Include the support for enumerating and provisioning ram regions for
v6.3. This also include a default policy change for ram / volatile
device-dax instances to assign them to the dax_kmem driver by default.
While platform firmware takes some responsibility for mapping the RAM
capacity of CXL devices present at boot, the OS is responsible for
mapping the remainder and hot-added devices. Platform firmware is also
responsible for identifying the platform general purpose memory pool,
typically DDR attached DRAM, and arranging for the remainder to be 'Soft
Reserved'. That reservation allows the CXL subsystem to route the memory
to core-mm via memory-hotplug (dax_kmem), or leave it for dedicated
access (device-dax).
The new 'struct cxl_dax_region' object allows for a CXL memory resource
(region) to be published, but also allow for udev and module policy to
act on that event. It also prevents cxl_core.ko from having a module
loading dependency on any drivers/dax/ modules.
Tested-by: Fan Ni <fan.ni@samsung.com>
Reviewed-by: Dave Jiang <dave.jiang@intel.com>
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Link: https://lore.kernel.org/r/167602003896.1924368.10335442077318970468.stgit@dwillia2-xfh.jf.intel.com
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Merge the general CXL updates with fixes targeting v6.2-rc for v6.3.
Resolve a conflict with the fix and move of cxl_report_and_clear() from
pci.c to core/pci.c.
The cxl_pmem.ko module houses the driver for both cxl_nvdimm_bridge
objects and cxl_nvdimm objects. When the core creates a cxl_nvdimm it
arranges for it to be autoremoved when the bridge goes down. However, if
the bridge never initialized because the cxl_pmem.ko module never
loaded, it sets up a the following crash scenario:
BUG: kernel NULL pointer dereference, address: 0000000000000478
[..]
RIP: 0010:cxl_nvdimm_probe+0x99/0x140 [cxl_pmem]
[..]
Call Trace:
<TASK>
cxl_bus_probe+0x17/0x50 [cxl_core]
really_probe+0xde/0x380
__driver_probe_device+0x78/0x170
driver_probe_device+0x1f/0x90
__driver_attach+0xd2/0x1c0
bus_for_each_dev+0x79/0xc0
bus_add_driver+0x1b1/0x200
driver_register+0x89/0xe0
cxl_pmem_init+0x50/0xff0 [cxl_pmem]
It turns out the recent rework to simplify nvdimm probing obviated the
need to unregister cxl_nvdimm objects at cxl_nvdimm_bridge ->remove()
time. Leave the cxl_nvdimm device registered until the hosting
cxl_memdev departs. The alternative is that the cxl_memdev needs to be
reattached whenever the cxl_nvdimm_bridge attach state cycles, which is
awkward and unnecessary.
The only requirement is to make sure that when the cxl_nvdimm_bridge
goes away any dependent cxl_nvdimm objects are shutdown. Handle that in
unregister_nvdimm_bus().
With these registration entanglements removed there is no longer a need
to pre-load the cxl_pmem module in cxl_acpi.
Fixes: cb9cfff82f ("cxl/acpi: Simplify cxl_nvdimm_bridge probing")
Reported-by: Gregory Price <gregory.price@memverge.com>
Debugged-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Tested-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Reviewed-by: Dave Jiang <dave.jiang@intel.com>
Link: https://lore.kernel.org/r/167426077263.3955046.9695309346988027311.stgit@dwillia2-xfh.jf.intel.com
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Change names for interleave ways macros to clearly indicate which
variable is encoded and which is the actual ways value.
ways == interleave ways
eiw == encoded interleave ways
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
Link: https://lore.kernel.org/r/167027516228.3124679.11265039496968588580.stgit@djiang5-desk3.ch.intel.com
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Change names for granularity macros to clearly indicate which
variable is encoded and which is the actual granularity.
granularity == interleave granularity
eig == encoded interleave granularity
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Reviewed-by: Alison Schofield <alison.schofield@intel.com>
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
Link: https://lore.kernel.org/r/167027493237.3124429.8948852388671827664.stgit@djiang5-desk3.ch.intel.com
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
After parsing for a CHBCR in cxl_get_chbcr() the case of (ctx.chbcr ==
CXL_RESOURCE_NONE) is a slighly different error reason than the
!ctx.chbcr case. In the first case the CHBS was found but the CHBCR
was invalid or something else failed to determine it, while in the
latter case no CHBS entry exists at all.
Update the warning message to reflect this. The log messages for both
cases can be differentiated now and the reason for a failure can be
determined better.
Signed-off-by: Robert Richter <rrichter@amd.com>
Reviewed-by: Dave Jiang <dave.jiang@intel.com>
Link: https://lore.kernel.org/r/167027170051.3542509.10494781536638424397.stgit@dwillia2-xfh.jf.intel.com
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
The BIOS provided CXIMS (CXL XOR Interleave Math Structure) is required
for calculating a targets position in an interleave list during region
creation. The CXL driver expects to discover a CXIMS that matches the
HBIG (Host Bridge Interleave Granularity) and stores the xormaps found
in that CXIMS for retrieval during region creation.
