Files
lucaswei 1fc07037f1 Merge android-4.9-q (4.9.200) into android-msm-pixel-4.9-qt-lts
Merge 4.9.200 into android-4.9-q
Linux 4.9.200
  * alarmtimer: Change remaining ENOTSUPP to EOPNOTSUPP
      kernel/time/alarmtimer.c
    dmaengine: qcom: bam_dma: Fix resource leak
  * net/flow_dissector: switch to siphash
      include/linux/skbuff.h
      include/net/flow_dissector.h
      net/core/flow_dissector.c
      net/sched/sch_fq_codel.c
  * kbuild: add -fcf-protection=none when using retpoline flags
      Makefile
  * kbuild: use -fmacro-prefix-map to make __FILE__ a relative path
      Makefile
  * Kbuild: make designated_init attribute fatal
      Makefile
  * inet: stop leaking jiffies on the wire
      net/ipv4/datagram.c
      net/ipv4/tcp_ipv4.c
    net/mlx4_core: Dynamically set guaranteed amount of counters per VF
    vxlan: check tun_info options_len properly
    net: bcmgenet: reset 40nm EPHY on energy detect
    net: dsa: fix switch tree list
  * net: add READ_ONCE() annotation in __skb_wait_for_more_packets()
      net/core/datagram.c
    selftests: net: reuseport_dualstack: fix uninitalized parameter
  * net: Zeroing the structure ethtool_wolinfo in ethtool_get_wol()
      net/core/ethtool.c
    net: hisilicon: Fix ping latency when deal with high throughput
  * net: fix sk_page_frag() recursion from memory reclaim
      include/linux/gfp.h
      include/net/sock.h
    dccp: do not leak jiffies on the wire
    cifs: Fix cifsInodeInfo lock_sem deadlock when reconnect occurs
    MIPS: bmips: mark exception vectors as char arrays
    of: unittest: fix memory leak in unittest_data_add
    scsi: target: core: Do not overwrite CDB byte 1
    ARM: davinci: dm365: Fix McBSP dma_slave_map entry
    perf kmem: Fix memory leak in compact_gfp_flags()
    ARM: dts: imx7s: Correct GPT's ipg clock source
  * scsi: fix kconfig dependency warning related to 53C700_LE_ON_BE
      drivers/scsi/Kconfig
    scsi: sni_53c710: fix compilation error
    scsi: scsi_dh_alua: handle RTPG sense code correctly during state transitions
    ARM: mm: fix alignment handler faults under memory pressure
    pinctrl: ns2: Fix off by one bugs in ns2_pinmux_enable()
    ARM: dts: logicpd-torpedo-som: Remove twl_keypad
    ASoc: rockchip: i2s: Fix RPM imbalance
    ASoC: wm_adsp: Don't generate kcontrols without READ flags
    regulator: pfuze100-regulator: Variable "val" in pfuze100_regulator_probe() could be uninitialized
    regulator: ti-abb: Fix timeout in ti_abb_wait_txdone/ti_abb_clear_all_txdone
    UPSTREAM: HID: steam: fix deadlock with input devices.
    UPSTREAM: HID: steam: fix boot loop with bluetooth firmware
    UPSTREAM: HID: steam: remove input device when a hid client is running.
    UPSTREAM: HID: steam: use hid_device.driver_data instead of hid_set_drvdata()
    UPSTREAM: HID: steam: add missing fields in client initialization
    UPSTREAM: HID: steam: add battery device.
  * UPSTREAM: HID: add driver for Valve Steam Controller
      drivers/hid/Kconfig
      drivers/hid/Makefile
      drivers/hid/hid-core.c
      drivers/hid/hid-ids.h
      include/linux/hid.h
  * UPSTREAM: HID: sony: Fix memory corruption issue on cleanup.
      drivers/hid/hid-sony.c
  * UPSTREAM: HID: sony: Fix race condition between rumble and device remove.
      drivers/hid/hid-sony.c
    Merge 4.9.199 into android-4.9-q
Linux 4.9.199
    Revert "ALSA: hda: Flush interrupts on disabling"
  * ALSA: timer: Fix mutex deadlock at releasing card
      sound/core/timer.c
  * ALSA: timer: Simplify error path in snd_timer_open()
      sound/core/timer.c
  * ALSA: timer: Limit max instances per timer
      include/sound/timer.h
      sound/core/timer.c
  * ALSA: timer: Follow standard EXPORT_SYMBOL() declarations
      sound/core/timer.c
    xfs: Correctly invert xfs_buftarg LRU isolation logic
    sctp: not bind the socket in sctp_connect
  * sctp: fix the issue that flags are ignored when using kernel_connect
      include/net/sctp/sctp.h
  * sch_netem: fix rcu splat in netem_enqueue()
      include/net/sch_generic.h
      net/sched/sch_netem.c
    net: usb: sr9800: fix uninitialized local variable
  * bonding: fix potential NULL deref in bond_update_slave_arr
      drivers/net/bonding/bond_main.c
    llc: fix sk_buff leak in llc_conn_service()
    llc: fix sk_buff leak in llc_sap_state_process()
    dmaengine: cppi41: Fix cppi41_dma_prep_slave_sg() when idle
    rtlwifi: Fix potential overflow on P2P code
    s390/cmm: fix information leak in cmm_timeout_handler()
  * nl80211: fix validation of mesh path nexthop
      net/wireless/nl80211.c
  * HID: fix error message in hid_open_report()
      drivers/hid/hid-core.c
  * HID: Fix assumption that devices have inputs
      drivers/hid/hid-dr.c
      drivers/hid/hid-gaff.c
      drivers/hid/hid-sony.c
    HID: i2c-hid: add Trekstor Primebook C11B to descriptor override
    USB: serial: whiteheat: fix line-speed endianness
    USB: serial: whiteheat: fix potential slab corruption
    USB: ldusb: fix control-message timeout
    USB: ldusb: fix ring-buffer locking
  * usb-storage: Revert commit 747668dbc061 ("usb-storage: Set virt_boundary_mask to avoid SG overflows")
      drivers/usb/storage/scsiglue.c
  * USB: gadget: Reject endpoints with 0 maxpacket value
      drivers/usb/gadget/udc/core.c
    UAS: Revert commit 3ae62a42090f ("UAS: fix alignment of scatter/gather segments")
    ALSA: bebob: Fix prototype of helper function to return negative value
  * fuse: truncate pending writes on O_TRUNC
      fs/fuse/file.c
  * fuse: flush dirty data/metadata before non-truncate setattr
