Files
kernel_google_redbull/mm/memblock.c
Lucas Wei b90a1cd836 Merge android-4.19-stable (4.19.234) into android-msm-pixel-4.19-lts
Merge 4.19.234 into android-4.19-stable
Linux 4.19.234
    xen/netfront: react properly to failing gnttab_end_foreign_access_ref()
  * xen/gnttab: fix gnttab_end_foreign_access() without page specified
      include/xen/grant_table.h
    xen/pvcalls: use alloc/free_pages_exact()
    xen/9p: use alloc/free_pages_exact()
  * xen: remove gnttab_query_foreign_access()
      include/xen/grant_table.h
    xen/gntalloc: don't use gnttab_query_foreign_access()
    xen/scsifront: don't use gnttab_query_foreign_access() for mapped status
    xen/netfront: don't use gnttab_query_foreign_access() for mapped status
    xen/blkfront: don't use gnttab_query_foreign_access() for mapped status
  * xen/grant-table: add gnttab_try_end_foreign_access()
      include/xen/grant_table.h
    xen/xenbus: don't let xenbus_grant_ring() remove grants in error case
    ARM: fix build warning in proc-v7-bugs.c
    ARM: Do not use NOCROSSREFS directive with ld.lld
    ARM: fix co-processor register typo
  * kbuild: add CONFIG_LD_IS_LLD
      init/Kconfig
    ARM: fix build error when BPF_SYSCALL is disabled
    ARM: include unprivileged BPF status in Spectre V2 reporting
    ARM: Spectre-BHB workaround
    ARM: use LOADADDR() to get load address of sections
    ARM: early traps initialisation
    ARM: report Spectre v2 status through sysfs
  * arm/arm64: smccc/psci: add arm_smccc_1_1_get_conduit()
      drivers/firmware/psci.c
      include/linux/arm-smccc.h
  * arm/arm64: Provide a wrapper for SMCCC 1.1 calls
      include/linux/arm-smccc.h
    x86/speculation: Warn about eIBRS + LFENCE + Unprivileged eBPF + SMT
    x86/speculation: Warn about Spectre v2 LFENCE mitigation
    x86/speculation: Update link to AMD speculation whitepaper
    x86/speculation: Use generic retpoline by default on AMD
  * x86/speculation: Include unprivileged eBPF status in Spectre v2 mitigation reporting
      include/linux/bpf.h
      kernel/sysctl.c
    Documentation/hw-vuln: Update spectre doc
    x86/speculation: Add eIBRS + Retpoline options
    x86/speculation: Rename RETPOLINE_AMD to RETPOLINE_LFENCE
    x86,bugs: Unconditionally allow spectre_v2=retpoline,amd
    x86/speculation: Merge one test in spectre_v2_user_select_mitigation()
    Merge 4.19.233 into android-4.19-stable
  * FROMGIT: Revert "xfrm: state and policy should fail if XFRMA_IF_ID 0"
      net/xfrm/xfrm_user.c
  * Revert "ANDROID: incremental-fs: fix mount_fs issue"
      fs/incfs/vfs.c
Linux 4.19.233
    hamradio: fix macro redefine warning
    net: dcb: disable softirqs in dcbnl_flush_dev()
    btrfs: add missing run of delayed items after unlink during log replay
    tracing/histogram: Fix sorting on old "cpu" value
  * memfd: fix F_SEAL_WRITE after shmem huge page allocated
      mm/memfd.c
  * HID: add mapping for KEY_ALL_APPLICATIONS
      drivers/hid/hid-debug.c
      drivers/hid/hid-input.c
      include/uapi/linux/input-event-codes.h
    Input: elan_i2c - fix regulator enable count imbalance after suspend/resume
    Input: elan_i2c - move regulator_[en|dis]able() out of elan_[en|dis]able_power()
  * nl80211: Handle nla_memdup failures in handle_nan_filter
      net/wireless/nl80211.c
    net: chelsio: cxgb3: check the return value of pci_find_capability()
    soc: fsl: qe: Check of ioremap return value
    ibmvnic: free reset-work-item when flushing
    ARM: 9182/1: mmu: fix returns from early_param() and __setup() functions
    arm64: dts: rockchip: Switch RK3399-Gru DP to SPDIF output
    can: gs_usb: change active_channels's type from atomic_t to u8
    firmware: arm_scmi: Remove space in MODULE_ALIAS name
    efivars: Respect "block" flag in efivar_entry_set_safe()
    net: arcnet: com20020: Fix null-ptr-deref in com20020pci_probe()
    net: sxgbe: fix return value of __setup handler
    net: stmmac: fix return value of __setup handler
    mac80211: fix forwarded mesh frames AC & queue selection
    xen/netfront: destroy queues before real_num_tx_queues is zeroed
    PCI: pciehp: Fix infinite loop in IRQ handler upon power fault
  * block: Fix fsync always failed if once failed
      block/blk-flush.c
    net/smc: fix unexpected SMC_CLC_DECL_ERR_REGRMB error cause by server
    net/smc: fix unexpected SMC_CLC_DECL_ERR_REGRMB error generated by client
    net: dcb: flush lingering app table entries for unregistered devices
    batman-adv: Don't expect inter-netns unique iflink indices
    batman-adv: Request iflink once in batadv_get_real_netdevice
    batman-adv: Request iflink once in batadv-on-batadv check
  * netfilter: nf_queue: fix possible use-after-free
      include/net/netfilter/nf_queue.h
      net/netfilter/nf_queue.c
      net/netfilter/nfnetlink_queue.c
  * netfilter: nf_queue: don't assume sk is full socket
      net/netfilter/nf_queue.c
  * xfrm: enforce validity of offload input flags
      include/uapi/linux/xfrm.h
      net/xfrm/xfrm_device.c
  * xfrm: fix the if_id check in changelink
      net/xfrm/xfrm_interface.c
  * netfilter: fix use-after-free in __nf_register_net_hook()
      net/netfilter/core.c
  * xfrm: fix MTU regression
      net/ipv6/ip6_output.c
  * ASoC: ops: Shift tested values in snd_soc_put_volsw() by +min
      sound/soc/soc-ops.c
    ALSA: intel_hdmi: Fix reference to PCM buffer address
    ata: pata_hpt37x: fix PCI clock detection
    usb: gadget: clear related members when goto fail
    usb: gadget: don't release an existing dev->buf
    net: usb: cdc_mbim: avoid altsetting toggling for Telit FN990
  * i2c: qup: allow COMPILE_TEST
      drivers/i2c/busses/Kconfig
  * i2c: cadence: allow COMPILE_TEST
      drivers/i2c/busses/Kconfig
    dmaengine: shdma: Fix runtime PM imbalance on error
    cifs: fix double free race when mount fails in cifs_get_root()
  * Input: clear BTN_RIGHT/MIDDLE on buttonpads
      drivers/input/input.c
    ASoC: rt5682: do not block workqueue if card is unbound
    ASoC: rt5668: do not block workqueue if card is unbound
    i2c: bcm2835: Avoid clock stretching timeouts
    mac80211_hwsim: initialize ieee80211_tx_info at hw_scan_work
    mac80211_hwsim: report NOACK frames in tx_status
    UPSTREAM: mac80211_hwsim: initialize ieee80211_tx_info at hw_scan_work
    Merge 4.19.232 into android-4.19-stable
Linux 4.19.232
    tty: n_gsm: fix encoding of control signal octet bit DV
  * xhci: Prevent futile URB re-submissions due to incorrect return value.
      drivers/usb/host/xhci.c
  * xhci: re-initialize the HC during resume if HCE was set
      drivers/usb/host/xhci.c
  * usb: dwc3: gadget: Let the interrupt handler disable bottom halves.
