From: Muchun Song <songmuchun@bytedance.com>
To: Jonathan Corbet <corbet@lwn.net>,
Mike Kravetz <mike.kravetz@oracle.com>,
Thomas Gleixner <tglx@linutronix.de>,
mingo@redhat.com, bp@alien8.de, x86@kernel.org, hpa@zytor.com,
dave.hansen@linux.intel.com, luto@kernel.org,
Peter Zijlstra <peterz@infradead.org>,
viro@zeniv.linux.org.uk,
Andrew Morton <akpm@linux-foundation.org>,
paulmck@kernel.org, mchehab+huawei@kernel.org,
pawan.kumar.gupta@linux.intel.com,
Randy Dunlap <rdunlap@infradead.org>,
oneukum@suse.com, anshuman.khandual@arm.com, jroedel@suse.de,
Mina Almasry <almasrymina@google.com>,
David Rientjes <rientjes@google.com>
Cc: linux-doc@vger.kernel.org, LKML <linux-kernel@vger.kernel.org>,
Linux Memory Management List <linux-mm@kvack.org>,
linux-fsdevel@vger.kernel.org
Subject: Re: [RFC PATCH 21/24] mm/hugetlb: Merge pte to huge pmd only for gigantic page
Date: Sun, 20 Sep 2020 17:59:01 +0800 [thread overview]
Message-ID: <CAMZfGtWXr0A3ymf_trBmUggRudbZbhfwNCJWSHZdkK9JeBY1fg@mail.gmail.com> (raw)
In-Reply-To: <20200915125947.26204-22-songmuchun@bytedance.com>
On Tue, Sep 15, 2020 at 9:03 PM Muchun Song <songmuchun@bytedance.com> 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.
>
> Signed-off-by: Muchun Song <songmuchun@bytedance.com>
> ---
> include/linux/hugetlb.h | 7 +++
> mm/hugetlb.c | 104 +++++++++++++++++++++++++++++++++++++++-
> 2 files changed, 109 insertions(+), 2 deletions(-)
>
> diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
> index e3aa192f1c39..c56df0da7ae5 100644
> --- a/include/linux/hugetlb.h
> +++ b/include/linux/hugetlb.h
> @@ -611,6 +611,13 @@ static inline bool vmemmap_pmd_huge(pmd_t *pmd)
> }
> #endif
>
> +#ifndef vmemmap_pmd_mkhuge
> +static inline pmd_t vmemmap_pmd_mkhuge(struct page *page)
> +{
> + return pmd_mkhuge(mk_pmd(page, PAGE_KERNEL));
> +}
> +#endif
> +
> #ifndef VMEMMAP_HPAGE_SHIFT
> #define VMEMMAP_HPAGE_SHIFT PMD_SHIFT
> #endif
> diff --git a/mm/hugetlb.c b/mm/hugetlb.c
> index 28c154679838..3ca36e259b4e 100644
> --- a/mm/hugetlb.c
> +++ b/mm/hugetlb.c
> @@ -1759,6 +1759,62 @@ 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);
> +
> + 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++, PAGE_KERNEL);
> + 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 alloc_vmemmap_pages(struct hstate *h, struct list_head *list)
> {
> int i;
> @@ -1772,6 +1828,15 @@ static inline void alloc_vmemmap_pages(struct hstate *h, struct list_head *list)
> }
> }
>
> +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_refcounted(page + i);
> +}
> +
> static void alloc_huge_page_vmemmap(struct hstate *h, struct page *head)
> {
> pmd_t *pmd;
> @@ -1791,10 +1856,45 @@ static 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(nr_vmemmap(h), VMEMMAP_HPAGE_NR)) {
> + unsigned long addr = (unsigned long)head;
> + unsigned long end = addr + nr_vmemmap_size(h);
> +
> + spin_unlock(ptl);
> +
> + 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;
Here forget to call dissolve_compound_page().
