struct page *huge_zero_page __read_mostly;
unsigned long huge_zero_pfn __read_mostly = ~0UL;
-bool transparent_hugepage_enabled(struct vm_area_struct *vma)
+static inline bool file_thp_enabled(struct vm_area_struct *vma)
+{
+ return transhuge_vma_enabled(vma, vma->vm_flags) && vma->vm_file &&
+ !inode_is_open_for_write(vma->vm_file->f_inode) &&
+ (vma->vm_flags & VM_EXEC);
+}
+
+bool transparent_hugepage_active(struct vm_area_struct *vma)
{
/* The addr is used to check if the vma size fits */
unsigned long addr = (vma->vm_end & HPAGE_PMD_MASK) - HPAGE_PMD_SIZE;
return __transparent_hugepage_enabled(vma);
if (vma_is_shmem(vma))
return shmem_huge_enabled(vma);
+ if (IS_ENABLED(CONFIG_READ_ONLY_THP_FOR_FS))
+ return file_thp_enabled(vma);
return false;
}
int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm,
pmd_t *dst_pmd, pmd_t *src_pmd, unsigned long addr,
- struct vm_area_struct *vma)
+ struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma)
{
spinlock_t *dst_ptl, *src_ptl;
struct page *src_page;
int ret = -ENOMEM;
/* Skip if can be re-fill on fault */
- if (!vma_is_anonymous(vma))
+ if (!vma_is_anonymous(dst_vma))
return 0;
pgtable = pte_alloc_one(dst_mm);
ret = -EAGAIN;
pmd = *src_pmd;
- /*
- * 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 (!(vma->vm_flags & VM_UFFD_WP))
- pmd = pmd_clear_uffd_wp(pmd);
-
#ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION
if (unlikely(is_swap_pmd(pmd))) {
swp_entry_t entry = pmd_to_swp_entry(pmd);
VM_BUG_ON(!is_pmd_migration_entry(pmd));
- if (is_write_migration_entry(entry)) {
- make_migration_entry_read(&entry);
+ if (is_writable_migration_entry(entry)) {
+ entry = make_readable_migration_entry(
+ swp_offset(entry));
pmd = swp_entry_to_pmd(entry);
if (pmd_swp_soft_dirty(*src_pmd))
pmd = pmd_swp_mksoft_dirty(pmd);
+ if (pmd_swp_uffd_wp(*src_pmd))
+ pmd = pmd_swp_mkuffd_wp(pmd);
set_pmd_at(src_mm, addr, src_pmd, pmd);
}
add_mm_counter(dst_mm, MM_ANONPAGES, HPAGE_PMD_NR);
mm_inc_nr_ptes(dst_mm);
pgtable_trans_huge_deposit(dst_mm, dst_pmd, pgtable);
+ if (!userfaultfd_wp(dst_vma))
+ pmd = pmd_swp_clear_uffd_wp(pmd);
set_pmd_at(dst_mm, addr, dst_pmd, pmd);
ret = 0;
goto out_unlock;
* a page table.
*/
if (is_huge_zero_pmd(pmd)) {
- struct page *zero_page;
/*
* get_huge_zero_page() will never allocate a new page here,
* since we already have a zero page to copy. It just takes a
* reference.
*/
- zero_page = mm_get_huge_zero_page(dst_mm);
- set_huge_zero_page(pgtable, dst_mm, vma, addr, dst_pmd,
- zero_page);
- ret = 0;
- goto out_unlock;
+ mm_get_huge_zero_page(dst_mm);
+ goto out_zero_page;
}
src_page = pmd_page(pmd);
* best effort that the pinned pages won't be replaced by another
* random page during the coming copy-on-write.
