npu2: Advertise correct TCE page size
diff mbox series

Message ID 20181206082910.114560-1-aik@ozlabs.ru
State Accepted
Headers show
Series
  • npu2: Advertise correct TCE page size
Related show

Checks

Context Check Description
snowpatch_ozlabs/snowpatch_job_snowpatch-skiboot success Test snowpatch/job/snowpatch-skiboot on branch master
snowpatch_ozlabs/apply_patch success master/apply_patch Successfully applied

Commit Message

Alexey Kardashevskiy Dec. 6, 2018, 8:29 a.m. UTC
The P9 NPU workbook says that only 4K/64K/16M/256M page size are supported
and in fact npu2_map_pe_dma_window() supports just these but in absence of
the "ibm,supported-tce-sizes" property Linux assumes the default P9 PHB4
page sizes - 4K/64K/2M/1G - so when Linux tries 2M/1G TCEs, we get lots of
"Unexpected TCE size" from npu2_tce_kill().

This advertises TCE page sizes so Linux could handle it correctly, i.e.
fall back to 4K/64K TCEs.

Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
---
 hw/npu2.c | 5 +++++
 1 file changed, 5 insertions(+)

Comments

Stewart Smith Dec. 11, 2018, 6:30 a.m. UTC | #1
Alexey Kardashevskiy <aik@ozlabs.ru> writes:
> The P9 NPU workbook says that only 4K/64K/16M/256M page size are supported
> and in fact npu2_map_pe_dma_window() supports just these but in absence of
> the "ibm,supported-tce-sizes" property Linux assumes the default P9 PHB4
> page sizes - 4K/64K/2M/1G - so when Linux tries 2M/1G TCEs, we get lots of
> "Unexpected TCE size" from npu2_tce_kill().
>
> This advertises TCE page sizes so Linux could handle it correctly, i.e.
> fall back to 4K/64K TCEs.

Merged to master as of 003ccd5775161d352c53cac3d00c6283eb036ffc - should
this also go to stable?
Alexey Kardashevskiy Dec. 12, 2018, 12:02 a.m. UTC | #2
On 11/12/2018 17:30, Stewart Smith wrote:
> Alexey Kardashevskiy <aik@ozlabs.ru> writes:
>> The P9 NPU workbook says that only 4K/64K/16M/256M page size are supported
>> and in fact npu2_map_pe_dma_window() supports just these but in absence of
>> the "ibm,supported-tce-sizes" property Linux assumes the default P9 PHB4
>> page sizes - 4K/64K/2M/1G - so when Linux tries 2M/1G TCEs, we get lots of
>> "Unexpected TCE size" from npu2_tce_kill().
>>
>> This advertises TCE page sizes so Linux could handle it correctly, i.e.
>> fall back to 4K/64K TCEs.
> 
> Merged to master as of 003ccd5775161d352c53cac3d00c6283eb036ffc - should
> this also go to stable?

The userspace can trigger those "Unexpected TCE size" messages a lot, is
this a good enough reason for stable?
Stewart Smith Dec. 12, 2018, 1:18 a.m. UTC | #3
Alexey Kardashevskiy <aik@ozlabs.ru> writes:
> On 11/12/2018 17:30, Stewart Smith wrote:
>> Alexey Kardashevskiy <aik@ozlabs.ru> writes:
>>> The P9 NPU workbook says that only 4K/64K/16M/256M page size are supported
>>> and in fact npu2_map_pe_dma_window() supports just these but in absence of
>>> the "ibm,supported-tce-sizes" property Linux assumes the default P9 PHB4
>>> page sizes - 4K/64K/2M/1G - so when Linux tries 2M/1G TCEs, we get lots of
>>> "Unexpected TCE size" from npu2_tce_kill().
>>>
>>> This advertises TCE page sizes so Linux could handle it correctly, i.e.
>>> fall back to 4K/64K TCEs.
>> 
>> Merged to master as of 003ccd5775161d352c53cac3d00c6283eb036ffc - should
>> this also go to stable?
>
> The userspace can trigger those "Unexpected TCE size" messages a lot, is
> this a good enough reason for stable?

Probably - annoying messages are a bug.

Patch
diff mbox series

diff --git a/hw/npu2.c b/hw/npu2.c
index 767306f..57f5c4b 100644
--- a/hw/npu2.c
+++ b/hw/npu2.c
@@ -1934,6 +1934,11 @@  static void npu2_add_phb_properties(struct npu2 *p)
 			      NPU2_MAX_PE_NUM);
 	dt_add_property_cells(np, "ibm,opal-reserved-pe",
 			      NPU2_RESERVED_PE_NUM);
+	dt_add_property_cells(np, "ibm,supported-tce-sizes",
+			      12, // 4K
+			      16, // 64K
+			      24, // 16M
+			      28); // 256M
 
 	dt_add_property_u64s(np, "ibm,mmio-atsd",
 			MMIO_ATSD_ADDR(p->regs, 0),