#include <linux/rmap.h>
#include <linux/swap.h>
#include <linux/swapops.h>
+#include <linux/secretmem.h>
#include <linux/sched/signal.h>
#include <linux/rwsem.h>
atomic_sub(refs, compound_pincount_ptr(page));
}
+/* Equivalent to calling put_page() @refs times. */
+static void put_page_refs(struct page *page, int refs)
+{
+#ifdef CONFIG_DEBUG_VM
+ if (VM_WARN_ON_ONCE_PAGE(page_ref_count(page) < refs, page))
+ return;
+#endif
+
+ /*
+ * Calling put_page() for each ref is unnecessarily slow. Only the last
+ * ref needs a put_page().
+ */
+ if (refs > 1)
+ page_ref_sub(page, refs - 1);
+ put_page(page);
+}
+
/*
* Return the compound head page with ref appropriately incremented,
* or NULL if that failed.
return NULL;
if (unlikely(!page_cache_add_speculative(head, refs)))
return NULL;
+
+ /*
+ * At this point we have a stable reference to the head page; but it
+ * could be that between the compound_head() lookup and the refcount
+ * increment, the compound page was split, in which case we'd end up
+ * holding a reference on a page that has nothing to do with the page
+ * we were given anymore.
+ * So now that the head page is stable, recheck that the pages still
+ * belong together.
+ */
+ if (unlikely(compound_head(page) != head)) {
+ put_page_refs(head, refs);
+ return NULL;
+ }
+
return head;
}
int orig_refs = refs;
/*
- * Can't do FOLL_LONGTERM + FOLL_PIN with CMA in the gup fast
- * path, so fail and let the caller fall back to the slow path.
+ * Can't do FOLL_LONGTERM + FOLL_PIN gup fast path if not in a
+ * right zone, so fail and let the caller fall back to the slow
+ * path.
+ */
+ if (unlikely((flags & FOLL_LONGTERM) &&
+ !is_pinnable_page(page)))
+ return NULL;
+
+ /*
+ * CAUTION: Don't use compound_head() on the page before this
+ * point, the result won't be stable.
*/
- if (unlikely(flags & FOLL_LONGTERM) &&
- is_migrate_cma_page(page))
+ page = try_get_compound_head(page, refs);
+ if (!page)
return NULL;
/*
* However, be sure to *also* increment the normal page refcount
* field at least once, so that the page really is pinned.
*/
- if (!hpage_pincount_available(page))
- refs *= GUP_PIN_COUNTING_BIAS;
-
- page = try_get_compound_head(page, refs);
- if (!page)
- return NULL;
-
if (hpage_pincount_available(page))
hpage_pincount_add(page, refs);
+ else
+ page_ref_add(page, refs * (GUP_PIN_COUNTING_BIAS - 1));
mod_node_page_state(page_pgdat(page), NR_FOLL_PIN_ACQUIRED,
orig_refs);
refs *= GUP_PIN_COUNTING_BIAS;
}
- VM_BUG_ON_PAGE(page_ref_count(page) < refs, page);
- /*
- * Calling put_page() for each ref is unnecessarily slow. Only the last
- * ref needs a put_page().
- */
- if (refs > 1)
- page_ref_sub(page, refs - 1);
- put_page(page);
+ put_page_refs(page, refs);
}
/**
}
EXPORT_SYMBOL(unpin_user_page);
+static inline void compound_range_next(unsigned long i, unsigned long npages,
+ struct page **list, struct page **head,
+ unsigned int *ntails)
+{
+ struct page *next, *page;
+ unsigned int nr = 1;
+
+ if (i >= npages)
+ return;
+
+ next = *list + i;
+ page = compound_head(next);
+ if (PageCompound(page) && compound_order(page) >= 1)
+ nr = min_t(unsigned int,
+ page + compound_nr(page) - next, npages - i);
+
+ *head = page;
+ *ntails = nr;
+}
+
+#define for_each_compound_range(__i, __list, __npages, __head, __ntails) \
+ for (__i = 0, \
+ compound_range_next(__i, __npages, __list, &(__head), &(__ntails)); \
+ __i < __npages; __i += __ntails, \
+ compound_range_next(__i, __npages, __list, &(__head), &(__ntails)))
+
+static inline void compound_next(unsigned long i, unsigned long npages,
+ struct page **list, struct page **head,
+ unsigned int *ntails)
+{
+ struct page *page;
+ unsigned int nr;
+
+ if (i >= npages)
+ return;
+
+ page = compound_head(list[i]);
+ for (nr = i + 1; nr < npages; nr++) {
+ if (compound_head(list[nr]) != page)
+ break;
+ }
+
+ *head = page;
+ *ntails = nr - i;
+}
+
+#define for_each_compound_head(__i, __list, __npages, __head, __ntails) \
+ for (__i = 0, \
+ compound_next(__i, __npages, __list, &(__head), &(__ntails)); \
+ __i < __npages; __i += __ntails, \
+ compound_next(__i, __npages, __list, &(__head), &(__ntails)))
+
/**
* unpin_user_pages_dirty_lock() - release and optionally dirty gup-pinned pages
* @pages: array of pages to be maybe marked dirty, and definitely released.
