* + mm-thp-split-huge-page-to-any-lower-order-pages.patch added to mm-unstable branch
@ 2023-04-04 21:45 Andrew Morton
0 siblings, 0 replies; 2+ messages in thread
From: Andrew Morton @ 2023-04-04 21:45 UTC (permalink / raw)
To: mm-commits, zokeefe, yuzhao, willy, shy828301, ryan.roberts,
roman.gushchin, mkoutny, kirill.shutemov, ziy, akpm
[-- Warning: decoded text below may be mangled, UTF-8 assumed --]
[-- Attachment #1: Type: text/plain, Size: 12734 bytes --]
The patch titled
Subject: mm: thp: split huge page to any lower order pages
has been added to the -mm mm-unstable branch. Its filename is
mm-thp-split-huge-page-to-any-lower-order-pages.patch
This patch will shortly appear at
https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patches/mm-thp-split-huge-page-to-any-lower-order-pages.patch
This patch will later appear in the mm-unstable branch at
git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/process/submit-checklist.rst when testing your code ***
The -mm tree is included into linux-next via the mm-everything
branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
and is updated there every 2-3 working days
------------------------------------------------------
From: Zi Yan <ziy@nvidia.com>
Subject: mm: thp: split huge page to any lower order pages
Date: Mon, 3 Apr 2023 16:18:37 -0400
To split a THP to any lower order pages, we need to reform THPs on
subpages at given order and add page refcount based on the new page order.
Also we need to reinitialize page_deferred_list after removing the page
from the split_queue, otherwise a subsequent split will see list
corruption when checking the page_deferred_list again.
It has many uses, like minimizing the number of pages after truncating a
huge pagecache page. For anonymous THPs, we can only split them to
order-0 like before until we add support for any size anonymous THPs.
Link: https://lkml.kernel.org/r/20230403201839.4097845-6-zi.yan@sent.com
Signed-off-by: Zi Yan <ziy@nvidia.com>
Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Michal Koutný <mkoutny@suse.com>
Cc: Roman Gushchin <roman.gushchin@linux.dev>
Cc: Ryan Roberts <ryan.roberts@arm.com>
Cc: Yang Shi <shy828301@gmail.com>
Cc: Yu Zhao <yuzhao@google.com>
Cc: Zach O'Keefe <zokeefe@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
include/linux/huge_mm.h | 10 ++-
mm/huge_memory.c | 102 +++++++++++++++++++++++++++-----------
2 files changed, 81 insertions(+), 31 deletions(-)
--- a/include/linux/huge_mm.h~mm-thp-split-huge-page-to-any-lower-order-pages
+++ a/include/linux/huge_mm.h
@@ -147,10 +147,11 @@ void prep_transhuge_page(struct page *pa
void free_transhuge_page(struct page *page);
bool can_split_folio(struct folio *folio, int *pextra_pins);
-int split_huge_page_to_list(struct page *page, struct list_head *list);
+int split_huge_page_to_list_to_order(struct page *page, struct list_head *list,
+ unsigned int new_order);
static inline int split_huge_page(struct page *page)
{
- return split_huge_page_to_list(page, NULL);
+ return split_huge_page_to_list_to_order(page, NULL, 0);
}
void deferred_split_folio(struct folio *folio);
@@ -297,7 +298,8 @@ can_split_folio(struct folio *folio, int
return false;
}
static inline int
-split_huge_page_to_list(struct page *page, struct list_head *list)
+split_huge_page_to_list_to_order(struct page *page, struct list_head *list,
+ unsigned int new_order)
{
return 0;
}
@@ -397,7 +399,7 @@ static inline bool thp_migration_support
static inline int split_folio_to_list(struct folio *folio,
struct list_head *list)
{
- return split_huge_page_to_list(&folio->page, list);
+ return split_huge_page_to_list_to_order(&folio->page, list, 0);
}
static inline int split_folio(struct folio *folio)
--- a/mm/huge_memory.c~mm-thp-split-huge-page-to-any-lower-order-pages
+++ a/mm/huge_memory.c
@@ -2359,11 +2359,13 @@ void vma_adjust_trans_huge(struct vm_are
static void unmap_folio(struct folio *folio)
{
- enum ttu_flags ttu_flags = TTU_RMAP_LOCKED | TTU_SPLIT_HUGE_PMD |
- TTU_SYNC;
+ enum ttu_flags ttu_flags = TTU_RMAP_LOCKED | TTU_SYNC;
VM_BUG_ON_FOLIO(!folio_test_large(folio), folio);
+ if (folio_test_pmd_mappable(folio))
+ ttu_flags |= TTU_SPLIT_HUGE_PMD;
+
/*
* Anon pages need migration entries to preserve them, but file
* pages can simply be left unmapped, then faulted back on demand.
