This allows disabling XDomain protocol completely if the user does not
plan to use the USB4/Thunderbolt peer-to-peer functionality, or for
security reasons.
XDomain protocol is enabled by default but with this commit it is
possible to disable it by passing "xdomain=0" as module parameter (or
through the kernel command line).
Signed-off-by: Mika Westerberg <mika.westerberg@linux.intel.com>
Acked-by: Yehezkel Bernat <YehezkelShB@gmail.com>
Recent Intel Thunderbolt firmware connection manager has support for
another security level, SL5, that disables PCIe tunneling. This option
can be turned on from the BIOS.
When this is set the driver exposes a new security level "nopcie" to the
userspace and hides the authorized attribute under connected devices.
While there we also hide it when "dponly" security level is enabled
since it is not really usable in that case anyway.
Signed-off-by: Mika Westerberg <mika.westerberg@linux.intel.com>
Acked-by: Yehezkel Bernat <YehezkelShB@gmail.com>
In some cases it is useful to be able de-authorize devices. For example
if user logs out the userspace can have a policy that disconnects PCIe
devices until logged in again. This is only possible for software based
connection manager as it directly controls the tunnels.
For this reason make the authorized attribute accept writing 0 which
makes the software connection manager to tear down the corresponding
PCIe tunnel. Userspace can check if this is supported by reading a new
domain attribute deauthorization, that holds 1 in that case.
While there correct tb_domain_approve_switch() kernel-doc and
description of authorized attribute to mention that it is only about
PCIe tunnels.
Cc: Christian Kellner <christian@kellner.me>
Signed-off-by: Mika Westerberg <mika.westerberg@linux.intel.com>
Acked-by: Yehezkel Bernat <YehezkelShB@gmail.com>
The only usage of these is to put their addresses in arrays of pointers
to const attribute_groups. Make them const to allow the compiler to put
them in read-only memory.
Signed-off-by: Rikard Falkeborn <rikard.falkeborn@gmail.com>
Signed-off-by: Mika Westerberg <mika.westerberg@linux.intel.com>
This adds a bit more build coverage for the tests even though these are
not expected to be enabled by normal users and distros. In order to make
this working we need to open-code kunit_test_suite() and call the
relevant functions directly in the driver init/exit hook.
Signed-off-by: Mika Westerberg <mika.westerberg@linux.intel.com>
According to the kernel power management documentation freeze phase
should only quiesce the device, no need to configure wakes or put it to
low power state. For this reason we simply stop the control channel and
in case of Software Connection Manager also mark the hotplug disabled.
This should align the driver better with the PM framework expectations.
Signed-off-by: Mika Westerberg <mika.westerberg@linux.intel.com>
This adds debugfs interface that can be used for debugging possible
issues in hardware/software. It exposes router and adapter config spaces
through files like this:
/sys/kernel/debug/thunderbolt/<DEVICE>/regs
/sys/kernel/debug/thunderbolt/<DEVICE>/<PORT1>/regs
/sys/kernel/debug/thunderbolt/<DEVICE>/<PORT1>/path
/sys/kernel/debug/thunderbolt/<DEVICE>/<PORT1>/counters
/sys/kernel/debug/thunderbolt/<DEVICE>/<PORT2>/regs
/sys/kernel/debug/thunderbolt/<DEVICE>/<PORT2>/path
/sys/kernel/debug/thunderbolt/<DEVICE>/<PORT2>/counters
...
The "regs" is either the router or port configuration space register
dump. The "path" is the port path configuration space and "counters" is
the optional counters configuration space.
These files contains one register per line so it should be easy to use
normal filtering tools to find the registers of interest if needed.
The router and adapter regs file becomes writable when
CONFIG_USB4_DEBUGFS_WRITE is enabled (which is not supposed to be done
in production systems) and in this case the developer can write "offset
value" lines there to modify the hardware directly. For convenience this
also supports the long format the read side produces (but ignores the
additional fields). The counters file can be written even when
CONFIG_USB4_DEBUGFS_WRITE is not enabled and it is only used to clear
the counter values.
Signed-off-by: Gil Fine <gil.fine@intel.com>
Signed-off-by: Mika Westerberg <mika.westerberg@linux.intel.com>
Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
In order for the router and the whole domain to wake up from system
suspend states we need to enable wakes for the connected routers. For
device routers we enable wakes from PCIe and USB 3.x. This allows
devices such as keyboards connected to USB 3.x hub that is tunneled to
wake the system up as expected. For all routers we enabled wake on USB4
for each connected ports. This is used to propagate the wake from router
to another.
