Merge branch 'for-6.9/cxl-einj' into for-6.9/cxl

Pick up support for injecting errors via ACPI EINJ into the CXL protocol
for v6.9.

Author: djbw

Documentation/ABI/testing/debugfs-cxl

@@ -33,3 +33,33 @@ Description:
 		device cannot clear poison from the address, -ENXIO is returned.
 		The clear_poison attribute is only visible for devices
 		supporting the capability.
+
+What:		/sys/kernel/debug/cxl/einj_types
+Date:		January, 2024
+KernelVersion:	v6.9
+Contact:	linux-cxl@vger.kernel.org
+Description:
+		(RO) Prints the CXL protocol error types made available by
+		the platform in the format "0x<error number>	<error type>".
+		The possible error types are (as of ACPI v6.5):
+			0x1000	CXL.cache Protocol Correctable
+			0x2000	CXL.cache Protocol Uncorrectable non-fatal
+			0x4000	CXL.cache Protocol Uncorrectable fatal
+			0x8000	CXL.mem Protocol Correctable
+			0x10000	CXL.mem Protocol Uncorrectable non-fatal
+			0x20000	CXL.mem Protocol Uncorrectable fatal
+
+		The <error number> can be written to einj_inject to inject
+		<error type> into a chosen dport.
+
+What:		/sys/kernel/debug/cxl/$dport_dev/einj_inject
+Date:		January, 2024
+KernelVersion:	v6.9
+Contact:	linux-cxl@vger.kernel.org
+Description:
+		(WO) Writing an integer to this file injects the corresponding
+		CXL protocol error into $dport_dev ($dport_dev will be a device
+		name from /sys/bus/pci/devices). The integer to type mapping for
+		injection can be found by reading from einj_types. If the dport
+		was enumerated in RCH mode, a CXL 1.1 error is injected, otherwise
+		a CXL 2.0 error is injected.

Documentation/firmware-guide/acpi/apei/einj.rst

@@ -32,6 +32,10 @@ configuration::
   CONFIG_ACPI_APEI
   CONFIG_ACPI_APEI_EINJ
 
+...and to (optionally) enable CXL protocol error injection set::
+
+  CONFIG_ACPI_APEI_EINJ_CXL
+
 The EINJ user interface is in <debugfs mount point>/apei/einj.
 
 The following files belong to it:
@@ -118,6 +122,24 @@ The following files belong to it:
   this actually works depends on what operations the BIOS actually
   includes in the trigger phase.
 
+CXL error types are supported from ACPI 6.5 onwards (given a CXL port
+is present). The EINJ user interface for CXL error types is at
+<debugfs mount point>/cxl. The following files belong to it:
+
+- einj_types:
+
+  Provides the same functionality as available_error_types above, but
+  for CXL error types
+
+- $dport_dev/einj_inject:
+
+  Injects a CXL error type into the CXL port represented by $dport_dev,
+  where $dport_dev is the name of the CXL port (usually a PCIe device name).
+  Error injections targeting a CXL 2.0+ port can use the legacy interface
+  under <debugfs mount point>/apei/einj, while CXL 1.1/1.0 port injections
+  must use this file.
+
+
 BIOS versions based on the ACPI 4.0 specification have limited options
 in controlling where the errors are injected. Your BIOS may support an
 extension (enabled with the param_extension=1 module parameter, or boot
@@ -181,6 +203,18 @@ You should see something like this in dmesg::
   [22715.834759] EDAC sbridge MC3: PROCESSOR 0:306e7 TIME 1422553404 SOCKET 0 APIC 0
   [22716.616173] EDAC MC3: 1 CE memory read error on CPU_SrcID#0_Channel#0_DIMM#0 (channel:0 slot:0 page:0x12345 offset:0x0 grain:32 syndrome:0x0 -  area:DRAM err_code:0001:0090 socket:0 channel_mask:1 rank:0)
 
+A CXL error injection example with $dport_dev=0000:e0:01.1::
+
+    # cd /sys/kernel/debug/cxl/
+    # ls
+    0000:e0:01.1 0000:0c:00.0
+    # cat einj_types                # See which errors can be injected
+	0x00008000  CXL.mem Protocol Correctable
+	0x00010000  CXL.mem Protocol Uncorrectable non-fatal
+	0x00020000  CXL.mem Protocol Uncorrectable fatal
+    # cd 0000:e0:01.1               # Navigate to dport to inject into
+    # echo 0x8000 > einj_inject     # Inject error
+
 Special notes for injection into SGX enclaves:
 
 There may be a separate BIOS setup option to enable SGX injection.

