[PATCH v3 0/2] Fix BTT data corruptions after crash

From: Toshi Kani
Date: Thu Feb 11 2016 - 15:31:18 EST


Data corruption issues were observed in tests which initiated a system
crash/reset while accessing BTT devices. This problem is reproducible.

The BTT driver calls pmem_rw_bytes() to update data in pmem devices.
This interface calls __copy_user_nocache(), which uses non-temporal
stores so that the stores to pmem are persistent.

__copy_user_nocache() uses non-temporal stores when a request size is
8 bytes or larger (and is aligned by 8 bytes). The BTT driver updates
the BTT map table, which entry size is 4 bytes. Therefore, updates to
the map table entries remain cached, and are not written to pmem after
a crash. Since the BTT driver makes previous blocks free and uses them
for subsequent writes, the map table ends up pointing to blocks allocated
for other LBAs after a crash.

Patch 1 cleans up __copy_user_nocache() before making changes.
Patch 2 makes __copy_user_nocache() handle 4-byte nocache copy.

---
v3:
- Add a cleanup patch to rename numeric labels to descriptively named
labels with .L. (Ingo Molnar, Borislav Petkov)
v2:
- Add comments (Ingo Molnar).
---
Toshi Kani (2):
1/2 x86/lib/copy_user_64.S: cleanup __copy_user_nocache()
2/2 x86/lib/copy_user_64.S: Handle 4-byte nocache copy

---
arch/x86/lib/copy_user_64.S | 142 +++++++++++++++++++++++++++++++-------------
1 file changed, 101 insertions(+), 41 deletions(-)