case MADV_FREE:
case MADV_POPULATE_READ:
case MADV_POPULATE_WRITE:
+ case MADV_COLLAPSE:
return 0;
default:
/* be safe, default to 1. list exceptions explicitly */
{
mmap_assert_locked(vma->vm_mm);
- if (vma->vm_file)
- return NULL;
-
return vma->anon_name;
}
#endif /* CONFIG_ANON_VMA_NAME */
/*
* Update the vm_flags on region of a vma, splitting it or merging it as
- * necessary. Must be called with mmap_sem held for writing;
+ * necessary. Must be called with mmap_lock held for writing;
* Caller should ensure anon_name stability by raising its refcount even when
* anon_name belongs to a valid vma because this function might free that vma.
*/
{
struct mm_struct *mm = vma->vm_mm;
int error;
- pgoff_t pgoff;
+ VMA_ITERATOR(vmi, mm, start);
if (new_flags == vma->vm_flags && anon_vma_name_eq(anon_vma_name(vma), anon_name)) {
*prev = vma;
return 0;
}
- pgoff = vma->vm_pgoff + ((start - vma->vm_start) >> PAGE_SHIFT);
- *prev = vma_merge(mm, *prev, start, end, new_flags, vma->anon_vma,
- vma->vm_file, pgoff, vma_policy(vma),
- vma->vm_userfaultfd_ctx, anon_name);
- if (*prev) {
- vma = *prev;
- goto success;
- }
+ vma = vma_modify_flags_name(&vmi, *prev, vma, start, end, new_flags,
+ anon_name);
+ if (IS_ERR(vma))
+ return PTR_ERR(vma);
*prev = vma;
- if (start != vma->vm_start) {
- if (unlikely(mm->map_count >= sysctl_max_map_count))
- return -ENOMEM;
- error = __split_vma(mm, vma, start, 1);
- if (error)
- return error;
- }
-
- if (end != vma->vm_end) {
- if (unlikely(mm->map_count >= sysctl_max_map_count))
- return -ENOMEM;
- error = __split_vma(mm, vma, end, 0);
- if (error)
- return error;
- }
-
-success:
- /*
- * vm_flags is protected by the mmap_lock held in write mode.
- */
- vma->vm_flags = new_flags;
- if (!vma->vm_file) {
+ /* vm_flags is protected by the mmap_lock held in write mode. */
+ vma_start_write(vma);
+ vm_flags_reset(vma, new_flags);
+ if (!vma->vm_file || vma_is_anon_shmem(vma)) {
error = replace_anon_vma_name(vma, anon_name);
if (error)
return error;
#ifdef CONFIG_SWAP
static int swapin_walk_pmd_entry(pmd_t *pmd, unsigned long start,
- unsigned long end, struct mm_walk *walk)
+ unsigned long end, struct mm_walk *walk)
{
struct vm_area_struct *vma = walk->private;
- unsigned long index;
struct swap_iocb *splug = NULL;
+ pte_t *ptep = NULL;
+ spinlock_t *ptl;
+ unsigned long addr;
- if (pmd_none_or_trans_huge_or_clear_bad(pmd))
- return 0;
-
- for (index = start; index != end; index += PAGE_SIZE) {
+ for (addr = start; addr < end; addr += PAGE_SIZE) {
pte_t pte;
swp_entry_t entry;
- struct page *page;
- spinlock_t *ptl;
- pte_t *ptep;
+ struct folio *folio;
- ptep = pte_offset_map_lock(vma->vm_mm, pmd, index, &ptl);
- pte = *ptep;
- pte_unmap_unlock(ptep, ptl);
