Merge branch 'for-next' of https://git.kernel.org/pub/scm/linux/kernel/git/mm/linux.git

13 files changed, 24 insertions, 41 deletions

diff --git a/kernel/bpf/arena.c b/kernel/bpf/arena.c
index 7b6847200b43..b69fe5e34339 100644
--- a/kernel/bpf/arena.c
+++ b/kernel/bpf/arena.c
@@ -620,8 +620,9 @@ static int arena_map_mmap(struct bpf_map *map, struct vm_area_struct *vma)
 	 * clears VM_MAYEXEC. Set VM_DONTEXPAND to avoid potential change
 	 * of user_vm_start. Set VM_DONTCOPY to prevent arena VMA from
 	 * being copied into the child process on fork.
+	 * This is a kernel page so set VM_MIXEDMAP.
 	 */
-	vm_flags_set(vma, VM_DONTEXPAND | VM_DONTCOPY);
+	vm_flags_set(vma, VM_MIXEDMAP | VM_DONTEXPAND | VM_DONTCOPY);
 	vma->vm_ops = &arena_vm_ops;
 	return 0;
 }
diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c
index d09d4c3fe547..f7e8d766d128 100644
--- a/kernel/bpf/stackmap.c
+++ b/kernel/bpf/stackmap.c
@@ -272,13 +272,10 @@ struct stack_map_vma_lock {
 /*
  * Acquire a stable read-side reference on the VMA covering @ip.
  *
- * With CONFIG_PER_VMA_LOCK=y this returns a VMA with its per-VMA read
- * lock held and mmap_lock dropped, so the caller may sleep.
- *
- * With CONFIG_PER_VMA_LOCK=n it returns a VMA with mmap_lock still
- * held; the caller must snapshot any fields it needs and pin vm_file
- * with get_file() before stack_map_unlock_vma() drops mmap_lock, as
- * the VMA may be split, merged, or freed after that.
+ * On NOMMU configurations, returns with the mmap_lock held.  If the MMU
+ * is enabled, the per-VMA lock will be held instead.  The lock
+ * should be released with stack_map_unlock_vma() which will release the
+ * appropriate lock.  Once the lock is released, the VMA may be freed.
  *
  * Returns NULL on failure, in which case no lock is held.
  */
@@ -288,7 +285,6 @@ stack_map_lock_vma(struct stack_map_vma_lock *lock, unsigned long ip)
 	struct mm_struct *mm = lock->mm;
 	struct vm_area_struct *vma;
 
-	/* noop under !CONFIG_PER_VMA_LOCK */
 	vma = lock_vma_under_rcu(mm, ip);
 	if (vma) {
 		lock->vma = vma;
@@ -308,21 +304,20 @@ stack_map_lock_vma(struct stack_map_vma_lock *lock, unsigned long ip)
 		return NULL;
 	}
 
-#ifdef CONFIG_PER_VMA_LOCK
+#ifdef CONFIG_MMU
 	if (!vma_start_read_locked(vma)) {
 		mmap_read_unlock(mm);
 		return NULL;
 	}
 	mmap_read_unlock(mm);
 #endif
-
 	lock->vma = vma;
 	return vma;
 }
 
 static void stack_map_unlock_vma(struct stack_map_vma_lock *lock)
 {
-#ifdef CONFIG_PER_VMA_LOCK
+#ifdef CONFIG_MMU
 	vma_end_read(lock->vma);
 #else
 	mmap_read_unlock(lock->mm);
diff --git a/kernel/bpf/task_iter.c b/kernel/bpf/task_iter.c
index 13e1aabe6f88..c65ba1dcd866 100644
--- a/kernel/bpf/task_iter.c
+++ b/kernel/bpf/task_iter.c
@@ -869,7 +869,7 @@ __bpf_kfunc int bpf_iter_task_vma_new(struct bpf_iter_task_vma *it,
 	BUILD_BUG_ON(sizeof(struct bpf_iter_task_vma_kern) != sizeof(struct bpf_iter_task_vma));
 	BUILD_BUG_ON(__alignof__(struct bpf_iter_task_vma_kern) != __alignof__(struct bpf_iter_task_vma));
 
