diff options
Diffstat (limited to 'arch/ia64/lib')
| -rw-r--r-- | arch/ia64/lib/Makefile | 7 | ||||
| -rw-r--r-- | arch/ia64/lib/checksum.c | 39 | ||||
| -rw-r--r-- | arch/ia64/lib/clear_page.S | 1 | ||||
| -rw-r--r-- | arch/ia64/lib/csum_partial_copy.c | 31 | ||||
| -rw-r--r-- | arch/ia64/lib/do_csum.S | 2 | ||||
| -rw-r--r-- | arch/ia64/lib/flush.S | 55 | ||||
| -rw-r--r-- | arch/ia64/lib/io.c | 1 | ||||
| -rw-r--r-- | arch/ia64/lib/ip_fast_csum.S | 60 | ||||
| -rw-r--r-- | arch/ia64/lib/memcpy_mck.S | 1 |
9 files changed, 145 insertions, 52 deletions
diff --git a/arch/ia64/lib/Makefile b/arch/ia64/lib/Makefile index d8536a2c22a..98771e2a78a 100644 --- a/arch/ia64/lib/Makefile +++ b/arch/ia64/lib/Makefile @@ -9,12 +9,11 @@ lib-y := __divsi3.o __udivsi3.o __modsi3.o __umodsi3.o \ checksum.o clear_page.o csum_partial_copy.o \ clear_user.o strncpy_from_user.o strlen_user.o strnlen_user.o \ flush.o ip_fast_csum.o do_csum.o \ - memset.o strlen.o + memset.o strlen.o xor.o -lib-$(CONFIG_ITANIUM) += copy_page.o copy_user.o memcpy.o -lib-$(CONFIG_MCKINLEY) += copy_page_mck.o memcpy_mck.o +obj-$(CONFIG_ITANIUM) += copy_page.o copy_user.o memcpy.o +obj-$(CONFIG_MCKINLEY) += copy_page_mck.o memcpy_mck.o lib-$(CONFIG_PERFMON) += carta_random.o -lib-$(CONFIG_MD_RAID5) += xor.o AFLAGS___divdi3.o = AFLAGS___udivdi3.o = -DUNSIGNED diff --git a/arch/ia64/lib/checksum.c b/arch/ia64/lib/checksum.c index beb11721d9f..9fc955026f8 100644 --- a/arch/ia64/lib/checksum.c +++ b/arch/ia64/lib/checksum.c @@ -33,33 +33,34 @@ from64to16 (unsigned long x) * computes the checksum of the TCP/UDP pseudo-header * returns a 16-bit checksum, already complemented. */ -unsigned short int -csum_tcpudp_magic (unsigned long saddr, unsigned long daddr, unsigned short len, - unsigned short proto, unsigned int sum) +__sum16 +csum_tcpudp_magic (__be32 saddr, __be32 daddr, unsigned short len, + unsigned short proto, __wsum sum) { - return ~from64to16(saddr + daddr + sum + ((unsigned long) ntohs(len) << 16) + - ((unsigned long) proto << 8)); + return (__force __sum16)~from64to16( + (__force u64)saddr + (__force u64)daddr + + (__force u64)sum + ((len + proto) << 8)); } EXPORT_SYMBOL(csum_tcpudp_magic); -unsigned int -csum_tcpudp_nofold (unsigned long saddr, unsigned long daddr, unsigned short len, - unsigned short proto, unsigned int sum) +__wsum +csum_tcpudp_nofold (__be32 saddr, __be32 daddr, unsigned short len, + unsigned short proto, __wsum sum) { unsigned long result; - result = (saddr + daddr + sum + - ((unsigned long) ntohs(len) << 16) + - ((unsigned long) proto << 8)); + result = (__force u64)saddr + (__force u64)daddr + + (__force u64)sum + ((len + proto) << 8); /* Fold down to 32-bits so we don't lose in the typedef-less network stack. */ /* 64 to 33 */ result = (result & 0xffffffff) + (result >> 32); /* 33 to 32 */ result = (result & 0xffffffff) + (result >> 32); - return result; + return (__force __wsum)result; } +EXPORT_SYMBOL(csum_tcpudp_nofold); extern unsigned long do_csum (const unsigned char *, long); @@ -75,16 +76,15 @@ extern unsigned long do_csum (const unsigned char *, long); * * it's best to have buff aligned on a 32-bit boundary */ -unsigned int -csum_partial (const unsigned char * buff, int len, unsigned int sum) +__wsum csum_partial(const void *buff, int len, __wsum sum) { - unsigned long result = do_csum(buff, len); + u64 result = do_csum(buff, len); /* add in old sum, and carry.. */ - result += sum; + result += (__force u32)sum; /* 32+c