This is a note to let you know that I've just added the patch titled
sparc: Use popc when possible for ffs/__ffs/ffz.
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-use-popc-when-possible-for-ffs-__ffs-ffz.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 <[email protected]> know about it.
>From d4503069f07ab8d88927ef4e10557ea95ebbd17b Mon Sep 17 00:00:00 2001
From: "David S. Miller" <[email protected]>
Date: Tue, 2 Aug 2011 20:23:34 -0700
Subject: sparc: Use popc when possible for ffs/__ffs/ffz.
From: "David S. Miller" <[email protected]>
[ Upstream commit 56d205cc5c0a3032a605121d4253e111193bf923 ]
Signed-off-by: David S. Miller <[email protected]>
Signed-off-by: Greg Kroah-Hartman <[email protected]>
---
arch/sparc/include/asm/bitops_64.h | 7 +--
arch/sparc/kernel/entry.h | 7 +++
arch/sparc/kernel/setup_64.c | 34 +++++++++-----
arch/sparc/kernel/sparc_ksyms_64.c | 4 +
arch/sparc/kernel/vmlinux.lds.S | 5 ++
arch/sparc/lib/Makefile | 2
arch/sparc/lib/ffs.S | 84 +++++++++++++++++++++++++++++++++++++
7 files changed, 127 insertions(+), 16 deletions(-)
create mode 100644 arch/sparc/lib/ffs.S
--- a/arch/sparc/include/asm/bitops_64.h
+++ b/arch/sparc/include/asm/bitops_64.h
@@ -26,16 +26,17 @@ extern void change_bit(unsigned long nr,
#define smp_mb__before_clear_bit() barrier()
#define smp_mb__after_clear_bit() barrier()
-#include <asm-generic/bitops/ffz.h>
-#include <asm-generic/bitops/__ffs.h>
#include <asm-generic/bitops/fls.h>
#include <asm-generic/bitops/__fls.h>
#include <asm-generic/bitops/fls64.h>
#ifdef __KERNEL__
+extern int ffs(int x);
+extern unsigned long __ffs(unsigned long);
+
+#include <asm-generic/bitops/ffz.h>
#include <asm-generic/bitops/sched.h>
-#include <asm-generic/bitops/ffs.h>
/*
* hweightN: returns the hamming weight (i.e. the number
--- a/arch/sparc/kernel/entry.h
+++ b/arch/sparc/kernel/entry.h
@@ -49,6 +49,13 @@ struct popc_3insn_patch_entry {
extern struct popc_3insn_patch_entry __popc_3insn_patch,
__popc_3insn_patch_end;
+struct popc_6insn_patch_entry {
+ unsigned int addr;
+ unsigned int insns[6];
+};
+extern struct popc_6insn_patch_entry __popc_6insn_patch,
+ __popc_6insn_patch_end;
+
extern void __init per_cpu_patch(void);
extern void __init sun4v_patch(void);
extern void __init boot_cpu_id_too_large(int cpu);
--- a/arch/sparc/kernel/setup_64.c
+++ b/arch/sparc/kernel/setup_64.c
@@ -275,25 +275,35 @@ void __init sun4v_patch(void)
static void __init popc_patch(void)
{
struct popc_3insn_patch_entry *p3;
+ struct popc_6insn_patch_entry *p6;
p3 = &__popc_3insn_patch;
while (p3 < &__popc_3insn_patch_end) {
- unsigned long addr = p3->addr;
+ unsigned long i, addr = p3->addr;
- *(unsigned int *) (addr + 0) = p3->insns[0];
- wmb();
- __asm__ __volatile__("flush %0" : : "r" (addr + 0));
-
- *(unsigned int *) (addr + 4) = p3->insns[1];
- wmb();
- __asm__ __volatile__("flush %0" : : "r" (addr + 4));
-
- *(unsigned int *) (addr + 8) = p3->insns[2];
- wmb();
- __asm__ __volatile__("flush %0" : : "r" (addr + 4));
+ for (i = 0; i < 3; i++) {
