Merge branch 'work.uaccess' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs

Pull uaccess unification updates from Al Viro:
 "This is the uaccess unification pile. It's _not_ the end of uaccess
  work, but the next batch of that will go into the next cycle. This one
  mostly takes copy_from_user() and friends out of arch/* and gets the
  zero-padding behaviour in sync for all architectures.

  Dealing with the nocache/writethrough mess is for the next cycle;
  fortunately, that's x86-only. Same for cleanups in iov_iter.c (I am
  sold on access_ok() in there, BTW; just not in this pile), same for
  reducing __copy_... callsites, strn*... stuff, etc. - there will be a
  pile about as large as this one in the next merge window.

  This one sat in -next for weeks. -3KLoC"

* 'work.uaccess' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs: (96 commits)
  HAVE_ARCH_HARDENED_USERCOPY is unconditional now
  CONFIG_ARCH_HAS_RAW_COPY_USER is unconditional now
  m32r: switch to RAW_COPY_USER
  hexagon: switch to RAW_COPY_USER
  microblaze: switch to RAW_COPY_USER
  get rid of padding, switch to RAW_COPY_USER
  ia64: get rid of copy_in_user()
  ia64: sanitize __access_ok()
  ia64: get rid of 'segment' argument of __do_{get,put}_user()
  ia64: get rid of 'segment' argument of __{get,put}_user_check()
  ia64: add extable.h
  powerpc: get rid of zeroing, switch to RAW_COPY_USER
  esas2r: don't open-code memdup_user()
  alpha: fix stack smashing in old_adjtimex(2)
  don't open-code kernel_setsockopt()
  mips: switch to RAW_COPY_USER
  mips: get rid of tail-zeroing in primitives
  mips: make copy_from_user() zero tail explicitly
  mips: clean and reorder the forest of macros...
  mips: consolidate __invoke_... wrappers
  ...

4 files changed, 226 insertions, 134 deletions

diff --git a/include/asm-generic/extable.h b/include/asm-generic/extable.h
new file mode 100644
index 000000000000..ca14c6664027
--- /dev/null
+++ b/include/asm-generic/extable.h
@@ -0,0 +1,26 @@
+#ifndef __ASM_GENERIC_EXTABLE_H
+#define __ASM_GENERIC_EXTABLE_H
+
+/*
+ * The exception table consists of pairs of addresses: the first is the
+ * address of an instruction that is allowed to fault, and the second is
+ * the address at which the program should continue.  No registers are
+ * modified, so it is entirely up to the continuation code to figure out
+ * what to do.
+ *
+ * All the routines below use bits of fixup code that are out of line
+ * with the main instruction path.  This means when everything is well,
+ * we don't even have to jump over them.  Further, they do not intrude
+ * on our cache or tlb entries.
+ */
+
+struct exception_table_entry
+{
+	unsigned long insn, fixup;
+};
+
+
+struct pt_regs;
+extern int fixup_exception(struct pt_regs *regs);
+
+#endif
diff --git a/include/asm-generic/uaccess.h b/include/asm-generic/uaccess.h
index cc6bb319e464..bbe4bb438e39 100644
--- a/include/asm-generic/uaccess.h
+++ b/include/asm-generic/uaccess.h
@@ -6,7 +6,6 @@
  * on any machine that has kernel and user data in the same
  * address space, e.g. all NOMMU machines.
  */
-#include <linux/sched.h>
 #include <linux/string.h>
 
 #include <asm/segment.h>
@@ -35,9 +34,6 @@ static inline void set_fs(mm_segment_t fs)
 #define segment_eq(a, b) ((a).seg == (b).seg)
 #endif
 
-#define VERIFY_READ	0
-#define VERIFY_WRITE	1
-
 #define access_ok(type, addr, size) __access_ok((unsigned long)(addr),(size))
 
 /*
@@ -52,87 +48,6 @@ static inline int __access_ok(unsigned long addr, unsigned long size)
 #endif
 