@@ -2395,7 +2397,6 @@ static void lru_add_page_tail(struct pag
struct lruvec *lruvec, struct list_head *list)
{
VM_BUG_ON_PAGE(!PageHead(head), head);
- VM_BUG_ON_PAGE(PageCompound(tail), head);
VM_BUG_ON_PAGE(PageLRU(tail), head);
lockdep_assert_held(&lruvec->lru_lock);
@@ -2416,7 +2417,7 @@ static void lru_add_page_tail(struct pag
}
static void __split_huge_page_tail(struct page *head, int tail,
- struct lruvec *lruvec, struct list_head *list)
+ struct lruvec *lruvec, struct list_head *list, unsigned int new_order)
{
struct page *page_tail = head + tail;
@@ -2483,10 +2484,15 @@ static void __split_huge_page_tail(struc
* which needs correct compound_head().
*/
clear_compound_head(page_tail);
+ if (new_order) {
+ prep_compound_page(page_tail, new_order);
+ prep_transhuge_page(page_tail);
+ }
/* Finally unfreeze refcount. Additional reference from page cache. */
- page_ref_unfreeze(page_tail, 1 + (!PageAnon(head) ||
- PageSwapCache(head)));
+ page_ref_unfreeze(page_tail, 1 + ((!PageAnon(head) ||
+ PageSwapCache(head)) ?
+ thp_nr_pages(page_tail) : 0));
if (page_is_young(head))
set_page_young(page_tail);
@@ -2504,7 +2510,7 @@ static void __split_huge_page_tail(struc
}
static void __split_huge_page(struct page *page, struct list_head *list,
- pgoff_t end)
+ pgoff_t end, unsigned int new_order)
{
struct folio *folio = page_folio(page);
struct page *head = &folio->page;
@@ -2512,11 +2518,12 @@ static void __split_huge_page(struct pag
struct address_space *swap_cache = NULL;
unsigned long offset = 0;
unsigned int nr = thp_nr_pages(head);
+ unsigned int new_nr = 1 << new_order;
int order = folio_order(folio);
int i;
/* complete memcg works before add pages to LRU */
- split_page_memcg(head, order, 0);
+ split_page_memcg(head, order, new_order);
if (PageAnon(head) && PageSwapCache(head)) {
swp_entry_t entry = { .val = page_private(head) };
@@ -2531,14 +2538,14 @@ static void __split_huge_page(struct pag
ClearPageHasHWPoisoned(head);
- for (i = nr - 1; i >= 1; i--) {
- __split_huge_page_tail(head, i, lruvec, list);
+ for (i = nr - new_nr; i >= new_nr; i -= new_nr) {
+ __split_huge_page_tail(head, i, lruvec, list, new_order);
/* Some pages can be beyond EOF: drop them from page cache */
if (head[i].index >= end) {
struct folio *tail = page_folio(head + i);
if (shmem_mapping(head->mapping))
- shmem_uncharge(head->mapping->host, 1);
+ shmem_uncharge(head->mapping->host, new_nr);
else if (folio_test_clear_dirty(tail))
folio_account_cleaned(tail,
inode_to_wb(folio->mapping->host));
@@ -2548,29 +2555,38 @@ static void __split_huge_page(struct pag
__xa_store(&head->mapping->i_pages, head[i].index,
head + i, 0);
} else if (swap_cache) {
+ /*
+ * split anonymous THPs (including swapped out ones) to
+ * non-zero order not supported
+ */
+ VM_WARN_ONCE(new_order,
+ "Split swap-cached anon folio to non-0 order not supported");
__xa_store(&swap_cache->i_pages, offset + i,
head + i, 0);
}
}
- ClearPageCompound(head);
+ if (!new_order)
+ ClearPageCompound(head);
+ else
+ set_compound_order(head, new_order);
unlock_page_lruvec(lruvec);
/* Caller disabled irqs, so they are still disabled here */
- split_page_owner(head, order, 0);
+ split_page_owner(head, order, new_order);
/* See comment in __split_huge_page_tail() */
if (PageAnon(head)) {
/* Additional pin to swap cache */
if (PageSwapCache(head)) {
- page_ref_add(head, 2);
+ page_ref_add(head, 1 + new_nr);
xa_unlock(&swap_cache->i_pages);
} else {
page_ref_inc(head);
}
} else {
/* Additional pin to page cache */
- page_ref_add(head, 2);
+ page_ref_add(head, 1 + new_nr);
xa_unlock(&head->mapping->i_pages);
}
local_irq_enable();
@@ -2583,7 +2599,15 @@ static void __split_huge_page(struct pag
split_swap_cluster(entry);
}
- for (i = 0; i < nr; i++) {
+ /*
+ * set page to its compound_head when split to non order-0 pages, so
+ * we can skip unlocking it below, since PG_locked is transferred to
+ * the compound_head of the page and the caller will unlock it.
