mm/vma: convert __mmap_region() to use vma_flags_t

Update the mmap() implementation logic implemented in __mmap_region() and
functions invoked by it.  The mmap_region() function converts its input
vm_flags_t parameter to a vma_flags_t value which it then passes to
__mmap_region() which uses the vma_flags_t value consistently from then
on.

As part of the change, we convert map_deny_write_exec() to using
vma_flags_t (it was incorrectly using unsigned long before), and place it
in vma.h, as it is only used internal to mm.

With this change, we eliminate the legacy is_shared_maywrite_vm_flags()
helper function which is now no longer required.

We are also able to update the MMAP_STATE() and VMG_MMAP_STATE() macros to
use the vma_flags_t value.

Finally, we update the VMA tests to reflect the change.

Link: https://lkml.kernel.org/r/1fc33a404c962f02da778da100387cc19bd62153.1774034900.git.ljs@kernel.org
Signed-off-by: Lorenzo Stoakes (Oracle) <ljs@kernel.org>
Acked-by: Vlastimil Babka (SUSE) <vbabka@kernel.org>
Cc: Albert Ou <aou@eecs.berkeley.edu>
Cc: Alexander Gordeev <agordeev@linux.ibm.com>
Cc: Alexandre Ghiti <alex@ghiti.fr>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Anton Ivanov <anton.ivanov@cambridgegreys.com>
Cc: "Borislav Petkov (AMD)" <bp@alien8.de>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Chengming Zhou <chengming.zhou@linux.dev>
Cc: Christian Borntraeger <borntraeger@linux.ibm.com>
Cc: Christian Brauner <brauner@kernel.org>
Cc: David Hildenbrand <david@kernel.org>
Cc: Dinh Nguyen <dinguyen@kernel.org>
Cc: Heiko Carstens <hca@linux.ibm.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Huacai Chen <chenhuacai@kernel.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jan Kara <jack@suse.cz>
Cc: Jann Horn <jannh@google.com>
Cc: Johannes Berg <johannes@sipsolutions.net>
Cc: Kees Cook <kees@kernel.org>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: Madhavan Srinivasan <maddy@linux.ibm.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Mike Rapoport <rppt@kernel.org>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: Ondrej Mosnacek <omosnace@redhat.com>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Cc: Paul Moore <paul@paul-moore.com>
Cc: Pedro Falcato <pfalcato@suse.de>
Cc: Richard Weinberger <richard@nod.at>
Cc: Russell King <linux@armlinux.org.uk>
Cc: Stephen Smalley <stephen.smalley.work@gmail.com>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Sven Schnelle <svens@linux.ibm.com>
Cc: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Cc: Vineet Gupta <vgupta@kernel.org>
Cc: WANG Xuerui <kernel@xen0n.name>
Cc: Will Deacon <will@kernel.org>
Cc: xu xin <xu.xin16@zte.com.cn>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

3 files changed, 67 insertions, 13 deletions

diff --git a/mm/mprotect.c b/mm/mprotect.c
index 941f1211da0d..007d9a72b2f0 100644
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -882,6 +882,7 @@ static int do_mprotect_pkey(unsigned long start, size_t len,
 	tmp = vma->vm_start;
 	for_each_vma_range(vmi, vma, end) {
 		vm_flags_t mask_off_old_flags;
+		vma_flags_t new_vma_flags;
 		vm_flags_t newflags;
 		int new_vma_pkey;
 
@@ -904,6 +905,7 @@ static int do_mprotect_pkey(unsigned long start, size_t len,
 		new_vma_pkey = arch_override_mprotect_pkey(vma, prot, pkey);
 		newflags = calc_vm_prot_bits(prot, new_vma_pkey);
 		newflags |= (vma->vm_flags & ~mask_off_old_flags);
+		new_vma_flags = legacy_to_vma_flags(newflags);
 
 		/* newflags >> 4 shift VM_MAY% in place of VM_% */
 		if ((newflags & ~(newflags >> 4)) & VM_ACCESS_FLAGS) {
@@ -911,7 +913,7 @@ static int do_mprotect_pkey(unsigned long start, size_t len,
 			break;
 		}
 
-		if (map_deny_write_exec(vma->vm_flags, newflags)) {
+		if (map_deny_write_exec(&vma->flags, &new_vma_flags)) {
 			error = -EACCES;
 			break;
 		}
diff --git a/mm/vma.c b/mm/vma.c
index 16a1d708c978..c335f989586f 100644
--- a/mm/vma.c
+++ b/mm/vma.c
@@ -44,7 +44,7 @@ struct mmap_state {
 	bool file_doesnt_need_get :1;
 };
 
-#define MMAP_STATE(name, mm_, vmi_, addr_, len_, pgoff_, vm_flags_, file_) \
+#define MMAP_STATE(name, mm_, vmi_, addr_, len_, pgoff_, vma_flags_, file_) \
 	struct mmap_state name = {					\
 		.mm = mm_,						\
 		.vmi = vmi_,						\
@@ -52,9 +52,9 @@ struct mmap_state {
 		.end = (addr_) + (len_),				\
 		.pgoff = pgoff_,					\
 		.pglen = PHYS_PFN(len_),				\
-		.vm_flags = vm_flags_,					\
+		.vma_flags = vma_flags_,				\
 		.file = file_,						\
-		.page_prot = vm_get_page_prot(vm_flags_),		\
+		.page_prot = vma_get_page_prot(vma_flags_),		\
 	}
 