      drivers/usb/dwc3/gadget.c
    usb: dwc3: pci: Fix Bay Trail phy GPIO mappings
    USB: serial: option: add Telit LE910R1 compositions
    USB: serial: option: add support for DW5829e
  * tracefs: Set the group ownership in apply_options() not parse_options()
      fs/tracefs/inode.c
    USB: gadget: validate endpoint index for xilinx udc
  * usb: gadget: rndis: add spinlock for rndis response list
      drivers/usb/gadget/function/rndis.c
      drivers/usb/gadget/function/rndis.h
    Revert "USB: serial: ch341: add new Product ID for CH341A"
    ata: pata_hpt37x: disable primary channel on HPT371
    iio: adc: men_z188_adc: Fix a resource leak in an error handling path
  * tracing: Have traceon and traceoff trigger honor the instance
      kernel/trace/trace_events_trigger.c
  * fget: clarify and improve __fget_files() implementation
      fs/file.c
  * memblock: use kfree() to release kmalloced memblock regions
      mm/memblock.c
    Revert "drm/nouveau/pmu/gm200-: avoid touching PMU outside of DEVINIT/PREOS/ACR"
    gpio: tegra186: Fix chip_data type confusion
    tty: n_gsm: fix proper link termination after failed open
    RDMA/ib_srp: Fix a deadlock
  * configfs: fix a race in configfs_{,un}register_subsystem()
      fs/configfs/dir.c
    net/mlx5e: Fix wrong return value on ioctl EEPROM query failure
  * drm/edid: Always set RGB444
      drivers/gpu/drm/drm_edid.c
  * openvswitch: Fix setting ipv6 fields causing hw csum failure
      include/net/checksum.h
  * gso: do not skip outer ip header in case of ipip and net_failover
      net/ipv4/af_inet.c
      net/ipv6/ip6_offload.c
  * tipc: Fix end of loop tests for list_for_each_entry()
      net/tipc/name_table.c
      net/tipc/socket.c
  * net: __pskb_pull_tail() & pskb_carve_frag_list() drop_monitor friends
      net/core/skbuff.c
  * ping: remove pr_err from ping_lookup
      net/ipv4/ping.c
  * USB: zaurus: support another broken Zaurus
      drivers/net/usb/cdc_ether.c
      drivers/net/usb/zaurus.c
    sr9700: sanity check for packet length
    parisc/unaligned: Fix ldw() and stw() unalignment handlers
    parisc/unaligned: Fix fldd and fstd unaligned handlers on 32-bit kernel
    vhost/vsock: don't check owner in vhost_vsock_stop() while releasing
  * cgroup/cpuset: Fix a race between cpuset_attach() and cpu hotplug
      kernel/cgroup/cpuset.c
    Merge 4.19.231 into android-4.19-stable
Linux 4.19.231
    net: macb: Align the dma and coherent dma masks
    net: usb: qmi_wwan: Add support for Dell DW5829e
  * tracing: Fix tp_printk option related with tp_printk_stop_on_boot
      kernel/trace/trace.c
    ata: libata-core: Disable TRIM on M88V29
  * kconfig: let 'shell' return enough output for deep path names
      scripts/kconfig/preprocess.c
    arm64: dts: meson-gx: add ATF BL32 reserved-memory region
  * netfilter: conntrack: don't refresh sctp entries in closed state
      net/netfilter/nf_conntrack_proto_sctp.c
    irqchip/sifive-plic: Add missing thead,c900-plic match string
    ARM: OMAP2+: hwmod: Add of_node_put() before break
    KVM: x86/pmu: Use AMD64_RAW_EVENT_MASK for PERF_TYPE_RAW
    Drivers: hv: vmbus: Fix memory leak in vmbus_add_channel_kobj
    Drivers: hv: vmbus: Expose monitor data only when monitor pages are used
    mtd: rawnand: brcmnand: Fixed incorrect sub-page ECC status
    mtd: rawnand: brcmnand: Refactored code to introduce helper functions
  * lib/iov_iter: initialize "flags" in new pipe_buffer
      lib/iov_iter.c
    i2c: brcmstb: fix support for DSL and CM variants
    dmaengine: sh: rcar-dmac: Check for error num after setting mask
  * net: sched: limit TC_ACT_REPEAT loops
      net/sched/act_api.c
  * EDAC: Fix calculation of returned address and next offset in edac_align_ptr()
      drivers/edac/edac_mc.c
    mtd: rawnand: qcom: Fix clock sequencing in qcom_nandc_probe()
    NFS: Do not report writeback errors in nfs_getattr()
    NFS: LOOKUP_DIRECTORY is also ok with symlinks
  * block/wbt: fix negative inflight counter when remove scsi device
      block/elevator.c
  * ext4: check for out-of-order index extents in ext4_valid_extent_entries()
      fs/ext4/extents.c
    powerpc/lib/sstep: fix 'ptesync' build error
  * ASoC: ops: Fix stereo change notifications in snd_soc_put_volsw_range()
      sound/soc/soc-ops.c
  * ASoC: ops: Fix stereo change notifications in snd_soc_put_volsw()
      sound/soc/soc-ops.c
    ALSA: hda: Fix missing codec probe on Shenker Dock 15
    ALSA: hda: Fix regression on forced probe mask option
    libsubcmd: Fix use-after-free for realloc(..., 0)
  * bonding: fix data-races around agg_select_timer
      drivers/net/bonding/bond_3ad.c
      include/net/bond_3ad.h
    drop_monitor: fix data-race in dropmon_net_event / trace_napi_poll_hit
  * ping: fix the dif and sdif check in ping_lookup
      net/ipv4/ping.c
    net: ieee802154: ca8210: Fix lifs/sifs periods
    net: dsa: lan9303: fix reset on probe
    iwlwifi: pcie: gen2: fix locking when "HW not ready"
    iwlwifi: pcie: fix locking when "HW not ready"
    vsock: remove vsock from connected table when connect is interrupted by a signal
    mmc: block: fix read single on recovery logic
  * taskstats: Cleanup the use of task->exit_code
      kernel/tsacct.c
  * xfrm: Don't accidentally set RTO_ONLINK in decode_session4()
      net/ipv4/xfrm4_policy.c
    drm/radeon: Fix backlight control on iMac 12,1
    iwlwifi: fix use-after-free
  * Revert "module, async: async_synchronize_full() on module init iff async is used"
      include/linux/sched.h
      kernel/async.c
      kernel/module.c
    nvme-rdma: fix possible use-after-free in transport error_recovery work
    nvme: fix a possible use-after-free in controller reset during load
  * quota: make dquot_quota_sync return errors from ->sync_fs
      fs/quota/dquot.c
  * vfs: make freeze_super abort when sync_filesystem returns error
      fs/super.c
    ax25: improve the incomplete fix to avoid UAF and NPD bugs
    selftests/zram: Adapt the situation that /dev/zram0 is being used
    selftests/zram01.sh: Fix compression ratio calculation
    selftests/zram: Skip max_comp_streams interface on newer kernel
    net: ieee802154: at86rf230: Stop leaking skb's
    btrfs: send: in case of IO error log it
    parisc: Fix sglist access in ccio-dma.c
    parisc: Fix data TLB miss in sba_unmap_sg
    serial: parisc: GSC: fix build when IOSAPIC is not set
  * net: usb: ax88179_178a: Fix out-of-bounds accesses in RX fixup
      drivers/net/usb/ax88179_178a.c
  * Makefile.extrawarn: Move -Wunaligned-access to W=1
      scripts/Makefile.extrawarn
    Merge 4.19.230 into android-4.19-stable
Linux 4.19.230
  * perf: Fix list corruption in perf_cgroup_switch()
      kernel/events/core.c
    hwmon: (dell-smm) Speed up setting of fan speed
  * seccomp: Invalidate seccomp mode to catch death failures
      kernel/seccomp.c
    USB: serial: cp210x: add CPI Bulk Coin Recycler id
    USB: serial: cp210x: add NCR Retail IO box id
    USB: serial: ch341: add support for GW Instek USB2.0-Serial devices
    USB: serial: option: add ZTE MF286D modem
    USB: serial: ftdi_sio: add support for Brainboxes US-159/235/320
  * usb: gadget: rndis: check size of RNDIS_MSG_SET command
      drivers/usb/gadget/function/rndis.c
  * USB: gadget: validate interface OS descriptor requests
      drivers/usb/gadget/composite.c
  * usb: dwc3: gadget: Prevent core from processing stale TRBs
      drivers/usb/dwc3/gadget.c
    usb: ulpi: Call of_node_put correctly
    usb: ulpi: Move of_node_put to ulpi_dev_release
  * n_tty: wake up poll(POLLRDNORM) on receiving data
      drivers/tty/n_tty.c
    vt_ioctl: add array_index_nospec to VT_ACTIVATE
    vt_ioctl: fix array_index_nospec in vt_setactivate
    net: amd-xgbe: disable interrupts during pci removal
  * tipc: rate limit warning for received illegal binding update
      net/tipc/name_distr.c
  * veth: fix races around rq->rx_notify_masked
      drivers/net/veth.c
  * net: fix a memleak when uncloning an skb dst and its metadata
      include/net/dst_metadata.h
  * net: do not keep the dst cache when uncloning an skb dst and its metadata
      include/net/dst_metadata.h
    ipmr,ip6mr: acquire RTNL before calling ip[6]mr_free_table() on failure path
  * bonding: pair enable_port with slave_arr_updates
      drivers/net/bonding/bond_3ad.c
    ixgbevf: Require large buffers for build_skb on 82599VF
  * usb: f_fs: Fix use-after-free for epfile
      drivers/usb/gadget/function/f_fs.c
    ARM: dts: imx6qdl-udoo: Properly describe the SD card detect
    staging: fbtft: Fix error path in fbtft_driver_module_init()
    ARM: dts: meson: Fix the UART compatible strings
    perf probe: Fix ppc64 'perf probe add events failed' case
  * net: bridge: fix stale eth hdr pointer in br_dev_xmit
      net/bridge/br_device.c
    ARM: dts: imx23-evk: Remove MX23_PAD_SSP1_DETECT from hog group
  * bpf: Add kconfig knob for disabling unpriv bpf by default
      init/Kconfig
      kernel/bpf/syscall.c
      kernel/sysctl.c
    net: stmmac: dwmac-sun8i: use return val of readl_poll_timeout()
    usb: dwc2: gadget: don't try to disable ep0 in dwc2_hsotg_suspend
    scsi: target: iscsi: Make sure the np under each tpg is unique
  * net: sched: Clarify error message when qdisc kind is unknown
      net/sched/sch_api.c
    NFSv4 expose nfs_parse_server_name function
    NFSv4 remove zero number of fs_locations entries error check
    NFSv4.1: Fix uninitialised variable in devicenotify
    nfs: nfs4clinet: check the return value of kstrdup()
    NFSv4 only print the label when its queried
    NFSD: Fix offset type in I/O trace points
    NFSD: Clamp WRITE offsets
    NFS: Fix initialisation of nfs_client cl_flags field
    net: phy: marvell: Fix MDI-x polarity setting in 88e1118-compatible PHYs
    mmc: sdhci-of-esdhc: Check for error num after setting mask
    ima: Allow template selection with ima_template[_fmt]= after ima_hash=
    ima: Remove ima_policy file before directory
  * integrity: check the return value of audit_log_start()
      security/integrity/integrity_audit.c
  * FROMGIT: f2fs: avoid EINVAL by SBI_NEED_FSCK when pinning a file
      fs/f2fs/data.c
      fs/f2fs/file.c
  * Revert "tracefs: Have tracefs directories not set OTH permission bits by default"
      fs/tracefs/inode.c
    ANDROID: GKI: Enable CONFIG_SERIAL_8250_RUNTIME_UARTS=0
    Merge 4.19.229 into android-4.19-stable
Linux 4.19.229
  * tipc: improve size validations for received domain records
      net/tipc/link.c
      net/tipc/monitor.c
    moxart: fix potential use-after-free on remove path
  * cgroup-v1: Require capabilities to set release_agent
      kernel/cgroup/cgroup-v1.c
    Merge 4.19.228 into android-4.19-stable
Linux 4.19.228
  * ext4: fix error handling in ext4_restore_inline_data()
      fs/ext4/inline.c
    EDAC/xgene: Fix deferred probing
    EDAC/altera: Fix deferred probing
    rtc: cmos: Evaluate century appropriate
    selftests: futex: Use variable MAKE instead of make
    nfsd: nfsd4_setclientid_confirm mistakenly expires confirmed client.
