1 files changed, 75 insertions, 24 deletions

diff --git a/mm/memory.c b/mm/memory.c
index 2366578015ad..75c2dfd04f72 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1,4 +1,3 @@
-
 // SPDX-License-Identifier: GPL-2.0-only
 /*
  *  linux/mm/memory.c
@@ -44,7 +43,6 @@
 #include <linux/mm.h>
 #include <linux/mm_inline.h>
 #include <linux/sched/mm.h>
-#include <linux/sched/coredump.h>
 #include <linux/sched/numa_balancing.h>
 #include <linux/sched/task.h>
 #include <linux/hugetlb.h>
@@ -1061,8 +1059,7 @@ static inline struct folio *folio_prealloc(struct mm_struct *src_mm,
 	if (need_zero)
 		new_folio = vma_alloc_zeroed_movable_folio(vma, addr);
 	else
-		new_folio = vma_alloc_folio(GFP_HIGHUSER_MOVABLE, 0, vma,
-					    addr, false);
+		new_folio = vma_alloc_folio(GFP_HIGHUSER_MOVABLE, 0, vma, addr);
 
 	if (!new_folio)
 		return NULL;
@@ -1085,6 +1082,7 @@ copy_pte_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma,
 	struct mm_struct *src_mm = src_vma->vm_mm;
 	pte_t *orig_src_pte, *orig_dst_pte;
 	pte_t *src_pte, *dst_pte;
+	pmd_t dummy_pmdval;
 	pte_t ptent;
 	spinlock_t *src_ptl, *dst_ptl;
 	int progress, max_nr, ret = 0;
@@ -1110,7 +1108,15 @@ again:
 		ret = -ENOMEM;
 		goto out;
 	}
-	src_pte = pte_offset_map_nolock(src_mm, src_pmd, addr, &src_ptl);
+
+	/*
+	 * We already hold the exclusive mmap_lock, the copy_pte_range() and
+	 * retract_page_tables() are using vma->anon_vma to be exclusive, so
+	 * the PTE page is stable, and there is no need to get pmdval and do
+	 * pmd_same() check.
+	 */
+	src_pte = pte_offset_map_rw_nolock(src_mm, src_pmd, addr, &dummy_pmdval,
+					   &src_ptl);
 	if (!src_pte) {
 		pte_unmap_unlock(dst_pte, dst_ptl);
 		/* ret == 0 */
@@ -1449,7 +1455,7 @@ static inline bool should_zap_folio(struct zap_details *details,
 	return !folio_test_anon(folio);
 }
 
-static inline bool zap_drop_file_uffd_wp(struct zap_details *details)
+static inline bool zap_drop_markers(struct zap_details *details)
 {
 	if (!details)
 		return false;
@@ -1470,7 +1476,7 @@ zap_install_uffd_wp_if_needed(struct vm_area_struct *vma,
 	if (vma_is_anonymous(vma))
 		return;
 
-	if (zap_drop_file_uffd_wp(details))
+	if (zap_drop_markers(details))
 		return;
 
 	for (;;) {
@@ -1665,7 +1671,15 @@ static unsigned long zap_pte_range(struct mmu_gather *tlb,
 			 * drop the marker if explicitly requested.
 			 */
 			if (!vma_is_anonymous(vma) &&
-			    !zap_drop_file_uffd_wp(details))
+			    !zap_drop_markers(details))
+				continue;
+		} else if (is_guard_swp_entry(entry)) {
+			/*
+			 * Ordinary zapping should not remove guard PTE
+			 * markers. Only do so if we should remove PTE markers
+			 * in general.
+			 */
+			if (!zap_drop_markers(details))
 				continue;
 		} else if (is_hwpoison_entry(entry) ||
 			   is_poisoned_swp_entry(entry)) {
@@ -3997,6 +4011,10 @@ static vm_fault_t handle_pte_marker(struct vm_fault *vmf)
 	if (marker & PTE_MARKER_POISONED)
 		return VM_FAULT_HWPOISON;
 
+	/* Hitting a guard page is always a fatal condition. */
+	if (marker & PTE_MARKER_GUARD)
+		return VM_FAULT_SIGSEGV;
+
 	if (pte_marker_entry_uffd_wp(entry))
 		return pte_marker_handle_uffd_wp(vmf);
 
