aboutsummaryrefslogtreecommitdiff
path: root/drivers/nvdimm/btt.c
diff options
context:
space:
mode:
authorVishal Verma <vishal.l.verma@intel.com>2019-02-27 17:06:27 -0700
committerDan Williams <dan.j.williams@intel.com>2019-02-28 09:57:39 -0800
commit9dedc73a4658ebcc0c9b58c3cb84e9ac80122213 (patch)
tree99e5a2f80c5820914f912b43713ff13e983dd1c9 /drivers/nvdimm/btt.c
parent2f8c9011151337d0bc106693f272f9bddbccfab2 (diff)
libnvdimm/btt: Fix LBA masking during 'free list' population
The Linux BTT implementation assumes that log entries will never have the 'zero' flag set, and indeed it never sets that flag for log entries itself. However, the UEFI spec is ambiguous on the exact format of the LBA field of a log entry, specifically as to whether it should include the additional flag bits or not. While a zero bit doesn't make sense in the context of a log entry, other BTT implementations might still have it set. If an implementation does happen to have it set, we would happily read it in as the next block to write to for writes. Since a high bit is set, it pushes the block number out of the range of an 'arena', and we fail such a write with an EIO. Follow the robustness principle, and tolerate such implementations by stripping out the zero flag when populating the free list during initialization. Additionally, use the same stripped out entries for detection of incomplete writes and map restoration that happens at this stage. Add a sysfs file 'log_zero_flags' that indicates the ability to accept such a layout to userspace applications. This enables 'ndctl check-namespace' to recognize whether the kernel is able to handle zero flags, or whether it should attempt a fix-up under the --repair option. Cc: Dan Williams <dan.j.williams@intel.com> Reported-by: Dexuan Cui <decui@microsoft.com> Reported-by: Pedro d'Aquino Filocre F S Barbuda <pbarbuda@microsoft.com> Tested-by: Dexuan Cui <decui@microsoft.com> Signed-off-by: Vishal Verma <vishal.l.verma@intel.com> Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Diffstat (limited to 'drivers/nvdimm/btt.c')
-rw-r--r--drivers/nvdimm/btt.c25
1 files changed, 19 insertions, 6 deletions
diff --git a/drivers/nvdimm/btt.c b/drivers/nvdimm/btt.c
index cd4fa87ea48c..4671776f5623 100644
--- a/drivers/nvdimm/btt.c
+++ b/drivers/nvdimm/btt.c
@@ -542,8 +542,8 @@ static int arena_clear_freelist_error(struct arena_info *arena, u32 lane)
static int btt_freelist_init(struct arena_info *arena)
{
int new, ret;
- u32 i, map_entry;
struct log_entry log_new;
+ u32 i, map_entry, log_oldmap, log_newmap;
arena->freelist = kcalloc(arena->nfree, sizeof(struct free_entry),
GFP_KERNEL);
@@ -555,16 +555,22 @@ static int btt_freelist_init(struct arena_info *arena)
if (new < 0)
return new;
+ /* old and new map entries with any flags stripped out */
+ log_oldmap = ent_lba(le32_to_cpu(log_new.old_map));
+ log_newmap = ent_lba(le32_to_cpu(log_new.new_map));
+
/* sub points to the next one to be overwritten */
arena->freelist[i].sub = 1 - new;
arena->freelist[i].seq = nd_inc_seq(le32_to_cpu(log_new.seq));
- arena->freelist[i].block = le32_to_cpu(log_new.old_map);
+ arena->freelist[i].block = log_oldmap;
/*
* FIXME: if error clearing fails during init, we want to make
* the BTT read-only
*/
- if (ent_e_flag(log_new.old_map)) {
+ if (ent_e_flag(log_new.old_map) &&
+ !ent_normal(log_new.old_map)) {
+ arena->freelist[i].has_err = 1;
ret = arena_clear_freelist_error(arena, i);
if (ret)
dev_err_ratelimited(to_dev(arena),
@@ -572,7 +578,7 @@ static int btt_freelist_init(struct arena_info *arena)
}
/* This implies a newly created or untouched flog entry */
- if (log_new.old_map == log_new.new_map)
+ if (log_oldmap == log_newmap)
continue;
/* Check if map recovery is needed */
@@ -580,8 +586,15 @@ static int btt_freelist_init(struct arena_info *arena)
NULL, NULL, 0);
if (ret)
return ret;
- if ((le32_to_cpu(log_new.new_map) != map_entry) &&
- (le32_to_cpu(log_new.old_map) == map_entry)) {
+
+ /*
+ * The map_entry from btt_read_map is stripped of any flag bits,
+ * so use the stripped out versions from the log as well for
+ * testing whether recovery is needed. For restoration, use the
+ * 'raw' version of the log entries as that captured what we
+ * were going to write originally.
+ */
+ if ((log_newmap != map_entry) && (log_oldmap == map_entry)) {
/*
* Last transaction wrote the flog, but wasn't able
* to complete the map write. So fix up the map.