+ if (!ptep++) {
+ ptep = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
+ if (!ptep)
+ break;
+ }
+ pte = ptep_get(ptep);
if (!is_swap_pte(pte))
continue;
entry = pte_to_swp_entry(pte);
if (unlikely(non_swap_entry(entry)))
continue;
- page = read_swap_cache_async(entry, GFP_HIGHUSER_MOVABLE,
- vma, index, false, &splug);
- if (page)
- put_page(page);
+ pte_unmap_unlock(ptep, ptl);
+ ptep = NULL;
+
+ folio = read_swap_cache_async(entry, GFP_HIGHUSER_MOVABLE,
+ vma, addr, &splug);
+ if (folio)
+ folio_put(folio);
}
+
+ if (ptep)
+ pte_unmap_unlock(ptep, ptl);
swap_read_unplug(splug);
+ cond_resched();
return 0;
}
static const struct mm_walk_ops swapin_walk_ops = {
.pmd_entry = swapin_walk_pmd_entry,
+ .walk_lock = PGWALK_RDLOCK,
};
-static void force_shm_swapin_readahead(struct vm_area_struct *vma,
+static void shmem_swapin_range(struct vm_area_struct *vma,
unsigned long start, unsigned long end,
struct address_space *mapping)
{
XA_STATE(xas, &mapping->i_pages, linear_page_index(vma, start));
- pgoff_t end_index = linear_page_index(vma, end + PAGE_SIZE - 1);
- struct page *page;
+ pgoff_t end_index = linear_page_index(vma, end) - 1;
+ struct folio *folio;
struct swap_iocb *splug = NULL;
rcu_read_lock();
- xas_for_each(&xas, page, end_index) {
- swp_entry_t swap;
+ xas_for_each(&xas, folio, end_index) {
+ unsigned long addr;
+ swp_entry_t entry;
- if (!xa_is_value(page))
+ if (!xa_is_value(folio))
continue;
- swap = radix_to_swp_entry(page);
+ entry = radix_to_swp_entry(folio);
/* There might be swapin error entries in shmem mapping. */
- if (non_swap_entry(swap))
+ if (non_swap_entry(entry))
continue;
+
+ addr = vma->vm_start +
+ ((xas.xa_index - vma->vm_pgoff) << PAGE_SHIFT);
xas_pause(&xas);
rcu_read_unlock();
- page = read_swap_cache_async(swap, GFP_HIGHUSER_MOVABLE,
- NULL, 0, false, &splug);
- if (page)
- put_page(page);
+ folio = read_swap_cache_async(entry, mapping_gfp_mask(mapping),
+ vma, addr, &splug);
+ if (folio)
+ folio_put(folio);
rcu_read_lock();
}
rcu_read_unlock();
swap_read_unplug(splug);
-
- lru_add_drain(); /* Push any new pages onto the LRU now */
}
#endif /* CONFIG_SWAP */
}
if (shmem_mapping(file->f_mapping)) {
- force_shm_swapin_readahead(vma, start, end,
- file->f_mapping);
+ shmem_swapin_range(vma, start, end, file->f_mapping);
+ lru_add_drain(); /* Push any new pages onto the LRU now */
return 0;
}
#else
return 0;
}
+static inline bool can_do_file_pageout(struct vm_area_struct *vma)
+{
+ if (!vma->vm_file)
+ return false;
+ /*
+ * paging out pagecache only for non-anonymous mappings that correspond
+ * to the files the calling process could (if tried) open for writing;
+ * otherwise we'd be including shared non-exclusive mappings, which
+ * opens a side channel.