MAINTAINERS

@@ -5289,6 +5289,7 @@ M:	Dan Williams <dan.j.williams@intel.com>
 L:	linux-cxl@vger.kernel.org
 S:	Maintained
 F:	drivers/cxl/
+F:	include/linux/cxl-einj.h
 F:	include/linux/cxl-event.h
 F:	include/uapi/linux/cxl_mem.h
 F:	tools/testing/cxl/

drivers/acpi/apei/Kconfig

@@ -60,6 +60,19 @@ config ACPI_APEI_EINJ
 	  mainly used for debugging and testing the other parts of
 	  APEI and some other RAS features.
 
+config ACPI_APEI_EINJ_CXL
+	bool "CXL Error INJection Support"
+	default ACPI_APEI_EINJ
+	depends on ACPI_APEI_EINJ
+	depends on CXL_BUS && CXL_BUS <= ACPI_APEI_EINJ
+	help
+	  Support for CXL protocol Error INJection through debugfs/cxl.
+	  Availability and which errors are supported is dependent on
+	  the host platform. Look to ACPI v6.5 section 18.6.4 and kernel
+	  EINJ documentation for more information.
+
+	  If unsure say 'n'
+
 config ACPI_APEI_ERST_DEBUG
 	tristate "APEI Error Record Serialization Table (ERST) Debug Support"
 	depends on ACPI_APEI

drivers/acpi/apei/Makefile

@@ -2,6 +2,8 @@
 obj-$(CONFIG_ACPI_APEI)		+= apei.o
 obj-$(CONFIG_ACPI_APEI_GHES)	+= ghes.o
 obj-$(CONFIG_ACPI_APEI_EINJ)	+= einj.o
+einj-y				:= einj-core.o
+einj-$(CONFIG_ACPI_APEI_EINJ_CXL) += einj-cxl.o
 obj-$(CONFIG_ACPI_APEI_ERST_DEBUG) += erst-dbg.o
 
 apei-y := apei-base.o hest.o erst.o bert.o

drivers/acpi/apei/apei-internal.h

@@ -130,4 +130,22 @@ static inline u32 cper_estatus_len(struct acpi_hest_generic_status *estatus)
 }
 
 int apei_osc_setup(void);
+
+int einj_get_available_error_type(u32 *type);
+int einj_error_inject(u32 type, u32 flags, u64 param1, u64 param2, u64 param3,
+		      u64 param4);
+int einj_cxl_rch_error_inject(u32 type, u32 flags, u64 param1, u64 param2,
+			      u64 param3, u64 param4);
+bool einj_is_cxl_error_type(u64 type);
+int einj_validate_error_type(u64 type);
+
+#ifndef ACPI_EINJ_CXL_CACHE_CORRECTABLE
+#define ACPI_EINJ_CXL_CACHE_CORRECTABLE     BIT(12)
+#define ACPI_EINJ_CXL_CACHE_UNCORRECTABLE   BIT(13)
+#define ACPI_EINJ_CXL_CACHE_FATAL           BIT(14)
+#define ACPI_EINJ_CXL_MEM_CORRECTABLE       BIT(15)
+#define ACPI_EINJ_CXL_MEM_UNCORRECTABLE     BIT(16)
+#define ACPI_EINJ_CXL_MEM_FATAL             BIT(17)
+#endif
+
 #endif

drivers/acpi/apei/einj.c drivers/acpi/apei/einj-core.cdrivers/acpi/apei/einj.c renamed to drivers/acpi/apei/einj-core.c

@@ -21,6 +21,7 @@
 #include <linux/nmi.h>
 #include <linux/delay.h>
 #include <linux/mm.h>
+#include <linux/platform_device.h>
 #include <asm/unaligned.h>
 
