Files
Greg Kroah-Hartman 8cb2595f93 Merge 6.12.35 into android16-6.12-lts
GKI (arm64) relevant 87 out of 414 changes, affecting 112 files +738/-352
  bdb71ee651 configfs: Do not override creating attribute file failure in populate_attrs() [1 file, +1/-1]
  ba789be63d io_uring: account drain memory to cgroup [1 file, +1/-1]
  c58b577cf7 io_uring/kbuf: account ring io_buffer_list memory [1 file, +1/-1]
  f78b38af35 jbd2: fix data-race and null-ptr-deref in jbd2_journal_dirty_metadata() [1 file, +3/-2]
  2429bb9fad media: v4l2-dev: fix error handling in __video_register_device() [1 file, +7/-7]
  5d8b057ed7 media: videobuf2: use sgtable-based scatterlist wrappers [1 file, +2/-2]
  b52dc88361 media: uvcvideo: Return the number of processed controls [1 file, +10/-1]
  6d2b12e7c5 media: uvcvideo: Send control events for partial succeeds [1 file, +9/-3]
  aac91ae06c media: uvcvideo: Fix deferred probing error [1 file, +19/-8]
  86d9837e46 arm64/mm: Close theoretical race where stale TLB entry remains valid [1 file, +5/-4]
  5538af3843 block: use plug request list tail for one-shot backmerge attempt [1 file, +13/-13]
  943801c380 block: Clear BIO_EMULATES_ZONE_APPEND flag on BIO completion [1 file, +1/-0]
  1c71f3cf5f cgroup,freezer: fix incomplete freezing when attaching tasks [1 file, +1/-2]
  a0890b7805 bus: firewall: Fix missing static inline annotations for stubs [1 file, +9/-6]
  5766da2237 ext4: inline: fix len overflow in ext4_prepare_inline_data [1 file, +1/-1]
  796632e6f8 ext4: fix calculation of credits for extent tree modification [1 file, +6/-5]
  4b36399711 ext4: ensure i_size is smaller than maxbytes [1 file, +2/-1]
  be5f3061a6 ext4: only dirty folios when data journaling regular files [1 file, +6/-1]
  a0b1c91ada Input: gpio-keys - fix possible concurrent access in gpio_keys_irq_timer() [1 file, +2/-0]
  fed611bd8c f2fs: fix to do sanity check on ino and xnid [1 file, +6/-0]
  aaa644e7ff f2fs: prevent kernel warning due to negative i_nlink from corrupted image [1 file, +9/-0]
  ee1b421c46 f2fs: fix to do sanity check on sit_bitmap_size [1 file, +8/-0]
  f16a797dce watchdog: fix watchdog may detect false positive of softlockup [1 file, +27/-14]
  02137179ff mm: fix ratelimit_pages update error in dirty_ratio_handler() [1 file, +1/-1]
  462eee6d42 firmware: arm_scmi: Ensure that the message-id supports fastchannel [2 files, +45/-33]
  e3cf1ef571 dm-verity: fix a memory leak if some arguments are specified multiple times [3 files, +24/-5]
  f2986bccf2 dm: lock limits when reading them [1 file, +7/-1]
  ec5f0b4412 ovl: Fix nested backing file paths [1 file, +2/-2]
  92776ca0cc remoteproc: core: Cleanup acquired resources when rproc_handle_resources() fails in rproc_attach() [1 file, +2/-3]
  f4ef928ca5 remoteproc: core: Release rproc->clean_table after rproc_attach() fails [1 file, +1/-0]
  68e58f5791 PCI: dwc: ep: Correct PBA offset in .set_msix() callback [1 file, +3/-2]
  b20701d594 PCI: Add ACS quirk for Loongson PCIe [1 file, +23/-0]
  be0cf75cbd PCI: Fix lock symmetry in pci_slot_unlock() [1 file, +2/-1]
  7b45d2401d clocksource: Fix the CPUs' choice in the watchdog per CPU verification [1 file, +1/-1]
  c05aba32a9 ACPICA: Avoid sequence overread in call to strncmp() [1 file, +1/-1]
  66613b13cd ACPI: Add missing prototype for non CONFIG_SUSPEND/CONFIG_X86 case [1 file, +8/-1]
  33cd650d38 pmdomain: core: Reset genpd->states to avoid freeing invalid data [1 file, +3/-1]
  f34e0c1556 platform-msi: Add msi_remove_device_irq_domain() in platform_device_msi_free_irqs_all() [1 file, +1/-0]
  c519f81e9c gpiolib: of: Add polarity quirk for s5m8767 [1 file, +9/-0]
  1f152ae557 PM: runtime: fix denying of auto suspend in pm_suspend_timer_fn() [1 file, +1/-1]
  6c1151d53c tipc: use kfree_sensitive() for aead cleanup [1 file, +1/-1]
  b0e647442c f2fs: use vmalloc instead of kvmalloc in .init_{,de}compress_ctx [2 files, +15/-13]
  2d834477bb bpf: Check rcu_read_lock_trace_held() in bpf_map_lookup_percpu_elem() [1 file, +2/-1]
  77ff6aec7c cpufreq: scmi: Skip SCMI devices that aren't used by the CPUs [1 file, +35/-1]
  0a8446058c tcp: always seek for minimal rtt in tcp_rcv_rtt_update() [1 file, +8/-14]
  f97085d365 tcp: remove zero TCP TS samples for autotuning [1 file, +5/-5]
  89b20c406e tcp: fix initial tp->rcvq_space.space value for passive TS enabled flows [1 file, +3/-3]
  84c156a351 tcp: add receive queue awareness in tcp_rcv_space_adjust() [2 files, +5/-3]
  3a9e74d158 ipv4/route: Use this_cpu_inc() for stats on PREEMPT_RT [1 file, +4/-0]
  5eb9c50e0c net: page_pool: Don't recycle into cache on PREEMPT_RT [1 file, +4/-0]
  8b0741b167 xfrm: validate assignment of maximal possible SEQ number [1 file, +42/-10]
  8fdf2f79eb bpf: Pass the same orig_call value to trampoline functions [1 file, +1/-1]
  f0023d7a2a f2fs: fix to bail out in get_new_segment() [2 files, +6/-1]
  448dc45eea bpf: Use proper type to calculate bpf_raw_tp_null_args.mask index [1 file, +2/-2]
  78f768e36c net: bridge: mcast: re-implement br_multicast_{enable, disable}_port functions [1 file, +69/-8]
  4b3383110b software node: Correct a OOB check in software_node_get_reference_args() [1 file, +1/-1]
  b7129ef57d sock: Correct error checking condition for (assign|release)_proto_idx() [1 file, +2/-2]
  a58f0a0e99 f2fs: fix to set atomic write status more clear [3 files, +12/-2]
  b8b4b8bb34 bpf, sockmap: Fix data lost during EAGAIN retries [1 file, +2/-1]
  7c41f73b64 fs/xattr.c: fix simple_xattr_list() [1 file, +1/-0]
  2e10dc9c2a io_uring/kbuf: don't truncate end buffer for multiple buffer peeks [1 file, +4/-1]
  1a4254ab06 io_uring: fix task leak issue in io_wq_create() [1 file, +3/-1]
  4220cc0b98 nvme: always punt polled uring_cmd end_io work to task_work [1 file, +7/-14]
  f9b97d466e net_sched: sch_sfq: reject invalid perturb period [1 file, +8/-2]
  2a3ad42a57 net: clear the dst when changing skb protocol [1 file, +13/-6]
  510a29d776 mm: close theoretical race where stale TLB entries could linger [1 file, +2/-0]
  57ec081869 sched_ext, sched/core: Don't call scx_group_set_weight() prematurely from sched_create_group() [3 files, +9/-2]
  3d828519bd atm: Revert atm_account_tx() if copy_from_iter_full() fails. [3 files, +8/-1]
  47f34289d1 arm64: Restrict pagetable teardown to avoid false warning [1 file, +2/-1]
  9cf5b2a3b7 mm/hugetlb: unshare page tables during VMA split, not before [5 files, +57/-16]
  dc5f0aef9e net: Fix checksum update for ILA adj-transport [4 files, +7/-7]
  2516299184 bpf: Fix L4 csum update on IPv6 in CHECKSUM_COMPLETE [3 files, +7/-2]
  50189d9c5e erofs: remove unused trace event erofs_destroy_inode [1 file, +0/-18]
  348e541fef ipv6: remove leftover ip6 cookie initializer [1 file, +0/-2]
  3c44ebad5a ipv6: replace ipcm6_init calls with ipcm6_init_sk [4 files, +3/-29]
  6b358b3adf io_uring/sqpoll: don't put task_struct on tctx setup failure [1 file, +1/-4]
  8873080b88 workqueue: Initialize wq_isolated_cpumask in workqueue_init_early() [1 file, +2/-1]
  ac462a75fd net: netmem: fix skb_ensure_writable with unreadable skbs [1 file, +0/-3]
  61b39e189d ptp: allow reading of currently dialed frequency to succeed on free-running clocks [1 file, +2/-1]
  397c1faf8f tcp: fix tcp_packet_delayed() for tcp_is_non_sack_preventing_reopen() behavior [1 file, +25/-12]
  0d3d91c350 tipc: fix null-ptr-deref when acquiring remote ip of ethernet bearer [1 file, +2/-2]
  31d50dfe9c tcp: fix passive TFO socket having invalid NAPI ID [1 file, +3/-0]
  0f8df5d6f2 ublk: santizize the arguments from userspace when adding a device [1 file, +3/-0]
  456019adaa perf: Fix sample vs do_exit() [2 files, +16/-8]
  7335c33d62 perf: Fix cgroup state vs ERROR [1 file, +30/-21]
  fd199366bf perf/core: Fix WARN in perf_cgroup_switch() [1 file, +20/-2]
  22f935bc86 arm64/ptrace: Fix stack-out-of-bounds read in regs_get_kernel_stack_nth() [1 file, +1/-1]

Changes in 6.12.35
	configfs: Do not override creating attribute file failure in populate_attrs()
	crypto: marvell/cesa - Do not chain submitted requests
	gfs2: move msleep to sleepable context
	crypto: qat - add shutdown handler to qat_c3xxx
	crypto: qat - add shutdown handler to qat_420xx
	crypto: qat - add shutdown handler to qat_4xxx
	crypto: qat - add shutdown handler to qat_c62x
	crypto: qat - add shutdown handler to qat_dh895xcc
	ASoC: qcom: sdm845: Add error handling in sdm845_slim_snd_hw_params()
	ASoC: meson: meson-card-utils: use of_property_present() for DT parsing
	ASoC: amd: sof_amd_sdw: Fix unlikely uninitialized variable use in create_sdw_dailinks()
	io_uring: account drain memory to cgroup
	io_uring/kbuf: account ring io_buffer_list memory
	powerpc/pseries/msi: Avoid reading PCI device registers in reduced power states
	s390/pci: Remove redundant bus removal and disable from zpci_release_device()
	s390/pci: Prevent self deletion in disable_slot()
	s390/pci: Allow re-add of a reserved but not yet removed device
	s390/pci: Serialize device addition and removal
	regulator: max20086: Fix MAX200086 chip id
	regulator: max20086: Change enable gpio to optional
	net/mlx5_core: Add error handling inmlx5_query_nic_vport_qkey_viol_cntr()
	net/mlx5: Add error handling in mlx5_query_nic_vport_node_guid()
	wifi: p54: prevent buffer-overflow in p54_rx_eeprom_readback()
	wifi: mt76: mt7925: fix host interrupt register initialization
	wifi: ath11k: fix rx completion meta data corruption
	wifi: rtw88: usb: Upload the firmware in bigger chunks
	wifi: ath11k: fix ring-buffer corruption
	NFSD: unregister filesystem in case genl_register_family() fails
	NFSD: fix race between nfsd registration and exports_proc
	NFSD: Implement FATTR4_CLONE_BLKSIZE attribute
	nfsd: nfsd4_spo_must_allow() must check this is a v4 compound request
	nfsd: Initialize ssc before laundromat_work to prevent NULL dereference
	SUNRPC: Prevent hang on NFS mount with xprtsec=[m]tls
	NFSv4: Don't check for OPEN feature support in v4.1
	fs/nfs/read: fix double-unlock bug in nfs_return_empty_folio()
	wifi: ath12k: fix ring-buffer corruption
	jbd2: fix data-race and null-ptr-deref in jbd2_journal_dirty_metadata()
	svcrdma: Unregister the device if svc_rdma_accept() fails
	wifi: rtw88: usb: Reduce control message timeout to 500 ms
	wifi: rtlwifi: disable ASPM for RTL8723BE with subsystem ID 11ad:1723
	media: ov8856: suppress probe deferral errors
	media: ov5675: suppress probe deferral errors
	media: imx335: Use correct register width for HNUM
	media: nxp: imx8-isi: better handle the m2m usage_count
	media: i2c: ds90ub913: Fix returned fmt from .set_fmt()
	media: ccs-pll: Start VT pre-PLL multiplier search from correct value
	media: ov2740: Move pm-runtime cleanup on probe-errors to proper place
	media: ccs-pll: Start OP pre-PLL multiplier search from correct value
	media: ccs-pll: Correct the upper limit of maximum op_pre_pll_clk_div
	media: ccs-pll: Check for too high VT PLL multiplier in dual PLL case
	media: cxusb: no longer judge rbuf when the write fails
	media: davinci: vpif: Fix memory leak in probe error path
	media: gspca: Add error handling for stv06xx_read_sensor()
	media: i2c: imx335: Fix frame size enumeration
	media: imagination: fix a potential memory leak in e5010_probe()
	media: intel/ipu6: Fix dma mask for non-secure mode
	media: ipu6: Remove workaround for Meteor Lake ES2
	media: mediatek: vcodec: Correct vsi_core framebuffer size
	media: omap3isp: use sgtable-based scatterlist wrappers
	media: v4l2-dev: fix error handling in __video_register_device()
	media: venus: Fix probe error handling
	media: videobuf2: use sgtable-based scatterlist wrappers
	media: vidtv: Terminating the subsequent process of initialization failure
	media: vivid: Change the siize of the composing
	media: imx-jpeg: Drop the first error frames
	media: imx-jpeg: Move mxc_jpeg_free_slot_data() ahead
	media: imx-jpeg: Reset slot data pointers when freed
	media: imx-jpeg: Cleanup after an allocation error
	media: uvcvideo: Return the number of processed controls
	media: uvcvideo: Send control events for partial succeeds
	media: uvcvideo: Fix deferred probing error
	arm64/mm: Close theoretical race where stale TLB entry remains valid
	ARM: 9447/1: arm/memremap: fix arch_memremap_can_ram_remap()
	ARM: omap: pmic-cpcap: do not mess around without CPCAP or OMAP4
	ASoC: codecs: wcd9375: Fix double free of regulator supplies
	ASoC: codecs: wcd937x: Drop unused buck_supply
	block: use plug request list tail for one-shot backmerge attempt
	block: Clear BIO_EMULATES_ZONE_APPEND flag on BIO completion
	bus: mhi: ep: Update read pointer only after buffer is written
	bus: mhi: host: Fix conflict between power_up and SYSERR
	can: kvaser_pciefd: refine error prone echo_skb_max handling logic
	can: tcan4x5x: fix power regulator retrieval during probe
	ceph: avoid kernel BUG for encrypted inode with unaligned file size
	ceph: set superblock s_magic for IMA fsmagic matching
	cgroup,freezer: fix incomplete freezing when attaching tasks
	bus: firewall: Fix missing static inline annotations for stubs
	ata: pata_via: Force PIO for ATAPI devices on VT6415/VT6330
	ata: ahci: Disallow LPM for ASUSPRO-D840SA motherboard
	ata: ahci: Disallow LPM for Asus B550-F motherboard
	bus: fsl-mc: do not add a device-link for the UAPI used DPMCP device
	bus: fsl-mc: fix GET/SET_TAILDROP command ids
	ext4: inline: fix len overflow in ext4_prepare_inline_data
	ext4: fix calculation of credits for extent tree modification
	ext4: factor out ext4_get_maxbytes()
	ext4: ensure i_size is smaller than maxbytes
	ext4: only dirty folios when data journaling regular files
	Input: ims-pcu - check record size in ims_pcu_flash_firmware()
	Input: gpio-keys - fix possible concurrent access in gpio_keys_irq_timer()
	f2fs: fix to do sanity check on ino and xnid
	f2fs: prevent kernel warning due to negative i_nlink from corrupted image
	f2fs: fix to do sanity check on sit_bitmap_size
	hwmon: (ftsteutates) Fix TOCTOU race in fts_read()
	NFC: nci: uart: Set tty->disc_data only in success path
	net/sched: fix use-after-free in taprio_dev_notifier
	net: ftgmac100: select FIXED_PHY
	iommu/vt-d: Restore context entry setup order for aliased devices
	fbdev: Fix do_register_framebuffer to prevent null-ptr-deref in fb_videomode_to_var
	EDAC/altera: Use correct write width with the INTTEST register
	fbdev: Fix fb_set_var to prevent null-ptr-deref in fb_videomode_to_var
	parisc/unaligned: Fix hex output to show 8 hex chars
	vgacon: Add check for vc_origin address range in vgacon_scroll()
	parisc: fix building with gcc-15
	clk: meson-g12a: add missing fclk_div2 to spicc
	ipc: fix to protect IPCS lookups using RCU
	watchdog: fix watchdog may detect false positive of softlockup
	RDMA/iwcm: Fix use-after-free of work objects after cm_id destruction
	mm: fix ratelimit_pages update error in dirty_ratio_handler()
	soc: qcom: pmic_glink_altmode: fix spurious DP hotplug events
	configfs-tsm-report: Fix NULL dereference of tsm_ops
	firmware: arm_scmi: Ensure that the message-id supports fastchannel
	mtd: rawnand: sunxi: Add randomizer configuration in sunxi_nfc_hw_ecc_write_chunk
	mtd: nand: sunxi: Add randomizer configuration before randomizer enable
	KVM: SVM: Clear current_vmcb during vCPU free for all *possible* CPUs
	KVM: VMX: Flush shadow VMCS on emergency reboot
	dm-mirror: fix a tiny race condition
	dm-verity: fix a memory leak if some arguments are specified multiple times
	mtd: rawnand: qcom: Fix read len for onfi param page
	ftrace: Fix UAF when lookup kallsym after ftrace disabled
	dm: lock limits when reading them
	phy: fsl-imx8mq-usb: fix phy_tx_vboost_level_from_property()
	net: ch9200: fix uninitialised access during mii_nway_restart
	KVM: s390: rename PROT_NONE to PROT_TYPE_DUMMY
	sysfb: Fix screen_info type check for VGA
	video: screen_info: Relocate framebuffers behind PCI bridges
	pwm: axi-pwmgen: fix missing separate external clock
	staging: iio: ad5933: Correct settling cycles encoding per datasheet
	mips: Add -std= flag specified in KBUILD_CFLAGS to vdso CFLAGS
	ovl: Fix nested backing file paths
	regulator: max14577: Add error check for max14577_read_reg()
	remoteproc: core: Cleanup acquired resources when rproc_handle_resources() fails in rproc_attach()
	remoteproc: core: Release rproc->clean_table after rproc_attach() fails
	remoteproc: k3-m4: Don't assert reset in detach routine
	cifs: reset connections for all channels when reconnect requested
	cifs: update dstaddr whenever channel iface is updated
	cifs: dns resolution is needed only for primary channel
	smb: client: add NULL check in automount_fullpath
	Drivers: hv: Allocate interrupt and monitor pages aligned to system page boundary
	uio_hv_generic: Use correct size for interrupt and monitor pages
	uio_hv_generic: Align ring size to system page
	PCI: cadence-ep: Correct PBA offset in .set_msix() callback
	PCI: dwc: ep: Correct PBA offset in .set_msix() callback
	PCI: Add ACS quirk for Loongson PCIe
	PCI: Fix lock symmetry in pci_slot_unlock()
	PCI: dw-rockchip: Remove PCIE_L0S_ENTRY check from rockchip_pcie_link_up()
	PCI: dw-rockchip: Fix PHY function call sequence in rockchip_pcie_phy_deinit()
	iio: accel: fxls8962af: Fix temperature scan element sign
	accel/ivpu: Improve buffer object logging
	accel/ivpu: Use firmware names from upstream repo
	accel/ivpu: Use dma_resv_lock() instead of a custom mutex
	accel/ivpu: Fix warning in ivpu_gem_bo_free()
	dummycon: Trigger redraw when switching consoles with deferred takeover
	mm/hugetlb: fix huge_pmd_unshare() vs GUP-fast race
	iio: imu: inv_icm42600: Fix temperature calculation
	iio: adc: ad7944: mask high bits on direct read
	iio: adc: ti-ads1298: Kconfig: add kfifo dependency to fix module build
	iio: adc: ad7606_spi: fix reg write value mask
	ACPICA: fix acpi operand cache leak in dswstate.c
	ASoC: amd: yc: Add quirk for Lenovo Yoga Pro 7 14ASP9
	clocksource: Fix the CPUs' choice in the watchdog per CPU verification
	power: supply: collie: Fix wakeup source leaks on device unbind
	mmc: Add quirk to disable DDR50 tuning
	ACPICA: Avoid sequence overread in call to strncmp()
	ASoC: tas2770: Power cycle amp on ISENSE/VSENSE change
	ASoC: intel/sdw_utils: Assign initial value in asoc_sdw_rt_amp_spk_rtd_init()
	ACPI: bus: Bail out if acpi_kobj registration fails
	ACPI: Add missing prototype for non CONFIG_SUSPEND/CONFIG_X86 case
	ACPICA: fix acpi parse and parseext cache leaks
	ACPICA: Apply pack(1) to union aml_resource
	ALSA: hda: cs35l41: Fix swapped l/r audio channels for Acer Helios laptops
	power: supply: bq27xxx: Retrieve again when busy
	pmdomain: core: Reset genpd->states to avoid freeing invalid data
	ACPICA: utilities: Fix overflow check in vsnprintf()
	platform-msi: Add msi_remove_device_irq_domain() in platform_device_msi_free_irqs_all()
	ASoC: tegra210_ahub: Add check to of_device_get_match_data()
	Make 'cc-option' work correctly for the -Wno-xyzzy pattern
	gpiolib: of: Add polarity quirk for s5m8767
	PM: runtime: fix denying of auto suspend in pm_suspend_timer_fn()
	power: supply: max17040: adjust thermal channel scaling
	ACPI: battery: negate current when discharging
	net: macb: Check return value of dma_set_mask_and_coherent()
	net: lan743x: Modify the EEPROM and OTP size for PCI1xxxx devices
	tipc: use kfree_sensitive() for aead cleanup
	f2fs: use vmalloc instead of kvmalloc in .init_{,de}compress_ctx
	bpf: Check rcu_read_lock_trace_held() in bpf_map_lookup_percpu_elem()
	Bluetooth: btusb: Add new VID/PID 13d3/3584 for MT7922
	i2c: designware: Invoke runtime suspend on quick slave re-registration
	wifi: mt76: mt7996: drop fragments with multicast or broadcast RA
	emulex/benet: correct command version selection in be_cmd_get_stats()
	Bluetooth: btusb: Add new VID/PID 13d3/3630 for MT7925
	wifi: mt76: mt76x2: Add support for LiteOn WN4516R,WN4519R
	wifi: mt76: mt7921: add 160 MHz AP for mt7922 device
	wifi: mt76: mt7925: introduce thermal protection
	wifi: mac80211: validate SCAN_FLAG_AP in scan request during MLO
	sctp: Do not wake readers in __sctp_write_space()
	libbpf/btf: Fix string handling to support multi-split BTF
	cpufreq: scmi: Skip SCMI devices that aren't used by the CPUs
	i2c: tegra: check msg length in SMBUS block read
	i2c: npcm: Add clock toggle recovery
	clk: qcom: gcc-x1e80100: Set FORCE MEM CORE for UFS clocks
	net: dlink: add synchronization for stats update
	wifi: ath12k: fix macro definition HAL_RX_MSDU_PKT_LENGTH_GET
	wifi: ath12k: fix a possible dead lock caused by ab->base_lock
	wifi: ath11k: Fix QMI memory reuse logic
	iommu/amd: Allow matching ACPI HID devices without matching UIDs
	wifi: rtw89: leave idle mode when setting WEP encryption for AP mode
	tcp: always seek for minimal rtt in tcp_rcv_rtt_update()
	tcp: remove zero TCP TS samples for autotuning
	tcp: fix initial tp->rcvq_space.space value for passive TS enabled flows
	tcp: add receive queue awareness in tcp_rcv_space_adjust()
	x86/sgx: Prevent attempts to reclaim poisoned pages
	ipv4/route: Use this_cpu_inc() for stats on PREEMPT_RT
	net: page_pool: Don't recycle into cache on PREEMPT_RT
	xfrm: validate assignment of maximal possible SEQ number
	net: atlantic: generate software timestamp just before the doorbell
	pinctrl: armada-37xx: propagate error from armada_37xx_pmx_set_by_name()
	pinctrl: armada-37xx: propagate error from armada_37xx_gpio_get_direction()
	bpf: Pass the same orig_call value to trampoline functions
	net: stmmac: generate software timestamp just before the doorbell
	pinctrl: armada-37xx: propagate error from armada_37xx_pmx_gpio_set_direction()
	libbpf: Check bpf_map_skeleton link for NULL
	pinctrl: armada-37xx: propagate error from armada_37xx_gpio_get()
	net: mlx4: add SOF_TIMESTAMPING_TX_SOFTWARE flag when getting ts info
	net: vertexcom: mse102x: Return code for mse102x_rx_pkt_spi
	wireless: purelifi: plfxlc: fix memory leak in plfxlc_usb_wreq_asyn()
	wifi: mac80211: do not offer a mesh path if forwarding is disabled
	clk: rockchip: rk3036: mark ddrphy as critical
	hid-asus: check ROG Ally MCU version and warn
	wifi: iwlwifi: mvm: fix beacon CCK flag
	f2fs: fix to bail out in get_new_segment()
	netfilter: nft_set_pipapo: clamp maximum map bucket size to INT_MAX
	libbpf: Add identical pointer detection to btf_dedup_is_equiv()
	scsi: lpfc: Fix lpfc_check_sli_ndlp() handling for GEN_REQUEST64 commands
	scsi: smartpqi: Add new PCI IDs
	iommu/amd: Ensure GA log notifier callbacks finish running before module unload
	wifi: iwlwifi: pcie: make sure to lock rxq->read
	wifi: rtw89: 8922a: fix TX fail with wrong VCO setting
	wifi: mac80211_hwsim: Prevent tsf from setting if beacon is disabled
	netdevsim: Mark NAPI ID on skb in nsim_rcv
	net/mlx5: HWS, Fix IP version decision
	bpf: Use proper type to calculate bpf_raw_tp_null_args.mask index
	wifi: mac80211: VLAN traffic in multicast path
	Revert "mac80211: Dynamically set CoDel parameters per station"
	wifi: iwlwifi: Add missing MODULE_FIRMWARE for Qu-c0-jf-b0
	net: bridge: mcast: update multicast contex when vlan state is changed
	net: bridge: mcast: re-implement br_multicast_{enable, disable}_port functions
	vxlan: Do not treat dst cache initialization errors as fatal
	bnxt_en: Remove unused field "ref_count" in struct bnxt_ulp
	wifi: ath12k: using msdu end descriptor to check for rx multicast packets
	net: ethernet: ti: am65-cpsw: handle -EPROBE_DEFER
	software node: Correct a OOB check in software_node_get_reference_args()
	isofs: fix Y2038 and Y2156 issues in Rock Ridge TF entry
	pinctrl: mcp23s08: Reset all pins to input at probe
	wifi: ath12k: fix failed to set mhi state error during reboot with hardware grouping
	scsi: lpfc: Use memcpy() for BIOS version
	sock: Correct error checking condition for (assign|release)_proto_idx()
	i40e: fix MMIO write access to an invalid page in i40e_clear_hw
	ixgbe: Fix unreachable retry logic in combined and byte I2C write functions
	RDMA/hns: initialize db in update_srq_db()
	ice: fix check for existing switch rule
	usbnet: asix AX88772: leave the carrier control to phylink
	f2fs: fix to set atomic write status more clear
	bpf, sockmap: Fix data lost during EAGAIN retries
	net: ethernet: cortina: Use TOE/TSO on all TCP
	octeontx2-pf: Add error log forcn10k_map_unmap_rq_policer()
	wifi: ath11k: determine PM policy based on machine model
	wifi: ath12k: fix link valid field initialization in the monitor Rx
	wifi: ath12k: fix incorrect CE addresses
	wifi: ath12k: Pass correct values of center freq1 and center freq2 for 160 MHz
	net/mlx5: HWS, Harden IP version definer checks
	fbcon: Make sure modelist not set on unregistered console
	watchdog: da9052_wdt: respect TWDMIN
	bus: fsl-mc: increase MC_CMD_COMPLETION_TIMEOUT_MS value
	ARM: OMAP2+: Fix l4ls clk domain handling in STANDBY
	tee: Prevent size calculation wraparound on 32-bit kernels
	Revert "bus: ti-sysc: Probe for l4_wkup and l4_cfg interconnect devices first"
	fs/xattr.c: fix simple_xattr_list()
	platform/x86/amd: pmc: Clear metrics table at start of cycle
	platform/x86/amd: pmf: Prevent amd_pmf_tee_deinit() from running twice
	platform/x86: dell_rbu: Fix list usage
	platform/x86: dell_rbu: Stop overwriting data buffer
	powerpc/vdso: Fix build of VDSO32 with pcrel
	powerpc/eeh: Fix missing PE bridge reconfiguration during VFIO EEH recovery
	io_uring/kbuf: don't truncate end buffer for multiple buffer peeks
	io_uring: fix task leak issue in io_wq_create()
	drivers/rapidio/rio_cm.c: prevent possible heap overwrite
	platform/loongarch: laptop: Get brightness setting from EC on probe
	platform/loongarch: laptop: Unregister generic_sub_drivers on exit
	platform/loongarch: laptop: Add backlight power control support
	LoongArch: vDSO: Correctly use asm parameters in syscall wrappers
	LoongArch: Avoid using $r0/$r1 as "mask" for csrxchg
	LoongArch: Fix panic caused by NULL-PMD in huge_pte_offset()
	jffs2: check that raw node were preallocated before writing summary
	jffs2: check jffs2_prealloc_raw_node_refs() result in few other places
	cifs: deal with the channel loading lag while picking channels
	cifs: serialize other channels when query server interfaces is pending
	cifs: do not disable interface polling on failure
	smb: improve directory cache reuse for readdir operations
	scsi: storvsc: Increase the timeouts to storvsc_timeout
	scsi: s390: zfcp: Ensure synchronous unit_add
	nvme: always punt polled uring_cmd end_io work to task_work
	net_sched: sch_sfq: reject invalid perturb period
	net: clear the dst when changing skb protocol
	mm: close theoretical race where stale TLB entries could linger
	udmabuf: use sgtable-based scatterlist wrappers
	x86/virt/tdx: Avoid indirect calls to TDX assembly functions
	selftests/x86: Add a test to detect infinite SIGTRAP handler loop
	ksmbd: fix null pointer dereference in destroy_previous_session
	platform/x86: ideapad-laptop: use usleep_range() for EC polling
	selinux: fix selinux_xfrm_alloc_user() to set correct ctx_len
	platform/x86/intel-uncore-freq: Fail module load when plat_info is NULL
	sched_ext, sched/core: Don't call scx_group_set_weight() prematurely from sched_create_group()
	atm: Revert atm_account_tx() if copy_from_iter_full() fails.
	wifi: rtw89: phy: add dummy C2H event handler for report of TAS power
	cpufreq/amd-pstate: Add missing NULL ptr check in amd_pstate_update
	Input: sparcspkr - avoid unannotated fall-through
	wifi: ath12k: Clear affinity hint before calling ath12k_pci_free_irq() in error path
	wifi: cfg80211: init wiphy_work before allocating rfkill fails
	arm64: Restrict pagetable teardown to avoid false warning
	ALSA: usb-audio: Rename ALSA kcontrol PCM and PCM1 for the KTMicro sound card
	ALSA: hda/intel: Add Thinkpad E15 to PM deny list
	ALSA: hda/realtek - Add mute LED support for HP Victus 16-s1xxx and HP Victus 15-fa1xxx
	ALSA: hda/realtek: enable headset mic on Latitude 5420 Rugged
	ALSA: hda/realtek: Fix built-in mic on ASUS VivoBook X513EA
	ALSA: hda/realtek: Add quirk for Asus GU605C
	iio: accel: fxls8962af: Fix temperature calculation
	mm/hugetlb: unshare page tables during VMA split, not before
	drm/amdgpu: read back register after written for VCN v4.0.5
	kbuild: rust: add rustc-min-version support function
	rust: compile libcore with edition 2024 for 1.87+
	net: Fix checksum update for ILA adj-transport
	bpf: Fix L4 csum update on IPv6 in CHECKSUM_COMPLETE
	erofs: remove unused trace event erofs_destroy_inode
	nfsd: use threads array as-is in netlink interface
	sunrpc: handle SVC_GARBAGE during svc auth processing as auth error
	drm/v3d: Avoid NULL pointer dereference in `v3d_job_update_stats()`
	Kunit to check the longest symbol length
	x86/tools: Drop duplicate unlikely() definition in insn_decoder_test.c
	ipv6: remove leftover ip6 cookie initializer
	ipv6: replace ipcm6_init calls with ipcm6_init_sk
	smb: fix secondary channel creation issue with kerberos by populating hostname when adding channels
	drm/msm/disp: Correct porch timing for SDM845
	drm/msm/dsi/dsi_phy_10nm: Fix missing initial VCO rate
	drm/msm: Fix CP_RESET_CONTEXT_STATE bitfield names
	drm/msm/a7xx: Call CP_RESET_CONTEXT_STATE
	drm/ssd130x: fix ssd132x_clear_screen() columns
	ionic: Prevent driver/fw getting out of sync on devcmd(s)
	drm/nouveau/bl: increase buffer size to avoid truncate warning
	drm/i915/pmu: Fix build error with GCOV and AutoFDO enabled
	hwmon: (occ) Rework attribute registration for stack usage
	hwmon: (occ) fix unaligned accesses
	hwmon: (ltc4282) avoid repeated register write
	pldmfw: Select CRC32 when PLDMFW is selected
	aoe: clean device rq_list in aoedev_downdev()
	io_uring/sqpoll: don't put task_struct on tctx setup failure
	net: ice: Perform accurate aRFS flow match
	ice: fix eswitch code memory leak in reset scenario
	e1000e: set fixed clock frequency indication for Nahum 11 and Nahum 13
	workqueue: Initialize wq_isolated_cpumask in workqueue_init_early()
	ksmbd: add free_transport ops in ksmbd connection
	net: netmem: fix skb_ensure_writable with unreadable skbs
	bnxt_en: Fix double invocation of bnxt_ulp_stop()/bnxt_ulp_start()
	eth: bnxt: fix out-of-range access of vnic_info array
	bnxt_en: Add a helper function to configure MRU and RSS
	bnxt_en: Update MRU and RSS table of RSS contexts on queue reset
	ptp: fix breakage after ptp_vclock_in_use() rework
	ptp: allow reading of currently dialed frequency to succeed on free-running clocks
	wifi: carl9170: do not ping device which has failed to load firmware
	mpls: Use rcu_dereference_rtnl() in mpls_route_input_rcu().
	atm: atmtcp: Free invalid length skb in atmtcp_c_send().
	tcp: fix tcp_packet_delayed() for tcp_is_non_sack_preventing_reopen() behavior
	tipc: fix null-ptr-deref when acquiring remote ip of ethernet bearer
	tcp: fix passive TFO socket having invalid NAPI ID
	eth: fbnic: avoid double free when failing to DMA-map FW msg
	net: lan743x: fix potential out-of-bounds write in lan743x_ptp_io_event_clock_get()
	ublk: santizize the arguments from userspace when adding a device
	drm/xe: Wire up device shutdown handler
	drm/xe/gt: Update handling of xe_force_wake_get return
	drm/xe/bmg: Update Wa_16023588340
	calipso: Fix null-ptr-deref in calipso_req_{set,del}attr().
	mlxbf_gige: return EPROBE_DEFER if PHY IRQ is not available
	net: atm: add lec_mutex
	net: atm: fix /proc/net/atm/lec handling
	EDAC/amd64: Correct number of UMCs for family 19h models 70h-7fh
	dt-bindings: i2c: nvidia,tegra20-i2c: Specify the required properties
	smb: Log an error when close_all_cached_dirs fails
	serial: sh-sci: Clean sci_ports[0] after at earlycon exit
	serial: sh-sci: Increment the runtime usage counter for the earlycon device
	smb: client: fix first command failure during re-negotiation
	smb: client: fix max_sge overflow in smb_extract_folioq_to_rdma()
	s390/pci: Fix __pcilg_mio_inuser() inline assembly
	perf: Fix sample vs do_exit()
	perf: Fix cgroup state vs ERROR
	perf/core: Fix WARN in perf_cgroup_switch()
	arm64/ptrace: Fix stack-out-of-bounds read in regs_get_kernel_stack_nth()
	scsi: elx: efct: Fix memory leak in efct_hw_parse_filter()
	RISC-V: KVM: Fix the size parameter check in SBI SFENCE calls
	RISC-V: KVM: Don't treat SBI HFENCE calls as NOPs
	gpio: pca953x: fix wrong error probe return value
	perf evsel: Missed close() when probing hybrid core PMUs
	perf test: Directory file descriptor leak
	gpio: mlxbf3: only get IRQ for device instance 0
	cifs: Remove duplicate fattr->cf_dtype assignment from wsl_to_fattr() function
	bpftool: Fix cgroup command to only show cgroup bpf programs
	Linux 6.12.35

Change-Id: Ida57d269272a624bedb979bfad0b3c5e7df7e846
Signed-off-by: Greg Kroah-Hartman <gregkh@google.com>
2025-07-10 16:01:38 +00:00

1889 lines
49 KiB
C

// SPDX-License-Identifier: GPL-2.0-or-later
/*
* UDP over IPv6
* Linux INET6 implementation
*
* Authors:
* Pedro Roque <roque@di.fc.ul.pt>
*
* Based on linux/ipv4/udp.c
*
* Fixes:
* Hideaki YOSHIFUJI : sin6_scope_id support
* YOSHIFUJI Hideaki @USAGI and: Support IPV6_V6ONLY socket option, which
* Alexey Kuznetsov allow both IPv4 and IPv6 sockets to bind
* a single port at the same time.