bits -> 32 bits */ result = (result & 0xffffffff) + (result >> 32); - return result; + return (__force __wsum)result; } EXPORT_SYMBOL(csum_partial); @@ -93,10 +93,9 @@ EXPORT_SYMBOL(csum_partial); * this routine is used for miscellaneous IP-like checksums, mainly * in icmp.c */ -unsigned short -ip_compute_csum (unsigned char * buff, int len) +__sum16 ip_compute_csum (const void *buff, int len) { - return ~do_csum(buff,len); + return (__force __sum16)~do_csum(buff,len); } EXPORT_SYMBOL(ip_compute_csum); diff --git a/arch/ia64/lib/clear_page.S b/arch/ia64/lib/clear_page.S index d4987061dda..2d814e7ed19 100644 --- a/arch/ia64/lib/clear_page.S +++ b/arch/ia64/lib/clear_page.S @@ -8,7 +8,6 @@ * 2/12/02 kchen Tuned for both Itanium and McKinley * 3/08/02 davidm Some more tweaking */ -#include <linux/config.h> #include <asm/asmmacro.h> #include <asm/page.h> diff --git a/arch/ia64/lib/csum_partial_copy.c b/arch/ia64/lib/csum_partial_copy.c index 36866e8a5d2..118daf5a063 100644 --- a/arch/ia64/lib/csum_partial_copy.c +++ b/arch/ia64/lib/csum_partial_copy.c @@ -104,9 +104,9 @@ out: */ extern unsigned long do_csum(const unsigned char *, long); -static unsigned int -do_csum_partial_copy_from_user (const unsigned char __user *src, unsigned char *dst, - int len, unsigned int psum, int *errp) +__wsum +csum_partial_copy_from_user(const void __user *src, void *dst, + int len, __wsum psum, int *errp) { unsigned long result; @@ -122,30 +122,19 @@ do_csum_partial_copy_from_user (const unsigned char __user *src, unsigned char * result = do_csum(dst, len); /* add in old sum, and carry.. */ - result += psum; + result += (__force u32)psum; /* 32+c bits -> 32 bits */ result = (result & 0xffffffff) + (result >> 32); - return result; + return (__force __wsum)result; } -unsigned int -csum_partial_copy_from_user (const unsigned char __user *src, unsigned char *dst, - int len, unsigned int sum, int *errp) -{ - if (!access_ok(VERIFY_READ, src, len)) { - *errp = -EFAULT; - memset(dst, 0, len); - return sum; - } - - return do_csum_partial_copy_from_user(src, dst, len, sum, errp); -} +EXPORT_SYMBOL(csum_partial_copy_from_user); -unsigned int -csum_partial_copy_nocheck(const unsigned char __user *src, unsigned char *dst, - int len, unsigned int sum) +__wsum +csum_partial_copy_nocheck(const void *src, void *dst, int len, __wsum sum) { - return do_csum_partial_copy_from_user(src, dst, len, sum, NULL); + return csum_partial_copy_from_user((__force const void __user *)src, + dst, len, sum, NULL); } EXPORT_SYMBOL(csum_partial_copy_nocheck); diff --git a/arch/ia64/lib/do_csum.S b/arch/ia64/lib/do_csum.S index 6bec2fc9f5b..1a431a5cf86 100644 --- a/arch/ia64/lib/do_csum.S +++ b/arch/ia64/lib/do_csum.S @@ -201,7 +201,7 @@ GLOBAL_ENTRY(do_csum) ;; (p6) adds result1[0]=1,result1[0] (p9) br.cond.sptk .do_csum_exit // if (count == 1) exit - // Fall through to caluculate the checksum, feeding result1[0] as + // Fall through to calculate the checksum, feeding result1[0] as // the initial value in result1[0]. // // Calculate the checksum loading two 8-byte words per loop. diff --git a/arch/ia64/lib/flush.S b/arch/ia64/lib/flush.S index 2a0d27f2f21..1d8c8886006 100644 --- a/arch/ia64/lib/flush.S +++ b/arch/ia64/lib/flush.S @@ -60,3 +60,58 @@ GLOBAL_ENTRY(flush_icache_range) mov ar.lc=r3 // restore ar.lc br.ret.sptk.many rp END(flush_icache_range) + + /* + * clflush_cache_range(start,size) + * + * Flush cache lines from start to start+size-1. + * + * Must deal with range