 #include "apei-internal.h"
@@ -36,6 +37,12 @@
 #define MEM_ERROR_MASK		(ACPI_EINJ_MEMORY_CORRECTABLE | \
 				ACPI_EINJ_MEMORY_UNCORRECTABLE | \
 				ACPI_EINJ_MEMORY_FATAL)
+#define CXL_ERROR_MASK		(ACPI_EINJ_CXL_CACHE_CORRECTABLE | \
+				ACPI_EINJ_CXL_CACHE_UNCORRECTABLE | \
+				ACPI_EINJ_CXL_CACHE_FATAL | \
+				ACPI_EINJ_CXL_MEM_CORRECTABLE | \
+				ACPI_EINJ_CXL_MEM_UNCORRECTABLE | \
+				ACPI_EINJ_CXL_MEM_FATAL)
 
 /*
  * ACPI version 5 provides a SET_ERROR_TYPE_WITH_ADDRESS action.
@@ -137,6 +144,11 @@ static struct apei_exec_ins_type einj_ins_type[] = {
  */
 static DEFINE_MUTEX(einj_mutex);
 
+/*
+ * Exported APIs use this flag to exit early if einj_probe() failed.
+ */
+bool einj_initialized __ro_after_init;
+
 static void *einj_param;
 
 static void einj_exec_ctx_init(struct apei_exec_context *ctx)
@@ -160,7 +172,7 @@ static int __einj_get_available_error_type(u32 *type)
 }
 
 /* Get error injection capabilities of the platform */
-static int einj_get_available_error_type(u32 *type)
+int einj_get_available_error_type(u32 *type)
 {
 	int rc;
 
@@ -530,8 +542,8 @@ static int __einj_error_inject(u32 type, u32 flags, u64 param1, u64 param2,
 }
 
 /* Inject the specified hardware error */
-static int einj_error_inject(u32 type, u32 flags, u64 param1, u64 param2,
-			     u64 param3, u64 param4)
+int einj_error_inject(u32 type, u32 flags, u64 param1, u64 param2, u64 param3,
+		      u64 param4)
 {
 	int rc;
 	u64 base_addr, size;
@@ -554,8 +566,17 @@ static int einj_error_inject(u32 type, u32 flags, u64 param1, u64 param2,
 	if (type & ACPI5_VENDOR_BIT) {
 		if (vendor_flags != SETWA_FLAGS_MEM)
 			goto inject;
-	} else if (!(type & MEM_ERROR_MASK) && !(flags & SETWA_FLAGS_MEM))
+	} else if (!(type & MEM_ERROR_MASK) && !(flags & SETWA_FLAGS_MEM)) {
 		goto inject;
+	}
+
+	/*
+	 * Injections targeting a CXL 1.0/1.1 port have to be injected
+	 * via the einj_cxl_rch_error_inject() path as that does the proper
+	 * validation of the given RCRB base (MMIO) address.
+	 */
+	if (einj_is_cxl_error_type(type) && (flags & SETWA_FLAGS_MEM))
+		return -EINVAL;
 
 	/*
 	 * Disallow crazy address masks that give BIOS leeway to pick
@@ -587,6 +608,21 @@ static int einj_error_inject(u32 type, u32 flags, u64 param1, u64 param2,
 	return rc;
 }
 
+int einj_cxl_rch_error_inject(u32 type, u32 flags, u64 param1, u64 param2,
+			      u64 param3, u64 param4)
+{
+	int rc;
+
+	if (!(einj_is_cxl_error_type(type) && (flags & SETWA_FLAGS_MEM)))
+		return -EINVAL;
+
+	mutex_lock(&einj_mutex);
+	rc = __einj_error_inject(type, flags, param1, param2, param3, param4);
+	mutex_unlock(&einj_mutex);
+
+	return rc;
+}
+
 static u32 error_type;
 static u32 error_flags;
 static u64 error_param1;
@@ -607,12 +643,6 @@ static struct { u32 mask; const char *str; } const einj_error_type_string[] = {
 	{ BIT(9), "Platform Correctable" },
 	{ BIT(10), "Platform Uncorrectable non-fatal" },
 	{ BIT(11), "Platform Uncorrectable fatal"},
-	{ BIT(12), "CXL.cache Protocol Correctable" },
-	{ BIT(13), "CXL.cache Protocol Uncorrectable non-fatal" },
-	{ BIT(14), "CXL.cache Protocol Uncorrectable fatal" },
-	{ BIT(15), "CXL.mem Protocol Correctable" },
-	{ BIT(16), "CXL.mem Protocol Uncorrectable non-fatal" },
-	{ BIT(17), "CXL.mem Protocol Uncorrectable fatal" },
 	{ BIT(31), "Vendor Defined Error Types" },
 };
 
