Merge tag 'mm-stable-2022-10-08' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

Pull MM updates from Andrew Morton:

 - Yu Zhao's Multi-Gen LRU patches are here. They've been under test in
   linux-next for a couple of months without, to my knowledge, any
   negative reports (or any positive ones, come to that).

 - Also the Maple Tree from Liam Howlett. An overlapping range-based
   tree for vmas. It it apparently slightly more efficient in its own
   right, but is mainly targeted at enabling work to reduce mmap_lock
   contention.

   Liam has identified a number of other tree users in the kernel which
   could be beneficially onverted to mapletrees.

   Yu Zhao has identified a hard-to-hit but "easy to fix" lockdep splat
   at [1]. This has yet to be addressed due to Liam's unfortunately
   timed vacation. He is now back and we'll get this fixed up.

 - Dmitry Vyukov introduces KMSAN: the Kernel Memory Sanitizer. It uses
   clang-generated instrumentation to detect used-unintialized bugs down
   to the single bit level.

   KMSAN keeps finding bugs. New ones, as well as the legacy ones.

 - Yang Shi adds a userspace mechanism (madvise) to induce a collapse of
   memory into THPs.

 - Zach O'Keefe has expanded Yang Shi's madvise(MADV_COLLAPSE) to
   support file/shmem-backed pages.

 - userfaultfd updates from Axel Rasmussen

 - zsmalloc cleanups from Alexey Romanov

 - cleanups from Miaohe Lin: vmscan, hugetlb_cgroup, hugetlb and
   memory-failure

 - Huang Ying adds enhancements to NUMA balancing memory tiering mode's
   page promotion, with a new way of detecting hot pages.

 - memcg updates from Shakeel Butt: charging optimizations and reduced
   memory consumption.

 - memcg cleanups from Kairui Song.

 - memcg fixes and cleanups from Johannes Weiner.

 - Vishal Moola provides more folio conversions

 - Zhang Yi removed ll_rw_block() :(

 - migration enhancements from Peter Xu

 - migration error-path bugfixes from Huang Ying

 - Aneesh Kumar added ability for a device driver to alter the memory
   tiering promotion paths. For optimizations by PMEM drivers, DRM
   drivers, etc.

 - vma merging improvements from Jakub Matěn.

 - NUMA hinting cleanups from David Hildenbrand.

 - xu xin added aditional userspace visibility into KSM merging
   activity.

 - THP & KSM code consolidation from Qi Zheng.

 - more folio work from Matthew Wilcox.

 - KASAN updates from Andrey Konovalov.

 - DAMON cleanups from Kaixu Xia.

 - DAMON work from SeongJae Park: fixes, cleanups.

 - hugetlb sysfs cleanups from Muchun Song.

 - Mike Kravetz fixes locking issues in hugetlbfs and in hugetlb core.

Link: https://lkml.kernel.org/r/CAOUHufZabH85CeUN-MEMgL8gJGzJEWUrkiM58JkTbBhh-jew0Q@mail.gmail.com [1]

* tag 'mm-stable-2022-10-08' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (555 commits)
  hugetlb: allocate vma lock for all sharable vmas
  hugetlb: take hugetlb vma_lock when clearing vma_lock->vma pointer
  hugetlb: fix vma lock handling during split vma and range unmapping
  mglru: mm/vmscan.c: fix imprecise comments
  mm/mglru: don't sync disk for each aging cycle
  mm: memcontrol: drop dead CONFIG_MEMCG_SWAP config symbol
  mm: memcontrol: use do_memsw_account() in a few more places
  mm: memcontrol: deprecate swapaccounting=0 mode
  mm: memcontrol: don't allocate cgroup swap arrays when memcg is disabled
  mm/secretmem: remove reduntant return value
  mm/hugetlb: add available_huge_pages() func
  mm: remove unused inline functions from include/linux/mm_inline.h
  selftests/vm: add selftest for MADV_COLLAPSE of uffd-minor memory
  selftests/vm: add file/shmem MADV_COLLAPSE selftest for cleared pmd
  selftests/vm: add thp collapse shmem testing
  selftests/vm: add thp collapse file and tmpfs testing
  selftests/vm: modularize thp collapse memory operations
  selftests/vm: dedup THP helpers
  mm/khugepaged: add tracepoint to hpage_collapse_scan_file()
  mm/madvise: add file and shmem support to MADV_COLLAPSE
  ...

1 files changed, 214 insertions, 86 deletions

diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index f7a5b5124d8a..ed57a029eab0 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -364,13 +364,155 @@ static int hugetlbfs_write_end(struct file *file, struct address_space *mapping,
 	return -EINVAL;
 }
 
-static void remove_huge_page(struct page *page)
+static void hugetlb_delete_from_page_cache(struct page *page)
 {
 	ClearPageDirty(page);
 	ClearPageUptodate(page);
 	delete_from_page_cache(page);
 }
 
+/*
+ * Called with i_mmap_rwsem held for inode based vma maps.  This makes
+ * sure vma (and vm_mm) will not go away.  We also hold the hugetlb fault
+ * mutex for the page in the mapping.  So, we can not race with page being
+ * faulted into the vma.
+ */
+static bool hugetlb_vma_maps_page(struct vm_area_struct *vma,
+				unsigned long addr, struct page *page)
+{
+	pte_t *ptep, pte;
+
+	ptep = huge_pte_offset(vma->vm_mm, addr,
+			huge_page_size(hstate_vma(vma)));
+
+	if (!ptep)
+		return false;
+
+	pte = huge_ptep_get(ptep);
+	if (huge_pte_none(pte) || !pte_present(pte))
+		return false;
+
+	if (pte_page(pte) == page)
+		return true;
+
+	return false;
+}
+
+/*
+ * Can vma_offset_start/vma_offset_end overflow on 32-bit arches?
+ * No, because the interval tree returns us only those vmas
+ * which overlap the truncated area starting at pgoff,
+ * and no vma on a 32-bit arch can span beyond the 4GB.
+ */
+static unsigned long vma_offset_start(struct vm_area_struct *vma, pgoff_t start)
+{
+	if (vma->vm_pgoff < start)
+		return (start - vma->vm_pgoff) << PAGE_SHIFT;
+	else
+		return 0;
+}
+
+static unsigned long vma_offset_end(struct vm_area_struct *vma, pgoff_t end)
+{
+	unsigned long t_end;
+
+	if (!end)
+		return vma->vm_end;
+
+	t_end = ((end - vma->vm_pgoff) << PAGE_SHIFT) + vma->vm_start;
+	if (t_end > vma->vm_end)
+		t_end = vma->vm_end;
+	return t_end;
+}
+
+/*
+ * Called with hugetlb fault mutex held.  Therefore, no more mappings to
+ * this folio can be created while executing the routine.
+ */
+static void hugetlb_unmap_file_folio(struct hstate *h,
+					struct address_space *mapping,
+					struct folio *folio, pgoff_t index)
+{
+	struct rb_root_cached *root = &mapping->i_mmap;
+	struct hugetlb_vma_lock *vma_lock;
+	struct page *page = &folio->page;
+	struct vm_area_struct *vma;
+	unsigned long v_start;
+	unsigned long v_end;
+	pgoff_t start, end;
