android_kernel_xiaomi_sm8350/mm/zsmalloc.c
Srinivasarao Pathipati 630e7df8c5 Merge android11-5.4.197+ (3970bc6) into msm-5.4
* refs/heads/tmp-3970bc6:
  UPSTREAM: Revert "net: af_key: add check for pfkey_broadcast in function pfkey_process"
  FROMGIT: arm64: fix oops in concurrently setting insn_emulation sysctls
  ANDROID: abi_gki_aarch64_qcom: Add vmemdup_user to qcom symbol list
  ANDROID: GKI: update Sony KMI symbol list
  UPSTREAM: mm: fix misplaced unlock_page in do_wp_page()
  BACKPORT: mm: do_wp_page() simplification
  UPSTREAM: mm/ksm: Remove reuse_ksm_page()
  BACKPORT: ALSA: pcm: Fix races among concurrent prealloc proc writes
  BACKPORT: ALSA: pcm: Fix races among concurrent prepare and hw_params/hw_free calls
  BACKPORT: ALSA: pcm: Fix races among concurrent read/write and buffer changes
  ANDROID: Fix up abi issue with struct snd_pcm_runtime
  BACKPORT: ALSA: pcm: Fix races among concurrent hw_params and hw_free calls
  BACKPORT: nfc: nfcmrvl: main: reorder destructive operations in nfcmrvl_nci_unregister_dev to avoid bugs
  Linux 5.4.197
  bpf: Enlarge offset check value to INT_MAX in bpf_skb_{load,store}_bytes
  NFSD: Fix possible sleep during nfsd4_release_lockowner()
  NFS: Memory allocation failures are not server fatal errors
  docs: submitting-patches: Fix crossref to 'The canonical patch format'
  tpm: ibmvtpm: Correct the return value in tpm_ibmvtpm_probe()
  tpm: Fix buffer access in tpm2_get_tpm_pt()
  HID: multitouch: Add support for Google Whiskers Touchpad
  raid5: introduce MD_BROKEN
  dm verity: set DM_TARGET_IMMUTABLE feature flag
  dm stats: add cond_resched when looping over entries
  dm crypt: make printing of the key constant-time
  dm integrity: fix error code in dm_integrity_ctr()
  zsmalloc: fix races between asynchronous zspage free and page migration
  crypto: ecrdsa - Fix incorrect use of vli_cmp
  netfilter: conntrack: re-fetch conntrack after insertion
  exec: Force single empty string when argv is empty
  drm/i915: Fix -Wstringop-overflow warning in call to intel_read_wm_latency()
  cfg80211: set custom regdomain after wiphy registration
  assoc_array: Fix BUG_ON during garbage collect
  drivers: i2c: thunderx: Allow driver to work with ACPI defined TWSI controllers
  i2c: ismt: Provide a DMA buffer for Interrupt Cause Logging
  net: ftgmac100: Disable hardware checksum on AST2600
  net: af_key: check encryption module availability consistency
  pinctrl: sunxi: fix f1c100s uart2 function
  ACPI: sysfs: Fix BERT error region memory mapping
  ACPI: sysfs: Make sparse happy about address space in use
  media: vim2m: initialize the media device earlier
  media: vim2m: Register video device after setting up internals
  secure_seq: use the 64 bits of the siphash for port offset calculation
  tcp: change source port randomizarion at connect() time
  Input: goodix - fix spurious key release events
  staging: rtl8723bs: prevent ->Ssid overflow in rtw_wx_set_scan()
  x86/pci/xen: Disable PCI/MSI[-X] masking for XEN_HVM guests
  lockdown: also lock down previous kgdb use
  Linux 5.4.196
  afs: Fix afs_getattr() to refetch file status if callback break occurred
  i2c: mt7621: fix missing clk_disable_unprepare() on error in mtk_i2c_probe()
  x86/xen: Mark cpu_bringup_and_idle() as dead_end_function
  x86/xen: fix booting 32-bit pv guest
  Reinstate some of "swiotlb: rework "fix info leak with DMA_FROM_DEVICE""
  ARM: dts: imx7: Use audio_mclk_post_div instead audio_mclk_root_clk
  firmware_loader: use kernel credentials when reading firmware
  net: stmmac: disable Split Header (SPH) for Intel platforms
  block: return ELEVATOR_DISCARD_MERGE if possible
  Input: ili210x - fix reset timing
  net: atlantic: verify hw_head_ lies within TX buffer ring
  net: stmmac: fix missing pci_disable_device() on error in stmmac_pci_probe()
  ethernet: tulip: fix missing pci_disable_device() on error in tulip_init_one()
  selftests: add ping test with ping_group_range tuned
  mac80211: fix rx reordering with non explicit / psmp ack policy
  scsi: qla2xxx: Fix missed DMA unmap for aborted commands
  perf bench numa: Address compiler error on s390
  gpio: mvebu/pwm: Refuse requests with inverted polarity
  gpio: gpio-vf610: do not touch other bits when set the target bit
  net: bridge: Clear offload_fwd_mark when passing frame up bridge interface.
  igb: skip phy status check where unavailable
  ARM: 9197/1: spectre-bhb: fix loop8 sequence for Thumb2
  ARM: 9196/1: spectre-bhb: enable for Cortex-A15
  net: af_key: add check for pfkey_broadcast in function pfkey_process
  net/mlx5e: Properly block LRO when XDP is enabled
  NFC: nci: fix sleep in atomic context bugs caused by nci_skb_alloc
  net/qla3xxx: Fix a test in ql_reset_work()
  clk: at91: generated: consider range when calculating best rate
  ice: fix possible under reporting of ethtool Tx and Rx statistics
  net: vmxnet3: fix possible NULL pointer dereference in vmxnet3_rq_cleanup()
  net: vmxnet3: fix possible use-after-free bugs in vmxnet3_rq_alloc_rx_buf()
  net/sched: act_pedit: sanitize shift argument before usage
  net: macb: Increment rx bd head after allocating skb and buffer
  ARM: dts: aspeed-g6: fix SPI1/SPI2 quad pin group
  ARM: dts: aspeed-g6: remove FWQSPID group in pinctrl dtsi
  dma-buf: fix use of DMA_BUF_SET_NAME_{A,B} in userspace
  drm/dp/mst: fix a possible memory leak in fetch_monitor_name()
  crypto: qcom-rng - fix infinite loop on requests not multiple of WORD_SZ
  KVM: x86/mmu: Update number of zapped pages even if page list is stable
  PCI/PM: Avoid putting Elo i2 PCIe Ports in D3cold
  Fix double fget() in vhost_net_set_backend()
  perf: Fix sys_perf_event_open() race against self
  ALSA: wavefront: Proper check of get_user() error
  SUNRPC: Ensure we flush any closed sockets before xs_xprt_free()
  SUNRPC: Don't call connect() more than once on a TCP socket
  SUNRPC: Prevent immediate close+reconnect
  SUNRPC: Clean up scheduling of autoclose
  mmc: core: Default to generic_cmd6_time as timeout in __mmc_switch()
  mmc: block: Use generic_cmd6_time when modifying INAND_CMD38_ARG_EXT_CSD
  mmc: core: Specify timeouts for BKOPS and CACHE_FLUSH for eMMC
  nilfs2: fix lockdep warnings during disk space reclamation
  nilfs2: fix lockdep warnings in page operations for btree nodes
  ARM: 9191/1: arm/stacktrace, kasan: Silence KASAN warnings in unwind_frame()
  platform/chrome: cros_ec_debugfs: detach log reader wq from devm
  drbd: remove usage of list iterator variable after loop
  MIPS: lantiq: check the return value of kzalloc()
  rtc: mc146818-lib: Fix the AltCentury for AMD platforms
  nvme-multipath: fix hang when disk goes live over reconnect
  ALSA: hda/realtek: Enable headset mic on Lenovo P360
  crypto: x86/chacha20 - Avoid spurious jumps to other functions
  crypto: stm32 - fix reference leak in stm32_crc_remove
  Input: stmfts - fix reference leak in stmfts_input_open
  Input: add bounds checking to input_set_capability()
  um: Cleanup syscall_handler_t definition/cast, fix warning
  rtc: fix use-after-free on device removal
  x86/xen: Make the secondary CPU idle tasks reliable
  x86/xen: Make the boot CPU idle task reliable
  floppy: use a statically allocated error counter
  ANDROID: fix up abi issue with struct snd_pcm_runtime
  Linux 5.4.195
  tty/serial: digicolor: fix possible null-ptr-deref in digicolor_uart_probe()
  ping: fix address binding wrt vrf
  arm[64]/memremap: don't abuse pfn_valid() to ensure presence of linear map
  net: phy: Fix race condition on link status change
  MIPS: fix build with gcc-12
  drm/vmwgfx: Initialize drm_mode_fb_cmd2
  cgroup/cpuset: Remove cpus_allowed/mems_allowed setup in cpuset_init_smp()
  i40e: i40e_main: fix a missing check on list iterator
  drm/nouveau/tegra: Stop using iommu_present()
  serial: 8250_mtk: Fix register address for XON/XOFF character
  serial: 8250_mtk: Fix UART_EFR register address
  slimbus: qcom: Fix IRQ check in qcom_slim_probe
  USB: serial: option: add Fibocom MA510 modem
  USB: serial: option: add Fibocom L610 modem
  USB: serial: qcserial: add support for Sierra Wireless EM7590
  USB: serial: pl2303: add device id for HP LM930 Display
  usb: typec: tcpci: Don't skip cleanup in .remove() on error
  usb: cdc-wdm: fix reading stuck on device close
  tty: n_gsm: fix mux activation issues in gsm_config()
  tcp: resalt the secret every 10 seconds
  net: emaclite: Don't advertise 1000BASE-T and do auto negotiation
  s390: disable -Warray-bounds
  ASoC: ops: Validate input values in snd_soc_put_volsw_range()
  ASoC: max98090: Generate notifications on changes for custom control
  ASoC: max98090: Reject invalid values in custom control put()
  hwmon: (f71882fg) Fix negative temperature
  gfs2: Fix filesystem block deallocation for short writes
  net: sfc: ef10: fix memory leak in efx_ef10_mtd_probe()
  net/smc: non blocking recvmsg() return -EAGAIN when no data and signal_pending
  net/sched: act_pedit: really ensure the skb is writable
  s390/lcs: fix variable dereferenced before check
  s390/ctcm: fix potential memory leak
  s390/ctcm: fix variable dereferenced before check
  hwmon: (ltq-cputemp) restrict it to SOC_XWAY
  dim: initialize all struct fields
  mac80211_hwsim: call ieee80211_tx_prepare_skb under RCU protection
  netlink: do not reset transport header in netlink_recvmsg()
  drm/nouveau: Fix a potential theorical leak in nouveau_get_backlight_name()
  ipv4: drop dst in multicast routing path
  net: Fix features skip in for_each_netdev_feature()
  mac80211: Reset MBSSID parameters upon connection
  hwmon: (tmp401) Add OF device ID table
  batman-adv: Don't skb_split skbuffs with frag_list
  Linux 5.4.194
  mm: userfaultfd: fix missing cache flush in mcopy_atomic_pte() and __mcopy_atomic()
  mm: hugetlb: fix missing cache flush in copy_huge_page_from_user()
  mm: fix missing cache flush for all tail pages of compound page
  Bluetooth: Fix the creation of hdev->name
  KVM: x86/svm: Account for family 17h event renumberings in amd_pmc_perf_hw_id
  x86: kprobes: Prohibit probing on instruction which has emulate prefix
  x86: xen: insn: Decode Xen and KVM emulate-prefix signature
  x86: xen: kvm: Gather the definition of emulate prefixes
  x86/asm: Allow to pass macros to __ASM_FORM()
  KVM: x86/pmu: Refactoring find_arch_event() to pmc_perf_hw_id()
  arm: remove CONFIG_ARCH_HAS_HOLES_MEMORYMODEL
  can: grcan: only use the NAPI poll budget for RX
  can: grcan: grcan_probe(): fix broken system id check for errata workaround needs
  nfp: bpf: silence bitwise vs. logical OR warning
