- Oct 29, 2021
-
-
Ben Widawsky authored
Reduce maintenance burden of DVSEC query implementation by using the centralized PCI core implementation. Signed-off-by:
Ben Widawsky <ben.widawsky@intel.com> [djbw: kill cxl_pci_dvsec()] Reviewed-by:
Jonathan Cameron <Jonathan.Cameron@huawei.com> Link: https://lore.kernel.org/r/163379788528.692348.11581080806976608802.stgit@dwillia2-desk3.amr.corp.intel.com Signed-off-by:
Dan Williams <dan.j.williams@intel.com>
-
Ben Widawsky authored
In preparation for moving parts of register mapping to cxl_core, split cxl_pci_setup_regs() into a helper that finds register blocks, (cxl_find_regblock()), and a generic wrapper that probes the precise register sets within a block (cxl_setup_regs()). Move the actual mapping (cxl_map_regs()) of the only register-set that cxl_pci cares about (memory device registers) up a level from the former cxl_pci_setup_regs() into cxl_pci_probe(). With this change the unused component registers are no longer mapped, but the helpers are primed to move into the core. [djbw: drop cxl_map_regs() for component registers] Signed-off-by:
Ira Weiny <ira.weiny@intel.com> Reviewed-by:
-
Dan Williams authored
In addition to carrying @barno, @block_offset, and @reg_type, add @base to keep all map/unmap parameters in one object. The helpers cxl_{map,unmap}_regblock() handle adjusting @base to the @block_offset at map and unmap time. Document that @base incorporates @block_offset so that downstream consumers of a mapped cxl_register_map instance do not need perform any fixups / can use @base directly. Cc: Jonathan Cameron <Jonathan.Cameron@huawei.com> Reviewed-by: -
Ben Widawsky authored
The structure exists to pass around information about register mapping. Use it for passing @barno and @block_offset, and eliminate duplicate local variables. The helpers that use @map do not care about @cxlm, so just pass them a pdev instead. [djbw: reorder before cxl_pci_setup_regs() refactor to improver readability] Signed-off-by:
kernel test robot <lkp@intel.com> Reviewed-by:
-
Ben Widawsky authored
Quoting Dan, "... the request + release regions should probably just be dropped. It's not like any of the register enumeration would collide with someone else who already has the registers mapped. The collision only comes when the registers are mapped for their final usage, and that will have more precision in the request." Suggested-by:
-
Dan Williams authored
cxl_pci_map_regblock() may return an ERR_PTR(), but cxl_pci_setup_regs() is only prepared for NULL as the error case. Pick the minimal fix for -stable backport purposes and just have cxl_pci_map_regblock() return NULL for errors. Fixes: f8a7e8c2 ("cxl/pci: Reserve all device regions at once") Cc: <stable@vger.kernel.org> Reviewed-by:
-
Ben Widawsky authored
While interesting to driver developers, the dev_dbg message doesn't do much except clutter up logs. This information should be attainable through sysfs, and someday lspci like utilities. This change additionally helps reduce the LOC in a subsequent patch to refactor some of cxl_pci register mapping. Signed-off-by:
-
Ben Widawsky authored
In preparation for passing around the Register Block Indicator (RBI) as a parameter, it is desirable to convert the type to an enum so that the interface can use a well defined parameter. Signed-off-by:
-
- Oct 08, 2021
-
-
Alison Schofield authored
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:
Alison Schofield <alison.schofield@intel.com> Tested-by:
Vishal Verma <vishal.l.verma@intel.com> Reviewed-by:
-
- Sep 25, 2021
-
-
Kees Cook authored
Use the newly introduced struct_group_typed() macro to clean up the declaration of struct cxl_regs. Cc: Alison Schofield <alison.schofield@intel.com> Cc: Vishal Verma <vishal.l.verma@intel.com> Cc: Ira Weiny <ira.weiny@intel.com> Cc: Ben Widawsky <ben.widawsky@intel.com> Cc: linux-cxl@vger.kernel.org Suggested-by:
Kees Cook <keescook@chromium.org>
-
- Sep 21, 2021
-
-
Ben Widawsky authored
Commit 21e9f767 ("cxl: Rename mem to pci") introduced the cxl_pci driver which had formerly been named cxl_mem. At the time, the goal was to be as light touch as possible because there were other patches in flight. Since things have settled now, and a new cxl_mem driver will be introduced shortly, spend the LOC now to clean up the existing names. While here, fix the kernel docs to explain the situation better after the core rework that has already landed. Reviewed-by:
