summaryrefslogtreecommitdiff
path: root/mm
diff options
context:
space:
mode:
Diffstat (limited to 'mm')
-rw-r--r--mm/backing-dev.c7
-rw-r--r--mm/hugetlb.c23
-rw-r--r--mm/kmemleak.c30
-rw-r--r--mm/memblock.c13
-rw-r--r--mm/memcontrol.c2
-rw-r--r--mm/memfd.c40
-rw-r--r--mm/memory.c42
-rw-r--r--mm/mempolicy.c14
-rw-r--r--mm/mmap.c10
-rw-r--r--mm/mremap.c3
-rw-r--r--mm/oom_kill.c54
-rw-r--r--mm/page_alloc.c32
-rw-r--r--mm/page_io.c54
-rw-r--r--mm/rmap.c25
-rw-r--r--mm/shmem.c37
-rw-r--r--mm/slab.h2
-rw-r--r--mm/usercopy.c5
17 files changed, 242 insertions, 151 deletions
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index 3f2480e4c5af..3954ef0cc770 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -1013,6 +1013,13 @@ void bdi_unregister(struct backing_dev_info *bdi)
wb_shutdown(&bdi->wb);
cgwb_bdi_unregister(bdi);
+ /*
+ * If this BDI's min ratio has been set, use bdi_set_min_ratio() to
+ * update the global bdi_min_ratio.
+ */
+ if (bdi->min_ratio)
+ bdi_set_min_ratio(bdi, 0);
+
if (bdi->dev) {
bdi_debug_unregister(bdi);
device_unregister(bdi->dev);
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 95a32749af4d..20da6ede7704 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -3589,6 +3589,7 @@ void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma,
struct hstate *h = hstate_vma(vma);
unsigned long sz = huge_page_size(h);
struct mmu_notifier_range range;
+ bool force_flush = false;
WARN_ON(!is_vm_hugetlb_page(vma));
BUG_ON(start & ~huge_page_mask(h));
@@ -3617,10 +3618,8 @@ void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma,
ptl = huge_pte_lock(h, mm, ptep);
if (huge_pmd_unshare(mm, &address, ptep)) {
spin_unlock(ptl);
- /*
- * We just unmapped a page of PMDs by clearing a PUD.
- * The caller's TLB flush range should cover this area.
- */
+ tlb_flush_pmd_range(tlb, address & PUD_MASK, PUD_SIZE);
+ force_flush = true;
continue;
}
@@ -3677,6 +3676,22 @@ void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma,
}
mmu_notifier_invalidate_range_end(&range);
tlb_end_vma(tlb, vma);
+
+ /*
+ * If we unshared PMDs, the TLB flush was not recorded in mmu_gather. We
+ * could defer the flush until now, since by holding i_mmap_rwsem we
+ * guaranteed that the last refernece would not be dropped. But we must
+ * do the flushing before we return, as otherwise i_mmap_rwsem will be
+ * dropped and the last reference to the shared PMDs page might be
+ * dropped as well.
+ *
+ * In theory we could defer the freeing of the PMD pages as well, but
+ * huge_pmd_unshare() relies on the exact page_count for the PMD page to
+ * detect sharing, so we cannot defer the release of the page either.
+ * Instead, do flush now.