-	if (!IS_ENABLED(CONFIG_PER_VMA_LOCK)) {
+	if (!IS_ENABLED(CONFIG_MMU)) {
 		kit->data = NULL;
 		return -EOPNOTSUPP;
 	}
diff --git a/kernel/cgroup/cgroup-internal.h b/kernel/cgroup/cgroup-internal.h
index 58797123b752..7c367c8d0cbe 100644
--- a/kernel/cgroup/cgroup-internal.h
+++ b/kernel/cgroup/cgroup-internal.h
@@ -285,7 +285,6 @@ extern struct kernfs_syscall_ops cgroup1_kf_syscall_ops;
 extern const struct fs_parameter_spec cgroup1_fs_parameters[];
 
 int proc_cgroupstats_show(struct seq_file *m, void *v);
-bool cgroup1_ssid_disabled(int ssid);
 void cgroup1_pidlist_destroy_all(struct cgroup *cgrp);
 void cgroup1_release_agent(struct work_struct *work);
 void cgroup1_check_for_release(struct cgroup *cgrp);
diff --git a/kernel/configs/debug.config b/kernel/configs/debug.config
index 307c97ac5fa9..ac878669c193 100644
--- a/kernel/configs/debug.config
+++ b/kernel/configs/debug.config
@@ -50,7 +50,7 @@ CONFIG_DEBUG_NET=y
 # CONFIG_DEBUG_PAGEALLOC is not set
 # CONFIG_DEBUG_KMEMLEAK_DEFAULT_OFF is not set
 # CONFIG_DEBUG_RODATA_TEST is not set
-# CONFIG_DEBUG_WX is not set
+# CONFIG_CHECK_WX is not set
 # CONFIG_KFENCE is not set
 # CONFIG_PAGE_POISONING is not set
 # CONFIG_SLUB_STATS is not set
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 7846d70be57f..bb11e9191a27 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -9797,7 +9797,7 @@ static void perf_event_mmap_event(struct perf_mmap_event *mmap_event)
 
 	if (vma->vm_flags & VM_LOCKED)
 		flags |= MAP_LOCKED;
-	if (is_vm_hugetlb_page(vma))
+	if (vma_is_hugetlb(vma))
 		flags |= MAP_HUGETLB;
 
 	if (file) {
diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c
index 13bd42e5493d..64d4dbdc6c07 100644
--- a/kernel/events/ring_buffer.c
+++ b/kernel/events/ring_buffer.c
@@ -634,11 +634,10 @@ static struct page *rb_alloc_aux_page(int node, int order)
 		/*
 		 * Communicate the allocation size to the driver:
 		 * if we managed to secure a high-order allocation,
-		 * set its first page's private to this order;
-		 * !PagePrivate(page) means it's just a normal page.
+		 * set its first page's private to this order, otherwise page's
+		 * private remains zero.
 		 */
 		split_page(page, order);
-		SetPagePrivate(page);
 		set_page_private(page, order);
 	}
 
@@ -649,7 +648,7 @@ static void rb_free_aux_page(struct perf_buffer *rb, int idx)
 {
 	struct page *page = virt_to_page(rb->aux_pages[idx]);
 
-	ClearPagePrivate(page);
+	set_page_private(page, 0);
 	__free_page(page);
 }
 
diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index 7709ea882477..b89cc5cee002 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -1726,8 +1726,8 @@ static int xol_add_vma(struct mm_struct *mm, struct xol_area *area)
 	}
 
 	vma = _install_special_mapping(mm, area->vaddr, PAGE_SIZE,
-				VM_EXEC|VM_MAYEXEC|VM_DONTCOPY|VM_IO|
-				VM_SEALED_SYSMAP,
+				VM_EXEC|VM_MAYEXEC|VM_DONTCOPY|
+				VM_MIXEDMAP|VM_SEALED_SYSMAP,
 				&xol_mapping);
 	if (IS_ERR(vma)) {
 		ret = PTR_ERR(vma);
diff --git a/kernel/fork.c b/kernel/fork.c
index eb198c8dfdc7..ceedb07a5a00 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1083,9 +1083,7 @@ static void mmap_init_lock(struct mm_struct *mm)
 {
 	init_rwsem(&mm->mmap_lock);
 	mm_lock_seqcount_init(mm);
-#ifdef CONFIG_PER_VMA_LOCK
 	rcuwait_init(&mm->vma_writer_wait);
-#endif
 }
 
