68fdd20442
-----BEGIN PGP SIGNATURE----- iQIzBAABCAAdFiEEZH8oZUiU471FcZm+ONu9yGCSaT4FAmPHzUQACgkQONu9yGCS aT7QohAAtxV33qGSKGUdKMZk1JzIYuc8tAa+CHZhTi6xjTsoy1a5MlQGrj8a9YQ7 /5VvwslGSn29h/ThO/ai04CfeOsWugMtnuo4mT4+198DgH0CNQMlfWq2c25cCvY6 dIrrMTA7B2YhpdbjM4vkX8QIAxBVCHOVkseSammhMnujP7d+k4LtC6rRV4uiF+lD cKtsIJn8h+pezBeo5+pjvcTwndaAoApVOES4uOjJcf9pYOOoHxyi+8StpiO+j2Pv sRvkbvvmpS+IWAH+DMa3SAFI3C3AihX2Fu0rIFzUZByAviB1NmyWluX5mU54wW3R P80fl0rQFwuygEBU1UqTXe4hQ8YYwpJGAQzbLR22a11IT2MSO+vMRINdqG1un2BE T9hHix5R0JMeIN9AP7nKGBLrEZ3V6DqxEBz6ZC1sOUIIVQv93twtiwb0rNM0e7pq PpkIXpwXPIgqFDGXrd0y5ksRT08jJUKCRttuRVWkcGX8adotngWnrl0WBI5zqSuo B+x8X9Dw7YblJ6yQ+8mAZGk0Mj3j+cb4uhuRaz/6rqHmFOrbHm+JDXvPzZY65xy3 k8Ebtq5CxINLDwahfb/o13MgbmzMPPNPPp0cz23zOhm88OmwVzB4hAoB/1CfHZvF XhSbZMVBhhP9hYr2gYl902EQeZGE5yjk5xhFT5Wrh7QoZaPW2XM= =as6n -----END PGP SIGNATURE----- Merge 5.4.229 into android11-5.4-lts Changes in 5.4.229 tracing/ring-buffer: Only do full wait when cpu != RING_BUFFER_ALL_CPUS udf: Discard preallocation before extending file with a hole udf: Fix preallocation discarding at indirect extent boundary udf: Do not bother looking for prealloc extents if i_lenExtents matches i_size udf: Fix extending file within last block usb: gadget: uvc: Prevent buffer overflow in setup handler USB: serial: option: add Quectel EM05-G modem USB: serial: cp210x: add Kamstrup RF sniffer PIDs USB: serial: f81232: fix division by zero on line-speed change USB: serial: f81534: fix division by zero on line-speed change igb: Initialize mailbox message for VF reset xen-netback: move removal of "hotplug-status" to the right place HID: ite: Add support for Acer S1002 keyboard-dock HID: ite: Enable QUIRK_TOUCHPAD_ON_OFF_REPORT on Acer Aspire Switch 10E HID: ite: Enable QUIRK_TOUCHPAD_ON_OFF_REPORT on Acer Aspire Switch V 10 HID: uclogic: Add HID_QUIRK_HIDINPUT_FORCE quirk Bluetooth: L2CAP: Fix u8 overflow net: loopback: use NET_NAME_PREDICTABLE for name_assign_type usb: musb: remove extra check in musb_gadget_vbus_draw ARM: dts: qcom: apq8064: fix coresight compatible arm64: dts: qcom: sdm845-cheza: fix AP suspend pin bias drivers: soc: ti: knav_qmss_queue: Mark knav_acc_firmwares as static arm: dts: spear600: Fix clcd interrupt soc: ti: knav_qmss_queue: Use pm_runtime_resume_and_get instead of pm_runtime_get_sync soc: ti: knav_qmss_queue: Fix PM disable depth imbalance in knav_queue_probe soc: ti: smartreflex: Fix PM disable depth imbalance in omap_sr_probe perf: arm_dsu: Fix hotplug callback leak in dsu_pmu_init() perf/smmuv3: Fix hotplug callback leak in arm_smmu_pmu_init() arm64: dts: mt2712e: Fix unit_address_vs_reg warning for oscillators arm64: dts: mt2712e: Fix unit address for pinctrl node arm64: dts: mt2712-evb: Fix vproc fixed regulators unit names arm64: dts: mt2712-evb: Fix usb vbus regulators unit names arm64: dts: mediatek: mt6797: Fix 26M oscillator unit name ARM: dts: dove: Fix assigned-addresses for every PCIe Root Port ARM: dts: armada-370: Fix assigned-addresses for every PCIe Root Port ARM: dts: armada-xp: Fix assigned-addresses for every PCIe Root Port ARM: dts: armada-375: Fix assigned-addresses for every PCIe Root Port ARM: dts: armada-38x: Fix assigned-addresses for every PCIe Root Port ARM: dts: armada-39x: Fix assigned-addresses for every PCIe Root Port ARM: dts: turris-omnia: Add ethernet aliases ARM: dts: turris-omnia: Add switch port 6 node arm64: dts: armada-3720-turris-mox: Add missing interrupt for RTC pstore/ram: Fix error return code in ramoops_probe() ARM: mmp: fix timer_read delay pstore: Avoid kcore oops by vmap()ing with VM_IOREMAP tpm/tpm_crb: Fix error message in __crb_relinquish_locality() cpuidle: dt: Return the correct numbers of parsed idle states alpha: fix syscall entry in !AUDUT_SYSCALL case PM: hibernate: Fix mistake in kerneldoc comment fs: don't audit the capability check in simple_xattr_list() selftests/ftrace: event_triggers: wait longer for test_event_enable perf: Fix possible memleak in pmu_dev_alloc() timerqueue: Use rb_entry_safe() in timerqueue_getnext() proc: fixup uptime selftest lib/fonts: fix undefined behavior in bit shift for get_default_font ocfs2: fix memory leak in ocfs2_stack_glue_init() MIPS: vpe-mt: fix possible memory leak while module exiting MIPS: vpe-cmp: fix possible memory leak while module exiting selftests/efivarfs: Add checking of the test return value PNP: fix name memory leak in pnp_alloc_dev() perf/x86/intel/uncore: Fix reference count leak in hswep_has_limit_sbox() irqchip: gic-pm: Use pm_runtime_resume_and_get() in gic_probe() EDAC/i10nm: fix refcount leak in pci_get_dev_wrapper() nfsd: don't call nfsd_file_put from client states seqfile display genirq/irqdesc: Don't try to remove non-existing sysfs files cpufreq: amd_freq_sensitivity: Add missing pci_dev_put() libfs: add DEFINE_SIMPLE_ATTRIBUTE_SIGNED for signed value lib/notifier-error-inject: fix error when writing -errno to debugfs file docs: fault-injection: fix non-working usage of negative values debugfs: fix error when writing negative value to atomic_t debugfs file ocfs2: ocfs2_mount_volume does cleanup job before return error ocfs2: rewrite error handling of ocfs2_fill_super ocfs2: fix memory leak in ocfs2_mount_volume() rapidio: fix possible name leaks when rio_add_device() fails rapidio: rio: fix possible name leak in rio_register_mport() clocksource/drivers/sh_cmt: Make sure channel clock supply is enabled ACPICA: Fix use-after-free in acpi_ut_copy_ipackage_to_ipackage() uprobes/x86: Allow to probe a NOP instruction with 0x66 prefix xen/events: only register debug interrupt for 2-level events x86/xen: Fix memory leak in xen_smp_intr_init{_pv}() x86/xen: Fix memory leak in xen_init_lock_cpu() xen/privcmd: Fix a possible warning in privcmd_ioctl_mmap_resource() PM: runtime: Improve path in rpm_idle() when no callback PM: runtime: Do not call __rpm_callback() from rpm_idle() platform/x86: mxm-wmi: fix memleak in mxm_wmi_call_mx[ds|mx]() MIPS: BCM63xx: Add check for NULL for clk in clk_enable MIPS: OCTEON: warn only once if deprecated link status is being used fs: sysv: Fix sysv_nblocks() returns wrong value rapidio: fix possible UAF when kfifo_alloc() fails eventfd: change int to __u64 in eventfd_signal() ifndef CONFIG_EVENTFD relay: fix type mismatch when allocating memory in relay_create_buf() hfs: Fix OOB Write in hfs_asc2mac rapidio: devices: fix missing put_device in mport_cdev_open wifi: ath9k: hif_usb: fix memory leak of urbs in ath9k_hif_usb_dealloc_tx_urbs() wifi: ath9k: hif_usb: Fix use-after-free in ath9k_hif_usb_reg_in_cb() wifi: rtl8xxxu: Fix reading the vendor of combo chips pata_ipx4xx_cf: Fix unsigned comparison with less than zero media: i2c: ad5820: Fix error path can: kvaser_usb: do not increase tx statistics when sending error message frames can: kvaser_usb: kvaser_usb_leaf: Get capabilities from device can: kvaser_usb: kvaser_usb_leaf: Rename {leaf,usbcan}_cmd_error_event to {leaf,usbcan}_cmd_can_error_event can: kvaser_usb: kvaser_usb_leaf: Handle CMD_ERROR_EVENT can: kvaser_usb_leaf: Set Warning state even without bus errors can: kvaser_usb_leaf: Fix improved state not being reported can: kvaser_usb_leaf: Fix wrong CAN state after stopping can: kvaser_usb_leaf: Fix bogus restart events can: kvaser_usb: Add struct kvaser_usb_busparams can: kvaser_usb: Compare requested bittiming parameters with actual parameters in do_set_{,data}_bittiming clk: renesas: r9a06g032: Repair grave increment error spi: Update reference to struct spi_controller drm/panel/panel-sitronix-st7701: Remove panel on DSI attach failure ima: Rename internal filter rule functions ima: Fix fall-through warnings for Clang ima: Handle -ESTALE returned by ima_filter_rule_match() media: vivid: fix compose size exceed boundary bpf: propagate precision in ALU/ALU64 operations mtd: Fix device name leak when register device failed in add_mtd_device() wifi: rsi: Fix handling of 802.3 EAPOL frames sent via control port media: camss: Clean up received buffers on failed start of streaming net, proc: Provide PROC_FS=n fallback for proc_create_net_single_write() rxrpc: Fix ack.bufferSize to be 0 when generating an ack drm/radeon: Add the missed acpi_put_table() to fix memory leak drm/mediatek: Modify dpi power on/off sequence. ASoC: pxa: fix null-pointer dereference in filter() regulator: core: fix unbalanced of node refcount in regulator_dev_lookup() amdgpu/pm: prevent array underflow in vega20_odn_edit_dpm_table() integrity: Fix memory leakage in keyring allocation error path ima: Fix misuse of dereference of pointer in template_desc_init_fields() wifi: ath10k: Fix return value in ath10k_pci_init() mtd: lpddr2_nvm: Fix possible null-ptr-deref Input: elants_i2c - properly handle the reset GPIO when power is off media: solo6x10: fix possible memory leak in solo_sysfs_init() media: platform: exynos4-is: Fix error handling in fimc_md_init() media: videobuf-dma-contig: use dma_mmap_coherent bpf: Move skb->len == 0 checks into __bpf_redirect HID: hid-sensor-custom: set fixed size for custom attributes ALSA: pcm: fix undefined behavior in bit shift for SNDRV_PCM_RATE_KNOT ALSA: seq: fix undefined behavior in bit shift for SNDRV_SEQ_FILTER_USE_EVENT regulator: core: use kfree_const() to free space conditionally clk: rockchip: Fix memory leak in rockchip_clk_register_pll() bonding: Export skip slave logic to function bonding: Rename slave_arr to usable_slaves bonding: fix link recovery in mode 2 when updelay is nonzero mtd: maps: pxa2xx-flash: fix memory leak in probe media: imon: fix a race condition in send_packet() clk: imx8mn: correct the usb1_ctrl parent to be usb_bus clk: imx: replace osc_hdmi with dummy pinctrl: pinconf-generic: add missing of_node_put() media: dvb-core: Fix ignored return value in dvb_register_frontend() media: dvb-usb: az6027: fix null-ptr-deref in az6027_i2c_xfer() media: s5p-mfc: Add variant data for MFC v7 hardware for Exynos 3250 SoC drm/tegra: Add missing clk_disable_unprepare() in tegra_dc_probe() ASoC: dt-bindings: wcd9335: fix reset line polarity in example ASoC: mediatek: mtk-btcvsd: Add checks for write and read of mtk_btcvsd_snd NFSv4.2: Clear FATTR4_WORD2_SECURITY_LABEL when done decoding NFSv4.2: Fix a memory stomp in decode_attr_security_label NFSv4.2: Fix initialisation of struct nfs4_label NFSv4: Fix a deadlock between nfs4_open_recover_helper() and delegreturn ALSA: asihpi: fix missing pci_disable_device() wifi: iwlwifi: mvm: fix double free on tx path. ASoC: mediatek: mt8173: Enable IRQ when pdata is ready drm/radeon: Fix PCI device refcount leak in radeon_atrm_get_bios() drm/amdgpu: Fix PCI device refcount leak in amdgpu_atrm_get_bios() ASoC: pcm512x: Fix PM disable depth imbalance in pcm512x_probe netfilter: conntrack: set icmpv6 redirects as RELATED bpf, sockmap: Fix repeated calls to sock_put() when msg has more_data bpf, sockmap: Fix data loss caused by using apply_bytes on ingress redirect bonding: uninitialized variable in bond_miimon_inspect() spi: spidev: mask SPI_CS_HIGH in SPI_IOC_RD_MODE wifi: cfg80211: Fix not unregister reg_pdev when load_builtin_regdb_keys() fails regulator: core: fix module refcount leak in set_supply() clk: qcom: clk-krait: fix wrong div2 functions hsr: Avoid double remove of a node. configfs: fix possible memory leak in configfs_create_dir() regulator: core: fix resource leak in regulator_register() bpf, sockmap: fix race in sock_map_free() media: saa7164: fix missing pci_disable_device() ALSA: mts64: fix possible null-ptr-defer in snd_mts64_interrupt xprtrdma: Fix regbuf data not freed in rpcrdma_req_create() SUNRPC: Fix missing release socket in rpc_sockname() NFSv4.x: Fail client initialisation if state manager thread can't run mmc: alcor: fix return value check of mmc_add_host() mmc: moxart: fix return value check of mmc_add_host() mmc: mxcmmc: fix return value check of mmc_add_host() mmc: pxamci: fix return value check of mmc_add_host() mmc: rtsx_usb_sdmmc: fix return value check of mmc_add_host() mmc: toshsd: fix return value check of mmc_add_host() mmc: vub300: fix return value check of mmc_add_host() mmc: wmt-sdmmc: fix return value check of mmc_add_host() mmc: atmel-mci: fix return value check of mmc_add_host() mmc: omap_hsmmc: fix return value check of mmc_add_host() mmc: meson-gx: fix return value check of mmc_add_host() mmc: via-sdmmc: fix return value check of mmc_add_host() mmc: wbsd: fix return value check of mmc_add_host() mmc: mmci: fix return value check of mmc_add_host() media: c8sectpfe: Add of_node_put() when breaking out of loop media: coda: Add check for dcoda_iram_alloc media: coda: Add check for kmalloc clk: samsung: Fix memory leak in _samsung_clk_register_pll() spi: spi-gpio: Don't set MOSI as an input if not 3WIRE mode wifi: rtl8xxxu: Add __packed to struct rtl8723bu_c2h wifi: brcmfmac: Fix error return code in brcmf_sdio_download_firmware() blktrace: Fix output non-blktrace event when blk_classic option enabled clk: socfpga: clk-pll: Remove unused variable 'rc' clk: socfpga: use clk_hw_register for a5/c5 clk: socfpga: Fix memory leak in socfpga_gate_init() net: vmw_vsock: vmci: Check memcpy_from_msg() net: defxx: Fix missing err handling in dfx_init() net: stmmac: selftests: fix potential memleak in stmmac_test_arpoffload() drivers: net: qlcnic: Fix potential memory leak in qlcnic_sriov_init() of: overlay: fix null pointer dereferencing in find_dup_cset_node_entry() and find_dup_cset_prop() ethernet: s2io: don't call dev_kfree_skb() under spin_lock_irqsave() net: farsync: Fix kmemleak when rmmods farsync net/tunnel: wait until all sk_user_data reader finish before releasing the sock net: apple: mace: don't call dev_kfree_skb() under spin_lock_irqsave() net: apple: bmac: don't call dev_kfree_skb() under spin_lock_irqsave() net: emaclite: don't call dev_kfree_skb() under spin_lock_irqsave() net: ethernet: dnet: don't call dev_kfree_skb() under spin_lock_irqsave() hamradio: don't call dev_kfree_skb() under spin_lock_irqsave() net: amd: lance: don't call dev_kfree_skb() under spin_lock_irqsave() net: amd-xgbe: Fix logic around active and passive cables net: amd-xgbe: Check only the minimum speed for active/passive cables can: tcan4x5x: Remove invalid write in clear_interrupts net: lan9303: Fix read error execution path ntb_netdev: Use dev_kfree_skb_any() in interrupt context Bluetooth: btusb: don't call kfree_skb() under spin_lock_irqsave() Bluetooth: hci_qca: don't call kfree_skb() under spin_lock_irqsave() Bluetooth: hci_ll: don't call kfree_skb() under spin_lock_irqsave() Bluetooth: hci_h5: don't call kfree_skb() under spin_lock_irqsave() Bluetooth: hci_bcsp: don't call kfree_skb() under spin_lock_irqsave() Bluetooth: hci_core: don't call kfree_skb() under spin_lock_irqsave() Bluetooth: RFCOMM: don't call kfree_skb() under spin_lock_irqsave() stmmac: fix potential division by 0 apparmor: fix a memleak in multi_transaction_new() apparmor: fix lockdep warning when removing a namespace