Merging upstream version 6.9.7.

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

7 files changed, 309 insertions, 27 deletions

diff --git a/drivers/acpi/apei/Kconfig b/drivers/acpi/apei/Kconfig
index 6b18f8bc7b..3cfe7e7475 100644
--- a/drivers/acpi/apei/Kconfig
+++ b/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
diff --git a/drivers/acpi/apei/Makefile b/drivers/acpi/apei/Makefile
index 4dfac21287..2c474e6477 100644
--- a/drivers/acpi/apei/Makefile
+++ b/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
diff --git a/drivers/acpi/apei/apei-internal.h b/drivers/acpi/apei/apei-internal.h
index 67c2c3b959..cd2766c69d 100644
--- a/drivers/acpi/apei/apei-internal.h
+++ b/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
diff --git a/drivers/acpi/apei/einj.c b/drivers/acpi/apei/einj-core.c
index 89fb9331c6..bb9f8475ce 100644
--- a/drivers/acpi/apei/einj.c
+++ b/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 @@ inject:
 	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 @@ err_put_table:
 	return rc;
 }
 
-static void __exit einj_exit(void)
+static void 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_unregister(einj_dev);
+}
+
 module_init(einj_init);
 module_exit(einj_exit);
 
diff --git a/drivers/acpi/apei/einj-cxl.c b/drivers/acpi/apei/einj-cxl.c
new file mode 100644
index 0000000000..8b8be0c907
--- /dev/null
+++ b/drivers/acpi/apei/einj-cxl.c
@@ -0,0 +1,113 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * CXL Error INJection support. Used by CXL core to inject
+ * protocol errors into CXL ports.
+ *
+ * Copyright (C) 2023 Advanced Micro Devices, Inc.
+ *
+ * Author: Ben Cheatham <benjamin.cheatham@amd.com>
+ */
+#include <linux/einj-cxl.h>
+#include <linux/seq_file.h>
+#include <linux/pci.h>
+
+#include "apei-internal.h"
+
+/* Defined in einj-core.c */
+extern bool einj_initialized;
+
+static struct { u32 mask; const char *str; } const einj_cxl_error_type_string[] = {
+	{ ACPI_EINJ_CXL_CACHE_CORRECTABLE, "CXL.cache Protocol Correctable" },
+	{ ACPI_EINJ_CXL_CACHE_UNCORRECTABLE, "CXL.cache Protocol Uncorrectable non-fatal" },
+	{ ACPI_EINJ_CXL_CACHE_FATAL, "CXL.cache Protocol Uncorrectable fatal" },
+	{ ACPI_EINJ_CXL_MEM_CORRECTABLE, "CXL.mem Protocol Correctable" },
+	{ ACPI_EINJ_CXL_MEM_UNCORRECTABLE, "CXL.mem Protocol Uncorrectable non-fatal" },
+	{ ACPI_EINJ_CXL_MEM_FATAL, "CXL.mem Protocol Uncorrectable fatal" },
+};
+
+int einj_cxl_available_error_type_show(struct seq_file *m, void *v)
+{
+	int cxl_err, rc;
+	u32 available_error_type = 0;
+
+	rc = einj_get_available_error_type(&available_error_type);
+	if (rc)
+		return rc;
+
+	for (int pos = 0; pos < ARRAY_SIZE(einj_cxl_error_type_string); pos++) {
+		cxl_err = ACPI_EINJ_CXL_CACHE_CORRECTABLE << pos;
+
+		if (available_error_type & cxl_err)
+			seq_printf(m, "0x%08x\t%s\n",
+				   einj_cxl_error_type_string[pos].mask,
+				   einj_cxl_error_type_string[pos].str);
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_NS_GPL(einj_cxl_available_error_type_show, CXL);
+
+static int cxl_dport_get_sbdf(struct pci_dev *dport_dev, u64 *sbdf)
+{
+	struct pci_bus *pbus;
+	struct pci_host_bridge *bridge;
+	u64 seg = 0, bus;
+
+	pbus = dport_dev->bus;
+	bridge = pci_find_host_bridge(pbus);
+
+	if (!bridge)
+		return -ENODEV;
+
+	if (bridge->domain_nr != PCI_DOMAIN_NR_NOT_SET)
+		seg = bridge->domain_nr;
+
+	bus = pbus->number;
+	*sbdf = (seg << 24) | (bus << 16) | dport_dev->devfn;
+
+	return 0;
+}
+
+int einj_cxl_inject_rch_error(u64 rcrb, u64 type)
+{
+	int rc;
+
+	/* Only CXL error types can be specified */
+	if (!einj_is_cxl_error_type(type))
+		return -EINVAL;
+
+	rc = einj_validate_error_type(type);
+	if (rc)
+		return rc;
+
+	return einj_cxl_rch_error_inject(type, 0x2, rcrb, GENMASK_ULL(63, 0),
+					 0, 0);
+}
+EXPORT_SYMBOL_NS_GPL(einj_cxl_inject_rch_error, CXL);
+
+int einj_cxl_inject_error(struct pci_dev *dport, u64 type)
+{
+	u64 param4 = 0;
+	int rc;
+
+	/* Only CXL error types can be specified */
+	if (!einj_is_cxl_error_type(type))
+		return -EINVAL;
+
+	rc = einj_validate_error_type(type);
+	if (rc)
+		return rc;
+
+	rc = cxl_dport_get_sbdf(dport, &param4);
+	if (rc)
+		return rc;
+
+	return einj_error_inject(type, 0x4, 0, 0, 0, param4);
+}
+EXPORT_SYMBOL_NS_GPL(einj_cxl_inject_error, CXL);
+
+bool einj_cxl_is_initialized(void)
+{
+	return einj_initialized;
+}
+EXPORT_SYMBOL_NS_GPL(einj_cxl_is_initialized, CXL);
diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c
index ab2a82cb1b..512067cac1 100644
--- a/drivers/acpi/apei/ghes.c
+++ b/drivers/acpi/apei/ghes.c
@@ -1455,7 +1455,7 @@ err:
 	return rc;
 }
 
