Merge tag 'core-uaccess-2025-11-30' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull scoped user access updates from Thomas Gleixner:
 "Scoped user mode access and related changes:

   - Implement the missing u64 user access function on ARM when
     CONFIG_CPU_SPECTRE=n.

     This makes it possible to access a 64bit value in generic code with
     [unsafe_]get_user(). All other architectures and ARM variants
     provide the relevant accessors already.

   - Ensure that ASM GOTO jump label usage in the user mode access
     helpers always goes through a local C scope label indirection
     inside the helpers.

     This is required because compilers are not supporting that a ASM
     GOTO target leaves a auto cleanup scope. GCC silently fails to emit
     the cleanup invocation and CLANG fails the build.

     [ Editor's note: gcc-16 will have fixed the code generation issue
       in commit f68fe3ddda4 ("eh: Invoke cleanups/destructors in asm
       goto jumps [PR122835]"). But we obviously have to deal with clang
       and older versions of gcc, so.. - Linus ]

     This provides generic wrapper macros and the conversion of affected
     architecture code to use them.

   - Scoped user mode access with auto cleanup

     Access to user mode memory can be required in hot code paths, but
     if it has to be done with user controlled pointers, the access is
     shielded with a speculation barrier, so that the CPU cannot
     speculate around the address range check. Those speculation
     barriers impact performance quite significantly.

     This cost can be avoided by "masking" the provided pointer so it is
     guaranteed to be in the valid user memory access range and
     otherwise to point to a guaranteed unpopulated address space. This
     has to be done without branches so it creates an address dependency
     for the access, which the CPU cannot speculate ahead.

     This results in repeating and error prone programming patterns:

       	    if (can_do_masked_user_access())
                      from = masked_user_read_access_begin((from));
              else if (!user_read_access_begin(from, sizeof(*from)))
                      return -EFAULT;
              unsafe_get_user(val, from, Efault);
              user_read_access_end();
              return 0;
        Efault:
              user_read_access_end();
              return -EFAULT;

      which can be replaced with scopes and automatic cleanup:

              scoped_user_read_access(from, Efault)
                      unsafe_get_user(val, from, Efault);
              return 0;
         Efault:
              return -EFAULT;

   - Convert code which implements the above pattern over to
     scope_user.*.access(). This also corrects a couple of imbalanced
     masked_*_begin() instances which are harmless on most
     architectures, but prevent PowerPC from implementing the masking
     optimization.

   - Add a missing speculation barrier in copy_from_user_iter()"

* tag 'core-uaccess-2025-11-30' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  lib/strn*,uaccess: Use masked_user_{read/write}_access_begin when required
  scm: Convert put_cmsg() to scoped user access
  iov_iter: Add missing speculation barrier to copy_from_user_iter()
  iov_iter: Convert copy_from_user_iter() to masked user access
  select: Convert to scoped user access
  x86/futex: Convert to scoped user access
  futex: Convert to get/put_user_inline()
  uaccess: Provide put/get_user_inline()
  uaccess: Provide scoped user access regions
  arm64: uaccess: Use unsafe wrappers for ASM GOTO
  s390/uaccess: Use unsafe wrappers for ASM GOTO
  riscv/uaccess: Use unsafe wrappers for ASM GOTO
  powerpc/uaccess: Use unsafe wrappers for ASM GOTO
  x86/uaccess: Use unsafe wrappers for ASM GOTO
  uaccess: Provide ASM GOTO safe wrappers for unsafe_*_user()
  ARM: uaccess: Implement missing __get_user_asm_dword()

1 files changed, 310 insertions, 4 deletions

diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h
index 1beb5b395d81..be395f5f7ee3 100644
--- a/include/linux/uaccess.h
+++ b/include/linux/uaccess.h
@@ -2,6 +2,7 @@
 #ifndef __LINUX_UACCESS_H__
 #define __LINUX_UACCESS_H__
 
+#include <linux/cleanup.h>
 #include <linux/fault-inject-usercopy.h>
 #include <linux/instrumented.h>
 #include <linux/minmax.h>
@@ -35,9 +36,17 @@
 
 #ifdef masked_user_access_begin
  #define can_do_masked_user_access() 1
+# ifndef masked_user_write_access_begin
+#  define masked_user_write_access_begin masked_user_access_begin
+# endif
+# ifndef masked_user_read_access_begin
+#  define masked_user_read_access_begin masked_user_access_begin
+#endif
 #else
  #define can_do_masked_user_access() 0
  #define masked_user_access_begin(src) NULL
+ #define masked_user_read_access_begin(src) NULL
+ #define masked_user_write_access_begin(src) NULL
  #define mask_user_address(src) (src)
 #endif
 