+ */
+ return inode_owner_or_capable(&nop_mnt_idmap,
+ file_inode(vma->vm_file)) ||
+ file_permission(vma->vm_file, MAY_WRITE) == 0;
+}
+
static int madvise_cold_or_pageout_pte_range(pmd_t *pmd,
unsigned long addr, unsigned long end,
struct mm_walk *walk)
bool pageout = private->pageout;
struct mm_struct *mm = tlb->mm;
struct vm_area_struct *vma = walk->vma;
- pte_t *orig_pte, *pte, ptent;
+ pte_t *start_pte, *pte, ptent;
spinlock_t *ptl;
- struct page *page = NULL;
- LIST_HEAD(page_list);
+ struct folio *folio = NULL;
+ LIST_HEAD(folio_list);
+ bool pageout_anon_only_filter;
+ unsigned int batch_count = 0;
if (fatal_signal_pending(current))
return -EINTR;
+ pageout_anon_only_filter = pageout && !vma_is_anonymous(vma) &&
+ !can_do_file_pageout(vma);
+
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
if (pmd_trans_huge(*pmd)) {
pmd_t orig_pmd;
goto huge_unlock;
}
- page = pmd_page(orig_pmd);
+ folio = pfn_folio(pmd_pfn(orig_pmd));
- /* Do not interfere with other mappings of this page */
- if (page_mapcount(page) != 1)
+ /* Do not interfere with other mappings of this folio */
+ if (folio_estimated_sharers(folio) != 1)
+ goto huge_unlock;
+
+ if (pageout_anon_only_filter && !folio_test_anon(folio))
goto huge_unlock;
if (next - addr != HPAGE_PMD_SIZE) {
int err;
- get_page(page);
+ folio_get(folio);
spin_unlock(ptl);
- lock_page(page);
- err = split_huge_page(page);
- unlock_page(page);
- put_page(page);
+ folio_lock(folio);
+ err = split_folio(folio);
+ folio_unlock(folio);
+ folio_put(folio);
if (!err)
- goto regular_page;
+ goto regular_folio;
return 0;
}
- if (pmd_young(orig_pmd)) {
+ if (!pageout && pmd_young(orig_pmd)) {
pmdp_invalidate(vma, addr, pmd);
orig_pmd = pmd_mkold(orig_pmd);
tlb_remove_pmd_tlb_entry(tlb, pmd, addr);
}
- ClearPageReferenced(page);
- test_and_clear_page_young(page);
+ folio_clear_referenced(folio);
+ folio_test_clear_young(folio);
+ if (folio_test_active(folio))
+ folio_set_workingset(folio);
if (pageout) {
- if (!isolate_lru_page(page)) {
- if (PageUnevictable(page))
- putback_lru_page(page);
+ if (folio_isolate_lru(folio)) {
+ if (folio_test_unevictable(folio))
+ folio_putback_lru(folio);
else
- list_add(&page->lru, &page_list);
+ list_add(&folio->lru, &folio_list);
}
} else
- deactivate_page(page);
+ folio_deactivate(folio);
huge_unlock:
spin_unlock(ptl);
if (pageout)
- reclaim_pages(&page_list);
+ reclaim_pages(&folio_list, true);
return 0;
}
-regular_page:
- if (pmd_trans_unstable(pmd))
- return 0;
+regular_folio:
#endif
tlb_change_page_size(tlb, PAGE_SIZE);
- orig_pte = pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
+restart:
+ start_pte = pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
+ if (!start_pte)
+ return 0;
flush_tlb_batched_pending(mm);
arch_enter_lazy_mmu_mode();
for (; addr < end; pte++, addr += PAGE_SIZE) {
- ptent = *pte;
+ ptent = ptep_get(pte);
+
+ if (++batch_count == SWAP_CLUSTER_MAX) {
+ batch_count = 0;
+ if (need_resched()) {
+ arch_leave_lazy_mmu_mode();
+ pte_unmap_unlock(start_pte, ptl);
+ cond_resched();
+ goto restart;
+ }
+ }
if (pte_none(ptent))
continue;
if (!pte_present(ptent))
continue;
- page = vm_normal_page(vma, addr, ptent);
- if (!page || is_zone_device_page(page))
+ folio = vm_normal_folio(vma, addr, ptent);
+ if (!folio || folio_is_zone_device(folio))
continue;
/*
* Creating a THP page is expensive so split it only if we
* are sure it's worth. Split it if we are only owner.
