aboutsummaryrefslogtreecommitdiff
path: root/mm
diff options
context:
space:
mode:
Diffstat (limited to 'mm')
-rw-r--r--mm/filemap.c96
-rw-r--r--mm/gup.c4
-rw-r--r--mm/highmem.c21
-rw-r--r--mm/huge_memory.c10
-rw-r--r--mm/hugetlb.c164
-rw-r--r--mm/hugetlb_cgroup.c10
-rw-r--r--mm/internal.h32
-rw-r--r--mm/kasan/common.c2
-rw-r--r--mm/kasan/hw_tags.c66
-rw-r--r--mm/kasan/kasan.h42
-rw-r--r--mm/kasan/report.c22
-rw-r--r--mm/kasan/report_generic.c2
-rw-r--r--mm/kfence/core.c9
-rw-r--r--mm/kfence/report.c30
-rw-r--r--mm/kmemleak.c3
-rw-r--r--mm/madvise.c13
-rw-r--r--mm/mapping_dirty_helpers.c2
-rw-r--r--mm/memcontrol.c15
-rw-r--r--mm/memory.c18
-rw-r--r--mm/memory_hotplug.c2
-rw-r--r--mm/mmap.c6
-rw-r--r--mm/mmu_gather.c29
-rw-r--r--mm/mmu_notifier.c23
-rw-r--r--mm/oom_kill.c2
-rw-r--r--mm/page-writeback.c16
-rw-r--r--mm/page_alloc.c171
-rw-r--r--mm/page_poison.c4
-rw-r--r--mm/percpu-internal.h2
-rw-r--r--mm/percpu-stats.c9
-rw-r--r--mm/percpu.c14
-rw-r--r--mm/ptdump.c2
-rw-r--r--mm/readahead.c101
-rw-r--r--mm/shuffle.c4
-rw-r--r--mm/slab.c2
-rw-r--r--mm/slab.h6
-rw-r--r--mm/slub.c15
-rw-r--r--mm/z3fold.c16
37 files changed, 728 insertions, 257 deletions
diff --git a/mm/filemap.c b/mm/filemap.c
index 43700480d897..151090fdcf29 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -1433,6 +1433,67 @@ void unlock_page(struct page *page)
EXPORT_SYMBOL(unlock_page);
/**
+ * end_page_private_2 - Clear PG_private_2 and release any waiters
+ * @page: The page
+ *
+ * Clear the PG_private_2 bit on a page and wake up any sleepers waiting for
+ * this. The page ref held for PG_private_2 being set is released.
+ *
+ * This is, for example, used when a netfs page is being written to a local
+ * disk cache, thereby allowing writes to the cache for the same page to be
+ * serialised.
+ */
+void end_page_private_2(struct page *page)
+{
+ page = compound_head(page);
+ VM_BUG_ON_PAGE(!PagePrivate2(page), page);
+ clear_bit_unlock(PG_private_2, &page->flags);
+ wake_up_page_bit(page, PG_private_2);
+ put_page(page);
+}
+EXPORT_SYMBOL(end_page_private_2);
+
+/**
+ * wait_on_page_private_2 - Wait for PG_private_2 to be cleared on a page
+ * @page: The page to wait on
+ *
+ * Wait for PG_private_2 (aka PG_fscache) to be cleared on a page.
+ */
+void wait_on_page_private_2(struct page *page)
+{
+ page = compound_head(page);
+ while (PagePrivate2(page))
+ wait_on_page_bit(page, PG_private_2);
+}
+EXPORT_SYMBOL(wait_on_page_private_2);
+
+/**
+ * wait_on_page_private_2_killable - Wait for PG_private_2 to be cleared on a page
+ * @page: The page to wait on
+ *
+ * Wait for PG_private_2 (aka PG_fscache) to be cleared on a page or until a
+ * fatal signal is received by the calling task.
+ *
+ * Return:
+ * - 0 if successful.
+ * - -EINTR if a fatal signal was encountered.
+ */
+int wait_on_page_private_2_killable(struct page *page)
+{
+ int ret = 0;
+
+ page = compound_head(page);
+ while (PagePrivate2(page)) {
+ ret = wait_on_page_bit_killable(page, PG_private_2);
+ if (ret < 0)
+ break;
+ }
+
+ return ret;
+}
+EXPORT_SYMBOL(wait_on_page_private_2_killable);
+
+/**
* end_page_writeback - end writeback against a page
* @page: the page
*/
@@ -1969,8 +2030,14 @@ unlock:
put:
put_page(page);
next:
- if (!xa_is_value(page) && PageTransHuge(page))
- xas_set(&xas, page->index + thp_nr_pages(page));
+ if (!xa_is_value(page) && PageTransHuge(page)) {
+ unsigned int nr_pages = thp_nr_pages(page);
+
+ /* Final THP may cross MAX_LFS_FILESIZE on 32-bit */
+ xas_set(&xas, page->index + nr_pages);
+ if (xas.xa_index < nr_pages)
+ break;
+ }
}
rcu_read_unlock();
@@ -2672,7 +2739,7 @@ loff_t mapping_seek_hole_data(struct address_space *mapping, loff_t start,
loff_t end, int whence)
{
XA_STATE(xas, &mapping->i_pages, start >> PAGE_SHIFT);
- pgoff_t max = (end - 1) / PAGE_SIZE;
+ pgoff_t max = (end - 1) >> PAGE_SHIFT;
bool seek_data = (whence == SEEK_DATA);
struct page *page;
@@ -2681,7 +2748,8 @@ loff_t mapping_seek_hole_data(struct address_space *mapping, loff_t start,
rcu_read_lock();
while ((page = find_get_entry(&xas, max, XA_PRESENT))) {
- loff_t pos = xas.xa_index * PAGE_SIZE;
+ loff_t pos = (u64)xas.xa_index << PAGE_SHIFT;
+ unsigned int seek_size;
if (start < pos) {
if (!seek_data)
@@ -2689,25 +2757,25 @@ loff_t mapping_seek_hole_data(struct address_space *mapping, loff_t start,
start = pos;
}
- pos += seek_page_size(&xas, page);
+ seek_size = seek_page_size(&xas, page);
+ pos = round_up(pos + 1, seek_size);
start = page_seek_hole_data(&xas, mapping, page, start, pos,
seek_data);
if (start < pos)
goto unlock;
+ if (start >= end)
+ break;
+ if (seek_size > PAGE_SIZE)
+ xas_set(&xas, pos >> PAGE_SHIFT);
if (!xa_is_value(page))
put_page(page);
}
- rcu_read_unlock();
-
if (seek_data)
- return -ENXIO;
- goto out;
-
+ start = -ENXIO;
unlock:
rcu_read_unlock();
- if (!xa_is_value(page))
+ if (page && !xa_is_value(page))
put_page(page);
-out:
if (start > end)
return end;
return start;
@@ -2771,7 +2839,7 @@ static struct file *do_sync_mmap_readahead(struct vm_fault *vmf)
struct file *file = vmf->vma->vm_file;
struct file_ra_state *ra = &file->f_ra;
struct address_space *mapping = file->f_mapping;
- DEFINE_READAHEAD(ractl, file, mapping, vmf->pgoff);
+ DEFINE_READAHEAD(ractl, file, ra, mapping, vmf->pgoff);
struct file *fpin = NULL;
unsigned int mmap_miss;
@@ -2783,7 +2851,7 @@ static struct file *do_sync_mmap_readahead(struct vm_fault *vmf)
if (vmf->vma->vm_flags & VM_SEQ_READ) {
fpin = maybe_unlock_mmap_for_io(vmf, fpin);
- page_cache_sync_ra(&ractl, ra, ra->ra_pages);
+ page_cache_sync_ra(&ractl, ra->ra_pages);
return fpin;
}
diff --git a/mm/gup.c b/mm/gup.c
index e40579624f10..ef7d2da9f03f 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -1535,6 +1535,10 @@ struct page *get_dump_page(unsigned long addr)
FOLL_FORCE | FOLL_DUMP | FOLL_GET);
if (locked)
mmap_read_unlock(mm);
+
+ if (ret == 1 && is_page_poisoned(page))
+ return NULL;
+
return (ret == 1) ? page : NULL;
}
#endif /* CONFIG_ELF_CORE */
diff --git a/mm/highmem.c b/mm/highmem.c
index 874b732b120c..6ef8f5e05e7e 100644
--- a/mm/highmem.c
+++ b/mm/highmem.c
@@ -368,20 +368,24 @@ void zero_user_segments(struct page *page, unsigned start1, unsigned end1,
BUG_ON(end1 > page_size(page) || end2 > page_size(page));
+ if (start1 >= end1)
+ start1 = end1 = 0;
+ if (start2 >= end2)
+ start2 = end2 = 0;
+
for (i = 0; i < compound_nr(page); i++) {
void *kaddr = NULL;
- if (start1 < PAGE_SIZE || start2 < PAGE_SIZE)
- kaddr = kmap_atomic(page + i);
-
if (start1 >= PAGE_SIZE) {
start1 -= PAGE_SIZE;
end1 -= PAGE_SIZE;
} else {
unsigned this_end = min_t(unsigned, end1, PAGE_SIZE);
- if (end1 > start1)
+ if (end1 > start1) {
+ kaddr = kmap_atomic(page + i);
memset(kaddr + start1, 0, this_end - start1);
+ }
end1 -= this_end;
start1 = 0;
}
@@ -392,8 +396,11 @@ void zero_user_segments(struct page *page, unsigned start1, unsigned end1,
} else {
unsigned this_end = min_t(unsigned, end2, PAGE_SIZE);
- if (end2 > start2)
+ if (end2 > start2) {
+ if (!kaddr)
+ kaddr = kmap_atomic(page + i);
memset(kaddr + start2, 0, this_end - start2);
+ }
end2 -= this_end;
start2 = 0;
}
@@ -611,7 +618,7 @@ void __kmap_local_sched_out(void)
int idx;
/* With debug all even slots are unmapped and act as guard */
- if (IS_ENABLED(CONFIG_DEBUG_HIGHMEM) && !(i & 0x01)) {
+ if (IS_ENABLED(CONFIG_DEBUG_KMAP_LOCAL) && !(i & 0x01)) {
WARN_ON_ONCE(!pte_none(pteval));
continue;
}
@@ -647,7 +654,7 @@ void __kmap_local_sched_in(void)
int idx;
/* With debug all even slots are unmapped and act as guard */
- if (IS_ENABLED(CONFIG_DEBUG_HIGHMEM) && !(i & 0x01)) {
+ if (IS_ENABLED(CONFIG_DEBUG_KMAP_LOCAL) && !(i & 0x01)) {
WARN_ON_ONCE(!pte_none(pteval));
continue;
}
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 395c75111d33..ae907a9c2050 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1100,9 +1100,7 @@ int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm,
* best effort that the pinned pages won't be replaced by another
* random page during the coming copy-on-write.
