Files
kernel_xiaomi_sm8250/include/linux/swap.h
Ivaylo Georgiev cbbfa7615c Merge android-4.19-q.88 (47d86d5) into msm-4.19
* refs/heads/tmp-47d86d5:
  Linux 4.19.88
  net: fec: fix clock count mis-match
  platform/x86: hp-wmi: Fix ACPI errors caused by passing 0 as input size
  platform/x86: hp-wmi: Fix ACPI errors caused by too small buffer
  dmaengine: stm32-dma: check whether length is aligned on FIFO threshold
  ASoC: stm32: sai: add missing put_device()
  ASoC: stm32: i2s: fix IRQ clearing
  ASoC: stm32: i2s: fix 16 bit format support
  ASoC: stm32: i2s: fix dma configuration
  pinctrl: stm32: fix memory leak issue
  mailbox: mailbox-test: fix null pointer if no mmio
  clk: stm32mp1: parent clocks update
  clk: stm32mp1: add CLK_SET_RATE_NO_REPARENT to Kernel clocks
  clk: stm32mp1: fix mcu divider table
  clk: stm32mp1: fix HSI divider flag
  hwrng: stm32 - fix unbalanced pm_runtime_enable
  media: stm32-dcmi: fix check of pm_runtime_get_sync return value
  media: stm32-dcmi: fix DMA corruption when stopping streaming
  crypto: stm32/hash - Fix hmac issue more than 256 bytes
  HID: core: check whether Usage Page item is after Usage ID items
  tcp: exit if nothing to retransmit on RTO timeout
  mailbox: stm32_ipcc: add spinlock to fix channels concurrent access
  drm/atmel-hlcdc: revert shift by 8
  mtd: spi-nor: cast to u64 to avoid uint overflows
  mtd: rawnand: atmel: fix possible object reference leak
  mtd: rawnand: atmel: Fix spelling mistake in error message
  net: macb driver, check for SKBTX_HW_TSTAMP
  net: macb: Fix SUBNS increment and increase resolution
  watchdog: sama5d4: fix WDD value to be always set to max
  ext4: add more paranoia checking in ext4_expand_extra_isize handling
  net: macb: add missed tasklet_kill
  net: sched: fix `tc -s class show` no bstats on class with nolock subqueues
  sctp: cache netns in sctp_ep_common
  tipc: fix link name length check
  selftests: bpf: test_sockmap: handle file creation failures gracefully
  openvswitch: remove another BUG_ON()
  openvswitch: drop unneeded BUG_ON() in ovs_flow_cmd_build_info()
  slip: Fix use-after-free Read in slip_open
  sctp: Fix memory leak in sctp_sf_do_5_2_4_dupcook
  openvswitch: fix flow command message size
  net: psample: fix skb_over_panic
  macvlan: schedule bc_work even if error
  media: atmel: atmel-isc: fix INIT_WORK misplacement
  media: atmel: atmel-isc: fix asd memory allocation
  pwm: Clear chip_data in pwm_put()
  net: macb: fix error format in dev_err()
  media: v4l2-ctrl: fix flags for DO_WHITE_BALANCE
  xfrm: Fix memleak on xfrm state destroy
  thunderbolt: Power cycle the router if NVM authentication fails
  mei: me: add comet point V device id
  mei: bus: prefix device names on bus with the bus name
  USB: serial: ftdi_sio: add device IDs for U-Blox C099-F9P
  staging: rtl8723bs: Add 024c:0525 to the list of SDIO device-ids
  staging: rtl8723bs: Drop ACPI device ids
  staging: rtl8192e: fix potential use after free
  usb: dwc2: use a longer core rest timeout in dwc2_core_reset()
  clk: at91: generated: set audio_pll_allowed in at91_clk_register_generated()
  clk: at91: fix update bit maps on CFG_MOR write
  mm, gup: add missing refcount overflow checks on s390
  mtd: Remove a debug trace in mtdpart.c
  xdp: fix cpumap redirect SKB creation bug
  powerpc/pseries/dlpar: Fix a missing check in dlpar_parse_cc_property()
  ASoC: rt5645: Headphone Jack sense inverts on the LattePanda board
  RDMA/hns: Use GFP_ATOMIC in hns_roce_v2_modify_qp
  RDMA/hns: Fix the state of rereg mr
  RDMA/hns: Bugfix for the scene without receiver queue
  RDMA/hns: Fix the bug with updating rq head pointer when flush cqe
  scsi: libsas: Check SMP PHY control function result
  scsi: hisi_sas: shutdown axi bus to avoid exception CQ returned
  ACPI / APEI: Switch estatus pool to use vmalloc memory
  ACPI / APEI: Don't wait to serialise with oops messages when panic()ing
  scsi: libsas: Support SATA PHY connection rate unmatch fixing during discovery
  apparmor: delete the dentry in aafs_remove() to avoid a leak
  iommu/amd: Fix NULL dereference bug in match_hid_uid
  net: hns3: fix an issue for hns3_update_new_int_gl
  net: hns3: fix an issue for hclgevf_ae_get_hdev
  net: hns3: fix PFC not setting problem for DCB module
  net: hns3: Change fw error code NOT_EXEC to NOT_SUPPORTED
  bpf: drop refcount if bpf_map_new_fd() fails in map_create()
  kvm: properly check debugfs dentry before using it
  net: dev: Use unsigned integer as an argument to left-shift
  mmc: core: align max segment size with logical block size
  bpf: decrease usercnt if bpf_map_new_fd() fails in bpf_map_get_fd_by_id()
  sctp: don't compare hb_timer expire date before starting it
  net: ip6_gre: do not report erspan_ver for ip6gre or ip6gretap
  net: ip_gre: do not report erspan_ver for gre or gretap
  net: fix possible overflow in __sk_mem_raise_allocated()
  geneve: change NET_UDP_TUNNEL dependency to select
  sfc: initialise found bitmap in efx_ef10_mtd_probe
