Update Linux to v5.4.2
Change-Id: Idf6911045d9d382da2cfe01b1edff026404ac8fd
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index d2cd70c..13cc937 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1,8 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0-only
/*
* Copyright (C) 2009 Red Hat, Inc.
- *
- * This work is licensed under the terms of the GNU GPL, version 2. See
- * the COPYING file in the top-level directory.
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
@@ -33,6 +31,8 @@
#include <linux/page_idle.h>
#include <linux/shmem_fs.h>
#include <linux/oom.h>
+#include <linux/numa.h>
+#include <linux/page_owner.h>
#include <asm/tlb.h>
#include <asm/pgalloc.h>
@@ -62,6 +62,21 @@
static atomic_t huge_zero_refcount;
struct page *huge_zero_page __read_mostly;
+bool transparent_hugepage_enabled(struct vm_area_struct *vma)
+{
+ /* The addr is used to check if the vma size fits */
+ unsigned long addr = (vma->vm_end & HPAGE_PMD_MASK) - HPAGE_PMD_SIZE;
+
+ if (!transhuge_vma_suitable(vma, addr))
+ return false;
+ if (vma_is_anonymous(vma))
+ return __transparent_hugepage_enabled(vma);
+ if (vma_is_shmem(vma))
+ return shmem_huge_enabled(vma);
+
+ return false;
+}
+
static struct page *get_huge_zero_page(void)
{
struct page *zero_page;
@@ -420,7 +435,7 @@
* where the extra memory used could hurt more than TLB overhead
* is likely to save. The admin can still enable it through /sys.
*/
- if (totalram_pages < (512 << (20 - PAGE_SHIFT))) {
+ if (totalram_pages() < (512 << (20 - PAGE_SHIFT))) {
transparent_hugepage_flags = 0;
return 0;
}
@@ -481,11 +496,25 @@
return pmd;
}
-static inline struct list_head *page_deferred_list(struct page *page)
+#ifdef CONFIG_MEMCG
+static inline struct deferred_split *get_deferred_split_queue(struct page *page)
{
- /* ->lru in the tail pages is occupied by compound_head. */
- return &page[2].deferred_list;
+ struct mem_cgroup *memcg = compound_head(page)->mem_cgroup;
+ struct pglist_data *pgdat = NODE_DATA(page_to_nid(page));
+
+ if (memcg)
+ return &memcg->deferred_split_queue;
+ else
+ return &pgdat->deferred_split_queue;
}
+#else
+static inline struct deferred_split *get_deferred_split_queue(struct page *page)
+{
+ struct pglist_data *pgdat = NODE_DATA(page_to_nid(page));
+
+ return &pgdat->deferred_split_queue;
+}
+#endif
void prep_transhuge_page(struct page *page)
{
@@ -498,7 +527,7 @@
set_compound_page_dtor(page, TRANSHUGE_PAGE_DTOR);
}
-unsigned long __thp_get_unmapped_area(struct file *filp, unsigned long len,
+static unsigned long __thp_get_unmapped_area(struct file *filp, unsigned long len,
loff_t off, unsigned long flags, unsigned long size)
{
unsigned long addr;
@@ -558,7 +587,7 @@
return VM_FAULT_FALLBACK;
}
- pgtable = pte_alloc_one(vma->vm_mm, haddr);
+ pgtable = pte_alloc_one(vma->vm_mm);
if (unlikely(!pgtable)) {
ret = VM_FAULT_OOM;
goto release;
@@ -606,6 +635,7 @@
mm_inc_nr_ptes(vma->vm_mm);
spin_unlock(vmf->ptl);
count_vm_event(THP_FAULT_ALLOC);
+ count_memcg_events(memcg, THP_FAULT_ALLOC, 1);
}
return 0;
@@ -633,16 +663,25 @@
{
const bool vma_madvised = !!(vma->vm_flags & VM_HUGEPAGE);
+ /* Always do synchronous compaction */
if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags))
return GFP_TRANSHUGE | (vma_madvised ? 0 : __GFP_NORETRY);
+
+ /* Kick kcompactd and fail quickly */
