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.c23
-rw-r--r--mm/damon/lru_sort.c5
-rw-r--r--mm/damon/reclaim.c5
-rw-r--r--mm/damon/sysfs-schemes.c2
-rw-r--r--mm/damon/sysfs.c14
-rw-r--r--mm/debug_vm_pgtable.c9
-rw-r--r--mm/hugetlb.c9
-rw-r--r--mm/kasan/init.c12
-rw-r--r--mm/kasan/kasan_test_c.c4
-rw-r--r--mm/kasan/shadow.c53
-rw-r--r--mm/khugepaged.c6
-rw-r--r--mm/kmemleak.c37
-rw-r--r--mm/memblock.c19
-rw-r--r--mm/memory-failure.c28
-rw-r--r--mm/memory_hotplug.c10
-rw-r--r--mm/migrate.c38
-rw-r--r--mm/mprotect.c23
-rw-r--r--mm/mremap.c95
-rw-r--r--mm/numa_emulation.c4
-rw-r--r--mm/numa_memblks.c6
-rw-r--r--mm/percpu.c26
-rw-r--r--mm/slub.c37
-rw-r--r--mm/sparse-vmemmap.c11
-rw-r--r--mm/sparse.c15
-rw-r--r--mm/userfaultfd.c26
-rw-r--r--mm/vmalloc.c8
-rw-r--r--mm/vmscan.c4
-rw-r--r--mm/zsmalloc.c10
29 files changed, 364 insertions, 181 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..c2e0b469fd43 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
@@ -2060,8 +2073,8 @@ static void damos_set_effective_quota(struct damos_quota *quota)
if (quota->ms) {
if (quota->total_charged_ns)
- throughput = quota->total_charged_sz * 1000000 /
- quota->total_charged_ns;
+ throughput = mult_frac(quota->total_charged_sz, 1000000,
+ quota->total_charged_ns);
else
throughput = PAGE_SIZE * 1024;
esz = min(throughput * quota->ms, esz);
@@ -2098,6 +2111,10 @@ static void damos_adjust_quota(struct damon_ctx *c, struct damos *s)
if (!quota->ms && !quota->sz && list_empty(&quota->goals))
return;
+ /* First charge window */
+ if (!quota->total_charged_sz && !quota->charged_from)
+ quota->charged_from = jiffies;
+
/* New charge window starts */
if (time_after_eq(jiffies, quota->charged_from +
msecs_to_jiffies(quota->reset_interval))) {
diff --git a/mm/damon/lru_sort.c b/mm/damon/lru_sort.c
index 151a9de5ad8b..b5a5ed16a7a5 100644
--- a/mm/damon/lru_sort.c
+++ b/mm/damon/lru_sort.c
@@ -198,6 +198,11 @@ static int damon_lru_sort_apply_parameters(void)
if (err)
return err;
+ if (!damon_lru_sort_mon_attrs.sample_interval) {
+ err = -EINVAL;
+ goto out;
+ }
+
err = damon_set_attrs(ctx, &damon_lru_sort_mon_attrs);
if (err)
goto out;
diff --git a/mm/damon/reclaim.c b/mm/damon/reclaim.c
index 3c71b4596676..fb7c982a0018 100644
--- a/mm/damon/reclaim.c
+++ b/mm/damon/reclaim.c
@@ -194,6 +194,11 @@ static int damon_reclaim_apply_parameters(void)
if (err)
return err;
+ if (!damon_reclaim_mon_attrs.aggr_interval) {
+ err = -EINVAL;
+ goto out;
+ }
+
err = damon_set_attrs(param_ctx, &damon_reclaim_mon_attrs);
if (err)
goto out;
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/damon/sysfs.c b/mm/damon/sysfs.c
index 6d2b0dab50cb..7b9254cadd5f 100644
--- a/mm/damon/sysfs.c
+++ b/mm/damon/sysfs.c
@@ -1260,14 +1260,18 @@ static ssize_t state_show(struct kobject *kobj, struct kobj_attribute *attr,
{
struct damon_sysfs_kdamond *kdamond = container_of(kobj,
struct damon_sysfs_kdamond, kobj);
- struct damon_ctx *ctx = kdamond->damon_ctx;
- bool running;
+ struct damon_ctx *ctx;
+ bool running = false;
- if (!ctx)
- running = false;
- else
+ if (!mutex_trylock(&damon_sysfs_lock))
+ return -EBUSY;
+
+ ctx = kdamond->damon_ctx;
+ if (ctx)
running = damon_is_running(ctx);
+ mutex_unlock(&damon_sysfs_lock);
+
return sysfs_emit(buf, "%s\n", running ?
damon_sysfs_cmd_strs[DAMON_SYSFS_CMD_ON] :
damon_sysfs_cmd_strs[DAMON_SYSFS_CMD_OFF]);
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/hugetlb.c b/mm/hugetlb.c
index 753f99b4c718..eed59cfb5d21 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -5851,7 +5851,7 @@ void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma,
spinlock_t *ptl;
struct hstate *h = hstate_vma(vma);
unsigned long sz = huge_page_size(h);
- bool adjust_reservation = false;
+ bool adjust_reservation;
unsigned long last_addr_mask;
bool force_flush = false;
@@ -5944,6 +5944,7 @@ void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma,
sz);
hugetlb_count_sub(pages_per_huge_page(h), mm);
hugetlb_remove_rmap(folio);
+ spin_unlock(ptl);
/*
* Restore the reservation for anonymous page, otherwise the
@@ -5951,14 +5952,16 @@ void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma,
* If there we are freeing a surplus, do not set the restore
* reservation bit.
