public inbox for linuxppc-dev@ozlabs.org 
 help / color / mirror / Atom feed
From: Usama Arif <usama.arif@linux•dev>
To: Muchun Song <songmuchun@bytedance•com>
Cc: Usama Arif <usama.arif@linux•dev>,
	Oscar Salvador <osalvador@suse•de>,
	David Hildenbrand <david@kernel•org>,
	Andrew Morton <akpm@linux-foundation•org>,
	Madhavan Srinivasan <maddy@linux•ibm.com>,
	Michael Ellerman <mpe@ellerman•id.au>,
	Muchun Song <muchun.song@linux•dev>,
	Mike Rapoport <rppt@kernel•org>, Lorenzo Stoakes <ljs@kernel•org>,
	"Liam R. Howlett" <liam@infradead•org>,
	Vlastimil Babka <vbabka@kernel•org>,
	linux-mm@kvack•org, linux-kernel@vger•kernel.org,
	Nicholas Piggin <npiggin@gmail•com>,
	"Christophe Leroy (CS GROUP)" <chleroy@kernel•org>,
	"Ritesh Harjani (IBM)" <ritesh.list@gmail•com>,
	"Aneesh Kumar K.V" <aneesh.kumar@linux•ibm.com>,
	linuxppc-dev@lists•ozlabs.org,
	Mike Kravetz <mike.kravetz@oracle•com>
Subject: Re: [PATCH v3 15/19] mm/hugetlb_vmemmap: Move bootmem HVO setup to early init
Date: Wed,  3 Jun 2026 05:02:44 -0700	[thread overview]
Message-ID: <20260603120246.1572177-1-usama.arif@linux.dev> (raw)
In-Reply-To: <20260602101039.1867613-16-songmuchun@bytedance.com>

On Tue,  2 Jun 2026 18:10:35 +0800 Muchun Song <songmuchun@bytedance•com> wrote:

> Bootmem HugeTLB pages currently defer HVO setup to
> hugetlb_vmemmap_init_late(), because the optimization needs zone
> information.
> 
> Now that zone initialization is available earlier, the bootmem HVO setup
> can be done directly from hugetlb_vmemmap_init_early(). This lets
> gigantic HugeTLB pages apply HVO as soon as they are allocated.
> 
> Bootmem gigantic pages that span multiple zones are now filtered out
> when they are allocated, so the remaining bootmem gigantic pages seen by
> later hugetlb initialization are already zone-valid. As a result,
> hugetlb_vmemmap_init_late() no longer needs to handle bootmem HVO setup.
> 
> Signed-off-by: Muchun Song <songmuchun@bytedance•com>
> ---
>  mm/hugetlb_vmemmap.c | 67 +++++++++-----------------------------------
>  1 file changed, 13 insertions(+), 54 deletions(-)
> 
> diff --git a/mm/hugetlb_vmemmap.c b/mm/hugetlb_vmemmap.c
> index ea6af85bfec1..464578ee246e 100644
> --- a/mm/hugetlb_vmemmap.c
> +++ b/mm/hugetlb_vmemmap.c
> @@ -745,6 +745,8 @@ static bool vmemmap_should_optimize_bootmem_page(struct huge_bootmem_page *m)
>  	return true;
>  }
>  
> +static struct zone *pfn_to_zone(unsigned nid, unsigned long pfn);
> +
>  /*
>   * Initialize memmap section for a gigantic page, HVO-style.
>   */
> @@ -752,6 +754,7 @@ void __init hugetlb_vmemmap_init_early(int nid)
>  {
>  	unsigned long psize, paddr, section_size;
>  	unsigned long ns, i, pnum, pfn, nr_pages;
> +	unsigned long start, end;
>  	struct huge_bootmem_page *m = NULL;
>  	void *map;
>  
> @@ -761,6 +764,8 @@ void __init hugetlb_vmemmap_init_early(int nid)
>  	section_size = (1UL << PA_SECTION_SHIFT);
>  
>  	list_for_each_entry(m, &huge_boot_pages[nid], list) {
> +		struct zone *zone;
> +
>  		if (!vmemmap_should_optimize_bootmem_page(m))
>  			continue;
>  
> @@ -769,6 +774,14 @@ void __init hugetlb_vmemmap_init_early(int nid)
>  		paddr = virt_to_phys(m);
>  		pfn = PHYS_PFN(paddr);
>  		map = pfn_to_page(pfn);
> +		start = (unsigned long)map;
> +		end = start + hugetlb_vmemmap_size(m->hstate);
> +		zone = pfn_to_zone(nid, pfn);
> +
> +		if (vmemmap_populate_hvo(start, end, huge_page_order(m->hstate),
> +					 zone, HUGETLB_VMEMMAP_RESERVE_SIZE))
> +			panic("Failed to allocate memmap for HugeTLB page\n");

The replaced hugetlb_vmemmap_init_late() path used to fall back to
vmemmap_populate() if vmemmap_populate_hvo() returned an error and
just lost the HVO optimization for that page.