If there is no CXIMS for an HBIG, no maps are stored. That leads to a
NULL pointer dereference at xormap retrieval during region creation.
Add a check during ACPI probe for the case of no matching CXIMS. Emit
an error message and fail to add the decoder.
Fixes: f9db85bfec ("cxl/acpi: Support CXL XOR Interleave Math (CXIMS)")
Suggested-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Alison Schofield <alison.schofield@intel.com>
Reviewed-by: Dave Jiang <dave.jiang@intel.com>
Link: https://lore.kernel.org/r/20221205002951.1788783-1-alison.schofield@intel.com
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Pick up support for "XOR" interleave math when parsing ACPI CFMWS window
structures. Fix up conflicts with the RCH emulation already pending in
cxl/next.
When the CFMWS is using XOR math, parse the corresponding
CXIMS structure and store the xormaps in the root decoder
structure. Use the xormaps in a new lookup, cxl_hb_xor(),
to find a targets entry in the host bridge interleave
target list.
Defined in CXL Specfication 3.0 Section: 9.17.1
Signed-off-by: Alison Schofield <alison.schofield@intel.com>
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Link: https://lore.kernel.org/r/5794813acdf7b67cfba3609c6aaff46932fa38d0.1669847017.git.alison.schofield@intel.com
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
A downstream port must be connected to a component register block.
For restricted hosts the base address is determined from the RCRB. The
RCRB is provided by the host's CEDT CHBS entry. Rework CEDT parser to
get the RCRB and add code to extract the component register block from
it.
RCRB's BAR[0..1] point to the component block containing CXL subsystem
component registers. MEMBAR extraction follows the PCI base spec here,
esp. 64 bit extraction and memory range alignment (6.0, 7.5.1.2.1). The
RCRB base address is cached in the cxl_dport per-host bridge so that the
upstream port component registers can be retrieved later by an RCD
(RCIEP) associated with the host bridge.
Note: Right now the component register block is used for HDM decoder
capability only which is optional for RCDs. If unsupported by the RCD,
the HDM init will fail. It is future work to bypass it in this case.
Co-developed-by: Terry Bowman <terry.bowman@amd.com>
Signed-off-by: Terry Bowman <terry.bowman@amd.com>
Signed-off-by: Robert Richter <rrichter@amd.com>
Link: https://lore.kernel.org/r/Y4dsGZ24aJlxSfI1@rric.localdomain
[djbw: introduce devm_cxl_add_rch_dport()]
Link: https://lore.kernel.org/r/166993044524.1882361.2539922887413208807.stgit@dwillia2-xfh.jf.intel.com
Reviewed-by: Dave Jiang <dave.jiang@intel.com>
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
A port of a CXL host bridge links to the bridge's ACPI device
(&adev->dev) with its corresponding uport/dport device (uport_dev and
dport_dev respectively). The device is not a direct parent device in
the PCI topology as pdev->dev.parent points to a PCI bridge's (struct
pci_host_bridge) device. The following CXL memory device hierarchy
would be valid for an endpoint once an RCD EP would be enabled (note
this will be done in a later patch):
VH mode:
cxlmd->dev.parent->parent
^^^\^^^^^^\ ^^^^^^\
\ \ pci_dev (Type 1, Downstream Port)
\ pci_dev (Type 0, PCI Express Endpoint)
cxl mem device
RCD mode:
cxlmd->dev.parent->parent
^^^\^^^^^^\ ^^^^^^\
\ \ pci_host_bridge
\ pci_dev (Type 0, RCiEP)
cxl mem device
In VH mode a downstream port is created by port enumeration and thus
always exists.
Now, in RCD mode the host bridge also already exists but it references
to an ACPI device. A port lookup by the PCI device's parent device
will fail as a direct link to the registered port is missing. The ACPI
device of the bridge must be determined first.
To prevent this, change port registration of a CXL host to use the
bridge device instead. Do this also for the VH case as port topology
will better reflect the PCI topology then.
Signed-off-by: Robert Richter <rrichter@amd.com>
[djbw: rebase on brige mocking]
Reviewed-by: Robert Richter <rrichter@amd.com>
Reviewed-by: Dave Jiang <dave.jiang@intel.com>
Link: https://lore.kernel.org/r/166993043978.1882361.16238060349889579369.stgit@dwillia2-xfh.jf.intel.com
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Accept any cxl_test topology device as the first argument in
cxl_chbs_context.
This is in preparation for reworking the detection of the component
registers across VH and RCH topologies. Move
mock_acpi_table_parse_cedt() beneath the definition of is_mock_port()
and use is_mock_port() instead of the explicit mock cxl_acpi device
check.