*/
- if (PageTransCompound(page)) {
- if (page_mapcount(page) != 1)
+ if (folio_test_large(folio)) {
+ int err;
+
+ if (folio_estimated_sharers(folio) > 1)
break;
- get_page(page);
- if (!trylock_page(page)) {
- put_page(page);
+ if (pageout_anon_only_filter && !folio_test_anon(folio))
break;
- }
- pte_unmap_unlock(orig_pte, ptl);
- if (split_huge_page(page)) {
- unlock_page(page);
- put_page(page);
- orig_pte = pte_offset_map_lock(mm, pmd, addr, &ptl);
+ if (!folio_trylock(folio))
break;
- }
- unlock_page(page);
- put_page(page);
- orig_pte = pte = pte_offset_map_lock(mm, pmd, addr, &ptl);
+ folio_get(folio);
+ arch_leave_lazy_mmu_mode();
+ pte_unmap_unlock(start_pte, ptl);
+ start_pte = NULL;
+ err = split_folio(folio);
+ folio_unlock(folio);
+ folio_put(folio);
+ if (err)
+ break;
+ start_pte = pte =
+ pte_offset_map_lock(mm, pmd, addr, &ptl);
+ if (!start_pte)
+ break;
+ arch_enter_lazy_mmu_mode();
pte--;
addr -= PAGE_SIZE;
continue;
}
- /* Do not interfere with other mappings of this page */
- if (page_mapcount(page) != 1)
+ /*
+ * Do not interfere with other mappings of this folio and
+ * non-LRU folio.
+ */
+ if (!folio_test_lru(folio) || folio_mapcount(folio) != 1)
+ continue;
+
+ if (pageout_anon_only_filter && !folio_test_anon(folio))
continue;
- VM_BUG_ON_PAGE(PageTransCompound(page), page);
+ VM_BUG_ON_FOLIO(folio_test_large(folio), folio);
- if (pte_young(ptent)) {
+ if (!pageout && pte_young(ptent)) {
ptent = ptep_get_and_clear_full(mm, addr, pte,
tlb->fullmm);
ptent = pte_mkold(ptent);
}
/*
- * We are deactivating a page for accelerating reclaiming.
- * VM couldn't reclaim the page unless we clear PG_young.
+ * We are deactivating a folio for accelerating reclaiming.
+ * VM couldn't reclaim the folio unless we clear PG_young.
* As a side effect, it makes confuse idle-page tracking
* because they will miss recent referenced history.
*/
- ClearPageReferenced(page);
- test_and_clear_page_young(page);
+ folio_clear_referenced(folio);
+ folio_test_clear_young(folio);
+ if (folio_test_active(folio))
+ folio_set_workingset(folio);
if (pageout) {
- if (!isolate_lru_page(page)) {
- if (PageUnevictable(page))
- putback_lru_page(page);
+ if (folio_isolate_lru(folio)) {
+ if (folio_test_unevictable(folio))
+ folio_putback_lru(folio);
else
- list_add(&page->lru, &page_list);
+ list_add(&folio->lru, &folio_list);
}
} else
- deactivate_page(page);
+ folio_deactivate(folio);
}
- arch_leave_lazy_mmu_mode();
- pte_unmap_unlock(orig_pte, ptl);
+ if (start_pte) {
+ arch_leave_lazy_mmu_mode();
+ pte_unmap_unlock(start_pte, ptl);
+ }
if (pageout)
- reclaim_pages(&page_list);
+ reclaim_pages(&folio_list, true);
cond_resched();
return 0;
static const struct mm_walk_ops cold_walk_ops = {
.pmd_entry = madvise_cold_or_pageout_pte_range,
+ .walk_lock = PGWALK_RDLOCK,
};
static void madvise_cold_page_range(struct mmu_gather *tlb,
tlb_end_vma(tlb, vma);
}
-static inline bool can_do_pageout(struct vm_area_struct *vma)
-{
- if (vma_is_anonymous(vma))
- return true;
- if (!vma->vm_file)
- return false;
- /*
- * paging out pagecache only for non-anonymous mappings that correspond
- * to the files the calling process could (if tried) open for writing;
- * otherwise we'd be including shared non-exclusive mappings, which
- * opens a side channel.
