Memory errors are at least somewhat more likely on disaggregated memory
than on-board memory. This commit registers to be notified by fsdev_dax
in the event that a memory failure is detected.

When a file access resolves to a daxdev with memory errors, it will fail
with an appropriate error.

If a daxdev failed fs_dax_get(), we set dd->dax_err. If a daxdev called
our notify_failure(), set dd->error. When any of the above happens, set
(file)->error and stop allowing access.

In general, the recovery from memory errors is to unmount the file
system and re-initialize the memory, but there may be usable degraded
modes of operation - particularly in the future when famfs supports
file systems backed by more than one daxdev. In those cases,
accessing data that is on a working daxdev can still work.

For now, return errors for any file that has encountered a memory or dax
error.

Signed-off-by: John Groves <[email protected]>
---
 fs/fuse/famfs.c       | 115 +++++++++++++++++++++++++++++++++++++++---
 fs/fuse/famfs_kfmap.h |   3 +-
 2 files changed, 109 insertions(+), 9 deletions(-)

diff --git a/fs/fuse/famfs.c b/fs/fuse/famfs.c
index c02b14789c6e..4eb87c5c628e 100644
--- a/fs/fuse/famfs.c
+++ b/fs/fuse/famfs.c
@@ -20,6 +20,26 @@
 #include "famfs_kfmap.h"
 #include "fuse_i.h"
 
+static void famfs_set_daxdev_err(
+       struct fuse_conn *fc, struct dax_device *dax_devp);
+
+static int
+famfs_dax_notify_failure(struct dax_device *dax_devp, u64 offset,
+                       u64 len, int mf_flags)
+{
+       struct fuse_conn *fc = dax_holder(dax_devp);
+
+       famfs_set_daxdev_err(fc, dax_devp);
+
+       return 0;
+}
+
+static const struct dax_holder_operations famfs_fuse_dax_holder_ops = {
+       .notify_failure         = famfs_dax_notify_failure,
+};
+
+/*****************************************************************************/
+
 /*
  * famfs_teardown()
  *
@@ -48,9 +68,12 @@ famfs_teardown(struct fuse_conn *fc)
                if (!dd->valid)
                        continue;
 
-               /* Release reference from dax_dev_get() */
-               if (dd->devp)
+               /* Only call fs_put_dax if fs_dax_get succeeded */
+               if (dd->devp) {
+                       if (!dd->dax_err)
+                               fs_put_dax(dd->devp, fc);
                        put_dax(dd->devp);
+               }
 
                kfree(dd->name);
        }
@@ -174,6 +197,17 @@ famfs_fuse_get_daxdev(struct fuse_mount *fm, const u64 
index)
                goto out;
        }
 
+       err = fs_dax_get(daxdev->devp, fc, &famfs_fuse_dax_holder_ops);
+       if (err) {
+               /* If fs_dax_get() fails, we don't attempt recovery;
+                * We mark the daxdev valid with dax_err
+                */
+               daxdev->dax_err = 1;
+               pr_err("%s: fs_dax_get(%lld) failed\n",
+                      __func__, (u64)daxdev->devno);
+               err = -EBUSY;
+       }
+
        daxdev->name = kstrdup(daxdev_out.name, GFP_KERNEL);
        wmb(); /* all daxdev fields must be visible before marking it valid */
        daxdev->valid = 1;
@@ -254,6 +288,38 @@ famfs_update_daxdev_table(
        return 0;
 }
 
+static void
+famfs_set_daxdev_err(
+       struct fuse_conn *fc,
+       struct dax_device *dax_devp)
+{
+       int i;
+
+       /* Gotta search the list by dax_devp;
+        * read lock because we're not adding or removing daxdev entries
+        */
+       down_read(&fc->famfs_devlist_sem);
+       for (i = 0; i < fc->dax_devlist->nslots; i++) {
+               if (fc->dax_devlist->devlist[i].valid) {
+                       struct famfs_daxdev *dd = &fc->dax_devlist->devlist[i];
+
+                       if (dd->devp != dax_devp)
+                               continue;
+
+                       dd->error = true;
+                       up_read(&fc->famfs_devlist_sem);
+
+                       pr_err("%s: memory error on daxdev %s (%d)\n",
+                              __func__, dd->name, i);
+                       goto done;
+               }
+       }
+       up_read(&fc->famfs_devlist_sem);
+       pr_err("%s: memory err on unrecognized daxdev\n", __func__);
+
+done:
+}
+
 /***************************************************************************/
 
 void
@@ -611,6 +677,26 @@ famfs_file_init_dax(
 
 static ssize_t famfs_file_bad(struct inode *inode);
 
