From: "manish.mishra" <manish.mishra@nutanix.com>
To: James Houghton <jthoughton@google.com>,
Mike Kravetz <mike.kravetz@oracle.com>,
Muchun Song <songmuchun@bytedance.com>,
Peter Xu <peterx@redhat.com>
Cc: David Hildenbrand <david@redhat.com>,
David Rientjes <rientjes@google.com>,
Axel Rasmussen <axelrasmussen@google.com>,
Mina Almasry <almasrymina@google.com>, Jue Wang <juew@google.com>,
"Dr . David Alan Gilbert" <dgilbert@redhat.com>,
linux-mm@kvack.org, linux-kernel@vger.kernel.org
Subject: Re: [RFC PATCH 04/26] hugetlb: make huge_pte_lockptr take an explicit shift argument.
Date: Mon, 27 Jun 2022 17:56:51 +0530 [thread overview]
Message-ID: <cbdd91ba-bfd4-2f6d-9f9f-9cdcc8ff81a4@nutanix.com> (raw)
In-Reply-To: <20220624173656.2033256-5-jthoughton@google.com>
On 24/06/22 11:06 pm, James Houghton wrote:
> This is needed to handle PTL locking with high-granularity mapping. We
> won't always be using the PMD-level PTL even if we're using the 2M
> hugepage hstate. It's possible that we're dealing with 4K PTEs, in which
> case, we need to lock the PTL for the 4K PTE.
>
> Signed-off-by: James Houghton <jthoughton@google.com>
> ---
> arch/powerpc/mm/pgtable.c | 3 ++-
> include/linux/hugetlb.h | 19 ++++++++++++++-----
> mm/hugetlb.c | 9 +++++----
> mm/migrate.c | 3 ++-
> mm/page_vma_mapped.c | 3 ++-
> 5 files changed, 25 insertions(+), 12 deletions(-)
>
> diff --git a/arch/powerpc/mm/pgtable.c b/arch/powerpc/mm/pgtable.c
> index e6166b71d36d..663d591a8f08 100644
> --- a/arch/powerpc/mm/pgtable.c
> +++ b/arch/powerpc/mm/pgtable.c
> @@ -261,7 +261,8 @@ int huge_ptep_set_access_flags(struct vm_area_struct *vma,
>
> psize = hstate_get_psize(h);
> #ifdef CONFIG_DEBUG_VM
> - assert_spin_locked(huge_pte_lockptr(h, vma->vm_mm, ptep));
> + assert_spin_locked(huge_pte_lockptr(huge_page_shift(h),
> + vma->vm_mm, ptep));
> #endif
>
> #else
> diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
> index 498a4ae3d462..5fe1db46d8c9 100644
> --- a/include/linux/hugetlb.h
> +++ b/include/linux/hugetlb.h
> @@ -868,12 +868,11 @@ static inline gfp_t htlb_modify_alloc_mask(struct hstate *h, gfp_t gfp_mask)
> return modified_mask;
> }
>
> -static inline spinlock_t *huge_pte_lockptr(struct hstate *h,
> +static inline spinlock_t *huge_pte_lockptr(unsigned int shift,
> struct mm_struct *mm, pte_t *pte)
> {
> - if (huge_page_size(h) == PMD_SIZE)
> + if (shift == PMD_SHIFT)
> return pmd_lockptr(mm, (pmd_t *) pte);
> - VM_BUG_ON(huge_page_size(h) == PAGE_SIZE);
I may have wrong understanding here, is per pmd lock for reducing
contention, if that is the case should be take per pmd lock of
PAGE_SIZE too and page_table_lock for anything higer than PMD.