Acked-by: Alison Schofield <alison.schofield@intel.com>
Reviewed-by: Robert Richter <rrichter@amd.com>
Reviewed-by: Dave Jiang <dave.jiang@intel.com>
Link: https://lore.kernel.org/r/166993043433.1882361.17651413716599606118.stgit@dwillia2-xfh.jf.intel.com
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
The 'struct cxl_nvdimm_bridge' object advertises platform CXL PMEM
resources. It coordinates with libnvdimm to attach nvdimm devices and
regions for each corresponding CXL object. That coordination is
complicated, i.e. difficult to reason about, and it turns out redundant.
It is already the case that the CXL core knows how to tear down a
cxl_region when a cxl_memdev goes through ->remove(), so that pathway
can be extended to directly cleanup cxl_nvdimm and cxl_pmem_region
objects.
Towards the goal of ripping out the cxl_nvdimm_bridge state machine,
arrange for cxl_acpi to optionally pre-load the cxl_pmem driver so that
the nvdimm bridge is active synchronously with
devm_cxl_add_nvdimm_bridge(), and remove all the bind attributes for the
cxl_nvdimm* objects since the cxl root device and cxl_memdev bind
attributes are sufficient.
Tested-by: Robert Richter <rrichter@amd.com>
Link: https://lore.kernel.org/r/166993040668.1882361.7450361097265836752.stgit@dwillia2-xfh.jf.intel.com
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
In cxl_acpi_probe() the iterator bus_for_each_dev() walks through all
CXL hosts. Since all dev_*() debug messages point to the ACPI0017
device which is the CXL root for all hosts, the device information is
pointless as it is always the same device. Change this to use the host
device for this instead.
Also, add additional host specific information such as CXL support,
UID and CHBCR.
This is an example log:
acpi ACPI0016:00: UID found: 4
acpi ACPI0016:00: CHBCR found: 0x28090000000
acpi ACPI0016:00: dport added to root0
acpi ACPI0016:00: host-bridge: ACPI0016:00
pci0000:7f: host supports CXL
Signed-off-by: Robert Richter <rrichter@amd.com>
Link: https://lore.kernel.org/r/20221018132341.76259-6-rrichter@amd.com
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
CXL dports are added in a couple of code paths using
devm_cxl_add_dport(). Debug messages are individually generated, but are
incomplete and inconsistent. Change this by moving its generation to
devm_cxl_add_dport(). This unifies the messages and reduces code
duplication. Also, generate messages on failure. Use a
__devm_cxl_add_dport() wrapper to keep the readability of the error
exits.
Signed-off-by: Robert Richter <rrichter@amd.com>
Link: https://lore.kernel.org/r/20221018132341.76259-5-rrichter@amd.com
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
CXL ports are added in a couple of code paths using devm_cxl_add_port().
Debug messages are individually generated, but are incomplete and
inconsistent. Change this by moving its generation to
devm_cxl_add_port(). This unifies the messages and reduces code
duplication. Also, generate messages on failure. Use a
__devm_cxl_add_port() wrapper to keep the readability of the error
exits.
Signed-off-by: Robert Richter <rrichter@amd.com>
Link: https://lore.kernel.org/r/20221018132341.76259-4-rrichter@amd.com
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
The kernel enforces that region granularity is >= to the top-level
interleave-granularity for the given CXL window. However, when the CXL
window interleave is x1, i.e. non-interleaved at the host bridge level,
then the specified granularity does not matter. Override the window
specified granularity to the CXL minimum so that any valid region
granularity is >= to the root granularity.
Reported-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Reviewed-by: Vishal Verma <vishal.l.verma@intel.com>
Reviewed-by: Alison Schofield <alison.schofield@intel.com>
Link: https://lore.kernel.org/r/165853776917.2430596.16823264262010844458.stgit@dwillia2-xfh.jf.intel.com
[djbw: add CXL_DECODER_MIN_GRANULARITY per vishal]
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
In support of CXL unit tests in the ndctl project, arrange for the
cxl_acpi driver to load in response to the registration of cxl_test
devices.
Reported-by: Dave Jiang <dave.jiang@intel.com>
Tested-by: Dave Jiang <dave.jiang@intel.com>
Reviewed-by: Vishal Verma <vishal.l.verma@intel.com>
Link: https://lore.kernel.org/r/165853775783.2430596.13637998086505316619.stgit@dwillia2-xfh.jf.intel.com
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
At the time that cxl_port instances are being created, cache the dport
from the parent port that points to this new child port. This will be
useful for region provisioning when walking the tree to calculate
decoder targets, and saves rewalking the dport list after the fact to
build this information.
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Link: https://lore.kernel.org/r/20220624041950.559155-1-dan.j.williams@intel.com
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Previously the target routing specifics of switch decoders were factored
out of 'struct cxl_decoder' into 'struct cxl_switch_decoder'.
This patch, 2 of 3, adds a 'struct cxl_root_decoder' as a superset of a
switch decoder that also track the associated CXL window platform
resource.
