Update Linux to v5.4.2
Change-Id: Idf6911045d9d382da2cfe01b1edff026404ac8fd
diff --git a/drivers/ras/Kconfig b/drivers/ras/Kconfig
index 4c3c67d..c2a236f 100644
--- a/drivers/ras/Kconfig
+++ b/drivers/ras/Kconfig
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
menuconfig RAS
bool "Reliability, Availability and Serviceability (RAS) features"
help
@@ -30,6 +31,6 @@
if RAS
-source arch/x86/ras/Kconfig
+source "arch/x86/ras/Kconfig"
endif
diff --git a/drivers/ras/Makefile b/drivers/ras/Makefile
index 7b26dd3..6f0404f 100644
--- a/drivers/ras/Makefile
+++ b/drivers/ras/Makefile
@@ -1,2 +1,4 @@
-obj-$(CONFIG_RAS) += ras.o debugfs.o
+# SPDX-License-Identifier: GPL-2.0-only
+obj-$(CONFIG_RAS) += ras.o
+obj-$(CONFIG_DEBUG_FS) += debugfs.o
obj-$(CONFIG_RAS_CEC) += cec.o
diff --git a/drivers/ras/cec.c b/drivers/ras/cec.c
index 2d9ec37..c09cf55 100644
--- a/drivers/ras/cec.c
+++ b/drivers/ras/cec.c
@@ -1,7 +1,12 @@
// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2017-2019 Borislav Petkov, SUSE Labs.
+ */
#include <linux/mm.h>
#include <linux/gfp.h>
+#include <linux/ras.h>
#include <linux/kernel.h>
+#include <linux/workqueue.h>
#include <asm/mce.h>
@@ -36,9 +41,9 @@
* thus emulate an an LRU-like behavior when deleting elements to free up space
* in the page.
*
- * When an element reaches it's max count of count_threshold, we try to poison
- * it by assuming that errors triggered count_threshold times in a single page
- * are excessive and that page shouldn't be used anymore. count_threshold is
+ * When an element reaches it's max count of action_threshold, we try to poison
+ * it by assuming that errors triggered action_threshold times in a single page
+ * are excessive and that page shouldn't be used anymore. action_threshold is
* initialized to COUNT_MASK which is the maximum.
*
* That error event entry causes cec_add_elem() to return !0 value and thus
@@ -121,18 +126,14 @@
static u64 dfs_pfn;
/* Amount of errors after which we offline */
-static unsigned int count_threshold = COUNT_MASK;
+static u64 action_threshold = COUNT_MASK;
-/*
- * The timer "decays" element count each timer_interval which is 24hrs by
- * default.
- */
-
-#define CEC_TIMER_DEFAULT_INTERVAL 24 * 60 * 60 /* 24 hrs */
-#define CEC_TIMER_MIN_INTERVAL 1 * 60 * 60 /* 1h */
-#define CEC_TIMER_MAX_INTERVAL 30 * 24 * 60 * 60 /* one month */
-static struct timer_list cec_timer;
-static u64 timer_interval = CEC_TIMER_DEFAULT_INTERVAL;
+/* Each element "decays" each decay_interval which is 24hrs by default. */
+#define CEC_DECAY_DEFAULT_INTERVAL 24 * 60 * 60 /* 24 hrs */
+#define CEC_DECAY_MIN_INTERVAL 1 * 60 * 60 /* 1h */
+#define CEC_DECAY_MAX_INTERVAL 30 * 24 * 60 * 60 /* one month */
+static struct delayed_work cec_work;
+static u64 decay_interval = CEC_DECAY_DEFAULT_INTERVAL;
/*
* Decrement decay value. We're using DECAY_BITS bits to denote decay of an
@@ -160,20 +161,21 @@
/*
* @interval in seconds
*/
-static void cec_mod_timer(struct timer_list *t, unsigned long interval)
+static void cec_mod_work(unsigned long interval)
{
unsigned long iv;
- iv = interval * HZ + jiffies;
-
- mod_timer(t, round_jiffies(iv));
+ iv = interval * HZ;
+ mod_delayed_work(system_wq, &cec_work, round_jiffies(iv));
}
-static void cec_timer_fn(struct timer_list *unused)
+static void cec_work_fn(struct work_struct *work)
{
+ mutex_lock(&ce_mutex);
do_spring_cleaning(&ce_arr);
+ mutex_unlock(&ce_mutex);
- cec_mod_timer(&cec_timer, timer_interval);
+ cec_mod_work(decay_interval);
}
/*
@@ -183,32 +185,38 @@
*/
static int __find_elem(struct ce_array *ca, u64 pfn, unsigned int *to)
{
+ int min = 0, max = ca->n - 1;
u64 this_pfn;
- int min = 0, max = ca->n;
- while (min < max) {
- int tmp = (max + min) >> 1;
+ while (min <= max) {
+ int i = (min + max) >> 1;
- this_pfn = PFN(ca->array[tmp]);
+ this_pfn = PFN(ca->array[i]);
if (this_pfn < pfn)
- min = tmp + 1;
+ min = i + 1;
else if (this_pfn > pfn)
- max = tmp;
- else {
- min = tmp;
- break;
+ max = i - 1;
+ else if (this_pfn == pfn) {
+ if (to)
+ *to = i;
+
+ return i;
}
}
+ /*
+ * When the loop terminates without finding @pfn, min has the index of
+ * the element slot where the new @pfn should be inserted. The loop
+ * terminates when min > max, which means the min index points to the
+ * bigger element while the max index to the smaller element, in-between
+ * which the new @pfn belongs to.
