#include <linux/wait.h>
#include <linux/pagemap.h>
#include <linux/fs.h>
+#include <linux/local_lock.h>
#define ZSPAGE_MAGIC 0x58
#define ZS_HANDLE_SIZE (sizeof(unsigned long))
+#ifdef CONFIG_PREEMPT_RT
+
+struct zsmalloc_handle {
+ unsigned long addr;
+ spinlock_t lock;
+};
+
+#define ZS_HANDLE_ALLOC_SIZE (sizeof(struct zsmalloc_handle))
+
+#else
+
+#define ZS_HANDLE_ALLOC_SIZE (sizeof(unsigned long))
+#endif
+
/*
* Object location (<PFN>, <obj_idx>) is encoded as
* a single (unsigned long) handle value.
};
struct mapping_area {
+ local_lock_t lock;
char *vm_buf; /* copy buffer for objects that span pages */
char *vm_addr; /* address of kmap_atomic()'ed pages */
enum zs_mapmode vm_mm; /* mapping mode */
static int create_cache(struct zs_pool *pool)
{
- pool->handle_cachep = kmem_cache_create("zs_handle", ZS_HANDLE_SIZE,
+ pool->handle_cachep = kmem_cache_create("zs_handle", ZS_HANDLE_ALLOC_SIZE,
0, 0, NULL);
if (!pool->handle_cachep)
return 1;
static unsigned long cache_alloc_handle(struct zs_pool *pool, gfp_t gfp)
{
- return (unsigned long)kmem_cache_alloc(pool->handle_cachep,
- gfp & ~(__GFP_HIGHMEM|__GFP_MOVABLE));
+ void *p;
+
+ p = kmem_cache_alloc(pool->handle_cachep,
+ gfp & ~(__GFP_HIGHMEM|__GFP_MOVABLE));
+#ifdef CONFIG_PREEMPT_RT
+ if (p) {
+ struct zsmalloc_handle *zh = p;
+
+ spin_lock_init(&zh->lock);
+ }
+#endif
+ return (unsigned long)p;
+}
+
+#ifdef CONFIG_PREEMPT_RT
+static struct zsmalloc_handle *zs_get_pure_handle(unsigned long handle)
+{
+ return (void *)(handle & ~((1 << OBJ_TAG_BITS) - 1));
}
+#endif
static void cache_free_handle(struct zs_pool *pool, unsigned long handle)
{
static void record_obj(unsigned long handle, unsigned long obj)
{
+#ifdef CONFIG_PREEMPT_RT
+ struct zsmalloc_handle *zh = zs_get_pure_handle(handle);
+
+ WRITE_ONCE(zh->addr, obj);
+#else
/*
* lsb of @obj represents handle lock while other bits
* represent object value the handle is pointing so
* updating shouldn't do store tearing.
