Merge tag 'denywrite-for-5.15' of git://github.com/davidhildenbrand/linux

Pull MAP_DENYWRITE removal from David Hildenbrand:
 "Remove all in-tree usage of MAP_DENYWRITE from the kernel and remove
  VM_DENYWRITE.

  There are some (minor) user-visible changes:

   - We no longer deny write access to shared libaries loaded via legacy
     uselib(); this behavior matches modern user space e.g. dlopen().

   - We no longer deny write access to the elf interpreter after exec
     completed, treating it just like shared libraries (which it often
     is).

   - We always deny write access to the file linked via /proc/pid/exe:
     sys_prctl(PR_SET_MM_MAP/EXE_FILE) will fail if write access to the
     file cannot be denied, and write access to the file will remain
     denied until the link is effectivel gone (exec, termination,
     sys_prctl(PR_SET_MM_MAP/EXE_FILE)) -- just as if exec'ing the file.

  Cross-compiled for a bunch of architectures (alpha, microblaze, i386,
  s390x, ...) and verified via ltp that especially the relevant tests
  (i.e., creat07 and execve04) continue working as expected"

* tag 'denywrite-for-5.15' of git://github.com/davidhildenbrand/linux:
  fs: update documentation of get_write_access() and friends
  mm: ignore MAP_DENYWRITE in ksys_mmap_pgoff()
  mm: remove VM_DENYWRITE
  binfmt: remove in-tree usage of MAP_DENYWRITE
  kernel/fork: always deny write access to current MM exe_file
  kernel/fork: factor out replacing the current MM exe_file
  binfmt: don't use MAP_DENYWRITE when loading shared libraries via uselib()

Author: torvalds

arch/x86/ia32/ia32_aout.c

@@ -202,17 +202,15 @@ static int load_aout_binary(struct linux_binprm *bprm)
 
 		error = vm_mmap(bprm->file, N_TXTADDR(ex), ex.a_text,
 				PROT_READ | PROT_EXEC,
-				MAP_FIXED | MAP_PRIVATE | MAP_DENYWRITE |
-				MAP_32BIT,
+				MAP_FIXED | MAP_PRIVATE | MAP_32BIT,
 				fd_offset);
 
 		if (error != N_TXTADDR(ex))
 			return error;
 
 		error = vm_mmap(bprm->file, N_DATADDR(ex), ex.a_data,
 				PROT_READ | PROT_WRITE | PROT_EXEC,
-				MAP_FIXED | MAP_PRIVATE | MAP_DENYWRITE |
-				MAP_32BIT,
+				MAP_FIXED | MAP_PRIVATE | MAP_32BIT,
 				fd_offset + ex.a_text);
 		if (error != N_DATADDR(ex))
 			return error;
@@ -293,7 +291,7 @@ static int load_aout_library(struct file *file)
 	/* Now use mmap to map the library into memory. */
 	error = vm_mmap(file, start_addr, ex.a_text + ex.a_data,
 			PROT_READ | PROT_WRITE | PROT_EXEC,
-			MAP_FIXED | MAP_PRIVATE | MAP_DENYWRITE | MAP_32BIT,
+			MAP_FIXED | MAP_PRIVATE | MAP_32BIT,
 			N_TXTOFF(ex));
 	retval = error;
 	if (error != start_addr)

fs/binfmt_aout.c

@@ -221,16 +221,15 @@ static int load_aout_binary(struct linux_binprm * bprm)
 		}
 
 		error = vm_mmap(bprm->file, N_TXTADDR(ex), ex.a_text,
-			PROT_READ | PROT_EXEC,
-			MAP_FIXED | MAP_PRIVATE | MAP_DENYWRITE,
+			PROT_READ | PROT_EXEC, MAP_FIXED | MAP_PRIVATE,
 			fd_offset);
 
 		if (error != N_TXTADDR(ex))
 			return error;
 
