This patch introduces two types of GPADL: HV_GPADL_{BUFFER, RING}. The
types of GPADL are purely the concept in the guest, IOW the hypervisor
treat them as the same.
The reason of introducing the types for GPADL is to support guests whose
page size is not 4k (the page size of Hyper-V hypervisor). In these
guests, both the headers and the data parts of the ringbuffers need to
be aligned to the PAGE_SIZE, because 1) some of the ringbuffers will be
mapped into userspace and 2) we use "double mapping" mechanism to
support fast wrap-around, and "double mapping" relies on ringbuffers
being page-aligned. However, the Hyper-V hypervisor only uses 4k
(HV_HYP_PAGE_SIZE) headers. Our solution to this is that we always make
the headers of ringbuffers take one guest page and when GPADL is
established between the guest and hypervisor, the only first 4k of
header is used. To handle this special case, we need the types of GPADL
to differ different guest memory usage for GPADL.
Type enum is introduced along with several general interfaces to
describe the differences between normal buffer GPADL and ringbuffer
GPADL.
Signed-off-by: Boqun Feng <boqun.feng@gmail.com>
Reviewed-by: Michael Kelley <mikelley@microsoft.com>
Link: https://lore.kernel.org/r/20200916034817.30282-4-boqun.feng@gmail.com
Signed-off-by: Wei Liu <wei.liu@kernel.org>
init_vp_index() uses the (per-node) hv_numa_map[] masks to record the
CPUs allocated for channel interrupts at a given time, and distribute
the performance-critical channels across the available CPUs: in part.,
the mask of "candidate" target CPUs in a given NUMA node, for a newly
offered channel, is determined by XOR-ing the node's CPU mask and the
node's hv_numa_map. This operation/mechanism assumes that no offline
CPUs is set in the hv_numa_map mask, an assumption that does not hold
since such mask is currently not updated when a channel is removed or
assigned to a different CPU.
To address the issues described above, this adds hooks in the channel
removal path (hv_process_channel_removal()) and in target_cpu_store()
in order to clear, resp. to update, the hv_numa_map[] masks as needed.
This also adds a (missed) update of the masks in init_vp_index() (cf.,
e.g., the memory-allocation failure path in this function).
Like in the case of init_vp_index(), such hooks require to determine
if the given channel is performance critical. init_vp_index() does
this by parsing the channel's offer, it can not rely on the device
data structure (device_obj) to retrieve such information because the
device data structure has not been allocated/linked with the channel
by the time that init_vp_index() executes. A similar situation may
hold in hv_is_alloced_cpu() (defined below); the adopted approach is
to "cache" the device type of the channel, as computed by parsing the
channel's offer, in the channel structure itself.
Fixes: 7527810573 ("Drivers: hv: vmbus: Introduce the CHANNELMSG_MODIFYCHANNEL message type")
Signed-off-by: Andrea Parri (Microsoft) <parri.andrea@gmail.com>
Reviewed-by: Michael Kelley <mikelley@microsoft.com>
Link: https://lore.kernel.org/r/20200522171901.204127-3-parri.andrea@gmail.com
Signed-off-by: Wei Liu <wei.liu@kernel.org>
The current codebase makes use of the zero-length array language
extension to the C90 standard, but the preferred mechanism to declare
variable-length types such as these ones is a flexible array member[1][2],
introduced in C99:
struct foo {
int stuff;
struct boo array[];
};
By making use of the mechanism above, we will get a compiler warning
in case the flexible array does not occur last in the structure, which
will help us prevent some kind of undefined behavior bugs from being
inadvertently introduced[3] to the codebase from now on.
Also, notice that, dynamic memory allocations won't be affected by
this change:
"Flexible array members have incomplete type, and so the sizeof operator
may not be applied. As a quirk of the original implementation of
zero-length arrays, sizeof evaluates to zero."[1]
sizeof(flexible-array-member) triggers a warning because flexible array
members have incomplete type[1]. There are some instances of code in
which the sizeof operator is being incorrectly/erroneously applied to
zero-length arrays and the result is zero. Such instances may be hiding
some bugs. So, this work (flexible-array member conversions) will also
help to get completely rid of those sorts of issues.