> return &mm->page_table_lock;
> }
>
> @@ -1076,7 +1075,7 @@ static inline gfp_t htlb_modify_alloc_mask(struct hstate *h, gfp_t gfp_mask)
> return 0;
> }
>
> -static inline spinlock_t *huge_pte_lockptr(struct hstate *h,
> +static inline spinlock_t *huge_pte_lockptr(unsigned int shift,
> struct mm_struct *mm, pte_t *pte)
> {
> return &mm->page_table_lock;
> @@ -1116,7 +1115,17 @@ static inline spinlock_t *huge_pte_lock(struct hstate *h,
> {
> spinlock_t *ptl;
>
> - ptl = huge_pte_lockptr(h, mm, pte);
> + ptl = huge_pte_lockptr(huge_page_shift(h), mm, pte);
> + spin_lock(ptl);
> + return ptl;
> +}
> +
> +static inline spinlock_t *huge_pte_lock_shift(unsigned int shift,
> + struct mm_struct *mm, pte_t *pte)
> +{
> + spinlock_t *ptl;
> +
> + ptl = huge_pte_lockptr(shift, mm, pte);
> spin_lock(ptl);
> return ptl;
> }
> diff --git a/mm/hugetlb.c b/mm/hugetlb.c
> index 0eec34edf3b2..d6d0d4c03def 100644
> --- a/mm/hugetlb.c
> +++ b/mm/hugetlb.c
> @@ -4817,7 +4817,7 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
> continue;
>
> dst_ptl = huge_pte_lock(h, dst, dst_pte);
> - src_ptl = huge_pte_lockptr(h, src, src_pte);
> + src_ptl = huge_pte_lockptr(huge_page_shift(h), src, src_pte);
> spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING);
> entry = huge_ptep_get(src_pte);
> dst_entry = huge_ptep_get(dst_pte);
> @@ -4894,7 +4894,8 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
>
> /* Install the new huge page if src pte stable */
> dst_ptl = huge_pte_lock(h, dst, dst_pte);
> - src_ptl = huge_pte_lockptr(h, src, src_pte);
> + src_ptl = huge_pte_lockptr(huge_page_shift(h),
> + src, src_pte);
> spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING);
> entry = huge_ptep_get(src_pte);
> if (!pte_same(src_pte_old, entry)) {
> @@ -4948,7 +4949,7 @@ static void move_huge_pte(struct vm_area_struct *vma, unsigned long old_addr,
> pte_t pte;
>
> dst_ptl = huge_pte_lock(h, mm, dst_pte);
> - src_ptl = huge_pte_lockptr(h, mm, src_pte);
> + src_ptl = huge_pte_lockptr(huge_page_shift(h), mm, src_pte);
>
> /*
> * We don't have to worry about the ordering of src and dst ptlocks
> @@ -6024,7 +6025,7 @@ int hugetlb_mcopy_atomic_pte(struct mm_struct *dst_mm,
> page_in_pagecache = true;
> }
>
> - ptl = huge_pte_lockptr(h, dst_mm, dst_pte);
> + ptl = huge_pte_lockptr(huge_page_shift(h), dst_mm, dst_pte);
> spin_lock(ptl);
>
> /*
> diff --git a/mm/migrate.c b/mm/migrate.c
> index e51588e95f57..a8a960992373 100644
> --- a/mm/migrate.c
> +++ b/mm/migrate.c
> @@ -318,7 +318,8 @@ void migration_entry_wait(struct mm_struct *mm, pmd_t *pmd,
> void migration_entry_wait_huge(struct vm_area_struct *vma,
> struct mm_struct *mm, pte_t *pte)
> {
> - spinlock_t *ptl = huge_pte_lockptr(hstate_vma(vma), mm, pte);
> + spinlock_t *ptl = huge_pte_lockptr(huge_page_shift(hstate_vma(vma)),
> + mm, pte);
> __migration_entry_wait(mm, pte, ptl);
> }
>
> diff --git a/mm/page_vma_mapped.c b/mm/page_vma_mapped.c
> index c10f839fc410..8921dd4e41b1 100644
> --- a/mm/page_vma_mapped.c
> +++ b/mm/page_vma_mapped.c
> @@ -174,7 +174,8 @@ bool page_vma_mapped_walk(struct page_vma_mapped_walk *pvmw)
> if (!pvmw->pte)
> return false;
>
> - pvmw->ptl = huge_pte_lockptr(hstate, mm, pvmw->pte);
> + pvmw->ptl = huge_pte_lockptr(huge_page_shift(hstate),
> + mm, pvmw->pte);
> spin_lock(pvmw->ptl);
> if (!check_pte(pvmw))
> return not_found(pvmw);