+ */
+ if (force_flush)
+ tlb_flush_mmu_tlbonly(tlb);
}
void __unmap_hugepage_range_final(struct mmu_gather *tlb,
diff --git a/mm/kmemleak.c b/mm/kmemleak.c
index 312942d78405..3761c79137b1 100644
--- a/mm/kmemleak.c
+++ b/mm/kmemleak.c
@@ -787,6 +787,8 @@ static void add_scan_area(unsigned long ptr, size_t size, gfp_t gfp)
unsigned long flags;
struct kmemleak_object *object;
struct kmemleak_scan_area *area = NULL;
+ unsigned long untagged_ptr;
+ unsigned long untagged_objp;
object = find_and_get_object(ptr, 1);
if (!object) {
@@ -795,6 +797,9 @@ static void add_scan_area(unsigned long ptr, size_t size, gfp_t gfp)
return;
}
+ untagged_ptr = (unsigned long)kasan_reset_tag((void *)ptr);
+ untagged_objp = (unsigned long)kasan_reset_tag((void *)object->pointer);
+
if (scan_area_cache)
area = kmem_cache_alloc(scan_area_cache, gfp_kmemleak_mask(gfp));
@@ -806,8 +811,8 @@ static void add_scan_area(unsigned long ptr, size_t size, gfp_t gfp)
goto out_unlock;
}
if (size == SIZE_MAX) {
- size = object->pointer + object->size - ptr;
- } else if (ptr + size > object->pointer + object->size) {
+ size = untagged_objp + object->size - untagged_ptr;
+ } else if (untagged_ptr + size > untagged_objp + object->size) {
kmemleak_warn("Scan area larger than object 0x%08lx\n", ptr);
dump_object_info(object);
kmem_cache_free(scan_area_cache, area);
@@ -1118,7 +1123,7 @@ EXPORT_SYMBOL(kmemleak_no_scan);
void __ref kmemleak_alloc_phys(phys_addr_t phys, size_t size, int min_count,
gfp_t gfp)
{
- if (!IS_ENABLED(CONFIG_HIGHMEM) || PHYS_PFN(phys) < max_low_pfn)
+ if (PHYS_PFN(phys) >= min_low_pfn && PHYS_PFN(phys) < max_low_pfn)
kmemleak_alloc(__va(phys), size, min_count, gfp);
}
EXPORT_SYMBOL(kmemleak_alloc_phys);
@@ -1132,7 +1137,7 @@ EXPORT_SYMBOL(kmemleak_alloc_phys);
*/
void __ref kmemleak_free_part_phys(phys_addr_t phys, size_t size)
{
- if (!IS_ENABLED(CONFIG_HIGHMEM) || PHYS_PFN(phys) < max_low_pfn)
+ if (PHYS_PFN(phys) >= min_low_pfn && PHYS_PFN(phys) < max_low_pfn)
kmemleak_free_part(__va(phys), size);
}
EXPORT_SYMBOL(kmemleak_free_part_phys);
@@ -1144,7 +1149,7 @@ EXPORT_SYMBOL(kmemleak_free_part_phys);
*/
void __ref kmemleak_not_leak_phys(phys_addr_t phys)
{
- if (!IS_ENABLED(CONFIG_HIGHMEM) || PHYS_PFN(phys) < max_low_pfn)
+ if (PHYS_PFN(phys) >= min_low_pfn && PHYS_PFN(phys) < max_low_pfn)
kmemleak_not_leak(__va(phys));
}
EXPORT_SYMBOL(kmemleak_not_leak_phys);
@@ -1156,7 +1161,7 @@ EXPORT_SYMBOL(kmemleak_not_leak_phys);
*/
void __ref kmemleak_ignore_phys(phys_addr_t phys)
{
- if (!IS_ENABLED(CONFIG_HIGHMEM) || PHYS_PFN(phys) < max_low_pfn)
+ if (PHYS_PFN(phys) >= min_low_pfn && PHYS_PFN(phys) < max_low_pfn)
kmemleak_ignore(__va(phys));
}
EXPORT_SYMBOL(kmemleak_ignore_phys);
@@ -1399,7 +1404,8 @@ static void kmemleak_scan(void)
{
unsigned long flags;
struct kmemleak_object *object;
- int i;
+ struct zone *zone;
+ int __maybe_unused i;
int new_leaks = 0;
jiffies_last_scan = jiffies;
@@ -1439,9 +1445,9 @@ static void kmemleak_scan(void)
* Struct page scanning for each node.
