rbd: flush dcache after zeroing page data

[~andy/linux] / drivers / block / rbd.c

diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c
index d6d314027b5d45a95ee762ef3c55dcb0769e15a8..cb728a01a19f2c5981fe98896ae42612c2798f06 100644 (file)
--- a/drivers/block/rbd.c
+++ b/drivers/block/rbd.c
@@ -519,8 +519,8 @@ static const struct block_device_operations rbd_bd_ops = {
 };
 
 /*
- * Initialize an rbd client instance.
- * We own *ceph_opts.
+ * Initialize an rbd client instance.  Success or not, this function
+ * consumes ceph_opts.
  */
 static struct rbd_client *rbd_client_create(struct ceph_options *ceph_opts)
 {
@@ -675,7 +675,8 @@ static int parse_rbd_opts_token(char *c, void *private)
 
 /*
  * Get a ceph client with specific addr and configuration, if one does
- * not exist create it.
+ * not exist create it.  Either way, ceph_opts is consumed by this
+ * function.
  */
 static struct rbd_client *rbd_get_client(struct ceph_options *ceph_opts)
 {
@@ -1035,12 +1036,16 @@ static const char *rbd_segment_name(struct rbd_device *rbd_dev, u64 offset)
        char *name;
        u64 segment;
        int ret;
+       char *name_format;
 
        name = kmem_cache_alloc(rbd_segment_name_cache, GFP_NOIO);
        if (!name)
                return NULL;
        segment = offset >> rbd_dev->header.obj_order;
-       ret = snprintf(name, MAX_OBJ_NAME_SIZE + 1, "%s.%012llx",
+       name_format = "%s.%012llx";
+       if (rbd_dev->image_format == 2)
+               name_format = "%s.%016llx";
+       ret = snprintf(name, MAX_OBJ_NAME_SIZE + 1, name_format,
                        rbd_dev->header.object_prefix, segment);
        if (ret < 0 || ret > MAX_OBJ_NAME_SIZE) {
                pr_err("error formatting segment name for #%llu (%d)\n",
@@ -1121,6 +1126,7 @@ static void zero_bio_chain(struct bio *chain, int start_ofs)
                                buf = bvec_kmap_irq(bv, &flags);
                                memset(buf + remainder, 0,
                                       bv->bv_len - remainder);
+                               flush_dcache_page(bv->bv_page);
                                bvec_kunmap_irq(buf, &flags);
                        }
                        pos += bv->bv_len;
@@ -1148,11 +1154,12 @@ static void zero_pages(struct page **pages, u64 offset, u64 end)
                unsigned long flags;
                void *kaddr;
 
-               page_offset = (size_t)(offset & ~PAGE_MASK);
-               length = min(PAGE_SIZE - page_offset, (size_t)(end - offset));
+               page_offset = offset & ~PAGE_MASK;
+               length = min_t(size_t, PAGE_SIZE - page_offset, end - offset);
                local_irq_save(flags);
                kaddr = kmap_atomic(*page);
                memset(kaddr + page_offset, 0, length);
+               flush_dcache_page(*page);
                kunmap_atomic(kaddr);
                local_irq_restore(flags);
 
@@ -2247,13 +2254,17 @@ static int rbd_img_request_fill(struct rbd_img_request *img_request,
                                        obj_request->pages, length,
                                        offset & ~PAGE_MASK, false, false);
 
+               /*
+                * set obj_request->img_request before formatting
+                * the osd_request so that it gets the right snapc
+                */
+               rbd_img_obj_request_add(img_request, obj_request);
                if (write_request)
                        rbd_osd_req_format_write(obj_request);
                else
                        rbd_osd_req_format_read(obj_request);
 
                obj_request->img_offset = img_offset;
-               rbd_img_obj_request_add(img_request, obj_request);
 
                img_offset += length;
                resid -= length;
@@ -2526,6 +2537,7 @@ static void rbd_img_obj_exists_callback(struct rbd_obj_request *obj_request)
         */
        orig_request = obj_request->obj_request;
        obj_request->obj_request = NULL;
+       rbd_obj_request_put(orig_request);
        rbd_assert(orig_request);
        rbd_assert(orig_request->img_request);
 
