This is a note to let you know that I've just added the patch titled
sparc: Minor tweaks to Niagara page copy/clear.
to the 3.0-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:
sparc-minor-tweaks-to-niagara-page-copy-clear.patch
and it can be found in the queue-3.0 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <sta...@kernel.org> know about it.
>From 6fa98bc470f338c16dd79d26e6104ddea48889d4 Mon Sep 17 00:00:00 2001
From: "David S. Miller" <da...@davemloft.net>
Date: Mon, 1 Aug 2011 18:18:57 -0700
Subject: sparc: Minor tweaks to Niagara page copy/clear.
From: "David S. Miller" <da...@davemloft.net>
[ Upstream commit e95ade083939dcb4b0c51c1a2c8504ea9ef3d6ef ]
Don't use floating point on Niagara2, use the traditional
plain Niagara code instead.
Unroll Niagara loops to 128 bytes for copy, and 256 bytes
for clear.
Signed-off-by: David S. Miller <da...@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gre...@suse.de>
---
arch/sparc/kernel/head_64.S | 2
arch/sparc/lib/Makefile | 2
arch/sparc/lib/NG2page.S | 61 -----------------------
arch/sparc/lib/NGpage.S | 114 ++++++++++++++++++++++++++++----------------
4 files changed, 77 insertions(+), 102 deletions(-)
delete mode 100644 arch/sparc/lib/NG2page.S
--- a/arch/sparc/kernel/head_64.S
+++ b/arch/sparc/kernel/head_64.S
@@ -559,7 +559,7 @@ niagara2_patch:
nop
call niagara_patch_bzero
nop
- call niagara2_patch_pageops
+ call niagara_patch_pageops
nop
ba,a,pt %xcc, 80f
--- a/arch/sparc/lib/Makefile
+++ b/arch/sparc/lib/Makefile
@@ -31,7 +31,7 @@ lib-$(CONFIG_SPARC64) += NGmemcpy.o NGco
lib-$(CONFIG_SPARC64) += NGpatch.o NGpage.o NGbzero.o
lib-$(CONFIG_SPARC64) += NG2memcpy.o NG2copy_from_user.o NG2copy_to_user.o
-lib-$(CONFIG_SPARC64) += NG2patch.o NG2page.o
+lib-$(CONFIG_SPARC64) += NG2patch.o
lib-$(CONFIG_SPARC64) += GENmemcpy.o GENcopy_from_user.o GENcopy_to_user.o
lib-$(CONFIG_SPARC64) += GENpatch.o GENpage.o GENbzero.o
--- a/arch/sparc/lib/NG2page.S
+++ /dev/null
@@ -1,61 +0,0 @@
-/* NG2page.S: Niagara-2 optimized clear and copy page.
- *
- * Copyright (C) 2007 (da...@davemloft.net)
- */
-
-#include <asm/asi.h>
-#include <asm/page.h>
-#include <asm/visasm.h>
-
- .text
- .align 32
-
- /* This is heavily simplified from the sun4u variants
- * because Niagara-2 does not have any D-cache aliasing issues.