+ *
+ * For more details, see exercise 1, Section 6.2.1 in TAOCP, vol. 3.
+ */
if (to)
*to = min;
- this_pfn = PFN(ca->array[min]);
-
- if (this_pfn == pfn)
- return min;
-
return -ENOKEY;
}
@@ -272,11 +280,39 @@
return pfn;
}
+static bool sanity_check(struct ce_array *ca)
+{
+ bool ret = false;
+ u64 prev = 0;
+ int i;
+
+ for (i = 0; i < ca->n; i++) {
+ u64 this = PFN(ca->array[i]);
+
+ if (WARN(prev > this, "prev: 0x%016llx <-> this: 0x%016llx\n", prev, this))
+ ret = true;
+
+ prev = this;
+ }
+
+ if (!ret)
+ return ret;
+
+ pr_info("Sanity check dump:\n{ n: %d\n", ca->n);
+ for (i = 0; i < ca->n; i++) {
+ u64 this = PFN(ca->array[i]);
+
+ pr_info(" %03d: [%016llx|%03llx]\n", i, this, FULL_COUNT(ca->array[i]));
+ }
+ pr_info("}\n");
+
+ return ret;
+}
int cec_add_elem(u64 pfn)
{
struct ce_array *ca = &ce_arr;
- unsigned int to;
+ unsigned int to = 0;
int count, ret = 0;
/*
@@ -286,10 +322,11 @@
if (!ce_arr.array || ce_arr.disabled)
return -ENODEV;
- ca->ces_entered++;
-
mutex_lock(&ce_mutex);
+ ca->ces_entered++;
+
+ /* Array full, free the LRU slot. */
if (ca->n == MAX_ELEMS)
WARN_ON(!del_lru_elem_unlocked(ca));
@@ -302,24 +339,17 @@
(void *)&ca->array[to],
(ca->n - to) * sizeof(u64));
- ca->array[to] = (pfn << PAGE_SHIFT) |
- (DECAY_MASK << COUNT_BITS) | 1;
-
+ ca->array[to] = pfn << PAGE_SHIFT;
ca->n++;
-
- ret = 0;
-
- goto decay;
}
+ /* Add/refresh element generation and increment count */
+ ca->array[to] |= DECAY_MASK << COUNT_BITS;
+ ca->array[to]++;
+
+ /* Check action threshold and soft-offline, if reached. */
count = COUNT(ca->array[to]);
-
- if (count < count_threshold) {
- ca->array[to] |= (DECAY_MASK << COUNT_BITS);
- ca->array[to]++;
-
- ret = 0;
- } else {
+ if (count >= action_threshold) {
u64 pfn = ca->array[to] >> PAGE_SHIFT;
if (!pfn_valid(pfn)) {
@@ -334,20 +364,21 @@
del_elem(ca, to);
/*
- * Return a >0 value to denote that we've reached the offlining
- * threshold.
+ * Return a >0 value to callers, to denote that we've reached
+ * the offlining threshold.
