297565aa22
Modern compilers are perfectly capable of extracting parallelism from the XOR routines, provided that the prototypes reflect the nature of the input accurately, in particular, the fact that the input vectors are expected not to overlap. This is not documented explicitly, but is implied by the interchangeability of the various C routines, some of which use temporary variables while others don't: this means that these routines only behave identically for non-overlapping inputs. So let's decorate these input vectors with the __restrict modifier, which informs the compiler that there is no overlap. While at it, make the input-only vectors pointer-to-const as well. Tested-by: Nathan Chancellor <nathan@kernel.org> Signed-off-by: Ard Biesheuvel <ardb@kernel.org> Reviewed-by: Nick Desaulniers <ndesaulniers@google.com> Link: https://github.com/ClangBuiltLinux/linux/issues/563 Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au> |
||
|---|---|---|
| .. | ||
| bitops | ||
| vdso | ||
| asm-offsets.h | ||
| asm-prototypes.h | ||
| atomic64.h | ||
| atomic.h | ||
| audit_change_attr.h | ||
| audit_dir_write.h | ||
| audit_read.h | ||
| audit_signal.h | ||
| audit_write.h | ||
| barrier.h | ||
| bitops.h | ||
| bitsperlong.h | ||
| bug.h | ||
| bugs.h | ||
| cache.h | ||
| cacheflush.h | ||
| checksum.h | ||
| cmpxchg-local.h | ||
| cmpxchg.h | ||
| compat.h | ||
| current.h | ||
| delay.h | ||
| device.h | ||
| div64.h | ||
| dma-mapping.h | ||
| dma.h | ||
| early_ioremap.h | ||
| emergency-restart.h | ||
| error-injection.h | ||
| exec.h | ||
| export.h | ||
| extable.h | ||
| fb.h | ||
| fixmap.h | ||
| flat.h | ||
| ftrace.h | ||
| futex.h | ||
| getorder.h | ||
| gpio.h | ||
| hardirq.h | ||
| hugetlb.h | ||
| hw_irq.h | ||
| hyperv-tlfs.h | ||
| ide_iops.h | ||
| int-ll64.h | ||
| io.h | ||
| ioctl.h | ||
| iomap.h | ||
| irq_regs.h | ||
| irq_work.h | ||
| irq.h | ||
| irqflags.h | ||
| Kbuild | ||
| kdebug.h | ||
| kmap_size.h | ||
| kprobes.h | ||
| kvm_para.h | ||
| kvm_types.h | ||
| linkage.h | ||
| local64.h | ||
| local.h | ||
| logic_io.h | ||
| mcs_spinlock.h | ||
| memory_model.h | ||
| mm_hooks.h | ||
| mmiowb_types.h | ||
| mmiowb.h | ||
| mmu_context.h | ||
| mmu.h | ||
| module.h | ||
| module.lds.h | ||
| mshyperv.h | ||
| msi.h | ||
| nommu_context.h | ||
| numa.h | ||
| page.h | ||
| param.h | ||
| parport.h | ||
| pci_iomap.h | ||
| pci.h | ||
| percpu.h | ||
| pgalloc.h | ||
| pgtable_uffd.h | ||
| pgtable-nop4d.h | ||
| pgtable-nopmd.h | ||
| pgtable-nopud.h | ||
| preempt.h | ||
| qrwlock_types.h | ||
| qrwlock.h | ||
| qspinlock_types.h | ||
| qspinlock.h | ||
| resource.h | ||
| rwonce.h | ||
| seccomp.h | ||
| sections.h | ||
| serial.h | ||
| set_memory.h | ||
| shmparam.h | ||
| signal.h | ||
| simd.h | ||
| softirq_stack.h | ||
| spinlock.h | ||
| statfs.h | ||
| string.h | ||
| switch_to.h | ||
| syscall.h | ||
| syscalls.h | ||
| termios-base.h | ||
| termios.h | ||
| timex.h | ||
| tlb.h | ||
| tlbflush.h | ||
| topology.h | ||
| trace_clock.h | ||
| uaccess.h | ||
| unaligned.h | ||
| user.h | ||
| vermagic.h | ||
| vga.h | ||
| vmlinux.lds.h | ||
| vtime.h | ||
| word-at-a-time.h | ||
| xor.h | ||