From: Wei Hu <weh@microsoft.com>
Date: Thu, 7 May 2020 13:03:00 +0800
Patch-mainline: v5.8-rc1
Subject: PCI: hv: Retry PCI bus D0 entry on invalid device state
Git-commit: c81992e7f4aa19a055dbff5bd6c6d5ff9408f2fb
References: bsc#1172871, bsc#1172872

When kdump is triggered, some PCI devices may have not been shut down
cleanly before the kdump kernel starts.

This causes the initial attempt to enter D0 state in the kdump kernel to
fail with invalid device state returned from Hyper-V host.

When this happens, explicitly call hv_pci_bus_exit() and retry to enter
the D0 state.

Link: https://lore.kernel.org/r/20200507050300.10974-1-weh@microsoft.com
Signed-off-by: Wei Hu <weh@microsoft.com>
[lorenzo.pieralisi@arm.com: commit log]
Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Reviewed-by: Michael Kelley <mikelley@microsoft.com>
Acked-by: Olaf Hering <ohering@suse.de>
---
 drivers/pci/host/pci-hyperv.c | 40 +++++++++++++++++++++++++++++++++++--
 1 file changed, 38 insertions(+), 2 deletions(-)

diff --git a/drivers/pci/host/pci-hyperv.c b/drivers/pci/host/pci-hyperv.c
--- a/drivers/pci/host/pci-hyperv.c
+++ b/drivers/pci/host/pci-hyperv.c
@@ -2739,6 +2739,8 @@ static void hv_free_config_window(struct hv_pcibus_device *hbus)
 	vmbus_free_mmio(hbus->mem_config->start, PCI_CONFIG_MMIO_LENGTH);
 }
 
+static int hv_pci_bus_exit(struct hv_device *hdev, bool keep_devs);
+
 /**
  * hv_pci_enter_d0() - Bring the "bus" into the D0 power state
  * @hdev:	VMBus's tracking struct for this root PCI bus
@@ -2751,8 +2753,10 @@ static int hv_pci_enter_d0(struct hv_device *hdev)
 	struct pci_bus_d0_entry *d0_entry;
 	struct hv_pci_compl comp_pkt;
 	struct pci_packet *pkt;
+	bool retry = true;
 	int ret;
 
+enter_d0_retry:
 	/*
 	 * Tell the host that the bus is ready to use, and moved into the
 	 * powered-on state.  This includes telling the host which region
@@ -2779,6 +2783,38 @@ static int hv_pci_enter_d0(struct hv_device *hdev)
 	if (ret)
 		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) {
 		dev_err(&hdev->device,
 			"PCI Pass-through VSP failed D0 Entry with status %x\n",
@@ -3185,7 +3221,7 @@ free_bus:
 	return ret;
 }
 
-static int hv_pci_bus_exit(struct hv_device *hdev, bool hibernating)
+static int hv_pci_bus_exit(struct hv_device *hdev, bool keep_devs)
 {
 	struct hv_pcibus_device *hbus = hv_get_drvdata(hdev);
 	struct {
@@ -3203,7 +3239,7 @@ static int hv_pci_bus_exit(struct hv_device *hdev, bool hibernating)
 	if (hdev->channel->rescind)
 		return 0;
 
-	if (!hibernating) {
+	if (!keep_devs) {
 		/* Delete any children which might still exist. */
 		dr = kzalloc(sizeof(*dr), GFP_KERNEL);
 		if (dr && hv_pci_start_relations_work(hbus, dr))