The new path panics on any non-zero return.  Is the panic intended,
given that vmemmap_populate_hvo() returns -ENOMEM on allocation
failure and HVO is normally treated as an optimization rather than a
hard requirement?

> +		memmap_boot_pages_add(DIV_ROUND_UP(HUGETLB_VMEMMAP_RESERVE_SIZE, PAGE_SIZE));
>  
>  		pnum = pfn_to_section_nr(pfn);
>  		ns = psize / section_size;
> @@ -800,60 +813,6 @@ static struct zone *pfn_to_zone(unsigned nid, unsigned long pfn)
>  
>  void __init hugetlb_vmemmap_init_late(int nid)
>  {
> -	struct huge_bootmem_page *m, *tm;
> -	unsigned long phys, nr_pages, start, end;
> -	unsigned long pfn, nr_mmap;
> -	struct zone *zone = NULL;
> -	struct hstate *h;
> -	void *map;
> -
> -	if (!READ_ONCE(vmemmap_optimize_enabled))
> -		return;
> -
> -	list_for_each_entry_safe(m, tm, &huge_boot_pages[nid], list) {
> -		if (!(m->flags & HUGE_BOOTMEM_HVO))
> -			continue;
> -
> -		phys = virt_to_phys(m);
> -		h = m->hstate;
> -		pfn = PHYS_PFN(phys);
> -		nr_pages = pages_per_huge_page(h);
> -		map = pfn_to_page(pfn);
> -		start = (unsigned long)map;
> -		end = start + nr_pages * sizeof(struct page);
> -
> -		if (!hugetlb_bootmem_page_zones_valid(nid, m)) {
> -			/*
> -			 * Oops, the hugetlb page spans multiple zones.
> -			 * Remove it from the list, and populate it normally.
> -			 */
> -			list_del(&m->list);
> -
> -			vmemmap_populate(start, end, nid, NULL);
> -			nr_mmap = end - start;
> -			memmap_boot_pages_add(DIV_ROUND_UP(nr_mmap, PAGE_SIZE));
> -
> -			memblock_phys_free(phys, huge_page_size(h));
> -			continue;
> -		}
> -
> -		if (!zone || !zone_spans_pfn(zone, pfn))
> -			zone = pfn_to_zone(nid, pfn);
> -		if (WARN_ON_ONCE(!zone))
> -			continue;
> -
> -		if (vmemmap_populate_hvo(start, end, huge_page_order(h), zone,
> -					 HUGETLB_VMEMMAP_RESERVE_SIZE) < 0) {
> -			/* Fallback if HVO population fails */
> -			vmemmap_populate(start, end, nid, NULL);
> -			nr_mmap = end - start;
> -		} else {
> -			m->flags |= HUGE_BOOTMEM_ZONES_VALID;
> -			nr_mmap = HUGETLB_VMEMMAP_RESERVE_SIZE;
> -		}
> -
> -		memmap_boot_pages_add(DIV_ROUND_UP(nr_mmap, PAGE_SIZE));
> -	}
>  }
>  #endif
>  
> -- 
> 2.54.0
> 
> 


  parent reply	other threads:[~2026-06-03 12:03 UTC|newest]

