2018-01-26 12:50:27 -06:00
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2021-07-27 02:06:57 +08:00
|
|
|
|
2017-07-31 16:48:29 -07:00
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
2018-07-29 12:15:33 +02:00
|
|
|
|
2025-07-07 10:20:16 +02:00
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
2017-04-18 09:02:48 -05:00
|
|
|
|
2022-01-05 11:32:36 -08:00
|
|
|
|
|
|
|
|
|
PCI: hv: Fix ring buffer size calculation
For a physical PCI device that is passed through to a Hyper-V guest VM,
current code specifies the VMBus ring buffer size as 4 pages. But this
is an inappropriate dependency, since the amount of ring buffer space
needed is unrelated to PAGE_SIZE. For example, on x86 the ring buffer
size ends up as 16 Kbytes, while on ARM64 with 64 Kbyte pages, the ring
size bloats to 256 Kbytes. The ring buffer for PCI pass-thru devices
is used for only a few messages during device setup and removal, so any
space above a few Kbytes is wasted.
Fix this by declaring the ring buffer size to be a fixed 16 Kbytes.
Furthermore, use the VMBUS_RING_SIZE() macro so that the ring buffer
header is properly accounted for, and so the size is rounded up to a
page boundary, using the page size for which the kernel is built. While
w/64 Kbyte pages this results in a 64 Kbyte ring buffer header plus a
64 Kbyte ring buffer, that's the smallest possible with that page size.
It's still 128 Kbytes better than the current code.
Link: https://lore.kernel.org/linux-pci/20240216202240.251818-1-mhklinux@outlook.com
Signed-off-by: Michael Kelley <mhklinux@outlook.com>
Signed-off-by: Krzysztof Wilczyński <kwilczynski@kernel.org>
Reviewed-by: Kuppuswamy Sathyanarayanan <sathyanarayanan.kuppuswamy@linux.intel.com>
Reviewed-by: Ilpo Jarvinen <ilpo.jarvinen@linux.intel.com>
Reviewed-by: Long Li <longli@microsoft.com>
Cc: <stable@vger.kernel.org> # 5.15.x
2024-02-16 12:22:40 -08:00
|
|
|
|
2025-04-28 14:07:42 -07:00
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2017-05-24 13:41:27 -07:00
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2017-05-24 13:41:27 -07:00
|
|
|
|
|
|
|
|
|
2017-05-24 13:41:28 -07:00
|
|
|
|
2020-02-25 21:06:08 -08:00
|
|
|
|
2021-07-12 21:58:18 +00:00
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
2017-03-24 11:07:21 -07:00
|
|
|
|
2017-05-24 13:41:27 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2021-07-12 21:58:18 +00:00
|
|
|
|
2020-02-25 21:06:08 -08:00
|
|
|
|
2017-05-24 13:41:28 -07:00
|
|
|
|
2017-05-24 13:41:27 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2017-05-24 13:41:27 -07:00
|
|
|
|
|
|
|
|
|
2018-09-14 12:54:56 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2022-04-19 14:23:21 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2017-05-24 13:41:28 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2020-02-25 21:06:08 -08:00
|
|
|
|
2021-07-12 21:58:18 +00:00
|
|
|
|
|
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2017-02-10 15:18:46 -06:00
|
|
|
|
|
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2020-02-25 21:06:08 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2017-05-24 13:41:28 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2021-07-12 21:58:18 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-08-23 04:45:51 +00:00
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-08-23 04:45:51 +00:00
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2017-05-24 13:41:24 -07:00
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2020-02-12 18:50:48 -06:00
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
2020-02-25 21:06:08 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2020-02-12 18:50:48 -06:00
|
|
|
|
2020-02-25 21:06:08 -08:00
|
|
|
|
|
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2019-09-28 02:43:08 +03:00
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2017-05-24 13:41:28 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2017-05-24 13:41:28 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2021-07-12 21:58:18 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2019-08-22 05:05:37 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-08-23 04:45:51 +00:00
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
PCI: hv: Fix ring buffer size calculation
For a physical PCI device that is passed through to a Hyper-V guest VM,
current code specifies the VMBus ring buffer size as 4 pages. But this
is an inappropriate dependency, since the amount of ring buffer space
needed is unrelated to PAGE_SIZE. For example, on x86 the ring buffer
size ends up as 16 Kbytes, while on ARM64 with 64 Kbyte pages, the ring
size bloats to 256 Kbytes. The ring buffer for PCI pass-thru devices
is used for only a few messages during device setup and removal, so any
space above a few Kbytes is wasted.
Fix this by declaring the ring buffer size to be a fixed 16 Kbytes.
Furthermore, use the VMBUS_RING_SIZE() macro so that the ring buffer
header is properly accounted for, and so the size is rounded up to a
page boundary, using the page size for which the kernel is built. While
w/64 Kbyte pages this results in a 64 Kbyte ring buffer header plus a
64 Kbyte ring buffer, that's the smallest possible with that page size.
It's still 128 Kbytes better than the current code.
Link: https://lore.kernel.org/linux-pci/20240216202240.251818-1-mhklinux@outlook.com
Signed-off-by: Michael Kelley <mhklinux@outlook.com>
Signed-off-by: Krzysztof Wilczyński <kwilczynski@kernel.org>
Reviewed-by: Kuppuswamy Sathyanarayanan <sathyanarayanan.kuppuswamy@linux.intel.com>
Reviewed-by: Ilpo Jarvinen <ilpo.jarvinen@linux.intel.com>
Reviewed-by: Long Li <longli@microsoft.com>
Cc: <stable@vger.kernel.org> # 5.15.x
2024-02-16 12:22:40 -08:00
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
PCI: hv: Add hibernation support
Add suspend() and resume() functions so that Hyper-V virtual PCI devices
are handled properly when the VM hibernates and resumes from
hibernation.
Note that the suspend() function must make sure there are no pending
work items before calling vmbus_close(), since it runs in a process
context as a callback in dpm_suspend(). When it starts to run, the
channel callback hv_pci_onchannelcallback(), which runs in a tasklet
context, can be still running concurrently and scheduling new work items
onto hbus->wq in hv_pci_devices_present() and hv_pci_eject_device(), and
the work item handlers can access the vmbus channel, which can be being
closed by hv_pci_suspend(), e.g. the work item handler
pci_devices_present_work() -> new_pcichild_device() writes to the vmbus
channel.
To eliminate the race, hv_pci_suspend() disables the channel callback
tasklet, sets hbus->state to hv_pcibus_removing, and re-enables the
tasklet. This way, when hv_pci_suspend() proceeds, it knows that no new
work item can be scheduled, and then it flushes hbus->wq and safely
closes the vmbus channel.
Signed-off-by: Dexuan Cui <decui@microsoft.com>
Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Reviewed-by: Michael Kelley <mikelley@microsoft.com>
2019-11-24 21:33:52 -08:00
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2021-07-27 02:06:57 +08:00
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
2021-07-27 02:06:57 +08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2021-07-27 02:06:54 +08:00
|
|
|
|
2021-07-27 02:06:56 +08:00
|
|
|
|
2019-11-24 21:33:53 -08:00
|
|
|
|
|
|
|
|
|
PCI: hv: Add a per-bus mutex state_lock
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@microsoft.com>
Reviewed-by: Michael Kelley <mikelley@microsoft.com>
Acked-by: Lorenzo Pieralisi <lpieralisi@kernel.org>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20230615044451.5580-6-decui@microsoft.com
Signed-off-by: Wei Liu <wei.liu@kernel.org>
2023-06-14 21:44:51 -07:00
|
|
|
|
|
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
PCI: hv: Add a per-bus mutex state_lock
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@microsoft.com>
Reviewed-by: Michael Kelley <mikelley@microsoft.com>
Acked-by: Lorenzo Pieralisi <lpieralisi@kernel.org>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20230615044451.5580-6-decui@microsoft.com
Signed-off-by: Wei Liu <wei.liu@kernel.org>
2023-06-14 21:44:51 -07:00
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2017-05-24 13:41:25 -07:00
|
|
|
|
2018-03-15 14:20:53 +00:00
|
|
|
|
2019-03-01 06:59:02 +00:00
|
|
|
|
2020-05-07 13:02:11 +08:00
|
|
|
|
|
|
|
|
|
2023-03-26 06:52:07 -07:00
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2020-02-25 21:06:07 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-09-22 10:52:57 -07:00
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2017-04-18 09:02:48 -05:00
|
|
|
|
2018-09-14 12:54:56 -07:00
|
|
|
|
2020-02-25 21:06:07 -08:00
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2019-08-22 05:05:37 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2019-09-28 02:43:08 +03:00
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
PCI: hv: Fix 2 hang issues in hv_compose_msi_msg()
1. With the patch "x86/vector/msi: Switch to global reservation mode",
the recent v4.15 and newer kernels always hang for 1-vCPU Hyper-V VM
with SR-IOV. This is because when we reach hv_compose_msi_msg() by
request_irq() -> request_threaded_irq() ->__setup_irq()->irq_startup()
-> __irq_startup() -> irq_domain_activate_irq() -> ... ->
msi_domain_activate() -> ... -> hv_compose_msi_msg(), local irq is
disabled in __setup_irq().
Note: when we reach hv_compose_msi_msg() by another code path:
pci_enable_msix_range() -> ... -> irq_domain_activate_irq() -> ... ->
hv_compose_msi_msg(), local irq is not disabled.
hv_compose_msi_msg() depends on an interrupt from the host.
With interrupts disabled, a UP VM always hangs in the busy loop in
the function, because the interrupt callback hv_pci_onchannelcallback()
can not be called.
We can do nothing but work it around by polling the channel. This
is ugly, but we don't have any other choice.
2. If the host is ejecting the VF device before we reach
hv_compose_msi_msg(), in a UP VM, we can hang in hv_compose_msi_msg()
forever, because at this time the host doesn't respond to the
CREATE_INTERRUPT request. This issue exists the first day the
pci-hyperv driver appears in the kernel.
Luckily, this can also by worked around by polling the channel
for the PCI_EJECT message and hpdev->state, and by checking the
PCI vendor ID.
Note: actually the above 2 issues also happen to a SMP VM, if
"hbus->hdev->channel->target_cpu == smp_processor_id()" is true.
Fixes: 4900be83602b ("x86/vector/msi: Switch to global reservation mode")
Tested-by: Adrian Suhov <v-adsuho@microsoft.com>
Tested-by: Chris Valean <v-chvale@microsoft.com>
Signed-off-by: Dexuan Cui <decui@microsoft.com>
Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Reviewed-by: Michael Kelley <mikelley@microsoft.com>
Acked-by: Haiyang Zhang <haiyangz@microsoft.com>
Cc: <stable@vger.kernel.org>
Cc: Stephen Hemminger <sthemmin@microsoft.com>
Cc: K. Y. Srinivasan <kys@microsoft.com>
Cc: Vitaly Kuznetsov <vkuznets@redhat.com>
Cc: Jack Morgenstein <jackm@mellanox.com>
2018-03-15 14:21:08 +00:00
|
|
|
|
|
|
|
|
|
2022-01-05 11:32:35 -08:00
|
|
|
|
2025-07-07 10:20:16 +02:00
|
|
|
|
|
|
|
|
|
2022-01-05 11:32:35 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2022-11-11 14:55:17 +01:00
|
|
|
|
2022-02-17 11:45:19 +08:00
|
|
|
|
|
|
|
|
|
2025-07-11 12:18:52 -07:00
|
|
|
|
2022-02-17 11:45:19 +08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2025-07-11 12:18:52 -07:00
|
|
|
|
2022-02-17 11:45:19 +08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2022-04-27 08:07:33 -06:00
|
|
|
|
2022-02-17 11:45:19 +08:00
|
|
|
|
2022-07-01 15:00:55 -05:00
|
|
|
|
2022-02-17 11:45:19 +08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2022-04-27 08:07:33 -06:00
|
|
|
|
PCI: hv: Fix a race condition in hv_irq_unmask() that can cause panic
When the host tries to remove a PCI device, the host first sends a
PCI_EJECT message to the guest, and the guest is supposed to gracefully
remove the PCI device and send a PCI_EJECTION_COMPLETE message to the host;
the host then sends a VMBus message CHANNELMSG_RESCIND_CHANNELOFFER to
the guest (when the guest receives this message, the device is already
unassigned from the guest) and the guest can do some final cleanup work;
if the guest fails to respond to the PCI_EJECT message within one minute,
the host sends the VMBus message CHANNELMSG_RESCIND_CHANNELOFFER and
removes the PCI device forcibly.
In the case of fast device addition/removal, it's possible that the PCI
device driver is still configuring MSI-X interrupts when the guest receives
the PCI_EJECT message; the channel callback calls hv_pci_eject_device(),
which sets hpdev->state to hv_pcichild_ejecting, and schedules a work
hv_eject_device_work(); if the PCI device driver is calling
pci_alloc_irq_vectors() -> ... -> hv_compose_msi_msg(), we can break the
while loop in hv_compose_msi_msg() due to the updated hpdev->state, and
leave data->chip_data with its default value of NULL; later, when the PCI
device driver calls request_irq() -> ... -> hv_irq_unmask(), the guest
crashes in hv_arch_irq_unmask() due to data->chip_data being NULL.
Fix the issue by not testing hpdev->state in the while loop: when the
guest receives PCI_EJECT, the device is still assigned to the guest, and
the guest has one minute to finish the device removal gracefully. We don't
really need to (and we should not) test hpdev->state in the loop.
Fixes: de0aa7b2f97d ("PCI: hv: Fix 2 hang issues in hv_compose_msi_msg()")
Signed-off-by: Dexuan Cui <decui@microsoft.com>
Reviewed-by: Michael Kelley <mikelley@microsoft.com>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20230615044451.5580-3-decui@microsoft.com
Signed-off-by: Wei Liu <wei.liu@kernel.org>
2023-06-14 21:44:48 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2022-02-17 11:45:19 +08:00
|
|
|
|
2023-04-20 18:30:25 -07:00
|
|
|
|
2022-02-17 11:45:19 +08:00
|
|
|
|
2023-04-20 18:30:25 -07:00
|
|
|
|
2022-02-17 11:45:19 +08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2022-04-27 08:07:33 -06:00
|
|
|
|
|
|
|
|
|
2022-02-17 11:45:19 +08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-04-20 18:30:25 -07:00
|
|
|
|
2022-02-17 11:45:19 +08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-04-20 18:30:25 -07:00
|
|
|
|
2022-02-17 11:45:19 +08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-04-20 18:30:25 -07:00
|
|
|
|
|
|
|
|
|
2022-02-17 11:45:19 +08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2022-11-07 17:18:31 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2022-02-17 11:45:19 +08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2025-07-11 12:18:52 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2022-01-05 11:32:36 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2025-07-07 10:20:16 +02:00
|
|
|
|
2022-01-05 11:32:36 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2025-04-28 14:07:42 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2022-01-05 11:32:36 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2025-04-28 14:07:42 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2022-01-05 11:32:36 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2025-04-28 14:07:42 -07:00
|
|
|
|
2022-01-05 11:32:36 -08:00
|
|
|
|
|
|
|
|
|
2026-02-21 16:37:42 -08:00
|
|
|
|
2022-01-05 11:32:36 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2025-04-28 14:07:42 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2022-01-05 11:32:36 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2022-02-17 11:45:19 +08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2022-01-05 11:32:36 -08:00
|
|
|
|
2022-01-05 11:32:35 -08:00
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-08-23 04:49:22 +00:00
|
|
|
|
|
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2022-05-12 00:32:06 +02:00
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2018-05-23 10:11:12 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
2018-05-23 21:12:01 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2017-02-10 15:18:46 -06:00
|
|
|
|
|
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2017-02-10 15:18:46 -06:00
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
2023-03-26 06:52:07 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-03-26 06:52:07 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-07-01 20:26:05 +00:00
|
|
|
|
|
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-03-26 06:52:07 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
2023-03-26 06:52:07 -07:00
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
2023-03-26 06:52:07 -07:00
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
PCI: hv: Fix 2 hang issues in hv_compose_msi_msg()
1. With the patch "x86/vector/msi: Switch to global reservation mode",
the recent v4.15 and newer kernels always hang for 1-vCPU Hyper-V VM
with SR-IOV. This is because when we reach hv_compose_msi_msg() by
request_irq() -> request_threaded_irq() ->__setup_irq()->irq_startup()
-> __irq_startup() -> irq_domain_activate_irq() -> ... ->
msi_domain_activate() -> ... -> hv_compose_msi_msg(), local irq is
disabled in __setup_irq().
Note: when we reach hv_compose_msi_msg() by another code path:
pci_enable_msix_range() -> ... -> irq_domain_activate_irq() -> ... ->
hv_compose_msi_msg(), local irq is not disabled.
hv_compose_msi_msg() depends on an interrupt from the host.
With interrupts disabled, a UP VM always hangs in the busy loop in
the function, because the interrupt callback hv_pci_onchannelcallback()
can not be called.
We can do nothing but work it around by polling the channel. This
is ugly, but we don't have any other choice.
2. If the host is ejecting the VF device before we reach
hv_compose_msi_msg(), in a UP VM, we can hang in hv_compose_msi_msg()
forever, because at this time the host doesn't respond to the
CREATE_INTERRUPT request. This issue exists the first day the
pci-hyperv driver appears in the kernel.
Luckily, this can also by worked around by polling the channel
for the PCI_EJECT message and hpdev->state, and by checking the
PCI vendor ID.
Note: actually the above 2 issues also happen to a SMP VM, if
"hbus->hdev->channel->target_cpu == smp_processor_id()" is true.
Fixes: 4900be83602b ("x86/vector/msi: Switch to global reservation mode")
Tested-by: Adrian Suhov <v-adsuho@microsoft.com>
Tested-by: Chris Valean <v-chvale@microsoft.com>
Signed-off-by: Dexuan Cui <decui@microsoft.com>
Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Reviewed-by: Michael Kelley <mikelley@microsoft.com>
Acked-by: Haiyang Zhang <haiyangz@microsoft.com>
Cc: <stable@vger.kernel.org>
Cc: Stephen Hemminger <sthemmin@microsoft.com>
Cc: K. Y. Srinivasan <kys@microsoft.com>
Cc: Vitaly Kuznetsov <vkuznets@redhat.com>
Cc: Jack Morgenstein <jackm@mellanox.com>
2018-03-15 14:21:08 +00:00
|
|
|
|
|
|
|
|
|
2023-03-26 06:52:07 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
PCI: hv: Fix 2 hang issues in hv_compose_msi_msg()
1. With the patch "x86/vector/msi: Switch to global reservation mode",
the recent v4.15 and newer kernels always hang for 1-vCPU Hyper-V VM
with SR-IOV. This is because when we reach hv_compose_msi_msg() by
request_irq() -> request_threaded_irq() ->__setup_irq()->irq_startup()
-> __irq_startup() -> irq_domain_activate_irq() -> ... ->
msi_domain_activate() -> ... -> hv_compose_msi_msg(), local irq is
disabled in __setup_irq().
Note: when we reach hv_compose_msi_msg() by another code path:
pci_enable_msix_range() -> ... -> irq_domain_activate_irq() -> ... ->
hv_compose_msi_msg(), local irq is not disabled.
hv_compose_msi_msg() depends on an interrupt from the host.
With interrupts disabled, a UP VM always hangs in the busy loop in
the function, because the interrupt callback hv_pci_onchannelcallback()
can not be called.
We can do nothing but work it around by polling the channel. This
is ugly, but we don't have any other choice.
2. If the host is ejecting the VF device before we reach
hv_compose_msi_msg(), in a UP VM, we can hang in hv_compose_msi_msg()
forever, because at this time the host doesn't respond to the
CREATE_INTERRUPT request. This issue exists the first day the
pci-hyperv driver appears in the kernel.
Luckily, this can also by worked around by polling the channel
for the PCI_EJECT message and hpdev->state, and by checking the
PCI vendor ID.
Note: actually the above 2 issues also happen to a SMP VM, if
"hbus->hdev->channel->target_cpu == smp_processor_id()" is true.
Fixes: 4900be83602b ("x86/vector/msi: Switch to global reservation mode")
Tested-by: Adrian Suhov <v-adsuho@microsoft.com>
Tested-by: Chris Valean <v-chvale@microsoft.com>
Signed-off-by: Dexuan Cui <decui@microsoft.com>
Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Reviewed-by: Michael Kelley <mikelley@microsoft.com>
Acked-by: Haiyang Zhang <haiyangz@microsoft.com>
Cc: <stable@vger.kernel.org>
Cc: Stephen Hemminger <sthemmin@microsoft.com>
Cc: K. Y. Srinivasan <kys@microsoft.com>
Cc: Vitaly Kuznetsov <vkuznets@redhat.com>
Cc: Jack Morgenstein <jackm@mellanox.com>
2018-03-15 14:21:08 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-03-26 06:52:07 -07:00
|
|
|
|
PCI: hv: Fix 2 hang issues in hv_compose_msi_msg()
1. With the patch "x86/vector/msi: Switch to global reservation mode",
the recent v4.15 and newer kernels always hang for 1-vCPU Hyper-V VM
with SR-IOV. This is because when we reach hv_compose_msi_msg() by
request_irq() -> request_threaded_irq() ->__setup_irq()->irq_startup()
-> __irq_startup() -> irq_domain_activate_irq() -> ... ->
msi_domain_activate() -> ... -> hv_compose_msi_msg(), local irq is
disabled in __setup_irq().