-static int ghes_remove(struct platform_device *ghes_dev)
+static void ghes_remove(struct platform_device *ghes_dev)
 {
 	int rc;
 	struct ghes *ghes;
@@ -1492,8 +1492,15 @@ static int ghes_remove(struct platform_device *ghes_dev)
 		break;
 	case ACPI_HEST_NOTIFY_SOFTWARE_DELEGATED:
 		rc = apei_sdei_unregister_ghes(ghes);
-		if (rc)
-			return rc;
+		if (rc) {
+			/*
+			 * Returning early results in a resource leak, but we're
+			 * only here if stopping the hardware failed.
+			 */
+			dev_err(&ghes_dev->dev, "Failed to unregister ghes (%pe)\n",
+				ERR_PTR(rc));
+			return;
+		}
 		break;
 	default:
 		BUG();
@@ -1507,8 +1514,6 @@ static int ghes_remove(struct platform_device *ghes_dev)
 	mutex_unlock(&ghes_devs_mutex);
 
 	kfree(ghes);
-
-	return 0;
 }
 
 static struct platform_driver ghes_platform_driver = {
@@ -1516,7 +1521,7 @@ static struct platform_driver ghes_platform_driver = {
 		.name	= "GHES",
 	},
 	.probe		= ghes_probe,
-	.remove		= ghes_remove,
+	.remove_new	= ghes_remove,
 };
 
 void __init acpi_ghes_init(void)
diff --git a/drivers/acpi/apei/hest.c b/drivers/acpi/apei/hest.c
index 6aef1ee5e1..20d757687e 100644
--- a/drivers/acpi/apei/hest.c
+++ b/drivers/acpi/apei/hest.c
@@ -37,6 +37,20 @@ EXPORT_SYMBOL_GPL(hest_disable);
 
 static struct acpi_table_hest *__read_mostly hest_tab;
 
