diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2021-09-08 22:55:35 +0300 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2021-09-08 22:55:35 +0300 |
commit | 2d338201d5311bcd79d42f66df4cecbcbc5f4f2c (patch) | |
tree | 75d87f65c31f4721ba6a5356d2a487af9e2961c3 /mm/memory_hotplug.c | |
parent | cc09ee80c3b18ae1a897a30a17fe710b2b2f620a (diff) | |
parent | b285437d1d929785a5bef3603da78d2cd5341893 (diff) | |
download | linux-2d338201d5311bcd79d42f66df4cecbcbc5f4f2c.tar.xz |
Merge branch 'akpm' (patches from Andrew)
Merge more updates from Andrew Morton:
"147 patches, based on 7d2a07b769330c34b4deabeed939325c77a7ec2f.
Subsystems affected by this patch series: mm (memory-hotplug, rmap,
ioremap, highmem, cleanups, secretmem, kfence, damon, and vmscan),
alpha, percpu, procfs, misc, core-kernel, MAINTAINERS, lib,
checkpatch, epoll, init, nilfs2, coredump, fork, pids, criu, kconfig,
selftests, ipc, and scripts"
* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (94 commits)
scripts: check_extable: fix typo in user error message
mm/workingset: correct kernel-doc notations
ipc: replace costly bailout check in sysvipc_find_ipc()
selftests/memfd: remove unused variable
Kconfig.debug: drop selecting non-existing HARDLOCKUP_DETECTOR_ARCH
configs: remove the obsolete CONFIG_INPUT_POLLDEV
prctl: allow to setup brk for et_dyn executables
pid: cleanup the stale comment mentioning pidmap_init().
kernel/fork.c: unexport get_{mm,task}_exe_file
coredump: fix memleak in dump_vma_snapshot()
fs/coredump.c: log if a core dump is aborted due to changed file permissions
nilfs2: use refcount_dec_and_lock() to fix potential UAF
nilfs2: fix memory leak in nilfs_sysfs_delete_snapshot_group
nilfs2: fix memory leak in nilfs_sysfs_create_snapshot_group
nilfs2: fix memory leak in nilfs_sysfs_delete_##name##_group
nilfs2: fix memory leak in nilfs_sysfs_create_##name##_group
nilfs2: fix NULL pointer in nilfs_##name##_attr_release
nilfs2: fix memory leak in nilfs_sysfs_create_device_group
trap: cleanup trap_init()
init: move usermodehelper_enable() to populate_rootfs()
...
Diffstat (limited to 'mm/memory_hotplug.c')
-rw-r--r-- | mm/memory_hotplug.c | 374 |
1 files changed, 341 insertions, 33 deletions
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 4c527a80b6c9..9fd0be32a281 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -52,6 +52,73 @@ module_param(memmap_on_memory, bool, 0444); MODULE_PARM_DESC(memmap_on_memory, "Enable memmap on memory for memory hotplug"); #endif +enum { + ONLINE_POLICY_CONTIG_ZONES = 0, + ONLINE_POLICY_AUTO_MOVABLE, +}; + +const char *online_policy_to_str[] = { + [ONLINE_POLICY_CONTIG_ZONES] = "contig-zones", + [ONLINE_POLICY_AUTO_MOVABLE] = "auto-movable", +}; + +static int set_online_policy(const char *val, const struct kernel_param *kp) +{ + int ret = sysfs_match_string(online_policy_to_str, val); + + if (ret < 0) + return ret; + *((int *)kp->arg) = ret; + return 0; +} + +static int get_online_policy(char *buffer, const struct kernel_param *kp) +{ + return sprintf(buffer, "%s\n", online_policy_to_str[*((int *)kp->arg)]); +} + +/* + * memory_hotplug.online_policy: configure online behavior when onlining without + * specifying a zone (MMOP_ONLINE) + * + * "contig-zones": keep zone contiguous + * "auto-movable": online memory to ZONE_MOVABLE if the configuration + * (auto_movable_ratio, auto_movable_numa_aware) allows for it + */ +static int online_policy __read_mostly = ONLINE_POLICY_CONTIG_ZONES; +static const struct kernel_param_ops online_policy_ops = { + .set = set_online_policy, + .get = get_online_policy, +}; +module_param_cb(online_policy, &online_policy_ops, &online_policy, 0644); +MODULE_PARM_DESC(online_policy, + "Set the