Note: when we reach hv_compose_msi_msg() by another code path:
pci_enable_msix_range() -> ... -> irq_domain_activate_irq() -> ... ->
hv_compose_msi_msg(), local irq is not disabled.
hv_compose_msi_msg() depends on an interrupt from the host.
With interrupts disabled, a UP VM always hangs in the busy loop in
the function, because the interrupt callback hv_pci_onchannelcallback()
can not be called.
We can do nothing but work it around by polling the channel. This
is ugly, but we don't have any other choice.
2. If the host is ejecting the VF device before we reach
hv_compose_msi_msg(), in a UP VM, we can hang in hv_compose_msi_msg()
forever, because at this time the host doesn't respond to the
CREATE_INTERRUPT request. This issue exists the first day the
pci-hyperv driver appears in the kernel.
Luckily, this can also by worked around by polling the channel
for the PCI_EJECT message and hpdev->state, and by checking the
PCI vendor ID.
Note: actually the above 2 issues also happen to a SMP VM, if
"hbus->hdev->channel->target_cpu == smp_processor_id()" is true.
Fixes: 4900be83602b ("x86/vector/msi: Switch to global reservation mode")
Tested-by: Adrian Suhov <v-adsuho@microsoft.com>
Tested-by: Chris Valean <v-chvale@microsoft.com>
Signed-off-by: Dexuan Cui <decui@microsoft.com>
Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Reviewed-by: Michael Kelley <mikelley@microsoft.com>
Acked-by: Haiyang Zhang <haiyangz@microsoft.com>
Cc: <stable@vger.kernel.org>
Cc: Stephen Hemminger <sthemmin@microsoft.com>
Cc: K. Y. Srinivasan <kys@microsoft.com>
Cc: Vitaly Kuznetsov <vkuznets@redhat.com>
Cc: Jack Morgenstein <jackm@mellanox.com>
2018-03-15 14:21:08 +00:00
|
|
|
|
2023-03-26 06:52:07 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
PCI: hv: Fix 2 hang issues in hv_compose_msi_msg()
1. With the patch "x86/vector/msi: Switch to global reservation mode",
the recent v4.15 and newer kernels always hang for 1-vCPU Hyper-V VM
with SR-IOV. This is because when we reach hv_compose_msi_msg() by
request_irq() -> request_threaded_irq() ->__setup_irq()->irq_startup()
-> __irq_startup() -> irq_domain_activate_irq() -> ... ->
msi_domain_activate() -> ... -> hv_compose_msi_msg(), local irq is
disabled in __setup_irq().
Note: when we reach hv_compose_msi_msg() by another code path:
pci_enable_msix_range() -> ... -> irq_domain_activate_irq() -> ... ->
hv_compose_msi_msg(), local irq is not disabled.
hv_compose_msi_msg() depends on an interrupt from the host.
With interrupts disabled, a UP VM always hangs in the busy loop in
the function, because the interrupt callback hv_pci_onchannelcallback()
can not be called.
We can do nothing but work it around by polling the channel. This
is ugly, but we don't have any other choice.
2. If the host is ejecting the VF device before we reach
hv_compose_msi_msg(), in a UP VM, we can hang in hv_compose_msi_msg()
forever, because at this time the host doesn't respond to the
CREATE_INTERRUPT request. This issue exists the first day the
pci-hyperv driver appears in the kernel.
Luckily, this can also by worked around by polling the channel
for the PCI_EJECT message and hpdev->state, and by checking the
PCI vendor ID.
Note: actually the above 2 issues also happen to a SMP VM, if
"hbus->hdev->channel->target_cpu == smp_processor_id()" is true.
Fixes: 4900be83602b ("x86/vector/msi: Switch to global reservation mode")
Tested-by: Adrian Suhov <v-adsuho@microsoft.com>
Tested-by: Chris Valean <v-chvale@microsoft.com>
Signed-off-by: Dexuan Cui <decui@microsoft.com>
Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Reviewed-by: Michael Kelley <mikelley@microsoft.com>
Acked-by: Haiyang Zhang <haiyangz@microsoft.com>
Cc: <stable@vger.kernel.org>
Cc: Stephen Hemminger <sthemmin@microsoft.com>
Cc: K. Y. Srinivasan <kys@microsoft.com>
Cc: Vitaly Kuznetsov <vkuznets@redhat.com>
Cc: Jack Morgenstein <jackm@mellanox.com>
2018-03-15 14:21:08 +00:00
|
|
|
|
2023-03-26 06:52:07 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
PCI: hv: Fix 2 hang issues in hv_compose_msi_msg()
1. With the patch "x86/vector/msi: Switch to global reservation mode",
the recent v4.15 and newer kernels always hang for 1-vCPU Hyper-V VM
with SR-IOV. This is because when we reach hv_compose_msi_msg() by
request_irq() -> request_threaded_irq() ->__setup_irq()->irq_startup()
-> __irq_startup() -> irq_domain_activate_irq() -> ... ->
msi_domain_activate() -> ... -> hv_compose_msi_msg(), local irq is
disabled in __setup_irq().
Note: when we reach hv_compose_msi_msg() by another code path:
pci_enable_msix_range() -> ... -> irq_domain_activate_irq() -> ... ->
hv_compose_msi_msg(), local irq is not disabled.
hv_compose_msi_msg() depends on an interrupt from the host.
With interrupts disabled, a UP VM always hangs in the busy loop in
the function, because the interrupt callback hv_pci_onchannelcallback()
can not be called.
We can do nothing but work it around by polling the channel. This
is ugly, but we don't have any other choice.
2. If the host is ejecting the VF device before we reach
hv_compose_msi_msg(), in a UP VM, we can hang in hv_compose_msi_msg()
forever, because at this time the host doesn't respond to the
CREATE_INTERRUPT request. This issue exists the first day the
pci-hyperv driver appears in the kernel.
Luckily, this can also by worked around by polling the channel
for the PCI_EJECT message and hpdev->state, and by checking the
PCI vendor ID.
Note: actually the above 2 issues also happen to a SMP VM, if
"hbus->hdev->channel->target_cpu == smp_processor_id()" is true.
Fixes: 4900be83602b ("x86/vector/msi: Switch to global reservation mode")
Tested-by: Adrian Suhov <v-adsuho@microsoft.com>
Tested-by: Chris Valean <v-chvale@microsoft.com>
Signed-off-by: Dexuan Cui <decui@microsoft.com>
Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Reviewed-by: Michael Kelley <mikelley@microsoft.com>
Acked-by: Haiyang Zhang <haiyangz@microsoft.com>
Cc: <stable@vger.kernel.org>
Cc: Stephen Hemminger <sthemmin@microsoft.com>
Cc: K. Y. Srinivasan <kys@microsoft.com>
Cc: Vitaly Kuznetsov <vkuznets@redhat.com>
Cc: Jack Morgenstein <jackm@mellanox.com>
2018-03-15 14:21:08 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-03-26 06:52:07 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-03-26 06:52:07 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
2023-03-26 06:52:07 -07:00
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
2023-03-26 06:52:07 -07:00
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2018-05-23 10:11:12 -07:00
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2018-05-23 10:11:12 -07:00
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2019-08-22 05:05:37 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2025-02-07 19:07:15 +00:00
|
|
|
|
2019-08-22 05:05:37 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2020-07-06 21:52:34 +08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2019-08-22 05:05:37 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2025-05-13 21:44:40 -07:00
|
|
|
|
2019-08-22 05:05:37 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2020-07-06 21:52:34 +08:00
|
|
|
|
|
|
|
|
|
2019-08-22 05:05:37 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2025-05-13 21:44:40 -07:00
|
|
|
|
2019-08-22 05:05:37 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2020-07-06 21:52:34 +08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2019-08-22 05:05:37 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-08-23 04:45:51 +00:00
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
2022-05-11 09:23:19 -06:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
2025-05-13 21:44:40 -07:00
|
|
|
|
2016-08-23 04:45:51 +00:00
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2022-04-19 14:23:21 +02:00
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2025-08-13 07:53:50 +02:00
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2025-07-07 10:20:16 +02:00
|
|
|
|
2016-07-12 11:31:24 -04:00
|
|
|
|
|
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
2016-07-12 11:31:24 -04:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
2016-07-12 11:31:24 -04:00
|
|
|
|
2018-05-23 10:11:12 -07:00
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
2016-10-31 12:04:09 +01:00
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
2022-01-05 11:32:36 -08:00
|
|
|
|
|
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
2016-10-31 12:04:09 +01:00
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
2022-02-17 11:45:19 +08:00
|
|
|
|
2017-05-24 13:41:28 -07:00
|
|
|
|
2022-01-05 11:32:36 -08:00
|
|
|
|
|
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2022-05-12 00:32:06 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
2022-05-12 00:32:06 +02:00
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2017-05-24 13:41:28 -07:00
|
|
|
|
PCI: hv: Only reuse existing IRTE allocation for Multi-MSI
Jeffrey added Multi-MSI support to the pci-hyperv driver by the 4 patches:
08e61e861a0e ("PCI: hv: Fix multi-MSI to allow more than one MSI vector")
455880dfe292 ("PCI: hv: Fix hv_arch_irq_unmask() for multi-MSI")
b4b77778ecc5 ("PCI: hv: Reuse existing IRTE allocation in compose_msi_msg()")
a2bad844a67b ("PCI: hv: Fix interrupt mapping for multi-MSI")
It turns out that the third patch (b4b77778ecc5) causes a performance
regression because all the interrupts now happen on 1 physical CPU (or two
pCPUs, if one pCPU doesn't have enough vectors). When a guest has many PCI
devices, it may suffer from soft lockups if the workload is heavy, e.g.,
see https://lwn.net/ml/linux-kernel/20220804025104.15673-1-decui@microsoft.com/
Commit b4b77778ecc5 itself is good. The real issue is that the hypercall in
hv_irq_unmask() -> hv_arch_irq_unmask() ->
hv_do_hypercall(HVCALL_RETARGET_INTERRUPT...) only changes the target
virtual CPU rather than physical CPU; with b4b77778ecc5, the pCPU is
determined only once in hv_compose_msi_msg() where only vCPU0 is specified;
consequently the hypervisor only uses 1 target pCPU for all the interrupts.
Note: before b4b77778ecc5, the pCPU is determined twice, and when the pCPU
is determined the second time, the vCPU in the effective affinity mask is
used (i.e., it isn't always vCPU0), so the hypervisor chooses different
pCPU for each interrupt.
The hypercall will be fixed in future to update the pCPU as well, but
that will take quite a while, so let's restore the old behavior in
hv_compose_msi_msg(), i.e., don't reuse the existing IRTE allocation for
single-MSI and MSI-X; for multi-MSI, we choose the vCPU in a round-robin
manner for each PCI device, so the interrupts of different devices can
happen on different pCPUs, though the interrupts of each device happen on
some single pCPU.
The hypercall fix may not be backported to all old versions of Hyper-V, so
we want to have this guest side change forever (or at least till we're sure
the old affected versions of Hyper-V are no longer supported).
Fixes: b4b77778ecc5 ("PCI: hv: Reuse existing IRTE allocation in compose_msi_msg()")
Co-developed-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
Signed-off-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
Co-developed-by: Carl Vanderlip <quic_carlv@quicinc.com>
Signed-off-by: Carl Vanderlip <quic_carlv@quicinc.com>
Signed-off-by: Dexuan Cui <decui@microsoft.com>
Reviewed-by: Michael Kelley <mikelley@microsoft.com>
Link: https://lore.kernel.org/r/20221104222953.11356-1-decui@microsoft.com
Signed-off-by: Wei Liu <wei.liu@kernel.org>
2022-11-04 15:29:53 -07:00
|
|
|
|
2022-10-27 13:52:56 -07:00
|
|
|
|
2017-05-24 13:41:28 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2022-05-11 09:23:19 -06:00
|
|
|
|
2022-01-05 11:32:35 -08:00
|
|
|
|
2017-05-24 13:41:28 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
PCI: hv: Only reuse existing IRTE allocation for Multi-MSI
Jeffrey added Multi-MSI support to the pci-hyperv driver by the 4 patches:
08e61e861a0e ("PCI: hv: Fix multi-MSI to allow more than one MSI vector")
455880dfe292 ("PCI: hv: Fix hv_arch_irq_unmask() for multi-MSI")
b4b77778ecc5 ("PCI: hv: Reuse existing IRTE allocation in compose_msi_msg()")
a2bad844a67b ("PCI: hv: Fix interrupt mapping for multi-MSI")
It turns out that the third patch (b4b77778ecc5) causes a performance
regression because all the interrupts now happen on 1 physical CPU (or two
pCPUs, if one pCPU doesn't have enough vectors). When a guest has many PCI
devices, it may suffer from soft lockups if the workload is heavy, e.g.,
see https://lwn.net/ml/linux-kernel/20220804025104.15673-1-decui@microsoft.com/
Commit b4b77778ecc5 itself is good. The real issue is that the hypercall in
hv_irq_unmask() -> hv_arch_irq_unmask() ->
hv_do_hypercall(HVCALL_RETARGET_INTERRUPT...) only changes the target
virtual CPU rather than physical CPU; with b4b77778ecc5, the pCPU is
determined only once in hv_compose_msi_msg() where only vCPU0 is specified;
consequently the hypervisor only uses 1 target pCPU for all the interrupts.
Note: before b4b77778ecc5, the pCPU is determined twice, and when the pCPU
is determined the second time, the vCPU in the effective affinity mask is
used (i.e., it isn't always vCPU0), so the hypervisor chooses different
pCPU for each interrupt.
The hypercall will be fixed in future to update the pCPU as well, but
that will take quite a while, so let's restore the old behavior in
hv_compose_msi_msg(), i.e., don't reuse the existing IRTE allocation for
single-MSI and MSI-X; for multi-MSI, we choose the vCPU in a round-robin
manner for each PCI device, so the interrupts of different devices can
happen on different pCPUs, though the interrupts of each device happen on
some single pCPU.
The hypercall fix may not be backported to all old versions of Hyper-V, so
we want to have this guest side change forever (or at least till we're sure
the old affected versions of Hyper-V are no longer supported).
Fixes: b4b77778ecc5 ("PCI: hv: Reuse existing IRTE allocation in compose_msi_msg()")
Co-developed-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
Signed-off-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
Co-developed-by: Carl Vanderlip <quic_carlv@quicinc.com>
Signed-off-by: Carl Vanderlip <quic_carlv@quicinc.com>
Signed-off-by: Dexuan Cui <decui@microsoft.com>
Reviewed-by: Michael Kelley <mikelley@microsoft.com>
Link: https://lore.kernel.org/r/20221104222953.11356-1-decui@microsoft.com
Signed-off-by: Wei Liu <wei.liu@kernel.org>
2022-11-04 15:29:53 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2021-07-12 21:58:18 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2022-07-07 19:49:31 -05:00
|
|
|
|
2021-07-12 21:58:18 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
PCI: hv: Only reuse existing IRTE allocation for Multi-MSI
Jeffrey added Multi-MSI support to the pci-hyperv driver by the 4 patches:
08e61e861a0e ("PCI: hv: Fix multi-MSI to allow more than one MSI vector")
455880dfe292 ("PCI: hv: Fix hv_arch_irq_unmask() for multi-MSI")
b4b77778ecc5 ("PCI: hv: Reuse existing IRTE allocation in compose_msi_msg()")
a2bad844a67b ("PCI: hv: Fix interrupt mapping for multi-MSI")
It turns out that the third patch (b4b77778ecc5) causes a performance
regression because all the interrupts now happen on 1 physical CPU (or two
pCPUs, if one pCPU doesn't have enough vectors). When a guest has many PCI
devices, it may suffer from soft lockups if the workload is heavy, e.g.,
see https://lwn.net/ml/linux-kernel/20220804025104.15673-1-decui@microsoft.com/
Commit b4b77778ecc5 itself is good. The real issue is that the hypercall in
hv_irq_unmask() -> hv_arch_irq_unmask() ->
hv_do_hypercall(HVCALL_RETARGET_INTERRUPT...) only changes the target
virtual CPU rather than physical CPU; with b4b77778ecc5, the pCPU is
determined only once in hv_compose_msi_msg() where only vCPU0 is specified;
consequently the hypervisor only uses 1 target pCPU for all the interrupts.
Note: before b4b77778ecc5, the pCPU is determined twice, and when the pCPU
is determined the second time, the vCPU in the effective affinity mask is
used (i.e., it isn't always vCPU0), so the hypervisor chooses different
pCPU for each interrupt.
The hypercall will be fixed in future to update the pCPU as well, but
that will take quite a while, so let's restore the old behavior in
hv_compose_msi_msg(), i.e., don't reuse the existing IRTE allocation for
single-MSI and MSI-X; for multi-MSI, we choose the vCPU in a round-robin
manner for each PCI device, so the interrupts of different devices can
happen on different pCPUs, though the interrupts of each device happen on
some single pCPU.
The hypercall fix may not be backported to all old versions of Hyper-V, so
we want to have this guest side change forever (or at least till we're sure
the old affected versions of Hyper-V are no longer supported).
Fixes: b4b77778ecc5 ("PCI: hv: Reuse existing IRTE allocation in compose_msi_msg()")
Co-developed-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
Signed-off-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
Co-developed-by: Carl Vanderlip <quic_carlv@quicinc.com>
Signed-off-by: Carl Vanderlip <quic_carlv@quicinc.com>
Signed-off-by: Dexuan Cui <decui@microsoft.com>
Reviewed-by: Michael Kelley <mikelley@microsoft.com>
Link: https://lore.kernel.org/r/20221104222953.11356-1-decui@microsoft.com
Signed-off-by: Wei Liu <wei.liu@kernel.org>
2022-11-04 15:29:53 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2017-05-24 13:41:28 -07:00
|
|
|
|
PCI: hv: Only reuse existing IRTE allocation for Multi-MSI
Jeffrey added Multi-MSI support to the pci-hyperv driver by the 4 patches:
08e61e861a0e ("PCI: hv: Fix multi-MSI to allow more than one MSI vector")
455880dfe292 ("PCI: hv: Fix hv_arch_irq_unmask() for multi-MSI")
b4b77778ecc5 ("PCI: hv: Reuse existing IRTE allocation in compose_msi_msg()")
a2bad844a67b ("PCI: hv: Fix interrupt mapping for multi-MSI")
It turns out that the third patch (b4b77778ecc5) causes a performance
regression because all the interrupts now happen on 1 physical CPU (or two
pCPUs, if one pCPU doesn't have enough vectors). When a guest has many PCI
devices, it may suffer from soft lockups if the workload is heavy, e.g.,
see https://lwn.net/ml/linux-kernel/20220804025104.15673-1-decui@microsoft.com/
Commit b4b77778ecc5 itself is good. The real issue is that the hypercall in
hv_irq_unmask() -> hv_arch_irq_unmask() ->
hv_do_hypercall(HVCALL_RETARGET_INTERRUPT...) only changes the target
virtual CPU rather than physical CPU; with b4b77778ecc5, the pCPU is
determined only once in hv_compose_msi_msg() where only vCPU0 is specified;
consequently the hypervisor only uses 1 target pCPU for all the interrupts.
Note: before b4b77778ecc5, the pCPU is determined twice, and when the pCPU
is determined the second time, the vCPU in the effective affinity mask is
used (i.e., it isn't always vCPU0), so the hypervisor chooses different
pCPU for each interrupt.
The hypercall will be fixed in future to update the pCPU as well, but
that will take quite a while, so let's restore the old behavior in
hv_compose_msi_msg(), i.e., don't reuse the existing IRTE allocation for
single-MSI and MSI-X; for multi-MSI, we choose the vCPU in a round-robin
manner for each PCI device, so the interrupts of different devices can
happen on different pCPUs, though the interrupts of each device happen on
some single pCPU.
The hypercall fix may not be backported to all old versions of Hyper-V, so
we want to have this guest side change forever (or at least till we're sure
the old affected versions of Hyper-V are no longer supported).
