summaryrefslogtreecommitdiffstats
path: root/mm/huge_memory.c
diff options
context:
space:
mode:
Diffstat (limited to 'mm/huge_memory.c')
-rw-r--r--mm/huge_memory.c146
1 files changed, 113 insertions, 33 deletions
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index e60837dc785..d9a21d06b86 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -715,13 +715,20 @@ static int __do_huge_pmd_anonymous_page(struct mm_struct *mm,
unsigned long haddr, pmd_t *pmd,
struct page *page)
{
+ struct mem_cgroup *memcg;
pgtable_t pgtable;
spinlock_t *ptl;
VM_BUG_ON_PAGE(!PageCompound(page), page);
+
+ if (mem_cgroup_try_charge(page, mm, GFP_TRANSHUGE, &memcg))
+ return VM_FAULT_OOM;
+
pgtable = pte_alloc_one(mm, haddr);
- if (unlikely(!pgtable))
+ if (unlikely(!pgtable)) {
+ mem_cgroup_cancel_charge(page, memcg);
return VM_FAULT_OOM;
+ }
clear_huge_page(page, haddr, HPAGE_PMD_NR);
/*
@@ -734,7 +741,7 @@ static int __do_huge_pmd_anonymous_page(struct mm_struct *mm,
ptl = pmd_lock(mm, pmd);
if (unlikely(!pmd_none(*pmd))) {
spin_unlock(ptl);
- mem_cgroup_uncharge_page(page);
+ mem_cgroup_cancel_charge(page, memcg);
put_page(page);
pte_free(mm, pgtable);
} else {
@@ -742,6 +749,8 @@ static int __do_huge_pmd_anonymous_page(struct mm_struct *mm,
entry = mk_huge_pmd(page, vma->vm_page_prot);
entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma);
page_add_new_anon_rmap(page, vma, haddr);
+ mem_cgroup_commit_charge(page, memcg, false);
+ lru_cache_add_active_or_unevictable(page, vma);
pgtable_trans_huge_deposit(mm, pmd, pgtable);
set_pmd_at(mm, haddr, pmd, entry);
add_mm_counter(mm, MM_ANONPAGES, HPAGE_PMD_NR);
@@ -827,13 +836,7 @@ int do_huge_pmd_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma,
count_vm_event(THP_FAULT_FALLBACK);
return VM_FAULT_FALLBACK;
}
- if (unlikely(mem_cgroup_charge_anon(page, mm, GFP_KERNEL))) {
- put_page(page);
- count_vm_event(THP_FAULT_FALLBACK);
- return VM_FAULT_FALLBACK;
- }
if (unlikely(__do_huge_pmd_anonymous_page(mm, vma, haddr, pmd, page))) {
- mem_cgroup_uncharge_page(page);
put_page(page);
count_vm_event(THP_FAULT_FALLBACK);
return VM_FAULT_FALLBACK;
@@ -941,6 +944,37 @@ unlock:
spin_unlock(ptl);
}
+/*
+ * Save CONFIG_DEBUG_PAGEALLOC from faulting falsely on tail pages
+ * during copy_user_huge_page()'s copy_page_rep(): in the case when
+ * the source page gets split and a tail freed before copy completes.
+ * Called under pmd_lock of checked pmd, so safe from splitting itself.
+ */
+static void get_user_huge_page(struct page *page)
+{
+ if (IS_ENABLED(CONFIG_DEBUG_PAGEALLOC)) {
+ struct page *endpage = page + HPAGE_PMD_NR;
+
+ atomic_add(HPAGE_PMD_NR, &page->_count);
+ while (++page < endpage)
+ get_huge_page_tail(page);
+ } else {
+ get_page(page);
+ }
+}
+
+static void put_user_huge_page(struct page *page)
+{
+ if (IS_ENABLED(CONFIG_DEBUG_PAGEALLOC)) {
+ struct page *endpage = page + HPAGE_PMD_NR;
+
+ while (page < endpage)
+ put_page(page++);
+ } else {
+ put_page(page);
+ }
+}
+
static int do_huge_pmd_wp_page_fallback(struct mm_struct *mm,
struct vm_area_struct *vma,
unsigned long address,
@@ -948,6 +982,7 @@ static int do_huge_pmd_wp_page_fallback(struct mm_struct *mm,
struct page *page,
unsigned long haddr)
{
+ struct mem_cgroup *memcg;
spinlock_t *ptl;
pgtable_t pgtable;
pmd_t _pmd;
@@ -968,20 +1003,21 @@ static int do_huge_pmd_wp_page_fallback(struct mm_struct *mm,
__GFP_OTHER_NODE,
vma, address, page_to_nid(page));
if (unlikely(!pages[i] ||
- mem_cgroup_charge_anon(pages[i], mm,
- GFP_KERNEL))) {
+ mem_cgroup_try_charge(pages[i], mm, GFP_KERNEL,
+ &memcg))) {
if (pages[i])
put_page(pages[i]);
- mem_cgroup_uncharge_start();
while (--i >= 0) {
- mem_cgroup_uncharge_page(pages[i]);
+ memcg = (void *)page_private(pages[i]);
+ set_page_private(pages[i], 0);
+ mem_cgroup_cancel_charge(pages[i], memcg);
put_page(pages[i]);
}
- mem_cgroup_uncharge_end();
kfree(pages);
ret |= VM_FAULT_OOM;
