mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-22 19:03:28 +07:00
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> |
||
|---|---|---|
| .. | ||
| numachip | ||
| uv | ||
| visws | ||
| xen | ||
| a.out-core.h | ||
| a.out.h | ||
| acpi.h | ||
| aes.h | ||
| agp.h | ||
| alternative-asm.h | ||
| alternative.h | ||
| amd_nb.h | ||
| apb_timer.h | ||
| apic_flat_64.h | ||
| apic.h | ||
| apicdef.h | ||
| apm.h | ||
| arch_hweight.h | ||
| archrandom.h | ||
| asm-offsets.h | ||
| asm.h | ||
| atomic64_32.h | ||
| atomic64_64.h | ||
| atomic.h | ||
| auxvec.h | ||
| barrier.h | ||
| bios_ebda.h | ||
| bitops.h | ||
| bitsperlong.h | ||
| boot.h | ||
| bootparam.h | ||
| bug.h | ||
| bugs.h | ||
| byteorder.h | ||
| cache.h | ||
| cacheflush.h | ||
| calgary.h | ||
| calling.h | ||
| ce4100.h | ||
| checksum_32.h | ||
| checksum_64.h | ||
| checksum.h | ||
| clocksource.h | ||
| cmpxchg_32.h | ||
| cmpxchg_64.h | ||
| cmpxchg.h | ||
| compat.h | ||
| cpu_device_id.h | ||
| cpu.h | ||
| cpufeature.h | ||
| cpumask.h | ||
| cputime.h | ||
| current.h | ||
| debugreg.h | ||
| delay.h | ||
| desc_defs.h | ||
| desc.h | ||
| device.h | ||
| div64.h | ||
| dma-contiguous.h | ||
| dma-mapping.h | ||
| dma.h | ||
| dmi.h | ||
| dwarf2.h | ||
| e820.h | ||
| edac.h | ||
| efi.h | ||
| elf.h | ||
| emergency-restart.h | ||
| entry_arch.h | ||
| errno.h | ||
| exec.h | ||
| fb.h | ||
| fcntl.h | ||
| fixmap.h | ||
| floppy.h | ||
| fpu-internal.h | ||
| frame.h | ||
| ftrace.h | ||
| futex.h | ||
| gart.h | ||
| genapic.h | ||
| geode.h | ||
| gpio.h | ||
| hardirq.h | ||
| highmem.h | ||
| hpet.h | ||
| hugetlb.h | ||
| hw_breakpoint.h | ||
| hw_irq.h | ||
| hypertransport.h | ||
| hyperv.h | ||
| hypervisor.h | ||
| i387.h | ||
| i8259.h | ||
| ia32_unistd.h | ||
| ia32.h | ||
| idle.h | ||
| inat_types.h | ||
| inat.h | ||
| init.h | ||
| insn.h | ||
| inst.h | ||
| intel_scu_ipc.h | ||
| io_apic.h | ||
| io.h | ||
| ioctl.h | ||
| ioctls.h | ||
| iomap.h | ||
| iommu_table.h | ||
| iommu.h | ||
| ipcbuf.h | ||
| ipi.h | ||
| irq_regs.h | ||
| irq_remapping.h | ||
| irq_vectors.h | ||
| irq.h | ||
| irqflags.h | ||
| ist.h | ||
| jump_label.h | ||
| kbdleds.h | ||
| Kbuild | ||
| kdebug.h | ||
| kexec.h | ||
| kgdb.h | ||
| kmap_types.h | ||
| kmemcheck.h | ||
| kprobes.h | ||
| kvm_emulate.h | ||
| kvm_host.h | ||
| kvm_para.h | ||
| kvm.h | ||
| ldt.h | ||
| lguest_hcall.h | ||
| lguest.h | ||
| linkage.h | ||
| local64.h | ||
| local.h | ||
| mach_timer.h | ||
| mach_traps.h | ||
| math_emu.h | ||
| mc146818rtc.h | ||
| mce.h | ||
| microcode.h | ||
| mman.h | ||
| mmconfig.h | ||
| mmu_context.h | ||
| mmu.h | ||
| mmx.h | ||
| mmzone_32.h | ||
| mmzone_64.h | ||
| mmzone.h | ||
| module.h | ||
| mpspec_def.h | ||
| mpspec.h | ||
| mrst-vrtc.h | ||
| mrst.h | ||
| msgbuf.h | ||
| mshyperv.h | ||