Fixes: b4b77778ecc5 ("PCI: hv: Reuse existing IRTE allocation in compose_msi_msg()")
Co-developed-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
Signed-off-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
Co-developed-by: Carl Vanderlip <quic_carlv@quicinc.com>
Signed-off-by: Carl Vanderlip <quic_carlv@quicinc.com>
Signed-off-by: Dexuan Cui <decui@microsoft.com>
Reviewed-by: Michael Kelley <mikelley@microsoft.com>
Link: https://lore.kernel.org/r/20221104222953.11356-1-decui@microsoft.com
Signed-off-by: Wei Liu <wei.liu@kernel.org>
2022-11-04 15:29:53 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2017-05-24 13:41:28 -07:00
|
|
|
|
|
|
|
|
|
PCI: hv: Only reuse existing IRTE allocation for Multi-MSI
Jeffrey added Multi-MSI support to the pci-hyperv driver by the 4 patches:
08e61e861a0e ("PCI: hv: Fix multi-MSI to allow more than one MSI vector")
455880dfe292 ("PCI: hv: Fix hv_arch_irq_unmask() for multi-MSI")
b4b77778ecc5 ("PCI: hv: Reuse existing IRTE allocation in compose_msi_msg()")
a2bad844a67b ("PCI: hv: Fix interrupt mapping for multi-MSI")
It turns out that the third patch (b4b77778ecc5) causes a performance
regression because all the interrupts now happen on 1 physical CPU (or two
pCPUs, if one pCPU doesn't have enough vectors). When a guest has many PCI
devices, it may suffer from soft lockups if the workload is heavy, e.g.,
see https://lwn.net/ml/linux-kernel/20220804025104.15673-1-decui@microsoft.com/
Commit b4b77778ecc5 itself is good. The real issue is that the hypercall in
hv_irq_unmask() -> hv_arch_irq_unmask() ->
hv_do_hypercall(HVCALL_RETARGET_INTERRUPT...) only changes the target
virtual CPU rather than physical CPU; with b4b77778ecc5, the pCPU is
determined only once in hv_compose_msi_msg() where only vCPU0 is specified;
consequently the hypervisor only uses 1 target pCPU for all the interrupts.
Note: before b4b77778ecc5, the pCPU is determined twice, and when the pCPU
is determined the second time, the vCPU in the effective affinity mask is
used (i.e., it isn't always vCPU0), so the hypervisor chooses different
pCPU for each interrupt.
The hypercall will be fixed in future to update the pCPU as well, but
that will take quite a while, so let's restore the old behavior in
hv_compose_msi_msg(), i.e., don't reuse the existing IRTE allocation for
single-MSI and MSI-X; for multi-MSI, we choose the vCPU in a round-robin
manner for each PCI device, so the interrupts of different devices can
happen on different pCPUs, though the interrupts of each device happen on
some single pCPU.
The hypercall fix may not be backported to all old versions of Hyper-V, so
we want to have this guest side change forever (or at least till we're sure
the old affected versions of Hyper-V are no longer supported).
Fixes: b4b77778ecc5 ("PCI: hv: Reuse existing IRTE allocation in compose_msi_msg()")
Co-developed-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
Signed-off-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
Co-developed-by: Carl Vanderlip <quic_carlv@quicinc.com>
Signed-off-by: Carl Vanderlip <quic_carlv@quicinc.com>
Signed-off-by: Dexuan Cui <decui@microsoft.com>
Reviewed-by: Michael Kelley <mikelley@microsoft.com>
Link: https://lore.kernel.org/r/20221104222953.11356-1-decui@microsoft.com
Signed-off-by: Wei Liu <wei.liu@kernel.org>
2022-11-04 15:29:53 -07:00
|
|
|
|
|
|
|
|
|
2025-01-28 11:46:41 -05:00
|
|
|
|
PCI: hv: Only reuse existing IRTE allocation for Multi-MSI
Jeffrey added Multi-MSI support to the pci-hyperv driver by the 4 patches:
08e61e861a0e ("PCI: hv: Fix multi-MSI to allow more than one MSI vector")
455880dfe292 ("PCI: hv: Fix hv_arch_irq_unmask() for multi-MSI")
b4b77778ecc5 ("PCI: hv: Reuse existing IRTE allocation in compose_msi_msg()")
a2bad844a67b ("PCI: hv: Fix interrupt mapping for multi-MSI")
It turns out that the third patch (b4b77778ecc5) causes a performance
regression because all the interrupts now happen on 1 physical CPU (or two
pCPUs, if one pCPU doesn't have enough vectors). When a guest has many PCI
devices, it may suffer from soft lockups if the workload is heavy, e.g.,
see https://lwn.net/ml/linux-kernel/20220804025104.15673-1-decui@microsoft.com/
Commit b4b77778ecc5 itself is good. The real issue is that the hypercall in
hv_irq_unmask() -> hv_arch_irq_unmask() ->
hv_do_hypercall(HVCALL_RETARGET_INTERRUPT...) only changes the target
virtual CPU rather than physical CPU; with b4b77778ecc5, the pCPU is
determined only once in hv_compose_msi_msg() where only vCPU0 is specified;
consequently the hypervisor only uses 1 target pCPU for all the interrupts.
Note: before b4b77778ecc5, the pCPU is determined twice, and when the pCPU
is determined the second time, the vCPU in the effective affinity mask is
used (i.e., it isn't always vCPU0), so the hypervisor chooses different
pCPU for each interrupt.
The hypercall will be fixed in future to update the pCPU as well, but
that will take quite a while, so let's restore the old behavior in
hv_compose_msi_msg(), i.e., don't reuse the existing IRTE allocation for
single-MSI and MSI-X; for multi-MSI, we choose the vCPU in a round-robin
manner for each PCI device, so the interrupts of different devices can
happen on different pCPUs, though the interrupts of each device happen on
some single pCPU.
The hypercall fix may not be backported to all old versions of Hyper-V, so
we want to have this guest side change forever (or at least till we're sure
the old affected versions of Hyper-V are no longer supported).
Fixes: b4b77778ecc5 ("PCI: hv: Reuse existing IRTE allocation in compose_msi_msg()")
Co-developed-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
Signed-off-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
Co-developed-by: Carl Vanderlip <quic_carlv@quicinc.com>
Signed-off-by: Carl Vanderlip <quic_carlv@quicinc.com>
Signed-off-by: Dexuan Cui <decui@microsoft.com>
Reviewed-by: Michael Kelley <mikelley@microsoft.com>
Link: https://lore.kernel.org/r/20221104222953.11356-1-decui@microsoft.com
Signed-off-by: Wei Liu <wei.liu@kernel.org>
2022-11-04 15:29:53 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2017-05-24 13:41:28 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2022-05-11 09:23:19 -06:00
|
|
|
|
2022-01-05 11:32:35 -08:00
|
|
|
|
2021-07-12 21:58:18 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2017-05-24 13:41:28 -07:00
|
|
|
|
2021-07-12 21:58:18 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
PCI: hv: Only reuse existing IRTE allocation for Multi-MSI
Jeffrey added Multi-MSI support to the pci-hyperv driver by the 4 patches:
08e61e861a0e ("PCI: hv: Fix multi-MSI to allow more than one MSI vector")
455880dfe292 ("PCI: hv: Fix hv_arch_irq_unmask() for multi-MSI")
b4b77778ecc5 ("PCI: hv: Reuse existing IRTE allocation in compose_msi_msg()")
a2bad844a67b ("PCI: hv: Fix interrupt mapping for multi-MSI")
It turns out that the third patch (b4b77778ecc5) causes a performance
regression because all the interrupts now happen on 1 physical CPU (or two
pCPUs, if one pCPU doesn't have enough vectors). When a guest has many PCI
devices, it may suffer from soft lockups if the workload is heavy, e.g.,
see https://lwn.net/ml/linux-kernel/20220804025104.15673-1-decui@microsoft.com/
Commit b4b77778ecc5 itself is good. The real issue is that the hypercall in
hv_irq_unmask() -> hv_arch_irq_unmask() ->
hv_do_hypercall(HVCALL_RETARGET_INTERRUPT...) only changes the target
virtual CPU rather than physical CPU; with b4b77778ecc5, the pCPU is
determined only once in hv_compose_msi_msg() where only vCPU0 is specified;
consequently the hypervisor only uses 1 target pCPU for all the interrupts.
Note: before b4b77778ecc5, the pCPU is determined twice, and when the pCPU
is determined the second time, the vCPU in the effective affinity mask is
used (i.e., it isn't always vCPU0), so the hypervisor chooses different
pCPU for each interrupt.
The hypercall will be fixed in future to update the pCPU as well, but
that will take quite a while, so let's restore the old behavior in
hv_compose_msi_msg(), i.e., don't reuse the existing IRTE allocation for
single-MSI and MSI-X; for multi-MSI, we choose the vCPU in a round-robin
manner for each PCI device, so the interrupts of different devices can
happen on different pCPUs, though the interrupts of each device happen on
some single pCPU.
The hypercall fix may not be backported to all old versions of Hyper-V, so
we want to have this guest side change forever (or at least till we're sure
the old affected versions of Hyper-V are no longer supported).
Fixes: b4b77778ecc5 ("PCI: hv: Reuse existing IRTE allocation in compose_msi_msg()")
Co-developed-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
Signed-off-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
Co-developed-by: Carl Vanderlip <quic_carlv@quicinc.com>
Signed-off-by: Carl Vanderlip <quic_carlv@quicinc.com>
Signed-off-by: Dexuan Cui <decui@microsoft.com>
Reviewed-by: Michael Kelley <mikelley@microsoft.com>
Link: https://lore.kernel.org/r/20221104222953.11356-1-decui@microsoft.com
Signed-off-by: Wei Liu <wei.liu@kernel.org>
2022-11-04 15:29:53 -07:00
|
|
|
|
2022-10-27 13:52:56 -07:00
|
|
|
|
2021-07-12 21:58:18 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2022-05-11 09:23:19 -06:00
|
|
|
|
2022-01-05 11:32:35 -08:00
|
|
|
|
2017-05-24 13:41:28 -07:00
|
|
|
|
2017-08-02 18:09:18 +02:00
|
|
|
|
2017-05-24 13:41:28 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2020-04-06 02:15:10 +02:00
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2022-07-01 15:00:55 -05:00
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
2022-05-11 09:23:19 -06:00
|
|
|
|
2022-10-27 13:52:56 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
2017-05-24 13:41:28 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2021-07-12 21:58:18 +00:00
|
|
|
|
2017-05-24 13:41:28 -07:00
|
|
|
|
|
|
|
|
|
PCI: hv: Only reuse existing IRTE allocation for Multi-MSI
Jeffrey added Multi-MSI support to the pci-hyperv driver by the 4 patches:
08e61e861a0e ("PCI: hv: Fix multi-MSI to allow more than one MSI vector")
455880dfe292 ("PCI: hv: Fix hv_arch_irq_unmask() for multi-MSI")
b4b77778ecc5 ("PCI: hv: Reuse existing IRTE allocation in compose_msi_msg()")
a2bad844a67b ("PCI: hv: Fix interrupt mapping for multi-MSI")
It turns out that the third patch (b4b77778ecc5) causes a performance
regression because all the interrupts now happen on 1 physical CPU (or two
pCPUs, if one pCPU doesn't have enough vectors). When a guest has many PCI
devices, it may suffer from soft lockups if the workload is heavy, e.g.,
see https://lwn.net/ml/linux-kernel/20220804025104.15673-1-decui@microsoft.com/
Commit b4b77778ecc5 itself is good. The real issue is that the hypercall in
hv_irq_unmask() -> hv_arch_irq_unmask() ->
hv_do_hypercall(HVCALL_RETARGET_INTERRUPT...) only changes the target
virtual CPU rather than physical CPU; with b4b77778ecc5, the pCPU is
determined only once in hv_compose_msi_msg() where only vCPU0 is specified;
consequently the hypervisor only uses 1 target pCPU for all the interrupts.
Note: before b4b77778ecc5, the pCPU is determined twice, and when the pCPU
is determined the second time, the vCPU in the effective affinity mask is
used (i.e., it isn't always vCPU0), so the hypervisor chooses different
pCPU for each interrupt.
The hypercall will be fixed in future to update the pCPU as well, but
that will take quite a while, so let's restore the old behavior in
hv_compose_msi_msg(), i.e., don't reuse the existing IRTE allocation for
single-MSI and MSI-X; for multi-MSI, we choose the vCPU in a round-robin
manner for each PCI device, so the interrupts of different devices can
happen on different pCPUs, though the interrupts of each device happen on
some single pCPU.
The hypercall fix may not be backported to all old versions of Hyper-V, so
we want to have this guest side change forever (or at least till we're sure
the old affected versions of Hyper-V are no longer supported).
Fixes: b4b77778ecc5 ("PCI: hv: Reuse existing IRTE allocation in compose_msi_msg()")
Co-developed-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
Signed-off-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
Co-developed-by: Carl Vanderlip <quic_carlv@quicinc.com>
Signed-off-by: Carl Vanderlip <quic_carlv@quicinc.com>
Signed-off-by: Dexuan Cui <decui@microsoft.com>
Reviewed-by: Michael Kelley <mikelley@microsoft.com>
Link: https://lore.kernel.org/r/20221104222953.11356-1-decui@microsoft.com
Signed-off-by: Wei Liu <wei.liu@kernel.org>
2022-11-04 15:29:53 -07:00
|
|
|
|
2022-04-19 14:23:25 +02:00
|
|
|
|
2017-05-24 13:41:28 -07:00
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
PCI: hv: Only reuse existing IRTE allocation for Multi-MSI
Jeffrey added Multi-MSI support to the pci-hyperv driver by the 4 patches:
08e61e861a0e ("PCI: hv: Fix multi-MSI to allow more than one MSI vector")
455880dfe292 ("PCI: hv: Fix hv_arch_irq_unmask() for multi-MSI")
b4b77778ecc5 ("PCI: hv: Reuse existing IRTE allocation in compose_msi_msg()")
a2bad844a67b ("PCI: hv: Fix interrupt mapping for multi-MSI")
It turns out that the third patch (b4b77778ecc5) causes a performance
regression because all the interrupts now happen on 1 physical CPU (or two
pCPUs, if one pCPU doesn't have enough vectors). When a guest has many PCI
devices, it may suffer from soft lockups if the workload is heavy, e.g.,
see https://lwn.net/ml/linux-kernel/20220804025104.15673-1-decui@microsoft.com/
Commit b4b77778ecc5 itself is good. The real issue is that the hypercall in
hv_irq_unmask() -> hv_arch_irq_unmask() ->
hv_do_hypercall(HVCALL_RETARGET_INTERRUPT...) only changes the target
virtual CPU rather than physical CPU; with b4b77778ecc5, the pCPU is
determined only once in hv_compose_msi_msg() where only vCPU0 is specified;
consequently the hypervisor only uses 1 target pCPU for all the interrupts.
Note: before b4b77778ecc5, the pCPU is determined twice, and when the pCPU
is determined the second time, the vCPU in the effective affinity mask is
used (i.e., it isn't always vCPU0), so the hypervisor chooses different
pCPU for each interrupt.
The hypercall will be fixed in future to update the pCPU as well, but
that will take quite a while, so let's restore the old behavior in
hv_compose_msi_msg(), i.e., don't reuse the existing IRTE allocation for
single-MSI and MSI-X; for multi-MSI, we choose the vCPU in a round-robin
manner for each PCI device, so the interrupts of different devices can
happen on different pCPUs, though the interrupts of each device happen on
some single pCPU.
The hypercall fix may not be backported to all old versions of Hyper-V, so
we want to have this guest side change forever (or at least till we're sure
the old affected versions of Hyper-V are no longer supported).
Fixes: b4b77778ecc5 ("PCI: hv: Reuse existing IRTE allocation in compose_msi_msg()")
Co-developed-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
Signed-off-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
Co-developed-by: Carl Vanderlip <quic_carlv@quicinc.com>
Signed-off-by: Carl Vanderlip <quic_carlv@quicinc.com>
Signed-off-by: Dexuan Cui <decui@microsoft.com>
Reviewed-by: Michael Kelley <mikelley@microsoft.com>
Link: https://lore.kernel.org/r/20221104222953.11356-1-decui@microsoft.com
Signed-off-by: Wei Liu <wei.liu@kernel.org>
2022-11-04 15:29:53 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
2022-05-11 09:23:02 -06:00
|
|
|
|
PCI: hv: Only reuse existing IRTE allocation for Multi-MSI
Jeffrey added Multi-MSI support to the pci-hyperv driver by the 4 patches:
08e61e861a0e ("PCI: hv: Fix multi-MSI to allow more than one MSI vector")
455880dfe292 ("PCI: hv: Fix hv_arch_irq_unmask() for multi-MSI")
b4b77778ecc5 ("PCI: hv: Reuse existing IRTE allocation in compose_msi_msg()")
a2bad844a67b ("PCI: hv: Fix interrupt mapping for multi-MSI")
It turns out that the third patch (b4b77778ecc5) causes a performance
regression because all the interrupts now happen on 1 physical CPU (or two
pCPUs, if one pCPU doesn't have enough vectors). When a guest has many PCI
devices, it may suffer from soft lockups if the workload is heavy, e.g.,
see https://lwn.net/ml/linux-kernel/20220804025104.15673-1-decui@microsoft.com/
Commit b4b77778ecc5 itself is good. The real issue is that the hypercall in
hv_irq_unmask() -> hv_arch_irq_unmask() ->
hv_do_hypercall(HVCALL_RETARGET_INTERRUPT...) only changes the target
virtual CPU rather than physical CPU; with b4b77778ecc5, the pCPU is
determined only once in hv_compose_msi_msg() where only vCPU0 is specified;
consequently the hypervisor only uses 1 target pCPU for all the interrupts.
Note: before b4b77778ecc5, the pCPU is determined twice, and when the pCPU
is determined the second time, the vCPU in the effective affinity mask is
used (i.e., it isn't always vCPU0), so the hypervisor chooses different
pCPU for each interrupt.
The hypercall will be fixed in future to update the pCPU as well, but
that will take quite a while, so let's restore the old behavior in
hv_compose_msi_msg(), i.e., don't reuse the existing IRTE allocation for
single-MSI and MSI-X; for multi-MSI, we choose the vCPU in a round-robin
manner for each PCI device, so the interrupts of different devices can
happen on different pCPUs, though the interrupts of each device happen on
some single pCPU.
The hypercall fix may not be backported to all old versions of Hyper-V, so
we want to have this guest side change forever (or at least till we're sure
the old affected versions of Hyper-V are no longer supported).
Fixes: b4b77778ecc5 ("PCI: hv: Reuse existing IRTE allocation in compose_msi_msg()")
Co-developed-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
Signed-off-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
Co-developed-by: Carl Vanderlip <quic_carlv@quicinc.com>
Signed-off-by: Carl Vanderlip <quic_carlv@quicinc.com>
Signed-off-by: Dexuan Cui <decui@microsoft.com>
Reviewed-by: Michael Kelley <mikelley@microsoft.com>
Link: https://lore.kernel.org/r/20221104222953.11356-1-decui@microsoft.com
Signed-off-by: Wei Liu <wei.liu@kernel.org>
2022-11-04 15:29:53 -07:00
|
|
|
|
2022-05-11 09:23:02 -06:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2022-05-11 09:23:19 -06:00
|
|
|
|
2017-11-01 20:30:53 +00:00
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
2020-04-06 02:15:10 +02:00
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
PCI: hv: Only reuse existing IRTE allocation for Multi-MSI
Jeffrey added Multi-MSI support to the pci-hyperv driver by the 4 patches:
08e61e861a0e ("PCI: hv: Fix multi-MSI to allow more than one MSI vector")
455880dfe292 ("PCI: hv: Fix hv_arch_irq_unmask() for multi-MSI")
b4b77778ecc5 ("PCI: hv: Reuse existing IRTE allocation in compose_msi_msg()")
a2bad844a67b ("PCI: hv: Fix interrupt mapping for multi-MSI")
It turns out that the third patch (b4b77778ecc5) causes a performance
regression because all the interrupts now happen on 1 physical CPU (or two
pCPUs, if one pCPU doesn't have enough vectors). When a guest has many PCI
devices, it may suffer from soft lockups if the workload is heavy, e.g.,
see https://lwn.net/ml/linux-kernel/20220804025104.15673-1-decui@microsoft.com/
Commit b4b77778ecc5 itself is good. The real issue is that the hypercall in
hv_irq_unmask() -> hv_arch_irq_unmask() ->
hv_do_hypercall(HVCALL_RETARGET_INTERRUPT...) only changes the target
virtual CPU rather than physical CPU; with b4b77778ecc5, the pCPU is
determined only once in hv_compose_msi_msg() where only vCPU0 is specified;
consequently the hypervisor only uses 1 target pCPU for all the interrupts.
Note: before b4b77778ecc5, the pCPU is determined twice, and when the pCPU
is determined the second time, the vCPU in the effective affinity mask is
used (i.e., it isn't always vCPU0), so the hypervisor chooses different
pCPU for each interrupt.
The hypercall will be fixed in future to update the pCPU as well, but
that will take quite a while, so let's restore the old behavior in
hv_compose_msi_msg(), i.e., don't reuse the existing IRTE allocation for
single-MSI and MSI-X; for multi-MSI, we choose the vCPU in a round-robin
manner for each PCI device, so the interrupts of different devices can
happen on different pCPUs, though the interrupts of each device happen on
some single pCPU.