+static int famfs_dax_err(struct famfs_daxdev *dd)
+{
+       if (!dd->valid) {
+               pr_err("%s: daxdev=%s invalid\n",
+                      __func__, dd->name);
+               return -EIO;
+       }
+       if (dd->dax_err) {
+               pr_err("%s: daxdev=%s dax_err\n",
+                      __func__, dd->name);
+               return -EIO;
+       }
+       if (dd->error) {
+               pr_err("%s: daxdev=%s memory error\n",
+                      __func__, dd->name);
+               return -EHWPOISON;
+       }
+       return 0;
+}
+
 static int
 famfs_interleave_fileofs_to_daxofs(struct inode *inode, struct iomap *iomap,
                         loff_t file_offset, off_t len, unsigned int flags)
@@ -648,6 +734,7 @@ famfs_interleave_fileofs_to_daxofs(struct inode *inode, 
struct iomap *iomap,
 
                /* Is the data is in this striped extent? */
                if (local_offset < ext_size) {
+                       struct famfs_daxdev *dd;
                        u64 chunk_num       = local_offset / chunk_size;
                        u64 chunk_offset    = local_offset % chunk_size;
                        u64 stripe_num      = chunk_num / nstrips;
@@ -656,6 +743,7 @@ famfs_interleave_fileofs_to_daxofs(struct inode *inode, 
struct iomap *iomap,
                        u64 strip_offset    = chunk_offset + (stripe_num * 
chunk_size);
                        u64 strip_dax_ofs = 
fei->ie_strips[strip_num].ext_offset;
                        u64 strip_devidx = fei->ie_strips[strip_num].dev_index;
+                       int rc;
 
                        if (strip_devidx >= fc->dax_devlist->nslots) {
                                pr_err("%s: strip_devidx %llu >= nslots %d\n",
@@ -670,6 +758,15 @@ famfs_interleave_fileofs_to_daxofs(struct inode *inode, 
struct iomap *iomap,
                                goto err_out;
                        }
 
+                       dd = &fc->dax_devlist->devlist[strip_devidx];
+
+                       rc = famfs_dax_err(dd);
+                       if (rc) {
+                               /* Shut down access to this file */
+                               meta->error = true;
+                               return rc;
+                       }
+
                        iomap->addr    = strip_dax_ofs + strip_offset;
                        iomap->offset  = file_offset;
                        iomap->length  = min_t(loff_t, len, chunk_remainder);
@@ -767,6 +864,7 @@ famfs_fileofs_to_daxofs(struct inode *inode, struct iomap 
*iomap,
                if (local_offset < dax_ext_len) {
                        loff_t ext_len_remainder = dax_ext_len - local_offset;
                        struct famfs_daxdev *dd;
+                       int rc;
 
                        if (daxdev_idx >= fc->dax_devlist->nslots) {
                                pr_err("%s: daxdev_idx %llu >= nslots %d\n",
@@ -777,11 +875,11 @@ famfs_fileofs_to_daxofs(struct inode *inode, struct iomap 
*iomap,
 
                        dd = &fc->dax_devlist->devlist[daxdev_idx];
 
-                       if (!dd->valid || dd->error) {
-                               pr_err("%s: daxdev=%lld %s\n", __func__,
-                                      daxdev_idx,
-                                      dd->valid ? "error" : "invalid");
-                               goto err_out;
+                       rc = famfs_dax_err(dd);
+                       if (rc) {
+                               /* Shut down access to this file */
+                               meta->error = true;
+                               return rc;
                        }
 
                        /*
@@ -966,7 +1064,8 @@ famfs_file_bad(struct inode *inode)
                return -EIO;
        }
        if (meta->error) {
-               pr_debug("%s: previously detected metadata errors\n", __func__);
+               pr_debug("%s: previously detected metadata errors\n",
+                        __func__);
                return -EIO;
        }
        if (i_size != meta->file_size) {
diff --git a/fs/fuse/famfs_kfmap.h b/fs/fuse/famfs_kfmap.h
index e76b9057a1e0..6a6420bdff48 100644
--- a/fs/fuse/famfs_kfmap.h
+++ b/fs/fuse/famfs_kfmap.h
@@ -73,7 +73,8 @@ struct famfs_file_meta {
 struct famfs_daxdev {
        /* Include dev uuid? */
        bool valid;
-       bool error;
+       bool error; /* Dax has reported a memory error (probably poison) */
+       bool dax_err; /* fs_dax_get() failed */
        dev_t devno;
        struct dax_device *devp;
        char *name;
-- 
2.49.0


Reply via email to