diff options
| author | Linus Torvalds <torvalds@ppc970.osdl.org> | 2005-04-16 15:20:36 -0700 |
|---|---|---|
| committer | Linus Torvalds <torvalds@ppc970.osdl.org> | 2005-04-16 15:20:36 -0700 |
| commit | 1da177e4c3f41524e886b7f1b8a0c1fc7321cac2 (patch) | |
| tree | 0bba044c4ce775e45a88a51686b5d9f90697ea9d /lib | |
Linux-2.6.12-rc2v2.6.12-rc2
Initial git repository build. I'm not bothering with the full history,
even though we have it. We can create a separate "historical" git
archive of that later if we want to, and in the meantime it's about
3.2GB when imported into git - space that would just make the early
git days unnecessarily complicated, when we don't have a lot of good
infrastructure for it.
Let it rip!
Diffstat (limited to 'lib')
60 files changed, 15017 insertions, 0 deletions
diff --git a/lib/Kconfig b/lib/Kconfig new file mode 100644 index 00000000000..eeb45225248 --- /dev/null +++ b/lib/Kconfig @@ -0,0 +1,61 @@ +# +# Library configuration +# + +menu "Library routines" + +config CRC_CCITT + tristate "CRC-CCITT functions" + help + This option is provided for the case where no in-kernel-tree + modules require CRC-CCITT functions, but a module built outside + the kernel tree does. Such modules that use library CRC-CCITT + functions require M here. + +config CRC32 + tristate "CRC32 functions" + default y + help + This option is provided for the case where no in-kernel-tree + modules require CRC32 functions, but a module built outside the + kernel tree does. Such modules that use library CRC32 functions + require M here. + +config LIBCRC32C + tristate "CRC32c (Castagnoli, et al) Cyclic Redundancy-Check" + help + This option is provided for the case where no in-kernel-tree + modules require CRC32c functions, but a module built outside the + kernel tree does. Such modules that use library CRC32c functions + require M here. See Castagnoli93. + Module will be libcrc32c. + +# +# compression support is select'ed if needed +# +config ZLIB_INFLATE + tristate + +config ZLIB_DEFLATE + tristate + +# +# reed solomon support is select'ed if needed +# +config REED_SOLOMON + tristate + +config REED_SOLOMON_ENC8 + boolean + +config REED_SOLOMON_DEC8 + boolean + +config REED_SOLOMON_ENC16 + boolean + +config REED_SOLOMON_DEC16 + boolean + +endmenu + diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug new file mode 100644 index 00000000000..426a0cf7b11 --- /dev/null +++ b/lib/Kconfig.debug @@ -0,0 +1,159 @@ + +config PRINTK_TIME + bool "Show timing information on printks" + help + Selecting this option causes timing information to be + included in printk output. This allows you to measure + the interval between kernel operations, including bootup + operations. This is useful for identifying long delays + in kernel startup. + + +config DEBUG_KERNEL + bool "Kernel debugging" + help + Say Y here if you are developing drivers or trying to debug and + identify kernel problems. + +config MAGIC_SYSRQ + bool "Magic SysRq key" + depends on DEBUG_KERNEL && !UML + help + If you say Y here, you will have some control over the system even + if the system crashes for example during kernel debugging (e.g., you + will be able to flush the buffer cache to disk, reboot the system + immediately or dump some status information). This is accomplished + by pressing various keys while holding SysRq (Alt+PrintScreen). It + also works on a serial console (on PC hardware at least), if you + send a BREAK and then within 5 seconds a command keypress. The + keys are documented in <file:Documentation/sysrq.txt>. Don't say Y + unless you really know what this hack does. + +config LOG_BUF_SHIFT + int "Kernel log buffer size (16 => 64KB, 17 => 128KB)" if DEBUG_KERNEL + range 12 21 + default 17 if ARCH_S390 + default 16 if X86_NUMAQ || IA64 + default 15 if SMP + default 14 + help + Select kernel log buffer size as a power of 2. + Defaults and Examples: + 17 => 128 KB for S/390 + 16 => 64 KB for x86 NUMAQ or IA-64 + 15 => 32 KB for SMP + 14 => 16 KB for uniprocessor + 13 => 8 KB + 12 => 4 KB + +config SCHEDSTATS + bool "Collect scheduler statistics" + depends on DEBUG_KERNEL && PROC_FS + help + If you say Y here, additional code will be inserted into the + scheduler and related routines to collect statistics about + scheduler behavior and provide them in /proc/schedstat. These + stats may be useful for both tuning and debugging the scheduler + If you aren't debugging the scheduler or trying to tune a specific + application, you can say N to avoid the very slight overhead + this adds. + +config DEBUG_SLAB + bool "Debug memory allocations" + depends on DEBUG_KERNEL + help + Say Y here to have the kernel do limited verification on memory + allocation as well as poisoning memory on free to catch use of freed + memory. This can make kmalloc/kfree-intensive workloads much slower. + +config DEBUG_PREEMPT + bool "Debug preemptible kernel" + depends on DEBUG_KERNEL && PREEMPT + default y + help + If you say Y here then the kernel will use a debug variant of the + commonly used smp_processor_id() function and will print warnings + if kernel code uses it in a preemption-unsafe way. Also, the kernel + will detect preemption count underflows. + +config DEBUG_SPINLOCK + bool "Spinlock debugging" + depends on DEBUG_KERNEL + help + Say Y here and build SMP to catch missing spinlock initialization + and certain other kinds of spinlock errors commonly made. This is + best used in conjunction with the NMI watchdog so that spinlock + deadlocks are also debuggable. + +config DEBUG_SPINLOCK_SLEEP + bool "Sleep-inside-spinlock checking" + depends on DEBUG_KERNEL + help + If you say Y here, various routines which may sleep will become very + noisy if they are called with a spinlock held. + +config DEBUG_KOBJECT + bool "kobject debugging" + depends on DEBUG_KERNEL + help + If you say Y here, some extra kobject debugging messages will be sent + to the syslog. + +config DEBUG_HIGHMEM + bool "Highmem debugging" + depends on DEBUG_KERNEL && HIGHMEM + help + This options enables addition error checking for high memory systems. + Disable for production systems. + +config DEBUG_BUGVERBOSE + bool "Verbose BUG() reporting (adds 70K)" if DEBUG_KERNEL && EMBEDDED + depends on ARM || ARM26 || M32R || M68K || SPARC32 || SPARC64 || (X86 && !X86_64) || FRV + default !EMBEDDED + help + Say Y here to make BUG() panics output the file name and line number + of the BUG call as well as the EIP and oops trace. This aids + debugging but costs about 70-100K of memory. + +config DEBUG_INFO + bool "Compile the kernel with debug info" + depends on DEBUG_KERNEL + help + If you say Y here the resulting kernel image will include + debugging info resulting in a larger kernel image. + Say Y here only if you plan to debug the kernel. + + If unsure, say N. + +config DEBUG_IOREMAP + bool "Enable ioremap() debugging" + depends on DEBUG_KERNEL && PARISC + help + Enabling this option will cause the kernel to distinguish between + ioremapped and physical addresses. It will print a backtrace (at + most one every 10 seconds), hopefully allowing you to see which + drivers need work. Fixing all these problems is a prerequisite + for turning on USE_HPPA_IOREMAP. The warnings are harmless; + the kernel has enough information to fix the broken drivers + automatically, but we'd like to make it more efficient by not + having to do that. + +config DEBUG_FS + bool "Debug Filesystem" + depends on DEBUG_KERNEL + help + debugfs is a virtual file system that kernel developers use to put + debugging files into. Enable this option to be able to read and + write to these files. + + If unsure, say N. + +config FRAME_POINTER + bool "Compile the kernel with frame pointers" + depends on DEBUG_KERNEL && ((X86 && !X86_64) || CRIS || M68K || M68KNOMMU || FRV) + help + If you say Y here the resulting kernel image will be slightly larger + and slower, but it will give very useful debugging information. + If you don't debug the kernel, you can say N, but we may not be able + to solve problems without frame pointers. + diff --git a/lib/Makefile b/lib/Makefile new file mode 100644 index 00000000000..7c70db79c0e --- /dev/null +++ b/lib/Makefile @@ -0,0 +1,45 @@ +# +# Makefile for some libs needed in the kernel. +# + +lib-y := errno.o ctype.o string.o vsprintf.o cmdline.o \ + bust_spinlocks.o rbtree.o radix-tree.o dump_stack.o \ + kobject.o kref.o idr.o div64.o int_sqrt.o \ + bitmap.o extable.o kobject_uevent.o prio_tree.o sha1.o \ + halfmd4.o + +obj-y += sort.o parser.o + +ifeq ($(CONFIG_DEBUG_KOBJECT),y) +CFLAGS_kobject.o += -DDEBUG +CFLAGS_kobject_uevent.o += -DDEBUG +endif + +lib-$(CONFIG_RWSEM_GENERIC_SPINLOCK) += rwsem-spinlock.o +lib-$(CONFIG_RWSEM_XCHGADD_ALGORITHM) += rwsem.o +lib-$(CONFIG_GENERIC_FIND_NEXT_BIT) += find_next_bit.o +obj-$(CONFIG_LOCK_KERNEL) += kernel_lock.o + +ifneq ($(CONFIG_HAVE_DEC_LOCK),y) + lib-y += dec_and_lock.o +endif + +obj-$(CONFIG_CRC_CCITT) += crc-ccitt.o +obj-$(CONFIG_CRC32) += crc32.o +obj-$(CONFIG_LIBCRC32C) += libcrc32c.o +obj-$(CONFIG_GENERIC_IOMAP) += iomap.o + +obj-$(CONFIG_ZLIB_INFLATE) += zlib_inflate/ +obj-$(CONFIG_ZLIB_DEFLATE) += zlib_deflate/ +obj-$(CONFIG_REED_SOLOMON) += reed_solomon/ + +hostprogs-y := gen_crc32table +clean-files := crc32table.h + +$(obj)/crc32.o: $(obj)/crc32table.h + +quiet_cmd_crc32 = GEN $@ + cmd_crc32 = $< > $@ + +$(obj)/crc32table.h: $(obj)/gen_crc32table + $(call cmd,crc32) diff --git a/lib/bitmap.c b/lib/bitmap.c new file mode 100644 index 00000000000..d1388a5ce89 --- /dev/null +++ b/lib/bitmap.c @@ -0,0 +1,595 @@ +/* + * lib/bitmap.c + * Helper functions for bitmap.h. + * + * This source code is licensed under the GNU General Public License, + * Version 2. See the file COPYING for more details. + */ +#include <linux/module.h> +#include <linux/ctype.h> +#include <linux/errno.h> +#include <linux/bitmap.h> +#include <linux/bitops.h> +#include <asm/uaccess.h> + +/* + * bitmaps provide an array of bits, implemented using an an + * array of unsigned longs. The number of valid bits in a + * given bitmap does _not_ need to be an exact multiple of + * BITS_PER_LONG. + * + * The possible unused bits in the last, partially used word + * of a bitmap are 'don't care'. The implementation makes + * no particular effort to keep them zero. It ensures that + * their value will not affect the results of any operation. + * The bitmap operations that return Boolean (bitmap_empty, + * for example) or scalar (bitmap_weight, for example) results + * carefully filter out these unused bits from impacting their + * results. + * + * These operations actually hold to a slightly stronger rule: + * if you don't input any bitmaps to these ops that have some + * unused bits set, then they won't output any set unused bits + * in output bitmaps. + * + * The byte ordering of bitmaps is more natural on little + * endian architectures. See the big-endian headers + * include/asm-ppc64/bitops.h and include/asm-s390/bitops.h + * for the best explanations of this ordering. + */ + +int __bitmap_empty(const unsigned long *bitmap, int bits) +{ + int k, lim = bits/BITS_PER_LONG; + for (k = 0; k < lim; ++k) + if (bitmap[k]) + return 0; + + if (bits % BITS_PER_LONG) + if (bitmap[k] & BITMAP_LAST_WORD_MASK(bits)) + return 0; + + return 1; +} +EXPORT_SYMBOL(__bitmap_empty); + +int __bitmap_full(const unsigned long *bitmap, int bits) +{ + int k, lim = bits/BITS_PER_LONG; + for (k = 0; k < lim; ++k) + if (~bitmap[k]) + return 0; + + if (bits % BITS_PER_LONG) + if (~bitmap[k] & BITMAP_LAST_WORD_MASK(bits)) + return 0; + + return 1; +} +EXPORT_SYMBOL(__bitmap_full); + +int __bitmap_equal(const unsigned long *bitmap1, + const unsigned long *bitmap2, int bits) +{ + int k, lim = bits/BITS_PER_LONG; + for (k = 0; k < lim; ++k) + if (bitmap1[k] != bitmap2[k]) + return 0; + + if (bits % BITS_PER_LONG) + if ((bitmap1[k] ^ bitmap2[k]) & BITMAP_LAST_WORD_MASK(bits)) + return 0; + + return 1; +} +EXPORT_SYMBOL(__bitmap_equal); + +void __bitmap_complement(unsigned long *dst, const unsigned long *src, int bits) +{ + int k, lim = bits/BITS_PER_LONG; + for (k = 0; k < lim; ++k) + dst[k] = ~src[k]; + + if (bits % BITS_PER_LONG) + dst[k] = ~src[k] & BITMAP_LAST_WORD_MASK(bits); +} +EXPORT_SYMBOL(__bitmap_complement); + +/* + * __bitmap_shift_right - logical right shift of the bits in a bitmap + * @dst - destination bitmap + * @src - source bitmap + * @nbits - shift by this many bits + * @bits - bitmap size, in bits + * + * Shifting right (dividing) means moving bits in the MS -> LS bit + * direction. Zeros are fed into the vacated MS positions and the + * LS bits shifted off the bottom are lost. + */ +void __bitmap_shift_right(unsigned long *dst, + const unsigned long *src, int shift, int bits) +{ + int k, lim = BITS_TO_LONGS(bits), left = bits % BITS_PER_LONG; + int off = shift/BITS_PER_LONG, rem = shift % BITS_PER_LONG; + unsigned long mask = (1UL << left) - 1; + for (k = 0; off + k < lim; ++k) { + unsigned long upper, lower; + + /* + * If shift is not word aligned, take lower rem bits of + * word above and make them the top rem bits of result. + */ + if (!rem || off + k + 1 >= lim) + upper = 0; + else { + upper = src[off + k + 1]; + if (off + k + 1 == lim - 1 && left) + upper &= mask; + } + lower = src[off + k]; + if (left && off + k == lim - 1) + lower &= mask; + dst[k] = upper << (BITS_PER_LONG - rem) | lower >> rem; + if (left && k == lim - 1) + dst[k] &= mask; + } + if (off) + memset(&dst[lim - off], 0, off*sizeof(unsigned long)); +} +EXPORT_SYMBOL(__bitmap_shift_right); + + +/* + * __bitmap_shift_left - logical left shift of the bits in a bitmap + * @dst - destination bitmap + * @src - source bitmap + * @nbits - shift by this many bits + * @bits - bitmap size, in bits + * + * Shifting left (multiplying) means moving bits in the LS -> MS + * direction. Zeros are fed into the vacated LS bit positions + * and those MS bits shifted off the top are lost. + */ + +void __bitmap_shift_left(unsigned long *dst, + const unsigned long *src, int shift, int bits) +{ + int k, lim = BITS_TO_LONGS(bits), left = bits % BITS_PER_LONG; + int off = shift/BITS_PER_LONG, rem = shift % BITS_PER_LONG; + for (k = lim - off - 1; k >= 0; --k) { + unsigned long upper, lower; + + /* + * If shift is not word aligned, take upper rem bits of + * word below and make them the bottom rem bits of result. + */ + if (rem && k > 0) + lower = src[k - 1]; + else + lower = 0; + upper = src[k]; + if (left && k == lim - 1) + upper &= (1UL << left) - 1; + dst[k + off] = lower >> (BITS_PER_LONG - rem) | upper << rem; + if (left && k + off == lim - 1) + dst[k + off] &= (1UL << left) - 1; + } + if (off) + memset(dst, 0, off*sizeof(unsigned long)); +} +EXPORT_SYMBOL(__bitmap_shift_left); + +void __bitmap_and(unsigned long *dst, const unsigned long *bitmap1, + const unsigned long *bitmap2, int bits) +{ + int k; + int nr = BITS_TO_LONGS(bits); + + for (k = 0; k < nr; k++) + dst[k] = bitmap1[k] & bitmap2[k]; +} +EXPORT_SYMBOL(__bitmap_and); + +void __bitmap_or(unsigned long *dst, const unsigned long *bitmap1, + const unsigned long *bitmap2, int bits) +{ + int k; + int nr = BITS_TO_LONGS(bits); + + for (k = 0; k < nr; k++) + dst[k] = bitmap1[k] | bitmap2[k]; +} +EXPORT_SYMBOL(__bitmap_or); + +void __bitmap_xor(unsigned long *dst, const unsigned long *bitmap1, + const unsigned long *bitmap2, int bits) +{ + int k; + int nr = BITS_TO_LONGS(bits); + + for (k = 0; k < nr; k++) + dst[k] = bitmap1[k] ^ bitmap2[k]; +} +EXPORT_SYMBOL(__bitmap_xor); + +void __bitmap_andnot(unsigned long *dst, const unsigned long *bitmap1, + const unsigned long *bitmap2, int bits) +{ + int k; + int nr = BITS_TO_LONGS(bits); + + for (k = 0; k < nr; k++) + dst[k] = bitmap1[k] & ~bitmap2[k]; +} +EXPORT_SYMBOL(__bitmap_andnot); + +int __bitmap_intersects(const unsigned long *bitmap1, + const unsigned long *bitmap2, int bits) +{ + int k, lim = bits/BITS_PER_LONG; + for (k = 0; k < lim; ++k) + if (bitmap1[k] & bitmap2[k]) + return 1; + + if (bits % BITS_PER_LONG) + if ((bitmap1[k] & bitmap2[k]) & BITMAP_LAST_WORD_MASK(bits)) + return 1; + return 0; +} +EXPORT_SYMBOL(__bitmap_intersects); + +int __bitmap_subset(const unsigned long *bitmap1, + const unsigned long *bitmap2, int bits) +{ + int k, lim = bits/BITS_PER_LONG; + for (k = 0; k < lim; ++k) + if (bitmap1[k] & ~bitmap2[k]) + return 0; + + if (bits % BITS_PER_LONG) + if ((bitmap1[k] & ~bitmap2[k]) & BITMAP_LAST_WORD_MASK(bits)) + return 0; + return 1; +} +EXPORT_SYMBOL(__bitmap_subset); + +#if BITS_PER_LONG == 32 +int __bitmap_weight(const unsigned long *bitmap, int bits) +{ + int k, w = 0, lim = bits/BITS_PER_LONG; + + for (k = 0; k < lim; k++) + w += hweight32(bitmap[k]); + + if (bits % BITS_PER_LONG) + w += hweight32(bitmap[k] & BITMAP_LAST_WORD_MASK(bits)); + + return w; +} +#else +int __bitmap_weight(const unsigned long *bitmap, int bits) +{ + int k, w = 0, lim = bits/BITS_PER_LONG; + + for (k = 0; k < lim; k++) + w += hweight64(bitmap[k]); + + if (bits % BITS_PER_LONG) + w += hweight64(bitmap[k] & BITMAP_LAST_WORD_MASK(bits)); + + return w; +} +#endif +EXPORT_SYMBOL(__bitmap_weight); + +/* + * Bitmap printing & parsing functions: first version by Bill Irwin, + * second version by Paul Jackson, third by Joe Korty. + */ + +#define CHUNKSZ 32 +#define nbits_to_hold_value(val) fls(val) +#define roundup_power2(val,modulus) (((val) + (modulus) - 1) & ~((modulus) - 1)) +#define unhex(c) (isdigit(c) ? (c - '0') : (toupper(c) - 'A' + 10)) +#define BASEDEC 10 /* fancier cpuset lists input in decimal */ + +/** + * bitmap_scnprintf - convert bitmap to an ASCII hex string. + * @buf: byte buffer into which string is placed + * @buflen: reserved size of @buf, in bytes + * @maskp: pointer to bitmap to convert + * @nmaskbits: size of bitmap, in bits + * + * Exactly @nmaskbits bits are displayed. Hex digits are grouped into + * comma-separated sets of eight digits per set. + */ +int bitmap_scnprintf(char *buf, unsigned int buflen, + const unsigned long *maskp, int nmaskbits) +{ + int i, word, bit, len = 0; + unsigned long val; + const char *sep = ""; + int chunksz; + u32 chunkmask; + + chunksz = nmaskbits & (CHUNKSZ - 1); + if (chunksz == 0) + chunksz = CHUNKSZ; + + i = roundup_power2(nmaskbits, CHUNKSZ) - CHUNKSZ; + for (; i >= 0; i -= CHUNKSZ) { + chunkmask = ((1ULL << chunksz) - 1); + word = i / BITS_PER_LONG; + bit = i % BITS_PER_LONG; + val = (maskp[word] >> bit) & chunkmask; + len += scnprintf(buf+len, buflen-len, "%s%0*lx", sep, + (chunksz+3)/4, val); + chunksz = CHUNKSZ; + sep = ","; + } + return len; +} +EXPORT_SYMBOL(bitmap_scnprintf); + +/** + * bitmap_parse - convert an ASCII hex string into a bitmap. + * @buf: pointer to buffer in user space containing string. + * @buflen: buffer size in bytes. If string is smaller than this + * then it must be terminated with a \0. + * @maskp: pointer to bitmap array that will contain result. + * @nmaskbits: size of bitmap, in bits. + * + * Commas group hex digits into chunks. Each chunk defines exactly 32 + * bits of the resultant bitmask. No chunk may specify a value larger + * than 32 bits (-EOVERFLOW), and if a chunk specifies a smaller value + * then leading 0-bits are prepended. -EINVAL is returned for illegal + * characters and for grouping errors such as "1,,5", ",44", "," and "". + * Leading and trailing whitespace accepted, but not embedded whitespace. + */ +int bitmap_parse(const char __user *ubuf, unsigned int ubuflen, + unsigned long *maskp, int nmaskbits) +{ + int c, old_c, totaldigits, ndigits, nchunks, nbits; + u32 chunk; + + bitmap_zero(maskp, nmaskbits); + + nchunks = nbits = totaldigits = c = 0; + do { + chunk = ndigits = 0; + + /* Get the next chunk of the bitmap */ + while (ubuflen) { + old_c = c; + if (get_user(c, ubuf++)) + return -EFAULT; + ubuflen--; + if (isspace(c)) + continue; + + /* + * If the last character was a space and the current + * character isn't '\0', we've got embedded whitespace. + * This is a no-no, so throw an error. + */ + if (totaldigits && c && isspace(old_c)) + return -EINVAL; + + /* A '\0' or a ',' signal the end of the chunk */ + if (c == '\0' || c == ',') + break; + + if (!isxdigit(c)) + return -EINVAL; + + /* + * Make sure there are at least 4 free bits in 'chunk'. + * If not, this hexdigit will overflow 'chunk', so + * throw an error. + */ + if (chunk & ~((1UL << (CHUNKSZ - 4)) - 1)) + return -EOVERFLOW; + + chunk = (chunk << 4) | unhex(c); + ndigits++; totaldigits++; + } + if (ndigits == 0) + return -EINVAL; + if (nchunks == 0 && chunk == 0) + continue; + + __bitmap_shift_left(maskp, maskp, CHUNKSZ, nmaskbits); + *maskp |= chunk; + nchunks++; + nbits += (nchunks == 1) ? nbits_to_hold_value(chunk) : CHUNKSZ; + if (nbits > nmaskbits) + return -EOVERFLOW; + } while (ubuflen && c == ','); + + return 0; +} +EXPORT_SYMBOL(bitmap_parse); + +/* + * bscnl_emit(buf, buflen, rbot, rtop, bp) + * + * Helper routine for bitmap_scnlistprintf(). Write decimal number + * or range to buf, suppressing output past buf+buflen, with optional + * comma-prefix. Return len of what would be written to buf, if it + * all fit. + */ +static inline int bscnl_emit(char *buf, int buflen, int rbot, int rtop, int len) +{ + if (len > 0) + len += scnprintf(buf + len, buflen - len, ","); + if (rbot == rtop) + len += scnprintf(buf + len, buflen - len, "%d", rbot); + else + len += scnprintf(buf + len, buflen - len, "%d-%d", rbot, rtop); + return len; +} + +/** + * bitmap_scnlistprintf - convert bitmap to list format ASCII string + * @buf: byte buffer into which string is placed + * @buflen: reserved size of @buf, in bytes + * @maskp: pointer to bitmap to convert + * @nmaskbits: size of bitmap, in bits + * + * Output format is a comma-separated list of decimal numbers and + * ranges. Consecutively set bits are shown as two hyphen-separated + * decimal numbers, the smallest and largest bit numbers set in + * the range. Output format is compatible with the format + * accepted as input by bitmap_parselist(). + * + * The return value is the number of characters which would be + * generated for the given input, excluding the trailing '\0', as + * per ISO C99. + */ +int bitmap_scnlistprintf(char *buf, unsigned int buflen, + const unsigned long *maskp, int nmaskbits) +{ + int len = 0; + /* current bit is 'cur', most recently seen range is [rbot, rtop] */ + int cur, rbot, rtop; + + rbot = cur = find_first_bit(maskp, nmaskbits); + while (cur < nmaskbits) { + rtop = cur; + cur = find_next_bit(maskp, nmaskbits, cur+1); + if (cur >= nmaskbits || cur > rtop + 1) { + len = bscnl_emit(buf, buflen, rbot, rtop, len); + rbot = cur; + } + } + return len; +} +EXPORT_SYMBOL(bitmap_scnlistprintf); + +/** + * bitmap_parselist - convert list format ASCII string to bitmap + * @buf: read nul-terminated user string from this buffer + * @mask: write resulting mask here + * @nmaskbits: number of bits in mask to be written + * + * Input format is a comma-separated list of decimal numbers and + * ranges. Consecutively set bits are shown as two hyphen-separated + * decimal numbers, the smallest and largest bit numbers set in + * the range. + * + * Returns 0 on success, -errno on invalid input strings: + * -EINVAL: second number in range smaller than first + * -EINVAL: invalid character in string + * -ERANGE: bit number specified too large for mask + */ +int bitmap_parselist(const char *bp, unsigned long *maskp, int nmaskbits) +{ + unsigned a, b; + + bitmap_zero(maskp, nmaskbits); + do { + if (!isdigit(*bp)) + return -EINVAL; + b = a = simple_strtoul(bp, (char **)&bp, BASEDEC); + if (*bp == '-') { + bp++; + if (!isdigit(*bp)) + return -EINVAL; + b = simple_strtoul(bp, (char **)&bp, BASEDEC); + } + if (!(a <= b)) + return -EINVAL; + if (b >= nmaskbits) + return -ERANGE; + while (a <= b) { + set_bit(a, maskp); + a++; + } + if (*bp == ',') + bp++; + } while (*bp != '\0' && *bp != '\n'); + return 0; +} +EXPORT_SYMBOL(bitmap_parselist); + +/** + * bitmap_find_free_region - find a contiguous aligned mem region + * @bitmap: an array of unsigned longs corresponding to the bitmap + * @bits: number of bits in the bitmap + * @order: region size to find (size is actually 1<<order) + * + * This is used to allocate a memory region from a bitmap. The idea is + * that the region has to be 1<<order sized and 1<<order aligned (this + * makes the search algorithm much faster). + * + * The region is marked as set bits in the bitmap if a free one is + * found. + * + * Returns either beginning of region or negative error + */ +int bitmap_find_free_region(unsigned long *bitmap, int bits, int order) +{ + unsigned long mask; + int pages = 1 << order; + int i; + + if(pages > BITS_PER_LONG) + return -EINVAL; + + /* make a mask of the order */ + mask = (1ul << (pages - 1)); + mask += mask - 1; + + /* run up the bitmap pages bits at a time */ + for (i = 0; i < bits; i += pages) { + int index = i/BITS_PER_LONG; + int offset = i - (index * BITS_PER_LONG); + if((bitmap[index] & (mask << offset)) == 0) { + /* set region in bimap */ + bitmap[index] |= (mask << offset); + return i; + } + } + return -ENOMEM; +} +EXPORT_SYMBOL(bitmap_find_free_region); + +/** + * bitmap_release_region - release allocated bitmap region + * @bitmap: a pointer to the bitmap + * @pos: the beginning of the region + * @order: the order of the bits to release (number is 1<<order) + * + * This is the complement to __bitmap_find_free_region and releases + * the found region (by clearing it in the bitmap). + */ +void bitmap_release_region(unsigned long *bitmap, int pos, int order) +{ + int pages = 1 << order; + unsigned long mask = (1ul << (pages - 1)); + int index = pos/BITS_PER_LONG; + int offset = pos - (index * BITS_PER_LONG); + mask += mask - 1; + bitmap[index] &= ~(mask << offset); +} +EXPORT_SYMBOL(bitmap_release_region); + +int bitmap_allocate_region(unsigned long *bitmap, int pos, int order) +{ + int pages = 1 << order; + unsigned long mask = (1ul << (pages - 1)); + int index = pos/BITS_PER_LONG; + int offset = pos - (index * BITS_PER_LONG); + + /* We don't do regions of pages > BITS_PER_LONG. The + * algorithm would be a simple look for multiple zeros in the + * array, but there's no driver today that needs this. If you + * trip this BUG(), you get to code it... */ + BUG_ON(pages > BITS_PER_LONG); + mask += mask - 1; + if (bitmap[index] & (mask << offset)) + return -EBUSY; + bitmap[index] |= (mask << offset); + return 0; +} +EXPORT_SYMBOL(bitmap_allocate_region); diff --git a/lib/bust_spinlocks.c b/lib/bust_spinlocks.c new file mode 100644 index 00000000000..6bb7319e09a --- /dev/null +++ b/lib/bust_spinlocks.c @@ -0,0 +1,39 @@ +/* + * lib/bust_spinlocks.c + * + * Provides a minimal bust_spinlocks for architectures which don't have one of their own. + * + * bust_spinlocks() clears any spinlocks which would prevent oops, die(), BUG() + * and panic() information from reaching the user. + */ + +#include <linux/config.h> +#include <linux/kernel.h> +#include <linux/spinlock.h> +#include <linux/tty.h> +#include <linux/wait.h> +#include <linux/vt_kern.h> + + +void bust_spinlocks(int yes) +{ + if (yes) { + oops_in_progress = 1; + } else { + int loglevel_save = console_loglevel; +#ifdef CONFIG_VT + unblank_screen(); +#endif + oops_in_progress = 0; + /* + * OK, the message is on the console. Now we call printk() + * without oops_in_progress set so that printk() will give klogd + * and the blanked console a poke. Hold onto your hats... + */ + console_loglevel = 15; /* NMI oopser may have shut the console up */ + printk(" "); + console_loglevel = loglevel_save; + } +} + + diff --git a/lib/cmdline.c b/lib/cmdline.c new file mode 100644 index 00000000000..0331ed825ea --- /dev/null +++ b/lib/cmdline.c @@ -0,0 +1,120 @@ +/* + * linux/lib/cmdline.c + * Helper functions generally used for parsing kernel command line + * and module options. + * + * Code and copyrights come from init/main.c and arch/i386/kernel/setup.c. + * + * This source code is licensed under the GNU General Public License, + * Version 2. See the file COPYING for more details. + * + * GNU Indent formatting options for this file: -kr -i8 -npsl -pcs + * + */ + +#include <linux/module.h> +#include <linux/kernel.h> +#include <linux/string.h> + + +/** + * get_option - Parse integer from an option string + * @str: option string + * @pint: (output) integer value parsed from @str + * + * Read an int from an option string; if available accept a subsequent + * comma as well. + * + * Return values: + * 0 : no int in string + * 1 : int found, no subsequent comma + * 2 : int found including a subsequent comma + */ + +int get_option (char **str, int *pint) +{ + char *cur = *str; + + if (!cur || !(*cur)) + return 0; + *pint = simple_strtol (cur, str, 0); + if (cur == *str) + return 0; + if (**str == ',') { + (*str)++; + return 2; + } + + return 1; +} + +/** + * get_options - Parse a string into a list of integers + * @str: String to be parsed + * @nints: size of integer array + * @ints: integer array + * + * This function parses a string containing a comma-separated + * list of integers. The parse halts when the array is + * full, or when no more numbers can be retrieved from the + * string. + * + * Return value is the character in the string which caused + * the parse to end (typically a null terminator, if @str is + * completely parseable). + */ + +char *get_options(const char *str, int nints, int *ints) +{ + int res, i = 1; + + while (i < nints) { + res = get_option ((char **)&str, ints + i); + if (res == 0) + break; + i++; + if (res == 1) + break; + } + ints[0] = i - 1; + return (char *)str; +} + +/** + * memparse - parse a string with mem suffixes into a number + * @ptr: Where parse begins + * @retptr: (output) Pointer to next char after parse completes + * + * Parses a string into a number. The number stored at @ptr is + * potentially suffixed with %K (for kilobytes, or 1024 bytes), + * %M (for megabytes, or 1048576 bytes), or %G (for gigabytes, or + * 1073741824). If the number is suffixed with K, M, or G, then + * the return value is the number multiplied by one kilobyte, one + * megabyte, or one gigabyte, respectively. + */ + +unsigned long long memparse (char *ptr, char **retptr) +{ + unsigned long long ret = simple_strtoull (ptr, retptr, 0); + + switch (**retptr) { + case 'G': + case 'g': + ret <<= 10; + case 'M': + case 'm': + ret <<= 10; + case 'K': + case 'k': + ret <<= 10; + (*retptr)++; + default: + break; + } + return ret; +} + + +EXPORT_SYMBOL(memparse); +EXPORT_SYMBOL(get_option); +EXPORT_SYMBOL(get_options); diff --git a/lib/crc-ccitt.c b/lib/crc-ccitt.c new file mode 100644 index 00000000000..115d149af40 --- /dev/null +++ b/lib/crc-ccitt.c @@ -0,0 +1,69 @@ +/* + * linux/lib/crc-ccitt.c + * + * This source code is licensed under the GNU General Public License, + * Version 2. See the file COPYING for more details. + */ + +#include <linux/types.h> +#include <linux/module.h> +#include <linux/crc-ccitt.h> + +/* + * This mysterious table is just the CRC of each possible byte. It can be + * computed using the standard bit-at-a-time methods. The polynomial can + * be seen in entry 128, 0x8408. This corresponds to x^0 + x^5 + x^12. + * Add the implicit x^16, and you have the standard CRC-CCITT. + */ +u16 const crc_ccitt_table[256] = { + 0x0000, 0x1189, 0x2312, 0x329b, 0x4624, 0x57ad, 0x6536, 0x74bf, + 0x8c48, 0x9dc1, 0xaf5a, 0xbed3, 0xca6c, 0xdbe5, 0xe97e, 0xf8f7, + 0x1081, 0x0108, 0x3393, 0x221a, 0x56a5, 0x472c, 0x75b7, 0x643e, + 0x9cc9, 0x8d40, 0xbfdb, 0xae52, 0xdaed, 0xcb64, 0xf9ff, 0xe876, + 0x2102, 0x308b, 0x0210, 0x1399, 0x6726, 0x76af, 0x4434, 0x55bd, + 0xad4a, 0xbcc3, 0x8e58, 0x9fd1, 0xeb6e, 0xfae7, 0xc87c, 0xd9f5, + 0x3183, 0x200a, 0x1291, 0x0318, 0x77a7, 0x662e, 0x54b5, 0x453c, + 0xbdcb, 0xac42, 0x9ed9, 0x8f50, 0xfbef, 0xea66, 0xd8fd, 0xc974, + 0x4204, 0x538d, 0x6116, 0x709f, 0x0420, 0x15a9, 0x2732, 0x36bb, + 0xce4c, 0xdfc5, 0xed5e, 0xfcd7, 0x8868, 0x99e1, 0xab7a, 0xbaf3, + 0x5285, 0x430c, 0x7197, 0x601e, 0x14a1, 0x0528, 0x37b3, 0x263a, + 0xdecd, 0xcf44, 0xfddf, 0xec56, 0x98e9, 0x8960, 0xbbfb, 0xaa72, + 0x6306, 0x728f, 0x4014, 0x519d, 0x2522, 0x34ab, 0x0630, 0x17b9, + 0xef4e, 0xfec7, 0xcc5c, 0xddd5, 0xa96a, 0xb8e3, 0x8a78, 0x9bf1, + 0x7387, 0x620e, 0x5095, 0x411c, 0x35a3, 0x242a, 0x16b1, 0x0738, + 0xffcf, 0xee46, 0xdcdd, 0xcd54, 0xb9eb, 0xa862, 0x9af9, 0x8b70, + 0x8408, 0x9581, 0xa71a, 0xb693, 0xc22c, 0xd3a5, 0xe13e, 0xf0b7, + 0x0840, 0x19c9, 0x2b52, 0x3adb, 0x4e64, 0x5fed, 0x6d76, 0x7cff, + 0x9489, 0x8500, 0xb79b, 0xa612, 0xd2ad, 0xc324, 0xf1bf, 0xe036, + 0x18c1, 0x0948, 0x3bd3, 0x2a5a, 0x5ee5, 0x4f6c, 0x7df7, 0x6c7e, + 0xa50a, 0xb483, 0x8618, 0x9791, 0xe32e, 0xf2a7, 0xc03c, 0xd1b5, + 0x2942, 0x38cb, 0x0a50, 0x1bd9, 0x6f66, 0x7eef, 0x4c74, 0x5dfd, + 0xb58b, 0xa402, 0x9699, 0x8710, 0xf3af, 0xe226, 0xd0bd, 0xc134, + 0x39c3, 0x284a, 0x1ad1, 0x0b58, 0x7fe7, 0x6e6e, 0x5cf5, 0x4d7c, + 0xc60c, 0xd785, 0xe51e, 0xf497, 0x8028, 0x91a1, 0xa33a, 0xb2b3, + 0x4a44, 0x5bcd, 0x6956, 0x78df, 0x0c60, 0x1de9, 0x2f72, 0x3efb, + 0xd68d, 0xc704, 0xf59f, 0xe416, 0x90a9, 0x8120, 0xb3bb, 0xa232, + 0x5ac5, 0x4b4c, 0x79d7, 0x685e, 0x1ce1, 0x0d68, 0x3ff3, 0x2e7a, + 0xe70e, 0xf687, 0xc41c, 0xd595, 0xa12a, 0xb0a3, 0x8238, 0x93b1, + 0x6b46, 0x7acf, 0x4854, 0x59dd, 0x2d62, 0x3ceb, 0x0e70, 0x1ff9, + 0xf78f, 0xe606, 0xd49d, 0xc514, 0xb1ab, 0xa022, 0x92b9, 0x8330, + 0x7bc7, 0x6a4e, 0x58d5, 0x495c, 0x3de3, 0x2c6a, 0x1ef1, 0x0f78 +}; +EXPORT_SYMBOL(crc_ccitt_table); + +/** + * crc_ccitt - recompute the CRC for the data buffer + * @crc - previous CRC value + * @buffer - data pointer + * @len - number of bytes in the buffer + */ +u16 crc_ccitt(u16 crc, u8 const *buffer, size_t len) +{ + while (len--) + crc = crc_ccitt_byte(crc, *buffer++); + return crc; +} +EXPORT_SYMBOL(crc_ccitt); + +MODULE_DESCRIPTION("CRC-CCITT calculations"); +MODULE_LICENSE("GPL"); diff --git a/lib/crc32.c b/lib/crc32.c new file mode 100644 index 00000000000..58b222783f9 --- /dev/null +++ b/lib/crc32.c @@ -0,0 +1,529 @@ +/* + * Oct 15, 2000 Matt Domsch <Matt_Domsch@dell.com> + * Nicer crc32 functions/docs submitted by linux@horizon.com. Thanks! + * Code was from the public domain, copyright abandoned. Code was + * subsequently included in the kernel, thus was re-licensed under the + * GNU GPL v2. + * + * Oct 12, 2000 Matt Domsch <Matt_Domsch@dell.com> + * Same crc32 function was used in 5 other places in the kernel. + * I made one version, and deleted the others. + * There are various incantations of crc32(). Some use a seed of 0 or ~0. + * Some xor at the end with ~0. The generic crc32() function takes + * seed as an argument, and doesn't xor at the end. Then individual + * users can do whatever they need. + * drivers/net/smc9194.c uses seed ~0, doesn't xor with ~0. + * fs/jffs2 uses seed 0, doesn't xor with ~0. + * fs/partitions/efi.c uses seed ~0, xor's with ~0. + * + * This source code is licensed under the GNU General Public License, + * Version 2. See the file COPYING for more details. + */ + +#include <linux/crc32.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/compiler.h> +#include <linux/types.h> +#include <linux/slab.h> +#include <linux/init.h> +#include <asm/atomic.h> +#include "crc32defs.h" +#if CRC_LE_BITS == 8 +#define tole(x) __constant_cpu_to_le32(x) +#define tobe(x) __constant_cpu_to_be32(x) +#else +#define tole(x) (x) +#define tobe(x) (x) +#endif +#include "crc32table.h" + +MODULE_AUTHOR("Matt Domsch <Matt_Domsch@dell.com>"); +MODULE_DESCRIPTION("Ethernet CRC32 calculations"); +MODULE_LICENSE("GPL"); + +#if CRC_LE_BITS == 1 +/* + * In fact, the table-based code will work in this case, but it can be + * simplified by inlining the table in ?: form. + */ + +/** + * crc32_le() - Calculate bitwise little-endian Ethernet AUTODIN II CRC32 + * @crc - seed value for computation. ~0 for Ethernet, sometimes 0 for + * other uses, or the previous crc32 value if computing incrementally. + * @p - pointer to buffer over which CRC is run + * @len - length of buffer @p + * + */ +u32 __attribute_pure__ crc32_le(u32 crc, unsigned char const *p, size_t len) +{ + int i; + while (len--) { + crc ^= *p++; + for (i = 0; i < 8; i++) + crc = (crc >> 1) ^ ((crc & 1) ? CRCPOLY_LE : 0); + } + return crc; +} +#else /* Table-based approach */ + +/** + * crc32_le() - Calculate bitwise little-endian Ethernet AUTODIN II CRC32 + * @crc - seed value for computation. ~0 for Ethernet, sometimes 0 for + * other uses, or the previous crc32 value if computing incrementally. + * @p - pointer to buffer over which CRC is run + * @len - length of buffer @p + * + */ +u32 __attribute_pure__ crc32_le(u32 crc, unsigned char const *p, size_t len) +{ +# if CRC_LE_BITS == 8 + const u32 *b =(u32 *)p; + const u32 *tab = crc32table_le; + +# ifdef __LITTLE_ENDIAN +# define DO_CRC(x) crc = tab[ (crc ^ (x)) & 255 ] ^ (crc>>8) +# else +# define DO_CRC(x) crc = tab[ ((crc >> 24) ^ (x)) & 255] ^ (crc<<8) +# endif + + crc = __cpu_to_le32(crc); + /* Align it */ + if(unlikely(((long)b)&3 && len)){ + do { + u8 *p = (u8 *)b; + DO_CRC(*p++); + b = (void *)p; + } while ((--len) && ((long)b)&3 ); + } + if(likely(len >= 4)){ + /* load data 32 bits wide, xor data 32 bits wide. */ + size_t save_len = len & 3; + len = len >> 2; + --b; /* use pre increment below(*++b) for speed */ + do { + crc ^= *++b; + DO_CRC(0); + DO_CRC(0); + DO_CRC(0); + DO_CRC(0); + } while (--len); + b++; /* point to next byte(s) */ + len = save_len; + } + /* And the last few bytes */ + if(len){ + do { + u8 *p = (u8 *)b; + DO_CRC(*p++); + b = (void *)p; + } while (--len); + } + + return __le32_to_cpu(crc); +#undef ENDIAN_SHIFT +#undef DO_CRC + +# elif CRC_LE_BITS == 4 + while (len--) { + crc ^= *p++; + crc = (crc >> 4) ^ crc32table_le[crc & 15]; + crc = (crc >> 4) ^ crc32table_le[crc & 15]; + } + return crc; +# elif CRC_LE_BITS == 2 + while (len--) { + crc ^= *p++; + crc = (crc >> 2) ^ crc32table_le[crc & 3]; + crc = (crc >> 2) ^ crc32table_le[crc & 3]; + crc = (crc >> 2) ^ crc32table_le[crc & 3]; + crc = (crc >> 2) ^ crc32table_le[crc & 3]; + } + return crc; +# endif +} +#endif + +#if CRC_BE_BITS == 1 +/* + * In fact, the table-based code will work in this case, but it can be + * simplified by inlining the table in ?: form. + */ + +/** + * crc32_be() - Calculate bitwise big-endian Ethernet AUTODIN II CRC32 + * @crc - seed value for computation. ~0 for Ethernet, sometimes 0 for + * other uses, or the previous crc32 value if computing incrementally. + * @p - pointer to buffer over which CRC is run + * @len - length of buffer @p + * + */ +u32 __attribute_pure__ crc32_be(u32 crc, unsigned char const *p, size_t len) +{ + int i; + while (len--) { + crc ^= *p++ << 24; + for (i = 0; i < 8; i++) + crc = + (crc << 1) ^ ((crc & 0x80000000) ? CRCPOLY_BE : + 0); + } + return crc; +} + +#else /* Table-based approach */ +/** + * crc32_be() - Calculate bitwise big-endian Ethernet AUTODIN II CRC32 + * @crc - seed value for computation. ~0 for Ethernet, sometimes 0 for + * other uses, or the previous crc32 value if computing incrementally. + * @p - pointer to buffer over which CRC is run + * @len - length of buffer @p + * + */ +u32 __attribute_pure__ crc32_be(u32 crc, unsigned char const *p, size_t len) +{ +# if CRC_BE_BITS == 8 + const u32 *b =(u32 *)p; + const u32 *tab = crc32table_be; + +# ifdef __LITTLE_ENDIAN +# define DO_CRC(x) crc = tab[ (crc ^ (x)) & 255 ] ^ (crc>>8) +# else +# define DO_CRC(x) crc = tab[ ((crc >> 24) ^ (x)) & 255] ^ (crc<<8) +# endif + + crc = __cpu_to_be32(crc); + /* Align it */ + if(unlikely(((long)b)&3 && len)){ + do { + u8 *p = (u8 *)b; + DO_CRC(*p++); + b = (u32 *)p; + } while ((--len) && ((long)b)&3 ); + } + if(likely(len >= 4)){ + /* load data 32 bits wide, xor data 32 bits wide. */ + size_t save_len = len & 3; + len = len >> 2; + --b; /* use pre increment below(*++b) for speed */ + do { + crc ^= *++b; + DO_CRC(0); + DO_CRC(0); + DO_CRC(0); + DO_CRC(0); + } while (--len); + b++; /* point to next byte(s) */ + len = save_len; + } + /* And the last few bytes */ + if(len){ + do { + u8 *p = (u8 *)b; + DO_CRC(*p++); + b = (void *)p; + } while (--len); + } + return __be32_to_cpu(crc); +#undef ENDIAN_SHIFT +#undef DO_CRC + +# elif CRC_BE_BITS == 4 + while (len--) { + crc ^= *p++ << 24; + crc = (crc << 4) ^ crc32table_be[crc >> 28]; + crc = (crc << 4) ^ crc32table_be[crc >> 28]; + } + return crc; +# elif CRC_BE_BITS == 2 + while (len--) { + crc ^= *p++ << 24; + crc = (crc << 2) ^ crc32table_be[crc >> 30]; + crc = (crc << 2) ^ crc32table_be[crc >> 30]; + crc = (crc << 2) ^ crc32table_be[crc >> 30]; + crc = (crc << 2) ^ crc32table_be[crc >> 30]; + } + return crc; +# endif +} +#endif + +u32 bitreverse(u32 x) +{ + x = (x >> 16) | (x << 16); + x = (x >> 8 & 0x00ff00ff) | (x << 8 & 0xff00ff00); + x = (x >> 4 & 0x0f0f0f0f) | (x << 4 & 0xf0f0f0f0); + x = (x >> 2 & 0x33333333) | (x << 2 & 0xcccccccc); + x = (x >> 1 & 0x55555555) | (x << 1 & 0xaaaaaaaa); + return x; +} + +EXPORT_SYMBOL(crc32_le); +EXPORT_SYMBOL(crc32_be); +EXPORT_SYMBOL(bitreverse); + +/* + * A brief CRC tutorial. + * + * A CRC is a long-division remainder. You add the CRC to the message, + * and the whole thing (message+CRC) is a multiple of the given + * CRC polynomial. To check the CRC, you can either check that the + * CRC matches the recomputed value, *or* you can check that the + * remainder computed on the message+CRC is 0. This latter approach + * is used by a lot of hardware implementations, and is why so many + * protocols put the end-of-frame flag after the CRC. + * + * It's actually the same long division you learned in school, except that + * - We're working in binary, so the digits are only 0 and 1, and + * - When dividing polynomials, there are no carries. Rather than add and + * subtract, we just xor. Thus, we tend to get a bit sloppy about + * the difference between adding and subtracting. + * + * A 32-bit CRC polynomial is actually 33 bits long. But since it's + * 33 bits long, bit 32 is always going to be set, so usually the CRC + * is written in hex with the most significant bit omitted. (If you're + * familiar with the IEEE 754 floating-point format, it's the same idea.) + * + * Note that a CRC is computed over a string of *bits*, so you have + * to decide on the endianness of the bits within each byte. To get + * the best error-detecting properties, this should correspond to the + * order they're actually sent. For example, standard RS-232 serial is + * little-endian; the most significant bit (sometimes used for parity) + * is sent last. And when appending a CRC word to a message, you should + * do it in the right order, matching the endianness. + * + * Just like with ordinary division, the remainder is always smaller than + * the divisor (the CRC polynomial) you're dividing by. Each step of the + * division, you take one more digit (bit) of the dividend and append it + * to the current remainder. Then you figure out the appropriate multiple + * of the divisor to subtract to being the remainder back into range. + * In binary, it's easy - it has to be either 0 or 1, and to make the + * XOR cancel, it's just a copy of bit 32 of the remainder. + * + * When computing a CRC, we don't care about the quotient, so we can + * throw the quotient bit away, but subtract the appropriate multiple of + * the polynomial from the remainder and we're back to where we started, + * ready to process the next bit. + * + * A big-endian CRC written this way would be coded like: + * for (i = 0; i < input_bits; i++) { + * multiple = remainder & 0x80000000 ? CRCPOLY : 0; + * remainder = (remainder << 1 | next_input_bit()) ^ multiple; + * } + * Notice how, to get at bit 32 of the shifted remainder, we look + * at bit 31 of the remainder *before* shifting it. + * + * But also notice how the next_input_bit() bits we're shifting into + * the remainder don't actually affect any decision-making until + * 32 bits later. Thus, the first 32 cycles of this are pretty boring. + * Also, to add the CRC to a message, we need a 32-bit-long hole for it at + * the end, so we have to add 32 extra cycles shifting in zeros at the + * end of every message, + * + * So the standard trick is to rearrage merging in the next_input_bit() + * until the moment it's needed. Then the first 32 cycles can be precomputed, + * and merging in the final 32 zero bits to make room for the CRC can be + * skipped entirely. + * This changes the code to: + * for (i = 0; i < input_bits; i++) { + * remainder ^= next_input_bit() << 31; + * multiple = (remainder & 0x80000000) ? CRCPOLY : 0; + * remainder = (remainder << 1) ^ multiple; + * } + * With this optimization, the little-endian code is simpler: + * for (i = 0; i < input_bits; i++) { + * remainder ^= next_input_bit(); + * multiple = (remainder & 1) ? CRCPOLY : 0; + * remainder = (remainder >> 1) ^ multiple; + * } + * + * Note that the other details of endianness have been hidden in CRCPOLY + * (which must be bit-reversed) and next_input_bit(). + * + * However, as long as next_input_bit is returning the bits in a sensible + * order, we can actually do the merging 8 or more bits at a time rather + * than one bit at a time: + * for (i = 0; i < input_bytes; i++) { + * remainder ^= next_input_byte() << 24; + * for (j = 0; j < 8; j++) { + * multiple = (remainder & 0x80000000) ? CRCPOLY : 0; + * remainder = (remainder << 1) ^ multiple; + * } + * } + * Or in little-endian: + * for (i = 0; i < input_bytes; i++) { + * remainder ^= next_input_byte(); + * for (j = 0; j < 8; j++) { + * multiple = (remainder & 1) ? CRCPOLY : 0; + * remainder = (remainder << 1) ^ multiple; + * } + * } + * If the input is a multiple of 32 bits, you can even XOR in a 32-bit + * word at a time and increase the inner loop count to 32. + * + * You can also mix and match the two loop styles, for example doing the + * bulk of a message byte-at-a-time and adding bit-at-a-time processing + * for any fractional bytes at the end. + * + * The only remaining optimization is to the byte-at-a-time table method. + * Here, rather than just shifting one bit of the remainder to decide + * in the correct multiple to subtract, we can shift a byte at a time. + * This produces a 40-bit (rather than a 33-bit) intermediate remainder, + * but again the multiple of the polynomial to subtract depends only on + * the high bits, the high 8 bits in this case. + * + * The multile we need in that case is the low 32 bits of a 40-bit + * value whose high 8 bits are given, and which is a multiple of the + * generator polynomial. This is simply the CRC-32 of the given + * one-byte message. + * + * Two more details: normally, appending zero bits to a message which + * is already a multiple of a polynomial produces a larger multiple of that + * polynomial. To enable a CRC to detect this condition, it's common to + * invert the CRC before appending it. This makes the remainder of the + * message+crc come out not as zero, but some fixed non-zero value. + * + * The same problem applies to zero bits prepended to the message, and + * a similar solution is used. Instead of starting with a remainder of + * 0, an initial remainder of all ones is used. As long as you start + * the same way on decoding, it doesn't make a difference. + */ + +#ifdef UNITTEST + +#include <stdlib.h> +#include <stdio.h> + +#if 0 /*Not used at present */ +static void +buf_dump(char const *prefix, unsigned char const *buf, size_t len) +{ + fputs(prefix, stdout); + while (len--) + printf(" %02x", *buf++); + putchar('\n'); + +} +#endif + +static void bytereverse(unsigned char *buf, size_t len) +{ + while (len--) { + unsigned char x = *buf; + x = (x >> 4) | (x << 4); + x = (x >> 2 & 0x33) | (x << 2 & 0xcc); + x = (x >> 1 & 0x55) | (x << 1 & 0xaa); + *buf++ = x; + } +} + +static void random_garbage(unsigned char *buf, size_t len) +{ + while (len--) + *buf++ = (unsigned char) random(); +} + +#if 0 /* Not used at present */ +static void store_le(u32 x, unsigned char *buf) +{ + buf[0] = (unsigned char) x; + buf[1] = (unsigned char) (x >> 8); + buf[2] = (unsigned char) (x >> 16); + buf[3] = (unsigned char) (x >> 24); +} +#endif + +static void store_be(u32 x, unsigned char *buf) +{ + buf[0] = (unsigned char) (x >> 24); + buf[1] = (unsigned char) (x >> 16); + buf[2] = (unsigned char) (x >> 8); + buf[3] = (unsigned char) x; +} + +/* + * This checks that CRC(buf + CRC(buf)) = 0, and that + * CRC commutes with bit-reversal. This has the side effect + * of bytewise bit-reversing the input buffer, and returns + * the CRC of the reversed buffer. + */ +static u32 test_step(u32 init, unsigned char *buf, size_t len) +{ + u32 crc1, crc2; + size_t i; + + crc1 = crc32_be(init, buf, len); + store_be(crc1, buf + len); + crc2 = crc32_be(init, buf, len + 4); + if (crc2) + printf("\nCRC cancellation fail: 0x%08x should be 0\n", + crc2); + + for (i = 0; i <= len + 4; i++) { + crc2 = crc32_be(init, buf, i); + crc2 = crc32_be(crc2, buf + i, len + 4 - i); + if (crc2) + printf("\nCRC split fail: 0x%08x\n", crc2); + } + + /* Now swap it around for the other test */ + + bytereverse(buf, len + 4); + init = bitreverse(init); + crc2 = bitreverse(crc1); + if (crc1 != bitreverse(crc2)) + printf("\nBit reversal fail: 0x%08x -> %0x08x -> 0x%08x\n", + crc1, crc2, bitreverse(crc2)); + crc1 = crc32_le(init, buf, len); + if (crc1 != crc2) + printf("\nCRC endianness fail: 0x%08x != 0x%08x\n", crc1, + crc2); + crc2 = crc32_le(init, buf, len + 4); + if (crc2) + printf("\nCRC cancellation fail: 0x%08x should be 0\n", + crc2); + + for (i = 0; i <= len + 4; i++) { + crc2 = crc32_le(init, buf, i); + crc2 = crc32_le(crc2, buf + i, len + 4 - i); + if (crc2) + printf("\nCRC split fail: 0x%08x\n", crc2); + } + + return crc1; +} + +#define SIZE 64 +#define INIT1 0 +#define INIT2 0 + +int main(void) +{ + unsigned char buf1[SIZE + 4]; + unsigned char buf2[SIZE + 4]; + unsigned char buf3[SIZE + 4]; + int i, j; + u32 crc1, crc2, crc3; + + for (i = 0; i <= SIZE; i++) { + printf("\rTesting length %d...", i); + fflush(stdout); + random_garbage(buf1, i); + random_garbage(buf2, i); + for (j = 0; j < i; j++) + buf3[j] = buf1[j] ^ buf2[j]; + + crc1 = test_step(INIT1, buf1, i); + crc2 = test_step(INIT2, buf2, i); + /* Now check that CRC(buf1 ^ buf2) = CRC(buf1) ^ CRC(buf2) */ + crc3 = test_step(INIT1 ^ INIT2, buf3, i); + if (crc3 != (crc1 ^ crc2)) + printf("CRC XOR fail: 0x%08x != 0x%08x ^ 0x%08x\n", + crc3, crc1, crc2); + } + printf("\nAll test complete. No failures expected.