Note that the reason the resource for a given root decoder needs to be
looked up after the fact (i.e. after cxl_parse_cfmws() and
add_cxl_resource()) is because add_cxl_resource() may have merged CXL
windows in order to keep them at the top of the resource tree / decode
hierarchy.
Co-developed-by: Ben Widawsky <bwidawsk@kernel.org>
Signed-off-by: Ben Widawsky <bwidawsk@kernel.org>
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Link: https://lore.kernel.org/r/165784326541.1758207.9915663937394448341.stgit@dwillia2-xfh.jf.intel.com
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Recall that CXL capable address ranges, on ACPI platforms, are published
in the CEDT.CFMWS (CXL Early Discovery Table: CXL Fixed Memory Window
Structures). These windows represent both the actively mapped capacity
and the potential address space that can be dynamically assigned to a
new CXL decode configuration (region / interleave-set).
CXL endpoints like DDR DIMMs can be mapped at any physical address
including 0 and legacy ranges.
There is an expectation and requirement that the /proc/iomem interface
and the iomem_resource tree in the kernel reflect the full set of
platform address ranges. I.e. that every address range that platform
firmware and bus drivers enumerate be reflected as an iomem_resource
entry. The hard requirement to do this for CXL arises from the fact that
facilities like CONFIG_DEVICE_PRIVATE expect to be able to treat empty
iomem_resource ranges as free for software to use as proxy address
space. Without CXL publishing its potential address ranges in
iomem_resource, the CONFIG_DEVICE_PRIVATE mechanism may inadvertently
steal capacity reserved for runtime provisioning of new CXL regions.
So, iomem_resource needs to know about both active and potential CXL
resource ranges. The active CXL resources might already be reflected in
iomem_resource as "System RAM". insert_resource_expand_to_fit() handles
re-parenting "System RAM" underneath a CXL window.
The "_expand_to_fit()" behavior handles cases where a CXL window is not
a strict superset of an existing entry in the iomem_resource tree. The
"_expand_to_fit()" behavior is acceptable from the perspective of
resource allocation. The expansion happens because a conflicting
resource range is already populated, which means the resource boundary
expansion does not result in any additional free CXL address space being
made available. CXL address space allocation is always bounded by the
orginal unexpanded address range.
However, the potential for expansion does mean that something like
walk_iomem_res_desc(IORES_DESC_CXL...) can only return fuzzy answers on
corner case platforms that cause the resource tree to expand a CXL
window resource over a range that is not decoded by CXL. This would be
an odd platform configuration, but if it becomes a problem in practice
the CXL subsytem could just publish an API that returns definitive
answers.
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: David Hildenbrand <david@redhat.com>
Cc: Jason Gunthorpe <jgg@nvidia.com>
Cc: Tony Luck <tony.luck@intel.com>
Cc: Christoph Hellwig <hch@lst.de>
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Link: https://lore.kernel.org/r/165784325943.1758207.5310344844375305118.stgit@dwillia2-xfh.jf.intel.com
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Currently 'struct cxl_decoder' contains the superset of attributes
needed for all decoder types. Before more type-specific attributes are
added to the common definition, reorganize 'struct cxl_decoder' into type
specific objects.
This patch, the first of three, factors out a cxl_switch_decoder type.
See the new kdoc for what a 'struct cxl_switch_decoder' represents in a
CXL topology.
Co-developed-by: Ben Widawsky <bwidawsk@kernel.org>
Signed-off-by: Ben Widawsky <bwidawsk@kernel.org>
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Reported-by: kernel test robot <lkp@intel.com>
Link: https://lore.kernel.org/r/165784325340.1758207.5064717153608954960.stgit@dwillia2-xfh.jf.intel.com
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Interleave granularity and ways have CXL specification defined encodings.
Promote the conversion helpers to a common header, and use them to
replace other open-coded instances.
Force caller to consider the error case of the conversion similarly to
other conversion helpers like kstrto*().
Co-developed-by: Ben Widawsky <bwidawsk@kernel.org>
Signed-off-by: Ben Widawsky <bwidawsk@kernel.org>
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Link: https://lore.kernel.org/r/165603875016.551046.17236943065932132355.stgit@dwillia2-xfh
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Root decoders are responsible for hosting the available host address
space for endpoints and regions to claim. The tracking of that available
capacity can be done in iomem_resource directly. As a result, root
decoders no longer need to host their own resource tree. The
current ->platform_res attribute was added prematurely.
Otherwise, ->hpa_range fills the role of conveying the current decode
range of the decoder.
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Reviewed-by: Adam Manzanares <a.manzanares@samsung.com>
Link: https://lore.kernel.org/r/165603873619.551046.791596854070136223.stgit@dwillia2-xfh
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
The CXL "root" device, ACPI0017, is an attach point for coordinating
platform level CXL resources and is the parent device for a CXL port
topology tree. As such it has distinct locking rules relative to other
CXL subsystem objects, but because it is an ACPI device the lock class
is established well before it is given to the cxl_acpi driver.
