@@ -30,6 +30,7 @@ man1_MANS = \
ndctl-create-namespace.1 \
ndctl-destroy-namespace.1 \
ndctl-check-namespace.1 \
+ ndctl-inject-error.1 \
ndctl-list.1
CLEANFILES = $(man1_MANS)
new file mode 100644
@@ -0,0 +1,108 @@
+ndctl-inject-error(1)
+=====================
+
+NAME
+----
+ndctl-inject-error - inject media errors at a namespace offset
+
+SYNOPSIS
+--------
+[verse]
+'ndctl inject-error' <namespace> [<options>]
+
+include::namespace-description.txt[]
+
+ndctl-inject-error can be used to ask the platform to simulate media errors
+in the NVDIMM address space to aid debugging and development of features
+related to error handling.
+
+WARNING: These commands are DANGEROUS and can cause data loss. They are
+only provided for testing and debugging purposes.
+
+EXAMPLES
+--------
+
+Inject errors in namespace0.0 at block 12 for a 2 blocks (i.e. 12, 13)
+[verse]
+ndctl inject-error --block=12 --count=2 namespace0.0
+
+Check status of injected errors on namespace0.0
+[verse]
+ndctl inject-error --status namespace0.0
+
+Uninject errors at block 12 for 2 blocks on namespace0.0
+[verse]
+ndctl inject-error --uninject --block=12 --count=2 namespace0.0
+
+OPTIONS
+-------
+-B::
+--block=::
+ Namespace block offset in 512 byte sized blocks where the error is
+ to be injected.
+
+ NOTE: The offset is interpreted in different ways based on the "mode"
+ of the namespace. For "raw" mode, the offset is the base namespace
+ offset. For "memory" mode (i.e. a "pfn" namespace), the offset is
+ relative to the user-visible part of the namespace, and the offset
+ introduced by the kernel's metadata will be accounted for. For a
+ "sector" mode namespace (i.e. a "BTT" namespace), the offset is
+ relative to the base namespace, as the BTT translation details are
+ internal to the kernel, and can't be accounted for while injecting
+ errors.
+
+-n::
+--count=::
+ Number of blocks to inject as errors. This is also in terms of fixed,
+ 512 byte blocks.
+
+-d::
+--uninject::
+ This option will ask the platform to remove any injected errors for the
+ specified block offset, and count.
+
+ WARNING: This will not clear the kernel's internal badblock tracking,
+ those can only be cleared by doing a write to the affected locations.
+ Hence use the --clear option only if you know exactly what you are
+ doing. For normal usage, injected errors should only be cleared by
+ doing writes. Do not expect have the original data intact after
+ injecting an error, and clearing it using --clear - it will be lost,
+ as the only "real" way to clear the error location is to write to it
+ or zero it (truncate/hole-punch).
+
+-t::
+--status::
+ This option will retrieve the status of injected errors. Note that
+ this will not retrieve all known/latent errors (i.e. non injected
+ ones), and is NOT equivalent to performing an Address Range Scrub.
+
+-N::
+--no-notify::
+ This option is only valid when injecting errors. By default, the error
+ inject command and will ask platform firmware to trigger a notification
+ in the kernel, asking it to update its state of known errors.
+ With this option, the error will still be injected, the kernel will not
+ get a notification, and the error will appear as a latent media error
+ when the location is accessed. If the platform firmware does not
+ support this feature, this will have no effect.
+
+-v::
+--verbose::
+ Emit debug messages for the error injection process
+
+include::human-option.txt[]
+
+-r::
+--region=::
+include::xable-region-options.txt[]
+
+COPYRIGHT
+---------
+Copyright (c) 2016 - 2017, Intel Corporation. License GPLv2: GNU GPL
+version 2 <http://gnu.org/licenses/gpl.html>. This is free software:
+you are free to change and redistribute it. There is NO WARRANTY, to
+the extent permitted by law.
