aboutsummaryrefslogtreecommitdiffstatshomepage
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2025-08-22 08:54:34 -0400
committerLinus Torvalds <torvalds@linux-foundation.org>2025-08-22 08:54:34 -0400
commit6eba757ce90483b76da4e7eda962d8b8b8930f2c (patch)
tree716c0662ea2644ed3ab08c6b06569409dc565dc0
parentMerge tag 'cgroup-for-6.17-rc2-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup (diff)
parentmm/mremap: fix WARN with uffd that has remap events disabled (diff)
downloadwireguard-linux-6eba757ce90483b76da4e7eda962d8b8b8930f2c.tar.xz
wireguard-linux-6eba757ce90483b76da4e7eda962d8b8b8930f2c.zip
Merge tag 'mm-hotfixes-stable-2025-08-21-18-17' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
Pull misc fixes from Andrew Morton: "20 hotfixes. 10 are cc:stable and the remainder address post-6.16 issues or aren't considered necessary for -stable kernels. 17 of these fixes are for MM. As usual, singletons all over the place, apart from a three-patch series of KHO followup work from Pasha which is actually also a bunch of singletons" * tag 'mm-hotfixes-stable-2025-08-21-18-17' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: mm/mremap: fix WARN with uffd that has remap events disabled mm/damon/sysfs-schemes: put damos dests dir after removing its files mm/migrate: fix NULL movable_ops if CONFIG_ZSMALLOC=m mm/damon/core: fix damos_commit_filter not changing allow mm/memory-failure: fix infinite UCE for VM_PFNMAP pfn MAINTAINERS: mark MGLRU as maintained mm: rust: add page.rs to MEMORY MANAGEMENT - RUST iov_iter: iterate_folioq: fix handling of offset >= folio size selftests/damon: fix selftests by installing drgn related script .mailmap: add entry for Easwar Hariharan selftests/mm: add test for invalid multi VMA operations mm/mremap: catch invalid multi VMA moves earlier mm/mremap: allow multi-VMA move when filesystem uses thp_get_unmapped_area mm/damon/core: fix commit_ops_filters by using correct nth function tools/testing: add linux/args.h header and fix radix, VMA tests mm/debug_vm_pgtable: clear page table entries at destroy_args() squashfs: fix memory leak in squashfs_fill_super kho: warn if KHO is disabled due to an error kho: mm: don't allow deferred struct page with KHO kho: init new_physxa->phys_bits to fix lockdep
-rw-r--r--.mailmap2
-rw-r--r--MAINTAINERS19
-rw-r--r--fs/squashfs/super.c14
-rw-r--r--include/linux/iov_iter.h20
-rw-r--r--include/linux/migrate.h5
-rw-r--r--kernel/Kconfig.kexec1
-rw-r--r--kernel/kexec_handover.c29
-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
-rw-r--r--tools/include/linux/args.h28
-rw-r--r--tools/testing/selftests/damon/Makefile1
-rw-r--r--tools/testing/selftests/mm/mremap_test.c264
-rw-r--r--tools/testing/shared/linux/idr.h4
19 files changed, 487 insertions, 70 deletions
diff --git a/.mailmap b/.mailmap
index d9fa1b555116..a124aeed52a2 100644
--- a/.mailmap
+++ b/.mailmap
@@ -226,6 +226,8 @@ Domen Puncer <domen@coderock.org>
Douglas Gilbert <dougg@torque.net>
Drew Fustini <fustini@kernel.org> <drew@pdp7.com>
<duje@dujemihanovic.xyz> <duje.mihanovic@skole.hr>
+Easwar Hariharan <easwar.hariharan@linux.microsoft.com> <easwar.hariharan@intel.com>
+Easwar Hariharan <easwar.hariharan@linux.microsoft.com> <eahariha@linux.microsoft.com>
Ed L. Cashin <ecashin@coraid.com>
Elliot Berman <quic_eberman@quicinc.com> <eberman@codeaurora.org>
Enric Balletbo i Serra <eballetbo@kernel.org> <enric.balletbo@collabora.com>