*/
get_online_mems();
- for_each_online_node(i) {
- unsigned long start_pfn = node_start_pfn(i);
- unsigned long end_pfn = node_end_pfn(i);
+ for_each_populated_zone(zone) {
+ unsigned long start_pfn = zone->zone_start_pfn;
+ unsigned long end_pfn = zone_end_pfn(zone);
unsigned long pfn;
for (pfn = start_pfn; pfn < end_pfn; pfn++) {
@@ -1450,8 +1456,8 @@ static void kmemleak_scan(void)
if (!page)
continue;
- /* only scan pages belonging to this node */
- if (page_to_nid(page) != i)
+ /* only scan pages belonging to this zone */
+ if (page_zone(page) != zone)
continue;
/* only scan if page is in use */
if (page_count(page) == 0)
diff --git a/mm/memblock.c b/mm/memblock.c
index 11f6ae37d669..a75cc65f0330 100644
--- a/mm/memblock.c
+++ b/mm/memblock.c
@@ -164,6 +164,8 @@ bool __init_memblock memblock_overlaps_region(struct memblock_type *type,
{
unsigned long i;
+ memblock_cap_size(base, &size);
+
for (i = 0; i < type->cnt; i++)
if (memblock_addrs_overlap(base, size, type->regions[i].base,
type->regions[i].size))
@@ -346,14 +348,20 @@ void __init memblock_discard(void)
addr = __pa(memblock.reserved.regions);
size = PAGE_ALIGN(sizeof(struct memblock_region) *
memblock.reserved.max);
- __memblock_free_late(addr, size);
+ if (memblock_reserved_in_slab)
+ kfree(memblock.reserved.regions);
+ else
+ __memblock_free_late(addr, size);
}
if (memblock.memory.regions != memblock_memory_init_regions) {
addr = __pa(memblock.memory.regions);
size = PAGE_ALIGN(sizeof(struct memblock_region) *
memblock.memory.max);
- __memblock_free_late(addr, size);
+ if (memblock_memory_in_slab)
+ kfree(memblock.memory.regions);
+ else
+ __memblock_free_late(addr, size);
}
}
#endif
@@ -1760,7 +1768,6 @@ bool __init_memblock memblock_is_region_memory(phys_addr_t base, phys_addr_t siz
*/
bool __init_memblock memblock_is_region_reserved(phys_addr_t base, phys_addr_t size)
{
- memblock_cap_size(base, &size);
return memblock_overlaps_region(&memblock.reserved, base, size);
}
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 6d7fe3589e4a..8fc663545498 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -6973,7 +6973,7 @@ static int __init cgroup_memory(char *s)
if (!strcmp(token, "nokmem"))
cgroup_memory_nokmem = true;
}
- return 0;
+ return 1;
}
__setup("cgroup.memory=", cgroup_memory);
diff --git a/mm/memfd.c b/mm/memfd.c
index 2647c898990c..fae4142f7d25 100644
--- a/mm/memfd.c
+++ b/mm/memfd.c
@@ -31,20 +31,28 @@
static void memfd_tag_pins(struct xa_state *xas)
{
struct page *page;
- unsigned int tagged = 0;
+ int latency = 0;
+ int cache_count;
lru_add_drain();
xas_lock_irq(xas);
xas_for_each(xas, page, ULONG_MAX) {
- if (xa_is_value(page))
- continue;
- page = find_subpage(page, xas->xa_index);
- if (page_count(page) - page_mapcount(page) > 1)
+ cache_count = 1;
+ if (!xa_is_value(page) &&
+ PageTransHuge(page) && !PageHuge(page))
+ cache_count = HPAGE_PMD_NR;
+
+ if (!xa_is_value(page) &&
+ page_count(page) - total_mapcount(page) != cache_count)
xas_set_mark(xas, MEMFD_TAG_PINNED);
+ if (cache_count != 1)
+ xas_set(xas, page->index + cache_count);
- if (++tagged % XA_CHECK_SCHED)
+ latency += cache_count;
+ if (latency < XA_CHECK_SCHED)
continue;
+ latency = 0;
xas_pause(xas);
xas_unlock_irq(xas);
@@ -73,7 +81,8 @@ static int memfd_wait_for_pins(struct address_space *mapping)
error = 0;
for (scan = 0; scan <= LAST_SCAN; scan++) {
- unsigned int tagged = 0;
+ int latency = 0;
+ int cache_count;
if (!xas_marked(&xas, MEMFD_TAG_PINNED))
break;
@@ -87,10 +96,14 @@ static int memfd_wait_for_pins(struct address_space *mapping)
xas_lock_irq(&xas);
xas_for_each_marked(&xas, page, ULONG_MAX, MEMFD_TAG_PINNED) {
bool clear = true;
- if (xa_is_value(page))
- continue;
- page = find_subpage(page, xas.xa_index);
