create-diff-object: Add support for arm64 DYNAMIC_FTRACE_WITH_CALL_OPS

For arm64 this option uses -fpatchable-function-entry=M,2, so 2 NOPs
are placed before the function entry point (in order to store a pointer
to ftrace_ops). When calculating function padding, check for the
presence of the two NOPs, and adjust the padding size by 8 if they are
found.

This was merged in the upstream kernel in v6.8 with:

      baaf553d3bc3 ("arm64: Implement HAVE_DYNAMIC_FTRACE_WITH_CALL_OPS")

With this into the equation, the entry of a function can look like one
of:

1. Without DYNAMIC_FTRACE_WITH_CALL_OPS and CONFIG_ARM64_BTI_KERNEL
-------------------------------------------------------------------

Disassembly of section .text.cmdline_proc_show:

0000000000000008 <cmdline_proc_show>:
   8:   d503201f        nop
   c:   d503201f        nop

2. Without DYNAMIC_FTRACE_WITH_CALL_OPS and with CONFIG_ARM64_BTI_KERNEL
------------------------------------------------------------------------

Disassembly of section .text.cmdline_proc_show:

0000000000000008 <cmdline_proc_show>:
   0:   d503245f        bti     c
   4:   d503201f        nop
   8:   d503201f        nop

3. With DYNAMIC_FTRACE_WITH_CALL_OPS and without CONFIG_ARM64_BTI_KERNEL
------------------------------------------------------------------------

Disassembly of section .text.cmdline_proc_show:

0000000000000000 <cmdline_proc_show-0x8>:
   0:   d503201f        nop
   4:   d503201f        nop

0000000000000008 <cmdline_proc_show>:
   8:   d503201f        nop
   c:   d503201f        nop

4. With DYNAMIC_FTRACE_WITH_CALL_OPS and with CONFIG_ARM64_BTI_KERNEL
---------------------------------------------------------------------

Disassembly of section .text.cmdline_proc_show:

0000000000000000 <cmdline_proc_show-0x8>:
   0:   d503201f        nop
   4:   d503201f        nop

0000000000000008 <cmdline_proc_show>:
   8:   d503245f        bti     c
   c:   d503201f        nop
  10:   d503201f        nop

make create-diff-object aware of DYNAMIC_FTRACE_WITH_CALL_OPS and its
quirks.

Signed-off-by: Dylan Hatch <dylanbhatch@google.com>
Signed-off-by: Puranjay Mohan <pjy@amazon.com>

Author: dylanbhatch

kpatch-build/create-diff-object.c

@@ -255,6 +255,37 @@ static bool kpatch_is_mapping_symbol(struct kpatch_elf *kelf, struct symbol *sym
 	return false;
 }
 
+static unsigned int function_padding_size(struct kpatch_elf *kelf, struct symbol *sym)
+{
+	unsigned int size = 0;
+
+	switch (kelf->arch) {
+	case AARCH64:
+	{
+		uint32_t *insn = sym->sec->data->d_buf;
+		unsigned int i;
+		void *insn_end = sym->sec->data->d_buf + sym->sym.st_value;
+
+		/*
+		 * If the arm64 kernel is compiled with CONFIG_DYNAMIC_FTRACE_WITH_CALL_OPS
+		 * then there are two NOPs before the function and a `BTI C` + 2 NOPs at the
+		 * start of the function. Verify the presence of the two NOPs before the
+		 * function entry.
+		 */
+		for (i = 0; (void *)insn < insn_end && *insn == 0xd503201f; i++, insn++)
+			;
+
+		if (i == 2)
+			size = 8;
+		break;
+	}
+	default:
+		break;
+	}
+
+	return size;
+}
+
 /*
  * When compiling with -ffunction-sections and -fdata-sections, almost every
  * symbol gets its own dedicated section.  We call such symbols "bundled"
@@ -271,6 +302,8 @@ static void kpatch_bundle_symbols(struct kpatch_elf *kelf)
 				expected_offset = sym->pfx->sym.st_size;
 			else if (is_gcc6_localentry_bundled_sym(kelf, sym))
 				expected_offset = 8;
+			else if (sym->type == STT_FUNC)
+				expected_offset = function_padding_size(kelf, sym);
 			else
 				expected_offset = 0;
 
@@ -3808,6 +3841,11 @@ static void kpatch_create_ftrace_callsite_sections(struct kpatch_elf *kelf, bool
 			unsigned char *insn = sym->sec->data->d_buf;
 			int i;
 
+			/*
+			 * Skip the padding NOPs added by CALL_OPS.
+			 */
+			insn += function_padding_size(kelf, sym);
+
 			/*
 			 * If BTI (Branch Target Identification) is enabled then there
 			 * might be an additional 'BTI C' instruction before the two