- */
- return inode_owner_or_capable(&init_user_ns,
- file_inode(vma->vm_file)) ||
- file_permission(vma->vm_file, MAY_WRITE) == 0;
-}
-
static long madvise_pageout(struct vm_area_struct *vma,
struct vm_area_struct **prev,
unsigned long start_addr, unsigned long end_addr)
if (!can_madv_lru_vma(vma))
return -EINVAL;
- if (!can_do_pageout(vma))
+ /*
+ * If the VMA belongs to a private file mapping, there can be private
+ * dirty pages which can be paged out if even this process is neither
+ * owner nor write capable of the file. We allow private file mappings
+ * further to pageout dirty anon pages.
+ */
+ if (!vma_is_anonymous(vma) && (!can_do_file_pageout(vma) &&
+ (vma->vm_flags & VM_MAYSHARE)))
return 0;
lru_add_drain();
struct mm_struct *mm = tlb->mm;
struct vm_area_struct *vma = walk->vma;
spinlock_t *ptl;
- pte_t *orig_pte, *pte, ptent;
- struct page *page;
+ pte_t *start_pte, *pte, ptent;
+ struct folio *folio;
int nr_swap = 0;
unsigned long next;
next = pmd_addr_end(addr, end);
if (pmd_trans_huge(*pmd))
if (madvise_free_huge_pmd(tlb, vma, pmd, addr, next))
- goto next;
-
- if (pmd_trans_unstable(pmd))
- return 0;
+ return 0;
tlb_change_page_size(tlb, PAGE_SIZE);
- orig_pte = pte = pte_offset_map_lock(mm, pmd, addr, &ptl);
+ start_pte = pte = pte_offset_map_lock(mm, pmd, addr, &ptl);
+ if (!start_pte)
+ return 0;
flush_tlb_batched_pending(mm);
arch_enter_lazy_mmu_mode();
for (; addr != end; pte++, addr += PAGE_SIZE) {
- ptent = *pte;
+ ptent = ptep_get(pte);
if (pte_none(ptent))
continue;
free_swap_and_cache(entry);
pte_clear_not_present_full(mm, addr, pte, tlb->fullmm);
} else if (is_hwpoison_entry(entry) ||
- is_swapin_error_entry(entry)) {
+ is_poisoned_swp_entry(entry)) {
pte_clear_not_present_full(mm, addr, pte, tlb->fullmm);
}
continue;
}
- page = vm_normal_page(vma, addr, ptent);
- if (!page || is_zone_device_page(page))
+ folio = vm_normal_folio(vma, addr, ptent);
+ if (!folio || folio_is_zone_device(folio))
continue;
/*
- * If pmd isn't transhuge but the page is THP and
+ * If pmd isn't transhuge but the folio is large and
* is owned by only this process, split it and
* deactivate all pages.
*/
- if (PageTransCompound(page)) {
- if (page_mapcount(page) != 1)
- goto out;
- get_page(page);
- if (!trylock_page(page)) {
- put_page(page);
- goto out;
- }
- pte_unmap_unlock(orig_pte, ptl);
- if (split_huge_page(page)) {
- unlock_page(page);
- put_page(page);
- orig_pte = pte_offset_map_lock(mm, pmd, addr, &ptl);
- goto out;
- }
- unlock_page(page);
- put_page(page);
- orig_pte = pte = pte_offset_map_lock(mm, pmd, addr, &ptl);
+ if (folio_test_large(folio)) {
+ int err;
+
+ if (folio_estimated_sharers(folio) != 1)
+ break;
+ if (!folio_trylock(folio))
+ break;
+ folio_get(folio);
+ arch_leave_lazy_mmu_mode();
+ pte_unmap_unlock(start_pte, ptl);
+ start_pte = NULL;
+ err = split_folio(folio);
+ folio_unlock(folio);
+ folio_put(folio);
+ if (err)
+ break;
+ start_pte = pte =
+ pte_offset_map_lock(mm, pmd, addr, &ptl);
+ if (!start_pte)
+ break;
+ arch_enter_lazy_mmu_mode();
pte--;
addr -= PAGE_SIZE;
continue;
}
- VM_BUG_ON_PAGE(PageTransCompound(page), page);
-
- if (PageSwapCache(page) || PageDirty(page)) {
- if (!trylock_page(page))
+ if (folio_test_swapcache(folio) || folio_test_dirty(folio)) {
+ if (!folio_trylock(folio))
continue;
/*
- * If page is shared with others, we couldn't clear
- * PG_dirty of the page.