apparmor: Fix abi check to include v8 abi apparmor: Use pointer to struct aa_label for lbs_cred RDMA/core: Fix order of nldev_exit call f2fs: fix normal discard process RDMA/siw: Fix immediate work request flush to completion queue RDMA/nldev: Return "-EAGAIN" if the cm_id isn't from expected port RDMA/siw: Set defined status for work completion with undefined status scsi: scsi_debug: Fix a warning in resp_write_scat() crypto: ccree - swap SHA384 and SHA512 larval hashes at build time crypto: ccree - Remove debugfs when platform_driver_register failed PCI: Check for alloc failure in pci_request_irq() RDMA/hfi: Decrease PCI device reference count in error path crypto: ccree - Make cc_debugfs_global_fini() available for module init function RDMA/rxe: Fix NULL-ptr-deref in rxe_qp_do_cleanup() when socket create failed scsi: hpsa: Fix possible memory leak in hpsa_init_one() crypto: tcrypt - Fix multibuffer skcipher speed test mem leak scsi: mpt3sas: Fix possible resource leaks in mpt3sas_transport_port_add() scsi: hpsa: Fix error handling in hpsa_add_sas_host() scsi: hpsa: Fix possible memory leak in hpsa_add_sas_device() scsi: fcoe: Fix possible name leak when device_register() fails scsi: ipr: Fix WARNING in ipr_init() scsi: fcoe: Fix transport not deattached when fcoe_if_init() fails scsi: snic: Fix possible UAF in snic_tgt_create() RDMA/nldev: Add checks for nla_nest_start() in fill_stat_counter_qps() f2fs: avoid victim selection from previous victim section crypto: omap-sham - Use pm_runtime_resume_and_get() in omap_sham_probe() RDMA/hfi1: Fix error return code in parse_platform_config() orangefs: Fix sysfs not cleanup when dev init failed crypto: img-hash - Fix variable dereferenced before check 'hdev->req' hwrng: amd - Fix PCI device refcount leak hwrng: geode - Fix PCI device refcount leak IB/IPoIB: Fix queue count inconsistency for PKEY child interfaces drivers: dio: fix possible memory leak in dio_init() tty: serial: tegra: Activate RX DMA transfer by request serial: tegra: Read DMA status before terminating class: fix possible memory leak in __class_register() vfio: platform: Do not pass return buffer to ACPI _RST method uio: uio_dmem_genirq: Fix missing unlock in irq configuration uio: uio_dmem_genirq: Fix deadlock between irq config and handling usb: fotg210-udc: Fix ages old endianness issues staging: vme_user: Fix possible UAF in tsi148_dma_list_add usb: typec: Check for ops->exit instead of ops->enter in altmode_exit usb: typec: tcpci: fix of node refcount leak in tcpci_register_port() serial: amba-pl011: avoid SBSA UART accessing DMACR register serial: pl011: Do not clear RX FIFO & RX interrupt in unthrottle. serial: pch: Fix PCI device refcount leak in pch_request_dma() tty: serial: clean up stop-tx part in altera_uart_tx_chars() tty: serial: altera_uart_{r,t}x_chars() need only uart_port serial: altera_uart: fix locking in polling mode serial: sunsab: Fix error handling in sunsab_init() test_firmware: fix memory leak in test_firmware_init() misc: ocxl: fix possible name leak in ocxl_file_register_afu() misc: tifm: fix possible memory leak in tifm_7xx1_switch_media() misc: sgi-gru: fix use-after-free error in gru_set_context_option, gru_fault and gru_handle_user_call_os cxl: fix possible null-ptr-deref in cxl_guest_init_afu|adapter() cxl: fix possible null-ptr-deref in cxl_pci_init_afu|adapter() counter: stm32-lptimer-cnt: fix the check on arr and cmp registers update usb: roles: fix of node refcount leak in usb_role_switch_is_parent() usb: gadget: f_hid: optional SETUP/SET_REPORT mode usb: gadget: f_hid: fix f_hidg lifetime vs cdev usb: gadget: f_hid: fix refcount leak on error path drivers: mcb: fix resource leak in mcb_probe() mcb: mcb-parse: fix error handing in chameleon_parse_gdd() chardev: fix error handling in cdev_device_add() i2c: pxa-pci: fix missing pci_disable_device() on error in ce4100_i2c_probe staging: rtl8192u: Fix use after free in ieee80211_rx() staging: rtl8192e: Fix potential use-after-free in rtllib_rx_Monitor() vme: Fix error not catched in fake_init() i2c: ismt: Fix an out-of-bounds bug in ismt_access() usb: storage: Add check for kcalloc tracing/hist: Fix issue of losting command info in error_log samples: vfio-mdev: Fix missing pci_disable_device() in mdpy_fb_probe() fbdev: ssd1307fb: Drop optional dependency fbdev: pm2fb: fix missing pci_disable_device() fbdev: via: Fix error in via_core_init() fbdev: vermilion: decrease reference count in error path fbdev: uvesafb: Fixes an error handling path in uvesafb_probe() HSI: omap_ssi_core: fix unbalanced pm_runtime_disable() HSI: omap_ssi_core: fix possible memory leak in ssi_probe() power: supply: fix residue sysfs file in error handle route of __power_supply_register() perf trace: Return error if a system call doesn't exist perf trace: Separate 'struct syscall_fmt' definition from syscall_fmts variable perf trace: Factor out the initialization of syscal_arg_fmt->scnprintf perf trace: Add the syscall_arg_fmt pointer to syscall_arg perf trace: Allow associating scnprintf routines with well known arg names perf trace: Add a strtoul() method to 'struct syscall_arg_fmt' perf trace: Use macro RAW_SYSCALL_ARGS_NUM to replace number perf trace: Handle failure when trace point folder is missed perf symbol: correction while adjusting symbol HSI: omap_ssi_core: Fix error handling in ssi_init() power: supply: fix null pointer dereferencing in power_supply_get_battery_info RDMA/siw: Fix pointer cast warning include/uapi/linux/swab: Fix potentially missing __always_inline rtc: snvs: Allow a time difference on clock register read rtc: pcf85063: Fix reading alarm iommu/amd: Fix pci device refcount leak in ppr_notifier() iommu/fsl_pamu: Fix resource leak in fsl_pamu_probe() macintosh: fix possible memory leak in macio_add_one_device() macintosh/macio-adb: check the return value of ioremap() powerpc/52xx: Fix a resource leak in an error handling path cxl: Fix refcount leak in cxl_calc_capp_routing powerpc/xive: add missing iounmap() in error path in xive_spapr_populate_irq_data() powerpc/perf: callchain validate kernel stack pointer bounds powerpc/83xx/mpc832x_rdb: call platform_device_put() in error case in of_fsl_spi_probe() powerpc/hv-gpci: Fix hv_gpci event list selftests/powerpc: Fix resource leaks pwm: sifive: Call pwm_sifive_update_clock() while mutex is held remoteproc: sysmon: fix memory leak in qcom_add_sysmon_subdev() remoteproc: qcom_q6v5_pas: Fix missing of_node_put() in adsp_alloc_memory_region() rtc: st-lpc: Add missing clk_disable_unprepare in st_rtc_probe() rtc: pic32: Move devm_rtc_allocate_device earlier in pic32_rtc_probe() nfsd: Define the file access mode enum for tracing NFSD: Add tracepoints to NFSD's duplicate reply cache nfsd: under NFSv4.1, fix double svc_xprt_put on rpc_create failure mISDN: hfcsusb: don't call dev_kfree_skb/kfree_skb() under spin_lock_irqsave() mISDN: hfcpci: don't call dev_kfree_skb/kfree_skb() under spin_lock_irqsave() mISDN: hfcmulti: don't call dev_kfree_skb/kfree_skb() under spin_lock_irqsave() nfc: pn533: Clear nfc_target before being used r6040: Fix kmemleak in probe and remove rtc: mxc_v2: Add missing clk_disable_unprepare() openvswitch: Fix flow lookup to use unmasked key skbuff: Account for tail adjustment during pull operations mailbox: zynq-ipi: fix error handling while device_register() fails net_sched: reject TCF_EM_SIMPLE case for complex ematch module rxrpc: Fix missing unlock in rxrpc_do_sendmsg() myri10ge: Fix an error handling path in myri10ge_probe() net: stream: purge sk_error_queue in sk_stream_kill_queues() rcu: Fix __this_cpu_read() lockdep warning in rcu_force_quiescent_state() binfmt_misc: fix shift-out-of-bounds in check_special_flags fs: jfs: fix shift-out-of-bounds in dbAllocAG udf: Avoid double brelse() in udf_rename() fs: jfs: fix shift-out-of-bounds in dbDiscardAG ACPICA: Fix error code path in acpi_ds_call_control_method() nilfs2: fix shift-out-of-bounds/overflow in nilfs_sb2_bad_offset() acct: fix potential integer overflow in encode_comp_t() hfs: fix OOB Read in __hfs_brec_find drm/etnaviv: add missing quirks for GC300 brcmfmac: return error when getting invalid max_flowrings from dongle wifi: ath9k: verify the expected usb_endpoints are present wifi: ar5523: Fix use-after-free on ar5523_cmd() timed out ASoC: codecs: rt298: Add quirk for KBL-R RVP platform ipmi: fix memleak when unload ipmi driver bpf: make sure skb->len != 0 when redirecting to a tunneling device net: ethernet: ti: Fix return type of netcp_ndo_start_xmit() hamradio: baycom_epp: Fix return type of baycom_send_packet() wifi: brcmfmac: Fix potential shift-out-of-bounds in brcmf_fw_alloc_request() igb: Do not free q_vector unless new one was allocated s390/ctcm: Fix return type of ctc{mp,}m_tx() s390/netiucv: Fix return type of netiucv_tx() s390/lcs: Fix return type of lcs_start_xmit() drm/rockchip: Use drm_mode_copy() drm/sti: Use drm_mode_copy() drivers/md/md-bitmap: check the return value of md_bitmap_get_counter() md/raid1: stop mdx_raid1 thread when raid1 array run failed net: add atomic_long_t to net_device_stats fields mrp: introduce active flags to prevent UAF when applicant uninit ppp: associate skb with a device at tx bpf: Prevent decl_tag from being referenced in func_proto arg media: dvb-frontends: fix leak of memory fw media: dvbdev: adopts refcnt to avoid UAF media: dvb-usb: fix memory leak in dvb_usb_adapter_init() blk-mq: fix possible memleak when register 'hctx' failed regulator: core: fix use_count leakage when handling boot-on mmc: f-sdh30: Add quirks for broken timeout clock capability media: si470x: Fix use-after-free in si470x_int_in_callback() clk: st: Fix memory leak in st_of_quadfs_setup() hugetlbfs: fix null-ptr-deref in hugetlbfs_parse_param() drm/fsl-dcu: Fix return type of fsl_dcu_drm_connector_mode_valid() drm/sti: Fix return type of sti_{dvo,hda,hdmi}_connector_mode_valid() orangefs: Fix kmemleak in orangefs_prepare_debugfs_help_string() orangefs: Fix kmemleak in orangefs_{kernel,client}_debug_init() ALSA/ASoC: hda: move/rename snd_hdac_ext_stop_streams to hdac_stream.c ALSA: hda: add snd_hdac_stop_streams() helper ASoC: Intel: Skylake: Fix driver hang during shutdown ASoC: mediatek: mt8173-rt5650-rt5514: fix refcount leak in mt8173_rt5650_rt5514_dev_probe() ASoC: audio-graph-card: fix refcount leak of cpu_ep in __graph_for_each_link() ASoC: rockchip: pdm: Add missing clk_disable_unprepare() in rockchip_pdm_runtime_resume() ASoC: wm8994: Fix potential deadlock ASoC: rockchip: spdif: Add missing clk_disable_unprepare() in rk_spdif_runtime_resume() ASoC: rt5670: Remove unbalanced pm_runtime_put() pstore: Switch pmsg_lock to an rt_mutex to avoid priority inversion pstore: Make sure CONFIG_PSTORE_PMSG selects CONFIG_RT_MUTEXES ALSA: hda/realtek: Add quirk for Lenovo TianYi510Pro-14IOB ALSA: hda/hdmi: Add HP Device 0x8711 to force connect list usb: dwc3: core: defer probe on ulpi_read_id timeout HID: wacom: Ensure bootloader PID is usable in hidraw mode reiserfs: Add missing calls to reiserfs_security_free() iio: adc: ad_sigma_delta: do not use internal iio_dev lock iio: adc128s052: add proper .data members in adc128_of_match table regulator: core: fix deadlock on regulator enable gcov: add support for checksum field media: dvbdev: fix build warning due to comments media: dvbdev: fix refcnt bug cifs: fix oops during encryption nvme-pci: fix doorbell buffer value endianness ata: ahci: Fix PCS quirk application for suspend nvme: resync include/linux/nvme.h with nvmecli nvme: fix the NVME_CMD_EFFECTS_CSE_MASK definition objtool: Fix SEGFAULT powerpc/rtas: avoid device tree lookups in rtas_os_term() powerpc/rtas: avoid scheduling in rtas_os_term() HID: multitouch: fix Asus ExpertBook P2 P2451FA trackpoint HID: plantronics: Additional PIDs for double volume key presses quirk hfsplus: fix bug causing custom uid and gid being unable to be assigned with mount ovl: Use ovl mounter's fsuid and fsgid in ovl_link() ALSA: line6: correct midi status byte when receiving data from podxt ALSA: line6: fix stack overflow in line6_midi_transmit pnode: terminate at peers of source md: fix a crash in mempool_free mm, compaction: fix fast_isolate_around() to stay within boundaries f2fs: should put a page when checking the summary info mmc: vub300: fix warning - do not call blocking ops when !TASK_RUNNING tpm: tpm_crb: Add the missed acpi_put_table() to fix memory leak tpm: tpm_tis: Add the missed acpi_put_table() to fix memory leak SUNRPC: Don't leak netobj memory when gss_read_proxy_verf() fails net/af_packet: add VLAN support for AF_PACKET SOCK_RAW GSO net/af_packet: make sure to pull mac header media: stv0288: use explicitly signed char soc: qcom: Select REMAP_MMIO for LLCC driver kest.pl: Fix grub2 menu handling for rebooting ktest.pl minconfig: Unset configs instead of just removing them mmc: sdhci-sprd: Disable CLK_AUTO when the clock is less than 400K btrfs: fix resolving backrefs for inline extent followed by prealloc ARM: ux500: do not directly dereference __iomem arm64: dts: qcom: sdm850-lenovo-yoga-c630: correct I2C12 pins drive strength selftests: Use optional USERCFLAGS and USERLDFLAGS cpufreq: Init completion before kobject_init_and_add() binfmt: Move install_exec_creds after setup_new_exec to match binfmt_elf binfmt: Fix error return code in load_elf_fdpic_binary() dm cache: Fix ABBA deadlock between shrink_slab and dm_cache_metadata_abort dm thin: Fix ABBA deadlock between shrink_slab and dm_pool_abort_metadata dm thin: Use last transaction's pmd->root when commit failed dm thin: Fix UAF in run_timer_softirq() dm integrity: Fix UAF in dm_integrity_dtr() dm clone: Fix UAF in clone_dtr() dm cache: Fix UAF in destroy() dm cache: set needs_check flag after aborting metadata tracing/hist: Fix out-of-bound write on 'action_data.var_ref_idx' x86/microcode/intel: Do not retry microcode reloading on the APs tracing/hist: Fix wrong return value in parse_action_params() tracing: Fix infinite loop in tracing_read_pipe on overflowed print_trace_line ARM: 9256/1: NWFPE: avoid compiler-generated __aeabi_uldivmod media: dvb-core: Fix double free in dvb_register_device() media: dvb-core: Fix UAF due to refcount races at releasing cifs: fix confusing debug message cifs: fix missing display of three mount options md/bitmap: Fix bitmap chunk size overflow issues efi: Add iMac Pro 2017 to uefi skip cert quirk ipmi: fix long wait in unload when IPMI disconnect mtd: spi-nor: Check for zero erase size in spi_nor_find_best_erase_type() ima: Fix a potential NULL pointer access in ima_restore_measurement_list ipmi: fix use after free in _ipmi_destroy_user() PCI: Fix pci_device_is_present() for VFs by checking PF PCI/sysfs: Fix double free in error path crypto: n2 - add missing hash statesize iommu/amd: Fix ivrs_acpihid cmdline parsing code parisc: led: Fix potential null-ptr-deref in start_task() device_cgroup: Roll back to original