From: <gregkh@linuxfoundation.org>
To: will.deacon@arm.com, gregkh@linuxfoundation.org, mark.rutland@arm.com
Cc: <stable@vger.kernel.org>, <stable-commits@vger.kernel.org>
Subject: Patch "arm64: percpu: rewrite ll/sc loops in assembly" has been added to the 4.8-stable tree
Date: Wed, 26 Oct 2016 13:59:54 +0200 [thread overview]
Message-ID: <147748319413646@kroah.com> (raw)
This is a note to let you know that I've just added the patch titled
arm64: percpu: rewrite ll/sc loops in assembly
to the 4.8-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=summary
The filename of the patch is:
arm64-percpu-rewrite-ll-sc-loops-in-assembly.patch
and it can be found in the queue-4.8 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable@vger.kernel.org> know about it.
>From 1e6e57d9b34a9075d5f9e2048ea7b09756590d11 Mon Sep 17 00:00:00 2001
From: Will Deacon <will.deacon@arm.com>
Date: Mon, 4 Jul 2016 17:44:48 +0100
Subject: arm64: percpu: rewrite ll/sc loops in assembly
From: Will Deacon <will.deacon@arm.com>
commit 1e6e57d9b34a9075d5f9e2048ea7b09756590d11 upstream.
Writing the outer loop of an LL/SC sequence using do {...} while
constructs potentially allows the compiler to hoist memory accesses
between the STXR and the branch back to the LDXR. On CPUs that do not
guarantee forward progress of LL/SC loops when faced with memory
accesses to the same ERG (up to 2k) between the failed STXR and the
branch back, we may end up livelocking.
This patch avoids this issue in our percpu atomics by rewriting the
outer loop as part of the LL/SC inline assembly block.
Fixes: f97fc810798c ("arm64: percpu: Implement this_cpu operations")
Reviewed-by: Mark Rutland <mark.rutland@arm.com>
Tested-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
arch/arm64/include/asm/percpu.h | 120 ++++++++++++++++++----------------------
1 file changed, 56 insertions(+), 64 deletions(-)
--- a/arch/arm64/include/asm/percpu.h
+++ b/arch/arm64/include/asm/percpu.h
@@ -44,48 +44,44 @@ static inline unsigned long __percpu_##o
\
switch (size) { \
case 1: \
- do { \
- asm ("//__per_cpu_" #op "_1\n" \
- "ldxrb %w[ret], %[ptr]\n" \
+ asm ("//__per_cpu_" #op "_1\n" \
+ "1: ldxrb %w[ret], %[ptr]\n" \
#asm_op " %w[ret], %w[ret], %w[val]\n" \
- "stxrb %w[loop], %w[ret], %[ptr]\n" \
- : [loop] "=&r" (loop), [ret] "=&r" (ret), \
- [ptr] "+Q"(*(u8 *)ptr) \
- : [val] "Ir" (val)); \
- } while (loop); \
+ " stxrb %w[loop], %w[ret], %[ptr]\n" \
+ " cbnz %w[loop], 1b" \
+ : [loop] "=&r" (loop), [ret] "=&r" (ret), \
+ [ptr] "+Q"(*(u8 *)ptr) \
+ : [val] "Ir" (val)); \
break; \
case 2: \
- do { \
- asm ("//__per_cpu_" #op "_2\n" \
- "ldxrh %w[ret], %[ptr]\n" \
+ asm ("//__per_cpu_" #op "_2\n" \
+ "1: ldxrh %w[ret], %[ptr]\n" \
#asm_op " %w[ret], %w[ret], %w[val]\n" \
- "stxrh %w[loop], %w[ret], %[ptr]\n" \
- : [loop] "=&r" (loop), [ret] "=&r" (ret), \
- [ptr] "+Q"(*(u16 *)ptr) \
- : [val] "Ir" (val)); \
- } while (loop); \
+ " stxrh %w[loop], %w[ret], %[ptr]\n" \
+ " cbnz %w[loop], 1b" \
+ : [loop] "=&r" (loop), [ret] "=&r" (ret), \
+ [ptr] "+Q"(*(u16 *)ptr) \
+ : [val] "Ir" (val)); \
break; \
case 4: \
- do { \
- asm ("//__per_cpu_" #op "_4\n" \
- "ldxr %w[ret], %[ptr]\n" \
+ asm ("//__per_cpu_" #op "_4\n" \
+ "1: ldxr %w[ret], %[ptr]\n" \
#asm_op " %w[ret], %w[ret], %w[val]\n" \
- "stxr %w[loop], %w[ret], %[ptr]\n" \
- : [loop] "=&r" (loop), [ret] "=&r" (ret), \
- [ptr] "+Q"(*(u32 *)ptr) \
- : [val] "Ir" (val)); \
- } while (loop); \
+ " stxr %w[loop], %w[ret], %[ptr]\n" \
