From: Michal Hocko <mhocko@suse.com>
To: Muchun Song <songmuchun@bytedance.com>
Cc: corbet@lwn.net, mike.kravetz@oracle.com, tglx@linutronix.de,
mingo@redhat.com, bp@alien8.de, x86@kernel.org, hpa@zytor.com,
dave.hansen@linux.intel.com, luto@kernel.org,
peterz@infradead.org, viro@zeniv.linux.org.uk,
akpm@linux-foundation.org, paulmck@kernel.org,
mchehab+huawei@kernel.org, pawan.kumar.gupta@linux.intel.com,
rdunlap@infradead.org, oneukum@suse.com,
anshuman.khandual@arm.com, jroedel@suse.de,
almasrymina@google.com, rientjes@google.com, willy@infradead.org,
osalvador@suse.de, song.bao.hua@hisilicon.com,
duanxiongchun@bytedance.com, linux-doc@vger.kernel.org,
linux-kernel@vger.kernel.org, linux-mm@kvack.org,
linux-fsdevel@vger.kernel.org
Subject: Re: [PATCH v5 18/21] mm/hugetlb: Merge pte to huge pmd only for gigantic page
Date: Fri, 20 Nov 2020 09:23:58 +0100 [thread overview]
Message-ID: <20201120082358.GH3200@dhcp22.suse.cz> (raw)
In-Reply-To: <20201120064325.34492-19-songmuchun@bytedance.com>
On Fri 20-11-20 14:43:22, Muchun Song wrote:
> Merge pte to huge pmd if it has ever been split. Now only support
> gigantic page which's vmemmap pages size is an integer multiple of
> PMD_SIZE. This is the simplest case to handle.
I think it would be benefitial for anybody who plan to implement this
for normal PMDs to document challenges while you still have them fresh
in your mind.
> Signed-off-by: Muchun Song <songmuchun@bytedance.com>
> ---
> arch/x86/include/asm/hugetlb.h | 8 +++
> mm/hugetlb_vmemmap.c | 118 ++++++++++++++++++++++++++++++++++++++++-
> 2 files changed, 124 insertions(+), 2 deletions(-)
>
> diff --git a/arch/x86/include/asm/hugetlb.h b/arch/x86/include/asm/hugetlb.h
> index c601fe042832..1de1c519a84a 100644
> --- a/arch/x86/include/asm/hugetlb.h
> +++ b/arch/x86/include/asm/hugetlb.h
> @@ -12,6 +12,14 @@ static inline bool vmemmap_pmd_huge(pmd_t *pmd)
> {
> return pmd_large(*pmd);
> }
> +
> +#define vmemmap_pmd_mkhuge vmemmap_pmd_mkhuge
> +static inline pmd_t vmemmap_pmd_mkhuge(struct page *page)
> +{
> + pte_t entry = pfn_pte(page_to_pfn(page), PAGE_KERNEL_LARGE);
> +
> + return __pmd(pte_val(entry));
> +}
> #endif
>
> #define hugepages_supported() boot_cpu_has(X86_FEATURE_PSE)
> diff --git a/mm/hugetlb_vmemmap.c b/mm/hugetlb_vmemmap.c
> index c958699d1393..bf2b6b3e75af 100644
> --- a/mm/hugetlb_vmemmap.c
> +++ b/mm/hugetlb_vmemmap.c
> @@ -144,6 +144,14 @@ static inline bool vmemmap_pmd_huge(pmd_t *pmd)
> }
> #endif
>
> +#ifndef vmemmap_pmd_mkhuge
> +#define vmemmap_pmd_mkhuge vmemmap_pmd_mkhuge
> +static inline pmd_t vmemmap_pmd_mkhuge(struct page *page)
> +{
> + return pmd_mkhuge(mk_pmd(page, PAGE_KERNEL));
> +}
> +#endif
> +
> static bool hugetlb_free_vmemmap_disabled __initdata;
>
> static int __init early_hugetlb_free_vmemmap_param(char *buf)
> @@ -422,6 +430,104 @@ static void __remap_huge_page_pte_vmemmap(struct page *reuse, pte_t *ptep,
> }
> }
>
> +static void __replace_huge_page_pte_vmemmap(pte_t *ptep, unsigned long start,