 /*
- * The exception table consists of pairs of addresses: the first is the
- * address of an instruction that is allowed to fault, and the second is
- * the address at which the program should continue.  No registers are
- * modified, so it is entirely up to the continuation code to figure out
- * what to do.
- *
- * All the routines below use bits of fixup code that are out of line
- * with the main instruction path.  This means when everything is well,
- * we don't even have to jump over them.  Further, they do not intrude
- * on our cache or tlb entries.
- */
-
-struct exception_table_entry
-{
-	unsigned long insn, fixup;
-};
-
-/*
- * architectures with an MMU should override these two
- */
-#ifndef __copy_from_user
-static inline __must_check long __copy_from_user(void *to,
-		const void __user * from, unsigned long n)
-{
-	if (__builtin_constant_p(n)) {
-		switch(n) {
-		case 1:
-			*(u8 *)to = *(u8 __force *)from;
-			return 0;
-		case 2:
-			*(u16 *)to = *(u16 __force *)from;
-			return 0;
-		case 4:
-			*(u32 *)to = *(u32 __force *)from;
-			return 0;
-#ifdef CONFIG_64BIT
-		case 8:
-			*(u64 *)to = *(u64 __force *)from;
-			return 0;
-#endif
-		default:
-			break;
-		}
-	}
-
-	memcpy(to, (const void __force *)from, n);
-	return 0;
-}
-#endif
-
-#ifndef __copy_to_user
-static inline __must_check long __copy_to_user(void __user *to,
-		const void *from, unsigned long n)
-{
-	if (__builtin_constant_p(n)) {
-		switch(n) {
-		case 1:
-			*(u8 __force *)to = *(u8 *)from;
-			return 0;
-		case 2:
-			*(u16 __force *)to = *(u16 *)from;
-			return 0;
-		case 4:
-			*(u32 __force *)to = *(u32 *)from;
-			return 0;
-#ifdef CONFIG_64BIT
-		case 8:
-			*(u64 __force *)to = *(u64 *)from;
-			return 0;
-#endif
-		default:
-			break;
-		}
-	}
-
-	memcpy((void __force *)to, from, n);
-	return 0;
-}
-#endif
-
-/*
  * These are the main single-value transfer routines.  They automatically
  * use the right size if we just have the right pointer type.
  * This version just falls back to copy_{from,to}_user, which should
@@ -171,8 +86,7 @@ static inline __must_check long __copy_to_user(void __user *to,
 
 static inline int __put_user_fn(size_t size, void __user *ptr, void *x)
 {
-	size = __copy_to_user(ptr, x, size);
-	return size ? -EFAULT : size;
+	return unlikely(raw_copy_to_user(ptr, x, size)) ? -EFAULT : 0;
 }
 
 #define __put_user_fn(sz, u, k)	__put_user_fn(sz, u, k)
@@ -187,28 +101,28 @@ extern int __put_user_bad(void) __attribute__((noreturn));
 	__chk_user_ptr(ptr);					\
 	switch (sizeof(*(ptr))) {				\
 	case 1: {						\
-		unsigned char __x;				\
+		unsigned char __x = 0;				\
 		__gu_err = __get_user_fn(sizeof (*(ptr)),	\
 					 ptr, &__x);		\
 		(x) = *(__force __typeof__(*(ptr)) *) &__x;	\
 		break;						\
 	};							\
 	case 2: {						\
-		unsigned short __x;				\
+		unsigned short __x = 0;				\
 		__gu_err = __get_user_fn(sizeof (*(ptr)),	\
 					 ptr, &__x);		\
 		(x) = *(__force __typeof__(*(ptr)) *) &__x;	\
 		break;						\
 	};							\
 	case 4: {						\
-		unsigned int __x;				\
+		unsigned int __x = 0;				\
 		__gu_err = __get_user_fn(sizeof (*(ptr)),	\
 					 ptr, &__x);		\
 		(x) = *(__force __typeof__(*(ptr)) *) &__x;	\
 		break;						\
 	};							\
 	case 8: {						\
-		unsigned long long __x;				\
+		unsigned long long __x = 0;			\
 		__gu_err = __get_user_fn(sizeof (*(ptr)),	\
 					 ptr, &__x);		\
 		(x) = *(__force __typeof__(*(ptr)) *) &__x;	\
@@ -233,12 +147,7 @@ extern int __put_user_bad(void) __attribute__((noreturn));
 #ifndef __get_user_fn
 static inline int __get_user_fn(size_t size, const void __user *ptr, void *x)
 {
-	size_t n = __copy_from_user(x, ptr, size);
-	if (unlikely(n)) {
-		memset(x + (size - n), 0, n);
-		return -EFAULT;
-	}
-	return 0;
+	return unlikely(raw_copy_from_user(x, ptr, size)) ? -EFAULT : 0;
 }
 
 #define __get_user_fn(sz, u, k)	__get_user_fn(sz, u, k)
@@ -247,36 +156,6 @@ static inline int __get_user_fn(size_t size, const void __user *ptr, void *x)
 
 extern int __get_user_bad(void) __attribute__((noreturn));
 
