public inbox for linux-arm-kernel@lists.infradead.org 
 help / color / mirror / Atom feed
From: Dev Jain <dev.jain@arm•com>
To: Wen Jiang <jiangwenxiaomi@gmail•com>,
	linux-mm@kvack•org, linux-arm-kernel@lists•infradead.org,
	catalin.marinas@arm•com, will@kernel•org,
	akpm@linux-foundation•org, urezki@gmail•com
Cc: baohua@kernel•org, Xueyuan.chen21@gmail•com, rppt@kernel•org,
	david@kernel•org, ryan.roberts@arm•com,
	anshuman.khandual@arm•com, ajd@linux•ibm.com,
	linux-kernel@vger•kernel.org, jiangwen6@xiaomi•com
Subject: Re: [PATCH v3 5/6] mm/vmalloc: map contiguous pages in batches for vmap() if possible
Date: Wed, 27 May 2026 13:57:54 +0530	[thread overview]
Message-ID: <340c811e-2501-46c3-8a55-19e955c5ae8a@arm.com> (raw)
In-Reply-To: <20260522053146.83209-6-jiangwenxiaomi@gmail.com>



On 22/05/26 11:01 am, Wen Jiang wrote:
> From: "Barry Song (Xiaomi)" <baohua@kernel•org>
> 
> In many cases, the pages passed to vmap() may include high-order
> pages. For example, the systemheap often allocates pages in descending
> order: order 8, then 4, then 0. Currently, vmap() iterates over every
> page individually—even pages inside a high-order block are handled
> one by one.
> 
> This patch detects physically contiguous pages (regardless of whether
> they are compound or non-compound) by scanning with
> num_pages_contiguous(), and maps them as a single contiguous block
> whenever possible. The first page's pfn must be aligned to the
> mapping order for the batched mapping to be used.
> 
> Pages with the same page_shift are coalesced and mapped via
> vmap_pages_range_noflush_walk() to avoid page table rewalk.
> 
> As users typically allocate memory in descending orders (e.g.
> 8 → 4 → 0), once an order-0 page is encountered, we stop scanning
> for contiguous pages since subsequent pages are likely order-0 as well.
> 
> Signed-off-by: Barry Song (Xiaomi) <baohua@kernel•org>
> Co-developed-by: Dev Jain <dev.jain@arm•com>
> Signed-off-by: Dev Jain <dev.jain@arm•com>
> Signed-off-by: Wen Jiang <jiangwen6@xiaomi•com>
> Tested-by: Xueyuan Chen <xueyuan.chen21@gmail•com>
> ---
>  mm/vmalloc.c | 82 ++++++++++++++++++++++++++++++++++++++++++++++++++--
>  1 file changed, 80 insertions(+), 2 deletions(-)
> 
> diff --git a/mm/vmalloc.c b/mm/vmalloc.c
> index deb764abc0571..50642246f4d40 100644
> --- a/mm/vmalloc.c
> +++ b/mm/vmalloc.c
> @@ -3542,6 +3542,84 @@ void vunmap(const void *addr)
>  }
>  EXPORT_SYMBOL(vunmap);
>  
> +static inline int get_vmap_batch_order(struct page **pages,
> +		unsigned int max_steps, unsigned int idx)
> +{
> +	unsigned int nr_contig;
> +	int order;
> +
> +	if (!IS_ENABLED(CONFIG_HAVE_ARCH_HUGE_VMAP) ||
> +			ioremap_max_page_shift == PAGE_SHIFT)


Why bail out on ioremap_max_page_shift == PAGE_SHIFT? The code
path for ioremap is different from vmap right?


> +		return 0;
> +
> +	nr_contig = num_pages_contiguous(&pages[idx], max_steps);
> +	if (nr_contig < 2)
> +		return 0;
> +
> +	order = fls(nr_contig) - 1;
> +
> +	if (arch_vmap_pte_supported_shift(PAGE_SIZE << order) == PAGE_SHIFT)
> +		return 0;
> +
> +	/* Ensure the first page's pfn is aligned to the order */
> +	if (!IS_ALIGNED(page_to_pfn(pages[idx]), 1 << order))
> +		return 0;
> +
> +	return order;
> +}
> +
> +static int vmap_batched(unsigned long addr, unsigned long end,
> +		pgprot_t prot, struct page **pages)
> +{
> +	unsigned int count = (end - addr) >> PAGE_SHIFT;
> +	unsigned int prev_shift = 0, idx = 0;
> +	unsigned long start = addr, map_addr = addr;
> +	int err;
> +
> +	err = kmsan_vmap_pages_range_noflush(addr, end, prot, pages,
> +						PAGE_SHIFT, GFP_KERNEL);
> +	if (err)
> +		goto out;
> +
> +	for (unsigned int i = 0; i < count; ) {
> +		unsigned int shift = PAGE_SHIFT +
> +			get_vmap_batch_order(pages, count - i, i);
> +
> +		if (!i)
> +			prev_shift = shift;
> +
> +		if (shift != prev_shift) {
> +			err = vmap_pages_range_noflush_walk(map_addr, addr,

It would be worth documenting vmap_pages_range_noflush_walk() that
it can take an array of pages which are not all contiguous, but it
may have contiguous chunks, as hinted by page_shift.

