This is a note to let you know that I've just added the patch titled
PCI: hv: Add a per-bus mutex state_lock
to the 5.15-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=summary
The filename of the patch is:
pci-hv-add-a-per-bus-mutex-state_lock.patch
and it can be found in the queue-5.15 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable@xxxxxxxxxxxxxxx> know about it.
>From 067d6ec7ed5b49380688e06c1e5f883a71bef4fe Mon Sep 17 00:00:00 2001
From: Dexuan Cui <decui@xxxxxxxxxxxxx>
Date: Wed, 14 Jun 2023 21:44:51 -0700
Subject: PCI: hv: Add a per-bus mutex state_lock
From: Dexuan Cui <decui@xxxxxxxxxxxxx>
commit 067d6ec7ed5b49380688e06c1e5f883a71bef4fe upstream.
In the case of fast device addition/removal, it's possible that
hv_eject_device_work() can start to run before create_root_hv_pci_bus()
starts to run; as a result, the pci_get_domain_bus_and_slot() in
hv_eject_device_work() can return a 'pdev' of NULL, and
hv_eject_device_work() can remove the 'hpdev', and immediately send a
message PCI_EJECTION_COMPLETE to the host, and the host immediately
unassigns the PCI device from the guest; meanwhile,
create_root_hv_pci_bus() and the PCI device driver can be probing the
dead PCI device and reporting timeout errors.
Fix the issue by adding a per-bus mutex 'state_lock' and grabbing the
mutex before powering on the PCI bus in hv_pci_enter_d0(): when
hv_eject_device_work() starts to run, it's able to find the 'pdev' and call
pci_stop_and_remove_bus_device(pdev): if the PCI device driver has
loaded, the PCI device driver's probe() function is already called in
create_root_hv_pci_bus() -> pci_bus_add_devices(), and now
hv_eject_device_work() -> pci_stop_and_remove_bus_device() is able
to call the PCI device driver's remove() function and remove the device
reliably; if the PCI device driver hasn't loaded yet, the function call
hv_eject_device_work() -> pci_stop_and_remove_bus_device() is able to
remove the PCI device reliably and the PCI device driver's probe()
function won't be called; if the PCI device driver's probe() is already
running (e.g., systemd-udev is loading the PCI device driver), it must
be holding the per-device lock, and after the probe() finishes and releases
the lock, hv_eject_device_work() -> pci_stop_and_remove_bus_device() is
able to proceed to remove the device reliably.
Fixes: 4daace0d8ce8 ("PCI: hv: Add paravirtual PCI front-end for Microsoft Hyper-V VMs")
Signed-off-by: Dexuan Cui <decui@xxxxxxxxxxxxx>
Reviewed-by: Michael Kelley <mikelley@xxxxxxxxxxxxx>
Acked-by: Lorenzo Pieralisi <lpieralisi@xxxxxxxxxx>
Cc: stable@xxxxxxxxxxxxxxx
Link: https://lore.kernel.org/r/20230615044451.5580-6-decui@xxxxxxxxxxxxx
Signed-off-by: Wei Liu <wei.liu@xxxxxxxxxx>
Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>
---
drivers/pci/controller/pci-hyperv.c | 29 ++++++++++++++++++++++++++---
1 file changed, 26 insertions(+), 3 deletions(-)
--- a/drivers/pci/controller/pci-hyperv.c
+++ b/drivers/pci/controller/pci-hyperv.c
@@ -483,7 +483,10 @@ struct hv_pcibus_device {
struct fwnode_handle *fwnode;
/* Protocol version negotiated with the host */
enum pci_protocol_version_t protocol_version;
+
+ struct mutex state_lock;
enum hv_pcibus_state state;
+
struct hv_device *hdev;
resource_size_t low_mmio_space;
resource_size_t high_mmio_space;
@@ -2191,6 +2194,8 @@ static void pci_devices_present_work(str
if (!dr)
return;
+ mutex_lock(&hbus->state_lock);
+
/* First, mark all existing children as reported missing. */
spin_lock_irqsave(&hbus->device_list_lock, flags);
list_for_each_entry(hpdev, &hbus->children, list_entry) {
@@ -2272,6 +2277,8 @@ static void pci_devices_present_work(str
break;
}
+ mutex_unlock(&hbus->state_lock);
+
kfree(dr);
}
@@ -2420,6 +2427,8 @@ static void hv_eject_device_work(struct
hpdev = container_of(work, struct hv_pci_dev, wrk);
hbus = hpdev->hbus;
+ mutex_lock(&hbus->state_lock);
+
/*
* Ejection can come before or after the PCI bus has been set up, so
* attempt to find it and tear down the bus state, if it exists. This
@@ -2456,6 +2465,8 @@ static void hv_eject_device_work(struct
put_pcichild(hpdev);
put_pcichild(hpdev);
/* hpdev has been freed. Do not use it any more. */
+
+ mutex_unlock(&hbus->state_lock);
}
/**
@@ -3218,6 +3229,7 @@ static int hv_pci_probe(struct hv_device
return -ENOMEM;
hbus->bridge = bridge;
+ mutex_init(&hbus->state_lock);
hbus->state = hv_pcibus_init;
hbus->wslot_res_allocated = -1;
@@ -3322,9 +3334,11 @@ static int hv_pci_probe(struct hv_device
if (ret)
goto free_irq_domain;
+ mutex_lock(&hbus->state_lock);
+
ret = hv_pci_enter_d0(hdev);
if (ret)
- goto free_irq_domain;
+ goto release_state_lock;
ret = hv_pci_allocate_bridge_windows(hbus);
if (ret)
@@ -3342,12 +3356,15 @@ static int hv_pci_probe(struct hv_device
if (ret)
goto free_windows;
+ mutex_unlock(&hbus->state_lock);
return 0;
free_windows:
hv_pci_free_bridge_windows(hbus);
exit_d0:
(void) hv_pci_bus_exit(hdev, true);
+release_state_lock:
+ mutex_unlock(&hbus->state_lock);
free_irq_domain:
irq_domain_remove(hbus->irq_domain);
free_fwnode:
@@ -3580,20 +3597,26 @@ static int hv_pci_resume(struct hv_devic
if (ret)
goto out;
+ mutex_lock(&hbus->state_lock);
+
ret = hv_pci_enter_d0(hdev);
if (ret)
- goto out;
+ goto release_state_lock;
ret = hv_send_resources_allocated(hdev);
if (ret)
- goto out;
+ goto release_state_lock;
prepopulate_bars(hbus);
hv_pci_restore_msi_state(hbus);
hbus->state = hv_pcibus_installed;
+ mutex_unlock(&hbus->state_lock);
return 0;
+
+release_state_lock:
+ mutex_unlock(&hbus->state_lock);
out:
vmbus_close(hdev->channel);
return ret;
Patches currently in stable-queue which might be from decui@xxxxxxxxxxxxx are
queue-5.15/pci-hv-add-a-per-bus-mutex-state_lock.patch
queue-5.15/pci-hv-fix-a-race-condition-in-hv_irq_unmask-that-can-cause-panic.patch
queue-5.15/revert-pci-hv-fix-a-timing-issue-which-causes-kdump-to-fail-occasionally.patch
queue-5.15/pci-hv-remove-the-useless-hv_pcichild_state-from-struct-hv_pci_dev.patch
queue-5.15/drivers-hv-vmbus-call-hv_synic_free-if-hv_synic_alloc-fails.patch
queue-5.15/pci-hv-fix-a-race-condition-bug-in-hv_pci_query_relations.patch
