mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-10-10 18:53:38 +00:00
48b4800a1c
This patch introduces run-time migration feature for zspage. For migration, VM uses page.lru field so it would be better to not use page.next field which is unified with page.lru for own purpose. For that, firstly, we can get first object offset of the page via runtime calculation instead of using page.index so we can use page.index as link for page chaining instead of page.next. In case of huge object, it stores handle to page.index instead of next link of page chaining because huge object doesn't need to next link for page chaining. So get_next_page need to identify huge object to return NULL. For it, this patch uses PG_owner_priv_1 flag of the page flag. For migration, it supports three functions * zs_page_isolate It isolates a zspage which includes a subpage VM want to migrate from class so anyone cannot allocate new object from the zspage. We could try to isolate a zspage by the number of subpage so subsequent isolation trial of other subpage of the zpsage shouldn't fail. For that, we introduce zspage.isolated count. With that, zs_page_isolate can know whether zspage is already isolated or not for migration so if it is isolated for migration, subsequent isolation trial can be successful without trying further isolation. * zs_page_migrate First of all, it holds write-side zspage->lock to prevent migrate other subpage in zspage. Then, lock all objects in the page VM want to migrate. The reason we should lock all objects in the page is due to race between zs_map_object and zs_page_migrate. zs_map_object zs_page_migrate pin_tag(handle) obj = handle_to_obj(handle) obj_to_location(obj, &page, &obj_idx); write_lock(&zspage->lock) if (!trypin_tag(handle)) goto unpin_object zspage = get_zspage(page); read_lock(&zspage->lock); If zs_page_migrate doesn't do trypin_tag, zs_map_object's page can be stale by migration so it goes crash. If it locks all of objects successfully, it copies content from old page to new one, finally, create new zspage chain with new page. And if it's last isolated subpage in the zspage, put the zspage back to class. * zs_page_putback It returns isolated zspage to right fullness_group list if it fails to migrate a page. If it find a zspage is ZS_EMPTY, it queues zspage freeing to workqueue. See below about async zspage freeing. This patch introduces asynchronous zspage free. The reason to need it is we need page_lock to clear PG_movable but unfortunately, zs_free path should be atomic so the apporach is try to grab page_lock. If it got page_lock of all of pages successfully, it can free zspage immediately. Otherwise, it queues free request and free zspage via workqueue in process context. If zs_free finds the zspage is isolated when it try to free zspage, it delays the freeing until zs_page_putback finds it so it will free free the zspage finally. In this patch, we expand fullness_list from ZS_EMPTY to ZS_FULL. First of all, it will use ZS_EMPTY list for delay freeing. And with adding ZS_FULL list, it makes to identify whether zspage is isolated or not via list_empty(&zspage->list) test. [minchan@kernel.org: zsmalloc: keep first object offset in struct page] Link: http://lkml.kernel.org/r/1465788015-23195-1-git-send-email-minchan@kernel.org [minchan@kernel.org: zsmalloc: zspage sanity check] Link: http://lkml.kernel.org/r/20160603010129.GC3304@bbox Link: http://lkml.kernel.org/r/1464736881-24886-12-git-send-email-minchan@kernel.org Signed-off-by: Minchan Kim <minchan@kernel.org> Cc: Sergey Senozhatsky <sergey.senozhatsky@gmail.com> Cc: Vlastimil Babka <vbabka@suse.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
