diff options
Diffstat (limited to 'lib')
-rw-r--r-- | lib/Kconfig | 68 | ||||
-rw-r--r-- | lib/Kconfig.debug | 44 | ||||
-rw-r--r-- | lib/Makefile | 2 | ||||
-rw-r--r-- | lib/bug.c | 2 | ||||
-rw-r--r-- | lib/clz_tab.c | 18 | ||||
-rw-r--r-- | lib/crc32.c | 1287 | ||||
-rw-r--r-- | lib/crc32defs.h | 56 | ||||
-rw-r--r-- | lib/debugobjects.c | 14 | ||||
-rw-r--r-- | lib/digsig.c | 52 | ||||
-rw-r--r-- | lib/dma-debug.c | 3 | ||||
-rw-r--r-- | lib/dynamic_debug.c | 270 | ||||
-rw-r--r-- | lib/dynamic_queue_limits.c | 1 | ||||
-rw-r--r-- | lib/gen_crc32table.c | 81 | ||||
-rw-r--r-- | lib/idr.c | 8 | ||||
-rw-r--r-- | lib/kobject_uevent.c | 19 | ||||
-rw-r--r-- | lib/kstrtox.c | 18 | ||||
-rw-r--r-- | lib/mpi/longlong.h | 44 | ||||
-rw-r--r-- | lib/mpi/mpi-bit.c | 19 | ||||
-rw-r--r-- | lib/mpi/mpi-div.c | 5 | ||||
-rw-r--r-- | lib/mpi/mpi-pow.c | 2 | ||||
-rw-r--r-- | lib/mpi/mpicoder.c | 91 | ||||
-rw-r--r-- | lib/mpi/mpih-div.c | 4 | ||||
-rw-r--r-- | lib/mpi/mpiutil.c | 5 | ||||
-rw-r--r-- | lib/pci_iomap.c | 2 | ||||
-rw-r--r-- | lib/prio_tree.c | 156 | ||||
-rw-r--r-- | lib/scatterlist.c | 4 | ||||
-rw-r--r-- | lib/string.c | 20 | ||||
-rw-r--r-- | lib/swiotlb.c | 5 | ||||
-rw-r--r-- | lib/vsprintf.c | 32 |
29 files changed, 1605 insertions, 727 deletions
diff --git a/lib/Kconfig b/lib/Kconfig index 169eb7c598e..43359bb1ca9 100644 --- a/lib/Kconfig +++ b/lib/Kconfig @@ -19,6 +19,9 @@ config RATIONAL config GENERIC_FIND_FIRST_BIT bool +config NO_GENERIC_PCI_IOPORT_MAP + bool + config GENERIC_PCI_IOMAP bool @@ -58,14 +61,67 @@ config CRC_ITU_T functions require M here. config CRC32 - tristate "CRC32 functions" + tristate "CRC32/CRC32c functions" default y select BITREVERSE 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. + modules require CRC32/CRC32c functions, but a module built outside + the kernel tree does. Such modules that use library CRC32/CRC32c + functions require M here. + +config CRC32_SELFTEST + bool "CRC32 perform self test on init" + default n + depends on CRC32 + help + This option enables the CRC32 library functions to perform a + self test on initialization. The self test computes crc32_le + and crc32_be over byte strings with random alignment and length + and computes the total elapsed time and number of bytes processed. + +choice + prompt "CRC32 implementation" + depends on CRC32 + default CRC32_SLICEBY8 + +config CRC32_SLICEBY8 + bool "Slice by 8 bytes" + help + Calculate checksum 8 bytes at a time with a clever slicing algorithm. + This is the fastest algorithm, but comes with a 8KiB lookup table. + Most modern processors have enough cache to hold this table without + thrashing the cache. + + This is the default implementation choice. Choose this one unless + you have