\n"); + return 0; +} + +#endif /* UNITTEST */ diff --git a/lib/crc32defs.h b/lib/crc32defs.h new file mode 100644 index 00000000000..9b6773d7374 --- /dev/null +++ b/lib/crc32defs.h @@ -0,0 +1,32 @@ +/* + * There are multiple 16-bit CRC polynomials in common use, but this is + * *the* standard CRC-32 polynomial, first popularized by Ethernet. + * x^32+x^26+x^23+x^22+x^16+x^12+x^11+x^10+x^8+x^7+x^5+x^4+x^2+x^1+x^0 + */ +#define CRCPOLY_LE 0xedb88320 +#define CRCPOLY_BE 0x04c11db7 + +/* How many bits at a time to use. Requires a table of 4<<CRC_xx_BITS bytes. */ +/* For less performance-sensitive, use 4 */ +#ifndef CRC_LE_BITS +# define CRC_LE_BITS 8 +#endif +#ifndef CRC_BE_BITS +# define CRC_BE_BITS 8 +#endif + +/* + * Little-endian CRC computation. Used with serial bit streams sent + * lsbit-first. Be sure to use cpu_to_le32() to append the computed CRC. + */ +#if CRC_LE_BITS > 8 || CRC_LE_BITS < 1 || CRC_LE_BITS & CRC_LE_BITS-1 +# error CRC_LE_BITS must be a power of 2 between 1 and 8 +#endif + +/* + * Big-endian CRC computation. Used with serial bit streams sent + * msbit-first. Be sure to use cpu_to_be32() to append the computed CRC. + */ +#if CRC_BE_BITS > 8 || CRC_BE_BITS < 1 || CRC_BE_BITS & CRC_BE_BITS-1 +# error CRC_BE_BITS must be a power of 2 between 1 and 8 +#endif diff --git a/lib/ctype.c b/lib/ctype.c new file mode 100644 index 00000000000..d02ace14a32 --- /dev/null +++ b/lib/ctype.c @@ -0,0 +1,36 @@ +/* + * linux/lib/ctype.c + * + * Copyright (C) 1991, 1992 Linus Torvalds + */ + +#include <linux/ctype.h> +#include <linux/module.h> + +unsigned char _ctype[] = { +_C,_C,_C,_C,_C,_C,_C,_C, /* 0-7 */ +_C,_C|_S,_C|_S,_C|_S,_C|_S,_C|_S,_C,_C, /* 8-15 */ +_C,_C,_C,_C,_C,_C,_C,_C, /* 16-23 */ +_C,_C,_C,_C,_C,_C,_C,_C, /* 24-31 */ +_S|_SP,_P,_P,_P,_P,_P,_P,_P, /* 32-39 */ +_P,_P,_P,_P,_P,_P,_P,_P, /* 40-47 */ +_D,_D,_D,_D,_D,_D,_D,_D, /* 48-55 */ +_D,_D,_P,_P,_P,_P,_P,_P, /* 56-63 */ +_P,_U|_X,_U|_X,_U|_X,_U|_X,_U|_X,_U|_X,_U, /* 64-71 */ +_U,_U,_U,_U,_U,_U,_U,_U, /* 72-79 */ +_U,_U,_U,_U,_U,_U,_U,_U, /* 80-87 */ +_U,_U,_U,_P,_P,_P,_P,_P, /* 88-95 */ +_P,_L|_X,_L|_X,_L|_X,_L|_X,_L|_X,_L|_X,_L, /* 96-103 */ +_L,_L,_L,_L,_L,_L,_L,_L, /* 104-111 */ +_L,_L,_L,_L,_L,_L,_L,_L, /* 112-119 */ +_L,_L,_L,_P,_P,_P,_P,_C, /* 120-127 */ +0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, /* 128-143 */ +0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, /* 144-159 */ +_S|_SP,_P,_P,_P,_P,_P,_P,_P,_P,_P,_P,_P,_P,_P,_P,_P, /* 160-175 */ +_P,_P,_P,_P,_P,_P,_P,_P,_P,_P,_P,_P,_P,_P,_P,_P, /* 176-191 */ +_U,_U,_U,_U,_U,_U,_U,_U,_U,_U,_U,_U,_U,_U,_U,_U, /* 192-207 */ +_U,_U,_U,_U,_U,_U,_U,_P,_U,_U,_U,_U,_U,_U,_U,_L, /* 208-223 */ +_L,_L,_L,_L,_L,_L,_L,_L,_L,_L,_L,_L,_L,_L,_L,_L, /* 224-239 */ +_L,_L,_L,_L,_L,_L,_L,_P,_L,_L,_L,_L,_L,_L,_L,_L}; /* 240-255 */ + +EXPORT_SYMBOL(_ctype); diff --git a/lib/dec_and_lock.c b/lib/dec_and_lock.c new file mode 100644 index 00000000000..6658d81e183 --- /dev/null +++ b/lib/dec_and_lock.c @@ -0,0 +1,40 @@ +#include <linux/module.h> +#include <linux/spinlock.h> +#include <asm/atomic.h> + +/* + * This is an architecture-neutral, but slow, + * implementation of the notion of "decrement + * a reference count, and return locked if it + * decremented to zero". + * + * NOTE NOTE NOTE! This is _not_ equivalent to + * + * if (atomic_dec_and_test(&atomic)) { + * spin_lock(&lock); + * return 1; + * } + * return 0; + * + * because the spin-lock and the decrement must be + * "atomic". + * + * This slow version gets the spinlock unconditionally, + * and releases it if it isn't needed. Architectures + * are encouraged to come up with better approaches, + * this is trivially done efficiently using a load-locked + * store-conditional approach, for example. + */ + +#ifndef ATOMIC_DEC_AND_LOCK +int _atomic_dec_and_lock(atomic_t *atomic, spinlock_t *lock) +{ + spin_lock(lock); + if (atomic_dec_and_test(atomic)) + return 1; + spin_unlock(lock); + return 0; +} + +EXPORT_SYMBOL(_atomic_dec_and_lock); +#endif diff --git a/lib/div64.c b/lib/div64.c new file mode 100644 index 00000000000..365719f8483 --- /dev/null +++ b/lib/div64.c @@ -0,0 +1,61 @@ +/* + * Copyright (C) 2003 Bernardo Innocenti <bernie@develer.com> + * + * Based on former do_div() implementation from asm-parisc/div64.h: + * Copyright (C) 1999 Hewlett-Packard Co + * Copyright (C) 1999 David Mosberger-Tang <davidm@hpl.hp.com> + * + * + * Generic C version of 64bit/32bit division and modulo, with + * 64bit result and 32bit remainder. + * + * The fast case for (n>>32 == 0) is handled inline by do_div(). + * + * Code generated for this function might be very inefficient + * for some CPUs. __div64_32() can be overridden by linking arch-specific + * assembly versions such as arch/ppc/lib/div64.S and arch/sh/lib/div64.S. + */ + +#include <linux/types.h> +#include <linux/module.h> +#include <asm/div64.h> + +/* Not needed on 64bit architectures */ +#if BITS_PER_LONG == 32 + +uint32_t __div64_32(uint64_t *n, uint32_t base) +{ + uint64_t rem = *n; + uint64_t b = base; + uint64_t res, d = 1; + uint32_t high = rem >> 32; + + /* Reduce the thing a bit first */ + res = 0; + if (high >= base) { + high /= base; + res = (uint64_t) high << 32; + rem -= (uint64_t) (high*base) << 32; + } + + while ((int64_t)b > 0 && b < rem) { + b = b+b; + d = d+d; + } + + do { + if (rem >= b) { + rem -= b; + res += d; + } + b >>= 1; + d >>= 1; + } while (d); + + *n = res; + return rem; +} + +EXPORT_SYMBOL(__div64_32); + +#endif /* BITS_PER_LONG == 32 */ diff --git a/lib/dump_stack.c b/lib/dump_stack.c new file mode 100644 index 00000000000..53bff4c8452 --- /dev/null +++ b/lib/dump_stack.c @@ -0,0 +1,15 @@ +/* + * Provide a default dump_stack() function for architectures + * which don't implement their own. + */ + +#include <linux/kernel.h> +#include <linux/module.h> + +void dump_stack(void) +{ + printk(KERN_NOTICE + "This architecture does not implement dump_stack()\n"); +} + +EXPORT_SYMBOL(dump_stack); diff --git a/lib/errno.c b/lib/errno.c new file mode 100644 index 00000000000..41cb9d76c05 --- /dev/null +++ b/lib/errno.c @@ -0,0 +1,7 @@ +/* + * linux/lib/errno.c + * + * Copyright (C) 1991, 1992 Linus Torvalds + */ + +int errno; diff --git a/lib/extable.c b/lib/extable.c new file mode 100644 index 00000000000..3f677a8f0c3 --- /dev/null +++ b/lib/extable.c @@ -0,0 +1,79 @@ +/* + * lib/extable.c + * Derived from arch/ppc/mm/extable.c and arch/i386/mm/extable.c. + * + * Copyright (C) 2004 Paul Mackerras, IBM Corp. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#include <linux/config.h> +#include <linux/module.h> +#include <linux/init.h> +#include <linux/sort.h> +#include <asm/uaccess.h> + +extern struct exception_table_entry __start___ex_table[]; +extern struct exception_table_entry __stop___ex_table[]; + +#ifndef ARCH_HAS_SORT_EXTABLE +/* + * The exception table needs to be sorted so that the binary + * search that we use to find entries in it works properly. + * This is used both for the kernel exception table and for + * the exception tables of modules that get loaded. + */ +static int cmp_ex(const void *a, const void *b) +{ + const struct exception_table_entry *x = a, *y = b; + + /* avoid overflow */ + if (x->insn > y->insn) + return 1; + if (x->insn < y->insn) + return -1; + return 0; +} + +void sort_extable(struct exception_table_entry *start, + struct exception_table_entry *finish) +{ + sort(start, finish - start, sizeof(struct exception_table_entry), + cmp_ex, NULL); +} +#endif + +#ifndef ARCH_HAS_SEARCH_EXTABLE +/* + * Search one exception table for an entry corresponding to the + * given instruction address, and return the address of the entry, + * or NULL if none is found. + * We use a binary search, and thus we assume that the table is + * already sorted. + */ +const struct exception_table_entry * +search_extable(const struct exception_table_entry *first, + const struct exception_table_entry *last, + unsigned long value) +{ + while (first <= last) { + const struct exception_table_entry *mid; + + mid = (last - first) / 2 + first; + /* + * careful, the distance between entries can be + * larger than 2GB: + */ + if (mid->insn < value) + first = mid + 1; + else if (mid->insn > value) + last = mid - 1; + else + return mid; + } + return NULL; +} +#endif diff --git a/lib/find_next_bit.c b/lib/find_next_bit.c new file mode 100644 index 00000000000..d08302d2a42 --- /dev/null +++ b/lib/find_next_bit.c @@ -0,0 +1,55 @@ +/* find_next_bit.c: fallback find next bit implementation + * + * Copyright (C) 2004 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#include <linux/bitops.h> + +int find_next_bit(const unsigned long *addr, int size, int offset) +{ + const unsigned long *base; + const int NBITS = sizeof(*addr) * 8; + unsigned long tmp; + + base = addr; + if (offset) { + int suboffset; + + addr += offset / NBITS; + + suboffset = offset % NBITS; + if (suboffset) { + tmp = *addr; + tmp >>= suboffset; + if (tmp) + goto finish; + } + + addr++; + } + + while ((tmp = *addr) == 0) + addr++; + + offset = (addr - base) * NBITS; + + finish: + /* count the remaining bits without using __ffs() since that takes a 32-bit arg */ + while (!(tmp & 0xff)) { + offset += 8; + tmp >>= 8; + } + + while (!(tmp & 1)) { + offset++; + tmp >>= 1; + } + + return offset; +} diff --git a/lib/gen_crc32table.c b/lib/gen_crc32table.c new file mode 100644 index 00000000000..bea5d97df99 --- /dev/null +++ b/lib/gen_crc32table.c @@ -0,0 +1,82 @@ +#include <stdio.h> +#include "crc32defs.h" +#include <inttypes.h> + +#define ENTRIES_PER_LINE 4 + +#define LE_TABLE_SIZE (1 << CRC_LE_BITS) +#define BE_TABLE_SIZE (1 << CRC_BE_BITS) + +static uint32_t crc32table_le[LE_TABLE_SIZE]; +static uint32_t crc32table_be[BE_TABLE_SIZE]; + +/** + * crc32init_le() - allocate and initialize LE table data + * + * crc is the crc of the byte i; other entries are filled in based on the + * fact that crctable[i^j] = crctable[i] ^ crctable[j]. + * + */ +static void crc32init_le(void) +{ + unsigned i, j; + uint32_t crc = 1; + + crc32table_le[0] = 0; + + for (i = 1 << (CRC_LE_BITS - 1); i; i >>= 1) { + crc = (crc >> 1) ^ ((crc & 1) ? CRCPOLY_LE : 0); + for (j = 0; j < LE_TABLE_SIZE; j += 2 * i) + crc32table_le[i + j] = crc ^ crc32table_le[j]; + } +} + +/** + * crc32init_be() - allocate and initialize BE table data + */ +static void crc32init_be(void) +{ + unsigned i, j; + uint32_t crc = 0x80000000; + + crc32table_be[0] = 0; + + for (i = 1; i < BE_TABLE_SIZE; i <<= 1) { + crc = (crc << 1) ^ ((crc & 0x80000000) ? CRCPOLY_BE : 0); + for (j = 0; j < i; j++) + crc32table_be[i + j] = crc ^ crc32table_be[j]; + } +} + +static void output_table(uint32_t table[], int len, char *trans) +{ + int i; + + for (i = 0; i < len - 1; i++) { + if (i % ENTRIES_PER_LINE == 0) + printf("\n"); + printf("%s(0x%8.8xL), ", trans, table[i]); + } + printf("%s(0x%8.8xL)\n", trans, table[len - 1]); +} + +int main(int argc, char** argv) +{ + printf("/* this file is generated - do not edit */\n\n"); + + if (CRC_LE_BITS > 1) { + crc32init_le(); + printf("static const u32 crc32table_le[] = {"); + output_table(crc32table_le, LE_TABLE_SIZE, "tole"); + printf("};\n"); + } + + if (CRC_BE_BITS > 1) { + crc32init_be(); + printf("static const u32 crc32table_be[] = {"); + output_table(crc32table_be, BE_TABLE_SIZE, "tobe"); + printf("};\n"); + } + + return 0; +} diff --git a/lib/halfmd4.c b/lib/halfmd4.c new file mode 100644 index 00000000000..e11db26f8ae --- /dev/null +++ b/lib/halfmd4.c @@ -0,0 +1,66 @@ +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/cryptohash.h> + +/* F, G and H are basic MD4 functions: selection, majority, parity */ +#define F(x, y, z) ((z) ^ ((x) & ((y) ^ (z)))) +#define G(x, y, z) (((x) & (y)) + (((x) ^ (y)) & (z))) +#define H(x, y, z) ((x) ^ (y) ^ (z)) + +/* + * The generic round function. The application is so specific that + * we don't bother protecting all the arguments with parens, as is generally + * good macro practice, in favor of extra legibility. + * Rotation is separate from addition to prevent recomputation + */ +#define ROUND(f, a, b, c, d, x, s) \ + (a += f(b, c, d) + x, a = (a << s) | (a >> (32 - s))) +#define K1 0 +#define K2 013240474631UL +#define K3 015666365641UL + +/* + * Basic cut-down MD4 transform. Returns only 32 bits of result. + */ +__u32 half_md4_transform(__u32 buf[4], __u32 const in[8]) +{ + __u32 a = buf[0], b = buf[1], c = buf[2], d = buf[3]; + + /* Round 1 */ + ROUND(F, a, b, c, d, in[0] + K1, 3); + ROUND(F, d, a, b, c, in[1] + K1, 7); + ROUND(F, c, d, a, b, in[2] + K1, 11); + ROUND(F, b, c, d, a, in[3] + K1, 19); + ROUND(F, a, b, c, d, in[4] + K1, 3); + ROUND(F, d, a, b, c, in[5] + K1, 7); + ROUND(F, c, d, a, b, in[6] + K1, 11); + ROUND(F, b, c, d, a, in[7] + K1, 19); + + /* Round 2 */ + ROUND(G, a, b, c, d, in[1] + K2, 3); + ROUND(G, d, a, b, c, in[3] + K2, 5); + ROUND(G, c, d, a, b, in[5] + K2, 9); + ROUND(G, b, c, d, a, in[7] + K2, 13); + ROUND(G, a, b, c, d, in[0] + K2, 3); + ROUND(G, d, a, b, c, in[2] + K2, 5); + ROUND(G, c, d, a, b, in[4] + K2, 9); + ROUND(G, b, c, d, a, in[6] + K2, 13); + + /* Round 3 */ + ROUND(H, a, b, c, d, in[3] + K3, 3); + ROUND(H, d, a, b, c, in[7] + K3, 9); + ROUND(H, c, d, a, b, in[2] + K3, 11); + ROUND(H, b, c, d, a, in[6] + K3, 15); + ROUND(H, a, b, c, d, in[1] + K3, 3); + ROUND(H, d, a, b, c, in[5] + K3, 9); + ROUND(H, c, d, a, b, in[0] + K3, 11); + ROUND(H, b, c, d, a, in[4] + K3, 15); + + buf[0] += a; + buf[1] += b; + buf[2] += c; + buf[3] += d; + + return buf[1]; /* "most hashed" word */ +} +EXPORT_SYMBOL(half_md4_transform); diff --git a/lib/idr.c b/lib/idr.c new file mode 100644 index 00000000000..81fc430602e --- /dev/null +++ b/lib/idr.c @@ -0,0 +1,408 @@ +/* + * 2002-10-18 written by Jim Houston jim.houston@ccur.com + * Copyright (C) 2002 by Concurrent Computer Corporation + * Distributed under the GNU GPL license version 2. + * + * Modified by George Anzinger to reuse immediately and to use + * find bit instructions. Also removed _irq on spinlocks. + * + * Small id to pointer translation service. + * + * It uses a radix tree like structure as a sparse array indexed + * by the id to obtain the pointer. The bitmap makes allocating + * a new id quick. + * + * You call it to allocate an id (an int) an associate with that id a + * pointer or what ever, we treat it as a (void *). You can pass this + * id to a user for him to pass back at a later time. You then pass + * that id to this code and it returns your pointer. + + * You can release ids at any time. When all ids are released, most of + * the memory is returned (we keep IDR_FREE_MAX) in a local pool so we + * don't need to go to the memory "store" during an id allocate, just + * so you don't need to be too concerned about locking and conflicts + * with the slab allocator. + */ + +#ifndef TEST // to test in user space... +#include <linux/slab.h> +#include <linux/init.h> +#include <linux/module.h> +#endif +#include <linux/string.h> +#include <linux/idr.h> + +static kmem_cache_t *idr_layer_cache; + +static struct idr_layer *alloc_layer(struct idr *idp) +{ + struct idr_layer *p; + + spin_lock(&idp->lock); + if ((p = idp->id_free)) { + idp->id_free = p->ary[0]; + idp->id_free_cnt--; + p->ary[0] = NULL; + } + spin_unlock(&idp->lock); + return(p); +} + +static void free_layer(struct idr *idp, struct idr_layer *p) +{ + /* + * Depends on the return element being zeroed. + */ + spin_lock(&idp->lock); + p->ary[0] = idp->id_free; + idp->id_free = p; + idp->id_free_cnt++; + spin_unlock(&idp->lock); +} + +/** + * idr_pre_get - reserver resources for idr allocation + * @idp: idr handle + * @gfp_mask: memory allocation flags + * + * This function should be called prior to locking and calling the + * following function. It preallocates enough memory to satisfy + * the worst possible allocation. + * + * If the system is REALLY out of memory this function returns 0, + * otherwise 1. + */ +int idr_pre_get(struct idr *idp, unsigned gfp_mask) +{ + while (idp->id_free_cnt < IDR_FREE_MAX) { + struct idr_layer *new; + new = kmem_cache_alloc(idr_layer_cache, gfp_mask); + if(new == NULL) + return (0); + free_layer(idp, new); + } + return 1; +} +EXPORT_SYMBOL(idr_pre_get); + +static int sub_alloc(struct idr *idp, void *ptr, int *starting_id) +{ + int n, m, sh; + struct idr_layer *p, *new; + struct idr_layer *pa[MAX_LEVEL]; + int l, id; + long bm; + + id = *starting_id; + p = idp->top; + l = idp->layers; + pa[l--] = NULL; + while (1) { + /* + * We run around this while until we reach the leaf node... + */ + n = (id >> (IDR_BITS*l)) & IDR_MASK; + bm = ~p->bitmap; + m = find_next_bit(&bm, IDR_SIZE, n); + if (m == IDR_SIZE) { + /* no space available go back to previous layer. */ + l++; + id = (id | ((1 << (IDR_BITS*l))-1)) + 1; + if (!(p = pa[l])) { + *starting_id = id; + return -2; + } + continue; + } + if (m != n) { + sh = IDR_BITS*l; + id = ((id >> sh) ^ n ^ m) << sh; + } + if ((id >= MAX_ID_BIT) || (id < 0)) + return -3; + if (l == 0) + break; + /* + * Create the layer below if it is missing. + */ + if (!p->ary[m]) { + if (!(new = alloc_layer(idp))) + return -1; + p->ary[m] = new; + p->count++; + } + pa[l--] = p; + p = p->ary[m]; + } + /* + * We have reached the leaf node, plant the + * users pointer and return the raw id. + */ + p->ary[m] = (struct idr_layer *)ptr; + __set_bit(m, &p->bitmap); + p->count++; + /* + * If this layer is full mark the bit in the layer above + * to show that this part of the radix tree is full. + * This may complete the layer above and require walking + * up the radix tree. + */ + n = id; + while (p->bitmap == IDR_FULL) { + if (!(p = pa[++l])) + break; + n = n >> IDR_BITS; + __set_bit((n & IDR_MASK), &p->bitmap); + } + return(id); +} + +static int idr_get_new_above_int(struct idr *idp, void *ptr, int starting_id) +{ + struct idr_layer *p, *new; + int layers, v, id; + + id = starting_id; +build_up: + p = idp->top; + layers = idp->layers; + if (unlikely(!p)) { + if (!(p = alloc_layer(idp))) + return -1; + layers = 1; + } + /* + * Add a new layer to the top of the tree if the requested + * id is larger than the currently allocated space. + */ + while ((layers < MAX_LEVEL) && (id >= (1 << (layers*IDR_BITS)))) { + layers++; + if (!p->count) + continue; + if (!(new = alloc_layer(idp))) { + /* + * The allocation failed. If we built part of + * the structure tear it down. + */ + for (new = p; p && p != idp->top; new = p) { + p = p->ary[0]; + new->ary[0] = NULL; + new->bitmap = new->count = 0; + free_layer(idp, new); + } + return -1; + } + new->ary[0] = p; + new->count = 1; + if (p->bitmap == IDR_FULL) + __set_bit(0, &new->bitmap); + p = new; + } + idp->top = p; + idp->layers = layers; + v = sub_alloc(idp, ptr, &id); + if (v == -2) + goto build_up; + return(v); +} + +/** + * idr_get_new_above - allocate new idr entry above a start id + * @idp: idr handle + * @ptr: pointer you want associated with the ide + * @start_id: id to start search at + * @id: pointer to the allocated handle + * + * This is the allocate id function. It should be called with any + * required locks. + * + * If memory is required, it will return -EAGAIN, you should unlock + * and go back to the idr_pre_get() call. If the idr is full, it will + * return -ENOSPC. + * + * @id returns a value in the range 0 ... 0x7fffffff + */ +int idr_get_new_above(struct idr *idp, void *ptr, int starting_id, int *id) +{ + int rv; + rv = idr_get_new_above_int(idp, ptr, starting_id); + /* + * This is a cheap hack until the IDR code can be fixed to + * return proper error values. + */ + if (rv < 0) { + if (rv == -1) + return -EAGAIN; + else /* Will be -3 */ + return -ENOSPC; + } + *id = rv; + return 0; +} +EXPORT_SYMBOL(idr_get_new_above); + +/** + * idr_get_new - allocate new idr entry + * @idp: idr handle + * @ptr: pointer you want associated with the ide + * @id: pointer to the allocated handle + * + * This is the allocate id function. It should be called with any + * required locks. + * + * If memory is required, it will return -EAGAIN, you should unlock + * and go back to the idr_pre_get() call. If the idr is full, it will + * return -ENOSPC. + * + * @id returns a value in the range 0 ... 0x7fffffff + */ +int idr_get_new(struct idr *idp, void *ptr, int *id) +{ + int rv; + rv = idr_get_new_above_int(idp, ptr, 0); + /* + * This is a cheap hack until the IDR code can be fixed to + * return proper error values. + */ + if (rv < 0) { + if (rv == -1) + return -EAGAIN; + else /* Will be -3 */ + return -ENOSPC; + } + *id = rv; + return 0; +} +EXPORT_SYMBOL(idr_get_new); + +static void idr_remove_warning(int id) +{ + printk("idr_remove called for id=%d which is not allocated.\n", id); + dump_stack(); +} + +static void sub_remove(struct idr *idp, int shift, int id) +{ + struct idr_layer *p = idp->top; + struct idr_layer **pa[MAX_LEVEL]; + struct idr_layer ***paa = &pa[0]; + int n; + + *paa = NULL; + *++paa = &idp->top; + + while ((shift > 0) && p) { + n = (id >> shift) & IDR_MASK; + __clear_bit(n, &p->bitmap); + *++paa = &p->ary[n]; + p = p->ary[n]; + shift -= IDR_BITS; + } + n = id & IDR_MASK; + if (likely(p != NULL && test_bit(n, &p->bitmap))){ + __clear_bit(n, &p->bitmap); + p->ary[n] = NULL; + while(*paa && ! --((**paa)->count)){ + free_layer(idp, **paa); + **paa-- = NULL; + } + if ( ! *paa ) + idp->layers = 0; + } else { + idr_remove_warning(id); + } +} + +/** + * idr_remove - remove the given id and free it's slot + * idp: idr handle + * id: uniqueue key + */ +void idr_remove(struct idr *idp, int id) +{ + struct idr_layer *p; + + /* Mask off upper bits we don't use for the search. */ + id &= MAX_ID_MASK; + + sub_remove(idp, (idp->layers - 1) * IDR_BITS, id); + if ( idp->top && idp->top->count == 1 && + (idp->layers > 1) && + idp->top->ary[0]){ // We can drop a layer + + p = idp->top->ary[0]; + idp->top->bitmap = idp->top->count = 0; + free_layer(idp, idp->top); + idp->top = p; + --idp->layers; + } + while (idp->id_free_cnt >= IDR_FREE_MAX) { + + p = alloc_layer(idp); + kmem_cache_free(idr_layer_cache, p); + return; + } +} +EXPORT_SYMBOL(idr_remove); + +/** + * idr_find - return pointer for given id + * @idp: idr handle + * @id: lookup key + * + * Return the pointer given the id it has been registered with. A %NULL + * return indicates that @id is not valid or you passed %NULL in + * idr_get_new(). + * + * The caller must serialize idr_find() vs idr_get_new() and idr_remove(). + */ +void *idr_find(struct idr *idp, int id) +{ + int n; + struct idr_layer *p; + + n = idp->layers * IDR_BITS; + p = idp->top; + + /* Mask off upper bits we don't use for the search. */ + id &= MAX_ID_MASK; + + if (id >= (1 << n)) + return NULL; + + while (n > 0 && p) { + n -= IDR_BITS; + p = p->ary[(id >> n) & IDR_MASK]; + } + return((void *)p); +} +EXPORT_SYMBOL(idr_find); + +static void idr_cache_ctor(void * idr_layer, + kmem_cache_t *idr_layer_cache, unsigned long flags) +{ + memset(idr_layer, 0, sizeof(struct idr_layer)); +} + +static int init_id_cache(void) +{ + if (!idr_layer_cache) + idr_layer_cache = kmem_cache_create("idr_layer_cache", + sizeof(struct idr_layer), 0, 0, idr_cache_ctor, NULL); + return 0; +} + +/** + * idr_init - initialize idr handle + * @idp: idr handle + * + * This function is use to set up the handle (@idp) that you will pass + * to the rest of the functions. + */ +void idr_init(struct idr *idp) +{ + init_id_cache(); + memset(idp, 0, sizeof(struct idr)); + spin_lock_init(&idp->lock); +} +EXPORT_SYMBOL(idr_init); diff --git a/lib/inflate.c b/lib/inflate.c new file mode 100644 index 00000000000..75e7d303c72 --- /dev/null +++ b/lib/inflate.c @@ -0,0 +1,1210 @@ +#define DEBG(x) +#define DEBG1(x) +/* inflate.c -- Not copyrighted 1992 by Mark Adler + version c10p1, 10 January 1993 */ + +/* + * Adapted for booting Linux by Hannu Savolainen 1993 + * based on gzip-1.0.3 + * + * Nicolas Pitre <nico@cam.org>, 1999/04/14 : + * Little mods for all variable to reside either into rodata or bss segments + * by marking constant variables with 'const' and initializing all the others + * at run-time only. This allows for the kernel uncompressor to run + * directly from Flash or ROM memory on embedded systems. + */ + +/* + Inflate deflated (PKZIP's method 8 compressed) data. The compression + method searches for as much of the current string of bytes (up to a + length of 258) in the previous 32 K bytes. If it doesn't find any + matches (of at least length 3), it codes the next byte. Otherwise, it + codes the length of the matched string and its distance backwards from + the current position. There is a single Huffman code that codes both + single bytes (called "literals") and match lengths. A second Huffman + code codes the distance information, which follows a length code. Each + length or distance code actually represents a base value and a number + of "extra" (sometimes zero) bits to get to add to the base value. At + the end of each deflated block is a special end-of-block (EOB) literal/ + length code. The decoding process is basically: get a literal/length + code; if EOB then done; if a literal, emit the decoded byte; if a + length then get the distance and emit the referred-to bytes from the + sliding window of previously emitted data. + + There are (currently) three kinds of inflate blocks: stored, fixed, and + dynamic. The compressor deals with some chunk of data at a time, and + decides which method to use on a chunk-by-chunk basis. A chunk might + typically be 32 K or 64 K. If the chunk is incompressible, then the + "stored" method is used. In this case, the bytes are simply stored as + is, eight bits per byte, with none of the above coding. The bytes are + preceded by a count, since there is no longer an EOB code. + + If the data is compressible, then either the fixed or dynamic methods + are used. In the dynamic method, the compressed data is preceded by + an encoding of the literal/length and distance Huffman codes that are + to be used to decode this block. The representation is itself Huffman + coded, and so is preceded by a description of that code. These code + descriptions take up a little space, and so for small blocks, there is + a predefined set of codes, called the fixed codes. The fixed method is + used if the block codes up smaller that way (usually for quite small + chunks), otherwise the dynamic method is used. In the latter case, the + codes are customized to the probabilities in the current block, and so + can code it much better than the pre-determined fixed codes. + + The Huffman codes themselves are decoded using a multi-level table + lookup, in order to maximize the speed of decoding plus the speed of + building the decoding tables. See the comments below that precede the + lbits and dbits tuning parameters. + */ + + +/* + Notes beyond the 1.93a appnote.txt: + + 1. Distance pointers never point before the beginning of the output + stream. + 2. Distance pointers can point back across blocks, up to 32k away. + 3. There is an implied maximum of 7 bits for the bit length table and + 15 bits for the actual data. + 4. If only one code exists, then it is encoded using one bit. (Zero + would be more efficient, but perhaps a little confusing.) If two + codes exist, they are coded using one bit each (0 and 1). + 5. There is no way of sending zero distance codes--a dummy must be + sent if there are none. (History: a pre 2.0 version of PKZIP would + store blocks with no distance codes, but this was discovered to be + too harsh a criterion.) Valid only for 1.93a. 2.04c does allow + zero distance codes, which is sent as one code of zero bits in + length. + 6. There are up to 286 literal/length codes. Code 256 represents the + end-of-block. Note however that the static length tree defines + 288 codes just to fill out the Huffman codes. Codes 286 and 287 + cannot be used though, since there is no length base or extra bits + defined for them. Similarly, there are up to 30 distance codes. + However, static trees define 32 codes (all 5 bits) to fill out the + Huffman codes, but the last two had better not show up in the data. + 7. Unzip can check dynamic Huffman blocks for complete code sets. + The exception is that a single code would not be complete (see #4). + 8. The five bits following the block type is really the number of + literal codes sent minus 257. + 9. Length codes 8,16,16 are interpreted as 13 length codes of 8 bits + (1+6+6). Therefore, to output three times the length, you output + three codes (1+1+1), whereas to output four times the same length, + you only need two codes (1+3). Hmm. + 10. In the tree reconstruction algorithm, Code = Code + Increment + only if BitLength(i) is not zero. (Pretty obvious.) + 11. Correction: 4 Bits: # of Bit Length codes - 4 (4 - 19) + 12. Note: length code 284 can represent 227-258, but length code 285 + really is 258. The last length deserves its own, short code + since it gets used a lot in very redundant files. The length + 258 is special since 258 - 3 (the min match length) is 255. + 13. The literal/length and distance code bit lengths are read as a + single stream of lengths. It is possible (and advantageous) for + a repeat code (16, 17, or 18) to go across the boundary between + the two sets of lengths. + */ +#include <linux/compiler.h> + +#ifdef RCSID +static char rcsid[] = "#Id: inflate.c,v 0.14 1993/06/10 13:27:04 jloup Exp #"; +#endif + +#ifndef STATIC + +#if defined(STDC_HEADERS) || defined(HAVE_STDLIB_H) +# include <sys/types.h> +# include <stdlib.h> +#endif + +#include "gzip.h" +#define STATIC +#endif /* !STATIC */ + +#ifndef INIT +#define INIT +#endif + +#define slide window + +/* Huffman code lookup table entry--this entry is four bytes for machines + that have 16-bit pointers (e.g. PC's in the small or medium model). + Valid extra bits are 0..13. e == 15 is EOB (end of block), e == 16 + means that v is a literal, 16 < e < 32 means that v is a pointer to + the next table, which codes e - 16 bits, and lastly e == 99 indicates + an unused code. If a code with e == 99 is looked up, this implies an + error in the data. */ +struct huft { + uch e; /* number of extra bits or operation */ + uch b; /* number of bits in this code or subcode */ + union { + ush n; /* literal, length base, or distance base */ + struct huft *t; /* pointer to next level of table */ + } v; +}; + + +/* Function prototypes */ +STATIC int INIT huft_build OF((unsigned *, unsigned, unsigned, + const ush *, const ush *, struct huft **, int *)); +STATIC int INIT huft_free OF((struct huft *)); +STATIC int INIT inflate_codes OF((struct huft *, struct huft *, int, int)); +STATIC int INIT inflate_stored OF((void)); +STATIC int INIT inflate_fixed OF((void)); +STATIC int INIT inflate_dynamic OF((void)); +STATIC int INIT inflate_block OF((int *)); +STATIC int INIT inflate OF((void)); + + +/* The inflate algorithm uses a sliding 32 K byte window on the uncompressed + stream to find repeated byte strings. This is implemented here as a + circular buffer. The index is updated simply by incrementing and then + ANDing with 0x7fff (32K-1). */ +/* It is left to other modules to supply the 32 K area. It is assumed + to be usable as if it were declared "uch slide[32768];" or as just + "uch *slide;" and then malloc'ed in the latter case. The definition + must be in unzip.h, included above. */ +/* unsigned wp; current position in slide */ +#define wp outcnt +#define flush_output(w) (wp=(w),flush_window()) + +/* Tables for deflate from PKZIP's appnote.txt. */ +static const unsigned border[] = { /* Order of the bit length code lengths */ + 16, 17, 18, 0, 8, 7, 9, 6, 10, 5, 11, 4, 12, 3, 13, 2, 14, 1, 15}; +static const ush cplens[] = { /* Copy lengths for literal codes 257..285 */ + 3, 4, 5, 6, 7, 8, 9, 10, 11, 13, 15, 17, 19, 23, 27, 31, + 35, 43, 51, 59, 67, 83, 99, 115, 131, 163, 195, 227, 258, 0, 0}; + /* note: see note #13 above about the 258 in this list. */ +static const ush cplext[] = { /* Extra bits for literal codes 257..285 */ + 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 2, 2, 2, 2, + 3, 3, 3, 3, 4, 4, 4, 4, 5, 5, 5, 5, 0, 99, 99}; /* 99==invalid */ +static const ush cpdist[] = { /* Copy offsets for distance codes 0..29 */ + 1, 2, 3, 4, 5, 7, 9, 13, 17, 25, 33, 49, 65, 97, 129, 193, + 257, 385, 513, 769, 1025, 1537, 2049, 3073, 4097, 6145, + 8193, 12289, 16385, 24577}; +static const ush cpdext[] = { /* Extra bits for distance codes */ + 0, 0, 0, 0, 1, 1, 2, 2, 3, 3, 4, 4, 5, 5, 6, 6, + 7, 7, 8, 8, 9, 9, 10, 10, 11, 11, + 12, 12, 13, 13}; + + + +/* Macros for inflate() bit peeking and grabbing. + The usage is: + + NEEDBITS(j) + x = b & mask_bits[j]; + DUMPBITS(j) + + where NEEDBITS makes sure that b has at least j bits in it, and + DUMPBITS removes the bits from b. The macros use the variable k + for the number of bits in b. Normally, b and k are register + variables for speed, and are initialized at the beginning of a + routine that uses these macros from a global bit buffer and count. + + If we assume that EOB will be the longest code, then we will never + ask for bits with NEEDBITS that are beyond the end of the stream. + So, NEEDBITS should not read any more bytes than are needed to + meet the request. Then no bytes need to be "returned" to the buffer + at the end of the last block. + + However, this assumption is not true for fixed blocks--the EOB code + is 7 bits, but the other literal/length codes can be 8 or 9 bits. + (The EOB code is shorter than other codes because fixed blocks are + generally short. So, while a block always has an EOB, many other + literal/length codes have a significantly lower probability of + showing up at all.) However, by making the first table have a + lookup of seven bits, the EOB code will be found in that first + lookup, and so will not require that too many bits be pulled from + the stream. + */ + +STATIC ulg bb; /* bit buffer */ +STATIC unsigned bk; /* bits in bit buffer */ + +STATIC const ush mask_bits[] = { + 0x0000, + 0x0001, 0x0003, 0x0007, 0x000f, 0x001f, 0x003f, 0x007f, 0x00ff, + 0x01ff, 0x03ff, 0x07ff, 0x0fff, 0x1fff, 0x3fff, 0x7fff, 0xffff +}; + +#define NEXTBYTE() ({ int v = get_byte(); if (v < 0) goto underrun; (uch)v; }) +#define NEEDBITS(n) {while(k<(n)){b|=((ulg)NEXTBYTE())<<k;k+=8;}} +#define DUMPBITS(n) {b>>=(n);k-=(n);} + + +/* + Huffman code decoding is performed using a multi-level table lookup. + The fastest way to decode is to simply build a lookup table whose + size is determined by the longest code. However, the time it takes + to build this table can also be a factor if the data being decoded + is not very long. The most common codes are necessarily the + shortest codes, so those codes dominate the decoding time, and hence + the speed. The idea is you can have a shorter table that decodes the + shorter, more probable codes, and then point to subsidiary tables for + the longer codes. The time it costs to decode the longer codes is + then traded against the time it takes to make longer tables. + + This results of this trade are in the variables lbits and dbits + below. lbits is the number of bits the first level table for literal/ + length codes can decode in one step, and dbits is the same thing for + the distance codes. Subsequent tables are also less than or equal to + those sizes. These values may be adjusted either when all of the + codes are shorter than that, in which case the longest code length in + bits is used, or when the shortest code is *longer* than the requested + table size, in which case the length of the shortest code in bits is + used. + + There are two different values for the two tables, since they code a + different number of possibilities each. The literal/length table + codes 286 possible values, or in a flat code, a little over eight + bits. The distance table codes 30 possible values, or a little less + than five bits, flat. The optimum values for speed end up being + about one bit more than those, so lbits is 8+1 and dbits is 5+1. + The optimum values may differ though from machine to machine, and + possibly even between compilers. Your mileage may vary. + */ + + +STATIC const int lbits = 9; /* bits in base literal/length lookup table */ +STATIC const int dbits = 6; /* bits in base distance lookup table */ + + +/* If BMAX needs to be larger than 16, then h and x[] should be ulg. */ +#define BMAX 16 /* maximum bit length of any code (16 for explode) */ +#define N_MAX 288 /* maximum number of codes in any set */ + + +STATIC unsigned hufts; /* track memory usage */ + + +STATIC int INIT huft_build( + unsigned *b, /* code lengths in bits (all assumed <= BMAX) */ + unsigned n, /* number of codes (assumed <= N_MAX) */ + unsigned s, /* number of simple-valued codes (0..s-1) */ + const ush *d, /* list of base values for non-simple codes */ + const ush *e, /* list of extra bits for non-simple codes */ + struct huft **t, /* result: starting table */ + int *m /* maximum lookup bits, returns actual */ + ) +/* Given a list of code lengths and a maximum table size, make a set of + tables to decode that set of codes. Return zero on success, one if + the given code set is incomplete (the tables are still built in this + case), two if the input is invalid (all zero length codes or an + oversubscribed set of lengths), and three if not enough memory. */ +{ + unsigned a; /* counter for codes of length k */ + unsigned c[BMAX+1]; /* bit length count table */ + unsigned f; /* i repeats in table every f entries */ + int g; /* maximum code length */ + int h; /* table level */ + register unsigned i; /* counter, current code */ + register unsigned j; /* counter */ + register int k; /* number of bits in current code */ + int l; /* bits per table (returned in m) */ + register unsigned *p; /* pointer into c[], b[], or v[] */ + register struct huft *q; /* points to current table */ + struct huft r; /* table entry for structure assignment */ + struct huft *u[BMAX]; /* table stack */ + unsigned v[N_MAX]; /* values in order of bit length */ + register int w; /* bits before this table == (l * h) */ + unsigned x[BMAX+1]; /* bit offsets, then code stack */ + unsigned *xp; /* pointer into x */ + int y; /* number of dummy codes added */ + unsigned z; /* number of entries in current table */ + +DEBG("huft1 "); + + /* Generate counts for each bit length */ + memzero(c, sizeof(c)); + p = b; i = n; + do { + Tracecv(*p, (stderr, (n-i >= ' ' && n-i <= '~' ? "%c %d\n" : "0x%x %d\n"), + n-i, *p)); + c[*p]++; /* assume all entries <= BMAX */ + p++; /* Can't combine with above line (Solaris bug) */ + } while (--i); + if (c[0] == n) /* null input--all zero length codes */ + { + *t = (struct huft *)NULL; + *m = 0; + return 0; + } + +DEBG("huft2 "); + + /* Find minimum and maximum length, bound *m by those */ + l = *m; + for (j = 1; j <= BMAX; j++) + if (c[j]) + break; + k = j; /* minimum code length */ + if ((unsigned)l < j) + l = j; + for (i = BMAX; i; i--) + if (c[i]) + break; + g = i; /* maximum code length */ + if ((unsigned)l > i) + l = i; + *m = l; + +DEBG("huft3 "); + + /* Adjust last length count to fill out codes, if needed */ + for (y = 1 << j; j < i; j++, y <<= 1) + if ((y -= c[j]) < 0) + return 2; /* bad input: more codes than bits */ + if ((y -= c[i]) < 0) + return 2; + c[i] += y; + +DEBG("huft4 "); + + /* Generate starting offsets into the value table for each length */ + x[1] = j = 0; + p = c + 1; xp = x + 2; + while (--i) { /* note that i == g from above */ + *xp++ = (j += *p++); + } + +DEBG("huft5 "); + + /* Make a table of values in order of bit lengths */ + p = b; i = 0; + do { + if ((j = *p++) != 0) + v[x[j]++] = i; + } while (++i < n); + +DEBG("h6 "); + + /* Generate the Huffman codes and for each, make the table entries */ + x[0] = i = 0; /* first Huffman code is zero */ + p = v; /* grab values in bit order */ + h = -1; /* no tables yet--level -1 */ + w = -l; /* bits decoded == (l * h) */ + u[0] = (struct huft *)NULL; /* just to keep compilers happy */ + q = (struct huft *)NULL; /* ditto */ + z = 0; /* ditto */ +DEBG("h6a "); + + /* go through the bit lengths (k already is bits in shortest code) */ + for (; k <= g; k++) + { +DEBG("h6b "); + a = c[k]; + while (a--) + { +DEBG("h6b1 "); + /* here i is the Huffman code of length k bits for value *p */ + /* make tables up to required level */ + while (k > w + l) + { +DEBG1("1 "); + h++; + w += l; /* previous table always l bits */ + + /* compute minimum size table less than or equal to l bits */ + z = (z = g - w) > (unsigned)l ? l : z; /* upper limit on table size */ + if ((f = 1 << (j = k - w)) > a + 1) /* try a k-w bit table */ + { /* too few codes for k-w bit table */ +DEBG1("2 "); + f -= a + 1; /* deduct codes from patterns left */ + xp = c + k; + while (++j < z) /* try smaller tables up to z bits */ + { + if ((f <<= 1) <= *++xp) + break; /* enough codes to use up j bits */ + f -= *xp; /* else deduct codes from patterns */ + } + } +DEBG1("3 "); + z = 1 << j; /* table entries for j-bit table */ + + /* allocate and link in new table */ + if ((q = (struct huft *)malloc((z + 1)*sizeof(struct huft))) == + (struct huft *)NULL) + { + if (h) + huft_free(u[0]); + return 3; /* not enough memory */ + } +DEBG1("4 "); + hufts += z + 1; /* track memory usage */ + *t = q + 1; /* link to list for huft_free() */ + *(t = &(q->v.t)) = (struct huft *)NULL; + u[h] = ++q; /* table starts after link */ + +DEBG1("5 "); + /* connect to last table, if there is one */ + if (h) + { + x[h] = i; /* save pattern for backing up */ + r.b = (uch)l; /* bits to dump before this table */ + r.e = (uch)(16 + j); /* bits in this table */ + r.v.t = q; /* pointer to this table */ + j = i >> (w - l); /* (get around Turbo C bug) */ + u[h-1][j] = r; /* connect to last table */ + } +DEBG1("6 "); + } +DEBG("h6c "); + + /* set up table entry in r */ + r.b = (uch)(k - w); + if (p >= v + n) + r.e = 99; /* out of values--invalid code */ + else if (*p < s) + { + r.e = (uch)(*p < 256 ? 16 : 15); /* 256 is end-of-block code */ + r.v.n = (ush)(*p); /* simple code is just the value */ + p++; /* one compiler does not like *p++ */ + } + else + { + r.e = (uch)e[*p - s]; /* non-simple--look up in lists */ + r.v.n = d[*p++ - s]; + } +DEBG("h6d "); + + /* fill code-like entries with r */ + f = 1 << (k - w); + for (j = i >> w; j < z; j += f) + q[j] = r; + + /* backwards increment the k-bit code i */ + for (j = 1 << (k - 1); i & j; j >>= 1) + i ^= j; + i ^= j; + + /* backup over finished tables */ + while ((i & ((1 << w) - 1)) != x[h]) + { + h--; /* don't need to update q */ + w -= l; + } +DEBG("h6e "); + } +DEBG("h6f "); + } + +DEBG("huft7 "); + + /* Return true (1) if we were given an incomplete table */ + return y != 0 && g != 1; +} + + + +STATIC int INIT huft_free( + struct huft *t /* table to free */ + ) +/* Free the malloc'ed tables built by huft_build(), which makes a linked + list of the tables it made, with the links in a dummy first entry of + each table. */ +{ + register struct huft *p, *q; + + + /* Go through linked list, freeing from the malloced (t[-1]) address. */ + p = t; + while (p != (struct huft *)NULL) + { + q = (--p)->v.t; + free((char*)p); + p = q; + } + return 0; +} + + +STATIC int INIT inflate_codes( + struct huft *tl, /* literal/length decoder tables */ + struct huft *td, /* distance decoder tables */ + int bl, /* number of bits decoded by tl[] */ + int bd /* number of bits decoded by td[] */ + ) +/* inflate (decompress) the codes in a deflated (compressed) block. + Return an error code or zero if it all goes ok. */ +{ + register unsigned e; /* table entry flag/number of extra bits */ + unsigned n, d; /* length and index for copy */ + unsigned w; /* current window position */ + struct huft *t; /* pointer to table entry */ + unsigned ml, md; /* masks for bl and bd bits */ + register ulg b; /* bit buffer */ + register unsigned k; /* number of bits in bit buffer */ + + + /* make local copies of globals */ + b = bb; /* initialize bit buffer */ + k = bk; + w = wp; /* initialize window position */ + + /* inflate the coded data */ + ml = mask_bits[bl]; /* precompute masks for speed */ + md = mask_bits[bd]; + for (;;) /* do until end of block */ + { + NEEDBITS((unsigned)bl) + if ((e = (t = tl + ((unsigned)b & ml))->e) > 16) + do { + if (e == 99) + return 1; + DUMPBITS(t->b) + e -= 16; + NEEDBITS(e) + } while ((e = (t = t->v.t + ((unsigned)b & mask_bits[e]))->e) > 16); + DUMPBITS(t->b) + if (e == 16) /* then it's a literal */ + { + slide[w++] = (uch)t->v.n; + Tracevv((stderr, "%c", slide[w-1])); + if (w == WSIZE) + { + flush_output(w); + w = 0; + } + } + else /* it's an EOB or a length */ + { + /* exit if end of block */ + if (e == 15) + break; + + /* get length of block to copy */ + NEEDBITS(e) + n = t->v.n + ((unsigned)b & mask_bits[e]); + DUMPBITS(e); + + /* decode distance of block to copy */ + NEEDBITS((unsigned)bd) + if ((e = (t = td + ((unsigned)b & md))->e) > 16) + do { + if (e == 99) + return 1; + DUMPBITS(t->b) + e -= 16; + NEEDBITS(e) + } while ((e = (t = t->v.t + ((unsigned)b & mask_bits[e]))->e) > 16); + DUMPBITS(t->b) + NEEDBITS(e) + d = w - t->v.n - ((unsigned)b & mask_bits[e]); + DUMPBITS(e) + Tracevv((stderr,"\\[%d,%d]", w-d, n)); + + /* do the copy */ + do { + n -= (e = (e = WSIZE - ((d &= WSIZE-1) > w ? d : w)) > n ? n : e); +#if !defined(NOMEMCPY) && !defined(DEBUG) + if (w - d >= e) /* (this test assumes unsigned comparison) */ + { + memcpy(slide + w, slide + d, e); + w += e; + d += e; + } + else /* do it slow to avoid memcpy() overlap */ +#endif /* !NOMEMCPY */ + do { + slide[w++] = slide[d++]; + Tracevv((stderr, "%c", slide[w-1])); + } while (--e); + if (w == WSIZE) + { + flush_output(w); + w = 0; + } + } while (n); + } + } + + + /* restore the globals from the locals */ + wp = w; /* restore global window pointer */ + bb = b; /* restore global bit buffer */ + bk = k; + + /* done */ + return 0; + + underrun: + return 4; /* Input underrun */ +} + + + +STATIC int INIT inflate_stored(void) +/* "decompress" an inflated type 0 (stored) block. */ +{ + unsigned n; /* number of bytes in block */ + unsigned w; /* current window position */ + register ulg b; /* bit buffer */ + register unsigned k; /* number of bits in bit buffer */ + +DEBG("<stor"); + + /* make local copies of globals */ + b = bb; /* initialize bit buffer */ + k = bk; + w = wp; /* initialize window position */ + + + /* go to byte boundary */ + n = k & 7; + DUMPBITS(n); + + + /* get the length and its complement */ + NEEDBITS(16) + n = ((unsigned)b & 0xffff); + DUMPBITS(16) + NEEDBITS(16) + if (n != (unsigned)((~b) & 0xffff)) + return 1; /* error in compressed data */ + DUMPBITS(16) + + + /* read and output the compressed data */ + while (n--) + { + NEEDBITS(8) + slide[w++] = (uch)b; + if (w == WSIZE) + { + flush_output(w); + w = 0; + } + DUMPBITS(8) + } + + + /* restore the globals from the locals */ + wp = w; /* restore global window pointer */ + bb = b; /* restore global bit buffer */ + bk = k; + + DEBG(">"); + return 0; + + underrun: + return 4; /* Input underrun */ +} + + +/* + * We use `noinline' here to prevent gcc-3.5 from using too much stack space + */ +STATIC int noinline INIT inflate_fixed(void) +/* decompress an inflated type 1 (fixed Huffman codes) block. We should + either replace this with a custom decoder, or at least precompute the + Huffman tables. */ +{ + int i; /* temporary variable */ + struct huft *tl; /* literal/length code table */ + struct huft *td; /* distance code table */ + int bl; /* lookup bits for tl */ + int bd; /* lookup bits for td */ + unsigned l[288]; /* length list for huft_build */ + +DEBG("<fix"); + + /* set up literal table */ + for (i = 0; i < 144; i++) + l[i] = 8; + for (; i < 256; i++) + l[i] = 9; + for (; i < 280; i++) + l[i] = 7; + for (; i < 288; i++) /* make a complete, but wrong code set */ + l[i] = 8; + bl = 7; + if ((i = huft_build(l, 288, 257, cplens, cplext, &tl, &bl)) != 0) + return i; + + + /* set up distance table */ + for (i = 0; i < 30; i++) /* make an incomplete code set */ + l[i] = 5; + bd = 5; + if ((i = huft_build(l, 30, 0, cpdist, cpdext, &td, &bd)) > 1) + { + huft_free(tl); + + DEBG(">"); + return i; + } + + + /* decompress until an end-of-block code */ + if (inflate_codes(tl, td, bl, bd)) + return 1; + + + /* free the decoding tables, return */ + huft_free(tl); + huft_free(td); + return 0; +} + + +/* + * We use `noinline' here to prevent gcc-3.5 from using too much stack space + */ +STATIC int noinline INIT inflate_dynamic(void) +/* decompress an inflated type 2 (dynamic Huffman codes) block. */ +{ + int i; /* temporary variables */ + unsigned j; + unsigned l; /* last length */ + unsigned m; /* mask for bit lengths table */ + unsigned n; /* number of lengths to get */ + struct huft *tl; /* literal/length code table */ + struct huft *td; /* distance code table */ + int bl; /* lookup bits for tl */ + int bd; /* lookup bits for td */ + unsigned nb; /* number of bit length codes */ + unsigned nl; /* number of literal/length codes */ + unsigned nd; /* number of distance codes */ +#ifdef PKZIP_BUG_WORKAROUND + unsigned ll[288+32]; /* literal/length and distance code lengths */ +#else + unsigned ll[286+30]; /* literal/length and distance code lengths */ +#endif + register ulg b; /* bit buffer */ + register unsigned k; /* number of bits in bit buffer */ + +DEBG("<dyn"); + + /* make local bit buffer */ + b = bb; + k = bk; + + + /* read in table lengths */ + NEEDBITS(5) + nl = 257 + ((unsigned)b & 0x1f); /* number of literal/length codes */ + DUMPBITS(5) + NEEDBITS(5) + nd = 1 + ((unsigned)b & 0x1f); /* number of distance codes */ + DUMPBITS(5) + NEEDBITS(4) + nb = 4 + ((unsigned)b & 0xf); /* number of bit length codes */ + DUMPBITS(4) +#ifdef PKZIP_BUG_WORKAROUND + if (nl > 288 || nd > 32) +#else + if (nl > 286 || nd > 30) +#endif + return 1; /* bad lengths */ + +DEBG("dyn1 "); + + /* read in bit-length-code lengths */ + for (j = 0; j < nb; j++) + { + NEEDBITS(3) + ll[border[j]] = (unsigned)b & 7; + DUMPBITS(3) + } + for (; j < 19; j++) + ll[border[j]] = 0; + +DEBG("dyn2 "); + + /* build decoding table for trees--single level, 7 bit lookup */ + bl = 7; + if ((i = huft_build(ll, 19, 19, NULL, NULL, &tl, &bl)) != 0) + { + if (i == 1) + huft_free(tl); + return i; /* incomplete code set */ + } + +DEBG("dyn3 "); + + /* read in literal and distance code lengths */ + n = nl + nd; + m = mask_bits[bl]; + i = l = 0; + while ((unsigned)i < n) + { + NEEDBITS((unsigned)bl) + j = (td = tl + ((unsigned)b & m))->b; + DUMPBITS(j) + j = td->v.n; + if (j < 16) /* length of code in bits (0..15) */ + ll[i++] = l = j; /* save last length in l */ + else if (j == 16) /* repeat last length 3 to 6 times */ + { + NEEDBITS(2) + j = 3 + ((unsigned)b & 3); + DUMPBITS(2) + if ((unsigned)i + j > n) + return 1; + while (j--) + ll[i++] = l; + } + else if (j == 17) /* 3 to 10 zero length codes */ + { + NEEDBITS(3) + j = 3 + ((unsigned)b & 7); + DUMPBITS(3) + if ((unsigned)i + j > n) + return 1; + while (j--) + ll[i++] = 0; + l = 0; + } + else /* j == 18: 11 to 138 zero length codes */ + { + NEEDBITS(7) + j = 11 + ((unsigned)b & 0x7f); + DUMPBITS(7) + if ((unsigned)i + j > n) + return 1; + while (j--) + ll[i++] = 0; + l = 0; + } + } + +DEBG("dyn4 "); + + /* free decoding table for trees */ + huft_free(tl); + +DEBG("dyn5 "); + + /* restore the global bit buffer */ + bb = b; + bk = k; + +DEBG("dyn5a "); + + /* build the decoding tables for literal/length and distance codes */ + bl = lbits; + if ((i = huft_build(ll, nl, 257, cplens, cplext, &tl, &bl)) != 0) + { +DEBG("dyn5b "); + if (i == 1) { + error("incomplete literal tree"); + huft_free(tl); + } + return i; /* incomplete code set */ + } +DEBG("dyn5c "); + bd = dbits; + if ((i = huft_build(ll + nl, nd, 0, cpdist, cpdext, &td, &bd)) != 0) + { +DEBG("dyn5d "); + if (i == 1) { + error("incomplete distance tree"); +#ifdef PKZIP_BUG_WORKAROUND + i = 0; + } +#else + huft_free(td); + } + huft_free(tl); + return i; /* incomplete code set */ +#endif + } + +DEBG("dyn6 "); + + /* decompress until an end-of-block code */ + if (inflate_codes(tl, td, bl, bd)) + return 1; + +DEBG("dyn7 "); + + /* free the decoding tables, return */ + huft_free(tl); + huft_free(td); + + DEBG(">"); + return 0; + + underrun: + return 4; /* Input underrun */ +} + + + +STATIC int INIT inflate_block( + int *e /* last block flag */ + ) +/* decompress an inflated block */ +{ + unsigned t; /* block type */ + register ulg b; /* bit buffer */ + register unsigned k; /* number of bits in bit buffer */ + + DEBG("<blk"); + + /* make local bit buffer */ + b = bb; + k = bk; + + + /* read in last block bit */ + NEEDBITS(1) + *e = (int)b & 1; + DUMPBITS(1) + + + /* read in block type */ + NEEDBITS(2) + t = (unsigned)b & 3; + DUMPBITS(2) + + + /* restore the global bit buffer */ + bb = b; + bk = k; + + /* inflate that block type */ + if (t == 2) + return inflate_dynamic(); + if (t == 0) + return inflate_stored(); + if (t == 1) + return inflate_fixed(); + + DEBG(">"); + + /* bad block type */ + return 2; + + underrun: + return 4; /* Input underrun */ +} + + + +STATIC int INIT inflate(void) +/* decompress an inflated entry */ +{ + int e; /* last block flag */ + int r; /* result code */ + unsigned h; /* maximum struct huft's malloc'ed */ + void *ptr; + + /* initialize window, bit buffer */ + wp = 0; + bk = 0; + bb = 0; + + + /* decompress until the last block */ + h = 0; + do { + hufts = 0; + gzip_mark(&ptr); + if ((r = inflate_block(&e)) != 0) { + gzip_release(&ptr); + return r; + } + gzip_release(&ptr); + if (hufts > h) + h = hufts; + } while (!e); + + /* Undo too much lookahead. The next read will be byte aligned so we + * can discard unused bits in the last meaningful byte. + */ + while (bk >= 8) { + bk -= 8; + inptr--; + } + + /* flush out slide */ + flush_output(wp); + + + /* return success */ +#ifdef DEBUG + fprintf(stderr, "<%u> ", h); +#endif /* DEBUG */ + return 0; +} + +/********************************************************************** + * + * The following are support routines for inflate.c + * + **********************************************************************/ + +static ulg crc_32_tab[256]; +static ulg crc; /* initialized in makecrc() so it'll reside in bss */ +#define CRC_VALUE (crc ^ 0xffffffffUL) + +/* + * Code to compute the CRC-32 table. Borrowed from + * gzip-1.0.3/makecrc.c. + */ + +static void INIT +makecrc(void) +{ +/* Not copyrighted 1990 Mark Adler */ + + unsigned long c; /* crc shift register */ + unsigned long e; /* polynomial exclusive-or pattern */ + int i; /* counter for all possible eight bit values */ + int k; /* byte being shifted into crc apparatus */ + + /* terms of polynomial defining this crc (except x^32): */ + static const int p[] = {0,1,2,4,5,7,8,10,11,12,16,22,23,26}; + + /* Make exclusive-or pattern from polynomial */ + e = 0; + for (i = 0; i < sizeof(p)/sizeof(int); i++) + e |= 1L << (31 - p[i]); + + crc_32_tab[0] = 0; + + for (i = 1; i < 256; i++) + { + c = 0; + for (k = i | 256; k != 1; k >>= 1) + { + c = c & 1 ? (c >> 1) ^ e : c >> 1; + if (k & 1) + c ^= e; + } + crc_32_tab[i] = c; + } + + /* this is initialized here so this code could reside in ROM */ + crc = (ulg)0xffffffffUL; /* shift register contents */ +} + +/* gzip flag byte */ +#define ASCII_FLAG 0x01 /* bit 0 set: file probably ASCII text */ +#define CONTINUATION 0x02 /* bit 1 set: continuation of multi-part gzip file */ +#define EXTRA_FIELD 0x04 /* bit 2 set: extra field present */ +#define ORIG_NAME 0x08 /* bit 3 set: original file name present */ +#define COMMENT 0x10 /* bit 4 set: file comment present */ +#define ENCRYPTED 0x20 /* bit 5 set: file is encrypted */ +#define RESERVED 0xC0 /* bit 6,7: reserved */ + +/* + * Do the uncompression! + */ +static int INIT gunzip(void) +{ + uch flags; + unsigned char magic[2]; /* magic header */ + char method; + ulg orig_crc = 0; /* original crc */ + ulg orig_len = 0; /* original uncompressed length */ + int res; + + magic[0] = NEXTBYTE(); + magic[1] = NEXTBYTE(); + method = NEXTBYTE(); + + if (magic[0] != 037 || + ((magic[1] != 0213) && (magic[1] != 0236))) { + error("bad gzip magic numbers"); + return -1; + } + + /* We only support method #8, DEFLATED */ + if (method != 8) { + error("internal error, invalid method"); + return -1; + } + + flags = (uch)get_byte(); + if ((flags & ENCRYPTED) != 0) { + error("Input is encrypted"); + return -1; + } + if ((flags & CONTINUATION) != 0) { + error("Multi part input"); + return -1; + } + if ((flags & RESERVED) != 0) { + error("Input has invalid flags"); + return -1; + } + NEXTBYTE(); /* Get timestamp */ + NEXTBYTE(); + NEXTBYTE(); + NEXTBYTE(); + + (void)NEXTBYTE(); /* Ignore extra flags for the moment */ + (void)NEXTBYTE(); /* Ignore OS type for the moment */ + + if ((flags & EXTRA_FIELD) != 0) { + unsigned len = (unsigned)NEXTBYTE(); + len |= ((unsigned)NEXTBYTE())<<8; + while (len--) (void)NEXTBYTE(); + } + + /* Get original file name if it was truncated */ + if ((flags & ORIG_NAME) != 0) { + /* Discard the old name */ + while (NEXTBYTE() != 0) /* null */ ; + } + + /* Discard file comment if any */ + if ((flags & COMMENT) != 0) { + while (NEXTBYTE() != 0) /* null */ ; + } + + /* Decompress */ + if ((res = inflate())) { + switch (res) { + case 0: + break; + case 1: + error("invalid compressed format (err=1)"); + break; + case 2: + error("invalid compressed format (err=2)"); + break; + case 3: + error("out of memory"); + break; + case 4: + error("out of input data"); + break; + default: + error("invalid compressed format (other)"); + } + return -1; + } + + /* Get the crc and original length */ + /* crc32 (see algorithm.doc) + * uncompressed input size modulo 2^32 + */ + orig_crc = (ulg) NEXTBYTE(); + orig_crc |= (ulg) NEXTBYTE() << 8; + orig_crc |= (ulg) NEXTBYTE() << 16; + orig_crc |= (ulg) NEXTBYTE() << 24; + + orig_len = (ulg) NEXTBYTE(); + orig_len |= (ulg) NEXTBYTE() << 8; + orig_len |= (ulg) NEXTBYTE() << 16; + orig_len |= (ulg) NEXTBYTE() << 24; + + /* Validate decompression */ + if (orig_crc != CRC_VALUE) { + error("crc error"); + return -1; + } + if (orig_len != bytes_out) { + error("length error"); + return -1; + } + return 0; + + underrun: /* NEXTBYTE() goto's here if needed */ + error("out of input data"); + return -1; +} + + diff --git a/lib/int_sqrt.c b/lib/int_sqrt.c new file mode 100644 index 00000000000..a5d2cdc5684 --- /dev/null +++ b/lib/int_sqrt.c @@ -0,0 +1,32 @@ + +#include <linux/kernel.h> +#include <linux/module.h> + +/** + * int_sqrt - rough approximation to sqrt + * @x: integer of which to calculate the sqrt + * + * A very rough approximation to the sqrt() function. + */ +unsigned long int_sqrt(unsigned long x) +{ + unsigned long op, res, one; + + op = x; + res = 0; + + one = 1 << 30; + while (one > op) + one >>= 2; + + while (one != 0) { + if (op >= res + one) { + op = op - (res + one); + res = res + 2 * one; + } + res /= 2; + one /= 4; + } + return res; +} +EXPORT_SYMBOL(int_sqrt); diff --git a/lib/iomap.c b/lib/iomap.c new file mode 100644 index 00000000000..5e74390852b --- /dev/null +++ b/lib/iomap.c @@ -0,0 +1,212 @@ +/* + * Implement the default iomap interfaces + * + * (C) Copyright 2004 Linus Torvalds + */ +#include <linux/pci.h> +#include <linux/module.h> +#include <asm/io.h> + +/* + * Read/write from/to an (offsettable) iomem cookie. It might be a PIO + * access or a MMIO access, these functions don't care. The info is + * encoded in the hardware mapping set up by the mapping functions + * (or the cookie itself, depending on implementation and hw). + * + * The generic routines don't assume any hardware mappings, and just + * encode the PIO/MMIO as part of the cookie. They coldly assume that + * the MMIO IO mappings are not in the low address range. + * + * Architectures for which this is not true can't use this generic + * implementation and should do their own copy. + */ + +#ifndef HAVE_ARCH_PIO_SIZE +/* + * We encode the physical PIO addresses (0-0xffff) into the + * pointer by offsetting them with a constant (0x10000) and + * assuming that all the low addresses are always PIO. That means + * we can do some sanity checks on the low bits, and don't + * need to just take things for granted. + */ +#define PIO_OFFSET 0x10000UL +#define PIO_MASK 0x0ffffUL +#define PIO_RESERVED 0x40000UL +#endif + +/* + * Ugly macros are a way of life. + */ +#define VERIFY_PIO(port) BUG_ON((port & ~PIO_MASK) != PIO_OFFSET) + +#define IO_COND(addr, is_pio, is_mmio) do { \ + unsigned long port = (unsigned long __force)addr; \ + if (port < PIO_RESERVED) { \ + VERIFY_PIO(port); \ + port &= PIO_MASK; \ + is_pio; \ + } else { \ + is_mmio; \ + } \ +} while (0) + +unsigned int fastcall ioread8(void __iomem *addr) +{ + IO_COND(addr, return inb(port), return readb(addr)); +} +unsigned int fastcall ioread16(void __iomem *addr) +{ + IO_COND(addr, return inw(port), return readw(addr)); +} +unsigned int fastcall ioread32(void __iomem *addr) +{ + IO_COND(addr, return inl(port), return readl(addr)); +} +EXPORT_SYMBOL(ioread8); +EXPORT_SYMBOL(ioread16); +EXPORT_SYMBOL(ioread32); + +void fastcall iowrite8(u8 val, void __iomem *addr) +{ + IO_COND(addr, outb(val,port), writeb(val, addr)); +} +void fastcall iowrite16(u16 val, void __iomem *addr) +{ + IO_COND(addr, outw(val,port), writew(val, addr)); +} +void fastcall iowrite32(u32 val, void __iomem *addr) +{ + IO_COND(addr, outl(val,port), writel(val, addr)); +} +EXPORT_SYMBOL(iowrite8); +EXPORT_SYMBOL(iowrite16); +EXPORT_SYMBOL(iowrite32); + +/* + * These are the "repeat MMIO read/write" functions. + * Note the "__raw" accesses, since we don't want to + * convert to CPU byte order. We write in "IO byte + * order" (we also don't have IO barriers). + */ +static inline void mmio_insb(void __iomem *addr, u8 *dst, int count) +{ + while (--count >= 0) { + u8 data = __raw_readb(addr); + *dst = data; + dst++; + } +} +static inline void mmio_insw(void __iomem *addr, u16 *dst, int count) +{ + while (--count >= 0) { + u16 data = __raw_readw(addr); + *dst = data; + dst++; + } +} +static inline void mmio_insl(void __iomem *addr, u32 *dst, int count) +{ + while (--count >= 0) { + u32 data = __raw_readl(addr); + *dst = data; + dst++; + } +} + +static inline void mmio_outsb(void __iomem *addr, const u8 *src, int count) +{ + while (--count >= 0) { + __raw_writeb(*src, addr); + src++; + } +} +static inline void mmio_outsw(void __iomem *addr, const u16 *src, int count) +{ + while (--count >= 0) { + __raw_writew(*src, addr); + src++; + } +} +static inline void mmio_outsl(void __iomem *addr, const u32 *src, int count) +{ + while (--count >= 0) { + __raw_writel(*src, addr); + src++; + } +} + +void fastcall ioread8_rep(void __iomem *addr, void *dst, unsigned long count) +{ + IO_COND(addr, insb(port,dst,count), mmio_insb(addr, dst, count)); +} +void fastcall ioread16_rep(void __iomem *addr, void *dst, unsigned long count) +{ + IO_COND(addr, insw(port,dst,count), mmio_insw(addr, dst, count)); +} +void fastcall ioread32_rep(void __iomem *addr, void *dst, unsigned long count) +{ + IO_COND(addr, insl(port,dst,count), mmio_insl(addr, dst, count)); +} +EXPORT_SYMBOL(ioread8_rep); +EXPORT_SYMBOL(ioread16_rep); +EXPORT_SYMBOL(ioread32_rep); + +void fastcall iowrite8_rep(void __iomem *addr, const void *src, unsigned long count) +{ + IO_COND(addr, outsb(port, src, count), mmio_outsb(addr, src, count)); +} +void fastcall iowrite16_rep(void __iomem *addr, const void *src, unsigned long count) +{ + IO_COND(addr, outsw(port, src, count), mmio_outsw(addr, src, count)); +} +void fastcall iowrite32_rep(void __iomem *addr, const void *src, unsigned long count) +{ + IO_COND(addr, outsl(port, src,count), mmio_outsl(addr, src, count)); +} +EXPORT_SYMBOL(iowrite8_rep); +EXPORT_SYMBOL(iowrite16_rep); +EXPORT_SYMBOL(iowrite32_rep); + +/* Create a virtual mapping cookie for an IO port range */ +void __iomem *ioport_map(unsigned long port, unsigned int nr) +{ + if (port > PIO_MASK) + return NULL; + return (void __iomem *) (unsigned long) (port + PIO_OFFSET); +} + +void ioport_unmap(void __iomem *addr) +{ + /* Nothing to do */ +} +EXPORT_SYMBOL(ioport_map); +EXPORT_SYMBOL(ioport_unmap); + +/* Create a virtual mapping cookie for a PCI BAR (memory or IO) */ +void __iomem *pci_iomap(struct pci_dev *dev, int bar, unsigned long maxlen) +{ + unsigned long start = pci_resource_start(dev, bar); + unsigned long len = pci_resource_len(dev, bar); + unsigned long flags = pci_resource_flags(dev, bar); + + if (!len || !start) + return NULL; + if (maxlen && len > maxlen) + len = maxlen; + if (flags & IORESOURCE_IO) + return ioport_map(start, len); + if (flags & IORESOURCE_MEM) { + if (flags & IORESOURCE_CACHEABLE) + return ioremap(start, len); + return ioremap_nocache(start, len); + } + /* What? */ + return NULL; +} + +void pci_iounmap(struct pci_dev *dev, void __iomem * addr) +{ + IO_COND(addr, /* nothing */, iounmap(addr)); +} +EXPORT_SYMBOL(pci_iomap); +EXPORT_SYMBOL(pci_iounmap); diff --git a/lib/kernel_lock.c b/lib/kernel_lock.c new file mode 100644 index 00000000000..99b0ae3d51d --- /dev/null +++ b/lib/kernel_lock.c @@ -0,0 +1,264 @@ +/* + * lib/kernel_lock.c + * + * This is the traditional BKL - big kernel lock. Largely + * relegated to obsolescense, but used by various less + * important (or lazy) subsystems. + */ +#include <linux/smp_lock.h> +#include <linux/module.h> +#include <linux/kallsyms.h> + +#if defined(CONFIG_PREEMPT) && defined(__smp_processor_id) && \ + defined(CONFIG_DEBUG_PREEMPT) + +/* + * Debugging check. + */ +unsigned int smp_processor_id(void) +{ + unsigned long preempt_count = preempt_count(); + int this_cpu = __smp_processor_id(); + cpumask_t this_mask; + + if (likely(preempt_count)) + goto out; + + if (irqs_disabled()) + goto out; + + /* + * Kernel threads bound to a single CPU can safely use + * smp_processor_id(): + */ + this_mask = cpumask_of_cpu(this_cpu); + + if (cpus_equal(current->cpus_allowed, this_mask)) + goto out; + + /* + * It is valid to assume CPU-locality during early bootup: + */ + if (system_state != SYSTEM_RUNNING) + goto out; + + /* + * Avoid recursion: + */ + preempt_disable(); + + if (!printk_ratelimit()) + goto out_enable; + + printk(KERN_ERR "BUG: using smp_processor_id() in preemptible [%08x] code: %s/%d\n", preempt_count(), current->comm, current->pid); + print_symbol("caller is %s\n", (long)__builtin_return_address(0)); + dump_stack(); + +out_enable: + preempt_enable_no_resched(); +out: + return this_cpu; +} + +EXPORT_SYMBOL(smp_processor_id); + +#endif /* PREEMPT && __smp_processor_id && DEBUG_PREEMPT */ + +#ifdef CONFIG_PREEMPT_BKL +/* + * The 'big kernel semaphore' + * + * This mutex is taken and released recursively by lock_kernel() + * and unlock_kernel(). It is transparently dropped and reaquired + * over schedule(). It is used to protect legacy code that hasn't + * been migrated to a proper locking design yet. + * + * Note: code locked by this semaphore will only be serialized against + * other code using the same locking facility. The code guarantees that + * the task remains on the same CPU. + * + * Don't use in new code. + */ +static DECLARE_MUTEX(kernel_sem); + +/* + * Re-acquire the kernel semaphore. + * + * This function is called with preemption off. + * + * We are executing in schedule() so the code must be extremely careful + * about recursion, both due to the down() and due to the enabling of + * preemption. schedule() will re-check the preemption flag after + * reacquiring the semaphore. + */ +int __lockfunc __reacquire_kernel_lock(void) +{ + struct task_struct *task = current; + int saved_lock_depth = task->lock_depth; + + BUG_ON(saved_lock_depth < 0); + + task->lock_depth = -1; + preempt_enable_no_resched(); + + down(&kernel_sem); + + preempt_disable(); + task->lock_depth = saved_lock_depth; + + return 0; +} + +void __lockfunc __release_kernel_lock(void) +{ + up(&kernel_sem); +} + +/* + * Getting the big kernel semaphore. + */ +void __lockfunc lock_kernel(void) +{ + struct task_struct *task = current; + int depth = task->lock_depth + 1; + + if (likely(!depth)) + /* + * No recursion worries - we set up lock_depth _after_ + */ + down(&kernel_sem); + + task->lock_depth = depth; +} + +void __lockfunc unlock_kernel(void) +{ + struct task_struct *task = current; + + BUG_ON(task->lock_depth < 0); + + if (likely(--task->lock_depth < 0)) + up(&kernel_sem); +} + +#else + +/* + * The 'big kernel lock' + * + * This spinlock is taken and released recursively by lock_kernel() + * and unlock_kernel(). It is transparently dropped and reaquired + * over schedule(). It is used to protect legacy code that hasn't + * been migrated to a proper locking design yet. + * + * Don't use in new code. + */ +static __cacheline_aligned_in_smp DEFINE_SPINLOCK(kernel_flag); + + +/* + * Acquire/release the underlying lock from the scheduler. + * + * This is called with preemption disabled, and should + * return an error value if it cannot get the lock and + * TIF_NEED_RESCHED gets set. + * + * If it successfully gets the lock, it should increment + * the preemption count like any spinlock does. + * + * (This works on UP too - _raw_spin_trylock will never + * return false in that case) + */ +int __lockfunc __reacquire_kernel_lock(void) +{ + while (!_raw_spin_trylock(&kernel_flag)) { + if (test_thread_flag(TIF_NEED_RESCHED)) + return -EAGAIN; + cpu_relax(); + } + preempt_disable(); + return 0; +} + +void __lockfunc __release_kernel_lock(void) +{ + _raw_spin_unlock(&kernel_flag); + preempt_enable_no_resched(); +} + +/* + * These are the BKL spinlocks - we try to be polite about preemption. + * If SMP is not on (ie UP preemption), this all goes away because the + * _raw_spin_trylock() will always succeed. + */ +#ifdef CONFIG_PREEMPT +static inline void __lock_kernel(void) +{ + preempt_disable(); + if (unlikely(!_raw_spin_trylock(&kernel_flag))) { + /* + * If preemption was disabled even before this + * was called, there's nothing we can be polite + * about - just spin. + */ + if (preempt_count() > 1) { + _raw_spin_lock(&kernel_flag); + return; + } + + /* + * Otherwise, let's wait for the kernel lock + * with preemption enabled.. + */ + do { + preempt_enable(); + while (spin_is_locked(&kernel_flag)) + cpu_relax(); + preempt_disable(); + } while (!_raw_spin_trylock(&kernel_flag)); + } +} + +#else + +/* + * Non-preemption case - just get the spinlock + */ +static inline void __lock_kernel(void) +{ + _raw_spin_lock(&kernel_flag); +} +#endif + +static inline void __unlock_kernel(void) +{ + _raw_spin_unlock(&kernel_flag); + preempt_enable(); +} + +/* + * Getting the big kernel lock. + * + * This cannot happen asynchronously, so we only need to + * worry about other CPU's. + */ +void __lockfunc lock_kernel(void) +{ + int depth = current->lock_depth+1; + if (likely(!depth)) + __lock_kernel(); + current->lock_depth = depth; +} + +void __lockfunc unlock_kernel(void) +{ + BUG_ON(current->lock_depth < 0); + if (likely(--current->lock_depth < 0)) + __unlock_kernel(); +} + +#endif + +EXPORT_SYMBOL(lock_kernel); +EXPORT_SYMBOL(unlock_kernel); + diff --git a/lib/kobject.c b/lib/kobject.c new file mode 100644 index 00000000000..ff9491986b3 --- /dev/null +++ b/lib/kobject.c @@ -0,0 +1,544 @@ +/* + * kobject.c - library routines for handling generic kernel objects + * + * Copyright (c) 2002-2003 Patrick Mochel <mochel@osdl.org> + * + * This file is released under the GPLv2. + * + * + * Please see the file Documentation/kobject.txt for critical information + * about using the kobject interface. + */ + +#include <linux/kobject.h> +#include <linux/string.h> +#include <linux/module.h> +#include <linux/stat.h> + +/** + * populate_dir - populate directory with attributes. + * @kobj: object we're working on. + * + * Most subsystems have a set of default attributes that + * are associated with an object that registers with them. + * This is a helper called during object registration that + * loops through the default attributes of the subsystem + * and creates attributes files for them in sysfs. + * + */ + +static int populate_dir(struct kobject * kobj) +{ + struct kobj_type * t = get_ktype(kobj); + struct attribute * attr; + int error = 0; + int i; + + if (t && t->default_attrs) { + for (i = 0; (attr = t->default_attrs[i]) != NULL; i++) { + if ((error = sysfs_create_file(kobj,attr))) + break; + } + } + return error; +} + +static int create_dir(struct kobject * kobj) +{ + int error = 0; + if (kobject_name(kobj)) { + error = sysfs_create_dir(kobj); + if (!error) { + if ((error = populate_dir(kobj))) + sysfs_remove_dir(kobj); + } + } + return error; +} + +static inline struct kobject * to_kobj(struct list_head * entry) +{ + return container_of(entry,struct kobject,entry); +} + +static int get_kobj_path_length(struct kobject *kobj) +{ + int length = 1; + struct kobject * parent = kobj; + + /* walk up the ancestors until we hit the one pointing to the + * root. + * Add 1 to strlen for leading '/' of each level. + */ + do { + length += strlen(kobject_name(parent)) + 1; + parent = parent->parent; + } while (parent); + return length; +} + +static void fill_kobj_path(struct kobject *kobj, char *path, int length) +{ + struct kobject * parent; + + --length; + for (parent = kobj; parent; parent = parent->parent) { + int cur = strlen(kobject_name(parent)); + /* back up enough to print this name with '/' */ + length -= cur; + strncpy (path + length, kobject_name(parent), cur); + *(path + --length) = '/'; + } + + pr_debug("%s: path = '%s'\n",__FUNCTION__,path); +} + +/** + * kobject_get_path - generate and return the path associated with a given kobj + * and kset pair. The result must be freed by the caller with kfree(). + * + * @kobj: kobject in question, with which to build the path + * @gfp_mask: the allocation type used to allocate the path + */ +char *kobject_get_path(struct kobject *kobj, int gfp_mask) +{ + char *path; + int len; + + len = get_kobj_path_length(kobj); + path = kmalloc(len, gfp_mask); + if (!path) + return NULL; + memset(path, 0x00, len); + fill_kobj_path(kobj, path, len); + + return path; +} + +/** + * kobject_init - initialize object. + * @kobj: object in question. + */ +void kobject_init(struct kobject * kobj) +{ + kref_init(&kobj->kref); + INIT_LIST_HEAD(&kobj->entry); + kobj->kset = kset_get(kobj->kset); +} + + +/** + * unlink - remove kobject from kset list. + * @kobj: kobject. + * + * Remove the kobject from the kset list and decrement + * its parent's refcount. + * This is separated out, so we can use it in both + * kobject_del() and kobject_add() on error. + */ + +static void unlink(struct kobject * kobj) +{ + if (kobj->kset) { + spin_lock(&kobj->kset->list_lock); + list_del_init(&kobj->entry); + spin_unlock(&kobj->kset->list_lock); + } + kobject_put(kobj); +} + +/** + * kobject_add - add an object to the hierarchy. + * @kobj: object. + */ + +int kobject_add(struct kobject * kobj) +{ + int error = 0; + struct kobject * parent; + + if (!(kobj = kobject_get(kobj))) + return -ENOENT; + if (!kobj->k_name) + kobj->k_name = kobj->name; + parent = kobject_get(kobj->parent); + + pr_debug("kobject %s: registering. parent: %s, set: %s\n", + kobject_name(kobj), parent ? kobject_name(parent) : "<NULL>", + kobj->kset ? kobj->kset->kobj.name : "<NULL>" ); + + if (kobj->kset) { + spin_lock(&kobj->kset->list_lock); + + if (!parent) + parent = kobject_get(&kobj->kset->kobj); + + list_add_tail(&kobj->entry,&kobj->kset->list); + spin_unlock(&kobj->kset->list_lock); + } + kobj->parent = parent; + + error = create_dir(kobj); + if (error) { + /* unlink does the kobject_put() for us */ + unlink(kobj); + if (parent) + kobject_put(parent); + } else { + kobject_hotplug(kobj, KOBJ_ADD); + } + + return error; +} + + +/** + * kobject_register - initialize and add an object. + * @kobj: object in question. + */ + +int kobject_register(struct kobject * kobj) +{ + int error = 0; + if (kobj) { + kobject_init(kobj); + error = kobject_add(kobj); + if (error) { + printk("kobject_register failed for %s (%d)\n", + kobject_name(kobj),error); + dump_stack(); + } + } else + error = -EINVAL; + return error; +} + + +/** + * kobject_set_name - Set the name of an object + * @kobj: object. + * @name: name. + * + * If strlen(name) >= KOBJ_NAME_LEN, then use a dynamically allocated + * string that @kobj->k_name points to. Otherwise, use the static + * @kobj->name array. + */ + +int kobject_set_name(struct kobject * kobj, const char * fmt, ...) +{ + int error = 0; + int limit = KOBJ_NAME_LEN; + int need; + va_list args; + char * name; + + /* + * First, try the static array + */ + va_start(args,fmt); + need = vsnprintf(kobj->name,limit,fmt,args); + va_end(args); + if (need < limit) + name = kobj->name; + else { + /* + * Need more space? Allocate it and try again + */ + limit = need + 1; + name = kmalloc(limit,GFP_KERNEL); + if (!name) { + error = -ENOMEM; + goto Done; + } + va_start(args,fmt); + need = vsnprintf(name,limit,fmt,args); + va_end(args); + + /* Still? Give up. */ + if (need >= limit) { + kfree(name); + error = -EFAULT; + goto Done; + } + } + + /* Free the old name, if necessary. */ + if (kobj->k_name && kobj->k_name != kobj->name) + kfree(kobj->k_name); + + /* Now, set the new name */ + kobj->k_name = name; + Done: + return error; +} + +EXPORT_SYMBOL(kobject_set_name); + + +/** + * kobject_rename - change the name of an object + * @kobj: object in question. + * @new_name: object's new name + */ + +int kobject_rename(struct kobject * kobj, char *new_name) +{ + int error = 0; + + kobj = kobject_get(kobj); + if (!kobj) + return -EINVAL; + error = sysfs_rename_dir(kobj, new_name); + kobject_put(kobj); + + return error; +} + +/** + * kobject_del - unlink kobject from hierarchy. + * @kobj: object. + */ + +void kobject_del(struct kobject * kobj) +{ + kobject_hotplug(kobj, KOBJ_REMOVE); + sysfs_remove_dir(kobj); + unlink(kobj); +} + +/** + * kobject_unregister - remove object from hierarchy and decrement refcount. + * @kobj: object going away. + */ + +void kobject_unregister(struct kobject * kobj) +{ + pr_debug("kobject %s: unregistering\n",kobject_name(kobj)); + kobject_del(kobj); + kobject_put(kobj); +} + +/** + * kobject_get - increment refcount for object. + * @kobj: object. + */ + +struct kobject * kobject_get(struct kobject * kobj) +{ + if (kobj) + kref_get(&kobj->kref); + return kobj; +} + +/** + * kobject_cleanup - free kobject resources. + * @kobj: object. + */ + +void kobject_cleanup(struct kobject * kobj) +{ + struct kobj_type * t = get_ktype(kobj); + struct kset * s = kobj->kset; + struct kobject * parent = kobj->parent; + + pr_debug("kobject %s: cleaning up\n",kobject_name(kobj)); + if (kobj->k_name != kobj->name) + kfree(kobj->k_name); + kobj->k_name = NULL; + if (t && t->release) + t->release(kobj); + if (s) + kset_put(s); + if (parent) + kobject_put(parent); +} + +static void kobject_release(struct kref *kref) +{ + kobject_cleanup(container_of(kref, struct kobject, kref)); +} + +/** + * kobject_put - decrement refcount for object. + * @kobj: object. + * + * Decrement the refcount, and if 0, call kobject_cleanup(). + */ +void kobject_put(struct kobject * kobj) +{ + if (kobj) + kref_put(&kobj->kref, kobject_release); +} + + +/** + * kset_init - initialize a kset for use + * @k: kset + */ + +void kset_init(struct kset * k) +{ + kobject_init(&k->kobj); + INIT_LIST_HEAD(&k->list); + spin_lock_init(&k->list_lock); +} + + +/** + * kset_add - add a kset object to the hierarchy. + * @k: kset. + * + * Simply, this adds the kset's embedded kobject to the + * hierarchy. + * We also try to make sure that the kset's embedded kobject + * has a parent before it is added. We only care if the embedded + * kobject is not part of a kset itself, since kobject_add() + * assigns a parent in that case. + * If that is the case, and the kset has a controlling subsystem, + * then we set the kset's parent to be said subsystem. + */ + +int kset_add(struct kset * k) +{ + if (!k->kobj.parent && !k->kobj.kset && k->subsys) + k->kobj.parent = &k->subsys->kset.kobj; + + return kobject_add(&k->kobj); +} + + +/** + * kset_register - initialize and add a kset. + * @k: kset. + */ + +int kset_register(struct kset * k) +{ + kset_init(k); + return kset_add(k); +} + + +/** + * kset_unregister - remove a kset. + * @k: kset. + */ + +void kset_unregister(struct kset * k) +{ + kobject_unregister(&k->kobj); +} + + +/** + * kset_find_obj - search for object in kset. + * @kset: kset we're looking in. + * @name: object's name. + * + * Lock kset via @kset->subsys, and iterate over @kset->list, + * looking for a matching kobject. If matching object is found + * take a reference and return the object. + */ + +struct kobject * kset_find_obj(struct kset * kset, const char * name) +{ + struct list_head * entry; + struct kobject * ret = NULL; + + spin_lock(&kset->list_lock); + list_for_each(entry,&kset->list) { + struct kobject * k = to_kobj(entry); + if (kobject_name(k) && !strcmp(kobject_name(k),name)) { + ret = kobject_get(k); + break; + } + } + spin_unlock(&kset->list_lock); + return ret; +} + + +void subsystem_init(struct subsystem * s) +{ + init_rwsem(&s->rwsem); + kset_init(&s->kset); +} + +/** + * subsystem_register - register a subsystem. + * @s: the subsystem we're registering. + * + * Once we register the subsystem, we want to make sure that + * the kset points back to this subsystem for correct usage of + * the rwsem. + */ + +int subsystem_register(struct subsystem * s) +{ + int error; + + subsystem_init(s); + pr_debug("subsystem %s: registering\n",s->kset.kobj.name); + + if (!(error = kset_add(&s->kset))) { + if (!s->kset.subsys) + s->kset.subsys = s; + } + return error; +} + +void subsystem_unregister(struct subsystem * s) +{ + pr_debug("subsystem %s: unregistering\n",s->kset.kobj.name); + kset_unregister(&s->kset); +} + + +/** + * subsystem_create_file - export sysfs attribute file. + * @s: subsystem. + * @a: subsystem attribute descriptor. + */ + +int subsys_create_file(struct subsystem * s, struct subsys_attribute * a) +{ + int error = 0; + if (subsys_get(s)) { + error = sysfs_create_file(&s->kset.kobj,&a->attr); + subsys_put(s); + } + return error; +} + + +/** + * subsystem_remove_file - remove sysfs attribute file. + * @s: subsystem. + * @a: attribute desciptor. + */ + +void subsys_remove_file(struct subsystem * s, struct subsys_attribute * a) +{ + if (subsys_get(s)) { + sysfs_remove_file(&s->kset.kobj,&a->attr); + subsys_put(s); + } +} + +EXPORT_SYMBOL(kobject_init); +EXPORT_SYMBOL(kobject_register); +EXPORT_SYMBOL(kobject_unregister); +EXPORT_SYMBOL(kobject_get); +EXPORT_SYMBOL(kobject_put); +EXPORT_SYMBOL(kobject_add); +EXPORT_SYMBOL(kobject_del); + +EXPORT_SYMBOL(kset_register); +EXPORT_SYMBOL(kset_unregister); +EXPORT_SYMBOL(kset_find_obj); + +EXPORT_SYMBOL(subsystem_init); +EXPORT_SYMBOL(subsystem_register); +EXPORT_SYMBOL(subsystem_unregister); +EXPORT_SYMBOL(subsys_create_file); +EXPORT_SYMBOL(subsys_remove_file); diff --git a/lib/kobject_uevent.c b/lib/kobject_uevent.c new file mode 100644 index 00000000000..2a4e7671eaf --- /dev/null +++ b/lib/kobject_uevent.c @@ -0,0 +1,369 @@ +/* + * kernel userspace event delivery + * + * Copyright (C) 2004 Red Hat, Inc. All rights reserved. + * Copyright (C) 2004 Novell, Inc. All rights reserved. + * Copyright (C) 2004 IBM, Inc. All rights reserved. + * + * Licensed under the GNU GPL v2. + * + * Authors: + * Robert Love <rml@novell.com> + * Kay Sievers <kay.sievers@vrfy.org> + * Arjan van de Ven <arjanv@redhat.com> + * Greg Kroah-Hartman <greg@kroah.com> + */ + +#include <linux/spinlock.h> +#include <linux/socket.h> +#include <linux/skbuff.h> +#include <linux/netlink.h> +#include <linux/string.h> +#include <linux/kobject_uevent.h> +#include <linux/kobject.h> +#include <net/sock.h> + +#define BUFFER_SIZE 1024 /* buffer for the hotplug env */ +#define NUM_ENVP 32 /* number of env pointers */ + +#if defined(CONFIG_KOBJECT_UEVENT) || defined(CONFIG_HOTPLUG) +static char *action_to_string(enum kobject_action action) +{ + switch (action) { + case KOBJ_ADD: + return "add"; + case KOBJ_REMOVE: + return "remove"; + case KOBJ_CHANGE: + return "change"; + case KOBJ_MOUNT: + return "mount"; + case KOBJ_UMOUNT: + return "umount"; + case KOBJ_OFFLINE: + return "offline"; + case KOBJ_ONLINE: + return "online"; + default: + return NULL; + } +} +#endif + +#ifdef CONFIG_KOBJECT_UEVENT +static struct sock *uevent_sock; + +/** + * send_uevent - notify userspace by sending event trough netlink socket + * + * @signal: signal name + * @obj: object path (kobject) + * @envp: possible hotplug environment to pass with the message + * @gfp_mask: + */ +static int send_uevent(const char *signal, const char *obj, + char **envp, int gfp_mask) +{ + struct sk_buff *skb; + char *pos; + int len; + + if (!uevent_sock) + return -EIO; + + len = strlen(signal) + 1; + len += strlen(obj) + 1; + + /* allocate buffer with the maximum possible message size */ + skb = alloc_skb(len + BUFFER_SIZE, gfp_mask); + if (!skb) + return -ENOMEM; + + pos = skb_put(skb, len); + sprintf(pos, "%s@%s", signal, obj); + + /* copy the environment key by key to our continuous buffer */ + if (envp) { + int i; + + for (i = 2; envp[i]; i++) { + len = strlen(envp[i]) + 1; + pos = skb_put(skb, len); + strcpy(pos, envp[i]); + } + } + + return netlink_broadcast(uevent_sock, skb, 0, 1, gfp_mask); +} + +static int do_kobject_uevent(struct kobject *kobj, enum kobject_action action, + struct attribute *attr, int gfp_mask) +{ + char *path; + char *attrpath; + char *signal; + int len; + int rc = -ENOMEM; + + path = kobject_get_path(kobj, gfp_mask); + if (!path) + return -ENOMEM; + + signal = action_to_string(action); + if (!signal) + return -EINVAL; + + if (attr) { + len = strlen(path); + len += strlen(attr->name) + 2; + attrpath = kmalloc(len, gfp_mask); + if (!attrpath) + goto exit; + sprintf(attrpath, "%s/%s", path, attr->name); + rc = send_uevent(signal, attrpath, NULL, gfp_mask); + kfree(attrpath); + } else + rc = send_uevent(signal, path, NULL, gfp_mask); + +exit: + kfree(path); + return rc; +} + +/** + * kobject_uevent - notify userspace by sending event through netlink socket + * + * @signal: signal name + * @kobj: struct kobject that the event is happening to + * @attr: optional struct attribute the event belongs to + */ +int kobject_uevent(struct kobject *kobj, enum kobject_action action, + struct attribute *attr) +{ + return do_kobject_uevent(kobj, action, attr, GFP_KERNEL); +} +EXPORT_SYMBOL_GPL(kobject_uevent); + +int kobject_uevent_atomic(struct kobject *kobj, enum kobject_action action, + struct attribute *attr) +{ + return do_kobject_uevent(kobj, action, attr, GFP_ATOMIC); +} +EXPORT_SYMBOL_GPL(kobject_uevent_atomic); + +static int __init kobject_uevent_init(void) +{ + uevent_sock = netlink_kernel_create(NETLINK_KOBJECT_UEVENT, NULL); + + if (!uevent_sock) { + printk(KERN_ERR + "kobject_uevent: unable to create netlink socket!\n"); + return -ENODEV; + } + + return 0; +} + +postcore_initcall(kobject_uevent_init); + +#else +static inline int send_uevent(const char *signal, const char *obj, + char **envp, int gfp_mask) +{ + return 0; +} + +#endif /* CONFIG_KOBJECT_UEVENT */ + + +#ifdef CONFIG_HOTPLUG +char hotplug_path[HOTPLUG_PATH_LEN] = "/sbin/hotplug"; +u64 hotplug_seqnum; +static DEFINE_SPINLOCK(sequence_lock); + +/** + * kobject_hotplug - notify userspace by executing /sbin/hotplug + * + * @action: action that is happening (usually "ADD" or "REMOVE") + * @kobj: struct kobject that the action is happening to + */ +void kobject_hotplug(struct kobject *kobj, enum kobject_action action) +{ + char *argv [3]; + char **envp = NULL; + char *buffer = NULL; + char *seq_buff; + char *scratch; + int i = 0; + int retval; + char *kobj_path = NULL; + char *name = NULL; + char *action_string; + u64 seq; + struct kobject *top_kobj = kobj; + struct kset *kset; + static struct kset_hotplug_ops null_hotplug_ops; + struct kset_hotplug_ops *hotplug_ops = &null_hotplug_ops; + + /* If this kobj does not belong to a kset, + try to find a parent that does. */ + if (!top_kobj->kset && top_kobj->parent) { + do { + top_kobj = top_kobj->parent; + } while (!top_kobj->kset && top_kobj->parent); + } + + if (top_kobj->kset) + kset = top_kobj->kset; + else + return; + + if (kset->hotplug_ops) + hotplug_ops = kset->hotplug_ops; + + /* If the kset has a filter operation, call it. + Skip the event, if the filter returns zero. */ + if (hotplug_ops->filter) { + if (!hotplug_ops->filter(kset, kobj)) + return; + } + + pr_debug ("%s\n", __FUNCTION__); + + action_string = action_to_string(action); + if (!action_string) + return; + + envp = kmalloc(NUM_ENVP * sizeof (char *), GFP_KERNEL); + if (!envp) + return; + memset (envp, 0x00, NUM_ENVP * sizeof (char *)); + + buffer = kmalloc(BUFFER_SIZE, GFP_KERNEL); + if (!buffer) + goto exit; + + if (hotplug_ops->name) + name = hotplug_ops->name(kset, kobj); + if (name == NULL) + name = kset->kobj.name; + + argv [0] = hotplug_path; + argv [1] = name; + argv [2] = NULL; + + /* minimal command environment */ + envp [i++] = "HOME=/"; + envp [i++] = "PATH=/sbin:/bin:/usr/sbin:/usr/bin"; + + scratch = buffer; + + envp [i++] = scratch; + scratch += sprintf(scratch, "ACTION=%s", action_string) + 1; + + kobj_path = kobject_get_path(kobj, GFP_KERNEL); + if (!kobj_path) + goto exit; + + envp [i++] = scratch; + scratch += sprintf (scratch, "DEVPATH=%s", kobj_path) + 1; + + envp [i++] = scratch; + scratch += sprintf(scratch, "SUBSYSTEM=%s", name) + 1; + + /* reserve space for the sequence, + * put the real one in after the hotplug call */ + envp[i++] = seq_buff = scratch; + scratch += strlen("SEQNUM=18446744073709551616") + 1; + + if (hotplug_ops->hotplug) { + /* have the kset specific function add its stuff */ + retval = hotplug_ops->hotplug (kset, kobj, + &envp[i], NUM_ENVP - i, scratch, + BUFFER_SIZE - (scratch - buffer)); + if (retval) { + pr_debug ("%s - hotplug() returned %d\n", + __FUNCTION__, retval); + goto exit; + } + } + + spin_lock(&sequence_lock); + seq = ++hotplug_seqnum; + spin_unlock(&sequence_lock); + sprintf(seq_buff, "SEQNUM=%llu", (unsigned long long)seq); + + pr_debug ("%s: %s %s seq=%llu %s %s %s %s %s\n", + __FUNCTION__, argv[0], argv[1], (unsigned long long)seq, + envp[0], envp[1], envp[2], envp[3], envp[4]); + + send_uevent(action_string, kobj_path, envp, GFP_KERNEL); + + if (!hotplug_path[0]) + goto exit; + + retval = call_usermodehelper (argv[0], argv, envp, 0); + if (retval) + pr_debug ("%s - call_usermodehelper returned %d\n", + __FUNCTION__, retval); + +exit: + kfree(kobj_path); + kfree(buffer); + kfree(envp); + return; +} +EXPORT_SYMBOL(kobject_hotplug); + +/** + * add_hotplug_env_var - helper for creating hotplug environment variables + * @envp: Pointer to table of environment variables, as passed into + * hotplug() method. + * @num_envp: Number of environment variable slots available, as + * passed into hotplug() method. + * @cur_index: Pointer to current index into @envp. It should be + * initialized to 0 before the first call to add_hotplug_env_var(), + * and will be incremented on success. + * @buffer: Pointer to buffer for environment variables, as passed + * into hotplug() method. + * @buffer_size: Length of @buffer, as passed into hotplug() method. + * @cur_len: Pointer to current length of space used in @buffer. + * Should be initialized to 0 before the first call to + * add_hotplug_env_var(), and will be incremented on success. + * @format: Format for creating environment variable (of the form + * "XXX=%x") for snprintf(). + * + * Returns 0 if environment variable was added successfully or -ENOMEM + * if no space was available. + */ +int add_hotplug_env_var(char **envp, int num_envp, int *cur_index, + char *buffer, int buffer_size, int *cur_len, + const char *format, ...) +{ + va_list args; + + /* + * We check against num_envp - 1 to make sure there is at + * least one slot left after we return, since the hotplug + * method needs to set the last slot to NULL. + */ + if (*cur_index >= num_envp - 1) + return -ENOMEM; + + envp[*cur_index] = buffer + *cur_len; + + va_start(args, format); + *cur_len += vsnprintf(envp[*cur_index], + max(buffer_size - *cur_len, 0), + format, args) + 1; + va_end(args); + + if (*cur_len > buffer_size) + return -ENOMEM; + + (*cur_index)++; + return 0; +} +EXPORT_SYMBOL(add_hotplug_env_var); + +#endif /* CONFIG_HOTPLUG */ diff --git a/lib/kref.c b/lib/kref.c new file mode 100644 index 00000000000..0d07cc31c81 --- /dev/null +++ b/lib/kref.c @@ -0,0 +1,64 @@ +/* + * kref.c - library routines for handling generic reference counted objects + * + * Copyright (C) 2004 Greg Kroah-Hartman <greg@kroah.com> + * Copyright (C) 2004 IBM Corp. + * + * based on lib/kobject.c which was: + * Copyright (C) 2002-2003 Patrick Mochel <mochel@osdl.org> + * + * This file is released under the GPLv2. + * + */ + +#include <linux/kref.h> +#include <linux/module.h> + +/** + * kref_init - initialize object. + * @kref: object in question. + */ +void kref_init(struct kref *kref) +{ + atomic_set(&kref->refcount,1); +} + +/** + * kref_get - increment refcount for object. + * @kref: object. + */ +void kref_get(struct kref *kref) +{ + WARN_ON(!atomic_read(&kref->refcount)); + atomic_inc(&kref->refcount); +} + +/** + * kref_put - decrement refcount for object. + * @kref: object. + * @release: pointer to the function that will clean up the object when the + * last reference to the object is released. + * This pointer is required, and it is not acceptable to pass kfree + * in as this function. + * + * Decrement the refcount, and if 0, call release(). + * Return 1 if the object was removed, otherwise return 0. Beware, if this + * function returns 0, you still can not count on the kref from remaining in + * memory. Only use the return value if you want to see if the kref is now + * gone, not present. + */ +int kref_put(struct kref *kref, void (*release)(struct kref *kref)) +{ + WARN_ON(release == NULL); + WARN_ON(release == (void (*)(struct kref *))kfree); + + if (atomic_dec_and_test(&kref->refcount)) { + release(kref); + return 1; + } + return 0; +} + +EXPORT_SYMBOL(kref_init); +EXPORT_SYMBOL(kref_get); +EXPORT_SYMBOL(kref_put); diff --git a/lib/libcrc32c.c b/lib/libcrc32c.c new file mode 100644 index 00000000000..52b6dc144ce --- /dev/null +++ b/lib/libcrc32c.c @@ -0,0 +1,200 @@ +/* + * CRC32C + *@Article{castagnoli-crc, + * author = { Guy Castagnoli and Stefan Braeuer and Martin Herrman}, + * title = {{Optimization of Cyclic Redundancy-Check Codes with 24 + * and 32 Parity Bits}}, + * journal = IEEE Transactions on Communication, + * year = {1993}, + * volume = {41}, + * number = {6}, + * pages = {}, + * month = {June}, + *} + * Used by the iSCSI driver, possibly others, and derived from the + * the iscsi-crc.c module of the linux-iscsi driver at + * http://linux-iscsi.sourceforge.net. + * + * Following the example of lib/crc32, this function is intended to be + * flexible and useful for all users. Modules that currently have their + * own crc32c, but hopefully may be able to use this one are: + * net/sctp (please add all your doco to here if you change to + * use this one!) + * <endoflist> + * + * Copyright (c) 2004 Cisco Systems, Inc. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the Free + * Software Foundation; either version 2 of the License, or (at your option) + * any later version. + * + */ +#include <linux/crc32c.h> +#include <linux/compiler.h> +#include <linux/module.h> +#include <asm/byteorder.h> + +MODULE_AUTHOR("Clay Haapala <chaapala@cisco.com>"); +MODULE_DESCRIPTION("CRC32c (Castagnoli) calculations"); +MODULE_LICENSE("GPL"); + +#define CRC32C_POLY_BE 0x1EDC6F41 +#define CRC32C_POLY_LE 0x82F63B78 + +#ifndef CRC_LE_BITS +# define CRC_LE_BITS 8 +#endif + + +/* + * Haven't generated a big-endian table yet, but the bit-wise version + * should at least work. + */ +#if defined CRC_BE_BITS && CRC_BE_BITS != 1 +#undef CRC_BE_BITS +#endif +#ifndef CRC_BE_BITS +# define CRC_BE_BITS 1 +#endif + +EXPORT_SYMBOL(crc32c_le); + +#if CRC_LE_BITS == 1 +/* + * Compute things bit-wise, as done in crc32.c. We could share the tight + * loop below with crc32 and vary the POLY if we don't find value in terms + * of space and maintainability in keeping the two modules separate. + */ +u32 __attribute_pure__ +crc32c_le(u32 crc, unsigned char const *p, size_t len) +{ + int i; + while (len--) { + crc ^= *p++; + for (i = 0; i < 8; i++) + crc = (crc >> 1) ^ ((crc & 1) ? CRC32C_POLY_LE : 0); + } + return crc; +} +#else + +/* + * This is the CRC-32C table + * Generated with: + * width = 32 bits + * poly = 0x1EDC6F41 + * reflect input bytes = true + * reflect output bytes = true + */ + +static u32 crc32c_table[256] = { + 0x00000000L, 0xF26B8303L, 0xE13B70F7L, 0x1350F3F4L, + 0xC79A971FL, 0x35F1141CL, 0x26A1E7E8L, 0xD4CA64EBL, + 0x8AD958CFL, 0x78B2DBCCL, 0x6BE22838L, 0x9989AB3BL, + 0x4D43CFD0L, 0xBF284CD3L, 0xAC78BF27L, 0x5E133C24L, + 0x105EC76FL, 0xE235446CL, 0xF165B798L, 0x030E349BL, + 0xD7C45070L, 0x25AFD373L, 0x36FF2087L, 0xC494A384L, + 0x9A879FA0L, 0x68EC1CA3L, 0x7BBCEF57L, 0x89D76C54L, + 0x5D1D08BFL, 0xAF768BBCL, 0xBC267848L, 0x4E4DFB4BL, + 0x20BD8EDEL, 0xD2D60DDDL, 0xC186FE29L, 0x33ED7D2AL, + 0xE72719C1L, 0x154C9AC2L, 0x061C6936L, 0xF477EA35L, + 0xAA64D611L, 0x580F5512L, 0x4B5FA6E6L, 0xB93425E5L, + 0x6DFE410EL, 0x9F95C20DL, 0x8CC531F9L, 0x7EAEB2FAL, + 0x30E349B1L, 0xC288CAB2L, 0xD1D83946L, 0x23B3BA45L, + 0xF779DEAEL, 0x05125DADL, 0x1642AE59L, 0xE4292D5AL, + 0xBA3A117EL, 0x4851927DL, 0x5B016189L, 0xA96AE28AL, + 0x7DA08661L, 0x8FCB0562L, 0x9C9BF696L, 0x6EF07595L, + 0x417B1DBCL, 0xB3109EBFL, 0xA0406D4BL, 0x522BEE48L, + 0x86E18AA3L, 0x748A09A0L, 0x67DAFA54L, 0x95B17957L, + 0xCBA24573L, 0x39C9C670L, 0x2A993584L, 0xD8F2B687L, + 0x0C38D26CL, 0xFE53516FL, 0xED03A29BL, 0x1F682198L, + 0x5125DAD3L, 0xA34E59D0L, 0xB01EAA24L, 0x42752927L, + 0x96BF4DCCL, 0x64D4CECFL, 0x77843D3BL, 0x85EFBE38L, + 0xDBFC821CL, 0x2997011FL, 0x3AC7F2EBL, 0xC8AC71E8L, + 0x1C661503L, 0xEE0D9600L, 0xFD5D65F4L, 0x0F36E6F7L, + 0x61C69362L, 0x93AD1061L, 0x80FDE395L, 0x72966096L, + 0xA65C047DL, 0x5437877EL, 0x4767748AL, 0xB50CF789L, + 0xEB1FCBADL, 0x197448AEL, 0x0A24BB5AL, 0xF84F3859L, + 0x2C855CB2L, 0xDEEEDFB1L, 0xCDBE2C45L, 0x3FD5AF46L, + 0x7198540DL, 0x83F3D70EL, 0x90A324FAL, 0x62C8A7F9L, + 0xB602C312L, 0x44694011L, 0x5739B3E5L, 0xA55230E6L, + 0xFB410CC2L, 0x092A8FC1L, 0x1A7A7C35L, 0xE811FF36L, + 0x3CDB9BDDL, 0xCEB018DEL, 0xDDE0EB2AL, 0x2F8B6829L, + 0x82F63B78L, 0x709DB87BL, 0x63CD4B8FL, 0x91A6C88CL, + 0x456CAC67L, 0xB7072F64L, 0xA457DC90L, 0x563C5F93L, + 0x082F63B7L, 0xFA44E0B4L, 0xE9141340L, 0x1B7F9043L, + 0xCFB5F4A8L, 0x3DDE77ABL, 0x2E8E845FL, 0xDCE5075CL, + 0x92A8FC17L, 0x60C37F14L, 0x73938CE0L, 0x81F80FE3L, + 0x55326B08L, 0xA759E80BL, 0xB4091BFFL, 0x466298FCL, + 0x1871A4D8L, 0xEA1A27DBL, 0xF94AD42FL, 0x0B21572CL, + 0xDFEB33C7L, 0x2D80B0C4L, 0x3ED04330L, 0xCCBBC033L, + 0xA24BB5A6L, 0x502036A5L, 0x4370C551L, 0xB11B4652L, + 0x65D122B9L, 0x97BAA1BAL, 0x84EA524EL, 0x7681D14DL, + 0x2892ED69L, 0xDAF96E6AL, 0xC9A99D9EL, 0x3BC21E9DL, + 0xEF087A76L, 0x1D63F975L, 0x0E330A81L, 0xFC588982L, + 0xB21572C9L, 0x407EF1CAL, 0x532E023EL, 0xA145813DL, + 0x758FE5D6L, 0x87E466D5L, 0x94B49521L, 0x66DF1622L, + 0x38CC2A06L, 0xCAA7A905L, 0xD9F75AF1L, 0x2B9CD9F2L, + 0xFF56BD19L, 0x0D3D3E1AL, 0x1E6DCDEEL, 0xEC064EEDL, + 0xC38D26C4L, 0x31E6A5C7L, 0x22B65633L, 0xD0DDD530L, + 0x0417B1DBL, 0xF67C32D8L, 0xE52CC12CL, 0x1747422FL, + 0x49547E0BL, 0xBB3FFD08L, 0xA86F0EFCL, 0x5A048DFFL, + 0x8ECEE914L, 0x7CA56A17L, 0x6FF599E3L, 0x9D9E1AE0L, + 0xD3D3E1ABL, 0x21B862A8L, 0x32E8915CL, 0xC083125FL, + 0x144976B4L, 0xE622F5B7L, 0xF5720643L, 0x07198540L, + 0x590AB964L, 0xAB613A67L, 0xB831C993L, 0x4A5A4A90L, + 0x9E902E7BL, 0x6CFBAD78L, 0x7FAB5E8CL, 0x8DC0DD8FL, + 0xE330A81AL, 0x115B2B19L, 0x020BD8EDL, 0xF0605BEEL, + 0x24AA3F05L, 0xD6C1BC06L, 0xC5914FF2L, 0x37FACCF1L, + 0x69E9F0D5L, 0x9B8273D6L, 0x88D28022L, 0x7AB90321L, + 0xAE7367CAL, 0x5C18E4C9L, 0x4F48173DL, 0xBD23943EL, + 0xF36E6F75L, 0x0105EC76L, 0x12551F82L, 0xE03E9C81L, + 0x34F4F86AL, 0xC69F7B69L, 0xD5CF889DL, 0x27A40B9EL, + 0x79B737BAL, 0x8BDCB4B9L, 0x988C474DL, 0x6AE7C44EL, + 0xBE2DA0A5L, 0x4C4623A6L, 0x5F16D052L, 0xAD7D5351L +}; + +/* + * Steps through buffer one byte at at time, calculates reflected + * crc using table. + */ + +u32 __attribute_pure__ +crc32c_le(u32 seed, unsigned char const *data, size_t length) +{ + u32 crc = __cpu_to_le32(seed); + + while (length--) + crc = + crc32c_table[(crc ^ *data++) & 0xFFL] ^ (crc >> 8); + + return __le32_to_cpu(crc); +} + +#endif /* CRC_LE_BITS == 8 */ + +EXPORT_SYMBOL(crc32c_be); + +#if CRC_BE_BITS == 1 +u32 __attribute_pure__ +crc32c_be(u32 crc, unsigned char const *p, size_t len) +{ + int i; + while (len--) { + crc ^= *p++ << 24; + for (i = 0; i < 8; i++) + crc = + (crc << 1) ^ ((crc & 0x80000000) ? CRC32C_POLY_BE : + 0); + } + return crc; +} +#endif + +/* + * Unit test + * + * A small unit test suite is implemented as part of the crypto suite. + * Select CRYPTO_CRC32C and use the tcrypt module to run the tests. + */ diff --git a/lib/parser.c b/lib/parser.c new file mode 100644 index 00000000000..7ad2a48abc5 --- /dev/null +++ b/lib/parser.c @@ -0,0 +1,220 @@ +/* + * lib/parser.c - simple parser for mount, etc. options. + * + * This source code is licensed under the GNU General Public License, + * Version 2. See the file COPYING for more details. + */ + +#include <linux/ctype.h> +#include <linux/module.h> +#include <linux/parser.h> +#include <linux/slab.h> +#include <linux/string.h> + +/** + * match_one: - Determines if a string matches a simple pattern + * @s: the string to examine for presense of the pattern + * @p: the string containing the pattern + * @args: array of %MAX_OPT_ARGS &substring_t elements. Used to return match + * locations. + * + * Description: Determines if the pattern @p is present in string @s. Can only + * match extremely simple token=arg style patterns. If the pattern is found, + * the location(s) of the arguments will be returned in the @args array. + */ +static int match_one(char *s, char *p, substring_t args[]) +{ + char *meta; + int argc = 0; + + if (!p) + return 1; + + while(1) { + int len = -1; + meta = strchr(p, '%'); + if (!meta) + return strcmp(p, s) == 0; + + if (strncmp(p, s, meta-p)) + return 0; + + s += meta - p; + p = meta + 1; + + if (isdigit(*p)) + len = simple_strtoul(p, &p, 10); + else if (*p == '%') { + if (*s++ != '%') + return 0; + p++; + continue; + } + + if (argc >= MAX_OPT_ARGS) + return 0; + + args[argc].from = s; + switch (*p++) { + case 's': + if (strlen(s) == 0) + return 0; + else if (len == -1 || len > strlen(s)) + len = strlen(s); + args[argc].to = s + len; + break; + case 'd': + simple_strtol(s, &args[argc].to, 0); + goto num; + case 'u': + simple_strtoul(s, &args[argc].to, 0); + goto num; + case 'o': + simple_strtoul(s, &args[argc].to, 8); + goto num; + case 'x': + simple_strtoul(s, &args[argc].to, 16); + num: + if (args[argc].to == args[argc].from) + return 0; + break; + default: + return 0; + } + s = args[argc].to; + argc++; + } +} + +/** + * match_token: - Find a token (and optional args) in a string + * @s: the string to examine for token/argument pairs + * @table: match_table_t describing the set of allowed option tokens and the + * arguments that may be associated with them. Must be terminated with a + * &struct match_token whose pattern is set to the NULL pointer. + * @args: array of %MAX_OPT_ARGS &substring_t elements. Used to return match + * locations. + * + * Description: Detects which if any of a set of token strings has been passed + * to it. Tokens can include up to MAX_OPT_ARGS instances of basic c-style + * format identifiers which will be taken into account when matching the + * tokens, and whose locations will be returned in the @args array. + */ +int match_token(char *s, match_table_t table, substring_t args[]) +{ + struct match_token *p; + + for (p = table; !match_one(s, p->pattern, args) ; p++) + ; + + return p->token; +} + +/** + * match_number: scan a number in the given base from a substring_t + * @s: substring to be scanned + * @result: resulting integer on success + * @base: base to use when converting string + * + * Description: Given a &substring_t and a base, attempts to parse the substring + * as a number in that base. On success, sets @result to the integer represented + * by the string and returns 0. Returns either -ENOMEM or -EINVAL on failure. + */ +static int match_number(substring_t *s, int *result, int base) +{ + char *endp; + char *buf; + int ret; + + buf = kmalloc(s->to - s->from + 1, GFP_KERNEL); + if (!buf) + return -ENOMEM; + memcpy(buf, s->from, s->to - s->from); + buf[s->to - s->from] = '\0'; + *result = simple_strtol(buf, &endp, base); + ret = 0; + if (endp == buf) + ret = -EINVAL; + kfree(buf); + return ret; +} + +/** + * match_int: - scan a decimal representation of an integer from a substring_t + * @s: substring_t to be scanned + * @result: resulting integer on success + * + * Description: Attempts to parse the &substring_t @s as a decimal integer. On + * success, sets @result to the integer represented by the string and returns 0. + * Returns either -ENOMEM or -EINVAL on failure. + */ +int match_int(substring_t *s, int *result) +{ + return match_number(s, result, 0); +} + +/** + * match_octal: - scan an octal representation of an integer from a substring_t + * @s: substring_t to be scanned + * @result: resulting integer on success + * + * Description: Attempts to parse the &substring_t @s as an octal integer. On + * success, sets @result to the integer represented by the string and returns + * 0. Returns either -ENOMEM or -EINVAL on failure. + */ +int match_octal(substring_t *s, int *result) +{ + return match_number(s, result, 8); +} + +/** + * match_hex: - scan a hex representation of an integer from a substring_t + * @s: substring_t to be scanned + * @result: resulting integer on success + * + * Description: Attempts to parse the &substring_t @s as a hexadecimal integer. + * On success, sets @result to the integer represented by the string and + * returns 0. Returns either -ENOMEM or -EINVAL on failure. + */ +int match_hex(substring_t *s, int *result) +{ + return match_number(s, result, 16); +} + +/** + * match_strcpy: - copies the characters from a substring_t to a string + * @to: string to copy characters to. + * @s: &substring_t to copy + * + * Description: Copies the set of characters represented by the given + * &substring_t @s to the c-style string @to. Caller guarantees that @to is + * large enough to hold the characters of @s. + */ +void match_strcpy(char *to, substring_t *s) +{ + memcpy(to, s->from, s->to - s->from); + to[s->to - s->from] = '\0'; +} + +/** + * match_strdup: - allocate a new string with the contents of a substring_t + * @s: &substring_t to copy + * + * Description: Allocates and returns a string filled with the contents of + * the &substring_t @s. The caller is responsible for freeing the returned + * string with kfree(). + */ +char *match_strdup(substring_t *s) +{ + char *p = kmalloc(s->to - s->from + 1, GFP_KERNEL); + if (p) + match_strcpy(p, s); + return p; +} + +EXPORT_SYMBOL(match_token); +EXPORT_SYMBOL(match_int); +EXPORT_SYMBOL(match_octal); +EXPORT_SYMBOL(match_hex); +EXPORT_SYMBOL(match_strcpy); +EXPORT_SYMBOL(match_strdup); diff --git a/lib/prio_tree.c b/lib/prio_tree.c new file mode 100644 index 00000000000..ccfd850b0de --- /dev/null +++ b/lib/prio_tree.c @@ -0,0 +1,484 @@ +/* + * lib/prio_tree.c - priority search tree + * + * Copyright (C) 2004, Rajesh Venkatasubramanian <vrajesh@umich.edu> + * + * This file is released under the GPL v2. + * + * Based on the radix priority search tree proposed by Edward M. McCreight + * SIAM Journal of Computing, vol. 14, no.2, pages 257-276, May 1985 + * + * 02Feb2004 Initial version + */ + +#include <linux/init.h> +#include <linux/mm.h> +#include <linux/prio_tree.h> + +/* + * A clever mix of heap and radix trees forms a radix priority search tree (PST) + * which is useful for storing intervals, e.g, we can consider a vma as a closed + * interval of file pages [offset_begin, offset_end], and store all vmas that + * map a file in a PST. Then, using the PST, we can answer a stabbing query, + * i.e., selecting a set of stored intervals (vmas) that overlap with (map) a + * given input interval X (a set of consecutive file pages), in "O(log n + m)" + * time where 'log n' is the height of the PST, and 'm' is the number of stored + * intervals (vmas) that overlap (map) with the input interval X (the set of + * consecutive file pages). + * + * In our implementation, we store closed intervals of the form [radix_index, + * heap_index]. We assume that always radix_index <= heap_index. McCreight's PST + * is designed for storing intervals with unique radix indices, i.e., each + * interval have different radix_index. However, this limitation can be easily + * overcome by using the size, i.e., heap_index - radix_index, as part of the + * index, so we index the tree using [(radix_index,size), heap_index]. + * + * When the above-mentioned indexing scheme is used, theoretically, in a 32 bit + * machine, the maximum height of a PST can be 64. We can use a balanced version + * of the priority search tree to optimize the tree height, but the balanced + * tree proposed by McCreight is too complex and memory-hungry for our purpose. + */ + +/* + * The following macros are used for implementing prio_tree for i_mmap + */ + +#define RADIX_INDEX(vma) ((vma)->vm_pgoff) +#define VMA_SIZE(vma) (((vma)->vm_end - (vma)->vm_start) >> PAGE_SHIFT) +/* avoid overflow */ +#define HEAP_INDEX(vma) ((vma)->vm_pgoff + (VMA_SIZE(vma) - 1)) + + +static void get_index(const struct prio_tree_root *root, + const struct prio_tree_node *node, + unsigned long *radix, unsigned long *heap) +{ + if (root->raw) { + struct vm_area_struct *vma = prio_tree_entry( + node, struct vm_area_struct, shared.prio_tree_node); + + *radix = RADIX_INDEX(vma); + *heap = HEAP_INDEX(vma); + } + else { + *radix = node->start; + *heap = node->last; + } +} + +static unsigned long index_bits_to_maxindex[BITS_PER_LONG]; + +void __init prio_tree_init(void) +{ + unsigned int i; + + for (i = 0; i < ARRAY_SIZE(index_bits_to_maxindex) - 1; i++) + index_bits_to_maxindex[i] = (1UL << (i + 1)) - 1; + index_bits_to_maxindex[ARRAY_SIZE(index_bits_to_maxindex) - 1] = ~0UL; +} + +/* + * Maximum heap_index that can be stored in a PST with index_bits bits + */ +static inline unsigned long prio_tree_maxindex(unsigned int bits) +{ + return index_bits_to_maxindex[bits - 1]; +} + +/* + * Extend a priority search tree so that it can store a node with heap_index + * max_heap_index. In the worst case, this algorithm takes O((log n)^2). + * However, this function is used rarely and the common case performance is + * not bad. + */ +static struct prio_tree_node *prio_tree_expand(struct prio_tree_root *root, + struct prio_tree_node *node, unsigned long max_heap_index) +{ + struct prio_tree_node *first = NULL, *prev, *last = NULL; + + if (max_heap_index > prio_tree_maxindex(root->index_bits)) + root->index_bits++; + + while (max_heap_index > prio_tree_maxindex(root->index_bits)) { + root->index_bits++; + + if (prio_tree_empty(root)) + continue; + + if (first == NULL) { + first = root->prio_tree_node; + prio_tree_remove(root, root->prio_tree_node); + INIT_PRIO_TREE_NODE(first); + last = first; + } else { + prev = last; + last = root->prio_tree_node; + prio_tree_remove(root, root->prio_tree_node); + INIT_PRIO_TREE_NODE(last); + prev->left = last; + last->parent = prev; + } + } + + INIT_PRIO_TREE_NODE(node); + + if (first) { + node->left = first; + first->parent = node; + } else + last = node; + + if (!prio_tree_empty(root)) { + last->left = root->prio_tree_node; + last->left->parent = last; + } + + root->prio_tree_node = node; + return node; +} + +/* + * Replace a prio_tree_node with a new node and return the old node + */ +struct prio_tree_node *prio_tree_replace(struct prio_tree_root *root, + struct prio_tree_node *old, struct prio_tree_node *node) +{ + INIT_PRIO_TREE_NODE(node); + + if (prio_tree_root(old)) { + BUG_ON(root->prio_tree_node != old); + /* + * We can reduce root->index_bits here. However, it is complex + * and does not help much to improve performance (IMO). + */ + node->parent = node; + root->prio_tree_node = node; + } else { + node->parent = old->parent; + if (old->parent->left == old) + old->parent->left = node; + else + old->parent->right = node; + } + + if (!prio_tree_left_empty(old)) { + node->left = old->left; + old->left->parent = node; + } + + if (!prio_tree_right_empty(old)) { + node->right = old->right; + old->right->parent = node; + } + + return old; +} + +/* + * Insert a prio_tree_node @node into a radix priority search tree @root. The + * algorithm typically takes O(log n) time where 'log n' is the number of bits + * required to represent the maximum heap_index. In the worst case, the algo + * can take O((log n)^2) - check prio_tree_expand. + * + * If a prior node with same radix_index and heap_index is already found in + * the tree, then returns the address of the prior node. Otherwise, inserts + * @node into the tree and returns @node. + */ +struct prio_tree_node *prio_tree_insert(struct prio_tree_root *root, + struct prio_tree_node *node) +{ + struct prio_tree_node *cur, *res = node; + unsigned long radix_index, heap_index; + unsigned long r_index, h_index, index, mask; + int size_flag = 0; + + get_index(root, node, &radix_index, &heap_index); + + if (prio_tree_empty(root) || + heap_index > prio_tree_maxindex(root->index_bits)) + return prio_tree_expand(root, node, heap_index); + + cur = root->prio_tree_node; + mask = 1UL << (root->index_bits - 1); + + while (mask) { + get_index(root, cur, &r_index, &h_index); + + if (r_index == radix_index && h_index == heap_index) + return cur; + + if (h_index < heap_index || + (h_index == heap_index && r_index > radix_index)) { + struct prio_tree_node *tmp = node; + node = prio_tree_replace(root, cur, node); + cur = tmp; + /* swap indices */ + index = r_index; + r_index = radix_index; + radix_index = index; + index = h_index; + h_index = heap_index; + heap_index = index; + } + + if (size_flag) + index = heap_index - radix_index; + else + index = radix_index; + + if (index & mask) { + if (prio_tree_right_empty(cur)) { + INIT_PRIO_TREE_NODE(node); + cur->right = node; + node->parent = cur; + return res; + } else + cur = cur->right; + } else { + if (prio_tree_left_empty(cur)) { + INIT_PRIO_TREE_NODE(node); + cur->left = node; + node->parent = cur; + return res; + } else + cur = cur->left; + } + + mask >>= 1; + + if (!mask) { + mask = 1UL << (BITS_PER_LONG - 1); + size_flag = 1; + } + } + /* Should not reach here */ + BUG(); + return NULL; +} + +/* + * Remove a prio_tree_node @node from a radix priority search tree @root. The + * algorithm takes O(log n) time where 'log n' is the number of bits required + * to represent the maximum heap_index. + */ +void prio_tree_remove(struct prio_tree_root *root, struct prio_tree_node *node) +{ + struct prio_tree_node *cur; + unsigned long r_index, h_index_right, h_index_left; + + cur = node; + + while (!prio_tree_left_empty(cur) || !prio_tree_right_empty(cur)) { + if (!prio_tree_left_empty(cur)) + get_index(root, cur->left, &r_index, &h_index_left); + else { + cur = cur->right; + continue; + } + + if (!prio_tree_right_empty(cur)) + get_index(root, cur->right, &r_index, &h_index_right); + else { + cur = cur->left; + continue; + } + + /* both h_index_left and h_index_right cannot be 0 */ + if (h_index_left >= h_index_right) + cur = cur->left; + else + cur = cur->right; + } + + if (prio_tree_root(cur)) { + BUG_ON(root->prio_tree_node != cur); + __INIT_PRIO_TREE_ROOT(root, root->raw); + return; + } + + if (cur->parent->right == cur) + cur->parent->right = cur->parent; + else + cur->parent->left = cur->parent; + + while (cur != node) + cur = prio_tree_replace(root, cur->parent, cur); +} + +/* + * Following functions help to enumerate all prio_tree_nodes in the tree that + * overlap with the input interval X [radix_index, heap_index]. The enumeration + * takes O(log n + m) time where 'log n' is the height of the tree (which is + * proportional to # of bits required to represent the maximum heap_index) and + * 'm' is the number of prio_tree_nodes that overlap the interval X. + */ + +static struct prio_tree_node *prio_tree_left(struct prio_tree_iter *iter, + unsigned long *r_index, unsigned long *h_index) +{ + if (prio_tree_left_empty(iter->cur)) + return NULL; + + get_index(iter->root, iter->cur->left, r_index, h_index); + + if (iter->r_index <= *h_index) { + iter->cur = iter->cur->left; + iter->mask >>= 1; + if (iter->mask) { + if (iter->size_level) + iter->size_level++; + } else { + if (iter->size_level) { + BUG_ON(!prio_tree_left_empty(iter->cur)); + BUG_ON(!prio_tree_right_empty(iter->cur)); + iter->size_level++; + iter->mask = ULONG_MAX; + } else { + iter->size_level = 1; + iter->mask = 1UL << (BITS_PER_LONG - 1); + } + } + return iter->cur; + } + + return NULL; +} + +static struct prio_tree_node *prio_tree_right(struct prio_tree_iter *iter, + unsigned long *r_index, unsigned long *h_index) +{ + unsigned long value; + + if (prio_tree_right_empty(iter->cur)) + return NULL; + + if (iter->size_level) + value = iter->value; + else + value = iter->value | iter->mask; + + if (iter->h_index < value) + return NULL; + + get_index(iter->root, iter->cur->right, r_index, h_index); + + if (iter->r_index <= *h_index) { + iter->cur = iter->cur->right; + iter->mask >>= 1; + iter->value = value; + if (iter->mask) { + if (iter->size_level) + iter->size_level++; + } else { + if (iter->size_level) { + BUG_ON(!prio_tree_left_empty(iter->cur)); + BUG_ON(!prio_tree_right_empty(iter->cur)); + iter->size_level++; + iter->mask = ULONG_MAX; + } else { + iter->size_level = 1; + iter->mask = 1UL << (BITS_PER_LONG - 1); + } + } + return iter->cur; + } + + return NULL; +} + +static struct prio_tree_node *prio_tree_parent(struct prio_tree_iter *iter) +{ + iter->cur = iter->cur->parent; + if (iter->mask == ULONG_MAX) + iter->mask = 1UL; + else if (iter->size_level == 1) + iter->mask = 1UL; + else + iter->mask <<= 1; + if (iter->size_level) + iter->size_level--; + if (!iter->size_level && (iter->value & iter->mask)) + iter->value ^= iter->mask; + return iter->cur; +} + +static inline int overlap(struct prio_tree_iter *iter, + unsigned long r_index, unsigned long h_index) +{ + return iter->h_index >= r_index && iter->r_index <= h_index; +} + +/* + * prio_tree_first: + * + * Get the first prio_tree_node that overlaps with the interval [radix_index, + * heap_index]. Note that always radix_index <= heap_index. We do a pre-order + * traversal of the tree. + */ +static struct prio_tree_node *prio_tree_first(struct prio_tree_iter *iter) +{ + struct prio_tree_root *root; + unsigned long r_index, h_index; + + INIT_PRIO_TREE_ITER(iter); + + root = iter->root; + if (prio_tree_empty(root)) + return NULL; + + get_index(root, root->prio_tree_node, &r_index, &h_index); + + if (iter->r_index > h_index) + return NULL; + + iter->mask = 1UL << (root->index_bits - 1); + iter->cur = root->prio_tree_node; + + while (1) { + if (overlap(iter, r_index, h_index)) + return iter->cur; + + if (prio_tree_left(iter, &r_index, &h_index)) + continue; + + if (prio_tree_right(iter, &r_index, &h_index)) + continue; + + break; + } + return NULL; +} + +/* + * prio_tree_next: + * + * Get the next prio_tree_node that overlaps with the input interval in iter + */ +struct prio_tree_node *prio_tree_next(struct prio_tree_iter *iter) +{ + unsigned long r_index, h_index; + + if (iter->cur == NULL) + return prio_tree_first(iter); + +repeat: + while (prio_tree_left(iter, &r_index, &h_index)) + if (overlap(iter, r_index, h_index)) + return iter->cur; + + while (!prio_tree_right(iter, &r_index, &h_index)) { + while (!prio_tree_root(iter->cur) && + iter->cur->parent->right == iter->cur) + prio_tree_parent(iter); + + if (prio_tree_root(iter->cur)) + return NULL; + + prio_tree_parent(iter); + } + + if (overlap(iter, r_index, h_index)) + return iter->cur; + + goto repeat; +} diff --git a/lib/radix-tree.c b/lib/radix-tree.c new file mode 100644 index 00000000000..04d664377f2 --- /dev/null +++ b/lib/radix-tree.c @@ -0,0 +1,807 @@ +/* + * Copyright (C) 2001 Momchil Velikov + * Portions Copyright (C) 2001 Christoph Hellwig + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License as + * published by the Free Software Foundation; either version 2, or (at + * your option) any later version. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. + */ + +#include <linux/errno.h> +#include <linux/init.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/radix-tree.h> +#include <linux/percpu.h> +#include <linux/slab.h> +#include <linux/notifier.h> +#include <linux/cpu.h> +#include <linux/gfp.h> +#include <linux/string.h> +#include <linux/bitops.h> + + +#ifdef __KERNEL__ +#define RADIX_TREE_MAP_SHIFT 6 +#else +#define RADIX_TREE_MAP_SHIFT 3 /* For more stressful testing */ +#endif +#define RADIX_TREE_TAGS 2 + +#define RADIX_TREE_MAP_SIZE (1UL << RADIX_TREE_MAP_SHIFT) +#define RADIX_TREE_MAP_MASK (RADIX_TREE_MAP_SIZE-1) + +#define RADIX_TREE_TAG_LONGS \ + ((RADIX_TREE_MAP_SIZE + BITS_PER_LONG - 1) / BITS_PER_LONG) + +struct radix_tree_node { + unsigned int count; + void *slots[RADIX_TREE_MAP_SIZE]; + unsigned long tags[RADIX_TREE_TAGS][RADIX_TREE_TAG_LONGS]; +}; + +struct radix_tree_path { + struct radix_tree_node *node, **slot; + int offset; +}; + +#define RADIX_TREE_INDEX_BITS (8 /* CHAR_BIT */ * sizeof(unsigned long)) +#define RADIX_TREE_MAX_PATH (RADIX_TREE_INDEX_BITS/RADIX_TREE_MAP_SHIFT + 2) + +static unsigned long height_to_maxindex[RADIX_TREE_MAX_PATH]; + +/* + * Radix tree node cache. + */ +static kmem_cache_t *radix_tree_node_cachep; + +/* + * Per-cpu pool of preloaded nodes + */ +struct radix_tree_preload { + int nr; + struct radix_tree_node *nodes[RADIX_TREE_MAX_PATH]; +}; +DEFINE_PER_CPU(struct radix_tree_preload, radix_tree_preloads) = { 0, }; + +/* + * This assumes that the caller has performed appropriate preallocation, and + * that the caller has pinned this thread of control to the current CPU. + */ +static struct radix_tree_node * +radix_tree_node_alloc(struct radix_tree_root *root) +{ + struct radix_tree_node *ret; + + ret = kmem_cache_alloc(radix_tree_node_cachep, root->gfp_mask); + if (ret == NULL && !(root->gfp_mask & __GFP_WAIT)) { + struct radix_tree_preload *rtp; + + rtp = &__get_cpu_var(radix_tree_preloads); + if (rtp->nr) { + ret = rtp->nodes[rtp->nr - 1]; + rtp->nodes[rtp->nr - 1] = NULL; + rtp->nr--; + } + } + return ret; +} + +static inline void +radix_tree_node_free(struct radix_tree_node *node) +{ + kmem_cache_free(radix_tree_node_cachep, node); +} + +/* + * Load up this CPU's radix_tree_node buffer with sufficient objects to + * ensure that the addition of a single element in the tree cannot fail. On + * success, return zero, with preemption disabled. On error, return -ENOMEM + * with preemption not disabled. + */ +int radix_tree_preload(int gfp_mask) +{ + struct radix_tree_preload *rtp; + struct radix_tree_node *node; + int ret = -ENOMEM; + + preempt_disable(); + rtp = &__get_cpu_var(radix_tree_preloads); + while (rtp->nr < ARRAY_SIZE(rtp->nodes)) { + preempt_enable(); + node = kmem_cache_alloc(radix_tree_node_cachep, gfp_mask); + if (node == NULL) + goto out; + preempt_disable(); + rtp = &__get_cpu_var(radix_tree_preloads); + if (rtp->nr < ARRAY_SIZE(rtp->nodes)) + rtp->nodes[rtp->nr++] = node; + else + kmem_cache_free(radix_tree_node_cachep, node); + } + ret = 0; +out: + return ret; +} + +static inline void tag_set(struct radix_tree_node *node, int tag, int offset) +{ + if (!test_bit(offset, &node->tags[tag][0])) + __set_bit(offset, &node->tags[tag][0]); +} + +static inline void tag_clear(struct radix_tree_node *node, int tag, int offset) +{ + __clear_bit(offset, &node->tags[tag][0]); +} + +static inline int tag_get(struct radix_tree_node *node, int tag, int offset) +{ + return test_bit(offset, &node->tags[tag][0]); +} + +/* + * Return the maximum key which can be store into a + * radix tree with height HEIGHT. + */ +static inline unsigned long radix_tree_maxindex(unsigned int height) +{ + return height_to_maxindex[height]; +} + +/* + * Extend a radix tree so it can store key @index. + */ +static int radix_tree_extend(struct radix_tree_root *root, unsigned long index) +{ + struct radix_tree_node *node; + unsigned int height; + char tags[RADIX_TREE_TAGS]; + int tag; + + /* Figure out what the height should be. */ + height = root->height + 1; + while (index > radix_tree_maxindex(height)) + height++; + + if (root->rnode == NULL) { + root->height = height; + goto out; + } + + /* + * Prepare the tag status of the top-level node for propagation + * into the newly-pushed top-level node(s) + */ + for (tag = 0; tag < RADIX_TREE_TAGS; tag++) { + int idx; + + tags[tag] = 0; + for (idx = 0; idx < RADIX_TREE_TAG_LONGS; idx++) { + if (root->rnode->tags[tag][idx]) { + tags[tag] = 1; + break; + } + } + } + + do { + if (!(node = radix_tree_node_alloc(root))) + return -ENOMEM; + + /* Increase the height. */ + node->slots[0] = root->rnode; + + /* Propagate the aggregated tag info into the new root */ + for (tag = 0; tag < RADIX_TREE_TAGS; tag++) { + if (tags[tag]) + tag_set(node, tag, 0); + } + + node->count = 1; + root->rnode = node; + root->height++; + } while (height > root->height); +out: + return 0; +} + +/** + * radix_tree_insert - insert into a radix tree + * @root: radix tree root + * @index: index key + * @item: item to insert + * + * Insert an item into the radix tree at position @index. + */ +int radix_tree_insert(struct radix_tree_root *root, + unsigned long index, void *item) +{ + struct radix_tree_node *node = NULL, *tmp, **slot; + unsigned int height, shift; + int offset; + int error; + + /* Make sure the tree is high enough. */ + if ((!index && !root->rnode) || + index > radix_tree_maxindex(root->height)) { + error = radix_tree_extend(root, index); + if (error) + return error; + } + + slot = &root->rnode; + height = root->height; + shift = (height-1) * RADIX_TREE_MAP_SHIFT; + + offset = 0; /* uninitialised var warning */ + while (height > 0) { + if (*slot == NULL) { + /* Have to add a child node. */ + if (!(tmp = radix_tree_node_alloc(root))) + return -ENOMEM; + *slot = tmp; + if (node) + node->count++; + } + + /* Go a level down */ + offset = (index >> shift) & RADIX_TREE_MAP_MASK; + node = *slot; + slot = (struct radix_tree_node **)(node->slots + offset); + shift -= RADIX_TREE_MAP_SHIFT; + height--; + } + + if (*slot != NULL) + return -EEXIST; + if (node) { + node->count++; + BUG_ON(tag_get(node, 0, offset)); + BUG_ON(tag_get(node, 1, offset)); + } + + *slot = item; + return 0; +} +EXPORT_SYMBOL(radix_tree_insert); + +/** + * radix_tree_lookup - perform lookup operation on a radix tree + * @root: radix tree root + * @index: index key + * + * Lookup the item at the position @index in the radix tree @root. + */ +void *radix_tree_lookup(struct radix_tree_root *root, unsigned long index) +{ + unsigned int height, shift; + struct radix_tree_node **slot; + + height = root->height; + if (index > radix_tree_maxindex(height)) + return NULL; + + shift = (height-1) * RADIX_TREE_MAP_SHIFT; + slot = &root->rnode; + + while (height > 0) { + if (*slot == NULL) + return NULL; + + slot = (struct radix_tree_node **) + ((*slot)->slots + + ((index >> shift) & RADIX_TREE_MAP_MASK)); + shift -= RADIX_TREE_MAP_SHIFT; + height--; + } + + return *slot; +} +EXPORT_SYMBOL(radix_tree_lookup); + +/** + * radix_tree_tag_set - set a tag on a radix tree node + * @root: radix tree root + * @index: index key + * @tag: tag index + * + * Set the search tag corresponging to @index in the radix tree. From + * the root all the way down to the leaf node. + * + * Returns the address of the tagged item. Setting a tag on a not-present + * item is a bug. + */ +void *radix_tree_tag_set(struct radix_tree_root *root, + unsigned long index, int tag) +{ + unsigned int height, shift; + struct radix_tree_node **slot; + + height = root->height; + if (index > radix_tree_maxindex(height)) + return NULL; + + shift = (height - 1) * RADIX_TREE_MAP_SHIFT; + slot = &root->rnode; + + while (height > 0) { + int offset; + + offset = (index >> shift) & RADIX_TREE_MAP_MASK; + tag_set(*slot, tag, offset); + slot = (struct radix_tree_node **)((*slot)->slots + offset); + BUG_ON(*slot == NULL); + shift -= RADIX_TREE_MAP_SHIFT; + height--; + } + + return *slot; +} +EXPORT_SYMBOL(radix_tree_tag_set); + +/** + * radix_tree_tag_clear - clear a tag on a radix tree node + * @root: radix tree root + * @index: index key + * @tag: tag index + * + * Clear the search tag corresponging to @index in the radix tree. If + * this causes the leaf node to have no tags set then clear the tag in the + * next-to-leaf node, etc. + * + * Returns the address of the tagged item on success, else NULL. ie: + * has the same return value and semantics as radix_tree_lookup(). + */ +void *radix_tree_tag_clear(struct radix_tree_root *root, + unsigned long index, int tag) +{ + struct radix_tree_path path[RADIX_TREE_MAX_PATH], *pathp = path; + unsigned int height, shift; + void *ret = NULL; + + height = root->height; + if (index > radix_tree_maxindex(height)) + goto out; + + shift = (height - 1) * RADIX_TREE_MAP_SHIFT; + pathp->node = NULL; + pathp->slot = &root->rnode; + + while (height > 0) { + int offset; + + if (*pathp->slot == NULL) + goto out; + + offset = (index >> shift) & RADIX_TREE_MAP_MASK; + pathp[1].offset = offset; + pathp[1].node = *pathp[0].slot; + pathp[1].slot = (struct radix_tree_node **) + (pathp[1].node->slots + offset); + pathp++; + shift -= RADIX_TREE_MAP_SHIFT; + height--; + } + + ret = *pathp[0].slot; + if (ret == NULL) + goto out; + + do { + int idx; + + tag_clear(pathp[0].node, tag, pathp[0].offset); + for (idx = 0; idx < RADIX_TREE_TAG_LONGS; idx++) { + if (pathp[0].node->tags[tag][idx]) + goto out; + } + pathp--; + } while (pathp[0].node); +out: + return ret; +} +EXPORT_SYMBOL(radix_tree_tag_clear); + +#ifndef __KERNEL__ /* Only the test harness uses this at present */ +/** + * radix_tree_tag_get - get a tag on a radix tree node + * @root: radix tree root + * @index: index key + * @tag: tag index + * + * Return the search tag corresponging to @index in the radix tree. + * + * Returns zero if the tag is unset, or if there is no corresponding item + * in the tree. + */ +int radix_tree_tag_get(struct radix_tree_root *root, + unsigned long index, int tag) +{ + unsigned int height, shift; + struct radix_tree_node **slot; + int saw_unset_tag = 0; + + height = root->height; + if (index > radix_tree_maxindex(height)) + return 0; + + shift = (height - 1) * RADIX_TREE_MAP_SHIFT; + slot = &root->rnode; + + for ( ; ; ) { + int offset; + + if (*slot == NULL) + return 0; + + offset = (index >> shift) & RADIX_TREE_MAP_MASK; + + /* + * This is just a debug check. Later, we can bale as soon as + * we see an unset tag. + */ + if (!tag_get(*slot, tag, offset)) + saw_unset_tag = 1; + if (height == 1) { + int ret = tag_get(*slot, tag, offset); + + BUG_ON(ret && saw_unset_tag); + return ret; + } + slot = (struct radix_tree_node **)((*slot)->slots + offset); + shift -= RADIX_TREE_MAP_SHIFT; + height--; + } +} +EXPORT_SYMBOL(radix_tree_tag_get); +#endif + +static unsigned int +__lookup(struct radix_tree_root *root, void **results, unsigned long index, + unsigned int max_items, unsigned long *next_index) +{ + unsigned int nr_found = 0; + unsigned int shift; + unsigned int height = root->height; + struct radix_tree_node *slot; + + shift = (height-1) * RADIX_TREE_MAP_SHIFT; + slot = root->rnode; + + while (height > 0) { + unsigned long i = (index >> shift) & RADIX_TREE_MAP_MASK; + + for ( ; i < RADIX_TREE_MAP_SIZE; i++) { + if (slot->slots[i] != NULL) + break; + index &= ~((1UL << shift) - 1); + index += 1UL << shift; + if (index == 0) + goto out; /* 32-bit wraparound */ + } + if (i == RADIX_TREE_MAP_SIZE) + goto out; + height--; + if (height == 0) { /* Bottom level: grab some items */ + unsigned long j = index & RADIX_TREE_MAP_MASK; + + for ( ; j < RADIX_TREE_MAP_SIZE; j++) { + index++; + if (slot->slots[j]) { + results[nr_found++] = slot->slots[j]; + if (nr_found == max_items) + goto out; + } + } + } + shift -= RADIX_TREE_MAP_SHIFT; + slot = slot->slots[i]; + } +out: + *next_index = index; + return nr_found; +} + +/** + * radix_tree_gang_lookup - perform multiple lookup on a radix tree + * @root: radix tree root + * @results: where the results of the lookup are placed + * @first_index: start the lookup from this key + * @max_items: place up to this many items at *results + * + * Performs an index-ascending scan of the tree for present items. Places + * them at *@results and returns the number of items which were placed at + * *@results. + * + * The implementation is naive. + */ +unsigned int +radix_tree_gang_lookup(struct radix_tree_root *root, void **results, + unsigned long first_index, unsigned int max_items) +{ + const unsigned long max_index = radix_tree_maxindex(root->height); + unsigned long cur_index = first_index; + unsigned int ret = 0; + + while (ret < max_items) { + unsigned int nr_found; + unsigned long next_index; /* Index of next search */ + + if (cur_index > max_index) + break; + nr_found = __lookup(root, results + ret, cur_index, + max_items - ret, &next_index); + ret += nr_found; + if (next_index == 0) + break; + cur_index = next_index; + } + return ret; +} +EXPORT_SYMBOL(radix_tree_gang_lookup); + +/* + * FIXME: the two tag_get()s here should use find_next_bit() instead of + * open-coding the search. + */ +static unsigned int +__lookup_tag(struct radix_tree_root *root, void **results, unsigned long index, + unsigned int max_items, unsigned long *next_index, int tag) +{ + unsigned int nr_found = 0; + unsigned int shift; + unsigned int height = root->height; + struct radix_tree_node *slot; + + shift = (height - 1) * RADIX_TREE_MAP_SHIFT; + slot = root->rnode; + + while (height > 0) { + unsigned long i = (index >> shift) & RADIX_TREE_MAP_MASK; + + for ( ; i < RADIX_TREE_MAP_SIZE; i++) { + if (tag_get(slot, tag, i)) { + BUG_ON(slot->slots[i] == NULL); + break; + } + index &= ~((1UL << shift) - 1); + index += 1UL << shift; + if (index == 0) + goto out; /* 32-bit wraparound */ + } + if (i == RADIX_TREE_MAP_SIZE) + goto out; + height--; + if (height == 0) { /* Bottom level: grab some items */ + unsigned long j = index & RADIX_TREE_MAP_MASK; + + for ( ; j < RADIX_TREE_MAP_SIZE; j++) { + index++; + if (tag_get(slot, tag, j)) { + BUG_ON(slot->slots[j] == NULL); + results[nr_found++] = slot->slots[j]; + if (nr_found == max_items) + goto out; + } + } + } + shift -= RADIX_TREE_MAP_SHIFT; + slot = slot->slots[i]; + } +out: + *next_index = index; + return nr_found; +} + +/** + * radix_tree_gang_lookup_tag - perform multiple lookup on a radix tree + * based on a tag + * @root: radix tree root + * @results: where the results of the lookup are placed + * @first_index: start the lookup from this key + * @max_items: place up to this many items at *results + * @tag: the tag index + * + * Performs an index-ascending scan of the tree for present items which + * have the tag indexed by @tag set. Places the items at *@results and + * returns the number of items which were placed at *@results. + */ +unsigned int +radix_tree_gang_lookup_tag(struct radix_tree_root *root, void **results, + unsigned long first_index, unsigned int max_items, int tag) +{ + const unsigned long max_index = radix_tree_maxindex(root->height); + unsigned long cur_index = first_index; + unsigned int ret = 0; + + while (ret < max_items) { + unsigned int nr_found; + unsigned long next_index; /* Index of next search */ + + if (cur_index > max_index) + break; + nr_found = __lookup_tag(root, results + ret, cur_index, + max_items - ret, &next_index, tag); + ret += nr_found; + if (next_index == 0) + break; + cur_index = next_index; + } + return ret; +} +EXPORT_SYMBOL(radix_tree_gang_lookup_tag); + +/** + * radix_tree_delete - delete an item from a radix tree + * @root: radix tree root + * @index: index key + * + * Remove the item at @index from the radix tree rooted at @root. + * + * Returns the address of the deleted item, or NULL if it was not present. + */ +void *radix_tree_delete(struct radix_tree_root *root, unsigned long index) +{ + struct radix_tree_path path[RADIX_TREE_MAX_PATH], *pathp = path; + struct radix_tree_path *orig_pathp; + unsigned int height, shift; + void *ret = NULL; + char tags[RADIX_TREE_TAGS]; + int nr_cleared_tags; + + height = root->height; + if (index > radix_tree_maxindex(height)) + goto out; + + shift = (height - 1) * RADIX_TREE_MAP_SHIFT; + pathp->node = NULL; + pathp->slot = &root->rnode; + + while (height > 0) { + int offset; + + if (*pathp->slot == NULL) + goto out; + + offset = (index >> shift) & RADIX_TREE_MAP_MASK; + pathp[1].offset = offset; + pathp[1].node = *pathp[0].slot; + pathp[1].slot = (struct radix_tree_node **) + (pathp[1].node->slots + offset); + pathp++; + shift -= RADIX_TREE_MAP_SHIFT; + height--; + } + + ret = *pathp[0].slot; + if (ret == NULL) + goto out; + + orig_pathp = pathp; + + /* + * Clear all tags associated with the just-deleted item + */ + memset(tags, 0, sizeof(tags)); + do { + int tag; + + nr_cleared_tags = RADIX_TREE_TAGS; + for (tag = 0; tag < RADIX_TREE_TAGS; tag++) { + int idx; + + if (tags[tag]) + continue; + + tag_clear(pathp[0].node, tag, pathp[0].offset); + + for (idx = 0; idx < RADIX_TREE_TAG_LONGS; idx++) { + if (pathp[0].node->tags[tag][idx]) { + tags[tag] = 1; + nr_cleared_tags--; + break; + } + } + } + pathp--; + } while (pathp[0].node && nr_cleared_tags); + + pathp = orig_pathp; + *pathp[0].slot = NULL; + while (pathp[0].node && --pathp[0].node->count == 0) { + pathp--; + BUG_ON(*pathp[0].slot == NULL); + *pathp[0].slot = NULL; + radix_tree_node_free(pathp[1].node); + } + if (root->rnode == NULL) + root->height = 0; +out: + return ret; +} +EXPORT_SYMBOL(radix_tree_delete); + +/** + * radix_tree_tagged - test whether any items in the tree are tagged + * @root: radix tree root + * @tag: tag to test + */ +int radix_tree_tagged(struct radix_tree_root *root, int tag) +{ + int idx; + + if (!root->rnode) + return 0; + for (idx = 0; idx < RADIX_TREE_TAG_LONGS; idx++) { + if (root->rnode->tags[tag][idx]) + return 1; + } + return 0; +} +EXPORT_SYMBOL(radix_tree_tagged); + +static void +radix_tree_node_ctor(void *node, kmem_cache_t *cachep, unsigned long flags) +{ + memset(node, 0, sizeof(struct radix_tree_node)); +} + +static __init unsigned long __maxindex(unsigned int height) +{ + unsigned int tmp = height * RADIX_TREE_MAP_SHIFT; + unsigned long index = (~0UL >> (RADIX_TREE_INDEX_BITS - tmp - 1)) >> 1; + + if (tmp >= RADIX_TREE_INDEX_BITS) + index = ~0UL; + return index; +} + +static __init void radix_tree_init_maxindex(void) +{ + unsigned int i; + + for (i = 0; i < ARRAY_SIZE(height_to_maxindex); i++) + height_to_maxindex[i] = __maxindex(i); +} + +#ifdef CONFIG_HOTPLUG_CPU +static int radix_tree_callback(struct notifier_block *nfb, + unsigned long action, + void *hcpu) +{ + int cpu = (long)hcpu; + struct radix_tree_preload *rtp; + + /* Free per-cpu pool of perloaded nodes */ + if (action == CPU_DEAD) { + rtp = &per_cpu(radix_tree_preloads, cpu); + while (rtp->nr) { + kmem_cache_free(radix_tree_node_cachep, + rtp->nodes[rtp->nr-1]); + rtp->nodes[rtp->nr-1] = NULL; + rtp->nr--; + } + } + return NOTIFY_OK; +} +#endif /* CONFIG_HOTPLUG_CPU */ + +void __init radix_tree_init(void) +{ + radix_tree_node_cachep = kmem_cache_create("radix_tree_node", + sizeof(struct radix_tree_node), 0, + SLAB_PANIC, radix_tree_node_ctor, NULL); + radix_tree_init_maxindex(); + hotcpu_notifier(radix_tree_callback, 0); +} diff --git a/lib/rbtree.c b/lib/rbtree.c new file mode 100644 index 00000000000..14b791ac508 --- /dev/null +++ b/lib/rbtree.c @@ -0,0 +1,394 @@ +/* + Red Black Trees + (C) 1999 Andrea Arcangeli <andrea@suse.de> + (C) 2002 David Woodhouse <dwmw2@infradead.org> + + This program is free software; you can redistribute it and/or modify + it under the terms of the GNU General Public License as published by + the Free Software Foundation; either version 2 of the License, or + (at your option) any later version. + + This program is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + GNU General Public License for more details. + + You should have received a copy of the GNU General Public License + along with this program; if not, write to the Free Software + Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + + linux/lib/rbtree.c +*/ + +#include <linux/rbtree.h> +#include <linux/module.h> + +static void __rb_rotate_left(struct rb_node *node, struct rb_root *root) +{ + struct rb_node *right = node->rb_right; + + if ((node->rb_right = right->rb_left)) + right->rb_left->rb_parent = node; + right->rb_left = node; + + if ((right->rb_parent = node->rb_parent)) + { + if (node == node->rb_parent->rb_left) + node->rb_parent->rb_left = right; + else + node->rb_parent->rb_right = right; + } + else + root->rb_node = right; + node->rb_parent = right; +} + +static void __rb_rotate_right(struct rb_node *node, struct rb_root *root) +{ + struct rb_node *left = node->rb_left; + + if ((node->rb_left = left->rb_right)) + left->rb_right->rb_parent = node; + left->rb_right = node; + + if ((left->rb_parent = node->rb_parent)) + { + if (node == node->rb_parent->rb_right) + node->rb_parent->rb_right = left; + else + node->rb_parent->rb_left = left; + } + else + root->rb_node = left; + node->rb_parent = left; +} + +void rb_insert_color(struct rb_node *node, struct rb_root *root) +{ + struct rb_node *parent, *gparent; + + while ((parent = node->rb_parent) && parent->rb_color == RB_RED) + { + gparent = parent->rb_parent; + + if (parent == gparent->rb_left) + { + { + register struct rb_node *uncle = gparent->rb_right; + if (uncle && uncle->rb_color == RB_RED) + { + uncle->rb_color = RB_BLACK; + parent->rb_color = RB_BLACK; + gparent->rb_color = RB_RED; + node = gparent; + continue; + } + } + + if (parent->rb_right == node) + { + register struct rb_node *tmp; + __rb_rotate_left(parent, root); + tmp = parent; + parent = node; + node = tmp; + } + + parent->rb_color = RB_BLACK; + gparent->rb_color = RB_RED; + __rb_rotate_right(gparent, root); + } else { + { + register struct rb_node *uncle = gparent->rb_left; + if (uncle && uncle->rb_color == RB_RED) + { + uncle->rb_color = RB_BLACK; + parent->rb_color = RB_BLACK; + gparent->rb_color = RB_RED; + node = gparent; + continue; + } + } + + if (parent->rb_left == node) + { + register struct rb_node *tmp; + __rb_rotate_right(parent, root); + tmp = parent; + parent = node; + node = tmp; + } + + parent->rb_color = RB_BLACK; + gparent->rb_color = RB_RED; + __rb_rotate_left(gparent, root); + } + } + + root->rb_node->rb_color = RB_BLACK; +} +EXPORT_SYMBOL(rb_insert_color); + +static void __rb_erase_color(struct rb_node *node, struct rb_node *parent, + struct rb_root *root) +{ + struct rb_node *other; + + while ((!node || node->rb_color == RB_BLACK) && node != root->rb_node) + { + if (parent->rb_left == node) + { + other = parent->rb_right; + if (other->rb_color == RB_RED) + { + other->rb_color = RB_BLACK; + parent->rb_color = RB_RED; + __rb_rotate_left(parent, root); + other = parent->rb_right; + } + if ((!other->rb_left || + other->rb_left->rb_color == RB_BLACK) + && (!other->rb_right || + other->rb_right->rb_color == RB_BLACK)) + { + other->rb_color = RB_RED; + node = parent; + parent = node->rb_parent; + } + else + { + if (!other->rb_right || + other->rb_right->rb_color == RB_BLACK) + { + register struct rb_node *o_left; + if ((o_left = other->rb_left)) + o_left->rb_color = RB_BLACK; + other->rb_color = RB_RED; + __rb_rotate_right(other, root); + other = parent->rb_right; + } + other->rb_color = parent->rb_color; + parent->rb_color = RB_BLACK; + if (other->rb_right) + other->rb_right->rb_color = RB_BLACK; + __rb_rotate_left(parent, root); + node = root->rb_node; + break; + } + } + else + { + other = parent->rb_left; + if (other->rb_color == RB_RED) + { + other->rb_color = RB_BLACK; + parent->rb_color = RB_RED; + __rb_rotate_right(parent, root); + other = parent->rb_left; + } + if ((!other->rb_left || + other->rb_left->rb_color == RB_BLACK) + && (!other->rb_right || + other->rb_right->rb_color == RB_BLACK)) + { + other->rb_color = RB_RED; + node = parent; + parent = node->rb_parent; + } + else + { + if (!other->rb_left || + other->rb_left->rb_color == RB_BLACK) + { + register struct rb_node *o_right; + if ((o_right = other->rb_right)) + o_right->rb_color = RB_BLACK; + other->rb_color = RB_RED; + __rb_rotate_left(other, root); + other = parent->rb_left; + } + other->rb_color = parent->rb_color; + parent->rb_color = RB_BLACK; + if (other->rb_left) + other->rb_left->rb_color = RB_BLACK; + __rb_rotate_right(parent, root); + node = root->rb_node; + break; + } + } + } + if (node) + node->rb_color = RB_BLACK; +} + +void rb_erase(struct rb_node *node, struct rb_root *root) +{ + struct rb_node *child, *parent; + int color; + + if (!node->rb_left) + child = node->rb_right; + else if (!node->rb_right) + child = node->rb_left; + else + { + struct rb_node *old = node, *left; + + node = node->rb_right; + while ((left = node->rb_left) != NULL) + node = left; + child = node->rb_right; + parent = node->rb_parent; + color = node->rb_color; + + if (child) + child->rb_parent = parent; + if (parent) + { + if (parent->rb_left == node) + parent->rb_left = child; + else + parent->rb_right = child; + } + else + root->rb_node = child; + + if (node->rb_parent == old) + parent = node; + node->rb_parent = old->rb_parent; + node->rb_color = old->rb_color; + node->rb_right = old->rb_right; + node->rb_left = old->rb_left; + + if (old->rb_parent) + { + if (old->rb_parent->rb_left == old) + old->rb_parent->rb_left = node; + else + old->rb_parent->rb_right = node; + } else + root->rb_node = node; + + old->rb_left->rb_parent = node; + if (old->rb_right) + old->rb_right->rb_parent = node; + goto color; + } + + parent = node->rb_parent; + color = node->rb_color; + + if (child) + child->rb_parent = parent; + if (parent) + { + if (parent->rb_left == node) + parent->rb_left = child; + else + parent->rb_right = child; + } + else + root->rb_node = child; + + color: + if (color == RB_BLACK) + __rb_erase_color(child, parent, root); +} +EXPORT_SYMBOL(rb_erase); + +/* + * This function returns the first node (in sort order) of the tree. + */ +struct rb_node *rb_first(struct rb_root *root) +{ + struct rb_node *n; + + n = root->rb_node; + if (!n) + return NULL; + while (n->rb_left) + n = n->rb_left; + return n; +} +EXPORT_SYMBOL(rb_first); + +struct rb_node *rb_last(struct rb_root *root) +{ + struct rb_node *n; + + n = root->rb_node; + if (!n) + return NULL; + while (n->rb_right) + n = n->rb_right; + return n; +} +EXPORT_SYMBOL(rb_last); + +struct rb_node *rb_next(struct rb_node *node) +{ + /* If we have a right-hand child, go down and then left as far + as we can. */ + if (node->rb_right) { + node = node->rb_right; + while (node->rb_left) + node=node->rb_left; + return node; + } + + /* No right-hand children. Everything down and left is + smaller than us, so any 'next' node must be in the general + direction of our parent. Go up the tree; any time the + ancestor is a right-hand child of its parent, keep going + up. First time it's a left-hand child of its parent, said + parent is our 'next' node. */ + while (node->rb_parent && node == node->rb_parent->rb_right) + node = node->rb_parent; + + return node->rb_parent; +} +EXPORT_SYMBOL(rb_next); + +struct rb_node *rb_prev(struct rb_node *node) +{ + /* If we have a left-hand child, go down and then right as far + as we can. */ + if (node->rb_left) { + node = node->rb_left; + while (node->rb_right) + node=node->rb_right; + return node; + } + + /* No left-hand children. Go up till we find an ancestor which + is a right-hand child of its parent */ + while (node->rb_parent && node == node->rb_parent->rb_left) + node = node->rb_parent; + + return node->rb_parent; +} +EXPORT_SYMBOL(rb_prev); + +void rb_replace_node(struct rb_node *victim, struct rb_node *new, + struct rb_root *root) +{ + struct rb_node *parent = victim->rb_parent; + + /* Set the surrounding nodes to point to the replacement */ + if (parent) { + if (victim == parent->rb_left) + parent->rb_left = new; + else + parent->rb_right = new; + } else { + root->rb_node = new; + } + if (victim->rb_left) + victim->rb_left->rb_parent = new; + if (victim->rb_right) + victim->rb_right->rb_parent = new; + + /* Copy the pointers/colour from the victim to the replacement */ + *new = *victim; +} +EXPORT_SYMBOL(rb_replace_node); diff --git a/lib/reed_solomon/Makefile b/lib/reed_solomon/Makefile new file mode 100644 index 00000000000..747a2de2934 --- /dev/null +++ b/lib/reed_solomon/Makefile @@ -0,0 +1,6 @@ +# +# This is a modified version of reed solomon lib, +# + +obj-$(CONFIG_REED_SOLOMON) += reed_solomon.o + diff --git a/lib/reed_solomon/decode_rs.c b/lib/reed_solomon/decode_rs.c new file mode 100644 index 00000000000..d401decd628 --- /dev/null +++ b/lib/reed_solomon/decode_rs.c @@ -0,0 +1,272 @@ +/* + * lib/reed_solomon/decode_rs.c + * + * Overview: + * Generic Reed Solomon encoder / decoder library + * + * Copyright 2002, Phil Karn, KA9Q + * May be used under the terms of the GNU General Public License (GPL) + * + * Adaption to the kernel by Thomas Gleixner (tglx@linutronix.de) + * + * $Id: decode_rs.c,v 1.6 2004/10/22 15:41:47 gleixner Exp $ + * + */ + +/* Generic data width independent code which is included by the + * wrappers. + */ +{ + int deg_lambda, el, deg_omega; + int i, j, r, k, pad; + int nn = rs->nn; + int nroots = rs->nroots; + int fcr = rs->fcr; + int prim = rs->prim; + int iprim = rs->iprim; + uint16_t *alpha_to = rs->alpha_to; + uint16_t *index_of = rs->index_of; + uint16_t u, q, tmp, num1, num2, den, discr_r, syn_error; + /* Err+Eras Locator poly and syndrome poly The maximum value + * of nroots is 8. So the necessary stack size will be about + * 220 bytes max. + */ + uint16_t lambda[nroots + 1], syn[nroots]; + uint16_t b[nroots + 1], t[nroots + 1], omega[nroots + 1]; + uint16_t root[nroots], reg[nroots + 1], loc[nroots]; + int count = 0; + uint16_t msk = (uint16_t) rs->nn; + + /* Check length parameter for validity */ + pad = nn - nroots - len; + if (pad < 0 || pad >= nn) + return -ERANGE; + + /* Does the caller provide the syndrome ? */ + if (s != NULL) + goto decode; + + /* form the syndromes; i.e., evaluate data(x) at roots of + * g(x) */ + for (i = 0; i < nroots; i++) + syn[i] = (((uint16_t) data[0]) ^ invmsk) & msk; + + for (j = 1; j < len; j++) { + for (i = 0; i < nroots; i++) { + if (syn[i] == 0) { + syn[i] = (((uint16_t) data[j]) ^ + invmsk) & msk; + } else { + syn[i] = ((((uint16_t) data[j]) ^ + invmsk) & msk) ^ + alpha_to[rs_modnn(rs, index_of[syn[i]] + + (fcr + i) * prim)]; + } + } + } + + for (j = 0; j < nroots; j++) { + for (i = 0; i < nroots; i++) { + if (syn[i] == 0) { + syn[i] = ((uint16_t) par[j]) & msk; + } else { + syn[i] = (((uint16_t) par[j]) & msk) ^ + alpha_to[rs_modnn(rs, index_of[syn[i]] + + (fcr+i)*prim)]; + } + } + } + s = syn; + + /* Convert syndromes to index form, checking for nonzero condition */ + syn_error = 0; + for (i = 0; i < nroots; i++) { + syn_error |= s[i]; + s[i] = index_of[s[i]]; + } + + if (!syn_error) { + /* if syndrome is zero, data[] is a codeword and there are no + * errors to correct. So return data[] unmodified + */ + count = 0; + goto finish; + } + + decode: + memset(&lambda[1], 0, nroots * sizeof(lambda[0])); + lambda[0] = 1; + + if (no_eras > 0) { + /* Init lambda to be the erasure locator polynomial */ + lambda[1] = alpha_to[rs_modnn(rs, + prim * (nn - 1 - eras_pos[0]))]; + for (i = 1; i < no_eras; i++) { + u = rs_modnn(rs, prim * (nn - 1 - eras_pos[i])); + for (j = i + 1; j > 0; j--) { + tmp = index_of[lambda[j - 1]]; + if (tmp != nn) { + lambda[j] ^= + alpha_to[rs_modnn(rs, u + tmp)]; + } + } + } + } + + for (i = 0; i < nroots + 1; i++) + b[i] = index_of[lambda[i]]; + + /* + * Begin Berlekamp-Massey algorithm to determine error+erasure + * locator polynomial + */ + r = no_eras; + el = no_eras; + while (++r <= nroots) { /* r is the step number */ + /* Compute discrepancy at the r-th step in poly-form */ + discr_r = 0; + for (i = 0; i < r; i++) { + if ((lambda[i] != 0) && (s[r - i - 1] != nn)) { + discr_r ^= + alpha_to[rs_modnn(rs, + index_of[lambda[i]] + + s[r - i - 1])]; + } + } + discr_r = index_of[discr_r]; /* Index form */ + if (discr_r == nn) { + /* 2 lines below: B(x) <-- x*B(x) */ + memmove (&b[1], b, nroots * sizeof (b[0])); + b[0] = nn; + } else { + /* 7 lines below: T(x) <-- lambda(x)-discr_r*x*b(x) */ + t[0] = lambda[0]; + for (i = 0; i < nroots; i++) { + if (b[i] != nn) { + t[i + 1] = lambda[i + 1] ^ + alpha_to[rs_modnn(rs, discr_r + + b[i])]; + } else + t[i + 1] = lambda[i + 1]; + } + if (2 * el <= r + no_eras - 1) { + el = r + no_eras - el; + /* + * 2 lines below: B(x) <-- inv(discr_r) * + * lambda(x) + */ + for (i = 0; i <= nroots; i++) { + b[i] = (lambda[i] == 0) ? nn : + rs_modnn(rs, index_of[lambda[i]] + - discr_r + nn); + } + } else { + /* 2 lines below: B(x) <-- x*B(x) */ + memmove(&b[1], b, nroots * sizeof(b[0])); + b[0] = nn; + } + memcpy(lambda, t, (nroots + 1) * sizeof(t[0])); + } + } + + /* Convert lambda to index form and compute deg(lambda(x)) */ + deg_lambda = 0; + for (i = 0; i < nroots + 1; i++) { + lambda[i] = index_of[lambda[i]]; + if (lambda[i] != nn) + deg_lambda = i; + } + /* Find roots of error+erasure locator polynomial by Chien search */ + memcpy(®[1], &lambda[1], nroots * sizeof(reg[0])); + count = 0; /* Number of roots of lambda(x) */ + for (i = 1, k = iprim - 1; i <= nn; i++, k = rs_modnn(rs, k + iprim)) { + q = 1; /* lambda[0] is always 0 */ + for (j = deg_lambda; j > 0; j--) { + if (reg[j] != nn) { + reg[j] = rs_modnn(rs, reg[j] + j); + q ^= alpha_to[reg[j]]; + } + } + if (q != 0) + continue; /* Not a root */ + /* store root (index-form) and error location number */ + root[count] = i; + loc[count] = k; + /* If we've already found max possible roots, + * abort the search to save time + */ + if (++count == deg_lambda) + break; + } + if (deg_lambda != count) { + /* + * deg(lambda) unequal to number of roots => uncorrectable + * error detected + */ + count = -1; + goto finish; + } + /* + * Compute err+eras evaluator poly omega(x) = s(x)*lambda(x) (modulo + * x**nroots). in index form. Also find deg(omega). + */ + deg_omega = deg_lambda - 1; + for (i = 0; i <= deg_omega; i++) { + tmp = 0; + for (j = i; j >= 0; j--) { + if ((s[i - j] != nn) && (lambda[j] != nn)) + tmp ^= + alpha_to[rs_modnn(rs, s[i - j] + lambda[j])]; + } + omega[i] = index_of[tmp]; + } + + /* + * Compute error values in poly-form. num1 = omega(inv(X(l))), num2 = + * inv(X(l))**(fcr-1) and den = lambda_pr(inv(X(l))) all in poly-form + */ + for (j = count - 1; j >= 0; j--) { + num1 = 0; + for (i = deg_omega; i >= 0; i--) { + if (omega[i] != nn) + num1 ^= alpha_to[rs_modnn(rs, omega[i] + + i * root[j])]; + } + num2 = alpha_to[rs_modnn(rs, root[j] * (fcr - 1) + nn)]; + den = 0; + + /* lambda[i+1] for i even is the formal derivative + * lambda_pr of lambda[i] */ + for (i = min(deg_lambda, nroots - 1) & ~1; i >= 0; i -= 2) { + if (lambda[i + 1] != nn) { + den ^= alpha_to[rs_modnn(rs, lambda[i + 1] + + i * root[j])]; + } + } + /* Apply error to data */ + if (num1 != 0 && loc[j] >= pad) { + uint16_t cor = alpha_to[rs_modnn(rs,index_of[num1] + + index_of[num2] + + nn - index_of[den])]; + /* Store the error correction pattern, if a + * correction buffer is available */ + if (corr) { + corr[j] = cor; + } else { + /* If a data buffer is given and the + * error is inside the message, + * correct it */ + if (data && (loc[j] < (nn - nroots))) + data[loc[j] - pad] ^= cor; + } + } + } + +finish: + if (eras_pos != NULL) { + for (i = 0; i < count; i++) + eras_pos[i] = loc[i] - pad; + } + return count; + +} diff --git a/lib/reed_solomon/encode_rs.c b/lib/reed_solomon/encode_rs.c new file mode 100644 index 00000000000..237bf65ae88 --- /dev/null +++ b/lib/reed_solomon/encode_rs.c @@ -0,0 +1,54 @@ +/* + * lib/reed_solomon/encode_rs.c + * + * Overview: + * Generic Reed Solomon encoder / decoder library + * + * Copyright 2002, Phil Karn, KA9Q + * May be used under the terms of the GNU General Public License (GPL) + * + * Adaption to the kernel by Thomas Gleixner (tglx@linutronix.de) + * + * $Id: encode_rs.c,v 1.4 2004/10/22 15:41:47 gleixner Exp $ + * + */ + +/* Generic data width independent code which is included by the + * wrappers. + * int encode_rsX (struct rs_control *rs, uintX_t *data, int len, uintY_t *par) + */ +{ + int i, j, pad; + int nn = rs->nn; + int nroots = rs->nroots; + uint16_t *alpha_to = rs->alpha_to; + uint16_t *index_of = rs->index_of; + uint16_t *genpoly = rs->genpoly; + uint16_t fb; + uint16_t msk = (uint16_t) rs->nn; + + /* Check length parameter for validity */ + pad = nn - nroots - len; + if (pad < 0 || pad >= nn) + return -ERANGE; + + for (i = 0; i < len; i++) { + fb = index_of[((((uint16_t) data[i])^invmsk) & msk) ^ par[0]]; + /* feedback term is non-zero */ + if (fb != nn) { + for (j = 1; j < nroots; j++) { + par[j] ^= alpha_to[rs_modnn(rs, fb + + genpoly[nroots - j])]; + } + } + /* Shift */ + memmove(&par[0], &par[1], sizeof(uint16_t) * (nroots - 1)); + if (fb != nn) { + par[nroots - 1] = alpha_to[rs_modnn(rs, + fb + genpoly[0])]; + } else { + par[nroots - 1] = 0; + } + } + return 0; +} diff --git a/lib/reed_solomon/reed_solomon.c b/lib/reed_solomon/reed_solomon.c new file mode 100644 index 00000000000..6604e3b1940 --- /dev/null +++ b/lib/reed_solomon/reed_solomon.c @@ -0,0 +1,335 @@ +/* + * lib/reed_solomon/rslib.c + * + * Overview: + * Generic Reed Solomon encoder / decoder library + * + * Copyright (C) 2004 Thomas Gleixner (tglx@linutronix.de) + * + * Reed Solomon code lifted from reed solomon library written by Phil Karn + * Copyright 2002 Phil Karn, KA9Q + * + * $Id: rslib.c,v 1.5 2004/10/22 15:41:47 gleixner Exp $ + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * Description: + * + * The generic Reed Solomon library provides runtime configurable + * encoding / decoding of RS codes. + * Each user must call init_rs to get a pointer to a rs_control + * structure for the given rs parameters. This structure is either + * generated or a already available matching control structure is used. + * If a structure is generated then the polynomial arrays for + * fast encoding / decoding are built. This can take some time so + * make sure not to call this function from a time critical path. + * Usually a module / driver should initialize the necessary + * rs_control structure on module / driver init and release it + * on exit. + * The encoding puts the calculated syndrome into a given syndrome + * buffer. + * The decoding is a two step