- if (page_count(page) - page_mapcount(page) != 1) {
+
+ cache_count = 1;
+ if (!xa_is_value(page) &&
+ PageTransHuge(page) && !PageHuge(page))
+ cache_count = HPAGE_PMD_NR;
+
+ if (!xa_is_value(page) && cache_count !=
+ page_count(page) - total_mapcount(page)) {
/*
* On the last scan, we clean up all those tags
* we inserted; but make a note that we still
@@ -103,8 +116,11 @@ static int memfd_wait_for_pins(struct address_space *mapping)
}
if (clear)
xas_clear_mark(&xas, MEMFD_TAG_PINNED);
- if (++tagged % XA_CHECK_SCHED)
+
+ latency += cache_count;
+ if (latency < XA_CHECK_SCHED)
continue;
+ latency = 0;
xas_pause(&xas);
xas_unlock_irq(&xas);
diff --git a/mm/memory.c b/mm/memory.c
index 4bb7c6a364c8..8a72fd3e73bf 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1013,6 +1013,17 @@ int copy_page_range(struct mm_struct *dst_mm, struct mm_struct *src_mm,
return ret;
}
+/* Whether we should zap all COWed (private) pages too */
+static inline bool should_zap_cows(struct zap_details *details)
+{
+ /* By default, zap all pages */
+ if (!details)
+ return true;
+
+ /* Or, we zap COWed pages only if the caller wants to */
+ return !details->check_mapping;
+}
+
static unsigned long zap_pte_range(struct mmu_gather *tlb,
struct vm_area_struct *vma, pmd_t *pmd,
unsigned long addr, unsigned long end,
@@ -1104,16 +1115,18 @@ again:
continue;
}
- /* If details->check_mapping, we leave swap entries. */
- if (unlikely(details))
- continue;
-
- if (!non_swap_entry(entry))
+ if (!non_swap_entry(entry)) {
+ /* Genuine swap entry, hence a private anon page */
+ if (!should_zap_cows(details))
+ continue;
rss[MM_SWAPENTS]--;
- else if (is_migration_entry(entry)) {
+ } else if (is_migration_entry(entry)) {
struct page *page;
page = migration_entry_to_page(entry);
+ if (details && details->check_mapping &&
+ details->check_mapping != page_rmapping(page))
+ continue;
rss[mm_counter(page)]--;
}
if (unlikely(!free_swap_and_cache(entry)))
@@ -3245,11 +3258,20 @@ static vm_fault_t __do_fault(struct vm_fault *vmf)
return ret;
if (unlikely(PageHWPoison(vmf->page))) {
- if (ret & VM_FAULT_LOCKED)
- unlock_page(vmf->page);
- put_page(vmf->page);
+ struct page *page = vmf->page;
+ vm_fault_t poisonret = VM_FAULT_HWPOISON;
+ if (ret & VM_FAULT_LOCKED) {
+ if (page_mapped(page))
+ unmap_mapping_pages(page_mapping(page),
+ page->index, 1, false);
+ /* Retry if a clean page was removed from the cache. */
+ if (invalidate_inode_page(page))
+ poisonret = VM_FAULT_NOPAGE;
+ unlock_page(page);
+ }
+ put_page(page);
vmf->page = NULL;
- return VM_FAULT_HWPOISON;
+ return poisonret;
}
if (unlikely(!(ret & VM_FAULT_LOCKED)))
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 87d165923fee..d79ab5116a7b 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -731,7 +731,6 @@ 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)
{
- struct vm_area_struct *next;
struct vm_area_struct *prev;
struct vm_area_struct *vma;
int err = 0;
@@ -747,8 +746,7 @@ static int mbind_range(struct mm_struct *mm, unsigned long start,
if (start > vma->vm_start)
prev = vma;
- for (; vma && vma->vm_start < end; prev = vma, vma = next) {
- next = vma->vm_next;
+ for (; vma && vma->vm_start < end; prev = vma, vma = vma->vm_next) {
vmstart = max(start, vma->vm_start);
vmend = min(end, vma->vm_end);
@@ -762,10 +760,6 @@ static int mbind_range(struct mm_struct *mm, unsigned long start,
new_pol, vma->vm_userfaultfd_ctx);
if (prev) {
vma = prev;
- next = vma->vm_next;
- if (mpol_equal(vma_policy(vma), new_pol))
- continue;
- /* vma_merge() joined vma && vma->next, case 8 */
goto replace;
}
if (vma->vm_start != vmstart) {
@@ -2143,8 +2137,9 @@ alloc_pages_vma(gfp_t gfp, int order, struct vm_area_struct *vma,
* memory as well.
