Merge tag 'cxl-for-6.2' of git://git.kernel.org/pub/scm/linux/kernel/git/cxl/cxl

Pull cxl updates from Dan Williams:
 "Compute Express Link (CXL) updates for 6.2.

  While it may seem backwards, the CXL update this time around includes
  some focus on CXL 1.x enabling where the work to date had been with
  CXL 2.0 (VH topologies) in mind.

  First generation CXL can mostly be supported via BIOS, similar to DDR,
  however it became clear there are use cases for OS native CXL error
  handling and some CXL 3.0 endpoint features can be deployed on CXL 1.x
  hosts (Restricted CXL Host (RCH) topologies). So, this update brings
  RCH topologies into the Linux CXL device model.

  In support of the ongoing CXL 2.0+ enabling two new core kernel
  facilities are added.

  One is the ability for the kernel to flag collisions between userspace
  access to PCI configuration registers and kernel accesses. This is
  brought on by the PCIe Data-Object-Exchange (DOE) facility, a hardware
  mailbox over config-cycles.

  The other is a cpu_cache_invalidate_memregion() API that maps to
  wbinvd_on_all_cpus() on x86. To prevent abuse it is disabled in guest
  VMs and architectures that do not support it yet. The CXL paths that
  need it, dynamic memory region creation and security commands (erase /
  unlock), are disabled when it is not present.

  As for the CXL 2.0+ this cycle the subsystem gains support Persistent
  Memory Security commands, error handling in response to PCIe AER
  notifications, and support for the "XOR" host bridge interleave
  algorithm.

  Summary:

   - Add the cpu_cache_invalidate_memregion() API for cache flushing in
     response to physical memory reconfiguration, or memory-side data
     invalidation from operations like secure erase or memory-device
     unlock.

   - Add a facility for the kernel to warn about collisions between
     kernel and userspace access to PCI configuration registers

   - Add support for Restricted CXL Host (RCH) topologies (formerly CXL
     1.1)

   - Add handling and reporting of CXL errors reported via the PCIe AER
     mechanism

   - Add support for CXL Persistent Memory Security commands

   - Add support for the "XOR" algorithm for CXL host bridge interleave

   - Rework / simplify CXL to NVDIMM interactions

   - Miscellaneous cleanups and fixes"

* tag 'cxl-for-6.2' of git://git.kernel.org/pub/scm/linux/kernel/git/cxl/cxl: (71 commits)
  cxl/region: Fix memdev reuse check
  cxl/pci: Remove endian confusion
  cxl/pci: Add some type-safety to the AER trace points
  cxl/security: Drop security command ioctl uapi
  cxl/mbox: Add variable output size validation for internal commands
  cxl/mbox: Enable cxl_mbox_send_cmd() users to validate output size
  cxl/security: Fix Get Security State output payload endian handling
  cxl: update names for interleave ways conversion macros
  cxl: update names for interleave granularity conversion macros
  cxl/acpi: Warn about an invalid CHBCR in an existing CHBS entry
  tools/testing/cxl: Require cache invalidation bypass
  cxl/acpi: Fail decoder add if CXIMS for HBIG is missing
  cxl/region: Fix spelling mistake "memergion" -> "memregion"
  cxl/regs: Fix sparse warning
  cxl/acpi: Set ACPI's CXL _OSC to indicate RCD mode support
  tools/testing/cxl: Add an RCH topology
  cxl/port: Add RCD endpoint port enumeration
  cxl/mem: Move devm_cxl_add_endpoint() from cxl_core to cxl_mem
  tools/testing/cxl: Add XOR Math support to cxl_test
  cxl/acpi: Support CXL XOR Interleave Math (CXIMS)
  ...

