Pull CXL updates from Dave Jiang: - Introduce cxl_memdev_attach and pave way for soft reserved handling, type2 accelerator enabling, and LSA 2.0 enabling. All these series require the endpoint driver to settle before continuing the memdev driver probe. - Address CXL port error protocol handling and reporting. The large patch series was split into three parts. The first two parts are included here with the final part coming later. The first part consists of a series of code refactoring to PCI AER sub-system that addresses CXL and also CXL RAS code to prepare for port error handling. The second part refactors the CXL code to move management of component registers to cxl_port objects to allow all CXL AER errors to be handled through the cxl_port hierarchy. - Provide AMD Zen5 platform address translation for CXL using ACPI PRMT. This includes a conventions document to explain why this is needed and how it's implemented. - Misc CXL patches of fixes, cleanups, and updates. Including CXL address translation for unaligned MOD3 regions. [ TLA service: CXL is "Compute Express Link" ] * tag 'cxl-for-7.0' of git://git.kernel.org/pub/scm/linux/kernel/git/cxl/cxl: (59 commits) cxl: Disable HPA/SPA translation handlers for Normalized Addressing cxl/region: Factor out code into cxl_region_setup_poison() cxl/atl: Lock decoders that need address translation cxl: Enable AMD Zen5 address translation using ACPI PRMT cxl/acpi: Prepare use of EFI runtime services cxl: Introduce callback for HPA address ranges translation cxl/region: Use region data to get the root decoder cxl/region: Add @hpa_range argument to function cxl_calc_interleave_pos() cxl/region: Separate region parameter setup and region construction cxl: Simplify cxl_root_ops allocation and handling cxl/region: Store HPA range in struct cxl_region cxl/region: Store root decoder in struct cxl_region cxl/region: Rename misleading variable name @hpa to @hpa_range Documentation/driver-api/cxl: ACPI PRM Address Translation Support and AMD Zen5 enablement cxl, doc: Moving conventions in separate files cxl, doc: Remove isonum.txt inclusion cxl/port: Unify endpoint and switch port lookup cxl/port: Move endpoint component register management to cxl_port cxl/port: Map Port RAS registers cxl/port: Move dport RAS setup to dport add time ...
Fixup and refactor downstream port enumeration to prepare for CXL port protocol error handling. Main motivation is to move endpoint component register mapping to a port object. cxl/port: Unify endpoint and switch port lookup cxl/port: Move endpoint component register management to cxl_port cxl/port: Map Port RAS registers cxl/port: Move dport RAS setup to dport add time cxl/port: Move dport probe operations to a driver event cxl/port: Move decoder setup before dport creation cxl/port: Cleanup dport removal with a devres group cxl/port: Reduce number of @dport variables in cxl_port_add_dport() cxl/port: Cleanup handling of the nr_dports 0 -> 1 transition
Towards the end goal of making all CXL RAS capability handling uniform across host bridge ports, upstream switch ports, and endpoint ports, move dport RAS setup. Move it to cxl_switch_port_probe() context for switch / VH dports (via cxl_port_add_dport()) and cxl_endpoint_port_probe() context for an RCH dport. Rename the RAS setup helper to devm_cxl_dport_ras_setup() for symmetry with devm_cxl_switch_port_decoders_setup(). Only the RCH version needs to be exported and the cxl_test mocking can be deleted with a dev_is_pci() check on the dport_dev. Reviewed-by: Dave Jiang <dave.jiang@intel.com> Reviewed-by: Jonathan Cameron <jonathan.cameron@huawei.com> Tested-by: Terry Bowman <terry.bowman@amd.com> Signed-off-by: Dan Williams <dan.j.williams@intel.com> Link: https://patch.msgid.link/20260131000403.2135324-7-dan.j.williams@intel.com Signed-off-by: Dave Jiang <dave.jiang@intel.com>
In preparation for adding more register setup to the cxl_port_add_dport() path (for RAS register mapping), move the dport creation event to a driver callback. This achieves two goals, it puts driver operations logically where they belong, in a driver, and it obviates the gymnastics of DECLARE_TESTABLE() which just makes a mess of grepping for CXL symbols. In other words, a driver callback is less of an ongoing maintenance burden than this DECLARE_TESTABLE arrangement that does not scale and diminishes the grep-ability of the codebase. cxl_port_add_dport() moves mostly unmodified from drivers/cxl/core/port.c. The only deliberate change is that it now assumes that the device_lock is held on entry and the driver is attached (just like cxl_port_probe()). Reviewed-by: Terry Bowman <terry.bowman@amd.com> Tested-by: Terry Bowman <terry.bowman@amd.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> Link: https://patch.msgid.link/20260131000403.2135324-6-dan.j.williams@intel.com Signed-off-by: Dave Jiang <dave.jiang@intel.com>
Translation functions may return an invalid address in case of errors.