*/
+ adjust_reservation = false;
+
+ spin_lock_irq(&hugetlb_lock);
if (!h->surplus_huge_pages && __vma_private_lock(vma) &&
folio_test_anon(folio)) {
folio_set_hugetlb_restore_reserve(folio);
/* Reservation to be adjusted after the spin lock */
adjust_reservation = true;
}
-
- spin_unlock(ptl);
+ spin_unlock_irq(&hugetlb_lock);
/*
* Adjust the reservation for the region that will have the
diff --git a/mm/kasan/init.c b/mm/kasan/init.c
index ced6b29fcf76..8fce3370c84e 100644
--- a/mm/kasan/init.c
+++ b/mm/kasan/init.c
@@ -13,9 +13,9 @@
#include <linux/mm.h>
#include <linux/pfn.h>
#include <linux/slab.h>
+#include <linux/pgalloc.h>
#include <asm/page.h>
-#include <asm/pgalloc.h>
#include "kasan.h"
@@ -191,7 +191,7 @@ static int __ref zero_p4d_populate(pgd_t *pgd, unsigned long addr,
pud_t *pud;
pmd_t *pmd;
- p4d_populate(&init_mm, p4d,
+ p4d_populate_kernel(addr, p4d,
lm_alias(kasan_early_shadow_pud));
pud = pud_offset(p4d, addr);
pud_populate(&init_mm, pud,
@@ -212,7 +212,7 @@ static int __ref zero_p4d_populate(pgd_t *pgd, unsigned long addr,
} else {
p = early_alloc(PAGE_SIZE, NUMA_NO_NODE);
pud_init(p);
- p4d_populate(&init_mm, p4d, p);
+ p4d_populate_kernel(addr, p4d, p);
}
}
zero_pud_populate(p4d, addr, next);
@@ -251,10 +251,10 @@ int __ref kasan_populate_early_shadow(const void *shadow_start,
* puds,pmds, so pgd_populate(), pud_populate()
* is noops.
*/
- pgd_populate(&init_mm, pgd,
+ pgd_populate_kernel(addr, pgd,
lm_alias(kasan_early_shadow_p4d));
p4d = p4d_offset(pgd, addr);
- p4d_populate(&init_mm, p4d,
+ p4d_populate_kernel(addr, p4d,
lm_alias(kasan_early_shadow_pud));
pud = pud_offset(p4d, addr);
pud_populate(&init_mm, pud,
@@ -273,7 +273,7 @@ int __ref kasan_populate_early_shadow(const void *shadow_start,
if (!p)
return -ENOMEM;
} else {
- pgd_populate(&init_mm, pgd,
+ pgd_populate_kernel(addr, pgd,
early_alloc(PAGE_SIZE, NUMA_NO_NODE));
}
}
diff --git a/mm/kasan/kasan_test_c.c b/mm/kasan/kasan_test_c.c
index 2aa12dfa427a..f4b17984b627 100644
--- a/mm/kasan/kasan_test_c.c
+++ b/mm/kasan/kasan_test_c.c
@@ -47,7 +47,7 @@ static struct {
* Some tests use these global variables to store return values from function
* calls that could otherwise be eliminated by the compiler as dead code.
*/
-static volatile void *kasan_ptr_result;
+static void *volatile kasan_ptr_result;
static volatile int kasan_int_result;
/* Probe for console output: obtains test_status lines of interest. */
@@ -1578,9 +1578,11 @@ static void kasan_strings(struct kunit *test)
ptr = kmalloc(size, GFP_KERNEL | __GFP_ZERO);
KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ptr);
+ OPTIMIZER_HIDE_VAR(ptr);
src = kmalloc(KASAN_GRANULE_SIZE, GFP_KERNEL | __GFP_ZERO);
strscpy(src, "f0cacc1a0000000", KASAN_GRANULE_SIZE);
+ OPTIMIZER_HIDE_VAR(src);
/*
* Make sure that strscpy() does not trigger KASAN if it overreads into
diff --git a/mm/kasan/shadow.c b/mm/kasan/shadow.c
index d2c70cd2afb1..11d472a5c4e8 100644
--- a/mm/kasan/shadow.c
+++ b/mm/kasan/shadow.c
@@ -305,8 +305,7 @@ static int kasan_populate_vmalloc_pte(pte_t *ptep, unsigned long addr,
pte_t pte;
int index;
- if (likely(!pte_none(ptep_get(ptep))))
- return 0;
+ arch_leave_lazy_mmu_mode();
index = PFN_DOWN(addr - data->start);
page = data->pages[index];
@@ -320,6 +319,8 @@ static int kasan_populate_vmalloc_pte(pte_t *ptep, unsigned long addr,
}
spin_unlock(&init_mm.page_table_lock);
+ arch_enter_lazy_mmu_mode();
+
return 0;
}
@@ -335,13 +336,13 @@ static void ___free_pages_bulk(struct page **pages, int nr_pages)
}
}
-static int ___alloc_pages_bulk(struct page **pages, int nr_pages)
+static int ___alloc_pages_bulk(struct page **pages, int nr_pages, gfp_t gfp_mask)
{
unsigned long nr_populated, nr_total = nr_pages;
struct page **page_array = pages;
while (nr_pages) {
- nr_populated = alloc_pages_bulk(GFP_KERNEL, nr_pages, pages);
+ nr_populated = alloc_pages_bulk(gfp_mask, nr_pages, pages);
if (!nr_populated) {
___free_pages_bulk(page_array, nr_total - nr_pages);
return -ENOMEM;
@@ -353,25 +354,42 @@ static int ___alloc_pages_bulk(struct page **pages, int nr_pages)
return 0;
}
-static int __kasan_populate_vmalloc(unsigned long start, unsigned long end)
+static int __kasan_populate_vmalloc(unsigned long start, unsigned long end, gfp_t gfp_mask)
{
unsigned long nr_pages, nr_total = PFN_UP(end - start);
struct vmalloc_populate_data data;
+ unsigned int flags;
int ret = 0;
- data.pages = (struct page **)__get_free_page(GFP_KERNEL | __GFP_ZERO);
+ data.pages = (struct page **)__get_free_page(gfp_mask | __GFP_ZERO);
if (!data.pages)
return -ENOMEM;
while (nr_total) {
nr_pages = min(nr_total, PAGE_SIZE / sizeof(data.pages[0]));
- ret = ___alloc_pages_bulk(data.pages, nr_pages);
