#include <linux/freezer.h>
#include <linux/pfn_t.h>
#include <linux/mman.h>
+#include <linux/memremap.h>
#include <linux/pagemap.h>
#include <linux/debugfs.h>
#include <linux/migrate.h>
return VM_FAULT_NOPAGE;
}
+static void touch_pmd(struct vm_area_struct *vma, unsigned long addr,
+ pmd_t *pmd)
+{
+ pmd_t _pmd;
+
+ /*
+ * We should set the dirty bit only for FOLL_WRITE but for now
+ * the dirty bit in the pmd is meaningless. And if the dirty
+ * bit will become meaningful and we'll only set it with
+ * FOLL_WRITE, an atomic set_bit will be required on the pmd to
+ * set the young bit, instead of the current set_pmd_at.
+ */
+ _pmd = pmd_mkyoung(pmd_mkdirty(*pmd));
+ if (pmdp_set_access_flags(vma, addr & HPAGE_PMD_MASK,
+ pmd, _pmd, 1))
+ update_mmu_cache_pmd(vma, addr, pmd);
+}
+
+struct page *follow_devmap_pmd(struct vm_area_struct *vma, unsigned long addr,
+ pmd_t *pmd, int flags)
+{
+ 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));
+
+ if (flags & FOLL_WRITE && !pmd_write(*pmd))
+ return NULL;
+
+ if (pmd_present(*pmd) && pmd_devmap(*pmd))
+ /* pass */;
+ else
+ return NULL;
+
+ if (flags & FOLL_TOUCH)
+ touch_pmd(vma, addr, pmd);
+
+ /*
+ * device mapped pages can only be returned if the
+ * caller will manage the page reference count.
+ */
+ if (!(flags & FOLL_GET))
+ return ERR_PTR(-EEXIST);
+
+ pfn += (addr & ~PMD_MASK) >> PAGE_SHIFT;
+ pgmap = get_dev_pagemap(pfn, NULL);
+ if (!pgmap)
+ return ERR_PTR(-EFAULT);
+ page = pfn_to_page(pfn);
+ get_page(page);
+ put_dev_pagemap(pgmap);
+
+ return page;
+}
+
int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm,
pmd_t *dst_pmd, pmd_t *src_pmd, unsigned long addr,
struct vm_area_struct *vma)
page = pmd_page(*pmd);
VM_BUG_ON_PAGE(!PageHead(page), page);
- if (flags & FOLL_TOUCH) {
- pmd_t _pmd;
- /*
- * We should set the dirty bit only for FOLL_WRITE but
- * for now the dirty bit in the pmd is meaningless.
- * And if the dirty bit will become meaningful and
- * we'll only set it with FOLL_WRITE, an atomic
- * set_bit will be required on the pmd to set the
- * young bit, instead of the current set_pmd_at.
- */
- _pmd = pmd_mkyoung(pmd_mkdirty(*pmd));
- if (pmdp_set_access_flags(vma, addr & HPAGE_PMD_MASK,
- pmd, _pmd, 1))
- update_mmu_cache_pmd(vma, addr, pmd);
- }
+ if (flags & FOLL_TOUCH)
+ touch_pmd(vma, addr, pmd);
if ((flags & FOLL_MLOCK) && (vma->vm_flags & VM_LOCKED)) {
/*
* We don't mlock() pte-mapped THPs. This way we can avoid
struct mm_struct *mm = tlb->mm;
int ret = 0;
- if (!pmd_trans_huge_lock(pmd, vma, &ptl))
- goto out;
+ ptl = pmd_trans_huge_lock(pmd, vma);
+ if (!ptl)
+ goto out_unlocked;
orig_pmd = *pmd;
if (is_huge_zero_pmd(orig_pmd)) {
pmd_t orig_pmd;
spinlock_t *ptl;
- if (!__pmd_trans_huge_lock(pmd, vma, &ptl))
+ ptl = __pmd_trans_huge_lock(pmd, vma);
+ if (!ptl)
return 0;
/*
* For architectures like ppc64 we look at deposited pgtable
* We don't have to worry about the ordering of src and dst
* ptlocks because exclusive mmap_sem prevents deadlock.
