linux/arch/s390/mm/init.c

251 lines
6.1 KiB
C
Raw Normal View History

/*
* S390 version
* Copyright IBM Corp. 1999
* Author(s): Hartmut Penner (hp@de.ibm.com)
*
* Derived from "arch/i386/mm/init.c"
* Copyright (C) 1995 Linus Torvalds
*/
#include <linux/signal.h>
#include <linux/sched.h>
#include <linux/kernel.h>
#include <linux/errno.h>
#include <linux/string.h>
#include <linux/types.h>
#include <linux/ptrace.h>
#include <linux/mman.h>
#include <linux/mm.h>
#include <linux/swap.h>
#include <linux/smp.h>
#include <linux/init.h>
#include <linux/pagemap.h>
#include <linux/bootmem.h>
#include <linux/memory.h>
#include <linux/pfn.h>
#include <linux/poison.h>
#include <linux/initrd.h>
#include <linux/export.h>
#include <linux/cma.h>
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 08:04:11 +00:00
#include <linux/gfp.h>
#include <linux/memblock.h>
#include <asm/processor.h>
#include <linux/uaccess.h>
#include <asm/pgtable.h>
#include <asm/pgalloc.h>
#include <asm/dma.h>
#include <asm/lowcore.h>
#include <asm/tlb.h>
#include <asm/tlbflush.h>
#include <asm/sections.h>
#include <asm/ctl_reg.h>
#include <asm/sclp.h>
#include <asm/set_memory.h>
pgd_t swapper_pg_dir[PTRS_PER_PGD] __section(.bss..swapper_pg_dir);
unsigned long empty_zero_page, zero_page_mask;
EXPORT_SYMBOL(empty_zero_page);
EXPORT_SYMBOL(zero_page_mask);
static void __init setup_zero_pages(void)
{
unsigned int order;
struct page *page;
int i;
/* Latest machines require a mapping granularity of 512KB */
order = 7;
/* Limit number of empty zero pages for small memory sizes */
while (order > 2 && (totalram_pages >> 10) < (1UL << order))
order--;
empty_zero_page = __get_free_pages(GFP_KERNEL | __GFP_ZERO, order);
if (!empty_zero_page)
panic("Out of memory in setup_zero_pages");
page = virt_to_page((void *) empty_zero_page);
split_page(page, order);
for (i = 1 << order; i > 0; i--) {
mark_page_reserved(page);
page++;
}
zero_page_mask = ((PAGE_SIZE << order) - 1) & PAGE_MASK;
}
/*
* paging_init() sets up the page tables
*/
void __init paging_init(void)
{
unsigned long max_zone_pfns[MAX_NR_ZONES];
unsigned long pgd_type, asce_bits;
psw_t psw;
init_mm.pgd = swapper_pg_dir;
if (VMALLOC_END > _REGION2_SIZE) {
asce_bits = _ASCE_TYPE_REGION2 | _ASCE_TABLE_LENGTH;
pgd_type = _REGION2_ENTRY_EMPTY;
} else {
asce_bits = _ASCE_TYPE_REGION3 | _ASCE_TABLE_LENGTH;
pgd_type = _REGION3_ENTRY_EMPTY;
}
s390/mm: fix asce_bits handling with dynamic pagetable levels There is a race with multi-threaded applications between context switch and pagetable upgrade. In switch_mm() a new user_asce is built from mm->pgd and mm->context.asce_bits, w/o holding any locks. A concurrent mmap with a pagetable upgrade on another thread in crst_table_upgrade() could already have set new asce_bits, but not yet the new mm->pgd. This would result in a corrupt user_asce in switch_mm(), and eventually in a kernel panic from a translation exception. Fix this by storing the complete asce instead of just the asce_bits, which can then be read atomically from switch_mm(), so that it either sees the old value or the new value, but no mixture. Both cases are OK. Having the old value would result in a page fault on access to the higher level memory, but the fault handler would see the new mm->pgd, if it was a valid access after the mmap on the other thread has completed. So as worst-case scenario we would have a page fault loop for the racing thread until the next time slice. Also remove dead code and simplify the upgrade/downgrade path, there are no upgrades from 2 levels, and only downgrades from 3 levels for compat tasks. There are also no concurrent upgrades, because the mmap_sem is held with down_write() in do_mmap, so the flush and table checks during upgrade can be removed. Reported-by: Michael Munday <munday@ca.ibm.com> Reviewed-by: Martin Schwidefsky <schwidefsky@de.ibm.com> Signed-off-by: Gerald Schaefer <gerald.schaefer@de.ibm.com> Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
