diff options
| -rw-r--r-- | arch/s390/mm/pgalloc.c | 2 | ||||
| -rw-r--r-- | arch/s390/mm/vmem.c | 21 | ||||
| -rw-r--r-- | drivers/base/memory.c | 23 | ||||
| -rw-r--r-- | drivers/s390/char/sclp_mem.c | 287 | ||||
| -rw-r--r-- | include/linux/memory.h | 9 | ||||
| -rw-r--r-- | include/linux/memory_hotplug.h | 18 | ||||
| -rw-r--r-- | include/linux/memremap.h | 1 | ||||
| -rw-r--r-- | mm/memory_hotplug.c | 17 | ||||
| -rw-r--r-- | mm/sparse.c | 3 |
9 files changed, 224 insertions, 157 deletions
diff --git a/arch/s390/mm/pgalloc.c b/arch/s390/mm/pgalloc.c index 626fca116cd7..7df23528c01b 100644 --- a/arch/s390/mm/pgalloc.c +++ b/arch/s390/mm/pgalloc.c @@ -164,6 +164,8 @@ void page_table_free(struct mm_struct *mm, unsigned long *table) { struct ptdesc *ptdesc = virt_to_ptdesc(table); + if (pagetable_is_reserved(ptdesc)) + return free_reserved_ptdesc(ptdesc); pagetable_dtor_free(ptdesc); } diff --git a/arch/s390/mm/vmem.c b/arch/s390/mm/vmem.c index f48ef361bc83..d96587b84e81 100644 --- a/arch/s390/mm/vmem.c +++ b/arch/s390/mm/vmem.c @@ -4,6 +4,7 @@ */ #include <linux/memory_hotplug.h> +#include <linux/bootmem_info.h> #include <linux/cpufeature.h> #include <linux/memblock.h> #include <linux/pfn.h> @@ -39,15 +40,21 @@ static void __ref *vmem_alloc_pages(unsigned int order) static void vmem_free_pages(unsigned long addr, int order, struct vmem_altmap *altmap) { + unsigned int nr_pages = 1 << order; + struct page *page; + if (altmap) { vmem_altmap_free(altmap, 1 << order); return; } - /* We don't expect boot memory to be removed ever. */ - if (!slab_is_available() || - WARN_ON_ONCE(PageReserved(virt_to_page((void *)addr)))) - return; - free_pages(addr, order); + page = virt_to_page((void *)addr); + if (PageReserved(page)) { + /* allocated from memblock */ + while (nr_pages--) + free_bootmem_page(page++); + } else { + free_pages(addr, order); + } } void *vmem_crst_alloc(unsigned long val) @@ -79,10 +86,6 @@ pte_t __ref *vmem_pte_alloc(void) static void vmem_pte_free(unsigned long *table) { - /* We don't expect boot memory to be removed ever. */ - if (!slab_is_available() || - WARN_ON_ONCE(PageReserved(virt_to_page(table)))) - return; page_table_free(&init_mm, table); } diff --git a/drivers/base/memory.c b/drivers/base/memory.c index 6d84a02cfa5d..fc43f2703ae0 100644 --- a/drivers/base/memory.c +++ b/drivers/base/memory.c @@ -226,7 +226,6 @@ static int memory_block_online(struct memory_block *mem) unsigned long start_pfn = section_nr_to_pfn(mem->start_section_nr); unsigned long nr_pages = PAGES_PER_SECTION * sections_per_block; unsigned long nr_vmemmap_pages = 0; - struct memory_notify arg; struct zone *zone; int ret; @@ -246,19 +245,9 @@ static int memory_block_online(struct memory_block *mem) if (mem->altmap) nr_vmemmap_pages = mem->altmap->free; - arg.altmap_start_pfn = start_pfn; - arg.altmap_nr_pages = nr_vmemmap_pages; - arg.start_pfn = start_pfn + nr_vmemmap_pages; - arg.nr_pages = nr_pages - nr_vmemmap_pages; mem_hotplug_begin(); - ret = memory_notify(MEM_PREPARE_ONLINE, &arg); - ret = notifier_to_errno(ret); - if (ret) - goto out_notifier; - if (nr_vmemmap_pages) { - ret = mhp_init_memmap_on_memory(start_pfn, nr_vmemmap_pages, - zone, mem->altmap->inaccessible); + ret = mhp_init_memmap_on_memory(start_pfn, nr_vmemmap_pages, zone); if (ret) goto out; } @@ -280,11 +269,7 @@ static int memory_block_online(struct memory_block *mem) nr_vmemmap_pages); mem->zone = zone; - mem_hotplug_done(); - return ret; out: - memory_notify(MEM_FINISH_OFFLINE, &arg); -out_notifier: mem_hotplug_done(); return ret; } @@ -297,7 +282,6 @@ static int memory_block_offline(struct memory_block *mem) unsigned long start_pfn = section_nr_to_pfn(mem->start_section_nr); unsigned long nr_pages = PAGES_PER_SECTION * sections_per_block; unsigned long nr_vmemmap_pages = 0; - struct memory_notify arg; int ret; if (!mem->zone) @@ -329,11 +313,6 @@ static int memory_block_offline(struct memory_block *mem) mhp_deinit_memmap_on_memory(start_pfn, nr_vmemmap_pages); mem->zone = NULL; - arg.altmap_start_pfn = start_pfn; - arg.altmap_nr_pages = nr_vmemmap_pages; - arg.start_pfn = start_pfn + nr_vmemmap_pages; - arg.nr_pages = nr_pages - nr_vmemmap_pages; - memory_notify(MEM_FINISH_OFFLINE, &arg); out: mem_hotplug_done(); return ret; diff --git a/drivers/s390/char/sclp_mem.c b/drivers/s390/char/sclp_mem.c index 27f49f5fd358..3a7a69615d99 100644 --- a/drivers/s390/char/sclp_mem.c +++ b/drivers/s390/char/sclp_mem.c @@ -9,9 +9,12 @@ #define pr_fmt(fmt) KMSG_COMPONENT ": " fmt #include <linux/cpufeature.h> +#include <linux/container_of.h> #include <linux/err.h> #include <linux/errno.h> #include <linux/init.h> +#include <linux/kobject.h> +#include <linux/kstrtox.h> #include <linux/memory.h> #include <linux/memory_hotplug.h> #include <linux/mm.h> @@ -27,7 +30,6 @@ #define SCLP_CMDW_ASSIGN_STORAGE 0x000d0001 #define SCLP_CMDW_UNASSIGN_STORAGE 0x000c0001 -static DEFINE_MUTEX(sclp_mem_mutex); static LIST_HEAD(sclp_mem_list); static u8 sclp_max_storage_id; static DECLARE_BITMAP(sclp_storage_ids, 256); @@ -38,6 +40,18 @@ struct memory_increment { int standby; }; +struct sclp_mem { + struct kobject kobj; + unsigned int id; + unsigned int memmap_on_memory; + unsigned int config; +}; + +struct sclp_mem_arg { + struct sclp_mem *sclp_mems; + struct kset *kset; +}; + struct assign_storage_sccb { struct sccb_header header; u16 rn; @@ -163,92 +177,166 @@ static int sclp_mem_change_state(unsigned long start, unsigned long size, return rc ? -EIO : 0; } -static bool contains_standby_increment(unsigned long start, unsigned long end) +static ssize_t sclp_config_mem_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { - struct memory_increment *incr; - unsigned long istart; + struct sclp_mem *sclp_mem = container_of(kobj, struct sclp_mem, kobj); - list_for_each_entry(incr, &sclp_mem_list, list) { - istart = rn2addr(incr->rn); - if (end - 1 < istart) - continue; - if (start > istart + sclp.rzm - 1) - continue; - if (incr->standby) - return true; - } - return false; + return sysfs_emit(buf, "%u\n", READ_ONCE(sclp_mem->config)); } -static int sclp_mem_notifier(struct notifier_block *nb, - unsigned long action, void *data) +static ssize_t sclp_config_mem_store(struct kobject *kobj, struct kobj_attribute *attr, + const char *buf, size_t count) { - unsigned long start, size; - struct memory_notify *arg; + unsigned long addr, block_size; + struct sclp_mem *sclp_mem; + struct memory_block *mem; unsigned char id; - int rc = 0; + bool value; + int rc; - arg = data; - start = arg->start_pfn << PAGE_SHIFT; - size = arg->nr_pages << PAGE_SHIFT; - mutex_lock(&sclp_mem_mutex); + rc = kstrtobool(buf, &value); + if (rc) + return rc; + sclp_mem = container_of(kobj, struct sclp_mem, kobj); + block_size = memory_block_size_bytes(); + addr = sclp_mem->id * block_size; + /* + * Hold device_hotplug_lock when adding/removing memory blocks. + * Additionally, also protect calls to find_memory_block() and + * sclp_attach_storage(). + */ + rc = lock_device_hotplug_sysfs(); + if (rc) + goto out; for_each_clear_bit(id, sclp_storage_ids, sclp_max_storage_id + 1) sclp_attach_storage(id); - switch (action) { - case MEM_GOING_OFFLINE: - /* - * Do not allow to set memory blocks offline that contain - * standby memory. This is done to simplify the "memory online" - * case. - */ - if (contains_standby_increment(start, start + size)) - rc = -EPERM; - break; - case MEM_PREPARE_ONLINE: + if (value) { + if (sclp_mem->config) + goto out_unlock; + rc = sclp_mem_change_state(addr, block_size, 1); + if (rc) + goto out_unlock; /* - * Access the altmap_start_pfn and altmap_nr_pages fields - * within the struct memory_notify specifically when dealing - * with only MEM_PREPARE_ONLINE/MEM_FINISH_OFFLINE notifiers. - * - * When altmap is in use, take the specified memory range - * online, which includes the altmap. + * Set entire memory block CMMA state to nodat. Later, when + * page tables pages are allocated via __add_memory(), those + * regions are marked __arch_set_page_dat(). */ - if (arg->altmap_nr_pages) { - start = PFN_PHYS(arg->altmap_start_pfn); - size += PFN_PHYS(arg->altmap_nr_pages); + __arch_set_page_nodat((void *)__va(addr), block_size >> PAGE_SHIFT); + rc = __add_memory(0, addr, block_size, + sclp_mem->memmap_on_memory ? + MHP_MEMMAP_ON_MEMORY : MHP_NONE); + if (rc) { + sclp_mem_change_state(addr, block_size, 0); + goto out_unlock; } - rc = sclp_mem_change_state(start, size, 1); - if (rc || !arg->altmap_nr_pages) - break; - /* - * Set CMMA state to nodat here, since the struct page memory - * at the beginning of the memory block will not go through the - * buddy allocator later. - */ - __arch_set_page_nodat((void *)__va(start), arg->altmap_nr_pages); - break; - case MEM_FINISH_OFFLINE: - /* - * When altmap is in use, take the specified memory range - * offline, which includes the altmap. - */ - if (arg->altmap_nr_pages) { - start = PFN_PHYS(arg->altmap_start_pfn); - size += PFN_PHYS(arg->altmap_nr_pages); + mem = find_memory_block(pfn_to_section_nr(PFN_DOWN(addr))); + put_device(&mem->dev); + WRITE_ONCE(sclp_mem->config, 1); + } else { + if (!sclp_mem->config) + goto out_unlock; + mem = find_memory_block(pfn_to_section_nr(PFN_DOWN(addr))); + if (mem->state != MEM_OFFLINE) { + put_device(&mem->dev); + rc = -EBUSY; + goto out_unlock; } - sclp_mem_change_state(start, size, 0); - break; - default: - break; + /* drop the ref just got via find_memory_block() */ + put_device(&mem->dev); + sclp_mem_change_state(addr, block_size, 0); + __remove_memory(addr, block_size); + WRITE_ONCE(sclp_mem->config, 0); + } +out_unlock: + unlock_device_hotplug(); +out: + return rc ? rc : count; +} + +static struct kobj_attribute sclp_config_mem_attr = + __ATTR(config, 0644, sclp_config_mem_show, sclp_config_mem_store); + +static ssize_t sclp_memmap_on_memory_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) +{ + struct sclp_mem *sclp_mem = container_of(kobj, struct sclp_mem, kobj); + + return sysfs_emit(buf, "%u\n", READ_ONCE(sclp_mem->memmap_on_memory)); +} + +static ssize_t sclp_memmap_on_memory_store(struct kobject *kobj, struct kobj_attribute *attr, + const char *buf, size_t count) +{ + struct sclp_mem *sclp_mem; + unsigned long block_size; + struct memory_block *mem; + bool value; + int rc; + + rc = kstrtobool(buf, &value); + if (rc) + return rc; + rc = lock_device_hotplug_sysfs(); + if (rc) + return rc; + block_size = memory_block_size_bytes(); + sclp_mem = container_of(kobj, struct sclp_mem, kobj); + mem = find_memory_block(pfn_to_section_nr(PFN_DOWN(sclp_mem->id * block_size))); + if (!mem) { + WRITE_ONCE(sclp_mem->memmap_on_memory, value); + } else { + put_device(&mem->dev); + rc = -EBUSY; } - mutex_unlock(&sclp_mem_mutex); - return rc ? NOTIFY_BAD : NOTIFY_OK; + unlock_device_hotplug(); + return rc ? rc : count; } -static struct notifier_block sclp_mem_nb = { - .notifier_call = sclp_mem_notifier, +static const struct kobj_type ktype = { + .sysfs_ops = &kobj_sysfs_ops, +}; + +static struct kobj_attribute sclp_memmap_attr = + __ATTR(memmap_on_memory, 0644, sclp_memmap_on_memory_show, sclp_memmap_on_memory_store); + +static struct attribute *sclp_mem_attrs[] = { + &sclp_config_mem_attr.attr, + &sclp_memmap_attr.attr, + NULL, }; +static struct attribute_group sclp_mem_attr_group = { + .attrs = sclp_mem_attrs, +}; + +static int sclp_create_mem(struct sclp_mem *sclp_mem, struct kset *kset, + unsigned int id, bool config, bool memmap_on_memory) +{ + int rc; + + sclp_mem->memmap_on_memory = memmap_on_memory; + sclp_mem->config = config; + sclp_mem->id = id; + kobject_init(&sclp_mem->kobj, &ktype); + rc = kobject_add(&sclp_mem->kobj, &kset->kobj, "memory%d", id); + if (rc) + return rc; + return sysfs_create_group(&sclp_mem->kobj, &sclp_mem_attr_group); +} + +static int sclp_create_configured_mem(struct memory_block *mem, void *argument) +{ + struct sclp_mem *sclp_mems; + struct sclp_mem_arg *arg; + struct kset *kset; + unsigned int id; + + id = mem->dev.id; + arg = (struct sclp_mem_arg *)argument; + sclp_mems = arg->sclp_mems; + kset = arg->kset; + return sclp_create_mem(&sclp_mems[id], kset, id, true, false); +} + static void __init align_to_block_size(unsigned long *start, unsigned long *size, unsigned long alignment) @@ -264,14 +352,17 @@ static void __init align_to_block_size(unsigned long *start, *size = size_align; } -static void __init add_memory_merged(u16 rn) +static int __init sclp_create_standby_mems_merged(struct sclp_mem *sclp_mems, + struct kset *kset, u16 rn) { unsigned long start, size, addr, block_size; static u16 first_rn, num; + unsigned int id; + int rc = 0; if (rn && first_rn && (first_rn + num == rn)) { num++; - return; + return rc; } if (!first_rn) goto skip_add; @@ -286,24 +377,57 @@ static void __init add_memory_merged(u16 rn) if (!size) goto skip_add; for (addr = start; addr < start + size; addr += block_size) { - add_memory(0, addr, block_size, - cpu_has_edat1() ? - MHP_MEMMAP_ON_MEMORY | MHP_OFFLINE_INACCESSIBLE : MHP_NONE); + id = addr / block_size; + rc = sclp_create_mem(&sclp_mems[id], kset, id, false, + mhp_supports_memmap_on_memory()); + if (rc) + break; } skip_add: first_rn = rn; num = 1; + return rc; } -static void __init sclp_add_standby_memory(void) +static int __init sclp_create_standby_mems(struct sclp_mem *sclp_mems, struct kset *kset) { struct memory_increment *incr; + int rc = 0; list_for_each_entry(incr, &sclp_mem_list, list) { if (incr->standby) - add_memory_merged(incr->rn); + rc = sclp_create_standby_mems_merged(sclp_mems, kset, incr->rn); + if (rc) + return rc; } - add_memory_merged(0); + return