From mboxrd@z Thu Jan 1 00:00:00 1970 Return-path: Received: from cantor2.suse.de ([195.135.220.15] helo=mx2.suse.de) by bombadil.infradead.org with esmtps (Exim 4.80.1 #2 (Red Hat Linux)) id 1XK0Yh-0007Bk-S5 for kexec@lists.infradead.org; Wed, 20 Aug 2014 07:43:53 +0000 Date: Wed, 20 Aug 2014 09:43:26 +0200 From: Petr Tesarik Subject: Re: [PATCH v4] makedumpfile: Exclude unnecessary hugepages. Message-ID: <20140820094326.1d0f7e80@hananiah.suse.cz> In-Reply-To: <0910DD04CBD6DE4193FCF86B9C00BE9724E000@BPXM01GP.gisp.nec.co.jp> References: <0910DD04CBD6DE4193FCF86B9C00BE9724E000@BPXM01GP.gisp.nec.co.jp> Mime-Version: 1.0 List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit Sender: "kexec" Errors-To: kexec-bounces+dwmw2=infradead.org@lists.infradead.org To: Atsushi Kumagai , "kexec@lists.infradead.org" On Wed, 20 Aug 2014 07:27:30 +0000 Atsushi Kumagai wrote: > There are 2 types of hugepages in the kernel, the both should be > excluded as user pages. > > 1. Transparent huge pages (THP) > All the pages are anonymous pages (at least for now), so we should > just get how many pages are in the corresponding hugepage. > It can be gotten from the page->lru.prev of the second page in the > hugepage. > > 2. Hugetlbfs pages > The pages aren't anonymous pages but kind of user pages, we should > exclude also these pages in any way. > Luckily, it's possible to detect these pages by looking the > page->lru.next of the second page in the hugepage. This idea came > from the kernel's PageHuge(). > The number of pages can be gotten in the same way as THP. > > Changelog: > v4: > - Cleaned up according to Petr's and Baoquan's comments. > v3: > - Cleaned up according to Petr's comments. > - Fix misdetection of hugetlb pages. > v2: > - Rebased to "Generic multi-page exclusion". > > Signed-off-by: Atsushi Kumagai Hello Kumagai-san, this version is perfect from my POV. Thank you for accepting all my suggestions! Petr Tesarik > --- > makedumpfile.c | 86 ++++++++++++++++++++++++++++++++++++++++++++++++---------- > makedumpfile.h | 7 +++++ > 2 files changed, 78 insertions(+), 15 deletions(-) > > diff --git a/makedumpfile.c b/makedumpfile.c > index 11cd473..b4b6eca 100644 > --- a/makedumpfile.c > +++ b/makedumpfile.c > @@ -1180,6 +1180,7 @@ get_symbol_info(void) > SYMBOL_INIT(vmemmap_list, "vmemmap_list"); > SYMBOL_INIT(mmu_psize_defs, "mmu_psize_defs"); > SYMBOL_INIT(mmu_vmemmap_psize, "mmu_vmemmap_psize"); > + SYMBOL_INIT(free_huge_page, "free_huge_page"); > > SYMBOL_INIT(cpu_pgd, "cpu_pgd"); > SYMBOL_INIT(demote_segment_4k, "demote_segment_4k"); > @@ -1296,6 +1297,15 @@ get_structure_info(void) > ENUM_NUMBER_INIT(PG_slab, "PG_slab"); > ENUM_NUMBER_INIT(PG_hwpoison, "PG_hwpoison"); > > + ENUM_NUMBER_INIT(PG_head_mask, "PG_head_mask"); > + if (NUMBER(PG_head_mask) == NOT_FOUND_NUMBER) { > + ENUM_NUMBER_INIT(PG_head, "PG_head"); > + if (NUMBER(PG_head) == NOT_FOUND_NUMBER) > + ENUM_NUMBER_INIT(PG_head, "PG_compound"); > + if (NUMBER(PG_head) != NOT_FOUND_NUMBER) > + NUMBER(PG_head_mask) = 1UL << NUMBER(PG_head); > + } > + > ENUM_TYPE_SIZE_INIT(pageflags, "pageflags"); > > TYPEDEF_SIZE_INIT(nodemask_t, "nodemask_t"); > @@ -1530,6 +1540,9 @@ get_value_for_old_linux(void) > NUMBER(PG_swapcache) = PG_swapcache_ORIGINAL; > if (NUMBER(PG_slab) == NOT_FOUND_NUMBER) > NUMBER(PG_slab) = PG_slab_ORIGINAL; > + if (NUMBER(PG_head_mask) == NOT_FOUND_NUMBER) > + NUMBER(PG_head_mask) = 1L << PG_compound_ORIGINAL; > + > /* > * The