hv_do_hypercall() assumes that we pass a segment from a physically
contiguous buffer. A buffer allocated on the stack may not work if
CONFIG_VMAP_STACK=y is set.
Use kmalloc() to allocate this buffer.
Reported-by: Haiyang Zhang <haiyangz@microsoft.com>
Signed-off-by: Long Li <longli@microsoft.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Acked-by: K. Y. Srinivasan <kys@microsoft.com>
After we send a PCI_EJECTION_COMPLETE message to the host, the host will
immediately send us a PCI_BUS_RELATIONS message with
relations->device_count == 0, so pci_devices_present_work(), running on
another thread, can find the being-ejected device, mark the
hpdev->reported_missing to true, and run list_move_tail()/list_del() for
the device -- this races hv_eject_device_work() -> list_del().
Move the list_del() in hv_eject_device_work() to an earlier place, i.e.,
before we send PCI_EJECTION_COMPLETE, so later the
pci_devices_present_work() can't see the device.
Signed-off-by: Dexuan Cui <decui@microsoft.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Jake Oshins <jakeo@microsoft.com>
Acked-by: K. Y. Srinivasan <kys@microsoft.com>
CC: Haiyang Zhang <haiyangz@microsoft.com>
CC: Vitaly Kuznetsov <vkuznets@redhat.com>
1. We don't really need such a big on-stack buffer when sending the
teardown_packet: vmbus_sendpacket() here only uses sizeof(struct
pci_message).
2. In the hot-remove case (PCI_EJECT), after we send PCI_EJECTION_COMPLETE
to the host, the host will send a RESCIND_CHANNEL message to us and the
host won't access the per-channel ringbuffer any longer, so we needn't send
PCI_RESOURCES_RELEASED/PCI_BUS_D0EXIT to the host, and we shouldn't expect
the host's completion message of PCI_BUS_D0EXIT, which will never come.
3. We should send PCI_BUS_D0EXIT after hv_send_resources_released().
Signed-off-by: Dexuan Cui <decui@microsoft.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Jake Oshins <jakeo@microsoft.com>
Acked-by: K. Y. Srinivasan <kys@microsoft.com>
CC: Haiyang Zhang <haiyangz@microsoft.com>
CC: Vitaly Kuznetsov <vkuznets@redhat.com>
We don't really need such a big on-stack buffer. vmbus_sendpacket() here
only uses sizeof(struct pci_child_message).
Signed-off-by: Dexuan Cui <decui@microsoft.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Jake Oshins <jakeo@microsoft.com>
Make hv_irq_mask() and hv_irq_unmask() static as they are only used in
pci-hyperv.c
This fixes a sparse warning.
Signed-off-by: Tobias Klauser <tklauser@distanz.ch>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Acked-by: K. Y. Srinivasan <kys@microsoft.com>
'completion_status' is used in some places, e.g.,
hv_pci_protocol_negotiation(), so we should make sure it's initialized in
error case too, though the error is unlikely here.
[bhelgaas: fix changelog typo and nearby whitespace]
Signed-off-by: Dexuan Cui <decui@microsoft.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Acked-by: KY Srinivasan <kys@microsoft.com>
CC: Jake Oshins <jakeo@microsoft.com>
CC: Haiyang Zhang <haiyangz@microsoft.com>
CC: Vitaly Kuznetsov <vkuznets@redhat.com>
Handle vmbus_sendpacket() failure in hv_compose_msi_msg().
I happened to find this when reading the code. I didn't get a real issue
however.
Signed-off-by: Dexuan Cui <decui@microsoft.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Acked-by: KY Srinivasan <kys@microsoft.com>
CC: Jake Oshins <jakeo@microsoft.com>
CC: Haiyang Zhang <haiyangz@microsoft.com>
CC: Vitaly Kuznetsov <vkuznets@redhat.com>
The 2 structs can use a zero-length array here, because dynamic memory of
the correct size is allocated in hv_pci_devices_present() and we don't need
this extra element.
No functional change.
