powerpc/ftrace: Add support for DYNAMIC_FTRACE_WITH_CALL_OPS

Implement support for DYNAMIC_FTRACE_WITH_CALL_OPS similar to the
arm64 implementation.

This works by patching-in a pointer to an associated ftrace_ops
structure before each traceable function. If multiple ftrace_ops are
associated with a call site, then a special ftrace_list_ops is used to
enable iterating over all the registered ftrace_ops. If no ftrace_ops
are associated with a call site, then a special ftrace_nop_ops structure
is used to render the ftrace call as a no-op. ftrace trampoline can then
read the associated ftrace_ops for a call site by loading from an offset
from the LR, and branch directly to the associated function.

The primary advantage with this approach is that we don't have to
iterate over all the registered ftrace_ops for call sites that have a
single ftrace_ops registered. This is the equivalent of implementing
support for dynamic ftrace trampolines, which set up a special ftrace
trampoline for each registered ftrace_ops and have individual call sites
branch into those directly.

A secondary advantage is that this gives us a way to add support for
direct ftrace callers without having to resort to using stubs. The
address of the direct call trampoline can be loaded from the ftrace_ops
structure.

To support this, we reserve a nop before each function on 32-bit
powerpc. For 64-bit powerpc, two nops are reserved before each
out-of-line stub. During ftrace activation, we update this location with
the associated ftrace_ops pointer. Then, on ftrace entry, we load from
this location and call into ftrace_ops->func().

For 64-bit powerpc, we ensure that the out-of-line stub area is
doubleword aligned so that ftrace_ops address can be updated atomically.

Signed-off-by: Naveen N Rao <naveen@kernel.org>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://patch.msgid.link/20241030070850.1361304-15-hbathini@linux.ibm.com

1 files changed, 58 insertions, 1 deletions

diff --git a/arch/powerpc/kernel/trace/ftrace.c b/arch/powerpc/kernel/trace/ftrace.c
index bee2c54a8c04..9090d1a21600 100644
--- a/arch/powerpc/kernel/trace/ftrace.c
+++ b/arch/powerpc/kernel/trace/ftrace.c
@@ -38,8 +38,11 @@ unsigned long ftrace_call_adjust(unsigned long addr)
 		return 0;
 
 	if (IS_ENABLED(CONFIG_ARCH_USING_PATCHABLE_FUNCTION_ENTRY) &&
-	    !IS_ENABLED(CONFIG_PPC_FTRACE_OUT_OF_LINE))
+	    !IS_ENABLED(CONFIG_PPC_FTRACE_OUT_OF_LINE)) {
 		addr += MCOUNT_INSN_SIZE;
+		if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_CALL_OPS))
+			addr += MCOUNT_INSN_SIZE;
+	}
 
 	return addr;
 }
@@ -264,6 +267,46 @@ static int ftrace_init_ool_stub(struct module *mod, struct dyn_ftrace *rec)
 #endif
 }
 
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_CALL_OPS
+static const struct ftrace_ops *powerpc_rec_get_ops(struct dyn_ftrace *rec)
+{
+	const struct ftrace_ops *ops = NULL;
+
+	if (rec->flags & FTRACE_FL_CALL_OPS_EN) {
+		ops = ftrace_find_unique_ops(rec);
+		WARN_ON_ONCE(!ops);
+	}
+
+	if (!ops)
+		ops = &ftrace_list_ops;
+
+	return ops;
+}
+
+static int ftrace_rec_set_ops(struct dyn_ftrace *rec, const struct ftrace_ops *ops)
+{
+	if (IS_ENABLED(CONFIG_PPC_FTRACE_OUT_OF_LINE))
+		return patch_ulong((void *)(ftrace_get_ool_stub(rec) - sizeof(unsigned long)),
+				   (unsigned long)ops);
+	else
+		return patch_ulong((void *)(rec->ip - MCOUNT_INSN_SIZE - sizeof(unsigned long)),
+				   (unsigned long)ops);
+}
+
+static int ftrace_rec_set_nop_ops(struct dyn_ftrace *rec)
+{
+	return ftrace_rec_set_ops(rec, &ftrace_nop_ops);
+}
+
+static int ftrace_rec_update_ops(struct dyn_ftrace *rec)
+{
+	return ftrace_rec_set_ops(rec, powerpc_rec_get_ops(rec));
+}
+#else
+static int ftrace_rec_set_nop_ops(struct dyn_ftrace *rec) { return 0; }
+static int ftrace_rec_update_ops(struct dyn_ftrace *rec) { return 0; }
+#endif
+
 #ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
 int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr, unsigned long addr)
 {
@@ -294,6 +337,10 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
 	if (!ret)
 		ret = ftrace_modify_code(ip, old, new);
 
+	ret = ftrace_rec_update_ops(rec);
+	if (ret)
+		return ret;
+
 	if (!ret && IS_ENABLED(CONFIG_PPC_FTRACE_OUT_OF_LINE))
 		ret = ftrace_modify_code(rec->ip, ppc_inst(PPC_RAW_NOP()),
 			 ppc_inst(PPC_RAW_BRANCH((long)ftrace_get_ool_stub(rec) - (long)rec->ip)));
@@ -345,16 +392,19 @@ void ftrace_replace_code(int enable)
 		case FTRACE_UPDATE_MODIFY_CALL:
 			ret = ftrace_get_call_inst(rec, new_addr, &new_call_inst);
 			ret |= ftrace_get_call_inst(rec, addr, &call_inst);
+			ret |= ftrace_rec_update_ops(rec);
 			old = call_inst;
 			new = new_call_inst;
 			break;
 		case FTRACE_UPDATE_MAKE_NOP:
 			ret = ftrace_get_call_inst(rec, addr, &call_inst);
+			ret |= ftrace_rec_set_nop_ops(rec);
 			old = call_inst;
 			new = nop_inst;
 			break;
 		case FTRACE_UPDATE_MAKE_CALL:
 			ret = ftrace_get_call_inst(rec, new_addr, &call_inst);
+			ret |= ftrace_rec_update_ops(rec);
 			old = nop_inst;
 			new = call_inst;
 			break;
@@ -470,6 +520,13 @@ int ftrace_update_ftrace_func(ftrace_func_t func)
 	ppc_inst_t old, new;
 	int ret;
 
+	/*
+	 * When using CALL_OPS, the function to call is associated with the
+	 * call site, and we don't have a global function pointer to update.
+	 */
+	if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_CALL_OPS))
+		return 0;
+
 	old = ppc_inst_read((u32 *)&ftrace_call);
 	new = ftrace_create_branch_inst(ip, ppc_function_entry(func), 1);
 	ret = ftrace_modify_code(ip, old, new);