      fs/fuse/dir.c
    ath6kl: fix a NULL-ptr-deref bug in ath6kl_usb_alloc_urb_from_pipe()
    thunderbolt: Use 32-bit writes when writing ring producer/consumer
    USB: legousbtower: fix a signedness bug in tower_probe()
  * tracing: Initialize iter->seq after zeroing in tracing_read_pipe()
      kernel/trace/trace.c
    s390/uaccess: avoid (false positive) compiler warnings
    NFSv4: Fix leak of clp->cl_acceptor string
    MIPS: fw: sni: Fix out of bounds init of o32 stack
    fs: ocfs2: fix a possible null-pointer dereference in ocfs2_info_scan_inode_alloc()
    fs: ocfs2: fix a possible null-pointer dereference in ocfs2_write_end_nolock()
    fs: ocfs2: fix possible null-pointer dereferences in ocfs2_xa_prepare_entry()
    ocfs2: clear zero in unaligned direct IO
    efi/x86: Do not clean dummy variable in kexec path
    efi/cper: Fix endianness of PCIe class code
    serial: mctrl_gpio: Check for NULL pointer
    fs: cifs: mute -Wunused-const-variable message
    gpio: max77620: Use correct unit for debounce times
    RDMA/iwcm: Fix a lock inversion issue
    staging: rtl8188eu: fix null dereference when kzalloc fails
    perf jevents: Fix period for Intel fixed counters
    perf map: Fix overlapped map handling
    iio: fix center temperature of bmc150-accel-core
  * exec: load_script: Do not exec truncated interpreter path
      fs/binfmt_script.c
    rtc: pcf8523: set xtal load capacitance from DT
  * usb: handle warm-reset port requests on hub resume
      drivers/usb/core/hub.c
  * scripts/setlocalversion: Improve -dirty check with git-status --no-optional-locks
      scripts/setlocalversion
    HID: i2c-hid: Add Odys Winbook 13 to descriptor override
    x86/cpu: Add Atom Tremont (Jacobsville)
    HID: i2c-hid: add Direkt-Tek DTLAPY133-1 to descriptor override
    sc16is7xx: Fix for "Unexpected interrupt: 8"
  * dm: Use kzalloc for all structs with embedded biosets/mempools
      drivers/md/dm-io.c
      drivers/md/dm-kcopyd.c
    dm snapshot: rework COW throttling to fix deadlock
    dm snapshot: introduce account_start_copy() and account_end_copy()
    dm snapshot: use mutex instead of rw_semaphore
  * binder: binder: fix possible UAF when freeing buffer
      drivers/android/binder.c
  * BACKPORT: dm bufio: introduce a global cache replacement
      drivers/md/dm-bufio.c
  * BACKPORT: dm bufio: remove old-style buffer cleanup
      drivers/md/dm-bufio.c
  * BACKPORT: dm bufio: introduce a global queue
      drivers/md/dm-bufio.c
  * BACKPORT: dm bufio: refactor adjust_total_allocated
      drivers/md/dm-bufio.c
  * BACKPORT: dm bufio: call adjust_total_allocated from __link_buffer and __unlink_buffer
      drivers/md/dm-bufio.c
    cuttlefish-4.9: Enable CONFIG_DM_SNAPSHOT
    Merge 4.9.198 into android-4.9-q
Linux 4.9.198
    RDMA/cxgb4: Do not dma memory off of the stack
  * Revert "net: sit: fix memory leak in sit_init_net()"
      net/ipv6/sit.c
  * PCI: PM: Fix pci_power_up()
      drivers/pci/pci.c
    xen/netback: fix error path of xenvif_connect_data()
  * cpufreq: Avoid cpufreq_suspend() deadlock on system shutdown
      drivers/base/core.c
      drivers/cpufreq/cpufreq.c
    memstick: jmb38x_ms: Fix an error handling path in 'jmb38x_ms_probe()'
    btrfs: block-group: Fix a memory leak due to missing btrfs_put_block_group()
    CIFS: avoid using MID 0xFFFF
    parisc: Fix vmap memory leak in ioremap()/iounmap()
    xtensa: drop EXPORT_SYMBOL for outs*/ins*
  * mm/slub: fix a deadlock in show_slab_objects()
      mm/slub.c
    scsi: zfcp: fix reaction on bit error threshold notification
  * drm/edid: Add 6 bpc quirk for SDC panel in Lenovo G50
      drivers/gpu/drm/drm_edid.c
    mac80211: Reject malformed SSID elements
    cfg80211: wext: avoid copying malformed SSIDs
    ASoC: rsnd: Reinitialize bit clock inversion flag for every format setting
    Input: da9063 - fix capability and drop KEY_SLEEP
  * scsi: core: try to get module before removing device
      drivers/scsi/scsi_sysfs.c
    staging: wlan-ng: fix exit return when sme->key_idx >= NUM_WEPKEYS
    MIPS: tlbex: Fix build_restore_pagemask KScratch restore
    USB: ldusb: fix read info leaks
    USB: usblp: fix use-after-free on disconnect
    USB: ldusb: fix memleak on disconnect
    USB: serial: ti_usb_3410_5052: fix port-close races
    usb: udc: lpc32xx: fix bad bit shift operation
    ALSA: hda/realtek - Add support for ALC711
    USB: legousbtower: fix memleak on disconnect
  * memfd: Fix locking when tagging pins
      mm/shmem.c
  * ipv4: Return -ENETUNREACH if we can't create route but saddr is valid
      net/ipv4/route.c
  * net: avoid potential infinite loop in tc_ctl_action()
      net/sched/act_api.c
    sctp: change sctp_prot .no_autobind with true
    net: bcmgenet: Set phydev->dev_flags only for internal PHYs
    net: bcmgenet: Fix RGMII_MODE_EN value for GENET v1/2/3
  * loop: Add LOOP_SET_DIRECT_IO to compat ioctl
      drivers/block/loop.c
    ocfs2: fix panic due to ocfs2_wq is null
    Revert "drm/radeon: Fix EEH during kexec"
    namespace: fix namespace.pl script to support relative paths
    net: hisilicon: Fix usage of uninitialized variable in function mdio_sc_cfg_reg_write()
    mips: Loongson: Fix the link time qualifier of 'serial_exit()'
    mac80211: fix txq null pointer dereference
  * nl80211: fix null pointer dereference
      net/wireless/nl80211.c
    MIPS: dts: ar9331: fix interrupt-controller size
    ARM: dts: am4372: Set memory bandwidth limit for DISPC
    ARM: OMAP2+: Fix missing reset done flag for am3 and am43
    scsi: qla2xxx: Fix unbound sleep in fcport delete path.
