* refs/heads/tmp-32e6695:
Linux 4.9.155
fanotify: fix handling of events on child sub-directory
fs: don't scan the inode cache before SB_BORN is set
drivers: core: Remove glue dirs from sysfs earlier
cifs: Always resolve hostname before reconnecting
mm: migrate: don't rely on __PageMovable() of newpage after unlocking it
mm: hwpoison: use do_send_sig_info() instead of force_sig()
mm, oom: fix use-after-free in oom_kill_process
kernel/exit.c: release ptraced tasks before zap_pid_ns_processes
mmc: sdhci-iproc: handle mmc_of_parse() errors during probe
platform/x86: asus-nb-wmi: Drop mapping of 0x33 and 0x34 scan codes
platform/x86: asus-nb-wmi: Map 0x35 to KEY_SCREENLOCK
gfs2: Revert "Fix loop in gfs2_rbm_find"
arm64: hibernate: Clean the __hyp_text to PoC after resume
arm64: hyp-stub: Forbid kprobing of the hyp-stub
arm64: kaslr: ensure randomized quantities are clean also when kaslr is off
ARM: cns3xxx: Fix writing to wrong PCI config registers after alignment
fs/dcache: Fix incorrect nr_dentry_unused accounting in shrink_dcache_sb()
CIFS: Do not count -ENODATA as failure for query directory
ipvlan, l3mdev: fix broken l3s mode wrt local routes
l2tp: fix reading optional fields of L2TPv3
l2tp: remove l2specific_len dependency in l2tp_core
net/mlx5e: Allow MAC invalidation while spoofchk is ON
ucc_geth: Reset BQL queue when stopping device
net/rose: fix NULL ax25_cb kernel panic
netrom: switch to sock timer API
net/mlx4_core: Add masking for a few queries on HCA caps
l2tp: copy 4 more bytes to linear part if necessary
ipv6: Consider sk_bound_dev_if when binding a socket to an address
fs: add the fsnotify call to vfs_iter_write
Fix "net: ipv4: do not handle duplicate fragments as overlapping"
BACKPORT: net: dev_is_mac_header_xmit() true for ARPHRD_RAWIP
UPSTREAM: binder: filter out nodes when showing binder procs
UPSTREAM: xfrm: Make set-mark default behavior backward compatible
ANDROID: cuttlefish_defconfig: Enable CONFIG_RTC_HCTOSYS
ANDROID: zram: fix incorrect assignment for access time
UPSTREAM: zram: idle writeback fixes and cleanup
UPSTREAM: zram: writeback throttle
UPSTREAM: zram: add bd_stat statistics
BACKPORT: zram: support idle/huge page writeback
UPSTREAM: zram: introduce ZRAM_IDLE flag
BACKPORT: zram: refactor flags and writeback stuff
UPSTREAM: zram: fix double free backing device
UPSTREAM: zram: fix lockdep warning of free block handling
Linux 4.9.154
btrfs: dev-replace: go back to suspended state if target device is missing
btrfs: fix error handling in btrfs_dev_replace_start
f2fs: read page index before freeing
nvmet-rdma: fix null dereference under heavy load
nvmet-rdma: Add unlikely for response allocated check
s390/smp: Fix calling smp_call_ipl_cpu() from ipl CPU
irqchip/gic-v3-its: Align PCI Multi-MSI allocation on their size
perf unwind: Take pgoff into account when reporting elf to libdwfl
perf unwind: Unwind with libdw doesn't take symfs into account
vt: invoke notifier on screen size change
can: bcm: check timer values before ktime conversion
can: dev: __can_get_echo_skb(): fix bogous check for non-existing skb by removing it
x86/kaslr: Fix incorrect i8254 outb() parameters
x86/selftests/pkeys: Fork() to check for state being preserved
KVM: x86: Fix single-step debugging
dm thin: fix passdown_double_checking_shared_status()
acpi/nfit: Fix command-supported detection
acpi/nfit: Block function zero DSMs