exceptions after copy failure drm/connector: send hotplug uevent on connector cleanup drm/vmwgfx: Validate the box size for the snooped cursor ext4: add inode table check in __ext4_get_inode_loc to aovid possible infinite loop ext4: fix undefined behavior in bit shift for ext4_check_flag_values ext4: add EXT4_IGET_BAD flag to prevent unexpected bad inode ext4: add helper to check quota inums ext4: fix reserved cluster accounting in __es_remove_extent() ext4: fix bug_on in __es_tree_search caused by bad boot loader inode ext4: init quota for 'old.inode' in 'ext4_rename' ext4: fix delayed allocation bug in ext4_clu_mapped for bigalloc + inline ext4: fix corruption when online resizing a 1K bigalloc fs ext4: fix error code return to user-space in ext4_get_branch() ext4: avoid BUG_ON when creating xattrs ext4: fix inode leak in ext4_xattr_inode_create() on an error path ext4: initialize quota before expanding inode in setproject ioctl ext4: avoid unaccounted block allocation when expanding inode ext4: allocate extended attribute value in vmalloc area btrfs: replace strncpy() with strscpy() PM/devfreq: governor: Add a private governor_data for governor media: s5p-mfc: Fix to handle reference queue during finishing media: s5p-mfc: Clear workbit to handle error condition media: s5p-mfc: Fix in register read and write for H264 dm thin: resume even if in FAIL mode perf probe: Use dwarf_attr_integrate as generic DWARF attr accessor perf probe: Fix to get the DW_AT_decl_file and DW_AT_call_file as unsinged data KVM: x86: optimize more exit handlers in vmx.c KVM: retpolines: x86: eliminate retpoline from vmx.c exit handlers KVM: VMX: Rename INTERRUPT_PENDING to INTERRUPT_WINDOW KVM: VMX: Rename NMI_PENDING to NMI_WINDOW KVM: VMX: Fix the spelling of CPU_BASED_USE_TSC_OFFSETTING KVM: nVMX: Properly expose ENABLE_USR_WAIT_PAUSE control to L1 ravb: Fix "failed to switch device to config mode" message during unbind ext4: goto right label 'failed_mount3a' ext4: correct inconsistent error msg in nojournal mode mm/highmem: Lift memcpy_[to|from]_page to core ext4: use memcpy_to_page() in pagecache_write() fs: ext4: initialize fsdata in pagecache_write() ext4: use kmemdup() to replace kmalloc + memcpy mbcache: don't reclaim used entries mbcache: add functions to delete entry if unused ext4: remove EA inode entry from mbcache on inode eviction ext4: unindent codeblock in ext4_xattr_block_set() ext4: fix race when reusing xattr blocks mbcache: automatically delete entries from cache on freeing ext4: fix deadlock due to mbcache entry corruption SUNRPC: ensure the matching upcall is in-flight upon downcall bpf: pull before calling skb_postpull_rcsum() nfsd: shut down the NFSv4 state objects before the filecache net: hns3: add interrupts re-initialization while doing VF FLR net: sched: fix memory leak in tcindex_set_parms qlcnic: prevent ->dcb use-after-free on qlcnic_dcb_enable() failure nfc: Fix potential resource leaks vhost: fix range used in translate_desc() net: amd-xgbe: add missed tasklet_kill net: phy: xgmiitorgmii: Fix refcount leak in xgmiitorgmii_probe RDMA/uverbs: Silence shiftTooManyBitsSigned warning RDMA/mlx5: Fix validation of max_rd_atomic caps for DC net: sched: atm: dont intepret cls results when asked to drop net: sched: cbq: dont intepret cls results when asked to drop perf tools: Fix resources leak in perf_data__open_dir() drivers/net/bonding/bond_3ad: return when there's no aggregator usb: rndis_host: Secure rndis_query check against int overflow drm/i915: unpin on error in intel_vgpu_shadow_mm_pin() caif: fix memory leak in cfctrl_linkup_request() udf: Fix extension of the last extent in the file ASoC: Intel: bytcr_rt5640: Add quirk for the Advantech MICA-071 tablet x86/bugs: Flush IBP in ib_prctl_set() nfsd: fix handling of readdir in v4root vs. mount upcall timeout riscv: uaccess: fix type of 0 variable on error in get_user() ext4: don't allow journal inode to have encrypt flag hfs/hfsplus: use WARN_ON for sanity check hfs/hfsplus: avoid WARN_ON() for sanity check, use proper error handling mbcache: Avoid nesting of cache->c_list_lock under bit locks parisc: Align parisc MADV_XXX constants with all other architectures selftests: Fix kselftest O=objdir build from cluttering top level objdir selftests: set the BUILD variable to absolute path driver core: Fix bus_type.match() error handling in __driver_attach() net: sched: disallow noqueue for qdisc classes KVM: arm64: Fix S1PTW handling on RO memslots efi: tpm: Avoid READ_ONCE() for accessing the event log docs: Fix the docs build with Sphinx 6.0 perf auxtrace: Fix address filter duplicate symbol selection s390/kexec: fix ipl report address for kdump s390/percpu: add READ_ONCE() to arch_this_cpu_to_op_simple() net/ulp: prevent ULP without clone op from entering the LISTEN status ALSA: pcm: Move rwsem lock inside snd_ctl_elem_read to prevent UAF ALSA: hda/hdmi: Add a HP device 0x8715 to force connect list cifs: Fix uninitialized memory read for smb311 posix symlink create drm/msm/adreno: Make adreno quirks not overwrite each other platform/x86: sony-laptop: Don't turn off 0x153 keyboard backlight during probe ixgbe: fix pci device refcount leak ipv6: raw: Deduct extension header length in rawv6_push_pending_frames wifi: wilc1000: sdio: fix module autoloading usb: ulpi: defer ulpi_register on ulpi_read_id timeout jbd2: use the correct print format quota: Factor out setup of quota inode ext4: fix bug_on in __es_tree_search caused by bad quota inode ext4: lost matching-pair of trace in ext4_truncate ext4: fix use-after-free in ext4_orphan_cleanup ext4: fix uninititialized value in 'ext4_evict_inode' netfilter: ipset: Fix overflow before widen in the bitmap_ip_create() function. powerpc/imc-pmu: Fix use of mutex in IRQs disabled section x86/boot: Avoid using Intel mnemonics in AT&T syntax asm EDAC/device: Fix period calculation in edac_device_reset_delay_period() regulator: da9211: Use irq handler when ready tipc: improve throughput between nodes in netns tipc: eliminate checking netns if node established tipc: fix unexpected link reset due to discovery messages hvc/xen: lock console list traversal nfc: pn533: Wait for out_urb's completion in pn533_usb_send_frame() net/sched: act_mpls: Fix warning during failed attribute validation net/mlx5: Rename ptp clock info net/mlx5: Fix ptp max frequency adjustment range iommu/mediatek-v1: Add error handle for mtk_iommu_probe iommu/mediatek-v1: Fix an error handling path in mtk_iommu_v1_probe() x86/resctrl: Use task_curr() instead of task_struct->on_cpu to prevent unnecessary IPI x86/resctrl: Fix task CLOSID/RMID update race drm/virtio: Fix GEM handle creation UAF arm64: atomics: format whitespace consistently arm64: atomics: remove LL/SC trampolines arm64: cmpxchg_double*: hazard against entire exchange variable efi: fix NULL-deref in init error path mm: Always release pages to the buddy allocator in memblock_free_late(). Revert "usb: ulpi: defer ulpi_register on ulpi_read_id timeout" tipc: fix use-after-free in tipc_disc_rcv() tty: serial: tegra: Handle RX transfer in PIO mode if DMA wasn't started tipc: Add a missing case of TIPC_DIRECT_MSG type ocfs2: fix freeing uninitialized resource on ocfs2_dlm_shutdown tipc: call tipc_lxc_xmit without holding node_read_lock Linux 5.4.229 Change-Id: If8e35d5d3e707352766ae3e4b665fd2369d9382b Signed-off-by: Greg Kroah-Hartman <gregkh@google.com>
2649 lines
63 KiB
C
2649 lines
63 KiB
C
// SPDX-License-Identifier: GPL-2.0-only
|
|
/* Copyright (C) 2009 Red Hat, Inc.
|
|
* Copyright (C) 2006 Rusty Russell IBM Corporation
|
|
*
|
|
* Author: Michael S. Tsirkin <mst@redhat.com>
|
|
*
|
|
* Inspiration, some code, and most witty comments come from
|
|
* Documentation/virtual/lguest/lguest.c, by Rusty Russell
|
|
*
|
|
* Generic code for virtio server in host kernel.
|
|
*/
|
|
|
|
#include <linux/eventfd.h>
|
|
#include <linux/vhost.h>
|
|
#include <linux/uio.h>
|
|
#include <linux/mm.h>
|
|
#include <linux/mmu_context.h>
|
|
#include <linux/miscdevice.h>
|
|
#include <linux/mutex.h>
|
|
#include <linux/poll.h>
|
|
#include <linux/file.h>
|
|
#include <linux/highmem.h>
|
|
#include <linux/slab.h>
|
|
#include <linux/vmalloc.h>
|
|
#include <linux/kthread.h>
|
|
#include <linux/cgroup.h>
|
|
#include <linux/module.h>
|
|
#include <linux/sort.h>
|
|
#include <linux/sched/mm.h>
|
|
#include <linux/sched/signal.h>
|
|
#include <linux/interval_tree_generic.h>
|
|
#include <linux/nospec.h>
|
|
#include <linux/kcov.h>
|
|
|
|
#include "vhost.h"
|
|
|
|
static ushort max_mem_regions = 64;
|
|
module_param(max_mem_regions, ushort, 0444);
|
|
MODULE_PARM_DESC(max_mem_regions,
|
|
"Maximum number of memory regions in memory map. (default: 64)");
|
|
static int max_iotlb_entries = 2048;
|
|
module_param(max_iotlb_entries, int, 0444);
|
|
MODULE_PARM_DESC(max_iotlb_entries,
|
|
"Maximum number of iotlb entries. (default: 2048)");
|
|
|
|
enum {
|
|
VHOST_MEMORY_F_LOG = 0x1,
|
|
};
|
|
|
|
#define vhost_used_event(vq) ((__virtio16 __user *)&vq->avail->ring[vq->num])
|
|
#define vhost_avail_event(vq) ((__virtio16 __user *)&vq->used->ring[vq->num])
|
|
|
|
INTERVAL_TREE_DEFINE(struct vhost_umem_node,
|
|
rb, __u64, __subtree_last,
|
|
START, LAST, static inline, vhost_umem_interval_tree);
|
|
|
|
#ifdef CONFIG_VHOST_CROSS_ENDIAN_LEGACY
|
|
static void vhost_disable_cross_endian(struct vhost_virtqueue *vq)
|
|
{
|
|
vq->user_be = !virtio_legacy_is_little_endian();
|
|
}
|
|
|
|
static void vhost_enable_cross_endian_big(struct vhost_virtqueue *vq)
|
|
{
|
|
vq->user_be = true;
|
|
}
|
|
|
|
static void vhost_enable_cross_endian_little(struct vhost_virtqueue *vq)
|
|
{
|
|
vq->user_be = false;
|
|
}
|
|
|
|
static long vhost_set_vring_endian(struct vhost_virtqueue *vq, int __user *argp)
|
|
{
|
|
struct vhost_vring_state s;
|
|
|
|
if (vq->private_data)
|
|
return -EBUSY;
|
|
|
|
if (copy_from_user(&s, argp, sizeof(s)))
|
|
return -EFAULT;
|
|
|
|
if (s.num != VHOST_VRING_LITTLE_ENDIAN &&
|
|
s.num != VHOST_VRING_BIG_ENDIAN)
|
|
return -EINVAL;
|
|
|
|
if (s.num == VHOST_VRING_BIG_ENDIAN)
|
|
vhost_enable_cross_endian_big(vq);
|
|
else
|
|
vhost_enable_cross_endian_little(vq);
|
|
|
|
return 0;
|
|
}
|
|
|
|
static long vhost_get_vring_endian(struct vhost_virtqueue *vq, u32 idx,
|
|
int __user *argp)
|
|
{
|
|
struct vhost_vring_state s = {
|
|
.index = idx,
|
|
.num = vq->user_be
|
|
};
|
|
|
|
if (copy_to_user(argp, &s, sizeof(s)))
|
|
return -EFAULT;
|
|
|
|
return 0;
|
|
}
|
|
|
|
static void vhost_init_is_le(struct vhost_virtqueue *vq)
|
|
{
|
|
/* Note for legacy virtio: user_be is initialized at reset time
|
|
* according to the host endianness. If userspace does not set an
|
|
* explicit endianness, the default behavior is native endian, as
|
|
* expected by legacy virtio.
|
|
*/
|
|
vq->is_le = vhost_has_feature(vq, VIRTIO_F_VERSION_1) || !vq->user_be;
|
|
}
|
|
#else
|
|
static void vhost_disable_cross_endian(struct vhost_virtqueue *vq)
|
|
{
|
|
}
|
|
|
|
static long vhost_set_vring_endian(struct vhost_virtqueue *vq, int __user *argp)
|
|
{
|
|
return -ENOIOCTLCMD;
|
|
}
|
|
|
|
static long vhost_get_vring_endian(struct vhost_virtqueue *vq, u32 idx,
|
|
int __user *argp)
|
|
{
|
|
return -ENOIOCTLCMD;
|
|
}
|
|
|
|
static void vhost_init_is_le(struct vhost_virtqueue *vq)
|
|
{
|
|
vq->is_le = vhost_has_feature(vq, VIRTIO_F_VERSION_1)
|
|
|| virtio_legacy_is_little_endian();
|
|
}
|
|
#endif /* CONFIG_VHOST_CROSS_ENDIAN_LEGACY */
|
|
|
|
static void vhost_reset_is_le(struct vhost_virtqueue *vq)
|
|
{
|
|
vhost_init_is_le(vq);
|
|
}
|
|
|
|
struct vhost_flush_struct {
|
|
struct vhost_work work;
|
|
struct completion wait_event;
|
|
};
|
|
|
|
static void vhost_flush_work(struct vhost_work *work)
|
|
{
|
|
struct vhost_flush_struct *s;
|
|
|
|
s = container_of(work, struct vhost_flush_struct, work);
|
|
complete(&s->wait_event);
|
|
}
|
|
|
|
static void vhost_poll_func(struct file *file, wait_queue_head_t *wqh,
|
|
poll_table *pt)
|
|
{
|
|
struct vhost_poll *poll;
|
|
|
|
poll = container_of(pt, struct vhost_poll, table);
|
|
poll->wqh = wqh;
|
|
add_wait_queue(wqh, &poll->wait);
|
|
}
|
|
|
|
static int vhost_poll_wakeup(wait_queue_entry_t *wait, unsigned mode, int sync,
|
|
void *key)
|
|
{
|
|
struct vhost_poll *poll = container_of(wait, struct vhost_poll, wait);
|
|
|
|
if (!(key_to_poll(key) & poll->mask))
|
|
return 0;
|
|
|
|
vhost_poll_queue(poll);
|
|
return 0;
|
|
}
|
|
|
|
void vhost_work_init(struct vhost_work *work, vhost_work_fn_t fn)
|
|
{
|
|
clear_bit(VHOST_WORK_QUEUED, &work->flags);
|
|
work->fn = fn;
|
|
}
|
|
EXPORT_SYMBOL_GPL(vhost_work_init);
|
|
|
|
/* Init poll structure */
|
|
void vhost_poll_init(struct vhost_poll *poll, vhost_work_fn_t fn,
|
|
__poll_t mask, struct vhost_dev *dev)
|
|
{
|
|
init_waitqueue_func_entry(&poll->wait, vhost_poll_wakeup);
|
|
init_poll_funcptr(&poll->table, vhost_poll_func);
|
|
poll->mask = mask;
|
|
poll->dev = dev;
|
|
poll->wqh = NULL;
|
|
|
|
vhost_work_init(&poll->work, fn);
|
|
}
|
|
EXPORT_SYMBOL_GPL(vhost_poll_init);
|
|
|
|
/* Start polling a file. We add ourselves to file's wait queue. The caller must
|
|
* keep a reference to a file until after vhost_poll_stop is called. */
|
|
int vhost_poll_start(struct vhost_poll *poll, struct file *file)
|
|
{
|
|
__poll_t mask;
|
|
|
|
if (poll->wqh)
|
|
return 0;
|
|
|
|
mask = vfs_poll(file, &poll->table);
|
|
if (mask)
|
|
vhost_poll_wakeup(&poll->wait, 0, 0, poll_to_key(mask));
|
|
if (mask & EPOLLERR) {
|
|
vhost_poll_stop(poll);
|
|
return -EINVAL;
|
|
}
|
|
|
|
return 0;
|
|
}
|
|
EXPORT_SYMBOL_GPL(vhost_poll_start);
|
|
|
|
/* Stop polling a file. After this function returns, it becomes safe to drop the
|
|
* file reference. You must also flush afterwards. */
|
|
void vhost_poll_stop(struct vhost_poll *poll)
|
|
{
|
|
if (poll->wqh) {
|
|
remove_wait_queue(poll->wqh, &poll->wait);
|
|
poll->wqh = NULL;
|
|
}
|
|
}
|
|
EXPORT_SYMBOL_GPL(vhost_poll_stop);
|
|
|
|
void vhost_work_flush(struct vhost_dev *dev, struct vhost_work *work)
|
|
{
|
|
struct vhost_flush_struct flush;
|
|
|
|
if (dev->worker) {
|
|
init_completion(&flush.wait_event);
|
|
vhost_work_init(&flush.work, vhost_flush_work);
|
|
|
|
vhost_work_queue(dev, &flush.work);
|
|
wait_for_completion(&flush.wait_event);
|
|
}
|
|
}
|
|
EXPORT_SYMBOL_GPL(vhost_work_flush);
|
|
|
|
/* Flush any work that has been scheduled. When calling this, don't hold any
|
|
* locks that are also used by the callback. */
|
|
void vhost_poll_flush(struct vhost_poll *poll)
|
|
{
|
|
vhost_work_flush(poll->dev, &poll->work);
|
|
}
|
|
EXPORT_SYMBOL_GPL(vhost_poll_flush);
|
|
|
|
void vhost_work_queue(struct vhost_dev *dev, struct vhost_work *work)
|
|
{
|
|
if (!dev->worker)
|
|
return;
|
|
|
|
if (!test_and_set_bit(VHOST_WORK_QUEUED, &work->flags)) {
|
|
/* We can only add the work to the list after we're
|
|
* sure it was not in the list.
|
|
* test_and_set_bit() implies a memory barrier.