*/
if (!page && (gfp & __GFP_DIRECT_RECLAIM))
- page = __alloc_pages_node(hpage_node,
- gfp | __GFP_NORETRY, order);
+ page = __alloc_pages_nodemask(gfp | __GFP_NORETRY,
+ order, hpage_node,
+ nmask);
goto out;
}
@@ -2564,6 +2559,7 @@ alloc_new:
mpol_new = kmem_cache_alloc(policy_cache, GFP_KERNEL);
if (!mpol_new)
goto err_out;
+ atomic_set(&mpol_new->refcnt, 1);
goto restart;
}
diff --git a/mm/mmap.c b/mm/mmap.c
index ba78f1f1b1bd..88e686367776 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -2077,14 +2077,6 @@ found_highest:
}
-#ifndef arch_get_mmap_end
-#define arch_get_mmap_end(addr) (TASK_SIZE)
-#endif
-
-#ifndef arch_get_mmap_base
-#define arch_get_mmap_base(addr, base) (base)
-#endif
-
/* Get an address range which is currently unmapped.
* For shmat() with addr=0.
*
@@ -2515,7 +2507,7 @@ static int __init cmdline_parse_stack_guard_gap(char *p)
if (!*endptr)
stack_guard_gap = val << PAGE_SHIFT;
- return 0;
+ return 1;
}
__setup("stack_guard_gap=", cmdline_parse_stack_guard_gap);
diff --git a/mm/mremap.c b/mm/mremap.c
index 8005d0b2b843..8ce1b7632fbb 100644
--- a/mm/mremap.c
+++ b/mm/mremap.c
@@ -246,6 +246,9 @@ unsigned long move_page_tables(struct vm_area_struct *vma,
struct mmu_notifier_range range;
pmd_t *old_pmd, *new_pmd;
+ if (!len)
+ return 0;
+
old_end = old_addr + len;
flush_cache_range(vma, old_addr, old_end);
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index dcbb9a28706f..ee927ffeb718 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -631,7 +631,7 @@ done:
*/
set_bit(MMF_OOM_SKIP, &mm->flags);
- /* Drop a reference taken by wake_oom_reaper */
+ /* Drop a reference taken by queue_oom_reaper */
put_task_struct(tsk);
}
@@ -641,12 +641,12 @@ static int oom_reaper(void *unused)
struct task_struct *tsk = NULL;
wait_event_freezable(oom_reaper_wait, oom_reaper_list != NULL);
- spin_lock(&oom_reaper_lock);
+ spin_lock_irq(&oom_reaper_lock);
if (oom_reaper_list != NULL) {
tsk = oom_reaper_list;
oom_reaper_list = tsk->oom_reaper_list;
}
- spin_unlock(&oom_reaper_lock);
+ spin_unlock_irq(&oom_reaper_lock);
if (tsk)
oom_reap_task(tsk);
@@ -655,22 +655,48 @@ static int oom_reaper(void *unused)
return 0;
}
-static void wake_oom_reaper(struct task_struct *tsk)
+static void wake_oom_reaper(struct timer_list *timer)
{
- /* mm is already queued? */
- if (test_and_set_bit(MMF_OOM_REAP_QUEUED, &tsk->signal->oom_mm->flags))
- return;
+ struct task_struct *tsk = container_of(timer, struct task_struct,
+ oom_reaper_timer);
+ struct mm_struct *mm = tsk->signal->oom_mm;
+ unsigned long flags;
- get_task_struct(tsk);
+ /* The victim managed to terminate on its own - see exit_mmap */
+ if (test_bit(MMF_OOM_SKIP, &mm->flags)) {
+ put_task_struct(tsk);
+ return;
+ }
- spin_lock(&oom_reaper_lock);
+ spin_lock_irqsave(&oom_reaper_lock, flags);
tsk->oom_reaper_list = oom_reaper_list;
oom_reaper_list = tsk;
- spin_unlock(&oom_reaper_lock);
+ spin_unlock_irqrestore(&oom_reaper_lock, flags);
trace_wake_reaper(tsk->pid);
wake_up(&oom_reaper_wait);
}
+/*
+ * Give the OOM victim time to exit naturally before invoking the oom_reaping.
+ * The timers timeout is arbitrary... the longer it is, the longer the worst
+ * case scenario for the OOM can take. If it is too small, the oom_reaper can
+ * get in the way and release resources needed by the process exit path.
