x86/debug: Sync BTF earlier

Move the BTF sync near the DR6 load, as this will be the only common
code guaranteed to run on every #DB.

Signed-off-by: Peter Zijlstra (Intel) <[email protected]>
Signed-off-by: Thomas Gleixner <[email protected]>
Tested-by: Daniel Thompson <[email protected]>
Acked-by: Andy Lutomirski <[email protected]>
Link: https://lore.kernel.org/r/[email protected]

arch/x86/kernel/traps.c

@@ -749,6 +749,13 @@ static __always_inline unsigned long debug_read_clear_dr6(void)
 	/* Filter out all the reserved bits which are preset to 1 */
 	dr6 &= ~DR6_RESERVED;
 
+	/*
+	 * The SDM says "The processor clears the BTF flag when it
+	 * generates a debug exception."  Clear TIF_BLOCKSTEP to keep
+	 * TIF_BLOCKSTEP in sync with the hardware BTF flag.
+	 */
+	clear_thread_flag(TIF_BLOCKSTEP);
+
 	return dr6;
 }
 
@@ -782,13 +789,6 @@ static void handle_debug(struct pt_regs *regs, unsigned long dr6, bool user)
 	bool user_icebp;
 	int si_code;
 
-	/*
-	 * The SDM says "The processor clears the BTF flag when it
-	 * generates a debug exception."  Clear TIF_BLOCKSTEP to keep
-	 * TIF_BLOCKSTEP in sync with the hardware BTF flag.
-	 */
-	clear_thread_flag(TIF_BLOCKSTEP);
-
 	/*
 	 * If DR6 is zero, no point in trying to handle it. The kernel is
 	 * not using INT1.