  ASoC: samsung: i2s: Fix prescaler setting for the secondary DAI
  tipc: fix skb may be leaky in tipc_link_input
  net/smc: fix byte_order for rx_curs_confirmed
  blktrace: Show requests without sector
  net/smc: fix sender_free computation
  xfs: end sync buffer I/O properly on shutdown error
  mm/hotplug: invalid PFNs from pfn_to_online_page()
  net/smc: don't wait for send buffer space when data was already sent
  net/smc: prevent races between smc_lgr_terminate() and smc_conn_free()
  decnet: fix DN_IFREQ_SIZE
  ip_tunnel: Make none-tunnel-dst tunnel port work with lwtunnel
  sfc: suppress duplicate nvmem partition types in efx_ef10_mtd_probe
  gpu: ipu-v3: pre: don't trigger update if buffer address doesn't change
  serial: 8250: Fix serial8250 initialization crash
  net/core/neighbour: fix kmemleak minimal reference count for hash tables
  PCI/MSI: Return -ENOSPC from pci_alloc_irq_vectors_affinity()
  ata: ahci: mvebu: do Armada 38x configuration only on relevant SoCs
  net/core/neighbour: tell kmemleak about hash tables
  tipc: fix memory leak in tipc_nl_compat_publ_dump
  mtd: Check add_mtd_device() ret code
  lib/genalloc.c: include vmalloc.h
  drivers/base/platform.c: kmemleak ignore a known leak
  fork: fix some -Wmissing-prototypes warnings
  lib/genalloc.c: use vzalloc_node() to allocate the bitmap
  lib/genalloc.c: fix allocation of aligned buffer from non-aligned chunk
  firmware: arm_sdei: Fix DT platform device creation
  firmware: arm_sdei: fix wrong of_node_put() in init function
  infiniband/qedr: Potential null ptr dereference of qp
  infiniband: bnxt_re: qplib: Check the return value of send_message
  xprtrdma: Prevent leak of rpcrdma_rep objects
  netfilter: nf_tables: fix a missing check of nla_put_failure
  tools/vm/page-types.c: fix "kpagecount returned fewer pages than expected" failures
  mm/page_alloc.c: deduplicate __memblock_free_early() and memblock_free()
  mm/page_alloc.c: use a single function to free page
  mm/page_alloc.c: free order-0 pages through PCP in page_frag_free()
  vmscan: return NODE_RECLAIM_NOSCAN in node_reclaim() when CONFIG_NUMA is n
  ocfs2: clear journal dirty flag after shutdown journal
  net/wan/fsl_ucc_hdlc: Avoid double free in ucc_hdlc_probe()
  net: marvell: fix a missing check of acpi_match_device
  tipc: fix a missing check of genlmsg_put
  atl1e: checking the status of atl1e_write_phy_reg
  net: dsa: bcm_sf2: Propagate error value from mdio_write
  net: stmicro: fix a missing check of clk_prepare
  net: (cpts) fix a missing check of clk_prepare
  um: Make GCOV depend on !KCOV
  um: Include sys/uio.h to have writev()
  f2fs: fix to dirty inode synchronously
  f2fs: fix block address for __check_sit_bitmap
  net/net_namespace: Check the return value of register_pernet_subsys()
  net/netlink_compat: Fix a missing check of nla_parse_nested
  pwm: clps711x: Fix period calculation
  crypto: mxc-scc - fix build warnings on ARM64
  powerpc: Fix HMIs on big-endian with CONFIG_RELOCATABLE=y
  powerpc/pseries: Fix node leak in update_lmb_associativity_index()
  powerpc/83xx: handle machine check caused by watchdog timer
  regulator: tps65910: fix a missing check of return value
  bpf/cpumap: make sure frame_size for build_skb is aligned if headroom isn't
  IB/rxe: Make counters thread safe
  drbd: fix print_st_err()'s prototype to match the definition
  drbd: do not block when adjusting "disk-options" while IO is frozen
  drbd: reject attach of unsuitable uuids even if connected
  drbd: ignore "all zero" peer volume sizes in handshake
  powerpc/powernv/eeh/npu: Fix uninitialized variables in opal_pci_eeh_freeze_status
  vfio/spapr_tce: Get rid of possible infinite loop
  powerpc/44x/bamboo: Fix PCI range
  powerpc/mm: Make NULL pointer deferences explicit on bad page faults.
  powerpc/prom: fix early DEBUG messages
  powerpc/32: Avoid unsupported flags with clang
  powerpc/perf: Fix unit_sel/cache_sel checks
  ath6kl: Fix off by one error in scan completion
  ath6kl: Only use match sets when firmware supports it
  brcmfmac: Fix access point mode
  scsi: csiostor: fix incorrect dma device in case of vport
  scsi: qla2xxx: deadlock by configfs_depend_item
  RDMA/srp: Propagate ib_post_send() failures to the SCSI mid-layer
  openrisc: Fix broken paths to arch/or32
  serial: max310x: Fix tx_empty() callback
  Bluetooth: hci_bcm: Handle specific unknown packets after firmware loading
  drivers/regulator: fix a missing check of return value
  powerpc/xmon: fix dump_segments()
  powerpc/book3s/32: fix number of bats in p/v_block_mapped()
  vxlan: Fix error path in __vxlan_dev_create()
  clocksource/drivers/fttmr010: Fix invalid interrupt register access
  IB/qib: Fix an error code in qib_sdma_verbs_send()
  xfs: Fix bulkstat compat ioctls on x32 userspace.
  xfs: Align compat attrlist_by_handle with native implementation.
  dm raid: fix false -EBUSY when handling check/repair message
  gfs2: take jdata unstuff into account in do_grow
  dm flakey: Properly corrupt multi-page bios.