next prev parent reply other threads:[~2022-06-27 12:27 UTC|newest]
Thread overview: 123+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-06-24 17:36 [RFC PATCH 00/26] hugetlb: Introduce HugeTLB high-granularity mapping James Houghton
2022-06-24 17:36 ` [RFC PATCH 01/26] hugetlb: make hstate accessor functions const James Houghton
2022-06-24 18:43 ` Mina Almasry
[not found] ` <e55f90f5-ba14-5d6e-8f8f-abf731b9095e@nutanix.com>
[not found] ` <bb903be9-546d-04a7-e9e4-f5ba313319de@nutanix.com>
2022-06-28 17:08 ` James Houghton
2022-06-29 6:18 ` Muchun Song
2022-06-24 17:36 ` [RFC PATCH 02/26] hugetlb: sort hstates in hugetlb_init_hstates James Houghton
2022-06-24 18:51 ` Mina Almasry
2022-06-27 12:08 ` manish.mishra
2022-06-28 15:35 ` James Houghton
2022-06-27 18:42 ` Mike Kravetz
2022-06-28 15:40 ` James Houghton
2022-06-29 6:39 ` Muchun Song
2022-06-29 21:06 ` Mike Kravetz
2022-06-29 21:13 ` James Houghton
2022-06-24 17:36 ` [RFC PATCH 03/26] hugetlb: add make_huge_pte_with_shift James Houghton
2022-06-24 19:01 ` Mina Almasry
2022-06-27 12:13 ` manish.mishra
2022-06-24 17:36 ` [RFC PATCH 04/26] hugetlb: make huge_pte_lockptr take an explicit shift argument James Houghton
2022-06-27 12:26 ` manish.mishra [this message]
2022-06-27 20:51 ` Mike Kravetz
2022-06-28 15:29 ` James Houghton
2022-06-29 6:09 ` Muchun Song
2022-06-29 21:03 ` Mike Kravetz
2022-06-29 21:39 ` James Houghton
2022-06-29 22:24 ` Mike Kravetz
2022-06-30 9:35 ` Muchun Song
2022-06-30 16:23 ` James Houghton
2022-06-30 17:40 ` Mike Kravetz
2022-07-01 3:32 ` Muchun Song
2022-06-24 17:36 ` [RFC PATCH 05/26] hugetlb: add CONFIG_HUGETLB_HIGH_GRANULARITY_MAPPING James Houghton
2022-06-27 12:28 ` manish.mishra
2022-06-28 20:03 ` Mina Almasry
2022-06-24 17:36 ` [RFC PATCH 06/26] mm: make free_p?d_range functions public James Houghton
2022-06-27 12:31 ` manish.mishra
2022-06-28 20:35 ` Mike Kravetz
2022-07-12 20:52 ` James Houghton
2022-06-24 17:36 ` [RFC PATCH 07/26] hugetlb: add hugetlb_pte to track HugeTLB page table entries James Houghton
2022-06-27 12:47 ` manish.mishra
2022-06-29 16:28 ` James Houghton
2022-06-28 20:25 ` Mina Almasry
2022-06-29 16:42 ` James Houghton
2022-06-28 20:44 ` Mike Kravetz
2022-06-29 16:24 ` James Houghton
2022-07-11 23:32 ` Mike Kravetz
2022-07-12 9:42 ` Dr. David Alan Gilbert
2022-07-12 17:51 ` Mike Kravetz
2022-07-15 16:35 ` Peter Xu
2022-07-15 21:52 ` Axel Rasmussen
2022-07-15 23:03 ` Peter Xu
2022-09-08 17:38 ` Peter Xu
2022-09-08 17:54 ` James Houghton
2022-06-24 17:36 ` [RFC PATCH 08/26] hugetlb: add hugetlb_free_range to free PT structures James Houghton
2022-06-27 12:52 ` manish.mishra
2022-06-28 20:27 ` Mina Almasry
2022-06-24 17:36 ` [RFC PATCH 09/26] hugetlb: add hugetlb_hgm_enabled James Houghton
2022-06-28 20:33 ` Mina Almasry
2022-09-08 18:07 ` Peter Xu
2022-09-08 18:13 ` James Houghton
2022-06-24 17:36 ` [RFC PATCH 10/26] hugetlb: add for_each_hgm_shift James Houghton
2022-06-27 13:01 ` manish.mishra
2022-06-28 21:58 ` Mina Almasry
2022-07-07 21:39 ` Mike Kravetz
2022-07-08 15:52 ` James Houghton
2022-07-09 21:55 ` Mina Almasry
2022-06-24 17:36 ` [RFC PATCH 11/26] hugetlb: add hugetlb_walk_to to do PT walks James Houghton
2022-06-27 13:07 ` manish.mishra
2022-07-07 23:03 ` Mike Kravetz
2022-09-08 18:20 ` Peter Xu
2022-06-24 17:36 ` [RFC PATCH 12/26] hugetlb: add HugeTLB splitting functionality James Houghton