    scsi: bnx2fc: Make bnx2fc_recv_frame() mp safe
    ASoC: max9759: fix underflow in speaker_gain_control_put()
    ASoC: cpcap: Check for NULL pointer after calling of_get_child_by_name
    ASoC: fsl: Add missing error handling in pcm030_fabric_probe
    drm/i915/overlay: Prevent divide by zero bugs in scaling
    net: stmmac: ensure PTP time register reads are consistent
    net: macsec: Verify that send_sci is on when setting Tx sci explicitly
    net: ieee802154: Return meaningful error codes from the netlink helpers
    net: ieee802154: ca8210: Stop leaking skb's
    net: ieee802154: mcr20a: Fix lifs/sifs periods
    net: ieee802154: hwsim: Ensure proper channel selection at probe time
    spi: meson-spicc: add IRQ check in meson_spicc_probe
    spi: mediatek: Avoid NULL pointer crash in interrupt
    spi: bcm-qspi: check for valid cs before applying chip select
    iommu/amd: Fix loop timeout issue in iommu_ga_log_enable()
    iommu/vt-d: Fix potential memory leak in intel_setup_irq_remapping()
    RDMA/mlx4: Don't continue event handler after memory allocation failure
    Revert "ASoC: mediatek: Check for error clk pointer"
    block: bio-integrity: Advance seed correctly for larger interval sizes
    drm/nouveau: fix off by one in BIOS boundary checking
    ALSA: hda/realtek: Fix silent output on Gigabyte X570 Aorus Xtreme after reboot from Windows
    ALSA: hda/realtek: Fix silent output on Gigabyte X570S Aorus Master (newer chipset)
    ALSA: hda/realtek: Add missing fixup-model entry for Gigabyte X570 ALC1220 quirks
  * ASoC: ops: Reject out of bounds values in snd_soc_put_xr_sx()
      sound/soc/soc-ops.c
  * ASoC: ops: Reject out of bounds values in snd_soc_put_volsw_sx()
      sound/soc/soc-ops.c
  * ASoC: ops: Reject out of bounds values in snd_soc_put_volsw()
      sound/soc/soc-ops.c
  * audit: improve audit queue handling when "audit=1" on cmdline
      kernel/audit.c
  * af_packet: fix data-race in packet_setsockopt / packet_setsockopt
      net/packet/af_packet.c
  * rtnetlink: make sure to refresh master_dev/m_ops in __rtnl_newlink()
      net/core/rtnetlink.c
    net: amd-xgbe: Fix skb data length underflow
    net: amd-xgbe: ensure to reset the tx_timer_active flag
    ipheth: fix EOVERFLOW in ipheth_rcvbulk_callback
  * tcp: fix possible socket leaks in internal pacing mode
      net/ipv4/tcp_output.c
  * netfilter: nat: limit port clash resolution attempts
      net/netfilter/nf_nat_proto_common.c
  * netfilter: nat: remove l4 protocol port rovers
      include/net/netfilter/nf_nat_l4proto.h
      net/netfilter/nf_nat_proto_common.c
      net/netfilter/nf_nat_proto_dccp.c
      net/netfilter/nf_nat_proto_sctp.c
      net/netfilter/nf_nat_proto_tcp.c
      net/netfilter/nf_nat_proto_udp.c
  * ipv4: tcp: send zero IPID in SYNACK messages
      net/ipv4/ip_output.c
  * ipv4: raw: lock the socket in raw_bind()
      net/ipv4/raw.c
    yam: fix a memory leak in yam_siocdevprivate()
    ibmvnic: don't spin in tasklet
    ibmvnic: init ->running_cap_crqs early
  * phylib: fix potential use-after-free
      drivers/net/phy/phy_device.c
    NFS: Ensure the server has an up to date ctime before renaming
    NFS: Ensure the server has an up to date ctime before hardlinking
  * ipv6: annotate accesses to fn->fn_sernum
      include/net/ip6_fib.h
      net/ipv6/ip6_fib.c
      net/ipv6/route.c
    drm/msm/dsi: invalid parameter check in msm_dsi_phy_enable
    drm/msm: Fix wrong size calculation
  * net-procfs: show net devices bound packet types
      net/core/net-procfs.c
    NFSv4: nfs_atomic_open() can race when looking up a non-regular file
    NFSv4: Handle case where the lookup of a directory fails
    hwmon: (lm90) Reduce maximum conversion rate for G781
  * ipv4: avoid using shared IP generator for connected sockets
      include/net/ip.h
  * ping: fix the sk_bound_dev_if match in ping_lookup
      net/ipv4/ping.c
  * net: fix information leakage in /proc/net/ptype
      include/linux/netdevice.h
      net/core/net-procfs.c
      net/packet/af_packet.c
  * ipv6_tunnel: Rate limit warning messages
      net/ipv6/ip6_tunnel.c
    scsi: bnx2fc: Flush destroy_work queue before calling bnx2fc_interface_put()
  * rpmsg: char: Fix race between the release of rpmsg_eptdev and cdev
      drivers/rpmsg/rpmsg_char.c
  * rpmsg: char: Fix race between the release of rpmsg_ctrldev and cdev
      drivers/rpmsg/rpmsg_char.c
    i40e: fix unsigned stat widths
    i40e: Fix queues reservation for XDP
    i40e: Fix issue when maximum queues is exceeded
    i40e: Increase delay to 1 s after global EMP reset
    powerpc/32: Fix boot failure with GCC latent entropy plugin
    net: sfp: ignore disabled SFP node
    usb: typec: tcpm: Do not disconnect while receiving VBUS off
  * USB: core: Fix hang in usb_kill_urb by adding memory barriers
      drivers/usb/core/hcd.c
      drivers/usb/core/urb.c
    usb: gadget: f_sourcesink: Fix isoc transfer for USB_SPEED_SUPER_PLUS
    usb: common: ulpi: Fix crash in ulpi_match()
  * usb-storage: Add unusual-devs entry for VL817 USB-SATA bridge
      drivers/usb/storage/unusual_devs.h
    tty: Add support for Brainboxes UC cards.
    tty: n_gsm: fix SW flow control encoding/handling
    serial: stm32: fix software flow control transfer
    serial: 8250: of: Fix mapped region size when using reg-offset property
    netfilter: nft_payload: do not update layer 4 checksum when mangling fragments
    drm/etnaviv: relax submit size limits
  * PM: wakeup: simplify the output logic of pm_show_wakelocks()
      kernel/power/wakelock.c
    udf: Fix NULL ptr deref when converting from inline format
    udf: Restore i_lenAlloc when inode expansion fails
    scsi: zfcp: Fix failed recovery on gone remote port with non-NPIV FCP devices
    s390/hypfs: include z/VM guests with access control group set
  * Bluetooth: refactor malicious adv data check
      net/bluetooth/hci_event.c
    ANDROID: Increase x86 cmdline size to 4k
  * ANDROID: incremental-fs: remove index and incomplete dir on umount
      fs/incfs/vfs.c

Bug: 225082527
Change-Id: Ibc8397e8e00434b782bbd270dbbe7deaced953d5
Signed-off-by: Lucas Wei <lucaswei@google.com>
2022-04-01 11:38:46 +08:00

1909 lines
54 KiB
C

/*
* Procedures for maintaining information about logical memory blocks.
*
* Peter Bergner, IBM Corp. June 2001.
* Copyright (C) 2001 Peter Bergner.
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License
* as published by the Free Software Foundation; either version
* 2 of the License, or (at your option) any later version.
*/
#include <linux/kernel.h>
#include <linux/slab.h>
#include <linux/init.h>
#include <linux/bitops.h>
#include <linux/poison.h>
#include <linux/pfn.h>
#include <linux/debugfs.h>
#include <linux/kmemleak.h>
#include <linux/seq_file.h>
#include <linux/memblock.h>
#include <linux/bootmem.h>
#include <asm/sections.h>
#include <linux/io.h>
#include "internal.h"
/**
* DOC: memblock overview
*
* Memblock is a method of managing memory regions during the early
* boot period when the usual kernel memory allocators are not up and
* running.
*
* Memblock views the system memory as collections of contiguous
* regions. There are several types of these collections:
*
* * ``memory`` - describes the physical memory available to the
* kernel; this may differ from the actual physical memory installed
* in the system, for instance when the memory is restricted with
* ``mem=`` command line parameter
* * ``reserved`` - describes the regions that were allocated
* * ``physmap`` - describes the actual physical memory regardless of
* the possible restrictions; the ``physmap`` type is only available
* on some architectures.
*
* Each region is represented by :c:type:`struct memblock_region` that
* defines the region extents, its attributes and NUMA node id on NUMA
* systems. Every memory type is described by the :c:type:`struct
* memblock_type` which contains an array of memory regions along with
* the allocator metadata. The memory types are nicely wrapped with
* :c:type:`struct memblock`. This structure is statically initialzed
* at build time. The region arrays for the "memory" and "reserved"
* types are initially sized to %INIT_MEMBLOCK_REGIONS and for the
* "physmap" type to %INIT_PHYSMEM_REGIONS.
* The :c:func:`memblock_allow_resize` enables automatic resizing of
* the region arrays during addition of new regions. This feature
* should be used with care so that memory allocated for the region
* array will not overlap with areas that should be reserved, for
* example initrd.
*
* The early architecture setup should tell memblock what the physical
* memory layout is by using :c:func:`memblock_add` or
* :c:func:`memblock_add_node` functions. The first function does not
* assign the region to a NUMA node and it is appropriate for UMA
* systems. Yet, it is possible to use it on NUMA systems as well and
* assign the region to a NUMA node later in the setup process using
* :c:func:`memblock_set_node`. The :c:func:`memblock_add_node`
* performs such an assignment directly.
*
* Once memblock is setup the memory can be allocated using either
* memblock or bootmem APIs.
*
* As the system boot progresses, the architecture specific
* :c:func:`mem_init` function frees all the memory to the buddy page
* allocator.
*
* If an architecure enables %CONFIG_ARCH_DISCARD_MEMBLOCK, the
* memblock data structures will be discarded after the system
* initialization compltes.
*/
static struct memblock_region memblock_memory_init_regions[INIT_MEMBLOCK_REGIONS] __initdata_memblock;
static struct memblock_region memblock_reserved_init_regions[INIT_MEMBLOCK_REGIONS] __initdata_memblock;
#ifdef CONFIG_HAVE_MEMBLOCK_PHYS_MAP
static struct memblock_region memblock_physmem_init_regions[INIT_PHYSMEM_REGIONS] __initdata_memblock;
#endif
struct memblock memblock __initdata_memblock = {
.memory.regions = memblock_memory_init_regions,
.memory.cnt = 1, /* empty dummy entry */
.memory.max = INIT_MEMBLOCK_REGIONS,
.memory.name = "memory",
.reserved.regions = memblock_reserved_init_regions,
.reserved.cnt = 1, /* empty dummy entry */
.reserved.max = INIT_MEMBLOCK_REGIONS,
.reserved.name = "reserved",
#ifdef CONFIG_HAVE_MEMBLOCK_PHYS_MAP
.physmem.regions = memblock_physmem_init_regions,
.physmem.cnt = 1, /* empty dummy entry */
.physmem.max = INIT_PHYSMEM_REGIONS,
.physmem.name = "physmem",
#endif
.bottom_up = false,
.current_limit = MEMBLOCK_ALLOC_ANYWHERE,
};
int memblock_debug __initdata_memblock;
static bool system_has_some_mirror __initdata_memblock = false;
static int memblock_can_resize __initdata_memblock;
static int memblock_memory_in_slab __initdata_memblock = 0;
static int memblock_reserved_in_slab __initdata_memblock = 0;
enum memblock_flags __init_memblock choose_memblock_flags(void)
{
return system_has_some_mirror ? MEMBLOCK_MIRROR : MEMBLOCK_NONE;
}
/* adjust *@size so that (@base + *@size) doesn't overflow, return new size */
static inline phys_addr_t memblock_cap_size(phys_addr_t base, phys_addr_t *size)
{
return *size = min(*size, PHYS_ADDR_MAX - base);
}
/*
* Address comparison utilities
*/
static unsigned long __init_memblock memblock_addrs_overlap(phys_addr_t base1, phys_addr_t size1,
phys_addr_t base2, phys_addr_t size2)
{
return ((base1 < (base2 + size2)) && (base2 < (base1 + size1)));
}
bool __init_memblock memblock_overlaps_region(struct memblock_type *type,
phys_addr_t base, phys_addr_t size)
{
unsigned long i;
for (i = 0; i < type->cnt; i++)
if (memblock_addrs_overlap(base, size, type->regions[i].base,
type->regions[i].size))
break;
return i < type->cnt;
}
/**
* __memblock_find_range_bottom_up - find free area utility in bottom-up
* @start: start of candidate range
* @end: end of candidate range, can be %MEMBLOCK_ALLOC_ANYWHERE or
* %MEMBLOCK_ALLOC_ACCESSIBLE
* @size: size of free area to find
* @align: alignment of free area to find
* @nid: nid of the free area to find, %NUMA_NO_NODE for any node
* @flags: pick from blocks based on memory attributes
*
* Utility called from memblock_find_in_range_node(), find free area bottom-up.