Input: uinput - fix undefined behavior in uinput_validate_absinfo()
compiler.h: enable builtin overflow checkers and add fallback code
Input: xpad - add support for SteelSeries Stratus Duo
CIFS: Fix possible hang during async MTU reads and writes
tty/n_hdlc: fix __might_sleep warning
uart: Fix crash in uart_write and uart_put_char
tty: Handle problem if line discipline does not have receive_buf
staging: rtl8188eu: Add device code for D-Link DWA-121 rev B1
char/mwave: fix potential Spectre v1 vulnerability
s390/smp: fix CPU hotplug deadlock with CPU rescan
s390/early: improve machine detection
ARC: perf: map generic branches to correct hardware condition
ARCv2: lib: memeset: fix doing prefetchw outside of buffer
ASoC: rt5514-spi: Fix potential NULL pointer dereference
ASoC: atom: fix a missing check of snd_pcm_lib_malloc_pages
USB: serial: pl2303: add new PID to support PL2303TB
USB: serial: simple: add Motorola Tetra TPG2200 device id
ipfrag: really prevent allocation on netns exit
net_sched: refetch skb protocol for each filter
net: ipv4: Fix memory leak in network namespace dismantle
vhost: log dirty page correctly
openvswitch: Avoid OOB read when parsing flow nlattrs
net: Fix usage of pskb_trim_rcsum
net: bridge: Fix ethernet header pointer before check skb forwardable
Linux 4.9.153
locking/qspinlock: Pull in asm/byteorder.h to ensure correct endianness
ipmi:ssif: Fix handling of multi-part return messages
mm, proc: be more verbose about unstable VMA flags in /proc/<pid>/smaps
mm/page-writeback.c: don't break integrity writeback on ->writepage() error
ocfs2: fix panic due to unrecovered local alloc
scsi: megaraid: fix out-of-bound array accesses
scsi: smartpqi: correct lun reset issues
sysfs: Disable lockdep for driver bind/unbind files
ALSA: bebob: fix model-id of unit for Apogee Ensemble
dm snapshot: Fix excessive memory usage and workqueue stalls
tools lib subcmd: Don't add the kernel sources to the include path
dm kcopyd: Fix bug causing workqueue stalls
perf parse-events: Fix unchecked usage of strncpy()
perf svghelper: Fix unchecked usage of strncpy()
perf intel-pt: Fix error with config term "pt=0"
tty/serial: do not free trasnmit buffer page under port lock
mmc: atmel-mci: do not assume idle after atmci_request_end
kconfig: fix memory leak when EOF is encountered in quotation
kconfig: fix file name and line number of warn_ignored_character()
clk: imx6q: reset exclusive gates on init
scsi: target: use consistent left-aligned ASCII INQUIRY data
net: call sk_dst_reset when set SO_DONTROUTE
media: firewire: Fix app_info parameter type in avc_ca{,_app}_info
powerpc/pseries/cpuidle: Fix preempt warning
powerpc/xmon: Fix invocation inside lock region
pstore/ram: Do not treat empty buffers as valid
jffs2: Fix use of uninitialized delayed_work, lockdep breakage
rxe: IB_WR_REG_MR does not capture MR's iova field
selinux: always allow mounting submounts
arm64: perf: set suppress_bind_attrs flag to true
MIPS: SiByte: Enable swiotlb for SWARM, LittleSur and BigSur
ALSA: oxfw: add support for APOGEE duet FireWire
serial: set suppress_bind_attrs flag only if builtin
writeback: don't decrement wb->refcnt if !wb->bdi
e1000e: allow non-monotonic SYSTIM readings
platform/x86: asus-wmi: Tell the EC the OS will handle the display off hotkey
ipv6: Take rcu_read_lock in __inet6_bind for mapped addresses
