From: Anton Blanchard <anton@samba.org>
To: Benjamin Herrenschmidt <benh@kernel.crashing.org>,
Paul Mackerras <paulus@samba.org>
Cc: linuxppc-dev@lists.ozlabs.org
Subject: [PATCH 01/39] powerpc: Fix endian issues in VMX copy loops
Date: Mon, 23 Sep 2013 12:04:35 +1000 [thread overview]
Message-ID: <1379901913-5945-2-git-send-email-anton@samba.org> (raw)
In-Reply-To: <1379901913-5945-1-git-send-email-anton@samba.org>
Fix the permute loops for little endian.
Signed-off-by: Anton Blanchard <anton@samba.org>
---
arch/powerpc/lib/copyuser_power7.S | 54 +++++++++++++++++++++----------------
arch/powerpc/lib/memcpy_power7.S | 55 ++++++++++++++++++++++----------------
2 files changed, 63 insertions(+), 46 deletions(-)
diff --git a/arch/powerpc/lib/copyuser_power7.S b/arch/powerpc/lib/copyuser_power7.S
index d1f1179..e8e9c36 100644
--- a/arch/powerpc/lib/copyuser_power7.S
+++ b/arch/powerpc/lib/copyuser_power7.S
@@ -19,6 +19,14 @@
*/
#include <asm/ppc_asm.h>
+#ifdef __BIG_ENDIAN__
+#define LVS(VRT,RA,RB) lvsl VRT,RA,RB
+#define VPERM(VRT,VRA,VRB,VRC) vperm VRT,VRA,VRB,VRC
+#else
+#define LVS(VRT,RA,RB) lvsr VRT,RA,RB
+#define VPERM(VRT,VRA,VRB,VRC) vperm VRT,VRB,VRA,VRC
+#endif
+
.macro err1
100:
.section __ex_table,"a"
@@ -552,13 +560,13 @@ err3; stw r7,4(r3)
li r10,32
li r11,48
- lvsl vr16,0,r4 /* Setup permute control vector */
+ LVS(vr16,0,r4) /* Setup permute control vector */
err3; lvx vr0,0,r4
addi r4,r4,16
bf cr7*4+3,5f
err3; lvx vr1,r0,r4
- vperm vr8,vr0,vr1,vr16
+ VPERM(vr8,vr0,vr1,vr16)
addi r4,r4,16
err3; stvx vr8,r0,r3
addi r3,r3,16
@@ -566,9 +574,9 @@ err3; stvx vr8,r0,r3
5: bf cr7*4+2,6f
err3; lvx vr1,r0,r4
- vperm vr8,vr0,vr1,vr16
+ VPERM(vr8,vr0,vr1,vr16)
err3; lvx vr0,r4,r9
- vperm vr9,vr1,vr0,vr16
+ VPERM(vr9,vr1,vr0,vr16)
addi r4,r4,32
err3; stvx vr8,r0,r3
err3; stvx vr9,r3,r9
@@ -576,13 +584,13 @@ err3; stvx vr9,r3,r9
6: bf cr7*4+1,7f
err3; lvx vr3,r0,r4
- vperm vr8,vr0,vr3,vr16
+ VPERM(vr8,vr0,vr3,vr16)
err3; lvx vr2,r4,r9
- vperm vr9,vr3,vr2,vr16
+ VPERM(vr9,vr3,vr2,vr16)
err3; lvx vr1,r4,r10
- vperm vr10,vr2,vr1,vr16
+ VPERM(vr10,vr2,vr1,vr16)
err3; lvx vr0,r4,r11
- vperm vr11,vr1,vr0,vr16
+ VPERM(vr11,vr1,vr0,vr16)
addi r4,r4,64
err3; stvx vr8,r0,r3
err3; stvx vr9,r3,r9
@@ -611,21 +619,21 @@ err3; stvx vr11,r3,r11
.align 5
8:
err4; lvx vr7,r0,r4
- vperm vr8,vr0,vr7,vr16
+ VPERM(vr8,vr0,vr7,vr16)