The hypercall fix may not be backported to all old versions of Hyper-V, so
we want to have this guest side change forever (or at least till we're sure
the old affected versions of Hyper-V are no longer supported).
Fixes: b4b77778ecc5 ("PCI: hv: Reuse existing IRTE allocation in compose_msi_msg()")
Co-developed-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
Signed-off-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
Co-developed-by: Carl Vanderlip <quic_carlv@quicinc.com>
Signed-off-by: Carl Vanderlip <quic_carlv@quicinc.com>
Signed-off-by: Dexuan Cui <decui@microsoft.com>
Reviewed-by: Michael Kelley <mikelley@microsoft.com>
Link: https://lore.kernel.org/r/20221104222953.11356-1-decui@microsoft.com
Signed-off-by: Wei Liu <wei.liu@kernel.org>
2022-11-04 15:29:53 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
treewide: Replace kmalloc with kmalloc_obj for non-scalar types
This is the result of running the Coccinelle script from
scripts/coccinelle/api/kmalloc_objs.cocci. The script is designed to
avoid scalar types (which need careful case-by-case checking), and
instead replace kmalloc-family calls that allocate struct or union
object instances:
Single allocations: kmalloc(sizeof(TYPE), ...)
are replaced with: kmalloc_obj(TYPE, ...)
Array allocations: kmalloc_array(COUNT, sizeof(TYPE), ...)
are replaced with: kmalloc_objs(TYPE, COUNT, ...)
Flex array allocations: kmalloc(struct_size(PTR, FAM, COUNT), ...)
are replaced with: kmalloc_flex(*PTR, FAM, COUNT, ...)
(where TYPE may also be *VAR)
The resulting allocations no longer return "void *", instead returning
"TYPE *".
Signed-off-by: Kees Cook <kees@kernel.org>
2026-02-20 23:49:23 -08:00
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
PCI: hv: Only reuse existing IRTE allocation for Multi-MSI
Jeffrey added Multi-MSI support to the pci-hyperv driver by the 4 patches:
08e61e861a0e ("PCI: hv: Fix multi-MSI to allow more than one MSI vector")
455880dfe292 ("PCI: hv: Fix hv_arch_irq_unmask() for multi-MSI")
b4b77778ecc5 ("PCI: hv: Reuse existing IRTE allocation in compose_msi_msg()")
a2bad844a67b ("PCI: hv: Fix interrupt mapping for multi-MSI")
It turns out that the third patch (b4b77778ecc5) causes a performance
regression because all the interrupts now happen on 1 physical CPU (or two
pCPUs, if one pCPU doesn't have enough vectors). When a guest has many PCI
devices, it may suffer from soft lockups if the workload is heavy, e.g.,
see https://lwn.net/ml/linux-kernel/20220804025104.15673-1-decui@microsoft.com/
Commit b4b77778ecc5 itself is good. The real issue is that the hypercall in
hv_irq_unmask() -> hv_arch_irq_unmask() ->
hv_do_hypercall(HVCALL_RETARGET_INTERRUPT...) only changes the target
virtual CPU rather than physical CPU; with b4b77778ecc5, the pCPU is
determined only once in hv_compose_msi_msg() where only vCPU0 is specified;
consequently the hypervisor only uses 1 target pCPU for all the interrupts.
Note: before b4b77778ecc5, the pCPU is determined twice, and when the pCPU
is determined the second time, the vCPU in the effective affinity mask is
used (i.e., it isn't always vCPU0), so the hypervisor chooses different
pCPU for each interrupt.
The hypercall will be fixed in future to update the pCPU as well, but
that will take quite a while, so let's restore the old behavior in
hv_compose_msi_msg(), i.e., don't reuse the existing IRTE allocation for
single-MSI and MSI-X; for multi-MSI, we choose the vCPU in a round-robin
manner for each PCI device, so the interrupts of different devices can
happen on different pCPUs, though the interrupts of each device happen on
some single pCPU.
The hypercall fix may not be backported to all old versions of Hyper-V, so
we want to have this guest side change forever (or at least till we're sure
the old affected versions of Hyper-V are no longer supported).
Fixes: b4b77778ecc5 ("PCI: hv: Reuse existing IRTE allocation in compose_msi_msg()")
Co-developed-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
Signed-off-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
Co-developed-by: Carl Vanderlip <quic_carlv@quicinc.com>
Signed-off-by: Carl Vanderlip <quic_carlv@quicinc.com>
Signed-off-by: Dexuan Cui <decui@microsoft.com>
Reviewed-by: Michael Kelley <mikelley@microsoft.com>
Link: https://lore.kernel.org/r/20221104222953.11356-1-decui@microsoft.com
Signed-off-by: Wei Liu <wei.liu@kernel.org>
2022-11-04 15:29:53 -07:00
|
|
|
|
2022-05-11 09:23:19 -06:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
PCI: hv: Only reuse existing IRTE allocation for Multi-MSI
Jeffrey added Multi-MSI support to the pci-hyperv driver by the 4 patches:
08e61e861a0e ("PCI: hv: Fix multi-MSI to allow more than one MSI vector")
455880dfe292 ("PCI: hv: Fix hv_arch_irq_unmask() for multi-MSI")
b4b77778ecc5 ("PCI: hv: Reuse existing IRTE allocation in compose_msi_msg()")
a2bad844a67b ("PCI: hv: Fix interrupt mapping for multi-MSI")
It turns out that the third patch (b4b77778ecc5) causes a performance
regression because all the interrupts now happen on 1 physical CPU (or two
pCPUs, if one pCPU doesn't have enough vectors). When a guest has many PCI
devices, it may suffer from soft lockups if the workload is heavy, e.g.,
see https://lwn.net/ml/linux-kernel/20220804025104.15673-1-decui@microsoft.com/
Commit b4b77778ecc5 itself is good. The real issue is that the hypercall in
hv_irq_unmask() -> hv_arch_irq_unmask() ->
hv_do_hypercall(HVCALL_RETARGET_INTERRUPT...) only changes the target
virtual CPU rather than physical CPU; with b4b77778ecc5, the pCPU is
determined only once in hv_compose_msi_msg() where only vCPU0 is specified;
consequently the hypervisor only uses 1 target pCPU for all the interrupts.
Note: before b4b77778ecc5, the pCPU is determined twice, and when the pCPU
is determined the second time, the vCPU in the effective affinity mask is
used (i.e., it isn't always vCPU0), so the hypervisor chooses different
pCPU for each interrupt.
The hypercall will be fixed in future to update the pCPU as well, but
that will take quite a while, so let's restore the old behavior in
hv_compose_msi_msg(), i.e., don't reuse the existing IRTE allocation for
single-MSI and MSI-X; for multi-MSI, we choose the vCPU in a round-robin
manner for each PCI device, so the interrupts of different devices can
happen on different pCPUs, though the interrupts of each device happen on
some single pCPU.
The hypercall fix may not be backported to all old versions of Hyper-V, so
we want to have this guest side change forever (or at least till we're sure
the old affected versions of Hyper-V are no longer supported).
Fixes: b4b77778ecc5 ("PCI: hv: Reuse existing IRTE allocation in compose_msi_msg()")
Co-developed-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
Signed-off-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
Co-developed-by: Carl Vanderlip <quic_carlv@quicinc.com>
Signed-off-by: Carl Vanderlip <quic_carlv@quicinc.com>
Signed-off-by: Dexuan Cui <decui@microsoft.com>
Reviewed-by: Michael Kelley <mikelley@microsoft.com>
Link: https://lore.kernel.org/r/20221104222953.11356-1-decui@microsoft.com
Signed-off-by: Wei Liu <wei.liu@kernel.org>
2022-11-04 15:29:53 -07:00
|
|
|
|
2022-05-11 09:23:19 -06:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
PCI: hv: Only reuse existing IRTE allocation for Multi-MSI
Jeffrey added Multi-MSI support to the pci-hyperv driver by the 4 patches:
08e61e861a0e ("PCI: hv: Fix multi-MSI to allow more than one MSI vector")
455880dfe292 ("PCI: hv: Fix hv_arch_irq_unmask() for multi-MSI")
b4b77778ecc5 ("PCI: hv: Reuse existing IRTE allocation in compose_msi_msg()")
a2bad844a67b ("PCI: hv: Fix interrupt mapping for multi-MSI")
It turns out that the third patch (b4b77778ecc5) causes a performance
regression because all the interrupts now happen on 1 physical CPU (or two
pCPUs, if one pCPU doesn't have enough vectors). When a guest has many PCI
devices, it may suffer from soft lockups if the workload is heavy, e.g.,
see https://lwn.net/ml/linux-kernel/20220804025104.15673-1-decui@microsoft.com/
Commit b4b77778ecc5 itself is good. The real issue is that the hypercall in
hv_irq_unmask() -> hv_arch_irq_unmask() ->
hv_do_hypercall(HVCALL_RETARGET_INTERRUPT...) only changes the target
virtual CPU rather than physical CPU; with b4b77778ecc5, the pCPU is
determined only once in hv_compose_msi_msg() where only vCPU0 is specified;
consequently the hypervisor only uses 1 target pCPU for all the interrupts.
Note: before b4b77778ecc5, the pCPU is determined twice, and when the pCPU
is determined the second time, the vCPU in the effective affinity mask is
used (i.e., it isn't always vCPU0), so the hypervisor chooses different
pCPU for each interrupt.
The hypercall will be fixed in future to update the pCPU as well, but
that will take quite a while, so let's restore the old behavior in
hv_compose_msi_msg(), i.e., don't reuse the existing IRTE allocation for
single-MSI and MSI-X; for multi-MSI, we choose the vCPU in a round-robin
manner for each PCI device, so the interrupts of different devices can
happen on different pCPUs, though the interrupts of each device happen on
some single pCPU.
The hypercall fix may not be backported to all old versions of Hyper-V, so
we want to have this guest side change forever (or at least till we're sure
the old affected versions of Hyper-V are no longer supported).
Fixes: b4b77778ecc5 ("PCI: hv: Reuse existing IRTE allocation in compose_msi_msg()")
Co-developed-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
Signed-off-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
Co-developed-by: Carl Vanderlip <quic_carlv@quicinc.com>
Signed-off-by: Carl Vanderlip <quic_carlv@quicinc.com>
Signed-off-by: Dexuan Cui <decui@microsoft.com>
Reviewed-by: Michael Kelley <mikelley@microsoft.com>
Link: https://lore.kernel.org/r/20221104222953.11356-1-decui@microsoft.com
Signed-off-by: Wei Liu <wei.liu@kernel.org>
2022-11-04 15:29:53 -07:00
|
|
|
|
2022-05-11 09:23:19 -06:00
|
|
|
|
|
|
|
|
|
2022-10-27 13:52:56 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
2017-05-24 13:41:28 -07:00
|
|
|
|
|
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
2019-11-24 21:33:53 -08:00
|
|
|
|
2017-05-24 13:41:28 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2022-10-27 13:52:56 -07:00
|
|
|
|
2022-05-11 09:23:19 -06:00
|
|
|
|
2017-05-24 13:41:28 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2020-02-25 21:06:08 -08:00
|
|
|
|
2017-05-24 13:41:28 -07:00
|
|
|
|
PCI: hv: Only reuse existing IRTE allocation for Multi-MSI
Jeffrey added Multi-MSI support to the pci-hyperv driver by the 4 patches:
08e61e861a0e ("PCI: hv: Fix multi-MSI to allow more than one MSI vector")
455880dfe292 ("PCI: hv: Fix hv_arch_irq_unmask() for multi-MSI")
b4b77778ecc5 ("PCI: hv: Reuse existing IRTE allocation in compose_msi_msg()")
a2bad844a67b ("PCI: hv: Fix interrupt mapping for multi-MSI")
It turns out that the third patch (b4b77778ecc5) causes a performance
regression because all the interrupts now happen on 1 physical CPU (or two
pCPUs, if one pCPU doesn't have enough vectors). When a guest has many PCI
devices, it may suffer from soft lockups if the workload is heavy, e.g.,
see https://lwn.net/ml/linux-kernel/20220804025104.15673-1-decui@microsoft.com/
Commit b4b77778ecc5 itself is good. The real issue is that the hypercall in
hv_irq_unmask() -> hv_arch_irq_unmask() ->
hv_do_hypercall(HVCALL_RETARGET_INTERRUPT...) only changes the target
virtual CPU rather than physical CPU; with b4b77778ecc5, the pCPU is
determined only once in hv_compose_msi_msg() where only vCPU0 is specified;
consequently the hypervisor only uses 1 target pCPU for all the interrupts.
Note: before b4b77778ecc5, the pCPU is determined twice, and when the pCPU
is determined the second time, the vCPU in the effective affinity mask is
used (i.e., it isn't always vCPU0), so the hypervisor chooses different
pCPU for each interrupt.
The hypercall will be fixed in future to update the pCPU as well, but
that will take quite a while, so let's restore the old behavior in
hv_compose_msi_msg(), i.e., don't reuse the existing IRTE allocation for
single-MSI and MSI-X; for multi-MSI, we choose the vCPU in a round-robin
manner for each PCI device, so the interrupts of different devices can
happen on different pCPUs, though the interrupts of each device happen on
some single pCPU.
The hypercall fix may not be backported to all old versions of Hyper-V, so
we want to have this guest side change forever (or at least till we're sure
the old affected versions of Hyper-V are no longer supported).
Fixes: b4b77778ecc5 ("PCI: hv: Reuse existing IRTE allocation in compose_msi_msg()")
Co-developed-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
Signed-off-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
Co-developed-by: Carl Vanderlip <quic_carlv@quicinc.com>
Signed-off-by: Carl Vanderlip <quic_carlv@quicinc.com>
Signed-off-by: Dexuan Cui <decui@microsoft.com>
Reviewed-by: Michael Kelley <mikelley@microsoft.com>
Link: https://lore.kernel.org/r/20221104222953.11356-1-decui@microsoft.com
Signed-off-by: Wei Liu <wei.liu@kernel.org>
2022-11-04 15:29:53 -07:00
|
|
|
|
2017-05-24 13:41:28 -07:00
|
|
|
|
2022-10-27 13:52:56 -07:00
|
|
|
|
2022-05-11 09:23:19 -06:00
|
|
|
|
2017-05-24 13:41:28 -07:00
|
|
|
|
|
|
|
|
|
2021-07-12 21:58:18 +00:00
|
|
|
|
|
|
|
|
|
PCI: hv: Only reuse existing IRTE allocation for Multi-MSI
Jeffrey added Multi-MSI support to the pci-hyperv driver by the 4 patches:
08e61e861a0e ("PCI: hv: Fix multi-MSI to allow more than one MSI vector")
455880dfe292 ("PCI: hv: Fix hv_arch_irq_unmask() for multi-MSI")
b4b77778ecc5 ("PCI: hv: Reuse existing IRTE allocation in compose_msi_msg()")
a2bad844a67b ("PCI: hv: Fix interrupt mapping for multi-MSI")
It turns out that the third patch (b4b77778ecc5) causes a performance
regression because all the interrupts now happen on 1 physical CPU (or two
pCPUs, if one pCPU doesn't have enough vectors). When a guest has many PCI
devices, it may suffer from soft lockups if the workload is heavy, e.g.,
see https://lwn.net/ml/linux-kernel/20220804025104.15673-1-decui@microsoft.com/
Commit b4b77778ecc5 itself is good. The real issue is that the hypercall in
hv_irq_unmask() -> hv_arch_irq_unmask() ->
hv_do_hypercall(HVCALL_RETARGET_INTERRUPT...) only changes the target
virtual CPU rather than physical CPU; with b4b77778ecc5, the pCPU is
determined only once in hv_compose_msi_msg() where only vCPU0 is specified;
consequently the hypervisor only uses 1 target pCPU for all the interrupts.
Note: before b4b77778ecc5, the pCPU is determined twice, and when the pCPU
is determined the second time, the vCPU in the effective affinity mask is
used (i.e., it isn't always vCPU0), so the hypervisor chooses different
pCPU for each interrupt.
The hypercall will be fixed in future to update the pCPU as well, but
that will take quite a while, so let's restore the old behavior in
hv_compose_msi_msg(), i.e., don't reuse the existing IRTE allocation for
single-MSI and MSI-X; for multi-MSI, we choose the vCPU in a round-robin
manner for each PCI device, so the interrupts of different devices can
happen on different pCPUs, though the interrupts of each device happen on
some single pCPU.
The hypercall fix may not be backported to all old versions of Hyper-V, so
we want to have this guest side change forever (or at least till we're sure
the old affected versions of Hyper-V are no longer supported).
Fixes: b4b77778ecc5 ("PCI: hv: Reuse existing IRTE allocation in compose_msi_msg()")
Co-developed-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
Signed-off-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
Co-developed-by: Carl Vanderlip <quic_carlv@quicinc.com>
Signed-off-by: Carl Vanderlip <quic_carlv@quicinc.com>
Signed-off-by: Dexuan Cui <decui@microsoft.com>
Reviewed-by: Michael Kelley <mikelley@microsoft.com>
Link: https://lore.kernel.org/r/20221104222953.11356-1-decui@microsoft.com
Signed-off-by: Wei Liu <wei.liu@kernel.org>
2022-11-04 15:29:53 -07:00
|
|
|
|
2021-07-12 21:58:18 +00:00
|
|
|
|
2022-05-11 09:23:19 -06:00
|
|
|
|
|
|
|
|
|
2021-07-12 21:58:18 +00:00
|
|
|
|
|
|
|
|
|
2017-05-24 13:41:28 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
2022-04-19 14:23:25 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2017-05-24 13:41:28 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-08-23 04:48:11 +00:00
|
|
|
|
2017-05-24 13:41:28 -07:00
|
|
|
|
2016-08-23 04:48:11 +00:00
|
|
|
|
2020-04-06 02:15:10 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2021-03-09 09:42:15 +01:00
|
|
|
|
2020-04-06 02:15:10 +02:00
|
|
|
|
2017-07-31 16:48:29 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
PCI: hv: Fix 2 hang issues in hv_compose_msi_msg()
1. With the patch "x86/vector/msi: Switch to global reservation mode",
the recent v4.15 and newer kernels always hang for 1-vCPU Hyper-V VM
with SR-IOV. This is because when we reach hv_compose_msi_msg() by
request_irq() -> request_threaded_irq() ->__setup_irq()->irq_startup()
-> __irq_startup() -> irq_domain_activate_irq() -> ... ->
msi_domain_activate() -> ... -> hv_compose_msi_msg(), local irq is
disabled in __setup_irq().
Note: when we reach hv_compose_msi_msg() by another code path:
pci_enable_msix_range() -> ... -> irq_domain_activate_irq() -> ... ->
hv_compose_msi_msg(), local irq is not disabled.
hv_compose_msi_msg() depends on an interrupt from the host.
With interrupts disabled, a UP VM always hangs in the busy loop in
the function, because the interrupt callback hv_pci_onchannelcallback()
can not be called.
We can do nothing but work it around by polling the channel. This
is ugly, but we don't have any other choice.
2. If the host is ejecting the VF device before we reach
hv_compose_msi_msg(), in a UP VM, we can hang in hv_compose_msi_msg()
forever, because at this time the host doesn't respond to the
CREATE_INTERRUPT request. This issue exists the first day the
pci-hyperv driver appears in the kernel.
Luckily, this can also by worked around by polling the channel
for the PCI_EJECT message and hpdev->state, and by checking the
PCI vendor ID.
Note: actually the above 2 issues also happen to a SMP VM, if
"hbus->hdev->channel->target_cpu == smp_processor_id()" is true.
Fixes: 4900be83602b ("x86/vector/msi: Switch to global reservation mode")
Tested-by: Adrian Suhov <v-adsuho@microsoft.com>
Tested-by: Chris Valean <v-chvale@microsoft.com>
Signed-off-by: Dexuan Cui <decui@microsoft.com>
Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Reviewed-by: Michael Kelley <mikelley@microsoft.com>
Acked-by: Haiyang Zhang <haiyangz@microsoft.com>
Cc: <stable@vger.kernel.org>
Cc: Stephen Hemminger <sthemmin@microsoft.com>
Cc: K. Y. Srinivasan <kys@microsoft.com>
Cc: Vitaly Kuznetsov <vkuznets@redhat.com>
Cc: Jack Morgenstein <jackm@mellanox.com>
2018-03-15 14:21:08 +00:00
|
|
|
|
2020-04-06 02:15:10 +02:00
|
|
|
|
|
|
|
|
|
PCI: hv: Fix 2 hang issues in hv_compose_msi_msg()
1. With the patch "x86/vector/msi: Switch to global reservation mode",
the recent v4.15 and newer kernels always hang for 1-vCPU Hyper-V VM
with SR-IOV. This is because when we reach hv_compose_msi_msg() by
request_irq() -> request_threaded_irq() ->__setup_irq()->irq_startup()
-> __irq_startup() -> irq_domain_activate_irq() -> ... ->
msi_domain_activate() -> ... -> hv_compose_msi_msg(), local irq is
disabled in __setup_irq().