    scsi: megaraid: disable device when probe failed after enabled device
  * scsi: ufs: skip shutdown if hba is not powered
      drivers/scsi/ufs/ufshcd.c
    rtlwifi: Fix potential overflow on P2P code
    ANDROID: clang: update to 9.0.8 based on r365631c
  * ANDROID: move up spin_unlock_bh() ahead of remove_proc_entry()
      net/netfilter/xt_quota2.c
    ANDROID: refactor build.config files to remove duplication
    Merge 4.9.197 into android-4.9-q
Linux 4.9.197
    xfs: clear sb->s_fs_info on mount failure
    x86/asm: Fix MWAITX C-state hint value
  * tracing: Get trace_array reference for available_tracers files
      kernel/trace/trace.c
    tracing/hwlat: Don't ignore outer-loop duration when calculating max_latency
    tracing/hwlat: Report total time spent in all NMIs during the sample
    media: stkwebcam: fix runtime PM after driver unbind
  * Fix the locking in dcache_readdir() and friends
      fs/libfs.c
    MIPS: Disable Loongson MMI instructions for kernel build
    Staging: fbtft: fix memory leak in fbtft_framebuffer_alloc
    staging: fbtft: Stop using BL_CORE_DRIVER1
  * kernel/sysctl.c: do not override max_threads provided by userspace
      kernel/fork.c
    CIFS: Force reval dentry if LOOKUP_REVAL flag is set
    CIFS: Force revalidate inode when dentry is stale
    CIFS: Gracefully handle QueryInfo errors during open
    perf inject jit: Fix JIT_CODE_MOVE filename
    perf llvm: Don't access out-of-scope array
    efivar/ssdt: Don't iterate over EFI vars if no SSDT override was specified
    iio: light: opt3001: fix mutex unlock race
    iio: adc: ad799x: fix probe error handling
    staging: vt6655: Fix memory leak in vt6655_probe
    USB: legousbtower: fix use-after-free on release
    USB: legousbtower: fix open after failed reset request
    USB: legousbtower: fix potential NULL-deref on disconnect
    USB: legousbtower: fix deadlock on disconnect
    USB: legousbtower: fix slab info leak at probe
    usb: renesas_usbhs: gadget: Fix usb_ep_set_{halt,wedge}() behavior
    usb: renesas_usbhs: gadget: Do not discard queues in usb_ep_set_{halt,wedge}()
    USB: dummy-hcd: fix power budget for SuperSpeed mode
    USB: microtek: fix info-leak at probe
    USB: usblcd: fix I/O after disconnect
    USB: serial: fix runtime PM after driver unbind
    USB: serial: option: add support for Cinterion CLS8 devices
    USB: serial: option: add Telit FN980 compositions
    USB: serial: ftdi_sio: add device IDs for Sienna and Echelon PL-20
    USB: serial: keyspan: fix NULL-derefs on open() and write()
    serial: uartlite: fix exit path null pointer
    USB: ldusb: fix NULL-derefs on driver unbind
    USB: chaoskey: fix use-after-free on release
    USB: usblp: fix runtime PM after driver unbind
    USB: iowarrior: fix use-after-free after driver unbind
    USB: iowarrior: fix use-after-free on release
    USB: iowarrior: fix use-after-free on disconnect
    USB: adutux: fix use-after-free on release
    USB: adutux: fix NULL-derefs on disconnect
    USB: adutux: fix use-after-free on disconnect
    USB: adutux: remove redundant variable minor
  * xhci: Increase STS_SAVE timeout in xhci_suspend()
      drivers/usb/host/xhci.c
  * usb: xhci: wait for CNR controller not ready bit in xhci resume
      drivers/usb/host/xhci.c
  * xhci: Check all endpoints for LPM timeout
      drivers/usb/host/xhci.c
  * xhci: Prevent device initiated U1/U2 link pm if exit latency is too long
      drivers/usb/host/xhci.c
  * xhci: Fix false warning message about wrong bounce buffer write length
      drivers/usb/host/xhci-ring.c
    USB: usb-skeleton: fix NULL-deref on disconnect
    USB: usb-skeleton: fix runtime PM after driver unbind
    USB: yurex: fix NULL-derefs on disconnect
    USB: yurex: Don't retry on unexpected errors
  * USB: rio500: Remove Rio 500 kernel driver
      drivers/usb/misc/Kconfig
      drivers/usb/misc/Makefile
  * panic: ensure preemption is disabled during panic()
      kernel/panic.c
    ASoC: sgtl5000: Improve VAG power and mute control
  * nl80211: validate beacon head
      net/wireless/nl80211.c
  * cfg80211: Use const more consistently in for_each_element macros
      include/linux/ieee80211.h
  * cfg80211: add and use strongly typed element iteration macros
      include/linux/ieee80211.h
      net/wireless/scan.c
    coresight: etm4x: Use explicit barriers on enable/disable
    crypto: caam - fix concurrency issue in givencrypt descriptor
    perf stat: Reset previous counts on repeat with interval
    perf stat: Fix a segmentation fault when using repeat forever
    perf tools: Fix segfault in cpu_cache_level__read()
    tools lib traceevent: Do not free tep->cmdlines in add_new_comm() on failure
  * kernel/elfcore.c: include proper prototypes
      kernel/elfcore.c
  * sched/core: Fix migration to invalid CPU in __set_cpus_allowed_ptr()
      kernel/sched/core.c
    fuse: fix memleak in cuse_channel_open
  * thermal: Fix use-after-free when unregistering thermal zone device
      drivers/thermal/thermal_core.c
    drm/amdgpu: Check for valid number of registers to read
    ceph: reconnect connection if session hang in opening state
    ceph: fix directories inode i_blkbits initialization
    xen/pci: reserve MCFG areas earlier
    9p: avoid attaching writeback_fid on mmap with type PRIVATE
    fs: nfs: Fix possible null-pointer dereferences in encode_attrs()
    ima: always return negative code for error
  * cfg80211: initialize on-stack chandefs
      net/wireless/nl80211.c
      net/wireless/reg.c
    ieee802154: atusb: fix use-after-free at disconnect
    watchdog: imx2_wdt: fix min() calculation in imx2_wdt_set_timeout
  * timer: Read jiffies once when forwarding base clk
      kernel/time/timer.c
  * usercopy: Avoid HIGHMEM pfn warning
      mm/usercopy.c
    crypto: qat - Silence smp_processor_id() warning
    can: mcp251x: mcp251x_hw_reset(): allow more time after a reset
    powerpc/powernv: Restrict OPAL symbol map to only be readable by root
  * ASoC: Define a set of DAPM pre/post-up events
      include/sound/soc-dapm.h
    KVM: nVMX: handle page fault in vmread fix
    s390/cio: exclude subchannels with no parent from pseudo check
    s390/cio: avoid calling strlen on null pointer
    s390/topology: avoid firing events before kobjs are created
    KVM: s390: Test for bad access register and size at the start of S390_MEM_OP
    ANDROID: cuttlefish_defconfig: Enable BPF_JIT and BPF_JIT_ALWAYS_ON

Change-Id: I55a3a4245646ca4ff5e4d0b29a592e4b4dce77fb
Signed-off-by: lucaswei <lucaswei@google.com>
2019-11-22 13:47:52 +08:00

590 lines
22 KiB
C

#ifndef __LINUX_GFP_H
#define __LINUX_GFP_H
#include <linux/mmdebug.h>
#include <linux/mmzone.h>
#include <linux/stddef.h>
#include <linux/linkage.h>
#include <linux/topology.h>
struct vm_area_struct;
/*
* In case of changes, please don't forget to update
* include/trace/events/mmflags.h and tools/perf/builtin-kmem.c
*/
/* Plain integer GFP bitmasks. Do not use this directly. */
#define ___GFP_DMA 0x01u
#define ___GFP_HIGHMEM 0x02u
#define ___GFP_DMA32 0x04u
#define ___GFP_MOVABLE 0x08u
#define ___GFP_RECLAIMABLE 0x10u
#define ___GFP_HIGH 0x20u
#define ___GFP_IO 0x40u
#define ___GFP_FS 0x80u
#define ___GFP_COLD 0x100u
#define ___GFP_NOWARN 0x200u
#define ___GFP_REPEAT 0x400u
#define ___GFP_NOFAIL 0x800u
#define ___GFP_NORETRY 0x1000u
#define ___GFP_MEMALLOC 0x2000u
#define ___GFP_COMP 0x4000u
#define ___GFP_ZERO 0x8000u
#define ___GFP_NOMEMALLOC 0x10000u
#define ___GFP_HARDWALL 0x20000u
#define ___GFP_THISNODE 0x40000u
#define ___GFP_ATOMIC 0x80000u
#define ___GFP_ACCOUNT 0x100000u
#define ___GFP_NOTRACK 0x200000u
#define ___GFP_DIRECT_RECLAIM 0x400000u
#define ___GFP_OTHER_NODE 0x800000u
#define ___GFP_WRITE 0x1000000u
#define ___GFP_KSWAPD_RECLAIM 0x2000000u
#define ___GFP_CMA 0x4000000u
/* If the above are modified, __GFP_BITS_SHIFT may need updating */
/*
* Physical address zone modifiers (see linux/mmzone.h - low four bits)
*
* Do not put any conditional on these. If necessary modify the definitions
* without the underscores and use them consistently. The definitions here may
* be used in bit comparisons.
*/
#define __GFP_DMA ((__force gfp_t)___GFP_DMA)
#define __GFP_HIGHMEM ((__force gfp_t)___GFP_HIGHMEM)
#define __GFP_DMA32 ((__force gfp_t)___GFP_DMA32)
#define __GFP_MOVABLE ((__force gfp_t)___GFP_MOVABLE) /* ZONE_MOVABLE allowed */
#define __GFP_CMA ((__force gfp_t)___GFP_CMA)
#define GFP_ZONEMASK (__GFP_DMA|__GFP_HIGHMEM|__GFP_DMA32|__GFP_MOVABLE| \
__GFP_CMA)
/*
* Page mobility and placement hints
*
* These flags provide hints about how mobile the page is. Pages with similar
* mobility are placed within the same pageblocks to minimise problems due
* to external fragmentation.
*
* __GFP_MOVABLE (also a zone modifier) indicates that the page can be
* moved by page migration during memory compaction or can be reclaimed.
*
* __GFP_RECLAIMABLE is used for slab allocations that specify
* SLAB_RECLAIM_ACCOUNT and whose pages can be freed via shrinkers.
*
* __GFP_WRITE indicates the caller intends to dirty the page. Where possible,
* these pages will be spread between local zones to avoid all the dirty
* pages being in one zone (fair zone allocation policy).
*
* __GFP_HARDWALL enforces the cpuset memory allocation policy.
*
* __GFP_THISNODE forces the allocation to be satisified from the requested
* node with no fallbacks or placement policy enforcements.
*
* __GFP_ACCOUNT causes the allocation to be accounted to kmemcg.
*/
#define __GFP_RECLAIMABLE ((__force gfp_t)___GFP_RECLAIMABLE)
#define __GFP_WRITE ((__force gfp_t)___GFP_WRITE)
#define __GFP_HARDWALL ((__force gfp_t)___GFP_HARDWALL)
#define __GFP_THISNODE ((__force gfp_t)___GFP_THISNODE)
#define __GFP_ACCOUNT ((__force gfp_t)___GFP_ACCOUNT)
/*
* Watermark modifiers -- controls access to emergency reserves
*
* __GFP_HIGH indicates that the caller is high-priority and that granting
* the request is necessary before the system can make forward progress.
* For example, creating an IO context to clean pages.
*
* __GFP_ATOMIC indicates that the caller cannot reclaim or sleep and is
* high priority. Users are typically interrupt handlers. This may be
* used in conjunction with __GFP_HIGH
*
* __GFP_MEMALLOC allows access to all memory. This should only be used when
* the caller guarantees the allocation will allow more memory to be freed
* very shortly e.g. process exiting or swapping. Users either should
* be the MM or co-ordinating closely with the VM (e.g. swap over NFS).
*
* __GFP_NOMEMALLOC is used to explicitly forbid access to emergency reserves.
* This takes precedence over the __GFP_MEMALLOC flag if both are set.
*/
#define __GFP_ATOMIC ((__force gfp_t)___GFP_ATOMIC)
#define __GFP_HIGH ((__force gfp_t)___GFP_HIGH)
#define __GFP_MEMALLOC ((__force gfp_t)___GFP_MEMALLOC)
#define __GFP_NOMEMALLOC ((__force gfp_t)___GFP_NOMEMALLOC)
/*
* Reclaim modifiers
*
* __GFP_IO can start physical IO.
*
* __GFP_FS can call down to the low-level FS. Clearing the flag avoids the
* allocator recursing into the filesystem which might already be holding
* locks.
*
* __GFP_DIRECT_RECLAIM indicates that the caller may enter direct reclaim.
* This flag can be cleared to avoid unnecessary delays when a fallback
* option is available.
*
* __GFP_KSWAPD_RECLAIM indicates that the caller wants to wake kswapd when
* the low watermark is reached and have it reclaim pages until the high
* watermark is reached. A caller may wish to clear this flag when fallback
* options are available and the reclaim is likely to disrupt the system. The
* canonical example is THP allocation where a fallback is cheap but
* reclaim/compaction may cause indirect stalls.
*
* __GFP_RECLAIM is shorthand to allow/forbid both direct and kswapd reclaim.
*
* __GFP_REPEAT: Try hard to allocate the memory, but the allocation attempt
* _might_ fail. This depends upon the particular VM implementation.
*
* __GFP_NOFAIL: The VM implementation _must_ retry infinitely: the caller
* cannot handle allocation failures. New users should be evaluated carefully
* (and the flag should be used only when there is no reasonable failure
* policy) but it is definitely preferable to use the flag rather than
* opencode endless loop around allocator.
*
* __GFP_NORETRY: The VM implementation must not retry indefinitely and will
* return NULL when direct reclaim and memory compaction have failed to allow
* the allocation to succeed. The OOM killer is not called with the current
* implementation.
*/
#define __GFP_IO ((__force gfp_t)___GFP_IO)
#define __GFP_FS ((__force gfp_t)___GFP_FS)
#define __GFP_DIRECT_RECLAIM ((__force gfp_t)___GFP_DIRECT_RECLAIM) /* Caller can reclaim */
#define __GFP_KSWAPD_RECLAIM ((__force gfp_t)___GFP_KSWAPD_RECLAIM) /* kswapd can wake */
#define __GFP_RECLAIM ((__force gfp_t)(___GFP_DIRECT_RECLAIM|___GFP_KSWAPD_RECLAIM))
#define __GFP_REPEAT ((__force gfp_t)___GFP_REPEAT)
#define __GFP_NOFAIL ((__force gfp_t)___GFP_NOFAIL)
#define __GFP_NORETRY ((__force gfp_t)___GFP_NORETRY)
/*
* Action modifiers
*
* __GFP_COLD indicates that the caller does not expect to be used in the near
* future. Where possible, a cache-cold page will be returned.
*
* __GFP_NOWARN suppresses allocation failure reports.
*
* __GFP_COMP address compound page metadata.
*
* __GFP_ZERO returns a zeroed page on success.
*
* __GFP_NOTRACK avoids tracking with kmemcheck.
*
* __GFP_NOTRACK_FALSE_POSITIVE is an alias of __GFP_NOTRACK. It's a means of
* distinguishing in the source between false positives and allocations that
* cannot be supported (e.g. page tables).
*
* __GFP_OTHER_NODE is for allocations that are on a remote node but that
* should not be accounted for as a remote allocation in vmstat. A
* typical user would be khugepaged collapsing a huge page on a remote
* node.
*/
#define __GFP_COLD ((__force gfp_t)___GFP_COLD)
#define __GFP_NOWARN ((__force gfp_t)___GFP_NOWARN)
#define __GFP_COMP ((__force gfp_t)___GFP_COMP)
#define __GFP_ZERO ((__force gfp_t)___GFP_ZERO)
#define __GFP_NOTRACK ((__force gfp_t)___GFP_NOTRACK)
#define __GFP_NOTRACK_FALSE_POSITIVE (__GFP_NOTRACK)
#define __GFP_OTHER_NODE ((__force gfp_t)___GFP_OTHER_NODE)
/* Room for N __GFP_FOO bits */
#define __GFP_BITS_SHIFT 27
#define __GFP_BITS_MASK ((__force gfp_t)((1 << __GFP_BITS_SHIFT) - 1))
/*
* Useful GFP flag combinations that are commonly used. It is recommended
* that subsystems start with one of these combinations and then set/clear
* __GFP_FOO flags as necessary.
*
* GFP_ATOMIC users can not sleep and need the allocation to succeed. A lower
* watermark is applied to allow access to "atomic reserves"
*
* GFP_KERNEL is typical for kernel-internal allocations. The caller requires
* ZONE_NORMAL or a lower zone for direct access but can direct reclaim.
