Merge branch 'acpi-apei'

Merge ACPI APEI updates for 6.17-rc1:

 - Fix iomem-related sparse warnings in the APEI EINJ driver (Zaid
   Alali, Tony Luck)

 - Add EINJv2 error injection support to the APEI EINJ driver (Zaid
   Alali)

 - Fix memory corruption in error_type_set() in the APEI EINJ driver (Dan
   Carpenter)

 - Fix less than zero comparison on a size_t variable in the APEI EINJ
   driver (Colin Ian King)

 - Fix check and iounmap of an uninitialized pointer in the APEI EINJ
   driver (Colin Ian King)

 - Add TAINT_MACHINE_CHECK to the GHES panic path in APEI to improve
   diagnostics and post-mortem analysis (Breno Leitao)

 - Update APEI reviewer records in MAINTAINERS (Rafael Wysocki)

 - Fix the handling of synchronous uncorrected memory errors in APEI
   (Shuai Xue)

* acpi-apei:
  ACPI: APEI: handle synchronous exceptions in task work
  ACPI: APEI: send SIGBUS to current task if synchronous memory error not recovered
  ACPI: APEI: MAINTAINERS: Update reviewers for APEI
  ACPI: APEI: EINJ: Fix trigger actions
  ACPI: APEI: GHES: add TAINT_MACHINE_CHECK on GHES panic path
  ACPI: APEI: EINJ: Fix check and iounmap of uninitialized pointer p
  ACPI: APEI: EINJ: Fix less than zero comparison on a size_t variable
  ACPI: APEI: EINJ: prevent memory corruption in error_type_set()
  ACPI: APEI: EINJ: Update the documentation for EINJv2 support
  ACPI: APEI: EINJ: Enable EINJv2 error injections
  ACPI: APEI: EINJ: Create debugfs files to enter device id and syndrome
  ACPI: APEI: EINJ: Discover EINJv2 parameters
  ACPI: APEI: EINJ: Add einjv2 extension struct
  ACPI: APEI: EINJ: Enable the discovery of EINJv2 capabilities
  ACPI: APEI: EINJ: Fix kernel test sparse warnings

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

@@ -59,6 +59,9 @@ The following files belong to it:
   0x00000200        Platform Correctable
   0x00000400        Platform Uncorrectable non-fatal
   0x00000800        Platform Uncorrectable fatal
+  V2_0x00000001     EINJV2 Processor Error
+  V2_0x00000002     EINJV2 Memory Error
+  V2_0x00000004     EINJV2 PCI Express Error
   ================  ===================================
 
   The format of the file contents are as above, except present are only
@@ -88,6 +91,8 @@ The following files belong to it:
       Memory address and mask valid (param1 and param2).
     Bit 2
       PCIe (seg,bus,dev,fn) valid (see param4 below).
+    Bit 3
+      EINJv2 extension structure is valid
 
   If set to zero, legacy behavior is mimicked where the type of
   injection specifies just one bit set, and param1 is multiplexed.
@@ -122,6 +127,13 @@ The following files belong to it:
   this actually works depends on what operations the BIOS actually
   includes in the trigger phase.
 
+- component_id0 .. component_idN, component_syndrome0 .. component_syndromeN
+
+  These files are used to set the "Component Array" field
+  of the EINJv2 Extension Structure. Each holds a 128-bit
+  hex value. Writing just a newline to any of these files
+  sets an invalid (all-ones) value.
+
 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:
@@ -194,6 +206,27 @@ An error injection example::
   # echo 0x8 > error_type			# Choose correctable memory error
   # echo 1 > error_inject			# Inject now
 
+An EINJv2 error injection example::
+
+  # cd /sys/kernel/debug/apei/einj
+  # cat available_error_type			# See which errors can be injected
+  0x00000002	Processor Uncorrectable non-fatal
+  0x00000008	Memory Correctable
+  0x00000010	Memory Uncorrectable non-fatal
+  V2_0x00000001	EINJV2 Processor Error
+  V2_0x00000002	EINJV2 Memory Error
+
+  # echo 0x12345000 > param1			# Set memory address for injection
+  # echo 0xfffffffffffff000 > param2		# Range - anywhere in this page
+  # echo 0x1 > component_id0			# First device ID
+  # echo 0x4 > component_syndrome0		# First error syndrome
+  # echo 0x2 > component_id1			# Second device ID
+  # echo 0x4 > component_syndrome1		# Second error syndrome
+  # echo '' > component_id2			# Mark id2 invalid to terminate list
+  # echo V2_0x2 > error_type			# Choose EINJv2 memory error
+  # echo 0xa > flags				# set flags to indicate EINJv2
+  # echo 1 > error_inject			# Inject now
+
 You should see something like this in dmesg::
 