if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags))
return GFP_TRANSHUGE_LIGHT | __GFP_KSWAPD_RECLAIM;
+
+ /* Synchronous compaction if madvised, otherwise kick kcompactd */
if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags))
- return GFP_TRANSHUGE_LIGHT | (vma_madvised ? __GFP_DIRECT_RECLAIM :
- __GFP_KSWAPD_RECLAIM);
+ return GFP_TRANSHUGE_LIGHT |
+ (vma_madvised ? __GFP_DIRECT_RECLAIM :
+ __GFP_KSWAPD_RECLAIM);
+
+ /* Only do synchronous compaction if madvised */
if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags))
- return GFP_TRANSHUGE_LIGHT | (vma_madvised ? __GFP_DIRECT_RECLAIM :
- 0);
+ return GFP_TRANSHUGE_LIGHT |
+ (vma_madvised ? __GFP_DIRECT_RECLAIM : 0);
+
return GFP_TRANSHUGE_LIGHT;
}
@@ -670,7 +709,7 @@
struct page *page;
unsigned long haddr = vmf->address & HPAGE_PMD_MASK;
- if (haddr < vma->vm_start || haddr + HPAGE_PMD_SIZE > vma->vm_end)
+ if (!transhuge_vma_suitable(vma, haddr))
return VM_FAULT_FALLBACK;
if (unlikely(anon_vma_prepare(vma)))
return VM_FAULT_OOM;
@@ -683,7 +722,7 @@
struct page *zero_page;
bool set;
vm_fault_t ret;
- pgtable = pte_alloc_one(vma->vm_mm, haddr);
+ pgtable = pte_alloc_one(vma->vm_mm);
if (unlikely(!pgtable))
return VM_FAULT_OOM;
zero_page = mm_get_huge_zero_page(vma->vm_mm);
@@ -734,6 +773,21 @@
spinlock_t *ptl;
ptl = pmd_lock(mm, pmd);
+ if (!pmd_none(*pmd)) {
+ if (write) {
+ if (pmd_pfn(*pmd) != pfn_t_to_pfn(pfn)) {
+ WARN_ON_ONCE(!is_huge_zero_pmd(*pmd));
+ goto out_unlock;
+ }
+ entry = pmd_mkyoung(*pmd);
+ entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma);
+ if (pmdp_set_access_flags(vma, addr, pmd, entry, 1))
+ update_mmu_cache_pmd(vma, addr, pmd);
+ }
+
+ goto out_unlock;
+ }
+
entry = pmd_mkhuge(pfn_t_pmd(pfn, prot));
if (pfn_t_devmap(pfn))
entry = pmd_mkdevmap(entry);
@@ -745,18 +799,25 @@
if (pgtable) {
pgtable_trans_huge_deposit(mm, pmd, pgtable);
mm_inc_nr_ptes(mm);
+ pgtable = NULL;
}
set_pmd_at(mm, addr, pmd, entry);
update_mmu_cache_pmd(vma, addr, pmd);
+
+out_unlock:
spin_unlock(ptl);
+ if (pgtable)
+ pte_free(mm, pgtable);
}
-vm_fault_t vmf_insert_pfn_pmd(struct vm_area_struct *vma, unsigned long addr,
- pmd_t *pmd, pfn_t pfn, bool write)
+vm_fault_t vmf_insert_pfn_pmd(struct vm_fault *vmf, pfn_t pfn, bool write)
{
+ unsigned long addr = vmf->address & PMD_MASK;
+ struct vm_area_struct *vma = vmf->vma;
pgprot_t pgprot = vma->vm_page_prot;
pgtable_t pgtable = NULL;
+
/*
* If we had pmd_special, we could avoid all these restrictions,
* but we need to be consistent with PTEs and architectures that
@@ -772,14 +833,14 @@
return VM_FAULT_SIGBUS;
if (arch_needs_pgtable_deposit()) {
- pgtable = pte_alloc_one(vma->vm_mm, addr);
+ pgtable = pte_alloc_one(vma->vm_mm);
if (!pgtable)
return VM_FAULT_OOM;
}
track_pfn_insert(vma, &pgprot, pfn);
- insert_pfn_pmd(vma, addr, pmd, pfn, pgprot, write, pgtable);
+ insert_pfn_pmd(vma, addr, vmf->pmd, pfn, pgprot, write, pgtable);
return VM_FAULT_NOPAGE;
}
EXPORT_SYMBOL_GPL(vmf_insert_pfn_pmd);
@@ -800,6 +861,20 @@
spinlock_t *ptl;
ptl = pud_lock(mm, pud);
+ if (!pud_none(*pud)) {
+ if (write) {
+ if (pud_pfn(*pud) != pfn_t_to_pfn(pfn)) {
+ WARN_ON_ONCE(!is_huge_zero_pud(*pud));
+ goto out_unlock;
+ }
+ entry = pud_mkyoung(*pud);
+ entry = maybe_pud_mkwrite(pud_mkdirty(entry), vma);
+ if (pudp_set_access_flags(vma, addr, pud, entry, 1))