*/
- if (unlikely(page_needs_cow_for_dma(vma, src_page))) {
+ if (unlikely(page_needs_cow_for_dma(src_vma, src_page))) {
pte_free(dst_mm, pgtable);
spin_unlock(src_ptl);
spin_unlock(dst_ptl);
- __split_huge_pmd(vma, src_pmd, addr, false, NULL);
+ __split_huge_pmd(src_vma, src_pmd, addr, false, NULL);
return -EAGAIN;
}
get_page(src_page);
page_dup_rmap(src_page, true);
add_mm_counter(dst_mm, MM_ANONPAGES, HPAGE_PMD_NR);
+out_zero_page:
mm_inc_nr_ptes(dst_mm);
pgtable_trans_huge_deposit(dst_mm, dst_pmd, pgtable);
-
pmdp_set_wrprotect(src_mm, addr, src_pmd);
+ if (!userfaultfd_wp(dst_vma))
+ pmd = pmd_clear_uffd_wp(pmd);
pmd = pmd_mkold(pmd_wrprotect(pmd));
set_pmd_at(dst_mm, addr, dst_pmd, pmd);
}
#endif /* CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */
-void huge_pmd_set_accessed(struct vm_fault *vmf, pmd_t orig_pmd)
+void huge_pmd_set_accessed(struct vm_fault *vmf)
{
pmd_t entry;
unsigned long haddr;
bool write = vmf->flags & FAULT_FLAG_WRITE;
+ pmd_t orig_pmd = vmf->orig_pmd;
vmf->ptl = pmd_lock(vmf->vma->vm_mm, vmf->pmd);
if (unlikely(!pmd_same(*vmf->pmd, orig_pmd)))
spin_unlock(vmf->ptl);
}
-vm_fault_t do_huge_pmd_wp_page(struct vm_fault *vmf, pmd_t orig_pmd)
+vm_fault_t do_huge_pmd_wp_page(struct vm_fault *vmf)
{
struct vm_area_struct *vma = vmf->vma;
struct page *page;
unsigned long haddr = vmf->address & HPAGE_PMD_MASK;
+ pmd_t orig_pmd = vmf->orig_pmd;
vmf->ptl = pmd_lockptr(vma->vm_mm, vmf->pmd);
VM_BUG_ON_VMA(!vma->anon_vma, vma);
}
/* NUMA hinting page fault entry point for trans huge pmds */
-vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf, pmd_t pmd)
+vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf)
{
struct vm_area_struct *vma = vmf->vma;
- struct anon_vma *anon_vma = NULL;
+ pmd_t oldpmd = vmf->orig_pmd;
+ pmd_t pmd;
struct page *page;
unsigned long haddr = vmf->address & HPAGE_PMD_MASK;
- int page_nid = NUMA_NO_NODE, this_nid = numa_node_id();
+ int page_nid = NUMA_NO_NODE;
int target_nid, last_cpupid = -1;
- bool page_locked;
bool migrated = false;
- bool was_writable;
+ bool was_writable = pmd_savedwrite(oldpmd);
int flags = 0;
vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd);
- if (unlikely(!pmd_same(pmd, *vmf->pmd)))
- goto out_unlock;
-
- /*
- * If there are potential migrations, wait for completion and retry
- * without disrupting NUMA hinting information. Do not relock and
- * check_same as the page may no longer be mapped.
- */
- if (unlikely(pmd_trans_migrating(*vmf->pmd))) {
- page = pmd_page(*vmf->pmd);
- if (!get_page_unless_zero(page))
- goto out_unlock;
+ if (unlikely(!pmd_same(oldpmd, *vmf->pmd))) {
spin_unlock(vmf->ptl);
- put_and_wait_on_page_locked(page, TASK_UNINTERRUPTIBLE);
goto out;
}
- page = pmd_page(pmd);
- BUG_ON(is_huge_zero_page(page));
- page_nid = page_to_nid(page);
- last_cpupid = page_cpupid_last(page);
- count_vm_numa_event(NUMA_HINT_FAULTS);
- if (page_nid == this_nid) {
- count_vm_numa_event(NUMA_HINT_FAULTS_LOCAL);
- flags |= TNF_FAULT_LOCAL;
- }
-
- /* See similar comment in do_numa_page for explanation */
- if (!pmd_savedwrite(pmd))
- flags |= TNF_NO_GROUP;
-
- /*
- * Acquire the page lock to serialise THP migrations but avoid dropping
- * page_table_lock if at all possible
- */
- page_locked = trylock_page(page);
- target_nid = mpol_misplaced(page, vma, haddr);
- /* Migration could have started since the pmd_trans_migrating check */
- if (!page_locked) {
- page_nid = NUMA_NO_NODE;
- if (!get_page_unless_zero(page))
- goto out_unlock;
- spin_unlock(vmf->ptl);
- put_and_wait_on_page_locked(page, TASK_UNINTERRUPTIBLE);
- goto out;
- } else if (target_nid == NUMA_NO_NODE) {
- /* There are no parallel migrations and page is in the right
- * node. Clear the numa hinting info in this pmd.