> + unsigned int nr, struct page *huge,
> + struct list_head *free_pages)
> +{
> + unsigned long addr;
> + unsigned long end = start + (nr << PAGE_SHIFT);
> + pgprot_t pgprot = PAGE_KERNEL;
> +
> + for (addr = start; addr < end; addr += PAGE_SIZE, ptep++) {
> + struct page *page;
> + pte_t old = *ptep;
> + pte_t entry;
> +
> + prepare_vmemmap_page(huge);
> +
> + entry = mk_pte(huge++, pgprot);
> + VM_WARN_ON(!pte_present(old));
> + page = pte_page(old);
> + list_add(&page->lru, free_pages);
> +
> + set_pte_at(&init_mm, addr, ptep, entry);
> + }
> +}
> +
> +static void replace_huge_page_pmd_vmemmap(pmd_t *pmd, unsigned long start,
> + struct page *huge,
> + struct list_head *free_pages)
> +{
> + unsigned long end = start + VMEMMAP_HPAGE_SIZE;
> +
> + flush_cache_vunmap(start, end);
> + __replace_huge_page_pte_vmemmap(pte_offset_kernel(pmd, start), start,
> + VMEMMAP_HPAGE_NR, huge, free_pages);
> + flush_tlb_kernel_range(start, end);
> +}
> +
> +static pte_t *merge_vmemmap_pte(pmd_t *pmdp, unsigned long addr)
> +{
> + pte_t *pte;
> + struct page *page;
> +
> + pte = pte_offset_kernel(pmdp, addr);
> + page = pte_page(*pte);
> + set_pmd(pmdp, vmemmap_pmd_mkhuge(page));
> +
> + return pte;
> +}
> +
> +static void merge_huge_page_pmd_vmemmap(pmd_t *pmd, unsigned long start,
> + struct page *huge,
> + struct list_head *free_pages)
> +{
> + replace_huge_page_pmd_vmemmap(pmd, start, huge, free_pages);
> + pte_free_kernel(&init_mm, merge_vmemmap_pte(pmd, start));
> + flush_tlb_kernel_range(start, start + VMEMMAP_HPAGE_SIZE);
> +}
> +
> +static inline void dissolve_compound_page(struct page *page, unsigned int order)
> +{
> + int i;
> + unsigned int nr_pages = 1 << order;
> +
> + for (i = 1; i < nr_pages; i++)
> + set_page_count(page + i, 1);
> +}
> +
> +static void merge_gigantic_page_vmemmap(struct hstate *h, struct page *head,
> + pmd_t *pmd)
> +{
> + LIST_HEAD(free_pages);
> + unsigned long addr = (unsigned long)head;
> + unsigned long end = addr + vmemmap_pages_size_per_hpage(h);
> +
> + for (; addr < end; addr += VMEMMAP_HPAGE_SIZE) {
> + void *to;
> + struct page *page;
> +
> + page = alloc_pages(GFP_VMEMMAP_PAGE & ~__GFP_NOFAIL,
> + VMEMMAP_HPAGE_ORDER);
> + if (!page)
> + goto out;
> +
> + dissolve_compound_page(page, VMEMMAP_HPAGE_ORDER);
> + to = page_to_virt(page);
> + memcpy(to, (void *)addr, VMEMMAP_HPAGE_SIZE);
> +
> + /*
> + * Make sure that any data that writes to the
> + * @to is made visible to the physical page.
> + */
> + flush_kernel_vmap_range(to, VMEMMAP_HPAGE_SIZE);
> +
> + merge_huge_page_pmd_vmemmap(pmd++, addr, page, &free_pages);
> + }
> +out:
> + free_vmemmap_page_list(&free_pages);
> +}
> +
> static inline void alloc_vmemmap_pages(struct hstate *h, struct list_head *list)
> {
> int i;
> @@ -454,10 +560,18 @@ void alloc_huge_page_vmemmap(struct hstate *h, struct page *head)
> __remap_huge_page_pte_vmemmap);
> if (!freed_vmemmap_hpage_dec(pmd_page(*pmd)) && pmd_split(pmd)) {
> /*
> - * Todo:
> - * Merge pte to huge pmd if it has ever been split.