Do the same for legacy routers through link controller vendor specific
registers as documented in USB4 spec chapter 13.
While there correct kernel-doc of usb4_switch_set_sleep() -- it does not
enable wakes instead there is a separate function (usb4_switch_set_wake())
that does.
Signed-off-by: Mika Westerberg <mika.westerberg@linux.intel.com>
Doesn't really matter for an individual driver, but it may
get coppied to lots more. I consider it's a little tidy up.
Signed-off-by: Tian Tao <tiantao6@hisilicon.com>
Signed-off-by: Mika Westerberg <mika.westerberg@linux.intel.com>
We are going to reuse some of this functionality to implement retimer
NVM upgrade so move common NVM functionality into its own file. We also
rename the structure from tb_switch_nvm to tb_nvm to make it clear that
it is not just for switches.
Signed-off-by: Mika Westerberg <mika.westerberg@linux.intel.com>
Since snprintf() returns the would-be-output size instead of the
actual output size, the succeeding calls may go beyond the given
buffer limit. Fix it by replacing with scnprintf().
Signed-off-by: Takashi Iwai <tiwai@suse.de>
Signed-off-by: Mika Westerberg <mika.westerberg@linux.intel.com>
The flags field in 'struct shash_desc' never actually does anything.
The only ostensibly supported flag is CRYPTO_TFM_REQ_MAY_SLEEP.
However, no shash algorithm ever sleeps, making this flag a no-op.
With this being the case, inevitably some users who can't sleep wrongly
pass MAY_SLEEP. These would all need to be fixed if any shash algorithm
actually started sleeping. For example, the shash_ahash_*() functions,
which wrap a shash algorithm with the ahash API, pass through MAY_SLEEP
from the ahash API to the shash API. However, the shash functions are
called under kmap_atomic(), so actually they're assumed to never sleep.
Even if it turns out that some users do need preemption points while
hashing large buffers, we could easily provide a helper function
crypto_shash_update_large() which divides the data into smaller chunks
and calls crypto_shash_update() and cond_resched() for each chunk. It's
not necessary to have a flag in 'struct shash_desc', nor is it necessary
to make individual shash algorithms aware of this at all.
Therefore, remove shash_desc::flags, and document that the
crypto_shash_*() functions can be called from any context.
Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Recent systems with Thunderbolt ports may support IOMMU natively. In
practice this means that Thunderbolt connected devices are placed behind
an IOMMU during the whole time it is connected (including during boot)
making Thunderbolt security levels redundant. This is called Kernel DMA
protection [1] by Microsoft.
Some of these systems still have Thunderbolt security level set to
"user" in order to support OS downgrade (the older version of the OS
might not support IOMMU based DMA protection so connecting a device
still relies on user approval).
Export this information to userspace by introducing a new sysfs
attribute (iommu_dma_protection). Based on it userspace tools can make
more accurate decision whether or not authorize the connected device.
In addition update Thunderbolt documentation regarding IOMMU based DMA
protection.
[1] https://docs.microsoft.com/en-us/windows/security/information-protection/kernel-dma-protection-for-thunderbolt
Signed-off-by: Mika Westerberg <mika.westerberg@linux.intel.com>
Reviewed-by: Yehezkel Bernat <YehezkelShB@gmail.com>
This gets rid of the licence boilerplate duplicated in each file. While
there fix doubled space in domain.c author line.
No functional changes intended.
Signed-off-by: Mika Westerberg <mika.westerberg@linux.intel.com>
Acked-by: Yehezkel Bernat <yehezkelshb@gmail.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
When Thunderbolt host controller is set to RTD3 mode (Runtime D3) it is
present all the time. Because of this it is important to runtime suspend
the controller whenever possible. In case of ICM we have following rules
which all needs to be true before the host controller can be put to D3:
- The controller firmware reports to support RTD3
- All the connected devices announce support for RTD3
- There is no active XDomain connection
Implement this using standard Linux runtime PM APIs so that when all the
children devices are runtime suspended, the Thunderbolt host controller
PCI device is runtime suspended as well. The ICM firmware then starts
powering down power domains towards RTD3 but it can prevent this if it
detects that there is an active Display Port stream (this is not visible
to the software, though).
