diff options
Diffstat (limited to 'arch/ia64/lib')
| -rw-r--r-- | arch/ia64/lib/Makefile | 10 | ||||
| -rw-r--r-- | arch/ia64/lib/bitop.c | 88 | ||||
| -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/dec_and_lock.c | 42 | ||||
| -rw-r--r-- | arch/ia64/lib/do_csum.S | 2 | ||||
| -rw-r--r-- | arch/ia64/lib/flush.S | 56 | ||||
| -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 | 13 | ||||
| -rw-r--r-- | arch/ia64/lib/swiotlb.c | 657 |
12 files changed, 156 insertions, 844 deletions
diff --git a/arch/ia64/lib/Makefile b/arch/ia64/lib/Makefile index 799407e7726..98771e2a78a 100644 --- a/arch/ia64/lib/Makefile +++ b/arch/ia64/lib/Makefile @@ -6,16 +6,14 @@ obj-y := io.o lib-y := __divsi3.o __udivsi3.o __modsi3.o __umodsi3.o \ __divdi3.o __udivdi3.o __moddi3.o __umoddi3.o \ - bitop.o checksum.o clear_page.o csum_partial_copy.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 swiotlb.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 -lib-$(CONFIG_HAVE_DEC_LOCK) += dec_and_lock.o AFLAGS___divdi3.o = AFLAGS___udivdi3.o = -DUNSIGNED diff --git a/arch/ia64/lib/bitop.c b/arch/ia64/lib/bitop.c deleted file mode 100644 index 82e299c8464..00000000000 --- a/arch/ia64/lib/bitop.c +++ /dev/null @@ -1,88 +0,0 @@ -#include <linux/compiler.h> -#include <linux/types.h> -#include <asm/intrinsics.h> -#include <linux/module.h> -#include <linux/bitops.h> - -/* - * Find next zero bit in a bitmap reasonably efficiently.. - */ - -int __find_next_zero_bit (const void *addr, unsigned long size, unsigned long offset) -{ - unsigned long *p = ((unsigned long *) addr) + (offset >> 6); - unsigned long result = offset & ~63UL; - unsigned long tmp; - - if (offset >= size) - return size; - size -= result; - offset &= 63UL; - if (offset) { - tmp = *(p++); - tmp |= ~0UL >> (64-offset); - if (size < 64) - goto found_first; - if (~tmp) - goto found_middle; - size -= 64; - result += 64; - } - while (size & ~63UL) { - if (~(tmp = *(p++))) - goto found_middle; - result += 64; - size -= 64; - } - if (!size) - return result; - tmp = *p; -found_first: - tmp |= ~0UL << size; - if (tmp == ~0UL) /* any bits zero? */ - return result + size; /* nope */ -found_middle: - return result + ffz(tmp); -} -EXPORT_SYMBOL(__find_next_zero_bit); - -/* - * Find next bit in a bitmap reasonably efficiently.. - */ -int __find_next_bit(const void *addr, unsigned long size, unsigned long offset) -{ - unsigned long *p = ((unsigned long *) addr) + (offset >> 6); - unsigned long result = offset & ~63UL; - unsigned long tmp; - - if (offset >= size) - return size; - size -= result; - offset &= 63UL; - if (offset) { - tmp = *(p++); - tmp &= ~0UL << offset; - if (size < 64) - goto found_first; - if (tmp) - goto found_middle; - size -= 64; - result += 64; - } - while (size & ~63UL) { - if ((tmp = *(p++))) - goto found_middle; - result += 64; - size -= 64; - } - if (!size) - return result; - tmp = *p; - found_first: - tmp &= ~0UL >> (64-size); - if (tmp == 0UL) /* Are any bits set? */ - return result + size; /* Nope. */ - found_middle: - return result + __ffs(tmp); -} -EXPORT_SYMBOL(__find_next_bit); 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/dec_and_lock.c b/arch/ia64/lib/dec_and_lock.c deleted file mode 100644 index c7ce92f968f..00000000000 --- a/arch/ia64/lib/dec_and_lock.c +++ /dev/null @@ -1,42 +0,0 @@ -/* - * Copyright (C) 2003 Jerome Marchand, Bull S.A. - * Cleaned up by David Mosberger-Tang <davidm@hpl.hp.com> - * - * This file is released under the GPLv2, or at your option any later version. - * - * ia64 version of "atomic_dec_and_lock()" using the atomic "cmpxchg" instruction. This - * code is an adaptation of the x86 version of "atomic_dec_and_lock()". - */ - -#include <linux/compiler.h> -#include <linux/module.h> -#include <linux/spinlock.h> -#include <asm/atomic.h> - -/* - * Decrement REFCOUNT and if the count reaches zero, acquire the spinlock. Both of these - * operations have to be done atomically, so that the count doesn't drop to zero without - * acquiring the spinlock first. - */ -int -_atomic_dec_and_lock (atomic_t *refcount, spinlock_t *lock) -{ - int old, new; - - do { - old = atomic_read(refcount); - new = old - 1; - - if (unlikely (old == 1)) { - /* oops, we may be decrementing to zero, do it the slow way... */ - spin_lock(lock); - if (atomic_dec_and_test(refcount)) - return 1; - spin_unlock(lock); - return 0; - } - } while (cmpxchg(&refcount->counter, old, new) != old); - return 0; -} - -EXPORT_SYMBOL(_atomic_dec_and_lock); 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 3e2cfa2c6d3..1d8c8886006 100644 --- a/arch/ia64/lib/flush.S +++ b/arch/ia64/lib/flush.S @@ -20,6 +20,7 @@ * * Note: "in0" and "in1" are preserved for debugging purposes. */ + .section .kprobes.text,"ax" GLOBAL_ENTRY(flush_icache_range) .prologue @@ -59,3 +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 6f308e62c13..ab0f8763972 100644 --- a/arch/ia64/lib/memcpy_mck.S +++ b/arch/ia64/lib/memcpy_mck.S @@ -6,12 +6,13 @@ * in1: source address * in2: number of bytes to copy * Output: - * 0 if success, or number of byte NOT copied if error occurred. + * for memcpy: return dest + * for copy_user: return 0 if success, + * or number of byte NOT copied if error occurred. * * 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> @@ -73,6 +74,7 @@ GLOBAL_ENTRY(memcpy) and r28=0x7,in0 and r29=0x7,in1 mov f6=f0 + mov retval=in0 br.cond.sptk .common_code ;; END(memcpy) @@ -84,7 +86,7 @@ GLOBAL_ENTRY(__copy_user) mov f6=f1 mov saved_in0=in0 // save dest pointer mov saved_in1=in1 // save src pointer - mov saved_in2=in2 // save len + mov retval=r0 // initialize return value ;; .common_code: cmp.gt p15,p0=8,in2 // check for small size @@ -92,7 +94,7 @@ GLOBAL_ENTRY(__copy_user) cmp.ne p14,p0=0,r29 // check src alignment add src0=0,in1 sub r30=8,r28 // for .align_dest - mov retval=r0 // initialize return value + mov saved_in2=in2 // save len ;; add dst0=0,in0 add dst1=1,in0 // dest odd index @@ -625,8 +627,11 @@ EK(.ex_handler, (p17) st8 [dst1]=r39,8); \ clrrrb ;; alloc saved_pfs_stack=ar.pfs,3,3,3,0 + cmp.lt p8,p0=A,r0 sub B = dst0, saved_in0 // how many byte copied so far ;; +(p8) mov A = 0; // A shouldn't be negative, cap it + ;; sub C = A, B sub D = saved_in2, A ;; diff --git a/arch/ia64/lib/swiotlb.c b/arch/ia64/lib/swiotlb.c deleted file mode 100644 index dbc0b3e449c..00000000000 --- a/arch/ia64/lib/swiotlb.c +++ /dev/null @@ -1,657 +0,0 @@ -/* - * Dynamic DMA mapping support. - * - * This implementation is for IA-64 platforms that do not support - * I/O TLBs (aka DMA address translation hardware). - * Copyright (C) 2000 Asit Mallick <Asit.K.Mallick@intel.com> - * Copyright (C) 2000 Goutham Rao <goutham.rao@intel.com> - * Copyright (C) 2000, 2003 Hewlett-Packard Co - * David Mosberger-Tang <davidm@hpl.hp.com> - * - * 03/05/07 davidm Switch from PCI-DMA to generic device DMA API. - * 00/12/13 davidm Rename to swiotlb.c and add mark_clean() to avoid - * unnecessary i-cache flushing. - * 04/07/.. ak Better overflow handling. Assorted fixes. - */ - -#include <linux/cache.h> -#include <linux/mm.h> -#include <linux/module.h> -#include <linux/pci.h> -#include <linux/spinlock.h> -#include <linux/string.h> -#include <linux/types.h> -#include <linux/ctype.h> - -#include <asm/io.h> -#include <asm/pci.h> -#include <asm/dma.h> - -#include <linux/init.h> -#include <linux/bootmem.h> - -#define OFFSET(val,align) ((unsigned long) \ - ( (val) & ( (align) - 1))) - -#define SG_ENT_VIRT_ADDRESS(sg) (page_address((sg)->page) + (sg)->offset) -#define SG_ENT_PHYS_ADDRESS(SG) virt_to_phys(SG_ENT_VIRT_ADDRESS(SG)) - -/* - * Maximum allowable number of contiguous slabs to map, - * must be a power of 2. What is the appropriate value ? - * The complexity of {map,unmap}_single is linearly dependent on this value. - */ -#define IO_TLB_SEGSIZE 128 - -/* - * log of the size of each IO TLB slab. The number of slabs is command line - * controllable. - */ -#define IO_TLB_SHIFT 11 - -int swiotlb_force; - -/* - * Used to do a quick range check in swiotlb_unmap_single and - * swiotlb_sync_single_*, to see if the memory was in fact allocated by this - * API. - */ -static char *io_tlb_start, *io_tlb_end; - -/* - * The number of IO TLB blocks (in groups of 64) betweeen io_tlb_start and - * io_tlb_end. This is command line adjustable via setup_io_tlb_npages. - */ -static unsigned long io_tlb_nslabs; - -/* - * When the IOMMU overflows we return a fallback buffer. This sets the size. - */ -static unsigned long io_tlb_overflow = 32*1024; - -void *io_tlb_overflow_buffer; - -/* - * This is a free list describing the number of free entries available from - * each index - */ -static unsigned int *io_tlb_list; -static unsigned int io_tlb_index; - -/* - * We need to save away the original address corresponding to a mapped entry - * for the sync operations. - */ -static unsigned char **io_tlb_orig_addr; - -/* - * Protect the above data structures in the map and unmap calls - */ -static DEFINE_SPINLOCK(io_tlb_lock); - -static int __init -setup_io_tlb_npages(char *str) -{ - if (isdigit(*str)) { - io_tlb_nslabs = simple_strtoul(str, &str, 0); - /* avoid tail segment of size < IO_TLB_SEGSIZE */ - io_tlb_nslabs = ALIGN(io_tlb_nslabs, IO_TLB_SEGSIZE); - } - if (*str == ',') - ++str; - if (!strcmp(str, "force")) - swiotlb_force = 1; - return 1; -} -__setup("swiotlb=", setup_io_tlb_npages); -/* make io_tlb_overflow tunable too? */ - -/* - * Statically reserve bounce buffer space and initialize bounce buffer data - * structures for the software IO TLB used to implement the PCI DMA API. - */ -void -swiotlb_init_with_default_size (size_t default_size) -{ - unsigned long i; - - if (!io_tlb_nslabs) { - io_tlb_nslabs = (default_size >> IO_TLB_SHIFT); - io_tlb_nslabs = ALIGN(io_tlb_nslabs, IO_TLB_SEGSIZE); - } - - /* - * Get IO TLB memory from the low pages - */ - io_tlb_start = alloc_bootmem_low_pages(io_tlb_nslabs * - (1 << IO_TLB_SHIFT)); - if (!io_tlb_start) - panic("Cannot allocate SWIOTLB buffer"); - io_tlb_end = io_tlb_start + io_tlb_nslabs * (1 << IO_TLB_SHIFT); - - /* - * Allocate and initialize the free list array. This array is used - * to find contiguous free memory regions of size up to IO_TLB_SEGSIZE - * between io_tlb_start and io_tlb_end. - */ - io_tlb_list = alloc_bootmem(io_tlb_nslabs * sizeof(int)); - for (i = 0; i < io_tlb_nslabs; i++) - io_tlb_list[i] = IO_TLB_SEGSIZE - OFFSET(i, IO_TLB_SEGSIZE); - io_tlb_index = 0; - io_tlb_orig_addr = alloc_bootmem(io_tlb_nslabs * sizeof(char *)); - - /* - * Get the overflow emergency buffer - */ - io_tlb_overflow_buffer = alloc_bootmem_low(io_tlb_overflow); - printk(KERN_INFO "Placing software IO TLB between 0x%lx - 0x%lx\n", - virt_to_phys(io_tlb_start), virt_to_phys(io_tlb_end)); -} - -void -swiotlb_init (void) -{ - swiotlb_init_with_default_size(64 * (1<<20)); /* default to 64MB */ -} - -static inline int -address_needs_mapping(struct device *hwdev, dma_addr_t addr) -{ - dma_addr_t mask = 0xffffffff; - /* If the device has a mask, use it, otherwise default to 32 bits */ - if (hwdev && hwdev->dma_mask) - mask = *hwdev->dma_mask; - return (addr & ~mask) != 0; -} - -/* - * Allocates bounce buffer and returns its kernel virtual address. - */ -static void * -map_single(struct device *hwdev, char *buffer, size_t size, int dir) -{ - unsigned long flags; - char *dma_addr; - unsigned int nslots, stride, index, wrap; - int i; - - /* - * For mappings greater than a page, we limit the stride (and - * hence alignment) to a page size. - */ - nslots = ALIGN(size, 1 << IO_TLB_SHIFT) >> IO_TLB_SHIFT; - if (size > PAGE_SIZE) - stride = (1 << (PAGE_SHIFT - IO_TLB_SHIFT)); - else - stride = 1; - - if (!nslots) - BUG(); - - /* - * Find suitable number of IO TLB entries size that will fit this - * request and allocate a buffer from that IO TLB pool. - */ - spin_lock_irqsave(&io_tlb_lock, flags); - { - wrap = index = ALIGN(io_tlb_index, stride); - - if (index >= io_tlb_nslabs) - wrap = index = 0; - - do { - /* - * If we find a slot that indicates we have 'nslots' - * number of contiguous buffers, we allocate the - * buffers from that slot and mark the entries as '0' - * indicating unavailable. - */ - if (io_tlb_list[index] >= nslots) { - int count = 0; - - for (i = index; i < (int) (index + nslots); i++) - io_tlb_list[i] = 0; - for (i = index - 1; (OFFSET(i, IO_TLB_SEGSIZE) != IO_TLB_SEGSIZE -1) && io_tlb_list[i]; i--) - io_tlb_list[i] = ++count; - dma_addr = io_tlb_start + (index << IO_TLB_SHIFT); - - /* - * Update the indices to avoid searching in - * the next round. - */ - io_tlb_index = ((index + nslots) < io_tlb_nslabs - ? (index + nslots) : 0); - - goto found; - } - index += stride; - if (index >= io_tlb_nslabs) - index = 0; - } while (index != wrap); - - spin_unlock_irqrestore(&io_tlb_lock, flags); - return NULL; - } - found: - spin_unlock_irqrestore(&io_tlb_lock, flags); - - /* - * Save away the mapping from the original address to the DMA address. - * This is needed when we sync the memory. Then we sync the buffer if - * needed. - */ - io_tlb_orig_addr[index] = buffer; - if (dir == DMA_TO_DEVICE || dir == DMA_BIDIRECTIONAL) - memcpy(dma_addr, buffer, size); - - return dma_addr; -} - -/* - * dma_addr is the kernel virtual address of the bounce buffer to unmap. - */ -static void -unmap_single(struct device *hwdev, char *dma_addr, size_t size, int dir) -{ - unsigned long flags; - int i, count, nslots = ALIGN(size, 1 << IO_TLB_SHIFT) >> IO_TLB_SHIFT; - int index = (dma_addr - io_tlb_start) >> IO_TLB_SHIFT; - char *buffer = io_tlb_orig_addr[index]; - - /* - * First, sync the memory before unmapping the entry - */ - if (buffer && ((dir == DMA_FROM_DEVICE) || (dir == DMA_BIDIRECTIONAL))) - /* - * bounce... copy the data back into the original buffer * and - * delete the bounce buffer. - */ - memcpy(buffer, dma_addr, size); - - /* - * Return the buffer to the free list by setting the corresponding - * entries to indicate the number of contigous entries available. - * While returning the entries to the free list, we merge the entries - * with slots below and above the pool being returned. - */ - spin_lock_irqsave(&io_tlb_lock, flags); - { - count = ((index + nslots) < ALIGN(index + 1, IO_TLB_SEGSIZE) ? - io_tlb_list[index + nslots] : 0); - /* - * Step 1: return the slots to the free list, merging the - * slots with superceeding slots - */ - for (i = index + nslots - 1; i >= index; i--) - io_tlb_list[i] = ++count; - /* - * Step 2: merge the returned slots with the preceding slots, - * if available (non zero) - */ - for (i = index - 1; (OFFSET(i, IO_TLB_SEGSIZE) != IO_TLB_SEGSIZE -1) && io_tlb_list[i]; i--) - io_tlb_list[i] = ++count; - } - spin_unlock_irqrestore(&io_tlb_lock, flags); -} - -static void -sync_single(struct device *hwdev, char *dma_addr, size_t size, int dir) -{ - int index = (dma_addr - io_tlb_start) >> IO_TLB_SHIFT; - char *buffer = io_tlb_orig_addr[index]; - - /* - * bounce... copy the data back into/from the original buffer - * XXX How do you handle DMA_BIDIRECTIONAL here ? - */ - if (dir == DMA_FROM_DEVICE) - memcpy(buffer, dma_addr, size); - else if (dir == DMA_TO_DEVICE) - memcpy(dma_addr, buffer, size); - else - BUG(); -} - -void * -swiotlb_alloc_coherent(struct device *hwdev, size_t size, - dma_addr_t *dma_handle, int flags) -{ - unsigned long dev_addr; - void *ret; - int order = get_order(size); - - /* - * XXX fix me: the DMA API should pass us an explicit DMA mask - * instead, or use ZONE_DMA32 (ia64 overloads ZONE_DMA to be a ~32 - * bit range instead of a 16MB one). - */ - flags |= GFP_DMA; - - ret = (void *)__get_free_pages(flags, order); - if (ret && address_needs_mapping(hwdev, virt_to_phys(ret))) { - /* - * The allocated memory isn't reachable by the device. - * Fall back on swiotlb_map_single(). - */ - free_pages((unsigned long) ret, order); - ret = NULL; - } - if (!ret) { - /* - * We are either out of memory or the device can't DMA - * to GFP_DMA memory; fall back on - * swiotlb_map_single(), which will grab memory from - * the lowest available address range. - */ - dma_addr_t handle; - handle = swiotlb_map_single(NULL, NULL, size, DMA_FROM_DEVICE); - if (dma_mapping_error(handle)) - return NULL; - - ret = phys_to_virt(handle); - } - - memset(ret, 0, size); - dev_addr = virt_to_phys(ret); - - /* Confirm address can be DMA'd by device */ - if (address_needs_mapping(hwdev, dev_addr)) { - printk("hwdev DMA mask = 0x%016Lx, dev_addr = 0x%016lx\n", - (unsigned long long)*hwdev->dma_mask, dev_addr); - panic("swiotlb_alloc_coherent: allocated memory is out of " - "range for device"); - } - *dma_handle = dev_addr; - return ret; -} - -void -swiotlb_free_coherent(struct device *hwdev, size_t size, void *vaddr, - dma_addr_t dma_handle) -{ - if (!(vaddr >= (void *)io_tlb_start - && vaddr < (void *)io_tlb_end)) - free_pages((unsigned long) vaddr, get_order(size)); - else - /* DMA_TO_DEVICE to avoid memcpy in unmap_single */ - swiotlb_unmap_single (hwdev, dma_handle, size, DMA_TO_DEVICE); -} - -static void -swiotlb_full(struct device *dev, size_t size, int dir, int do_panic) -{ - /* - * Ran out of IOMMU space for this operation. This is very bad. - * Unfortunately the drivers cannot handle this operation properly. - * unless they check for pci_dma_mapping_error (most don't) - * When the mapping is small enough return a static buffer to limit - * the damage, or panic when the transfer is too big. - */ - printk(KERN_ERR "PCI-DMA: Out of SW-IOMMU space for %lu bytes at " - "device %s\n", size, dev ? dev->bus_id : "?"); - - if (size > io_tlb_overflow && do_panic) { - if (dir == PCI_DMA_FROMDEVICE || dir == PCI_DMA_BIDIRECTIONAL) - panic("PCI-DMA: Memory would be corrupted\n"); - if (dir == PCI_DMA_TODEVICE || dir == PCI_DMA_BIDIRECTIONAL) - panic("PCI-DMA: Random memory would be DMAed\n"); - } -} - -/* - * Map a single buffer of the indicated size for DMA in streaming mode. The - * PCI address to use is returned. - * - * Once the device is given the dma address, the device owns this memory until - * either swiotlb_unmap_single or swiotlb_dma_sync_single is performed. - */ -dma_addr_t -swiotlb_map_single(struct device *hwdev, void *ptr, size_t size, int dir) -{ - unsigned long dev_addr = virt_to_phys(ptr); - void *map; - - if (dir == DMA_NONE) - BUG(); - /* - * If the pointer passed in happens to be in the device's DMA window, - * we can safely return the device addr and not worry about bounce - * buffering it. - */ - if (!address_needs_mapping(hwdev, dev_addr) && !swiotlb_force) - return dev_addr; - - /* - * Oh well, have to allocate and map a bounce buffer. - */ - map = map_single(hwdev, ptr, size, dir); - if (!map) { - swiotlb_full(hwdev, size, dir, 1); - map = io_tlb_overflow_buffer; - } - - dev_addr = virt_to_phys(map); - - /* - * Ensure that the address returned is DMA'ble - */ - if (address_needs_mapping(hwdev, dev_addr)) - panic("map_single: bounce buffer is not DMA'ble"); - - return dev_addr; -} - -/* - * Since DMA is i-cache coherent, any (complete) pages that were written via - * DMA can be marked as "clean" so that lazy_mmu_prot_update() doesn't have to - * flush them when they get mapped into an executable vm-area. - */ -static void -mark_clean(void *addr, size_t size) -{ - unsigned long pg_addr, end; - - pg_addr = PAGE_ALIGN((unsigned long) addr); - end = (unsigned long) addr + size; - while (pg_addr + PAGE_SIZE <= end) { - struct page *page = virt_to_page(pg_addr); - set_bit(PG_arch_1, &page->flags); - pg_addr += PAGE_SIZE; - } -} - -/* - * Unmap a single streaming mode DMA translation. The dma_addr and size must - * match what was provided for in a previous swiotlb_map_single call. All - * other usages are undefined. - * - * After this call, reads by the cpu to the buffer are guaranteed to see - * whatever the device wrote there. - */ -void -swiotlb_unmap_single(struct device *hwdev, dma_addr_t dev_addr, size_t size, - int dir) -{ - char *dma_addr = phys_to_virt(dev_addr); - - if (dir == DMA_NONE) - BUG(); - if (dma_addr >= io_tlb_start && dma_addr < io_tlb_end) - unmap_single(hwdev, dma_addr, size, dir); - else if (dir == DMA_FROM_DEVICE) - mark_clean(dma_addr, size); -} - -/* - * Make physical memory consistent for a single streaming mode DMA translation - * after a transfer. - * - * If you perform a swiotlb_map_single() but wish to interrogate the buffer - * using the cpu, yet do not wish to teardown the PCI dma mapping, you must - * call this function before doing so. At the next point you give the PCI dma - * address back to the card, you must first perform a - * swiotlb_dma_sync_for_device, and then the device again owns the buffer - */ -void -swiotlb_sync_single_for_cpu(struct device *hwdev, dma_addr_t dev_addr, - size_t size, int dir) -{ - char *dma_addr = phys_to_virt(dev_addr); - - if (dir == DMA_NONE) - BUG(); - if (dma_addr >= io_tlb_start && dma_addr < io_tlb_end) - sync_single(hwdev, dma_addr, size, dir); - else if (dir == DMA_FROM_DEVICE) - mark_clean(dma_addr, size); -} - -void -swiotlb_sync_single_for_device(struct device *hwdev, dma_addr_t dev_addr, - size_t size, int dir) -{ - char *dma_addr = phys_to_virt(dev_addr); - - if (dir == DMA_NONE) - BUG(); - if (dma_addr >= io_tlb_start && dma_addr < io_tlb_end) - sync_single(hwdev, dma_addr, size, dir); - else if (dir == DMA_FROM_DEVICE) - mark_clean(dma_addr, size); -} - -/* - * Map a set of buffers described by scatterlist in streaming mode for DMA. - * This is the scatter-gather version of the above swiotlb_map_single - * interface. Here the scatter gather list elements are each tagged with the - * appropriate dma address and length. They are