+ */
+ if (new_order)
+ page = compound_head(page);
+
+ for (i = 0; i < nr; i += new_nr) {
struct page *subpage = head + i;
if (subpage == page)
continue;
@@ -2617,29 +2641,31 @@ bool can_split_folio(struct folio *folio
}
/*
- * This function splits huge page into normal pages. @page can point to any
- * subpage of huge page to split. Split doesn't change the position of @page.
+ * This function splits huge page into pages in @new_order. @page can point to
+ * any subpage of huge page to split. Split doesn't change the position of
+ * @page.
*
* Only caller must hold pin on the @page, otherwise split fails with -EBUSY.
* The huge page must be locked.
*
* If @list is null, tail pages will be added to LRU list, otherwise, to @list.
*
- * Both head page and tail pages will inherit mapping, flags, and so on from
- * the hugepage.
+ * Pages in new_order will inherit mapping, flags, and so on from the hugepage.
*
- * GUP pin and PG_locked transferred to @page. Rest subpages can be freed if
- * they are not mapped.
+ * GUP pin and PG_locked transferred to @page or the compound page @page belongs
+ * to. Rest subpages can be freed if they are not mapped.
*
* Returns 0 if the hugepage is split successfully.
* Returns -EBUSY if the page is pinned or if anon_vma disappeared from under
* us.
*/
-int split_huge_page_to_list(struct page *page, struct list_head *list)
+int split_huge_page_to_list_to_order(struct page *page, struct list_head *list,
+ unsigned int new_order)
{
struct folio *folio = page_folio(page);
struct deferred_split *ds_queue = get_deferred_split_queue(folio);
- XA_STATE(xas, &folio->mapping->i_pages, folio->index);
+ /* reset xarray order to new order after split */
+ XA_STATE_ORDER(xas, &folio->mapping->i_pages, folio->index, new_order);
struct anon_vma *anon_vma = NULL;
struct address_space *mapping = NULL;
int extra_pins, ret;
@@ -2649,6 +2675,18 @@ int split_huge_page_to_list(struct page
VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio);
VM_BUG_ON_FOLIO(!folio_test_large(folio), folio);
+ /* Cannot split THP to order-1 (no order-1 THPs) */
+ if (new_order == 1) {
+ VM_WARN_ONCE(1, "Cannot split to order-1 folio");
+ return -EINVAL;
+ }
+
+ /* Split anonymous folio to non-zero order not support */
+ if (folio_test_anon(folio) && new_order) {
+ VM_WARN_ONCE(1, "Split anon folio to non-0 order not support");
+ return -EINVAL;
+ }
+
is_hzp = is_huge_zero_page(&folio->page);
VM_WARN_ON_ONCE_FOLIO(is_hzp, folio);
if (is_hzp)
@@ -2744,7 +2782,13 @@ int split_huge_page_to_list(struct page
if (folio_ref_freeze(folio, 1 + extra_pins)) {
if (!list_empty(&folio->_deferred_list)) {
ds_queue->split_queue_len--;
- list_del(&folio->_deferred_list);
+ /*
+ * Reinitialize page_deferred_list after removing the
+ * page from the split_queue, otherwise a subsequent
+ * split will see list corruption when checking the
+ * page_deferred_list.