diff --git a/MAINTAINERS b/MAINTAINERS
index 2720544cd91f..75b041097c18 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -16058,6 +16058,23 @@ F: mm/mempolicy.c
F: mm/migrate.c
F: mm/migrate_device.c
+MEMORY MANAGEMENT - MGLRU (MULTI-GEN LRU)
+M: Andrew Morton <akpm@linux-foundation.org>
+M: Axel Rasmussen <axelrasmussen@google.com>
+M: Yuanchu Xie <yuanchu@google.com>
+R: Wei Xu <weixugc@google.com>
+L: linux-mm@kvack.org
+S: Maintained
+W: http://www.linux-mm.org
+T: git git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
+F: Documentation/admin-guide/mm/multigen_lru.rst
+F: Documentation/mm/multigen_lru.rst
+F: include/linux/mm_inline.h
+F: include/linux/mmzone.h
+F: mm/swap.c
+F: mm/vmscan.c
+F: mm/workingset.c
+
MEMORY MANAGEMENT - MISC
M: Andrew Morton <akpm@linux-foundation.org>
M: David Hildenbrand <david@redhat.com>
@@ -16248,8 +16265,10 @@ S: Maintained
W: http://www.linux-mm.org
T: git git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
F: rust/helpers/mm.c
+F: rust/helpers/page.c
F: rust/kernel/mm.rs
F: rust/kernel/mm/
+F: rust/kernel/page.rs
MEMORY MAPPING
M: Andrew Morton <akpm@linux-foundation.org>
diff --git a/fs/squashfs/super.c b/fs/squashfs/super.c
index 992ea0e37257..4465cf05603a 100644
--- a/fs/squashfs/super.c
+++ b/fs/squashfs/super.c
@@ -187,10 +187,15 @@ static int squashfs_fill_super(struct super_block *sb, struct fs_context *fc)
unsigned short flags;
unsigned int fragments;
u64 lookup_table_start, xattr_id_table_start, next_table;
- int err;
+ int err, devblksize = sb_min_blocksize(sb, SQUASHFS_DEVBLK_SIZE);
TRACE("Entered squashfs_fill_superblock\n");
+ if (!devblksize) {
+ errorf(fc, "squashfs: unable to set blocksize\n");
+ return -EINVAL;
+ }
+
sb->s_fs_info = kzalloc(sizeof(*msblk), GFP_KERNEL);
if (sb->s_fs_info == NULL) {
ERROR("Failed to allocate squashfs_sb_info\n");
@@ -201,12 +206,7 @@ static int squashfs_fill_super(struct super_block *sb, struct fs_context *fc)
msblk->panic_on_errors = (opts->errors == Opt_errors_panic);
- msblk->devblksize = sb_min_blocksize(sb, SQUASHFS_DEVBLK_SIZE);
- if (!msblk->devblksize) {
- errorf(fc, "squashfs: unable to set blocksize\n");
- return -EINVAL;
- }
-
+ msblk->devblksize = devblksize;
msblk->devblksize_log2 = ffz(~msblk->devblksize);
mutex_init(&msblk->meta_index_mutex);
diff --git a/include/linux/iov_iter.h b/include/linux/iov_iter.h
index c4aa58032faf..f9a17fbbd398 100644
--- a/include/linux/iov_iter.h
+++ b/include/linux/iov_iter.h
@@ -160,7 +160,7 @@ size_t iterate_folioq(struct iov_iter *iter, size_t len, void *priv, void *priv2
do {
struct folio *folio = folioq_folio(folioq, slot);
- size_t part, remain, consumed;
+ size_t part, remain = 0, consumed;
size_t fsize;
void *base;
@@ -168,14 +168,16 @@ size_t iterate_folioq(struct iov_iter *iter, size_t len, void *priv, void *priv2
break;
fsize = folioq_folio_size(folioq, slot);
- base = kmap_local_folio(folio, skip);
- part = umin(len, PAGE_SIZE - skip % PAGE_SIZE);
- remain = step(base, progress, part, priv, priv2);
- kunmap_local(base);
- consumed = part - remain;
- len -= consumed;
- progress += consumed;
- skip += consumed;
+ if (skip < fsize) {
+ base = kmap_local_folio(folio, skip);
+ part = umin(len, PAGE_SIZE - skip % PAGE_SIZE);
+ remain = step(base, progress, part, priv, priv2);
+ kunmap_local(base);
+ consumed = part - remain;
+ len -= consumed;
+ progress += consumed;
+ skip += consumed;
+ }
if (skip >= fsize) {