However, the lockdep API does support changing the lock class "live" for
situations like this. Add a device_lock_set_class() helper that a driver
can use in ->probe() to set a custom lock class, and
device_lock_reset_class() to return to the default "no validate" class
before the custom lock class key goes out of scope after ->remove().
Note the helpers are all macros to support dead code elimination in the
CONFIG_PROVE_LOCKING=n case, however device_set_lock_class() still needs
#ifdef CONFIG_PROVE_LOCKING since lockdep_match_class() explicitly does
not have a helper in the CONFIG_PROVE_LOCKING=n case (see comment in
lockdep.h). The lockdep API needs 2 small tweaks to prevent "unused"
warnings for the @key argument to lock_set_class(), and a new
lock_set_novalidate_class() is added to supplement
lockdep_set_novalidate_class() in the cases where the lock class is
converted while the lock is held.
Suggested-by: Peter Zijlstra <peterz@infradead.org>
Cc: "Rafael J. Wysocki" <rafael@kernel.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Will Deacon <will@kernel.org>
Cc: Waiman Long <longman@redhat.com>
Cc: Boqun Feng <boqun.feng@gmail.com>
Cc: Alison Schofield <alison.schofield@intel.com>
Cc: Vishal Verma <vishal.l.verma@intel.com>
Cc: Ben Widawsky <ben.widawsky@intel.com>
Cc: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Reviewed-by: Ira Weiny <ira.weiny@intel.com>
Link: https://lore.kernel.org/r/165100081305.1528964.11138612430659737238.stgit@dwillia2-desk3.amr.corp.intel.com
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
At this point the subsystem can enumerate all CXL ports (CXL.mem decode
resources in upstream switch ports and host bridges) in a system. The
last mile is connecting those ports to endpoints.
The cxl_mem driver connects an endpoint device to the platform CXL.mem
protoctol decode-topology. At ->probe() time it walks its
device-topology-ancestry and adds a CXL Port object at every Upstream
Port hop until it gets to CXL root. The CXL root object is only present
after a platform firmware driver registers platform CXL resources. For
ACPI based platform this is managed by the ACPI0017 device and the
cxl_acpi driver.
The ports are registered such that disabling a given port automatically
unregisters all descendant ports, and the chain can only be registered
after the root is established.
Given ACPI device scanning may run asynchronously compared to PCI device
scanning the root driver is tasked with rescanning the bus after the
root successfully probes.
Conversely if any ports in a chain between the root and an endpoint
becomes disconnected it subsequently triggers the endpoint to
unregister. Given lock depenedencies the endpoint unregistration happens
in a workqueue asynchronously. If userspace cares about synchronizing
delayed work after port events the /sys/bus/cxl/flush attribute is
available for that purpose.
Reported-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Ben Widawsky <ben.widawsky@intel.com>
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
[djbw: clarify changelog, rework hotplug support]
Link: https://lore.kernel.org/r/164398782997.903003.9725273241627693186.stgit@dwillia2-desk3.amr.corp.intel.com
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
So far the platorm level CXL resources have been enumerated by the
cxl_acpi driver, and cxl_pci has gathered all the pre-requisite
information it needs to fire up a cxl_mem driver. However, the first
thing the cxl_mem driver will be tasked to do is validate that all the
PCIe Switches in its ancestry also have CXL capabilities and an CXL.mem
link established.
Provide a common mechanism for a CXL.mem endpoint driver to enumerate
all the ancestor CXL ports in the topology and validate CXL.mem
connectivity.
Multiple endpoints may end up racing to establish a shared port in the
topology. This race is resolved via taking the device-lock on a parent
CXL Port before establishing a new child. The winner of the race
establishes the port, the loser simply registers its interest in the
port via 'struct cxl_ep' place-holder reference.
At endpoint teardown the same parent port lock is taken as 'struct
cxl_ep' references are deleted. Last endpoint to drop its reference
unregisters the port.
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Link: https://lore.kernel.org/r/164398731146.902644.1029761300481366248.stgit@dwillia2-desk3.amr.corp.intel.com
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Now that dport and decoder enumeration is centralized in the port
driver, the @host argument for these helpers can be made implicit. For
the root port the host is the port's uport device (ACPI0017 for
cxl_acpi), and for all other descendant ports the devm context is the
parent of @port.
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Reviewed-by: Ben Widawsky <ben.widawsky@intel.com>
Link: https://lore.kernel.org/r/164375043390.484143.17617734732003230076.stgit@dwillia2-desk3.amr.corp.intel.com
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
The need for a CXL port driver and a dedicated cxl_bus_type is driven by
a need to simultaneously support 2 independent physical memory decode
domains (cache coherent CXL.mem and uncached PCI.mmio) that also
intersect at a single PCIe device node. A CXL Port is a device that
advertises a CXL Component Register block with an "HDM Decoder
Capability Structure".
