Merge tag 'trace-v7.3-2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-tracegrafted

Pull tracing fixes from Steven Rostedt:

 - Fix error output of boot instance creation failure

   Currently if a boot instance creation fails, instead of printing out
   the name of the instance that failed, it prints "(null)". That is
   because it prints "cur_str" that had already been processed by
   strsep(). Print the saved name instead.

   While at it, print the error code of the failure.

 - Fix use-after-free for same named historgrams

   Histograms can be named so that they can be used in multiple events.
   But if the named histogram has a variable attached, the second event
   that uses the named histogram which duplicates it and needs to free
   the original after duplication leaves the old variable in place and
   still visible. If another histogram uses than variable, it will use
   the stale one which will try to reference the freed duplicate
   histogram and crash the kernel.

   Free the duplicate variables along with the duplicated histogram
   data.

 - Check return value of kthread_run() in event self test

   The events self tests uses a kthread for testing but does not check
   if it succeeded in creating a kthread. If the kthread creation were
   to fail, the code will still try to call kthread_stop() on the error
   returned.

 - Fix race between reading trace_pipe and updating subbuffer size

   If a user is reading the trace_pipe file at the same time they update
   the ring buffer sub-buffer size, can cause the trace_pipe read to
   read stale data. Add trace_access_lock() around updating the ring
   buffer sub-buffer size.

 - Fix eventfs_inode on failure path in creation of the events directory

   In the creation of the "events" directory, if after allocating the
   eventfs_inode a failure is detected, it calls cleanup_ei() which
   calls free_ei(). The free_ei() will test if eventfs_inode being freed
   has no children. It is a bug if it does. But on the failure case of
   the creation of the "events" directory, the children lists have not
   yet been initialized and the free will trigger a warning because
   list_empty() on an uninitialized list returns false.

   Move the initialization into init_ei() where it makes more sense and
   makes sure that a created eventfs_inode has its lists initialized
   upon creation.

 - Check return value of kthread_run() in ftrace direct sample code

   The sample code that shows how to use the ftrace direct calls does
   not test the return of kthread_run() to see if it succeeds. Return a
   failure if the kthread_run() doesn't succeed.

 - Clear user events state on fork in case of alloc failure

   On fork, the child gets a pointer to the parent's user events state.
   It makes a copy of it then updates the child's pointer to it. But if
   the allocation fails, the duplication function leaves the child with
   a pointer to its parent's descriptor. When the child cleans up its
   data, it will free the parent's descriptor while the parent is still
   using it.

   In the duplication function, set the child's user_event_mm to NULL
   before testing if the allocation succeeded, and when it exits it will
   not free the parent's descriptor.

 - Fix retry exhaustion in simple ring buffer reader swap

   simple_ring_buffer_swap_reader_page() starts with retry set to 8 and
   post-decrements it only after a failed link replacement. On the final
   attempt, a successful replacement leaves retry at zero, while a
   failed replacement leaves it at -1.

   But the check for success expects the retry value to be non-zero and
   exits with an error on zero. This is the opposite result. Fix it.

 - Fail nicely when the remote swap_reader_page() returns an error

   Currently, if the swap_reader_page() of a remote buffer fails, it
   triggers a WARN_ON_ONCE() and continues normally. Instead, have it
   exit with an error and a pr_warn() print instead of a full WARNING.

* tag 'trace-v7.3-2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace:
  ring-buffer: Stop remote reader update when page swap fails
  tracing: Fix retry exhaustion in simple ring buffer reader swap
  tracing/user_events: Clear copied tracing state before fork duplication
  samples/ftrace: Fix kthread_stop() on ERR_PTR in ftrace-direct-multi-modify
  samples/ftrace: Fix kthread_stop() on ERR_PTR in ftrace-direct-modify
  eventfs: Initialize ei->children and ei->list in init_ei()
  tracing: Fix use-after-free in trace_pipe read on sub-buffer order change
  tracing: Fix crash passing ERR_PTR to kthread_stop()
  tracing: Fix use-after-free with same-name named triggers
  tracing: Fix logged instance name on creation failure

