linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Mike Kravetz <mike.kravetz@oracle.com>
To: James Houghton <jthoughton@google.com>
Cc: Muchun Song <songmuchun@bytedance.com>,
	Peter Xu <peterx@redhat.com>,
	Andrew Morton <akpm@linux-foundation.org>,
	David Hildenbrand <david@redhat.com>,
	David Rientjes <rientjes@google.com>,
	Axel Rasmussen <axelrasmussen@google.com>,
	Mina Almasry <almasrymina@google.com>,
	Zach O'Keefe <zokeefe@google.com>,
	Manish Mishra <manish.mishra@nutanix.com>,
	Naoya Horiguchi <naoya.horiguchi@nec.com>,
	"Dr . David Alan Gilbert" <dgilbert@redhat.com>,
	"Matthew Wilcox (Oracle)" <willy@infradead.org>,
	Vlastimil Babka <vbabka@suse.cz>,
	Baolin Wang <baolin.wang@linux.alibaba.com>,
	Miaohe Lin <linmiaohe@huawei.com>, Yang Shi <shy828301@gmail.com>,
	Frank van der Linden <fvdl@google.com>,
	Jiaqi Yan <jiaqiyan@google.com>,
	linux-mm@kvack.org, linux-kernel@vger.kernel.org
Subject: Re: [PATCH v2 14/46] hugetlb: split PTE markers when doing HGM walks
Date: Tue, 28 Feb 2023 14:48:18 -0800	[thread overview]
Message-ID: <Y/6EsomcdMDl8Ffh@monkey> (raw)
In-Reply-To: <20230218002819.1486479-15-jthoughton@google.com>

On 02/18/23 00:27, James Houghton wrote:
> Fix how UFFDIO_CONTINUE and UFFDIO_WRITEPROTECT interact in these two
> ways:
>  - UFFDIO_WRITEPROTECT no longer prevents a high-granularity
>    UFFDIO_CONTINUE.
>  - UFFD-WP PTE markers installed with UFFDIO_WRITEPROTECT will be
>    properly propagated when high-granularily UFFDIO_CONTINUEs are
>    performed.
> 
> Note: UFFDIO_WRITEPROTECT is not yet permitted at PAGE_SIZE granularity.
> 
> Signed-off-by: James Houghton <jthoughton@google.com>
> 
> diff --git a/mm/hugetlb.c b/mm/hugetlb.c
> index 810c05feb41f..f74183acc521 100644
> --- a/mm/hugetlb.c
> +++ b/mm/hugetlb.c