*/
- if (unlikely(is_cow_mapping(vma->vm_flags) &&
- atomic_read(&src_mm->has_pinned) &&
- page_maybe_dma_pinned(src_page))) {
+ if (unlikely(page_needs_cow_for_dma(vma, src_page))) {
pte_free(dst_mm, pgtable);
spin_unlock(src_ptl);
spin_unlock(dst_ptl);
@@ -1214,9 +1212,7 @@ int copy_huge_pud(struct mm_struct *dst_mm, struct mm_struct *src_mm,
}
/* Please refer to comments in copy_huge_pmd() */
- if (unlikely(is_cow_mapping(vma->vm_flags) &&
- atomic_read(&src_mm->has_pinned) &&
- page_maybe_dma_pinned(pud_page(pud)))) {
+ if (unlikely(page_needs_cow_for_dma(vma, pud_page(pud)))) {
spin_unlock(src_ptl);
spin_unlock(dst_ptl);
__split_huge_pud(vma, src_pud, addr);
@@ -2471,7 +2467,7 @@ static void __split_huge_page(struct page *page, struct list_head *list,
int i;
/* complete memcg works before add pages to LRU */
- mem_cgroup_split_huge_fixup(head);
+ split_page_memcg(head, nr);
if (PageAnon(head) && PageSwapCache(head)) {
swp_entry_t entry = { .val = page_private(head) };
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 8fb42c6dd74b..a86a58ef132d 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -280,6 +280,17 @@ static void record_hugetlb_cgroup_uncharge_info(struct hugetlb_cgroup *h_cg,
nrg->reservation_counter =
&h_cg->rsvd_hugepage[hstate_index(h)];
nrg->css = &h_cg->css;
+ /*
+ * The caller will hold exactly one h_cg->css reference for the
+ * whole contiguous reservation region. But this area might be
+ * scattered when there are already some file_regions reside in
+ * it. As a result, many file_regions may share only one css
+ * reference. In order to ensure that one file_region must hold
+ * exactly one h_cg->css reference, we should do css_get for
+ * each file_region and leave the reference held by caller
+ * untouched.
+ */
+ css_get(&h_cg->css);
if (!resv->pages_per_hpage)
resv->pages_per_hpage = pages_per_huge_page(h);
/* pages_per_hpage should be the same for all entries in
@@ -293,6 +304,14 @@ static void record_hugetlb_cgroup_uncharge_info(struct hugetlb_cgroup *h_cg,
#endif
}
+static void put_uncharge_info(struct file_region *rg)
+{
+#ifdef CONFIG_CGROUP_HUGETLB
+ if (rg->css)
+ css_put(rg->css);
+#endif
+}
+
static bool has_same_uncharge_info(struct file_region *rg,
struct file_region *org)
{
@@ -316,6 +335,7 @@ static void coalesce_file_region(struct resv_map *resv, struct file_region *rg)
prg->to = rg->to;
list_del(&rg->link);
+ put_uncharge_info(rg);
kfree(rg);
rg = prg;
@@ -327,10 +347,29 @@ static void coalesce_file_region(struct resv_map *resv, struct file_region *rg)
nrg->from = rg->from;
list_del(&rg->link);
+ put_uncharge_info(rg);
kfree(rg);
}
}
+static inline long
+hugetlb_resv_map_add(struct resv_map *map, struct file_region *rg, long from,
+ long to, struct hstate *h, struct hugetlb_cgroup *cg,
+ long *regions_needed)
+{
+ struct file_region *nrg;
+
+ if (!regions_needed) {
+ nrg = get_file_region_entry_from_cache(map, from, to);
+ record_hugetlb_cgroup_uncharge_info(cg, h, map, nrg);
+ list_add(&nrg->link, rg->link.prev);
+ coalesce_file_region(map, nrg);
+ } else
+ *regions_needed += 1;
+
+ return to - from;
+}
+
/*
* Must be called with resv->lock held.
*
@@ -346,7 +385,7 @@ static long add_reservation_in_range(struct resv_map *resv, long f, long t,
long add = 0;
struct list_head *head = &resv->regions;
long last_accounted_offset = f;
- struct file_region *rg = NULL, *trg = NULL, *nrg = NULL;
+ struct file_region *rg = NULL, *trg = NULL;
if (regions_needed)
*regions_needed = 0;
@@ -369,24 +408,17 @@ static long add_reservation_in_range(struct resv_map *resv, long f, long t,
/* When we find a region that starts beyond our range, we've
* finished.
*/
- if (rg->from > t)
+ if (rg->from >= t)
break;
/* Add an entry for last_accounted_offset -> rg->from, and
* update last_accounted_offset.
*/
- if (rg->from > last_accounted_offset) {
- add += rg->from - last_accounted_offset;
- if (!regions_needed) {
- nrg = get_file_region_entry_from_cache(
- resv, last_accounted_offset, rg->from);
- record_hugetlb_cgroup_uncharge_info(h_cg, h,
- resv, nrg);
- list_add(&nrg->link, rg->link.prev);
- coalesce_file_region(resv, nrg);
- } else
- *regions_needed += 1;
- }
+ if (rg->from > last_accounted_offset)
+ add += hugetlb_resv_map_add(resv, rg,
+ last_accounted_offset,
+ rg->from, h, h_cg,
+ regions_needed);
last_accounted_offset = rg->to;
}
@@ -394,17 +426,9 @@ static long add_reservation_in_range(struct resv_map *resv, long f, long t,
/* Handle the case where our range extends beyond
* last_accounted_offset.
*/
- if (last_accounted_offset < t) {
- add += t - last_accounted_offset;
- if (!regions_needed) {
- nrg = get_file_region_entry_from_cache(
- resv, last_accounted_offset, t);
- record_hugetlb_cgroup_uncharge_info(h_cg, h, resv, nrg);
- list_add(&nrg->link, rg->link.prev);
- coalesce_file_region(resv, nrg);
- } else
- *regions_needed += 1;
- }
+ if (last_accounted_offset < t)
+ add += hugetlb_resv_map_add(resv, rg, last_accounted_offset,
+ t, h, h_cg, regions_needed);
VM_BUG_ON(add < 0);
return add;
@@ -659,7 +683,7 @@ retry:
del += t - f;
hugetlb_cgroup_uncharge_file_region(
- resv, rg, t - f);
+ resv, rg, t - f, false);
/* New entry for end of split region */
nrg->from = t;
@@ -680,7 +704,7 @@ retry:
if (f <= rg->from && t >= rg->to) { /* Remove entire region */
del += rg->to - rg->from;
hugetlb_cgroup_uncharge_file_region(resv, rg,
- rg->to - rg->from);
+ rg->to - rg->from, true);
list_del(&rg->link);
kfree(rg);
continue;
@@ -688,13 +712,13 @@ retry:
if (f <= rg->from) { /* Trim beginning of region */
hugetlb_cgroup_uncharge_file_region(resv, rg,
- t - rg->from);
+ t - rg->from, false);
del += t - rg->from;
rg->from = t;
} else { /* Trim end of region */
hugetlb_cgroup_uncharge_file_region(resv, rg,
- rg->to - f);
+ rg->to - f, false);
del += rg->to - f;
rg->to = f;
@@ -3725,21 +3749,32 @@ static bool is_hugetlb_entry_hwpoisoned(pte_t pte)
return false;
}
+static void
+hugetlb_install_page(struct vm_area_struct *vma, pte_t *ptep, unsigned long addr,
+ struct page *new_page)
+{
+ __SetPageUptodate(new_page);
+ set_huge_pte_at(vma->vm_mm, addr, ptep, make_huge_pte(vma, new_page, 1));
+ hugepage_add_new_anon_rmap(new_page, vma, addr);
+ hugetlb_count_add(pages_per_huge_page(hstate_vma(vma)), vma->vm_mm);
+ ClearHPageRestoreReserve(new_page);
+ SetHPageMigratable(new_page);
+}
+
int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
struct vm_area_struct *vma)
{
pte_t *src_pte, *dst_pte, entry, dst_entry;
struct page *ptepage;
unsigned long addr;
- int cow;
+ bool cow = is_cow_mapping(vma->vm_flags);
struct hstate *h = hstate_vma(vma);
unsigned long sz = huge_page_size(h);
+ unsigned long npages = pages_per_huge_page(h);
struct address_space *mapping = vma->vm_file->f_mapping;
struct mmu_notifier_range range;
int ret = 0;
- cow = (vma->vm_flags & (VM_SHARED | VM_MAYWRITE)) == VM_MAYWRITE;
-
if (cow) {
mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, src,
vma->vm_start,
@@ -3784,6 +3819,7 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING);
entry = huge_ptep_get(src_pte);
dst_entry = huge_ptep_get(dst_pte);
+again:
if (huge_pte_none(entry) || !huge_pte_none(dst_entry)) {
/*
* Skip if src entry none. Also, skip in the
@@ -3807,6 +3843,52 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
}
set_huge_swap_pte_at(dst, addr, dst_pte, entry, sz);
} else {
+ entry = huge_ptep_get(src_pte);
+ ptepage = pte_page(entry);
+ get_page(ptepage);
+
+ /*
+ * This is a rare case where we see pinned hugetlb
+ * pages while they're prone to COW. We need to do the
+ * COW earlier during fork.
+ *
+ * When pre-allocating the page or copying data, we
+ * need to be without the pgtable locks since we could
+ * sleep during the process.