+ * e.g. The futex robust list can sit in Anon|Private memory that gets reaped
+ * before the exit path is able to wake the futex waiters.
+ */
+#define OOM_REAPER_DELAY (2*HZ)
+static void queue_oom_reaper(struct task_struct *tsk)
+{
+ /* mm is already queued? */
+ if (test_and_set_bit(MMF_OOM_REAP_QUEUED, &tsk->signal->oom_mm->flags))
+ return;
+
+ get_task_struct(tsk);
+ timer_setup(&tsk->oom_reaper_timer, wake_oom_reaper, 0);
+ tsk->oom_reaper_timer.expires = jiffies + OOM_REAPER_DELAY;
+ add_timer(&tsk->oom_reaper_timer);
+}
+
static int __init oom_init(void)
{
oom_reaper_th = kthread_run(oom_reaper, NULL, "oom_reaper");
@@ -678,7 +704,7 @@ static int __init oom_init(void)
}
subsys_initcall(oom_init)
#else
-static inline void wake_oom_reaper(struct task_struct *tsk)
+static inline void queue_oom_reaper(struct task_struct *tsk)
{
}
#endif /* CONFIG_MMU */
@@ -927,7 +953,7 @@ static void __oom_kill_process(struct task_struct *victim, const char *message)
rcu_read_unlock();
if (can_oom_reap)
- wake_oom_reaper(victim);
+ queue_oom_reaper(victim);
mmdrop(mm);
put_task_struct(victim);
@@ -963,7 +989,7 @@ static void oom_kill_process(struct oom_control *oc, const char *message)
task_lock(victim);
if (task_will_free_mem(victim)) {
mark_oom_victim(victim);
- wake_oom_reaper(victim);
+ queue_oom_reaper(victim);
task_unlock(victim);
put_task_struct(victim);
return;
@@ -1061,7 +1087,7 @@ bool out_of_memory(struct oom_control *oc)
*/
if (task_will_free_mem(current)) {
mark_oom_victim(current);
- wake_oom_reaper(current);
+ queue_oom_reaper(current);
return true;
}
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 283ac9d9f6dd..f08ce248af2a 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -3767,7 +3767,9 @@ void warn_alloc(gfp_t gfp_mask, nodemask_t *nodemask, const char *fmt, ...)
va_list args;
static DEFINE_RATELIMIT_STATE(nopage_rs, 10*HZ, 1);
- if ((gfp_mask & __GFP_NOWARN) || !__ratelimit(&nopage_rs))
+ if ((gfp_mask & __GFP_NOWARN) ||
+ !__ratelimit(&nopage_rs) ||
+ ((gfp_mask & __GFP_DMA) && !has_managed_dma()))
return;
va_start(args, fmt);
@@ -5479,7 +5481,7 @@ static int build_zonerefs_node(pg_data_t *pgdat, struct zoneref *zonerefs)
do {
zone_type--;
zone = pgdat->node_zones + zone_type;
- if (managed_zone(zone)) {
+ if (populated_zone(zone)) {
zoneref_set_zone(zone, &zonerefs[nr_zones++]);
check_highest_zone(zone_type);
}
@@ -7324,10 +7326,17 @@ restart:
out2:
/* Align start of ZONE_MOVABLE on all nids to MAX_ORDER_NR_PAGES */
- for (nid = 0; nid < MAX_NUMNODES; nid++)
+ for (nid = 0; nid < MAX_NUMNODES; nid++) {
+ unsigned long start_pfn, end_pfn;
+
zone_movable_pfn[nid] =
roundup(zone_movable_pfn[nid], MAX_ORDER_NR_PAGES);
+ get_pfn_range_for_nid(nid, &start_pfn, &end_pfn);
+ if (zone_movable_pfn[nid] >= end_pfn)
+ zone_movable_pfn[nid] = 0;
+ }
+
out:
/* restore the node_state */
node_states[N_MEMORY] = saved_node_state;
@@ -7579,7 +7588,7 @@ void __init mem_init_print_info(const char *str)
*/
#define adj_init_size(start, end, size, pos, adj) \
do { \
- if (start <= pos && pos < end && size > adj) \
+ if (&start[0] <= &pos[0] && &pos[0] < &end[0] && size > adj) \
size -= adj; \
} while (0)
@@ -8694,3 +8703,18 @@ bool set_hwpoison_free_buddy_page(struct page *page)
return hwpoisoned;
}
#endif
+
+#ifdef CONFIG_ZONE_DMA
+bool has_managed_dma(void)
+{
+ struct pglist_data *pgdat;
+
+ for_each_online_pgdat(pgdat) {
+ struct zone *zone = &pgdat->node_zones[ZONE_DMA];
+
+ if (managed_zone(zone))
+ return true;
+ }
+ return false;
+}
+#endif /* CONFIG_ZONE_DMA */
diff --git a/mm/page_io.c b/mm/page_io.c
index bcf27d057253..f0e3f2be7b44 100644
--- a/mm/page_io.c
+++ b/mm/page_io.c
@@ -69,54 +69,6 @@ void end_swap_bio_write(struct bio *bio)
bio_put(bio);
}
-static void swap_slot_free_notify(struct page *page)
-{
- struct swap_info_struct *sis;
- struct gendisk *disk;
- swp_entry_t entry;
-
- /*
- * There is no guarantee that the page is in swap cache - the software
- * suspend code (at least) uses end_swap_bio_read() against a non-
- * swapcache page. So we must check PG_swapcache before proceeding with
- * this optimization.