goto out;
}
+ set_page_private(pages[i], (unsigned long)memcg);
}
for (i = 0; i < HPAGE_PMD_NR; i++) {
@@ -1010,7 +1046,11 @@ static int do_huge_pmd_wp_page_fallback(struct mm_struct *mm,
pte_t *pte, entry;
entry = mk_pte(pages[i], vma->vm_page_prot);
entry = maybe_mkwrite(pte_mkdirty(entry), vma);
+ memcg = (void *)page_private(pages[i]);
+ set_page_private(pages[i], 0);
page_add_new_anon_rmap(pages[i], vma, haddr);
+ mem_cgroup_commit_charge(pages[i], memcg, false);
+ lru_cache_add_active_or_unevictable(pages[i], vma);
pte = pte_offset_map(&_pmd, haddr);
VM_BUG_ON(!pte_none(*pte));
set_pte_at(mm, haddr, pte, entry);
@@ -1034,12 +1074,12 @@ out:
out_free_pages:
spin_unlock(ptl);
mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end);
- mem_cgroup_uncharge_start();
for (i = 0; i < HPAGE_PMD_NR; i++) {
- mem_cgroup_uncharge_page(pages[i]);
+ memcg = (void *)page_private(pages[i]);
+ set_page_private(pages[i], 0);
+ mem_cgroup_cancel_charge(pages[i], memcg);
put_page(pages[i]);
}
- mem_cgroup_uncharge_end();
kfree(pages);
goto out;
}
@@ -1050,6 +1090,7 @@ int do_huge_pmd_wp_page(struct mm_struct *mm, struct vm_area_struct *vma,
spinlock_t *ptl;
int ret = 0;
struct page *page = NULL, *new_page;
+ struct mem_cgroup *memcg;
unsigned long haddr;
unsigned long mmun_start; /* For mmu_notifiers */
unsigned long mmun_end; /* For mmu_notifiers */
@@ -1074,7 +1115,7 @@ int do_huge_pmd_wp_page(struct mm_struct *mm, struct vm_area_struct *vma,
ret |= VM_FAULT_WRITE;
goto out_unlock;
}
- get_page(page);
+ get_user_huge_page(page);
spin_unlock(ptl);
alloc:
if (transparent_hugepage_enabled(vma) &&
@@ -1095,17 +1136,18 @@ alloc:
split_huge_page(page);
ret |= VM_FAULT_FALLBACK;
}
- put_page(page);
+ put_user_huge_page(page);
}
count_vm_event(THP_FAULT_FALLBACK);
goto out;
}
- if (unlikely(mem_cgroup_charge_anon(new_page, mm, GFP_KERNEL))) {
+ if (unlikely(mem_cgroup_try_charge(new_page, mm,
+ GFP_TRANSHUGE, &memcg))) {
put_page(new_page);
if (page) {
split_huge_page(page);
- put_page(page);
+ put_user_huge_page(page);
} else
split_huge_page_pmd(vma, address, pmd);
ret |= VM_FAULT_FALLBACK;
@@ -1127,10 +1169,10 @@ alloc:
spin_lock(ptl);
if (page)
- put_page(page);
+ put_user_huge_page(page);
if (unlikely(!pmd_same(*pmd, orig_pmd))) {
spin_unlock(ptl);
- mem_cgroup_uncharge_page(new_page);
+ mem_cgroup_cancel_charge(new_page, memcg);
put_page(new_page);
goto out_mn;
} else {
@@ -1139,6 +1181,8 @@ alloc:
entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma);
pmdp_clear_flush(vma, haddr, pmd);
page_add_new_anon_rmap(new_page, vma, haddr);
+ mem_cgroup_commit_charge(new_page, memcg, false);
+ lru_cache_add_active_or_unevictable(new_page, vma);
set_pmd_at(mm, haddr, pmd, entry);
update_mmu_cache_pmd(vma, address, pmd);
if (!page) {
@@ -1650,7 +1694,7 @@ static void __split_huge_page_refcount(struct page *page,
&page_tail->_count);
/* after clearing PageTail the gup refcount can be released */
- smp_mb();
+ smp_mb__after_atomic();
/*
* retain hwpoison flag of the poisoned tail page:
@@ -1744,6 +1788,8 @@ static int __split_huge_page_map(struct page *page,
if (pmd) {
pgtable = pgtable_trans_huge_withdraw(mm, pmd);
pmd_populate(mm, &_pmd, pgtable);
+ if (pmd_write(*pmd))
+ BUG_ON(page_mapcount(page) != 1);
haddr = address;
for (i = 0; i < HPAGE_PMD_NR; i++, haddr += PAGE_SIZE) {
@@ -1753,8 +1799,6 @@ static int __split_huge_page_map(struct page *page,
entry = maybe_mkwrite(pte_mkdirty(entry), vma);
if (!pmd_write(*pmd))
entry = pte_wrprotect(entry);
- else
- BUG_ON(page_mapcount(page) != 1);
if (!pmd_young(*pmd))
entry = pte_mkold(entry);
if (pmd_numa(*pmd))
@@ -2202,6 +2246,30 @@ static void khugepaged_alloc_sleep(void)
static int khugepaged_node_load[MAX_NUMNODES];
+static bool khugepaged_scan_abort(int nid)
+{
+ int i;
+
+ /*
+ * If zone_reclaim_mode is disabled, then no extra effort is made to
+ * allocate memory locally.
