diff options
author | Marcelo Tosatti <mtosatti@redhat.com> | 2013-03-21 11:11:52 -0300 |
---|---|---|
committer | Marcelo Tosatti <mtosatti@redhat.com> | 2013-03-21 11:11:52 -0300 |
commit | 2ae33b389601b86a3d0cfe2d09f5e3189d5322fd (patch) | |
tree | 53e658f7ef511b5afb7d2e88753e1aaaed3de5ba /arch/arm/lib/memset.S | |
parent | 04b66839d312d3bdaff77f265eb7305347fa1fb7 (diff) | |
parent | 2ffdd7e23cde5a8b94d41ec0adfdd58cffe67f3a (diff) |
Merge remote-tracking branch 'upstream/master' into queue
Merge reason:
From: Alexander Graf <agraf@suse.de>
"Just recently this really important patch got pulled into Linus' tree for 3.9:
commit 1674400aaee5b466c595a8fc310488263ce888c7
Author: Anton Blanchard <anton <at> samba.org>
Date: Tue Mar 12 01:51:51 2013 +0000
Without that commit, I can not boot my G5, thus I can't run automated tests on it against my queue.
Could you please merge kvm/next against linus/master, so that I can base my trees against that?"
* upstream/master: (653 commits)
PCI: Use ROM images from firmware only if no other ROM source available
sparc: remove unused "config BITS"
sparc: delete "if !ULTRA_HAS_POPULATION_COUNT"
KVM: Fix bounds checking in ioapic indirect register reads (CVE-2013-1798)
KVM: x86: Convert MSR_KVM_SYSTEM_TIME to use gfn_to_hva_cache functions (CVE-2013-1797)
KVM: x86: fix for buffer overflow in handling of MSR_KVM_SYSTEM_TIME (CVE-2013-1796)
arm64: Kconfig.debug: Remove unused CONFIG_DEBUG_ERRORS
arm64: Do not select GENERIC_HARDIRQS_NO_DEPRECATED
inet: limit length of fragment queue hash table bucket lists
qeth: Fix scatter-gather regression
qeth: Fix invalid router settings handling
qeth: delay feature trace
sgy-cts1000: Remove __dev* attributes
KVM: x86: fix deadlock in clock-in-progress request handling
KVM: allow host header to be included even for !CONFIG_KVM
hwmon: (lm75) Fix tcn75 prefix
hwmon: (lm75.h) Update header inclusion
MAINTAINERS: Remove Mark M. Hoffman
xfs: ensure we capture IO errors correctly
xfs: fix xfs_iomap_eof_prealloc_initial_size type
...
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Diffstat (limited to 'arch/arm/lib/memset.S')
-rw-r--r-- | arch/arm/lib/memset.S | 100 |
1 files changed, 48 insertions, 52 deletions
diff --git a/arch/arm/lib/memset.S b/arch/arm/lib/memset.S index 650d5923ab83..94b0650ea98f 100644 --- a/arch/arm/lib/memset.S +++ b/arch/arm/lib/memset.S @@ -14,27 +14,15 @@ .text .align 5 - .word 0 - -1: subs r2, r2, #4 @ 1 do we have enough - blt 5f @ 1 bytes to align with? - cmp r3, #2 @ 1 - strltb r1, [r0], #1 @ 1 - strleb r1, [r0], #1 @ 1 - strb r1, [r0], #1 @ 1 - add r2, r2, r3 @ 1 (r2 = r2 - (4 - r3)) -/* - * The pointer is now aligned and the length is adjusted. Try doing the - * memset again. - */ ENTRY(memset) ands r3, r0, #3 @ 1 unaligned? - bne 1b @ 1 + mov ip, r0 @ preserve r0 as return value + bne 6f @ 1 /* - * we know that the pointer in r0 is aligned to