+ ret = ___alloc_pages_bulk(data.pages, nr_pages, gfp_mask);
if (ret)
break;
data.start = start;
+
+ /*
+ * page tables allocations ignore external gfp mask, enforce it
+ * by the scope API
+ */
+ if ((gfp_mask & (__GFP_FS | __GFP_IO)) == __GFP_IO)
+ flags = memalloc_nofs_save();
+ else if ((gfp_mask & (__GFP_FS | __GFP_IO)) == 0)
+ flags = memalloc_noio_save();
+
ret = apply_to_page_range(&init_mm, start, nr_pages * PAGE_SIZE,
kasan_populate_vmalloc_pte, &data);
+
+ if ((gfp_mask & (__GFP_FS | __GFP_IO)) == __GFP_IO)
+ memalloc_nofs_restore(flags);
+ else if ((gfp_mask & (__GFP_FS | __GFP_IO)) == 0)
+ memalloc_noio_restore(flags);
+
___free_pages_bulk(data.pages, nr_pages);
if (ret)
break;
@@ -385,7 +403,7 @@ static int __kasan_populate_vmalloc(unsigned long start, unsigned long end)
return ret;
}
-int kasan_populate_vmalloc(unsigned long addr, unsigned long size)
+int kasan_populate_vmalloc(unsigned long addr, unsigned long size, gfp_t gfp_mask)
{
unsigned long shadow_start, shadow_end;
int ret;
@@ -414,7 +432,7 @@ int kasan_populate_vmalloc(unsigned long addr, unsigned long size)
shadow_start = PAGE_ALIGN_DOWN(shadow_start);
shadow_end = PAGE_ALIGN(shadow_end);
- ret = __kasan_populate_vmalloc(shadow_start, shadow_end);
+ ret = __kasan_populate_vmalloc(shadow_start, shadow_end, gfp_mask);
if (ret)
return ret;
@@ -461,18 +479,23 @@ int kasan_populate_vmalloc(unsigned long addr, unsigned long size)
static int kasan_depopulate_vmalloc_pte(pte_t *ptep, unsigned long addr,
void *unused)
{
- unsigned long page;
+ pte_t pte;
+ int none;
- page = (unsigned long)__va(pte_pfn(ptep_get(ptep)) << PAGE_SHIFT);
+ arch_leave_lazy_mmu_mode();
spin_lock(&init_mm.page_table_lock);
-
- if (likely(!pte_none(ptep_get(ptep)))) {
+ pte = ptep_get(ptep);
+ none = pte_none(pte);
+ if (likely(!none))
pte_clear(&init_mm, addr, ptep);
- free_page(page);
- }
spin_unlock(&init_mm.page_table_lock);
+ if (likely(!none))
+ __free_page(pfn_to_page(pte_pfn(pte)));
+
+ arch_enter_lazy_mmu_mode();
+
return 0;
}
diff --git a/mm/khugepaged.c b/mm/khugepaged.c
index 374a6a5193a7..b486c1d19b2d 100644
--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -1172,11 +1172,11 @@ static int collapse_huge_page(struct mm_struct *mm, unsigned long address,
if (result != SCAN_SUCCEED)
goto out_up_write;
/* check if the pmd is still valid */
+ vma_start_write(vma);
result = check_pmd_still_valid(mm, address, pmd);
if (result != SCAN_SUCCEED)
goto out_up_write;
- vma_start_write(vma);
anon_vma_lock_write(vma->anon_vma);
mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, mm, address,
@@ -1417,8 +1417,8 @@ static int hpage_collapse_scan_pmd(struct mm_struct *mm,
*/
if (cc->is_khugepaged &&
(pte_young(pteval) || folio_test_young(folio) ||
- folio_test_referenced(folio) || mmu_notifier_test_young(vma->vm_mm,
- address)))
+ folio_test_referenced(folio) ||
+ mmu_notifier_test_young(vma->vm_mm, _address)))
referenced++;
}
if (!writable) {
diff --git a/mm/kmemleak.c b/mm/kmemleak.c
index 8d588e685311..1ac56ceb29b6 100644
--- a/mm/kmemleak.c
+++ b/mm/kmemleak.c
@@ -437,9 +437,15 @@ static struct kmemleak_object *__lookup_object(unsigned long ptr, int alias,
else if (untagged_objp == untagged_ptr || alias)
return object;
else {
+ /*
+ * Printk deferring due to the kmemleak_lock held.
+ * This is done to avoid deadlock.
+ */
+ printk_deferred_enter();
kmemleak_warn("Found object by alias at 0x%08lx\n",
ptr);
dump_object_info(object);
+ printk_deferred_exit();
break;
}
}
@@ -470,6 +476,7 @@ static struct kmemleak_object *mem_pool_alloc(gfp_t gfp)
{
unsigned long flags;
struct kmemleak_object *object;
+ bool warn = false;
/* try the slab allocator first */
if (object_cache) {
@@ -488,8 +495,10 @@ static struct kmemleak_object *mem_pool_alloc(gfp_t gfp)
else if (mem_pool_free_count)
object = &mem_pool[--mem_pool_free_count];
else
- pr_warn_once("Memory pool empty, consider increasing CONFIG_DEBUG_KMEMLEAK_MEM_POOL_SIZE\n");
+ warn = true;
raw_spin_unlock_irqrestore(&kmemleak_lock, flags);
+ if (warn)
+ pr_warn_once("Memory pool empty, consider increasing CONFIG_DEBUG_KMEMLEAK_MEM_POOL_SIZE\n");
return object;
}
@@ -733,6 +742,11 @@ static int __link_object(struct kmemleak_object *object, unsigned long ptr,
else if (untagged_objp + parent->size <= untagged_ptr)
link = &parent->rb_node.rb_right;
else {
+ /*
+ * Printk deferring due to the kmemleak_lock held.
+ * This is done to avoid deadlock.
+ */
+ printk_deferred_enter();
kmemleak_stop("Cannot insert 0x%lx into the object search tree (overlaps existing)\n",
ptr);
/*
@@ -740,6 +754,7 @@ static int __link_object(struct kmemleak_object *object, unsigned long ptr,
* be freed while the kmemleak_lock is held.
