[PATCH v1 5/6] PKEY: Apply PKEY_ENFORCE_API to munmap

[jeffxu]

From: Jeff Xu <jeffxu@xxxxxxxxxx>

This patch enables PKEY_ENFORCE_API for the munmap
syscall.

Signed-off-by: Jeff Xu<jeffxu@xxxxxxxxxx>
---
 include/linux/mm.h |  8 +++++++-
 mm/mmap.c          | 31 +++++++++++++++++++++++--------
 mm/mremap.c        |  6 ++++--
 3 files changed, 34 insertions(+), 11 deletions(-)

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 27ce77080c79..795cdeee2ea7 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -429,6 +429,12 @@ extern unsigned int kobjsize(const void *objp);
 #endif
 #define VM_FLAGS_CLEAR	(ARCH_VM_PKEY_FLAGS | VM_ARCH_CLEAR)
 
+/* The current call stack is originated from user space or kernel */
+enum caller_origin {
+	ON_BEHALF_OF_KERNEL = 0,
+	ON_BEHALF_OF_USERSPACE,
+};
+
 /*
  * mapping from the currently active vm_flags protection bits (the
  * low four bits) to a page protection mask..
@@ -3136,7 +3142,7 @@ extern unsigned long do_mmap(struct file *file, unsigned long addr,
 	unsigned long pgoff, unsigned long *populate, struct list_head *uf);
 extern int do_vmi_munmap(struct vma_iterator *vmi, struct mm_struct *mm,
 			 unsigned long start, size_t len, struct list_head *uf,
-			 bool downgrade);
+			 bool downgrade, enum caller_origin called);
 extern int do_munmap(struct mm_struct *, unsigned long, size_t,
 		     struct list_head *uf);
 extern int do_madvise(struct mm_struct *mm, unsigned long start, size_t len_in, int behavior);
diff --git a/mm/mmap.c b/mm/mmap.c
index 13678edaa22c..3de95a6a4397 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -2498,6 +2498,7 @@ do_vmi_align_munmap(struct vma_iterator *vmi, struct vm_area_struct *vma,
  * @uf: The userfaultfd list_head
  * @downgrade: set to true if the user wants to attempt to write_downgrade the
  * mmap_lock
+ * @called: originated from user space or kernel
  *
  * This function takes a @mas that is either pointing to the previous VMA or set
  * to MA_START and sets it up to remove the mapping(s).  The @len will be
@@ -2507,7 +2508,7 @@ do_vmi_align_munmap(struct vma_iterator *vmi, struct vm_area_struct *vma,
  */
 int do_vmi_munmap(struct vma_iterator *vmi, struct mm_struct *mm,
 		  unsigned long start, size_t len, struct list_head *uf,
-		  bool downgrade)
+		  bool downgrade, enum caller_origin called)
 {
 	unsigned long end;
 	struct vm_area_struct *vma;
@@ -2519,6 +2520,15 @@ int do_vmi_munmap(struct vma_iterator *vmi, struct mm_struct *mm,
 	if (end == start)
 		return -EINVAL;
 
+	/*
+	 * When called by syscall from userspace, check if the calling
+	 * thread has the PKEY permission to modify the memory mapping.
+	 */
+	if (called == ON_BEHALF_OF_USERSPACE &&
+		arch_check_pkey_enforce_api(mm, start, end) < 0) {
+		return -EACCES;
+	}
+
 	 /* arch_unmap() might do unmaps itself.  */
 	arch_unmap(mm, start, end);
 
@@ -2541,7 +2551,7 @@ int do_munmap(struct mm_struct *mm, unsigned long start, size_t len,
 {
 	VMA_ITERATOR(vmi, mm, start);
 
-	return do_vmi_munmap(&vmi, mm, start, len, uf, false);
+	return do_vmi_munmap(&vmi, mm, start, len, uf, false, ON_BEHALF_OF_KERNEL);
 }
 
 unsigned long mmap_region(struct file *file, unsigned long addr,
@@ -2575,7 +2585,8 @@ unsigned long mmap_region(struct file *file, unsigned long addr,
 	}
 