>From Documentation/driver-api/cxl/memory-devices.rst:
Similar to how a RAID driver takes disk objects and assembles them into
a new logical device, the CXL subsystem is tasked to take PCIe and ACPI
objects and assemble them into a CXL.mem decode topology. The need for
runtime configuration of the CXL.mem topology is also similar to RAID in
that different environments with the same hardware configuration may
decide to assemble the topology in contrasting ways. One may choose
performance (RAID0) striping memory across multiple Host Bridges and
endpoints while another may opt for fault tolerance and disable any
striping in the CXL.mem topology.
The port driver identifies whether an endpoint Memory Expander is
connected to a CXL topology. If an active (bound to the 'cxl_port'
driver) CXL Port is not found at every PCIe Switch Upstream port and an
active "root" CXL Port then the device is just a plain PCIe endpoint
only capable of participating in PCI.mmio and DMA cycles, not CXL.mem
coherent interleave sets.
The 'cxl_port' driver lets the CXL subsystem leverage driver-core
infrastructure for setup and teardown of register resources and
communicating device activation status to userspace. The cxl_bus_type
can rendezvous the async arrival of platform level CXL resources (via
the 'cxl_acpi' driver) with the asynchronous enumeration of Memory
Expander endpoints, while also implementing a hierarchical locking model
independent of the associated 'struct pci_dev' locking model. The
locking for dport and decoder enumeration is now handled in the core
rather than callers.
For now the port driver only enumerates and registers CXL resources
(downstream port metadata and decoder resources) later it will be used
to take action on its decoders in response to CXL.mem region
provisioning requests.
Note1: cxlpci.h has long depended on pci.h, but port.c was the first to
not include pci.h. Carry that dependency in cxlpci.h.
Note2: cxl port enumeration and probing complicates CXL subsystem init
to the point that it helps to have centralized debug logging of probe
events in cxl_bus_probe().
Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: Ben Widawsky <ben.widawsky@intel.com>
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Co-developed-by: Dan Williams <dan.j.williams@intel.com>
Link: https://lore.kernel.org/r/164374948116.464348.1772618057599155408.stgit@dwillia2-desk3.amr.corp.intel.com
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Unlike the decoder enumeration for "root decoders" described by platform
firmware, standard decoders can be enumerated from the component
registers space once the base address has been identified (via PCI,
ACPI, or another mechanism).
Add common infrastructure for HDM (Host-managed-Device-Memory) Decoder
enumeration and share it between host-bridge, upstream switch port, and
cxl_test defined decoders.
The locking model for switch level decoders is to hold the port lock
over the enumeration. This facilitates moving the dport and decoder
enumeration to a 'port' driver. For now, the only enumerator of decoder
resources is the cxl_acpi root driver.
Co-developed-by: Ben Widawsky <ben.widawsky@intel.com>
Signed-off-by: Ben Widawsky <ben.widawsky@intel.com>
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Link: https://lore.kernel.org/r/164374688404.395335.9239248252443123526.stgit@dwillia2-desk3.amr.corp.intel.com
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
The core houses infrastructure for decoder resources. A CXL port's
dports are more closely related to decoder infrastructure than topology
enumeration. Implement generic PCI based dport enumeration in the core,
i.e. arrange for existing root port enumeration from cxl_acpi to share
code with switch port enumeration which just amounts to a small
difference in a pci_walk_bus() invocation once the appropriate 'struct
pci_bus' has been retrieved.
Set the convention that decoder objects are registered after all dports
are enumerated. This enables userspace to know when the CXL core is
finished establishing 'dportX' links underneath the 'portX' object.
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Link: https://lore.kernel.org/r/164368114191.354031.5270501846455462665.stgit@dwillia2-desk3.amr.corp.intel.com
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Similar to the mem.h rename, if the core wants to reuse definitions from
drivers/cxl/pci.h it is unable to use <pci.h> as that collides with
archs that have an arch/$arch/include/asm/pci.h, like MIPS.
Reported-by: kernel test robot <lkp@intel.com>
Acked-by: Ben Widawsky <ben.widawsky@intel.com>
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Link: https://lore.kernel.org/r/164298422510.3018233.14693126572756675563.stgit@dwillia2-desk3.amr.corp.intel.com
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Add a helper for converting a PCI enumerated cxl_port into the pci_bus
that hosts its dports. For switch ports this is trivial, but for root
ports there is no generic way to go from a platform defined host bridge
device, like ACPI0016 to its corresponding pci_bus. Rather than spill
ACPI goop outside of the cxl_acpi driver, just arrange for it to
register an xarray translation from the uport device to the
corresponding pci_bus.
This is in preparation for centralizing dport enumeration in the core.