*/
dump_object_info(parent);
+ printk_deferred_exit();
return -EEXIST;
}
}
@@ -853,13 +868,8 @@ static void delete_object_part(unsigned long ptr, size_t size,
raw_spin_lock_irqsave(&kmemleak_lock, flags);
object = __find_and_remove_object(ptr, 1, objflags);
- if (!object) {
-#ifdef DEBUG
- kmemleak_warn("Partially freeing unknown object at 0x%08lx (size %zu)\n",
- ptr, size);
-#endif
+ if (!object)
goto unlock;
- }
/*
* Create one or two objects that may result from the memory block
@@ -879,8 +889,14 @@ static void delete_object_part(unsigned long ptr, size_t size,
unlock:
raw_spin_unlock_irqrestore(&kmemleak_lock, flags);
- if (object)
+ if (object) {
__delete_object(object);
+ } else {
+#ifdef DEBUG
+ kmemleak_warn("Partially freeing unknown object at 0x%08lx (size %zu)\n",
+ ptr, size);
+#endif
+ }
out:
if (object_l)
@@ -2181,6 +2197,7 @@ static const struct file_operations kmemleak_fops = {
static void __kmemleak_do_cleanup(void)
{
struct kmemleak_object *object, *tmp;
+ unsigned int cnt = 0;
/*
* Kmemleak has already been disabled, no need for RCU list traversal
@@ -2189,6 +2206,10 @@ static void __kmemleak_do_cleanup(void)
list_for_each_entry_safe(object, tmp, &object_list, object_list) {
__remove_object(object);
__delete_object(object);
+
+ /* Call cond_resched() once per 64 iterations to avoid soft lockup */
+ if (!(++cnt & 0x3f))
+ cond_resched();
}
}
diff --git a/mm/memblock.c b/mm/memblock.c
index 154f1d73b61f..117d963e677c 100644
--- a/mm/memblock.c
+++ b/mm/memblock.c
@@ -780,9 +780,9 @@ bool __init_memblock memblock_validate_numa_coverage(unsigned long threshold_byt
}
if ((nr_pages << PAGE_SHIFT) > threshold_bytes) {
- mem_size_mb = memblock_phys_mem_size() >> 20;
+ mem_size_mb = memblock_phys_mem_size() / SZ_1M;
pr_err("NUMA: no nodes coverage for %luMB of %luMB RAM\n",
- (nr_pages << PAGE_SHIFT) >> 20, mem_size_mb);
+ (nr_pages << PAGE_SHIFT) / SZ_1M, mem_size_mb);
return false;
}
@@ -1091,13 +1091,20 @@ int __init_memblock memblock_clear_nomap(phys_addr_t base, phys_addr_t size)
/**
* memblock_reserved_mark_noinit - Mark a reserved memory region with flag
- * MEMBLOCK_RSRV_NOINIT which results in the struct pages not being initialized
- * for this region.
+ * MEMBLOCK_RSRV_NOINIT
+ *
* @base: the base phys addr of the region
* @size: the size of the region
*
- * struct pages will not be initialized for reserved memory regions marked with
- * %MEMBLOCK_RSRV_NOINIT.
+ * The struct pages for the reserved regions marked %MEMBLOCK_RSRV_NOINIT will
+ * not be fully initialized to allow the caller optimize their initialization.
+ *
+ * When %CONFIG_DEFERRED_STRUCT_PAGE_INIT is enabled, setting this flag
+ * completely bypasses the initialization of struct pages for such region.
+ *
+ * When %CONFIG_DEFERRED_STRUCT_PAGE_INIT is disabled, struct pages in this
+ * region will be initialized with default values but won't be marked as
+ * reserved.
*
* Return: 0 on success, -errno on failure.
*/
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index e2e685b971bb..df6ee59527dd 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,
};
@@ -948,7 +956,7 @@ static const char * const action_page_types[] = {
[MF_MSG_BUDDY] = "free buddy page",
[MF_MSG_DAX] = "dax page",
[MF_MSG_UNSPLIT_THP] = "unsplit thp",
- [MF_MSG_ALREADY_POISONED] = "already poisoned",
+ [MF_MSG_ALREADY_POISONED] = "already poisoned page",
[MF_MSG_UNKNOWN] = "unknown page",
};
@@ -1341,9 +1349,10 @@ static int action_result(unsigned long pfn, enum mf_action_page_type type,
{
trace_memory_failure_event(pfn, type, result);
- num_poisoned_pages_inc(pfn);
-
- update_per_node_mf_stats(pfn, result);
+ if (type != MF_MSG_ALREADY_POISONED) {
+ num_poisoned_pages_inc(pfn);
+ update_per_node_mf_stats(pfn, result);
+ }
pr_err("%#lx: recovery action for %s: %s\n",
pfn, action_page_types[type], action_name[result]);
@@ -2086,12 +2095,11 @@ retry:
*hugetlb = 0;
return 0;
} else if (res == -EHWPOISON) {
- pr_err("%#lx: already hardware poisoned\n", pfn);
if (flags & MF_ACTION_REQUIRED) {
folio = page_folio(p);
res = kill_accessing_process(current, folio_pfn(folio), flags);
- action_result(pfn, MF_MSG_ALREADY_POISONED, MF_FAILED);
}
+ action_result(pfn, MF_MSG_ALREADY_POISONED, MF_FAILED);
return res;
} else if (res == -EBUSY) {
if (!(flags & MF_NO_RETRY)) {
@@ -2277,7 +2285,6 @@ try_again:
goto unlock_mutex;
if (TestSetPageHWPoison(p)) {
- pr_err("%#lx: already hardware poisoned\n", pfn);
res = -EHWPOISON;
if (flags & MF_ACTION_REQUIRED)
res = kill_accessing_process(current, pfn, flags);
@@ -2561,10 +2568,9 @@ int unpoison_memory(unsigned long pfn)
static DEFINE_RATELIMIT_STATE(unpoison_rs, DEFAULT_RATELIMIT_INTERVAL,
DEFAULT_RATELIMIT_BURST);
- if (!pfn_valid(pfn))
- return -ENXIO;
-
- p = pfn_to_page(pfn);
+ p = pfn_to_online_page(pfn);
+ if (!p)
+ return -EIO;
folio = page_folio(p);
mutex_lock(&mf_mutex);
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 1f15af712bc3..74318c787715 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -1815,8 +1815,14 @@ static void do_migrate_range(unsigned long start_pfn, unsigned long end_pfn)
pfn = folio_pfn(folio) + folio_nr_pages(folio) - 1;
if (folio_contain_hwpoisoned_page(folio)) {
- if (WARN_ON(folio_test_lru(folio)))
- folio_isolate_lru(folio);
+ /*
+ * unmap_poisoned_folio() cannot handle large folios
+ * in all cases yet.
