#warning Unfortunate NUMA and NUMA Balancing config, growing page-frame for last_cpupid.
#endif
-#ifndef CONFIG_NEED_MULTIPLE_NODES
-/* use the per-pgdat data instead for discontigmem - mbligh */
+#ifndef CONFIG_NUMA
unsigned long max_mapnr;
EXPORT_SYMBOL(max_mapnr);
}
#endif
+static void restore_exclusive_pte(struct vm_area_struct *vma,
+ struct page *page, unsigned long address,
+ pte_t *ptep)
+{
+ pte_t pte;
+ swp_entry_t entry;
+
+ pte = pte_mkold(mk_pte(page, READ_ONCE(vma->vm_page_prot)));
+ if (pte_swp_soft_dirty(*ptep))
+ pte = pte_mksoft_dirty(pte);
+
+ entry = pte_to_swp_entry(*ptep);
+ if (pte_swp_uffd_wp(*ptep))
+ pte = pte_mkuffd_wp(pte);
+ else if (is_writable_device_exclusive_entry(entry))
+ pte = maybe_mkwrite(pte_mkdirty(pte), vma);
+
+ set_pte_at(vma->vm_mm, address, ptep, pte);
+
+ /*
+ * No need to take a page reference as one was already
+ * created when the swap entry was made.
+ */
+ if (PageAnon(page))
+ page_add_anon_rmap(page, vma, address, false);
+ else
+ /*
+ * Currently device exclusive access only supports anonymous
+ * memory so the entry shouldn't point to a filebacked page.
+ */
+ WARN_ON_ONCE(!PageAnon(page));
+
+ if (vma->vm_flags & VM_LOCKED)
+ mlock_vma_page(page);
+
+ /*
+ * No need to invalidate - it was non-present before. However
+ * secondary CPUs may have mappings that need invalidating.
+ */
+ update_mmu_cache(vma, address, ptep);
+}
+
+/*
+ * Tries to restore an exclusive pte if the page lock can be acquired without
+ * sleeping.
+ */
+static int
+try_restore_exclusive_pte(pte_t *src_pte, struct vm_area_struct *vma,
+ unsigned long addr)
+{
+ swp_entry_t entry = pte_to_swp_entry(*src_pte);
+ struct page *page = pfn_swap_entry_to_page(entry);
+
+ if (trylock_page(page)) {
+ restore_exclusive_pte(vma, page, addr, src_pte);
+ unlock_page(page);
+ return 0;
+ }
+
+ return -EBUSY;
+}
+
/*
* copy one vm_area from one task to the other. Assumes the page tables
* already present in the new task to be cleared in the whole range
static unsigned long
copy_nonpresent_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm,
- pte_t *dst_pte, pte_t *src_pte, struct vm_area_struct *vma,
- unsigned long addr, int *rss)
+ pte_t *dst_pte, pte_t *src_pte, struct vm_area_struct *dst_vma,
+ struct vm_area_struct *src_vma, unsigned long addr, int *rss)
{
- unsigned long vm_flags = vma->vm_flags;
+ unsigned long vm_flags = dst_vma->vm_flags;
pte_t pte = *src_pte;
struct page *page;
swp_entry_t entry = pte_to_swp_entry(pte);
if (likely(!non_swap_entry(entry))) {
if (swap_duplicate(entry) < 0)
- return entry.val;
+ return -EIO;
/* make sure dst_mm is on swapoff's mmlist. */
if (unlikely(list_empty(&dst_mm->mmlist))) {
}
rss[MM_SWAPENTS]++;
} else if (is_migration_entry(entry)) {
- page = migration_entry_to_page(entry);
+ page = pfn_swap_entry_to_page(entry);
rss[mm_counter(page)]++;
- if (is_write_migration_entry(entry) &&
+ if (is_writable_migration_entry(entry) &&
is_cow_mapping(vm_flags)) {
/*
* COW mappings require pages in both
* parent and child to be set to read.