1 files changed, 112 insertions, 0 deletions

diff --git a/include/trace/events/cxl.h b/include/trace/events/cxl.h
new file mode 100644
index 000000000000..ad085a2534ef
--- /dev/null
+++ b/include/trace/events/cxl.h
@@ -0,0 +1,112 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM cxl
+
+#if !defined(_CXL_EVENTS_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _CXL_EVENTS_H
+
+#include <linux/tracepoint.h>
+
+#define CXL_HEADERLOG_SIZE		SZ_512
+#define CXL_HEADERLOG_SIZE_U32		SZ_512 / sizeof(u32)
+
+#define CXL_RAS_UC_CACHE_DATA_PARITY	BIT(0)
+#define CXL_RAS_UC_CACHE_ADDR_PARITY	BIT(1)
+#define CXL_RAS_UC_CACHE_BE_PARITY	BIT(2)
+#define CXL_RAS_UC_CACHE_DATA_ECC	BIT(3)
+#define CXL_RAS_UC_MEM_DATA_PARITY	BIT(4)
+#define CXL_RAS_UC_MEM_ADDR_PARITY	BIT(5)
+#define CXL_RAS_UC_MEM_BE_PARITY	BIT(6)
+#define CXL_RAS_UC_MEM_DATA_ECC		BIT(7)
+#define CXL_RAS_UC_REINIT_THRESH	BIT(8)
+#define CXL_RAS_UC_RSVD_ENCODE		BIT(9)
+#define CXL_RAS_UC_POISON		BIT(10)
+#define CXL_RAS_UC_RECV_OVERFLOW	BIT(11)
+#define CXL_RAS_UC_INTERNAL_ERR		BIT(14)
+#define CXL_RAS_UC_IDE_TX_ERR		BIT(15)
+#define CXL_RAS_UC_IDE_RX_ERR		BIT(16)
+
+#define show_uc_errs(status)	__print_flags(status, " | ",		  \
+	{ CXL_RAS_UC_CACHE_DATA_PARITY, "Cache Data Parity Error" },	  \
+	{ CXL_RAS_UC_CACHE_ADDR_PARITY, "Cache Address Parity Error" },	  \
+	{ CXL_RAS_UC_CACHE_BE_PARITY, "Cache Byte Enable Parity Error" }, \
+	{ CXL_RAS_UC_CACHE_DATA_ECC, "Cache Data ECC Error" },		  \
+	{ CXL_RAS_UC_MEM_DATA_PARITY, "Memory Data Parity Error" },	  \
+	{ CXL_RAS_UC_MEM_ADDR_PARITY, "Memory Address Parity Error" },	  \
+	{ CXL_RAS_UC_MEM_BE_PARITY, "Memory Byte Enable Parity Error" },  \
+	{ CXL_RAS_UC_MEM_DATA_ECC, "Memory Data ECC Error" },		  \
+	{ CXL_RAS_UC_REINIT_THRESH, "REINIT Threshold Hit" },		  \
+	{ CXL_RAS_UC_RSVD_ENCODE, "Received Unrecognized Encoding" },	  \
+	{ CXL_RAS_UC_POISON, "Received Poison From Peer" },		  \
+	{ CXL_RAS_UC_RECV_OVERFLOW, "Receiver Overflow" },		  \
+	{ CXL_RAS_UC_INTERNAL_ERR, "Component Specific Error" },	  \
+	{ CXL_RAS_UC_IDE_TX_ERR, "IDE Tx Error" },			  \
+	{ CXL_RAS_UC_IDE_RX_ERR, "IDE Rx Error" }			  \
+)
+
+TRACE_EVENT(cxl_aer_uncorrectable_error,
+	TP_PROTO(const struct device *dev, u32 status, u32 fe, u32 *hl),
+	TP_ARGS(dev, status, fe, hl),
+	TP_STRUCT__entry(
+		__string(dev_name, dev_name(dev))
+		__field(u32, status)
+		__field(u32, first_error)
+		__array(u32, header_log, CXL_HEADERLOG_SIZE_U32)
+	),
+	TP_fast_assign(
+		__assign_str(dev_name, dev_name(dev));
+		__entry->status = status;
+		__entry->first_error = fe;
+		/*
+		 * Embed the 512B headerlog data for user app retrieval and
+		 * parsing, but no need to print this in the trace buffer.
+		 */
+		memcpy(__entry->header_log, hl, CXL_HEADERLOG_SIZE);
+	),
+	TP_printk("%s: status: '%s' first_error: '%s'",
+		  __get_str(dev_name),
+		  show_uc_errs(__entry->status),
+		  show_uc_errs(__entry->first_error)
+	)
+);
+
+#define CXL_RAS_CE_CACHE_DATA_ECC	BIT(0)
+#define CXL_RAS_CE_MEM_DATA_ECC		BIT(1)
+#define CXL_RAS_CE_CRC_THRESH		BIT(2)
+#define CLX_RAS_CE_RETRY_THRESH		BIT(3)
+#define CXL_RAS_CE_CACHE_POISON		BIT(4)
+#define CXL_RAS_CE_MEM_POISON		BIT(5)
+#define CXL_RAS_CE_PHYS_LAYER_ERR	BIT(6)
+
+#define show_ce_errs(status)	__print_flags(status, " | ",			\
+	{ CXL_RAS_CE_CACHE_DATA_ECC, "Cache Data ECC Error" },			\
+	{ CXL_RAS_CE_MEM_DATA_ECC, "Memory Data ECC Error" },			\
+	{ CXL_RAS_CE_CRC_THRESH, "CRC Threshold Hit" },				\
+	{ CLX_RAS_CE_RETRY_THRESH, "Retry Threshold" },				\
+	{ CXL_RAS_CE_CACHE_POISON, "Received Cache Poison From Peer" },		\
+	{ CXL_RAS_CE_MEM_POISON, "Received Memory Poison From Peer" },		\
+	{ CXL_RAS_CE_PHYS_LAYER_ERR, "Received Error From Physical Layer" }	\
+)
+
+TRACE_EVENT(cxl_aer_correctable_error,
+	TP_PROTO(const struct device *dev, u32 status),
+	TP_ARGS(dev, status),
+	TP_STRUCT__entry(
+		__string(dev_name, dev_name(dev))
+		__field(u32, status)
+	),
+	TP_fast_assign(
+		__assign_str(dev_name, dev_name(dev));
+		__entry->status = status;
+	),
+	TP_printk("%s: status: '%s'",
+		  __get_str(dev_name), show_ce_errs(__entry->status)
+	)
+);
+
+#endif /* _CXL_EVENTS_H */
+
+/* This part must be outside protection */
+#undef TRACE_INCLUDE_FILE
+#define TRACE_INCLUDE_FILE cxl
+#include <trace/define_trace.h>