sclp_create_standby_mems_merged(sclp_mems, kset, 0); +} + +static int __init sclp_init_mem(void) +{ + const unsigned long block_size = memory_block_size_bytes(); + unsigned int max_sclp_mems; + struct sclp_mem *sclp_mems; + struct sclp_mem_arg arg; + struct kset *kset; + int rc; + + max_sclp_mems = roundup(sclp.rnmax * sclp.rzm, block_size) / block_size; + /* Allocate memory for all blocks ahead of time. */ + sclp_mems = kcalloc(max_sclp_mems, sizeof(struct sclp_mem), GFP_KERNEL); + if (!sclp_mems) + return -ENOMEM; + kset = kset_create_and_add("memory", NULL, firmware_kobj); + if (!kset) + return -ENOMEM; + /* Initial memory is in the "configured" state already. */ + arg.sclp_mems = sclp_mems; + arg.kset = kset; + rc = for_each_memory_block(&arg, sclp_create_configured_mem); + if (rc) + return rc; + /* Standby memory is "deconfigured". */ + return sclp_create_standby_mems(sclp_mems, kset); } static void __init insert_increment(u16 rn, int standby, int assigned) @@ -336,7 +460,7 @@ static void __init insert_increment(u16 rn, int standby, int assigned) list_add(&new_incr->list, prev); } -static int __init sclp_detect_standby_memory(void) +static int __init sclp_setup_memory(void) { struct read_storage_sccb *sccb; int i, id, assigned, rc; @@ -388,12 +512,9 @@ static int __init sclp_detect_standby_memory(void) goto out; for (i = 1; i <= sclp.rnmax - assigned; i++) insert_increment(0, 1, 0); - rc = register_memory_notifier(&sclp_mem_nb); - if (rc) - goto out; - sclp_add_standby_memory(); + rc = sclp_init_mem(); out: free_page((unsigned long)sccb); return rc; } -__initcall(sclp_detect_standby_memory); +__initcall(sclp_setup_memory); diff --git a/include/linux/memory.h b/include/linux/memory.h index 0c214256216f..ba1515160894 100644 --- a/include/linux/memory.h +++ b/include/linux/memory.h @@ -96,17 +96,8 @@ int set_memory_block_size_order(unsigned int order); #define MEM_GOING_ONLINE (1<<3) #define MEM_CANCEL_ONLINE (1<<4) #define MEM_CANCEL_OFFLINE (1<<5) -#define MEM_PREPARE_ONLINE (1<<6) -#define MEM_FINISH_OFFLINE (1<<7) struct memory_notify { - /* - * The altmap_start_pfn and altmap_nr_pages fields are designated for - * specifying the altmap range and are exclusively intended for use in - * MEM_PREPARE_ONLINE/MEM_FINISH_OFFLINE notifiers. - */ - unsigned long altmap_start_pfn; - unsigned long altmap_nr_pages; unsigned long start_pfn; unsigned long nr_pages; }; diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index 23f038a16231..f2f16cdd73ee 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -58,22 +58,6 @@ typedef int __bitwise mhp_t; * implies the node id (nid). */ #define MHP_NID_IS_MGID ((__force mhp_t)BIT(2)) -/* - * The hotplugged memory is completely inaccessible while the memory is - * offline. The memory provider will handle MEM_PREPARE_ONLINE / - * MEM_FINISH_OFFLINE notifications and make the memory accessible. - * - * This flag is only relevant when used along with MHP_MEMMAP_ON_MEMORY, - * because the altmap cannot be written (e.g., poisoned) when adding - * memory -- before it is set online. - * - * This allows for adding memory with an altmap that is not currently - * made available by a hypervisor. When onlining that memory, the - * hypervisor can be instructed to make that memory available, and - * the onlining phase will not require any memory allocations, which is - * helpful in low-memory