process. The first step calculates + * the syndrome over the received (data + syndrome) and calls the + * second stage, which does the decoding / error correction itself. + * Many hw encoders provide a syndrome calculation over the received + * data + syndrome and can call the second stage directly. + * + */ + +#include <linux/errno.h> +#include <linux/kernel.h> +#include <linux/init.h> +#include <linux/module.h> +#include <linux/rslib.h> +#include <linux/slab.h> +#include <asm/semaphore.h> + +/* This list holds all currently allocated rs control structures */ +static LIST_HEAD (rslist); +/* Protection for the list */ +static DECLARE_MUTEX(rslistlock); + +/** + * rs_init - Initialize a Reed-Solomon codec + * + * @symsize: symbol size, bits (1-8) + * @gfpoly: Field generator polynomial coefficients + * @fcr: first root of RS code generator polynomial, index form + * @prim: primitive element to generate polynomial roots + * @nroots: RS code generator polynomial degree (number of roots) + * + * Allocate a control structure and the polynom arrays for faster + * en/decoding. Fill the arrays according to the given parameters + */ +static struct rs_control *rs_init(int symsize, int gfpoly, int fcr, + int prim, int nroots) +{ + struct rs_control *rs; + int i, j, sr, root, iprim; + + /* Allocate the control structure */ + rs = kmalloc(sizeof (struct rs_control), GFP_KERNEL); + if (rs == NULL) + return NULL; + + INIT_LIST_HEAD(&rs->list); + + rs->mm = symsize; + rs->nn = (1 << symsize) - 1; + rs->fcr = fcr; + rs->prim = prim; + rs->nroots = nroots; + rs->gfpoly = gfpoly; + + /* Allocate the arrays */ + rs->alpha_to = kmalloc(sizeof(uint16_t) * (rs->nn + 1), GFP_KERNEL); + if (rs->alpha_to == NULL) + goto errrs; + + rs->index_of = kmalloc(sizeof(uint16_t) * (rs->nn + 1), GFP_KERNEL); + if (rs->index_of == NULL) + goto erralp; + + rs->genpoly = kmalloc(sizeof(uint16_t) * (rs->nroots + 1), GFP_KERNEL); + if(rs->genpoly == NULL) + goto erridx; + + /* Generate Galois field lookup tables */ + rs->index_of[0] = rs->nn; /* log(zero) = -inf */ + rs->alpha_to[rs->nn] = 0; /* alpha**-inf = 0 */ + sr = 1; + for (i = 0; i < rs->nn; i++) { + rs->index_of[sr] = i; + rs->alpha_to[i] = sr; + sr <<= 1; + if (sr & (1 << symsize)) + sr ^= gfpoly; + sr &= rs->nn; + } + /* If it's not primitive, exit */ + if(sr != 1) + goto errpol; + + /* Find prim-th root of 1, used in decoding */ + for(iprim = 1; (iprim % prim) != 0; iprim += rs->nn); + /* prim-th root of 1, index form */ + rs->iprim = iprim / prim; + + /* Form RS code generator polynomial from its roots */ + rs->genpoly[0] = 1; + for (i = 0, root = fcr * prim; i < nroots; i++, root += prim) { + rs->genpoly[i + 1] = 1; + /* Multiply rs->genpoly[] by @**(root + x) */ + for (j = i; j > 0; j--) { + if (rs->genpoly[j] != 0) { + rs->genpoly[j] = rs->genpoly[j -1] ^ + rs->alpha_to[rs_modnn(rs, + rs->index_of[rs->genpoly[j]] + root)]; + } else + rs->genpoly[j] = rs->genpoly[j - 1]; + } + /* rs->genpoly[0] can never be zero */ + rs->genpoly[0] = + rs->alpha_to[rs_modnn(rs, + rs->index_of[rs->genpoly[0]] + root)]; + } + /* convert rs->genpoly[] to index form for quicker encoding */ + for (i = 0; i <= nroots; i++) + rs->genpoly[i] = rs->index_of[rs->genpoly[i]]; + return rs; + + /* Error exit */ +errpol: + kfree(rs->genpoly); +erridx: + kfree(rs->index_of); +erralp: + kfree(rs->alpha_to); +errrs: + kfree(rs); + return NULL; +} + + +/** + * free_rs - Free the rs control structure, if its not longer used + * + * @rs: the control structure which is not longer used by the + * caller + */ +void free_rs(struct rs_control *rs) +{ + down(&rslistlock); + rs->users--; + if(!rs->users) { + list_del(&rs->list); + kfree(rs->alpha_to); + kfree(rs->index_of); + kfree(rs->genpoly); + kfree(rs); + } + up(&rslistlock); +} + +/** + * init_rs - Find a matching or allocate a new rs control structure + * + * @symsize: the symbol size (number of bits) + * @gfpoly: the extended Galois field generator polynomial coefficients, + * with the 0th coefficient in the low order bit. The polynomial + * must be primitive; + * @fcr: the first consecutive root of the rs code generator polynomial + * in index form + * @prim: primitive element to generate polynomial roots + * @nroots: RS code generator polynomial degree (number of roots) + */ +struct rs_control *init_rs(int symsize, int gfpoly, int fcr, int prim, + int nroots) +{ + struct list_head *tmp; + struct rs_control *rs; + + /* Sanity checks */ + if (symsize < 1) + return NULL; + if (fcr < 0 || fcr >= (1<<symsize)) + return NULL; + if (prim <= 0 || prim >= (1<<symsize)) + return NULL; + if (nroots < 0 || nroots >= (1<<symsize) || nroots > 8) + return NULL; + + down(&rslistlock); + + /* Walk through the list and look for a matching entry */ + list_for_each(tmp, &rslist) { + rs = list_entry(tmp, struct rs_control, list); + if (symsize != rs->mm) + continue; + if (gfpoly != rs->gfpoly) + continue; + if (fcr != rs->fcr) + continue; + if (prim != rs->prim) + continue; + if (nroots != rs->nroots) + continue; + /* We have a matching one already */ + rs->users++; + goto out; + } + + /* Create a new one */ + rs = rs_init(symsize, gfpoly, fcr, prim, nroots); + if (rs) { + rs->users = 1; + list_add(&rs->list, &rslist); + } +out: + up(&rslistlock); + return rs; +} + +#ifdef CONFIG_REED_SOLOMON_ENC8 +/** + * encode_rs8 - Calculate the parity for data values (8bit data width) + * + * @rs: the rs control structure + * @data: data field of a given type + * @len: data length + * @par: parity data, must be initialized by caller (usually all 0) + * @invmsk: invert data mask (will be xored on data) + * + * The parity uses a uint16_t data type to enable + * symbol size > 8. The calling code must take care of encoding of the + * syndrome result for storage itself. + */ +int encode_rs8(struct rs_control *rs, uint8_t *data, int len, uint16_t *par, + uint16_t invmsk) +{ +#include "encode_rs.c" +} +EXPORT_SYMBOL_GPL(encode_rs8); +#endif + +#ifdef CONFIG_REED_SOLOMON_DEC8 +/** + * decode_rs8 - Decode codeword (8bit data width) + * + * @rs: the rs control structure + * @data: data field of a given type + * @par: received parity data field + * @len: data length + * @s: syndrome data field (if NULL, syndrome is calculated) + * @no_eras: number of erasures + * @eras_pos: position of erasures, can be NULL + * @invmsk: invert data mask (will be xored on data, not on parity!) + * @corr: buffer to store correction bitmask on eras_pos + * + * The syndrome and parity uses a uint16_t data type to enable + * symbol size > 8. The calling code must take care of decoding of the + * syndrome result and the received parity before calling this code. + */ +int decode_rs8(struct rs_control *rs, uint8_t *data, uint16_t *par, int len, + uint16_t *s, int no_eras, int *eras_pos, uint16_t invmsk, + uint16_t *corr) +{ +#include "decode_rs.c" +} +EXPORT_SYMBOL_GPL(decode_rs8); +#endif + +#ifdef CONFIG_REED_SOLOMON_ENC16 +/** + * encode_rs16 - Calculate the parity for data values (16bit data width) + * + * @rs: the rs control structure + * @data: data field of a given type + * @len: data length + * @par: parity data, must be initialized by caller (usually all 0) + * @invmsk: invert data mask (will be xored on data, not on parity!) + * + * Each field in the data array contains up to symbol size bits of valid data. + */ +int encode_rs16(struct rs_control *rs, uint16_t *data, int len, uint16_t *par, + uint16_t invmsk) +{ +#include "encode_rs.c" +} +EXPORT_SYMBOL_GPL(encode_rs16); +#endif + +#ifdef CONFIG_REED_SOLOMON_DEC16 +/** + * decode_rs16 - Decode codeword (16bit data width) + * + * @rs: the rs control structure + * @data: data field of a given type + * @par: received parity data field + * @len: data length + * @s: syndrome data field (if NULL, syndrome is calculated) + * @no_eras: number of erasures + * @eras_pos: position of erasures, can be NULL + * @invmsk: invert data mask (will be xored on data, not on parity!) + * @corr: buffer to store correction bitmask on eras_pos + * + * Each field in the data array contains up to symbol size bits of valid data. + */ +int decode_rs16(struct rs_control *rs, uint16_t *data, uint16_t *par, int len, + uint16_t *s, int no_eras, int *eras_pos, uint16_t invmsk, + uint16_t *corr) +{ +#include "decode_rs.c" +} +EXPORT_SYMBOL_GPL(decode_rs16); +#endif + +EXPORT_SYMBOL_GPL(init_rs); +EXPORT_SYMBOL_GPL(free_rs); + +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("Reed Solomon encoder/decoder"); +MODULE_AUTHOR("Phil Karn, Thomas Gleixner"); + diff --git a/lib/rwsem-spinlock.c b/lib/rwsem-spinlock.c new file mode 100644 index 00000000000..21f0db2c971 --- /dev/null +++ b/lib/rwsem-spinlock.c @@ -0,0 +1,344 @@ +/* rwsem-spinlock.c: R/W semaphores: contention handling functions for + * generic spinlock implementation + * + * Copyright (c) 2001 David Howells (dhowells@redhat.com). + * - Derived partially from idea by Andrea Arcangeli <andrea@suse.de> + * - Derived also from comments by Linus + */ +#include <linux/rwsem.h> +#include <linux/sched.h> +#include <linux/module.h> + +struct rwsem_waiter { + struct list_head list; + struct task_struct *task; + unsigned int flags; +#define RWSEM_WAITING_FOR_READ 0x00000001 +#define RWSEM_WAITING_FOR_WRITE 0x00000002 +}; + +#if RWSEM_DEBUG +void rwsemtrace(struct rw_semaphore *sem, const char *str) +{ + if (sem->debug) + printk("[%d] %s({%d,%d})\n", + current->pid, str, sem->activity, + list_empty(&sem->wait_list) ? 0 : 1); +} +#endif + +/* + * initialise the semaphore + */ +void fastcall init_rwsem(struct rw_semaphore *sem) +{ + sem->activity = 0; + spin_lock_init(&sem->wait_lock); + INIT_LIST_HEAD(&sem->wait_list); +#if RWSEM_DEBUG + sem->debug = 0; +#endif +} + +/* + * handle the lock release when processes blocked on it that can now run + * - if we come here, then: + * - the 'active count' _reached_ zero + * - the 'waiting count' is non-zero + * - the spinlock must be held by the caller + * - woken process blocks are discarded from the list after having task zeroed + * - writers are only woken if wakewrite is non-zero + */ +static inline struct rw_semaphore * +__rwsem_do_wake(struct rw_semaphore *sem, int wakewrite) +{ + struct rwsem_waiter *waiter; + struct task_struct *tsk; + int woken; + + rwsemtrace(sem, "Entering __rwsem_do_wake"); + + waiter = list_entry(sem->wait_list.next, struct rwsem_waiter, list); + + if (!wakewrite) { + if (waiter->flags & RWSEM_WAITING_FOR_WRITE) + goto out; + goto dont_wake_writers; + } + + /* if we are allowed to wake writers try to grant a single write lock + * if there's a writer at the front of the queue + * - we leave the 'waiting count' incremented to signify potential + * contention + */ + if (waiter->flags & RWSEM_WAITING_FOR_WRITE) { + sem->activity = -1; + list_del(&waiter->list); + tsk = waiter->task; + /* Don't touch waiter after ->task has been NULLed */ + mb(); + waiter->task = NULL; + wake_up_process(tsk); + put_task_struct(tsk); + goto out; + } + + /* grant an infinite number of read locks to the front of the queue */ + dont_wake_writers: + woken = 0; + while (waiter->flags & RWSEM_WAITING_FOR_READ) { + struct list_head *next = waiter->list.next; + + list_del(&waiter->list); + tsk = waiter->task; + mb(); + waiter->task = NULL; + wake_up_process(tsk); + put_task_struct(tsk); + woken++; + if (list_empty(&sem->wait_list)) + break; + waiter = list_entry(next, struct rwsem_waiter, list); + } + + sem->activity += woken; + + out: + rwsemtrace(sem, "Leaving __rwsem_do_wake"); + return sem; +} + +/* + * wake a single writer + */ +static inline struct rw_semaphore * +__rwsem_wake_one_writer(struct rw_semaphore *sem) +{ + struct rwsem_waiter *waiter; + struct task_struct *tsk; + + sem->activity = -1; + + waiter = list_entry(sem->wait_list.next, struct rwsem_waiter, list); + list_del(&waiter->list); + + tsk = waiter->task; + mb(); + waiter->task = NULL; + wake_up_process(tsk); + put_task_struct(tsk); + return sem; +} + +/* + * get a read lock on the semaphore + */ +void fastcall __sched __down_read(struct rw_semaphore *sem) +{ + struct rwsem_waiter waiter; + struct task_struct *tsk; + + rwsemtrace(sem, "Entering __down_read"); + + spin_lock_irq(&sem->wait_lock); + + if (sem->activity >= 0 && list_empty(&sem->wait_list)) { + /* granted */ + sem->activity++; + spin_unlock_irq(&sem->wait_lock); + goto out; + } + + tsk = current; + set_task_state(tsk, TASK_UNINTERRUPTIBLE); + + /* set up my own style of waitqueue */ + waiter.task = tsk; + waiter.flags = RWSEM_WAITING_FOR_READ; + get_task_struct(tsk); + + list_add_tail(&waiter.list, &sem->wait_list); + + /* we don't need to touch the semaphore struct anymore */ + spin_unlock_irq(&sem->wait_lock); + + /* wait to be given the lock */ + for (;;) { + if (!waiter.task) + break; + schedule(); + set_task_state(tsk, TASK_UNINTERRUPTIBLE); + } + + tsk->state = TASK_RUNNING; + + out: + rwsemtrace(sem, "Leaving __down_read"); +} + +/* + * trylock for reading -- returns 1 if successful, 0 if contention + */ +int fastcall __down_read_trylock(struct rw_semaphore *sem) +{ + unsigned long flags; + int ret = 0; + + rwsemtrace(sem, "Entering __down_read_trylock"); + + spin_lock_irqsave(&sem->wait_lock, flags); + + if (sem->activity >= 0 && list_empty(&sem->wait_list)) { + /* granted */ + sem->activity++; + ret = 1; + } + + spin_unlock_irqrestore(&sem->wait_lock, flags); + + rwsemtrace(sem, "Leaving __down_read_trylock"); + return ret; +} + +/* + * get a write lock on the semaphore + * - we increment the waiting count anyway to indicate an exclusive lock + */ +void fastcall __sched __down_write(struct rw_semaphore *sem) +{ + struct rwsem_waiter waiter; + struct task_struct *tsk; + + rwsemtrace(sem, "Entering __down_write"); + + spin_lock_irq(&sem->wait_lock); + + if (sem->activity == 0 && list_empty(&sem->wait_list)) { + /* granted */ + sem->activity = -1; + spin_unlock_irq(&sem->wait_lock); + goto out; + } + + tsk = current; + set_task_state(tsk, TASK_UNINTERRUPTIBLE); + + /* set up my own style of waitqueue */ + waiter.task = tsk; + waiter.flags = RWSEM_WAITING_FOR_WRITE; + get_task_struct(tsk); + + list_add_tail(&waiter.list, &sem->wait_list); + + /* we don't need to touch the semaphore struct anymore */ + spin_unlock_irq(&sem->wait_lock); + + /* wait to be given the lock */ + for (;;) { + if (!waiter.task) + break; + schedule(); + set_task_state(tsk, TASK_UNINTERRUPTIBLE); + } + + tsk->state = TASK_RUNNING; + + out: + rwsemtrace(sem, "Leaving __down_write"); +} + +/* + * trylock for writing -- returns 1 if successful, 0 if contention + */ +int fastcall __down_write_trylock(struct rw_semaphore *sem) +{ + unsigned long flags; + int ret = 0; + + rwsemtrace(sem, "Entering __down_write_trylock"); + + spin_lock_irqsave(&sem->wait_lock, flags); + + if (sem->activity == 0 && list_empty(&sem->wait_list)) { + /* granted */ + sem->activity = -1; + ret = 1; + } + + spin_unlock_irqrestore(&sem->wait_lock, flags); + + rwsemtrace(sem, "Leaving __down_write_trylock"); + return ret; +} + +/* + * release a read lock on the semaphore + */ +void fastcall __up_read(struct rw_semaphore *sem) +{ + unsigned long flags; + + rwsemtrace(sem, "Entering __up_read"); + + spin_lock_irqsave(&sem->wait_lock, flags); + + if (--sem->activity == 0 && !list_empty(&sem->wait_list)) + sem = __rwsem_wake_one_writer(sem); + + spin_unlock_irqrestore(&sem->wait_lock, flags); + + rwsemtrace(sem, "Leaving __up_read"); +} + +/* + * release a write lock on the semaphore + */ +void fastcall __up_write(struct rw_semaphore *sem) +{ + unsigned long flags; + + rwsemtrace(sem, "Entering __up_write"); + + spin_lock_irqsave(&sem->wait_lock, flags); + + sem->activity = 0; + if (!list_empty(&sem->wait_list)) + sem = __rwsem_do_wake(sem, 1); + + spin_unlock_irqrestore(&sem->wait_lock, flags); + + rwsemtrace(sem, "Leaving __up_write"); +} + +/* + * downgrade a write lock into a read lock + * - just wake up any readers at the front of the queue + */ +void fastcall __downgrade_write(struct rw_semaphore *sem) +{ + unsigned long flags; + + rwsemtrace(sem, "Entering __downgrade_write"); + + spin_lock_irqsave(&sem->wait_lock, flags); + + sem->activity = 1; + if (!list_empty(&sem->wait_list)) + sem = __rwsem_do_wake(sem, 0); + + spin_unlock_irqrestore(&sem->wait_lock, flags); + + rwsemtrace(sem, "Leaving __downgrade_write"); +} + +EXPORT_SYMBOL(init_rwsem); +EXPORT_SYMBOL(__down_read); +EXPORT_SYMBOL(__down_read_trylock); +EXPORT_SYMBOL(__down_write); +EXPORT_SYMBOL(__down_write_trylock); +EXPORT_SYMBOL(__up_read); +EXPORT_SYMBOL(__up_write); +EXPORT_SYMBOL(__downgrade_write); +#if RWSEM_DEBUG +EXPORT_SYMBOL(rwsemtrace); +#endif diff --git a/lib/rwsem.c b/lib/rwsem.c new file mode 100644 index 00000000000..7644089ec8f --- /dev/null +++ b/lib/rwsem.c @@ -0,0 +1,268 @@ +/* rwsem.c: R/W semaphores: contention handling functions + * + * Written by David Howells (dhowells@redhat.com). + * Derived from arch/i386/kernel/semaphore.c + */ +#include <linux/rwsem.h> +#include <linux/sched.h> +#include <linux/init.h> +#include <linux/module.h> + +struct rwsem_waiter { + struct list_head list; + struct task_struct *task; + unsigned int flags; +#define RWSEM_WAITING_FOR_READ 0x00000001 +#define RWSEM_WAITING_FOR_WRITE 0x00000002 +}; + +#if RWSEM_DEBUG +#undef rwsemtrace +void rwsemtrace(struct rw_semaphore *sem, const char *str) +{ + printk("sem=%p\n", sem); + printk("(sem)=%08lx\n", sem->count); + if (sem->debug) + printk("[%d] %s({%08lx})\n", current->pid, str, sem->count); +} +#endif + +/* + * handle the lock release when processes blocked on it that can now run + * - if we come here from up_xxxx(), then: + * - the 'active part' of count (&0x0000ffff) reached 0 (but may have changed) + * - the 'waiting part' of count (&0xffff0000) is -ve (and will still be so) + * - there must be someone on the queue + * - the spinlock must be held by the caller + * - woken process blocks are discarded from the list after having task zeroed + * - writers are only woken if downgrading is false + */ +static inline struct rw_semaphore * +__rwsem_do_wake(struct rw_semaphore *sem, int downgrading) +{ + struct rwsem_waiter *waiter; + struct task_struct *tsk; + struct list_head *next; + signed long oldcount, woken, loop; + + rwsemtrace(sem, "Entering __rwsem_do_wake"); + + if (downgrading) + goto dont_wake_writers; + + /* if we came through an up_xxxx() call, we only only wake someone up + * if we can transition the active part of the count from 0 -> 1 + */ + try_again: + oldcount = rwsem_atomic_update(RWSEM_ACTIVE_BIAS, sem) + - RWSEM_ACTIVE_BIAS; + if (oldcount & RWSEM_ACTIVE_MASK) + goto undo; + + waiter = list_entry(sem->wait_list.next, struct rwsem_waiter, list); + + /* try to grant a single write lock if there's a writer at the front + * of the queue - note we leave the 'active part' of the count + * incremented by 1 and the waiting part incremented by 0x00010000 + */ + if (!(waiter->flags & RWSEM_WAITING_FOR_WRITE)) + goto readers_only; + + /* We must be careful not to touch 'waiter' after we set ->task = NULL. + * It is an allocated on the waiter's stack and may become invalid at + * any time after that point (due to a wakeup from another source). + */ + list_del(&waiter->list); + tsk = waiter->task; + mb(); + waiter->task = NULL; + wake_up_process(tsk); + put_task_struct(tsk); + goto out; + + /* don't want to wake any writers */ + dont_wake_writers: + waiter = list_entry(sem->wait_list.next, struct rwsem_waiter, list); + if (waiter->flags & RWSEM_WAITING_FOR_WRITE) + goto out; + + /* grant an infinite number of read locks to the readers at the front + * of the queue + * - note we increment the 'active part' of the count by the number of + * readers before waking any processes up + */ + readers_only: + woken = 0; + do { + woken++; + + if (waiter->list.next == &sem->wait_list) + break; + + waiter = list_entry(waiter->list.next, + struct rwsem_waiter, list); + + } while (waiter->flags & RWSEM_WAITING_FOR_READ); + + loop = woken; + woken *= RWSEM_ACTIVE_BIAS - RWSEM_WAITING_BIAS; + if (!downgrading) + /* we'd already done one increment earlier */ + woken -= RWSEM_ACTIVE_BIAS; + + rwsem_atomic_add(woken, sem); + + next = sem->wait_list.next; + for (; loop > 0; loop--) { + waiter = list_entry(next, struct rwsem_waiter, list); + next = waiter->list.next; + tsk = waiter->task; + mb(); + waiter->task = NULL; + wake_up_process(tsk); + put_task_struct(tsk); + } + + sem->wait_list.next = next; + next->prev = &sem->wait_list; + + out: + rwsemtrace(sem, "Leaving __rwsem_do_wake"); + return sem; + + /* undo the change to count, but check for a transition 1->0 */ + undo: + if (rwsem_atomic_update(-RWSEM_ACTIVE_BIAS, sem) != 0) + goto out; + goto try_again; +} + +/* + * wait for a lock to be granted + */ +static inline struct rw_semaphore * +rwsem_down_failed_common(struct rw_semaphore *sem, + struct rwsem_waiter *waiter, signed long adjustment) +{ + struct task_struct *tsk = current; + signed long count; + + set_task_state(tsk, TASK_UNINTERRUPTIBLE); + + /* set up my own style of waitqueue */ + spin_lock_irq(&sem->wait_lock); + waiter->task = tsk; + get_task_struct(tsk); + + list_add_tail(&waiter->list, &sem->wait_list); + + /* we're now waiting on the lock, but no longer actively read-locking */ + count = rwsem_atomic_update(adjustment, sem); + + /* if there are no active locks, wake the front queued process(es) up */ + if (!(count & RWSEM_ACTIVE_MASK)) + sem = __rwsem_do_wake(sem, 0); + + spin_unlock_irq(&sem->wait_lock); + + /* wait to be given the lock */ + for (;;) { + if (!waiter->task) + break; + schedule(); + set_task_state(tsk, TASK_UNINTERRUPTIBLE); + } + + tsk->state = TASK_RUNNING; + + return sem; +} + +/* + * wait for the read lock to be granted + */ +struct rw_semaphore fastcall __sched * +rwsem_down_read_failed(struct rw_semaphore *sem) +{ + struct rwsem_waiter waiter; + + rwsemtrace(sem, "Entering rwsem_down_read_failed"); + + waiter.flags = RWSEM_WAITING_FOR_READ; + rwsem_down_failed_common(sem, &waiter, + RWSEM_WAITING_BIAS - RWSEM_ACTIVE_BIAS); + + rwsemtrace(sem, "Leaving rwsem_down_read_failed"); + return sem; +} + +/* + * wait for the write lock to be granted + */ +struct rw_semaphore fastcall __sched * +rwsem_down_write_failed(struct rw_semaphore *sem) +{ + struct rwsem_waiter waiter; + + rwsemtrace(sem, "Entering rwsem_down_write_failed"); + + waiter.flags = RWSEM_WAITING_FOR_WRITE; + rwsem_down_failed_common(sem, &waiter, -RWSEM_ACTIVE_BIAS); + + rwsemtrace(sem, "Leaving rwsem_down_write_failed"); + return sem; +} + +/* + * handle waking up a waiter on the semaphore + * - up_read/up_write has decremented the active part of count if we come here + */ +struct rw_semaphore fastcall *rwsem_wake(struct rw_semaphore *sem) +{ + unsigned long flags; + + rwsemtrace(sem, "Entering rwsem_wake"); + + spin_lock_irqsave(&sem->wait_lock, flags); + + /* do nothing if list empty */ + if (!list_empty(&sem->wait_list)) + sem = __rwsem_do_wake(sem, 0); + + spin_unlock_irqrestore(&sem->wait_lock, flags); + + rwsemtrace(sem, "Leaving rwsem_wake"); + + return sem; +} + +/* + * downgrade a write lock into a read lock + * - caller incremented waiting part of count and discovered it still negative + * - just wake up any readers at the front of the queue + */ +struct rw_semaphore fastcall *rwsem_downgrade_wake(struct rw_semaphore *sem) +{ + unsigned long flags; + + rwsemtrace(sem, "Entering rwsem_downgrade_wake"); + + spin_lock_irqsave(&sem->wait_lock, flags); + + /* do nothing if list empty */ + if (!list_empty(&sem->wait_list)) + sem = __rwsem_do_wake(sem, 1); + + spin_unlock_irqrestore(&sem->wait_lock, flags); + + rwsemtrace(sem, "Leaving rwsem_downgrade_wake"); + return sem; +} + +EXPORT_SYMBOL(rwsem_down_read_failed); +EXPORT_SYMBOL(rwsem_down_write_failed); +EXPORT_SYMBOL(rwsem_wake); +EXPORT_SYMBOL(rwsem_downgrade_wake); +#if RWSEM_DEBUG +EXPORT_SYMBOL(rwsemtrace); +#endif diff --git a/lib/sha1.c b/lib/sha1.c new file mode 100644 index 00000000000..2f7f1148dfd --- /dev/null +++ b/lib/sha1.c @@ -0,0 +1,96 @@ +/* + * SHA transform algorithm, originally taken from code written by + * Peter Gutmann, and placed in the public domain. + */ + +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/cryptohash.h> + +/* The SHA f()-functions. */ + +#define f1(x,y,z) (z ^ (x & (y ^ z))) /* x ? y : z */ +#define f2(x,y,z) (x ^ y ^ z) /* XOR */ +#define f3(x,y,z) ((x & y) + (z & (x ^ y))) /* majority */ + +/* The SHA Mysterious Constants */ + +#define K1 0x5A827999L /* Rounds 0-19: sqrt(2) * 2^30 */ +#define K2 0x6ED9EBA1L /* Rounds 20-39: sqrt(3) * 2^30 */ +#define K3 0x8F1BBCDCL /* Rounds 40-59: sqrt(5) * 2^30 */ +#define K4 0xCA62C1D6L /* Rounds 60-79: sqrt(10) * 2^30 */ + +/* + * sha_transform: single block SHA1 transform + * + * @digest: 160 bit digest to update + * @data: 512 bits of data to hash + * @W: 80 words of workspace (see note) + * + * This function generates a SHA1 digest for a single 512-bit block. + * Be warned, it does not handle padding and message digest, do not + * confuse it with the full FIPS 180-1 digest algorithm for variable + * length messages. + * + * Note: If the hash is security sensitive, the caller should be sure + * to clear the workspace. This is left to the caller to avoid + * unnecessary clears between chained hashing operations. + */ +void sha_transform(__u32 *digest, const char *in, __u32 *W) +{ + __u32 a, b, c, d, e, t, i; + + for (i = 0; i < 16; i++) + W[i] = be32_to_cpu(((const __u32 *)in)[i]); + + for (i = 0; i < 64; i++) + W[i+16] = rol32(W[i+13] ^ W[i+8] ^ W[i+2] ^ W[i], 1); + + a = digest[0]; + b = digest[1]; + c = digest[2]; + d = digest[3]; + e = digest[4]; + + for (i = 0; i < 20; i++) { + t = f1(b, c, d) + K1 + rol32(a, 5) + e + W[i]; + e = d; d = c; c = rol32(b, 30); b = a; a = t; + } + + for (; i < 40; i ++) { + t = f2(b, c, d) + K2 + rol32(a, 5) + e + W[i]; + e = d; d = c; c = rol32(b, 30); b = a; a = t; + } + + for (; i < 60; i ++) { + t = f3(b, c, d) + K3 + rol32(a, 5) + e + W[i]; + e = d; d = c; c = rol32(b, 30); b = a; a = t; + } + + for (; i < 80; i ++) { + t = f2(b, c, d) + K4 + rol32(a, 5) + e + W[i]; + e = d; d = c; c = rol32(b, 30); b = a; a = t; + } + + digest[0] += a; + digest[1] += b; + digest[2] += c; + digest[3] += d; + digest[4] += e; +} +EXPORT_SYMBOL(sha_transform); + +/* + * sha_init: initialize the vectors for a SHA1 digest + * + * @buf: vector to initialize + */ +void sha_init(__u32 *buf) +{ + buf[0] = 0x67452301; + buf[1] = 0xefcdab89; + buf[2] = 0x98badcfe; + buf[3] = 0x10325476; + buf[4] = 0xc3d2e1f0; +} + diff --git a/lib/sort.c b/lib/sort.c new file mode 100644 index 00000000000..ea3caedeabd --- /dev/null +++ b/lib/sort.c @@ -0,0 +1,119 @@ +/* + * A fast, small, non-recursive O(nlog n) sort for the Linux kernel + * + * Jan 23 2005 Matt Mackall <mpm@selenic.com> + */ + +#include <linux/kernel.h> +#include <linux/module.h> + +void u32_swap(void *a, void *b, int size) +{ + u32 t = *(u32 *)a; + *(u32 *)a = *(u32 *)b; + *(u32 *)b = t; +} + +void generic_swap(void *a, void *b, int size) +{ + char t; + + do { + t = *(char *)a; + *(char *)a++ = *(char *)b; + *(char *)b++ = t; + } while (--size > 0); +} + +/* + * sort - sort an array of elements + * @base: pointer to data to sort + * @num: number of elements + * @size: size of each element + * @cmp: pointer to comparison function + * @swap: pointer to swap function or NULL + * + * This function does a heapsort on the given array. You may provide a + * swap function optimized to your element type. + * + * Sorting time is O(n log n) both on average and worst-case. While + * qsort is about 20% faster on average, it suffers from exploitable + * O(n*n) worst-case behavior and extra memory requirements that make + * it less suitable for kernel use. + */ + +void sort(void *base, size_t num, size_t size, + int (*cmp)(const void *, const void *), + void (*swap)(void *, void *, int size)) +{ + /* pre-scale counters for performance */ + int i = (num/2) * size, n = num * size, c, r; + + if (!swap) + swap = (size == 4 ? u32_swap : generic_swap); + + /* heapify */ + for ( ; i >= 0; i -= size) { + for (r = i; r * 2 < n; r = c) { + c = r * 2; + if (c < n - size && cmp(base + c, base + c + size) < 0) + c += size; + if (cmp(base + r, base + c) >= 0) + break; + swap(base + r, base + c, size); + } + } + + /* sort */ + for (i = n - size; i >= 0; i -= size) { + swap(base, base + i, size); + for (r = 0; r * 2 < i; r = c) { + c = r * 2; + if (c < i - size && cmp(base + c, base + c + size) < 0) + c += size; + if (cmp(base + r, base + c) >= 0) + break; + swap(base + r, base + c, size); + } + } +} + +EXPORT_SYMBOL(sort); + +#if 0 +/* a simple boot-time regression test */ + +int cmpint(const void *a, const void *b) +{ + return *(int *)a - *(int *)b; +} + +static int sort_test(void) +{ + int *a, i, r = 0; + + a = kmalloc(1000 * sizeof(int), GFP_KERNEL); + BUG_ON(!a); + + printk("testing sort()\n"); + + for (i = 0; i < 1000; i++) { + r = (r * 725861) % 6599; + a[i] = r; + } + + sort(a, 1000, sizeof(int), cmpint, NULL); + + for (i = 0; i < 999; i++) + if (a[i] > a[i+1]) { + printk("sort() failed!\n"); + break; + } + + kfree(a); + + return 0; +} + +module_init(sort_test); +#endif diff --git a/lib/string.c b/lib/string.c new file mode 100644 index 00000000000..4bb93ad23c6 --- /dev/null +++ b/lib/string.c @@ -0,0 +1,601 @@ +/* + * linux/lib/string.c + * + * Copyright (C) 1991, 1992 Linus Torvalds + */ + +/* + * stupid library routines.. The optimized versions should generally be found + * as inline code in <asm-xx/string.h> + * + * These are buggy as well.. + * + * * Fri Jun 25 1999, Ingo Oeser <ioe@informatik.tu-chemnitz.de> + * - Added strsep() which will replace strtok() soon (because strsep() is + * reentrant and should be faster). Use only strsep() in new code, please. + * + * * Sat Feb 09 2002, Jason Thomas <jason@topic.com.au>, + * Matthew Hawkins <matt@mh.dropbear.id.au> + * - Kissed strtok() goodbye + */ + +#include <linux/types.h> +#include <linux/string.h> +#include <linux/ctype.h> +#include <linux/module.h> + +#ifndef __HAVE_ARCH_STRNICMP +/** + * strnicmp - Case insensitive, length-limited string comparison + * @s1: One string + * @s2: The other string + * @len: the maximum number of characters to compare + */ +int strnicmp(const char *s1, const char *s2, size_t len) +{ + /* Yes, Virginia, it had better be unsigned */ + unsigned char c1, c2; + + c1 = 0; c2 = 0; + if (len) { + do { + c1 = *s1; c2 = *s2; + s1++; s2++; + if (!c1) + break; + if (!c2) + break; + if (c1 == c2) + continue; + c1 = tolower(c1); + c2 = tolower(c2); + if (c1 != c2) + break; + } while (--len); + } + return (int)c1 - (int)c2; +} + +EXPORT_SYMBOL(strnicmp); +#endif + +#ifndef __HAVE_ARCH_STRCPY +/** + * strcpy - Copy a %NUL terminated string + * @dest: Where to copy the string to + * @src: Where to copy the string from + */ +char * strcpy(char * dest,const char *src) +{ + char *tmp = dest; + + while ((*dest++ = *src++) != '\0') + /* nothing */; + return tmp; +} +EXPORT_SYMBOL(strcpy); +#endif + +#ifndef __HAVE_ARCH_STRNCPY +/** + * strncpy - Copy a length-limited, %NUL-terminated string + * @dest: Where to copy the string to + * @src: Where to copy the string from + * @count: The maximum number of bytes to copy + * + * The result is not %NUL-terminated if the source exceeds + * @count bytes. + */ +char * strncpy(char * dest,const char *src,size_t count) +{ + char *tmp = dest; + + while (count) { + if ((*tmp = *src) != 0) src++; + tmp++; + count--; + } + return dest; +} +EXPORT_SYMBOL(strncpy); +#endif + +#ifndef __HAVE_ARCH_STRLCPY +/** + * strlcpy - Copy a %NUL terminated string into a sized buffer + * @dest: Where to copy the string to + * @src: Where to copy the string from + * @size: size of destination buffer + * + * Compatible with *BSD: the result is always a valid + * NUL-terminated string that fits in the buffer (unless, + * of course, the buffer size is zero). It does not pad + * out the result like strncpy() does. + */ +size_t strlcpy(char *dest, const char *src, size_t size) +{ + size_t ret = strlen(src); + + if (size) { + size_t len = (ret >= size) ? size-1 : ret; + memcpy(dest, src, len); + dest[len] = '\0'; + } + return ret; +} +EXPORT_SYMBOL(strlcpy); +#endif + +#ifndef __HAVE_ARCH_STRCAT +/** + * strcat - Append one %NUL-terminated string to another + * @dest: The string to be appended to + * @src: The string to append to it + */ +char * strcat(char * dest, const char * src) +{ + char *tmp = dest; + + while (*dest) + dest++; + while ((*dest++ = *src++) != '\0') + ; + + return tmp; +} +EXPORT_SYMBOL(strcat); +#endif + +#ifndef __HAVE_ARCH_STRNCAT +/** + * strncat - Append a length-limited, %NUL-terminated string to another + * @dest: The string to be appended to + * @src: The string to append to it + * @count: The maximum numbers of bytes to copy + * + * Note that in contrast to strncpy, strncat ensures the result is + * terminated. + */ +char * strncat(char *dest, const char *src, size_t count) +{ + char *tmp = dest; + + if (count) { + while (*dest) + dest++; + while ((*dest++ = *src++) != 0) { + if (--count == 0) { + *dest = '\0'; + break; + } + } + } + + return tmp; +} +EXPORT_SYMBOL(strncat); +#endif + +#ifndef __HAVE_ARCH_STRLCAT +/** + * strlcat - Append a length-limited, %NUL-terminated string to another + * @dest: The string to be appended to + * @src: The string to append to it + * @count: The size of the destination buffer. + */ +size_t strlcat(char *dest, const char *src, size_t count) +{ + size_t dsize = strlen(dest); + size_t len = strlen(src); + size_t res = dsize + len; + + /* This would be a bug */ + BUG_ON(dsize >= count); + + dest += dsize; + count -= dsize; + if (len >= count) + len = count-1; + memcpy(dest, src, len); + dest[len] = 0; + return res; +} +EXPORT_SYMBOL(strlcat); +#endif + +#ifndef __HAVE_ARCH_STRCMP +/** + * strcmp - Compare two strings + * @cs: One string + * @ct: Another string + */ +int strcmp(const char * cs,const char * ct) +{ + register signed char __res; + + while (1) { + if ((__res = *cs - *ct++) != 0 || !*cs++) + break; + } + + return __res; +} +EXPORT_SYMBOL(strcmp); +#endif + +#ifndef __HAVE_ARCH_STRNCMP +/** + * strncmp - Compare two length-limited strings + * @cs: One string + * @ct: Another string + * @count: The maximum number of bytes to compare + */ +int strncmp(const char * cs,const char * ct,size_t count) +{ + register signed char __res = 0; + + while (count) { + if ((__res = *cs - *ct++) != 0 || !*cs++) + break; + count--; + } + + return __res; +} +EXPORT_SYMBOL(strncmp); +#endif + +#ifndef __HAVE_ARCH_STRCHR +/** + * strchr - Find the first occurrence of a character in a string + * @s: The string to be searched + * @c: The character to search for + */ +char * strchr(const char * s, int c) +{ + for(; *s != (char) c; ++s) + if (*s == '\0') + return NULL; + return (char *) s; +} +EXPORT_SYMBOL(strchr); +#endif + +#ifndef __HAVE_ARCH_STRRCHR +/** + * strrchr - Find the last occurrence of a character in a string + * @s: The string to be searched + * @c: The character to search for + */ +char * strrchr(const char * s, int c) +{ + const char *p = s + strlen(s); + do { + if (*p == (char)c) + return (char *)p; + } while (--p >= s); + return NULL; +} +EXPORT_SYMBOL(strrchr); +#endif + +#ifndef __HAVE_ARCH_STRNCHR +/** + * strnchr - Find a character in a length limited string + * @s: The string to be searched + * @count: The number of characters to be searched + * @c: The character to search for + */ +char *strnchr(const char *s, size_t count, int c) +{ + for (; count-- && *s != '\0'; ++s) + if (*s == (char) c) + return (char *) s; + return NULL; +} +EXPORT_SYMBOL(strnchr); +#endif + +#ifndef __HAVE_ARCH_STRLEN +/** + * strlen - Find the length of a string + * @s: The string to be sized + */ +size_t strlen(const char * s) +{ + const char *sc; + + for (sc = s; *sc != '\0'; ++sc) + /* nothing */; + return sc - s; +} +EXPORT_SYMBOL(strlen); +#endif + +#ifndef __HAVE_ARCH_STRNLEN +/** + * strnlen - Find the length of a length-limited string + * @s: The string to be sized + * @count: The maximum number of bytes to search + */ +size_t strnlen(const char * s, size_t count) +{ + const char *sc; + + for (sc = s; count-- && *sc != '\0'; ++sc) + /* nothing */; + return sc - s; +} +EXPORT_SYMBOL(strnlen); +#endif + +#ifndef __HAVE_ARCH_STRSPN +/** + * strspn - Calculate the length of the initial substring of @s which only + * contain letters in @accept + * @s: The string to be searched + * @accept: The string to search for + */ +size_t strspn(const char *s, const char *accept) +{ + const char *p; + const char *a; + size_t count = 0; + + for (p = s; *p != '\0'; ++p) { + for (a = accept; *a != '\0'; ++a) { + if (*p == *a) + break; + } + if (*a == '\0') + return count; + ++count; + } + + return count; +} + +EXPORT_SYMBOL(strspn); +#endif + +/** + * strcspn - Calculate the length of the initial substring of @s which does + * not contain letters in @reject + * @s: The string to be searched + * @reject: The string to avoid + */ +size_t strcspn(const char *s, const char *reject) +{ + const char *p; + const char *r; + size_t count = 0; + + for (p = s; *p != '\0'; ++p) { + for (r = reject; *r != '\0'; ++r) { + if (*p == *r) + return count; + } + ++count; + } + + return count; +} +EXPORT_SYMBOL(strcspn); + +#ifndef __HAVE_ARCH_STRPBRK +/** + * strpbrk - Find the first occurrence of a set of characters + * @cs: The string to be searched + * @ct: The characters to search for + */ +char * strpbrk(const char * cs,const char * ct) +{ + const char *sc1,*sc2; + + for( sc1 = cs; *sc1 != '\0'; ++sc1) { + for( sc2 = ct; *sc2 != '\0'; ++sc2) { + if (*sc1 == *sc2) + return (char *) sc1; + } + } + return NULL; +} +EXPORT_SYMBOL(strpbrk); +#endif + +#ifndef __HAVE_ARCH_STRSEP +/** + * strsep - Split a string into tokens + * @s: The string to be searched + * @ct: The characters to search for + * + * strsep() updates @s to point after the token, ready for the next call. + * + * It returns empty tokens, too, behaving exactly like the libc function + * of that name. In fact, it was stolen from glibc2 and de-fancy-fied. + * Same semantics, slimmer shape. ;) + */ +char * strsep(char **s, const char *ct) +{ + char *sbegin = *s, *end; + + if (sbegin == NULL) + return NULL; + + end = strpbrk(sbegin, ct); + if (end) + *end++ = '\0'; + *s = end; + + return sbegin; +} + +EXPORT_SYMBOL(strsep); +#endif + +#ifndef __HAVE_ARCH_MEMSET +/** + * memset - Fill a region of memory with the given value + * @s: Pointer to the start of the area. + * @c: The byte to fill the area with + * @count: The size of the area. + * + * Do not use memset() to access IO space, use memset_io() instead. + */ +void * memset(void * s,int c,size_t count) +{ + char *xs = (char *) s; + + while (count--) + *xs++ = c; + + return s; +} +EXPORT_SYMBOL(memset); +#endif + +#ifndef __HAVE_ARCH_MEMCPY +/** + * memcpy - Copy one area of memory to another + * @dest: Where to copy to + * @src: Where to copy from + * @count: The size of the area. + * + * You should not use this function to access IO space, use memcpy_toio() + * or memcpy_fromio() instead. + */ +void * memcpy(void * dest,const void *src,size_t count) +{ + char *tmp = (char *) dest, *s = (char *) src; + + while (count--) + *tmp++ = *s++; + + return dest; +} +EXPORT_SYMBOL(memcpy); +#endif + +#ifndef __HAVE_ARCH_MEMMOVE +/** + * memmove - Copy one area of memory to another + * @dest: Where to copy to + * @src: Where to copy from + * @count: The size of the area. + * + * Unlike memcpy(), memmove() copes with overlapping areas. + */ +void * memmove(void * dest,const void *src,size_t count) +{ + char *tmp, *s; + + if (dest <= src) { + tmp = (char *) dest; + s = (char *) src; + while (count--) + *tmp++ = *s++; + } + else { + tmp = (char *) dest + count; + s = (char *) src + count; + while (count--) + *--tmp = *--s; + } + + return dest; +} +EXPORT_SYMBOL(memmove); +#endif + +#ifndef __HAVE_ARCH_MEMCMP +/** + * memcmp - Compare two areas of memory + * @cs: One area of memory + * @ct: Another area of memory + * @count: The size of the area. + */ +int memcmp(const void * cs,const void * ct,size_t count) +{ + const unsigned char *su1, *su2; + int res = 0; + + for( su1 = cs, su2 = ct; 0 < count; ++su1, ++su2, count--) + if ((res = *su1 - *su2) != 0) + break; + return res; +} +EXPORT_SYMBOL(memcmp); +#endif + +#ifndef __HAVE_ARCH_MEMSCAN +/** + * memscan - Find a character in an area of memory. + * @addr: The memory area + * @c: The byte to search for + * @size: The size of the area. + * + * returns the address of the first occurrence of @c, or 1 byte past + * the area if @c is not found + */ +void * memscan(void * addr, int c, size_t size) +{ + unsigned char * p = (unsigned char *) addr; + + while (size) { + if (*p == c) + return (void *) p; + p++; + size--; + } + return (void *) p; +} +EXPORT_SYMBOL(memscan); +#endif + +#ifndef __HAVE_ARCH_STRSTR +/** + * strstr - Find the first substring in a %NUL terminated string + * @s1: The string to be searched + * @s2: The string to search for + */ +char * strstr(const char * s1,const char * s2) +{ + int l1, l2; + + l2 = strlen(s2); + if (!l2) + return (char *) s1; + l1 = strlen(s1); + while (l1 >= l2) { + l1--; + if (!memcmp(s1,s2,l2)) + return (char *) s1; + s1++; + } + return NULL; +} +EXPORT_SYMBOL(strstr); +#endif + +#ifndef __HAVE_ARCH_MEMCHR +/** + * memchr - Find a character in an area of memory. + * @s: The memory area + * @c: The byte to search for + * @n: The size of the area. + * + * returns the address of the first occurrence of @c, or %NULL + * if @c is not found + */ +void *memchr(const void *s, int c, size_t n) +{ + const unsigned char *p = s; + while (n-- != 0) { + if ((unsigned char)c == *p++) { + return (void *)(p-1); + } + } + return NULL; +} +EXPORT_SYMBOL(memchr); +#endif diff --git a/lib/vsprintf.c b/lib/vsprintf.c new file mode 100644 index 00000000000..a9bda0a361f --- /dev/null +++ b/lib/vsprintf.c @@ -0,0 +1,846 @@ +/* + * linux/lib/vsprintf.c + * + * Copyright (C) 1991, 1992 Linus Torvalds + */ + +/* vsprintf.c -- Lars Wirzenius & Linus Torvalds. */ +/* + * Wirzenius wrote this portably, Torvalds fucked it up :-) + */ + +/* + * Fri Jul 13 2001 Crutcher Dunnavant <crutcher+kernel@datastacks.com> + * - changed to provide snprintf and vsnprintf functions + * So Feb 1 16:51:32 CET 2004 Juergen Quade <quade@hsnr.de> + * - scnprintf and vscnprintf + */ + +#include <stdarg.h> +#include <linux/module.h> +#include <linux/types.h> +#include <linux/string.h> +#include <linux/ctype.h> +#include <linux/kernel.h> + +#include <asm/div64.h> + +/** + * simple_strtoul - convert a string to an unsigned long + * @cp: The start of the string + * @endp: A pointer to the end of the parsed string will be placed here + * @base: The number base to use + */ +unsigned long simple_strtoul(const char *cp,char **endp,unsigned int base) +{ + unsigned long result = 0,value; + + if (!base) { + base = 10; + if (*cp == '0') { + base = 8; + cp++; + if ((toupper(*cp) == 'X') && isxdigit(cp[1])) { + cp++; + base = 16; + } + } + } else if (base == 16) { + if (cp[0] == '0' && toupper(cp[1]) == 'X') + cp += 2; + } + while (isxdigit(*cp) && + (value = isdigit(*cp) ? *cp-'0' : toupper(*cp)-'A'+10) < base) { + result = result*base + value; + cp++; + } + if (endp) + *endp = (char *)cp; + return result; +} + +EXPORT_SYMBOL(simple_strtoul); + +/** + * simple_strtol - convert a string to a signed long + * @cp: The start of the string + * @endp: A pointer to the end of the parsed string will be placed here + * @base: The number base to use + */ +long simple_strtol(const char *cp,char **endp,unsigned int base) +{ + if(*cp=='-') + return -simple_strtoul(cp+1,endp,base); + return simple_strtoul(cp,endp,base); +} + +EXPORT_SYMBOL(simple_strtol); + +/** + * simple_strtoull - convert a string to an unsigned long long + * @cp: The start of the string + * @endp: A pointer to the end of the parsed string will be placed here + * @base: The number base to use + */ +unsigned long long simple_strtoull(const char *cp,char **endp,unsigned int base) +{ + unsigned long long result = 0,value; + + if (!base) { + base = 10; + if (*cp == '0') { + base = 8; + cp++; + if ((toupper(*cp) == 'X') && isxdigit(cp[1])) { + cp++; + base = 16; + } + } + } else if (base == 16) { + if (cp[0] == '0' && toupper(cp[1]) == 'X') + cp += 2; + } + while (isxdigit(*cp) && (value = isdigit(*cp) ? *cp-'0' : (islower(*cp) + ? toupper(*cp) : *cp)-'A'+10) < base) { + result = result*base + value; + cp++; + } + if (endp) + *endp = (char *)cp; + return result; +} + +EXPORT_SYMBOL(simple_strtoull); + +/** + * simple_strtoll - convert a string to a signed long long + * @cp: The start of the string + * @endp: A pointer to the end of the parsed string will be placed here + * @base: The number base to use + */ +long long simple_strtoll(const char *cp,char **endp,unsigned int base) +{ + if(*cp=='-') + return -simple_strtoull(cp+1,endp,base); + return simple_strtoull(cp,endp,base); +} + +static int skip_atoi(const char **s) +{ + int i=0; + + while (isdigit(**s)) + i = i*10 + *((*s)++) - '0'; + return i; +} + +#define ZEROPAD 1 /* pad with zero */ +#define SIGN 2 /* unsigned/signed long */ +#define PLUS 4 /* show plus */ +#define SPACE 8 /* space if plus */ +#define LEFT 16 /* left justified */ +#define SPECIAL 32 /* 0x */ +#define LARGE 64 /* use 'ABCDEF' instead of 'abcdef' */ + +static char * number(char * buf, char * end, unsigned long long num, int base, int size, int precision, int type) +{ + char c,sign,tmp[66]; + const char *digits; + static const char small_digits[] = "0123456789abcdefghijklmnopqrstuvwxyz"; + static const char large_digits[] = "0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZ"; + int i; + + digits = (type & LARGE) ? large_digits : small_digits; + if (type & LEFT) + type &= ~ZEROPAD; + if (base < 2 || base > 36) + return NULL; + c = (type & ZEROPAD) ? '0' : ' '; + sign = 0; + if (type & SIGN) { + if ((signed long long) num < 0) { + sign = '-'; + num = - (signed long long) num; + size--; + } else if (type & PLUS) { + sign = '+'; + size--; + } else if (type & SPACE) { + sign = ' '; + size--; + } + } + if (type & SPECIAL) { + if (base == 16) + size -= 2; + else if (base == 8) + size--; + } + i = 0; + if (num == 0) + tmp[i++]='0'; + else while (num != 0) + tmp[i++] = digits[do_div(num,base)]; + if (i > precision) + precision = i; + size -= precision; + if (!(type&(ZEROPAD+LEFT))) { + while(size-->0) { + if (buf <= end) + *buf = ' '; + ++buf; + } + } + if (sign) { + if (buf <= end) + *buf = sign; + ++buf; + } + if (type & SPECIAL) { + if (base==8) { + if (buf <= end) + *buf = '0'; + ++buf; + } else if (base==16) { + if (buf <= end) + *buf = '0'; + ++buf; + if (buf <= end) + *buf = digits[33]; + ++buf; + } + } + if (!(type & LEFT)) { + while (size-- > 0) { + if (buf <= end) + *buf = c; + ++buf; + } + } + while (i < precision--) { + if (buf <= end) + *buf = '0'; + ++buf; + } + while (i-- > 0) { + if (buf <= end) + *buf = tmp[i]; + ++buf; + } + while (size-- > 0) { + if (buf <= end) + *buf = ' '; + ++buf; + } + return buf; +} + +/** + * vsnprintf - Format a string and place it in a buffer + * @buf: The buffer to place the result into + * @size: The size of the buffer, including the trailing null space + * @fmt: The format string to use + * @args: Arguments for the format string + * + * The return value is the number of characters which would + * be generated for the given input, excluding the trailing + * '\0', as per ISO C99. If you want to have the exact + * number of characters written into @buf as return value + * (not including the trailing '\0'), use vscnprintf. If the + * return is greater than or equal to @size, the resulting + * string is truncated. + * + * Call this function if you are already dealing with a va_list. + * You probably want snprintf instead. + */ +int vsnprintf(char *buf, size_t size, const char *fmt, va_list args) +{ + int len; + unsigned long long num; + int i, base; + char *str, *end, c; + const char *s; + + int flags; /* flags to number() */ + + int field_width; /* width of output field */ + int precision; /* min. # of digits for integers; max + number of chars for from string */ + int qualifier; /* 'h', 'l', or 'L' for integer fields */ + /* 'z' support added 23/7/1999 S.H. */ + /* 'z' changed to 'Z' --davidm 1/25/99 */ + + /* Reject out-of-range values early */ + if (unlikely((int) size < 0)) { + /* There can be only one.. */ + static int warn = 1; + WARN_ON(warn); + warn = 0; + return 0; + } + + str = buf; + end = buf + size - 1; + + if (end < buf - 1) { + end = ((void *) -1); + size = end - buf + 1; + } + + for (; *fmt ; ++fmt) { + if (*fmt != '%') { + if (str <= end) + *str = *fmt; + ++str; + continue; + } + + /* process flags */ + flags = 0; + repeat: + ++fmt; /* this also skips first '%' */ + switch (*fmt) { + case '-': flags |= LEFT; goto repeat; + case '+': flags |= PLUS; goto repeat; + case ' ': flags |= SPACE; goto repeat; + case '#': flags |= SPECIAL; goto repeat; + case '0': flags |= ZEROPAD; goto repeat; + } + + /* get field width */ + field_width = -1; + if (isdigit(*fmt)) + field_width = skip_atoi(&fmt); + else if (*fmt == '*') { + ++fmt; + /* it's the next argument */ + field_width = va_arg(args, int); + if (field_width < 0) { + field_width = -field_width; + flags |= LEFT; + } + } + + /* get the precision */ + precision = -1; + if (*fmt == '.') { + ++fmt; + if (isdigit(*fmt)) + precision = skip_atoi(&fmt); + else if (*fmt == '*') { + ++fmt; + /* it's the next argument */ + precision = va_arg(args, int); + } + if (precision < 0) + precision = 0; + } + + /* get the conversion qualifier */ + qualifier = -1; + if (*fmt == 'h' || *fmt == 'l' || *fmt == 'L' || + *fmt =='Z' || *fmt == 'z') { + qualifier = *fmt; + ++fmt; + if (qualifier == 'l' && *fmt == 'l') { + qualifier = 'L'; + ++fmt; + } + } + + /* default base */ + base = 10; + + switch (*fmt) { + case 'c': + if (!(flags & LEFT)) { + while (--field_width > 0) { + if (str <= end) + *str = ' '; + ++str; + } + } + c = (unsigned char) va_arg(args, int); + if (str <= end) + *str = c; + ++str; + while (--field_width > 0) { + if (str <= end) + *str = ' '; + ++str; + } + continue; + + case 's': + s = va_arg(args, char *); + if ((unsigned long)s < PAGE_SIZE) + s = "<NULL>"; + + len = strnlen(s, precision); + + if (!