static unsigned int khugepaged_max_ptes_shared __read_mostly;
#define MM_SLOTS_HASH_BITS 10
-static __read_mostly DEFINE_HASHTABLE(mm_slots_hash, MM_SLOTS_HASH_BITS);
+static DEFINE_READ_MOSTLY_HASHTABLE(mm_slots_hash, MM_SLOTS_HASH_BITS);
static struct kmem_cache *mm_slot_cache __read_mostly;
struct mm_slot *slot;
int wakeup;
+ /* __khugepaged_exit() must not run from under us */
+ VM_BUG_ON_MM(hpage_collapse_test_exit(mm), mm);
+ if (unlikely(test_and_set_bit(MMF_VM_HUGEPAGE, &mm->flags)))
+ return;
+
mm_slot = mm_slot_alloc(mm_slot_cache);
if (!mm_slot)
return;
slot = &mm_slot->slot;
- /* __khugepaged_exit() must not run from under us */
- VM_BUG_ON_MM(hpage_collapse_test_exit(mm), mm);
- if (unlikely(test_and_set_bit(MMF_VM_HUGEPAGE, &mm->flags))) {
- mm_slot_free(mm_slot_cache, mm_slot);
- return;
- }
-
spin_lock(&khugepaged_mm_lock);
mm_slot_insert(mm_slots_hash, mm, slot);
/*
struct folio *folio, *tmp;
while (--_pte >= pte) {
- pte_t pteval = *_pte;
+ pte_t pteval = ptep_get(_pte);
unsigned long pfn;
if (pte_none(pteval))
for (_pte = pte; _pte < pte + HPAGE_PMD_NR;
_pte++, address += PAGE_SIZE) {
- pte_t pteval = *_pte;
+ pte_t pteval = ptep_get(_pte);
if (pte_none(pteval) || (pte_present(pteval) &&
is_zero_pfn(pte_pfn(pteval)))) {
++none_or_zero;
for (_pte = pte; _pte < pte + HPAGE_PMD_NR;
_pte++, address += PAGE_SIZE) {
- pteval = *_pte;
+ pteval = ptep_get(_pte);
if (pte_none(pteval) || is_zero_pfn(pte_pfn(pteval))) {
add_mm_counter(vma->vm_mm, MM_ANONPAGES, 1);
if (is_zero_pfn(pte_pfn(pteval))) {
*/
for (_pte = pte, _address = address; _pte < pte + HPAGE_PMD_NR;
_pte++, page++, _address += PAGE_SIZE) {
- pteval = *_pte;
+ pteval = ptep_get(_pte);
if (pte_none(pteval) || is_zero_pfn(pte_pfn(pteval))) {
clear_user_highpage(page, _address);
continue;
return SCAN_SUCCEED;
}
-/*
- * See pmd_trans_unstable() for how the result may change out from
- * underneath us, even if we hold mmap_lock in read.
- */
static int find_pmd_or_thp_or_none(struct mm_struct *mm,
unsigned long address,
pmd_t **pmd)
return SCAN_PMD_NULL;
pmde = pmdp_get_lockless(*pmd);
-
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
- /* See comments in pmd_none_or_trans_huge_or_clear_bad() */
- barrier();
-#endif
if (pmd_none(pmde))
return SCAN_PMD_NONE;
if (!pmd_present(pmde))
* Only done if hpage_collapse_scan_pmd believes it is worthwhile.
*
* Called and returns without pte mapped or spinlocks held.
- * Note that if false is returned, mmap_lock will be released.
+ * Returns result: if not SCAN_SUCCEED, mmap_lock has been released.
*/
-
static int __collapse_huge_page_swapin(struct mm_struct *mm,
struct vm_area_struct *vma,
unsigned long haddr, pmd_t *pmd,
int swapped_in = 0;
vm_fault_t ret = 0;
unsigned long address, end = haddr + (HPAGE_PMD_NR * PAGE_SIZE);
+ int result;
+ pte_t *pte = NULL;
+ spinlock_t *ptl;
for (address = haddr; address < end; address += PAGE_SIZE) {
struct vm_fault vmf = {
.vma = vma,
.address = address,
- .pgoff = linear_page_index(vma, haddr),
+ .pgoff = linear_page_index(vma, address),
.flags = FAULT_FLAG_ALLOW_RETRY,
.pmd = pmd,
};
- vmf.pte = pte_offset_map(pmd, address);
- vmf.orig_pte = *vmf.pte;
- if (!is_swap_pte(vmf.orig_pte)) {
- pte_unmap(vmf.pte);
- continue;
+ if (!pte++) {
+ pte = pte_offset_map_nolock(mm, pmd, address, &ptl);
+ if (!pte) {
+ mmap_read_unlock(mm);
+ result = SCAN_PMD_NULL;
+ goto out;
+ }
}
+
+ vmf.orig_pte = ptep_get_lockless(pte);
+ if (!is_swap_pte(vmf.orig_pte))
+ continue;
+
+ vmf.pte = pte;
+ vmf.ptl = ptl;
ret = do_swap_page(&vmf);
+ /* Which unmaps pte (after perhaps re-checking the entry) */
+ pte = NULL;
/*
* do_swap_page returns VM_FAULT_RETRY with released mmap_lock.
* resulting in later failure.