-
Dan Williams authored
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:Nathan Chancellor <nathan@kernel.org> Reported-by:
Dan Carpenter <dan.carpenter@oracle.com> Reviewed-by:
-
Dan Williams authored
Introduce an emulated device-set plus driver to register CXL memory devices, 'struct cxl_memdev' instances, in the mock cxl_test topology. This enables the development of HDM Decoder (Host-managed Device Memory Decoder) programming flow (region provisioning) in an environment that can be updated alongside the kernel as it gains more functionality. Whereas the cxl_pci module looks for CXL memory expanders on the 'pci' bus, the cxl_mock_mem module attaches to CXL expanders on the platform bus emitted by cxl_test. Acked-by:
-
Dan Williams authored
In preparation for cxl_test to mock responses to mailbox command requests, move some definitions from core/mbox.c to cxlmem.h. No functional changes intended. Acked-by:
-
Dan Williams authored
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:
-
Dan Williams authored
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:
-
Dan Williams authored
In preparation for a mocked unit test environment for CXL objects, allow for multiple unique nvdimm-bridge objects. For now, just allow multiple bridges to be registered. Later, when there are multiple present, further updates are needed to cxl_find_nvdimm_bridge() to identify which bridge is associated with which CXL hierarchy for nvdimm registration. Note that this does change the kernel device-name for the bridge object. User space should not have any attachment to the device name at this point as it is still early days in the CXL driver development. Acked-by:
-
Dan Williams authored
The LIBNVDIMM IOCTL UAPI calls back to the nvdimm-bus-provider to translate the Linux command payload to the device native command format. The LIBNVDIMM commands get-config-size, get-config-data, and set-config-data, map to the CXL memory device commands device-identify, get-lsa, and set-lsa. Recall that the label-storage-area (LSA) on an NVDIMM device arranges for the provisioning of namespaces. Additionally for CXL the LSA is used for provisioning regions as well. The data from device-identify is already cached in the 'struct cxl_mem' instance associated with @cxl_nvd, so that payload return is simply crafted and no CXL command is issued. The conversion for get-lsa is straightforward, but the conversion for set-lsa requires an allocation to append the set-lsa header in front of the payload. Reviewed-by:
-
Dan Williams authored
The CXL_PMEM driver expects exclusive control of the label storage area space. Similar to the LIBNVDIMM expectation that the label storage area is only writable from userspace when the corresponding memory device is not active in any region, the expectation is the native CXL_PCI UAPI path is disabled while the cxl_nvdimm for a given cxl_memdev device is active in LIBNVDIMM. Add the ability to toggle the availability of a given command for the UAPI path. Use that new capability to shutdown changes to partitions and the label storage area while the cxl_nvdimm device is actively proxying commands for LIBNVDIMM. Reviewed-by:
-
Dan Williams authored
Define enabled_cmds as an embedded member of 'struct cxl_mem' rather than a pointer to another dynamic allocation. As this leaves only one user of cxl_cmd_count, just open code it and delete the helper. Acked-by:
-
Dan Williams authored
Now that cxl_mem_{init,exit} no longer need to manage debugfs, switch back to the smaller form of the boiler plate. Acked-by: -
Dan Williams authored
Now that the internals of mailbox operations are abstracted from the PCI specifics a bulk of infrastructure can move to the core. The CXL_PMEM driver intends to proxy LIBNVDIMM UAPI and driver requests to the equivalent functionality provided by the CXL hardware mailbox interface. In support of that intent move the mailbox implementation to a shared location for the CXL_PCI driver native IOCTL path and CXL_PMEM nvdimm command proxy path to share. A unit test framework seeks to implement a unit test backend transport for mailbox commands to communicate mocked up payloads. It can reuse all of the mailbox infrastructure minus the PCI specifics, so that also gets moved to the core. Finally with the mailbox infrastructure and ioctl handling being transport generic there is no longer any need to pass file file_operations to devm_cxl_add_memdev(). That allows all the ioctl boilerplate to move into the core for unit test reuse. No functional change intended, just code movement. Acked-by:
-
Dan Williams authored
Commit 3d135db5 ("cxl/core: Move memdev management to core") left this straggling include for cxl_memdev setup. Clean it up. Cc: Ben Widawsky <ben.widawsky@intel.com> Reported-by:
-
Dan Williams authored
In preparation for implementing a unit test backend transport for ioctl operations, and making the mailbox available to the cxl/pmem infrastructure, move the existing PCI specific portion of mailbox handling to an "mbox_send" operation. With this split all the PCI-specific transport details are comprehended by a single operation and the rest of the mailbox infrastructure is 'struct cxl_mem' and 'struct cxl_memdev' generic. Acked-by:
-
Dan Williams authored
Commit 0b9159d0 ("cxl/pci: Store memory capacity values") missed updating the kernel-doc for 'struct cxl_mem' leading to the following warnings: ./scripts/kernel-doc -v drivers/cxl/cxlmem.h 2>&1 | grep warn drivers/cxl/cxlmem.h:107: warning: Function parameter or member 'total_bytes' not described in 'cxl_mem' drivers/cxl/cxlmem.h:107: warning: Function parameter or member 'volatile_only_bytes' not described in 'cxl_mem' drivers/cxl/cxlmem.h:107: warning: Function parameter or member 'persistent_only_bytes' not described in 'cxl_mem' drivers/cxl/cxlmem.h:107: warning: Function parameter or member 'partition_align_bytes' not described in 'cxl_mem' drivers/cxl/cxlmem.h:107: warning: Function parameter or member 'active_volatile_bytes' not described in 'cxl_mem' drivers/cxl/cxlmem.h:107: warning: Function parameter or member 'active_persistent_bytes' not described in 'cxl_mem' drivers/cxl/cxlmem.h:107: warning: Function parameter or member 'next_volatile_bytes' not described in 'cxl_mem' drivers/cxl/cxlmem.h:107: warning: Function parameter or member 'next_persistent_bytes' not described in 'cxl_mem' Also, it is redundant to describe those same parameters in the kernel-doc for cxl_mem_get_partition_info(). Given the only user of that routine updates the values in @cxlm, just do that implicitly internal to the helper. Cc: Ira Weiny <ira.weiny@intel.com> Reported-by:
-
Dan Williams authored
In preparation for adding a unit test provider of a cxl_memdev, convert the 'struct cxl_mem' driver context to carry a generic device rather than a pci device. Note, some dev_dbg() lines needed extra reformatting per clang-format. This conversion also allows the cxl_mem_create() and devm_cxl_add_memdev() calling conventions to be simplified. The "host" for a cxl_memdev, must be the same device for the driver that allocated @cxlm. Acked-by:
-
- Sep 07, 2021
-
-
Dan Williams authored
Commit 0f06157e ("cxl/core: Move register mapping infrastructure") neglected to add a DOC header for the new drivers/core/regs.c file. Reported-by:
-
Dan Williams authored
Commit 06737cd0 ("cxl/core: Move pmem functionality") neglected to add a DOC header for the new drivers/cxl/core/pmem.c file. Reported-by:
Jonathan Cameron <Jonathan.Cameron@huwei.com> Link: https://lore.kernel.org/r/163072206163.2250120.11486436976516079516.stgit@dwillia2-desk3.amr.corp.intel.com Signed-off-by:
-
Li Qiang (Johnny Li) authored
Indicator string for mbox and memdev register set to status incorrectly in error message. Cc: <stable@vger.kernel.org> Fixes: 30af9729 ("cxl/pci: Map registers based on capabilities") Signed-off-by:
Li Qiang (Johnny Li) <johnny.li@montage-tech.com> Reviewed-by:
-
Dan Williams authored
A proposed rework of security_locked_down() users identified that the cxl_pci driver was passing the wrong lockdown_reason. Update cxl_mem_raw_command_allowed() to fail raw command access when raw pci access is also disabled. Fixes: 13237183 ("cxl/mem: Add a "RAW" send command") Cc: Ben Widawsky <ben.widawsky@intel.com> Cc: Jonathan Cameron <Jonathan.Cameron@huawei.com> Cc: <stable@vger.kernel.org> Cc: Ondrej Mosnacek <omosnace@redhat.com> Cc: Paul Moore <paul@paul-moore.com> Link: https://lore.kernel.org/r/163072204525.2250120.16615792476976546735.stgit@dwillia2-desk3.amr.corp.intel.com Signed-off-by:
-
Alison Schofield authored