This issue was found with the help of Coccinelle.
[1] https://gcc.gnu.org/onlinedocs/gcc/Zero-Length.html
[2] https://github.com/KSPP/linux/issues/21
[3] commit 7649773293 ("cxgb3/l2t: Fix undefined behaviour")
Signed-off-by: Gustavo A. R. Silva <gustavoars@kernel.org>
Link: https://lore.kernel.org/r/20200507185323.GA14416@embeddedor
Signed-off-by: Wei Liu <wei.liu@kernel.org>
VMBus version 4.1 and later support the CHANNELMSG_MODIFYCHANNEL(22)
message type which can be used to request Hyper-V to change the vCPU
that a channel will interrupt.
Introduce the CHANNELMSG_MODIFYCHANNEL message type, and define the
vmbus_send_modifychannel() function to send CHANNELMSG_MODIFYCHANNEL
requests to the host via a hypercall. The function is then used to
define a sysfs "store" operation, which allows to change the (v)CPU
the channel will interrupt by using the sysfs interface. The feature
can be used for load balancing or other purposes.
One interesting catch here is that Hyper-V can *not* currently ACK
CHANNELMSG_MODIFYCHANNEL messages with the promise that (after the ACK
is sent) the channel won't send any more interrupts to the "old" CPU.
The peculiarity of the CHANNELMSG_MODIFYCHANNEL messages is problematic
if the user want to take a CPU offline, since we don't want to take a
CPU offline (and, potentially, "lose" channel interrupts on such CPU)
if the host is still processing a CHANNELMSG_MODIFYCHANNEL message
associated to that CPU.
It is worth mentioning, however, that we have been unable to observe
the above mentioned "race": in all our tests, CHANNELMSG_MODIFYCHANNEL
requests appeared *as if* they were processed synchronously by the host.
Suggested-by: Michael Kelley <mikelley@microsoft.com>
Signed-off-by: Andrea Parri (Microsoft) <parri.andrea@gmail.com>
Link: https://lore.kernel.org/r/20200406001514.19876-11-parri.andrea@gmail.com
Reviewed-by: Michael Kelley <mikelley@microsoft.com>
[ wei: fix conflict in channel_mgmt.c ]
Signed-off-by: Wei Liu <wei.liu@kernel.org>
Since vmbus_chan_sched() dereferences the ring buffer pointer, we have
to make sure that the ring buffer data structures don't get freed while
such dereferencing is happening. Current code does this by sending an
IPI to the CPU that is allowed to access that ring buffer from interrupt
level, cf., vmbus_reset_channel_cb(). But with the new functionality
to allow changing the CPU that a channel will interrupt, we can't be
sure what CPU will be running the vmbus_chan_sched() function for a
particular channel, so the current IPI mechanism is infeasible.
Instead synchronize vmbus_chan_sched() and vmbus_reset_channel_cb() by
using the (newly introduced) per-channel spin lock "sched_lock". Move
the test for onchannel_callback being NULL before the "switch" control
statement in vmbus_chan_sched(), in order to not access the ring buffer
if the vmbus_reset_channel_cb() has been completed on the channel.
Suggested-by: Michael Kelley <mikelley@microsoft.com>
Signed-off-by: Andrea Parri (Microsoft) <parri.andrea@gmail.com>
Link: https://lore.kernel.org/r/20200406001514.19876-7-parri.andrea@gmail.com
Reviewed-by: Michael Kelley <mikelley@microsoft.com>
Signed-off-by: Wei Liu <wei.liu@kernel.org>
When Hyper-V sends an interrupt to the guest, the guest has to figure
out which channel the interrupt is associated with. Hyper-V sets a bit
in a memory page that is shared with the guest, indicating a particular
"relid" that the interrupt is associated with. The current Linux code
then uses a set of per-CPU linked lists to map a given "relid" to a
pointer to a channel structure.