*/
WRITE_ONCE(*(unsigned long *)handle, obj);
+#endif
}
/* zpool driver */
#endif /* CONFIG_ZPOOL */
/* per-cpu VM mapping areas for zspage accesses that cross page boundaries */
-static DEFINE_PER_CPU(struct mapping_area, zs_map_area);
+static DEFINE_PER_CPU(struct mapping_area, zs_map_area) = {
+ .lock = INIT_LOCAL_LOCK(lock),
+};
static bool is_zspage_isolated(struct zspage *zspage)
{
static unsigned long handle_to_obj(unsigned long handle)
{
+#ifdef CONFIG_PREEMPT_RT
+ struct zsmalloc_handle *zh = zs_get_pure_handle(handle);
+
+ return zh->addr;
+#else
return *(unsigned long *)handle;
+#endif
}
static unsigned long obj_to_head(struct page *page, void *obj)
static inline int testpin_tag(unsigned long handle)
{
+#ifdef CONFIG_PREEMPT_RT
+ struct zsmalloc_handle *zh = zs_get_pure_handle(handle);
+
+ return spin_is_locked(&zh->lock);
+#else
return bit_spin_is_locked(HANDLE_PIN_BIT, (unsigned long *)handle);
+#endif
}
static inline int trypin_tag(unsigned long handle)
{
+#ifdef CONFIG_PREEMPT_RT
+ struct zsmalloc_handle *zh = zs_get_pure_handle(handle);
+
+ return spin_trylock(&zh->lock);
+#else
return bit_spin_trylock(HANDLE_PIN_BIT, (unsigned long *)handle);
+#endif
}
static void pin_tag(unsigned long handle) __acquires(bitlock)
{
+#ifdef CONFIG_PREEMPT_RT
+ struct zsmalloc_handle *zh = zs_get_pure_handle(handle);
+
+ return spin_lock(&zh->lock);
+#else
bit_spin_lock(HANDLE_PIN_BIT, (unsigned long *)handle);
+#endif
}
static void unpin_tag(unsigned long handle) __releases(bitlock)
{
+#ifdef CONFIG_PREEMPT_RT
+ struct zsmalloc_handle *zh = zs_get_pure_handle(handle);
+
+ return spin_unlock(&zh->lock);
+#else
bit_spin_unlock(HANDLE_PIN_BIT, (unsigned long *)handle);
+#endif
}
static void reset_page(struct page *page)
class = pool->size_class[class_idx];
off = (class->size * obj_idx) & ~PAGE_MASK;
- area = &get_cpu_var(zs_map_area);
+ local_lock(&zs_map_area.lock);
+ area = this_cpu_ptr(&zs_map_area);
area->vm_mm = mm;
if (off + class->size <= PAGE_SIZE) {
/* this object is contained entirely within a page */
__zs_unmap_object(area, pages, off, class->size);
}
- put_cpu_var(zs_map_area);
+ local_unlock(&zs_map_area.lock);
migrate_read_unlock(zspage);
unpin_tag(handle);
*/
static void lock_zspage(struct zspage *zspage)
{
- struct page *page = get_first_page(zspage);
+ struct page *curr_page, *page;
- do {
- lock_page(page);
- } while ((page = get_next_page(page)) != NULL);
+ /*
+ * Pages we haven't locked yet can be migrated off the list while we're
+ * trying to lock them, so we need to be careful and only attempt to
+ * lock each page under migrate_read_lock(). Otherwise, the page we lock
+ * may no longer belong to the zspage. This means that we may wait for
+ * the wrong page to unlock, so we must take a reference to the page
+ * prior to waiting for it to unlock outside migrate_read_lock().
+ */
+ while (1) {
+ migrate_read_lock(zspage);
+ page = get_first_page(zspage);
+ if (trylock_page(page))
+ break;
+ get_page(page);
+ migrate_read_unlock(zspage);
+ wait_on_page_locked(page);
+ put_page(page);
+ }
+
+ curr_page = page;
+ while ((page = get_next_page(curr_page))) {
+ if (trylock_page(page)) {
+ curr_page = page;
+ } else {
+ get_page(page);
+ migrate_read_unlock(zspage);
+ wait_on_page_locked(page);
+ put_page(page);
+ migrate_read_lock(zspage);
+ }
+ }
+ migrate_read_unlock(zspage);
}
static int zs_init_fs_context(struct fs_context *fc)
VM_BUG_ON(atomic_long_read(&pool->isolated_pages) <= 0);
atomic_long_dec(&pool->isolated_pages);
/*
- * There's no possibility of racing, since wait_for_isolated_drain()
- * checks the isolated count under &class->lock after enqueuing
- * on migration_wait.
+ * Checking pool->destroying must happen after atomic_long_dec()
+ * for pool->isolated_pages above. Paired with the smp_mb() in
+ * zs_unregister_migration().
*/
+ smp_mb__after_atomic();
if (atomic_long_read(&pool->isolated_pages) == 0 && pool->destroying)
wake_up_all(&pool->migration_wait);
}