aboutsummaryrefslogtreecommitdiffstatshomepage
path: root/mm/huge_memory.c
diff options
context:
space:
mode:
Diffstat (limited to 'mm/huge_memory.c')
-rw-r--r--mm/huge_memory.c98
1 files changed, 61 insertions, 37 deletions
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 25ef59b7ee34..622cced74fd9 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -629,21 +629,40 @@ release:
* available
* never: never stall for any thp allocation
*/
-static inline gfp_t alloc_hugepage_direct_gfpmask(struct vm_area_struct *vma)
+static inline gfp_t alloc_hugepage_direct_gfpmask(struct vm_area_struct *vma, unsigned long addr)
{
const bool vma_madvised = !!(vma->vm_flags & VM_HUGEPAGE);
+ gfp_t this_node = 0;
+
+#ifdef CONFIG_NUMA
+ struct mempolicy *pol;
+ /*
+ * __GFP_THISNODE is used only when __GFP_DIRECT_RECLAIM is not
+ * specified, to express a general desire to stay on the current
+ * node for optimistic allocation attempts. If the defrag mode
+ * and/or madvise hint requires the direct reclaim then we prefer
+ * to fallback to other node rather than node reclaim because that
+ * can lead to excessive reclaim even though there is free memory
+ * on other nodes. We expect that NUMA preferences are specified
+ * by memory policies.
+ */
+ pol = get_vma_policy(vma, addr);
+ if (pol->mode != MPOL_BIND)
+ this_node = __GFP_THISNODE;
+ mpol_cond_put(pol);
+#endif
if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags))
return GFP_TRANSHUGE | (vma_madvised ? 0 : __GFP_NORETRY);
if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags))
- return GFP_TRANSHUGE_LIGHT | __GFP_KSWAPD_RECLAIM;
+ return GFP_TRANSHUGE_LIGHT | __GFP_KSWAPD_RECLAIM | this_node;
if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags))
return GFP_TRANSHUGE_LIGHT | (vma_madvised ? __GFP_DIRECT_RECLAIM :
- __GFP_KSWAPD_RECLAIM);
+ __GFP_KSWAPD_RECLAIM | this_node);
if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags))
return GFP_TRANSHUGE_LIGHT | (vma_madvised ? __GFP_DIRECT_RECLAIM :
- 0);
- return GFP_TRANSHUGE_LIGHT;
+ this_node);
+ return GFP_TRANSHUGE_LIGHT | this_node;
}
/* Caller must hold page table lock. */
@@ -715,8 +734,8 @@ vm_fault_t do_huge_pmd_anonymous_page(struct vm_fault *vmf)
pte_free(vma->vm_mm, pgtable);
return ret;
}
- gfp = alloc_hugepage_direct_gfpmask(vma);
- page = alloc_hugepage_vma(gfp, vma, haddr, HPAGE_PMD_ORDER);
+ gfp = alloc_hugepage_direct_gfpmask(vma, haddr);
+ page = alloc_pages_vma(gfp, HPAGE_PMD_ORDER, vma, haddr, numa_node_id());
if (unlikely(!page)) {
count_vm_event(THP_FAULT_FALLBACK);
return VM_FAULT_FALLBACK;
@@ -1286,8 +1305,9 @@ vm_fault_t do_huge_pmd_wp_page(struct vm_fault *vmf, pmd_t orig_pmd)
alloc:
if (transparent_hugepage_enabled(vma) &&
!transparent_hugepage_debug_cow()) {
- huge_gfp = alloc_hugepage_direct_gfpmask(vma);
- new_page = alloc_hugepage_vma(huge_gfp, vma, haddr, HPAGE_PMD_ORDER);
+ huge_gfp = alloc_hugepage_direct_gfpmask(vma, haddr);
+ new_page = alloc_pages_vma(huge_gfp, HPAGE_PMD_ORDER, vma,
+ haddr, numa_node_id());
} else
new_page = NULL;
@@ -2330,7 +2350,7 @@ void vma_adjust_trans_huge(struct vm_area_struct *vma,
}
}
-static void freeze_page(struct page *page)
+static void unmap_page(struct page *page)
{
enum ttu_flags ttu_flags = TTU_IGNORE_MLOCK | TTU_IGNORE_ACCESS |
TTU_RMAP_LOCKED | TTU_SPLIT_HUGE_PMD;
@@ -2345,7 +2365,7 @@ static void freeze_page(struct page *page)
VM_BUG_ON_PAGE(!unmap_success, page);
}
-static void unfreeze_page(struct page *page)
+static void remap_page(struct page *page)
{
int i;
if (PageTransHuge(page)) {
@@ -2382,6 +2402,12 @@ static void __split_huge_page_tail(struct page *head, int tail,
(1L << PG_unevictable) |
(1L << PG_dirty)));
+ /* ->mapping in first tail page is compound_mapcount */
+ VM_BUG_ON_PAGE(tail > 2 && page_tail->mapping != TAIL_MAPPING,
+ page_tail);
+ page_tail->mapping = head->mapping;
+ page_tail->index = head->index + tail;
+
/* Page flags must be visible before we make the page non-compound. */
smp_wmb();
@@ -2402,12 +2428,6 @@ static void __split_huge_page_tail(struct page *head, int tail,
if (page_is_idle(head))
set_page_idle(page_tail);
- /* ->mapping in first tail page is compound_mapcount */
- VM_BUG_ON_PAGE(tail > 2 && page_tail->mapping != TAIL_MAPPING,
- page_tail);
- page_tail->mapping = head->mapping;
-
- page_tail->index = head->index + tail;
page_cpupid_xchg_last(page_tail, page_cpupid_last(head));
/*
@@ -2419,12 +2439,11 @@ static void __split_huge_page_tail(struct page *head, int tail,
}