+ */
+ list_del_init(&folio->_deferred_list);
}
spin_unlock(&ds_queue->split_queue_lock);
if (mapping) {
@@ -2754,14 +2798,18 @@ int split_huge_page_to_list(struct page
if (folio_test_swapbacked(folio)) {
__lruvec_stat_mod_folio(folio, NR_SHMEM_THPS,
-nr);
- } else {
+ } else if (!new_order) {
+ /*
+ * Decrease THP stats only if split to normal
+ * pages
+ */
__lruvec_stat_mod_folio(folio, NR_FILE_THPS,
-nr);
filemap_nr_thps_dec(mapping);
}
}
- __split_huge_page(page, list, end);
+ __split_huge_page(page, list, end, new_order);
ret = 0;
} else {
spin_unlock(&ds_queue->split_queue_lock);
_
Patches currently in -mm which might be from ziy@nvidia.com are
mm-memcg-use-order-instead-of-nr-in-split_page_memcg.patch
mm-page_owner-use-order-instead-of-nr-in-split_page_owner.patch
mm-memcg-make-memcg-huge-page-split-support-any-order-split.patch
mm-page_owner-add-support-for-splitting-to-any-order-in-split-page_owner.patch
mm-thp-split-huge-page-to-any-lower-order-pages.patch
mm-truncate-split-huge-page-cache-page-to-a-non-zero-order-if-possible.patch
mm-huge_memory-enable-debugfs-to-split-huge-pages-to-any-order.patch
^ permalink raw reply [flat|nested] 2+ messages in thread* + mm-thp-split-huge-page-to-any-lower-order-pages.patch added to mm-unstable branch
@ 2024-02-26 22:25 Andrew Morton
0 siblings, 0 replies; 2+ messages in thread
From: Andrew Morton @ 2024-02-26 22:25 UTC (permalink / raw)
To: mm-commits, zokeefe, yuzhao, willy, shy828301, ryan.roberts,
roman.gushchin, mkoutny, mcgrof, kirill.shutemov, hughd, david,
ziy, akpm
The patch titled
Subject: mm: thp: split huge page to any lower order pages
has been added to the -mm mm-unstable branch. Its filename is
mm-thp-split-huge-page-to-any-lower-order-pages.patch
This patch will shortly appear at
https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patches/mm-thp-split-huge-page-to-any-lower-order-pages.patch
This patch will later appear in the mm-unstable branch at
git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/process/submit-checklist.rst when testing your code ***
The -mm tree is included into linux-next via the mm-everything
branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
and is updated there every 2-3 working days
------------------------------------------------------
From: Zi Yan <ziy@nvidia.com>
Subject: mm: thp: split huge page to any lower order pages
Date: Mon, 26 Feb 2024 15:55:33 -0500
To split a THP to any lower order pages, we need to reform THPs on
subpages at given order and add page refcount based on the new page order.
Also we need to reinitialize page_deferred_list after removing the page
from the split_queue, otherwise a subsequent split will see list
corruption when checking the page_deferred_list again.
Note: Anonymous order-1 folio is not supported because _deferred_list,
which is used by partially mapped folios, is stored in subpage 2 and an
order-1 folio only has subpage 0 and 1. File-backed order-1 folios are
fine, since they do not use _deferred_list.