skip = 0;
slot++;
diff --git a/include/linux/migrate.h b/include/linux/migrate.h
index acadd41e0b5c..9009e27b5f44 100644
--- a/include/linux/migrate.h
+++ b/include/linux/migrate.h
@@ -79,6 +79,7 @@ void migration_entry_wait_on_locked(swp_entry_t entry, spinlock_t *ptl)
void folio_migrate_flags(struct folio *newfolio, struct folio *folio);
int folio_migrate_mapping(struct address_space *mapping,
struct folio *newfolio, struct folio *folio, int extra_count);
+int set_movable_ops(const struct movable_operations *ops, enum pagetype type);
#else
@@ -100,6 +101,10 @@ static inline int migrate_huge_page_move_mapping(struct address_space *mapping,
{
return -ENOSYS;
}
+static inline int set_movable_ops(const struct movable_operations *ops, enum pagetype type)
+{
+ return -ENOSYS;
+}
#endif /* CONFIG_MIGRATION */
diff --git a/kernel/Kconfig.kexec b/kernel/Kconfig.kexec
index 2ee603a98813..1224dd937df0 100644
--- a/kernel/Kconfig.kexec
+++ b/kernel/Kconfig.kexec
@@ -97,6 +97,7 @@ config KEXEC_JUMP
config KEXEC_HANDOVER
bool "kexec handover"
depends on ARCH_SUPPORTS_KEXEC_HANDOVER && ARCH_SUPPORTS_KEXEC_FILE
+ depends on !DEFERRED_STRUCT_PAGE_INIT
select MEMBLOCK_KHO_SCRATCH
select KEXEC_FILE
select DEBUG_FS
diff --git a/kernel/kexec_handover.c b/kernel/kexec_handover.c
index e49743ae52c5..ecd1ac210dbd 100644
--- a/kernel/kexec_handover.c
+++ b/kernel/kexec_handover.c
@@ -144,14 +144,34 @@ static int __kho_preserve_order(struct kho_mem_track *track, unsigned long pfn,
unsigned int order)
{
struct kho_mem_phys_bits *bits;
- struct kho_mem_phys *physxa;
+ struct kho_mem_phys *physxa, *new_physxa;
const unsigned long pfn_high = pfn >> order;
might_sleep();
- physxa = xa_load_or_alloc(&track->orders, order, sizeof(*physxa));
- if (IS_ERR(physxa))
- return PTR_ERR(physxa);
+ physxa = xa_load(&track->orders, order);
+ if (!physxa) {
+ int err;
+
+ new_physxa = kzalloc(sizeof(*physxa), GFP_KERNEL);
+ if (!new_physxa)
+ return -ENOMEM;
+
+ xa_init(&new_physxa->phys_bits);
+ physxa = xa_cmpxchg(&track->orders, order, NULL, new_physxa,
+ GFP_KERNEL);
+
+ err = xa_err(physxa);
+ if (err || physxa) {
+ xa_destroy(&new_physxa->phys_bits);
+ kfree(new_physxa);
+
+ if (err)
+ return err;
+ } else {
+ physxa = new_physxa;
+ }
+ }
bits = xa_load_or_alloc(&physxa->phys_bits, pfn_high / PRESERVE_BITS,
sizeof(*bits));
@@ -544,6 +564,7 @@ err_free_scratch_areas:
err_free_scratch_desc:
memblock_free(kho_scratch, kho_scratch_cnt * sizeof(*kho_scratch));
err_disable_kho:
+ pr_warn("Failed to reserve scratch area, disabling kexec handover\n");
kho_enable = false;
}
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();
}
diff --git a/tools/include/linux/args.h b/tools/include/linux/args.h
new file mode 100644
index 000000000000..2e8e65d975c7
--- /dev/null
+++ b/tools/include/linux/args.h
@@ -0,0 +1,28 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef _LINUX_ARGS_H
+#define _LINUX_ARGS_H
+
+/*
+ * How do these macros work?
+ *
+ * In __COUNT_ARGS() _0 to _12 are just placeholders from the start
+ * in order to make sure _n is positioned over the correct number
+ * from 12 to 0 (depending on X, which is a variadic argument list).
+ * They serve no purpose other than occupying a position. Since each
+ * macro parameter must have a distinct identifier, those identifiers
+ * are as good as any.
+ *
+ * In COUNT_ARGS() we use actual integers, so __COUNT_ARGS() returns
+ * that as _n.