*/
- make_migration_entry_read(&entry);
+ entry = make_readable_migration_entry(
+ swp_offset(entry));
pte = swp_entry_to_pte(entry);
if (pte_swp_soft_dirty(*src_pte))
pte = pte_swp_mksoft_dirty(pte);
set_pte_at(src_mm, addr, src_pte, pte);
}
} else if (is_device_private_entry(entry)) {
- page = device_private_entry_to_page(entry);
+ page = pfn_swap_entry_to_page(entry);
/*
* Update rss count even for unaddressable pages, as
* when a device driver is involved (you cannot easily
* save and restore device driver state).
*/
- if (is_write_device_private_entry(entry) &&
+ if (is_writable_device_private_entry(entry) &&
is_cow_mapping(vm_flags)) {
- make_device_private_entry_read(&entry);
+ entry = make_readable_device_private_entry(
+ swp_offset(entry));
pte = swp_entry_to_pte(entry);
if (pte_swp_uffd_wp(*src_pte))
pte = pte_swp_mkuffd_wp(pte);
set_pte_at(src_mm, addr, src_pte, pte);
}
+ } else if (is_device_exclusive_entry(entry)) {
+ /*
+ * Make device exclusive entries present by restoring the
+ * original entry then copying as for a present pte. Device
+ * exclusive entries currently only support private writable
+ * (ie. COW) mappings.
+ */
+ VM_BUG_ON(!is_cow_mapping(src_vma->vm_flags));
+ if (try_restore_exclusive_pte(src_pte, src_vma, addr))
+ return -EBUSY;
+ return -ENOENT;
}
+ if (!userfaultfd_wp(dst_vma))
+ pte = pte_swp_clear_uffd_wp(pte);
set_pte_at(dst_mm, addr, dst_pte, pte);
return 0;
}
/* All done, just insert the new page copy in the child */
pte = mk_pte(new_page, dst_vma->vm_page_prot);
pte = maybe_mkwrite(pte_mkdirty(pte), dst_vma);
+ if (userfaultfd_pte_wp(dst_vma, *src_pte))
+ /* Uffd-wp needs to be delivered to dest pte as well */
+ pte = pte_wrprotect(pte_mkuffd_wp(pte));
set_pte_at(dst_vma->vm_mm, addr, dst_pte, pte);
return 0;
}
pte = pte_mkclean(pte);
pte = pte_mkold(pte);
- /*
- * Make sure the _PAGE_UFFD_WP bit is cleared if the new VMA
- * does not have the VM_UFFD_WP, which means that the uffd
- * fork event is not enabled.
- */
- if (!(vm_flags & VM_UFFD_WP))
+ if (!userfaultfd_wp(dst_vma))
pte = pte_clear_uffd_wp(pte);
set_pte_at(dst_vma->vm_mm, addr, dst_pte, pte);
continue;
}
if (unlikely(!pte_present(*src_pte))) {
- entry.val = copy_nonpresent_pte(dst_mm, src_mm,
- dst_pte, src_pte,
- src_vma, addr, rss);
- if (entry.val)
+ ret = copy_nonpresent_pte(dst_mm, src_mm,
+ dst_pte, src_pte,
+ dst_vma, src_vma,
+ addr, rss);
+ if (ret == -EIO) {
+ entry = pte_to_swp_entry(*src_pte);
break;
- progress += 8;
- continue;
+ } else if (ret == -EBUSY) {
+ break;
+ } else if (!ret) {
+ progress += 8;
+ continue;
+ }
+
+ /*
+ * Device exclusive entry restored, continue by copying
+ * the now present pte.