*
* Return:
* Found address on success, 0 on failure.
*/
static phys_addr_t __init_memblock
__memblock_find_range_bottom_up(phys_addr_t start, phys_addr_t end,
phys_addr_t size, phys_addr_t align, int nid,
enum memblock_flags flags)
{
phys_addr_t this_start, this_end, cand;
u64 i;
for_each_free_mem_range(i, nid, flags, &this_start, &this_end, NULL) {
this_start = clamp(this_start, start, end);
this_end = clamp(this_end, start, end);
cand = round_up(this_start, align);
if (cand < this_end && this_end - cand >= size)
return cand;
}
return 0;
}
/**
* __memblock_find_range_top_down - find free area utility, in top-down
* @start: start of candidate range
* @end: end of candidate range, can be %MEMBLOCK_ALLOC_ANYWHERE or
* %MEMBLOCK_ALLOC_ACCESSIBLE
* @size: size of free area to find
* @align: alignment of free area to find
* @nid: nid of the free area to find, %NUMA_NO_NODE for any node
* @flags: pick from blocks based on memory attributes
*
* Utility called from memblock_find_in_range_node(), find free area top-down.
*
* Return:
* Found address on success, 0 on failure.
*/
static phys_addr_t __init_memblock
__memblock_find_range_top_down(phys_addr_t start, phys_addr_t end,
phys_addr_t size, phys_addr_t align, int nid,
enum memblock_flags flags)
{
phys_addr_t this_start, this_end, cand;
u64 i;
for_each_free_mem_range_reverse(i, nid, flags, &this_start, &this_end,
NULL) {
this_start = clamp(this_start, start, end);
this_end = clamp(this_end, start, end);
if (this_end < size)
continue;
cand = round_down(this_end - size, align);
if (cand >= this_start)
return cand;
}
return 0;
}
/**
* memblock_find_in_range_node - find free area in given range and node
* @size: size of free area to find
* @align: alignment of free area to find
* @start: start of candidate range
* @end: end of candidate range, can be %MEMBLOCK_ALLOC_ANYWHERE or
* %MEMBLOCK_ALLOC_ACCESSIBLE
* @nid: nid of the free area to find, %NUMA_NO_NODE for any node
* @flags: pick from blocks based on memory attributes
*
* Find @size free area aligned to @align in the specified range and node.
*
* Return:
* Found address on success, 0 on failure.
*/
phys_addr_t __init_memblock memblock_find_in_range_node(phys_addr_t size,
phys_addr_t align, phys_addr_t start,
phys_addr_t end, int nid,
enum memblock_flags flags)
{
/* pump up @end */
if (end == MEMBLOCK_ALLOC_ACCESSIBLE ||
end == MEMBLOCK_ALLOC_KASAN)
end = memblock.current_limit;
/* avoid allocating the first page */
start = max_t(phys_addr_t, start, PAGE_SIZE);
end = max(start, end);
if (memblock_bottom_up())
return __memblock_find_range_bottom_up(start, end, size, align,
nid, flags);
else
return __memblock_find_range_top_down(start, end, size, align,
nid, flags);
}
/**
* memblock_find_in_range - find free area in given range
* @start: start of candidate range
* @end: end of candidate range, can be %MEMBLOCK_ALLOC_ANYWHERE or
* %MEMBLOCK_ALLOC_ACCESSIBLE
* @size: size of free area to find
* @align: alignment of free area to find
*
* Find @size free area aligned to @align in the specified range.
*
* Return:
* Found address on success, 0 on failure.
*/
phys_addr_t __init_memblock memblock_find_in_range(phys_addr_t start,
phys_addr_t end, phys_addr_t size,
phys_addr_t align)
{
phys_addr_t ret;
enum memblock_flags flags = choose_memblock_flags();
again:
ret = memblock_find_in_range_node(size, align, start, end,
NUMA_NO_NODE, flags);
if (!ret && (flags & MEMBLOCK_MIRROR)) {
pr_warn("Could not allocate %pap bytes of mirrored memory\n",
&size);
flags &= ~MEMBLOCK_MIRROR;
goto again;
}
return ret;
}
static void __init_memblock memblock_remove_region(struct memblock_type *type, unsigned long r)
{
type->total_size -= type->regions[r].size;
memmove(&type->regions[r], &type->regions[r + 1],
(type->cnt - (r + 1)) * sizeof(type->regions[r]));
type->cnt--;
/* Special case for empty arrays */
if (type->cnt == 0) {
WARN_ON(type->total_size != 0);
type->cnt = 1;
type->regions[0].base = 0;
type->regions[0].size = 0;
type->regions[0].flags = 0;
memblock_set_region_node(&type->regions[0], MAX_NUMNODES);
}
}
#ifdef CONFIG_ARCH_DISCARD_MEMBLOCK
/**
* memblock_discard - discard memory and reserved arrays if they were allocated
*/
void __init memblock_discard(void)
{
phys_addr_t addr, size;
if (memblock.reserved.regions != memblock_reserved_init_regions) {
addr = __pa(memblock.reserved.regions);
size = PAGE_ALIGN(sizeof(struct memblock_region) *
memblock.reserved.max);
if (memblock_reserved_in_slab)
kfree(memblock.reserved.regions);
else
__memblock_free_late(addr, size);
}
if (memblock.memory.regions != memblock_memory_init_regions) {
addr = __pa(memblock.memory.regions);
size = PAGE_ALIGN(sizeof(struct memblock_region) *
memblock.memory.max);
if (memblock_memory_in_slab)
kfree(memblock.memory.regions);
else
__memblock_free_late(addr, size);
}
}
#endif
/**
* memblock_double_array - double the size of the memblock regions array
* @type: memblock type of the regions array being doubled
* @new_area_start: starting address of memory range to avoid overlap with
* @new_area_size: size of memory range to avoid overlap with
*
* Double the size of the @type regions array. If memblock is being used to
* allocate memory for a new reserved regions array and there is a previously
* allocated memory range [@new_area_start, @new_area_start + @new_area_size]
* waiting to be reserved, ensure the memory used by the new array does
* not overlap.
*
* Return:
* 0 on success, -1 on failure.
*/
static int __init_memblock memblock_double_array(struct memblock_type *type,
phys_addr_t new_area_start,
phys_addr_t new_area_size)
{
struct memblock_region *new_array, *old_array;
phys_addr_t old_alloc_size, new_alloc_size;
phys_addr_t old_size, new_size, addr, new_end;
int use_slab = slab_is_available();
int *in_slab;
/* We don't allow resizing until we know about the reserved regions
* of memory that aren't suitable for allocation
*/
if (!memblock_can_resize)
return -1;
/* Calculate new doubled size */
old_size = type->max * sizeof(struct memblock_region);
new_size = old_size << 1;
/*
* We need to allocated new one align to PAGE_SIZE,
* so we can free them completely later.
*/
old_alloc_size = PAGE_ALIGN(old_size);
new_alloc_size = PAGE_ALIGN(new_size);
/* Retrieve the slab flag */
if (type == &memblock.memory)
in_slab = &memblock_memory_in_slab;
else
in_slab = &memblock_reserved_in_slab;
/* Try to find some space for it.
*
* WARNING: We assume that either slab_is_available() and we use it or
* we use MEMBLOCK for allocations. That means that this is unsafe to
* use when bootmem is currently active (unless bootmem itself is
* implemented on top of MEMBLOCK which isn't the case yet)
*
* This should however not be an issue for now, as we currently only
* call into MEMBLOCK while it's still active, or much later when slab
* is active for memory hotplug operations
*/
if (use_slab) {
new_array = kmalloc(new_size, GFP_KERNEL);
addr = new_array ? __pa(new_array) : 0;
} else {
/* only exclude range when trying to double reserved.regions */
if (type != &memblock.reserved)
new_area_start = new_area_size = 0;
addr = memblock_find_in_range(new_area_start + new_area_size,
memblock.current_limit,
new_alloc_size, PAGE_SIZE);
if (!addr && new_area_size)
addr = memblock_find_in_range(0,
min(new_area_start, memblock.current_limit),
new_alloc_size, PAGE_SIZE);
new_array = addr ? __va(addr) : NULL;
}
if (!addr) {
pr_err("memblock: Failed to double %s array from %ld to %ld entries !\n",
type->name, type->max, type->max * 2);
return -1;
}
new_end = addr + new_size - 1;
memblock_dbg("memblock: %s is doubled to %ld at [%pa-%pa]",
type->name, type->max * 2, &addr, &new_end);
/*
* Found space, we now need to move the array over before we add the
* reserved region since it may be our reserved array itself that is
* full.
*/
memcpy(new_array, type->regions, old_size);
memset(new_array + type->max, 0, old_size);
old_array = type->regions;
type->regions = new_array;
type->max <<= 1;
/* Free old array. We needn't free it if the array is the static one */
if (*in_slab)
kfree(old_array);
else if (old_array != memblock_memory_init_regions &&
old_array != memblock_reserved_init_regions)
memblock_free(__pa(old_array), old_alloc_size);
/*
* Reserve the new array if that comes from the memblock. Otherwise, we
* needn't do it
*/
if (!use_slab)
BUG_ON(memblock_reserve(addr, new_alloc_size));
/* Update slab flag */
*in_slab = use_slab;
return 0;
}
/**
* memblock_merge_regions - merge neighboring compatible regions
* @type: memblock type to scan
*
* Scan @type and merge neighboring compatible regions.
