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, 97 insertions, 36 deletions

diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c
index 0c1d33c4f74c1..07c81ab3fd4dd 100644
--- a/fs/userfaultfd.c
+++ b/fs/userfaultfd.c
@@ -30,6 +30,7 @@
 #include <linux/security.h>
 #include <linux/hugetlb.h>
 #include <linux/swapops.h>
+#include <linux/miscdevice.h>
 
 int sysctl_unprivileged_userfaultfd __read_mostly;
 
@@ -415,13 +416,8 @@ vm_fault_t handle_userfault(struct vm_fault *vmf, unsigned long reason)
 
 	if (ctx->features & UFFD_FEATURE_SIGBUS)
 		goto out;
-	if ((vmf->flags & FAULT_FLAG_USER) == 0 &&
-	    ctx->flags & UFFD_USER_MODE_ONLY) {
-		printk_once(KERN_WARNING "uffd: Set unprivileged_userfaultfd "
-			"sysctl knob to 1 if kernel faults must be handled "
-			"without obtaining CAP_SYS_PTRACE capability\n");
+	if (!(vmf->flags & FAULT_FLAG_USER) && (ctx->flags & UFFD_USER_MODE_ONLY))
 		goto out;
-	}
 
 	/*
 	 * If it's already released don't get it. This avoids to loop
@@ -615,14 +611,16 @@ static void userfaultfd_event_wait_completion(struct userfaultfd_ctx *ctx,
 	if (release_new_ctx) {
 		struct vm_area_struct *vma;
 		struct mm_struct *mm = release_new_ctx->mm;
+		VMA_ITERATOR(vmi, mm, 0);
 
 		/* the various vma->vm_userfaultfd_ctx still points to it */
 		mmap_write_lock(mm);
-		for (vma = mm->mmap; vma; vma = vma->vm_next)
+		for_each_vma(vmi, vma) {
 			if (vma->vm_userfaultfd_ctx.ctx == release_new_ctx) {
 				vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX;
 				vma->vm_flags &= ~__VM_UFFD_FLAGS;
 			}
+		}
 		mmap_write_unlock(mm);
 
 		userfaultfd_ctx_put(release_new_ctx);
@@ -803,11 +801,13 @@ static bool has_unmap_ctx(struct userfaultfd_ctx *ctx, struct list_head *unmaps,
 	return false;
 }
 
-int userfaultfd_unmap_prep(struct vm_area_struct *vma,
-			   unsigned long start, unsigned long end,
-			   struct list_head *unmaps)
+int userfaultfd_unmap_prep(struct mm_struct *mm, unsigned long start,
+			   unsigned long end, struct list_head *unmaps)
 {
-	for ( ; vma && vma->vm_start < end; vma = vma->vm_next) {
+	VMA_ITERATOR(vmi, mm, start);
+	struct vm_area_struct *vma;
+
+	for_each_vma_range(vmi, vma, end) {
 		struct userfaultfd_unmap_ctx *unmap_ctx;
 		struct userfaultfd_ctx *ctx = vma->vm_userfaultfd_ctx.ctx;
 
@@ -857,6 +857,7 @@ static int userfaultfd_release(struct inode *inode, struct file *file)
 	/* len == 0 means wake all */
 	struct userfaultfd_wake_range range = { .len = 0, };
 	unsigned long new_flags;
+	MA_STATE(mas, &mm->mm_mt, 0, 0);
 
 	WRITE_ONCE(ctx->released, true);
 
