Merge branch 'akpm' (patches from Andrew)

Merge misc mm fixes from Andrew Morton:
 "15 patches.

  VM subsystems affected by this patch series: userfaultfd, kfence,
  highmem, pagealloc, memblock, pagecache, secretmem, pagemap, and
  hugetlbfs"

* akpm:
  hugetlbfs: fix mount mode command line processing
  mm: fix the deadlock in finish_fault()
  mm: mmap_lock: fix disabling preemption directly
  mm/secretmem: wire up ->set_page_dirty
  writeback, cgroup: do not reparent dax inodes
  writeback, cgroup: remove wb from offline list before releasing refcnt
  memblock: make for_each_mem_range() traverse MEMBLOCK_HOTPLUG regions
  mm: page_alloc: fix page_poison=1 / INIT_ON_ALLOC_DEFAULT_ON interaction
  mm: use kmap_local_page in memzero_page
  mm: call flush_dcache_page() in memcpy_to_page() and memzero_page()
  kfence: skip all GFP_ZONEMASK allocations
  kfence: move the size check to the beginning of __kfence_alloc()
  kfence: defer kfence_test_init to ensure that kunit debugfs is created
  selftest: use mmap instead of posix_memalign to allocate memory
  userfaultfd: do not untag user pointers

Documentation/arm64/tagged-address-abi.rst

@@ -45,8 +45,9 @@ how the user addresses are used by the kernel:
 
 1. User addresses not accessed by the kernel but used for address space
    management (e.g. ``mprotect()``, ``madvise()``). The use of valid
-   tagged pointers in this context is allowed with the exception of
-   ``brk()``, ``mmap()`` and the ``new_address`` argument to
+   tagged pointers in this context is allowed with these exceptions:
+
+   - ``brk()``, ``mmap()`` and the ``new_address`` argument to
      ``mremap()`` as these have the potential to alias with existing
       user addresses.
 
@@ -54,6 +55,15 @@ how the user addresses are used by the kernel:
      incorrectly accept valid tagged pointers for the ``brk()``,
      ``mmap()`` and ``mremap()`` system calls.
 
+   - The ``range.start``, ``start`` and ``dst`` arguments to the
+     ``UFFDIO_*`` ``ioctl()``s used on a file descriptor obtained from
+     ``userfaultfd()``, as fault addresses subsequently obtained by reading
+     the file descriptor will be untagged, which may otherwise confuse
+     tag-unaware programs.
+
+     NOTE: This behaviour changed in v5.14 and so some earlier kernels may
+     incorrectly accept valid tagged pointers for this system call.
+
 2. User addresses accessed by the kernel (e.g. ``write()``). This ABI
    relaxation is disabled by default and the application thread needs to
    explicitly enable it via ``prctl()`` as follows:

fs/fs-writeback.c

@@ -521,6 +521,9 @@ static bool inode_prepare_wbs_switch(struct inode *inode,
 	 */
 	smp_mb();
 
+	if (IS_DAX(inode))
+		return false;
+
 	/* while holding I_WB_SWITCH, no one else can update the association */
 	spin_lock(&inode->i_lock);
 	if (!(inode->i_sb->s_flags & SB_ACTIVE) ||

fs/hugetlbfs/inode.c

@@ -77,7 +77,7 @@ enum hugetlb_param {
 static const struct fs_parameter_spec hugetlb_fs_parameters[] = {
 	fsparam_u32   ("gid",		Opt_gid),
 	fsparam_string("min_size",	Opt_min_size),
-	fsparam_u32   ("mode",		Opt_mode),
+	fsparam_u32oct("mode",		Opt_mode),
 	fsparam_string("nr_inodes",	Opt_nr_inodes),
 	fsparam_string("pagesize",	Opt_pagesize),
 	fsparam_string("size",		Opt_size),

fs/userfaultfd.c

@@ -1236,23 +1236,21 @@ static __always_inline void wake_userfault(struct userfaultfd_ctx *ctx,
 }
 
 static __always_inline int validate_range(struct mm_struct *mm,
-					  __u64 *start, __u64 len)
+					  __u64 start, __u64 len)
 {
 	__u64 task_size = mm->task_size;
 