- */
-NG2copy_user_page: /* %o0=dest, %o1=src, %o2=vaddr */
- prefetch [%o1 + 0x00], #one_read
- prefetch [%o1 + 0x40], #one_read
- VISEntryHalf
- set PAGE_SIZE, %g7
- sub %o0, %o1, %g3
-1: stxa %g0, [%o1 + %g3] ASI_BLK_INIT_QUAD_LDD_P
- subcc %g7, 64, %g7
- ldda [%o1] ASI_BLK_P, %f0
- stda %f0, [%o1 + %g3] ASI_BLK_P
- add %o1, 64, %o1
- bne,pt %xcc, 1b
- prefetch [%o1 + 0x40], #one_read
- membar #Sync
- VISExitHalf
- retl
- nop
-
-#define BRANCH_ALWAYS 0x10680000
-#define NOP 0x01000000
-#define NG_DO_PATCH(OLD, NEW) \
- sethi %hi(NEW), %g1; \
- or %g1, %lo(NEW), %g1; \
- sethi %hi(OLD), %g2; \
- or %g2, %lo(OLD), %g2; \
- sub %g1, %g2, %g1; \
- sethi %hi(BRANCH_ALWAYS), %g3; \
- sll %g1, 11, %g1; \
- srl %g1, 11 + 2, %g1; \
- or %g3, %lo(BRANCH_ALWAYS), %g3; \
- or %g3, %g1, %g3; \
- stw %g3, [%g2]; \
- sethi %hi(NOP), %g3; \
- or %g3, %lo(NOP), %g3; \
- stw %g3, [%g2 + 0x4]; \
- flush %g2;
-
- .globl niagara2_patch_pageops
- .type niagara2_patch_pageops,#function
-niagara2_patch_pageops:
- NG_DO_PATCH(copy_user_page, NG2copy_user_page)
- NG_DO_PATCH(_clear_page, NGclear_page)
- NG_DO_PATCH(clear_user_page, NGclear_user_page)
- retl
- nop
- .size niagara2_patch_pageops,.-niagara2_patch_pageops
--- a/arch/sparc/lib/NGpage.S
+++ b/arch/sparc/lib/NGpage.S
@@ -16,55 +16,91 @@
*/
NGcopy_user_page: /* %o0=dest, %o1=src, %o2=vaddr */
- prefetch [%o1 + 0x00], #one_read
- mov 8, %g1
- mov 16, %g2
- mov 24, %g3
+ save %sp, -192, %sp
+ rd %asi, %g3
+ wr %g0, ASI_BLK_INIT_QUAD_LDD_P, %asi
set PAGE_SIZE, %g7
+ prefetch [%i1 + 0x00], #one_read
+ prefetch [%i1 + 0x40], #one_read
-1: ldda [%o1 + %g0] ASI_BLK_INIT_QUAD_LDD_P, %o2
- ldda [%o1 + %g2] ASI_BLK_INIT_QUAD_LDD_P, %o4
- prefetch [%o1 + 0x40], #one_read
- add %o1, 32, %o1
- stxa %o2, [%o0 + %g0] ASI_BLK_INIT_QUAD_LDD_P
- stxa %o3, [%o0 + %g1] ASI_BLK_INIT_QUAD_LDD_P
- ldda [%o1 + %g0] ASI_BLK_INIT_QUAD_LDD_P, %o2
- stxa %o4, [%o0 + %g2] ASI_BLK_INIT_QUAD_LDD_P
- stxa %o5, [%o0 + %g3] ASI_BLK_INIT_QUAD_LDD_P
- ldda [%o1 + %g2] ASI_BLK_INIT_QUAD_LDD_P, %o4
- add %o1, 32, %o1
- add %o0, 32, %o0
- stxa %o2, [%o0 + %g0] ASI_BLK_INIT_QUAD_LDD_P
- stxa %o3, [%o0 + %g1] ASI_BLK_INIT_QUAD_LDD_P
- stxa %o4, [%o0 + %g2] ASI_BLK_INIT_QUAD_LDD_P
- stxa %o5, [%o0 + %g3] ASI_BLK_INIT_QUAD_LDD_P
- subcc %g7, 64, %g7
+1: prefetch [%i1 + 0x80], #one_read
+ prefetch [%i1 + 0xc0], #one_read
+ ldda [%i1 + 0x00] %asi, %o2
+ ldda [%i1 + 0x10] %asi, %o4
+ ldda [%i1 + 0x20] %asi, %l2
+ ldda [%i1 + 0x30] %asi, %l4
+ stxa %o2, [%i0 + 0x00] %asi
+ stxa %o3, [%i0 + 0x08] %asi