| msidef.h | ||
| msr-index.h | ||
| msr.h | ||
| mtrr.h | ||
| mutex_32.h | ||
| mutex_64.h | ||
| mutex.h | ||
| mwait.h | ||
| nmi.h | ||
| nops.h | ||
| numa_32.h | ||
| numa_64.h | ||
| numa.h | ||
| numaq.h | ||
| olpc_ofw.h | ||
| olpc.h | ||
| page_32_types.h | ||
| page_32.h | ||
| page_64_types.h | ||
| page_64.h | ||
| page_types.h | ||
| page.h | ||
| param.h | ||
| paravirt_types.h | ||
| paravirt.h | ||
| parport.h | ||
| pat.h | ||
| pci_64.h | ||
| pci_x86.h | ||
| pci-direct.h | ||
| pci-functions.h | ||
| pci.h | ||
| percpu.h | ||
| perf_event_p4.h | ||
| perf_event.h | ||
| pgalloc.h | ||
| pgtable_32_types.h | ||
| pgtable_32.h | ||
| pgtable_64_types.h | ||
| pgtable_64.h | ||
| pgtable_types.h | ||
| pgtable-2level_types.h | ||
| pgtable-2level.h | ||
| pgtable-3level_types.h | ||
| pgtable-3level.h | ||
| pgtable.h | ||
| poll.h | ||
| posix_types_32.h | ||
| posix_types_64.h | ||
| posix_types_x32.h | ||
| posix_types.h | ||
| prctl.h | ||
| probe_roms.h | ||
| processor-cyrix.h | ||
| processor-flags.h | ||
| processor.h | ||
| prom.h | ||
| proto.h | ||
| ptrace-abi.h | ||
| ptrace.h | ||
| pvclock-abi.h | ||
| pvclock.h | ||
| reboot_fixups.h | ||
| reboot.h | ||
| required-features.h | ||
| resource.h | ||
| resume-trace.h | ||
| rio.h | ||
| rtc.h | ||
| rwlock.h | ||
| rwsem.h | ||
| scatterlist.h | ||
| seccomp_32.h | ||
| seccomp_64.h | ||
| seccomp.h | ||
| sections.h | ||
| segment.h | ||
| sembuf.h | ||
| serial.h | ||
| serpent.h | ||
| setup_arch.h | ||
| setup.h | ||
| shmbuf.h | ||
| shmparam.h | ||
| sigcontext32.h | ||
| sigcontext.h | ||
| sigframe.h | ||
| sighandling.h | ||
| siginfo.h | ||
| signal.h | ||
| smp.h | ||
| smpboot_hooks.h | ||
| socket.h | ||
| sockios.h | ||
| sparsemem.h | ||
| special_insns.h | ||
| spinlock_types.h | ||
| spinlock.h | ||
| stackprotector.h | ||
| stacktrace.h | ||
| stat.h | ||
| statfs.h | ||
| string_32.h | ||
| string_64.h | ||
| string.h | ||
| suspend_32.h | ||
| suspend_64.h | ||
| suspend.h | ||
| svm.h | ||
| swab.h | ||
| swiotlb.h | ||
| switch_to.h | ||
| sync_bitops.h | ||
| sys_ia32.h | ||
| syscall.h | ||
| syscalls.h | ||
| tce.h | ||
| termbits.h | ||
| termios.h | ||
| thread_info.h | ||
| time.h | ||
| timer.h | ||
| timex.h | ||
| tlb.h | ||
| tlbflush.h | ||
| topology.h | ||
| trampoline.h | ||
| traps.h | ||
| tsc.h | ||
| types.h | ||
| uaccess_32.h | ||
| uaccess_64.h | ||
| uaccess.h | ||
| ucontext.h | ||
| unaligned.h | ||
| unistd.h | ||
| uprobes.h | ||
| user32.h | ||
| user_32.h | ||
| user_64.h | ||
| user.h | ||
| vdso.h | ||
| vga.h | ||
| vgtod.h | ||
| virtext.h | ||
| vm86.h | ||
| vmx.h | ||
| vsyscall.h | ||
| vvar.h | ||
| word-at-a-time.h | ||
| x2apic.h | ||
| x86_init.h | ||
| xcr.h | ||
| xor_32.h | ||
| xor_64.h | ||
| xor_avx.h | ||
| xor.h | ||
| xsave.h | ||