2016-04-15 14:38:40 +00:00
init_mm.context.asce = (__pa(init_mm.pgd) & PAGE_MASK) | asce_bits;
S390_lowcore.kernel_asce = init_mm.context.asce;
crst_table_init((unsigned long *) init_mm.pgd, pgd_type);
vmem_map_init();
/* enable virtual mapping in kernel mode */
__ctl_load(S390_lowcore.kernel_asce, 1, 1);
__ctl_load(S390_lowcore.kernel_asce, 7, 7);
__ctl_load(S390_lowcore.kernel_asce, 13, 13);
psw.mask = __extract_psw();
psw_bits(psw).dat = 1;
psw_bits(psw).as = PSW_BITS_AS_HOME;
__load_psw_mask(psw.mask);
sparse_memory_present_with_active_regions(MAX_NUMNODES);
sparse_init();
memset(max_zone_pfns, 0, sizeof(max_zone_pfns));
max_zone_pfns[ZONE_DMA] = PFN_DOWN(MAX_DMA_ADDRESS);
max_zone_pfns[ZONE_NORMAL] = max_low_pfn;
free_area_init_nodes(max_zone_pfns);
}
void mark_rodata_ro(void)
{
unsigned long size = __end_ro_after_init - __start_ro_after_init;
set_memory_ro((unsigned long)__start_ro_after_init, size >> PAGE_SHIFT);
pr_info("Write protected read-only-after-init data: %luk\n", size >> 10);
}
void __init mem_init(void)
{
cpumask_set_cpu(0, &init_mm.context.cpu_attach_mask);
cpumask_set_cpu(0, mm_cpumask(&init_mm));
set_max_mapnr(max_low_pfn);
high_memory = (void *) __va(max_low_pfn * PAGE_SIZE);
/* Setup guest page hinting */
cmma_init();
/* this will put all low memory onto the freelists */
mm: concentrate modification of totalram_pages into the mm core Concentrate code to modify totalram_pages into the mm core, so the arch memory initialized code doesn't need to take care of it. With these changes applied, only following functions from mm core modify global variable totalram_pages: free_bootmem_late(), free_all_bootmem(), free_all_bootmem_node(), adjust_managed_page_count(). With this patch applied, it will be much more easier for us to keep totalram_pages and zone->managed_pages in consistence. Signed-off-by: Jiang Liu <jiang.liu@huawei.com> Acked-by: David Howells <dhowells@redhat.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: "Michael S. Tsirkin" <mst@redhat.com> Cc: <sworddragon2@aol.com> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Chris Metcalf <cmetcalf@tilera.com> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Jianguo Wu <wujianguo@huawei.com> Cc: Joonsoo Kim <js1304@gmail.com> Cc: Kamezawa Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Cc: Marek Szyprowski <m.szyprowski@samsung.com> Cc: Mel Gorman <mel@csn.ul.ie> Cc: Michel Lespinasse <walken@google.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Rik van Riel <riel@redhat.com> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: Tang Chen <tangchen@cn.fujitsu.com> Cc: Tejun Heo <tj@kernel.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Wen Congyang <wency@cn.fujitsu.com> Cc: Will Deacon <will.deacon@arm.com> Cc: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Cc: Yinghai Lu <yinghai@kernel.org> Cc: Russell King <rmk@arm.linux.org.uk> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-07-03 22:03:24 +00:00
free_all_bootmem();
setup_zero_pages(); /* Setup zeroed pages. */
cmma_init_nodat();
mem_init_print_info(NULL);
}
void free_initmem(void)
{
__set_memory((unsigned long) _sinittext,
(_einittext - _sinittext) >> PAGE_SHIFT,
SET_MEMORY_RW | SET_MEMORY_NX);
mm: enhance free_reserved_area() to support poisoning memory with zero Address more review comments from last round of code review. 1) Enhance free_reserved_area() to support poisoning freed memory with pattern '0'. This could be used to get rid of poison_init_mem() on ARM64. 2) A previous patch has disabled memory poison for initmem on s390 by mistake, so restore to the original behavior. 3) Remove redundant PAGE_ALIGN() when calling free_reserved_area(). Signed-off-by: Jiang Liu <jiang.liu@huawei.com> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: "Michael S. Tsirkin" <mst@redhat.com> Cc: <sworddragon2@aol.com> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Chris Metcalf <cmetcalf@tilera.com> Cc: David Howells <dhowells@redhat.