*
* GFP_KERNEL_ACCOUNT is the same as GFP_KERNEL, except the allocation is
* accounted to kmemcg.
*
* GFP_NOWAIT is for kernel allocations that should not stall for direct
* reclaim, start physical IO or use any filesystem callback.
*
* GFP_NOIO will use direct reclaim to discard clean pages or slab pages
* that do not require the starting of any physical IO.
*
* GFP_NOFS will use direct reclaim but will not use any filesystem interfaces.
*
* GFP_USER is for userspace allocations that also need to be directly
* accessibly by the kernel or hardware. It is typically used by hardware
* for buffers that are mapped to userspace (e.g. graphics) that hardware
* still must DMA to. cpuset limits are enforced for these allocations.
*
* GFP_DMA exists for historical reasons and should be avoided where possible.
* The flags indicates that the caller requires that the lowest zone be
* used (ZONE_DMA or 16M on x86-64). Ideally, this would be removed but
* it would require careful auditing as some users really require it and
* others use the flag to avoid lowmem reserves in ZONE_DMA and treat the
* lowest zone as a type of emergency reserve.
*
* GFP_DMA32 is similar to GFP_DMA except that the caller requires a 32-bit
* address.
*
* GFP_HIGHUSER is for userspace allocations that may be mapped to userspace,
* do not need to be directly accessible by the kernel but that cannot
* move once in use. An example may be a hardware allocation that maps
* data directly into userspace but has no addressing limitations.
*
* GFP_HIGHUSER_MOVABLE is for userspace allocations that the kernel does not
* need direct access to but can use kmap() when access is required. They
* are expected to be movable via page reclaim or page migration. Typically,
* pages on the LRU would also be allocated with GFP_HIGHUSER_MOVABLE.
*
* GFP_TRANSHUGE and GFP_TRANSHUGE_LIGHT are used for THP allocations. They are
* compound allocations that will generally fail quickly if memory is not
* available and will not wake kswapd/kcompactd on failure. The _LIGHT
* version does not attempt reclaim/compaction at all and is by default used
* in page fault path, while the non-light is used by khugepaged.
*/
#define GFP_ATOMIC (__GFP_HIGH|__GFP_ATOMIC|__GFP_KSWAPD_RECLAIM)
#define GFP_KERNEL (__GFP_RECLAIM | __GFP_IO | __GFP_FS)
#define GFP_KERNEL_ACCOUNT (GFP_KERNEL | __GFP_ACCOUNT)
#define GFP_NOWAIT (__GFP_KSWAPD_RECLAIM)
#define GFP_NOIO (__GFP_RECLAIM)
#define GFP_NOFS (__GFP_RECLAIM | __GFP_IO)
#define GFP_TEMPORARY (__GFP_RECLAIM | __GFP_IO | __GFP_FS | \
__GFP_RECLAIMABLE)
#define GFP_USER (__GFP_RECLAIM | __GFP_IO | __GFP_FS | __GFP_HARDWALL)
#define GFP_DMA __GFP_DMA
#define GFP_DMA32 __GFP_DMA32
#define GFP_HIGHUSER (GFP_USER | __GFP_HIGHMEM)
#define GFP_HIGHUSER_MOVABLE (GFP_HIGHUSER | __GFP_MOVABLE)
#define GFP_TRANSHUGE_LIGHT ((GFP_HIGHUSER_MOVABLE | __GFP_COMP | \
__GFP_NOMEMALLOC | __GFP_NOWARN) & ~__GFP_RECLAIM)
#define GFP_TRANSHUGE (GFP_TRANSHUGE_LIGHT | __GFP_DIRECT_RECLAIM)
/* Convert GFP flags to their corresponding migrate type */
#define GFP_MOVABLE_MASK (__GFP_RECLAIMABLE|__GFP_MOVABLE)
#define GFP_MOVABLE_SHIFT 3
static inline int gfpflags_to_migratetype(const gfp_t gfp_flags)
{
VM_WARN_ON((gfp_flags & GFP_MOVABLE_MASK) == GFP_MOVABLE_MASK);
BUILD_BUG_ON((1UL << GFP_MOVABLE_SHIFT) != ___GFP_MOVABLE);
BUILD_BUG_ON((___GFP_MOVABLE >> GFP_MOVABLE_SHIFT) != MIGRATE_MOVABLE);
if (unlikely(page_group_by_mobility_disabled))
return MIGRATE_UNMOVABLE;
/* Group based on mobility */
#ifndef CONFIG_CMA
return (gfp_flags & GFP_MOVABLE_MASK) >> GFP_MOVABLE_SHIFT;
#else
return ((gfp_flags & GFP_MOVABLE_MASK) >> GFP_MOVABLE_SHIFT) |
((gfp_flags & __GFP_CMA) != 0);
#endif
}
#undef GFP_MOVABLE_MASK
#undef GFP_MOVABLE_SHIFT
static inline bool gfpflags_allow_blocking(const gfp_t gfp_flags)
{
return !!(gfp_flags & __GFP_DIRECT_RECLAIM);
}
/**
* gfpflags_normal_context - is gfp_flags a normal sleepable context?
* @gfp_flags: gfp_flags to test
*
* Test whether @gfp_flags indicates that the allocation is from the
* %current context and allowed to sleep.
*
* An allocation being allowed to block doesn't mean it owns the %current
* context. When direct reclaim path tries to allocate memory, the
* allocation context is nested inside whatever %current was doing at the
* time of the original allocation. The nested allocation may be allowed
* to block but modifying anything %current owns can corrupt the outer
* context's expectations.
*
* %true result from this function indicates that the allocation context
* can sleep and use anything that's associated with %current.