*/
ret = 1;
goto unlock;
}
-decay:
ca->decay_count++;
if (ca->decay_count >= CLEAN_ELEMS)
do_spring_cleaning(ca);
+ WARN_ON_ONCE(sanity_check(ca));
+
unlock:
mutex_unlock(&ce_mutex);
@@ -365,45 +396,48 @@
{
*(u64 *)data = val;
- return cec_add_elem(val);
+ cec_add_elem(val);
+
+ return 0;
}
DEFINE_DEBUGFS_ATTRIBUTE(pfn_ops, u64_get, pfn_set, "0x%llx\n");
static int decay_interval_set(void *data, u64 val)
{
- *(u64 *)data = val;
-
- if (val < CEC_TIMER_MIN_INTERVAL)
+ if (val < CEC_DECAY_MIN_INTERVAL)
return -EINVAL;
- if (val > CEC_TIMER_MAX_INTERVAL)
+ if (val > CEC_DECAY_MAX_INTERVAL)
return -EINVAL;
- timer_interval = val;
+ *(u64 *)data = val;
+ decay_interval = val;
- cec_mod_timer(&cec_timer, timer_interval);
+ cec_mod_work(decay_interval);
+
return 0;
}
DEFINE_DEBUGFS_ATTRIBUTE(decay_interval_ops, u64_get, decay_interval_set, "%lld\n");
-static int count_threshold_set(void *data, u64 val)
+static int action_threshold_set(void *data, u64 val)
{
*(u64 *)data = val;
if (val > COUNT_MASK)
val = COUNT_MASK;
- count_threshold = val;
+ action_threshold = val;
return 0;
}
-DEFINE_DEBUGFS_ATTRIBUTE(count_threshold_ops, u64_get, count_threshold_set, "%lld\n");
+DEFINE_DEBUGFS_ATTRIBUTE(action_threshold_ops, u64_get, action_threshold_set, "%lld\n");
+
+static const char * const bins[] = { "00", "01", "10", "11" };
static int array_dump(struct seq_file *m, void *v)
{
struct ce_array *ca = &ce_arr;
- u64 prev = 0;
int i;
mutex_lock(&ce_mutex);
@@ -412,11 +446,8 @@
for (i = 0; i < ca->n; i++) {
u64 this = PFN(ca->array[i]);
- seq_printf(m, " %03d: [%016llx|%03llx]\n", i, this, FULL_COUNT(ca->array[i]));
-
- WARN_ON(prev > this);
-
- prev = this;
+ seq_printf(m, " %3d: [%016llx|%s|%03llx]\n",
+ i, this, bins[DECAY(ca->array[i])], COUNT(ca->array[i]));
}
seq_printf(m, "}\n");
@@ -426,10 +457,10 @@
seq_printf(m, "Flags: 0x%x\n", ca->flags);
- seq_printf(m, "Timer interval: %lld seconds\n", timer_interval);
+ seq_printf(m, "Decay interval: %lld seconds\n", decay_interval);
seq_printf(m, "Decays: %lld\n", ca->decays_done);
- seq_printf(m, "Action threshold: %d\n", count_threshold);
+ seq_printf(m, "Action threshold: %lld\n", action_threshold);
mutex_unlock(&ce_mutex);
@@ -459,6 +490,23 @@
return -1;
}
+ decay = debugfs_create_file("decay_interval", S_IRUSR | S_IWUSR, d,
+ &decay_interval, &decay_interval_ops);
+ if (!decay) {
+ pr_warn("Error creating decay_interval debugfs node!\n");
+ goto err;
+ }
+
+ count = debugfs_create_file("action_threshold", S_IRUSR | S_IWUSR, d,
+ &action_threshold, &action_threshold_ops);
+ if (!count) {
+ pr_warn("Error creating action_threshold debugfs node!\n");
+ goto err;
+ }
+
+ if (!IS_ENABLED(CONFIG_RAS_CEC_DEBUG))
+ return 0;
+
pfn = debugfs_create_file("pfn", S_IRUSR | S_IWUSR, d, &dfs_pfn, &pfn_ops);
if (!pfn) {
pr_warn("Error creating pfn debugfs node!\n");
@@ -471,21 +519,6 @@
goto err;
}
- decay = debugfs_create_file("decay_interval", S_IRUSR | S_IWUSR, d,
- &timer_interval, &decay_interval_ops);
- if (!decay) {
- pr_warn("Error creating decay_interval debugfs node!\n");
- goto err;
- }
-
- count = debugfs_create_file("count_threshold", S_IRUSR | S_IWUSR, d,
- &count_threshold, &count_threshold_ops);
- if (!count) {
- pr_warn("Error creating count_threshold debugfs node!\n");
- goto err;
- }
-
-
return 0;
err:
@@ -505,11 +538,13 @@
return;
}
- if (create_debugfs_nodes())
+ if (create_debugfs_nodes()) {
+ free_page((unsigned long)ce_arr.array);
return;
+ }
- timer_setup(&cec_timer, cec_timer_fn, 0);
- cec_mod_timer(&cec_timer, CEC_TIMER_DEFAULT_INTERVAL);
+ INIT_DELAYED_WORK(&cec_work, cec_work_fn);
+ schedule_delayed_work(&cec_work, CEC_DECAY_DEFAULT_INTERVAL);
pr_info("Correctable Errors collector initialized.\n");
}
diff --git a/drivers/ras/debugfs.c b/drivers/ras/debugfs.c
index 5016030..0d4f985 100644
--- a/drivers/ras/debugfs.c
+++ b/drivers/ras/debugfs.c
@@ -1,4 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0-only
#include <linux/debugfs.h>
+#include <linux/ras.h>
+#include "debugfs.h"
struct dentry *ras_debugfs_dir;
diff --git a/drivers/ras/ras.c b/drivers/ras/ras.c
index 3f38907..95540ea 100644
--- a/drivers/ras/ras.c
+++ b/drivers/ras/ras.c
@@ -14,7 +14,7 @@
#define TRACE_INCLUDE_PATH ../../include/ras
#include <ras/ras_event.h>
-void log_non_standard_event(const uuid_le *sec_type, const uuid_le *fru_id,
+void log_non_standard_event(const guid_t *sec_type, const guid_t *fru_id,
const char *fru_text, const u8 sev, const u8 *err,
const u32 len)
{