obtained via - * sg_dma_{address,length}(SG). - * - * NOTE: An implementation may be able to use a smaller number of - * DMA address/length pairs than there are SG table elements. - * (for example via virtual mapping capabilities) - * The routine returns the number of addr/length pairs actually - * used, at most nents. - * - * Device ownership issues as mentioned above for swiotlb_map_single are the - * same here. - */ -int -swiotlb_map_sg(struct device *hwdev, struct scatterlist *sg, int nelems, - int dir) -{ - void *addr; - unsigned long dev_addr; - int i; - - if (dir == DMA_NONE) - BUG(); - - for (i = 0; i < nelems; i++, sg++) { - addr = SG_ENT_VIRT_ADDRESS(sg); - dev_addr = virt_to_phys(addr); - if (swiotlb_force || address_needs_mapping(hwdev, dev_addr)) { - sg->dma_address = (dma_addr_t) virt_to_phys(map_single(hwdev, addr, sg->length, dir)); - if (!sg->dma_address) { - /* Don't panic here, we expect map_sg users - to do proper error handling. */ - swiotlb_full(hwdev, sg->length, dir, 0); - swiotlb_unmap_sg(hwdev, sg - i, i, dir); - sg[0].dma_length = 0; - return 0; - } - } else - sg->dma_address = dev_addr; - sg->dma_length = sg->length; - } - return nelems; -} - -/* - * Unmap a set of streaming mode DMA translations. Again, cpu read rules - * concerning calls here are the same as for swiotlb_unmap_single() above. - */ -void -swiotlb_unmap_sg(struct device *hwdev, struct scatterlist *sg, int nelems, - int dir) -{ - int i; - - if (dir == DMA_NONE) - BUG(); - - for (i = 0; i < nelems; i++, sg++) - if (sg->dma_address != SG_ENT_PHYS_ADDRESS(sg)) - unmap_single(hwdev, (void *) phys_to_virt(sg->dma_address), sg->dma_length, dir); - else if (dir == DMA_FROM_DEVICE) - mark_clean(SG_ENT_VIRT_ADDRESS(sg), sg->dma_length); -} - -/* - * Make physical memory consistent for a set of streaming mode DMA translations - * after a transfer. - * - * The same as swiotlb_sync_single_* but for a scatter-gather list, same rules - * and usage. - */ -void -swiotlb_sync_sg_for_cpu(struct device *hwdev, struct scatterlist *sg, - int nelems, int dir) -{ - int i; - - if (dir == DMA_NONE) - BUG(); - - for (i = 0; i < nelems; i++, sg++) - if (sg->dma_address != SG_ENT_PHYS_ADDRESS(sg)) - sync_single(hwdev, (void *) sg->dma_address, - sg->dma_length, dir); -} - -void -swiotlb_sync_sg_for_device(struct device *hwdev, struct scatterlist *sg, - int nelems, int dir) -{ - int i; - - if (dir == DMA_NONE) - BUG(); - - for (i = 0; i < nelems; i++, sg++) - if (sg->dma_address != SG_ENT_PHYS_ADDRESS(sg)) - sync_single(hwdev, (void *) sg->dma_address, - sg->dma_length, dir); -} - -int -swiotlb_dma_mapping_error(dma_addr_t dma_addr) -{ - return (dma_addr == virt_to_phys(io_tlb_overflow_buffer)); -} - -/* - * Return whether the given PCI device DMA address mask can be supported - * properly. For example, if your device can only drive the low 24-bits - * during PCI bus mastering, then you would pass 0x00ffffff as the mask to - * this function. - */ -int -swiotlb_dma_supported (struct device *hwdev, u64 mask) -{ - return (virt_to_phys (io_tlb_end) - 1) <= mask; -} - -EXPORT_SYMBOL(swiotlb_init); -EXPORT_SYMBOL(swiotlb_map_single); -EXPORT_SYMBOL(swiotlb_unmap_single); -EXPORT_SYMBOL(swiotlb_map_sg); -EXPORT_SYMBOL(swiotlb_unmap_sg); -EXPORT_SYMBOL(swiotlb_sync_single_for_cpu); -EXPORT_SYMBOL(swiotlb_sync_single_for_device); -EXPORT_SYMBOL(swiotlb_sync_sg_for_cpu); -EXPORT_SYMBOL(swiotlb_sync_sg_for_device); -EXPORT_SYMBOL(swiotlb_dma_mapping_error); -EXPORT_SYMBOL(swiotlb_alloc_coherent); -EXPORT_SYMBOL(swiotlb_free_coherent); -EXPORT_SYMBOL(swiotlb_dma_supported); |