*/
static inline bool gfpflags_normal_context(const gfp_t gfp_flags)
{
return (gfp_flags & (__GFP_DIRECT_RECLAIM | __GFP_MEMALLOC)) ==
__GFP_DIRECT_RECLAIM;
}
#ifdef CONFIG_HIGHMEM
#define OPT_ZONE_HIGHMEM ZONE_HIGHMEM
#else
#define OPT_ZONE_HIGHMEM ZONE_NORMAL
#endif
#ifdef CONFIG_ZONE_DMA
#define OPT_ZONE_DMA ZONE_DMA
#else
#define OPT_ZONE_DMA ZONE_NORMAL
#endif
#ifdef CONFIG_ZONE_DMA32
#define OPT_ZONE_DMA32 ZONE_DMA32
#else
#define OPT_ZONE_DMA32 ZONE_NORMAL
#endif
/*
* GFP_ZONE_TABLE is a word size bitstring that is used for looking up the
* zone to use given the lowest 4 bits of gfp_t. Entries are ZONE_SHIFT long
* and there are 16 of them to cover all possible combinations of
* __GFP_DMA, __GFP_DMA32, __GFP_MOVABLE and __GFP_HIGHMEM.
*
* The zone fallback order is MOVABLE=>HIGHMEM=>NORMAL=>DMA32=>DMA.
* But GFP_MOVABLE is not only a zone specifier but also an allocation
* policy. Therefore __GFP_MOVABLE plus another zone selector is valid.
* Only 1 bit of the lowest 3 bits (DMA,DMA32,HIGHMEM) can be set to "1".
*
* bit result
* =================
* 0x0 => NORMAL
* 0x1 => DMA or NORMAL
* 0x2 => HIGHMEM or NORMAL
* 0x3 => BAD (DMA+HIGHMEM)
* 0x4 => DMA32 or DMA or NORMAL
* 0x5 => BAD (DMA+DMA32)
* 0x6 => BAD (HIGHMEM+DMA32)
* 0x7 => BAD (HIGHMEM+DMA32+DMA)
* 0x8 => NORMAL (MOVABLE+0)
* 0x9 => DMA or NORMAL (MOVABLE+DMA)
* 0xa => MOVABLE (Movable is valid only if HIGHMEM is set too)
* 0xb => BAD (MOVABLE+HIGHMEM+DMA)
* 0xc => DMA32 (MOVABLE+DMA32)
* 0xd => BAD (MOVABLE+DMA32+DMA)
* 0xe => BAD (MOVABLE+DMA32+HIGHMEM)
* 0xf => BAD (MOVABLE+DMA32+HIGHMEM+DMA)
*
* GFP_ZONES_SHIFT must be <= 2 on 32 bit platforms.
*/
#if defined(CONFIG_ZONE_DEVICE) && (MAX_NR_ZONES-1) <= 4
/* ZONE_DEVICE is not a valid GFP zone specifier */
#define GFP_ZONES_SHIFT 2
#else
#define GFP_ZONES_SHIFT ZONES_SHIFT
#endif
#if 16 * GFP_ZONES_SHIFT > BITS_PER_LONG
#error GFP_ZONES_SHIFT too large to create GFP_ZONE_TABLE integer
#endif
#define GFP_ZONE_TABLE ( \
(ZONE_NORMAL << 0 * GFP_ZONES_SHIFT) \
| (OPT_ZONE_DMA << ___GFP_DMA * GFP_ZONES_SHIFT) \
| (OPT_ZONE_HIGHMEM << ___GFP_HIGHMEM * GFP_ZONES_SHIFT) \
| (OPT_ZONE_DMA32 << ___GFP_DMA32 * GFP_ZONES_SHIFT) \
| (ZONE_NORMAL << ___GFP_MOVABLE * GFP_ZONES_SHIFT) \
| (OPT_ZONE_DMA << (___GFP_MOVABLE | ___GFP_DMA) * GFP_ZONES_SHIFT) \
| (ZONE_MOVABLE << (___GFP_MOVABLE | ___GFP_HIGHMEM) * GFP_ZONES_SHIFT)\
| (OPT_ZONE_DMA32 << (___GFP_MOVABLE | ___GFP_DMA32) * GFP_ZONES_SHIFT)\
)
/*
* GFP_ZONE_BAD is a bitmap for all combinations of __GFP_DMA, __GFP_DMA32
* __GFP_HIGHMEM and __GFP_MOVABLE that are not permitted. One flag per
* entry starting with bit 0. Bit is set if the combination is not
* allowed.
*/
#define GFP_ZONE_BAD ( \
1 << (___GFP_DMA | ___GFP_HIGHMEM) \
| 1 << (___GFP_DMA | ___GFP_DMA32) \
| 1 << (___GFP_DMA32 | ___GFP_HIGHMEM) \
| 1 << (___GFP_DMA | ___GFP_DMA32 | ___GFP_HIGHMEM) \
| 1 << (___GFP_MOVABLE | ___GFP_HIGHMEM | ___GFP_DMA) \
| 1 << (___GFP_MOVABLE | ___GFP_DMA32 | ___GFP_DMA) \
| 1 << (___GFP_MOVABLE | ___GFP_DMA32 | ___GFP_HIGHMEM) \
| 1 << (___GFP_MOVABLE | ___GFP_DMA32 | ___GFP_DMA | ___GFP_HIGHMEM) \
)
static inline enum zone_type gfp_zone(gfp_t flags)
{
enum zone_type z;
int bit = (__force int) (flags & GFP_ZONEMASK);
z = (GFP_ZONE_TABLE >> (bit * GFP_ZONES_SHIFT)) &
((1 << GFP_ZONES_SHIFT) - 1);
VM_BUG_ON((GFP_ZONE_BAD >> bit) & 1);
return z;
}
/*
* There is only one page-allocator function, and two main namespaces to
* it. The alloc_page*() variants return 'struct page *' and as such
* can allocate highmem pages, the *get*page*() variants return
* virtual kernel addresses to the allocated page(s).
*/
static inline int gfp_zonelist(gfp_t flags)
{
#ifdef CONFIG_NUMA
if (unlikely(flags & __GFP_THISNODE))
return ZONELIST_NOFALLBACK;
#endif
return ZONELIST_FALLBACK;
}
/*
* We get the zone list from the current node and the gfp_mask.
* This zone list contains a maximum of MAXNODES*MAX_NR_ZONES zones.
