forked from luck/tmp_suning_uos_patched
36126f8f2e
This changes the interfaces in <asm/word-at-a-time.h> to be a bit more complicated, but a lot more generic. In particular, it allows us to really do the operations efficiently on both little-endian and big-endian machines, pretty much regardless of machine details. For example, if you can rely on a fast population count instruction on your architecture, this will allow you to make your optimized <asm/word-at-a-time.h> file with that. NOTE! The "generic" version in include/asm-generic/word-at-a-time.h is not truly generic, it actually only works on big-endian. Why? Because on little-endian the generic algorithms are wasteful, since you can inevitably do better. The x86 implementation is an example of that. (The only truly non-generic part of the asm-generic implementation is the "find_zero()" function, and you could make a little-endian version of it. And if the Kbuild infrastructure allowed us to pick a particular header file, that would be lovely) The <asm/word-at-a-time.h> functions are as follows: - WORD_AT_A_TIME_CONSTANTS: specific constants that the algorithm uses. - has_zero(): take a word, and determine if it has a zero byte in it. It gets the word, the pointer to the constant pool, and a pointer to an intermediate "data" field it can set. This is the "quick-and-dirty" zero tester: it's what is run inside the hot loops. - "prep_zero_mask()": take the word, the data that has_zero() produced, and the constant pool, and generate an *exact* mask of which byte had the first zero. This is run directly *outside* the loop, and allows the "has_zero()" function to answer the "is there a zero byte" question without necessarily getting exactly *which* byte is the first one to contain a zero. If you do multiple byte lookups concurrently (eg "hash_name()", which looks for both NUL and '/' bytes), after you've done the prep_zero_mask() phase, the result of those can be or'ed together to get the "either or" case. - The result from "prep_zero_mask()" can then be fed into "find_zero()" (to find the byte offset of the first byte that was zero) or into "zero_bytemask()" (to find the bytemask of the bytes preceding the zero byte). The existence of zero_bytemask() is optional, and is not necessary for the normal string routines. But dentry name hashing needs it, so if you enable DENTRY_WORD_AT_A_TIME you need to expose it. This changes the generic strncpy_from_user() function and the dentry hashing functions to use these modified word-at-a-time interfaces. This gets us back to the optimized state of the x86 strncpy that we lost in the previous commit when moving over to the generic version. Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> |
||
|---|---|---|
| .. | ||
| lzo | ||
| mpi | ||
| raid6 | ||
| reed_solomon | ||
| xz | ||
| zlib_deflate | ||
| zlib_inflate | ||
| .gitignore | ||
| argv_split.c | ||
| atomic64_test.c | ||
| atomic64.c | ||
| audit.c | ||
| average.c | ||
| bcd.c | ||
| bch.c | ||
| bitmap.c | ||
| bitrev.c | ||
| bsearch.c | ||
| btree.c | ||
| bug.c | ||
| bust_spinlocks.c | ||
| check_signature.c | ||
| checksum.c | ||
| clz_tab.c | ||
| cmdline.c | ||
| cordic.c | ||
| cpu_rmap.c | ||
| cpu-notifier-error-inject.c | ||
| cpumask.c | ||
| crc-ccitt.c | ||
| crc-itu-t.c | ||
| crc-t10dif.c | ||
| crc7.c | ||
| crc8.c | ||
| crc16.c | ||
| crc32.c | ||
| crc32defs.h | ||
| ctype.c | ||
| debug_locks.c | ||
| debugobjects.c | ||
| dec_and_lock.c | ||
| decompress_bunzip2.c | ||
| decompress_inflate.c | ||
| decompress_unlzma.c | ||
| decompress_unlzo.c | ||
| decompress_unxz.c | ||
| decompress.c | ||
| devres.c | ||
| digsig.c | ||
| div64.c | ||
| dma-debug.c | ||
| dump_stack.c | ||
| dynamic_debug.c | ||
| dynamic_queue_limits.c | ||
| extable.c | ||
| fault-inject.c | ||
| find_last_bit.c | ||
| find_next_bit.c | ||
| flex_array.c | ||
| gcd.c | ||
| gen_crc32table.c | ||
| genalloc.c | ||
| halfmd4.c | ||
| hexdump.c | ||
| hweight.c | ||
| idr.c | ||
| inflate.c | ||
| int_sqrt.c | ||
| iomap_copy.c | ||
| iomap.c | ||
| iommu-helper.c | ||
| ioremap.c | ||
| irq_regs.c | ||
| is_single_threaded.c | ||
| jedec_ddr_data.c | ||
| kasprintf.c | ||
| Kconfig | ||
| Kconfig.debug | ||
| Kconfig.kgdb | ||
| Kconfig.kmemcheck | ||
| klist.c | ||
| kobject_uevent.c | ||
| kobject.c | ||
| kstrtox.c | ||
| kstrtox.h | ||
| lcm.c | ||
| libcrc32c.c | ||
| list_debug.c | ||
| list_sort.c | ||
| llist.c | ||
| locking-selftest-hardirq.h | ||
| locking-selftest-mutex.h | ||
| locking-selftest-rlock-hardirq.h | ||
| locking-selftest-rlock-softirq.h | ||
| locking-selftest-rlock.h | ||
| locking-selftest-rsem.h | ||
| locking-selftest-softirq.h | ||
| locking-selftest-spin-hardirq.h | ||
| locking-selftest-spin-softirq.h | ||
| locking-selftest-spin.h | ||
| locking-selftest-wlock-hardirq.h | ||
| locking-selftest-wlock-softirq.h | ||
| locking-selftest-wlock.h | ||
| locking-selftest-wsem.h | ||
| locking-selftest.c | ||
| lru_cache.c | ||
| Makefile | ||
| md5.c | ||
| nlattr.c | ||
| parser.c | ||
| pci_iomap.c | ||
| percpu_counter.c | ||
| plist.c | ||
| prio_heap.c | ||
| prio_tree.c | ||
| proportions.c | ||
| radix-tree.c | ||
| random32.c | ||
| ratelimit.c | ||
| rational.c | ||
| rbtree.c | ||
| reciprocal_div.c | ||
| rwsem-spinlock.c | ||
| rwsem.c | ||
| scatterlist.c | ||
| sha1.c | ||
| show_mem.c | ||
| smp_processor_id.c | ||
| sort.c | ||
| spinlock_debug.c | ||
| string_helpers.c | ||
| string.c | ||
| strncpy_from_user.c | ||
| swiotlb.c | ||
| syscall.c | ||
| test-kstrtox.c | ||
| textsearch.c | ||
| timerqueue.c | ||
| ts_bm.c | ||
| ts_fsm.c | ||
| ts_kmp.c | ||
| uuid.c | ||
| vsprintf.c | ||