Link: https://lkml.kernel.org/r/20240226205534.1603748-8-zi.yan@sent.com
Signed-off-by: Zi Yan <ziy@nvidia.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Luis Chamberlain <mcgrof@kernel.org>
Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Cc: Michal Koutny <mkoutny@suse.com>
Cc: Roman Gushchin <roman.gushchin@linux.dev>
Cc: Ryan Roberts <ryan.roberts@arm.com>
Cc: Yang Shi <shy828301@gmail.com>
Cc: Yu Zhao <yuzhao@google.com>
Cc: Zach O'Keefe <zokeefe@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
include/linux/huge_mm.h | 21 ++++---
mm/huge_memory.c | 110 +++++++++++++++++++++++++++++---------
2 files changed, 99 insertions(+), 32 deletions(-)
--- a/include/linux/huge_mm.h~mm-thp-split-huge-page-to-any-lower-order-pages
+++ a/include/linux/huge_mm.h
@@ -265,10 +265,11 @@ unsigned long thp_get_unmapped_area(stru
void folio_prep_large_rmappable(struct folio *folio);
bool can_split_folio(struct folio *folio, int *pextra_pins);
-int split_huge_page_to_list(struct page *page, struct list_head *list);
+int split_huge_page_to_list_to_order(struct page *page, struct list_head *list,
+ unsigned int new_order);
static inline int split_huge_page(struct page *page)
{
- return split_huge_page_to_list(page, NULL);
+ return split_huge_page_to_list_to_order(page, NULL, 0);
}
void deferred_split_folio(struct folio *folio);
@@ -422,7 +423,8 @@ can_split_folio(struct folio *folio, int
return false;
}
static inline int
-split_huge_page_to_list(struct page *page, struct list_head *list)
+split_huge_page_to_list_to_order(struct page *page, struct list_head *list,
+ unsigned int new_order)
{
return 0;
}
@@ -519,17 +521,20 @@ static inline bool thp_migration_support
}
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
-static inline int split_folio_to_list(struct folio *folio,
- struct list_head *list)
+static inline int split_folio_to_list_to_order(struct folio *folio,
+ struct list_head *list, int new_order)
{
- return split_huge_page_to_list(&folio->page, list);
+ return split_huge_page_to_list_to_order(&folio->page, list, new_order);
}
-static inline int split_folio(struct folio *folio)
+static inline int split_folio_to_order(struct folio *folio, int new_order)
{
- return split_folio_to_list(folio, NULL);
+ return split_folio_to_list_to_order(folio, NULL, new_order);
}
+#define split_folio_to_list(f, l) split_folio_to_list_to_order(f, l, 0)
+#define split_folio(f) split_folio_to_order(f, 0)
+
/*
* archs that select ARCH_WANTS_THP_SWAP but don't support THP_SWP due to
* limitations in the implementation like arm64 MTE can override this to
--- a/mm/huge_memory.c~mm-thp-split-huge-page-to-any-lower-order-pages
+++ a/mm/huge_memory.c
@@ -2770,7 +2770,6 @@ static void lru_add_page_tail(struct pag
struct lruvec *lruvec, struct list_head *list)
{
VM_BUG_ON_PAGE(!PageHead(head), head);
- VM_BUG_ON_PAGE(PageCompound(tail), head);
VM_BUG_ON_PAGE(PageLRU(tail), head);
lockdep_assert_held(&lruvec->lru_lock);
@@ -2791,7 +2790,8 @@ static void lru_add_page_tail(struct pag
}
static void __split_huge_page_tail(struct folio *folio, int tail,
- struct lruvec *lruvec, struct list_head *list)
+ struct lruvec *lruvec, struct list_head *list,
+ unsigned int new_order)
{
struct page *head = &folio->page;
struct page *page_tail = head + tail;
@@ -2861,10 +2861,15 @@ static void __split_huge_page_tail(struc
* which needs correct compound_head().
*/
clear_compound_head(page_tail);
+ if (new_order) {
+ prep_compound_page(page_tail, new_order);
+ folio_prep_large_rmappable(new_folio);
+ }
/* Finally unfreeze refcount. Additional reference from page cache. */
- page_ref_unfreeze(page_tail, 1 + (!folio_test_anon(folio) ||
- folio_test_swapcache(folio)));
+ page_ref_unfreeze(page_tail,
+ 1 + ((!folio_test_anon(folio) || folio_test_swapcache(folio)) ?
