From: Benjamin Gray <bgray@linux.ibm.com>
To: linuxppc-dev@lists.ozlabs.org
Cc: christophe.leroy@c-s.fr, ajd@linux.ibm.com, peterz@infradead.org,
Benjamin Gray <bgray@linux.ibm.com>,
npiggin@gmail.com, ardb@kernel.org, jbaron@akamai.com,
rostedt@goodmis.org, jpoimboe@kernel.org
Subject: [PATCH 3/6] powerpc/module: Optimise nearby branches in ELF V2 ABI stub
Date: Fri, 16 Sep 2022 16:23:27 +1000 [thread overview]
Message-ID: <20220916062330.430468-4-bgray@linux.ibm.com> (raw)
In-Reply-To: <20220916062330.430468-1-bgray@linux.ibm.com>
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@linux.ibm.com>
---
arch/powerpc/kernel/module_64.c | 13 +++++++++++--
1 file changed, 11 insertions(+), 2 deletions(-)
diff --git a/arch/powerpc/kernel/module_64.c b/arch/powerpc/kernel/module_64.c
index 3656476097c2..03ab28d86008 100644
--- a/arch/powerpc/kernel/module_64.c
+++ b/arch/powerpc/kernel/module_64.c
@@ -432,8 +432,17 @@ static inline int create_stub(const Elf64_Shdr *sechdrs,
return create_ftrace_stub(entry, addr, me);
for (i = 0; i < ARRAY_SIZE(ppc64_stub_insns); i++) {
- if (patch_instruction(&entry->jump[i],
- ppc_inst(ppc64_stub_insns[i])))
+ ppc_inst_t inst = ppc_inst(ppc64_stub_insns[i]);
+
+ // Replace the indirect branch with a direct branch where possible
+ if (IS_ENABLED(CONFIG_PPC64_ELF_ABI_V2) && i == 4) {
+ ppc_inst_t direct;
+ if (create_branch(&direct, (void*) entry + (i * 4), addr, 0) == 0) {
+ inst = direct;
+ }
+ }
+
+ if (patch_instruction(&entry->jump[i], inst))
return 0;
}
--
2.37.3
next prev parent reply other threads:[~2022-09-16 6:27 UTC|newest]
Thread overview: 21+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-09-16 6:23 [PATCH 0/6] Out-of-line static calls for powerpc64 ELF V2 Benjamin Gray
2022-09-16 6:23 ` [PATCH 1/6] powerpc/code-patching: Implement generic text patching function Benjamin Gray
2022-09-16 9:39 ` kernel test robot
2022-09-16 11:16 ` kernel test robot
2022-09-19 6:04 ` Christophe Leroy
2022-09-19 6:49 ` Benjamin Gray
2022-09-19 7:16 ` Christophe Leroy
2022-09-20 2:32 ` Benjamin Gray
2022-09-20 5:44 ` Christophe Leroy
2022-09-20 7:01 ` Benjamin Gray
2022-09-19 6:38 ` Christophe Leroy
2022-09-20 1:49 ` Benjamin Gray
2022-09-16 6:23 ` [PATCH 2/6] powerpc/module: Handle caller-saved TOC in module linker Benjamin Gray
2022-09-19 6:09 ` Christophe Leroy
2022-09-16 6:23 ` Benjamin Gray [this message]
2022-09-19 6:11 ` [PATCH 3/6] powerpc/module: Optimise nearby branches in ELF V2 ABI stub Christophe Leroy
2022-09-16 6:23 ` [PATCH 4/6] static_call: Move static call selftest to static_call_selftest.c Benjamin Gray
2022-09-20 4:30 ` Andrew Donnellan
2022-09-16 6:23 ` [PATCH 5/6] powerpc/64: Add support for out-of-line static calls Benjamin Gray
2022-09-16 8:32 ` kernel test robot
2022-09-16 6:23 ` [PATCH 6/6] powerpc/64: Add tests " Benjamin Gray
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20220916062330.430468-4-bgray@linux.ibm.com \
--to=bgray@linux.ibm.com \
--cc=ajd@linux.ibm.com \
--cc=ardb@kernel.org \
--cc=christophe.leroy@c-s.fr \
--cc=jbaron@akamai.com \
--cc=jpoimboe@kernel.org \
--cc=linuxppc-dev@lists.ozlabs.org \
--cc=npiggin@gmail.com \
--cc=peterz@infradead.org \
--cc=rostedt@goodmis.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).