summaryrefslogtreecommitdiffstats
path: root/mm/khugepaged.c
diff options
context:
space:
mode:
authorSong Liu <songliubraving@fb.com>2019-09-23 15:38:30 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2019-09-24 15:54:11 -0700
commit27e1f8273113adec0e98bf513e4091636b27cc2a (patch)
treecd1f81f4765ab885b2ed04d178691c4ed9c7845b /mm/khugepaged.c
parent5a52c9df62b422087d0c88fc79641028e4472a3b (diff)
downloadlinux-27e1f8273113adec0e98bf513e4091636b27cc2a.tar.bz2
khugepaged: enable collapse pmd for pte-mapped THP
khugepaged needs exclusive mmap_sem to access page table. When it fails to lock mmap_sem, the page will fault in as pte-mapped THP. As the page is already a THP, khugepaged will not handle this pmd again. This patch enables the khugepaged to retry collapse the page table. struct mm_slot (in khugepaged.c) is extended with an array, containing addresses of pte-mapped THPs. We use array here for simplicity. We can easily replace it with more advanced data structures when needed. In khugepaged_scan_mm_slot(), if the mm contains pte-mapped THP, we try to collapse the page table. Since collapse may happen at an later time, some pages may already fault in. collapse_pte_mapped_thp() is added to properly handle these pages. collapse_pte_mapped_thp() also double checks whether all ptes in this pmd are mapping to the same THP. This is necessary because some subpage of the THP may be replaced, for example by uprobe. In such cases, it is not possible to collapse the pmd. [kirill.shutemov@linux.intel.com: add comments for retract_page_tables()] Link: http://lkml.kernel.org/r/20190816145443.6ard3iilytc6jlgv@box Link: http://lkml.kernel.org/r/20190815164525.1848545-6-songliubraving@fb.com Signed-off-by: Song Liu <songliubraving@fb.com> Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Suggested-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Oleg Nesterov <oleg@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'mm/khugepaged.c')
-rw-r--r--mm/khugepaged.c192
1 files changed, 188 insertions, 4 deletions
diff --git a/mm/khugepaged.c b/mm/khugepaged.c
index e89430ec5267..0a1b4b484ac5 100644
--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -77,6 +77,8 @@ static __read_mostly DEFINE_HASHTABLE(mm_slots_hash, MM_SLOTS_HASH_BITS);
static struct kmem_cache *mm_slot_cache __read_mostly;
+#define MAX_PTE_MAPPED_THP 8
+
/**
* struct mm_slot - hash lookup from mm to mm_slot
* @hash: hash collision list
@@ -87,6 +89,10 @@ struct mm_slot {
struct hlist_node hash;
struct list_head mm_node;
struct mm_struct *mm;
+
+ /* pte-mapped THP in this mm */
+ int nr_pte_mapped_thp;
+ unsigned long pte_mapped_thp[MAX_PTE_MAPPED_THP];
};
/**
@@ -1254,6 +1260,159 @@ static void collect_mm_slot(struct mm_slot *mm_slot)
}
#if defined(CONFIG_SHMEM) && defined(CONFIG_TRANSPARENT_HUGE_PAGECACHE)
+/*
+ * Notify khugepaged that given addr of the mm is pte-mapped THP. Then
+ * khugepaged should try to collapse the page table.
+ */
+static int khugepaged_add_pte_mapped_thp(struct mm_struct *mm,
+ unsigned long addr)
+{
+ struct mm_slot *mm_slot;
+
+ VM_BUG_ON(addr & ~HPAGE_PMD_MASK);
+
+ spin_lock(&khugepaged_mm_lock);
+ mm_slot = get_mm_slot(mm);
+ if (likely(mm_slot && mm_slot->nr_pte_mapped_thp < MAX_PTE_MAPPED_THP))
+ mm_slot->pte_mapped_thp[mm_slot->nr_pte_mapped_thp++] = addr;
+ spin_unlock(&khugepaged_mm_lock);
+ return 0;
+}
+
+/**
+ * Try to collapse a pte-mapped THP for mm at address haddr.
+ *
+ * This function checks whether all the PTEs in the PMD are pointing to the
+ * right THP. If so, retract the page table so the THP can refault in with
+ * as pmd-mapped.
+ */
+void collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr)
+{
+ unsigned long haddr = addr & HPAGE_PMD_MASK;
+ struct vm_area_struct *vma = find_vma(mm, haddr);
+ struct page *hpage = NULL;
+ pte_t *start_pte, *pte;
+ pmd_t *pmd, _pmd;
+ spinlock_t *ptl;
+ int count = 0;
+ int i;
+
+ if (!vma || !vma->vm_file ||
+ vma->vm_start > haddr || vma->vm_end < haddr + HPAGE_PMD_SIZE)
+ return;
+
+ /*
+ * This vm_flags may not have VM_HUGEPAGE if the page was not
+ * collapsed by this mm. But we can still collapse if the page is
+ * the valid THP. Add extra VM_HUGEPAGE so hugepage_vma_check()
+ * will not fail the vma for missing VM_HUGEPAGE
+ */
+ if (!hugepage_vma_check(vma, vma->vm_flags | VM_HUGEPAGE))
+ return;
+
+ pmd = mm_find_pmd(mm, haddr);
+ if (!pmd)
+ return;
+
+ start_pte = pte_offset_map_lock(mm, pmd, haddr, &ptl);
+
+ /* 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;
+
+ /* empty pte, skip */
+ if (pte_none(*pte))
+ continue;
+
+ /* page swapped out, abort */
+ if (!pte_present(*pte))
+ goto abort;
+
+ page = vm_normal_page(vma, addr, *pte);
+
+ if (!page || !PageCompound(page))
+ goto abort;
+
+ if (!hpage) {
+ hpage = compound_head(page);
+ /*
+ * The mapping of the THP should not change.