  HID: doc: fix wrong data structure reference for UHID_OUTPUT
  pinctrl: sh-pfc: sh7734: Fix shifted values in IPSR10
  pinctrl: sh-pfc: sh7264: Fix PFCR3 and PFCR0 register configuration
  pinctrl: sh-pfc: r8a77990: Fix MOD_SEL0 SEL_I2C1 field width
  KVM: s390: unregister debug feature on failing arch init
  bnxt_en: query force speeds before disabling autoneg mode.
  bnxt_en: Save ring statistics before reset.
  bnxt_en: Return linux standard errors in bnxt_ethtool.c
  exofs_mount(): fix leaks on failure exits
  netfilter: nf_nat_sip: fix RTP/RTCP source port translations
  net/mlx5: Continue driver initialization despite debugfs failure
  pinctrl: xway: fix gpio-hog related boot issues
  memory: omap-gpmc: Get the header of the enum
  vfio-mdev/samples: Use u8 instead of char for handle functions
  kprobes/x86: Show x86-64 specific blacklisted symbols correctly
  kprobes: Blacklist symbols in arch-defined prohibited area
  xen/pciback: Check dev_data before using it
  kprobes/x86/xen: blacklist non-attachable xen interrupt functions
  serial: 8250: Rate limit serial port rx interrupts during input overruns
  gpio: raspberrypi-exp: decrease refcount on firmware dt node
  HID: intel-ish-hid: fixes incorrect error handling
  serial: sh-sci: Fix crash in rx_timer_fn() on PIO fallback
  btrfs: only track ref_heads in delayed_ref_updates
  Btrfs: allow clear_extent_dirty() to receive a cached extent state record
  btrfs: dev-replace: set result code of cancel by status of scrub
  btrfs: fix ncopies raid_attr for RAID56
  btrfs: Check for missing device before bio submission in btrfs_map_bio
  usb: ehci-omap: Fix deferred probe for phy handling
  mtd: rawnand: sunxi: Write pageprog related opcodes to WCMD_SET
  mmc: meson-gx: make sure the descriptor is stopped on errors
  VSOCK: bind to random port for VMADDR_PORT_ANY
  crypto/chelsio/chtls: listen fails with multiadapt
  Revert "KVM: nVMX: move check_vmentry_postreqs() call to nested_vmx_enter_non_root_mode()"
  Revert "KVM: nVMX: reset cache/shadows when switching loaded VMCS"
  kvm: vmx: Set IA32_TSC_AUX for legacy mode guests
  gpiolib: Fix return value of gpio_to_desc() stub if !GPIOLIB
  gpio: pca953x: Fix AI overflow on PCAL6524
  iwlwifi: pcie: set cmd_len in the correct place
  iwlwifi: pcie: fix erroneous print
  iwlwifi: mvm: force TCM re-evaluation on TCM resume
  iwlwifi: move iwl_nvm_check_version() into dvm
  microblaze: fix multiple bugs in arch/microblaze/boot/Makefile
  microblaze: move "... is ready" messages to arch/microblaze/Makefile
  microblaze: adjust the help to the real behavior
  ubi: Do not drop UBI device reference before using
  ubi: Put MTD device after it is not used
  ubifs: Fix default compression selection in ubifs
  nvme: fix kernel paging oops
  xfs: require both realtime inodes to mount
  bcache: do not mark writeback_running too early
  bcache: do not check if debug dentry is ERR or NULL explicitly on remove
  rtl818x: fix potential use after free
  brcmfmac: set SDIO F1 MesBusyCtrl for CYW4373
  brcmfmac: set F2 watermark to 256 for 4373
  mwifiex: debugfs: correct histogram spacing, formatting
  mwifiex: fix potential NULL dereference and use after free
  arm64: dts: renesas: draak: Fix CVBS input
  crypto: user - support incremental algorithm dumps
  s390/zcrypt: make sysfs reset attribute trigger queue reset
  nvme: provide fallback for discard alloc failure
  scsi: qla2xxx: Fix for FC-NVMe discovery for NPIV port
  scsi: qla2xxx: Fix NPIV handling for FC-NVMe
  scsi: lpfc: Enable Management features for IF_TYPE=6
  ACPI / LPSS: Ignore acpi_device_fix_up_power() return value
  ARM: ks8695: fix section mismatch warning
  xfs: zero length symlinks are not valid
  PM / AVS: SmartReflex: NULL check before some freeing functions is not needed
  RDMA/vmw_pvrdma: Use atomic memory allocation in create AH
  arm64: preempt: Fix big-endian when checking preempt count in assembly
  RDMA/hns: Fix the bug while use multi-hop of pbl
  ARM: OMAP1: fix USB configuration for device-only setups
  platform/x86: mlx-platform: Fix LED configuration
  bus: ti-sysc: Check for no-reset and no-idle flags at the child level
  arm64: smp: Handle errors reported by the firmware
  arm64: mm: Prevent mismatched 52-bit VA support
  ARM: dts: Fix hsi gdd range for omap4
  parisc: Fix HP SDC hpa address output
  parisc: Fix serio address output
  ARM: dts: imx53-voipac-dmm-668: Fix memory node duplication
  ARM: dts: imx25: Fix memory node duplication
  ARM: dts: imx27: Fix memory node duplication
  ARM: dts: imx1: Fix memory node duplication
  ARM: dts: imx23: Fix memory node duplication
  ARM: dts: imx50: Fix memory node duplication
  ARM: dts: imx6sl: Fix memory node duplication
  ARM: dts: imx6sx: Fix memory node duplication
  ARM: dts: imx6ul: Fix memory node duplication
  ARM: dts: imx7: Fix memory node duplication
  ARM: dts: imx35: Fix memory node duplication
  ARM: dts: imx31: Fix memory node duplication