> + * Merge pte to huge pmd if it has ever been split. Now only
> + * support gigantic page which's vmemmap pages size is an
> + * integer multiple of PMD_SIZE. This is the simplest case
> + * to handle.
> */
> clear_pmd_split(pmd);
> +
> + if (IS_ALIGNED(vmemmap_pages_per_hpage(h), VMEMMAP_HPAGE_NR)) {
> + spin_unlock(ptl);
> + merge_gigantic_page_vmemmap(h, head, pmd);
> + return;
> + }
> }
> spin_unlock(ptl);
> }
> --
> 2.11.0
--
Michal Hocko
SUSE Labs
next prev parent reply other threads:[~2020-11-20 8:24 UTC|newest]
Thread overview: 77+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-11-20 6:43 [PATCH v5 00/21] Free some vmemmap pages of hugetlb page Muchun Song
2020-11-20 6:43 ` [PATCH v5 01/21] mm/memory_hotplug: Move bootmem info registration API to bootmem_info.c Muchun Song
2020-11-20 6:43 ` [PATCH v5 02/21] mm/memory_hotplug: Move {get,put}_page_bootmem() " Muchun Song
2020-11-20 6:43 ` [PATCH v5 03/21] mm/hugetlb: Introduce a new config HUGETLB_PAGE_FREE_VMEMMAP Muchun Song
2020-11-20 7:49 ` Michal Hocko
2020-11-20 8:35 ` [External] " Muchun Song
2020-11-20 8:47 ` Michal Hocko
2020-11-20 8:53 ` Muchun Song
2020-11-20 6:43 ` [PATCH v5 04/21] mm/hugetlb: Introduce nr_free_vmemmap_pages in the struct hstate Muchun Song
2020-11-20 6:43 ` [PATCH v5 05/21] mm/hugetlb: Introduce pgtable allocation/freeing helpers Muchun Song
2020-11-20 6:43 ` [PATCH v5 06/21] mm/bootmem_info: Introduce {free,prepare}_vmemmap_page() Muchun Song
2020-11-20 6:43 ` [PATCH v5 07/21] mm/bootmem_info: Combine bootmem info and type into page->freelist Muchun Song
2020-11-20 6:43 ` [PATCH v5 08/21] mm/hugetlb: Initialize page table lock for vmemmap Muchun Song
2020-11-20 6:43 ` [PATCH v5 09/21] mm/hugetlb: Free the vmemmap pages associated with each hugetlb page Muchun Song
2020-11-20 6:43 ` [PATCH v5 10/21] mm/hugetlb: Defer freeing of hugetlb pages Muchun Song
2020-11-20 6:43 ` [PATCH v5 11/21] mm/hugetlb: Allocate the vmemmap pages associated with each hugetlb page Muchun Song
2020-11-20 8:11 ` Michal Hocko
2020-11-20 8:51 ` [External] " Muchun Song
2020-11-20 9:28 ` Michal Hocko
2020-11-20 9:37 ` Muchun Song
2020-11-20 11:10 ` Michal Hocko
2020-11-20 11:56 ` Muchun Song
2020-11-20 6:43 ` [PATCH v5 12/21] mm/hugetlb: Introduce remap_huge_page_pmd_vmemmap helper Muchun Song
2020-11-20 6:43 ` [PATCH v5 13/21] mm/hugetlb: Use PG_slab to indicate split pmd Muchun Song
2020-11-20 8:16 ` Michal Hocko
2020-11-20 9:30 ` [External] " Muchun Song
2020-11-23 7:48 ` Michal Hocko
2020-11-23 8:01 ` Muchun Song
2020-11-20 6:43 ` [PATCH v5 14/21] mm/hugetlb: Support freeing vmemmap pages of gigantic page Muchun Song
2020-11-20 6:43 ` [PATCH v5 15/21] mm/hugetlb: Set the PageHWPoison to the raw error page Muchun Song
2020-11-20 8:19 ` Michal Hocko
2020-11-20 10:32 ` [External] " Muchun Song
2020-11-20 6:43 ` [PATCH v5 16/21] mm/hugetlb: Flush work when dissolving hugetlb page Muchun Song