   [22715.830801] EDAC sbridge MC3: HANDLING MCE MEMORY ERROR

MAINTAINERS

@@ -306,10 +306,11 @@ F:	tools/power/acpi/
 
 ACPI APEI
 M:	"Rafael J. Wysocki" <rafael@kernel.org>
-R:	Len Brown <lenb@kernel.org>
-R:	James Morse <james.morse@arm.com>
 R:	Tony Luck <tony.luck@intel.com>
 R:	Borislav Petkov <bp@alien8.de>
+R:	Hanjun Guo <guohanjun@huawei.com>
+R:	Mauro Carvalho Chehab <mchehab@kernel.org>
+R:	Shuai Xue <xueshuai@linux.alibaba.com>
 L:	linux-acpi@vger.kernel.org
 F:	drivers/acpi/apei/
 

drivers/acpi/apei/apei-internal.h

@@ -131,7 +131,7 @@ 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_get_available_error_type(u32 *type, int einj_action);
 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,

drivers/acpi/apei/einj-core.c

@@ -33,6 +33,8 @@
 #define SLEEP_UNIT_MAX		5000			/* 5ms */
 /* Firmware should respond within 1 seconds */
 #define FIRMWARE_TIMEOUT	(1 * USEC_PER_SEC)
+#define COMPONENT_LEN		16
+#define ACPI65_EINJV2_SUPP	BIT(30)
 #define ACPI5_VENDOR_BIT	BIT(31)
 #define MEM_ERROR_MASK		(ACPI_EINJ_MEMORY_CORRECTABLE | \
 				ACPI_EINJ_MEMORY_UNCORRECTABLE | \
@@ -49,6 +51,28 @@
  */
 static int acpi5;
 
+struct syndrome_array {
+	union {
+		u8	acpi_id[COMPONENT_LEN];
+		u8	device_id[COMPONENT_LEN];
+		u8	pcie_sbdf[COMPONENT_LEN];
+		u8	vendor_id[COMPONENT_LEN];
+	} comp_id;
+	union {
+		u8	proc_synd[COMPONENT_LEN];
+		u8	mem_synd[COMPONENT_LEN];
+		u8	pcie_synd[COMPONENT_LEN];
+		u8	vendor_synd[COMPONENT_LEN];
+	} comp_synd;
+};
+
+struct einjv2_extension_struct {
+	u32 length;
+	u16 revision;
+	u16 component_arr_count;
+	struct syndrome_array component_arr[] __counted_by(component_arr_count);
+};
+
 struct set_error_type_with_address {
 	u32	type;
 	u32	vendor_extension;
@@ -57,11 +81,13 @@ struct set_error_type_with_address {
 	u64	memory_address;
 	u64	memory_address_range;
 	u32	pcie_sbdf;
+	struct	einjv2_extension_struct einjv2_struct;
 };
 enum {
 	SETWA_FLAGS_APICID = 1,
 	SETWA_FLAGS_MEM = 2,
 	SETWA_FLAGS_PCIE_SBDF = 4,
+	SETWA_FLAGS_EINJV2 = 8,
 };
 
 /*
@@ -83,7 +109,10 @@ static struct debugfs_blob_wrapper vendor_blob;
 static struct debugfs_blob_wrapper vendor_errors;
 static char vendor_dev[64];
 
+static u32 max_nr_components;
 static u32 available_error_type;
+static u32 available_error_type_v2;
+static struct syndrome_array *syndrome_data;
 
 /*
  * Some BIOSes allow parameters to the SET_ERROR_TYPE entries in the
@@ -151,7 +180,9 @@ static DEFINE_MUTEX(einj_mutex);
  */
 bool einj_initialized __ro_after_init;
 
-static void *einj_param;
+static void __iomem *einj_param;
+static u32 v5param_size;
+static bool is_v2;
 
 static void einj_exec_ctx_init(struct apei_exec_context *ctx)
 {
@@ -159,13 +190,13 @@ static void einj_exec_ctx_init(struct apei_exec_context *ctx)
 			   EINJ_TAB_ENTRY(einj_tab), einj_tab->entries);
 }
 
-static int __einj_get_available_error_type(u32 *type)
+static int __einj_get_available_error_type(u32 *type, int einj_action)
 {
 	struct apei_exec_context ctx;
 	int rc;
 
 	einj_exec_ctx_init(&ctx);
-	rc = apei_exec_run(&ctx, ACPI_EINJ_GET_ERROR_TYPE);
+	rc = apei_exec_run(&ctx, einj_action);
 	if (rc)
 		return rc;
 	*type = apei_exec_ctx_get_output(&ctx);
@@ -174,17 +205,34 @@ static int __einj_get_available_error_type(u32 *type)
 }
 
 /* Get error injection capabilities of the platform */
-int einj_get_available_error_type(u32 *type)
+int einj_get_available_error_type(u32 *type, int einj_action)
 {
 	int rc;
 
 	mutex_lock(&einj_mutex);
-	rc = __einj_get_available_error_type(type);
+	rc = __einj_get_available_error_type(type, einj_action);
 	mutex_unlock(&einj_mutex);
 
 	return rc;
 }
 
+static int einj_get_available_error_types(u32 *type1, u32 *type2)
+{
+	int rc;
+
+	rc = einj_get_available_error_type(type1, ACPI_EINJ_GET_ERROR_TYPE);
+	if (rc)
+		return rc;
+	if (*type1 & ACPI65_EINJV2_SUPP) {
+		rc = einj_get_available_error_type(type2,
+						   ACPI_EINJV2_GET_ERROR_TYPE);
+		if (rc)
+			return rc;
+	}
+
+	return 0;
+}
+
 static int einj_timedout(u64 *t)
 {
 	if ((s64)*t < SLEEP_UNIT_MIN) {
@@ -216,24 +264,26 @@ static void check_vendor_extension(u64 paddr,
 				   struct set_error_type_with_address *v5param)
 {
 	int	offset = v5param->vendor_extension;
-	struct	vendor_error_type_extension *v;
+	struct	vendor_error_type_extension v;
+	struct vendor_error_type_extension __iomem *p;
 	u32	sbdf;
 