+ update_mmu_cache_pud(vma, addr, pud);
+ }
+ goto out_unlock;
+ }
+
entry = pud_mkhuge(pfn_t_pud(pfn, prot));
if (pfn_t_devmap(pfn))
entry = pud_mkdevmap(entry);
@@ -809,13 +884,17 @@
}
set_pud_at(mm, addr, pud, entry);
update_mmu_cache_pud(vma, addr, pud);
+
+out_unlock:
spin_unlock(ptl);
}
-vm_fault_t vmf_insert_pfn_pud(struct vm_area_struct *vma, unsigned long addr,
- pud_t *pud, pfn_t pfn, bool write)
+vm_fault_t vmf_insert_pfn_pud(struct vm_fault *vmf, pfn_t pfn, bool write)
{
+ unsigned long addr = vmf->address & PUD_MASK;
+ struct vm_area_struct *vma = vmf->vma;
pgprot_t pgprot = vma->vm_page_prot;
+
/*
* If we had pud_special, we could avoid all these restrictions,
* but we need to be consistent with PTEs and architectures that
@@ -832,7 +911,7 @@
track_pfn_insert(vma, &pgprot, pfn);
- insert_pfn_pud(vma, addr, pud, pfn, pgprot, write);
+ insert_pfn_pud(vma, addr, vmf->pud, pfn, pgprot, write);
return VM_FAULT_NOPAGE;
}
EXPORT_SYMBOL_GPL(vmf_insert_pfn_pud);
@@ -852,11 +931,10 @@
}
struct page *follow_devmap_pmd(struct vm_area_struct *vma, unsigned long addr,
- pmd_t *pmd, int flags)
+ pmd_t *pmd, int flags, struct dev_pagemap **pgmap)
{
unsigned long pfn = pmd_pfn(*pmd);
struct mm_struct *mm = vma->vm_mm;
- struct dev_pagemap *pgmap;
struct page *page;
assert_spin_locked(pmd_lockptr(mm, pmd));
@@ -886,12 +964,11 @@
return ERR_PTR(-EEXIST);
pfn += (addr & ~PMD_MASK) >> PAGE_SHIFT;
- pgmap = get_dev_pagemap(pfn, NULL);
- if (!pgmap)
+ *pgmap = get_dev_pagemap(pfn, *pgmap);
+ if (!*pgmap)
return ERR_PTR(-EFAULT);
page = pfn_to_page(pfn);
get_page(page);
- put_dev_pagemap(pgmap);
return page;
}
@@ -910,7 +987,7 @@
if (!vma_is_anonymous(vma))
return 0;
- pgtable = pte_alloc_one(dst_mm, addr);
+ pgtable = pte_alloc_one(dst_mm);
if (unlikely(!pgtable))
goto out;
@@ -1000,11 +1077,10 @@
}
struct page *follow_devmap_pud(struct vm_area_struct *vma, unsigned long addr,
- pud_t *pud, int flags)
+ pud_t *pud, int flags, struct dev_pagemap **pgmap)
{
unsigned long pfn = pud_pfn(*pud);
struct mm_struct *mm = vma->vm_mm;
- struct dev_pagemap *pgmap;
struct page *page;
assert_spin_locked(pud_lockptr(mm, pud));
@@ -1028,12 +1104,11 @@
return ERR_PTR(-EEXIST);
pfn += (addr & ~PUD_MASK) >> PAGE_SHIFT;
- pgmap = get_dev_pagemap(pfn, NULL);
- if (!pgmap)
+ *pgmap = get_dev_pagemap(pfn, *pgmap);
+ if (!*pgmap)
return ERR_PTR(-EFAULT);
page = pfn_to_page(pfn);
get_page(page);
- put_dev_pagemap(pgmap);
return page;
}
@@ -1129,8 +1204,7 @@
int i;
vm_fault_t ret = 0;
struct page **pages;
- unsigned long mmun_start; /* For mmu_notifiers */
- unsigned long mmun_end; /* For mmu_notifiers */
+ struct mmu_notifier_range range;
pages = kmalloc_array(HPAGE_PMD_NR, sizeof(struct page *),
GFP_KERNEL);
@@ -1168,9 +1242,9 @@
cond_resched();
}
- mmun_start = haddr;
- mmun_end = haddr + HPAGE_PMD_SIZE;
- mmu_notifier_invalidate_range_start(vma->vm_mm, mmun_start, mmun_end);
+ mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, vma->vm_mm,
+ haddr, haddr + HPAGE_PMD_SIZE);
+ mmu_notifier_invalidate_range_start(&range);
vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd);
if (unlikely(!pmd_same(*vmf->pmd, orig_pmd)))
@@ -1215,8 +1289,7 @@
* No need to double call mmu_notifier->invalidate_range() callback as
* the above pmdp_huge_clear_flush_notify() did already call it.