values from here are for free page filtering based on > * mem_map array. These are minimum effort to cover old > @@ -1699,6 +1712,7 @@ write_vmcoreinfo_data(void) > WRITE_SYMBOL("mmu_vmemmap_psize", mmu_vmemmap_psize); > WRITE_SYMBOL("cpu_pgd", cpu_pgd); > WRITE_SYMBOL("demote_segment_4k", demote_segment_4k); > + WRITE_SYMBOL("free_huge_page", free_huge_page); > > /* > * write the structure size of 1st kernel > @@ -1788,6 +1802,7 @@ write_vmcoreinfo_data(void) > > WRITE_NUMBER("PG_lru", PG_lru); > WRITE_NUMBER("PG_private", PG_private); > + WRITE_NUMBER("PG_head_mask", PG_head_mask); > WRITE_NUMBER("PG_swapcache", PG_swapcache); > WRITE_NUMBER("PG_buddy", PG_buddy); > WRITE_NUMBER("PG_slab", PG_slab); > @@ -2040,6 +2055,7 @@ read_vmcoreinfo(void) > READ_SYMBOL("mmu_vmemmap_psize", mmu_vmemmap_psize); > READ_SYMBOL("cpu_pgd", cpu_pgd); > READ_SYMBOL("demote_segment_4k", demote_segment_4k); > + READ_SYMBOL("free_huge_page", free_huge_page); > > READ_STRUCTURE_SIZE("page", page); > READ_STRUCTURE_SIZE("mem_section", mem_section); > @@ -2116,6 +2132,7 @@ read_vmcoreinfo(void) > > READ_NUMBER("PG_lru", PG_lru); > READ_NUMBER("PG_private", PG_private); > + READ_NUMBER("PG_head_mask", PG_head_mask); > READ_NUMBER("PG_swapcache", PG_swapcache); > READ_NUMBER("PG_slab", PG_slab); > READ_NUMBER("PG_buddy", PG_buddy); > @@ -4643,13 +4660,16 @@ __exclude_unnecessary_pages(unsigned long mem_map, > mdf_pfn_t pfn_start, mdf_pfn_t pfn_end, struct cycle *cycle) > { > mdf_pfn_t pfn; > + mdf_pfn_t *pfn_counter; > + mdf_pfn_t nr_pages; > unsigned long index_pg, pfn_mm; > unsigned long long maddr; > mdf_pfn_t pfn_read_start, pfn_read_end; > unsigned char page_cache[SIZE(page) * PGMM_CACHED]; > unsigned char *pcache; > - unsigned int _count, _mapcount = 0; > + unsigned int _count, _mapcount = 0, compound_order = 0; > unsigned long flags, mapping, private = 0; > + unsigned long compound_dtor; > > /* > * If a multi-page exclusion is pending, do it first > @@ -4715,11 +4735,36 @@ __exclude_unnecessary_pages(unsigned long mem_map, > flags = ULONG(pcache + OFFSET(page.flags)); > _count = UINT(pcache + OFFSET(page._count)); > mapping = ULONG(pcache + OFFSET(page.mapping)); > + > + if ((index_pg < PGMM_CACHED - 1) && > + isCompoundHead(flags)) { > + compound_order = ULONG(pcache + SIZE(page) + OFFSET(page.lru) > + + OFFSET(list_head.prev)); > + compound_dtor = ULONG(pcache + SIZE(page) + OFFSET(page.lru) > + + OFFSET(list_head.next)); > + > + if ((compound_order >= sizeof(unsigned long) * 8) > + || ((pfn & ((1UL << compound_order) - 1)) != 0)) { > + /* Invalid order */ > + compound_order = 0; > + } > + } else { > + /* > + * The last pfn of the mem_map cache must not be compound page > + * since all compound pages are aligned to its page order and > + * PGMM_CACHED is a power of 2. > + */ > + compound_order = 0; > + compound_dtor = 0; > + } > + > if (OFFSET(page._mapcount) != NOT_FOUND_STRUCTURE) > _mapcount = UINT(pcache + OFFSET(page._mapcount)); > if (OFFSET(page.private) != NOT_FOUND_STRUCTURE) > private = ULONG(pcache + OFFSET(page.private)); > > + nr_pages = 1 << compound_order; > + pfn_counter = NULL; > /* > * Exclude the free page managed by a buddy > * Use buddy identification of free pages whether cyclic or not. > @@ -4727,12 +4772,8 @@ __exclude_unnecessary_pages(unsigned long mem_map, > if ((info->dump_level & DL_EXCLUDE_FREE) > && info->page_is_buddy > && info->page_is_buddy(flags, _mapcount, private, _count)) { > - int