From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from pegase1.c-s.fr (pegase1.c-s.fr [93.17.236.30]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by lists.ozlabs.org (Postfix) with ESMTPS id 3zwfvZ6wXzzF1Z9 for ; Wed, 7 Mar 2018 01:55:06 +1100 (AEDT) Subject: Re: [PATCH 08/10] powerpc/mm/slice: Use const pointers to cached slice masks where possible To: Nicholas Piggin , linuxppc-dev@lists.ozlabs.org Cc: "Aneesh Kumar K . V" References: <20180306132507.10649-1-npiggin@gmail.com> <20180306132507.10649-9-npiggin@gmail.com> From: Christophe LEROY Message-ID: <248c0062-7710-bb96-6677-3c6d7bdc13ee@c-s.fr> Date: Tue, 6 Mar 2018 15:55:04 +0100 MIME-Version: 1.0 In-Reply-To: <20180306132507.10649-9-npiggin@gmail.com> Content-Type: text/plain; charset=utf-8; format=flowed List-Id: Linux on PowerPC Developers Mail List List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Le 06/03/2018 à 14:25, Nicholas Piggin a écrit : > The slice_mask cache was a basic conversion which copied the slice > mask into caller's structures, because that's how the original code > worked. In most cases the pointer can be used directly instead, saving > a copy and an on-stack structure. > > On POWER8, this increases vfork+exec+exit performance by 0.3% > and reduces time to mmap+munmap a 64kB page by 2%. > > Signed-off-by: Nicholas Piggin > --- > arch/powerpc/mm/slice.c | 77 +++++++++++++++++++++---------------------------- > 1 file changed, 33 insertions(+), 44 deletions(-) > > diff --git a/arch/powerpc/mm/slice.c b/arch/powerpc/mm/slice.c > index 46daa1d1794f..086c31b8b982 100644 > --- a/arch/powerpc/mm/slice.c > +++ b/arch/powerpc/mm/slice.c > @@ -472,10 +472,10 @@ unsigned long slice_get_unmapped_area(unsigned long addr, unsigned long len, > unsigned long flags, unsigned int psize, > int topdown) > { > - struct slice_mask mask; > struct slice_mask good_mask; > struct slice_mask potential_mask; > - struct slice_mask compat_mask; > + const struct slice_mask *maskp; > + const struct slice_mask *compat_maskp = NULL; > int fixed = (flags & MAP_FIXED); > int pshift = max_t(int, mmu_psize_defs[psize].shift, PAGE_SHIFT); > unsigned long page_size = 1UL << pshift; > @@ -509,22 +509,6 @@ unsigned long slice_get_unmapped_area(unsigned long addr, unsigned long len, > on_each_cpu(slice_flush_segments, mm, 1); > } > > - /* > - * init different masks > - */ > - mask.low_slices = 0; > - > - /* silence stupid warning */; > - potential_mask.low_slices = 0; > - > - compat_mask.low_slices = 0; > - > - if (SLICE_NUM_HIGH) { > - bitmap_zero(mask.high_slices, SLICE_NUM_HIGH); > - bitmap_zero(potential_mask.high_slices, SLICE_NUM_HIGH); > - bitmap_zero(compat_mask.high_slices, SLICE_NUM_HIGH); > - } > - > /* Sanity checks */ > BUG_ON(mm->task_size == 0); > BUG_ON(mm->context.slb_addr_limit == 0); > @@ -547,8 +531,7 @@ unsigned long slice_get_unmapped_area(unsigned long addr, unsigned long len, > /* First make up a "good" mask of slices that have the right size > * already > */ > - good_mask = *slice_mask_for_size(mm, psize); > - slice_print_mask(" good_mask", &good_mask); > + maskp = slice_mask_for_size(mm, psize); > > /* > * Here "good" means slices that are already the right page size, > @@ -572,11 +555,19 @@ unsigned long slice_get_unmapped_area(unsigned long addr, unsigned long len, > #ifdef CONFIG_PPC_64K_PAGES > /* If we support combo pages, we can allow 64k pages in 4k slices */ > if (psize == MMU_PAGE_64K) { > - compat_mask = *slice_mask_for_size(mm, MMU_PAGE_4K); > + compat_maskp = slice_mask_for_size(mm, MMU_PAGE_4K); > if (fixed) > - slice_or_mask(&good_mask, &good_mask, &compat_mask); > - } > + slice_or_mask(&good_mask, maskp, compat_maskp); > + else > + slice_copy_mask(&good_mask, maskp); > + } else > #endif > + { > + slice_copy_mask(&good_mask, maskp); > + } You could get something nicer by removing that #ifdef and doing instead: if (IS_ENABLED(CONFIG_PPC_64K_PAGES) && psize == MMU_PAGE_64K) { ... } else { slice_copy_mask(&good_mask, maskp); } > + slice_print_mask(" good_mask", &good_mask); > + if (compat_maskp) > + slice_print_mask(" compat_mask", compat_maskp); > > /* First check hint if it's valid or if we have MAP_FIXED */ > if (addr || fixed) { > @@ -643,7 +634,7 @@ unsigned long slice_get_unmapped_area(unsigned long addr, unsigned long len, > #ifdef CONFIG_PPC_64K_PAGES > if (addr == -ENOMEM && psize == MMU_PAGE_64K) { > /* retry the search with 4k-page slices included */ > - slice_or_mask(&potential_mask, &potential_mask, &compat_mask); > + slice_or_mask(&potential_mask, &potential_mask, compat_maskp); > addr = slice_find_area(mm, len, &potential_mask, > psize, topdown, high_limit); > } > @@ -652,17 +643,18 @@ unsigned long slice_get_unmapped_area(unsigned long addr, unsigned long len, > if (addr == -ENOMEM) > return -ENOMEM; > > - slice_range_to_mask(addr, len, &mask); > + slice_range_to_mask(addr, len, &potential_mask); > slice_dbg(" found potential area at 0x%lx\n", addr); > - slice_print_mask(" mask", &mask); > + slice_print_mask(" mask", &potential_mask); > > convert: > - slice_andnot_mask(&mask, &mask, &good_mask); > - slice_andnot_mask(&mask, &mask, &compat_mask); > - if (mask.low_slices || > - (SLICE_NUM_HIGH && > - !bitmap_empty(mask.high_slices, SLICE_NUM_HIGH))) { > - slice_convert(mm, &mask, psize); > + slice_andnot_mask(&potential_mask, &potential_mask, &good_mask); > + if (compat_maskp && !fixed) > + slice_andnot_mask(&potential_mask, &potential_mask, compat_maskp); > + if (potential_mask.low_slices || > + (SLICE_NUM_HIGH && > + !bitmap_empty(potential_mask.high_slices, SLICE_NUM_HIGH))) { > + slice_convert(mm, &potential_mask, psize); > if (psize > MMU_PAGE_BASE) > on_each_cpu(slice_flush_segments, mm, 1); > } > @@ -786,28 +778,25 @@ void slice_set_range_psize(struct mm_struct *mm, unsigned long start, > int is_hugepage_only_range(struct mm_struct *mm, unsigned long addr, > unsigned long len) > { > - struct slice_mask available; > + const struct slice_mask *maskp; > unsigned int psize = mm->context.user_psize; > > if (radix_enabled()) > return 0; > > - available = *slice_mask_for_size(mm, psize); > + maskp = slice_mask_for_size(mm, psize); > #ifdef CONFIG_PPC_64K_PAGES > /* We need to account for 4k slices too */ > if (psize == MMU_PAGE_64K) { > - struct slice_mask compat_mask; > - compat_mask = *slice_mask_for_size(mm, MMU_PAGE_4K); > - slice_or_mask(&available, &available, &compat_mask); > + const struct slice_mask *compat_maskp; > + struct slice_mask available; > + > + compat_maskp = slice_mask_for_size(mm, MMU_PAGE_4K); > + slice_or_mask(&available, maskp, compat_maskp); > + return !slice_check_range_fits(mm, &available, addr, len); > } > #endif > > -#if 0 /* too verbose */ > - slice_dbg("is_hugepage_only_range(mm=%p, addr=%lx, len=%lx)\n", > - mm, addr, len); > - slice_print_mask(" mask", &mask); > - slice_print_mask(" available", &available); > -#endif That's cleanup, should be in a previous patch. Christophe > - return !slice_check_range_fits(mm, &available, addr, len); > + return !slice_check_range_fits(mm, maskp, addr, len); > } > #endif >