This design introduces a synchronization problem if the CPU that Hyper-V
will interrupt for a certain channel is changed. If the interrupt comes
on the "old CPU" and the channel was already moved to the per-CPU list
of the "new CPU", then the relid -> channel mapping will fail and the
interrupt is dropped. Similarly, if the interrupt comes on the new CPU
but the channel was not moved to the per-CPU list of the new CPU, then
the mapping will fail and the interrupt is dropped.
Relids are integers ranging from 0 to 2047. The mapping from relids to
channel structures can be done by setting up an array with 2048 entries,
each entry being a pointer to a channel structure (hence total size ~16K
bytes, which is not a problem). The array is global, so there are no
per-CPU linked lists to update. The array can be searched and updated
by loading from/storing to the array at the specified index. With no
per-CPU data structures, the above mentioned synchronization problem is
avoided and the relid2channel() function gets simpler.
Suggested-by: Michael Kelley <mikelley@microsoft.com>
Signed-off-by: Andrea Parri (Microsoft) <parri.andrea@gmail.com>
Link: https://lore.kernel.org/r/20200406001514.19876-4-parri.andrea@gmail.com
Reviewed-by: Michael Kelley <mikelley@microsoft.com>
Signed-off-by: Wei Liu <wei.liu@kernel.org>
Add util_pre_suspend() and util_pre_resume() for some hv_utils devices
(e.g. kvp/vss/fcopy), because they need special handling before
util_suspend() calls vmbus_close().
For kvp, all the possible pending work items should be cancelled.
For vss and fcopy, some extra clean-up needs to be done, i.e. fake a
THAW message for hv_vss_daemon and fake a CANCEL_FCOPY message for
hv_fcopy_daemon, otherwise when the VM resums back, the daemons
can end up in an inconsistent state (i.e. the file systems are
frozen but will never be thawed; the file transmitted via fcopy
may not be complete). Note: there is an extra patch for the daemons:
"Tools: hv: Reopen the devices if read() or write() returns errors",
because the hv_utils driver can not guarantee the whole transaction
finishes completely once util_suspend() starts to run (at this time,
all the userspace processes are frozen).
util_probe() disables channel->callback_event to avoid the race with
the channel callback.
Signed-off-by: Dexuan Cui <decui@microsoft.com>
Reviewed-by: Michael Kelley <mikelley@microsoft.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
When a Linux hv_sock app tries to connect to a Service GUID on which no
host app is listening, a recent host (RS3+) sends a
CHANNELMSG_TL_CONNECT_RESULT (23) message to Linux and this triggers such
a warning:
unknown msgtype=23
WARNING: CPU: 2 PID: 0 at drivers/hv/vmbus_drv.c:1031 vmbus_on_msg_dpc
Actually Linux can safely ignore the message because the Linux app's
connect() will time out in 2 seconds: see VSOCK_DEFAULT_CONNECT_TIMEOUT
and vsock_stream_connect(). We don't bother to make use of the message
because: 1) it's only supported on recent hosts; 2) a non-trivial effort
is required to use the message in Linux, but the benefit is small.
So, let's not see the warning by silently ignoring the message.
Signed-off-by: Dexuan Cui <decui@microsoft.com>
Reviewed-by: Michael Kelley <mikelley@microsoft.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
Introduce user specified latency in the packet reception path
By exposing the test parameters as part of the debugfs channel
attributes. We will control the testing state via these attributes.
Signed-off-by: Branden Bonaby <brandonbonaby94@gmail.com>
Reviewed-by: Michael Kelley <mikelley@microsoft.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
Hyper-V has added VMBus protocol versions 5.1 and 5.2 in recent release
versions. Allow Linux guests to negotiate these new protocol versions
on versions of Hyper-V that support them. While on this, also allow
guests to negotiate the VMBus protocol version 4.1 (which was missing).
Signed-off-by: Andrea Parri <parri.andrea@gmail.com>
Reviewed-by: Wei Liu <wei.liu@kernel.org>
Reviewed-by: Michael Kelley <mikelley@microsoft.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
The technique used to get the next VMBus version seems increasisly
clumsy as the number of VMBus versions increases. Performance is
not a concern since this is only done once during system boot; it's
just that we'll end up with more lines of code than is really needed.