1 files changed, 1045 insertions, 0 deletions

diff --git a/drivers/acpi/sysfs.c b/drivers/acpi/sysfs.c
new file mode 100644
index 000000000..dd4a99f09
--- /dev/null
+++ b/drivers/acpi/sysfs.c
@@ -0,0 +1,1045 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * sysfs.c - ACPI sysfs interface to userspace.
+ */
+
+#define pr_fmt(fmt) "ACPI: " fmt
+
+#include <linux/acpi.h>
+#include <linux/bitmap.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/kstrtox.h>
+#include <linux/moduleparam.h>
+
+#include "internal.h"
+
+#ifdef CONFIG_ACPI_DEBUG
+/*
+ * ACPI debug sysfs I/F, including:
+ * /sys/module/acpi/parameters/debug_layer
+ * /sys/module/acpi/parameters/debug_level
+ * /sys/module/acpi/parameters/trace_method_name
+ * /sys/module/acpi/parameters/trace_state
+ * /sys/module/acpi/parameters/trace_debug_layer
+ * /sys/module/acpi/parameters/trace_debug_level
+ */
+
+struct acpi_dlayer {
+	const char *name;
+	unsigned long value;
+};
+struct acpi_dlevel {
+	const char *name;
+	unsigned long value;
+};
+#define ACPI_DEBUG_INIT(v)	{ .name = #v, .value = v }
+
+static const struct acpi_dlayer acpi_debug_layers[] = {
+	ACPI_DEBUG_INIT(ACPI_UTILITIES),
+	ACPI_DEBUG_INIT(ACPI_HARDWARE),
+	ACPI_DEBUG_INIT(ACPI_EVENTS),
+	ACPI_DEBUG_INIT(ACPI_TABLES),
+	ACPI_DEBUG_INIT(ACPI_NAMESPACE),
+	ACPI_DEBUG_INIT(ACPI_PARSER),
+	ACPI_DEBUG_INIT(ACPI_DISPATCHER),
+	ACPI_DEBUG_INIT(ACPI_EXECUTER),
+	ACPI_DEBUG_INIT(ACPI_RESOURCES),
+	ACPI_DEBUG_INIT(ACPI_CA_DEBUGGER),
+	ACPI_DEBUG_INIT(ACPI_OS_SERVICES),
+	ACPI_DEBUG_INIT(ACPI_CA_DISASSEMBLER),
+	ACPI_DEBUG_INIT(ACPI_COMPILER),
+	ACPI_DEBUG_INIT(ACPI_TOOLS),
+};
+
+static const struct acpi_dlevel acpi_debug_levels[] = {
+	ACPI_DEBUG_INIT(ACPI_LV_INIT),
+	ACPI_DEBUG_INIT(ACPI_LV_DEBUG_OBJECT),
+	ACPI_DEBUG_INIT(ACPI_LV_INFO),
+	ACPI_DEBUG_INIT(ACPI_LV_REPAIR),
+	ACPI_DEBUG_INIT(ACPI_LV_TRACE_POINT),
+
+	ACPI_DEBUG_INIT(ACPI_LV_INIT_NAMES),
+	ACPI_DEBUG_INIT(ACPI_LV_PARSE),
+	ACPI_DEBUG_INIT(ACPI_LV_LOAD),
+	ACPI_DEBUG_INIT(ACPI_LV_DISPATCH),
+	ACPI_DEBUG_INIT(ACPI_LV_EXEC),
+	ACPI_DEBUG_INIT(ACPI_LV_NAMES),
+	ACPI_DEBUG_INIT(ACPI_LV_OPREGION),
+	ACPI_DEBUG_INIT(ACPI_LV_BFIELD),
+	ACPI_DEBUG_INIT(ACPI_LV_TABLES),
+	ACPI_DEBUG_INIT(ACPI_LV_VALUES),
+	ACPI_DEBUG_INIT(ACPI_LV_OBJECTS),
+	ACPI_DEBUG_INIT(ACPI_LV_RESOURCES),
+	ACPI_DEBUG_INIT(ACPI_LV_USER_REQUESTS),
+	ACPI_DEBUG_INIT(ACPI_LV_PACKAGE),
+
+	ACPI_DEBUG_INIT(ACPI_LV_ALLOCATIONS),
+	ACPI_DEBUG_INIT(ACPI_LV_FUNCTIONS),
+	ACPI_DEBUG_INIT(ACPI_LV_OPTIMIZATIONS),
+
+	ACPI_DEBUG_INIT(ACPI_LV_MUTEX),
+	ACPI_DEBUG_INIT(ACPI_LV_THREADS),
+	ACPI_DEBUG_INIT(ACPI_LV_IO),
+	ACPI_DEBUG_INIT(ACPI_LV_INTERRUPTS),
+
+	ACPI_DEBUG_INIT(ACPI_LV_AML_DISASSEMBLE),
+	ACPI_DEBUG_INIT(ACPI_LV_VERBOSE_INFO),
+	ACPI_DEBUG_INIT(ACPI_LV_FULL_TABLES),
+	ACPI_DEBUG_INIT(ACPI_LV_EVENTS),
+};
+
+static int param_get_debug_layer(char *buffer, const struct kernel_param *kp)
+{
+	int result = 0;
+	int i;
+
+	result = sprintf(buffer, "%-25s\tHex        SET\n", "Description");
+
+	for (i = 0; i < ARRAY_SIZE(acpi_debug_layers); i++) {
+		result += sprintf(buffer + result, "%-25s\t0x%08lX [%c]\n",
+				  acpi_debug_layers[i].name,
+				  acpi_debug_layers[i].value,
+				  (acpi_dbg_layer & acpi_debug_layers[i].value)
+				  ? '*' : ' ');
+	}
+	result +=
+	    sprintf(buffer + result, "%-25s\t0x%08X [%c]\n", "ACPI_ALL_DRIVERS",
+		    ACPI_ALL_DRIVERS,
+		    (acpi_dbg_layer & ACPI_ALL_DRIVERS) ==
+		    ACPI_ALL_DRIVERS ? '*' : (acpi_dbg_layer & ACPI_ALL_DRIVERS)
+		    == 0 ? ' ' : '-');
+	result +=
+	    sprintf(buffer + result,
+		    "--\ndebug_layer = 0x%08X ( * = enabled)\n",
+		    acpi_dbg_layer);
+
+	return result;
+}
+
+static int param_get_debug_level(char *buffer, const struct kernel_param *kp)
+{
+	int result = 0;
+	int i;
+
+	result = sprintf(buffer, "%-25s\tHex        SET\n", "Description");
+
+	for (i = 0; i < ARRAY_SIZE(acpi_debug_levels); i++) {
+		result += sprintf(buffer + result, "%-25s\t0x%08lX [%c]\n",
+				  acpi_debug_levels[i].name,
+				  acpi_debug_levels[i].value,
+				  (acpi_dbg_level & acpi_debug_levels[i].value)
+				  ? '*' : ' ');
+	}
+	result +=
+	    sprintf(buffer + result, "--\ndebug_level = 0x%08X (* = enabled)\n",
