From: Greg KH <gregkh@suse.de>
To: linux-kernel@vger.kernel.org, stable@kernel.org
Cc: stable-review@kernel.org, torvalds@linux-foundation.org,
akpm@linux-foundation.org, alan@lxorguk.ukuu.org.uk,
"David S. Miller" <davem@davemloft.net>
Subject: [68/90] sparc: Minor tweaks to Niagara page copy/clear.
Date: Fri, 12 Aug 2011 14:04:53 -0700 [thread overview]
Message-ID: <20110812210558.068970326@clark.kroah.org> (raw)
In-Reply-To: <20110812210626.GA4725@kroah.com>
3.0-stable review patch. If anyone has any objections, please let us know.
------------------
From: "David S. Miller" <davem@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 <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@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 (davem@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
next prev parent reply other threads:[~2011-08-14 16:09 UTC|newest]
Thread overview: 99+ messages / expand[flat|nested] mbox.gz Atom feed top
2011-08-12 21:06 [00/90] 3.0.2-stable review Greg KH
2011-08-12 21:03 ` [01/90] cris: fix a build error in kernel/fork.c Greg KH
2011-08-12 21:03 ` [02/90] cris: fix a build error in sync_serial_open() Greg KH
2011-08-12 21:03 ` [03/90] cris: fix the prototype of sync_serial_ioctl() Greg KH
2011-08-12 21:03 ` [04/90] cris: add missing declaration of kgdb_init() and breakpoint() Greg KH
2011-08-12 21:03 ` [05/90] futex: Fix regression with read only mappings Greg KH
2011-08-12 21:03 ` [06/90] [PARISC] wire up sendmmsg syscall Greg KH
2011-08-12 21:03 ` [07/90] [PARISC] Fix futex support Greg KH
2011-08-12 21:03 ` [08/90] [PARISC] fix return type of __atomic64_add_return Greg KH
2011-08-12 21:03 ` [09/90] rt2x00: rt2800: fix zeroing skb structure Greg KH
2011-08-12 21:03 ` [10/90] rt2x00: fix usage of NULL queue Greg KH
2011-08-12 21:03 ` [11/90] rtlwifi: Fix kernel oops on ARM SOC Greg KH
2011-08-12 21:03 ` [12/90] iwlegacy: set tx power after rxon_assoc Greg KH
2011-08-12 21:03 ` [13/90] ath9k: initialize tx chainmask before testing channel tx power values Greg KH
2011-08-12 21:03 ` [14/90] ath9k: skip ->config_pci_powersave() if PCIe port has ASPM disabled Greg KH
2011-08-12 21:04 ` [15/90] net: sendmmsg should only return an error if no messages were sent Greg KH
2011-08-12 21:04 ` [16/90] net: Cap number of elements for sendmmsg Greg KH
2011-08-12 21:04 ` [17/90] net: Fix security_socket_sendmsg() bypass problem Greg KH
2011-08-12 21:04 ` [18/90] xen: allow enable use of VGA console on dom0 Greg KH
2011-08-12 21:04 ` [19/90] drm: Separate EDID Header Check from EDID Block Check Greg KH
2011-08-12 21:04 ` [20/90] drm/radeon: Extended DDC Probing for Connectors with Improperly Wired DDC Lines (here: Asus M2A-VM HDMI) Greg KH
2011-08-12 21:04 ` [21/90] drm/radeon: Extended DDC Probing for ECS A740GM-M DVI-D Connector Greg KH
2011-08-12 21:04 ` [22/90] drm/radeon: Log Subsystem Vendor and Device Information Greg KH
2011-08-12 21:04 ` [23/90] drm/i915/pch: Fix integer math bugs in panel fitting Greg KH
2011-08-12 21:04 ` [24/90] drm/i915: load the LUT before pipe enable on ILK+ Greg KH