 #define VMG_MMAP_STATE(name, map_, vma_)				\
@@ -63,7 +63,7 @@ struct mmap_state {
 		.vmi = (map_)->vmi,					\
 		.start = (map_)->addr,					\
 		.end = (map_)->end,					\
-		.vm_flags = (map_)->vm_flags,				\
+		.vma_flags = (map_)->vma_flags,				\
 		.pgoff = (map_)->pgoff,					\
 		.file = (map_)->file,					\
 		.prev = (map_)->prev,					\
@@ -2746,14 +2746,14 @@ static int call_action_complete(struct mmap_state *map,
 }
 
 static unsigned long __mmap_region(struct file *file, unsigned long addr,
-		unsigned long len, vm_flags_t vm_flags, unsigned long pgoff,
-		struct list_head *uf)
+		unsigned long len, vma_flags_t vma_flags,
+		unsigned long pgoff, struct list_head *uf)
 {
 	struct mm_struct *mm = current->mm;
 	struct vm_area_struct *vma = NULL;
 	bool have_mmap_prepare = file && file->f_op->mmap_prepare;
 	VMA_ITERATOR(vmi, mm, addr);
-	MMAP_STATE(map, mm, &vmi, addr, len, pgoff, vm_flags, file);
+	MMAP_STATE(map, mm, &vmi, addr, len, pgoff, vma_flags, file);
 	struct vm_area_desc desc = {
 		.mm = mm,
 		.file = file,
@@ -2837,16 +2837,17 @@ abort_munmap:
  * been performed.
  */
 unsigned long mmap_region(struct file *file, unsigned long addr,
-			  unsigned long len, vm_flags_t vm_flags, unsigned long pgoff,
-			  struct list_head *uf)
+			  unsigned long len, vm_flags_t vm_flags,
+			  unsigned long pgoff, struct list_head *uf)
 {
 	unsigned long ret;
 	bool writable_file_mapping = false;
+	const vma_flags_t vma_flags = legacy_to_vma_flags(vm_flags);
 
 	mmap_assert_write_locked(current->mm);
 
 	/* Check to see if MDWE is applicable. */
-	if (map_deny_write_exec(vm_flags, vm_flags))
+	if (map_deny_write_exec(&vma_flags, &vma_flags))
 		return -EACCES;
 
 	/* Allow architectures to sanity-check the vm_flags. */
@@ -2854,7 +2855,7 @@ unsigned long mmap_region(struct file *file, unsigned long addr,
 		return -EINVAL;
 
 	/* Map writable and ensure this isn't a sealed memfd. */
-	if (file && is_shared_maywrite_vm_flags(vm_flags)) {
+	if (file && is_shared_maywrite(&vma_flags)) {
 		int error = mapping_map_writable(file->f_mapping);
 
 		if (error)
@@ -2862,7 +2863,7 @@ unsigned long mmap_region(struct file *file, unsigned long addr,
 		writable_file_mapping = true;
 	}
 
-	ret = __mmap_region(file, addr, len, vm_flags, pgoff, uf);
+	ret = __mmap_region(file, addr, len, vma_flags, pgoff, uf);
 
 	/* Clear our write mapping regardless of error. */
 	if (writable_file_mapping)
diff --git a/mm/vma.h b/mm/vma.h
index 270008e5babc..adc18f7dd9f1 100644
--- a/mm/vma.h
+++ b/mm/vma.h
@@ -704,4 +704,55 @@ int create_init_stack_vma(struct mm_struct *mm, struct vm_area_struct **vmap,
 int relocate_vma_down(struct vm_area_struct *vma, unsigned long shift);
 #endif
 
+#ifdef CONFIG_MMU
+/*
+ * Denies creating a writable executable mapping or gaining executable permissions.
+ *
+ * This denies the following:
+ *
+ *	a)	mmap(PROT_WRITE | PROT_EXEC)
+ *
+ *	b)	mmap(PROT_WRITE)
+ *		mprotect(PROT_EXEC)
+ *
+ *	c)	mmap(PROT_WRITE)
+ *		mprotect(PROT_READ)
+ *		mprotect(PROT_EXEC)
+ *
+ * But allows the following:
+ *
+ *	d)	mmap(PROT_READ | PROT_EXEC)
+ *		mmap(PROT_READ | PROT_EXEC | PROT_BTI)
+ *
+ * This is only applicable if the user has set the Memory-Deny-Write-Execute
+ * (MDWE) protection mask for the current process.
+ *
+ * @old specifies the VMA flags the VMA originally possessed, and @new the ones
+ * we propose to set.
+ *
+ * Return: false if proposed change is OK, true if not ok and should be denied.
+ */
+static inline bool map_deny_write_exec(const vma_flags_t *old,
+				       const vma_flags_t *new)
+{
+	/* If MDWE is disabled, we have nothing to deny. */
+	if (!mm_flags_test(MMF_HAS_MDWE, current->mm))
+		return false;
+
+	/* If the new VMA is not executable, we have nothing to deny. */
+	if (!vma_flags_test(new, VMA_EXEC_BIT))
+		return false;
+
+	/* Under MDWE we do not accept newly writably executable VMAs... */
+	if (vma_flags_test(new, VMA_WRITE_BIT))
+		return true;
+
+	/* ...nor previously non-executable VMAs becoming executable. */
+	if (!vma_flags_test(old, VMA_EXEC_BIT))
+		return true;
+
+	return false;
+}
+#endif
+
 #endif	/* __MM_VMA_H */