Hi Hanjun,


On Fri, Jul 21, 2017 at 4:50 PM, Marc Zyngier [off-list ref] wrote:

On 21/07/17 11:06, Hanjun Guo wrote:

quoted

On 2017/7/21 17:51, Hanjun Guo wrote:

quoted

From: Hanjun Guo <redacted>

When running 4.13-rc1 on top of D05, I got the boot log:

[    0.000000] SRAT: PXM 0 -> ITS 0 -> Node 0
[    0.000000] SRAT: PXM 0 -> ITS 1 -> Node 0
[    0.000000] SRAT: PXM 0 -> ITS 2 -> Node 0
[    0.000000] SRAT: PXM 1 -> ITS 3 -> Node 1
[    0.000000] SRAT: ITS affinity exceeding max count[4]

This is wrong on D05 as we have 8 ITSes with 4 NUMA nodes.

Used static array to keep it simple.  we can have either dynamic array
or increase static array size (which is in init data) to a larger
number.
We may have to go for dynamic array to be more sane. You can refer my
v2 patch [1], which was doing dynamic allocation and avoids
2 calls to acpi parser as done in this patch.

[1] https://patchwork.kernel.org/patch/9798659/

I'm not seeing this on the D05 I have access to. Actually, I'm not
seeing any data related to SRAT and the ITS. Is that a different firmware?

quoted

quoted

So dynamically alloc the memory needed instead of using
its_srat_maps[MAX_NUMNODES], which count the number of
ITS entry(ies) in SRAT and alloc its_srat_maps as needed,
then build the mapping of numa node to ITS ID.

After doing this, I got what I wanted:

[    0.000000] SRAT: PXM 0 -> ITS 0 -> Node 0
[    0.000000] SRAT: PXM 0 -> ITS 1 -> Node 0
[    0.000000] SRAT: PXM 0 -> ITS 2 -> Node 0
[    0.000000] SRAT: PXM 1 -> ITS 3 -> Node 1
[    0.000000] SRAT: PXM 2 -> ITS 4 -> Node 2
[    0.000000] SRAT: PXM 2 -> ITS 5 -> Node 2
[    0.000000] SRAT: PXM 2 -> ITS 6 -> Node 2
[    0.000000] SRAT: PXM 3 -> ITS 7 -> Node 3

Fixes: dbd2b8267233 ("irqchip/gic-v3-its: Add ACPI NUMA node mapping")
Signed-off-by: Hanjun Guo <redacted>
Cc: Ganapatrao Kulkarni <redacted>
Cc: Lorenzo Pieralisi <redacted>
Cc: Marc Zyngier <redacted>
---
 drivers/irqchip/irq-gic-v3-its.c | 28 +++++++++++++++++++++-------
 1 file changed, 21 insertions(+), 7 deletions(-)

diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c
index 3ccdf76..fb1c090 100644
--- a/drivers/irqchip/irq-gic-v3-its.c
+++ b/drivers/irqchip/irq-gic-v3-its.c

@@ -1847,7 +1847,7 @@ struct its_srat_map {
     u32     its_id;
 };

-static struct its_srat_map its_srat_maps[MAX_NUMNODES] __initdata;
+static struct its_srat_map *its_srat_maps __initdata;
 static int its_in_srat __initdata;

 static int __init acpi_get_its_numa_node(u32 its_id)

@@ -1861,6 +1861,12 @@ static int __init acpi_get_its_numa_node(u32 its_id)
     return NUMA_NO_NODE;
 }

Oops, need to check if the its_srat_maps valid or not here, please
comment on what else I'm missing or wrong, then I will prepare another
version.

Please post a patch that has all of the fixes, and I'll review that.

Thanks,

        M.
--
Jazz is not dead. It just smells funny...

_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel at lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel

thanks
Ganapat