With commit f84b21da3624 ("PCI: hv: Don't load the driver for baremetal root
partition"),
the bare metal Linux root partition won't use the pci-hyperv driver, but
when a Linux VM runs on the Linux root partition, pci-hyperv's module_init
function init_hv_pci_drv() can still run, e.g. in the case of
CONFIG_PCI_HYPERV=y, even if the VMBus driver is not used in such a VM
(i.e. the hv_vmbus driver's init function returns -ENODEV due to
vmbus_root_device being NULL).
In such a Linux VM, init_hv_pci_drv() runs with a side effect: the 3
hvpci_block_ops callbacks are set to functions that depend on hv_vmbus.
Later, when the MLX driver in such a VM invokes the callbacks, e.g. in
drivers/net/ethernet/mellanox/mlx5/core/lib/hv.c:
mlx5_hv_register_invalidate(), hvpci_block_ops.reg_blk_invalidate() is
hv_register_block_invalidate() rather than a NULL function pointer, and
hv_register_block_invalidate() assumes that it can find a struct
hv_pcibus_device from pdev->bus->sysdata, which is false in such a VM.
Consequently, hv_register_block_invalidate() -> get_pcichild_wslot() ->
spin_lock_irqsave() may hang since it can be accessing an invalid
spinlock pointer.
Fix the issue by exporting hv_vmbus_exists() and using it in pci-hyperv:
hv_root_partition() is true and hv_nested is false ==>
hv_vmbus_exists() is false.
hv_root_partition() is true and hv_nested is true ==>
hv_vmbus_exists() is true.
hv_root_partition() is false ==> hv_vmbus_exists() is true.
While at it, rename vmbus_exists() to hv_vmbus_exists() to follow the
convention that all public functions have the hv_ prefix; also change
the return value's type from int to bool to make the code more readable;
also move the two pr_info() calls.
Reported-by: Mukesh Rathor <[email protected]>
Signed-off-by: Dexuan Cui <[email protected]>
---
drivers/hv/vmbus_drv.c | 20 ++++++++------------
drivers/pci/controller/pci-hyperv.c | 2 +-
include/linux/hyperv.h | 2 ++
3 files changed, 11 insertions(+), 13 deletions(-)
diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c
index bc4fc1951ae1..2c8936efc8d1 100644
--- a/drivers/hv/vmbus_drv.c
+++ b/drivers/hv/vmbus_drv.c
@@ -101,13 +101,11 @@ struct device *hv_get_vmbus_root_device(void)
}
EXPORT_SYMBOL_GPL(hv_get_vmbus_root_device);
-static int vmbus_exists(void)
+bool hv_vmbus_exists(void)
{
- if (vmbus_root_device == NULL)
- return -ENODEV;
-
- return 0;
+ return vmbus_root_device != NULL;
}
+EXPORT_SYMBOL_GPL(hv_vmbus_exists);
static u8 channel_monitor_group(const struct vmbus_channel *channel)
{
@@ -1582,11 +1580,10 @@ int __vmbus_driver_register(struct hv_driver
*hv_driver, struct module *owner, c
{
int ret;
- pr_info("registering driver %s\n", hv_driver->name);
+ if (!hv_vmbus_exists())
+ return -ENODEV;
- ret = vmbus_exists();
- if (ret < 0)
- return ret;
+ pr_info("registering driver %s\n", hv_driver->name);
hv_driver->driver.name = hv_driver->name;
hv_driver->driver.owner = owner;
@@ -1612,9 +1609,8 @@ EXPORT_SYMBOL_GPL(__vmbus_driver_register);
*/
void vmbus_driver_unregister(struct hv_driver *hv_driver)
{
- pr_info("unregistering driver %s\n", hv_driver->name);
-
- if (!vmbus_exists()) {
+ if (hv_vmbus_exists()) {
+ pr_info("unregistering driver %s\n", hv_driver->name);
driver_unregister(&hv_driver->driver);
vmbus_free_dynids(hv_driver);
}
diff --git a/drivers/pci/controller/pci-hyperv.c
b/drivers/pci/controller/pci-hyperv.c
index 2c7a406b4ba8..226b8bb802f3 100644
--- a/drivers/pci/controller/pci-hyperv.c
+++ b/drivers/pci/controller/pci-hyperv.c
@@ -4166,7 +4166,7 @@ static int __init init_hv_pci_drv(void)
if (!hv_is_hyperv_initialized())
return -ENODEV;
- if (hv_root_partition() && !hv_nested)
+ if (!hv_vmbus_exists())
return -ENODEV;
ret = hv_pci_irqchip_init();
diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h
index dfc516c1c719..5459e776ec17 100644
--- a/include/linux/hyperv.h
+++ b/include/linux/hyperv.h
@@ -1304,6 +1304,8 @@ static inline void *hv_get_drvdata(struct hv_device *dev)
struct device *hv_get_vmbus_root_device(void);
+bool hv_vmbus_exists(void);
+
struct hv_ring_buffer_debug_info {
u32 current_interrupt_mask;
u32 current_read_index;
--
2.43.0