- */
- goto clear_pmdnuma;
- }
-
- /*
- * Page is misplaced. Page lock serialises migrations. Acquire anon_vma
- * to serialises splits
- */
- get_page(page);
- spin_unlock(vmf->ptl);
- anon_vma = page_lock_anon_vma_read(page);
-
- /* Confirm the PMD did not change while page_table_lock was released */
- spin_lock(vmf->ptl);
- if (unlikely(!pmd_same(pmd, *vmf->pmd))) {
- unlock_page(page);
- put_page(page);
- page_nid = NUMA_NO_NODE;
- goto out_unlock;
- }
-
- /* Bail if we fail to protect against THP splits for any reason */
- if (unlikely(!anon_vma)) {
- put_page(page);
- page_nid = NUMA_NO_NODE;
- goto clear_pmdnuma;
- }
-
/*
* Since we took the NUMA fault, we must have observed the !accessible
* bit. Make sure all other CPUs agree with that, to avoid them
haddr + HPAGE_PMD_SIZE);
}
- /*
- * Migrate the THP to the requested node, returns with page unlocked
- * and access rights restored.
- */
+ pmd = pmd_modify(oldpmd, vma->vm_page_prot);
+ page = vm_normal_page_pmd(vma, haddr, pmd);
+ if (!page)
+ goto out_map;
+
+ /* See similar comment in do_numa_page for explanation */
+ if (!was_writable)
+ flags |= TNF_NO_GROUP;
+
+ page_nid = page_to_nid(page);
+ last_cpupid = page_cpupid_last(page);
+ target_nid = numa_migrate_prep(page, vma, haddr, page_nid,
+ &flags);
+
+ if (target_nid == NUMA_NO_NODE) {
+ put_page(page);
+ goto out_map;
+ }
+
spin_unlock(vmf->ptl);
- migrated = migrate_misplaced_transhuge_page(vma->vm_mm, vma,
- vmf->pmd, pmd, vmf->address, page, target_nid);
+ migrated = migrate_misplaced_page(page, vma, target_nid);
if (migrated) {
flags |= TNF_MIGRATED;
page_nid = target_nid;
- } else
+ } else {
flags |= TNF_MIGRATE_FAIL;
-
- goto out;
-clear_pmdnuma:
- BUG_ON(!PageLocked(page));
- was_writable = pmd_savedwrite(pmd);
- pmd = pmd_modify(pmd, vma->vm_page_prot);
- pmd = pmd_mkyoung(pmd);
- if (was_writable)
- pmd = pmd_mkwrite(pmd);
- set_pmd_at(vma->vm_mm, haddr, vmf->pmd, pmd);
- update_mmu_cache_pmd(vma, vmf->address, vmf->pmd);
- unlock_page(page);
-out_unlock:
- spin_unlock(vmf->ptl);
+ vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd);
+ if (unlikely(!pmd_same(oldpmd, *vmf->pmd))) {
+ spin_unlock(vmf->ptl);
+ goto out;
+ }
+ goto out_map;
+ }
out:
- if (anon_vma)
- page_unlock_anon_vma_read(anon_vma);
-
if (page_nid != NUMA_NO_NODE)
task_numa_fault(last_cpupid, page_nid, HPAGE_PMD_NR,
flags);
return 0;
+
+out_map:
+ /* Restore the PMD */
+ pmd = pmd_modify(oldpmd, vma->vm_page_prot);
+ pmd = pmd_mkyoung(pmd);
+ if (was_writable)
+ pmd = pmd_mkwrite(pmd);
+ set_pmd_at(vma->vm_mm, haddr, vmf->pmd, pmd);
+ update_mmu_cache_pmd(vma, vmf->address, vmf->pmd);
+ spin_unlock(vmf->ptl);
+ goto out;
}
/*
* If other processes are mapping this page, we couldn't discard
* the page unless they all do MADV_FREE so let's skip the page.