+
+	start = index * pages_per_huge_page(h);
+	end = (index + 1) * pages_per_huge_page(h);
+
+	i_mmap_lock_write(mapping);
+retry:
+	vma_lock = NULL;
+	vma_interval_tree_foreach(vma, root, start, end - 1) {
+		v_start = vma_offset_start(vma, start);
+		v_end = vma_offset_end(vma, end);
+
+		if (!hugetlb_vma_maps_page(vma, vma->vm_start + v_start, page))
+			continue;
+
+		if (!hugetlb_vma_trylock_write(vma)) {
+			vma_lock = vma->vm_private_data;
+			/*
+			 * If we can not get vma lock, we need to drop
+			 * immap_sema and take locks in order.  First,
+			 * take a ref on the vma_lock structure so that
+			 * we can be guaranteed it will not go away when
+			 * dropping immap_sema.
+			 */
+			kref_get(&vma_lock->refs);
+			break;
+		}
+
+		unmap_hugepage_range(vma, vma->vm_start + v_start, v_end,
+				NULL, ZAP_FLAG_DROP_MARKER);
+		hugetlb_vma_unlock_write(vma);
+	}
+
+	i_mmap_unlock_write(mapping);
+
+	if (vma_lock) {
+		/*
+		 * Wait on vma_lock.  We know it is still valid as we have
+		 * a reference.  We must 'open code' vma locking as we do
+		 * not know if vma_lock is still attached to vma.
+		 */
+		down_write(&vma_lock->rw_sema);
+		i_mmap_lock_write(mapping);
+
+		vma = vma_lock->vma;
+		if (!vma) {
+			/*
+			 * If lock is no longer attached to vma, then just
+			 * unlock, drop our reference and retry looking for
+			 * other vmas.
+			 */
+			up_write(&vma_lock->rw_sema);
+			kref_put(&vma_lock->refs, hugetlb_vma_lock_release);
+			goto retry;
+		}
+
+		/*
+		 * vma_lock is still attached to vma.  Check to see if vma
+		 * still maps page and if so, unmap.
+		 */
+		v_start = vma_offset_start(vma, start);
+		v_end = vma_offset_end(vma, end);
+		if (hugetlb_vma_maps_page(vma, vma->vm_start + v_start, page))
+			unmap_hugepage_range(vma, vma->vm_start + v_start,
+						v_end, NULL,
+						ZAP_FLAG_DROP_MARKER);
+
+		kref_put(&vma_lock->refs, hugetlb_vma_lock_release);
+		hugetlb_vma_unlock_write(vma);
+
+		goto retry;
+	}
+}
+
 static void
 hugetlb_vmdelete_list(struct rb_root_cached *root, pgoff_t start, pgoff_t end,
 		      zap_flags_t zap_flags)
@@ -383,32 +525,66 @@ hugetlb_vmdelete_list(struct rb_root_cached *root, pgoff_t start, pgoff_t end,
 	 * an inclusive "last".
 	 */
 	vma_interval_tree_foreach(vma, root, start, end ? end - 1 : ULONG_MAX) {
-		unsigned long v_offset;
+		unsigned long v_start;
 		unsigned long v_end;
 