2011-08-12 21:04 ` [25/90] drm/i915: Fix typo in DRM_I915_OVERLAY_PUT_IMAGE ioctl define Greg KH
2011-08-12 21:04 ` [26/90] drm/i915: Initialize RCS ring status page address in intel_render_ring_init_dri Greg KH
2011-08-12 21:04 ` [27/90] drm/i915: Hold mode_config->mutex during hotplug processing Greg KH
2011-08-12 21:04 ` [28/90] drm/i915: Fixup for Hold mode_config->mutex during hotplug Greg KH
2011-08-12 21:04 ` [29/90] crypto: Move md5_transform to lib/md5.c Greg KH
2011-08-12 21:04 ` [30/90] net: Compute protocol sequence numbers and fragment IDs using MD5 Greg KH
2011-08-12 21:04 ` [31/90] asus-wmi: fix hwmon/pwm1 Greg KH
2011-08-12 21:04 ` [32/90] asus-wmi: return proper value in store_cpufv() Greg KH
2011-08-12 21:04 ` [33/90] CIFS: Fix missing a decrement of inFlight value Greg KH
2011-08-12 21:04 ` [34/90] cifs: cope with negative dentries in cifs_get_root Greg KH
2011-08-12 21:04 ` [35/90] cifs: convert prefixpath delimiters in Greg KH
2011-08-12 21:04 ` [36/90] ASoC: sgtl5000: fix cache handling Greg KH
2011-08-12 21:04 ` [37/90] ALSA: timer - Fix Oops at closing slave timer Greg KH
2011-08-12 21:04 ` [38/90] ALSA: snd-usb-caiaq: Fix keymap for RigKontrol3 Greg KH
2011-08-12 21:04 ` [39/90] ALSA: snd-usb: avoid dividing by zero on invalid input Greg KH
2011-08-12 21:04 ` [40/90] ALSA: snd-usb: operate on given mixer interface only Greg KH
2011-08-12 21:04 ` [41/90] ALSA: snd-usb: Accept UAC2 FORMAT_TYPE descriptors with Greg KH
2011-08-12 21:04 ` [42/90] ipv6: make fragment identifications less predictable Greg KH
2011-08-12 21:04 ` [43/90] icmp: Fix regression in nexthop resolution during replies Greg KH
2011-08-12 21:04 ` [44/90] ipv4: Constrain UFO fragment sizes to multiples of 8 bytes Greg KH
2011-08-12 21:04 ` [45/90] ipv4: fix the reusing of routing cache entries Greg KH
2011-08-12 21:04 ` [46/90] IPVS: Free resources on module removal Greg KH
2011-08-12 21:04 ` [47/90] net: adjust array index Greg KH
2011-08-12 21:04 ` [48/90] drivers/net/niu.c: " Greg KH
2011-08-12 21:04 ` [49/90] sch_sfq: fix sfq_enqueue() Greg KH
2011-08-12 21:04 ` [50/90] IPv4: Send gratuitous ARP for secondary IP addresses also Greg KH
2011-08-12 21:04 ` [51/90] net: add IFF_SKB_TX_SHARED flag to priv_flags Greg KH
2011-08-12 21:04 ` [52/90] net: Audit drivers to identify those needing IFF_TX_SKB_SHARING cleared Greg KH
2011-08-12 21:04 ` [53/90] bonding: fix string comparison errors Greg KH
2011-08-12 21:04 ` [54/90] Fix cdc-phonet build Greg KH
2011-08-12 21:04 ` [55/90] xfrm: Fix key lengths for rfc3686(ctr(aes)) Greg KH
2011-08-12 21:04 ` [56/90] sis190: Rx filter init is needed for MAC address change Greg KH
2011-08-12 21:04 ` [57/90] r8169: Add support for D-Link 530T rev C1 (Kernel Bug 38862) Greg KH
2011-08-12 21:04 ` [58/90] net: allow netif_carrier to be called safely from IRQ Greg KH
2011-08-12 21:04 ` [59/90] ipv4: use RT_TOS after some rt_tos conversions Greg KH
2011-08-12 21:04 ` [60/90] gre: fix improper error handling Greg KH
2011-08-12 21:04 ` [61/90] iwlagn: 5000 do not support idle mode Greg KH
2011-08-12 21:04 ` [62/90] [SCSI] mpt2sas: Fixed Big Indian Issues on 32 bit PPC Greg KH
