Update Linux to v5.4.148
Sourced from [1]
[1] https://cdn.kernel.org/pub/linux/kernel/v5.x/linux-5.4.148.tar.gz
Change-Id: Ib3d26c5ba9b022e2e03533005c4fed4d7c30b61b
Signed-off-by: Olivier Deprez <olivier.deprez@arm.com>
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 13cc937..e50799d 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -61,6 +61,7 @@
static atomic_t huge_zero_refcount;
struct page *huge_zero_page __read_mostly;
+unsigned long huge_zero_pfn __read_mostly = ~0UL;
bool transparent_hugepage_enabled(struct vm_area_struct *vma)
{
@@ -97,6 +98,7 @@
__free_pages(zero_page, compound_order(zero_page));
goto retry;
}
+ WRITE_ONCE(huge_zero_pfn, page_to_pfn(zero_page));
/* We take additional reference here. It will be put back by shrinker */
atomic_set(&huge_zero_refcount, 2);
@@ -146,6 +148,7 @@
if (atomic_cmpxchg(&huge_zero_refcount, 1, 0) == 1) {
struct page *zero_page = xchg(&huge_zero_page, NULL);
BUG_ON(zero_page == NULL);
+ WRITE_ONCE(huge_zero_pfn, ~0UL);
__free_pages(zero_page, compound_order(zero_page));
return HPAGE_PMD_NR;
}
@@ -177,16 +180,13 @@
{
ssize_t ret = count;
- if (!memcmp("always", buf,
- min(sizeof("always")-1, count))) {
+ if (sysfs_streq(buf, "always")) {
clear_bit(TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG, &transparent_hugepage_flags);
set_bit(TRANSPARENT_HUGEPAGE_FLAG, &transparent_hugepage_flags);
- } else if (!memcmp("madvise", buf,
- min(sizeof("madvise")-1, count))) {
+ } else if (sysfs_streq(buf, "madvise")) {
clear_bit(TRANSPARENT_HUGEPAGE_FLAG, &transparent_hugepage_flags);
set_bit(TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG, &transparent_hugepage_flags);
- } else if (!memcmp("never", buf,
- min(sizeof("never")-1, count))) {
+ } else if (sysfs_streq(buf, "never")) {
clear_bit(TRANSPARENT_HUGEPAGE_FLAG, &transparent_hugepage_flags);
clear_bit(TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG, &transparent_hugepage_flags);
} else
@@ -250,32 +250,27 @@
struct kobj_attribute *attr,
const char *buf, size_t count)
{
- if (!memcmp("always", buf,
- min(sizeof("always")-1, count))) {
+ if (sysfs_streq(buf, "always")) {
clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags);
clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags);
clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags);
set_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags);
- } else if (!memcmp("defer+madvise", buf,
- min(sizeof("defer+madvise")-1, count))) {
+ } else if (sysfs_streq(buf, "defer+madvise")) {
clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags);
clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags);
clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags);
set_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags);
- } else if (!memcmp("defer", buf,
- min(sizeof("defer")-1, count))) {
+ } else if (sysfs_streq(buf, "defer")) {
clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags);
clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags);
clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags);
set_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags);
- } else if (!memcmp("madvise", buf,
- min(sizeof("madvise")-1, count))) {
+ } else if (sysfs_streq(buf, "madvise")) {
clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags);
clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags);
clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags);
set_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags);
- } else if (!memcmp("never", buf,
- min(sizeof("never")-1, count))) {
+ } else if (sysfs_streq(buf, "never")) {
clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags);
clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags);
clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags);
@@ -527,13 +522,13 @@
set_compound_page_dtor(page, TRANSHUGE_PAGE_DTOR);
}
-static unsigned long __thp_get_unmapped_area(struct file *filp, unsigned long len,
+static unsigned long __thp_get_unmapped_area(struct file *filp,
+ unsigned long addr, unsigned long len,
loff_t off, unsigned long flags, unsigned long size)
{
- unsigned long addr;
loff_t off_end = off + len;
loff_t off_align = round_up(off, size);
- unsigned long len_pad;
+ unsigned long len_pad, ret;
if (off_end <= off_align || (off_end - off_align) < size)
return 0;
@@ -542,30 +537,40 @@
if (len_pad < len || (off + len_pad) < off)
return 0;
- addr = current->mm->get_unmapped_area(filp, 0, len_pad,
+ ret = current->mm->get_unmapped_area(filp, addr, len_pad,
off >> PAGE_SHIFT, flags);
- if (IS_ERR_VALUE(addr))
+
+ /*
+ * The failure might be due to length padding. The caller will retry
+ * without the padding.