+ 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,
> + &remap_pages);
> + }
> +
> +out:
> + free_vmemmap_page_list(&remap_pages);
> + return;
> + }
> }
> spin_unlock(ptl);
> }
> --
> 2.20.1
>
--
Yours,
Muchun
next prev parent reply other threads:[~2020-09-20 9:59 UTC|newest]
Thread overview: 48+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-09-15 12:59 [RFC PATCH 00/24] mm/hugetlb: Free some vmemmap pages of hugetlb page Muchun Song
2020-09-15 12:59 ` [RFC PATCH 01/24] mm/memory_hotplug: Move bootmem info registration API to bootmem_info.c Muchun Song
2020-09-29 22:46 ` Mike Kravetz
2020-09-15 12:59 ` [RFC PATCH 02/24] mm/memory_hotplug: Move {get,put}_page_bootmem() " Muchun Song
2020-09-29 23:30 ` Mike Kravetz
2020-09-15 12:59 ` [RFC PATCH 03/24] mm/hugetlb: Introduce a new config HUGETLB_PAGE_FREE_VMEMMAP Muchun Song
2020-09-16 2:13 ` Randy Dunlap
2020-09-29 23:41 ` Mike Kravetz
2020-09-30 2:56 ` [External] " Muchun Song
2020-09-15 12:59 ` [RFC PATCH 04/24] mm/hugetlb: Register bootmem info when CONFIG_HUGETLB_PAGE_FREE_VMEMMAP Muchun Song
2020-09-15 12:59 ` [RFC PATCH 05/24] mm/hugetlb: Introduce nr_free_vmemmap_pages in the struct hstate Muchun Song
2020-09-30 22:41 ` Mike Kravetz
2020-10-01 2:57 ` [External] " Muchun Song
2020-09-15 12:59 ` [RFC PATCH 06/24] mm/hugetlb: Introduce pgtable allocation/freeing helpers Muchun Song
2020-09-15 12:59 ` [RFC PATCH 07/24] mm/hugetlb: Add freeing unused vmemmap pages support for x86 Muchun Song
2020-09-15 12:59 ` [RFC PATCH 08/24] mm/bootmem_info: Introduce {free,prepare}_vmemmap_page() Muchun Song
2020-09-15 12:59 ` [RFC PATCH 09/24] x86/mm: Introduce VMEMMAP_SIZE/VMEMMAP_END macro Muchun Song
2020-09-15 12:59 ` [RFC PATCH 10/24] mm/hugetlb: Free the vmemmap pages associated with each hugetlb page Muchun Song
2020-09-15 12:59 ` [RFC PATCH 11/24] mm/hugetlb: Add vmemmap_pmd_huge macro for x86 Muchun Song
2020-09-15 12:59 ` [RFC PATCH 12/24] mm/hugetlb: Defer freeing of hugetlb pages Muchun Song
2020-09-15 12:59 ` [RFC PATCH 13/24] mm/hugetlb: Allocate the vmemmap pages associated with each hugetlb page Muchun Song
2020-09-15 12:59 ` [RFC PATCH 14/24] mm/hugetlb: Introduce remap_huge_page_pmd_vmemmap helper Muchun Song
2020-09-15 12:59 ` [RFC PATCH 15/24] mm/hugetlb: Use PG_slab to indicate split pmd Muchun Song
2020-09-15 12:59 ` [RFC PATCH 16/24] mm/hugetlb: Support freeing vmemmap pages of gigantic page Muchun Song
2020-09-15 12:59 ` [RFC PATCH 17/24] mm/hugetlb: Add a BUILD_BUG_ON to check if struct page size is a power of two Muchun Song
2020-09-15 12:59 ` [RFC PATCH 18/24] mm/hugetlb: Clear PageHWPoison on the non-error memory page Muchun Song
2020-09-15 12:59 ` [RFC PATCH 19/24] mm/hugetlb: Flush work when dissolving hugetlb page Muchun Song
2020-09-15 12:59 ` [RFC PATCH 20/24] mm/hugetlb: Add a kernel parameter hugetlb_free_vmemmap Muchun Song
2020-09-16 2:10 ` Randy Dunlap
2020-09-16 2:50 ` [External] " Muchun Song
2020-09-15 12:59 ` [RFC PATCH 21/24] mm/hugetlb: Merge pte to huge pmd only for gigantic page Muchun Song
2020-09-20 9:59 ` Muchun Song [this message]
2020-09-15 12:59 ` [RFC PATCH 22/24] mm/hugetlb: Implement vmemmap_pmd_mkhuge macro Muchun Song
2020-09-15 12:59 ` [RFC PATCH 23/24] mm/hugetlb: Gather discrete indexes of tail page Muchun Song
2020-09-15 12:59 ` [RFC PATCH 24/24] mm/hugetlb: Add BUILD_BUG_ON to catch invalid usage of tail struct page Muchun Song
2020-09-15 14:32 ` [RFC PATCH 00/24] mm/hugetlb: Free some vmemmap pages of hugetlb page Matthew Wilcox
2020-09-15 14:53 ` Dave Hansen
2020-09-15 15:28 ` [External] " Muchun Song
2020-09-15 15:42 ` Matthew Wilcox
2020-09-15 17:32 ` Muchun Song
2020-09-15 17:39 ` Matthew Wilcox
2020-09-15 18:03 ` Muchun Song
2020-09-15 18:15 ` Matthew Wilcox
2020-09-16 2:45 ` Muchun Song
2020-09-29 21:58 ` Mike Kravetz
2020-09-30 3:13 ` Matthew Wilcox
2020-10-07 21:12 ` Mike Kravetz
2020-10-09 4:13 ` [External] " Muchun Song
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=CAMZfGtWXr0A3ymf_trBmUggRudbZbhfwNCJWSHZdkK9JeBY1fg@mail.gmail.com \
--to=songmuchun@bytedance.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=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=paulmck@kernel.org \
--cc=pawan.kumar.gupta@linux.intel.com \
--cc=peterz@infradead.org \
--cc=rdunlap@infradead.org \
--cc=rientjes@google.com \
--cc=tglx@linutronix.de \
--cc=viro@zeniv.linux.org.uk \
--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).