mm: Add fault_in_subpage_writeable() to probe at sub-page granularity

On hardware with features like arm64 MTE or SPARC ADI, an access fault
can be triggered at sub-page granularity. Depending on how the
fault_in_writeable() function is used, the caller can get into a
live-lock by continuously retrying the fault-in on an address different
from the one where the uaccess failed.

In the majority of cases progress is ensured by the following
conditions:

1. copy_to_user_nofault() guarantees at least one byte access if the
   user address is not faulting.

2. The fault_in_writeable() loop is resumed from the first address that
   could not be accessed by copy_to_user_nofault().

If the loop iteration is restarted from an earlier (initial) point, the
loop is repeated with the same conditions and it would live-lock.

Introduce an arch-specific probe_subpage_writeable() and call it from
the newly added fault_in_subpage_writeable() function. The arch code
with sub-page faults will have to implement the specific probing
functionality.

Note that no other fault_in_subpage_*() functions are added since they
have no callers currently susceptible to a live-lock.

Signed-off-by: Catalin Marinas <[email protected]>
Cc: Andrew Morton <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Catalin Marinas <[email protected]>

Author: ctmarinas

arch/Kconfig

@@ -24,6 +24,13 @@ config KEXEC_ELF
 config HAVE_IMA_KEXEC
 	bool
 
+config ARCH_HAS_SUBPAGE_FAULTS
+	bool
+	help
+	  Select if the architecture can check permissions at sub-page
+	  granularity (e.g. arm64 MTE). The probe_user_*() functions
+	  must be implemented.
+
 config HOTPLUG_SMT
 	bool
 

include/linux/pagemap.h

@@ -1046,6 +1046,7 @@ void folio_add_wait_queue(struct folio *folio, wait_queue_entry_t *waiter);
  * Fault in userspace address range.
  */
 size_t fault_in_writeable(char __user *uaddr, size_t size);
+size_t fault_in_subpage_writeable(char __user *uaddr, size_t size);
 size_t fault_in_safe_writeable(const char __user *uaddr, size_t size);
 size_t fault_in_readable(const char __user *uaddr, size_t size);
 

include/linux/uaccess.h

@@ -231,6 +231,28 @@ static inline bool pagefault_disabled(void)
  */
 #define faulthandler_disabled() (pagefault_disabled() || in_atomic())
 
+#ifndef CONFIG_ARCH_HAS_SUBPAGE_FAULTS
+
+/**
+ * probe_subpage_writeable: probe the user range for write faults at sub-page
+ *			    granularity (e.g. arm64 MTE)
+ * @uaddr: start of address range
+ * @size: size of address range
+ *
+ * Returns 0 on success, the number of bytes not probed on fault.
+ *
+ * It is expected that the caller checked for the write permission of each
+ * page in the range either by put_user() or GUP. The architecture port can
+ * implement a more efficient get_user() probing if the same sub-page faults
+ * are triggered by either a read or a write.
+ */
+static inline size_t probe_subpage_writeable(char __user *uaddr, size_t size)
+{
+	return 0;
+}
+
+#endif /* CONFIG_ARCH_HAS_SUBPAGE_FAULTS */
+
 #ifndef ARCH_HAS_NOCACHE_UACCESS
 
 static inline __must_check unsigned long

mm/gup.c

@@ -1648,6 +1648,35 @@ size_t fault_in_writeable(char __user *uaddr, size_t size)
 }
 EXPORT_SYMBOL(fault_in_writeable);
 
+/**
+ * fault_in_subpage_writeable - fault in an address range for writing
+ * @uaddr: start of address range
+ * @size: size of address range
+ *
+ * Fault in a user address range for writing while checking for permissions at
+ * sub-page granularity (e.g. arm64 MTE). This function should be used when
+ * the caller cannot guarantee forward progress of a copy_to_user() loop.
+ *
+ * Returns the number of bytes not faulted in (like copy_to_user() and
+ * copy_from_user()).
+ */
+size_t fault_in_subpage_writeable(char __user *uaddr, size_t size)
+{
+	size_t faulted_in;
+
+	/*
+	 * Attempt faulting in at page granularity first for page table
+	 * permission checking. The arch-specific probe_subpage_writeable()
+	 * functions may not check for this.
+	 */
+	faulted_in = size - fault_in_writeable(uaddr, size);
+	if (faulted_in)
+		faulted_in -= probe_subpage_writeable(uaddr, faulted_in);
+
+	return size - faulted_in;
+}
+EXPORT_SYMBOL(fault_in_subpage_writeable);
+
 /*
  * fault_in_safe_writeable - fault in an address range for writing
  * @uaddr: start of address range