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, 174 insertions, 0 deletions

diff --git a/drivers/acpi/apei/bert.c b/drivers/acpi/apei/bert.c
new file mode 100644
index 000000000..5427e49e6
--- /dev/null
+++ b/drivers/acpi/apei/bert.c
@@ -0,0 +1,174 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * APEI Boot Error Record Table (BERT) support
+ *
+ * Copyright 2011 Intel Corp.
+ *   Author: Huang Ying <ying.huang@intel.com>
+ *
+ * Under normal circumstances, when a hardware error occurs, the error
+ * handler receives control and processes the error. This gives OSPM a
+ * chance to process the error condition, report it, and optionally attempt
+ * recovery. In some cases, the system is unable to process an error.
+ * For example, system firmware or a management controller may choose to
+ * reset the system or the system might experience an uncontrolled crash
+ * or reset.The boot error source is used to report unhandled errors that
+ * occurred in a previous boot. This mechanism is described in the BERT
+ * table.
+ *
+ * For more information about BERT, please refer to ACPI Specification
+ * version 4.0, section 17.3.1
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/acpi.h>
+#include <linux/cper.h>
+#include <linux/io.h>
+
+#include "apei-internal.h"
+
+#undef pr_fmt
+#define pr_fmt(fmt) "BERT: " fmt
+
+#define ACPI_BERT_PRINT_MAX_RECORDS 5
+#define ACPI_BERT_PRINT_MAX_LEN 1024
+
+static int bert_disable __initdata;
+
+/*
+ * Print "all" the error records in the BERT table, but avoid huge spam to
+ * the console if the BIOS included oversize records, or too many records.
+ * Skipping some records here does not lose anything because the full
+ * data is available to user tools in:
+ *	/sys/firmware/acpi/tables/data/BERT
+ */
+static void __init bert_print_all(struct acpi_bert_region *region,
+				  unsigned int region_len)
+{
+	struct acpi_hest_generic_status *estatus =
+		(struct acpi_hest_generic_status *)region;
+	int remain = region_len;
+	int printed = 0, skipped = 0;
+	u32 estatus_len;
+
+	while (remain >= sizeof(struct acpi_bert_region)) {
+		estatus_len = cper_estatus_len(estatus);
+		if (remain < estatus_len) {
+			pr_err(FW_BUG "Truncated status block (length: %u).\n",
+			       estatus_len);
+			break;
+		}
+
+		/* No more error records. */
+		if (!estatus->block_status)
+			break;
+
+		if (cper_estatus_check(estatus)) {
+			pr_err(FW_BUG "Invalid error record.\n");
+			break;
+		}
+
+		if (estatus_len < ACPI_BERT_PRINT_MAX_LEN &&
+		    printed < ACPI_BERT_PRINT_MAX_RECORDS) {
+			pr_info_once("Error records from previous boot:\n");
+			cper_estatus_print(KERN_INFO HW_ERR, estatus);
+			printed++;
+		} else {
+			skipped++;
+		}
+
+		/*
+		 * Because the boot error source is "one-time polled" type,
+		 * clear Block Status of current Generic Error Status Block,
+		 * once it's printed.
+		 */
+		estatus->block_status = 0;
+
+		estatus = (void *)estatus + estatus_len;
+		remain -= estatus_len;
+	}
+
+	if (skipped)
+		pr_info(HW_ERR "Skipped %d error records\n", skipped);
+
+	if (printed + skipped)
+		pr_info("Total records found: %d\n", printed + skipped);
+}
+
+static int __init setup_bert_disable(char *str)
+{
+	bert_disable = 1;
+
+	return 1;
+}
+__setup("bert_disable", setup_bert_disable);
+
+static int __init bert_check_table(struct acpi_table_bert *bert_tab)
+{
+	if (bert_tab->header.length < sizeof(struct acpi_table_bert) ||
+	    bert_tab->region_length < sizeof(struct acpi_bert_region))
+		return -EINVAL;
+
+	return 0;
+}
+
+static int __init bert_init(void)
+{
+	struct apei_resources bert_resources;
+	struct acpi_bert_region *boot_error_region;
+	struct acpi_table_bert *bert_tab;
+	unsigned int region_len;
+	acpi_status status;
+	int rc = 0;
+
+	if (acpi_disabled)
+		return 0;
+
+	if (bert_disable) {
+		pr_info("Boot Error Record Table support is disabled.\n");
+		return 0;
+	}
+
+	status = acpi_get_table(ACPI_SIG_BERT, 0, (struct acpi_table_header **)&bert_tab);
+	if (status == AE_NOT_FOUND)
+		return 0;
+
+	if (ACPI_FAILURE(status)) {
+		pr_err("get table failed, %s.\n", acpi_format_exception(status));
+		return -EINVAL;
+	}
+
+	rc = bert_check_table(bert_tab);
+	if (rc) {
+		pr_err(FW_BUG "table invalid.\n");
+		goto out_put_bert_tab;
+	}
+
+	region_len = bert_tab->region_length;
+	apei_resources_init(&bert_resources);
+	rc = apei_resources_add(&bert_resources, bert_tab->address,
+				region_len, true);
+	if (rc)
+		goto out_put_bert_tab;
+	rc = apei_resources_request(&bert_resources, "APEI BERT");
+	if (rc)
+		goto out_fini;
+	boot_error_region = ioremap_cache(bert_tab->address, region_len);
+	if (boot_error_region) {
+		bert_print_all(boot_error_region, region_len);
+		iounmap(boot_error_region);
+	} else {
+		rc = -ENOMEM;
+	}
+
+	apei_resources_release(&bert_resources);
+out_fini:
+	apei_resources_fini(&bert_resources);
+out_put_bert_tab:
+	acpi_put_table((struct acpi_table_header *)bert_tab);
+
+	return rc;
+}
+
+late_initcall(bert_init);