err4; lvx vr6,r4,r9
- vperm vr9,vr7,vr6,vr16
+ VPERM(vr9,vr7,vr6,vr16)
err4; lvx vr5,r4,r10
- vperm vr10,vr6,vr5,vr16
+ VPERM(vr10,vr6,vr5,vr16)
err4; lvx vr4,r4,r11
- vperm vr11,vr5,vr4,vr16
+ VPERM(vr11,vr5,vr4,vr16)
err4; lvx vr3,r4,r12
- vperm vr12,vr4,vr3,vr16
+ VPERM(vr12,vr4,vr3,vr16)
err4; lvx vr2,r4,r14
- vperm vr13,vr3,vr2,vr16
+ VPERM(vr13,vr3,vr2,vr16)
err4; lvx vr1,r4,r15
- vperm vr14,vr2,vr1,vr16
+ VPERM(vr14,vr2,vr1,vr16)
err4; lvx vr0,r4,r16
- vperm vr15,vr1,vr0,vr16
+ VPERM(vr15,vr1,vr0,vr16)
addi r4,r4,128
err4; stvx vr8,r0,r3
err4; stvx vr9,r3,r9
@@ -649,13 +657,13 @@ err4; stvx vr15,r3,r16
bf cr7*4+1,9f
err3; lvx vr3,r0,r4
- vperm vr8,vr0,vr3,vr16
+ VPERM(vr8,vr0,vr3,vr16)
err3; lvx vr2,r4,r9
- vperm vr9,vr3,vr2,vr16
+ VPERM(vr9,vr3,vr2,vr16)
err3; lvx vr1,r4,r10
- vperm vr10,vr2,vr1,vr16
+ VPERM(vr10,vr2,vr1,vr16)
err3; lvx vr0,r4,r11
- vperm vr11,vr1,vr0,vr16
+ VPERM(vr11,vr1,vr0,vr16)
addi r4,r4,64
err3; stvx vr8,r0,r3
err3; stvx vr9,r3,r9
@@ -665,9 +673,9 @@ err3; stvx vr11,r3,r11
9: bf cr7*4+2,10f
err3; lvx vr1,r0,r4
- vperm vr8,vr0,vr1,vr16
+ VPERM(vr8,vr0,vr1,vr16)
err3; lvx vr0,r4,r9
- vperm vr9,vr1,vr0,vr16
+ VPERM(vr9,vr1,vr0,vr16)
addi r4,r4,32
err3; stvx vr8,r0,r3
err3; stvx vr9,r3,r9
@@ -675,7 +683,7 @@ err3; stvx vr9,r3,r9
10: bf cr7*4+3,11f
err3; lvx vr1,r0,r4
- vperm vr8,vr0,vr1,vr16
+ VPERM(vr8,vr0,vr1,vr16)
addi r4,r4,16
err3; stvx vr8,r0,r3
addi r3,r3,16
diff --git a/arch/powerpc/lib/memcpy_power7.S b/arch/powerpc/lib/memcpy_power7.S
index 0663630..e4177db 100644
--- a/arch/powerpc/lib/memcpy_power7.S
+++ b/arch/powerpc/lib/memcpy_power7.S
@@ -20,6 +20,15 @@
#include <asm/ppc_asm.h>
_GLOBAL(memcpy_power7)
+
+#ifdef __BIG_ENDIAN__
+#define LVS(VRT,RA,RB) lvsl VRT,RA,RB
+#define VPERM(VRT,VRA,VRB,VRC) vperm VRT,VRA,VRB,VRC
+#else
+#define LVS(VRT,RA,RB) lvsr VRT,RA,RB
+#define VPERM(VRT,VRA,VRB,VRC) vperm VRT,VRB,VRA,VRC
+#endif
+
#ifdef CONFIG_ALTIVEC
cmpldi r5,16
cmpldi cr1,r5,4096
@@ -485,13 +494,13 @@ _GLOBAL(memcpy_power7)
li r10,32
li r11,48
- lvsl vr16,0,r4 /* Setup permute control vector */
+ LVS(vr16,0,r4) /* Setup permute control vector */
lvx vr0,0,r4
addi r4,r4,16
bf cr7*4+3,5f
lvx vr1,r0,r4
- vperm vr8,vr0,vr1,vr16
+ VPERM(vr8,vr0,vr1,vr16)
addi r4,r4,16
stvx vr8,r0,r3
addi r3,r3,16
@@ -499,9 +508,9 @@ _GLOBAL(memcpy_power7)
5: bf cr7*4+2,6f