@@ -518,7 +527,34 @@ long strncpy_from_user_nofault(char *dst, const void __user *unsafe_addr,
 		long count);
 long strnlen_user_nofault(const void __user *unsafe_addr, long count);
 
-#ifndef __get_kernel_nofault
+#ifdef arch_get_kernel_nofault
+/*
+ * Wrap the architecture implementation so that @label can be outside of a
+ * cleanup() scope. A regular C goto works correctly, but ASM goto does
+ * not. Clang rejects such an attempt, but GCC silently emits buggy code.
+ */
+#define __get_kernel_nofault(dst, src, type, label)		\
+do {								\
+	__label__ local_label;					\
+	arch_get_kernel_nofault(dst, src, type, local_label);	\
+	if (0) {						\
+	local_label:						\
+		goto label;					\
+	}							\
+} while (0)
+
+#define __put_kernel_nofault(dst, src, type, label)		\
+do {								\
+	__label__ local_label;					\
+	arch_put_kernel_nofault(dst, src, type, local_label);	\
+	if (0) {						\
+	local_label:						\
+		goto label;					\
+	}							\
+} while (0)
+
+#elif !defined(__get_kernel_nofault) /* arch_get_kernel_nofault */
+
 #define __get_kernel_nofault(dst, src, type, label)	\
 do {							\
 	type __user *p = (type __force __user *)(src);	\
@@ -535,7 +571,8 @@ do {							\
 	if (__put_user(data, p))			\
 		goto label;				\
 } while (0)
-#endif
+
+#endif  /* !__get_kernel_nofault */
 
 /**
  * get_kernel_nofault(): safely attempt to read from a location
@@ -549,7 +586,42 @@ do {							\
 	copy_from_kernel_nofault(&(val), __gk_ptr, sizeof(val));\
 })
 
-#ifndef user_access_begin
+#ifdef user_access_begin
+
+#ifdef arch_unsafe_get_user
+/*
+ * Wrap the architecture implementation so that @label can be outside of a
+ * cleanup() scope. A regular C goto works correctly, but ASM goto does
+ * not. Clang rejects such an attempt, but GCC silently emits buggy code.
+ *
+ * Some architectures use internal local labels already, but this extra
+ * indirection here is harmless because the compiler optimizes it out
+ * completely in any case. This construct just ensures that the ASM GOTO
+ * target is always in the local scope. The C goto 'label' works correctly
+ * when leaving a cleanup() scope.
+ */
+#define unsafe_get_user(x, ptr, label)			\
+do {							\
+	__label__ local_label;				\
+	arch_unsafe_get_user(x, ptr, local_label);	\
+	if (0) {					\
+	local_label:					\
+		goto label;				\
+	}						\
+} while (0)
+
+#define unsafe_put_user(x, ptr, label)			\
+do {							\
+	__label__ local_label;				\
+	arch_unsafe_put_user(x, ptr, local_label);	\
+	if (0) {					\
+	local_label:					\
+		goto label;				\
+	}						\
+} while (0)
+#endif /* arch_unsafe_get_user */
+
+#else /* user_access_begin */
 #define user_access_begin(ptr,len) access_ok(ptr, len)
 #define user_access_end() do { } while (0)
 #define unsafe_op_wrap(op, err) do { if (unlikely(op)) goto err; } while (0)
@@ -559,7 +631,8 @@ do {							\
 #define unsafe_copy_from_user(d,s,l,e) unsafe_op_wrap(__copy_from_user(d,s,l),e)
 static inline unsigned long user_access_save(void) { return 0UL; }
 static inline void user_access_restore(unsigned long flags) { }
-#endif
+#endif /* !user_access_begin */
+
 #ifndef user_write_access_begin
 #define user_write_access_begin user_access_begin
 #define user_write_access_end user_access_end
@@ -569,6 +642,239 @@ static inline void user_access_restore(unsigned long flags) { }
 #define user_read_access_end user_access_end
 #endif
 
