Hi, Tiezhu
> ------------------ Original ------------------
> From: "Tiezhu Yang"<yangtiezhu@xxxxxxxxxxx>;
> Date: Mon, Sep 14, 2020 04:29 AM
> To: "Bjorn Helgaas"<bhelgaas@xxxxxxxxxx>;
> Cc: "Konstantin Khlebnikov"<khlebnikov@xxxxxxxxxx>; "Khalid Aziz"<khalid.aziz@xxxxxxxxxx>; "Vivek Goyal"<vgoyal@xxxxxxxxxx>; "Lukas Wunner"<lukas@xxxxxxxxx>; "oohall"<oohall@xxxxxxxxx>; "rafael.j.wysocki"<rafael.j.wysocki@xxxxxxxxx>; "Xuefeng Li"<lixuefeng@xxxxxxxxxxx>; "Huacai Chen"<chenhc@xxxxxxxxxx>; "Jiaxun Yang"<jiaxun.yang@xxxxxxxxxxx>; "linux-pci"<linux-pci@xxxxxxxxxxxxxxx>; "linux-kernel"<linux-kernel@xxxxxxxxxxxxxxx>;
> Subject: [RFC PATCH v2] 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.
>
> 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 similar with 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 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);
> }
Have you really tried kexec? Why do you think kexec can disable pci
device successfully while normal reboot/poweroff cannot?
Huacai
>
> Signed-off-by: Tiezhu Yang <yangtiezhu@xxxxxxxxxxx>
> ---
> drivers/pci/pcie/portdrv_core.c | 1 -
> drivers/pci/pcie/portdrv_pci.c | 25 ++++++++++++++++++++++++-
> 2 files changed, 24 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..ce89a9e8 100644
> --- a/drivers/pci/pcie/portdrv_pci.c
> +++ b/drivers/pci/pcie/portdrv_pci.c
> @@ -15,6 +15,7 @@
> #include <linux/init.h>
> #include <linux/aer.h>
> #include <linux/dmi.h>
> +#include <linux/kexec.h>
>
> #include "../pci.h"
> #include "portdrv.h"
> @@ -143,6 +144,28 @@ 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);
> +
> + /*
> + * 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 && (dev->current_state <= PCI_D3hot))
> + pci_disable_device(dev);
> }
>
> static pci_ers_result_t pcie_portdrv_error_detected(struct pci_dev *dev,
> @@ -211,7 +234,7 @@ static void pcie_portdrv_err_resume(struct pci_dev *dev)
>
> .probe = pcie_portdrv_probe,
> .remove = pcie_portdrv_remove,
> - .shutdown = pcie_portdrv_remove,
> + .shutdown = pcie_portdrv_shutdown,
>
> .err_handler = &pcie_portdrv_err_handler,
>
> --
> 1.8.3.1
