[PATCH] PCI: Clear Bus Master bit only on kexec reboot

[Khalid Aziz]

Add a flag to tell the PCI subsystem that kernel is shutting down
in prepapration to kexec a kernel. Add code in PCI subsystem to use
this flag to clear Bus Master bit on PCI devices only in case of
kexec reboot. This fixes https://bugzilla.kernel.org/show_bug.cgi?id=63861
and avoids any other issues caused by clearing Bus Master bit on PCI
devices in normal shutdown path. This patch is based on discussion at
http://marc.info/?l=linux-pci&m=138425645204355&w=2

Signed-off-by: Khalid Aziz <khalid.aziz at oracle.com>
Acked-by: Konstantin Khlebnikov <koct9i at gmail.com>
Cc: stable at vger.kernel.org
---
 drivers/pci/pci-driver.c | 9 ++++++---
 drivers/pci/pci.h        | 3 +++
 kernel/kexec.c           | 4 ++++
 3 files changed, 13 insertions(+), 3 deletions(-)

diff --git a/drivers/pci/pci-driver.c b/drivers/pci/pci-driver.c
index 9042fdb..e920195 100644
--- a/drivers/pci/pci-driver.c
+++ b/drivers/pci/pci-driver.c
@@ -400,10 +400,13 @@ static void pci_device_shutdown(struct device *dev)
 	pci_msix_shutdown(pci_dev);
 
 	/*
-	 * 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 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 (pci_dev->current_state <= PCI_D3hot)
+	if (kexec_in_progress && (pci_dev->current_state <= PCI_D3hot))
 		pci_clear_master(pci_dev);
 }
 
diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h
index 9c91ecc..7d85733 100644
--- a/drivers/pci/pci.h
+++ b/drivers/pci/pci.h
@@ -9,6 +9,9 @@
 extern const unsigned char pcix_bus_speed[];
 extern const unsigned char pcie_link_speed[];
 
+/* flag to track if kexec reboot is in progress */
+extern unsigned long kexec_in_progress;
+
 /* Functions internal to the PCI core code */
 
 int pci_create_sysfs_dev_files(struct pci_dev *pdev);
diff --git a/kernel/kexec.c b/kernel/kexec.c
index 490afc0..fd2d63e 100644
--- a/kernel/kexec.c
+++ b/kernel/kexec.c
@@ -47,6 +47,9 @@ u32 vmcoreinfo_note[VMCOREINFO_NOTE_SIZE/4];
 size_t vmcoreinfo_size;
 size_t vmcoreinfo_max_size = sizeof(vmcoreinfo_data);
 
+/* Flag to indicate we are going to kexec a new kernel */
+unsigned long kexec_in_progress = 0;
+
 /* Location of the reserved area for the crash kernel */
 struct resource crashk_res = {
 	.name  = "Crash kernel",
@@ -1675,6 +1678,7 @@ int kernel_kexec(void)
 	} else
 #endif
 	{
+		kexec_in_progress = 1;
 		kernel_restart_prepare(NULL);
 		printk(KERN_EMERG "Starting new kernel\n");
 		machine_shutdown();
-- 
1.8.3.2