  ARM: dts: imx53: Fix memory node duplication
  ARM: dts: imx51: Fix memory node duplication
  ARM: debug-imx: only define DEBUG_IMX_UART_PORT if needed
  tracing: Lock event_mutex before synth_event_mutex
  ARM: dts: Fix up SQ201 flash access
  scsi: lpfc: Fix dif and first burst use in write commands
  scsi: lpfc: Fix kernel Oops due to null pring pointers
  scsi: target/tcmu: Fix queue_cmd_ring() declaration
  pwm: bcm-iproc: Prevent unloading the driver module while in use
  block: drbd: remove a stray unlock in __drbd_send_protocol()
  mac80211: fix station inactive_time shortly after boot
  net/fq_impl: Switch to kvmalloc() for memory allocation
  ceph: return -EINVAL if given fsc mount option on kernel w/o support
  net: mscc: ocelot: fix __ocelot_rmw_ix prototype
  net: bcmgenet: reapply manual settings to the PHY
  net: bcmgenet: use RGMII loopback for MAC reset
  scripts/gdb: fix debugging modules compiled with hot/cold partitioning
  ASoC: stm32: sai: add restriction on mmap support
  watchdog: meson: Fix the wrong value of left time
  can: mcp251x: mcp251x_restart_work_handler(): Fix potential force_quit race condition
  can: flexcan: increase error counters if skb enqueueing via can_rx_offload_queue_sorted() fails
  can: rx-offload: can_rx_offload_irq_offload_fifo(): continue on error
  can: rx-offload: can_rx_offload_irq_offload_timestamp(): continue on error
  can: rx-offload: can_rx_offload_offload_one(): use ERR_PTR() to propagate error value in case of errors
  can: rx-offload: can_rx_offload_offload_one(): increment rx_fifo_errors on queue overflow or OOM
  can: rx-offload: can_rx_offload_offload_one(): do not increase the skb_queue beyond skb_queue_len_max
  can: rx-offload: can_rx_offload_queue_tail(): fix error handling, avoid skb mem leak
  can: c_can: D_CAN: c_can_chip_config(): perform a sofware reset on open
  can: peak_usb: report bus recovery as well
  bridge: ebtables: don't crash when using dnat target in output chains
  net: fec: add missed clk_disable_unprepare in remove
  clk: ti: clkctrl: Fix failed to enable error with double udelay timeout
  clk: ti: dra7-atl-clock: Remove ti_clk_add_alias call
  x86/resctrl: Prevent NULL pointer dereference when reading mondata
  idr: Fix idr_alloc_u32 on 32-bit systems
  idr: Fix integer overflow in idr_for_each_entry
  powerpc/bpf: Fix tail call implementation
  samples/bpf: fix build by setting HAVE_ATTR_TEST to zero
  ARM: dts: sun8i-a83t-tbs-a711: Fix WiFi resume from suspend
  clk: sunxi-ng: a80: fix the zero'ing of bits 16 and 18
  clk: sunxi: Fix operator precedence in sunxi_divs_clk_setup
  clk: at91: avoid sleeping early
  reset: fix reset_control_ops kerneldoc comment
  ARM: dts: imx6qdl-sabreauto: Fix storm of accelerometer interrupts
  pinctrl: cherryview: Allocate IRQ chip dynamic
  clk: samsung: exynos5420: Preserve PLL configuration during suspend/resume
  ASoC: kirkwood: fix device remove ordering
  ASoC: kirkwood: fix external clock probe defer
  clk: samsung: exynos5433: Fix error paths
  reset: Fix memory leak in reset_control_array_put()
  ASoC: compress: fix unsigned integer overflow check
  ASoC: msm8916-wcd-analog: Fix RX1 selection in RDAC2 MUX
  clocksource/drivers/mediatek: Fix error handling
  clk: meson: gxbb: let sar_adc_clk_div set the parent clock rate

Conflicts:
	drivers/mmc/core/queue.c

Change-Id: I17f5829400ece4e39be4c9f6223fff206c710d06
Signed-off-by: Ivaylo Georgiev <irgeorgiev@codeaurora.org>
2020-01-28 03:20:43 -08:00

698 lines
22 KiB
C

/* SPDX-License-Identifier: GPL-2.0 */
#ifndef _LINUX_SWAP_H
#define _LINUX_SWAP_H
#include <linux/spinlock.h>
#include <linux/linkage.h>
#include <linux/mmzone.h>
#include <linux/list.h>
#include <linux/memcontrol.h>
#include <linux/sched.h>
#include <linux/node.h>
#include <linux/fs.h>
#include <linux/atomic.h>
#include <linux/page-flags.h>
#include <asm/page.h>
struct notifier_block;
struct bio;
#define SWAP_FLAG_PREFER 0x8000 /* set if swap priority specified */
#define SWAP_FLAG_PRIO_MASK 0x7fff
#define SWAP_FLAG_PRIO_SHIFT 0
#define SWAP_FLAG_DISCARD 0x10000 /* enable discard for swap */
#define SWAP_FLAG_DISCARD_ONCE 0x20000 /* discard swap area at swapon-time */
#define SWAP_FLAG_DISCARD_PAGES 0x40000 /* discard page-clusters after use */
#define SWAP_FLAGS_VALID (SWAP_FLAG_PRIO_MASK | SWAP_FLAG_PREFER | \
SWAP_FLAG_DISCARD | SWAP_FLAG_DISCARD_ONCE | \
SWAP_FLAG_DISCARD_PAGES)
#define SWAP_BATCH 64
static inline int current_is_kswapd(void)
{
return current->flags & PF_KSWAPD;
}
/*
* MAX_SWAPFILES defines the maximum number of swaptypes: things which can
* be swapped to. The swap type and the offset into that swap type are
* encoded into pte's and into pgoff_t's in the swapcache. Using five bits
* for the type means that the maximum number of swapcache pages is 27 bits
* on 32-bit-pgoff_t architectures. And that assumes that the architecture packs
* the type/offset into the pte as 5/27 as well.
