arm64: implement ftrace with regs

This patch implements FTRACE_WITH_REGS for arm64, which allows a traced
function's arguments (and some other registers) to be captured into a
struct pt_regs, allowing these to be inspected and/or modified. This is
a building block for live-patching, where a function's arguments may be
forwarded to another function. This is also necessary to enable ftrace
and in-kernel pointer authentication at the same time, as it allows the
LR value to be captured and adjusted prior to signing.

Using GCC's -fpatchable-function-entry=N option, we can have the
compiler insert a configurable number of NOPs between the function entry
point and the usual prologue. This also ensures functions are AAPCS
compliant (e.g. disabling inter-procedural register allocation).

For example, with -fpatchable-function-entry=2, GCC 8.1.0 compiles the
following:

| unsigned long bar(void);
|
| unsigned long foo(void)
| {
|         return bar() + 1;
| }

... to:

| <foo>:
|         nop
|         nop
|         stp     x29, x30, [sp, #-16]!
|         mov     x29, sp
|         bl      0 <bar>
|         add     x0, x0, #0x1
|         ldp     x29, x30, [sp], #16
|         ret

This patch builds the kernel with -fpatchable-function-entry=2,
prefixing each function with two NOPs. To trace a function, we replace
these NOPs with a sequence that saves the LR into a GPR, then calls an
ftrace entry assembly function which saves this and other relevant
registers:

| mov	x9, x30
| bl	<ftrace-entry>

Since patchable functions are AAPCS compliant (and the kernel does not
use x18 as a platform register), x9-x18 can be safely clobbered in the
patched sequence and the ftrace entry code.

There are now two ftrace entry functions, ftrace_regs_entry (which saves
all GPRs), and ftrace_entry (which saves the bare minimum). A PLT is
allocated for each within modules.

Signed-off-by: Torsten Duwe <duwe@suse.de>
[Mark: rework asm, comments, PLTs, initialization, commit message]
Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Reviewed-by: Amit Daniel Kachhap <amit.kachhap@arm.com>
Reviewed-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Reviewed-by: Torsten Duwe <duwe@suse.de>
Tested-by: Amit Daniel Kachhap <amit.kachhap@arm.com>
Tested-by: Torsten Duwe <duwe@suse.de>
Cc: AKASHI Takahiro <takahiro.akashi@linaro.org>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Julien Thierry <jthierry@redhat.com>
Cc: Will Deacon <will@kernel.org>

1 files changed, 70 insertions, 14 deletions

diff --git a/arch/arm64/kernel/ftrace.c b/arch/arm64/kernel/ftrace.c
index 822718eafdb4..aea652c33a38 100644
--- a/arch/arm64/kernel/ftrace.c
+++ b/arch/arm64/kernel/ftrace.c
@@ -62,6 +62,19 @@ int ftrace_update_ftrace_func(ftrace_func_t func)
 	return ftrace_modify_code(pc, 0, new, false);
 }
 
+#ifdef CONFIG_ARM64_MODULE_PLTS
+static struct plt_entry *get_ftrace_plt(struct module *mod, unsigned long addr)
+{
+	struct plt_entry *plt = mod->arch.ftrace_trampolines;
+
+	if (addr == FTRACE_ADDR)
+		return &plt[FTRACE_PLT_IDX];
+	if (addr == FTRACE_REGS_ADDR && IS_ENABLED(CONFIG_FTRACE_WITH_REGS))
+		return &plt[FTRACE_REGS_PLT_IDX];
+	return NULL;
+}
+#endif
+
 /*
  * Turn on the call to ftrace_caller() in instrumented function
  */
@@ -74,19 +87,7 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
 	if (offset < -SZ_128M || offset >= SZ_128M) {
 #ifdef CONFIG_ARM64_MODULE_PLTS
 		struct module *mod;
-
-		/*
-		 * There is only one ftrace trampoline per module. For now,
-		 * this is not a problem since on arm64, all dynamic ftrace
-		 * invocations are routed via ftrace_caller(). This will need
-		 * to be revisited if support for multiple ftrace entry points
-		 * is added in the future, but for now, the pr_err() below
-		 * deals with a theoretical issue only.
-		 */
-		if (addr != FTRACE_ADDR) {
-			pr_err("ftrace: far branches to multiple entry points unsupported inside a single module\n");
-			return -EINVAL;
-		}
+		struct plt_entry *plt;
 
 		/*
 		 * On kernels that support module PLTs, the offset between the
@@ -105,7 +106,13 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
 		if (WARN_ON(!mod))
 			return -EINVAL;
 
-		addr = (unsigned long)mod->arch.ftrace_trampoline;
+		plt = get_ftrace_plt(mod, addr);
+		if (!plt) {
+			pr_err("ftrace: no module PLT for %ps\n", (void *)addr);
+			return -EINVAL;
+		}
+
+		addr = (unsigned long)plt;
 #else /* CONFIG_ARM64_MODULE_PLTS */
 		return -EINVAL;
 #endif /* CONFIG_ARM64_MODULE_PLTS */
@@ -117,6 +124,55 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
 	return ftrace_modify_code(pc, old, new, true);
 }
 
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
+int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr,
+			unsigned long addr)
+{
+	unsigned long pc = rec->ip;
+	u32 old, new;
+
+	old = aarch64_insn_gen_branch_imm(pc, old_addr,
+					  AARCH64_INSN_BRANCH_LINK);
+	new = aarch64_insn_gen_branch_imm(pc, addr, AARCH64_INSN_BRANCH_LINK);
+
+	return ftrace_modify_code(pc, old, new, true);
+}
+
+/*
+ * The compiler has inserted two NOPs before the regular function prologue.
+ * All instrumented functions follow the AAPCS, so x0-x8 and x19-x30 are live,
+ * and x9-x18 are free for our use.
+ *
+ * At runtime we want to be able to swing a single NOP <-> BL to enable or
+ * disable the ftrace call. The BL requires us to save the original LR value,
+ * so here we insert a <MOV X9, LR> over the first NOP so the instructions
+ * before the regular prologue are:
+ *
+ * | Compiled | Disabled   | Enabled    |
+ * +----------+------------+------------+
+ * | NOP      | MOV X9, LR | MOV X9, LR |
+ * | NOP      | NOP        | BL <entry> |
+ *
+ * The LR value will be recovered by ftrace_regs_entry, and restored into LR
+ * before returning to the regular function prologue. When a function is not
+ * being traced, the MOV is not harmful given x9 is not live per the AAPCS.
+ *
+ * Note: ftrace_process_locs() has pre-adjusted rec->ip to be the address of
+ * the BL.
+ */
+int ftrace_init_nop(struct module *mod, struct dyn_ftrace *rec)
+{
+	unsigned long pc = rec->ip - AARCH64_INSN_SIZE;
+	u32 old, new;
+
+	old = aarch64_insn_gen_nop();
+	new = aarch64_insn_gen_move_reg(AARCH64_INSN_REG_9,
+					AARCH64_INSN_REG_LR,
+					AARCH64_INSN_VARIANT_64BIT);
+	return ftrace_modify_code(pc, old, new, true);
+}
+#endif
+
 /*
  * Turn off the call to ftrace_caller() in instrumented function
  */