1 files changed, 131 insertions, 70 deletions

diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c
index 22bf14ab2d16..98ac37e34e3d 100644
--- a/fs/userfaultfd.c
+++ b/fs/userfaultfd.c
@@ -15,6 +15,7 @@
 #include <linux/sched/signal.h>
 #include <linux/sched/mm.h>
 #include <linux/mm.h>
+#include <linux/mm_inline.h>
 #include <linux/mmu_notifier.h>
 #include <linux/poll.h>
 #include <linux/slab.h>
@@ -28,6 +29,8 @@
 #include <linux/ioctl.h>
 #include <linux/security.h>
 #include <linux/hugetlb.h>
+#include <linux/swapops.h>
+#include <linux/miscdevice.h>
 
 int sysctl_unprivileged_userfaultfd __read_mostly;
 
@@ -190,14 +193,19 @@ static inline void msg_init(struct uffd_msg *msg)
 }
 
 static inline struct uffd_msg userfault_msg(unsigned long address,
+					    unsigned long real_address,
 					    unsigned int flags,
 					    unsigned long reason,
 					    unsigned int features)
 {
 	struct uffd_msg msg;
+
 	msg_init(&msg);
 	msg.event = UFFD_EVENT_PAGEFAULT;
-	msg.arg.pagefault.address = address;
+
+	msg.arg.pagefault.address = (features & UFFD_FEATURE_EXACT_ADDRESS) ?
+				    real_address : address;
+
 	/*
 	 * These flags indicate why the userfault occurred:
 	 * - UFFD_PAGEFAULT_FLAG_WP indicates a write protect fault.
@@ -245,9 +253,10 @@ static inline bool userfaultfd_huge_must_wait(struct userfaultfd_ctx *ctx,
 
 	/*
 	 * Lockless access: we're in a wait_event so it's ok if it
-	 * changes under us.
+	 * changes under us.  PTE markers should be handled the same as none
+	 * ptes here.
 	 */
-	if (huge_pte_none(pte))
+	if (huge_pte_none_mostly(pte))
 		ret = true;
 	if (!huge_pte_write(pte) && (reason & VM_UFFD_WP))
 		ret = true;
@@ -326,9 +335,10 @@ static inline bool userfaultfd_must_wait(struct userfaultfd_ctx *ctx,
 	pte = pte_offset_map(pmd, address);
 	/*
 	 * Lockless access: we're in a wait_event so it's ok if it
-	 * changes under us.
+	 * changes under us.  PTE markers should be handled the same as none
+	 * ptes here.
 	 */
-	if (pte_none(*pte))
+	if (pte_none_mostly(*pte))
 		ret = true;
 	if (!pte_write(*pte) && (reason & VM_UFFD_WP))
 		ret = true;
@@ -406,13 +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
@@ -481,8 +486,8 @@ vm_fault_t handle_userfault(struct vm_fault *vmf, unsigned long reason)
 
 	init_waitqueue_func_entry(&uwq.wq, userfaultfd_wake_function);
 	uwq.wq.private = current;
-	uwq.msg = userfault_msg(vmf->address, vmf->flags, reason,
-			ctx->features);
+	uwq.msg = userfault_msg(vmf->address, vmf->real_address, vmf->flags,
+				reason, ctx->features);
 	uwq.ctx = ctx;
 	uwq.waken = false;
 
@@ -606,14 +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);
@@ -794,11 +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;
 
@@ -848,6 +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);
 
@@ -864,7 +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));
@@ -877,11 +887,14 @@ static int userfaultfd_release(struct inode *inode, struct file *file)
 				 new_flags, vma->anon_vma,
 				 vma->vm_file, vma->vm_pgoff,
 				 vma_policy(vma),
-				 NULL_VM_UFFD_CTX);
-		if (prev)
+				 NULL_VM_UFFD_CTX, anon_vma_name(vma));
+		if (prev) {
+			mas_pause(&mas);
 			vma = prev;
-		else
+		} else {
 			prev = vma;
+		}
+
 		vma->vm_flags = new_flags;
 		vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX;
 	}
@@ -982,7 +995,7 @@ static int resolve_userfault_fork(struct userfaultfd_ctx *new,
 	int fd;
 
 	fd = anon_inode_getfd_secure("[userfaultfd]", &userfaultfd_fops, new,
-			O_RDWR | (new->flags & UFFD_SHARED_FCNTL_FLAGS), inode);
+			O_RDONLY | (new->flags & UFFD_SHARED_FCNTL_FLAGS), inode);
 	if (fd < 0)
 		return fd;
 
@@ -1251,24 +1264,6 @@ static __always_inline int validate_range(struct mm_struct *mm,
 	return 0;
 }
 
