mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-09-12 13:55:32 +00:00
![David Hildenbrand](/assets/img/avatar_default.png)
test_pages_in_a_zone() is just another nasty PFN walker that can easily stumble over ZONE_DEVICE memory ranges falling into the same memory block as ordinary system RAM: the memmap of parts of these ranges might possibly be uninitialized. In fact, we observed (on an older kernel) with UBSAN: UBSAN: Undefined behaviour in ./include/linux/mm.h:1133:50 index 7 is out of range for type 'zone [5]' CPU: 121 PID: 35603 Comm: read_all Kdump: loaded Tainted: [...] Hardware name: Dell Inc. PowerEdge R7425/08V001, BIOS 1.12.2 11/15/2019 Call Trace: dump_stack+0x9a/0xf0 ubsan_epilogue+0x9/0x7a __ubsan_handle_out_of_bounds+0x13a/0x181 test_pages_in_a_zone+0x3c4/0x500 show_valid_zones+0x1fa/0x380 dev_attr_show+0x43/0xb0 sysfs_kf_seq_show+0x1c5/0x440 seq_read+0x49d/0x1190 vfs_read+0xff/0x300 ksys_read+0xb8/0x170 do_syscall_64+0xa5/0x4b0 entry_SYSCALL_64_after_hwframe+0x6a/0xdf RIP: 0033:0x7f01f4439b52 We seem to stumble over a memmap that contains a garbage zone id. While we could try inserting pfn_to_online_page() calls, it will just make memory offlining slower, because we use test_pages_in_a_zone() to make sure we're offlining pages that all belong to the same zone. Let's just get rid of this PFN walker and determine the single zone of a memory block -- if any -- for early memory blocks during boot. For memory onlining, we know the single zone already. Let's avoid any additional memmap scanning and just rely on the zone information available during boot. For memory hot(un)plug, we only really care about memory blocks that: * span a single zone (and, thereby, a single node) * are completely System RAM (IOW, no holes, no ZONE_DEVICE) If one of these conditions is not met, we reject memory offlining. Hotplugged memory blocks (starting out offline), always meet both conditions. There are three scenarios to handle: (1) Memory hot(un)plug A memory block with zone == NULL cannot be offlined, corresponding to our previous test_pages_in_a_zone() check. After successful memory onlining/offlining, we simply set the zone accordingly. * Memory onlining: set the zone we just used for onlining * Memory offlining: set zone = NULL So a hotplugged memory block starts with zone = NULL. Once memory onlining is done, we set the proper zone. (2) Boot memory with !CONFIG_NUMA We know that there is just a single pgdat, so we simply scan all zones of that pgdat for an intersection with our memory block PFN range when adding the memory block. If more than one zone intersects (e.g., DMA and DMA32 on x86 for the first memory block) we set zone = NULL and consequently mimic what test_pages_in_a_zone() used to do. (3) Boot memory with CONFIG_NUMA At the point in time we create the memory block devices during boot, we don't know yet which nodes *actually* span a memory block. While we could scan all zones of all nodes for intersections, overlapping nodes complicate the situation and scanning all nodes is possibly expensive. But that problem has already been solved by the code that sets the node of a memory block and creates the link in the sysfs -- do_register_memory_block_under_node(). So, we hook into the code that sets the node id for a memory block. If we already have a different node id set for the memory block, we know that multiple nodes *actually* have PFNs falling into our memory block: we set zone = NULL and consequently mimic what test_pages_in_a_zone() used to do. If there is no node id set, we do the same as (2) for the given node. Note that the call order in driver_init() is: -> memory_dev_init(): create memory block devices -> node_dev_init(): link memory block devices to the node and set the node id So in summary, we detect if there is a single zone responsible for this memory block and we consequently store the zone in that case in the memory block, updating it during memory onlining/offlining. Link: https://lkml.kernel.org/r/20220210184359.235565-3-david@redhat.com Signed-off-by: David Hildenbrand <david@redhat.com> Reported-by: Rafael Parra <rparrazo@redhat.com> Reviewed-by: Oscar Salvador <osalvador@suse.de> Cc: "Rafael J. Wysocki" <rafael@kernel.org> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Michal Hocko <mhocko@suse.com> Cc: Rafael Parra <rparrazo@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
184 lines
6.3 KiB
C
184 lines
6.3 KiB
C
/* SPDX-License-Identifier: GPL-2.0 */
|
|
/*
|
|
* include/linux/memory.h - generic memory definition
|
|
*
|
|
* This is mainly for topological representation. We define the
|
|
* basic "struct memory_block" here, which can be embedded in per-arch
|
|
* definitions or NUMA information.
|
|
*
|
|
* Basic handling of the devices is done in drivers/base/memory.c
|
|
* and system devices are handled in drivers/base/sys.c.
|
|
*
|
|
* Memory block are exported via sysfs in the class/memory/devices/
|
|
* directory.
|
|
*
|
|
*/
|
|
#ifndef _LINUX_MEMORY_H_
|
|
#define _LINUX_MEMORY_H_
|
|
|
|
#include <linux/node.h>
|
|
#include <linux/compiler.h>
|
|
#include <linux/mutex.h>
|
|
#include <linux/notifier.h>
|
|
|
|
#define MIN_MEMORY_BLOCK_SIZE (1UL << SECTION_SIZE_BITS)
|
|
|
|
/**
|
|
* struct memory_group - a logical group of memory blocks
|
|
* @nid: The node id for all memory blocks inside the memory group.
|
|
* @blocks: List of all memory blocks belonging to this memory group.
|
|
* @present_kernel_pages: Present (online) memory outside ZONE_MOVABLE of this
|
|
* memory group.
|
|
* @present_movable_pages: Present (online) memory in ZONE_MOVABLE of this
|
|
* memory group.
|
|
* @is_dynamic: The memory group type: static vs. dynamic
|
|
* @s.max_pages: Valid with &memory_group.is_dynamic == false. The maximum
|
|
* number of pages we'll have in this static memory group.
|
|
* @d.unit_pages: Valid with &memory_group.is_dynamic == true. Unit in pages
|
|
* in which memory is added/removed in this dynamic memory group.
|
|
* This granularity defines the alignment of a unit in physical
|
|
* address space; it has to be at least as big as a single
|
|
* memory block.
|
|
*
|
|
* A memory group logically groups memory blocks; each memory block
|
|
* belongs to at most one memory group. A memory group corresponds to
|
|
* a memory device, such as a DIMM or a NUMA node, which spans multiple
|
|
* memory blocks and might even span multiple non-contiguous physical memory
|
|
* ranges.
|
|
*
|
|
* Modification of members after registration is serialized by memory
|
|
* hot(un)plug code.
|
|
*/
|
|
struct memory_group {
|
|
int nid;
|
|
struct list_head memory_blocks;
|
|
unsigned long present_kernel_pages;
|
|
unsigned long present_movable_pages;
|
|
bool is_dynamic;
|
|
union {
|
|
struct {
|
|
unsigned long max_pages;
|
|
} s;
|
|
struct {
|
|
unsigned long unit_pages;
|
|
} d;
|
|
};
|
|
};
|
|
|
|
struct memory_block {
|
|
unsigned long start_section_nr;
|
|
unsigned long state; /* serialized by the dev->lock */
|
|
int online_type; /* for passing data to online routine */
|
|
int nid; /* NID for this memory block */
|
|
/*
|
|
* The single zone of this memory block if all PFNs of this memory block
|
|
* that are System RAM (not a memory hole, not ZONE_DEVICE ranges) are
|
|
* managed by a single zone. NULL if multiple zones (including nodes)
|
|
* apply.
|
|
*/
|
|
struct zone *zone;
|
|
struct device dev;
|
|
/*
|
|
* Number of vmemmap pages. These pages
|
|
* lay at the beginning of the memory block.