 	if (!offset)
 		return;
-	v = acpi_os_map_iomem(paddr + offset, sizeof(*v));
-	if (!v)
+	p = acpi_os_map_iomem(paddr + offset, sizeof(*p));
+	if (!p)
 		return;
-	get_oem_vendor_struct(paddr, offset, v);
-	sbdf = v->pcie_sbdf;
+	memcpy_fromio(&v, p, sizeof(v));
+	get_oem_vendor_struct(paddr, offset, &v);
+	sbdf = v.pcie_sbdf;
 	sprintf(vendor_dev, "%x:%x:%x.%x vendor_id=%x device_id=%x rev_id=%x\n",
 		sbdf >> 24, (sbdf >> 16) & 0xff,
 		(sbdf >> 11) & 0x1f, (sbdf >> 8) & 0x7,
-		 v->vendor_id, v->device_id, v->rev_id);
-	acpi_os_unmap_iomem(v, sizeof(*v));
+		 v.vendor_id, v.device_id, v.rev_id);
+	acpi_os_unmap_iomem(p, sizeof(v));
 }
 
-static void *einj_get_parameter_address(void)
+static void __iomem *einj_get_parameter_address(void)
 {
 	int i;
 	u64 pa_v4 = 0, pa_v5 = 0;
@@ -254,26 +304,50 @@ static void *einj_get_parameter_address(void)
 		entry++;
 	}
 	if (pa_v5) {
-		struct set_error_type_with_address *v5param;
+		struct set_error_type_with_address v5param;
+		struct set_error_type_with_address __iomem *p;
 
-		v5param = acpi_os_map_iomem(pa_v5, sizeof(*v5param));
-		if (v5param) {
+		v5param_size = sizeof(v5param);
+		p = acpi_os_map_iomem(pa_v5, sizeof(*p));
+		if (p) {
+			int offset, len;
+
+			memcpy_fromio(&v5param, p, v5param_size);
 			acpi5 = 1;
-			check_vendor_extension(pa_v5, v5param);
-			return v5param;
+			check_vendor_extension(pa_v5, &v5param);
+			if (available_error_type & ACPI65_EINJV2_SUPP) {
+				len = v5param.einjv2_struct.length;
+				offset = offsetof(struct einjv2_extension_struct, component_arr);
+				max_nr_components = (len - offset) /
+						sizeof(v5param.einjv2_struct.component_arr[0]);
+				/*
+				 * The first call to acpi_os_map_iomem above does not include the
+				 * component array, instead it is used to read and calculate maximum
+				 * number of components supported by the system. Below, the mapping
+				 * is expanded to include the component array.
+				 */
+				acpi_os_unmap_iomem(p, v5param_size);
+				offset = offsetof(struct set_error_type_with_address, einjv2_struct);
+				v5param_size = offset + struct_size(&v5param.einjv2_struct,
+					component_arr, max_nr_components);
+				p = acpi_os_map_iomem(pa_v5, v5param_size);
+			}
+			return p;
 		}
 	}
 	if (param_extension && pa_v4) {
-		struct einj_parameter *v4param;
+		struct einj_parameter v4param;
+		struct einj_parameter __iomem *p;
 
-		v4param = acpi_os_map_iomem(pa_v4, sizeof(*v4param));
-		if (!v4param)
+		p = acpi_os_map_iomem(pa_v4, sizeof(*p));
+		if (!p)
 			return NULL;
-		if (v4param->reserved1 || v4param->reserved2) {
-			acpi_os_unmap_iomem(v4param, sizeof(*v4param));
+		memcpy_fromio(&v4param, p, sizeof(v4param));
+		if (v4param.reserved1 || v4param.reserved2) {
+			acpi_os_unmap_iomem(p, sizeof(v4param));
 			return NULL;
 		}
-		return v4param;
+		return p;
 	}
 
 	return NULL;
@@ -319,7 +393,8 @@ static struct acpi_generic_address *einj_get_trigger_parameter_region(
 static int __einj_error_trigger(u64 trigger_paddr, u32 type,
 				u64 param1, u64 param2)
 {
-	struct acpi_einj_trigger *trigger_tab = NULL;
+	struct acpi_einj_trigger trigger_tab;
+	struct acpi_einj_trigger *full_trigger_tab;
 	struct apei_exec_context trigger_ctx;
 	struct apei_resources trigger_resources;
 	struct acpi_whea_header *trigger_entry;
@@ -327,54 +402,60 @@ static int __einj_error_trigger(u64 trigger_paddr, u32 type,
 	u32 table_size;
 	int rc = -EIO;
 	struct acpi_generic_address *trigger_param_region = NULL;
+	struct acpi_einj_trigger __iomem *p = NULL;
 
