android_kernel_oneplus_msm8998/include/linux/backing-dev.h
Srinivasarao P ee76c85f71 Merge android-4.4.129 (b1c4836) into msm-4.4
* refs/heads/tmp-b1c4836
  Linux 4.4.129
  writeback: safer lock nesting
  fanotify: fix logic of events on child
  ext4: bugfix for mmaped pages in mpage_release_unused_pages()
  mm/filemap.c: fix NULL pointer in page_cache_tree_insert()
  mm: allow GFP_{FS,IO} for page_cache_read page cache allocation
  autofs: mount point create should honour passed in mode
  Don't leak MNT_INTERNAL away from internal mounts
  rpc_pipefs: fix double-dput()
  hypfs_kill_super(): deal with failed allocations
  jffs2_kill_sb(): deal with failed allocations
  powerpc/lib: Fix off-by-one in alternate feature patching
  powerpc/eeh: Fix enabling bridge MMIO windows
  MIPS: memset.S: Fix clobber of v1 in last_fixup
  MIPS: memset.S: Fix return of __clear_user from Lpartial_fixup
  MIPS: memset.S: EVA & fault support for small_memset
  MIPS: uaccess: Add micromips clobbers to bzero invocation
  HID: hidraw: Fix crash on HIDIOCGFEATURE with a destroyed device
  ALSA: hda - New VIA controller suppor no-snoop path
  ALSA: rawmidi: Fix missing input substream checks in compat ioctls
  ALSA: line6: Use correct endpoint type for midi output
  ext4: fix deadlock between inline_data and ext4_expand_extra_isize_ea()
  ext4: fix crashes in dioread_nolock mode
  drm/radeon: Fix PCIe lane width calculation
  ext4: don't allow r/w mounts if metadata blocks overlap the superblock
  vfio/pci: Virtualize Maximum Read Request Size
  vfio/pci: Virtualize Maximum Payload Size
  vfio-pci: Virtualize PCIe & AF FLR
  ALSA: pcm: Fix endless loop for XRUN recovery in OSS emulation
  ALSA: pcm: Fix mutex unbalance in OSS emulation ioctls
  ALSA: pcm: Return -EBUSY for OSS ioctls changing busy streams
  ALSA: pcm: Avoid potential races between OSS ioctls and read/write
  ALSA: pcm: Use ERESTARTSYS instead of EINTR in OSS emulation
  ALSA: oss: consolidate kmalloc/memset 0 call to kzalloc
  watchdog: f71808e_wdt: Fix WD_EN register read
  thermal: imx: Fix race condition in imx_thermal_probe()
  clk: bcm2835: De-assert/assert PLL reset signal when appropriate
  clk: mvebu: armada-38x: add support for missing clocks
  clk: mvebu: armada-38x: add support for 1866MHz variants
  mmc: jz4740: Fix race condition in IRQ mask update
  iommu/vt-d: Fix a potential memory leak
  um: Use POSIX ucontext_t instead of struct ucontext
  dmaengine: at_xdmac: fix rare residue corruption
  IB/srp: Fix completion vector assignment algorithm
  IB/srp: Fix srp_abort()
  ALSA: pcm: Fix UAF at PCM release via PCM timer access
  RDMA/ucma: Don't allow setting RDMA_OPTION_IB_PATH without an RDMA device
  ext4: fail ext4_iget for root directory if unallocated
  ext4: don't update checksum of new initialized bitmaps
  jbd2: if the journal is aborted then don't allow update of the log tail
  random: use a tighter cap in credit_entropy_bits_safe()
  thunderbolt: Resume control channel after hibernation image is created
  ASoC: ssm2602: Replace reg_default_raw with reg_default
  HID: core: Fix size as type u32