situations. - */ -#define MHP_OFFLINE_INACCESSIBLE ((__force mhp_t)BIT(3)) /* * Extended parameters for memory hotplug: @@ -123,7 +107,7 @@ extern void adjust_present_page_count(struct page *page, long nr_pages); /* VM interface that may be used by firmware interface */ extern int mhp_init_memmap_on_memory(unsigned long pfn, unsigned long nr_pages, - struct zone *zone, bool mhp_off_inaccessible); + struct zone *zone); extern void mhp_deinit_memmap_on_memory(unsigned long pfn, unsigned long nr_pages); extern int online_pages(unsigned long pfn, unsigned long nr_pages, struct zone *zone, struct memory_group *group); diff --git a/include/linux/memremap.h b/include/linux/memremap.h index e5951ba12a28..30c7aecbd245 100644 --- a/include/linux/memremap.h +++ b/include/linux/memremap.h @@ -25,7 +25,6 @@ struct vmem_altmap { unsigned long free; unsigned long align; unsigned long alloc; - bool inaccessible; }; /* diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 0be83039c3b5..238a6712738e 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -1088,7 +1088,7 @@ void adjust_present_page_count(struct page *page, struct memory_group *group, } int mhp_init_memmap_on_memory(unsigned long pfn, unsigned long nr_pages, - struct zone *zone, bool mhp_off_inaccessible) + struct zone *zone) { unsigned long end_pfn = pfn + nr_pages; int ret, i; @@ -1097,15 +1097,6 @@ int mhp_init_memmap_on_memory(unsigned long pfn, unsigned long nr_pages, if (ret) return ret; - /* - * Memory block is accessible at this stage and hence poison the struct - * pages now. If the memory block is accessible during memory hotplug - * addition phase, then page poisining is already performed in - * sparse_add_section(). - */ - if (mhp_off_inaccessible) - page_init_poison(pfn_to_page(pfn), sizeof(struct page) * nr_pages); - move_pfn_range_to_zone(zone, pfn, nr_pages, NULL, MIGRATE_UNMOVABLE, false); @@ -1444,7 +1435,7 @@ static void remove_memory_blocks_and_altmaps(u64 start, u64 size) } static int create_altmaps_and_memory_blocks(int nid, struct memory_group *group, - u64 start, u64 size, mhp_t mhp_flags) + u64 start, u64 size) { unsigned long memblock_size = memory_block_size_bytes(); u64 cur_start; @@ -1460,8 +1451,6 @@ static int create_altmaps_and_memory_blocks(int nid, struct memory_group *group, }; mhp_altmap.free = memory_block_memmap_on_memory_pages(); - if (mhp_flags & MHP_OFFLINE_INACCESSIBLE) - mhp_altmap.inaccessible = true; params.altmap = kmemdup(&mhp_altmap, sizeof(struct vmem_altmap), GFP_KERNEL); if (!params.altmap) { @@ -1555,7 +1544,7 @@ int add_memory_resource(int nid, struct resource *res, mhp_t mhp_flags) */ if ((mhp_flags & MHP_MEMMAP_ON_MEMORY) && mhp_supports_memmap_on_memory()) { - ret = create_altmaps_and_memory_blocks(nid, group, start, size, mhp_flags); + ret = create_altmaps_and_memory_blocks(nid, group, start, size); if (ret) goto error; } else { diff --git a/mm/sparse.c b/mm/sparse.c index 17c50a6415c2..b5b2b6f7041b 100644 --- a/mm/sparse.c +++ b/mm/sparse.c @@ -951,8 +951,7 @@ int __meminit sparse_add_section(int nid, unsigned long start_pfn, * Poison uninitialized struct pages in order to catch invalid flags * combinations. */ - if (!altmap || !altmap->inaccessible) - page_init_poison(memmap, sizeof(struct page) * nr_pages); + page_init_poison(memmap, sizeof(struct page) * nr_pages); ms = __nr_to_section(section_nr); set_section_nid(section_nr, nid); |