+ stxa %o4, [%i0 + 0x10] %asi
+ stxa %o5, [%i0 + 0x18] %asi
+ stxa %l2, [%i0 + 0x20] %asi
+ stxa %l3, [%i0 + 0x28] %asi
+ stxa %l4, [%i0 + 0x30] %asi
+ stxa %l5, [%i0 + 0x38] %asi
+ ldda [%i1 + 0x40] %asi, %o2
+ ldda [%i1 + 0x50] %asi, %o4
+ ldda [%i1 + 0x60] %asi, %l2
+ ldda [%i1 + 0x70] %asi, %l4
+ stxa %o2, [%i0 + 0x40] %asi
+ stxa %o3, [%i0 + 0x48] %asi
+ stxa %o4, [%i0 + 0x50] %asi
+ stxa %o5, [%i0 + 0x58] %asi
+ stxa %l2, [%i0 + 0x60] %asi
+ stxa %l3, [%i0 + 0x68] %asi
+ stxa %l4, [%i0 + 0x70] %asi
+ stxa %l5, [%i0 + 0x78] %asi
+ add %i1, 128, %i1
+ subcc %g7, 128, %g7
bne,pt %xcc, 1b
- add %o0, 32, %o0
+ add %i0, 128, %i0
+ wr %g3, 0x0, %asi
membar #Sync
- retl
- nop
+ ret
+ restore
- .globl NGclear_page, NGclear_user_page
+ .align 32
NGclear_page: /* %o0=dest */
NGclear_user_page: /* %o0=dest, %o1=vaddr */
- mov 8, %g1
- mov 16, %g2
- mov 24, %g3
+ rd %asi, %g3
+ wr %g0, ASI_BLK_INIT_QUAD_LDD_P, %asi
set PAGE_SIZE, %g7
-1: stxa %g0, [%o0 + %g0] ASI_BLK_INIT_QUAD_LDD_P
- stxa %g0, [%o0 + %g1] ASI_BLK_INIT_QUAD_LDD_P
- stxa %g0, [%o0 + %g2] ASI_BLK_INIT_QUAD_LDD_P
- stxa %g0, [%o0 + %g3] ASI_BLK_INIT_QUAD_LDD_P
- add %o0, 32, %o0
- stxa %g0, [%o0 + %g0] ASI_BLK_INIT_QUAD_LDD_P
- stxa %g0, [%o0 + %g1] ASI_BLK_INIT_QUAD_LDD_P
- stxa %g0, [%o0 + %g2] ASI_BLK_INIT_QUAD_LDD_P
- stxa %g0, [%o0 + %g3] ASI_BLK_INIT_QUAD_LDD_P
- subcc %g7, 64, %g7
+1: stxa %g0, [%o0 + 0x00] %asi
+ stxa %g0, [%o0 + 0x08] %asi
+ stxa %g0, [%o0 + 0x10] %asi
+ stxa %g0, [%o0 + 0x18] %asi
+ stxa %g0, [%o0 + 0x20] %asi
+ stxa %g0, [%o0 + 0x28] %asi
+ stxa %g0, [%o0 + 0x30] %asi
+ stxa %g0, [%o0 + 0x38] %asi
+ stxa %g0, [%o0 + 0x40] %asi
+ stxa %g0, [%o0 + 0x48] %asi
+ stxa %g0, [%o0 + 0x50] %asi
+ stxa %g0, [%o0 + 0x58] %asi
+ stxa %g0, [%o0 + 0x60] %asi
+ stxa %g0, [%o0 + 0x68] %asi
+ stxa %g0, [%o0 + 0x70] %asi
+ stxa %g0, [%o0 + 0x78] %asi
+ stxa %g0, [%o0 + 0x80] %asi
+ stxa %g0, [%o0 + 0x88] %asi
+ stxa %g0, [%o0 + 0x90] %asi
+ stxa %g0, [%o0 + 0x98] %asi
+ stxa %g0, [%o0 + 0xa0] %asi
+ stxa %g0, [%o0 + 0xa8] %asi
+ stxa %g0, [%o0 + 0xb0] %asi
+ stxa %g0, [%o0 + 0xb8] %asi
+ stxa %g0, [%o0 + 0xc0] %asi
+ stxa %g0, [%o0 + 0xc8] %asi
+ stxa %g0, [%o0 + 0xd0] %asi
+ stxa %g0, [%o0 + 0xd8] %asi
+ stxa %g0, [%o0 + 0xe0] %asi
+ stxa %g0, [%o0 + 0xe8] %asi
+ stxa %g0, [%o0 + 0xf0] %asi
+ stxa %g0, [%o0 + 0xf8] %asi
+ subcc %g7, 256, %g7
bne,pt %xcc, 1b
- add %o0, 32, %o0
+ add %o0, 256, %o0
+ wr %g3, 0x0, %asi
membar #Sync
retl
nop
Patches currently in stable-queue which might be from da...@davemloft.net are