+ */
+ if (unlikely(page_needs_cow_for_dma(vma, ptepage))) {
+ pte_t src_pte_old = entry;
+ struct page *new;
+
+ spin_unlock(src_ptl);
+ spin_unlock(dst_ptl);
+ /* Do not use reserve as it's private owned */
+ new = alloc_huge_page(vma, addr, 1);
+ if (IS_ERR(new)) {
+ put_page(ptepage);
+ ret = PTR_ERR(new);
+ break;
+ }
+ copy_user_huge_page(new, ptepage, addr, vma,
+ npages);
+ put_page(ptepage);
+
+ /* Install the new huge page if src pte stable */
+ dst_ptl = huge_pte_lock(h, dst, dst_pte);
+ src_ptl = huge_pte_lockptr(h, src, src_pte);
+ spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING);
+ entry = huge_ptep_get(src_pte);
+ if (!pte_same(src_pte_old, entry)) {
+ put_page(new);
+ /* dst_entry won't change as in child */
+ goto again;
+ }
+ hugetlb_install_page(vma, dst_pte, addr, new);
+ spin_unlock(src_ptl);
+ spin_unlock(dst_ptl);
+ continue;
+ }
+
if (cow) {
/*
* No need to notify as we are downgrading page
@@ -3817,12 +3899,10 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
*/
huge_ptep_set_wrprotect(src, addr, src_pte);
}
- entry = huge_ptep_get(src_pte);
- ptepage = pte_page(entry);
- get_page(ptepage);
+
page_dup_rmap(ptepage, true);
set_huge_pte_at(dst, addr, dst_pte, entry);
- hugetlb_count_add(pages_per_huge_page(h), dst);
+ hugetlb_count_add(npages, dst);
}
spin_unlock(src_ptl);
spin_unlock(dst_ptl);
@@ -5128,6 +5208,10 @@ bool hugetlb_reserve_pages(struct inode *inode,
*/
long rsv_adjust;
+ /*
+ * hugetlb_cgroup_uncharge_cgroup_rsvd() will put the
+ * reference to h_cg->css. See comment below for detail.
+ */
hugetlb_cgroup_uncharge_cgroup_rsvd(
hstate_index(h),
(chg - add) * pages_per_huge_page(h), h_cg);
@@ -5135,6 +5219,14 @@ bool hugetlb_reserve_pages(struct inode *inode,
rsv_adjust = hugepage_subpool_put_pages(spool,
chg - add);
hugetlb_acct_memory(h, -rsv_adjust);
+ } else if (h_cg) {
+ /*
+ * The file_regions will hold their own reference to
+ * h_cg->css. So we should release the reference held
+ * via hugetlb_cgroup_charge_cgroup_rsvd() when we are
+ * done.
+ */
+ hugetlb_cgroup_put_rsvd_cgroup(h_cg);
}
}
return true;
diff --git a/mm/hugetlb_cgroup.c b/mm/hugetlb_cgroup.c
index f68b51fcda3d..603a131e262d 100644
--- a/mm/hugetlb_cgroup.c
+++ b/mm/hugetlb_cgroup.c
@@ -391,7 +391,8 @@ void hugetlb_cgroup_uncharge_counter(struct resv_map *resv, unsigned long start,
void hugetlb_cgroup_uncharge_file_region(struct resv_map *resv,
struct file_region *rg,
- unsigned long nr_pages)
+ unsigned long nr_pages,
+ bool region_del)
{
if (hugetlb_cgroup_disabled() || !resv || !rg || !nr_pages)
return;
@@ -400,7 +401,12 @@ void hugetlb_cgroup_uncharge_file_region(struct resv_map *resv,
!resv->reservation_counter) {
page_counter_uncharge(rg->reservation_counter,
nr_pages * resv->pages_per_hpage);
- css_put(rg->css);
+ /*
+ * Only do css_put(rg->css) when we delete the entire region
+ * because one file_region must hold exactly one css reference.
+ */
+ if (region_del)
+ css_put(rg->css);
}
}
diff --git a/mm/internal.h b/mm/internal.h
index 9902648f2206..bbe900f9f095 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -51,13 +51,12 @@ void unmap_page_range(struct mmu_gather *tlb,
void do_page_cache_ra(struct readahead_control *, unsigned long nr_to_read,
unsigned long lookahead_size);
-void force_page_cache_ra(struct readahead_control *, struct file_ra_state *,
- unsigned long nr);
+void force_page_cache_ra(struct readahead_control *, unsigned long nr);
static inline void force_page_cache_readahead(struct address_space *mapping,
struct file *file, pgoff_t index, unsigned long nr_to_read)
{
- DEFINE_READAHEAD(ractl, file, mapping, index);
- force_page_cache_ra(&ractl, &file->f_ra, nr_to_read);
+ DEFINE_READAHEAD(ractl, file, &file->f_ra, mapping, index);
+ force_page_cache_ra(&ractl, nr_to_read);
}
unsigned find_lock_entries(struct address_space *mapping, pgoff_t start,
@@ -97,6 +96,26 @@ static inline void set_page_refcounted(struct page *page)
set_page_count(page, 1);
}
+/*
+ * When kernel touch the user page, the user page may be have been marked
+ * poison but still mapped in user space, if without this page, the kernel
+ * can guarantee the data integrity and operation success, the kernel is
+ * better to check the posion status and avoid touching it, be good not to
+ * panic, coredump for process fatal signal is a sample case matching this
+ * scenario. Or if kernel can't guarantee the data integrity, it's better
+ * not to call this function, let kernel touch the poison page and get to
+ * panic.
+ */
+static inline bool is_page_poisoned(struct page *page)
+{
+ if (PageHWPoison(page))
+ return true;
+ else if (PageHuge(page) && PageHWPoison(compound_head(page)))
+ return true;
+
+ return false;
+}
+
extern unsigned long highest_memmap_pfn;
/*
@@ -296,11 +315,6 @@ static inline unsigned int buddy_order(struct page *page)
*/
#define buddy_order_unsafe(page) READ_ONCE(page_private(page))
-static inline bool is_cow_mapping(vm_flags_t flags)
-{
- return (flags & (VM_SHARED | VM_MAYWRITE)) == VM_MAYWRITE;
-}
-
/*
* These three helpers classifies VMAs for virtual memory accounting.
*/
diff --git a/mm/kasan/common.c b/mm/kasan/common.c
index b5e08d4cefec..7b53291dafa1 100644
--- a/mm/kasan/common.c
+++ b/mm/kasan/common.c
@@ -63,7 +63,7 @@ void __kasan_unpoison_range(const void *address, size_t size)
kasan_unpoison(address, size);
}
-#if CONFIG_KASAN_STACK
+#ifdef CONFIG_KASAN_STACK
/* Unpoison the entire stack for a task. */
void kasan_unpoison_task_stack(struct task_struct *task)
{
diff --git a/mm/kasan/hw_tags.c b/mm/kasan/hw_tags.c
index 2aad21fda156..4004388b4e4b 100644
--- a/mm/kasan/hw_tags.c
+++ b/mm/kasan/hw_tags.c
@@ -25,6 +25,12 @@ enum kasan_arg {
KASAN_ARG_ON,
};
+enum kasan_arg_mode {
+ KASAN_ARG_MODE_DEFAULT,
+ KASAN_ARG_MODE_SYNC,
+ KASAN_ARG_MODE_ASYNC,
+};
+
enum kasan_arg_stacktrace {
KASAN_ARG_STACKTRACE_DEFAULT,
KASAN_ARG_STACKTRACE_OFF,
@@ -38,6 +44,7 @@ enum kasan_arg_fault {
};
static enum kasan_arg kasan_arg __ro_after_init;
+static enum kasan_arg_mode kasan_arg_mode __ro_after_init;
static enum kasan_arg_stacktrace kasan_arg_stacktrace __ro_after_init;
static enum kasan_arg_fault kasan_arg_fault __ro_after_init;
@@ -45,6 +52,10 @@ static enum kasan_arg_fault kasan_arg_fault __ro_after_init;
DEFINE_STATIC_KEY_FALSE(kasan_flag_enabled);
EXPORT_SYMBOL(kasan_flag_enabled);
+/* Whether the asynchronous mode is enabled. */
+bool kasan_flag_async __ro_after_init;
+EXPORT_SYMBOL_GPL(kasan_flag_async);
+
/* Whether to collect alloc/free stack traces. */
DEFINE_STATIC_KEY_FALSE(kasan_flag_stacktrace);
@@ -68,6 +79,23 @@ static int __init early_kasan_flag(char *arg)
}
early_param("kasan", early_kasan_flag);
+/* kasan.mode=sync/async */
+static int __init early_kasan_mode(char *arg)
+{
+ if (!arg)
+ return -EINVAL;
+
+ if (!strcmp(arg, "sync"))
+ kasan_arg_mode = KASAN_ARG_MODE_SYNC;
+ else if (!strcmp(arg, "async"))
+ kasan_arg_mode = KASAN_ARG_MODE_ASYNC;
+ else
+ return -EINVAL;
+
+ return 0;
+}
+early_param("kasan.mode", early_kasan_mode);
+
/* kasan.stacktrace=off/on */
static int __init early_kasan_flag_stacktrace(char *arg)
{
@@ -115,7 +143,15 @@ void kasan_init_hw_tags_cpu(void)
return;
hw_init_tags(KASAN_TAG_MAX);
- hw_enable_tagging();
+
+ /*
+ * Enable async mode only when explicitly requested through
+ * the command line.
+ */
+ if (kasan_arg_mode == KASAN_ARG_MODE_ASYNC)
+ hw_enable_tagging_async();
+ else
+ hw_enable_tagging_sync();
}
/* kasan_init_hw_tags() is called once on boot CPU. */
@@ -132,6 +168,22 @@ void __init kasan_init_hw_tags(void)
/* Enable KASAN. */
static_branch_enable(&kasan_flag_enabled);
+ switch (kasan_arg_mode) {
+ case KASAN_ARG_MODE_DEFAULT:
+ /*
+ * Default to sync mode.
+ * Do nothing, kasan_flag_async keeps its default value.