If the address is not checked the further use of the invalid value
will cause an address corruption.
Consistently check for a valid address returned by translation
functions. Use RESOURCE_SIZE_MAX to indicate an invalid address for
type resource_size_t. Depending on the type either RESOURCE_SIZE_MAX
or ULLONG_MAX is used to indicate an address error.
Propagating an invalid address from a failed translation may cause
userspace to think it has received a valid SPA, when in fact it is
wrong. The CXL userspace API, using trace events, expects ULLONG_MAX
to indicate a translation failure. If ULLONG_MAX is not returned
immediately, subsequent calculations can transform that bad address
into a different value (!ULLONG_MAX), and an invalid SPA may be
returned to userspace. This can lead to incorrect diagnostics and
erroneous corrective actions.
[ dj: Added user impact statement from Alison. ]
[ dj: Fixed checkpatch tab alignment issue. ]
Reviewed-by: Dave Jiang <dave.jiang@intel.com>
Signed-off-by: Robert Richter <rrichter@amd.com>
Fixes: c3dd67681c70 ("cxl/region: Add inject and clear poison by region offset")
Fixes: b78b9e7b7979 ("cxl/region: Refactor address translation funcs for testing")
Reviewed-by: Alison Schofield <alison.schofield@intel.com>
Reviewed-by: Jonathan Cameron <jonathan.cameron@huawei.com>
Link: https://patch.msgid.link/20260107120544.410993-1-rrichter@amd.com
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
Unlike the cxl_pci class driver that opportunistically enables memory expansion with no other dependent functionality, CXL accelerator drivers have distinct PCIe-only and CXL-enhanced operation states. If CXL is available some additional coherent memory/cache operations can be enabled, otherwise traditional DMA+MMIO over PCIe/CXL.io is a fallback. This constitutes a new mode of operation where the caller of devm_cxl_add_memdev() wants to make a "go/no-go" decision about running in CXL accelerated mode or falling back to PCIe-only operation. Part of that decision making process likely also includes additional CXL-acceleration-specific resource setup. Encapsulate both of those requirements into 'struct cxl_memdev_attach' that provides a ->probe() callback. The probe callback runs in cxl_mem_probe() context, after the port topology is successfully attached for the given memdev. It supports a contract where, upon successful return from devm_cxl_add_memdev(), everything needed for CXL accelerated operation has been enabled. Additionally the presence of @cxlmd->attach indicates that the accelerator driver be detached when CXL operation ends. This conceptually makes a CXL link loss event mirror a PCIe link loss event which results in triggering the ->remove() callback of affected devices+drivers. A driver can re-attach to recover back to PCIe-only operation. Live recovery, i.e. without a ->remove()/->probe() cycle, is left as a future consideration. [ dj: Repalce with updated commit log from Dan ] Cc: Smita Koralahalli <Smita.KoralahalliChannabasappa@amd.com> Reviewed-by: Ben Cheatham <benjamin.cheatham@amd.com> Reviewed-by: Dave Jiang <dave.jiang@intel.com> Tested-by: Alejandro Lucero <alucerop@amd.com> Reviewed-by: Jonathan Cameron <jonathan.cameron@huawei.com> Link: https://patch.msgid.link/20251216005616.3090129-7-dan.j.williams@intel.com Signed-off-by: Dan Williams <dan.j.williams@intel.com> Signed-off-by: Dave Jiang <dave.jiang@intel.com>