ipv6: Consider sk_bound_dev_if when binding a socket to a v4 mapped address
r8169: Add support for new Realtek Ethernet
ANDROID: cfi: fix shadow rebasing
UPSTREAM: dm: do not allow readahead to limit IO size
UPSTREAM: readahead: stricter check for bdi io_pages
UPSTREAM: mm: don't cap request size based on read-ahead setting
Revert "UPSTREAM: dm: do not allow readahead to limit IO size"
UPSTREAM: dm: do not allow readahead to limit IO size
UPSTREAM: ppp: Move PFC decompression to PPP generic layer
UPSTREAM: l2tp: Add protocol field decompression
BACKPORT: l2tp: remove ->recv_payload_hook
Change-Id: Ied9b99c5d4cec558b44c3cb720257458d7e3f40e
Signed-off-by: jianzhou <jianzhou@codeaurora.org>
278 lines
7.8 KiB
C
278 lines
7.8 KiB
C
#ifndef __LINUX_BACKING_DEV_DEFS_H
|
|
#define __LINUX_BACKING_DEV_DEFS_H
|
|
|
|
#include <linux/list.h>
|
|
#include <linux/radix-tree.h>
|
|
#include <linux/rbtree.h>
|
|
#include <linux/spinlock.h>
|
|
#include <linux/percpu_counter.h>
|
|
#include <linux/percpu-refcount.h>
|
|
#include <linux/flex_proportions.h>
|
|
#include <linux/timer.h>
|
|
#include <linux/workqueue.h>
|
|
#include <linux/kref.h>
|
|
|
|
struct page;
|
|
struct device;
|
|
struct dentry;
|
|
|
|
/*
|
|
* Bits in bdi_writeback.state
|
|
*/
|
|
enum wb_state {
|
|
WB_registered, /* bdi_register() was done */
|
|
WB_shutting_down, /* wb_shutdown() in progress */
|
|
WB_writeback_running, /* Writeback is in progress */
|
|
WB_has_dirty_io, /* Dirty inodes on ->b_{dirty|io|more_io} */
|
|
};
|
|
|
|
enum wb_congested_state {
|
|
WB_async_congested, /* The async (write) queue is getting full */
|
|
WB_sync_congested, /* The sync queue is getting full */
|
|
};
|
|
|
|
typedef int (congested_fn)(void *, int);
|
|
|
|
enum wb_stat_item {
|
|
WB_RECLAIMABLE,
|
|
WB_WRITEBACK,
|
|
WB_DIRTIED,
|
|
WB_WRITTEN,
|
|
NR_WB_STAT_ITEMS
|
|
};
|
|
|
|
#define WB_STAT_BATCH (8*(1+ilog2(nr_cpu_ids)))
|
|
|
|
/*
|
|
* For cgroup writeback, multiple wb's may map to the same blkcg. Those
|
|
* wb's can operate mostly independently but should share the congested
|
|
* state. To facilitate such sharing, the congested state is tracked using
|
|
* the following struct which is created on demand, indexed by blkcg ID on
|
|
* its bdi, and refcounted.
|
|
*/
|
|
struct bdi_writeback_congested {
|
|
unsigned long state; /* WB_[a]sync_congested flags */
|
|
atomic_t refcnt; /* nr of attached wb's and blkg */
|
|
|
|
#ifdef CONFIG_CGROUP_WRITEBACK
|
|
struct backing_dev_info *__bdi; /* the associated bdi, set to NULL
|
|
* on bdi unregistration. For memcg-wb
|
|
* internal use only! */
|
|
int blkcg_id; /* ID of the associated blkcg */
|
|
struct rb_node rb_node; /* on bdi->cgwb_congestion_tree */
|
|
#endif
|
|
};
|
|
|
|
/*
|
|
* Each wb (bdi_writeback) can perform writeback operations, is measured
|
|
* and throttled, independently. Without cgroup writeback, each bdi
|
|
* (bdi_writeback) is served by its embedded bdi->wb.
|
|
*
|
|
* On the default hierarchy, blkcg implicitly enables memcg. This allows
|
|
* using memcg's page ownership for attributing writeback IOs, and every
|
|
* memcg - blkcg combination can be served by its own wb by assigning a
|
|
* dedicated wb to each memcg, which enables isolation across different
|
|
* cgroups and propagation of IO back pressure down from the IO layer upto
|
|
* the tasks which are generating the dirty pages to be written back.
