Files
jianzhou b82a5df2dc Merge android-4.9.165 (72b54df) into msm-4.9
* refs/heads/tmp-72b54df:
  Linux 4.9.165
  KVM: X86: Fix residual mmio emulation request to userspace
  KVM: nVMX: Ignore limit checks on VMX instructions using flat segments
  KVM: nVMX: Sign extend displacements of VMX instr's mem operands
  drm/radeon/evergreen_cs: fix missing break in switch statement
  media: uvcvideo: Avoid NULL pointer dereference at the end of streaming
  rcu: Do RCU GP kthread self-wakeup from softirq and interrupt
  md: Fix failed allocation of md_register_thread
  perf intel-pt: Fix divide by zero when TSC is not available
  perf intel-pt: Fix overlap calculation for padding
  perf auxtrace: Define auxtrace record alignment
  perf intel-pt: Fix CYC timestamp calculation after OVF
  bcache: never writeback a discard operation
  PM / wakeup: Rework wakeup source timer cancellation
  nfsd: fix wrong check in write_v4_end_grace()
  nfsd: fix memory corruption caused by readdir
  NFS: Don't recoalesce on error in nfs_pageio_complete_mirror()
  NFS: Fix an I/O request leakage in nfs_do_recoalesce
  NFS: Fix I/O request leakages
  dm: fix to_sector() for 32bit
  ARM: s3c24xx: Fix boolean expressions in osiris_dvs_notify
  powerpc/ptrace: Simplify vr_get/set() to avoid GCC warning
  powerpc: Fix 32-bit KVM-PR lockup and host crash with MacOS guest
  powerpc/83xx: Also save/restore SPRG4-7 during suspend
  powerpc/powernv: Make opal log only readable by root
  powerpc/wii: properly disable use of BATs when requested.
  powerpc/32: Clear on-stack exception marker upon exception return
  jbd2: fix compile warning when using JBUFFER_TRACE
  jbd2: clear dirty flag when revoking a buffer from an older transaction
  serial: 8250_pci: Have ACCES cards that use the four port Pericom PI7C9X7954 chip use the pci_pericom_setup()
  serial: 8250_pci: Fix number of ports for ACCES serial cards
  8250: FIX Fourth port offset of Pericom PI7C9X7954 boards
  serial: 8250_of: assume reg-shift of 2 for mrvl,mmp-uart
  serial: uartps: Fix stuck ISR if RX disabled with non-empty FIFO
  drm/i915: Relax mmap VMA check
  i2c: tegra: fix maximum transfer size
  parport_pc: fix find_superio io compare code, should use equal test.
  intel_th: Don't reference unassigned outputs
  device property: Fix the length used in PROPERTY_ENTRY_STRING()
  kernel/sysctl.c: add missing range check in do_proc_dointvec_minmax_conv
  mm/vmalloc: fix size check for remap_vmalloc_range_partial()
  mm: hwpoison: fix thp split handing in soft_offline_in_use_page()
  nfit: acpi_nfit_ctl(): Check out_obj->type in the right place
  clk: ingenic: Fix doc of ingenic_cgu_div_info
  clk: ingenic: Fix round_rate misbehaving with non-integer dividers
  clk: clk-twl6040: Fix imprecise external abort for pdmclk
  ext2: Fix underflow in ext2_max_size()
  ext4: fix crash during online resizing
  cpufreq: pxa2xx: remove incorrect __init annotation
  cpufreq: tegra124: add missing of_node_put()
  libertas_tf: don't set URB_ZERO_PACKET on IN USB transfer
  crypto: pcbc - remove bogus memcpy()s with src == dest
  Btrfs: fix corruption reading shared and compressed extents after hole punching
  btrfs: ensure that a DUP or RAID1 block group has exactly two stripes
  m68k: Add -ffreestanding to CFLAGS
  splice: don't merge into linked buffers
  fs/devpts: always delete dcache dentry-s in dput()
  scsi: target/iscsi: Avoid iscsit_release_commands_from_conn() deadlock
  scsi: sd: Optimal I/O size should be a multiple of physical block size