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Jianguo Wu <wujianguo@huawei.com> Cc: Joonsoo Kim <js1304@gmail.com> Cc: Kamezawa Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Cc: Marek Szyprowski <m.szyprowski@samsung.com> Cc: Mel Gorman <mel@csn.ul.ie> Cc: Michel Lespinasse <walken@google.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Rik van Riel <riel@redhat.com> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: Tang Chen <tangchen@cn.fujitsu.com> Cc: Tejun Heo <tj@kernel.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Wen Congyang <wency@cn.fujitsu.com> Cc: Will Deacon <will.deacon@arm.com> Cc: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Cc: Yinghai Lu <yinghai@kernel.org> Cc: Russell King <rmk@arm.linux.org.uk> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-07-03 22:02:51 +00:00
free_initmem_default(POISON_FREE_INITMEM);
}
#ifdef CONFIG_BLK_DEV_INITRD
void __init free_initrd_mem(unsigned long start, unsigned long end)
{
mm: change signature of free_reserved_area() to fix building warnings Change signature of free_reserved_area() according to Russell King's suggestion to fix following build warnings: arch/arm/mm/init.c: In function 'mem_init': arch/arm/mm/init.c:603:2: warning: passing argument 1 of 'free_reserved_area' makes integer from pointer without a cast [enabled by default] free_reserved_area(__va(PHYS_PFN_OFFSET), swapper_pg_dir, 0, NULL); ^ In file included from include/linux/mman.h:4:0, from arch/arm/mm/init.c:15: include/linux/mm.h:1301:22: note: expected 'long unsigned int' but argument is of type 'void *' extern unsigned long free_reserved_area(unsigned long start, unsigned long end, mm/page_alloc.c: In function 'free_reserved_area': >> mm/page_alloc.c:5134:3: warning: passing argument 1 of 'virt_to_phys' makes pointer from integer without a cast [enabled by default] In file included from arch/mips/include/asm/page.h:49:0, from include/linux/mmzone.h:20, from include/linux/gfp.h:4, from include/linux/mm.h:8, from mm/page_alloc.c:18: arch/mips/include/asm/io.h:119:29: note: expected 'const volatile void *' but argument is of type 'long unsigned int' mm/page_alloc.c: In function 'free_area_init_nodes': mm/page_alloc.c:5030:34: warning: array subscript is below array bounds [-Warray-bounds] Also address some minor code review comments. Signed-off-by: Jiang Liu <jiang.liu@huawei.com> Reported-by: Arnd Bergmann <arnd@arndb.de> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: "Michael S. Tsirkin" <mst@redhat.com> Cc: <sworddragon2@aol.com> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Chris Metcalf <cmetcalf@tilera.com> Cc: David Howells <dhowells@redhat.com> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Jianguo Wu <wujianguo@huawei.com> Cc: Joonsoo Kim <js1304@gmail.com> Cc: Kamezawa Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Cc: Marek Szyprowski <m.szyprowski@samsung.com> Cc: Mel Gorman <mel@csn.ul.ie> Cc: Michel Lespinasse <walken@google.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Rik van Riel <riel@redhat.com> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: Tang Chen <tangchen@cn.fujitsu.com> Cc: Tejun Heo <tj@kernel.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Wen Congyang <wency@cn.fujitsu.com> Cc: Will Deacon <will.deacon@arm.com> Cc: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Cc: Yinghai Lu <yinghai@kernel.org> Cc: Russell King <rmk@arm.linux.org.uk> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-07-03 22:02:48 +00:00
free_reserved_area((void *)start, (void *)end, POISON_FREE_INITMEM,
"initrd");
}
#endif
unsigned long memory_block_size_bytes(void)
{
/*
* Make sure the memory block size is always greater
* or equal than the memory increment size.