|
|
*/
|
|
llist_add(&work->node, &dev->work_list);
|
|
wake_up_process(dev->worker);
|
|
}
|
|
}
|
|
EXPORT_SYMBOL_GPL(vhost_work_queue);
|
|
|
|
/* A lockless hint for busy polling code to exit the loop */
|
|
bool vhost_has_work(struct vhost_dev *dev)
|
|
{
|
|
return !llist_empty(&dev->work_list);
|
|
}
|
|
EXPORT_SYMBOL_GPL(vhost_has_work);
|
|
|
|
void vhost_poll_queue(struct vhost_poll *poll)
|
|
{
|
|
vhost_work_queue(poll->dev, &poll->work);
|
|
}
|
|
EXPORT_SYMBOL_GPL(vhost_poll_queue);
|
|
|
|
static void __vhost_vq_meta_reset(struct vhost_virtqueue *vq)
|
|
{
|
|
int j;
|
|
|
|
for (j = 0; j < VHOST_NUM_ADDRS; j++)
|
|
vq->meta_iotlb[j] = NULL;
|
|
}
|
|
|
|
static void vhost_vq_meta_reset(struct vhost_dev *d)
|
|
{
|
|
int i;
|
|
|
|
for (i = 0; i < d->nvqs; ++i)
|
|
__vhost_vq_meta_reset(d->vqs[i]);
|
|
}
|
|
|
|
static void vhost_vq_reset(struct vhost_dev *dev,
|
|
struct vhost_virtqueue *vq)
|
|
{
|
|
vq->num = 1;
|
|
vq->desc = NULL;
|
|
vq->avail = NULL;
|
|
vq->used = NULL;
|
|
vq->last_avail_idx = 0;
|
|
vq->avail_idx = 0;
|
|
vq->last_used_idx = 0;
|
|
vq->signalled_used = 0;
|
|
vq->signalled_used_valid = false;
|
|
vq->used_flags = 0;
|
|
vq->log_used = false;
|
|
vq->log_addr = -1ull;
|
|
vq->private_data = NULL;
|
|
vq->acked_features = 0;
|
|
vq->acked_backend_features = 0;
|
|
vq->log_base = NULL;
|
|
vq->error_ctx = NULL;
|
|
vq->kick = NULL;
|
|
vq->call_ctx = NULL;
|
|
vq->log_ctx = NULL;
|
|
vhost_disable_cross_endian(vq);
|
|
vhost_reset_is_le(vq);
|
|
vq->busyloop_timeout = 0;
|
|
vq->umem = NULL;
|
|
vq->iotlb = NULL;
|
|
__vhost_vq_meta_reset(vq);
|
|
}
|
|
|
|
static int vhost_worker(void *data)
|
|
{
|
|
struct vhost_dev *dev = data;
|
|
struct vhost_work *work, *work_next;
|
|
struct llist_node *node;
|
|
mm_segment_t oldfs = get_fs();
|
|
|
|
set_fs(USER_DS);
|
|
use_mm(dev->mm);
|
|
|
|
for (;;) {
|
|
/* mb paired w/ kthread_stop */
|
|
set_current_state(TASK_INTERRUPTIBLE);
|
|
|
|
if (kthread_should_stop()) {
|
|
__set_current_state(TASK_RUNNING);
|
|
break;
|
|
}
|
|
|
|
node = llist_del_all(&dev->work_list);
|
|
if (!node)
|
|
schedule();
|
|
|
|
node = llist_reverse_order(node);
|
|
/* make sure flag is seen after deletion */
|
|
smp_wmb();
|
|
llist_for_each_entry_safe(work, work_next, node, node) {
|
|
clear_bit(VHOST_WORK_QUEUED, &work->flags);
|
|
__set_current_state(TASK_RUNNING);
|
|
kcov_remote_start_common(dev->kcov_handle);
|
|
work->fn(work);
|
|
kcov_remote_stop();
|
|
if (need_resched())
|
|
schedule();
|
|
}
|
|
}
|
|
unuse_mm(dev->mm);
|
|
set_fs(oldfs);
|
|
return 0;
|
|
}
|
|
|
|
static void vhost_vq_free_iovecs(struct vhost_virtqueue *vq)
|
|
{
|
|
kfree(vq->indirect);
|
|
vq->indirect = NULL;
|
|
kfree(vq->log);
|
|
vq->log = NULL;
|
|
kfree(vq->heads);
|
|
vq->heads = NULL;
|
|
}
|
|
|
|
/* Helper to allocate iovec buffers for all vqs. */
|
|
static long vhost_dev_alloc_iovecs(struct vhost_dev *dev)
|
|
{
|
|
struct vhost_virtqueue *vq;
|
|
int i;
|
|
|
|
for (i = 0; i < dev->nvqs; ++i) {
|
|
vq = dev->vqs[i];
|
|
vq->indirect = kmalloc_array(UIO_MAXIOV,
|
|
sizeof(*vq->indirect),
|
|
GFP_KERNEL);
|
|
vq->log = kmalloc_array(dev->iov_limit, sizeof(*vq->log),
|
|
GFP_KERNEL);
|
|
vq->heads = kmalloc_array(dev->iov_limit, sizeof(*vq->heads),
|
|
GFP_KERNEL);
|
|
if (!vq->indirect || !vq->log || !vq->heads)
|
|
goto err_nomem;
|
|
}
|
|
return 0;
|
|
|
|
err_nomem:
|
|
for (; i >= 0; --i)
|
|
vhost_vq_free_iovecs(dev->vqs[i]);
|
|
return -ENOMEM;
|
|
}
|
|
|
|
static void vhost_dev_free_iovecs(struct vhost_dev *dev)
|
|
{
|
|
int i;
|
|
|
|
for (i = 0; i < dev->nvqs; ++i)
|
|
vhost_vq_free_iovecs(dev->vqs[i]);
|
|
}
|
|
|
|
bool vhost_exceeds_weight(struct vhost_virtqueue *vq,
|
|
int pkts, int total_len)
|
|
{
|
|
struct vhost_dev *dev = vq->dev;
|
|
|
|
if ((dev->byte_weight && total_len >= dev->byte_weight) ||
|
|
pkts >= dev->weight) {
|
|
vhost_poll_queue(&vq->poll);
|
|
return true;
|
|
}
|
|
|
|
return false;
|
|
}
|
|
EXPORT_SYMBOL_GPL(vhost_exceeds_weight);
|
|
|
|
static size_t vhost_get_avail_size(struct vhost_virtqueue *vq,
|
|
unsigned int num)
|
|
{
|
|
size_t event __maybe_unused =
|
|
vhost_has_feature(vq, VIRTIO_RING_F_EVENT_IDX) ? 2 : 0;
|
|
|
|
return sizeof(*vq->avail) +
|
|
sizeof(*vq->avail->ring) * num + event;
|
|
}
|
|
|
|
static size_t vhost_get_used_size(struct vhost_virtqueue *vq,
|
|
unsigned int num)
|
|
{
|
|
size_t event __maybe_unused =
|
|
vhost_has_feature(vq, VIRTIO_RING_F_EVENT_IDX) ? 2 : 0;
|
|
|
|
return sizeof(*vq->used) +
|
|
sizeof(*vq->used->ring) * num + event;
|
|
}
|
|
|
|
static size_t vhost_get_desc_size(struct vhost_virtqueue *vq,
|
|
unsigned int num)
|
|
{
|
|
return sizeof(*vq->desc) * num;
|
|
}
|
|
|
|
void vhost_dev_init(struct vhost_dev *dev,
|
|
struct vhost_virtqueue **vqs, int nvqs,
|
|
int iov_limit, int weight, int byte_weight)
|
|
{
|
|
struct vhost_virtqueue *vq;
|
|
int i;
|
|
|
|
dev->vqs = vqs;
|
|
dev->nvqs = nvqs;
|
|
mutex_init(&dev->mutex);
|
|
dev->log_ctx = NULL;
|
|
dev->umem = NULL;
|
|
dev->iotlb = NULL;
|
|
dev->mm = NULL;
|
|
dev->worker = NULL;
|
|
dev->iov_limit = iov_limit;
|
|
dev->weight = weight;
|
|
dev->byte_weight = byte_weight;
|
|
init_llist_head(&dev->work_list);
|
|
init_waitqueue_head(&dev->wait);
|
|
INIT_LIST_HEAD(&dev->read_list);
|
|
INIT_LIST_HEAD(&dev->pending_list);
|
|
spin_lock_init(&dev->iotlb_lock);
|
|
|
|
|
|
for (i = 0; i < dev->nvqs; ++i) {
|
|
vq = dev->vqs[i];
|
|
vq->log = NULL;
|
|
vq->indirect = NULL;
|
|
vq->heads = NULL;
|
|
vq->dev = dev;
|
|
mutex_init(&vq->mutex);
|
|
vhost_vq_reset(dev, vq);
|
|
if (vq->handle_kick)
|
|
vhost_poll_init(&vq->poll, vq->handle_kick,
|
|
EPOLLIN, dev);
|
|
}
|
|
}
|
|
EXPORT_SYMBOL_GPL(vhost_dev_init);
|
|
|
|
/* Caller should have device mutex */
|
|
long vhost_dev_check_owner(struct vhost_dev *dev)
|
|
{
|
|
/* Are you the owner? If not, I don't think you mean to do that */
|
|
return dev->mm == current->mm ? 0 : -EPERM;
|
|
}
|
|
EXPORT_SYMBOL_GPL(vhost_dev_check_owner);
|
|
|
|
struct vhost_attach_cgroups_struct {
|
|
struct vhost_work work;
|
|
struct task_struct *owner;
|
|
int ret;
|
|
};
|
|
|
|
static void vhost_attach_cgroups_work(struct vhost_work *work)
|
|
{
|
|
struct vhost_attach_cgroups_struct *s;
|
|
|
|
s = container_of(work, struct vhost_attach_cgroups_struct, work);
|
|
s->ret = cgroup_attach_task_all(s->owner, current);
|
|
}
|
|
|
|
static int vhost_attach_cgroups(struct vhost_dev *dev)
|
|
{
|
|
struct vhost_attach_cgroups_struct attach;
|
|
|
|
attach.owner = current;
|
|
vhost_work_init(&attach.work, vhost_attach_cgroups_work);
|
|
vhost_work_queue(dev, &attach.work);
|
|
vhost_work_flush(dev, &attach.work);
|
|
return attach.ret;
|
|
}
|
|
|
|
/* Caller should have device mutex */
|
|
bool vhost_dev_has_owner(struct vhost_dev *dev)
|
|
{
|
|
return dev->mm;
|
|
}
|
|
EXPORT_SYMBOL_GPL(vhost_dev_has_owner);
|
|
|
|
/* Caller should have device mutex */
|
|
long vhost_dev_set_owner(struct vhost_dev *dev)
|
|
{
|
|
struct task_struct *worker;
|
|
int err;
|
|
|
|
/* Is there an owner already? */
|
|
if (vhost_dev_has_owner(dev)) {
|
|
err = -EBUSY;
|
|
goto err_mm;
|
|
}
|
|
|
|
/* No owner, become one */
|
|
dev->mm = get_task_mm(current);
|
|
dev->kcov_handle = kcov_common_handle();
|
|
worker = kthread_create(vhost_worker, dev, "vhost-%d", current->pid);
|
|
if (IS_ERR(worker)) {
|
|
err = PTR_ERR(worker);
|
|
goto err_worker;
|
|
}
|
|
|
|
dev->worker = worker;
|
|
wake_up_process(worker); /* avoid contributing to loadavg */
|
|
|
|
err = vhost_attach_cgroups(dev);
|
|
if (err)
|
|
goto err_cgroup;
|
|
|
|
err = vhost_dev_alloc_iovecs(dev);
|
|
if (err)
|
|
goto err_cgroup;
|
|
|
|
return 0;
|
|
err_cgroup:
|
|
kthread_stop(worker);
|
|
dev->worker = NULL;
|
|
err_worker:
|
|
if (dev->mm)
|
|
mmput(dev->mm);
|
|
dev->mm = NULL;
|
|
dev->kcov_handle = 0;
|
|
err_mm:
|
|
return err;
|
|
}
|
|
EXPORT_SYMBOL_GPL(vhost_dev_set_owner);
|
|
|
|
struct vhost_umem *vhost_dev_reset_owner_prepare(void)
|
|
{
|
|
return kvzalloc(sizeof(struct vhost_umem), GFP_KERNEL);
|
|
}
|
|
EXPORT_SYMBOL_GPL(vhost_dev_reset_owner_prepare);
|
|
|
|
/* Caller should have device mutex */
|
|
void vhost_dev_reset_owner(struct vhost_dev *dev, struct vhost_umem *umem)
|
|
{
|
|
int i;
|
|
|
|
vhost_dev_cleanup(dev);
|
|
|
|
/* Restore memory to default empty mapping. */
|
|
INIT_LIST_HEAD(&umem->umem_list);
|
|
dev->umem = umem;
|
|
/* We don't need VQ locks below since vhost_dev_cleanup makes sure
|
|
* VQs aren't running.
|
|
*/
|
|
for (i = 0; i < dev->nvqs; ++i)
|
|
dev->vqs[i]->umem = umem;
|
|
}
|
|
EXPORT_SYMBOL_GPL(vhost_dev_reset_owner);
|
|
|
|
void vhost_dev_stop(struct vhost_dev *dev)
|
|
{
|
|
int i;
|
|
|
|
for (i = 0; i < dev->nvqs; ++i) {
|
|
if (dev->vqs[i]->kick && dev->vqs[i]->handle_kick) {
|
|
vhost_poll_stop(&dev->vqs[i]->poll);
|
|
vhost_poll_flush(&dev->vqs[i]->poll);
|
|
}
|
|
}
|
|
}
|
|
EXPORT_SYMBOL_GPL(vhost_dev_stop);
|
|
|
|
static void vhost_umem_free(struct vhost_umem *umem,
|
|
struct vhost_umem_node *node)
|
|
{
|
|
vhost_umem_interval_tree_remove(node, &umem->umem_tree);
|
|
list_del(&node->link);
|
|
kfree(node);
|
|
umem->numem--;
|
|
}
|
|
|
|
static void vhost_umem_clean(struct vhost_umem *umem)
|
|
{
|
|
struct vhost_umem_node *node, *tmp;
|
|
|
|
if (!umem)
|
|
return;
|
|
|
|
list_for_each_entry_safe(node, tmp, &umem->umem_list, link)
|
|
vhost_umem_free(umem, node);
|
|
|
|
kvfree(umem);
|
|
}
|
|
|
|
static void vhost_clear_msg(struct vhost_dev *dev)
|
|
{
|
|
struct vhost_msg_node *node, *n;
|
|
|
|
spin_lock(&dev->iotlb_lock);
|
|
|
|
list_for_each_entry_safe(node, n, &dev->read_list, node) {
|
|
list_del(&node->node);
|
|
kfree(node);
|
|
}
|
|
|
|
list_for_each_entry_safe(node, n, &dev->pending_list, node) {
|
|
list_del(&node->node);
|
|
kfree(node);
|
|
}
|
|
|
|
spin_unlock(&dev->iotlb_lock);
|
|
}
|
|
|
|
void vhost_dev_cleanup(struct vhost_dev *dev)
|
|
{
|
|
int i;
|
|
|
|
for (i = 0; i < dev->nvqs; ++i) {
|
|
if (dev->vqs[i]->error_ctx)
|
|
eventfd_ctx_put(dev->vqs[i]->error_ctx);
|
|
if (dev->vqs[i]->kick)
|
|
fput(dev->vqs[i]->kick);
|
|
if (dev->vqs[i]->call_ctx)
|
|
eventfd_ctx_put(dev->vqs[i]->call_ctx);
|
|
vhost_vq_reset(dev, dev->vqs[i]);
|
|
}
|
|
vhost_dev_free_iovecs(dev);
|
|
if (dev->log_ctx)
|
|
eventfd_ctx_put(dev->log_ctx);
|
|
dev->log_ctx = NULL;
|
|
/* No one will access memory at this point */
|
|
vhost_umem_clean(dev->umem);
|
|
dev->umem = NULL;
|
|
vhost_umem_clean(dev->iotlb);
|
|
dev->iotlb = NULL;
|
|
vhost_clear_msg(dev);
|
|
wake_up_interruptible_poll(&dev->wait, EPOLLIN | EPOLLRDNORM);
|
|
WARN_ON(!llist_empty(&dev->work_list));
|
|
if (dev->worker) {
|
|
kthread_stop(dev->worker);
|
|
dev->worker = NULL;
|
|
dev->kcov_handle = 0;
|
|
}
|
|
if (dev->mm)
|
|
mmput(dev->mm);
|
|
dev->mm = NULL;
|
|
}
|
|
EXPORT_SYMBOL_GPL(vhost_dev_cleanup);
|
|
|
|
static bool log_access_ok(void __user *log_base, u64 addr, unsigned long sz)
|
|
{
|
|
u64 a = addr / VHOST_PAGE_SIZE / 8;
|
|
|
|
/* Make sure 64 bit math will not overflow. */
|
|
if (a > ULONG_MAX - (unsigned long)log_base ||
|
|
a + (unsigned long)log_base > ULONG_MAX)
|
|
return false;
|
|
|
|
return access_ok(log_base + a,
|
|
(sz + VHOST_PAGE_SIZE * 8 - 1) / VHOST_PAGE_SIZE / 8);
|
|
}
|
|
|
|
/* Make sure 64 bit math will not overflow. */
|
|
static bool vhost_overflow(u64 uaddr, u64 size)
|
|
{
|
|
if (uaddr > ULONG_MAX || size > ULONG_MAX)
|
|
return true;
|
|
|
|
if (!size)
|
|
return false;
|
|
|
|
return uaddr > ULONG_MAX - size + 1;
|
|
}
|
|
|
|
/* Caller should have vq mutex and device mutex. */
|
|
static bool vq_memory_access_ok(void __user *log_base, struct vhost_umem *umem,
|
|
int log_all)
|
|
{
|
|
struct vhost_umem_node *node;
|
|
|
|
if (!umem)
|
|
return false;
|
|
|
|
list_for_each_entry(node, &umem->umem_list, link) {
|
|
unsigned long a = node->userspace_addr;
|
|
|
|
if (vhost_overflow(node->userspace_addr, node->size))
|
|
return false;
|
|
|
|
|
|
if (!access_ok((void __user *)a,
|
|
node->size))
|
|
return false;
|
|
else if (log_all && !log_access_ok(log_base,
|
|
node->start,
|
|
node->size))
|
|
return false;
|
|
}
|
|
return true;
|
|
}
|
|
|
|
static inline void __user *vhost_vq_meta_fetch(struct vhost_virtqueue *vq,
|
|
u64 addr, unsigned int size,
|
|
int type)
|
|
{
|
|
const struct vhost_umem_node *node = vq->meta_iotlb[type];
|
|
|
|
if (!node)
|
|
return NULL;
|
|
|
|
return (void *)(uintptr_t)(node->userspace_addr + addr - node->start);
|
|
}
|
|
|
|
/* Can we switch to this memory table? */
|
|
/* Caller should have device mutex but not vq mutex */
|
|
static bool memory_access_ok(struct vhost_dev *d, struct vhost_umem *umem,
|
|
int log_all)
|
|
{
|
|
int i;
|
|
|
|
for (i = 0; i < d->nvqs; ++i) {
|
|
bool ok;
|
|
bool log;
|
|
|
|
mutex_lock(&d->vqs[i]->mutex);
|
|
log = log_all || vhost_has_feature(d->vqs[i], VHOST_F_LOG_ALL);
|
|
/* If ring is inactive, will check when it's enabled. */
|
|
if (d->vqs[i]->private_data)
|
|
ok = vq_memory_access_ok(d->vqs[i]->log_base,
|
|
umem, log);
|
|
else
|
|
ok = true;
|
|
mutex_unlock(&d->vqs[i]->mutex);
|
|
if (!ok)
|
|
return false;
|
|
}
|
|
return true;
|
|
}
|
|
|
|
static int translate_desc(struct vhost_virtqueue *vq, u64 addr, u32 len,
|
|
struct iovec iov[], int iov_size, int access);
|
|
|
|
static int vhost_copy_to_user(struct vhost_virtqueue *vq, void __user *to,
|
|
const void *from, unsigned size)
|
|
{
|
|
int ret;
|
|
|
|
if (!vq->iotlb)
|
|
return __copy_to_user(to, from, size);
|
|
else {
|
|
/* This function should be called after iotlb
|
|
* prefetch, which means we're sure that all vq
|
|
* could be access through iotlb. So -EAGAIN should
|
|
* not happen in this case.