  HID: Fix hid_report_len usage
  powerpc/powernv: Fix OPAL NVRAM driver OPAL_BUSY loops
  powerpc/powernv: define a standard delay for OPAL_BUSY type retry loops
  powerpc/64: Fix smp_wmb barrier definition use use lwsync consistently
  powerpc/powernv: Handle unknown OPAL errors in opal_nvram_write()
  HID: i2c-hid: fix size check and type usage
  usb: dwc3: pci: Properly cleanup resource
  USB:fix USB3 devices behind USB3 hubs not resuming at hibernate thaw
  ACPI / hotplug / PCI: Check presence of slot itself in get_slot_status()
  ACPI / video: Add quirk to force acpi-video backlight on Samsung 670Z5E
  regmap: Fix reversed bounds check in regmap_raw_write()
  xen-netfront: Fix hang on device removal
  ARM: dts: at91: sama5d4: fix pinctrl compatible string
  ARM: dts: at91: at91sam9g25: fix mux-mask pinctrl property
  usb: musb: gadget: misplaced out of bounds check
  mm, slab: reschedule cache_reap() on the same CPU
  ipc/shm: fix use-after-free of shm file via remap_file_pages()
  resource: fix integer overflow at reallocation
  fs/reiserfs/journal.c: add missing resierfs_warning() arg
  ubi: Reject MLC NAND
  ubi: Fix error for write access
  ubi: fastmap: Don't flush fastmap work on detach
  ubifs: Check ubifs_wbuf_sync() return code
  tty: make n_tty_read() always abort if hangup is in progress
  x86/hweight: Don't clobber %rdi
  x86/hweight: Get rid of the special calling convention
  lan78xx: Correctly indicate invalid OTP
  slip: Check if rstate is initialized before uncompressing
  cdc_ether: flag the Cinterion AHS8 modem by gemalto as WWAN
  hwmon: (ina2xx) Fix access to uninitialized mutex
  rtl8187: Fix NULL pointer dereference in priv->conf_mutex
  getname_kernel() needs to make sure that ->name != ->iname in long case
  s390/ipl: ensure loadparm valid flag is set
  s390/qdio: don't merge ERROR output buffers
  s390/qdio: don't retry EQBS after CCQ 96
  block/loop: fix deadlock after loop_set_status
  Revert "perf tests: Decompress kernel module before objdump"
  radeon: hide pointless #warning when compile testing
  perf intel-pt: Fix timestamp following overflow
  perf intel-pt: Fix error recovery from missing TIP packet
  perf intel-pt: Fix sync_switch
  perf intel-pt: Fix overlap detection to identify consecutive buffers correctly
  parisc: Fix out of array access in match_pci_device()
  media: v4l2-compat-ioctl32: don't oops on overlay
  f2fs: check cap_resource only for data blocks
  Revert "f2fs: introduce f2fs_set_page_dirty_nobuffer"
  f2fs: clear PageError on writepage
  UPSTREAM: timer: Export destroy_hrtimer_on_stack()
  BACKPORT: dm verity: add 'check_at_most_once' option to only validate hashes once
  f2fs: call unlock_new_inode() before d_instantiate()
  f2fs: refactor read path to allow multiple postprocessing steps
  fscrypt: allow synchronous bio decryption

Change-Id: I45f4ac10734d92023b53118d83dcd6c83974a283
Signed-off-by: Srinivasarao P <spathi@codeaurora.org>
2018-04-24 19:07:57 +05:30

529 lines
14 KiB
C

/*
* include/linux/backing-dev.h
*
* low-level device information and state which is propagated up through
* to high-level code.