+		    acpi_dbg_level);
+
+	return result;
+}
+
+static const struct kernel_param_ops param_ops_debug_layer = {
+	.set = param_set_uint,
+	.get = param_get_debug_layer,
+};
+
+static const struct kernel_param_ops param_ops_debug_level = {
+	.set = param_set_uint,
+	.get = param_get_debug_level,
+};
+
+module_param_cb(debug_layer, &param_ops_debug_layer, &acpi_dbg_layer, 0644);
+module_param_cb(debug_level, &param_ops_debug_level, &acpi_dbg_level, 0644);
+
+static char trace_method_name[1024];
+
+static int param_set_trace_method_name(const char *val,
+				       const struct kernel_param *kp)
+{
+	u32 saved_flags = 0;
+	bool is_abs_path = true;
+
+	if (*val != '\\')
+		is_abs_path = false;
+
+	if ((is_abs_path && strlen(val) > 1023) ||
+	    (!is_abs_path && strlen(val) > 1022)) {
+		pr_err("%s: string parameter too long\n", kp->name);
+		return -ENOSPC;
+	}
+
+	/*
+	 * It's not safe to update acpi_gbl_trace_method_name without
+	 * having the tracer stopped, so we save the original tracer
+	 * state and disable it.
+	 */
+	saved_flags = acpi_gbl_trace_flags;
+	(void)acpi_debug_trace(NULL,
+			       acpi_gbl_trace_dbg_level,
+			       acpi_gbl_trace_dbg_layer,
+			       0);
+
+	/* This is a hack.  We can't kmalloc in early boot. */
+	if (is_abs_path)
+		strcpy(trace_method_name, val);
+	else {
+		trace_method_name[0] = '\\';
+		strcpy(trace_method_name+1, val);
+	}
+
+	/* Restore the original tracer state */
+	(void)acpi_debug_trace(trace_method_name,
+			       acpi_gbl_trace_dbg_level,
+			       acpi_gbl_trace_dbg_layer,
+			       saved_flags);
+
+	return 0;
+}
+
+static int param_get_trace_method_name(char *buffer, const struct kernel_param *kp)
+{
+	return sysfs_emit(buffer, "%s\n", acpi_gbl_trace_method_name);
+}
+
+static const struct kernel_param_ops param_ops_trace_method = {
+	.set = param_set_trace_method_name,
+	.get = param_get_trace_method_name,
+};
+
+static const struct kernel_param_ops param_ops_trace_attrib = {
+	.set = param_set_uint,
+	.get = param_get_uint,
+};
+
+module_param_cb(trace_method_name, &param_ops_trace_method, &trace_method_name, 0644);
+module_param_cb(trace_debug_layer, &param_ops_trace_attrib, &acpi_gbl_trace_dbg_layer, 0644);
+module_param_cb(trace_debug_level, &param_ops_trace_attrib, &acpi_gbl_trace_dbg_level, 0644);
+
+static int param_set_trace_state(const char *val,
+				 const struct kernel_param *kp)
+{
+	acpi_status status;
+	const char *method = trace_method_name;
+	u32 flags = 0;
+
+/* So "xxx-once" comparison should go prior than "xxx" comparison */
+#define acpi_compare_param(val, key)	\
+	strncmp((val), (key), sizeof(key) - 1)
+
+	if (!acpi_compare_param(val, "enable")) {
+		method = NULL;
+		flags = ACPI_TRACE_ENABLED;
+	} else if (!acpi_compare_param(val, "disable"))
+		method = NULL;
+	else if (!acpi_compare_param(val, "method-once"))
+		flags = ACPI_TRACE_ENABLED | ACPI_TRACE_ONESHOT;
+	else if (!acpi_compare_param(val, "method"))
+		flags = ACPI_TRACE_ENABLED;
+	else if (!acpi_compare_param(val, "opcode-once"))
+		flags = ACPI_TRACE_ENABLED | ACPI_TRACE_ONESHOT | ACPI_TRACE_OPCODE;
+	else if (!acpi_compare_param(val, "opcode"))
+		flags = ACPI_TRACE_ENABLED | ACPI_TRACE_OPCODE;
+	else
+		return -EINVAL;
+
+	status = acpi_debug_trace(method,
+				  acpi_gbl_trace_dbg_level,
+				  acpi_gbl_trace_dbg_layer,
+				  flags);
+	if (ACPI_FAILURE(status))
+		return -EBUSY;
+
+	return 0;
+}
+
+static int param_get_trace_state(char *buffer, const struct kernel_param *kp)
+{
+	if (!(acpi_gbl_trace_flags & ACPI_TRACE_ENABLED))
+		return sprintf(buffer, "disable\n");
+	if (!acpi_gbl_trace_method_name)
+		return sprintf(buffer, "enable\n");
+	if (acpi_gbl_trace_flags & ACPI_TRACE_ONESHOT)
+		return sprintf(buffer, "method-once\n");
+	else
+		return sprintf(buffer, "method\n");
+}
+
+module_param_call(trace_state, param_set_trace_state, param_get_trace_state,
+		  NULL, 0644);
+#endif /* CONFIG_ACPI_DEBUG */
+
+
+/* /sys/module/acpi/parameters/aml_debug_output */
+
+module_param_named(aml_debug_output, acpi_gbl_enable_aml_debug_object,
+		   byte, 0644);
+MODULE_PARM_DESC(aml_debug_output,
+		 "To enable/disable the ACPI Debug Object output.");
+
+/* /sys/module/acpi/parameters/acpica_version */
+static int param_get_acpica_version(char *buffer,
+				    const struct kernel_param *kp)
+{
+	int result;
+
+	result = sprintf(buffer, "%x\n", ACPI_CA_VERSION);
+
+	return result;
+}
+
+module_param_call(acpica_version, NULL, param_get_acpica_version, NULL, 0444);
+
+/*
+ * ACPI table sysfs I/F:
+ * /sys/firmware/acpi/tables/
+ * /sys/firmware/acpi/tables/data/
+ * /sys/firmware/acpi/tables/dynamic/
+ */
+
+static LIST_HEAD(acpi_table_attr_list);
+static struct kobject *tables_kobj;
+static struct kobject *tables_data_kobj;
+static struct kobject *dynamic_tables_kobj;
+static struct kobject *hotplug_kobj;
+
+#define ACPI_MAX_TABLE_INSTANCES	999
+#define ACPI_INST_SIZE			4 /* including trailing 0 */
+
+struct acpi_table_attr {
+	struct bin_attribute attr;
+	char name[ACPI_NAMESEG_SIZE];
+	int instance;
+	char filename[ACPI_NAMESEG_SIZE+ACPI_INST_SIZE];
+	struct list_head node;
+};
+
+struct acpi_data_attr {
+	struct bin_attribute attr;
+	u64	addr;
+	char filename[ACPI_NAMESEG_SIZE+ACPI_INST_SIZE];
+};
+
+static ssize_t acpi_table_show(struct file *filp, struct kobject *kobj,
+			       const struct bin_attribute *bin_attr, char *buf,
+			       loff_t offset, size_t count)
+{
+	struct acpi_table_attr *table_attr =
+	    container_of(bin_attr, struct acpi_table_attr, attr);
+	struct acpi_table_header *table_header = NULL;
+	acpi_status status;
+	ssize_t rc;
+
+	status = acpi_get_table(table_attr->name, table_attr->instance,
+				&table_header);
+	if (ACPI_FAILURE(status))
+		return -ENODEV;
+
+	rc = memory_read_from_buffer(buf, count, &offset, table_header,
+			table_header->length);
+	acpi_put_table(table_header);
+	return rc;
+}
+
+static int acpi_table_attr_init(struct kobject *tables_obj,
+				struct acpi_table_attr *table_attr,
+				struct acpi_table_header *table_header)
+{
+	struct acpi_table_header *header = NULL;
+	struct acpi_table_attr *attr = NULL;
+	char instance_str[ACPI_INST_SIZE];
+
+	sysfs_attr_init(&table_attr->attr.attr);
+	ACPI_COPY_NAMESEG(table_attr->name, table_header->signature);
+
+	list_for_each_entry(attr, &acpi_table_attr_list, node) {
+		if (ACPI_COMPARE_NAMESEG(table_attr->name, attr->name))
+			if (table_attr->instance < attr->instance)
+				table_attr->instance = attr->instance;
+	}
+	table_attr->instance++;
+	if (table_attr->instance > ACPI_MAX_TABLE_INSTANCES) {
+		pr_warn("%4.4s: too many table instances\n", table_attr->name);
+		return -ERANGE;
+	}
+
+	ACPI_COPY_NAMESEG(table_attr->filename, table_header->signature);
+	table_attr->filename[ACPI_NAMESEG_SIZE] = '\0';
+	if (table_attr->instance > 1 || (table_attr->instance == 1 &&
+					 !acpi_get_table
+					 (table_header->signature, 2, &header))) {
+		snprintf(instance_str, sizeof(instance_str), "%u",
+			 table_attr->instance);
+		strcat(table_attr->filename, instance_str);
+	}
+
+	table_attr->attr.size = table_header->length;
+	table_attr->attr.read = acpi_table_show;
+	table_attr->attr.attr.name = table_attr->filename;
+	table_attr->attr.attr.mode = 0400;
+
+	return sysfs_create_bin_file(tables_obj, &table_attr->attr);
+}
+
+acpi_status acpi_sysfs_table_handler(u32 event, void *table, void *context)
+{
+	struct acpi_table_attr *table_attr;
+
+	switch (event) {
+	case ACPI_TABLE_EVENT_INSTALL:
+		table_attr = kzalloc_obj(*table_attr);
+		if (!table_attr)
+			return AE_NO_MEMORY;
+
+		if (acpi_table_attr_init(dynamic_tables_kobj,
+					 table_attr, table)) {
+			kfree(table_attr);
+			return AE_ERROR;
+		}
+		list_add_tail(&table_attr->node, &acpi_table_attr_list);
+		break;
+	case ACPI_TABLE_EVENT_LOAD:
+	case ACPI_TABLE_EVENT_UNLOAD:
+	case ACPI_TABLE_EVENT_UNINSTALL:
+		/*
+		 * we do not need to do anything right now
+		 * because the table is not deleted from the
+		 * global table list when unloading it.
+		 */
+		break;
+	default:
+		return AE_BAD_PARAMETER;
+	}
+	return AE_OK;
+}
+
+static ssize_t acpi_data_show(struct file *filp, struct kobject *kobj,
+			      const struct bin_attribute *bin_attr, char *buf,
+			      loff_t offset, size_t count)
+{
+	struct acpi_data_attr *data_attr;
+	void __iomem *base;
+	ssize_t size;
+