+ */
+ WARN_ON_ONCE(ret != -ENOENT);
}
/* copy_present_pte() will clear `*prealloc' if consumed */
ret = copy_present_pte(dst_vma, src_vma, dst_pte, src_pte,
pte_unmap_unlock(orig_dst_pte, dst_ptl);
cond_resched();
- if (entry.val) {
+ if (ret == -EIO) {
+ VM_WARN_ON_ONCE(!entry.val);
if (add_swap_count_continuation(entry, GFP_KERNEL) < 0) {
ret = -ENOMEM;
goto out;
}
entry.val = 0;
- } else if (ret) {
- WARN_ON_ONCE(ret != -EAGAIN);
+ } else if (ret == -EBUSY) {
+ goto out;
+ } else if (ret == -EAGAIN) {
prealloc = page_copy_prealloc(src_mm, src_vma, addr);
if (!prealloc)
return -ENOMEM;
- /* We've captured and resolved the error. Reset, try again. */
- ret = 0;
+ } else if (ret) {
+ VM_WARN_ON_ONCE(1);
}
+
+ /* We've captured and resolved the error. Reset, try again. */
+ ret = 0;
+
if (addr != end)
goto again;
out:
|| pmd_devmap(*src_pmd)) {
int err;
VM_BUG_ON_VMA(next-addr != HPAGE_PMD_SIZE, src_vma);
- err = copy_huge_pmd(dst_mm, src_mm,
- dst_pmd, src_pmd, addr, src_vma);
+ err = copy_huge_pmd(dst_mm, src_mm, dst_pmd, src_pmd,
+ addr, dst_vma, src_vma);
if (err == -ENOMEM)
return -ENOMEM;
if (!err)
}
entry = pte_to_swp_entry(ptent);
- if (is_device_private_entry(entry)) {
- struct page *page = device_private_entry_to_page(entry);
+ if (is_device_private_entry(entry) ||
+ is_device_exclusive_entry(entry)) {
+ struct page *page = pfn_swap_entry_to_page(entry);
if (unlikely(details && details->check_mapping)) {
/*
pte_clear_not_present_full(mm, addr, pte, tlb->fullmm);
rss[mm_counter(page)]--;
- page_remove_rmap(page, false);
+
+ if (is_device_private_entry(entry))
+ page_remove_rmap(page, false);
+
put_page(page);
continue;
}
else if (is_migration_entry(entry)) {
struct page *page;
- page = migration_entry_to_page(entry);
+ page = pfn_swap_entry_to_page(entry);
rss[mm_counter(page)]--;
}
if (unlikely(!free_swap_and_cache(entry)))
else if (zap_huge_pmd(tlb, vma, pmd, addr))
goto next;
/* fall through */
+ } else if (details && details->single_page &&
+ PageTransCompound(details->single_page) &&
+ next - addr == HPAGE_PMD_SIZE && pmd_none(*pmd)) {
+ spinlock_t *ptl = pmd_lock(tlb->mm, pmd);
+ /*
+ * Take and drop THP pmd lock so that we cannot return
+ * prematurely, while zap_huge_pmd() has cleared *pmd,
+ * but not yet decremented compound_mapcount().
+ */
+ spin_unlock(ptl);
}
+
/*
* Here there can be other concurrent MADV_DONTNEED or
* trans huge page faults running, and if the pmd is
return 0;
}
-/**
- * remap_pfn_range - remap kernel memory to userspace
- * @vma: user vma to map to
- * @addr: target page aligned user address to start at
- * @pfn: page frame number of kernel physical memory address
- * @size: size of mapping area
- * @prot: page protection flags for this mapping
- *
- * Note: this is only safe if the mm semaphore is held when called.
- *
- * Return: %0 on success, negative error code otherwise.
+/*
+ * Variant of remap_pfn_range that does not call track_pfn_remap. The caller
+ * must have pre-validated the caching bits of the pgprot_t.
*/
-int remap_pfn_range(struct vm_area_struct *vma, unsigned long addr,
- unsigned long pfn, unsigned long size, pgprot_t prot)
+int remap_pfn_range_notrack(struct vm_area_struct *vma, unsigned long addr,
+ unsigned long pfn, unsigned long size, pgprot_t prot)
{
pgd_t *pgd;
unsigned long next;
unsigned long end = addr + PAGE_ALIGN(size);
struct mm_struct *mm = vma->vm_mm;
- unsigned long remap_pfn = pfn;
int err;
if (WARN_ON_ONCE(!PAGE_ALIGNED(addr)))
vma->vm_pgoff = pfn;
}
- err = track_pfn_remap(vma, &prot, remap_pfn, addr, PAGE_ALIGN(size));
- if (err)
- return -EINVAL;
-
vma->vm_flags |= VM_IO | VM_PFNMAP | VM_DONTEXPAND | VM_DONTDUMP;
BUG_ON(addr >= end);
err = remap_p4d_range(mm, pgd, addr, next,
pfn + (addr >> PAGE_SHIFT), prot);
if (err)
- break;
+ return err;
} while (pgd++, addr = next, addr != end);
+ return 0;
+}
+
+/**
+ * remap_pfn_range - remap kernel memory to userspace
+ * @vma: user vma to map to
+ * @addr: target page aligned user address to start at
+ * @pfn: page frame number of kernel physical memory address
+ * @size: size of mapping area
+ * @prot: page protection flags for this mapping
+ *
+ * Note: this is only safe if the mm semaphore is held when called.
