#include <linux/ceph/mon_client.h>
#include <linux/ceph/decode.h>
#include <linux/parser.h>
+#include <linux/bsearch.h>
#include <linux/kernel.h>
#include <linux/device.h>
#include <linux/module.h>
#include <linux/fs.h>
#include <linux/blkdev.h>
+#include <linux/slab.h>
#include "rbd_types.h"
static LIST_HEAD(rbd_client_list); /* clients */
static DEFINE_SPINLOCK(rbd_client_list_lock);
+/* Slab caches for frequently-allocated structures */
+
+static struct kmem_cache *rbd_img_request_cache;
+static struct kmem_cache *rbd_obj_request_cache;
+static struct kmem_cache *rbd_segment_name_cache;
+
static int rbd_img_request_submit(struct rbd_img_request *img_request);
static void rbd_dev_device_release(struct device *dev);
return kstrdup(snap_name, GFP_KERNEL);
}
+/*
+ * Snapshot id comparison function for use with qsort()/bsearch().
+ * Note that result is for snapshots in *descending* order.
+ */
+static int snapid_compare_reverse(const void *s1, const void *s2)
+{
+ u64 snap_id1 = *(u64 *)s1;
+ u64 snap_id2 = *(u64 *)s2;
+
+ if (snap_id1 < snap_id2)
+ return 1;
+ return snap_id1 == snap_id2 ? 0 : -1;
+}
+
+/*
+ * Search a snapshot context to see if the given snapshot id is
+ * present.
+ *
+ * Returns the position of the snapshot id in the array if it's found,
+ * or BAD_SNAP_INDEX otherwise.
+ *
+ * Note: The snapshot array is in kept sorted (by the osd) in
+ * reverse order, highest snapshot id first.
+ */
static u32 rbd_dev_snap_index(struct rbd_device *rbd_dev, u64 snap_id)
{
struct ceph_snap_context *snapc = rbd_dev->header.snapc;
- u32 which;
+ u64 *found;
- for (which = 0; which < snapc->num_snaps; which++)
- if (snapc->snaps[which] == snap_id)
- return which;
+ found = bsearch(&snap_id, &snapc->snaps, snapc->num_snaps,
+ sizeof (snap_id), snapid_compare_reverse);
- return BAD_SNAP_INDEX;
+ return found ? (u32)(found - &snapc->snaps[0]) : BAD_SNAP_INDEX;
}
static const char *rbd_dev_v1_snap_name(struct rbd_device *rbd_dev,
u64 segment;
int ret;
- name = kmalloc(MAX_OBJ_NAME_SIZE + 1, GFP_NOIO);
+ name = kmem_cache_alloc(rbd_segment_name_cache, GFP_NOIO);
if (!name)
return NULL;
segment = offset >> rbd_dev->header.obj_order;
return name;
}
+static void rbd_segment_name_free(const char *name)
+{
+ /* The explicit cast here is needed to drop the const qualifier */
+
+ kmem_cache_free(rbd_segment_name_cache, (void *)name);
+}
+
static u64 rbd_segment_offset(struct rbd_device *rbd_dev, u64 offset)
{
u64 segment_size = (u64) 1 << rbd_dev->header.obj_order;
rbd_assert(obj_request_type_valid(type));
size = strlen(object_name) + 1;
- obj_request = kzalloc(sizeof (*obj_request) + size, GFP_KERNEL);
- if (!obj_request)
+ name = kmalloc(size, GFP_KERNEL);
+ if (!name)
+ return NULL;
+
+ obj_request = kmem_cache_zalloc(rbd_obj_request_cache, GFP_KERNEL);
+ if (!obj_request) {
+ kfree(name);
return NULL;
+ }
- name = (char *)(obj_request + 1);
obj_request->object_name = memcpy(name, object_name, size);
obj_request->offset = offset;
obj_request->length = length;
break;
}
- kfree(obj_request);
+ kfree(obj_request->object_name);
+ obj_request->object_name = NULL;
+ kmem_cache_free(rbd_obj_request_cache, obj_request);
}
/*
{
struct rbd_img_request *img_request;
- img_request = kmalloc(sizeof (*img_request), GFP_ATOMIC);
+ img_request = kmem_cache_alloc(rbd_img_request_cache, GFP_ATOMIC);
if (!img_request)
return NULL;
if (img_request_child_test(img_request))
rbd_obj_request_put(img_request->obj_request);
- kfree(img_request);
+ kmem_cache_free(rbd_img_request_cache, img_request);
}
static bool rbd_img_obj_end_request(struct rbd_obj_request *obj_request)
length = rbd_segment_length(rbd_dev, img_offset, resid);
obj_request = rbd_obj_request_create(object_name,
offset, length, type);
- kfree(object_name); /* object request has its own copy */
+ /* object request has its own copy of the object name */
+ rbd_segment_name_free(object_name);
if (!obj_request)
goto out_unwind;
obj_request->xferred = img_request->xferred;
}
out:
+ rbd_img_request_put(img_request);
rbd_img_obj_request_read_callback(obj_request);
rbd_obj_request_complete(obj_request);
}
return ret;
}
+/*
+ * Clear the rbd device's EXISTS flag if the snapshot it's mapped to
+ * has disappeared from the (just updated) snapshot context.