*/
- if (page_mapcount(page) != 1)
+ if (total_mapcount(page) != 1)
goto out;
if (!trylock_page(page))
if (arch_needs_pgtable_deposit())
zap_deposited_table(tlb->mm, pmd);
spin_unlock(ptl);
- if (is_huge_zero_pmd(orig_pmd))
- tlb_remove_page_size(tlb, pmd_page(orig_pmd), HPAGE_PMD_SIZE);
} else if (is_huge_zero_pmd(orig_pmd)) {
zap_deposited_table(tlb->mm, pmd);
spin_unlock(ptl);
- tlb_remove_page_size(tlb, pmd_page(orig_pmd), HPAGE_PMD_SIZE);
} else {
struct page *page = NULL;
int flush_needed = 1;
VM_BUG_ON(!is_pmd_migration_entry(orig_pmd));
entry = pmd_to_swp_entry(orig_pmd);
- page = migration_entry_to_page(entry);
+ page = pfn_swap_entry_to_page(entry);
flush_needed = 0;
} else
WARN_ONCE(1, "Non present huge pmd without pmd migration enabled!");
* Returns
* - 0 if PMD could not be locked
* - 1 if PMD was locked but protections unchanged and TLB flush unnecessary
+ * or if prot_numa but THP migration is not supported
* - HPAGE_PMD_NR if protections changed and TLB flush necessary
*/
int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
bool uffd_wp = cp_flags & MM_CP_UFFD_WP;
bool uffd_wp_resolve = cp_flags & MM_CP_UFFD_WP_RESOLVE;
+ if (prot_numa && !thp_migration_supported())
+ return 1;
+
ptl = __pmd_trans_huge_lock(pmd, vma);
if (!ptl)
return 0;
swp_entry_t entry = pmd_to_swp_entry(*pmd);
VM_BUG_ON(!is_pmd_migration_entry(*pmd));
- if (is_write_migration_entry(entry)) {
+ if (is_writable_migration_entry(entry)) {
pmd_t newpmd;
/*
* A protection check is difficult so
* just be safe and disable write
*/
- make_migration_entry_read(&entry);
+ entry = make_readable_migration_entry(
+ swp_offset(entry));
newpmd = swp_entry_to_pmd(entry);
if (pmd_swp_soft_dirty(*pmd))
newpmd = pmd_swp_mksoft_dirty(newpmd);
+ if (pmd_swp_uffd_wp(*pmd))
+ newpmd = pmd_swp_mkuffd_wp(newpmd);
set_pmd_at(mm, addr, pmd, newpmd);
}
goto unlock;
swp_entry_t entry;
entry = pmd_to_swp_entry(old_pmd);
- page = migration_entry_to_page(entry);
+ page = pfn_swap_entry_to_page(entry);
} else {
page = pmd_page(old_pmd);
if (!PageDirty(page) && pmd_dirty(old_pmd))
swp_entry_t entry;
entry = pmd_to_swp_entry(old_pmd);
- page = migration_entry_to_page(entry);
- write = is_write_migration_entry(entry);
+ page = pfn_swap_entry_to_page(entry);
+ write = is_writable_migration_entry(entry);
young = false;
soft_dirty = pmd_swp_soft_dirty(old_pmd);
uffd_wp = pmd_swp_uffd_wp(old_pmd);
*/
if (freeze || pmd_migration) {
swp_entry_t swp_entry;
- swp_entry = make_migration_entry(page + i, write);
+ if (write)
+ swp_entry = make_writable_migration_entry(
+ page_to_pfn(page + i));
+ else
+ swp_entry = make_readable_migration_entry(
+ page_to_pfn(page + i));
entry = swp_entry_to_pte(swp_entry);
if (soft_dirty)
entry = pte_swp_mksoft_dirty(entry);
static void unmap_page(struct page *page)
{
- enum ttu_flags ttu_flags = TTU_IGNORE_MLOCK | TTU_SYNC |
- TTU_RMAP_LOCKED | TTU_SPLIT_HUGE_PMD;
+ enum ttu_flags ttu_flags = TTU_RMAP_LOCKED | TTU_SPLIT_HUGE_PMD |
+ TTU_SYNC;
VM_BUG_ON_PAGE(!PageHead(page), page);
+ /*
+ * Anon pages need migration entries to preserve them, but file
+ * pages can simply be left unmapped, then faulted back on demand.