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Reviewed-by: Ben Widawsky <ben.widawsky@intel.com>
Link: https://lore.kernel.org/r/164364745633.85488.9744017377155103992.stgit@dwillia2-desk3.amr.corp.intel.com
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
When CONFIG_PROVE_LOCKING is enabled the 'struct device' definition gets
an additional mutex that is not clobbered by
lockdep_set_novalidate_class() like the typical device_lock(). This
allows for local annotation of subsystem locks with mutex_lock_nested()
per the subsystem's object/lock hierarchy. For CXL, this primarily needs
the ability to lock ports by depth and child objects of ports by their
parent parent-port lock.
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Reviewed-by: Ben Widawsky <ben.widawsky@intel.com>
Link: https://lore.kernel.org/r/164365853422.99383.1052399160445197427.stgit@dwillia2-desk3.amr.corp.intel.com
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Unused CXL decoders, or ports which use a passthrough decoder (no HDM
decoder registers) are expected to be initialized in a specific way.
Since upcoming drivers will want the same initialization, and it was
already a requirement to have consumers of the API configure the decoder
specific to their needs, initialize to this passthrough state by
default.
Signed-off-by: Ben Widawsky <ben.widawsky@intel.com>
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Link: https://lore.kernel.org/r/164298418778.3018233.13573986275832546547.stgit@dwillia2-desk3.amr.corp.intel.com
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Add wrappers for the creation of decoder objects at the root level and
switch level, and keep the core helper private to cxl/core/port.c. Root
decoders are static descriptors conveyed from platform firmware (e.g.
ACPI CFMWS). Switch decoders are CXL standard decoders enumerated via
the HDM decoder capability structure. The base address for the HDM
decoder capability structure may be conveyed either by PCIe or platform
firmware (ACPI CEDT.CHBS).
Additionally, the kdoc descriptions for these helpers and their
dependencies is updated.
Signed-off-by: Ben Widawsky <ben.widawsky@intel.com>
[djbw: fixup changelog, clarify kdoc]
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Link: https://lore.kernel.org/r/164366463014.111117.9714595404002687111.stgit@dwillia2-desk3.amr.corp.intel.com
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
CXL decoders manage address ranges in a hierarchical fashion whereby a
leaf is a unique subregion of its parent decoder (midlevel or root). It
therefore makes sense to use the resource API for handling this.
Reviewed-by: Dan Williams <dan.j.williams@intel.com>
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com> (v1)
Signed-off-by: Ben Widawsky <ben.widawsky@intel.com>
Link: https://lore.kernel.org/r/164298417191.3018233.5201055578165414714.stgit@dwillia2-desk3.amr.corp.intel.com
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
This implements the TODO in cxl_acpi for mapping component registers.
cxl_acpi becomes the second consumer of CXL register block enumeration
(cxl_pci being the first). Moving the functionality to cxl_core allows
both of these drivers to use the functionality. Equally importantly it
allows cxl_core to use the functionality in the future.
CXL 2.0 root ports are similar to CXL 2.0 Downstream Ports with the main
distinction being they're a part of the CXL 2.0 host bridge. While
mapping their component registers is not immediately useful for the CXL
drivers, the movement of register block enumeration into core is a vital
step towards HDM decoder programming.
Signed-off-by: Ben Widawsky <ben.widawsky@intel.com>
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
[djbw: fix cxl_regmap_to_base() failure cases]
Link: https://lore.kernel.org/r/164298415080.3018233.14694957480228676592.stgit@dwillia2-desk3.amr.corp.intel.com
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
During NUMA init, CXL memory defined in the SRAT Memory Affinity
subtable may be assigned to a NUMA node. Since there is no
requirement that the SRAT be comprehensive for CXL memory another
mechanism is needed to assign NUMA nodes to CXL memory not identified
in the SRAT.
Use the CXL Fixed Memory Window Structure (CFMWS) of the ACPI CXL
Early Discovery Table (CEDT) to find all CXL memory ranges.
Create a NUMA node for each CFMWS that is not already assigned to
a NUMA node. Add a memblk attaching its host physical address
range to the node.
Note that these ranges may not actually map any memory at boot time.
They may describe persistent capacity or may be present to enable
hot-plug.
Consumers can use phys_to_target_node() to discover the NUMA node.
Signed-off-by: Alison Schofield <alison.schofield@intel.com>
Acked-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Link: https://lore.kernel.org/r/163553711933.2509508.2203471175679990.stgit@dwillia2-desk3.amr.corp.intel.com
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Now that cxl_acpi has been converted to use the core ACPI CEDT sub-table
parser, update cxl_test to inject CFMWS and CHBS data directly into
cxl_acpi's handlers.
Cc: Alison Schofield <alison.schofield@intel.com>
Acked-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Link: https://lore.kernel.org/r/163553711363.2509508.17428994087868269952.stgit@dwillia2-desk3.amr.corp.intel.com
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
The cxl_acpi driver originally open-coded its table parsing since the
ACPI subtable helpers were marked __init and only used in early NUMA
initialization. Now that those helpers have been exported for driver
usage replace the open-coded solution with the common one.