-	r = request_mem_region(trigger_paddr, sizeof(*trigger_tab),
+	r = request_mem_region(trigger_paddr, sizeof(trigger_tab),
 			       "APEI EINJ Trigger Table");
 	if (!r) {
 		pr_err("Can not request [mem %#010llx-%#010llx] for Trigger table\n",
 		       (unsigned long long)trigger_paddr,
 		       (unsigned long long)trigger_paddr +
-			    sizeof(*trigger_tab) - 1);
+			    sizeof(trigger_tab) - 1);
 		goto out;
 	}
-	trigger_tab = ioremap_cache(trigger_paddr, sizeof(*trigger_tab));
-	if (!trigger_tab) {
+	p = ioremap_cache(trigger_paddr, sizeof(*p));
+	if (!p) {
 		pr_err("Failed to map trigger table!\n");
 		goto out_rel_header;
 	}
-	rc = einj_check_trigger_header(trigger_tab);
+	memcpy_fromio(&trigger_tab, p, sizeof(trigger_tab));
+	rc = einj_check_trigger_header(&trigger_tab);
 	if (rc) {
 		pr_warn(FW_BUG "Invalid trigger error action table.\n");
 		goto out_rel_header;
 	}
 
 	/* No action structures in the TRIGGER_ERROR table, nothing to do */
-	if (!trigger_tab->entry_count)
+	if (!trigger_tab.entry_count)
 		goto out_rel_header;
 
 	rc = -EIO;
-	table_size = trigger_tab->table_size;
-	r = request_mem_region(trigger_paddr + sizeof(*trigger_tab),
-			       table_size - sizeof(*trigger_tab),
+	table_size = trigger_tab.table_size;
+	full_trigger_tab = kmalloc(table_size, GFP_KERNEL);
+	if (!full_trigger_tab)
+		goto out_rel_header;
+	r = request_mem_region(trigger_paddr + sizeof(trigger_tab),
+			       table_size - sizeof(trigger_tab),
 			       "APEI EINJ Trigger Table");
 	if (!r) {
 		pr_err("Can not request [mem %#010llx-%#010llx] for Trigger Table Entry\n",
-		       (unsigned long long)trigger_paddr + sizeof(*trigger_tab),
+		       (unsigned long long)trigger_paddr + sizeof(trigger_tab),
 		       (unsigned long long)trigger_paddr + table_size - 1);
-		goto out_rel_header;
+		goto out_free_trigger_tab;
 	}
-	iounmap(trigger_tab);
-	trigger_tab = ioremap_cache(trigger_paddr, table_size);
-	if (!trigger_tab) {
+	iounmap(p);
+	p = ioremap_cache(trigger_paddr, table_size);
+	if (!p) {
 		pr_err("Failed to map trigger table!\n");
 		goto out_rel_entry;
 	}
+	memcpy_fromio(full_trigger_tab, p, table_size);
 	trigger_entry = (struct acpi_whea_header *)
-		((char *)trigger_tab + sizeof(struct acpi_einj_trigger));
+		((char *)full_trigger_tab + sizeof(struct acpi_einj_trigger));
 	apei_resources_init(&trigger_resources);
 	apei_exec_ctx_init(&trigger_ctx, einj_ins_type,
 			   ARRAY_SIZE(einj_ins_type),
-			   trigger_entry, trigger_tab->entry_count);
+			   trigger_entry, trigger_tab.entry_count);
 	rc = apei_exec_collect_resources(&trigger_ctx, &trigger_resources);
 	if (rc)
 		goto out_fini;
@@ -392,7 +473,7 @@ static int __einj_error_trigger(u64 trigger_paddr, u32 type,
 
 		apei_resources_init(&addr_resources);
 		trigger_param_region = einj_get_trigger_parameter_region(
-			trigger_tab, param1, param2);
+			full_trigger_tab, param1, param2);
 		if (trigger_param_region) {
 			rc = apei_resources_add(&addr_resources,
 				trigger_param_region->address,
@@ -421,23 +502,33 @@ out_release:
 out_fini:
 	apei_resources_fini(&trigger_resources);
 out_rel_entry:
-	release_mem_region(trigger_paddr + sizeof(*trigger_tab),
-			   table_size - sizeof(*trigger_tab));
+	release_mem_region(trigger_paddr + sizeof(trigger_tab),
+			   table_size - sizeof(trigger_tab));
+out_free_trigger_tab:
+	kfree(full_trigger_tab);
 out_rel_header:
-	release_mem_region(trigger_paddr, sizeof(*trigger_tab));
+	release_mem_region(trigger_paddr, sizeof(trigger_tab));
 out:
-	if (trigger_tab)
-		iounmap(trigger_tab);
+	if (p)
+		iounmap(p);
 
 	return rc;
 }
 
+static bool is_end_of_list(u8 *val)
+{
+	for (int i = 0; i < COMPONENT_LEN; ++i) {
+		if (val[i] != 0xFF)
+			return false;
+	}
+	return true;
+}
 static int __einj_error_inject(u32 type, u32 flags, u64 param1, u64 param2,
 			       u64 param3, u64 param4)
 {
 	struct apei_exec_context ctx;
 	u64 val, trigger_paddr, timeout = FIRMWARE_TIMEOUT;
-	int rc;
+	int i, rc;
 
 	einj_exec_ctx_init(&ctx);
 
