* [PATCH] mm/percpu-internal.h: optimise pcpu_chunk_struct to save memory
@ 2026-03-05 7:26 zenghongling
0 siblings, 0 replies; 2+ messages in thread
From: zenghongling @ 2026-03-05 7:26 UTC (permalink / raw)
To: dennis, tj, cl, akpm; +Cc: linux-mm, kernel, zhongling0719, zenghongling
The pcpu_chunk_struct has a hole of 4 bytes and pushes the struct to three
cachelines. Relocating the three booleans upwards allows for the struct
to only use two cachelines.
Before:
struct pcpu_chunk {
struct list_head list; /* 0 16 */
int free_bytes; /* 16 4 */
struct pcpu_block_md chunk_md; /* 20 32 */
/* XXX 4 bytes hole, try to pack */
long unsigned int * bound_map; /* 56 8 */
/* --- cacheline 1 boundary (64 bytes) --- */
void * base_addr __attribute__((__aligned__(64))); /* 64 8 */
long unsigned int * alloc_map; /* 72 8 */
struct pcpu_block_md * md_blocks; /* 80 8 */
void * data; /* 88 8 */
bool immutable; /* 96 1 */
bool isolated; /* 97 1 */
/* XXX 2 bytes hole, try to pack */
int start_offset; /* 100 4 */
int end_offset; /* 104 4 */
/* XXX 4 bytes hole, try to pack */
struct obj_cgroup * * obj_cgroups; /* 112 8 */
int nr_pages; /* 120 4 */
int nr_populated; /* 124 4 */
/* --- cacheline 2 boundary (128 bytes) --- */
int nr_empty_pop_pages; /* 128 4 */
/* XXX 4 bytes hole, try to pack */
long unsigned int populated[]; /* 136 0 */
/* size: 192, cachelines: 3, members: 17 */
/* sum members: 122, holes: 4, sum holes: 14 */
/* padding: 56 */
/* forced alignments: 1 */
} __attribute__((__aligned__(64)));
After:
struct pcpu_chunk {
struct list_head list; /* 0 16 */
int free_bytes; /* 16 4 */
struct pcpu_block_md chunk_md; /* 20 32 */
/* XXX 4 bytes hole, try to pack */
long unsigned int * bound_map; /* 56 8 */
/* --- cacheline 1 boundary (64 bytes) --- */
void * base_addr __attribute__((__aligned__(64))); /* 64 8 */
long unsigned int * alloc_map; /* 72 8 */
struct pcpu_block_md * md_blocks; /* 80 8 */
void * data; /* 88 8 */
bool immutable; /* 96 1 */
bool isolated; /* 97 1 */
/* XXX 2 bytes hole, try to pack */
int start_offset; /* 100 4 */
int end_offset; /* 104 4 */
int nr_empty_pop_pages; /* 108 4 */
struct obj_cgroup * * obj_cgroups; /* 112 8 */
int nr_pages; /* 120 4 */
int nr_populated; /* 124 4 */
/* --- cacheline 2 boundary (128 bytes) --- */
long unsigned int populated[]; /* 128 0 */
/* size: 128, cachelines: 2, members: 17 */
/* sum members: 122, holes: 2, sum holes: 6 */
/* forced alignments: 1 */
} __attribute__((__aligned__(64)));
Signed-off-by: zenghongling <zenghongling@kylinos.cn>
---
mm/percpu-internal.h | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/mm/percpu-internal.h b/mm/percpu-internal.h
index 4b3d6ec43703..26f3ac39f8c3 100644
--- a/mm/percpu-internal.h
+++ b/mm/percpu-internal.h
@@ -77,13 +77,13 @@ struct pcpu_chunk {
int end_offset; /* additional area required to
have the region end page
aligned */
+ int nr_empty_pop_pages; /* # of empty populated pages */
#ifdef NEED_PCPUOBJ_EXT
struct pcpuobj_ext *obj_exts; /* vector of object cgroups */
#endif
int nr_pages; /* # of pages served by this chunk */
int nr_populated; /* # of populated pages */
- int nr_empty_pop_pages; /* # of empty populated pages */
unsigned long populated[]; /* populated bitmap */
};
--
2.25.1
^ permalink raw reply [flat|nested] 2+ messages in thread
* [PATCH] mm/percpu-internal.h: optimise pcpu_chunk_struct to save memory
@ 2026-03-05 7:30 zenghongling
0 siblings, 0 replies; 2+ messages in thread
From: zenghongling @ 2026-03-05 7:30 UTC (permalink / raw)
To: dennis, tj, cl, akpm; +Cc: linux-mm, zhongling0719, zenghongling
The pcpu_chunk_struct has a hole of 4 bytes and pushes the struct to three
cachelines. Relocating the three booleans upwards allows for the struct
to only use two cachelines.