a good reason not to. + +config CRC32_SLICEBY4 + bool "Slice by 4 bytes" + help + Calculate checksum 4 bytes at a time with a clever slicing algorithm. + This is a bit slower than slice by 8, but has a smaller 4KiB lookup + table. + + Only choose this option if you know what you are doing. + +config CRC32_SARWATE + bool "Sarwate's Algorithm (one byte at a time)" + help + Calculate checksum a byte at a time using Sarwate's algorithm. This + is not particularly fast, but has a small 256 byte lookup table. + + Only choose this option if you know what you are doing. + +config CRC32_BIT + bool "Classic Algorithm (one bit at a time)" + help + Calculate checksum one bit at a time. This is VERY slow, but has + no lookup table. This is provided as a debugging option. + + Only choose this option if you are debugging crc32. + +endchoice config CRC7 tristate "CRC7 functions" @@ -279,6 +335,9 @@ config AVERAGE If unsure, say N. +config CLZ_TAB + bool + config CORDIC tristate "CORDIC algorithm" help @@ -287,6 +346,7 @@ config CORDIC config MPILIB tristate + select CLZ_TAB help Multiprecision maths library from GnuPG. It is used to implement RSA digital signature verification, diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 943a6182cdf..f7af95d304c 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -166,22 +166,25 @@ config LOCKUP_DETECTOR hard and soft lockups. Softlockups are bugs that cause the kernel to loop in kernel - mode for more than 60 seconds, without giving other tasks a + mode for more than 20 seconds, without giving other tasks a chance to run. The current stack trace is displayed upon detection and the system will stay locked up. Hardlockups are bugs that cause the CPU to loop in kernel mode - for more than 60 seconds, without letting other interrupts have a + for more than 10 seconds, without letting other interrupts have a chance to run. The current stack trace is displayed upon detection and the system will stay locked up. The overhead should be minimal. A periodic hrtimer runs to - generate interrupts and kick the watchdog task every 10-12 seconds. - An NMI is generated every 60 seconds or so to check for hardlockups. + generate interrupts and kick the watchdog task every 4 seconds. + An NMI is generated every 10 seconds or so to check for hardlockups. + + The frequency of hrtimer and NMI events and the soft and hard lockup + thresholds can be controlled through the sysctl watchdog_thresh. config HARDLOCKUP_DETECTOR def_bool LOCKUP_DETECTOR && PERF_EVENTS && HAVE_PERF_EVENTS_NMI && \ - !ARCH_HAS_NMI_WATCHDOG + !HAVE_NMI_WATCHDOG config BOOTPARAM_HARDLOCKUP_PANIC bool "Panic (Reboot) On Hard Lockups" @@ -189,7 +192,8 @@ config BOOTPARAM_HARDLOCKUP_PANIC help Say Y here to enable