2020-11-20 8:20 ` Michal Hocko
2020-11-20 6:43 ` [PATCH v5 17/21] mm/hugetlb: Add a kernel parameter hugetlb_free_vmemmap Muchun Song
2020-11-20 8:22 ` Michal Hocko
2020-11-20 10:39 ` [External] " Muchun Song
2020-11-20 6:43 ` [PATCH v5 18/21] mm/hugetlb: Merge pte to huge pmd only for gigantic page Muchun Song
2020-11-20 8:23 ` Michal Hocko [this message]
2020-11-20 10:41 ` [External] " Muchun Song
2020-11-20 6:43 ` [PATCH v5 19/21] mm/hugetlb: Gather discrete indexes of tail page Muchun Song
2020-11-20 6:43 ` [PATCH v5 20/21] mm/hugetlb: Add BUILD_BUG_ON to catch invalid usage of tail struct page Muchun Song
2020-11-20 6:43 ` [PATCH v5 21/21] mm/hugetlb: Disable freeing vmemmap if struct page size is not power of two Muchun Song
2020-11-20 8:25 ` Michal Hocko
2020-11-20 9:15 ` David Hildenbrand
2020-11-22 13:30 ` Mike Rapoport
2020-11-22 19:00 ` Matthew Wilcox
2020-11-23 3:14 ` [External] " Muchun Song
2020-11-20 9:16 ` David Hildenbrand
2020-11-20 10:42 ` [External] " Muchun Song
2020-11-20 8:42 ` [PATCH v5 00/21] Free some vmemmap pages of hugetlb page Michal Hocko
2020-11-20 9:27 ` David Hildenbrand
2020-11-20 9:39 ` Michal Hocko
2020-11-20 9:43 ` David Hildenbrand
2020-11-20 17:45 ` Mike Kravetz
2020-11-20 18:00 ` David Hildenbrand
2020-11-22 7:29 ` [External] " Muchun Song
2020-11-23 7:38 ` Michal Hocko
2020-11-23 21:52 ` Mike Kravetz
2020-11-23 22:01 ` Matthew Wilcox
2020-11-20 12:40 ` [External] " Muchun Song
2020-11-20 13:11 ` Michal Hocko
2020-11-20 15:44 ` Muchun Song
2020-11-23 7:40 ` Michal Hocko
2020-11-23 8:53 ` Muchun Song
2020-11-23 9:43 ` Michal Hocko
2020-11-23 10:36 ` Muchun Song
2020-11-23 10:42 ` Michal Hocko
2020-11-23 11:16 ` Muchun Song
2020-11-23 11:32 ` Michal Hocko
2020-11-23 12:07 ` Muchun Song
2020-11-23 12:18 ` Michal Hocko
2020-11-23 12:40 ` Muchun Song
2020-11-23 12:48 ` Michal Hocko
2020-11-23 12:45 ` Matthew Wilcox
2020-11-23 13:05 ` Muchun Song
2020-11-23 13:13 ` Michal Hocko
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20201120082358.GH3200@dhcp22.suse.cz \
--to=mhocko@suse.com \
--cc=akpm@linux-foundation.org \
--cc=almasrymina@google.com \
--cc=anshuman.khandual@arm.com \
--cc=bp@alien8.de \
--cc=corbet@lwn.net \
--cc=dave.hansen@linux.intel.com \
--cc=duanxiongchun@bytedance.com \
--cc=hpa@zytor.com \
--cc=jroedel@suse.de \
--cc=linux-doc@vger.kernel.org \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=luto@kernel.org \
--cc=mchehab+huawei@kernel.org \
--cc=mike.kravetz@oracle.com \
--cc=mingo@redhat.com \
--cc=oneukum@suse.com \
--cc=osalvador@suse.de \
--cc=paulmck@kernel.org \
--cc=pawan.kumar.gupta@linux.intel.com \
--cc=peterz@infradead.org \
--cc=rdunlap@infradead.org \
--cc=rientjes@google.com \
--cc=song.bao.hua@hisilicon.com \
--cc=songmuchun@bytedance.com \
--cc=tglx@linutronix.de \
--cc=viro@zeniv.linux.org.uk \
--cc=willy@infradead.org \
--cc=x86@kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).