-	*start = untagged_addr(*start);
-
-	if (*start & ~PAGE_MASK)
+	if (start & ~PAGE_MASK)
 		return -EINVAL;
 	if (len & ~PAGE_MASK)
 		return -EINVAL;
 	if (!len)
 		return -EINVAL;
-	if (*start < mmap_min_addr)
+	if (start < mmap_min_addr)
 		return -EINVAL;
-	if (*start >= task_size)
+	if (start >= task_size)
 		return -EINVAL;
-	if (len > task_size - *start)
+	if (len > task_size - start)
 		return -EINVAL;
 	return 0;
 }
@@ -1316,7 +1314,7 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx,
 		vm_flags |= VM_UFFD_MINOR;
 	}
 
-	ret = validate_range(mm, &uffdio_register.range.start,
+	ret = validate_range(mm, uffdio_register.range.start,
 			     uffdio_register.range.len);
 	if (ret)
 		goto out;
@@ -1522,7 +1520,7 @@ static int userfaultfd_unregister(struct userfaultfd_ctx *ctx,
 	if (copy_from_user(&uffdio_unregister, buf, sizeof(uffdio_unregister)))
 		goto out;
 
-	ret = validate_range(mm, &uffdio_unregister.start,
+	ret = validate_range(mm, uffdio_unregister.start,
 			     uffdio_unregister.len);
 	if (ret)
 		goto out;
@@ -1671,7 +1669,7 @@ static int userfaultfd_wake(struct userfaultfd_ctx *ctx,
 	if (copy_from_user(&uffdio_wake, buf, sizeof(uffdio_wake)))
 		goto out;
 
-	ret = validate_range(ctx->mm, &uffdio_wake.start, uffdio_wake.len);
+	ret = validate_range(ctx->mm, uffdio_wake.start, uffdio_wake.len);
 	if (ret)
 		goto out;
 
@@ -1711,7 +1709,7 @@ static int userfaultfd_copy(struct userfaultfd_ctx *ctx,
 			   sizeof(uffdio_copy)-sizeof(__s64)))
 		goto out;
 
-	ret = validate_range(ctx->mm, &uffdio_copy.dst, uffdio_copy.len);
+	ret = validate_range(ctx->mm, uffdio_copy.dst, uffdio_copy.len);
 	if (ret)
 		goto out;
 	/*
@@ -1768,7 +1766,7 @@ static int userfaultfd_zeropage(struct userfaultfd_ctx *ctx,
 			   sizeof(uffdio_zeropage)-sizeof(__s64)))
 		goto out;
 
-	ret = validate_range(ctx->mm, &uffdio_zeropage.range.start,
+	ret = validate_range(ctx->mm, uffdio_zeropage.range.start,
 			     uffdio_zeropage.range.len);
 	if (ret)
 		goto out;
@@ -1818,7 +1816,7 @@ static int userfaultfd_writeprotect(struct userfaultfd_ctx *ctx,
 			   sizeof(struct uffdio_writeprotect)))
 		return -EFAULT;
 
-	ret = validate_range(ctx->mm, &uffdio_wp.range.start,
+	ret = validate_range(ctx->mm, uffdio_wp.range.start,
 			     uffdio_wp.range.len);
 	if (ret)
 		return ret;
@@ -1866,7 +1864,7 @@ static int userfaultfd_continue(struct userfaultfd_ctx *ctx, unsigned long arg)
 			   sizeof(uffdio_continue) - (sizeof(__s64))))
 		goto out;
 
-	ret = validate_range(ctx->mm, &uffdio_continue.range.start,
+	ret = validate_range(ctx->mm, uffdio_continue.range.start,
 			     uffdio_continue.range.len);
 	if (ret)
 		goto out;

include/linux/highmem.h

@@ -318,14 +318,16 @@ static inline void memcpy_to_page(struct page *page, size_t offset,
 
 	VM_BUG_ON(offset + len > PAGE_SIZE);
 	memcpy(to + offset, from, len);
+	flush_dcache_page(page);
 	kunmap_local(to);
 }
 
 static inline void memzero_page(struct page *page, size_t offset, size_t len)
 {
-	char *addr = kmap_atomic(page);
+	char *addr = kmap_local_page(page);
 	memset(addr + offset, 0, len);
-	kunmap_atomic(addr);
+	flush_dcache_page(page);
+	kunmap_local(addr);
 }
 