  scsi: virtio_scsi: don't send sc payload with tmfs
  s390/virtio: handle find on invalid queue gracefully
  clocksource/drivers/exynos_mct: Clear timer interrupt when shutdown
  clocksource/drivers/exynos_mct: Move one-shot check from tick clear to ISR
  regulator: s2mpa01: Fix step values for some LDOs
  regulator: s2mps11: Fix steps for buck7, buck8 and LDO35
  spi: pxa2xx: Setup maximum supported DMA transfer length
  spi: ti-qspi: Fix mmap read when more than one CS in use
  ACPI / device_sysfs: Avoid OF modalias creation for removed device
  tracing: Do not free iter->trace in fail path of tracing_open_pipe()
  tracing: Use strncpy instead of memcpy for string keys in hist triggers
  CIFS: Fix read after write for files with read caching
  CIFS: Do not reset lease state to NONE on lease break
  crypto: arm64/aes-ccm - fix logical bug in AAD MAC handling
  crypto: hash - set CRYPTO_TFM_NEED_KEY if ->setkey() fails
  libnvdimm: Fix altmap reservation size calculation
  libnvdimm/pmem: Honor force_raw for legacy pmem regions
  libnvdimm/label: Clear 'updating' flag after label-set update
  stm class: Prevent division by zero
  tmpfs: fix uninitialized return value in shmem_link
  net: set static variable an initial value in atl2_probe()
  nfp: bpf: fix ALU32 high bits clearance bug
  nfp: bpf: fix code-gen bug on BPF_ALU | BPF_XOR | BPF_K
  net: thunderx: make CFG_DONE message to run through generic send-ack sequence
  mac80211_hwsim: propagate genlmsg_reply return code
  phonet: fix building with clang
  ARC: uacces: remove lp_start, lp_end from clobber list
  ARCv2: lib: memcpy: fix doing prefetchw outside of buffer
  tmpfs: fix link accounting when a tmpfile is linked in
  net: marvell: mvneta: fix DMA debug warning
  arm64: Relax GIC version check during early boot
  ASoC: topology: free created components in tplg load error
  net: mv643xx_eth: disable clk on error path in mv643xx_eth_shared_probe()
  qmi_wwan: apply SET_DTR quirk to Sierra WP7607
  pinctrl: meson: meson8b: fix the sdxc_a data 1..3 pins
  net: systemport: Fix reception of BPDUs
  scsi: libiscsi: Fix race between iscsi_xmit_task and iscsi_complete_task
  assoc_array: Fix shortcut creation
  ARM: 8824/1: fix a migrating irq bug when hotplug cpu
  clk: sunxi: A31: Fix wrong AHB gate number
  Input: st-keyscan - fix potential zalloc NULL dereference
  i2c: cadence: Fix the hold bit setting
  net: hns: Fix object reference leaks in hns_dsaf_roce_reset()
  mm: page_alloc: fix ref bias in page_frag_alloc() for 1-byte allocs
  mm/gup: fix gup_pmd_range() for dax
  floppy: check_events callback should not return a negative number
  Input: matrix_keypad - use flush_delayed_work()
  Input: cap11xx - switch to using set_brightness_blocking()
  ARM: OMAP2+: Variable "reg" in function omap4_dsi_mux_pads() could be uninitialized
  s390/dasd: fix using offset into zero size array error
  gpu: ipu-v3: Fix CSI offsets for imx53
  gpu: ipu-v3: Fix i.MX51 CSI control registers offset
  crypto: ahash - fix another early termination in hash walk
  crypto: caam - fixed handling of sg list
  stm class: Fix an endless loop in channel allocation
  iio: adc: exynos-adc: Fix NULL pointer exception on unbind
  ASoC: fsl_esai: fix register setting issue in RIGHT_J mode
  9p/net: fix memory leak in p9_client_create
  9p: use inode->i_lock to protect i_size_write() under 32-bit
  media: videobuf2-v4l2: drop WARN_ON in vb2_warn_zero_bytesused()
  FROMLIST: psi: introduce psi monitor
