summaryrefslogtreecommitdiff
path: root/mm/memory.c
diff options
context:
space:
mode:
Diffstat (limited to 'mm/memory.c')
-rw-r--r--mm/memory.c77
1 files changed, 47 insertions, 30 deletions
diff --git a/mm/memory.c b/mm/memory.c
index 7a089145cad4..a78814413ac0 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -624,6 +624,14 @@ struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr,
if (is_zero_pfn(pfn))
return NULL;
if (pte_devmap(pte))
+ /*
+ * NOTE: New users of ZONE_DEVICE will not set pte_devmap()
+ * and will have refcounts incremented on their struct pages
+ * when they are inserted into PTEs, thus they are safe to
+ * return here. Legacy ZONE_DEVICE pages that set pte_devmap()
+ * do not have refcounts. Example of legacy ZONE_DEVICE is
+ * MEMORY_DEVICE_FS_DAX type in pmem or virtio_fs drivers.
+ */
return NULL;
print_bad_pte(vma, addr, pte, NULL);
@@ -736,7 +744,7 @@ static void restore_exclusive_pte(struct vm_area_struct *vma,
* Currently device exclusive access only supports anonymous
* memory so the entry shouldn't point to a filebacked page.
*/
- WARN_ON_ONCE(!PageAnon(page));
+ WARN_ON_ONCE(1);
set_pte_at(vma->vm_mm, address, ptep, pte);
@@ -1245,7 +1253,7 @@ vma_needs_copy(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma)
if (userfaultfd_wp(dst_vma))
return true;
- if (src_vma->vm_flags & (VM_HUGETLB | VM_PFNMAP | VM_MIXEDMAP))
+ if (src_vma->vm_flags & (VM_PFNMAP | VM_MIXEDMAP))
return true;
if (src_vma->anon_vma)
@@ -3020,7 +3028,7 @@ static vm_fault_t fault_dirty_shared_page(struct vm_fault *vmf)
balance_dirty_pages_ratelimited(mapping);
if (fpin) {
fput(fpin);
- return VM_FAULT_RETRY;
+ return VM_FAULT_COMPLETED;
}
}
@@ -3043,7 +3051,7 @@ static inline void wp_page_reuse(struct vm_fault *vmf)
pte_t entry;
VM_BUG_ON(!(vmf->flags & FAULT_FLAG_WRITE));
- VM_BUG_ON(PageAnon(page) && !PageAnonExclusive(page));
+ VM_BUG_ON(page && PageAnon(page) && !PageAnonExclusive(page));
/*
* Clear the pages cpupid information as the existing
@@ -4369,20 +4377,29 @@ vm_fault_t finish_fault(struct vm_fault *vmf)
return VM_FAULT_OOM;
}
- /* See comment in handle_pte_fault() */
+ /*
+ * See comment in handle_pte_fault() for how this scenario happens, we
+ * need to return NOPAGE so that we drop this page.
+ */
if (pmd_devmap_trans_unstable(vmf->pmd))
- return 0;
+ return VM_FAULT_NOPAGE;
vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd,
vmf->address, &vmf->ptl);
- ret = 0;
+
/* Re-check under ptl */
- if (likely(!vmf_pte_changed(vmf)))
+ if (likely(!vmf_pte_changed(vmf))) {
do_set_pte(vmf, page, vmf->address);
- else
+
+ /* no need to invalidate: a not-present page won't be cached */
+ update_mmu_cache(vma, vmf->address, vmf->pte);
+
+ ret = 0;
+ } else {
+ update_mmu_tlb(vma, vmf->address, vmf->pte);
ret = VM_FAULT_NOPAGE;
+ }
- update_mmu_tlb(vma, vmf->address, vmf->pte);
pte_unmap_unlock(vmf->pte, vmf->ptl);
return ret;
}
@@ -4431,10 +4448,6 @@ late_initcall(fault_around_debugfs);
* It uses vm_ops->map_pages() to map the pages, which skips the page if it's
* not ready to be mapped: not up-to-date, locked, etc.