  drm/i915: Cast remain to unsigned long in eb_relocate_vma
  drm/amd/display/dc/gpio/gpio_service: Pass around correct dce_{version, environment} types
  block: drbd: drbd_nl: Make conversion to 'enum drbd_ret_code' explicit
  MIPS: Use address-of operator on section symbols
  ANDROID: GKI: update the abi .xml file
  Revert "tcp: ensure to use the most recently sent skb when filling the rate sample"
  Linux 5.4.193
  mmc: rtsx: add 74 Clocks in power on flow
  PCI: aardvark: Fix reading MSI interrupt number
  PCI: aardvark: Clear all MSIs at setup
  dm: interlock pending dm_io and dm_wait_for_bios_completion
  dm: fix mempool NULL pointer race when completing IO
  tcp: make sure treq->af_specific is initialized
  ALSA: pcm: Fix potential AB/BA lock with buffer_mutex and mmap_lock
  ALSA: pcm: Fix races among concurrent prealloc proc writes
  ALSA: pcm: Fix races among concurrent prepare and hw_params/hw_free calls
  ALSA: pcm: Fix races among concurrent read/write and buffer changes
  ALSA: pcm: Fix races among concurrent hw_params and hw_free calls
  mm: fix unexpected zeroed page mapping with zram swap
  block-map: add __GFP_ZERO flag for alloc_page in function bio_copy_kern
  net: ipv6: ensure we call ipv6_mc_down() at most once
  KVM: LAPIC: Enable timer posted-interrupt only when mwait/hlt is advertised
  x86/kvm: Preserve BSP MSR_KVM_POLL_CONTROL across suspend/resume
  kvm: x86/cpuid: Only provide CPUID leaf 0xA if host has architectural PMU
  NFSv4: Don't invalidate inode attributes on delegation return
  drm/amdkfd: Use drm_priv to pass VM from KFD to amdgpu
  net: igmp: respect RCU rules in ip_mc_source() and ip_mc_msfilter()
  btrfs: always log symlinks in full mode
  smsc911x: allow using IRQ0
  bnxt_en: Fix possible bnxt_open() failure caused by wrong RFS flag
  selftests: mirror_gre_bridge_1q: Avoid changing PVID while interface is operational
  net: emaclite: Add error handling for of_address_to_resource()
  net: stmmac: dwmac-sun8i: add missing of_node_put() in sun8i_dwmac_register_mdio_mux()
  net: ethernet: mediatek: add missing of_node_put() in mtk_sgmii_init()
  RDMA/siw: Fix a condition race issue in MPA request processing
  ASoC: dmaengine: Restore NULL prepare_slave_config() callback
  hwmon: (adt7470) Fix warning on module removal
  NFC: netlink: fix sleep in atomic bug when firmware download timeout
  nfc: nfcmrvl: main: reorder destructive operations in nfcmrvl_nci_unregister_dev to avoid bugs
  nfc: replace improper check device_is_registered() in netlink related functions
  can: grcan: use ofdev->dev when allocating DMA memory
  can: grcan: grcan_close(): fix deadlock
  s390/dasd: Fix read inconsistency for ESE DASD devices
  s390/dasd: Fix read for ESE with blksize < 4k
  s390/dasd: prevent double format of tracks for ESE devices
  s390/dasd: fix data corruption for ESE devices
  ASoC: meson: Fix event generation for G12A tohdmi mux
  ASoC: wm8958: Fix change notifications for DSP controls
  ASoC: da7219: Fix change notifications for tone generator frequency
  genirq: Synchronize interrupt thread startup
  ACPICA: Always create namespace nodes using acpi_ns_create_node()
  firewire: core: extend card->lock in fw_core_handle_bus_reset
  firewire: remove check of list iterator against head past the loop body
  firewire: fix potential uaf in outbound_phy_packet_callback()
  Revert "SUNRPC: attempt AF_LOCAL connect on setup"
  gpiolib: of: fix bounds check for 'gpio-reserved-ranges'
  ALSA: fireworks: fix wrong return count shorter than expected by 4 bytes
  parisc: Merge model and model name into one line in /proc/cpuinfo
  MIPS: Fix CP0 counter erratum detection for R4k CPUs
  Linux 5.4.192
  mm, hugetlb: allow for "high" userspace addresses
  hugetlbfs: get unmapped area below TASK_UNMAPPED_BASE for hugetlbfs
  tty: n_gsm: fix incorrect UA handling
  tty: n_gsm: fix wrong command frame length field encoding
  tty: n_gsm: fix wrong command retry handling
  tty: n_gsm: fix missing explicit ldisc flush
  tty: n_gsm: fix insufficient txframe size
  netfilter: nft_socket: only do sk lookups when indev is available
  tty: n_gsm: fix malformed counter for out of frame data
  tty: n_gsm: fix wrong signal octet encoding in convergence layer type 2
  x86/cpu: Load microcode during restore_processor_state()
  net: ethernet: stmmac: fix write to sgmii_adapter_base
  drivers: net: hippi: Fix deadlock in rr_close()
  cifs: destage any unwritten data to the server before calling copychunk_write
  x86: __memcpy_flushcache: fix wrong alignment if size > 2^32
  ip6_gre: Avoid updating tunnel->tun_hlen in __gre6_xmit()
  ASoC: wm8731: Disable the regulator when probing fails
  tcp: fix F-RTO may not work correctly when receiving DSACK
  ixgbe: ensure IPsec VF<->PF compatibility
  bnx2x: fix napi API usage sequence
  tls: Skip tls_append_frag on zero copy size
  drm/amd/display: Fix memory leak in dcn21_clock_source_create
  net: dsa: lantiq_gswip: Don't set GSWIP_MII_CFG_RMII_CLK
  net: bcmgenet: hide status block before TX timestamping
  clk: sunxi: sun9i-mmc: check return value after calling platform_get_resource()
  bus: sunxi-rsb: Fix the return value of sunxi_rsb_device_create()
  tcp: fix potential xmit stalls caused by TCP_NOTSENT_LOWAT
  ip_gre: Make o_seqno start from 0 in native mode
  net/smc: sync err code when tcp connection was refused
  net: hns3: add validity check for message data length
  cpufreq: fix memory leak in sun50i_cpufreq_nvmem_probe
  pinctrl: pistachio: fix use of irq_of_parse_and_map()
  arm64: dts: imx8mn-ddr4-evk: Describe the 32.768 kHz PMIC clock
  ARM: dts: imx6ull-colibri: fix vqmmc regulator
  sctp: check asoc strreset_chunk in sctp_generate_reconf_event
  tcp: ensure to use the most recently sent skb when filling the rate sample
  tcp: md5: incorrect tcp_header_len for incoming connections
  bpf, lwt: Fix crash when using bpf_skb_set_tunnel_key() from bpf_xmit lwt hook
  mtd: rawnand: Fix return value check of wait_for_completion_timeout
  ipvs: correctly print the memory size of ip_vs_conn_tab
  ARM: dts: logicpd-som-lv: Fix wrong pinmuxing on OMAP35
  ARM: dts: am3517-evm: Fix misc pinmuxing
  ARM: dts: Fix mmc order for omap3-gta04
  phy: ti: Add missing pm_runtime_disable() in serdes_am654_probe
  phy: mapphone-mdm6600: Fix PM error handling in phy_mdm6600_probe
  ARM: dts: at91: Map MCLK for wm8731 on at91sam9g20ek
  phy: ti: omap-usb2: Fix error handling in omap_usb2_enable_clocks
  ARM: OMAP2+: Fix refcount leak in omap_gic_of_init
  phy: samsung: exynos5250-sata: fix missing device put in probe error paths
  phy: samsung: Fix missing of_node_put() in exynos_sata_phy_probe
  ARM: dts: imx6qdl-apalis: Fix sgtl5000 detection issue
  USB: Fix xhci event ring dequeue pointer ERDP update issue
  mtd: rawnand: fix ecc parameters for mt7622
  arm64: dts: meson: remove CPU opps below 1GHz for SM1 boards
  arm64: dts: meson: remove CPU opps below 1GHz for G12B boards
  video: fbdev: udlfb: properly check endpoint type
  hex2bin: fix access beyond string end
  hex2bin: make the function hex_to_bin constant-time
  arch_topology: Do not set llc_sibling if llc_id is invalid
  serial: 8250: Correct the clock for EndRun PTP/1588 PCIe device
  serial: 8250: Also set sticky MCR bits in console restoration
  serial: imx: fix overrun interrupts in DMA mode
  usb: dwc3: gadget: Return proper request status
  usb: dwc3: core: Fix tx/rx threshold settings
  usb: gadget: configfs: clear deactivation flag in configfs_composite_unbind()
  usb: gadget: uvc: Fix crash when encoding data for usb request
  usb: typec: ucsi: Fix role swapping
  usb: misc: fix improper handling of refcount in uss720_probe()
  iio: magnetometer: ak8975: Fix the error handling in ak8975_power_on()
  iio: dac: ad5446: Fix read_raw not returning set value
  iio: dac: ad5592r: Fix the missing return value.
  xhci: increase usb U3 -> U0 link resume timeout from 100ms to 500ms
  xhci: stop polling roothubs after shutdown
  USB: serial: option: add Telit 0x1057, 0x1058, 0x1075 compositions
  USB: serial: option: add support for Cinterion MV32-WA/MV32-WB
  USB: serial: cp210x: add PIDs for Kamstrup USB Meter Reader
  USB: serial: whiteheat: fix heap overflow in WHITEHEAT_GET_DTR_RTS
  USB: quirks: add STRING quirk for VCOM device
  USB: quirks: add a Realtek card reader
  usb: mtu3: fix USB 3.0 dual-role-switch from device to host
  lightnvm: disable the subsystem
  hamradio: remove needs_free_netdev to avoid UAF
  hamradio: defer 6pack kfree after unregister_netdev
  floppy: disable FDRAWCMD by default

 Conflicts:
	drivers/usb/dwc3/gadget.c
	include/linux/dma-mapping.h
	include/linux/stmmac.h
	mm/memory.c

Change-Id: I3bf49e11ae4aeaf1db353efbdfee950cd12de8cf
Signed-off-by: Srinivasarao Pathipati <quic_c_spathi@quicinc.com>
2022-08-16 16:52:01 +05:30

2582 lines
62 KiB
C

/*
* zsmalloc memory allocator
*
* Copyright (C) 2011 Nitin Gupta
* Copyright (C) 2012, 2013 Minchan Kim
*
* This code is released using a dual license strategy: BSD/GPL
* You can choose the license that better fits your requirements.
*
* Released under the terms of 3-clause BSD License
* Released under the terms of GNU General Public License Version 2.0
*/
/*
* Following is how we use various fields and flags of underlying
* struct page(s) to form a zspage.
*
* Usage of struct page fields:
* page->private: points to zspage
* page->freelist(index): links together all component pages of a zspage
* For the huge page, this is always 0, so we use this field
* to store handle.
* page->units: first object offset in a subpage of zspage
*
* Usage of struct page flags:
* PG_private: identifies the first component page
* PG_owner_priv_1: identifies the huge component page
*
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/module.h>
#include <linux/kernel.h>
#include <linux/sched.h>
#include <linux/magic.h>
#include <linux/bitops.h>
#include <linux/errno.h>
#include <linux/highmem.h>
#include <linux/string.h>
#include <linux/slab.h>
#include <asm/tlbflush.h>
#include <asm/pgtable.h>
#include <linux/cpumask.h>
#include <linux/cpu.h>
#include <linux/vmalloc.h>
#include <linux/preempt.h>
#include <linux/spinlock.h>
#include <linux/shrinker.h>
#include <linux/types.h>
#include <linux/debugfs.h>
#include <linux/zsmalloc.h>
#include <linux/zpool.h>
#include <linux/mount.h>
#include <linux/pseudo_fs.h>
#include <linux/migrate.h>
#include <linux/wait.h>
#include <linux/pagemap.h>
#include <linux/fs.h>
#define ZSPAGE_MAGIC 0x58
/*
* This must be power of 2 and greater than of equal to sizeof(link_free).