+ *
+ * Return: %0 on success, negative error code otherwise.
+ */
+int remap_pfn_range(struct vm_area_struct *vma, unsigned long addr,
+ unsigned long pfn, unsigned long size, pgprot_t prot)
+{
+ int err;
+
+ err = track_pfn_remap(vma, &prot, pfn, addr, PAGE_ALIGN(size));
if (err)
- untrack_pfn(vma, remap_pfn, PAGE_ALIGN(size));
+ return -EINVAL;
+ err = remap_pfn_range_notrack(vma, addr, pfn, size, prot);
+ if (err)
+ untrack_pfn(vma, pfn, PAGE_ALIGN(size));
return err;
}
EXPORT_SYMBOL(remap_pfn_range);
}
do {
next = pmd_addr_end(addr, end);
- if (create || !pmd_none_or_clear_bad(pmd)) {
- err = apply_to_pte_range(mm, pmd, addr, next, fn, data,
- create, mask);
- if (err)
- break;
+ if (pmd_none(*pmd) && !create)
+ continue;
+ if (WARN_ON_ONCE(pmd_leaf(*pmd)))
+ return -EINVAL;
+ if (!pmd_none(*pmd) && WARN_ON_ONCE(pmd_bad(*pmd))) {
+ if (!create)
+ continue;
+ pmd_clear_bad(pmd);
}
+ err = apply_to_pte_range(mm, pmd, addr, next,
+ fn, data, create, mask);
+ if (err)
+ break;
} while (pmd++, addr = next, addr != end);
+
return err;
}
}
do {
next = pud_addr_end(addr, end);
- if (create || !pud_none_or_clear_bad(pud)) {
- err = apply_to_pmd_range(mm, pud, addr, next, fn, data,
- create, mask);
- if (err)
- break;
+ if (pud_none(*pud) && !create)
+ continue;
+ if (WARN_ON_ONCE(pud_leaf(*pud)))
+ return -EINVAL;
+ if (!pud_none(*pud) && WARN_ON_ONCE(pud_bad(*pud))) {
+ if (!create)
+ continue;
+ pud_clear_bad(pud);
}
+ err = apply_to_pmd_range(mm, pud, addr, next,
+ fn, data, create, mask);
+ if (err)
+ break;
} while (pud++, addr = next, addr != end);
+
return err;
}
}
do {
next = p4d_addr_end(addr, end);
- if (create || !p4d_none_or_clear_bad(p4d)) {
- err = apply_to_pud_range(mm, p4d, addr, next, fn, data,
- create, mask);
- if (err)
- break;
+ if (p4d_none(*p4d) && !create)
+ continue;
+ if (WARN_ON_ONCE(p4d_leaf(*p4d)))
+ return -EINVAL;
+ if (!p4d_none(*p4d) && WARN_ON_ONCE(p4d_bad(*p4d))) {
+ if (!create)
+ continue;
+ p4d_clear_bad(p4d);
}
+ err = apply_to_pud_range(mm, p4d, addr, next,
+ fn, data, create, mask);
+ if (err)
+ break;
} while (p4d++, addr = next, addr != end);
+
return err;
}
pgd = pgd_offset(mm, addr);
do {
next = pgd_addr_end(addr, end);
- if (!create && pgd_none_or_clear_bad(pgd))
+ if (pgd_none(*pgd) && !create)
continue;
- err = apply_to_p4d_range(mm, pgd, addr, next, fn, data, create, &mask);
+ if (WARN_ON_ONCE(pgd_leaf(*pgd)))
+ return -EINVAL;
+ if (!pgd_none(*pgd) && WARN_ON_ONCE(pgd_bad(*pgd))) {
+ if (!create)
+ continue;
+ pgd_clear_bad(pgd);
+ }
+ err = apply_to_p4d_range(mm, pgd, addr, next,
+ fn, data, create, &mask);
if (err)
break;
} while (pgd++, addr = next, addr != end);
}
flush_cache_page(vma, vmf->address, pte_pfn(vmf->orig_pte));
entry = mk_pte(new_page, vma->vm_page_prot);
+ entry = pte_sw_mkyoung(entry);
entry = maybe_mkwrite(pte_mkdirty(entry), vma);
/*
munlock_vma_page(old_page);
unlock_page(old_page);
}
+ if (page_copied)
+ free_swap_cache(old_page);
put_page(old_page);
}
return page_copied ? VM_FAULT_WRITE : 0;
* The function expects the page to be locked or other protection against
* concurrent faults / writeback (such as DAX radix tree locks).
