Merge tag 'random-6.11-rc1-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/crng/random

Pull random number generator updates from Jason Donenfeld:
 "This adds getrandom() support to the vDSO.

  First, it adds a new kind of mapping to mmap(2), MAP_DROPPABLE, which
  lets the kernel zero out pages anytime under memory pressure, which
  enables allocating memory that never gets swapped to disk but also
  doesn't count as being mlocked.

  Then, the vDSO implementation of getrandom() is introduced in a
  generic manner and hooked into random.c.

  Next, this is implemented on x86. (Also, though it's not ready for
  this pull, somebody has begun an arm64 implementation already)

  Finally, two vDSO selftests are added.

  There are also two housekeeping cleanup commits"

* tag 'random-6.11-rc1-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/crng/random:
  MAINTAINERS: add random.h headers to RNG subsection
  random: note that RNDGETPOOL was removed in 2.6.9-rc2
  selftests/vDSO: add tests for vgetrandom
  x86: vdso: Wire up getrandom() vDSO implementation
  random: introduce generic vDSO getrandom() implementation
  mm: add MAP_DROPPABLE for designating always lazily freeable mappings

8 files changed, 70 insertions, 15 deletions

diff --git a/mm/ksm.c b/mm/ksm.c
index df6bae3a5a2c..14d9e53b1ec2 100644
--- a/mm/ksm.c
+++ b/mm/ksm.c
@@ -713,7 +713,7 @@ static bool vma_ksm_compatible(struct vm_area_struct *vma)
 {
 	if (vma->vm_flags & (VM_SHARED  | VM_MAYSHARE   | VM_PFNMAP  |
 			     VM_IO      | VM_DONTEXPAND | VM_HUGETLB |
-			     VM_MIXEDMAP))
+			     VM_MIXEDMAP| VM_DROPPABLE))
 		return false;		/* just ignore the advice */
 
 	if (vma_is_dax(vma))
diff --git a/mm/madvise.c b/mm/madvise.c
index 96c026fe0c99..89089d84f8df 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -1068,13 +1068,16 @@ static int madvise_vma_behavior(struct vm_area_struct *vma,
 		new_flags |= VM_WIPEONFORK;
 		break;
 	case MADV_KEEPONFORK:
+		if (vma->vm_flags & VM_DROPPABLE)
+			return -EINVAL;
 		new_flags &= ~VM_WIPEONFORK;
 		break;
 	case MADV_DONTDUMP:
 		new_flags |= VM_DONTDUMP;
 		break;
 	case MADV_DODUMP:
-		if (!is_vm_hugetlb_page(vma) && new_flags & VM_SPECIAL)
+		if ((!is_vm_hugetlb_page(vma) && new_flags & VM_SPECIAL) ||
+		    (vma->vm_flags & VM_DROPPABLE))
 			return -EINVAL;
 		new_flags &= ~VM_DONTDUMP;
 		break;
diff --git a/mm/memory.c b/mm/memory.c
index 4bcd79619574..1ff7b6f51ec1 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -5801,6 +5801,7 @@ vm_fault_t handle_mm_fault(struct vm_area_struct *vma, unsigned long address,
 	/* If the fault handler drops the mmap_lock, vma may be freed */
 	struct mm_struct *mm = vma->vm_mm;
 	vm_fault_t ret;
+	bool is_droppable;
 
 	__set_current_state(TASK_RUNNING);
 
@@ -5815,6 +5816,8 @@ vm_fault_t handle_mm_fault(struct vm_area_struct *vma, unsigned long address,
 		goto out;
 	}
 
+	is_droppable = !!(vma->vm_flags & VM_DROPPABLE);
+
 	/*
 	 * Enable the memcg OOM handling for faults triggered in user
 	 * space.  Kernel faults are handled more gracefully.
@@ -5829,8 +5832,18 @@ vm_fault_t handle_mm_fault(struct vm_area_struct *vma, unsigned long address,
 	else
 		ret = __handle_mm_fault(vma, address, flags);
 
+	/*
+	 * Warning: It is no longer safe to dereference vma-> after this point,
+	 * because mmap_lock might have been dropped by __handle_mm_fault(), so
+	 * vma might be destroyed from underneath us.
+	 */
+
 	lru_gen_exit_fault();
 
+	/* If the mapping is droppable, then errors due to OOM aren't fatal. */
+	if (is_droppable)
+		ret &= ~VM_FAULT_OOM;
+
 	if (flags & FAULT_FLAG_USER) {
 		mem_cgroup_exit_user_fault();
 		/*
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 327a19b0883d..b858e22b259d 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -2305,6 +2305,9 @@ struct folio *vma_alloc_folio_noprof(gfp_t gfp, int order, struct vm_area_struct
 	pgoff_t ilx;
 	struct folio *folio;
 