+/* Define RW variant so the below _mode macro expansion works */
+#define masked_user_rw_access_begin(u)	masked_user_access_begin(u)
+#define user_rw_access_begin(u, s)	user_access_begin(u, s)
+#define user_rw_access_end()		user_access_end()
+
+/* Scoped user access */
+#define USER_ACCESS_GUARD(_mode)				\
+static __always_inline void __user *				\
+class_user_##_mode##_begin(void __user *ptr)			\
+{								\
+	return ptr;						\
+}								\
+								\
+static __always_inline void					\
+class_user_##_mode##_end(void __user *ptr)			\
+{								\
+	user_##_mode##_access_end();				\
+}								\
+								\
+DEFINE_CLASS(user_ ##_mode## _access, void __user *,		\
+	     class_user_##_mode##_end(_T),			\
+	     class_user_##_mode##_begin(ptr), void __user *ptr)	\
+								\
+static __always_inline class_user_##_mode##_access_t		\
+class_user_##_mode##_access_ptr(void __user *scope)		\
+{								\
+	return scope;						\
+}
+
+USER_ACCESS_GUARD(read)
+USER_ACCESS_GUARD(write)
+USER_ACCESS_GUARD(rw)
+#undef USER_ACCESS_GUARD
+
+/**
+ * __scoped_user_access_begin - Start a scoped user access
+ * @mode:	The mode of the access class (read, write, rw)
+ * @uptr:	The pointer to access user space memory
+ * @size:	Size of the access
+ * @elbl:	Error label to goto when the access region is rejected
+ *
+ * Internal helper for __scoped_user_access(). Don't use directly.
+ */
+#define __scoped_user_access_begin(mode, uptr, size, elbl)		\
+({									\
+	typeof(uptr) __retptr;						\
+									\
+	if (can_do_masked_user_access()) {				\
+		__retptr = masked_user_##mode##_access_begin(uptr);	\
+	} else {							\
+		__retptr = uptr;					\
+		if (!user_##mode##_access_begin(uptr, size))		\
+			goto elbl;					\
+	}								\
+	__retptr;							\
+})
+
+/**
+ * __scoped_user_access - Open a scope for user access
+ * @mode:	The mode of the access class (read, write, rw)
+ * @uptr:	The pointer to access user space memory
+ * @size:	Size of the access
+ * @elbl:	Error label to goto when the access region is rejected. It
+ *		must be placed outside the scope
+ *
+ * If the user access function inside the scope requires a fault label, it
+ * can use @elbl or a different label outside the scope, which requires
+ * that user access which is implemented with ASM GOTO has been properly
+ * wrapped. See unsafe_get_user() for reference.
+ *
+ *	scoped_user_rw_access(ptr, efault) {
+ *		unsafe_get_user(rval, &ptr->rval, efault);
+ *		unsafe_put_user(wval, &ptr->wval, efault);
+ *	}
+ *	return 0;
+ *  efault:
+ *	return -EFAULT;
+ *
+ * The scope is internally implemented as a autoterminating nested for()
+ * loop, which can be left with 'return', 'break' and 'goto' at any
+ * point.
+ *
+ * When the scope is left user_##@_mode##_access_end() is automatically
+ * invoked.
+ *
+ * When the architecture supports masked user access and the access region
+ * which is determined by @uptr and @size is not a valid user space
+ * address, i.e. < TASK_SIZE, the scope sets the pointer to a faulting user
+ * space address and does not terminate early. This optimizes for the good
+ * case and lets the performance uncritical bad case go through the fault.
+ *
+ * The eventual modification of the pointer is limited to the scope.
+ * Outside of the scope the original pointer value is unmodified, so that
+ * the original pointer value is available for diagnostic purposes in an
+ * out of scope fault path.
+ *
+ * Nesting scoped user access into a user access scope is invalid and fails
+ * the build. Nesting into other guards, e.g. pagefault is safe.
+ *
+ * The masked variant does not check the size of the access and relies on a
+ * mapping hole (e.g. guard page) to catch an out of range pointer, the
+ * first access to user memory inside the scope has to be within
+ * @uptr ... @uptr + PAGE_SIZE - 1
+ *
+ * Don't use directly. Use scoped_masked_user_$MODE_access() instead.
+ */
+#define __scoped_user_access(mode, uptr, size, elbl)					\
+for (bool done = false; !done; done = true)						\
+	for (void __user *_tmpptr = __scoped_user_access_begin(mode, uptr, size, elbl); \
+	     !done; done = true)							\
+		for (CLASS(user_##mode##_access, scope)(_tmpptr); !done; done = true)	\
+			/* Force modified pointer usage within the scope */		\
