linux/drivers/ras/cec.c

// 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>

#include "debugfs.h"

/*
 * RAS Correctable Errors Collector
 *
 * This is a simple gadget which collects correctable errors and counts their
 * occurrence per physical page address.
 *
 * We've opted for possibly the simplest data structure to collect those - an
 * array of the size of a memory page. It stores 512 u64's with the following
 * structure:
 *
 * [63 ... PFN ... 12 | 11 ... generation ... 10 | 9 ... count ... 0]
 *
 * The generation in the two highest order bits is two bits which are set to 11b
 * on every insertion. During the course of each entry's existence, the
 * generation field gets decremented during spring cleaning to 10b, then 01b and
 * then 00b.
 *
 * This way we're employing the natural numeric ordering to make sure that newly
 * inserted/touched elements have higher 12-bit counts (which we've manufactured)
 * and thus iterating over the array initially won't kick out those elements
 * which were inserted last.
 *
 * Spring cleaning is what we do when we reach a certain number CLEAN_ELEMS of
 * elements entered into the array, during which, we're decaying all elements.
 * If, after decay, an element gets inserted again, its generation is set to 11b
 * to make sure it has higher numerical count than other, older elements and
 * thus emulate an LRU-like behavior when deleting elements to free up space
 * in the page.
 *
 * 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
 * signal to its callers to log the error.
 *
 * To the question why we've chosen a page and moving elements around with
 * memmove(), it is because it is a very simple structure to handle and max data
 * movement is 4K which on highly optimized modern CPUs is almost unnoticeable.
 * We wanted to avoid the pointer traversal of more complex structures like a
 * linked list or some sort of a balancing search tree.
 *
 * Deleting an element takes O(n) but since it is only a single page, it should
 * be fast enough and it shouldn't happen all too often depending on error
 * patterns.
 */

#undef pr_fmt
#define pr_fmt(fmt)

/*
 * We use DECAY_BITS bits of PAGE_SHIFT bits for counting decay, i.e., how long
 * elements have stayed in the array without having been accessed again.
 */
#define DECAY_BITS
#define DECAY_MASK
#define MAX_ELEMS

/*
 * Threshold amount of inserted elements after which we start spring
 * cleaning.
 */
#define CLEAN_ELEMS

/* Bits which count the number of errors happened in this 4K page. */
#define COUNT_BITS
#define COUNT_MASK
#define FULL_COUNT_MASK

/*
 * u64: [ 63 ... 12 | DECAY_BITS | COUNT_BITS ]
 */

#define PFN(e)
#define DECAY(e)
#define COUNT(e)
#define FULL_COUNT(e)

static struct ce_array {} ce_arr;

static DEFINE_MUTEX(ce_mutex);
static u64 dfs_pfn;

/* Amount of errors after which we offline */
static u64 action_threshold =;

/* Each element "decays" each decay_interval which is 24hrs by default. */
#define CEC_DECAY_DEFAULT_INTERVAL
#define CEC_DECAY_MIN_INTERVAL
#define CEC_DECAY_MAX_INTERVAL
static struct delayed_work cec_work;
static u64 decay_interval =;

/*
 * Decrement decay value. We're using DECAY_BITS bits to denote decay of an
 * element in the array. On insertion and any access, it gets reset to max.
 */
static void do_spring_cleaning(struct ce_array *ca)
{}

/*
 * @interval in seconds
 */
static void cec_mod_work(unsigned long interval)
{}

static void cec_work_fn(struct work_struct *work)
{}

/*
 * @to: index of the smallest element which is >= then @pfn.
 *
 * Return the index of the pfn if found, otherwise negative value.
 */
static int __find_elem(struct ce_array *ca, u64 pfn, unsigned int *to)
{}

static int find_elem(struct ce_array *ca, u64 pfn, unsigned int *to)
{}

static void del_elem(struct ce_array *ca, int idx)
{}

static u64 del_lru_elem_unlocked(struct ce_array *ca)
{}

/*
 * We return the 0th pfn in the error case under the assumption that it cannot
 * be poisoned and excessive CEs in there are a serious deal anyway.
 */
static u64 __maybe_unused del_lru_elem(void)
{}

static bool sanity_check(struct ce_array *ca)
{}

/**
 * cec_add_elem - Add an element to the CEC array.
 * @pfn:	page frame number to insert
 *
 * Return values:
 * - <0:	on error
 * -  0:	on success
 * - >0:	when the inserted pfn was offlined
 */
static int cec_add_elem(u64 pfn)
{}

static int u64_get(void *data, u64 *val)
{}

static int pfn_set(void *data, u64 val)
{}

DEFINE_DEBUGFS_ATTRIBUTE();

static int decay_interval_set(void *data, u64 val)
{}
DEFINE_DEBUGFS_ATTRIBUTE();

static int action_threshold_set(void *data, u64 val)
{}
DEFINE_DEBUGFS_ATTRIBUTE();

static const char * const bins[] =;

static int array_show(struct seq_file *m, void *v)
{}

DEFINE_SHOW_ATTRIBUTE();

static int __init create_debugfs_nodes(void)
{}

static int cec_notifier(struct notifier_block *nb, unsigned long val,
			void *data)
{}

static struct notifier_block cec_nb =;

static int __init cec_init(void)
{}
late_initcall(cec_init);

int __init parse_cec_param(char *str)
{}