-#ifndef __copy_from_user_inatomic
-#define __copy_from_user_inatomic __copy_from_user
-#endif
-
-#ifndef __copy_to_user_inatomic
-#define __copy_to_user_inatomic __copy_to_user
-#endif
-
-static inline long copy_from_user(void *to,
-		const void __user * from, unsigned long n)
-{
-	unsigned long res = n;
-	might_fault();
-	if (likely(access_ok(VERIFY_READ, from, n)))
-		res = __copy_from_user(to, from, n);
-	if (unlikely(res))
-		memset(to + (n - res), 0, res);
-	return res;
-}
-
-static inline long copy_to_user(void __user *to,
-		const void *from, unsigned long n)
-{
-	might_fault();
-	if (access_ok(VERIFY_WRITE, to, n))
-		return __copy_to_user(to, from, n);
-	else
-		return n;
-}
-
 /*
  * Copy a null terminated string from userspace.
  */
@@ -348,4 +227,6 @@ clear_user(void __user *to, unsigned long n)
 	return __clear_user(to, n);
 }
 
+#include <asm/extable.h>
+
 #endif /* __ASM_GENERIC_UACCESS_H */
diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h
index f30c187ed785..e0cbfb09e60f 100644
--- a/include/linux/uaccess.h
+++ b/include/linux/uaccess.h
@@ -2,8 +2,199 @@
 #define __LINUX_UACCESS_H__
 
 #include <linux/sched.h>
+#include <linux/thread_info.h>
+#include <linux/kasan-checks.h>
+
+#define VERIFY_READ 0
+#define VERIFY_WRITE 1
+
+#define uaccess_kernel() segment_eq(get_fs(), KERNEL_DS)
+
 #include <asm/uaccess.h>
 