+ */
+ break;
+ case KASAN_ARG_MODE_SYNC:
+ /* Do nothing, kasan_flag_async keeps its default value. */
+ break;
+ case KASAN_ARG_MODE_ASYNC:
+ /* Async mode enabled. */
+ kasan_flag_async = true;
+ break;
+ }
+
switch (kasan_arg_stacktrace) {
case KASAN_ARG_STACKTRACE_DEFAULT:
/* Default to enabling stack trace collection. */
@@ -194,10 +246,16 @@ void kasan_set_tagging_report_once(bool state)
}
EXPORT_SYMBOL_GPL(kasan_set_tagging_report_once);
-void kasan_enable_tagging(void)
+void kasan_enable_tagging_sync(void)
+{
+ hw_enable_tagging_sync();
+}
+EXPORT_SYMBOL_GPL(kasan_enable_tagging_sync);
+
+void kasan_force_async_fault(void)
{
- hw_enable_tagging();
+ hw_force_async_tag_fault();
}
-EXPORT_SYMBOL_GPL(kasan_enable_tagging);
+EXPORT_SYMBOL_GPL(kasan_force_async_fault);
#endif
diff --git a/mm/kasan/kasan.h b/mm/kasan/kasan.h
index 8c55634d6edd..c1581e8a9b8e 100644
--- a/mm/kasan/kasan.h
+++ b/mm/kasan/kasan.h
@@ -7,20 +7,37 @@
#include <linux/stackdepot.h>
#ifdef CONFIG_KASAN_HW_TAGS
+
#include <linux/static_key.h>
+
DECLARE_STATIC_KEY_FALSE(kasan_flag_stacktrace);
+extern bool kasan_flag_async __ro_after_init;
+
static inline bool kasan_stack_collection_enabled(void)
{
return static_branch_unlikely(&kasan_flag_stacktrace);
}
+
+static inline bool kasan_async_mode_enabled(void)
+{
+ return kasan_flag_async;
+}
#else
+
static inline bool kasan_stack_collection_enabled(void)
{
return true;
}
+
+static inline bool kasan_async_mode_enabled(void)
+{
+ return false;
+}
+
#endif
extern bool kasan_flag_panic __ro_after_init;
+extern bool kasan_flag_async __ro_after_init;
#if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS)
#define KASAN_GRANULE_SIZE (1UL << KASAN_SHADOW_SCALE_SHIFT)
@@ -231,7 +248,7 @@ void *kasan_find_first_bad_addr(void *addr, size_t size);
const char *kasan_get_bug_type(struct kasan_access_info *info);
void kasan_metadata_fetch_row(char *buffer, void *row);
-#if defined(CONFIG_KASAN_GENERIC) && CONFIG_KASAN_STACK
+#if defined(CONFIG_KASAN_GENERIC) && defined(CONFIG_KASAN_STACK)
void kasan_print_address_stack_frame(const void *addr);
#else
static inline void kasan_print_address_stack_frame(const void *addr) { }
@@ -275,8 +292,11 @@ static inline const void *arch_kasan_set_tag(const void *addr, u8 tag)
#ifdef CONFIG_KASAN_HW_TAGS
-#ifndef arch_enable_tagging
-#define arch_enable_tagging()
+#ifndef arch_enable_tagging_sync
+#define arch_enable_tagging_sync()
+#endif
+#ifndef arch_enable_tagging_async
+#define arch_enable_tagging_async()
#endif
#ifndef arch_init_tags
#define arch_init_tags(max_tag)
@@ -284,6 +304,9 @@ static inline const void *arch_kasan_set_tag(const void *addr, u8 tag)
#ifndef arch_set_tagging_report_once
#define arch_set_tagging_report_once(state)
#endif
+#ifndef arch_force_async_tag_fault
+#define arch_force_async_tag_fault()
+#endif
#ifndef arch_get_random_tag
#define arch_get_random_tag() (0xFF)
#endif
@@ -294,16 +317,19 @@ static inline const void *arch_kasan_set_tag(const void *addr, u8 tag)
#define arch_set_mem_tag_range(addr, size, tag) ((void *)(addr))
#endif
-#define hw_enable_tagging() arch_enable_tagging()
+#define hw_enable_tagging_sync() arch_enable_tagging_sync()
+#define hw_enable_tagging_async() arch_enable_tagging_async()
#define hw_init_tags(max_tag) arch_init_tags(max_tag)
#define hw_set_tagging_report_once(state) arch_set_tagging_report_once(state)
+#define hw_force_async_tag_fault() arch_force_async_tag_fault()
#define hw_get_random_tag() arch_get_random_tag()
#define hw_get_mem_tag(addr) arch_get_mem_tag(addr)
#define hw_set_mem_tag_range(addr, size, tag) arch_set_mem_tag_range((addr), (size), (tag))
#else /* CONFIG_KASAN_HW_TAGS */
-#define hw_enable_tagging()
+#define hw_enable_tagging_sync()
+#define hw_enable_tagging_async()
#define hw_set_tagging_report_once(state)
#endif /* CONFIG_KASAN_HW_TAGS */
@@ -311,12 +337,14 @@ static inline const void *arch_kasan_set_tag(const void *addr, u8 tag)
#if defined(CONFIG_KASAN_HW_TAGS) && IS_ENABLED(CONFIG_KASAN_KUNIT_TEST)
void kasan_set_tagging_report_once(bool state);
-void kasan_enable_tagging(void);
+void kasan_enable_tagging_sync(void);
+void kasan_force_async_fault(void);
#else /* CONFIG_KASAN_HW_TAGS || CONFIG_KASAN_KUNIT_TEST */
static inline void kasan_set_tagging_report_once(bool state) { }
-static inline void kasan_enable_tagging(void) { }
+static inline void kasan_enable_tagging_sync(void) { }
+static inline void kasan_force_async_fault(void) { }
#endif /* CONFIG_KASAN_HW_TAGS || CONFIG_KASAN_KUNIT_TEST */
diff --git a/mm/kasan/report.c b/mm/kasan/report.c
index 87b271206163..14bd51ea2348 100644
--- a/mm/kasan/report.c
+++ b/mm/kasan/report.c
@@ -87,7 +87,8 @@ static void start_report(unsigned long *flags)
static void end_report(unsigned long *flags, unsigned long addr)
{
- trace_error_report_end(ERROR_DETECTOR_KASAN, addr);
+ if (!kasan_async_mode_enabled())
+ trace_error_report_end(ERROR_DETECTOR_KASAN, addr);
pr_err("==================================================================\n");
add_taint(TAINT_BAD_PAGE, LOCKDEP_NOW_UNRELIABLE);
spin_unlock_irqrestore(&report_lock, *flags);
@@ -360,6 +361,25 @@ void kasan_report_invalid_free(void *object, unsigned long ip)
end_report(&flags, (unsigned long)object);
}
+#ifdef CONFIG_KASAN_HW_TAGS
+void kasan_report_async(void)
+{
+ unsigned long flags;
+
+#if IS_ENABLED(CONFIG_KUNIT)
+ if (current->kunit_test)
+ kasan_update_kunit_status(current->kunit_test);
+#endif /* IS_ENABLED(CONFIG_KUNIT) */
+
+ start_report(&flags);
+ pr_err("BUG: KASAN: invalid-access\n");
+ pr_err("Asynchronous mode enabled: no access details available\n");
+ pr_err("\n");
+ dump_stack();
+ end_report(&flags, 0);
+}
+#endif /* CONFIG_KASAN_HW_TAGS */
+
static void __kasan_report(unsigned long addr, size_t size, bool is_write,
unsigned long ip)
{
diff --git a/mm/kasan/report_generic.c b/mm/kasan/report_generic.c
index 41f374585144..de732bc341c5 100644
--- a/mm/kasan/report_generic.c
+++ b/mm/kasan/report_generic.c
@@ -128,7 +128,7 @@ void kasan_metadata_fetch_row(char *buffer, void *row)
memcpy(buffer, kasan_mem_to_shadow(row), META_BYTES_PER_ROW);
}
-#if CONFIG_KASAN_STACK
+#ifdef CONFIG_KASAN_STACK
static bool __must_check tokenize_frame_descr(const char **frame_descr,
char *token, size_t max_tok_len,
unsigned long *value)
diff --git a/mm/kfence/core.c b/mm/kfence/core.c
index 3b8ec938470a..d53c91f881a4 100644
--- a/mm/kfence/core.c
+++ b/mm/kfence/core.c
@@ -12,6 +12,7 @@
#include <linux/debugfs.h>
#include <linux/kcsan-checks.h>
#include <linux/kfence.h>
+#include <linux/kmemleak.h>
#include <linux/list.h>
#include <linux/lockdep.h>
#include <linux/memblock.h>
@@ -480,6 +481,14 @@ static bool __init kfence_init_pool(void)
addr += 2 * PAGE_SIZE;
}
+ /*
+ * The pool is live and will never be deallocated from this point on.
+ * Remove the pool object from the kmemleak object tree, as it would
+ * otherwise overlap with allocations returned by kfence_alloc(), which
+ * are registered with kmemleak through the slab post-alloc hook.
+ */
+ kmemleak_free(__kfence_pool);
+
return true;
err:
diff --git a/mm/kfence/report.c b/mm/kfence/report.c
index ab83d5a59bb1..e3f71451ad9e 100644
--- a/mm/kfence/report.c
+++ b/mm/kfence/report.c
@@ -20,6 +20,11 @@
#include "kfence.h"
+/* May be overridden by <asm/kfence.h>. */
+#ifndef ARCH_FUNC_PREFIX
+#define ARCH_FUNC_PREFIX ""
+#endif
+
extern bool no_hash_pointers;
/* Helper function to either print to a seq_file or to console. */
@@ -67,8 +72,9 @@ static int get_stack_skipnr(const unsigned long stack_entries[], int num_entries
for (skipnr = 0; skipnr < num_entries; skipnr++) {
int len = scnprintf(buf, sizeof(buf), "%ps", (void *)stack_entries[skipnr]);
- if (str_has_prefix(buf, "kfence_") || str_has_prefix(buf, "__kfence_") ||
- !strncmp(buf, "__slab_free", len)) {
+ if (str_has_prefix(buf, ARCH_FUNC_PREFIX "kfence_") ||
+ str_has_prefix(buf, ARCH_FUNC_PREFIX "__kfence_") ||
+ !strncmp(buf, ARCH_FUNC_PREFIX "__slab_free", len)) {
/*
* In case of tail calls from any of the below
* to any of the above.