a word boundary. + * we know that the pointer in ip is aligned to a word boundary. */ - orr r1, r1, r1, lsl #8 +1: orr r1, r1, r1, lsl #8 orr r1, r1, r1, lsl #16 mov r3, r1 cmp r2, #16 @@ -43,29 +31,28 @@ ENTRY(memset) #if ! CALGN(1)+0 /* - * We need an extra register for this loop - save the return address and - * use the LR + * We need 2 extra registers for this loop - use r8 and the LR */ - str lr, [sp, #-4]! - mov ip, r1 + stmfd sp!, {r8, lr} + mov r8, r1 mov lr, r1 2: subs r2, r2, #64 - stmgeia r0!, {r1, r3, ip, lr} @ 64 bytes at a time. - stmgeia r0!, {r1, r3, ip, lr} - stmgeia r0!, {r1, r3, ip, lr} - stmgeia r0!, {r1, r3, ip, lr} + stmgeia ip!, {r1, r3, r8, lr} @ 64 bytes at a time. + stmgeia ip!, {r1, r3, r8, lr} + stmgeia ip!, {r1, r3, r8, lr} + stmgeia ip!, {r1, r3, r8, lr} bgt 2b - ldmeqfd sp!, {pc} @ Now <64 bytes to go. + ldmeqfd sp!, {r8, pc} @ Now <64 bytes to go. /* * No need to correct the count; we're only testing bits from now on */ tst r2, #32 - stmneia r0!, {r1, r3, ip, lr} - stmneia r0!, {r1, r3, ip, lr} + stmneia ip!, {r1, r3, r8, lr} + stmneia ip!, {r1, r3, r8, lr} tst r2, #16 - stmneia r0!, {r1, r3, ip, lr} - ldr lr, [sp], #4 + stmneia ip!, {r1, r3, r8, lr} + ldmfd sp!, {r8, lr} #else @@ -74,54 +61,63 @@ ENTRY(memset) * whole cache lines at once. */ - stmfd sp!, {r4-r7, lr} + stmfd sp!, {r4-r8, lr} mov r4, r1 mov r5, r1 mov r6, r1 mov r7, r1 - mov ip, r1 + mov r8, r1 mov lr, r1 cmp r2, #96 - tstgt r0, #31 + tstgt ip, #31 ble 3f - and ip, r0, #31 - rsb ip, ip, #32 - sub r2, r2, ip - movs ip, ip, lsl #(32 - 4) - stmcsia r0!, {r4, r5, r6, r7} - stmmiia r0!, {r4, r5} - tst ip, #(1 << 30) - mov ip, r1 - strne r1, [r0], #4 + and r8, ip, #31 + rsb r8, r8, #32 + sub r2, r2, r8 + movs r8, r8, lsl #(32 - 4) + stmcsia ip!, {r4, r5, r6, r7} + stmmiia ip!, {r4, r5} + tst r8, #(1 << 30) + mov r8, r1 + strne r1, [ip], #4 3: subs r2, r2, #64 - stmgeia r0!, {r1, r3-r7, ip, lr} - stmgeia r0!, {r1, r3-r7, ip, lr} + stmgeia ip!, {r1, r3-r8, lr} + stmgeia ip!, {r1, r3-r8, lr} bgt 3b - ldmeqfd sp!, {r4-r7, pc} + ldmeqfd sp!, {r4-r8, pc} tst r2, #32 - stmneia r0!, {r1, r3-r7, ip, lr} + stmneia ip!, {r1, r3-r8, lr} tst r2, #16 - stmneia r0!, {r4-r7} - ldmfd sp!, {r4-r7, lr} + stmneia ip!, {r4-r7} + ldmfd sp!, {r4-r8, lr} #endif 4: tst r2, #8 - stmneia r0!, {r1, r3} + stmneia ip!, {r1, r3} tst r2, #4 - strne r1, [r0], #4 + strne r1, [ip], #4 /* * When we get here, we've got less than 4 bytes to zero. We * may have an unaligned pointer as well. */ 5: tst r2, #2 - strneb r1, [r0], #1 - strneb r1, [r0], #1 + strneb r1, [ip], #1 + strneb r1, [ip], #1 tst r2, #1 - strneb r1, [r0], #1 + strneb r1, [ip], #1 mov pc, lr + +6: subs r2, r2, #4 @ 1 do we have enough + blt 5b @ 1 bytes to align with? + cmp r3, #2 @ 1 + strltb r1, [ip], #1 @ 1 + strleb r1, [ip], #1 @ 1 + strb r1, [ip], #1 @ 1 + add r2, r2, r3 @ 1 (r2 = r2 - (4 - r3)) + b 1b ENDPROC(memset) |