*/
static void __init_memblock memblock_merge_regions(struct memblock_type *type)
{
int i = 0;
/* cnt never goes below 1 */
while (i < type->cnt - 1) {
struct memblock_region *this = &type->regions[i];
struct memblock_region *next = &type->regions[i + 1];
if (this->base + this->size != next->base ||
memblock_get_region_node(this) !=
memblock_get_region_node(next) ||
this->flags != next->flags) {
BUG_ON(this->base + this->size > next->base);
i++;
continue;
}
this->size += next->size;
/* move forward from next + 1, index of which is i + 2 */
memmove(next, next + 1, (type->cnt - (i + 2)) * sizeof(*next));
type->cnt--;
}
}
/**
* memblock_insert_region - insert new memblock region
* @type: memblock type to insert into
* @idx: index for the insertion point
* @base: base address of the new region
* @size: size of the new region
* @nid: node id of the new region
* @flags: flags of the new region
*
* Insert new memblock region [@base, @base + @size) into @type at @idx.
* @type must already have extra room to accommodate the new region.
*/
static void __init_memblock memblock_insert_region(struct memblock_type *type,
int idx, phys_addr_t base,
phys_addr_t size,
int nid,
enum memblock_flags flags)
{
struct memblock_region *rgn = &type->regions[idx];
BUG_ON(type->cnt >= type->max);
memmove(rgn + 1, rgn, (type->cnt - idx) * sizeof(*rgn));
rgn->base = base;
rgn->size = size;
rgn->flags = flags;
memblock_set_region_node(rgn, nid);
type->cnt++;
type->total_size += size;
}
/**
* memblock_add_range - add new memblock region
* @type: memblock type to add new region into
* @base: base address of the new region
* @size: size of the new region
* @nid: nid of the new region
* @flags: flags of the new region
*
* Add new memblock region [@base, @base + @size) into @type. The new region
* is allowed to overlap with existing ones - overlaps don't affect already
* existing regions. @type is guaranteed to be minimal (all neighbouring
* compatible regions are merged) after the addition.
*
* Return:
* 0 on success, -errno on failure.
*/
int __init_memblock memblock_add_range(struct memblock_type *type,
phys_addr_t base, phys_addr_t size,
int nid, enum memblock_flags flags)
{
bool insert = false;
phys_addr_t obase = base;
phys_addr_t end = base + memblock_cap_size(base, &size);
int idx, nr_new;
struct memblock_region *rgn;
if (!size)
return 0;
/* special case for empty array */
if (type->regions[0].size == 0) {
WARN_ON(type->cnt != 1 || type->total_size);
type->regions[0].base = base;
type->regions[0].size = size;
type->regions[0].flags = flags;
memblock_set_region_node(&type->regions[0], nid);
type->total_size = size;
return 0;
}
repeat:
/*
* The following is executed twice. Once with %false @insert and
* then with %true. The first counts the number of regions needed
* to accommodate the new area. The second actually inserts them.
*/
base = obase;
nr_new = 0;
for_each_memblock_type(idx, type, rgn) {
phys_addr_t rbase = rgn->base;
phys_addr_t rend = rbase + rgn->size;
if (rbase >= end)
break;
if (rend <= base)
continue;
/*
* @rgn overlaps. If it separates the lower part of new
* area, insert that portion.
*/
if (rbase > base) {
#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
WARN_ON(nid != memblock_get_region_node(rgn));
#endif
WARN_ON(flags != rgn->flags);
nr_new++;
if (insert)
memblock_insert_region(type, idx++, base,
rbase - base, nid,
flags);
}
/* area below @rend is dealt with, forget about it */
base = min(rend, end);
}
/* insert the remaining portion */
if (base < end) {
nr_new++;
if (insert)
memblock_insert_region(type, idx, base, end - base,
nid, flags);
}
if (!nr_new)
return 0;
/*
* If this was the first round, resize array and repeat for actual
* insertions; otherwise, merge and return.
*/
if (!insert) {
while (type->cnt + nr_new > type->max)
if (memblock_double_array(type, obase, size) < 0)
return -ENOMEM;
insert = true;
goto repeat;
} else {
memblock_merge_regions(type);
return 0;
}
}
/**
* memblock_add_node - add new memblock region within a NUMA node
* @base: base address of the new region
* @size: size of the new region
* @nid: nid of the new region
*
* Add new memblock region [@base, @base + @size) to the "memory"
* type. See memblock_add_range() description for mode details
*
* Return:
* 0 on success, -errno on failure.
*/
int __init_memblock memblock_add_node(phys_addr_t base, phys_addr_t size,
int nid)
{
return memblock_add_range(&memblock.memory, base, size, nid, 0);
}
/**
* memblock_add - add new memblock region
* @base: base address of the new region
* @size: size of the new region
*
* Add new memblock region [@base, @base + @size) to the "memory"
* type. See memblock_add_range() description for mode details
*
* Return:
* 0 on success, -errno on failure.
*/
int __init_memblock memblock_add(phys_addr_t base, phys_addr_t size)
{
phys_addr_t end = base + size - 1;
memblock_dbg("memblock_add: [%pa-%pa] %pF\n",
&base, &end, (void *)_RET_IP_);
return memblock_add_range(&memblock.memory, base, size, MAX_NUMNODES, 0);
}
/**
* memblock_isolate_range - isolate given range into disjoint memblocks
* @type: memblock type to isolate range for
* @base: base of range to isolate
* @size: size of range to isolate
* @start_rgn: out parameter for the start of isolated region
* @end_rgn: out parameter for the end of isolated region
*
* Walk @type and ensure that regions don't cross the boundaries defined by
* [@base, @base + @size). Crossing regions are split at the boundaries,
* which may create at most two more regions. The index of the first
* region inside the range is returned in *@start_rgn and end in *@end_rgn.
*
* Return:
* 0 on success, -errno on failure.
*/
static int __init_memblock memblock_isolate_range(struct memblock_type *type,
phys_addr_t base, phys_addr_t size,
int *start_rgn, int *end_rgn)
{
phys_addr_t end = base + memblock_cap_size(base, &size);
int idx;
struct memblock_region *rgn;
*start_rgn = *end_rgn = 0;
if (!size)
return 0;
/* we'll create at most two more regions */
while (type->cnt + 2 > type->max)
if (memblock_double_array(type, base, size) < 0)
return -ENOMEM;
for_each_memblock_type(idx, type, rgn) {
phys_addr_t rbase = rgn->base;
phys_addr_t rend = rbase + rgn->size;
if (rbase >= end)
break;
if (rend <= base)
continue;
if (rbase < base) {
/*
* @rgn intersects from below. Split and continue
* to process the next region - the new top half.
*/
rgn->base = base;
rgn->size -= base - rbase;
type->total_size -= base - rbase;
memblock_insert_region(type, idx, rbase, base - rbase,
memblock_get_region_node(rgn),
rgn->flags);
} else if (rend > end) {
/*
* @rgn intersects from above. Split and redo the
* current region - the new bottom half.
*/
rgn->base = end;
rgn->size -= end - rbase;
type->total_size -= end - rbase;
memblock_insert_region(type, idx--, rbase, end - rbase,
memblock_get_region_node(rgn),
rgn->flags);
} else {
/* @rgn is fully contained, record it */
if (!*end_rgn)
*start_rgn = idx;
*end_rgn = idx + 1;
}
}
return 0;
}
static int __init_memblock memblock_remove_range(struct memblock_type *type,
phys_addr_t base, phys_addr_t size)
{
int start_rgn, end_rgn;
int i, ret;
ret = memblock_isolate_range(type, base, size, &start_rgn, &end_rgn);
if (ret)
return ret;
for (i = end_rgn - 1; i >= start_rgn; i--)
memblock_remove_region(type, i);
return 0;
}
int __init_memblock memblock_remove(phys_addr_t base, phys_addr_t size)
{
phys_addr_t end = base + size - 1;
memblock_dbg("memblock_remove: [%pa-%pa] %pS\n",
&base, &end, (void *)_RET_IP_);
return memblock_remove_range(&memblock.memory, base, size);
}
int __init_memblock memblock_free(phys_addr_t base, phys_addr_t size)
{
phys_addr_t end = base + size - 1;
memblock_dbg(" memblock_free: [%pa-%pa] %pF\n",
&base, &end, (void *)_RET_IP_);
if (base < memblock.current_limit)
kmemleak_free_part(__va(base), size);
return memblock_remove_range(&memblock.reserved, base, size);
}
EXPORT_SYMBOL_GPL(memblock_free);
int __init_memblock memblock_reserve(phys_addr_t base, phys_addr_t size)
{
phys_addr_t end = base + size - 1;
memblock_dbg("memblock_reserve: [%pa-%pa] %pF\n",
&base, &end, (void *)_RET_IP_);
return memblock_add_range(&memblock.reserved, base, size, MAX_NUMNODES, 0);
}
/**
* memblock_setclr_flag - set or clear flag for a memory region
* @base: base address of the region
* @size: size of the region
* @set: set or clear the flag
* @flag: the flag to udpate
*
* This function isolates region [@base, @base + @size), and sets/clears flag
*
* Return: 0 on success, -errno on failure.
*/
static int __init_memblock memblock_setclr_flag(phys_addr_t base,
phys_addr_t size, int set, int flag)
{
struct memblock_type *type = &memblock.memory;
int i, ret, start_rgn, end_rgn;
ret = memblock_isolate_range(type, base, size, &start_rgn, &end_rgn);
if (ret)
return ret;
for (i = start_rgn; i < end_rgn; i++)
if (set)
memblock_set_region_flags(&type->regions[i], flag);
else
memblock_clear_region_flags(&type->regions[i], flag);
memblock_merge_regions(type);
return 0;
}
/**
* memblock_mark_hotplug - Mark hotpluggable memory with flag MEMBLOCK_HOTPLUG.
* @base: the base phys addr of the region
* @size: the size of the region
*
* Return: 0 on success, -errno on failure.
*/
int __init_memblock memblock_mark_hotplug(phys_addr_t base, phys_addr_t size)
{
return memblock_setclr_flag(base, size, 1, MEMBLOCK_HOTPLUG);
}
/**
* memblock_clear_hotplug - Clear flag MEMBLOCK_HOTPLUG for a specified region.
* @base: the base phys addr of the region
* @size: the size of the region
*
* Return: 0 on success, -errno on failure.
*/
int __init_memblock memblock_clear_hotplug(phys_addr_t base, phys_addr_t size)
{
return memblock_setclr_flag(base, size, 0, MEMBLOCK_HOTPLUG);
}
/**
* memblock_mark_mirror - Mark mirrored memory with flag MEMBLOCK_MIRROR.
* @base: the base phys addr of the region
* @size: the size of the region
*
* Return: 0 on success, -errno on failure.
*/
int __init_memblock memblock_mark_mirror(phys_addr_t base, phys_addr_t size)
{
system_has_some_mirror = true;
return memblock_setclr_flag(base, size, 1, MEMBLOCK_MIRROR);
}
/**
* memblock_mark_nomap - Mark a memory region with flag MEMBLOCK_NOMAP.