- */
- if (unlikely(!PageSwapCache(page)))
- return;
-
- sis = page_swap_info(page);
- if (!(sis->flags & SWP_BLKDEV))
- return;
-
- /*
- * The swap subsystem performs lazy swap slot freeing,
- * expecting that the page will be swapped out again.
- * So we can avoid an unnecessary write if the page
- * isn't redirtied.
- * This is good for real swap storage because we can
- * reduce unnecessary I/O and enhance wear-leveling
- * if an SSD is used as the as swap device.
- * But if in-memory swap device (eg zram) is used,
- * this causes a duplicated copy between uncompressed
- * data in VM-owned memory and compressed data in
- * zram-owned memory. So let's free zram-owned memory
- * and make the VM-owned decompressed page *dirty*,
- * so the page should be swapped out somewhere again if
- * we again wish to reclaim it.
- */
- disk = sis->bdev->bd_disk;
- entry.val = page_private(page);
- if (disk->fops->swap_slot_free_notify && __swap_count(entry) == 1) {
- unsigned long offset;
-
- offset = swp_offset(entry);
-
- SetPageDirty(page);
- disk->fops->swap_slot_free_notify(sis->bdev,
- offset);
- }
-}
-
static void end_swap_bio_read(struct bio *bio)
{
struct page *page = bio_first_page_all(bio);
@@ -132,7 +84,6 @@ static void end_swap_bio_read(struct bio *bio)
}
SetPageUptodate(page);
- swap_slot_free_notify(page);
out:
unlock_page(page);
WRITE_ONCE(bio->bi_private, NULL);
@@ -371,11 +322,6 @@ int swap_readpage(struct page *page, bool synchronous)
ret = bdev_read_page(sis->bdev, swap_page_sector(page), page);
if (!ret) {
- if (trylock_page(page)) {
- swap_slot_free_notify(page);
- unlock_page(page);
- }
-
count_vm_event(PSWPIN);
return 0;
}
diff --git a/mm/rmap.c b/mm/rmap.c
index 45f2106852e8..6d80e92688fe 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -1602,7 +1602,30 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
/* MADV_FREE page check */
if (!PageSwapBacked(page)) {
- if (!PageDirty(page)) {
+ int ref_count, map_count;
+
+ /*
+ * Synchronize with gup_pte_range():
+ * - clear PTE; barrier; read refcount
+ * - inc refcount; barrier; read PTE
+ */
+ smp_mb();
+
+ ref_count = page_ref_count(page);
+ map_count = page_mapcount(page);
+
+ /*
+ * Order reads for page refcount and dirty flag
+ * (see comments in __remove_mapping()).
+ */
+ smp_rmb();
+
+ /*
+ * The only page refs must be one from isolation
+ * plus the rmap(s) (dropped by discard:).