As an alternative, introduce a table with the version numbers listed
in order (from the most recent to the oldest). vmbus_connect() loops
through the versions listed in the table until it gets an accepted
connection or gets to the end of the table (invalid version).
Suggested-by: Michael Kelley <mikelley@microsoft.com>
Signed-off-by: Andrea Parri <parri.andrea@gmail.com>
Reviewed-by: Wei Liu <wei.liu@kernel.org>
Reviewed-by: Michael Kelley <mikelley@microsoft.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
Pull Hyper-V updates from Sasha Levin:
- first round of vmbus hibernation support (Dexuan Cui)
- remove dependencies on PAGE_SIZE (Maya Nakamura)
- move the hyper-v tools/ code into the tools build system (Andy
Shevchenko)
- hyper-v balloon cleanups (Dexuan Cui)
* tag 'hyperv-next-signed' of git://git.kernel.org/pub/scm/linux/kernel/git/hyperv/linux:
Drivers: hv: vmbus: Resume after fixing up old primary channels
Drivers: hv: vmbus: Suspend after cleaning up hv_sock and sub channels
Drivers: hv: vmbus: Clean up hv_sock channels by force upon suspend
Drivers: hv: vmbus: Suspend/resume the vmbus itself for hibernation
Drivers: hv: vmbus: Ignore the offers when resuming from hibernation
Drivers: hv: vmbus: Implement suspend/resume for VSC drivers for hibernation
Drivers: hv: vmbus: Add a helper function is_sub_channel()
Drivers: hv: vmbus: Suspend/resume the synic for hibernation
Drivers: hv: vmbus: Break out synic enable and disable operations
HID: hv: Remove dependencies on PAGE_SIZE for ring buffer
Tools: hv: move to tools buildsystem
hv_balloon: Reorganize the probe function
hv_balloon: Use a static page for the balloon_up send buffer
When the host re-offers the primary channels upon resume, the host only
guarantees the Instance GUID doesn't change, so vmbus_bus_suspend()
should invalidate channel->offermsg.child_relid and figure out the
number of primary channels that need to be fixed up upon resume.
Upon resume, vmbus_onoffer() finds the old channel structs, and maps
the new offers to the old channels, and fixes up the old structs,
and finally the resume callbacks of the VSC drivers will re-open
the channels.
Signed-off-by: Dexuan Cui <decui@microsoft.com>
Reviewed-by: Michael Kelley <mikelley@microsoft.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
The existing method of telling if a channel is sub-channel in
vmbus_process_offer() is cumbersome. This new simple helper function
is preferred in future.
Signed-off-by: Dexuan Cui <decui@microsoft.com>
Reviewed-by: Michael Kelley <mikelley@microsoft.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
This interface driver is a helper driver allows other drivers to
have a common interface with the Hyper-V PCI frontend driver.
Signed-off-by: Haiyang Zhang <haiyangz@microsoft.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Windows SR-IOV provides a backchannel mechanism in software for communication
between a VF driver and a PF driver. These "configuration blocks" are
similar in concept to PCI configuration space, but instead of doing reads and
writes in 32-bit chunks through a very slow path, packets of up to 128 bytes
can be sent or received asynchronously.
Nearly every SR-IOV device contains just such a communications channel in
hardware, so using this one in software is usually optional. Using the
software channel, however, allows driver implementers to leverage software
tools that fuzz the communications channel looking for vulnerabilities.
The usage model for these packets puts the responsibility for reading or
writing on the VF driver. The VF driver sends a read or a write packet,
indicating which "block" is being referred to by number.
If the PF driver wishes to initiate communication, it can "invalidate" one or
more of the first 64 blocks. This invalidation is delivered via a callback
supplied by the VF driver by this driver.
No protocol is implied, except that supplied by the PF and VF drivers.
Signed-off-by: Jake Oshins <jakeo@microsoft.com>
Signed-off-by: Dexuan Cui <decui@microsoft.com>
Cc: Haiyang Zhang <haiyangz@microsoft.com>
Cc: K. Y. Srinivasan <kys@microsoft.com>
Cc: Stephen Hemminger <sthemmin@microsoft.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: Haiyang Zhang <haiyangz@microsoft.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