+ * If folio is shared with others, we mustn't clear
+ * the folio's dirty flag.
*/
- if (page_mapcount(page) != 1) {
- unlock_page(page);
+ if (folio_mapcount(folio) != 1) {
+ folio_unlock(folio);
continue;
}
- if (PageSwapCache(page) && !try_to_free_swap(page)) {
- unlock_page(page);
+ if (folio_test_swapcache(folio) &&
+ !folio_free_swap(folio)) {
+ folio_unlock(folio);
continue;
}
- ClearPageDirty(page);
- unlock_page(page);
+ folio_clear_dirty(folio);
+ folio_unlock(folio);
}
if (pte_young(ptent) || pte_dirty(ptent)) {
set_pte_at(mm, addr, pte, ptent);
tlb_remove_tlb_entry(tlb, pte, addr);
}
- mark_page_lazyfree(page);
+ folio_mark_lazyfree(folio);
}
-out:
- if (nr_swap) {
- if (current->mm == mm)
- sync_mm_rss(mm);
+ if (nr_swap)
add_mm_counter(mm, MM_SWAPENTS, nr_swap);
+ if (start_pte) {
+ arch_leave_lazy_mmu_mode();
+ pte_unmap_unlock(start_pte, ptl);
}
- arch_leave_lazy_mmu_mode();
- pte_unmap_unlock(orig_pte, ptl);
cond_resched();
-next:
+
return 0;
}
static const struct mm_walk_ops madvise_free_walk_ops = {
.pmd_entry = madvise_free_pte_range,
+ .walk_lock = PGWALK_RDLOCK,
};
static int madvise_free_single_vma(struct vm_area_struct *vma,
range.end = min(vma->vm_end, end_addr);
if (range.end <= vma->vm_start)
return -EINVAL;
- mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, mm,
+ mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, mm,
range.start, range.end);
lru_add_drain();
* Application no longer needs these pages. If the pages are dirty,
* it's OK to just throw them away. The app will be more careful about
* data it wants to keep. Be sure to free swap resources too. The
- * zap_page_range call sets things up for shrink_active_list to actually free
- * these pages later if no one else has touched them in the meantime,
+ * zap_page_range_single call sets things up for shrink_active_list to actually
+ * free these pages later if no one else has touched them in the meantime,
* although we could add these pages to a global reuse list for
* shrink_active_list to pick up before reclaiming other pages.
*
static long madvise_dontneed_single_vma(struct vm_area_struct *vma,
unsigned long start, unsigned long end)
{
- zap_page_range(vma, start, end - start);
+ zap_page_range_single(vma, start, end - start, NULL);
return 0;
}
if (start & ~huge_page_mask(hstate_vma(vma)))
return false;
- *end = ALIGN(*end, huge_page_size(hstate_vma(vma)));
+ /*
+ * Madvise callers expect the length to be rounded up to PAGE_SIZE
+ * boundaries, and may be unaware that this VMA uses huge pages.
+ * Avoid unexpected data loss by rounding down the number of
+ * huge pages freed.
+ */
+ *end = ALIGN_DOWN(*end, huge_page_size(hstate_vma(vma)));
+
return true;
}
if (!madvise_dontneed_free_valid_vma(vma, start, &end, behavior))
return -EINVAL;
+ if (start == end)
+ return 0;
+
if (!userfaultfd_remove(vma, start, end)) {
*prev = NULL; /* mmap_lock has been dropped, prev is stale */
mmap_read_lock(mm);
- vma = find_vma(mm, start);
+ vma = vma_lookup(mm, start);
if (!vma)
return -ENOMEM;
- if (start < vma->vm_start) {
- /*
- * This "vma" under revalidation is the one
- * with the lowest vma->vm_start where start
- * is also < vma->vm_end. If start <
- * vma->vm_start it means an hole materialized
- * in the user address space within the
- * virtual range passed to MADV_DONTNEED
- * or MADV_FREE.