  FROMLIST: refactor header includes to allow kthread.h inclusion in psi_types.h
  FROMLIST: psi: track changed states
  FROMLIST: psi: split update_stats into parts
  FROMLIST: psi: rename psi fields in preparation for psi trigger addition
  FROMLIST: psi: make psi_enable static
  FROMLIST: psi: introduce state_mask to represent stalled psi states
  ANDROID: cuttlefish_defconfig: Enable CONFIG_PSI
  BACKPORT: kernel: cgroup: add poll file operation
  BACKPORT: fs: kernfs: add poll file operation
  UPSTREAM: psi: avoid divide-by-zero crash inside virtual machines
  UPSTREAM: psi: clarify the Kconfig text for the default-disable option
  UPSTREAM: psi: fix aggregation idle shut-off
  UPSTREAM: cgroup add cftype->open/release() callbacks
  UPSTREAM: kernfs: Check KERNFS_HAS_RELEASE before calling kernfs_release_file()
  UPSTREAM: kernfs: fix locking around kernfs_ops->release() callback
  UPSTREAM: kernfs: add kernfs_ops->open/release() callbacks
  UPSTREAM: psi: fix reference to kernel commandline enable
  BACKPORT: psi: make disabling/enabling easier for vendor kernels
  UPSTREAM: kernel/sched/psi.c: simplify cgroup_move_task()
  BACKPORT: psi: cgroup support
  UPSTREAM: psi: pressure stall information for CPU, memory, and IO
  BACKPORT: sched: introduce this_rq_lock_irq()
  BACKPORT: sched: sched.h: make rq locking and clock functions available in stats.h
  UPSTREAM: sched: loadavg: make calc_load_n() public
  UPSTREAM: sched: loadavg: consolidate LOAD_INT, LOAD_FRAC, CALC_LOAD
  BACKPORT: delayacct: track delays from thrashing cache pages
  BACKPORT: mm: workingset: tell cache transitions from workingset thrashing
  BACKPORT: cgroup: misc changes
  UPSTREAM: sched/headers: Remove <linux/sched.h> from <linux/sched/loadavg.h>
  UPSTREAM: sched/headers: Move loadavg related definitions from <linux/sched.h> to <linux/sched/loadavg.h>
  UPSTREAM: sched/headers, delayacct: Move the 'struct task_delay_info' definition from <linux/sched.h> to <linux/delayacct.h>
  UPSTREAM: sched/headers: Prepare for new header dependencies before moving code to <linux/sched/loadavg.h>
  BACKPORT: sched/core: Add wrappers for lockdep_(un)pin_lock()
  UPSTREAM: Avoid page waitqueue race leaving possible page locker waiting
  UPSTREAM: mm: add PageWaiters indicating tasks are waiting for a page bit
  UPSTREAM: workqueue: make workqueue available early during boot
  ANDROID: ion_dummy_driver: Remove SYSTEM_CONTIG heap
  ANDROID: ion_dummy_driver: Rework ion_dummy_driver to avoid direct indexing into the heaps
  ANDROID: ion_dummy_driver: Use IS_ERR_OR_NULL() before destroying heaps
  ANDROID: sched/fair: fix energy compute when a cluster is only a cpu core in multi-cluster system

Conflicts:
	arch/arm/kernel/irq.c
	drivers/scsi/sd.c
	include/linux/cgroup.h
	include/linux/sched.h
	kernel/sched/Makefile
	kernel/sched/core.c
	mm/page_alloc.c

Change-Id: I387345d8f6d2145e2456fbead266c897475dfb4c
Signed-off-by: jianzhou <jianzhou@codeaurora.org>
2019-05-21 17:01:55 +08:00

390 lines
12 KiB
C

/*
* include/linux/writeback.h
*/
#ifndef WRITEBACK_H
#define WRITEBACK_H
#include <linux/sched.h>
#include <linux/workqueue.h>
#include <linux/fs.h>
#include <linux/flex_proportions.h>
#include <linux/backing-dev-defs.h>
DECLARE_PER_CPU(int, dirty_throttle_leaks);
/*
* The 1/4 region under the global dirty thresh is for smooth dirty throttling:
*
* (thresh - thresh/DIRTY_FULL_SCOPE, thresh)
*
* Further beyond, all dirtier tasks will enter a loop waiting (possibly long
* time) for the dirty pages to drop, unless written enough pages.