Otherwise this looks good.

> +					prot, pages + idx,
> +					min(prev_shift, PMD_SHIFT));
> +			if (err)
> +				goto out;
> +			prev_shift = shift;
> +			map_addr = addr;
> +			idx = i;
> +		}
> +
> +		/*
> +		 * Once small pages are encountered, the remaining pages
> +		 * are likely small as well.
> +		 */
> +		if (shift == PAGE_SHIFT)
> +			break;
> +
> +		addr += 1UL << shift;
> +		i += 1U << (shift - PAGE_SHIFT);
> +	}
> +
> +	/* Remaining */
> +	if (map_addr < end)
> +		err = vmap_pages_range_noflush_walk(map_addr, end,
> +				prot, pages + idx, min(prev_shift, PMD_SHIFT));
> +
> +out:
> +	flush_cache_vmap(start, end);
> +	return err;
> +}
> +
>  /**
>   * vmap - map an array of pages into virtually contiguous space
>   * @pages: array of page pointers
> @@ -3585,8 +3663,8 @@ void *vmap(struct page **pages, unsigned int count,
>  		return NULL;
>  
>  	addr = (unsigned long)area->addr;
> -	if (vmap_pages_range(addr, addr + size, pgprot_nx(prot),
> -				pages, PAGE_SHIFT) < 0) {
> +	if (vmap_batched(addr, addr + size, pgprot_nx(prot),
> +				pages) < 0) {
>  		vunmap(area->addr);
>  		return NULL;
>  	}



  reply	other threads:[~2026-05-27  8:28 UTC|newest]

Thread overview: 25+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-05-22  5:31 [PATCH v3 0/6] mm/vmalloc: Speed up ioremap, vmalloc and vmap with contiguous memory Wen Jiang
2026-05-22  5:31 ` [PATCH v3 1/6] arm64/hugetlb: Extend batching of multiple CONT_PTE in a single PTE setup Wen Jiang
2026-05-26  7:56   ` Dev Jain
2026-05-22  5:31 ` [PATCH v3 2/6] arm64/vmalloc: Allow arch_vmap_pte_range_map_size to batch multiple CONT_PTE Wen Jiang
2026-05-27  5:43   ` Dev Jain
2026-05-22  5:31 ` [PATCH v3 3/6] mm/vmalloc: Extract vmap_set_ptes() to consolidate PTE mapping logic Wen Jiang
2026-06-01 17:34   ` Uladzislau Rezki
2026-06-02  7:45     ` Wen Jiang
2026-05-22  5:31 ` [PATCH v3 4/6] mm/vmalloc: Extend page table walk to support larger page_shift sizes and eliminate page table rewalk Wen Jiang
2026-05-27  5:58   ` Dev Jain
2026-05-28  3:39     ` Wen Jiang
2026-05-29  5:28       ` Dev Jain
2026-06-05  6:02       ` Dev Jain
2026-05-22  5:31 ` [PATCH v3 5/6] mm/vmalloc: map contiguous pages in batches for vmap() if possible Wen Jiang
2026-05-27  8:27   ` Dev Jain [this message]
2026-05-28  3:42     ` Wen Jiang
2026-05-29  5:57       ` Dev Jain
2026-06-02  7:34         ` Wen Jiang
2026-05-22  5:31 ` [PATCH v3 6/6] mm/vmalloc: align vm_area so vmap() can batch mappings Wen Jiang
2026-05-23  7:53   ` Uladzislau Rezki
2026-05-27  6:25   ` Dev Jain
2026-06-02  8:57     ` Wen Jiang
2026-05-22 18:07 ` [PATCH v3 0/6] mm/vmalloc: Speed up ioremap, vmalloc and vmap with contiguous memory Andrew Morton
2026-05-23  8:26   ` Wen Jiang
2026-05-23 21:40     ` Andrew Morton

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=340c811e-2501-46c3-8a55-19e955c5ae8a@arm.com \
    --to=dev.jain@arm$(echo .)com \
    --cc=Xueyuan.chen21@gmail$(echo .)com \
    --cc=ajd@linux$(echo .)ibm.com \
    --cc=akpm@linux-foundation$(echo .)org \
    --cc=anshuman.khandual@arm$(echo .)com \
    --cc=baohua@kernel$(echo .)org \
    --cc=catalin.marinas@arm$(echo .)com \
    --cc=david@kernel$(echo .)org \
    --cc=jiangwen6@xiaomi$(echo .)com \
    --cc=jiangwenxiaomi@gmail$(echo .)com \
    --cc=linux-arm-kernel@lists$(echo .)infradead.org \
    --cc=linux-kernel@vger$(echo .)kernel.org \
    --cc=linux-mm@kvack$(echo .)org \
    --cc=rppt@kernel$(echo .)org \
    --cc=ryan.roberts@arm$(echo .)com \
    --cc=urezki@gmail$(echo .)com \
    --cc=will@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