*
- * This function is called with the page table lock taken. In the split ptlock
- * case the page table lock only protects only those entries which belong to
- * the page table corresponding to the fault address.
- *
* This function doesn't cross the VMA boundaries, in order to call map_pages()
* only once.
*
@@ -4693,7 +4706,7 @@ static vm_fault_t do_numa_page(struct vm_fault *vmf)
pte = pte_modify(old_pte, vma->vm_page_prot);
page = vm_normal_page(vma, vmf->address, pte);
- if (!page)
+ if (!page || is_zone_device_page(page))
goto out_map;
/* TODO: handle PTE-mapped THP */
@@ -4802,6 +4815,19 @@ static vm_fault_t create_huge_pud(struct vm_fault *vmf)
defined(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD)
/* No support for anonymous transparent PUD pages yet */
if (vma_is_anonymous(vmf->vma))
+ return VM_FAULT_FALLBACK;
+ if (vmf->vma->vm_ops->huge_fault)
+ return vmf->vma->vm_ops->huge_fault(vmf, PE_SIZE_PUD);
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
+ return VM_FAULT_FALLBACK;
+}
+
+static vm_fault_t wp_huge_pud(struct vm_fault *vmf, pud_t orig_pud)
+{
+#if defined(CONFIG_TRANSPARENT_HUGEPAGE) && \
+ defined(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD)
+ /* No support for anonymous transparent PUD pages yet */
+ if (vma_is_anonymous(vmf->vma))
goto split;
if (vmf->vma->vm_ops->huge_fault) {
vm_fault_t ret = vmf->vma->vm_ops->huge_fault(vmf, PE_SIZE_PUD);
@@ -4812,19 +4838,7 @@ static vm_fault_t create_huge_pud(struct vm_fault *vmf)
split:
/* COW or write-notify not handled on PUD level: split pud.*/
__split_huge_pud(vmf->vma, vmf->pud, vmf->address);
-#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
- return VM_FAULT_FALLBACK;
-}
-
-static vm_fault_t wp_huge_pud(struct vm_fault *vmf, pud_t orig_pud)
-{
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
- /* No support for anonymous transparent PUD pages yet */
- if (vma_is_anonymous(vmf->vma))
- return VM_FAULT_FALLBACK;
- if (vmf->vma->vm_ops->huge_fault)
- return vmf->vma->vm_ops->huge_fault(vmf, PE_SIZE_PUD);
-#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE && CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */
return VM_FAULT_FALLBACK;
}
@@ -4962,6 +4976,7 @@ static vm_fault_t __handle_mm_fault(struct vm_area_struct *vma,
.gfp_mask = __get_fault_gfp_mask(vma),
};
struct mm_struct *mm = vma->vm_mm;
+ unsigned long vm_flags = vma->vm_flags;
pgd_t *pgd;
p4d_t *p4d;
vm_fault_t ret;
@@ -4975,7 +4990,8 @@ static vm_fault_t __handle_mm_fault(struct vm_area_struct *vma,
if (!vmf.pud)
return VM_FAULT_OOM;
retry_pud:
- if (pud_none(*vmf.pud) && __transparent_hugepage_enabled(vma)) {
+ if (pud_none(*vmf.pud) &&
+ hugepage_vma_check(vma, vm_flags, false, true)) {
ret = create_huge_pud(&vmf);
if (!(ret & VM_FAULT_FALLBACK))
return ret;
@@ -5008,7 +5024,8 @@ retry_pud:
if (pud_trans_unstable(vmf.pud))
goto retry_pud;
- if (pmd_none(*vmf.pmd) && __transparent_hugepage_enabled(vma)) {
+ if (pmd_none(*vmf.pmd) &&
+ hugepage_vma_check(vma, vm_flags, false, true)) {
ret = create_huge_pmd(&vmf);
if (!(ret & VM_FAULT_FALLBACK))
return ret;
generated by cgit v1.2.3 (git 2.46.0) at 2025-08-27 22:54:14 +0000