| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <7d0129fb-551f-e37a-f6cd-8fd96c896851@linux.dev>
Date: Tue, 19 Sep 2023 14:27:44 +0800
From: Muchun Song <muchun.song@...ux.dev>
To: Mike Kravetz <mike.kravetz@...cle.com>, linux-mm@...ck.org,
linux-kernel@...r.kernel.org
Cc: Muchun Song <songmuchun@...edance.com>,
Joao Martins <joao.m.martins@...cle.com>,
Oscar Salvador <osalvador@...e.de>,
David Hildenbrand <david@...hat.com>,
Miaohe Lin <linmiaohe@...wei.com>,
David Rientjes <rientjes@...gle.com>,
Anshuman Khandual <anshuman.khandual@....com>,
Naoya Horiguchi <naoya.horiguchi@...ux.dev>,
Barry Song <21cnbao@...il.com>, Michal Hocko <mhocko@...e.com>,
Matthew Wilcox <willy@...radead.org>,
Xiongchun Duan <duanxiongchun@...edance.com>,
Andrew Morton <akpm@...ux-foundation.org>
Subject: Re: [PATCH v4 6/8] hugetlb: batch PMD split for bulk vmemmap dedup
On 2023/9/19 07:01, Mike Kravetz wrote:
> From: Joao Martins <joao.m.martins@...cle.com>
>
> In an effort to minimize amount of TLB flushes, batch all PMD splits
> belonging to a range of pages in order to perform only 1 (global) TLB
> flush.
>
> Add a flags field to the walker and pass whether it's a bulk allocation
> or just a single page to decide to remap. First value
> (VMEMMAP_SPLIT_NO_TLB_FLUSH) designates the request to not do the TLB
> flush when we split the PMD.
>
> Rebased and updated by Mike Kravetz
>
> Signed-off-by: Joao Martins <joao.m.martins@...cle.com>
> Signed-off-by: Mike Kravetz <mike.kravetz@...cle.com>
> ---
> mm/hugetlb_vmemmap.c | 79 +++++++++++++++++++++++++++++++++++++++++---
> 1 file changed, 75 insertions(+), 4 deletions(-)
>
> diff --git a/mm/hugetlb_vmemmap.c b/mm/hugetlb_vmemmap.c
> index 147ed15bcae4..e8bc2f7567db 100644
> --- a/mm/hugetlb_vmemmap.c
> +++ b/mm/hugetlb_vmemmap.c
> @@ -27,6 +27,7 @@
> * @reuse_addr: the virtual address of the @reuse_page page.
> * @vmemmap_pages: the list head of the vmemmap pages that can be freed
> * or is mapped from.
> + * @flags: used to modify behavior in bulk operations
> */
> struct vmemmap_remap_walk {
> void (*remap_pte)(pte_t *pte, unsigned long addr,
> @@ -35,9 +36,11 @@ struct vmemmap_remap_walk {
> struct page *reuse_page;
> unsigned long reuse_addr;
> struct list_head *vmemmap_pages;
> +#define VMEMMAP_SPLIT_NO_TLB_FLUSH BIT(0)
Please add a brief comment following this macro to explain what's the
behavior.
> + unsigned long flags;
> };
>
> -static int split_vmemmap_huge_pmd(pmd_t *pmd, unsigned long start)
> +static int split_vmemmap_huge_pmd(pmd_t *pmd, unsigned long start, bool flush)
> {
> pmd_t __pmd;
> int i;
> @@ -80,7 +83,8 @@ static int split_vmemmap_huge_pmd(pmd_t *pmd, unsigned long start)
> /* Make pte visible before pmd. See comment in pmd_install(). */
> smp_wmb();
> pmd_populate_kernel(&init_mm, pmd, pgtable);
> - flush_tlb_kernel_range(start, start + PMD_SIZE);
> + if (flush)
> + flush_tlb_kernel_range(start, start + PMD_SIZE);
> } else {
> pte_free_kernel(&init_mm, pgtable);
> }
> @@ -127,11 +131,20 @@ static int vmemmap_pmd_range(pud_t *pud, unsigned long addr,
> do {
> int ret;
>
> - ret = split_vmemmap_huge_pmd(pmd, addr & PMD_MASK);
> + ret = split_vmemmap_huge_pmd(pmd, addr & PMD_MASK,
> + walk->flags & VMEMMAP_SPLIT_NO_TLB_FLUSH);
!(walk->flags & VMEMMAP_SPLIT_NO_TLB_FLUSH)?
Thanks.
> if (ret)
> return ret;
>
> next = pmd_addr_end(addr, end);
> +
> + /*
> + * We are only splitting, not remapping the hugetlb vmemmap
> + * pages.