* These two conditions ensure that any 'struct link_free' itself doesn't
* span more than 1 page which avoids complex case of mapping 2 pages simply
* to restore link_free pointer values.
*/
#define ZS_ALIGN 8
/*
* A single 'zspage' is composed of up to 2^N discontiguous 0-order (single)
* pages. ZS_MAX_ZSPAGE_ORDER defines upper limit on N.
*/
#define ZS_MAX_ZSPAGE_ORDER 2
#define ZS_MAX_PAGES_PER_ZSPAGE (_AC(1, UL) << ZS_MAX_ZSPAGE_ORDER)
#define ZS_HANDLE_SIZE (sizeof(unsigned long))
/*
* Object location (<PFN>, <obj_idx>) is encoded as
* as single (unsigned long) handle value.
*
* Note that object index <obj_idx> starts from 0.
*
* This is made more complicated by various memory models and PAE.
*/
#ifndef MAX_POSSIBLE_PHYSMEM_BITS
#ifdef MAX_PHYSMEM_BITS
#define MAX_POSSIBLE_PHYSMEM_BITS MAX_PHYSMEM_BITS
#else
/*
* If this definition of MAX_PHYSMEM_BITS is used, OBJ_INDEX_BITS will just
* be PAGE_SHIFT
*/
#define MAX_POSSIBLE_PHYSMEM_BITS BITS_PER_LONG
#endif
#endif
#define _PFN_BITS (MAX_POSSIBLE_PHYSMEM_BITS - PAGE_SHIFT)
/*
* Memory for allocating for handle keeps object position by
* encoding <page, obj_idx> and the encoded value has a room
* in least bit(ie, look at obj_to_location).
* We use the bit to synchronize between object access by
* user and migration.
*/
#define HANDLE_PIN_BIT 0
/*
* Head in allocated object should have OBJ_ALLOCATED_TAG
* to identify the object was allocated or not.
* It's okay to add the status bit in the least bit because
* header keeps handle which is 4byte-aligned address so we
* have room for two bit at least.
*/
#define OBJ_ALLOCATED_TAG 1
#define OBJ_TAG_BITS 1
#define OBJ_INDEX_BITS (BITS_PER_LONG - _PFN_BITS - OBJ_TAG_BITS)
#define OBJ_INDEX_MASK ((_AC(1, UL) << OBJ_INDEX_BITS) - 1)
#define FULLNESS_BITS 2
#define CLASS_BITS 8
#define ISOLATED_BITS 3
#define MAGIC_VAL_BITS 8
#define MAX(a, b) ((a) >= (b) ? (a) : (b))
/* ZS_MIN_ALLOC_SIZE must be multiple of ZS_ALIGN */
#define ZS_MIN_ALLOC_SIZE \
MAX(32, (ZS_MAX_PAGES_PER_ZSPAGE << PAGE_SHIFT >> OBJ_INDEX_BITS))
/* each chunk includes extra space to keep handle */
#define ZS_MAX_ALLOC_SIZE PAGE_SIZE
/*
* On systems with 4K page size, this gives 255 size classes! There is a
* trader-off here:
* - Large number of size classes is potentially wasteful as free page are
* spread across these classes
* - Small number of size classes causes large internal fragmentation
* - Probably its better to use specific size classes (empirically
* determined). NOTE: all those class sizes must be set as multiple of
* ZS_ALIGN to make sure link_free itself never has to span 2 pages.
*
* ZS_MIN_ALLOC_SIZE and ZS_SIZE_CLASS_DELTA must be multiple of ZS_ALIGN
* (reason above)
*/
#define ZS_SIZE_CLASS_DELTA (PAGE_SIZE >> CLASS_BITS)
#define ZS_SIZE_CLASSES (DIV_ROUND_UP(ZS_MAX_ALLOC_SIZE - ZS_MIN_ALLOC_SIZE, \
ZS_SIZE_CLASS_DELTA) + 1)
enum fullness_group {
ZS_EMPTY,
ZS_ALMOST_EMPTY,
ZS_ALMOST_FULL,
ZS_FULL,
NR_ZS_FULLNESS,
};
enum zs_stat_type {
CLASS_EMPTY,
CLASS_ALMOST_EMPTY,
CLASS_ALMOST_FULL,
CLASS_FULL,
OBJ_ALLOCATED,
OBJ_USED,
NR_ZS_STAT_TYPE,
};
struct zs_size_stat {
unsigned long objs[NR_ZS_STAT_TYPE];
};
#ifdef CONFIG_ZSMALLOC_STAT
static struct dentry *zs_stat_root;
#endif
#ifdef CONFIG_COMPACTION
static struct vfsmount *zsmalloc_mnt;
#endif
/*
* We assign a page to ZS_ALMOST_EMPTY fullness group when:
* n <= N / f, where
* n = number of allocated objects
* N = total number of objects zspage can store
* f = fullness_threshold_frac
*
* Similarly, we assign zspage to:
* ZS_ALMOST_FULL when n > N / f
* ZS_EMPTY when n == 0
* ZS_FULL when n == N
*
* (see: fix_fullness_group())
*/
static const int fullness_threshold_frac = 4;
static size_t huge_class_size;
struct size_class {
spinlock_t lock;
struct list_head fullness_list[NR_ZS_FULLNESS];
/*
* Size of objects stored in this class. Must be multiple
* of ZS_ALIGN.
*/
int size;
int objs_per_zspage;
/* Number of PAGE_SIZE sized pages to combine to form a 'zspage' */
int pages_per_zspage;
unsigned int index;
struct zs_size_stat stats;
};
/* huge object: pages_per_zspage == 1 && maxobj_per_zspage == 1 */
static void SetPageHugeObject(struct page *page)
{
SetPageOwnerPriv1(page);
}
static void ClearPageHugeObject(struct page *page)
{
ClearPageOwnerPriv1(page);
}
static int PageHugeObject(struct page *page)
{
return PageOwnerPriv1(page);
}
/*
* Placed within free objects to form a singly linked list.
* For every zspage, zspage->freeobj gives head of this list.
*
* This must be power of 2 and less than or equal to ZS_ALIGN
*/
struct link_free {
union {
/*
* Free object index;
* It's valid for non-allocated object
*/
unsigned long next;
/*
* Handle of allocated object.
*/
unsigned long handle;
};
};
struct zs_pool {
const char *name;
struct size_class *size_class[ZS_SIZE_CLASSES];
struct kmem_cache *handle_cachep;
struct kmem_cache *zspage_cachep;
atomic_long_t pages_allocated;
struct zs_pool_stats stats;
/* Compact classes */
struct shrinker shrinker;
#ifdef CONFIG_ZSMALLOC_STAT
struct dentry *stat_dentry;
#endif
#ifdef CONFIG_COMPACTION
struct inode *inode;
struct work_struct free_work;
/* A wait queue for when migration races with async_free_zspage() */
struct wait_queue_head migration_wait;
atomic_long_t isolated_pages;
bool destroying;
#endif
};
struct zspage {
struct {
unsigned int fullness:FULLNESS_BITS;
unsigned int class:CLASS_BITS + 1;
unsigned int isolated:ISOLATED_BITS;
unsigned int magic:MAGIC_VAL_BITS;
};
unsigned int inuse;
unsigned int freeobj;
struct page *first_page;
struct list_head list; /* fullness list */
#ifdef CONFIG_COMPACTION
rwlock_t lock;
#endif
};
struct mapping_area {
char *vm_buf; /* copy buffer for objects that span pages */
char *vm_addr; /* address of kmap_atomic()'ed pages */
enum zs_mapmode vm_mm; /* mapping mode */
};
#ifdef CONFIG_COMPACTION
static int zs_register_migration(struct zs_pool *pool);
static void zs_unregister_migration(struct zs_pool *pool);
static void migrate_lock_init(struct zspage *zspage);
static void migrate_read_lock(struct zspage *zspage);
static void migrate_read_unlock(struct zspage *zspage);
static void kick_deferred_free(struct zs_pool *pool);
static void init_deferred_free(struct zs_pool *pool);
static void SetZsPageMovable(struct zs_pool *pool, struct zspage *zspage);
#else
static int zsmalloc_mount(void) { return 0; }
static void zsmalloc_unmount(void) {}
static int zs_register_migration(struct zs_pool *pool) { return 0; }
static void zs_unregister_migration(struct zs_pool *pool) {}
static void migrate_lock_init(struct zspage *zspage) {}
static void migrate_read_lock(struct zspage *zspage) {}
static void migrate_read_unlock(struct zspage *zspage) {}
static void kick_deferred_free(struct zs_pool *pool) {}
static void init_deferred_free(struct zs_pool *pool) {}
static void SetZsPageMovable(struct zs_pool *pool, struct zspage *zspage) {}
#endif
static int create_cache(struct zs_pool *pool)
{
pool->handle_cachep = kmem_cache_create("zs_handle", ZS_HANDLE_SIZE,
0, 0, NULL);
if (!pool->handle_cachep)
return 1;
pool->zspage_cachep = kmem_cache_create("zspage", sizeof(struct zspage),
0, 0, NULL);
if (!pool->zspage_cachep) {
kmem_cache_destroy(pool->handle_cachep);
pool->handle_cachep = NULL;
return 1;
}
return 0;
}
static void destroy_cache(struct zs_pool *pool)
{
kmem_cache_destroy(pool->handle_cachep);
kmem_cache_destroy(pool->zspage_cachep);
}
static unsigned long cache_alloc_handle(struct zs_pool *pool, gfp_t gfp)
{
return (unsigned long)kmem_cache_alloc(pool->handle_cachep, gfp &
~(__GFP_HIGHMEM|__GFP_MOVABLE|__GFP_CMA|__GFP_OFFLINABLE));
}
static void cache_free_handle(struct zs_pool *pool, unsigned long handle)
{
kmem_cache_free(pool->handle_cachep, (void *)handle);
}
static struct zspage *cache_alloc_zspage(struct zs_pool *pool, gfp_t flags)
{
return kmem_cache_alloc(pool->zspage_cachep, flags &
~(__GFP_HIGHMEM|__GFP_MOVABLE|__GFP_CMA|__GFP_OFFLINABLE));
}
static void cache_free_zspage(struct zs_pool *pool, struct zspage *zspage)
{
kmem_cache_free(pool->zspage_cachep, zspage);
}
static void record_obj(unsigned long handle, unsigned long obj)
{
/*
* lsb of @obj represents handle lock while other bits
* represent object value the handle is pointing so
* updating shouldn't do store tearing.
*/
WRITE_ONCE(*(unsigned long *)handle, obj);
}
/* zpool driver */
#ifdef CONFIG_ZPOOL
static void *zs_zpool_create(const char *name, gfp_t gfp,
const struct zpool_ops *zpool_ops,
struct zpool *zpool)
{
/*
* Ignore global gfp flags: zs_malloc() may be invoked from
* different contexts and its caller must provide a valid
* gfp mask.