the kernel to panic on "hard lockups", which are bugs that cause the kernel to loop in kernel - mode with interrupts disabled for more than 60 seconds. + mode with interrupts disabled for more than 10 seconds (configurable + using the watchdog_thresh sysctl). Say N if unsure. @@ -206,8 +210,8 @@ config BOOTPARAM_SOFTLOCKUP_PANIC help Say Y here to enable the kernel to panic on "soft lockups", which are bugs that cause the kernel to loop in kernel - mode for more than 60 seconds, without giving other tasks a - chance to run. + mode for more than 20 seconds (configurable using the watchdog_thresh + sysctl), without giving other tasks a chance to run. The panic can be used in combination with panic_timeout, to cause the system to reboot automatically after a @@ -927,6 +931,30 @@ config RCU_CPU_STALL_VERBOSE Say Y if you want to enable such checks. +config RCU_CPU_STALL_INFO + bool "Print additional diagnostics on RCU CPU stall" + depends on (TREE_RCU || TREE_PREEMPT_RCU) && DEBUG_KERNEL + default n + help + For each stalled CPU that is aware of the current RCU grace + period, print out additional per-CPU diagnostic information + regarding scheduling-clock ticks, idle state, and, + for RCU_FAST_NO_HZ kernels, idle-entry state. + + Say N if you are unsure. + + Say Y if you want to enable such diagnostics. + +config RCU_TRACE + bool "Enable tracing for RCU" + depends on DEBUG_KERNEL + help + This option provides tracing in RCU which presents stats + in debugfs for debugging RCU implementation. + + Say Y here if you want to enable RCU tracing + Say N if you are unsure. + config KPROBES_SANITY_TEST bool "Kprobes sanity tests" depends on DEBUG_KERNEL diff --git a/lib/Makefile b/lib/Makefile index d71aae1b01b..18515f0267c 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -121,6 +121,8 @@ obj-$(CONFIG_DQL) += dynamic_queue_limits.o obj-$(CONFIG_MPILIB) += mpi/ obj-$(CONFIG_SIGNATURE) += digsig.o +obj-$(CONFIG_CLZ_TAB) += clz_tab.o + hostprogs-y := gen_crc32table clean-files := crc32table.h diff --git a/lib/bug.c b/lib/bug.c index 19552096d16..a28c1415357 100644 --- a/lib/bug.c +++ b/lib/bug.c @@ -169,7 +169,7 @@ enum bug_trap_type report_bug(unsigned long bugaddr, struct pt_regs *regs) return BUG_TRAP_TYPE_WARN; } - printk(KERN_EMERG "------------[ cut here ]------------\n"); + printk(KERN_DEFAULT "------------[ cut here ]------------\n"); if (file) printk(KERN_CRIT "kernel BUG at %s:%u!