aboutsummaryrefslogtreecommitdiffstats
path: root/mm/mempolicy.c
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2023-02-23 17:09:35 -0800
committerLinus Torvalds <torvalds@linux-foundation.org>2023-02-23 17:09:35 -0800
commit3822a7c40997dc86b1458766a3f146d62393f084 (patch)
tree4473720ecbfaabeedfe58484425be77d0f89f736 /mm/mempolicy.c
parente4bc15889506723d7b93c053ad4a75cd58248d74 (diff)
parentf9366f4c2a29d14f5992b195e268240c2deb116e (diff)
downloadnet-3822a7c40997dc86b1458766a3f146d62393f084.tar.gz
Merge tag 'mm-stable-2023-02-20-13-37' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
Pull MM updates from Andrew Morton: - Daniel Verkamp has contributed a memfd series ("mm/memfd: add F_SEAL_EXEC") which permits the setting of the memfd execute bit at memfd creation time, with the option of sealing the state of the X bit. - Peter Xu adds a patch series ("mm/hugetlb: Make huge_pte_offset() thread-safe for pmd unshare") which addresses a rare race condition related to PMD unsharing. - Several folioification patch serieses from Matthew Wilcox, Vishal Moola, Sidhartha Kumar and Lorenzo Stoakes - Johannes Weiner has a series ("mm: push down lock_page_memcg()") which does perform some memcg maintenance and cleanup work. - SeongJae Park has added DAMOS filtering to DAMON, with the series "mm/damon/core: implement damos filter". These filters provide users with finer-grained control over DAMOS's actions. SeongJae has also done some DAMON cleanup work. - Kairui Song adds a series ("Clean up and fixes for swap"). - Vernon Yang contributed the series "Clean up and refinement for maple tree". - Yu Zhao has contributed the "mm: multi-gen LRU: memcg LRU" series. It adds to MGLRU an LRU of memcgs, to improve the scalability of global reclaim. - David Hildenbrand has added some userfaultfd cleanup work in the series "mm: uffd-wp + change_protection() cleanups". - Christoph Hellwig has removed the generic_writepages() library function in the series "remove generic_writepages". - Baolin Wang has performed some maintenance on the compaction code in his series "Some small improvements for compaction". - Sidhartha Kumar is doing some maintenance work on struct page in his series "Get rid of tail page fields". - David Hildenbrand contributed some cleanup, bugfixing and generalization of pte management and of pte debugging in his series "mm: support __HAVE_ARCH_PTE_SWP_EXCLUSIVE on all architectures with swap PTEs". - Mel Gorman and Neil Brown have removed the __GFP_ATOMIC allocation flag in the series "Discard __GFP_ATOMIC". - Sergey Senozhatsky has improved zsmalloc's memory utilization with his series "zsmalloc: make zspage chain size configurable". - Joey Gouly has added prctl() support for prohibiting the creation of writeable+executable mappings. The previous BPF-based approach had shortcomings. See "mm: In-kernel support for memory-deny-write-execute (MDWE)". - Waiman Long did some kmemleak cleanup and bugfixing in the series "mm/kmemleak: Simplify kmemleak_cond_resched() & fix UAF". - T.J. Alumbaugh has contributed some MGLRU cleanup work in his series "mm: multi-gen LRU: improve". - Jiaqi Yan has provided some enhancements to our memory error statistics reporting, mainly by presenting the statistics on a per-node basis. See the series "Introduce per NUMA node memory error statistics". - Mel Gorman has a second and hopefully final shot at fixing a CPU-hog regression in compaction via his series "Fix excessive CPU usage during compaction". - Christoph Hellwig does some vmalloc maintenance work in the series "cleanup vfree and vunmap". - Christoph Hellwig has removed block_device_operations.rw_page() in ths series "remove ->rw_page". - We get some maple_tree improvements and cleanups in Liam Howlett's series "VMA tree type safety and remove __vma_adjust()". - Suren Baghdasaryan has done some work on