Merge branch 'slab/for-5.18/cleanups' into slab/for-linus

Non-trivial SLUB code cleanups, notably refactoring of deactivate_slab().
This commit is contained in:
Vlastimil Babka 2022-03-21 19:48:49 +01:00
commit 94fa31e99b

105
mm/slub.c
View File

@ -2348,10 +2348,10 @@ static void init_kmem_cache_cpus(struct kmem_cache *s)
static void deactivate_slab(struct kmem_cache *s, struct slab *slab,
void *freelist)
{
enum slab_modes { M_NONE, M_PARTIAL, M_FULL, M_FREE };
enum slab_modes { M_NONE, M_PARTIAL, M_FULL, M_FREE, M_FULL_NOLIST };
struct kmem_cache_node *n = get_node(s, slab_nid(slab));
int lock = 0, free_delta = 0;
enum slab_modes l = M_NONE, m = M_NONE;
int free_delta = 0;
enum slab_modes mode = M_NONE;
void *nextfree, *freelist_iter, *freelist_tail;
int tail = DEACTIVATE_TO_HEAD;
unsigned long flags = 0;
@ -2393,14 +2393,10 @@ static void deactivate_slab(struct kmem_cache *s, struct slab *slab,
* Ensure that the slab is unfrozen while the list presence
* reflects the actual number of objects during unfreeze.
*
* We setup the list membership and then perform a cmpxchg
* with the count. If there is a mismatch then the slab
* is not unfrozen but the slab is on the wrong list.
*
* Then we restart the process which may have to remove
* the slab from the list that we just put it on again
* because the number of objects in the slab may have
* changed.
* We first perform cmpxchg holding lock and insert to list
* when it succeed. If there is mismatch then the slab is not
* unfrozen and number of objects in the slab may have changed.
* Then release lock and retry cmpxchg again.
*/
redo:
@ -2419,61 +2415,52 @@ redo:
new.frozen = 0;
if (!new.inuse && n->nr_partial >= s->min_partial)
m = M_FREE;
else if (new.freelist) {
m = M_PARTIAL;
if (!lock) {
lock = 1;
/*
* Taking the spinlock removes the possibility that
* acquire_slab() will see a slab that is frozen
*/
spin_lock_irqsave(&n->list_lock, flags);
}
if (!new.inuse && n->nr_partial >= s->min_partial) {
mode = M_FREE;
} else if (new.freelist) {
mode = M_PARTIAL;
/*
* Taking the spinlock removes the possibility that
* acquire_slab() will see a slab that is frozen
*/
spin_lock_irqsave(&n->list_lock, flags);
} else if (kmem_cache_debug_flags(s, SLAB_STORE_USER)) {
mode = M_FULL;
/*
* This also ensures that the scanning of full
* slabs from diagnostic functions will not see
* any frozen slabs.
*/
spin_lock_irqsave(&n->list_lock, flags);
} else {
m = M_FULL;
if (kmem_cache_debug_flags(s, SLAB_STORE_USER) && !lock) {
lock = 1;
/*
* This also ensures that the scanning of full
* slabs from diagnostic functions will not see
* any frozen slabs.
*/
spin_lock_irqsave(&n->list_lock, flags);
}
mode = M_FULL_NOLIST;
}
if (l != m) {
if (l == M_PARTIAL)
remove_partial(n, slab);
else if (l == M_FULL)
remove_full(s, n, slab);
if (m == M_PARTIAL)
add_partial(n, slab, tail);
else if (m == M_FULL)
add_full(s, n, slab);
}
l = m;
if (!cmpxchg_double_slab(s, slab,
old.freelist, old.counters,
new.freelist, new.counters,
"unfreezing slab"))
"unfreezing slab")) {
if (mode == M_PARTIAL || mode == M_FULL)
spin_unlock_irqrestore(&n->list_lock, flags);
goto redo;
}
if (lock)
if (mode == M_PARTIAL) {
add_partial(n, slab, tail);
spin_unlock_irqrestore(&n->list_lock, flags);
if (m == M_PARTIAL)
stat(s, tail);
else if (m == M_FULL)
stat(s, DEACTIVATE_FULL);
else if (m == M_FREE) {
} else if (mode == M_FREE) {
stat(s, DEACTIVATE_EMPTY);
discard_slab(s, slab);
stat(s, FREE_SLAB);
} else if (mode == M_FULL) {
add_full(s, n, slab);
spin_unlock_irqrestore(&n->list_lock, flags);
stat(s, DEACTIVATE_FULL);
} else if (mode == M_FULL_NOLIST) {
stat(s, DEACTIVATE_FULL);
}
}
@ -4000,15 +3987,6 @@ static int init_kmem_cache_nodes(struct kmem_cache *s)
return 1;
}
static void set_min_partial(struct kmem_cache *s, unsigned long min)
{
if (min < MIN_PARTIAL)
min = MIN_PARTIAL;
else if (min > MAX_PARTIAL)
min = MAX_PARTIAL;
s->min_partial = min;
}
static void set_cpu_partial(struct kmem_cache *s)
{
#ifdef CONFIG_SLUB_CPU_PARTIAL
@ -4212,7 +4190,8 @@ static int kmem_cache_open(struct kmem_cache *s, slab_flags_t flags)
* The larger the object size is, the more slabs we want on the partial
* list to avoid pounding the page allocator excessively.
*/
set_min_partial(s, ilog2(s->size) / 2);
s->min_partial = min_t(unsigned long, MAX_PARTIAL, ilog2(s->size) / 2);
s->min_partial = max_t(unsigned long, MIN_PARTIAL, s->min_partial);
set_cpu_partial(s);
@ -5391,7 +5370,7 @@ static ssize_t min_partial_store(struct kmem_cache *s, const char *buf,
if (err)
return err;
set_min_partial(s, min);
s->min_partial = min;
return length;
}
SLAB_ATTR(min_partial);