+ */
+ if (IS_ERR_VALUE(ret))
return 0;
- addr += (off - addr) & (size - 1);
- return addr;
+ /*
+ * Do not try to align to THP boundary if allocation at the address
+ * hint succeeds.
+ */
+ if (ret == addr)
+ return addr;
+
+ ret += (off - ret) & (size - 1);
+ return ret;
}
unsigned long thp_get_unmapped_area(struct file *filp, unsigned long addr,
unsigned long len, unsigned long pgoff, unsigned long flags)
{
+ unsigned long ret;
loff_t off = (loff_t)pgoff << PAGE_SHIFT;
- if (addr)
- goto out;
if (!IS_DAX(filp->f_mapping->host) || !IS_ENABLED(CONFIG_FS_DAX_PMD))
goto out;
- addr = __thp_get_unmapped_area(filp, len, off, flags, PMD_SIZE);
- if (addr)
- return addr;
-
- out:
+ ret = __thp_get_unmapped_area(filp, addr, len, off, flags, PMD_SIZE);
+ if (ret)
+ return ret;
+out:
return current->mm->get_unmapped_area(filp, addr, len, pgoff, flags);
}
EXPORT_SYMBOL_GPL(thp_get_unmapped_area);
@@ -720,7 +725,6 @@
transparent_hugepage_use_zero_page()) {
pgtable_t pgtable;
struct page *zero_page;
- bool set;
vm_fault_t ret;
pgtable = pte_alloc_one(vma->vm_mm);
if (unlikely(!pgtable))
@@ -733,25 +737,25 @@
}
vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd);
ret = 0;
- set = false;
if (pmd_none(*vmf->pmd)) {
ret = check_stable_address_space(vma->vm_mm);
if (ret) {
spin_unlock(vmf->ptl);
+ pte_free(vma->vm_mm, pgtable);
} else if (userfaultfd_missing(vma)) {
spin_unlock(vmf->ptl);
+ pte_free(vma->vm_mm, pgtable);
ret = handle_userfault(vmf, VM_UFFD_MISSING);
VM_BUG_ON(ret & VM_FAULT_FALLBACK);
} else {
set_huge_zero_page(pgtable, vma->vm_mm, vma,
haddr, vmf->pmd, zero_page);
spin_unlock(vmf->ptl);
- set = true;
}
- } else
+ } else {
spin_unlock(vmf->ptl);
- if (!set)
pte_free(vma->vm_mm, pgtable);
+ }
return ret;
}
gfp = alloc_hugepage_direct_gfpmask(vma);
@@ -1452,13 +1456,12 @@
}
/*
- * FOLL_FORCE can write to even unwritable pmd's, but only
- * after we've gone through a COW cycle and they are dirty.
+ * FOLL_FORCE or a forced COW break can write even to unwritable pmd's,
+ * but only after we've gone through a COW cycle and they are dirty.
*/
static inline bool can_follow_write_pmd(pmd_t pmd, unsigned int flags)
{
- return pmd_write(pmd) ||
- ((flags & FOLL_FORCE) && (flags & FOLL_COW) && pmd_dirty(pmd));
+ return pmd_write(pmd) || ((flags & FOLL_COW) && pmd_dirty(pmd));
}
struct page *follow_trans_huge_pmd(struct vm_area_struct *vma,
@@ -1720,7 +1723,7 @@
* If other processes are mapping this page, we couldn't discard
* the page unless they all do MADV_FREE so let's skip the page.
