summaryrefslogtreecommitdiff
path: root/mm
diff options
context:
space:
mode:
Diffstat (limited to 'mm')
-rw-r--r--mm/balloon_compaction.c6
-rw-r--r--mm/damon/core.c15
-rw-r--r--mm/damon/sysfs-schemes.c2
-rw-r--r--mm/debug_vm_pgtable.c9
-rw-r--r--mm/memory-failure.c8
-rw-r--r--mm/migrate.c38
-rw-r--r--mm/mremap.c82
-rw-r--r--mm/zsmalloc.c10
8 files changed, 123 insertions, 47 deletions
diff --git a/mm/balloon_compaction.c b/mm/balloon_compaction.c
index 2a4a649805c1..03c5dbabb156 100644
--- a/mm/balloon_compaction.c
+++ b/mm/balloon_compaction.c
@@ -254,4 +254,10 @@ const struct movable_operations balloon_mops = {
.putback_page = balloon_page_putback,
};
+static int __init balloon_init(void)
+{
+ return set_movable_ops(&balloon_mops, PGTY_offline);
+}
+core_initcall(balloon_init);
+
#endif /* CONFIG_BALLOON_COMPACTION */
diff --git a/mm/damon/core.c b/mm/damon/core.c
index 52a48c9316bc..70eff5cbe6ee 100644
--- a/mm/damon/core.c
+++ b/mm/damon/core.c
@@ -845,6 +845,18 @@ static struct damos_filter *damos_nth_filter(int n, struct damos *s)
return NULL;
}
+static struct damos_filter *damos_nth_ops_filter(int n, struct damos *s)
+{
+ struct damos_filter *filter;
+ int i = 0;
+
+ damos_for_each_ops_filter(filter, s) {
+ if (i++ == n)
+ return filter;
+ }
+ return NULL;
+}
+
static void damos_commit_filter_arg(
struct damos_filter *dst, struct damos_filter *src)
{
@@ -871,6 +883,7 @@ static void damos_commit_filter(
{
dst->type = src->type;
dst->matching = src->matching;
+ dst->allow = src->allow;
damos_commit_filter_arg(dst, src);
}
@@ -908,7 +921,7 @@ static int damos_commit_ops_filters(struct damos *dst, struct damos *src)
int i = 0, j = 0;
damos_for_each_ops_filter_safe(dst_filter, next, dst) {
- src_filter = damos_nth_filter(i++, src);
+ src_filter = damos_nth_ops_filter(i++, src);
if (src_filter)
damos_commit_filter(dst_filter, src_filter);
else
diff --git a/mm/damon/sysfs-schemes.c b/mm/damon/sysfs-schemes.c
index 74056bcd6a2c..6536f16006c9 100644
--- a/mm/damon/sysfs-schemes.c
+++ b/mm/damon/sysfs-schemes.c
@@ -2158,8 +2158,8 @@ static void damon_sysfs_scheme_rm_dirs(struct damon_sysfs_scheme *scheme)
{
damon_sysfs_access_pattern_rm_dirs(scheme->access_pattern);
kobject_put(&scheme->access_pattern->kobj);
- kobject_put(&scheme->dests->kobj);
damos_sysfs_dests_rm_dirs(scheme->dests);
+ kobject_put(&scheme->dests->kobj);
damon_sysfs_quotas_rm_dirs(scheme->quotas);
kobject_put(&scheme->quotas->kobj);
kobject_put(&scheme->watermarks->kobj);
diff --git a/mm/debug_vm_pgtable.c b/mm/debug_vm_pgtable.c
index d19031f275a3..830107b6dd08 100644
--- a/mm/debug_vm_pgtable.c
+++ b/mm/debug_vm_pgtable.c
@@ -990,29 +990,34 @@ static void __init destroy_args(struct pgtable_debug_args *args)
/* Free page table entries */
if (args->start_ptep) {
+ pmd_clear(args->pmdp);
pte_free(args->mm, args->start_ptep);
mm_dec_nr_ptes(args->mm);
}
if (args->start_pmdp) {
+ pud_clear(args->pudp);
pmd_free(args->mm, args->start_pmdp);
mm_dec_nr_pmds(args->mm);
}
if (args->start_pudp) {
+ p4d_clear(args->p4dp);
pud_free(args->mm, args->start_pudp);
mm_dec_nr_puds(args->mm);
}
- if (args->start_p4dp)
+ if (args->start_p4dp) {
+ pgd_clear(args->pgdp);
p4d_free(args->mm, args->start_p4dp);
+ }
/* Free vma and mm struct */
if (args->vma)
vm_area_free(args->vma);
if (args->mm)
- mmdrop(args->mm);
+ mmput(args->mm);
}
static struct page * __init
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index e2e685b971bb..fc30ca4804bf 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -853,9 +853,17 @@ static int hwpoison_hugetlb_range(pte_t *ptep, unsigned long hmask,
#define hwpoison_hugetlb_range NULL
#endif
+static int hwpoison_test_walk(unsigned long start, unsigned long end,
+ struct mm_walk *walk)
+{
+ /* We also want to consider pages mapped into VM_PFNMAP. */
+ return 0;
+}
+
static const struct mm_walk_ops hwpoison_walk_ops = {
.pmd_entry = hwpoison_pte_range,
.hugetlb_entry = hwpoison_hugetlb_range,
+ .test_walk = hwpoison_test_walk,
.walk_lock = PGWALK_RDLOCK,
};
diff --git a/mm/migrate.c b/mm/migrate.c
index 425401b2d4e1..9e5ef39ce73a 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -43,8 +43,6 @@
#include <linux/sched/sysctl.h>
#include <linux/memory-tiers.h>
#include <linux/pagewalk.h>
-#include <linux/balloon_compaction.h>
-#include <linux/zsmalloc.h>
#include <asm/tlbflush.h>
@@ -53,6 +51,33 @@
#include "internal.h"
#include "swap.h"
+static const struct movable_operations *offline_movable_ops;
+static const struct movable_operations *zsmalloc_movable_ops;
+
+int set_movable_ops(const struct movable_operations *ops, enum pagetype type)
+{
+ /*
+ * We only allow for selected types and don't handle concurrent
+ * registration attempts yet.