*
- * Return: %VM_FAULT_WRITE on success, %0 when PTE got changed before
+ * Return: %0 on success, %VM_FAULT_NOPAGE when PTE got changed before
* we acquired PTE lock.
*/
vm_fault_t finish_mkwrite_fault(struct vm_fault *vmf)
}
}
+/**
+ * unmap_mapping_page() - Unmap single page from processes.
+ * @page: The locked page to be unmapped.
+ *
+ * Unmap this page from any userspace process which still has it mmaped.
+ * Typically, for efficiency, the range of nearby pages has already been
+ * unmapped by unmap_mapping_pages() or unmap_mapping_range(). But once
+ * truncation or invalidation holds the lock on a page, it may find that
+ * the page has been remapped again: and then uses unmap_mapping_page()
+ * to unmap it finally.
+ */
+void unmap_mapping_page(struct page *page)
+{
+ struct address_space *mapping = page->mapping;
+ struct zap_details details = { };
+
+ VM_BUG_ON(!PageLocked(page));
+ VM_BUG_ON(PageTail(page));
+
+ details.check_mapping = mapping;
+ details.first_index = page->index;
+ details.last_index = page->index + thp_nr_pages(page) - 1;
+ details.single_page = page;
+
+ i_mmap_lock_write(mapping);
+ if (unlikely(!RB_EMPTY_ROOT(&mapping->i_mmap.rb_root)))
+ unmap_mapping_range_tree(&mapping->i_mmap, &details);
+ i_mmap_unlock_write(mapping);
+}
+
/**
* unmap_mapping_pages() - Unmap pages from processes.
* @mapping: The address space containing pages to be unmapped.
}
EXPORT_SYMBOL(unmap_mapping_range);
+/*
+ * Restore a potential device exclusive pte to a working pte entry
+ */
+static vm_fault_t remove_device_exclusive_entry(struct vm_fault *vmf)
+{
+ struct page *page = vmf->page;
+ struct vm_area_struct *vma = vmf->vma;
+ struct mmu_notifier_range range;
+
+ if (!lock_page_or_retry(page, vma->vm_mm, vmf->flags))
+ return VM_FAULT_RETRY;
+ mmu_notifier_range_init_owner(&range, MMU_NOTIFY_EXCLUSIVE, 0, vma,
+ vma->vm_mm, vmf->address & PAGE_MASK,
+ (vmf->address & PAGE_MASK) + PAGE_SIZE, NULL);
+ mmu_notifier_invalidate_range_start(&range);
+
+ vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, vmf->address,
+ &vmf->ptl);
+ if (likely(pte_same(*vmf->pte, vmf->orig_pte)))
+ restore_exclusive_pte(vma, page, vmf->address, vmf->pte);
+
+ pte_unmap_unlock(vmf->pte, vmf->ptl);
+ unlock_page(page);
+
+ mmu_notifier_invalidate_range_end(&range);
+ return 0;
+}
+
/*
* We enter with non-exclusive mmap_lock (to exclude vma changes,
* but allow concurrent faults), and pte mapped but not yet locked.
