pnfs-obj: report errors and .encode_layoutreturn Implementation.

An io_state pre-allocates an error information structure for each
possible osd-device that might error during IO. When IO is done if all
was well the io_state is freed. (as today). If the I/O has ended with an
error, the io_state is queued on a per-layout err_list. When eventually
encode_layoutreturn() is called, each error is properly encoded on the
XDR buffer and only then the io_state is removed from err_list and
de-allocated.

It is up to the io_engine to fill in the segment that fault and the type
of osd_error that occurred. By calling objlayout_io_set_result() for
each failing device.

In objio_osd:
* Allocate io-error descriptors space as part of io_state
* Use generic objlayout error reporting at end of io.

Signed-off-by: Boaz Harrosh <bharrosh@panasas.com>
Signed-off-by: Benny Halevy <bhalevy@panasas.com>

1 files changed, 43 insertions, 1 deletions

diff --git a/fs/nfs/objlayout/objio_osd.c b/fs/nfs/objlayout/objio_osd.c
index 4e8de3ec9a63..8bca5e13f3ef 100644
--- a/fs/nfs/objlayout/objio_osd.c
+++ b/fs/nfs/objlayout/objio_osd.c
@@ -396,12 +396,16 @@ int objio_alloc_io_state(struct pnfs_layout_segment *lseg,
         struct objio_state *ios;
         const unsigned first_size = sizeof(*ios) +
                                 objio_seg->num_comps * sizeof(ios->per_dev[0]);
+        const unsigned sec_size = objio_seg->num_comps *
+                                                sizeof(ios->ol_state.ioerrs[0]);
 
-        ios = kzalloc(first_size, gfp_flags);
+        ios = kzalloc(first_size + sec_size, gfp_flags);
         if (unlikely(!ios))
                 return -ENOMEM;
 
         ios->layout = objio_seg;
+        ios->ol_state.ioerrs = ((void *)ios) + first_size;
+        ios->ol_state.num_comps = objio_seg->num_comps;
 
         *outp = &ios->ol_state;
         return 0;
@@ -415,6 +419,36 @@ void objio_free_io_state(struct objlayout_io_state *ol_state)
         kfree(ios);
 }
 
+enum pnfs_osd_errno osd_pri_2_pnfs_err(enum osd_err_priority oep)
+{
+        switch (oep) {
+        case OSD_ERR_PRI_NO_ERROR:
+                return (enum pnfs_osd_errno)0;
+
+        case OSD_ERR_PRI_CLEAR_PAGES:
+                BUG_ON(1);
+                return 0;
+
+        case OSD_ERR_PRI_RESOURCE:
+                return PNFS_OSD_ERR_RESOURCE;
+        case OSD_ERR_PRI_BAD_CRED:
+                return PNFS_OSD_ERR_BAD_CRED;
+        case OSD_ERR_PRI_NO_ACCESS:
+                return PNFS_OSD_ERR_NO_ACCESS;
+        case OSD_ERR_PRI_UNREACHABLE:
+                return PNFS_OSD_ERR_UNREACHABLE;
+        case OSD_ERR_PRI_NOT_FOUND:
+                return PNFS_OSD_ERR_NOT_FOUND;
+        case OSD_ERR_PRI_NO_SPACE:
+                return PNFS_OSD_ERR_NO_SPACE;
+        default:
+                WARN_ON(1);
+                /* fallthrough */
+        case OSD_ERR_PRI_EIO:
+                return PNFS_OSD_ERR_EIO;
+        }
+}
+
 static void _clear_bio(struct bio *bio)
 {
         struct bio_vec *bv;
@@ -461,6 +495,12 @@ static int _io_check(struct objio_state *ios, bool is_write)
                         continue; /* we recovered */
                 }
                 dev = ios->per_dev[i].dev;
+                objlayout_io_set_result(&ios->ol_state, dev,
+                                        &ios->layout->comps[dev].oc_object_id,
+                                        osd_pri_2_pnfs_err(osi.osd_err_pri),
+                                        ios->per_dev[i].offset,
+                                        ios->per_dev[i].length,
+                                        is_write);
 
                 if (osi.osd_err_pri >= oep) {
                         oep = osi.osd_err_pri;
@@ -977,6 +1017,8 @@ static struct pnfs_layoutdriver_type objlayout_type = {
         .pg_test                 = objlayout_pg_test,
 
         .free_deviceid_node      = objio_free_deviceid_node,
+
+        .encode_layoutreturn     = objlayout_encode_layoutreturn,
 };
 
 MODULE_DESCRIPTION("pNFS Layout Driver for OSD2 objects");