#include <linux/mmu_notifier.h>
#include <linux/migrate.h>
#include <linux/perf_event.h>
+#include <linux/ksm.h>
#include <asm/uaccess.h>
#include <asm/pgtable.h>
#include <asm/cacheflush.h>
#include <asm/tlbflush.h>
-#ifndef pgprot_modify
-static inline pgprot_t pgprot_modify(pgprot_t oldprot, pgprot_t newprot)
+#include "internal.h"
+
+/*
+ * For a prot_numa update we only hold mmap_sem for read so there is a
+ * potential race with faulting where a pmd was temporarily none. This
+ * function checks for a transhuge pmd under the appropriate lock. It
+ * returns a pte if it was successfully locked or NULL if it raced with
+ * a transhuge insertion.
+ */
+static pte_t *lock_pte_protection(struct vm_area_struct *vma, pmd_t *pmd,
+ unsigned long addr, int prot_numa, spinlock_t **ptl)
{
- return newprot;
+ pte_t *pte;
+ spinlock_t *pmdl;
+
+ /* !prot_numa is protected by mmap_sem held for write */
+ if (!prot_numa)
+ return pte_offset_map_lock(vma->vm_mm, pmd, addr, ptl);
+
+ pmdl = pmd_lock(vma->vm_mm, pmd);
+ if (unlikely(pmd_trans_huge(*pmd) || pmd_none(*pmd))) {
+ spin_unlock(pmdl);
+ return NULL;
+ }
+
+ pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, ptl);
+ spin_unlock(pmdl);
+ return pte;
}
-#endif
static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
unsigned long addr, unsigned long end, pgprot_t newprot,
- int dirty_accountable, int prot_numa, bool *ret_all_same_node)
+ int dirty_accountable, int prot_numa)
{
struct mm_struct *mm = vma->vm_mm;
pte_t *pte, oldpte;
spinlock_t *ptl;
unsigned long pages = 0;
- bool all_same_node = true;
- int last_nid = -1;
- pte = pte_offset_map_lock(mm, pmd, addr, &ptl);
+ pte = lock_pte_protection(vma, pmd, addr, prot_numa, &ptl);
+ if (!pte)
+ return 0;
+
arch_enter_lazy_mmu_mode();
do {
oldpte = *pte;
if (pte_present(oldpte)) {
pte_t ptent;
- bool updated = false;
+ bool preserve_write = prot_numa && pte_write(oldpte);
- ptent = ptep_modify_prot_start(mm, addr, pte);
- if (!prot_numa) {
- ptent = pte_modify(ptent, newprot);
- updated = true;
- } else {
+ /*
+ * Avoid trapping faults against the zero or KSM
+ * pages. See similar comment in change_huge_pmd.
+ */
+ if (prot_numa) {
struct page *page;
page = vm_normal_page(vma, addr, oldpte);
- if (page) {
- int this_nid = page_to_nid(page);
- if (last_nid == -1)
- last_nid = this_nid;
- if (last_nid != this_nid)
- all_same_node = false;
-
- /* only check non-shared pages */
- if (!pte_numa(oldpte) &&
- page_mapcount(page) == 1) {
- ptent = pte_mknuma(ptent);
- updated = true;
- }
- }
+ if (!page || PageKsm(page))
+ continue;
+
+ /* Avoid TLB flush if possible */
+ if (pte_protnone(oldpte))
+ continue;
}
- /*
- * Avoid taking write faults for pages we know to be
- * dirty.
- */
- if (dirty_accountable && pte_dirty(ptent)) {
+ ptent = ptep_modify_prot_start(mm, addr, pte);
+ ptent = pte_modify(ptent, newprot);
+ if (preserve_write)
ptent = pte_mkwrite(ptent);
- updated = true;
- }
- if (updated)
- pages++;
+ /* Avoid taking write faults for known dirty pages */
+ if (dirty_accountable && pte_dirty(ptent) &&
+ (pte_soft_dirty(ptent) ||
+ !(vma->vm_flags & VM_SOFTDIRTY))) {
+ ptent = pte_mkwrite(ptent);
+ }
ptep_modify_prot_commit(mm, addr, pte, ptent);
- } else if (IS_ENABLED(CONFIG_MIGRATION) && !pte_file(oldpte)) {
+ pages++;
+ } else if (IS_ENABLED(CONFIG_MIGRATION)) {
swp_entry_t entry = pte_to_swp_entry(oldpte);
if (is_write_migration_entry(entry)) {
+ pte_t newpte;
/*
* A protection check is difficult so
* just be safe and disable write
*/
make_migration_entry_read(&entry);
- set_pte_at(mm, addr, pte,
- swp_entry_to_pte(entry));
+ newpte = swp_entry_to_pte(entry);
+ if (pte_swp_soft_dirty(oldpte))
+ newpte = pte_swp_mksoft_dirty(newpte);
+ set_pte_at(mm, addr, pte, newpte);
+
+ pages++;
}
- pages++;
}
} while (pte++, addr += PAGE_SIZE, addr != end);
arch_leave_lazy_mmu_mode();
pte_unmap_unlock(pte - 1, ptl);
- *ret_all_same_node = all_same_node;
return pages;
}
-#ifdef CONFIG_NUMA_BALANCING