The Thunderbolt host controller will be runtime resumed either when
there is a remote wake event (device is connected or disconnected), or
when there is access from userspace that requires hardware access.
Signed-off-by: Mika Westerberg <mika.westerberg@linux.intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
If the connection manager implementation needs to touch the domain
structures it ought to take the lock itself. Currently only ICM
implements these hooks and it does not need the lock because we there
will be no notifications before driver ready message is sent to it.
Signed-off-by: Mika Westerberg <mika.westerberg@linux.intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
The commit 9aaa3b8b4c ("thunderbolt: Add support for preboot ACL")
introduced boot_acl attribute but missed the fact that now userspace
needs to poll the attribute constantly to find out whether it has
changed or not. Fix this by sending notification to the userspace
whenever the boot_acl attribute is changed.
Fixes: 9aaa3b8b4c ("thunderbolt: Add support for preboot ACL")
Reported-and-tested-by: Christian Kellner <christian@kellner.me>
Signed-off-by: Mika Westerberg <mika.westerberg@linux.intel.com>
Reviewed-by: Christian Kellner <christian@kellner.me>
Acked-by: Yehezkel Bernat <yehezkelshb@gmail.com>
Cc: stable@vger.kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
This new security level works so that it creates one PCIe tunnel to the
connected Thunderbolt dock, removing PCIe links downstream of the dock.
This leaves only the internal USB controller visible.
Display Port tunnels are created normally.
While there make sure security sysfs attribute returns "unknown" for any
future security level.
Signed-off-by: Mika Westerberg <mika.westerberg@linux.intel.com>
Reviewed-by: Andy Shevchenko <andy.shevchenko@gmail.com>
Preboot ACL is a mechanism that allows connecting Thunderbolt devices
boot time in more secure way than the legacy Thunderbolt boot support.
As with the legacy boot option, this also needs to be enabled from the
BIOS before booting is allowed. Difference to the legacy mode is that
the userspace software explicitly adds device UUIDs by sending a special
message to the ICM firmware. Only the devices listed in the boot ACL are
connected automatically during the boot. This works in both "user" and
"secure" security levels.
We implement this in Linux by exposing a new sysfs attribute (boot_acl)
below each Thunderbolt domain. The userspace software can then update
the full list as needed.
Signed-off-by: Mika Westerberg <mika.westerberg@linux.intel.com>
Reviewed-by: Andy Shevchenko <andy.shevchenko@gmail.com>
When two hosts are connected over a Thunderbolt cable, there is a
protocol they can use to communicate capabilities supported by the host.
The discovery protocol uses automatically configured control channel
(ring 0) and is build on top of request/response transactions using
special XDomain primitives provided by the Thunderbolt base protocol.
The capabilities consists of a root directory block of basic properties
used for identification of the host, and then there can be zero or more
directories each describing a Thunderbolt service and its capabilities.
Once both sides have discovered what is supported the two hosts can
setup high-speed DMA paths and transfer data to the other side using
whatever protocol was agreed based on the properties. The software
protocol used to communicate which DMA paths to enable is service
specific.
This patch adds support for the XDomain discovery protocol to the
Thunderbolt bus. We model each remote host connection as a Linux XDomain
device. For each Thunderbolt service found supported on the XDomain
device, we create Linux Thunderbolt service device which Thunderbolt
service drivers can then bind to based on the protocol identification
information retrieved from the property directory describing the
service.
This code is based on the work done by Amir Levy and Michael Jamet.
Signed-off-by: Michael Jamet <michael.jamet@intel.com>
Signed-off-by: Mika Westerberg <mika.westerberg@linux.intel.com>
Reviewed-by: Yehezkel Bernat <yehezkel.bernat@intel.com>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Starting from Intel Falcon Ridge the NVM firmware can be upgraded by
using DMA configuration based mailbox commands. If we detect that the
host or device (device support starts from Intel Alpine Ridge) has the
DMA configuration based mailbox we expose NVM information to the
userspace as two separate Linux NVMem devices: nvm_active and
nvm_non_active. The former is read-only portion of the active NVM which
firmware upgrade tools can be use to find out suitable NVM image if the
device identification strings are not enough.
The latter is write-only portion where the new NVM image is to be
written by the userspace. It is up to the userspace to find out right
NVM image (the kernel does very minimal validation). The ICM firmware
itself authenticates the new NVM firmware and fails the operation if it
is not what is expected.