{
struct vm_area_struct *vma = vmf->vma;
struct page *page = NULL, *swapcache;
+ struct swap_info_struct *si = NULL;
swp_entry_t entry;
pte_t pte;
int locked;
if (is_migration_entry(entry)) {
migration_entry_wait(vma->vm_mm, vmf->pmd,
vmf->address);
+ } else if (is_device_exclusive_entry(entry)) {
+ vmf->page = pfn_swap_entry_to_page(entry);
+ ret = remove_device_exclusive_entry(vmf);
} else if (is_device_private_entry(entry)) {
- vmf->page = device_private_entry_to_page(entry);
+ vmf->page = pfn_swap_entry_to_page(entry);
ret = vmf->page->pgmap->ops->migrate_to_ram(vmf);
} else if (is_hwpoison_entry(entry)) {
ret = VM_FAULT_HWPOISON;
goto out;
}
+ /* Prevent swapoff from happening to us. */
+ si = get_swap_device(entry);
+ if (unlikely(!si))
+ goto out;
- delayacct_set_flag(DELAYACCT_PF_SWAPIN);
+ delayacct_set_flag(current, DELAYACCT_PF_SWAPIN);
page = lookup_swap_cache(entry, vma, vmf->address);
swapcache = page;
if (!page) {
- struct swap_info_struct *si = swp_swap_info(entry);
-
if (data_race(si->flags & SWP_SYNCHRONOUS_IO) &&
__swap_count(entry) == 1) {
/* skip swapcache */
page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma,
vmf->address);
if (page) {
- int err;
-
__SetPageLocked(page);
__SetPageSwapBacked(page);
- set_page_private(page, entry.val);
- /* Tell memcg to use swap ownership records */
- SetPageSwapCache(page);
- err = mem_cgroup_charge(page, vma->vm_mm,
- GFP_KERNEL);
- ClearPageSwapCache(page);
- if (err) {
+ if (mem_cgroup_swapin_charge_page(page,
+ vma->vm_mm, GFP_KERNEL, entry)) {
ret = VM_FAULT_OOM;
goto out_page;
}
+ mem_cgroup_swapin_uncharge_swap(entry);
shadow = get_shadow_from_swap_cache(entry);
if (shadow)
workingset_refault(page, shadow);
lru_cache_add(page);
+
+ /* To provide entry to swap_readpage() */
+ set_page_private(page, entry.val);
swap_readpage(page, true);
+ set_page_private(page, 0);
}
} else {
page = swapin_readahead(entry, GFP_HIGHUSER_MOVABLE,
vmf->address, &vmf->ptl);
if (likely(pte_same(*vmf->pte, vmf->orig_pte)))
ret = VM_FAULT_OOM;
- delayacct_clear_flag(DELAYACCT_PF_SWAPIN);
+ delayacct_clear_flag(current, DELAYACCT_PF_SWAPIN);
goto unlock;
}
* owner processes (which may be unknown at hwpoison time)
*/
ret = VM_FAULT_HWPOISON;
- delayacct_clear_flag(DELAYACCT_PF_SWAPIN);
+ delayacct_clear_flag(current, DELAYACCT_PF_SWAPIN);
goto out_release;
}
locked = lock_page_or_retry(page, vma->vm_mm, vmf->flags);
- delayacct_clear_flag(DELAYACCT_PF_SWAPIN);
+ delayacct_clear_flag(current, DELAYACCT_PF_SWAPIN);
if (!locked) {
ret |= VM_FAULT_RETRY;
goto out_release;
unlock:
pte_unmap_unlock(vmf->pte, vmf->ptl);
out:
+ if (si)
+ put_swap_device(si);
return ret;
out_nomap:
pte_unmap_unlock(vmf->pte, vmf->ptl);
unlock_page(swapcache);
put_page(swapcache);
}
+ if (si)
+ put_swap_device(si);
return ret;
}
__SetPageUptodate(page);
entry = mk_pte(page, vma->vm_page_prot);
+ entry = pte_sw_mkyoung(entry);
if (vma->vm_flags & VM_WRITE)
entry = pte_mkwrite(pte_mkdirty(entry));
return ret;
/*
- * Archs like ppc64 need additonal space to store information
+ * Archs like ppc64 need additional space to store information
* related to pte entry. Use the preallocated table for that.
*/
if (arch_needs_pgtable_deposit() && !vmf->prealloc_pte) {
if (prefault && arch_wants_old_prefaulted_pte())
entry = pte_mkold(entry);
+ else
+ entry = pte_sw_mkyoung(entry);
if (write)
entry = maybe_mkwrite(pte_mkdirty(entry), vma);
* something).