*/
- if (__pmd_trans_huge_lock(old_pmd, vma, &old_ptl)) {
+ old_ptl = __pmd_trans_huge_lock(old_pmd, vma);
+ if (old_ptl) {
new_ptl = pmd_lockptr(mm, new_pmd);
if (new_ptl != old_ptl)
spin_lock_nested(new_ptl, SINGLE_DEPTH_NESTING);
spinlock_t *ptl;
int ret = 0;
- if (__pmd_trans_huge_lock(pmd, vma, &ptl)) {
+ ptl = __pmd_trans_huge_lock(pmd, vma);
+ if (ptl) {
pmd_t entry;
bool preserve_write = prot_numa && pmd_write(*pmd);
ret = 1;
* Note that if it returns true, this routine returns without unlocking page
* table lock. So callers must unlock it.
*/
-bool __pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma,
- spinlock_t **ptl)
+spinlock_t *__pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma)
{
- *ptl = pmd_lock(vma->vm_mm, pmd);
+ spinlock_t *ptl;
+ ptl = pmd_lock(vma->vm_mm, pmd);
if (likely(pmd_trans_huge(*pmd) || pmd_devmap(*pmd)))
- return true;
- spin_unlock(*ptl);
- return false;
+ return ptl;
+ spin_unlock(ptl);
+ return NULL;
}
#define VM_NO_THP (VM_SPECIAL | VM_HUGETLB | VM_SHARED | VM_MAYSHARE)
if (likely(writable)) {
if (likely(referenced)) {
result = SCAN_SUCCEED;
- trace_mm_collapse_huge_page_isolate(page_to_pfn(page), none_or_zero,
+ trace_mm_collapse_huge_page_isolate(page, none_or_zero,
referenced, writable, result);
return 1;
}
out:
release_pte_pages(pte, _pte);
- trace_mm_collapse_huge_page_isolate(page_to_pfn(page), none_or_zero,
+ trace_mm_collapse_huge_page_isolate(page, none_or_zero,
referenced, writable, result);
return 0;
}
pgtable_t pgtable;
struct page *new_page;
spinlock_t *pmd_ptl, *pte_ptl;
- int isolated, result = 0;
+ int isolated = 0, result = 0;
unsigned long hstart, hend;
struct mem_cgroup *memcg;
unsigned long mmun_start; /* For mmu_notifiers */
collapse_huge_page(mm, address, hpage, vma, node);
}
out:
- trace_mm_khugepaged_scan_pmd(mm, page_to_pfn(page), writable, referenced,
+ trace_mm_khugepaged_scan_pmd(mm, page, writable, referenced,
none_or_zero, result);
return ret;
}
struct anon_vma *anon_vma;
int count, mapcount, ret;
bool mlocked;
+ unsigned long flags;
VM_BUG_ON_PAGE(is_huge_zero_page(page), page);
VM_BUG_ON_PAGE(!PageAnon(page), page);
lru_add_drain();
/* Prevent deferred_split_scan() touching ->_count */
- spin_lock(&split_queue_lock);
+ spin_lock_irqsave(&split_queue_lock, flags);
count = page_count(head);
mapcount = total_mapcount(head);
if (!mapcount && count == 1) {
split_queue_len--;
list_del(page_deferred_list(head));
}
- spin_unlock(&split_queue_lock);
+ spin_unlock_irqrestore(&split_queue_lock, flags);
__split_huge_page(page, list);
ret = 0;
} else if (IS_ENABLED(CONFIG_DEBUG_VM) && mapcount) {
- spin_unlock(&split_queue_lock);
+ spin_unlock_irqrestore(&split_queue_lock, flags);
pr_alert("total_mapcount: %u, page_count(): %u\n",
mapcount, count);
if (PageTail(page))
dump_page(page, "total_mapcount(head) > 0");
BUG();
} else {
- spin_unlock(&split_queue_lock);
+ spin_unlock_irqrestore(&split_queue_lock, flags);
unfreeze_page(anon_vma, head);
ret = -EBUSY;
}
projects / deliverable / linux.git / blobdiff