 		error = vm_mmap(bprm->file, N_DATADDR(ex), ex.a_data,
 				PROT_READ | PROT_WRITE | PROT_EXEC,
-				MAP_FIXED | MAP_PRIVATE | MAP_DENYWRITE,
+				MAP_FIXED | MAP_PRIVATE,
 				fd_offset + ex.a_text);
 		if (error != N_DATADDR(ex))
 			return error;
@@ -309,7 +308,7 @@ static int load_aout_library(struct file *file)
 	/* Now use mmap to map the library into memory. */
 	error = vm_mmap(file, start_addr, ex.a_text + ex.a_data,
 			PROT_READ | PROT_WRITE | PROT_EXEC,
-			MAP_FIXED | MAP_PRIVATE | MAP_DENYWRITE,
+			MAP_FIXED | MAP_PRIVATE;
 			N_TXTOFF(ex));
 	retval = error;
 	if (error != start_addr)

fs/binfmt_elf.c

@@ -622,7 +622,7 @@ static unsigned long load_elf_interp(struct elfhdr *interp_elf_ex,
 	eppnt = interp_elf_phdata;
 	for (i = 0; i < interp_elf_ex->e_phnum; i++, eppnt++) {
 		if (eppnt->p_type == PT_LOAD) {
-			int elf_type = MAP_PRIVATE | MAP_DENYWRITE;
+			int elf_type = MAP_PRIVATE;
 			int elf_prot = make_prot(eppnt->p_flags, arch_state,
 						 true, true);
 			unsigned long vaddr = 0;
@@ -1070,7 +1070,7 @@ static int load_elf_binary(struct linux_binprm *bprm)
 		elf_prot = make_prot(elf_ppnt->p_flags, &arch_state,
 				     !!interpreter, false);
 
-		elf_flags = MAP_PRIVATE | MAP_DENYWRITE;
+		elf_flags = MAP_PRIVATE;
 
 		vaddr = elf_ppnt->p_vaddr;
 		/*
@@ -1384,7 +1384,7 @@ static int load_elf_library(struct file *file)
 			(eppnt->p_filesz +
 			 ELF_PAGEOFFSET(eppnt->p_vaddr)),
 			PROT_READ | PROT_WRITE | PROT_EXEC,
-			MAP_FIXED_NOREPLACE | MAP_PRIVATE | MAP_DENYWRITE,
+			MAP_FIXED_NOREPLACE | MAP_PRIVATE,
 			(eppnt->p_offset -
 			 ELF_PAGEOFFSET(eppnt->p_vaddr)));
 	if (error != ELF_PAGESTART(eppnt->p_vaddr))

fs/binfmt_elf_fdpic.c

@@ -1041,7 +1041,7 @@ static int elf_fdpic_map_file_by_direct_mmap(struct elf_fdpic_params *params,
 		if (phdr->p_flags & PF_W) prot |= PROT_WRITE;
 		if (phdr->p_flags & PF_X) prot |= PROT_EXEC;
 
-		flags = MAP_PRIVATE | MAP_DENYWRITE;
+		flags = MAP_PRIVATE;
 		maddr = 0;
 
 		switch (params->flags & ELF_FDPIC_FLAG_ARRANGEMENT) {

fs/exec.c

@@ -1272,7 +1272,9 @@ int begin_new_exec(struct linux_binprm * bprm)
 	 * not visibile until then. This also enables the update
 	 * to be lockless.
 	 */
-	set_mm_exe_file(bprm->mm, bprm->file);
+	retval = set_mm_exe_file(bprm->mm, bprm->file);
+	if (retval)
+		goto out;
 
 	/* If the binary is not readable then enforce mm->dumpable=0 */
 	would_dump(bprm, bprm->file);

fs/proc/task_mmu.c

@@ -619,7 +619,6 @@ static void show_smap_vma_flags(struct seq_file *m, struct vm_area_struct *vma)
 		[ilog2(VM_MAYSHARE)]	= "ms",
 		[ilog2(VM_GROWSDOWN)]	= "gd",
 		[ilog2(VM_PFNMAP)]	= "pf",
-		[ilog2(VM_DENYWRITE)]	= "dw",
 		[ilog2(VM_LOCKED)]	= "lo",
 		[ilog2(VM_IO)]		= "io",
 		[ilog2(VM_SEQ_READ)]	= "sr",

