* [SPDK] Re: sysfs-pci and SPDK IOAT
@ 2021-03-23 1:53 wiz.chen
0 siblings, 0 replies; 5+ messages in thread
From: wiz.chen @ 2021-03-23 1:53 UTC (permalink / raw)
To: spdk
[-- Attachment #1: Type: text/plain, Size: 434 bytes --]
Hi,
we change to use SPDK pci APIs to access NTB.
After spdk_pci_device_map_bar(), it can get the "mapped address" for accessing remote memory.
It's okay that using memcpy to copy "data" to "mapped address":
memcpy(mapped_addr, data_buf, size);
However, when using SPDK IOAT:
spdk_ioat_build_copy(ioat, cb_arg, cb_fn, mapped_addr, data_buf, size);
It will fail to translate mapped_addr by spdk_vtophys().
^ permalink raw reply [flat|nested] 5+ messages in thread
* [SPDK] Re: sysfs-pci and SPDK IOAT
@ 2021-03-26 8:22 Yufan Chen
0 siblings, 0 replies; 5+ messages in thread
From: Yufan Chen @ 2021-03-26 8:22 UTC (permalink / raw)
To: spdk
[-- Attachment #1: Type: text/plain, Size: 575 bytes --]
Hi,
Because changing ntb bar size, It needs to upgrade EEPROM.
Thus, I use the patch: https://staging.gerrithub.io/c/spdk/dpdk/+/441070
to check if spdk_mem_register can work or not.
However, if I create a nvmf target, it will cause segfault.
After investigation, create nvmf target will call mem_map_notify_walk() to register all
mapped memory.
It seems that the mapped memory of NTB PCI bar cannot be registered into RDMA
(Note: I use 'mlx5_dv' provider.)
Do you have any suggestion?
Thanks.
-yufan
^ permalink raw reply [flat|nested] 5+ messages in thread
* [SPDK] Re: sysfs-pci and SPDK IOAT
@ 2021-03-23 14:04 Harris, James R
0 siblings, 0 replies; 5+ messages in thread
From: Harris, James R @ 2021-03-23 14:04 UTC (permalink / raw)
To: spdk
[-- Attachment #1: Type: text/plain, Size: 886 bytes --]
Hi,
You'll need to do the alignment yourself for now. I cannot vouch for the correctness of the vfio patch.
-Jim
On 3/22/21, 8:25 PM, "wiz.chen(a)gmail.com" <wiz.chen(a)gmail.com> wrote:
hi,
I check spdk_mem_register(), it needs 2-MB aligned address.
After some investigation:
1. nvme cmb --> nvme_pcie_ctrlr_map_io_cmb():
it do 2MB alignment here.
2. vfio: map all PCI BARs in 2MB-aligned virtual addresses
https://staging.gerrithub.io/c/spdk/dpdk/+/441070
Does the patch: "vfio: map all PCI BARs in 2MB-aligned virtual addresses" have any side effect?
Or I do the 2MB alignment by myself is a batter choice?
_______________________________________________
SPDK mailing list -- spdk(a)lists.01.org
To unsubscribe send an email to spdk-leave(a)lists.01.org
^ permalink raw reply [flat|nested] 5+ messages in thread
* [SPDK] Re: sysfs-pci and SPDK IOAT
@ 2021-03-23 2:45 wiz.chen
0 siblings, 0 replies; 5+ messages in thread
From: wiz.chen @ 2021-03-23 2:45 UTC (permalink / raw)
To: spdk
[-- Attachment #1: Type: text/plain, Size: 479 bytes --]
hi,
I check spdk_mem_register(), it needs 2-MB aligned address.
After some investigation:
1. nvme cmb --> nvme_pcie_ctrlr_map_io_cmb():
it do 2MB alignment here.
2. vfio: map all PCI BARs in 2MB-aligned virtual addresses
https://staging.gerrithub.io/c/spdk/dpdk/+/441070
Does the patch: "vfio: map all PCI BARs in 2MB-aligned virtual addresses" have any side effect?
Or I do the 2MB alignment by myself is a batter choice?
^ permalink raw reply [flat|nested] 5+ messages in thread
* [SPDK] Re: sysfs-pci and SPDK IOAT
@ 2021-03-23 2:08 Harris, James R
0 siblings, 0 replies; 5+ messages in thread
From: Harris, James R @ 2021-03-23 2:08 UTC (permalink / raw)
To: spdk
[-- Attachment #1: Type: text/plain, Size: 818 bytes --]
Hi,
Can you try using spdk_mem_register() after you have called spdk_pci_device_map_bar()?
-Jim
On 3/22/21, 7:05 PM, "wiz.chen(a)gmail.com" <wiz.chen(a)gmail.com> wrote:
Hi,
we change to use SPDK pci APIs to access NTB.
After spdk_pci_device_map_bar(), it can get the "mapped address" for accessing remote memory.
It's okay that using memcpy to copy "data" to "mapped address":
memcpy(mapped_addr, data_buf, size);
However, when using SPDK IOAT:
spdk_ioat_build_copy(ioat, cb_arg, cb_fn, mapped_addr, data_buf, size);
It will fail to translate mapped_addr by spdk_vtophys().
_______________________________________________
SPDK mailing list -- spdk(a)lists.01.org
To unsubscribe send an email to spdk-leave(a)lists.01.org
^ permalink raw reply [flat|nested] 5+ messages in thread
end of thread, other threads:[~2021-03-26 8:22 UTC | newest]
Thread overview: 5+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2021-03-23 1:53 [SPDK] Re: sysfs-pci and SPDK IOAT wiz.chen
2021-03-23 2:08 Harris, James R
2021-03-23 2:45 wiz.chen
2021-03-23 14:04 Harris, James R
2021-03-26 8:22 Yufan Chen
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.