online policy (\"contig-zones\", \"auto-movable\") " + "Default: \"contig-zones\""); + +/* + * memory_hotplug.auto_movable_ratio: specify maximum MOVABLE:KERNEL ratio + * + * The ratio represent an upper limit and the kernel might decide to not + * online some memory to ZONE_MOVABLE -- e.g., because hotplugged KERNEL memory + * doesn't allow for more MOVABLE memory. + */ +static unsigned int auto_movable_ratio __read_mostly = 301; +module_param(auto_movable_ratio, uint, 0644); +MODULE_PARM_DESC(auto_movable_ratio, + "Set the maximum ratio of MOVABLE:KERNEL memory in the system " + "in percent for \"auto-movable\" online policy. Default: 301"); + +/* + * memory_hotplug.auto_movable_numa_aware: consider numa node stats + */ +#ifdef CONFIG_NUMA +static bool auto_movable_numa_aware __read_mostly = true; +module_param(auto_movable_numa_aware, bool, 0644); +MODULE_PARM_DESC(auto_movable_numa_aware, + "Consider numa node stats in addition to global stats in " + "\"auto-movable\" online policy. Default: true"); +#endif /* CONFIG_NUMA */ + /* * online_page_callback contains pointer to current page onlining function. * Initially it is generic_online_page(). If it is required it could be @@ -410,15 +477,13 @@ void __ref remove_pfn_range_from_zone(struct zone *zone, sizeof(struct page) * cur_nr_pages); } -#ifdef CONFIG_ZONE_DEVICE /* * Zone shrinking code cannot properly deal with ZONE_DEVICE. So * we will not try to shrink the zones - which is okay as * set_zone_contiguous() cannot deal with ZONE_DEVICE either way. */ - if (zone_idx(zone) == ZONE_DEVICE) + if (zone_is_zone_device(zone)) return; -#endif clear_zone_contiguous(zone); @@ -663,6 +728,109 @@ void __ref move_pfn_range_to_zone(struct zone *zone, unsigned long start_pfn, set_zone_contiguous(zone); } +struct auto_movable_stats { + unsigned long kernel_early_pages; + unsigned long movable_pages; +}; + +static void auto_movable_stats_account_zone(struct auto_movable_stats *stats, + struct zone *zone) +{ + if (zone_idx(zone) == ZONE_MOVABLE) { + stats->movable_pages += zone->present_pages; + } else { + stats->kernel_early_pages += zone->present_early_pages; +#ifdef CONFIG_CMA + /* + * CMA pages (never on hotplugged memory) behave like + * ZONE_MOVABLE. + */ + stats->movable_pages += zone->cma_pages; + stats->kernel_early_pages -= zone->cma_pages; +#endif /* CONFIG_CMA */ + } +} +struct auto_movable_group_stats { + unsigned long movable_pages; + unsigned long req_kernel_early_pages; +}; + +static int auto_movable_stats_account_group(struct memory_group *group, + void *arg) +{ + const int ratio = READ_ONCE(auto_movable_ratio); + struct auto_movable_group_stats *stats = arg; + long pages; + + /* + * We don't support modifying the config while the auto-movable online + * policy is already enabled. Just avoid the division by zero below. + */ + if (!ratio) + return 0; + + /* + * Calculate how many early kernel pages this group requires to + * satisfy the configured zone ratio. + */ + pages = group->present_movable_pages * 100 / ratio; + pages -= group->present_kernel_pages; + + if (pages > 0) + stats->req_kernel_early_pages += pages; + stats->movable_pages += group->present_movable_pages; + return 0; +} + +static bool auto_movable_can_online_movable(int nid, struct memory_group *group, + unsigned long nr_pages) +{ + unsigned long kernel_early_pages, movable_pages; + struct auto_movable_group_stats group_stats = {}; + struct auto_movable_stats stats = {}; + pg_data_t *pgdat = NODE_DATA(nid); + struct zone *zone; + int i; + + /* Walk all relevant zones and collect MOVABLE vs. KERNEL stats. */ + if (nid == NUMA_NO_NODE) { + /* TODO: cache values */ + for_each_populated_zone(zone) + auto_movable_stats_account_zone(&stats, zone); + } else { + for (i = 0; i < MAX_NR_ZONES; i++) { + zone = pgdat->node_zones + i; + if (populated_zone(zone)) + auto_movable_stats_account_zone(&stats, zone); + } + } + + kernel_early_pages = stats.kernel_early_pages; + movable_pages = stats.movable_pages; + + /* + * Kernel memory inside dynamic memory group allows for more MOVABLE + * memory within the same group. Remove the effect of all but the + * current group from the stats. + */ + walk_dynamic_memory_groups(nid, auto_movable_stats_account_group, + group, &group_stats); + if (kernel_early_pages <= group_stats.req_kernel_early_pages) + return false; + kernel_early_pages -= group_stats.req_kernel_early_pages; + movable_pages -= group_stats.movable_pages; + + if (group && group->is_dynamic) + kernel_early_pages += group->present_kernel_pages; + + /* + * Test if we could online the given number of pages to ZONE_MOVABLE + * and still stay in the configured ratio. + */ + movable_pages += nr_pages; + return movable_pages <= (auto_movable_ratio * kernel_early_pages) / 100; +} + /* * Returns a default kernel memory zone for the given pfn range. * If no kernel zone covers this pfn range it will automatically go @@ -684,6 +852,117 @@ static struct zone *default_kernel_zone_for_pfn(int nid, unsigned long start_pfn return &pgdat->node_zones[ZONE_NORMAL]; } +/* + * Determine to which zone to online memory dynamically based on user + * configuration and system stats. We care about the following ratio: + * + * MOVABLE : KERNEL + * + * Whereby MOVABLE is memory in ZONE_MOVABLE and KERNEL is memory in + * one of the kernel zones. CMA pages inside one of the kernel zones really + * behaves like ZONE_MOVABLE, so we treat them accordingly. + * + * We don't allow for hotplugged memory in a KERNEL zone to increase the + * amount of MOVABLE memory we can have, so we end up with: + * + * MOVABLE : KERNEL_EARLY + * + * Whereby KERNEL_EARLY is memory in one of the kernel zones, available sinze + * boot. We base our calculation on KERNEL_EARLY internally, because: + * + * a) Hotplugged memory in one of the kernel zones can sometimes still get + * hotunplugged, especially when hot(un)plugging individual memory blocks. + * There is no coordination across memory devices, therefore "automatic" + * hotunplugging, as implemented in hypervisors, could result in zone + * imbalances. + * b) Early/boot memory in one of the kernel zones can usually not get + * hotunplugged again (e.g., no firmware interface to unplug, fragmented + * with unmovable allocations). While there are corner cases where it might + * still work, it is barely relevant in practice. + * + * Exceptions are dynamic memory groups, which allow for more MOVABLE + * memory within the same memory group -- because in that case, there is + * coordination within the single memory device managed by a single driver. + * + * We rely on "present pages" instead of "managed pages", as the latter is + * highly unreliable and dynamic in virtualized environments, and does not + * consider boot time allocations. For example, memory ballooning adjusts the + * managed pages when inflating/deflating the balloon, and balloon compaction + * can even migrate inflated pages between zones. + * + * Using "present pages" is better but some things to keep in mind are: + * + * a) Some memblock allocations, such as for the crashkernel area, are + * effectively unused by the kernel, yet they account to "present pages". + * Fortunately, these allocations are comparatively small in relevant setups + * (e.g., fraction of system memory). + * b) Some hotplugged memory blocks in virtualized environments, esecially + * hotplugged by virtio-mem, look like they are