86 lines
3.1 KiB
C
86 lines
3.1 KiB
C
#ifndef __LINUX_MAGIC_H__
|
|
#define __LINUX_MAGIC_H__
|
|
|
|
#define ADFS_SUPER_MAGIC 0xadf5
|
|
#define AFFS_SUPER_MAGIC 0xadff
|
|
#define AFS_SUPER_MAGIC 0x5346414F
|
|
#define AUTOFS_SUPER_MAGIC 0x0187
|
|
#define CODA_SUPER_MAGIC 0x73757245
|
|
#define CRAMFS_MAGIC 0x28cd3d45 /* some random number */
|
|
#define CRAMFS_MAGIC_WEND 0x453dcd28 /* magic number with the wrong endianess */
|
|
#define DEBUGFS_MAGIC 0x64626720
|
|
#define SECURITYFS_MAGIC 0x73636673
|
|
#define SELINUX_MAGIC 0xf97cff8c
|
|
#define SMACK_MAGIC 0x43415d53 /* "SMAC" */
|
|
#define RAMFS_MAGIC 0x858458f6 /* some random number */
|
|
#define TMPFS_MAGIC 0x01021994
|
|
#define HUGETLBFS_MAGIC 0x958458f6 /* some random number */
|
|
#define SQUASHFS_MAGIC 0x73717368
|
|
#define ECRYPTFS_SUPER_MAGIC 0xf15f
|
|
#define EFS_SUPER_MAGIC 0x414A53
|
|
#define EXT2_SUPER_MAGIC 0xEF53
|
|
#define EXT3_SUPER_MAGIC 0xEF53
|
|
#define XENFS_SUPER_MAGIC 0xabba1974
|
|
#define EXT4_SUPER_MAGIC 0xEF53
|
|
#define BTRFS_SUPER_MAGIC 0x9123683E
|
|
#define NILFS_SUPER_MAGIC 0x3434
|
|
#define F2FS_SUPER_MAGIC 0xF2F52010
|
|
#define HPFS_SUPER_MAGIC 0xf995e849
|
|
#define ISOFS_SUPER_MAGIC 0x9660
|
|
#define JFFS2_SUPER_MAGIC 0x72b6
|
|
#define PSTOREFS_MAGIC 0x6165676C
|
|
#define EFIVARFS_MAGIC 0xde5e81e4
|
|
#define HOSTFS_SUPER_MAGIC 0x00c0ffee
|
|
#define OVERLAYFS_SUPER_MAGIC 0x794c7630
|
|
|
|
#define MINIX_SUPER_MAGIC 0x137F /* minix v1 fs, 14 char names */
|
|
#define MINIX_SUPER_MAGIC2 0x138F /* minix v1 fs, 30 char names */
|
|
#define MINIX2_SUPER_MAGIC 0x2468 /* minix v2 fs, 14 char names */
|
|
#define MINIX2_SUPER_MAGIC2 0x2478 /* minix v2 fs, 30 char names */
|
|
#define MINIX3_SUPER_MAGIC 0x4d5a /* minix v3 fs, 60 char names */
|
|
|
|
#define MSDOS_SUPER_MAGIC 0x4d44 /* MD */
|
|
#define NCP_SUPER_MAGIC 0x564c /* Guess, what 0x564c is :-) */
|
|
#define NFS_SUPER_MAGIC 0x6969
|
|
#define OPENPROM_SUPER_MAGIC 0x9fa1
|
|
#define QNX4_SUPER_MAGIC 0x002f /* qnx4 fs detection */
|
|
#define QNX6_SUPER_MAGIC 0x68191122 /* qnx6 fs detection */
|
|
|
|
#define REISERFS_SUPER_MAGIC 0x52654973 /* used by gcc */
|
|
/* used by file system utilities that
|
|
look at the superblock, etc. */
|
|
#define REISERFS_SUPER_MAGIC_STRING "ReIsErFs"
|
|
#define REISER2FS_SUPER_MAGIC_STRING "ReIsEr2Fs"
|
|
#define REISER2FS_JR_SUPER_MAGIC_STRING "ReIsEr3Fs"
|
|
|
|
#define SMB_SUPER_MAGIC 0x517B
|
|
#define CGROUP_SUPER_MAGIC 0x27e0eb
|
|
#define CGROUP2_SUPER_MAGIC 0x63677270
|
|
|
|
|
|
#define STACK_END_MAGIC 0x57AC6E9D
|
|
|
|
#define TRACEFS_MAGIC 0x74726163
|
|
|
|
#define V9FS_MAGIC 0x01021997
|
|
|
|
#define BDEVFS_MAGIC 0x62646576
|
|
#define BINFMTFS_MAGIC 0x42494e4d
|
|
#define DEVPTS_SUPER_MAGIC 0x1cd1
|
|
#define FUTEXFS_SUPER_MAGIC 0xBAD1DEA
|
|
#define PIPEFS_MAGIC 0x50495045
|
|
#define PROC_SUPER_MAGIC 0x9fa0
|
|
#define SOCKFS_MAGIC 0x534F434B
|
|
#define SYSFS_MAGIC 0x62656572
|
|
#define USBDEVICE_SUPER_MAGIC 0x9fa2
|
|
#define MTD_INODE_FS_MAGIC 0x11307854
|
|
#define ANON_INODE_FS_MAGIC 0x09041934
|
|
#define BTRFS_TEST_MAGIC 0x73727279
|
|
#define NSFS_MAGIC 0x6e736673
|
|
#define BPF_FS_MAGIC 0xcafe4a11
|
|
/* Since UDF 2.01 is ISO 13346 based... */
|
|
#define UDF_SUPER_MAGIC 0x15013346
|
|
#define BALLOON_KVM_MAGIC 0x13661366
|
|
#define ZSMALLOC_MAGIC 0x58295829
|
|
|
|
#endif /* __LINUX_MAGIC_H__ */
|