 #endif /* _LINUX_HIGHMEM_H */

include/linux/memblock.h

@@ -209,7 +209,7 @@ static inline void __next_physmem_range(u64 *idx, struct memblock_type *type,
  */
 #define for_each_mem_range(i, p_start, p_end) \
 	__for_each_mem_range(i, &memblock.memory, NULL, NUMA_NO_NODE,	\
-			     MEMBLOCK_NONE, p_start, p_end, NULL)
+			     MEMBLOCK_HOTPLUG, p_start, p_end, NULL)
 
 /**
  * for_each_mem_range_rev - reverse iterate through memblock areas from
@@ -220,7 +220,7 @@ static inline void __next_physmem_range(u64 *idx, struct memblock_type *type,
  */
 #define for_each_mem_range_rev(i, p_start, p_end)			\
 	__for_each_mem_range_rev(i, &memblock.memory, NULL, NUMA_NO_NODE, \
-				 MEMBLOCK_NONE, p_start, p_end, NULL)
+				 MEMBLOCK_HOTPLUG, p_start, p_end, NULL)
 
 /**
  * for_each_reserved_mem_range - iterate over all reserved memblock areas

mm/backing-dev.c

@@ -398,12 +398,12 @@ static void cgwb_release_workfn(struct work_struct *work)
 	blkcg_unpin_online(blkcg);
 
 	fprop_local_destroy_percpu(&wb->memcg_completions);
-	percpu_ref_exit(&wb->refcnt);
 
 	spin_lock_irq(&cgwb_lock);
 	list_del(&wb->offline_node);
 	spin_unlock_irq(&cgwb_lock);
 
+	percpu_ref_exit(&wb->refcnt);
 	wb_exit(wb);
 	WARN_ON_ONCE(!list_empty(&wb->b_attached));
 	kfree_rcu(wb, rcu);

mm/kfence/core.c

@@ -733,6 +733,22 @@ void kfence_shutdown_cache(struct kmem_cache *s)
 
 void *__kfence_alloc(struct kmem_cache *s, size_t size, gfp_t flags)
 {
+	/*
+	 * Perform size check before switching kfence_allocation_gate, so that
+	 * we don't disable KFENCE without making an allocation.
+	 */
+	if (size > PAGE_SIZE)
+		return NULL;
+
+	/*
+	 * Skip allocations from non-default zones, including DMA. We cannot
+	 * guarantee that pages in the KFENCE pool will have the requested
+	 * properties (e.g. reside in DMAable memory).
+	 */
+	if ((flags & GFP_ZONEMASK) ||
+	    (s->flags & (SLAB_CACHE_DMA | SLAB_CACHE_DMA32)))
+		return NULL;
+
 	/*
 	 * allocation_gate only needs to become non-zero, so it doesn't make
 	 * sense to continue writing to it and pay the associated contention
@@ -757,9 +773,6 @@ void *__kfence_alloc(struct kmem_cache *s, size_t size, gfp_t flags)
 	if (!READ_ONCE(kfence_enabled))
 		return NULL;
 
-	if (size > PAGE_SIZE)
-		return NULL;
-
 	return kfence_guarded_alloc(s, size, flags);
 }
 

mm/kfence/kfence_test.c

@@ -852,7 +852,7 @@ static void kfence_test_exit(void)
 	tracepoint_synchronize_unregister();
 }
 
-late_initcall(kfence_test_init);
+late_initcall_sync(kfence_test_init);
 module_exit(kfence_test_exit);
 
 MODULE_LICENSE("GPL v2");

mm/memblock.c

@@ -947,7 +947,8 @@ static bool should_skip_region(struct memblock_type *type,
 		return true;
 
 	/* skip hotpluggable memory regions if needed */
-	if (movable_node_is_enabled() && memblock_is_hotpluggable(m))
+	if (movable_node_is_enabled() && memblock_is_hotpluggable(m) &&
+	    !(flags & MEMBLOCK_HOTPLUG))
 		return true;
 
 	/* if we want mirror memory skip non-mirror memory regions */

mm/memory.c

@@ -4026,9 +4026,18 @@ vm_fault_t finish_fault(struct vm_fault *vmf)
 				return ret;
 		}
 