@@ -77,10 +83,10 @@ static int get_stack_skipnr(const unsigned long stack_entries[], int num_entries
}
/* Also the *_bulk() variants by only checking prefixes. */
- if (str_has_prefix(buf, "kfree") ||
- str_has_prefix(buf, "kmem_cache_free") ||
- str_has_prefix(buf, "__kmalloc") ||
- str_has_prefix(buf, "kmem_cache_alloc"))
+ if (str_has_prefix(buf, ARCH_FUNC_PREFIX "kfree") ||
+ str_has_prefix(buf, ARCH_FUNC_PREFIX "kmem_cache_free") ||
+ str_has_prefix(buf, ARCH_FUNC_PREFIX "__kmalloc") ||
+ str_has_prefix(buf, ARCH_FUNC_PREFIX "kmem_cache_alloc"))
goto found;
}
if (fallback < num_entries)
@@ -116,12 +122,12 @@ void kfence_print_object(struct seq_file *seq, const struct kfence_metadata *met
lockdep_assert_held(&meta->lock);
if (meta->state == KFENCE_OBJECT_UNUSED) {
- seq_con_printf(seq, "kfence-#%zd unused\n", meta - kfence_metadata);
+ seq_con_printf(seq, "kfence-#%td unused\n", meta - kfence_metadata);
return;
}
seq_con_printf(seq,
- "kfence-#%zd [0x%p-0x%p"
+ "kfence-#%td [0x%p-0x%p"
", size=%d, cache=%s] allocated by task %d:\n",
meta - kfence_metadata, (void *)start, (void *)(start + size - 1), size,
(cache && cache->name) ? cache->name : "<destroyed>", meta->alloc_track.pid);
@@ -204,7 +210,7 @@ void kfence_report_error(unsigned long address, bool is_write, struct pt_regs *r
pr_err("BUG: KFENCE: out-of-bounds %s in %pS\n\n", get_access_type(is_write),
(void *)stack_entries[skipnr]);
- pr_err("Out-of-bounds %s at 0x%p (%luB %s of kfence-#%zd):\n",
+ pr_err("Out-of-bounds %s at 0x%p (%luB %s of kfence-#%td):\n",
get_access_type(is_write), (void *)address,
left_of_object ? meta->addr - address : address - meta->addr,
left_of_object ? "left" : "right", object_index);
@@ -213,14 +219,14 @@ void kfence_report_error(unsigned long address, bool is_write, struct pt_regs *r
case KFENCE_ERROR_UAF:
pr_err("BUG: KFENCE: use-after-free %s in %pS\n\n", get_access_type(is_write),
(void *)stack_entries[skipnr]);
- pr_err("Use-after-free %s at 0x%p (in kfence-#%zd):\n",
+ pr_err("Use-after-free %s at 0x%p (in kfence-#%td):\n",
get_access_type(is_write), (void *)address, object_index);
break;
case KFENCE_ERROR_CORRUPTION:
pr_err("BUG: KFENCE: memory corruption in %pS\n\n", (void *)stack_entries[skipnr]);
pr_err("Corrupted memory at 0x%p ", (void *)address);
print_diff_canary(address, 16, meta);
- pr_cont(" (in kfence-#%zd):\n", object_index);
+ pr_cont(" (in kfence-#%td):\n", object_index);
break;
case KFENCE_ERROR_INVALID:
pr_err("BUG: KFENCE: invalid %s in %pS\n\n", get_access_type(is_write),
@@ -230,7 +236,7 @@ void kfence_report_error(unsigned long address, bool is_write, struct pt_regs *r
break;
case KFENCE_ERROR_INVALID_FREE:
pr_err("BUG: KFENCE: invalid free in %pS\n\n", (void *)stack_entries[skipnr]);
- pr_err("Invalid free of 0x%p (in kfence-#%zd):\n", (void *)address,
+ pr_err("Invalid free of 0x%p (in kfence-#%td):\n", (void *)address,
object_index);
break;
}
diff --git a/mm/kmemleak.c b/mm/kmemleak.c
index c0014d3b91c1..fe6e3ae8e8c6 100644
--- a/mm/kmemleak.c
+++ b/mm/kmemleak.c
@@ -97,6 +97,7 @@
#include <linux/atomic.h>
#include <linux/kasan.h>
+#include <linux/kfence.h>
#include <linux/kmemleak.h>
#include <linux/memory_hotplug.h>
@@ -589,7 +590,7 @@ static struct kmemleak_object *create_object(unsigned long ptr, size_t size,
atomic_set(&object->use_count, 1);
object->flags = OBJECT_ALLOCATED;
object->pointer = ptr;
- object->size = size;
+ object->size = kfence_ksize((void *)ptr) ?: size;
object->excess_ref = 0;
object->min_count = min_count;
object->count = 0; /* white color initially */
diff --git a/mm/madvise.c b/mm/madvise.c
index df692d2e35d4..01fef79ac761 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -1198,12 +1198,22 @@ SYSCALL_DEFINE5(process_madvise, int, pidfd, const struct iovec __user *, vec,
goto release_task;
}
- mm = mm_access(task, PTRACE_MODE_ATTACH_FSCREDS);
+ /* Require PTRACE_MODE_READ to avoid leaking ASLR metadata. */
+ mm = mm_access(task, PTRACE_MODE_READ_FSCREDS);
if (IS_ERR_OR_NULL(mm)) {
ret = IS_ERR(mm) ? PTR_ERR(mm) : -ESRCH;
goto release_task;
}
+ /*
+ * Require CAP_SYS_NICE for influencing process performance. Note that
+ * only non-destructive hints are currently supported.
+ */
+ if (!capable(CAP_SYS_NICE)) {
+ ret = -EPERM;
+ goto release_mm;
+ }
+
total_len = iov_iter_count(&iter);
while (iov_iter_count(&iter)) {
@@ -1218,6 +1228,7 @@ SYSCALL_DEFINE5(process_madvise, int, pidfd, const struct iovec __user *, vec,
if (ret == 0)
ret = total_len - iov_iter_count(&iter);
+release_mm:
mmput(mm);
release_task:
put_task_struct(task);
diff --git a/mm/mapping_dirty_helpers.c b/mm/mapping_dirty_helpers.c
index b59054ef2e10..b890854ec761 100644
--- a/mm/mapping_dirty_helpers.c
+++ b/mm/mapping_dirty_helpers.c
@@ -165,10 +165,12 @@ static int wp_clean_pud_entry(pud_t *pud, unsigned long addr, unsigned long end,
return 0;
}
+#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
/* Huge pud */
walk->action = ACTION_CONTINUE;
if (pud_trans_huge(pudval) || pud_devmap(pudval))
WARN_ON(pud_write(pudval) || pud_dirty(pudval));
+#endif
return 0;
}
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 845eec01ef9d..e064ac0d850a 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -3287,24 +3287,21 @@ void obj_cgroup_uncharge(struct obj_cgroup *objcg, size_t size)
#endif /* CONFIG_MEMCG_KMEM */
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
/*
- * Because page_memcg(head) is not set on compound tails, set it now.
+ * Because page_memcg(head) is not set on tails, set it now.
*/
-void mem_cgroup_split_huge_fixup(struct page *head)
+void split_page_memcg(struct page *head, unsigned int nr)
{
struct mem_cgroup *memcg = page_memcg(head);
int i;
- if (mem_cgroup_disabled())
+ if (mem_cgroup_disabled() || !memcg)
return;
- for (i = 1; i < HPAGE_PMD_NR; i++) {
- css_get(&memcg->css);
- head[i].memcg_data = (unsigned long)memcg;
- }
+ for (i = 1; i < nr; i++)
+ head[i].memcg_data = head->memcg_data;
+ css_get_many(&memcg->css, nr - 1);
}
-#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
#ifdef CONFIG_MEMCG_SWAP
/**
diff --git a/mm/memory.c b/mm/memory.c
index c8e357627318..550405fc3b5e 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -166,7 +166,7 @@ static int __init init_zero_pfn(void)
zero_pfn = page_to_pfn(ZERO_PAGE(0));
return 0;
}
-core_initcall(init_zero_pfn);
+early_initcall(init_zero_pfn);
void mm_trace_rss_stat(struct mm_struct *mm, int member, long count)
{
@@ -809,12 +809,8 @@ copy_present_page(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma
pte_t *dst_pte, pte_t *src_pte, unsigned long addr, int *rss,
struct page **prealloc, pte_t pte, struct page *page)
{
- struct mm_struct *src_mm = src_vma->vm_mm;
struct page *new_page;
- if (!is_cow_mapping(src_vma->vm_flags))
- return 1;
-
/*
* What we want to do is to check whether this page may
* have been pinned by the parent process. If so,
@@ -828,9 +824,7 @@ copy_present_page(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma
* the page count. That might give false positives for
* for pinning, but it will work correctly.
*/
- if (likely(!atomic_read(&src_mm->has_pinned)))
- return 1;
- if (likely(!page_maybe_dma_pinned(page)))
+ if (likely(!page_needs_cow_for_dma(src_vma, page)))
return 1;
new_page = *prealloc;
@@ -3103,6 +3097,14 @@ static vm_fault_t do_wp_page(struct vm_fault *vmf)
return handle_userfault(vmf, VM_UFFD_WP);
}
+ /*
+ * Userfaultfd write-protect can defer flushes. Ensure the TLB
+ * is flushed in this case before copying.
+ */
+ if (unlikely(userfaultfd_wp(vmf->vma) &&
+ mm_tlb_flush_pending(vmf->vma->vm_mm)))
+ flush_tlb_page(vmf->vma, vmf->address);
+
vmf->page = vm_normal_page(vma, vmf->address, vmf->orig_pte);
if (!vmf->page) {
/*
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 5ba51a8bdaeb..0cdbbfbc5757 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -1072,7 +1072,7 @@ static int online_memory_block(struct memory_block *mem, void *arg)
*/
int __ref add_memory_resource(int nid, struct resource *res, mhp_t mhp_flags)
{
- struct mhp_params params = { .pgprot = PAGE_KERNEL };
+ struct mhp_params params = { .pgprot = pgprot_mhp(PAGE_KERNEL) };
u64 start, size;
bool new_node = false;
int ret;
diff --git a/mm/mmap.c b/mm/mmap.c
index 3f287599a7a3..1d96a21acb2f 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -93,6 +93,12 @@ static void unmap_region(struct mm_struct *mm,
* MAP_PRIVATE r: (no) no r: (yes) yes r: (no) yes r: (no) yes
* w: (no) no w: (no) no w: (copy) copy w: (no) no
* x: (no) no x: (no) yes x: (no) yes x: (yes) yes
+ *
+ * On arm64, PROT_EXEC has the following behaviour for both MAP_SHARED and
+ * MAP_PRIVATE (with Enhanced PAN supported):
+ * r: (no) no
+ * w: (no) no
+ * x: (yes) yes
*/
pgprot_t protection_map[16] __ro_after_init = {
__P000, __P001, __P010, __P011, __P100, __P101, __P110, __P111,
diff --git a/mm/mmu_gather.c b/mm/mmu_gather.c
index 0dc7149b0c61..1b9837419bf9 100644
--- a/mm/mmu_gather.c
+++ b/mm/mmu_gather.c
@@ -249,16 +249,6 @@ void tlb_flush_mmu(struct mmu_gather *tlb)
tlb_flush_mmu_free(tlb);
}
-/**
- * tlb_gather_mmu - initialize an mmu_gather structure for page-table tear-down
- * @tlb: the mmu_gather structure to initialize
- * @mm: the mm_struct of the target address space
- * @fullmm: @mm is without users and we're going to destroy the full address
- * space (exit/execve)
- *
- * Called to initialize an (on-stack) mmu_gather structure for page-table
- * tear-down from @mm.