*/
#ifndef _LINUX_BACKING_DEV_H
#define _LINUX_BACKING_DEV_H
#include <linux/kernel.h>
#include <linux/fs.h>
#include <linux/sched.h>
#include <linux/blkdev.h>
#include <linux/writeback.h>
#include <linux/blk-cgroup.h>
#include <linux/backing-dev-defs.h>
#include <linux/slab.h>
int __must_check bdi_init(struct backing_dev_info *bdi);
static inline struct backing_dev_info *bdi_get(struct backing_dev_info *bdi)
{
kref_get(&bdi->refcnt);
return bdi;
}
void bdi_put(struct backing_dev_info *bdi);
__printf(3, 4)
int bdi_register(struct backing_dev_info *bdi, struct device *parent,
const char *fmt, ...);
int bdi_register_dev(struct backing_dev_info *bdi, dev_t dev);
int bdi_register_owner(struct backing_dev_info *bdi, struct device *owner);
void bdi_unregister(struct backing_dev_info *bdi);
int __must_check bdi_setup_and_register(struct backing_dev_info *, char *);
void bdi_destroy(struct backing_dev_info *bdi);
struct backing_dev_info *bdi_alloc_node(gfp_t gfp_mask, int node_id);
void wb_start_writeback(struct bdi_writeback *wb, long nr_pages,
bool range_cyclic, enum wb_reason reason);
void wb_start_background_writeback(struct bdi_writeback *wb);
void wb_workfn(struct work_struct *work);
void wb_wakeup_delayed(struct bdi_writeback *wb);
extern spinlock_t bdi_lock;
extern struct list_head bdi_list;
extern struct workqueue_struct *bdi_wq;
static inline bool wb_has_dirty_io(struct bdi_writeback *wb)
{
return test_bit(WB_has_dirty_io, &wb->state);
}
static inline bool bdi_has_dirty_io(struct backing_dev_info *bdi)
{
/*
* @bdi->tot_write_bandwidth is guaranteed to be > 0 if there are
* any dirty wbs. See wb_update_write_bandwidth().
*/
return atomic_long_read(&bdi->tot_write_bandwidth);
}
static inline void __add_wb_stat(struct bdi_writeback *wb,
enum wb_stat_item item, s64 amount)
{
__percpu_counter_add(&wb->stat[item], amount, WB_STAT_BATCH);
}
static inline void __inc_wb_stat(struct bdi_writeback *wb,
enum wb_stat_item item)
{
__add_wb_stat(wb, item, 1);
}
static inline void inc_wb_stat(struct bdi_writeback *wb, enum wb_stat_item item)
{
unsigned long flags;
local_irq_save(flags);
__inc_wb_stat(wb, item);
local_irq_restore(flags);
}
static inline void __dec_wb_stat(struct bdi_writeback *wb,
enum wb_stat_item item)
{
__add_wb_stat(wb, item, -1);
}
static inline void dec_wb_stat(struct bdi_writeback *wb, enum wb_stat_item item)
{
unsigned long flags;
local_irq_save(flags);
__dec_wb_stat(wb, item);
local_irq_restore(flags);
}
static inline s64 wb_stat(struct bdi_writeback *wb, enum wb_stat_item item)
{
return percpu_counter_read_positive(&wb->stat[item]);
}
static inline s64 __wb_stat_sum(struct bdi_writeback *wb,
enum wb_stat_item item)
{
return percpu_counter_sum_positive(&wb->stat[item]);
}
static inline s64 wb_stat_sum(struct bdi_writeback *wb, enum wb_stat_item item)
{
s64 sum;
unsigned long flags;
local_irq_save(flags);
sum = __wb_stat_sum(wb, item);
local_irq_restore(flags);
return sum;
}
extern void wb_writeout_inc(struct bdi_writeback *wb);
/*
* maximal error of a stat counter.
*/
static inline unsigned long wb_stat_error(struct bdi_writeback *wb)
{
#ifdef CONFIG_SMP
return nr_cpu_ids * WB_STAT_BATCH;
#else
return 1;
#endif
}
int bdi_set_min_ratio(struct backing_dev_info *bdi, unsigned int min_ratio);
int bdi_set_max_ratio(struct backing_dev_info *bdi, unsigned int max_ratio);
/*
* Flags in backing_dev_info::capability
*
* The first three flags control whether dirty pages will contribute to the
* VM's accounting and whether writepages() should be called for dirty pages
* (something that would not, for example, be appropriate for ramfs)
*
* WARNING: these flags are closely related and should not normally be
* used separately. The BDI_CAP_NO_ACCT_AND_WRITEBACK combines these
* three flags into a single convenience macro.
*
* BDI_CAP_NO_ACCT_DIRTY: Dirty pages shouldn't contribute to accounting
* BDI_CAP_NO_WRITEBACK: Don't write pages back
* BDI_CAP_NO_ACCT_WB: Don't automatically account writeback pages
* BDI_CAP_STRICTLIMIT: Keep number of dirty pages below bdi threshold.
