v2 -> v3:
* patch 1-4: Abandoned
* patch 5:
- Eliminate "flags" (suggested by Uladzislau Rezki)
- Based on https://lkml.org/lkml/2019/6/6/455
and https://lkml.org/lkml/2019/7/3/661
v1 -> v2:
* patch 3: Rename __find_vmap_area to __search_va_in_busy_tree
instead of __search_va_from_busy_tree.
* patch 5: Add motivation and necessary test data to the commit
message.
* patch 5: Let va->flags use only some low bits of va_start
instead of completely overwriting va_start.
The current implementation of struct vmap_area wasted space.
After applying this commit, sizeof(struct vmap_area) has been
reduced from 11 words to 8 words.
Pengfei Li (1):
Modify struct vmap_area to reduce its size
include/linux/vmalloc.h | 20 +++++++++++++-------
mm/vmalloc.c | 24 ++++++++++--------------
2 files changed, 23 insertions(+), 21 deletions(-)
--
2.21.0
Objective
---------
The current implementation of struct vmap_area wasted space.
After applying this commit, sizeof(struct vmap_area) has been
reduced from 11 words to 8 words.
Description
-----------
1) Pack "subtree_max_size", "vm" and "purge_list".
It is correct because these three variables are used in different
states.
A) "subtree_max_size" is only used when vmap_area is in
"free" tree
B) "vm" is only used when vmap_area is in "busy" tree
C) "purge_list" is only used when vmap_area is in
vmap_purge_list
2) Eliminate "flags".
Since now only one flag VM_VM_AREA is being used, and the same
thing can be done by judging whether "vm" is NULL, then the
"flags" can be eliminated.
Signed-off-by: Pengfei Li <[email protected]>
Suggested-by: Uladzislau Rezki (Sony) <[email protected]>
---
include/linux/vmalloc.h | 20 +++++++++++++-------
mm/vmalloc.c | 24 ++++++++++--------------
2 files changed, 23 insertions(+), 21 deletions(-)
diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h
index 51e131245379..2bc04b717600 100644
--- a/include/linux/vmalloc.h
+++ b/include/linux/vmalloc.h
@@ -51,15 +51,21 @@ struct vmap_area {
unsigned long va_start;
unsigned long va_end;
- /*
- * Largest available free size in subtree.
- */
- unsigned long subtree_max_size;
- unsigned long flags;
struct rb_node rb_node; /* address sorted rbtree */
struct list_head list; /* address sorted list */
- struct llist_node purge_list; /* "lazy purge" list */
- struct vm_struct *vm;
+
+ /*
+ * The following three variables can be packed, because
+ * a vmap_area object is always one of the three states:
+ * 1) in "free" tree (root is vmap_area_root)
+ * 2) in "busy" tree (root is free_vmap_area_root)
+ * 3) in purge list (head is vmap_purge_list)
+ */
+ union {
+ unsigned long subtree_max_size; /* in "free" tree */
+ struct vm_struct *vm; /* in "buys" tree */
+ struct llist_node purge_list; /* in purge list */
+ };
};
/*
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index 948f4e35341b..07c1823d7ea5 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -329,7 +329,6 @@ EXPORT_SYMBOL(vmalloc_to_pfn);
#define DEBUG_AUGMENT_PROPAGATE_CHECK 0
#define DEBUG_AUGMENT_LOWEST_MATCH_CHECK 0
-#define VM_VM_AREA 0x04
static DEFINE_SPINLOCK(vmap_area_lock);
/* Export for kexec only */
@@ -1108,7 +1107,7 @@ static struct vmap_area *alloc_vmap_area(unsigned long size,
va->va_start = addr;
va->va_end = addr + size;
- va->flags = 0;
+ va->vm = NULL;
insert_vmap_area(va, &vmap_area_root, &vmap_area_list);
spin_unlock(&vmap_area_lock);
@@ -1912,7 +1911,6 @@ void __init vmalloc_init(void)
if (WARN_ON_ONCE(!va))
continue;
- va->flags = VM_VM_AREA;
va->va_start = (unsigned long)tmp->addr;
va->va_end = va->va_start + tmp->size;
va->vm = tmp;
@@ -2010,7 +2008,6 @@ static void setup_vmalloc_vm(struct vm_struct *vm, struct vmap_area *va,
vm->size = va->va_end - va->va_start;
vm->caller = caller;
va->vm = vm;
- va->flags |= VM_VM_AREA;
spin_unlock(&vmap_area_lock);
}
@@ -2115,10 +2112,10 @@ struct vm_struct *find_vm_area(const void *addr)
struct vmap_area *va;
va = find_vmap_area((unsigned long)addr);
- if (va && va->flags & VM_VM_AREA)
- return va->vm;
+ if (!va)
+ return NULL;
- return NULL;
+ return va->vm;
}
/**
@@ -2139,11 +2136,10 @@ struct vm_struct *remove_vm_area(const void *addr)
spin_lock(&vmap_area_lock);
va = __find_vmap_area((unsigned long)addr);
- if (va && va->flags & VM_VM_AREA) {
+ if (va && va->vm) {
struct vm_struct *vm = va->vm;
va->vm = NULL;
- va->flags &= ~VM_VM_AREA;
spin_unlock(&vmap_area_lock);
kasan_free_shadow(vm);
@@ -2854,7 +2850,7 @@ long vread(char *buf, char *addr, unsigned long count)
if (!count)
break;
- if (!(va->flags & VM_VM_AREA))
+ if (!va->vm)
continue;
vm = va->vm;
@@ -2934,7 +2930,7 @@ long vwrite(char *buf, char *addr, unsigned long count)
if (!count)
break;
- if (!(va->flags & VM_VM_AREA))
+ if (!va->vm)
continue;
vm = va->vm;
@@ -3464,10 +3460,10 @@ static int s_show(struct seq_file *m, void *p)
va = list_entry(p, struct vmap_area, list);
/*
- * s_show can encounter race with remove_vm_area, !VM_VM_AREA on
- * behalf of vmap area is being tear down or vm_map_ram allocation.
+ * If !va->vm then this vmap_area object is allocated
+ * by vm_map_ram.
*/
- if (!(va->flags & VM_VM_AREA)) {
+ if (!va->vm) {
seq_printf(m, "0x%pK-0x%pK %7ld vm_map_ram\n",
(void *)va->va_start, (void *)va->va_end,
va->va_end - va->va_start);
--
2.21.0