@@ -446,8 +537,10 @@ static int __einj_error_inject(u32 type, u32 flags, u64 param1, u64 param2,
 		return rc;
 	apei_exec_ctx_set_input(&ctx, type);
 	if (acpi5) {
-		struct set_error_type_with_address *v5param = einj_param;
+		struct set_error_type_with_address *v5param;
 
+		v5param = kmalloc(v5param_size, GFP_KERNEL);
+		memcpy_fromio(v5param, einj_param, v5param_size);
 		v5param->type = type;
 		if (type & ACPI5_VENDOR_BIT) {
 			switch (vendor_flags) {
@@ -467,8 +560,21 @@ static int __einj_error_inject(u32 type, u32 flags, u64 param1, u64 param2,
 			v5param->flags = flags;
 			v5param->memory_address = param1;
 			v5param->memory_address_range = param2;
-			v5param->apicid = param3;
-			v5param->pcie_sbdf = param4;
+
+			if (is_v2) {
+				for (i = 0; i < max_nr_components; i++) {
+					if (is_end_of_list(syndrome_data[i].comp_id.acpi_id))
+						break;
+					v5param->einjv2_struct.component_arr[i].comp_id =
+						syndrome_data[i].comp_id;
+					v5param->einjv2_struct.component_arr[i].comp_synd =
+						syndrome_data[i].comp_synd;
+				}
+				v5param->einjv2_struct.component_arr_count = i;
+			} else {
+				v5param->apicid = param3;
+				v5param->pcie_sbdf = param4;
+			}
 		} else {
 			switch (type) {
 			case ACPI_EINJ_PROCESSOR_CORRECTABLE:
@@ -492,15 +598,19 @@ static int __einj_error_inject(u32 type, u32 flags, u64 param1, u64 param2,
 				break;
 			}
 		}
+		memcpy_toio(einj_param, v5param, v5param_size);
+		kfree(v5param);
 	} else {
 		rc = apei_exec_run(&ctx, ACPI_EINJ_SET_ERROR_TYPE);
 		if (rc)
 			return rc;
 		if (einj_param) {
-			struct einj_parameter *v4param = einj_param;
+			struct einj_parameter v4param;
 
-			v4param->param1 = param1;
-			v4param->param2 = param2;
+			memcpy_fromio(&v4param, einj_param, sizeof(v4param));
+			v4param.param1 = param1;
+			v4param.param2 = param2;
+			memcpy_toio(einj_param, &v4param, sizeof(v4param));
 		}
 	}
 	rc = apei_exec_run(&ctx, ACPI_EINJ_EXECUTE_OPERATION);
@@ -551,10 +661,15 @@ int einj_error_inject(u32 type, u32 flags, u64 param1, u64 param2, u64 param3,
 	u64 base_addr, size;
 
 	/* If user manually set "flags", make sure it is legal */
-	if (flags && (flags &
-		~(SETWA_FLAGS_APICID|SETWA_FLAGS_MEM|SETWA_FLAGS_PCIE_SBDF)))
+	if (flags && (flags & ~(SETWA_FLAGS_APICID | SETWA_FLAGS_MEM |
+		      SETWA_FLAGS_PCIE_SBDF | SETWA_FLAGS_EINJV2)))
 		return -EINVAL;
 
+	/* check if type is a valid EINJv2 error type */
+	if (is_v2) {
+		if (!(type & available_error_type_v2))
+			return -EINVAL;
+	}
 	/*
 	 * We need extra sanity checks for memory errors.
 	 * Other types leap directly to injection.
@@ -632,6 +747,8 @@ static u64 error_param2;
 static u64 error_param3;
 static u64 error_param4;
 static struct dentry *einj_debug_dir;
+static char einj_buf[32];
+static bool einj_v2_enabled;
 static struct { u32 mask; const char *str; } const einj_error_type_string[] = {
 	{ BIT(0), "Processor Correctable" },
 	{ BIT(1), "Processor Uncorrectable non-fatal" },
@@ -648,6 +765,12 @@ static struct { u32 mask; const char *str; } const einj_error_type_string[] = {
 	{ BIT(31), "Vendor Defined Error Types" },
 };
 
+static struct { u32 mask; const char *str; } const einjv2_error_type_string[] = {
+	{ BIT(0), "EINJV2 Processor Error" },
+	{ BIT(1), "EINJV2 Memory Error" },
+	{ BIT(2), "EINJV2 PCI Express Error" },
+};
+
 static int available_error_type_show(struct seq_file *m, void *v)
 {
 
@@ -655,17 +778,22 @@ static int available_error_type_show(struct seq_file *m, void *v)
 		if (available_error_type & einj_error_type_string[pos].mask)
 			seq_printf(m, "0x%08x\t%s\n", einj_error_type_string[pos].mask,
 				   einj_error_type_string[pos].str);
-
+	if ((available_error_type & ACPI65_EINJV2_SUPP) && einj_v2_enabled) {
+		for (int pos = 0; pos < ARRAY_SIZE(einjv2_error_type_string); pos++) {
+			if (available_error_type_v2 & einjv2_error_type_string[pos].mask)
+				seq_printf(m, "V2_0x%08x\t%s\n", einjv2_error_type_string[pos].mask,
+					   einjv2_error_type_string[pos].str);
+		}
+	}
 	return 0;
 }
 
 DEFINE_SHOW_ATTRIBUTE(available_error_type);
 