*/
- if (page_mapcount(page) != 1)
+ if (total_mapcount(page) != 1)
goto out;
if (!trylock_page(page))
@@ -2155,7 +2158,7 @@
count_vm_event(THP_SPLIT_PMD);
if (!vma_is_anonymous(vma)) {
- _pmd = pmdp_huge_clear_flush_notify(vma, haddr, pmd);
+ old_pmd = pmdp_huge_clear_flush_notify(vma, haddr, pmd);
/*
* We are going to unmap this huge page. So
* just go ahead and zap it
@@ -2164,16 +2167,25 @@
zap_deposited_table(mm, pmd);
if (vma_is_dax(vma))
return;
- page = pmd_page(_pmd);
- if (!PageDirty(page) && pmd_dirty(_pmd))
- set_page_dirty(page);
- if (!PageReferenced(page) && pmd_young(_pmd))
- SetPageReferenced(page);
- page_remove_rmap(page, true);
- put_page(page);
+ if (unlikely(is_pmd_migration_entry(old_pmd))) {
+ swp_entry_t entry;
+
+ entry = pmd_to_swp_entry(old_pmd);
+ page = migration_entry_to_page(entry);
+ } else {
+ page = pmd_page(old_pmd);
+ if (!PageDirty(page) && pmd_dirty(old_pmd))
+ set_page_dirty(page);
+ if (!PageReferenced(page) && pmd_young(old_pmd))
+ SetPageReferenced(page);
+ page_remove_rmap(page, true);
+ put_page(page);
+ }
add_mm_counter(mm, mm_counter_file(page), -HPAGE_PMD_NR);
return;
- } else if (is_huge_zero_pmd(*pmd)) {
+ }
+
+ if (is_huge_zero_pmd(*pmd)) {
/*
* FIXME: Do we want to invalidate secondary mmu by calling
* mmu_notifier_invalidate_range() see comments below inside
@@ -2261,27 +2273,33 @@
pte = pte_offset_map(&_pmd, addr);
BUG_ON(!pte_none(*pte));
set_pte_at(mm, addr, pte, entry);
- atomic_inc(&page[i]._mapcount);
+ if (!pmd_migration)
+ atomic_inc(&page[i]._mapcount);
pte_unmap(pte);
}
- /*
- * Set PG_double_map before dropping compound_mapcount to avoid
- * false-negative page_mapped().
- */
- if (compound_mapcount(page) > 1 && !TestSetPageDoubleMap(page)) {
- for (i = 0; i < HPAGE_PMD_NR; i++)
- atomic_inc(&page[i]._mapcount);
- }
-
- if (atomic_add_negative(-1, compound_mapcount_ptr(page))) {
- /* Last compound_mapcount is gone. */
- __dec_node_page_state(page, NR_ANON_THPS);
- if (TestClearPageDoubleMap(page)) {
- /* No need in mapcount reference anymore */
+ if (!pmd_migration) {
+ /*
+ * Set PG_double_map before dropping compound_mapcount to avoid
+ * false-negative page_mapped().
+ */
+ if (compound_mapcount(page) > 1 &&
+ !TestSetPageDoubleMap(page)) {
for (i = 0; i < HPAGE_PMD_NR; i++)
- atomic_dec(&page[i]._mapcount);
+ atomic_inc(&page[i]._mapcount);
}
+
+ lock_page_memcg(page);
+ if (atomic_add_negative(-1, compound_mapcount_ptr(page))) {
+ /* Last compound_mapcount is gone. */
+ __dec_lruvec_page_state(page, NR_ANON_THPS);
+ if (TestClearPageDoubleMap(page)) {
+ /* No need in mapcount reference anymore */
+ for (i = 0; i < HPAGE_PMD_NR; i++)
+ atomic_dec(&page[i]._mapcount);
+ }
+ }
+ unlock_page_memcg(page);
}
smp_wmb(); /* make pte visible before pmd */
@@ -2300,6 +2318,8 @@
{
spinlock_t *ptl;
struct mmu_notifier_range range;
+ bool do_unlock_page = false;
+ pmd_t _pmd;
mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, vma->vm_mm,
address & HPAGE_PMD_MASK,
@@ -2312,11 +2332,41 @@
* pmd against. Otherwise we can end up replacing wrong page.
*/
VM_BUG_ON(freeze && !page);
- if (page && page != pmd_page(*pmd))
- goto out;
+ if (page) {
+ VM_WARN_ON_ONCE(!PageLocked(page));
+ if (page != pmd_page(*pmd))
+ goto out;
+ }
+repeat:
if (pmd_trans_huge(*pmd)) {
- page = pmd_page(*pmd);
+ if (!page) {
+ page = pmd_page(*pmd);
+ /*
+ * An anonymous page must be locked, to ensure that a
+ * concurrent reuse_swap_page() sees stable mapcount;
+ * but reuse_swap_page() is not used on shmem or file,
+ * and page lock must not be taken when zap_pmd_range()
+ * calls __split_huge_pmd() while i_mmap_lock is held.