*/
return zs_create_pool(name);
}
static void zs_zpool_destroy(void *pool)
{
zs_destroy_pool(pool);
}
static int zs_zpool_malloc(void *pool, size_t size, gfp_t gfp,
unsigned long *handle)
{
*handle = zs_malloc(pool, size, gfp);
return *handle ? 0 : -1;
}
static void zs_zpool_free(void *pool, unsigned long handle)
{
zs_free(pool, handle);
}
static void *zs_zpool_map(void *pool, unsigned long handle,
enum zpool_mapmode mm)
{
enum zs_mapmode zs_mm;
switch (mm) {
case ZPOOL_MM_RO:
zs_mm = ZS_MM_RO;
break;
case ZPOOL_MM_WO:
zs_mm = ZS_MM_WO;
break;
case ZPOOL_MM_RW: /* fall through */
default:
zs_mm = ZS_MM_RW;
break;
}
return zs_map_object(pool, handle, zs_mm);
}
static void zs_zpool_unmap(void *pool, unsigned long handle)
{
zs_unmap_object(pool, handle);
}
static u64 zs_zpool_total_size(void *pool)
{
return zs_get_total_pages(pool) << PAGE_SHIFT;
}
static struct zpool_driver zs_zpool_driver = {
.type = "zsmalloc",
.owner = THIS_MODULE,
.create = zs_zpool_create,
.destroy = zs_zpool_destroy,
.malloc_support_movable = true,
.malloc = zs_zpool_malloc,
.free = zs_zpool_free,
.map = zs_zpool_map,
.unmap = zs_zpool_unmap,
.total_size = zs_zpool_total_size,
};
MODULE_ALIAS("zpool-zsmalloc");
#endif /* CONFIG_ZPOOL */
/* per-cpu VM mapping areas for zspage accesses that cross page boundaries */
static DEFINE_PER_CPU(struct mapping_area, zs_map_area);
static bool is_zspage_isolated(struct zspage *zspage)
{
return zspage->isolated;
}
static __maybe_unused int is_first_page(struct page *page)
{
return PagePrivate(page);
}
/* Protected by class->lock */
static inline int get_zspage_inuse(struct zspage *zspage)
{
return zspage->inuse;
}
static inline void mod_zspage_inuse(struct zspage *zspage, int val)
{
zspage->inuse += val;
}
static inline struct page *get_first_page(struct zspage *zspage)
{
struct page *first_page = zspage->first_page;
VM_BUG_ON_PAGE(!is_first_page(first_page), first_page);
return first_page;
}
static inline int get_first_obj_offset(struct page *page)
{
return page->units;
}
static inline void set_first_obj_offset(struct page *page, int offset)
{
page->units = offset;
}
static inline unsigned int get_freeobj(struct zspage *zspage)
{
return zspage->freeobj;
}
static inline void set_freeobj(struct zspage *zspage, unsigned int obj)
{
zspage->freeobj = obj;
}
static void get_zspage_mapping(struct zspage *zspage,
unsigned int *class_idx,
enum fullness_group *fullness)
{
BUG_ON(zspage->magic != ZSPAGE_MAGIC);
*fullness = zspage->fullness;
*class_idx = zspage->class;
}
static void set_zspage_mapping(struct zspage *zspage,
unsigned int class_idx,
enum fullness_group fullness)
{
zspage->class = class_idx;
zspage->fullness = fullness;
}
/*
* zsmalloc divides the pool into various size classes where each
* class maintains a list of zspages where each zspage is divided
* into equal sized chunks. Each allocation falls into one of these
* classes depending on its size. This function returns index of the
* size class which has chunk size big enough to hold the give size.
*/
static int get_size_class_index(int size)
{
int idx = 0;
if (likely(size > ZS_MIN_ALLOC_SIZE))
idx = DIV_ROUND_UP(size - ZS_MIN_ALLOC_SIZE,
ZS_SIZE_CLASS_DELTA);
return min_t(int, ZS_SIZE_CLASSES - 1, idx);
}
/* type can be of enum type zs_stat_type or fullness_group */
static inline void zs_stat_inc(struct size_class *class,
int type, unsigned long cnt)
{
class->stats.objs[type] += cnt;
}
/* type can be of enum type zs_stat_type or fullness_group */
static inline void zs_stat_dec(struct size_class *class,
int type, unsigned long cnt)
{
class->stats.objs[type] -= cnt;
}
/* type can be of enum type zs_stat_type or fullness_group */
static inline unsigned long zs_stat_get(struct size_class *class,
int type)
{
return class->stats.objs[type];
}
#ifdef CONFIG_ZSMALLOC_STAT
static void __init zs_stat_init(void)
{
if (!debugfs_initialized()) {
pr_warn("debugfs not available, stat dir not created\n");
return;
}
zs_stat_root = debugfs_create_dir("zsmalloc", NULL);
}
static void __exit zs_stat_exit(void)
{
debugfs_remove_recursive(zs_stat_root);
}
static unsigned long zs_can_compact(struct size_class *class);
static int zs_stats_size_show(struct seq_file *s, void *v)
{
int i;
struct zs_pool *pool = s->private;
struct size_class *class;
int objs_per_zspage;
unsigned long class_almost_full, class_almost_empty;
unsigned long obj_allocated, obj_used, pages_used, freeable;
unsigned long total_class_almost_full = 0, total_class_almost_empty = 0;
unsigned long total_objs = 0, total_used_objs = 0, total_pages = 0;
unsigned long total_freeable = 0;
seq_printf(s, " %5s %5s %11s %12s %13s %10s %10s %16s %8s\n",
"class", "size", "almost_full", "almost_empty",
"obj_allocated", "obj_used", "pages_used",
"pages_per_zspage", "freeable");
for (i = 0; i < ZS_SIZE_CLASSES; i++) {
class = pool->size_class[i];
if (class->index != i)
continue;
spin_lock(&class->lock);
class_almost_full = zs_stat_get(class, CLASS_ALMOST_FULL);
class_almost_empty = zs_stat_get(class, CLASS_ALMOST_EMPTY);
obj_allocated = zs_stat_get(class, OBJ_ALLOCATED);
obj_used = zs_stat_get(class, OBJ_USED);
freeable = zs_can_compact(class);
spin_unlock(&class->lock);
objs_per_zspage = class->objs_per_zspage;
pages_used = obj_allocated / objs_per_zspage *
class->pages_per_zspage;
seq_printf(s, " %5u %5u %11lu %12lu %13lu"
" %10lu %10lu %16d %8lu\n",
i, class->size, class_almost_full, class_almost_empty,
obj_allocated, obj_used, pages_used,
class->pages_per_zspage, freeable);
total_class_almost_full += class_almost_full;
total_class_almost_empty += class_almost_empty;
total_objs += obj_allocated;
total_used_objs += obj_used;
total_pages += pages_used;
total_freeable += freeable;
}
seq_puts(s, "\n");
seq_printf(s, " %5s %5s %11lu %12lu %13lu %10lu %10lu %16s %8lu\n",
"Total", "", total_class_almost_full,
total_class_almost_empty, total_objs,
total_used_objs, total_pages, "", total_freeable);
return 0;
}
DEFINE_SHOW_ATTRIBUTE(zs_stats_size);
static void zs_pool_stat_create(struct zs_pool *pool, const char *name)
{
if (!zs_stat_root) {
pr_warn("no root stat dir, not creating <%s> stat dir\n", name);
return;
}
pool->stat_dentry = debugfs_create_dir(name, zs_stat_root);
debugfs_create_file("classes", S_IFREG | 0444, pool->stat_dentry, pool,
&zs_stats_size_fops);
}
static void zs_pool_stat_destroy(struct zs_pool *pool)
{
debugfs_remove_recursive(pool->stat_dentry);
}
#else /* CONFIG_ZSMALLOC_STAT */
static void __init zs_stat_init(void)
{
}
static void __exit zs_stat_exit(void)
{
}
static inline void zs_pool_stat_create(struct zs_pool *pool, const char *name)
{
}
static inline void zs_pool_stat_destroy(struct zs_pool *pool)
{
}
#endif
/*
* For each size class, zspages are divided into different groups
* depending on how "full" they are. This was done so that we could
* easily find empty or nearly empty zspages when we try to shrink
* the pool (not yet implemented). This function returns fullness
* status of the given page.
*/
static enum fullness_group get_fullness_group(struct size_class *class,
struct zspage *zspage)
{
int inuse, objs_per_zspage;
enum fullness_group fg;
inuse = get_zspage_inuse(zspage);
objs_per_zspage = class->objs_per_zspage;
if (inuse == 0)
fg = ZS_EMPTY;
else if (inuse == objs_per_zspage)
fg = ZS_FULL;
else if (inuse <= 3 * objs_per_zspage / fullness_threshold_frac)
fg = ZS_ALMOST_EMPTY;
else
fg = ZS_ALMOST_FULL;
return fg;
}
/*
* Each size class maintains various freelists and zspages are assigned
* to one of these freelists based on the number of live objects they
* have. This functions inserts the given zspage into the freelist
* identified by <class, fullness_group>.
*/
static void insert_zspage(struct size_class *class,
struct zspage *zspage,
enum fullness_group fullness)
{
struct zspage *head;
zs_stat_inc(class, fullness, 1);
head = list_first_entry_or_null(&class->fullness_list[fullness],
struct zspage, list);
/*
* We want to see more ZS_FULL pages and less almost empty/full.
* Put pages with higher ->inuse first.
*/
if (head) {
if (get_zspage_inuse(zspage) < get_zspage_inuse(head)) {
list_add(&zspage->list, &head->list);
return;
}
}
list_add(&zspage->list, &class->fullness_list[fullness]);
}
/*
* This function removes the given zspage from the freelist identified
* by <class, fullness_group>.
*/
static void remove_zspage(struct size_class *class,
struct zspage *zspage,
enum fullness_group fullness)
{
VM_BUG_ON(list_empty(&class->fullness_list[fullness]));
VM_BUG_ON(is_zspage_isolated(zspage));
list_del_init(&zspage->list);
zs_stat_dec(class, fullness, 1);
}
/*
* Each size class maintains zspages in different fullness groups depending
* on the number of live objects they contain. When allocating or freeing
* objects, the fullness status of the page can change, say, from ALMOST_FULL
* to ALMOST_EMPTY when freeing an object. This function checks if such
* a status change has occurred for the given page and accordingly moves the
* page from the freelist of the old fullness group to that of the new
* fullness group.
*/
static enum fullness_group fix_fullness_group(struct size_class *class,
struct zspage *zspage)
{
int class_idx;
enum fullness_group currfg, newfg;
get_zspage_mapping(zspage, &class_idx, &currfg);
newfg = get_fullness_group(class, zspage);
if (newfg == currfg)
goto out;
if (!is_zspage_isolated(zspage)) {
remove_zspage(class, zspage, currfg);
insert_zspage(class, zspage, newfg);
}
set_zspage_mapping(zspage, class_idx, newfg);
out:
return newfg;
}
/*
* We have to decide on how many pages to link together
* to form a zspage for each size class. This is important
* to reduce wastage due to unusable space left at end of
* each zspage which is given as:
* wastage = Zp % class_size
* usage = Zp - wastage
* where Zp = zspage size = k * PAGE_SIZE where k = 1, 2, ...
*
* For example, for size class of 3/8 * PAGE_SIZE, we should
* link together 3 PAGE_SIZE sized pages to form a zspage
* since then we can perfectly fit in 8 such objects.