-static int error_type_get(void *data, u64 *val)
+static ssize_t error_type_get(struct file *file, char __user *buf,
+				size_t count, loff_t *ppos)
 {
-	*val = error_type;
-
-	return 0;
+	return simple_read_from_buffer(buf, count, ppos, einj_buf, strlen(einj_buf));
 }
 
 bool einj_is_cxl_error_type(u64 type)
@@ -692,15 +820,35 @@ int einj_validate_error_type(u64 type)
 	if (tval & (tval - 1))
 		return -EINVAL;
 	if (!vendor)
-		if (!(type & available_error_type))
+		if (!(type & (available_error_type | available_error_type_v2)))
 			return -EINVAL;
 
 	return 0;
 }
 
-static int error_type_set(void *data, u64 val)
+static ssize_t error_type_set(struct file *file, const char __user *buf,
+				size_t count, loff_t *ppos)
 {
 	int rc;
+	u64 val;
+
+	/* Leave the last character for the NUL terminator */
+	if (count > sizeof(einj_buf) - 1)
+		return -EINVAL;
+
+	memset(einj_buf, 0, sizeof(einj_buf));
+	if (copy_from_user(einj_buf, buf, count))
+		return -EFAULT;
+
+	if (strncmp(einj_buf, "V2_", 3) == 0) {
+		if (!sscanf(einj_buf, "V2_%llx", &val))
+			return -EINVAL;
+		is_v2 = true;
+	} else {
+		if (!sscanf(einj_buf, "%llx", &val))
+			return -EINVAL;
+		is_v2 = false;
+	}
 
 	rc = einj_validate_error_type(val);
 	if (rc)
@@ -708,17 +856,24 @@ static int error_type_set(void *data, u64 val)
 
 	error_type = val;
 
-	return 0;
+	return count;
 }
 
-DEFINE_DEBUGFS_ATTRIBUTE(error_type_fops, error_type_get, error_type_set,
-			 "0x%llx\n");
+static const struct file_operations error_type_fops = {
+	.read		= error_type_get,
+	.write		= error_type_set,
+};
 
 static int error_inject_set(void *data, u64 val)
 {
 	if (!error_type)
 		return -EINVAL;
 
+	if (is_v2)
+		error_flags |= SETWA_FLAGS_EINJV2;
+	else
+		error_flags &= ~SETWA_FLAGS_EINJV2;
+
 	return einj_error_inject(error_type, error_flags, error_param1, error_param2,
 		error_param3, error_param4);
 }
@@ -741,6 +896,98 @@ static int einj_check_table(struct acpi_table_einj *einj_tab)
 	return 0;
 }
 
+static ssize_t u128_read(struct file *f, char __user *buf, size_t count, loff_t *off)
+{
+	char output[2 * COMPONENT_LEN + 1];
+	u8 *data = f->f_inode->i_private;
+	int i;
+
+	if (*off >= sizeof(output))
+		return 0;
+
+	for (i = 0; i < COMPONENT_LEN; i++)
+		sprintf(output + 2 * i, "%.02x", data[COMPONENT_LEN - i - 1]);
+	output[2 * COMPONENT_LEN] = '\n';
+
+	return simple_read_from_buffer(buf, count, off, output, sizeof(output));
+}
+
+static ssize_t u128_write(struct file *f, const char __user *buf, size_t count, loff_t *off)
+{
+	char input[2 + 2 * COMPONENT_LEN + 2];
+	u8 *save = f->f_inode->i_private;
+	u8 tmp[COMPONENT_LEN];
+	char byte[3] = {};
+	char *s, *e;
+	ssize_t c;
+	long val;
+	int i;
+
+	/* Require that user supply whole input line in one write(2) syscall */
+	if (*off)
+		return -EINVAL;
+
+	c = simple_write_to_buffer(input, sizeof(input), off, buf, count);
+	if (c < 0)
+		return c;
+
+	if (c < 1 || input[c - 1] != '\n')
+		return -EINVAL;
+
+	/* Empty line means invalidate this entry */
+	if (c == 1) {
+		memset(save, 0xff, COMPONENT_LEN);
+		return c;
+	}
+
+	if (input[0] == '0' && (input[1] == 'x' || input[1] == 'X'))
+		s = input + 2;
+	else
+		s = input;
+	e = input + c - 1;
+
+	for (i = 0; i < COMPONENT_LEN; i++) {
+		byte[1] = *--e;
+		byte[0] = e > s ? *--e : '0';
+		if (kstrtol(byte, 16, &val))
+			return -EINVAL;
+		tmp[i] = val;
+		if (e <= s)
+			break;
+	}
+	while (++i < COMPONENT_LEN)
+		tmp[i] = 0;
+
+	memcpy(save, tmp, COMPONENT_LEN);
+
+	return c;
+}
+
+static const struct file_operations u128_fops = {
+	.read	= u128_read,
+	.write	= u128_write,
+};
+
+static bool setup_einjv2_component_files(void)
+{
+	char name[32];
+
+	syndrome_data = kcalloc(max_nr_components, sizeof(syndrome_data[0]), GFP_KERNEL);
+	if (!syndrome_data)
+		return false;
+
+	for (int i = 0; i < max_nr_components; i++) {
+		sprintf(name, "component_id%d", i);
+		debugfs_create_file(name, 0600, einj_debug_dir,
+				    &syndrome_data[i].comp_id, &u128_fops);
+		sprintf(name, "component_syndrome%d", i);
+		debugfs_create_file(name, 0600, einj_debug_dir,
+				    &syndrome_data[i].comp_synd, &u128_fops);
+	}
+
+	return true;
+}
+
 static int __init einj_probe(struct faux_device *fdev)
 {
 	int rc;
@@ -764,7 +1011,7 @@ static int __init einj_probe(struct faux_device *fdev)
 		goto err_put_table;
 	}
 