*
* The global dirty threshold is normally equal to the global dirty limit,
* except when the system suddenly allocates a lot of anonymous memory and
* knocks down the global dirty threshold quickly, in which case the global
* dirty limit will follow down slowly to prevent livelocking all dirtier tasks.
*/
#define DIRTY_SCOPE 8
#define DIRTY_FULL_SCOPE (DIRTY_SCOPE / 2)
struct backing_dev_info;
/*
* fs/fs-writeback.c
*/
enum writeback_sync_modes {
WB_SYNC_NONE, /* Don't wait on anything */
WB_SYNC_ALL, /* Wait on every mapping */
};
/*
* why some writeback work was initiated
*/
enum wb_reason {
WB_REASON_BACKGROUND,
WB_REASON_VMSCAN,
WB_REASON_SYNC,
WB_REASON_PERIODIC,
WB_REASON_LAPTOP_TIMER,
WB_REASON_FREE_MORE_MEM,
WB_REASON_FS_FREE_SPACE,
/*
* There is no bdi forker thread any more and works are done
* by emergency worker, however, this is TPs userland visible
* and we'll be exposing exactly the same information,
* so it has a mismatch name.
*/
WB_REASON_FORKER_THREAD,
WB_REASON_MAX,
};
/*
* A control structure which tells the writeback code what to do. These are
* always on the stack, and hence need no locking. They are always initialised
* in a manner such that unspecified fields are set to zero.
*/
struct writeback_control {
long nr_to_write; /* Write this many pages, and decrement
this for each page written */
long pages_skipped; /* Pages which were not written */
/*
* For a_ops->writepages(): if start or end are non-zero then this is
* a hint that the filesystem need only write out the pages inside that
* byterange. The byte at `end' is included in the writeout request.
*/
loff_t range_start;
loff_t range_end;
enum writeback_sync_modes sync_mode;
unsigned for_kupdate:1; /* A kupdate writeback */
unsigned for_background:1; /* A background writeback */
unsigned tagged_writepages:1; /* tag-and-write to avoid livelock */
unsigned for_reclaim:1; /* Invoked from the page allocator */
unsigned range_cyclic:1; /* range_start is cyclic */
unsigned for_sync:1; /* sync(2) WB_SYNC_ALL writeback */
#ifdef CONFIG_CGROUP_WRITEBACK
struct bdi_writeback *wb; /* wb this writeback is issued under */
struct inode *inode; /* inode being written out */
/* foreign inode detection, see wbc_detach_inode() */
int wb_id; /* current wb id */
int wb_lcand_id; /* last foreign candidate wb id */
int wb_tcand_id; /* this foreign candidate wb id */
size_t wb_bytes; /* bytes written by current wb */
size_t wb_lcand_bytes; /* bytes written by last candidate */
size_t wb_tcand_bytes; /* bytes written by this candidate */
#endif
};
/*
* A wb_domain represents a domain that wb's (bdi_writeback's) belong to
* and are measured against each other in. There always is one global
* domain, global_wb_domain, that every wb in the system is a member of.
* This allows measuring the relative bandwidth of each wb to distribute
* dirtyable memory accordingly.
*/
struct wb_domain {
spinlock_t lock;
/*
* Scale the writeback cache size proportional to the relative
* writeout speed.
*
* We do this by keeping a floating proportion between BDIs, based
* on page writeback completions [end_page_writeback()]. Those
* devices that write out pages fastest will get the larger share,
* while the slower will get a smaller share.
*
* We use page writeout completions because we are interested in
* getting rid of dirty pages. Having them written out is the
* primary goal.
*
* We introduce a concept of time, a period over which we measure
* these events, because demand can/will vary over time. The length
* of this period itself is measured in page writeback completions.
*/
struct fprop_global completions;
struct timer_list period_timer; /* timer for aging of completions */
unsigned long period_time;
/*
* The dirtyable memory and dirty threshold could be suddenly
* knocked down by a large amount (eg. on the startup of KVM in a
* swapless system). This may throw the system into deep dirty
* exceeded state and throttle heavy/light dirtiers alike. To
* retain good responsiveness, maintain global_dirty_limit for
* tracking slowly down to the knocked down dirty threshold.