+ folio_nr_pages(new_folio) : 0));
if (folio_test_young(folio))
folio_set_young(new_folio);
@@ -2882,7 +2887,7 @@ static void __split_huge_page_tail(struc
}
static void __split_huge_page(struct page *page, struct list_head *list,
- pgoff_t end)
+ pgoff_t end, unsigned int new_order)
{
struct folio *folio = page_folio(page);
struct page *head = &folio->page;
@@ -2890,11 +2895,12 @@ static void __split_huge_page(struct pag
struct address_space *swap_cache = NULL;
unsigned long offset = 0;
int i, nr_dropped = 0;
+ unsigned int new_nr = 1 << new_order;
int order = folio_order(folio);
unsigned int nr = 1 << order;
/* complete memcg works before add pages to LRU */
- split_page_memcg(head, order, 0);
+ split_page_memcg(head, order, new_order);
if (folio_test_anon(folio) && folio_test_swapcache(folio)) {
offset = swp_offset(folio->swap);
@@ -2907,8 +2913,8 @@ static void __split_huge_page(struct pag
ClearPageHasHWPoisoned(head);
- for (i = nr - 1; i >= 1; i--) {
- __split_huge_page_tail(folio, i, lruvec, list);
+ for (i = nr - new_nr; i >= new_nr; i -= new_nr) {
+ __split_huge_page_tail(folio, i, lruvec, list, new_order);
/* Some pages can be beyond EOF: drop them from page cache */
if (head[i].index >= end) {
struct folio *tail = page_folio(head + i);
@@ -2929,24 +2935,30 @@ static void __split_huge_page(struct pag
}
}
- ClearPageCompound(head);
+ if (!new_order)
+ ClearPageCompound(head);
+ else {
+ struct folio *new_folio = (struct folio *)head;
+
+ folio_set_order(new_folio, new_order);
+ }
unlock_page_lruvec(lruvec);
/* Caller disabled irqs, so they are still disabled here */
- split_page_owner(head, order, 0);
+ split_page_owner(head, order, new_order);
/* See comment in __split_huge_page_tail() */
if (PageAnon(head)) {
/* Additional pin to swap cache */
if (PageSwapCache(head)) {
- page_ref_add(head, 2);
+ page_ref_add(head, 1 + new_nr);
xa_unlock(&swap_cache->i_pages);
} else {
page_ref_inc(head);
}
} else {
/* Additional pin to page cache */
- page_ref_add(head, 2);
+ page_ref_add(head, 1 + new_nr);
xa_unlock(&head->mapping->i_pages);
}
local_irq_enable();
@@ -2958,7 +2970,15 @@ static void __split_huge_page(struct pag
if (folio_test_swapcache(folio))
split_swap_cluster(folio->swap);
- for (i = 0; i < nr; i++) {
+ /*
+ * set page to its compound_head when split to non order-0 pages, so
+ * we can skip unlocking it below, since PG_locked is transferred to
+ * the compound_head of the page and the caller will unlock it.
+ */
+ if (new_order)
+ page = compound_head(page);
+
+ for (i = 0; i < nr; i += new_nr) {
struct page *subpage = head + i;
if (subpage == page)
continue;
@@ -2992,29 +3012,36 @@ bool can_split_folio(struct folio *folio
}
/*
- * This function splits huge page into normal pages. @page can point to any
- * subpage of huge page to split. Split doesn't change the position of @page.
+ * This function splits huge page into pages in @new_order. @page can point to
+ * any subpage of huge page to split. Split doesn't change the position of
+ * @page.
+ *
+ * NOTE: order-1 anonymous folio is not supported because _deferred_list,
+ * which is used by partially mapped folios, is stored in subpage 2 and an
+ * order-1 folio only has subpage 0 and 1. File-backed order-1 folios are OK,
+ * since they do not use _deferred_list.
*
* Only caller must hold pin on the @page, otherwise split fails with -EBUSY.
* The huge page must be locked.
*
* If @list is null, tail pages will be added to LRU list, otherwise, to @list.
*
- * Both head page and tail pages will inherit mapping, flags, and so on from
- * the hugepage.
+ * Pages in new_order will inherit mapping, flags, and so on from the hugepage.
*
- * GUP pin and PG_locked transferred to @page. Rest subpages can be freed if
- * they are not mapped.
+ * GUP pin and PG_locked transferred to @page or the compound page @page belongs
+ * to. Rest subpages can be freed if they are not mapped.
*
* Returns 0 if the hugepage is split successfully.
* Returns -EBUSY if the page is pinned or if anon_vma disappeared from under
* us.