from start to start+size-1 but nothing else + * (need to be careful not to touch addresses that may be + * unmapped). + * + * Note: "in0" and "in1" are preserved for debugging purposes. + */ + .section .kprobes.text,"ax" +GLOBAL_ENTRY(clflush_cache_range) + + .prologue + alloc r2=ar.pfs,2,0,0,0 + movl r3=ia64_cache_stride_shift + mov r21=1 + add r22=in1,in0 + ;; + ld8 r20=[r3] // r20: stride shift + sub r22=r22,r0,1 // last byte address + ;; + shr.u r23=in0,r20 // start / (stride size) + shr.u r22=r22,r20 // (last byte address) / (stride size) + shl r21=r21,r20 // r21: stride size of the i-cache(s) + ;; + sub r8=r22,r23 // number of strides - 1 + shl r24=r23,r20 // r24: addresses for "fc" = + // "start" rounded down to stride + // boundary + .save ar.lc,r3 + mov r3=ar.lc // save ar.lc + ;; + + .body + mov ar.lc=r8 + ;; + /* + * 32 byte aligned loop, even number of (actually 2) bundles + */ +.Loop_fc: + fc r24 // issuable on M0 only + add r24=r21,r24 // we flush "stride size" bytes per iteration + nop.i 0 + br.cloop.sptk.few .Loop_fc + ;; + sync.i + ;; + srlz.i + ;; + mov ar.lc=r3 // restore ar.lc + br.ret.sptk.many rp +END(clflush_cache_range) diff --git a/arch/ia64/lib/io.c b/arch/ia64/lib/io.c index 8949e44091a..bcd16f8ad9d 100644 --- a/arch/ia64/lib/io.c +++ b/arch/ia64/lib/io.c @@ -1,4 +1,3 @@ -#include <linux/config.h> #include <linux/module.h> #include <linux/types.h> diff --git a/arch/ia64/lib/ip_fast_csum.S b/arch/ia64/lib/ip_fast_csum.S index 19674ca2acf..620d9dc5220 100644 --- a/arch/ia64/lib/ip_fast_csum.S +++ b/arch/ia64/lib/ip_fast_csum.S @@ -8,8 +8,8 @@ * in0: address of buffer to checksum (char *) * in1: length of the buffer (int) * - * Copyright (C) 2002 Intel Corp. - * Copyright (C) 2002 Ken Chen <kenneth.w.chen@intel.com> + * Copyright (C) 2002, 2006 Intel Corp. + * Copyright (C) 2002, 2006 Ken Chen <kenneth.w.chen@intel.com> */ #include <asm/asmmacro.h> @@ -25,6 +25,9 @@ #define in0 r32 #define in1 r33 +#define in2 r34 +#define in3 r35 +#define in4 r36 #define ret0 r8 GLOBAL_ENTRY(ip_fast_csum) @@ -65,8 +68,9 @@ GLOBAL_ENTRY(ip_fast_csum) zxt2 r20=r20 ;; add r20=ret0,r20 + mov r9=0xffff ;; - andcm ret0=-1,r20 + andcm ret0=r9,r20 .restore sp // reset frame state br.ret.sptk.many b0 ;; @@ -88,3 +92,53 @@ GLOBAL_ENTRY(ip_fast_csum) mov b0=r34 br.ret.sptk.many b0 END(ip_fast_csum) + +GLOBAL_ENTRY(csum_ipv6_magic) + ld4 r20=[in0],4 + ld4 r21=[in1],4 + zxt4 in2=in2 + ;; + ld4 r22=[in0],4 + ld4 r23=[in1],4 + dep r15=in3,in2,32,16 + ;; + ld4 r24=[in0],4 + ld4 r25=[in1],4 + mux1 r15=r15,@rev + add r16=r20,r21 + add r17=r22,r23 + zxt4 in4=in4 + ;; + ld4 r26=[in0],4 + ld4 r27=[in1],4 + shr.u r15=r15,16 + add r18=r24,r25 + add r8=r16,r17 + ;; + add r19=r26,r27 + add r8=r8,r18 + ;; + add r8=r8,r19 + add r15=r15,in4 + ;; + add r8=r8,r15 + ;; + shr.u r10=r8,32 // now fold sum into short + zxt4 r11=r8 + ;; + add r8=r10,r11 + ;; + shr.u r10=r8,16 // yeah, keep it rolling + zxt2 r11=r8 + ;; + add r8=r10,r11 + ;; + shr.u r10=r8,16 // three times lucky + zxt2 r11=r8 + ;; + add r8=r10,r11 + mov r9=0xffff + ;; + andcm r8=r9,r8 + br.ret.sptk.many b0 +END(csum_ipv6_magic) diff --git a/arch/ia64/lib/memcpy_mck.S b/arch/ia64/lib/memcpy_mck.S index 9e534d52b1d..ab0f8763972 100644 --- a/arch/ia64/lib/memcpy_mck.S +++ b/arch/ia64/lib/memcpy_mck.S @@ -13,7 +13,6 @@ * Copyright (C) 2002 Intel Corp. * Copyright (C) 2002 Ken Chen <kenneth.w.chen@intel.com> */ -#include <linux/config.h> #include <asm/asmmacro.h> #include <asm/page.h> |