+ */
+ if (folio_test_large(folio) && !folio_test_hugetlb(folio))
+ goto put_folio;
+ if (folio_test_lru(folio) && !folio_isolate_lru(folio))
+ goto put_folio;
if (folio_mapped(folio)) {
folio_lock(folio);
unmap_poisoned_folio(folio, pfn, false);
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/mprotect.c b/mm/mprotect.c
index 78bded7acf79..113b48985834 100644
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -120,9 +120,8 @@ static int mprotect_folio_pte_batch(struct folio *folio, pte_t *ptep,
static bool prot_numa_skip(struct vm_area_struct *vma, unsigned long addr,
pte_t oldpte, pte_t *pte, int target_node,
- struct folio **foliop)
+ struct folio *folio)
{
- struct folio *folio = NULL;
bool ret = true;
bool toptier;
int nid;
@@ -131,7 +130,6 @@ static bool prot_numa_skip(struct vm_area_struct *vma, unsigned long addr,
if (pte_protnone(oldpte))
goto skip;
- folio = vm_normal_folio(vma, addr, oldpte);
if (!folio)
goto skip;
@@ -173,7 +171,6 @@ static bool prot_numa_skip(struct vm_area_struct *vma, unsigned long addr,
folio_xchg_access_time(folio, jiffies_to_msecs(jiffies));
skip:
- *foliop = folio;
return ret;
}
@@ -231,10 +228,9 @@ static int page_anon_exclusive_sub_batch(int start_idx, int max_len,
* retrieve sub-batches.
*/
static void commit_anon_folio_batch(struct vm_area_struct *vma,
- struct folio *folio, unsigned long addr, pte_t *ptep,
+ struct folio *folio, struct page *first_page, unsigned long addr, pte_t *ptep,
pte_t oldpte, pte_t ptent, int nr_ptes, struct mmu_gather *tlb)
{
- struct page *first_page = folio_page(folio, 0);
bool expected_anon_exclusive;
int sub_batch_idx = 0;
int len;
@@ -251,7 +247,7 @@ static void commit_anon_folio_batch(struct vm_area_struct *vma,
}
static void set_write_prot_commit_flush_ptes(struct vm_area_struct *vma,
- struct folio *folio, unsigned long addr, pte_t *ptep,
+ struct folio *folio, struct page *page, unsigned long addr, pte_t *ptep,
pte_t oldpte, pte_t ptent, int nr_ptes, struct mmu_gather *tlb)
{
bool set_write;
@@ -270,7 +266,7 @@ static void set_write_prot_commit_flush_ptes(struct vm_area_struct *vma,
/* idx = */ 0, set_write, tlb);
return;
}
- commit_anon_folio_batch(vma, folio, addr, ptep, oldpte, ptent, nr_ptes, tlb);
+ commit_anon_folio_batch(vma, folio, page, addr, ptep, oldpte, ptent, nr_ptes, tlb);
}
static long change_pte_range(struct mmu_gather *tlb,
@@ -305,15 +301,19 @@ static long change_pte_range(struct mmu_gather *tlb,
const fpb_t flags = FPB_RESPECT_SOFT_DIRTY | FPB_RESPECT_WRITE;
int max_nr_ptes = (end - addr) >> PAGE_SHIFT;
struct folio *folio = NULL;
+ struct page *page;
pte_t ptent;
+ page = vm_normal_page(vma, addr, oldpte);
+ if (page)
+ folio = page_folio(page);
/*
* Avoid trapping faults against the zero or KSM
* pages. See similar comment in change_huge_pmd.
*/
if (prot_numa) {
int ret = prot_numa_skip(vma, addr, oldpte, pte,
- target_node, &folio);
+ target_node, folio);
if (ret) {
/* determine batch to skip */
@@ -323,9 +323,6 @@ static long change_pte_range(struct mmu_gather *tlb,
}
}
- if (!folio)
- folio = vm_normal_folio(vma, addr, oldpte);
-
nr_ptes = mprotect_folio_pte_batch(folio, pte, oldpte, max_nr_ptes, flags);
oldpte = modify_prot_start_ptes(vma, addr, pte, nr_ptes);
@@ -351,7 +348,7 @@ static long change_pte_range(struct mmu_gather *tlb,
*/
if ((cp_flags & MM_CP_TRY_CHANGE_WRITABLE) &&
!pte_write(ptent))
- set_write_prot_commit_flush_ptes(vma, folio,
+ set_write_prot_commit_flush_ptes(vma, folio, page,
addr, pte, oldpte, ptent, nr_ptes, tlb);
else
prot_commit_flush_ptes(vma, addr, pte, oldpte, ptent,
diff --git a/mm/mremap.c b/mm/mremap.c
index 677a4d744df9..35de0a7b910e 100644
--- a/mm/mremap.c
+++ b/mm/mremap.c
@@ -179,6 +179,10 @@ static int mremap_folio_pte_batch(struct vm_area_struct *vma, unsigned long addr
if (max_nr == 1)
return 1;
+ /* Avoid expensive folio lookup if we stand no chance of benefit. */
+ if (pte_batch_hint(ptep, pte) == 1)
+ return 1;
+
folio = vm_normal_folio(vma, addr, pte);
if (!folio || !folio_test_large(folio))
return 1;
@@ -319,6 +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)
@@ -331,6 +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.
@@ -357,15 +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.
@@ -414,6 +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.
@@ -421,15 +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.