|
|
*
|
|
* A cgroup wb is indexed on its bdi by the ID of the associated memcg,
|
|
* refcounted with the number of inodes attached to it, and pins the memcg
|
|
* and the corresponding blkcg. As the corresponding blkcg for a memcg may
|
|
* change as blkcg is disabled and enabled higher up in the hierarchy, a wb
|
|
* is tested for blkcg after lookup and removed from index on mismatch so
|
|
* that a new wb for the combination can be created.
|
|
*/
|
|
struct bdi_writeback {
|
|
struct backing_dev_info *bdi; /* our parent bdi */
|
|
|
|
unsigned long state; /* Always use atomic bitops on this */
|
|
unsigned long last_old_flush; /* last old data flush */
|
|
|
|
struct list_head b_dirty; /* dirty inodes */
|
|
struct list_head b_io; /* parked for writeback */
|
|
struct list_head b_more_io; /* parked for more writeback */
|
|
struct list_head b_dirty_time; /* time stamps are dirty */
|
|
spinlock_t list_lock; /* protects the b_* lists */
|
|
|
|
struct percpu_counter stat[NR_WB_STAT_ITEMS];
|
|
|
|
struct bdi_writeback_congested *congested;
|
|
|
|
unsigned long bw_time_stamp; /* last time write bw is updated */
|
|
unsigned long dirtied_stamp;
|
|
unsigned long written_stamp; /* pages written at bw_time_stamp */
|
|
unsigned long write_bandwidth; /* the estimated write bandwidth */
|
|
unsigned long avg_write_bandwidth; /* further smoothed write bw, > 0 */
|
|
|
|
/*
|
|
* The base dirty throttle rate, re-calculated on every 200ms.
|
|
* All the bdi tasks' dirty rate will be curbed under it.
|
|
* @dirty_ratelimit tracks the estimated @balanced_dirty_ratelimit
|
|
* in small steps and is much more smooth/stable than the latter.
|
|
*/
|
|
unsigned long dirty_ratelimit;
|
|
unsigned long balanced_dirty_ratelimit;
|
|
|
|
struct fprop_local_percpu completions;
|
|
int dirty_exceeded;
|
|
|
|
spinlock_t work_lock; /* protects work_list & dwork scheduling */
|
|
struct list_head work_list;
|
|
struct delayed_work dwork; /* work item used for writeback */
|
|
|
|
struct list_head bdi_node; /* anchored at bdi->wb_list */
|
|
|
|
#ifdef CONFIG_CGROUP_WRITEBACK
|
|
struct percpu_ref refcnt; /* used only for !root wb's */
|
|
struct fprop_local_percpu memcg_completions;
|
|
struct cgroup_subsys_state *memcg_css; /* the associated memcg */
|
|
struct cgroup_subsys_state *blkcg_css; /* and blkcg */
|
|
struct list_head memcg_node; /* anchored at memcg->cgwb_list */
|
|
struct list_head blkcg_node; /* anchored at blkcg->cgwb_list */
|
|
|
|
union {
|
|
struct work_struct release_work;
|
|
struct rcu_head rcu;
|
|
};
|
|
#endif
|
|
};
|
|
|
|
struct backing_dev_info {
|
|
struct list_head bdi_list;
|
|
unsigned long ra_pages; /* max readahead in PAGE_SIZE units */
|
|
unsigned long io_pages; /* max allowed IO size */
|
|
unsigned int capabilities; /* Device capabilities */
|
|
congested_fn *congested_fn; /* Function pointer if device is md/dm */
|
|
void *congested_data; /* Pointer to aux data for congested func */
|
|
|
|
char *name;
|
|
|
|
struct kref refcnt; /* Reference counter for the structure */
|
|
unsigned int min_ratio;
|
|
unsigned int max_ratio, max_prop_frac;
|
|
|
|
/*
|
|
* Sum of avg_write_bw of wbs with dirty inodes. > 0 if there are
|
|
* any dirty wbs, which is depended upon by bdi_has_dirty().