+	data_attr = container_of(bin_attr, struct acpi_data_attr, attr);
+	size = data_attr->attr.size;
+
+	if (offset < 0)
+		return -EINVAL;
+
+	if (offset >= size)
+		return 0;
+
+	if (count > size - offset)
+		count = size - offset;
+
+	base = acpi_os_map_iomem(data_attr->addr, size);
+	if (!base)
+		return -ENOMEM;
+
+	memcpy_fromio(buf, base + offset, count);
+
+	acpi_os_unmap_iomem(base, size);
+
+	return count;
+}
+
+static int acpi_bert_data_init(void *th, struct acpi_data_attr *data_attr)
+{
+	struct acpi_table_bert *bert = th;
+
+	if (bert->header.length < sizeof(struct acpi_table_bert) ||
+	    bert->region_length < sizeof(struct acpi_bert_region)) {
+		kfree(data_attr);
+		return -EINVAL;
+	}
+	data_attr->addr = bert->address;
+	data_attr->attr.size = bert->region_length;
+
+	return sysfs_create_bin_file(tables_data_kobj, &data_attr->attr);
+}
+
+static int acpi_ccel_data_init(void *th, struct acpi_data_attr *data_attr)
+{
+	struct acpi_table_ccel *ccel = th;
+
+	if (ccel->header.length < sizeof(struct acpi_table_ccel) ||
+	    !ccel->log_area_start_address || !ccel->log_area_minimum_length) {
+		kfree(data_attr);
+		return -EINVAL;
+	}
+	data_attr->addr = ccel->log_area_start_address;
+	data_attr->attr.size = ccel->log_area_minimum_length;
+
+	return sysfs_create_bin_file(tables_data_kobj, &data_attr->attr);
+}
+
+static struct acpi_data_obj {
+	char *name;
+	int (*fn)(void *, struct acpi_data_attr *);
+} acpi_data_objs[] = {
+	{ ACPI_SIG_BERT, acpi_bert_data_init },
+	{ ACPI_SIG_CCEL, acpi_ccel_data_init },
+};
+
+#define NUM_ACPI_DATA_OBJS ARRAY_SIZE(acpi_data_objs)
+
+static int acpi_table_data_init(struct acpi_table_header *th, struct acpi_table_attr *table_attr)
+{
+	struct acpi_data_attr *data_attr;
+	int i;
+
+	for (i = 0; i < NUM_ACPI_DATA_OBJS; i++) {
+		if (ACPI_COMPARE_NAMESEG(th->signature, acpi_data_objs[i].name)) {
+			data_attr = kzalloc_obj(*data_attr);
+			if (!data_attr)
+				return -ENOMEM;
+			sysfs_attr_init(&data_attr->attr.attr);
+			data_attr->attr.read = acpi_data_show;
+			data_attr->attr.attr.mode = 0400;
+			strscpy(data_attr->filename, table_attr->filename);
+			data_attr->attr.attr.name = data_attr->filename;
+			return acpi_data_objs[i].fn(th, data_attr);
+		}
+	}
+	return 0;
+}
+
+static int acpi_tables_sysfs_init(void)
+{
+	struct acpi_table_attr *table_attr;
+	struct acpi_table_header *table_header = NULL;
+	int table_index;
+	acpi_status status;
+	int ret;
+
+	tables_kobj = kobject_create_and_add("tables", acpi_kobj);
+	if (!tables_kobj)
+		goto err;
+
+	tables_data_kobj = kobject_create_and_add("data", tables_kobj);
+	if (!tables_data_kobj)
+		goto err_tables_data;
+
+	dynamic_tables_kobj = kobject_create_and_add("dynamic", tables_kobj);
+	if (!dynamic_tables_kobj)
+		goto err_dynamic_tables;
+
+	for (table_index = 0;; table_index++) {
+		status = acpi_get_table_by_index(table_index, &table_header);
+
+		if (status == AE_BAD_PARAMETER)
+			break;
+
+		if (ACPI_FAILURE(status))
+			continue;
+
+		table_attr = kzalloc_obj(*table_attr);
+		if (!table_attr)
+			return -ENOMEM;
+
+		ret = acpi_table_attr_init(tables_kobj,
+					   table_attr, table_header);
+		if (ret) {
+			kfree(table_attr);
+			return ret;
+		}
+		list_add_tail(&table_attr->node, &acpi_table_attr_list);
+		acpi_table_data_init(table_header, table_attr);
+	}
+
+	kobject_uevent(tables_kobj, KOBJ_ADD);
+	kobject_uevent(tables_data_kobj, KOBJ_ADD);
+	kobject_uevent(dynamic_tables_kobj, KOBJ_ADD);
+
+	return 0;
+err_dynamic_tables:
+	kobject_put(tables_data_kobj);
+err_tables_data:
+	kobject_put(tables_kobj);
+err:
+	return -ENOMEM;
+}
+
+/*
+ * Detailed ACPI IRQ counters:
+ * /sys/firmware/acpi/interrupts/
+ */
+
+u32 acpi_irq_handled;
+u32 acpi_irq_not_handled;
+
+#define COUNT_GPE 0
+#define COUNT_SCI 1		/* acpi_irq_handled */
+#define COUNT_SCI_NOT 2		/* acpi_irq_not_handled */
+#define COUNT_ERROR 3		/* other */
+#define NUM_COUNTERS_EXTRA 4
+
+struct event_counter {
+	u32 count;
+	u32 flags;
+};
+
+static struct event_counter *all_counters;
+static u32 num_gpes;
+static u32 num_counters;
+static struct attribute **all_attrs;
+static u32 acpi_gpe_count;
+
+static struct attribute_group interrupt_stats_attr_group = {
+	.name = "interrupts",
+};
+
+static struct kobj_attribute *counter_attrs;
+
+static void delete_gpe_attr_array(void)
+{
+	struct event_counter *tmp = all_counters;
+
+	all_counters = NULL;
+	kfree(tmp);
+
+	if (counter_attrs) {
+		int i;
+
+		for (i = 0; i < num_gpes; i++)
+			kfree(counter_attrs[i].attr.name);
+
+		kfree(counter_attrs);
+	}
+	kfree(all_attrs);
+}
+
+static void gpe_count(u32 gpe_number)
+{
+	acpi_gpe_count++;
+
+	if (!all_counters)
+		return;
+
+	if (gpe_number < num_gpes)
+		all_counters[gpe_number].count++;
+	else
+		all_counters[num_gpes + ACPI_NUM_FIXED_EVENTS +
+			     COUNT_ERROR].count++;
+}
+
+static void fixed_event_count(u32 event_number)
+{
+	if (!all_counters)
+		return;
+
+	if (event_number < ACPI_NUM_FIXED_EVENTS)
+		all_counters[num_gpes + event_number].count++;
+	else
+		all_counters[num_gpes + ACPI_NUM_FIXED_EVENTS +
+			     COUNT_ERROR].count++;
+}
+
+static void acpi_global_event_handler(u32 event_type, acpi_handle device,
+	u32 event_number, void *context)
+{
+	if (event_type == ACPI_EVENT_TYPE_GPE) {
+		gpe_count(event_number);
+		pr_debug("GPE event 0x%02x\n", event_number);
+	} else if (event_type == ACPI_EVENT_TYPE_FIXED) {
+		fixed_event_count(event_number);
+		pr_debug("Fixed event 0x%02x\n", event_number);
+	} else {
+		pr_debug("Other event 0x%02x\n", event_number);
+	}
+}
+
+static int get_status(u32 index, acpi_event_status *ret,
+		      acpi_handle *handle)
+{
+	acpi_status status;
+
+	if (index >= num_gpes + ACPI_NUM_FIXED_EVENTS)
+		return -EINVAL;
+
+	if (index < num_gpes) {
+		status = acpi_get_gpe_device(index, handle);
+		if (ACPI_FAILURE(status)) {
+			pr_warn("Invalid GPE 0x%x", index);
+			return -ENXIO;
+		}
+		status = acpi_get_gpe_status(*handle, index, ret);
+	} else {
+		status = acpi_get_event_status(index - num_gpes, ret);
+	}
+	if (ACPI_FAILURE(status))
+		return -EIO;
+
+	return 0;
+}
+
+static ssize_t counter_show(struct kobject *kobj,
+			    struct kobj_attribute *attr, char *buf)
+{
+	int index = attr - counter_attrs;
+	int size;
+	acpi_handle handle;
+	acpi_event_status status;
+	int result = 0;
+
+	all_counters[num_gpes + ACPI_NUM_FIXED_EVENTS + COUNT_SCI].count =
+	    acpi_irq_handled;
+	all_counters[num_gpes + ACPI_NUM_FIXED_EVENTS + COUNT_SCI_NOT].count =
+	    acpi_irq_not_handled;
+	all_counters[num_gpes + ACPI_NUM_FIXED_EVENTS + COUNT_GPE].count =
+	    acpi_gpe_count;
+	size = sysfs_emit(buf, "%8u", all_counters[index].count);
+
+	/* "gpe_all" or "sci" */
+	if (index >= num_gpes + ACPI_NUM_FIXED_EVENTS)
+		goto end;
+
+	result = get_status(index, &status, &handle);
+	if (result)
+		goto end;
+
+	if (status & ACPI_EVENT_FLAG_ENABLE_SET)
+		size += sysfs_emit_at(buf, size, "  EN");
+	else
+		size += sysfs_emit_at(buf, size, "    ");
+	if (status & ACPI_EVENT_FLAG_STATUS_SET)
+		size += sysfs_emit_at(buf, size, " STS");
+	else
+		size += sysfs_emit_at(buf, size, "    ");
+
+	if (!(status & ACPI_EVENT_FLAG_HAS_HANDLER))
+		size += sysfs_emit_at(buf, size, " invalid     ");
+	else if (status & ACPI_EVENT_FLAG_ENABLED)
+		size += sysfs_emit_at(buf, size, " enabled     ");
+	else if (status & ACPI_EVENT_FLAG_WAKE_ENABLED)
+		size += sysfs_emit_at(buf, size, " wake_enabled");
+	else
+		size += sysfs_emit_at(buf, size, " disabled    ");
+	if (status & ACPI_EVENT_FLAG_MASKED)
+		size += sysfs_emit_at(buf, size, " masked  ");
+	else
+		size += sysfs_emit_at(buf, size, " unmasked");
+
+end:
+	size += sysfs_emit_at(buf, size, "\n");
+	return result ? result : size;
+}
+
+/*
+ * counter_set() sets the specified counter.
+ * setting the total "sci" file to any value clears all counters.
+ * enable/disable/clear a gpe/fixed event in user space.
+ */
+static ssize_t counter_set(struct kobject *kobj,
+			   struct kobj_attribute *attr, const char *buf,
+			   size_t size)
+{
+	int index = attr - counter_attrs;
+	acpi_event_status status;
+	acpi_handle handle;
+	int result = 0;
+	unsigned long tmp;
+
+	if (index == num_gpes + ACPI_NUM_FIXED_EVENTS + COUNT_SCI) {
+		int i;
+		for (i = 0; i < num_counters; ++i)
+			all_counters[i].count = 0;
+		acpi_gpe_count = 0;
+		acpi_irq_handled = 0;
+		acpi_irq_not_handled = 0;
+		goto end;
+	}
+
+	/* show the event status for both GPEs and Fixed Events */
+	result = get_status(index, &status, &handle);
+	if (result)
+		goto end;
+
+	if (!(status & ACPI_EVENT_FLAG_HAS_HANDLER)) {
+		pr_warn("Can not change Invalid GPE/Fixed Event status\n");
+		return -EINVAL;
+	}
+
+	if (index < num_gpes) {
+		if (!strcmp(buf, "disable\n") &&
+		    (status & ACPI_EVENT_FLAG_ENABLED))
+			result = acpi_disable_gpe(handle, index);
+		else if (!strcmp(buf, "enable\n") &&
+			 !(status & ACPI_EVENT_FLAG_ENABLED))
+			result = acpi_enable_gpe(handle, index);
+		else if (!strcmp(buf, "clear\n") &&
+			 (status & ACPI_EVENT_FLAG_STATUS_SET))
+			result = acpi_clear_gpe(handle, index);
+		else if (!strcmp(buf, "mask\n"))
+			result = acpi_mask_gpe(handle, index, TRUE);
+		else if (!strcmp(buf, "unmask\n"))
+			result = acpi_mask_gpe(handle, index, FALSE);
+		else if (!kstrtoul(buf, 0, &tmp))
+			all_counters[index].count = tmp;
+		else
+			result = -EINVAL;
+	} else if (index < num_gpes + ACPI_NUM_FIXED_EVENTS) {
+		int event = index - num_gpes;
+		if (!strcmp(buf, "disable\n") &&
+		    (status & ACPI_EVENT_FLAG_ENABLE_SET))
+			result = acpi_disable_event(event, ACPI_NOT_ISR);
+		else if (!strcmp(buf, "enable\n") &&
+			 !(status & ACPI_EVENT_FLAG_ENABLE_SET))
+			result = acpi_enable_event(event, ACPI_NOT_ISR);
+		else if (!strcmp(buf, "clear\n") &&
+			 (status & ACPI_EVENT_FLAG_STATUS_SET))
+			result = acpi_clear_event(event);
+		else if (!kstrtoul(buf, 0, &tmp))
+			all_counters[index].count = tmp;
+		else
+			result = -EINVAL;
+	} else
+		all_counters[index].count = strtoul(buf, NULL, 0);
+
+	if (ACPI_FAILURE(result))
+		result = -EINVAL;
+end:
+	return result ? result : size;
+}
+
+/*
+ * A Quirk Mechanism for GPE Flooding Prevention:
+ *
+ * Quirks may be needed to prevent GPE flooding on a specific GPE. The
+ * flooding typically cannot be detected and automatically prevented by
+ * ACPI_GPE_DISPATCH_NONE check because there is a _Lxx/_Exx prepared in
+ * the AML tables. This normally indicates a feature gap in Linux, thus
+ * instead of providing endless quirk tables, we provide a boot parameter
+ * for those who want this quirk. For example, if the users want to prevent
+ * the GPE flooding for GPE 00, they need to specify the following boot
+ * parameter:
+ *   acpi_mask_gpe=0x00
+ * Note, the parameter can be a list (see bitmap_parselist() for the details).
+ * The masking status can be modified by the following runtime controlling
+ * interface:
+ *   echo unmask > /sys/firmware/acpi/interrupts/gpe00
+ */
+#define ACPI_MASKABLE_GPE_MAX	0x100
+static DECLARE_BITMAP(acpi_masked_gpes_map, ACPI_MASKABLE_GPE_MAX) __initdata;
+
+static int __init acpi_gpe_set_masked_gpes(char *val)
+{
+	int ret;
+	u8 gpe;
+
+	ret = kstrtou8(val, 0, &gpe);
+	if (ret) {
+		ret = bitmap_parselist(val, acpi_masked_gpes_map, ACPI_MASKABLE_GPE_MAX);
+		if (ret)
+			return ret;
+	} else
+		set_bit(gpe, acpi_masked_gpes_map);
+
+	return 1;
+}
+__setup("acpi_mask_gpe=", acpi_gpe_set_masked_gpes);
+
+void __init acpi_gpe_apply_masked_gpes(void)
+{
+	acpi_handle handle;
+	acpi_status status;
+	u16 gpe;
+
+	for_each_set_bit(gpe, acpi_masked_gpes_map, ACPI_MASKABLE_GPE_MAX) {
+		status = acpi_get_gpe_device(gpe, &handle);
+		if (ACPI_SUCCESS(status)) {
+			pr_info("Masking GPE 0x%x.\n", gpe);
+			(void)acpi_mask_gpe(handle, gpe, TRUE);
+		}
+	}
+}
+
+void acpi_irq_stats_init(void)
+{
+	acpi_status status;
+	int i;
+
+	if (all_counters)
+		return;
+
+	num_gpes = acpi_current_gpe_count;
+	num_counters = num_gpes + ACPI_NUM_FIXED_EVENTS + NUM_COUNTERS_EXTRA;
+
+	all_attrs = kzalloc_objs(*all_attrs, num_counters + 1);
+	if (all_attrs == NULL)
+		return;
+
+	all_counters = kzalloc_objs(*all_counters, num_counters);
+	if (all_counters == NULL)
+		goto fail;
+
+	status = acpi_install_global_event_handler(acpi_global_event_handler, NULL);
+	if (ACPI_FAILURE(status))
+		goto fail;
+
+	counter_attrs = kzalloc_objs(*counter_attrs, num_counters);
+	if (counter_attrs == NULL)
+		goto fail;
+
+	for (i = 0; i < num_counters; ++i) {
+		char buffer[12];
+		char *name;
+
+		if (i < num_gpes)
+			sprintf(buffer, "gpe%02X", i);