+ */
+ switch (type) {
+ case PGTY_offline:
+ if (offline_movable_ops && ops)
+ return -EBUSY;
+ offline_movable_ops = ops;
+ break;
+ case PGTY_zsmalloc:
+ if (zsmalloc_movable_ops && ops)
+ return -EBUSY;
+ zsmalloc_movable_ops = ops;
+ break;
+ default:
+ return -EINVAL;
+ }
+ return 0;
+}
+EXPORT_SYMBOL_GPL(set_movable_ops);
+
static const struct movable_operations *page_movable_ops(struct page *page)
{
VM_WARN_ON_ONCE_PAGE(!page_has_movable_ops(page), page);
@@ -62,15 +87,12 @@ static const struct movable_operations *page_movable_ops(struct page *page)
* it as movable, the page type must be sticky until the page gets freed
* back to the buddy.
*/
-#ifdef CONFIG_BALLOON_COMPACTION
if (PageOffline(page))
/* Only balloon compaction sets PageOffline pages movable. */
- return &balloon_mops;
-#endif /* CONFIG_BALLOON_COMPACTION */
-#if defined(CONFIG_ZSMALLOC) && defined(CONFIG_COMPACTION)
+ return offline_movable_ops;
if (PageZsmalloc(page))
- return &zsmalloc_mops;
-#endif /* defined(CONFIG_ZSMALLOC) && defined(CONFIG_COMPACTION) */
+ return zsmalloc_movable_ops;
+
return NULL;
}
diff --git a/mm/mremap.c b/mm/mremap.c
index 9afa8cd524f5..e618a706aff5 100644
--- a/mm/mremap.c
+++ b/mm/mremap.c
@@ -323,6 +323,25 @@ static inline bool arch_supports_page_table_move(void)
}
#endif
+static inline bool uffd_supports_page_table_move(struct pagetable_move_control *pmc)
+{
+ /*
+ * If we are moving a VMA that has uffd-wp registered but with
+ * remap events disabled (new VMA will not be registered with uffd), we
+ * need to ensure that the uffd-wp state is cleared from all pgtables.
+ * This means recursing into lower page tables in move_page_tables().
+ *
+ * We might get called with VMAs reversed when recovering from a
+ * failed page table move. In that case, the
+ * "old"-but-actually-"originally new" VMA during recovery will not have
+ * a uffd context. Recursing into lower page tables during the original
+ * move but not during the recovery move will cause trouble, because we
+ * run into already-existing page tables. So check both VMAs.
+ */
+ return !vma_has_uffd_without_event_remap(pmc->old) &&
+ !vma_has_uffd_without_event_remap(pmc->new);
+}
+
#ifdef CONFIG_HAVE_MOVE_PMD
static bool move_normal_pmd(struct pagetable_move_control *pmc,
pmd_t *old_pmd, pmd_t *new_pmd)
@@ -335,6 +354,8 @@ static bool move_normal_pmd(struct pagetable_move_control *pmc,
if (!arch_supports_page_table_move())
return false;
+ if (!uffd_supports_page_table_move(pmc))
+ return false;
/*
* The destination pmd shouldn't be established, free_pgtables()
* should have released it.
@@ -361,15 +382,6 @@ static bool move_normal_pmd(struct pagetable_move_control *pmc,
if (WARN_ON_ONCE(!pmd_none(*new_pmd)))
return false;
- /* If this pmd belongs to a uffd vma with remap events disabled, we need
- * to ensure that the uffd-wp state is cleared from all pgtables. This
- * means recursing into lower page tables in move_page_tables(), and we
- * can reuse the existing code if we simply treat the entry as "not
- * moved".
- */
- if (vma_has_uffd_without_event_remap(vma))
- return false;
-
/*
* We don't have to worry about the ordering of src and dst
* ptlocks because exclusive mmap_lock prevents deadlock.
@@ -418,6 +430,8 @@ static bool move_normal_pud(struct pagetable_move_control *pmc,
if (!arch_supports_page_table_move())
return false;
+ if (!uffd_supports_page_table_move(pmc))
+ return false;
/*
* The destination pud shouldn't be established, free_pgtables()
* should have released it.
