vfs: Test for and handle paths that are unreachable from their mnt_root

index 0d766d2..6551acb 100644
@@ -434,6 +434,24 @@ static struct dentry * cached_lookup(struct dentry * parent, struct qstr * name,
 	return dentry;
 }
 
+/**
+ * path_connected - Verify that a path->dentry is below path->mnt.mnt_root
+ * @path: nameidate to verify
+ *
+ * Rename can sometimes move a file or directory outside of a bind
+ * mount, path_connected allows those cases to be detected.
+ */
+static bool path_connected(const struct path *path)
+{
+	struct vfsmount *mnt = path->mnt;
+
+	/* Only bind mounts can have disconnected paths */
+	if (mnt->mnt_root == mnt->mnt_sb->s_root)
+		return true;
+
+	return is_subdir(path->dentry, mnt->mnt_root);
+}
+
 /*
  * Short-cut version of permission(), for calling by
  * path_walk(), when dcache lock is held.  Combines parts

@@ -754,7 +772,7 @@ int follow_down(struct path *path)
 	return 0;
 }
 
-static __always_inline void follow_dotdot(struct nameidata *nd)
+static __always_inline int follow_dotdot(struct nameidata *nd)
 {
 	set_root(nd);
 

@@ -771,6 +789,8 @@ static __always_inline void follow_dotdot(struct nameidata *nd)
 			nd->path.dentry = dget(nd->path.dentry->d_parent);
 			spin_unlock(&dcache_lock);
 			dput(old);
+			if (unlikely(!path_connected(&nd->path)))
+				return -ENOENT;
 			break;
 		}
 		spin_unlock(&dcache_lock);

@@ -788,6 +808,7 @@ static __always_inline void follow_dotdot(struct nameidata *nd)
 		nd->path.mnt = parent;
 	}
 	follow_mount(&nd->path);
+	return 0;
 }
 
 /*

@@ -905,7 +926,9 @@ static int __link_path_walk(const char *name, struct nameidata *nd)
 			case 2:	
 				if (this.name[1] != '.')
 					break;
-				follow_dotdot(nd);
+				err = follow_dotdot(nd);
+				if (err < 0)
+					goto out_nd_path_put;
 				inode = nd->path.dentry->d_inode;
 				/* fallthrough */
 			case 1:

@@ -960,7 +983,9 @@ last_component:
 			case 2:	
 				if (this.name[1] != '.')
 					break;
-				follow_dotdot(nd);
+				err = follow_dotdot(nd);
+				if (err < 0)
+					goto out_nd_path_put;
 				inode = nd->path.dentry->d_inode;
 				/* fallthrough */
 			case 1:

@@ -1022,6 +1047,7 @@ out_dput:
 		path_put_conditional(&next, nd);
 		break;
 	}
+out_nd_path_put:
 	path_put(&nd->path);
 return_err:
 	return err;

index 73db5a6..36c1edf 100644
@@ -8,6 +8,7 @@
 #include <linux/mempolicy.h>
 #include <linux/swap.h>
 #include <linux/swapops.h>
+#include <linux/security.h>
 
 #include <asm/elf.h>
 #include <asm/uaccess.h>

@@ -539,6 +540,7 @@ const struct file_operations proc_clear_refs_operations = {
 
 struct pagemapread {
 	u64 __user *out, *end;
+	bool show_pfn;
 };
 
 #define PM_ENTRY_BYTES      sizeof(u64)

@@ -589,14 +591,14 @@ static u64 swap_pte_to_pagemap_entry(pte_t pte)
 	return swp_type(e) | (swp_offset(e) << MAX_SWAPFILES_SHIFT);
 }
 