*/
static int get_pages_per_zspage(int class_size)
{
int i, max_usedpc = 0;
/* zspage order which gives maximum used size per KB */
int max_usedpc_order = 1;
for (i = 1; i <= ZS_MAX_PAGES_PER_ZSPAGE; i++) {
int zspage_size;
int waste, usedpc;
zspage_size = i * PAGE_SIZE;
waste = zspage_size % class_size;
usedpc = (zspage_size - waste) * 100 / zspage_size;
if (usedpc > max_usedpc) {
max_usedpc = usedpc;
max_usedpc_order = i;
}
}
return max_usedpc_order;
}
static struct zspage *get_zspage(struct page *page)
{
struct zspage *zspage = (struct zspage *)page->private;
BUG_ON(zspage->magic != ZSPAGE_MAGIC);
return zspage;
}
static struct page *get_next_page(struct page *page)
{
if (unlikely(PageHugeObject(page)))
return NULL;
return page->freelist;
}
/**
* obj_to_location - get (<page>, <obj_idx>) from encoded object value
* @obj: the encoded object value
* @page: page object resides in zspage
* @obj_idx: object index
*/
static void obj_to_location(unsigned long obj, struct page **page,
unsigned int *obj_idx)
{
obj >>= OBJ_TAG_BITS;
*page = pfn_to_page(obj >> OBJ_INDEX_BITS);
*obj_idx = (obj & OBJ_INDEX_MASK);
}
/**
* location_to_obj - get obj value encoded from (<page>, <obj_idx>)
* @page: page object resides in zspage
* @obj_idx: object index
*/
static unsigned long location_to_obj(struct page *page, unsigned int obj_idx)
{
unsigned long obj;
obj = page_to_pfn(page) << OBJ_INDEX_BITS;
obj |= obj_idx & OBJ_INDEX_MASK;
obj <<= OBJ_TAG_BITS;
return obj;
}
static unsigned long handle_to_obj(unsigned long handle)
{
return *(unsigned long *)handle;
}
static unsigned long obj_to_head(struct page *page, void *obj)
{
if (unlikely(PageHugeObject(page))) {
VM_BUG_ON_PAGE(!is_first_page(page), page);
return page->index;
} else
return *(unsigned long *)obj;
}
static inline int testpin_tag(unsigned long handle)
{
return bit_spin_is_locked(HANDLE_PIN_BIT, (unsigned long *)handle);
}
static inline int trypin_tag(unsigned long handle)
{
return bit_spin_trylock(HANDLE_PIN_BIT, (unsigned long *)handle);
}
static void pin_tag(unsigned long handle)
{
bit_spin_lock(HANDLE_PIN_BIT, (unsigned long *)handle);
}
static void unpin_tag(unsigned long handle)
{
bit_spin_unlock(HANDLE_PIN_BIT, (unsigned long *)handle);
}
static void reset_page(struct page *page)
{
__ClearPageMovable(page);
ClearPagePrivate(page);
set_page_private(page, 0);
page_mapcount_reset(page);
ClearPageHugeObject(page);
page->freelist = NULL;
}
static int trylock_zspage(struct zspage *zspage)
{
struct page *cursor, *fail;
for (cursor = get_first_page(zspage); cursor != NULL; cursor =
get_next_page(cursor)) {
if (!trylock_page(cursor)) {
fail = cursor;
goto unlock;
}
}
return 1;
unlock:
for (cursor = get_first_page(zspage); cursor != fail; cursor =
get_next_page(cursor))
unlock_page(cursor);
return 0;
}
static void __free_zspage(struct zs_pool *pool, struct size_class *class,
struct zspage *zspage)
{
struct page *page, *next;
enum fullness_group fg;
unsigned int class_idx;
get_zspage_mapping(zspage, &class_idx, &fg);
assert_spin_locked(&class->lock);
VM_BUG_ON(get_zspage_inuse(zspage));
VM_BUG_ON(fg != ZS_EMPTY);
next = page = get_first_page(zspage);
do {
VM_BUG_ON_PAGE(!PageLocked(page), page);
next = get_next_page(page);
reset_page(page);
unlock_page(page);
dec_zone_page_state(page, NR_ZSPAGES);
put_page(page);
page = next;
} while (page != NULL);
cache_free_zspage(pool, zspage);
zs_stat_dec(class, OBJ_ALLOCATED, class->objs_per_zspage);
atomic_long_sub(class->pages_per_zspage,
&pool->pages_allocated);
}
static void free_zspage(struct zs_pool *pool, struct size_class *class,
struct zspage *zspage)
{
VM_BUG_ON(get_zspage_inuse(zspage));
VM_BUG_ON(list_empty(&zspage->list));
if (!trylock_zspage(zspage)) {
kick_deferred_free(pool);
return;
}
remove_zspage(class, zspage, ZS_EMPTY);
__free_zspage(pool, class, zspage);
}
/* Initialize a newly allocated zspage */
static void init_zspage(struct size_class *class, struct zspage *zspage)
{
unsigned int freeobj = 1;
unsigned long off = 0;
struct page *page = get_first_page(zspage);
while (page) {
struct page *next_page;
struct link_free *link;
void *vaddr;
set_first_obj_offset(page, off);
vaddr = kmap_atomic(page);
link = (struct link_free *)vaddr + off / sizeof(*link);
while ((off += class->size) < PAGE_SIZE) {
link->next = freeobj++ << OBJ_TAG_BITS;
link += class->size / sizeof(*link);
}
/*
* We now come to the last (full or partial) object on this
* page, which must point to the first object on the next
* page (if present)
*/
next_page = get_next_page(page);
if (next_page) {
link->next = freeobj++ << OBJ_TAG_BITS;
} else {
/*
* Reset OBJ_TAG_BITS bit to last link to tell
* whether it's allocated object or not.
*/
link->next = -1UL << OBJ_TAG_BITS;
}
kunmap_atomic(vaddr);
page = next_page;
off %= PAGE_SIZE;
}
set_freeobj(zspage, 0);
}
static void create_page_chain(struct size_class *class, struct zspage *zspage,
struct page *pages[])
{
int i;
struct page *page;
struct page *prev_page = NULL;
int nr_pages = class->pages_per_zspage;
/*
* Allocate individual pages and link them together as:
* 1. all pages are linked together using page->freelist
* 2. each sub-page point to zspage using page->private
*
* we set PG_private to identify the first page (i.e. no other sub-page
* has this flag set).
*/
for (i = 0; i < nr_pages; i++) {
page = pages[i];
set_page_private(page, (unsigned long)zspage);
page->freelist = NULL;
if (i == 0) {
zspage->first_page = page;
SetPagePrivate(page);
if (unlikely(class->objs_per_zspage == 1 &&
class->pages_per_zspage == 1))
SetPageHugeObject(page);
} else {
prev_page->freelist = page;
}
prev_page = page;
}
}
/*
* Allocate a zspage for the given size class
*/
static struct zspage *alloc_zspage(struct zs_pool *pool,
struct size_class *class,
gfp_t gfp)
{
int i;
struct page *pages[ZS_MAX_PAGES_PER_ZSPAGE];
struct zspage *zspage = cache_alloc_zspage(pool, gfp);
if (!zspage)
return NULL;
memset(zspage, 0, sizeof(struct zspage));
zspage->magic = ZSPAGE_MAGIC;
migrate_lock_init(zspage);
for (i = 0; i < class->pages_per_zspage; i++) {
struct page *page;
page = alloc_page(gfp);
if (!page) {
while (--i >= 0) {
dec_zone_page_state(pages[i], NR_ZSPAGES);
__free_page(pages[i]);
}
cache_free_zspage(pool, zspage);
return NULL;
}
inc_zone_page_state(page, NR_ZSPAGES);
pages[i] = page;
}
create_page_chain(class, zspage, pages);
init_zspage(class, zspage);
return zspage;
}
static struct zspage *find_get_zspage(struct size_class *class)
{
int i;
struct zspage *zspage;
for (i = ZS_ALMOST_FULL; i >= ZS_EMPTY; i--) {
zspage = list_first_entry_or_null(&class->fullness_list[i],
struct zspage, list);
if (zspage)
break;
}
return zspage;
}
static inline int __zs_cpu_up(struct mapping_area *area)
{
/*
* Make sure we don't leak memory if a cpu UP notification
* and zs_init() race and both call zs_cpu_up() on the same cpu
*/
if (area->vm_buf)
return 0;
area->vm_buf = kmalloc(ZS_MAX_ALLOC_SIZE, GFP_KERNEL);
if (!area->vm_buf)
return -ENOMEM;
return 0;
}
static inline void __zs_cpu_down(struct mapping_area *area)
{
kfree(area->vm_buf);
area->vm_buf = NULL;
}
static void *__zs_map_object(struct mapping_area *area,
struct page *pages[2], int off, int size)
{
int sizes[2];
void *addr;
char *buf = area->vm_buf;
/* disable page faults to match kmap_atomic() return conditions */
pagefault_disable();
/* no read fastpath */
if (area->vm_mm == ZS_MM_WO)
goto out;
sizes[0] = PAGE_SIZE - off;
sizes[1] = size - sizes[0];
/* copy object to per-cpu buffer */
addr = kmap_atomic(pages[0]);
memcpy(buf, addr + off, sizes[0]);
kunmap_atomic(addr);
addr = kmap_atomic(pages[1]);
memcpy(buf + sizes[0], addr, sizes[1]);
kunmap_atomic(addr);
out:
return area->vm_buf;
}
static void __zs_unmap_object(struct mapping_area *area,
struct page *pages[2], int off, int size)
{
int sizes[2];
void *addr;
char *buf;
/* no write fastpath */
if (area->vm_mm == ZS_MM_RO)
goto out;
buf = area->vm_buf;
buf = buf + ZS_HANDLE_SIZE;
size -= ZS_HANDLE_SIZE;
off += ZS_HANDLE_SIZE;
sizes[0] = PAGE_SIZE - off;
sizes[1] = size - sizes[0];
/* copy per-cpu buffer to object */
addr = kmap_atomic(pages[0]);
memcpy(addr + off, buf, sizes[0]);
kunmap_atomic(addr);
addr = kmap_atomic(pages[1]);
memcpy(addr, buf + sizes[0], sizes[1]);
kunmap_atomic(addr);
out:
/* enable page faults to match kunmap_atomic() return conditions */
pagefault_enable();
}
static int zs_cpu_prepare(unsigned int cpu)
{
struct mapping_area *area;
area = &per_cpu(zs_map_area, cpu);
return __zs_cpu_up(area);
}
static int zs_cpu_dead(unsigned int cpu)
{
struct mapping_area *area;
area = &per_cpu(zs_map_area, cpu);
__zs_cpu_down(area);
return 0;
}
static bool can_merge(struct size_class *prev, int pages_per_zspage,
int objs_per_zspage)
{
if (prev->pages_per_zspage == pages_per_zspage &&
prev->objs_per_zspage == objs_per_zspage)
return true;
return false;
}
static bool zspage_full(struct size_class *class, struct zspage *zspage)
{
return get_zspage_inuse(zspage) == class->objs_per_zspage;
}
unsigned long zs_get_total_pages(struct zs_pool *pool)
{
return atomic_long_read(&pool->pages_allocated);
}
EXPORT_SYMBOL_GPL(zs_get_total_pages);
/**
* zs_map_object - get address of allocated object from handle.
* @pool: pool from which the object was allocated
* @handle: handle returned from zs_malloc
* @mm: maping mode to use
*
* Before using an object allocated from zs_malloc, it must be mapped using
* this function. When done with the object, it must be unmapped using
* zs_unmap_object.
*
* Only one object can be mapped per cpu at a time. There is no protection
* against nested mappings.
*
* This function returns with preemption and page faults disabled.
*/
void *zs_map_object(struct zs_pool *pool, unsigned long handle,
enum zs_mapmode mm)
{
struct zspage *zspage;
struct page *page;
unsigned long obj, off;
unsigned int obj_idx;
unsigned int class_idx;
enum fullness_group fg;
struct size_class *class;
struct mapping_area *area;
struct page *pages[2];
void *ret;
/*
* Because we use per-cpu mapping areas shared among the
* pools/users, we can't allow mapping in interrupt context
* because it can corrupt another users mappings.