Cc: Alison Schofield <alison.schofield@intel.com>
Acked-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Link: https://lore.kernel.org/r/163553710810.2509508.14686373989517930921.stgit@dwillia2-desk3.amr.corp.intel.com
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
When an ACPI0016 Host Bridge device is present yet no corresponding
CEDT Host Bridge Structure (CHBS) exists, the ACPI probe method
fails.
Rather than fail, emit this warning and continue:
cxl_acpi ACPI0017:00: No CHBS found for Host Bridge: ACPI0016:02
This error may occur on systems that are not compliant with the
ACPI specification. Compliant systems include a CHBS entry for
every CXL host bridge that is present at boot.
Suggested-by: Ira Weiny <ira.weiny@intel.com>
Signed-off-by: Alison Schofield <alison.schofield@intel.com>
Tested-by: Vishal Verma <vishal.l.verma@intel.com>
Reviewed-by: Ira Weiny <ira.weiny@intel.com>
Link: https://lore.kernel.org/r/20211007213426.392644-1-alison.schofield@intel.com
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
The kbuild robot reports:
drivers/cxl/core/bus.c:516:1: warning: stack frame size (1032) exceeds
limit (1024) in function 'devm_cxl_add_decoder'
It is also the case the devm_cxl_add_decoder() is unwieldy to use for
all the different decoder types. Fix the stack usage by splitting the
creation into alloc and add steps. This also allows for context
specific construction before adding.
With the split the caller is responsible for registering a devm callback
to trigger device_unregister() for the decoder rather than it being
implicit in the decoder registration. I.e. the routine that calls alloc
is responsible for calling put_device() if the "add" operation fails.
Reported-by: kernel test robot <lkp@intel.com>
Reported-by: Nathan Chancellor <nathan@kernel.org>
Reported-by: Dan Carpenter <dan.carpenter@oracle.com>
Reviewed-by: Ben Widawsky <ben.widawsky@intel.com>
Link: https://lore.kernel.org/r/163225205828.3038145.6831131648369404859.stgit@dwillia2-desk3.amr.corp.intel.com
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
As found by cxl_test, the implementation populated the target_list for
the single dport exceptional case, it missed populating the target_list
for the typical multi-dport case. Root decoders always know their target
list at the beginning of time, and even switch-level decoders should
have a target list of one or more zeros by default, depending on the
interleave-ways setting.
Walk the hosting port's dport list and populate based on the passed in
map.
Move devm_cxl_add_passthrough_decoder() out of line now that it does the
work of generating a target_map.
Before:
$ cat /sys/bus/cxl/devices/root2/decoder*/target_list
0
0
After:
$ cat /sys/bus/cxl/devices/root2/decoder*/target_list
0
0,1,2,3
0
0,1,2,3
Where root2 is a CXL topology root object generated by 'cxl_test'.
Acked-by: Ben Widawsky <ben.widawsky@intel.com>
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Link: https://lore.kernel.org/r/163116439000.2460985.11713777051267946018.stgit@dwillia2-desk3.amr.corp.intel.com
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Create an environment for CXL plumbing unit tests. Especially when it
comes to an algorithm for HDM Decoder (Host-managed Device Memory
Decoder) programming, the availability of an in-kernel-tree emulation
environment for CXL configuration complexity and corner cases speeds
development and deters regressions.
The approach taken mirrors what was done for tools/testing/nvdimm/. I.e.
an external module, cxl_test.ko built out of the tools/testing/cxl/
directory, provides mock implementations of kernel APIs and kernel
objects to simulate a real world device hierarchy.
One feedback for the tools/testing/nvdimm/ proposal was "why not do this
in QEMU?". In fact, the CXL development community has developed a QEMU
model for CXL [1]. However, there are a few blocking issues that keep
QEMU from being a tight fit for topology + provisioning unit tests:
1/ The QEMU community has yet to show interest in merging any of this
support that has had patches on the list since November 2020. So,
testing CXL to date involves building custom QEMU with out-of-tree
patches.
2/ CXL mechanisms like cross-host-bridge interleave do not have a clear
path to be emulated by QEMU without major infrastructure work. This
is easier to achieve with the alloc_mock_res() approach taken in this
patch to shortcut-define emulated system physical address ranges with
interleave behavior.
The QEMU enabling has been critical to get the driver off the ground,
and may still move forward, but it does not address the ongoing needs of
a regression testing environment and test driven development.
This patch adds an ACPI CXL Platform definition with emulated CXL
multi-ported host-bridges. A follow on patch adds emulated memory
expander devices.
Acked-by: Ben Widawsky <ben.widawsky@intel.com>
Reported-by: Vishal Verma <vishal.l.verma@intel.com>
Link: https://lore.kernel.org/r/20210202005948.241655-1-ben.widawsky@intel.com [1]
Link: https://lore.kernel.org/r/163164680798.2831381.838684634806668012.stgit@dwillia2-desk3.amr.corp.intel.com
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