*/
return max_t(unsigned long, MIN_MEMORY_BLOCK_SIZE, sclp.rzm);
}
#ifdef CONFIG_MEMORY_HOTPLUG
#ifdef CONFIG_CMA
/* Prevent memory blocks which contain cma regions from going offline */
struct s390_cma_mem_data {
unsigned long start;
unsigned long end;
};
static int s390_cma_check_range(struct cma *cma, void *data)
{
struct s390_cma_mem_data *mem_data;
unsigned long start, end;
mem_data = data;
start = cma_get_base(cma);
end = start + cma_get_size(cma);
if (end < mem_data->start)
return 0;
if (start >= mem_data->end)
return 0;
return -EBUSY;
}
static int s390_cma_mem_notifier(struct notifier_block *nb,
unsigned long action, void *data)
{
struct s390_cma_mem_data mem_data;
struct memory_notify *arg;
int rc = 0;
arg = data;
mem_data.start = arg->start_pfn << PAGE_SHIFT;
mem_data.end = mem_data.start + (arg->nr_pages << PAGE_SHIFT);
if (action == MEM_GOING_OFFLINE)
rc = cma_for_each_area(s390_cma_check_range, &mem_data);
return notifier_from_errno(rc);
}
static struct notifier_block s390_cma_mem_nb = {
.notifier_call = s390_cma_mem_notifier,
};
static int __init s390_cma_mem_init(void)
{
return register_memory_notifier(&s390_cma_mem_nb);
}
device_initcall(s390_cma_mem_init);
#endif /* CONFIG_CMA */
mm, memory_hotplug: replace for_device by want_memblock in arch_add_memory arch_add_memory gets for_device argument which then controls whether we want to create memblocks for created memory sections. Simplify the logic by telling whether we want memblocks directly rather than going through pointless negation. This also makes the api easier to understand because it is clear what we want rather than nothing telling for_device which can mean anything. This shouldn't introduce any functional change. Link: http://lkml.kernel.org/r/20170515085827.16474-13-mhocko@kernel.org Signed-off-by: Michal Hocko <mhocko@suse.com> Tested-by: Dan Williams <dan.j.williams@intel.com> Acked-by: Vlastimil Babka <vbabka@suse.cz> Cc: Andi Kleen <ak@linux.intel.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Balbir Singh <bsingharora@gmail.com> Cc: Daniel Kiper <daniel.kiper@oracle.com> Cc: David Rientjes <rientjes@google.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Igor Mammedov <imammedo@redhat.com> Cc: Jerome Glisse <jglisse@redhat.com> Cc: Joonsoo Kim <js1304@gmail.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Reza Arbab <arbab@linux.vnet.ibm.com> Cc: Tobias Regnery <tobias.regnery@gmail.com> Cc: Toshi Kani <toshi.kani@hpe.com> Cc: Vitaly Kuznetsov <vkuznets@redhat.com> Cc: Xishi Qiu <qiuxishi@huawei.com> Cc: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-07-06 22:38:21 +00:00
int arch_add_memory(int nid, u64 start, u64 size, bool want_memblock)
{
unsigned long start_pfn = PFN_DOWN(start);
unsigned long size_pages = PFN_DOWN(size);
mm, memory_hotplug: do not associate hotadded memory to zones until online The current memory hotplug implementation relies on having all the struct pages associate with a zone/node during the physical hotplug phase (arch_add_memory->__add_pages->__add_section->__add_zone). In the vast majority of cases this means that they are added to ZONE_NORMAL. This has been so since 9d99aaa31f59 ("[PATCH] x86_64: Support memory hotadd without sparsemem") and it wasn't a big deal back then because movable onlining didn't exist yet. Much later memory hotplug wanted to (ab)use ZONE_MOVABLE for movable onlining 511c2aba8f07 ("mm, memory-hotplug: dynamic configure movable memory and portion memory") and then things got more complicated. Rather than