powerpc/kprobes: Prefer ftrace when probing function entry

KPROBES_ON_FTRACE avoids much of the overhead of regular kprobes as it
eliminates the need for a trap, as well as the need to emulate or single-step
instructions.

Though OPTPROBES provides us with similar performance, we have limited
optprobes trampoline slots. As such, when asked to probe at a function
entry, default to using the ftrace infrastructure.

With:
  # cd /sys/kernel/debug/tracing
  # echo 'p _do_fork' > kprobe_events

before patch:
  # cat ../kprobes/list
  c0000000000daf08  k  _do_fork+0x8    [DISABLED]
  c000000000044fc0  k  kretprobe_trampoline+0x0    [OPTIMIZED]

and after patch:
  # cat ../kprobes/list
  c0000000000d074c  k  _do_fork+0xc    [DISABLED][FTRACE]
  c0000000000412b0  k  kretprobe_trampoline+0x0    [OPTIMIZED]
Signed-off-by: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

arch/powerpc/kernel/kprobes.c

@@ -49,8 +49,21 @@ kprobe_opcode_t *kprobe_lookup_name(const char *name, unsigned int offset)
 #ifdef PPC64_ELF_ABI_v2
 	/* PPC64 ABIv2 needs local entry point */
 	addr = (kprobe_opcode_t *)kallsyms_lookup_name(name);
-	if (addr && !offset)
-		addr = (kprobe_opcode_t *)ppc_function_entry(addr);
+	if (addr && !offset) {
+#ifdef CONFIG_KPROBES_ON_FTRACE
+		unsigned long faddr;
+		/*
+		 * Per livepatch.h, ftrace location is always within the first
+		 * 16 bytes of a function on powerpc with -mprofile-kernel.
+		 */
+		faddr = ftrace_location_range((unsigned long)addr,
+					      (unsigned long)addr + 16);
+		if (faddr)
+			addr = (kprobe_opcode_t *)faddr;
+		else
+#endif
+			addr = (kprobe_opcode_t *)ppc_function_entry(addr);
+	}
 #elif defined(PPC64_ELF_ABI_v1)
 	/*
 	 * 64bit powerpc ABIv1 uses function descriptors: