linux-loongson/include/linux/memory-tiers.h
Li Zhijian cce3510313 mm/memory-tier: fix abstract distance calculation overflow
In mt_perf_to_adistance(), the calculation of abstract distance (adist)
involves multiplying several int values including
MEMTIER_ADISTANCE_DRAM.

*adist = MEMTIER_ADISTANCE_DRAM *
		(perf->read_latency + perf->write_latency) /
		(default_dram_perf.read_latency + default_dram_perf.write_latency) *
		(default_dram_perf.read_bandwidth + default_dram_perf.write_bandwidth) /
		(perf->read_bandwidth + perf->write_bandwidth);

Since these values can be large, the multiplication may exceed the
maximum value of an int (INT_MAX) and overflow (Our platform did),
leading to an incorrect adist.

User-visible impact:
The memory tiering subsystem will misinterpret slow memory (like CXL)
as faster than DRAM, causing inappropriate demotion of pages from
CXL (slow memory) to DRAM (fast memory).

For example, we will see the following demotion chains from the dmesg, where
Node0,1 are DRAM, and Node2,3 are CXL node:
 Demotion targets for Node 0: null
 Demotion targets for Node 1: null
 Demotion targets for Node 2: preferred: 0-1, fallback: 0-1
 Demotion targets for Node 3: preferred: 0-1, fallback: 0-1

Change MEMTIER_ADISTANCE_DRAM to be a long constant by writing it with
the 'L' suffix.  This prevents the overflow because the multiplication
will then be done in the long type which has a larger range.

Link: https://lkml.kernel.org/r/20250611023439.2845785-1-lizhijian@fujitsu.com
Link: https://lkml.kernel.org/r/20250610062751.2365436-1-lizhijian@fujitsu.com
Fixes: 3718c02dbd ("acpi, hmat: calculate abstract distance with HMAT")
Signed-off-by: Li Zhijian <lizhijian@fujitsu.com>
Reviewed-by: Huang Ying <ying.huang@linux.alibaba.com>
Acked-by: Balbir Singh <balbirs@nvidia.com>
Reviewed-by: Donet Tom <donettom@linux.ibm.com>
Reviewed-by: Oscar Salvador <osalvador@suse.de>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2025-07-09 22:42:06 -07:00

156 lines
3.9 KiB
C

/* SPDX-License-Identifier: GPL-2.0 */
#ifndef _LINUX_MEMORY_TIERS_H
#define _LINUX_MEMORY_TIERS_H
#include <linux/types.h>
#include <linux/nodemask.h>
#include <linux/kref.h>
#include <linux/mmzone.h>
#include <linux/notifier.h>
/*
* Each tier cover a abstrace distance chunk size of 128
*/
#define MEMTIER_CHUNK_BITS 7
#define MEMTIER_CHUNK_SIZE (1 << MEMTIER_CHUNK_BITS)
/*
* Smaller abstract distance values imply faster (higher) memory tiers. Offset
* the DRAM adistance so that we can accommodate devices with a slightly lower
* adistance value (slightly faster) than default DRAM adistance to be part of
* the same memory tier.
*/
#define MEMTIER_ADISTANCE_DRAM ((4L * MEMTIER_CHUNK_SIZE) + (MEMTIER_CHUNK_SIZE >> 1))
struct memory_tier;
struct memory_dev_type {
/* list of memory types that are part of same tier as this type */
struct list_head tier_sibling;
/* list of memory types that are managed by one driver */
struct list_head list;
/* abstract distance for this specific memory type */
int adistance;
/* Nodes of same abstract distance */
nodemask_t nodes;
struct kref kref;
};
struct access_coordinate;
#ifdef CONFIG_NUMA
extern bool numa_demotion_enabled;
extern struct memory_dev_type *default_dram_type;
extern nodemask_t default_dram_nodes;
struct memory_dev_type *alloc_memory_type(int adistance);
void put_memory_type(struct memory_dev_type *memtype);
void init_node_memory_type(int node, struct memory_dev_type *default_type);
void clear_node_memory_type(int node, struct memory_dev_type *memtype);
int register_mt_adistance_algorithm(struct notifier_block *nb);
int unregister_mt_adistance_algorithm(struct notifier_block *nb);
int mt_calc_adistance(int node, int *adist);
int mt_set_default_dram_perf(int nid, struct access_coordinate *perf,
const char *source);
int mt_perf_to_adistance(struct access_coordinate *perf, int *adist);
struct memory_dev_type *mt_find_alloc_memory_type(int adist,
struct list_head *memory_types);
void mt_put_memory_types(struct list_head *memory_types);
#ifdef CONFIG_MIGRATION
int next_demotion_node(int node);
void node_get_allowed_targets(pg_data_t *pgdat, nodemask_t *targets);
bool node_is_toptier(int node);
#else
static inline int next_demotion_node(int node)
{
return NUMA_NO_NODE;
}
static inline void node_get_allowed_targets(pg_data_t *pgdat, nodemask_t *targets)
{
*targets = NODE_MASK_NONE;
}
static inline bool node_is_toptier(int node)
{
return true;
}
#endif
#else
#define numa_demotion_enabled false
#define default_dram_type NULL
#define default_dram_nodes NODE_MASK_NONE
/*
* CONFIG_NUMA implementation returns non NULL error.
*/
static inline struct memory_dev_type *alloc_memory_type(int adistance)
{
return NULL;
}
static inline void put_memory_type(struct memory_dev_type *memtype)
{
}
static inline void init_node_memory_type(int node, struct memory_dev_type *default_type)
{
}
static inline void clear_node_memory_type(int node, struct memory_dev_type *memtype)
{
}
static inline int next_demotion_node(int node)
{
return NUMA_NO_NODE;
}
static inline void node_get_allowed_targets(pg_data_t *pgdat, nodemask_t *targets)
{
*targets = NODE_MASK_NONE;
}
static inline bool node_is_toptier(int node)
{
return true;
}
static inline int register_mt_adistance_algorithm(struct notifier_block *nb)
{
return 0;
}
static inline int unregister_mt_adistance_algorithm(struct notifier_block *nb)
{
return 0;
}
static inline int mt_calc_adistance(int node, int *adist)
{
return NOTIFY_DONE;
}
static inline int mt_set_default_dram_perf(int nid, struct access_coordinate *perf,
const char *source)
{
return -EIO;
}
static inline int mt_perf_to_adistance(struct access_coordinate *perf, int *adist)
{
return -EIO;
}
static inline struct memory_dev_type *mt_find_alloc_memory_type(int adist,
struct list_head *memory_types)
{
return NULL;
}
static inline void mt_put_memory_types(struct list_head *memory_types)
{
}
#endif /* CONFIG_NUMA */
#endif /* _LINUX_MEMORY_TIERS_H */