+ * If that is ever changed (perhaps for mlock), update remap_page().
+ */
if (PageAnon(page))
- ttu_flags |= TTU_SPLIT_FREEZE;
-
- try_to_unmap(page, ttu_flags);
+ try_to_migrate(page, ttu_flags);
+ else
+ try_to_unmap(page, ttu_flags | TTU_IGNORE_MLOCK);
VM_WARN_ON_ONCE_PAGE(page_mapped(page), page);
}
static void remap_page(struct page *page, unsigned int nr)
{
int i;
+
+ /* If unmap_page() uses try_to_migrate() on file, remove this check */
+ if (!PageAnon(page))
+ return;
if (PageTransHuge(page)) {
remove_migration_ptes(page, page, true);
} else {
spin_lock_irqsave(&ds_queue->split_queue_lock, flags);
/* Take pin on all head pages to avoid freeing them under us */
list_for_each_safe(pos, next, &ds_queue->split_queue) {
- page = list_entry((void *)pos, struct page, mapping);
+ page = list_entry((void *)pos, struct page, deferred_list);
page = compound_head(page);
if (get_page_unless_zero(page)) {
list_move(page_deferred_list(page), &list);
spin_unlock_irqrestore(&ds_queue->split_queue_lock, flags);
list_for_each_safe(pos, next, &list) {
- page = list_entry((void *)pos, struct page, mapping);
+ page = list_entry((void *)pos, struct page, deferred_list);
if (!trylock_page(page))
goto next;
/* split_huge_page() removes page from list on success */
tok = strsep(&buf, ",");
if (tok) {
- strncpy(file_path, tok, MAX_INPUT_BUF_SZ);
+ strcpy(file_path, tok);
} else {
ret = -EINVAL;
goto out;
pmdval = pmdp_invalidate(vma, address, pvmw->pmd);
if (pmd_dirty(pmdval))
set_page_dirty(page);
- entry = make_migration_entry(page, pmd_write(pmdval));
+ if (pmd_write(pmdval))
+ entry = make_writable_migration_entry(page_to_pfn(page));
+ else
+ entry = make_readable_migration_entry(page_to_pfn(page));
pmdswp = swp_entry_to_pmd(entry);
if (pmd_soft_dirty(pmdval))
pmdswp = pmd_swp_mksoft_dirty(pmdswp);
pmde = pmd_mkold(mk_huge_pmd(new, vma->vm_page_prot));
if (pmd_swp_soft_dirty(*pvmw->pmd))
pmde = pmd_mksoft_dirty(pmde);
- if (is_write_migration_entry(entry))
+ if (is_writable_migration_entry(entry))
pmde = maybe_pmd_mkwrite(pmde, vma);
+ if (pmd_swp_uffd_wp(*pvmw->pmd))
+ pmde = pmd_wrprotect(pmd_mkuffd_wp(pmde));
flush_cache_range(vma, mmun_start, mmun_start + HPAGE_PMD_SIZE);
if (PageAnon(new))
projects / linux-2.6-microblaze.git / blobdiff