completely present, however, + * only parts of the memory block are actually currently usable. + * "present pages" is an upper limit that can get reached at runtime. As + * we base our calculations on KERNEL_EARLY, this is not an issue. + */ +static struct zone *auto_movable_zone_for_pfn(int nid, + struct memory_group *group, + unsigned long pfn, + unsigned long nr_pages) +{ + unsigned long online_pages = 0, max_pages, end_pfn; + struct page *page; + + if (!auto_movable_ratio) + goto kernel_zone; + + if (group && !group->is_dynamic) { + max_pages = group->s.max_pages; + online_pages = group->present_movable_pages; + + /* If anything is !MOVABLE online the rest !MOVABLE. */ + if (group->present_kernel_pages) + goto kernel_zone; + } else if (!group || group->d.unit_pages == nr_pages) { + max_pages = nr_pages; + } else { + max_pages = group->d.unit_pages; + /* + * Take a look at all online sections in the current unit. + * We can safely assume that all pages within a section belong + * to the same zone, because dynamic memory groups only deal + * with hotplugged memory. + */ + pfn = ALIGN_DOWN(pfn, group->d.unit_pages); + end_pfn = pfn + group->d.unit_pages; + for (; pfn < end_pfn; pfn += PAGES_PER_SECTION) { + page = pfn_to_online_page(pfn); + if (!page) + continue; + /* If anything is !MOVABLE online the rest !MOVABLE. */ + if (page_zonenum(page) != ZONE_MOVABLE) + goto kernel_zone; + online_pages += PAGES_PER_SECTION; + } + } + + /* + * Online MOVABLE if we could *currently* online all remaining parts + * MOVABLE. We expect to (add+) online them immediately next, so if + * nobody interferes, all will be MOVABLE if possible. + */ + nr_pages = max_pages - online_pages; + if (!auto_movable_can_online_movable(NUMA_NO_NODE, group, nr_pages)) + goto kernel_zone; + +#ifdef CONFIG_NUMA + if (auto_movable_numa_aware && + !auto_movable_can_online_movable(nid, group, nr_pages)) + goto kernel_zone; +#endif /* CONFIG_NUMA */ + + return &NODE_DATA(nid)->node_zones[ZONE_MOVABLE]; +kernel_zone: + return default_kernel_zone_for_pfn(nid, pfn, nr_pages); +} + static inline struct zone *default_zone_for_pfn(int nid, unsigned long start_pfn, unsigned long nr_pages) { @@ -708,7 +987,8 @@ static inline struct zone *default_zone_for_pfn(int nid, unsigned long start_pfn return movable_node_enabled ? movable_zone : kernel_zone; } -struct zone *zone_for_pfn_range(int online_type, int nid, unsigned start_pfn, +struct zone *zone_for_pfn_range(int online_type, int nid, + struct memory_group *group, unsigned long start_pfn, unsigned long nr_pages) { if (online_type == MMOP_ONLINE_KERNEL) @@ -717,6 +997,9 @@ struct zone *zone_for_pfn_range(int online_type, int nid, unsigned start_pfn, if (online_type == MMOP_ONLINE_MOVABLE) return &NODE_DATA(nid)->node_zones[ZONE_MOVABLE]; + if (online_policy == ONLINE_POLICY_AUTO_MOVABLE) + return auto_movable_zone_for_pfn(nid, group, start_pfn, nr_pages); + return default_zone_for_pfn(nid, start_pfn, nr_pages); } @@ -724,10 +1007,25 @@ struct zone *zone_for_pfn_range(int online_type, int nid, unsigned start_pfn, * This function should only be called by memory_block_{online,offline}, * and {online,offline}_pages. */ -void adjust_present_page_count(struct zone *zone, long nr_pages) +void adjust_present_page_count(struct page *page, struct memory_group *group, + long nr_pages) { + struct zone *zone = page_zone(page); + const bool movable = zone_idx(zone) == ZONE_MOVABLE; + + /* + * We only support onlining/offlining/adding/removing of complete + * memory blocks; therefore, either all is either early or hotplugged. + */ + if (early_section(__pfn_to_section(page_to_pfn(page)))) + zone->present_early_pages += nr_pages; zone->present_pages += nr_pages; zone->zone_pgdat->node_present_pages += nr_pages; + + if (group && movable) + group->present_movable_pages += nr_pages; + else if (group && !movable) + group->present_kernel_pages += nr_pages; } int mhp_init_memmap_on_memory(unsigned long pfn, unsigned long nr_pages, @@ -773,7 +1071,8 @@ void mhp_deinit_memmap_on_memory(unsigned long pfn, unsigned long nr_pages) kasan_remove_zero_shadow(__va(PFN_PHYS(pfn)), PFN_PHYS(nr_pages)); } -int __ref online_pages(unsigned long pfn, unsigned long nr_pages, struct zone *zone) +int __ref online_pages(unsigned long pfn, unsigned long nr_pages, + struct zone *zone, struct memory_group *group) { unsigned long flags; int need_zonelists_rebuild = 0; @@ -826,7 +1125,7 @@ int __ref online_pages(unsigned long pfn, unsigned long nr_pages, struct zone *z } online_pages_range(pfn, nr_pages); - adjust_present_page_count(zone, nr_pages); + adjust_present_page_count(pfn_to_page(pfn), group, nr_pages); node_states_set_node(nid, &arg); if (need_zonelists_rebuild) @@ -1059,6 +1358,7 @@ int __ref add_memory_resource(int nid, struct resource *res, mhp_t mhp_flags) { struct mhp_params params = { .pgprot = pgprot_mhp(PAGE_KERNEL) }; struct vmem_altmap mhp_altmap = {}; + struct memory_group *group = NULL; u64 start, size; bool new_node = false; int ret; @@ -1070,6 +1370,13 @@ int __ref add_memory_resource(int nid, struct resource *res, mhp_t mhp_flags) if (ret) return ret; + if (mhp_flags & MHP_NID_IS_MGID) { + group = memory_group_find_by_id(nid); + if (!group) + return -EINVAL; + nid = group->nid; + } + if (!node_possible(nid)) { WARN(1, "node %d was absent from the node_possible_map\n", nid); return -EINVAL; @@ -1104,9 +1411,10 @@ int __ref add_memory_resource(int nid, struct resource *res, mhp_t mhp_flags) goto error; /* create memory block devices after memory was added */ - ret = create_memory_block_devices(start, size, mhp_altmap.alloc); + ret = create_memory_block_devices(start, size, mhp_altmap.alloc, + group); if (ret) { - arch_remove_memory(nid, start, size, NULL); + arch_remove_memory(start, size, NULL); goto error; } @@ -1298,7 +1606,7 @@ struct zone *test_pages_in_a_zone(unsigned long start_pfn, unsigned long pfn, sec_end_pfn; struct zone *zone = NULL; struct page *page; - int i; + for (pfn = start_pfn, sec_end_pfn = SECTION_ALIGN_UP(start_pfn + 1); pfn < end_pfn; pfn = sec_end_pfn, sec_end_pfn += PAGES_PER_SECTION) { @@ -1307,17 +1615,10 @@ struct zone *test_pages_in_a_zone(unsigned long start_pfn, continue; for (; pfn < sec_end_pfn && pfn < end_pfn; pfn += MAX_ORDER_NR_PAGES) { - i = 0; - /* This is just a CONFIG_HOLES_IN_ZONE check.*/ - while ((i < MAX_ORDER_NR_PAGES) && - !pfn_valid_within(pfn + i)) - i++; - if (i == MAX_ORDER_NR_PAGES || pfn + i >= end_pfn) - continue; /* Check if we got outside of the zone */ - if (zone && !zone_spans_pfn(zone, pfn + i)) + if (zone && !zone_spans_pfn(zone, pfn)) return NULL; - page = pfn_to_page(pfn + i); + page = pfn_to_page(pfn); if (zone && page_zone(page) != zone) return NULL; zone = page_zone(page); @@ -1568,7 +1869,8 @@ static int count_system_ram_pages_cb(unsigned long start_pfn, return 0; } -int __ref offline_pages(unsigned long start_pfn, unsigned long nr_pages) +int __ref offline_pages(unsigned long start_pfn, unsigned long nr_pages, + struct memory_group *group) { const unsigned long end_pfn = start_pfn + nr_pages; unsigned long pfn, system_ram_pages = 0; @@ -1704,7 +2006,7 @@ int __ref offline_pages(unsigned long start_pfn, unsigned long nr_pages) /* removal success */ adjust_managed_page_count(pfn_to_page(start_pfn), -nr_pages); - adjust_present_page_count(zone, -nr_pages); + adjust_present_page_count(pfn_to_page(start_pfn), group, -nr_pages); /* reinitialise