it's apparent
that with the proposed patch driver could choose the optimal
IO path when iopolicy is set to NUMA and we get the better
IO performance. With the proposed patch we get ~12% of perf-
ormance improvment.
Nilay Shroff (1):
powerpc/numa: Online a node if PHB is attached.
arch/po
is attached to a PCI host bridge which has numa-node id
value set to NUMA_NO_NODE. This patch helps fix this ensuring
that a cpu/memory less numa node is made online if it's
attached to PCI host bridge.
Signed-off-by: Nilay Shroff
---
arch/powerpc/mm/numa.c
.kernel.org/oe-kbuild-all/202405171615.nbra8poe-...@intel.com/
Nilay Shroff (1):
powerpc/numa: Online a node if PHB is attached.
arch/powerpc/mm/numa.c | 14 +-
arch/powerpc/platforms/pseries/pci_dlpar.c | 14 ++
2 files changed, 27 insertions(+), 1 deletion(-)
--
2.44.0
is attached to a PCI host bridge which has numa-node id
value set to NUMA_NO_NODE. This patch helps fix this ensuring
that a cpu/memory less numa node is made online if it's
attached to PCI host bridge.
Signed-off-by: Nilay Shroff
---
arch/powerpc/mm/numa.c
"int" while the address is "unsigned long". This results in
>negative value when setting the bitmap.
>
> 2. The DMA offset is page shifted but the MMIO range is used as-is (64-bit
> address). MMIO address needs to be page shifted as well.
>
> Fixes: 3c33066a2190 ("powerpc/kernel/iommu: Add new iommu_table_in_use()
> helper")
>
> Signed-off-by: Gaurav Batra
Looks good to me:
Reviewed-by: Nilay Shroff
previous one.
Otherwise, changes look good to me:
Reviewed-by: Nilay Shroff
