Linux-mm Archive on lore.kernel.org
 help / color / mirror / Atom feed
From: Muchun Song <songmuchun@bytedance.com>
To: Andrew Morton <akpm@linux-foundation.org>,
	David Hildenbrand <david@kernel.org>,
	Oscar Salvador <osalvador@suse.de>,
	Madhavan Srinivasan <maddy@linux.ibm.com>,
	Michael Ellerman <mpe@ellerman.id.au>,
	Jonathan Corbet <corbet@lwn.net>
Cc: linux-mm@kvack.org, linux-kernel@vger.kernel.org,
	linuxppc-dev@lists.ozlabs.org, linux-doc@vger.kernel.org,
	Muchun Song <muchun.song@linux.dev>,
	Lorenzo Stoakes <ljs@kernel.org>, Mike Rapoport <rppt@kernel.org>,
	Qi Zheng <qi.zheng@linux.dev>,
	Nicholas Piggin <npiggin@gmail.com>,
	Christophe Leroy <chleroy@kernel.org>,
	Randy Dunlap <rdunlap@infradead.org>,
	Muchun Song <songmuchun@bytedance.com>
Subject: [PATCH 04/11] mm/sparse-vmemmap: prepare DAX vmemmap population for section orders
Date: Mon, 31 Aug 2026 15:53:35 +0800	[thread overview]
Message-ID: <20260831075342.57563-5-songmuchun@bytedance.com> (raw)
In-Reply-To: <20260831075342.57563-1-songmuchun@bytedance.com>

Device DAX still uses vmemmap_populate_compound_pages() to populate its
compound-page vmemmap mappings. That helper allocates the head and first
tail vmemmap pages explicitly, then reuses the first tail page for the
remaining tail page mappings.

Device DAX is being moved to the section-based vmemmap optimization
infrastructure, but it cannot switch to the generic section-based
population path yet. Once a later patch records the DAX compound-page
geometry in the section order, DAX head and first-tail PFNs can look
optimizable to the generic helpers as well.

Add a DAX-specific population flag for this transition. It keeps DAX
head/first-tail allocations on the normal vmemmap allocation path, while
preserving the existing page reference for reused DAX tail mappings.

Signed-off-by: Muchun Song <songmuchun@bytedance.com>
---
 mm/sparse-vmemmap.c | 27 +++++++++++++++------------
 1 file changed, 15 insertions(+), 12 deletions(-)

diff --git a/mm/sparse-vmemmap.c b/mm/sparse-vmemmap.c
index e453ce4675a0..54ae8c284324 100644
--- a/mm/sparse-vmemmap.c
+++ b/mm/sparse-vmemmap.c
@@ -35,8 +35,8 @@
 /*
  * Flags for vmemmap_populate_range and friends.
  */
-/* Get a ref on the head page struct page, for ZONE_DEVICE compound pages */
-#define VMEMMAP_POPULATE_PAGEREF	0x0001
+/* Vmemmap population for ZONE_DEVICE compound pages */
+#define VMEMMAP_POPULATE_DAX		0x0001
 
 #include "internal.h"
 #include "mm_init.h"
@@ -208,13 +208,17 @@ struct page __ref *vmemmap_shared_tail_page(unsigned int order, struct zone *zon
 }
 
 static __meminit void *vmemmap_alloc_pte(unsigned long pfn, int node,
-					 struct vmem_altmap *altmap)
+		struct vmem_altmap *altmap, unsigned long flags)
 {
 	struct zone *zone;
 	struct page *page;
 	const unsigned int order = pfn_to_section_order(pfn);
 
-	if (!vmemmap_optimizable_pfn(pfn))
+	/*
+	 * Device DAX still relies on vmemmap_populate_compound_pages() for
+	 * head/first-tail allocation and tail-page reuse.
+	 */
+	if (!vmemmap_optimizable_pfn(pfn) || flags & VMEMMAP_POPULATE_DAX)
 		return vmemmap_alloc_block_buf(PAGE_SIZE, node, altmap);
 
 	zone = pfn_to_zone(pfn, node);
@@ -236,7 +240,7 @@ static pte_t * __meminit vmemmap_pte_populate(pmd_t *pmd, unsigned long addr, in
 		pte_t entry;
 
 		if (ptpfn == (unsigned long)-1) {
-			void *p = vmemmap_alloc_pte(pfn, node, altmap);
+			void *p = vmemmap_alloc_pte(pfn, node, altmap, flags);
 
 			if (!p)
 				return NULL;
@@ -251,7 +255,7 @@ static pte_t * __meminit vmemmap_pte_populate(pmd_t *pmd, unsigned long addr, in
 			 * and through vmemmap_populate_compound_pages() when
 			 * slab is available.
 			 */
-			if (flags & VMEMMAP_POPULATE_PAGEREF)
+			if (flags & VMEMMAP_POPULATE_DAX)
 				get_page(pfn_to_page(ptpfn));
 		}
 		entry = pfn_pte(ptpfn, PAGE_KERNEL);
@@ -511,6 +515,7 @@ static int __meminit vmemmap_populate_compound_pages(unsigned long start_pfn,
 	unsigned long size, addr;
 	pte_t *pte;
 	int rc;
+	unsigned long flags = VMEMMAP_POPULATE_DAX;
 