@@ -873,7 +874,7 @@ static int userfaultfd_release(struct inode *inode, struct file *file)
 	 */
 	mmap_write_lock(mm);
 	prev = NULL;
-	for (vma = mm->mmap; vma; vma = vma->vm_next) {
+	mas_for_each(&mas, vma, ULONG_MAX) {
 		cond_resched();
 		BUG_ON(!!vma->vm_userfaultfd_ctx.ctx ^
 		       !!(vma->vm_flags & __VM_UFFD_FLAGS));
@@ -887,10 +888,13 @@ static int userfaultfd_release(struct inode *inode, struct file *file)
 				 vma->vm_file, vma->vm_pgoff,
 				 vma_policy(vma),
 				 NULL_VM_UFFD_CTX, anon_vma_name(vma));
-		if (prev)
+		if (prev) {
+			mas_pause(&mas);
 			vma = prev;
-		else
+		} else {
 			prev = vma;
+		}
+
 		vma->vm_flags = new_flags;
 		vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX;
 	}
@@ -1272,6 +1276,7 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx,
 	bool found;
 	bool basic_ioctls;
 	unsigned long start, end, vma_end;
+	MA_STATE(mas, &mm->mm_mt, 0, 0);
 
 	user_uffdio_register = (struct uffdio_register __user *) arg;
 
@@ -1314,7 +1319,8 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx,
 		goto out;
 
 	mmap_write_lock(mm);
-	vma = find_vma_prev(mm, start, &prev);
+	mas_set(&mas, start);
+	vma = mas_find(&mas, ULONG_MAX);
 	if (!vma)
 		goto out_unlock;
 
@@ -1339,7 +1345,7 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx,
 	 */
 	found = false;
 	basic_ioctls = false;
-	for (cur = vma; cur && cur->vm_start < end; cur = cur->vm_next) {
+	for (cur = vma; cur; cur = mas_next(&mas, end - 1)) {
 		cond_resched();
 
 		BUG_ON(!!cur->vm_userfaultfd_ctx.ctx ^
@@ -1399,8 +1405,10 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx,
 	}
 	BUG_ON(!found);
 
-	if (vma->vm_start < start)
-		prev = vma;
+	mas_set(&mas, start);
+	prev = mas_prev(&mas, 0);
+	if (prev != vma)
+		mas_next(&mas, ULONG_MAX);
 
 	ret = 0;
 	do {
@@ -1430,6 +1438,8 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx,
 				 ((struct vm_userfaultfd_ctx){ ctx }),
 				 anon_vma_name(vma));
 		if (prev) {
+			/* vma_merge() invalidated the mas */
+			mas_pause(&mas);
 			vma = prev;
 			goto next;
 		}
@@ -1437,11 +1447,15 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx,
 			ret = split_vma(mm, vma, start, 1);
 			if (ret)
 				break;
+			/* split_vma() invalidated the mas */
+			mas_pause(&mas);
 		}
 		if (vma->vm_end > end) {
 			ret = split_vma(mm, vma, end, 0);
 			if (ret)
 				break;
+			/* split_vma() invalidated the mas */
+			mas_pause(&mas);
 		}
 	next:
 		/*
@@ -1458,8 +1472,8 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx,
 	skip:
 		prev = vma;
 		start = vma->vm_end;
-		vma = vma->vm_next;
-	} while (vma && vma->vm_start < end);
+		vma = mas_next(&mas, end - 1);
+	} while (vma);
 out_unlock:
 	mmap_write_unlock(mm);
 	mmput(mm);
@@ -1503,6 +1517,7 @@ static int userfaultfd_unregister(struct userfaultfd_ctx *ctx,
 	bool found;
 	unsigned long start, end, vma_end;
 	const void __user *buf = (void __user *)arg;
+	MA_STATE(mas, &mm->mm_mt, 0, 0);
 
 	ret = -EFAULT;
 	if (copy_from_user(&uffdio_unregister, buf, sizeof(uffdio_unregister)))
@@ -1521,7 +1536,8 @@ static int userfaultfd_unregister(struct userfaultfd_ctx *ctx,
 		goto out;
 
 	mmap_write_lock(mm);
-	vma = find_vma_prev(mm, start, &prev);
+	mas_set(&mas, start);
+	vma = mas_find(&mas, ULONG_MAX);
 	if (!vma)
 		goto out_unlock;
 
@@ -1546,7 +1562,7 @@ static int userfaultfd_unregister(struct userfaultfd_ctx *ctx,
 	 */
 	found = false;
 	ret = -EINVAL;
-	for (cur = vma; cur && cur->vm_start < end; cur = cur->vm_next) {
+	for (cur = vma; cur; cur = mas_next(&mas, end - 1)) {
 		cond_resched();
 