+ */
+ if (ref_count == 1 + map_count &&
+ !PageDirty(page)) {
/* Invalidate as we cleared the pte */
mmu_notifier_invalidate_range(mm,
address, address + PAGE_SIZE);
diff --git a/mm/shmem.c b/mm/shmem.c
index b119c44435bf..aae2f408f905 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -466,7 +466,7 @@ static unsigned long shmem_unused_huge_shrink(struct shmem_sb_info *sbinfo,
struct shmem_inode_info *info;
struct page *page;
unsigned long batch = sc ? sc->nr_to_scan : 128;
- int removed = 0, split = 0;
+ int split = 0;
if (list_empty(&sbinfo->shrinklist))
return SHRINK_STOP;
@@ -481,7 +481,6 @@ static unsigned long shmem_unused_huge_shrink(struct shmem_sb_info *sbinfo,
/* inode is about to be evicted */
if (!inode) {
list_del_init(&info->shrinklist);
- removed++;
goto next;
}
@@ -489,12 +488,12 @@ static unsigned long shmem_unused_huge_shrink(struct shmem_sb_info *sbinfo,
if (round_up(inode->i_size, PAGE_SIZE) ==
round_up(inode->i_size, HPAGE_PMD_SIZE)) {
list_move(&info->shrinklist, &to_remove);
- removed++;
goto next;
}
list_move(&info->shrinklist, &list);
next:
+ sbinfo->shrinklist_len--;
if (!--batch)
break;
}
@@ -514,7 +513,7 @@ next:
inode = &info->vfs_inode;
if (nr_to_split && split >= nr_to_split)
- goto leave;
+ goto move_back;
page = find_get_page(inode->i_mapping,
(inode->i_size & HPAGE_PMD_MASK) >> PAGE_SHIFT);
@@ -528,38 +527,44 @@ next:
}
/*
- * Leave the inode on the list if we failed to lock
- * the page at this time.
+ * Move the inode on the list back to shrinklist if we failed
+ * to lock the page at this time.
*
* Waiting for the lock may lead to deadlock in the
* reclaim path.
*/
if (!trylock_page(page)) {
put_page(page);
- goto leave;
+ goto move_back;
}
ret = split_huge_page(page);
unlock_page(page);
put_page(page);
- /* If split failed leave the inode on the list */
+ /* If split failed move the inode on the list back to shrinklist */
if (ret)
- goto leave;
+ goto move_back;
split++;
drop:
list_del_init(&info->shrinklist);
- removed++;
-leave:
+ goto put;
+move_back:
+ /*
+ * Make sure the inode is either on the global list or deleted
+ * from any local list before iput() since it could be deleted
+ * in another thread once we put the inode (then the local list
+ * is corrupted).
+ */
+ spin_lock(&sbinfo->shrinklist_lock);
+ list_move(&info->shrinklist, &sbinfo->shrinklist);
+ sbinfo->shrinklist_len++;
+ spin_unlock(&sbinfo->shrinklist_lock);
+put:
iput(inode);
}
- spin_lock(&sbinfo->shrinklist_lock);
- list_splice_tail(&list, &sbinfo->shrinklist);
- sbinfo->shrinklist_len -= removed;
- spin_unlock(&sbinfo->shrinklist_lock);
-
return split;
}
diff --git a/mm/slab.h b/mm/slab.h
index b2b01694dc43..61feda3d7e00 100644
--- a/mm/slab.h
+++ b/mm/slab.h
@@ -211,7 +211,7 @@ static inline slab_flags_t kmem_cache_flags(unsigned int object_size,
#define SLAB_CACHE_FLAGS (SLAB_NOLEAKTRACE | SLAB_RECLAIM_ACCOUNT | \
SLAB_TEMPORARY | SLAB_ACCOUNT)
#else
-#define SLAB_CACHE_FLAGS (0)
+#define SLAB_CACHE_FLAGS (SLAB_NOLEAKTRACE)
#endif
/* Common flags available with current configuration */
diff --git a/mm/usercopy.c b/mm/usercopy.c
index 660717a1ea5c..f70455bad7f3 100644
--- a/mm/usercopy.c
+++ b/mm/usercopy.c
@@ -294,7 +294,10 @@ static bool enable_checks __initdata = true;
static int __init parse_hardened_usercopy(char *str)
{
- return strtobool(str, &enable_checks);
+ if (strtobool(str, &enable_checks))
+ pr_warn("Invalid option string for hardened_usercopy: '%s'\n",
+ str);
+ return 1;
}
__setup("hardened_usercopy=", parse_hardened_usercopy);
generated by cgit v1.2.3 (git 2.0.4) at 2024-05-16 22:24:17 +0000