* @base: the base phys addr of the region
* @size: the size of the region
*
* Return: 0 on success, -errno on failure.
*/
int __init_memblock memblock_mark_nomap(phys_addr_t base, phys_addr_t size)
{
return memblock_setclr_flag(base, size, 1, MEMBLOCK_NOMAP);
}
/**
* memblock_clear_nomap - Clear flag MEMBLOCK_NOMAP for a specified region.
* @base: the base phys addr of the region
* @size: the size of the region
*
* Return: 0 on success, -errno on failure.
*/
int __init_memblock memblock_clear_nomap(phys_addr_t base, phys_addr_t size)
{
return memblock_setclr_flag(base, size, 0, MEMBLOCK_NOMAP);
}
/**
* __next_reserved_mem_region - next function for for_each_reserved_region()
* @idx: pointer to u64 loop variable
* @out_start: ptr to phys_addr_t for start address of the region, can be %NULL
* @out_end: ptr to phys_addr_t for end address of the region, can be %NULL
*
* Iterate over all reserved memory regions.
*/
void __init_memblock __next_reserved_mem_region(u64 *idx,
phys_addr_t *out_start,
phys_addr_t *out_end)
{
struct memblock_type *type = &memblock.reserved;
if (*idx < type->cnt) {
struct memblock_region *r = &type->regions[*idx];
phys_addr_t base = r->base;
phys_addr_t size = r->size;
if (out_start)
*out_start = base;
if (out_end)
*out_end = base + size - 1;
*idx += 1;
return;
}
/* signal end of iteration */
*idx = ULLONG_MAX;
}
/**
* __next__mem_range - next function for for_each_free_mem_range() etc.
* @idx: pointer to u64 loop variable
* @nid: node selector, %NUMA_NO_NODE for all nodes
* @flags: pick from blocks based on memory attributes
* @type_a: pointer to memblock_type from where the range is taken
* @type_b: pointer to memblock_type which excludes memory from being taken
* @out_start: ptr to phys_addr_t for start address of the range, can be %NULL
* @out_end: ptr to phys_addr_t for end address of the range, can be %NULL
* @out_nid: ptr to int for nid of the range, can be %NULL
*
* Find the first area from *@idx which matches @nid, fill the out
* parameters, and update *@idx for the next iteration. The lower 32bit of
* *@idx contains index into type_a and the upper 32bit indexes the
* areas before each region in type_b. For example, if type_b regions
* look like the following,
*
* 0:[0-16), 1:[32-48), 2:[128-130)
*
* The upper 32bit indexes the following regions.
*
* 0:[0-0), 1:[16-32), 2:[48-128), 3:[130-MAX)
*
* As both region arrays are sorted, the function advances the two indices
* in lockstep and returns each intersection.
*/
void __init_memblock __next_mem_range(u64 *idx, int nid,
enum memblock_flags flags,
struct memblock_type *type_a,
struct memblock_type *type_b,
phys_addr_t *out_start,
phys_addr_t *out_end, int *out_nid)
{
int idx_a = *idx & 0xffffffff;
int idx_b = *idx >> 32;
if (WARN_ONCE(nid == MAX_NUMNODES,
"Usage of MAX_NUMNODES is deprecated. Use NUMA_NO_NODE instead\n"))
nid = NUMA_NO_NODE;
for (; idx_a < type_a->cnt; idx_a++) {
struct memblock_region *m = &type_a->regions[idx_a];
phys_addr_t m_start = m->base;
phys_addr_t m_end = m->base + m->size;
int m_nid = memblock_get_region_node(m);
/* only memory regions are associated with nodes, check it */
if (nid != NUMA_NO_NODE && nid != m_nid)
continue;
/* skip hotpluggable memory regions if needed */
if (movable_node_is_enabled() && memblock_is_hotpluggable(m))
continue;
/* if we want mirror memory skip non-mirror memory regions */
if ((flags & MEMBLOCK_MIRROR) && !memblock_is_mirror(m))
continue;
/* skip nomap memory unless we were asked for it explicitly */
if (!(flags & MEMBLOCK_NOMAP) && memblock_is_nomap(m))
continue;
if (!type_b) {
if (out_start)
*out_start = m_start;
if (out_end)
*out_end = m_end;
if (out_nid)
*out_nid = m_nid;
idx_a++;
*idx = (u32)idx_a | (u64)idx_b << 32;
return;
}
/* scan areas before each reservation */
for (; idx_b < type_b->cnt + 1; idx_b++) {
struct memblock_region *r;
phys_addr_t r_start;
phys_addr_t r_end;
r = &type_b->regions[idx_b];
r_start = idx_b ? r[-1].base + r[-1].size : 0;
r_end = idx_b < type_b->cnt ?
r->base : PHYS_ADDR_MAX;
/*
* if idx_b advanced past idx_a,
* break out to advance idx_a
*/
if (r_start >= m_end)
break;
/* if the two regions intersect, we're done */
if (m_start < r_end) {
if (out_start)
*out_start =
max(m_start, r_start);
if (out_end)
*out_end = min(m_end, r_end);
if (out_nid)
*out_nid = m_nid;
/*
* The region which ends first is
* advanced for the next iteration.
*/
if (m_end <= r_end)
idx_a++;
else
idx_b++;
*idx = (u32)idx_a | (u64)idx_b << 32;
return;
}
}
}
/* signal end of iteration */
*idx = ULLONG_MAX;
}
/**
* __next_mem_range_rev - generic next function for for_each_*_range_rev()
*
* @idx: pointer to u64 loop variable
* @nid: node selector, %NUMA_NO_NODE for all nodes
* @flags: pick from blocks based on memory attributes
* @type_a: pointer to memblock_type from where the range is taken
* @type_b: pointer to memblock_type which excludes memory from being taken
* @out_start: ptr to phys_addr_t for start address of the range, can be %NULL
* @out_end: ptr to phys_addr_t for end address of the range, can be %NULL
* @out_nid: ptr to int for nid of the range, can be %NULL
*
* Finds the next range from type_a which is not marked as unsuitable
* in type_b.
*
* Reverse of __next_mem_range().
*/
void __init_memblock __next_mem_range_rev(u64 *idx, int nid,
enum memblock_flags flags,
struct memblock_type *type_a,
struct memblock_type *type_b,
phys_addr_t *out_start,
phys_addr_t *out_end, int *out_nid)
{
int idx_a = *idx & 0xffffffff;
int idx_b = *idx >> 32;
if (WARN_ONCE(nid == MAX_NUMNODES, "Usage of MAX_NUMNODES is deprecated. Use NUMA_NO_NODE instead\n"))
nid = NUMA_NO_NODE;
if (*idx == (u64)ULLONG_MAX) {
idx_a = type_a->cnt - 1;
if (type_b != NULL)
idx_b = type_b->cnt;
else
idx_b = 0;
}
for (; idx_a >= 0; idx_a--) {
struct memblock_region *m = &type_a->regions[idx_a];
phys_addr_t m_start = m->base;
phys_addr_t m_end = m->base + m->size;
int m_nid = memblock_get_region_node(m);
/* only memory regions are associated with nodes, check it */
if (nid != NUMA_NO_NODE && nid != m_nid)
continue;
/* skip hotpluggable memory regions if needed */
if (movable_node_is_enabled() && memblock_is_hotpluggable(m))
continue;
/* if we want mirror memory skip non-mirror memory regions */
if ((flags & MEMBLOCK_MIRROR) && !memblock_is_mirror(m))
continue;
/* skip nomap memory unless we were asked for it explicitly */
if (!(flags & MEMBLOCK_NOMAP) && memblock_is_nomap(m))
continue;
if (!type_b) {
if (out_start)
*out_start = m_start;
if (out_end)
*out_end = m_end;
if (out_nid)
*out_nid = m_nid;
idx_a--;
*idx = (u32)idx_a | (u64)idx_b << 32;
return;
}
/* scan areas before each reservation */
for (; idx_b >= 0; idx_b--) {
struct memblock_region *r;
phys_addr_t r_start;
phys_addr_t r_end;
r = &type_b->regions[idx_b];
r_start = idx_b ? r[-1].base + r[-1].size : 0;
r_end = idx_b < type_b->cnt ?
r->base : PHYS_ADDR_MAX;
/*
* if idx_b advanced past idx_a,
* break out to advance idx_a
*/
if (r_end <= m_start)
break;
/* if the two regions intersect, we're done */
if (m_end > r_start) {
if (out_start)
*out_start = max(m_start, r_start);
if (out_end)
*out_end = min(m_end, r_end);
if (out_nid)
*out_nid = m_nid;
if (m_start >= r_start)
idx_a--;
else
idx_b--;
*idx = (u32)idx_a | (u64)idx_b << 32;
return;
}
}
}
/* signal end of iteration */
*idx = ULLONG_MAX;
}
#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
/*
* Common iterator interface used to define for_each_mem_range().
*/
void __init_memblock __next_mem_pfn_range(int *idx, int nid,
unsigned long *out_start_pfn,
unsigned long *out_end_pfn, int *out_nid)
{
struct memblock_type *type = &memblock.memory;
struct memblock_region *r;
while (++*idx < type->cnt) {
r = &type->regions[*idx];
if (PFN_UP(r->base) >= PFN_DOWN(r->base + r->size))
continue;
if (nid == MAX_NUMNODES || nid == r->nid)
break;
}
if (*idx >= type->cnt) {
*idx = -1;
return;
}
if (out_start_pfn)
*out_start_pfn = PFN_UP(r->base);
if (out_end_pfn)
*out_end_pfn = PFN_DOWN(r->base + r->size);
if (out_nid)
*out_nid = r->nid;
}
/**
* memblock_set_node - set node ID on memblock regions
* @base: base of area to set node ID for
* @size: size of area to set node ID for
* @type: memblock type to set node ID for
* @nid: node ID to set
*
* Set the nid of memblock @type regions in [@base, @base + @size) to @nid.
* Regions which cross the area boundaries are split as necessary.
*
* Return:
* 0 on success, -errno on failure.
*/
int __init_memblock memblock_set_node(phys_addr_t base, phys_addr_t size,
struct memblock_type *type, int nid)
{
int start_rgn, end_rgn;
int i, ret;
ret = memblock_isolate_range(type, base, size, &start_rgn, &end_rgn);
if (ret)
return ret;
for (i = start_rgn; i < end_rgn; i++)
memblock_set_region_node(&type->regions[i], nid);
memblock_merge_regions(type);
return 0;
}
#endif /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */
static phys_addr_t __init memblock_alloc_range_nid(phys_addr_t size,
phys_addr_t align, phys_addr_t start,
phys_addr_t end, int nid,
enum memblock_flags flags)
{
phys_addr_t found;
if (!align)
align = SMP_CACHE_BYTES;
found = memblock_find_in_range_node(size, align, start, end, nid,
flags);
if (found && !memblock_reserve(found, size)) {
/*
* The min_count is set to 0 so that memblock allocations are
* never reported as leaks.
