forked from luck/tmp_suning_uos_patched
fb5924fddf
This patch adds support for flushing potentially dirty cache lines
when memory is hot-plugged/hot-un-plugged. The support is currently
limited to 64 bit systems.
The bug was exposed when mappings for a device were actually
hot-unplugged and plugged in back later. A similar issue was observed
during the development of memtrace, but memtrace does it's own
flushing of region via a custom routine.
These patches do a flush both on hotplug/unplug to clear any stale
data in the cache w.r.t mappings, there is a small race window where a
clean cache line may be created again just prior to tearing down the
mapping.
The patches were tested by disabling the flush routines in memtrace
and doing I/O on the trace file. The system immediately
checkstops (quite reliablly if prior to the hot-unplug of the memtrace
region, we memset the regions we are about to hot unplug). After these
patches no custom flushing is needed in the memtrace code.
Fixes:
|
||
---|---|---|
.. | ||
8xx_mmu.c | ||
40x_mmu.c | ||
44x_mmu.c | ||
copro_fault.c | ||
dma-noncoherent.c | ||
drmem.c | ||
dump_hashpagetable.c | ||
dump_linuxpagetables.c | ||
fault.c | ||
fsl_booke_mmu.c | ||
hash_low_32.S | ||
hash_native_64.c | ||
hash_utils_64.c | ||
hash64_4k.c | ||
hash64_64k.c | ||
highmem.c | ||
hugepage-hash64.c | ||
hugetlbpage-book3e.c | ||
hugetlbpage-hash64.c | ||
hugetlbpage-radix.c | ||
hugetlbpage.c | ||
init_32.c | ||
init_64.c | ||
init-common.c | ||
Makefile | ||
mem.c | ||
mmap.c | ||
mmu_context_book3s64.c | ||
mmu_context_hash32.c | ||
mmu_context_iommu.c | ||
mmu_context_nohash.c | ||
mmu_context.c | ||
mmu_decl.h | ||
numa.c | ||
pgtable_32.c | ||
pgtable_64.c | ||
pgtable-book3e.c | ||
pgtable-book3s64.c | ||
pgtable-hash64.c | ||
pgtable-radix.c | ||
pgtable.c | ||
pkeys.c | ||
ppc_mmu_32.c | ||
slb_low.S | ||
slb.c | ||
slice.c | ||
subpage-prot.c | ||
tlb_hash32.c | ||
tlb_hash64.c | ||
tlb_low_64e.S | ||
tlb_nohash_low.S | ||
tlb_nohash.c | ||
tlb-radix.c | ||
vphn.c | ||
vphn.h |