-static inline void change_pmd_protnuma(struct mm_struct *mm, unsigned long addr,
- pmd_t *pmd)
-{
- spin_lock(&mm->page_table_lock);
- set_pmd_at(mm, addr & PMD_MASK, pmd, pmd_mknuma(*pmd));
- spin_unlock(&mm->page_table_lock);
-}
-#else
-static inline void change_pmd_protnuma(struct mm_struct *mm, unsigned long addr,
- pmd_t *pmd)
-{
- BUG();
-}
-#endif /* CONFIG_NUMA_BALANCING */
-
static inline unsigned long change_pmd_range(struct vm_area_struct *vma,
pud_t *pud, unsigned long addr, unsigned long end,
pgprot_t newprot, int dirty_accountable, int prot_numa)
{
pmd_t *pmd;
+ struct mm_struct *mm = vma->vm_mm;
unsigned long next;
unsigned long pages = 0;
unsigned long nr_huge_updates = 0;
- bool all_same_node;
+ unsigned long mni_start = 0;
pmd = pmd_offset(pud, addr);
do {
+ unsigned long this_pages;
+
next = pmd_addr_end(addr, end);
+ if (!pmd_trans_huge(*pmd) && pmd_none_or_clear_bad(pmd))
+ continue;
+
+ /* invoke the mmu notifier if the pmd is populated */
+ if (!mni_start) {
+ mni_start = addr;
+ mmu_notifier_invalidate_range_start(mm, mni_start, end);
+ }
+
if (pmd_trans_huge(*pmd)) {
if (next - addr != HPAGE_PMD_SIZE)
split_huge_page_pmd(vma, addr, pmd);
- else if (change_huge_pmd(vma, pmd, addr, newprot,
- prot_numa)) {
- pages += HPAGE_PMD_NR;
- nr_huge_updates++;
- continue;
+ else {
+ int nr_ptes = change_huge_pmd(vma, pmd, addr,
+ newprot, prot_numa);
+
+ if (nr_ptes) {
+ if (nr_ptes == HPAGE_PMD_NR) {
+ pages += HPAGE_PMD_NR;
+ nr_huge_updates++;
+ }
+
+ /* huge pmd was handled */
+ continue;
+ }
}
- /* fall through */
+ /* fall through, the trans huge pmd just split */
}
- if (pmd_none_or_clear_bad(pmd))
- continue;
- pages += change_pte_range(vma, pmd, addr, next, newprot,
- dirty_accountable, prot_numa, &all_same_node);
-
- /*
- * If we are changing protections for NUMA hinting faults then
- * set pmd_numa if the examined pages were all on the same
- * node. This allows a regular PMD to be handled as one fault
- * and effectively batches the taking of the PTL
- */
- if (prot_numa && all_same_node)
- change_pmd_protnuma(vma->vm_mm, addr, pmd);
+ this_pages = change_pte_range(vma, pmd, addr, next, newprot,
+ dirty_accountable, prot_numa);
+ pages += this_pages;
} while (pmd++, addr = next, addr != end);
+ if (mni_start)
+ mmu_notifier_invalidate_range_end(mm, mni_start, end);
+
if (nr_huge_updates)
count_vm_numa_events(NUMA_HUGE_PTE_UPDATES, nr_huge_updates);
-
return pages;
}
unsigned long end, pgprot_t newprot,
int dirty_accountable, int prot_numa)
{
- struct mm_struct *mm = vma->vm_mm;
unsigned long pages;
- mmu_notifier_invalidate_range_start(mm, start, end);
if (is_vm_hugetlb_page(vma))
pages = hugetlb_change_protection(vma, start, end, newprot);
else
pages = change_protection_range(vma, start, end, newprot, dirty_accountable, prot_numa);
- mmu_notifier_invalidate_range_end(mm, start, end);
return pages;
}
*/
pgoff = vma->vm_pgoff + ((start - vma->vm_start) >> PAGE_SHIFT);
*pprev = vma_merge(mm, *pprev, start, end, newflags,
- vma->anon_vma, vma->vm_file, pgoff, vma_policy(vma),
- vma_get_anon_name(vma));
+ vma->anon_vma, vma->vm_file, pgoff, vma_policy(vma),
+ vma->vm_userfaultfd_ctx, vma_get_anon_name(vma));
if (*pprev) {
vma = *pprev;
goto success;
* held in write mode.
*/
vma->vm_flags = newflags;
- vma->vm_page_prot = pgprot_modify(vma->vm_page_prot,
- vm_get_page_prot(newflags));
-
- if (vma_wants_writenotify(vma)) {
- vma->vm_page_prot = vm_get_page_prot(newflags & ~VM_SHARED);
- dirty_accountable = 1;
- }
+ dirty_accountable = vma_wants_writenotify(vma);
+ vma_set_page_prot(vma);
change_protection(vma, start, end, vma->vm_page_prot,
dirty_accountable, 0);
+ /*
+ * Private VM_LOCKED VMA becoming writable: trigger COW to avoid major
+ * fault on access.
+ */
+ if ((oldflags & (VM_WRITE | VM_SHARED | VM_LOCKED)) == VM_LOCKED &&
+ (newflags & VM_WRITE)) {
+ populate_vma_page_range(vma, start, end, NULL);
+ }
+
vm_stat_account(mm, oldflags, vma->vm_file, -nrpages);
vm_stat_account(mm, newflags, vma->vm_file, nrpages);
perf_event_mmap(vma);