vm_area_struct *vma, unsigned long addr,
+ pmd_t *pmd, unsigned long pfn, bool write)
+{
+ pgprot_t pgprot = vma->vm_page_prot;
+ /*
+ * If we had pmd_special, we could avoid all these restrictions,
+ * but we need to be consistent with PTEs and architectures that
+ * can't support a 'special' bit.
+ */
+ BUG_ON(!(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP)));
+ BUG_ON((vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP)) ==
+ (VM_PFNMAP|VM_MIXEDMAP));
+ BUG_ON((vma->vm_flags & VM_PFNMAP) && is_cow_mapping(vma->vm_flags));
+ BUG_ON((vma->vm_flags & VM_MIXEDMAP) && pfn_valid(pfn));
+
+ if (addr < vma->vm_start || addr >= vma->vm_end)
+ return VM_FAULT_SIGBUS;
+ if (track_pfn_insert(vma, &pgprot, pfn))
+ return VM_FAULT_SIGBUS;
+ insert_pfn_pmd(vma, addr, pmd, pfn, pgprot, write);
+ return VM_FAULT_NOPAGE;
}
int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm,
int ret = 0;
if (__pmd_trans_huge_lock(pmd, vma, &ptl) == 1) {
- struct page *page;
pgtable_t pgtable;
pmd_t orig_pmd;
/*
orig_pmd = pmdp_huge_get_and_clear_full(tlb->mm, addr, pmd,
tlb->fullmm);
tlb_remove_pmd_tlb_entry(tlb, pmd, addr);
- pgtable = pgtable_trans_huge_withdraw(tlb->mm, pmd);
+ if (vma_is_dax(vma)) {
+ if (is_huge_zero_pmd(orig_pmd)) {
+ pgtable = NULL;
+ } else {
+ spin_unlock(ptl);
+ return 1;
+ }
+ } else {
+ pgtable = pgtable_trans_huge_withdraw(tlb->mm, pmd);
+ }
if (is_huge_zero_pmd(orig_pmd)) {
atomic_long_dec(&tlb->mm->nr_ptes);
spin_unlock(ptl);
put_huge_zero_page();
} else {
- page = pmd_page(orig_pmd);
+ struct page *page = pmd_page(orig_pmd);
page_remove_rmap(page);
VM_BUG_ON_PAGE(page_mapcount(page) < 0, page);
add_mm_counter(tlb->mm, MM_ANONPAGES, -HPAGE_PMD_NR);
spin_unlock(ptl);
tlb_remove_page(tlb, page);
}
- pte_free(tlb->mm, pgtable);
+ if (pgtable)
+ pte_free(tlb->mm, pgtable);
ret = 1;
}
return ret;
pmd_t *pmd)
{
spinlock_t *ptl;
- struct page *page;
+ struct page *page = NULL;
struct mm_struct *mm = vma->vm_mm;
unsigned long haddr = address & HPAGE_PMD_MASK;
unsigned long mmun_start; /* For mmu_notifiers */
again:
mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end);
ptl = pmd_lock(mm, pmd);
- if (unlikely(!pmd_trans_huge(*pmd))) {
- spin_unlock(ptl);
- mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end);
- return;
- }
- if (is_huge_zero_pmd(*pmd)) {
+ if (unlikely(!pmd_trans_huge(*pmd)))
+ goto unlock;
+ if (vma_is_dax(vma)) {
+ pmdp_huge_clear_flush(vma, haddr, pmd);
+ } else if (is_huge_zero_pmd(*pmd)) {
__split_huge_zero_page_pmd(vma, haddr, pmd);
- spin_unlock(ptl);
- mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end);
- return;
+ } else {
+ page = pmd_page(*pmd);
+ VM_BUG_ON_PAGE(!page_count(page), page);
+ get_page(page);
}
- page = pmd_page(*pmd);
- VM_BUG_ON_PAGE(!page_count(page), page);
- get_page(page);
+ unlock:
spin_unlock(ptl);
mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end);
- split_huge_page(page);
+ if (!page)
+ return;
+ split_huge_page(page);
put_page(page);
/*
split_huge_page_pmd_mm(mm, address, pmd);
}
-void __vma_adjust_trans_huge(struct vm_area_struct *vma,
+void vma_adjust_trans_huge(struct vm_area_struct *vma,
unsigned long start,
unsigned long end,
long adjust_next)