+ */
+
+/* This counts to 15. Any more, it will return 16th argument. */
+#define __COUNT_ARGS(_0, _1, _2, _3, _4, _5, _6, _7, _8, _9, _10, _11, _12, _13, _14, _15, _n, X...) _n
+#define COUNT_ARGS(X...) __COUNT_ARGS(, ##X, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0)
+
+/* Concatenate two parameters, but allow them to be expanded beforehand. */
+#define __CONCAT(a, b) a ## b
+#define CONCATENATE(a, b) __CONCAT(a, b)
+
+#endif /* _LINUX_ARGS_H */
diff --git a/tools/testing/selftests/damon/Makefile b/tools/testing/selftests/damon/Makefile
index 5b230deb19e8..9a3499827d4b 100644
--- a/tools/testing/selftests/damon/Makefile
+++ b/tools/testing/selftests/damon/Makefile
@@ -4,6 +4,7 @@
TEST_GEN_FILES += access_memory access_memory_even
TEST_FILES = _damon_sysfs.py
+TEST_FILES += drgn_dump_damon_status.py
# functionality tests
TEST_PROGS += sysfs.sh
diff --git a/tools/testing/selftests/mm/mremap_test.c b/tools/testing/selftests/mm/mremap_test.c
index fccf9e797a0c..5bd52a951cbd 100644
--- a/tools/testing/selftests/mm/mremap_test.c
+++ b/tools/testing/selftests/mm/mremap_test.c
@@ -5,10 +5,14 @@
#define _GNU_SOURCE
#include <errno.h>
+#include <fcntl.h>
+#include <linux/userfaultfd.h>
#include <stdlib.h>
#include <stdio.h>
#include <string.h>
+#include <sys/ioctl.h>
#include <sys/mman.h>
+#include <syscall.h>
#include <time.h>
#include <stdbool.h>
@@ -168,6 +172,7 @@ static bool is_range_mapped(FILE *maps_fp, unsigned long start,
if (first_val <= start && second_val >= end) {
success = true;
+ fflush(maps_fp);
break;
}
}
@@ -175,6 +180,15 @@ static bool is_range_mapped(FILE *maps_fp, unsigned long start,
return success;
}
+/* Check if [ptr, ptr + size) mapped in /proc/self/maps. */
+static bool is_ptr_mapped(FILE *maps_fp, void *ptr, unsigned long size)
+{
+ unsigned long start = (unsigned long)ptr;
+ unsigned long end = start + size;
+
+ return is_range_mapped(maps_fp, start, end);
+}
+
/*
* Returns the start address of the mapping on success, else returns
* NULL on failure.
@@ -733,6 +747,249 @@ out:
dont_unmap ? " [dontunnmap]" : "");
}
+#ifdef __NR_userfaultfd
+static void mremap_move_multi_invalid_vmas(FILE *maps_fp,
+ unsigned long page_size)
+{
+ char *test_name = "mremap move multiple invalid vmas";
+ const size_t size = 10 * page_size;
+ bool success = true;
+ char *ptr, *tgt_ptr;
+ int uffd, err, i;
+ void *res;
+ struct uffdio_api api = {
+ .api = UFFD_API,
+ .features = UFFD_EVENT_PAGEFAULT,
+ };
+
+ uffd = syscall(__NR_userfaultfd, O_NONBLOCK);
+ if (uffd == -1) {
+ err = errno;
+ perror("userfaultfd");
+ if (err == EPERM) {
+ ksft_test_result_skip("%s - missing uffd", test_name);
+ return;
+ }
+ success = false;
+ goto out;
+ }
+ if (ioctl(uffd, UFFDIO_API, &api)) {
+ perror("ioctl UFFDIO_API");
+ success = false;
+ goto out_close_uffd;
+ }
+
+ ptr = mmap(NULL, size, PROT_READ | PROT_WRITE,
+ MAP_PRIVATE | MAP_ANON, -1, 0);
+ if (ptr == MAP_FAILED) {
+ perror("mmap");
+ success = false;
+ goto out_close_uffd;
+ }
+
+ tgt_ptr = mmap(NULL, size, PROT_NONE, MAP_PRIVATE | MAP_ANON, -1, 0);
+ if (tgt_ptr == MAP_FAILED) {
+ perror("mmap");
+ success = false;
+ goto out_close_uffd;
+ }
+ if (munmap(tgt_ptr, size)) {
+ perror("munmap");
+ success = false;
+ goto out_unmap;
+ }
+
+ /*
+ * Unmap so we end up with:
+ *
+ * 0 2 4 6 8 10 offset in buffer
+ * |*| |*| |*| |*| |*|
+ * |*| |*| |*| |*| |*|
+ *
+ * Additionally, register each with UFFD.