 	/* Unmap any existing mapping in the area */
-	if (do_vmi_munmap(&vmi, mm, addr, len, uf, false))
+	if (do_vmi_munmap(&vmi, mm, addr, len, uf, false,
+			ON_BEHALF_OF_KERNEL))
 		return -ENOMEM;
 
 	/*
@@ -2792,7 +2803,11 @@ unsigned long mmap_region(struct file *file, unsigned long addr,
 	return error;
 }
 
-static int __vm_munmap(unsigned long start, size_t len, bool downgrade)
+/*
+ * @called: originated from user space or kernel
+ */
+static int __vm_munmap(unsigned long start, size_t len, bool downgrade,
+			enum caller_origin called)
 {
 	int ret;
 	struct mm_struct *mm = current->mm;
@@ -2802,7 +2817,7 @@ static int __vm_munmap(unsigned long start, size_t len, bool downgrade)
 	if (mmap_write_lock_killable(mm))
 		return -EINTR;
 
-	ret = do_vmi_munmap(&vmi, mm, start, len, &uf, downgrade);
+	ret = do_vmi_munmap(&vmi, mm, start, len, &uf, downgrade, called);
 	/*
 	 * Returning 1 indicates mmap_lock is downgraded.
 	 * But 1 is not legal return value of vm_munmap() and munmap(), reset
@@ -2820,14 +2835,14 @@ static int __vm_munmap(unsigned long start, size_t len, bool downgrade)
 
 int vm_munmap(unsigned long start, size_t len)
 {
-	return __vm_munmap(start, len, false);
+	return __vm_munmap(start, len, false, ON_BEHALF_OF_KERNEL);
 }
 EXPORT_SYMBOL(vm_munmap);
 
 SYSCALL_DEFINE2(munmap, unsigned long, addr, size_t, len)
 {
 	addr = untagged_addr(addr);
-	return __vm_munmap(addr, len, true);
+	return __vm_munmap(addr, len, true, ON_BEHALF_OF_USERSPACE);
 }
 
 
@@ -3055,7 +3070,7 @@ int vm_brk_flags(unsigned long addr, unsigned long request, unsigned long flags)
 	if (ret)
 		goto limits_failed;
 
-	ret = do_vmi_munmap(&vmi, mm, addr, len, &uf, 0);
+	ret = do_vmi_munmap(&vmi, mm, addr, len, &uf, 0, ON_BEHALF_OF_KERNEL);
 	if (ret)
 		goto munmap_failed;
 
diff --git a/mm/mremap.c b/mm/mremap.c
index b11ce6c92099..a3f576effbb1 100644
--- a/mm/mremap.c
+++ b/mm/mremap.c
@@ -703,7 +703,8 @@ static unsigned long move_vma(struct vm_area_struct *vma,
 	}
 
 	vma_iter_init(&vmi, mm, old_addr);
-	if (do_vmi_munmap(&vmi, mm, old_addr, old_len, uf_unmap, false) < 0) {
+	if (do_vmi_munmap(&vmi, mm, old_addr, old_len, uf_unmap, false,
+				ON_BEHALF_OF_KERNEL) < 0) {
 		/* OOM: unable to split vma, just get accounts right */
 		if (vm_flags & VM_ACCOUNT && !(flags & MREMAP_DONTUNMAP))
 			vm_acct_memory(old_len >> PAGE_SHIFT);
@@ -993,7 +994,8 @@ SYSCALL_DEFINE5(mremap, unsigned long, addr, unsigned long, old_len,
 		VMA_ITERATOR(vmi, mm, addr + new_len);
 
 		retval = do_vmi_munmap(&vmi, mm, addr + new_len,
-				       old_len - new_len, &uf_unmap, true);
+				       old_len - new_len, &uf_unmap, true,
+				       ON_BEHALF_OF_KERNEL);
 		/* Returning 1 indicates mmap_lock is downgraded to read. */
 		if (retval == 1) {
 			downgraded = true;
-- 
2.40.1.606.ga4b1b128d6-goog