*
* BDI_CAP_CGROUP_WRITEBACK: Supports cgroup-aware writeback.
*/
#define BDI_CAP_NO_ACCT_DIRTY 0x00000001
#define BDI_CAP_NO_WRITEBACK 0x00000002
#define BDI_CAP_NO_ACCT_WB 0x00000004
#define BDI_CAP_STABLE_WRITES 0x00000008
#define BDI_CAP_STRICTLIMIT 0x00000010
#define BDI_CAP_CGROUP_WRITEBACK 0x00000020
#define BDI_CAP_NO_ACCT_AND_WRITEBACK \
(BDI_CAP_NO_WRITEBACK | BDI_CAP_NO_ACCT_DIRTY | BDI_CAP_NO_ACCT_WB)
extern struct backing_dev_info noop_backing_dev_info;
/**
* writeback_in_progress - determine whether there is writeback in progress
* @wb: bdi_writeback of interest
*
* Determine whether there is writeback waiting to be handled against a
* bdi_writeback.
*/
static inline bool writeback_in_progress(struct bdi_writeback *wb)
{
return test_bit(WB_writeback_running, &wb->state);
}
static inline struct backing_dev_info *inode_to_bdi(struct inode *inode)
{
struct super_block *sb;
if (!inode)
return &noop_backing_dev_info;
sb = inode->i_sb;
#ifdef CONFIG_BLOCK
if (sb_is_blkdev_sb(sb))
return blk_get_backing_dev_info(I_BDEV(inode));
#endif
return sb->s_bdi;
}
static inline int wb_congested(struct bdi_writeback *wb, int cong_bits)
{
struct backing_dev_info *bdi = wb->bdi;
if (bdi->congested_fn)
return bdi->congested_fn(bdi->congested_data, cong_bits);
return wb->congested->state & cong_bits;
}
long congestion_wait(int sync, long timeout);
long wait_iff_congested(struct zone *zone, int sync, long timeout);
int pdflush_proc_obsolete(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos);
static inline bool bdi_cap_stable_pages_required(struct backing_dev_info *bdi)
{
return bdi->capabilities & BDI_CAP_STABLE_WRITES;
}
static inline bool bdi_cap_writeback_dirty(struct backing_dev_info *bdi)
{
return !(bdi->capabilities & BDI_CAP_NO_WRITEBACK);
}
static inline bool bdi_cap_account_dirty(struct backing_dev_info *bdi)
{
return !(bdi->capabilities & BDI_CAP_NO_ACCT_DIRTY);
}
static inline bool bdi_cap_account_writeback(struct backing_dev_info *bdi)
{
/* Paranoia: BDI_CAP_NO_WRITEBACK implies BDI_CAP_NO_ACCT_WB */
return !(bdi->capabilities & (BDI_CAP_NO_ACCT_WB |
BDI_CAP_NO_WRITEBACK));
}
static inline bool mapping_cap_writeback_dirty(struct address_space *mapping)
{
return bdi_cap_writeback_dirty(inode_to_bdi(mapping->host));
}
static inline bool mapping_cap_account_dirty(struct address_space *mapping)
{
return bdi_cap_account_dirty(inode_to_bdi(mapping->host));
}
static inline int bdi_sched_wait(void *word)
{
schedule();
return 0;
}
#ifdef CONFIG_CGROUP_WRITEBACK
struct bdi_writeback_congested *
wb_congested_get_create(struct backing_dev_info *bdi, int blkcg_id, gfp_t gfp);
void wb_congested_put(struct bdi_writeback_congested *congested);
struct bdi_writeback *wb_get_create(struct backing_dev_info *bdi,
struct cgroup_subsys_state *memcg_css,
gfp_t gfp);
void wb_memcg_offline(struct mem_cgroup *memcg);
void wb_blkcg_offline(struct blkcg *blkcg);
int inode_congested(struct inode *inode, int cong_bits);
/**
* inode_cgwb_enabled - test whether cgroup writeback is enabled on an inode
* @inode: inode of interest
*
* cgroup writeback requires support from both the bdi and filesystem.