|
|
*/
|
|
struct iov_iter t;
|
|
void __user *uaddr = vhost_vq_meta_fetch(vq,
|
|
(u64)(uintptr_t)to, size,
|
|
VHOST_ADDR_USED);
|
|
|
|
if (uaddr)
|
|
return __copy_to_user(uaddr, from, size);
|
|
|
|
ret = translate_desc(vq, (u64)(uintptr_t)to, size, vq->iotlb_iov,
|
|
ARRAY_SIZE(vq->iotlb_iov),
|
|
VHOST_ACCESS_WO);
|
|
if (ret < 0)
|
|
goto out;
|
|
iov_iter_init(&t, WRITE, vq->iotlb_iov, ret, size);
|
|
ret = copy_to_iter(from, size, &t);
|
|
if (ret == size)
|
|
ret = 0;
|
|
}
|
|
out:
|
|
return ret;
|
|
}
|
|
|
|
static int vhost_copy_from_user(struct vhost_virtqueue *vq, void *to,
|
|
void __user *from, unsigned size)
|
|
{
|
|
int ret;
|
|
|
|
if (!vq->iotlb)
|
|
return __copy_from_user(to, from, size);
|
|
else {
|
|
/* This function should be called after iotlb
|
|
* prefetch, which means we're sure that vq
|
|
* could be access through iotlb. So -EAGAIN should
|
|
* not happen in this case.
|
|
*/
|
|
void __user *uaddr = vhost_vq_meta_fetch(vq,
|
|
(u64)(uintptr_t)from, size,
|
|
VHOST_ADDR_DESC);
|
|
struct iov_iter f;
|
|
|
|
if (uaddr)
|
|
return __copy_from_user(to, uaddr, size);
|
|
|
|
ret = translate_desc(vq, (u64)(uintptr_t)from, size, vq->iotlb_iov,
|
|
ARRAY_SIZE(vq->iotlb_iov),
|
|
VHOST_ACCESS_RO);
|
|
if (ret < 0) {
|
|
vq_err(vq, "IOTLB translation failure: uaddr "
|
|
"%p size 0x%llx\n", from,
|
|
(unsigned long long) size);
|
|
goto out;
|
|
}
|
|
iov_iter_init(&f, READ, vq->iotlb_iov, ret, size);
|
|
ret = copy_from_iter(to, size, &f);
|
|
if (ret == size)
|
|
ret = 0;
|
|
}
|
|
|
|
out:
|
|
return ret;
|
|
}
|
|
|
|
static void __user *__vhost_get_user_slow(struct vhost_virtqueue *vq,
|
|
void __user *addr, unsigned int size,
|
|
int type)
|
|
{
|
|
int ret;
|
|
|
|
ret = translate_desc(vq, (u64)(uintptr_t)addr, size, vq->iotlb_iov,
|
|
ARRAY_SIZE(vq->iotlb_iov),
|
|
VHOST_ACCESS_RO);
|
|
if (ret < 0) {
|
|
vq_err(vq, "IOTLB translation failure: uaddr "
|
|
"%p size 0x%llx\n", addr,
|
|
(unsigned long long) size);
|
|
return NULL;
|
|
}
|
|
|
|
if (ret != 1 || vq->iotlb_iov[0].iov_len != size) {
|
|
vq_err(vq, "Non atomic userspace memory access: uaddr "
|
|
"%p size 0x%llx\n", addr,
|
|
(unsigned long long) size);
|
|
return NULL;
|
|
}
|
|
|
|
return vq->iotlb_iov[0].iov_base;
|
|
}
|
|
|
|
/* This function should be called after iotlb
|
|
* prefetch, which means we're sure that vq
|
|
* could be access through iotlb. So -EAGAIN should
|
|
* not happen in this case.
|
|
*/
|
|
static inline void __user *__vhost_get_user(struct vhost_virtqueue *vq,
|
|
void *addr, unsigned int size,
|
|
int type)
|
|
{
|
|
void __user *uaddr = vhost_vq_meta_fetch(vq,
|
|
(u64)(uintptr_t)addr, size, type);
|
|
if (uaddr)
|
|
return uaddr;
|
|
|
|
return __vhost_get_user_slow(vq, addr, size, type);
|
|
}
|
|
|
|
#define vhost_put_user(vq, x, ptr) \
|
|
({ \
|
|
int ret = -EFAULT; \
|
|
if (!vq->iotlb) { \
|
|
ret = __put_user(x, ptr); \
|
|
} else { \
|
|
__typeof__(ptr) to = \
|
|
(__typeof__(ptr)) __vhost_get_user(vq, ptr, \
|
|
sizeof(*ptr), VHOST_ADDR_USED); \
|
|
if (to != NULL) \
|
|
ret = __put_user(x, to); \
|
|
else \
|
|
ret = -EFAULT; \
|
|
} \
|
|
ret; \
|
|
})
|
|
|
|
static inline int vhost_put_avail_event(struct vhost_virtqueue *vq)
|
|
{
|
|
return vhost_put_user(vq, cpu_to_vhost16(vq, vq->avail_idx),
|
|
vhost_avail_event(vq));
|
|
}
|
|
|
|
static inline int vhost_put_used(struct vhost_virtqueue *vq,
|
|
struct vring_used_elem *head, int idx,
|
|
int count)
|
|
{
|
|
return vhost_copy_to_user(vq, vq->used->ring + idx, head,
|
|
count * sizeof(*head));
|
|
}
|
|
|
|
static inline int vhost_put_used_flags(struct vhost_virtqueue *vq)
|
|
|
|
{
|
|
return vhost_put_user(vq, cpu_to_vhost16(vq, vq->used_flags),
|
|
&vq->used->flags);
|
|
}
|
|
|
|
static inline int vhost_put_used_idx(struct vhost_virtqueue *vq)
|
|
|
|
{
|
|
return vhost_put_user(vq, cpu_to_vhost16(vq, vq->last_used_idx),
|
|
&vq->used->idx);
|
|
}
|
|
|
|
#define vhost_get_user(vq, x, ptr, type) \
|
|
({ \
|
|
int ret; \
|
|
if (!vq->iotlb) { \
|
|
ret = __get_user(x, ptr); \
|
|
} else { \
|
|
__typeof__(ptr) from = \
|
|
(__typeof__(ptr)) __vhost_get_user(vq, ptr, \
|
|
sizeof(*ptr), \
|
|
type); \
|
|
if (from != NULL) \
|
|
ret = __get_user(x, from); \
|
|
else \
|
|
ret = -EFAULT; \
|
|
} \
|
|
ret; \
|
|
})
|
|
|
|
#define vhost_get_avail(vq, x, ptr) \
|
|
vhost_get_user(vq, x, ptr, VHOST_ADDR_AVAIL)
|
|
|
|
#define vhost_get_used(vq, x, ptr) \
|
|
vhost_get_user(vq, x, ptr, VHOST_ADDR_USED)
|
|
|
|
static void vhost_dev_lock_vqs(struct vhost_dev *d)
|
|
{
|
|
int i = 0;
|
|
for (i = 0; i < d->nvqs; ++i)
|
|
mutex_lock_nested(&d->vqs[i]->mutex, i);
|
|
}
|
|
|
|
static void vhost_dev_unlock_vqs(struct vhost_dev *d)
|
|
{
|
|
int i = 0;
|
|
for (i = 0; i < d->nvqs; ++i)
|
|
mutex_unlock(&d->vqs[i]->mutex);
|
|
}
|
|
|
|
static inline int vhost_get_avail_idx(struct vhost_virtqueue *vq,
|
|
__virtio16 *idx)
|
|
{
|
|
return vhost_get_avail(vq, *idx, &vq->avail->idx);
|
|
}
|
|
|
|
static inline int vhost_get_avail_head(struct vhost_virtqueue *vq,
|
|
__virtio16 *head, int idx)
|
|
{
|
|
return vhost_get_avail(vq, *head,
|
|
&vq->avail->ring[idx & (vq->num - 1)]);
|
|
}
|
|
|
|
static inline int vhost_get_avail_flags(struct vhost_virtqueue *vq,
|
|
__virtio16 *flags)
|
|
{
|
|
return vhost_get_avail(vq, *flags, &vq->avail->flags);
|
|
}
|
|
|
|
static inline int vhost_get_used_event(struct vhost_virtqueue *vq,
|
|
__virtio16 *event)
|
|
{
|
|
return vhost_get_avail(vq, *event, vhost_used_event(vq));
|
|
}
|
|
|
|
static inline int vhost_get_used_idx(struct vhost_virtqueue *vq,
|
|
__virtio16 *idx)
|
|
{
|
|
return vhost_get_used(vq, *idx, &vq->used->idx);
|
|
}
|
|
|
|
static inline int vhost_get_desc(struct vhost_virtqueue *vq,
|
|
struct vring_desc *desc, int idx)
|
|
{
|
|
return vhost_copy_from_user(vq, desc, vq->desc + idx, sizeof(*desc));
|
|
}
|
|
|
|
static int vhost_new_umem_range(struct vhost_umem *umem,
|
|
u64 start, u64 size, u64 end,
|
|
u64 userspace_addr, int perm)
|
|
{
|
|
struct vhost_umem_node *tmp, *node;
|
|
|
|
if (!size)
|
|
return -EFAULT;
|
|
|
|
node = kmalloc(sizeof(*node), GFP_ATOMIC);
|
|
if (!node)
|
|
return -ENOMEM;
|
|
|
|
if (umem->numem == max_iotlb_entries) {
|
|
tmp = list_first_entry(&umem->umem_list, typeof(*tmp), link);
|
|
vhost_umem_free(umem, tmp);
|
|
}
|
|
|
|
node->start = start;
|
|
node->size = size;
|
|
node->last = end;
|
|
node->userspace_addr = userspace_addr;
|
|
node->perm = perm;
|
|
INIT_LIST_HEAD(&node->link);
|
|
list_add_tail(&node->link, &umem->umem_list);
|
|
vhost_umem_interval_tree_insert(node, &umem->umem_tree);
|
|
umem->numem++;
|
|
|
|
return 0;
|
|
}
|
|
|
|
static void vhost_del_umem_range(struct vhost_umem *umem,
|
|
u64 start, u64 end)
|
|
{
|
|
struct vhost_umem_node *node;
|
|
|
|
while ((node = vhost_umem_interval_tree_iter_first(&umem->umem_tree,
|
|
start, end)))
|
|
vhost_umem_free(umem, node);
|
|
}
|
|
|
|
static void vhost_iotlb_notify_vq(struct vhost_dev *d,
|
|
struct vhost_iotlb_msg *msg)
|
|
{
|
|
struct vhost_msg_node *node, *n;
|
|
|
|
spin_lock(&d->iotlb_lock);
|
|
|
|
list_for_each_entry_safe(node, n, &d->pending_list, node) {
|
|
struct vhost_iotlb_msg *vq_msg = &node->msg.iotlb;
|
|
if (msg->iova <= vq_msg->iova &&
|
|
msg->iova + msg->size - 1 >= vq_msg->iova &&
|
|
vq_msg->type == VHOST_IOTLB_MISS) {
|
|
vhost_poll_queue(&node->vq->poll);
|
|
list_del(&node->node);
|
|
kfree(node);
|
|
}
|
|
}
|
|
|
|
spin_unlock(&d->iotlb_lock);
|
|
}
|
|
|
|
static bool umem_access_ok(u64 uaddr, u64 size, int access)
|
|
{
|
|
unsigned long a = uaddr;
|
|
|
|
/* Make sure 64 bit math will not overflow. */
|
|
if (vhost_overflow(uaddr, size))
|
|
return false;
|
|
|
|
if ((access & VHOST_ACCESS_RO) &&
|
|
!access_ok((void __user *)a, size))
|
|
return false;
|
|
if ((access & VHOST_ACCESS_WO) &&
|
|
!access_ok((void __user *)a, size))
|
|
return false;
|
|
return true;
|
|
}
|
|
|
|
static int vhost_process_iotlb_msg(struct vhost_dev *dev,
|
|
struct vhost_iotlb_msg *msg)
|
|
{
|
|
int ret = 0;
|
|
|
|
mutex_lock(&dev->mutex);
|
|
vhost_dev_lock_vqs(dev);
|
|
switch (msg->type) {
|
|
case VHOST_IOTLB_UPDATE:
|
|
if (!dev->iotlb) {
|
|
ret = -EFAULT;
|
|
break;
|
|
}
|
|
if (!umem_access_ok(msg->uaddr, msg->size, msg->perm)) {
|
|
ret = -EFAULT;
|
|
break;
|
|
}
|
|
vhost_vq_meta_reset(dev);
|
|
if (vhost_new_umem_range(dev->iotlb, msg->iova, msg->size,
|
|
msg->iova + msg->size - 1,
|
|
msg->uaddr, msg->perm)) {
|
|
ret = -ENOMEM;
|
|
break;
|
|
}
|
|
vhost_iotlb_notify_vq(dev, msg);
|
|
break;
|
|
case VHOST_IOTLB_INVALIDATE:
|
|
if (!dev->iotlb) {
|
|
ret = -EFAULT;
|
|
break;
|
|
}
|
|
vhost_vq_meta_reset(dev);
|
|
vhost_del_umem_range(dev->iotlb, msg->iova,
|
|
msg->iova + msg->size - 1);
|
|
break;
|
|
default:
|
|
ret = -EINVAL;
|
|
break;
|
|
}
|
|
|
|
vhost_dev_unlock_vqs(dev);
|
|
mutex_unlock(&dev->mutex);
|
|
|
|
return ret;
|
|
}
|
|
ssize_t vhost_chr_write_iter(struct vhost_dev *dev,
|
|
struct iov_iter *from)
|
|
{
|
|
struct vhost_iotlb_msg msg;
|
|
size_t offset;
|
|
int type, ret;
|
|
|
|
ret = copy_from_iter(&type, sizeof(type), from);
|
|
if (ret != sizeof(type)) {
|
|
ret = -EINVAL;
|
|
goto done;
|
|
}
|
|
|
|
switch (type) {
|
|
case VHOST_IOTLB_MSG:
|
|
/* There maybe a hole after type for V1 message type,
|
|
* so skip it here.