Note: when we reach hv_compose_msi_msg() by another code path:
pci_enable_msix_range() -> ... -> irq_domain_activate_irq() -> ... ->
hv_compose_msi_msg(), local irq is not disabled.
hv_compose_msi_msg() depends on an interrupt from the host.
With interrupts disabled, a UP VM always hangs in the busy loop in
the function, because the interrupt callback hv_pci_onchannelcallback()
can not be called.
We can do nothing but work it around by polling the channel. This
is ugly, but we don't have any other choice.
2. If the host is ejecting the VF device before we reach
hv_compose_msi_msg(), in a UP VM, we can hang in hv_compose_msi_msg()
forever, because at this time the host doesn't respond to the
CREATE_INTERRUPT request. This issue exists the first day the
pci-hyperv driver appears in the kernel.
Luckily, this can also by worked around by polling the channel
for the PCI_EJECT message and hpdev->state, and by checking the
PCI vendor ID.
Note: actually the above 2 issues also happen to a SMP VM, if
"hbus->hdev->channel->target_cpu == smp_processor_id()" is true.
Fixes: 4900be83602b ("x86/vector/msi: Switch to global reservation mode")
Tested-by: Adrian Suhov <v-adsuho@microsoft.com>
Tested-by: Chris Valean <v-chvale@microsoft.com>
Signed-off-by: Dexuan Cui <decui@microsoft.com>
Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Reviewed-by: Michael Kelley <mikelley@microsoft.com>
Acked-by: Haiyang Zhang <haiyangz@microsoft.com>
Cc: <stable@vger.kernel.org>
Cc: Stephen Hemminger <sthemmin@microsoft.com>
Cc: K. Y. Srinivasan <kys@microsoft.com>
Cc: Vitaly Kuznetsov <vkuznets@redhat.com>
Cc: Jack Morgenstein <jackm@mellanox.com>
2018-03-15 14:21:08 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2020-04-06 02:15:10 +02:00
|
|
|
|
PCI: hv: Fix 2 hang issues in hv_compose_msi_msg()
1. With the patch "x86/vector/msi: Switch to global reservation mode",
the recent v4.15 and newer kernels always hang for 1-vCPU Hyper-V VM
with SR-IOV. This is because when we reach hv_compose_msi_msg() by
request_irq() -> request_threaded_irq() ->__setup_irq()->irq_startup()
-> __irq_startup() -> irq_domain_activate_irq() -> ... ->
msi_domain_activate() -> ... -> hv_compose_msi_msg(), local irq is
disabled in __setup_irq().
Note: when we reach hv_compose_msi_msg() by another code path:
pci_enable_msix_range() -> ... -> irq_domain_activate_irq() -> ... ->
hv_compose_msi_msg(), local irq is not disabled.
hv_compose_msi_msg() depends on an interrupt from the host.
With interrupts disabled, a UP VM always hangs in the busy loop in
the function, because the interrupt callback hv_pci_onchannelcallback()
can not be called.
We can do nothing but work it around by polling the channel. This
is ugly, but we don't have any other choice.
2. If the host is ejecting the VF device before we reach
hv_compose_msi_msg(), in a UP VM, we can hang in hv_compose_msi_msg()
forever, because at this time the host doesn't respond to the
CREATE_INTERRUPT request. This issue exists the first day the
pci-hyperv driver appears in the kernel.
Luckily, this can also by worked around by polling the channel
for the PCI_EJECT message and hpdev->state, and by checking the
PCI vendor ID.
Note: actually the above 2 issues also happen to a SMP VM, if
"hbus->hdev->channel->target_cpu == smp_processor_id()" is true.
Fixes: 4900be83602b ("x86/vector/msi: Switch to global reservation mode")
Tested-by: Adrian Suhov <v-adsuho@microsoft.com>
Tested-by: Chris Valean <v-chvale@microsoft.com>
Signed-off-by: Dexuan Cui <decui@microsoft.com>
Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Reviewed-by: Michael Kelley <mikelley@microsoft.com>
Acked-by: Haiyang Zhang <haiyangz@microsoft.com>
Cc: <stable@vger.kernel.org>
Cc: Stephen Hemminger <sthemmin@microsoft.com>
Cc: K. Y. Srinivasan <kys@microsoft.com>
Cc: Vitaly Kuznetsov <vkuznets@redhat.com>
Cc: Jack Morgenstein <jackm@mellanox.com>
2018-03-15 14:21:08 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2020-04-06 02:15:10 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
PCI: hv: Fix 2 hang issues in hv_compose_msi_msg()
1. With the patch "x86/vector/msi: Switch to global reservation mode",
the recent v4.15 and newer kernels always hang for 1-vCPU Hyper-V VM
with SR-IOV. This is because when we reach hv_compose_msi_msg() by
request_irq() -> request_threaded_irq() ->__setup_irq()->irq_startup()
-> __irq_startup() -> irq_domain_activate_irq() -> ... ->
msi_domain_activate() -> ... -> hv_compose_msi_msg(), local irq is
disabled in __setup_irq().
Note: when we reach hv_compose_msi_msg() by another code path:
pci_enable_msix_range() -> ... -> irq_domain_activate_irq() -> ... ->
hv_compose_msi_msg(), local irq is not disabled.
hv_compose_msi_msg() depends on an interrupt from the host.
With interrupts disabled, a UP VM always hangs in the busy loop in
the function, because the interrupt callback hv_pci_onchannelcallback()
can not be called.
We can do nothing but work it around by polling the channel. This
is ugly, but we don't have any other choice.
2. If the host is ejecting the VF device before we reach
hv_compose_msi_msg(), in a UP VM, we can hang in hv_compose_msi_msg()
forever, because at this time the host doesn't respond to the
CREATE_INTERRUPT request. This issue exists the first day the
pci-hyperv driver appears in the kernel.
Luckily, this can also by worked around by polling the channel
for the PCI_EJECT message and hpdev->state, and by checking the
PCI vendor ID.
Note: actually the above 2 issues also happen to a SMP VM, if
"hbus->hdev->channel->target_cpu == smp_processor_id()" is true.
Fixes: 4900be83602b ("x86/vector/msi: Switch to global reservation mode")
Tested-by: Adrian Suhov <v-adsuho@microsoft.com>
Tested-by: Chris Valean <v-chvale@microsoft.com>
Signed-off-by: Dexuan Cui <decui@microsoft.com>
Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Reviewed-by: Michael Kelley <mikelley@microsoft.com>
Acked-by: Haiyang Zhang <haiyangz@microsoft.com>
Cc: <stable@vger.kernel.org>
Cc: Stephen Hemminger <sthemmin@microsoft.com>
Cc: K. Y. Srinivasan <kys@microsoft.com>
Cc: Vitaly Kuznetsov <vkuznets@redhat.com>
Cc: Jack Morgenstein <jackm@mellanox.com>
2018-03-15 14:21:08 +00:00
|
|
|
|
2020-04-06 02:15:10 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
PCI: hv: Fix 2 hang issues in hv_compose_msi_msg()
1. With the patch "x86/vector/msi: Switch to global reservation mode",
the recent v4.15 and newer kernels always hang for 1-vCPU Hyper-V VM
with SR-IOV. This is because when we reach hv_compose_msi_msg() by
request_irq() -> request_threaded_irq() ->__setup_irq()->irq_startup()
-> __irq_startup() -> irq_domain_activate_irq() -> ... ->
msi_domain_activate() -> ... -> hv_compose_msi_msg(), local irq is
disabled in __setup_irq().
Note: when we reach hv_compose_msi_msg() by another code path:
pci_enable_msix_range() -> ... -> irq_domain_activate_irq() -> ... ->
hv_compose_msi_msg(), local irq is not disabled.
hv_compose_msi_msg() depends on an interrupt from the host.
With interrupts disabled, a UP VM always hangs in the busy loop in
the function, because the interrupt callback hv_pci_onchannelcallback()
can not be called.
We can do nothing but work it around by polling the channel. This
is ugly, but we don't have any other choice.
2. If the host is ejecting the VF device before we reach
hv_compose_msi_msg(), in a UP VM, we can hang in hv_compose_msi_msg()
forever, because at this time the host doesn't respond to the
CREATE_INTERRUPT request. This issue exists the first day the
pci-hyperv driver appears in the kernel.
Luckily, this can also by worked around by polling the channel
for the PCI_EJECT message and hpdev->state, and by checking the
PCI vendor ID.
Note: actually the above 2 issues also happen to a SMP VM, if
"hbus->hdev->channel->target_cpu == smp_processor_id()" is true.
Fixes: 4900be83602b ("x86/vector/msi: Switch to global reservation mode")
Tested-by: Adrian Suhov <v-adsuho@microsoft.com>
Tested-by: Chris Valean <v-chvale@microsoft.com>
Signed-off-by: Dexuan Cui <decui@microsoft.com>
Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Reviewed-by: Michael Kelley <mikelley@microsoft.com>
Acked-by: Haiyang Zhang <haiyangz@microsoft.com>
Cc: <stable@vger.kernel.org>
Cc: Stephen Hemminger <sthemmin@microsoft.com>
Cc: K. Y. Srinivasan <kys@microsoft.com>
Cc: Vitaly Kuznetsov <vkuznets@redhat.com>
Cc: Jack Morgenstein <jackm@mellanox.com>
2018-03-15 14:21:08 +00:00
|
|
|
|
2017-07-31 16:48:29 -07:00
|
|
|
|
PCI: hv: Fix 2 hang issues in hv_compose_msi_msg()
1. With the patch "x86/vector/msi: Switch to global reservation mode",
the recent v4.15 and newer kernels always hang for 1-vCPU Hyper-V VM
with SR-IOV. This is because when we reach hv_compose_msi_msg() by
request_irq() -> request_threaded_irq() ->__setup_irq()->irq_startup()
-> __irq_startup() -> irq_domain_activate_irq() -> ... ->
msi_domain_activate() -> ... -> hv_compose_msi_msg(), local irq is
disabled in __setup_irq().
Note: when we reach hv_compose_msi_msg() by another code path:
pci_enable_msix_range() -> ... -> irq_domain_activate_irq() -> ... ->
hv_compose_msi_msg(), local irq is not disabled.
hv_compose_msi_msg() depends on an interrupt from the host.
With interrupts disabled, a UP VM always hangs in the busy loop in
the function, because the interrupt callback hv_pci_onchannelcallback()
can not be called.
We can do nothing but work it around by polling the channel. This
is ugly, but we don't have any other choice.
2. If the host is ejecting the VF device before we reach
hv_compose_msi_msg(), in a UP VM, we can hang in hv_compose_msi_msg()
forever, because at this time the host doesn't respond to the
CREATE_INTERRUPT request. This issue exists the first day the
pci-hyperv driver appears in the kernel.
Luckily, this can also by worked around by polling the channel
for the PCI_EJECT message and hpdev->state, and by checking the
PCI vendor ID.
Note: actually the above 2 issues also happen to a SMP VM, if
"hbus->hdev->channel->target_cpu == smp_processor_id()" is true.
Fixes: 4900be83602b ("x86/vector/msi: Switch to global reservation mode")
Tested-by: Adrian Suhov <v-adsuho@microsoft.com>
Tested-by: Chris Valean <v-chvale@microsoft.com>
Signed-off-by: Dexuan Cui <decui@microsoft.com>
Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Reviewed-by: Michael Kelley <mikelley@microsoft.com>
Acked-by: Haiyang Zhang <haiyangz@microsoft.com>
Cc: <stable@vger.kernel.org>
Cc: Stephen Hemminger <sthemmin@microsoft.com>
Cc: K. Y. Srinivasan <kys@microsoft.com>
Cc: Vitaly Kuznetsov <vkuznets@redhat.com>
Cc: Jack Morgenstein <jackm@mellanox.com>
2018-03-15 14:21:08 +00:00
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
2020-04-06 02:15:10 +02:00
|
|
|
|
|
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2018-05-23 10:11:12 -07:00
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
2020-04-06 02:15:10 +02:00
|
|
|
|
|
|
|
|
|
2022-04-19 14:23:25 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2018-05-23 10:11:12 -07:00
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2025-07-07 10:20:16 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2022-01-05 11:32:35 -08:00
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
2022-01-05 11:32:36 -08:00
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2025-07-07 10:20:16 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2025-08-13 07:53:50 +02:00
|
|
|
|
2025-07-07 10:20:16 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2025-07-07 10:20:16 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2021-07-27 02:06:56 +08:00
|
|
|
|
|
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2018-05-23 10:11:14 -07:00
|
|
|
|
2019-09-28 02:43:08 +03:00
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
PCI: hv: Add hibernation support
Add suspend() and resume() functions so that Hyper-V virtual PCI devices
are handled properly when the VM hibernates and resumes from
hibernation.
Note that the suspend() function must make sure there are no pending
work items before calling vmbus_close(), since it runs in a process
context as a callback in dpm_suspend(). When it starts to run, the
channel callback hv_pci_onchannelcallback(), which runs in a tasklet
context, can be still running concurrently and scheduling new work items
onto hbus->wq in hv_pci_devices_present() and hv_pci_eject_device(), and
the work item handlers can access the vmbus channel, which can be being
closed by hv_pci_suspend(), e.g. the work item handler
pci_devices_present_work() -> new_pcichild_device() writes to the vmbus
channel.
To eliminate the race, hv_pci_suspend() disables the channel callback
tasklet, sets hbus->state to hv_pcibus_removing, and re-enables the
tasklet. This way, when hv_pci_suspend() proceeds, it knows that no new
work item can be scheduled, and then it flushes hbus->wq and safely
closes the vmbus channel.
Signed-off-by: Dexuan Cui <decui@microsoft.com>
Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Reviewed-by: Michael Kelley <mikelley@microsoft.com>
2019-11-24 21:33:52 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2021-01-26 15:38:55 -06:00
|
|
|
|
PCI: hv: Add hibernation support
Add suspend() and resume() functions so that Hyper-V virtual PCI devices
are handled properly when the VM hibernates and resumes from
hibernation.
Note that the suspend() function must make sure there are no pending
work items before calling vmbus_close(), since it runs in a process
context as a callback in dpm_suspend(). When it starts to run, the
channel callback hv_pci_onchannelcallback(), which runs in a tasklet
context, can be still running concurrently and scheduling new work items
onto hbus->wq in hv_pci_devices_present() and hv_pci_eject_device(), and
the work item handlers can access the vmbus channel, which can be being
closed by hv_pci_suspend(), e.g. the work item handler
pci_devices_present_work() -> new_pcichild_device() writes to the vmbus
channel.
To eliminate the race, hv_pci_suspend() disables the channel callback
tasklet, sets hbus->state to hv_pcibus_removing, and re-enables the
tasklet. This way, when hv_pci_suspend() proceeds, it knows that no new
work item can be scheduled, and then it flushes hbus->wq and safely
closes the vmbus channel.
Signed-off-by: Dexuan Cui <decui@microsoft.com>
Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Reviewed-by: Michael Kelley <mikelley@microsoft.com>
2019-11-24 21:33:52 -08:00
|
|
|
|
|
|
|
|
|
2021-11-18 19:33:34 +05:30
|
|
|
|
PCI: hv: Add hibernation support
Add suspend() and resume() functions so that Hyper-V virtual PCI devices
are handled properly when the VM hibernates and resumes from
hibernation.
Note that the suspend() function must make sure there are no pending
work items before calling vmbus_close(), since it runs in a process
context as a callback in dpm_suspend(). When it starts to run, the
channel callback hv_pci_onchannelcallback(), which runs in a tasklet
context, can be still running concurrently and scheduling new work items
onto hbus->wq in hv_pci_devices_present() and hv_pci_eject_device(), and
the work item handlers can access the vmbus channel, which can be being
closed by hv_pci_suspend(), e.g. the work item handler
pci_devices_present_work() -> new_pcichild_device() writes to the vmbus
channel.
To eliminate the race, hv_pci_suspend() disables the channel callback
tasklet, sets hbus->state to hv_pcibus_removing, and re-enables the
tasklet. This way, when hv_pci_suspend() proceeds, it knows that no new
work item can be scheduled, and then it flushes hbus->wq and safely
closes the vmbus channel.
Signed-off-by: Dexuan Cui <decui@microsoft.com>
Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Reviewed-by: Michael Kelley <mikelley@microsoft.com>
2019-11-24 21:33:52 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
2018-05-23 10:11:14 -07:00
|
|
|
|
2019-09-28 02:43:08 +03:00
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2022-05-02 00:42:55 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2018-09-14 12:54:56 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2021-07-27 02:06:54 +08:00
|
|
|
|
2018-09-14 12:54:56 -07:00
|
|
|
|
2018-09-21 02:53:17 +00:00
|
|
|
|
2018-09-14 12:54:56 -07:00
|
|
|
|
2018-09-21 02:53:17 +00:00
|
|
|
|
|
|
|
|
|
2018-09-14 12:54:56 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2019-03-04 21:34:48 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2020-02-25 21:06:08 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2021-07-27 02:06:54 +08:00
|
|
|
|
2020-02-25 21:06:08 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2026-03-16 14:07:42 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2022-01-26 17:43:34 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2020-02-25 21:06:08 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2021-07-27 02:06:54 +08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
2017-03-23 14:58:32 -07:00
|
|
|
|
2020-02-25 21:06:08 -08:00
|
|
|
|
2021-07-27 02:06:54 +08:00
|
|
|
|
2018-09-14 12:54:56 -07:00
|
|
|
|
2021-07-27 02:06:54 +08:00
|
|
|
|
2017-03-23 14:58:32 -07:00
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2022-05-12 00:32:06 +02:00
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
2022-05-12 00:32:06 +02:00
|
|
|
|
|
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
2022-05-12 00:32:06 +02:00
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
2019-09-28 02:43:08 +03:00
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2020-02-25 21:06:07 -08:00
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-11-10 07:17:48 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2026-02-21 16:37:42 -08:00
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2025-05-13 21:44:40 -07:00
|
|
|
|
2016-08-23 04:45:51 +00:00
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2018-05-23 21:12:01 +00:00
|
|
|
|
|
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
2017-04-18 09:02:48 -05:00
|
|
|
|
2018-05-23 10:11:12 -07:00
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
2017-02-13 18:10:11 +00:00
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2018-05-23 10:11:12 -07:00
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2018-03-15 14:20:53 +00:00
|
|
|
|
|
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2020-02-25 21:06:07 -08:00
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2021-05-12 01:06:49 -07:00
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
PCI: hv: Add a per-bus mutex state_lock
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@microsoft.com>
Reviewed-by: Michael Kelley <mikelley@microsoft.com>
Acked-by: Lorenzo Pieralisi <lpieralisi@kernel.org>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20230615044451.5580-6-decui@microsoft.com
Signed-off-by: Wei Liu <wei.liu@kernel.org>
2023-06-14 21:44:51 -07:00
|
|
|
|
|
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
2018-05-23 10:11:14 -07:00
|
|
|
|
|
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2018-05-23 10:11:14 -07:00
|
|
|
|
|
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2018-05-23 10:11:14 -07:00
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
2018-05-23 10:11:12 -07:00
|
|
|
|
2016-07-28 16:16:48 +00:00
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
PCI: hv: Add pci_destroy_slot() in pci_devices_present_work(), if necessary
When we hot-remove a device, usually the host sends us a PCI_EJECT message,
and a PCI_BUS_RELATIONS message with bus_rel->device_count == 0.
When we execute the quick hot-add/hot-remove test, the host may not send
us the PCI_EJECT message if the guest has not fully finished the
initialization by sending the PCI_RESOURCES_ASSIGNED* message to the
host, so it's potentially unsafe to only depend on the
pci_destroy_slot() in hv_eject_device_work() because the code path
create_root_hv_pci_bus()
-> hv_pci_assign_slots()
is not called in this case. Note: in this case, the host still sends the
guest a PCI_BUS_RELATIONS message with bus_rel->device_count == 0.
In the quick hot-add/hot-remove test, we can have such a race before
the code path
pci_devices_present_work()
-> new_pcichild_device()
adds the new device into the hbus->children list, we may have already
received the PCI_EJECT message, and since the tasklet handler
hv_pci_onchannelcallback()
may fail to find the "hpdev" by calling
get_pcichild_wslot(hbus, dev_message->wslot.slot)
hv_pci_eject_device() is not called; Later, by continuing execution
create_root_hv_pci_bus()
-> hv_pci_assign_slots()
creates the slot and the PCI_BUS_RELATIONS message with
bus_rel->device_count == 0 removes the device from hbus->children, and
we end up being unable to remove the slot in
hv_pci_remove()
-> hv_pci_remove_slots()
Remove the slot in pci_devices_present_work() when the device
is removed to address this race.
pci_devices_present_work() and hv_eject_device_work() run in the
singled-threaded hbus->wq, so there is not a double-remove issue for the
slot.
