mm/percpu-internal.h: optimise pcpu_chunk struct to save memory

Using pahole, we can see that there are some padding holes in the current
pcpu_chunk structure,Adjusting the layout of pcpu_chunk can reduce these
holes,decreasing its size from 192 bytes to 128 bytes and eliminating a
wasted cache line.

With allmodconfig (CONFIG_PERCPU_STATS + NEED_PCPUOBJ_EXT)
Before:
 /* size: 256, cachelines: 4, members: 19 */

After:
 /* size: 192, cachelines: 3, members: 19 */

with NEED_PCPUOBJ_EXT
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_pages;             /*   108     4 */
	int                        nr_populated;         /*   112     4 */
	int                        nr_empty_pop_pages;   /*   116     4 */
	struct obj_cgroup * *      obj_cgroups;          /*   120     8 */
	/* --- 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)));

Link: https://lore.kernel.org/20260511070309.44044-1-zenghongling@kylinos.cn
Signed-off-by: zenghongling <zenghongling@kylinos.cn>
Suggested-by: Dennis Zhou <dennis@kernel.org>
Acked-by: Dennis Zhou <dennis@kernel.org>
Cc: Tejun Heo <tj@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

diff --git a/mm/percpu-internal.h b/mm/percpu-internal.h
index 4b3d6ec43703eb7db042546ebf0600787f9017ff..8cbe039bf847ac03fddb403a4c135747742b2ff2 100644 (file)
--- 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_pages;       /* # of pages served by this chunk */
+       int                     nr_populated;   /* # of populated pages */
+       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 */
 };