*/
- mmu_notifier_invalidate_range_only_end(vma->vm_mm, mmun_start,
- mmun_end);
+ mmu_notifier_invalidate_range_only_end(&range);
ret |= VM_FAULT_WRITE;
put_page(page);
@@ -1226,7 +1299,7 @@
out_free_pages:
spin_unlock(vmf->ptl);
- mmu_notifier_invalidate_range_end(vma->vm_mm, mmun_start, mmun_end);
+ mmu_notifier_invalidate_range_end(&range);
for (i = 0; i < HPAGE_PMD_NR; i++) {
memcg = (void *)page_private(pages[i]);
set_page_private(pages[i], 0);
@@ -1243,8 +1316,7 @@
struct page *page = NULL, *new_page;
struct mem_cgroup *memcg;
unsigned long haddr = vmf->address & HPAGE_PMD_MASK;
- unsigned long mmun_start; /* For mmu_notifiers */
- unsigned long mmun_end; /* For mmu_notifiers */
+ struct mmu_notifier_range range;
gfp_t huge_gfp; /* for allocation and charge */
vm_fault_t ret = 0;
@@ -1288,7 +1360,7 @@
get_page(page);
spin_unlock(vmf->ptl);
alloc:
- if (transparent_hugepage_enabled(vma) &&
+ if (__transparent_hugepage_enabled(vma) &&
!transparent_hugepage_debug_cow()) {
huge_gfp = alloc_hugepage_direct_gfpmask(vma);
new_page = alloc_hugepage_vma(huge_gfp, vma, haddr, HPAGE_PMD_ORDER);
@@ -1325,6 +1397,7 @@
}
count_vm_event(THP_FAULT_ALLOC);
+ count_memcg_events(memcg, THP_FAULT_ALLOC, 1);
if (!page)
clear_huge_page(new_page, vmf->address, HPAGE_PMD_NR);
@@ -1333,9 +1406,9 @@
vma, HPAGE_PMD_NR);
__SetPageUptodate(new_page);
- mmun_start = haddr;
- mmun_end = haddr + HPAGE_PMD_SIZE;
- mmu_notifier_invalidate_range_start(vma->vm_mm, mmun_start, mmun_end);
+ mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, vma->vm_mm,
+ haddr, haddr + HPAGE_PMD_SIZE);
+ mmu_notifier_invalidate_range_start(&range);
spin_lock(vmf->ptl);
if (page)
@@ -1370,8 +1443,7 @@
* No need to double call mmu_notifier->invalidate_range() callback as
* the above pmdp_huge_clear_flush_notify() did already call it.
*/
- mmu_notifier_invalidate_range_only_end(vma->vm_mm, mmun_start,
- mmun_end);
+ mmu_notifier_invalidate_range_only_end(&range);
out:
return ret;
out_unlock:
@@ -1464,7 +1536,7 @@
struct anon_vma *anon_vma = NULL;
struct page *page;
unsigned long haddr = vmf->address & HPAGE_PMD_MASK;
- int page_nid = -1, this_nid = numa_node_id();
+ int page_nid = NUMA_NO_NODE, this_nid = numa_node_id();
int target_nid, last_cpupid = -1;
bool page_locked;
bool migrated = false;
@@ -1485,8 +1557,7 @@
if (!get_page_unless_zero(page))
goto out_unlock;
spin_unlock(vmf->ptl);
- wait_on_page_locked(page);
- put_page(page);
+ put_and_wait_on_page_locked(page);
goto out;
}
@@ -1510,7 +1581,7 @@
*/
page_locked = trylock_page(page);
target_nid = mpol_misplaced(page, vma, haddr);
- if (target_nid == -1) {
+ if (target_nid == NUMA_NO_NODE) {
/* If the page was locked, there are no parallel migrations */
if (page_locked)
goto clear_pmdnuma;
@@ -1518,12 +1589,11 @@
/* Migration could have started since the pmd_trans_migrating check */
if (!page_locked) {
- page_nid = -1;
+ page_nid = NUMA_NO_NODE;
if (!get_page_unless_zero(page))
goto out_unlock;
spin_unlock(vmf->ptl);
- wait_on_page_locked(page);
- put_page(page);
+ put_and_wait_on_page_locked(page);
goto out;
}
@@ -1540,14 +1610,14 @@
if (unlikely(!pmd_same(pmd, *vmf->pmd))) {
unlock_page(page);
put_page(page);
- page_nid = -1;
+ page_nid = NUMA_NO_NODE;
goto out_unlock;
}
/* Bail if we fail to protect against THP splits for any reason */
if (unlikely(!anon_vma)) {
put_page(page);
- page_nid = -1;
+ page_nid = NUMA_NO_NODE;
goto clear_pmdnuma;
}
@@ -1562,8 +1632,20 @@
* We are not sure a pending tlb flush here is for a huge page
* mapping or not. Hence use the tlb range variant
*/
- if (mm_tlb_flush_pending(vma->vm_mm))
+ if (mm_tlb_flush_pending(vma->vm_mm)) {
flush_tlb_range(vma, haddr, haddr + HPAGE_PMD_SIZE);
+ /*
+ * change_huge_pmd() released the pmd lock before
+ * invalidating the secondary MMUs sharing the primary
+ * MMU pagetables (with ->invalidate_range()). The
+ * mmu_notifier_invalidate_range_end() (which
+ * internally calls ->invalidate_range()) in
+ * change_pmd_range() will run after us, so we can't
+ * rely on it here and we need an explicit invalidate.
+ */
+ mmu_notifier_invalidate_range(vma->vm_mm, haddr,
+ haddr + HPAGE_PMD_SIZE);
+ }
/*
* Migrate the THP to the requested node, returns with page unlocked
@@ -1597,7 +1679,7 @@
if (anon_vma)
page_unlock_anon_vma_read(anon_vma);
- if (page_nid != -1)
+ if (page_nid != NUMA_NO_NODE)
task_numa_fault(last_cpupid, page_nid, HPAGE_PMD_NR,
flags);
@@ -1617,7 +1699,7 @@
struct mm_struct *mm = tlb->mm;
bool ret = false;
- tlb_remove_check_page_size_change(tlb, HPAGE_PMD_SIZE);
+ tlb_change_page_size(tlb, HPAGE_PMD_SIZE);
ptl = pmd_trans_huge_lock(pmd, vma);
if (!ptl)
@@ -1693,7 +1775,7 @@
pmd_t orig_pmd;
spinlock_t *ptl;
- tlb_remove_check_page_size_change(tlb, HPAGE_PMD_SIZE);
+ tlb_change_page_size(tlb, HPAGE_PMD_SIZE);
ptl = __pmd_trans_huge_lock(pmd, vma);
if (!ptl)
@@ -1958,7 +2040,6 @@
int zap_huge_pud(struct mmu_gather *tlb, struct vm_area_struct *vma,
pud_t *pud, unsigned long addr)
{
- pud_t orig_pud;
spinlock_t *ptl;
ptl = __pud_trans_huge_lock(pud, vma);
@@ -1970,8 +2051,7 @@
* pgtable_trans_huge_withdraw after finishing pudp related
* operations.
*/
- orig_pud = pudp_huge_get_and_clear_full(tlb->mm, addr, pud,
- tlb->fullmm);
+ pudp_huge_get_and_clear_full(tlb->mm, addr, pud, tlb->fullmm);
tlb_remove_pud_tlb_entry(tlb, pud, addr);
if (vma_is_dax(vma)) {
spin_unlock(ptl);
@@ -2000,14 +2080,16 @@
unsigned long address)
{
spinlock_t *ptl;
- struct mm_struct *mm = vma->vm_mm;
- unsigned long haddr = address & HPAGE_PUD_MASK;
+ struct mmu_notifier_range range;
- mmu_notifier_invalidate_range_start(mm, haddr, haddr + HPAGE_PUD_SIZE);
- ptl = pud_lock(mm, pud);
+ mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, vma->vm_mm,
+ address & HPAGE_PUD_MASK,
+ (address & HPAGE_PUD_MASK) + HPAGE_PUD_SIZE);
+ mmu_notifier_invalidate_range_start(&range);
+ ptl = pud_lock(vma->vm_mm, pud);
if (unlikely(!pud_trans_huge(*pud) && !pud_devmap(*pud)))
goto out;
- __split_huge_pud_locked(vma, pud, haddr);
+ __split_huge_pud_locked(vma, pud, range.start);
out:
spin_unlock(ptl);
@@ -2015,8 +2097,7 @@
* No need to double call mmu_notifier->invalidate_range() callback as
* the above pudp_huge_clear_flush_notify() did already call it.