bool make_dirty)
{
unsigned long index;
-
- /*
- * TODO: this can be optimized for huge pages: if a series of pages is
- * physically contiguous and part of the same compound page, then a
- * single operation to the head page should suffice.
- */
+ struct page *head;
+ unsigned int ntails;
if (!make_dirty) {
unpin_user_pages(pages, npages);
return;
}
- for (index = 0; index < npages; index++) {
- struct page *page = compound_head(pages[index]);
+ for_each_compound_head(index, pages, npages, head, ntails) {
/*
* Checking PageDirty at this point may race with
* clear_page_dirty_for_io(), but that's OK. Two key
* written back, so it gets written back again in the
* next writeback cycle. This is harmless.
*/
- if (!PageDirty(page))
- set_page_dirty_lock(page);
- unpin_user_page(page);
+ if (!PageDirty(head))
+ set_page_dirty_lock(head);
+ put_compound_head(head, ntails, FOLL_PIN);
}
}
EXPORT_SYMBOL(unpin_user_pages_dirty_lock);
+/**
+ * unpin_user_page_range_dirty_lock() - release and optionally dirty
+ * gup-pinned page range
+ *
+ * @page: the starting page of a range maybe marked dirty, and definitely released.
+ * @npages: number of consecutive pages to release.
+ * @make_dirty: whether to mark the pages dirty
+ *
+ * "gup-pinned page range" refers to a range of pages that has had one of the
+ * pin_user_pages() variants called on that page.
+ *
+ * For the page ranges defined by [page .. page+npages], make that range (or
+ * its head pages, if a compound page) dirty, if @make_dirty is true, and if the
+ * page range was previously listed as clean.
+ *
+ * set_page_dirty_lock() is used internally. If instead, set_page_dirty() is
+ * required, then the caller should a) verify that this is really correct,
+ * because _lock() is usually required, and b) hand code it:
+ * set_page_dirty_lock(), unpin_user_page().
+ *
+ */
+void unpin_user_page_range_dirty_lock(struct page *page, unsigned long npages,
+ bool make_dirty)
+{
+ unsigned long index;
+ struct page *head;
+ unsigned int ntails;
+
+ for_each_compound_range(index, &page, npages, head, ntails) {
+ if (make_dirty && !PageDirty(head))
+ set_page_dirty_lock(head);
+ put_compound_head(head, ntails, FOLL_PIN);
+ }
+}
+EXPORT_SYMBOL(unpin_user_page_range_dirty_lock);
+
/**
* unpin_user_pages() - release an array of gup-pinned pages.
* @pages: array of pages to be marked dirty and released.
void unpin_user_pages(struct page **pages, unsigned long npages)
{
unsigned long index;
+ struct page *head;
+ unsigned int ntails;
/*
* If this WARN_ON() fires, then the system *might* be leaking pages (by
*/
if (WARN_ON(IS_ERR_VALUE(npages)))
return;
- /*
- * TODO: this can be optimized for huge pages: if a series of pages is
- * physically contiguous and part of the same compound page, then a
- * single operation to the head page should suffice.
- */
- for (index = 0; index < npages; index++)
- unpin_user_page(pages[index]);
+
+ for_each_compound_head(index, pages, npages, head, ntails)
+ put_compound_head(head, ntails, FOLL_PIN);
}
EXPORT_SYMBOL(unpin_user_pages);
+/*
+ * Set the MMF_HAS_PINNED if not set yet; after set it'll be there for the mm's
+ * lifecycle. Avoid setting the bit unless necessary, or it might cause write
+ * cache bouncing on large SMP machines for concurrent pinned gups.