- */
static void __tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm,
bool fullmm)
{
@@ -283,11 +273,30 @@ static void __tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm,
inc_tlb_flush_pending(tlb->mm);
}
+/**
+ * tlb_gather_mmu - initialize an mmu_gather structure for page-table tear-down
+ * @tlb: the mmu_gather structure to initialize
+ * @mm: the mm_struct of the target address space
+ *
+ * Called to initialize an (on-stack) mmu_gather structure for page-table
+ * tear-down from @mm.
+ */
void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm)
{
__tlb_gather_mmu(tlb, mm, false);
}
+/**
+ * tlb_gather_mmu_fullmm - initialize an mmu_gather structure for page-table tear-down
+ * @tlb: the mmu_gather structure to initialize
+ * @mm: the mm_struct of the target address space
+ *
+ * In this case, @mm is without users and we're going to destroy the
+ * full address space (exit/execve).
+ *
+ * Called to initialize an (on-stack) mmu_gather structure for page-table
+ * tear-down from @mm.
+ */
void tlb_gather_mmu_fullmm(struct mmu_gather *tlb, struct mm_struct *mm)
{
__tlb_gather_mmu(tlb, mm, true);
diff --git a/mm/mmu_notifier.c b/mm/mmu_notifier.c
index 61ee40ed804e..459d195d2ff6 100644
--- a/mm/mmu_notifier.c
+++ b/mm/mmu_notifier.c
@@ -501,10 +501,33 @@ static int mn_hlist_invalidate_range_start(
"");
WARN_ON(mmu_notifier_range_blockable(range) ||
_ret != -EAGAIN);
+ /*
+ * We call all the notifiers on any EAGAIN,
+ * there is no way for a notifier to know if
+ * its start method failed, thus a start that
+ * does EAGAIN can't also do end.
+ */
+ WARN_ON(ops->invalidate_range_end);
ret = _ret;
}
}
}
+
+ if (ret) {
+ /*
+ * Must be non-blocking to get here. If there are multiple
+ * notifiers and one or more failed start, any that succeeded
+ * start are expecting their end to be called. Do so now.
+ */
+ hlist_for_each_entry_rcu(subscription, &subscriptions->list,
+ hlist, srcu_read_lock_held(&srcu)) {
+ if (!subscription->ops->invalidate_range_end)
+ continue;
+
+ subscription->ops->invalidate_range_end(subscription,
+ range);
+ }
+ }
srcu_read_unlock(&srcu, id);
return ret;
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index 9efaf430cfd3..fa1cf18bac97 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -170,7 +170,7 @@ static bool oom_unkillable_task(struct task_struct *p)
return false;
}
-/**
+/*
* Check whether unreclaimable slab amount is greater than
* all user memory(LRU pages).
* dump_unreclaimable_slab() could help in the case that
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index eb34d204d4ee..9e35b636a393 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -2833,6 +2833,22 @@ void wait_on_page_writeback(struct page *page)
}
EXPORT_SYMBOL_GPL(wait_on_page_writeback);
+/*
+ * Wait for a page to complete writeback. Returns -EINTR if we get a
+ * fatal signal while waiting.
+ */
+int wait_on_page_writeback_killable(struct page *page)
+{
+ while (PageWriteback(page)) {
+ trace_wait_on_page_writeback(page, page_mapping(page));
+ if (wait_on_page_bit_killable(page, PG_writeback))
+ return -EINTR;
+ }
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(wait_on_page_writeback_killable);
+
/**
* wait_for_stable_page() - wait for writeback to finish, if necessary.
* @page: The page to wait on.
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 3e4b29ee2b1e..e2f19bf948db 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -167,10 +167,10 @@ unsigned long totalcma_pages __read_mostly;
int percpu_pagelist_fraction;
gfp_t gfp_allowed_mask __read_mostly = GFP_BOOT_MASK;
-DEFINE_STATIC_KEY_FALSE(init_on_alloc);
+DEFINE_STATIC_KEY_MAYBE(CONFIG_INIT_ON_ALLOC_DEFAULT_ON, init_on_alloc);
EXPORT_SYMBOL(init_on_alloc);
-DEFINE_STATIC_KEY_FALSE(init_on_free);
+DEFINE_STATIC_KEY_MAYBE(CONFIG_INIT_ON_FREE_DEFAULT_ON, init_on_free);
EXPORT_SYMBOL(init_on_free);
static bool _init_on_alloc_enabled_early __read_mostly
@@ -1282,6 +1282,12 @@ static __always_inline bool free_pages_prepare(struct page *page,
kernel_poison_pages(page, 1 << order);
/*
+ * With hardware tag-based KASAN, memory tags must be set before the
+ * page becomes unavailable via debug_pagealloc or arch_free_page.
+ */
+ kasan_free_nondeferred_pages(page, order);
+
+ /*
* arch_free_page() can make the page's contents inaccessible. s390
* does this. So nothing which can access the page's contents should
* happen after this.
@@ -1290,8 +1296,6 @@ static __always_inline bool free_pages_prepare(struct page *page,
debug_pagealloc_unmap_pages(page, 1 << order);
- kasan_free_nondeferred_pages(page, order);
-
return true;
}
@@ -3310,6 +3314,7 @@ void split_page(struct page *page, unsigned int order)
for (i = 1; i < (1 << order); i++)
set_page_refcounted(page + i);
split_page_owner(page, 1 << order);
+ split_page_memcg(page, 1 << order);
}
EXPORT_SYMBOL_GPL(split_page);
@@ -6259,12 +6264,65 @@ static void __meminit zone_init_free_lists(struct zone *zone)
}
}
+#if !defined(CONFIG_FLAT_NODE_MEM_MAP)
+/*
+ * Only struct pages that correspond to ranges defined by memblock.memory
+ * are zeroed and initialized by going through __init_single_page() during
+ * memmap_init_zone().
+ *
+ * But, there could be struct pages that correspond to holes in
+ * memblock.memory. This can happen because of the following reasons:
+ * - physical memory bank size is not necessarily the exact multiple of the
+ * arbitrary section size
+ * - early reserved memory may not be listed in memblock.memory
+ * - memory layouts defined with memmap= kernel parameter may not align
+ * nicely with memmap sections
+ *
+ * Explicitly initialize those struct pages so that:
+ * - PG_Reserved is set
+ * - zone and node links point to zone and node that span the page if the
+ * hole is in the middle of a zone
+ * - zone and node links point to adjacent zone/node if the hole falls on
+ * the zone boundary; the pages in such holes will be prepended to the
+ * zone/node above the hole except for the trailing pages in the last
+ * section that will be appended to the zone/node below.
+ */
+static u64 __meminit init_unavailable_range(unsigned long spfn,
+ unsigned long epfn,
+ int zone, int node)
+{
+ unsigned long pfn;
+ u64 pgcnt = 0;
+
+ for (pfn = spfn; pfn < epfn; pfn++) {
+ if (!pfn_valid(ALIGN_DOWN(pfn, pageblock_nr_pages))) {
+ pfn = ALIGN_DOWN(pfn, pageblock_nr_pages)
+ + pageblock_nr_pages - 1;
+ continue;
+ }
+ __init_single_page(pfn_to_page(pfn), pfn, zone, node);
+ __SetPageReserved(pfn_to_page(pfn));
+ pgcnt++;
+ }
+
+ return pgcnt;
+}
+#else
+static inline u64 init_unavailable_range(unsigned long spfn, unsigned long epfn,
+ int zone, int node)
+{
+ return 0;
+}
+#endif
+
void __meminit __weak memmap_init_zone(struct zone *zone)
{
unsigned long zone_start_pfn = zone->zone_start_pfn;
unsigned long zone_end_pfn = zone_start_pfn + zone->spanned_pages;
int i, nid = zone_to_nid(zone), zone_id = zone_idx(zone);
+ static unsigned long hole_pfn;
unsigned long start_pfn, end_pfn;
+ u64 pgcnt = 0;
for_each_mem_pfn_range(i, nid, &start_pfn, &end_pfn, NULL) {
start_pfn = clamp(start_pfn, zone_start_pfn, zone_end_pfn);
@@ -6274,7 +6332,29 @@ void __meminit __weak memmap_init_zone(struct zone *zone)
memmap_init_range(end_pfn - start_pfn, nid,
zone_id, start_pfn, zone_end_pfn,
MEMINIT_EARLY, NULL, MIGRATE_MOVABLE);
+
+ if (hole_pfn < start_pfn)
+ pgcnt += init_unavailable_range(hole_pfn, start_pfn,
+ zone_id, nid);
+ hole_pfn = end_pfn;
}
+
+#ifdef CONFIG_SPARSEMEM
+ /*
+ * Initialize the hole in the range [zone_end_pfn, section_end].
+ * If zone boundary falls in the middle of a section, this hole
+ * will be re-initialized during the call to this function for the
+ * higher zone.
+ */
+ end_pfn = round_up(zone_end_pfn, PAGES_PER_SECTION);
+ if (hole_pfn < end_pfn)
+ pgcnt += init_unavailable_range(hole_pfn, end_pfn,
+ zone_id, nid);
+#endif
+
+ if (pgcnt)
+ pr_info(" %s zone: %llu pages in unavailable ranges\n",
+ zone->name, pgcnt);
}
static int zone_batchsize(struct zone *zone)
@@ -7071,88 +7151,6 @@ void __init free_area_init_memoryless_node(int nid)
free_area_init_node(nid);
}
-#if !defined(CONFIG_FLAT_NODE_MEM_MAP)
-/*
- * Initialize all valid struct pages in the range [spfn, epfn) and mark them
- * PageReserved(). Return the number of struct pages that were initialized.
- */
-static u64 __init init_unavailable_range(unsigned long spfn, unsigned long epfn)
-{
- unsigned long pfn;
- u64 pgcnt = 0;
-
- for (pfn = spfn; pfn < epfn; pfn++) {
- if (!pfn_valid(ALIGN_DOWN(pfn, pageblock_nr_pages))) {
- pfn = ALIGN_DOWN(pfn, pageblock_nr_pages)
- + pageblock_nr_pages - 1;
- continue;
- }
- /*
- * Use a fake node/zone (0) for now. Some of these pages
- * (in memblock.reserved but not in memblock.memory) will
- * get re-initialized via reserve_bootmem_region() later.
