[PATCH 02/49] mm/sparse: add a @pgmap argument to memory deactivation paths
Muchun Song
songmuchun at bytedance.com
Sun Apr 5 22:51:53 AEST 2026
Currently, memory hot-remove paths do not pass the struct dev_pagemap
pointer down to section_deactivate(). This prevents the lower levels
from knowing whether the section was originally populated with vmemmap
optimizations (e.g., DAX with HVO enabled).
Without this information, we cannot call vmemmap_can_optimize() to
determine if the vmemmap pages were optimized. As a result, the vmemmap
page accounting during teardown will mistakenly assume a non-optimized
allocation, leading to incorrect page statistics.
To lay the groundwork for fixing the vmemmap page accounting, we need
to pass the @pgmap pointer down to the deactivation location. Plumb the
@pgmap argument through the APIs of arch_remove_memory(), __remove_pages()
and sparse_remove_section(), mirroring the corresponding *_activate()
paths.
Signed-off-by: Muchun Song <songmuchun at bytedance.com>
---
arch/arm64/mm/mmu.c | 5 +++--
arch/loongarch/mm/init.c | 5 +++--
arch/powerpc/mm/mem.c | 5 +++--
arch/riscv/mm/init.c | 5 +++--
arch/s390/mm/init.c | 5 +++--
arch/x86/mm/init_64.c | 5 +++--
include/linux/memory_hotplug.h | 8 +++++---
mm/memory_hotplug.c | 12 ++++++------
mm/memremap.c | 4 ++--
mm/sparse-vmemmap.c | 8 ++++----
10 files changed, 35 insertions(+), 27 deletions(-)
diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index ec1c6971a561..dc8a8281888c 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -1994,12 +1994,13 @@ int arch_add_memory(int nid, u64 start, u64 size,
return ret;
}
-void arch_remove_memory(u64 start, u64 size, struct vmem_altmap *altmap)
+void arch_remove_memory(u64 start, u64 size, struct vmem_altmap *altmap,
+ struct dev_pagemap *pgmap)
{
unsigned long start_pfn = start >> PAGE_SHIFT;
unsigned long nr_pages = size >> PAGE_SHIFT;
- __remove_pages(start_pfn, nr_pages, altmap);
+ __remove_pages(start_pfn, nr_pages, altmap, pgmap);
__remove_pgd_mapping(swapper_pg_dir, __phys_to_virt(start), size);
}
diff --git a/arch/loongarch/mm/init.c b/arch/loongarch/mm/init.c
index 00f3822b6e47..c9c57f08fa2c 100644
--- a/arch/loongarch/mm/init.c
+++ b/arch/loongarch/mm/init.c
@@ -86,7 +86,8 @@ int arch_add_memory(int nid, u64 start, u64 size, struct mhp_params *params)
return ret;
}
-void arch_remove_memory(u64 start, u64 size, struct vmem_altmap *altmap)
+void arch_remove_memory(u64 start, u64 size, struct vmem_altmap *altmap,
+ struct dev_pagemap *pgmap)
{
unsigned long start_pfn = start >> PAGE_SHIFT;
unsigned long nr_pages = size >> PAGE_SHIFT;
@@ -95,7 +96,7 @@ void arch_remove_memory(u64 start, u64 size, struct vmem_altmap *altmap)
/* With altmap the first mapped page is offset from @start */
if (altmap)
page += vmem_altmap_offset(altmap);
- __remove_pages(start_pfn, nr_pages, altmap);
+ __remove_pages(start_pfn, nr_pages, altmap, pgmap);
}
#endif
diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c
index 648d0c5602ec..4c1afab91996 100644
--- a/arch/powerpc/mm/mem.c
+++ b/arch/powerpc/mm/mem.c
@@ -158,12 +158,13 @@ int __ref arch_add_memory(int nid, u64 start, u64 size,
return rc;
}
-void __ref arch_remove_memory(u64 start, u64 size, struct vmem_altmap *altmap)
+void __ref arch_remove_memory(u64 start, u64 size, struct vmem_altmap *altmap,
+ struct dev_pagemap *pgmap)
{
unsigned long start_pfn = start >> PAGE_SHIFT;
unsigned long nr_pages = size >> PAGE_SHIFT;
- __remove_pages(start_pfn, nr_pages, altmap);
+ __remove_pages(start_pfn, nr_pages, altmap, pgmap);
arch_remove_linear_mapping(start, size);
