arm64: ftrace: Add direct call support

This builds up on the CALL_OPS work which extends the ftrace patchsite
on arm64 with an ops pointer usable by the ftrace trampoline.

This ops pointer is valid at all time. Indeed, it is either pointing to
ftrace_list_ops or to the single ops which should be called from that
patchsite.

There are a few cases to distinguish:
- If a direct call ops is the only one tracing a function:
  - If the direct called trampoline is within the reach of a BL
    instruction
     -> the ftrace patchsite jumps to the trampoline
  - Else
     -> the ftrace patchsite jumps to the ftrace_caller trampoline which
        reads the ops pointer in the patchsite and jumps to the direct
        call address stored in the ops
- Else
  -> the ftrace patchsite jumps to the ftrace_caller trampoline and its
     ops literal points to ftrace_list_ops so it iterates over all
     registered ftrace ops, including the direct call ops and calls its
     call_direct_funcs handler which stores the direct called
     trampoline's address in the ftrace_regs and the ftrace_caller
     trampoline will return to that address instead of returning to the
     traced function

Signed-off-by: Florent Revest <revest@chromium.org>
Co-developed-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Link: https://lore.kernel.org/r/20230405180250.2046566-2-revest@chromium.org
Signed-off-by: Will Deacon <will@kernel.org>

1 files changed, 31 insertions, 5 deletions

diff --git a/arch/arm64/kernel/ftrace.c b/arch/arm64/kernel/ftrace.c
index 5545fe1a9012..758436727fba 100644
--- a/arch/arm64/kernel/ftrace.c
+++ b/arch/arm64/kernel/ftrace.c
@@ -206,6 +206,13 @@ static struct plt_entry *get_ftrace_plt(struct module *mod, unsigned long addr)
 	return NULL;
 }
 
+static bool reachable_by_bl(unsigned long addr, unsigned long pc)
+{
+	long offset = (long)addr - (long)pc;
+
+	return offset >= -SZ_128M && offset < SZ_128M;
+}
+
 /*
  * Find the address the callsite must branch to in order to reach '*addr'.
  *
@@ -220,14 +227,21 @@ static bool ftrace_find_callable_addr(struct dyn_ftrace *rec,
 				      unsigned long *addr)
 {
 	unsigned long pc = rec->ip;
-	long offset = (long)*addr - (long)pc;
 	struct plt_entry *plt;
 
 	/*
+	 * If a custom trampoline is unreachable, rely on the ftrace_caller
+	 * trampoline which knows how to indirectly reach that trampoline
+	 * through ops->direct_call.
+	 */
+	if (*addr != FTRACE_ADDR && !reachable_by_bl(*addr, pc))
+		*addr = FTRACE_ADDR;
+
+	/*
 	 * When the target is within range of the 'BL' instruction, use 'addr'
 	 * as-is and branch to that directly.
 	 */
-	if (offset >= -SZ_128M && offset < SZ_128M)
+	if (reachable_by_bl(*addr, pc))
 		return true;
 
 	/*
@@ -330,12 +344,24 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
 int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr,
 		       unsigned long addr)
 {
-	if (WARN_ON_ONCE(old_addr != (unsigned long)ftrace_caller))
+	unsigned long pc = rec->ip;
+	u32 old, new;
+	int ret;
+
+	ret = ftrace_rec_set_ops(rec, arm64_rec_get_ops(rec));
+	if (ret)
+		return ret;
+
+	if (!ftrace_find_callable_addr(rec, NULL, &old_addr))
 		return -EINVAL;
-	if (WARN_ON_ONCE(addr != (unsigned long)ftrace_caller))
+	if (!ftrace_find_callable_addr(rec, NULL, &addr))
 		return -EINVAL;
 
-	return ftrace_rec_update_ops(rec);
+	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);
 }
 #endif