* Kazunori MIYAZAWA @USAGI: change process style to use ip6_append_data
* YOSHIFUJI Hideaki @USAGI: convert /proc/net/udp6 to seq_file.
*/
#include <linux/bpf-cgroup.h>
#include <linux/errno.h>
#include <linux/types.h>
#include <linux/socket.h>
#include <linux/sockios.h>
#include <linux/net.h>
#include <linux/in6.h>
#include <linux/netdevice.h>
#include <linux/if_arp.h>
#include <linux/ipv6.h>
#include <linux/icmpv6.h>
#include <linux/init.h>
#include <linux/module.h>
#include <linux/skbuff.h>
#include <linux/slab.h>
#include <linux/uaccess.h>
#include <linux/indirect_call_wrapper.h>
#include <trace/events/udp.h>
#include <net/addrconf.h>
#include <net/ndisc.h>
#include <net/protocol.h>
#include <net/transp_v6.h>
#include <net/ip6_route.h>
#include <net/raw.h>
#include <net/seg6.h>
#include <net/tcp_states.h>
#include <net/ip6_checksum.h>
#include <net/ip6_tunnel.h>
#include <net/xfrm.h>
#include <net/inet_hashtables.h>
#include <net/inet6_hashtables.h>
#include <net/busy_poll.h>
#include <net/sock_reuseport.h>
#include <net/gro.h>
#include <linux/proc_fs.h>
#include <linux/seq_file.h>
#include <trace/events/skb.h>
#include "udp_impl.h"
#include <trace/hooks/net.h>
static void udpv6_destruct_sock(struct sock *sk)
{
udp_destruct_common(sk);
inet6_sock_destruct(sk);
}
int udpv6_init_sock(struct sock *sk)
{
udp_lib_init_sock(sk);
sk->sk_destruct = udpv6_destruct_sock;
set_bit(SOCK_SUPPORT_ZC, &sk->sk_socket->flags);
return 0;
}
INDIRECT_CALLABLE_SCOPE
u32 udp6_ehashfn(const struct net *net,
const struct in6_addr *laddr,
const u16 lport,
const struct in6_addr *faddr,
const __be16 fport)
{
u32 lhash, fhash;
net_get_random_once(&udp6_ehash_secret,
sizeof(udp6_ehash_secret));
net_get_random_once(&udp_ipv6_hash_secret,
sizeof(udp_ipv6_hash_secret));
lhash = (__force u32)laddr->s6_addr32[3];
fhash = __ipv6_addr_jhash(faddr, udp_ipv6_hash_secret);
return __inet6_ehashfn(lhash, lport, fhash, fport,
udp6_ehash_secret + net_hash_mix(net));
}
int udp_v6_get_port(struct sock *sk, unsigned short snum)
{
unsigned int hash2_nulladdr =
ipv6_portaddr_hash(sock_net(sk), &in6addr_any, snum);
unsigned int hash2_partial =
ipv6_portaddr_hash(sock_net(sk), &sk->sk_v6_rcv_saddr, 0);
/* precompute partial secondary hash */
udp_sk(sk)->udp_portaddr_hash = hash2_partial;
return udp_lib_get_port(sk, snum, hash2_nulladdr);
}
void udp_v6_rehash(struct sock *sk)
{
u16 new_hash = ipv6_portaddr_hash(sock_net(sk),
&sk->sk_v6_rcv_saddr,
inet_sk(sk)->inet_num);
udp_lib_rehash(sk, new_hash);
}
static int compute_score(struct sock *sk, const struct net *net,
const struct in6_addr *saddr, __be16 sport,
const struct in6_addr *daddr, unsigned short hnum,
int dif, int sdif)
{
int bound_dev_if, score;
struct inet_sock *inet;
bool dev_match;
if (!net_eq(sock_net(sk), net) ||
udp_sk(sk)->udp_port_hash != hnum ||
sk->sk_family != PF_INET6)
return -1;
if (!ipv6_addr_equal(&sk->sk_v6_rcv_saddr, daddr))
return -1;
score = 0;
inet = inet_sk(sk);
if (inet->inet_dport) {
if (inet->inet_dport != sport)
return -1;
score++;
}
if (!ipv6_addr_any(&sk->sk_v6_daddr)) {
if (!ipv6_addr_equal(&sk->sk_v6_daddr, saddr))
return -1;
score++;
}
bound_dev_if = READ_ONCE(sk->sk_bound_dev_if);
dev_match = udp_sk_bound_dev_eq(net, bound_dev_if, dif, sdif);
if (!dev_match)
return -1;
if (bound_dev_if)
score++;
if (READ_ONCE(sk->sk_incoming_cpu) == raw_smp_processor_id())
score++;
return score;
}
/**
* udp6_lib_lookup1() - Simplified lookup using primary hash (destination port)
* @net: Network namespace
* @saddr: Source address, network order
* @sport: Source port, network order
* @daddr: Destination address, network order
* @hnum: Destination port, host order
* @dif: Destination interface index
* @sdif: Destination bridge port index, if relevant
* @udptable: Set of UDP hash tables
*
* Simplified lookup to be used as fallback if no sockets are found due to a
* potential race between (receive) address change, and lookup happening before
* the rehash operation. This function ignores SO_REUSEPORT groups while scoring
* result sockets, because if we have one, we don't need the fallback at all.
*
* Called under rcu_read_lock().
*
* Return: socket with highest matching score if any, NULL if none
*/
static struct sock *udp6_lib_lookup1(const struct net *net,
const struct in6_addr *saddr, __be16 sport,
const struct in6_addr *daddr,
unsigned int hnum, int dif, int sdif,
const struct udp_table *udptable)
{
unsigned int slot = udp_hashfn(net, hnum, udptable->mask);
struct udp_hslot *hslot = &udptable->hash[slot];
struct sock *sk, *result = NULL;
int score, badness = 0;
sk_for_each_rcu(sk, &hslot->head) {
score = compute_score(sk, net,
saddr, sport, daddr, hnum, dif, sdif);
if (score > badness) {
result = sk;
badness = score;
}
}
return result;
}
/* called with rcu_read_lock() */
static struct sock *udp6_lib_lookup2(const struct net *net,
const struct in6_addr *saddr, __be16 sport,
const struct in6_addr *daddr, unsigned int hnum,
int dif, int sdif, struct udp_hslot *hslot2,
struct sk_buff *skb)
{
struct sock *sk, *result;
int score, badness;
bool need_rescore;
result = NULL;
badness = -1;
udp_portaddr_for_each_entry_rcu(sk, &hslot2->head) {
need_rescore = false;
rescore:
score = compute_score(need_rescore ? result : sk, net, saddr,
sport, daddr, hnum, dif, sdif);
if (score > badness) {
badness = score;
if (need_rescore)
continue;
if (sk->sk_state == TCP_ESTABLISHED) {
result = sk;
continue;
}
result = inet6_lookup_reuseport(net, sk, skb, sizeof(struct udphdr),
saddr, sport, daddr, hnum, udp6_ehashfn);
if (!result) {
result = sk;
continue;
}
/* Fall back to scoring if group has connections */
if (!reuseport_has_conns(sk))
return result;
/* Reuseport logic returned an error, keep original score. */
if (IS_ERR(result))
continue;
/* compute_score is too long of a function to be
* inlined, and calling it again here yields
* measureable overhead for some
* workloads. Work around it by jumping
* backwards to rescore 'result'.
*/
need_rescore = true;
goto rescore;
}
}
return result;
}
/* rcu_read_lock() must be held */
struct sock *__udp6_lib_lookup(const struct net *net,
const struct in6_addr *saddr, __be16 sport,
const struct in6_addr *daddr, __be16 dport,
int dif, int sdif, struct udp_table *udptable,
struct sk_buff *skb)
{
unsigned short hnum = ntohs(dport);
unsigned int hash2, slot2;
struct udp_hslot *hslot2;
struct sock *result, *sk;
hash2 = ipv6_portaddr_hash(net, daddr, hnum);
slot2 = hash2 & udptable->mask;
hslot2 = &udptable->hash2[slot2];
/* Lookup connected or non-wildcard sockets */
result = udp6_lib_lookup2(net, saddr, sport,
daddr, hnum, dif, sdif,
hslot2, skb);
if (!IS_ERR_OR_NULL(result) && result->sk_state == TCP_ESTABLISHED)
goto done;
/* Lookup redirect from BPF */
if (static_branch_unlikely(&bpf_sk_lookup_enabled) &&
udptable == net->ipv4.udp_table) {
sk = inet6_lookup_run_sk_lookup(net, IPPROTO_UDP, skb, sizeof(struct udphdr),
saddr, sport, daddr, hnum, dif,
udp6_ehashfn);
if (sk) {
result = sk;
goto done;
}
}
/* Got non-wildcard socket or error on first lookup */
if (result)
goto done;
/* Lookup wildcard sockets */
hash2 = ipv6_portaddr_hash(net, &in6addr_any, hnum);
slot2 = hash2 & udptable->mask;
hslot2 = &udptable->hash2[slot2];
result = udp6_lib_lookup2(net, saddr, sport,
&in6addr_any, hnum, dif, sdif,
hslot2, skb);
if (!IS_ERR_OR_NULL(result))
goto done;
/* Cover address change/lookup/rehash race: see __udp4_lib_lookup() */
result = udp6_lib_lookup1(net, saddr, sport, daddr, hnum, dif, sdif,
udptable);
done:
if (IS_ERR(result))
return NULL;
return result;
}
EXPORT_SYMBOL_GPL(__udp6_lib_lookup);
static struct sock *__udp6_lib_lookup_skb(struct sk_buff *skb,
__be16 sport, __be16 dport,
struct udp_table *udptable)
{
const struct ipv6hdr *iph = ipv6_hdr(skb);
return __udp6_lib_lookup(dev_net(skb->dev), &iph->saddr, sport,
&iph->daddr, dport, inet6_iif(skb),
inet6_sdif(skb), udptable, skb);
}
struct sock *udp6_lib_lookup_skb(const struct sk_buff *skb,
__be16 sport, __be16 dport)
{
const u16 offset = NAPI_GRO_CB(skb)->network_offsets[skb->encapsulation];
const struct ipv6hdr *iph = (struct ipv6hdr *)(skb->data + offset);
struct net *net = dev_net(skb->dev);
int iif, sdif;
inet6_get_iif_sdif(skb, &iif, &sdif);
return __udp6_lib_lookup(net, &iph->saddr, sport,
&iph->daddr, dport, iif,
sdif, net->ipv4.udp_table, NULL);
}
/* Must be called under rcu_read_lock().
* Does increment socket refcount.
*/
#if IS_ENABLED(CONFIG_NF_TPROXY_IPV6) || IS_ENABLED(CONFIG_NF_SOCKET_IPV6)
struct sock *udp6_lib_lookup(const struct net *net, const struct in6_addr *saddr, __be16 sport,
const struct in6_addr *daddr, __be16 dport, int dif)
{
struct sock *sk;
sk = __udp6_lib_lookup(net, saddr, sport, daddr, dport,
dif, 0, net->ipv4.udp_table, NULL);
if (sk && !refcount_inc_not_zero(&sk->sk_refcnt))
sk = NULL;
return sk;
}
EXPORT_SYMBOL_GPL(udp6_lib_lookup);
#endif
/* do not use the scratch area len for jumbogram: their length execeeds the
* scratch area space; note that the IP6CB flags is still in the first
* cacheline, so checking for jumbograms is cheap
*/
static int udp6_skb_len(struct sk_buff *skb)
{
return unlikely(inet6_is_jumbogram(skb)) ? skb->len : udp_skb_len(skb);
}
/*
* This should be easy, if there is something there we
* return it, otherwise we block.