@@ -425,15 +439,6 @@ static bool move_normal_pud(struct pagetable_move_control *pmc,
if (WARN_ON_ONCE(!pud_none(*new_pud)))
return false;
- /* If this pud belongs to a uffd vma with remap events disabled, we need
- * to ensure that the uffd-wp state is cleared from all pgtables. This
- * means recursing into lower page tables in move_page_tables(), and we
- * can reuse the existing code if we simply treat the entry as "not
- * moved".
- */
- if (vma_has_uffd_without_event_remap(vma))
- return false;
-
/*
* We don't have to worry about the ordering of src and dst
* ptlocks because exclusive mmap_lock prevents deadlock.
@@ -1620,7 +1625,7 @@ static void notify_uffd(struct vma_remap_struct *vrm, bool failed)
static bool vma_multi_allowed(struct vm_area_struct *vma)
{
- struct file *file;
+ struct file *file = vma->vm_file;
/*
* We can't support moving multiple uffd VMAs as notify requires
@@ -1633,15 +1638,17 @@ static bool vma_multi_allowed(struct vm_area_struct *vma)
* Custom get unmapped area might result in MREMAP_FIXED not
* being obeyed.
*/
- file = vma->vm_file;
- if (file && !vma_is_shmem(vma) && !is_vm_hugetlb_page(vma)) {
- const struct file_operations *fop = file->f_op;
-
- if (fop->get_unmapped_area)
- return false;
- }
+ if (!file || !file->f_op->get_unmapped_area)
+ return true;
+ /* Known good. */
+ if (vma_is_shmem(vma))
+ return true;
+ if (is_vm_hugetlb_page(vma))
+ return true;
+ if (file->f_op->get_unmapped_area == thp_get_unmapped_area)
+ return true;
- return true;
+ return false;
}
static int check_prep_vma(struct vma_remap_struct *vrm)
@@ -1818,10 +1825,11 @@ static unsigned long remap_move(struct vma_remap_struct *vrm)
unsigned long start = vrm->addr;
unsigned long end = vrm->addr + vrm->old_len;
unsigned long new_addr = vrm->new_addr;
- bool allowed = true, seen_vma = false;
unsigned long target_addr = new_addr;
unsigned long res = -EFAULT;
unsigned long last_end;
+ bool seen_vma = false;
+
VMA_ITERATOR(vmi, current->mm, start);
/*
@@ -1834,9 +1842,7 @@ static unsigned long remap_move(struct vma_remap_struct *vrm)
unsigned long addr = max(vma->vm_start, start);
unsigned long len = min(end, vma->vm_end) - addr;
unsigned long offset, res_vma;
-
- if (!allowed)
- return -EFAULT;
+ bool multi_allowed;
/* No gap permitted at the start of the range. */
if (!seen_vma && start < vma->vm_start)
@@ -1865,9 +1871,15 @@ static unsigned long remap_move(struct vma_remap_struct *vrm)
vrm->new_addr = target_addr + offset;
vrm->old_len = vrm->new_len = len;
- allowed = vma_multi_allowed(vma);
- if (seen_vma && !allowed)
- return -EFAULT;
+ multi_allowed = vma_multi_allowed(vma);
+ if (!multi_allowed) {
+ /* This is not the first VMA, abort immediately. */
+ if (seen_vma)
+ return -EFAULT;
+ /* This is the first, but there are more, abort. */
+ if (vma->vm_end < end)
+ return -EFAULT;
+ }
res_vma = check_prep_vma(vrm);
if (!res_vma)
@@ -1876,7 +1888,7 @@ static unsigned long remap_move(struct vma_remap_struct *vrm)
return res_vma;
if (!seen_vma) {
- VM_WARN_ON_ONCE(allowed && res_vma != new_addr);
+ VM_WARN_ON_ONCE(multi_allowed && res_vma != new_addr);
res = res_vma;
}
diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c
index 2c5e56a65354..805a10b41266 100644
--- a/mm/zsmalloc.c
+++ b/mm/zsmalloc.c
@@ -2246,9 +2246,16 @@ EXPORT_SYMBOL_GPL(zs_destroy_pool);
static int __init zs_init(void)
{
+ int rc __maybe_unused;
+
#ifdef CONFIG_ZPOOL
zpool_register_driver(&zs_zpool_driver);
#endif
+#ifdef CONFIG_COMPACTION
+ rc = set_movable_ops(&zsmalloc_mops, PGTY_zsmalloc);
+ if (rc)
+ return rc;
+#endif
zs_stat_init();
return 0;
}
@@ -2258,6 +2265,9 @@ static void __exit zs_exit(void)
#ifdef CONFIG_ZPOOL
zpool_unregister_driver(&zs_zpool_driver);
#endif
+#ifdef CONFIG_COMPACTION
+ set_movable_ops(NULL, PGTY_zsmalloc);
+#endif
zs_stat_exit();
}
generated by cgit v1.2.3 (git 2.39.0) at 2025-08-24 01:48:25 +0300