 	if (reuse_compound_section(start_pfn, pgmap)) {
 		pte = compound_section_tail_page(start);
@@ -522,8 +527,7 @@ static int __meminit vmemmap_populate_compound_pages(unsigned long start_pfn,
 		 * with just tail struct pages.
 		 */
 		return vmemmap_populate_range(start, end, node, NULL,
-					      pte_pfn(ptep_get(pte)),
-					      VMEMMAP_POPULATE_PAGEREF);
+					      pte_pfn(ptep_get(pte)), flags);
 	}
 
 	size = min(end - start, pgmap_vmemmap_nr(pgmap) * sizeof(struct page));
@@ -531,13 +535,13 @@ static int __meminit vmemmap_populate_compound_pages(unsigned long start_pfn,
 		unsigned long next, last = addr + size;
 
 		/* Populate the head page vmemmap page */
-		pte = vmemmap_populate_address(addr, node, NULL, -1, 0);
+		pte = vmemmap_populate_address(addr, node, NULL, -1, flags);
 		if (!pte)
 			return -ENOMEM;
 
 		/* Populate the tail pages vmemmap page */
 		next = addr + PAGE_SIZE;
-		pte = vmemmap_populate_address(next, node, NULL, -1, 0);
+		pte = vmemmap_populate_address(next, node, NULL, -1, flags);
 		if (!pte)
 			return -ENOMEM;
 
@@ -547,8 +551,7 @@ static int __meminit vmemmap_populate_compound_pages(unsigned long start_pfn,
 		 */
 		next += PAGE_SIZE;
 		rc = vmemmap_populate_range(next, last, node, NULL,
-					    pte_pfn(ptep_get(pte)),
-					    VMEMMAP_POPULATE_PAGEREF);
+					    pte_pfn(ptep_get(pte)), flags);
 		if (rc)
 			return -ENOMEM;
 	}
-- 
2.54.0



  parent reply	other threads:[~2026-08-31  7:54 UTC|newest]

Thread overview: 17+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-08-31  7:53 [PATCH 00/11] mm: Switch device DAX to section-based vmemmap optimization Muchun Song
2026-08-31  7:53 ` [PATCH 01/11] mm/sparse-vmemmap: introduce CONFIG_SPARSEMEM_VMEMMAP_OPTIMIZATION Muchun Song
2026-08-31  9:44   ` Qi Zheng
2026-08-31  9:49     ` Muchun Song
2026-08-31  7:53 ` [PATCH 02/11] mm/sparse-vmemmap: factor out shared vmemmap tail page allocation Muchun Song
2026-09-01  3:05   ` Qi Zheng
2026-08-31  7:53 ` [PATCH 03/11] mm/sparse-vmemmap: open-code init_compound_tail() Muchun Song
2026-09-01  3:18   ` Qi Zheng
2026-08-31  7:53 ` Muchun Song [this message]
2026-09-03  6:36   ` [PATCH 04/11] mm/sparse-vmemmap: prepare DAX vmemmap population for section orders Qi Zheng
2026-08-31  7:53 ` [PATCH 05/11] mm/sparse-vmemmap: set section order for device DAX Muchun Song
2026-08-31  7:53 ` [PATCH 06/11] mm/sparse-vmemmap: switch device DAX to shared tail vmemmap pages Muchun Song
2026-08-31  7:53 ` [PATCH 07/11] mm/sparse-vmemmap: move HVO helpers to a public header Muchun Song
2026-08-31  7:53 ` [PATCH 08/11] powerpc/mm: switch device DAX to shared tail vmemmap pages Muchun Song
2026-08-31  7:53 ` [PATCH 09/11] mm/sparse-vmemmap: drop the extra tail page from device DAX reservation Muchun Song
2026-08-31  7:53 ` [PATCH 10/11] mm/sparse-vmemmap: drop unused section_nr_vmemmap_pages() arguments Muchun Song
2026-08-31  7:53 ` [PATCH 11/11] Documentation/mm: update DAX vmemmap deduplication docs 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=20260831075342.57563-5-songmuchun@bytedance.com \
    --to=songmuchun@bytedance.com \
    --cc=akpm@linux-foundation.org \
    --cc=chleroy@kernel.org \
    --cc=corbet@lwn.net \
    --cc=david@kernel.org \
    --cc=linux-doc@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=linuxppc-dev@lists.ozlabs.org \
    --cc=ljs@kernel.org \
    --cc=maddy@linux.ibm.com \
    --cc=mpe@ellerman.id.au \
    --cc=muchun.song@linux.dev \
    --cc=npiggin@gmail.com \
    --cc=osalvador@suse.de \
    --cc=qi.zheng@linux.dev \
    --cc=rdunlap@infradead.org \
    --cc=rppt@kernel.org \
    /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