* There are two zonelists per node, one for all zones with memory and
* one containing just zones from the node the zonelist belongs to.
*
* For the normal case of non-DISCONTIGMEM systems the NODE_DATA() gets
* optimized to &contig_page_data at compile-time.
*/
static inline struct zonelist *node_zonelist(int nid, gfp_t flags)
{
return NODE_DATA(nid)->node_zonelists + gfp_zonelist(flags);
}
#ifndef HAVE_ARCH_FREE_PAGE
static inline void arch_free_page(struct page *page, int order) { }
#endif
#ifndef HAVE_ARCH_ALLOC_PAGE
static inline void arch_alloc_page(struct page *page, int order) { }
#endif
struct page *
__alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order,
struct zonelist *zonelist, nodemask_t *nodemask);
static inline struct page *
__alloc_pages(gfp_t gfp_mask, unsigned int order,
struct zonelist *zonelist)
{
return __alloc_pages_nodemask(gfp_mask, order, zonelist, NULL);
}
/*
* Allocate pages, preferring the node given as nid. The node must be valid and
* online. For more general interface, see alloc_pages_node().
*/
static inline struct page *
__alloc_pages_node(int nid, gfp_t gfp_mask, unsigned int order)
{
VM_BUG_ON(nid < 0 || nid >= MAX_NUMNODES);
VM_WARN_ON(!node_online(nid));
return __alloc_pages(gfp_mask, order, node_zonelist(nid, gfp_mask));
}
/*
* Allocate pages, preferring the node given as nid. When nid == NUMA_NO_NODE,
* prefer the current CPU's closest node. Otherwise node must be valid and
* online.
*/
static inline struct page *alloc_pages_node(int nid, gfp_t gfp_mask,
unsigned int order)
{
if (nid == NUMA_NO_NODE)
nid = numa_mem_id();
return __alloc_pages_node(nid, gfp_mask, order);
}
#ifdef CONFIG_NUMA
extern struct page *alloc_pages_current(gfp_t gfp_mask, unsigned order);
static inline struct page *
alloc_pages(gfp_t gfp_mask, unsigned int order)
{
return alloc_pages_current(gfp_mask, order);
}
extern struct page *alloc_pages_vma(gfp_t gfp_mask, int order,
struct vm_area_struct *vma, unsigned long addr,
int node, bool hugepage);
#define alloc_hugepage_vma(gfp_mask, vma, addr, order) \
alloc_pages_vma(gfp_mask, order, vma, addr, numa_node_id(), true)
#else
#define alloc_pages(gfp_mask, order) \
alloc_pages_node(numa_node_id(), gfp_mask, order)
#define alloc_pages_vma(gfp_mask, order, vma, addr, node, false)\
alloc_pages(gfp_mask, order)
#define alloc_hugepage_vma(gfp_mask, vma, addr, order) \
alloc_pages(gfp_mask, order)
#endif
#define alloc_page(gfp_mask) alloc_pages(gfp_mask, 0)
#define alloc_page_vma(gfp_mask, vma, addr) \
alloc_pages_vma(gfp_mask, 0, vma, addr, numa_node_id(), false)
#define alloc_page_vma_node(gfp_mask, vma, addr, node) \
alloc_pages_vma(gfp_mask, 0, vma, addr, node, false)
extern unsigned long __get_free_pages(gfp_t gfp_mask, unsigned int order);
extern unsigned long get_zeroed_page(gfp_t gfp_mask);
void *alloc_pages_exact(size_t size, gfp_t gfp_mask);
void free_pages_exact(void *virt, size_t size);
void * __meminit alloc_pages_exact_nid(int nid, size_t size, gfp_t gfp_mask);
#define __get_free_page(gfp_mask) \
__get_free_pages((gfp_mask), 0)
#define __get_dma_pages(gfp_mask, order) \
__get_free_pages((gfp_mask) | GFP_DMA, (order))
extern void __free_pages(struct page *page, unsigned int order);
extern void free_pages(unsigned long addr, unsigned int order);
extern void free_hot_cold_page(struct page *page, bool cold);
extern void free_hot_cold_page_list(struct list_head *list, bool cold);
struct page_frag_cache;
extern void *__alloc_page_frag(struct page_frag_cache *nc,
unsigned int fragsz, gfp_t gfp_mask);
extern void __free_page_frag(void *addr);
#define __free_page(page) __free_pages((page), 0)
#define free_page(addr) free_pages((addr), 0)
void page_alloc_init(void);
void drain_zone_pages(struct zone *zone, struct per_cpu_pages *pcp);
void drain_all_pages(struct zone *zone);
void drain_local_pages(void *zone);
void page_alloc_init_late(void);
/*
* gfp_allowed_mask is set to GFP_BOOT_MASK during early boot to restrict what
* GFP flags are used before interrupts are enabled. Once interrupts are
* enabled, it is set to __GFP_BITS_MASK while the system is running. During
* hibernation, it is used by PM to avoid I/O during memory allocation while
* devices are suspended.
*/
extern gfp_t gfp_allowed_mask;
/* Returns true if the gfp_mask allows use of ALLOC_NO_WATERMARK */
bool gfp_pfmemalloc_allowed(gfp_t gfp_mask);
extern void pm_restrict_gfp_mask(void);
extern void pm_restore_gfp_mask(void);
#ifdef CONFIG_PM_SLEEP
extern bool pm_suspended_storage(void);
#else
static inline bool pm_suspended_storage(void)
{
return false;
}
#endif /* CONFIG_PM_SLEEP */
#if (defined(CONFIG_MEMORY_ISOLATION) && defined(CONFIG_COMPACTION)) || defined(CONFIG_CMA)
/* The below functions must be run on a range from a single zone. */
extern int alloc_contig_range(unsigned long start, unsigned long end,
unsigned migratetype);
extern void free_contig_range(unsigned long pfn, unsigned nr_pages);
#endif
#ifdef CONFIG_CMA
/* CMA stuff */
extern void init_cma_reserved_pageblock(struct page *page);
#endif
#endif /* __LINUX_GFP_H */