- */
- __init_single_page(pfn_to_page(pfn), pfn, 0, 0);
- __SetPageReserved(pfn_to_page(pfn));
- pgcnt++;
- }
-
- return pgcnt;
-}
-
-/*
- * Only struct pages that are backed by physical memory are zeroed and
- * initialized by going through __init_single_page(). But, there are some
- * struct pages which are reserved in memblock allocator and their fields
- * may be accessed (for example page_to_pfn() on some configuration accesses
- * flags). We must explicitly initialize those struct pages.
- *
- * This function also addresses a similar issue where struct pages are left
- * uninitialized because the physical address range is not covered by
- * memblock.memory or memblock.reserved. That could happen when memblock
- * layout is manually configured via memmap=, or when the highest physical
- * address (max_pfn) does not end on a section boundary.
- */
-static void __init init_unavailable_mem(void)
-{
- phys_addr_t start, end;
- u64 i, pgcnt;
- phys_addr_t next = 0;
-
- /*
- * Loop through unavailable ranges not covered by memblock.memory.
- */
- pgcnt = 0;
- for_each_mem_range(i, &start, &end) {
- if (next < start)
- pgcnt += init_unavailable_range(PFN_DOWN(next),
- PFN_UP(start));
- next = end;
- }
-
- /*
- * Early sections always have a fully populated memmap for the whole
- * section - see pfn_valid(). If the last section has holes at the
- * end and that section is marked "online", the memmap will be
- * considered initialized. Make sure that memmap has a well defined
- * state.
- */
- pgcnt += init_unavailable_range(PFN_DOWN(next),
- round_up(max_pfn, PAGES_PER_SECTION));
-
- /*
- * Struct pages that do not have backing memory. This could be because
- * firmware is using some of this memory, or for some other reasons.
- */
- if (pgcnt)
- pr_info("Zeroed struct page in unavailable ranges: %lld pages", pgcnt);
-}
-#else
-static inline void __init init_unavailable_mem(void)
-{
-}
-#endif /* !CONFIG_FLAT_NODE_MEM_MAP */
-
#if MAX_NUMNODES > 1
/*
* Figure out the number of possible node ids.
@@ -7576,7 +7574,6 @@ void __init free_area_init(unsigned long *max_zone_pfn)
/* Initialise every node */
mminit_verify_pageflags_layout();
setup_nr_node_ids();
- init_unavailable_mem();
for_each_online_node(nid) {
pg_data_t *pgdat = NODE_DATA(nid);
free_area_init_node(nid);
diff --git a/mm/page_poison.c b/mm/page_poison.c
index 65cdf844c8ad..655dc5895604 100644
--- a/mm/page_poison.c
+++ b/mm/page_poison.c
@@ -77,12 +77,14 @@ static void unpoison_page(struct page *page)
void *addr;
addr = kmap_atomic(page);
+ kasan_disable_current();
/*
* Page poisoning when enabled poisons each and every page
* that is freed to buddy. Thus no extra check is done to
* see if a page was poisoned.
*/
- check_poison_mem(addr, PAGE_SIZE);
+ check_poison_mem(kasan_reset_tag(addr), PAGE_SIZE);
+ kasan_enable_current();
kunmap_atomic(addr);
}
diff --git a/mm/percpu-internal.h b/mm/percpu-internal.h
index 18b768ac7dca..095d7eaa0db4 100644
--- a/mm/percpu-internal.h
+++ b/mm/percpu-internal.h
@@ -87,7 +87,7 @@ extern spinlock_t pcpu_lock;
extern struct list_head *pcpu_chunk_lists;
extern int pcpu_nr_slots;
-extern int pcpu_nr_empty_pop_pages;
+extern int pcpu_nr_empty_pop_pages[];
extern struct pcpu_chunk *pcpu_first_chunk;
extern struct pcpu_chunk *pcpu_reserved_chunk;
diff --git a/mm/percpu-stats.c b/mm/percpu-stats.c
index c8400a2adbc2..f6026dbcdf6b 100644
--- a/mm/percpu-stats.c
+++ b/mm/percpu-stats.c
@@ -145,6 +145,7 @@ static int percpu_stats_show(struct seq_file *m, void *v)
int slot, max_nr_alloc;
int *buffer;
enum pcpu_chunk_type type;
+ int nr_empty_pop_pages;
alloc_buffer:
spin_lock_irq(&pcpu_lock);
@@ -165,7 +166,11 @@ alloc_buffer:
goto alloc_buffer;
}
-#define PL(X) \
+ nr_empty_pop_pages = 0;
+ for (type = 0; type < PCPU_NR_CHUNK_TYPES; type++)
+ nr_empty_pop_pages += pcpu_nr_empty_pop_pages[type];
+
+#define PL(X) \
seq_printf(m, " %-20s: %12lld\n", #X, (long long int)pcpu_stats_ai.X)
seq_printf(m,
@@ -196,7 +201,7 @@ alloc_buffer:
PU(nr_max_chunks);
PU(min_alloc_size);
PU(max_alloc_size);
- P("empty_pop_pages", pcpu_nr_empty_pop_pages);
+ P("empty_pop_pages", nr_empty_pop_pages);
seq_putc(m, '\n');
#undef PU
diff --git a/mm/percpu.c b/mm/percpu.c
index 6596a0a4286e..23308113a5ff 100644
--- a/mm/percpu.c
+++ b/mm/percpu.c
@@ -173,10 +173,10 @@ struct list_head *pcpu_chunk_lists __ro_after_init; /* chunk list slots */
static LIST_HEAD(pcpu_map_extend_chunks);
/*
- * The number of empty populated pages, protected by pcpu_lock. The
- * reserved chunk doesn't contribute to the count.
+ * The number of empty populated pages by chunk type, protected by pcpu_lock.
+ * The reserved chunk doesn't contribute to the count.
*/
-int pcpu_nr_empty_pop_pages;
+int pcpu_nr_empty_pop_pages[PCPU_NR_CHUNK_TYPES];
/*
* The number of populated pages in use by the allocator, protected by
@@ -556,7 +556,7 @@ static inline void pcpu_update_empty_pages(struct pcpu_chunk *chunk, int nr)
{
chunk->nr_empty_pop_pages += nr;
if (chunk != pcpu_reserved_chunk)
- pcpu_nr_empty_pop_pages += nr;
+ pcpu_nr_empty_pop_pages[pcpu_chunk_type(chunk)] += nr;
}
/*
@@ -1832,7 +1832,7 @@ area_found:
mutex_unlock(&pcpu_alloc_mutex);
}
- if (pcpu_nr_empty_pop_pages < PCPU_EMPTY_POP_PAGES_LOW)
+ if (pcpu_nr_empty_pop_pages[type] < PCPU_EMPTY_POP_PAGES_LOW)
pcpu_schedule_balance_work();
/* clear the areas and return address relative to base address */
@@ -2000,7 +2000,7 @@ retry_pop:
pcpu_atomic_alloc_failed = false;
} else {
nr_to_pop = clamp(PCPU_EMPTY_POP_PAGES_HIGH -
- pcpu_nr_empty_pop_pages,
+ pcpu_nr_empty_pop_pages[type],
0, PCPU_EMPTY_POP_PAGES_HIGH);
}
@@ -2580,7 +2580,7 @@ void __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai,
/* link the first chunk in */
pcpu_first_chunk = chunk;
- pcpu_nr_empty_pop_pages = pcpu_first_chunk->nr_empty_pop_pages;
+ pcpu_nr_empty_pop_pages[PCPU_CHUNK_ROOT] = pcpu_first_chunk->nr_empty_pop_pages;
pcpu_chunk_relocate(pcpu_first_chunk, -1);
/* include all regions of the first chunk */
diff --git a/mm/ptdump.c b/mm/ptdump.c
index 4354c1422d57..da751448d0e4 100644
--- a/mm/ptdump.c
+++ b/mm/ptdump.c
@@ -111,7 +111,7 @@ static int ptdump_pte_entry(pte_t *pte, unsigned long addr,
unsigned long next, struct mm_walk *walk)
{
struct ptdump_state *st = walk->private;
- pte_t val = READ_ONCE(*pte);
+ pte_t val = ptep_get(pte);
if (st->effective_prot)
st->effective_prot(st, 4, pte_val(val));
diff --git a/mm/readahead.c b/mm/readahead.c
index c5b0457415be..d589f147f4c2 100644
--- a/mm/readahead.c
+++ b/mm/readahead.c
@@ -198,8 +198,6 @@ void page_cache_ra_unbounded(struct readahead_control *ractl,
for (i = 0; i < nr_to_read; i++) {
struct page *page = xa_load(&mapping->i_pages, index + i);
- BUG_ON(index + i != ractl->_index + ractl->_nr_pages);
-
if (page && !xa_is_value(page)) {
/*
* Page already present? Kick off the current batch
@@ -210,6 +208,7 @@ void page_cache_ra_unbounded(struct readahead_control *ractl,
* not worth getting one just for that.
*/
read_pages(ractl, &page_pool, true);
+ i = ractl->_index + ractl->_nr_pages - index - 1;
continue;
}
@@ -223,6 +222,7 @@ void page_cache_ra_unbounded(struct readahead_control *ractl,
gfp_mask) < 0) {
put_page(page);
read_pages(ractl, &page_pool, true);
+ i = ractl->_index + ractl->_nr_pages - index - 1;
continue;
}
if (i == nr_to_read - lookahead_size)
@@ -272,9 +272,10 @@ void do_page_cache_ra(struct readahead_control *ractl,
* memory at once.
*/
void force_page_cache_ra(struct readahead_control *ractl,
- struct file_ra_state *ra, unsigned long nr_to_read)
+ unsigned long nr_to_read)
{
struct address_space *mapping = ractl->mapping;
+ struct file_ra_state *ra = ractl->ra;
struct backing_dev_info *bdi = inode_to_bdi(mapping->host);
unsigned long max_pages, index;
@@ -433,10 +434,10 @@ static int try_context_readahead(struct address_space *mapping,
* A minimal readahead algorithm for trivial sequential/random reads.
*/
static void ondemand_readahead(struct readahead_control *ractl,
- struct file_ra_state *ra, bool hit_readahead_marker,
- unsigned long req_size)
+ bool hit_readahead_marker, unsigned long req_size)
{
struct backing_dev_info *bdi = inode_to_bdi(ractl->mapping->host);
+ struct file_ra_state *ra = ractl->ra;
unsigned long max_pages = ra->ra_pages;
unsigned long add_pages;
unsigned long index = readahead_index(ractl);
@@ -550,7 +551,7 @@ readit:
}
void page_cache_sync_ra(struct readahead_control *ractl,
- struct file_ra_state *ra, unsigned long req_count)
+ unsigned long req_count)
{
bool do_forced_ra = ractl->file && (ractl->file->f_mode & FMODE_RANDOM);
@@ -560,7 +561,7 @@ void page_cache_sync_ra(struct readahead_control *ractl,
* read-ahead will do the right thing and limit the read to just the
* requested range, which we'll set to 1 page for this case.