\n", diff --git a/lib/clz_tab.c b/lib/clz_tab.c new file mode 100644 index 00000000000..7287b4a991a --- /dev/null +++ b/lib/clz_tab.c @@ -0,0 +1,18 @@ +const unsigned char __clz_tab[] = { + 0, 1, 2, 2, 3, 3, 3, 3, 4, 4, 4, 4, 4, 4, 4, 4, 5, 5, 5, 5, 5, 5, 5, 5, + 5, 5, 5, 5, 5, 5, 5, 5, + 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, + 6, 6, 6, 6, 6, 6, 6, 6, + 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, + 7, 7, 7, 7, 7, 7, 7, 7, + 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, + 7, 7, 7, 7, 7, 7, 7, 7, + 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, + 8, 8, 8, 8, 8, 8, 8, 8, + 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, + 8, 8, 8, 8, 8, 8, 8, 8, + 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, + 8, 8, 8, 8, 8, 8, 8, 8, + 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, + 8, 8, 8, 8, 8, 8, 8, 8, +}; diff --git a/lib/crc32.c b/lib/crc32.c index 4b35d2b4437..b0d278fb1d9 100644 --- a/lib/crc32.c +++ b/lib/crc32.c @@ -1,4 +1,8 @@ /* + * Aug 8, 2011 Bob Pearson with help from Joakim Tjernlund and George Spelvin + * cleaned up code to current version of sparse and added the slicing-by-8 + * algorithm to the closely similar existing slicing-by-4 algorithm. + * * 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 @@ -20,52 +24,58 @@ * Version 2. See the file COPYING for more details. */ +/* see: Documentation/crc32.txt for a description of algorithms */ + #include <linux/crc32.h> -#include <linux/kernel.h> #include <linux/module.h> -#include <linux/compiler.h> #include <linux/types.h> -#include <linux/init.h> -#include <linux/atomic.h> #include "crc32defs.h" -#if CRC_LE_BITS == 8 -# define tole(x) __constant_cpu_to_le32(x) + +#if CRC_LE_BITS > 8 +# define tole(x) ((__force u32) __constant_cpu_to_le32(x)) #else # define tole(x) (x) #endif -#if CRC_BE_BITS == 8 -# define tobe(x) __constant_cpu_to_be32(x) +#if CRC_BE_BITS > 8 +# define tobe(x) ((__force u32) __constant_cpu_to_be32(x)) #else # define tobe(x) (x) #endif + #include "crc32table.h" MODULE_AUTHOR("Matt Domsch <Matt_Domsch@dell.com>"); -MODULE_DESCRIPTION("Ethernet CRC32 calculations"); +MODULE_DESCRIPTION("Various CRC32 calculations"); MODULE_LICENSE("GPL"); -#if CRC_LE_BITS == 8 || CRC_BE_BITS == 8 +#if CRC_LE_BITS > 8 || CRC_BE_BITS > 8 +/* implements slicing-by-4 or slicing-by-8 algorithm */ static inline u32 crc32_body(u32 crc, unsigned char const *buf, size_t len, const u32 (*tab)[256]) { # ifdef __LITTLE_ENDIAN # define DO_CRC(x) crc = t0[(crc ^ (x)) & 255] ^ (crc >> 8) -# define DO_CRC4 crc = t3[(crc) & 255] ^ \ - t2[(crc >> 8) & 255] ^ \ - t1[(crc >> 16) & 255] ^ \ - t0[(crc >> 24) & 255] +# define DO_CRC4 (t3[(q) & 255] ^ t2[(q >> 8) & 255] ^ \ + t1[(q >> 16) & 255] ^ t0[(q >> 24) & 255]) +# define DO_CRC8 (t7[(q) & 255] ^ t6[(q >> 8) & 255] ^ \ + t5[(q >> 16) & 255] ^ t4[(q >> 24) & 255]) # else # define DO_CRC(x) crc = t0[((crc >> 24) ^ (x)) & 255] ^ (crc << 8) -# define DO_CRC4 crc = t0[(crc) & 255] ^ \ - t1[(crc >> 8) & 255] ^ \ - t2[(crc >> 16) & 255] ^ \ - t3[(crc >> 24) & 255] +# define