@@ -1616,7 +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
@@ -1629,15 +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)
@@ -1763,15 +1774,18 @@ static unsigned long check_mremap_params(struct vma_remap_struct *vrm)
if (!vrm->new_len)
return -EINVAL;
- /* Is the new length or address silly? */
- if (vrm->new_len > TASK_SIZE ||
- vrm->new_addr > TASK_SIZE - vrm->new_len)
+ /* Is the new length silly? */
+ if (vrm->new_len > TASK_SIZE)
return -EINVAL;
/* Remainder of checks are for cases with specific new_addr. */
if (!vrm_implies_new_addr(vrm))
return 0;
+ /* Is the new address silly? */
+ if (vrm->new_addr > TASK_SIZE - vrm->new_len)
+ return -EINVAL;
+
/* The new address must be page-aligned. */
if (offset_in_page(vrm->new_addr))
return -EINVAL;
@@ -1814,10 +1828,11 @@ 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);
/*
@@ -1830,9 +1845,7 @@ 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)
@@ -1861,9 +1874,15 @@ 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)
@@ -1872,7 +1891,7 @@ 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/numa_emulation.c b/mm/numa_emulation.c
index 9d55679d99ce..703c8fa05048 100644
--- a/mm/numa_emulation.c
+++ b/mm/numa_emulation.c
@@ -73,7 +73,7 @@ static int __init emu_setup_memblk(struct numa_meminfo *ei,
}
printk(KERN_INFO "Faking node %d at [mem %#018Lx-%#018Lx] (%LuMB)\n",
- nid, eb->start, eb->end - 1, (eb->end - eb->start) >> 20);
+ nid, eb->start, eb->end - 1, (eb->end - eb->start) / SZ_1M);
return 0;
}
@@ -264,7 +264,7 @@ static int __init split_nodes_size_interleave_uniform(struct numa_meminfo *ei,
min_size = ALIGN(max(min_size, FAKE_NODE_MIN_SIZE), FAKE_NODE_MIN_SIZE);
if (size < min_size) {
pr_err("Fake node size %LuMB too small, increasing to %LuMB\n",
- size >> 20, min_size >> 20);
+ size / SZ_1M, min_size / SZ_1M);
size = min_size;
}
size = ALIGN_DOWN(size, FAKE_NODE_MIN_SIZE);
diff --git a/mm/numa_memblks.c b/mm/numa_memblks.c
index 541a99c4071a..5b009a9cd8b4 100644
--- a/mm/numa_memblks.c
+++ b/mm/numa_memblks.c
@@ -76,7 +76,7 @@ static int __init numa_alloc_distance(void)
for (j = 0; j < cnt; j++)
numa_distance[i * cnt + j] = i == j ?
LOCAL_DISTANCE : REMOTE_DISTANCE;
- printk(KERN_DEBUG "NUMA: Initialized distance table, cnt=%d\n", cnt);
+ pr_debug("NUMA: Initialized distance table, cnt=%d\n", cnt);
return 0;
}
@@ -427,9 +427,9 @@ static int __init numa_register_meminfo(struct numa_meminfo *mi)
unsigned long pfn_align = node_map_pfn_alignment();
if (pfn_align && pfn_align < PAGES_PER_SECTION) {
- unsigned long node_align_mb = PFN_PHYS(pfn_align) >> 20;
+ unsigned long node_align_mb = PFN_PHYS(pfn_align) / SZ_1M;
- unsigned long sect_align_mb = PFN_PHYS(PAGES_PER_SECTION) >> 20;
+ unsigned long sect_align_mb = PFN_PHYS(PAGES_PER_SECTION) / SZ_1M;
pr_warn("Node alignment %luMB < min %luMB, rejecting NUMA config\n",
node_align_mb, sect_align_mb);
diff --git a/mm/percpu.c b/mm/percpu.c
index d9cbaee92b60..81462ce5866e 100644
--- a/mm/percpu.c
+++ b/mm/percpu.c
@@ -1734,7 +1734,7 @@ void __percpu *pcpu_alloc_noprof(size_t size, size_t align, bool reserved,
bool is_atomic;
bool do_warn;
struct obj_cgroup *objcg = NULL;
- static int warn_limit = 10;
+ static atomic_t warn_limit = ATOMIC_INIT(10);
struct pcpu_chunk *chunk, *next;
const char *err;
int slot, off, cpu, ret;
@@ -1904,13 +1904,17 @@ fail_unlock:
fail:
trace_percpu_alloc_percpu_fail(reserved, is_atomic, size, align);
- if (do_warn && warn_limit) {
- pr_warn("allocation failed, size=%zu align=%zu atomic=%d, %s\n",
- size, align, is_atomic, err);
- if (!is_atomic)
- dump_stack();
- if (!--warn_limit)
- pr_info("limit reached, disable warning\n");
+ if (do_warn) {
+ int remaining = atomic_dec_if_positive(&warn_limit);
+
+ if (remaining >= 0) {
+ pr_warn("allocation failed, size=%zu align=%zu atomic=%d, %s\n",
+ size, align, is_atomic, err);
+ if (!is_atomic)
+ dump_stack();
+ if (remaining == 0)
+ pr_info("limit reached, disable warning\n");
+ }
}
if (is_atomic) {
@@ -3108,7 +3112,7 @@ out_free:
#endif /* BUILD_EMBED_FIRST_CHUNK */
#ifdef BUILD_PAGE_FIRST_CHUNK
-#include <asm/pgalloc.h>
+#include <linux/pgalloc.h>
#ifndef P4D_TABLE_SIZE
#define P4D_TABLE_SIZE PAGE_SIZE
@@ -3134,13 +3138,13 @@ void __init __weak pcpu_populate_pte(unsigned long addr)
if (pgd_none(*pgd)) {
p4d = memblock_alloc_or_panic(P4D_TABLE_SIZE, P4D_TABLE_SIZE);
- pgd_populate(&init_mm, pgd, p4d);
+ pgd_populate_kernel(addr, pgd, p4d);
}
p4d = p4d_offset(pgd, addr);
if (p4d_none(*p4d)) {
pud = memblock_alloc_or_panic(PUD_TABLE_SIZE, PUD_TABLE_SIZE);
- p4d_populate(&init_mm, p4d, pud);
+ p4d_populate_kernel(addr, p4d, pud);
}
pud = pud_offset(p4d, addr);
diff --git a/mm/slub.c b/mm/slub.c
index 30003763d224..d257141896c9 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -962,19 +962,19 @@ static struct track *get_track(struct kmem_cache *s, void *object,
}
#ifdef CONFIG_STACKDEPOT
-static noinline depot_stack_handle_t set_track_prepare(void)
+static noinline depot_stack_handle_t set_track_prepare(gfp_t gfp_flags)
{
depot_stack_handle_t handle;
unsigned long entries[TRACK_ADDRS_COUNT];
unsigned int nr_entries;
nr_entries = stack_trace_save(entries, ARRAY_SIZE(entries), 3);
- handle = stack_depot_save(entries, nr_entries, GFP_NOWAIT);
+ handle = stack_depot_save(entries, nr_entries, gfp_flags);
return handle;
}
#else
