mm: introduce linear_anon_page_index()

This function provides the anonymous equivalent of linear_page_index(),
instead offsetting based on the anonymous page offset of the VMA.

It is valid only for anonymous or MAP_PRIVATE file-backed mappings, in
other words CoW mappings.

For pure anon VMAs, this will be equal to linear_page_index().

Assert that both of these invariants are true in linear_anon_page_index()
and implement the algorithm in __linear_anon_page_index().

Note that MAP_PRIVATE-/dev/zero mappings will satisfy vma_is_anonymous()
but not fulfill this invariant, so when asserting this we check
vma->vm_file to account for this.

We do not update callsites yet, so no functional change intended.

Also const-ify vma_is_anonymous() to make it compatible with the
const-ified linear_anon_page_index().

While we're here, update linear_page_index() to be more succinct.

VMA userland tests are also updated accordingly.

Link: https://lore.kernel.org/20260813-b4-scalable-cow-virt-pgoff-v5-3-c21581c0c3c8@kernel.org
Signed-off-by: Lorenzo Stoakes (ARM) <ljs@kernel.org>
Reviewed-by: Gregory Price (Meta) <gourry@gourry.net>
Acked-by: David Hildenbrand (Arm) <david@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Deucher <alexander.deucher@amd.com>
Cc: Alexander Gordeev <agordeev@linux.ibm.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Alistair Popple <apopple@nvidia.com>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Baolin Wang <baolin.wang@linux.alibaba.com>
Cc: Baoquan He <baoquan.he@linux.dev>
Cc: Barry Song <baohua@kernel.org>
Cc: Boris Brezillon <boris.brezillon@collabora.com>
Cc: Byungchul Park <byungchul@sk.com>
Cc: Chengming Zhou <chengming.zhou@linux.dev>
Cc: Chris Li <chrisl@kernel.org>
Cc: Christan König <christian.koenig@amd.com>
Cc: Christian Borntraeger <borntraeger@linux.ibm.com>
Cc: Claudio Imbrenda <imbrenda@linux.ibm.com>
Cc: Dave Airlie <airlied@gmail.com>
Cc: Dev Jain <dev.jain@arm.com>
Cc: Gerald Schaefer <gerald.schaefer@linux.ibm.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Harry Yoo <harry@kernel.org>
Cc: Heiko Carstens <hca@linux.ibm.com>
Cc: Huang Ray <Ray.Huang@amd.com>
Cc: "Huang, Ying" <ying.huang@linux.alibaba.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@linaro.org>
Cc: Jan Kara <jack@suse.cz>
Cc: Jann Horn <jannh@google.com>
Cc: Janosch Frank <frankja@linux.ibm.com>
Cc: Jason Gunthorpe <jgg@ziepe.ca>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: John Hubbard <jhubbard@nvidia.com>
Cc: Joshua Hahn <joshua.hahnjy@gmail.com>
Cc: Kairui Song <kasong@tencent.com>
Cc: Kees Cook <kees@kernel.org>
Cc: Kemeng Shi <shikemeng@huaweicloud.com>
Cc: Lance Yang <lance.yang@linux.dev>
Cc: Liam R. Howlett <liam@infradead.org>
Cc: Liviu Dudau <liviu.dudau@arm.com>
Cc: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Cc: Marc Rutland <mark.rutland@arm.com>
Cc: "Masami Hiramatsu (Google)" <mhiramat@kernel.org>
Cc: Matthew Auld <matthew.auld@intel.com>
Cc: Matthew Brost <matthew.brost@intel.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Maxime Ripard <mripard@kernel.org>
Cc: Miaohe Lin <linmiaohe@huawei.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Mike Rapoport <rppt@kernel.org>
Cc: Muchun Song <muchun.song@linux.dev>
Cc: Namhyung kim <namhyung@kernel.org>
Cc: Naoya Horiguchi <nao.horiguchi@gmail.com>
Cc: Nhat Pham <nphamcs@gmail.com>
Cc: Nico Pache <npache@redhat.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: Pedro Falcato <pfalcato@suse.de>
Cc: Peter Xu <peterx@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rakie Kim <rakie.kim@sk.com>
Cc: Rik van Riel <riel@surriel.com>
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Cc: Ryan Roberts <ryan.roberts@arm.com>
Cc: Steven Price <steven.price@arm.com>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Sven Schnelle <svens@linux.ibm.com>
Cc: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Cc: Thomas Zimemrmann <tzimmermann@suse.de>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Cc: Vlastimil Babka <vbabka@kernel.org>
Cc: xu xin <xu.xin16@zte.com.cn>
Cc: Zi Yan <ziy@nvidia.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

include/linux/mm.h

@@ -1556,7 +1556,7 @@ static inline void vma_desc_set_anonymous(struct vm_area_desc *desc)
 	desc->vm_ops = NULL;
 }
 