Seems relatively straight forward,

Acked-by: Mike Kravetz <mike.kravetz@oracle.com>
-- 
Mike Kravetz

> @@ -506,6 +506,30 @@ static bool has_same_uncharge_info(struct file_region *rg,
>  #endif
>  }
>  
> +static void hugetlb_install_markers_pmd(pmd_t *pmdp, pte_marker marker)
> +{
> +	int i;
> +
> +	for (i = 0; i < PTRS_PER_PMD; ++i)
> +		/*
> +		 * WRITE_ONCE not needed because the pud hasn't been
> +		 * installed yet.
> +		 */
> +		pmdp[i] = __pmd(pte_val(make_pte_marker(marker)));
> +}
> +
> +static void hugetlb_install_markers_pte(pte_t *ptep, pte_marker marker)
> +{
> +	int i;
> +
> +	for (i = 0; i < PTRS_PER_PTE; ++i)
> +		/*
> +		 * WRITE_ONCE not needed because the pmd hasn't been
> +		 * installed yet.
> +		 */
> +		ptep[i] = make_pte_marker(marker);
> +}
> +
>  /*
>   * hugetlb_alloc_pmd -- Allocate or find a PMD beneath a PUD-level hpte.
>   *
> @@ -528,23 +552,32 @@ pmd_t *hugetlb_alloc_pmd(struct mm_struct *mm, struct hugetlb_pte *hpte,
>  	pmd_t *new;
>  	pud_t *pudp;
>  	pud_t pud;
> +	bool is_marker;
> +	pte_marker marker;
>  
>  	if (hpte->level != HUGETLB_LEVEL_PUD)
>  		return ERR_PTR(-EINVAL);
>  
>  	pudp = (pud_t *)hpte->ptep;
>  retry:
> +	is_marker = false;
>  	pud = READ_ONCE(*pudp);
>  	if (likely(pud_present(pud)))
>  		return unlikely(pud_leaf(pud))
>  			? ERR_PTR(-EEXIST)
>  			: pmd_offset(pudp, addr);
> -	else if (!pud_none(pud))
> +	else if (!pud_none(pud)) {
>  		/*
> -		 * Not present and not none means that a swap entry lives here,
> -		 * and we can't get rid of it.
> +		 * Not present and not none means that a swap entry lives here.
> +		 * If it's a PTE marker, we can deal with it. If it's another
> +		 * swap entry, we don't attempt to split it.
>  		 */
> -		return ERR_PTR(-EEXIST);
> +		is_marker = is_pte_marker(__pte(pud_val(pud)));
> +		if (!is_marker)
> +			return ERR_PTR(-EEXIST);
> +
> +		marker = pte_marker_get(pte_to_swp_entry(__pte(pud_val(pud))));
> +	}
>  
>  	new = pmd_alloc_one(mm, addr);
>  	if (!new)
> @@ -557,6 +590,13 @@ pmd_t *hugetlb_alloc_pmd(struct mm_struct *mm, struct hugetlb_pte *hpte,
>  		goto retry;
>  	}
>  
> +	/*
> +	 * Install markers before PUD to avoid races with other
> +	 * page tables walks.
> +	 */
> +	if (is_marker)
> +		hugetlb_install_markers_pmd(new, marker);
> +
>  	mm_inc_nr_pmds(mm);
>  	smp_wmb(); /* See comment in pmd_install() */
>  	pud_populate(mm, pudp, new);
> @@ -576,23 +616,32 @@ pte_t *hugetlb_alloc_pte(struct mm_struct *mm, struct hugetlb_pte *hpte,
>  	pgtable_t new;
>  	pmd_t *pmdp;
>  	pmd_t pmd;
> +	bool is_marker;
> +	pte_marker marker;
>  
>  	if (hpte->level != HUGETLB_LEVEL_PMD)
>  		return ERR_PTR(-EINVAL);
>  
>  	pmdp = (pmd_t *)hpte->ptep;
>  retry:
> +	is_marker = false;
>  	pmd = READ_ONCE(*pmdp);
>  	if (likely(pmd_present(pmd)))
>  		return unlikely(pmd_leaf(pmd))
>  			? ERR_PTR(-EEXIST)
>  			: pte_offset_kernel(pmdp, addr);
> -	else if (!pmd_none(pmd))
> +	else if (!pmd_none(pmd)) {
>  		/*
> -		 * Not present and not none means that a swap entry lives here,
> -		 * and we can't get rid of it.
> +		 * Not present and not none means that a swap entry lives here.
> +		 * If it's a PTE marker, we can deal with it. If it's another
> +		 * swap entry, we don't attempt to split it.
>  		 */
> -		return ERR_PTR(-EEXIST);
> +		is_marker = is_pte_marker(__pte(pmd_val(pmd)));
> +		if (!is_marker)
> +			return ERR_PTR(-EEXIST);
> +
> +		marker = pte_marker_get(pte_to_swp_entry(__pte(pmd_val(pmd))));
> +	}
>  
>  	/*
>  	 * With CONFIG_HIGHPTE, calling `pte_alloc_one` directly may result
> @@ -613,6 +662,9 @@ pte_t *hugetlb_alloc_pte(struct mm_struct *mm, struct hugetlb_pte *hpte,
>  		goto retry;
>  	}
>  
> +	if (is_marker)
> +		hugetlb_install_markers_pte(page_address(new), marker);
> +
>  	mm_inc_nr_ptes(mm);
>  	smp_wmb(); /* See comment in pmd_install() */
>  	pmd_populate(mm, pmdp, new);
> @@ -7384,7 +7436,12 @@ static int __hugetlb_hgm_walk(struct mm_struct *mm, struct vm_area_struct *vma,
>  		if (!pte_present(pte)) {
>  			if (!alloc)
>  				return 0;
> -			if (unlikely(!huge_pte_none(pte)))
> +			/*
> +			 * In hugetlb_alloc_pmd and hugetlb_alloc_pte,
> +			 * we split PTE markers, so we can tolerate
> +			 * PTE markers here.
> +			 */
> +			if (unlikely(!huge_pte_none_mostly(pte)))
>  				return -EEXIST;
>  		} else if (hugetlb_pte_present_leaf(hpte, pte))
>  			return 0;
> -- 
> 2.39.2.637.g21b0678d19-goog
> 

  parent reply	other threads:[~2023-02-28 22:49 UTC|newest]