+			for (const typeof(uptr) uptr = _tmpptr; !done; done = true)
+
+/**
+ * scoped_user_read_access_size - Start a scoped user read access with given size
+ * @usrc:	Pointer to the user space address to read from
+ * @size:	Size of the access starting from @usrc
+ * @elbl:	Error label to goto when the access region is rejected
+ *
+ * For further information see __scoped_user_access() above.
+ */
+#define scoped_user_read_access_size(usrc, size, elbl)		\
+	__scoped_user_access(read, usrc, size, elbl)
+
+/**
+ * scoped_user_read_access - Start a scoped user read access
+ * @usrc:	Pointer to the user space address to read from
+ * @elbl:	Error label to goto when the access region is rejected
+ *
+ * The size of the access starting from @usrc is determined via sizeof(*@usrc)).
+ *
+ * For further information see __scoped_user_access() above.
+ */
+#define scoped_user_read_access(usrc, elbl)				\
+	scoped_user_read_access_size(usrc, sizeof(*(usrc)), elbl)
+
+/**
+ * scoped_user_write_access_size - Start a scoped user write access with given size
+ * @udst:	Pointer to the user space address to write to
+ * @size:	Size of the access starting from @udst
+ * @elbl:	Error label to goto when the access region is rejected
+ *
+ * For further information see __scoped_user_access() above.
+ */
+#define scoped_user_write_access_size(udst, size, elbl)			\
+	__scoped_user_access(write, udst, size, elbl)
+
+/**
+ * scoped_user_write_access - Start a scoped user write access
+ * @udst:	Pointer to the user space address to write to
+ * @elbl:	Error label to goto when the access region is rejected
+ *
+ * The size of the access starting from @udst is determined via sizeof(*@udst)).
+ *
+ * For further information see __scoped_user_access() above.
+ */
+#define scoped_user_write_access(udst, elbl)				\
+	scoped_user_write_access_size(udst, sizeof(*(udst)), elbl)
+
+/**
+ * scoped_user_rw_access_size - Start a scoped user read/write access with given size
+ * @uptr	Pointer to the user space address to read from and write to
+ * @size:	Size of the access starting from @uptr
+ * @elbl:	Error label to goto when the access region is rejected
+ *
+ * For further information see __scoped_user_access() above.
+ */
+#define scoped_user_rw_access_size(uptr, size, elbl)			\
+	__scoped_user_access(rw, uptr, size, elbl)
+
+/**
+ * scoped_user_rw_access - Start a scoped user read/write access
+ * @uptr	Pointer to the user space address to read from and write to
+ * @elbl:	Error label to goto when the access region is rejected
+ *
+ * The size of the access starting from @uptr is determined via sizeof(*@uptr)).
+ *
+ * For further information see __scoped_user_access() above.
+ */
+#define scoped_user_rw_access(uptr, elbl)				\
+	scoped_user_rw_access_size(uptr, sizeof(*(uptr)), elbl)
+
+/**
+ * get_user_inline - Read user data inlined
+ * @val:	The variable to store the value read from user memory
+ * @usrc:	Pointer to the user space memory to read from
+ *
+ * Return: 0 if successful, -EFAULT when faulted
+ *
+ * Inlined variant of get_user(). Only use when there is a demonstrable
+ * performance reason.
+ */
+#define get_user_inline(val, usrc)				\
+({								\
+	__label__ efault;					\
+	typeof(usrc) _tmpsrc = usrc;				\
+	int _ret = 0;						\
+								\
+	scoped_user_read_access(_tmpsrc, efault)		\
+		unsafe_get_user(val, _tmpsrc, efault);		\
+	if (0) {						\
+	efault:							\
+		_ret = -EFAULT;					\
+	}							\
+	_ret;							\
+})
+
+/**
+ * put_user_inline - Write to user memory inlined
+ * @val:	The value to write
+ * @udst:	Pointer to the user space memory to write to
+ *
+ * Return: 0 if successful, -EFAULT when faulted
+ *
+ * Inlined variant of put_user(). Only use when there is a demonstrable
+ * performance reason.
+ */
+#define put_user_inline(val, udst)				\
+({								\
+	__label__ efault;					\
+	typeof(udst) _tmpdst = udst;				\
+	int _ret = 0;						\
+								\
+	scoped_user_write_access(_tmpdst, efault)		\
+		unsafe_put_user(val, _tmpdst, efault);		\
+	if (0) {						\
+	efault:							\
+		_ret = -EFAULT;					\
+	}							\
+	_ret;							\
+})
+
 #ifdef CONFIG_HARDENED_USERCOPY
 void __noreturn usercopy_abort(const char *name, const char *detail,
 			       bool to_user, unsigned long offset,