2011-08-12 21:04 ` [63/90] sparc: Dont leave sparc_pmu_type NULL on sun4v Greg KH
2011-08-12 21:04 ` [64/90] sparc: Add T3 sun4v cpu type and hypervisor group defines Greg KH
2011-08-12 21:04 ` [65/90] sparc: Dont do expensive hypervisor PCR write unless necessary Greg KH
2011-08-12 21:04 ` [66/90] sparc: Detect and handle UltraSPARC-T3 cpu types Greg KH
2011-08-12 21:04 ` [67/90] sparc: Sanitize cpu feature detection and reporting Greg KH
2011-08-12 21:04 ` Greg KH [this message]
2011-08-12 21:04 ` [69/90] sparc: Use popc if possible for hweight routines Greg KH
2011-08-12 21:04 ` [70/90] sparc: Use hweight64() in popc emulation Greg KH
2011-08-12 21:04 ` [71/90] sparc: Add some missing hypervisor API groups Greg KH
2011-08-12 21:04 ` [72/90] sparc: Set reboot-cmd using reboot data hypervisor call if available Greg KH
2011-08-12 21:04 ` [73/90] sparc: Use popc when possible for ffs/__ffs/ffz Greg KH
2011-08-12 21:04 ` [74/90] sparc: Access kernel TSB using physical addressing when possible Greg KH
2011-08-12 21:05 ` [75/90] sparc: Size mondo queues more sanely Greg KH
2011-08-12 21:05 ` [76/90] sparc: Fix build with DEBUG_PAGEALLOC enabled Greg KH
2011-08-12 21:05 ` [77/90] Ecryptfs: Add mount option to check uid of device being Greg KH
2011-08-12 21:05 ` [78/90] eCryptfs: Return error when lower file pointer is NULL Greg KH
2011-08-12 21:05 ` [79/90] powerpc/pseries: Fix kexec on recent firmware versions Greg KH
2011-08-12 21:05 ` [80/90] powerpc: Fix device tree claim code Greg KH
2011-08-12 21:05 ` [81/90] powerpc: pseries: Fix kexec on machines with more than 4TB of RAM Greg KH
2011-08-12 21:05 ` [82/90] ext3: Properly count journal credits for long symlinks Greg KH
2011-08-12 21:05 ` [83/90] ext4: " Greg KH
2011-08-12 21:05 ` [84/90] e1000e: alternate MAC address does not work on device id 0x1060 Greg KH
2011-08-12 21:05 ` [85/90] gianfar: fix fiper alignment after resetting the time Greg KH
2011-08-12 21:05 ` [86/90] dp83640: increase receive time stamp buffer size Greg KH
2011-08-12 21:05 ` [87/90] ath9k_hw: Fix incorrect Tx control power in AR9003 template Greg KH
2011-08-12 21:05 ` [88/90] ath9k: fix a misprint which leads to incorrect calibration Greg KH
2011-08-12 21:05 ` [89/90] sparc: Dont do hypervisor calls on non-sun4v in DS driver Greg KH
2011-08-12 21:05 ` [90/90] mm: Fix fixup_user_fault() for MMU=n Greg KH
2011-08-14 10:31 ` [00/90] 3.0.2-stable review Jiri Slaby
2011-08-14 16:18 ` Greg KH
2011-08-15 20:56 ` Dave Jones
2011-08-16 1:24 ` Greg KH
2011-08-16 17:46 ` Arnaud Lacombe
2011-08-16 17:59 ` Greg KH
2011-08-16 18:10 ` Linus Torvalds
2011-08-16 21:11 ` H. Peter Anvin
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=20110812210558.068970326@clark.kroah.org \
--to=gregkh@suse.de \
--cc=akpm@linux-foundation.org \
--cc=alan@lxorguk.ukuu.org.uk \
--cc=davem@davemloft.net \
--cc=linux-kernel@vger.kernel.org \
--cc=stable-review@kernel.org \
--cc=stable@kernel.org \
--cc=torvalds@linux-foundation.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
all inboxes | Powered by JetHome®