|
|
*/
|
|
offset = offsetof(struct vhost_msg, iotlb) - sizeof(int);
|
|
break;
|
|
case VHOST_IOTLB_MSG_V2:
|
|
offset = sizeof(__u32);
|
|
break;
|
|
default:
|
|
ret = -EINVAL;
|
|
goto done;
|
|
}
|
|
|
|
iov_iter_advance(from, offset);
|
|
ret = copy_from_iter(&msg, sizeof(msg), from);
|
|
if (ret != sizeof(msg)) {
|
|
ret = -EINVAL;
|
|
goto done;
|
|
}
|
|
if (vhost_process_iotlb_msg(dev, &msg)) {
|
|
ret = -EFAULT;
|
|
goto done;
|
|
}
|
|
|
|
ret = (type == VHOST_IOTLB_MSG) ? sizeof(struct vhost_msg) :
|
|
sizeof(struct vhost_msg_v2);
|
|
done:
|
|
return ret;
|
|
}
|
|
EXPORT_SYMBOL(vhost_chr_write_iter);
|
|
|
|
__poll_t vhost_chr_poll(struct file *file, struct vhost_dev *dev,
|
|
poll_table *wait)
|
|
{
|
|
__poll_t mask = 0;
|
|
|
|
poll_wait(file, &dev->wait, wait);
|
|
|
|
if (!list_empty(&dev->read_list))
|
|
mask |= EPOLLIN | EPOLLRDNORM;
|
|
|
|
return mask;
|
|
}
|
|
EXPORT_SYMBOL(vhost_chr_poll);
|
|
|
|
ssize_t vhost_chr_read_iter(struct vhost_dev *dev, struct iov_iter *to,
|
|
int noblock)
|
|
{
|
|
DEFINE_WAIT(wait);
|
|
struct vhost_msg_node *node;
|
|
ssize_t ret = 0;
|
|
unsigned size = sizeof(struct vhost_msg);
|
|
|
|
if (iov_iter_count(to) < size)
|
|
return 0;
|
|
|
|
while (1) {
|
|
if (!noblock)
|
|
prepare_to_wait(&dev->wait, &wait,
|
|
TASK_INTERRUPTIBLE);
|
|
|
|
node = vhost_dequeue_msg(dev, &dev->read_list);
|
|
if (node)
|
|
break;
|
|
if (noblock) {
|
|
ret = -EAGAIN;
|
|
break;
|
|
}
|
|
if (signal_pending(current)) {
|
|
ret = -ERESTARTSYS;
|
|
break;
|
|
}
|
|
if (!dev->iotlb) {
|
|
ret = -EBADFD;
|
|
break;
|
|
}
|
|
|
|
schedule();
|
|
}
|
|
|
|
if (!noblock)
|
|
finish_wait(&dev->wait, &wait);
|
|
|
|
if (node) {
|
|
struct vhost_iotlb_msg *msg;
|
|
void *start = &node->msg;
|
|
|
|
switch (node->msg.type) {
|
|
case VHOST_IOTLB_MSG:
|
|
size = sizeof(node->msg);
|
|
msg = &node->msg.iotlb;
|
|
break;
|
|
case VHOST_IOTLB_MSG_V2:
|
|
size = sizeof(node->msg_v2);
|
|
msg = &node->msg_v2.iotlb;
|
|
break;
|
|
default:
|
|
BUG();
|
|
break;
|
|
}
|
|
|
|
ret = copy_to_iter(start, size, to);
|
|
if (ret != size || msg->type != VHOST_IOTLB_MISS) {
|
|
kfree(node);
|
|
return ret;
|
|
}
|
|
vhost_enqueue_msg(dev, &dev->pending_list, node);
|
|
}
|
|
|
|
return ret;
|
|
}
|
|
EXPORT_SYMBOL_GPL(vhost_chr_read_iter);
|
|
|
|
static int vhost_iotlb_miss(struct vhost_virtqueue *vq, u64 iova, int access)
|
|
{
|
|
struct vhost_dev *dev = vq->dev;
|
|
struct vhost_msg_node *node;
|
|
struct vhost_iotlb_msg *msg;
|
|
bool v2 = vhost_backend_has_feature(vq, VHOST_BACKEND_F_IOTLB_MSG_V2);
|
|
|
|
node = vhost_new_msg(vq, v2 ? VHOST_IOTLB_MSG_V2 : VHOST_IOTLB_MSG);
|
|
if (!node)
|
|
return -ENOMEM;
|
|
|
|
if (v2) {
|
|
node->msg_v2.type = VHOST_IOTLB_MSG_V2;
|
|
msg = &node->msg_v2.iotlb;
|
|
} else {
|
|
msg = &node->msg.iotlb;
|
|
}
|
|
|
|
msg->type = VHOST_IOTLB_MISS;
|
|
msg->iova = iova;
|
|
msg->perm = access;
|
|
|
|
vhost_enqueue_msg(dev, &dev->read_list, node);
|
|
|
|
return 0;
|
|
}
|
|
|
|
static bool vq_access_ok(struct vhost_virtqueue *vq, unsigned int num,
|
|
struct vring_desc __user *desc,
|
|
struct vring_avail __user *avail,
|
|
struct vring_used __user *used)
|
|
|
|
{
|
|
/* If an IOTLB device is present, the vring addresses are
|
|
* GIOVAs. Access validation occurs at prefetch time. */
|
|
if (vq->iotlb)
|
|
return true;
|
|
|
|
return access_ok(desc, vhost_get_desc_size(vq, num)) &&
|
|
access_ok(avail, vhost_get_avail_size(vq, num)) &&
|
|
access_ok(used, vhost_get_used_size(vq, num));
|
|
}
|
|
|
|
static void vhost_vq_meta_update(struct vhost_virtqueue *vq,
|
|
const struct vhost_umem_node *node,
|
|
int type)
|
|
{
|
|
int access = (type == VHOST_ADDR_USED) ?
|
|
VHOST_ACCESS_WO : VHOST_ACCESS_RO;
|
|
|
|
if (likely(node->perm & access))
|
|
vq->meta_iotlb[type] = node;
|
|
}
|
|
|
|
static bool iotlb_access_ok(struct vhost_virtqueue *vq,
|
|
int access, u64 addr, u64 len, int type)
|
|
{
|
|
const struct vhost_umem_node *node;
|
|
struct vhost_umem *umem = vq->iotlb;
|
|
u64 s = 0, size, orig_addr = addr, last = addr + len - 1;
|
|
|
|
if (vhost_vq_meta_fetch(vq, addr, len, type))
|
|
return true;
|
|
|
|
while (len > s) {
|
|
node = vhost_umem_interval_tree_iter_first(&umem->umem_tree,
|
|
addr,
|
|
last);
|
|
if (node == NULL || node->start > addr) {
|
|
vhost_iotlb_miss(vq, addr, access);
|
|
return false;
|
|
} else if (!(node->perm & access)) {
|
|
/* Report the possible access violation by
|
|
* request another translation from userspace.
|
|
*/
|
|
return false;
|
|
}
|
|
|
|
size = node->size - addr + node->start;
|
|
|
|
if (orig_addr == addr && size >= len)
|
|
vhost_vq_meta_update(vq, node, type);
|
|
|
|
s += size;
|
|
addr += size;
|
|
}
|
|
|
|
return true;
|
|
}
|
|
|
|
int vq_meta_prefetch(struct vhost_virtqueue *vq)
|
|
{
|
|
unsigned int num = vq->num;
|
|
|
|
if (!vq->iotlb)
|
|
return 1;
|
|
|
|
return iotlb_access_ok(vq, VHOST_ACCESS_RO, (u64)(uintptr_t)vq->desc,
|
|
vhost_get_desc_size(vq, num), VHOST_ADDR_DESC) &&
|
|
iotlb_access_ok(vq, VHOST_ACCESS_RO, (u64)(uintptr_t)vq->avail,
|
|
vhost_get_avail_size(vq, num),
|
|
VHOST_ADDR_AVAIL) &&
|
|
iotlb_access_ok(vq, VHOST_ACCESS_WO, (u64)(uintptr_t)vq->used,
|
|
vhost_get_used_size(vq, num), VHOST_ADDR_USED);
|
|
}
|
|
EXPORT_SYMBOL_GPL(vq_meta_prefetch);
|
|
|
|
/* Can we log writes? */
|
|
/* Caller should have device mutex but not vq mutex */
|
|
bool vhost_log_access_ok(struct vhost_dev *dev)
|
|
{
|
|
return memory_access_ok(dev, dev->umem, 1);
|
|
}
|
|
EXPORT_SYMBOL_GPL(vhost_log_access_ok);
|
|
|
|
/* Verify access for write logging. */
|
|
/* Caller should have vq mutex and device mutex */
|
|
static bool vq_log_access_ok(struct vhost_virtqueue *vq,
|
|
void __user *log_base)
|
|
{
|
|
return vq_memory_access_ok(log_base, vq->umem,
|
|
vhost_has_feature(vq, VHOST_F_LOG_ALL)) &&
|
|
(!vq->log_used || log_access_ok(log_base, vq->log_addr,
|
|
vhost_get_used_size(vq, vq->num)));
|
|
}
|
|
|
|
/* Can we start vq? */
|
|
/* Caller should have vq mutex and device mutex */
|
|
bool vhost_vq_access_ok(struct vhost_virtqueue *vq)
|
|
{
|
|
if (!vq_log_access_ok(vq, vq->log_base))
|
|
return false;
|
|
|
|
return vq_access_ok(vq, vq->num, vq->desc, vq->avail, vq->used);
|
|
}
|
|
EXPORT_SYMBOL_GPL(vhost_vq_access_ok);
|
|
|
|
static struct vhost_umem *vhost_umem_alloc(void)
|
|
{
|
|
struct vhost_umem *umem = kvzalloc(sizeof(*umem), GFP_KERNEL);
|
|
|
|
if (!umem)
|
|
return NULL;
|
|
|
|
umem->umem_tree = RB_ROOT_CACHED;
|
|
umem->numem = 0;
|
|
INIT_LIST_HEAD(&umem->umem_list);
|
|
|
|
return umem;
|
|
}
|
|
|
|
static long vhost_set_memory(struct vhost_dev *d, struct vhost_memory __user *m)
|
|
{
|
|
struct vhost_memory mem, *newmem;
|
|
struct vhost_memory_region *region;
|
|
struct vhost_umem *newumem, *oldumem;
|
|
unsigned long size = offsetof(struct vhost_memory, regions);
|
|
int i;
|
|
|
|
if (copy_from_user(&mem, m, size))
|
|
return -EFAULT;
|
|
if (mem.padding)
|
|
return -EOPNOTSUPP;
|
|
if (mem.nregions > max_mem_regions)
|
|
return -E2BIG;
|
|
newmem = kvzalloc(struct_size(newmem, regions, mem.nregions),
|
|
GFP_KERNEL);
|
|
if (!newmem)
|
|
return -ENOMEM;
|
|
|
|
memcpy(newmem, &mem, size);
|
|
if (copy_from_user(newmem->regions, m->regions,
|
|
mem.nregions * sizeof *m->regions)) {
|
|
kvfree(newmem);
|
|
return -EFAULT;
|
|
}
|
|
|
|
newumem = vhost_umem_alloc();
|
|
if (!newumem) {
|
|
kvfree(newmem);
|
|
return -ENOMEM;
|
|
}
|
|
|
|
for (region = newmem->regions;
|
|
region < newmem->regions + mem.nregions;
|
|
region++) {
|
|
if (vhost_new_umem_range(newumem,
|
|
region->guest_phys_addr,
|
|
region->memory_size,
|
|
region->guest_phys_addr +
|
|
region->memory_size - 1,
|
|
region->userspace_addr,
|
|
VHOST_ACCESS_RW))
|
|
goto err;
|
|
}
|
|
|
|
if (!memory_access_ok(d, newumem, 0))
|
|
goto err;
|
|
|
|
oldumem = d->umem;
|
|
d->umem = newumem;
|
|
|
|
/* All memory accesses are done under some VQ mutex. */
|
|
for (i = 0; i < d->nvqs; ++i) {
|
|
mutex_lock(&d->vqs[i]->mutex);
|
|
d->vqs[i]->umem = newumem;
|
|
mutex_unlock(&d->vqs[i]->mutex);
|
|
}
|
|
|
|
kvfree(newmem);
|
|
vhost_umem_clean(oldumem);
|
|
return 0;
|
|
|
|
err:
|
|
vhost_umem_clean(newumem);
|
|
kvfree(newmem);
|
|
return -EFAULT;
|
|
}
|
|
|
|
static long vhost_vring_set_num(struct vhost_dev *d,
|
|
struct vhost_virtqueue *vq,
|
|
void __user *argp)
|
|
{
|
|
struct vhost_vring_state s;
|
|
|
|
/* Resizing ring with an active backend?
|
|
* You don't want to do that. */
|
|
if (vq->private_data)
|
|
return -EBUSY;
|
|
|
|
if (copy_from_user(&s, argp, sizeof s))
|
|
return -EFAULT;
|
|
|
|
if (!s.num || s.num > 0xffff || (s.num & (s.num - 1)))
|
|
return -EINVAL;
|
|
vq->num = s.num;
|
|
|
|
return 0;
|
|
}
|
|
|
|
static long vhost_vring_set_addr(struct vhost_dev *d,
|
|
struct vhost_virtqueue *vq,
|
|
void __user *argp)
|
|
{
|
|
struct vhost_vring_addr a;
|
|
|
|
if (copy_from_user(&a, argp, sizeof a))
|
|
return -EFAULT;
|
|
if (a.flags & ~(0x1 << VHOST_VRING_F_LOG))
|
|
return -EOPNOTSUPP;
|
|
|
|
/* For 32bit, verify that the top 32bits of the user
|
|
data are set to zero. */
|
|
if ((u64)(unsigned long)a.desc_user_addr != a.desc_user_addr ||
|
|
(u64)(unsigned long)a.used_user_addr != a.used_user_addr ||
|
|
(u64)(unsigned long)a.avail_user_addr != a.avail_user_addr)
|
|
return -EFAULT;
|
|
|
|
/* Make sure it's safe to cast pointers to vring types. */
|
|
BUILD_BUG_ON(__alignof__ *vq->avail > VRING_AVAIL_ALIGN_SIZE);
|
|
BUILD_BUG_ON(__alignof__ *vq->used > VRING_USED_ALIGN_SIZE);
|
|
if ((a.avail_user_addr & (VRING_AVAIL_ALIGN_SIZE - 1)) ||
|
|
(a.used_user_addr & (VRING_USED_ALIGN_SIZE - 1)) ||
|
|
(a.log_guest_addr & (VRING_USED_ALIGN_SIZE - 1)))
|
|
return -EINVAL;
|
|
|
|
/* We only verify access here if backend is configured.
|
|
* If it is not, we don't as size might not have been setup.
|
|
* We will verify when backend is configured. */
|
|
if (vq->private_data) {
|
|
if (!vq_access_ok(vq, vq->num,
|
|
(void __user *)(unsigned long)a.desc_user_addr,
|
|
(void __user *)(unsigned long)a.avail_user_addr,
|
|
(void __user *)(unsigned long)a.used_user_addr))
|
|
return -EINVAL;
|
|
|
|
/* Also validate log access for used ring if enabled. */
|
|
if ((a.flags & (0x1 << VHOST_VRING_F_LOG)) &&
|
|
!log_access_ok(vq->log_base, a.log_guest_addr,
|
|
vhost_get_used_size(vq, vq->num)))
|
|
return -EINVAL;
|
|
}
|
|
|
|
vq->log_used = !!(a.flags & (0x1 << VHOST_VRING_F_LOG));
|
|
vq->desc = (void __user *)(unsigned long)a.desc_user_addr;
|
|
vq->avail = (void __user *)(unsigned long)a.avail_user_addr;
|
|
vq->log_addr = a.log_guest_addr;
|
|
vq->used = (void __user *)(unsigned long)a.used_user_addr;
|
|
|
|
return 0;
|
|
}
|
|
|
|
static long vhost_vring_set_num_addr(struct vhost_dev *d,
|
|
struct vhost_virtqueue *vq,
|
|
unsigned int ioctl,
|
|
void __user *argp)
|
|
{
|
|
long r;
|
|
|
|
mutex_lock(&vq->mutex);
|
|
|
|
switch (ioctl) {
|
|
case VHOST_SET_VRING_NUM:
|
|
r = vhost_vring_set_num(d, vq, argp);
|
|
break;
|
|
case VHOST_SET_VRING_ADDR:
|
|
r = vhost_vring_set_addr(d, vq, argp);
|
|
break;
|
|
default:
|
|
BUG();
|
|
}
|
|
|
|
mutex_unlock(&vq->mutex);
|
|
|
|
return r;
|
|
}
|
|
long vhost_vring_ioctl(struct vhost_dev *d, unsigned int ioctl, void __user *argp)
|
|
{
|
|
struct file *eventfp, *filep = NULL;
|
|
bool pollstart = false, pollstop = false;
|
|
struct eventfd_ctx *ctx = NULL;
|
|
u32 __user *idxp = argp;
|
|
struct vhost_virtqueue *vq;
|
|
struct vhost_vring_state s;
|
|
struct vhost_vring_file f;
|
|
u32 idx;
|
|
long r;
|
|
|
|
r = get_user(idx, idxp);
|
|
if (r < 0)
|
|
return r;
|
|
if (idx >= d->nvqs)
|
|
return -ENOBUFS;
|
|
|
|
idx = array_index_nospec(idx, d->nvqs);
|
|
vq = d->vqs[idx];
|
|
|
|
if (ioctl == VHOST_SET_VRING_NUM ||
|
|
ioctl == VHOST_SET_VRING_ADDR) {
|
|
return vhost_vring_set_num_addr(d, vq, ioctl, argp);
|
|
}
|
|
|
|
mutex_lock(&vq->mutex);
|
|
|
|
switch (ioctl) {
|
|
case VHOST_SET_VRING_BASE:
|
|
/* Moving base with an active backend?
