arm64: Add trampoline code for kretprobes

The trampoline code is used by kretprobes to capture a return from a probed
function.  This is done by saving the registers, calling the handler, and
restoring the registers. The code then returns to the original saved caller
return address. It is necessary to do this directly instead of using a
software breakpoint because the code used in processing that breakpoint
could itself be kprobe'd and cause a problematic reentry into the debug
exception handler.

Signed-off-by: William Cohen <wcohen@redhat.com>
Signed-off-by: David A. Long <dave.long@linaro.org>
Acked-by: Masami Hiramatsu <mhiramat@kernel.org>
[catalin.marinas@arm.com: removed unnecessary masking of the PSTATE bits]
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>

arch/arm64/include/asm/kprobes.h

@@ -56,5 +56,7 @@ int kprobe_exceptions_notify(struct notifier_block *self,
 			     unsigned long val, void *data);
 int kprobe_breakpoint_handler(struct pt_regs *regs, unsigned int esr);
 int kprobe_single_step_handler(struct pt_regs *regs, unsigned int esr);
+void kretprobe_trampoline(void);
+void __kprobes *trampoline_probe_handler(struct pt_regs *regs);
 
 #endif /* _ARM_KPROBES_H */

arch/arm64/kernel/asm-offsets.c

@@ -51,6 +51,17 @@ int main(void)
   DEFINE(S_X5,			offsetof(struct pt_regs, regs[5]));
   DEFINE(S_X6,			offsetof(struct pt_regs, regs[6]));
   DEFINE(S_X7,			offsetof(struct pt_regs, regs[7]));
+  DEFINE(S_X8,			offsetof(struct pt_regs, regs[8]));
+  DEFINE(S_X10,			offsetof(struct pt_regs, regs[10]));
+  DEFINE(S_X12,			offsetof(struct pt_regs, regs[12]));
+  DEFINE(S_X14,			offsetof(struct pt_regs, regs[14]));
+  DEFINE(S_X16,			offsetof(struct pt_regs, regs[16]));
+  DEFINE(S_X18,			offsetof(struct pt_regs, regs[18]));
+  DEFINE(S_X20,			offsetof(struct pt_regs, regs[20]));
+  DEFINE(S_X22,			offsetof(struct pt_regs, regs[22]));
+  DEFINE(S_X24,			offsetof(struct pt_regs, regs[24]));
+  DEFINE(S_X26,			offsetof(struct pt_regs, regs[26]));
+  DEFINE(S_X28,			offsetof(struct pt_regs, regs[28]));
   DEFINE(S_LR,			offsetof(struct pt_regs, regs[30]));
   DEFINE(S_SP,			offsetof(struct pt_regs, sp));
 #ifdef CONFIG_COMPAT

arch/arm64/kernel/probes/Makefile

@@ -1,2 +1,3 @@
 obj-$(CONFIG_KPROBES)		+= kprobes.o decode-insn.o	\
+				   kprobes_trampoline.o		\
 				   simulate-insn.o

arch/arm64/kernel/probes/kprobes.c

@@ -576,6 +576,11 @@ bool arch_within_kprobe_blacklist(unsigned long addr)
 	return false;
 }
 
+void __kprobes __used *trampoline_probe_handler(struct pt_regs *regs)
+{
+	return NULL;
+}
+
 int __init arch_init_kprobes(void)
 {
 	return 0;

arch/arm64/kernel/probes/kprobes_trampoline.S

@@ -0,0 +1,81 @@
+/*
+ * trampoline entry and return code for kretprobes.
+ */
+
+#include <linux/linkage.h>
+#include <asm/asm-offsets.h>
+#include <asm/assembler.h>
+
+	.text
+
+	.macro	save_all_base_regs
+	stp x0, x1, [sp, #S_X0]
+	stp x2, x3, [sp, #S_X2]
+	stp x4, x5, [sp, #S_X4]
+	stp x6, x7, [sp, #S_X6]
+	stp x8, x9, [sp, #S_X8]
+	stp x10, x11, [sp, #S_X10]
+	stp x12, x13, [sp, #S_X12]
+	stp x14, x15, [sp, #S_X14]
+	stp x16, x17, [sp, #S_X16]
+	stp x18, x19, [sp, #S_X18]
+	stp x20, x21, [sp, #S_X20]
+	stp x22, x23, [sp, #S_X22]
+	stp x24, x25, [sp, #S_X24]
+	stp x26, x27, [sp, #S_X26]
+	stp x28, x29, [sp, #S_X28]
+	add x0, sp, #S_FRAME_SIZE
+	stp lr, x0, [sp, #S_LR]
+	/*
+	 * Construct a useful saved PSTATE
+	 */
+	mrs x0, nzcv
+	mrs x1, daif
+	orr x0, x0, x1
+	mrs x1, CurrentEL
+	orr x0, x0, x1
+	mrs x1, SPSel
+	orr x0, x0, x1
+	stp xzr, x0, [sp, #S_PC]
+	.endm
+
+	.macro	restore_all_base_regs
+	ldr x0, [sp, #S_PSTATE]
+	and x0, x0, #(PSR_N_BIT | PSR_Z_BIT | PSR_C_BIT | PSR_V_BIT)
+	msr nzcv, x0
+	ldp x0, x1, [sp, #S_X0]
+	ldp x2, x3, [sp, #S_X2]
+	ldp x4, x5, [sp, #S_X4]
+	ldp x6, x7, [sp, #S_X6]
+	ldp x8, x9, [sp, #S_X8]
+	ldp x10, x11, [sp, #S_X10]
+	ldp x12, x13, [sp, #S_X12]
+	ldp x14, x15, [sp, #S_X14]
+	ldp x16, x17, [sp, #S_X16]
+	ldp x18, x19, [sp, #S_X18]
+	ldp x20, x21, [sp, #S_X20]
+	ldp x22, x23, [sp, #S_X22]
+	ldp x24, x25, [sp, #S_X24]
+	ldp x26, x27, [sp, #S_X26]
+	ldp x28, x29, [sp, #S_X28]
+	.endm
+
+ENTRY(kretprobe_trampoline)
+	sub sp, sp, #S_FRAME_SIZE
+
+	save_all_base_regs
+
+	mov x0, sp
+	bl trampoline_probe_handler
+	/*
+	 * Replace trampoline address in lr with actual orig_ret_addr return
+	 * address.
+	 */
+	mov lr, x0
+
+	restore_all_base_regs
+
+	add sp, sp, #S_FRAME_SIZE
+	ret
+
+ENDPROC(kretprobe_trampoline)