x86/dumpstack: Dump user space code correctly againx86-urgent-2020-07-25

H.J. reported that post 5.7 a segfault of a user space task does not longer
dump the Code bytes when /proc/sys/debug/exception-trace is enabled. It
prints 'Code: Bad RIP value.' instead.

This was broken by a recent change which made probe_kernel_read() reject
non-kernel addresses.

Update show_opcodes() so it retrieves user space opcodes via
copy_from_user_nmi().

Fixes: 98a23609b103 ("maccess: always use strict semantics for probe_kernel_read")
Reported-by: H.J. Lu <hjl.tools@gmail.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lkml.kernel.org/r/87h7tz306w.fsf@nanos.tec.linutronix.de

1 files changed, 17 insertions, 10 deletions

diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c
index b037cfa7c0c5..7401cc12c3cc 100644
--- a/arch/x86/kernel/dumpstack.c
+++ b/arch/x86/kernel/dumpstack.c
@@ -71,6 +71,22 @@ static void printk_stack_address(unsigned long address, int reliable,
 	printk("%s %s%pB\n", log_lvl, reliable ? "" : "? ", (void *)address);
 }
 
+static int copy_code(struct pt_regs *regs, u8 *buf, unsigned long src,
+		     unsigned int nbytes)
+{
+	if (!user_mode(regs))
+		return copy_from_kernel_nofault(buf, (u8 *)src, nbytes);
+
+	/*
+	 * Make sure userspace isn't trying to trick us into dumping kernel
+	 * memory by pointing the userspace instruction pointer at it.
+	 */
+	if (__chk_range_not_ok(src, nbytes, TASK_SIZE_MAX))
+		return -EINVAL;
+
+	return copy_from_user_nmi(buf, (void __user *)src, nbytes);
+}
+
 /*
  * There are a couple of reasons for the 2/3rd prologue, courtesy of Linus:
  *
@@ -97,17 +113,8 @@ void show_opcodes(struct pt_regs *regs, const char *loglvl)
 #define OPCODE_BUFSIZE (PROLOGUE_SIZE + 1 + EPILOGUE_SIZE)
 	u8 opcodes[OPCODE_BUFSIZE];
 	unsigned long prologue = regs->ip - PROLOGUE_SIZE;
-	bool bad_ip;
-
-	/*
-	 * Make sure userspace isn't trying to trick us into dumping kernel
-	 * memory by pointing the userspace instruction pointer at it.
-	 */
-	bad_ip = user_mode(regs) &&
-		__chk_range_not_ok(prologue, OPCODE_BUFSIZE, TASK_SIZE_MAX);
 
-	if (bad_ip || copy_from_kernel_nofault(opcodes, (u8 *)prologue,
-					OPCODE_BUFSIZE)) {
+	if (copy_code(regs, opcodes, prologue, sizeof(opcodes))) {
 		printk("%sCode: Bad RIP value.\n", loglvl);
 	} else {
 		printk("%sCode: %" __stringify(PROLOGUE_SIZE) "ph <%02x> %"