*/
if (ret & VM_FAULT_RETRY) {
- trace_mm_collapse_huge_page_swapin(mm, swapped_in, referenced, 0);
/* Likely, but not guaranteed, that page lock failed */
- return SCAN_PAGE_LOCK;
+ result = SCAN_PAGE_LOCK;
+ goto out;
}
if (ret & VM_FAULT_ERROR) {
mmap_read_unlock(mm);
- trace_mm_collapse_huge_page_swapin(mm, swapped_in, referenced, 0);
- return SCAN_FAIL;
+ result = SCAN_FAIL;
+ goto out;
}
swapped_in++;
}
- /* Drain LRU add pagevec to remove extra pin on the swapped in pages */
+ if (pte)
+ pte_unmap(pte);
+
+ /* Drain LRU cache to remove extra pin on the swapped in pages */
if (swapped_in)
lru_add_drain();
- trace_mm_collapse_huge_page_swapin(mm, swapped_in, referenced, 1);
- return SCAN_SUCCEED;
+ result = SCAN_SUCCEED;
+out:
+ trace_mm_collapse_huge_page_swapin(mm, swapped_in, referenced, result);
+ return result;
}
static int alloc_charge_hpage(struct page **hpage, struct mm_struct *mm,
address + HPAGE_PMD_SIZE);
mmu_notifier_invalidate_range_start(&range);
- pte = pte_offset_map(pmd, address);
- pte_ptl = pte_lockptr(mm, pmd);
-
pmd_ptl = pmd_lock(mm, pmd); /* probably unnecessary */
/*
* This removes any huge TLB entry from the CPU so we won't allow
mmu_notifier_invalidate_range_end(&range);
tlb_remove_table_sync_one();
- spin_lock(pte_ptl);
- result = __collapse_huge_page_isolate(vma, address, pte, cc,
- &compound_pagelist);
- spin_unlock(pte_ptl);
+ pte = pte_offset_map_lock(mm, &_pmd, address, &pte_ptl);
+ if (pte) {
+ result = __collapse_huge_page_isolate(vma, address, pte, cc,
+ &compound_pagelist);
+ spin_unlock(pte_ptl);
+ } else {
+ result = SCAN_PMD_NULL;
+ }
if (unlikely(result != SCAN_SUCCEED)) {
- pte_unmap(pte);
+ if (pte)
+ pte_unmap(pte);
spin_lock(pmd_ptl);
BUG_ON(!pmd_none(*pmd));
/*
memset(cc->node_load, 0, sizeof(cc->node_load));
nodes_clear(cc->alloc_nmask);
pte = pte_offset_map_lock(mm, pmd, address, &ptl);
+ if (!pte) {
+ result = SCAN_PMD_NULL;
+ goto out;
+ }
+
for (_address = address, _pte = pte; _pte < pte + HPAGE_PMD_NR;
_pte++, _address += PAGE_SIZE) {
- pte_t pteval = *_pte;
+ pte_t pteval = ptep_get(_pte);
if (is_swap_pte(pteval)) {
++unmapped;
if (!cc->is_khugepaged ||
* lockless_pages_from_mm() and the hardware page walker can access page
* tables while all the high-level locks are held in write mode.
*/
- start_pte = pte_offset_map_lock(mm, pmd, haddr, &ptl);
result = SCAN_FAIL;
+ start_pte = pte_offset_map_lock(mm, pmd, haddr, &ptl);
+ if (!start_pte)
+ goto drop_immap;
/* step 1: check all mapped PTEs are to the right huge page */
for (i = 0, addr = haddr, pte = start_pte;
i < HPAGE_PMD_NR; i++, addr += PAGE_SIZE, pte++) {
struct page *page;
+ pte_t ptent = ptep_get(pte);
/* empty pte, skip */
- if (pte_none(*pte))
+ if (pte_none(ptent))
continue;
/* page swapped out, abort */
- if (!pte_present(*pte)) {
+ if (!pte_present(ptent)) {
result = SCAN_PTE_NON_PRESENT;
goto abort;
}
- page = vm_normal_page(vma, addr, *pte);
+ page = vm_normal_page(vma, addr, ptent);
if (WARN_ON_ONCE(page && is_zone_device_page(page)))
page = NULL;
/*
for (i = 0, addr = haddr, pte = start_pte;
i < HPAGE_PMD_NR; i++, addr += PAGE_SIZE, pte++) {
struct page *page;
+ pte_t ptent = ptep_get(pte);
- if (pte_none(*pte))
+ if (pte_none(ptent))
continue;
- page = vm_normal_page(vma, addr, *pte);
+ page = vm_normal_page(vma, addr, ptent);
if (WARN_ON_ONCE(page && is_zone_device_page(page)))
goto abort;
page_remove_rmap(page, vma, false);
abort:
pte_unmap_unlock(start_pte, ptl);
+drop_immap:
i_mmap_unlock_write(vma->vm_file->f_mapping);
goto drop_hpage;
}
}
} while (1);
- xas_set(&xas, start);
for (index = start; index < end; index++) {
- page = xas_next(&xas);
+ xas_set(&xas, index);
+ page = xas_load(&xas);
VM_BUG_ON(index != xas.xa_index);
if (is_shmem) {
result = SCAN_TRUNCATED;
goto xa_locked;
}
- xas_set(&xas, index + 1);
}
if (!shmem_charge(mapping->host, 1)) {
result = SCAN_FAIL;
result = SCAN_FAIL;
goto xa_unlocked;
}
- /* drain pagevecs to help isolate_lru_page() */
+ /* drain lru cache to help isolate_lru_page() */
lru_add_drain();
page = folio_file_page(folio, index);
} else if (trylock_page(page)) {
page_cache_sync_readahead(mapping, &file->f_ra,
file, index,
end - index);
- /* drain pagevecs to help isolate_lru_page() */
+ /* drain lru cache to help isolate_lru_page() */
lru_add_drain();
page = find_lock_page(mapping, index);
if (unlikely(page == NULL)) {
xas_lock_irq(&xas);
- VM_BUG_ON_PAGE(page != xas_load(&xas), page);
+ VM_BUG_ON_PAGE(page != xa_load(xas.xa, index), page);
/*
* We control three references to the page:
projects / linux-2.6-microblaze.git / blobdiff