* Also, both memcg and iocg have to be on the default hierarchy. Test
* whether all conditions are met.
*
* Note that the test result may change dynamically on the same inode
* depending on how memcg and iocg are configured.
*/
static inline bool inode_cgwb_enabled(struct inode *inode)
{
struct backing_dev_info *bdi = inode_to_bdi(inode);
return cgroup_subsys_on_dfl(memory_cgrp_subsys) &&
cgroup_subsys_on_dfl(io_cgrp_subsys) &&
bdi_cap_account_dirty(bdi) &&
(bdi->capabilities & BDI_CAP_CGROUP_WRITEBACK) &&
(inode->i_sb->s_iflags & SB_I_CGROUPWB);
}
/**
* wb_find_current - find wb for %current on a bdi
* @bdi: bdi of interest
*
* Find the wb of @bdi which matches both the memcg and blkcg of %current.
* Must be called under rcu_read_lock() which protects the returend wb.
* NULL if not found.
*/
static inline struct bdi_writeback *wb_find_current(struct backing_dev_info *bdi)
{
struct cgroup_subsys_state *memcg_css;
struct bdi_writeback *wb;
memcg_css = task_css(current, memory_cgrp_id);
if (!memcg_css->parent)
return &bdi->wb;
wb = radix_tree_lookup(&bdi->cgwb_tree, memcg_css->id);
/*
* %current's blkcg equals the effective blkcg of its memcg. No
* need to use the relatively expensive cgroup_get_e_css().
*/
if (likely(wb && wb->blkcg_css == task_css(current, io_cgrp_id)))
return wb;
return NULL;
}
/**
* wb_get_create_current - get or create wb for %current on a bdi
* @bdi: bdi of interest
* @gfp: allocation mask
*
* Equivalent to wb_get_create() on %current's memcg. This function is
* called from a relatively hot path and optimizes the common cases using
* wb_find_current().
*/
static inline struct bdi_writeback *
wb_get_create_current(struct backing_dev_info *bdi, gfp_t gfp)
{
struct bdi_writeback *wb;
rcu_read_lock();
wb = wb_find_current(bdi);
if (wb && unlikely(!wb_tryget(wb)))
wb = NULL;
rcu_read_unlock();
if (unlikely(!wb)) {
struct cgroup_subsys_state *memcg_css;
memcg_css = task_get_css(current, memory_cgrp_id);
wb = wb_get_create(bdi, memcg_css, gfp);
css_put(memcg_css);
}
return wb;
}
/**
* inode_to_wb_is_valid - test whether an inode has a wb associated
* @inode: inode of interest
*
* Returns %true if @inode has a wb associated. May be called without any
* locking.
*/
static inline bool inode_to_wb_is_valid(struct inode *inode)
{
return inode->i_wb;
}
/**
* inode_to_wb - determine the wb of an inode
* @inode: inode of interest
*
* Returns the wb @inode is currently associated with. The caller must be
* holding either @inode->i_lock, @inode->i_mapping->tree_lock, or the
* associated wb's list_lock.
*/
static inline struct bdi_writeback *inode_to_wb(struct inode *inode)
{
#ifdef CONFIG_LOCKDEP
WARN_ON_ONCE(debug_locks &&
(!lockdep_is_held(&inode->i_lock) &&
!lockdep_is_held(&inode->i_mapping->tree_lock) &&
!lockdep_is_held(&inode->i_wb->list_lock)));
#endif
return inode->i_wb;
}
/**
* unlocked_inode_to_wb_begin - begin unlocked inode wb access transaction
* @inode: target inode
* @cookie: output param, to be passed to the end function
*
* The caller wants to access the wb associated with @inode but isn't
* holding inode->i_lock, mapping->tree_lock or wb->list_lock. This
* function determines the wb associated with @inode and ensures that the
* association doesn't change until the transaction is finished with
* unlocked_inode_to_wb_end().
*
* The caller must call unlocked_inode_to_wb_end() with *@cookie afterwards and
* can't sleep during the transaction. IRQs may or may not be disabled on
* return.