|
|
*/
|
|
unsigned long nr_vmemmap_pages;
|
|
struct memory_group *group; /* group (if any) for this block */
|
|
struct list_head group_next; /* next block inside memory group */
|
|
};
|
|
|
|
int arch_get_memory_phys_device(unsigned long start_pfn);
|
|
unsigned long memory_block_size_bytes(void);
|
|
int set_memory_block_size_order(unsigned int order);
|
|
|
|
/* These states are exposed to userspace as text strings in sysfs */
|
|
#define MEM_ONLINE (1<<0) /* exposed to userspace */
|
|
#define MEM_GOING_OFFLINE (1<<1) /* exposed to userspace */
|
|
#define MEM_OFFLINE (1<<2) /* exposed to userspace */
|
|
#define MEM_GOING_ONLINE (1<<3)
|
|
#define MEM_CANCEL_ONLINE (1<<4)
|
|
#define MEM_CANCEL_OFFLINE (1<<5)
|
|
|
|
struct memory_notify {
|
|
unsigned long start_pfn;
|
|
unsigned long nr_pages;
|
|
int status_change_nid_normal;
|
|
int status_change_nid;
|
|
};
|
|
|
|
struct notifier_block;
|
|
struct mem_section;
|
|
|
|
/*
|
|
* Priorities for the hotplug memory callback routines (stored in decreasing
|
|
* order in the callback chain)
|
|
*/
|
|
#define SLAB_CALLBACK_PRI 1
|
|
#define IPC_CALLBACK_PRI 10
|
|
|
|
#ifndef CONFIG_MEMORY_HOTPLUG
|
|
static inline void memory_dev_init(void)
|
|
{
|
|
return;
|
|
}
|
|
static inline int register_memory_notifier(struct notifier_block *nb)
|
|
{
|
|
return 0;
|
|
}
|
|
static inline void unregister_memory_notifier(struct notifier_block *nb)
|
|
{
|
|
}
|
|
static inline int memory_notify(unsigned long val, void *v)
|
|
{
|
|
return 0;
|
|
}
|
|
static inline int hotplug_memory_notifier(notifier_fn_t fn, int pri)
|
|
{
|
|
return 0;
|
|
}
|
|
/* These aren't inline functions due to a GCC bug. */
|
|
#define register_hotmemory_notifier(nb) ({ (void)(nb); 0; })
|
|
#define unregister_hotmemory_notifier(nb) ({ (void)(nb); })
|
|
#else /* CONFIG_MEMORY_HOTPLUG */
|
|
extern int register_memory_notifier(struct notifier_block *nb);
|
|
extern void unregister_memory_notifier(struct notifier_block *nb);
|
|
int create_memory_block_devices(unsigned long start, unsigned long size,
|
|
unsigned long vmemmap_pages,
|
|
struct memory_group *group);
|
|
void remove_memory_block_devices(unsigned long start, unsigned long size);
|
|
extern void memory_dev_init(void);
|
|
extern int memory_notify(unsigned long val, void *v);
|
|
extern struct memory_block *find_memory_block(unsigned long section_nr);
|
|
typedef int (*walk_memory_blocks_func_t)(struct memory_block *, void *);
|
|
extern int walk_memory_blocks(unsigned long start, unsigned long size,
|
|
void *arg, walk_memory_blocks_func_t func);
|
|
extern int for_each_memory_block(void *arg, walk_memory_blocks_func_t func);
|
|
|
|
extern int memory_group_register_static(int nid, unsigned long max_pages);
|
|
extern int memory_group_register_dynamic(int nid, unsigned long unit_pages);
|
|
extern int memory_group_unregister(int mgid);
|
|
struct memory_group *memory_group_find_by_id(int mgid);
|
|
typedef int (*walk_memory_groups_func_t)(struct memory_group *, void *);
|
|
int walk_dynamic_memory_groups(int nid, walk_memory_groups_func_t func,
|
|
struct memory_group *excluded, void *arg);
|
|
#define hotplug_memory_notifier(fn, pri) ({ \
|
|
static __meminitdata struct notifier_block fn##_mem_nb =\
|
|
{ .notifier_call = fn, .priority = pri };\
|
|
register_memory_notifier(&fn##_mem_nb); \
|
|
})
|
|
#define register_hotmemory_notifier(nb) register_memory_notifier(nb)
|
|
#define unregister_hotmemory_notifier(nb) unregister_memory_notifier(nb)
|
|
|
|
#ifdef CONFIG_NUMA
|
|
void memory_block_add_nid(struct memory_block *mem, int nid,
|
|
enum meminit_context context);
|
|
#endif /* CONFIG_NUMA */
|
|
#endif /* CONFIG_MEMORY_HOTPLUG */
|
|
|
|
/*
|
|
* Kernel text modification mutex, used for code patching. Users of this lock
|
|
* can sleep.
|
|
*/
|
|
extern struct mutex text_mutex;
|
|
|
|
#endif /* _LINUX_MEMORY_H_ */
|