+
+SEE ALSO
+--------
+linkndctl:ndctl-list[1],
@@ -50,6 +50,7 @@ linkndctl:ndctl-enable-namespace[1],
linkndctl:ndctl-disable-namespace[1],
linkndctl:ndctl-zero-labels[1],
linkndctl:ndctl-read-labels[1],
+linkndctl:ndctl-inject-error[1],
linkndctl:ndctl-list[1],
https://www.kernel.org/doc/Documentation/nvdimm/nvdimm.txt[LIBNVDIMM
Overview],
@@ -35,6 +35,7 @@ int cmd_read_labels(int argc, const char **argv, void *ctx);
int cmd_write_labels(int argc, const char **argv, void *ctx);
int cmd_init_labels(int argc, const char **argv, void *ctx);
int cmd_check_labels(int argc, const char **argv, void *ctx);
+int cmd_inject_error(int argc, const char **argv, void *ctx);
int cmd_list(int argc, const char **argv, void *ctx);
#ifdef ENABLE_TEST
int cmd_test(int argc, const char **argv, void *ctx);
@@ -91,7 +91,7 @@ __ndctlcomp()
COMPREPLY=( $( compgen -W "$1" -- "$2" ) )
for cword in "${COMPREPLY[@]}"; do
- if [[ "$cword" == @(--bus|--region|--type|--mode|--size|--dimm|--reconfig|--uuid|--name|--sector-size|--map|--namespace|--input|--output|--label-version|--align) ]]; then
+ if [[ "$cword" == @(--bus|--region|--type|--mode|--size|--dimm|--reconfig|--uuid|--name|--sector-size|--map|--namespace|--input|--output|--label-version|--align|--block|--count) ]]; then
COMPREPLY[$i]="${cword}="
else
COMPREPLY[$i]="${cword} "
@@ -257,6 +257,9 @@ __ndctl_comp_non_option_args()
zero-labels)
opts="$(__ndctl_get_dimms -i) all"
;;
+ inject-error)
+ opts="$(__ndctl_get_ns -i)"
+ ;;
*)
return
;;
@@ -11,7 +11,8 @@ ndctl_SOURCES = ndctl.c \
../util/log.c \
list.c \
test.c \
- ../util/json.c
+ ../util/json.c \
+ inject-error.c
if ENABLE_SMART
ndctl_SOURCES += util/json-smart.c
new file mode 100644
@@ -0,0 +1,373 @@
+/*
+ * Copyright(c) 2015-2017 Intel Corporation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of version 2 of the GNU General Public License as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ */
+#include <stdio.h>
+#include <fcntl.h>
+#include <errno.h>
+#include <stdlib.h>
+#include <string.h>
+#include <limits.h>
+#include <unistd.h>
+#include <stdint.h>
+#include <stdbool.h>
+#include <sys/types.h>
+#include <sys/ioctl.h>
+
+#include <util/log.h>
+#include <util/size.h>
+#include <util/json.h>
+#include <json-c/json.h>
+#include <util/filter.h>
+#include <ndctl/libndctl.h>
+#include <util/parse-options.h>
+#include <ccan/array_size/array_size.h>
+#include <ccan/short_types/short_types.h>
+#ifdef HAVE_NDCTL_H
+#include <linux/ndctl.h>
+#else
+#include <ndctl.h>
+#endif
+
+#include "private.h"
+#include <builtin.h>
+#include <test.h>
+
+static bool verbose;
+static struct parameters {
+ const char *bus;
+ const char *region;
+ const char *namespace;
+ const char *block;
+ const char *count;
+ bool clear;
+ bool status;
+ bool no_notify;
+ bool human;
+} param;
+
+static struct inject_ctx {
+ u64 block;
+ u64 count;
+ unsigned int op_mask;
+ unsigned long flags;
+ bool notify;
+} ictx;
+
+#define BASE_OPTIONS() \
+OPT_STRING('b', "bus", ¶m.bus, "bus-id", \