During CXL ACPI probe, host bridge ports are discovered by scanning the ACPI0017 root port for ACPI0016 host bridge devices. The scan matches on the hardware id of "ACPI0016". An issue occurs when an ACPI0016 device is defined in the DSDT yet disabled on the platform. Attempts by the cxl_acpi driver to add host bridge ports using a disabled device fails, and the entire cxl_acpi probe fails. The DSDT table includes an _STA method that sets the status and the ACPI subsystem has checks available to examine it. One such check is in the acpi_pci_find_root() path. Move the call to acpi_pci_find_root() to the matching function to prevent this issue when adding either upstream or downstream ports. Suggested-by:
-
- Aug 11, 2021
-
-
Ira Weiny authored
CXL spec defines the volatile DPA range to be 0 to Volatile memory size. It further defines the persistent DPA range to follow directly after the end of the Volatile DPA through the persistent memory size. Essentially Volatile DPA range = [0, Volatile size) Persistent DPA range = [Volatile size, Volatile size + Persistent size) Adjust the pmem_range start to reflect this and remote the TODO. Signed-off-by:
-
- Aug 10, 2021
-
-
Ira Weiny authored
Memory devices may specify volatile only, persistent only, and partitionable space which when added together result in a total capacity. If Identify Memory Device.Partition Alignment != 0 the device supports partitionable space. This partitionable space can be split between volatile and persistent space. The total volatile and persistent sizes are reported in Get Partition Info. ie active volatile memory = volatile only + partitionable volatile active persistent memory = persistent only + partitionable persistent Define cxl_mem_get_partition(), check for partitionable support, and use cxl_mem_get_partition() if applicable. Reviewed-by:
-
- Aug 07, 2021
-
-
Ira Weiny authored
The Identify Memory Device command returns information about the volatile only and persistent only memory capacities. Store those values in the cxl_mem structure for later use. While at it, reuse those calculations to calculate the ram and pmem ranges. Signed-off-by:
-
- Aug 06, 2021
-
-
Ben Widawsky authored
It is desirable to retain the mappings from the calling function. By simplifying this code, it will be much more straightforward to do that. Signed-off-by:
-
Ben Widawsky authored
In an effort to explicit avoid supporting vendor specific register blocks (which can happily be mapped from userspace), entirely skip probing unknown types. The secondary benefit of this will be revealed in the future with code simplification. Signed-off-by:
-
Ben Widawsky authored
The motivation for moving cxl_memdev allocation to the core (beyond better file organization of sysfs attributes in core/ and drivers in cxl/), is that device lifetime is longer than module lifetime. The cxl_pci module should be free to come and go without needing to coordinate with devices that need the text associated with cxl_memdev_release() to stay resident. The move fixes a use after free bug when looping driver load / unload with CONFIG_DEBUG_KOBJECT_RELEASE=y. Another motivation for disconnecting cxl_memdev creation from cxl_pci is to enable other drivers, like a unit test driver, to registers memdevs. Fixes: b39cb105 ("cxl/mem: Register CXL memX devices") Signed-off-by:
-
Dan Williams authored
In preparation for moving cxl_memdev allocation to the core, introduce cdevm_file_operations to coordinate file operations shutdown relative to driver data release. The motivation for moving cxl_memdev allocation to the core (beyond better file organization of sysfs attributes in core/ and drivers in cxl/), is that device lifetime is longer than module lifetime. The cxl_pci module should be free to come and go without needing to coordinate with devices that need the text associated with cxl_memdev_release() to stay resident. The move will fix a use after free bug when looping driver load / unload with CONFIG_DEBUG_KOBJECT_RELEASE=y. Another motivation for passing in file_operations to the core cxl_memdev creation flow is to allow for alternate drivers, like unit test code, to define their own ioctl backends. Signed-off-by:
-
Dan Williams authored
The register mapping infrastructure is large enough to move to its own compilation unit. This also cleans up an unnecessary include of <mem.h> core/bus.c. Reported-by:
-
Dan Williams authored
Refactor the pmem / nvdimm-bridge functionality from core/bus.c to core/pmem.c. Introduce drivers/core/core.h to communicate data structures and helpers between the core bus and other functionality that registers devices on the bus. Signed-off-by:
-