*/
#define MAX_SWAPFILES_SHIFT 5
/*
* Use some of the swap files numbers for other purposes. This
* is a convenient way to hook into the VM to trigger special
* actions on faults.
*/
/*
* Unaddressable device memory support. See include/linux/hmm.h and
* Documentation/vm/hmm.rst. Short description is we need struct pages for
* device memory that is unaddressable (inaccessible) by CPU, so that we can
* migrate part of a process memory to device memory.
*
* When a page is migrated from CPU to device, we set the CPU page table entry
* to a special SWP_DEVICE_* entry.
*/
#ifdef CONFIG_DEVICE_PRIVATE
#define SWP_DEVICE_NUM 2
#define SWP_DEVICE_WRITE (MAX_SWAPFILES+SWP_HWPOISON_NUM+SWP_MIGRATION_NUM)
#define SWP_DEVICE_READ (MAX_SWAPFILES+SWP_HWPOISON_NUM+SWP_MIGRATION_NUM+1)
#else
#define SWP_DEVICE_NUM 0
#endif
/*
* NUMA node memory migration support
*/
#ifdef CONFIG_MIGRATION
#define SWP_MIGRATION_NUM 2
#define SWP_MIGRATION_READ (MAX_SWAPFILES + SWP_HWPOISON_NUM)
#define SWP_MIGRATION_WRITE (MAX_SWAPFILES + SWP_HWPOISON_NUM + 1)
#else
#define SWP_MIGRATION_NUM 0
#endif
/*
* Handling of hardware poisoned pages with memory corruption.
*/
#ifdef CONFIG_MEMORY_FAILURE
#define SWP_HWPOISON_NUM 1
#define SWP_HWPOISON MAX_SWAPFILES
#else
#define SWP_HWPOISON_NUM 0
#endif
#define MAX_SWAPFILES \
((1 << MAX_SWAPFILES_SHIFT) - SWP_DEVICE_NUM - \
SWP_MIGRATION_NUM - SWP_HWPOISON_NUM)
/*
* Magic header for a swap area. The first part of the union is
* what the swap magic looks like for the old (limited to 128MB)
* swap area format, the second part of the union adds - in the
* old reserved area - some extra information. Note that the first
* kilobyte is reserved for boot loader or disk label stuff...
*
* Having the magic at the end of the PAGE_SIZE makes detecting swap
* areas somewhat tricky on machines that support multiple page sizes.
* For 2.5 we'll probably want to move the magic to just beyond the
* bootbits...
*/
union swap_header {
struct {
char reserved[PAGE_SIZE - 10];
char magic[10]; /* SWAP-SPACE or SWAPSPACE2 */
} magic;
struct {
char bootbits[1024]; /* Space for disklabel etc. */
__u32 version;
__u32 last_page;
__u32 nr_badpages;
unsigned char sws_uuid[16];
unsigned char sws_volume[16];
__u32 padding[117];
__u32 badpages[1];
} info;
};
/*
* current->reclaim_state points to one of these when a task is running
* memory reclaim
*/
struct reclaim_state {
unsigned long reclaimed_slab;
};
#ifdef __KERNEL__
struct address_space;
struct sysinfo;
struct writeback_control;
struct zone;
/*
* A swap extent maps a range of a swapfile's PAGE_SIZE pages onto a range of
* disk blocks. A list of swap extents maps the entire swapfile. (Where the
* term `swapfile' refers to either a blockdevice or an IS_REG file. Apart
* from setup, they're handled identically.
*
* We always assume that blocks are of size PAGE_SIZE.
*/
struct swap_extent {
struct list_head list;
pgoff_t start_page;
pgoff_t nr_pages;
sector_t start_block;
};
/*
* Max bad pages in the new format..
*/
#define MAX_SWAP_BADPAGES \
((offsetof(union swap_header, magic.magic) - \
offsetof(union swap_header, info.badpages)) / sizeof(int))
enum {
SWP_USED = (1 << 0), /* is slot in swap_info[] used? */
SWP_WRITEOK = (1 << 1), /* ok to write to this swap? */
SWP_DISCARDABLE = (1 << 2), /* blkdev support discard */
SWP_DISCARDING = (1 << 3), /* now discarding a free cluster */
SWP_SOLIDSTATE = (1 << 4), /* blkdev seeks are cheap */
SWP_CONTINUED = (1 << 5), /* swap_map has count continuation */
SWP_BLKDEV = (1 << 6), /* its a block device */
SWP_FILE = (1 << 7), /* set after swap_activate success */
SWP_AREA_DISCARD = (1 << 8), /* single-time swap area discards */
SWP_PAGE_DISCARD = (1 << 9), /* freed swap page-cluster discards */
SWP_STABLE_WRITES = (1 << 10), /* no overwrite PG_writeback pages */
SWP_SYNCHRONOUS_IO = (1 << 11), /* synchronous IO is efficient */
/* add others here before... */
SWP_SCANNING = (1 << 12), /* refcount in scan_swap_map */
};
#define SWAP_CLUSTER_MAX 32UL
#define COMPACT_CLUSTER_MAX SWAP_CLUSTER_MAX
#define SWAPFILE_CLUSTER 256
#define SWAP_MAP_MAX 0x3e /* Max duplication count, in first swap_map */
#define SWAP_MAP_BAD 0x3f /* Note pageblock is bad, in first swap_map */
#define SWAP_HAS_CACHE 0x40 /* Flag page is cached, in first swap_map */
#define SWAP_CONT_MAX 0x7f /* Max count, in each swap_map continuation */
#define COUNT_CONTINUED 0x80 /* See swap_map continuation for full count */
#define SWAP_MAP_SHMEM 0xbf /* Owned by shmem/tmpfs, in first swap_map */
/*
* We use this to track usage of a cluster. A cluster is a block of swap disk
* space with SWAPFILE_CLUSTER pages long and naturally aligns in disk. All
* free clusters are organized into a list. We fetch an entry from the list to
* get a free cluster.
