bianbu-repo-mirror/bianbu-linux-6.6
1
0
Fork 0
mirror of https://gitee.com/bianbu-linux/linux-6.6 synced 2025-04-24 14:07:52 -04:00
Code Issues Projects Releases Packages Wiki Activity Actions

PCI: hv: Fix a timing issue which causes kdump to fail occasionally

Browse source 
Kdump could fail sometime on Hyper-V guest because the retry in
hv_pci_enter_d0() releases child device structures in hv_pci_bus_exit().

Although there is a second asynchronous device relations message sending
from the host, if this message arrives to the guest after
hv_send_resource_allocated() is called, the retry would fail.

Fix the problem by moving retry to hv_pci_probe() and start the retry
from hv_pci_query_relations() call.  This will cause a device relations
message to arrive to the guest synchronously; the guest would then be
able to rebuild the child device structures before calling
hv_send_resource_allocated().

Link: https://lore.kernel.org/r/20200727071731.18516-1-weh@microsoft.com
Fixes: c81992e7f4 ("PCI: hv: Retry PCI bus D0 entry on invalid device state")
Signed-off-by: Wei Hu <weh@microsoft.com>
[lorenzo.pieralisi@arm.com: fixed a comment and commit log]
Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Reviewed-by: Michael Kelley <mikelley@microsoft.com>
This commit is contained in:
Wei Hu 2020-07-27 15:17:31 +08:00 • committed by Lorenzo Pieralisi
parent b3a9e3b962
commit d6af2ed29c
1 changed files with 37 additions and 34 deletions
Download patch file Download diff file Expand all files Collapse all files

71
drivers/pci/controller/pci-hyperv.c
View file

@ -2759,10 +2759,8 @@ static int hv_pci_enter_d0(struct hv_device *hdev)
struct pci_bus_d0_entry *d0_entry; struct pci_bus_d0_entry *d0_entry;
struct hv_pci_compl comp_pkt; struct hv_pci_compl comp_pkt;
struct pci_packet *pkt; struct pci_packet *pkt;
bool retry = true;
int ret; int ret;
enter_d0_retry:
/* /*
* Tell the host that the bus is ready to use, and moved into the * Tell the host that the bus is ready to use, and moved into the
* powered-on state. This includes telling the host which region * powered-on state. This includes telling the host which region
@ -2789,38 +2787,6 @@ enter_d0_retry:
if (ret) if (ret)
goto exit; goto exit;
/*
* In certain case (Kdump) the pci device of interest was
* not cleanly shut down and resource is still held on host
* side, the host could return invalid device status.
* We need to explicitly request host to release the resource
* and try to enter D0 again.
*/
if (comp_pkt.completion_status < 0 && retry) {
retry = false;
dev_err(&hdev->device, "Retrying D0 Entry\n");
/*
* Hv_pci_bus_exit() calls hv_send_resource_released()
* to free up resources of its child devices.
* In the kdump kernel we need to set the
* wslot_res_allocated to 255 so it scans all child
* devices to release resources allocated in the
* normal kernel before panic happened.
*/
hbus->wslot_res_allocated = 255;
ret = hv_pci_bus_exit(hdev, true);
if (ret == 0) {
kfree(pkt);
goto enter_d0_retry;
}
dev_err(&hdev->device,
"Retrying D0 failed with ret %d\n", ret);
}
if (comp_pkt.completion_status < 0) { if (comp_pkt.completion_status < 0) {
dev_err(&hdev->device, dev_err(&hdev->device,
"PCI Pass-through VSP failed D0 Entry with status %x\n", "PCI Pass-through VSP failed D0 Entry with status %x\n",
@ -3058,6 +3024,7 @@ static int hv_pci_probe(struct hv_device *hdev,
struct hv_pcibus_device *hbus; struct hv_pcibus_device *hbus;
u16 dom_req, dom; u16 dom_req, dom;
char *name; char *name;
bool enter_d0_retry = true;
int ret; int ret;
/* /*
@ -3178,11 +3145,47 @@ static int hv_pci_probe(struct hv_device *hdev,
if (ret) if (ret)
goto free_fwnode; goto free_fwnode;
retry:
ret = hv_pci_query_relations(hdev); ret = hv_pci_query_relations(hdev);
if (ret) if (ret)
goto free_irq_domain; goto free_irq_domain;
ret = hv_pci_enter_d0(hdev); ret = hv_pci_enter_d0(hdev);
/*
* In certain case (Kdump) the pci device of interest was
* not cleanly shut down and resource is still held on host
* side, the host could return invalid device status.
* We need to explicitly request host to release the resource
* and try to enter D0 again.
* Since the hv_pci_bus_exit() call releases structures
* of all its child devices, we need to start the retry from
* hv_pci_query_relations() call, requesting host to send
* the synchronous child device relations message before this
* information is needed in hv_send_resources_allocated()
* call later.
*/
if (ret == -EPROTO && enter_d0_retry) {
enter_d0_retry = false;
dev_err(&hdev->device, "Retrying D0 Entry\n");
/*
* Hv_pci_bus_exit() calls hv_send_resources_released()
* to free up resources of its child devices.
* In the kdump kernel we need to set the
* wslot_res_allocated to 255 so it scans all child
* devices to release resources allocated in the
* normal kernel before panic happened.
*/
hbus->wslot_res_allocated = 255;
ret = hv_pci_bus_exit(hdev, true);
if (ret == 0)
goto retry;
dev_err(&hdev->device,
"Retrying D0 failed with ret %d\n", ret);
}
if (ret) if (ret)
goto free_irq_domain; goto free_irq_domain;