+	if (vma->vm_flags & VM_DROPPABLE)
+		gfp |= __GFP_NOWARN;
+
 	pol = get_vma_policy(vma, addr, order, &ilx);
 	folio = folio_alloc_mpol_noprof(gfp, order, pol, ilx, numa_node_id());
 	mpol_cond_put(pol);
diff --git a/mm/mlock.c b/mm/mlock.c
index 52d6e401ad67..e3e3dc2b2956 100644
--- a/mm/mlock.c
+++ b/mm/mlock.c
@@ -474,7 +474,7 @@ static int mlock_fixup(struct vma_iterator *vmi, struct vm_area_struct *vma,
 
 	if (newflags == oldflags || (oldflags & VM_SPECIAL) ||
 	    is_vm_hugetlb_page(vma) || vma == get_gate_vma(current->mm) ||
-	    vma_is_dax(vma) || vma_is_secretmem(vma))
+	    vma_is_dax(vma) || vma_is_secretmem(vma) || (oldflags & VM_DROPPABLE))
 		/* don't set VM_LOCKED or VM_LOCKONFAULT and don't count */
 		goto out;
 
diff --git a/mm/mmap.c b/mm/mmap.c
index e42d89f98071..d0dfc85b209b 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -1410,6 +1410,36 @@ unsigned long do_mmap(struct file *file, unsigned long addr,
 			pgoff = 0;
 			vm_flags |= VM_SHARED | VM_MAYSHARE;
 			break;
+		case MAP_DROPPABLE:
+			if (VM_DROPPABLE == VM_NONE)
+				return -ENOTSUPP;
+			/*
+			 * A locked or stack area makes no sense to be droppable.
+			 *
+			 * Also, since droppable pages can just go away at any time
+			 * it makes no sense to copy them on fork or dump them.
+			 *
+			 * And don't attempt to combine with hugetlb for now.
+			 */
+			if (flags & (MAP_LOCKED | MAP_HUGETLB))
+			        return -EINVAL;
+			if (vm_flags & (VM_GROWSDOWN | VM_GROWSUP))
+			        return -EINVAL;
+
+			vm_flags |= VM_DROPPABLE;
+
+			/*
+			 * If the pages can be dropped, then it doesn't make
+			 * sense to reserve them.
+			 */
+			vm_flags |= VM_NORESERVE;
+
+			/*
+			 * Likewise, they're volatile enough that they
+			 * shouldn't survive forks or coredumps.
+			 */
+			vm_flags |= VM_WIPEONFORK | VM_DONTDUMP;
+			fallthrough;
 		case MAP_PRIVATE:
 			/*
 			 * Set pgoff according to addr for anon_vma.
diff --git a/mm/rmap.c b/mm/rmap.c
index 8616308610b9..2490e727e2dc 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -1412,7 +1412,11 @@ void folio_add_new_anon_rmap(struct folio *folio, struct vm_area_struct *vma,
 	VM_BUG_ON_VMA(address < vma->vm_start ||
 			address + (nr << PAGE_SHIFT) > vma->vm_end, vma);
 
-	if (!folio_test_swapbacked(folio))
+	/*
+	 * VM_DROPPABLE mappings don't swap; instead they're just dropped when
+	 * under memory pressure.
+	 */
+	if (!folio_test_swapbacked(folio) && !(vma->vm_flags & VM_DROPPABLE))
 		__folio_set_swapbacked(folio);
 	__folio_set_anon(folio, vma, address, exclusive);
 
@@ -1848,7 +1852,13 @@ static bool try_to_unmap_one(struct folio *folio, struct vm_area_struct *vma,
 				 * plus the rmap(s) (dropped by discard:).
 				 */
 				if (ref_count == 1 + map_count &&
-				    !folio_test_dirty(folio)) {
+				    (!folio_test_dirty(folio) ||
+				     /*
+				      * Unlike MADV_FREE mappings, VM_DROPPABLE
+				      * ones can be dropped even if they've
+				      * been dirtied.
+				      */
+				     (vma->vm_flags & VM_DROPPABLE))) {
 					dec_mm_counter(mm, MM_ANONPAGES);
 					goto discard;
 				}
@@ -1858,7 +1868,12 @@ static bool try_to_unmap_one(struct folio *folio, struct vm_area_struct *vma,
 				 * discarded. Remap the page to page table.
 				 */
 				set_pte_at(mm, address, pvmw.pte, pteval);
-				folio_set_swapbacked(folio);
+				/*
+				 * Unlike MADV_FREE mappings, VM_DROPPABLE ones
+				 * never get swap backed on failure to drop.
+				 */
+				if (!(vma->vm_flags & VM_DROPPABLE))
+					folio_set_swapbacked(folio);
 				goto walk_abort;
 			}
 
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 525d3ffa8451..cfa839284b92 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -4301,15 +4301,6 @@ static bool sort_folio(struct lruvec *lruvec, struct folio *folio, struct scan_c
 		return true;
 	}
 
-	/* dirty lazyfree */
-	if (type == LRU_GEN_FILE && folio_test_anon(folio) && folio_test_dirty(folio)) {
-		success = lru_gen_del_folio(lruvec, folio, true);
-		VM_WARN_ON_ONCE_FOLIO(!success, folio);
-		folio_set_swapbacked(folio);
-		lruvec_add_folio_tail(lruvec, folio);
-		return true;
-	}
-
 	/* promoted */
 	if (gen != lru_gen_from_seq(lrugen->min_seq[type])) {
 		list_move(&folio->lru, &lrugen->folios[gen][type][zone]);