*/
- if (!ra->ra_pages || blk_cgroup_congested()) {
+ if (!ractl->ra->ra_pages || blk_cgroup_congested()) {
if (!ractl->file)
return;
req_count = 1;
@@ -569,21 +570,20 @@ void page_cache_sync_ra(struct readahead_control *ractl,
/* be dumb */
if (do_forced_ra) {
- force_page_cache_ra(ractl, ra, req_count);
+ force_page_cache_ra(ractl, req_count);
return;
}
/* do read-ahead */
- ondemand_readahead(ractl, ra, false, req_count);
+ ondemand_readahead(ractl, false, req_count);
}
EXPORT_SYMBOL_GPL(page_cache_sync_ra);
void page_cache_async_ra(struct readahead_control *ractl,
- struct file_ra_state *ra, struct page *page,
- unsigned long req_count)
+ struct page *page, unsigned long req_count)
{
/* no read-ahead */
- if (!ra->ra_pages)
+ if (!ractl->ra->ra_pages)
return;
/*
@@ -604,7 +604,7 @@ void page_cache_async_ra(struct readahead_control *ractl,
return;
/* do read-ahead */
- ondemand_readahead(ractl, ra, true, req_count);
+ ondemand_readahead(ractl, true, req_count);
}
EXPORT_SYMBOL_GPL(page_cache_async_ra);
@@ -638,3 +638,78 @@ SYSCALL_DEFINE3(readahead, int, fd, loff_t, offset, size_t, count)
{
return ksys_readahead(fd, offset, count);
}
+
+/**
+ * readahead_expand - Expand a readahead request
+ * @ractl: The request to be expanded
+ * @new_start: The revised start
+ * @new_len: The revised size of the request
+ *
+ * Attempt to expand a readahead request outwards from the current size to the
+ * specified size by inserting locked pages before and after the current window
+ * to increase the size to the new window. This may involve the insertion of
+ * THPs, in which case the window may get expanded even beyond what was
+ * requested.
+ *
+ * The algorithm will stop if it encounters a conflicting page already in the
+ * pagecache and leave a smaller expansion than requested.
+ *
+ * The caller must check for this by examining the revised @ractl object for a
+ * different expansion than was requested.
+ */
+void readahead_expand(struct readahead_control *ractl,
+ loff_t new_start, size_t new_len)
+{
+ struct address_space *mapping = ractl->mapping;
+ struct file_ra_state *ra = ractl->ra;
+ pgoff_t new_index, new_nr_pages;
+ gfp_t gfp_mask = readahead_gfp_mask(mapping);
+
+ new_index = new_start / PAGE_SIZE;
+
+ /* Expand the leading edge downwards */
+ while (ractl->_index > new_index) {
+ unsigned long index = ractl->_index - 1;
+ struct page *page = xa_load(&mapping->i_pages, index);
+
+ if (page && !xa_is_value(page))
+ return; /* Page apparently present */
+
+ page = __page_cache_alloc(gfp_mask);
+ if (!page)
+ return;
+ if (add_to_page_cache_lru(page, mapping, index, gfp_mask) < 0) {
+ put_page(page);
+ return;
+ }
+
+ ractl->_nr_pages++;
+ ractl->_index = page->index;
+ }
+
+ new_len += new_start - readahead_pos(ractl);
+ new_nr_pages = DIV_ROUND_UP(new_len, PAGE_SIZE);
+
+ /* Expand the trailing edge upwards */
+ while (ractl->_nr_pages < new_nr_pages) {
+ unsigned long index = ractl->_index + ractl->_nr_pages;
+ struct page *page = xa_load(&mapping->i_pages, index);
+
+ if (page && !xa_is_value(page))
+ return; /* Page apparently present */
+
+ page = __page_cache_alloc(gfp_mask);
+ if (!page)
+ return;
+ if (add_to_page_cache_lru(page, mapping, index, gfp_mask) < 0) {
+ put_page(page);
+ return;
+ }
+ ractl->_nr_pages++;
+ if (ra) {
+ ra->size++;
+ ra->async_size++;
+ }
+ }
+}
+EXPORT_SYMBOL(readahead_expand);
diff --git a/mm/shuffle.c b/mm/shuffle.c
index 9c2e145a747a..c13c33b247e8 100644
--- a/mm/shuffle.c
+++ b/mm/shuffle.c
@@ -147,8 +147,8 @@ void __meminit __shuffle_zone(struct zone *z)
spin_unlock_irqrestore(&z->lock, flags);
}
-/**
- * shuffle_free_memory - reduce the predictability of the page allocator
+/*
+ * __shuffle_free_memory - reduce the predictability of the page allocator
* @pgdat: node page data
*/
void __meminit __shuffle_free_memory(pg_data_t *pgdat)
diff --git a/mm/slab.c b/mm/slab.c
index 51fd424e0d6d..ae651bf540b7 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -2992,7 +2992,7 @@ static void *cache_alloc_debugcheck_after(struct kmem_cache *cachep,
gfp_t flags, void *objp, unsigned long caller)
{
WARN_ON_ONCE(cachep->ctor && (flags & __GFP_ZERO));
- if (!objp)
+ if (!objp || is_kfence_address(objp))
return objp;
if (cachep->flags & SLAB_POISON) {
check_poison_obj(cachep, objp);
diff --git a/mm/slab.h b/mm/slab.h
index 076582f58f68..774c7221efdc 100644
--- a/mm/slab.h
+++ b/mm/slab.h
@@ -601,7 +601,8 @@ static inline void cache_random_seq_destroy(struct kmem_cache *cachep) { }
static inline bool slab_want_init_on_alloc(gfp_t flags, struct kmem_cache *c)
{
- if (static_branch_unlikely(&init_on_alloc)) {
+ if (static_branch_maybe(CONFIG_INIT_ON_ALLOC_DEFAULT_ON,
+ &init_on_alloc)) {
if (c->ctor)
return false;
if (c->flags & (SLAB_TYPESAFE_BY_RCU | SLAB_POISON))
@@ -613,7 +614,8 @@ static inline bool slab_want_init_on_alloc(gfp_t flags, struct kmem_cache *c)
static inline bool slab_want_init_on_free(struct kmem_cache *c)
{
- if (static_branch_unlikely(&init_on_free))
+ if (static_branch_maybe(CONFIG_INIT_ON_FREE_DEFAULT_ON,
+ &init_on_free))
return !(c->ctor ||
(c->flags & (SLAB_TYPESAFE_BY_RCU | SLAB_POISON)));
return false;
diff --git a/mm/slub.c b/mm/slub.c
index e26c274b4657..7ed388077633 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -624,7 +624,7 @@ static void print_track(const char *s, struct track *t, unsigned long pr_time)
if (!t->addr)
return;
- pr_err("INFO: %s in %pS age=%lu cpu=%u pid=%d\n",
+ pr_err("%s in %pS age=%lu cpu=%u pid=%d\n",
s, (void *)t->addr, pr_time - t->when, t->cpu, t->pid);
#ifdef CONFIG_STACKTRACE
{
@@ -650,8 +650,9 @@ void print_tracking(struct kmem_cache *s, void *object)
static void print_page_info(struct page *page)
{
- pr_err("INFO: Slab 0x%p objects=%u used=%u fp=0x%p flags=0x%04lx\n",
- page, page->objects, page->inuse, page->freelist, page->flags);
+ pr_err("Slab 0x%p objects=%u used=%u fp=0x%p flags=%#lx(%pGp)\n",
+ page, page->objects, page->inuse, page->freelist,
+ page->flags, &page->flags);
}
@@ -706,7 +707,7 @@ static void print_trailer(struct kmem_cache *s, struct page *page, u8 *p)
print_page_info(page);
- pr_err("INFO: Object 0x%p @offset=%tu fp=0x%p\n\n",
+ pr_err("Object 0x%p @offset=%tu fp=0x%p\n\n",
p, p - addr, get_freepointer(s, p));
if (s->flags & SLAB_RED_ZONE)
@@ -799,7 +800,7 @@ static int check_bytes_and_report(struct kmem_cache *s, struct page *page,
end--;
slab_bug(s, "%s overwritten", what);
- pr_err("INFO: 0x%p-0x%p @offset=%tu. First byte 0x%x instead of 0x%x\n",
+ pr_err("0x%p-0x%p @offset=%tu. First byte 0x%x instead of 0x%x\n",
fault, end - 1, fault - addr,
fault[0], value);
print_trailer(s, page, object);
@@ -1993,7 +1994,7 @@ static void *get_partial_node(struct kmem_cache *s, struct kmem_cache_node *n,
t = acquire_slab(s, n, page, object == NULL, &objects);
if (!t)
- continue; /* cmpxchg raced */
+ break;
available += objects;
if (!object) {
@@ -3898,7 +3899,7 @@ static void list_slab_objects(struct kmem_cache *s, struct page *page,
for_each_object(p, s, addr, page->objects) {
if (!test_bit(__obj_to_index(s, addr, p), map)) {
- pr_err("INFO: Object 0x%p @offset=%tu\n", p, p - addr);
+ pr_err("Object 0x%p @offset=%tu\n", p, p - addr);
print_tracking(s, p);
}
}
diff --git a/mm/z3fold.c b/mm/z3fold.c
index b5dafa7e44e4..9d889ad2bb86 100644
--- a/mm/z3fold.c
+++ b/mm/z3fold.c
@@ -1346,8 +1346,22 @@ static int z3fold_reclaim_page(struct z3fold_pool *pool, unsigned int retries)
page = list_entry(pos, struct page, lru);
zhdr = page_address(page);
- if (test_bit(PAGE_HEADLESS, &page->private))
+ if (test_bit(PAGE_HEADLESS, &page->private)) {
+ /*
+ * For non-headless pages, we wait to do this
+ * until we have the page lock to avoid racing
+ * with __z3fold_alloc(). Headless pages don't
+ * have a lock (and __z3fold_alloc() will never
+ * see them), but we still need to test and set
+ * PAGE_CLAIMED to avoid racing with
+ * z3fold_free(), so just do it now before
+ * leaving the loop.
+ */
+ if (test_and_set_bit(PAGE_CLAIMED, &page->private))
+ continue;
+
break;
+ }
if (kref_get_unless_zero(&zhdr->refcount) == 0) {
zhdr = NULL;