*/
if (vma->vm_ops->map_pages && fault_around_bytes >> PAGE_SHIFT > 1) {
- ret = do_fault_around(vmf);
- if (ret)
- return ret;
+ if (likely(!userfaultfd_minor(vmf->vma))) {
+ ret = do_fault_around(vmf);
+ if (ret)
+ return ret;
+ }
}
ret = __do_fault(vmf);
return ret;
}
-static int numa_migrate_prep(struct page *page, struct vm_area_struct *vma,
- unsigned long addr, int page_nid,
- int *flags)
+int numa_migrate_prep(struct page *page, struct vm_area_struct *vma,
+ unsigned long addr, int page_nid, int *flags)
{
get_page(page);
int page_nid = NUMA_NO_NODE;
int last_cpupid;
int target_nid;
- bool migrated = false;
pte_t pte, old_pte;
bool was_writable = pte_savedwrite(vmf->orig_pte);
int flags = 0;
goto out;
}
- /*
- * Make it present again, Depending on how arch implementes non
- * accessible ptes, some can allow access by kernel mode.
- */
- old_pte = ptep_modify_prot_start(vma, vmf->address, vmf->pte);
+ /* Get the normal PTE */
+ old_pte = ptep_get(vmf->pte);
pte = pte_modify(old_pte, vma->vm_page_prot);
- pte = pte_mkyoung(pte);
- if (was_writable)
- pte = pte_mkwrite(pte);
- ptep_modify_prot_commit(vma, vmf->address, vmf->pte, old_pte, pte);
- update_mmu_cache(vma, vmf->address, vmf->pte);
page = vm_normal_page(vma, vmf->address, pte);
- if (!page) {
- pte_unmap_unlock(vmf->pte, vmf->ptl);
- return 0;
- }
+ if (!page)
+ goto out_map;
/* TODO: handle PTE-mapped THP */
- if (PageCompound(page)) {
- pte_unmap_unlock(vmf->pte, vmf->ptl);
- return 0;
- }
+ if (PageCompound(page))
+ goto out_map;
/*
* Avoid grouping on RO pages in general. RO pages shouldn't hurt as
* pte_dirty has unpredictable behaviour between PTE scan updates,
* background writeback, dirty balancing and application behaviour.
*/
- if (!pte_write(pte))
+ if (!was_writable)
flags |= TNF_NO_GROUP;
/*
page_nid = page_to_nid(page);
target_nid = numa_migrate_prep(page, vma, vmf->address, page_nid,
&flags);
- pte_unmap_unlock(vmf->pte, vmf->ptl);
if (target_nid == NUMA_NO_NODE) {
put_page(page);
- goto out;
+ goto out_map;
}
+ pte_unmap_unlock(vmf->pte, vmf->ptl);
/* Migrate to the requested node */
- migrated = migrate_misplaced_page(page, vma, target_nid);
- if (migrated) {
+ if (migrate_misplaced_page(page, vma, target_nid)) {
page_nid = target_nid;
flags |= TNF_MIGRATED;
- } else
+ } else {
flags |= TNF_MIGRATE_FAIL;
+ vmf->pte = pte_offset_map(vmf->pmd, vmf->address);
+ spin_lock(vmf->ptl);
+ if (unlikely(!pte_same(*vmf->pte, vmf->orig_pte))) {
+ pte_unmap_unlock(vmf->pte, vmf->ptl);
+ goto out;
+ }
+ goto out_map;
+ }
out:
if (page_nid != NUMA_NO_NODE)
task_numa_fault(last_cpupid, page_nid, 1, flags);
return 0;
+out_map:
+ /*
+ * Make it present again, depending on how arch implements
+ * non-accessible ptes, some can allow access by kernel mode.