+		if (!hugetlb_vma_trylock_write(vma))
+			continue;
+
+		v_start = vma_offset_start(vma, start);
+		v_end = vma_offset_end(vma, end);
+
+		unmap_hugepage_range(vma, vma->vm_start + v_start, v_end,
+				     NULL, zap_flags);
+
 		/*
-		 * Can the expression below overflow on 32-bit arches?
-		 * No, because the interval tree returns us only those vmas
-		 * which overlap the truncated area starting at pgoff,
-		 * and no vma on a 32-bit arch can span beyond the 4GB.
+		 * Note that vma lock only exists for shared/non-private
+		 * vmas.  Therefore, lock is not held when calling
+		 * unmap_hugepage_range for private vmas.
 		 */
-		if (vma->vm_pgoff < start)
-			v_offset = (start - vma->vm_pgoff) << PAGE_SHIFT;
-		else
-			v_offset = 0;
-
-		if (!end)
-			v_end = vma->vm_end;
-		else {
-			v_end = ((end - vma->vm_pgoff) << PAGE_SHIFT)
-							+ vma->vm_start;
-			if (v_end > vma->vm_end)
-				v_end = vma->vm_end;
-		}
+		hugetlb_vma_unlock_write(vma);
+	}
+}
 
-		unmap_hugepage_range(vma, vma->vm_start + v_offset, v_end,
-				     NULL, zap_flags);
+/*
+ * Called with hugetlb fault mutex held.
+ * Returns true if page was actually removed, false otherwise.
+ */
+static bool remove_inode_single_folio(struct hstate *h, struct inode *inode,
+					struct address_space *mapping,
+					struct folio *folio, pgoff_t index,
+					bool truncate_op)
+{
+	bool ret = false;
+
+	/*
+	 * If folio is mapped, it was faulted in after being
+	 * unmapped in caller.  Unmap (again) while holding
+	 * the fault mutex.  The mutex will prevent faults
+	 * until we finish removing the folio.
+	 */
+	if (unlikely(folio_mapped(folio)))
+		hugetlb_unmap_file_folio(h, mapping, folio, index);
+
+	folio_lock(folio);
+	/*
+	 * We must remove the folio from page cache before removing
+	 * the region/ reserve map (hugetlb_unreserve_pages).  In
+	 * rare out of memory conditions, removal of the region/reserve
+	 * map could fail.  Correspondingly, the subpool and global
+	 * reserve usage count can need to be adjusted.
+	 */
+	VM_BUG_ON(HPageRestoreReserve(&folio->page));
+	hugetlb_delete_from_page_cache(&folio->page);
+	ret = true;
+	if (!truncate_op) {
+		if (unlikely(hugetlb_unreserve_pages(inode, index,
+							index + 1, 1)))
+			hugetlb_fix_reserve_counts(inode);
 	}
+
+	folio_unlock(folio);
+	return ret;
 }
 
 /*
@@ -418,10 +594,10 @@ hugetlb_vmdelete_list(struct rb_root_cached *root, pgoff_t start, pgoff_t end,
  * truncation is indicated by end of range being LLONG_MAX
  *	In this case, we first scan the range and release found pages.
  *	After releasing pages, hugetlb_unreserve_pages cleans up region/reserve
- *	maps and global counts.  Page faults can not race with truncation
- *	in this routine.  hugetlb_no_page() holds i_mmap_rwsem and prevents
- *	page faults in the truncated range by checking i_size.  i_size is
- *	modified while holding i_mmap_rwsem.
+ *	maps and global counts.  Page faults can race with truncation.
+ *	During faults, hugetlb_no_page() checks i_size before page allocation,
+ *	and again after obtaining page table lock.  It will 'back out'
+ *	allocations in the truncated range.
  * hole punch is indicated if end is not LLONG_MAX
  *	In the hole punch case we scan the range and release found pages.
  *	Only when releasing a page is the associated region/reserve map
@@ -451,61 +627,17 @@ static void remove_inode_hugepages(struct inode *inode, loff_t lstart,
 			u32 hash = 0;
 
 			index = folio->index;
-			if (!truncate_op) {
-				/*
-				 * Only need to hold the fault mutex in the
-				 * hole punch case.  This prevents races with
-				 * page faults.  Races are not possible in the
-				 * case of truncation.
-				 */
-				hash = hugetlb_fault_mutex_hash(mapping, index);
-				mutex_lock(&hugetlb_fault_mutex_table[hash]);
-			}
+			hash = hugetlb_fault_mutex_hash(mapping, index);
+			mutex_lock(&hugetlb_fault_mutex_table[hash]);
 