*/
int udpv6_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
int flags, int *addr_len)
{
struct ipv6_pinfo *np = inet6_sk(sk);
struct inet_sock *inet = inet_sk(sk);
struct sk_buff *skb;
unsigned int ulen, copied;
int off, err, peeking = flags & MSG_PEEK;
int is_udplite = IS_UDPLITE(sk);
struct udp_mib __percpu *mib;
bool checksum_valid = false;
int is_udp4;
if (flags & MSG_ERRQUEUE)
return ipv6_recv_error(sk, msg, len, addr_len);
if (np->rxpmtu && np->rxopt.bits.rxpmtu)
return ipv6_recv_rxpmtu(sk, msg, len, addr_len);
try_again:
off = sk_peek_offset(sk, flags);
skb = __skb_recv_udp(sk, flags, &off, &err);
if (!skb)
return err;
ulen = udp6_skb_len(skb);
copied = len;
if (copied > ulen - off)
copied = ulen - off;
else if (copied < ulen)
msg->msg_flags |= MSG_TRUNC;
is_udp4 = (skb->protocol == htons(ETH_P_IP));
mib = __UDPX_MIB(sk, is_udp4);
/*
* If checksum is needed at all, try to do it while copying the
* data. If the data is truncated, or if we only want a partial
* coverage checksum (UDP-Lite), do it before the copy.
*/
if (copied < ulen || peeking ||
(is_udplite && UDP_SKB_CB(skb)->partial_cov)) {
checksum_valid = udp_skb_csum_unnecessary(skb) ||
!__udp_lib_checksum_complete(skb);
if (!checksum_valid)
goto csum_copy_err;
}
if (checksum_valid || udp_skb_csum_unnecessary(skb)) {
if (udp_skb_is_linear(skb))
err = copy_linear_skb(skb, copied, off, &msg->msg_iter);
else
err = skb_copy_datagram_msg(skb, off, msg, copied);
} else {
err = skb_copy_and_csum_datagram_msg(skb, off, msg);
if (err == -EINVAL)
goto csum_copy_err;
}
if (unlikely(err)) {
if (!peeking) {
atomic_inc(&sk->sk_drops);
SNMP_INC_STATS(mib, UDP_MIB_INERRORS);
}
kfree_skb(skb);
return err;
}
if (!peeking)
SNMP_INC_STATS(mib, UDP_MIB_INDATAGRAMS);
sock_recv_cmsgs(msg, sk, skb);
/* Copy the address. */
if (msg->msg_name) {
DECLARE_SOCKADDR(struct sockaddr_in6 *, sin6, msg->msg_name);
sin6->sin6_family = AF_INET6;
sin6->sin6_port = udp_hdr(skb)->source;
sin6->sin6_flowinfo = 0;
if (is_udp4) {
ipv6_addr_set_v4mapped(ip_hdr(skb)->saddr,
&sin6->sin6_addr);
sin6->sin6_scope_id = 0;
} else {
sin6->sin6_addr = ipv6_hdr(skb)->saddr;
sin6->sin6_scope_id =
ipv6_iface_scope_id(&sin6->sin6_addr,
inet6_iif(skb));
}
*addr_len = sizeof(*sin6);
BPF_CGROUP_RUN_PROG_UDP6_RECVMSG_LOCK(sk,
(struct sockaddr *)sin6,
addr_len);
}
if (udp_test_bit(GRO_ENABLED, sk))
udp_cmsg_recv(msg, sk, skb);
if (np->rxopt.all)
ip6_datagram_recv_common_ctl(sk, msg, skb);
if (is_udp4) {
if (inet_cmsg_flags(inet))
ip_cmsg_recv_offset(msg, sk, skb,
sizeof(struct udphdr), off);
} else {
if (np->rxopt.all)
ip6_datagram_recv_specific_ctl(sk, msg, skb);
}
err = copied;
if (flags & MSG_TRUNC)
err = ulen;
trace_android_rvh_udpv6_recvmsg(sk, msg, len, flags, addr_len);
skb_consume_udp(sk, skb, peeking ? -err : err);
return err;
csum_copy_err:
if (!__sk_queue_drop_skb(sk, &udp_sk(sk)->reader_queue, skb, flags,
udp_skb_destructor)) {
SNMP_INC_STATS(mib, UDP_MIB_CSUMERRORS);
SNMP_INC_STATS(mib, UDP_MIB_INERRORS);
}
kfree_skb(skb);
/* starting over for a new packet, but check if we need to yield */
cond_resched();
msg->msg_flags &= ~MSG_TRUNC;
goto try_again;
}
DECLARE_STATIC_KEY_FALSE(udpv6_encap_needed_key);
void udpv6_encap_enable(void)
{
static_branch_inc(&udpv6_encap_needed_key);
}
EXPORT_SYMBOL(udpv6_encap_enable);
/* Handler for tunnels with arbitrary destination ports: no socket lookup, go
* through error handlers in encapsulations looking for a match.
*/
static int __udp6_lib_err_encap_no_sk(struct sk_buff *skb,
struct inet6_skb_parm *opt,
u8 type, u8 code, int offset, __be32 info)
{
int i;
for (i = 0; i < MAX_IPTUN_ENCAP_OPS; i++) {
int (*handler)(struct sk_buff *skb, struct inet6_skb_parm *opt,
u8 type, u8 code, int offset, __be32 info);
const struct ip6_tnl_encap_ops *encap;
encap = rcu_dereference(ip6tun_encaps[i]);
if (!encap)
continue;
handler = encap->err_handler;
if (handler && !handler(skb, opt, type, code, offset, info))
return 0;
}
return -ENOENT;
}
/* Try to match ICMP errors to UDP tunnels by looking up a socket without
* reversing source and destination port: this will match tunnels that force the
* same destination port on both endpoints (e.g. VXLAN, GENEVE). Note that
* lwtunnels might actually break this assumption by being configured with
* different destination ports on endpoints, in this case we won't be able to
* trace ICMP messages back to them.
*
* If this doesn't match any socket, probe tunnels with arbitrary destination
* ports (e.g. FoU, GUE): there, the receiving socket is useless, as the port
* we've sent packets to won't necessarily match the local destination port.
*
* Then ask the tunnel implementation to match the error against a valid
* association.
*
* Return an error if we can't find a match, the socket if we need further
* processing, zero otherwise.
*/
static struct sock *__udp6_lib_err_encap(struct net *net,
const struct ipv6hdr *hdr, int offset,
struct udphdr *uh,
struct udp_table *udptable,
struct sock *sk,
struct sk_buff *skb,
struct inet6_skb_parm *opt,
u8 type, u8 code, __be32 info)
{
int (*lookup)(struct sock *sk, struct sk_buff *skb);
int network_offset, transport_offset;
struct udp_sock *up;
network_offset = skb_network_offset(skb);
transport_offset = skb_transport_offset(skb);
/* Network header needs to point to the outer IPv6 header inside ICMP */
skb_reset_network_header(skb);
/* Transport header needs to point to the UDP header */
skb_set_transport_header(skb, offset);
if (sk) {
up = udp_sk(sk);
lookup = READ_ONCE(up->encap_err_lookup);
if (lookup && lookup(sk, skb))
sk = NULL;
goto out;
}
sk = __udp6_lib_lookup(net, &hdr->daddr, uh->source,
&hdr->saddr, uh->dest,
inet6_iif(skb), 0, udptable, skb);
if (sk) {
up = udp_sk(sk);
lookup = READ_ONCE(up->encap_err_lookup);
if (!lookup || lookup(sk, skb))
sk = NULL;
}
out:
if (!sk) {
sk = ERR_PTR(__udp6_lib_err_encap_no_sk(skb, opt, type, code,
offset, info));
}
skb_set_transport_header(skb, transport_offset);
skb_set_network_header(skb, network_offset);
return sk;
}
int __udp6_lib_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
u8 type, u8 code, int offset, __be32 info,
struct udp_table *udptable)
{
struct ipv6_pinfo *np;
const struct ipv6hdr *hdr = (const struct ipv6hdr *)skb->data;
const struct in6_addr *saddr = &hdr->saddr;
const struct in6_addr *daddr = seg6_get_daddr(skb, opt) ? : &hdr->daddr;
struct udphdr *uh = (struct udphdr *)(skb->data+offset);
bool tunnel = false;
struct sock *sk;
int harderr;
int err;
struct net *net = dev_net(skb->dev);
sk = __udp6_lib_lookup(net, daddr, uh->dest, saddr, uh->source,
inet6_iif(skb), inet6_sdif(skb), udptable, NULL);
if (!sk || READ_ONCE(udp_sk(sk)->encap_type)) {
/* No socket for error: try tunnels before discarding */
if (static_branch_unlikely(&udpv6_encap_needed_key)) {
sk = __udp6_lib_err_encap(net, hdr, offset, uh,
udptable, sk, skb,
opt, type, code, info);
if (!sk)
return 0;
} else
sk = ERR_PTR(-ENOENT);
if (IS_ERR(sk)) {
__ICMP6_INC_STATS(net, __in6_dev_get(skb->dev),
ICMP6_MIB_INERRORS);
return PTR_ERR(sk);
}
tunnel = true;
}
harderr = icmpv6_err_convert(type, code, &err);
np = inet6_sk(sk);
if (type == ICMPV6_PKT_TOOBIG) {
if (!ip6_sk_accept_pmtu(sk))
goto out;
ip6_sk_update_pmtu(skb, sk, info);
if (READ_ONCE(np->pmtudisc) != IPV6_PMTUDISC_DONT)
harderr = 1;
}
if (type == NDISC_REDIRECT) {
if (tunnel) {
ip6_redirect(skb, sock_net(sk), inet6_iif(skb),
READ_ONCE(sk->sk_mark), sk->sk_uid);
} else {
ip6_sk_redirect(skb, sk);
}
goto out;
}
/* Tunnels don't have an application socket: don't pass errors back */
if (tunnel) {
if (udp_sk(sk)->encap_err_rcv)
udp_sk(sk)->encap_err_rcv(sk, skb, err, uh->dest,
ntohl(info), (u8 *)(uh+1));
goto out;
}
if (!inet6_test_bit(RECVERR6, sk)) {
if (!harderr || sk->sk_state != TCP_ESTABLISHED)
goto out;
} else {
ipv6_icmp_error(sk, skb, err, uh->dest, ntohl(info), (u8 *)(uh+1));
}
sk->sk_err = err;
sk_error_report(sk);
out:
return 0;
}
static int __udpv6_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
{
int rc;
if (!ipv6_addr_any(&sk->sk_v6_daddr)) {
sock_rps_save_rxhash(sk, skb);
sk_mark_napi_id(sk, skb);
sk_incoming_cpu_update(sk);
} else {
sk_mark_napi_id_once(sk, skb);
}
rc = __udp_enqueue_schedule_skb(sk, skb);
if (rc < 0) {
int is_udplite = IS_UDPLITE(sk);
enum skb_drop_reason drop_reason;
/* Note that an ENOMEM error is charged twice */
if (rc == -ENOMEM) {
UDP6_INC_STATS(sock_net(sk),
UDP_MIB_RCVBUFERRORS, is_udplite);
drop_reason = SKB_DROP_REASON_SOCKET_RCVBUFF;
} else {
UDP6_INC_STATS(sock_net(sk),
UDP_MIB_MEMERRORS, is_udplite);
drop_reason = SKB_DROP_REASON_PROTO_MEM;
}
UDP6_INC_STATS(sock_net(sk), UDP_MIB_INERRORS, is_udplite);
trace_udp_fail_queue_rcv_skb(rc, sk, skb);
sk_skb_reason_drop(sk, skb, drop_reason);
return -1;
}
return 0;
}
static __inline__ int udpv6_err(struct sk_buff *skb,
struct inet6_skb_parm *opt, u8 type,
u8 code, int offset, __be32 info)
{
return __udp6_lib_err(skb, opt, type, code, offset, info,
dev_net(skb->dev)->ipv4.udp_table);
}
static int udpv6_queue_rcv_one_skb(struct sock *sk, struct sk_buff *skb)
{
enum skb_drop_reason drop_reason = SKB_DROP_REASON_NOT_SPECIFIED;
struct udp_sock *up = udp_sk(sk);
int is_udplite = IS_UDPLITE(sk);
if (!xfrm6_policy_check(sk, XFRM_POLICY_IN, skb)) {
drop_reason = SKB_DROP_REASON_XFRM_POLICY;
goto drop;
}
nf_reset_ct(skb);
if (static_branch_unlikely(&udpv6_encap_needed_key) &&
READ_ONCE(up->encap_type)) {
int (*encap_rcv)(struct sock *sk, struct sk_buff *skb);
/*
* This is an encapsulation socket so pass the skb to
* the socket's udp_encap_rcv() hook. Otherwise, just
* fall through and pass this up the UDP socket.
