ubi: Be more paranoid while seaching for the most recent Fastmap

commit 74f2c6e9a47cf4e508198c8594626cc82906a13d upstream.

Since PEB erasure is asynchornous it can happen that there is
more than one Fastmap on the MTD. This is fine because the attach logic
will pick the Fastmap data structure with the highest sequence number.

On a not so well configured MTD stack spurious ECC errors are common.
Causes can be different, bad hardware, wrong operating modes, etc...
If the most current Fastmap renders bad due to ECC errors UBI might
pick an older Fastmap to attach from.
While this can only happen on an anyway broken setup it will show
completely different sympthoms and makes finding the root cause much
more difficult.
So, be debug friendly and fall back to scanning mode of we're facing
an ECC error while scanning for Fastmap.

Cc: <stable@vger.kernel.org>
Signed-off-by: Richard Weinberger <richard@nod.at>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

diff --git a/drivers/mtd/ubi/attach.c b/drivers/mtd/ubi/attach.c
index 68ff57435c89e4489d704da568256716fc5d83b5..5cde3ad1665e3f120e95dd9c867a0f99b62a5c5a 100644 (file)
--- a/drivers/mtd/ubi/attach.c
+++ b/drivers/mtd/ubi/attach.c
@@ -856,13 +856,15 @@ static bool vol_ignored(int vol_id)
  * @ubi: UBI device description object
  * @ai: attaching information
  * @pnum: the physical eraseblock number
+ * @fast: true if we're scanning for a Fastmap
  *
  * This function reads UBI headers of PEB @pnum, checks them, and adds
  * information about this PEB to the corresponding list or RB-tree in the
  * "attaching info" structure. Returns zero if the physical eraseblock was
  * successfully handled and a negative error code in case of failure.
  */
-static int scan_peb(struct ubi_device *ubi, struct ubi_attach_info *ai, int pnum)
+static int scan_peb(struct ubi_device *ubi, struct ubi_attach_info *ai,
+                   int pnum, bool fast)
 {
        long long ec;
        int err, bitflips = 0, vol_id = -1, ec_err = 0;
@@ -980,6 +982,20 @@ static int scan_peb(struct ubi_device *ubi, struct ubi_attach_info *ai, int pnum
                         */
                        ai->maybe_bad_peb_count += 1;
        case UBI_IO_BAD_HDR:
+                       /*
+                        * If we're facing a bad VID header we have to drop *all*
+                        * Fastmap data structures we find. The most recent Fastmap
+                        * could be bad and therefore there is a chance that we attach
+                        * from an old one. On a fine MTD stack a PEB must not render
+                        * bad all of a sudden, but the reality is different.
+                        * So, let's be paranoid and help finding the root cause by
+                        * falling back to scanning mode instead of attaching with a
+                        * bad EBA table and cause data corruption which is hard to
+                        * analyze.
+                        */
+                       if (fast)
+                               ai->force_full_scan = 1;
+
                if (ec_err)
                        /*
                         * Both headers are corrupted. There is a possibility
@@ -1293,7 +1309,7 @@ static int scan_all(struct ubi_device *ubi, struct ubi_attach_info *ai,
                cond_resched();
 
                dbg_gen("process PEB %d", pnum);
-               err = scan_peb(ubi, ai, pnum);
+               err = scan_peb(ubi, ai, pnum, false);
                if (err < 0)
                        goto out_vidh;
        }
@@ -1407,7 +1423,7 @@ static int scan_fast(struct ubi_device *ubi, struct ubi_attach_info **ai)
                cond_resched();
 
                dbg_gen("process PEB %d", pnum);
-               err = scan_peb(ubi, scan_ai, pnum);
+               err = scan_peb(ubi, scan_ai, pnum, true);
                if (err < 0)
                        goto out_vidh;
        }
@@ -1415,7 +1431,11 @@ static int scan_fast(struct ubi_device *ubi, struct ubi_attach_info **ai)
        ubi_free_vid_hdr(ubi, vidh);
        kfree(ech);
 
-       err = ubi_scan_fastmap(ubi, *ai, scan_ai);
+       if (scan_ai->force_full_scan)
+               err = UBI_NO_FASTMAP;
+       else
+               err = ubi_scan_fastmap(ubi, *ai, scan_ai);
+
        if (err) {
                /*
                 * Didn't attach via fastmap, do a full scan but reuse what

diff --git a/drivers/mtd/ubi/ubi.h b/drivers/mtd/ubi/ubi.h
index 051976caf8f0ca671bdc7eb210bc15f294848930..05d9ec66437c33fe40b9a8de3518ad46dfc21b17 100644 (file)
--- a/drivers/mtd/ubi/ubi.h
+++ b/drivers/mtd/ubi/ubi.h
@@ -711,6 +711,8 @@ struct ubi_ainf_volume {
  * @vols_found: number of volumes found
  * @highest_vol_id: highest volume ID
  * @is_empty: flag indicating whether the MTD device is empty or not
+ * @force_full_scan: flag indicating whether we need to do a full scan and drop
+                    all existing Fastmap data structures
  * @min_ec: lowest erase counter value
  * @max_ec: highest erase counter value
  * @max_sqnum: highest sequence number value
@@ -738,6 +740,7 @@ struct ubi_attach_info {
        int vols_found;
        int highest_vol_id;
        int is_empty;
+       int force_full_scan;
        int min_ec;
        int max_ec;
        unsigned long long max_sqnum;