the maintainability of our vm_flags handling in the series "introduce vm_flags modifier functions". - Some pagemap cleanup and generalization work in Mike Rapoport's series "mm, arch: add generic implementation of pfn_valid() for FLATMEM" and "fixups for generic implementation of pfn_valid()" - Baoquan He has done some work to make /proc/vmallocinfo and /proc/kcore better represent the real state of things in his series "mm/vmalloc.c: allow vread() to read out vm_map_ram areas". - Jason Gunthorpe rationalized the GUP system's interface to the rest of the kernel in the series "Simplify the external interface for GUP". - SeongJae Park wishes to migrate people from DAMON's debugfs interface over to its sysfs interface. To support this, we'll temporarily be printing warnings when people use the debugfs interface. See the series "mm/damon: deprecate DAMON debugfs interface". - Andrey Konovalov provided the accurately named "lib/stackdepot: fixes and clean-ups" series. - Huang Ying has provided a dramatic reduction in migration's TLB flush IPI rates with the series "migrate_pages(): batch TLB flushing". - Arnd Bergmann has some objtool fixups in "objtool warning fixes". * tag 'mm-stable-2023-02-20-13-37' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (505 commits) include/linux/migrate.h: remove unneeded externs mm/memory_hotplug: cleanup return value handing in do_migrate_range() mm/uffd: fix comment in handling pte markers mm: change to return bool for isolate_movable_page() mm: hugetlb: change to return bool for isolate_hugetlb() mm: change to return bool for isolate_lru_page() mm: change to return bool for folio_isolate_lru() objtool: add UACCESS exceptions for __tsan_volatile_read/write kmsan: disable ftrace in kmsan core code kasan: mark addr_has_metadata __always_inline mm: memcontrol: rename memcg_kmem_enabled() sh: initialize max_mapnr m68k/nommu: add missing definition of ARCH_PFN_OFFSET mm: percpu: fix incorrect size in pcpu_obj_full_size() maple_tree: reduce stack usage with gcc-9 and earlier mm: page_alloc: call panic() when memoryless node allocation fails mm: multi-gen LRU: avoid futile retries migrate_pages: move THP/hugetlb migration support check to simplify code migrate_pages: batch flushing TLB migrate_pages: share more code between _unmap and _move ...
Diffstat (limited to 'mm/mempolicy.c')
-rw-r--r--mm/mempolicy.c188
1 files changed, 92 insertions, 96 deletions
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index f940395667c82f..a256a241fd1dae 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -414,7 +414,7 @@ static const struct mempolicy_operations mpol_ops[MPOL_MAX] = {
},
};
-static int migrate_page_add(struct page *page, struct list_head *pagelist,
+static int migrate_folio_add(struct folio *folio, struct list_head *foliolist,
unsigned long flags);
struct queue_pages {
@@ -427,36 +427,36 @@ struct queue_pages {
};
/*
- * Check if the page's nid is in qp->nmask.
+ * Check if the folio's nid is in qp->nmask.
*
* If MPOL_MF_INVERT is set in qp->flags, check if the nid is
* in the invert of qp->nmask.
*/
-static inline bool queue_pages_required(struct page *page,
+static inline bool queue_folio_required(struct folio *folio,
struct queue_pages *qp)
{
- int nid = page_to_nid(page);
+ int nid = folio_nid(folio);
unsigned long flags = qp->flags;
return node_isset(nid, *qp->nmask) == !(flags & MPOL_MF_INVERT);
}
/*
- * queue_pages_pmd() has three possible return values:
- * 0 - pages are placed on the right node or queued successfully, or
+ * queue_folios_pmd() has three possible return values:
+ * 0 - folios are placed on the right node or queued successfully, or
* special page is met, i.e. huge zero page.
- * 1 - there is unmovable page, and MPOL_MF_MOVE* & MPOL_MF_STRICT were
+ * 1 - there is unmovable folio, and MPOL_MF_MOVE* & MPOL_MF_STRICT were
* specified.