+ *(unsigned int *) (addr + (i * 4)) = p3->insns[i];
+ wmb();
+ __asm__ __volatile__("flush %0"
+ : : "r" (addr + (i * 4)));
+ }
p3++;
}
+
+ p6 = &__popc_6insn_patch;
+ while (p6 < &__popc_6insn_patch_end) {
+ unsigned long i, addr = p6->addr;
+
+ for (i = 0; i < 6; i++) {
+ *(unsigned int *) (addr + (i * 4)) = p6->insns[i];
+ wmb();
+ __asm__ __volatile__("flush %0"
+ : : "r" (addr + (i * 4)));
+ }
+
+ p6++;
+ }
}
#ifdef CONFIG_SMP
--- a/arch/sparc/kernel/sparc_ksyms_64.c
+++ b/arch/sparc/kernel/sparc_ksyms_64.c
@@ -45,5 +45,9 @@ EXPORT_SYMBOL(__arch_hweight16);
EXPORT_SYMBOL(__arch_hweight32);
EXPORT_SYMBOL(__arch_hweight64);
+/* from ffs_ffz.S */
+EXPORT_SYMBOL(ffs);
+EXPORT_SYMBOL(__ffs);
+
/* Exporting a symbol from /init/main.c */
EXPORT_SYMBOL(saved_command_line);
--- a/arch/sparc/kernel/vmlinux.lds.S
+++ b/arch/sparc/kernel/vmlinux.lds.S
@@ -112,6 +112,11 @@ SECTIONS
*(.popc_3insn_patch)
__popc_3insn_patch_end = .;
}
+ .popc_6insn_patch : {
+ __popc_6insn_patch = .;
+ *(.popc_6insn_patch)
+ __popc_6insn_patch_end = .;
+ }
PERCPU_SECTION(SMP_CACHE_BYTES)
. = ALIGN(PAGE_SIZE);
--- a/arch/sparc/lib/Makefile
+++ b/arch/sparc/lib/Makefile
@@ -37,7 +37,7 @@ lib-$(CONFIG_SPARC64) += GENmemcpy.o GEN
lib-$(CONFIG_SPARC64) += GENpatch.o GENpage.o GENbzero.o
lib-$(CONFIG_SPARC64) += copy_in_user.o user_fixup.o memmove.o
-lib-$(CONFIG_SPARC64) += mcount.o ipcsum.o xor.o hweight.o
+lib-$(CONFIG_SPARC64) += mcount.o ipcsum.o xor.o hweight.o ffs.o
obj-y += iomap.o
obj-$(CONFIG_SPARC32) += atomic32.o
--- /dev/null
+++ b/arch/sparc/lib/ffs.S
@@ -0,0 +1,84 @@
+#include <linux/linkage.h>
+
+ .register %g2,#scratch
+
+ .text
+ .align 32
+
+ENTRY(ffs)
+ brnz,pt %o0, 1f
+ mov 1, %o1
+ retl
+ clr %o0
+ nop
+ nop
+ENTRY(__ffs)
+ sllx %o0, 32, %g1 /* 1 */
+ srlx %o0, 32, %g2
+
+ clr %o1 /* 2 */
+ movrz %g1, %g2, %o0
+
+ movrz %g1, 32, %o1 /* 3 */
+1: clr %o2
+
+ sllx %o0, (64 - 16), %g1 /* 4 */
+ srlx %o0, 16, %g2
+
+ movrz %g1, %g2, %o0 /* 5 */
+ clr %o3
+
+ movrz %g1, 16, %o2 /* 6 */
+ clr %o4
+
+ and %o0, 0xff, %g1 /* 7 */
+ srlx %o0, 8, %g2
+
+ movrz %g1, %g2, %o0 /* 8 */
+ clr %o5
+
+ movrz %g1, 8, %o3 /* 9 */
+ add %o2, %o1, %o2
+
+ and %o0, 0xf, %g1 /* 10 */
+ srlx %o0, 4, %g2
+
+ movrz %g1, %g2, %o0 /* 11 */
+ add %o2, %o3, %o2
+
+ movrz %g1, 4, %o4 /* 12 */
+
+ and %o0, 0x3, %g1 /* 13 */
+ srlx %o0, 2, %g2
+
+ movrz %g1, %g2, %o0 /* 14 */
+ add %o2, %o4, %o2
+
+ movrz %g1, 2, %o5 /* 15 */
+
+ and %o0, 0x1, %g1 /* 16 */
+
+ add %o2, %o5, %o2 /* 17 */
+ xor %g1, 0x1, %g1
+
+ retl /* 18 */
+ add %o2, %g1, %o0
+ENDPROC(ffs)
+ENDPROC(__ffs)
+
+ .section .popc_6insn_patch, "ax"
+ .word ffs
+ brz,pn %o0, 98f
+ neg %o0, %g1
+ xnor %o0, %g1, %o1
+ popc %o1, %o0
+98: retl
+ nop
+ .word __ffs
+ neg %o0, %g1
+ xnor %o0, %g1, %o1
+ popc %o1, %o0
+ retl
+ sub %o0, 1, %o0
+ nop
+ .previous
Patches currently in stable-queue which might be from [email protected] 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
[email protected]
http://linux.kernel.org/mailman/listinfo/stable