* up->encap_rcv() returns the following value:
* =0 if skb was successfully passed to the encap
* handler or was discarded by it.
* >0 if skb should be passed on to UDP.
* <0 if skb should be resubmitted as proto -N
*/
/* if we're overly short, let UDP handle it */
encap_rcv = READ_ONCE(up->encap_rcv);
if (encap_rcv) {
int ret;
/* Verify checksum before giving to encap */
if (udp_lib_checksum_complete(skb))
goto csum_error;
ret = encap_rcv(sk, skb);
if (ret <= 0) {
__UDP6_INC_STATS(sock_net(sk),
UDP_MIB_INDATAGRAMS,
is_udplite);
return -ret;
}
}
/* FALLTHROUGH -- it's a UDP Packet */
}
/*
* UDP-Lite specific tests, ignored on UDP sockets (see net/ipv4/udp.c).
*/
if (udp_test_bit(UDPLITE_RECV_CC, sk) && UDP_SKB_CB(skb)->partial_cov) {
u16 pcrlen = READ_ONCE(up->pcrlen);
if (pcrlen == 0) { /* full coverage was set */
net_dbg_ratelimited("UDPLITE6: partial coverage %d while full coverage %d requested\n",
UDP_SKB_CB(skb)->cscov, skb->len);
goto drop;
}
if (UDP_SKB_CB(skb)->cscov < pcrlen) {
net_dbg_ratelimited("UDPLITE6: coverage %d too small, need min %d\n",
UDP_SKB_CB(skb)->cscov, pcrlen);
goto drop;
}
}
prefetch(&sk->sk_rmem_alloc);
if (rcu_access_pointer(sk->sk_filter) &&
udp_lib_checksum_complete(skb))
goto csum_error;
if (sk_filter_trim_cap(sk, skb, sizeof(struct udphdr))) {
drop_reason = SKB_DROP_REASON_SOCKET_FILTER;
goto drop;
}
udp_csum_pull_header(skb);
skb_dst_drop(skb);
return __udpv6_queue_rcv_skb(sk, skb);
csum_error:
drop_reason = SKB_DROP_REASON_UDP_CSUM;
__UDP6_INC_STATS(sock_net(sk), UDP_MIB_CSUMERRORS, is_udplite);
drop:
__UDP6_INC_STATS(sock_net(sk), UDP_MIB_INERRORS, is_udplite);
atomic_inc(&sk->sk_drops);
sk_skb_reason_drop(sk, skb, drop_reason);
return -1;
}
static int udpv6_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
{
struct sk_buff *next, *segs;
int ret;
if (likely(!udp_unexpected_gso(sk, skb)))
return udpv6_queue_rcv_one_skb(sk, skb);
__skb_push(skb, -skb_mac_offset(skb));
segs = udp_rcv_segment(sk, skb, false);
skb_list_walk_safe(segs, skb, next) {
__skb_pull(skb, skb_transport_offset(skb));
udp_post_segment_fix_csum(skb);
ret = udpv6_queue_rcv_one_skb(sk, skb);
if (ret > 0)
ip6_protocol_deliver_rcu(dev_net(skb->dev), skb, ret,
true);
}
return 0;
}
static bool __udp_v6_is_mcast_sock(struct net *net, const struct sock *sk,
__be16 loc_port, const struct in6_addr *loc_addr,
__be16 rmt_port, const struct in6_addr *rmt_addr,
int dif, int sdif, unsigned short hnum)
{
const struct inet_sock *inet = inet_sk(sk);
if (!net_eq(sock_net(sk), net))
return false;
if (udp_sk(sk)->udp_port_hash != hnum ||
sk->sk_family != PF_INET6 ||
(inet->inet_dport && inet->inet_dport != rmt_port) ||
(!ipv6_addr_any(&sk->sk_v6_daddr) &&
!ipv6_addr_equal(&sk->sk_v6_daddr, rmt_addr)) ||
!udp_sk_bound_dev_eq(net, READ_ONCE(sk->sk_bound_dev_if), dif, sdif) ||
(!ipv6_addr_any(&sk->sk_v6_rcv_saddr) &&
!ipv6_addr_equal(&sk->sk_v6_rcv_saddr, loc_addr)))
return false;
if (!inet6_mc_check(sk, loc_addr, rmt_addr))
return false;
return true;
}
static void udp6_csum_zero_error(struct sk_buff *skb)
{
/* RFC 2460 section 8.1 says that we SHOULD log
* this error. Well, it is reasonable.
*/
net_dbg_ratelimited("IPv6: udp checksum is 0 for [%pI6c]:%u->[%pI6c]:%u\n",
&ipv6_hdr(skb)->saddr, ntohs(udp_hdr(skb)->source),
&ipv6_hdr(skb)->daddr, ntohs(udp_hdr(skb)->dest));
}
/*
* Note: called only from the BH handler context,
* so we don't need to lock the hashes.
*/
static int __udp6_lib_mcast_deliver(struct net *net, struct sk_buff *skb,
const struct in6_addr *saddr, const struct in6_addr *daddr,
struct udp_table *udptable, int proto)
{
struct sock *sk, *first = NULL;
const struct udphdr *uh = udp_hdr(skb);
unsigned short hnum = ntohs(uh->dest);
struct udp_hslot *hslot = udp_hashslot(udptable, net, hnum);
unsigned int offset = offsetof(typeof(*sk), sk_node);
unsigned int hash2 = 0, hash2_any = 0, use_hash2 = (hslot->count > 10);
int dif = inet6_iif(skb);
int sdif = inet6_sdif(skb);
struct hlist_node *node;
struct sk_buff *nskb;
if (use_hash2) {
hash2_any = ipv6_portaddr_hash(net, &in6addr_any, hnum) &
udptable->mask;
hash2 = ipv6_portaddr_hash(net, daddr, hnum) & udptable->mask;
start_lookup:
hslot = &udptable->hash2[hash2];
offset = offsetof(typeof(*sk), __sk_common.skc_portaddr_node);
}
sk_for_each_entry_offset_rcu(sk, node, &hslot->head, offset) {
if (!__udp_v6_is_mcast_sock(net, sk, uh->dest, daddr,
uh->source, saddr, dif, sdif,
hnum))
continue;
/* If zero checksum and no_check is not on for
* the socket then skip it.
*/
if (!uh->check && !udp_get_no_check6_rx(sk))
continue;
if (!first) {
first = sk;
continue;
}
nskb = skb_clone(skb, GFP_ATOMIC);
if (unlikely(!nskb)) {
atomic_inc(&sk->sk_drops);
__UDP6_INC_STATS(net, UDP_MIB_RCVBUFERRORS,
IS_UDPLITE(sk));
__UDP6_INC_STATS(net, UDP_MIB_INERRORS,
IS_UDPLITE(sk));
continue;
}
if (udpv6_queue_rcv_skb(sk, nskb) > 0)
consume_skb(nskb);
}
/* Also lookup *:port if we are using hash2 and haven't done so yet. */
if (use_hash2 && hash2 != hash2_any) {
hash2 = hash2_any;
goto start_lookup;
}
if (first) {
if (udpv6_queue_rcv_skb(first, skb) > 0)
consume_skb(skb);
} else {
kfree_skb(skb);
__UDP6_INC_STATS(net, UDP_MIB_IGNOREDMULTI,
proto == IPPROTO_UDPLITE);
}
return 0;
}
static void udp6_sk_rx_dst_set(struct sock *sk, struct dst_entry *dst)
{
if (udp_sk_rx_dst_set(sk, dst))
sk->sk_rx_dst_cookie = rt6_get_cookie(dst_rt6_info(dst));
}
/* wrapper for udp_queue_rcv_skb tacking care of csum conversion and
* return code conversion for ip layer consumption
*/
static int udp6_unicast_rcv_skb(struct sock *sk, struct sk_buff *skb,
struct udphdr *uh)
{
int ret;
if (inet_get_convert_csum(sk) && uh->check && !IS_UDPLITE(sk))
skb_checksum_try_convert(skb, IPPROTO_UDP, ip6_compute_pseudo);
trace_android_vh_udp6_unicast_rcv_skb(skb, sk);
ret = udpv6_queue_rcv_skb(sk, skb);
/* a return value > 0 means to resubmit the input */
if (ret > 0)
return ret;
return 0;
}
int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable,
int proto)
{
enum skb_drop_reason reason = SKB_DROP_REASON_NOT_SPECIFIED;
const struct in6_addr *saddr, *daddr;
struct net *net = dev_net(skb->dev);
struct sock *sk = NULL;
struct udphdr *uh;
bool refcounted;
u32 ulen = 0;
if (!pskb_may_pull(skb, sizeof(struct udphdr)))
goto discard;
saddr = &ipv6_hdr(skb)->saddr;
daddr = &ipv6_hdr(skb)->daddr;
uh = udp_hdr(skb);
ulen = ntohs(uh->len);
if (ulen > skb->len)
goto short_packet;
if (proto == IPPROTO_UDP) {
/* UDP validates ulen. */
/* Check for jumbo payload */
if (ulen == 0)
ulen = skb->len;
if (ulen < sizeof(*uh))
goto short_packet;
if (ulen < skb->len) {
if (pskb_trim_rcsum(skb, ulen))
goto short_packet;
saddr = &ipv6_hdr(skb)->saddr;
daddr = &ipv6_hdr(skb)->daddr;
uh = udp_hdr(skb);
}
}
if (udp6_csum_init(skb, uh, proto))
goto csum_error;
/* Check if the socket is already available, e.g. due to early demux */
sk = inet6_steal_sock(net, skb, sizeof(struct udphdr), saddr, uh->source, daddr, uh->dest,
&refcounted, udp6_ehashfn);
if (IS_ERR(sk))
goto no_sk;
if (sk) {
struct dst_entry *dst = skb_dst(skb);
int ret;
if (unlikely(rcu_dereference(sk->sk_rx_dst) != dst))
udp6_sk_rx_dst_set(sk, dst);
if (!uh->check && !udp_get_no_check6_rx(sk)) {
if (refcounted)
sock_put(sk);
goto report_csum_error;
}
ret = udp6_unicast_rcv_skb(sk, skb, uh);
if (refcounted)
sock_put(sk);
return ret;
}
/*
* Multicast receive code
*/
if (ipv6_addr_is_multicast(daddr))
return __udp6_lib_mcast_deliver(net, skb,
saddr, daddr, udptable, proto);
/* Unicast */
sk = __udp6_lib_lookup_skb(skb, uh->source, uh->dest, udptable);
if (sk) {
if (!uh->check && !udp_get_no_check6_rx(sk))
goto report_csum_error;
return udp6_unicast_rcv_skb(sk, skb, uh);
}
no_sk:
reason = SKB_DROP_REASON_NO_SOCKET;
if (!uh->check)
goto report_csum_error;
if (!xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb))
goto discard;
nf_reset_ct(skb);
if (udp_lib_checksum_complete(skb))
goto csum_error;
__UDP6_INC_STATS(net, UDP_MIB_NOPORTS, proto == IPPROTO_UDPLITE);
icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_PORT_UNREACH, 0);
sk_skb_reason_drop(sk, skb, reason);
return 0;
short_packet:
if (reason == SKB_DROP_REASON_NOT_SPECIFIED)
reason = SKB_DROP_REASON_PKT_TOO_SMALL;
net_dbg_ratelimited("UDP%sv6: short packet: From [%pI6c]:%u %d/%d to [%pI6c]:%u\n",
proto == IPPROTO_UDPLITE ? "-Lite" : "",
saddr, ntohs(uh->source),
ulen, skb->len,
daddr, ntohs(uh->dest));
goto discard;
report_csum_error:
udp6_csum_zero_error(skb);
csum_error:
if (reason == SKB_DROP_REASON_NOT_SPECIFIED)
reason = SKB_DROP_REASON_UDP_CSUM;
__UDP6_INC_STATS(net, UDP_MIB_CSUMERRORS, proto == IPPROTO_UDPLITE);
discard:
__UDP6_INC_STATS(net, UDP_MIB_INERRORS, proto == IPPROTO_UDPLITE);
sk_skb_reason_drop(sk, skb, reason);
return 0;
}
static struct sock *__udp6_lib_demux_lookup(struct net *net,
__be16 loc_port, const struct in6_addr *loc_addr,
__be16 rmt_port, const struct in6_addr *rmt_addr,
int dif, int sdif)
{
struct udp_table *udptable = net->ipv4.udp_table;
unsigned short hnum = ntohs(loc_port);
unsigned int hash2, slot2;
struct udp_hslot *hslot2;
__portpair ports;
struct sock *sk;
hash2 = ipv6_portaddr_hash(net, loc_addr, hnum);
slot2 = hash2 & udptable->mask;
hslot2 = &udptable->hash2[slot2];
ports = INET_COMBINED_PORTS(rmt_port, hnum);
udp_portaddr_for_each_entry_rcu(sk, &hslot2->head) {
if (sk->sk_state == TCP_ESTABLISHED &&
inet6_match(net, sk, rmt_addr, loc_addr, ports, dif, sdif))
return sk;
/* Only check first socket in chain */
break;
}
return NULL;
}
void udp_v6_early_demux(struct sk_buff *skb)
{
struct net *net = dev_net(skb->dev);
const struct udphdr *uh;
struct sock *sk;
struct dst_entry *dst;
int dif = skb->dev->ifindex;
int sdif = inet6_sdif(skb);
if (!pskb_may_pull(skb, skb_transport_offset(skb) +
sizeof(struct udphdr)))
return;
uh = udp_hdr(skb);
if (skb->pkt_type == PACKET_HOST)
sk = __udp6_lib_demux_lookup(net, uh->dest,
&ipv6_hdr(skb)->daddr,
uh->source, &ipv6_hdr(skb)->saddr,
dif, sdif);
else
return;
if (!sk)
return;
skb->sk = sk;
DEBUG_NET_WARN_ON_ONCE(sk_is_refcounted(sk));
skb->destructor = sock_pfree;
dst = rcu_dereference(sk->sk_rx_dst);
if (dst)
dst = dst_check(dst, sk->sk_rx_dst_cookie);
if (dst) {
/* set noref for now.
* any place which wants to hold dst has to call
* dst_hold_safe()
*/
skb_dst_set_noref(skb, dst);
}
}
INDIRECT_CALLABLE_SCOPE int udpv6_rcv(struct sk_buff *skb)
{
return __udp6_lib_rcv(skb, dev_net(skb->dev)->ipv4.udp_table, IPPROTO_UDP);
}
/*
* Throw away all pending data and cancel the corking. Socket is locked.
*/
static void udp_v6_flush_pending_frames(struct sock *sk)
{
struct udp_sock *up = udp_sk(sk);
if (up->pending == AF_INET)
udp_flush_pending_frames(sk);
else if (up->pending) {
up->len = 0;
WRITE_ONCE(up->pending, 0);
ip6_flush_pending_frames(sk);
}
}
static int udpv6_pre_connect(struct sock *sk, struct sockaddr *uaddr,
int addr_len)
{
if (addr_len < offsetofend(struct sockaddr, sa_family))
return -EINVAL;
/* The following checks are replicated from __ip6_datagram_connect()
* and intended to prevent BPF program called below from accessing
* bytes that are out of the bound specified by user in addr_len.
*/
if (uaddr->sa_family == AF_INET) {
if (ipv6_only_sock(sk))
return -EAFNOSUPPORT;
return udp_pre_connect(sk, uaddr, addr_len);
}
if (addr_len < SIN6_LEN_RFC2133)
return -EINVAL;
return BPF_CGROUP_RUN_PROG_INET6_CONNECT_LOCK(sk, uaddr, &addr_len);
}
/**
* udp6_hwcsum_outgoing - handle outgoing HW checksumming
* @sk: socket we are sending on
* @skb: sk_buff containing the filled-in UDP header
* (checksum field must be zeroed out)
* @saddr: source address
* @daddr: destination address
* @len: length of packet
*/
static void udp6_hwcsum_outgoing(struct sock *sk, struct sk_buff *skb,
const struct in6_addr *saddr,
const struct in6_addr *daddr, int len)
{
unsigned int offset;
struct udphdr *uh = udp_hdr(skb);
struct sk_buff *frags = skb_shinfo(skb)->frag_list;
__wsum csum = 0;
if (!frags) {
/* Only one fragment on the socket. */
skb->csum_start = skb_transport_header(skb) - skb->head;
skb->csum_offset = offsetof(struct udphdr, check);
uh->check = ~csum_ipv6_magic(saddr, daddr, len, IPPROTO_UDP, 0);
} else {
/*
* HW-checksum won't work as there are two or more
* fragments on the socket so that all csums of sk_buffs
* should be together
*/
offset = skb_transport_offset(skb);
skb->csum = skb_checksum(skb, offset, skb->len - offset, 0);
csum = skb->csum;
skb->ip_summed = CHECKSUM_NONE;
do {
csum = csum_add(csum, frags->csum);
} while ((frags = frags->next));
uh->check = csum_ipv6_magic(saddr, daddr, len, IPPROTO_UDP,
csum);
if (uh->check == 0)
uh->check = CSUM_MANGLED_0;
}
}
/*
* Sending
*/
static int udp_v6_send_skb(struct sk_buff *skb, struct flowi6 *fl6,
struct inet_cork *cork)
{
struct sock *sk = skb->sk;
struct udphdr *uh;
int err = 0;
int is_udplite = IS_UDPLITE(sk);
__wsum csum = 0;
int offset = skb_transport_offset(skb);
int len = skb->len - offset;
int datalen = len - sizeof(*uh);
/*
* Create a UDP header
*/
uh = udp_hdr(skb);
uh->source = fl6->fl6_sport;
uh->dest = fl6->fl6_dport;
uh->len = htons(len);
uh->check = 0;
if (cork->gso_size) {
const int hlen = skb_network_header_len(skb) +
sizeof(struct udphdr);
if (hlen + min(datalen, cork->gso_size) > cork->fragsize) {
kfree_skb(skb);
return -EMSGSIZE;
}
if (datalen > cork->gso_size * UDP_MAX_SEGMENTS) {
kfree_skb(skb);
return -EINVAL;
}
if (udp_get_no_check6_tx(sk)) {
kfree_skb(skb);
return -EINVAL;
}
if (is_udplite || dst_xfrm(skb_dst(skb))) {
kfree_skb(skb);
return -EIO;
}
if (datalen > cork->gso_size) {
skb_shinfo(skb)->gso_size = cork->gso_size;
skb_shinfo(skb)->gso_type = SKB_GSO_UDP_L4;
skb_shinfo(skb)->gso_segs = DIV_ROUND_UP(datalen,
cork->gso_size);
/* Don't checksum the payload, skb will get segmented */
goto csum_partial;
}
}
if (is_udplite)
csum = udplite_csum(skb);
else if (udp_get_no_check6_tx(sk)) { /* UDP csum disabled */
skb->ip_summed = CHECKSUM_NONE;
goto send;
} else if (skb->ip_summed == CHECKSUM_PARTIAL) { /* UDP hardware csum */
csum_partial:
udp6_hwcsum_outgoing(sk, skb, &fl6->saddr, &fl6->daddr, len);
goto send;
} else
csum = udp_csum(skb);
/* add protocol-dependent pseudo-header */
uh->check = csum_ipv6_magic(&fl6->saddr, &fl6->daddr,
len, fl6->flowi6_proto, csum);
if (uh->check == 0)
uh->check = CSUM_MANGLED_0;
send:
err = ip6_send_skb(skb);
if (err) {
if (err == -ENOBUFS && !inet6_test_bit(RECVERR6, sk)) {
UDP6_INC_STATS(sock_net(sk),
UDP_MIB_SNDBUFERRORS, is_udplite);
err = 0;
}
} else {
UDP6_INC_STATS(sock_net(sk),
UDP_MIB_OUTDATAGRAMS, is_udplite);
}
return err;
}
static int udp_v6_push_pending_frames(struct sock *sk)
{
struct sk_buff *skb;
struct udp_sock *up = udp_sk(sk);
int err = 0;
if (up->pending == AF_INET)
return udp_push_pending_frames(sk);
skb = ip6_finish_skb(sk);
if (!skb)
goto out;
err = udp_v6_send_skb(skb, &inet_sk(sk)->cork.fl.u.ip6,
&inet_sk(sk)->cork.base);
out:
up->len = 0;
WRITE_ONCE(up->pending, 0);
return err;
}
int udpv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
{
struct ipv6_txoptions opt_space;
struct udp_sock *up = udp_sk(sk);
struct inet_sock *inet = inet_sk(sk);
struct ipv6_pinfo *np = inet6_sk(sk);
DECLARE_SOCKADDR(struct sockaddr_in6 *, sin6, msg->msg_name);
struct in6_addr *daddr, *final_p, final;
struct ipv6_txoptions *opt = NULL;
struct ipv6_txoptions *opt_to_free = NULL;
struct ip6_flowlabel *flowlabel = NULL;
struct inet_cork_full cork;
struct flowi6 *fl6 = &cork.fl.u.ip6;
struct dst_entry *dst;
struct ipcm6_cookie ipc6;
int addr_len = msg->msg_namelen;
bool connected = false;
int ulen = len;
int corkreq = udp_test_bit(CORK, sk) || msg->msg_flags & MSG_MORE;
int err;
int is_udplite = IS_UDPLITE(sk);
int (*getfrag)(void *, char *, int, int, int, struct sk_buff *);
trace_android_rvh_udpv6_sendmsg(sk, msg, len);
ipcm6_init_sk(&ipc6, sk);
ipc6.gso_size = READ_ONCE(up->gso_size);
ipc6.sockc.tsflags = READ_ONCE(sk->sk_tsflags);
ipc6.sockc.mark = READ_ONCE(sk->sk_mark);
/* destination address check */
if (sin6) {
if (addr_len < offsetof(struct sockaddr, sa_data))
return -EINVAL;
switch (sin6->sin6_family) {
case AF_INET6:
if (addr_len < SIN6_LEN_RFC2133)
return -EINVAL;
daddr = &sin6->sin6_addr;
if (ipv6_addr_any(daddr) &&
ipv6_addr_v4mapped(&np->saddr))
ipv6_addr_set_v4mapped(htonl(INADDR_LOOPBACK),
daddr);
break;
case AF_INET:
goto do_udp_sendmsg;
case AF_UNSPEC:
msg->msg_name = sin6 = NULL;
msg->msg_namelen = addr_len = 0;
daddr = NULL;
break;
default:
return -EINVAL;
}
} else if (!READ_ONCE(up->pending)) {
if (sk->sk_state != TCP_ESTABLISHED)
return -EDESTADDRREQ;
daddr = &sk->sk_v6_daddr;
} else
daddr = NULL;
if (daddr) {
if (ipv6_addr_v4mapped(daddr)) {
struct sockaddr_in sin;
sin.sin_family = AF_INET;
sin.sin_port = sin6 ? sin6->sin6_port : inet->inet_dport;
sin.sin_addr.s_addr = daddr->s6_addr32[3];
msg->msg_name = &sin;
msg->msg_namelen = sizeof(sin);
do_udp_sendmsg:
err = ipv6_only_sock(sk) ?
-ENETUNREACH : udp_sendmsg(sk, msg, len);
msg->msg_name = sin6;
msg->msg_namelen = addr_len;
return err;
}
}
/* Rough check on arithmetic overflow,
better check is made in ip6_append_data().
*/
if (len > INT_MAX - sizeof(struct udphdr))
return -EMSGSIZE;
getfrag = is_udplite ? udplite_getfrag : ip_generic_getfrag;
if (READ_ONCE(up->pending)) {
if (READ_ONCE(up->pending) == AF_INET)
return udp_sendmsg(sk, msg, len);
/*
* There are pending frames.
* The socket lock must be held while it's corked.
*/
lock_sock(sk);
if (likely(up->pending)) {
if (unlikely(up->pending != AF_INET6)) {
release_sock(sk);
return -EAFNOSUPPORT;
}
dst = NULL;
goto do_append_data;
}
release_sock(sk);
}
ulen += sizeof(struct udphdr);
memset(fl6, 0, sizeof(*fl6));
if (sin6) {
if (sin6->sin6_port == 0)
return -EINVAL;
fl6->fl6_dport = sin6->sin6_port;
daddr = &sin6->sin6_addr;
if (inet6_test_bit(SNDFLOW, sk)) {
fl6->flowlabel = sin6->sin6_flowinfo&IPV6_FLOWINFO_MASK;
if (fl6->flowlabel & IPV6_FLOWLABEL_MASK) {
flowlabel = fl6_sock_lookup(sk, fl6->flowlabel);
if (IS_ERR(flowlabel))
return -EINVAL;
}
}
/*
* Otherwise it will be difficult to maintain
* sk->sk_dst_cache.
*/
if (sk->sk_state == TCP_ESTABLISHED &&
ipv6_addr_equal(daddr, &sk->sk_v6_daddr))
daddr = &sk->sk_v6_daddr;
if (addr_len >= sizeof(struct sockaddr_in6) &&
sin6->sin6_scope_id &&
__ipv6_addr_needs_scope_id(__ipv6_addr_type(daddr)))
fl6->flowi6_oif = sin6->sin6_scope_id;
} else {
if (sk->sk_state != TCP_ESTABLISHED)
return -EDESTADDRREQ;
fl6->fl6_dport = inet->inet_dport;
daddr = &sk->sk_v6_daddr;
fl6->flowlabel = np->flow_label;
connected = true;
}
trace_android_vh_udp_v6_connect(sk, sin6);
if (!fl6->flowi6_oif)
fl6->flowi6_oif = READ_ONCE(sk->sk_bound_dev_if);
if (!fl6->flowi6_oif)
fl6->flowi6_oif = np->sticky_pktinfo.ipi6_ifindex;
fl6->flowi6_uid = sk->sk_uid;
if (msg->msg_controllen) {
opt = &opt_space;
memset(opt, 0, sizeof(struct ipv6_txoptions));
opt->tot_len = sizeof(*opt);
ipc6.opt = opt;
err = udp_cmsg_send(sk, msg, &ipc6.gso_size);
if (err > 0) {
err = ip6_datagram_send_ctl(sock_net(sk), sk, msg, fl6,
&ipc6);
connected = false;
}
if (err < 0) {
fl6_sock_release(flowlabel);
return err;
}
if ((fl6->flowlabel&IPV6_FLOWLABEL_MASK) && !flowlabel) {
flowlabel = fl6_sock_lookup(sk, fl6->flowlabel);
if (IS_ERR(flowlabel))
return -EINVAL;
}
if (!(opt->opt_nflen|opt->opt_flen))
opt = NULL;
}
if (!opt) {
opt = txopt_get(np);
opt_to_free = opt;
}
if (flowlabel)
opt = fl6_merge_options(&opt_space, flowlabel, opt);
opt = ipv6_fixup_options(&opt_space, opt);
ipc6.opt = opt;
fl6->flowi6_proto = sk->sk_protocol;
fl6->flowi6_mark = ipc6.sockc.mark;
fl6->daddr = *daddr;
if (ipv6_addr_any(&fl6->saddr) && !ipv6_addr_any(&np->saddr))
fl6->saddr = np->saddr;
fl6->fl6_sport = inet->inet_sport;
if (cgroup_bpf_enabled(CGROUP_UDP6_SENDMSG) && !connected) {
err = BPF_CGROUP_RUN_PROG_UDP6_SENDMSG_LOCK(sk,
(struct sockaddr *)sin6,
&addr_len,
&fl6->saddr);
if (err)
goto out_no_dst;
if (sin6) {
if (ipv6_addr_v4mapped(&sin6->sin6_addr)) {
/* BPF program rewrote IPv6-only by IPv4-mapped
* IPv6. It's currently unsupported.
*/
err = -ENOTSUPP;
goto out_no_dst;
}
if (sin6->sin6_port == 0) {
/* BPF program set invalid port. Reject it. */
err = -EINVAL;
goto out_no_dst;
}
fl6->fl6_dport = sin6->sin6_port;
fl6->daddr = sin6->sin6_addr;
}
}
if (ipv6_addr_any(&fl6->daddr))
fl6->daddr.s6_addr[15] = 0x1; /* :: means loopback (BSD'ism) */
final_p = fl6_update_dst(fl6, opt, &final);
if (final_p)
connected = false;
if (!fl6->flowi6_oif && ipv6_addr_is_multicast(&fl6->daddr)) {
fl6->flowi6_oif = READ_ONCE(np->mcast_oif);
connected = false;
} else if (!fl6->flowi6_oif)
fl6->flowi6_oif = READ_ONCE(np->ucast_oif);
security_sk_classify_flow(sk, flowi6_to_flowi_common(fl6));
fl6->flowlabel = ip6_make_flowinfo(ipc6.tclass, fl6->flowlabel);
dst = ip6_sk_dst_lookup_flow(sk, fl6, final_p, connected);
if (IS_ERR(dst)) {
err = PTR_ERR(dst);
dst = NULL;
goto out;
}
if (ipc6.hlimit < 0)
ipc6.hlimit = ip6_sk_dst_hoplimit(np, fl6, dst);
if (msg->msg_flags&MSG_CONFIRM)
goto do_confirm;
back_from_confirm:
/* Lockless fast path for the non-corking case */
if (!corkreq) {
struct sk_buff *skb;
skb = ip6_make_skb(sk, getfrag, msg, ulen,
sizeof(struct udphdr), &ipc6,
dst_rt6_info(dst),
msg->msg_flags, &cork);
err = PTR_ERR(skb);
if (!IS_ERR_OR_NULL(skb))
err = udp_v6_send_skb(skb, fl6, &cork.base);
/* ip6_make_skb steals dst reference */
goto out_no_dst;
}
lock_sock(sk);
if (unlikely(up->pending)) {
/* The socket is already corked while preparing it. */
/* ... which is an evident application bug. --ANK */
release_sock(sk);
net_dbg_ratelimited("udp cork app bug 2\n");
err = -EINVAL;
goto out;
}
WRITE_ONCE(up->pending, AF_INET6);
do_append_data:
up->len += ulen;
err = ip6_append_data(sk, getfrag, msg, ulen, sizeof(struct udphdr),
&ipc6, fl6, dst_rt6_info(dst),
corkreq ? msg->msg_flags|MSG_MORE : msg->msg_flags);
if (err)
udp_v6_flush_pending_frames(sk);
else if (!corkreq)
err = udp_v6_push_pending_frames(sk);
else if (unlikely(skb_queue_empty(&sk->sk_write_queue)))
WRITE_ONCE(up->pending, 0);
if (err > 0)
err = inet6_test_bit(RECVERR6, sk) ? net_xmit_errno(err) : 0;
release_sock(sk);
out:
dst_release(dst);
out_no_dst:
fl6_sock_release(flowlabel);
txopt_put(opt_to_free);
if (!err)
return len;
/*
* ENOBUFS = no kernel mem, SOCK_NOSPACE = no sndbuf space. Reporting
* ENOBUFS might not be good (it's not tunable per se), but otherwise
* we don't have a good statistic (IpOutDiscards but it can be too many
* things). We could add another new stat but at least for now that
* seems like overkill.
*/
if (err == -ENOBUFS || test_bit(SOCK_NOSPACE, &sk->sk_socket->flags)) {
UDP6_INC_STATS(sock_net(sk),
UDP_MIB_SNDBUFERRORS, is_udplite);
}
return err;
do_confirm:
if (msg->msg_flags & MSG_PROBE)
dst_confirm_neigh(dst, &fl6->daddr);
if (!(msg->msg_flags&MSG_PROBE) || len)
goto back_from_confirm;
err = 0;
goto out;
}
EXPORT_SYMBOL(udpv6_sendmsg);
static void udpv6_splice_eof(struct socket *sock)
{
struct sock *sk = sock->sk;
struct udp_sock *up = udp_sk(sk);
if (!READ_ONCE(up->pending) || udp_test_bit(CORK, sk))
return;
lock_sock(sk);
if (up->pending && !udp_test_bit(CORK, sk))
udp_v6_push_pending_frames(sk);
release_sock(sk);
}
void udpv6_destroy_sock(struct sock *sk)
{
struct udp_sock *up = udp_sk(sk);
lock_sock(sk);
/* protects from races with udp_abort() */
sock_set_flag(sk, SOCK_DEAD);
udp_v6_flush_pending_frames(sk);
release_sock(sk);
if (static_branch_unlikely(&udpv6_encap_needed_key)) {
if (up->encap_type) {
void (*encap_destroy)(struct sock *sk);
encap_destroy = READ_ONCE(up->encap_destroy);
if (encap_destroy)
encap_destroy(sk);
}
if (udp_test_bit(ENCAP_ENABLED, sk)) {
static_branch_dec(&udpv6_encap_needed_key);
udp_encap_disable();
}
}
}
/*
* Socket option code for UDP
*/
int udpv6_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval,
unsigned int optlen)
{
if (level == SOL_UDP || level == SOL_UDPLITE || level == SOL_SOCKET)
return udp_lib_setsockopt(sk, level, optname,
optval, optlen,
udp_v6_push_pending_frames);
return ipv6_setsockopt(sk, level, optname, optval, optlen);
}
int udpv6_getsockopt(struct sock *sk, int level, int optname,
char __user *optval, int __user *optlen)
{
if (level == SOL_UDP || level == SOL_UDPLITE)
return udp_lib_getsockopt(sk, level, optname, optval, optlen);
return ipv6_getsockopt(sk, level, optname, optval, optlen);
}
/* ------------------------------------------------------------------------ */
#ifdef CONFIG_PROC_FS
int udp6_seq_show(struct seq_file *seq, void *v)
{
if (v == SEQ_START_TOKEN) {
seq_puts(seq, IPV6_SEQ_DGRAM_HEADER);
} else {
int bucket = ((struct udp_iter_state *)seq->private)->bucket;
const struct inet_sock *inet = inet_sk((const struct sock *)v);
__u16 srcp = ntohs(inet->inet_sport);
__u16 destp = ntohs(inet->inet_dport);
__ip6_dgram_sock_seq_show(seq, v, srcp, destp,
udp_rqueue_get(v), bucket);
}
return 0;
}
const struct seq_operations udp6_seq_ops = {
.start = udp_seq_start,
.next = udp_seq_next,
.stop = udp_seq_stop,
.show = udp6_seq_show,
};
EXPORT_SYMBOL(udp6_seq_ops);
static struct udp_seq_afinfo udp6_seq_afinfo = {
.family = AF_INET6,
.udp_table = NULL,
};
int __net_init udp6_proc_init(struct net *net)
{
if (!proc_create_net_data("udp6", 0444, net->proc_net, &udp6_seq_ops,
sizeof(struct udp_iter_state), &udp6_seq_afinfo))
return -ENOMEM;
return 0;
}
void udp6_proc_exit(struct net *net)
{
remove_proc_entry("udp6", net->proc_net);
}
#endif /* CONFIG_PROC_FS */
/* ------------------------------------------------------------------------ */
struct proto udpv6_prot = {
.name = "UDPv6",
.owner = THIS_MODULE,
.close = udp_lib_close,
.pre_connect = udpv6_pre_connect,
.connect = ip6_datagram_connect,
.disconnect = udp_disconnect,
.ioctl = udp_ioctl,
.init = udpv6_init_sock,
.destroy = udpv6_destroy_sock,
.setsockopt = udpv6_setsockopt,
.getsockopt = udpv6_getsockopt,
.sendmsg = udpv6_sendmsg,
.recvmsg = udpv6_recvmsg,
.splice_eof = udpv6_splice_eof,
.release_cb = ip6_datagram_release_cb,
.hash = udp_lib_hash,
.unhash = udp_lib_unhash,
.rehash = udp_v6_rehash,
.get_port = udp_v6_get_port,
.put_port = udp_lib_unhash,
#ifdef CONFIG_BPF_SYSCALL
.psock_update_sk_prot = udp_bpf_update_proto,
#endif
.memory_allocated = &udp_memory_allocated,
.per_cpu_fw_alloc = &udp_memory_per_cpu_fw_alloc,
.sysctl_mem = sysctl_udp_mem,
.sysctl_wmem_offset = offsetof(struct net, ipv4.sysctl_udp_wmem_min),
.sysctl_rmem_offset = offsetof(struct net, ipv4.sysctl_udp_rmem_min),
.obj_size = sizeof(struct udp6_sock),
.ipv6_pinfo_offset = offsetof(struct udp6_sock, inet6),
.h.udp_table = NULL,
.diag_destroy = udp_abort,
};
static struct inet_protosw udpv6_protosw = {
.type = SOCK_DGRAM,
.protocol = IPPROTO_UDP,
.prot = &udpv6_prot,
.ops = &inet6_dgram_ops,
.flags = INET_PROTOSW_PERMANENT,
};
int __init udpv6_init(void)
{
int ret;
net_hotdata.udpv6_protocol = (struct inet6_protocol) {
.handler = udpv6_rcv,
.err_handler = udpv6_err,
.flags = INET6_PROTO_NOPOLICY | INET6_PROTO_FINAL,
};
ret = inet6_add_protocol(&net_hotdata.udpv6_protocol, IPPROTO_UDP);
if (ret)
goto out;
ret = inet6_register_protosw(&udpv6_protosw);
if (ret)
goto out_udpv6_protocol;
out:
return ret;
out_udpv6_protocol:
inet6_del_protocol(&net_hotdata.udpv6_protocol, IPPROTO_UDP);
goto out;
}
void udpv6_exit(void)
{
inet6_unregister_protosw(&udpv6_protosw);
inet6_del_protocol(&net_hotdata.udpv6_protocol, IPPROTO_UDP);
}