* -EIO - is migration entry or only MPOL_MF_STRICT was specified and an
- * existing page was already on a node that does not follow the
+ * existing folio was already on a node that does not follow the
* policy.
*/
-static int queue_pages_pmd(pmd_t *pmd, spinlock_t *ptl, unsigned long addr,
+static int queue_folios_pmd(pmd_t *pmd, spinlock_t *ptl, unsigned long addr,
unsigned long end, struct mm_walk *walk)
__releases(ptl)
{
int ret = 0;
- struct page *page;
+ struct folio *folio;
struct queue_pages *qp = walk->private;
unsigned long flags;
@@ -464,19 +464,19 @@ static int queue_pages_pmd(pmd_t *pmd, spinlock_t *ptl, unsigned long addr,
ret = -EIO;
goto unlock;
}
- page = pmd_page(*pmd);
- if (is_huge_zero_page(page)) {
+ folio = pfn_folio(pmd_pfn(*pmd));
+ if (is_huge_zero_page(&folio->page)) {
walk->action = ACTION_CONTINUE;
goto unlock;
}
- if (!queue_pages_required(page, qp))
+ if (!queue_folio_required(folio, qp))
goto unlock;
flags = qp->flags;
- /* go to thp migration */
+ /* go to folio migration */
if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) {
if (!vma_migratable(walk->vma) ||
- migrate_page_add(page, qp->pagelist, flags)) {
+ migrate_folio_add(folio, qp->pagelist, flags)) {
ret = 1;
goto unlock;
}
@@ -491,19 +491,19 @@ unlock:
* Scan through pages checking if pages follow certain conditions,
* and move them to the pagelist if they do.
*
- * queue_pages_pte_range() has three possible return values:
- * 0 - pages are placed on the right node or queued successfully, or
+ * queue_folios_pte_range() has three possible return values:
+ * 0 - folios are placed on the right node or queued successfully, or
* special page is met, i.e. zero page.
- * 1 - there is unmovable page, and MPOL_MF_MOVE* & MPOL_MF_STRICT were
+ * 1 - there is unmovable folio, and MPOL_MF_MOVE* & MPOL_MF_STRICT were
* specified.
- * -EIO - only MPOL_MF_STRICT was specified and an existing page was already
+ * -EIO - only MPOL_MF_STRICT was specified and an existing folio was already
* on a node that does not follow the policy.
*/
-static int queue_pages_pte_range(pmd_t *pmd, unsigned long addr,
+static int queue_folios_pte_range(pmd_t *pmd, unsigned long addr,
unsigned long end, struct mm_walk *walk)
{
struct vm_area_struct *vma = walk->vma;
- struct page *page;
+ struct folio *folio;
struct queue_pages *qp = walk->private;
unsigned long flags = qp->flags;
bool has_unmovable = false;
@@ -512,7 +512,7 @@ static int queue_pages_pte_range(pmd_t *pmd, unsigned long addr,
ptl = pmd_trans_huge_lock(pmd, vma);
if (ptl)
- return queue_pages_pmd(pmd, ptl, addr, end, walk);
+ return queue_folios_pmd(pmd, ptl, addr, end, walk);
if (pmd_trans_unstable(pmd))
return 0;
@@ -521,16 +521,16 @@ static int queue_pages_pte_range(pmd_t *pmd, unsigned long addr,
for (; addr != end; pte++, addr += PAGE_SIZE) {
if (!pte_present(*pte))
continue;
- page = vm_normal_page(vma, addr, *pte);
- if (!page || is_zone_device_page(page))
+ folio = vm_normal_folio(vma, addr, *pte);
+ if (!folio || folio_is_zone_device(folio))
continue;
/*
- * vm_normal_page() filters out zero pages, but there might
- * still be PageReserved pages to skip, perhaps in a VDSO.
+ * vm_normal_folio() filters out zero pages, but there might
+ * still be reserved folios to skip, perhaps in a VDSO.