lvx vr1,r0,r4
- vperm vr8,vr0,vr1,vr16
+ VPERM(vr8,vr0,vr1,vr16)
lvx vr0,r4,r9
- vperm vr9,vr1,vr0,vr16
+ VPERM(vr9,vr1,vr0,vr16)
addi r4,r4,32
stvx vr8,r0,r3
stvx vr9,r3,r9
@@ -509,13 +518,13 @@ _GLOBAL(memcpy_power7)
6: bf cr7*4+1,7f
lvx vr3,r0,r4
- vperm vr8,vr0,vr3,vr16
+ VPERM(vr8,vr0,vr3,vr16)
lvx vr2,r4,r9
- vperm vr9,vr3,vr2,vr16
+ VPERM(vr9,vr3,vr2,vr16)
lvx vr1,r4,r10
- vperm vr10,vr2,vr1,vr16
+ VPERM(vr10,vr2,vr1,vr16)
lvx vr0,r4,r11
- vperm vr11,vr1,vr0,vr16
+ VPERM(vr11,vr1,vr0,vr16)
addi r4,r4,64
stvx vr8,r0,r3
stvx vr9,r3,r9
@@ -544,21 +553,21 @@ _GLOBAL(memcpy_power7)
.align 5
8:
lvx vr7,r0,r4
- vperm vr8,vr0,vr7,vr16
+ VPERM(vr8,vr0,vr7,vr16)
lvx vr6,r4,r9
- vperm vr9,vr7,vr6,vr16
+ VPERM(vr9,vr7,vr6,vr16)
lvx vr5,r4,r10
- vperm vr10,vr6,vr5,vr16
+ VPERM(vr10,vr6,vr5,vr16)
lvx vr4,r4,r11
- vperm vr11,vr5,vr4,vr16
+ VPERM(vr11,vr5,vr4,vr16)
lvx vr3,r4,r12
- vperm vr12,vr4,vr3,vr16
+ VPERM(vr12,vr4,vr3,vr16)
lvx vr2,r4,r14
- vperm vr13,vr3,vr2,vr16
+ VPERM(vr13,vr3,vr2,vr16)
lvx vr1,r4,r15
- vperm vr14,vr2,vr1,vr16
+ VPERM(vr14,vr2,vr1,vr16)
lvx vr0,r4,r16
- vperm vr15,vr1,vr0,vr16
+ VPERM(vr15,vr1,vr0,vr16)
addi r4,r4,128
stvx vr8,r0,r3
stvx vr9,r3,r9
@@ -582,13 +591,13 @@ _GLOBAL(memcpy_power7)
bf cr7*4+1,9f
lvx vr3,r0,r4
- vperm vr8,vr0,vr3,vr16
+ VPERM(vr8,vr0,vr3,vr16)
lvx vr2,r4,r9
- vperm vr9,vr3,vr2,vr16
+ VPERM(vr9,vr3,vr2,vr16)
lvx vr1,r4,r10
- vperm vr10,vr2,vr1,vr16
+ VPERM(vr10,vr2,vr1,vr16)
lvx vr0,r4,r11
- vperm vr11,vr1,vr0,vr16
+ VPERM(vr11,vr1,vr0,vr16)
addi r4,r4,64
stvx vr8,r0,r3
stvx vr9,r3,r9
@@ -598,9 +607,9 @@ _GLOBAL(memcpy_power7)
9: bf cr7*4+2,10f
lvx vr1,r0,r4
- vperm vr8,vr0,vr1,vr16
+ VPERM(vr8,vr0,vr1,vr16)
lvx vr0,r4,r9
- vperm vr9,vr1,vr0,vr16
+ VPERM(vr9,vr1,vr0,vr16)
addi r4,r4,32
stvx vr8,r0,r3
stvx vr9,r3,r9
@@ -608,7 +617,7 @@ _GLOBAL(memcpy_power7)
10: bf cr7*4+3,11f
lvx vr1,r0,r4
- vperm vr8,vr0,vr1,vr16
+ VPERM(vr8,vr0,vr1,vr16)
addi r4,r4,16
stvx vr8,r0,r3
addi r3,r3,16
--
1.8.1.2
next prev parent reply other threads:[~2013-09-23 2:04 UTC|newest]
Thread overview: 49+ messages / expand[flat|nested] mbox.gz Atom feed top
2013-09-23 2:04 [PATCH 00/39] Second round of 64bit PowerPC little endian patches Anton Blanchard
2013-09-23 2:04 ` Anton Blanchard [this message]
2013-09-23 2:04 ` [PATCH 02/39] powerpc: Book 3S MMU little endian support Anton Blanchard