We also expose two new sysfs files per each switch: nvm_version and
nvm_authenticate which can be used to read the active NVM version and
start the upgrade process.
We also introduce safe mode which is the mode a switch goes when it does
not have properly authenticated firmware. In this mode the switch only
accepts a couple of commands including flashing a new NVM firmware image
and triggering power cycle.
This code is based on the work done by Amir Levy and Michael Jamet.
Signed-off-by: Michael Jamet <michael.jamet@intel.com>
Signed-off-by: Mika Westerberg <mika.westerberg@linux.intel.com>
Reviewed-by: Yehezkel Bernat <yehezkel.bernat@intel.com>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Andreas Noever <andreas.noever@gmail.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Starting from Intel Falcon Ridge the internal connection manager running
on the Thunderbolt host controller has been supporting 4 security
levels. One reason for this is to prevent DMA attacks and only allow
connecting devices the user trusts.
The internal connection manager (ICM) is the preferred way of connecting
Thunderbolt devices over software only implementation typically used on
Macs. The driver communicates with ICM using special Thunderbolt ring 0
(control channel) messages. In order to handle these messages we add
support for the ICM messages to the control channel.
The security levels are as follows:
none - No security, all tunnels are created automatically
user - User needs to approve the device before tunnels are created
secure - User need to approve the device before tunnels are created.
The device is sent a challenge on future connects to be able
to verify it is actually the approved device.
dponly - Only Display Port and USB tunnels can be created and those
are created automatically.
The security levels are typically configurable from the system BIOS and
by default it is set to "user" on many systems.
In this patch each Thunderbolt device will have either one or two new
sysfs attributes: authorized and key. The latter appears for devices
that support secure connect.
In order to identify the device the user can read identication
information, including UUID and name of the device from sysfs and based
on that make a decision to authorize the device. The device is
authorized by simply writing 1 to the "authorized" sysfs attribute. This
is following the USB bus device authorization mechanism. The secure
connect requires an additional challenge step (writing 2 to the
"authorized" attribute) in future connects when the key has already been
stored to the NVM of the device.
Non-ICM systems (before Alpine Ridge) continue to use the existing
functionality and the security level is set to none. For systems with
Alpine Ridge, even on Apple hardware, we will use ICM.
This code is based on the work done by Amir Levy and Michael Jamet.
Signed-off-by: Michael Jamet <michael.jamet@intel.com>
Signed-off-by: Mika Westerberg <mika.westerberg@linux.intel.com>
Reviewed-by: Yehezkel Bernat <yehezkel.bernat@intel.com>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Andreas Noever <andreas.noever@gmail.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Currently the control channel (ctl.c) handles the one supported
notification (PLUG_EVENT) and sends back ACK accordingly. However, we
are going to add support for the internal connection manager (ICM) that
needs to handle a different notifications. So instead of dealing
everything in the control channel, we change the callback to take an
arbitrary thunderbolt packet and convert the native connection manager
to handle the event itself.
In addition we only push replies we know of to the response FIFO.
Everything else is treated as notification (or request) and is expected
to be dealt by the connection manager implementation.
Signed-off-by: Mika Westerberg <mika.westerberg@linux.intel.com>
Reviewed-by: Yehezkel Bernat <yehezkel.bernat@intel.com>
Reviewed-by: Michael Jamet <michael.jamet@intel.com>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Andreas Noever <andreas.noever@gmail.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Thunderbolt fabric consists of one or more switches. This fabric is
called domain and it is controlled by an entity called connection
manager. The connection manager can be either internal (driven by a
firmware running on the host controller) or external (software driver).
This driver currently implements support for the latter.
In order to manage switches and their properties more easily we model
this domain structure as a Linux bus. Each host controller adds a domain
device to this bus, and these devices are named as domainN where N
stands for index or id of the current domain.
We then abstract connection manager specific operations into a new
structure tb_cm_ops and convert the existing tb.c to fill those
accordingly. This makes it easier to add support for the internal
connection manager in subsequent patches.
Signed-off-by: Mika Westerberg <mika.westerberg@linux.intel.com>
Reviewed-by: Yehezkel Bernat <yehezkel.bernat@intel.com>
Reviewed-by: Michael Jamet <michael.jamet@intel.com>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Andreas Noever <andreas.noever@gmail.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>