[<prev] [next>] [thread-next>] [day] [month] [year] [list]
Message-Id: <5B73DFB602000078001DE35E@prv1-mh.provo.novell.com>
Date: Wed, 15 Aug 2018 02:09:26 -0600
From: "Jan Beulich" <JBeulich@...e.com>
To: "the arch/x86 maintainers" <x86@...nel.org>,
"Juergen Gross" <jgross@...e.com>,
"Alok Kataria" <akataria@...are.com>
Cc: "Linux Virtualization" <virtualization@...ts.linux-foundation.org>,
<linux-kernel@...r.kernel.org>, <hpa@...or.com>
Subject: [PATCH RESEND] x86-64: use RIP-relative calls for paravirt
indirect ones
This saves one insn byte per instance, summing up to a savings of over
4k in my (stripped down) configuration. No variant of to be patched in
replacement code relies on the one byte larger size.
Signed-off-by: Jan Beulich <jbeulich@...e.com>
Reviewed-by: Juergen Gross <jgross@...e.com>
---
Resend to include x86 maintainers, who aren't listed explicitly for the
file changed.
---
arch/x86/include/asm/paravirt_types.h | 6 ++++++
1 file changed, 6 insertions(+)
--- 4.18/arch/x86/include/asm/paravirt_types.h
+++ 4.18-x86_64-pvops-call-RIPrel/arch/x86/include/asm/paravirt_types.h
@@ -393,9 +393,15 @@ int paravirt_disable_iospace(void);
* offset into the paravirt_patch_template structure, and can therefore be
* freely converted back into a structure offset.
*/
+#ifdef CONFIG_X86_32
#define PARAVIRT_CALL \
ANNOTATE_RETPOLINE_SAFE \
"call *%c[paravirt_opptr];"
+#else
+#define PARAVIRT_CALL \
+ ANNOTATE_RETPOLINE_SAFE \
+ "call *%c[paravirt_opptr](%%rip);"
+#endif
/*
* These macros are intended to wrap calls through one of the paravirt
Powered by blists - more mailing lists