}
#endif
diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c
index 5142ca80be6f..980f693e6b19 100644
--- a/arch/riscv/mm/init.c
+++ b/arch/riscv/mm/init.c
@@ -1810,9 +1810,10 @@ int __ref arch_add_memory(int nid, u64 start, u64 size, struct mhp_params *param
return ret;
}
-void __ref arch_remove_memory(u64 start, u64 size, struct vmem_altmap *altmap)
+void __ref arch_remove_memory(u64 start, u64 size, struct vmem_altmap *altmap,
+ struct dev_pagemap *pgmap)
{
- __remove_pages(start >> PAGE_SHIFT, size >> PAGE_SHIFT, altmap);
+ __remove_pages(start >> PAGE_SHIFT, size >> PAGE_SHIFT, altmap, pgmap);
remove_linear_mapping(start, size);
flush_tlb_all();
}
diff --git a/arch/s390/mm/init.c b/arch/s390/mm/init.c
index 1f72efc2a579..11a689423440 100644
--- a/arch/s390/mm/init.c
+++ b/arch/s390/mm/init.c
@@ -276,12 +276,13 @@ int arch_add_memory(int nid, u64 start, u64 size,
return rc;
}
-void arch_remove_memory(u64 start, u64 size, struct vmem_altmap *altmap)
+void arch_remove_memory(u64 start, u64 size, struct vmem_altmap *altmap,
+ struct dev_pagemap *pgmap)
{
unsigned long start_pfn = start >> PAGE_SHIFT;
unsigned long nr_pages = size >> PAGE_SHIFT;
- __remove_pages(start_pfn, nr_pages, altmap);
+ __remove_pages(start_pfn, nr_pages, altmap, pgmap);
vmem_remove_mapping(start, size);
}
#endif /* CONFIG_MEMORY_HOTPLUG */
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index df2261fa4f98..77b889b71cf3 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -1288,12 +1288,13 @@ kernel_physical_mapping_remove(unsigned long start, unsigned long end)
remove_pagetable(start, end, true, NULL);
}
-void __ref arch_remove_memory(u64 start, u64 size, struct vmem_altmap *altmap)
+void __ref arch_remove_memory(u64 start, u64 size, struct vmem_altmap *altmap,
+ struct dev_pagemap *pgmap)
{
unsigned long start_pfn = start >> PAGE_SHIFT;
unsigned long nr_pages = size >> PAGE_SHIFT;
- __remove_pages(start_pfn, nr_pages, altmap);
+ __remove_pages(start_pfn, nr_pages, altmap, pgmap);
kernel_physical_mapping_remove(start, start + size);
}
#endif /* CONFIG_MEMORY_HOTPLUG */
diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h
index 815e908c4135..7c9d66729c60 100644
--- a/include/linux/memory_hotplug.h
+++ b/include/linux/memory_hotplug.h
@@ -135,9 +135,10 @@ static inline bool movable_node_is_enabled(void)
return movable_node_enabled;
}
-extern void arch_remove_memory(u64 start, u64 size, struct vmem_altmap *altmap);
+extern void arch_remove_memory(u64 start, u64 size, struct vmem_altmap *altmap,
+ struct dev_pagemap *pgmap);
extern void __remove_pages(unsigned long start_pfn, unsigned long nr_pages,
- struct vmem_altmap *altmap);
+ struct vmem_altmap *altmap, struct dev_pagemap *pgmap);
/* reasonably generic interface to expand the physical pages */
extern int __add_pages(int nid, unsigned long start_pfn, unsigned long nr_pages,
@@ -307,7 +308,8 @@ extern int sparse_add_section(int nid, unsigned long pfn,
unsigned long nr_pages, struct vmem_altmap *altmap,
struct dev_pagemap *pgmap);
extern void sparse_remove_section(unsigned long pfn, unsigned long nr_pages,
- struct vmem_altmap *altmap);
+ struct vmem_altmap *altmap,
+ struct dev_pagemap *pgmap);
extern struct zone *zone_for_pfn_range(enum mmop online_type,
int nid, struct memory_group *group, unsigned long start_pfn,
unsigned long nr_pages);
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 8b18ddd1e7d5..05f5df12d843 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -583,7 +583,7 @@ void remove_pfn_range_from_zone(struct zone *zone,
* calling offline_pages().