+ */
+ for (i = 0; i < 10; i += 2) {
+ void *unmap_ptr = &ptr[(i + 1) * page_size];
+ unsigned long start = (unsigned long)&ptr[i * page_size];
+ struct uffdio_register reg = {
+ .range = {
+ .start = start,
+ .len = page_size,
+ },
+ .mode = UFFDIO_REGISTER_MODE_MISSING,
+ };
+
+ if (ioctl(uffd, UFFDIO_REGISTER, &reg) == -1) {
+ perror("ioctl UFFDIO_REGISTER");
+ success = false;
+ goto out_unmap;
+ }
+ if (munmap(unmap_ptr, page_size)) {
+ perror("munmap");
+ success = false;
+ goto out_unmap;
+ }
+ }
+
+ /*
+ * Now try to move the entire range which is invalid for multi VMA move.
+ *
+ * This will fail, and no VMA should be moved, as we check this ahead of
+ * time.
+ */
+ res = mremap(ptr, size, size, MREMAP_MAYMOVE | MREMAP_FIXED, tgt_ptr);
+ err = errno;
+ if (res != MAP_FAILED) {
+ fprintf(stderr, "mremap() succeeded for multi VMA uffd armed\n");
+ success = false;
+ goto out_unmap;
+ }
+ if (err != EFAULT) {
+ errno = err;
+ perror("mrmeap() unexpected error");
+ success = false;
+ goto out_unmap;
+ }
+ if (is_ptr_mapped(maps_fp, tgt_ptr, page_size)) {
+ fprintf(stderr,
+ "Invalid uffd-armed VMA at start of multi range moved\n");
+ success = false;
+ goto out_unmap;
+ }
+
+ /*
+ * Now try to move a single VMA, this should succeed as not multi VMA
+ * move.
+ */
+ res = mremap(ptr, page_size, page_size,
+ MREMAP_MAYMOVE | MREMAP_FIXED, tgt_ptr);
+ if (res == MAP_FAILED) {
+ perror("mremap single invalid-multi VMA");
+ success = false;
+ goto out_unmap;
+ }
+
+ /*
+ * Unmap the VMA, and remap a non-uffd registered (therefore, multi VMA
+ * move valid) VMA at the start of ptr range.
+ */
+ if (munmap(tgt_ptr, page_size)) {
+ perror("munmap");
+ success = false;
+ goto out_unmap;
+ }
+ res = mmap(ptr, page_size, PROT_READ | PROT_WRITE,
+ MAP_PRIVATE | MAP_ANON | MAP_FIXED, -1, 0);
+ if (res == MAP_FAILED) {
+ perror("mmap");
+ success = false;
+ goto out_unmap;
+ }
+
+ /*
+ * Now try to move the entire range, we should succeed in moving the
+ * first VMA, but no others, and report a failure.
+ */
+ res = mremap(ptr, size, size, MREMAP_MAYMOVE | MREMAP_FIXED, tgt_ptr);
+ err = errno;
+ if (res != MAP_FAILED) {
+ fprintf(stderr, "mremap() succeeded for multi VMA uffd armed\n");
+ success = false;
+ goto out_unmap;
+ }
+ if (err != EFAULT) {
+ errno = err;
+ perror("mrmeap() unexpected error");
+ success = false;
+ goto out_unmap;
+ }
+ if (!is_ptr_mapped(maps_fp, tgt_ptr, page_size)) {
+ fprintf(stderr, "Valid VMA not moved\n");
+ success = false;
+ goto out_unmap;
+ }
+
+ /*
+ * Unmap the VMA, and map valid VMA at start of ptr range, and replace
+ * all existing multi-move invalid VMAs, except the last, with valid
+ * multi-move VMAs.