*/
if (found < memblock.current_limit)
kmemleak_alloc(__va(found), size, 0, 0);
return found;
}
return 0;
}
phys_addr_t __init memblock_alloc_range(phys_addr_t size, phys_addr_t align,
phys_addr_t start, phys_addr_t end,
enum memblock_flags flags)
{
return memblock_alloc_range_nid(size, align, start, end, NUMA_NO_NODE,
flags);
}
phys_addr_t __init memblock_alloc_base_nid(phys_addr_t size,
phys_addr_t align, phys_addr_t max_addr,
int nid, enum memblock_flags flags)
{
return memblock_alloc_range_nid(size, align, 0, max_addr, nid, flags);
}
phys_addr_t __init memblock_alloc_nid(phys_addr_t size, phys_addr_t align, int nid)
{
enum memblock_flags flags = choose_memblock_flags();
phys_addr_t ret;
again:
ret = memblock_alloc_base_nid(size, align, MEMBLOCK_ALLOC_ACCESSIBLE,
nid, flags);
if (!ret && (flags & MEMBLOCK_MIRROR)) {
flags &= ~MEMBLOCK_MIRROR;
goto again;
}
return ret;
}
phys_addr_t __init __memblock_alloc_base(phys_addr_t size, phys_addr_t align, phys_addr_t max_addr)
{
return memblock_alloc_base_nid(size, align, max_addr, NUMA_NO_NODE,
MEMBLOCK_NONE);
}
phys_addr_t __init memblock_alloc_base(phys_addr_t size, phys_addr_t align, phys_addr_t max_addr)
{
phys_addr_t alloc;
alloc = __memblock_alloc_base(size, align, max_addr);
if (alloc == 0)
panic("ERROR: Failed to allocate %pa bytes below %pa.\n",
&size, &max_addr);
return alloc;
}
phys_addr_t __init memblock_alloc(phys_addr_t size, phys_addr_t align)
{
return memblock_alloc_base(size, align, MEMBLOCK_ALLOC_ACCESSIBLE);
}
phys_addr_t __init memblock_alloc_try_nid(phys_addr_t size, phys_addr_t align, int nid)
{
phys_addr_t res = memblock_alloc_nid(size, align, nid);
if (res)
return res;
return memblock_alloc_base(size, align, MEMBLOCK_ALLOC_ACCESSIBLE);
}
#if defined(CONFIG_NO_BOOTMEM)
/**
* memblock_virt_alloc_internal - allocate boot memory block
* @size: size of memory block to be allocated in bytes
* @align: alignment of the region and block's size
* @min_addr: the lower bound of the memory region to allocate (phys address)
* @max_addr: the upper bound of the memory region to allocate (phys address)
* @nid: nid of the free area to find, %NUMA_NO_NODE for any node
*
* The @min_addr limit is dropped if it can not be satisfied and the allocation
* will fall back to memory below @min_addr. Also, allocation may fall back
* to any node in the system if the specified node can not
* hold the requested memory.
*
* The allocation is performed from memory region limited by
* memblock.current_limit if @max_addr == %BOOTMEM_ALLOC_ACCESSIBLE.
*
* The memory block is aligned on %SMP_CACHE_BYTES if @align == 0.
*
* The phys address of allocated boot memory block is converted to virtual and
* allocated memory is reset to 0.
*
* In addition, function sets the min_count to 0 using kmemleak_alloc for
* allocated boot memory block, so that it is never reported as leaks.
*
* Return:
* Virtual address of allocated memory block on success, NULL on failure.
*/
static void * __init memblock_virt_alloc_internal(
phys_addr_t size, phys_addr_t align,
phys_addr_t min_addr, phys_addr_t max_addr,
int nid)
{
phys_addr_t alloc;
void *ptr;
enum memblock_flags flags = choose_memblock_flags();
if (WARN_ONCE(nid == MAX_NUMNODES, "Usage of MAX_NUMNODES is deprecated. Use NUMA_NO_NODE instead\n"))
nid = NUMA_NO_NODE;
/*
* Detect any accidental use of these APIs after slab is ready, as at
* this moment memblock may be deinitialized already and its
* internal data may be destroyed (after execution of free_all_bootmem)
*/
if (WARN_ON_ONCE(slab_is_available()))
return kzalloc_node(size, GFP_NOWAIT, nid);
if (!align)
align = SMP_CACHE_BYTES;
if (max_addr > memblock.current_limit)
max_addr = memblock.current_limit;
again:
alloc = memblock_find_in_range_node(size, align, min_addr, max_addr,
nid, flags);
if (alloc && !memblock_reserve(alloc, size))
goto done;
if (nid != NUMA_NO_NODE) {
alloc = memblock_find_in_range_node(size, align, min_addr,
max_addr, NUMA_NO_NODE,
flags);
if (alloc && !memblock_reserve(alloc, size))
goto done;
}
if (min_addr) {
min_addr = 0;
goto again;
}
if (flags & MEMBLOCK_MIRROR) {
flags &= ~MEMBLOCK_MIRROR;
pr_warn("Could not allocate %pap bytes of mirrored memory\n",
&size);
goto again;
}
return NULL;
done:
ptr = phys_to_virt(alloc);
/* Skip kmemleak for kasan_init() due to high volume. */
if (max_addr != MEMBLOCK_ALLOC_KASAN)
/*
* The min_count is set to 0 so that bootmem allocated
* blocks are never reported as leaks. This is because many
* of these blocks are only referred via the physical
* address which is not looked up by kmemleak.
*/
kmemleak_alloc(ptr, size, 0, 0);
return ptr;
}
/**
* memblock_virt_alloc_try_nid_raw - allocate boot memory block without zeroing
* memory and without panicking
* @size: size of memory block to be allocated in bytes
* @align: alignment of the region and block's size
* @min_addr: the lower bound of the memory region from where the allocation
* is preferred (phys address)
* @max_addr: the upper bound of the memory region from where the allocation
* is preferred (phys address), or %BOOTMEM_ALLOC_ACCESSIBLE to
* allocate only from memory limited by memblock.current_limit value
* @nid: nid of the free area to find, %NUMA_NO_NODE for any node
*
* Public function, provides additional debug information (including caller
* info), if enabled. Does not zero allocated memory, does not panic if request
* cannot be satisfied.
*
* Return:
* Virtual address of allocated memory block on success, NULL on failure.
*/
void * __init memblock_virt_alloc_try_nid_raw(
phys_addr_t size, phys_addr_t align,
phys_addr_t min_addr, phys_addr_t max_addr,
int nid)
{
void *ptr;
memblock_dbg("%s: %llu bytes align=0x%llx nid=%d from=%pa max_addr=%pa %pF\n",
__func__, (u64)size, (u64)align, nid, &min_addr,
&max_addr, (void *)_RET_IP_);
ptr = memblock_virt_alloc_internal(size, align,
min_addr, max_addr, nid);
#ifdef CONFIG_DEBUG_VM
if (ptr && size > 0)
memset(ptr, PAGE_POISON_PATTERN, size);
#endif
return ptr;
}
/**
* memblock_virt_alloc_try_nid_nopanic - allocate boot memory block
* @size: size of memory block to be allocated in bytes
* @align: alignment of the region and block's size
* @min_addr: the lower bound of the memory region from where the allocation
* is preferred (phys address)
* @max_addr: the upper bound of the memory region from where the allocation
* is preferred (phys address), or %BOOTMEM_ALLOC_ACCESSIBLE to
* allocate only from memory limited by memblock.current_limit value
* @nid: nid of the free area to find, %NUMA_NO_NODE for any node
*
* Public function, provides additional debug information (including caller
* info), if enabled. This function zeroes the allocated memory.
*
* Return:
* Virtual address of allocated memory block on success, NULL on failure.
*/
void * __init memblock_virt_alloc_try_nid_nopanic(
phys_addr_t size, phys_addr_t align,
phys_addr_t min_addr, phys_addr_t max_addr,
int nid)
{
void *ptr;
memblock_dbg("%s: %llu bytes align=0x%llx nid=%d from=%pa max_addr=%pa %pF\n",
__func__, (u64)size, (u64)align, nid, &min_addr,
&max_addr, (void *)_RET_IP_);
ptr = memblock_virt_alloc_internal(size, align,
min_addr, max_addr, nid);
if (ptr)
memset(ptr, 0, size);
return ptr;
}
/**
* memblock_virt_alloc_try_nid - allocate boot memory block with panicking
* @size: size of memory block to be allocated in bytes
* @align: alignment of the region and block's size
* @min_addr: the lower bound of the memory region from where the allocation
* is preferred (phys address)
* @max_addr: the upper bound of the memory region from where the allocation
* is preferred (phys address), or %BOOTMEM_ALLOC_ACCESSIBLE to
* allocate only from memory limited by memblock.current_limit value
* @nid: nid of the free area to find, %NUMA_NO_NODE for any node
*
* Public panicking version of memblock_virt_alloc_try_nid_nopanic()
* which provides debug information (including caller info), if enabled,
* and panics if the request can not be satisfied.
*
* Return:
* Virtual address of allocated memory block on success, NULL on failure.
*/
void * __init memblock_virt_alloc_try_nid(
phys_addr_t size, phys_addr_t align,
phys_addr_t min_addr, phys_addr_t max_addr,
int nid)
{
void *ptr;
memblock_dbg("%s: %llu bytes align=0x%llx nid=%d from=%pa max_addr=%pa %pF\n",
__func__, (u64)size, (u64)align, nid, &min_addr,
&max_addr, (void *)_RET_IP_);
ptr = memblock_virt_alloc_internal(size, align,
min_addr, max_addr, nid);
if (ptr) {
memset(ptr, 0, size);
return ptr;
}
panic("%s: Failed to allocate %llu bytes align=0x%llx nid=%d from=%pa max_addr=%pa\n",
__func__, (u64)size, (u64)align, nid, &min_addr, &max_addr);
return NULL;
}
#endif
/**
* __memblock_free_early - free boot memory block
* @base: phys starting address of the boot memory block
* @size: size of the boot memory block in bytes
*
* Free boot memory block previously allocated by memblock_virt_alloc_xx() API.
* The freeing memory will not be released to the buddy allocator.
*/
void __init __memblock_free_early(phys_addr_t base, phys_addr_t size)
{
memblock_free(base, size);
}
/**
* __memblock_free_late - free bootmem block pages directly to buddy allocator
* @base: phys starting address of the boot memory block
* @size: size of the boot memory block in bytes
*
* This is only useful when the bootmem allocator has already been torn
* down, but we are still initializing the system. Pages are released directly
* to the buddy allocator, no bootmem metadata is updated because it is gone.