*/
BUG_ON(in_interrupt());
/* From now on, migration cannot move the object */
pin_tag(handle);
obj = handle_to_obj(handle);
obj_to_location(obj, &page, &obj_idx);
zspage = get_zspage(page);
/* migration cannot move any subpage in this zspage */
migrate_read_lock(zspage);
get_zspage_mapping(zspage, &class_idx, &fg);
class = pool->size_class[class_idx];
off = (class->size * obj_idx) & ~PAGE_MASK;
area = &get_cpu_var(zs_map_area);
area->vm_mm = mm;
if (off + class->size <= PAGE_SIZE) {
/* this object is contained entirely within a page */
area->vm_addr = kmap_atomic(page);
ret = area->vm_addr + off;
goto out;
}
/* this object spans two pages */
pages[0] = page;
pages[1] = get_next_page(page);
BUG_ON(!pages[1]);
ret = __zs_map_object(area, pages, off, class->size);
out:
if (likely(!PageHugeObject(page)))
ret += ZS_HANDLE_SIZE;
return ret;
}
EXPORT_SYMBOL_GPL(zs_map_object);
void zs_unmap_object(struct zs_pool *pool, unsigned long handle)
{
struct zspage *zspage;
struct page *page;
unsigned long obj, off;
unsigned int obj_idx;
unsigned int class_idx;
enum fullness_group fg;
struct size_class *class;
struct mapping_area *area;
obj = handle_to_obj(handle);
obj_to_location(obj, &page, &obj_idx);
zspage = get_zspage(page);
get_zspage_mapping(zspage, &class_idx, &fg);
class = pool->size_class[class_idx];
off = (class->size * obj_idx) & ~PAGE_MASK;
area = this_cpu_ptr(&zs_map_area);
if (off + class->size <= PAGE_SIZE)
kunmap_atomic(area->vm_addr);
else {
struct page *pages[2];
pages[0] = page;
pages[1] = get_next_page(page);
BUG_ON(!pages[1]);
__zs_unmap_object(area, pages, off, class->size);
}
put_cpu_var(zs_map_area);
migrate_read_unlock(zspage);
unpin_tag(handle);
}
EXPORT_SYMBOL_GPL(zs_unmap_object);
/**
* zs_huge_class_size() - Returns the size (in bytes) of the first huge
* zsmalloc &size_class.
* @pool: zsmalloc pool to use
*
* The function returns the size of the first huge class - any object of equal
* or bigger size will be stored in zspage consisting of a single physical
* page.
*
* Context: Any context.
*
* Return: the size (in bytes) of the first huge zsmalloc &size_class.
*/
size_t zs_huge_class_size(struct zs_pool *pool)
{
return huge_class_size;
}
EXPORT_SYMBOL_GPL(zs_huge_class_size);
static unsigned long obj_malloc(struct size_class *class,
struct zspage *zspage, unsigned long handle)
{
int i, nr_page, offset;
unsigned long obj;
struct link_free *link;
struct page *m_page;
unsigned long m_offset;
void *vaddr;
handle |= OBJ_ALLOCATED_TAG;
obj = get_freeobj(zspage);
offset = obj * class->size;
nr_page = offset >> PAGE_SHIFT;
m_offset = offset & ~PAGE_MASK;
m_page = get_first_page(zspage);
for (i = 0; i < nr_page; i++)
m_page = get_next_page(m_page);
vaddr = kmap_atomic(m_page);
link = (struct link_free *)vaddr + m_offset / sizeof(*link);
set_freeobj(zspage, link->next >> OBJ_TAG_BITS);
if (likely(!PageHugeObject(m_page)))
/* record handle in the header of allocated chunk */
link->handle = handle;
else
/* record handle to page->index */
zspage->first_page->index = handle;
kunmap_atomic(vaddr);
mod_zspage_inuse(zspage, 1);
zs_stat_inc(class, OBJ_USED, 1);
obj = location_to_obj(m_page, obj);
return obj;
}
/**
* zs_malloc - Allocate block of given size from pool.
* @pool: pool to allocate from
* @size: size of block to allocate
* @gfp: gfp flags when allocating object
*
* On success, handle to the allocated object is returned,
* otherwise 0.
* Allocation requests with size > ZS_MAX_ALLOC_SIZE will fail.
*/
unsigned long zs_malloc(struct zs_pool *pool, size_t size, gfp_t gfp)
{
unsigned long handle, obj;
struct size_class *class;
enum fullness_group newfg;
struct zspage *zspage;
if (unlikely(!size || size > ZS_MAX_ALLOC_SIZE))
return 0;
handle = cache_alloc_handle(pool, gfp);
if (!handle)
return 0;
/* extra space in chunk to keep the handle */
size += ZS_HANDLE_SIZE;
class = pool->size_class[get_size_class_index(size)];
spin_lock(&class->lock);
zspage = find_get_zspage(class);
if (likely(zspage)) {
obj = obj_malloc(class, zspage, handle);
/* Now move the zspage to another fullness group, if required */
fix_fullness_group(class, zspage);
record_obj(handle, obj);
spin_unlock(&class->lock);
return handle;
}
spin_unlock(&class->lock);
zspage = alloc_zspage(pool, class, gfp);
if (!zspage) {
cache_free_handle(pool, handle);
return 0;
}
spin_lock(&class->lock);
obj = obj_malloc(class, zspage, handle);
newfg = get_fullness_group(class, zspage);
insert_zspage(class, zspage, newfg);
set_zspage_mapping(zspage, class->index, newfg);
record_obj(handle, obj);
atomic_long_add(class->pages_per_zspage,
&pool->pages_allocated);
zs_stat_inc(class, OBJ_ALLOCATED, class->objs_per_zspage);
/* We completely set up zspage so mark them as movable */
SetZsPageMovable(pool, zspage);
spin_unlock(&class->lock);
return handle;
}
EXPORT_SYMBOL_GPL(zs_malloc);
static void obj_free(struct size_class *class, unsigned long obj)
{
struct link_free *link;
struct zspage *zspage;
struct page *f_page;
unsigned long f_offset;
unsigned int f_objidx;
void *vaddr;
obj &= ~OBJ_ALLOCATED_TAG;
obj_to_location(obj, &f_page, &f_objidx);
f_offset = (class->size * f_objidx) & ~PAGE_MASK;
zspage = get_zspage(f_page);
vaddr = kmap_atomic(f_page);
/* Insert this object in containing zspage's freelist */
link = (struct link_free *)(vaddr + f_offset);
link->next = get_freeobj(zspage) << OBJ_TAG_BITS;
kunmap_atomic(vaddr);
set_freeobj(zspage, f_objidx);
mod_zspage_inuse(zspage, -1);
zs_stat_dec(class, OBJ_USED, 1);
}
void zs_free(struct zs_pool *pool, unsigned long handle)
{
struct zspage *zspage;
struct page *f_page;
unsigned long obj;
unsigned int f_objidx;
int class_idx;
struct size_class *class;
enum fullness_group fullness;
bool isolated;
if (unlikely(!handle))
return;
pin_tag(handle);
obj = handle_to_obj(handle);
obj_to_location(obj, &f_page, &f_objidx);
zspage = get_zspage(f_page);
migrate_read_lock(zspage);
get_zspage_mapping(zspage, &class_idx, &fullness);
class = pool->size_class[class_idx];
spin_lock(&class->lock);
obj_free(class, obj);
fullness = fix_fullness_group(class, zspage);
if (fullness != ZS_EMPTY) {
migrate_read_unlock(zspage);
goto out;
}
isolated = is_zspage_isolated(zspage);
migrate_read_unlock(zspage);
/* If zspage is isolated, zs_page_putback will free the zspage */
if (likely(!isolated))
free_zspage(pool, class, zspage);
out:
spin_unlock(&class->lock);
unpin_tag(handle);
cache_free_handle(pool, handle);
}
EXPORT_SYMBOL_GPL(zs_free);
static void zs_object_copy(struct size_class *class, unsigned long dst,
unsigned long src)
{
struct page *s_page, *d_page;
unsigned int s_objidx, d_objidx;
unsigned long s_off, d_off;
void *s_addr, *d_addr;
int s_size, d_size, size;
int written = 0;
s_size = d_size = class->size;
obj_to_location(src, &s_page, &s_objidx);
obj_to_location(dst, &d_page, &d_objidx);
s_off = (class->size * s_objidx) & ~PAGE_MASK;
d_off = (class->size * d_objidx) & ~PAGE_MASK;
if (s_off + class->size > PAGE_SIZE)
s_size = PAGE_SIZE - s_off;
if (d_off + class->size > PAGE_SIZE)
d_size = PAGE_SIZE - d_off;
s_addr = kmap_atomic(s_page);
d_addr = kmap_atomic(d_page);
while (1) {
size = min(s_size, d_size);
memcpy(d_addr + d_off, s_addr + s_off, size);
written += size;
if (written == class->size)
break;
s_off += size;
s_size -= size;
d_off += size;
d_size -= size;
if (s_off >= PAGE_SIZE) {
kunmap_atomic(d_addr);
kunmap_atomic(s_addr);
s_page = get_next_page(s_page);
s_addr = kmap_atomic(s_page);
d_addr = kmap_atomic(d_page);
s_size = class->size - written;
s_off = 0;
}
if (d_off >= PAGE_SIZE) {
kunmap_atomic(d_addr);
d_page = get_next_page(d_page);
d_addr = kmap_atomic(d_page);
d_size = class->size - written;
d_off = 0;
}
}
kunmap_atomic(d_addr);
kunmap_atomic(s_addr);
}
/*
* Find alloced object in zspage from index object and
* return handle.
*/
static unsigned long find_alloced_obj(struct size_class *class,
struct page *page, int *obj_idx)
{
unsigned long head;
int offset = 0;
int index = *obj_idx;
unsigned long handle = 0;
void *addr = kmap_atomic(page);
offset = get_first_obj_offset(page);
offset += class->size * index;
while (offset < PAGE_SIZE) {
head = obj_to_head(page, addr + offset);
if (head & OBJ_ALLOCATED_TAG) {
handle = head & ~OBJ_ALLOCATED_TAG;
if (trypin_tag(handle))
break;
handle = 0;
}
offset += class->size;
index++;
}
kunmap_atomic(addr);
*obj_idx = index;
return handle;
}
struct zs_compact_control {
/* Source spage for migration which could be a subpage of zspage */
struct page *s_page;
/* Destination page for migration which should be a first page
* of zspage. */
struct page *d_page;
/* Starting object index within @s_page which used for live object
* in the subpage. */
int obj_idx;
};
static int migrate_zspage(struct zs_pool *pool, struct size_class *class,
struct zs_compact_control *cc)
{
unsigned long used_obj, free_obj;
unsigned long handle;
struct page *s_page = cc->s_page;
struct page *d_page = cc->d_page;
int obj_idx = cc->obj_idx;
int ret = 0;
while (1) {
handle = find_alloced_obj(class, s_page, &obj_idx);
if (!handle) {
s_page = get_next_page(s_page);
if (!s_page)
break;
obj_idx = 0;
continue;
}
/* Stop if there is no more space */
if (zspage_full(class, get_zspage(d_page))) {
unpin_tag(handle);
ret = -ENOMEM;
break;
}
used_obj = handle_to_obj(handle);
free_obj = obj_malloc(class, get_zspage(d_page), handle);
zs_object_copy(class, free_obj, used_obj);
obj_idx++;
/*
* record_obj updates handle's value to free_obj and it will
* invalidate lock bit(ie, HANDLE_PIN_BIT) of handle, which
* breaks synchronization using pin_tag(e,g, zs_free) so
* let's keep the lock bit.