include/linux/fs.h

@@ -3023,15 +3023,20 @@ static inline void file_end_write(struct file *file)
 }
 
 /*
+ * This is used for regular files where some users -- especially the
+ * currently executed binary in a process, previously handled via
+ * VM_DENYWRITE -- cannot handle concurrent write (and maybe mmap
+ * read-write shared) accesses.
+ *
  * get_write_access() gets write permission for a file.
  * put_write_access() releases this write permission.
- * This is used for regular files.
- * We cannot support write (and maybe mmap read-write shared) accesses and
- * MAP_DENYWRITE mmappings simultaneously. The i_writecount field of an inode
- * can have the following values:
- * 0: no writers, no VM_DENYWRITE mappings
- * < 0: (-i_writecount) vm_area_structs with VM_DENYWRITE set exist
- * > 0: (i_writecount) users are writing to the file.
+ * deny_write_access() denies write access to a file.
+ * allow_write_access() re-enables write access to a file.
+ *
+ * The i_writecount field of an inode can have the following values:
+ * 0: no write access, no denied write access
+ * < 0: (-i_writecount) users that denied write access to the file.
+ * > 0: (i_writecount) users that have write access to the file.
  *
  * Normally we operate on that counter with atomic_{inc,dec} and it's safe
  * except for the cases where we don't hold i_writecount yet. Then we need to

include/linux/mm.h

@@ -281,7 +281,6 @@ extern unsigned int kobjsize(const void *objp);
 #define VM_GROWSDOWN	0x00000100	/* general info on the segment */
 #define VM_UFFD_MISSING	0x00000200	/* missing pages tracking */
 #define VM_PFNMAP	0x00000400	/* Page-ranges managed without "struct page", just pure PFN */
-#define VM_DENYWRITE	0x00000800	/* ETXTBSY on write attempts.. */
 #define VM_UFFD_WP	0x00001000	/* wrprotect pages tracking */
 
 #define VM_LOCKED	0x00002000
@@ -2573,7 +2572,8 @@ static inline int check_data_rlimit(unsigned long rlim,
 extern int mm_take_all_locks(struct mm_struct *mm);
 extern void mm_drop_all_locks(struct mm_struct *mm);
 
-extern void set_mm_exe_file(struct mm_struct *mm, struct file *new_exe_file);
+extern int set_mm_exe_file(struct mm_struct *mm, struct file *new_exe_file);
+extern int replace_mm_exe_file(struct mm_struct *mm, struct file *new_exe_file);
 extern struct file *get_mm_exe_file(struct mm_struct *mm);
 extern struct file *get_task_exe_file(struct task_struct *task);
 

include/linux/mman.h

@@ -32,7 +32,8 @@
  * The historical set of flags that all mmap implementations implicitly
  * support when a ->mmap_validate() op is not provided in file_operations.
  *
- * MAP_EXECUTABLE is completely ignored throughout the kernel.
+ * MAP_EXECUTABLE and MAP_DENYWRITE are completely ignored throughout the
+ * kernel.
  */
 #define LEGACY_MAP_MASK (MAP_SHARED \
 		| MAP_PRIVATE \
@@ -153,7 +154,6 @@ static inline unsigned long
 calc_vm_flag_bits(unsigned long flags)
 {
 	return _calc_vm_trans(flags, MAP_GROWSDOWN,  VM_GROWSDOWN ) |
-	       _calc_vm_trans(flags, MAP_DENYWRITE,  VM_DENYWRITE ) |
 	       _calc_vm_trans(flags, MAP_LOCKED,     VM_LOCKED    ) |
 	       _calc_vm_trans(flags, MAP_SYNC,	     VM_SYNC      ) |
 	       arch_calc_vm_flag_bits(flags);

include/trace/events/mmflags.h

@@ -165,7 +165,6 @@ IF_HAVE_PG_SKIP_KASAN_POISON(PG_skip_kasan_poison, "skip_kasan_poison")
 	{VM_UFFD_MISSING,		"uffd_missing"	},		\
 IF_HAVE_UFFD_MINOR(VM_UFFD_MINOR,	"uffd_minor"	)		\
 	{VM_PFNMAP,			"pfnmap"	},		\
-	{VM_DENYWRITE,			"denywrite"	},		\
 	{VM_UFFD_WP,			"uffd_wp"	},		\
 	{VM_LOCKED,			"locked"	},		\
 	{VM_IO,				"io"		},		\

kernel/events/core.c

@@ -8320,8 +8320,6 @@ static void perf_event_mmap_event(struct perf_mmap_event *mmap_event)
 	else
 		flags = MAP_PRIVATE;
 
