summaryrefslogtreecommitdiff
path: root/mm/memory.c
diff options
context:
space:
mode:
Diffstat (limited to 'mm/memory.c')
-rw-r--r--mm/memory.c32
1 files changed, 24 insertions, 8 deletions
diff --git a/mm/memory.c b/mm/memory.c
index 2366578015ad..bdf77a3ec47b 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -4181,17 +4181,14 @@ fallback:
return __alloc_swap_folio(vmf);
}
#else /* !CONFIG_TRANSPARENT_HUGEPAGE */
-static inline bool can_swapin_thp(struct vm_fault *vmf, pte_t *ptep, int nr_pages)
-{
- return false;
-}
-
static struct folio *alloc_swap_folio(struct vm_fault *vmf)
{
return __alloc_swap_folio(vmf);
}
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
+static DECLARE_WAIT_QUEUE_HEAD(swapcache_wq);
+
/*
* We enter with non-exclusive mmap_lock (to exclude vma changes,
* but allow concurrent faults), and pte mapped but not yet locked.
@@ -4204,6 +4201,7 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
{
struct vm_area_struct *vma = vmf->vma;
struct folio *swapcache, *folio = NULL;
+ DECLARE_WAITQUEUE(wait, current);
struct page *page;
struct swap_info_struct *si = NULL;
rmap_t rmap_flags = RMAP_NONE;
@@ -4302,7 +4300,9 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
* Relax a bit to prevent rapid
* repeated page faults.
*/
+ add_wait_queue(&swapcache_wq, &wait);
schedule_timeout_uninterruptible(1);
+ remove_wait_queue(&swapcache_wq, &wait);
goto out_page;
}
need_clear_cache = true;
@@ -4609,8 +4609,11 @@ unlock:
pte_unmap_unlock(vmf->pte, vmf->ptl);
out:
/* Clear the swap cache pin for direct swapin after PTL unlock */
- if (need_clear_cache)
+ if (need_clear_cache) {
swapcache_clear(si, entry, nr_pages);
+ if (waitqueue_active(&swapcache_wq))
+ wake_up(&swapcache_wq);
+ }
if (si)
put_swap_device(si);
return ret;
@@ -4625,8 +4628,11 @@ out_release:
folio_unlock(swapcache);
folio_put(swapcache);
}
- if (need_clear_cache)
+ if (need_clear_cache) {
swapcache_clear(si, entry, nr_pages);
+ if (waitqueue_active(&swapcache_wq))
+ wake_up(&swapcache_wq);
+ }
if (si)
put_swap_device(si);
return ret;
@@ -4925,6 +4931,15 @@ vm_fault_t do_set_pmd(struct vm_fault *vmf, struct page *page)
pmd_t entry;
vm_fault_t ret = VM_FAULT_FALLBACK;
+ /*
+ * It is too late to allocate a small folio, we already have a large
+ * folio in the pagecache: especially s390 KVM cannot tolerate any
+ * PMD mappings, but PTE-mapped THP are fine. So let's simply refuse any
+ * PMD mappings if THPs are disabled.
+ */
+ if (thp_disabled_by_hw() || vma_thp_disabled(vma, vma->vm_flags))
+ return ret;
+
if (!thp_vma_suitable_order(vma, haddr, PMD_ORDER))
return ret;
@@ -6346,7 +6361,8 @@ static inline void pfnmap_args_setup(struct follow_pfnmap_args *args,
static inline void pfnmap_lockdep_assert(struct vm_area_struct *vma)
{
#ifdef CONFIG_LOCKDEP
- struct address_space *mapping = vma->vm_file->f_mapping;
+ struct file *file = vma->vm_file;
+ struct address_space *mapping = file ? file->f_mapping : NULL;
if (mapping)
lockdep_assert(lockdep_is_held(&vma->vm_file->f_mapping->i_mmap_rwsem) ||