> + */
> + if (!walk->remap_pte)
> + continue;
> +
> vmemmap_pte_range(pmd, addr, next, walk);
> } while (pmd++, addr = next, addr != end);
>
> @@ -198,7 +211,8 @@ static int vmemmap_remap_range(unsigned long start, unsigned long end,
> return ret;
> } while (pgd++, addr = next, addr != end);
>
> - flush_tlb_kernel_range(start, end);
> + if (walk->remap_pte)
> + flush_tlb_kernel_range(start, end);
>
> return 0;
> }
> @@ -300,6 +314,36 @@ static void vmemmap_restore_pte(pte_t *pte, unsigned long addr,
> set_pte_at(&init_mm, addr, pte, mk_pte(page, pgprot));
> }
>
> +/**
> + * vmemmap_remap_split - split the vmemmap virtual address range [@start, @end)
> + * backing PMDs of the directmap into PTEs
> + * @start: start address of the vmemmap virtual address range that we want
> + * to remap.
> + * @end: end address of the vmemmap virtual address range that we want to
> + * remap.
> + * @reuse: reuse address.
> + *
> + * Return: %0 on success, negative error code otherwise.
> + */
> +static int vmemmap_remap_split(unsigned long start, unsigned long end,
> + unsigned long reuse)
> +{
> + int ret;
> + struct vmemmap_remap_walk walk = {
> + .remap_pte = NULL,
> + .flags = VMEMMAP_SPLIT_NO_TLB_FLUSH,
> + };
> +
> + /* See the comment in the vmemmap_remap_free(). */
> + BUG_ON(start - reuse != PAGE_SIZE);
> +
> + mmap_read_lock(&init_mm);
> + ret = vmemmap_remap_range(reuse, end, &walk);
> + mmap_read_unlock(&init_mm);
> +
> + return ret;
> +}
> +
> /**
> * vmemmap_remap_free - remap the vmemmap virtual address range [@start, @end)
> * to the page which @reuse is mapped to, then free vmemmap
> @@ -323,6 +367,7 @@ static int vmemmap_remap_free(unsigned long start, unsigned long end,
> .remap_pte = vmemmap_remap_pte,
> .reuse_addr = reuse,
> .vmemmap_pages = vmemmap_pages,
> + .flags = 0,
> };
> int nid = page_to_nid((struct page *)reuse);
> gfp_t gfp_mask = GFP_KERNEL | __GFP_NORETRY | __GFP_NOWARN;
> @@ -371,6 +416,7 @@ static int vmemmap_remap_free(unsigned long start, unsigned long end,
> .remap_pte = vmemmap_restore_pte,
> .reuse_addr = reuse,
> .vmemmap_pages = vmemmap_pages,
> + .flags = 0,
> };
>
> vmemmap_remap_range(reuse, end, &walk);
> @@ -422,6 +468,7 @@ static int vmemmap_remap_alloc(unsigned long start, unsigned long end,
> .remap_pte = vmemmap_restore_pte,
> .reuse_addr = reuse,
> .vmemmap_pages = &vmemmap_pages,
> + .flags = 0,
> };
>
> /* See the comment in the vmemmap_remap_free(). */
> @@ -630,11 +677,35 @@ void hugetlb_vmemmap_optimize(const struct hstate *h, struct page *head)
> free_vmemmap_page_list(&vmemmap_pages);
> }
>
> +static void hugetlb_vmemmap_split(const struct hstate *h, struct page *head)
> +{
> + unsigned long vmemmap_start = (unsigned long)head, vmemmap_end;
> + unsigned long vmemmap_reuse;
> +
> + if (!vmemmap_should_optimize(h, head))
> + return;
> +
> + vmemmap_end = vmemmap_start + hugetlb_vmemmap_size(h);
> + vmemmap_reuse = vmemmap_start;
> + vmemmap_start += HUGETLB_VMEMMAP_RESERVE_SIZE;
> +
> + /*
> + * Split PMDs on the vmemmap virtual address range [@vmemmap_start,
> + * @vmemmap_end]
> + */
> + vmemmap_remap_split(vmemmap_start, vmemmap_end, vmemmap_reuse);
> +}
> +
> void hugetlb_vmemmap_optimize_folios(struct hstate *h, struct list_head *folio_list)
> {
> struct folio *folio;
> LIST_HEAD(vmemmap_pages);
>
> + list_for_each_entry(folio, folio_list, lru)
> + hugetlb_vmemmap_split(h, &folio->page);
> +
> + flush_tlb_all();
> +
> list_for_each_entry(folio, folio_list, lru) {
> int ret = __hugetlb_vmemmap_optimize(h, &folio->page,
> &vmemmap_pages);
Powered by blists - more mailing lists