-	rc = einj_get_available_error_type(&available_error_type);
+	rc = einj_get_available_error_types(&available_error_type, &available_error_type_v2);
 	if (rc)
 		goto err_put_table;
 
@@ -812,6 +1059,8 @@ static int __init einj_probe(struct faux_device *fdev)
 				   &error_param4);
 		debugfs_create_x32("notrigger", S_IRUSR | S_IWUSR,
 				   einj_debug_dir, &notrigger);
+		if (available_error_type & ACPI65_EINJV2_SUPP)
+			einj_v2_enabled = setup_einjv2_component_files();
 	}
 
 	if (vendor_dev[0]) {
@@ -848,7 +1097,7 @@ static void __exit einj_remove(struct faux_device *fdev)
 
 	if (einj_param) {
 		acpi_size size = (acpi5) ?
-			sizeof(struct set_error_type_with_address) :
+			v5param_size :
 			sizeof(struct einj_parameter);
 
 		acpi_os_unmap_iomem(einj_param, size);
@@ -860,6 +1109,7 @@ static void __exit einj_remove(struct faux_device *fdev)
 	apei_resources_release(&einj_resources);
 	apei_resources_fini(&einj_resources);
 	debugfs_remove_recursive(einj_debug_dir);
+	kfree(syndrome_data);
 	acpi_put_table((struct acpi_table_header *)einj_tab);
 }
 

drivers/acpi/apei/einj-cxl.c

@@ -30,7 +30,7 @@ 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);
+	rc = einj_get_available_error_type(&available_error_type, ACPI_EINJ_GET_ERROR_TYPE);
 	if (rc)
 		return rc;
 

drivers/acpi/apei/ghes.c

@@ -464,28 +464,41 @@ static void ghes_clear_estatus(struct ghes *ghes,
 		ghes_ack_error(ghes->generic_v2);
 }
 
-/*
- * Called as task_work before returning to user-space.
- * Ensure any queued work has been done before we return to the context that
- * triggered the notification.
+/**
+ * struct ghes_task_work - for synchronous RAS event
+ *
+ * @twork:                callback_head for task work
+ * @pfn:                  page frame number of corrupted page
+ * @flags:                work control flags
+ *
+ * Structure to pass task work to be handled before
+ * returning to user-space via task_work_add().
  */
-static void ghes_kick_task_work(struct callback_head *head)
+struct ghes_task_work {
+	struct callback_head twork;
+	u64 pfn;
+	int flags;
+};
+
+static void memory_failure_cb(struct callback_head *twork)
 {
-	struct acpi_hest_generic_status *estatus;
-	struct ghes_estatus_node *estatus_node;
-	u32 node_len;
+	struct ghes_task_work *twcb = container_of(twork, struct ghes_task_work, twork);
+	int ret;
 
-	estatus_node = container_of(head, struct ghes_estatus_node, task_work);
-	if (IS_ENABLED(CONFIG_ACPI_APEI_MEMORY_FAILURE))
-		memory_failure_queue_kick(estatus_node->task_work_cpu);
+	ret = memory_failure(twcb->pfn, twcb->flags);
+	gen_pool_free(ghes_estatus_pool, (unsigned long)twcb, sizeof(*twcb));
 
-	estatus = GHES_ESTATUS_FROM_NODE(estatus_node);
-	node_len = GHES_ESTATUS_NODE_LEN(cper_estatus_len(estatus));
-	gen_pool_free(ghes_estatus_pool, (unsigned long)estatus_node, node_len);
+	if (!ret || ret == -EHWPOISON || ret == -EOPNOTSUPP)
+		return;
+
+	pr_err("%#llx: Sending SIGBUS to %s:%d due to hardware memory corruption\n",
+			twcb->pfn, current->comm, task_pid_nr(current));
+	force_sig(SIGBUS);
 }
 
 static bool ghes_do_memory_failure(u64 physical_addr, int flags)
 {
+	struct ghes_task_work *twcb;
 	unsigned long pfn;
 
 	if (!IS_ENABLED(CONFIG_ACPI_APEI_MEMORY_FAILURE))
@@ -499,6 +512,18 @@ static bool ghes_do_memory_failure(u64 physical_addr, int flags)
 		return false;
 	}
 
+	if (flags == MF_ACTION_REQUIRED && current->mm) {
+		twcb = (void *)gen_pool_alloc(ghes_estatus_pool, sizeof(*twcb));
+		if (!twcb)
+			return false;
+
+		twcb->pfn = pfn;
+		twcb->flags = flags;
+		init_task_work(&twcb->twork, memory_failure_cb);
+		task_work_add(current, &twcb->twork, TWA_RESUME);
+		return true;
+	}
+
 	memory_failure_queue(pfn, flags);
 	return true;
 }
@@ -842,7 +867,7 @@ int cxl_cper_kfifo_get(struct cxl_cper_work_data *wd)
 }
 EXPORT_SYMBOL_NS_GPL(cxl_cper_kfifo_get, "CXL");
 