|
|
*/
|
|
atomic_long_t tot_write_bandwidth;
|
|
|
|
struct bdi_writeback wb; /* the root writeback info for this bdi */
|
|
struct list_head wb_list; /* list of all wbs */
|
|
#ifdef CONFIG_CGROUP_WRITEBACK
|
|
struct radix_tree_root cgwb_tree; /* radix tree of active cgroup wbs */
|
|
struct rb_root cgwb_congested_tree; /* their congested states */
|
|
#else
|
|
struct bdi_writeback_congested *wb_congested;
|
|
#endif
|
|
wait_queue_head_t wb_waitq;
|
|
|
|
struct device *dev;
|
|
struct device *owner;
|
|
|
|
struct timer_list laptop_mode_wb_timer;
|
|
|
|
#ifdef CONFIG_DEBUG_FS
|
|
struct dentry *debug_dir;
|
|
struct dentry *debug_stats;
|
|
#endif
|
|
};
|
|
|
|
enum {
|
|
BLK_RW_ASYNC = 0,
|
|
BLK_RW_SYNC = 1,
|
|
};
|
|
|
|
void clear_wb_congested(struct bdi_writeback_congested *congested, int sync);
|
|
void set_wb_congested(struct bdi_writeback_congested *congested, int sync);
|
|
|
|
static inline void clear_bdi_congested(struct backing_dev_info *bdi, int sync)
|
|
{
|
|
clear_wb_congested(bdi->wb.congested, sync);
|
|
}
|
|
|
|
static inline void set_bdi_congested(struct backing_dev_info *bdi, int sync)
|
|
{
|
|
set_wb_congested(bdi->wb.congested, sync);
|
|
}
|
|
|
|
struct wb_lock_cookie {
|
|
bool locked;
|
|
unsigned long flags;
|
|
};
|
|
|
|
#ifdef CONFIG_CGROUP_WRITEBACK
|
|
|
|
/**
|
|
* wb_tryget - try to increment a wb's refcount
|
|
* @wb: bdi_writeback to get
|
|
*/
|
|
static inline bool wb_tryget(struct bdi_writeback *wb)
|
|
{
|
|
if (wb != &wb->bdi->wb)
|
|
return percpu_ref_tryget(&wb->refcnt);
|
|
return true;
|
|
}
|
|
|
|
/**
|
|
* wb_get - increment a wb's refcount
|
|
* @wb: bdi_writeback to get
|
|
*/
|
|
static inline void wb_get(struct bdi_writeback *wb)
|
|
{
|
|
if (wb != &wb->bdi->wb)
|
|
percpu_ref_get(&wb->refcnt);
|
|
}
|
|
|
|
/**
|
|
* wb_put - decrement a wb's refcount
|
|
* @wb: bdi_writeback to put
|
|
*/
|
|
static inline void wb_put(struct bdi_writeback *wb)
|
|
{
|
|
if (WARN_ON_ONCE(!wb->bdi)) {
|
|
/*
|
|
* A driver bug might cause a file to be removed before bdi was
|
|
* initialized.
|
|
*/
|
|
return;
|
|
}
|
|
|
|
if (wb != &wb->bdi->wb)
|
|
percpu_ref_put(&wb->refcnt);
|
|
}
|
|
|
|
/**
|
|
* wb_dying - is a wb dying?
|
|
* @wb: bdi_writeback of interest
|
|
*
|
|
* Returns whether @wb is unlinked and being drained.
|
|
*/
|
|
static inline bool wb_dying(struct bdi_writeback *wb)
|
|
{
|
|
return percpu_ref_is_dying(&wb->refcnt);
|
|
}
|
|
|
|
#else /* CONFIG_CGROUP_WRITEBACK */
|
|
|
|
static inline bool wb_tryget(struct bdi_writeback *wb)
|
|
{
|
|
return true;
|
|
}
|
|
|
|
static inline void wb_get(struct bdi_writeback *wb)
|
|
{
|
|
}
|
|
|
|
static inline void wb_put(struct bdi_writeback *wb)
|
|
{
|
|
}
|
|
|
|
static inline bool wb_dying(struct bdi_writeback *wb)
|
|
{
|
|
return false;
|
|
}
|
|
|
|
#endif /* CONFIG_CGROUP_WRITEBACK */
|
|
|
|
#endif /* __LINUX_BACKING_DEV_DEFS_H */
|