*
* Both fields are protected by ->lock.
*/
unsigned long dirty_limit_tstamp;
unsigned long dirty_limit;
};
/**
* wb_domain_size_changed - memory available to a wb_domain has changed
* @dom: wb_domain of interest
*
* This function should be called when the amount of memory available to
* @dom has changed. It resets @dom's dirty limit parameters to prevent
* the past values which don't match the current configuration from skewing
* dirty throttling. Without this, when memory size of a wb_domain is
* greatly reduced, the dirty throttling logic may allow too many pages to
* be dirtied leading to consecutive unnecessary OOMs and may get stuck in
* that situation.
*/
static inline void wb_domain_size_changed(struct wb_domain *dom)
{
spin_lock(&dom->lock);
dom->dirty_limit_tstamp = jiffies;
dom->dirty_limit = 0;
spin_unlock(&dom->lock);
}
/*
* fs/fs-writeback.c
*/
struct bdi_writeback;
void writeback_inodes_sb(struct super_block *, enum wb_reason reason);
void writeback_inodes_sb_nr(struct super_block *, unsigned long nr,
enum wb_reason reason);
bool try_to_writeback_inodes_sb(struct super_block *, enum wb_reason reason);
bool try_to_writeback_inodes_sb_nr(struct super_block *, unsigned long nr,
enum wb_reason reason);
void sync_inodes_sb(struct super_block *);
void wakeup_flusher_threads(long nr_pages, enum wb_reason reason);
void inode_wait_for_writeback(struct inode *inode);
/* writeback.h requires fs.h; it, too, is not included from here. */
static inline void wait_on_inode(struct inode *inode)
{
might_sleep();
wait_on_bit(&inode->i_state, __I_NEW, TASK_UNINTERRUPTIBLE);
}
#ifdef CONFIG_CGROUP_WRITEBACK
#include <linux/cgroup.h>
#include <linux/bio.h>
void __inode_attach_wb(struct inode *inode, struct page *page);
void wbc_attach_and_unlock_inode(struct writeback_control *wbc,
struct inode *inode)
__releases(&inode->i_lock);
void wbc_detach_inode(struct writeback_control *wbc);
void wbc_account_io(struct writeback_control *wbc, struct page *page,
size_t bytes);
void cgroup_writeback_umount(void);
/**
* inode_attach_wb - associate an inode with its wb
* @inode: inode of interest
* @page: page being dirtied (may be NULL)
*
* If @inode doesn't have its wb, associate it with the wb matching the
* memcg of @page or, if @page is NULL, %current. May be called w/ or w/o
* @inode->i_lock.
*/
static inline void inode_attach_wb(struct inode *inode, struct page *page)
{
if (!inode->i_wb)
__inode_attach_wb(inode, page);
}
/**
* inode_detach_wb - disassociate an inode from its wb
* @inode: inode of interest
*
* @inode is being freed. Detach from its wb.
*/
static inline void inode_detach_wb(struct inode *inode)
{
if (inode->i_wb) {
WARN_ON_ONCE(!(inode->i_state & I_CLEAR));
wb_put(inode->i_wb);
inode->i_wb = NULL;
}
}
/**
* wbc_attach_fdatawrite_inode - associate wbc and inode for fdatawrite
* @wbc: writeback_control of interest
* @inode: target inode
*
* This function is to be used by __filemap_fdatawrite_range(), which is an
* alternative entry point into writeback code, and first ensures @inode is
* associated with a bdi_writeback and attaches it to @wbc.
*/
static inline void wbc_attach_fdatawrite_inode(struct writeback_control *wbc,
struct inode *inode)
{
spin_lock(&inode->i_lock);
inode_attach_wb(inode, NULL);
wbc_attach_and_unlock_inode(wbc, inode);
}
/**
* wbc_init_bio - writeback specific initializtion of bio
* @wbc: writeback_control for the writeback in progress
* @bio: bio to be initialized
*
* @bio is a part of the writeback in progress controlled by @wbc. Perform
* writeback specific initialization. This is used to apply the cgroup
* writeback context.
