mm/sparse-vmemmap: pass @pgmap argument to memory deactivation paths

Currently, the memory hot-remove call chain -- arch_remove_memory(),
__remove_pages(), sparse_remove_section() and section_deactivate() -- does
not carry the struct dev_pagemap pointer.  This prevents the lower levels
from knowing whether the section was originally populated with vmemmap
optimizations (e.g., DAX with vmemmap optimization 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 memmap 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.

Link: https://lore.kernel.org/20260428081855.1249045-4-songmuchun@bytedance.com
Signed-off-by: Muchun Song <songmuchun@bytedance.com>
Acked-by: Mike Rapoport (Microsoft) <rppt@kernel.org>
Reviewed-by: Oscar Salvador <osalvador@suse.de>
Acked-by: David Hildenbrand (Arm) <david@kernel.org>
Acked-by: Liam R. Howlett <liam@infradead.org>
Cc: "Aneesh Kumar K.V" <aneesh.kumar@linux.ibm.com>
Cc: Joao Martins <joao.m.martins@oracle.com>
Cc: Lorenzo Stoakes <ljs@kernel.org>
Cc: Madhavan Srinivasan <maddy@linux.ibm.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Vlastimil Babka <vbabka@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
This commit is contained in:
Muchun Song
2026-04-28 16:18:52 +08:00
committed by Andrew Morton
parent 2fac4afa0e
commit 3bbc54dd1b
10 changed files with 38 additions and 29 deletions

View File

@@ -2024,12 +2024,13 @@ 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);
}

View File

@@ -119,12 +119,13 @@ 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;
__remove_pages(start_pfn, nr_pages, altmap);
__remove_pages(start_pfn, nr_pages, altmap, pgmap);
}
#endif

View File

@@ -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

View File

@@ -1742,9 +1742,10 @@ 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();
}

View File

@@ -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 */

View File

@@ -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 */

View File

@@ -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);

View File

@@ -576,6 +576,7 @@ void remove_pfn_range_from_zone(struct zone *zone,
* @pfn: starting pageframe (must be aligned to start of a section)
* @nr_pages: number of pages to remove (must be multiple of section size)
* @altmap: alternative device page map or %NULL if default memmap is used
* @pgmap: device page map or %NULL if not ZONE_DEVICE
*
* Generic helper function to remove section mappings and sysfs entries
* for the section of the memory we are removing. Caller needs to make
@@ -583,7 +584,7 @@ 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 +599,7 @@ 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);
}
}
@@ -1427,7 +1428,7 @@ 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");
@@ -1470,7 +1471,7 @@ 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, params.altmap);
arch_remove_memory(cur_start, memblock_size, params.altmap, NULL);
kfree(params.altmap);
goto out;
}
@@ -1556,7 +1557,7 @@ 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;
}
}
@@ -2268,7 +2269,7 @@ 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);

View File

@@ -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();

View File

@@ -660,7 +660,7 @@ static struct page * __meminit populate_section_memmap(unsigned long pfn,
}
static void depopulate_section_memmap(unsigned long pfn, unsigned long nr_pages,
struct vmem_altmap *altmap)
struct vmem_altmap *altmap, struct dev_pagemap *pgmap)
{
unsigned long start = (unsigned long) pfn_to_page(pfn);
unsigned long end = start + nr_pages * sizeof(struct page);
@@ -741,7 +741,7 @@ 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);
@@ -779,7 +779,7 @@ static void section_deactivate(unsigned long pfn, unsigned long nr_pages,
* section_activate() and pfn_valid() .
*/
if (!section_is_early)
depopulate_section_memmap(pfn, nr_pages, altmap);
depopulate_section_memmap(pfn, nr_pages, altmap, pgmap);
else if (memmap)
free_map_bootmem(memmap);
@@ -823,7 +823,7 @@ static struct page * __meminit section_activate(int nid, unsigned long pfn,
memmap = populate_section_memmap(pfn, nr_pages, nid, altmap, pgmap);
if (!memmap) {
section_deactivate(pfn, nr_pages, altmap);
section_deactivate(pfn, nr_pages, altmap, pgmap);
return ERR_PTR(-ENOMEM);
}
@@ -884,13 +884,13 @@ 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 */