queue-3.0/ipv4-send-gratuitous-arp-for-secondary-ip-addresses-also.patch
queue-3.0/ipv4-constrain-ufo-fragment-sizes-to-multiples-of-8-bytes.patch
queue-3.0/sparc-detect-and-handle-ultrasparc-t3-cpu-types.patch
queue-3.0/bonding-fix-string-comparison-errors.patch
queue-3.0/sparc-use-popc-if-possible-for-hweight-routines.patch
queue-3.0/drivers-net-niu.c-adjust-array-index.patch
queue-3.0/sparc-set-reboot-cmd-using-reboot-data-hypervisor-call-if-available.patch
queue-3.0/net-audit-drivers-to-identify-those-needing-iff_tx_skb_sharing-cleared.patch
queue-3.0/sparc-size-mondo-queues-more-sanely.patch
queue-3.0/sparc-don-t-leave-sparc_pmu_type-null-on-sun4v.patch
queue-3.0/ipv4-use-rt_tos-after-some-rt_tos-conversions.patch
queue-3.0/net-cap-number-of-elements-for-sendmmsg.patch
queue-3.0/sch_sfq-fix-sfq_enqueue.patch
queue-3.0/sparc-sanitize-cpu-feature-detection-and-reporting.patch
queue-3.0/sparc-use-popc-when-possible-for-ffs-__ffs-ffz.patch
queue-3.0/sparc-add-t3-sun4v-cpu-type-and-hypervisor-group-defines.patch
queue-3.0/net-fix-security_socket_sendmsg-bypass-problem.patch
queue-3.0/sparc-use-hweight64-in-popc-emulation.patch
queue-3.0/0002-net-Compute-protocol-sequence-numbers-and-fragment-I.patch
queue-3.0/sparc-add-some-missing-hypervisor-api-groups.patch
queue-3.0/fix-cdc-phonet-build.patch
queue-3.0/sparc-minor-tweaks-to-niagara-page-copy-clear.patch
queue-3.0/ipv4-fix-the-reusing-of-routing-cache-entries.patch
queue-3.0/ipv6-make-fragment-identifications-less-predictable.patch
queue-3.0/sis190-rx-filter-init-is-needed-for-mac-address-change.patch
queue-3.0/net-adjust-array-index.patch
queue-3.0/sparc-access-kernel-tsb-using-physical-addressing-when-possible.patch
queue-3.0/net-allow-netif_carrier-to-be-called-safely-from-irq.patch
queue-3.0/sparc-fix-build-with-debug_pagealloc-enabled.patch
queue-3.0/icmp-fix-regression-in-nexthop-resolution-during-replies.patch
queue-3.0/xfrm-fix-key-lengths-for-rfc3686-ctr-aes.patch
queue-3.0/0001-crypto-Move-md5_transform-to-lib-md5.c.patch
queue-3.0/gre-fix-improper-error-handling.patch
queue-3.0/net-add-iff_skb_tx_shared-flag-to-priv_flags.patch
queue-3.0/r8169-add-support-for-d-link-530t-rev-c1-kernel-bug-38862.patch
queue-3.0/sparc-don-t-do-expensive-hypervisor-pcr-write-unless-necessary.patch
queue-3.0/net-sendmmsg-should-only-return-an-error-if-no-messages-were-sent.patch
queue-3.0/mpt2sas-fixed-big-indian-issues-on-32-bit-ppc.patch
_______________________________________________
stable mailing list
stable@linux.kernel.org
http://linux.kernel.org/mailman/listinfo/stable