*/
void __remove_pages(unsigned long pfn, unsigned long nr_pages,
- struct vmem_altmap *altmap)
+ struct vmem_altmap *altmap, struct dev_pagemap *pgmap)
{
const unsigned long end_pfn = pfn + nr_pages;
unsigned long cur_nr_pages;
@@ -598,7 +598,7 @@ void __remove_pages(unsigned long pfn, unsigned long nr_pages,
/* Select all remaining pages up to the next section boundary */
cur_nr_pages = min(end_pfn - pfn,
SECTION_ALIGN_UP(pfn + 1) - pfn);
- sparse_remove_section(pfn, cur_nr_pages, altmap);
+ sparse_remove_section(pfn, cur_nr_pages, altmap, pgmap);
}
}
@@ -1418,7 +1418,7 @@ static void remove_memory_blocks_and_altmaps(u64 start, u64 size)
remove_memory_block_devices(cur_start, memblock_size);
- arch_remove_memory(cur_start, memblock_size, altmap);
+ arch_remove_memory(cur_start, memblock_size, altmap, NULL);
/* Verify that all vmemmap pages have actually been freed. */
WARN(altmap->alloc, "Altmap not fully unmapped");
@@ -1461,7 +1461,7 @@ static int create_altmaps_and_memory_blocks(int nid, struct memory_group *group,
ret = create_memory_block_devices(cur_start, memblock_size, nid,
params.altmap, group);
if (ret) {
- arch_remove_memory(cur_start, memblock_size, NULL);
+ arch_remove_memory(cur_start, memblock_size, NULL, NULL);
kfree(params.altmap);
goto out;
}
@@ -1547,7 +1547,7 @@ int add_memory_resource(int nid, struct resource *res, mhp_t mhp_flags)
/* create memory block devices after memory was added */
ret = create_memory_block_devices(start, size, nid, NULL, group);
if (ret) {
- arch_remove_memory(start, size, params.altmap);
+ arch_remove_memory(start, size, params.altmap, NULL);
goto error;
}
}
@@ -2246,7 +2246,7 @@ static int try_remove_memory(u64 start, u64 size)
* No altmaps present, do the removal directly
*/
remove_memory_block_devices(start, size);
- arch_remove_memory(start, size, NULL);
+ arch_remove_memory(start, size, NULL, NULL);
} else {
/* all memblocks in the range have altmaps */
remove_memory_blocks_and_altmaps(start, size);
diff --git a/mm/memremap.c b/mm/memremap.c
index ac7be07e3361..c45b90f334ea 100644
--- a/mm/memremap.c
+++ b/mm/memremap.c
@@ -97,10 +97,10 @@ static void pageunmap_range(struct dev_pagemap *pgmap, int range_id)
PHYS_PFN(range_len(range)));
if (pgmap->type == MEMORY_DEVICE_PRIVATE) {
__remove_pages(PHYS_PFN(range->start),
- PHYS_PFN(range_len(range)), NULL);
+ PHYS_PFN(range_len(range)), NULL, pgmap);
} else {
arch_remove_memory(range->start, range_len(range),
- pgmap_altmap(pgmap));
+ pgmap_altmap(pgmap), pgmap);
kasan_remove_zero_shadow(__va(range->start), range_len(range));
}
mem_hotplug_done();
diff --git a/mm/sparse-vmemmap.c b/mm/sparse-vmemmap.c
index ee27d0c0efe2..7aa9a97498eb 100644
--- a/mm/sparse-vmemmap.c
+++ b/mm/sparse-vmemmap.c
@@ -737,7 +737,7 @@ static int fill_subsection_map(unsigned long pfn, unsigned long nr_pages)
* usage map, but still need to free the vmemmap range.
*/
static void section_deactivate(unsigned long pfn, unsigned long nr_pages,
- struct vmem_altmap *altmap)
+ struct vmem_altmap *altmap, struct dev_pagemap *pgmap)
{
struct mem_section *ms = __pfn_to_section(pfn);
bool section_is_early = early_section(ms);
@@ -824,7 +824,7 @@ static struct page * __meminit section_activate(int nid, unsigned long pfn,
memmap = populate_section_memmap(pfn, nr_pages, nid, altmap, pgmap);
memmap_pages_add(DIV_ROUND_UP(nr_pages * sizeof(struct page), PAGE_SIZE));
if (!memmap) {
- section_deactivate(pfn, nr_pages, altmap);
+ section_deactivate(pfn, nr_pages, altmap, pgmap);
return ERR_PTR(-ENOMEM);
}
@@ -885,13 +885,13 @@ int __meminit sparse_add_section(int nid, unsigned long start_pfn,
}
void sparse_remove_section(unsigned long pfn, unsigned long nr_pages,
- struct vmem_altmap *altmap)
+ struct vmem_altmap *altmap, struct dev_pagemap *pgmap)
{
struct mem_section *ms = __pfn_to_section(pfn);
if (WARN_ON_ONCE(!valid_section(ms)))
return;
- section_deactivate(pfn, nr_pages, altmap);
+ section_deactivate(pfn, nr_pages, altmap, pgmap);
}
#endif /* CONFIG_MEMORY_HOTPLUG */
--
2.20.1
More information about the Linuxppc-dev
mailing list