+ */
+ if (munmap(tgt_ptr, page_size)) {
+ perror("munmap");
+ success = false;
+ goto out_unmap;
+ }
+ if (munmap(ptr, size - 2 * page_size)) {
+ perror("munmap");
+ success = false;
+ goto out_unmap;
+ }
+ for (i = 0; i < 8; i += 2) {
+ res = mmap(&ptr[i * page_size], page_size,
+ PROT_READ | PROT_WRITE,
+ MAP_PRIVATE | MAP_ANON | MAP_FIXED, -1, 0);
+ if (res == MAP_FAILED) {
+ perror("mmap");
+ success = false;
+ goto out_unmap;
+ }
+ }
+
+ /*
+ * Now try to move the entire range, we should succeed in moving all but
+ * the last VMA, and report a failure.
+ */
+ res = mremap(ptr, size, size, MREMAP_MAYMOVE | MREMAP_FIXED, tgt_ptr);
+ err = errno;
+ if (res != MAP_FAILED) {
+ fprintf(stderr, "mremap() succeeded for multi VMA uffd armed\n");
+ success = false;
+ goto out_unmap;
+ }
+ if (err != EFAULT) {
+ errno = err;
+ perror("mrmeap() unexpected error");
+ success = false;
+ goto out_unmap;
+ }
+
+ for (i = 0; i < 10; i += 2) {
+ bool is_mapped = is_ptr_mapped(maps_fp,
+ &tgt_ptr[i * page_size], page_size);
+
+ if (i < 8 && !is_mapped) {
+ fprintf(stderr, "Valid VMA not moved at %d\n", i);
+ success = false;
+ goto out_unmap;
+ } else if (i == 8 && is_mapped) {
+ fprintf(stderr, "Invalid VMA moved at %d\n", i);
+ success = false;
+ goto out_unmap;
+ }
+ }
+
+out_unmap:
+ if (munmap(tgt_ptr, size))
+ perror("munmap tgt");
+ if (munmap(ptr, size))
+ perror("munmap src");
+out_close_uffd:
+ close(uffd);
+out:
+ if (success)
+ ksft_test_result_pass("%s\n", test_name);
+ else
+ ksft_test_result_fail("%s\n", test_name);
+}
+#else
+static void mremap_move_multi_invalid_vmas(FILE *maps_fp, unsigned long page_size)
+{
+ char *test_name = "mremap move multiple invalid vmas";
+
+ ksft_test_result_skip("%s - missing uffd", test_name);
+}
+#endif /* __NR_userfaultfd */
+
/* Returns the time taken for the remap on success else returns -1. */
static long long remap_region(struct config c, unsigned int threshold_mb,
char *rand_addr)
@@ -1074,7 +1331,7 @@ int main(int argc, char **argv)
char *rand_addr;
size_t rand_size;
int num_expand_tests = 2;
- int num_misc_tests = 8;
+ int num_misc_tests = 9;
struct test test_cases[MAX_TEST] = {};
struct test perf_test_cases[MAX_PERF_TEST];
int page_size;
@@ -1197,8 +1454,6 @@ int main(int argc, char **argv)
mremap_expand_merge(maps_fp, page_size);
mremap_expand_merge_offset(maps_fp, page_size);
- fclose(maps_fp);
-
mremap_move_within_range(pattern_seed, rand_addr);
mremap_move_1mb_from_start(pattern_seed, rand_addr);
mremap_shrink_multiple_vmas(page_size, /* inplace= */true);
@@ -1207,6 +1462,9 @@ int main(int argc, char **argv)
mremap_move_multiple_vmas(pattern_seed, page_size, /* dontunmap= */ true);
mremap_move_multiple_vmas_split(pattern_seed, page_size, /* dontunmap= */ false);
mremap_move_multiple_vmas_split(pattern_seed, page_size, /* dontunmap= */ true);
+ mremap_move_multi_invalid_vmas(maps_fp, page_size);
+
+ fclose(maps_fp);
if (run_perf_tests) {
ksft_print_msg("\n%s\n",
diff --git a/tools/testing/shared/linux/idr.h b/tools/testing/shared/linux/idr.h
index 4e342f2e37cf..676c5564e33f 100644
--- a/tools/testing/shared/linux/idr.h
+++ b/tools/testing/shared/linux/idr.h
@@ -1 +1,5 @@
+/* Avoid duplicate definitions due to system headers. */
+#ifdef __CONCAT
+#undef __CONCAT
+#endif
#include "../../../../include/linux/idr.h"