*
* The data field stores next cluster if the cluster is free or cluster usage
* counter otherwise. The flags field determines if a cluster is free. This is
* protected by swap_info_struct.lock.
*/
struct swap_cluster_info {
spinlock_t lock; /*
* Protect swap_cluster_info fields
* and swap_info_struct->swap_map
* elements correspond to the swap
* cluster
*/
unsigned int data:24;
unsigned int flags:8;
};
#define CLUSTER_FLAG_FREE 1 /* This cluster is free */
#define CLUSTER_FLAG_NEXT_NULL 2 /* This cluster has no next cluster */
#define CLUSTER_FLAG_HUGE 4 /* This cluster is backing a transparent huge page */
/*
* We assign a cluster to each CPU, so each CPU can allocate swap entry from
* its own cluster and swapout sequentially. The purpose is to optimize swapout
* throughput.
*/
struct percpu_cluster {
struct swap_cluster_info index; /* Current cluster index */
unsigned int next; /* Likely next allocation offset */
};
struct swap_cluster_list {
struct swap_cluster_info head;
struct swap_cluster_info tail;
};
/*
* The in-memory structure used to track swap areas.
*/
struct swap_info_struct {
unsigned long flags; /* SWP_USED etc: see above */
signed short prio; /* swap priority of this type */
struct plist_node list; /* entry in swap_active_head */
signed char type; /* strange name for an index */
unsigned int max; /* extent of the swap_map */
unsigned char *swap_map; /* vmalloc'ed array of usage counts */
struct swap_cluster_info *cluster_info; /* cluster info. Only for SSD */
struct swap_cluster_list free_clusters; /* free clusters list */
unsigned int lowest_bit; /* index of first free in swap_map */
unsigned int highest_bit; /* index of last free in swap_map */
unsigned int pages; /* total of usable pages of swap */
unsigned int inuse_pages; /* number of those currently in use */
unsigned int cluster_next; /* likely index for next allocation */
unsigned int cluster_nr; /* countdown to next cluster search */
struct percpu_cluster __percpu *percpu_cluster; /* per cpu's swap location */
struct swap_extent *curr_swap_extent;
struct swap_extent first_swap_extent;
struct block_device *bdev; /* swap device or bdev of swap file */
struct file *swap_file; /* seldom referenced */
unsigned int old_block_size; /* seldom referenced */
#ifdef CONFIG_FRONTSWAP
unsigned long *frontswap_map; /* frontswap in-use, one bit per page */
atomic_t frontswap_pages; /* frontswap pages in-use counter */
#endif
spinlock_t lock; /*
* protect map scan related fields like
* swap_map, lowest_bit, highest_bit,
* inuse_pages, cluster_next,
* cluster_nr, lowest_alloc,
* highest_alloc, free/discard cluster
* list. other fields are only changed
* at swapon/swapoff, so are protected
* by swap_lock. changing flags need
* hold this lock and swap_lock. If
* both locks need hold, hold swap_lock
* first.
*/
spinlock_t cont_lock; /*
* protect swap count continuation page
* list.
*/
struct work_struct discard_work; /* discard worker */
struct swap_cluster_list discard_clusters; /* discard clusters list */
unsigned int write_pending;
unsigned int max_writes;
struct plist_node avail_lists[0]; /*
* entries in swap_avail_heads, one
* entry per node.
* Must be last as the number of the
* array is nr_node_ids, which is not
* a fixed value so have to allocate
* dynamically.
* And it has to be an array so that
* plist_for_each_* can work.
*/
};
#ifdef CONFIG_64BIT
#define SWAP_RA_ORDER_CEILING 5
#else
/* Avoid stack overflow, because we need to save part of page table */
#define SWAP_RA_ORDER_CEILING 3
#define SWAP_RA_PTE_CACHE_SIZE (1 << SWAP_RA_ORDER_CEILING)
#endif
struct vma_swap_readahead {
unsigned short win;
unsigned short offset;
unsigned short nr_pte;
#ifdef CONFIG_64BIT
pte_t *ptes;
#else
pte_t ptes[SWAP_RA_PTE_CACHE_SIZE];
#endif
};
/* linux/mm/workingset.c */
void *workingset_eviction(struct address_space *mapping, struct page *page);
void workingset_refault(struct page *page, void *shadow);
void workingset_activation(struct page *page);
/* Do not use directly, use workingset_lookup_update */
void workingset_update_node(struct radix_tree_node *node);
/* Returns workingset_update_node() if the mapping has shadow entries. */
#define workingset_lookup_update(mapping) \
({ \
radix_tree_update_node_t __helper = workingset_update_node; \
if (dax_mapping(mapping) || shmem_mapping(mapping)) \
__helper = NULL; \
__helper; \
})
/* linux/mm/page_alloc.c */
extern unsigned long totalram_pages;
extern unsigned long totalreserve_pages;
extern unsigned long nr_free_buffer_pages(void);
extern unsigned long nr_free_pagecache_pages(void);
/* Definition of global_zone_page_state not available yet */
#define nr_free_pages() global_zone_page_state(NR_FREE_PAGES)
/* linux/mm/swap.c */
extern void lru_cache_add(struct page *);
extern void lru_cache_add_anon(struct page *page);
extern void lru_cache_add_file(struct page *page);
extern void lru_add_page_tail(struct page *page, struct page *page_tail,
struct lruvec *lruvec, struct list_head *head);
extern void activate_page(struct page *);