 static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p)
diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c
index b209712cb2c3..d5dba0e50b2e 100644
--- a/kernel/power/snapshot.c
+++ b/kernel/power/snapshot.c
@@ -88,7 +88,7 @@ static inline int hibernate_restore_unprotect_page(void *page_address) {return 0
 static inline void hibernate_map_page(struct page *page)
 {
 	if (IS_ENABLED(CONFIG_ARCH_HAS_SET_DIRECT_MAP)) {
-		int ret = set_direct_map_default_noflush(page);
+		int ret = set_direct_map_default_noflush(page, 1);
 
 		if (ret)
 			pr_warn_once("Failed to remap page\n");
@@ -101,7 +101,7 @@ static inline void hibernate_unmap_page(struct page *page)
 {
 	if (IS_ENABLED(CONFIG_ARCH_HAS_SET_DIRECT_MAP)) {
 		unsigned long addr = (unsigned long)page_address(page);
-		int ret  = set_direct_map_invalid_noflush(page);
+		int ret  = set_direct_map_invalid_noflush(page, 1);
 
 		if (ret)
 			pr_warn_once("Failed to remap page\n");
diff --git a/kernel/power/user.c b/kernel/power/user.c
index d0fcfba7ac23..6e4f40e49319 100644
--- a/kernel/power/user.c
+++ b/kernel/power/user.c
@@ -218,6 +218,7 @@ static int snapshot_set_swap_area(struct snapshot_data *data,
 {
 	sector_t offset;
 	dev_t swdev;
+	int new_type;
 
 	if (swsusp_swap_in_use())
 		return -EPERM;
@@ -238,19 +239,11 @@ static int snapshot_set_swap_area(struct snapshot_data *data,
 		offset = swap_area.offset;
 	}
 
-	/*
-	 * Unpin the swap device if a swap area was already
-	 * set by SNAPSHOT_SET_SWAP_AREA.
-	 */
-	unpin_hibernation_swap_type(data->swap);
+	new_type = repin_hibernation_swap_type(data->swap, swdev, offset);
+	if (new_type < 0)
+		return new_type;
 
-	/*
-	 * User space encodes device types as two-byte values,
-	 * so we need to recode them
-	 */
-	data->swap = pin_hibernation_swap_type(swdev, offset);
-	if (data->swap < 0)
-		return swdev ? -ENODEV : -EINVAL;
+	data->swap = new_type;
 	data->dev = swdev;
 	return 0;
 }
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 57360f5cdde4..000d4cb7aca9 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -22,7 +22,6 @@
  */
 #include <linux/energy_model.h>
 #include <linux/mmap_lock.h>
-#include <linux/hugetlb_inline.h>
 #include <linux/jiffies.h>
 #include <linux/mm_api.h>
 #include <linux/highmem.h>
@@ -4417,7 +4416,7 @@ retry_pids:
 
 	for (; vma; vma = vma_next(&vmi)) {
 		if (!vma_migratable(vma) || !vma_policy_mof(vma) ||
-			is_vm_hugetlb_page(vma) || (vma->vm_flags & VM_MIXEDMAP)) {
+			vma_is_hugetlb(vma) || !vma_is_mm_managed(vma)) {
 			trace_sched_skip_vma_numa(mm, vma, NUMAB_SKIP_UNSUITABLE);
 			continue;
 		}
diff --git a/kernel/vmcore_info.c b/kernel/vmcore_info.c
index 8614430ca212..5a417f8a922a 100644
--- a/kernel/vmcore_info.c
+++ b/kernel/vmcore_info.c
@@ -216,7 +216,6 @@ static int __init crash_save_vmcoreinfo_init(void)
 	VMCOREINFO_LENGTH(free_area.free_list, MIGRATE_TYPES);
 	VMCOREINFO_NUMBER(NR_FREE_PAGES);
 	VMCOREINFO_NUMBER(PG_lru);
-	VMCOREINFO_NUMBER(PG_private);
 	VMCOREINFO_NUMBER(PG_swapcache);
 	VMCOREINFO_NUMBER(PG_swapbacked);
 #define PAGE_SLAB_MAPCOUNT_VALUE	(PGTY_slab << 24)