+ *
+ * Note that uprobe, debugger, or MAP_PRIVATE may
+ * change the page table, but the new page will
+ * not pass PageCompound() check.
+ */
+ if (WARN_ON(hpage->mapping != vma->vm_file->f_mapping))
+ goto abort;
+ }
+
+ /*
+ * Confirm the page maps to the correct subpage.
+ *
+ * Note that uprobe, debugger, or MAP_PRIVATE may change
+ * the page table, but the new page will not pass
+ * PageCompound() check.
+ */
+ if (WARN_ON(hpage + i != page))
+ goto abort;
+ count++;
+ }
+
+ /* step 2: adjust rmap */
+ for (i = 0, addr = haddr, pte = start_pte;
+ i < HPAGE_PMD_NR; i++, addr += PAGE_SIZE, pte++) {
+ struct page *page;
+
+ if (pte_none(*pte))
+ continue;
+ page = vm_normal_page(vma, addr, *pte);
+ page_remove_rmap(page, false);
+ }
+
+ pte_unmap_unlock(start_pte, ptl);
+
+ /* step 3: set proper refcount and mm_counters. */
+ if (hpage) {
+ page_ref_sub(hpage, count);
+ add_mm_counter(vma->vm_mm, mm_counter_file(hpage), -count);
+ }
+
+ /* step 4: collapse pmd */
+ ptl = pmd_lock(vma->vm_mm, pmd);
+ _pmd = pmdp_collapse_flush(vma, addr, pmd);
+ spin_unlock(ptl);
+ mm_dec_nr_ptes(mm);
+ pte_free(mm, pmd_pgtable(_pmd));
+ return;
+
+abort:
+ pte_unmap_unlock(start_pte, ptl);
+}
+
+static int khugepaged_collapse_pte_mapped_thps(struct mm_slot *mm_slot)
+{
+ struct mm_struct *mm = mm_slot->mm;
+ int i;
+
+ if (likely(mm_slot->nr_pte_mapped_thp == 0))
+ return 0;
+
+ if (!down_write_trylock(&mm->mmap_sem))
+ return -EBUSY;
+
+ if (unlikely(khugepaged_test_exit(mm)))
+ goto out;
+
+ for (i = 0; i < mm_slot->nr_pte_mapped_thp; i++)
+ collapse_pte_mapped_thp(mm, mm_slot->pte_mapped_thp[i]);
+
+out:
+ mm_slot->nr_pte_mapped_thp = 0;
+ up_write(&mm->mmap_sem);
+ return 0;
+}
+
static void retract_page_tables(struct address_space *mapping, pgoff_t pgoff)
{
struct vm_area_struct *vma;
@@ -1262,7 +1421,22 @@ static void retract_page_tables(struct address_space *mapping, pgoff_t pgoff)
i_mmap_lock_write(mapping);
vma_interval_tree_foreach(vma, &mapping->i_mmap, pgoff, pgoff) {
- /* probably overkill */
+ /*
+ * Check vma->anon_vma to exclude MAP_PRIVATE mappings that
+ * got written to. These VMAs are likely not worth investing
+ * down_write(mmap_sem) as PMD-mapping is likely to be split
+ * later.
+ *
+ * Not that vma->anon_vma check is racy: it can be set up after
+ * the check but before we took mmap_sem by the fault path.
+ * But page lock would prevent establishing any new ptes of the
+ * page, so we are safe.
+ *
+ * An alternative would be drop the check, but check that page
+ * table is clear before calling pmdp_collapse_flush() under
+ * ptl. It has higher chance to recover THP for the VMA, but
+ * has higher cost too.
+ */
if (vma->anon_vma)
continue;
addr = vma->vm_start + ((pgoff - vma->vm_pgoff) << PAGE_SHIFT);
@@ -1275,9 +1449,10 @@ static void retract_page_tables(struct address_space *mapping, pgoff_t pgoff)
continue;
/*
* We need exclusive mmap_sem to retract page table.
- * If trylock fails we would end up with pte-mapped THP after
- * re-fault. Not ideal, but it's more important to not disturb
- * the system too much.
+ *
+ * We use trylock due to lock inversion: we need to acquire
+ * mmap_sem while holding page lock. Fault path does it in
+ * reverse order. Trylock is a way to avoid deadlock.
*/
if (down_write_trylock(&vma->vm_mm->mmap_sem)) {
spinlock_t *ptl = pmd_lock(vma->vm_mm, pmd);
@@ -1287,6 +1462,9 @@ static void retract_page_tables(struct address_space *mapping, pgoff_t pgoff)
up_write(&vma->vm_mm->mmap_sem);
mm_dec_nr_ptes(vma->vm_mm);
pte_free(vma->vm_mm, pmd_pgtable(_pmd));
+ } else {
+ /* Try again later */
+ khugepaged_add_pte_mapped_thp(vma->vm_mm, addr);
}
}
i_mmap_unlock_write(mapping);
@@ -1709,6 +1887,11 @@ static void khugepaged_scan_file(struct mm_struct *mm,
{
BUILD_BUG();
}
+
+static int khugepaged_collapse_pte_mapped_thps(struct mm_slot *mm_slot)
+{
+ return 0;
+}
#endif
static unsigned int khugepaged_scan_mm_slot(unsigned int pages,
@@ -1733,6 +1916,7 @@ static unsigned int khugepaged_scan_mm_slot(unsigned int pages,
khugepaged_scan.mm_slot = mm_slot;
}
spin_unlock(&khugepaged_mm_lock);
+ khugepaged_collapse_pte_mapped_thps(mm_slot);
mm = mm_slot->mm;
/*