nr_pages = 1 << private; > - > - exclude_range(&pfn_free, pfn, pfn + nr_pages, cycle); > - > - pfn += nr_pages - 1; > - mem_map += (nr_pages - 1) * SIZE(page); > + nr_pages = 1 << private; > + pfn_counter = &pfn_free; > } > /* > * Exclude the cache page without the private page. > @@ -4740,8 +4781,7 @@ __exclude_unnecessary_pages(unsigned long mem_map, > else if ((info->dump_level & DL_EXCLUDE_CACHE) > && (isLRU(flags) || isSwapCache(flags)) > && !isPrivate(flags) && !isAnon(mapping)) { > - if (clear_bit_on_2nd_bitmap_for_kernel(pfn, cycle)) > - pfn_cache++; > + pfn_counter = &pfn_cache; > } > /* > * Exclude the cache page with the private page. > @@ -4749,23 +4789,39 @@ __exclude_unnecessary_pages(unsigned long mem_map, > else if ((info->dump_level & DL_EXCLUDE_CACHE_PRI) > && (isLRU(flags) || isSwapCache(flags)) > && !isAnon(mapping)) { > - if (clear_bit_on_2nd_bitmap_for_kernel(pfn, cycle)) > - pfn_cache_private++; > + pfn_counter = &pfn_cache_private; > } > /* > * Exclude the data page of the user process. > + * - anonymous pages > + * - hugetlbfs pages > */ > else if ((info->dump_level & DL_EXCLUDE_USER_DATA) > - && isAnon(mapping)) { > - if (clear_bit_on_2nd_bitmap_for_kernel(pfn, cycle)) > - pfn_user++; > + && (isAnon(mapping) || isHugetlb(compound_dtor))) { > + pfn_counter = &pfn_user; > } > /* > * Exclude the hwpoison page. > */ > else if (isHWPOISON(flags)) { > + pfn_counter = &pfn_hwpoison; > + } > + /* > + * Unexcludable page > + */ > + else > + continue; > + > + /* > + * Execute exclusion > + */ > + if (nr_pages == 1) { > if (clear_bit_on_2nd_bitmap_for_kernel(pfn, cycle)) > - pfn_hwpoison++; > + (*pfn_counter)++; > + } else { > + exclude_range(pfn_counter, pfn, pfn + nr_pages, cycle); > + pfn += nr_pages - 1; > + mem_map += (nr_pages - 1) * SIZE(page); > } > } > return TRUE; > diff --git a/makedumpfile.h b/makedumpfile.h > index eba9798..9f90b53 100644 > --- a/makedumpfile.h > +++ b/makedumpfile.h > @@ -74,6 +74,7 @@ int get_mem_type(void); > #define PG_lru_ORIGINAL (5) > #define PG_slab_ORIGINAL (7) > #define PG_private_ORIGINAL (11) /* Has something at ->private */ > +#define PG_compound_ORIGINAL (14) /* Is part of a compound page */ > #define PG_swapcache_ORIGINAL (15) /* Swap page: swp_entry_t in private */ > > #define PAGE_BUDDY_MAPCOUNT_VALUE_v2_6_38 (-2) > @@ -148,6 +149,9 @@ test_bit(int nr, unsigned long addr) > > #define isLRU(flags) test_bit(NUMBER(PG_lru), flags) > #define isPrivate(flags) test_bit(NUMBER(PG_private), flags) > +#define isCompoundHead(flags) (!!((flags) & NUMBER(PG_head_mask))) > +#define isHugetlb(dtor) ((SYMBOL(free_huge_page) != NOT_FOUND_SYMBOL) \ > + && (SYMBOL(free_huge_page) == dtor)) > #define isSwapCache(flags) test_bit(NUMBER(PG_swapcache), flags) > #define isHWPOISON(flags) (test_bit(NUMBER(PG_hwpoison), flags) \ > && (NUMBER(PG_hwpoison) != NOT_FOUND_NUMBER)) > @@ -1218,6 +1222,7 @@ struct symbol_table { > unsigned long long node_remap_start_vaddr; > unsigned long long node_remap_end_vaddr; > unsigned long long node_remap_start_pfn; > + unsigned long long free_huge_page; > > /* > * for Xen extraction > @@ -1509,6 +1514,8 @@ struct number_table { > */ > long PG_lru; > long PG_private; > + long PG_head; > + long PG_head_mask; > long PG_swapcache; > long PG_buddy; > long PG_slab; _______________________________________________ kexec mailing list kexec@lists.infradead.org http://lists.infradead.org/mailman/listinfo/kexec