@@ -641,22 +671,26 @@ static int error_type_get(void *data, u64 *val)
 	return 0;
 }
 
-static int error_type_set(void *data, u64 val)
+bool einj_is_cxl_error_type(u64 type)
 {
+	return (type & CXL_ERROR_MASK) && (!(type & ACPI5_VENDOR_BIT));
+}
+
+int einj_validate_error_type(u64 type)
+{
+	u32 tval, vendor, available_error_type = 0;
 	int rc;
-	u32 available_error_type = 0;
-	u32 tval, vendor;
 
 	/* Only low 32 bits for error type are valid */
-	if (val & GENMASK_ULL(63, 32))
+	if (type & GENMASK_ULL(63, 32))
 		return -EINVAL;
 
 	/*
 	 * Vendor defined types have 0x80000000 bit set, and
 	 * are not enumerated by ACPI_EINJ_GET_ERROR_TYPE
 	 */
-	vendor = val & ACPI5_VENDOR_BIT;
-	tval = val & 0x7fffffff;
+	vendor = type & ACPI5_VENDOR_BIT;
+	tval = type & GENMASK(30, 0);
 
 	/* Only one error type can be specified */
 	if (tval & (tval - 1))
@@ -665,9 +699,21 @@ static int error_type_set(void *data, u64 val)
 		rc = einj_get_available_error_type(&available_error_type);
 		if (rc)
 			return rc;
-		if (!(val & available_error_type))
+		if (!(type & available_error_type))
 			return -EINVAL;
 	}
+
+	return 0;
+}
+
+static int error_type_set(void *data, u64 val)
+{
+	int rc;
+
+	rc = einj_validate_error_type(val);
+	if (rc)
+		return rc;
+
 	error_type = val;
 
 	return 0;
@@ -703,21 +749,21 @@ static int einj_check_table(struct acpi_table_einj *einj_tab)
 	return 0;
 }
 
-static int __init einj_init(void)
+static int __init einj_probe(struct platform_device *pdev)
 {
 	int rc;
 	acpi_status status;
 	struct apei_exec_context ctx;
 
 	if (acpi_disabled) {
-		pr_info("ACPI disabled.\n");
+		pr_debug("ACPI disabled.\n");
 		return -ENODEV;
 	}
 
 	status = acpi_get_table(ACPI_SIG_EINJ, 0,
 				(struct acpi_table_header **)&einj_tab);
 	if (status == AE_NOT_FOUND) {
-		pr_warn("EINJ table not found.\n");
+		pr_debug("EINJ table not found.\n");
 		return -ENODEV;
 	} else if (ACPI_FAILURE(status)) {
 		pr_err("Failed to get EINJ table: %s\n",
@@ -805,7 +851,7 @@ static int __init einj_init(void)
 	return rc;
 }
 
-static void __exit einj_exit(void)
+static void __exit einj_remove(struct platform_device *pdev)
 {
 	struct apei_exec_context ctx;
 
@@ -826,6 +872,40 @@ static void __exit einj_exit(void)
 	acpi_put_table((struct acpi_table_header *)einj_tab);
 }
 
+static struct platform_device *einj_dev;
+static struct platform_driver einj_driver = {
+	.remove_new = einj_remove,
+	.driver = {
+		.name = "acpi-einj",
+	},
+};
+
+static int __init einj_init(void)
+{
+	struct platform_device_info einj_dev_info = {
+		.name = "acpi-einj",
+		.id = -1,
+	};
+	int rc;
+
+	einj_dev = platform_device_register_full(&einj_dev_info);
+	if (IS_ERR(einj_dev))
+		return PTR_ERR(einj_dev);
+
+	rc = platform_driver_probe(&einj_driver, einj_probe);
+	einj_initialized = rc == 0;
+
+	return 0;
+}
+
+static void __exit einj_exit(void)
+{
+	if (einj_initialized)
+		platform_driver_unregister(&einj_driver);
+
+	platform_device_del(einj_dev);
+}
+
 module_init(einj_init);
 module_exit(einj_exit);