+ */
+static inline void mm_set_has_pinned_flag(unsigned long *mm_flags)
+{
+ if (!test_bit(MMF_HAS_PINNED, mm_flags))
+ set_bit(MMF_HAS_PINNED, mm_flags);
+}
+
#ifdef CONFIG_MMU
static struct page *no_page_table(struct vm_area_struct *vma,
unsigned int flags)
}
}
- if (flags & FOLL_SPLIT && PageTransCompound(page)) {
- get_page(page);
- pte_unmap_unlock(ptep, ptl);
- lock_page(page);
- ret = split_huge_page(page);
- unlock_page(page);
- put_page(page);
- if (ret)
- return ERR_PTR(ret);
- goto retry;
- }
-
/* try_grab_page() does nothing unless FOLL_GET or FOLL_PIN is set. */
if (unlikely(!try_grab_page(page, flags))) {
page = ERR_PTR(-ENOMEM);
spin_unlock(ptl);
return follow_page_pte(vma, address, pmd, flags, &ctx->pgmap);
}
- if (flags & (FOLL_SPLIT | FOLL_SPLIT_PMD)) {
+ if (flags & FOLL_SPLIT_PMD) {
int ret;
page = pmd_page(*pmd);
if (is_huge_zero_page(page)) {
split_huge_pmd(vma, pmd, address);
if (pmd_trans_unstable(pmd))
ret = -EBUSY;
- } else if (flags & FOLL_SPLIT) {
- if (unlikely(!try_get_page(page))) {
- spin_unlock(ptl);
- return ERR_PTR(-ENOMEM);
- }
- spin_unlock(ptl);
- lock_page(page);
- ret = split_huge_page(page);
- unlock_page(page);
- put_page(page);
- if (pmd_none(*pmd))
- return no_page_table(vma, flags);
- } else { /* flags & FOLL_SPLIT_PMD */
+ } else {
spin_unlock(ptl);
split_huge_pmd(vma, pmd, address);
ret = pte_alloc(mm, pmd) ? -ENOMEM : 0;
struct follow_page_context ctx = { NULL };
struct page *page;
+ if (vma_is_secretmem(vma))
+ return NULL;
+
page = follow_page_mask(vma, address, foll_flags, &ctx);
if (ctx.pgmap)
put_dev_pagemap(ctx.pgmap);
if ((gup_flags & FOLL_LONGTERM) && vma_is_fsdax(vma))
return -EOPNOTSUPP;
+ if (vma_is_secretmem(vma))
+ return -EFAULT;
+
if (write) {
if (!(vm_flags & VM_WRITE)) {
if (!(gup_flags & FOLL_FORCE))
}
if (flags & FOLL_PIN)
- atomic_set(&mm->has_pinned, 1);
+ mm_set_has_pinned_flag(&mm->flags);
/*
* FOLL_PIN and FOLL_GET are mutually exclusive. Traditional behavior
NULL, NULL, locked);
}
+/*
+ * faultin_vma_page_range() - populate (prefault) page tables inside the
+ * given VMA range readable/writable
+ *
+ * This takes care of mlocking the pages, too, if VM_LOCKED is set.
+ *
+ * @vma: target vma
+ * @start: start address
+ * @end: end address
+ * @write: whether to prefault readable or writable
+ * @locked: whether the mmap_lock is still held
+ *
+ * Returns either number of processed pages in the vma, or a negative error
+ * code on error (see __get_user_pages()).
+ *
+ * vma->vm_mm->mmap_lock must be held. The range must be page-aligned and
+ * covered by the VMA.
+ *
+ * If @locked is NULL, it may be held for read or write and will be unperturbed.
+ *
+ * If @locked is non-NULL, it must held for read only and may be released. If
+ * it's released, *@locked will be set to 0.
+ */
+long faultin_vma_page_range(struct vm_area_struct *vma, unsigned long start,
+ unsigned long end, bool write, int *locked)
+{
+ struct mm_struct *mm = vma->vm_mm;
+ unsigned long nr_pages = (end - start) / PAGE_SIZE;
+ int gup_flags;
+
+ VM_BUG_ON(!PAGE_ALIGNED(start));
+ VM_BUG_ON(!PAGE_ALIGNED(end));
+ VM_BUG_ON_VMA(start < vma->vm_start, vma);
+ VM_BUG_ON_VMA(end > vma->vm_end, vma);
+ mmap_assert_locked(mm);
+
+ /*
+ * FOLL_TOUCH: Mark page accessed and thereby young; will also mark
+ * the page dirty with FOLL_WRITE -- which doesn't make a
+ * difference with !FOLL_FORCE, because the page is writable
+ * in the page table.
+ * FOLL_HWPOISON: Return -EHWPOISON instead of -EFAULT when we hit
+ * a poisoned page.