DO_CRC4 (t0[(q) & 255] ^ t1[(q >> 8) & 255] ^ \ + t2[(q >> 16) & 255] ^ t3[(q >> 24) & 255]) +# define DO_CRC8 (t4[(q) & 255] ^ t5[(q >> 8) & 255] ^ \ + t6[(q >> 16) & 255] ^ t7[(q >> 24) & 255]) # endif const u32 *b; size_t rem_len; +# ifdef CONFIG_X86 + size_t i; +# endif const u32 *t0=tab[0], *t1=tab[1], *t2=tab[2], *t3=tab[3]; + const u32 *t4 = tab[4], *t5 = tab[5], *t6 = tab[6], *t7 = tab[7]; + u32 q; /* Align it */ if (unlikely((long)buf & 3 && len)) { @@ -73,27 +83,51 @@ crc32_body(u32 crc, unsigned char const *buf, size_t len, const u32 (*tab)[256]) DO_CRC(*buf++); } while ((--len) && ((long)buf)&3); } + +# if CRC_LE_BITS == 32 rem_len = len & 3; - /* load data 32 bits wide, xor data 32 bits wide. */ len = len >> 2; +# else + rem_len = len & 7; + len = len >> 3; +# endif + b = (const u32 *)buf; +# ifdef CONFIG_X86 + --b; + for (i = 0; i < len; i++) { +# else for (--b; len; --len) { - crc ^= *++b; /* use pre increment for speed */ - DO_CRC4; +# endif + q = crc ^ *++b; /* use pre increment for speed */ +# if CRC_LE_BITS == 32 + crc = DO_CRC4; +# else + crc = DO_CRC8; + q = *++b; + crc ^= DO_CRC4; +# endif } len = rem_len; /* And the last few bytes */ if (len) { u8 *p = (u8 *)(b + 1) - 1; +# ifdef CONFIG_X86 + for (i = 0; i < len; i++) + DO_CRC(*++p); /* use pre increment for speed */ +# else do { DO_CRC(*++p); /* use pre increment for speed */ } while (--len); +# endif } return crc; #undef DO_CRC #undef DO_CRC4 +#undef DO_CRC8 } #endif + /** * crc32_le() - Calculate bitwise little-endian Ethernet AUTODIN II CRC32 * @crc: seed value for computation. ~0 for Ethernet, sometimes 0 for @@ -101,53 +135,66 @@ crc32_body(u32 crc, unsigned char const *buf, size_t len, const u32 (*tab)[256]) * @p: pointer to buffer over which CRC is run * @len: length of buffer @p */ -u32 __pure crc32_le(u32 crc, unsigned char const *p, size_t len); - -#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. - */ - -u32 __pure crc32_le(u32 crc, unsigned char const *p, size_t len) +static inline u32 __pure crc32_le_generic(u32 crc, unsigned char const *p, + size_t len, const u32 (*tab)[256], + u32 polynomial) { +#if CRC_LE_BITS == 1 int i; while (len--) { crc ^= *p++; for (i = 0; i < 8; i++) - crc = (crc >> 1) ^ ((crc & 1) ? CRCPOLY_LE : 0); + crc = (crc >> 1) ^ ((crc & 1) ? polynomial : 0); + } +# elif CRC_LE_BITS == 2 + while (len--) { + crc ^= *p++; + crc = (crc >> 2) ^ tab[0][crc & 3]; + crc = (crc >> 2) ^ tab[0][crc & 3]; + crc = (crc >> 2) ^ tab[0][crc & 3]; + crc = (crc >> 2) ^ tab[0][crc & 3]; } - return crc; -} -#else /* Table-based approach */ - -u32 __pure crc32_le(u32 crc, unsigned char const *p, size_t len) -{ -# if CRC_LE_BITS == 8 - const u32 (*tab)[] = crc32table_le; - - crc = __cpu_to_le32(crc); - crc = crc32_body(crc, p, len, tab); - return __le32_to_cpu(crc); # elif CRC_LE_BITS == 4 while (len--) { crc ^= *p++; - crc = (crc >> 4) ^ crc32table_le[crc & 15]; - crc = (crc >> 4) ^ crc32table_le[crc & 15]; + crc = (crc >> 4) ^ tab[0][crc & 15]; + crc = (crc >> 4) ^ tab[0][crc & 15]; } - return crc; -# elif CRC_LE_BITS == 2 +# elif CRC_LE_BITS == 8 + /* aka Sarwate algorithm */ 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]; + crc = (crc >> 8) ^ tab[0][crc & 255]; } +# else + crc = (__force u32) __cpu_to_le32(crc); + crc = crc32_body(crc, p, len, tab); + crc = __le32_to_cpu((__force __le32)crc); +#endif return crc; -# endif +} + +#if CRC_LE_BITS == 1 +u32 __pure crc32_le(u32 crc, unsigned char const *p, size_t len) +{ + return crc32_le_generic(crc, p, len, NULL, CRCPOLY_LE); +} +u32 __pure __crc32c_le(u32 crc, unsigned char const *p, size_t len) +{ + return crc32_le_generic(crc, p, len, NULL, CRC32C_POLY_LE); +} +#else +u32 __pure crc32_le(u32 crc, unsigned char const *p, size_t len) +{ + return crc32_le_generic(crc, p, len, crc32table_le, CRCPOLY_LE); +} +u32 __pure __crc32c_le(u32 crc, unsigned char const *p, size_t len) +{ + return crc32_le_generic(crc, p, len, crc32ctable_le, CRC32C_POLY_LE); } #endif +EXPORT_SYMBOL(crc32_le); +EXPORT_SYMBOL(__crc32c_le); /** * crc32_be() - Calculate bitwise big-endian Ethernet AUTODIN II CRC32 @@ -156,317 +203,913 @@ u32 __pure crc32_le(u32 crc, unsigned char const *p, size_t len) * @p: pointer to buffer over which CRC is run * @len: length of buffer @p */ -u32 __pure crc32_be(u32 crc, unsigned char const *p, size_t len); - -#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. - */ - -u32 __pure crc32_be(u32 crc, unsigned char const *p, size_t len) +static inline u32 __pure crc32_be_generic(u32 crc, unsigned char const *p, + size_t len, const u32 (*tab)[256], + u32 polynomial) { +#if CRC_BE_BITS == 1 int i; while (len--) { crc ^= *p++ << 24; for (i = 0; i < 8; i++) crc = - (crc << 1) ^ ((crc & 0x80000000) ? CRCPOLY_BE : + (crc << 1) ^ ((crc & 0x80000000) ? polynomial : 0); } - return crc; -} - -#else /* Table-based approach */ -u32 __pure crc32_be(u32 crc, unsigned char const *p, size_t len) -{ -# if CRC_BE_BITS == 8 - const u32 (*tab)[] = crc32table_be; - - crc = __cpu_to_be32(crc); - crc = crc32_body(crc, p, len, tab); - return __be32_to_cpu(crc); +# elif CRC_BE_BITS == 2 + while (len--) { + crc ^= *p++ << 24; + crc = (crc << 2) ^ tab[0][crc >> 30]; + crc = (crc << 2) ^ tab[0][crc >> 30]; + crc = (crc << 2) ^ tab[0][crc >> 30]; + crc = (crc << 2) ^ tab[0][crc >> 30]; + } # elif CRC_BE_BITS == 4 while (len--) { crc ^= *p++ << 24; - crc = (crc << 4) ^ crc32table_be[crc >> 28]; - crc = (crc << 4) ^ crc32table_be[crc >> 28]; + crc = (crc << 4) ^ tab[0][crc >> 28]; + crc = (crc << 4) ^ tab[0][crc >> 28]; } - return crc; -# elif CRC_BE_BITS == 2 +# elif CRC_BE_BITS == 8 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]; + crc = (crc << 8) ^ tab[0][crc >> 24]; } - return crc; +# else + crc = (__force u32) __cpu_to_be32(crc); + crc = crc32_body(crc, p, len, tab); + crc = __be32_to_cpu((__force __be32)crc); # endif + return crc; } -#endif -EXPORT_SYMBOL(crc32_le); +#if CRC_LE_BITS == 1 +u32 __pure crc32_be(u32 crc, unsigned char const *p, size_t len) +{ + return crc32_be_generic(crc, p, len, NULL, CRCPOLY_BE); +} +#else +u32 __pure crc32_be(u32 crc, unsigned char const *p, size_t len) +{ + return crc32_be_generic(crc, p, len, crc32table_be, CRCPOLY_BE); +} +#endif EXPORT_SYMBOL(crc32_be); -/* - * 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 multiple 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 +#ifdef CONFIG_CRC32_SELFTEST -#include <stdlib.h> -#include <stdio.h> +/* 4096 random bytes */ +static u8 __attribute__((__aligned__(8))) test_buf[] = +{ + 0x5b, 0x85, 0x21, 0xcb, 0x09, 0x68, 0x7d, 0x30, + 0xc7, 0x69, 0xd7, 0x30, 0x92, 0xde, 0x59, 0xe4, + 0xc9, 0x6e, 0x8b, 0xdb, 0x98, 0x6b, 0xaa, 0x60, + 0xa8, 0xb5, 0xbc, 0x6c, 0xa9, 0xb1, 0x5b, 0x2c, + 0xea, 0xb4, 0x92, 0x6a, 0x3f, 0x79, 0x91, 0xe4, + 0xe9, 0x70, 0x51, 0x8c, 0x7f, 0x95, 0x6f, 0x1a, + 0x56, 0xa1, 0x5c, 0x27, 0x03, 0x67, 0x9f, 0x3a, + 0xe2, 0x31, 0x11, 0x29, 0x6b, 0x98, 0xfc, 0xc4, + 0x53, 0x24, 0xc5, 0x8b, 0xce, 0x47, 0xb2, 0xb9, + 0x32, 0xcb, 0xc1, 0xd0, 0x03, 0x57, 0x4e, 0xd4, + 0xe9, 0x3c, 0xa1, 0x63, 0xcf, 0x12, 0x0e, 0xca, + 0xe1, 0x13, 0xd1, 0x93, 0xa6, 0x88, 0x5c, 0x61, + 0x5b, 0xbb, 0xf0, 0x19, 0x46, 0xb4, 0xcf, 0x9e, + 0xb6, 0x6b, 0x4c, 0x3a, 0xcf, 0x60, 0xf9, 0x7a, + 0x8d, 0x07, 0x63, 0xdb, 0x40, 0xe9, 0x0b, 0x6f, + 0xad, 0x97, 0xf1, 0xed, 0xd0, 0x1e, 0x26, 0xfd, + 0xbf, 0xb7, 0xc8, 0x04, 0x94, 0xf8, 0x8b, 0x8c, + 0xf1, 0xab, 0x7a, 0xd4, 0xdd, 0xf3, 0xe8, 0x88, + 0xc3, 0xed, 0x17, 0x8a, 0x9b, 0x40, 0x0d, 0x53, + 0x62, 0x12, 0x03, 0x5f, 0x1b, 0x35, 0x32, 0x1f, + 0xb4, 0x7b, 0x93, 0x78, 0x0d, 0xdb, 0xce, 0xa4, + 0xc0, 0x47, 0xd5, 0xbf, 0x68, 0xe8, 0x5d, 0x74, + 0x8f, 0x8e, 0x75, 0x1c, 0xb2, 0x4f, 0x9a, 0x60, + 0xd1, 0xbe, 0x10, 0xf4, 0x5c, 0xa1, 0x53, 0x09, + 0xa5, 0xe0, 0x09, 0x54, 0x85, 0x5c, 0xdc, 0x07, + 0xe7, 0x21, 0x69, 0x7b, 0x8a, 0xfd, 0x90, 0xf1, + 0x22, 0xd0, 0xb4, 0x36, 0x28, 0xe6, 0xb8, 0x0f, + 0x39, 0xde, 0xc8, 0xf3, 0x86, 0x60, 0x34, 0xd2, + 0x5e, 0xdf, 0xfd, 0xcf, 0x0f, 0xa9, 0x65, 0xf0, + 0xd5, 0x4d, 0x96, 0x40, 0xe3, 0xdf, 0x3f, 0x95, + 0x5a, 0x39, 0x19, 0x93, 0xf4, 0x75, 0xce, 0x22, + 0x00, 0x1c, 0x93, 0xe2, 0x03, 0x66, 0xf4, 0x93, + 0x73, 0x86, 0x81, 0x8e, 0x29, 0x44, 0x48, 0x86, + 0x61, 0x7c, 0x48, 0xa3, 0x43, 0xd2, 0x9c, 0x8d, + 0xd4, 