reconsidering the zone association which was no longer needed (because the memory hotplug already depended on SPARSEMEM) a convoluted semantic of zone shifting has been developed. Only the currently last memblock or the one adjacent to the zone_movable can be onlined movable. This essentially means that the online type changes as the new memblocks are added. Let's simulate memory hot online manually $ echo 0x100000000 > /sys/devices/system/memory/probe $ grep . /sys/devices/system/memory/memory32/valid_zones Normal Movable $ echo $((0x100000000+(128<<20))) > /sys/devices/system/memory/probe $ grep . /sys/devices/system/memory/memory3?/valid_zones /sys/devices/system/memory/memory32/valid_zones:Normal /sys/devices/system/memory/memory33/valid_zones:Normal Movable $ echo $((0x100000000+2*(128<<20))) > /sys/devices/system/memory/probe $ grep . /sys/devices/system/memory/memory3?/valid_zones /sys/devices/system/memory/memory32/valid_zones:Normal /sys/devices/system/memory/memory33/valid_zones:Normal /sys/devices/system/memory/memory34/valid_zones:Normal Movable $ echo online_movable > /sys/devices/system/memory/memory34/state $ grep . /sys/devices/system/memory/memory3?/valid_zones /sys/devices/system/memory/memory32/valid_zones:Normal /sys/devices/system/memory/memory33/valid_zones:Normal Movable /sys/devices/system/memory/memory34/valid_zones:Movable Normal This is an awkward semantic because an udev event is sent as soon as the block is onlined and an udev handler might want to online it based on some policy (e.g. association with a node) but it will inherently race with new blocks showing up. This patch changes the physical online phase to not associate pages with any zone at all. All the pages are just marked reserved and wait for the onlining phase to be associated with the zone as per the online request. There are only two requirements - existing ZONE_NORMAL and ZONE_MOVABLE cannot overlap - ZONE_NORMAL precedes ZONE_MOVABLE in physical addresses the latter one is not an inherent requirement and can be changed in the future. It preserves the current behavior and made the code slightly simpler. This is subject to change in future. This means that the same physical online steps as above will lead to the following state: Normal Movable /sys/devices/system/memory/memory32/valid_zones:Normal Movable /sys/devices/system/memory/memory33/valid_zones:Normal Movable /sys/devices/system/memory/memory32/valid_zones:Normal Movable /sys/devices/system/memory/memory33/valid_zones:Normal Movable /sys/devices/system/memory/memory34/valid_zones:Normal Movable /sys/devices/system/memory/memory32/valid_zones:Normal Movable /sys/devices/system/memory/memory33/valid_zones:Normal Movable /sys/devices/system/memory/memory34/valid_zones:Movable Implementation: The current move_pfn_range is reimplemented to check the above requirements (allow_online_pfn_range) and then updates the respective zone (move_pfn_range_to_zone), the pgdat and links all the pages in the pfn range with the zone/node. __add_pages is updated to not require the zone and only initializes sections in the range. This allowed to simplify the arch_add_memory code (s390 could get rid of quite some of code). devm_memremap_pages is the only user of arch_add_memory which relies on the zone association because it only hooks into the memory hotplug only half way. It uses it to associate the new memory with ZONE_DEVICE but doesn't allow it to be {on,off}lined via sysfs. This means that this particular code path has to call