Thread overview: 96+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2023-02-18  0:27 [PATCH v2 00/46] hugetlb: introduce HugeTLB high-granularity mapping James Houghton
2023-02-18  0:27 ` [PATCH v2 01/46] hugetlb: don't set PageUptodate for UFFDIO_CONTINUE James Houghton
2023-02-18  0:41   ` Mina Almasry
2023-02-21 15:59     ` James Houghton
2023-02-21 19:33       ` Mike Kravetz
2023-02-21 19:58         ` James Houghton
2023-02-18  0:27 ` [PATCH v2 02/46] hugetlb: remove mk_huge_pte; it is unused James Houghton
2023-02-18  0:27 ` [PATCH v2 03/46] hugetlb: remove redundant pte_mkhuge in migration path James Houghton
2023-02-18  0:27 ` [PATCH v2 04/46] hugetlb: only adjust address ranges when VMAs want PMD sharing James Houghton
2023-02-18  1:10   ` Mina Almasry
2023-02-18  0:27 ` [PATCH v2 05/46] rmap: hugetlb: switch from page_dup_file_rmap to page_add_file_rmap James Houghton
2023-03-02  1:06   ` Jiaqi Yan
2023-03-02 15:44     ` James Houghton
2023-03-02 16:43       ` James Houghton
2023-03-02 19:22         ` Mike Kravetz
2023-02-18  0:27 ` [PATCH v2 06/46] hugetlb: add CONFIG_HUGETLB_HIGH_GRANULARITY_MAPPING James Houghton
2023-02-18  0:27 ` [PATCH v2 07/46] mm: add VM_HUGETLB_HGM VMA flag James Houghton
2023-02-24 22:35   ` Mike Kravetz
2023-02-18  0:27 ` [PATCH v2 08/46] hugetlb: add HugeTLB HGM enablement helpers James Houghton
2023-02-18  1:40   ` Mina Almasry
2023-02-21 16:16     ` James Houghton
2023-02-24 23:08   ` Mike Kravetz
2023-02-18  0:27 ` [PATCH v2 09/46] mm: add MADV_SPLIT to enable HugeTLB HGM James Houghton
2023-02-18  1:58   ` Mina Almasry
2023-02-21 16:33     ` James Houghton
2023-02-24 23:25   ` Mike Kravetz
2023-02-27 15:14     ` James Houghton
2023-02-18  0:27 ` [PATCH v2 10/46] hugetlb: make huge_pte_lockptr take an explicit shift argument James Houghton
2023-02-18  0:27 ` [PATCH v2 11/46] hugetlb: add hugetlb_pte to track HugeTLB page table entries James Houghton
2023-02-18  5:24   ` Mina Almasry
2023-02-21 16:36     ` James Houghton
2023-02-25  0:09   ` Mike Kravetz
2023-02-18  0:27 ` [PATCH v2 12/46] hugetlb: add hugetlb_alloc_pmd and hugetlb_alloc_pte James Houghton
2023-02-18 17:46   ` kernel test robot
2023-02-27 19:16   ` Mike Kravetz
2023-02-27 19:31     ` James Houghton
2023-02-18  0:27 ` [PATCH v2 13/46] hugetlb: add hugetlb_hgm_walk and hugetlb_walk_step James Houghton
2023-02-18  7:43   ` kernel test robot
2023-02-18 18:07   ` kernel test robot
2023-02-21 17:09     ` James Houghton
2023-02-28 22:14   ` Mike Kravetz
2023-02-28 23:03     ` James Houghton
2023-02-18  0:27 ` [PATCH v2 14/46] hugetlb: split PTE markers when doing HGM walks James Houghton
2023-02-18 19:49   ` kernel test robot
2023-02-28 22:48   ` Mike Kravetz [this message]
2023-02-18  0:27 ` [PATCH v2 15/46] hugetlb: add make_huge_pte_with_shift James Houghton
2023-02-22 21:14   ` Mina Almasry
2023-02-22 22:53     ` James Houghton
2023-02-18  0:27 ` [PATCH v2 16/46] hugetlb: make default arch_make_huge_pte understand small mappings James Houghton
2023-02-22 21:17   ` Mina Almasry
2023-02-22 22:52     ` James Houghton
2023-02-28 23:02   ` Mike Kravetz
2023-02-18  0:27 ` [PATCH v2 17/46] hugetlbfs: do a full walk to check if vma maps a page James Houghton
2023-02-22 15:46   ` James Houghton
2023-02-28 23:52     ` Mike Kravetz
2023-02-18  0:27 ` [PATCH v2 18/46] hugetlb: add HGM support to __unmap_hugepage_range James Houghton
2023-02-18  0:27 ` [PATCH v2 19/46] hugetlb: add HGM support to hugetlb_change_protection James Houghton
2023-02-18  0:27 ` [PATCH v2 20/46] hugetlb: add HGM support to follow_hugetlb_page James Houghton
2023-02-18  0:27 ` [PATCH v2 21/46] hugetlb: add HGM support to hugetlb_follow_page_mask James Houghton
2023-02-18  0:27 ` [PATCH v2 22/46] hugetlb: add HGM support to copy_hugetlb_page_range James Houghton
2023-02-24 17:39   ` James Houghton