+		else if (i == num_gpes + ACPI_EVENT_PMTIMER)
+			sprintf(buffer, "ff_pmtimer");
+		else if (i == num_gpes + ACPI_EVENT_GLOBAL)
+			sprintf(buffer, "ff_gbl_lock");
+		else if (i == num_gpes + ACPI_EVENT_POWER_BUTTON)
+			sprintf(buffer, "ff_pwr_btn");
+		else if (i == num_gpes + ACPI_EVENT_SLEEP_BUTTON)
+			sprintf(buffer, "ff_slp_btn");
+		else if (i == num_gpes + ACPI_EVENT_RTC)
+			sprintf(buffer, "ff_rt_clk");
+		else if (i == num_gpes + ACPI_NUM_FIXED_EVENTS + COUNT_GPE)
+			sprintf(buffer, "gpe_all");
+		else if (i == num_gpes + ACPI_NUM_FIXED_EVENTS + COUNT_SCI)
+			sprintf(buffer, "sci");
+		else if (i == num_gpes + ACPI_NUM_FIXED_EVENTS + COUNT_SCI_NOT)
+			sprintf(buffer, "sci_not");
+		else if (i == num_gpes + ACPI_NUM_FIXED_EVENTS + COUNT_ERROR)
+			sprintf(buffer, "error");
+		else
+			sprintf(buffer, "bug%02X", i);
+
+		name = kstrdup(buffer, GFP_KERNEL);
+		if (name == NULL)
+			goto fail;
+
+		sysfs_attr_init(&counter_attrs[i].attr);
+		counter_attrs[i].attr.name = name;
+		counter_attrs[i].attr.mode = 0644;
+		counter_attrs[i].show = counter_show;
+		counter_attrs[i].store = counter_set;
+
+		all_attrs[i] = &counter_attrs[i].attr;
+	}
+
+	interrupt_stats_attr_group.attrs = all_attrs;
+	if (!sysfs_create_group(acpi_kobj, &interrupt_stats_attr_group))
+		return;
+
+fail:
+	delete_gpe_attr_array();
+}
+
+static void __exit interrupt_stats_exit(void)
+{
+	sysfs_remove_group(acpi_kobj, &interrupt_stats_attr_group);
+
+	delete_gpe_attr_array();
+}
+
+static ssize_t pm_profile_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf)
+{
+	return sysfs_emit(buf, "%d\n", acpi_gbl_FADT.preferred_profile);
+}
+
+static const struct kobj_attribute pm_profile_attr = __ATTR_RO(pm_profile);
+
+static ssize_t enabled_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf)
+{
+	struct acpi_hotplug_profile *hotplug = to_acpi_hotplug_profile(kobj);
+
+	return sysfs_emit(buf, "%d\n", hotplug->enabled);
+}
+
+static ssize_t enabled_store(struct kobject *kobj, struct kobj_attribute *attr,
+			     const char *buf, size_t size)
+{
+	struct acpi_hotplug_profile *hotplug = to_acpi_hotplug_profile(kobj);
+	unsigned int val;
+
+	if (kstrtouint(buf, 10, &val) || val > 1)
+		return -EINVAL;
+
+	acpi_scan_hotplug_enabled(hotplug, val);
+	return size;
+}
+
+static struct kobj_attribute hotplug_enabled_attr = __ATTR_RW(enabled);
+
+static struct attribute *hotplug_profile_attrs[] = {
+	&hotplug_enabled_attr.attr,
+	NULL
+};
+ATTRIBUTE_GROUPS(hotplug_profile);
+
+static const struct kobj_type acpi_hotplug_profile_ktype = {
+	.sysfs_ops = &kobj_sysfs_ops,
+	.default_groups = hotplug_profile_groups,
+};
+
+void acpi_sysfs_add_hotplug_profile(struct acpi_hotplug_profile *hotplug,
+				    const char *name)
+{
+	int error;
+
+	if (!hotplug_kobj)
+		goto err_out;
+
+	error = kobject_init_and_add(&hotplug->kobj,
+		&acpi_hotplug_profile_ktype, hotplug_kobj, "%s", name);
+	if (error) {
+		kobject_put(&hotplug->kobj);
+		goto err_out;
+	}
+
+	kobject_uevent(&hotplug->kobj, KOBJ_ADD);
+	return;
+
+ err_out:
+	pr_err("Unable to add hotplug profile '%s'\n", name);
+}
+
+static ssize_t force_remove_show(struct kobject *kobj,
+				 struct kobj_attribute *attr, char *buf)
+{
+	return sysfs_emit(buf, "%d\n", 0);
+}
+
+static ssize_t force_remove_store(struct kobject *kobj,
+				  struct kobj_attribute *attr,
+				  const char *buf, size_t size)
+{
+	bool val;
+	int ret;
+
+	ret = kstrtobool(buf, &val);
+	if (ret < 0)
+		return ret;
+
+	if (val) {
+		pr_err("Enabling force_remove is not supported anymore. Please report to linux-acpi@vger.kernel.org if you depend on this functionality\n");
+		return -EINVAL;
+	}
+	return size;
+}
+
+static const struct kobj_attribute force_remove_attr = __ATTR_RW(force_remove);
+
+int __init acpi_sysfs_init(void)
+{
+	int result;
+
+	result = acpi_tables_sysfs_init();
+	if (result)
+		return result;
+
+	hotplug_kobj = kobject_create_and_add("hotplug", acpi_kobj);
+	if (!hotplug_kobj)
+		return -ENOMEM;
+
+	result = sysfs_create_file(hotplug_kobj, &force_remove_attr.attr);
+	if (result)
+		return result;
+
+	result = sysfs_create_file(acpi_kobj, &pm_profile_attr.attr);
+	return result;
+}