-static inline depot_stack_handle_t set_track_prepare(void)
+static inline depot_stack_handle_t set_track_prepare(gfp_t gfp_flags)
{
return 0;
}
@@ -996,9 +996,9 @@ static void set_track_update(struct kmem_cache *s, void *object,
}
static __always_inline void set_track(struct kmem_cache *s, void *object,
- enum track_item alloc, unsigned long addr)
+ enum track_item alloc, unsigned long addr, gfp_t gfp_flags)
{
- depot_stack_handle_t handle = set_track_prepare();
+ depot_stack_handle_t handle = set_track_prepare(gfp_flags);
set_track_update(s, object, alloc, addr, handle);
}
@@ -1140,7 +1140,12 @@ static void object_err(struct kmem_cache *s, struct slab *slab,
return;
slab_bug(s, reason);
- print_trailer(s, slab, object);
+ if (!object || !check_valid_pointer(s, slab, object)) {
+ print_slab_info(slab);
+ pr_err("Invalid pointer 0x%p\n", object);
+ } else {
+ print_trailer(s, slab, object);
+ }
add_taint(TAINT_BAD_PAGE, LOCKDEP_NOW_UNRELIABLE);
WARN_ON(1);
@@ -1921,9 +1926,9 @@ static inline bool free_debug_processing(struct kmem_cache *s,
static inline void slab_pad_check(struct kmem_cache *s, struct slab *slab) {}
static inline int check_object(struct kmem_cache *s, struct slab *slab,
void *object, u8 val) { return 1; }
-static inline depot_stack_handle_t set_track_prepare(void) { return 0; }
+static inline depot_stack_handle_t set_track_prepare(gfp_t gfp_flags) { return 0; }
static inline void set_track(struct kmem_cache *s, void *object,
- enum track_item alloc, unsigned long addr) {}
+ enum track_item alloc, unsigned long addr, gfp_t gfp_flags) {}
static inline void add_full(struct kmem_cache *s, struct kmem_cache_node *n,
struct slab *slab) {}
static inline void remove_full(struct kmem_cache *s, struct kmem_cache_node *n,
@@ -3876,9 +3881,14 @@ new_objects:
* For debug caches here we had to go through
* alloc_single_from_partial() so just store the
* tracking info and return the object.
+ *
+ * Due to disabled preemption we need to disallow
+ * blocking. The flags are further adjusted by
+ * gfp_nested_mask() in stack_depot itself.
*/
if (s->flags & SLAB_STORE_USER)
- set_track(s, freelist, TRACK_ALLOC, addr);
+ set_track(s, freelist, TRACK_ALLOC, addr,
+ gfpflags & ~(__GFP_DIRECT_RECLAIM));
return freelist;
}
@@ -3910,7 +3920,8 @@ new_objects:
goto new_objects;
if (s->flags & SLAB_STORE_USER)
- set_track(s, freelist, TRACK_ALLOC, addr);
+ set_track(s, freelist, TRACK_ALLOC, addr,
+ gfpflags & ~(__GFP_DIRECT_RECLAIM));
return freelist;
}
@@ -4421,8 +4432,12 @@ static noinline void free_to_partial_list(
unsigned long flags;
depot_stack_handle_t handle = 0;
+ /*
+ * We cannot use GFP_NOWAIT as there are callsites where waking up
+ * kswapd could deadlock
+ */
if (s->flags & SLAB_STORE_USER)
- handle = set_track_prepare();
+ handle = set_track_prepare(__GFP_NOWARN);
spin_lock_irqsave(&n->list_lock, flags);
diff --git a/mm/sparse-vmemmap.c b/mm/sparse-vmemmap.c
index fd2ab5118e13..dbd8daccade2 100644
--- a/mm/sparse-vmemmap.c
+++ b/mm/sparse-vmemmap.c
@@ -27,9 +27,9 @@
#include <linux/spinlock.h>
#include <linux/vmalloc.h>
#include <linux/sched.h>
+#include <linux/pgalloc.h>
#include <asm/dma.h>
-#include <asm/pgalloc.h>
#include <asm/tlbflush.h>
#include "hugetlb_vmemmap.h"
@@ -229,7 +229,7 @@ p4d_t * __meminit vmemmap_p4d_populate(pgd_t *pgd, unsigned long addr, int node)
if (!p)
return NULL;
pud_init(p);
- p4d_populate(&init_mm, p4d, p);
+ p4d_populate_kernel(addr, p4d, p);
}
return p4d;
}
@@ -241,7 +241,7 @@ pgd_t * __meminit vmemmap_pgd_populate(unsigned long addr, int node)
void *p = vmemmap_alloc_block_zero(PAGE_SIZE, node);
if (!p)
return NULL;
- pgd_populate(&init_mm, pgd, p);
+ pgd_populate_kernel(addr, pgd, p);
}
return pgd;
}
@@ -578,11 +578,6 @@ struct page * __meminit __populate_section_memmap(unsigned long pfn,
if (r < 0)
return NULL;
- if (system_state == SYSTEM_BOOTING)
- memmap_boot_pages_add(DIV_ROUND_UP(end - start, PAGE_SIZE));
- else
- memmap_pages_add(DIV_ROUND_UP(end - start, PAGE_SIZE));
-
return pfn_to_page(pfn);
}
diff --git a/mm/sparse.c b/mm/sparse.c
index 3c012cf83cc2..e6075b622407 100644
--- a/mm/sparse.c
+++ b/mm/sparse.c
@@ -454,9 +454,6 @@ static void __init sparse_buffer_init(unsigned long size, int nid)
*/
sparsemap_buf = memmap_alloc(size, section_map_size(), addr, nid, true);
sparsemap_buf_end = sparsemap_buf + size;
-#ifndef CONFIG_SPARSEMEM_VMEMMAP
- memmap_boot_pages_add(DIV_ROUND_UP(size, PAGE_SIZE));
-#endif
}
static void __init sparse_buffer_fini(void)
@@ -567,6 +564,8 @@ static void __init sparse_init_nid(int nid, unsigned long pnum_begin,
sparse_buffer_fini();
goto failed;
}
+ memmap_boot_pages_add(DIV_ROUND_UP(PAGES_PER_SECTION * sizeof(struct page),
+ PAGE_SIZE));
sparse_init_early_section(nid, map, pnum, 0);
}
}
@@ -680,7 +679,6 @@ static void depopulate_section_memmap(unsigned long pfn, unsigned long nr_pages,
unsigned long start = (unsigned long) pfn_to_page(pfn);
unsigned long end = start + nr_pages * sizeof(struct page);
- memmap_pages_add(-1L * (DIV_ROUND_UP(end - start, PAGE_SIZE)));
vmemmap_free(start, end, altmap);
}
static void free_map_bootmem(struct page *memmap)
@@ -856,10 +854,14 @@ static void section_deactivate(unsigned long pfn, unsigned long nr_pages,
* The memmap of early sections is always fully populated. See
* section_activate() and pfn_valid() .