*/
- if (PageReserved(page))
+ if (folio_test_reserved(folio))
continue;
- if (!queue_pages_required(page, qp))
+ if (!queue_folio_required(folio, qp))
continue;
if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) {
/* MPOL_MF_STRICT must be specified if we get here */
@@ -544,7 +544,7 @@ static int queue_pages_pte_range(pmd_t *pmd, unsigned long addr,
* temporary off LRU pages in the range. Still
* need migrate other LRU pages.
*/
- if (migrate_page_add(page, qp->pagelist, flags))
+ if (migrate_folio_add(folio, qp->pagelist, flags))
has_unmovable = true;
} else
break;
@@ -558,7 +558,7 @@ static int queue_pages_pte_range(pmd_t *pmd, unsigned long addr,
return addr != end ? -EIO : 0;
}
-static int queue_pages_hugetlb(pte_t *pte, unsigned long hmask,
+static int queue_folios_hugetlb(pte_t *pte, unsigned long hmask,
unsigned long addr, unsigned long end,
struct mm_walk *walk)
{
@@ -566,7 +566,7 @@ static int queue_pages_hugetlb(pte_t *pte, unsigned long hmask,
#ifdef CONFIG_HUGETLB_PAGE
struct queue_pages *qp = walk->private;
unsigned long flags = (qp->flags & MPOL_MF_VALID);
- struct page *page;
+ struct folio *folio;
spinlock_t *ptl;
pte_t entry;
@@ -574,13 +574,13 @@ static int queue_pages_hugetlb(pte_t *pte, unsigned long hmask,
entry = huge_ptep_get(pte);
if (!pte_present(entry))
goto unlock;
- page = pte_page(entry);
- if (!queue_pages_required(page, qp))
+ folio = pfn_folio(pte_pfn(entry));
+ if (!queue_folio_required(folio, qp))
goto unlock;
if (flags == MPOL_MF_STRICT) {
/*
- * STRICT alone means only detecting misplaced page and no
+ * STRICT alone means only detecting misplaced folio and no
* need to further check other vma.
*/
ret = -EIO;
@@ -591,21 +591,28 @@ static int queue_pages_hugetlb(pte_t *pte, unsigned long hmask,
/*
* Must be STRICT with MOVE*, otherwise .test_walk() have
* stopped walking current vma.
- * Detecting misplaced page but allow migrating pages which
+ * Detecting misplaced folio but allow migrating folios which
* have been queued.
*/
ret = 1;
goto unlock;
}
- /* With MPOL_MF_MOVE, we migrate only unshared hugepage. */
+ /*
+ * With MPOL_MF_MOVE, we try to migrate only unshared folios. If it
+ * is shared it is likely not worth migrating.
+ *
+ * To check if the folio is shared, ideally we want to make sure
+ * every page is mapped to the same process. Doing that is very
+ * expensive, so check the estimated mapcount of the folio instead.
+ */
if (flags & (MPOL_MF_MOVE_ALL) ||
- (flags & MPOL_MF_MOVE && page_mapcount(page) == 1 &&
+ (flags & MPOL_MF_MOVE && folio_estimated_sharers(folio) == 1 &&
!hugetlb_pmd_shared(pte))) {
- if (isolate_hugetlb(page, qp->pagelist) &&
+ if (!isolate_hugetlb(folio, qp->pagelist) &&
(flags & MPOL_MF_STRICT))
/*
- * Failed to isolate page but allow migrating pages
+ * Failed to isolate folio but allow migrating pages
* which have been queued.