We cannot offload hv_pci_eject_device() from hv_pci_onchannelcallback()
to the workqueue, because we need the hv_pci_onchannelcallback()
synchronously call hv_pci_eject_device() to poll the channel
ringbuffer to work around the "hangs in hv_compose_msi_msg()" issue
fixed in commit de0aa7b2f97d ("PCI: hv: Fix 2 hang issues in
hv_compose_msi_msg()")
Fixes: a15f2c08c708 ("PCI: hv: support reporting serial number as slot information")
Signed-off-by: Dexuan Cui <decui@microsoft.com>
[lorenzo.pieralisi@arm.com: rewritten commit log]
Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Reviewed-by: Stephen Hemminger <stephen@networkplumber.org>
Reviewed-by: Michael Kelley <mikelley@microsoft.com>
Cc: stable@vger.kernel.org
2019-03-04 21:34:49 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2018-05-23 10:11:12 -07:00
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
2017-05-24 13:41:24 -07:00
|
|
|
|
2017-03-23 14:58:10 -07:00
|
|
|
|
|
|
|
|
|
2017-05-24 13:41:24 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
2021-07-27 02:06:54 +08:00
|
|
|
|
2020-02-25 21:06:08 -08:00
|
|
|
|
2018-09-14 12:54:56 -07:00
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
2017-03-23 14:58:10 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
2017-03-23 14:58:10 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
PCI: hv: Add a per-bus mutex state_lock
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@microsoft.com>
Reviewed-by: Michael Kelley <mikelley@microsoft.com>
Acked-by: Lorenzo Pieralisi <lpieralisi@kernel.org>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20230615044451.5580-6-decui@microsoft.com
Signed-off-by: Wei Liu <wei.liu@kernel.org>
2023-06-14 21:44:51 -07:00
|
|
|
|
|
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2020-02-25 21:06:07 -08:00
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
2020-02-25 21:06:07 -08:00
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
2020-02-25 21:06:07 -08:00
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
2020-02-25 21:06:07 -08:00
|
|
|
|
|
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2018-03-15 14:22:00 +00:00
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
PCI: hv: Add hibernation support
Add suspend() and resume() functions so that Hyper-V virtual PCI devices
are handled properly when the VM hibernates and resumes from
hibernation.
Note that the suspend() function must make sure there are no pending
work items before calling vmbus_close(), since it runs in a process
context as a callback in dpm_suspend(). When it starts to run, the
channel callback hv_pci_onchannelcallback(), which runs in a tasklet
context, can be still running concurrently and scheduling new work items
onto hbus->wq in hv_pci_devices_present() and hv_pci_eject_device(), and
the work item handlers can access the vmbus channel, which can be being
closed by hv_pci_suspend(), e.g. the work item handler
pci_devices_present_work() -> new_pcichild_device() writes to the vmbus
channel.
To eliminate the race, hv_pci_suspend() disables the channel callback
tasklet, sets hbus->state to hv_pcibus_removing, and re-enables the
tasklet. This way, when hv_pci_suspend() proceeds, it knows that no new
work item can be scheduled, and then it flushes hbus->wq and safely
closes the vmbus channel.
Signed-off-by: Dexuan Cui <decui@microsoft.com>
Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Reviewed-by: Michael Kelley <mikelley@microsoft.com>
2019-11-24 21:33:52 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2020-02-25 21:06:07 -08:00
|
|
|
|
PCI: hv: Add hibernation support
Add suspend() and resume() functions so that Hyper-V virtual PCI devices
are handled properly when the VM hibernates and resumes from
hibernation.
Note that the suspend() function must make sure there are no pending
work items before calling vmbus_close(), since it runs in a process
context as a callback in dpm_suspend(). When it starts to run, the
channel callback hv_pci_onchannelcallback(), which runs in a tasklet
context, can be still running concurrently and scheduling new work items
onto hbus->wq in hv_pci_devices_present() and hv_pci_eject_device(), and
the work item handlers can access the vmbus channel, which can be being
closed by hv_pci_suspend(), e.g. the work item handler
pci_devices_present_work() -> new_pcichild_device() writes to the vmbus
channel.
To eliminate the race, hv_pci_suspend() disables the channel callback
tasklet, sets hbus->state to hv_pcibus_removing, and re-enables the
tasklet. This way, when hv_pci_suspend() proceeds, it knows that no new
work item can be scheduled, and then it flushes hbus->wq and safely
closes the vmbus channel.
Signed-off-by: Dexuan Cui <decui@microsoft.com>
Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Reviewed-by: Michael Kelley <mikelley@microsoft.com>
2019-11-24 21:33:52 -08:00
|
|
|
|
|
|
|
|
|
treewide: Replace kmalloc with kmalloc_obj for non-scalar types
This is the result of running the Coccinelle script from
scripts/coccinelle/api/kmalloc_objs.cocci. The script is designed to
avoid scalar types (which need careful case-by-case checking), and
instead replace kmalloc-family calls that allocate struct or union
object instances:
Single allocations: kmalloc(sizeof(TYPE), ...)
are replaced with: kmalloc_obj(TYPE, ...)
Array allocations: kmalloc_array(COUNT, sizeof(TYPE), ...)
are replaced with: kmalloc_objs(TYPE, COUNT, ...)
Flex array allocations: kmalloc(struct_size(PTR, FAM, COUNT), ...)
are replaced with: kmalloc_flex(*PTR, FAM, COUNT, ...)
(where TYPE may also be *VAR)
The resulting allocations no longer return "void *", instead returning
"TYPE *".
Signed-off-by: Kees Cook <kees@kernel.org>
2026-02-20 23:49:23 -08:00
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
2020-02-25 21:06:07 -08:00
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2018-03-15 14:22:00 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2021-05-12 01:06:49 -07:00
|
|
|
|
2018-03-15 14:22:00 +00:00
|
|
|
|
2021-05-12 01:06:49 -07:00
|
|
|
|
2018-03-15 14:22:00 +00:00
|
|
|
|
2020-02-25 21:06:07 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
treewide: Replace kmalloc with kmalloc_obj for non-scalar types
This is the result of running the Coccinelle script from
scripts/coccinelle/api/kmalloc_objs.cocci. The script is designed to
avoid scalar types (which need careful case-by-case checking), and
instead replace kmalloc-family calls that allocate struct or union
object instances:
Single allocations: kmalloc(sizeof(TYPE), ...)
are replaced with: kmalloc_obj(TYPE, ...)
Array allocations: kmalloc_array(COUNT, sizeof(TYPE), ...)
are replaced with: kmalloc_objs(TYPE, COUNT, ...)
Flex array allocations: kmalloc(struct_size(PTR, FAM, COUNT), ...)
are replaced with: kmalloc_flex(*PTR, FAM, COUNT, ...)
(where TYPE may also be *VAR)
The resulting allocations no longer return "void *", instead returning
"TYPE *".
Signed-off-by: Kees Cook <kees@kernel.org>
2026-02-20 23:49:23 -08:00
|
|
|
|
2020-02-25 21:06:07 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
2020-02-25 21:06:08 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
treewide: Replace kmalloc with kmalloc_obj for non-scalar types
This is the result of running the Coccinelle script from
scripts/coccinelle/api/kmalloc_objs.cocci. The script is designed to
avoid scalar types (which need careful case-by-case checking), and
instead replace kmalloc-family calls that allocate struct or union
object instances:
Single allocations: kmalloc(sizeof(TYPE), ...)
are replaced with: kmalloc_obj(TYPE, ...)
Array allocations: kmalloc_array(COUNT, sizeof(TYPE), ...)
are replaced with: kmalloc_objs(TYPE, COUNT, ...)
Flex array allocations: kmalloc(struct_size(PTR, FAM, COUNT), ...)
are replaced with: kmalloc_flex(*PTR, FAM, COUNT, ...)
(where TYPE may also be *VAR)
The resulting allocations no longer return "void *", instead returning
"TYPE *".
Signed-off-by: Kees Cook <kees@kernel.org>
2026-02-20 23:49:23 -08:00
|
|
|
|
2020-02-25 21:06:08 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2019-06-21 23:45:23 +00:00
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-08-23 04:45:51 +00:00
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2019-06-21 23:45:23 +00:00
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
PCI: hv: Add a per-bus mutex state_lock
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@microsoft.com>
Reviewed-by: Michael Kelley <mikelley@microsoft.com>
Acked-by: Lorenzo Pieralisi <lpieralisi@kernel.org>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20230615044451.5580-6-decui@microsoft.com
Signed-off-by: Wei Liu <wei.liu@kernel.org>
2023-06-14 21:44:51 -07:00
|
|
|
|
|
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2021-07-27 02:06:54 +08:00
|
|
|
|
|
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
2021-07-27 02:06:55 +08:00
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
2017-03-23 14:58:32 -07:00
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
2017-03-23 14:58:32 -07:00
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
2019-06-21 23:45:23 +00:00
|
|
|
|
2016-11-10 07:19:52 +00:00
|
|
|
|
2019-06-21 23:45:23 +00:00
|
|
|
|
2016-11-10 07:19:52 +00:00
|
|
|
|
2018-09-14 12:54:56 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
2025-05-13 21:44:40 -07:00
|
|
|
|
2016-08-23 04:45:51 +00:00
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
2019-06-21 23:45:23 +00:00
|
|
|
|
2022-04-19 14:23:21 +02:00
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
2019-03-04 21:34:48 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2018-05-23 10:11:12 -07:00
|
|
|
|
|
|
|
|
|
2019-06-21 23:45:23 +00:00
|
|
|
|
PCI: hv: Add a per-bus mutex state_lock
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@microsoft.com>
Reviewed-by: Michael Kelley <mikelley@microsoft.com>
Acked-by: Lorenzo Pieralisi <lpieralisi@kernel.org>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20230615044451.5580-6-decui@microsoft.com
Signed-off-by: Wei Liu <wei.liu@kernel.org>
2023-06-14 21:44:51 -07:00
|
|
|
|
|
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
PCI: hv: Add hibernation support
Add suspend() and resume() functions so that Hyper-V virtual PCI devices
are handled properly when the VM hibernates and resumes from
hibernation.
Note that the suspend() function must make sure there are no pending
work items before calling vmbus_close(), since it runs in a process
context as a callback in dpm_suspend(). When it starts to run, the
channel callback hv_pci_onchannelcallback(), which runs in a tasklet
context, can be still running concurrently and scheduling new work items
onto hbus->wq in hv_pci_devices_present() and hv_pci_eject_device(), and
the work item handlers can access the vmbus channel, which can be being
closed by hv_pci_suspend(), e.g. the work item handler
pci_devices_present_work() -> new_pcichild_device() writes to the vmbus
channel.
To eliminate the race, hv_pci_suspend() disables the channel callback
tasklet, sets hbus->state to hv_pcibus_removing, and re-enables the
tasklet. This way, when hv_pci_suspend() proceeds, it knows that no new
work item can be scheduled, and then it flushes hbus->wq and safely
closes the vmbus channel.
Signed-off-by: Dexuan Cui <decui@microsoft.com>
Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Reviewed-by: Michael Kelley <mikelley@microsoft.com>
2019-11-24 21:33:52 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2018-05-23 10:11:12 -07:00
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
PCI: hv: Add hibernation support
Add suspend() and resume() functions so that Hyper-V virtual PCI devices
are handled properly when the VM hibernates and resumes from
hibernation.
Note that the suspend() function must make sure there are no pending
work items before calling vmbus_close(), since it runs in a process
context as a callback in dpm_suspend(). When it starts to run, the
channel callback hv_pci_onchannelcallback(), which runs in a tasklet
context, can be still running concurrently and scheduling new work items
onto hbus->wq in hv_pci_devices_present() and hv_pci_eject_device(), and
the work item handlers can access the vmbus channel, which can be being
closed by hv_pci_suspend(), e.g. the work item handler
pci_devices_present_work() -> new_pcichild_device() writes to the vmbus
channel.
To eliminate the race, hv_pci_suspend() disables the channel callback
tasklet, sets hbus->state to hv_pcibus_removing, and re-enables the
tasklet. This way, when hv_pci_suspend() proceeds, it knows that no new
work item can be scheduled, and then it flushes hbus->wq and safely
closes the vmbus channel.
Signed-off-by: Dexuan Cui <decui@microsoft.com>
Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Reviewed-by: Michael Kelley <mikelley@microsoft.com>
2019-11-24 21:33:52 -08:00
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2022-04-19 14:23:21 +02:00
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
2022-04-19 14:23:21 +02:00
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2020-02-25 21:06:08 -08:00
|
|
|
|
2019-08-22 05:05:37 +00:00
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
2022-04-19 14:23:25 +02:00
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2022-04-19 14:23:21 +02:00
|
|
|
|
|
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-06-17 12:45:30 -05:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-05-30 16:17:58 +02:00
|
|
|
|
2016-06-17 12:45:30 -05:00
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2022-04-19 14:23:25 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2022-04-19 14:23:21 +02:00
|
|
|
|
2022-04-19 14:23:25 +02:00
|
|
|
|
2022-04-19 14:23:21 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
2022-04-19 14:23:25 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2022-04-19 14:23:25 +02:00
|
|
|
|
2016-05-30 16:17:58 +02:00
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-08-23 04:45:51 +00:00
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2022-05-12 00:32:06 +02:00
|
|
|
|
|
|
|
|
|
2020-05-25 11:43:19 -05:00
|
|
|
|
|
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2020-02-25 21:06:08 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2022-05-12 00:32:06 +02:00
|
|
|
|
|
|
|
|
|
2020-05-25 11:43:19 -05:00
|
|
|
|
|
|
|
|
|
2020-02-25 21:06:08 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2022-05-12 00:32:06 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2018-05-23 10:11:12 -07:00
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2019-08-22 05:05:37 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2022-05-12 00:32:06 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2019-08-22 05:05:37 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-08-23 04:45:51 +00:00
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-05-30 16:17:58 +02:00
|
|
|
|
|
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2020-09-25 23:47:53 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2019-11-24 21:33:51 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
2019-11-24 21:33:53 -08:00
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2017-05-24 13:41:27 -07:00
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2025-05-13 21:44:40 -07:00
|
|
|
|
2016-08-23 04:45:51 +00:00
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
2019-11-24 21:33:51 -08:00
|
|
|
|
|
|
|
|
|
2017-05-24 13:41:27 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2018-05-23 21:12:01 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2017-05-24 13:41:27 -07:00
|
|
|
|
|
|
|
|
|
2018-05-23 21:12:01 +00:00
|
|
|
|
2017-05-24 13:41:27 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
2017-05-24 13:41:27 -07:00
|
|
|
|
2019-11-24 21:33:53 -08:00
|
|
|
|
2017-05-24 13:41:27 -07:00
|
|
|
|
|
|
|
|
|
2019-11-24 21:33:53 -08:00
|
|
|
|
2017-05-24 13:41:27 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
2017-05-24 13:41:27 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-04-05 10:22:52 -07:00
|
|
|
|
|
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-04-05 10:22:52 -07:00
|
|
|
|
|
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2021-07-27 02:06:54 +08:00
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2021-07-27 02:06:54 +08:00
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-04-05 10:22:52 -07:00
|
|
|
|
|
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-04-05 10:22:52 -07:00
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
2020-05-07 13:03:00 +08:00
|
|
|
|
|
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-06-14 21:44:50 -07:00
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
2023-06-14 21:44:50 -07:00
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2025-05-13 21:44:40 -07:00
|
|
|
|
2016-08-23 04:45:51 +00:00
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2018-05-23 21:12:01 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-06-14 21:44:50 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-08-23 04:45:51 +00:00
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2018-05-23 21:12:01 +00:00
|
|
|
|
|
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
2023-06-14 21:44:47 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2018-05-23 21:12:01 +00:00
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2017-05-24 13:41:28 -07:00
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2017-05-24 13:41:28 -07:00
|
|
|
|
2020-05-07 13:02:11 +08:00
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
2019-11-24 21:33:53 -08:00
|
|
|
|
2017-05-24 13:41:28 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2017-05-24 13:41:28 -07:00
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2019-11-24 21:33:53 -08:00
|
|
|
|
2017-05-24 13:41:28 -07:00
|
|
|
|
2025-05-13 21:44:40 -07:00
|
|
|
|
2017-05-24 13:41:28 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2025-05-13 21:44:40 -07:00
|
|
|
|
2017-05-24 13:41:28 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2018-05-23 10:11:12 -07:00
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
2025-05-13 21:44:40 -07:00
|
|
|
|
2017-05-24 13:41:28 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2018-05-23 21:12:01 +00:00
|
|
|
|
|
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2020-05-07 13:02:11 +08:00
|
|
|
|
|
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2020-05-07 13:02:11 +08:00
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
2020-05-07 13:02:11 +08:00
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-08-23 04:45:51 +00:00
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
2018-05-23 10:11:12 -07:00
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2020-05-07 13:02:11 +08:00
|
|
|
|
|
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
2020-05-07 13:02:11 +08:00
|
|
|
|
|
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2021-07-27 02:06:54 +08:00
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
2025-10-24 15:46:21 -07:00
|
|
|
|
|
|
|
|
|
2019-08-06 15:23:33 +01:00
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
2021-07-27 02:06:54 +08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2026-02-21 16:37:42 -08:00
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
2021-07-27 02:06:54 +08:00
|
|
|
|
|
|
|
|
|
PCI: hv: Add a per-bus mutex state_lock
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@microsoft.com>
Reviewed-by: Michael Kelley <mikelley@microsoft.com>
Acked-by: Lorenzo Pieralisi <lpieralisi@kernel.org>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20230615044451.5580-6-decui@microsoft.com
Signed-off-by: Wei Liu <wei.liu@kernel.org>
2023-06-14 21:44:51 -07:00
|
|
|
|
2017-03-23 14:58:10 -07:00
|
|
|
|
2020-05-07 13:02:11 +08:00
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
2019-08-15 17:01:37 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2025-10-24 15:46:21 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
2019-08-15 17:01:45 +00:00
|
|
|
|
2025-10-24 15:46:21 -07:00
|
|
|
|
|
|
|
|
|
2019-08-15 17:01:37 +00:00
|
|
|
|
2021-10-08 22:27:30 +00:00
|
|
|
|
2019-08-15 17:01:37 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2021-10-08 22:27:30 +00:00
|
|
|
|
2019-08-15 17:01:37 +00:00
|
|
|
|
|
|
|
|
|
2021-07-27 02:06:55 +08:00
|
|
|
|
2021-07-27 02:06:57 +08:00
|
|
|
|
2019-08-15 17:01:37 +00:00
|
|
|
|
2023-03-26 06:52:07 -07:00
|
|
|
|
2022-03-24 09:14:52 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-03-26 06:52:07 -07:00
|
|
|
|
2021-07-27 02:06:57 +08:00
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2018-03-15 14:20:53 +00:00
|
|
|
|
2021-07-27 02:06:55 +08:00
|
|
|
|
2018-03-15 14:20:53 +00:00
|
|
|
|
|
|
|
|
|
2026-04-03 05:09:29 -07:00
|
|
|
|
2018-03-15 14:20:53 +00:00
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
2022-04-19 14:23:21 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2018-03-15 14:20:53 +00:00
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2019-11-24 21:33:51 -08:00
|
|
|
|
|
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2019-08-06 15:23:33 +01:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2021-07-27 02:06:56 +08:00
|
|
|
|
2019-08-06 15:23:33 +01:00
|
|
|
|
2021-07-27 02:06:56 +08:00
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
PCI: hv: Add a per-bus mutex state_lock
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@microsoft.com>
Reviewed-by: Michael Kelley <mikelley@microsoft.com>
Acked-by: Lorenzo Pieralisi <lpieralisi@kernel.org>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20230615044451.5580-6-decui@microsoft.com
Signed-off-by: Wei Liu <wei.liu@kernel.org>
2023-06-14 21:44:51 -07:00
|
|
|
|
|
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
PCI: hv: Add a per-bus mutex state_lock
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@microsoft.com>
Reviewed-by: Michael Kelley <mikelley@microsoft.com>
Acked-by: Lorenzo Pieralisi <lpieralisi@kernel.org>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20230615044451.5580-6-decui@microsoft.com
Signed-off-by: Wei Liu <wei.liu@kernel.org>
2023-06-14 21:44:51 -07:00
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2020-05-07 13:02:11 +08:00
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
PCI: hv: Add a per-bus mutex state_lock
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@microsoft.com>
Reviewed-by: Michael Kelley <mikelley@microsoft.com>
Acked-by: Lorenzo Pieralisi <lpieralisi@kernel.org>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20230615044451.5580-6-decui@microsoft.com
Signed-off-by: Wei Liu <wei.liu@kernel.org>
2023-06-14 21:44:51 -07:00
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2020-05-07 13:02:11 +08:00
|
|
|
|
|
|
|
|
|
PCI: hv: Add a per-bus mutex state_lock
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@microsoft.com>
Reviewed-by: Michael Kelley <mikelley@microsoft.com>
Acked-by: Lorenzo Pieralisi <lpieralisi@kernel.org>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20230615044451.5580-6-decui@microsoft.com
Signed-off-by: Wei Liu <wei.liu@kernel.org>
2023-06-14 21:44:51 -07:00
|
|
|
|
|
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2021-07-27 02:06:56 +08:00
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2018-03-15 14:20:53 +00:00
|
|
|
|
|
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
2020-02-21 21:59:57 -08:00
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2020-05-07 13:03:00 +08:00
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
2016-11-10 07:18:47 +00:00
|
|
|
|
2022-05-12 00:32:07 +02:00
|
|
|
|
2016-11-10 07:18:47 +00:00
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
2016-11-10 07:18:47 +00:00
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
2025-05-13 21:44:40 -07:00
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
2021-05-12 01:06:40 -07:00
|
|
|
|
|
|
|
|
|
2022-05-12 00:32:07 +02:00
|
|
|
|
2016-11-10 07:18:47 +00:00
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
2016-11-10 07:18:47 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2022-05-12 00:32:07 +02:00
|
|
|
|
2019-11-24 21:33:51 -08:00
|
|
|
|
2016-11-10 07:18:47 +00:00
|
|
|
|
2020-05-07 13:03:00 +08:00
|
|
|
|
2021-08-30 16:13:27 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2021-05-12 01:06:40 -07:00
|
|
|
|
2021-08-30 16:13:27 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2021-05-12 01:06:40 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2019-11-24 21:33:51 -08:00
|
|
|
|
2016-11-10 07:18:47 +00:00
|
|
|
|
|
|
|
|
|
2019-11-24 21:33:51 -08:00
|
|
|
|
2016-11-10 07:18:47 +00:00
|
|
|
|
|
|
|
|
|
2019-11-24 21:33:51 -08:00
|
|
|
|
|
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2025-05-13 21:44:40 -07:00
|
|
|
|
|
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
2025-05-13 21:44:40 -07:00
|
|
|
|
2022-05-12 00:32:07 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2019-11-24 21:33:51 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2022-05-12 00:32:07 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2019-11-24 21:33:51 -08:00
|
|
|
|
2022-05-12 00:32:07 +02:00
|
|
|
|
2019-11-24 21:33:51 -08:00
|
|
|
|
|
|
|
|
|
2016-11-10 07:18:47 +00:00
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
2016-11-10 07:18:47 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-01-05 22:51:23 +08:00
|
|
|
|
2016-11-10 07:18:47 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
2021-05-12 01:06:40 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
2021-07-27 02:06:54 +08:00
|
|
|
|
2019-03-04 21:34:48 +00:00
|
|
|
|
2021-07-27 02:06:54 +08:00
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-01-05 22:51:23 +08:00
|
|
|
|
2016-04-29 11:39:10 +02:00
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2021-07-27 02:06:56 +08:00
|
|
|
|
2019-08-15 17:01:37 +00:00
|
|
|
|
2019-11-24 21:33:54 -08:00
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
PCI: hv: Add hibernation support
Add suspend() and resume() functions so that Hyper-V virtual PCI devices
are handled properly when the VM hibernates and resumes from
hibernation.