*/
- mmu_notifier_invalidate_range_only_end(mm, haddr, haddr +
- HPAGE_PUD_SIZE);
+ mmu_notifier_invalidate_range_only_end(&range);
}
#endif /* CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */
@@ -2218,11 +2299,13 @@
unsigned long address, bool freeze, struct page *page)
{
spinlock_t *ptl;
- struct mm_struct *mm = vma->vm_mm;
- unsigned long haddr = address & HPAGE_PMD_MASK;
+ struct mmu_notifier_range range;
- mmu_notifier_invalidate_range_start(mm, haddr, haddr + HPAGE_PMD_SIZE);
- ptl = pmd_lock(mm, pmd);
+ mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, vma->vm_mm,
+ address & HPAGE_PMD_MASK,
+ (address & HPAGE_PMD_MASK) + HPAGE_PMD_SIZE);
+ mmu_notifier_invalidate_range_start(&range);
+ ptl = pmd_lock(vma->vm_mm, pmd);
/*
* If caller asks to setup a migration entries, we need a page to check
@@ -2238,7 +2321,7 @@
clear_page_mlock(page);
} else if (!(pmd_devmap(*pmd) || is_pmd_migration_entry(*pmd)))
goto out;
- __split_huge_pmd_locked(vma, pmd, haddr, freeze);
+ __split_huge_pmd_locked(vma, pmd, range.start, freeze);
out:
spin_unlock(ptl);
/*
@@ -2254,8 +2337,7 @@
* any further changes to individual pte will notify. So no need
* to call mmu_notifier->invalidate_range()
*/
- mmu_notifier_invalidate_range_only_end(mm, haddr, haddr +
- HPAGE_PMD_SIZE);
+ mmu_notifier_invalidate_range_only_end(&range);
}
void split_huge_pmd_address(struct vm_area_struct *vma, unsigned long address,
@@ -2371,6 +2453,7 @@
(1L << PG_mlocked) |
(1L << PG_uptodate) |
(1L << PG_active) |
+ (1L << PG_workingset) |
(1L << PG_locked) |
(1L << PG_unevictable) |
(1L << PG_dirty)));
@@ -2415,15 +2498,25 @@
pgoff_t end, unsigned long flags)
{
struct page *head = compound_head(page);
- struct zone *zone = page_zone(head);
+ pg_data_t *pgdat = page_pgdat(head);
struct lruvec *lruvec;
+ struct address_space *swap_cache = NULL;
+ unsigned long offset = 0;
int i;
- lruvec = mem_cgroup_page_lruvec(head, zone->zone_pgdat);
+ lruvec = mem_cgroup_page_lruvec(head, pgdat);
/* complete memcg works before add pages to LRU */
mem_cgroup_split_huge_fixup(head);
+ if (PageAnon(head) && PageSwapCache(head)) {
+ swp_entry_t entry = { .val = page_private(head) };
+
+ offset = swp_offset(entry);
+ swap_cache = swap_address_space(entry);
+ xa_lock(&swap_cache->i_pages);
+ }
+
for (i = HPAGE_PMD_NR - 1; i >= 1; i--) {
__split_huge_page_tail(head, i, lruvec, list);
/* Some pages can be beyond i_size: drop them from page cache */
@@ -2433,24 +2526,35 @@
if (IS_ENABLED(CONFIG_SHMEM) && PageSwapBacked(head))
shmem_uncharge(head->mapping->host, 1);
put_page(head + i);
+ } else if (!PageAnon(page)) {
+ __xa_store(&head->mapping->i_pages, head[i].index,
+ head + i, 0);
+ } else if (swap_cache) {
+ __xa_store(&swap_cache->i_pages, offset + i,
+ head + i, 0);
}
}
ClearPageCompound(head);
+
+ split_page_owner(head, HPAGE_PMD_ORDER);
+
/* See comment in __split_huge_page_tail() */
if (PageAnon(head)) {
- /* Additional pin to radix tree of swap cache */
- if (PageSwapCache(head))
+ /* Additional pin to swap cache */
+ if (PageSwapCache(head)) {
page_ref_add(head, 2);
- else
+ xa_unlock(&swap_cache->i_pages);
+ } else {
page_ref_inc(head);
+ }
} else {
- /* Additional pin to radix tree */
+ /* Additional pin to page cache */
page_ref_add(head, 2);
xa_unlock(&head->mapping->i_pages);
}
- spin_unlock_irqrestore(zone_lru_lock(page_zone(head)), flags);
+ spin_unlock_irqrestore(&pgdat->lru_lock, flags);
remap_page(head);
@@ -2557,7 +2661,7 @@
{
int extra_pins;
- /* Additional pins from radix tree */
+ /* Additional pins from page cache */
if (PageAnon(page))
extra_pins = PageSwapCache(page) ? HPAGE_PMD_NR : 0;
else
@@ -2590,6 +2694,7 @@
{
struct page *head = compound_head(page);
struct pglist_data *pgdata = NODE_DATA(page_to_nid(head));
+ 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;
@@ -2661,35 +2766,37 @@
lru_add_drain();
/* prevent PageLRU to go away from under us, and freeze lru stats */
- spin_lock_irqsave(zone_lru_lock(page_zone(head)), flags);
+ spin_lock_irqsave(&pgdata->lru_lock, flags);
if (mapping) {
- void **pslot;
+ XA_STATE(xas, &mapping->i_pages, page_index(head));
- xa_lock(&mapping->i_pages);
- pslot = radix_tree_lookup_slot(&mapping->i_pages,
- page_index(head));
/*
- * Check if the head page is present in radix tree.