+ "limit namespace to a bus with an id or provider of <bus-id>"), \
+OPT_STRING('r', "region", ¶m.region, "region-id", \
+ "limit namespace to a region with an id or name of <region-id>"), \
+OPT_BOOLEAN('v', "verbose", &verbose, "emit extra debug messages to stderr")
+
+#define INJECT_OPTIONS() \
+OPT_STRING('B', "block", ¶m.block, "namespace block offset (512B)", \
+ "specify the block at which to (un)inject the error"), \
+OPT_STRING('n', "count", ¶m.count, "count", \
+ "specify the number of blocks of errors to (un)inject"), \
+OPT_BOOLEAN('d', "uninject", ¶m.clear, \
+ "un-inject a previously injected error"), \
+OPT_BOOLEAN('t', "status", ¶m.status, "get error injection status"), \
+OPT_BOOLEAN('N', "no-notify", ¶m.no_notify, "firmware should not notify OS"), \
+OPT_BOOLEAN('u', "human", ¶m.human, "use human friendly number formats ")
+
+static const struct option inject_options[] = {
+ BASE_OPTIONS(),
+ INJECT_OPTIONS(),
+ OPT_END(),
+};
+
+enum {
+ OP_INJECT = 0,
+ OP_CLEAR,
+ OP_STATUS,
+};
+
+static int inject_init(void)
+{
+ if (!param.clear && !param.status) {
+ ictx.op_mask |= 1 << OP_INJECT;
+ ictx.notify = true;
+ if (param.no_notify)
+ ictx.notify = false;
+ }
+ if (param.clear) {
+ if (param.status) {
+ error("status is invalid with inject or uninject\n");
+ return -EINVAL;
+ }
+ ictx.op_mask |= 1 << OP_CLEAR;
+ }
+ if (param.status) {
+ if (param.block || param.count) {
+ error("status is invalid with inject or uninject\n");
+ return -EINVAL;
+ }
+ ictx.op_mask |= 1 << OP_STATUS;
+ }
+
+ if (ictx.op_mask == 0) {
+ error("Unable to determine operation\n");
+ return -EINVAL;
+ }
+ ictx.op_mask &= (
+ (1 << OP_INJECT) |
+ (1 << OP_CLEAR) |
+ (1 << OP_STATUS));
+
+ if (param.block) {
+ ictx.block = parse_size64(param.block);
+ if (ictx.block == ULLONG_MAX) {
+ error("Invalid block: %s\n", param.block);
+ return -EINVAL;
+ }
+ }
+ if (param.count) {
+ ictx.count = parse_size64(param.count);
+ if (ictx.count == ULLONG_MAX) {
+ error("Invalid count: %s\n", param.count);
+ return -EINVAL;
+ }
+ }
+
+ /* For inject or clear, an block and count are required */
+ if (ictx.op_mask & ((1 << OP_INJECT) | (1 << OP_CLEAR))) {
+ if (!param.block || !param.count) {
+ error("block and count required for inject/uninject\n");
+ return -EINVAL;
+ }
+ }
+
+ if (param.human)
+ ictx.flags |= UTIL_JSON_HUMAN;
+
+ return 0;
+}
+
+static int ns_errors_to_json(struct ndctl_namespace *ndns,
+ unsigned int start_count)
+{
+ unsigned long flags = ictx.flags | UTIL_JSON_MEDIA_ERRORS;
+ struct ndctl_bus *bus = ndctl_namespace_get_bus(ndns);
+ struct json_object *jndns;
+ unsigned int count;
+ int rc, tmo = 30;
+
+ /* only wait for scrubs for the inject and notify case */
+ if ((ictx.op_mask & (1 << OP_INJECT)) && ictx.notify) {
+ do {
+ /* wait for a scrub to start */
+ count = ndctl_bus_get_scrub_count(bus);
+ if (count == UINT_MAX) {
+ fprintf(stderr, "Unable to get scrub count\n");
+ return -ENXIO;
+ }
+ sleep(1);
+ } while (count <= start_count && --tmo > 0);
+
+ rc = ndctl_bus_wait_for_scrub_completion(bus);
+ if (rc) {
+ fprintf(stderr, "Error waiting for scrub\n");
+ return rc;
+ }
+ }
+
+ jndns = util_namespace_to_json(ndns, flags);
+ if (jndns)
+ printf("%s\n", json_object_to_json_string_ext(jndns,
+ JSON_C_TO_STRING_PRETTY));
+ return 0;
+}
+
+static int inject_error(struct ndctl_namespace *ndns, u64 offset, u64 length,
+ bool notify)
+{
+ struct ndctl_bus *bus = ndctl_namespace_get_bus(ndns);
+ unsigned int scrub_count;
+ int rc;
+
+ scrub_count = ndctl_bus_get_scrub_count(bus);
+ if (scrub_count == UINT_MAX) {
+ fprintf(stderr, "Unable to get scrub count\n");
+ return -ENXIO;
+ }
+
+ rc = ndctl_namespace_inject_error(ndns, offset, length, notify);
+ if (rc) {
+ fprintf(stderr, "Unable to inject error: %d\n", rc);
+ return rc;
+ }
+
+ return ns_errors_to_json(ndns, scrub_count);
+}
+
+static int uninject_error(struct ndctl_namespace *ndns, u64 offset, u64 length)
+{
+ int rc;
+
+ rc = ndctl_namespace_uninject_error(ndns, offset, length);
+ if (rc) {
+ fprintf(stderr, "Unable to uninject error: %d\n", rc);
+ return rc;
+ }
+
+ printf("Warning: Un-injecting previously injected errors here will\n");
+ printf("not cause the kernel to 'forget' its badblock entries. Those\n");
+ printf("have to be cleared through the normal process of writing\n");
+ printf("the affected blocks\n\n");
+ return ns_errors_to_json(ndns, 0);
+}
+
+static int injection_status(struct ndctl_namespace *ndns)
+{
+ unsigned long long block, count, bbs = 0;
+ struct json_object *jbbs, *jbb, *jobj;
+ struct ndctl_bb *bb;
+ int rc;
+
+ rc = ndctl_namespace_injection_status(ndns);
+ if (rc) {
+ fprintf(stderr, "Unable to get injection status: %d\n", rc);
+ return rc;
+ }
+
+ jobj = json_object_new_object();
+ if (!jobj)
+ return -ENOMEM;
+ jbbs = json_object_new_array();
+ if (!jbbs) {
+ json_object_put(jobj);
+ return -ENOMEM;
+ }
+
+ ndctl_namespace_bb_foreach(ndns, bb) {
+ if (!bb)
+ break;
+
+ block = ndctl_bb_get_block(bb);
+ count = ndctl_bb_get_count(bb);
+ jbb = util_badblock_rec_to_json(block, count, ictx.flags);
+ if (!jbb)
+ break;
+ json_object_array_add(jbbs, jbb);
+ bbs++;
+ }
+
+ if (bbs) {
+ json_object_object_add(jobj, "badblocks", jbbs);
+ printf("%s\n", json_object_to_json_string_ext(jobj,
+ JSON_C_TO_STRING_PRETTY));
+ }
+
+ json_object_put(jbbs);
+ json_object_put(jobj);
+
+ return rc;
+}
+
+static int err_inject_ns(struct ndctl_namespace *ndns)
+{
+ unsigned int op_mask;
+ int rc;
+
+ op_mask = ictx.op_mask;
+ while (op_mask) {
+ if (op_mask & (1 << OP_INJECT)) {
+ rc = inject_error(ndns, ictx.block, ictx.count,
+ ictx.notify);
+ if (rc)
+ return rc;
+ op_mask &= ~(1 << OP_INJECT);
+ }
+ if (op_mask & (1 << OP_CLEAR)) {
+ rc = uninject_error(ndns, ictx.block, ictx.count);
+ if (rc)
+ return rc;
+ op_mask &= ~(1 << OP_CLEAR);
+ }
+ if (op_mask & (1 << OP_STATUS)) {
+ rc = injection_status(ndns);
+ if (rc)
+ return rc;
+ op_mask &= ~(1 << OP_STATUS);
+ }
+ }
+
+ return rc;
+}
+
+static int do_inject(const char *namespace, struct ndctl_ctx *ctx)
+{
+ struct ndctl_namespace *ndns;
