Merge tag 'cxl-for-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/cxl/cxl

Pull Compute Express Link (CXL) updates from Dan Williams:
 "To date Linux has been dependent on platform-firmware to map CXL RAM
  regions and handle events / errors from devices. With this update we
  can now parse / update the CXL memory layout, and report events /
  errors from devices. This is a precursor for the CXL subsystem to
  handle the end-to-end "RAS" flow for CXL memory. i.e. the flow that
  for DDR-attached-DRAM is handled by the EDAC driver where it maps
  system physical address events to a field-replaceable-unit (FRU /
  endpoint device). In general, CXL has the potential to standardize
  what has historically been a pile of memory-controller-specific error
  handling logic.

  Another change of note is the default policy for handling RAM-backed
  device-dax instances. Previously the default access mode was "device",
  mmap(2) a device special file to access memory. The new default is
  "kmem" where the address range is assigned to the core-mm via
  add_memory_driver_managed(). This saves typical users from wondering
  why their platform memory is not visible via free(1) and stuck behind
  a device-file. At the same time it allows expert users to deploy
  policy to, for example, get dedicated access to high performance
  memory, or hide low performance memory from general purpose kernel
  allocations. This affects not only CXL, but also systems with
  high-bandwidth-memory that platform-firmware tags with the
  EFI_MEMORY_SP (special purpose) designation.

  Summary:

   - CXL RAM region enumeration: instantiate 'struct cxl_region' objects
     for platform firmware created memory regions

   - CXL RAM region provisioning: complement the existing PMEM region
     creation support with RAM region support

   - "Soft Reservation" policy change: Online (memory hot-add)
     soft-reserved memory (EFI_MEMORY_SP) by default, but still allow
     for setting aside such memory for dedicated access via device-dax.

   - CXL Events and Interrupts: Takeover CXL event handling from
     platform-firmware (ACPI calls this CXL Memory Error Reporting) and
     export CXL Events via Linux Trace Events.

   - Convey CXL _OSC results to drivers: Similar to PCI, let the CXL
     subsystem interrogate the result of CXL _OSC negotiation.

   - Emulate CXL DVSEC Range Registers as "decoders": Allow for
     first-generation devices that pre-date the definition of the CXL
     HDM Decoder Capability to translate the CXL DVSEC Range Registers
     into 'struct cxl_decoder' objects.

   - Set timestamp: Per spec, set the device timestamp in case of
     hotplug, or if platform-firwmare failed to set it.

   - General fixups: linux-next build issues, non-urgent fixes for
     pre-production hardware, unit test fixes, spelling and debug
     message improvements"

* tag 'cxl-for-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/cxl/cxl: (66 commits)
  dax/kmem: Fix leak of memory-hotplug resources
  cxl/mem: Add kdoc param for event log driver state
  cxl/trace: Add serial number to trace points
  cxl/trace: Add host output to trace points
  cxl/trace: Standardize device information output
  cxl/pci: Remove locked check for dvsec_range_allowed()
  cxl/hdm: Add emulation when HDM decoders are not committed
  cxl/hdm: Create emulated cxl_hdm for devices that do not have HDM decoders
  cxl/hdm: Emulate HDM decoder from DVSEC range registers
  cxl/pci: Refactor cxl_hdm_decode_init()
  cxl/port: Export cxl_dvsec_rr_decode() to cxl_port
  cxl/pci: Break out range register decoding from cxl_hdm_decode_init()
  cxl: add RAS status unmasking for CXL
  cxl: remove unnecessary calling of pci_enable_pcie_error_reporting()
  dax/hmem: build hmem device support as module if possible
  dax: cxl: add CXL_REGION dependency
  cxl: avoid returning uninitialized error code
  cxl/pmem: Fix nvdimm registration races
  cxl/mem: Fix UAPI command comment
  cxl/uapi: Tag commands from cxl_query_cmd()
  ...

1 files changed, 94 insertions, 2 deletions

diff --git a/drivers/cxl/cxl.h b/drivers/cxl/cxl.h
index c9e1b48a1a53..f2b0962a552d 100644
--- a/drivers/cxl/cxl.h
+++ b/drivers/cxl/cxl.h
@@ -130,6 +130,7 @@ static inline int ways_to_eiw(unsigned int ways, u8 *eiw)
 #define   CXL_RAS_UNCORRECTABLE_STATUS_MASK (GENMASK(16, 14) | GENMASK(11, 0))
 #define CXL_RAS_UNCORRECTABLE_MASK_OFFSET 0x4
 #define   CXL_RAS_UNCORRECTABLE_MASK_MASK (GENMASK(16, 14) | GENMASK(11, 0))
+#define   CXL_RAS_UNCORRECTABLE_MASK_F256B_MASK BIT(8)
 #define CXL_RAS_UNCORRECTABLE_SEVERITY_OFFSET 0x8
 #define   CXL_RAS_UNCORRECTABLE_SEVERITY_MASK (GENMASK(16, 14) | GENMASK(11, 0))
 #define CXL_RAS_CORRECTABLE_STATUS_OFFSET 0xC
@@ -140,6 +141,8 @@ static inline int ways_to_eiw(unsigned int ways, u8 *eiw)
 #define CXL_RAS_CAP_CONTROL_FE_MASK GENMASK(5, 0)
 #define CXL_RAS_HEADER_LOG_OFFSET 0x18
 #define CXL_RAS_CAPABILITY_LENGTH 0x58
+#define CXL_HEADERLOG_SIZE SZ_512
+#define CXL_HEADERLOG_SIZE_U32 SZ_512 / sizeof(u32)
 
