On 12/18/20 3:31 PM, Kajol Jain wrote:
hv_24x7 performance monitoring unit creates list of supported events
from the event catalog obtained via HCALL. hv_24x7 catalog could also
contain invalid or dummy events (with names like FREE_* or CPM_FREE_*
and RESERVED*). These events do not have any ha
This allows the function to be entirely noped if hash support is
compiled out (not possible yet).
Signed-off-by: Nicholas Piggin
---
arch/powerpc/include/asm/book3s/pgtable.h | 11 ++-
arch/powerpc/mm/book3s32/mmu.c| 4 ++--
arch/powerpc/mm/book3s64/hash_utils.c | 7 ++-
This is not entirely settled because of future compatibility concern
but in terms of Linux code and existing processors I think the approach
works.
Thanks,
Nick
Nicholas Piggin (5):
powerpc/64s: update_mmu_cache inline the radix test
powerpc/64s: implement mm_nmmu_has_tlbs
powerpc/64s: add
Rather than read the copros field directly. This allows coprocessors
to be compiled out.
Signed-off-by: Nicholas Piggin
---
arch/powerpc/include/asm/book3s/64/tlbflush.h | 9 ++-
arch/powerpc/mm/book3s64/radix_hugetlbpage.c | 3 +--
arch/powerpc/mm/book3s64/radix_pgtable.c | 5 ++--
This allows some nest MMU features to be compiled away if coprocessor
support is not selected.
Signed-off-by: Nicholas Piggin
---
arch/powerpc/Kconfig | 1 +
arch/powerpc/include/asm/book3s/64/mmu.h | 2 ++
arch/powerpc/include/asm/book3s/64/tlbflush.h | 2 ++
arch/
Currently the radix variant is only called when full=true. Allow
radix to take over the entire function.
Signed-off-by: Nicholas Piggin
---
arch/powerpc/include/asm/book3s/64/pgtable.h | 10 +++---
arch/powerpc/include/asm/book3s/64/radix.h | 4
2 files changed, 7 insertions(+), 7 de
PTE updates performed by Linux are serialized by the page table locks.
There is no need to use atomic operations for these modifications if the
hardware does not perform updates asynchronously (e.g., via the MMU RC
update mechanism).
Current POWER CPUs that support radix do not perform such update