move_pfn_range_to_zone explicitly. The original zone shifting code is kept in place and will be removed in the follow up patch for an easier review. Please note that this patch also changes the original behavior when offlining a memory block adjacent to another zone (Normal vs. Movable) used to allow to change its movable type. This will be handled later. [richard.weiyang@gmail.com: simplify zone_intersects()] Link: http://lkml.kernel.org/r/20170616092335.5177-1-richard.weiyang@gmail.com [richard.weiyang@gmail.com: remove duplicate call for set_page_links] Link: http://lkml.kernel.org/r/20170616092335.5177-2-richard.weiyang@gmail.com [akpm@linux-foundation.org: remove unused local `i'] Link: http://lkml.kernel.org/r/20170515085827.16474-12-mhocko@kernel.org Signed-off-by: Michal Hocko <mhocko@suse.com> Signed-off-by: Wei Yang <richard.weiyang@gmail.com> Tested-by: Dan Williams <dan.j.williams@intel.com> Tested-by: Reza Arbab <arbab@linux.vnet.ibm.com> Acked-by: Heiko Carstens <heiko.carstens@de.ibm.com> # For s390 bits Acked-by: Vlastimil Babka <vbabka@suse.cz> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Balbir Singh <bsingharora@gmail.com> Cc: Daniel Kiper <daniel.kiper@oracle.com> Cc: David Rientjes <rientjes@google.com> Cc: Igor Mammedov <imammedo@redhat.com> Cc: Jerome Glisse <jglisse@redhat.com> Cc: Joonsoo Kim <js1304@gmail.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Tobias Regnery <tobias.regnery@gmail.com> Cc: Toshi Kani <toshi.kani@hpe.com> Cc: Vitaly Kuznetsov <vkuznets@redhat.com> Cc: Xishi Qiu <qiuxishi@huawei.com> Cc: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-07-06 22:38:11 +00:00
int rc;
rc = vmem_add_mapping(start, size);
if (rc)
return rc;
mm, memory_hotplug: replace for_device by want_memblock in arch_add_memory arch_add_memory gets for_device argument which then controls whether we want to create memblocks for created memory sections. Simplify the logic by telling whether we want memblocks directly rather than going through pointless negation. This also makes the api easier to understand because it is clear what we want rather than nothing telling for_device which can mean anything. This shouldn't introduce any functional change. Link: http://lkml.kernel.org/r/20170515085827.16474-13-mhocko@kernel.org Signed-off-by: Michal Hocko <mhocko@suse.com> Tested-by: Dan Williams <dan.j.williams@intel.com> Acked-by: Vlastimil Babka <vbabka@suse.cz> Cc: Andi Kleen <ak@linux.intel.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Balbir Singh <bsingharora@gmail.com> Cc: Daniel Kiper <daniel.kiper@oracle.com> Cc: David Rientjes <rientjes@google.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Igor Mammedov <imammedo@redhat.com> Cc: Jerome Glisse <jglisse@redhat.com> Cc: Joonsoo Kim <js1304@gmail.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Reza Arbab <arbab@linux.vnet.ibm.com> Cc: Tobias Regnery <tobias.regnery@gmail.com> Cc: Toshi Kani <toshi.kani@hpe.com> Cc: Vitaly Kuznetsov <vkuznets@redhat.com> Cc: Xishi Qiu <qiuxishi@huawei.com> Cc: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-07-06 22:38:21 +00:00
rc = __add_pages(nid, start_pfn, size_pages, want_memblock);
if (rc)
vmem_remove_mapping(start, size);
return rc;
}
#ifdef CONFIG_MEMORY_HOTREMOVE
int arch_remove_memory(u64 start, u64 size)
{
/*
* There is no hardware or firmware interface which could trigger a
* hot memory remove on s390. So there is nothing that needs to be
* implemented.
*/
return -EBUSY;
}
#endif
#endif /* CONFIG_MEMORY_HOTPLUG */