*/
static inline void wbc_init_bio(struct writeback_control *wbc, struct bio *bio)
{
/*
* pageout() path doesn't attach @wbc to the inode being written
* out. This is intentional as we don't want the function to block
* behind a slow cgroup. Ultimately, we want pageout() to kick off
* regular writeback instead of writing things out itself.
*/
if (wbc->wb)
bio_associate_blkcg(bio, wbc->wb->blkcg_css);
}
#else /* CONFIG_CGROUP_WRITEBACK */
static inline void inode_attach_wb(struct inode *inode, struct page *page)
{
}
static inline void inode_detach_wb(struct inode *inode)
{
}
static inline void wbc_attach_and_unlock_inode(struct writeback_control *wbc,
struct inode *inode)
__releases(&inode->i_lock)
{
spin_unlock(&inode->i_lock);
}
static inline void wbc_attach_fdatawrite_inode(struct writeback_control *wbc,
struct inode *inode)
{
}
static inline void wbc_detach_inode(struct writeback_control *wbc)
{
}
static inline void wbc_init_bio(struct writeback_control *wbc, struct bio *bio)
{
}
static inline void wbc_account_io(struct writeback_control *wbc,
struct page *page, size_t bytes)
{
}
static inline void cgroup_writeback_umount(void)
{
}
#endif /* CONFIG_CGROUP_WRITEBACK */
/*
* mm/page-writeback.c
*/
#ifdef CONFIG_BLOCK
void laptop_io_completion(struct backing_dev_info *info);
void laptop_sync_completion(void);
void laptop_mode_sync(struct work_struct *work);
void laptop_mode_timer_fn(unsigned long data);
#else
static inline void laptop_sync_completion(void) { }
#endif
bool node_dirty_ok(struct pglist_data *pgdat);
int wb_domain_init(struct wb_domain *dom, gfp_t gfp);
#ifdef CONFIG_CGROUP_WRITEBACK
void wb_domain_exit(struct wb_domain *dom);
#endif
extern struct wb_domain global_wb_domain;
/* These are exported to sysctl. */
extern int dirty_background_ratio;
extern unsigned long dirty_background_bytes;
extern int vm_dirty_ratio;
extern unsigned long vm_dirty_bytes;
extern unsigned int dirty_writeback_interval;
extern unsigned int dirty_expire_interval;
extern unsigned int dirtytime_expire_interval;
extern int vm_highmem_is_dirtyable;
extern int block_dump;
extern int laptop_mode;
extern int dirty_background_ratio_handler(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp,
loff_t *ppos);
extern int dirty_background_bytes_handler(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp,
loff_t *ppos);
extern int dirty_ratio_handler(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp,
loff_t *ppos);
extern int dirty_bytes_handler(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp,
loff_t *ppos);
int dirtytime_interval_handler(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos);
struct ctl_table;
int dirty_writeback_centisecs_handler(struct ctl_table *, int,
void __user *, size_t *, loff_t *);
void global_dirty_limits(unsigned long *pbackground, unsigned long *pdirty);
unsigned long wb_calc_thresh(struct bdi_writeback *wb, unsigned long thresh);
void wb_update_bandwidth(struct bdi_writeback *wb, unsigned long start_time);
void balance_dirty_pages_ratelimited(struct address_space *mapping);
bool wb_over_bg_thresh(struct bdi_writeback *wb);
typedef int (*writepage_t)(struct page *page, struct writeback_control *wbc,
void *data);
int generic_writepages(struct address_space *mapping,
struct writeback_control *wbc);
void tag_pages_for_writeback(struct address_space *mapping,
pgoff_t start, pgoff_t end);
int write_cache_pages(struct address_space *mapping,
struct writeback_control *wbc, writepage_t writepage,
void *data);
int do_writepages(struct address_space *mapping, struct writeback_control *wbc);
void writeback_set_ratelimit(void);
void tag_pages_for_writeback(struct address_space *mapping,
pgoff_t start, pgoff_t end);
void account_page_redirty(struct page *page);
void sb_mark_inode_writeback(struct inode *inode);
void sb_clear_inode_writeback(struct inode *inode);
#endif /* WRITEBACK_H */