2013-09-23 2:04 ` [PATCH 03/39] powerpc: Fix offset of FPRs in VSX registers in little endian builds Anton Blanchard
2013-09-23 2:04 ` [PATCH 04/39] powerpc: PTRACE_PEEKUSR/PTRACE_POKEUSER of FPR " Anton Blanchard
2013-09-23 2:04 ` [PATCH 05/39] powerpc: Little endian builds double word swap VSX state during context save/restore Anton Blanchard
2013-09-23 2:04 ` [PATCH 06/39] powerpc: Support endian agnostic MMIO Anton Blanchard
2013-09-23 2:04 ` [PATCH 07/39] powerpc: Add little endian support for word-at-a-time functions Anton Blanchard
2013-09-23 2:04 ` [PATCH 08/39] powerpc: Set MSR_LE bit on little endian builds Anton Blanchard
2013-09-23 2:04 ` [PATCH 09/39] powerpc: Reset MSR_LE on signal entry Anton Blanchard
2013-09-23 2:04 ` [PATCH 10/39] powerpc: Include the appropriate endianness header Anton Blanchard
2013-09-23 2:04 ` [PATCH 11/39] powerpc: endian safe trampoline Anton Blanchard
2013-12-28 7:24 ` Olof Johansson
2013-12-28 7:58 ` Benjamin Herrenschmidt
2013-09-23 2:04 ` [PATCH 12/39] powerpc: Remove open coded byte swap macro in alignment handler Anton Blanchard
2013-09-23 2:04 ` [PATCH 13/39] powerpc: Remove hard coded FP offsets " Anton Blanchard
2013-09-23 2:04 ` [PATCH 14/39] powerpc: Alignment handler shouldn't access VSX registers with TS_FPR Anton Blanchard
2013-09-23 2:04 ` [PATCH 15/39] powerpc: Add little endian support to alignment handler Anton Blanchard
2013-09-23 2:04 ` [PATCH 16/39] powerpc: Handle VSX alignment faults in little endian mode Anton Blanchard
2013-09-23 2:04 ` [PATCH 17/39] powerpc: Use generic checksum code in little endian Anton Blanchard
2013-09-23 2:04 ` [PATCH 18/39] powerpc: Use generic memcpy " Anton Blanchard
2013-09-23 2:04 ` [PATCH 19/39] powerpc: uname should return ppc64le/ppcle on little endian builds Anton Blanchard
2013-09-23 2:04 ` [PATCH 20/39] powerpc: Little endian fixes for platforms/powernv/opal.c Anton Blanchard
2013-09-23 2:04 ` [PATCH 21/39] powerpc: Little endian fix for arch/powerpc/platforms/powernv/pci.c Anton Blanchard
2013-09-23 2:04 ` [PATCH 22/39] powerpc: Little endian fix for arch/powerpc/platforms/powernv/pci-p5ioc2.c Anton Blanchard
2013-09-23 2:04 ` [PATCH 23/39] powerpc: Little endian sparse clean up for arch/powerpc/platforms/powernv/pci-ioda.c Anton Blanchard