*/
ret = 1;
@@ -632,13 +639,12 @@ unsigned long change_prot_numa(struct vm_area_struct *vma,
unsigned long addr, unsigned long end)
{
struct mmu_gather tlb;
- int nr_updated;
+ long nr_updated;
tlb_gather_mmu(&tlb, vma->vm_mm);
- nr_updated = change_protection(&tlb, vma, addr, end, PAGE_NONE,
- MM_CP_PROT_NUMA);
- if (nr_updated)
+ nr_updated = change_protection(&tlb, vma, addr, end, MM_CP_PROT_NUMA);
+ if (nr_updated > 0)
count_vm_numa_events(NUMA_PTE_UPDATES, nr_updated);
tlb_finish_mmu(&tlb);
@@ -704,8 +710,8 @@ static int queue_pages_test_walk(unsigned long start, unsigned long end,
}
static const struct mm_walk_ops queue_pages_walk_ops = {
- .hugetlb_entry = queue_pages_hugetlb,
- .pmd_entry = queue_pages_pte_range,
+ .hugetlb_entry = queue_folios_hugetlb,
+ .pmd_entry = queue_folios_pte_range,
.test_walk = queue_pages_test_walk,
};
@@ -788,24 +794,21 @@ static int vma_replace_policy(struct vm_area_struct *vma,
static int mbind_range(struct mm_struct *mm, unsigned long start,
unsigned long end, struct mempolicy *new_pol)
{
- MA_STATE(mas, &mm->mm_mt, start, start);
+ VMA_ITERATOR(vmi, mm, start);
struct vm_area_struct *prev;
struct vm_area_struct *vma;
int err = 0;
pgoff_t pgoff;
- prev = mas_prev(&mas, 0);
- if (unlikely(!prev))
- mas_set(&mas, start);
-
- vma = mas_find(&mas, end - 1);
+ prev = vma_prev(&vmi);
+ vma = vma_find(&vmi, end);
if (WARN_ON(!vma))
return 0;
if (start > vma->vm_start)
prev = vma;
- for (; vma; vma = mas_next(&mas, end - 1)) {
+ do {
unsigned long vmstart = max(start, vma->vm_start);
unsigned long vmend = min(end, vma->vm_end);
@@ -814,29 +817,23 @@ static int mbind_range(struct mm_struct *mm, unsigned long start,
pgoff = vma->vm_pgoff +
((vmstart - vma->vm_start) >> PAGE_SHIFT);
- prev = vma_merge(mm, prev, vmstart, vmend, vma->vm_flags,
+ prev = vma_merge(&vmi, mm, prev, vmstart, vmend, vma->vm_flags,
vma->anon_vma, vma->vm_file, pgoff,
new_pol, vma->vm_userfaultfd_ctx,
anon_vma_name(vma));
if (prev) {
- /* vma_merge() invalidated the mas */
- mas_pause(&mas);
vma = prev;
goto replace;
}
if (vma->vm_start != vmstart) {
- err = split_vma(vma->vm_mm, vma, vmstart, 1);
+ err = split_vma(&vmi, vma, vmstart, 1);
if (err)
goto out;
- /* split_vma() invalidated the mas */
- mas_pause(&mas);
}
if (vma->vm_end != vmend) {
- err = split_vma(vma->vm_mm, vma, vmend, 0);
+ err = split_vma(&vmi, vma, vmend, 0);
if (err)
goto out;
- /* split_vma() invalidated the mas */
- mas_pause(&mas);
}
replace:
err = vma_replace_policy(vma, new_pol);
@@ -844,7 +841,7 @@ replace:
goto out;
next:
prev = vma;
- }
+ } for_each_vma_range(vmi, vma, end);
out:
return err;
@@ -1024,27 +1021,28 @@ static long do_get_mempolicy(int *policy, nodemask_t *nmask,
}
#ifdef CONFIG_MIGRATION
-/*
- * page migration, thp tail pages can be passed.
- */
-static int migrate_page_add(struct page *page, struct list_head *pagelist,
+static int migrate_folio_add(struct folio *folio, struct list_head *foliolist,
unsigned long flags)
{
- struct page *head = compound_head(page);
/*
- * Avoid migrating a page that is shared with others.
+ * We try to migrate only unshared folios. If it is shared it
+ * is likely not worth migrating.
