[PATCH v9 12/17] mm: move lesser used vma_area_struct members into the last cacheline

[Suren Baghdasaryan <surenb@google.com>]

Move several vma_area_struct members which are rarely or never used
during page fault handling into the last cacheline to better pack
vm_area_struct. As a result vm_area_struct will fit into 3 as opposed
to 4 cachelines. New typical vm_area_struct layout:

struct vm_area_struct {
    union {
        struct {
            long unsigned int vm_start;              /*     0     8 */
            long unsigned int vm_end;                /*     8     8 */
        };                                           /*     0    16 */
        freeptr_t          vm_freeptr;               /*     0     8 */
    };                                               /*     0    16 */
    struct mm_struct *         vm_mm;                /*    16     8 */
    pgprot_t                   vm_page_prot;         /*    24     8 */
    union {
        const vm_flags_t   vm_flags;                 /*    32     8 */
        vm_flags_t         __vm_flags;               /*    32     8 */
    };                                               /*    32     8 */
    unsigned int               vm_lock_seq;          /*    40     4 */

    /* XXX 4 bytes hole, try to pack */

    struct list_head           anon_vma_chain;       /*    48    16 */
    /* --- cacheline 1 boundary (64 bytes) --- */
    struct anon_vma *          anon_vma;             /*    64     8 */
    const struct vm_operations_struct  * vm_ops;     /*    72     8 */
    long unsigned int          vm_pgoff;             /*    80     8 */
    struct file *              vm_file;              /*    88     8 */
    void *                     vm_private_data;      /*    96     8 */
    atomic_long_t              swap_readahead_info;  /*   104     8 */
    struct mempolicy *         vm_policy;            /*   112     8 */
    struct vma_numab_state *   numab_state;          /*   120     8 */
    /* --- cacheline 2 boundary (128 bytes) --- */
    refcount_t          vm_refcnt (__aligned__(64)); /*   128     4 */

    /* XXX 4 bytes hole, try to pack */

    struct {
        struct rb_node     rb (__aligned__(8));      /*   136    24 */
        long unsigned int  rb_subtree_last;          /*   160     8 */
    } __attribute__((__aligned__(8))) shared;        /*   136    32 */
    struct anon_vma_name *     anon_name;            /*   168     8 */
    struct vm_userfaultfd_ctx  vm_userfaultfd_ctx;   /*   176     8 */

    /* size: 192, cachelines: 3, members: 18 */
    /* sum members: 176, holes: 2, sum holes: 8 */
    /* padding: 8 */
    /* forced alignments: 2, forced holes: 1, sum forced holes: 4 */
} __attribute__((__aligned__(64)));

Memory consumption per 1000 VMAs becomes 48 pages:

    slabinfo after vm_area_struct changes:
     <name>           ... <objsize> <objperslab> <pagesperslab> : ...
     vm_area_struct   ...    192   42    2 : ...

Signed-off-by: Suren Baghdasaryan <surenb@google.com>
---
 include/linux/mm_types.h | 38 ++++++++++++++++++--------------------
 1 file changed, 18 insertions(+), 20 deletions(-)

diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 9228d19662c6..d902e6730654 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -725,17 +725,6 @@ struct vm_area_struct {
 	 */
 	unsigned int vm_lock_seq;
 #endif
-
-	/*
-	 * For areas with an address space and backing store,
-	 * linkage into the address_space->i_mmap interval tree.
-	 *
-	 */
-	struct {
-		struct rb_node rb;
-		unsigned long rb_subtree_last;
-	} shared;
-
 	/*
 	 * A file's MAP_PRIVATE vma can be in both i_mmap tree and anon_vma
 	 * list, after a COW of one of the file pages.	A MAP_SHARED vma
@@ -755,14 +744,6 @@ struct vm_area_struct {
 	struct file * vm_file;		/* File we map to (can be NULL). */
 	void * vm_private_data;		/* was vm_pte (shared mem) */
 
-#ifdef CONFIG_ANON_VMA_NAME
-	/*
-	 * For private and shared anonymous mappings, a pointer to a null
-	 * terminated string containing the name given to the vma, or NULL if
-	 * unnamed. Serialized by mmap_lock. Use anon_vma_name to access.
-	 */
-	struct anon_vma_name *anon_name;
-#endif
 #ifdef CONFIG_SWAP
 	atomic_long_t swap_readahead_info;
 #endif
@@ -775,7 +756,6 @@ struct vm_area_struct {
 #ifdef CONFIG_NUMA_BALANCING
 	struct vma_numab_state *numab_state;	/* NUMA Balancing state */
 #endif
-	struct vm_userfaultfd_ctx vm_userfaultfd_ctx;
 #ifdef CONFIG_PER_VMA_LOCK
 	/* Unstable RCU readers are allowed to read this. */
 	refcount_t vm_refcnt ____cacheline_aligned_in_smp;
@@ -783,6 +763,24 @@ struct vm_area_struct {
 	struct lockdep_map vmlock_dep_map;
 #endif
 #endif
+	/*
+	 * For areas with an address space and backing store,
+	 * linkage into the address_space->i_mmap interval tree.
+	 *
+	 */
+	struct {
+		struct rb_node rb;
+		unsigned long rb_subtree_last;
+	} shared;
+#ifdef CONFIG_ANON_VMA_NAME
+	/*
+	 * For private and shared anonymous mappings, a pointer to a null
+	 * terminated string containing the name given to the vma, or NULL if
+	 * unnamed. Serialized by mmap_lock. Use anon_vma_name to access.
+	 */
+	struct anon_vma_name *anon_name;
+#endif
+	struct vm_userfaultfd_ctx vm_userfaultfd_ctx;
 } __randomize_layout;
 
 #ifdef CONFIG_NUMA
-- 
2.47.1.613.gc27f4b7a9f-goog