(flags & LEFT)) { + while (len < field_width--) { + if (str <= end) + *str = ' '; + ++str; + } + } + for (i = 0; i < len; ++i) { + if (str <= end) + *str = *s; + ++str; ++s; + } + while (len < field_width--) { + if (str <= end) + *str = ' '; + ++str; + } + continue; + + case 'p': + if (field_width == -1) { + field_width = 2*sizeof(void *); + flags |= ZEROPAD; + } + str = number(str, end, + (unsigned long) va_arg(args, void *), + 16, field_width, precision, flags); + continue; + + + case 'n': + /* FIXME: + * What does C99 say about the overflow case here? */ + if (qualifier == 'l') { + long * ip = va_arg(args, long *); + *ip = (str - buf); + } else if (qualifier == 'Z' || qualifier == 'z') { + size_t * ip = va_arg(args, size_t *); + *ip = (str - buf); + } else { + int * ip = va_arg(args, int *); + *ip = (str - buf); + } + continue; + + case '%': + if (str <= end) + *str = '%'; + ++str; + continue; + + /* integer number formats - set up the flags and "break" */ + case 'o': + base = 8; + break; + + case 'X': + flags |= LARGE; + case 'x': + base = 16; + break; + + case 'd': + case 'i': + flags |= SIGN; + case 'u': + break; + + default: + if (str <= end) + *str = '%'; + ++str; + if (*fmt) { + if (str <= end) + *str = *fmt; + ++str; + } else { + --fmt; + } + continue; + } + if (qualifier == 'L') + num = va_arg(args, long long); + else if (qualifier == 'l') { + num = va_arg(args, unsigned long); + if (flags & SIGN) + num = (signed long) num; + } else if (qualifier == 'Z' || qualifier == 'z') { + num = va_arg(args, size_t); + } else if (qualifier == 'h') { + num = (unsigned short) va_arg(args, int); + if (flags & SIGN) + num = (signed short) num; + } else { + num = va_arg(args, unsigned int); + if (flags & SIGN) + num = (signed int) num; + } + str = number(str, end, num, base, + field_width, precision, flags); + } + if (str <= end) + *str = '\0'; + else if (size > 0) + /* don't write out a null byte if the buf size is zero */ + *end = '\0'; + /* the trailing null byte doesn't count towards the total + * ++str; + */ + return str-buf; +} + +EXPORT_SYMBOL(vsnprintf); + +/** + * vscnprintf - Format a string and place it in a buffer + * @buf: The buffer to place the result into + * @size: The size of the buffer, including the trailing null space + * @fmt: The format string to use + * @args: Arguments for the format string + * + * The return value is the number of characters which have been written into + * the @buf not including the trailing '\0'. If @size is <= 0 the function + * returns 0. + * + * Call this function if you are already dealing with a va_list. + * You probably want scnprintf instead. + */ +int vscnprintf(char *buf, size_t size, const char *fmt, va_list args) +{ + int i; + + i=vsnprintf(buf,size,fmt,args); + return (i >= size) ? (size - 1) : i; +} + +EXPORT_SYMBOL(vscnprintf); + +/** + * snprintf - Format a string and place it in a buffer + * @buf: The buffer to place the result into + * @size: The size of the buffer, including the trailing null space + * @fmt: The format string to use + * @...: Arguments for the format string + * + * The return value is the number of characters which would be + * generated for the given input, excluding the trailing null, + * as per ISO C99. If the return is greater than or equal to + * @size, the resulting string is truncated. + */ +int snprintf(char * buf, size_t size, const char *fmt, ...) +{ + va_list args; + int i; + + va_start(args, fmt); + i=vsnprintf(buf,size,fmt,args); + va_end(args); + return i; +} + +EXPORT_SYMBOL(snprintf); + +/** + * scnprintf - Format a string and place it in a buffer + * @buf: The buffer to place the result into + * @size: The size of the buffer, including the trailing null space + * @fmt: The format string to use + * @...: Arguments for the format string + * + * The return value is the number of characters written into @buf not including + * the trailing '\0'. If @size is <= 0 the function returns 0. If the return is + * greater than or equal to @size, the resulting string is truncated. + */ + +int scnprintf(char * buf, size_t size, const char *fmt, ...) +{ + va_list args; + int i; + + va_start(args, fmt); + i = vsnprintf(buf, size, fmt, args); + va_end(args); + return (i >= size) ? (size - 1) : i; +} +EXPORT_SYMBOL(scnprintf); + +/** + * vsprintf - Format a string and place it in a buffer + * @buf: The buffer to place the result into + * @fmt: The format string to use + * @args: Arguments for the format string + * + * The function returns the number of characters written + * into @buf. Use vsnprintf or vscnprintf in order to avoid + * buffer overflows. + * + * Call this function if you are already dealing with a va_list. + * You probably want sprintf instead. + */ +int vsprintf(char *buf, const char *fmt, va_list args) +{ + return vsnprintf(buf, INT_MAX, fmt, args); +} + +EXPORT_SYMBOL(vsprintf); + +/** + * sprintf - Format a string and place it in a buffer + * @buf: The buffer to place the result into + * @fmt: The format string to use + * @...: Arguments for the format string + * + * The function returns the number of characters written + * into @buf. Use snprintf or scnprintf in order to avoid + * buffer overflows. + */ +int sprintf(char * buf, const char *fmt, ...) +{ + va_list args; + int i; + + va_start(args, fmt); + i=vsnprintf(buf, INT_MAX, fmt, args); + va_end(args); + return i; +} + +EXPORT_SYMBOL(sprintf); + +/** + * vsscanf - Unformat a buffer into a list of arguments + * @buf: input buffer + * @fmt: format of buffer + * @args: arguments + */ +int vsscanf(const char * buf, const char * fmt, va_list args) +{ + const char *str = buf; + char *next; + char digit; + int num = 0; + int qualifier; + int base; + int field_width; + int is_sign = 0; + + while(*fmt && *str) { + /* skip any white space in format */ + /* white space in format matchs any amount of + * white space, including none, in the input. + */ + if (isspace(*fmt)) { + while (isspace(*fmt)) + ++fmt; + while (isspace(*str)) + ++str; + } + + /* anything that is not a conversion must match exactly */ + if (*fmt != '%' && *fmt) { + if (*fmt++ != *str++) + break; + continue; + } + + if (!*fmt) + break; + ++fmt; + + /* skip this conversion. + * advance both strings to next white space + */ + if (*fmt == '*') { + while (!isspace(*fmt) && *fmt) + fmt++; + while (!isspace(*str) && *str) + str++; + continue; + } + + /* get field width */ + field_width = -1; + if (isdigit(*fmt)) + field_width = skip_atoi(&fmt); + + /* get conversion qualifier */ + qualifier = -1; + if (*fmt == 'h' || *fmt == 'l' || *fmt == 'L' || + *fmt == 'Z' || *fmt == 'z') { + qualifier = *fmt++; + if (unlikely(qualifier == *fmt)) { + if (qualifier == 'h') { + qualifier = 'H'; + fmt++; + } else if (qualifier == 'l') { + qualifier = 'L'; + fmt++; + } + } + } + base = 10; + is_sign = 0; + + if (!*fmt || !*str) + break; + + switch(*fmt++) { + case 'c': + { + char *s = (char *) va_arg(args,char*); + if (field_width == -1) + field_width = 1; + do { + *s++ = *str++; + } while (--field_width > 0 && *str); + num++; + } + continue; + case 's': + { + char *s = (char *) va_arg(args, char *); + if(field_width == -1) + field_width = INT_MAX; + /* first, skip leading white space in buffer */ + while (isspace(*str)) + str++; + + /* now copy until next white space */ + while (*str && !isspace(*str) && field_width--) { + *s++ = *str++; + } + *s = '\0'; + num++; + } + continue; + case 'n': + /* return number of characters read so far */ + { + int *i = (int *)va_arg(args,int*); + *i = str - buf; + } + continue; + case 'o': + base = 8; + break; + case 'x': + case 'X': + base = 16; + break; + case 'i': + base = 0; + case 'd': + is_sign = 1; + case 'u': + break; + case '%': + /* looking for '%' in str */ + if (*str++ != '%') + return num; + continue; + default: + /* invalid format; stop here */ + return num; + } + + /* have some sort of integer conversion. + * first, skip white space in buffer. + */ + while (isspace(*str)) + str++; + + digit = *str; + if (is_sign && digit == '-') + digit = *(str + 1); + + if (!digit + || (base == 16 && !isxdigit(digit)) + || (base == 10 && !isdigit(digit)) + || (base == 8 && (!isdigit(digit) || digit > '7')) + || (base == 0 && !isdigit(digit))) + break; + + switch(qualifier) { + case 'H': /* that's 'hh' in format */ + if (is_sign) { + signed char *s = (signed char *) va_arg(args,signed char *); + *s = (signed char) simple_strtol(str,&next,base); + } else { + unsigned char *s = (unsigned char *) va_arg(args, unsigned char *); + *s = (unsigned char) simple_strtoul(str, &next, base); + } + break; + case 'h': + if (is_sign) { + short *s = (short *) va_arg(args,short *); + *s = (short) simple_strtol(str,&next,base); + } else { + unsigned short *s = (unsigned short *) va_arg(args, unsigned short *); + *s = (unsigned short) simple_strtoul(str, &next, base); + } + break; + case 'l': + if (is_sign) { + long *l = (long *) va_arg(args,long *); + *l = simple_strtol(str,&next,base); + } else { + unsigned long *l = (unsigned long*) va_arg(args,unsigned long*); + *l = simple_strtoul(str,&next,base); + } + break; + case 'L': + if (is_sign) { + long long *l = (long long*) va_arg(args,long long *); + *l = simple_strtoll(str,&next,base); + } else { + unsigned long long *l = (unsigned long long*) va_arg(args,unsigned long long*); + *l = simple_strtoull(str,&next,base); + } + break; + case 'Z': + case 'z': + { + size_t *s = (size_t*) va_arg(args,size_t*); + *s = (size_t) simple_strtoul(str,&next,base); + } + break; + default: + if (is_sign) { + int *i = (int *) va_arg(args, int*); + *i = (int) simple_strtol(str,&next,base); + } else { + unsigned int *i = (unsigned int*) va_arg(args, unsigned int*); + *i = (unsigned int) simple_strtoul(str,&next,base); + } + break; + } + num++; + + if (!next) + break; + str = next; + } + return num; +} + +EXPORT_SYMBOL(vsscanf); + +/** + * sscanf - Unformat a buffer into a list of arguments + * @buf: input buffer + * @fmt: formatting of buffer + * @...: resulting arguments + */ +int sscanf(const char * buf, const char * fmt, ...) +{ + va_list args; + int i; + + va_start(args,fmt); + i = vsscanf(buf,fmt,args); + va_end(args); + return i; +} + +EXPORT_SYMBOL(sscanf); diff --git a/lib/zlib_deflate/Makefile b/lib/zlib_deflate/Makefile new file mode 100644 index 00000000000..86275e3fdcb --- /dev/null +++ b/lib/zlib_deflate/Makefile @@ -0,0 +1,11 @@ +# +# This is a modified version of zlib, which does all memory +# allocation ahead of time. +# +# This is the compression code, see zlib_inflate for the +# decompression code. +# + +obj-$(CONFIG_ZLIB_DEFLATE) += zlib_deflate.o + +zlib_deflate-objs := deflate.o deftree.o deflate_syms.o diff --git a/lib/zlib_deflate/deflate.c b/lib/zlib_deflate/deflate.c new file mode 100644 index 00000000000..ad9a1bf4fc6 --- /dev/null +++ b/lib/zlib_deflate/deflate.c @@ -0,0 +1,1268 @@ +/* +++ deflate.c */ +/* deflate.c -- compress data using the deflation algorithm + * Copyright (C) 1995-1996 Jean-loup Gailly. + * For conditions of distribution and use, see copyright notice in zlib.h + */ + +/* + * ALGORITHM + * + * The "deflation" process depends on being able to identify portions + * of the input text which are identical to earlier input (within a + * sliding window trailing behind the input currently being processed). + * + * The most straightforward technique turns out to be the fastest for + * most input files: try all possible matches and select the longest. + * The key feature of this algorithm is that insertions into the string + * dictionary are very simple and thus fast, and deletions are avoided + * completely. Insertions are performed at each input character, whereas + * string matches are performed only when the previous match ends. So it + * is preferable to spend more time in matches to allow very fast string + * insertions and avoid deletions. The matching algorithm for small + * strings is inspired from that of Rabin & Karp. A brute force approach + * is used to find longer strings when a small match has been found. + * A similar algorithm is used in comic (by Jan-Mark Wams) and freeze + * (by Leonid Broukhis). + * A previous version of this file used a more sophisticated algorithm + * (by Fiala and Greene) which is guaranteed to run in linear amortized + * time, but has a larger average cost, uses more memory and is patented. + * However the F&G algorithm may be faster for some highly redundant + * files if the parameter max_chain_length (described below) is too large. + * + * ACKNOWLEDGEMENTS + * + * The idea of lazy evaluation of matches is due to Jan-Mark Wams, and + * I found it in 'freeze' written by Leonid Broukhis. + * Thanks to many people for bug reports and testing. + * + * REFERENCES + * + * Deutsch, L.P.,"DEFLATE Compressed Data Format Specification". + * Available in ftp://ds.internic.net/rfc/rfc1951.txt + * + * A description of the Rabin and Karp algorithm is given in the book + * "Algorithms" by R. Sedgewick, Addison-Wesley, p252. + * + * Fiala,E.R., and Greene,D.H. + * Data Compression with Finite Windows, Comm.ACM, 32,4 (1989) 490-595 + * + */ + +#include <linux/module.h> +#include <linux/zutil.h> +#include "defutil.h" + + +/* =========================================================================== + * Function prototypes. + */ +typedef enum { + need_more, /* block not completed, need more input or more output */ + block_done, /* block flush performed */ + finish_started, /* finish started, need only more output at next deflate */ + finish_done /* finish done, accept no more input or output */ +} block_state; + +typedef block_state (*compress_func) (deflate_state *s, int flush); +/* Compression function. Returns the block state after the call. */ + +static void fill_window (deflate_state *s); +static block_state deflate_stored (deflate_state *s, int flush); +static block_state deflate_fast (deflate_state *s, int flush); +static block_state deflate_slow (deflate_state *s, int flush); +static void lm_init (deflate_state *s); +static void putShortMSB (deflate_state *s, uInt b); +static void flush_pending (z_streamp strm); +static int read_buf (z_streamp strm, Byte *buf, unsigned size); +static uInt longest_match (deflate_state *s, IPos cur_match); + +#ifdef DEBUG_ZLIB +static void check_match (deflate_state *s, IPos start, IPos match, + int length); +#endif + +/* =========================================================================== + * Local data + */ + +#define NIL 0 +/* Tail of hash chains */ + +#ifndef TOO_FAR +# define TOO_FAR 4096 +#endif +/* Matches of length 3 are discarded if their distance exceeds TOO_FAR */ + +#define MIN_LOOKAHEAD (MAX_MATCH+MIN_MATCH+1) +/* Minimum amount of lookahead, except at the end of the input file. + * See deflate.c for comments about the MIN_MATCH+1. + */ + +/* Values for max_lazy_match, good_match and max_chain_length, depending on + * the desired pack level (0..9). The values given below have been tuned to + * exclude worst case performance for pathological files. Better values may be + * found for specific files. + */ +typedef struct config_s { + ush good_length; /* reduce lazy search above this match length */ + ush max_lazy; /* do not perform lazy search above this match length */ + ush nice_length; /* quit search above this match length */ + ush max_chain; + compress_func func; +} config; + +static const config configuration_table[10] = { +/* good lazy nice chain */ +/* 0 */ {0, 0, 0, 0, deflate_stored}, /* store only */ +/* 1 */ {4, 4, 8, 4, deflate_fast}, /* maximum speed, no lazy matches */ +/* 2 */ {4, 5, 16, 8, deflate_fast}, +/* 3 */ {4, 6, 32, 32, deflate_fast}, + +/* 4 */ {4, 4, 16, 16, deflate_slow}, /* lazy matches */ +/* 5 */ {8, 16, 32, 32, deflate_slow}, +/* 6 */ {8, 16, 128, 128, deflate_slow}, +/* 7 */ {8, 32, 128, 256, deflate_slow}, +/* 8 */ {32, 128, 258, 1024, deflate_slow}, +/* 9 */ {32, 258, 258, 4096, deflate_slow}}; /* maximum compression */ + +/* Note: the deflate() code requires max_lazy >= MIN_MATCH and max_chain >= 4 + * For deflate_fast() (levels <= 3) good is ignored and lazy has a different + * meaning. + */ + +#define EQUAL 0 +/* result of memcmp for equal strings */ + +/* =========================================================================== + * Update a hash value with the given input byte + * IN assertion: all calls to to UPDATE_HASH are made with consecutive + * input characters, so that a running hash key can be computed from the + * previous key instead of complete recalculation each time. + */ +#define UPDATE_HASH(s,h,c) (h = (((h)<<s->hash_shift) ^ (c)) & s->hash_mask) + + +/* =========================================================================== + * Insert string str in the dictionary and set match_head to the previous head + * of the hash chain (the most recent string with same hash key). Return + * the previous length of the hash chain. + * IN assertion: all calls to to INSERT_STRING are made with consecutive + * input characters and the first MIN_MATCH bytes of str are valid + * (except for the last MIN_MATCH-1 bytes of the input file). + */ +#define INSERT_STRING(s, str, match_head) \ + (UPDATE_HASH(s, s->ins_h, s->window[(str) + (MIN_MATCH-1)]), \ + s->prev[(str) & s->w_mask] = match_head = s->head[s->ins_h], \ + s->head[s->ins_h] = (Pos)(str)) + +/* =========================================================================== + * Initialize the hash table (avoiding 64K overflow for 16 bit systems). + * prev[] will be initialized on the fly. + */ +#define CLEAR_HASH(s) \ + s->head[s->hash_size-1] = NIL; \ + memset((char *)s->head, 0, (unsigned)(s->hash_size-1)*sizeof(*s->head)); + +/* ========================================================================= */ +int zlib_deflateInit_( + z_streamp strm, + int level, + const char *version, + int stream_size +) +{ + return zlib_deflateInit2_(strm, level, Z_DEFLATED, MAX_WBITS, + DEF_MEM_LEVEL, + Z_DEFAULT_STRATEGY, version, stream_size); + /* To do: ignore strm->next_in if we use it as window */ +} + +/* ========================================================================= */ +int zlib_deflateInit2_( + z_streamp strm, + int level, + int method, + int windowBits, + int memLevel, + int strategy, + const char *version, + int stream_size +) +{ + deflate_state *s; + int noheader = 0; + static char* my_version = ZLIB_VERSION; + deflate_workspace *mem; + + ush *overlay; + /* We overlay pending_buf and d_buf+l_buf. This works since the average + * output size for (length,distance) codes is <= 24 bits. + */ + + if (version == NULL || version[0] != my_version[0] || + stream_size != sizeof(z_stream)) { + return Z_VERSION_ERROR; + } + if (strm == NULL) return Z_STREAM_ERROR; + + strm->msg = NULL; + + if (level == Z_DEFAULT_COMPRESSION) level = 6; + + mem = (deflate_workspace *) strm->workspace; + + if (windowBits < 0) { /* undocumented feature: suppress zlib header */ + noheader = 1; + windowBits = -windowBits; + } + if (memLevel < 1 || memLevel > MAX_MEM_LEVEL || method != Z_DEFLATED || + windowBits < 9 || windowBits > 15 || level < 0 || level > 9 || + strategy < 0 || strategy > Z_HUFFMAN_ONLY) { + return Z_STREAM_ERROR; + } + s = (deflate_state *) &(mem->deflate_memory); + strm->state = (struct internal_state *)s; + s->strm = strm; + + s->noheader = noheader; + s->w_bits = windowBits; + s->w_size = 1 << s->w_bits; + s->w_mask = s->w_size - 1; + + s->hash_bits = memLevel + 7; + s->hash_size = 1 << s->hash_bits; + s->hash_mask = s->hash_size - 1; + s->hash_shift = ((s->hash_bits+MIN_MATCH-1)/MIN_MATCH); + + s->window = (Byte *) mem->window_memory; + s->prev = (Pos *) mem->prev_memory; + s->head = (Pos *) mem->head_memory; + + s->lit_bufsize = 1 << (memLevel + 6); /* 16K elements by default */ + + overlay = (ush *) mem->overlay_memory; + s->pending_buf = (uch *) overlay; + s->pending_buf_size = (ulg)s->lit_bufsize * (sizeof(ush)+2L); + + s->d_buf = overlay + s->lit_bufsize/sizeof(ush); + s->l_buf = s->pending_buf + (1+sizeof(ush))*s->lit_bufsize; + + s->level = level; + s->strategy = strategy; + s->method = (Byte)method; + + return zlib_deflateReset(strm); +} + +/* ========================================================================= */ +int zlib_deflateSetDictionary( + z_streamp strm, + const Byte *dictionary, + uInt dictLength +) +{ + deflate_state *s; + uInt length = dictLength; + uInt n; + IPos hash_head = 0; + + if (strm == NULL || strm->state == NULL || dictionary == NULL) + return Z_STREAM_ERROR; + + s = (deflate_state *) strm->state; + if (s->status != INIT_STATE) return Z_STREAM_ERROR; + + strm->adler = zlib_adler32(strm->adler, dictionary, dictLength); + + if (length < MIN_MATCH) return Z_OK; + if (length > MAX_DIST(s)) { + length = MAX_DIST(s); +#ifndef USE_DICT_HEAD + dictionary += dictLength - length; /* use the tail of the dictionary */ +#endif + } + memcpy((char *)s->window, dictionary, length); + s->strstart = length; + s->block_start = (long)length; + + /* Insert all strings in the hash table (except for the last two bytes). + * s->lookahead stays null, so s->ins_h will be recomputed at the next + * call of fill_window. + */ + s->ins_h = s->window[0]; + UPDATE_HASH(s, s->ins_h, s->window[1]); + for (n = 0; n <= length - MIN_MATCH; n++) { + INSERT_STRING(s, n, hash_head); + } + if (hash_head) hash_head = 0; /* to make compiler happy */ + return Z_OK; +} + +/* ========================================================================= */ +int zlib_deflateReset( + z_streamp strm +) +{ + deflate_state *s; + + if (strm == NULL || strm->state == NULL) + return Z_STREAM_ERROR; + + strm->total_in = strm->total_out = 0; + strm->msg = NULL; + strm->data_type = Z_UNKNOWN; + + s = (deflate_state *)strm->state; + s->pending = 0; + s->pending_out = s->pending_buf; + + if (s->noheader < 0) { + s->noheader = 0; /* was set to -1 by deflate(..., Z_FINISH); */ + } + s->status = s->noheader ? BUSY_STATE : INIT_STATE; + strm->adler = 1; + s->last_flush = Z_NO_FLUSH; + + zlib_tr_init(s); + lm_init(s); + + return Z_OK; +} + +/* ========================================================================= */ +int zlib_deflateParams( + z_streamp strm, + int level, + int strategy +) +{ + deflate_state *s; + compress_func func; + int err = Z_OK; + + if (strm == NULL || strm->state == NULL) return Z_STREAM_ERROR; + s = (deflate_state *) strm->state; + + if (level == Z_DEFAULT_COMPRESSION) { + level = 6; + } + if (level < 0 || level > 9 || strategy < 0 || strategy > Z_HUFFMAN_ONLY) { + return Z_STREAM_ERROR; + } + func = configuration_table[s->level].func; + + if (func != configuration_table[level].func && strm->total_in != 0) { + /* Flush the last buffer: */ + err = zlib_deflate(strm, Z_PARTIAL_FLUSH); + } + if (s->level != level) { + s->level = level; + s->max_lazy_match = configuration_table[level].max_lazy; + s->good_match = configuration_table[level].good_length; + s->nice_match = configuration_table[level].nice_length; + s->max_chain_length = configuration_table[level].max_chain; + } + s->strategy = strategy; + return err; +} + +/* ========================================================================= + * Put a short in the pending buffer. The 16-bit value is put in MSB order. + * IN assertion: the stream state is correct and there is enough room in + * pending_buf. + */ +static void putShortMSB( + deflate_state *s, + uInt b +) +{ + put_byte(s, (Byte)(b >> 8)); + put_byte(s, (Byte)(b & 0xff)); +} + +/* ========================================================================= + * Flush as much pending output as possible. All deflate() output goes + * through this function so some applications may wish to modify it + * to avoid allocating a large strm->next_out buffer and copying into it. + * (See also read_buf()). + */ +static void flush_pending( + z_streamp strm +) +{ + deflate_state *s = (deflate_state *) strm->state; + unsigned len = s->pending; + + if (len > strm->avail_out) len = strm->avail_out; + if (len == 0) return; + + if (strm->next_out != NULL) { + memcpy(strm->next_out, s->pending_out, len); + strm->next_out += len; + } + s->pending_out += len; + strm->total_out += len; + strm->avail_out -= len; + s->pending -= len; + if (s->pending == 0) { + s->pending_out = s->pending_buf; + } +} + +/* ========================================================================= */ +int zlib_deflate( + z_streamp strm, + int flush +) +{ + int old_flush; /* value of flush param for previous deflate call */ + deflate_state *s; + + if (strm == NULL || strm->state == NULL || + flush > Z_FINISH || flush < 0) { + return Z_STREAM_ERROR; + } + s = (deflate_state *) strm->state; + + if ((strm->next_in == NULL && strm->avail_in != 0) || + (s->status == FINISH_STATE && flush != Z_FINISH)) { + return Z_STREAM_ERROR; + } + if (strm->avail_out == 0) return Z_BUF_ERROR; + + s->strm = strm; /* just in case */ + old_flush = s->last_flush; + s->last_flush = flush; + + /* Write the zlib header */ + if (s->status == INIT_STATE) { + + uInt header = (Z_DEFLATED + ((s->w_bits-8)<<4)) << 8; + uInt level_flags = (s->level-1) >> 1; + + if (level_flags > 3) level_flags = 3; + header |= (level_flags << 6); + if (s->strstart != 0) header |= PRESET_DICT; + header += 31 - (header % 31); + + s->status = BUSY_STATE; + putShortMSB(s, header); + + /* Save the adler32 of the preset dictionary: */ + if (s->strstart != 0) { + putShortMSB(s, (uInt)(strm->adler >> 16)); + putShortMSB(s, (uInt)(strm->adler & 0xffff)); + } + strm->adler = 1L; + } + + /* Flush as much pending output as possible */ + if (s->pending != 0) { + flush_pending(strm); + if (strm->avail_out == 0) { + /* Since avail_out is 0, deflate will be called again with + * more output space, but possibly with both pending and + * avail_in equal to zero. There won't be anything to do, + * but this is not an error situation so make sure we + * return OK instead of BUF_ERROR at next call of deflate: + */ + s->last_flush = -1; + return Z_OK; + } + + /* Make sure there is something to do and avoid duplicate consecutive + * flushes. For repeated and useless calls with Z_FINISH, we keep + * returning Z_STREAM_END instead of Z_BUFF_ERROR. + */ + } else if (strm->avail_in == 0 && flush <= old_flush && + flush != Z_FINISH) { + return Z_BUF_ERROR; + } + + /* User must not provide more input after the first FINISH: */ + if (s->status == FINISH_STATE && strm->avail_in != 0) { + return Z_BUF_ERROR; + } + + /* Start a new block or continue the current one. + */ + if (strm->avail_in != 0 || s->lookahead != 0 || + (flush != Z_NO_FLUSH && s->status != FINISH_STATE)) { + block_state bstate; + + bstate = (*(configuration_table[s->level].func))(s, flush); + + if (bstate == finish_started || bstate == finish_done) { + s->status = FINISH_STATE; + } + if (bstate == need_more || bstate == finish_started) { + if (strm->avail_out == 0) { + s->last_flush = -1; /* avoid BUF_ERROR next call, see above */ + } + return Z_OK; + /* If flush != Z_NO_FLUSH && avail_out == 0, the next call + * of deflate should use the same flush parameter to make sure + * that the flush is complete. So we don't have to output an + * empty block here, this will be done at next call. This also + * ensures that for a very small output buffer, we emit at most + * one empty block. + */ + } + if (bstate == block_done) { + if (flush == Z_PARTIAL_FLUSH) { + zlib_tr_align(s); + } else if (flush == Z_PACKET_FLUSH) { + /* Output just the 3-bit `stored' block type value, + but not a zero length. */ + zlib_tr_stored_type_only(s); + } else { /* FULL_FLUSH or SYNC_FLUSH */ + zlib_tr_stored_block(s, (char*)0, 0L, 0); + /* For a full flush, this empty block will be recognized + * as a special marker by inflate_sync(). + */ + if (flush == Z_FULL_FLUSH) { + CLEAR_HASH(s); /* forget history */ + } + } + flush_pending(strm); + if (strm->avail_out == 0) { + s->last_flush = -1; /* avoid BUF_ERROR at next call, see above */ + return Z_OK; + } + } + } + Assert(strm->avail_out > 0, "bug2"); + + if (flush != Z_FINISH) return Z_OK; + if (s->noheader) return Z_STREAM_END; + + /* Write the zlib trailer (adler32) */ + putShortMSB(s, (uInt)(strm->adler >> 16)); + putShortMSB(s, (uInt)(strm->adler & 0xffff)); + flush_pending(strm); + /* If avail_out is zero, the application will call deflate again + * to flush the rest. + */ + s->noheader = -1; /* write the trailer only once! */ + return s->pending != 0 ? Z_OK : Z_STREAM_END; +} + +/* ========================================================================= */ +int zlib_deflateEnd( + z_streamp strm +) +{ + int status; + deflate_state *s; + + if (strm == NULL || strm->state == NULL) return Z_STREAM_ERROR; + s = (deflate_state *) strm->state; + + status = s->status; + if (status != INIT_STATE && status != BUSY_STATE && + status != FINISH_STATE) { + return Z_STREAM_ERROR; + } + + strm->state = NULL; + + return status == BUSY_STATE ? Z_DATA_ERROR : Z_OK; +} + +/* ========================================================================= + * Copy the source state to the destination state. + */ +int zlib_deflateCopy ( + z_streamp dest, + z_streamp source +) +{ +#ifdef MAXSEG_64K + return Z_STREAM_ERROR; +#else + deflate_state *ds; + deflate_state *ss; + ush *overlay; + deflate_workspace *mem; + + + if (source == NULL || dest == NULL || source->state == NULL) { + return Z_STREAM_ERROR; + } + + ss = (deflate_state *) source->state; + + *dest = *source; + + mem = (deflate_workspace *) dest->workspace; + + ds = &(mem->deflate_memory); + + dest->state = (struct internal_state *) ds; + *ds = *ss; + ds->strm = dest; + + ds->window = (Byte *) mem->window_memory; + ds->prev = (Pos *) mem->prev_memory; + ds->head = (Pos *) mem->head_memory; + overlay = (ush *) mem->overlay_memory; + ds->pending_buf = (uch *) overlay; + + memcpy(ds->window, ss->window, ds->w_size * 2 * sizeof(Byte)); + memcpy(ds->prev, ss->prev, ds->w_size * sizeof(Pos)); + memcpy(ds->head, ss->head, ds->hash_size * sizeof(Pos)); + memcpy(ds->pending_buf, ss->pending_buf, (uInt)ds->pending_buf_size); + + ds->pending_out = ds->pending_buf + (ss->pending_out - ss->pending_buf); + ds->d_buf = overlay + ds->lit_bufsize/sizeof(ush); + ds->l_buf = ds->pending_buf + (1+sizeof(ush))*ds->lit_bufsize; + + ds->l_desc.dyn_tree = ds->dyn_ltree; + ds->d_desc.dyn_tree = ds->dyn_dtree; + ds->bl_desc.dyn_tree = ds->bl_tree; + + return Z_OK; +#endif +} + +/* =========================================================================== + * Read a new buffer from the current input stream, update the adler32 + * and total number of bytes read. All deflate() input goes through + * this function so some applications may wish to modify it to avoid + * allocating a large strm->next_in buffer and copying from it. + * (See also flush_pending()). + */ +static int read_buf( + z_streamp strm, + Byte *buf, + unsigned size +) +{ + unsigned len = strm->avail_in; + + if (len > size) len = size; + if (len == 0) return 0; + + strm->avail_in -= len; + + if (!((deflate_state *)(strm->state))->noheader) { + strm->adler = zlib_adler32(strm->adler, strm->next_in, len); + } + memcpy(buf, strm->next_in, len); + strm->next_in += len; + strm->total_in += len; + + return (int)len; +} + +/* =========================================================================== + * Initialize the "longest match" routines for a new zlib stream + */ +static void lm_init( + deflate_state *s +) +{ + s->window_size = (ulg)2L*s->w_size; + + CLEAR_HASH(s); + + /* Set the default configuration parameters: + */ + s->max_lazy_match = configuration_table[s->level].max_lazy; + s->good_match = configuration_table[s->level].good_length; + s->nice_match = configuration_table[s->level].nice_length; + s->max_chain_length = configuration_table[s->level].max_chain; + + s->strstart = 0; + s->block_start = 0L; + s->lookahead = 0; + s->match_length = s->prev_length = MIN_MATCH-1; + s->match_available = 0; + s->ins_h = 0; +} + +/* =========================================================================== + * Set match_start to the longest match starting at the given string and + * return its length. Matches shorter or equal to prev_length are discarded, + * in which case the result is equal to prev_length and match_start is + * garbage. + * IN assertions: cur_match is the head of the hash chain for the current + * string (strstart) and its distance is <= MAX_DIST, and prev_length >= 1 + * OUT assertion: the match length is not greater than s->lookahead. + */ +/* For 80x86 and 680x0, an optimized version will be provided in match.asm or + * match.S. The code will be functionally equivalent. + */ +static uInt longest_match( + deflate_state *s, + IPos cur_match /* current match */ +) +{ + unsigned chain_length = s->max_chain_length;/* max hash chain length */ + register Byte *scan = s->window + s->strstart; /* current string */ + register Byte *match; /* matched string */ + register int len; /* length of current match */ + int best_len = s->prev_length; /* best match length so far */ + int nice_match = s->nice_match; /* stop if match long enough */ + IPos limit = s->strstart > (IPos)MAX_DIST(s) ? + s->strstart - (IPos)MAX_DIST(s) : NIL; + /* Stop when cur_match becomes <= limit. To simplify the code, + * we prevent matches with the string of window index 0. + */ + Pos *prev = s->prev; + uInt wmask = s->w_mask; + +#ifdef UNALIGNED_OK + /* Compare two bytes at a time. Note: this is not always beneficial. + * Try with and without -DUNALIGNED_OK to check. + */ + register Byte *strend = s->window + s->strstart + MAX_MATCH - 1; + register ush scan_start = *(ush*)scan; + register ush scan_end = *(ush*)(scan+best_len-1); +#else + register Byte *strend = s->window + s->strstart + MAX_MATCH; + register Byte scan_end1 = scan[best_len-1]; + register Byte scan_end = scan[best_len]; +#endif + + /* The code is optimized for HASH_BITS >= 8 and MAX_MATCH-2 multiple of 16. + * It is easy to get rid of this optimization if necessary. + */ + Assert(s->hash_bits >= 8 && MAX_MATCH == 258, "Code too clever"); + + /* Do not waste too much time if we already have a good match: */ + if (s->prev_length >= s->good_match) { + chain_length >>= 2; + } + /* Do not look for matches beyond the end of the input. This is necessary + * to make deflate deterministic. + */ + if ((uInt)nice_match > s->lookahead) nice_match = s->lookahead; + + Assert((ulg)s->strstart <= s->window_size-MIN_LOOKAHEAD, "need lookahead"); + + do { + Assert(cur_match < s->strstart, "no future"); + match = s->window + cur_match; + + /* Skip to next match if the match length cannot increase + * or if the match length is less than 2: + */ +#if (defined(UNALIGNED_OK) && MAX_MATCH == 258) + /* This code assumes sizeof(unsigned short) == 2. Do not use + * UNALIGNED_OK if your compiler uses a different size. + */ + if (*(ush*)(match+best_len-1) != scan_end || + *(ush*)match != scan_start) continue; + + /* It is not necessary to compare scan[2] and match[2] since they are + * always equal when the other bytes match, given that the hash keys + * are equal and that HASH_BITS >= 8. Compare 2 bytes at a time at + * strstart+3, +5, ... up to strstart+257. We check for insufficient + * lookahead only every 4th comparison; the 128th check will be made + * at strstart+257. If MAX_MATCH-2 is not a multiple of 8, it is + * necessary to put more guard bytes at the end of the window, or + * to check more often for insufficient lookahead. + */ + Assert(scan[2] == match[2], "scan[2]?"); + scan++, match++; + do { + } while (*(ush*)(scan+=2) == *(ush*)(match+=2) && + *(ush*)(scan+=2) == *(ush*)(match+=2) && + *(ush*)(scan+=2) == *(ush*)(match+=2) && + *(ush*)(scan+=2) == *(ush*)(match+=2) && + scan < strend); + /* The funny "do {}" generates better code on most compilers */ + + /* Here, scan <= window+strstart+257 */ + Assert(scan <= s->window+(unsigned)(s->window_size-1), "wild scan"); + if (*scan == *match) scan++; + + len = (MAX_MATCH - 1) - (int)(strend-scan); + scan = strend - (MAX_MATCH-1); + +#else /* UNALIGNED_OK */ + + if (match[best_len] != scan_end || + match[best_len-1] != scan_end1 || + *match != *scan || + *++match != scan[1]) continue; + + /* The check at best_len-1 can be removed because it will be made + * again later. (This heuristic is not always a win.) + * It is not necessary to compare scan[2] and match[2] since they + * are always equal when the other bytes match, given that + * the hash keys are equal and that HASH_BITS >= 8. + */ + scan += 2, match++; + Assert(*scan == *match, "match[2]?"); + + /* We check for insufficient lookahead only every 8th comparison; + * the 256th check will be made at strstart+258. + */ + do { + } while (*++scan == *++match && *++scan == *++match && + *++scan == *++match && *++scan == *++match && + *++scan == *++match && *++scan == *++match && + *++scan == *++match && *++scan == *++match && + scan < strend); + + Assert(scan <= s->window+(unsigned)(s->window_size-1), "wild scan"); + + len = MAX_MATCH - (int)(strend - scan); + scan = strend - MAX_MATCH; + +#endif /* UNALIGNED_OK */ + + if (len > best_len) { + s->match_start = cur_match; + best_len = len; + if (len >= nice_match) break; +#ifdef UNALIGNED_OK + scan_end = *(ush*)(scan+best_len-1); +#else + scan_end1 = scan[best_len-1]; + scan_end = scan[best_len]; +#endif + } + } while ((cur_match = prev[cur_match & wmask]) > limit + && --chain_length != 0); + + if ((uInt)best_len <= s->lookahead) return best_len; + return s->lookahead; +} + +#ifdef DEBUG_ZLIB +/* =========================================================================== + * Check that the match at match_start is indeed a match. + */ +static void check_match( + deflate_state *s, + IPos start, + IPos match, + int length +) +{ + /* check that the match is indeed a match */ + if (memcmp((char *)s->window + match, + (char *)s->window + start, length) != EQUAL) { + fprintf(stderr, " start %u, match %u, length %d\n", + start, match, length); + do { + fprintf(stderr, "%c%c", s->window[match++], s->window[start++]); + } while (--length != 0); + z_error("invalid match"); + } + if (z_verbose > 1) { + fprintf(stderr,"\\[%d,%d]", start-match, length); + do { putc(s->window[start++], stderr); } while (--length != 0); + } +} +#else +# define check_match(s, start, match, length) +#endif + +/* =========================================================================== + * Fill the window when the lookahead becomes insufficient. + * Updates strstart and lookahead. + * + * IN assertion: lookahead < MIN_LOOKAHEAD + * OUT assertions: strstart <= window_size-MIN_LOOKAHEAD + * At least one byte has been read, or avail_in == 0; reads are + * performed for at least two bytes (required for the zip translate_eol + * option -- not supported here). + */ +static void fill_window( + deflate_state *s +) +{ + register unsigned n, m; + register Pos *p; + unsigned more; /* Amount of free space at the end of the window. */ + uInt wsize = s->w_size; + + do { + more = (unsigned)(s->window_size -(ulg)s->lookahead -(ulg)s->strstart); + + /* Deal with !@#$% 64K limit: */ + if (more == 0 && s->strstart == 0 && s->lookahead == 0) { + more = wsize; + + } else if (more == (unsigned)(-1)) { + /* Very unlikely, but possible on 16 bit machine if strstart == 0 + * and lookahead == 1 (input done one byte at time) + */ + more--; + + /* If the window is almost full and there is insufficient lookahead, + * move the upper half to the lower one to make room in the upper half. + */ + } else if (s->strstart >= wsize+MAX_DIST(s)) { + + memcpy((char *)s->window, (char *)s->window+wsize, + (unsigned)wsize); + s->match_start -= wsize; + s->strstart -= wsize; /* we now have strstart >= MAX_DIST */ + s->block_start -= (long) wsize; + + /* Slide the hash table (could be avoided with 32 bit values + at the expense of memory usage). We slide even when level == 0 + to keep the hash table consistent if we switch back to level > 0 + later. (Using level 0 permanently is not an optimal usage of + zlib, so we don't care about this pathological case.) + */ + n = s->hash_size; + p = &s->head[n]; + do { + m = *--p; + *p = (Pos)(m >= wsize ? m-wsize : NIL); + } while (--n); + + n = wsize; + p = &s->prev[n]; + do { + m = *--p; + *p = (Pos)(m >= wsize ? m-wsize : NIL); + /* If n is not on any hash chain, prev[n] is garbage but + * its value will never be used. + */ + } while (--n); + more += wsize; + } + if (s->strm->avail_in == 0) return; + + /* If there was no sliding: + * strstart <= WSIZE+MAX_DIST-1 && lookahead <= MIN_LOOKAHEAD - 1 && + * more == window_size - lookahead - strstart + * => more >= window_size - (MIN_LOOKAHEAD-1 + WSIZE + MAX_DIST-1) + * => more >= window_size - 2*WSIZE + 2 + * In the BIG_MEM or MMAP case (not yet supported), + * window_size == input_size + MIN_LOOKAHEAD && + * strstart + s->lookahead <= input_size => more >= MIN_LOOKAHEAD. + * Otherwise, window_size == 2*WSIZE so more >= 2. + * If there was sliding, more >= WSIZE. So in all cases, more >= 2. + */ + Assert(more >= 2, "more < 2"); + + n = read_buf(s->strm, s->window + s->strstart + s->lookahead, more); + s->lookahead += n; + + /* Initialize the hash value now that we have some input: */ + if (s->lookahead >= MIN_MATCH) { + s->ins_h = s->window[s->strstart]; + UPDATE_HASH(s, s->ins_h, s->window[s->strstart+1]); +#if MIN_MATCH != 3 + Call UPDATE_HASH() MIN_MATCH-3 more times +#endif + } + /* If the whole input has less than MIN_MATCH bytes, ins_h is garbage, + * but this is not important since only literal bytes will be emitted. + */ + + } while (s->lookahead < MIN_LOOKAHEAD && s->strm->avail_in != 0); +} + +/* =========================================================================== + * Flush the current block, with given end-of-file flag. + * IN assertion: strstart is set to the end of the current match. + */ +#define FLUSH_BLOCK_ONLY(s, eof) { \ + zlib_tr_flush_block(s, (s->block_start >= 0L ? \ + (char *)&s->window[(unsigned)s->block_start] : \ + NULL), \ + (ulg)((long)s->strstart - s->block_start), \ + (eof)); \ + s->block_start = s->strstart; \ + flush_pending(s->strm); \ + Tracev((stderr,"[FLUSH]")); \ +} + +/* Same but force premature exit if necessary. */ +#define FLUSH_BLOCK(s, eof) { \ + FLUSH_BLOCK_ONLY(s, eof); \ + if (s->strm->avail_out == 0) return (eof) ? finish_started : need_more; \ +} + +/* =========================================================================== + * Copy without compression as much as possible from the input stream, return + * the current block state. + * This function does not insert new strings in the dictionary since + * uncompressible data is probably not useful. This function is used + * only for the level=0 compression option. + * NOTE: this function should be optimized to avoid extra copying from + * window to pending_buf. + */ +static block_state deflate_stored( + deflate_state *s, + int flush +) +{ + /* Stored blocks are limited to 0xffff bytes, pending_buf is limited + * to pending_buf_size, and each stored block has a 5 byte header: + */ + ulg max_block_size = 0xffff; + ulg max_start; + + if (max_block_size > s->pending_buf_size - 5) { + max_block_size = s->pending_buf_size - 5; + } + + /* Copy as much as possible from input to output: */ + for (;;) { + /* Fill the window as much as possible: */ + if (s->lookahead <= 1) { + + Assert(s->strstart < s->w_size+MAX_DIST(s) || + s->block_start >= (long)s->w_size, "slide too late"); + + fill_window(s); + if (s->lookahead == 0 && flush == Z_NO_FLUSH) return need_more; + + if (s->lookahead == 0) break; /* flush the current block */ + } + Assert(s->block_start >= 0L, "block gone"); + + s->strstart += s->lookahead; + s->lookahead = 0; + + /* Emit a stored block if pending_buf will be full: */ + max_start = s->block_start + max_block_size; + if (s->strstart == 0 || (ulg)s->strstart >= max_start) { + /* strstart == 0 is possible when wraparound on 16-bit machine */ + s->lookahead = (uInt)(s->strstart - max_start); + s->strstart = (uInt)max_start; + FLUSH_BLOCK(s, 0); + } + /* Flush if we may have to slide, otherwise block_start may become + * negative and the data will be gone: + */ + if (s->strstart - (uInt)s->block_start >= MAX_DIST(s)) { + FLUSH_BLOCK(s, 0); + } + } + FLUSH_BLOCK(s, flush == Z_FINISH); + return flush == Z_FINISH ? finish_done : block_done; +} + +/* =========================================================================== + * Compress as much as possible from the input stream, return the current + * block state. + * This function does not perform lazy evaluation of matches and inserts + * new strings in the dictionary only for unmatched strings or for short + * matches. It is used only for the fast compression options. + */ +static block_state deflate_fast( + deflate_state *s, + int flush +) +{ + IPos hash_head = NIL; /* head of the hash chain */ + int bflush; /* set if current block must be flushed */ + + for (;;) { + /* Make sure that we always have enough lookahead, except + * at the end of the input file. We need MAX_MATCH bytes + * for the next match, plus MIN_MATCH bytes to insert the + * string following the next match. + */ + if (s->lookahead < MIN_LOOKAHEAD) { + fill_window(s); + if (s->lookahead < MIN_LOOKAHEAD && flush == Z_NO_FLUSH) { + return need_more; + } + if (s->lookahead == 0) break; /* flush the current block */ + } + + /* Insert the string window[strstart .. strstart+2] in the + * dictionary, and set hash_head to the head of the hash chain: + */ + if (s->lookahead >= MIN_MATCH) { + INSERT_STRING(s, s->strstart, hash_head); + } + + /* Find the longest match, discarding those <= prev_length. + * At this point we have always match_length < MIN_MATCH + */ + if (hash_head != NIL && s->strstart - hash_head <= MAX_DIST(s)) { + /* To simplify the code, we prevent matches with the string + * of window index 0 (in particular we have to avoid a match + * of the string with itself at the start of the input file). + */ + if (s->strategy != Z_HUFFMAN_ONLY) { + s->match_length = longest_match (s, hash_head); + } + /* longest_match() sets match_start */ + } + if (s->match_length >= MIN_MATCH) { + check_match(s, s->strstart, s->match_start, s->match_length); + + bflush = zlib_tr_tally(s, s->strstart - s->match_start, + s->match_length - MIN_MATCH); + + s->lookahead -= s->match_length; + + /* Insert new strings in the hash table only if the match length + * is not too large. This saves time but degrades compression. + */ + if (s->match_length <= s->max_insert_length && + s->lookahead >= MIN_MATCH) { + s->match_length--; /* string at strstart already in hash table */ + do { + s->strstart++; + INSERT_STRING(s, s->strstart, hash_head); + /* strstart never exceeds WSIZE-MAX_MATCH, so there are + * always MIN_MATCH bytes ahead. + */ + } while (--s->match_length != 0); + s->strstart++; + } else { + s->strstart += s->match_length; + s->match_length = 0; + s->ins_h = s->window[s->strstart]; + UPDATE_HASH(s, s->ins_h, s->window[s->strstart+1]); +#if MIN_MATCH != 3 + Call UPDATE_HASH() MIN_MATCH-3 more times +#endif + /* If lookahead < MIN_MATCH, ins_h is garbage, but it does not + * matter since it will be recomputed at next deflate call. + */ + } + } else { + /* No match, output a literal byte */ + Tracevv((stderr,"%c", s->window[s->strstart])); + bflush = zlib_tr_tally (s, 0, s->window[s->strstart]); + s->lookahead--; + s->strstart++; + } + if (bflush) FLUSH_BLOCK(s, 0); + } + FLUSH_BLOCK(s, flush == Z_FINISH); + return flush == Z_FINISH ? finish_done : block_done; +} + +/* =========================================================================== + * Same as above, but achieves better compression. We use a lazy + * evaluation for matches: a match is finally adopted only if there is + * no better match at the next window position. + */ +static block_state deflate_slow( + deflate_state *s, + int flush +) +{ + IPos hash_head = NIL; /* head of hash chain */ + int bflush; /* set if current block must be flushed */ + + /* Process the input block. */ + for (;;) { + /* Make sure that we always have enough lookahead, except + * at the end of the input file. We need MAX_MATCH bytes + * for the next match, plus MIN_MATCH bytes to insert the + * string following the next match. + */ + if (s->lookahead < MIN_LOOKAHEAD) { + fill_window(s); + if (s->lookahead < MIN_LOOKAHEAD && flush == Z_NO_FLUSH) { + return need_more; + } + if (s->lookahead == 0) break; /* flush the current block */ + } + + /* Insert the string window[strstart .. strstart+2] in the + * dictionary, and set hash_head to the head of the hash chain: + */ + if (s->lookahead >= MIN_MATCH) { + INSERT_STRING(s, s->strstart, hash_head); + } + + /* Find the longest match, discarding those <= prev_length. + */ + s->prev_length = s->match_length, s->prev_match = s->match_start; + s->match_length = MIN_MATCH-1; + + if (hash_head != NIL && s->prev_length < s->max_lazy_match && + s->strstart - hash_head <= MAX_DIST(s)) { + /* To simplify the code, we prevent matches with the string + * of window index 0 (in particular we have to avoid a match + * of the string with itself at the start of the input file). + */ + if (s->strategy != Z_HUFFMAN_ONLY) { + s->match_length = longest_match (s, hash_head); + } + /* longest_match() sets match_start */ + + if (s->match_length <= 5 && (s->strategy == Z_FILTERED || + (s->match_length == MIN_MATCH && + s->strstart - s->match_start > TOO_FAR))) { + + /* If prev_match is also MIN_MATCH, match_start is garbage + * but we will ignore the current match anyway. + */ + s->match_length = MIN_MATCH-1; + } + } + /* If there was a match at the previous step and the current + * match is not better, output the previous match: + */ + if (s->prev_length >= MIN_MATCH && s->match_length <= s->prev_length) { + uInt max_insert = s->strstart + s->lookahead - MIN_MATCH; + /* Do not insert strings in hash table beyond this. */ + + check_match(s, s->strstart-1, s->prev_match, s->prev_length); + + bflush = zlib_tr_tally(s, s->strstart -1 - s->prev_match, + s->prev_length - MIN_MATCH); + + /* Insert in hash table all strings up to the end of the match. + * strstart-1 and strstart are already inserted. If there is not + * enough lookahead, the last two strings are not inserted in + * the hash table. + */ + s->lookahead -= s->prev_length-1; + s->prev_length -= 2; + do { + if (++s->strstart <= max_insert) { + INSERT_STRING(s, s->strstart, hash_head); + } + } while (--s->prev_length != 0); + s->match_available = 0; + s->match_length = MIN_MATCH-1; + s->strstart++; + + if (bflush) FLUSH_BLOCK(s, 0); + + } else if (s->match_available) { + /* If there was no match at the previous position, output a + * single literal. If there was a match but the current match + * is longer, truncate the previous match to a single literal. + */ + Tracevv((stderr,"%c", s->window[s->strstart-1])); + if (zlib_tr_tally (s, 0, s->window[s->strstart-1])) { + FLUSH_BLOCK_ONLY(s, 0); + } + s->strstart++; + s->lookahead--; + if (s->strm->avail_out == 0) return need_more; + } else { + /* There is no previous match to compare with, wait for + * the next step to decide. + */ + s->match_available = 1; + s->strstart++; + s->lookahead--; + } + } + Assert (flush != Z_NO_FLUSH, "no flush?"); + if (s->match_available) { + Tracevv((stderr,"%c", s->window[s->strstart-1])); + zlib_tr_tally (s, 0, s->window[s->strstart-1]); + s->match_available = 0; + } + FLUSH_BLOCK(s, flush == Z_FINISH); + return flush == Z_FINISH ? finish_done : block_done; +} + +int zlib_deflate_workspacesize(void) +{ + return sizeof(deflate_workspace); +} diff --git a/lib/zlib_deflate/deflate_syms.c b/lib/zlib_deflate/deflate_syms.c new file mode 100644 index 00000000000..5985b28c8e3 --- /dev/null +++ b/lib/zlib_deflate/deflate_syms.c @@ -0,0 +1,21 @@ +/* + * linux/lib/zlib_deflate/deflate_syms.c + * + * Exported symbols for the deflate functionality. + * + */ + +#include <linux/module.h> +#include <linux/init.h> + +#include <linux/zlib.h> + +EXPORT_SYMBOL(zlib_deflate_workspacesize); +EXPORT_SYMBOL(zlib_deflate); +EXPORT_SYMBOL(zlib_deflateInit_); +EXPORT_SYMBOL(zlib_deflateInit2_); +EXPORT_SYMBOL(zlib_deflateEnd); +EXPORT_SYMBOL(zlib_deflateReset); +EXPORT_SYMBOL(zlib_deflateCopy); +EXPORT_SYMBOL(zlib_deflateParams); +MODULE_LICENSE("GPL"); diff --git a/lib/zlib_deflate/deftree.c b/lib/zlib_deflate/deftree.c new file mode 100644 index 00000000000..ddf348299f2 --- /dev/null +++ b/lib/zlib_deflate/deftree.c @@ -0,0 +1,1113 @@ +/* +++ trees.c */ +/* trees.c -- output deflated data using Huffman coding + * Copyright (C) 1995-1996 Jean-loup Gailly + * For conditions of distribution and use, see copyright notice in zlib.h + */ + +/* + * ALGORITHM + * + * The "deflation" process uses several Huffman trees. The more + * common source values are represented by shorter bit sequences. + * + * Each code tree is stored in a compressed form which is itself + * a Huffman encoding of the lengths of all the code strings (in + * ascending order by source values). The actual code strings are + * reconstructed from the lengths in the inflate process, as described + * in the deflate specification. + * + * REFERENCES + * + * Deutsch, L.P.,"'Deflate' Compressed Data Format Specification". + * Available in ftp.uu.net:/pub/archiving/zip/doc/deflate-1.1.doc + * + * Storer, James A. + * Data Compression: Methods and Theory, pp. 49-50. + * Computer Science Press, 1988. ISBN 0-7167-8156-5. + * + * Sedgewick, R. + * Algorithms, p290. + * Addison-Wesley, 1983. ISBN 0-201-06672-6. + */ + +/* From: trees.c,v 1.11 1996/07/24 13:41:06 me Exp $ */ + +/* #include "deflate.h" */ + +#include <linux/zutil.h> +#include "defutil.h" + +#ifdef DEBUG_ZLIB +# include <ctype.h> +#endif + +/* =========================================================================== + * Constants + */ + +#define MAX_BL_BITS 7 +/* Bit length codes must not exceed MAX_BL_BITS bits */ + +#define END_BLOCK 256 +/* end of block literal code */ + +#define REP_3_6 16 +/* repeat previous bit length 3-6 times (2 bits of repeat count) */ + +#define REPZ_3_10 17 +/* repeat a zero length 3-10 times (3 bits of repeat count) */ + +#define REPZ_11_138 18 +/* repeat a zero length 11-138 times (7 bits of repeat count) */ + +static const int extra_lbits[LENGTH_CODES] /* extra bits for each length code */ + = {0,0,0,0,0,0,0,0,1,1,1,1,2,2,2,2,3,3,3,3,4,4,4,4,5,5,5,5,0}; + +static const int extra_dbits[D_CODES] /* extra bits for each distance code */ + = {0,0,0,0,1,1,2,2,3,3,4,4,5,5,6,6,7,7,8,8,9,9,10,10,11,11,12,12,13,13}; + +static const int extra_blbits[BL_CODES]/* extra bits for each bit length code */ + = {0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,2,3,7}; + +static const uch bl_order[BL_CODES] + = {16,17,18,0,8,7,9,6,10,5,11,4,12,3,13,2,14,1,15}; +/* The lengths of the bit length codes are sent in order of decreasing + * probability, to avoid transmitting the lengths for unused bit length codes. + */ + +#define Buf_size (8 * 2*sizeof(char)) +/* Number of bits used within bi_buf. (bi_buf might be implemented on + * more than 16 bits on some systems.) + */ + +/* =========================================================================== + * Local data. These are initialized only once. + */ + +static ct_data static_ltree[L_CODES+2]; +/* The static literal tree. Since the bit lengths are imposed, there is no + * need for the L_CODES extra codes used during heap construction. However + * The codes 286 and 287 are needed to build a canonical tree (see zlib_tr_init + * below). + */ + +static ct_data static_dtree[D_CODES]; +/* The static distance tree. (Actually a trivial tree since all codes use + * 5 bits.) + */ + +static uch dist_code[512]; +/* distance codes. The first 256 values correspond to the distances + * 3 .. 258, the last 256 values correspond to the top 8 bits of + * the 15 bit distances. + */ + +static uch length_code[MAX_MATCH-MIN_MATCH+1]; +/* length code for each normalized match length (0 == MIN_MATCH) */ + +static int base_length[LENGTH_CODES]; +/* First normalized length for each code (0 = MIN_MATCH) */ + +static int base_dist[D_CODES]; +/* First normalized distance for each code (0 = distance of 1) */ + +struct static_tree_desc_s { + const ct_data *static_tree; /* static tree or NULL */ + const int *extra_bits; /* extra bits for each code or NULL */ + int extra_base; /* base index for extra_bits */ + int elems; /* max number of elements in the tree */ + int max_length; /* max bit length for the codes */ +}; + +static static_tree_desc static_l_desc = +{static_ltree, extra_lbits, LITERALS+1, L_CODES, MAX_BITS}; + +static static_tree_desc static_d_desc = +{static_dtree, extra_dbits, 0, D_CODES, MAX_BITS}; + +static static_tree_desc static_bl_desc = +{(const ct_data *)0, extra_blbits, 0, BL_CODES, MAX_BL_BITS}; + +/* =========================================================================== + * Local (static) routines in this file. + */ + +static void tr_static_init (void); +static void init_block (deflate_state *s); +static void pqdownheap (deflate_state *s, ct_data *tree, int k); +static void gen_bitlen (deflate_state *s, tree_desc *desc); +static void gen_codes (ct_data *tree, int max_code, ush *bl_count); +static void build_tree (deflate_state *s, tree_desc *desc); +static void scan_tree (deflate_state *s, ct_data *tree, int max_code); +static void send_tree (deflate_state *s, ct_data *tree, int max_code); +static int build_bl_tree (deflate_state *s); +static void send_all_trees (deflate_state *s, int lcodes, int dcodes, + int blcodes); +static void compress_block (deflate_state *s, ct_data *ltree, + ct_data *dtree); +static void set_data_type (deflate_state *s); +static unsigned bi_reverse (unsigned value, int length); +static void bi_windup (deflate_state *s); +static void bi_flush (deflate_state *s); +static void copy_block (deflate_state *s, char *buf, unsigned len, + int header); + +#ifndef DEBUG_ZLIB +# define send_code(s, c, tree) send_bits(s, tree[c].Code, tree[c].Len) + /* Send a code of the given tree. c and tree must not have side effects */ + +#else /* DEBUG_ZLIB */ +# define send_code(s, c, tree) \ + { if (z_verbose>2) fprintf(stderr,"\ncd %3d ",(c)); \ + send_bits(s, tree[c].Code, tree[c].Len); } +#endif + +#define d_code(dist) \ + ((dist) < 256 ? dist_code[dist] : dist_code[256+((dist)>>7)]) +/* Mapping from a distance to a distance code. dist is the distance - 1 and + * must not have side effects. dist_code[256] and dist_code[257] are never + * used. + */ + +/* =========================================================================== + * Send a value on a given number of bits. + * IN assertion: length <= 16 and value fits in length bits. + */ +#ifdef DEBUG_ZLIB +static void send_bits (deflate_state *s, int value, int length); + +static void send_bits( + deflate_state *s, + int value, /* value to send */ + int length /* number of bits */ +) +{ + Tracevv((stderr," l %2d v %4x ", length, value)); + Assert(length > 0 && length <= 15, "invalid length"); + s->bits_sent += (ulg)length; + + /* If not enough room in bi_buf, use (valid) bits from bi_buf and + * (16 - bi_valid) bits from value, leaving (width - (16-bi_valid)) + * unused bits in value. + */ + if (s->bi_valid > (int)Buf_size - length) { + s->bi_buf |= (value << s->bi_valid); + put_short(s, s->bi_buf); + s->bi_buf = (ush)value >> (Buf_size - s->bi_valid); + s->bi_valid += length - Buf_size; + } else { + s->bi_buf |= value << s->bi_valid; + s->bi_valid += length; + } +} +#else /* !DEBUG_ZLIB */ + +#define send_bits(s, value, length) \ +{ int len = length;\ + if (s->bi_valid > (int)Buf_size - len) {\ + int val = value;\ + s->bi_buf |= (val << s->bi_valid);\ + put_short(s, s->bi_buf);\ + s->bi_buf = (ush)val >> (Buf_size - s->bi_valid);\ + s->bi_valid += len - Buf_size;\ + } else {\ + s->bi_buf |= (value) << s->bi_valid;\ + s->bi_valid += len;\ + }\ +} +#endif /* DEBUG_ZLIB */ + +/* =========================================================================== + * Initialize the various 'constant' tables. In a multi-threaded environment, + * this function may be called by two threads concurrently, but this is + * harmless since both invocations do exactly the same thing. + */ +static void tr_static_init(void) +{ + static int static_init_done; + int n; /* iterates over tree elements */ + int bits; /* bit counter */ + int length; /* length value */ + int code; /* code value */ + int dist; /* distance index */ + ush bl_count[MAX_BITS+1]; + /* number of codes at each bit length for an optimal tree */ + + if (static_init_done) return; + + /* Initialize the mapping length (0..255) -> length code (0..28) */ + length = 0; + for (code = 0; code < LENGTH_CODES-1; code++) { + base_length[code] = length; + for (n = 0; n < (1<<extra_lbits[code]); n++) { + length_code[length++] = (uch)code; + } + } + Assert (length == 256, "tr_static_init: length != 256"); + /* Note that the length 255 (match length 258) can be represented + * in two different ways: code 284 + 5 bits or code 285, so we + * overwrite length_code[255] to use the best encoding: + */ + length_code[length-1] = (uch)code; + + /* Initialize the mapping dist (0..32K) -> dist code (0..29) */ + dist = 0; + for (code = 0 ; code < 16; code++) { + base_dist[code] = dist; + for (n = 0; n < (1<<extra_dbits[code]); n++) { + dist_code[dist++] = (uch)code; + } + } + Assert (dist == 256, "tr_static_init: dist != 256"); + dist >>= 7; /* from now on, all distances are divided by 128 */ + for ( ; code < D_CODES; code++) { + base_dist[code] = dist << 7; + for (n = 0; n < (1<<(extra_dbits[code]-7)); n++) { + dist_code[256 + dist++] = (uch)code; + } + } + Assert (dist == 256, "tr_static_init: 256+dist != 512"); + + /* Construct the codes of the static literal tree */ + for (bits = 0; bits <= MAX_BITS; bits++) bl_count[bits] = 0; + n = 0; + while (n <= 143) static_ltree[n++].Len = 8, bl_count[8]++; + while (n <= 255) static_ltree[n++].Len = 9, bl_count[9]++; + while (n <= 279) static_ltree[n++].Len = 7, bl_count[7]++; + while (n <= 287) static_ltree[n++].Len = 8, bl_count[8]++; + /* Codes 286 and 287 do not exist, but we must include them in the + * tree construction to get a canonical Huffman tree (longest code + * all ones) + */ + gen_codes((ct_data *)static_ltree, L_CODES+1, bl_count); + + /* The static distance tree is trivial: */ + for (n = 0; n < D_CODES; n++) { + static_dtree[n].Len = 5; + static_dtree[n].Code = bi_reverse((unsigned)n, 5); + } + static_init_done = 1; +} + +/* =========================================================================== + * Initialize the tree data structures for a new zlib stream. + */ +void zlib_tr_init( + deflate_state *s +) +{ + tr_static_init(); + + s->compressed_len = 0L; + + s->l_desc.dyn_tree = s->dyn_ltree; + s->l_desc.stat_desc = &static_l_desc; + + s->d_desc.dyn_tree = s->dyn_dtree; + s->d_desc.stat_desc = &static_d_desc; + + s->bl_desc.dyn_tree = s->bl_tree; + s->bl_desc.stat_desc = &static_bl_desc; + + s->bi_buf = 0; + s->bi_valid = 0; + s->last_eob_len = 8; /* enough lookahead for inflate */ +#ifdef DEBUG_ZLIB + s->bits_sent = 0L; +#endif + + /* Initialize the first block of the first file: */ + init_block(s); +} + +/* =========================================================================== + * Initialize a new block. + */ +static void init_block( + deflate_state *s +) +{ + int n; /* iterates over tree elements */ + + /* Initialize the trees. */ + for (n = 0; n < L_CODES; n++) s->dyn_ltree[n].Freq = 0; + for (n = 0; n < D_CODES; n++) s->dyn_dtree[n].Freq = 0; + for (n = 0; n < BL_CODES; n++) s->bl_tree[n].Freq = 0; + + s->dyn_ltree[END_BLOCK].Freq = 1; + s->opt_len = s->static_len = 0L; + s->last_lit = s->matches = 0; +} + +#define SMALLEST 1 +/* Index within the heap array of least frequent node in the Huffman tree */ + + +/* =========================================================================== + * Remove the smallest element from the heap and recreate the heap with + * one less element. Updates heap and heap_len. + */ +#define pqremove(s, tree, top) \ +{\ + top = s->heap[SMALLEST]; \ + s->heap[SMALLEST] = s->heap[s->heap_len--]; \ + pqdownheap(s, tree, SMALLEST); \ +} + +/* =========================================================================== + * Compares to subtrees, using the tree depth as tie breaker when + * the subtrees have equal frequency. This minimizes the worst case length. + */ +#define smaller(tree, n, m, depth) \ + (tree[n].Freq < tree[m].Freq || \ + (tree[n].Freq == tree[m].Freq && depth[n] <= depth[m])) + +/* =========================================================================== + * Restore the heap property by moving down the tree starting at node k, + * exchanging a node with the smallest of its two sons if necessary, stopping + * when the heap property is re-established (each father smaller than its + * two sons). + */ +static void pqdownheap( + deflate_state *s, + ct_data *tree, /* the tree to restore */ + int k /* node to move down */ +) +{ + int v = s->heap[k]; + int j = k << 1; /* left son of k */ + while (j <= s->heap_len) { + /* Set j to the smallest of the two sons: */ + if (j < s->heap_len && + smaller(tree, s->heap[j+1], s->heap[j], s->depth)) { + j++; + } + /* Exit if v is smaller than both sons */ + if (smaller(tree, v, s->heap[j], s->depth)) break; + + /* Exchange v with the smallest son */ + s->heap[k] = s->heap[j]; k = j; + + /* And continue down the tree, setting j to the left son of k */ + j <<= 1; + } + s->heap[k] = v; +} + +/* =========================================================================== + * Compute the optimal bit lengths for a tree and update the total bit length + * for the current block. + * IN assertion: the fields freq and dad are set, heap[heap_max] and + * above are the tree nodes sorted by increasing frequency. + * OUT assertions: the field len is set to the optimal bit length, the + * array bl_count contains the frequencies for each bit length. + * The length opt_len is updated; static_len is also updated if stree is + * not null. + */ +static void gen_bitlen( + deflate_state *s, + tree_desc *desc /* the tree descriptor */ +) +{ + ct_data *tree = desc->dyn_tree; + int max_code = desc->max_code; + const ct_data *stree = desc->stat_desc->static_tree; + const int *extra = desc->stat_desc->extra_bits; + int base = desc->stat_desc->extra_base; + int max_length = desc->stat_desc->max_length; + int h; /* heap index */ + int n, m; /* iterate over the tree elements */ + int bits; /* bit length */ + int xbits; /* extra bits */ + ush f; /* frequency */ + int overflow = 0; /* number of elements with bit length too large */ + + for (bits = 0; bits <= MAX_BITS; bits++) s->bl_count[bits] = 0; + + /* In a first pass, compute the optimal bit lengths (which may + * overflow in the case of the bit length tree). + */ + tree[s->heap[s->heap_max]].Len = 0; /* root of the heap */ + + for (h = s->heap_max+1; h < HEAP_SIZE; h++) { + n = s->heap[h]; + bits = tree[tree[n].Dad].Len + 1; + if (bits > max_length) bits = max_length, overflow++; + tree[n].Len = (ush)bits; + /* We overwrite tree[n].Dad which is no longer needed */ + + if (n > max_code) continue; /* not a leaf node */ + + s->bl_count[bits]++; + xbits = 0; + if (n >= base) xbits = extra[n-base]; + f = tree[n].Freq; + s->opt_len += (ulg)f * (bits + xbits); + if (stree) s->static_len += (ulg)f * (stree[n].Len + xbits); + } + if (overflow == 0) return; + + Trace((stderr,"\nbit length overflow\n")); + /* This happens for example on obj2 and pic of the Calgary corpus */ + + /* Find the first bit length which could increase: */ + do { + bits = max_length-1; + while (s->bl_count[bits] == 0) bits--; + s->bl_count[bits]--; /* move one leaf down the tree */ + s->bl_count[bits+1] += 2; /* move one overflow item as its brother */ + s->bl_count[max_length]--; + /* The brother of the overflow item also moves one step up, + * but this does not affect bl_count[max_length] + */ + overflow -= 2; + } while (overflow > 0); + + /* Now recompute all bit lengths, scanning in increasing frequency. + * h is still equal to HEAP_SIZE. (It is simpler to reconstruct all + * lengths instead of fixing only the wrong ones. This idea is taken + * from 'ar' written by Haruhiko Okumura.) + */ + for (bits = max_length; bits != 0; bits--) { + n = s->bl_count[bits]; + while (n != 0) { + m = s->heap[--h]; + if (m > max_code) continue; + if (tree[m].Len != (unsigned) bits) { + Trace((stderr,"code %d bits %d->%d\n", m, tree[m].Len, bits)); + s->opt_len += ((long)bits - (long)tree[m].Len) + *(long)tree[m].Freq; + tree[m].Len = (ush)bits; + } + n--; + } + } +} + +/* =========================================================================== + * Generate the codes for a given tree and bit counts (which need not be + * optimal). + * IN assertion: the array bl_count contains the bit length statistics for + * the given tree and the field len is set for all tree elements. + * OUT assertion: the field code is set for all tree elements of non + * zero code length. + */ +static void gen_codes( + ct_data *tree, /* the tree to decorate */ + int max_code, /* largest code with non zero frequency */ + ush *bl_count /* number of codes at each bit length */ +) +{ + ush next_code[MAX_BITS+1]; /* next code value for each bit length */ + ush code = 0; /* running code value */ + int bits; /* bit index */ + int n; /* code index */ + + /* The distribution counts are first used to generate the code values + * without bit reversal. + */ + for (bits = 1; bits <= MAX_BITS; bits++) { + next_code[bits] = code = (code + bl_count[bits-1]) << 1; + } + /* Check that the bit counts in bl_count are consistent. The last code + * must be all ones. + */ + Assert (code + bl_count[MAX_BITS]-1 == (1<<MAX_BITS)-1, + "inconsistent bit counts"); + Tracev((stderr,"\ngen_codes: max_code %d ", max_code)); + + for (n = 0; n <= max_code; n++) { + int len = tree[n].Len; + if (len == 0) continue; + /* Now reverse the bits */ + tree[n].Code = bi_reverse(next_code[len]++, len); + + Tracecv(tree != static_ltree, (stderr,"\nn %3d %c l %2d c %4x (%x) ", + n, (isgraph(n) ? n : ' '), len, tree[n].Code, next_code[len]-1)); + } +} + +/* =========================================================================== + * Construct one Huffman tree and assigns the code bit strings and lengths. + * Update the total bit length for the current block. + * IN assertion: the field freq is set for all tree elements. + * OUT assertions: the fields len and code are set to the optimal bit length + * and corresponding code. The length opt_len is updated; static_len is + * also updated if stree is not null. The field max_code is set. + */ +static void build_tree( + deflate_state *s, + tree_desc *desc /* the tree descriptor */ +) +{ + ct_data *tree = desc->dyn_tree; + const ct_data *stree = desc->stat_desc->static_tree; + int elems = desc->stat_desc->elems; + int n, m; /* iterate over heap elements */ + int max_code = -1; /* largest code with non zero frequency */ + int node; /* new node being created */ + + /* Construct the initial heap, with least frequent element in + * heap[SMALLEST]. The sons of heap[n] are heap[2*n] and heap[2*n+1]. + * heap[0] is not used. + */ + s->heap_len = 0, s->heap_max = HEAP_SIZE; + + for (n = 0; n < elems; n++) { + if (tree[n].Freq != 0) { + s->heap[++(s->heap_len)] = max_code = n; + s->depth[n] = 0; + } else { + tree[n].Len = 0; + } + } + + /* The pkzip format requires that at least one distance code exists, + * and that at least one bit should be sent even if there is only one + * possible code. So to avoid special checks later on we force at least + * two codes of non zero frequency. + */ + while (s->heap_len < 2) { + node = s->heap[++(s->heap_len)] = (max_code < 2 ? ++max_code : 0); + tree[node].Freq = 1; + s->depth[node] = 0; + s->opt_len--; if (stree) s->static_len -= stree[node].Len; + /* node is 0 or 1 so it does not have extra bits */ + } + desc->max_code = max_code; + + /* The elements heap[heap_len/2+1 .. heap_len] are leaves of the tree, + * establish sub-heaps of increasing lengths: + */ + for (n = s->heap_len/2; n >= 1; n--) pqdownheap(s, tree, n); + + /* Construct the Huffman tree by repeatedly combining the least two + * frequent nodes. + */ + node = elems; /* next internal node of the tree */ + do { + pqremove(s, tree, n); /* n = node of least frequency */ + m = s->heap[SMALLEST]; /* m = node of next least frequency */ + + s->heap[--(s->heap_max)] = n; /* keep the nodes sorted by frequency */ + s->heap[--(s->heap_max)] = m; + + /* Create a new node father of n and m */ + tree[node].Freq = tree[n].Freq + tree[m].Freq; + s->depth[node] = (uch) (max(s->depth[n], s->depth[m]) + 1); + tree[n].Dad = tree[m].Dad = (ush)node; +#ifdef DUMP_BL_TREE + if (tree == s->bl_tree) { + fprintf(stderr,"\nnode %d(%d), sons %d(%d) %d(%d)", + node, tree[node].Freq, n, tree[n].Freq, m, tree[m].Freq); + } +#endif + /* and insert the new node in the heap */ + s->heap[SMALLEST] = node++; + pqdownheap(s, tree, SMALLEST); + + } while (s->heap_len >= 2); + + s->heap[--(s->heap_max)] = s->heap[SMALLEST]; + + /* At this point, the fields freq and dad are set. We can now + * generate the bit lengths. + */ + gen_bitlen(s, (tree_desc *)desc); + + /* The field len is now set, we can generate the bit codes */ + gen_codes ((ct_data *)tree, max_code, s->bl_count); +} + +/* =========================================================================== + * Scan a literal or distance tree to determine the frequencies of the codes + * in the bit length tree. + */ +static void scan_tree( + deflate_state *s, + ct_data *tree, /* the tree to be scanned */ + int max_code /* and its largest code of non zero frequency */ +) +{ + int n; /* iterates over all tree elements */ + int prevlen = -1; /* last emitted length */ + int curlen; /* length of current code */ + int nextlen = tree[0].Len; /* length of next code */ + int count = 0; /* repeat count of the current code */ + int max_count = 7; /* max repeat count */ + int min_count = 4; /* min repeat count */ + + if (nextlen == 0) max_count = 138, min_count = 3; + tree[max_code+1].Len = (ush)0xffff; /* guard */ + + for (n = 0; n <= max_code; n++) { + curlen = nextlen; nextlen = tree[n+1].Len; + if (++count < max_count && curlen == nextlen) { + continue; + } else if (count < min_count) { + s->bl_tree[curlen].Freq += count; + } else if (curlen != 0) { + if (curlen != prevlen) s->bl_tree[curlen].Freq++; + s->bl_tree[REP_3_6].Freq++; + } else if (count <= 10) { + s->bl_tree[REPZ_3_10].Freq++; + } else { + s->bl_tree[REPZ_11_138].Freq++; + } + count = 0; prevlen = curlen; + if (nextlen == 0) { + max_count = 138, min_count = 3; + } else if (curlen == nextlen) { + max_count = 6, min_count = 3; + } else { + max_count = 7, min_count = 4; + } + } +} + +/* =========================================================================== + * Send a literal or distance tree in compressed form, using the codes in + * bl_tree. + */ +static void send_tree( + deflate_state *s, + ct_data *tree, /* the tree to be scanned */ + int max_code /* and its largest code of non zero frequency */ +) +{ + int n; /* iterates over all tree elements */ + int prevlen = -1; /* last emitted length */ + int curlen; /* length of current code */ + int nextlen = tree[0].Len; /* length of next code */ + int count = 0; /* repeat count of the current code */ + int max_count = 7; /* max repeat count */ + int min_count = 4; /* min repeat count */ + + /* tree[max_code+1].Len = -1; */ /* guard already set */ + if (nextlen == 0) max_count = 138, min_count = 3; + + for (n = 0; n <= max_code; n++) { + curlen = nextlen; nextlen = tree[n+1].Len; + if (++count < max_count && curlen == nextlen) { + continue; + } else if (count < min_count) { + do { send_code(s, curlen, s->bl_tree); } while (--count != 0); + + } else if (curlen != 0) { + if (curlen != prevlen) { + send_code(s, curlen, s->bl_tree); count--; + } + Assert(count >= 3 && count <= 6, " 3_6?"); + send_code(s, REP_3_6, s->bl_tree); send_bits(s, count-3, 2); + + } else if (count <= 10) { + send_code(s, REPZ_3_10, s->bl_tree); send_bits(s, count-3, 3); + + } else { + send_code(s, REPZ_11_138, s->bl_tree); send_bits(s, count-11, 7); + } + count = 0; prevlen = curlen; + if (nextlen == 0) { + max_count = 138, min_count = 3; + } else if (curlen == nextlen) { + max_count = 6, min_count = 3; + } else { + max_count = 7, min_count = 4; + } + } +} + +/* =========================================================================== + * Construct the Huffman tree for the bit lengths and return the index in + * bl_order of the last bit length code to send. + */ +static int build_bl_tree( + deflate_state *s +) +{ + int max_blindex; /* index of last bit length code of non zero freq */ + + /* Determine the bit length frequencies for literal and distance trees */ + scan_tree(s, (ct_data *)s->dyn_ltree, s->l_desc.max_code); + scan_tree(s, (ct_data *)s->dyn_dtree, s->d_desc.max_code); + + /* Build the bit length tree: */ + build_tree(s, (tree_desc *)(&(s->bl_desc))); + /* opt_len now includes the length of the tree representations, except + * the lengths of the bit lengths codes and the 5+5+4 bits for the counts. + */ + + /* Determine the number of bit length codes to send. The pkzip format + * requires that at least 4 bit length codes be sent. (appnote.txt says + * 3 but the actual value used is 4.) + */ + for (max_blindex = BL_CODES-1; max_blindex >= 3; max_blindex--) { + if (s->bl_tree[bl_order[max_blindex]].Len != 0) break; + } + /* Update opt_len to include the bit length tree and counts */ + s->opt_len += 3*(max_blindex+1) + 5+5+4; + Tracev((stderr, "\ndyn trees: dyn %ld, stat %ld", + s->opt_len, s->static_len)); + + return max_blindex; +} + +/* =========================================================================== + * Send the header for a block using dynamic Huffman trees: the counts, the + * lengths of the bit length codes, the literal tree and the distance tree. + * IN assertion: lcodes >= 257, dcodes >= 1, blcodes >= 4. + */ +static void send_all_trees( + deflate_state *s, + int lcodes, /* number of codes for each tree */ + int dcodes, /* number of codes for each tree */ + int blcodes /* number of codes for each tree */ +) +{ + int rank; /* index in bl_order */ + + Assert (lcodes >= 257 && dcodes >= 1 && blcodes >= 4, "not enough codes"); + Assert (lcodes <= L_CODES && dcodes <= D_CODES && blcodes <= BL_CODES, + "too many codes"); + Tracev((stderr, "\nbl counts: ")); + send_bits(s, lcodes-257, 5); /* not +255 as stated in appnote.txt */ + send_bits(s, dcodes-1, 5); + send_bits(s, blcodes-4, 4); /* not -3 as stated in appnote.txt */ + for (rank = 0; rank < blcodes; rank++) { + Tracev((stderr, "\nbl code %2d ", bl_order[rank])); + send_bits(s, s->bl_tree[bl_order[rank]].Len, 3); + } + Tracev((stderr, "\nbl tree: sent %ld", s->bits_sent)); + + send_tree(s, (ct_data *)s->dyn_ltree, lcodes-1); /* literal tree */ + Tracev((stderr, "\nlit tree: sent %ld", s->bits_sent)); + + send_tree(s, (ct_data *)s->dyn_dtree, dcodes-1); /* distance tree */ + Tracev((stderr, "\ndist tree: sent %ld", s->bits_sent)); +} + +/* =========================================================================== + * Send a stored block + */ +void zlib_tr_stored_block( + deflate_state *s, + char *buf, /* input block */ + ulg stored_len, /* length of input block */ + int eof /* true if this is the last block for a file */ +) +{ + send_bits(s, (STORED_BLOCK<<1)+eof, 3); /* send block type */ + s->compressed_len = (s->compressed_len + 3 + 7) & (ulg)~7L; + s->compressed_len += (stored_len + 4) << 3; + + copy_block(s, buf, (unsigned)stored_len, 1); /* with header */ +} + +/* Send just the `stored block' type code without any length bytes or data. + */ +void zlib_tr_stored_type_only( + deflate_state *s +) +{ + send_bits(s, (STORED_BLOCK << 1), 3); + bi_windup(s); + s->compressed_len = (s->compressed_len + 3) & ~7L; +} + + +/* =========================================================================== + * Send one empty static block to give enough lookahead for inflate. + * This takes 10 bits, of which 7 may remain in the bit buffer. + * The current inflate code requires 9 bits of lookahead. If the + * last two codes for the previous block (real code plus EOB) were coded + * on 5 bits or less, inflate may have only 5+3 bits of lookahead to decode + * the last real code. In this case we send two empty static blocks instead + * of one. (There are no problems if the previous block is stored or fixed.) + * To simplify the code, we assume the worst case of last real code encoded + * on one bit only. + */ +void zlib_tr_align( + deflate_state *s +) +{ + send_bits(s, STATIC_TREES<<1, 3); + send_code(s, END_BLOCK, static_ltree); + s->compressed_len += 10L; /* 3 for block type, 7 for EOB */ + bi_flush(s); + /* Of the 10 bits for the empty block, we have already sent + * (10 - bi_valid) bits. The lookahead for the last real code (before + * the EOB of the previous block) was thus at least one plus the length + * of the EOB plus what we have just sent of the empty static block. + */ + if (1 + s->last_eob_len + 10 - s->bi_valid < 9) { + send_bits(s, STATIC_TREES<<1, 3); + send_code(s, END_BLOCK, static_ltree); + s->compressed_len += 10L; + bi_flush(s); + } + s->last_eob_len = 7; +} + +/* =========================================================================== + * Determine the best encoding for the current block: dynamic trees, static + * trees or store, and output the encoded block to the zip file. This function + * returns the total compressed length for the file so far. + */ +ulg zlib_tr_flush_block( + deflate_state *s, + char *buf, /* input block, or NULL if too old */ + ulg stored_len, /* length of input block */ + int eof /* true if this is the last block for a file */ +) +{ + ulg opt_lenb, static_lenb; /* opt_len and static_len in bytes */ + int max_blindex = 0; /* index of last bit length code of non zero freq */ + + /* Build the Huffman trees unless a stored block is forced */ + if (s->level > 0) { + + /* Check if the file is ascii or binary */ + if (s->data_type == Z_UNKNOWN) set_data_type(s); + + /* Construct the literal and distance trees */ + build_tree(s, (tree_desc *)(&(s->l_desc))); + Tracev((stderr, "\nlit data: dyn %ld, stat %ld", s->opt_len, + s->static_len)); + + build_tree(s, (tree_desc *)(&(s->d_desc))); + Tracev((stderr, "\ndist data: dyn %ld, stat %ld", s->opt_len, + s->static_len)); + /* At this point, opt_len and static_len are the total bit lengths of + * the compressed block data, excluding the tree representations. + */ + + /* Build the bit length tree for the above two trees, and get the index + * in bl_order of the last bit length code to send. + */ + max_blindex = build_bl_tree(s); + + /* Determine the best encoding. Compute first the block length in bytes*/ + opt_lenb = (s->opt_len+3+7)>>3; + static_lenb = (s->static_len+3+7)>>3; + + Tracev((stderr, "\nopt %lu(%lu) stat %lu(%lu) stored %lu lit %u ", + opt_lenb, s->opt_len, static_lenb, s->static_len, stored_len, + s->last_lit)); + + if (static_lenb <= opt_lenb) opt_lenb = static_lenb; + + } else { + Assert(buf != (char*)0, "lost buf"); + opt_lenb = static_lenb = stored_len + 5; /* force a stored block */ + } + + /* If compression failed and this is the first and last block, + * and if the .zip file can be seeked (to rewrite the local header), + * the whole file is transformed into a stored file: + */ +#ifdef STORED_FILE_OK +# ifdef FORCE_STORED_FILE + if (eof && s->compressed_len == 0L) { /* force stored file */ +# else + if (stored_len <= opt_lenb && eof && s->compressed_len==0L && seekable()) { +# endif + /* Since LIT_BUFSIZE <= 2*WSIZE, the input data must be there: */ + if (buf == (char*)0) error ("block vanished"); + + copy_block(s, buf, (unsigned)stored_len, 0); /* without header */ + s->compressed_len = stored_len << 3; + s->method = STORED; + } else +#endif /* STORED_FILE_OK */ + +#ifdef FORCE_STORED + if (buf != (char*)0) { /* force stored block */ +#else + if (stored_len+4 <= opt_lenb && buf != (char*)0) { + /* 4: two words for the lengths */ +#endif + /* The test buf != NULL is only necessary if LIT_BUFSIZE > WSIZE. + * Otherwise we can't have processed more than WSIZE input bytes since + * the last block flush, because compression would have been + * successful. If LIT_BUFSIZE <= WSIZE, it is never too late to + * transform a block into a stored block. + */ + zlib_tr_stored_block(s, buf, stored_len, eof); + +#ifdef FORCE_STATIC + } else if (static_lenb >= 0) { /* force static trees */ +#else + } else if (static_lenb == opt_lenb) { +#endif + send_bits(s, (STATIC_TREES<<1)+eof, 3); + compress_block(s, (ct_data *)static_ltree, (ct_data *)static_dtree); + s->compressed_len += 3 + s->static_len; + } else { + send_bits(s, (DYN_TREES<<1)+eof, 3); + send_all_trees(s, s->l_desc.max_code+1, s->d_desc.max_code+1, + max_blindex+1); + compress_block(s, (ct_data *)s->dyn_ltree, (ct_data *)s->dyn_dtree); + s->compressed_len += 3 + s->opt_len; + } + Assert (s->compressed_len == s->bits_sent, "bad compressed size"); + init_block(s); + + if (eof) { + bi_windup(s); + s->compressed_len += 7; /* align on byte boundary */ + } + Tracev((stderr,"\ncomprlen %lu(%lu) ", s->compressed_len>>3, + s->compressed_len-7*eof)); + + return s->compressed_len >> 3; +} + +/* =========================================================================== + * Save the match info and tally the frequency counts. Return true if + * the current block must be flushed. + */ +int zlib_tr_tally( + deflate_state *s, + unsigned dist, /* distance of matched string */ + unsigned lc /* match length-MIN_MATCH or unmatched char (if dist==0) */ +) +{ + s->d_buf[s->last_lit] = (ush)dist; + s->l_buf[s->last_lit++] = (uch)lc; + if (dist == 0) { + /* lc is the unmatched char */ + s->dyn_ltree[lc].Freq++; + } else { + s->matches++; + /* Here, lc is the match length - MIN_MATCH */ + dist--; /* dist = match distance - 1 */ + Assert((ush)dist < (ush)MAX_DIST(s) && + (ush)lc <= (ush)(MAX_MATCH-MIN_MATCH) && + (ush)d_code(dist) < (ush)D_CODES, "zlib_tr_tally: bad match"); + + s->dyn_ltree[length_code[lc]+LITERALS+1].Freq++; + s->dyn_dtree[d_code(dist)].Freq++; + } + + /* Try to guess if it is profitable to stop the current block here */ + if ((s->last_lit & 0xfff) == 0 && s->level > 2) { + /* Compute an upper bound for the compressed length */ + ulg out_length = (ulg)s->last_lit*8L; + ulg in_length = (ulg)((long)s->strstart - s->block_start); + int dcode; + for (dcode = 0; dcode < D_CODES; dcode++) { + out_length += (ulg)s->dyn_dtree[dcode].Freq * + (5L+extra_dbits[dcode]); + } + out_length >>= 3; + Tracev((stderr,"\nlast_lit %u, in %ld, out ~%ld(%ld%%) ", + s->last_lit, in_length, out_length, + 100L - out_length*100L/in_length)); + if (s->matches < s->last_lit/2 && out_length < in_length/2) return 1; + } + return (s->last_lit == s->lit_bufsize-1); + /* We avoid equality with lit_bufsize because of wraparound at 64K + * on 16 bit machines and because stored blocks are restricted to + * 64K-1 bytes. + */ +} + +/* =========================================================================== + * Send the block data compressed using the given Huffman trees + */ +static void compress_block( + deflate_state *s, + ct_data *ltree, /* literal tree */ + ct_data *dtree /* distance tree */ +) +{ + unsigned dist; /* distance of matched string */ + int lc; /* match length or unmatched char (if dist == 0) */ + unsigned lx = 0; /* running index in l_buf */ + unsigned code; /* the code to send */ + int extra; /* number of extra bits to send */ + + if (s->last_lit != 0) do { + dist = s->d_buf[lx]; + lc = s->l_buf[lx++]; + if (dist == 0) { + send_code(s, lc, ltree); /* send a literal byte */ + Tracecv(isgraph(lc), (stderr," '%c' ", lc)); + } else { + /* Here, lc is the match length - MIN_MATCH */ + code = length_code[lc]; + send_code(s, code+LITERALS+1, ltree); /* send the length code */ + extra = extra_lbits[code]; + if (extra != 0) { + lc -= base_length[code]; + send_bits(s, lc, extra); /* send the extra length bits */ + } + dist--; /* dist is now the match distance - 1 */ + code = d_code(dist); + Assert (code < D_CODES, "bad d_code"); + + send_code(s, code, dtree); /* send the distance code */ + extra = extra_dbits[code]; + if (extra != 0) { + dist -= base_dist[code]; + send_bits(s, dist, extra); /* send the extra distance bits */ + } + } /* literal or match pair ? */ + + /* Check that the overlay between pending_buf and d_buf+l_buf is ok: */ + Assert(s->pending < s->lit_bufsize + 2*lx, "pendingBuf overflow"); + + } while (lx < s->last_lit); + + send_code(s, END_BLOCK, ltree); + s->last_eob_len = ltree[END_BLOCK].Len; +} + +/* =========================================================================== + * Set the data type to ASCII or BINARY, using a crude approximation: + * binary if more than 20% of the bytes are <= 6 or >= 128, ascii otherwise. + * IN assertion: the fields freq of dyn_ltree are set and the total of all + * frequencies does not exceed 64K (to fit in an int on 16 bit machines). + */ +static void set_data_type( + deflate_state *s +) +{ + int n = 0; + unsigned ascii_freq = 0; + unsigned bin_freq = 0; + while (n < 7) bin_freq += s->dyn_ltree[n++].Freq; + while (n < 128) ascii_freq += s->dyn_ltree[n++].Freq; + while (n < LITERALS) bin_freq += s->dyn_ltree[n++].Freq; + s->data_type = (Byte)(bin_freq > (ascii_freq >> 2) ? Z_BINARY : Z_ASCII); +} + +/* =========================================================================== + * Copy a stored block, storing first the length and its + * one's complement if requested. + */ +static void copy_block( + deflate_state *s, + char *buf, /* the input data */ + unsigned len, /* its length */ + int header /* true if block header must be written */ +) +{ + bi_windup(s); /* align on byte boundary */ + s->last_eob_len = 8; /* enough lookahead for inflate */ + + if (header) { + put_short(s, (ush)len); + put_short(s, (ush)~len); +#ifdef DEBUG_ZLIB + s->bits_sent += 2*16; +#endif + } +#ifdef DEBUG_ZLIB + s->bits_sent += (ulg)len<<3; +#endif + /* bundle up the put_byte(s, *buf++) calls */ + memcpy(&s->pending_buf[s->pending], buf, len); + s->pending += len; +} + diff --git a/lib/zlib_deflate/defutil.h b/lib/zlib_deflate/defutil.h new file mode 100644 index 00000000000..d9feaf63860 --- /dev/null +++ b/lib/zlib_deflate/defutil.h @@ -0,0 +1,334 @@ + + + +#define Assert(err, str) +#define Trace(dummy) +#define Tracev(dummy) +#define Tracecv(err, dummy) +#define Tracevv(dummy) + + + +#define LENGTH_CODES 29 +/* number of length codes, not counting the special END_BLOCK code */ + +#define LITERALS 256 +/* number of literal bytes 0..255 */ + +#define L_CODES (LITERALS+1+LENGTH_CODES) +/* number of Literal or Length codes, including the END_BLOCK code */ + +#define D_CODES 30 +/* number of distance codes */ + +#define BL_CODES 19 +/* number of codes used to transfer the bit lengths */ + +#define HEAP_SIZE (2*L_CODES+1) +/* maximum heap size */ + +#define MAX_BITS 15 +/* All codes must not exceed MAX_BITS bits */ + +#define INIT_STATE 42 +#define BUSY_STATE 113 +#define FINISH_STATE 666 +/* Stream status */ + + +/* Data structure describing a single value and its code string. */ +typedef struct ct_data_s { + union { + ush freq; /* frequency count */ + ush code; /* bit string */ + } fc; + union { + ush dad; /* father node in Huffman tree */ + ush len; /* length of bit string */ + } dl; +} ct_data; + +#define Freq fc.freq +#define Code fc.code +#define Dad dl.dad +#define Len dl.len + +typedef struct static_tree_desc_s static_tree_desc; + +typedef struct tree_desc_s { + ct_data *dyn_tree; /* the dynamic tree */ + int max_code; /* largest code with non zero frequency */ + static_tree_desc *stat_desc; /* the corresponding static tree */ +} tree_desc; + +typedef ush Pos; +typedef unsigned IPos; + +/* A Pos is an index in the character window. We use short instead of int to + * save space in the various tables. IPos is used only for parameter passing. + */ + +typedef struct deflate_state { + z_streamp strm; /* pointer back to this zlib stream */ + int status; /* as the name implies */ + Byte *pending_buf; /* output still pending */ + ulg pending_buf_size; /* size of pending_buf */ + Byte *pending_out; /* next pending byte to output to the stream */ + int pending; /* nb of bytes in the pending buffer */ + int noheader; /* suppress zlib header and adler32 */ + Byte data_type; /* UNKNOWN, BINARY or ASCII */ + Byte method; /* STORED (for zip only) or DEFLATED */ + int last_flush; /* value of flush param for previous deflate call */ + + /* used by deflate.c: */ + + uInt w_size; /* LZ77 window size (32K by default) */ + uInt w_bits; /* log2(w_size) (8..16) */ + uInt w_mask; /* w_size - 1 */ + + Byte *window; + /* Sliding window. Input bytes are read into the second half of the window, + * and move to the first half later to keep a dictionary of at least wSize + * bytes. With this organization, matches are limited to a distance of + * wSize-MAX_MATCH bytes, but this ensures that IO is always + * performed with a length multiple of the block size. Also, it limits + * the window size to 64K, which is quite useful on MSDOS. + * To do: use the user input buffer as sliding window. + */ + + ulg window_size; + /* Actual size of window: 2*wSize, except when the user input buffer + * is directly used as sliding window. + */ + + Pos *prev; + /* Link to older string with same hash index. To limit the size of this + * array to 64K, this link is maintained only for the last 32K strings. + * An index in this array is thus a window index modulo 32K. + */ + + Pos *head; /* Heads of the hash chains or NIL. */ + + uInt ins_h; /* hash index of string to be inserted */ + uInt hash_size; /* number of elements in hash table */ + uInt hash_bits; /* log2(hash_size) */ + uInt hash_mask; /* hash_size-1 */ + + uInt hash_shift; + /* Number of bits by which ins_h must be shifted at each input + * step. It must be such that after MIN_MATCH steps, the oldest + * byte no longer takes part in the hash key, that is: + * hash_shift * MIN_MATCH >= hash_bits + */ + + long block_start; + /* Window position at the beginning of the current output block. Gets + * negative when the window is moved backwards. + */ + + uInt match_length; /* length of best match */ + IPos prev_match; /* previous match */ + int match_available; /* set if previous match exists */ + uInt strstart; /* start of string to insert */ + uInt match_start; /* start of matching string */ + uInt lookahead; /* number of valid bytes ahead in window */ + + uInt prev_length; + /* Length of the best match at previous step. Matches not greater than this + * are discarded. This is used in the lazy match evaluation. + */ + + uInt max_chain_length; + /* To speed up deflation, hash chains are never searched beyond this + * length. A higher limit improves compression ratio but degrades the + * speed. + */ + + uInt max_lazy_match; + /* Attempt to find a better match only when the current match is strictly + * smaller than this value. This mechanism is used only for compression + * levels >= 4. + */ +# define max_insert_length max_lazy_match + /* Insert new strings in the hash table only if the match length is not + * greater than this length. This saves time but degrades compression. + * max_insert_length is used only for compression levels <= 3. + */ + + int level; /* compression level (1..9) */ + int strategy; /* favor or force Huffman coding*/ + + uInt good_match; + /* Use a faster search when the previous match is longer than this */ + + int nice_match; /* Stop searching when current match exceeds this */ + + /* used by trees.c: */ + /* Didn't use ct_data typedef below to supress compiler warning */ + struct ct_data_s dyn_ltree[HEAP_SIZE]; /* literal and length tree */ + struct ct_data_s dyn_dtree[2*D_CODES+1]; /* distance tree */ + struct ct_data_s bl_tree[2*BL_CODES+1]; /* Huffman tree for bit lengths */ + + struct tree_desc_s l_desc; /* desc. for literal tree */ + struct tree_desc_s d_desc; /* desc. for distance tree */ + struct tree_desc_s bl_desc; /* desc. for bit length tree */ + + ush bl_count[MAX_BITS+1]; + /* number of codes at each bit length for an optimal tree */ + + int heap[2*L_CODES+1]; /* heap used to build the Huffman trees */ + int heap_len; /* number of elements in the heap */ + int heap_max; /* element of largest frequency */ + /* The sons of heap[n] are heap[2*n] and heap[2*n+1]. heap[0] is not used. + * The same heap array is used to build all trees. + */ + + uch depth[2*L_CODES+1]; + /* Depth of each subtree used as tie breaker for trees of equal frequency + */ + + uch *l_buf; /* buffer for literals or lengths */ + + uInt lit_bufsize; + /* Size of match buffer for literals/lengths. There are 4 reasons for + * limiting lit_bufsize to 64K: + * - frequencies can be kept in 16 bit counters + * - if compression is not successful for the first block, all input + * data is still in the window so we can still emit a stored block even + * when input comes from standard input. (This can also be done for + * all blocks if lit_bufsize is not greater than 32K.) + * - if compression is not successful for a file smaller than 64K, we can + * even emit a stored file instead of a stored block (saving 5 bytes). + * This is applicable only for zip (not gzip or zlib). + * - creating new Huffman trees less frequently may not provide fast + * adaptation to changes in the input data statistics. (Take for + * example a binary file with poorly compressible code followed by + * a highly compressible string table.) Smaller buffer sizes give + * fast adaptation but have of course the overhead of transmitting + * trees more frequently. + * - I can't count above 4 + */ + + uInt last_lit; /* running index in l_buf */ + + ush *d_buf; + /* Buffer for distances. To simplify the code, d_buf and l_buf have + * the same number of elements. To use different lengths, an extra flag + * array would be necessary. + */ + + ulg opt_len; /* bit length of current block with optimal trees */ + ulg static_len; /* bit length of current block with static trees */ + ulg compressed_len; /* total bit length of compressed file */ + uInt matches; /* number of string matches in current block */ + int last_eob_len; /* bit length of EOB code for last block */ + +#ifdef DEBUG_ZLIB + ulg bits_sent; /* bit length of the compressed data */ +#endif + + ush bi_buf; + /* Output buffer. bits are inserted starting at the bottom (least + * significant bits). + */ + int bi_valid; + /* Number of valid bits in bi_buf. All bits above the last valid bit + * are always zero. + */ + +} deflate_state; + +typedef struct deflate_workspace { + /* State memory for the deflator */ + deflate_state deflate_memory; + Byte window_memory[2 * (1 << MAX_WBITS)]; + Pos prev_memory[1 << MAX_WBITS]; + Pos head_memory[1 << (MAX_MEM_LEVEL + 7)]; + char overlay_memory[(1 << (MAX_MEM_LEVEL + 6)) * (sizeof(ush)+2)]; +} deflate_workspace; + +/* Output a byte on the stream. + * IN assertion: there is enough room in pending_buf. + */ +#define put_byte(s, c) {s->pending_buf[s->pending++] = (c);} + + +#define MIN_LOOKAHEAD (MAX_MATCH+MIN_MATCH+1) +/* Minimum amount of lookahead, except at the end of the input file. + * See deflate.c for comments about the MIN_MATCH+1. + */ + +#define MAX_DIST(s) ((s)->w_size-MIN_LOOKAHEAD) +/* In order to simplify the code, particularly on 16 bit machines, match + * distances are limited to MAX_DIST instead of WSIZE. + */ + + /* in trees.c */ +void zlib_tr_init (deflate_state *s); +int zlib_tr_tally (deflate_state *s, unsigned dist, unsigned lc); +ulg zlib_tr_flush_block (deflate_state *s, char *buf, ulg stored_len, + int eof); +void zlib_tr_align (deflate_state *s); +void zlib_tr_stored_block (deflate_state *s, char *buf, ulg stored_len, + int eof); +void zlib_tr_stored_type_only (deflate_state *); + + +/* =========================================================================== + * Output a short LSB first on the stream. + * IN assertion: there is enough room in pendingBuf. + */ +#define put_short(s, w) { \ + put_byte(s, (uch)((w) & 0xff)); \ + put_byte(s, (uch)((ush)(w) >> 8)); \ +} + +/* =========================================================================== + * Reverse the first len bits of a code, using straightforward code (a faster + * method would use a table) + * IN assertion: 1 <= len <= 15 + */ +static inline unsigned bi_reverse(unsigned code, /* the value to invert */ + int len) /* its bit length */ +{ + register unsigned res = 0; + do { + res |= code & 1; + code >>= 1, res <<= 1; + } while (--len > 0); + return res >> 1; +} + +/* =========================================================================== + * Flush the bit buffer, keeping at most 7 bits in it. + */ +static inline void bi_flush(deflate_state *s) +{ + if (s->bi_valid == 16) { + put_short(s, s->bi_buf); + s->bi_buf = 0; + s->bi_valid = 0; + } else if (s->bi_valid >= 8) { + put_byte(s, (Byte)s->bi_buf); + s->bi_buf >>= 8; + s->bi_valid -= 8; + } +} + +/* =========================================================================== + * Flush the bit buffer and align the output on a byte boundary + */ +static inline void bi_windup(deflate_state *s) +{ + if (s->bi_valid > 8) { + put_short(s, s->bi_buf); + } else if (s->bi_valid > 0) { + put_byte(s, (Byte)s->bi_buf); + } + s->bi_buf = 0; + s->bi_valid = 0; +#ifdef DEBUG_ZLIB + s->bits_sent = (s->bits_sent+7) & ~7; +#endif +} + diff --git a/lib/zlib_inflate/Makefile b/lib/zlib_inflate/Makefile new file mode 100644 index 00000000000..221c139e0df --- /dev/null +++ b/lib/zlib_inflate/Makefile @@ -0,0 +1,19 @@ +# +# This is a modified version of zlib, which does all memory +# allocation ahead of time. +# +# This is only the decompression, see zlib_deflate for the +# the compression +# +# Decompression needs to be serialized for each memory +# allocation. +# +# (The upsides of the simplification is that you can't get in +# any nasty situations wrt memory management, and that the +# uncompression can be done without blocking on allocation). +# + +obj-$(CONFIG_ZLIB_INFLATE) += zlib_inflate.o + +zlib_inflate-objs := infblock.o infcodes.o inffast.o inflate.o \ + inflate_sync.o inftrees.o infutil.o inflate_syms.o diff --git a/lib/zlib_inflate/infblock.c b/lib/zlib_inflate/infblock.c new file mode 100644 index 00000000000..50f21ca4ef7 --- /dev/null +++ b/lib/zlib_inflate/infblock.c @@ -0,0 +1,361 @@ +/* infblock.c -- interpret and process block types to last block + * Copyright (C) 1995-1998 Mark Adler + * For conditions of distribution and use, see copyright notice in zlib.h + */ + +#include <linux/zutil.h> +#include "infblock.h" +#include "inftrees.h" +#include "infcodes.h" +#include "infutil.h" + +struct inflate_codes_state; + +/* simplify the use of the inflate_huft type with some defines */ +#define exop word.what.Exop +#define bits word.what.Bits + +/* Table for deflate from PKZIP's appnote.txt. */ +static const uInt border[] = { /* Order of the bit length code lengths */ + 16, 17, 18, 0, 8, 7, 9, 6, 10, 5, 11, 4, 12, 3, 13, 2, 14, 1, 15}; + +/* + Notes beyond the 1.93a appnote.txt: + + 1. Distance pointers never point before the beginning of the output + stream. + 2. Distance pointers can point back across blocks, up to 32k away. + 3. There is an implied maximum of 7 bits for the bit length table and + 15 bits for the actual data. + 4. If only one code exists, then it is encoded using one bit. (Zero + would be more efficient, but perhaps a little confusing.) If two + codes exist, they are coded using one bit each (0 and 1). + 5. There is no way of sending zero distance codes--a dummy must be + sent if there are none. (History: a pre 2.0 version of PKZIP would + store blocks with no distance codes, but this was discovered to be + too harsh a criterion.) Valid only for 1.93a. 2.04c does allow + zero distance codes, which is sent as one code of zero bits in + length. + 6. There are up to 286 literal/length codes. Code 256 represents the + end-of-block. Note however that the static length tree defines + 288 codes just to fill out the Huffman codes. Codes 286 and 287 + cannot be used though, since there is no length base or extra bits + defined for them. Similarily, there are up to 30 distance codes. + However, static trees define 32 codes (all 5 bits) to fill out the + Huffman codes, but the last two had better not show up in the data. + 7. Unzip can check dynamic Huffman blocks for complete code sets. + The exception is that a single code would not be complete (see #4). + 8. The five bits following the block type is really the number of + literal codes sent minus 257. + 9. Length codes 8,16,16 are interpreted as 13 length codes of 8 bits + (1+6+6). Therefore, to output three times the length, you output + three codes (1+1+1), whereas to output four times the same length, + you only need two codes (1+3). Hmm. + 10. In the tree reconstruction algorithm, Code = Code + Increment + only if BitLength(i) is not zero. (Pretty obvious.) + 11. Correction: 4 Bits: # of Bit Length codes - 4 (4 - 19) + 12. Note: length code 284 can represent 227-258, but length code 285 + really is 258. The last length deserves its own, short code + since it gets used a lot in very redundant files. The length + 258 is special since 258 - 3 (the min match length) is 255. + 13. The literal/length and distance code bit lengths are read as a + single stream of lengths. It is possible (and advantageous) for + a repeat code (16, 17, or 18) to go across the boundary between + the two sets of lengths. + */ + + +void zlib_inflate_blocks_reset( + inflate_blocks_statef *s, + z_streamp z, + uLong *c +) +{ + if (c != NULL) + *c = s->check; + if (s->mode == CODES) + zlib_inflate_codes_free(s->sub.decode.codes, z); + s->mode = TYPE; + s->bitk = 0; + s->bitb = 0; + s->read = s->write = s->window; + if (s->checkfn != NULL) + z->adler = s->check = (*s->checkfn)(0L, NULL, 0); +} + +inflate_blocks_statef *zlib_inflate_blocks_new( + z_streamp z, + check_func c, + uInt w +) +{ + inflate_blocks_statef *s; + + s = &WS(z)->working_blocks_state; + s->hufts = WS(z)->working_hufts; + s->window = WS(z)->working_window; + s->end = s->window + w; + s->checkfn = c; + s->mode = TYPE; + zlib_inflate_blocks_reset(s, z, NULL); + return s; +} + + +int zlib_inflate_blocks( + inflate_blocks_statef *s, + z_streamp z, + int r +) +{ + uInt t; /* temporary storage */ + uLong b; /* bit buffer */ + uInt k; /* bits in bit buffer */ + Byte *p; /* input data pointer */ + uInt n; /* bytes available there */ + Byte *q; /* output window write pointer */ + uInt m; /* bytes to end of window or read pointer */ + + /* copy input/output information to locals (UPDATE macro restores) */ + LOAD + + /* process input based on current state */ + while (1) switch (s->mode) + { + case TYPE: + NEEDBITS(3) + t = (uInt)b & 7; + s->last = t & 1; + switch (t >> 1) + { + case 0: /* stored */ + DUMPBITS(3) + t = k & 7; /* go to byte boundary */ + DUMPBITS(t) + s->mode = LENS; /* get length of stored block */ + break; + case 1: /* fixed */ + { + uInt bl, bd; + inflate_huft *tl, *td; + + zlib_inflate_trees_fixed(&bl, &bd, &tl, &td, s->hufts, z); + s->sub.decode.codes = zlib_inflate_codes_new(bl, bd, tl, td, z); + if (s->sub.decode.codes == NULL) + { + r = Z_MEM_ERROR; + LEAVE + } + } + DUMPBITS(3) + s->mode = CODES; + break; + case 2: /* dynamic */ + DUMPBITS(3) + s->mode = TABLE; + break; + case 3: /* illegal */ + DUMPBITS(3) + s->mode = B_BAD; + z->msg = (char*)"invalid block type"; + r = Z_DATA_ERROR; + LEAVE + } + break; + case LENS: + NEEDBITS(32) + if ((((~b) >> 16) & 0xffff) != (b & 0xffff)) + { + s->mode = B_BAD; + z->msg = (char*)"invalid stored block lengths"; + r = Z_DATA_ERROR; + LEAVE + } + s->sub.left = (uInt)b & 0xffff; + b = k = 0; /* dump bits */ + s->mode = s->sub.left ? STORED : (s->last ? DRY : TYPE); + break; + case STORED: + if (n == 0) + LEAVE + NEEDOUT + t = s->sub.left; + if (t > n) t = n; + if (t > m) t = m; + memcpy(q, p, t); + p += t; n -= t; + q += t; m -= t; + if ((s->sub.left -= t) != 0) + break; + s->mode = s->last ? DRY : TYPE; + break; + case TABLE: + NEEDBITS(14) + s->sub.trees.table = t = (uInt)b & 0x3fff; +#ifndef PKZIP_BUG_WORKAROUND + if ((t & 0x1f) > 29 || ((t >> 5) & 0x1f) > 29) + { + s->mode = B_BAD; + z->msg = (char*)"too many length or distance symbols"; + r = Z_DATA_ERROR; + LEAVE + } +#endif + { + s->sub.trees.blens = WS(z)->working_blens; + } + DUMPBITS(14) + s->sub.trees.index = 0; + s->mode = BTREE; + case BTREE: + while (s->sub.trees.index < 4 + (s->sub.trees.table >> 10)) + { + NEEDBITS(3) + s->sub.trees.blens[border[s->sub.trees.index++]] = (uInt)b & 7; + DUMPBITS(3) + } + while (s->sub.trees.index < 19) + s->sub.trees.blens[border[s->sub.trees.index++]] = 0; + s->sub.trees.bb = 7; + t = zlib_inflate_trees_bits(s->sub.trees.blens, &s->sub.trees.bb, + &s->sub.trees.tb, s->hufts, z); + if (t != Z_OK) + { + r = t; + if (r == Z_DATA_ERROR) + s->mode = B_BAD; + LEAVE + } + s->sub.trees.index = 0; + s->mode = DTREE; + case DTREE: + while (t = s->sub.trees.table, + s->sub.trees.index < 258 + (t & 0x1f) + ((t >> 5) & 0x1f)) + { + inflate_huft *h; + uInt i, j, c; + + t = s->sub.trees.bb; + NEEDBITS(t) + h = s->sub.trees.tb + ((uInt)b & zlib_inflate_mask[t]); + t = h->bits; + c = h->base; + if (c < 16) + { + DUMPBITS(t) + s->sub.trees.blens[s->sub.trees.index++] = c; + } + else /* c == 16..18 */ + { + i = c == 18 ? 