printk: hash addresses printed with %p

Currently there exist approximately 14 000 places in the kernel where
addresses are being printed using an unadorned %p. This potentially
leaks sensitive information regarding the Kernel layout in memory. Many
of these calls are stale, instead of fixing every call lets hash the
address by default before printing. This will of course break some
users, forcing code printing needed addresses to be updated.

Code that _really_ needs the address will soon be able to use the new
printk specifier %px to print the address.

For what it's worth, usage of unadorned %p can be broken down as
follows (thanks to Joe Perches).

$ git grep -E '%p[^A-Za-z0-9]' | cut -f1 -d"/" | sort | uniq -c
   1084 arch
     20 block
     10 crypto
     32 Documentation
   8121 drivers
   1221 fs
    143 include
    101 kernel
     69 lib
    100 mm
   1510 net
     40 samples
      7 scripts
     11 security
    166 sound
    152 tools
      2 virt

Add function ptr_to_id() to map an address to a 32 bit unique
identifier. Hash any unadorned usage of specifier %p and any malformed
specifiers.

Signed-off-by: Tobin C. Harding <me@tobin.cc>

1 files changed, 74 insertions, 7 deletions

diff --git a/lib/vsprintf.c b/lib/vsprintf.c
index 8dc5cf85cef47..d69452a0f2fa5 100644
--- a/lib/vsprintf.c
+++ b/lib/vsprintf.c
@@ -33,6 +33,8 @@
 #include <linux/uuid.h>
 #include <linux/of.h>
 #include <net/addrconf.h>
+#include <linux/siphash.h>
+#include <linux/compiler.h>
 #ifdef CONFIG_BLOCK
 #include <linux/blkdev.h>
 #endif
@@ -1644,6 +1646,73 @@ char *device_node_string(char *buf, char *end, struct device_node *dn,
 	return widen_string(buf, buf - buf_start, end, spec);
 }
 
+static bool have_filled_random_ptr_key __read_mostly;
+static siphash_key_t ptr_key __read_mostly;
+
+static void fill_random_ptr_key(struct random_ready_callback *unused)
+{
+	get_random_bytes(&ptr_key, sizeof(ptr_key));
+	/*
+	 * have_filled_random_ptr_key==true is dependent on get_random_bytes().
+	 * ptr_to_id() needs to see have_filled_random_ptr_key==true
+	 * after get_random_bytes() returns.
+	 */
+	smp_mb();
+	WRITE_ONCE(have_filled_random_ptr_key, true);
+}
+
+static struct random_ready_callback random_ready = {
+	.func = fill_random_ptr_key
+};
+
+static int __init initialize_ptr_random(void)
+{
+	int ret = add_random_ready_callback(&random_ready);
+
+	if (!ret) {
+		return 0;
+	} else if (ret == -EALREADY) {
+		fill_random_ptr_key(&random_ready);
+		return 0;
+	}
+
+	return ret;
+}
+early_initcall(initialize_ptr_random);
+
+/* Maps a pointer to a 32 bit unique identifier. */
+static char *ptr_to_id(char *buf, char *end, void *ptr, struct printf_spec spec)
+{
+	unsigned long hashval;
+	const int default_width = 2 * sizeof(ptr);
+
+	if (unlikely(!have_filled_random_ptr_key)) {
+		spec.field_width = default_width;
+		/* string length must be less than default_width */
+		return string(buf, end, "(ptrval)", spec);
+	}
+
+#ifdef CONFIG_64BIT
+	hashval = (unsigned long)siphash_1u64((u64)ptr, &ptr_key);
+	/*
+	 * Mask off the first 32 bits, this makes explicit that we have
+	 * modified the address (and 32 bits is plenty for a unique ID).
+	 */
+	hashval = hashval & 0xffffffff;
+#else
+	hashval = (unsigned long)siphash_1u32((u32)ptr, &ptr_key);
+#endif
+
+	spec.flags |= SMALL;
+	if (spec.field_width == -1) {
+		spec.field_width = default_width;
+		spec.flags |= ZEROPAD;
+	}
+	spec.base = 16;
+
+	return number(buf, end, hashval, spec);
+}
+
 /*
  * Show a '%p' thing.  A kernel extension is that the '%p' is followed
  * by an extra set of alphanumeric characters that are extended format
@@ -1754,6 +1823,9 @@ char *device_node_string(char *buf, char *end, struct device_node *dn,
  * Note: The difference between 'S' and 'F' is that on ia64 and ppc64
  * function pointers are really function descriptors, which contain a
  * pointer to the real address.
+ *
+ * Note: The default behaviour (unadorned %p) is to hash the address,
+ * rendering it useful as a unique identifier.
  */
 static noinline_for_stack
 char *pointer(const char *fmt, char *buf, char *end, void *ptr,
@@ -1869,14 +1941,9 @@ char *pointer(const char *fmt, char *buf, char *end, void *ptr,
 			return device_node_string(buf, end, ptr, spec, fmt + 1);
 		}
 	}
-	spec.flags |= SMALL;
-	if (spec.field_width == -1) {
-		spec.field_width = default_width;
-		spec.flags |= ZEROPAD;
-	}
-	spec.base = 16;
 
-	return number(buf, end, (unsigned long) ptr, spec);
+	/* default is to _not_ leak addresses, hash before printing */
+	return ptr_to_id(buf, end, ptr, spec);
 }
 
 /*