Note that the suspend() function must make sure there are no pending
work items before calling vmbus_close(), since it runs in a process
context as a callback in dpm_suspend(). When it starts to run, the
channel callback hv_pci_onchannelcallback(), which runs in a tasklet
context, can be still running concurrently and scheduling new work items
onto hbus->wq in hv_pci_devices_present() and hv_pci_eject_device(), and
the work item handlers can access the vmbus channel, which can be being
closed by hv_pci_suspend(), e.g. the work item handler
pci_devices_present_work() -> new_pcichild_device() writes to the vmbus
channel.
To eliminate the race, hv_pci_suspend() disables the channel callback
tasklet, sets hbus->state to hv_pcibus_removing, and re-enables the
tasklet. This way, when hv_pci_suspend() proceeds, it knows that no new
work item can be scheduled, and then it flushes hbus->wq and safely
closes the vmbus channel.
Signed-off-by: Dexuan Cui <decui@microsoft.com>
Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Reviewed-by: Michael Kelley <mikelley@microsoft.com>
2019-11-24 21:33:52 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
PCI: hv: Fix hibernation in case interrupts are not re-created
pci_restore_msi_state() directly writes the MSI/MSI-X related registers
via MMIO. On a physical machine, this works perfectly; for a Linux VM
running on a hypervisor, which typically enables IOMMU interrupt remapping,
the hypervisor usually should trap and emulate the MMIO accesses in order
to re-create the necessary interrupt remapping table entries in the IOMMU,
otherwise the interrupts can not work in the VM after hibernation.
Hyper-V is different from other hypervisors in that it does not trap and
emulate the MMIO accesses, and instead it uses a para-virtualized method,
which requires the VM to call hv_compose_msi_msg() to notify the hypervisor
of the info that would be passed to the hypervisor in the case of the
trap-and-emulate method. This is not an issue to a lot of PCI device
drivers, which destroy and re-create the interrupts across hibernation, so
hv_compose_msi_msg() is called automatically. However, some PCI device
drivers (e.g. the in-tree GPU driver nouveau and the out-of-tree Nvidia
proprietary GPU driver) do not destroy and re-create MSI/MSI-X interrupts
across hibernation, so hv_pci_resume() has to call hv_compose_msi_msg(),
otherwise the PCI device drivers can no longer receive interrupts after
the VM resumes from hibernation.
Hyper-V is also different in that chip->irq_unmask() may fail in a
Linux VM running on Hyper-V (on a physical machine, chip->irq_unmask()
can not fail because unmasking an MSI/MSI-X register just means an MMIO
write): during hibernation, when a CPU is offlined, the kernel tries
to move the interrupt to the remaining CPUs that haven't been offlined
yet. In this case, hv_irq_unmask() -> hv_do_hypercall() always fails
because the vmbus channel has been closed: here the early "return" in
hv_irq_unmask() means the pci_msi_unmask_irq() is not called, i.e. the
desc->masked remains "true", so later after hibernation, the MSI interrupt
always remains masked, which is incorrect. Refer to cpu_disable_common()
-> fixup_irqs() -> irq_migrate_all_off_this_cpu() -> migrate_one_irq():
static bool migrate_one_irq(struct irq_desc *desc)
{
...
if (maskchip && chip->irq_mask)
chip->irq_mask(d);
...
err = irq_do_set_affinity(d, affinity, false);
...
if (maskchip && chip->irq_unmask)
chip->irq_unmask(d);
Fix the issue by calling pci_msi_unmask_irq() unconditionally in
hv_irq_unmask(). Also suppress the error message for hibernation because
the hypercall failure during hibernation does not matter (at this time
all the devices have been frozen). Note: the correct affinity info is
still updated into the irqdata data structure in migrate_one_irq() ->
irq_do_set_affinity() -> hv_set_affinity(), so later when the VM
resumes, hv_pci_restore_msi_state() is able to correctly restore
the interrupt with the correct affinity.
Link: https://lore.kernel.org/r/20201002085158.9168-1-decui@microsoft.com
Fixes: ac82fc832708 ("PCI: hv: Add hibernation support")
Signed-off-by: Dexuan Cui <decui@microsoft.com>
Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Reviewed-by: Jake Oshins <jakeo@microsoft.com>
2020-10-02 01:51:58 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2021-12-06 23:51:33 +01:00
|
|
|
|
PCI: hv: Fix hibernation in case interrupts are not re-created
pci_restore_msi_state() directly writes the MSI/MSI-X related registers
via MMIO. On a physical machine, this works perfectly; for a Linux VM
running on a hypervisor, which typically enables IOMMU interrupt remapping,
the hypervisor usually should trap and emulate the MMIO accesses in order
to re-create the necessary interrupt remapping table entries in the IOMMU,
otherwise the interrupts can not work in the VM after hibernation.
Hyper-V is different from other hypervisors in that it does not trap and
emulate the MMIO accesses, and instead it uses a para-virtualized method,
which requires the VM to call hv_compose_msi_msg() to notify the hypervisor
of the info that would be passed to the hypervisor in the case of the
trap-and-emulate method. This is not an issue to a lot of PCI device
drivers, which destroy and re-create the interrupts across hibernation, so
hv_compose_msi_msg() is called automatically. However, some PCI device
drivers (e.g. the in-tree GPU driver nouveau and the out-of-tree Nvidia
proprietary GPU driver) do not destroy and re-create MSI/MSI-X interrupts
across hibernation, so hv_pci_resume() has to call hv_compose_msi_msg(),
otherwise the PCI device drivers can no longer receive interrupts after
the VM resumes from hibernation.
Hyper-V is also different in that chip->irq_unmask() may fail in a
Linux VM running on Hyper-V (on a physical machine, chip->irq_unmask()
can not fail because unmasking an MSI/MSI-X register just means an MMIO
write): during hibernation, when a CPU is offlined, the kernel tries
to move the interrupt to the remaining CPUs that haven't been offlined
yet. In this case, hv_irq_unmask() -> hv_do_hypercall() always fails
because the vmbus channel has been closed: here the early "return" in
hv_irq_unmask() means the pci_msi_unmask_irq() is not called, i.e. the
desc->masked remains "true", so later after hibernation, the MSI interrupt
always remains masked, which is incorrect. Refer to cpu_disable_common()
-> fixup_irqs() -> irq_migrate_all_off_this_cpu() -> migrate_one_irq():
static bool migrate_one_irq(struct irq_desc *desc)
{
...
if (maskchip && chip->irq_mask)
chip->irq_mask(d);
...
err = irq_do_set_affinity(d, affinity, false);
...
if (maskchip && chip->irq_unmask)
chip->irq_unmask(d);
Fix the issue by calling pci_msi_unmask_irq() unconditionally in
hv_irq_unmask(). Also suppress the error message for hibernation because
the hypercall failure during hibernation does not matter (at this time
all the devices have been frozen). Note: the correct affinity info is
still updated into the irqdata data structure in migrate_one_irq() ->
irq_do_set_affinity() -> hv_set_affinity(), so later when the VM
resumes, hv_pci_restore_msi_state() is able to correctly restore
the interrupt with the correct affinity.
Link: https://lore.kernel.org/r/20201002085158.9168-1-decui@microsoft.com
Fixes: ac82fc832708 ("PCI: hv: Add hibernation support")
Signed-off-by: Dexuan Cui <decui@microsoft.com>
Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Reviewed-by: Jake Oshins <jakeo@microsoft.com>
2020-10-02 01:51:58 -07:00
|
|
|
|
2023-08-16 10:59:39 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2025-03-19 11:56:55 +01:00
|
|
|
|
2021-12-06 23:51:33 +01:00
|
|
|
|
PCI: hv: Fix hibernation in case interrupts are not re-created
pci_restore_msi_state() directly writes the MSI/MSI-X related registers
via MMIO. On a physical machine, this works perfectly; for a Linux VM
running on a hypervisor, which typically enables IOMMU interrupt remapping,
the hypervisor usually should trap and emulate the MMIO accesses in order
to re-create the necessary interrupt remapping table entries in the IOMMU,
otherwise the interrupts can not work in the VM after hibernation.
Hyper-V is different from other hypervisors in that it does not trap and
emulate the MMIO accesses, and instead it uses a para-virtualized method,
which requires the VM to call hv_compose_msi_msg() to notify the hypervisor
of the info that would be passed to the hypervisor in the case of the
trap-and-emulate method. This is not an issue to a lot of PCI device
drivers, which destroy and re-create the interrupts across hibernation, so
hv_compose_msi_msg() is called automatically. However, some PCI device
drivers (e.g. the in-tree GPU driver nouveau and the out-of-tree Nvidia
proprietary GPU driver) do not destroy and re-create MSI/MSI-X interrupts
across hibernation, so hv_pci_resume() has to call hv_compose_msi_msg(),
otherwise the PCI device drivers can no longer receive interrupts after
the VM resumes from hibernation.
Hyper-V is also different in that chip->irq_unmask() may fail in a
Linux VM running on Hyper-V (on a physical machine, chip->irq_unmask()
can not fail because unmasking an MSI/MSI-X register just means an MMIO
write): during hibernation, when a CPU is offlined, the kernel tries
to move the interrupt to the remaining CPUs that haven't been offlined
yet. In this case, hv_irq_unmask() -> hv_do_hypercall() always fails
because the vmbus channel has been closed: here the early "return" in
hv_irq_unmask() means the pci_msi_unmask_irq() is not called, i.e. the
desc->masked remains "true", so later after hibernation, the MSI interrupt
always remains masked, which is incorrect. Refer to cpu_disable_common()
-> fixup_irqs() -> irq_migrate_all_off_this_cpu() -> migrate_one_irq():
static bool migrate_one_irq(struct irq_desc *desc)
{
...
if (maskchip && chip->irq_mask)
chip->irq_mask(d);
...
err = irq_do_set_affinity(d, affinity, false);
...
if (maskchip && chip->irq_unmask)
chip->irq_unmask(d);
Fix the issue by calling pci_msi_unmask_irq() unconditionally in
hv_irq_unmask(). Also suppress the error message for hibernation because
the hypercall failure during hibernation does not matter (at this time
all the devices have been frozen). Note: the correct affinity info is
still updated into the irqdata data structure in migrate_one_irq() ->
irq_do_set_affinity() -> hv_set_affinity(), so later when the VM
resumes, hv_pci_restore_msi_state() is able to correctly restore
the interrupt with the correct affinity.
Link: https://lore.kernel.org/r/20201002085158.9168-1-decui@microsoft.com
Fixes: ac82fc832708 ("PCI: hv: Add hibernation support")
Signed-off-by: Dexuan Cui <decui@microsoft.com>
Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Reviewed-by: Jake Oshins <jakeo@microsoft.com>
2020-10-02 01:51:58 -07:00
|
|
|
|
2025-03-19 11:56:55 +01:00
|
|
|
|
|
|
|
|
|
PCI: hv: Fix hibernation in case interrupts are not re-created
pci_restore_msi_state() directly writes the MSI/MSI-X related registers
via MMIO. On a physical machine, this works perfectly; for a Linux VM
running on a hypervisor, which typically enables IOMMU interrupt remapping,
the hypervisor usually should trap and emulate the MMIO accesses in order
to re-create the necessary interrupt remapping table entries in the IOMMU,
otherwise the interrupts can not work in the VM after hibernation.
Hyper-V is different from other hypervisors in that it does not trap and
emulate the MMIO accesses, and instead it uses a para-virtualized method,
which requires the VM to call hv_compose_msi_msg() to notify the hypervisor
of the info that would be passed to the hypervisor in the case of the
trap-and-emulate method. This is not an issue to a lot of PCI device
drivers, which destroy and re-create the interrupts across hibernation, so
hv_compose_msi_msg() is called automatically. However, some PCI device
drivers (e.g. the in-tree GPU driver nouveau and the out-of-tree Nvidia
proprietary GPU driver) do not destroy and re-create MSI/MSI-X interrupts
across hibernation, so hv_pci_resume() has to call hv_compose_msi_msg(),
otherwise the PCI device drivers can no longer receive interrupts after
the VM resumes from hibernation.
Hyper-V is also different in that chip->irq_unmask() may fail in a
Linux VM running on Hyper-V (on a physical machine, chip->irq_unmask()
can not fail because unmasking an MSI/MSI-X register just means an MMIO
write): during hibernation, when a CPU is offlined, the kernel tries
to move the interrupt to the remaining CPUs that haven't been offlined
yet. In this case, hv_irq_unmask() -> hv_do_hypercall() always fails
because the vmbus channel has been closed: here the early "return" in
hv_irq_unmask() means the pci_msi_unmask_irq() is not called, i.e. the
desc->masked remains "true", so later after hibernation, the MSI interrupt
always remains masked, which is incorrect. Refer to cpu_disable_common()
-> fixup_irqs() -> irq_migrate_all_off_this_cpu() -> migrate_one_irq():
static bool migrate_one_irq(struct irq_desc *desc)
{
...
if (maskchip && chip->irq_mask)
chip->irq_mask(d);
...
err = irq_do_set_affinity(d, affinity, false);
...
if (maskchip && chip->irq_unmask)
chip->irq_unmask(d);
Fix the issue by calling pci_msi_unmask_irq() unconditionally in
hv_irq_unmask(). Also suppress the error message for hibernation because
the hypercall failure during hibernation does not matter (at this time
all the devices have been frozen). Note: the correct affinity info is
still updated into the irqdata data structure in migrate_one_irq() ->
irq_do_set_affinity() -> hv_set_affinity(), so later when the VM
resumes, hv_pci_restore_msi_state() is able to correctly restore
the interrupt with the correct affinity.
Link: https://lore.kernel.org/r/20201002085158.9168-1-decui@microsoft.com
Fixes: ac82fc832708 ("PCI: hv: Add hibernation support")
Signed-off-by: Dexuan Cui <decui@microsoft.com>
Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Reviewed-by: Jake Oshins <jakeo@microsoft.com>
2020-10-02 01:51:58 -07:00
|
|
|
|
|
|
|
|
|
2025-03-19 11:56:55 +01:00
|
|
|
|
PCI: hv: Fix hibernation in case interrupts are not re-created
pci_restore_msi_state() directly writes the MSI/MSI-X related registers
via MMIO. On a physical machine, this works perfectly; for a Linux VM
running on a hypervisor, which typically enables IOMMU interrupt remapping,
the hypervisor usually should trap and emulate the MMIO accesses in order
to re-create the necessary interrupt remapping table entries in the IOMMU,
otherwise the interrupts can not work in the VM after hibernation.
Hyper-V is different from other hypervisors in that it does not trap and
emulate the MMIO accesses, and instead it uses a para-virtualized method,
which requires the VM to call hv_compose_msi_msg() to notify the hypervisor
of the info that would be passed to the hypervisor in the case of the
trap-and-emulate method. This is not an issue to a lot of PCI device
drivers, which destroy and re-create the interrupts across hibernation, so
hv_compose_msi_msg() is called automatically. However, some PCI device
drivers (e.g. the in-tree GPU driver nouveau and the out-of-tree Nvidia
proprietary GPU driver) do not destroy and re-create MSI/MSI-X interrupts
across hibernation, so hv_pci_resume() has to call hv_compose_msi_msg(),
otherwise the PCI device drivers can no longer receive interrupts after
the VM resumes from hibernation.
Hyper-V is also different in that chip->irq_unmask() may fail in a
Linux VM running on Hyper-V (on a physical machine, chip->irq_unmask()
can not fail because unmasking an MSI/MSI-X register just means an MMIO
write): during hibernation, when a CPU is offlined, the kernel tries
to move the interrupt to the remaining CPUs that haven't been offlined
yet. In this case, hv_irq_unmask() -> hv_do_hypercall() always fails
because the vmbus channel has been closed: here the early "return" in
hv_irq_unmask() means the pci_msi_unmask_irq() is not called, i.e. the
desc->masked remains "true", so later after hibernation, the MSI interrupt
always remains masked, which is incorrect. Refer to cpu_disable_common()
-> fixup_irqs() -> irq_migrate_all_off_this_cpu() -> migrate_one_irq():
static bool migrate_one_irq(struct irq_desc *desc)
{
...
if (maskchip && chip->irq_mask)
chip->irq_mask(d);
...
err = irq_do_set_affinity(d, affinity, false);
...
if (maskchip && chip->irq_unmask)
chip->irq_unmask(d);
Fix the issue by calling pci_msi_unmask_irq() unconditionally in
hv_irq_unmask(). Also suppress the error message for hibernation because
the hypercall failure during hibernation does not matter (at this time
all the devices have been frozen). Note: the correct affinity info is
still updated into the irqdata data structure in migrate_one_irq() ->
irq_do_set_affinity() -> hv_set_affinity(), so later when the VM
resumes, hv_pci_restore_msi_state() is able to correctly restore
the interrupt with the correct affinity.
Link: https://lore.kernel.org/r/20201002085158.9168-1-decui@microsoft.com
Fixes: ac82fc832708 ("PCI: hv: Add hibernation support")
Signed-off-by: Dexuan Cui <decui@microsoft.com>
Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Reviewed-by: Jake Oshins <jakeo@microsoft.com>
2020-10-02 01:51:58 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2021-07-27 02:06:54 +08:00
|
|
|
|
PCI: hv: Fix hibernation in case interrupts are not re-created
pci_restore_msi_state() directly writes the MSI/MSI-X related registers
via MMIO. On a physical machine, this works perfectly; for a Linux VM
running on a hypervisor, which typically enables IOMMU interrupt remapping,
the hypervisor usually should trap and emulate the MMIO accesses in order
to re-create the necessary interrupt remapping table entries in the IOMMU,
otherwise the interrupts can not work in the VM after hibernation.