+ * FOLL_POPULATE: Always populate memory with VM_LOCKONFAULT.
+ * !FOLL_FORCE: Require proper access permissions.
+ */
+ gup_flags = FOLL_TOUCH | FOLL_POPULATE | FOLL_MLOCK | FOLL_HWPOISON;
+ if (write)
+ gup_flags |= FOLL_WRITE;
+
+ /*
+ * See check_vma_flags(): Will return -EFAULT on incompatible mappings
+ * or with insufficient permissions.
+ */
+ return __get_user_pages(mm, start, nr_pages, gup_flags,
+ NULL, NULL, locked);
+}
+
/*
* __mm_populate - populate and/or mlock pages within a range of address space.
*
{
struct vm_area_struct *vma;
unsigned long vm_flags;
- int i;
+ long i;
/* calculate required read or write permissions.
* If FOLL_FORCE is set, we only require the "MAY" flags.
* Returns NULL on any kind of failure - a hole must then be inserted into
* the corefile, to preserve alignment with its headers; and also returns
* NULL wherever the ZERO_PAGE, or an anonymous pte_none, has been found -
- * allowing a hole to be left in the corefile to save diskspace.
+ * allowing a hole to be left in the corefile to save disk space.
*
* Called without mmap_lock (takes and releases the mmap_lock by itself).
*/
FOLL_FORCE | FOLL_DUMP | FOLL_GET);
if (locked)
mmap_read_unlock(mm);
-
- if (ret == 1 && is_page_poisoned(page))
- return NULL;
-
return (ret == 1) ? page : NULL;
}
#endif /* CONFIG_ELF_CORE */
-#ifdef CONFIG_CMA
-static long check_and_migrate_cma_pages(struct mm_struct *mm,
- unsigned long start,
- unsigned long nr_pages,
- struct page **pages,
- struct vm_area_struct **vmas,
- unsigned int gup_flags)
+#ifdef CONFIG_MIGRATION
+/*
+ * Check whether all pages are pinnable, if so return number of pages. If some
+ * pages are not pinnable, migrate them, and unpin all pages. Return zero if
+ * pages were migrated, or if some pages were not successfully isolated.
+ * Return negative error if migration fails.
+ */
+static long check_and_migrate_movable_pages(unsigned long nr_pages,
+ struct page **pages,
+ unsigned int gup_flags)
{
unsigned long i;
- unsigned long step;
+ unsigned long isolation_error_count = 0;
bool drain_allow = true;
- bool migrate_allow = true;
- LIST_HEAD(cma_page_list);
- long ret = nr_pages;
+ LIST_HEAD(movable_page_list);
+ long ret = 0;
+ struct page *prev_head = NULL;
+ struct page *head;
struct migration_target_control mtc = {
.nid = NUMA_NO_NODE,
- .gfp_mask = GFP_USER | __GFP_MOVABLE | __GFP_NOWARN,
+ .gfp_mask = GFP_USER | __GFP_NOWARN,
};
-check_again:
- for (i = 0; i < nr_pages;) {
-
- struct page *head = compound_head(pages[i]);
-
- /*
- * gup may start from a tail page. Advance step by the left
- * part.
- */
- step = compound_nr(head) - (pages[i] - head);
+ for (i = 0; i < nr_pages; i++) {
+ head = compound_head(pages[i]);
+ if (head == prev_head)
+ continue;
+ prev_head = head;
/*
- * If we get a page from the CMA zone, since we are going to
- * be pinning these entries, we might as well move them out
- * of the CMA zone if possible.
+ * If we get a movable page, since we are going to be pinning
+ * these entries, try to move them out if possible.
*/
- if (is_migrate_cma_page(head)) {
- if (PageHuge(head))
- isolate_huge_page(head, &cma_page_list);
- else {
+ if (!is_pinnable_page(head)) {
+ if (PageHuge(head)) {
+ if (!isolate_huge_page(head, &movable_page_list))
+ isolation_error_count++;
+ } else {
if (!PageLRU(head) && drain_allow) {
lru_add_drain_all();
drain_allow = false;
}
- if (!isolate_lru_page(head)) {
- list_add_tail(&head->lru, &cma_page_list);
- mod_node_page_state(page_pgdat(head),
- NR_ISOLATED_ANON +
- page_is_file_lru(head),
- thp_nr_pages(head));
+ if (isolate_lru_page(head)) {
+ isolation_error_count++;
+ continue;
}
+ list_add_tail(&head->lru, &movable_page_list);
+ mod_node_page_state(page_pgdat(head),
+ NR_ISOLATED_ANON +
+ page_is_file_lru(head),
+ thp_nr_pages(head));
}
}
-
- i += step;
}
- if (!list_empty(&cma_page_list)) {
- /*
- * drop the above get_user_pages reference.