2023-02-18  0:27 ` [PATCH v2 23/46] hugetlb: add HGM support to move_hugetlb_page_tables James Houghton
2023-02-18  0:27 ` [PATCH v2 24/46] hugetlb: add HGM support to hugetlb_fault and hugetlb_no_page James Houghton
2023-02-18  0:27 ` [PATCH v2 25/46] hugetlb: use struct hugetlb_pte for walk_hugetlb_range James Houghton
2023-02-18  0:27 ` [PATCH v2 26/46] mm: rmap: provide pte_order in page_vma_mapped_walk James Houghton
2023-02-18  0:28 ` [PATCH v2 27/46] mm: rmap: update try_to_{migrate,unmap} to handle mapcount for HGM James Houghton
2023-02-18  0:28 ` [PATCH v2 28/46] mm: rmap: in try_to_{migrate,unmap}, check head page for hugetlb page flags James Houghton
2023-02-18  0:28 ` [PATCH v2 29/46] hugetlb: update page_vma_mapped to do high-granularity walks James Houghton
2023-02-18  0:28 ` [PATCH v2 30/46] hugetlb: add high-granularity migration support James Houghton
2023-02-18  0:28 ` [PATCH v2 31/46] hugetlb: sort hstates in hugetlb_init_hstates James Houghton
2023-02-18  0:28 ` [PATCH v2 32/46] hugetlb: add for_each_hgm_shift James Houghton
2023-02-18  0:28 ` [PATCH v2 33/46] hugetlb: userfaultfd: add support for high-granularity UFFDIO_CONTINUE James Houghton
2023-02-18  0:28 ` [PATCH v2 34/46] hugetlb: add MADV_COLLAPSE for hugetlb James Houghton
2023-02-18  0:28 ` [PATCH v2 35/46] hugetlb: add check to prevent refcount overflow via HGM James Houghton
2023-02-24 17:42   ` James Houghton
2023-02-24 18:05     ` James Houghton
2023-02-18  0:28 ` [PATCH v2 36/46] hugetlb: remove huge_pte_lock and huge_pte_lockptr James Houghton
2023-02-18  0:28 ` [PATCH v2 37/46] hugetlb: replace make_huge_pte with make_huge_pte_with_shift James Houghton
2023-02-18  0:28 ` [PATCH v2 38/46] mm: smaps: add stats for HugeTLB mapping size James Houghton
2023-02-18  0:28 ` [PATCH v2 39/46] hugetlb: x86: enable high-granularity mapping for x86_64 James Houghton
2023-02-18  0:28 ` [PATCH v2 40/46] docs: hugetlb: update hugetlb and userfaultfd admin-guides with HGM info James Houghton
2023-02-18  0:28 ` [PATCH v2 41/46] docs: proc: include information about HugeTLB HGM James Houghton
2023-02-18  0:28 ` [PATCH v2 42/46] selftests/mm: add HugeTLB HGM to userfaultfd selftest James Houghton
2023-02-18  0:28 ` [PATCH v2 43/46] KVM: selftests: add HugeTLB HGM to KVM demand paging selftest James Houghton
2023-02-18  0:28 ` [PATCH v2 44/46] selftests/mm: add anon and shared hugetlb to migration test James Houghton
2023-02-18  0:28 ` [PATCH v2 45/46] selftests/mm: add hugetlb HGM test to migration selftest James Houghton
2023-02-18  0:28 ` [PATCH v2 46/46] selftests/mm: add HGM UFFDIO_CONTINUE and hwpoison tests James Houghton
2023-02-24 17:37   ` James Houghton
2023-02-21 21:46 ` [PATCH v2 00/46] hugetlb: introduce HugeTLB high-granularity mapping Mike Kravetz
2023-02-22 15:48   ` David Hildenbrand
2023-02-22 20:57     ` Mina Almasry
2023-02-23  9:07       ` David Hildenbrand
2023-02-23 15:53         ` James Houghton
2023-02-23 16:17           ` David Hildenbrand
2023-02-23 18:33             ` Dr. David Alan Gilbert
2023-02-23 18:25           ` Mike Kravetz

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=Y/6EsomcdMDl8Ffh@monkey \
    --to=mike.kravetz@oracle.com \
    --cc=akpm@linux-foundation.org \
    --cc=almasrymina@google.com \
    --cc=axelrasmussen@google.com \
    --cc=baolin.wang@linux.alibaba.com \
    --cc=david@redhat.com \
    --cc=dgilbert@redhat.com \
    --cc=fvdl@google.com \
    --cc=jiaqiyan@google.com \
    --cc=jthoughton@google.com \
    --cc=linmiaohe@huawei.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=manish.mishra@nutanix.com \
    --cc=naoya.horiguchi@nec.com \
    --cc=peterx@redhat.com \
    --cc=rientjes@google.com \
    --cc=shy828301@gmail.com \
    --cc=songmuchun@bytedance.com \
    --cc=vbabka@suse.cz \
    --cc=willy@infradead.org \
    --cc=zokeefe@google.com \
    /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).