 /* CXL 2.0 8.2.8.1 Device Capabilities Array Register */
 #define CXLDEV_CAP_ARRAY_OFFSET 0x0
@@ -154,6 +157,22 @@ static inline int ways_to_eiw(unsigned int ways, u8 *eiw)
 #define CXLDEV_CAP_CAP_ID_SECONDARY_MAILBOX 0x3
 #define CXLDEV_CAP_CAP_ID_MEMDEV 0x4000
 
+/* CXL 3.0 8.2.8.3.1 Event Status Register */
+#define CXLDEV_DEV_EVENT_STATUS_OFFSET		0x00
+#define CXLDEV_EVENT_STATUS_INFO		BIT(0)
+#define CXLDEV_EVENT_STATUS_WARN		BIT(1)
+#define CXLDEV_EVENT_STATUS_FAIL		BIT(2)
+#define CXLDEV_EVENT_STATUS_FATAL		BIT(3)
+
+#define CXLDEV_EVENT_STATUS_ALL (CXLDEV_EVENT_STATUS_INFO |	\
+				 CXLDEV_EVENT_STATUS_WARN |	\
+				 CXLDEV_EVENT_STATUS_FAIL |	\
+				 CXLDEV_EVENT_STATUS_FATAL)
+
+/* CXL rev 3.0 section 8.2.9.2.4; Table 8-52 */
+#define CXLDEV_EVENT_INT_MODE_MASK	GENMASK(1, 0)
+#define CXLDEV_EVENT_INT_MSGNUM_MASK	GENMASK(7, 4)
+
 /* CXL 2.0 8.2.8.4 Mailbox Registers */
 #define CXLDEV_MBOX_CAPS_OFFSET 0x00
 #define   CXLDEV_MBOX_CAP_PAYLOAD_SIZE_MASK GENMASK(4, 0)
@@ -259,6 +278,8 @@ resource_size_t cxl_rcrb_to_component(struct device *dev,
  * cxl_decoder flags that define the type of memory / devices this
  * decoder supports as well as configuration lock status See "CXL 2.0
  * 8.2.5.12.7 CXL HDM Decoder 0 Control Register" for details.
+ * Additionally indicate whether decoder settings were autodetected,
+ * user customized.
  */
 #define CXL_DECODER_F_RAM   BIT(0)
 #define CXL_DECODER_F_PMEM  BIT(1)
@@ -318,12 +339,36 @@ enum cxl_decoder_mode {
 	CXL_DECODER_DEAD,
 };
 
+static inline const char *cxl_decoder_mode_name(enum cxl_decoder_mode mode)
+{
+	static const char * const names[] = {
+		[CXL_DECODER_NONE] = "none",
+		[CXL_DECODER_RAM] = "ram",
+		[CXL_DECODER_PMEM] = "pmem",
+		[CXL_DECODER_MIXED] = "mixed",
+	};
+
+	if (mode >= CXL_DECODER_NONE && mode <= CXL_DECODER_MIXED)
+		return names[mode];
+	return "mixed";
+}
+
+/*
+ * Track whether this decoder is reserved for region autodiscovery, or
+ * free for userspace provisioning.
+ */
+enum cxl_decoder_state {
+	CXL_DECODER_STATE_MANUAL,
+	CXL_DECODER_STATE_AUTO,
+};
+
 /**
  * struct cxl_endpoint_decoder - Endpoint  / SPA to DPA decoder
  * @cxld: base cxl_decoder_object
  * @dpa_res: actively claimed DPA span of this decoder
  * @skip: offset into @dpa_res where @cxld.hpa_range maps
  * @mode: which memory type / access-mode-partition this decoder targets
+ * @state: autodiscovery state
  * @pos: interleave position in @cxld.region
  */
 struct cxl_endpoint_decoder {
@@ -331,6 +376,7 @@ struct cxl_endpoint_decoder {
 	struct resource *dpa_res;
 	resource_size_t skip;
 	enum cxl_decoder_mode mode;
+	enum cxl_decoder_state state;
 	int pos;
 };
 
@@ -364,6 +410,7 @@ typedef struct cxl_dport *(*cxl_calc_hb_fn)(struct cxl_root_decoder *cxlrd,
  * @region_id: region id for next region provisioning event
  * @calc_hb: which host bridge covers the n'th position by granularity
  * @platform_data: platform specific configuration data
+ * @range_lock: sync region autodiscovery by address range
  * @cxlsd: base cxl switch decoder
  */
 struct cxl_root_decoder {
@@ -371,6 +418,7 @@ struct cxl_root_decoder {
 	atomic_t region_id;
 	cxl_calc_hb_fn calc_hb;
 	void *platform_data;
+	struct mutex range_lock;
 	struct cxl_switch_decoder cxlsd;
 };
 