Signed-off-by: Dexuan Cui <decui@microsoft.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Acked-by: KY Srinivasan <kys@microsoft.com>
CC: Jake Oshins <jakeo@microsoft.com>
CC: Haiyang Zhang <haiyangz@microsoft.com>
CC: Vitaly Kuznetsov <vkuznets@redhat.com>
Use zero-length array in struct pci_packet and rename struct pci_message's
field "message_type" to "type". This makes the code more readable.
No functionality change.
Signed-off-by: Dexuan Cui <decui@microsoft.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Acked-by: KY Srinivasan <kys@microsoft.com>
CC: Jake Oshins <jakeo@microsoft.com>
CC: Haiyang Zhang <haiyangz@microsoft.com>
CC: Vitaly Kuznetsov <vkuznets@redhat.com>
SR-IOV disabled from the host causes a memory leak. pci-hyperv usually
first receives a PCI_EJECT notification and then proceeds to delete the
hpdev list entry in hv_eject_device_work(). Later in hv_msi_free() since
the device is no longer on the device list hpdev is NULL and hv_msi_free
returns without freeing int_desc as part of hv_int_desc_free().
Signed-off-by: Cathy Avery <cavery@redhat.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Acked-by: Jake Oshins <jakeo@microsoft.com>
When we have an interrupt from the host we have a bit set in event page
indicating there are messages for the particular channel. We need to read
them all as we won't get signaled for what was on the queue before we
cleared the bit in vmbus_on_event(). This applies to all Hyper-V drivers
and the pass-through driver should do the same.
I did not meet any bugs; the issue was found by code inspection. We don't
have many events going through hv_pci_onchannelcallback(), which explains
why nobody reported the issue before.
While on it, fix handling non-zero vmbus_recvpacket_raw() return values by
dropping out. If the return value is not zero, it is wrong to inspect
buffer or bytes_recvd as these may contain invalid data.
Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Acked-by: Jake Oshins <jakeo@microsoft.com>
We don't free buffer on several code paths in hv_pci_onchannelcallback(),
put kfree() to the end of the function to fix the issue. Direct { kfree();
return; } can now be replaced with a simple 'break';
Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Acked-by: Jake Oshins <jakeo@microsoft.com>
Here's the big char and misc driver update for 4.7-rc1.
Lots of different tiny driver subsystems have updates here with new
drivers and functionality. Details in the shortlog.
All have been in linux-next with no reported issues for a while.
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v2
iEYEABECAAYFAlc/0YYACgkQMUfUDdst+ynmtACeLpLLKZsy1v7WfkW92cLSOPBD
2C8AoLFPKoh55rlOJrNz3bW9ANAaOloX
=/nsL
-----END PGP SIGNATURE-----
Merge tag 'char-misc-4.7-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/char-misc
Pull char / misc driver updates from Greg KH:
"Here's the big char and misc driver update for 4.7-rc1.
Lots of different tiny driver subsystems have updates here with new
drivers and functionality. Details in the shortlog.
All have been in linux-next with no reported issues for a while"
* tag 'char-misc-4.7-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/char-misc: (125 commits)
mcb: Delete num_cells variable which is not required
mcb: Fixed bar number assignment for the gdd
mcb: Replace ioremap and request_region with the devm version
mcb: Implement bus->dev.release callback
mcb: export bus information via sysfs
mcb: Correctly initialize the bus's device
mei: bus: call mei_cl_read_start under device lock
coresight: etb10: adjust read pointer only when needed
coresight: configuring ETF in FIFO mode when acting as link
coresight: tmc: implementing TMC-ETF AUX space API
coresight: moving struct cs_buffers to header file
coresight: tmc: keep track of memory width
coresight: tmc: make sysFS and Perf mode mutually exclusive
coresight: tmc: dump system memory content only when needed
coresight: tmc: adding mode of operation for link/sinks
coresight: tmc: getting rid of multiple read access
coresight: tmc: allocating memory when needed
coresight: tmc: making prepare/unprepare functions generic
coresight: tmc: splitting driver in ETB/ETF and ETR components
coresight: tmc: cleaning up header file
...