0x95, 0xdd, 0xe1, 0x22, 0x89, 0x3a, 0x40, + 0x4c, 0x1b, 0x8a, 0x04, 0xa8, 0x09, 0x69, 0x8b, + 0xea, 0xc6, 0x55, 0x8e, 0x57, 0xe6, 0x64, 0x35, + 0xf0, 0xc7, 0x16, 0x9f, 0x5d, 0x5e, 0x86, 0x40, + 0x46, 0xbb, 0xe5, 0x45, 0x88, 0xfe, 0xc9, 0x63, + 0x15, 0xfb, 0xf5, 0xbd, 0x71, 0x61, 0xeb, 0x7b, + 0x78, 0x70, 0x07, 0x31, 0x03, 0x9f, 0xb2, 0xc8, + 0xa7, 0xab, 0x47, 0xfd, 0xdf, 0xa0, 0x78, 0x72, + 0xa4, 0x2a, 0xe4, 0xb6, 0xba, 0xc0, 0x1e, 0x86, + 0x71, 0xe6, 0x3d, 0x18, 0x37, 0x70, 0xe6, 0xff, + 0xe0, 0xbc, 0x0b, 0x22, 0xa0, 0x1f, 0xd3, 0xed, + 0xa2, 0x55, 0x39, 0xab, 0xa8, 0x13, 0x73, 0x7c, + 0x3f, 0xb2, 0xd6, 0x19, 0xac, 0xff, 0x99, 0xed, + 0xe8, 0xe6, 0xa6, 0x22, 0xe3, 0x9c, 0xf1, 0x30, + 0xdc, 0x01, 0x0a, 0x56, 0xfa, 0xe4, 0xc9, 0x99, + 0xdd, 0xa8, 0xd8, 0xda, 0x35, 0x51, 0x73, 0xb4, + 0x40, 0x86, 0x85, 0xdb, 0x5c, 0xd5, 0x85, 0x80, + 0x14, 0x9c, 0xfd, 0x98, 0xa9, 0x82, 0xc5, 0x37, + 0xff, 0x32, 0x5d, 0xd0, 0x0b, 0xfa, 0xdc, 0x04, + 0x5e, 0x09, 0xd2, 0xca, 0x17, 0x4b, 0x1a, 0x8e, + 0x15, 0xe1, 0xcc, 0x4e, 0x52, 0x88, 0x35, 0xbd, + 0x48, 0xfe, 0x15, 0xa0, 0x91, 0xfd, 0x7e, 0x6c, + 0x0e, 0x5d, 0x79, 0x1b, 0x81, 0x79, 0xd2, 0x09, + 0x34, 0x70, 0x3d, 0x81, 0xec, 0xf6, 0x24, 0xbb, + 0xfb, 0xf1, 0x7b, 0xdf, 0x54, 0xea, 0x80, 0x9b, + 0xc7, 0x99, 0x9e, 0xbd, 0x16, 0x78, 0x12, 0x53, + 0x5e, 0x01, 0xa7, 0x4e, 0xbd, 0x67, 0xe1, 0x9b, + 0x4c, 0x0e, 0x61, 0x45, 0x97, 0xd2, 0xf0, 0x0f, + 0xfe, 0x15, 0x08, 0xb7, 0x11, 0x4c, 0xe7, 0xff, + 0x81, 0x53, 0xff, 0x91, 0x25, 0x38, 0x7e, 0x40, + 0x94, 0xe5, 0xe0, 0xad, 0xe6, 0xd9, 0x79, 0xb6, + 0x92, 0xc9, 0xfc, 0xde, 0xc3, 0x1a, 0x23, 0xbb, + 0xdd, 0xc8, 0x51, 0x0c, 0x3a, 0x72, 0xfa, 0x73, + 0x6f, 0xb7, 0xee, 0x61, 0x39, 0x03, 0x01, 0x3f, + 0x7f, 0x94, 0x2e, 0x2e, 0xba, 0x3a, 0xbb, 0xb4, + 0xfa, 0x6a, 0x17, 0xfe, 0xea, 0xef, 0x5e, 0x66, + 0x97, 0x3f, 0x32, 0x3d, 0xd7, 0x3e, 0xb1, 0xf1, + 0x6c, 0x14, 0x4c, 0xfd, 0x37, 0xd3, 0x38, 0x80, + 0xfb, 0xde, 0xa6, 0x24, 0x1e, 0xc8, 0xca, 0x7f, + 0x3a, 0x93, 0xd8, 0x8b, 0x18, 0x13, 0xb2, 0xe5, + 0xe4, 0x93, 0x05, 0x53, 0x4f, 0x84, 0x66, 0xa7, + 0x58, 0x5c, 0x7b, 0x86, 0x52, 0x6d, 0x0d, 0xce, + 0xa4, 0x30, 0x7d, 0xb6, 0x18, 0x9f, 0xeb, 0xff, + 0x22, 0xbb, 0x72, 0x29, 0xb9, 0x44, 0x0b, 0x48, + 0x1e, 0x84, 0x71, 0x81, 0xe3, 0x6d, 0x73, 0x26, + 0x92, 0xb4, 0x4d, 0x2a, 0x29, 0xb8, 0x1f, 0x72, + 0xed, 0xd0, 0xe1, 0x64, 0x77, 0xea, 0x8e, 0x88, + 0x0f, 0xef, 0x3f, 0xb1, 0x3b, 0xad, 0xf9, 0xc9, + 0x8b, 0xd0, 0xac, 0xc6, 0xcc, 0xa9, 0x40, 0xcc, + 0x76, 0xf6, 0x3b, 0x53, 0xb5, 0x88, 0xcb, 0xc8, + 0x37, 0xf1, 0xa2, 0xba, 0x23, 0x15, 0x99, 0x09, + 0xcc, 0xe7, 0x7a, 0x3b, 0x37, 0xf7, 0x58, 0xc8, + 0x46, 0x8c, 0x2b, 0x2f, 0x4e, 0x0e, 0xa6, 0x5c, + 0xea, 0x85, 0x55, 0xba, 0x02, 0x0e, 0x0e, 0x48, + 0xbc, 0xe1, 0xb1, 0x01, 0x35, 0x79, 0x13, 0x3d, |