Hyper-V is different from other hypervisors in that it does not trap and
emulate the MMIO accesses, and instead it uses a para-virtualized method,
which requires the VM to call hv_compose_msi_msg() to notify the hypervisor
of the info that would be passed to the hypervisor in the case of the
trap-and-emulate method. This is not an issue to a lot of PCI device
drivers, which destroy and re-create the interrupts across hibernation, so
hv_compose_msi_msg() is called automatically. However, some PCI device
drivers (e.g. the in-tree GPU driver nouveau and the out-of-tree Nvidia
proprietary GPU driver) do not destroy and re-create MSI/MSI-X interrupts
across hibernation, so hv_pci_resume() has to call hv_compose_msi_msg(),
otherwise the PCI device drivers can no longer receive interrupts after
the VM resumes from hibernation.
Hyper-V is also different in that chip->irq_unmask() may fail in a
Linux VM running on Hyper-V (on a physical machine, chip->irq_unmask()
can not fail because unmasking an MSI/MSI-X register just means an MMIO
write): during hibernation, when a CPU is offlined, the kernel tries
to move the interrupt to the remaining CPUs that haven't been offlined
yet. In this case, hv_irq_unmask() -> hv_do_hypercall() always fails
because the vmbus channel has been closed: here the early "return" in
hv_irq_unmask() means the pci_msi_unmask_irq() is not called, i.e. the
desc->masked remains "true", so later after hibernation, the MSI interrupt
always remains masked, which is incorrect. Refer to cpu_disable_common()
-> fixup_irqs() -> irq_migrate_all_off_this_cpu() -> migrate_one_irq():
static bool migrate_one_irq(struct irq_desc *desc)
{
...
if (maskchip && chip->irq_mask)
chip->irq_mask(d);
...
err = irq_do_set_affinity(d, affinity, false);
...
if (maskchip && chip->irq_unmask)
chip->irq_unmask(d);
Fix the issue by calling pci_msi_unmask_irq() unconditionally in
hv_irq_unmask(). Also suppress the error message for hibernation because
the hypercall failure during hibernation does not matter (at this time
all the devices have been frozen). Note: the correct affinity info is
still updated into the irqdata data structure in migrate_one_irq() ->
irq_do_set_affinity() -> hv_set_affinity(), so later when the VM
resumes, hv_pci_restore_msi_state() is able to correctly restore
the interrupt with the correct affinity.
Link: https://lore.kernel.org/r/20201002085158.9168-1-decui@microsoft.com
Fixes: ac82fc832708 ("PCI: hv: Add hibernation support")
Signed-off-by: Dexuan Cui <decui@microsoft.com>
Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Reviewed-by: Jake Oshins <jakeo@microsoft.com>
2020-10-02 01:51:58 -07:00
|
|
|
|
|
|
|
|
|
PCI: hv: Add hibernation support
Add suspend() and resume() functions so that Hyper-V virtual PCI devices
are handled properly when the VM hibernates and resumes from
hibernation.
Note that the suspend() function must make sure there are no pending
work items before calling vmbus_close(), since it runs in a process
context as a callback in dpm_suspend(). When it starts to run, the
channel callback hv_pci_onchannelcallback(), which runs in a tasklet
context, can be still running concurrently and scheduling new work items
onto hbus->wq in hv_pci_devices_present() and hv_pci_eject_device(), and
the work item handlers can access the vmbus channel, which can be being
closed by hv_pci_suspend(), e.g. the work item handler
pci_devices_present_work() -> new_pcichild_device() writes to the vmbus
channel.
To eliminate the race, hv_pci_suspend() disables the channel callback
tasklet, sets hbus->state to hv_pcibus_removing, and re-enables the
tasklet. This way, when hv_pci_suspend() proceeds, it knows that no new
work item can be scheduled, and then it flushes hbus->wq and safely
closes the vmbus channel.
Signed-off-by: Dexuan Cui <decui@microsoft.com>
Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Reviewed-by: Michael Kelley <mikelley@microsoft.com>
2019-11-24 21:33:52 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2022-04-19 14:23:21 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
PCI: hv: Add hibernation support
Add suspend() and resume() functions so that Hyper-V virtual PCI devices
are handled properly when the VM hibernates and resumes from
hibernation.
Note that the suspend() function must make sure there are no pending
work items before calling vmbus_close(), since it runs in a process
context as a callback in dpm_suspend(). When it starts to run, the
channel callback hv_pci_onchannelcallback(), which runs in a tasklet
context, can be still running concurrently and scheduling new work items
onto hbus->wq in hv_pci_devices_present() and hv_pci_eject_device(), and
the work item handlers can access the vmbus channel, which can be being
closed by hv_pci_suspend(), e.g. the work item handler
pci_devices_present_work() -> new_pcichild_device() writes to the vmbus
channel.
To eliminate the race, hv_pci_suspend() disables the channel callback
tasklet, sets hbus->state to hv_pcibus_removing, and re-enables the
tasklet. This way, when hv_pci_suspend() proceeds, it knows that no new
work item can be scheduled, and then it flushes hbus->wq and safely
closes the vmbus channel.
Signed-off-by: Dexuan Cui <decui@microsoft.com>
Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Reviewed-by: Michael Kelley <mikelley@microsoft.com>
2019-11-24 21:33:52 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2019-11-24 21:33:53 -08:00
|
|
|
|
PCI: hv: Add hibernation support
Add suspend() and resume() functions so that Hyper-V virtual PCI devices
are handled properly when the VM hibernates and resumes from
hibernation.
Note that the suspend() function must make sure there are no pending
work items before calling vmbus_close(), since it runs in a process
context as a callback in dpm_suspend(). When it starts to run, the
channel callback hv_pci_onchannelcallback(), which runs in a tasklet
context, can be still running concurrently and scheduling new work items
onto hbus->wq in hv_pci_devices_present() and hv_pci_eject_device(), and
the work item handlers can access the vmbus channel, which can be being
closed by hv_pci_suspend(), e.g. the work item handler
pci_devices_present_work() -> new_pcichild_device() writes to the vmbus
channel.
To eliminate the race, hv_pci_suspend() disables the channel callback
tasklet, sets hbus->state to hv_pcibus_removing, and re-enables the
tasklet. This way, when hv_pci_suspend() proceeds, it knows that no new
work item can be scheduled, and then it flushes hbus->wq and safely
closes the vmbus channel.
Signed-off-by: Dexuan Cui <decui@microsoft.com>
Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Reviewed-by: Michael Kelley <mikelley@microsoft.com>
2019-11-24 21:33:52 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
PCI: hv: Add a per-bus mutex state_lock
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@microsoft.com>
Reviewed-by: Michael Kelley <mikelley@microsoft.com>
Acked-by: Lorenzo Pieralisi <lpieralisi@kernel.org>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20230615044451.5580-6-decui@microsoft.com
Signed-off-by: Wei Liu <wei.liu@kernel.org>
2023-06-14 21:44:51 -07:00
|
|
|
|
|
|
|
|
|
PCI: hv: Add hibernation support
Add suspend() and resume() functions so that Hyper-V virtual PCI devices
are handled properly when the VM hibernates and resumes from
hibernation.
Note that the suspend() function must make sure there are no pending
work items before calling vmbus_close(), since it runs in a process
context as a callback in dpm_suspend(). When it starts to run, the
channel callback hv_pci_onchannelcallback(), which runs in a tasklet
context, can be still running concurrently and scheduling new work items
onto hbus->wq in hv_pci_devices_present() and hv_pci_eject_device(), and
the work item handlers can access the vmbus channel, which can be being
closed by hv_pci_suspend(), e.g. the work item handler
pci_devices_present_work() -> new_pcichild_device() writes to the vmbus
channel.
To eliminate the race, hv_pci_suspend() disables the channel callback
tasklet, sets hbus->state to hv_pcibus_removing, and re-enables the
tasklet. This way, when hv_pci_suspend() proceeds, it knows that no new
work item can be scheduled, and then it flushes hbus->wq and safely
closes the vmbus channel.
Signed-off-by: Dexuan Cui <decui@microsoft.com>
Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Reviewed-by: Michael Kelley <mikelley@microsoft.com>
2019-11-24 21:33:52 -08:00
|
|
|
|
|
|
|
|
|
PCI: hv: Add a per-bus mutex state_lock
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@microsoft.com>
Reviewed-by: Michael Kelley <mikelley@microsoft.com>
Acked-by: Lorenzo Pieralisi <lpieralisi@kernel.org>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20230615044451.5580-6-decui@microsoft.com
Signed-off-by: Wei Liu <wei.liu@kernel.org>
2023-06-14 21:44:51 -07:00
|
|
|
|
PCI: hv: Add hibernation support
Add suspend() and resume() functions so that Hyper-V virtual PCI devices
are handled properly when the VM hibernates and resumes from
hibernation.
Note that the suspend() function must make sure there are no pending
work items before calling vmbus_close(), since it runs in a process
context as a callback in dpm_suspend(). When it starts to run, the
channel callback hv_pci_onchannelcallback(), which runs in a tasklet
context, can be still running concurrently and scheduling new work items
onto hbus->wq in hv_pci_devices_present() and hv_pci_eject_device(), and
the work item handlers can access the vmbus channel, which can be being
closed by hv_pci_suspend(), e.g. the work item handler
pci_devices_present_work() -> new_pcichild_device() writes to the vmbus
channel.
To eliminate the race, hv_pci_suspend() disables the channel callback
tasklet, sets hbus->state to hv_pcibus_removing, and re-enables the
tasklet. This way, when hv_pci_suspend() proceeds, it knows that no new
work item can be scheduled, and then it flushes hbus->wq and safely
closes the vmbus channel.
Signed-off-by: Dexuan Cui <decui@microsoft.com>
Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Reviewed-by: Michael Kelley <mikelley@microsoft.com>
2019-11-24 21:33:52 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
PCI: hv: Add a per-bus mutex state_lock
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@microsoft.com>
Reviewed-by: Michael Kelley <mikelley@microsoft.com>
Acked-by: Lorenzo Pieralisi <lpieralisi@kernel.org>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20230615044451.5580-6-decui@microsoft.com
Signed-off-by: Wei Liu <wei.liu@kernel.org>
2023-06-14 21:44:51 -07:00
|
|
|
|
PCI: hv: Add hibernation support
Add suspend() and resume() functions so that Hyper-V virtual PCI devices
are handled properly when the VM hibernates and resumes from
hibernation.
Note that the suspend() function must make sure there are no pending
work items before calling vmbus_close(), since it runs in a process
context as a callback in dpm_suspend(). When it starts to run, the
channel callback hv_pci_onchannelcallback(), which runs in a tasklet
context, can be still running concurrently and scheduling new work items
onto hbus->wq in hv_pci_devices_present() and hv_pci_eject_device(), and
the work item handlers can access the vmbus channel, which can be being
closed by hv_pci_suspend(), e.g. the work item handler
pci_devices_present_work() -> new_pcichild_device() writes to the vmbus
channel.
To eliminate the race, hv_pci_suspend() disables the channel callback
tasklet, sets hbus->state to hv_pcibus_removing, and re-enables the
tasklet. This way, when hv_pci_suspend() proceeds, it knows that no new
work item can be scheduled, and then it flushes hbus->wq and safely
closes the vmbus channel.
Signed-off-by: Dexuan Cui <decui@microsoft.com>
Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Reviewed-by: Michael Kelley <mikelley@microsoft.com>
2019-11-24 21:33:52 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
PCI: hv: Fix hibernation in case interrupts are not re-created
pci_restore_msi_state() directly writes the MSI/MSI-X related registers
via MMIO. On a physical machine, this works perfectly; for a Linux VM
running on a hypervisor, which typically enables IOMMU interrupt remapping,
the hypervisor usually should trap and emulate the MMIO accesses in order
to re-create the necessary interrupt remapping table entries in the IOMMU,
otherwise the interrupts can not work in the VM after hibernation.
Hyper-V is different from other hypervisors in that it does not trap and
emulate the MMIO accesses, and instead it uses a para-virtualized method,
which requires the VM to call hv_compose_msi_msg() to notify the hypervisor
of the info that would be passed to the hypervisor in the case of the
trap-and-emulate method. This is not an issue to a lot of PCI device
drivers, which destroy and re-create the interrupts across hibernation, so
hv_compose_msi_msg() is called automatically. However, some PCI device
drivers (e.g. the in-tree GPU driver nouveau and the out-of-tree Nvidia
proprietary GPU driver) do not destroy and re-create MSI/MSI-X interrupts
across hibernation, so hv_pci_resume() has to call hv_compose_msi_msg(),
otherwise the PCI device drivers can no longer receive interrupts after
the VM resumes from hibernation.
Hyper-V is also different in that chip->irq_unmask() may fail in a
Linux VM running on Hyper-V (on a physical machine, chip->irq_unmask()
can not fail because unmasking an MSI/MSI-X register just means an MMIO
write): during hibernation, when a CPU is offlined, the kernel tries
to move the interrupt to the remaining CPUs that haven't been offlined
yet. In this case, hv_irq_unmask() -> hv_do_hypercall() always fails
because the vmbus channel has been closed: here the early "return" in
hv_irq_unmask() means the pci_msi_unmask_irq() is not called, i.e. the
desc->masked remains "true", so later after hibernation, the MSI interrupt
always remains masked, which is incorrect. Refer to cpu_disable_common()
-> fixup_irqs() -> irq_migrate_all_off_this_cpu() -> migrate_one_irq():
static bool migrate_one_irq(struct irq_desc *desc)
{
...
if (maskchip && chip->irq_mask)
chip->irq_mask(d);
...
err = irq_do_set_affinity(d, affinity, false);
...
if (maskchip && chip->irq_unmask)
chip->irq_unmask(d);
Fix the issue by calling pci_msi_unmask_irq() unconditionally in
hv_irq_unmask(). Also suppress the error message for hibernation because
the hypercall failure during hibernation does not matter (at this time
all the devices have been frozen). Note: the correct affinity info is
still updated into the irqdata data structure in migrate_one_irq() ->
irq_do_set_affinity() -> hv_set_affinity(), so later when the VM
resumes, hv_pci_restore_msi_state() is able to correctly restore
the interrupt with the correct affinity.
Link: https://lore.kernel.org/r/20201002085158.9168-1-decui@microsoft.com
Fixes: ac82fc832708 ("PCI: hv: Add hibernation support")
Signed-off-by: Dexuan Cui <decui@microsoft.com>
Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Reviewed-by: Jake Oshins <jakeo@microsoft.com>
2020-10-02 01:51:58 -07:00
|
|
|
|
|
|
|
|
|
PCI: hv: Add hibernation support
Add suspend() and resume() functions so that Hyper-V virtual PCI devices
are handled properly when the VM hibernates and resumes from
hibernation.
Note that the suspend() function must make sure there are no pending
work items before calling vmbus_close(), since it runs in a process
context as a callback in dpm_suspend(). When it starts to run, the
channel callback hv_pci_onchannelcallback(), which runs in a tasklet
context, can be still running concurrently and scheduling new work items
onto hbus->wq in hv_pci_devices_present() and hv_pci_eject_device(), and
the work item handlers can access the vmbus channel, which can be being
closed by hv_pci_suspend(), e.g. the work item handler
pci_devices_present_work() -> new_pcichild_device() writes to the vmbus
channel.
To eliminate the race, hv_pci_suspend() disables the channel callback
tasklet, sets hbus->state to hv_pcibus_removing, and re-enables the
tasklet. This way, when hv_pci_suspend() proceeds, it knows that no new
work item can be scheduled, and then it flushes hbus->wq and safely
closes the vmbus channel.
Signed-off-by: Dexuan Cui <decui@microsoft.com>
Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Reviewed-by: Michael Kelley <mikelley@microsoft.com>
2019-11-24 21:33:52 -08:00
|
|
|
|
PCI: hv: Add a per-bus mutex state_lock
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@microsoft.com>
Reviewed-by: Michael Kelley <mikelley@microsoft.com>
Acked-by: Lorenzo Pieralisi <lpieralisi@kernel.org>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20230615044451.5580-6-decui@microsoft.com
Signed-off-by: Wei Liu <wei.liu@kernel.org>
2023-06-14 21:44:51 -07:00
|
|
|
|
PCI: hv: Add hibernation support
Add suspend() and resume() functions so that Hyper-V virtual PCI devices
are handled properly when the VM hibernates and resumes from
hibernation.
Note that the suspend() function must make sure there are no pending
work items before calling vmbus_close(), since it runs in a process
context as a callback in dpm_suspend(). When it starts to run, the
channel callback hv_pci_onchannelcallback(), which runs in a tasklet
context, can be still running concurrently and scheduling new work items
onto hbus->wq in hv_pci_devices_present() and hv_pci_eject_device(), and
the work item handlers can access the vmbus channel, which can be being
closed by hv_pci_suspend(), e.g. the work item handler
pci_devices_present_work() -> new_pcichild_device() writes to the vmbus
channel.
To eliminate the race, hv_pci_suspend() disables the channel callback
tasklet, sets hbus->state to hv_pcibus_removing, and re-enables the
tasklet. This way, when hv_pci_suspend() proceeds, it knows that no new
work item can be scheduled, and then it flushes hbus->wq and safely
closes the vmbus channel.
Signed-off-by: Dexuan Cui <decui@microsoft.com>
Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Reviewed-by: Michael Kelley <mikelley@microsoft.com>
2019-11-24 21:33:52 -08:00
|
|
|
|
PCI: hv: Add a per-bus mutex state_lock
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@microsoft.com>
Reviewed-by: Michael Kelley <mikelley@microsoft.com>
Acked-by: Lorenzo Pieralisi <lpieralisi@kernel.org>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20230615044451.5580-6-decui@microsoft.com
Signed-off-by: Wei Liu <wei.liu@kernel.org>
2023-06-14 21:44:51 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
PCI: hv: Add hibernation support
Add suspend() and resume() functions so that Hyper-V virtual PCI devices
are handled properly when the VM hibernates and resumes from
hibernation.
Note that the suspend() function must make sure there are no pending
work items before calling vmbus_close(), since it runs in a process
context as a callback in dpm_suspend(). When it starts to run, the
channel callback hv_pci_onchannelcallback(), which runs in a tasklet
context, can be still running concurrently and scheduling new work items
onto hbus->wq in hv_pci_devices_present() and hv_pci_eject_device(), and
the work item handlers can access the vmbus channel, which can be being
closed by hv_pci_suspend(), e.g. the work item handler
pci_devices_present_work() -> new_pcichild_device() writes to the vmbus
channel.
To eliminate the race, hv_pci_suspend() disables the channel callback
tasklet, sets hbus->state to hv_pcibus_removing, and re-enables the
tasklet. This way, when hv_pci_suspend() proceeds, it knows that no new
work item can be scheduled, and then it flushes hbus->wq and safely
closes the vmbus channel.
Signed-off-by: Dexuan Cui <decui@microsoft.com>
Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Reviewed-by: Michael Kelley <mikelley@microsoft.com>
2019-11-24 21:33:52 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
PCI: hv: Add hibernation support
Add suspend() and resume() functions so that Hyper-V virtual PCI devices
are handled properly when the VM hibernates and resumes from
hibernation.
Note that the suspend() function must make sure there are no pending
work items before calling vmbus_close(), since it runs in a process
context as a callback in dpm_suspend(). When it starts to run, the
channel callback hv_pci_onchannelcallback(), which runs in a tasklet
context, can be still running concurrently and scheduling new work items
onto hbus->wq in hv_pci_devices_present() and hv_pci_eject_device(), and
the work item handlers can access the vmbus channel, which can be being
closed by hv_pci_suspend(), e.g. the work item handler
pci_devices_present_work() -> new_pcichild_device() writes to the vmbus
channel.
To eliminate the race, hv_pci_suspend() disables the channel callback
tasklet, sets hbus->state to hv_pcibus_removing, and re-enables the
tasklet. This way, when hv_pci_suspend() proceeds, it knows that no new
work item can be scheduled, and then it flushes hbus->wq and safely
closes the vmbus channel.
Signed-off-by: Dexuan Cui <decui@microsoft.com>
Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Reviewed-by: Michael Kelley <mikelley@microsoft.com>
2019-11-24 21:33:52 -08:00
|
|
|
|
|
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2019-08-22 05:05:41 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2022-01-05 11:32:35 -08:00
|
|
|
|
|
|
|
|
|
2021-05-25 16:17:33 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Drivers: hv: vmbus: Export hv_vmbus_exists() and use it in pci-hyperv
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 <mrathor@linux.microsoft.com>
Signed-off-by: Dexuan Cui <decui@microsoft.com>
Signed-off-by: Wei Liu <wei.liu@kernel.org>
2026-04-09 14:52:32 -07:00
|
|
|
|
2025-07-03 15:44:32 -07:00
|
|
|
|
|
|
|
|
|
2022-01-05 11:32:35 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2019-08-22 05:05:41 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-02-16 21:56:23 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|