- */
- return -ENOMEM;
- }
/*
* Potential end adjustment for hugetlb vma is OK as
* the check below keeps end within vma.
return -EINVAL;
}
- if ((vma->vm_flags & (VM_SHARED|VM_WRITE)) != (VM_SHARED|VM_WRITE))
+ if (!vma_is_shared_maywrite(vma))
return -EACCES;
offset = (loff_t)(start - vma->vm_start)
if (error)
goto out;
break;
+ case MADV_COLLAPSE:
+ return madvise_collapse(vma, prev, start, end);
}
anon_name = anon_vma_name(vma);
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
case MADV_HUGEPAGE:
case MADV_NOHUGEPAGE:
+ case MADV_COLLAPSE:
#endif
case MADV_DONTDUMP:
case MADV_DODUMP:
}
}
-static bool
-process_madvise_behavior_valid(int behavior)
+static bool process_madvise_behavior_valid(int behavior)
{
switch (behavior) {
case MADV_COLD:
case MADV_PAGEOUT:
case MADV_WILLNEED:
+ case MADV_COLLAPSE:
return true;
default:
return false;
if (start >= end)
break;
if (prev)
- vma = prev->vm_next;
+ vma = find_vma(mm, prev->vm_end);
else /* madvise_remove dropped mmap_lock */
vma = find_vma(mm, start);
}
int error;
/* Only anonymous mappings can be named */
- if (vma->vm_file)
+ if (vma->vm_file && !vma_is_anon_shmem(vma))
return -EBADF;
error = madvise_update_vma(vma, prev, start, end, vma->vm_flags,
* MADV_NOHUGEPAGE - mark the given range as not worth being backed by
* transparent huge pages so the existing pages will not be
* coalesced into THP and new pages will not be allocated as THP.
+ * MADV_COLLAPSE - synchronously coalesce pages into new THP.
* MADV_DONTDUMP - the application wants to prevent pages in the given range
* from being included in its core dump.
* MADV_DODUMP - cancel MADV_DONTDUMP: no longer exclude from core dump.
size_t len;
struct blk_plug plug;
- start = untagged_addr(start);
-
if (!madvise_behavior_valid(behavior))
return -EINVAL;
mmap_read_lock(mm);
}
+ start = untagged_addr_remote(mm, start);
+ end = start + len;
+
blk_start_plug(&plug);
error = madvise_walk_vmas(mm, start, end, behavior,
madvise_vma_behavior);
size_t, vlen, int, behavior, unsigned int, flags)
{
ssize_t ret;
- struct iovec iovstack[UIO_FASTIOV], iovec;
+ struct iovec iovstack[UIO_FASTIOV];
struct iovec *iov = iovstack;
struct iov_iter iter;
struct task_struct *task;
goto out;
}
- ret = import_iovec(READ, vec, vlen, ARRAY_SIZE(iovstack), &iov, &iter);
+ ret = import_iovec(ITER_DEST, vec, vlen, ARRAY_SIZE(iovstack), &iov, &iter);
if (ret < 0)
goto out;
total_len = iov_iter_count(&iter);
while (iov_iter_count(&iter)) {
- iovec = iov_iter_iovec(&iter);
- ret = do_madvise(mm, (unsigned long)iovec.iov_base,
- iovec.iov_len, behavior);
+ ret = do_madvise(mm, (unsigned long)iter_iov_addr(&iter),
+ iter_iov_len(&iter), behavior);
if (ret < 0)
break;
- iov_iter_advance(&iter, iovec.iov_len);
+ iov_iter_advance(&iter, iter_iov_len(&iter));
}
ret = (total_len - iov_iter_count(&iter)) ? : ret;