Hi, Barry I have changed SECTION_SIZE_BITS to 27 in our products, but I don't have to submit it.
-----邮件原件----- 发件人: Song Bao Hua (Barry Song) 发送时间: 2020年11月16日 16:34 收件人: Catalin Marinas <catalin.mari...@arm.com>; Mike Rapoport <r...@linux.ibm.com>; liwei (CM) <liwei...@huawei.com> 抄送: w...@kernel.org; Xiaqing (A) <saberlily....@hisilicon.com>; Chenfeng (puck) <puck.c...@hisilicon.com>; butao <bu...@hisilicon.com>; fengbaopeng <fengbaope...@hisilicon.com>; nsaenzjulie...@suse.de; steve.cap...@arm.com; linux-arm-ker...@lists.infradead.org; linux-kernel@vger.kernel.org; sujunfei <sujunf...@hisilicon.com>; Linuxarm <linux...@huawei.com> 主题: RE: [PATCH v2] arm64: mm: free unused memmap for sparse memory model that define VMEMMAP > -----Original Message----- > From: Catalin Marinas [mailto:catalin.mari...@arm.com] > Sent: Friday, September 4, 2020 12:06 AM > To: Mike Rapoport <r...@linux.ibm.com> > Cc: liwei (CM) <liwei...@huawei.com>; w...@kernel.org; Xiaqing (A) > <saberlily....@hisilicon.com>; Chenfeng (puck) > <puck.c...@hisilicon.com>; butao <bu...@hisilicon.com>; fengbaopeng > <fengbaope...@hisilicon.com>; nsaenzjulie...@suse.de; > steve.cap...@arm.com; Song Bao Hua (Barry Song) > <song.bao....@hisilicon.com>; linux-arm-ker...@lists.infradead.org; > linux-kernel@vger.kernel.org; sujunfei <sujunf...@hisilicon.com> > Subject: Re: [PATCH v2] arm64: mm: free unused memmap for sparse > memory model that define VMEMMAP > > On Mon, Aug 17, 2020 at 11:04:05AM +0300, Mike Rapoport wrote: > > On Wed, Aug 12, 2020 at 09:06:55AM +0800, Wei Li wrote: > > > For the memory hole, sparse memory model that define > SPARSEMEM_VMEMMAP > > > do not free the reserved memory for the page map, this patch do it. > > > > I've been thinking about it a bit more and it seems that instead of > > freeing unused memory map it would be better to allocate the exact > > memory map from the beginning. > > > > In sparse_init_nid() we can replace PAGES_PER_SECTION parameter to > > __populate_section_memmap() with the calculated value for > > architectures that define HAVE_ARCH_PFN_VALID. > > Or just use a smaller PAGES_PER_SECTION and reduce the waste ;). > > Just to be clear, are you suggesting that we should use pfn_valid() on > the pages within a section to calculate the actual range? The > pfn_valid() implementation on arm64 checks for the validity of a > sparse section, so this would be called from within the sparse_init() > code path. I hope there's no dependency but I haven't checked. If it > works, it's fine by me, it solves the FLATMEM mem_map freeing as well. > > With 4KB pages on arm64, vmemmap_populate() stops at the pmd level, so > it always allocates PMD_SIZE. Wei's patch also only frees in PMD_SIZE > amounts. So, with a sizeof(struct page) of 64 (2^6), a PMD_SIZE > mem_map section would cover 2^(21-6) pages, so that's equivalent to a > SECTION_SIZE_BITS of 21-6+12 = 27. > > If we reduce SECTION_SIZE_BITS to 27 or less, this patch is a no-op. It would be the simplest way to fix this issue. It seems X86_64 is also using 27. @wei, has you ever tried to send a patch to change SECTION_SIZE_BITS to 27 for ARM64? > > -- > Catalin Thanks Barry