Before:
struct pcpu_chunk {
struct list_head list; /* 0 16 */
int free_bytes; /* 16 4 */
struct pcpu_block_md chunk_md; /* 20 32 */
/* XXX 4 bytes hole, try to pack */
long unsigned int * bound_map; /* 56 8 */
/* --- cacheline 1 boundary (64 bytes) --- */
void * base_addr __attribute__((__aligned__(64))); /* 64 8 */
long unsigned int * alloc_map; /* 72 8 */
struct pcpu_block_md * md_blocks; /* 80 8 */
void * data; /* 88 8 */
bool immutable; /* 96 1 */
bool isolated; /* 97 1 */
/* XXX 2 bytes hole, try to pack */
int start_offset; /* 100 4 */
int end_offset; /* 104 4 */
/* XXX 4 bytes hole, try to pack */
struct obj_cgroup * * obj_cgroups; /* 112 8 */
int nr_pages; /* 120 4 */
int nr_populated; /* 124 4 */
/* --- cacheline 2 boundary (128 bytes) --- */
int nr_empty_pop_pages; /* 128 4 */
/* XXX 4 bytes hole, try to pack */
long unsigned int populated[]; /* 136 0 */
/* size: 192, cachelines: 3, members: 17 */
/* sum members: 122, holes: 4, sum holes: 14 */
/* padding: 56 */
/* forced alignments: 1 */
} __attribute__((__aligned__(64)));
After:
struct pcpu_chunk {
struct list_head list; /* 0 16 */
int free_bytes; /* 16 4 */
struct pcpu_block_md chunk_md; /* 20 32 */
/* XXX 4 bytes hole, try to pack */
long unsigned int * bound_map; /* 56 8 */
/* --- cacheline 1 boundary (64 bytes) --- */
void * base_addr __attribute__((__aligned__(64))); /* 64 8 */
long unsigned int * alloc_map; /* 72 8 */
struct pcpu_block_md * md_blocks; /* 80 8 */
void * data; /* 88 8 */
bool immutable; /* 96 1 */
bool isolated; /* 97 1 */
/* XXX 2 bytes hole, try to pack */
int start_offset; /* 100 4 */
int end_offset; /* 104 4 */
int nr_empty_pop_pages; /* 108 4 */
struct obj_cgroup * * obj_cgroups; /* 112 8 */
int nr_pages; /* 120 4 */
int nr_populated; /* 124 4 */
/* --- cacheline 2 boundary (128 bytes) --- */
long unsigned int populated[]; /* 128 0 */
/* size: 128, cachelines: 2, members: 17 */
/* sum members: 122, holes: 2, sum holes: 6 */
/* forced alignments: 1 */
} __attribute__((__aligned__(64)));
Signed-off-by: zenghongling <zenghongling@kylinos.cn>
---
mm/percpu-internal.h | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/mm/percpu-internal.h b/mm/percpu-internal.h
index 4b3d6ec43703..26f3ac39f8c3 100644
--- a/mm/percpu-internal.h
+++ b/mm/percpu-internal.h
@@ -77,13 +77,13 @@ struct pcpu_chunk {
int end_offset; /* additional area required to
have the region end page
aligned */
+ int nr_empty_pop_pages; /* # of empty populated pages */
#ifdef NEED_PCPUOBJ_EXT
struct pcpuobj_ext *obj_exts; /* vector of object cgroups */
#endif
int nr_pages; /* # of pages served by this chunk */
int nr_populated; /* # of populated pages */
- int nr_empty_pop_pages; /* # of empty populated pages */
unsigned long populated[]; /* populated bitmap */
};
--
2.25.1
^ permalink raw reply [flat|nested] 2+ messages in thread
end of thread, other threads:[~2026-03-05 7:31 UTC | newest]
Thread overview: 2+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2026-03-05 7:26 [PATCH] mm/percpu-internal.h: optimise pcpu_chunk_struct to save memory zenghongling
2026-03-05 7:30 zenghongling
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox