5bd75403be
* remotes/origin/tmp-f686d9f:
ANDROID: update abi_gki_aarch64.xml for 5.2-rc6
Linux 5.2-rc6
Revert "iommu/vt-d: Fix lock inversion between iommu->lock and device_domain_lock"
Bluetooth: Fix regression with minimum encryption key size alignment
tcp: refine memory limit test in tcp_fragment()
x86/vdso: Prevent segfaults due to hoisted vclock reads
SUNRPC: Fix a credential refcount leak
Revert "SUNRPC: Declare RPC timers as TIMER_DEFERRABLE"
net :sunrpc :clnt :Fix xps refcount imbalance on the error path
NFS4: Only set creation opendata if O_CREAT
ANDROID: gki_defconfig: workaround to enable configs
ANDROID: gki_defconfig: more configs for partners
ARM: 8867/1: vdso: pass --be8 to linker if necessary
KVM: nVMX: reorganize initial steps of vmx_set_nested_state
KVM: PPC: Book3S HV: Invalidate ERAT when flushing guest TLB entries
habanalabs: use u64_to_user_ptr() for reading user pointers
nfsd: replace Jeff by Chuck as nfsd co-maintainer
inet: clear num_timeout reqsk_alloc()
PCI/P2PDMA: Ignore root complex whitelist when an IOMMU is present
net: mvpp2: debugfs: Add pmap to fs dump
ipv6: Default fib6_type to RTN_UNICAST when not set
net: hns3: Fix inconsistent indenting
net/af_iucv: always register net_device notifier
net/af_iucv: build proper skbs for HiperTransport
net/af_iucv: remove GFP_DMA restriction for HiperTransport
doc: fix documentation about UIO_MEM_LOGICAL using
MAINTAINERS / Documentation: Thorsten Scherer is the successor of Gavin Schenk
docs: fb: Add TER16x32 to the available font names
MAINTAINERS: fpga: hand off maintainership to Moritz
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 507
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 506
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 505
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 504
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 503
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 502
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 501
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 500
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 499
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 498
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 497
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 496
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 495
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 491
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 490
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 489
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 488
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 487
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 486
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 485
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 484
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 482
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 481
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 480
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 479
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 477
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 475
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 474
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 473
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 472
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 471
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 469
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 468
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 467
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 466
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 465
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 464
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 463
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 462
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 461
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 460
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 459
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 457
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 456
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 455
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 454
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 452
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 451
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 250
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 248
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 247
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 246
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 245
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 244
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 243
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 239
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 238
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 237
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 235
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 234
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 233
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 232
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 231
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 230
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 226
KVM: arm/arm64: Fix emulated ptimer irq injection
net: dsa: mv88e6xxx: fix shift of FID bits in mv88e6185_g1_vtu_loadpurge()
tests: kvm: Check for a kernel warning
kvm: tests: Sort tests in the Makefile alphabetically
KVM: x86/mmu: Allocate PAE root array when using SVM's 32-bit NPT
KVM: x86: Modify struct kvm_nested_state to have explicit fields for data
fanotify: update connector fsid cache on add mark
quota: fix a problem about transfer quota
drm/i915: Don't clobber M/N values during fastset check
powerpc: enable a 30-bit ZONE_DMA for 32-bit pmac
ovl: make i_ino consistent with st_ino in more cases
scsi: qla2xxx: Fix hardlockup in abort command during driver remove
scsi: ufs: Avoid runtime suspend possibly being blocked forever
scsi: qedi: update driver version to 8.37.0.20
scsi: qedi: Check targetname while finding boot target information
hvsock: fix epollout hang from race condition
net/udp_gso: Allow TX timestamp with UDP GSO
net: netem: fix use after free and double free with packet corruption
net: netem: fix backlog accounting for corrupted GSO frames
net: lio_core: fix potential sign-extension overflow on large shift
tipc: pass tunnel dev as NULL to udp_tunnel(6)_xmit_skb
ip6_tunnel: allow not to count pkts on tstats by passing dev as NULL
ip_tunnel: allow not to count pkts on tstats by setting skb's dev to NULL
apparmor: reset pos on failure to unpack for various functions
apparmor: enforce nullbyte at end of tag string
apparmor: fix PROFILE_MEDIATES for untrusted input
RDMA/efa: Handle mmap insertions overflow
tun: wake up waitqueues after IFF_UP is set
drm: return -EFAULT if copy_to_user() fails
net: remove duplicate fetch in sock_getsockopt
tipc: fix issues with early FAILOVER_MSG from peer
bnx2x: Check if transceiver implements DDM before access
xhci: detect USB 3.2 capable host controllers correctly
usb: xhci: Don't try to recover an endpoint if port is in error state.
KVM: fix typo in documentation
drm/panfrost: Make sure a BO is only unmapped when appropriate
md: fix for divide error in status_resync
soc: ixp4xx: npe: Fix an IS_ERR() vs NULL check in probe
arm64/mm: don't initialize pgd_cache twice
MAINTAINERS: Update my email address
arm64/sve: <uapi/asm/ptrace.h> should not depend on <uapi/linux/prctl.h>
ovl: fix typo in MODULE_PARM_DESC
ovl: fix bogus -Wmaybe-unitialized warning
ovl: don't fail with disconnected lower NFS
mmc: core: Prevent processing SDIO IRQs when the card is suspended
mmc: sdhci: sdhci-pci-o2micro: Correctly set bus width when tuning
brcmfmac: sdio: Don't tune while the card is off
mmc: core: Add sdio_retune_hold_now() and sdio_retune_release()
brcmfmac: sdio: Disable auto-tuning around commands expected to fail
mmc: core: API to temporarily disable retuning for SDIO CRC errors
Revert "brcmfmac: disable command decode in sdio_aos"
ARM: ixp4xx: include irqs.h where needed
ARM: ixp4xx: mark ixp4xx_irq_setup as __init
ARM: ixp4xx: don't select SERIAL_OF_PLATFORM
firmware: trusted_foundations: add ARMv7 dependency
usb: dwc2: Use generic PHY width in params setup
RDMA/efa: Fix success return value in case of error
IB/hfi1: Handle port down properly in pio
IB/hfi1: Handle wakeup of orphaned QPs for pio
IB/hfi1: Wakeup QPs orphaned on wait list after flush
IB/hfi1: Use aborts to trigger RC throttling
IB/hfi1: Create inline to get extended headers
IB/hfi1: Silence txreq allocation warnings
IB/hfi1: Avoid hardlockup with flushlist_lock
KVM: PPC: Book3S HV: Only write DAWR[X] when handling h_set_dawr in real mode
KVM: PPC: Book3S HV: Fix r3 corruption in h_set_dabr()
fs/namespace: fix unprivileged mount propagation
vfs: fsmount: add missing mntget()
cifs: fix GlobalMid_Lock bug in cifs_reconnect
SMB3: retry on STATUS_INSUFFICIENT_RESOURCES instead of failing write
staging: erofs: add requirements field in superblock
arm64: ssbd: explicitly depend on <linux/prctl.h>
block: fix page leak when merging to same page
block: return from __bio_try_merge_page if merging occured in the same page
Btrfs: fix failure to persist compression property xattr deletion on fsync
riscv: remove unused barrier defines
usb: chipidea: udc: workaround for endpoint conflict issue
MAINTAINERS: Change QCOM repo location
mmc: mediatek: fix SDIO IRQ detection issue
mmc: mediatek: fix SDIO IRQ interrupt handle flow
mmc: core: complete HS400 before checking status
riscv: mm: synchronize MMU after pte change
MAINTAINERS: Update my email address to use @kernel.org
ANDROID: update abi_gki_aarch64.xml for 5.2-rc5
riscv: dts: add initial board data for the SiFive HiFive Unleashed
riscv: dts: add initial support for the SiFive FU540-C000 SoC
dt-bindings: riscv: convert cpu binding to json-schema
dt-bindings: riscv: sifive: add YAML documentation for the SiFive FU540
arch: riscv: add support for building DTB files from DT source data
drm/i915/gvt: ignore unexpected pvinfo write
lapb: fixed leak of control-blocks.
tipc: purge deferredq list for each grp member in tipc_group_delete
ax25: fix inconsistent lock state in ax25_destroy_timer
neigh: fix use-after-free read in pneigh_get_next
tcp: fix compile error if !CONFIG_SYSCTL
hv_sock: Suppress bogus "may be used uninitialized" warnings
be2net: Fix number of Rx queues used for flow hashing
net: handle 802.1P vlan 0 packets properly
Linux 5.2-rc5
tcp: enforce tcp_min_snd_mss in tcp_mtu_probing()
tcp: add tcp_min_snd_mss sysctl
tcp: tcp_fragment() should apply sane memory limits
tcp: limit payload size of sacked skbs
Revert "net: phylink: set the autoneg state in phylink_phy_change"
bpf: fix nested bpf tracepoints with per-cpu data
bpf: Fix out of bounds memory access in bpf_sk_storage
vsock/virtio: set SOCK_DONE on peer shutdown
net: dsa: rtl8366: Fix up VLAN filtering
net: phylink: set the autoneg state in phylink_phy_change
powerpc/32: fix build failure on book3e with KVM
powerpc/booke: fix fast syscall entry on SMP
powerpc/32s: fix initial setup of segment registers on secondary CPU
x86/microcode, cpuhotplug: Add a microcode loader CPU hotplug callback
net: add high_order_alloc_disable sysctl/static key
tcp: add tcp_tx_skb_cache sysctl
tcp: add tcp_rx_skb_cache sysctl
sysctl: define proc_do_static_key()
hv_netvsc: Set probe mode to sync
net: sched: flower: don't call synchronize_rcu() on mask creation
net: dsa: fix warning same module names
sctp: Free cookie before we memdup a new one
net: dsa: microchip: Don't try to read stats for unused ports
qmi_wwan: extend permitted QMAP mux_id value range
qmi_wwan: avoid RCU stalls on device disconnect when in QMAP mode
qmi_wwan: add network device usage statistics for qmimux devices
qmi_wwan: add support for QMAP padding in the RX path
bpf, x64: fix stack layout of JITed bpf code
Smack: Restore the smackfsdef mount option and add missing prefixes
bpf, devmap: Add missing RCU read lock on flush
bpf, devmap: Add missing bulk queue free
bpf, devmap: Fix premature entry free on destroying map
ftrace: Fix NULL pointer dereference in free_ftrace_func_mapper()
module: Fix livepatch/ftrace module text permissions race
tracing/uprobe: Fix obsolete comment on trace_uprobe_create()
tracing/uprobe: Fix NULL pointer dereference in trace_uprobe_create()
tracing: Make two symbols static
tracing: avoid build warning with HAVE_NOP_MCOUNT
tracing: Fix out-of-range read in trace_stack_print()
gfs2: Fix rounding error in gfs2_iomap_page_prepare
net: phylink: further mac_config documentation improvements
nfc: Ensure presence of required attributes in the deactivate_target handler
btrfs: start readahead also in seed devices
x86/kasan: Fix boot with 5-level paging and KASAN
cfg80211: report measurement start TSF correctly
cfg80211: fix memory leak of wiphy device name
cfg80211: util: fix bit count off by one
mac80211: do not start any work during reconfigure flow
cfg80211: use BIT_ULL in cfg80211_parse_mbssid_data()
mac80211: only warn once on chanctx_conf being NULL
mac80211: drop robust management frames from unknown TA
gpu: ipu-v3: image-convert: Fix image downsize coefficients
gpu: ipu-v3: image-convert: Fix input bytesperline for packed formats
gpu: ipu-v3: image-convert: Fix input bytesperline width/height align
thunderbolt: Implement CIO reset correctly for Titan Ridge
ARM: davinci: da8xx: specify dma_coherent_mask for lcdc
ARM: davinci: da850-evm: call regulator_has_full_constraints()
timekeeping: Repair ktime_get_coarse*() granularity
Revert "ALSA: hda/realtek - Improve the headset mic for Acer Aspire laptops"
ANDROID: update abi_gki_aarch64.xml
mm/devm_memremap_pages: fix final page put race
PCI/P2PDMA: track pgmap references per resource, not globally
lib/genalloc: introduce chunk owners
PCI/P2PDMA: fix the gen_pool_add_virt() failure path
mm/devm_memremap_pages: introduce devm_memunmap_pages
drivers/base/devres: introduce devm_release_action()
mm/vmscan.c: fix trying to reclaim unevictable LRU page
coredump: fix race condition between collapse_huge_page() and core dumping
mm/mlock.c: change count_mm_mlocked_page_nr return type
mm: mmu_gather: remove __tlb_reset_range() for force flush
fs/ocfs2: fix race in ocfs2_dentry_attach_lock()
mm/vmscan.c: fix recent_rotated history
mm/mlock.c: mlockall error for flag MCL_ONFAULT
scripts/decode_stacktrace.sh: prefix addr2line with $CROSS_COMPILE
mm/list_lru.c: fix memory leak in __memcg_init_list_lru_node
mm: memcontrol: don't batch updates of local VM stats and events
PCI: PM: Skip devices in D0 for suspend-to-idle
ANDROID: Removed extraneous configs from gki
powerpc/bpf: use unsigned division instruction for 64-bit operations
bpf: fix div64 overflow tests to properly detect errors
bpf: sync BPF_FIB_LOOKUP flag changes with BPF uapi
bpf: simplify definition of BPF_FIB_LOOKUP related flags
cifs: add spinlock for the openFileList to cifsInodeInfo
cifs: fix panic in smb2_reconnect
x86/fpu: Don't use current->mm to check for a kthread
KVM: nVMX: use correct clean fields when copying from eVMCS
vfio-ccw: Destroy kmem cache region on module exit
block/ps3vram: Use %llu to format sector_t after LBDAF removal
libata: Extend quirks for the ST1000LM024 drives with NOLPM quirk
bcache: only set BCACHE_DEV_WB_RUNNING when cached device attached
bcache: fix stack corruption by PRECEDING_KEY()
arm64/sve: Fix missing SVE/FPSIMD endianness conversions
blk-mq: remove WARN_ON(!q->elevator) from blk_mq_sched_free_requests
blkio-controller.txt: Remove references to CFQ
block/switching-sched.txt: Update to blk-mq schedulers
null_blk: remove duplicate check for report zone
blk-mq: no need to check return value of debugfs_create functions
io_uring: fix memory leak of UNIX domain socket inode
block: force select mq-deadline for zoned block devices
binder: fix possible UAF when freeing buffer
drm/amdgpu: return 0 by default in amdgpu_pm_load_smu_firmware
drm/amdgpu: Fix bounds checking in amdgpu_ras_is_supported()
ANDROID: x86 gki_defconfig: enable DMA_CMA
ANDROID: Fixed x86 regression
ANDROID: gki_defconfig: enable DMA_CMA
Input: synaptics - enable SMBus on ThinkPad E480 and E580
net: mvpp2: prs: Use the correct helpers when removing all VID filters
net: mvpp2: prs: Fix parser range for VID filtering
mlxsw: spectrum: Disallow prio-tagged packets when PVID is removed
mlxsw: spectrum_buffers: Reduce pool size on Spectrum-2
selftests: tc_flower: Add TOS matching test
mlxsw: spectrum_flower: Fix TOS matching
selftests: mlxsw: Test nexthop offload indication
mlxsw: spectrum_router: Refresh nexthop neighbour when it becomes dead
mlxsw: spectrum: Use different seeds for ECMP and LAG hash
net: tls, correctly account for copied bytes with multiple sk_msgs
vrf: Increment Icmp6InMsgs on the original netdev
cpuset: restore sanity to cpuset_cpus_allowed_fallback()
net: ethtool: Allow matching on vlan DEI bit
linux-next: DOC: RDS: Fix a typo in rds.txt
x86/kgdb: Return 0 from kgdb_arch_set_breakpoint()
mpls: fix af_mpls dependencies for real
selinux: fix a missing-check bug in selinux_sb_eat_lsm_opts()
selinux: fix a missing-check bug in selinux_add_mnt_opt( )
arm64: tlbflush: Ensure start/end of address range are aligned to stride
usb: typec: Make sure an alt mode exist before getting its partner
KVM: arm/arm64: vgic: Fix kvm_device leak in vgic_its_destroy
KVM: arm64: Filter out invalid core register IDs in KVM_GET_REG_LIST
KVM: arm64: Implement vq_present() as a macro
xdp: check device pointer before clearing
bpf: net: Set sk_bpf_storage back to NULL for cloned sk
Btrfs: fix race between block group removal and block group allocation
clocksource/drivers/arm_arch_timer: Don't trace count reader functions
i2c: pca-platform: Fix GPIO lookup code
thunderbolt: Make sure device runtime resume completes before taking domain lock
drm: add fallback override/firmware EDID modes workaround
i2c: acorn: fix i2c warning
arm64: Don't unconditionally add -Wno-psabi to KBUILD_CFLAGS
drm/edid: abstract override/firmware EDID retrieval
platform/mellanox: mlxreg-hotplug: Add devm_free_irq call to remove flow
platform/x86: mlx-platform: Fix parent device in i2c-mux-reg device registration
platform/x86: intel-vbtn: Report switch events when event wakes device
platform/x86: asus-wmi: Only Tell EC the OS will handle display hotkeys from asus_nb_wmi
ARM: mvebu_v7_defconfig: fix Ethernet on Clearfog
x86/resctrl: Prevent NULL pointer dereference when local MBM is disabled
x86/resctrl: Don't stop walking closids when a locksetup group is found
iommu/arm-smmu: Avoid constant zero in TLBI writes
drm/i915/perf: fix whitelist on Gen10+
drm/i915/sdvo: Implement proper HDMI audio support for SDVO
drm/i915: Fix per-pixel alpha with CCS
drm/i915/dmc: protect against reading random memory
drm/i915/dsi: Use a fuzzy check for burst mode clock check
Input: imx_keypad - make sure keyboard can always wake up system
selinux: log raw contexts as untrusted strings
ptrace: restore smp_rmb() in __ptrace_may_access()
IB/hfi1: Correct tid qp rcd to match verbs context
IB/hfi1: Close PSM sdma_progress sleep window
IB/hfi1: Validate fault injection opcode user input
geneve: Don't assume linear buffers in error handler
vxlan: Don't assume linear buffers in error handler
net: openvswitch: do not free vport if register_netdevice() is failed.
net: correct udp zerocopy refcnt also when zerocopy only on append
drm/amdgpu/{uvd,vcn}: fetch ring's read_ptr after alloc
ovl: fix wrong flags check in FS_IOC_FS[SG]ETXATTR ioctls
riscv: Fix udelay in RV32.
drm/vmwgfx: fix a warning due to missing dma_parms
riscv: export pm_power_off again
drm/vmwgfx: Honor the sg list segment size limitation
RISC-V: defconfig: enable clocks, serial console
drm/vmwgfx: Use the backdoor port if the HB port is not available
bpf: lpm_trie: check left child of last leftmost node for NULL
Revert "fuse: require /dev/fuse reads to have enough buffer capacity"
ALSA: ice1712: Check correct return value to snd_i2c_sendbytes (EWS/DMX 6Fire)
ALSA: oxfw: allow PCM capture for Stanton SCS.1m
ALSA: firewire-motu: fix destruction of data for isochronous resources
s390/ctl_reg: mark __ctl_set_bit and __ctl_clear_bit as __always_inline
s390/boot: disable address-of-packed-member warning
ANDROID: update gki aarch64 ABI representation
cgroup: Fix css_task_iter_advance_css_set() cset skip condition
drm/panfrost: Require the simple_ondemand governor
drm/panfrost: make devfreq optional again
drm/gem_shmem: Use a writecombine mapping for ->vaddr
mmc: sdhi: disallow HS400 for M3-W ES1.2, RZ/G2M, and V3H
ASoC: Intel: sst: fix kmalloc call with wrong flags
ASoC: core: Fix deadlock in snd_soc_instantiate_card()
cgroup/bfq: revert bfq.weight symlink change
ARM: dts: am335x phytec boards: Fix cd-gpios active level
ARM: dts: dra72x: Disable usb4_tm target module
nfp: ensure skb network header is set for packet redirect
tcp: fix undo spurious SYNACK in passive Fast Open
mpls: fix af_mpls dependencies
ibmvnic: Fix unchecked return codes of memory allocations
ibmvnic: Refresh device multicast list after reset
ibmvnic: Do not close unopened driver during reset
mpls: fix warning with multi-label encap
net: phy: rename Asix Electronics PHY driver
ipv6: flowlabel: fl6_sock_lookup() must use atomic_inc_not_zero
net: ipv4: fib_semantics: fix uninitialized variable
Input: iqs5xx - get axis info before calling input_mt_init_slots()
Linux 5.2-rc4
drm: panel-orientation-quirks: Add quirk for GPD MicroPC
drm: panel-orientation-quirks: Add quirk for GPD pocket2
counter/ftm-quaddec: Add missing dependencies in Kconfig
staging: iio: adt7316: Fix build errors when GPIOLIB is not set
x86/fpu: Update kernel's FPU state before using for the fsave header
MAINTAINERS: Karthikeyan Ramasubramanian is MIA
i2c: xiic: Add max_read_len quirk
ANDROID: update ABI representation
gpio: pca953x: hack to fix 24 bit gpio expanders
net/mlx5e: Support tagged tunnel over bond
net/mlx5e: Avoid detaching non-existing netdev under switchdev mode
net/mlx5e: Fix source port matching in fdb peer flow rule
net/mlx5e: Replace reciprocal_scale in TX select queue function
net/mlx5e: Add ndo_set_feature for uplink representor
net/mlx5: Avoid reloading already removed devices
net/mlx5: Update pci error handler entries and command translation
RAS/CEC: Convert the timer callback to a workqueue
RAS/CEC: Fix binary search function
x86/mm/KASLR: Compute the size of the vmemmap section properly
can: purge socket error queue on sock destruct
can: flexcan: Remove unneeded registration message
can: af_can: Fix error path of can_init()
can: m_can: implement errata "Needless activation of MRAF irq"
can: mcp251x: add support for mcp25625
dt-bindings: can: mcp251x: add mcp25625 support
can: xilinx_can: use correct bittiming_const for CAN FD core
can: flexcan: fix timeout when set small bitrate
can: usb: Kconfig: Remove duplicate menu entry
lockref: Limit number of cmpxchg loop retries
uaccess: add noop untagged_addr definition
x86/insn-eval: Fix use-after-free access to LDT entry
kbuild: use more portable 'command -v' for cc-cross-prefix
s390/unwind: correct stack switching during unwind
scsi: hpsa: correct ioaccel2 chaining
btrfs: Always trim all unallocated space in btrfs_trim_free_extents
netfilter: ipv6: nf_defrag: accept duplicate fragments again
powerpc/32s: fix booting with CONFIG_PPC_EARLY_DEBUG_BOOTX
drm/meson: fix G12A primary plane disabling
drm/meson: fix primary plane disabling
drm/meson: fix G12A HDMI PLL settings for 4K60 1000/1001 variations
block, bfq: add weight symlink to the bfq.weight cgroup parameter
cgroup: let a symlink too be created with a cftype file
powerpc/64s: __find_linux_pte() synchronization vs pmdp_invalidate()
powerpc/64s: Fix THP PMD collapse serialisation
powerpc: Fix kexec failure on book3s/32
drm/nouveau/secboot/gp10[2467]: support newer FW to fix SEC2 failures on some boards
drm/nouveau/secboot: enable loading of versioned LS PMU/SEC2 ACR msgqueue FW
drm/nouveau/secboot: split out FW version-specific LS function pointers
drm/nouveau/secboot: pass max supported FW version to LS load funcs
drm/nouveau/core: support versioned firmware loading
drm/nouveau/core: pass subdev into nvkm_firmware_get, rather than device
block: free sched's request pool in blk_cleanup_queue
bpf: expand section tests for test_section_names
bpf: more msg_name rewrite tests to test_sock_addr
bpf, bpftool: enable recvmsg attach types
bpf, libbpf: enable recvmsg attach types
bpf: sync tooling uapi header
bpf: fix unconnected udp hooks
vfio/mdev: Synchronize device create/remove with parent removal
vfio/mdev: Avoid creating sysfs remove file on stale device removal
pktgen: do not sleep with the thread lock held.
net: mvpp2: Use strscpy to handle stat strings
net: rds: fix memory leak in rds_ib_flush_mr_pool
ipv6: fix EFAULT on sendto with icmpv6 and hdrincl
ipv6: use READ_ONCE() for inet->hdrincl as in ipv4
soundwire: intel: set dai min and max channels correctly
soundwire: stream: fix bad unlock balance
x86/fpu: Use fault_in_pages_writeable() for pre-faulting
nvme-rdma: use dynamic dma mapping per command
nvme: Fix u32 overflow in the number of namespace list calculation
vfio/mdev: Improve the create/remove sequence
SoC: rt274: Fix internal jack assignment in set_jack callback
ALSA: hdac: fix memory release for SST and SOF drivers
ASoC: SOF: Intel: hda: use the defined ppcap functions
ASoC: core: move DAI pre-links initiation to snd_soc_instantiate_card
ASoC: Intel: cht_bsw_rt5672: fix kernel oops with platform_name override
ASoC: Intel: cht_bsw_nau8824: fix kernel oops with platform_name override
ASoC: Intel: bytcht_es8316: fix kernel oops with platform_name override
ASoC: Intel: cht_bsw_max98090: fix kernel oops with platform_name override
Revert "gfs2: Replace gl_revokes with a GLF flag"
arm64: Silence gcc warnings about arch ABI drift
parisc: Fix crash due alternative coding for NP iopdir_fdc bit
parisc: Use lpa instruction to load physical addresses in driver code
parisc: configs: Remove useless UEVENT_HELPER_PATH
parisc: Use implicit space register selection for loading the coherence index of I/O pdirs
usb: gadget: udc: lpc32xx: fix return value check in lpc32xx_udc_probe()
usb: gadget: dwc2: fix zlp handling
usb: dwc2: Set actual frame number for completed ISOC transfer for none DDMA
usb: gadget: udc: lpc32xx: allocate descriptor with GFP_ATOMIC
usb: gadget: fusb300_udc: Fix memory leak of fusb300->ep[i]
usb: phy: mxs: Disable external charger detect in mxs_phy_hw_init()
usb: dwc2: Fix DMA cache alignment issues
usb: dwc2: host: Fix wMaxPacketSize handling (fix webcam regression)
ARM64: trivial: s/TIF_SECOMP/TIF_SECCOMP/ comment typo fix
drm/komeda: Potential error pointer dereference
drm/komeda: remove set but not used variable 'kcrtc'
x86/CPU: Add more Icelake model numbers
hwmon: (pmbus/core) Treat parameters as paged if on multiple pages
hwmon: (pmbus/core) mutex_lock write in pmbus_set_samples
hwmon: (core) add thermal sensors only if dev->of_node is present
Revert "fib_rules: return 0 directly if an exactly same rule exists when NLM_F_EXCL not supplied"
net: aquantia: fix wol configuration not applied sometimes
ethtool: fix potential userspace buffer overflow
Fix memory leak in sctp_process_init
net: rds: fix memory leak when unload rds_rdma
ipv6: fix the check before getting the cookie in rt6_get_cookie
ipv4: not do cache for local delivery if bc_forwarding is enabled
selftests: vm: Fix test build failure when built by itself
tools: bpftool: Fix JSON output when lookup fails
mmc: also set max_segment_size in the device
mtip32xx: also set max_segment_size in the device
rsxx: don't call dma_set_max_seg_size
nvme-pci: don't limit DMA segement size
s390/qeth: handle error when updating TX queue count
s390/qeth: fix VLAN attribute in bridge_hostnotify udev event
s390/qeth: check dst entry before use
s390/qeth: handle limited IPv4 broadcast in L3 TX path
ceph: fix error handling in ceph_get_caps()
ceph: avoid iput_final() while holding mutex or in dispatch thread
ceph: single workqueue for inode related works
cgroup: css_task_iter_skip()'d iterators must be advanced before accessed
drm/amd/amdgpu: add RLC firmware to support raven1 refresh
drm/amd/powerplay: add set_power_profile_mode for raven1_refresh
drm/amdgpu: fix ring test failure issue during s3 in vce 3.0 (V2)
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 450
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 449
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 448
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 446
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 445
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 444
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 443
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 442
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 441
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 440
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 438
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 437
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 436
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 435
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 434
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 433
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 432
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 431
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 430
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 429
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 428
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 426
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 424
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 423
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 422
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 421
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 420
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 419
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 418
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 417
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 416
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 414
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 412
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 411
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 410
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 409
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 408
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 407
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 406
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 405
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 404
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 403
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 402
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 401
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 400
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 399
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 398
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 397
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 396
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 395
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 394
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 393
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 392
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 391
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 390
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 389
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 388
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 387
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 380
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 378
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 377
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 376
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 375
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 373
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 372
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 371
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 370
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 367
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 365
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 364
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 363
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 362
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 354
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 353
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 352
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 351
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 350
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 349
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 348
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 347
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 346
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 345
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 344
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 343
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 342
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 341
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 340
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 339
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 338
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 336
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 335
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 334
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 333
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 332
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 330
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 328
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 326
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 325
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 324
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 323
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 322
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 321
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 320
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 316
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 315
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 314
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 313
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 312
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 311
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 310
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 309
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 308
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 307
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 305
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 301
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 300
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 299
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 297
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 296
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 295
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 294
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 292
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 291
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 290
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 289
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 288
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 287
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 286
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 285
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 284
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 283
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 282
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 281
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 280
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 278
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 277
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 276
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 275
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 274
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 273
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 272
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 271
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 270
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 269
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 268
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 267
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 266
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 265
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 264
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 263
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 262
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 260
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 258
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 257
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 256
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 254
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 253
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 252
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 251
lib/test_stackinit: Handle Clang auto-initialization pattern
block: Drop unlikely before IS_ERR(_OR_NULL)
xen/swiotlb: don't initialize swiotlb twice on arm64
s390/mm: fix address space detection in exception handling
HID: logitech-dj: Fix 064d:c52f receiver support
Revert "HID: core: Call request_module before doing device_add"
Revert "HID: core: Do not call request_module() in async context"
Revert "HID: Increase maximum report size allowed by hid_field_extract()"
tests: fix pidfd-test compilation
signal: improve comments
samples: fix pidfd-metadata compilation
arm64: arch_timer: mark functions as __always_inline
arm64: smp: Moved cpu_logical_map[] to smp.h
arm64: cpufeature: Fix missing ZFR0 in __read_sysreg_by_encoding()
selftests/bpf: move test_lirc_mode2_user to TEST_GEN_PROGS_EXTENDED
USB: Fix chipmunk-like voice when using Logitech C270 for recording audio.
USB: usb-storage: Add new ID to ums-realtek
udmabuf: actually unmap the scatterlist
net: fix indirect calls helpers for ptype list hooks.
net: ipvlan: Fix ipvlan device tso disabled while NETIF_F_IP_CSUM is set
scsi: smartpqi: unlock on error in pqi_submit_raid_request_synchronous()
scsi: ufs: Check that space was properly alloced in copy_query_response
udp: only choose unbound UDP socket for multicast when not in a VRF
net/tls: replace the sleeping lock around RX resync with a bit lock
Revert "net/tls: avoid NULL-deref on resync during device removal"
block: aoe: no need to check return value of debugfs_create functions
net: dsa: sja1105: Fix link speed not working at 100 Mbps and below
net: phylink: avoid reducing support mask
scripts/checkstack.pl: Fix arm64 wrong or unknown architecture
kbuild: tar-pkg: enable communication with jobserver
kconfig: tests: fix recursive inclusion unit test
kbuild: teach kselftest-merge to find nested config files
nvmet: fix data_len to 0 for bdev-backed write_zeroes
MAINTAINERS: Hand over skd maintainership
ASoC: sun4i-i2s: Add offset to RX channel select
ASoC: sun4i-i2s: Fix sun8i tx channel offset mask
ASoC: max98090: remove 24-bit format support if RJ is 0
ASoC: da7219: Fix build error without CONFIG_I2C
ASoC: SOF: Intel: hda: Fix COMPILE_TEST build error
drm/arm/hdlcd: Allow a bit of clock tolerance
drm/arm/hdlcd: Actually validate CRTC modes
drm/arm/mali-dp: Add a loop around the second set CVAL and try 5 times
drm/komeda: fixing of DMA mapping sg segment warning
netfilter: ipv6: nf_defrag: fix leakage of unqueued fragments
habanalabs: Read upper bits of trace buffer from RWPHI
arm64: arch_k3: Fix kconfig dependency warning
drm: don't block fb changes for async plane updates
drm/vc4: fix fb references in async update
drm/msm: fix fb references in async update
drm/amd: fix fb references in async update
drm/rockchip: fix fb references in async update
xen-blkfront: switch kcalloc to kvcalloc for large array allocation
drm/mediatek: call mtk_dsi_stop() after mtk_drm_crtc_atomic_disable()
drm/mediatek: clear num_pipes when unbind driver
drm/mediatek: call drm_atomic_helper_shutdown() when unbinding driver
drm/mediatek: unbind components in mtk_drm_unbind()
drm/mediatek: fix unbind functions
net: sfp: read eeprom in maximum 16 byte increments
selftests: set sysctl bc_forwarding properly in router_broadcast.sh
ANDROID: update gki aarch64 ABI representation
net: ethernet: mediatek: Use NET_IP_ALIGN to judge if HW RX_2BYTE_OFFSET is enabled
net: ethernet: mediatek: Use hw_feature to judge if HWLRO is supported
net: ethernet: ti: cpsw_ethtool: fix ethtool ring param set
ANDROID: gki_defconfig: Enable CMA, SLAB_FREELIST (RANDOM and HARDENED) on x86
bpf: udp: Avoid calling reuseport's bpf_prog from udp_gro
bpf: udp: ipv6: Avoid running reuseport's bpf_prog from __udp6_lib_err
rcu: locking and unlocking need to always be at least barriers
ANDROID: gki_defconfig: enable SLAB_FREELIST_RANDOM, SLAB_FREELIST_HARDENED
ANDROID: gki_defconfig: enable CMA and increase CMA_AREAS
ASoC: SOF: fix DSP oops definitions in FW ABI
ASoC: hda: fix unbalanced codec dev refcount for HDA_DEV_ASOC
ASoC: SOF: ipc: replace fw ready bitfield with explicit bit ordering
ASoC: SOF: bump to ABI 3.6
ASoC: SOF: soundwire: add initial soundwire support
ASoC: SOF: uapi: mirror firmware changes
ASoC: Intel: Baytrail: add quirk for Aegex 10 (RU2) tablet
xfs: inode btree scrubber should calculate im_boffset correctly
mmc: sdhci_am654: Fix SLOTTYPE write
usb: typec: ucsi: ccg: fix memory leak in do_flash
ANDROID: update gki aarch64 ABI representation
habanalabs: Fix virtual address access via debugfs for 2MB pages
drm/komeda: Constify the usage of komeda_component/pipeline/dev_funcs
x86/power: Fix 'nosmt' vs hibernation triple fault during resume
mm/vmalloc: Avoid rare case of flushing TLB with weird arguments
mm/vmalloc: Fix calculation of direct map addr range
PM: sleep: Add kerneldoc comments to some functions
drm/i915/gvt: save RING_HEAD into vreg when vgpu switched out
sparc: perf: fix updated event period in response to PERF_EVENT_IOC_PERIOD
mdesc: fix a missing-check bug in get_vdev_port_node_info()
drm/i915/gvt: add F_CMD_ACCESS flag for wa regs
sparc64: Fix regression in non-hypervisor TLB flush xcall
packet: unconditionally free po->rollover
Update my email address
net: hns: Fix loopback test failed at copper ports
Linux 5.2-rc3
net: dsa: mv88e6xxx: avoid error message on remove from VLAN 0
mm, compaction: make sure we isolate a valid PFN
include/linux/generic-radix-tree.h: fix kerneldoc comment
kernel/signal.c: trace_signal_deliver when signal_group_exit
drivers/iommu/intel-iommu.c: fix variable 'iommu' set but not used
spdxcheck.py: fix directory structures
kasan: initialize tag to 0xff in __kasan_kmalloc
z3fold: fix sheduling while atomic
scripts/gdb: fix invocation when CONFIG_COMMON_CLK is not set
mm/gup: continue VM_FAULT_RETRY processing even for pre-faults
ocfs2: fix error path kobject memory leak
memcg: make it work on sparse non-0-node systems
mm, memcg: consider subtrees in memory.events
prctl_set_mm: downgrade mmap_sem to read lock
prctl_set_mm: refactor checks from validate_prctl_map
kernel/fork.c: make max_threads symbol static
arch/arm/boot/compressed/decompress.c: fix build error due to lz4 changes
arch/parisc/configs/c8000_defconfig: remove obsoleted CONFIG_DEBUG_SLAB_LEAK
mm/vmalloc.c: fix typo in comment
lib/sort.c: fix kernel-doc notation warnings
mm: fix Documentation/vm/hmm.rst Sphinx warnings
treewide: fix typos of SPDX-License-Identifier
crypto: ux500 - fix license comment syntax error
MAINTAINERS: add I2C DT bindings to ARM platforms
MAINTAINERS: add DT bindings to i2c drivers
mwifiex: Fix heap overflow in mwifiex_uap_parse_tail_ies()
iwlwifi: mvm: change TLC config cmd sent by rs to be async
iwlwifi: Fix double-free problems in iwl_req_fw_callback()
iwlwifi: fix AX201 killer sku loading firmware issue
iwlwifi: print fseq info upon fw assert
iwlwifi: clear persistence bit according to device family
iwlwifi: fix load in rfkill flow for unified firmware
iwlwifi: mvm: remove d3_sram debugfs file
bpf, riscv: clear high 32 bits for ALU32 add/sub/neg/lsh/rsh/arsh
libbpf: Return btf_fd for load_sk_storage_btf
HID: a4tech: fix horizontal scrolling
HID: hyperv: Add a module description line
net: dsa: sja1105: Don't store frame type in skb->cb
block: print offending values when cloned rq limits are exceeded
blk-mq: Document the blk_mq_hw_queue_to_node() arguments
blk-mq: Fix spelling in a source code comment
block: Fix bsg_setup_queue() kernel-doc header
block: Fix rq_qos_wait() kernel-doc header
block: Fix blk_mq_*_map_queues() kernel-doc headers
block: Fix throtl_pending_timer_fn() kernel-doc header
block: Convert blk_invalidate_devt() header into a non-kernel-doc header
block/partitions/ldm: Convert a kernel-doc header into a non-kernel-doc header
leds: avoid flush_work in atomic context
cgroup: Include dying leaders with live threads in PROCS iterations
cgroup: Implement css_task_iter_skip()
cgroup: Call cgroup_release() before __exit_signal()
netfilter: nf_tables: fix module autoload with inet family
Revert "lockd: Show pid of lockd for remote locks"
ALSA: hda/realtek - Update headset mode for ALC256
fs/adfs: fix filename fixup handling for "/" and "//" names
fs/adfs: move append_filetype_suffix() into adfs_object_fixup()
fs/adfs: remove truncated filename hashing
fs/adfs: factor out filename fixup
fs/adfs: factor out object fixups
fs/adfs: factor out filename case lowering
fs/adfs: factor out filename comparison
ovl: doc: add non-standard corner cases
pstore/ram: Run without kernel crash dump region
MAINTAINERS: add Vasily Gorbik and Christian Borntraeger for s390
MAINTAINERS: Farewell Martin Schwidefsky
pstore: Set tfm to NULL on free_buf_for_compression
nds32: add new emulations for floating point instruction
nds32: Avoid IEX status being incorrectly modified
math-emu: Use statement expressions to fix Wshift-count-overflow warning
net: correct zerocopy refcnt with udp MSG_MORE
ethtool: Check for vlan etype or vlan tci when parsing flow_rule
net: don't clear sock->sk early to avoid trouble in strparser
net-gro: fix use-after-free read in napi_gro_frags()
net: dsa: tag_8021q: Create a stable binary format
net: dsa: tag_8021q: Change order of rx_vid setup
net: mvpp2: fix bad MVPP2_TXQ_SCHED_TOKEN_CNTR_REG queue value
docs cgroups: add another example size for hugetlb
NFSv4.1: Fix bug only first CB_NOTIFY_LOCK is handled
NFSv4.1: Again fix a race where CB_NOTIFY_LOCK fails to wake a waiter
ipv4: tcp_input: fix stack out of bounds when parsing TCP options.
mlxsw: spectrum: Prevent force of 56G
mlxsw: spectrum_acl: Avoid warning after identical rules insertion
SUNRPC: Fix a use after free when a server rejects the RPCSEC_GSS credential
net: dsa: mv88e6xxx: fix handling of upper half of STATS_TYPE_PORT
SUNRPC fix regression in umount of a secure mount
r8169: fix MAC address being lost in PCI D3
treewide: Add SPDX license identifier - Kbuild
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 225
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 224
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 223
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 222
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 221
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 220
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 218
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 217
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 216
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 215
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 214
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 213
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 211
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 210
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 209
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 207
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 206
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 203
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 201
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 200
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 199
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 198
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 197
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 195
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 194
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 193
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 191
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 190
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 188
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 185
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 183
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 182
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 180
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 179
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 178
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 177
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 176
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 175
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 174
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 173
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 172
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 171
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 170
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 167
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 166
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 165
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 164
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 162
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 161
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 160
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 159
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 158
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 157
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 156
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 155
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 154
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 153
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 152
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 151
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 150
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 149
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 148
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 147
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 145
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 144
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 143
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 142
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 140
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 139
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 138
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 137
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 136
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 135
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 133
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 132
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 131
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 130
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 129
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 128
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 127
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 126
net: core: support XDP generic on stacked devices.
netvsc: unshare skb in VF rx handler
udp: Avoid post-GRO UDP checksum recalculation
nvme-tcp: fix queue mapping when queue count is limited
nvme-rdma: fix queue mapping when queue count is limited
fpga: zynqmp-fpga: Correctly handle error pointer
selftests: vm: install test_vmalloc.sh for run_vmtests
userfaultfd: selftest: fix compiler warning
kselftest/cgroup: fix incorrect test_core skip
kselftest/cgroup: fix unexpected testing failure on test_core
kselftest/cgroup: fix unexpected testing failure on test_memcontrol
xtensa: Fix section mismatch between memblock_reserve and mem_reserve
signal/ptrace: Don't leak unitialized kernel memory with PTRACE_PEEK_SIGINFO
mwifiex: Abort at too short BSS descriptor element
mwifiex: Fix possible buffer overflows at parsing bss descriptor
drm/i915/gvt: Assign NULL to the pointer after memory free.
drm/i915/gvt: Check if cur_pt_type is valid
x86: intel_epb: Do not build when CONFIG_PM is unset
crypto: hmac - fix memory leak in hmac_init_tfm()
crypto: jitterentropy - change back to module_init()
ARM: dts: Drop bogus CLKSEL for timer12 on dra7
KVM: PPC: Book3S HV: Restore SPRG3 in kvmhv_p9_guest_entry()
KVM: PPC: Book3S HV: Fix lockdep warning when entering guest on POWER9
KVM: PPC: Book3S HV: XIVE: Fix page offset when clearing ESB pages
KVM: PPC: Book3S HV: XIVE: Take the srcu read lock when accessing memslots
KVM: PPC: Book3S HV: XIVE: Do not clear IRQ data of passthrough interrupts
KVM: PPC: Book3S HV: XIVE: Introduce a new mutex for the XIVE device
drm/i915/gvt: Fix cmd length of VEB_DI_IECP
drm/i915/gvt: refine ggtt range validation
drm/i915/gvt: Fix vGPU CSFE_CHICKEN1_REG mmio handler
drm/i915/gvt: Fix GFX_MODE handling
drm/i915/gvt: Update force-to-nonpriv register whitelist
drm/i915/gvt: Initialize intel_gvt_gtt_entry in stack
ima: show rules with IMA_INMASK correctly
evm: check hash algorithm passed to init_desc()
scsi: libsas: delete sas port if expander discover failed
scsi: libsas: only clear phy->in_shutdown after shutdown event done
scsi: scsi_dh_alua: Fix possible null-ptr-deref
scsi: smartpqi: properly set both the DMA mask and the coherent DMA mask
scsi: zfcp: fix to prevent port_remove with pure auto scan LUNs (only sdevs)
scsi: zfcp: fix missing zfcp_port reference put on -EBUSY from port_remove
scsi: libcxgbi: add a check for NULL pointer in cxgbi_check_route()
net: phy: dp83867: Set up RGMII TX delay
net: phy: dp83867: do not call config_init twice
net: phy: dp83867: increase SGMII autoneg timer duration
net: phy: dp83867: fix speed 10 in sgmii mode
net: phy: marvell10g: report if the PHY fails to boot firmware
net: phylink: ensure consistent phy interface mode
cgroup: Use css_tryget() instead of css_tryget_online() in task_get_css()
blk-mq: Fix memory leak in error handling
usbip: usbip_host: fix stub_dev lock context imbalance regression
net: sh_eth: fix mdio access in sh_eth_close() for R-Car Gen2 and RZ/A1 SoCs
MIPS: uprobes: remove set but not used variable 'epc'
s390/crypto: fix possible sleep during spinlock aquired
MIPS: pistachio: Build uImage.gz by default
MIPS: Make virt_addr_valid() return bool
MIPS: Bounds check virt_addr_valid
CIFS: cifs_read_allocate_pages: don't iterate through whole page array on ENOMEM
RDMA/efa: Remove MAYEXEC flag check from mmap flow
mlx5: avoid 64-bit division
IB/hfi1: Validate page aligned for a given virtual address
IB/{qib, hfi1, rdmavt}: Correct ibv_devinfo max_mr value
IB/hfi1: Insure freeze_work work_struct is canceled on shutdown
IB/rdmavt: Fix alloc_qpn() WARN_ON()
ASoC: sun4i-codec: fix first delay on Speaker
drm/amdgpu: reserve stollen vram for raven series
media: venus: hfi_parser: fix a regression in parser
selftests: bpf: fix compiler warning in flow_dissector test
arm64: use the correct function type for __arm64_sys_ni_syscall
arm64: use the correct function type in SYSCALL_DEFINE0
arm64: fix syscall_fn_t type
block: don't protect generic_make_request_checks with blk_queue_enter
block: move blk_exit_queue into __blk_release_queue
selftests: bpf: complete sub-register zero extension checks
selftests: bpf: move sub-register zero extension checks into subreg.c
ovl: detect overlapping layers
drm/i915/icl: Add WaDisableBankHangMode
ALSA: fireface: Use ULL suffixes for 64-bit constants
signal/arm64: Use force_sig not force_sig_fault for SIGKILL
nl80211: fill all policy .type entries
mac80211: free peer keys before vif down in mesh
ANDROID: ABI out: Use the extension .xml rather then .out
drm/mediatek: respect page offset for PRIME mmap calls
drm/mediatek: adjust ddp clock control flow
ALSA: hda/realtek - Improve the headset mic for Acer Aspire laptops
KVM: PPC: Book3S HV: XIVE: Fix the enforced limit on the vCPU identifier
KVM: PPC: Book3S HV: XIVE: Do not test the EQ flag validity when resetting
KVM: PPC: Book3S HV: XIVE: Clear file mapping when device is released
KVM: PPC: Book3S HV: Don't take kvm->lock around kvm_for_each_vcpu
KVM: PPC: Book3S: Use new mutex to synchronize access to rtas token list
KVM: PPC: Book3S HV: Use new mutex to synchronize MMU setup
KVM: PPC: Book3S HV: Avoid touching arch.mmu_ready in XIVE release functions
Revert "drivers: thermal: tsens: Add new operation to check if a sensor is enabled"
net/mlx5e: Disable rxhash when CQE compress is enabled
net/mlx5e: restrict the real_dev of vlan device is the same as uplink device
net/mlx5: Allocate root ns memory using kzalloc to match kfree
net/mlx5: Avoid double free in fs init error unwinding path
net/mlx5: Avoid double free of root ns in the error flow path
net/mlx5: Fix error handling in mlx5_load()
Documentation: net-sysfs: Remove duplicate PHY device documentation
llc: fix skb leak in llc_build_and_send_ui_pkt()
selftests: pmtu: Fix encapsulating device in pmtu_vti6_link_change_mtu
dfs_cache: fix a wrong use of kfree in flush_cache_ent()
fs/cifs/smb2pdu.c: fix buffer free in SMB2_ioctl_free
cifs: fix memory leak of pneg_inbuf on -EOPNOTSUPP ioctl case
xenbus: Avoid deadlock during suspend due to open transactions
xen/pvcalls: Remove set but not used variable
tracing: Avoid memory leak in predicate_parse()
habanalabs: fix bug in checking huge page optimization
mmc: sdhci: Fix SDIO IRQ thread deadlock
dpaa_eth: use only online CPU portals
net: mvneta: Fix err code path of probe
net: stmmac: Do not output error on deferred probe
Btrfs: fix race updating log root item during fsync
Btrfs: fix wrong ctime and mtime of a directory after log replay
ARC: [plat-hsdk] Get rid of inappropriate PHY settings
ARC: [plat-hsdk]: Add support of Vivante GPU
ARC: [plat-hsdk]: enable creg-gpio controller
Btrfs: fix fsync not persisting changed attributes of a directory
btrfs: qgroup: Check bg while resuming relocation to avoid NULL pointer dereference
btrfs: reloc: Also queue orphan reloc tree for cleanup to avoid BUG_ON()
Btrfs: incremental send, fix emission of invalid clone operations
Btrfs: incremental send, fix file corruption when no-holes feature is enabled
btrfs: correct zstd workspace manager lock to use spin_lock_bh()
btrfs: Ensure replaced device doesn't have pending chunk allocation
ia64: fix build errors by exporting paddr_to_nid()
ASoC: SOF: Intel: hda: fix the hda init chip
ASoC: SOF: ipc: fix a race, leading to IPC timeouts
ASoC: SOF: control: correct the copy size for bytes kcontrol put
ASoC: SOF: pcm: remove warning - initialize workqueue on open
ASoC: SOF: pcm: clear hw_params_upon_resume flag correctly
ASoC: SOF: core: fix error handling with the probe workqueue
ASoC: SOF: core: remove snd_soc_unregister_component in case of error
ASoC: SOF: core: remove DSP after unregistering machine driver
ASoC: soc-core: fixup references at soc_cleanup_card_resources()
arm64/module: revert to unsigned interpretation of ABS16/32 relocations
KVM: s390: Do not report unusabled IDs via KVM_CAP_MAX_VCPU_ID
kvm: fix compile on s390 part 2
xprtrdma: Use struct_size() in kzalloc()
tools headers UAPI: Sync kvm.h headers with the kernel sources
perf record: Fix s390 missing module symbol and warning for non-root users
perf machine: Read also the end of the kernel
perf test vmlinux-kallsyms: Ignore aliases to _etext when searching on kallsyms
perf session: Add missing swap ops for namespace events
perf namespace: Protect reading thread's namespace
tools headers UAPI: Sync drm/drm.h with the kernel
s390/crypto: fix gcm-aes-s390 selftest failures
s390/zcrypt: Fix wrong dispatching for control domain CPRBs
s390/pci: fix assignment of bus resources
s390/pci: fix struct definition for set PCI function
s390: mark __cpacf_check_opcode() and cpacf_query_func() as __always_inline
s390: add unreachable() to dump_fault_info() to fix -Wmaybe-uninitialized
tools headers UAPI: Sync drm/i915_drm.h with the kernel
tools headers UAPI: Sync linux/fs.h with the kernel
tools headers UAPI: Sync linux/sched.h with the kernel
tools arch x86: Sync asm/cpufeatures.h with the with the kernel
tools include UAPI: Update copy of files related to new fspick, fsmount, fsconfig, fsopen, move_mount and open_tree syscalls
perf arm64: Fix mksyscalltbl when system kernel headers are ahead of the kernel
perf data: Fix 'strncat may truncate' build failure with recent gcc
arm64: Fix the arm64_personality() syscall wrapper redirection
rtw88: Make some symbols static
rtw88: avoid circular locking between local->iflist_mtx and rtwdev->mutex
rsi: Properly initialize data in rsi_sdio_ta_reset
rtw88: fix unassigned rssi_level in rtw_sta_info
rtw88: fix subscript above array bounds compiler warning
fuse: extract helper for range writeback
fuse: fix copy_file_range() in the writeback case
mmc: meson-gx: fix irq ack
mmc: tmio: fix SCC error handling to avoid false positive CRC error
mmc: tegra: Fix a warning message
memstick: mspro_block: Fix an error code in mspro_block_issue_req()
mac80211: mesh: fix RCU warning
nl80211: fix station_info pertid memory leak
mac80211: Do not use stack memory with scatterlist for GMAC
ALSA: line6: Assure canceling delayed work at disconnection
configfs: Fix use-after-free when accessing sd->s_dentry
ALSA: hda - Force polling mode on CNL for fixing codec communication
i2c: synquacer: fix synquacer_i2c_doxfer() return value
i2c: mlxcpld: Fix wrong initialization order in probe
i2c: dev: fix potential memory leak in i2cdev_ioctl_rdwr
RDMA/core: Fix panic when port_data isn't initialized
RDMA/uverbs: Pass udata on uverbs error unwind
RDMA/core: Clear out the udata before error unwind
net: aquantia: tcp checksum 0xffff being handled incorrectly
net: aquantia: fix LRO with FCS error
net: aquantia: check rx csum for all packets in LRO session
net: aquantia: tx clean budget logic error
vhost: scsi: add weight support
vhost: vsock: add weight support
vhost_net: fix possible infinite loop
vhost: introduce vhost_exceeds_weight()
virtio: Fix indentation of VIRTIO_MMIO
virtio: add unlikely() to WARN_ON_ONCE()
iommu/vt-d: Set the right field for Page Walk Snoop
iommu/vt-d: Fix lock inversion between iommu->lock and device_domain_lock
iommu: Add missing new line for dma type
drm/etnaviv: lock MMU while dumping core
block: Don't revalidate bdev of hidden gendisk
loop: Don't change loop device under exclusive opener
drm/imx: ipuv3-plane: fix atomic update status query for non-plus i.MX6Q
drm/qxl: drop WARN_ONCE()
iio: temperature: mlx90632 Relax the compatibility check
iio: imu: st_lsm6dsx: fix PM support for st_lsm6dsx i2c controller
staging:iio:ad7150: fix threshold mode config bit
fuse: add FUSE_WRITE_KILL_PRIV
fuse: fallocate: fix return with locked inode
PCI: PM: Avoid possible suspend-to-idle issue
ACPI: PM: Call pm_set_suspend_via_firmware() during hibernation
ACPI/PCI: PM: Add missing wakeup.flags.valid checks
ovl: support the FS_IOC_FS[SG]ETXATTR ioctls
soundwire: stream: fix out of boundary access on port properties
net: tulip: de4x5: Drop redundant MODULE_DEVICE_TABLE()
selftests/tls: add test for sleeping even though there is data
net/tls: fix no wakeup on partial reads
selftests/tls: test for lowat overshoot with multiple records
net/tls: fix lowat calculation if some data came from previous record
dpaa2-eth: Make constant 64-bit long
dpaa2-eth: Use PTR_ERR_OR_ZERO where appropriate
dpaa2-eth: Fix potential spectre issue
bonding/802.3ad: fix slave link initialization transition states
io_uring: Fix __io_uring_register() false success
net: ethtool: Document get_rxfh_context and set_rxfh_context ethtool ops
net: stmmac: dwmac-mediatek: modify csr_clk value to fix mdio read/write fail
net: stmmac: fix csr_clk can't be zero issue
net: stmmac: update rx tail pointer register to fix rx dma hang issue.
ip_sockglue: Fix missing-check bug in ip_ra_control()
ipv6_sockglue: Fix a missing-check bug in ip6_ra_control()
efi: Allow the number of EFI configuration tables entries to be zero
efi/x86/Add missing error handling to old_memmap 1:1 mapping code
parisc: Fix compiler warnings in float emulation code
parisc/slab: cleanup after /proc/slab_allocators removal
bpf: sockmap, fix use after free from sleep in psock backlog workqueue
net: sched: don't use tc_action->order during action dump
cxgb4: Revert "cxgb4: Remove SGE_HOST_PAGE_SIZE dependency on page size"
net: fec: fix the clk mismatch in failed_reset path
habanalabs: Avoid using a non-initialized MMU cache mutex
habanalabs: fix debugfs code
uapi/habanalabs: add opcode for enable/disable device debug mode
habanalabs: halt debug engines on user process close
selftests: rtc: rtctest: specify timeouts
selftests/harness: Allow test to configure timeout
selftests/ftrace: Add checkbashisms meta-testcase
selftests/ftrace: Make a script checkbashisms clean
media: smsusb: better handle optional alignment
test_firmware: Use correct snprintf() limit
genwqe: Prevent an integer overflow in the ioctl
parport: Fix mem leak in parport_register_dev_model
fpga: dfl: expand minor range when registering chrdev region
fpga: dfl: Add lockdep classes for pdata->lock
fpga: dfl: afu: Pass the correct device to dma_mapping_error()
fpga: stratix10-soc: fix use-after-free on s10_init()
w1: ds2408: Fix typo after 49695ac468
(reset on output_write retry with readback)
kheaders: Do not regenerate archive if config is not changed
kheaders: Move from proc to sysfs
drm/amd/display: Don't load DMCU for Raven 1 (v2)
drm/i915: Maintain consistent documentation subsection ordering
scripts/sphinx-pre-install: make it handle Sphinx versions
docs: Fix conf.py for Sphinx 2.0
vt/fbcon: deinitialize resources in visual_init() after failed memory allocation
xfs: fix broken log reservation debugging
clocksource/drivers/timer-ti-dm: Change to new style declaration
ASoC: core: lock client_mutex while removing link components
ASoC: simple-card: Restore original configuration of DAI format
{nl,mac}80211: allow 4addr AP operation on crypto controlled devices
mac80211_hwsim: mark expected switch fall-through
mac80211: fix rate reporting inside cfg80211_calculate_bitrate_he()
mac80211: remove set but not used variable 'old'
mac80211: handle deauthentication/disassociation from TDLS peer
gpio: fix gpio-adp5588 build errors
pinctrl: stmfx: Fix compile issue when CONFIG_OF_GPIO is not defined
staging: kpc2000: Add dependency on MFD_CORE to kconfig symbol 'KPC2000'
perf/ring-buffer: Use regular variables for nesting
perf/ring-buffer: Always use {READ,WRITE}_ONCE() for rb->user_page data
perf/ring_buffer: Add ordering to rb->nest increment
perf/ring_buffer: Fix exposing a temporarily decreased data_head
x86/CPU/AMD: Don't force the CPB cap when running under a hypervisor
x86/boot: Provide KASAN compatible aliases for string routines
ALSA: hda/realtek - Enable micmute LED for Huawei laptops
Input: uinput - add compat ioctl number translation for UI_*_FF_UPLOAD
Input: silead - add MSSL0017 to acpi_device_id
cxgb4: offload VLAN flows regardless of VLAN ethtype
hsr: fix don't prune the master node from the node_db
net: mvpp2: cls: Fix leaked ethtool_rx_flow_rule
docs: fix multiple doc build warnings in enumeration.rst
lib/list_sort: fix kerneldoc build error
docs: fix numaperf.rst and add it to the doc tree
doc: Cope with the deprecation of AutoReporter
doc: Cope with Sphinx logging deprecations
bpf: sockmap, restore sk_write_space when psock gets dropped
selftests: bpf: add zero extend checks for ALU32 and/or/xor
bpf, riscv: clear target register high 32-bits for and/or/xor on ALU32
spi: abort spi_sync if failed to prepare_transfer_hardware
ALSA: hda/realtek - Set default power save node to 0
ipv4/igmp: fix build error if !CONFIG_IP_MULTICAST
powerpc/kexec: Fix loading of kernel + initramfs with kexec_file_load()
MIPS: TXx9: Fix boot crash in free_initmem()
MIPS: remove a space after -I to cope with header search paths for VDSO
MIPS: mark ginvt() as __always_inline
ipv4/igmp: fix another memory leak in igmpv3_del_delrec()
bnxt_en: Device serial number is supported only for PFs.
bnxt_en: Reduce memory usage when running in kdump kernel.
bnxt_en: Fix possible BUG() condition when calling pci_disable_msix().
bnxt_en: Fix aggregation buffer leak under OOM condition.
ipv6: Fix redirect with VRF
net: stmmac: fix reset gpio free missing
mISDN: make sure device name is NUL terminated
net: macb: save/restore the remaining registers and features
media: dvb: warning about dvb frequency limits produces too much noise
net/tls: don't ignore netdev notifications if no TLS features
net/tls: fix state removal with feature flags off
net/tls: avoid NULL-deref on resync during device removal
Documentation: add TLS offload documentation
Documentation: tls: RSTify the ktls documentation
Documentation: net: move device drivers docs to a submenu
mISDN: Fix indenting in dsp_cmx.c
ocelot: Dont allocate another multicast list, use __dev_mc_sync
Validate required parameters in inet6_validate_link_af
xhci: Use %zu for printing size_t type
xhci: Convert xhci_handshake() to use readl_poll_timeout_atomic()
xhci: Fix immediate data transfer if buffer is already DMA mapped
usb: xhci: avoid null pointer deref when bos field is NULL
usb: xhci: Fix a potential null pointer dereference in xhci_debugfs_create_endpoint()
xhci: update bounce buffer with correct sg num
media: usb: siano: Fix false-positive "uninitialized variable" warning
spi: spi-fsl-spi: call spi_finalize_current_message() at the end
ALSA: hda/realtek - Check headset type by unplug and resume
powerpc/perf: Fix MMCRA corruption by bhrb_filter
powerpc/powernv: Return for invalid IMC domain
HID: logitech-hidpp: Add support for the S510 remote control
HID: multitouch: handle faulty Elo touch device
selftests: netfilter: add flowtable test script
netfilter: nft_flow_offload: IPCB is only valid for ipv4 family
netfilter: nft_flow_offload: don't offload when sequence numbers need adjustment
netfilter: nft_flow_offload: set liberal tracking mode for tcp
netfilter: nf_flow_table: ignore DF bit setting
ASoC: Intel: sof-rt5682: fix AMP quirk support
ASoC: Intel: sof-rt5682: fix for codec button mapping
clk: ti: clkctrl: Fix clkdm_clk handling
clk: imx: imx8mm: fix int pll clk gate
clk: sifive: restrict Kconfig scope for the FU540 PRCI driver
RDMA/hns: Fix PD memory leak for internal allocation
netfilter: nat: fix udp checksum corruption
selftests: netfilter: missing error check when setting up veth interface
RDMA/srp: Rename SRP sysfs name after IB device rename trigger
ipvs: Fix use-after-free in ip_vs_in
ARC: [plat-hsdk]: Add missing FIFO size entry in GMAC node
ARC: [plat-hsdk]: Add missing multicast filter bins number to GMAC node
samples, bpf: suppress compiler warning
samples, bpf: fix to change the buffer size for read()
bpf: Check sk_fullsock() before returning from bpf_sk_lookup()
bpf: fix out-of-bounds read in __bpf_skc_lookup
Documentation/networking: fix af_xdp.rst Sphinx warnings
netfilter: nft_fib: Fix existence check support
netfilter: nf_queue: fix reinject verdict handling
dmaengine: sprd: Add interrupt support for 2-stage transfer
dmaengine: sprd: Fix the right place to configure 2-stage transfer
dmaengine: sprd: Fix block length overflow
dmaengine: sprd: Fix the incorrect start for 2-stage destination channels
dmaengine: sprd: Add validation of current descriptor in irq handler
dmaengine: sprd: Fix the possible crash when getting descriptor status
tty: max310x: Fix external crystal register setup
serial: sh-sci: disable DMA for uart_console
serial: imx: remove log spamming error message
tty: serial: msm_serial: Fix XON/XOFF
USB: serial: option: add Telit 0x1260 and 0x1261 compositions
USB: serial: pl2303: add Allied Telesis VT-Kit3
USB: serial: option: add support for Simcom SIM7500/SIM7600 RNDIS mode
dmaengine: tegra210-adma: Fix spelling
dmaengine: tegra210-adma: Fix channel FIFO configuration
dmaengine: tegra210-adma: Fix crash during probe
dmaengine: mediatek-cqdma: sleeping in atomic context
dmaengine: dw-axi-dmac: fix null dereference when pointer first is null
perf/x86/intel/ds: Fix EVENT vs. UEVENT PEBS constraints
USB: rio500: update Documentation
USB: rio500: simplify locking
USB: rio500: fix memory leak in close after disconnect
USB: rio500: refuse more than one device at a time
usbip: usbip_host: fix BUG: sleeping function called from invalid context
USB: sisusbvga: fix oops in error path of sisusb_probe
USB: Add LPM quirk for Surface Dock GigE adapter
media: usb: siano: Fix general protection fault in smsusb
usb: mtu3: fix up undefined reference to usb_debug_root
USB: Fix slab-out-of-bounds write in usb_get_bos_descriptor
Input: elantech - enable middle button support on 2 ThinkPads
dmaengine: fsl-qdma: Add improvement
dmaengine: jz4780: Fix transfers being ACKed too soon
gcc-plugins: Fix build failures under Darwin host
MAINTAINERS: Update Stefan Wahren email address
netfilter: nf_tables: fix oops during rule dump
ARC: mm: SIGSEGV userspace trying to access kernel virtual memory
ARC: fix build warnings
ARM: dts: bcm: Add missing device_type = "memory" property
soc: bcm: brcmstb: biuctrl: Register writes require a barrier
soc: brcmstb: Fix error path for unsupported CPUs
ARM: dts: dra71x: Disable usb4_tm target module
ARM: dts: dra71x: Disable rtc target module
ARM: dts: dra76x: Disable usb4_tm target module
ARM: dts: dra76x: Disable rtc target module
ASoC: simple-card: Fix configuration of DAI format
ASoC: Intel: soc-acpi: Fix machine selection order
ASoC: rt5677-spi: Handle over reading when flipping bytes
ASoC: soc-dpm: fixup DAI active unbalance
pinctrl: intel: Clear interrupt status in mask/unmask callback
pinctrl: intel: Use GENMASK() consistently
parisc: Allow building 64-bit kernel without -mlong-calls compiler option
parisc: Kconfig: remove ARCH_DISCARD_MEMBLOCK
staging: wilc1000: Fix some double unlock bugs in wilc_wlan_cleanup()
staging: vc04_services: prevent integer overflow in create_pagelist()
Staging: vc04_services: Fix a couple error codes
staging: wlan-ng: fix adapter initialization failure
staging: kpc2000: double unlock in error handling in kpc_dma_transfer()
staging: kpc2000: Fix build error without CONFIG_UIO
staging: kpc2000: fix build error on xtensa
staging: erofs: set sb->s_root to NULL when failing from __getname()
ARM: imx: cpuidle-imx6sx: Restrict the SW2ISO increase to i.MX6SX
firmware: imx: SCU irq should ONLY be enabled after SCU IPC is ready
arm64: imx: Fix build error without CONFIG_SOC_BUS
ima: fix wrong signed policy requirement when not appraising
x86/ima: Check EFI_RUNTIME_SERVICES before using
stacktrace: Unbreak stack_trace_save_tsk_reliable()
HID: wacom: Sync INTUOSP2_BT touch state after each frame if necessary
HID: wacom: Correct button numbering 2nd-gen Intuos Pro over Bluetooth
HID: wacom: Send BTN_TOUCH in response to INTUOSP2_BT eraser contact
HID: wacom: Don't report anything prior to the tool entering range
HID: wacom: Don't set tool type until we're in range
ASoC: cs42xx8: Add regcache mask dirty
regulator: tps6507x: Fix boot regression due to testing wrong init_data pointer
ASoC: fsl_asrc: Fix the issue about unsupported rate
spi: bitbang: Fix NULL pointer dereference in spi_unregister_master
Input: elan_i2c - increment wakeup count if wake source
wireless: Skip directory when generating certificates
ASoC: ak4458: rstn_control - return a non-zero on error only
ASoC: soc-pcm: BE dai needs prepare when pause release after resume
ASoC: ak4458: add return value for ak4458_probe
ASoC : cs4265 : readable register too low
ASoC: SOF: fix error in verbose ipc command parsing
ASoC: SOF: fix race in FW boot timeout handling
ASoC: SOF: nocodec: fix undefined reference
iio: adc: ti-ads8688: fix timestamp is not updated in buffer
iio: dac: ds4422/ds4424 fix chip verification
HID: rmi: Use SET_REPORT request on control endpoint for Acer Switch 3 and 5
HID: logitech-hidpp: add support for the MX5500 keyboard
HID: logitech-dj: add support for the Logitech MX5500's Bluetooth Mini-Receiver
HID: i2c-hid: add iBall Aer3 to descriptor override
spi: Fix Raspberry Pi breakage
ARM: dts: dra76x: Update MMC2_HS200_MANUAL1 iodelay values
ARM: dts: am57xx-idk: Remove support for voltage switching for SD card
bus: ti-sysc: Handle devices with no control registers
ARM: dts: Configure osc clock for d_can on am335x
iio: imu: mpu6050: Fix FIFO layout for ICM20602
lkdtm/bugs: Adjust recursion test to avoid elision
lkdtm/usercopy: Moves the KERNEL_DS test to non-canonical
iio: adc: ads124: avoid buffer overflow
iio: adc: modify NPCM ADC read reference voltage
Change-Id: I98c823993370027391cc21dfb239c3049f025136
Signed-off-by: Raghavendra Rao Ananta <rananta@codeaurora.org>
3878 lines
91 KiB
C
3878 lines
91 KiB
C
// SPDX-License-Identifier: GPL-2.0-or-later
|
|
/*
|
|
* Copyright (C) International Business Machines Corp., 2000-2005
|
|
*/
|
|
/*
|
|
* jfs_xtree.c: extent allocation descriptor B+-tree manager
|
|
*/
|
|
|
|
#include <linux/fs.h>
|
|
#include <linux/module.h>
|
|
#include <linux/quotaops.h>
|
|
#include <linux/seq_file.h>
|
|
#include "jfs_incore.h"
|
|
#include "jfs_filsys.h"
|
|
#include "jfs_metapage.h"
|
|
#include "jfs_dmap.h"
|
|
#include "jfs_dinode.h"
|
|
#include "jfs_superblock.h"
|
|
#include "jfs_debug.h"
|
|
|
|
/*
|
|
* xtree local flag
|
|
*/
|
|
#define XT_INSERT 0x00000001
|
|
|
|
/*
|
|
* xtree key/entry comparison: extent offset
|
|
*
|
|
* return:
|
|
* -1: k < start of extent
|
|
* 0: start_of_extent <= k <= end_of_extent
|
|
* 1: k > end_of_extent
|
|
*/
|
|
#define XT_CMP(CMP, K, X, OFFSET64)\
|
|
{\
|
|
OFFSET64 = offsetXAD(X);\
|
|
(CMP) = ((K) >= OFFSET64 + lengthXAD(X)) ? 1 :\
|
|
((K) < OFFSET64) ? -1 : 0;\
|
|
}
|
|
|
|
/* write a xad entry */
|
|
#define XT_PUTENTRY(XAD, FLAG, OFF, LEN, ADDR)\
|
|
{\
|
|
(XAD)->flag = (FLAG);\
|
|
XADoffset((XAD), (OFF));\
|
|
XADlength((XAD), (LEN));\
|
|
XADaddress((XAD), (ADDR));\
|
|
}
|
|
|
|
#define XT_PAGE(IP, MP) BT_PAGE(IP, MP, xtpage_t, i_xtroot)
|
|
|
|
/* get page buffer for specified block address */
|
|
/* ToDo: Replace this ugly macro with a function */
|
|
#define XT_GETPAGE(IP, BN, MP, SIZE, P, RC) \
|
|
do { \
|
|
BT_GETPAGE(IP, BN, MP, xtpage_t, SIZE, P, RC, i_xtroot); \
|
|
if (!(RC)) { \
|
|
if ((le16_to_cpu((P)->header.nextindex) < XTENTRYSTART) || \
|
|
(le16_to_cpu((P)->header.nextindex) > \
|
|
le16_to_cpu((P)->header.maxentry)) || \
|
|
(le16_to_cpu((P)->header.maxentry) > \
|
|
(((BN) == 0) ? XTROOTMAXSLOT : PSIZE >> L2XTSLOTSIZE))) { \
|
|
jfs_error((IP)->i_sb, \
|
|
"XT_GETPAGE: xtree page corrupt\n"); \
|
|
BT_PUTPAGE(MP); \
|
|
MP = NULL; \
|
|
RC = -EIO; \
|
|
} \
|
|
} \
|
|
} while (0)
|
|
|
|
/* for consistency */
|
|
#define XT_PUTPAGE(MP) BT_PUTPAGE(MP)
|
|
|
|
#define XT_GETSEARCH(IP, LEAF, BN, MP, P, INDEX) \
|
|
BT_GETSEARCH(IP, LEAF, BN, MP, xtpage_t, P, INDEX, i_xtroot)
|
|
/* xtree entry parameter descriptor */
|
|
struct xtsplit {
|
|
struct metapage *mp;
|
|
s16 index;
|
|
u8 flag;
|
|
s64 off;
|
|
s64 addr;
|
|
int len;
|
|
struct pxdlist *pxdlist;
|
|
};
|
|
|
|
|
|
/*
|
|
* statistics
|
|
*/
|
|
#ifdef CONFIG_JFS_STATISTICS
|
|
static struct {
|
|
uint search;
|
|
uint fastSearch;
|
|
uint split;
|
|
} xtStat;
|
|
#endif
|
|
|
|
|
|
/*
|
|
* forward references
|
|
*/
|
|
static int xtSearch(struct inode *ip, s64 xoff, s64 *next, int *cmpp,
|
|
struct btstack * btstack, int flag);
|
|
|
|
static int xtSplitUp(tid_t tid,
|
|
struct inode *ip,
|
|
struct xtsplit * split, struct btstack * btstack);
|
|
|
|
static int xtSplitPage(tid_t tid, struct inode *ip, struct xtsplit * split,
|
|
struct metapage ** rmpp, s64 * rbnp);
|
|
|
|
static int xtSplitRoot(tid_t tid, struct inode *ip,
|
|
struct xtsplit * split, struct metapage ** rmpp);
|
|
|
|
#ifdef _STILL_TO_PORT
|
|
static int xtDeleteUp(tid_t tid, struct inode *ip, struct metapage * fmp,
|
|
xtpage_t * fp, struct btstack * btstack);
|
|
|
|
static int xtSearchNode(struct inode *ip,
|
|
xad_t * xad,
|
|
int *cmpp, struct btstack * btstack, int flag);
|
|
|
|
static int xtRelink(tid_t tid, struct inode *ip, xtpage_t * fp);
|
|
#endif /* _STILL_TO_PORT */
|
|
|
|
/*
|
|
* xtLookup()
|
|
*
|
|
* function: map a single page into a physical extent;
|
|
*/
|
|
int xtLookup(struct inode *ip, s64 lstart,
|
|
s64 llen, int *pflag, s64 * paddr, s32 * plen, int no_check)
|
|
{
|
|
int rc = 0;
|
|
struct btstack btstack;
|
|
int cmp;
|
|
s64 bn;
|
|
struct metapage *mp;
|
|
xtpage_t *p;
|
|
int index;
|
|
xad_t *xad;
|
|
s64 next, size, xoff, xend;
|
|
int xlen;
|
|
s64 xaddr;
|
|
|
|
*paddr = 0;
|
|
*plen = llen;
|
|
|
|
if (!no_check) {
|
|
/* is lookup offset beyond eof ? */
|
|
size = ((u64) ip->i_size + (JFS_SBI(ip->i_sb)->bsize - 1)) >>
|
|
JFS_SBI(ip->i_sb)->l2bsize;
|
|
if (lstart >= size)
|
|
return 0;
|
|
}
|
|
|
|
/*
|
|
* search for the xad entry covering the logical extent
|
|
*/
|
|
//search:
|
|
if ((rc = xtSearch(ip, lstart, &next, &cmp, &btstack, 0))) {
|
|
jfs_err("xtLookup: xtSearch returned %d", rc);
|
|
return rc;
|
|
}
|
|
|
|
/*
|
|
* compute the physical extent covering logical extent
|
|
*
|
|
* N.B. search may have failed (e.g., hole in sparse file),
|
|
* and returned the index of the next entry.
|
|
*/
|
|
/* retrieve search result */
|
|
XT_GETSEARCH(ip, btstack.top, bn, mp, p, index);
|
|
|
|
/* is xad found covering start of logical extent ?
|
|
* lstart is a page start address,
|
|
* i.e., lstart cannot start in a hole;
|
|
*/
|
|
if (cmp) {
|
|
if (next)
|
|
*plen = min(next - lstart, llen);
|
|
goto out;
|
|
}
|
|
|
|
/*
|
|
* lxd covered by xad
|
|
*/
|
|
xad = &p->xad[index];
|
|
xoff = offsetXAD(xad);
|
|
xlen = lengthXAD(xad);
|
|
xend = xoff + xlen;
|
|
xaddr = addressXAD(xad);
|
|
|
|
/* initialize new pxd */
|
|
*pflag = xad->flag;
|
|
*paddr = xaddr + (lstart - xoff);
|
|
/* a page must be fully covered by an xad */
|
|
*plen = min(xend - lstart, llen);
|
|
|
|
out:
|
|
XT_PUTPAGE(mp);
|
|
|
|
return rc;
|
|
}
|
|
|
|
/*
|
|
* xtSearch()
|
|
*
|
|
* function: search for the xad entry covering specified offset.
|
|
*
|
|
* parameters:
|
|
* ip - file object;
|
|
* xoff - extent offset;
|
|
* nextp - address of next extent (if any) for search miss
|
|
* cmpp - comparison result:
|
|
* btstack - traverse stack;
|
|
* flag - search process flag (XT_INSERT);
|
|
*
|
|
* returns:
|
|
* btstack contains (bn, index) of search path traversed to the entry.
|
|
* *cmpp is set to result of comparison with the entry returned.
|
|
* the page containing the entry is pinned at exit.
|
|
*/
|
|
static int xtSearch(struct inode *ip, s64 xoff, s64 *nextp,
|
|
int *cmpp, struct btstack * btstack, int flag)
|
|
{
|
|
struct jfs_inode_info *jfs_ip = JFS_IP(ip);
|
|
int rc = 0;
|
|
int cmp = 1; /* init for empty page */
|
|
s64 bn; /* block number */
|
|
struct metapage *mp; /* page buffer */
|
|
xtpage_t *p; /* page */
|
|
xad_t *xad;
|
|
int base, index, lim, btindex;
|
|
struct btframe *btsp;
|
|
int nsplit = 0; /* number of pages to split */
|
|
s64 t64;
|
|
s64 next = 0;
|
|
|
|
INCREMENT(xtStat.search);
|
|
|
|
BT_CLR(btstack);
|
|
|
|
btstack->nsplit = 0;
|
|
|
|
/*
|
|
* search down tree from root:
|
|
*
|
|
* between two consecutive entries of <Ki, Pi> and <Kj, Pj> of
|
|
* internal page, child page Pi contains entry with k, Ki <= K < Kj.
|
|
*
|
|
* if entry with search key K is not found
|
|
* internal page search find the entry with largest key Ki
|
|
* less than K which point to the child page to search;
|
|
* leaf page search find the entry with smallest key Kj
|
|
* greater than K so that the returned index is the position of
|
|
* the entry to be shifted right for insertion of new entry.
|
|
* for empty tree, search key is greater than any key of the tree.
|
|
*
|
|
* by convention, root bn = 0.
|
|
*/
|
|
for (bn = 0;;) {
|
|
/* get/pin the page to search */
|
|
XT_GETPAGE(ip, bn, mp, PSIZE, p, rc);
|
|
if (rc)
|
|
return rc;
|
|
|
|
/* try sequential access heuristics with the previous
|
|
* access entry in target leaf page:
|
|
* once search narrowed down into the target leaf,
|
|
* key must either match an entry in the leaf or
|
|
* key entry does not exist in the tree;
|
|
*/
|
|
//fastSearch:
|
|
if ((jfs_ip->btorder & BT_SEQUENTIAL) &&
|
|
(p->header.flag & BT_LEAF) &&
|
|
(index = jfs_ip->btindex) <
|
|
le16_to_cpu(p->header.nextindex)) {
|
|
xad = &p->xad[index];
|
|
t64 = offsetXAD(xad);
|
|
if (xoff < t64 + lengthXAD(xad)) {
|
|
if (xoff >= t64) {
|
|
*cmpp = 0;
|
|
goto out;
|
|
}
|
|
|
|
/* stop sequential access heuristics */
|
|
goto binarySearch;
|
|
} else { /* (t64 + lengthXAD(xad)) <= xoff */
|
|
|
|
/* try next sequential entry */
|
|
index++;
|
|
if (index <
|
|
le16_to_cpu(p->header.nextindex)) {
|
|
xad++;
|
|
t64 = offsetXAD(xad);
|
|
if (xoff < t64 + lengthXAD(xad)) {
|
|
if (xoff >= t64) {
|
|
*cmpp = 0;
|
|
goto out;
|
|
}
|
|
|
|
/* miss: key falls between
|
|
* previous and this entry
|
|
*/
|
|
*cmpp = 1;
|
|
next = t64;
|
|
goto out;
|
|
}
|
|
|
|
/* (xoff >= t64 + lengthXAD(xad));
|
|
* matching entry may be further out:
|
|
* stop heuristic search
|
|
*/
|
|
/* stop sequential access heuristics */
|
|
goto binarySearch;
|
|
}
|
|
|
|
/* (index == p->header.nextindex);
|
|
* miss: key entry does not exist in
|
|
* the target leaf/tree
|
|
*/
|
|
*cmpp = 1;
|
|
goto out;
|
|
}
|
|
|
|
/*
|
|
* if hit, return index of the entry found, and
|
|
* if miss, where new entry with search key is
|
|
* to be inserted;
|
|
*/
|
|
out:
|
|
/* compute number of pages to split */
|
|
if (flag & XT_INSERT) {
|
|
if (p->header.nextindex == /* little-endian */
|
|
p->header.maxentry)
|
|
nsplit++;
|
|
else
|
|
nsplit = 0;
|
|
btstack->nsplit = nsplit;
|
|
}
|
|
|
|
/* save search result */
|
|
btsp = btstack->top;
|
|
btsp->bn = bn;
|
|
btsp->index = index;
|
|
btsp->mp = mp;
|
|
|
|
/* update sequential access heuristics */
|
|
jfs_ip->btindex = index;
|
|
|
|
if (nextp)
|
|
*nextp = next;
|
|
|
|
INCREMENT(xtStat.fastSearch);
|
|
return 0;
|
|
}
|
|
|
|
/* well, ... full search now */
|
|
binarySearch:
|
|
lim = le16_to_cpu(p->header.nextindex) - XTENTRYSTART;
|
|
|
|
/*
|
|
* binary search with search key K on the current page
|
|
*/
|
|
for (base = XTENTRYSTART; lim; lim >>= 1) {
|
|
index = base + (lim >> 1);
|
|
|
|
XT_CMP(cmp, xoff, &p->xad[index], t64);
|
|
if (cmp == 0) {
|
|
/*
|
|
* search hit
|
|
*/
|
|
/* search hit - leaf page:
|
|
* return the entry found
|
|
*/
|
|
if (p->header.flag & BT_LEAF) {
|
|
*cmpp = cmp;
|
|
|
|
/* compute number of pages to split */
|
|
if (flag & XT_INSERT) {
|
|
if (p->header.nextindex ==
|
|
p->header.maxentry)
|
|
nsplit++;
|
|
else
|
|
nsplit = 0;
|
|
btstack->nsplit = nsplit;
|
|
}
|
|
|
|
/* save search result */
|
|
btsp = btstack->top;
|
|
btsp->bn = bn;
|
|
btsp->index = index;
|
|
btsp->mp = mp;
|
|
|
|
/* init sequential access heuristics */
|
|
btindex = jfs_ip->btindex;
|
|
if (index == btindex ||
|
|
index == btindex + 1)
|
|
jfs_ip->btorder = BT_SEQUENTIAL;
|
|
else
|
|
jfs_ip->btorder = BT_RANDOM;
|
|
jfs_ip->btindex = index;
|
|
|
|
return 0;
|
|
}
|
|
/* search hit - internal page:
|
|
* descend/search its child page
|
|
*/
|
|
if (index < le16_to_cpu(p->header.nextindex)-1)
|
|
next = offsetXAD(&p->xad[index + 1]);
|
|
goto next;
|
|
}
|
|
|
|
if (cmp > 0) {
|
|
base = index + 1;
|
|
--lim;
|
|
}
|
|
}
|
|
|
|
/*
|
|
* search miss
|
|
*
|
|
* base is the smallest index with key (Kj) greater than
|
|
* search key (K) and may be zero or maxentry index.
|
|
*/
|
|
if (base < le16_to_cpu(p->header.nextindex))
|
|
next = offsetXAD(&p->xad[base]);
|
|
/*
|
|
* search miss - leaf page:
|
|
*
|
|
* return location of entry (base) where new entry with
|
|
* search key K is to be inserted.
|
|
*/
|
|
if (p->header.flag & BT_LEAF) {
|
|
*cmpp = cmp;
|
|
|
|
/* compute number of pages to split */
|
|
if (flag & XT_INSERT) {
|
|
if (p->header.nextindex ==
|
|
p->header.maxentry)
|
|
nsplit++;
|
|
else
|
|
nsplit = 0;
|
|
btstack->nsplit = nsplit;
|
|
}
|
|
|
|
/* save search result */
|
|
btsp = btstack->top;
|
|
btsp->bn = bn;
|
|
btsp->index = base;
|
|
btsp->mp = mp;
|
|
|
|
/* init sequential access heuristics */
|
|
btindex = jfs_ip->btindex;
|
|
if (base == btindex || base == btindex + 1)
|
|
jfs_ip->btorder = BT_SEQUENTIAL;
|
|
else
|
|
jfs_ip->btorder = BT_RANDOM;
|
|
jfs_ip->btindex = base;
|
|
|
|
if (nextp)
|
|
*nextp = next;
|
|
|
|
return 0;
|
|
}
|
|
|
|
/*
|
|
* search miss - non-leaf page:
|
|
*
|
|
* if base is non-zero, decrement base by one to get the parent
|
|
* entry of the child page to search.
|
|
*/
|
|
index = base ? base - 1 : base;
|
|
|
|
/*
|
|
* go down to child page
|
|
*/
|
|
next:
|
|
/* update number of pages to split */
|
|
if (p->header.nextindex == p->header.maxentry)
|
|
nsplit++;
|
|
else
|
|
nsplit = 0;
|
|
|
|
/* push (bn, index) of the parent page/entry */
|
|
if (BT_STACK_FULL(btstack)) {
|
|
jfs_error(ip->i_sb, "stack overrun!\n");
|
|
XT_PUTPAGE(mp);
|
|
return -EIO;
|
|
}
|
|
BT_PUSH(btstack, bn, index);
|
|
|
|
/* get the child page block number */
|
|
bn = addressXAD(&p->xad[index]);
|
|
|
|
/* unpin the parent page */
|
|
XT_PUTPAGE(mp);
|
|
}
|
|
}
|
|
|
|
/*
|
|
* xtInsert()
|
|
*
|
|
* function:
|
|
*
|
|
* parameter:
|
|
* tid - transaction id;
|
|
* ip - file object;
|
|
* xflag - extent flag (XAD_NOTRECORDED):
|
|
* xoff - extent offset;
|
|
* xlen - extent length;
|
|
* xaddrp - extent address pointer (in/out):
|
|
* if (*xaddrp)
|
|
* caller allocated data extent at *xaddrp;
|
|
* else
|
|
* allocate data extent and return its xaddr;
|
|
* flag -
|
|
*
|
|
* return:
|
|
*/
|
|
int xtInsert(tid_t tid, /* transaction id */
|
|
struct inode *ip, int xflag, s64 xoff, s32 xlen, s64 * xaddrp,
|
|
int flag)
|
|
{
|
|
int rc = 0;
|
|
s64 xaddr, hint;
|
|
struct metapage *mp; /* meta-page buffer */
|
|
xtpage_t *p; /* base B+-tree index page */
|
|
s64 bn;
|
|
int index, nextindex;
|
|
struct btstack btstack; /* traverse stack */
|
|
struct xtsplit split; /* split information */
|
|
xad_t *xad;
|
|
int cmp;
|
|
s64 next;
|
|
struct tlock *tlck;
|
|
struct xtlock *xtlck;
|
|
|
|
jfs_info("xtInsert: nxoff:0x%lx nxlen:0x%x", (ulong) xoff, xlen);
|
|
|
|
/*
|
|
* search for the entry location at which to insert:
|
|
*
|
|
* xtFastSearch() and xtSearch() both returns (leaf page
|
|
* pinned, index at which to insert).
|
|
* n.b. xtSearch() may return index of maxentry of
|
|
* the full page.
|
|
*/
|
|
if ((rc = xtSearch(ip, xoff, &next, &cmp, &btstack, XT_INSERT)))
|
|
return rc;
|
|
|
|
/* retrieve search result */
|
|
XT_GETSEARCH(ip, btstack.top, bn, mp, p, index);
|
|
|
|
/* This test must follow XT_GETSEARCH since mp must be valid if
|
|
* we branch to out: */
|
|
if ((cmp == 0) || (next && (xlen > next - xoff))) {
|
|
rc = -EEXIST;
|
|
goto out;
|
|
}
|
|
|
|
/*
|
|
* allocate data extent requested
|
|
*
|
|
* allocation hint: last xad
|
|
*/
|
|
if ((xaddr = *xaddrp) == 0) {
|
|
if (index > XTENTRYSTART) {
|
|
xad = &p->xad[index - 1];
|
|
hint = addressXAD(xad) + lengthXAD(xad) - 1;
|
|
} else
|
|
hint = 0;
|
|
if ((rc = dquot_alloc_block(ip, xlen)))
|
|
goto out;
|
|
if ((rc = dbAlloc(ip, hint, (s64) xlen, &xaddr))) {
|
|
dquot_free_block(ip, xlen);
|
|
goto out;
|
|
}
|
|
}
|
|
|
|
/*
|
|
* insert entry for new extent
|
|
*/
|
|
xflag |= XAD_NEW;
|
|
|
|
/*
|
|
* if the leaf page is full, split the page and
|
|
* propagate up the router entry for the new page from split
|
|
*
|
|
* The xtSplitUp() will insert the entry and unpin the leaf page.
|
|
*/
|
|
nextindex = le16_to_cpu(p->header.nextindex);
|
|
if (nextindex == le16_to_cpu(p->header.maxentry)) {
|
|
split.mp = mp;
|
|
split.index = index;
|
|
split.flag = xflag;
|
|
split.off = xoff;
|
|
split.len = xlen;
|
|
split.addr = xaddr;
|
|
split.pxdlist = NULL;
|
|
if ((rc = xtSplitUp(tid, ip, &split, &btstack))) {
|
|
/* undo data extent allocation */
|
|
if (*xaddrp == 0) {
|
|
dbFree(ip, xaddr, (s64) xlen);
|
|
dquot_free_block(ip, xlen);
|
|
}
|
|
return rc;
|
|
}
|
|
|
|
*xaddrp = xaddr;
|
|
return 0;
|
|
}
|
|
|
|
/*
|
|
* insert the new entry into the leaf page
|
|
*/
|
|
/*
|
|
* acquire a transaction lock on the leaf page;
|
|
*
|
|
* action: xad insertion/extension;
|
|
*/
|
|
BT_MARK_DIRTY(mp, ip);
|
|
|
|
/* if insert into middle, shift right remaining entries. */
|
|
if (index < nextindex)
|
|
memmove(&p->xad[index + 1], &p->xad[index],
|
|
(nextindex - index) * sizeof(xad_t));
|
|
|
|
/* insert the new entry: mark the entry NEW */
|
|
xad = &p->xad[index];
|
|
XT_PUTENTRY(xad, xflag, xoff, xlen, xaddr);
|
|
|
|
/* advance next available entry index */
|
|
le16_add_cpu(&p->header.nextindex, 1);
|
|
|
|
/* Don't log it if there are no links to the file */
|
|
if (!test_cflag(COMMIT_Nolink, ip)) {
|
|
tlck = txLock(tid, ip, mp, tlckXTREE | tlckGROW);
|
|
xtlck = (struct xtlock *) & tlck->lock;
|
|
xtlck->lwm.offset =
|
|
(xtlck->lwm.offset) ? min(index,
|
|
(int)xtlck->lwm.offset) : index;
|
|
xtlck->lwm.length =
|
|
le16_to_cpu(p->header.nextindex) - xtlck->lwm.offset;
|
|
}
|
|
|
|
*xaddrp = xaddr;
|
|
|
|
out:
|
|
/* unpin the leaf page */
|
|
XT_PUTPAGE(mp);
|
|
|
|
return rc;
|
|
}
|
|
|
|
|
|
/*
|
|
* xtSplitUp()
|
|
*
|
|
* function:
|
|
* split full pages as propagating insertion up the tree
|
|
*
|
|
* parameter:
|
|
* tid - transaction id;
|
|
* ip - file object;
|
|
* split - entry parameter descriptor;
|
|
* btstack - traverse stack from xtSearch()
|
|
*
|
|
* return:
|
|
*/
|
|
static int
|
|
xtSplitUp(tid_t tid,
|
|
struct inode *ip, struct xtsplit * split, struct btstack * btstack)
|
|
{
|
|
int rc = 0;
|
|
struct metapage *smp;
|
|
xtpage_t *sp; /* split page */
|
|
struct metapage *rmp;
|
|
s64 rbn; /* new right page block number */
|
|
struct metapage *rcmp;
|
|
xtpage_t *rcp; /* right child page */
|
|
s64 rcbn; /* right child page block number */
|
|
int skip; /* index of entry of insertion */
|
|
int nextindex; /* next available entry index of p */
|
|
struct btframe *parent; /* parent page entry on traverse stack */
|
|
xad_t *xad;
|
|
s64 xaddr;
|
|
int xlen;
|
|
int nsplit; /* number of pages split */
|
|
struct pxdlist pxdlist;
|
|
pxd_t *pxd;
|
|
struct tlock *tlck;
|
|
struct xtlock *xtlck;
|
|
|
|
smp = split->mp;
|
|
sp = XT_PAGE(ip, smp);
|
|
|
|
/* is inode xtree root extension/inline EA area free ? */
|
|
if ((sp->header.flag & BT_ROOT) && (!S_ISDIR(ip->i_mode)) &&
|
|
(le16_to_cpu(sp->header.maxentry) < XTROOTMAXSLOT) &&
|
|
(JFS_IP(ip)->mode2 & INLINEEA)) {
|
|
sp->header.maxentry = cpu_to_le16(XTROOTMAXSLOT);
|
|
JFS_IP(ip)->mode2 &= ~INLINEEA;
|
|
|
|
BT_MARK_DIRTY(smp, ip);
|
|
/*
|
|
* acquire a transaction lock on the leaf page;
|
|
*
|
|
* action: xad insertion/extension;
|
|
*/
|
|
|
|
/* if insert into middle, shift right remaining entries. */
|
|
skip = split->index;
|
|
nextindex = le16_to_cpu(sp->header.nextindex);
|
|
if (skip < nextindex)
|
|
memmove(&sp->xad[skip + 1], &sp->xad[skip],
|
|
(nextindex - skip) * sizeof(xad_t));
|
|
|
|
/* insert the new entry: mark the entry NEW */
|
|
xad = &sp->xad[skip];
|
|
XT_PUTENTRY(xad, split->flag, split->off, split->len,
|
|
split->addr);
|
|
|
|
/* advance next available entry index */
|
|
le16_add_cpu(&sp->header.nextindex, 1);
|
|
|
|
/* Don't log it if there are no links to the file */
|
|
if (!test_cflag(COMMIT_Nolink, ip)) {
|
|
tlck = txLock(tid, ip, smp, tlckXTREE | tlckGROW);
|
|
xtlck = (struct xtlock *) & tlck->lock;
|
|
xtlck->lwm.offset = (xtlck->lwm.offset) ?
|
|
min(skip, (int)xtlck->lwm.offset) : skip;
|
|
xtlck->lwm.length =
|
|
le16_to_cpu(sp->header.nextindex) -
|
|
xtlck->lwm.offset;
|
|
}
|
|
|
|
return 0;
|
|
}
|
|
|
|
/*
|
|
* allocate new index blocks to cover index page split(s)
|
|
*
|
|
* allocation hint: ?
|
|
*/
|
|
if (split->pxdlist == NULL) {
|
|
nsplit = btstack->nsplit;
|
|
split->pxdlist = &pxdlist;
|
|
pxdlist.maxnpxd = pxdlist.npxd = 0;
|
|
pxd = &pxdlist.pxd[0];
|
|
xlen = JFS_SBI(ip->i_sb)->nbperpage;
|
|
for (; nsplit > 0; nsplit--, pxd++) {
|
|
if ((rc = dbAlloc(ip, (s64) 0, (s64) xlen, &xaddr))
|
|
== 0) {
|
|
PXDaddress(pxd, xaddr);
|
|
PXDlength(pxd, xlen);
|
|
|
|
pxdlist.maxnpxd++;
|
|
|
|
continue;
|
|
}
|
|
|
|
/* undo allocation */
|
|
|
|
XT_PUTPAGE(smp);
|
|
return rc;
|
|
}
|
|
}
|
|
|
|
/*
|
|
* Split leaf page <sp> into <sp> and a new right page <rp>.
|
|
*
|
|
* The split routines insert the new entry into the leaf page,
|
|
* and acquire txLock as appropriate.
|
|
* return <rp> pinned and its block number <rpbn>.
|
|
*/
|
|
rc = (sp->header.flag & BT_ROOT) ?
|
|
xtSplitRoot(tid, ip, split, &rmp) :
|
|
xtSplitPage(tid, ip, split, &rmp, &rbn);
|
|
|
|
XT_PUTPAGE(smp);
|
|
|
|
if (rc)
|
|
return -EIO;
|
|
/*
|
|
* propagate up the router entry for the leaf page just split
|
|
*
|
|
* insert a router entry for the new page into the parent page,
|
|
* propagate the insert/split up the tree by walking back the stack
|
|
* of (bn of parent page, index of child page entry in parent page)
|
|
* that were traversed during the search for the page that split.
|
|
*
|
|
* the propagation of insert/split up the tree stops if the root
|
|
* splits or the page inserted into doesn't have to split to hold
|
|
* the new entry.
|
|
*
|
|
* the parent entry for the split page remains the same, and
|
|
* a new entry is inserted at its right with the first key and
|
|
* block number of the new right page.
|
|
*
|
|
* There are a maximum of 3 pages pinned at any time:
|
|
* right child, left parent and right parent (when the parent splits)
|
|
* to keep the child page pinned while working on the parent.
|
|
* make sure that all pins are released at exit.
|
|
*/
|
|
while ((parent = BT_POP(btstack)) != NULL) {
|
|
/* parent page specified by stack frame <parent> */
|
|
|
|
/* keep current child pages <rcp> pinned */
|
|
rcmp = rmp;
|
|
rcbn = rbn;
|
|
rcp = XT_PAGE(ip, rcmp);
|
|
|
|
/*
|
|
* insert router entry in parent for new right child page <rp>
|
|
*/
|
|
/* get/pin the parent page <sp> */
|
|
XT_GETPAGE(ip, parent->bn, smp, PSIZE, sp, rc);
|
|
if (rc) {
|
|
XT_PUTPAGE(rcmp);
|
|
return rc;
|
|
}
|
|
|
|
/*
|
|
* The new key entry goes ONE AFTER the index of parent entry,
|
|
* because the split was to the right.
|
|
*/
|
|
skip = parent->index + 1;
|
|
|
|
/*
|
|
* split or shift right remaining entries of the parent page
|
|
*/
|
|
nextindex = le16_to_cpu(sp->header.nextindex);
|
|
/*
|
|
* parent page is full - split the parent page
|
|
*/
|
|
if (nextindex == le16_to_cpu(sp->header.maxentry)) {
|
|
/* init for parent page split */
|
|
split->mp = smp;
|
|
split->index = skip; /* index at insert */
|
|
split->flag = XAD_NEW;
|
|
split->off = offsetXAD(&rcp->xad[XTENTRYSTART]);
|
|
split->len = JFS_SBI(ip->i_sb)->nbperpage;
|
|
split->addr = rcbn;
|
|
|
|
/* unpin previous right child page */
|
|
XT_PUTPAGE(rcmp);
|
|
|
|
/* The split routines insert the new entry,
|
|
* and acquire txLock as appropriate.
|
|
* return <rp> pinned and its block number <rpbn>.
|
|
*/
|
|
rc = (sp->header.flag & BT_ROOT) ?
|
|
xtSplitRoot(tid, ip, split, &rmp) :
|
|
xtSplitPage(tid, ip, split, &rmp, &rbn);
|
|
if (rc) {
|
|
XT_PUTPAGE(smp);
|
|
return rc;
|
|
}
|
|
|
|
XT_PUTPAGE(smp);
|
|
/* keep new child page <rp> pinned */
|
|
}
|
|
/*
|
|
* parent page is not full - insert in parent page
|
|
*/
|
|
else {
|
|
/*
|
|
* insert router entry in parent for the right child
|
|
* page from the first entry of the right child page:
|
|
*/
|
|
/*
|
|
* acquire a transaction lock on the parent page;
|
|
*
|
|
* action: router xad insertion;
|
|
*/
|
|
BT_MARK_DIRTY(smp, ip);
|
|
|
|
/*
|
|
* if insert into middle, shift right remaining entries
|
|
*/
|
|
if (skip < nextindex)
|
|
memmove(&sp->xad[skip + 1], &sp->xad[skip],
|
|
(nextindex -
|
|
skip) << L2XTSLOTSIZE);
|
|
|
|
/* insert the router entry */
|
|
xad = &sp->xad[skip];
|
|
XT_PUTENTRY(xad, XAD_NEW,
|
|
offsetXAD(&rcp->xad[XTENTRYSTART]),
|
|
JFS_SBI(ip->i_sb)->nbperpage, rcbn);
|
|
|
|
/* advance next available entry index. */
|
|
le16_add_cpu(&sp->header.nextindex, 1);
|
|
|
|
/* Don't log it if there are no links to the file */
|
|
if (!test_cflag(COMMIT_Nolink, ip)) {
|
|
tlck = txLock(tid, ip, smp,
|
|
tlckXTREE | tlckGROW);
|
|
xtlck = (struct xtlock *) & tlck->lock;
|
|
xtlck->lwm.offset = (xtlck->lwm.offset) ?
|
|
min(skip, (int)xtlck->lwm.offset) : skip;
|
|
xtlck->lwm.length =
|
|
le16_to_cpu(sp->header.nextindex) -
|
|
xtlck->lwm.offset;
|
|
}
|
|
|
|
/* unpin parent page */
|
|
XT_PUTPAGE(smp);
|
|
|
|
/* exit propagate up */
|
|
break;
|
|
}
|
|
}
|
|
|
|
/* unpin current right page */
|
|
XT_PUTPAGE(rmp);
|
|
|
|
return 0;
|
|
}
|
|
|
|
|
|
/*
|
|
* xtSplitPage()
|
|
*
|
|
* function:
|
|
* split a full non-root page into
|
|
* original/split/left page and new right page
|
|
* i.e., the original/split page remains as left page.
|
|
*
|
|
* parameter:
|
|
* int tid,
|
|
* struct inode *ip,
|
|
* struct xtsplit *split,
|
|
* struct metapage **rmpp,
|
|
* u64 *rbnp,
|
|
*
|
|
* return:
|
|
* Pointer to page in which to insert or NULL on error.
|
|
*/
|
|
static int
|
|
xtSplitPage(tid_t tid, struct inode *ip,
|
|
struct xtsplit * split, struct metapage ** rmpp, s64 * rbnp)
|
|
{
|
|
int rc = 0;
|
|
struct metapage *smp;
|
|
xtpage_t *sp;
|
|
struct metapage *rmp;
|
|
xtpage_t *rp; /* new right page allocated */
|
|
s64 rbn; /* new right page block number */
|
|
struct metapage *mp;
|
|
xtpage_t *p;
|
|
s64 nextbn;
|
|
int skip, maxentry, middle, righthalf, n;
|
|
xad_t *xad;
|
|
struct pxdlist *pxdlist;
|
|
pxd_t *pxd;
|
|
struct tlock *tlck;
|
|
struct xtlock *sxtlck = NULL, *rxtlck = NULL;
|
|
int quota_allocation = 0;
|
|
|
|
smp = split->mp;
|
|
sp = XT_PAGE(ip, smp);
|
|
|
|
INCREMENT(xtStat.split);
|
|
|
|
pxdlist = split->pxdlist;
|
|
pxd = &pxdlist->pxd[pxdlist->npxd];
|
|
pxdlist->npxd++;
|
|
rbn = addressPXD(pxd);
|
|
|
|
/* Allocate blocks to quota. */
|
|
rc = dquot_alloc_block(ip, lengthPXD(pxd));
|
|
if (rc)
|
|
goto clean_up;
|
|
|
|
quota_allocation += lengthPXD(pxd);
|
|
|
|
/*
|
|
* allocate the new right page for the split
|
|
*/
|
|
rmp = get_metapage(ip, rbn, PSIZE, 1);
|
|
if (rmp == NULL) {
|
|
rc = -EIO;
|
|
goto clean_up;
|
|
}
|
|
|
|
jfs_info("xtSplitPage: ip:0x%p smp:0x%p rmp:0x%p", ip, smp, rmp);
|
|
|
|
BT_MARK_DIRTY(rmp, ip);
|
|
/*
|
|
* action: new page;
|
|
*/
|
|
|
|
rp = (xtpage_t *) rmp->data;
|
|
rp->header.self = *pxd;
|
|
rp->header.flag = sp->header.flag & BT_TYPE;
|
|
rp->header.maxentry = sp->header.maxentry; /* little-endian */
|
|
rp->header.nextindex = cpu_to_le16(XTENTRYSTART);
|
|
|
|
BT_MARK_DIRTY(smp, ip);
|
|
/* Don't log it if there are no links to the file */
|
|
if (!test_cflag(COMMIT_Nolink, ip)) {
|
|
/*
|
|
* acquire a transaction lock on the new right page;
|
|
*/
|
|
tlck = txLock(tid, ip, rmp, tlckXTREE | tlckNEW);
|
|
rxtlck = (struct xtlock *) & tlck->lock;
|
|
rxtlck->lwm.offset = XTENTRYSTART;
|
|
/*
|
|
* acquire a transaction lock on the split page
|
|
*/
|
|
tlck = txLock(tid, ip, smp, tlckXTREE | tlckGROW);
|
|
sxtlck = (struct xtlock *) & tlck->lock;
|
|
}
|
|
|
|
/*
|
|
* initialize/update sibling pointers of <sp> and <rp>
|
|
*/
|
|
nextbn = le64_to_cpu(sp->header.next);
|
|
rp->header.next = cpu_to_le64(nextbn);
|
|
rp->header.prev = cpu_to_le64(addressPXD(&sp->header.self));
|
|
sp->header.next = cpu_to_le64(rbn);
|
|
|
|
skip = split->index;
|
|
|
|
/*
|
|
* sequential append at tail (after last entry of last page)
|
|
*
|
|
* if splitting the last page on a level because of appending
|
|
* a entry to it (skip is maxentry), it's likely that the access is
|
|
* sequential. adding an empty page on the side of the level is less
|
|
* work and can push the fill factor much higher than normal.
|
|
* if we're wrong it's no big deal - we will do the split the right
|
|
* way next time.
|
|
* (it may look like it's equally easy to do a similar hack for
|
|
* reverse sorted data, that is, split the tree left, but it's not.
|
|
* Be my guest.)
|
|
*/
|
|
if (nextbn == 0 && skip == le16_to_cpu(sp->header.maxentry)) {
|
|
/*
|
|
* acquire a transaction lock on the new/right page;
|
|
*
|
|
* action: xad insertion;
|
|
*/
|
|
/* insert entry at the first entry of the new right page */
|
|
xad = &rp->xad[XTENTRYSTART];
|
|
XT_PUTENTRY(xad, split->flag, split->off, split->len,
|
|
split->addr);
|
|
|
|
rp->header.nextindex = cpu_to_le16(XTENTRYSTART + 1);
|
|
|
|
if (!test_cflag(COMMIT_Nolink, ip)) {
|
|
/* rxtlck->lwm.offset = XTENTRYSTART; */
|
|
rxtlck->lwm.length = 1;
|
|
}
|
|
|
|
*rmpp = rmp;
|
|
*rbnp = rbn;
|
|
|
|
jfs_info("xtSplitPage: sp:0x%p rp:0x%p", sp, rp);
|
|
return 0;
|
|
}
|
|
|
|
/*
|
|
* non-sequential insert (at possibly middle page)
|
|
*/
|
|
|
|
/*
|
|
* update previous pointer of old next/right page of <sp>
|
|
*/
|
|
if (nextbn != 0) {
|
|
XT_GETPAGE(ip, nextbn, mp, PSIZE, p, rc);
|
|
if (rc) {
|
|
XT_PUTPAGE(rmp);
|
|
goto clean_up;
|
|
}
|
|
|
|
BT_MARK_DIRTY(mp, ip);
|
|
/*
|
|
* acquire a transaction lock on the next page;
|
|
*
|
|
* action:sibling pointer update;
|
|
*/
|
|
if (!test_cflag(COMMIT_Nolink, ip))
|
|
tlck = txLock(tid, ip, mp, tlckXTREE | tlckRELINK);
|
|
|
|
p->header.prev = cpu_to_le64(rbn);
|
|
|
|
/* sibling page may have been updated previously, or
|
|
* it may be updated later;
|
|
*/
|
|
|
|
XT_PUTPAGE(mp);
|
|
}
|
|
|
|
/*
|
|
* split the data between the split and new/right pages
|
|
*/
|
|
maxentry = le16_to_cpu(sp->header.maxentry);
|
|
middle = maxentry >> 1;
|
|
righthalf = maxentry - middle;
|
|
|
|
/*
|
|
* skip index in old split/left page - insert into left page:
|
|
*/
|
|
if (skip <= middle) {
|
|
/* move right half of split page to the new right page */
|
|
memmove(&rp->xad[XTENTRYSTART], &sp->xad[middle],
|
|
righthalf << L2XTSLOTSIZE);
|
|
|
|
/* shift right tail of left half to make room for new entry */
|
|
if (skip < middle)
|
|
memmove(&sp->xad[skip + 1], &sp->xad[skip],
|
|
(middle - skip) << L2XTSLOTSIZE);
|
|
|
|
/* insert new entry */
|
|
xad = &sp->xad[skip];
|
|
XT_PUTENTRY(xad, split->flag, split->off, split->len,
|
|
split->addr);
|
|
|
|
/* update page header */
|
|
sp->header.nextindex = cpu_to_le16(middle + 1);
|
|
if (!test_cflag(COMMIT_Nolink, ip)) {
|
|
sxtlck->lwm.offset = (sxtlck->lwm.offset) ?
|
|
min(skip, (int)sxtlck->lwm.offset) : skip;
|
|
}
|
|
|
|
rp->header.nextindex =
|
|
cpu_to_le16(XTENTRYSTART + righthalf);
|
|
}
|
|
/*
|
|
* skip index in new right page - insert into right page:
|
|
*/
|
|
else {
|
|
/* move left head of right half to right page */
|
|
n = skip - middle;
|
|
memmove(&rp->xad[XTENTRYSTART], &sp->xad[middle],
|
|
n << L2XTSLOTSIZE);
|
|
|
|
/* insert new entry */
|
|
n += XTENTRYSTART;
|
|
xad = &rp->xad[n];
|
|
XT_PUTENTRY(xad, split->flag, split->off, split->len,
|
|
split->addr);
|
|
|
|
/* move right tail of right half to right page */
|
|
if (skip < maxentry)
|
|
memmove(&rp->xad[n + 1], &sp->xad[skip],
|
|
(maxentry - skip) << L2XTSLOTSIZE);
|
|
|
|
/* update page header */
|
|
sp->header.nextindex = cpu_to_le16(middle);
|
|
if (!test_cflag(COMMIT_Nolink, ip)) {
|
|
sxtlck->lwm.offset = (sxtlck->lwm.offset) ?
|
|
min(middle, (int)sxtlck->lwm.offset) : middle;
|
|
}
|
|
|
|
rp->header.nextindex = cpu_to_le16(XTENTRYSTART +
|
|
righthalf + 1);
|
|
}
|
|
|
|
if (!test_cflag(COMMIT_Nolink, ip)) {
|
|
sxtlck->lwm.length = le16_to_cpu(sp->header.nextindex) -
|
|
sxtlck->lwm.offset;
|
|
|
|
/* rxtlck->lwm.offset = XTENTRYSTART; */
|
|
rxtlck->lwm.length = le16_to_cpu(rp->header.nextindex) -
|
|
XTENTRYSTART;
|
|
}
|
|
|
|
*rmpp = rmp;
|
|
*rbnp = rbn;
|
|
|
|
jfs_info("xtSplitPage: sp:0x%p rp:0x%p", sp, rp);
|
|
return rc;
|
|
|
|
clean_up:
|
|
|
|
/* Rollback quota allocation. */
|
|
if (quota_allocation)
|
|
dquot_free_block(ip, quota_allocation);
|
|
|
|
return (rc);
|
|
}
|
|
|
|
|
|
/*
|
|
* xtSplitRoot()
|
|
*
|
|
* function:
|
|
* split the full root page into original/root/split page and new
|
|
* right page
|
|
* i.e., root remains fixed in tree anchor (inode) and the root is
|
|
* copied to a single new right child page since root page <<
|
|
* non-root page, and the split root page contains a single entry
|
|
* for the new right child page.
|
|
*
|
|
* parameter:
|
|
* int tid,
|
|
* struct inode *ip,
|
|
* struct xtsplit *split,
|
|
* struct metapage **rmpp)
|
|
*
|
|
* return:
|
|
* Pointer to page in which to insert or NULL on error.
|
|
*/
|
|
static int
|
|
xtSplitRoot(tid_t tid,
|
|
struct inode *ip, struct xtsplit * split, struct metapage ** rmpp)
|
|
{
|
|
xtpage_t *sp;
|
|
struct metapage *rmp;
|
|
xtpage_t *rp;
|
|
s64 rbn;
|
|
int skip, nextindex;
|
|
xad_t *xad;
|
|
pxd_t *pxd;
|
|
struct pxdlist *pxdlist;
|
|
struct tlock *tlck;
|
|
struct xtlock *xtlck;
|
|
int rc;
|
|
|
|
sp = &JFS_IP(ip)->i_xtroot;
|
|
|
|
INCREMENT(xtStat.split);
|
|
|
|
/*
|
|
* allocate a single (right) child page
|
|
*/
|
|
pxdlist = split->pxdlist;
|
|
pxd = &pxdlist->pxd[pxdlist->npxd];
|
|
pxdlist->npxd++;
|
|
rbn = addressPXD(pxd);
|
|
rmp = get_metapage(ip, rbn, PSIZE, 1);
|
|
if (rmp == NULL)
|
|
return -EIO;
|
|
|
|
/* Allocate blocks to quota. */
|
|
rc = dquot_alloc_block(ip, lengthPXD(pxd));
|
|
if (rc) {
|
|
release_metapage(rmp);
|
|
return rc;
|
|
}
|
|
|
|
jfs_info("xtSplitRoot: ip:0x%p rmp:0x%p", ip, rmp);
|
|
|
|
/*
|
|
* acquire a transaction lock on the new right page;
|
|
*
|
|
* action: new page;
|
|
*/
|
|
BT_MARK_DIRTY(rmp, ip);
|
|
|
|
rp = (xtpage_t *) rmp->data;
|
|
rp->header.flag =
|
|
(sp->header.flag & BT_LEAF) ? BT_LEAF : BT_INTERNAL;
|
|
rp->header.self = *pxd;
|
|
rp->header.nextindex = cpu_to_le16(XTENTRYSTART);
|
|
rp->header.maxentry = cpu_to_le16(PSIZE >> L2XTSLOTSIZE);
|
|
|
|
/* initialize sibling pointers */
|
|
rp->header.next = 0;
|
|
rp->header.prev = 0;
|
|
|
|
/*
|
|
* copy the in-line root page into new right page extent
|
|
*/
|
|
nextindex = le16_to_cpu(sp->header.maxentry);
|
|
memmove(&rp->xad[XTENTRYSTART], &sp->xad[XTENTRYSTART],
|
|
(nextindex - XTENTRYSTART) << L2XTSLOTSIZE);
|
|
|
|
/*
|
|
* insert the new entry into the new right/child page
|
|
* (skip index in the new right page will not change)
|
|
*/
|
|
skip = split->index;
|
|
/* if insert into middle, shift right remaining entries */
|
|
if (skip != nextindex)
|
|
memmove(&rp->xad[skip + 1], &rp->xad[skip],
|
|
(nextindex - skip) * sizeof(xad_t));
|
|
|
|
xad = &rp->xad[skip];
|
|
XT_PUTENTRY(xad, split->flag, split->off, split->len, split->addr);
|
|
|
|
/* update page header */
|
|
rp->header.nextindex = cpu_to_le16(nextindex + 1);
|
|
|
|
if (!test_cflag(COMMIT_Nolink, ip)) {
|
|
tlck = txLock(tid, ip, rmp, tlckXTREE | tlckNEW);
|
|
xtlck = (struct xtlock *) & tlck->lock;
|
|
xtlck->lwm.offset = XTENTRYSTART;
|
|
xtlck->lwm.length = le16_to_cpu(rp->header.nextindex) -
|
|
XTENTRYSTART;
|
|
}
|
|
|
|
/*
|
|
* reset the root
|
|
*
|
|
* init root with the single entry for the new right page
|
|
* set the 1st entry offset to 0, which force the left-most key
|
|
* at any level of the tree to be less than any search key.
|
|
*/
|
|
/*
|
|
* acquire a transaction lock on the root page (in-memory inode);
|
|
*
|
|
* action: root split;
|
|
*/
|
|
BT_MARK_DIRTY(split->mp, ip);
|
|
|
|
xad = &sp->xad[XTENTRYSTART];
|
|
XT_PUTENTRY(xad, XAD_NEW, 0, JFS_SBI(ip->i_sb)->nbperpage, rbn);
|
|
|
|
/* update page header of root */
|
|
sp->header.flag &= ~BT_LEAF;
|
|
sp->header.flag |= BT_INTERNAL;
|
|
|
|
sp->header.nextindex = cpu_to_le16(XTENTRYSTART + 1);
|
|
|
|
if (!test_cflag(COMMIT_Nolink, ip)) {
|
|
tlck = txLock(tid, ip, split->mp, tlckXTREE | tlckGROW);
|
|
xtlck = (struct xtlock *) & tlck->lock;
|
|
xtlck->lwm.offset = XTENTRYSTART;
|
|
xtlck->lwm.length = 1;
|
|
}
|
|
|
|
*rmpp = rmp;
|
|
|
|
jfs_info("xtSplitRoot: sp:0x%p rp:0x%p", sp, rp);
|
|
return 0;
|
|
}
|
|
|
|
|
|
/*
|
|
* xtExtend()
|
|
*
|
|
* function: extend in-place;
|
|
*
|
|
* note: existing extent may or may not have been committed.
|
|
* caller is responsible for pager buffer cache update, and
|
|
* working block allocation map update;
|
|
* update pmap: alloc whole extended extent;
|
|
*/
|
|
int xtExtend(tid_t tid, /* transaction id */
|
|
struct inode *ip, s64 xoff, /* delta extent offset */
|
|
s32 xlen, /* delta extent length */
|
|
int flag)
|
|
{
|
|
int rc = 0;
|
|
int cmp;
|
|
struct metapage *mp; /* meta-page buffer */
|
|
xtpage_t *p; /* base B+-tree index page */
|
|
s64 bn;
|
|
int index, nextindex, len;
|
|
struct btstack btstack; /* traverse stack */
|
|
struct xtsplit split; /* split information */
|
|
xad_t *xad;
|
|
s64 xaddr;
|
|
struct tlock *tlck;
|
|
struct xtlock *xtlck = NULL;
|
|
|
|
jfs_info("xtExtend: nxoff:0x%lx nxlen:0x%x", (ulong) xoff, xlen);
|
|
|
|
/* there must exist extent to be extended */
|
|
if ((rc = xtSearch(ip, xoff - 1, NULL, &cmp, &btstack, XT_INSERT)))
|
|
return rc;
|
|
|
|
/* retrieve search result */
|
|
XT_GETSEARCH(ip, btstack.top, bn, mp, p, index);
|
|
|
|
if (cmp != 0) {
|
|
XT_PUTPAGE(mp);
|
|
jfs_error(ip->i_sb, "xtSearch did not find extent\n");
|
|
return -EIO;
|
|
}
|
|
|
|
/* extension must be contiguous */
|
|
xad = &p->xad[index];
|
|
if ((offsetXAD(xad) + lengthXAD(xad)) != xoff) {
|
|
XT_PUTPAGE(mp);
|
|
jfs_error(ip->i_sb, "extension is not contiguous\n");
|
|
return -EIO;
|
|
}
|
|
|
|
/*
|
|
* acquire a transaction lock on the leaf page;
|
|
*
|
|
* action: xad insertion/extension;
|
|
*/
|
|
BT_MARK_DIRTY(mp, ip);
|
|
if (!test_cflag(COMMIT_Nolink, ip)) {
|
|
tlck = txLock(tid, ip, mp, tlckXTREE | tlckGROW);
|
|
xtlck = (struct xtlock *) & tlck->lock;
|
|
}
|
|
|
|
/* extend will overflow extent ? */
|
|
xlen = lengthXAD(xad) + xlen;
|
|
if ((len = xlen - MAXXLEN) <= 0)
|
|
goto extendOld;
|
|
|
|
/*
|
|
* extent overflow: insert entry for new extent
|
|
*/
|
|
//insertNew:
|
|
xoff = offsetXAD(xad) + MAXXLEN;
|
|
xaddr = addressXAD(xad) + MAXXLEN;
|
|
nextindex = le16_to_cpu(p->header.nextindex);
|
|
|
|
/*
|
|
* if the leaf page is full, insert the new entry and
|
|
* propagate up the router entry for the new page from split
|
|
*
|
|
* The xtSplitUp() will insert the entry and unpin the leaf page.
|
|
*/
|
|
if (nextindex == le16_to_cpu(p->header.maxentry)) {
|
|
/* xtSpliUp() unpins leaf pages */
|
|
split.mp = mp;
|
|
split.index = index + 1;
|
|
split.flag = XAD_NEW;
|
|
split.off = xoff; /* split offset */
|
|
split.len = len;
|
|
split.addr = xaddr;
|
|
split.pxdlist = NULL;
|
|
if ((rc = xtSplitUp(tid, ip, &split, &btstack)))
|
|
return rc;
|
|
|
|
/* get back old page */
|
|
XT_GETPAGE(ip, bn, mp, PSIZE, p, rc);
|
|
if (rc)
|
|
return rc;
|
|
/*
|
|
* if leaf root has been split, original root has been
|
|
* copied to new child page, i.e., original entry now
|
|
* resides on the new child page;
|
|
*/
|
|
if (p->header.flag & BT_INTERNAL) {
|
|
ASSERT(p->header.nextindex ==
|
|
cpu_to_le16(XTENTRYSTART + 1));
|
|
xad = &p->xad[XTENTRYSTART];
|
|
bn = addressXAD(xad);
|
|
XT_PUTPAGE(mp);
|
|
|
|
/* get new child page */
|
|
XT_GETPAGE(ip, bn, mp, PSIZE, p, rc);
|
|
if (rc)
|
|
return rc;
|
|
|
|
BT_MARK_DIRTY(mp, ip);
|
|
if (!test_cflag(COMMIT_Nolink, ip)) {
|
|
tlck = txLock(tid, ip, mp, tlckXTREE|tlckGROW);
|
|
xtlck = (struct xtlock *) & tlck->lock;
|
|
}
|
|
}
|
|
}
|
|
/*
|
|
* insert the new entry into the leaf page
|
|
*/
|
|
else {
|
|
/* insert the new entry: mark the entry NEW */
|
|
xad = &p->xad[index + 1];
|
|
XT_PUTENTRY(xad, XAD_NEW, xoff, len, xaddr);
|
|
|
|
/* advance next available entry index */
|
|
le16_add_cpu(&p->header.nextindex, 1);
|
|
}
|
|
|
|
/* get back old entry */
|
|
xad = &p->xad[index];
|
|
xlen = MAXXLEN;
|
|
|
|
/*
|
|
* extend old extent
|
|
*/
|
|
extendOld:
|
|
XADlength(xad, xlen);
|
|
if (!(xad->flag & XAD_NEW))
|
|
xad->flag |= XAD_EXTENDED;
|
|
|
|
if (!test_cflag(COMMIT_Nolink, ip)) {
|
|
xtlck->lwm.offset =
|
|
(xtlck->lwm.offset) ? min(index,
|
|
(int)xtlck->lwm.offset) : index;
|
|
xtlck->lwm.length =
|
|
le16_to_cpu(p->header.nextindex) - xtlck->lwm.offset;
|
|
}
|
|
|
|
/* unpin the leaf page */
|
|
XT_PUTPAGE(mp);
|
|
|
|
return rc;
|
|
}
|
|
|
|
#ifdef _NOTYET
|
|
/*
|
|
* xtTailgate()
|
|
*
|
|
* function: split existing 'tail' extent
|
|
* (split offset >= start offset of tail extent), and
|
|
* relocate and extend the split tail half;
|
|
*
|
|
* note: existing extent may or may not have been committed.
|
|
* caller is responsible for pager buffer cache update, and
|
|
* working block allocation map update;
|
|
* update pmap: free old split tail extent, alloc new extent;
|
|
*/
|
|
int xtTailgate(tid_t tid, /* transaction id */
|
|
struct inode *ip, s64 xoff, /* split/new extent offset */
|
|
s32 xlen, /* new extent length */
|
|
s64 xaddr, /* new extent address */
|
|
int flag)
|
|
{
|
|
int rc = 0;
|
|
int cmp;
|
|
struct metapage *mp; /* meta-page buffer */
|
|
xtpage_t *p; /* base B+-tree index page */
|
|
s64 bn;
|
|
int index, nextindex, llen, rlen;
|
|
struct btstack btstack; /* traverse stack */
|
|
struct xtsplit split; /* split information */
|
|
xad_t *xad;
|
|
struct tlock *tlck;
|
|
struct xtlock *xtlck = 0;
|
|
struct tlock *mtlck;
|
|
struct maplock *pxdlock;
|
|
|
|
/*
|
|
printf("xtTailgate: nxoff:0x%lx nxlen:0x%x nxaddr:0x%lx\n",
|
|
(ulong)xoff, xlen, (ulong)xaddr);
|
|
*/
|
|
|
|
/* there must exist extent to be tailgated */
|
|
if ((rc = xtSearch(ip, xoff, NULL, &cmp, &btstack, XT_INSERT)))
|
|
return rc;
|
|
|
|
/* retrieve search result */
|
|
XT_GETSEARCH(ip, btstack.top, bn, mp, p, index);
|
|
|
|
if (cmp != 0) {
|
|
XT_PUTPAGE(mp);
|
|
jfs_error(ip->i_sb, "couldn't find extent\n");
|
|
return -EIO;
|
|
}
|
|
|
|
/* entry found must be last entry */
|
|
nextindex = le16_to_cpu(p->header.nextindex);
|
|
if (index != nextindex - 1) {
|
|
XT_PUTPAGE(mp);
|
|
jfs_error(ip->i_sb, "the entry found is not the last entry\n");
|
|
return -EIO;
|
|
}
|
|
|
|
BT_MARK_DIRTY(mp, ip);
|
|
/*
|
|
* acquire tlock of the leaf page containing original entry
|
|
*/
|
|
if (!test_cflag(COMMIT_Nolink, ip)) {
|
|
tlck = txLock(tid, ip, mp, tlckXTREE | tlckGROW);
|
|
xtlck = (struct xtlock *) & tlck->lock;
|
|
}
|
|
|
|
/* completely replace extent ? */
|
|
xad = &p->xad[index];
|
|
/*
|
|
printf("xtTailgate: xoff:0x%lx xlen:0x%x xaddr:0x%lx\n",
|
|
(ulong)offsetXAD(xad), lengthXAD(xad), (ulong)addressXAD(xad));
|
|
*/
|
|
if ((llen = xoff - offsetXAD(xad)) == 0)
|
|
goto updateOld;
|
|
|
|
/*
|
|
* partially replace extent: insert entry for new extent
|
|
*/
|
|
//insertNew:
|
|
/*
|
|
* if the leaf page is full, insert the new entry and
|
|
* propagate up the router entry for the new page from split
|
|
*
|
|
* The xtSplitUp() will insert the entry and unpin the leaf page.
|
|
*/
|
|
if (nextindex == le16_to_cpu(p->header.maxentry)) {
|
|
/* xtSpliUp() unpins leaf pages */
|
|
split.mp = mp;
|
|
split.index = index + 1;
|
|
split.flag = XAD_NEW;
|
|
split.off = xoff; /* split offset */
|
|
split.len = xlen;
|
|
split.addr = xaddr;
|
|
split.pxdlist = NULL;
|
|
if ((rc = xtSplitUp(tid, ip, &split, &btstack)))
|
|
return rc;
|
|
|
|
/* get back old page */
|
|
XT_GETPAGE(ip, bn, mp, PSIZE, p, rc);
|
|
if (rc)
|
|
return rc;
|
|
/*
|
|
* if leaf root has been split, original root has been
|
|
* copied to new child page, i.e., original entry now
|
|
* resides on the new child page;
|
|
*/
|
|
if (p->header.flag & BT_INTERNAL) {
|
|
ASSERT(p->header.nextindex ==
|
|
cpu_to_le16(XTENTRYSTART + 1));
|
|
xad = &p->xad[XTENTRYSTART];
|
|
bn = addressXAD(xad);
|
|
XT_PUTPAGE(mp);
|
|
|
|
/* get new child page */
|
|
XT_GETPAGE(ip, bn, mp, PSIZE, p, rc);
|
|
if (rc)
|
|
return rc;
|
|
|
|
BT_MARK_DIRTY(mp, ip);
|
|
if (!test_cflag(COMMIT_Nolink, ip)) {
|
|
tlck = txLock(tid, ip, mp, tlckXTREE|tlckGROW);
|
|
xtlck = (struct xtlock *) & tlck->lock;
|
|
}
|
|
}
|
|
}
|
|
/*
|
|
* insert the new entry into the leaf page
|
|
*/
|
|
else {
|
|
/* insert the new entry: mark the entry NEW */
|
|
xad = &p->xad[index + 1];
|
|
XT_PUTENTRY(xad, XAD_NEW, xoff, xlen, xaddr);
|
|
|
|
/* advance next available entry index */
|
|
le16_add_cpu(&p->header.nextindex, 1);
|
|
}
|
|
|
|
/* get back old XAD */
|
|
xad = &p->xad[index];
|
|
|
|
/*
|
|
* truncate/relocate old extent at split offset
|
|
*/
|
|
updateOld:
|
|
/* update dmap for old/committed/truncated extent */
|
|
rlen = lengthXAD(xad) - llen;
|
|
if (!(xad->flag & XAD_NEW)) {
|
|
/* free from PWMAP at commit */
|
|
if (!test_cflag(COMMIT_Nolink, ip)) {
|
|
mtlck = txMaplock(tid, ip, tlckMAP);
|
|
pxdlock = (struct maplock *) & mtlck->lock;
|
|
pxdlock->flag = mlckFREEPXD;
|
|
PXDaddress(&pxdlock->pxd, addressXAD(xad) + llen);
|
|
PXDlength(&pxdlock->pxd, rlen);
|
|
pxdlock->index = 1;
|
|
}
|
|
} else
|
|
/* free from WMAP */
|
|
dbFree(ip, addressXAD(xad) + llen, (s64) rlen);
|
|
|
|
if (llen)
|
|
/* truncate */
|
|
XADlength(xad, llen);
|
|
else
|
|
/* replace */
|
|
XT_PUTENTRY(xad, XAD_NEW, xoff, xlen, xaddr);
|
|
|
|
if (!test_cflag(COMMIT_Nolink, ip)) {
|
|
xtlck->lwm.offset = (xtlck->lwm.offset) ?
|
|
min(index, (int)xtlck->lwm.offset) : index;
|
|
xtlck->lwm.length = le16_to_cpu(p->header.nextindex) -
|
|
xtlck->lwm.offset;
|
|
}
|
|
|
|
/* unpin the leaf page */
|
|
XT_PUTPAGE(mp);
|
|
|
|
return rc;
|
|
}
|
|
#endif /* _NOTYET */
|
|
|
|
/*
|
|
* xtUpdate()
|
|
*
|
|
* function: update XAD;
|
|
*
|
|
* update extent for allocated_but_not_recorded or
|
|
* compressed extent;
|
|
*
|
|
* parameter:
|
|
* nxad - new XAD;
|
|
* logical extent of the specified XAD must be completely
|
|
* contained by an existing XAD;
|
|
*/
|
|
int xtUpdate(tid_t tid, struct inode *ip, xad_t * nxad)
|
|
{ /* new XAD */
|
|
int rc = 0;
|
|
int cmp;
|
|
struct metapage *mp; /* meta-page buffer */
|
|
xtpage_t *p; /* base B+-tree index page */
|
|
s64 bn;
|
|
int index0, index, newindex, nextindex;
|
|
struct btstack btstack; /* traverse stack */
|
|
struct xtsplit split; /* split information */
|
|
xad_t *xad, *lxad, *rxad;
|
|
int xflag;
|
|
s64 nxoff, xoff;
|
|
int nxlen, xlen, lxlen, rxlen;
|
|
s64 nxaddr, xaddr;
|
|
struct tlock *tlck;
|
|
struct xtlock *xtlck = NULL;
|
|
int newpage = 0;
|
|
|
|
/* there must exist extent to be tailgated */
|
|
nxoff = offsetXAD(nxad);
|
|
nxlen = lengthXAD(nxad);
|
|
nxaddr = addressXAD(nxad);
|
|
|
|
if ((rc = xtSearch(ip, nxoff, NULL, &cmp, &btstack, XT_INSERT)))
|
|
return rc;
|
|
|
|
/* retrieve search result */
|
|
XT_GETSEARCH(ip, btstack.top, bn, mp, p, index0);
|
|
|
|
if (cmp != 0) {
|
|
XT_PUTPAGE(mp);
|
|
jfs_error(ip->i_sb, "Could not find extent\n");
|
|
return -EIO;
|
|
}
|
|
|
|
BT_MARK_DIRTY(mp, ip);
|
|
/*
|
|
* acquire tlock of the leaf page containing original entry
|
|
*/
|
|
if (!test_cflag(COMMIT_Nolink, ip)) {
|
|
tlck = txLock(tid, ip, mp, tlckXTREE | tlckGROW);
|
|
xtlck = (struct xtlock *) & tlck->lock;
|
|
}
|
|
|
|
xad = &p->xad[index0];
|
|
xflag = xad->flag;
|
|
xoff = offsetXAD(xad);
|
|
xlen = lengthXAD(xad);
|
|
xaddr = addressXAD(xad);
|
|
|
|
/* nXAD must be completely contained within XAD */
|
|
if ((xoff > nxoff) ||
|
|
(nxoff + nxlen > xoff + xlen)) {
|
|
XT_PUTPAGE(mp);
|
|
jfs_error(ip->i_sb,
|
|
"nXAD in not completely contained within XAD\n");
|
|
return -EIO;
|
|
}
|
|
|
|
index = index0;
|
|
newindex = index + 1;
|
|
nextindex = le16_to_cpu(p->header.nextindex);
|
|
|
|
#ifdef _JFS_WIP_NOCOALESCE
|
|
if (xoff < nxoff)
|
|
goto updateRight;
|
|
|
|
/*
|
|
* replace XAD with nXAD
|
|
*/
|
|
replace: /* (nxoff == xoff) */
|
|
if (nxlen == xlen) {
|
|
/* replace XAD with nXAD:recorded */
|
|
*xad = *nxad;
|
|
xad->flag = xflag & ~XAD_NOTRECORDED;
|
|
|
|
goto out;
|
|
} else /* (nxlen < xlen) */
|
|
goto updateLeft;
|
|
#endif /* _JFS_WIP_NOCOALESCE */
|
|
|
|
/* #ifdef _JFS_WIP_COALESCE */
|
|
if (xoff < nxoff)
|
|
goto coalesceRight;
|
|
|
|
/*
|
|
* coalesce with left XAD
|
|
*/
|
|
//coalesceLeft: /* (xoff == nxoff) */
|
|
/* is XAD first entry of page ? */
|
|
if (index == XTENTRYSTART)
|
|
goto replace;
|
|
|
|
/* is nXAD logically and physically contiguous with lXAD ? */
|
|
lxad = &p->xad[index - 1];
|
|
lxlen = lengthXAD(lxad);
|
|
if (!(lxad->flag & XAD_NOTRECORDED) &&
|
|
(nxoff == offsetXAD(lxad) + lxlen) &&
|
|
(nxaddr == addressXAD(lxad) + lxlen) &&
|
|
(lxlen + nxlen < MAXXLEN)) {
|
|
/* extend right lXAD */
|
|
index0 = index - 1;
|
|
XADlength(lxad, lxlen + nxlen);
|
|
|
|
/* If we just merged two extents together, need to make sure the
|
|
* right extent gets logged. If the left one is marked XAD_NEW,
|
|
* then we know it will be logged. Otherwise, mark as
|
|
* XAD_EXTENDED
|
|
*/
|
|
if (!(lxad->flag & XAD_NEW))
|
|
lxad->flag |= XAD_EXTENDED;
|
|
|
|
if (xlen > nxlen) {
|
|
/* truncate XAD */
|
|
XADoffset(xad, xoff + nxlen);
|
|
XADlength(xad, xlen - nxlen);
|
|
XADaddress(xad, xaddr + nxlen);
|
|
goto out;
|
|
} else { /* (xlen == nxlen) */
|
|
|
|
/* remove XAD */
|
|
if (index < nextindex - 1)
|
|
memmove(&p->xad[index], &p->xad[index + 1],
|
|
(nextindex - index -
|
|
1) << L2XTSLOTSIZE);
|
|
|
|
p->header.nextindex =
|
|
cpu_to_le16(le16_to_cpu(p->header.nextindex) -
|
|
1);
|
|
|
|
index = index0;
|
|
newindex = index + 1;
|
|
nextindex = le16_to_cpu(p->header.nextindex);
|
|
xoff = nxoff = offsetXAD(lxad);
|
|
xlen = nxlen = lxlen + nxlen;
|
|
xaddr = nxaddr = addressXAD(lxad);
|
|
goto coalesceRight;
|
|
}
|
|
}
|
|
|
|
/*
|
|
* replace XAD with nXAD
|
|
*/
|
|
replace: /* (nxoff == xoff) */
|
|
if (nxlen == xlen) {
|
|
/* replace XAD with nXAD:recorded */
|
|
*xad = *nxad;
|
|
xad->flag = xflag & ~XAD_NOTRECORDED;
|
|
|
|
goto coalesceRight;
|
|
} else /* (nxlen < xlen) */
|
|
goto updateLeft;
|
|
|
|
/*
|
|
* coalesce with right XAD
|
|
*/
|
|
coalesceRight: /* (xoff <= nxoff) */
|
|
/* is XAD last entry of page ? */
|
|
if (newindex == nextindex) {
|
|
if (xoff == nxoff)
|
|
goto out;
|
|
goto updateRight;
|
|
}
|
|
|
|
/* is nXAD logically and physically contiguous with rXAD ? */
|
|
rxad = &p->xad[index + 1];
|
|
rxlen = lengthXAD(rxad);
|
|
if (!(rxad->flag & XAD_NOTRECORDED) &&
|
|
(nxoff + nxlen == offsetXAD(rxad)) &&
|
|
(nxaddr + nxlen == addressXAD(rxad)) &&
|
|
(rxlen + nxlen < MAXXLEN)) {
|
|
/* extend left rXAD */
|
|
XADoffset(rxad, nxoff);
|
|
XADlength(rxad, rxlen + nxlen);
|
|
XADaddress(rxad, nxaddr);
|
|
|
|
/* If we just merged two extents together, need to make sure
|
|
* the left extent gets logged. If the right one is marked
|
|
* XAD_NEW, then we know it will be logged. Otherwise, mark as
|
|
* XAD_EXTENDED
|
|
*/
|
|
if (!(rxad->flag & XAD_NEW))
|
|
rxad->flag |= XAD_EXTENDED;
|
|
|
|
if (xlen > nxlen)
|
|
/* truncate XAD */
|
|
XADlength(xad, xlen - nxlen);
|
|
else { /* (xlen == nxlen) */
|
|
|
|
/* remove XAD */
|
|
memmove(&p->xad[index], &p->xad[index + 1],
|
|
(nextindex - index - 1) << L2XTSLOTSIZE);
|
|
|
|
p->header.nextindex =
|
|
cpu_to_le16(le16_to_cpu(p->header.nextindex) -
|
|
1);
|
|
}
|
|
|
|
goto out;
|
|
} else if (xoff == nxoff)
|
|
goto out;
|
|
|
|
if (xoff >= nxoff) {
|
|
XT_PUTPAGE(mp);
|
|
jfs_error(ip->i_sb, "xoff >= nxoff\n");
|
|
return -EIO;
|
|
}
|
|
/* #endif _JFS_WIP_COALESCE */
|
|
|
|
/*
|
|
* split XAD into (lXAD, nXAD):
|
|
*
|
|
* |---nXAD--->
|
|
* --|----------XAD----------|--
|
|
* |-lXAD-|
|
|
*/
|
|
updateRight: /* (xoff < nxoff) */
|
|
/* truncate old XAD as lXAD:not_recorded */
|
|
xad = &p->xad[index];
|
|
XADlength(xad, nxoff - xoff);
|
|
|
|
/* insert nXAD:recorded */
|
|
if (nextindex == le16_to_cpu(p->header.maxentry)) {
|
|
|
|
/* xtSpliUp() unpins leaf pages */
|
|
split.mp = mp;
|
|
split.index = newindex;
|
|
split.flag = xflag & ~XAD_NOTRECORDED;
|
|
split.off = nxoff;
|
|
split.len = nxlen;
|
|
split.addr = nxaddr;
|
|
split.pxdlist = NULL;
|
|
if ((rc = xtSplitUp(tid, ip, &split, &btstack)))
|
|
return rc;
|
|
|
|
/* get back old page */
|
|
XT_GETPAGE(ip, bn, mp, PSIZE, p, rc);
|
|
if (rc)
|
|
return rc;
|
|
/*
|
|
* if leaf root has been split, original root has been
|
|
* copied to new child page, i.e., original entry now
|
|
* resides on the new child page;
|
|
*/
|
|
if (p->header.flag & BT_INTERNAL) {
|
|
ASSERT(p->header.nextindex ==
|
|
cpu_to_le16(XTENTRYSTART + 1));
|
|
xad = &p->xad[XTENTRYSTART];
|
|
bn = addressXAD(xad);
|
|
XT_PUTPAGE(mp);
|
|
|
|
/* get new child page */
|
|
XT_GETPAGE(ip, bn, mp, PSIZE, p, rc);
|
|
if (rc)
|
|
return rc;
|
|
|
|
BT_MARK_DIRTY(mp, ip);
|
|
if (!test_cflag(COMMIT_Nolink, ip)) {
|
|
tlck = txLock(tid, ip, mp, tlckXTREE|tlckGROW);
|
|
xtlck = (struct xtlock *) & tlck->lock;
|
|
}
|
|
} else {
|
|
/* is nXAD on new page ? */
|
|
if (newindex >
|
|
(le16_to_cpu(p->header.maxentry) >> 1)) {
|
|
newindex =
|
|
newindex -
|
|
le16_to_cpu(p->header.nextindex) +
|
|
XTENTRYSTART;
|
|
newpage = 1;
|
|
}
|
|
}
|
|
} else {
|
|
/* if insert into middle, shift right remaining entries */
|
|
if (newindex < nextindex)
|
|
memmove(&p->xad[newindex + 1], &p->xad[newindex],
|
|
(nextindex - newindex) << L2XTSLOTSIZE);
|
|
|
|
/* insert the entry */
|
|
xad = &p->xad[newindex];
|
|
*xad = *nxad;
|
|
xad->flag = xflag & ~XAD_NOTRECORDED;
|
|
|
|
/* advance next available entry index. */
|
|
p->header.nextindex =
|
|
cpu_to_le16(le16_to_cpu(p->header.nextindex) + 1);
|
|
}
|
|
|
|
/*
|
|
* does nXAD force 3-way split ?
|
|
*
|
|
* |---nXAD--->|
|
|
* --|----------XAD-------------|--
|
|
* |-lXAD-| |-rXAD -|
|
|
*/
|
|
if (nxoff + nxlen == xoff + xlen)
|
|
goto out;
|
|
|
|
/* reorient nXAD as XAD for further split XAD into (nXAD, rXAD) */
|
|
if (newpage) {
|
|
/* close out old page */
|
|
if (!test_cflag(COMMIT_Nolink, ip)) {
|
|
xtlck->lwm.offset = (xtlck->lwm.offset) ?
|
|
min(index0, (int)xtlck->lwm.offset) : index0;
|
|
xtlck->lwm.length =
|
|
le16_to_cpu(p->header.nextindex) -
|
|
xtlck->lwm.offset;
|
|
}
|
|
|
|
bn = le64_to_cpu(p->header.next);
|
|
XT_PUTPAGE(mp);
|
|
|
|
/* get new right page */
|
|
XT_GETPAGE(ip, bn, mp, PSIZE, p, rc);
|
|
if (rc)
|
|
return rc;
|
|
|
|
BT_MARK_DIRTY(mp, ip);
|
|
if (!test_cflag(COMMIT_Nolink, ip)) {
|
|
tlck = txLock(tid, ip, mp, tlckXTREE | tlckGROW);
|
|
xtlck = (struct xtlock *) & tlck->lock;
|
|
}
|
|
|
|
index0 = index = newindex;
|
|
} else
|
|
index++;
|
|
|
|
newindex = index + 1;
|
|
nextindex = le16_to_cpu(p->header.nextindex);
|
|
xlen = xlen - (nxoff - xoff);
|
|
xoff = nxoff;
|
|
xaddr = nxaddr;
|
|
|
|
/* recompute split pages */
|
|
if (nextindex == le16_to_cpu(p->header.maxentry)) {
|
|
XT_PUTPAGE(mp);
|
|
|
|
if ((rc = xtSearch(ip, nxoff, NULL, &cmp, &btstack, XT_INSERT)))
|
|
return rc;
|
|
|
|
/* retrieve search result */
|
|
XT_GETSEARCH(ip, btstack.top, bn, mp, p, index0);
|
|
|
|
if (cmp != 0) {
|
|
XT_PUTPAGE(mp);
|
|
jfs_error(ip->i_sb, "xtSearch failed\n");
|
|
return -EIO;
|
|
}
|
|
|
|
if (index0 != index) {
|
|
XT_PUTPAGE(mp);
|
|
jfs_error(ip->i_sb, "unexpected value of index\n");
|
|
return -EIO;
|
|
}
|
|
}
|
|
|
|
/*
|
|
* split XAD into (nXAD, rXAD)
|
|
*
|
|
* ---nXAD---|
|
|
* --|----------XAD----------|--
|
|
* |-rXAD-|
|
|
*/
|
|
updateLeft: /* (nxoff == xoff) && (nxlen < xlen) */
|
|
/* update old XAD with nXAD:recorded */
|
|
xad = &p->xad[index];
|
|
*xad = *nxad;
|
|
xad->flag = xflag & ~XAD_NOTRECORDED;
|
|
|
|
/* insert rXAD:not_recorded */
|
|
xoff = xoff + nxlen;
|
|
xlen = xlen - nxlen;
|
|
xaddr = xaddr + nxlen;
|
|
if (nextindex == le16_to_cpu(p->header.maxentry)) {
|
|
/*
|
|
printf("xtUpdate.updateLeft.split p:0x%p\n", p);
|
|
*/
|
|
/* xtSpliUp() unpins leaf pages */
|
|
split.mp = mp;
|
|
split.index = newindex;
|
|
split.flag = xflag;
|
|
split.off = xoff;
|
|
split.len = xlen;
|
|
split.addr = xaddr;
|
|
split.pxdlist = NULL;
|
|
if ((rc = xtSplitUp(tid, ip, &split, &btstack)))
|
|
return rc;
|
|
|
|
/* get back old page */
|
|
XT_GETPAGE(ip, bn, mp, PSIZE, p, rc);
|
|
if (rc)
|
|
return rc;
|
|
|
|
/*
|
|
* if leaf root has been split, original root has been
|
|
* copied to new child page, i.e., original entry now
|
|
* resides on the new child page;
|
|
*/
|
|
if (p->header.flag & BT_INTERNAL) {
|
|
ASSERT(p->header.nextindex ==
|
|
cpu_to_le16(XTENTRYSTART + 1));
|
|
xad = &p->xad[XTENTRYSTART];
|
|
bn = addressXAD(xad);
|
|
XT_PUTPAGE(mp);
|
|
|
|
/* get new child page */
|
|
XT_GETPAGE(ip, bn, mp, PSIZE, p, rc);
|
|
if (rc)
|
|
return rc;
|
|
|
|
BT_MARK_DIRTY(mp, ip);
|
|
if (!test_cflag(COMMIT_Nolink, ip)) {
|
|
tlck = txLock(tid, ip, mp, tlckXTREE|tlckGROW);
|
|
xtlck = (struct xtlock *) & tlck->lock;
|
|
}
|
|
}
|
|
} else {
|
|
/* if insert into middle, shift right remaining entries */
|
|
if (newindex < nextindex)
|
|
memmove(&p->xad[newindex + 1], &p->xad[newindex],
|
|
(nextindex - newindex) << L2XTSLOTSIZE);
|
|
|
|
/* insert the entry */
|
|
xad = &p->xad[newindex];
|
|
XT_PUTENTRY(xad, xflag, xoff, xlen, xaddr);
|
|
|
|
/* advance next available entry index. */
|
|
p->header.nextindex =
|
|
cpu_to_le16(le16_to_cpu(p->header.nextindex) + 1);
|
|
}
|
|
|
|
out:
|
|
if (!test_cflag(COMMIT_Nolink, ip)) {
|
|
xtlck->lwm.offset = (xtlck->lwm.offset) ?
|
|
min(index0, (int)xtlck->lwm.offset) : index0;
|
|
xtlck->lwm.length = le16_to_cpu(p->header.nextindex) -
|
|
xtlck->lwm.offset;
|
|
}
|
|
|
|
/* unpin the leaf page */
|
|
XT_PUTPAGE(mp);
|
|
|
|
return rc;
|
|
}
|
|
|
|
|
|
/*
|
|
* xtAppend()
|
|
*
|
|
* function: grow in append mode from contiguous region specified ;
|
|
*
|
|
* parameter:
|
|
* tid - transaction id;
|
|
* ip - file object;
|
|
* xflag - extent flag:
|
|
* xoff - extent offset;
|
|
* maxblocks - max extent length;
|
|
* xlen - extent length (in/out);
|
|
* xaddrp - extent address pointer (in/out):
|
|
* flag -
|
|
*
|
|
* return:
|
|
*/
|
|
int xtAppend(tid_t tid, /* transaction id */
|
|
struct inode *ip, int xflag, s64 xoff, s32 maxblocks,
|
|
s32 * xlenp, /* (in/out) */
|
|
s64 * xaddrp, /* (in/out) */
|
|
int flag)
|
|
{
|
|
int rc = 0;
|
|
struct metapage *mp; /* meta-page buffer */
|
|
xtpage_t *p; /* base B+-tree index page */
|
|
s64 bn, xaddr;
|
|
int index, nextindex;
|
|
struct btstack btstack; /* traverse stack */
|
|
struct xtsplit split; /* split information */
|
|
xad_t *xad;
|
|
int cmp;
|
|
struct tlock *tlck;
|
|
struct xtlock *xtlck;
|
|
int nsplit, nblocks, xlen;
|
|
struct pxdlist pxdlist;
|
|
pxd_t *pxd;
|
|
s64 next;
|
|
|
|
xaddr = *xaddrp;
|
|
xlen = *xlenp;
|
|
jfs_info("xtAppend: xoff:0x%lx maxblocks:%d xlen:%d xaddr:0x%lx",
|
|
(ulong) xoff, maxblocks, xlen, (ulong) xaddr);
|
|
|
|
/*
|
|
* search for the entry location at which to insert:
|
|
*
|
|
* xtFastSearch() and xtSearch() both returns (leaf page
|
|
* pinned, index at which to insert).
|
|
* n.b. xtSearch() may return index of maxentry of
|
|
* the full page.
|
|
*/
|
|
if ((rc = xtSearch(ip, xoff, &next, &cmp, &btstack, XT_INSERT)))
|
|
return rc;
|
|
|
|
/* retrieve search result */
|
|
XT_GETSEARCH(ip, btstack.top, bn, mp, p, index);
|
|
|
|
if (cmp == 0) {
|
|
rc = -EEXIST;
|
|
goto out;
|
|
}
|
|
|
|
if (next)
|
|
xlen = min(xlen, (int)(next - xoff));
|
|
//insert:
|
|
/*
|
|
* insert entry for new extent
|
|
*/
|
|
xflag |= XAD_NEW;
|
|
|
|
/*
|
|
* if the leaf page is full, split the page and
|
|
* propagate up the router entry for the new page from split
|
|
*
|
|
* The xtSplitUp() will insert the entry and unpin the leaf page.
|
|
*/
|
|
nextindex = le16_to_cpu(p->header.nextindex);
|
|
if (nextindex < le16_to_cpu(p->header.maxentry))
|
|
goto insertLeaf;
|
|
|
|
/*
|
|
* allocate new index blocks to cover index page split(s)
|
|
*/
|
|
nsplit = btstack.nsplit;
|
|
split.pxdlist = &pxdlist;
|
|
pxdlist.maxnpxd = pxdlist.npxd = 0;
|
|
pxd = &pxdlist.pxd[0];
|
|
nblocks = JFS_SBI(ip->i_sb)->nbperpage;
|
|
for (; nsplit > 0; nsplit--, pxd++, xaddr += nblocks, maxblocks -= nblocks) {
|
|
if ((rc = dbAllocBottomUp(ip, xaddr, (s64) nblocks)) == 0) {
|
|
PXDaddress(pxd, xaddr);
|
|
PXDlength(pxd, nblocks);
|
|
|
|
pxdlist.maxnpxd++;
|
|
|
|
continue;
|
|
}
|
|
|
|
/* undo allocation */
|
|
|
|
goto out;
|
|
}
|
|
|
|
xlen = min(xlen, maxblocks);
|
|
|
|
/*
|
|
* allocate data extent requested
|
|
*/
|
|
if ((rc = dbAllocBottomUp(ip, xaddr, (s64) xlen)))
|
|
goto out;
|
|
|
|
split.mp = mp;
|
|
split.index = index;
|
|
split.flag = xflag;
|
|
split.off = xoff;
|
|
split.len = xlen;
|
|
split.addr = xaddr;
|
|
if ((rc = xtSplitUp(tid, ip, &split, &btstack))) {
|
|
/* undo data extent allocation */
|
|
dbFree(ip, *xaddrp, (s64) * xlenp);
|
|
|
|
return rc;
|
|
}
|
|
|
|
*xaddrp = xaddr;
|
|
*xlenp = xlen;
|
|
return 0;
|
|
|
|
/*
|
|
* insert the new entry into the leaf page
|
|
*/
|
|
insertLeaf:
|
|
/*
|
|
* allocate data extent requested
|
|
*/
|
|
if ((rc = dbAllocBottomUp(ip, xaddr, (s64) xlen)))
|
|
goto out;
|
|
|
|
BT_MARK_DIRTY(mp, ip);
|
|
/*
|
|
* acquire a transaction lock on the leaf page;
|
|
*
|
|
* action: xad insertion/extension;
|
|
*/
|
|
tlck = txLock(tid, ip, mp, tlckXTREE | tlckGROW);
|
|
xtlck = (struct xtlock *) & tlck->lock;
|
|
|
|
/* insert the new entry: mark the entry NEW */
|
|
xad = &p->xad[index];
|
|
XT_PUTENTRY(xad, xflag, xoff, xlen, xaddr);
|
|
|
|
/* advance next available entry index */
|
|
le16_add_cpu(&p->header.nextindex, 1);
|
|
|
|
xtlck->lwm.offset =
|
|
(xtlck->lwm.offset) ? min(index,(int) xtlck->lwm.offset) : index;
|
|
xtlck->lwm.length = le16_to_cpu(p->header.nextindex) -
|
|
xtlck->lwm.offset;
|
|
|
|
*xaddrp = xaddr;
|
|
*xlenp = xlen;
|
|
|
|
out:
|
|
/* unpin the leaf page */
|
|
XT_PUTPAGE(mp);
|
|
|
|
return rc;
|
|
}
|
|
#ifdef _STILL_TO_PORT
|
|
|
|
/* - TBD for defragmentaion/reorganization -
|
|
*
|
|
* xtDelete()
|
|
*
|
|
* function:
|
|
* delete the entry with the specified key.
|
|
*
|
|
* N.B.: whole extent of the entry is assumed to be deleted.
|
|
*
|
|
* parameter:
|
|
*
|
|
* return:
|
|
* ENOENT: if the entry is not found.
|
|
*
|
|
* exception:
|
|
*/
|
|
int xtDelete(tid_t tid, struct inode *ip, s64 xoff, s32 xlen, int flag)
|
|
{
|
|
int rc = 0;
|
|
struct btstack btstack;
|
|
int cmp;
|
|
s64 bn;
|
|
struct metapage *mp;
|
|
xtpage_t *p;
|
|
int index, nextindex;
|
|
struct tlock *tlck;
|
|
struct xtlock *xtlck;
|
|
|
|
/*
|
|
* find the matching entry; xtSearch() pins the page
|
|
*/
|
|
if ((rc = xtSearch(ip, xoff, NULL, &cmp, &btstack, 0)))
|
|
return rc;
|
|
|
|
XT_GETSEARCH(ip, btstack.top, bn, mp, p, index);
|
|
if (cmp) {
|
|
/* unpin the leaf page */
|
|
XT_PUTPAGE(mp);
|
|
return -ENOENT;
|
|
}
|
|
|
|
/*
|
|
* delete the entry from the leaf page
|
|
*/
|
|
nextindex = le16_to_cpu(p->header.nextindex);
|
|
le16_add_cpu(&p->header.nextindex, -1);
|
|
|
|
/*
|
|
* if the leaf page bocome empty, free the page
|
|
*/
|
|
if (p->header.nextindex == cpu_to_le16(XTENTRYSTART))
|
|
return (xtDeleteUp(tid, ip, mp, p, &btstack));
|
|
|
|
BT_MARK_DIRTY(mp, ip);
|
|
/*
|
|
* acquire a transaction lock on the leaf page;
|
|
*
|
|
* action:xad deletion;
|
|
*/
|
|
tlck = txLock(tid, ip, mp, tlckXTREE);
|
|
xtlck = (struct xtlock *) & tlck->lock;
|
|
xtlck->lwm.offset =
|
|
(xtlck->lwm.offset) ? min(index, xtlck->lwm.offset) : index;
|
|
|
|
/* if delete from middle, shift left/compact the remaining entries */
|
|
if (index < nextindex - 1)
|
|
memmove(&p->xad[index], &p->xad[index + 1],
|
|
(nextindex - index - 1) * sizeof(xad_t));
|
|
|
|
XT_PUTPAGE(mp);
|
|
|
|
return 0;
|
|
}
|
|
|
|
|
|
/* - TBD for defragmentaion/reorganization -
|
|
*
|
|
* xtDeleteUp()
|
|
*
|
|
* function:
|
|
* free empty pages as propagating deletion up the tree
|
|
*
|
|
* parameter:
|
|
*
|
|
* return:
|
|
*/
|
|
static int
|
|
xtDeleteUp(tid_t tid, struct inode *ip,
|
|
struct metapage * fmp, xtpage_t * fp, struct btstack * btstack)
|
|
{
|
|
int rc = 0;
|
|
struct metapage *mp;
|
|
xtpage_t *p;
|
|
int index, nextindex;
|
|
s64 xaddr;
|
|
int xlen;
|
|
struct btframe *parent;
|
|
struct tlock *tlck;
|
|
struct xtlock *xtlck;
|
|
|
|
/*
|
|
* keep root leaf page which has become empty
|
|
*/
|
|
if (fp->header.flag & BT_ROOT) {
|
|
/* keep the root page */
|
|
fp->header.flag &= ~BT_INTERNAL;
|
|
fp->header.flag |= BT_LEAF;
|
|
fp->header.nextindex = cpu_to_le16(XTENTRYSTART);
|
|
|
|
/* XT_PUTPAGE(fmp); */
|
|
|
|
return 0;
|
|
}
|
|
|
|
/*
|
|
* free non-root leaf page
|
|
*/
|
|
if ((rc = xtRelink(tid, ip, fp))) {
|
|
XT_PUTPAGE(fmp);
|
|
return rc;
|
|
}
|
|
|
|
xaddr = addressPXD(&fp->header.self);
|
|
xlen = lengthPXD(&fp->header.self);
|
|
/* free the page extent */
|
|
dbFree(ip, xaddr, (s64) xlen);
|
|
|
|
/* free the buffer page */
|
|
discard_metapage(fmp);
|
|
|
|
/*
|
|
* propagate page deletion up the index tree
|
|
*
|
|
* If the delete from the parent page makes it empty,
|
|
* continue all the way up the tree.
|
|
* stop if the root page is reached (which is never deleted) or
|
|
* if the entry deletion does not empty the page.
|
|
*/
|
|
while ((parent = BT_POP(btstack)) != NULL) {
|
|
/* get/pin the parent page <sp> */
|
|
XT_GETPAGE(ip, parent->bn, mp, PSIZE, p, rc);
|
|
if (rc)
|
|
return rc;
|
|
|
|
index = parent->index;
|
|
|
|
/* delete the entry for the freed child page from parent.
|
|
*/
|
|
nextindex = le16_to_cpu(p->header.nextindex);
|
|
|
|
/*
|
|
* the parent has the single entry being deleted:
|
|
* free the parent page which has become empty.
|
|
*/
|
|
if (nextindex == 1) {
|
|
if (p->header.flag & BT_ROOT) {
|
|
/* keep the root page */
|
|
p->header.flag &= ~BT_INTERNAL;
|
|
p->header.flag |= BT_LEAF;
|
|
p->header.nextindex =
|
|
cpu_to_le16(XTENTRYSTART);
|
|
|
|
/* XT_PUTPAGE(mp); */
|
|
|
|
break;
|
|
} else {
|
|
/* free the parent page */
|
|
if ((rc = xtRelink(tid, ip, p)))
|
|
return rc;
|
|
|
|
xaddr = addressPXD(&p->header.self);
|
|
/* free the page extent */
|
|
dbFree(ip, xaddr,
|
|
(s64) JFS_SBI(ip->i_sb)->nbperpage);
|
|
|
|
/* unpin/free the buffer page */
|
|
discard_metapage(mp);
|
|
|
|
/* propagate up */
|
|
continue;
|
|
}
|
|
}
|
|
/*
|
|
* the parent has other entries remaining:
|
|
* delete the router entry from the parent page.
|
|
*/
|
|
else {
|
|
BT_MARK_DIRTY(mp, ip);
|
|
/*
|
|
* acquire a transaction lock on the leaf page;
|
|
*
|
|
* action:xad deletion;
|
|
*/
|
|
tlck = txLock(tid, ip, mp, tlckXTREE);
|
|
xtlck = (struct xtlock *) & tlck->lock;
|
|
xtlck->lwm.offset =
|
|
(xtlck->lwm.offset) ? min(index,
|
|
xtlck->lwm.
|
|
offset) : index;
|
|
|
|
/* if delete from middle,
|
|
* shift left/compact the remaining entries in the page
|
|
*/
|
|
if (index < nextindex - 1)
|
|
memmove(&p->xad[index], &p->xad[index + 1],
|
|
(nextindex - index -
|
|
1) << L2XTSLOTSIZE);
|
|
|
|
le16_add_cpu(&p->header.nextindex, -1);
|
|
jfs_info("xtDeleteUp(entry): 0x%lx[%d]",
|
|
(ulong) parent->bn, index);
|
|
}
|
|
|
|
/* unpin the parent page */
|
|
XT_PUTPAGE(mp);
|
|
|
|
/* exit propagation up */
|
|
break;
|
|
}
|
|
|
|
return 0;
|
|
}
|
|
|
|
|
|
/*
|
|
* NAME: xtRelocate()
|
|
*
|
|
* FUNCTION: relocate xtpage or data extent of regular file;
|
|
* This function is mainly used by defragfs utility.
|
|
*
|
|
* NOTE: This routine does not have the logic to handle
|
|
* uncommitted allocated extent. The caller should call
|
|
* txCommit() to commit all the allocation before call
|
|
* this routine.
|
|
*/
|
|
int
|
|
xtRelocate(tid_t tid, struct inode * ip, xad_t * oxad, /* old XAD */
|
|
s64 nxaddr, /* new xaddr */
|
|
int xtype)
|
|
{ /* extent type: XTPAGE or DATAEXT */
|
|
int rc = 0;
|
|
struct tblock *tblk;
|
|
struct tlock *tlck;
|
|
struct xtlock *xtlck;
|
|
struct metapage *mp, *pmp, *lmp, *rmp; /* meta-page buffer */
|
|
xtpage_t *p, *pp, *rp, *lp; /* base B+-tree index page */
|
|
xad_t *xad;
|
|
pxd_t *pxd;
|
|
s64 xoff, xsize;
|
|
int xlen;
|
|
s64 oxaddr, sxaddr, dxaddr, nextbn, prevbn;
|
|
cbuf_t *cp;
|
|
s64 offset, nbytes, nbrd, pno;
|
|
int nb, npages, nblks;
|
|
s64 bn;
|
|
int cmp;
|
|
int index;
|
|
struct pxd_lock *pxdlock;
|
|
struct btstack btstack; /* traverse stack */
|
|
|
|
xtype = xtype & EXTENT_TYPE;
|
|
|
|
xoff = offsetXAD(oxad);
|
|
oxaddr = addressXAD(oxad);
|
|
xlen = lengthXAD(oxad);
|
|
|
|
/* validate extent offset */
|
|
offset = xoff << JFS_SBI(ip->i_sb)->l2bsize;
|
|
if (offset >= ip->i_size)
|
|
return -ESTALE; /* stale extent */
|
|
|
|
jfs_info("xtRelocate: xtype:%d xoff:0x%lx xlen:0x%x xaddr:0x%lx:0x%lx",
|
|
xtype, (ulong) xoff, xlen, (ulong) oxaddr, (ulong) nxaddr);
|
|
|
|
/*
|
|
* 1. get and validate the parent xtpage/xad entry
|
|
* covering the source extent to be relocated;
|
|
*/
|
|
if (xtype == DATAEXT) {
|
|
/* search in leaf entry */
|
|
rc = xtSearch(ip, xoff, NULL, &cmp, &btstack, 0);
|
|
if (rc)
|
|
return rc;
|
|
|
|
/* retrieve search result */
|
|
XT_GETSEARCH(ip, btstack.top, bn, pmp, pp, index);
|
|
|
|
if (cmp) {
|
|
XT_PUTPAGE(pmp);
|
|
return -ESTALE;
|
|
}
|
|
|
|
/* validate for exact match with a single entry */
|
|
xad = &pp->xad[index];
|
|
if (addressXAD(xad) != oxaddr || lengthXAD(xad) != xlen) {
|
|
XT_PUTPAGE(pmp);
|
|
return -ESTALE;
|
|
}
|
|
} else { /* (xtype == XTPAGE) */
|
|
|
|
/* search in internal entry */
|
|
rc = xtSearchNode(ip, oxad, &cmp, &btstack, 0);
|
|
if (rc)
|
|
return rc;
|
|
|
|
/* retrieve search result */
|
|
XT_GETSEARCH(ip, btstack.top, bn, pmp, pp, index);
|
|
|
|
if (cmp) {
|
|
XT_PUTPAGE(pmp);
|
|
return -ESTALE;
|
|
}
|
|
|
|
/* xtSearchNode() validated for exact match with a single entry
|
|
*/
|
|
xad = &pp->xad[index];
|
|
}
|
|
jfs_info("xtRelocate: parent xad entry validated.");
|
|
|
|
/*
|
|
* 2. relocate the extent
|
|
*/
|
|
if (xtype == DATAEXT) {
|
|
/* if the extent is allocated-but-not-recorded
|
|
* there is no real data to be moved in this extent,
|
|
*/
|
|
if (xad->flag & XAD_NOTRECORDED)
|
|
goto out;
|
|
else
|
|
/* release xtpage for cmRead()/xtLookup() */
|
|
XT_PUTPAGE(pmp);
|
|
|
|
/*
|
|
* cmRelocate()
|
|
*
|
|
* copy target data pages to be relocated;
|
|
*
|
|
* data extent must start at page boundary and
|
|
* multiple of page size (except the last data extent);
|
|
* read in each page of the source data extent into cbuf,
|
|
* update the cbuf extent descriptor of the page to be
|
|
* homeward bound to new dst data extent
|
|
* copy the data from the old extent to new extent.
|
|
* copy is essential for compressed files to avoid problems
|
|
* that can arise if there was a change in compression
|
|
* algorithms.
|
|
* it is a good strategy because it may disrupt cache
|
|
* policy to keep the pages in memory afterwards.
|
|
*/
|
|
offset = xoff << JFS_SBI(ip->i_sb)->l2bsize;
|
|
assert((offset & CM_OFFSET) == 0);
|
|
nbytes = xlen << JFS_SBI(ip->i_sb)->l2bsize;
|
|
pno = offset >> CM_L2BSIZE;
|
|
npages = (nbytes + (CM_BSIZE - 1)) >> CM_L2BSIZE;
|
|
/*
|
|
npages = ((offset + nbytes - 1) >> CM_L2BSIZE) -
|
|
(offset >> CM_L2BSIZE) + 1;
|
|
*/
|
|
sxaddr = oxaddr;
|
|
dxaddr = nxaddr;
|
|
|
|
/* process the request one cache buffer at a time */
|
|
for (nbrd = 0; nbrd < nbytes; nbrd += nb,
|
|
offset += nb, pno++, npages--) {
|
|
/* compute page size */
|
|
nb = min(nbytes - nbrd, CM_BSIZE);
|
|
|
|
/* get the cache buffer of the page */
|
|
if (rc = cmRead(ip, offset, npages, &cp))
|
|
break;
|
|
|
|
assert(addressPXD(&cp->cm_pxd) == sxaddr);
|
|
assert(!cp->cm_modified);
|
|
|
|
/* bind buffer with the new extent address */
|
|
nblks = nb >> JFS_IP(ip->i_sb)->l2bsize;
|
|
cmSetXD(ip, cp, pno, dxaddr, nblks);
|
|
|
|
/* release the cbuf, mark it as modified */
|
|
cmPut(cp, true);
|
|
|
|
dxaddr += nblks;
|
|
sxaddr += nblks;
|
|
}
|
|
|
|
/* get back parent page */
|
|
if ((rc = xtSearch(ip, xoff, NULL, &cmp, &btstack, 0)))
|
|
return rc;
|
|
|
|
XT_GETSEARCH(ip, btstack.top, bn, pmp, pp, index);
|
|
jfs_info("xtRelocate: target data extent relocated.");
|
|
} else { /* (xtype == XTPAGE) */
|
|
|
|
/*
|
|
* read in the target xtpage from the source extent;
|
|
*/
|
|
XT_GETPAGE(ip, oxaddr, mp, PSIZE, p, rc);
|
|
if (rc) {
|
|
XT_PUTPAGE(pmp);
|
|
return rc;
|
|
}
|
|
|
|
/*
|
|
* read in sibling pages if any to update sibling pointers;
|
|
*/
|
|
rmp = NULL;
|
|
if (p->header.next) {
|
|
nextbn = le64_to_cpu(p->header.next);
|
|
XT_GETPAGE(ip, nextbn, rmp, PSIZE, rp, rc);
|
|
if (rc) {
|
|
XT_PUTPAGE(pmp);
|
|
XT_PUTPAGE(mp);
|
|
return (rc);
|
|
}
|
|
}
|
|
|
|
lmp = NULL;
|
|
if (p->header.prev) {
|
|
prevbn = le64_to_cpu(p->header.prev);
|
|
XT_GETPAGE(ip, prevbn, lmp, PSIZE, lp, rc);
|
|
if (rc) {
|
|
XT_PUTPAGE(pmp);
|
|
XT_PUTPAGE(mp);
|
|
if (rmp)
|
|
XT_PUTPAGE(rmp);
|
|
return (rc);
|
|
}
|
|
}
|
|
|
|
/* at this point, all xtpages to be updated are in memory */
|
|
|
|
/*
|
|
* update sibling pointers of sibling xtpages if any;
|
|
*/
|
|
if (lmp) {
|
|
BT_MARK_DIRTY(lmp, ip);
|
|
tlck = txLock(tid, ip, lmp, tlckXTREE | tlckRELINK);
|
|
lp->header.next = cpu_to_le64(nxaddr);
|
|
XT_PUTPAGE(lmp);
|
|
}
|
|
|
|
if (rmp) {
|
|
BT_MARK_DIRTY(rmp, ip);
|
|
tlck = txLock(tid, ip, rmp, tlckXTREE | tlckRELINK);
|
|
rp->header.prev = cpu_to_le64(nxaddr);
|
|
XT_PUTPAGE(rmp);
|
|
}
|
|
|
|
/*
|
|
* update the target xtpage to be relocated
|
|
*
|
|
* update the self address of the target page
|
|
* and write to destination extent;
|
|
* redo image covers the whole xtpage since it is new page
|
|
* to the destination extent;
|
|
* update of bmap for the free of source extent
|
|
* of the target xtpage itself:
|
|
* update of bmap for the allocation of destination extent
|
|
* of the target xtpage itself:
|
|
* update of bmap for the extents covered by xad entries in
|
|
* the target xtpage is not necessary since they are not
|
|
* updated;
|
|
* if not committed before this relocation,
|
|
* target page may contain XAD_NEW entries which must
|
|
* be scanned for bmap update (logredo() always
|
|
* scan xtpage REDOPAGE image for bmap update);
|
|
* if committed before this relocation (tlckRELOCATE),
|
|
* scan may be skipped by commit() and logredo();
|
|
*/
|
|
BT_MARK_DIRTY(mp, ip);
|
|
/* tlckNEW init xtlck->lwm.offset = XTENTRYSTART; */
|
|
tlck = txLock(tid, ip, mp, tlckXTREE | tlckNEW);
|
|
xtlck = (struct xtlock *) & tlck->lock;
|
|
|
|
/* update the self address in the xtpage header */
|
|
pxd = &p->header.self;
|
|
PXDaddress(pxd, nxaddr);
|
|
|
|
/* linelock for the after image of the whole page */
|
|
xtlck->lwm.length =
|
|
le16_to_cpu(p->header.nextindex) - xtlck->lwm.offset;
|
|
|
|
/* update the buffer extent descriptor of target xtpage */
|
|
xsize = xlen << JFS_SBI(ip->i_sb)->l2bsize;
|
|
bmSetXD(mp, nxaddr, xsize);
|
|
|
|
/* unpin the target page to new homeward bound */
|
|
XT_PUTPAGE(mp);
|
|
jfs_info("xtRelocate: target xtpage relocated.");
|
|
}
|
|
|
|
/*
|
|
* 3. acquire maplock for the source extent to be freed;
|
|
*
|
|
* acquire a maplock saving the src relocated extent address;
|
|
* to free of the extent at commit time;
|
|
*/
|
|
out:
|
|
/* if DATAEXT relocation, write a LOG_UPDATEMAP record for
|
|
* free PXD of the source data extent (logredo() will update
|
|
* bmap for free of source data extent), and update bmap for
|
|
* free of the source data extent;
|
|
*/
|
|
if (xtype == DATAEXT)
|
|
tlck = txMaplock(tid, ip, tlckMAP);
|
|
/* if XTPAGE relocation, write a LOG_NOREDOPAGE record
|
|
* for the source xtpage (logredo() will init NoRedoPage
|
|
* filter and will also update bmap for free of the source
|
|
* xtpage), and update bmap for free of the source xtpage;
|
|
* N.B. We use tlckMAP instead of tlkcXTREE because there
|
|
* is no buffer associated with this lock since the buffer
|
|
* has been redirected to the target location.
|
|
*/
|
|
else /* (xtype == XTPAGE) */
|
|
tlck = txMaplock(tid, ip, tlckMAP | tlckRELOCATE);
|
|
|
|
pxdlock = (struct pxd_lock *) & tlck->lock;
|
|
pxdlock->flag = mlckFREEPXD;
|
|
PXDaddress(&pxdlock->pxd, oxaddr);
|
|
PXDlength(&pxdlock->pxd, xlen);
|
|
pxdlock->index = 1;
|
|
|
|
/*
|
|
* 4. update the parent xad entry for relocation;
|
|
*
|
|
* acquire tlck for the parent entry with XAD_NEW as entry
|
|
* update which will write LOG_REDOPAGE and update bmap for
|
|
* allocation of XAD_NEW destination extent;
|
|
*/
|
|
jfs_info("xtRelocate: update parent xad entry.");
|
|
BT_MARK_DIRTY(pmp, ip);
|
|
tlck = txLock(tid, ip, pmp, tlckXTREE | tlckGROW);
|
|
xtlck = (struct xtlock *) & tlck->lock;
|
|
|
|
/* update the XAD with the new destination extent; */
|
|
xad = &pp->xad[index];
|
|
xad->flag |= XAD_NEW;
|
|
XADaddress(xad, nxaddr);
|
|
|
|
xtlck->lwm.offset = min(index, xtlck->lwm.offset);
|
|
xtlck->lwm.length = le16_to_cpu(pp->header.nextindex) -
|
|
xtlck->lwm.offset;
|
|
|
|
/* unpin the parent xtpage */
|
|
XT_PUTPAGE(pmp);
|
|
|
|
return rc;
|
|
}
|
|
|
|
|
|
/*
|
|
* xtSearchNode()
|
|
*
|
|
* function: search for the internal xad entry covering specified extent.
|
|
* This function is mainly used by defragfs utility.
|
|
*
|
|
* parameters:
|
|
* ip - file object;
|
|
* xad - extent to find;
|
|
* cmpp - comparison result:
|
|
* btstack - traverse stack;
|
|
* flag - search process flag;
|
|
*
|
|
* returns:
|
|
* btstack contains (bn, index) of search path traversed to the entry.
|
|
* *cmpp is set to result of comparison with the entry returned.
|
|
* the page containing the entry is pinned at exit.
|
|
*/
|
|
static int xtSearchNode(struct inode *ip, xad_t * xad, /* required XAD entry */
|
|
int *cmpp, struct btstack * btstack, int flag)
|
|
{
|
|
int rc = 0;
|
|
s64 xoff, xaddr;
|
|
int xlen;
|
|
int cmp = 1; /* init for empty page */
|
|
s64 bn; /* block number */
|
|
struct metapage *mp; /* meta-page buffer */
|
|
xtpage_t *p; /* page */
|
|
int base, index, lim;
|
|
struct btframe *btsp;
|
|
s64 t64;
|
|
|
|
BT_CLR(btstack);
|
|
|
|
xoff = offsetXAD(xad);
|
|
xlen = lengthXAD(xad);
|
|
xaddr = addressXAD(xad);
|
|
|
|
/*
|
|
* search down tree from root:
|
|
*
|
|
* between two consecutive entries of <Ki, Pi> and <Kj, Pj> of
|
|
* internal page, child page Pi contains entry with k, Ki <= K < Kj.
|
|
*
|
|
* if entry with search key K is not found
|
|
* internal page search find the entry with largest key Ki
|
|
* less than K which point to the child page to search;
|
|
* leaf page search find the entry with smallest key Kj
|
|
* greater than K so that the returned index is the position of
|
|
* the entry to be shifted right for insertion of new entry.
|
|
* for empty tree, search key is greater than any key of the tree.
|
|
*
|
|
* by convention, root bn = 0.
|
|
*/
|
|
for (bn = 0;;) {
|
|
/* get/pin the page to search */
|
|
XT_GETPAGE(ip, bn, mp, PSIZE, p, rc);
|
|
if (rc)
|
|
return rc;
|
|
if (p->header.flag & BT_LEAF) {
|
|
XT_PUTPAGE(mp);
|
|
return -ESTALE;
|
|
}
|
|
|
|
lim = le16_to_cpu(p->header.nextindex) - XTENTRYSTART;
|
|
|
|
/*
|
|
* binary search with search key K on the current page
|
|
*/
|
|
for (base = XTENTRYSTART; lim; lim >>= 1) {
|
|
index = base + (lim >> 1);
|
|
|
|
XT_CMP(cmp, xoff, &p->xad[index], t64);
|
|
if (cmp == 0) {
|
|
/*
|
|
* search hit
|
|
*
|
|
* verify for exact match;
|
|
*/
|
|
if (xaddr == addressXAD(&p->xad[index]) &&
|
|
xoff == offsetXAD(&p->xad[index])) {
|
|
*cmpp = cmp;
|
|
|
|
/* save search result */
|
|
btsp = btstack->top;
|
|
btsp->bn = bn;
|
|
btsp->index = index;
|
|
btsp->mp = mp;
|
|
|
|
return 0;
|
|
}
|
|
|
|
/* descend/search its child page */
|
|
goto next;
|
|
}
|
|
|
|
if (cmp > 0) {
|
|
base = index + 1;
|
|
--lim;
|
|
}
|
|
}
|
|
|
|
/*
|
|
* search miss - non-leaf page:
|
|
*
|
|
* base is the smallest index with key (Kj) greater than
|
|
* search key (K) and may be zero or maxentry index.
|
|
* if base is non-zero, decrement base by one to get the parent
|
|
* entry of the child page to search.
|
|
*/
|
|
index = base ? base - 1 : base;
|
|
|
|
/*
|
|
* go down to child page
|
|
*/
|
|
next:
|
|
/* get the child page block number */
|
|
bn = addressXAD(&p->xad[index]);
|
|
|
|
/* unpin the parent page */
|
|
XT_PUTPAGE(mp);
|
|
}
|
|
}
|
|
|
|
|
|
/*
|
|
* xtRelink()
|
|
*
|
|
* function:
|
|
* link around a freed page.
|
|
*
|
|
* Parameter:
|
|
* int tid,
|
|
* struct inode *ip,
|
|
* xtpage_t *p)
|
|
*
|
|
* returns:
|
|
*/
|
|
static int xtRelink(tid_t tid, struct inode *ip, xtpage_t * p)
|
|
{
|
|
int rc = 0;
|
|
struct metapage *mp;
|
|
s64 nextbn, prevbn;
|
|
struct tlock *tlck;
|
|
|
|
nextbn = le64_to_cpu(p->header.next);
|
|
prevbn = le64_to_cpu(p->header.prev);
|
|
|
|
/* update prev pointer of the next page */
|
|
if (nextbn != 0) {
|
|
XT_GETPAGE(ip, nextbn, mp, PSIZE, p, rc);
|
|
if (rc)
|
|
return rc;
|
|
|
|
/*
|
|
* acquire a transaction lock on the page;
|
|
*
|
|
* action: update prev pointer;
|
|
*/
|
|
BT_MARK_DIRTY(mp, ip);
|
|
tlck = txLock(tid, ip, mp, tlckXTREE | tlckRELINK);
|
|
|
|
/* the page may already have been tlock'd */
|
|
|
|
p->header.prev = cpu_to_le64(prevbn);
|
|
|
|
XT_PUTPAGE(mp);
|
|
}
|
|
|
|
/* update next pointer of the previous page */
|
|
if (prevbn != 0) {
|
|
XT_GETPAGE(ip, prevbn, mp, PSIZE, p, rc);
|
|
if (rc)
|
|
return rc;
|
|
|
|
/*
|
|
* acquire a transaction lock on the page;
|
|
*
|
|
* action: update next pointer;
|
|
*/
|
|
BT_MARK_DIRTY(mp, ip);
|
|
tlck = txLock(tid, ip, mp, tlckXTREE | tlckRELINK);
|
|
|
|
/* the page may already have been tlock'd */
|
|
|
|
p->header.next = le64_to_cpu(nextbn);
|
|
|
|
XT_PUTPAGE(mp);
|
|
}
|
|
|
|
return 0;
|
|
}
|
|
#endif /* _STILL_TO_PORT */
|
|
|
|
|
|
/*
|
|
* xtInitRoot()
|
|
*
|
|
* initialize file root (inline in inode)
|
|
*/
|
|
void xtInitRoot(tid_t tid, struct inode *ip)
|
|
{
|
|
xtpage_t *p;
|
|
|
|
/*
|
|
* acquire a transaction lock on the root
|
|
*
|
|
* action:
|
|
*/
|
|
txLock(tid, ip, (struct metapage *) &JFS_IP(ip)->bxflag,
|
|
tlckXTREE | tlckNEW);
|
|
p = &JFS_IP(ip)->i_xtroot;
|
|
|
|
p->header.flag = DXD_INDEX | BT_ROOT | BT_LEAF;
|
|
p->header.nextindex = cpu_to_le16(XTENTRYSTART);
|
|
|
|
if (S_ISDIR(ip->i_mode))
|
|
p->header.maxentry = cpu_to_le16(XTROOTINITSLOT_DIR);
|
|
else {
|
|
p->header.maxentry = cpu_to_le16(XTROOTINITSLOT);
|
|
ip->i_size = 0;
|
|
}
|
|
|
|
|
|
return;
|
|
}
|
|
|
|
|
|
/*
|
|
* We can run into a deadlock truncating a file with a large number of
|
|
* xtree pages (large fragmented file). A robust fix would entail a
|
|
* reservation system where we would reserve a number of metadata pages
|
|
* and tlocks which we would be guaranteed without a deadlock. Without
|
|
* this, a partial fix is to limit number of metadata pages we will lock
|
|
* in a single transaction. Currently we will truncate the file so that
|
|
* no more than 50 leaf pages will be locked. The caller of xtTruncate
|
|
* will be responsible for ensuring that the current transaction gets
|
|
* committed, and that subsequent transactions are created to truncate
|
|
* the file further if needed.
|
|
*/
|
|
#define MAX_TRUNCATE_LEAVES 50
|
|
|
|
/*
|
|
* xtTruncate()
|
|
*
|
|
* function:
|
|
* traverse for truncation logging backward bottom up;
|
|
* terminate at the last extent entry at the current subtree
|
|
* root page covering new down size.
|
|
* truncation may occur within the last extent entry.
|
|
*
|
|
* parameter:
|
|
* int tid,
|
|
* struct inode *ip,
|
|
* s64 newsize,
|
|
* int type) {PWMAP, PMAP, WMAP; DELETE, TRUNCATE}
|
|
*
|
|
* return:
|
|
*
|
|
* note:
|
|
* PWMAP:
|
|
* 1. truncate (non-COMMIT_NOLINK file)
|
|
* by jfs_truncate() or jfs_open(O_TRUNC):
|
|
* xtree is updated;
|
|
* 2. truncate index table of directory when last entry removed
|
|
* map update via tlock at commit time;
|
|
* PMAP:
|
|
* Call xtTruncate_pmap instead
|
|
* WMAP:
|
|
* 1. remove (free zero link count) on last reference release
|
|
* (pmap has been freed at commit zero link count);
|
|
* 2. truncate (COMMIT_NOLINK file, i.e., tmp file):
|
|
* xtree is updated;
|
|
* map update directly at truncation time;
|
|
*
|
|
* if (DELETE)
|
|
* no LOG_NOREDOPAGE is required (NOREDOFILE is sufficient);
|
|
* else if (TRUNCATE)
|
|
* must write LOG_NOREDOPAGE for deleted index page;
|
|
*
|
|
* pages may already have been tlocked by anonymous transactions
|
|
* during file growth (i.e., write) before truncation;
|
|
*
|
|
* except last truncated entry, deleted entries remains as is
|
|
* in the page (nextindex is updated) for other use
|
|
* (e.g., log/update allocation map): this avoid copying the page
|
|
* info but delay free of pages;
|
|
*
|
|
*/
|
|
s64 xtTruncate(tid_t tid, struct inode *ip, s64 newsize, int flag)
|
|
{
|
|
int rc = 0;
|
|
s64 teof;
|
|
struct metapage *mp;
|
|
xtpage_t *p;
|
|
s64 bn;
|
|
int index, nextindex;
|
|
xad_t *xad;
|
|
s64 xoff, xaddr;
|
|
int xlen, len, freexlen;
|
|
struct btstack btstack;
|
|
struct btframe *parent;
|
|
struct tblock *tblk = NULL;
|
|
struct tlock *tlck = NULL;
|
|
struct xtlock *xtlck = NULL;
|
|
struct xdlistlock xadlock; /* maplock for COMMIT_WMAP */
|
|
struct pxd_lock *pxdlock; /* maplock for COMMIT_WMAP */
|
|
s64 nfreed;
|
|
int freed, log;
|
|
int locked_leaves = 0;
|
|
|
|
/* save object truncation type */
|
|
if (tid) {
|
|
tblk = tid_to_tblock(tid);
|
|
tblk->xflag |= flag;
|
|
}
|
|
|
|
nfreed = 0;
|
|
|
|
flag &= COMMIT_MAP;
|
|
assert(flag != COMMIT_PMAP);
|
|
|
|
if (flag == COMMIT_PWMAP)
|
|
log = 1;
|
|
else {
|
|
log = 0;
|
|
xadlock.flag = mlckFREEXADLIST;
|
|
xadlock.index = 1;
|
|
}
|
|
|
|
/*
|
|
* if the newsize is not an integral number of pages,
|
|
* the file between newsize and next page boundary will
|
|
* be cleared.
|
|
* if truncating into a file hole, it will cause
|
|
* a full block to be allocated for the logical block.
|
|
*/
|
|
|
|
/*
|
|
* release page blocks of truncated region <teof, eof>
|
|
*
|
|
* free the data blocks from the leaf index blocks.
|
|
* delete the parent index entries corresponding to
|
|
* the freed child data/index blocks.
|
|
* free the index blocks themselves which aren't needed
|
|
* in new sized file.
|
|
*
|
|
* index blocks are updated only if the blocks are to be
|
|
* retained in the new sized file.
|
|
* if type is PMAP, the data and index pages are NOT
|
|
* freed, and the data and index blocks are NOT freed
|
|
* from working map.
|
|
* (this will allow continued access of data/index of
|
|
* temporary file (zerolink count file truncated to zero-length)).
|
|
*/
|
|
teof = (newsize + (JFS_SBI(ip->i_sb)->bsize - 1)) >>
|
|
JFS_SBI(ip->i_sb)->l2bsize;
|
|
|
|
/* clear stack */
|
|
BT_CLR(&btstack);
|
|
|
|
/*
|
|
* start with root
|
|
*
|
|
* root resides in the inode
|
|
*/
|
|
bn = 0;
|
|
|
|
/*
|
|
* first access of each page:
|
|
*/
|
|
getPage:
|
|
XT_GETPAGE(ip, bn, mp, PSIZE, p, rc);
|
|
if (rc)
|
|
return rc;
|
|
|
|
/* process entries backward from last index */
|
|
index = le16_to_cpu(p->header.nextindex) - 1;
|
|
|
|
|
|
/* Since this is the rightmost page at this level, and we may have
|
|
* already freed a page that was formerly to the right, let's make
|
|
* sure that the next pointer is zero.
|
|
*/
|
|
if (p->header.next) {
|
|
if (log)
|
|
/*
|
|
* Make sure this change to the header is logged.
|
|
* If we really truncate this leaf, the flag
|
|
* will be changed to tlckTRUNCATE
|
|
*/
|
|
tlck = txLock(tid, ip, mp, tlckXTREE|tlckGROW);
|
|
BT_MARK_DIRTY(mp, ip);
|
|
p->header.next = 0;
|
|
}
|
|
|
|
if (p->header.flag & BT_INTERNAL)
|
|
goto getChild;
|
|
|
|
/*
|
|
* leaf page
|
|
*/
|
|
freed = 0;
|
|
|
|
/* does region covered by leaf page precede Teof ? */
|
|
xad = &p->xad[index];
|
|
xoff = offsetXAD(xad);
|
|
xlen = lengthXAD(xad);
|
|
if (teof >= xoff + xlen) {
|
|
XT_PUTPAGE(mp);
|
|
goto getParent;
|
|
}
|
|
|
|
/* (re)acquire tlock of the leaf page */
|
|
if (log) {
|
|
if (++locked_leaves > MAX_TRUNCATE_LEAVES) {
|
|
/*
|
|
* We need to limit the size of the transaction
|
|
* to avoid exhausting pagecache & tlocks
|
|
*/
|
|
XT_PUTPAGE(mp);
|
|
newsize = (xoff + xlen) << JFS_SBI(ip->i_sb)->l2bsize;
|
|
goto getParent;
|
|
}
|
|
tlck = txLock(tid, ip, mp, tlckXTREE);
|
|
tlck->type = tlckXTREE | tlckTRUNCATE;
|
|
xtlck = (struct xtlock *) & tlck->lock;
|
|
xtlck->hwm.offset = le16_to_cpu(p->header.nextindex) - 1;
|
|
}
|
|
BT_MARK_DIRTY(mp, ip);
|
|
|
|
/*
|
|
* scan backward leaf page entries
|
|
*/
|
|
for (; index >= XTENTRYSTART; index--) {
|
|
xad = &p->xad[index];
|
|
xoff = offsetXAD(xad);
|
|
xlen = lengthXAD(xad);
|
|
xaddr = addressXAD(xad);
|
|
|
|
/*
|
|
* The "data" for a directory is indexed by the block
|
|
* device's address space. This metadata must be invalidated
|
|
* here
|
|
*/
|
|
if (S_ISDIR(ip->i_mode) && (teof == 0))
|
|
invalidate_xad_metapages(ip, *xad);
|
|
/*
|
|
* entry beyond eof: continue scan of current page
|
|
* xad
|
|
* ---|---=======------->
|
|
* eof
|
|
*/
|
|
if (teof < xoff) {
|
|
nfreed += xlen;
|
|
continue;
|
|
}
|
|
|
|
/*
|
|
* (xoff <= teof): last entry to be deleted from page;
|
|
* If other entries remain in page: keep and update the page.
|
|
*/
|
|
|
|
/*
|
|
* eof == entry_start: delete the entry
|
|
* xad
|
|
* -------|=======------->
|
|
* eof
|
|
*
|
|
*/
|
|
if (teof == xoff) {
|
|
nfreed += xlen;
|
|
|
|
if (index == XTENTRYSTART)
|
|
break;
|
|
|
|
nextindex = index;
|
|
}
|
|
/*
|
|
* eof within the entry: truncate the entry.
|
|
* xad
|
|
* -------===|===------->
|
|
* eof
|
|
*/
|
|
else if (teof < xoff + xlen) {
|
|
/* update truncated entry */
|
|
len = teof - xoff;
|
|
freexlen = xlen - len;
|
|
XADlength(xad, len);
|
|
|
|
/* save pxd of truncated extent in tlck */
|
|
xaddr += len;
|
|
if (log) { /* COMMIT_PWMAP */
|
|
xtlck->lwm.offset = (xtlck->lwm.offset) ?
|
|
min(index, (int)xtlck->lwm.offset) : index;
|
|
xtlck->lwm.length = index + 1 -
|
|
xtlck->lwm.offset;
|
|
xtlck->twm.offset = index;
|
|
pxdlock = (struct pxd_lock *) & xtlck->pxdlock;
|
|
pxdlock->flag = mlckFREEPXD;
|
|
PXDaddress(&pxdlock->pxd, xaddr);
|
|
PXDlength(&pxdlock->pxd, freexlen);
|
|
}
|
|
/* free truncated extent */
|
|
else { /* COMMIT_WMAP */
|
|
|
|
pxdlock = (struct pxd_lock *) & xadlock;
|
|
pxdlock->flag = mlckFREEPXD;
|
|
PXDaddress(&pxdlock->pxd, xaddr);
|
|
PXDlength(&pxdlock->pxd, freexlen);
|
|
txFreeMap(ip, pxdlock, NULL, COMMIT_WMAP);
|
|
|
|
/* reset map lock */
|
|
xadlock.flag = mlckFREEXADLIST;
|
|
}
|
|
|
|
/* current entry is new last entry; */
|
|
nextindex = index + 1;
|
|
|
|
nfreed += freexlen;
|
|
}
|
|
/*
|
|
* eof beyond the entry:
|
|
* xad
|
|
* -------=======---|--->
|
|
* eof
|
|
*/
|
|
else { /* (xoff + xlen < teof) */
|
|
|
|
nextindex = index + 1;
|
|
}
|
|
|
|
if (nextindex < le16_to_cpu(p->header.nextindex)) {
|
|
if (!log) { /* COMMIT_WAMP */
|
|
xadlock.xdlist = &p->xad[nextindex];
|
|
xadlock.count =
|
|
le16_to_cpu(p->header.nextindex) -
|
|
nextindex;
|
|
txFreeMap(ip, (struct maplock *) & xadlock,
|
|
NULL, COMMIT_WMAP);
|
|
}
|
|
p->header.nextindex = cpu_to_le16(nextindex);
|
|
}
|
|
|
|
XT_PUTPAGE(mp);
|
|
|
|
/* assert(freed == 0); */
|
|
goto getParent;
|
|
} /* end scan of leaf page entries */
|
|
|
|
freed = 1;
|
|
|
|
/*
|
|
* leaf page become empty: free the page if type != PMAP
|
|
*/
|
|
if (log) { /* COMMIT_PWMAP */
|
|
/* txCommit() with tlckFREE:
|
|
* free data extents covered by leaf [XTENTRYSTART:hwm);
|
|
* invalidate leaf if COMMIT_PWMAP;
|
|
* if (TRUNCATE), will write LOG_NOREDOPAGE;
|
|
*/
|
|
tlck->type = tlckXTREE | tlckFREE;
|
|
} else { /* COMMIT_WAMP */
|
|
|
|
/* free data extents covered by leaf */
|
|
xadlock.xdlist = &p->xad[XTENTRYSTART];
|
|
xadlock.count =
|
|
le16_to_cpu(p->header.nextindex) - XTENTRYSTART;
|
|
txFreeMap(ip, (struct maplock *) & xadlock, NULL, COMMIT_WMAP);
|
|
}
|
|
|
|
if (p->header.flag & BT_ROOT) {
|
|
p->header.flag &= ~BT_INTERNAL;
|
|
p->header.flag |= BT_LEAF;
|
|
p->header.nextindex = cpu_to_le16(XTENTRYSTART);
|
|
|
|
XT_PUTPAGE(mp); /* debug */
|
|
goto out;
|
|
} else {
|
|
if (log) { /* COMMIT_PWMAP */
|
|
/* page will be invalidated at tx completion
|
|
*/
|
|
XT_PUTPAGE(mp);
|
|
} else { /* COMMIT_WMAP */
|
|
|
|
if (mp->lid)
|
|
lid_to_tlock(mp->lid)->flag |= tlckFREELOCK;
|
|
|
|
/* invalidate empty leaf page */
|
|
discard_metapage(mp);
|
|
}
|
|
}
|
|
|
|
/*
|
|
* the leaf page become empty: delete the parent entry
|
|
* for the leaf page if the parent page is to be kept
|
|
* in the new sized file.
|
|
*/
|
|
|
|
/*
|
|
* go back up to the parent page
|
|
*/
|
|
getParent:
|
|
/* pop/restore parent entry for the current child page */
|
|
if ((parent = BT_POP(&btstack)) == NULL)
|
|
/* current page must have been root */
|
|
goto out;
|
|
|
|
/* get back the parent page */
|
|
bn = parent->bn;
|
|
XT_GETPAGE(ip, bn, mp, PSIZE, p, rc);
|
|
if (rc)
|
|
return rc;
|
|
|
|
index = parent->index;
|
|
|
|
/*
|
|
* child page was not empty:
|
|
*/
|
|
if (freed == 0) {
|
|
/* has any entry deleted from parent ? */
|
|
if (index < le16_to_cpu(p->header.nextindex) - 1) {
|
|
/* (re)acquire tlock on the parent page */
|
|
if (log) { /* COMMIT_PWMAP */
|
|
/* txCommit() with tlckTRUNCATE:
|
|
* free child extents covered by parent [);
|
|
*/
|
|
tlck = txLock(tid, ip, mp, tlckXTREE);
|
|
xtlck = (struct xtlock *) & tlck->lock;
|
|
if (!(tlck->type & tlckTRUNCATE)) {
|
|
xtlck->hwm.offset =
|
|
le16_to_cpu(p->header.
|
|
nextindex) - 1;
|
|
tlck->type =
|
|
tlckXTREE | tlckTRUNCATE;
|
|
}
|
|
} else { /* COMMIT_WMAP */
|
|
|
|
/* free child extents covered by parent */
|
|
xadlock.xdlist = &p->xad[index + 1];
|
|
xadlock.count =
|
|
le16_to_cpu(p->header.nextindex) -
|
|
index - 1;
|
|
txFreeMap(ip, (struct maplock *) & xadlock,
|
|
NULL, COMMIT_WMAP);
|
|
}
|
|
BT_MARK_DIRTY(mp, ip);
|
|
|
|
p->header.nextindex = cpu_to_le16(index + 1);
|
|
}
|
|
XT_PUTPAGE(mp);
|
|
goto getParent;
|
|
}
|
|
|
|
/*
|
|
* child page was empty:
|
|
*/
|
|
nfreed += lengthXAD(&p->xad[index]);
|
|
|
|
/*
|
|
* During working map update, child page's tlock must be handled
|
|
* before parent's. This is because the parent's tlock will cause
|
|
* the child's disk space to be marked available in the wmap, so
|
|
* it's important that the child page be released by that time.
|
|
*
|
|
* ToDo: tlocks should be on doubly-linked list, so we can
|
|
* quickly remove it and add it to the end.
|
|
*/
|
|
|
|
/*
|
|
* Move parent page's tlock to the end of the tid's tlock list
|
|
*/
|
|
if (log && mp->lid && (tblk->last != mp->lid) &&
|
|
lid_to_tlock(mp->lid)->tid) {
|
|
lid_t lid = mp->lid;
|
|
struct tlock *prev;
|
|
|
|
tlck = lid_to_tlock(lid);
|
|
|
|
if (tblk->next == lid)
|
|
tblk->next = tlck->next;
|
|
else {
|
|
for (prev = lid_to_tlock(tblk->next);
|
|
prev->next != lid;
|
|
prev = lid_to_tlock(prev->next)) {
|
|
assert(prev->next);
|
|
}
|
|
prev->next = tlck->next;
|
|
}
|
|
lid_to_tlock(tblk->last)->next = lid;
|
|
tlck->next = 0;
|
|
tblk->last = lid;
|
|
}
|
|
|
|
/*
|
|
* parent page become empty: free the page
|
|
*/
|
|
if (index == XTENTRYSTART) {
|
|
if (log) { /* COMMIT_PWMAP */
|
|
/* txCommit() with tlckFREE:
|
|
* free child extents covered by parent;
|
|
* invalidate parent if COMMIT_PWMAP;
|
|
*/
|
|
tlck = txLock(tid, ip, mp, tlckXTREE);
|
|
xtlck = (struct xtlock *) & tlck->lock;
|
|
xtlck->hwm.offset =
|
|
le16_to_cpu(p->header.nextindex) - 1;
|
|
tlck->type = tlckXTREE | tlckFREE;
|
|
} else { /* COMMIT_WMAP */
|
|
|
|
/* free child extents covered by parent */
|
|
xadlock.xdlist = &p->xad[XTENTRYSTART];
|
|
xadlock.count =
|
|
le16_to_cpu(p->header.nextindex) -
|
|
XTENTRYSTART;
|
|
txFreeMap(ip, (struct maplock *) & xadlock, NULL,
|
|
COMMIT_WMAP);
|
|
}
|
|
BT_MARK_DIRTY(mp, ip);
|
|
|
|
if (p->header.flag & BT_ROOT) {
|
|
p->header.flag &= ~BT_INTERNAL;
|
|
p->header.flag |= BT_LEAF;
|
|
p->header.nextindex = cpu_to_le16(XTENTRYSTART);
|
|
if (le16_to_cpu(p->header.maxentry) == XTROOTMAXSLOT) {
|
|
/*
|
|
* Shrink root down to allow inline
|
|
* EA (otherwise fsck complains)
|
|
*/
|
|
p->header.maxentry =
|
|
cpu_to_le16(XTROOTINITSLOT);
|
|
JFS_IP(ip)->mode2 |= INLINEEA;
|
|
}
|
|
|
|
XT_PUTPAGE(mp); /* debug */
|
|
goto out;
|
|
} else {
|
|
if (log) { /* COMMIT_PWMAP */
|
|
/* page will be invalidated at tx completion
|
|
*/
|
|
XT_PUTPAGE(mp);
|
|
} else { /* COMMIT_WMAP */
|
|
|
|
if (mp->lid)
|
|
lid_to_tlock(mp->lid)->flag |=
|
|
tlckFREELOCK;
|
|
|
|
/* invalidate parent page */
|
|
discard_metapage(mp);
|
|
}
|
|
|
|
/* parent has become empty and freed:
|
|
* go back up to its parent page
|
|
*/
|
|
/* freed = 1; */
|
|
goto getParent;
|
|
}
|
|
}
|
|
/*
|
|
* parent page still has entries for front region;
|
|
*/
|
|
else {
|
|
/* try truncate region covered by preceding entry
|
|
* (process backward)
|
|
*/
|
|
index--;
|
|
|
|
/* go back down to the child page corresponding
|
|
* to the entry
|
|
*/
|
|
goto getChild;
|
|
}
|
|
|
|
/*
|
|
* internal page: go down to child page of current entry
|
|
*/
|
|
getChild:
|
|
/* save current parent entry for the child page */
|
|
if (BT_STACK_FULL(&btstack)) {
|
|
jfs_error(ip->i_sb, "stack overrun!\n");
|
|
XT_PUTPAGE(mp);
|
|
return -EIO;
|
|
}
|
|
BT_PUSH(&btstack, bn, index);
|
|
|
|
/* get child page */
|
|
xad = &p->xad[index];
|
|
bn = addressXAD(xad);
|
|
|
|
/*
|
|
* first access of each internal entry:
|
|
*/
|
|
/* release parent page */
|
|
XT_PUTPAGE(mp);
|
|
|
|
/* process the child page */
|
|
goto getPage;
|
|
|
|
out:
|
|
/*
|
|
* update file resource stat
|
|
*/
|
|
/* set size
|
|
*/
|
|
if (S_ISDIR(ip->i_mode) && !newsize)
|
|
ip->i_size = 1; /* fsck hates zero-length directories */
|
|
else
|
|
ip->i_size = newsize;
|
|
|
|
/* update quota allocation to reflect freed blocks */
|
|
dquot_free_block(ip, nfreed);
|
|
|
|
/*
|
|
* free tlock of invalidated pages
|
|
*/
|
|
if (flag == COMMIT_WMAP)
|
|
txFreelock(ip);
|
|
|
|
return newsize;
|
|
}
|
|
|
|
|
|
/*
|
|
* xtTruncate_pmap()
|
|
*
|
|
* function:
|
|
* Perform truncate to zero length for deleted file, leaving the
|
|
* the xtree and working map untouched. This allows the file to
|
|
* be accessed via open file handles, while the delete of the file
|
|
* is committed to disk.
|
|
*
|
|
* parameter:
|
|
* tid_t tid,
|
|
* struct inode *ip,
|
|
* s64 committed_size)
|
|
*
|
|
* return: new committed size
|
|
*
|
|
* note:
|
|
*
|
|
* To avoid deadlock by holding too many transaction locks, the
|
|
* truncation may be broken up into multiple transactions.
|
|
* The committed_size keeps track of part of the file has been
|
|
* freed from the pmaps.
|
|
*/
|
|
s64 xtTruncate_pmap(tid_t tid, struct inode *ip, s64 committed_size)
|
|
{
|
|
s64 bn;
|
|
struct btstack btstack;
|
|
int cmp;
|
|
int index;
|
|
int locked_leaves = 0;
|
|
struct metapage *mp;
|
|
xtpage_t *p;
|
|
struct btframe *parent;
|
|
int rc;
|
|
struct tblock *tblk;
|
|
struct tlock *tlck = NULL;
|
|
xad_t *xad;
|
|
int xlen;
|
|
s64 xoff;
|
|
struct xtlock *xtlck = NULL;
|
|
|
|
/* save object truncation type */
|
|
tblk = tid_to_tblock(tid);
|
|
tblk->xflag |= COMMIT_PMAP;
|
|
|
|
/* clear stack */
|
|
BT_CLR(&btstack);
|
|
|
|
if (committed_size) {
|
|
xoff = (committed_size >> JFS_SBI(ip->i_sb)->l2bsize) - 1;
|
|
rc = xtSearch(ip, xoff, NULL, &cmp, &btstack, 0);
|
|
if (rc)
|
|
return rc;
|
|
|
|
XT_GETSEARCH(ip, btstack.top, bn, mp, p, index);
|
|
|
|
if (cmp != 0) {
|
|
XT_PUTPAGE(mp);
|
|
jfs_error(ip->i_sb, "did not find extent\n");
|
|
return -EIO;
|
|
}
|
|
} else {
|
|
/*
|
|
* start with root
|
|
*
|
|
* root resides in the inode
|
|
*/
|
|
bn = 0;
|
|
|
|
/*
|
|
* first access of each page:
|
|
*/
|
|
getPage:
|
|
XT_GETPAGE(ip, bn, mp, PSIZE, p, rc);
|
|
if (rc)
|
|
return rc;
|
|
|
|
/* process entries backward from last index */
|
|
index = le16_to_cpu(p->header.nextindex) - 1;
|
|
|
|
if (p->header.flag & BT_INTERNAL)
|
|
goto getChild;
|
|
}
|
|
|
|
/*
|
|
* leaf page
|
|
*/
|
|
|
|
if (++locked_leaves > MAX_TRUNCATE_LEAVES) {
|
|
/*
|
|
* We need to limit the size of the transaction
|
|
* to avoid exhausting pagecache & tlocks
|
|
*/
|
|
xad = &p->xad[index];
|
|
xoff = offsetXAD(xad);
|
|
xlen = lengthXAD(xad);
|
|
XT_PUTPAGE(mp);
|
|
return (xoff + xlen) << JFS_SBI(ip->i_sb)->l2bsize;
|
|
}
|
|
tlck = txLock(tid, ip, mp, tlckXTREE);
|
|
tlck->type = tlckXTREE | tlckFREE;
|
|
xtlck = (struct xtlock *) & tlck->lock;
|
|
xtlck->hwm.offset = index;
|
|
|
|
|
|
XT_PUTPAGE(mp);
|
|
|
|
/*
|
|
* go back up to the parent page
|
|
*/
|
|
getParent:
|
|
/* pop/restore parent entry for the current child page */
|
|
if ((parent = BT_POP(&btstack)) == NULL)
|
|
/* current page must have been root */
|
|
goto out;
|
|
|
|
/* get back the parent page */
|
|
bn = parent->bn;
|
|
XT_GETPAGE(ip, bn, mp, PSIZE, p, rc);
|
|
if (rc)
|
|
return rc;
|
|
|
|
index = parent->index;
|
|
|
|
/*
|
|
* parent page become empty: free the page
|
|
*/
|
|
if (index == XTENTRYSTART) {
|
|
/* txCommit() with tlckFREE:
|
|
* free child extents covered by parent;
|
|
* invalidate parent if COMMIT_PWMAP;
|
|
*/
|
|
tlck = txLock(tid, ip, mp, tlckXTREE);
|
|
xtlck = (struct xtlock *) & tlck->lock;
|
|
xtlck->hwm.offset = le16_to_cpu(p->header.nextindex) - 1;
|
|
tlck->type = tlckXTREE | tlckFREE;
|
|
|
|
XT_PUTPAGE(mp);
|
|
|
|
if (p->header.flag & BT_ROOT) {
|
|
|
|
goto out;
|
|
} else {
|
|
goto getParent;
|
|
}
|
|
}
|
|
/*
|
|
* parent page still has entries for front region;
|
|
*/
|
|
else
|
|
index--;
|
|
/*
|
|
* internal page: go down to child page of current entry
|
|
*/
|
|
getChild:
|
|
/* save current parent entry for the child page */
|
|
if (BT_STACK_FULL(&btstack)) {
|
|
jfs_error(ip->i_sb, "stack overrun!\n");
|
|
XT_PUTPAGE(mp);
|
|
return -EIO;
|
|
}
|
|
BT_PUSH(&btstack, bn, index);
|
|
|
|
/* get child page */
|
|
xad = &p->xad[index];
|
|
bn = addressXAD(xad);
|
|
|
|
/*
|
|
* first access of each internal entry:
|
|
*/
|
|
/* release parent page */
|
|
XT_PUTPAGE(mp);
|
|
|
|
/* process the child page */
|
|
goto getPage;
|
|
|
|
out:
|
|
|
|
return 0;
|
|
}
|
|
|
|
#ifdef CONFIG_JFS_STATISTICS
|
|
int jfs_xtstat_proc_show(struct seq_file *m, void *v)
|
|
{
|
|
seq_printf(m,
|
|
"JFS Xtree statistics\n"
|
|
"====================\n"
|
|
"searches = %d\n"
|
|
"fast searches = %d\n"
|
|
"splits = %d\n",
|
|
xtStat.search,
|
|
xtStat.fastSearch,
|
|
xtStat.split);
|
|
return 0;
|
|
}
|
|
#endif
|