*/
free_obj |= BIT(HANDLE_PIN_BIT);
record_obj(handle, free_obj);
unpin_tag(handle);
obj_free(class, used_obj);
}
/* Remember last position in this iteration */
cc->s_page = s_page;
cc->obj_idx = obj_idx;
return ret;
}
static struct zspage *isolate_zspage(struct size_class *class, bool source)
{
int i;
struct zspage *zspage;
enum fullness_group fg[2] = {ZS_ALMOST_EMPTY, ZS_ALMOST_FULL};
if (!source) {
fg[0] = ZS_ALMOST_FULL;
fg[1] = ZS_ALMOST_EMPTY;
}
for (i = 0; i < 2; i++) {
zspage = list_first_entry_or_null(&class->fullness_list[fg[i]],
struct zspage, list);
if (zspage) {
VM_BUG_ON(is_zspage_isolated(zspage));
remove_zspage(class, zspage, fg[i]);
return zspage;
}
}
return zspage;
}
/*
* putback_zspage - add @zspage into right class's fullness list
* @class: destination class
* @zspage: target page
*
* Return @zspage's fullness_group
*/
static enum fullness_group putback_zspage(struct size_class *class,
struct zspage *zspage)
{
enum fullness_group fullness;
VM_BUG_ON(is_zspage_isolated(zspage));
fullness = get_fullness_group(class, zspage);
insert_zspage(class, zspage, fullness);
set_zspage_mapping(zspage, class->index, fullness);
return fullness;
}
#ifdef CONFIG_COMPACTION
/*
* To prevent zspage destroy during migration, zspage freeing should
* hold locks of all pages in the zspage.
*/
static void lock_zspage(struct zspage *zspage)
{
struct page *curr_page, *page;
/*
* Pages we haven't locked yet can be migrated off the list while we're
* trying to lock them, so we need to be careful and only attempt to
* lock each page under migrate_read_lock(). Otherwise, the page we lock
* may no longer belong to the zspage. This means that we may wait for
* the wrong page to unlock, so we must take a reference to the page
* prior to waiting for it to unlock outside migrate_read_lock().
*/
while (1) {
migrate_read_lock(zspage);
page = get_first_page(zspage);
if (trylock_page(page))
break;
get_page(page);
migrate_read_unlock(zspage);
wait_on_page_locked(page);
put_page(page);
}
curr_page = page;
while ((page = get_next_page(curr_page))) {
if (trylock_page(page)) {
curr_page = page;
} else {
get_page(page);
migrate_read_unlock(zspage);
wait_on_page_locked(page);
put_page(page);
migrate_read_lock(zspage);
}
}
migrate_read_unlock(zspage);
}
static int zs_init_fs_context(struct fs_context *fc)
{
return init_pseudo(fc, ZSMALLOC_MAGIC) ? 0 : -ENOMEM;
}
static struct file_system_type zsmalloc_fs = {
.name = "zsmalloc",
.init_fs_context = zs_init_fs_context,
.kill_sb = kill_anon_super,
};
static int zsmalloc_mount(void)
{
int ret = 0;
zsmalloc_mnt = kern_mount(&zsmalloc_fs);
if (IS_ERR(zsmalloc_mnt))
ret = PTR_ERR(zsmalloc_mnt);
return ret;
}
static void zsmalloc_unmount(void)
{
kern_unmount(zsmalloc_mnt);
}
static void migrate_lock_init(struct zspage *zspage)
{
rwlock_init(&zspage->lock);
}
static void migrate_read_lock(struct zspage *zspage)
{
read_lock(&zspage->lock);
}
static void migrate_read_unlock(struct zspage *zspage)
{
read_unlock(&zspage->lock);
}
static void migrate_write_lock(struct zspage *zspage)
{
write_lock(&zspage->lock);
}
static void migrate_write_unlock(struct zspage *zspage)
{
write_unlock(&zspage->lock);
}
/* Number of isolated subpage for *page migration* in this zspage */
static void inc_zspage_isolation(struct zspage *zspage)
{
zspage->isolated++;
}
static void dec_zspage_isolation(struct zspage *zspage)
{
zspage->isolated--;
}
static void putback_zspage_deferred(struct zs_pool *pool,
struct size_class *class,
struct zspage *zspage)
{
enum fullness_group fg;
fg = putback_zspage(class, zspage);
if (fg == ZS_EMPTY)
schedule_work(&pool->free_work);
}
static inline void zs_pool_dec_isolated(struct zs_pool *pool)
{
VM_BUG_ON(atomic_long_read(&pool->isolated_pages) <= 0);
atomic_long_dec(&pool->isolated_pages);
/*
* Checking pool->destroying must happen after atomic_long_dec()
* for pool->isolated_pages above. Paired with the smp_mb() in
* zs_unregister_migration().
*/
smp_mb__after_atomic();
if (atomic_long_read(&pool->isolated_pages) == 0 && pool->destroying)
wake_up_all(&pool->migration_wait);
}
static void replace_sub_page(struct size_class *class, struct zspage *zspage,
struct page *newpage, struct page *oldpage)
{
struct page *page;
struct page *pages[ZS_MAX_PAGES_PER_ZSPAGE] = {NULL, };
int idx = 0;
page = get_first_page(zspage);
do {
if (page == oldpage)
pages[idx] = newpage;
else
pages[idx] = page;
idx++;
} while ((page = get_next_page(page)) != NULL);
create_page_chain(class, zspage, pages);
set_first_obj_offset(newpage, get_first_obj_offset(oldpage));
if (unlikely(PageHugeObject(oldpage)))
newpage->index = oldpage->index;
__SetPageMovable(newpage, page_mapping(oldpage));
}
static bool zs_page_isolate(struct page *page, isolate_mode_t mode)
{
struct zs_pool *pool;
struct size_class *class;
int class_idx;
enum fullness_group fullness;
struct zspage *zspage;
struct address_space *mapping;
/*
* Page is locked so zspage couldn't be destroyed. For detail, look at
* lock_zspage in free_zspage.
*/
VM_BUG_ON_PAGE(!PageMovable(page), page);
VM_BUG_ON_PAGE(PageIsolated(page), page);
zspage = get_zspage(page);
/*
* Without class lock, fullness could be stale while class_idx is okay
* because class_idx is constant unless page is freed so we should get
* fullness again under class lock.
*/
get_zspage_mapping(zspage, &class_idx, &fullness);
mapping = page_mapping(page);
pool = mapping->private_data;
class = pool->size_class[class_idx];
spin_lock(&class->lock);
if (get_zspage_inuse(zspage) == 0) {
spin_unlock(&class->lock);
return false;
}
/* zspage is isolated for object migration */
if (list_empty(&zspage->list) && !is_zspage_isolated(zspage)) {
spin_unlock(&class->lock);
return false;
}
/*
* If this is first time isolation for the zspage, isolate zspage from
* size_class to prevent further object allocation from the zspage.
*/
if (!list_empty(&zspage->list) && !is_zspage_isolated(zspage)) {
get_zspage_mapping(zspage, &class_idx, &fullness);
atomic_long_inc(&pool->isolated_pages);
remove_zspage(class, zspage, fullness);
}
inc_zspage_isolation(zspage);
spin_unlock(&class->lock);
return true;
}
static int zs_page_migrate(struct address_space *mapping, struct page *newpage,
struct page *page, enum migrate_mode mode)
{
struct zs_pool *pool;
struct size_class *class;
int class_idx;
enum fullness_group fullness;
struct zspage *zspage;
struct page *dummy;
void *s_addr, *d_addr, *addr;
int offset, pos;
unsigned long handle, head;
unsigned long old_obj, new_obj;
unsigned int obj_idx;
int ret = -EAGAIN;
/*
* We cannot support the _NO_COPY case here, because copy needs to
* happen under the zs lock, which does not work with
* MIGRATE_SYNC_NO_COPY workflow.
*/
if (mode == MIGRATE_SYNC_NO_COPY)
return -EINVAL;
VM_BUG_ON_PAGE(!PageMovable(page), page);
VM_BUG_ON_PAGE(!PageIsolated(page), page);
zspage = get_zspage(page);
/* Concurrent compactor cannot migrate any subpage in zspage */
migrate_write_lock(zspage);
get_zspage_mapping(zspage, &class_idx, &fullness);
pool = mapping->private_data;
class = pool->size_class[class_idx];
offset = get_first_obj_offset(page);
spin_lock(&class->lock);
if (!get_zspage_inuse(zspage)) {
/*
* Set "offset" to end of the page so that every loops
* skips unnecessary object scanning.
*/
offset = PAGE_SIZE;
}
pos = offset;
s_addr = kmap_atomic(page);
while (pos < PAGE_SIZE) {
head = obj_to_head(page, s_addr + pos);
if (head & OBJ_ALLOCATED_TAG) {
handle = head & ~OBJ_ALLOCATED_TAG;
if (!trypin_tag(handle))
goto unpin_objects;
}
pos += class->size;
}
/*
* Here, any user cannot access all objects in the zspage so let's move.
*/
d_addr = kmap_atomic(newpage);
memcpy(d_addr, s_addr, PAGE_SIZE);
kunmap_atomic(d_addr);
for (addr = s_addr + offset; addr < s_addr + pos;
addr += class->size) {
head = obj_to_head(page, addr);
if (head & OBJ_ALLOCATED_TAG) {
handle = head & ~OBJ_ALLOCATED_TAG;
if (!testpin_tag(handle))
BUG();
old_obj = handle_to_obj(handle);
obj_to_location(old_obj, &dummy, &obj_idx);
new_obj = (unsigned long)location_to_obj(newpage,
obj_idx);
new_obj |= BIT(HANDLE_PIN_BIT);
record_obj(handle, new_obj);
}
}
replace_sub_page(class, zspage, newpage, page);
get_page(newpage);
dec_zspage_isolation(zspage);
/*
* Page migration is done so let's putback isolated zspage to
* the list if @page is final isolated subpage in the zspage.
*/
if (!is_zspage_isolated(zspage)) {
/*
* We cannot race with zs_destroy_pool() here because we wait
* for isolation to hit zero before we start destroying.
* Also, we ensure that everyone can see pool->destroying before
* we start waiting.
*/
putback_zspage_deferred(pool, class, zspage);
zs_pool_dec_isolated(pool);
}
if (page_zone(newpage) != page_zone(page)) {
dec_zone_page_state(page, NR_ZSPAGES);
inc_zone_page_state(newpage, NR_ZSPAGES);
}
reset_page(page);
put_page(page);
page = newpage;
ret = MIGRATEPAGE_SUCCESS;
unpin_objects:
for (addr = s_addr + offset; addr < s_addr + pos;
addr += class->size) {
head = obj_to_head(page, addr);
if (head & OBJ_ALLOCATED_TAG) {
handle = head & ~OBJ_ALLOCATED_TAG;
if (!testpin_tag(handle))
BUG();
unpin_tag(handle);
}
}
kunmap_atomic(s_addr);
spin_unlock(&class->lock);
migrate_write_unlock(zspage);
return ret;
}
static void zs_page_putback(struct page *page)
{
struct zs_pool *pool;
struct size_class *class;
int class_idx;
enum fullness_group fg;
struct address_space *mapping;
struct zspage *zspage;
VM_BUG_ON_PAGE(!PageMovable(page), page);
VM_BUG_ON_PAGE(!PageIsolated(page), page);
zspage = get_zspage(page);
get_zspage_mapping(zspage, &class_idx, &fg);
mapping = page_mapping(page);
pool = mapping->private_data;
class = pool->size_class[class_idx];
spin_lock(&class->lock);
dec_zspage_isolation(zspage);
if (!is_zspage_isolated(zspage)) {
/*
* Due to page_lock, we cannot free zspage immediately
* so let's defer.
*/
putback_zspage_deferred(pool, class, zspage);
zs_pool_dec_isolated(pool);
}
spin_unlock(&class->lock);
}
static const struct address_space_operations zsmalloc_aops = {
.isolate_page = zs_page_isolate,
.migratepage = zs_page_migrate,
.putback_page = zs_page_putback,
};
static int zs_register_migration(struct zs_pool *pool)
{
pool->inode = alloc_anon_inode(zsmalloc_mnt->mnt_sb);
if (IS_ERR(pool->inode)) {
pool->inode = NULL;
return 1;
}
pool->inode->i_mapping->private_data = pool;
pool->inode->i_mapping->a_ops = &zsmalloc_aops;
return 0;
}
static bool pool_isolated_are_drained(struct zs_pool *pool)
{
return atomic_long_read(&pool->isolated_pages) == 0;
}
/* Function for resolving migration */
static void wait_for_isolated_drain(struct zs_pool *pool)
{
/*
* We're in the process of destroying the pool, so there are no
* active allocations. zs_page_isolate() fails for completely free
* zspages, so we need only wait for the zs_pool's isolated
* count to hit zero.