+ * Check if the head page is present in page cache.
* We assume all tail are present too, if head is there.
*/
- if (radix_tree_deref_slot_protected(pslot,
- &mapping->i_pages.xa_lock) != head)
+ xa_lock(&mapping->i_pages);
+ if (xas_load(&xas) != head)
goto fail;
}
/* Prevent deferred_split_scan() touching ->_refcount */
- spin_lock(&pgdata->split_queue_lock);
+ 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 (!list_empty(page_deferred_list(head))) {
- pgdata->split_queue_len--;
+ ds_queue->split_queue_len--;
list_del(page_deferred_list(head));
}
- if (mapping)
- __dec_node_page_state(page, NR_SHMEM_THPS);
- spin_unlock(&pgdata->split_queue_lock);
+ if (mapping) {
+ if (PageSwapBacked(page))
+ __dec_node_page_state(page, NR_SHMEM_THPS);
+ else
+ __dec_node_page_state(page, NR_FILE_THPS);
+ }
+
+ spin_unlock(&ds_queue->split_queue_lock);
__split_huge_page(page, list, end, flags);
if (PageSwapCache(head)) {
swp_entry_t entry = { .val = page_private(head) };
@@ -2706,10 +2813,10 @@
dump_page(page, "total_mapcount(head) > 0");
BUG();
}
- spin_unlock(&pgdata->split_queue_lock);
+ spin_unlock(&ds_queue->split_queue_lock);
fail: if (mapping)
xa_unlock(&mapping->i_pages);
- spin_unlock_irqrestore(zone_lru_lock(page_zone(head)), flags);
+ spin_unlock_irqrestore(&pgdata->lru_lock, flags);
remap_page(head);
ret = -EBUSY;
}
@@ -2728,53 +2835,86 @@
void free_transhuge_page(struct page *page)
{
- struct pglist_data *pgdata = NODE_DATA(page_to_nid(page));
+ struct deferred_split *ds_queue = get_deferred_split_queue(page);
unsigned long flags;
- spin_lock_irqsave(&pgdata->split_queue_lock, flags);
+ spin_lock_irqsave(&ds_queue->split_queue_lock, flags);
if (!list_empty(page_deferred_list(page))) {
- pgdata->split_queue_len--;
+ ds_queue->split_queue_len--;
list_del(page_deferred_list(page));
}
- spin_unlock_irqrestore(&pgdata->split_queue_lock, flags);
+ spin_unlock_irqrestore(&ds_queue->split_queue_lock, flags);
free_compound_page(page);
}
void deferred_split_huge_page(struct page *page)
{
- struct pglist_data *pgdata = NODE_DATA(page_to_nid(page));
+ struct deferred_split *ds_queue = get_deferred_split_queue(page);
+#ifdef CONFIG_MEMCG
+ struct mem_cgroup *memcg = compound_head(page)->mem_cgroup;
+#endif
unsigned long flags;
VM_BUG_ON_PAGE(!PageTransHuge(page), page);
- spin_lock_irqsave(&pgdata->split_queue_lock, flags);
+ /*
+ * The try_to_unmap() in page reclaim path might reach here too,
+ * this may cause a race condition to corrupt deferred split queue.
+ * And, if page reclaim is already handling the same page, it is
+ * unnecessary to handle it again in shrinker.
+ *
+ * Check PageSwapCache to determine if the page is being
+ * handled by page reclaim since THP swap would add the page into
+ * swap cache before calling try_to_unmap().