static void __split_huge_page(struct page *page, struct list_head *list,
- unsigned long flags)
+ pgoff_t end, unsigned long flags)
{
struct page *head = compound_head(page);
struct zone *zone = page_zone(head);
struct lruvec *lruvec;
- pgoff_t end = -1;
int i;
lruvec = mem_cgroup_page_lruvec(head, zone->zone_pgdat);
@@ -2432,9 +2451,6 @@ static void __split_huge_page(struct page *page, struct list_head *list,
/* complete memcg works before add pages to LRU */
mem_cgroup_split_huge_fixup(head);
- if (!PageAnon(page))
- end = DIV_ROUND_UP(i_size_read(head->mapping->host), PAGE_SIZE);
-
for (i = HPAGE_PMD_NR - 1; i >= 1; i--) {
__split_huge_page_tail(head, i, lruvec, list);
/* Some pages can be beyond i_size: drop them from page cache */
@@ -2450,20 +2466,20 @@ static void __split_huge_page(struct page *page, struct list_head *list,
ClearPageCompound(head);
/* See comment in __split_huge_page_tail() */
if (PageAnon(head)) {
- /* Additional pin to radix tree of swap cache */
+ /* Additional pin to swap cache */
if (PageSwapCache(head))
page_ref_add(head, 2);
else
page_ref_inc(head);
} else {
- /* Additional pin to radix tree */
+ /* Additional pin to page cache */
page_ref_add(head, 2);
xa_unlock(&head->mapping->i_pages);
}
spin_unlock_irqrestore(zone_lru_lock(page_zone(head)), flags);
- unfreeze_page(head);
+ remap_page(head);
for (i = 0; i < HPAGE_PMD_NR; i++) {
struct page *subpage = head + i;
@@ -2568,7 +2584,7 @@ bool can_split_huge_page(struct page *page, int *pextra_pins)
{
int extra_pins;
- /* Additional pins from radix tree */
+ /* Additional pins from page cache */
if (PageAnon(page))
extra_pins = PageSwapCache(page) ? HPAGE_PMD_NR : 0;
else
@@ -2606,6 +2622,7 @@ int split_huge_page_to_list(struct page *page, struct list_head *list)
int count, mapcount, extra_pins, ret;
bool mlocked;
unsigned long flags;
+ pgoff_t end;
VM_BUG_ON_PAGE(is_huge_zero_page(page), page);
VM_BUG_ON_PAGE(!PageLocked(page), page);
@@ -2628,6 +2645,7 @@ int split_huge_page_to_list(struct page *page, struct list_head *list)
ret = -EBUSY;
goto out;
}
+ end = -1;
mapping = NULL;
anon_vma_lock_write(anon_vma);
} else {
@@ -2641,10 +2659,19 @@ int split_huge_page_to_list(struct page *page, struct list_head *list)
anon_vma = NULL;
i_mmap_lock_read(mapping);
+
+ /*
+ *__split_huge_page() may need to trim off pages beyond EOF:
+ * but on 32-bit, i_size_read() takes an irq-unsafe seqlock,
+ * which cannot be nested inside the page tree lock. So note
+ * end now: i_size itself may be changed at any moment, but
+ * head page lock is good enough to serialize the trimming.
+ */
+ end = DIV_ROUND_UP(i_size_read(mapping->host), PAGE_SIZE);
}
/*
- * Racy check if we can split the page, before freeze_page() will
+ * Racy check if we can split the page, before unmap_page() will
* split PMDs
*/
if (!can_split_huge_page(head, &extra_pins)) {
@@ -2653,7 +2680,7 @@ int split_huge_page_to_list(struct page *page, struct list_head *list)
}
mlocked = PageMlocked(page);
- freeze_page(head);
+ unmap_page(head);
VM_BUG_ON_PAGE(compound_mapcount(head), head);
/* Make sure the page is not on per-CPU pagevec as it takes pin */
@@ -2664,17 +2691,14 @@ int split_huge_page_to_list(struct page *page, struct list_head *list)
spin_lock_irqsave(zone_lru_lock(page_zone(head)), flags);
if (mapping) {
- void **pslot;
+ XA_STATE(xas, &mapping->i_pages, page_index(head));
- xa_lock(&mapping->i_pages);
- pslot = radix_tree_lookup_slot(&mapping->i_pages,
- page_index(head));
/*
- * Check if the head page is present in radix tree.
+ * Check if the head page is present in page cache.
* We assume all tail are present too, if head is there.
*/
- if (radix_tree_deref_slot_protected(pslot,
- &mapping->i_pages.xa_lock) != head)
+ xa_lock(&mapping->i_pages);
+ if (xas_load(&xas) != head)
goto fail;
}
@@ -2690,7 +2714,7 @@ int split_huge_page_to_list(struct page *page, struct list_head *list)
if (mapping)
__dec_node_page_state(page, NR_SHMEM_THPS);
spin_unlock(&pgdata->split_queue_lock);
- __split_huge_page(page, list, flags);
+ __split_huge_page(page, list, end, flags);
if (PageSwapCache(head)) {
swp_entry_t entry = { .val = page_private(head) };
@@ -2710,7 +2734,7 @@ int split_huge_page_to_list(struct page *page, struct list_head *list)
fail: if (mapping)
xa_unlock(&mapping->i_pages);
spin_unlock_irqrestore(zone_lru_lock(page_zone(head)), flags);
- unfreeze_page(head);
+ remap_page(head);
ret = -EBUSY;
}
Copyright © 1996 – 2023 Jason A. Donenfeld. All Rights Reverse Engineered.