Thread overview: 38+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-06-02 10:10 [PATCH v3 00/19] mm: Refactor bootmem gigantic hugepage allocation Muchun Song
2026-06-02 10:10 ` [PATCH v3 01/19] mm/hugetlb: Fix boot panic with CONFIG_DEBUG_VM and HVO bootmem pages Muchun Song
2026-06-02 10:10 ` [PATCH v3 02/19] mm/hugetlb_vmemmap: Fix __hugetlb_vmemmap_optimize_folios() Muchun Song
2026-06-02 10:10 ` [PATCH v3 03/19] powerpc/mm: Fix wrong addr_pfn tracking in compound vmemmap population Muchun Song
2026-06-03 14:36   ` Ritesh Harjani
2026-06-04  2:09     ` Muchun Song
2026-06-02 10:10 ` [PATCH v3 04/19] mm/hugetlb: Initialize gigantic bootmem hugepage struct pages earlier Muchun Song
2026-06-02 10:10 ` [PATCH v3 05/19] mm/mm_init: Simplify deferred_free_pages() migratetype init Muchun Song
2026-06-02 10:10 ` [PATCH v3 06/19] mm/sparse: Panic on memmap and usemap allocation failure Muchun Song
2026-06-02 10:10 ` [PATCH v3 07/19] mm/sparse: Move subsection_map_init() into sparse_init() Muchun Song
2026-06-02 10:10 ` [PATCH v3 08/19] mm/mm_init: Defer sparse_init() until after zone initialization Muchun Song
2026-06-02 10:10 ` [PATCH v3 09/19] mm/mm_init: Defer hugetlb reservation " Muchun Song
2026-06-02 10:10 ` [PATCH v3 10/19] mm/mm_init: Remove set_pageblock_order() call from sparse_init() Muchun Song
2026-06-02 10:10 ` [PATCH v3 11/19] mm/sparse: Move sparse_vmemmap_init_nid_late() into sparse_init_nid() Muchun Song
2026-06-02 10:10 ` [PATCH v3 12/19] mm/hugetlb_cma: Validate hugetlb CMA range by zone at reserve time Muchun Song
2026-06-02 10:10 ` [PATCH v3 13/19] mm/hugetlb: Refactor early boot gigantic hugepage allocation Muchun Song
2026-06-02 10:10 ` [PATCH v3 14/19] mm/hugetlb: Free cross-zone bootmem gigantic pages after allocation Muchun Song
2026-06-02 15:41   ` Mike Rapoport
2026-06-03  2:53     ` Muchun Song
2026-06-02 10:10 ` [PATCH v3 15/19] mm/hugetlb_vmemmap: Move bootmem HVO setup to early init Muchun Song
2026-06-02 15:41   ` Mike Rapoport
2026-06-03  2:42     ` Muchun Song
2026-06-03 12:02   ` Usama Arif [this message]
2026-06-03 12:24     ` Muchun Song
2026-06-03 12:35       ` Usama Arif
2026-06-02 10:10 ` [PATCH v3 16/19] mm/hugetlb: Remove obsolete bootmem cross-zone checks Muchun Song
2026-06-02 15:41   ` Mike Rapoport
2026-06-02 10:10 ` [PATCH v3 17/19] mm/sparse-vmemmap: Remove sparse_vmemmap_init_nid_late() Muchun Song
2026-06-02 15:41   ` Mike Rapoport
2026-06-02 10:10 ` [PATCH v3 18/19] mm/hugetlb: Remove unused bootmem cma field Muchun Song
2026-06-02 15:41   ` Mike Rapoport
2026-06-03  2:41     ` Muchun Song
2026-06-02 10:10 ` [PATCH v3 19/19] mm/mm_init: Fold __init_page_from_nid() into __init_deferred_page() Muchun Song
2026-06-02 14:46   ` Mike Rapoport
2026-06-02 15:41   ` Mike Rapoport
2026-06-03  2:39     ` Muchun Song
2026-06-02 10:34 ` [PATCH v3 00/19] mm: Refactor bootmem gigantic hugepage allocation Oscar Salvador (SUSE)
2026-06-02 12:01   ` 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=20260603120246.1572177-1-usama.arif@linux.dev \
    --to=usama.arif@linux$(echo .)dev \
    --cc=akpm@linux-foundation$(echo .)org \
    --cc=aneesh.kumar@linux$(echo .)ibm.com \
    --cc=chleroy@kernel$(echo .)org \
    --cc=david@kernel$(echo .)org \
    --cc=liam@infradead$(echo .)org \
    --cc=linux-kernel@vger$(echo .)kernel.org \
    --cc=linux-mm@kvack$(echo .)org \
    --cc=linuxppc-dev@lists$(echo .)ozlabs.org \
    --cc=ljs@kernel$(echo .)org \
    --cc=maddy@linux$(echo .)ibm.com \
    --cc=mike.kravetz@oracle$(echo .)com \
    --cc=mpe@ellerman$(echo .)id.au \
    --cc=muchun.song@linux$(echo .)dev \
    --cc=npiggin@gmail$(echo .)com \
    --cc=osalvador@suse$(echo .)de \
    --cc=ritesh.list@gmail$(echo .)com \
    --cc=rppt@kernel$(echo .)org \
    --cc=songmuchun@bytedance$(echo .)com \
    --cc=vbabka@kernel$(echo .)org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html
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