[PATCH v2 3/6] powerpc/module: Optimise nearby branches in ELF V2 ABI stub

[Benjamin Gray]

Inserts a direct branch to the stub target when possible, replacing the
mtctr/btctr sequence.

The load into r12 could potentially be skipped too, but that change
would need to refactor the arguments to indicate that the address
does not have a separate local entry point.

This helps the static call implementation, where modules calling their
own trampolines are called through this stub and the trampoline is
easily within range of a direct branch.

Signed-off-by: Benjamin Gray <bgray at linux.ibm.com>
---
 arch/powerpc/kernel/module_64.c | 13 +++++++++++++
 1 file changed, 13 insertions(+)

diff --git a/arch/powerpc/kernel/module_64.c b/arch/powerpc/kernel/module_64.c
index 4d816f7785b4..745ce9097dcf 100644
--- a/arch/powerpc/kernel/module_64.c
+++ b/arch/powerpc/kernel/module_64.c
@@ -141,6 +141,12 @@ static u32 ppc64_stub_insns[] = {
 	PPC_RAW_BCTR(),
 };
 
+#ifdef CONFIG_PPC64_ELF_ABI_V1
+#define PPC64_STUB_MTCTR_OFFSET 5
+#else
+#define PPC64_STUB_MTCTR_OFFSET 4
+#endif
+
 /* Count how many different 24-bit relocations (different symbol,
    different addend) */
 static unsigned int count_relocs(const Elf64_Rela *rela, unsigned int num)
@@ -429,6 +435,8 @@ static inline int create_stub(const Elf64_Shdr *sechdrs,
 	long reladdr;
 	func_desc_t desc;
 	int i;
+	u32 *jump_seq_addr = &entry->jump[PPC64_STUB_MTCTR_OFFSET];
+	ppc_inst_t direct;
 
 	if (is_mprofile_ftrace_call(name))
 		return create_ftrace_stub(entry, addr, me);
@@ -439,6 +447,11 @@ static inline int create_stub(const Elf64_Shdr *sechdrs,
 			return 0;
 	}
 
+	/* Replace indirect branch sequence with direct branch where possible */
+	if (!create_branch(&direct, jump_seq_addr, addr, 0))
+		if (patch_instruction(jump_seq_addr, direct))
+			return 0;
+
 	/* Stub uses address relative to r2. */
 	reladdr = (unsigned long)entry - my_r2(sechdrs, me);
 	if (reladdr > 0x7FFFFFFF || reladdr < -(0x80000000L)) {
-- 
2.37.3