watermarks and update pcp limits */ init_per_zone_wmark_min(); @@ -1746,7 +2048,9 @@ failed_removal: static int check_memblock_offlined_cb(struct memory_block *mem, void *arg) { int ret = !is_memblock_offlined(mem); + int *nid = arg; + *nid = mem->nid; if (unlikely(ret)) { phys_addr_t beginpa, endpa; @@ -1839,12 +2143,12 @@ void try_offline_node(int nid) } EXPORT_SYMBOL(try_offline_node); -static int __ref try_remove_memory(int nid, u64 start, u64 size) +static int __ref try_remove_memory(u64 start, u64 size) { - int rc = 0; struct vmem_altmap mhp_altmap = {}; struct vmem_altmap *altmap = NULL; unsigned long nr_vmemmap_pages; + int rc = 0, nid = NUMA_NO_NODE; BUG_ON(check_hotplug_memory_range(start, size)); @@ -1852,8 +2156,12 @@ static int __ref try_remove_memory(int nid, u64 start, u64 size) * All memory blocks must be offlined before removing memory. Check * whether all memory blocks in question are offline and return error * if this is not the case. + * + * While at it, determine the nid. Note that if we'd have mixed nodes, + * we'd only try to offline the last determined one -- which is good + * enough for the cases we care about. */ - rc = walk_memory_blocks(start, size, NULL, check_memblock_offlined_cb); + rc = walk_memory_blocks(start, size, &nid, check_memblock_offlined_cb); if (rc) return rc; @@ -1893,7 +2201,7 @@ static int __ref try_remove_memory(int nid, u64 start, u64 size) mem_hotplug_begin(); - arch_remove_memory(nid, start, size, altmap); + arch_remove_memory(start, size, altmap); if (IS_ENABLED(CONFIG_ARCH_KEEP_MEMBLOCK)) { memblock_free(start, size); @@ -1902,7 +2210,8 @@ static int __ref try_remove_memory(int nid, u64 start, u64 size) release_mem_region_adjustable(start, size); - try_offline_node(nid); + if (nid != NUMA_NO_NODE) + try_offline_node(nid); mem_hotplug_done(); return 0; @@ -1910,7 +2219,6 @@ static int __ref try_remove_memory(int nid, u64 start, u64 size) /** * __remove_memory - Remove memory if every memory block is offline - * @nid: the node ID * @start: physical address of the region to remove * @size: size of the region to remove * @@ -1918,14 +2226,14 @@ static int __ref try_remove_memory(int nid, u64 start, u64 size) * and online/offline operations before this call, as required by * try_offline_node(). */ -void __remove_memory(int nid, u64 start, u64 size) +void __remove_memory(u64 start, u64 size) { /* * trigger BUG() if some memory is not offlined prior to calling this * function */ - if (try_remove_memory(nid, start, size)) + if (try_remove_memory(start, size)) BUG(); } @@ -1933,12 +2241,12 @@ void __remove_memory(int nid, u64 start, u64 size) * Remove memory if every memory block is offline, otherwise return -EBUSY is * some memory is not offline */ -int remove_memory(int nid, u64 start, u64 size) +int remove_memory(u64 start, u64 size) { int rc; lock_device_hotplug(); - rc = try_remove_memory(nid, start, size); + rc = try_remove_memory(start, size); unlock_device_hotplug(); return rc; @@ -1998,7 +2306,7 @@ static int try_reonline_memory_block(struct memory_block *mem, void *arg) * unplugged all memory (so it's no longer in use) and want to offline + remove * that memory. */ -int offline_and_remove_memory(int nid, u64 start, u64 size) +int offline_and_remove_memory(u64 start, u64 size) { const unsigned long mb_count = size / memory_block_size_bytes(); uint8_t *online_types, *tmp; @@ -2034,7 +2342,7 @@ int offline_and_remove_memory(int nid, u64 start, u64 size) * This cannot fail as it cannot get onlined in the meantime. */ if (!rc) { - rc = try_remove_memory(nid, start, size); + rc = try_remove_memory(start, size); if (rc) pr_err("%s: Failed to remove memory: %d", __func__, rc); } |