In all cases the device that created the 'struct cxl_dev_state' instance is also the device to host the devm cleanup of devm_cxl_add_memdev(). This simplifies the function prototype, and limits a degree of freedom of the API. Cc: Smita Koralahalli <Smita.KoralahalliChannabasappa@amd.com> Reviewed-by: Jonathan Cameron <jonathan.cameron@huawei.com> Reviewed-by: Alison Schofield <alison.schofield@intel.com> Reviewed-by: Dave Jiang <dave.jiang@intel.com> Reviewed-by: Ben Cheatham <benjamin.cheatham@amd.com> Tested-by: Alejandro Lucero <alucerop@amd.com> Link: https://patch.msgid.link/20251216005616.3090129-6-dan.j.williams@intel.com Signed-off-by: Dan Williams <dan.j.williams@intel.com> Signed-off-by: Dave Jiang <dave.jiang@intel.com>
- Remove ret_limit race condition in mock_get_event() - Assign overflow_err_count from log->nr_overflow
mock_get_event() uses an uninitialized local variable, nr_overflow, to populate the overflow_err_count field. That results in incorrect overflow_err_count values in mocked cxl_overflow trace events, such as this case where the records are reported as 0 and should be non-zero: [] cxl_overflow: memdev=mem7 host=cxl_mem.6 serial=7: log=Failure : 0 records from 1763228189130895685 to 1763228193130896180 Fix by using log->nr_overflow and remove the unused local variable. A follow-up change was considered in cxl_mem_get_records_log() to confirm that the overflow_err_count is non-zero when the overflow flag is set [1]. Since the driver has no functional dependency on this constraint, and a device that violates this specific requirement does not cause incorrect driver behavior, no validation check is added. [1] CXL 3.2, Table 8-65 Get Event Records Output Payload Signed-off-by: Alison Schofield <alison.schofield@intel.com> Reviewed-by: Ira Weiny <ira.weiny@intel.com> Reviewed-by: Dave Jiang <dave.jiang@intel.com>> --- Link: https://patch.msgid.link/20251116013036.1713313-1-alison.schofield@intel.com Signed-off-by: Dave Jiang <dave.jiang@intel.com>
Commit 364ee9f3265e ("cxl/test: Enhance event testing") changed the
loop iterator in mock_get_event() from a static constant,
CXL_TEST_EVENT_CNT, to a dynamic global variable, ret_limit. The
intent was to vary the number of events returned per call to simulate
events occurring while logs are being read.
However, ret_limit is modified without synchronization. When multiple
threads call mock_get_event() concurrently, one thread may read
ret_limit, another thread may increment it, and the first thread's
loop condition and size calculation see and use the updated value.
This is visible during cxl_test module load when all memdevs are
initializing simultaneously, which includes getting event records. It
is not tied to the cxl-events.sh unit test specifically, as that
operates on a single memdev.
While no actual harm results (the buffer is always large enough and
the record count fields correctly reflect what was written), this is
a correctness issue. The race creates an inconsistent state within
mock_get_event() and adding variability based on a race appears
unintended.
Make ret_limit a local variable populated from an atomic counter. Each
call gets a stable value that won't change during execution. That
preserves the intended behavior of varying the return counts across
calls while eliminating the race condition.
This implementation uses "+ 1" to produce the full range of 1 to
CXL_TEST_EVENT_RET_MAX (4) records. Previously only 1, 2, 3 were
produced.
Signed-off-by: Alison Schofield <alison.schofield@intel.com>
Reviewed-by: Ira Weiny <ira.weiny@intel.com>
Reviewed-by: Dave Jiang <dave.jiang@intel.com>> ---
Link: https://patch.msgid.link/20251116013819.1713780-1-alison.schofield@intel.com
Signed-off-by: Dave Jiang <dave.jiang@intel.com>