|
|
* You don't want to do that. */
|
|
if (vq->private_data) {
|
|
r = -EBUSY;
|
|
break;
|
|
}
|
|
if (copy_from_user(&s, argp, sizeof s)) {
|
|
r = -EFAULT;
|
|
break;
|
|
}
|
|
if (s.num > 0xffff) {
|
|
r = -EINVAL;
|
|
break;
|
|
}
|
|
vq->last_avail_idx = s.num;
|
|
/* Forget the cached index value. */
|
|
vq->avail_idx = vq->last_avail_idx;
|
|
break;
|
|
case VHOST_GET_VRING_BASE:
|
|
s.index = idx;
|
|
s.num = vq->last_avail_idx;
|
|
if (copy_to_user(argp, &s, sizeof s))
|
|
r = -EFAULT;
|
|
break;
|
|
case VHOST_SET_VRING_KICK:
|
|
if (copy_from_user(&f, argp, sizeof f)) {
|
|
r = -EFAULT;
|
|
break;
|
|
}
|
|
eventfp = f.fd == -1 ? NULL : eventfd_fget(f.fd);
|
|
if (IS_ERR(eventfp)) {
|
|
r = PTR_ERR(eventfp);
|
|
break;
|
|
}
|
|
if (eventfp != vq->kick) {
|
|
pollstop = (filep = vq->kick) != NULL;
|
|
pollstart = (vq->kick = eventfp) != NULL;
|
|
} else
|
|
filep = eventfp;
|
|
break;
|
|
case VHOST_SET_VRING_CALL:
|
|
if (copy_from_user(&f, argp, sizeof f)) {
|
|
r = -EFAULT;
|
|
break;
|
|
}
|
|
ctx = f.fd == -1 ? NULL : eventfd_ctx_fdget(f.fd);
|
|
if (IS_ERR(ctx)) {
|
|
r = PTR_ERR(ctx);
|
|
break;
|
|
}
|
|
swap(ctx, vq->call_ctx);
|
|
break;
|
|
case VHOST_SET_VRING_ERR:
|
|
if (copy_from_user(&f, argp, sizeof f)) {
|
|
r = -EFAULT;
|
|
break;
|
|
}
|
|
ctx = f.fd == -1 ? NULL : eventfd_ctx_fdget(f.fd);
|
|
if (IS_ERR(ctx)) {
|
|
r = PTR_ERR(ctx);
|
|
break;
|
|
}
|
|
swap(ctx, vq->error_ctx);
|
|
break;
|
|
case VHOST_SET_VRING_ENDIAN:
|
|
r = vhost_set_vring_endian(vq, argp);
|
|
break;
|
|
case VHOST_GET_VRING_ENDIAN:
|
|
r = vhost_get_vring_endian(vq, idx, argp);
|
|
break;
|
|
case VHOST_SET_VRING_BUSYLOOP_TIMEOUT:
|
|
if (copy_from_user(&s, argp, sizeof(s))) {
|
|
r = -EFAULT;
|
|
break;
|
|
}
|
|
vq->busyloop_timeout = s.num;
|
|
break;
|
|
case VHOST_GET_VRING_BUSYLOOP_TIMEOUT:
|
|
s.index = idx;
|
|
s.num = vq->busyloop_timeout;
|
|
if (copy_to_user(argp, &s, sizeof(s)))
|
|
r = -EFAULT;
|
|
break;
|
|
default:
|
|
r = -ENOIOCTLCMD;
|
|
}
|
|
|
|
if (pollstop && vq->handle_kick)
|
|
vhost_poll_stop(&vq->poll);
|
|
|
|
if (!IS_ERR_OR_NULL(ctx))
|
|
eventfd_ctx_put(ctx);
|
|
if (filep)
|
|
fput(filep);
|
|
|
|
if (pollstart && vq->handle_kick)
|
|
r = vhost_poll_start(&vq->poll, vq->kick);
|
|
|
|
mutex_unlock(&vq->mutex);
|
|
|
|
if (pollstop && vq->handle_kick)
|
|
vhost_poll_flush(&vq->poll);
|
|
return r;
|
|
}
|
|
EXPORT_SYMBOL_GPL(vhost_vring_ioctl);
|
|
|
|
int vhost_init_device_iotlb(struct vhost_dev *d, bool enabled)
|
|
{
|
|
struct vhost_umem *niotlb, *oiotlb;
|
|
int i;
|
|
|
|
niotlb = vhost_umem_alloc();
|
|
if (!niotlb)
|
|
return -ENOMEM;
|
|
|
|
oiotlb = d->iotlb;
|
|
d->iotlb = niotlb;
|
|
|
|
for (i = 0; i < d->nvqs; ++i) {
|
|
struct vhost_virtqueue *vq = d->vqs[i];
|
|
|
|
mutex_lock(&vq->mutex);
|
|
vq->iotlb = niotlb;
|
|
__vhost_vq_meta_reset(vq);
|
|
mutex_unlock(&vq->mutex);
|
|
}
|
|
|
|
vhost_umem_clean(oiotlb);
|
|
|
|
return 0;
|
|
}
|
|
EXPORT_SYMBOL_GPL(vhost_init_device_iotlb);
|
|
|
|
/* Caller must have device mutex */
|
|
long vhost_dev_ioctl(struct vhost_dev *d, unsigned int ioctl, void __user *argp)
|
|
{
|
|
struct eventfd_ctx *ctx;
|
|
u64 p;
|
|
long r;
|
|
int i, fd;
|
|
|
|
/* If you are not the owner, you can become one */
|
|
if (ioctl == VHOST_SET_OWNER) {
|
|
r = vhost_dev_set_owner(d);
|
|
goto done;
|
|
}
|
|
|
|
/* You must be the owner to do anything else */
|
|
r = vhost_dev_check_owner(d);
|
|
if (r)
|
|
goto done;
|
|
|
|
switch (ioctl) {
|
|
case VHOST_SET_MEM_TABLE:
|
|
r = vhost_set_memory(d, argp);
|
|
break;
|
|
case VHOST_SET_LOG_BASE:
|
|
if (copy_from_user(&p, argp, sizeof p)) {
|
|
r = -EFAULT;
|
|
break;
|
|
}
|
|
if ((u64)(unsigned long)p != p) {
|
|
r = -EFAULT;
|
|
break;
|
|
}
|
|
for (i = 0; i < d->nvqs; ++i) {
|
|
struct vhost_virtqueue *vq;
|
|
void __user *base = (void __user *)(unsigned long)p;
|
|
vq = d->vqs[i];
|
|
mutex_lock(&vq->mutex);
|
|
/* If ring is inactive, will check when it's enabled. */
|
|
if (vq->private_data && !vq_log_access_ok(vq, base))
|
|
r = -EFAULT;
|
|
else
|
|
vq->log_base = base;
|
|
mutex_unlock(&vq->mutex);
|
|
}
|
|
break;
|
|
case VHOST_SET_LOG_FD:
|
|
r = get_user(fd, (int __user *)argp);
|
|
if (r < 0)
|
|
break;
|
|
ctx = fd == -1 ? NULL : eventfd_ctx_fdget(fd);
|
|
if (IS_ERR(ctx)) {
|
|
r = PTR_ERR(ctx);
|
|
break;
|
|
}
|
|
swap(ctx, d->log_ctx);
|
|
for (i = 0; i < d->nvqs; ++i) {
|
|
mutex_lock(&d->vqs[i]->mutex);
|
|
d->vqs[i]->log_ctx = d->log_ctx;
|
|
mutex_unlock(&d->vqs[i]->mutex);
|
|
}
|
|
if (ctx)
|
|
eventfd_ctx_put(ctx);
|
|
break;
|
|
default:
|
|
r = -ENOIOCTLCMD;
|
|
break;
|
|
}
|
|
done:
|
|
return r;
|
|
}
|
|
EXPORT_SYMBOL_GPL(vhost_dev_ioctl);
|
|
|
|
/* TODO: This is really inefficient. We need something like get_user()
|
|
* (instruction directly accesses the data, with an exception table entry
|
|
* returning -EFAULT). See Documentation/x86/exception-tables.rst.
|
|
*/
|
|
static int set_bit_to_user(int nr, void __user *addr)
|
|
{
|
|
unsigned long log = (unsigned long)addr;
|
|
struct page *page;
|
|
void *base;
|
|
int bit = nr + (log % PAGE_SIZE) * 8;
|
|
int r;
|
|
|
|
r = get_user_pages_fast(log, 1, FOLL_WRITE, &page);
|
|
if (r < 0)
|
|
return r;
|
|
BUG_ON(r != 1);
|
|
base = kmap_atomic(page);
|
|
set_bit(bit, base);
|
|
kunmap_atomic(base);
|
|
set_page_dirty_lock(page);
|
|
put_page(page);
|
|
return 0;
|
|
}
|
|
|
|
static int log_write(void __user *log_base,
|
|
u64 write_address, u64 write_length)
|
|
{
|
|
u64 write_page = write_address / VHOST_PAGE_SIZE;
|
|
int r;
|
|
|
|
if (!write_length)
|
|
return 0;
|
|
write_length += write_address % VHOST_PAGE_SIZE;
|
|
for (;;) {
|
|
u64 base = (u64)(unsigned long)log_base;
|
|
u64 log = base + write_page / 8;
|
|
int bit = write_page % 8;
|
|
if ((u64)(unsigned long)log != log)
|
|
return -EFAULT;
|
|
r = set_bit_to_user(bit, (void __user *)(unsigned long)log);
|
|
if (r < 0)
|
|
return r;
|
|
if (write_length <= VHOST_PAGE_SIZE)
|
|
break;
|
|
write_length -= VHOST_PAGE_SIZE;
|
|
write_page += 1;
|
|
}
|
|
return r;
|
|
}
|
|
|
|
static int log_write_hva(struct vhost_virtqueue *vq, u64 hva, u64 len)
|
|
{
|
|
struct vhost_umem *umem = vq->umem;
|
|
struct vhost_umem_node *u;
|
|
u64 start, end, l, min;
|
|
int r;
|
|
bool hit = false;
|
|
|
|
while (len) {
|
|
min = len;
|
|
/* More than one GPAs can be mapped into a single HVA. So
|
|
* iterate all possible umems here to be safe.
|
|
*/
|
|
list_for_each_entry(u, &umem->umem_list, link) {
|
|
if (u->userspace_addr > hva - 1 + len ||
|
|
u->userspace_addr - 1 + u->size < hva)
|
|
continue;
|
|
start = max(u->userspace_addr, hva);
|
|
end = min(u->userspace_addr - 1 + u->size,
|
|
hva - 1 + len);
|
|
l = end - start + 1;
|
|
r = log_write(vq->log_base,
|
|
u->start + start - u->userspace_addr,
|
|
l);
|
|
if (r < 0)
|
|
return r;
|
|
hit = true;
|
|
min = min(l, min);
|
|
}
|
|
|
|
if (!hit)
|
|
return -EFAULT;
|
|
|
|
len -= min;
|
|
hva += min;
|
|
}
|
|
|
|
return 0;
|
|
}
|
|
|
|
static int log_used(struct vhost_virtqueue *vq, u64 used_offset, u64 len)
|
|
{
|
|
struct iovec iov[64];
|
|
int i, ret;
|
|
|
|
if (!vq->iotlb)
|
|
return log_write(vq->log_base, vq->log_addr + used_offset, len);
|
|
|
|
ret = translate_desc(vq, (uintptr_t)vq->used + used_offset,
|
|
len, iov, 64, VHOST_ACCESS_WO);
|
|
if (ret < 0)
|
|
return ret;
|
|
|
|
for (i = 0; i < ret; i++) {
|
|
ret = log_write_hva(vq, (uintptr_t)iov[i].iov_base,
|
|
iov[i].iov_len);
|
|
if (ret)
|
|
return ret;
|
|
}
|
|
|
|
return 0;
|
|
}
|
|
|
|
int vhost_log_write(struct vhost_virtqueue *vq, struct vhost_log *log,
|
|
unsigned int log_num, u64 len, struct iovec *iov, int count)
|
|
{
|
|
int i, r;
|
|
|
|
/* Make sure data written is seen before log. */
|
|
smp_wmb();
|
|
|
|
if (vq->iotlb) {
|
|
for (i = 0; i < count; i++) {
|
|
r = log_write_hva(vq, (uintptr_t)iov[i].iov_base,
|
|
iov[i].iov_len);
|
|
if (r < 0)
|
|
return r;
|
|
}
|
|
return 0;
|
|
}
|
|
|
|
for (i = 0; i < log_num; ++i) {
|
|
u64 l = min(log[i].len, len);
|
|
r = log_write(vq->log_base, log[i].addr, l);
|
|
if (r < 0)
|
|
return r;
|
|
len -= l;
|
|
if (!len) {
|
|
if (vq->log_ctx)
|
|
eventfd_signal(vq->log_ctx, 1);
|
|
return 0;
|
|
}
|
|
}
|
|
/* Length written exceeds what we have stored. This is a bug. */
|
|
BUG();
|
|
return 0;
|
|
}
|
|
EXPORT_SYMBOL_GPL(vhost_log_write);
|
|
|
|
static int vhost_update_used_flags(struct vhost_virtqueue *vq)
|
|
{
|
|
void __user *used;
|
|
if (vhost_put_used_flags(vq))
|
|
return -EFAULT;
|
|
if (unlikely(vq->log_used)) {
|
|
/* Make sure the flag is seen before log. */
|
|
smp_wmb();
|
|
/* Log used flag write. */
|
|
used = &vq->used->flags;
|
|
log_used(vq, (used - (void __user *)vq->used),
|
|
sizeof vq->used->flags);
|
|
if (vq->log_ctx)
|
|
eventfd_signal(vq->log_ctx, 1);
|
|
}
|
|
return 0;
|
|
}
|
|
|
|
static int vhost_update_avail_event(struct vhost_virtqueue *vq, u16 avail_event)
|
|
{
|
|
if (vhost_put_avail_event(vq))
|
|
return -EFAULT;
|
|
if (unlikely(vq->log_used)) {
|
|
void __user *used;
|
|
/* Make sure the event is seen before log. */
|
|
smp_wmb();
|
|
/* Log avail event write */
|
|
used = vhost_avail_event(vq);
|
|
log_used(vq, (used - (void __user *)vq->used),
|
|
sizeof *vhost_avail_event(vq));
|
|
if (vq->log_ctx)
|
|
eventfd_signal(vq->log_ctx, 1);
|
|
}
|
|
return 0;
|
|
}
|
|
|
|
int vhost_vq_init_access(struct vhost_virtqueue *vq)
|
|
{
|
|
__virtio16 last_used_idx;
|
|
int r;
|
|
bool is_le = vq->is_le;
|
|
|
|
if (!vq->private_data)
|
|
return 0;
|
|
|
|
vhost_init_is_le(vq);
|
|
|
|
r = vhost_update_used_flags(vq);
|
|
if (r)
|
|
goto err;
|
|
vq->signalled_used_valid = false;
|
|
if (!vq->iotlb &&
|
|
!access_ok(&vq->used->idx, sizeof vq->used->idx)) {
|
|
r = -EFAULT;
|
|
goto err;
|
|
}
|
|
r = vhost_get_used_idx(vq, &last_used_idx);
|
|
if (r) {
|
|
vq_err(vq, "Can't access used idx at %p\n",
|
|
&vq->used->idx);
|
|
goto err;
|
|
}
|
|
vq->last_used_idx = vhost16_to_cpu(vq, last_used_idx);
|
|
return 0;
|
|
|
|
err:
|
|
vq->is_le = is_le;
|
|
return r;
|
|
}
|
|
EXPORT_SYMBOL_GPL(vhost_vq_init_access);
|
|
|
|
static int translate_desc(struct vhost_virtqueue *vq, u64 addr, u32 len,
|
|
struct iovec iov[], int iov_size, int access)
|
|
{
|
|
const struct vhost_umem_node *node;
|
|
struct vhost_dev *dev = vq->dev;
|
|
struct vhost_umem *umem = dev->iotlb ? dev->iotlb : dev->umem;
|
|
struct iovec *_iov;
|
|
u64 s = 0, last = addr + len - 1;
|
|
int ret = 0;
|
|
|
|
while ((u64)len > s) {
|
|
u64 size;
|
|
if (unlikely(ret >= iov_size)) {
|
|
ret = -ENOBUFS;
|
|
break;
|
|
}
|
|
|
|
node = vhost_umem_interval_tree_iter_first(&umem->umem_tree,
|
|
addr, last);
|
|
if (node == NULL || node->start > addr) {
|
|
if (umem != dev->iotlb) {
|
|
ret = -EFAULT;
|
|
break;
|
|
}
|
|
ret = -EAGAIN;
|
|
break;
|
|
} else if (!(node->perm & access)) {
|
|
ret = -EPERM;
|
|
break;
|
|
}
|
|
|
|
_iov = iov + ret;
|
|
size = node->size - addr + node->start;
|
|
_iov->iov_len = min((u64)len - s, size);
|
|
_iov->iov_base = (void __user *)(unsigned long)
|
|
(node->userspace_addr + addr - node->start);
|
|
s += size;
|
|
addr += size;
|
|
++ret;
|
|
}
|
|
|
|
if (ret == -EAGAIN)
|
|
vhost_iotlb_miss(vq, addr, access);
|
|
return ret;
|
|
}
|
|
|
|
/* Each buffer in the virtqueues is actually a chain of descriptors. This
|
|
* function returns the next descriptor in the chain,
|
|
* or -1U if we're at the end. */
|
|
static unsigned next_desc(struct vhost_virtqueue *vq, struct vring_desc *desc)
|
|
{
|
|
unsigned int next;
|
|
|
|
/* If this descriptor says it doesn't chain, we're done. */
|
|
if (!(desc->flags & cpu_to_vhost16(vq, VRING_DESC_F_NEXT)))
|
|
return -1U;
|
|
|
|
/* Check they're not leading us off end of descriptors. */
|
|
next = vhost16_to_cpu(vq, READ_ONCE(desc->next));
|
|
return next;
|
|
}
|
|
|
|
static int get_indirect(struct vhost_virtqueue *vq,
|
|
struct iovec iov[], unsigned int iov_size,
|
|
unsigned int *out_num, unsigned int *in_num,
|
|
struct vhost_log *log, unsigned int *log_num,
|
|
struct vring_desc *indirect)
|
|
{
|
|
struct vring_desc desc;
|
|
unsigned int i = 0, count, found = 0;
|
|
u32 len = vhost32_to_cpu(vq, indirect->len);
|
|
struct iov_iter from;
|
|
int ret, access;
|
|
|
|
/* Sanity check */
|
|
if (unlikely(len % sizeof desc)) {
|
|
vq_err(vq, "Invalid length in indirect descriptor: "
|
|
"len 0x%llx not multiple of 0x%zx\n",
|
|
(unsigned long long)len,
|
|
sizeof desc);
|
|
return -EINVAL;
|
|
}
|
|
|
|
ret = translate_desc(vq, vhost64_to_cpu(vq, indirect->addr), len, vq->indirect,
|
|
UIO_MAXIOV, VHOST_ACCESS_RO);
|
|
if (unlikely(ret < 0)) {
|
|
if (ret != -EAGAIN)
|
|
vq_err(vq, "Translation failure %d in indirect.\n", ret);
|
|
return ret;
|
|
}
|
|
iov_iter_init(&from, READ, vq->indirect, ret, len);
|
|
|
|
/* We will use the result as an address to read from, so most
|
|
* architectures only need a compiler barrier here. */
|
|
read_barrier_depends();
|
|
|
|
count = len / sizeof desc;
|
|
/* Buffers are chained via a 16 bit next field, so
|
|
* we can have at most 2^16 of these. */
|
|
if (unlikely(count > USHRT_MAX + 1)) {
|
|
vq_err(vq, "Indirect buffer length too big: %d\n",
|
|
indirect->len);
|
|
return -E2BIG;
|
|
}
|
|
|
|
do {
|
|
unsigned iov_count = *in_num + *out_num;
|
|
if (unlikely(++found > count)) {
|
|
vq_err(vq, "Loop detected: last one at %u "
|
|
"indirect size %u\n",
|
|
i, count);
|
|
return -EINVAL;
|
|
}
|
|
if (unlikely(!copy_from_iter_full(&desc, sizeof(desc), &from))) {
|
|
vq_err(vq, "Failed indirect descriptor: idx %d, %zx\n",
|
|
i, (size_t)vhost64_to_cpu(vq, indirect->addr) + i * sizeof desc);
|
|
return -EINVAL;
|
|
}
|
|
if (unlikely(desc.flags & cpu_to_vhost16(vq, VRING_DESC_F_INDIRECT))) {
|
|
vq_err(vq, "Nested indirect descriptor: idx %d, %zx\n",
|
|
i, (size_t)vhost64_to_cpu(vq, indirect->addr) + i * sizeof desc);
|
|
return -EINVAL;
|
|
}
|
|
|
|
if (desc.flags & cpu_to_vhost16(vq, VRING_DESC_F_WRITE))
|
|
access = VHOST_ACCESS_WO;
|
|
else
|
|
access = VHOST_ACCESS_RO;
|
|
|
|
ret = translate_desc(vq, vhost64_to_cpu(vq, desc.addr),
|
|
vhost32_to_cpu(vq, desc.len), iov + iov_count,
|
|
iov_size - iov_count, access);
|
|
if (unlikely(ret < 0)) {
|
|
if (ret != -EAGAIN)
|
|
vq_err(vq, "Translation failure %d indirect idx %d\n",
|
|
ret, i);
|
|
return ret;
|
|
}
|
|
/* If this is an input descriptor, increment that count. */
|
|
if (access == VHOST_ACCESS_WO) {
|
|
*in_num += ret;
|
|
if (unlikely(log && ret)) {
|
|
log[*log_num].addr = vhost64_to_cpu(vq, desc.addr);
|
|
log[*log_num].len = vhost32_to_cpu(vq, desc.len);
|
|
++*log_num;
|
|
}
|
|
} else {
|
|
/* If it's an output descriptor, they're all supposed
|
|
* to come before any input descriptors. */
|
|
if (unlikely(*in_num)) {
|
|
vq_err(vq, "Indirect descriptor "
|
|
"has out after in: idx %d\n", i);
|
|
return -EINVAL;
|
|
}
|
|
*out_num += ret;
|
|
}
|
|
} while ((i = next_desc(vq, &desc)) != -1);
|
|
return 0;
|
|
}
|
|
|
|
/* This looks in the virtqueue and for the first available buffer, and converts
|
|
* it to an iovec for convenient access. Since descriptors consist of some
|
|
* number of output then some number of input descriptors, it's actually two
|
|
* iovecs, but we pack them into one and note how many of each there were.