-	if (vma->vm_flags & VM_DENYWRITE)
-		flags |= MAP_DENYWRITE;
 	if (vma->vm_flags & VM_LOCKED)
 		flags |= MAP_LOCKED;
 	if (is_vm_hugetlb_page(vma))

kernel/fork.c

@@ -471,6 +471,20 @@ void free_task(struct task_struct *tsk)
 }
 EXPORT_SYMBOL(free_task);
 
+static void dup_mm_exe_file(struct mm_struct *mm, struct mm_struct *oldmm)
+{
+	struct file *exe_file;
+
+	exe_file = get_mm_exe_file(oldmm);
+	RCU_INIT_POINTER(mm->exe_file, exe_file);
+	/*
+	 * We depend on the oldmm having properly denied write access to the
+	 * exe_file already.
+	 */
+	if (exe_file && deny_write_access(exe_file))
+		pr_warn_once("deny_write_access() failed in %s\n", __func__);
+}
+
 #ifdef CONFIG_MMU
 static __latent_entropy int dup_mmap(struct mm_struct *mm,
 					struct mm_struct *oldmm)
@@ -494,7 +508,7 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm,
 	mmap_write_lock_nested(mm, SINGLE_DEPTH_NESTING);
 
 	/* No ordering required: file already has been exposed. */
-	RCU_INIT_POINTER(mm->exe_file, get_mm_exe_file(oldmm));
+	dup_mm_exe_file(mm, oldmm);
 
 	mm->total_vm = oldmm->total_vm;
 	mm->data_vm = oldmm->data_vm;
@@ -557,12 +571,9 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm,
 		tmp->vm_flags &= ~(VM_LOCKED | VM_LOCKONFAULT);
 		file = tmp->vm_file;
 		if (file) {
-			struct inode *inode = file_inode(file);
 			struct address_space *mapping = file->f_mapping;
 
 			get_file(file);
-			if (tmp->vm_flags & VM_DENYWRITE)
-				put_write_access(inode);
 			i_mmap_lock_write(mapping);
 			if (tmp->vm_flags & VM_SHARED)
 				mapping_allow_writable(mapping);
@@ -640,7 +651,7 @@ static inline void mm_free_pgd(struct mm_struct *mm)
 static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm)
 {
 	mmap_write_lock(oldmm);
-	RCU_INIT_POINTER(mm->exe_file, get_mm_exe_file(oldmm));
+	dup_mm_exe_file(mm, oldmm);
 	mmap_write_unlock(oldmm);
 	return 0;
 }
@@ -1150,11 +1161,11 @@ void mmput_async(struct mm_struct *mm)
  *
  * Main users are mmput() and sys_execve(). Callers prevent concurrent
  * invocations: in mmput() nobody alive left, in execve task is single
- * threaded. sys_prctl(PR_SET_MM_MAP/EXE_FILE) also needs to set the
- * mm->exe_file, but does so without using set_mm_exe_file() in order
- * to avoid the need for any locks.
+ * threaded.
+ *
+ * Can only fail if new_exe_file != NULL.
  */
-void set_mm_exe_file(struct mm_struct *mm, struct file *new_exe_file)
+int set_mm_exe_file(struct mm_struct *mm, struct file *new_exe_file)
 {
 	struct file *old_exe_file;
 
@@ -1165,11 +1176,73 @@ void set_mm_exe_file(struct mm_struct *mm, struct file *new_exe_file)
 	 */
 	old_exe_file = rcu_dereference_raw(mm->exe_file);
 