+ */
+ old_pte = ptep_modify_prot_start(vma, vmf->address, vmf->pte);
+ pte = pte_modify(old_pte, vma->vm_page_prot);
+ pte = pte_mkyoung(pte);
+ if (was_writable)
+ pte = pte_mkwrite(pte);
+ ptep_modify_prot_commit(vma, vmf->address, vmf->pte, old_pte, pte);
+ update_mmu_cache(vma, vmf->address, vmf->pte);
+ pte_unmap_unlock(vmf->pte, vmf->ptl);
+ goto out;
}
static inline vm_fault_t create_huge_pmd(struct vm_fault *vmf)
}
/* `inline' is required to avoid gcc 4.1.2 build error */
-static inline vm_fault_t wp_huge_pmd(struct vm_fault *vmf, pmd_t orig_pmd)
+static inline vm_fault_t wp_huge_pmd(struct vm_fault *vmf)
{
if (vma_is_anonymous(vmf->vma)) {
- if (userfaultfd_huge_pmd_wp(vmf->vma, orig_pmd))
+ if (userfaultfd_huge_pmd_wp(vmf->vma, vmf->orig_pmd))
return handle_userfault(vmf, VM_UFFD_WP);
- return do_huge_pmd_wp_page(vmf, orig_pmd);
+ return do_huge_pmd_wp_page(vmf);
}
if (vmf->vma->vm_ops->huge_fault) {
vm_fault_t ret = vmf->vma->vm_ops->huge_fault(vmf, PE_SIZE_PMD);
if (!(ret & VM_FAULT_FALLBACK))
return ret;
} else {
- pmd_t orig_pmd = *vmf.pmd;
+ vmf.orig_pmd = *vmf.pmd;
barrier();
- if (unlikely(is_swap_pmd(orig_pmd))) {
+ if (unlikely(is_swap_pmd(vmf.orig_pmd))) {
VM_BUG_ON(thp_migration_supported() &&
- !is_pmd_migration_entry(orig_pmd));
- if (is_pmd_migration_entry(orig_pmd))
+ !is_pmd_migration_entry(vmf.orig_pmd));
+ if (is_pmd_migration_entry(vmf.orig_pmd))
pmd_migration_entry_wait(mm, vmf.pmd);
return 0;
}
- if (pmd_trans_huge(orig_pmd) || pmd_devmap(orig_pmd)) {
- if (pmd_protnone(orig_pmd) && vma_is_accessible(vma))
- return do_huge_pmd_numa_page(&vmf, orig_pmd);
+ if (pmd_trans_huge(vmf.orig_pmd) || pmd_devmap(vmf.orig_pmd)) {
+ if (pmd_protnone(vmf.orig_pmd) && vma_is_accessible(vma))
+ return do_huge_pmd_numa_page(&vmf);
- if (dirty && !pmd_write(orig_pmd)) {
- ret = wp_huge_pmd(&vmf, orig_pmd);
+ if (dirty && !pmd_write(vmf.orig_pmd)) {
+ ret = wp_huge_pmd(&vmf);
if (!(ret & VM_FAULT_FALLBACK))
return ret;
} else {
- huge_pmd_set_accessed(&vmf, orig_pmd);
+ huge_pmd_set_accessed(&vmf);
return 0;
}
}
}
/**
- * mm_account_fault - Do page fault accountings
+ * mm_account_fault - Do page fault accounting
*
* @regs: the pt_regs struct pointer. When set to NULL, will skip accounting
* of perf event counters, but we'll still do the per-task accounting to
* @flags: the fault flags.
* @ret: the fault retcode.
*
- * This will take care of most of the page fault accountings. Meanwhile, it
+ * This will take care of most of the page fault accounting. Meanwhile, it
* will also include the PERF_COUNT_SW_PAGE_FAULTS_[MAJ|MIN] perf counter
- * updates. However note that the handling of PERF_COUNT_SW_PAGE_FAULTS should
+ * updates. However, note that the handling of PERF_COUNT_SW_PAGE_FAULTS should
* still be in per-arch page fault handlers at the entry of page fault.
*/
static inline void mm_account_fault(struct pt_regs *regs,
/**
* generic_access_phys - generic implementation for iomem mmap access
* @vma: the vma to access
- * @addr: userspace addres, not relative offset within @vma
+ * @addr: userspace address, not relative offset within @vma
* @buf: buffer to read/write
* @len: length of transfer
* @write: set to FOLL_WRITE when writing, otherwise reading
* Check if this is a VM_IO | VM_PFNMAP VMA, which
* we can access using slightly different code.
*/
- vma = find_vma(mm, addr);
- if (!vma || vma->vm_start > addr)
+ vma = vma_lookup(mm, addr);
+ if (!vma)
break;
if (vma->vm_ops && vma->vm_ops->access)
ret = vma->vm_ops->access(vma, addr, buf,