+ */
+ if (PageAnon(page)) {
+ if (unlikely(!trylock_page(page))) {
+ get_page(page);
+ _pmd = *pmd;
+ spin_unlock(ptl);
+ lock_page(page);
+ spin_lock(ptl);
+ if (unlikely(!pmd_same(*pmd, _pmd))) {
+ unlock_page(page);
+ put_page(page);
+ page = NULL;
+ goto repeat;
+ }
+ put_page(page);
+ }
+ do_unlock_page = true;
+ }
+ }
if (PageMlocked(page))
clear_page_mlock(page);
} else if (!(pmd_devmap(*pmd) || is_pmd_migration_entry(*pmd)))
@@ -2324,6 +2374,8 @@
__split_huge_pmd_locked(vma, pmd, range.start, freeze);
out:
spin_unlock(ptl);
+ if (do_unlock_page)
+ unlock_page(page);
/*
* No need to double call mmu_notifier->invalidate_range() callback.
* They are 3 cases to consider inside __split_huge_pmd_locked():
@@ -2409,16 +2461,16 @@
static void unmap_page(struct page *page)
{
enum ttu_flags ttu_flags = TTU_IGNORE_MLOCK | TTU_IGNORE_ACCESS |
- TTU_RMAP_LOCKED | TTU_SPLIT_HUGE_PMD;
- bool unmap_success;
+ TTU_RMAP_LOCKED | TTU_SPLIT_HUGE_PMD | TTU_SYNC;
VM_BUG_ON_PAGE(!PageHead(page), page);
if (PageAnon(page))
ttu_flags |= TTU_SPLIT_FREEZE;
- unmap_success = try_to_unmap(page, ttu_flags);
- VM_BUG_ON_PAGE(!unmap_success, page);
+ try_to_unmap(page, ttu_flags);
+
+ VM_WARN_ON_ONCE_PAGE(page_mapped(page), page);
}
static void remap_page(struct page *page)
@@ -2537,7 +2589,7 @@
ClearPageCompound(head);
- split_page_owner(head, HPAGE_PMD_ORDER);
+ split_page_owner(head, HPAGE_PMD_NR);
/* See comment in __split_huge_page_tail() */
if (PageAnon(head)) {
@@ -2697,12 +2749,12 @@
struct deferred_split *ds_queue = get_deferred_split_queue(page);
struct anon_vma *anon_vma = NULL;
struct address_space *mapping = NULL;
- int count, mapcount, extra_pins, ret;
+ int extra_pins, ret;
bool mlocked;
unsigned long flags;
pgoff_t end;
- VM_BUG_ON_PAGE(is_huge_zero_page(page), page);
+ VM_BUG_ON_PAGE(is_huge_zero_page(head), head);
VM_BUG_ON_PAGE(!PageLocked(page), page);
VM_BUG_ON_PAGE(!PageCompound(page), page);
@@ -2759,7 +2811,6 @@
mlocked = PageMlocked(page);
unmap_page(head);
- VM_BUG_ON_PAGE(compound_mapcount(head), head);
/* Make sure the page is not on per-CPU pagevec as it takes pin */
if (mlocked)
@@ -2782,9 +2833,7 @@
/* Prevent deferred_split_scan() touching ->_refcount */
spin_lock(&ds_queue->split_queue_lock);
- count = page_count(head);
- mapcount = total_mapcount(head);
- if (!mapcount && page_ref_freeze(head, 1 + extra_pins)) {
+ if (page_ref_freeze(head, 1 + extra_pins)) {
if (!list_empty(page_deferred_list(head))) {
ds_queue->split_queue_len--;
list_del(page_deferred_list(head));
@@ -2805,16 +2854,9 @@
} else
ret = 0;
} else {
- if (IS_ENABLED(CONFIG_DEBUG_VM) && mapcount) {
- pr_alert("total_mapcount: %u, page_count(): %u\n",
- mapcount, count);
- if (PageTail(page))
- dump_page(head, NULL);
- dump_page(page, "total_mapcount(head) > 0");
- BUG();
- }
spin_unlock(&ds_queue->split_queue_lock);
-fail: if (mapping)
+fail:
+ if (mapping)
xa_unlock(&mapping->i_pages);
spin_unlock_irqrestore(&pgdata->lru_lock, flags);
remap_page(head);
@@ -3030,8 +3072,7 @@
return;
flush_cache_range(vma, address, address + HPAGE_PMD_SIZE);
- pmdval = *pvmw->pmd;
- pmdp_invalidate(vma, address, pvmw->pmd);
+ pmdval = pmdp_invalidate(vma, address, pvmw->pmd);
if (pmd_dirty(pmdval))
set_page_dirty(page);
entry = make_migration_entry(page, pmd_write(pmdval));