-static inline bool vma_can_userfault(struct vm_area_struct *vma,
-				     unsigned long vm_flags)
-{
-	/* FIXME: add WP support to hugetlbfs and shmem */
-	if (vm_flags & VM_UFFD_WP) {
-		if (is_vm_hugetlb_page(vma) || vma_is_shmem(vma))
-			return false;
-	}
-
-	if (vm_flags & VM_UFFD_MINOR) {
-		if (!(is_vm_hugetlb_page(vma) || vma_is_shmem(vma)))
-			return false;
-	}
-
-	return vma_is_anonymous(vma) || is_vm_hugetlb_page(vma) ||
-	       vma_is_shmem(vma);
-}
-
 static int userfaultfd_register(struct userfaultfd_ctx *ctx,
 				unsigned long arg)
 {
@@ -1281,6 +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;
 
@@ -1323,7 +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;
 
@@ -1348,7 +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 ^
@@ -1408,8 +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 {
@@ -1436,8 +1435,11 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx,
 		prev = vma_merge(mm, prev, start, vma_end, new_flags,
 				 vma->anon_vma, vma->vm_file, vma->vm_pgoff,
 				 vma_policy(vma),
-				 ((struct vm_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;
 		}
@@ -1445,11 +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:
 		/*
@@ -1466,8 +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);
@@ -1511,6 +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)))
@@ -1529,7 +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;
 
@@ -1554,7 +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 ^
@@ -1574,8 +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 {
@@ -1609,24 +1619,31 @@ static int userfaultfd_unregister(struct userfaultfd_ctx *ctx,
 			wake_userfault(vma->vm_userfaultfd_ctx.ctx, &range);
 		}
 
+		/* Reset ptes for the whole vma range if wr-protected */
+		if (userfaultfd_wp(vma))
+			uffd_wp_range(mm, vma, start, vma_end - start, false);
+
 		new_flags = vma->vm_flags & ~__VM_UFFD_FLAGS;
 		prev = vma_merge(mm, prev, start, vma_end, new_flags,
 				 vma->anon_vma, vma->vm_file, vma->vm_pgoff,
 				 vma_policy(vma),
-				 NULL_VM_UFFD_CTX);
+				 NULL_VM_UFFD_CTX, anon_vma_name(vma));
 		if (prev) {
 			vma = prev;
+			mas_pause(&mas);
 			goto next;
 		}
 		if (vma->vm_start < start) {
 			ret = split_vma(mm, vma, start, 1);
 			if (ret)
 				break;
+			mas_pause(&mas);
 		}
 		if (vma->vm_end > end) {
 			ret = split_vma(mm, vma, end, 0);
 			if (ret)
 				break;
+			mas_pause(&mas);
 		}
 	next:
 		/*
@@ -1640,8 +1657,8 @@ 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);
@@ -1933,10 +1950,8 @@ static int userfaultfd_api(struct userfaultfd_ctx *ctx,
 	ret = -EFAULT;
 	if (copy_from_user(&uffdio_api, buf, sizeof(uffdio_api)))
 		goto out;
-	features = uffdio_api.features;
-	ret = -EINVAL;
-	if (uffdio_api.api != UFFD_API || (features & ~UFFD_API_FEATURES))
-		goto err_out;
+	/* Ignore unsupported features (userspace built against newer kernel) */
+	features = uffdio_api.features & UFFD_API_FEATURES;
 	ret = -EPERM;
 	if ((features & UFFD_FEATURE_EVENT_FORK) && !capable(CAP_SYS_PTRACE))
 		goto err_out;
@@ -1949,6 +1964,9 @@ static int userfaultfd_api(struct userfaultfd_ctx *ctx,
 #ifndef CONFIG_HAVE_ARCH_USERFAULTFD_WP
 	uffdio_api.features &= ~UFFD_FEATURE_PAGEFAULT_FLAG_WP;
 #endif
+#ifndef CONFIG_PTE_MARKER_UFFD_WP
+	uffdio_api.features &= ~UFFD_FEATURE_WP_HUGETLBFS_SHMEM;
+#endif
 	uffdio_api.ioctls = UFFD_API_IOCTLS;
 	ret = -EFAULT;
 	if (copy_to_user(buf, &uffdio_api, sizeof(uffdio_api)))
@@ -2059,20 +2077,11 @@ 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.  */
@@ -2097,7 +2106,7 @@ SYSCALL_DEFINE1(userfaultfd, int, flags)
 	mmgrab(ctx->mm);
 
 	fd = anon_inode_getfd_secure("[userfaultfd]", &userfaultfd_fops, ctx,
-			O_RDWR | (flags & UFFD_SHARED_FCNTL_FLAGS), NULL);
+			O_RDONLY | (flags & UFFD_SHARED_FCNTL_FLAGS), NULL);
 	if (fd < 0) {
 		mmdrop(ctx->mm);
 		kmem_cache_free(userfaultfd_ctx_cachep, ctx);
@@ -2105,8 +2114,60 @@ 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,