 		BUG_ON(!!cur->vm_userfaultfd_ctx.ctx ^
@@ -1566,8 +1582,10 @@ static int userfaultfd_unregister(struct userfaultfd_ctx *ctx,
 	}
 	BUG_ON(!found);
 
-	if (vma->vm_start < start)
-		prev = vma;
+	mas_set(&mas, start);
+	prev = mas_prev(&mas, 0);
+	if (prev != vma)
+		mas_next(&mas, ULONG_MAX);
 
 	ret = 0;
 	do {
@@ -1636,8 +1654,8 @@ static int userfaultfd_unregister(struct userfaultfd_ctx *ctx,
 	skip:
 		prev = vma;
 		start = vma->vm_end;
-		vma = vma->vm_next;
-	} while (vma && vma->vm_start < end);
+		vma = mas_next(&mas, end - 1);
+	} while (vma);
 out_unlock:
 	mmap_write_unlock(mm);
 	mmput(mm);
@@ -2056,20 +2074,11 @@ static void init_once_userfaultfd_ctx(void *mem)
 	seqcount_spinlock_init(&ctx->refile_seq, &ctx->fault_pending_wqh.lock);
 }
 
-SYSCALL_DEFINE1(userfaultfd, int, flags)
+static int new_userfaultfd(int flags)
 {
 	struct userfaultfd_ctx *ctx;
 	int fd;
 
-	if (!sysctl_unprivileged_userfaultfd &&
-	    (flags & UFFD_USER_MODE_ONLY) == 0 &&
-	    !capable(CAP_SYS_PTRACE)) {
-		printk_once(KERN_WARNING "uffd: Set unprivileged_userfaultfd "
-			"sysctl knob to 1 if kernel faults must be handled "
-			"without obtaining CAP_SYS_PTRACE capability\n");
-		return -EPERM;
-	}
-
 	BUG_ON(!current->mm);
 
 	/* Check the UFFD_* constants for consistency.  */
@@ -2102,8 +2111,60 @@ SYSCALL_DEFINE1(userfaultfd, int, flags)
 	return fd;
 }
 
+static inline bool userfaultfd_syscall_allowed(int flags)
+{
+	/* Userspace-only page faults are always allowed */
+	if (flags & UFFD_USER_MODE_ONLY)
+		return true;
+
+	/*
+	 * The user is requesting a userfaultfd which can handle kernel faults.
+	 * Privileged users are always allowed to do this.
+	 */
+	if (capable(CAP_SYS_PTRACE))
+		return true;
+
+	/* Otherwise, access to kernel fault handling is sysctl controlled. */
+	return sysctl_unprivileged_userfaultfd;
+}
+
+SYSCALL_DEFINE1(userfaultfd, int, flags)
+{
+	if (!userfaultfd_syscall_allowed(flags))
+		return -EPERM;
+
+	return new_userfaultfd(flags);
+}
+
+static long userfaultfd_dev_ioctl(struct file *file, unsigned int cmd, unsigned long flags)
+{
+	if (cmd != USERFAULTFD_IOC_NEW)
+		return -EINVAL;
+
+	return new_userfaultfd(flags);
+}
+
+static const struct file_operations userfaultfd_dev_fops = {
+	.unlocked_ioctl = userfaultfd_dev_ioctl,
+	.compat_ioctl = userfaultfd_dev_ioctl,
+	.owner = THIS_MODULE,
+	.llseek = noop_llseek,
+};
+
+static struct miscdevice userfaultfd_misc = {
+	.minor = MISC_DYNAMIC_MINOR,
+	.name = "userfaultfd",
+	.fops = &userfaultfd_dev_fops
+};
+
 static int __init userfaultfd_init(void)
 {
+	int ret;
+
+	ret = misc_register(&userfaultfd_misc);
+	if (ret)
+		return ret;
+
 	userfaultfd_ctx_cachep = kmem_cache_create("userfaultfd_ctx_cache",
 						sizeof(struct userfaultfd_ctx),
 						0,