*/
wait_event(pool->migration_wait,
pool_isolated_are_drained(pool));
}
static void zs_unregister_migration(struct zs_pool *pool)
{
pool->destroying = true;
/*
* We need a memory barrier here to ensure global visibility of
* pool->destroying. Thus pool->isolated pages will either be 0 in which
* case we don't care, or it will be > 0 and pool->destroying will
* ensure that we wake up once isolation hits 0.
*/
smp_mb();
wait_for_isolated_drain(pool); /* This can block */
flush_work(&pool->free_work);
iput(pool->inode);
}
/*
* Caller should hold page_lock of all pages in the zspage
* In here, we cannot use zspage meta data.
*/
static void async_free_zspage(struct work_struct *work)
{
int i;
struct size_class *class;
unsigned int class_idx;
enum fullness_group fullness;
struct zspage *zspage, *tmp;
LIST_HEAD(free_pages);
struct zs_pool *pool = container_of(work, struct zs_pool,
free_work);
for (i = 0; i < ZS_SIZE_CLASSES; i++) {
class = pool->size_class[i];
if (class->index != i)
continue;
spin_lock(&class->lock);
list_splice_init(&class->fullness_list[ZS_EMPTY], &free_pages);
spin_unlock(&class->lock);
}
list_for_each_entry_safe(zspage, tmp, &free_pages, list) {
list_del(&zspage->list);
lock_zspage(zspage);
get_zspage_mapping(zspage, &class_idx, &fullness);
VM_BUG_ON(fullness != ZS_EMPTY);
class = pool->size_class[class_idx];
spin_lock(&class->lock);
__free_zspage(pool, pool->size_class[class_idx], zspage);
spin_unlock(&class->lock);
}
};
static void kick_deferred_free(struct zs_pool *pool)
{
schedule_work(&pool->free_work);
}
static void init_deferred_free(struct zs_pool *pool)
{
INIT_WORK(&pool->free_work, async_free_zspage);
}
static void SetZsPageMovable(struct zs_pool *pool, struct zspage *zspage)
{
struct page *page = get_first_page(zspage);
do {
WARN_ON(!trylock_page(page));
__SetPageMovable(page, pool->inode->i_mapping);
unlock_page(page);
} while ((page = get_next_page(page)) != NULL);
}
#endif
/*
*
* Based on the number of unused allocated objects calculate
* and return the number of pages that we can free.
*/
static unsigned long zs_can_compact(struct size_class *class)
{
unsigned long obj_wasted;
unsigned long obj_allocated = zs_stat_get(class, OBJ_ALLOCATED);
unsigned long obj_used = zs_stat_get(class, OBJ_USED);
if (obj_allocated <= obj_used)
return 0;
obj_wasted = obj_allocated - obj_used;
obj_wasted /= class->objs_per_zspage;
return obj_wasted * class->pages_per_zspage;
}
static unsigned long __zs_compact(struct zs_pool *pool,
struct size_class *class)
{
struct zs_compact_control cc;
struct zspage *src_zspage;
struct zspage *dst_zspage = NULL;
unsigned long pages_freed = 0;
spin_lock(&class->lock);
while ((src_zspage = isolate_zspage(class, true))) {
if (!zs_can_compact(class))
break;
cc.obj_idx = 0;
cc.s_page = get_first_page(src_zspage);
while ((dst_zspage = isolate_zspage(class, false))) {
cc.d_page = get_first_page(dst_zspage);
/*
* If there is no more space in dst_page, resched
* and see if anyone had allocated another zspage.
*/
if (!migrate_zspage(pool, class, &cc))
break;
putback_zspage(class, dst_zspage);
}
/* Stop if we couldn't find slot */
if (dst_zspage == NULL)
break;
putback_zspage(class, dst_zspage);
if (putback_zspage(class, src_zspage) == ZS_EMPTY) {
free_zspage(pool, class, src_zspage);
pages_freed += class->pages_per_zspage;
}
spin_unlock(&class->lock);
cond_resched();
spin_lock(&class->lock);
}
if (src_zspage)
putback_zspage(class, src_zspage);
spin_unlock(&class->lock);
return pages_freed;
}
unsigned long zs_compact(struct zs_pool *pool)
{
int i;
struct size_class *class;
unsigned long pages_freed = 0;
for (i = ZS_SIZE_CLASSES - 1; i >= 0; i--) {
class = pool->size_class[i];
if (!class)
continue;
if (class->index != i)
continue;
pages_freed += __zs_compact(pool, class);
}
atomic_long_add(pages_freed, &pool->stats.pages_compacted);
return pages_freed;
}
EXPORT_SYMBOL_GPL(zs_compact);
void zs_pool_stats(struct zs_pool *pool, struct zs_pool_stats *stats)
{
memcpy(stats, &pool->stats, sizeof(struct zs_pool_stats));
}
EXPORT_SYMBOL_GPL(zs_pool_stats);
static unsigned long zs_shrinker_scan(struct shrinker *shrinker,
struct shrink_control *sc)
{
unsigned long pages_freed;
struct zs_pool *pool = container_of(shrinker, struct zs_pool,
shrinker);
/*
* Compact classes and calculate compaction delta.
* Can run concurrently with a manually triggered
* (by user) compaction.
*/
pages_freed = zs_compact(pool);
return pages_freed ? pages_freed : SHRINK_STOP;
}
static unsigned long zs_shrinker_count(struct shrinker *shrinker,
struct shrink_control *sc)
{
int i;
struct size_class *class;
unsigned long pages_to_free = 0;
struct zs_pool *pool = container_of(shrinker, struct zs_pool,
shrinker);
for (i = ZS_SIZE_CLASSES - 1; i >= 0; i--) {
class = pool->size_class[i];
if (!class)
continue;
if (class->index != i)
continue;
pages_to_free += zs_can_compact(class);
}
return pages_to_free;
}
static void zs_unregister_shrinker(struct zs_pool *pool)
{
unregister_shrinker(&pool->shrinker);
}
static int zs_register_shrinker(struct zs_pool *pool)
{
pool->shrinker.scan_objects = zs_shrinker_scan;
pool->shrinker.count_objects = zs_shrinker_count;
pool->shrinker.batch = 0;
pool->shrinker.seeks = DEFAULT_SEEKS;
return register_shrinker(&pool->shrinker);
}
/**
* zs_create_pool - Creates an allocation pool to work from.
* @name: pool name to be created
*
* This function must be called before anything when using
* the zsmalloc allocator.
*
* On success, a pointer to the newly created pool is returned,
* otherwise NULL.
*/
struct zs_pool *zs_create_pool(const char *name)
{
int i;
struct zs_pool *pool;
struct size_class *prev_class = NULL;
pool = kzalloc(sizeof(*pool), GFP_KERNEL);
if (!pool)
return NULL;
init_deferred_free(pool);
pool->name = kstrdup(name, GFP_KERNEL);
if (!pool->name)
goto err;
#ifdef CONFIG_COMPACTION
init_waitqueue_head(&pool->migration_wait);
#endif
if (create_cache(pool))
goto err;
/*
* Iterate reversely, because, size of size_class that we want to use
* for merging should be larger or equal to current size.
*/
for (i = ZS_SIZE_CLASSES - 1; i >= 0; i--) {
int size;
int pages_per_zspage;
int objs_per_zspage;
struct size_class *class;
int fullness = 0;
size = ZS_MIN_ALLOC_SIZE + i * ZS_SIZE_CLASS_DELTA;
if (size > ZS_MAX_ALLOC_SIZE)
size = ZS_MAX_ALLOC_SIZE;
pages_per_zspage = get_pages_per_zspage(size);
objs_per_zspage = pages_per_zspage * PAGE_SIZE / size;
/*
* We iterate from biggest down to smallest classes,
* so huge_class_size holds the size of the first huge
* class. Any object bigger than or equal to that will
* endup in the huge class.
*/
if (pages_per_zspage != 1 && objs_per_zspage != 1 &&
!huge_class_size) {
huge_class_size = size;
/*
* The object uses ZS_HANDLE_SIZE bytes to store the
* handle. We need to subtract it, because zs_malloc()
* unconditionally adds handle size before it performs
* size class search - so object may be smaller than
* huge class size, yet it still can end up in the huge
* class because it grows by ZS_HANDLE_SIZE extra bytes
* right before class lookup.
*/
huge_class_size -= (ZS_HANDLE_SIZE - 1);
}
/*
* size_class is used for normal zsmalloc operation such
* as alloc/free for that size. Although it is natural that we
* have one size_class for each size, there is a chance that we
* can get more memory utilization if we use one size_class for
* many different sizes whose size_class have same
* characteristics. So, we makes size_class point to
* previous size_class if possible.
*/
if (prev_class) {
if (can_merge(prev_class, pages_per_zspage, objs_per_zspage)) {
pool->size_class[i] = prev_class;
continue;
}
}
class = kzalloc(sizeof(struct size_class), GFP_KERNEL);
if (!class)
goto err;
class->size = size;
class->index = i;
class->pages_per_zspage = pages_per_zspage;
class->objs_per_zspage = objs_per_zspage;
spin_lock_init(&class->lock);
pool->size_class[i] = class;
for (fullness = ZS_EMPTY; fullness < NR_ZS_FULLNESS;
fullness++)
INIT_LIST_HEAD(&class->fullness_list[fullness]);
prev_class = class;
}
/* debug only, don't abort if it fails */
zs_pool_stat_create(pool, name);
if (zs_register_migration(pool))
goto err;
/*
* Not critical since shrinker is only used to trigger internal
* defragmentation of the pool which is pretty optional thing. If
* registration fails we still can use the pool normally and user can
* trigger compaction manually. Thus, ignore return code.
*/
zs_register_shrinker(pool);
return pool;
err:
zs_destroy_pool(pool);
return NULL;
}
EXPORT_SYMBOL_GPL(zs_create_pool);
void zs_destroy_pool(struct zs_pool *pool)
{
int i;
zs_unregister_shrinker(pool);
zs_unregister_migration(pool);
zs_pool_stat_destroy(pool);
for (i = 0; i < ZS_SIZE_CLASSES; i++) {
int fg;
struct size_class *class = pool->size_class[i];
if (!class)
continue;
if (class->index != i)
continue;
for (fg = ZS_EMPTY; fg < NR_ZS_FULLNESS; fg++) {
if (!list_empty(&class->fullness_list[fg])) {
pr_info("Freeing non-empty class with size %db, fullness group %d\n",
class->size, fg);
}
}
kfree(class);
}
destroy_cache(pool);
kfree(pool->name);
kfree(pool);
}
EXPORT_SYMBOL_GPL(zs_destroy_pool);
static int __init zs_init(void)
{
int ret;
ret = zsmalloc_mount();
if (ret)
goto out;
ret = cpuhp_setup_state(CPUHP_MM_ZS_PREPARE, "mm/zsmalloc:prepare",
zs_cpu_prepare, zs_cpu_dead);
if (ret)
goto hp_setup_fail;
#ifdef CONFIG_ZPOOL
zpool_register_driver(&zs_zpool_driver);
#endif
zs_stat_init();
return 0;
hp_setup_fail:
zsmalloc_unmount();
out:
return ret;
}
static void __exit zs_exit(void)
{
#ifdef CONFIG_ZPOOL
zpool_unregister_driver(&zs_zpool_driver);
#endif
zsmalloc_unmount();
cpuhp_remove_state(CPUHP_MM_ZS_PREPARE);
zs_stat_exit();
}
module_init(zs_init);
module_exit(zs_exit);
MODULE_LICENSE("Dual BSD/GPL");
MODULE_AUTHOR("Nitin Gupta <ngupta@vflare.org>");