-static bool ghes_do_proc(struct ghes *ghes,
+static void ghes_do_proc(struct ghes *ghes,
 			 const struct acpi_hest_generic_status *estatus)
 {
 	int sev, sec_sev;
@@ -902,7 +927,16 @@ static bool ghes_do_proc(struct ghes *ghes,
 		}
 	}
 
-	return queued;
+	/*
+	 * If no memory failure work is queued for abnormal synchronous
+	 * errors, do a force kill.
+	 */
+	if (sync && !queued) {
+		dev_err(ghes->dev,
+			HW_ERR GHES_PFX "%s:%d: synchronous unrecoverable error (SIGBUS)\n",
+			current->comm, task_pid_nr(current));
+		force_sig(SIGBUS);
+	}
 }
 
 static void __ghes_print_estatus(const char *pfx,
@@ -1088,6 +1122,8 @@ static void __ghes_panic(struct ghes *ghes,
 
 	__ghes_print_estatus(KERN_EMERG, ghes->generic, estatus);
 
+	add_taint(TAINT_MACHINE_CHECK, LOCKDEP_STILL_OK);
+
 	ghes_clear_estatus(ghes, estatus, buf_paddr, fixmap_idx);
 
 	if (!panic_timeout)
@@ -1206,9 +1242,7 @@ static void ghes_proc_in_irq(struct irq_work *irq_work)
 	struct ghes_estatus_node *estatus_node;
 	struct acpi_hest_generic *generic;
 	struct acpi_hest_generic_status *estatus;
-	bool task_work_pending;
 	u32 len, node_len;
-	int ret;
 
 	llnode = llist_del_all(&ghes_estatus_llist);
 	/*
@@ -1223,25 +1257,16 @@ static void ghes_proc_in_irq(struct irq_work *irq_work)
 		estatus = GHES_ESTATUS_FROM_NODE(estatus_node);
 		len = cper_estatus_len(estatus);
 		node_len = GHES_ESTATUS_NODE_LEN(len);
-		task_work_pending = ghes_do_proc(estatus_node->ghes, estatus);
+
+		ghes_do_proc(estatus_node->ghes, estatus);
+
 		if (!ghes_estatus_cached(estatus)) {
 			generic = estatus_node->generic;
 			if (ghes_print_estatus(NULL, generic, estatus))
 				ghes_estatus_cache_add(generic, estatus);
 		}
-
-		if (task_work_pending && current->mm) {
-			estatus_node->task_work.func = ghes_kick_task_work;
-			estatus_node->task_work_cpu = smp_processor_id();
-			ret = task_work_add(current, &estatus_node->task_work,
-					    TWA_RESUME);
-			if (ret)
-				estatus_node->task_work.func = NULL;
-		}
-
-		if (!estatus_node->task_work.func)
-			gen_pool_free(ghes_estatus_pool,
-				      (unsigned long)estatus_node, node_len);
+		gen_pool_free(ghes_estatus_pool, (unsigned long)estatus_node,
+			      node_len);
 
 		llnode = next;
 	}
@@ -1302,7 +1327,6 @@ static int ghes_in_nmi_queue_one_entry(struct ghes *ghes,
 
 	estatus_node->ghes = ghes;
 	estatus_node->generic = ghes->generic;
-	estatus_node->task_work.func = NULL;
 	estatus = GHES_ESTATUS_FROM_NODE(estatus_node);
 
 	if (__ghes_read_estatus(estatus, buf_paddr, fixmap_idx, len)) {

include/acpi/ghes.h

@@ -35,9 +35,6 @@ struct ghes_estatus_node {
 	struct llist_node llnode;
 	struct acpi_hest_generic *generic;
 	struct ghes *ghes;
-
-	int task_work_cpu;
-	struct callback_head task_work;
 };
 
 struct ghes_estatus_cache {

include/linux/mm.h

@@ -3901,7 +3901,6 @@ enum mf_flags {
 int mf_dax_kill_procs(struct address_space *mapping, pgoff_t index,
 		      unsigned long count, int mf_flags);
 extern int memory_failure(unsigned long pfn, int flags);
-extern void memory_failure_queue_kick(int cpu);
 extern int unpoison_memory(unsigned long pfn);
 extern atomic_long_t num_poisoned_pages __read_mostly;
 extern int soft_offline_page(unsigned long pfn, int flags);

mm/memory-failure.c

@@ -2503,19 +2503,6 @@ static void memory_failure_work_func(struct work_struct *work)
 	}
 }
 
-/*
- * Process memory_failure work queued on the specified CPU.
- * Used to avoid return-to-userspace racing with the memory_failure workqueue.
- */
-void memory_failure_queue_kick(int cpu)
-{
-	struct memory_failure_cpu *mf_cpu;
-
-	mf_cpu = &per_cpu(memory_failure_cpu, cpu);
-	cancel_work_sync(&mf_cpu->work);
-	memory_failure_work_func(&mf_cpu->work);
-}
-
 static int __init memory_failure_init(void)
 {
 	struct memory_failure_cpu *mf_cpu;