+ struct ndctl_region *region;
+ const char *ndns_name;
+ struct ndctl_bus *bus;
+ int rc = -ENXIO;
+
+ if (namespace == NULL)
+ return rc;
+
+ if (verbose)
+ ndctl_set_log_priority(ctx, LOG_DEBUG);
+
+ ndctl_bus_foreach(ctx, bus) {
+ if (!util_bus_filter(bus, param.bus))
+ continue;
+
+ ndctl_region_foreach(bus, region) {
+ if (!util_region_filter(region, param.region))
+ continue;
+
+ ndctl_namespace_foreach(region, ndns) {
+ ndns_name = ndctl_namespace_get_devname(ndns);
+
+ if (strcmp(namespace, ndns_name) != 0)
+ continue;
+
+ if (!ndctl_bus_has_error_injection(bus)) {
+ fprintf(stderr,
+ "%s: error injection not supported\n",
+ ndns_name);
+ return -EOPNOTSUPP;
+ }
+ return err_inject_ns(ndns);
+ }
+ }
+ }
+
+ return 0;
+}
+
+int cmd_inject_error(int argc, const char **argv, void *ctx)
+{
+ const char * const u[] = {
+ "ndctl inject-error <namespace> [<options>]",
+ NULL
+ };
+ int i, rc;
+
+ argc = parse_options(argc, argv, inject_options, u, 0);
+ rc = inject_init();
+ if (rc)
+ return rc;
+
+ if (argc == 0)
+ error("specify a namespace to inject error to\n");
+ for (i = 1; i < argc; i++)
+ error("unknown extra parameter \"%s\"\n", argv[i]);
+ if (argc == 0 || argc > 1) {
+ usage_with_options(u, inject_options);
+ return -ENODEV; /* we won't return from usage_with_options() */
+ }
+
+ return do_inject(argv[0], ctx);
+}
@@ -33,6 +33,14 @@ enum {
/* error number of Translate SPA by firmware */
#define ND_TRANSLATE_SPA_STATUS_INVALID_SPA 2
+/* status definitions for error injection */
+#define ND_ARS_ERR_INJ_STATUS_NOT_SUPP 1
+#define ND_ARS_ERR_INJ_STATUS_INVALID_PARAM 2
+
+enum err_inj_options {
+ ND_ARS_ERR_INJ_OPT_NOTIFY = 0,
+};
+
/*
* The following structures are command packages which are
* defined by ACPI 6.2 (or later).
@@ -83,6 +83,7 @@ static struct cmd_struct commands[] = {
{ "write-labels", cmd_write_labels },
{ "init-labels", cmd_init_labels },
{ "check-labels", cmd_check_labels },
+ { "inject-error", cmd_inject_error },
{ "list", cmd_list },
{ "help", cmd_help },
#ifdef ENABLE_TEST
@@ -20,6 +20,7 @@
#include <ndctl/libndctl.h>
#include <daxctl/libdaxctl.h>
#include <ccan/array_size/array_size.h>
+#include <ccan/short_types/short_types.h>
#ifdef HAVE_NDCTL_H
#include <linux/ndctl.h>
@@ -845,3 +846,28 @@ struct json_object *util_mapping_to_json(struct ndctl_mapping *mapping,
json_object_put(jmapping);
return NULL;
}
+
+struct json_object *util_badblock_rec_to_json(u64 block, u64 count,
+ unsigned long flags)
+{
+ struct json_object *jerr = json_object_new_object();
+ struct json_object *jobj;
+
+ if (!jerr)
+ return NULL;
+
+ jobj = util_json_object_hex(block, flags);
+ if (!jobj)
+ goto err;
+ json_object_object_add(jerr, "block", jobj);
+
+ jobj = util_json_object_hex(count, flags);
+ if (!jobj)
+ goto err;
+ json_object_object_add(jerr, "count", jobj);
+
+ return jerr;
+ err:
+ json_object_put(jerr);
+ return NULL;
+}
@@ -15,6 +15,7 @@
#include <stdio.h>
#include <stdbool.h>
#include <ndctl/libndctl.h>
+#include <ccan/short_types/short_types.h>