*/
static inline struct bdi_writeback *
unlocked_inode_to_wb_begin(struct inode *inode, struct wb_lock_cookie *cookie)
{
rcu_read_lock();
/*
* Paired with store_release in inode_switch_wb_work_fn() and
* ensures that we see the new wb if we see cleared I_WB_SWITCH.
*/
cookie->locked = smp_load_acquire(&inode->i_state) & I_WB_SWITCH;
if (unlikely(cookie->locked))
spin_lock_irqsave(&inode->i_mapping->tree_lock, cookie->flags);
/*
* Protected by either !I_WB_SWITCH + rcu_read_lock() or tree_lock.
* inode_to_wb() will bark. Deref directly.
*/
return inode->i_wb;
}
/**
* unlocked_inode_to_wb_end - end inode wb access transaction
* @inode: target inode
* @cookie: @cookie from unlocked_inode_to_wb_begin()
*/
static inline void unlocked_inode_to_wb_end(struct inode *inode,
struct wb_lock_cookie *cookie)
{
if (unlikely(cookie->locked))
spin_unlock_irqrestore(&inode->i_mapping->tree_lock,
cookie->flags);
rcu_read_unlock();
}
#else /* CONFIG_CGROUP_WRITEBACK */
static inline bool inode_cgwb_enabled(struct inode *inode)
{
return false;
}
static inline struct bdi_writeback_congested *
wb_congested_get_create(struct backing_dev_info *bdi, int blkcg_id, gfp_t gfp)
{
atomic_inc(&bdi->wb_congested->refcnt);
return bdi->wb_congested;
}
static inline void wb_congested_put(struct bdi_writeback_congested *congested)
{
if (atomic_dec_and_test(&congested->refcnt))
kfree(congested);
}
static inline struct bdi_writeback *wb_find_current(struct backing_dev_info *bdi)
{
return &bdi->wb;
}
static inline struct bdi_writeback *
wb_get_create_current(struct backing_dev_info *bdi, gfp_t gfp)
{
return &bdi->wb;
}
static inline bool inode_to_wb_is_valid(struct inode *inode)
{
return true;
}
static inline struct bdi_writeback *inode_to_wb(struct inode *inode)
{
return &inode_to_bdi(inode)->wb;
}
static inline struct bdi_writeback *
unlocked_inode_to_wb_begin(struct inode *inode, struct wb_lock_cookie *cookie)
{
return inode_to_wb(inode);
}
static inline void unlocked_inode_to_wb_end(struct inode *inode,
struct wb_lock_cookie *cookie)
{
}
static inline void wb_memcg_offline(struct mem_cgroup *memcg)
{
}
static inline void wb_blkcg_offline(struct blkcg *blkcg)
{
}
static inline int inode_congested(struct inode *inode, int cong_bits)
{
return wb_congested(&inode_to_bdi(inode)->wb, cong_bits);
}
#endif /* CONFIG_CGROUP_WRITEBACK */
static inline int inode_read_congested(struct inode *inode)
{
return inode_congested(inode, 1 << WB_sync_congested);
}
static inline int inode_write_congested(struct inode *inode)
{
return inode_congested(inode, 1 << WB_async_congested);
}
static inline int inode_rw_congested(struct inode *inode)
{
return inode_congested(inode, (1 << WB_sync_congested) |
(1 << WB_async_congested));
}
static inline int bdi_congested(struct backing_dev_info *bdi, int cong_bits)
{
return wb_congested(&bdi->wb, cong_bits);
}
static inline int bdi_read_congested(struct backing_dev_info *bdi)
{
return bdi_congested(bdi, 1 << WB_sync_congested);
}
static inline int bdi_write_congested(struct backing_dev_info *bdi)
{
return bdi_congested(bdi, 1 << WB_async_congested);
}
static inline int bdi_rw_congested(struct backing_dev_info *bdi)
{
return bdi_congested(bdi, (1 << WB_sync_congested) |
(1 << WB_async_congested));
}
#endif /* _LINUX_BACKING_DEV_H */