@@ -2546,7 +2558,6 @@ static void rbd_img_obj_exists_callback(struct rbd_obj_request *obj_request)
        if (!rbd_dev->parent_overlap) {
                struct ceph_osd_client *osdc;
 
-               rbd_obj_request_put(orig_request);
                osdc = &rbd_dev->rbd_client->client->osdc;
                result = rbd_obj_request_submit(osdc, orig_request);
                if (!result)
@@ -2576,7 +2587,6 @@ static void rbd_img_obj_exists_callback(struct rbd_obj_request *obj_request)
 out:
        if (orig_request->result)
                rbd_obj_request_complete(orig_request);
-       rbd_obj_request_put(orig_request);
 }
 
 static int rbd_img_obj_exists_submit(struct rbd_obj_request *obj_request)
@@ -4238,6 +4248,10 @@ static int rbd_dev_v2_header_info(struct rbd_device *rbd_dev)
 
        down_write(&rbd_dev->header_rwsem);
 
+       ret = rbd_dev_v2_image_size(rbd_dev);
+       if (ret)
+               goto out;
+
        if (first_time) {
                ret = rbd_dev_v2_header_onetime(rbd_dev);
                if (ret)
@@ -4271,10 +4285,6 @@ static int rbd_dev_v2_header_info(struct rbd_device *rbd_dev)
                                        "is EXPERIMENTAL!");
        }
 
-       ret = rbd_dev_v2_image_size(rbd_dev);
-       if (ret)
-               goto out;
-
        if (rbd_dev->spec->snap_id == CEPH_NOSNAP)
                if (rbd_dev->mapping.size != rbd_dev->header.image_size)
                        rbd_dev->mapping.size = rbd_dev->header.image_size;
@@ -4697,8 +4707,10 @@ out:
        return ret;
 }
 
-/* Undo whatever state changes are made by v1 or v2 image probe */
-
+/*
+ * Undo whatever state changes are made by v1 or v2 header info
+ * call.
+ */
 static void rbd_dev_unprobe(struct rbd_device *rbd_dev)
 {
        struct rbd_image_header *header;
@@ -4902,9 +4914,10 @@ static int rbd_dev_image_probe(struct rbd_device *rbd_dev, bool mapping)
        int tmp;
 
        /*
-        * Get the id from the image id object.  If it's not a
-        * format 2 image, we'll get ENOENT back, and we'll assume
-        * it's a format 1 image.
+        * Get the id from the image id object.  Unless there's an
+        * error, rbd_dev->spec->image_id will be filled in with
+        * a dynamically-allocated string, and rbd_dev->image_format
+        * will be set to either 1 or 2.
         */
        ret = rbd_dev_image_id(rbd_dev);
        if (ret)
@@ -4992,7 +5005,6 @@ static ssize_t rbd_add(struct bus_type *bus,
                rc = PTR_ERR(rbdc);
                goto err_out_args;
        }
-       ceph_opts = NULL;       /* rbd_dev client now owns this */
 
        /* pick the pool */
        osdc = &rbdc->client->osdc;
@@ -5027,18 +5039,18 @@ static ssize_t rbd_add(struct bus_type *bus,
        rbd_dev->mapping.read_only = read_only;
 
        rc = rbd_dev_device_setup(rbd_dev);
-       if (!rc)
-               return count;
+       if (rc) {
+               rbd_dev_image_release(rbd_dev);
+               goto err_out_module;
+       }
+
+       return count;
 
-       rbd_dev_image_release(rbd_dev);
 err_out_rbd_dev:
        rbd_dev_destroy(rbd_dev);
 err_out_client:
        rbd_put_client(rbdc);
 err_out_args:
-       if (ceph_opts)
-               ceph_destroy_options(ceph_opts);
-       kfree(rbd_opts);
        rbd_spec_put(spec);
 err_out_module:
        module_put(THIS_MODULE);