2013-09-23 2:04 ` [PATCH 24/39] powerpc/powernv: Fix endian issues in OPAL RTC driver Anton Blanchard
2013-09-23 2:04 ` [PATCH 25/39] powerpc/powernv: Fix endian issues in OPAL ICS backend Anton Blanchard
2013-09-23 2:05 ` [PATCH 26/39] powerpc/powernv: Make OPAL NVRAM device tree accesses endian safe Anton Blanchard
2013-09-23 2:05 ` [PATCH 27/39] powerpc/powernv: Fix endian issues in powernv PCI code Anton Blanchard
2013-09-23 2:05 ` [PATCH 28/39] powerpc/powernv: Fix endian issues in OPAL console and udbg backend Anton Blanchard
2013-09-23 2:05 ` [PATCH 29/39] powerpc/powernv: Fix OPAL entry and exit in little endian mode Anton Blanchard
2013-09-23 2:05 ` [PATCH 30/39] powerpc/powernv: Don't register exception handlers " Anton Blanchard
2013-09-23 2:05 ` [PATCH 31/39] powerpc/powernv: More little endian issues in OPAL RTC driver Anton Blanchard
2013-09-23 2:05 ` [PATCH 32/39] powerpc/powernv: Fix some PCI sparse errors and one LE bug Anton Blanchard
2013-09-23 2:05 ` [PATCH 33/39] powerpc/hvsi: Fix endian issues in HVSI driver Anton Blanchard
2013-09-23 2:05 ` [PATCH 34/39] tty/hvc_opal: powerpc: Make OPAL HVC device tree accesses endian safe Anton Blanchard
2013-09-23 2:05 ` [PATCH 35/39] KVM: PPC: Disable KVM on little endian builds Anton Blanchard
2013-09-23 2:05 ` [PATCH 36/39] powerpc/kvm/book3s_hv: Add little endian guest support Anton Blanchard
2013-09-25 12:10 ` [PATCH] powerpc/kvmbook3s_hv: propagate H_SET_MODE to the host Laurent Dufour
2013-09-25 12:27 ` Greg Kurz
2013-09-25 22:31 ` Paul Mackerras
2013-09-27 8:14 ` Laurent Dufour
2013-09-27 13:59 ` [PATCH V2] powerpc/kvm/book3s_hv: propagate H_SET_MODE_RESOURCE_LE " Laurent Dufour
2013-09-27 14:45 ` Greg Kurz
2013-09-30 18:40 ` [PATCH 36/39] powerpc/kvm/book3s_hv: Add little endian guest support Alexander Graf
2013-09-23 2:05 ` [PATCH 37/39] powerpc: Add ability to build little endian kernels Anton Blanchard
2013-09-23 2:05 ` [PATCH 38/39] powerpc: Don't set HAVE_EFFICIENT_UNALIGNED_ACCESS on little endian builds Anton Blanchard
2013-09-23 2:05 ` [PATCH 39/39] powerpc: Work around little endian gcc bug Anton Blanchard
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=1379901913-5945-2-git-send-email-anton@samba.org \
--to=anton@samba.org \
--cc=benh@kernel.crashing.org \
--cc=linuxppc-dev@lists.ozlabs.org \
--cc=paulus@samba.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).