[bpf-next,v2,2/8] uaccess: Add strict non-pagefault kernel-space read function

diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile
index 84373dc9b341..bbc68a54795e 100644
--- a/arch/x86/mm/Makefile
+++ b/arch/x86/mm/Makefile
@@ -13,7 +13,7 @@  CFLAGS_REMOVE_mem_encrypt_identity.o	= -pg
 endif
 
 obj-y	:=  init.o init_$(BITS).o fault.o ioremap.o extable.o pageattr.o mmap.o \
-	    pat.o pgtable.o physaddr.o setup_nx.o tlb.o cpu_entry_area.o
+	    pat.o pgtable.o physaddr.o setup_nx.o tlb.o cpu_entry_area.o maccess.o
 
 # Make sure __phys_addr has no stackprotector
 nostackp := $(call cc-option, -fno-stack-protector)
diff --git a/arch/x86/mm/maccess.c b/arch/x86/mm/maccess.c
new file mode 100644
index 000000000000..fcc55a7cbde2
--- /dev/null
+++ b/arch/x86/mm/maccess.c
@@ -0,0 +1,38 @@ 
+// SPDX-License-Identifier: GPL-2.0-only
+
+#include <linux/uaccess.h>
+#include <linux/kernel.h>
+
+static __always_inline u64 canonical_address(u64 vaddr, u8 vaddr_bits)
+{
+	return ((s64)vaddr << (64 - vaddr_bits)) >> (64 - vaddr_bits);
+}
+
+static __always_inline bool non_canonical_address(u64 vaddr)
+{
+#ifdef CONFIG_X86_64
+	return canonical_address(vaddr, boot_cpu_data.x86_virt_bits) != vaddr;
+#else
+	return false;
+#endif
+}
+
+long probe_kernel_read_strict(void *dst, const void *src, size_t size)
+{
+	u64 addr = (unsigned long)src;
+
+	if (unlikely(addr < TASK_SIZE_MAX || non_canonical_address(addr)))
+		return -EFAULT;
+
+	return __probe_kernel_read(dst, src, size);
+}
+
+long strncpy_from_unsafe_strict(char *dst, const void *unsafe_addr, long count)
+{
+	u64 addr = (unsigned long)unsafe_addr;
+
+	if (unlikely(addr < TASK_SIZE_MAX || non_canonical_address(addr)))
+		return -EFAULT;
+
+	return __strncpy_from_unsafe(dst, unsafe_addr, count);
+}
diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h
index 38555435a64a..67f016010aad 100644
--- a/include/linux/uaccess.h
+++ b/include/linux/uaccess.h
@@ -311,6 +311,7 @@  copy_struct_from_user(void *dst, size_t ksize, const void __user *src,
  * happens, handle that and return -EFAULT.
  */
 extern long probe_kernel_read(void *dst, const void *src, size_t size);
+extern long probe_kernel_read_strict(void *dst, const void *src, size_t size);
 extern long __probe_kernel_read(void *dst, const void *src, size_t size);
 
 /*
@@ -350,6 +351,9 @@  extern long notrace probe_user_write(void __user *dst, const void *src, size_t s
 extern long notrace __probe_user_write(void __user *dst, const void *src, size_t size);
 
 extern long strncpy_from_unsafe(char *dst, const void *unsafe_addr, long count);
+extern long strncpy_from_unsafe_strict(char *dst, const void *unsafe_addr,
+				       long count);
+extern long __strncpy_from_unsafe(char *dst, const void *unsafe_addr, long count);
 extern long strncpy_from_unsafe_user(char *dst, const void __user *unsafe_addr,
 				     long count);
 extern long strnlen_unsafe_user(const void __user *unsafe_addr, long count);
diff --git a/mm/maccess.c b/mm/maccess.c
index 2d3c3d01064c..3ca8d97e5010 100644
--- a/mm/maccess.c
+++ b/mm/maccess.c
@@ -43,11 +43,20 @@  probe_write_common(void __user *dst, const void *src, size_t size)
  * do_page_fault() doesn't attempt to take mmap_sem.  This makes
  * probe_kernel_read() suitable for use within regions where the caller
  * already holds mmap_sem, or other locks which nest inside mmap_sem.
+ *
+ * probe_kernel_read_strict() is the same as probe_kernel_read() except for
+ * the case where architectures have non-overlapping user and kernel address
+ * ranges: probe_kernel_read_strict() will additionally return -EFAULT for
+ * probing memory on a user address range where probe_user_read() is supposed
+ * to be used instead.
  */
 
 long __weak probe_kernel_read(void *dst, const void *src, size_t size)
     __attribute__((alias("__probe_kernel_read")));
 
+long __weak probe_kernel_read_strict(void *dst, const void *src, size_t size)
+    __attribute__((alias("__probe_kernel_read")));
+
 long __probe_kernel_read(void *dst, const void *src, size_t size)
 {
 	long ret;
@@ -157,8 +166,22 @@  EXPORT_SYMBOL_GPL(probe_user_write);
  *
  * If @count is smaller than the length of the string, copies @count-1 bytes,
  * sets the last byte of @dst buffer to NUL and returns @count.
+ *
+ * strncpy_from_unsafe_strict() is the same as strncpy_from_unsafe() except
+ * for the case where architectures have non-overlapping user and kernel address
+ * ranges: strncpy_from_unsafe_strict() will additionally return -EFAULT for
+ * probing memory on a user address range where strncpy_from_unsafe_user() is
+ * supposed to be used instead.
  */
-long strncpy_from_unsafe(char *dst, const void *unsafe_addr, long count)
+
+long __weak strncpy_from_unsafe(char *dst, const void *unsafe_addr, long count)
+    __attribute__((alias("__strncpy_from_unsafe")));
+
+long __weak strncpy_from_unsafe_strict(char *dst, const void *unsafe_addr,
+				       long count)
+    __attribute__((alias("__strncpy_from_unsafe")));
+
+long __strncpy_from_unsafe(char *dst, const void *unsafe_addr, long count)
 {
 	mm_segment_t old_fs = get_fs();
 	const void *src = unsafe_addr;