@@ -420,6 +468,13 @@ struct cxl_region_params {
  */
 #define CXL_REGION_F_INCOHERENT 0
 
+/*
+ * Indicate whether this region has been assembled by autodetection or
+ * userspace assembly. Prevent endpoint decoders outside of automatic
+ * detection from being added to the region.
+ */
+#define CXL_REGION_F_AUTO 1
+
 /**
  * struct cxl_region - CXL region
  * @dev: This region's device
@@ -475,6 +530,12 @@ struct cxl_pmem_region {
 	struct cxl_pmem_region_mapping mapping[];
 };
 
+struct cxl_dax_region {
+	struct device dev;
+	struct cxl_region *cxlr;
+	struct range hpa_range;
+};
+
 /**
  * struct cxl_port - logical collection of upstream port devices and
  *		     downstream port devices to construct a CXL memory
@@ -615,8 +676,10 @@ struct cxl_dport *devm_cxl_add_rch_dport(struct cxl_port *port,
 
 struct cxl_decoder *to_cxl_decoder(struct device *dev);
 struct cxl_root_decoder *to_cxl_root_decoder(struct device *dev);
+struct cxl_switch_decoder *to_cxl_switch_decoder(struct device *dev);
 struct cxl_endpoint_decoder *to_cxl_endpoint_decoder(struct device *dev);
 bool is_root_decoder(struct device *dev);
+bool is_switch_decoder(struct device *dev);
 bool is_endpoint_decoder(struct device *dev);
 struct cxl_root_decoder *cxl_root_decoder_alloc(struct cxl_port *port,
 						unsigned int nr_targets,
@@ -630,10 +693,26 @@ int cxl_decoder_add_locked(struct cxl_decoder *cxld, int *target_map);
 int cxl_decoder_autoremove(struct device *host, struct cxl_decoder *cxld);
 int cxl_endpoint_autoremove(struct cxl_memdev *cxlmd, struct cxl_port *endpoint);
 
+/**
+ * struct cxl_endpoint_dvsec_info - Cached DVSEC info
+ * @mem_enabled: cached value of mem_enabled in the DVSEC, PCIE_DEVICE
+ * @ranges: Number of active HDM ranges this device uses.
+ * @dvsec_range: cached attributes of the ranges in the DVSEC, PCIE_DEVICE
+ */
+struct cxl_endpoint_dvsec_info {
+	bool mem_enabled;
+	int ranges;
+	struct range dvsec_range[2];
+};
+
 struct cxl_hdm;
-struct cxl_hdm *devm_cxl_setup_hdm(struct cxl_port *port);
-int devm_cxl_enumerate_decoders(struct cxl_hdm *cxlhdm);
+struct cxl_hdm *devm_cxl_setup_hdm(struct cxl_port *port,
+				   struct cxl_endpoint_dvsec_info *info);
+int devm_cxl_enumerate_decoders(struct cxl_hdm *cxlhdm,
+				struct cxl_endpoint_dvsec_info *info);
 int devm_cxl_add_passthrough_decoder(struct cxl_port *port);
+int cxl_dvsec_rr_decode(struct device *dev, int dvsec,
+			struct cxl_endpoint_dvsec_info *info);
 
 bool is_cxl_region(struct device *dev);
 
@@ -667,6 +746,7 @@ void cxl_driver_unregister(struct cxl_driver *cxl_drv);
 #define CXL_DEVICE_MEMORY_EXPANDER	5
 #define CXL_DEVICE_REGION		6
 #define CXL_DEVICE_PMEM_REGION		7
+#define CXL_DEVICE_DAX_REGION		8
 
 #define MODULE_ALIAS_CXL(type) MODULE_ALIAS("cxl:t" __stringify(type) "*")
 #define CXL_MODALIAS_FMT "cxl:t%d"
@@ -683,6 +763,9 @@ struct cxl_nvdimm_bridge *cxl_find_nvdimm_bridge(struct device *dev);
 #ifdef CONFIG_CXL_REGION
 bool is_cxl_pmem_region(struct device *dev);
 struct cxl_pmem_region *to_cxl_pmem_region(struct device *dev);
+int cxl_add_to_region(struct cxl_port *root,
+		      struct cxl_endpoint_decoder *cxled);
+struct cxl_dax_region *to_cxl_dax_region(struct device *dev);
 #else
 static inline bool is_cxl_pmem_region(struct device *dev)
 {
@@ -692,6 +775,15 @@ static inline struct cxl_pmem_region *to_cxl_pmem_region(struct device *dev)
 {
 	return NULL;
 }
+static inline int cxl_add_to_region(struct cxl_port *root,
+				    struct cxl_endpoint_decoder *cxled)
+{
+	return 0;
+}
+static inline struct cxl_dax_region *to_cxl_dax_region(struct device *dev)
+{
+	return NULL;
+}
 #endif
 
 /*