+/*
+ * Since GHES_ASSIST is not supported, skip initialization of GHES_ASSIST
+ * structures for MCA.
+ * During HEST parsing, detected MCA error sources are cached from early
+ * table entries so that the Flags and Source Id fields from these cached
+ * values are then referred to in later table entries to determine if the
+ * encountered GHES_ASSIST structure should be initialized.
+ */
+static struct {
+	struct acpi_hest_ia_corrected *cmc;
+	struct acpi_hest_ia_machine_check *mc;
+	struct acpi_hest_ia_deferred_check *dmc;
+} mces;
+
 static const int hest_esrc_len_tab[ACPI_HEST_TYPE_RESERVED] = {
 	[ACPI_HEST_TYPE_IA32_CHECK] = -1,	/* need further calculation */
 	[ACPI_HEST_TYPE_IA32_CORRECTED_CHECK] = -1,
@@ -70,22 +84,54 @@ static int hest_esrc_len(struct acpi_hest_header *hest_hdr)
 		cmc = (struct acpi_hest_ia_corrected *)hest_hdr;
 		len = sizeof(*cmc) + cmc->num_hardware_banks *
 			sizeof(struct acpi_hest_ia_error_bank);
+		mces.cmc = cmc;
 	} else if (hest_type == ACPI_HEST_TYPE_IA32_CHECK) {
 		struct acpi_hest_ia_machine_check *mc;
 		mc = (struct acpi_hest_ia_machine_check *)hest_hdr;
 		len = sizeof(*mc) + mc->num_hardware_banks *
 			sizeof(struct acpi_hest_ia_error_bank);
+		mces.mc = mc;
 	} else if (hest_type == ACPI_HEST_TYPE_IA32_DEFERRED_CHECK) {
 		struct acpi_hest_ia_deferred_check *mc;
 		mc = (struct acpi_hest_ia_deferred_check *)hest_hdr;
 		len = sizeof(*mc) + mc->num_hardware_banks *
 			sizeof(struct acpi_hest_ia_error_bank);
+		mces.dmc = mc;
 	}
 	BUG_ON(len == -1);
 
 	return len;
 };
 
+/*
+ * GHES and GHESv2 structures share the same format, starting from
+ * Source Id and ending in Error Status Block Length (inclusive).
+ */
+static bool is_ghes_assist_struct(struct acpi_hest_header *hest_hdr)
+{
+	struct acpi_hest_generic *ghes;
+	u16 related_source_id;
+
+	if (hest_hdr->type != ACPI_HEST_TYPE_GENERIC_ERROR &&
+	    hest_hdr->type != ACPI_HEST_TYPE_GENERIC_ERROR_V2)
+		return false;
+
+	ghes = (struct acpi_hest_generic *)hest_hdr;
+	related_source_id = ghes->related_source_id;
+
+	if (mces.cmc && mces.cmc->flags & ACPI_HEST_GHES_ASSIST &&
+	    related_source_id == mces.cmc->header.source_id)
+		return true;
+	if (mces.mc && mces.mc->flags & ACPI_HEST_GHES_ASSIST &&
+	    related_source_id == mces.mc->header.source_id)
+		return true;
+	if (mces.dmc && mces.dmc->flags & ACPI_HEST_GHES_ASSIST &&
+	    related_source_id == mces.dmc->header.source_id)
+		return true;
+
+	return false;
+}
+
 typedef int (*apei_hest_func_t)(struct acpi_hest_header *hest_hdr, void *data);
 
 static int apei_hest_parse(apei_hest_func_t func, void *data)
@@ -114,6 +160,11 @@ static int apei_hest_parse(apei_hest_func_t func, void *data)
 			return -EINVAL;
 		}
 
+		if (is_ghes_assist_struct(hest_hdr)) {
+			hest_hdr = (void *)hest_hdr + len;
+			continue;
+		}
+
 		rc = func(hest_hdr, data);
 		if (rc)
 			return rc;