+ *
+ * To check if the folio is shared, ideally we want to make sure
+ * every page is mapped to the same process. Doing that is very
+ * expensive, so check the estimated mapcount of the folio instead.
*/
- if ((flags & MPOL_MF_MOVE_ALL) || page_mapcount(head) == 1) {
- if (!isolate_lru_page(head)) {
- list_add_tail(&head->lru, pagelist);
- mod_node_page_state(page_pgdat(head),
- NR_ISOLATED_ANON + page_is_file_lru(head),
- thp_nr_pages(head));
+ if ((flags & MPOL_MF_MOVE_ALL) || folio_estimated_sharers(folio) == 1) {
+ if (folio_isolate_lru(folio)) {
+ list_add_tail(&folio->lru, foliolist);
+ node_stat_mod_folio(folio,
+ NR_ISOLATED_ANON + folio_is_file_lru(folio),
+ folio_nr_pages(folio));
} else if (flags & MPOL_MF_STRICT) {
/*
- * Non-movable page may reach here. And, there may be
- * temporary off LRU pages or non-LRU movable pages.
- * Treat them as unmovable pages since they can't be
+ * Non-movable folio may reach here. And, there may be
+ * temporary off LRU folios or non-LRU movable folios.
+ * Treat them as unmovable folios since they can't be
* isolated, so they can't be moved at the moment. It
* should return -EIO for this case too.
*/
@@ -1220,9 +1218,11 @@ static struct page *new_page(struct page *page, unsigned long start)
break;
}
- if (folio_test_hugetlb(src))
- return alloc_huge_page_vma(page_hstate(&src->page),
+ if (folio_test_hugetlb(src)) {
+ dst = alloc_hugetlb_folio_vma(folio_hstate(src),
vma, address);
+ return &dst->page;
+ }
if (folio_test_large(src))
gfp = GFP_TRANSHUGE;
@@ -1236,7 +1236,7 @@ static struct page *new_page(struct page *page, unsigned long start)
}
#else
-static int migrate_page_add(struct page *page, struct list_head *pagelist,
+static int migrate_folio_add(struct folio *folio, struct list_head *foliolist,
unsigned long flags)
{
return -EIO;
@@ -1490,7 +1490,7 @@ SYSCALL_DEFINE4(set_mempolicy_home_node, unsigned long, start, unsigned long, le
{
struct mm_struct *mm = current->mm;
struct vm_area_struct *vma;
- struct mempolicy *new;
+ struct mempolicy *new, *old;
unsigned long vmstart;
unsigned long vmend;
unsigned long end;
@@ -1522,31 +1522,27 @@ SYSCALL_DEFINE4(set_mempolicy_home_node, unsigned long, start, unsigned long, le
return 0;
mmap_write_lock(mm);
for_each_vma_range(vmi, vma, end) {
- vmstart = max(start, vma->vm_start);
- vmend = min(end, vma->vm_end);
- new = mpol_dup(vma_policy(vma));
- if (IS_ERR(new)) {
- err = PTR_ERR(new);
- break;
- }
- /*
- * Only update home node if there is an existing vma policy
- */
- if (!new)
- continue;
-
/*
* If any vma in the range got policy other than MPOL_BIND
* or MPOL_PREFERRED_MANY we return error. We don't reset
* the home node for vmas we already updated before.
*/
- if (new->mode != MPOL_BIND && new->mode != MPOL_PREFERRED_MANY) {
- mpol_put(new);
+ old = vma_policy(vma);
+ if (!old)
+ continue;
+ if (old->mode != MPOL_BIND && old->mode != MPOL_PREFERRED_MANY) {
err = -EOPNOTSUPP;
break;
}
+ new = mpol_dup(old);
+ if (IS_ERR(new)) {
+ err = PTR_ERR(new);
+ break;
+ }
new->home_node = home_node;
+ vmstart = max(start, vma->vm_start);
+ vmend = min(end, vma->vm_end);
err = mbind_range(mm, vmstart, vmend, new);
mpol_put(new);
if (err)