*/
void __init __memblock_free_late(phys_addr_t base, phys_addr_t size)
{
phys_addr_t cursor, end;
end = base + size - 1;
memblock_dbg("%s: [%pa-%pa] %pF\n",
__func__, &base, &end, (void *)_RET_IP_);
kmemleak_free_part_phys(base, size);
cursor = PFN_UP(base);
end = PFN_DOWN(base + size);
for (; cursor < end; cursor++) {
__free_pages_bootmem(pfn_to_page(cursor), cursor, 0);
totalram_pages++;
}
}
/*
* Remaining API functions
*/
phys_addr_t __init_memblock memblock_phys_mem_size(void)
{
return memblock.memory.total_size;
}
phys_addr_t __init_memblock memblock_reserved_size(void)
{
return memblock.reserved.total_size;
}
phys_addr_t __init memblock_mem_size(unsigned long limit_pfn)
{
unsigned long pages = 0;
struct memblock_region *r;
unsigned long start_pfn, end_pfn;
for_each_memblock(memory, r) {
start_pfn = memblock_region_memory_base_pfn(r);
end_pfn = memblock_region_memory_end_pfn(r);
start_pfn = min_t(unsigned long, start_pfn, limit_pfn);
end_pfn = min_t(unsigned long, end_pfn, limit_pfn);
pages += end_pfn - start_pfn;
}
return PFN_PHYS(pages);
}
/* lowest address */
phys_addr_t __init_memblock memblock_start_of_DRAM(void)
{
return memblock.memory.regions[0].base;
}
EXPORT_SYMBOL_GPL(memblock_start_of_DRAM);
phys_addr_t __init_memblock memblock_end_of_DRAM(void)
{
int idx = memblock.memory.cnt - 1;
return (memblock.memory.regions[idx].base + memblock.memory.regions[idx].size);
}
EXPORT_SYMBOL_GPL(memblock_end_of_DRAM);
static phys_addr_t __init_memblock __find_max_addr(phys_addr_t limit)
{
phys_addr_t max_addr = PHYS_ADDR_MAX;
struct memblock_region *r;
/*
* translate the memory @limit size into the max address within one of
* the memory memblock regions, if the @limit exceeds the total size
* of those regions, max_addr will keep original value PHYS_ADDR_MAX
*/
for_each_memblock(memory, r) {
if (limit <= r->size) {
max_addr = r->base + limit;
break;
}
limit -= r->size;
}
return max_addr;
}
phys_addr_t __init_memblock memblock_max_addr(phys_addr_t limit)
{
return __find_max_addr(limit);
}
void __init memblock_enforce_memory_limit(phys_addr_t limit)
{
phys_addr_t max_addr = PHYS_ADDR_MAX;
if (!limit)
return;
max_addr = __find_max_addr(limit);
/* @limit exceeds the total size of the memory, do nothing */
if (max_addr == PHYS_ADDR_MAX)
return;
/* truncate both memory and reserved regions */
memblock_remove_range(&memblock.memory, max_addr,
PHYS_ADDR_MAX);
memblock_remove_range(&memblock.reserved, max_addr,
PHYS_ADDR_MAX);
}
void __init memblock_cap_memory_range(phys_addr_t base, phys_addr_t size)
{
int start_rgn, end_rgn;
int i, ret;
if (!size)
return;
ret = memblock_isolate_range(&memblock.memory, base, size,
&start_rgn, &end_rgn);
if (ret)
return;
/* remove all the MAP regions */
for (i = memblock.memory.cnt - 1; i >= end_rgn; i--)
if (!memblock_is_nomap(&memblock.memory.regions[i]))
memblock_remove_region(&memblock.memory, i);
for (i = start_rgn - 1; i >= 0; i--)
if (!memblock_is_nomap(&memblock.memory.regions[i]))
memblock_remove_region(&memblock.memory, i);
/* truncate the reserved regions */
memblock_remove_range(&memblock.reserved, 0, base);
memblock_remove_range(&memblock.reserved,
base + size, PHYS_ADDR_MAX);
}
void __init memblock_mem_limit_remove_map(phys_addr_t limit)
{
phys_addr_t max_addr;
if (!limit)
return;
max_addr = __find_max_addr(limit);
/* @limit exceeds the total size of the memory, do nothing */
if (max_addr == PHYS_ADDR_MAX)
return;
memblock_cap_memory_range(0, max_addr);
}
static int __init_memblock memblock_search(struct memblock_type *type, phys_addr_t addr)
{
unsigned int left = 0, right = type->cnt;
do {
unsigned int mid = (right + left) / 2;
if (addr < type->regions[mid].base)
right = mid;
else if (addr >= (type->regions[mid].base +
type->regions[mid].size))
left = mid + 1;
else
return mid;
} while (left < right);
return -1;
}
bool __init memblock_is_reserved(phys_addr_t addr)
{
return memblock_search(&memblock.reserved, addr) != -1;
}
bool __init_memblock memblock_is_memory(phys_addr_t addr)
{
return memblock_search(&memblock.memory, addr) != -1;
}
bool __init_memblock memblock_is_map_memory(phys_addr_t addr)
{
int i = memblock_search(&memblock.memory, addr);
if (i == -1)
return false;
return !memblock_is_nomap(&memblock.memory.regions[i]);
}
#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
int __init_memblock memblock_search_pfn_nid(unsigned long pfn,
unsigned long *start_pfn, unsigned long *end_pfn)
{
struct memblock_type *type = &memblock.memory;
int mid = memblock_search(type, PFN_PHYS(pfn));
if (mid == -1)
return -1;
*start_pfn = PFN_DOWN(type->regions[mid].base);
*end_pfn = PFN_DOWN(type->regions[mid].base + type->regions[mid].size);
return type->regions[mid].nid;
}
#endif
/**
* memblock_is_region_memory - check if a region is a subset of memory
* @base: base of region to check
* @size: size of region to check
*
* Check if the region [@base, @base + @size) is a subset of a memory block.
*
* Return:
* 0 if false, non-zero if true
*/
bool __init_memblock memblock_is_region_memory(phys_addr_t base, phys_addr_t size)
{
int idx = memblock_search(&memblock.memory, base);
phys_addr_t end = base + memblock_cap_size(base, &size);
if (idx == -1)
return false;
return (memblock.memory.regions[idx].base +
memblock.memory.regions[idx].size) >= end;
}
bool __init_memblock memblock_overlaps_memory(phys_addr_t base,
phys_addr_t size)
{
memblock_cap_size(base, &size);
return memblock_overlaps_region(&memblock.memory, base, size);
}
EXPORT_SYMBOL_GPL(memblock_overlaps_memory);
/**
* memblock_is_region_reserved - check if a region intersects reserved memory
* @base: base of region to check
* @size: size of region to check
*
* Check if the region [@base, @base + @size) intersects a reserved
* memory block.
*
* Return:
* True if they intersect, false if not.
*/
bool __init_memblock memblock_is_region_reserved(phys_addr_t base, phys_addr_t size)
{
memblock_cap_size(base, &size);
return memblock_overlaps_region(&memblock.reserved, base, size);
}
void __init_memblock memblock_trim_memory(phys_addr_t align)
{
phys_addr_t start, end, orig_start, orig_end;
struct memblock_region *r;
for_each_memblock(memory, r) {
orig_start = r->base;
orig_end = r->base + r->size;
start = round_up(orig_start, align);
end = round_down(orig_end, align);
if (start == orig_start && end == orig_end)
continue;
if (start < end) {
r->base = start;
r->size = end - start;
} else {
memblock_remove_region(&memblock.memory,
r - memblock.memory.regions);
r--;
}
}
}
void __init_memblock memblock_set_current_limit(phys_addr_t limit)
{
memblock.current_limit = limit;
}
phys_addr_t __init_memblock memblock_get_current_limit(void)
{
return memblock.current_limit;
}
static void __init_memblock memblock_dump(struct memblock_type *type)
{
phys_addr_t base, end, size;
enum memblock_flags flags;
int idx;
struct memblock_region *rgn;
pr_info(" %s.cnt = 0x%lx\n", type->name, type->cnt);
for_each_memblock_type(idx, type, rgn) {
char nid_buf[32] = "";
base = rgn->base;
size = rgn->size;
end = base + size - 1;
flags = rgn->flags;
#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
if (memblock_get_region_node(rgn) != MAX_NUMNODES)
snprintf(nid_buf, sizeof(nid_buf), " on node %d",
memblock_get_region_node(rgn));
#endif
pr_info(" %s[%#x]\t[%pa-%pa], %pa bytes%s flags: %#x\n",
type->name, idx, &base, &end, &size, nid_buf, flags);
}
}
void __init_memblock __memblock_dump_all(void)
{
pr_info("MEMBLOCK configuration:\n");
pr_info(" memory size = %pa reserved size = %pa\n",
&memblock.memory.total_size,
&memblock.reserved.total_size);
memblock_dump(&memblock.memory);
memblock_dump(&memblock.reserved);
#ifdef CONFIG_HAVE_MEMBLOCK_PHYS_MAP
memblock_dump(&memblock.physmem);
#endif
}
void __init memblock_allow_resize(void)
{
memblock_can_resize = 1;
}
static int __init early_memblock(char *p)
{
if (p && strstr(p, "debug"))
memblock_debug = 1;
return 0;
}
early_param("memblock", early_memblock);
#if defined(CONFIG_DEBUG_FS) && !defined(CONFIG_ARCH_DISCARD_MEMBLOCK)
static int memblock_debug_show(struct seq_file *m, void *private)
{
struct memblock_type *type = m->private;
struct memblock_region *reg;
int i;
phys_addr_t end;
for (i = 0; i < type->cnt; i++) {
reg = &type->regions[i];
end = reg->base + reg->size - 1;
seq_printf(m, "%4d: ", i);
seq_printf(m, "%pa..%pa\n", &reg->base, &end);
}
return 0;
}
DEFINE_SHOW_ATTRIBUTE(memblock_debug);
static int __init memblock_init_debugfs(void)
{
struct dentry *root = debugfs_create_dir("memblock", NULL);
if (!root)
return -ENXIO;
debugfs_create_file("memory", 0444, root,
&memblock.memory, &memblock_debug_fops);
debugfs_create_file("reserved", 0444, root,
&memblock.reserved, &memblock_debug_fops);
#ifdef CONFIG_HAVE_MEMBLOCK_PHYS_MAP
debugfs_create_file("physmem", 0444, root,
&memblock.physmem, &memblock_debug_fops);
#endif
return 0;
}
__initcall(memblock_init_debugfs);
#endif /* CONFIG_DEBUG_FS */