I'm trying to pass-through Broadcom BCM5720 NIC (Dell device 1f5b) on a
Dell R720 server. Everything works fine when the target VM has only one
CPU, but SMP guests reboot when the NIC driver accesses PCI config space
with hv_pcifront_read_config()/hv_pcifront_write_config(). The reboot
appears to be induced by the hypervisor and no crash is observed. Windows
event logs are not helpful at all ('Virtual machine ... has quit
unexpectedly'). The particular access point is always different and
putting debug between them (printk/mdelay/...) moves the issue further
away. The server model affects the issue as well: on Dell R420 I'm able to
pass-through BCM5720 NIC to SMP guests without issues.
While I'm obviously failing to reveal the essence of the issue I was able
to come up with a (possible) solution: if explicit barriers are added to
hv_pcifront_read_config()/hv_pcifront_write_config() the issue goes away.
The essential minimum is rmb() at the end on _hv_pcifront_read_config() and
wmb() at the end of _hv_pcifront_write_config() but I'm not confident it
will be sufficient for all hardware. I suggest the following barriers:
1) wmb()/mb() between choosing the function and writing to its space.
2) mb() before releasing the spinlock in both _hv_pcifront_read_config()/
_hv_pcifront_write_config() to ensure that consecutive reads/writes to
the space won't get re-ordered as drivers may count on that.
Config space access is not supposed to be performance-critical so these
explicit barriers should not cause any slowdown.
[bhelgaas: use Linux "barriers" terminology]
Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Acked-by: Jake Oshins <jakeo@microsoft.com>
Kernel hang is observed when pci-hyperv module is release with device
drivers still attached. E.g., when I do 'rmmod pci_hyperv' with BCM5720
device pass-through-ed (tg3 module) I see the following:
NMI watchdog: BUG: soft lockup - CPU#1 stuck for 22s! [rmmod:2104]
...
Call Trace:
[<ffffffffa0641487>] tg3_read_mem+0x87/0x100 [tg3]
[<ffffffffa063f000>] ? 0xffffffffa063f000
[<ffffffffa0644375>] tg3_poll_fw+0x85/0x150 [tg3]
[<ffffffffa0649877>] tg3_chip_reset+0x357/0x8c0 [tg3]
[<ffffffffa064ca8b>] tg3_halt+0x3b/0x190 [tg3]
[<ffffffffa0657611>] tg3_stop+0x171/0x230 [tg3]
...
[<ffffffffa064c550>] tg3_remove_one+0x90/0x140 [tg3]
[<ffffffff813bee59>] pci_device_remove+0x39/0xc0
[<ffffffff814a3201>] __device_release_driver+0xa1/0x160
[<ffffffff814a32e3>] device_release_driver+0x23/0x30
[<ffffffff813b794a>] pci_stop_bus_device+0x8a/0xa0
[<ffffffff813b7ab6>] pci_stop_root_bus+0x36/0x60
[<ffffffffa02c3f38>] hv_pci_remove+0x238/0x260 [pci_hyperv]
The problem seems to be that we report local resources release before
stopping the bus and removing devices from it and device drivers may try to
perform some operations with these resources on shutdown. Move resources
release report after we do pci_stop_root_bus().
Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Acked-by: Jake Oshins <jakeo@microsoft.com>
This patch modifies all the callers of vmbus_mmio_allocate()
to call vmbus_mmio_free() instead of release_mem_region().
Signed-off-by: Jake Oshins <jakeo@microsoft.com>
Signed-off-by: K. Y. Srinivasan <kys@microsoft.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Add a new driver which exposes a root PCI bus whenever a PCI Express device
is passed through to a guest VM under Hyper-V. The device can be single-
or multi-function. The interrupts for the devices are managed by an IRQ
domain, implemented within the driver.
[bhelgaas: fold in race condition fix (http://lkml.kernel.org/r/1456340196-13717-1-git-send-email-jakeo@microsoft.com)]
Signed-off-by: Jake Oshins <jakeo@microsoft.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