@@ -4010,8 +4028,7 @@ static struct folio *__alloc_swap_folio(struct vm_fault *vmf)
 	struct folio *folio;
 	swp_entry_t entry;
 
-	folio = vma_alloc_folio(GFP_HIGHUSER_MOVABLE, 0, vma,
-				vmf->address, false);
+	folio = vma_alloc_folio(GFP_HIGHUSER_MOVABLE, 0, vma, vmf->address);
 	if (!folio)
 		return NULL;
 
@@ -4167,7 +4184,7 @@ static struct folio *alloc_swap_folio(struct vm_fault *vmf)
 	gfp = vma_thp_gfp_mask(vma);
 	while (orders) {
 		addr = ALIGN_DOWN(vmf->address, PAGE_SIZE << order);
-		folio = vma_alloc_folio(gfp, order, vma, addr, true);
+		folio = vma_alloc_folio(gfp, order, vma, addr);
 		if (folio) {
 			if (!mem_cgroup_swapin_charge_folio(folio, vma->vm_mm,
 							    gfp, entry))
@@ -4181,17 +4198,14 @@ 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 +4218,7 @@ 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 +4317,9 @@ 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 +4626,11 @@ 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 +4645,11 @@ 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;
@@ -4700,7 +4723,7 @@ static struct folio *alloc_anon_folio(struct vm_fault *vmf)
 	gfp = vma_thp_gfp_mask(vma);
 	while (orders) {
 		addr = ALIGN_DOWN(vmf->address, PAGE_SIZE << order);
-		folio = vma_alloc_folio(gfp, order, vma, addr, true);
+		folio = vma_alloc_folio(gfp, order, vma, addr);
 		if (folio) {
 			if (mem_cgroup_charge(folio, vma->vm_mm, gfp)) {
 				count_mthp_stat(order, MTHP_STAT_ANON_FAULT_FALLBACK_CHARGE);
@@ -4708,7 +4731,15 @@ static struct folio *alloc_anon_folio(struct vm_fault *vmf)
 				goto next;
 			}
 			folio_throttle_swaprate(folio, gfp);
-			folio_zero_user(folio, vmf->address);
+			/*
+			 * When a folio is not zeroed during allocation
+			 * (__GFP_ZERO not used), folio_zero_user() is used
+			 * to make sure that the page corresponding to the
+			 * faulting address will be hot in the cache after
+			 * zeroing.
+			 */
+			if (!alloc_zeroed())
+				folio_zero_user(folio, vmf->address);
 			return folio;
 		}
 next:
@@ -4925,6 +4956,15 @@ 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;
 
@@ -5728,14 +5768,24 @@ static vm_fault_t handle_pte_fault(struct vm_fault *vmf)
 		vmf->pte = NULL;
 		vmf->flags &= ~FAULT_FLAG_ORIG_PTE_VALID;
 	} else {
+		pmd_t dummy_pmdval;
+
 		/*
 		 * A regular pmd is established and it can't morph into a huge
 		 * pmd by anon khugepaged, since that takes mmap_lock in write
 		 * mode; but shmem or file collapse to THP could still morph
 		 * it into a huge pmd: just retry later if so.
+		 *
+		 * Use the maywrite version to indicate that vmf->pte may be
+		 * modified, but since we will use pte_same() to detect the
+		 * change of the !pte_none() entry, there is no need to recheck
+		 * the pmdval. Here we chooes to pass a dummy variable instead
+		 * of NULL, which helps new user think about why this place is
+		 * special.
 		 */
-		vmf->pte = pte_offset_map_nolock(vmf->vma->vm_mm, vmf->pmd,
-						 vmf->address, &vmf->ptl);
+		vmf->pte = pte_offset_map_rw_nolock(vmf->vma->vm_mm, vmf->pmd,
+						    vmf->address, &dummy_pmdval,
+						    &vmf->ptl);
 		if (unlikely(!vmf->pte))
 			return 0;
 		vmf->orig_pte = ptep_get_lockless(vmf->pte);
@@ -6346,10 +6396,11 @@ 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) ||
+		lockdep_assert(lockdep_is_held(&mapping->i_mmap_rwsem) ||
 			       lockdep_is_held(&vma->vm_mm->mmap_lock));
 	else
 		lockdep_assert(lockdep_is_held(&vma->vm_mm->mmap_lock));