-		if (unlikely(pte_alloc(vma->vm_mm, vmf->pmd)))
+		if (vmf->prealloc_pte) {
+			vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd);
+			if (likely(pmd_none(*vmf->pmd))) {
+				mm_inc_nr_ptes(vma->vm_mm);
+				pmd_populate(vma->vm_mm, vmf->pmd, vmf->prealloc_pte);
+				vmf->prealloc_pte = NULL;
+			}
+			spin_unlock(vmf->ptl);
+		} else if (unlikely(pte_alloc(vma->vm_mm, vmf->pmd))) {
 			return VM_FAULT_OOM;
 		}
+	}
 
 	/* See comment in handle_pte_fault() */
 	if (pmd_devmap_trans_unstable(vmf->pmd))

mm/mmap_lock.c

@@ -156,14 +156,14 @@ static inline void put_memcg_path_buf(void)
 #define TRACE_MMAP_LOCK_EVENT(type, mm, ...)                                   \
 	do {                                                                   \
 		const char *memcg_path;                                        \
-		preempt_disable();                                             \
+		local_lock(&memcg_paths.lock);                                 \
 		memcg_path = get_mm_memcg_path(mm);                            \
 		trace_mmap_lock_##type(mm,                                     \
 				       memcg_path != NULL ? memcg_path : "",   \
 				       ##__VA_ARGS__);                         \
 		if (likely(memcg_path != NULL))                                \
 			put_memcg_path_buf();                                  \
-		preempt_enable();                                              \
+		local_unlock(&memcg_paths.lock);                               \
 	} while (0)
 
 #else /* !CONFIG_MEMCG */

mm/page_alloc.c

@@ -840,20 +840,23 @@ void init_mem_debugging_and_hardening(void)
 	}
 #endif
 
-	if (_init_on_alloc_enabled_early) {
-		if (page_poisoning_requested)
+	if ((_init_on_alloc_enabled_early || _init_on_free_enabled_early) &&
+	    page_poisoning_requested) {
 		pr_info("mem auto-init: CONFIG_PAGE_POISONING is on, "
-				"will take precedence over init_on_alloc\n");
-		else
-			static_branch_enable(&init_on_alloc);
+			"will take precedence over init_on_alloc and init_on_free\n");
+		_init_on_alloc_enabled_early = false;
+		_init_on_free_enabled_early = false;
 	}
-	if (_init_on_free_enabled_early) {
-		if (page_poisoning_requested)
-			pr_info("mem auto-init: CONFIG_PAGE_POISONING is on, "
-				"will take precedence over init_on_free\n");
+
+	if (_init_on_alloc_enabled_early)
+		static_branch_enable(&init_on_alloc);
 	else
+		static_branch_disable(&init_on_alloc);
+
+	if (_init_on_free_enabled_early)
 		static_branch_enable(&init_on_free);
-	}
+	else
+		static_branch_disable(&init_on_free);
 
 #ifdef CONFIG_DEBUG_PAGEALLOC
 	if (!debug_pagealloc_enabled())

mm/secretmem.c

@@ -152,6 +152,7 @@ static void secretmem_freepage(struct page *page)
 }
 
 const struct address_space_operations secretmem_aops = {
+	.set_page_dirty	= __set_page_dirty_no_writeback,
 	.freepage	= secretmem_freepage,
 	.migratepage	= secretmem_migratepage,
 	.isolate_page	= secretmem_isolate_page,

tools/testing/selftests/vm/userfaultfd.c

@@ -210,8 +210,10 @@ static void anon_release_pages(char *rel_area)
 
 static void anon_allocate_area(void **alloc_area)
 {
-	if (posix_memalign(alloc_area, page_size, nr_pages * page_size))
-		err("posix_memalign() failed");
+	*alloc_area = mmap(NULL, nr_pages * page_size, PROT_READ | PROT_WRITE,
+			   MAP_ANONYMOUS | MAP_PRIVATE, -1, 0);
+	if (*alloc_area == MAP_FAILED)
+		err("mmap of anonymous memory failed");
 }
 
 static void noop_alias_mapping(__u64 *start, size_t len, unsigned long offset)