-static inline bool vma_is_anonymous(struct vm_area_struct *vma)
+static inline bool vma_is_anonymous(const struct vm_area_struct *vma)
 {
 	return !vma->vm_ops;
 }

include/linux/pagemap.h

@@ -1094,10 +1094,44 @@ static inline pgoff_t linear_page_delta(const struct vm_area_struct *vma,
 static inline pgoff_t linear_page_index(const struct vm_area_struct *vma,
 					const unsigned long address)
 {
-	pgoff_t pgoff;
+	return linear_page_delta(vma, address) + vma_start_pgoff(vma);
+}
+
+static inline pgoff_t __linear_anon_page_index(const struct vm_area_struct *vma,
+		const unsigned long address)
+{
+	return linear_page_delta(vma, address) + vma_start_anon_pgoff(vma);
+}
+
+/**
+ * linear_anon_page_index() - Determine the absolute anonymous page offset of
+ * @address within @vma.
+ * @vma: An anonymous or MAP_PRIVATE file-backed VMA in which @address resides.
+ * @address: The address whose absolute page offset is required.
+ *
+ * This returns the anonymous page offset of @address, which is the page offset
+ * the address possessed at the time the VMA was first faulted.
+ *
+ * For anonymous mappings, this returns the same value as linear_page_index().
+ *
+ * For MAP_PRIVATE file-backed mappings, this returns the anonymous page offset
+ * of @address, which is the page offset the address possessed at the time the
+ * VMA was first faulted.
+ *
+ * It is not valid to call this function for shared file-backed mappings.
+ *
+ * Returns: The absolute anonymous page offset of @address within @vma.
+ */
+static inline pgoff_t linear_anon_page_index(const struct vm_area_struct *vma,
+		const unsigned long address)
+{
+	const pgoff_t pgoff = __linear_anon_page_index(vma, address);
+
+	VM_WARN_ON_ONCE(!vma_is_cow_mapping(vma));
+	/* Account for MAP_PRIVATE-/dev/zero which is only semi-anonymous. */
+	if (vma_is_anonymous(vma) && !vma->vm_file)
+		VM_WARN_ON_ONCE(pgoff != linear_page_index(vma, address));
 
-	pgoff = linear_page_delta(vma, address);
-	pgoff += vma_start_pgoff(vma);
 	return pgoff;
 }
 

tools/testing/vma/include/dup.h

@@ -1428,7 +1428,7 @@ static inline void vma_iter_set(struct vma_iterator *vmi, unsigned long addr)
 	mas_set(&vmi->mas, addr);
 }
 
-static inline bool vma_is_anonymous(struct vm_area_struct *vma)
+static inline bool vma_is_anonymous(const struct vm_area_struct *vma)
 {
 	return !vma->vm_ops;
 }
@@ -1621,3 +1621,26 @@ static inline pgprot_t vma_get_page_prot(const struct vm_area_struct *vma)
 {
 	return vma_flags_to_page_prot(vma->flags);
 }
+
+static inline pgoff_t __linear_anon_page_index(const struct vm_area_struct *vma,
+					       const unsigned long address)
+{
+	pgoff_t pgoff;
+
+	pgoff = linear_page_delta(vma, address);
+	pgoff += vma_start_anon_pgoff(vma);
+	return pgoff;
+}
+
+static inline pgoff_t linear_anon_page_index(const struct vm_area_struct *vma,
+		const unsigned long address)
+{
+	const pgoff_t pgoff = __linear_anon_page_index(vma, address);
+
+	VM_WARN_ON_ONCE(!vma_is_cow_mapping(vma));
+	/* Account for MAP_PRIVATE-/dev/zero which is only semi-anonymous. */
+	if (vma_is_anonymous(vma) && !vma->vm_file)
+		VM_WARN_ON_ONCE(pgoff != linear_page_index(vma, address));
+
+	return pgoff;
+}