2022-06-27 13:50 ` manish.mishra
2022-06-29 16:10 ` James Houghton
2022-06-29 14:33 ` manish.mishra
2022-06-29 16:20 ` James Houghton
2022-06-24 17:36 ` [RFC PATCH 13/26] hugetlb: add huge_pte_alloc_high_granularity James Houghton
2022-06-29 14:11 ` manish.mishra
2022-06-24 17:36 ` [RFC PATCH 14/26] hugetlb: add HGM support for hugetlb_fault and hugetlb_no_page James Houghton
2022-06-29 14:40 ` manish.mishra
2022-06-29 15:56 ` James Houghton
2022-06-24 17:36 ` [RFC PATCH 15/26] hugetlb: make unmapping compatible with high-granularity mappings James Houghton
2022-07-19 10:19 ` manish.mishra
2022-07-19 15:58 ` James Houghton
2022-06-24 17:36 ` [RFC PATCH 16/26] hugetlb: make hugetlb_change_protection compatible with HGM James Houghton
2022-06-24 17:36 ` [RFC PATCH 17/26] hugetlb: update follow_hugetlb_page to support HGM James Houghton
2022-07-19 10:48 ` manish.mishra
2022-07-19 16:19 ` James Houghton
2022-06-24 17:36 ` [RFC PATCH 18/26] hugetlb: use struct hugetlb_pte for walk_hugetlb_range James Houghton
2022-06-24 17:36 ` [RFC PATCH 19/26] hugetlb: add HGM support for copy_hugetlb_page_range James Houghton
2022-07-11 23:41 ` Mike Kravetz
2022-07-12 17:19 ` James Houghton
2022-07-12 18:06 ` Mike Kravetz
2022-07-15 21:39 ` Axel Rasmussen
2022-06-24 17:36 ` [RFC PATCH 20/26] hugetlb: add support for high-granularity UFFDIO_CONTINUE James Houghton
2022-07-15 16:21 ` Peter Xu
2022-07-15 16:58 ` James Houghton
2022-07-15 17:20 ` Peter Xu
2022-07-20 20:58 ` James Houghton
2022-07-21 19:09 ` Peter Xu
2022-07-21 19:44 ` James Houghton
2022-07-21 19:53 ` Peter Xu
2022-06-24 17:36 ` [RFC PATCH 21/26] hugetlb: add hugetlb_collapse James Houghton
2022-06-24 17:36 ` [RFC PATCH 22/26] madvise: add uapi for HugeTLB HGM collapse: MADV_COLLAPSE James Houghton
2022-06-24 17:36 ` [RFC PATCH 23/26] userfaultfd: add UFFD_FEATURE_MINOR_HUGETLBFS_HGM James Houghton
2022-06-24 17:36 ` [RFC PATCH 24/26] arm64/hugetlb: add support for high-granularity mappings James Houghton
2022-06-24 17:36 ` [RFC PATCH 25/26] selftests: add HugeTLB HGM to userfaultfd selftest James Houghton
2022-06-24 17:36 ` [RFC PATCH 26/26] selftests: add HugeTLB HGM to KVM demand paging selftest James Houghton
2022-06-24 18:29 ` [RFC PATCH 00/26] hugetlb: Introduce HugeTLB high-granularity mapping Matthew Wilcox
2022-06-27 16:36 ` James Houghton
2022-06-27 17:56 ` Dr. David Alan Gilbert
2022-06-27 20:31 ` James Houghton
2022-06-28 0:04 ` Nadav Amit
2022-06-30 19:21 ` Peter Xu
2022-07-01 5:54 ` Nadav Amit
2022-06-28 8:20 ` Dr. David Alan Gilbert
2022-06-30 16:09 ` Peter Xu
2022-06-24 18:41 ` Mina Almasry
2022-06-27 16:27 ` James Houghton
2022-06-28 14:17 ` Muchun Song
2022-06-28 17:26 ` Mina Almasry
2022-06-28 17:56 ` Dr. David Alan Gilbert
2022-06-29 18:31 ` James Houghton
2022-06-29 20:39 ` Axel Rasmussen
2022-06-24 18:47 ` Matthew Wilcox
2022-06-27 16:48 ` James Houghton
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=cbdd91ba-bfd4-2f6d-9f9f-9cdcc8ff81a4@nutanix.com \
--to=manish.mishra@nutanix.com \
--cc=almasrymina@google.com \
--cc=axelrasmussen@google.com \
--cc=david@redhat.com \
--cc=dgilbert@redhat.com \
--cc=jthoughton@google.com \
--cc=juew@google.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=mike.kravetz@oracle.com \
--cc=peterx@redhat.com \
--cc=rientjes@google.com \
--cc=songmuchun@bytedance.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).