- */
- if (gup_flags & FOLL_PIN)
- unpin_user_pages(pages, nr_pages);
- else
- for (i = 0; i < nr_pages; i++)
- put_page(pages[i]);
-
- if (migrate_pages(&cma_page_list, alloc_migration_target, NULL,
- (unsigned long)&mtc, MIGRATE_SYNC, MR_CONTIG_RANGE)) {
- /*
- * some of the pages failed migration. Do get_user_pages
- * without migration.
- */
- migrate_allow = false;
+ /*
+ * If list is empty, and no isolation errors, means that all pages are
+ * in the correct zone.
+ */
+ if (list_empty(&movable_page_list) && !isolation_error_count)
+ return nr_pages;
- if (!list_empty(&cma_page_list))
- putback_movable_pages(&cma_page_list);
- }
- /*
- * We did migrate all the pages, Try to get the page references
- * again migrating any new CMA pages which we failed to isolate
- * earlier.
- */
- ret = __get_user_pages_locked(mm, start, nr_pages,
- pages, vmas, NULL,
- gup_flags);
-
- if ((ret > 0) && migrate_allow) {
- nr_pages = ret;
- drain_allow = true;
- goto check_again;
- }
+ if (gup_flags & FOLL_PIN) {
+ unpin_user_pages(pages, nr_pages);
+ } else {
+ for (i = 0; i < nr_pages; i++)
+ put_page(pages[i]);
+ }
+ if (!list_empty(&movable_page_list)) {
+ ret = migrate_pages(&movable_page_list, alloc_migration_target,
+ NULL, (unsigned long)&mtc, MIGRATE_SYNC,
+ MR_LONGTERM_PIN);
+ if (ret && !list_empty(&movable_page_list))
+ putback_movable_pages(&movable_page_list);
}
- return ret;
+ return ret > 0 ? -ENOMEM : ret;
}
#else
-static long check_and_migrate_cma_pages(struct mm_struct *mm,
- unsigned long start,
- unsigned long nr_pages,
- struct page **pages,
- struct vm_area_struct **vmas,
- unsigned int gup_flags)
+static long check_and_migrate_movable_pages(unsigned long nr_pages,
+ struct page **pages,
+ unsigned int gup_flags)
{
return nr_pages;
}
-#endif /* CONFIG_CMA */
+#endif /* CONFIG_MIGRATION */
/*
* __gup_longterm_locked() is a wrapper for __get_user_pages_locked which
struct vm_area_struct **vmas,
unsigned int gup_flags)
{
- unsigned long flags = 0;
+ unsigned int flags;
long rc;
- if (gup_flags & FOLL_LONGTERM)
- flags = memalloc_nocma_save();
-
- rc = __get_user_pages_locked(mm, start, nr_pages, pages, vmas, NULL,
- gup_flags);
+ if (!(gup_flags & FOLL_LONGTERM))
+ return __get_user_pages_locked(mm, start, nr_pages, pages, vmas,
+ NULL, gup_flags);
+ flags = memalloc_pin_save();
+ do {
+ rc = __get_user_pages_locked(mm, start, nr_pages, pages, vmas,
+ NULL, gup_flags);
+ if (rc <= 0)
+ break;
+ rc = check_and_migrate_movable_pages(rc, pages, gup_flags);
+ } while (!rc);
+ memalloc_pin_restore(flags);
- if (gup_flags & FOLL_LONGTERM) {
- if (rc > 0)
- rc = check_and_migrate_cma_pages(mm, start, rc, pages,
- vmas, gup_flags);
- memalloc_nocma_restore(flags);
- }
return rc;
}
if (!head)
goto pte_unmap;
+ if (unlikely(page_is_secretmem(page))) {
+ put_compound_head(head, 1, flags);
+ goto pte_unmap;
+ }
+
if (unlikely(pte_val(pte) != pte_val(*ptep))) {
put_compound_head(head, 1, flags);
goto pte_unmap;
return -EINVAL;
if (gup_flags & FOLL_PIN)
- atomic_set(¤t->mm->has_pinned, 1);
+ mm_set_has_pinned_flag(¤t->mm->flags);
if (!(gup_flags & FOLL_FAST_ONLY))
might_lock_read(¤t->mm->mmap_lock);