-static u64 pte_to_pagemap_entry(pte_t pte)
+static u64 pte_to_pagemap_entry(struct pagemapread *pm, pte_t pte)
 {
 	u64 pme = 0;
 	if (is_swap_pte(pte))
 		pme = PM_PFRAME(swap_pte_to_pagemap_entry(pte))
 			| PM_PSHIFT(PAGE_SHIFT) | PM_SWAP;
 	else if (pte_present(pte))
-		pme = PM_PFRAME(pte_pfn(pte))
+		pme = (pm->show_pfn ? PM_PFRAME(pte_pfn(pte)) : 0)
 			| PM_PSHIFT(PAGE_SHIFT) | PM_PRESENT;
 	return pme;
 }

@@ -624,7 +626,7 @@ static int pagemap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
 		if (vma && (vma->vm_start <= addr) &&
 		    !is_vm_hugetlb_page(vma)) {
 			pte = pte_offset_map(pmd, addr);
-			pfn = pte_to_pagemap_entry(*pte);
+			pfn = pte_to_pagemap_entry(pm, *pte);
 			/* unmap before userspace copy */
 			pte_unmap(pte);
 		}

@@ -695,6 +697,9 @@ static ssize_t pagemap_read(struct file *file, char __user *buf,
 	if (!count)
 		goto out_task;
 
+	/* do not disclose physical addresses: attack vector */
+	pm.show_pfn = !security_capable(file->f_cred, CAP_SYS_ADMIN);
+
 	mm = get_task_mm(task);
 	if (!mm)
 		goto out_task;

@@ -773,19 +778,9 @@ out:
 	return ret;
 }
 
-static int pagemap_open(struct inode *inode, struct file *file)
-{
-	/* do not disclose physical addresses to unprivileged
-	   userspace (closes a rowhammer attack vector) */
-	if (!capable(CAP_SYS_ADMIN))
-		return -EPERM;
-	return 0;
-}
-
 const struct file_operations proc_pagemap_operations = {
 	.llseek		= mem_lseek, /* borrow this */
 	.read		= pagemap_read,
-	.open		= pagemap_open,
 };
 #endif /* CONFIG_PROC_PAGE_MONITOR */
 

index d40d23f..73ebc3f 100644
@@ -1733,7 +1733,7 @@ int security_capset(struct cred *new, const struct cred *old,
 		    const kernel_cap_t *effective,
 		    const kernel_cap_t *inheritable,
 		    const kernel_cap_t *permitted);
-int security_capable(int cap);
+int security_capable(const struct cred *cred, int cap);
 int security_real_capable(struct task_struct *tsk, int cap);
 int security_real_capable_noaudit(struct task_struct *tsk, int cap);
 int security_acct(struct file *file);

@@ -1938,9 +1938,9 @@ static inline int security_capset(struct cred *new,
 	return cap_capset(new, old, effective, inheritable, permitted);
 }
 
-static inline int security_capable(int cap)
+static inline int security_capable(const struct cred *cred, int cap)
 {
-	return cap_capable(current, current_cred(), cap, SECURITY_CAP_AUDIT);
+	return cap_capable(current, cred, cap, SECURITY_CAP_AUDIT);
 }
 
 static inline int security_real_capable(struct task_struct *tsk, int cap)

index 8a944f5..771618c 100644
@@ -305,7 +305,7 @@ int capable(int cap)
 		BUG();
 	}
 
-	if (security_capable(cap) == 0) {
+	if (security_capable(current_cred(), cap) == 0) {
 		current->flags |= PF_SUPERPRIV;
 		return 1;
 	}

index c4c6732..227b173 100644
@@ -151,10 +151,9 @@ int security_capset(struct cred *new, const struct cred *old,
 				    effective, inheritable, permitted);
 }
 
-int security_capable(int cap)
+int security_capable(const struct cred *cred, int cap)
 {
-	return security_ops->capable(current, current_cred(), cap,
-				     SECURITY_CAP_AUDIT);
+	return security_ops->capable(current, cred, cap, SECURITY_CAP_AUDIT);
 }
 
 int security_real_capable(struct task_struct *tsk, int cap)