7 : c - 14; + j = c == 18 ? 11 : 3; + NEEDBITS(t + i) + DUMPBITS(t) + j += (uInt)b & zlib_inflate_mask[i]; + DUMPBITS(i) + i = s->sub.trees.index; + t = s->sub.trees.table; + if (i + j > 258 + (t & 0x1f) + ((t >> 5) & 0x1f) || + (c == 16 && i < 1)) + { + s->mode = B_BAD; + z->msg = (char*)"invalid bit length repeat"; + r = Z_DATA_ERROR; + LEAVE + } + c = c == 16 ? s->sub.trees.blens[i - 1] : 0; + do { + s->sub.trees.blens[i++] = c; + } while (--j); + s->sub.trees.index = i; + } + } + s->sub.trees.tb = NULL; + { + uInt bl, bd; + inflate_huft *tl, *td; + inflate_codes_statef *c; + + bl = 9; /* must be <= 9 for lookahead assumptions */ + bd = 6; /* must be <= 9 for lookahead assumptions */ + t = s->sub.trees.table; + t = zlib_inflate_trees_dynamic(257 + (t & 0x1f), 1 + ((t >> 5) & 0x1f), + s->sub.trees.blens, &bl, &bd, &tl, &td, + s->hufts, z); + if (t != Z_OK) + { + if (t == (uInt)Z_DATA_ERROR) + s->mode = B_BAD; + r = t; + LEAVE + } + if ((c = zlib_inflate_codes_new(bl, bd, tl, td, z)) == NULL) + { + r = Z_MEM_ERROR; + LEAVE + } + s->sub.decode.codes = c; + } + s->mode = CODES; + case CODES: + UPDATE + if ((r = zlib_inflate_codes(s, z, r)) != Z_STREAM_END) + return zlib_inflate_flush(s, z, r); + r = Z_OK; + zlib_inflate_codes_free(s->sub.decode.codes, z); + LOAD + if (!s->last) + { + s->mode = TYPE; + break; + } + s->mode = DRY; + case DRY: + FLUSH + if (s->read != s->write) + LEAVE + s->mode = B_DONE; + case B_DONE: + r = Z_STREAM_END; + LEAVE + case B_BAD: + r = Z_DATA_ERROR; + LEAVE + default: + r = Z_STREAM_ERROR; + LEAVE + } +} + + +int zlib_inflate_blocks_free( + inflate_blocks_statef *s, + z_streamp z +) +{ + zlib_inflate_blocks_reset(s, z, NULL); + return Z_OK; +} + + +void zlib_inflate_set_dictionary( + inflate_blocks_statef *s, + const Byte *d, + uInt n +) +{ + memcpy(s->window, d, n); + s->read = s->write = s->window + n; +} + + +/* Returns true if inflate is currently at the end of a block generated + * by Z_SYNC_FLUSH or Z_FULL_FLUSH. + * IN assertion: s != NULL + */ +int zlib_inflate_blocks_sync_point( + inflate_blocks_statef *s +) +{ + return s->mode == LENS; +} diff --git a/lib/zlib_inflate/infblock.h b/lib/zlib_inflate/infblock.h new file mode 100644 index 00000000000..f5221ddf605 --- /dev/null +++ b/lib/zlib_inflate/infblock.h @@ -0,0 +1,44 @@ +/* infblock.h -- header to use infblock.c + * Copyright (C) 1995-1998 Mark Adler + * For conditions of distribution and use, see copyright notice in zlib.h + */ + +/* WARNING: this file should *not* be used by applications. It is + part of the implementation of the compression library and is + subject to change. Applications should only use zlib.h. + */ + +#ifndef _INFBLOCK_H +#define _INFBLOCK_H + +struct inflate_blocks_state; +typedef struct inflate_blocks_state inflate_blocks_statef; + +extern inflate_blocks_statef * zlib_inflate_blocks_new ( + z_streamp z, + check_func c, /* check function */ + uInt w); /* window size */ + +extern int zlib_inflate_blocks ( + inflate_blocks_statef *, + z_streamp , + int); /* initial return code */ + +extern void zlib_inflate_blocks_reset ( + inflate_blocks_statef *, + z_streamp , + uLong *); /* check value on output */ + +extern int zlib_inflate_blocks_free ( + inflate_blocks_statef *, + z_streamp); + +extern void zlib_inflate_set_dictionary ( + inflate_blocks_statef *s, + const Byte *d, /* dictionary */ + uInt n); /* dictionary length */ + +extern int zlib_inflate_blocks_sync_point ( + inflate_blocks_statef *s); + +#endif /* _INFBLOCK_H */ diff --git a/lib/zlib_inflate/infcodes.c b/lib/zlib_inflate/infcodes.c new file mode 100644 index 00000000000..07cd7591cbb --- /dev/null +++ b/lib/zlib_inflate/infcodes.c @@ -0,0 +1,202 @@ +/* infcodes.c -- process literals and length/distance pairs + * Copyright (C) 1995-1998 Mark Adler + * For conditions of distribution and use, see copyright notice in zlib.h + */ + +#include <linux/zutil.h> +#include "inftrees.h" +#include "infblock.h" +#include "infcodes.h" +#include "infutil.h" +#include "inffast.h" + +/* simplify the use of the inflate_huft type with some defines */ +#define exop word.what.Exop +#define bits word.what.Bits + +inflate_codes_statef *zlib_inflate_codes_new( + uInt bl, + uInt bd, + inflate_huft *tl, + inflate_huft *td, /* need separate declaration for Borland C++ */ + z_streamp z +) +{ + inflate_codes_statef *c; + + c = &WS(z)->working_state; + { + c->mode = START; + c->lbits = (Byte)bl; + c->dbits = (Byte)bd; + c->ltree = tl; + c->dtree = td; + } + return c; +} + + +int zlib_inflate_codes( + inflate_blocks_statef *s, + z_streamp z, + int r +) +{ + uInt j; /* temporary storage */ + inflate_huft *t; /* temporary pointer */ + uInt e; /* extra bits or operation */ + uLong b; /* bit buffer */ + uInt k; /* bits in bit buffer */ + Byte *p; /* input data pointer */ + uInt n; /* bytes available there */ + Byte *q; /* output window write pointer */ + uInt m; /* bytes to end of window or read pointer */ + Byte *f; /* pointer to copy strings from */ + inflate_codes_statef *c = s->sub.decode.codes; /* codes state */ + + /* copy input/output information to locals (UPDATE macro restores) */ + LOAD + + /* process input and output based on current state */ + while (1) switch (c->mode) + { /* waiting for "i:"=input, "o:"=output, "x:"=nothing */ + case START: /* x: set up for LEN */ +#ifndef SLOW + if (m >= 258 && n >= 10) + { + UPDATE + r = zlib_inflate_fast(c->lbits, c->dbits, c->ltree, c->dtree, s, z); + LOAD + if (r != Z_OK) + { + c->mode = r == Z_STREAM_END ? WASH : BADCODE; + break; + } + } +#endif /* !SLOW */ + c->sub.code.need = c->lbits; + c->sub.code.tree = c->ltree; + c->mode = LEN; + case LEN: /* i: get length/literal/eob next */ + j = c->sub.code.need; + NEEDBITS(j) + t = c->sub.code.tree + ((uInt)b & zlib_inflate_mask[j]); + DUMPBITS(t->bits) + e = (uInt)(t->exop); + if (e == 0) /* literal */ + { + c->sub.lit = t->base; + c->mode = LIT; + break; + } + if (e & 16) /* length */ + { + c->sub.copy.get = e & 15; + c->len = t->base; + c->mode = LENEXT; + break; + } + if ((e & 64) == 0) /* next table */ + { + c->sub.code.need = e; + c->sub.code.tree = t + t->base; + break; + } + if (e & 32) /* end of block */ + { + c->mode = WASH; + break; + } + c->mode = BADCODE; /* invalid code */ + z->msg = (char*)"invalid literal/length code"; + r = Z_DATA_ERROR; + LEAVE + case LENEXT: /* i: getting length extra (have base) */ + j = c->sub.copy.get; + NEEDBITS(j) + c->len += (uInt)b & zlib_inflate_mask[j]; + DUMPBITS(j) + c->sub.code.need = c->dbits; + c->sub.code.tree = c->dtree; + c->mode = DIST; + case DIST: /* i: get distance next */ + j = c->sub.code.need; + NEEDBITS(j) + t = c->sub.code.tree + ((uInt)b & zlib_inflate_mask[j]); + DUMPBITS(t->bits) + e = (uInt)(t->exop); + if (e & 16) /* distance */ + { + c->sub.copy.get = e & 15; + c->sub.copy.dist = t->base; + c->mode = DISTEXT; + break; + } + if ((e & 64) == 0) /* next table */ + { + c->sub.code.need = e; + c->sub.code.tree = t + t->base; + break; + } + c->mode = BADCODE; /* invalid code */ + z->msg = (char*)"invalid distance code"; + r = Z_DATA_ERROR; + LEAVE + case DISTEXT: /* i: getting distance extra */ + j = c->sub.copy.get; + NEEDBITS(j) + c->sub.copy.dist += (uInt)b & zlib_inflate_mask[j]; + DUMPBITS(j) + c->mode = COPY; + case COPY: /* o: copying bytes in window, waiting for space */ + f = q - c->sub.copy.dist; + while (f < s->window) /* modulo window size-"while" instead */ + f += s->end - s->window; /* of "if" handles invalid distances */ + while (c->len) + { + NEEDOUT + OUTBYTE(*f++) + if (f == s->end) + f = s->window; + c->len--; + } + c->mode = START; + break; + case LIT: /* o: got literal, waiting for output space */ + NEEDOUT + OUTBYTE(c->sub.lit) + c->mode = START; + break; + case WASH: /* o: got eob, possibly more output */ + if (k > 7) /* return unused byte, if any */ + { + k -= 8; + n++; + p--; /* can always return one */ + } + FLUSH + if (s->read != s->write) + LEAVE + c->mode = END; + case END: + r = Z_STREAM_END; + LEAVE + case BADCODE: /* x: got error */ + r = Z_DATA_ERROR; + LEAVE + default: + r = Z_STREAM_ERROR; + LEAVE + } +#ifdef NEED_DUMMY_RETURN + return Z_STREAM_ERROR; /* Some dumb compilers complain without this */ +#endif +} + + +void zlib_inflate_codes_free( + inflate_codes_statef *c, + z_streamp z +) +{ +} diff --git a/lib/zlib_inflate/infcodes.h b/lib/zlib_inflate/infcodes.h new file mode 100644 index 00000000000..5cff417523b --- /dev/null +++ b/lib/zlib_inflate/infcodes.h @@ -0,0 +1,33 @@ +/* infcodes.h -- header to use infcodes.c + * Copyright (C) 1995-1998 Mark Adler + * For conditions of distribution and use, see copyright notice in zlib.h + */ + +/* WARNING: this file should *not* be used by applications. It is + part of the implementation of the compression library and is + subject to change. Applications should only use zlib.h. + */ + +#ifndef _INFCODES_H +#define _INFCODES_H + +#include "infblock.h" + +struct inflate_codes_state; +typedef struct inflate_codes_state inflate_codes_statef; + +extern inflate_codes_statef *zlib_inflate_codes_new ( + uInt, uInt, + inflate_huft *, inflate_huft *, + z_streamp ); + +extern int zlib_inflate_codes ( + inflate_blocks_statef *, + z_streamp , + int); + +extern void zlib_inflate_codes_free ( + inflate_codes_statef *, + z_streamp ); + +#endif /* _INFCODES_H */ diff --git a/lib/zlib_inflate/inffast.c b/lib/zlib_inflate/inffast.c new file mode 100644 index 00000000000..0bd7623fc85 --- /dev/null +++ b/lib/zlib_inflate/inffast.c @@ -0,0 +1,176 @@ +/* inffast.c -- process literals and length/distance pairs fast + * Copyright (C) 1995-1998 Mark Adler + * For conditions of distribution and use, see copyright notice in zlib.h + */ + +#include <linux/zutil.h> +#include "inftrees.h" +#include "infblock.h" +#include "infcodes.h" +#include "infutil.h" +#include "inffast.h" + +struct inflate_codes_state; + +/* simplify the use of the inflate_huft type with some defines */ +#define exop word.what.Exop +#define bits word.what.Bits + +/* macros for bit input with no checking and for returning unused bytes */ +#define GRABBITS(j) {while(k<(j)){b|=((uLong)NEXTBYTE)<<k;k+=8;}} +#define UNGRAB {c=z->avail_in-n;c=(k>>3)<c?k>>3:c;n+=c;p-=c;k-=c<<3;} + +/* Called with number of bytes left to write in window at least 258 + (the maximum string length) and number of input bytes available + at least ten. The ten bytes are six bytes for the longest length/ + distance pair plus four bytes for overloading the bit buffer. */ + +int zlib_inflate_fast( + uInt bl, + uInt bd, + inflate_huft *tl, + inflate_huft *td, /* need separate declaration for Borland C++ */ + inflate_blocks_statef *s, + z_streamp z +) +{ + inflate_huft *t; /* temporary pointer */ + uInt e; /* extra bits or operation */ + uLong b; /* bit buffer */ + uInt k; /* bits in bit buffer */ + Byte *p; /* input data pointer */ + uInt n; /* bytes available there */ + Byte *q; /* output window write pointer */ + uInt m; /* bytes to end of window or read pointer */ + uInt ml; /* mask for literal/length tree */ + uInt md; /* mask for distance tree */ + uInt c; /* bytes to copy */ + uInt d; /* distance back to copy from */ + Byte *r; /* copy source pointer */ + + /* load input, output, bit values */ + LOAD + + /* initialize masks */ + ml = zlib_inflate_mask[bl]; + md = zlib_inflate_mask[bd]; + + /* do until not enough input or output space for fast loop */ + do { /* assume called with m >= 258 && n >= 10 */ + /* get literal/length code */ + GRABBITS(20) /* max bits for literal/length code */ + if ((e = (t = tl + ((uInt)b & ml))->exop) == 0) + { + DUMPBITS(t->bits) + *q++ = (Byte)t->base; + m--; + continue; + } + do { + DUMPBITS(t->bits) + if (e & 16) + { + /* get extra bits for length */ + e &= 15; + c = t->base + ((uInt)b & zlib_inflate_mask[e]); + DUMPBITS(e) + + /* decode distance base of block to copy */ + GRABBITS(15); /* max bits for distance code */ + e = (t = td + ((uInt)b & md))->exop; + do { + DUMPBITS(t->bits) + if (e & 16) + { + /* get extra bits to add to distance base */ + e &= 15; + GRABBITS(e) /* get extra bits (up to 13) */ + d = t->base + ((uInt)b & zlib_inflate_mask[e]); + DUMPBITS(e) + + /* do the copy */ + m -= c; + r = q - d; + if (r < s->window) /* wrap if needed */ + { + do { + r += s->end - s->window; /* force pointer in window */ + } while (r < s->window); /* covers invalid distances */ + e = s->end - r; + if (c > e) + { + c -= e; /* wrapped copy */ + do { + *q++ = *r++; + } while (--e); + r = s->window; + do { + *q++ = *r++; + } while (--c); + } + else /* normal copy */ + { + *q++ = *r++; c--; + *q++ = *r++; c--; + do { + *q++ = *r++; + } while (--c); + } + } + else /* normal copy */ + { + *q++ = *r++; c--; + *q++ = *r++; c--; + do { + *q++ = *r++; + } while (--c); + } + break; + } + else if ((e & 64) == 0) + { + t += t->base; + e = (t += ((uInt)b & zlib_inflate_mask[e]))->exop; + } + else + { + z->msg = (char*)"invalid distance code"; + UNGRAB + UPDATE + return Z_DATA_ERROR; + } + } while (1); + break; + } + if ((e & 64) == 0) + { + t += t->base; + if ((e = (t += ((uInt)b & zlib_inflate_mask[e]))->exop) == 0) + { + DUMPBITS(t->bits) + *q++ = (Byte)t->base; + m--; + break; + } + } + else if (e & 32) + { + UNGRAB + UPDATE + return Z_STREAM_END; + } + else + { + z->msg = (char*)"invalid literal/length code"; + UNGRAB + UPDATE + return Z_DATA_ERROR; + } + } while (1); + } while (m >= 258 && n >= 10); + + /* not enough input or output--restore pointers and return */ + UNGRAB + UPDATE + return Z_OK; +} diff --git a/lib/zlib_inflate/inffast.h b/lib/zlib_inflate/inffast.h new file mode 100644 index 00000000000..fc720f0fa7f --- /dev/null +++ b/lib/zlib_inflate/inffast.h @@ -0,0 +1,17 @@ +/* inffast.h -- header to use inffast.c + * Copyright (C) 1995-1998 Mark Adler + * For conditions of distribution and use, see copyright notice in zlib.h + */ + +/* WARNING: this file should *not* be used by applications. It is + part of the implementation of the compression library and is + subject to change. Applications should only use zlib.h. + */ + +extern int zlib_inflate_fast ( + uInt, + uInt, + inflate_huft *, + inflate_huft *, + inflate_blocks_statef *, + z_streamp ); diff --git a/lib/zlib_inflate/inflate.c b/lib/zlib_inflate/inflate.c new file mode 100644 index 00000000000..3d94cb90c1d --- /dev/null +++ b/lib/zlib_inflate/inflate.c @@ -0,0 +1,248 @@ +/* inflate.c -- zlib interface to inflate modules + * Copyright (C) 1995-1998 Mark Adler + * For conditions of distribution and use, see copyright notice in zlib.h + */ + +#include <linux/module.h> +#include <linux/zutil.h> +#include "infblock.h" +#include "infutil.h" + +int zlib_inflate_workspacesize(void) +{ + return sizeof(struct inflate_workspace); +} + + +int zlib_inflateReset( + z_streamp z +) +{ + if (z == NULL || z->state == NULL || z->workspace == NULL) + return Z_STREAM_ERROR; + z->total_in = z->total_out = 0; + z->msg = NULL; + z->state->mode = z->state->nowrap ? BLOCKS : METHOD; + zlib_inflate_blocks_reset(z->state->blocks, z, NULL); + return Z_OK; +} + + +int zlib_inflateEnd( + z_streamp z +) +{ + if (z == NULL || z->state == NULL || z->workspace == NULL) + return Z_STREAM_ERROR; + if (z->state->blocks != NULL) + zlib_inflate_blocks_free(z->state->blocks, z); + z->state = NULL; + return Z_OK; +} + + +int zlib_inflateInit2_( + z_streamp z, + int w, + const char *version, + int stream_size +) +{ + if (version == NULL || version[0] != ZLIB_VERSION[0] || + stream_size != sizeof(z_stream) || z->workspace == NULL) + return Z_VERSION_ERROR; + + /* initialize state */ + z->msg = NULL; + z->state = &WS(z)->internal_state; + z->state->blocks = NULL; + + /* handle undocumented nowrap option (no zlib header or check) */ + z->state->nowrap = 0; + if (w < 0) + { + w = - w; + z->state->nowrap = 1; + } + + /* set window size */ + if (w < 8 || w > 15) + { + zlib_inflateEnd(z); + return Z_STREAM_ERROR; + } + z->state->wbits = (uInt)w; + + /* create inflate_blocks state */ + if ((z->state->blocks = + zlib_inflate_blocks_new(z, z->state->nowrap ? NULL : zlib_adler32, (uInt)1 << w)) + == NULL) + { + zlib_inflateEnd(z); + return Z_MEM_ERROR; + } + + /* reset state */ + zlib_inflateReset(z); + return Z_OK; +} + + +/* + * At the end of a Deflate-compressed PPP packet, we expect to have seen + * a `stored' block type value but not the (zero) length bytes. + */ +static int zlib_inflate_packet_flush(inflate_blocks_statef *s) +{ + if (s->mode != LENS) + return Z_DATA_ERROR; + s->mode = TYPE; + return Z_OK; +} + + +int zlib_inflateInit_( + z_streamp z, + const char *version, + int stream_size +) +{ + return zlib_inflateInit2_(z, DEF_WBITS, version, stream_size); +} + +#undef NEEDBYTE +#undef NEXTBYTE +#define NEEDBYTE {if(z->avail_in==0)goto empty;r=trv;} +#define NEXTBYTE (z->avail_in--,z->total_in++,*z->next_in++) + +int zlib_inflate( + z_streamp z, + int f +) +{ + int r, trv; + uInt b; + + if (z == NULL || z->state == NULL || z->next_in == NULL) + return Z_STREAM_ERROR; + trv = f == Z_FINISH ? Z_BUF_ERROR : Z_OK; + r = Z_BUF_ERROR; + while (1) switch (z->state->mode) + { + case METHOD: + NEEDBYTE + if (((z->state->sub.method = NEXTBYTE) & 0xf) != Z_DEFLATED) + { + z->state->mode = I_BAD; + z->msg = (char*)"unknown compression method"; + z->state->sub.marker = 5; /* can't try inflateSync */ + break; + } + if ((z->state->sub.method >> 4) + 8 > z->state->wbits) + { + z->state->mode = I_BAD; + z->msg = (char*)"invalid window size"; + z->state->sub.marker = 5; /* can't try inflateSync */ + break; + } + z->state->mode = FLAG; + case FLAG: + NEEDBYTE + b = NEXTBYTE; + if (((z->state->sub.method << 8) + b) % 31) + { + z->state->mode = I_BAD; + z->msg = (char*)"incorrect header check"; + z->state->sub.marker = 5; /* can't try inflateSync */ + break; + } + if (!(b & PRESET_DICT)) + { + z->state->mode = BLOCKS; + break; + } + z->state->mode = DICT4; + case DICT4: + NEEDBYTE + z->state->sub.check.need = (uLong)NEXTBYTE << 24; + z->state->mode = DICT3; + case DICT3: + NEEDBYTE + z->state->sub.check.need += (uLong)NEXTBYTE << 16; + z->state->mode = DICT2; + case DICT2: + NEEDBYTE + z->state->sub.check.need += (uLong)NEXTBYTE << 8; + z->state->mode = DICT1; + case DICT1: + NEEDBYTE + z->state->sub.check.need += (uLong)NEXTBYTE; + z->adler = z->state->sub.check.need; + z->state->mode = DICT0; + return Z_NEED_DICT; + case DICT0: + z->state->mode = I_BAD; + z->msg = (char*)"need dictionary"; + z->state->sub.marker = 0; /* can try inflateSync */ + return Z_STREAM_ERROR; + case BLOCKS: + r = zlib_inflate_blocks(z->state->blocks, z, r); + if (f == Z_PACKET_FLUSH && z->avail_in == 0 && z->avail_out != 0) + r = zlib_inflate_packet_flush(z->state->blocks); + if (r == Z_DATA_ERROR) + { + z->state->mode = I_BAD; + z->state->sub.marker = 0; /* can try inflateSync */ + break; + } + if (r == Z_OK) + r = trv; + if (r != Z_STREAM_END) + return r; + r = trv; + zlib_inflate_blocks_reset(z->state->blocks, z, &z->state->sub.check.was); + if (z->state->nowrap) + { + z->state->mode = I_DONE; + break; + } + z->state->mode = CHECK4; + case CHECK4: + NEEDBYTE + z->state->sub.check.need = (uLong)NEXTBYTE << 24; + z->state->mode = CHECK3; + case CHECK3: + NEEDBYTE + z->state->sub.check.need += (uLong)NEXTBYTE << 16; + z->state->mode = CHECK2; + case CHECK2: + NEEDBYTE + z->state->sub.check.need += (uLong)NEXTBYTE << 8; + z->state->mode = CHECK1; + case CHECK1: + NEEDBYTE + z->state->sub.check.need += (uLong)NEXTBYTE; + + if (z->state->sub.check.was != z->state->sub.check.need) + { + z->state->mode = I_BAD; + z->msg = (char*)"incorrect data check"; + z->state->sub.marker = 5; /* can't try inflateSync */ + break; + } + z->state->mode = I_DONE; + case I_DONE: + return Z_STREAM_END; + case I_BAD: + return Z_DATA_ERROR; + default: + return Z_STREAM_ERROR; + } + empty: + if (f != Z_PACKET_FLUSH) + return r; + z->state->mode = I_BAD; + z->msg = (char *)"need more for packet flush"; + z->state->sub.marker = 0; /* can try inflateSync */ + return Z_DATA_ERROR; +} diff --git a/lib/zlib_inflate/inflate_syms.c b/lib/zlib_inflate/inflate_syms.c new file mode 100644 index 00000000000..aa1b0818912 --- /dev/null +++ b/lib/zlib_inflate/inflate_syms.c @@ -0,0 +1,22 @@ +/* + * linux/lib/zlib_inflate/inflate_syms.c + * + * Exported symbols for the inflate functionality. + * + */ + +#include <linux/module.h> +#include <linux/init.h> + +#include <linux/zlib.h> + +EXPORT_SYMBOL(zlib_inflate_workspacesize); +EXPORT_SYMBOL(zlib_inflate); +EXPORT_SYMBOL(zlib_inflateInit_); +EXPORT_SYMBOL(zlib_inflateInit2_); +EXPORT_SYMBOL(zlib_inflateEnd); +EXPORT_SYMBOL(zlib_inflateSync); +EXPORT_SYMBOL(zlib_inflateReset); +EXPORT_SYMBOL(zlib_inflateSyncPoint); +EXPORT_SYMBOL(zlib_inflateIncomp); +MODULE_LICENSE("GPL"); diff --git a/lib/zlib_inflate/inflate_sync.c b/lib/zlib_inflate/inflate_sync.c new file mode 100644 index 00000000000..e07bdb21f55 --- /dev/null +++ b/lib/zlib_inflate/inflate_sync.c @@ -0,0 +1,148 @@ +/* inflate.c -- zlib interface to inflate modules + * Copyright (C) 1995-1998 Mark Adler + * For conditions of distribution and use, see copyright notice in zlib.h + */ + +#include <linux/zutil.h> +#include "infblock.h" +#include "infutil.h" + +int zlib_inflateSync( + z_streamp z +) +{ + uInt n; /* number of bytes to look at */ + Byte *p; /* pointer to bytes */ + uInt m; /* number of marker bytes found in a row */ + uLong r, w; /* temporaries to save total_in and total_out */ + + /* set up */ + if (z == NULL || z->state == NULL) + return Z_STREAM_ERROR; + if (z->state->mode != I_BAD) + { + z->state->mode = I_BAD; + z->state->sub.marker = 0; + } + if ((n = z->avail_in) == 0) + return Z_BUF_ERROR; + p = z->next_in; + m = z->state->sub.marker; + + /* search */ + while (n && m < 4) + { + static const Byte mark[4] = {0, 0, 0xff, 0xff}; + if (*p == mark[m]) + m++; + else if (*p) + m = 0; + else + m = 4 - m; + p++, n--; + } + + /* restore */ + z->total_in += p - z->next_in; + z->next_in = p; + z->avail_in = n; + z->state->sub.marker = m; + + /* return no joy or set up to restart on a new block */ + if (m != 4) + return Z_DATA_ERROR; + r = z->total_in; w = z->total_out; + zlib_inflateReset(z); + z->total_in = r; z->total_out = w; + z->state->mode = BLOCKS; + return Z_OK; +} + + +/* Returns true if inflate is currently at the end of a block generated + * by Z_SYNC_FLUSH or Z_FULL_FLUSH. This function is used by one PPP + * implementation to provide an additional safety check. PPP uses Z_SYNC_FLUSH + * but removes the length bytes of the resulting empty stored block. When + * decompressing, PPP checks that at the end of input packet, inflate is + * waiting for these length bytes. + */ +int zlib_inflateSyncPoint( + z_streamp z +) +{ + if (z == NULL || z->state == NULL || z->state->blocks == NULL) + return Z_STREAM_ERROR; + return zlib_inflate_blocks_sync_point(z->state->blocks); +} + +/* + * This subroutine adds the data at next_in/avail_in to the output history + * without performing any output. The output buffer must be "caught up"; + * i.e. no pending output (hence s->read equals s->write), and the state must + * be BLOCKS (i.e. we should be willing to see the start of a series of + * BLOCKS). On exit, the output will also be caught up, and the checksum + * will have been updated if need be. + */ +static int zlib_inflate_addhistory(inflate_blocks_statef *s, + z_stream *z) +{ + uLong b; /* bit buffer */ /* NOT USED HERE */ + uInt k; /* bits in bit buffer */ /* NOT USED HERE */ + uInt t; /* temporary storage */ + Byte *p; /* input data pointer */ + uInt n; /* bytes available there */ + Byte *q; /* output window write pointer */ + uInt m; /* bytes to end of window or read pointer */ + + if (s->read != s->write) + return Z_STREAM_ERROR; + if (s->mode != TYPE) + return Z_DATA_ERROR; + + /* we're ready to rock */ + LOAD + /* while there is input ready, copy to output buffer, moving + * pointers as needed. + */ + while (n) { + t = n; /* how many to do */ + /* is there room until end of buffer? */ + if (t > m) t = m; + /* update check information */ + if (s->checkfn != NULL) + s->check = (*s->checkfn)(s->check, q, t); + memcpy(q, p, t); + q += t; + p += t; + n -= t; + z->total_out += t; + s->read = q; /* drag read pointer forward */ +/* WWRAP */ /* expand WWRAP macro by hand to handle s->read */ + if (q == s->end) { + s->read = q = s->window; + m = WAVAIL; + } + } + UPDATE + return Z_OK; +} + + +/* + * This subroutine adds the data at next_in/avail_in to the output history + * without performing any output. The output buffer must be "caught up"; + * i.e. no pending output (hence s->read equals s->write), and the state must + * be BLOCKS (i.e. we should be willing to see the start of a series of + * BLOCKS). On exit, the output will also be caught up, and the checksum + * will have been updated if need be. + */ + +int zlib_inflateIncomp( + z_stream *z + +) +{ + if (z->state->mode != BLOCKS) + return Z_DATA_ERROR; + return zlib_inflate_addhistory(z->state->blocks, z); +} diff --git a/lib/zlib_inflate/inftrees.c b/lib/zlib_inflate/inftrees.c new file mode 100644 index 00000000000..874950ec485 --- /dev/null +++ b/lib/zlib_inflate/inftrees.c @@ -0,0 +1,412 @@ +/* inftrees.c -- generate Huffman trees for efficient decoding + * Copyright (C) 1995-1998 Mark Adler + * For conditions of distribution and use, see copyright notice in zlib.h + */ + +#include <linux/zutil.h> +#include "inftrees.h" +#include "infutil.h" + +static const char inflate_copyright[] __attribute_used__ = + " inflate 1.1.3 Copyright 1995-1998 Mark Adler "; +/* + If you use the zlib library in a product, an acknowledgment is welcome + in the documentation of your product. If for some reason you cannot + include such an acknowledgment, I would appreciate that you keep this + copyright string in the executable of your product. + */ +struct internal_state; + +/* simplify the use of the inflate_huft type with some defines */ +#define exop word.what.Exop +#define bits word.what.Bits + + +static int huft_build ( + uInt *, /* code lengths in bits */ + uInt, /* number of codes */ + uInt, /* number of "simple" codes */ + const uInt *, /* list of base values for non-simple codes */ + const uInt *, /* list of extra bits for non-simple codes */ + inflate_huft **, /* result: starting table */ + uInt *, /* maximum lookup bits (returns actual) */ + inflate_huft *, /* space for trees */ + uInt *, /* hufts used in space */ + uInt * ); /* space for values */ + +/* Tables for deflate from PKZIP's appnote.txt. */ +static const uInt cplens[31] = { /* Copy lengths for literal codes 257..285 */ + 3, 4, 5, 6, 7, 8, 9, 10, 11, 13, 15, 17, 19, 23, 27, 31, + 35, 43, 51, 59, 67, 83, 99, 115, 131, 163, 195, 227, 258, 0, 0}; + /* see note #13 above about 258 */ +static const uInt cplext[31] = { /* Extra bits for literal codes 257..285 */ + 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 2, 2, 2, 2, + 3, 3, 3, 3, 4, 4, 4, 4, 5, 5, 5, 5, 0, 112, 112}; /* 112==invalid */ +static const uInt cpdist[30] = { /* Copy offsets for distance codes 0..29 */ + 1, 2, 3, 4, 5, 7, 9, 13, 17, 25, 33, 49, 65, 97, 129, 193, + 257, 385, 513, 769, 1025, 1537, 2049, 3073, 4097, 6145, + 8193, 12289, 16385, 24577}; +static const uInt cpdext[30] = { /* Extra bits for distance codes */ + 0, 0, 0, 0, 1, 1, 2, 2, 3, 3, 4, 4, 5, 5, 6, 6, + 7, 7, 8, 8, 9, 9, 10, 10, 11, 11, + 12, 12, 13, 13}; + +/* + Huffman code decoding is performed using a multi-level table lookup. + The fastest way to decode is to simply build a lookup table whose + size is determined by the longest code. However, the time it takes + to build this table can also be a factor if the data being decoded + is not very long. The most common codes are necessarily the + shortest codes, so those codes dominate the decoding time, and hence + the speed. The idea is you can have a shorter table that decodes the + shorter, more probable codes, and then point to subsidiary tables for + the longer codes. The time it costs to decode the longer codes is + then traded against the time it takes to make longer tables. + + This results of this trade are in the variables lbits and dbits + below. lbits is the number of bits the first level table for literal/ + length codes can decode in one step, and dbits is the same thing for + the distance codes. Subsequent tables are also less than or equal to + those sizes. These values may be adjusted either when all of the + codes are shorter than that, in which case the longest code length in + bits is used, or when the shortest code is *longer* than the requested + table size, in which case the length of the shortest code in bits is + used. + + There are two different values for the two tables, since they code a + different number of possibilities each. The literal/length table + codes 286 possible values, or in a flat code, a little over eight + bits. The distance table codes 30 possible values, or a little less + than five bits, flat. The optimum values for speed end up being + about one bit more than those, so lbits is 8+1 and dbits is 5+1. + The optimum values may differ though from machine to machine, and + possibly even between compilers. Your mileage may vary. + */ + + +/* If BMAX needs to be larger than 16, then h and x[] should be uLong. */ +#define BMAX 15 /* maximum bit length of any code */ + +static int huft_build( + uInt *b, /* code lengths in bits (all assumed <= BMAX) */ + uInt n, /* number of codes (assumed <= 288) */ + uInt s, /* number of simple-valued codes (0..s-1) */ + const uInt *d, /* list of base values for non-simple codes */ + const uInt *e, /* list of extra bits for non-simple codes */ + inflate_huft **t, /* result: starting table */ + uInt *m, /* maximum lookup bits, returns actual */ + inflate_huft *hp, /* space for trees */ + uInt *hn, /* hufts used in space */ + uInt *v /* working area: values in order of bit length */ +) +/* Given a list of code lengths and a maximum table size, make a set of + tables to decode that set of codes. Return Z_OK on success, Z_BUF_ERROR + if the given code set is incomplete (the tables are still built in this + case), Z_DATA_ERROR if the input is invalid (an over-subscribed set of + lengths), or Z_MEM_ERROR if not enough memory. */ +{ + + uInt a; /* counter for codes of length k */ + uInt c[BMAX+1]; /* bit length count table */ + uInt f; /* i repeats in table every f entries */ + int g; /* maximum code length */ + int h; /* table level */ + register uInt i; /* counter, current code */ + register uInt j; /* counter */ + register int k; /* number of bits in current code */ + int l; /* bits per table (returned in m) */ + uInt mask; /* (1 << w) - 1, to avoid cc -O bug on HP */ + register uInt *p; /* pointer into c[], b[], or v[] */ + inflate_huft *q; /* points to current table */ + struct inflate_huft_s r; /* table entry for structure assignment */ + inflate_huft *u[BMAX]; /* table stack */ + register int w; /* bits before this table == (l * h) */ + uInt x[BMAX+1]; /* bit offsets, then code stack */ + uInt *xp; /* pointer into x */ + int y; /* number of dummy codes added */ + uInt z; /* number of entries in current table */ + + + /* Generate counts for each bit length */ + p = c; +#define C0 *p++ = 0; +#define C2 C0 C0 C0 C0 +#define C4 C2 C2 C2 C2 + C4 /* clear c[]--assume BMAX+1 is 16 */ + p = b; i = n; + do { + c[*p++]++; /* assume all entries <= BMAX */ + } while (--i); + if (c[0] == n) /* null input--all zero length codes */ + { + *t = NULL; + *m = 0; + return Z_OK; + } + + + /* Find minimum and maximum length, bound *m by those */ + l = *m; + for (j = 1; j <= BMAX; j++) + if (c[j]) + break; + k = j; /* minimum code length */ + if ((uInt)l < j) + l = j; + for (i = BMAX; i; i--) + if (c[i]) + break; + g = i; /* maximum code length */ + if ((uInt)l > i) + l = i; + *m = l; + + + /* Adjust last length count to fill out codes, if needed */ + for (y = 1 << j; j < i; j++, y <<= 1) + if ((y -= c[j]) < 0) + return Z_DATA_ERROR; + if ((y -= c[i]) < 0) + return Z_DATA_ERROR; + c[i] += y; + + + /* Generate starting offsets into the value table for each length */ + x[1] = j = 0; + p = c + 1; xp = x + 2; + while (--i) { /* note that i == g from above */ + *xp++ = (j += *p++); + } + + + /* Make a table of values in order of bit lengths */ + p = b; i = 0; + do { + if ((j = *p++) != 0) + v[x[j]++] = i; + } while (++i < n); + n = x[g]; /* set n to length of v */ + + + /* Generate the Huffman codes and for each, make the table entries */ + x[0] = i = 0; /* first Huffman code is zero */ + p = v; /* grab values in bit order */ + h = -1; /* no tables yet--level -1 */ + w = -l; /* bits decoded == (l * h) */ + u[0] = NULL; /* just to keep compilers happy */ + q = NULL; /* ditto */ + z = 0; /* ditto */ + + /* go through the bit lengths (k already is bits in shortest code) */ + for (; k <= g; k++) + { + a = c[k]; + while (a--) + { + /* here i is the Huffman code of length k bits for value *p */ + /* make tables up to required level */ + while (k > w + l) + { + h++; + w += l; /* previous table always l bits */ + + /* compute minimum size table less than or equal to l bits */ + z = g - w; + z = z > (uInt)l ? l : z; /* table size upper limit */ + if ((f = 1 << (j = k - w)) > a + 1) /* try a k-w bit table */ + { /* too few codes for k-w bit table */ + f -= a + 1; /* deduct codes from patterns left */ + xp = c + k; + if (j < z) + while (++j < z) /* try smaller tables up to z bits */ + { + if ((f <<= 1) <= *++xp) + break; /* enough codes to use up j bits */ + f -= *xp; /* else deduct codes from patterns */ + } + } + z = 1 << j; /* table entries for j-bit table */ + + /* allocate new table */ + if (*hn + z > MANY) /* (note: doesn't matter for fixed) */ + return Z_DATA_ERROR; /* overflow of MANY */ + u[h] = q = hp + *hn; + *hn += z; + + /* connect to last table, if there is one */ + if (h) + { + x[h] = i; /* save pattern for backing up */ + r.bits = (Byte)l; /* bits to dump before this table */ + r.exop = (Byte)j; /* bits in this table */ + j = i >> (w - l); + r.base = (uInt)(q - u[h-1] - j); /* offset to this table */ + u[h-1][j] = r; /* connect to last table */ + } + else + *t = q; /* first table is returned result */ + } + + /* set up table entry in r */ + r.bits = (Byte)(k - w); + if (p >= v + n) + r.exop = 128 + 64; /* out of values--invalid code */ + else if (*p < s) + { + r.exop = (Byte)(*p < 256 ? 0 : 32 + 64); /* 256 is end-of-block */ + r.base = *p++; /* simple code is just the value */ + } + else + { + r.exop = (Byte)(e[*p - s] + 16 + 64);/* non-simple--look up in lists */ + r.base = d[*p++ - s]; + } + + /* fill code-like entries with r */ + f = 1 << (k - w); + for (j = i >> w; j < z; j += f) + q[j] = r; + + /* backwards increment the k-bit code i */ + for (j = 1 << (k - 1); i & j; j >>= 1) + i ^= j; + i ^= j; + + /* backup over finished tables */ + mask = (1 << w) - 1; /* needed on HP, cc -O bug */ + while ((i & mask) != x[h]) + { + h--; /* don't need to update q */ + w -= l; + mask = (1 << w) - 1; + } + } + } + + + /* Return Z_BUF_ERROR if we were given an incomplete table */ + return y != 0 && g != 1 ? Z_BUF_ERROR : Z_OK; +} + + +int zlib_inflate_trees_bits( + uInt *c, /* 19 code lengths */ + uInt *bb, /* bits tree desired/actual depth */ + inflate_huft **tb, /* bits tree result */ + inflate_huft *hp, /* space for trees */ + z_streamp z /* for messages */ +) +{ + int r; + uInt hn = 0; /* hufts used in space */ + uInt *v; /* work area for huft_build */ + + v = WS(z)->tree_work_area_1; + r = huft_build(c, 19, 19, NULL, NULL, tb, bb, hp, &hn, v); + if (r == Z_DATA_ERROR) + z->msg = (char*)"oversubscribed dynamic bit lengths tree"; + else if (r == Z_BUF_ERROR || *bb == 0) + { + z->msg = (char*)"incomplete dynamic bit lengths tree"; + r = Z_DATA_ERROR; + } + return r; +} + +int zlib_inflate_trees_dynamic( + uInt nl, /* number of literal/length codes */ + uInt nd, /* number of distance codes */ + uInt *c, /* that many (total) code lengths */ + uInt *bl, /* literal desired/actual bit depth */ + uInt *bd, /* distance desired/actual bit depth */ + inflate_huft **tl, /* literal/length tree result */ + inflate_huft **td, /* distance tree result */ + inflate_huft *hp, /* space for trees */ + z_streamp z /* for messages */ +) +{ + int r; + uInt hn = 0; /* hufts used in space */ + uInt *v; /* work area for huft_build */ + + /* allocate work area */ + v = WS(z)->tree_work_area_2; + + /* build literal/length tree */ + r = huft_build(c, nl, 257, cplens, cplext, tl, bl, hp, &hn, v); + if (r != Z_OK || *bl == 0) + { + if (r == Z_DATA_ERROR) + z->msg = (char*)"oversubscribed literal/length tree"; + else if (r != Z_MEM_ERROR) + { + z->msg = (char*)"incomplete literal/length tree"; + r = Z_DATA_ERROR; + } + return r; + } + + /* build distance tree */ + r = huft_build(c + nl, nd, 0, cpdist, cpdext, td, bd, hp, &hn, v); + if (r != Z_OK || (*bd == 0 && nl > 257)) + { + if (r == Z_DATA_ERROR) + z->msg = (char*)"oversubscribed distance tree"; + else if (r == Z_BUF_ERROR) { +#ifdef PKZIP_BUG_WORKAROUND + r = Z_OK; + } +#else + z->msg = (char*)"incomplete distance tree"; + r = Z_DATA_ERROR; + } + else if (r != Z_MEM_ERROR) + { + z->msg = (char*)"empty distance tree with lengths"; + r = Z_DATA_ERROR; + } + return r; +#endif + } + + /* done */ + return Z_OK; +} + + +int zlib_inflate_trees_fixed( + uInt *bl, /* literal desired/actual bit depth */ + uInt *bd, /* distance desired/actual bit depth */ + inflate_huft **tl, /* literal/length tree result */ + inflate_huft **td, /* distance tree result */ + inflate_huft *hp, /* space for trees */ + z_streamp z /* for memory allocation */ +) +{ + int i; /* temporary variable */ + unsigned l[288]; /* length list for huft_build */ + uInt *v; /* work area for huft_build */ + + /* set up literal table */ + for (i = 0; i < 144; i++) + l[i] = 8; + for (; i < 256; i++) + l[i] = 9; + for (; i < 280; i++) + l[i] = 7; + for (; i < 288; i++) /* make a complete, but wrong code set */ + l[i] = 8; + *bl = 9; + v = WS(z)->tree_work_area_1; + if ((i = huft_build(l, 288, 257, cplens, cplext, tl, bl, hp, &i, v)) != 0) + return i; + + /* set up distance table */ + for (i = 0; i < 30; i++) /* make an incomplete code set */ + l[i] = 5; + *bd = 5; + if ((i = huft_build(l, 30, 0, cpdist, cpdext, td, bd, hp, &i, v)) > 1) + return i; + + return Z_OK; +} diff --git a/lib/zlib_inflate/inftrees.h b/lib/zlib_inflate/inftrees.h new file mode 100644 index 00000000000..e37705adc00 --- /dev/null +++ b/lib/zlib_inflate/inftrees.h @@ -0,0 +1,64 @@ +/* inftrees.h -- header to use inftrees.c + * Copyright (C) 1995-1998 Mark Adler + * For conditions of distribution and use, see copyright notice in zlib.h + */ + +/* WARNING: this file should *not* be used by applications. It is + part of the implementation of the compression library and is + subject to change. Applications should only use zlib.h. + */ + +/* Huffman code lookup table entry--this entry is four bytes for machines + that have 16-bit pointers (e.g. PC's in the small or medium model). */ + +#ifndef _INFTREES_H +#define _INFTREES_H + +typedef struct inflate_huft_s inflate_huft; + +struct inflate_huft_s { + union { + struct { + Byte Exop; /* number of extra bits or operation */ + Byte Bits; /* number of bits in this code or subcode */ + } what; + uInt pad; /* pad structure to a power of 2 (4 bytes for */ + } word; /* 16-bit, 8 bytes for 32-bit int's) */ + uInt base; /* literal, length base, distance base, + or table offset */ +}; + +/* Maximum size of dynamic tree. The maximum found in a long but non- + exhaustive search was 1004 huft structures (850 for length/literals + and 154 for distances, the latter actually the result of an + exhaustive search). The actual maximum is not known, but the + value below is more than safe. */ +#define MANY 1440 + +extern int zlib_inflate_trees_bits ( + uInt *, /* 19 code lengths */ + uInt *, /* bits tree desired/actual depth */ + inflate_huft **, /* bits tree result */ + inflate_huft *, /* space for trees */ + z_streamp); /* for messages */ + +extern int zlib_inflate_trees_dynamic ( + uInt, /* number of literal/length codes */ + uInt, /* number of distance codes */ + uInt *, /* that many (total) code lengths */ + uInt *, /* literal desired/actual bit depth */ + uInt *, /* distance desired/actual bit depth */ + inflate_huft **, /* literal/length tree result */ + inflate_huft **, /* distance tree result */ + inflate_huft *, /* space for trees */ + z_streamp); /* for messages */ + +extern int zlib_inflate_trees_fixed ( + uInt *, /* literal desired/actual bit depth */ + uInt *, /* distance desired/actual bit depth */ + inflate_huft **, /* literal/length tree result */ + inflate_huft **, /* distance tree result */ + inflate_huft *, /* space for trees */ + z_streamp); /* for memory allocation */ + +#endif /* _INFTREES_H */ diff --git a/lib/zlib_inflate/infutil.c b/lib/zlib_inflate/infutil.c new file mode 100644 index 00000000000..00202b3438e --- /dev/null +++ b/lib/zlib_inflate/infutil.c @@ -0,0 +1,88 @@ +/* inflate_util.c -- data and routines common to blocks and codes + * Copyright (C) 1995-1998 Mark Adler + * For conditions of distribution and use, see copyright notice in zlib.h + */ + +#include <linux/zutil.h> +#include "infblock.h" +#include "inftrees.h" +#include "infcodes.h" +#include "infutil.h" + +struct inflate_codes_state; + +/* And'ing with mask[n] masks the lower n bits */ +uInt zlib_inflate_mask[17] = { + 0x0000, + 0x0001, 0x0003, 0x0007, 0x000f, 0x001f, 0x003f, 0x007f, 0x00ff, + 0x01ff, 0x03ff, 0x07ff, 0x0fff, 0x1fff, 0x3fff, 0x7fff, 0xffff +}; + + +/* copy as much as possible from the sliding window to the output area */ +int zlib_inflate_flush( + inflate_blocks_statef *s, + z_streamp z, + int r +) +{ + uInt n; + Byte *p; + Byte *q; + + /* local copies of source and destination pointers */ + p = z->next_out; + q = s->read; + + /* compute number of bytes to copy as far as end of window */ + n = (uInt)((q <= s->write ? s->write : s->end) - q); + if (n > z->avail_out) n = z->avail_out; + if (n && r == Z_BUF_ERROR) r = Z_OK; + + /* update counters */ + z->avail_out -= n; + z->total_out += n; + + /* update check information */ + if (s->checkfn != NULL) + z->adler = s->check = (*s->checkfn)(s->check, q, n); + + /* copy as far as end of window */ + memcpy(p, q, n); + p += n; + q += n; + + /* see if more to copy at beginning of window */ + if (q == s->end) + { + /* wrap pointers */ + q = s->window; + if (s->write == s->end) + s->write = s->window; + + /* compute bytes to copy */ + n = (uInt)(s->write - q); + if (n > z->avail_out) n = z->avail_out; + if (n && r == Z_BUF_ERROR) r = Z_OK; + + /* update counters */ + z->avail_out -= n; + z->total_out += n; + + /* update check information */ + if (s->checkfn != NULL) + z->adler = s->check = (*s->checkfn)(s->check, q, n); + + /* copy */ + memcpy(p, q, n); + p += n; + q += n; + } + + /* update pointers */ + z->next_out = p; + s->read = q; + + /* done */ + return r; +} diff --git a/lib/zlib_inflate/infutil.h b/lib/zlib_inflate/infutil.h new file mode 100644 index 00000000000..a15875fc5f7 --- /dev/null +++ b/lib/zlib_inflate/infutil.h @@ -0,0 +1,197 @@ +/* infutil.h -- types and macros common to blocks and codes + * Copyright (C) 1995-1998 Mark Adler + * For conditions of distribution and use, see copyright notice in zlib.h + */ + +/* WARNING: this file should *not* be used by applications. It is + part of the implementation of the compression library and is + subject to change. Applications should only use zlib.h. + */ + +#ifndef _INFUTIL_H +#define _INFUTIL_H + +#include <linux/zconf.h> +#include "inftrees.h" +#include "infcodes.h" + +typedef enum { + TYPE, /* get type bits (3, including end bit) */ + LENS, /* get lengths for stored */ + STORED, /* processing stored block */ + TABLE, /* get table lengths */ + BTREE, /* get bit lengths tree for a dynamic block */ + DTREE, /* get length, distance trees for a dynamic block */ + CODES, /* processing fixed or dynamic block */ + DRY, /* output remaining window bytes */ + B_DONE, /* finished last block, done */ + B_BAD} /* got a data error--stuck here */ +inflate_block_mode; + +/* inflate blocks semi-private state */ +struct inflate_blocks_state { + + /* mode */ + inflate_block_mode mode; /* current inflate_block mode */ + + /* mode dependent information */ + union { + uInt left; /* if STORED, bytes left to copy */ + struct { + uInt table; /* table lengths (14 bits) */ + uInt index; /* index into blens (or border) */ + uInt *blens; /* bit lengths of codes */ + uInt bb; /* bit length tree depth */ + inflate_huft *tb; /* bit length decoding tree */ + } trees; /* if DTREE, decoding info for trees */ + struct { + inflate_codes_statef + *codes; + } decode; /* if CODES, current state */ + } sub; /* submode */ + uInt last; /* true if this block is the last block */ + + /* mode independent information */ + uInt bitk; /* bits in bit buffer */ + uLong bitb; /* bit buffer */ + inflate_huft *hufts; /* single malloc for tree space */ + Byte *window; /* sliding window */ + Byte *end; /* one byte after sliding window */ + Byte *read; /* window read pointer */ + Byte *write; /* window write pointer */ + check_func checkfn; /* check function */ + uLong check; /* check on output */ + +}; + + +/* defines for inflate input/output */ +/* update pointers and return */ +#define UPDBITS {s->bitb=b;s->bitk=k;} +#define UPDIN {z->avail_in=n;z->total_in+=p-z->next_in;z->next_in=p;} +#define UPDOUT {s->write=q;} +#define UPDATE {UPDBITS UPDIN UPDOUT} +#define LEAVE {UPDATE return zlib_inflate_flush(s,z,r);} +/* get bytes and bits */ +#define LOADIN {p=z->next_in;n=z->avail_in;b=s->bitb;k=s->bitk;} +#define NEEDBYTE {if(n)r=Z_OK;else LEAVE} +#define NEXTBYTE (n--,*p++) +#define NEEDBITS(j) {while(k<(j)){NEEDBYTE;b|=((uLong)NEXTBYTE)<<k;k+=8;}} +#define DUMPBITS(j) {b>>=(j);k-=(j);} +/* output bytes */ +#define WAVAIL (uInt)(q<s->read?s->read-q-1:s->end-q) +#define LOADOUT {q=s->write;m=(uInt)WAVAIL;} +#define WRAP {if(q==s->end&&s->read!=s->window){q=s->window;m=(uInt)WAVAIL;}} +#define FLUSH {UPDOUT r=zlib_inflate_flush(s,z,r); LOADOUT} +#define NEEDOUT {if(m==0){WRAP if(m==0){FLUSH WRAP if(m==0) LEAVE}}r=Z_OK;} +#define OUTBYTE(a) {*q++=(Byte)(a);m--;} +/* load local pointers */ +#define LOAD {LOADIN LOADOUT} + +/* masks for lower bits (size given to avoid silly warnings with Visual C++) */ +extern uInt zlib_inflate_mask[17]; + +/* copy as much as possible from the sliding window to the output area */ +extern int zlib_inflate_flush ( + inflate_blocks_statef *, + z_streamp , + int); + +/* inflate private state */ +typedef enum { + METHOD, /* waiting for method byte */ + FLAG, /* waiting for flag byte */ + DICT4, /* four dictionary check bytes to go */ + DICT3, /* three dictionary check bytes to go */ + DICT2, /* two dictionary check bytes to go */ + DICT1, /* one dictionary check byte to go */ + DICT0, /* waiting for inflateSetDictionary */ + BLOCKS, /* decompressing blocks */ + CHECK4, /* four check bytes to go */ + CHECK3, /* three check bytes to go */ + CHECK2, /* two check bytes to go */ + CHECK1, /* one check byte to go */ + I_DONE, /* finished check, done */ + I_BAD} /* got an error--stay here */ +inflate_mode; + +struct internal_state { + + /* mode */ + inflate_mode mode; /* current inflate mode */ + + /* mode dependent information */ + union { + uInt method; /* if FLAGS, method byte */ + struct { + uLong was; /* computed check value */ + uLong need; /* stream check value */ + } check; /* if CHECK, check values to compare */ + uInt marker; /* if BAD, inflateSync's marker bytes count */ + } sub; /* submode */ + + /* mode independent information */ + int nowrap; /* flag for no wrapper */ + uInt wbits; /* log2(window size) (8..15, defaults to 15) */ + inflate_blocks_statef + *blocks; /* current inflate_blocks state */ + +}; + +/* inflate codes private state */ +typedef enum { /* waiting for "i:"=input, "o:"=output, "x:"=nothing */ + START, /* x: set up for LEN */ + LEN, /* i: get length/literal/eob next */ + LENEXT, /* i: getting length extra (have base) */ + DIST, /* i: get distance next */ + DISTEXT, /* i: getting distance extra */ + COPY, /* o: copying bytes in window, waiting for space */ + LIT, /* o: got literal, waiting for output space */ + WASH, /* o: got eob, possibly still output waiting */ + END, /* x: got eob and all data flushed */ + BADCODE} /* x: got error */ +inflate_codes_mode; + +struct inflate_codes_state { + + /* mode */ + inflate_codes_mode mode; /* current inflate_codes mode */ + + /* mode dependent information */ + uInt len; + union { + struct { + inflate_huft *tree; /* pointer into tree */ + uInt need; /* bits needed */ + } code; /* if LEN or DIST, where in tree */ + uInt lit; /* if LIT, literal */ + struct { + uInt get; /* bits to get for extra */ + uInt dist; /* distance back to copy from */ + } copy; /* if EXT or COPY, where and how much */ + } sub; /* submode */ + + /* mode independent information */ + Byte lbits; /* ltree bits decoded per branch */ + Byte dbits; /* dtree bits decoder per branch */ + inflate_huft *ltree; /* literal/length/eob tree */ + inflate_huft *dtree; /* distance tree */ + +}; + +/* memory allocation for inflation */ + +struct inflate_workspace { + inflate_codes_statef working_state; + struct inflate_blocks_state working_blocks_state; + struct internal_state internal_state; + unsigned int tree_work_area_1[19]; + unsigned int tree_work_area_2[288]; + unsigned working_blens[258 + 0x1f + 0x1f]; + inflate_huft working_hufts[MANY]; + unsigned char working_window[1 << MAX_WBITS]; +}; + +#define WS(z) ((struct inflate_workspace *)(z->workspace)) + +#endif |