*/
-int split_huge_page_to_list(struct page *page, struct list_head *list)
+int split_huge_page_to_list_to_order(struct page *page, struct list_head *list,
+ unsigned int new_order)
{
struct folio *folio = page_folio(page);
struct deferred_split *ds_queue = get_deferred_split_queue(folio);
- XA_STATE(xas, &folio->mapping->i_pages, folio->index);
+ /* reset xarray order to new order after split */
+ XA_STATE_ORDER(xas, &folio->mapping->i_pages, folio->index, new_order);
struct anon_vma *anon_vma = NULL;
struct address_space *mapping = NULL;
int extra_pins, ret;
@@ -3024,6 +3051,34 @@ int split_huge_page_to_list(struct page
VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio);
VM_BUG_ON_FOLIO(!folio_test_large(folio), folio);
+ /* Cannot split anonymous THP to order-1 */
+ if (new_order == 1 && folio_test_anon(folio)) {
+ VM_WARN_ONCE(1, "Cannot split to order-1 folio");
+ return -EINVAL;
+ }
+
+ if (new_order) {
+ /* Only swapping a whole PMD-mapped folio is supported */
+ if (folio_test_swapcache(folio)) {
+ VM_WARN_ONCE(1,
+ "Cannot split swap-cached folio to non-0 order");
+ return -EINVAL;
+ }
+ /* Split shmem folio to non-zero order not supported */
+ if (shmem_mapping(folio->mapping)) {
+ VM_WARN_ONCE(1,
+ "Cannot split shmem folio to non-0 order");
+ return -EINVAL;
+ }
+ /* No split if the file system does not support large folio */
+ if (!mapping_large_folio_support(folio->mapping)) {
+ VM_WARN_ONCE(1,
+ "Cannot split file folio to non-0 order");
+ return -EINVAL;
+ }
+ }
+
+
is_hzp = is_huge_zero_page(&folio->page);
if (is_hzp) {
pr_warn_ratelimited("Called split_huge_page for huge zero page\n");
@@ -3120,14 +3175,21 @@ int split_huge_page_to_list(struct page
if (folio_order(folio) > 1 &&
!list_empty(&folio->_deferred_list)) {
ds_queue->split_queue_len--;
- list_del(&folio->_deferred_list);
+ /*
+ * Reinitialize page_deferred_list after removing the
+ * page from the split_queue, otherwise a subsequent
+ * split will see list corruption when checking the
+ * page_deferred_list.
+ */
+ list_del_init(&folio->_deferred_list);
}
spin_unlock(&ds_queue->split_queue_lock);
if (mapping) {
int nr = folio_nr_pages(folio);
xas_split(&xas, folio, folio_order(folio));
- if (folio_test_pmd_mappable(folio)) {
+ if (folio_test_pmd_mappable(folio) &&
+ new_order < HPAGE_PMD_ORDER) {
if (folio_test_swapbacked(folio)) {
__lruvec_stat_mod_folio(folio,
NR_SHMEM_THPS, -nr);
@@ -3139,7 +3201,7 @@ int split_huge_page_to_list(struct page
}
}
- __split_huge_page(page, list, end);
+ __split_huge_page(page, list, end, new_order);
ret = 0;
} else {
spin_unlock(&ds_queue->split_queue_lock);
_
Patches currently in -mm which might be from ziy@nvidia.com are
mm-huge_memory-only-split-pmd-mapping-when-necessary-in-unmap_folio.patch
mm-memcg-use-order-instead-of-nr-in-split_page_memcg.patch
mm-page_owner-use-order-instead-of-nr-in-split_page_owner.patch
mm-memcg-make-memcg-huge-page-split-support-any-order-split.patch
mm-page_owner-add-support-for-splitting-to-any-order-in-split-page_owner.patch
mm-thp-split-huge-page-to-any-lower-order-pages.patch
mm-huge_memory-enable-debugfs-to-split-huge-pages-to-any-order.patch
^ permalink raw reply [flat|nested] 2+ messages in thread
end of thread, other threads:[~2024-02-26 22:25 UTC | newest]
Thread overview: 2+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2023-04-04 21:45 + mm-thp-split-huge-page-to-any-lower-order-pages.patch added to mm-unstable branch Andrew Morton
-- strict thread matches above, loose matches on Subject: below --
2024-02-26 22:25 Andrew Morton
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.