 			/*
-			 * If folio is mapped, it was faulted in after being
-			 * unmapped in caller.  Unmap (again) now after taking
-			 * the fault mutex.  The mutex will prevent faults
-			 * until we finish removing the folio.
-			 *
-			 * This race can only happen in the hole punch case.
-			 * Getting here in a truncate operation is a bug.
+			 * Remove folio that was part of folio_batch.
 			 */
-			if (unlikely(folio_mapped(folio))) {
-				BUG_ON(truncate_op);
-
-				mutex_unlock(&hugetlb_fault_mutex_table[hash]);
-				i_mmap_lock_write(mapping);
-				mutex_lock(&hugetlb_fault_mutex_table[hash]);
-				hugetlb_vmdelete_list(&mapping->i_mmap,
-					index * pages_per_huge_page(h),
-					(index + 1) * pages_per_huge_page(h),
-					ZAP_FLAG_DROP_MARKER);
-				i_mmap_unlock_write(mapping);
-			}
-
-			folio_lock(folio);
-			/*
-			 * We must free the huge page and remove from page
-			 * cache (remove_huge_page) BEFORE removing the
-			 * region/reserve map (hugetlb_unreserve_pages).  In
-			 * rare out of memory conditions, removal of the
-			 * region/reserve map could fail. Correspondingly,
-			 * the subpool and global reserve usage count can need
-			 * to be adjusted.
-			 */
-			VM_BUG_ON(HPageRestoreReserve(&folio->page));
-			remove_huge_page(&folio->page);
-			freed++;
-			if (!truncate_op) {
-				if (unlikely(hugetlb_unreserve_pages(inode,
-							index, index + 1, 1)))
-					hugetlb_fix_reserve_counts(inode);
-			}
-
-			folio_unlock(folio);
-			if (!truncate_op)
-				mutex_unlock(&hugetlb_fault_mutex_table[hash]);
+			if (remove_inode_single_folio(h, inode, mapping, folio,
+							index, truncate_op))
+				freed++;
+
+			mutex_unlock(&hugetlb_fault_mutex_table[hash]);
 		}
 		folio_batch_release(&fbatch);
 		cond_resched();
@@ -543,8 +675,8 @@ static void hugetlb_vmtruncate(struct inode *inode, loff_t offset)
 	BUG_ON(offset & ~huge_page_mask(h));
 	pgoff = offset >> PAGE_SHIFT;
 
-	i_mmap_lock_write(mapping);
 	i_size_write(inode, offset);
+	i_mmap_lock_write(mapping);
 	if (!RB_EMPTY_ROOT(&mapping->i_mmap.rb_root))
 		hugetlb_vmdelete_list(&mapping->i_mmap, pgoff, 0,
 				      ZAP_FLAG_DROP_MARKER);
@@ -703,11 +835,7 @@ static long hugetlbfs_fallocate(struct file *file, int mode, loff_t offset,
 		/* addr is the offset within the file (zero based) */
 		addr = index * hpage_size;
 
-		/*
-		 * fault mutex taken here, protects against fault path
-		 * and hole punch.  inode_lock previously taken protects
-		 * against truncation.
-		 */
+		/* mutex taken here, fault path and hole punch */
 		hash = hugetlb_fault_mutex_hash(mapping, index);
 		mutex_lock(&hugetlb_fault_mutex_table[hash]);
 
@@ -737,7 +865,7 @@ static long hugetlbfs_fallocate(struct file *file, int mode, loff_t offset,
 		}
 		clear_huge_page(page, addr, pages_per_huge_page(h));
 		__SetPageUptodate(page);
-		error = huge_add_to_page_cache(page, mapping, index);
+		error = hugetlb_add_to_page_cache(page, mapping, index);
 		if (unlikely(error)) {
 			restore_reserve_on_error(h, &pseudo_vma, addr, page);
 			put_page(page);
@@ -749,7 +877,7 @@ static long hugetlbfs_fallocate(struct file *file, int mode, loff_t offset,
 
 		SetHPageMigratable(page);
 		/*
-		 * unlock_page because locked by huge_add_to_page_cache()
+		 * unlock_page because locked by hugetlb_add_to_page_cache()
 		 * put_page() due to reference from alloc_huge_page()
 		 */
 		unlock_page(page);
@@ -994,7 +1122,7 @@ static int hugetlbfs_error_remove_page(struct address_space *mapping,
 	struct inode *inode = mapping->host;
 	pgoff_t index = page->index;
 
-	remove_huge_page(page);
+	hugetlb_delete_from_page_cache(page);
 	if (unlikely(hugetlb_unreserve_pages(inode, index, index + 1, 1)))
 		hugetlb_fix_reserve_counts(inode);