[PATCH v2 6/6] riscv: Add KPROBES_ON_FTRACE supported

[guoren at kernel.org]

From: Guo Ren <guoren at linux.alibaba.com>

This patch adds support for kprobes on ftrace call sites to avoids
much of the overhead with regular kprobes. Try it with simple
steps:

1. Get _do_fork ftrace call site.
Dump of assembler code for function _do_fork:
   0xffffffe00020af64 <+0>:     addi    sp,sp,-128
   0xffffffe00020af66 <+2>:     sd      s0,112(sp)
   0xffffffe00020af68 <+4>:     sd      ra,120(sp)
   0xffffffe00020af6a <+6>:     addi    s0,sp,128
   0xffffffe00020af6c <+8>:     sd      s1,104(sp)
   0xffffffe00020af6e <+10>:    sd      s2,96(sp)
   0xffffffe00020af70 <+12>:    sd      s3,88(sp)
   0xffffffe00020af72 <+14>:    sd      s4,80(sp)
   0xffffffe00020af74 <+16>:    sd      s5,72(sp)
   0xffffffe00020af76 <+18>:    sd      s6,64(sp)
   0xffffffe00020af78 <+20>:    sd      s7,56(sp)
   0xffffffe00020af7a <+22>:    mv      s4,a0
   0xffffffe00020af7c <+24>:    mv      a0,ra
   0xffffffe00020af7e <+26>:    nop	<<<<<<<< here!
   0xffffffe00020af82 <+30>:    nop
   0xffffffe00020af86 <+34>:    ld      s3,0(s4)

2. Set _do_fork+26 as the kprobe.
  echo 'p:myprobe _do_fork+26 dfd=%a0 filename=%a1 flags=%a2 mode=+4($stack)' > /sys/kernel/debug/tracing/kprobe_events
  echo 1 > /sys/kernel/debug/tracing/events/kprobes/enable
  cat /sys/kernel/debug/tracing/trace
  tracer: nop

  entries-in-buffer/entries-written: 3/3   #P:1

                               _-----=> irqs-off
                              / _----=> need-resched
                             | / _---=> hardirq/softirq
                             || / _--=> preempt-depth
                             ||| /     delay
            TASK-PID   CPU#  ||||    TIMESTAMP  FUNCTION
               | |       |   ||||       |         |
              sh-87    [000] ....   551.557031: myprobe: (_do_fork+0x1a/0x2e6) dfd=0xffffffe00020af7e filename=0xffffffe00020b34e flags=0xffffffe00101e7c0 mode=0x20af86ffffffe0

  cat /sys/kernel/debug/kprobes/list
ffffffe00020af7e  k  _do_fork+0x1a    [FTRACE]
                                       ^^^^^^

Signed-off-by: Guo Ren <guoren at linux.alibaba.com>
Cc: Masami Hiramatsu <mhiramat at kernel.org>
Cc: Palmer Dabbelt <palmerdabbelt at google.com>
Cc: Paul Walmsley <paul.walmsley at sifive.com>
Cc: Björn Töpel <bjorn.topel at gmail.com>
Cc: Zong Li <zong.li at sifive.com>
Cc: Pekka Enberg <penberg at kernel.org>
---
 arch/riscv/Kconfig                |  1 +
 arch/riscv/kernel/probes/Makefile |  1 +
 arch/riscv/kernel/probes/ftrace.c | 53 +++++++++++++++++++++++++++++++++++++++
 3 files changed, 55 insertions(+)
 create mode 100644 arch/riscv/kernel/probes/ftrace.c

diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index f927a91..91bfc6c 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -58,6 +58,7 @@ config RISCV
 	select HAVE_FUTEX_CMPXCHG if FUTEX
 	select HAVE_GENERIC_VDSO if MMU && 64BIT
 	select HAVE_KPROBES
+	select HAVE_KPROBES_ON_FTRACE
 	select HAVE_KRETPROBES
 	select HAVE_PCI
 	select HAVE_PERF_EVENTS
diff --git a/arch/riscv/kernel/probes/Makefile b/arch/riscv/kernel/probes/Makefile
index cb62991..7f0840d 100644
--- a/arch/riscv/kernel/probes/Makefile
+++ b/arch/riscv/kernel/probes/Makefile
@@ -1,5 +1,6 @@
 # SPDX-License-Identifier: GPL-2.0
 obj-$(CONFIG_KPROBES)		+= kprobes.o decode-insn.o simulate-insn.o
 obj-$(CONFIG_KPROBES)		+= kprobes_trampoline.o
+obj-$(CONFIG_KPROBES_ON_FTRACE)	+= ftrace.o
 obj-$(CONFIG_UPROBES)		+= uprobes.o decode-insn.o simulate-insn.o
 CFLAGS_REMOVE_simulate-insn.o = $(CC_FLAGS_FTRACE)
diff --git a/arch/riscv/kernel/probes/ftrace.c b/arch/riscv/kernel/probes/ftrace.c
new file mode 100644
index 00000000..08fc1cc
--- /dev/null
+++ b/arch/riscv/kernel/probes/ftrace.c
@@ -0,0 +1,53 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/kprobes.h>
+
+/* Ftrace callback handler for kprobes -- called under preepmt disabed */
+void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip,
+			   struct ftrace_ops *ops, struct pt_regs *regs)
+{
+	struct kprobe *p;
+	struct kprobe_ctlblk *kcb;
+
+	p = get_kprobe((kprobe_opcode_t *)ip);
+	if (unlikely(!p) || kprobe_disabled(p))
+		return;
+
+	kcb = get_kprobe_ctlblk();
+	if (kprobe_running()) {
+		kprobes_inc_nmissed_count(p);
+	} else {
+		/*
+		 * The regs->epc hasn't been saved by SAVE_ALL in mcount-dyn.S
+		 * So no need to resume it, just for kprobe handler.
+		 */
+		instruction_pointer_set(regs, ip);
+		__this_cpu_write(current_kprobe, p);
+		kcb->kprobe_status = KPROBE_HIT_ACTIVE;
+		if (!p->pre_handler || !p->pre_handler(p, regs)) {
+			/*
+			 * Emulate singlestep (and also recover regs->pc)
+			 * as if there is a nop
+			 */
+			instruction_pointer_set(regs,
+				(unsigned long)p->addr + MCOUNT_INSN_SIZE);
+			if (unlikely(p->post_handler)) {
+				kcb->kprobe_status = KPROBE_HIT_SSDONE;
+				p->post_handler(p, regs, 0);
+			}
+		}
+
+		/*
+		 * If pre_handler returns !0, it changes regs->pc. We have to
+		 * skip emulating post_handler.
+		 */
+		__this_cpu_write(current_kprobe, NULL);
+	}
+}
+NOKPROBE_SYMBOL(kprobe_ftrace_handler);
+
+int arch_prepare_kprobe_ftrace(struct kprobe *p)
+{
+	p->ainsn.api.insn = NULL;
+	return 0;
+}
-- 
2.7.4