[PATCH v3 2/4] x86/traps: Print non-canonical address on #GP

[Jann Horn]

A frequent cause of #GP exceptions are memory accesses to non-canonical
addresses. Unlike #PF, #GP doesn't come with a fault address in CR2, so
the kernel doesn't currently print the fault address for #GP.
Luckily, we already have the necessary infrastructure for decoding X86
instructions and computing the memory address that is being accessed;
hook it up to the #GP handler so that we can figure out whether the #GP
looks like it was caused by a non-canonical address, and if so, print
that address.

While it is already possible to compute the faulting address manually by
disassembling the opcode dump and evaluating the instruction against the
register dump, this should make it slightly easier to identify crashes
at a glance.

Signed-off-by: Jann Horn <jannh@xxxxxxxxxx>
---

Notes:
    v2:
     - print different message for segment-related GP (Borislav)
     - rewrite check for non-canonical address (Sean)
     - make it clear we don't know for sure why the GP happened (Andy)
    v3:
     - change message format to one line (Borislav)
    
    I have already sent a patch to syzkaller that relaxes their parsing of GPF
    messages (https://github.com/google/syzkaller/commit/432c7650) such that
    changes like the one in this patch don't break it.
    That patch has already made its way into syzbot's syzkaller instances
    according to <https://syzkaller.appspot.com/upstream>.

 arch/x86/kernel/traps.c | 56 ++++++++++++++++++++++++++++++++++++++---
 1 file changed, 53 insertions(+), 3 deletions(-)

diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index c90312146da0..19afedcd6f4e 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -56,6 +56,8 @@
 #include <asm/mpx.h>
 #include <asm/vm86.h>
 #include <asm/umip.h>
+#include <asm/insn.h>
+#include <asm/insn-eval.h>
 
 #ifdef CONFIG_X86_64
 #include <asm/x86_init.h>
@@ -509,11 +511,45 @@ dotraplinkage void do_bounds(struct pt_regs *regs, long error_code)
 	do_trap(X86_TRAP_BR, SIGSEGV, "bounds", regs, error_code, 0, NULL);
 }
 
+/*
+ * On 64-bit, if an uncaught #GP occurs while dereferencing a non-canonical
+ * address, return that address.
+ */
+static unsigned long get_kernel_gp_address(struct pt_regs *regs)
+{
+#ifdef CONFIG_X86_64
+	u8 insn_bytes[MAX_INSN_SIZE];
+	struct insn insn;
+	unsigned long addr_ref;
+
+	if (probe_kernel_read(insn_bytes, (void *)regs->ip, MAX_INSN_SIZE))
+		return 0;
+
+	kernel_insn_init(&insn, insn_bytes, MAX_INSN_SIZE);
+	insn_get_modrm(&insn);
+	insn_get_sib(&insn);
+	addr_ref = (unsigned long)insn_get_addr_ref(&insn, regs);
+
+	/* Bail out if insn_get_addr_ref() failed or we got a kernel address. */
+	if (addr_ref >= ~__VIRTUAL_MASK)
+		return 0;
+
+	/* Bail out if the entire operand is in the canonical user half. */
+	if (addr_ref + insn.opnd_bytes - 1 <= __VIRTUAL_MASK)
+		return 0;
+
+	return addr_ref;
+#else
+	return 0;
+#endif
+}
+
+#define GPFSTR "general protection fault"
 dotraplinkage void
 do_general_protection(struct pt_regs *regs, long error_code)
 {
-	const char *desc = "general protection fault";
 	struct task_struct *tsk;
+	char desc[90] = GPFSTR;
 
 	RCU_LOCKDEP_WARN(!rcu_is_watching(), "entry code didn't wake RCU");
 	cond_local_irq_enable(regs);
@@ -531,6 +567,8 @@ do_general_protection(struct pt_regs *regs, long error_code)
 
 	tsk = current;
 	if (!user_mode(regs)) {
+		unsigned long non_canonical_addr = 0;
+
 		if (fixup_exception(regs, X86_TRAP_GP, error_code, 0))
 			return;
 
@@ -547,8 +585,20 @@ do_general_protection(struct pt_regs *regs, long error_code)
 			return;
 
 		if (notify_die(DIE_GPF, desc, regs, error_code,
-			       X86_TRAP_GP, SIGSEGV) != NOTIFY_STOP)
-			die(desc, regs, error_code);
+			       X86_TRAP_GP, SIGSEGV) == NOTIFY_STOP)
+			return;
+
+		if (error_code)
+			snprintf(desc, sizeof(desc), "segment-related " GPFSTR);
+		else
+			non_canonical_addr = get_kernel_gp_address(regs);
+
+		if (non_canonical_addr)
+			snprintf(desc, sizeof(desc),
+			    GPFSTR " probably for non-canonical address 0x%lx",
+			    non_canonical_addr);
+
+		die(desc, regs, error_code);
 		return;
 	}
 
-- 
2.24.0.432.g9d3f5f5b63-goog