+/*
+ * Architectures should provide two primitives (raw_copy_{to,from}_user())
+ * and get rid of their private instances of copy_{to,from}_user() and
+ * __copy_{to,from}_user{,_inatomic}().
+ *
+ * raw_copy_{to,from}_user(to, from, size) should copy up to size bytes and
+ * return the amount left to copy.  They should assume that access_ok() has
+ * already been checked (and succeeded); they should *not* zero-pad anything.
+ * No KASAN or object size checks either - those belong here.
+ *
+ * Both of these functions should attempt to copy size bytes starting at from
+ * into the area starting at to.  They must not fetch or store anything
+ * outside of those areas.  Return value must be between 0 (everything
+ * copied successfully) and size (nothing copied).
+ *
+ * If raw_copy_{to,from}_user(to, from, size) returns N, size - N bytes starting
+ * at to must become equal to the bytes fetched from the corresponding area
+ * starting at from.  All data past to + size - N must be left unmodified.
+ *
+ * If copying succeeds, the return value must be 0.  If some data cannot be
+ * fetched, it is permitted to copy less than had been fetched; the only
+ * hard requirement is that not storing anything at all (i.e. returning size)
+ * should happen only when nothing could be copied.  In other words, you don't
+ * have to squeeze as much as possible - it is allowed, but not necessary.
+ *
+ * For raw_copy_from_user() to always points to kernel memory and no faults
+ * on store should happen.  Interpretation of from is affected by set_fs().
+ * For raw_copy_to_user() it's the other way round.
+ *
+ * Both can be inlined - it's up to architectures whether it wants to bother
+ * with that.  They should not be used directly; they are used to implement
+ * the 6 functions (copy_{to,from}_user(), __copy_{to,from}_user_inatomic())
+ * that are used instead.  Out of those, __... ones are inlined.  Plain
+ * copy_{to,from}_user() might or might not be inlined.  If you want them
+ * inlined, have asm/uaccess.h define INLINE_COPY_{TO,FROM}_USER.
+ *
+ * NOTE: only copy_from_user() zero-pads the destination in case of short copy.
+ * Neither __copy_from_user() nor __copy_from_user_inatomic() zero anything
+ * at all; their callers absolutely must check the return value.
+ *
+ * Biarch ones should also provide raw_copy_in_user() - similar to the above,
+ * but both source and destination are __user pointers (affected by set_fs()
+ * as usual) and both source and destination can trigger faults.
+ */
+
+static __always_inline unsigned long
+__copy_from_user_inatomic(void *to, const void __user *from, unsigned long n)
+{
+	kasan_check_write(to, n);
+	check_object_size(to, n, false);
+	return raw_copy_from_user(to, from, n);
+}
+
+static __always_inline unsigned long
+__copy_from_user(void *to, const void __user *from, unsigned long n)
+{
+	might_fault();
+	kasan_check_write(to, n);
+	check_object_size(to, n, false);
+	return raw_copy_from_user(to, from, n);
+}
+
+/**
+ * __copy_to_user_inatomic: - Copy a block of data into user space, with less checking.
+ * @to:   Destination address, in user space.
+ * @from: Source address, in kernel space.
+ * @n:    Number of bytes to copy.
+ *
+ * Context: User context only.
+ *
+ * Copy data from kernel space to user space.  Caller must check
+ * the specified block with access_ok() before calling this function.
+ * The caller should also make sure he pins the user space address
+ * so that we don't result in page fault and sleep.
+ */
+static __always_inline unsigned long
+__copy_to_user_inatomic(void __user *to, const void *from, unsigned long n)
+{
+	kasan_check_read(from, n);
+	check_object_size(from, n, true);
+	return raw_copy_to_user(to, from, n);
+}
+
+static __always_inline unsigned long
+__copy_to_user(void __user *to, const void *from, unsigned long n)
+{
+	might_fault();
+	kasan_check_read(from, n);
+	check_object_size(from, n, true);
+	return raw_copy_to_user(to, from, n);
+}
+
+#ifdef INLINE_COPY_FROM_USER
+static inline unsigned long
+_copy_from_user(void *to, const void __user *from, unsigned long n)
+{
+	unsigned long res = n;
+	if (likely(access_ok(VERIFY_READ, from, n)))
+		res = raw_copy_from_user(to, from, n);
+	if (unlikely(res))
+		memset(to + (n - res), 0, res);
+	return res;
+}
+#else
+extern unsigned long
+_copy_from_user(void *, const void __user *, unsigned long);
+#endif
+
+#ifdef INLINE_COPY_TO_USER
+static inline unsigned long
+_copy_to_user(void __user *to, const void *from, unsigned long n)
+{
+	if (access_ok(VERIFY_WRITE, to, n))
+		n = raw_copy_to_user(to, from, n);
+	return n;
+}
+#else
+extern unsigned long
+_copy_to_user(void __user *, const void *, unsigned long);
+#endif
+
+extern void __compiletime_error("usercopy buffer size is too small")
+__bad_copy_user(void);
+
+static inline void copy_user_overflow(int size, unsigned long count)
+{
+	WARN(1, "Buffer overflow detected (%d < %lu)!\n", size, count);
+}
+
+static __always_inline unsigned long __must_check
+copy_from_user(void *to, const void __user *from, unsigned long n)
+{
+	int sz = __compiletime_object_size(to);
+
+	might_fault();
+	kasan_check_write(to, n);
+
+	if (likely(sz < 0 || sz >= n)) {
+		check_object_size(to, n, false);
+		n = _copy_from_user(to, from, n);
+	} else if (!__builtin_constant_p(n))
+		copy_user_overflow(sz, n);
+	else
+		__bad_copy_user();
+
+	return n;
+}
+
+static __always_inline unsigned long __must_check
+copy_to_user(void __user *to, const void *from, unsigned long n)
+{
+	int sz = __compiletime_object_size(from);
+
+	kasan_check_read(from, n);
+	might_fault();
+
+	if (likely(sz < 0 || sz >= n)) {
+		check_object_size(from, n, true);
+		n = _copy_to_user(to, from, n);
+	} else if (!__builtin_constant_p(n))
+		copy_user_overflow(sz, n);
+	else
+		__bad_copy_user();
+
+	return n;
+}
+#ifdef CONFIG_COMPAT
+static __always_inline unsigned long __must_check
+__copy_in_user(void __user *to, const void *from, unsigned long n)
+{
+	might_fault();
+	return raw_copy_in_user(to, from, n);
+}
+static __always_inline unsigned long __must_check
+copy_in_user(void __user *to, const void *from, unsigned long n)
+{
+	might_fault();
+	if (access_ok(VERIFY_WRITE, to, n) && access_ok(VERIFY_READ, from, n))
+		n = raw_copy_in_user(to, from, n);
+	return n;
+}
+#endif
+
 static __always_inline void pagefault_disabled_inc(void)
 {
 	current->pagefault_disabled++;
@@ -67,12 +258,6 @@ static inline unsigned long __copy_from_user_inatomic_nocache(void *to,
 	return __copy_from_user_inatomic(to, from, n);
 }
 
-static inline unsigned long __copy_from_user_nocache(void *to,
-				const void __user *from, unsigned long n)
-{
-	return __copy_from_user(to, from, n);
-}
-
 #endif		/* ARCH_HAS_NOCACHE_UACCESS */
 
 /*
diff --git a/include/rdma/ib.h b/include/rdma/ib.h
index 9b4c22a36931..66dbed0c146d 100644
--- a/include/rdma/ib.h
+++ b/include/rdma/ib.h
@@ -100,7 +100,7 @@ struct sockaddr_ib {
  */
 static inline bool ib_safe_file_access(struct file *filp)
 {
-	return filp->f_cred == current_cred() && segment_eq(get_fs(), USER_DS);
+	return filp->f_cred == current_cred() && !uaccess_kernel();
 }
 
 #endif /* _RDMA_IB_H */