enum util_json_flags {
UTIL_JSON_IDLE = (1 << 0),
@@ -33,6 +34,8 @@ struct json_object *util_mapping_to_json(struct ndctl_mapping *mapping,
unsigned long flags);
struct json_object *util_namespace_to_json(struct ndctl_namespace *ndns,
unsigned long flags);
+struct json_object *util_badblock_rec_to_json(u64 block, u64 count,
+ unsigned long flags);
struct daxctl_region;
struct daxctl_dev;
struct json_object *util_region_badblocks_to_json(struct ndctl_region *region,
new file mode 100644
@@ -0,0 +1,50 @@
+/*
+ * Copyright(c) 2015-2017 Intel Corporation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of version 2 of the GNU General Public License as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ */
+#ifndef _NDCTL_LIST_H_
+#define _NDCTL_LIST_H_
+
+#include <ccan/list/list.h>
+
+/**
+ * list_add_after - add an entry after the given node in the linked list.
+ * @h: the list_head to add the node to
+ * @l: the list_node after which to add to
+ * @n: the list_node to add to the list.
+ *
+ * The list_node does not need to be initialized; it will be overwritten.
+ * Example:
+ * struct child *child = malloc(sizeof(*child));
+ *
+ * child->name = "geoffrey";
+ * list_add_after(&parent->children, &child1->list, &child->list);
+ * parent->num_children++;
+ */
+#define list_add_after(h, l, n) list_add_after_(h, l, n, LIST_LOC)
+static inline void list_add_after_(struct list_head *h,
+ struct list_node *l,
+ struct list_node *n,
+ const char *abortstr)
+{
+ if (l->next == &h->n) {
+ /* l is the last element, this becomes a list_add_tail */
+ list_add_tail(h, n);
+ return;
+ }
+ n->next = l->next;
+ n->prev = l;
+ l->next->prev = n;
+ l->next = n;
+ (void)list_debug(h, abortstr);
+}
+
+#endif /* _NDCTL_LIST_H_ */
@@ -28,6 +28,7 @@ unsigned long long parse_size64(const char *str);
unsigned long long __parse_size64(const char *str, unsigned long long *units);
#define ALIGN(x, a) ((((unsigned long long) x) + (a - 1)) & ~(a - 1))
+#define ALIGN_DOWN(x, a) (((((unsigned long long) x) + a) & ~(a - 1)) - a)
#define BITS_PER_LONG (sizeof(unsigned long) * 8)
#define HPAGE_SIZE (2 << 20)
Add an inject-error command to ndctl. This uses the error injection DSMs in ACPI6.2 to provide a generic error injection and management interface. Once can inject errors, and view as well as clear injected errors using these commands. Cc: Dan Williams <dan.j.williams@intel.com> Signed-off-by: Vishal Verma <vishal.l.verma@intel.com> --- Documentation/ndctl/Makefile.am | 1 + Documentation/ndctl/ndctl-inject-error.txt | 108 +++++++++ Documentation/ndctl/ndctl.txt | 1 + builtin.h | 1 + contrib/ndctl | 5 +- ndctl/Makefile.am | 3 +- ndctl/inject-error.c | 373 +++++++++++++++++++++++++++++ ndctl/libndctl-nfit.h | 8 + ndctl/ndctl.c | 1 + util/json.c | 26 ++ util/json.h | 3 + util/list.h | 50 ++++ util/size.h | 1 + 13 files changed, 579 insertions(+), 2 deletions(-) create mode 100644 Documentation/ndctl/ndctl-inject-error.txt create mode 100644 ndctl/inject-error.c create mode 100644 util/list.h