+ " cbnz %w[loop], 1b" \
+ : [loop] "=&r" (loop), [ret] "=&r" (ret), \
+ [ptr] "+Q"(*(u32 *)ptr) \
+ : [val] "Ir" (val)); \
break; \
case 8: \
- do { \
- asm ("//__per_cpu_" #op "_8\n" \
- "ldxr %[ret], %[ptr]\n" \
+ asm ("//__per_cpu_" #op "_8\n" \
+ "1: ldxr %[ret], %[ptr]\n" \
#asm_op " %[ret], %[ret], %[val]\n" \
- "stxr %w[loop], %[ret], %[ptr]\n" \
- : [loop] "=&r" (loop), [ret] "=&r" (ret), \
- [ptr] "+Q"(*(u64 *)ptr) \
- : [val] "Ir" (val)); \
- } while (loop); \
+ " stxr %w[loop], %[ret], %[ptr]\n" \
+ " cbnz %w[loop], 1b" \
+ : [loop] "=&r" (loop), [ret] "=&r" (ret), \
+ [ptr] "+Q"(*(u64 *)ptr) \
+ : [val] "Ir" (val)); \
break; \
default: \
BUILD_BUG(); \
@@ -150,44 +146,40 @@ static inline unsigned long __percpu_xch
switch (size) {
case 1:
- do {
- asm ("//__percpu_xchg_1\n"
- "ldxrb %w[ret], %[ptr]\n"
- "stxrb %w[loop], %w[val], %[ptr]\n"
- : [loop] "=&r"(loop), [ret] "=&r"(ret),
- [ptr] "+Q"(*(u8 *)ptr)
- : [val] "r" (val));
- } while (loop);
+ asm ("//__percpu_xchg_1\n"
+ "1: ldxrb %w[ret], %[ptr]\n"
+ " stxrb %w[loop], %w[val], %[ptr]\n"
+ " cbnz %w[loop], 1b"
+ : [loop] "=&r"(loop), [ret] "=&r"(ret),
+ [ptr] "+Q"(*(u8 *)ptr)
+ : [val] "r" (val));
break;
case 2:
- do {
- asm ("//__percpu_xchg_2\n"
- "ldxrh %w[ret], %[ptr]\n"
- "stxrh %w[loop], %w[val], %[ptr]\n"
- : [loop] "=&r"(loop), [ret] "=&r"(ret),
- [ptr] "+Q"(*(u16 *)ptr)
- : [val] "r" (val));
- } while (loop);
+ asm ("//__percpu_xchg_2\n"
+ "1: ldxrh %w[ret], %[ptr]\n"
+ " stxrh %w[loop], %w[val], %[ptr]\n"
+ " cbnz %w[loop], 1b"
+ : [loop] "=&r"(loop), [ret] "=&r"(ret),
+ [ptr] "+Q"(*(u16 *)ptr)
+ : [val] "r" (val));
break;
case 4:
- do {
- asm ("//__percpu_xchg_4\n"
- "ldxr %w[ret], %[ptr]\n"
- "stxr %w[loop], %w[val], %[ptr]\n"
- : [loop] "=&r"(loop), [ret] "=&r"(ret),
- [ptr] "+Q"(*(u32 *)ptr)
- : [val] "r" (val));
- } while (loop);
+ asm ("//__percpu_xchg_4\n"
+ "1: ldxr %w[ret], %[ptr]\n"
+ " stxr %w[loop], %w[val], %[ptr]\n"
+ " cbnz %w[loop], 1b"
+ : [loop] "=&r"(loop), [ret] "=&r"(ret),
+ [ptr] "+Q"(*(u32 *)ptr)
+ : [val] "r" (val));
break;
case 8:
- do {
- asm ("//__percpu_xchg_8\n"
- "ldxr %[ret], %[ptr]\n"
- "stxr %w[loop], %[val], %[ptr]\n"
- : [loop] "=&r"(loop), [ret] "=&r"(ret),
- [ptr] "+Q"(*(u64 *)ptr)
- : [val] "r" (val));
- } while (loop);
+ asm ("//__percpu_xchg_8\n"
+ "1: ldxr %[ret], %[ptr]\n"
+ " stxr %w[loop], %[val], %[ptr]\n"
+ " cbnz %w[loop], 1b"
+ : [loop] "=&r"(loop), [ret] "=&r"(ret),
+ [ptr] "+Q"(*(u64 *)ptr)
+ : [val] "r" (val));
break;
default:
BUILD_BUG();
Patches currently in stable-queue which might be from will.deacon@arm.com are
queue-4.8/arm64-swp-emulation-bound-ll-sc-retries-before-rescheduling.patch
queue-4.8/arm64-kaslr-fix-breakage-with-config_modversions-y.patch
queue-4.8/arm64-cortex-a53-errata-workaround-check-for-kernel-addresses.patch
queue-4.8/arm64-kernel-init-mdcr_el2-even-in-the-absence-of-a-pmu.patch
queue-4.8/arm64-kvm-take-s1-walks-into-account-when-determining-s2-write-faults.patch
queue-4.8/arm64-percpu-rewrite-ll-sc-loops-in-assembly.patch
reply other threads:[~2016-10-26 12:00 UTC|newest]
Thread overview: [no followups] expand[flat|nested] mbox.gz Atom feed
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=147748319413646@kroah.com \
--to=gregkh@linuxfoundation.org \
--cc=mark.rutland@arm.com \
--cc=stable-commits@vger.kernel.org \
--cc=stable@vger.kernel.org \
--cc=will.deacon@arm.com \
/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).