-	if (new_exe_file)
+	if (new_exe_file) {
+		/*
+		 * We expect the caller (i.e., sys_execve) to already denied
+		 * write access, so this is unlikely to fail.
+		 */
+		if (unlikely(deny_write_access(new_exe_file)))
+			return -EACCES;
 		get_file(new_exe_file);
+	}
 	rcu_assign_pointer(mm->exe_file, new_exe_file);
-	if (old_exe_file)
+	if (old_exe_file) {
+		allow_write_access(old_exe_file);
 		fput(old_exe_file);
+	}
+	return 0;
+}
+
+/**
+ * replace_mm_exe_file - replace a reference to the mm's executable file
+ *
+ * This changes mm's executable file (shown as symlink /proc/[pid]/exe),
+ * dealing with concurrent invocation and without grabbing the mmap lock in
+ * write mode.
+ *
+ * Main user is sys_prctl(PR_SET_MM_MAP/EXE_FILE).
+ */
+int replace_mm_exe_file(struct mm_struct *mm, struct file *new_exe_file)
+{
+	struct vm_area_struct *vma;
+	struct file *old_exe_file;
+	int ret = 0;
+
+	/* Forbid mm->exe_file change if old file still mapped. */
+	old_exe_file = get_mm_exe_file(mm);
+	if (old_exe_file) {
+		mmap_read_lock(mm);
+		for (vma = mm->mmap; vma && !ret; vma = vma->vm_next) {
+			if (!vma->vm_file)
+				continue;
+			if (path_equal(&vma->vm_file->f_path,
+				       &old_exe_file->f_path))
+				ret = -EBUSY;
+		}
+		mmap_read_unlock(mm);
+		fput(old_exe_file);
+		if (ret)
+			return ret;
+	}
+
+	/* set the new file, lockless */
+	ret = deny_write_access(new_exe_file);
+	if (ret)
+		return -EACCES;
+	get_file(new_exe_file);
+
+	old_exe_file = xchg(&mm->exe_file, new_exe_file);
+	if (old_exe_file) {
+		/*
+		 * Don't race with dup_mmap() getting the file and disallowing
+		 * write access while someone might open the file writable.
+		 */
+		mmap_read_lock(mm);
+		allow_write_access(old_exe_file);
+		fput(old_exe_file);
+		mmap_read_unlock(mm);
+	}
+	return 0;
 }
 
 /**

kernel/sys.c

@@ -1847,7 +1847,6 @@ SYSCALL_DEFINE1(umask, int, mask)
 static int prctl_set_mm_exe_file(struct mm_struct *mm, unsigned int fd)
 {
 	struct fd exe;
-	struct file *old_exe, *exe_file;
 	struct inode *inode;
 	int err;
 
@@ -1870,40 +1869,10 @@ static int prctl_set_mm_exe_file(struct mm_struct *mm, unsigned int fd)
 	if (err)
 		goto exit;
 
-	/*
-	 * Forbid mm->exe_file change if old file still mapped.
-	 */
-	exe_file = get_mm_exe_file(mm);
-	err = -EBUSY;
-	if (exe_file) {
-		struct vm_area_struct *vma;
-
-		mmap_read_lock(mm);
-		for (vma = mm->mmap; vma; vma = vma->vm_next) {
-			if (!vma->vm_file)
-				continue;
-			if (path_equal(&vma->vm_file->f_path,
-				       &exe_file->f_path))
-				goto exit_err;
-		}
-
-		mmap_read_unlock(mm);
-		fput(exe_file);
-	}
-
-	err = 0;
-	/* set the new file, lockless */
-	get_file(exe.file);
-	old_exe = xchg(&mm->exe_file, exe.file);
-	if (old_exe)
-		fput(old_exe);
+	err = replace_mm_exe_file(mm, exe.file);
 exit:
 	fdput(exe);
 	return err;
-exit_err:
-	mmap_read_unlock(mm);
-	fput(exe_file);
-	goto exit;
 }
 
 /*

lib/test_printf.c

@@ -675,9 +675,8 @@ flags(void)
 			"uptodate|dirty|lru|active|swapbacked",
 			cmp_buffer);
 
-	flags = VM_READ | VM_EXEC | VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC
-			| VM_DENYWRITE;
-	test("read|exec|mayread|maywrite|mayexec|denywrite", "%pGv", &flags);
+	flags = VM_READ | VM_EXEC | VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC;
+	test("read|exec|mayread|maywrite|mayexec", "%pGv", &flags);
 
 	gfp = GFP_TRANSHUGE;
 	test("GFP_TRANSHUGE", "%pGg", &gfp);