+ */
+ if (PageSwapCache(page))
+ return;
+
+ spin_lock_irqsave(&ds_queue->split_queue_lock, flags);
if (list_empty(page_deferred_list(page))) {
count_vm_event(THP_DEFERRED_SPLIT_PAGE);
- list_add_tail(page_deferred_list(page), &pgdata->split_queue);
- pgdata->split_queue_len++;
+ list_add_tail(page_deferred_list(page), &ds_queue->split_queue);
+ ds_queue->split_queue_len++;
+#ifdef CONFIG_MEMCG
+ if (memcg)
+ memcg_set_shrinker_bit(memcg, page_to_nid(page),
+ deferred_split_shrinker.id);
+#endif
}
- spin_unlock_irqrestore(&pgdata->split_queue_lock, flags);
+ spin_unlock_irqrestore(&ds_queue->split_queue_lock, flags);
}
static unsigned long deferred_split_count(struct shrinker *shrink,
struct shrink_control *sc)
{
struct pglist_data *pgdata = NODE_DATA(sc->nid);
- return READ_ONCE(pgdata->split_queue_len);
+ struct deferred_split *ds_queue = &pgdata->deferred_split_queue;
+
+#ifdef CONFIG_MEMCG
+ if (sc->memcg)
+ ds_queue = &sc->memcg->deferred_split_queue;
+#endif
+ return READ_ONCE(ds_queue->split_queue_len);
}
static unsigned long deferred_split_scan(struct shrinker *shrink,
struct shrink_control *sc)
{
struct pglist_data *pgdata = NODE_DATA(sc->nid);
+ struct deferred_split *ds_queue = &pgdata->deferred_split_queue;
unsigned long flags;
LIST_HEAD(list), *pos, *next;
struct page *page;
int split = 0;
- spin_lock_irqsave(&pgdata->split_queue_lock, flags);
+#ifdef CONFIG_MEMCG
+ if (sc->memcg)
+ ds_queue = &sc->memcg->deferred_split_queue;
+#endif
+
+ spin_lock_irqsave(&ds_queue->split_queue_lock, flags);
/* Take pin on all head pages to avoid freeing them under us */
- list_for_each_safe(pos, next, &pgdata->split_queue) {
+ list_for_each_safe(pos, next, &ds_queue->split_queue) {
page = list_entry((void *)pos, struct page, mapping);
page = compound_head(page);
if (get_page_unless_zero(page)) {
@@ -2782,12 +2922,12 @@
} else {
/* We lost race with put_compound_page() */
list_del_init(page_deferred_list(page));
- pgdata->split_queue_len--;
+ ds_queue->split_queue_len--;
}
if (!--sc->nr_to_scan)
break;
}
- spin_unlock_irqrestore(&pgdata->split_queue_lock, flags);
+ spin_unlock_irqrestore(&ds_queue->split_queue_lock, flags);
list_for_each_safe(pos, next, &list) {
page = list_entry((void *)pos, struct page, mapping);
@@ -2801,15 +2941,15 @@
put_page(page);
}
- spin_lock_irqsave(&pgdata->split_queue_lock, flags);
- list_splice_tail(&list, &pgdata->split_queue);
- spin_unlock_irqrestore(&pgdata->split_queue_lock, flags);
+ spin_lock_irqsave(&ds_queue->split_queue_lock, flags);
+ list_splice_tail(&list, &ds_queue->split_queue);
+ spin_unlock_irqrestore(&ds_queue->split_queue_lock, flags);
/*
* Stop shrinker if we didn't split any page, but the queue is empty.
* This can happen if pages were freed under us.
*/
- if (!split && list_empty(&pgdata->split_queue))
+ if (!split && list_empty(&ds_queue->split_queue))
return SHRINK_STOP;
return split;
}
@@ -2818,7 +2958,8 @@
.count_objects = deferred_split_count,
.scan_objects = deferred_split_scan,
.seeks = DEFAULT_SEEKS,
- .flags = SHRINKER_NUMA_AWARE,
+ .flags = SHRINKER_NUMA_AWARE | SHRINKER_MEMCG_AWARE |
+ SHRINKER_NONSLAB,
};
#ifdef CONFIG_DEBUG_FS
@@ -2867,12 +3008,8 @@
static int __init split_huge_pages_debugfs(void)
{
- void *ret;
-
- ret = debugfs_create_file("split_huge_pages", 0200, NULL, NULL,
- &split_huge_pages_fops);
- if (!ret)
- pr_warn("Failed to create split_huge_pages in debugfs");
+ debugfs_create_file("split_huge_pages", 0200, NULL, NULL,
+ &split_huge_pages_fops);
return 0;
}
late_initcall(split_huge_pages_debugfs);