+ */
+static void rbd_exists_validate(struct rbd_device *rbd_dev)
+{
+ u64 snap_id;
+
+ if (!test_bit(RBD_DEV_FLAG_EXISTS, &rbd_dev->flags))
+ return;
+
+ snap_id = rbd_dev->spec->snap_id;
+ if (snap_id == CEPH_NOSNAP)
+ return;
+
+ if (rbd_dev_snap_index(rbd_dev, snap_id) == BAD_SNAP_INDEX)
+ clear_bit(RBD_DEV_FLAG_EXISTS, &rbd_dev->flags);
+}
+
static int rbd_dev_refresh(struct rbd_device *rbd_dev)
{
u64 image_size;
ret = rbd_dev_v1_refresh(rbd_dev);
else
ret = rbd_dev_v2_refresh(rbd_dev);
+
+ /* If it's a mapped snapshot, validate its EXISTS flag */
+
+ rbd_exists_validate(rbd_dev);
mutex_unlock(&ctl_mutex);
if (ret)
rbd_warn(rbd_dev, "got notification but failed to "
device_unregister(&rbd_root_dev);
}
+static int rbd_slab_init(void)
+{
+ rbd_assert(!rbd_img_request_cache);
+ rbd_img_request_cache = kmem_cache_create("rbd_img_request",
+ sizeof (struct rbd_img_request),
+ __alignof__(struct rbd_img_request),
+ 0, NULL);
+ if (!rbd_img_request_cache)
+ return -ENOMEM;
+
+ rbd_assert(!rbd_obj_request_cache);
+ rbd_obj_request_cache = kmem_cache_create("rbd_obj_request",
+ sizeof (struct rbd_obj_request),
+ __alignof__(struct rbd_obj_request),
+ 0, NULL);
+ if (!rbd_obj_request_cache)
+ goto out_err;
+
+ rbd_assert(!rbd_segment_name_cache);
+ rbd_segment_name_cache = kmem_cache_create("rbd_segment_name",
+ MAX_OBJ_NAME_SIZE + 1, 1, 0, NULL);
+ if (rbd_segment_name_cache)
+ return 0;
+out_err:
+ if (rbd_obj_request_cache) {
+ kmem_cache_destroy(rbd_obj_request_cache);
+ rbd_obj_request_cache = NULL;
+ }
+
+ kmem_cache_destroy(rbd_img_request_cache);
+ rbd_img_request_cache = NULL;
+
+ return -ENOMEM;
+}
+
+static void rbd_slab_exit(void)
+{
+ rbd_assert(rbd_segment_name_cache);
+ kmem_cache_destroy(rbd_segment_name_cache);
+ rbd_segment_name_cache = NULL;
+
+ rbd_assert(rbd_obj_request_cache);
+ kmem_cache_destroy(rbd_obj_request_cache);
+ rbd_obj_request_cache = NULL;
+
+ rbd_assert(rbd_img_request_cache);
+ kmem_cache_destroy(rbd_img_request_cache);
+ rbd_img_request_cache = NULL;
+}
+
static int __init rbd_init(void)
{
int rc;
return -EINVAL;
}
- rc = rbd_sysfs_init();
+ rc = rbd_slab_init();
if (rc)
return rc;
- pr_info("loaded " RBD_DRV_NAME_LONG "\n");
- return 0;
+ rc = rbd_sysfs_init();
+ if (rc)
+ rbd_slab_exit();
+ else
+ pr_info("loaded " RBD_DRV_NAME_LONG "\n");
+
+ return rc;
}
static void __exit rbd_exit(void)
{
rbd_sysfs_cleanup();
+ rbd_slab_exit();
}
module_init(rbd_init);