extern void mark_page_accessed(struct page *);
extern void lru_add_drain(void);
extern void lru_add_drain_cpu(int cpu);
extern void lru_add_drain_all(void);
extern void rotate_reclaimable_page(struct page *page);
extern void deactivate_file_page(struct page *page);
extern void mark_page_lazyfree(struct page *page);
extern void swap_setup(void);
extern void __lru_cache_add_active_or_unevictable(struct page *page,
unsigned long vma_flags);
static inline void lru_cache_add_active_or_unevictable(struct page *page,
struct vm_area_struct *vma)
{
return __lru_cache_add_active_or_unevictable(page, vma->vm_flags);
}
/* linux/mm/vmscan.c */
extern unsigned long zone_reclaimable_pages(struct zone *zone);
extern unsigned long try_to_free_pages(struct zonelist *zonelist, int order,
gfp_t gfp_mask, nodemask_t *mask);
extern int __isolate_lru_page(struct page *page, isolate_mode_t mode);
extern unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg,
unsigned long nr_pages,
gfp_t gfp_mask,
bool may_swap);
extern unsigned long mem_cgroup_shrink_node(struct mem_cgroup *mem,
gfp_t gfp_mask, bool noswap,
pg_data_t *pgdat,
unsigned long *nr_scanned);
extern unsigned long shrink_all_memory(unsigned long nr_pages);
extern int vm_swappiness;
extern int sysctl_swap_ratio;
extern int sysctl_swap_ratio_enable;
extern int remove_mapping(struct address_space *mapping, struct page *page);
extern unsigned long vm_total_pages;
#ifdef CONFIG_NUMA
extern int node_reclaim_mode;
extern int sysctl_min_unmapped_ratio;
extern int sysctl_min_slab_ratio;
#else
#define node_reclaim_mode 0
#endif
extern int page_evictable(struct page *page);
extern void check_move_unevictable_pages(struct page **, int nr_pages);
extern int kswapd_run(int nid);
extern void kswapd_stop(int nid);
#ifdef CONFIG_SWAP
#include <linux/blk_types.h> /* for bio_end_io_t */
/* linux/mm/page_io.c */
extern int swap_readpage(struct page *page, bool do_poll);
extern int swap_writepage(struct page *page, struct writeback_control *wbc);
extern void end_swap_bio_write(struct bio *bio);
extern int __swap_writepage(struct page *page, struct writeback_control *wbc,
bio_end_io_t end_write_func);
extern int swap_set_page_dirty(struct page *page);
int add_swap_extent(struct swap_info_struct *sis, unsigned long start_page,
unsigned long nr_pages, sector_t start_block);
int generic_swapfile_activate(struct swap_info_struct *, struct file *,
sector_t *);
/* linux/mm/swap_state.c */
/* One swap address space for each 64M swap space */
#define SWAP_ADDRESS_SPACE_SHIFT 14
#define SWAP_ADDRESS_SPACE_PAGES (1 << SWAP_ADDRESS_SPACE_SHIFT)
extern struct address_space *swapper_spaces[];
#define swap_address_space(entry) \
(&swapper_spaces[swp_type(entry)][swp_offset(entry) \
>> SWAP_ADDRESS_SPACE_SHIFT])
extern unsigned long total_swapcache_pages(void);
extern void show_swap_cache_info(void);
extern int add_to_swap(struct page *page);
extern int add_to_swap_cache(struct page *, swp_entry_t, gfp_t);
extern int __add_to_swap_cache(struct page *page, swp_entry_t entry);
extern void __delete_from_swap_cache(struct page *);
extern void delete_from_swap_cache(struct page *);
extern void free_page_and_swap_cache(struct page *);
extern void free_pages_and_swap_cache(struct page **, int);
extern struct page *lookup_swap_cache(swp_entry_t entry,
struct vm_area_struct *vma,
unsigned long addr);
extern struct page *read_swap_cache_async(swp_entry_t, gfp_t,
struct vm_area_struct *vma, unsigned long addr,
bool do_poll);
extern struct page *__read_swap_cache_async(swp_entry_t, gfp_t,
struct vm_area_struct *vma, unsigned long addr,
bool *new_page_allocated);
extern struct page *swap_cluster_readahead(swp_entry_t entry, gfp_t flag,
struct vm_fault *vmf);
extern struct page *swapin_readahead(swp_entry_t entry, gfp_t flag,
struct vm_fault *vmf);
/* linux/mm/swapfile.c */
extern atomic_long_t nr_swap_pages;
extern long total_swap_pages;
extern atomic_t nr_rotate_swap;
extern bool has_usable_swap(void);
/* Swap 50% full? Release swapcache more aggressively.. */
static inline bool vm_swap_full(void)
{
return atomic_long_read(&nr_swap_pages) * 2 < total_swap_pages;
}
static inline long get_nr_swap_pages(void)
{
return atomic_long_read(&nr_swap_pages);
}
extern void si_swapinfo(struct sysinfo *);
extern swp_entry_t get_swap_page(struct page *page);
extern void put_swap_page(struct page *page, swp_entry_t entry);
extern swp_entry_t get_swap_page_of_type(int);
extern int get_swap_pages(int n, swp_entry_t swp_entries[], int entry_size);
extern int add_swap_count_continuation(swp_entry_t, gfp_t);
extern void swap_shmem_alloc(swp_entry_t);
extern int swap_duplicate(swp_entry_t);
extern int swapcache_prepare(swp_entry_t);
extern void swap_free(swp_entry_t);
extern void swapcache_free_entries(swp_entry_t *entries, int n);
extern int free_swap_and_cache(swp_entry_t);
extern int swap_type_of(dev_t, sector_t, struct block_device **);
extern unsigned int count_swap_pages(int, int);
extern sector_t map_swap_page(struct page *, struct block_device **);