+ */
+ if (!zone_reclaim_mode)
+ return false;
+
+ /* If there is a count for this node already, it must be acceptable */
+ if (khugepaged_node_load[nid])
+ return false;
+
+ for (i = 0; i < MAX_NUMNODES; i++) {
+ if (!khugepaged_node_load[i])
+ continue;
+ if (node_distance(nid, i) > RECLAIM_DISTANCE)
+ return true;
+ }
+ return false;
+}
+
#ifdef CONFIG_NUMA
static int khugepaged_find_target_node(void)
{
@@ -2358,6 +2426,7 @@ static void collapse_huge_page(struct mm_struct *mm,
spinlock_t *pmd_ptl, *pte_ptl;
int isolated;
unsigned long hstart, hend;
+ struct mem_cgroup *memcg;
unsigned long mmun_start; /* For mmu_notifiers */
unsigned long mmun_end; /* For mmu_notifiers */
@@ -2368,7 +2437,8 @@ static void collapse_huge_page(struct mm_struct *mm,
if (!new_page)
return;
- if (unlikely(mem_cgroup_charge_anon(new_page, mm, GFP_KERNEL)))
+ if (unlikely(mem_cgroup_try_charge(new_page, mm,
+ GFP_TRANSHUGE, &memcg)))
return;
/*
@@ -2392,8 +2462,6 @@ static void collapse_huge_page(struct mm_struct *mm,
pmd = mm_find_pmd(mm, address);
if (!pmd)
goto out;
- if (pmd_trans_huge(*pmd))
- goto out;
anon_vma_lock_write(vma->anon_vma);
@@ -2457,6 +2525,8 @@ static void collapse_huge_page(struct mm_struct *mm,
spin_lock(pmd_ptl);
BUG_ON(!pmd_none(*pmd));
page_add_new_anon_rmap(new_page, vma, address);
+ mem_cgroup_commit_charge(new_page, memcg, false);
+ lru_cache_add_active_or_unevictable(new_page, vma);
pgtable_trans_huge_deposit(mm, pmd, pgtable);
set_pmd_at(mm, address, pmd, _pmd);
update_mmu_cache_pmd(vma, address, pmd);
@@ -2470,7 +2540,7 @@ out_up_write:
return;
out:
- mem_cgroup_uncharge_page(new_page);
+ mem_cgroup_cancel_charge(new_page, memcg);
goto out_up_write;
}
@@ -2492,8 +2562,6 @@ static int khugepaged_scan_pmd(struct mm_struct *mm,
pmd = mm_find_pmd(mm, address);
if (!pmd)
goto out;
- if (pmd_trans_huge(*pmd))
- goto out;
memset(khugepaged_node_load, 0, sizeof(khugepaged_node_load));
pte = pte_offset_map_lock(mm, pmd, address, &ptl);
@@ -2518,6 +2586,8 @@ static int khugepaged_scan_pmd(struct mm_struct *mm,
* hit record.
*/
node = page_to_nid(page);
+ if (khugepaged_scan_abort(node))
+ goto out_unmap;
khugepaged_node_load[node]++;
VM_BUG_ON_PAGE(PageCompound(page), page);
if (!PageLRU(page) || PageLocked(page) || !PageAnon(page))
@@ -2846,12 +2916,22 @@ void split_huge_page_pmd_mm(struct mm_struct *mm, unsigned long address,
static void split_huge_page_address(struct mm_struct *mm,
unsigned long address)
{
+ pgd_t *pgd;
+ pud_t *pud;
pmd_t *pmd;
VM_BUG_ON(!(address & ~HPAGE_PMD_MASK));
- pmd = mm_find_pmd(mm, address);
- if (!pmd)
+ pgd = pgd_offset(mm, address);
+ if (!pgd_present(*pgd))
+ return;
+
+ pud = pud_offset(pgd, address);
+ if (!pud_present(*pud))
+ return;
+
+ pmd = pmd_offset(pud, address);
+ if (!pmd_present(*pmd))
return;
/*
* Caller holds the mmap_sem write mode, so a huge pmd cannot
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2025-06-20 10:07:28 +0000