Hi, Tiezhu,
How do you test kexec? kexec -e or systemctl kexec? Or both?
Huacai
陈华才江苏航天龙梦信息技术有限公司/研发中心/软件部 ------------------ Original ------------------From: "Tiezhu Yang"<yangtiezhu@xxxxxxxxxxx>;Date: Mon, Sep 14, 2020 03:57 PMTo: "Bjorn Helgaas"<bhelgaas@xxxxxxxxxx>; Cc: "linux-pci"<linux-pci@xxxxxxxxxxxxxxx>; "linux-kernel"<linux-kernel@xxxxxxxxxxxxxxx>; "Rafael J. Wysocki"<rafael.j.wysocki@xxxxxxxxx>; "Konstantin Khlebnikov"<khlebnikov@xxxxxxxxxx>; "Khalid Aziz"<khalid.aziz@xxxxxxxxxx>; "Vivek Goyal"<vgoyal@xxxxxxxxxx>; "Lukas Wunner"<lukas@xxxxxxxxx>; "Oliver O'Halloran"<oohall@xxxxxxxxx>; "Huacai Chen"<chenhc@xxxxxxxxxx>; "Jiaxun Yang"<jiaxun.yang@xxxxxxxxxxx>; "Xuefeng Li"<lixuefeng@xxxxxxxxxxx>; Subject: [RFC PATCH v3] PCI/portdrv: Only disable Bus Master on kexec reboot and connected PCI devices After commit 745be2e700cd ("PCIe: portdrv: call pci_disable_device
during remove") and commit cc27b735ad3a ("PCI/portdrv: Turn off PCIe
services during shutdown"), it also calls pci_disable_device() during
shutdown, this leads to shutdown or reboot failure occasionally due to
clear PCI_COMMAND_MASTER on the device in do_pci_disable_device().
drivers/pci/pci.c
static void do_pci_disable_device(struct pci_dev *dev)
{
u16 pci_command;
pci_read_config_word(dev, PCI_COMMAND, &pci_command);
if (pci_command & PCI_COMMAND_MASTER) {
pci_command &= ~PCI_COMMAND_MASTER;
pci_write_config_word(dev, PCI_COMMAND, pci_command);
}
pcibios_disable_device(dev);
}
When remove "pci_command &= ~PCI_COMMAND_MASTER;", it can work well when
shutdown or reboot.
As Oliver O'Halloran said, no need to call pci_disable_device() when
actually shutting down, but we should call pci_disable_device() before
handing over to the new kernel on kexec reboot, so we can do some
condition checks which are already executed afterwards by the function
pci_device_shutdown(), this is done by commit 4fc9bbf98fd6 ("PCI: Disable
Bus Master only on kexec reboot") and commit 6e0eda3c3898 ("PCI: Don't try
to disable Bus Master on disconnected PCI devices").
drivers/pci/pci-driver.c
static void pci_device_shutdown(struct device *dev)
{
...
if (drv && drv->shutdown)
drv->shutdown(pci_dev);
/*
* If this is a kexec reboot, turn off Bus Master bit on the
* device to tell it to not continue to do DMA. Don't touch
* devices in D3cold or unknown states.
* If it is not a kexec reboot, firmware will hit the PCI
* devices with big hammer and stop their DMA any way.
*/
if (kexec_in_progress && (pci_dev->current_state <= PCI_D3hot))
pci_clear_master(pci_dev);
}
[ 36.159446] Call Trace:
[ 36.241688] [<ffffffff80211434>] show_stack+0x9c/0x130
[ 36.326619] [<ffffffff80661b70>] dump_stack+0xb0/0xf0
[ 36.410403] [<ffffffff806a8240>] pcie_portdrv_shutdown+0x18/0x78
[ 36.495302] [<ffffffff8069c6b4>] pci_device_shutdown+0x44/0x90
[ 36.580027] [<ffffffff807aac90>] device_shutdown+0x130/0x290
[ 36.664486] [<ffffffff80265448>] kernel_power_off+0x38/0x80
[ 36.748272] [<ffffffff80265634>] __do_sys_reboot+0x1a4/0x258
[ 36.831985] [<ffffffff80218b90>] syscall_common+0x34/0x58
Signed-off-by: Tiezhu Yang <yangtiezhu@xxxxxxxxxxx>
---
drivers/pci/pcie/portdrv_core.c | 1 -
drivers/pci/pcie/portdrv_pci.c | 14 +++++++++++++-
2 files changed, 13 insertions(+), 2 deletions(-)
diff --git a/drivers/pci/pcie/portdrv_core.c b/drivers/pci/pcie/portdrv_core.c
index 50a9522..1991aca 100644
--- a/drivers/pci/pcie/portdrv_core.c
+++ b/drivers/pci/pcie/portdrv_core.c
@@ -491,7 +491,6 @@ void pcie_port_device_remove(struct pci_dev *dev)
{
device_for_each_child(&dev->dev, NULL, remove_iter);
pci_free_irq_vectors(dev);
- pci_disable_device(dev);
}
/**
diff --git a/drivers/pci/pcie/portdrv_pci.c b/drivers/pci/pcie/portdrv_pci.c
index 3a3ce40..cab37a8 100644
--- a/drivers/pci/pcie/portdrv_pci.c
+++ b/drivers/pci/pcie/portdrv_pci.c
@@ -143,6 +143,18 @@ static void pcie_portdrv_remove(struct pci_dev *dev)
}
pcie_port_device_remove(dev);
+ pci_disable_device(dev);
+}
+
+static void pcie_portdrv_shutdown(struct pci_dev *dev)
+{
+ if (pci_bridge_d3_possible(dev)) {
+ pm_runtime_forbid(&dev->dev);
+ pm_runtime_get_noresume(&dev->dev);
+ pm_runtime_dont_use_autosuspend(&dev->dev);
+ }
+
+ pcie_port_device_remove(dev);
}
static pci_ers_result_t pcie_portdrv_error_detected(struct pci_dev *dev,
@@ -211,7 +223,7 @@ static struct pci_driver pcie_portdriver = {
.probe = pcie_portdrv_probe,
.remove = pcie_portdrv_remove,
- .shutdown = pcie_portdrv_remove,
+ .shutdown = pcie_portdrv_shutdown,
.err_handler = &pcie_portdrv_err_handler,
--
2.1.0