extern sector_t swapdev_block(int, pgoff_t);
extern int page_swapcount(struct page *);
extern int __swap_count(struct swap_info_struct *si, swp_entry_t entry);
extern int __swp_swapcount(swp_entry_t entry);
extern int swp_swapcount(swp_entry_t entry);
extern struct swap_info_struct *page_swap_info(struct page *);
extern struct swap_info_struct *swp_swap_info(swp_entry_t entry);
extern bool reuse_swap_page(struct page *, int *);
extern int try_to_free_swap(struct page *);
struct backing_dev_info;
extern int init_swap_address_space(unsigned int type, unsigned long nr_pages);
extern void exit_swap_address_space(unsigned int type);
#else /* CONFIG_SWAP */
static inline int swap_readpage(struct page *page, bool do_poll)
{
return 0;
}
static inline struct swap_info_struct *swp_swap_info(swp_entry_t entry)
{
return NULL;
}
#define swap_address_space(entry) (NULL)
#define get_nr_swap_pages() 0L
#define total_swap_pages 0L
#define total_swapcache_pages() 0UL
#define vm_swap_full() 0
#define si_swapinfo(val) \
do { (val)->freeswap = (val)->totalswap = 0; } while (0)
/* only sparc can not include linux/pagemap.h in this file
* so leave put_page and release_pages undeclared... */
#define free_page_and_swap_cache(page) \
put_page(page)
#define free_pages_and_swap_cache(pages, nr) \
release_pages((pages), (nr));
static inline void show_swap_cache_info(void)
{
}
#define free_swap_and_cache(e) ({(is_migration_entry(e) || is_device_private_entry(e));})
#define swapcache_prepare(e) ({(is_migration_entry(e) || is_device_private_entry(e));})
static inline int add_swap_count_continuation(swp_entry_t swp, gfp_t gfp_mask)
{
return 0;
}
static inline void swap_shmem_alloc(swp_entry_t swp)
{
}
static inline int swap_duplicate(swp_entry_t swp)
{
return 0;
}
static inline void swap_free(swp_entry_t swp)
{
}
static inline void put_swap_page(struct page *page, swp_entry_t swp)
{
}
static inline struct page *swap_cluster_readahead(swp_entry_t entry,
gfp_t gfp_mask, struct vm_fault *vmf)
{
return NULL;
}
static inline struct page *swapin_readahead(swp_entry_t swp, gfp_t gfp_mask,
struct vm_fault *vmf)
{
return NULL;
}
static inline int swap_writepage(struct page *p, struct writeback_control *wbc)
{
return 0;
}
static inline struct page *lookup_swap_cache(swp_entry_t swp,
struct vm_area_struct *vma,
unsigned long addr)
{
return NULL;
}
static inline int add_to_swap(struct page *page)
{
return 0;
}
static inline int add_to_swap_cache(struct page *page, swp_entry_t entry,
gfp_t gfp_mask)
{
return -1;
}
static inline void __delete_from_swap_cache(struct page *page)
{
}
static inline void delete_from_swap_cache(struct page *page)
{
}
static inline int page_swapcount(struct page *page)
{
return 0;
}
static inline int __swap_count(struct swap_info_struct *si, swp_entry_t entry)
{
return 0;
}
static inline int __swp_swapcount(swp_entry_t entry)
{
return 0;
}
static inline int swp_swapcount(swp_entry_t entry)
{
return 0;
}
#define reuse_swap_page(page, total_map_swapcount) \
(page_trans_huge_mapcount(page, total_map_swapcount) == 1)
static inline int try_to_free_swap(struct page *page)
{
return 0;
}
static inline swp_entry_t get_swap_page(struct page *page)
{
swp_entry_t entry;
entry.val = 0;
return entry;
}
#endif /* CONFIG_SWAP */
#ifdef CONFIG_THP_SWAP
extern int split_swap_cluster(swp_entry_t entry);
#else
static inline int split_swap_cluster(swp_entry_t entry)
{
return 0;
}
#endif
#ifdef CONFIG_MEMCG
static inline int mem_cgroup_swappiness(struct mem_cgroup *memcg)
{
/* Cgroup2 doesn't have per-cgroup swappiness */
if (cgroup_subsys_on_dfl(memory_cgrp_subsys))
return vm_swappiness;
/* root ? */
if (mem_cgroup_disabled() || !memcg->css.parent)
return vm_swappiness;
return memcg->swappiness;
}
#else
static inline int mem_cgroup_swappiness(struct mem_cgroup *mem)
{
return vm_swappiness;
}
#endif
#if defined(CONFIG_SWAP) && defined(CONFIG_MEMCG) && defined(CONFIG_BLK_CGROUP)
extern void mem_cgroup_throttle_swaprate(struct mem_cgroup *memcg, int node,
gfp_t gfp_mask);
#else
static inline void mem_cgroup_throttle_swaprate(struct mem_cgroup *memcg,
int node, gfp_t gfp_mask)
{
}
#endif
#ifdef CONFIG_MEMCG_SWAP
extern void mem_cgroup_swapout(struct page *page, swp_entry_t entry);
extern int mem_cgroup_try_charge_swap(struct page *page, swp_entry_t entry);
extern void mem_cgroup_uncharge_swap(swp_entry_t entry, unsigned int nr_pages);
extern long mem_cgroup_get_nr_swap_pages(struct mem_cgroup *memcg);
extern bool mem_cgroup_swap_full(struct page *page);
#else
static inline void mem_cgroup_swapout(struct page *page, swp_entry_t entry)
{
}
static inline int mem_cgroup_try_charge_swap(struct page *page,
swp_entry_t entry)
{
return 0;
}
static inline void mem_cgroup_uncharge_swap(swp_entry_t entry,
unsigned int nr_pages)
{
}
static inline long mem_cgroup_get_nr_swap_pages(struct mem_cgroup *memcg)
{
return get_nr_swap_pages();
}
static inline bool mem_cgroup_swap_full(struct page *page)
{
return vm_swap_full();
}
#endif
#endif /* __KERNEL__*/
#endif /* _LINUX_SWAP_H */