*/
- if (!section_is_early)
+ if (!section_is_early) {
+ memmap_pages_add(-1L * (DIV_ROUND_UP(nr_pages * sizeof(struct page), PAGE_SIZE)));
depopulate_section_memmap(pfn, nr_pages, altmap);
- else if (memmap)
+ } else if (memmap) {
+ memmap_boot_pages_add(-1L * (DIV_ROUND_UP(nr_pages * sizeof(struct page),
+ PAGE_SIZE)));
free_map_bootmem(memmap);
+ }
if (empty)
ms->section_mem_map = (unsigned long)NULL;
@@ -904,6 +906,7 @@ static struct page * __meminit section_activate(int nid, unsigned long pfn,
section_deactivate(pfn, nr_pages, altmap);
return ERR_PTR(-ENOMEM);
}
+ memmap_pages_add(DIV_ROUND_UP(nr_pages * sizeof(struct page), PAGE_SIZE));
return memmap;
}
diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c
index cbed91b09640..aefdf3a812a1 100644
--- a/mm/userfaultfd.c
+++ b/mm/userfaultfd.c
@@ -1453,10 +1453,15 @@ out:
folio_unlock(src_folio);
folio_put(src_folio);
}
- if (dst_pte)
- pte_unmap(dst_pte);
+ /*
+ * Unmap in reverse order (LIFO) to maintain proper kmap_local
+ * index ordering when CONFIG_HIGHPTE is enabled. We mapped dst_pte
+ * first, then src_pte, so we must unmap src_pte first, then dst_pte.
+ */
if (src_pte)
pte_unmap(src_pte);
+ if (dst_pte)
+ pte_unmap(dst_pte);
mmu_notifier_invalidate_range_end(&range);
if (si)
put_swap_device(si);
@@ -1821,13 +1826,16 @@ ssize_t move_pages(struct userfaultfd_ctx *ctx, unsigned long dst_start,
/* Check if we can move the pmd without splitting it. */
if (move_splits_huge_pmd(dst_addr, src_addr, src_start + len) ||
!pmd_none(dst_pmdval)) {
- struct folio *folio = pmd_folio(*src_pmd);
-
- if (!folio || (!is_huge_zero_folio(folio) &&
- !PageAnonExclusive(&folio->page))) {
- spin_unlock(ptl);
- err = -EBUSY;
- break;
+ /* Can be a migration entry */
+ if (pmd_present(*src_pmd)) {
+ struct folio *folio = pmd_folio(*src_pmd);
+
+ if (!is_huge_zero_folio(folio) &&
+ !PageAnonExclusive(&folio->page)) {
+ spin_unlock(ptl);
+ err = -EBUSY;
+ break;
+ }
}
spin_unlock(ptl);
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index 6dbcdceecae1..5edd536ba9d2 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -2026,6 +2026,8 @@ static struct vmap_area *alloc_vmap_area(unsigned long size,
if (unlikely(!vmap_initialized))
return ERR_PTR(-EBUSY);
+ /* Only reclaim behaviour flags are relevant. */
+ gfp_mask = gfp_mask & GFP_RECLAIM_MASK;
might_sleep();
/*
@@ -2038,8 +2040,6 @@ static struct vmap_area *alloc_vmap_area(unsigned long size,
*/
va = node_alloc(size, align, vstart, vend, &addr, &vn_id);
if (!va) {
- gfp_mask = gfp_mask & GFP_RECLAIM_MASK;
-
va = kmem_cache_alloc_node(vmap_area_cachep, gfp_mask, node);
if (unlikely(!va))
return ERR_PTR(-ENOMEM);
@@ -2089,7 +2089,7 @@ retry:
BUG_ON(va->va_start < vstart);
BUG_ON(va->va_end > vend);
- ret = kasan_populate_vmalloc(addr, size);
+ ret = kasan_populate_vmalloc(addr, size, gfp_mask);
if (ret) {
free_vmap_area(va);
return ERR_PTR(ret);
@@ -4826,7 +4826,7 @@ retry:
/* populate the kasan shadow space */
for (area = 0; area < nr_vms; area++) {
- if (kasan_populate_vmalloc(vas[area]->va_start, sizes[area]))
+ if (kasan_populate_vmalloc(vas[area]->va_start, sizes[area], GFP_KERNEL))
goto err_free_shadow;
}
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 7de11524a936..a48aec8bfd92 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -5772,9 +5772,9 @@ static int __init init_lru_gen(void)
if (sysfs_create_group(mm_kobj, &lru_gen_attr_group))
pr_err("lru_gen: failed to create sysfs group\n");
- debugfs_create_file_aux_num("lru_gen", 0644, NULL, NULL, 1,
+ debugfs_create_file_aux_num("lru_gen", 0644, NULL, NULL, false,
&lru_gen_rw_fops);
- debugfs_create_file_aux_num("lru_gen_full", 0444, NULL, NULL, 0,
+ debugfs_create_file_aux_num("lru_gen_full", 0444, NULL, NULL, true,
&lru_gen_ro_fops);
return 0;
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 2.39.1) at 2025-09-12 08:41:36 +0000