|
|
*
|
|
* This function returns the descriptor number found, or vq->num (which is
|
|
* never a valid descriptor number) if none was found. A negative code is
|
|
* returned on error. */
|
|
int vhost_get_vq_desc(struct vhost_virtqueue *vq,
|
|
struct iovec iov[], unsigned int iov_size,
|
|
unsigned int *out_num, unsigned int *in_num,
|
|
struct vhost_log *log, unsigned int *log_num)
|
|
{
|
|
struct vring_desc desc;
|
|
unsigned int i, head, found = 0;
|
|
u16 last_avail_idx;
|
|
__virtio16 avail_idx;
|
|
__virtio16 ring_head;
|
|
int ret, access;
|
|
|
|
/* Check it isn't doing very strange things with descriptor numbers. */
|
|
last_avail_idx = vq->last_avail_idx;
|
|
|
|
if (vq->avail_idx == vq->last_avail_idx) {
|
|
if (unlikely(vhost_get_avail_idx(vq, &avail_idx))) {
|
|
vq_err(vq, "Failed to access avail idx at %p\n",
|
|
&vq->avail->idx);
|
|
return -EFAULT;
|
|
}
|
|
vq->avail_idx = vhost16_to_cpu(vq, avail_idx);
|
|
|
|
if (unlikely((u16)(vq->avail_idx - last_avail_idx) > vq->num)) {
|
|
vq_err(vq, "Guest moved used index from %u to %u",
|
|
last_avail_idx, vq->avail_idx);
|
|
return -EFAULT;
|
|
}
|
|
|
|
/* If there's nothing new since last we looked, return
|
|
* invalid.
|
|
*/
|
|
if (vq->avail_idx == last_avail_idx)
|
|
return vq->num;
|
|
|
|
/* Only get avail ring entries after they have been
|
|
* exposed by guest.
|
|
*/
|
|
smp_rmb();
|
|
}
|
|
|
|
/* Grab the next descriptor number they're advertising, and increment
|
|
* the index we've seen. */
|
|
if (unlikely(vhost_get_avail_head(vq, &ring_head, last_avail_idx))) {
|
|
vq_err(vq, "Failed to read head: idx %d address %p\n",
|
|
last_avail_idx,
|
|
&vq->avail->ring[last_avail_idx % vq->num]);
|
|
return -EFAULT;
|
|
}
|
|
|
|
head = vhost16_to_cpu(vq, ring_head);
|
|
|
|
/* If their number is silly, that's an error. */
|
|
if (unlikely(head >= vq->num)) {
|
|
vq_err(vq, "Guest says index %u > %u is available",
|
|
head, vq->num);
|
|
return -EINVAL;
|
|
}
|
|
|
|
/* When we start there are none of either input nor output. */
|
|
*out_num = *in_num = 0;
|
|
if (unlikely(log))
|
|
*log_num = 0;
|
|
|
|
i = head;
|
|
do {
|
|
unsigned iov_count = *in_num + *out_num;
|
|
if (unlikely(i >= vq->num)) {
|
|
vq_err(vq, "Desc index is %u > %u, head = %u",
|
|
i, vq->num, head);
|
|
return -EINVAL;
|
|
}
|
|
if (unlikely(++found > vq->num)) {
|
|
vq_err(vq, "Loop detected: last one at %u "
|
|
"vq size %u head %u\n",
|
|
i, vq->num, head);
|
|
return -EINVAL;
|
|
}
|
|
ret = vhost_get_desc(vq, &desc, i);
|
|
if (unlikely(ret)) {
|
|
vq_err(vq, "Failed to get descriptor: idx %d addr %p\n",
|
|
i, vq->desc + i);
|
|
return -EFAULT;
|
|
}
|
|
if (desc.flags & cpu_to_vhost16(vq, VRING_DESC_F_INDIRECT)) {
|
|
ret = get_indirect(vq, iov, iov_size,
|
|
out_num, in_num,
|
|
log, log_num, &desc);
|
|
if (unlikely(ret < 0)) {
|
|
if (ret != -EAGAIN)
|
|
vq_err(vq, "Failure detected "
|
|
"in indirect descriptor at idx %d\n", i);
|
|
return ret;
|
|
}
|
|
continue;
|
|
}
|
|
|
|
if (desc.flags & cpu_to_vhost16(vq, VRING_DESC_F_WRITE))
|
|
access = VHOST_ACCESS_WO;
|
|
else
|
|
access = VHOST_ACCESS_RO;
|
|
ret = translate_desc(vq, vhost64_to_cpu(vq, desc.addr),
|
|
vhost32_to_cpu(vq, desc.len), iov + iov_count,
|
|
iov_size - iov_count, access);
|
|
if (unlikely(ret < 0)) {
|
|
if (ret != -EAGAIN)
|
|
vq_err(vq, "Translation failure %d descriptor idx %d\n",
|
|
ret, i);
|
|
return ret;
|
|
}
|
|
if (access == VHOST_ACCESS_WO) {
|
|
/* If this is an input descriptor,
|
|
* increment that count. */
|
|
*in_num += ret;
|
|
if (unlikely(log && ret)) {
|
|
log[*log_num].addr = vhost64_to_cpu(vq, desc.addr);
|
|
log[*log_num].len = vhost32_to_cpu(vq, desc.len);
|
|
++*log_num;
|
|
}
|
|
} else {
|
|
/* If it's an output descriptor, they're all supposed
|
|
* to come before any input descriptors. */
|
|
if (unlikely(*in_num)) {
|
|
vq_err(vq, "Descriptor has out after in: "
|
|
"idx %d\n", i);
|
|
return -EINVAL;
|
|
}
|
|
*out_num += ret;
|
|
}
|
|
} while ((i = next_desc(vq, &desc)) != -1);
|
|
|
|
/* On success, increment avail index. */
|
|
vq->last_avail_idx++;
|
|
|
|
/* Assume notifications from guest are disabled at this point,
|
|
* if they aren't we would need to update avail_event index. */
|
|
BUG_ON(!(vq->used_flags & VRING_USED_F_NO_NOTIFY));
|
|
return head;
|
|
}
|
|
EXPORT_SYMBOL_GPL(vhost_get_vq_desc);
|
|
|
|
/* Reverse the effect of vhost_get_vq_desc. Useful for error handling. */
|
|
void vhost_discard_vq_desc(struct vhost_virtqueue *vq, int n)
|
|
{
|
|
vq->last_avail_idx -= n;
|
|
}
|
|
EXPORT_SYMBOL_GPL(vhost_discard_vq_desc);
|
|
|
|
/* After we've used one of their buffers, we tell them about it. We'll then
|
|
* want to notify the guest, using eventfd. */
|
|
int vhost_add_used(struct vhost_virtqueue *vq, unsigned int head, int len)
|
|
{
|
|
struct vring_used_elem heads = {
|
|
cpu_to_vhost32(vq, head),
|
|
cpu_to_vhost32(vq, len)
|
|
};
|
|
|
|
return vhost_add_used_n(vq, &heads, 1);
|
|
}
|
|
EXPORT_SYMBOL_GPL(vhost_add_used);
|
|
|
|
static int __vhost_add_used_n(struct vhost_virtqueue *vq,
|
|
struct vring_used_elem *heads,
|
|
unsigned count)
|
|
{
|
|
struct vring_used_elem __user *used;
|
|
u16 old, new;
|
|
int start;
|
|
|
|
start = vq->last_used_idx & (vq->num - 1);
|
|
used = vq->used->ring + start;
|
|
if (vhost_put_used(vq, heads, start, count)) {
|
|
vq_err(vq, "Failed to write used");
|
|
return -EFAULT;
|
|
}
|
|
if (unlikely(vq->log_used)) {
|
|
/* Make sure data is seen before log. */
|
|
smp_wmb();
|
|
/* Log used ring entry write. */
|
|
log_used(vq, ((void __user *)used - (void __user *)vq->used),
|
|
count * sizeof *used);
|
|
}
|
|
old = vq->last_used_idx;
|
|
new = (vq->last_used_idx += count);
|
|
/* If the driver never bothers to signal in a very long while,
|
|
* used index might wrap around. If that happens, invalidate
|
|
* signalled_used index we stored. TODO: make sure driver
|
|
* signals at least once in 2^16 and remove this. */
|
|
if (unlikely((u16)(new - vq->signalled_used) < (u16)(new - old)))
|
|
vq->signalled_used_valid = false;
|
|
return 0;
|
|
}
|
|
|
|
/* After we've used one of their buffers, we tell them about it. We'll then
|
|
* want to notify the guest, using eventfd. */
|
|
int vhost_add_used_n(struct vhost_virtqueue *vq, struct vring_used_elem *heads,
|
|
unsigned count)
|
|
{
|
|
int start, n, r;
|
|
|
|
start = vq->last_used_idx & (vq->num - 1);
|
|
n = vq->num - start;
|
|
if (n < count) {
|
|
r = __vhost_add_used_n(vq, heads, n);
|
|
if (r < 0)
|
|
return r;
|
|
heads += n;
|
|
count -= n;
|
|
}
|
|
r = __vhost_add_used_n(vq, heads, count);
|
|
|
|
/* Make sure buffer is written before we update index. */
|
|
smp_wmb();
|
|
if (vhost_put_used_idx(vq)) {
|
|
vq_err(vq, "Failed to increment used idx");
|
|
return -EFAULT;
|
|
}
|
|
if (unlikely(vq->log_used)) {
|
|
/* Make sure used idx is seen before log. */
|
|
smp_wmb();
|
|
/* Log used index update. */
|
|
log_used(vq, offsetof(struct vring_used, idx),
|
|
sizeof vq->used->idx);
|
|
if (vq->log_ctx)
|
|
eventfd_signal(vq->log_ctx, 1);
|
|
}
|
|
return r;
|
|
}
|
|
EXPORT_SYMBOL_GPL(vhost_add_used_n);
|
|
|
|
static bool vhost_notify(struct vhost_dev *dev, struct vhost_virtqueue *vq)
|
|
{
|
|
__u16 old, new;
|
|
__virtio16 event;
|
|
bool v;
|
|
/* Flush out used index updates. This is paired
|
|
* with the barrier that the Guest executes when enabling
|
|
* interrupts. */
|
|
smp_mb();
|
|
|
|
if (vhost_has_feature(vq, VIRTIO_F_NOTIFY_ON_EMPTY) &&
|
|
unlikely(vq->avail_idx == vq->last_avail_idx))
|
|
return true;
|
|
|
|
if (!vhost_has_feature(vq, VIRTIO_RING_F_EVENT_IDX)) {
|
|
__virtio16 flags;
|
|
if (vhost_get_avail_flags(vq, &flags)) {
|
|
vq_err(vq, "Failed to get flags");
|
|
return true;
|
|
}
|
|
return !(flags & cpu_to_vhost16(vq, VRING_AVAIL_F_NO_INTERRUPT));
|
|
}
|
|
old = vq->signalled_used;
|
|
v = vq->signalled_used_valid;
|
|
new = vq->signalled_used = vq->last_used_idx;
|
|
vq->signalled_used_valid = true;
|
|
|
|
if (unlikely(!v))
|
|
return true;
|
|
|
|
if (vhost_get_used_event(vq, &event)) {
|
|
vq_err(vq, "Failed to get used event idx");
|
|
return true;
|
|
}
|
|
return vring_need_event(vhost16_to_cpu(vq, event), new, old);
|
|
}
|
|
|
|
/* This actually signals the guest, using eventfd. */
|
|
void vhost_signal(struct vhost_dev *dev, struct vhost_virtqueue *vq)
|
|
{
|
|
/* Signal the Guest tell them we used something up. */
|
|
if (vq->call_ctx && vhost_notify(dev, vq))
|
|
eventfd_signal(vq->call_ctx, 1);
|
|
}
|
|
EXPORT_SYMBOL_GPL(vhost_signal);
|
|
|
|
/* And here's the combo meal deal. Supersize me! */
|
|
void vhost_add_used_and_signal(struct vhost_dev *dev,
|
|
struct vhost_virtqueue *vq,
|
|
unsigned int head, int len)
|
|
{
|
|
vhost_add_used(vq, head, len);
|
|
vhost_signal(dev, vq);
|
|
}
|
|
EXPORT_SYMBOL_GPL(vhost_add_used_and_signal);
|
|
|
|
/* multi-buffer version of vhost_add_used_and_signal */
|
|
void vhost_add_used_and_signal_n(struct vhost_dev *dev,
|
|
struct vhost_virtqueue *vq,
|
|
struct vring_used_elem *heads, unsigned count)
|
|
{
|
|
vhost_add_used_n(vq, heads, count);
|
|
vhost_signal(dev, vq);
|
|
}
|
|
EXPORT_SYMBOL_GPL(vhost_add_used_and_signal_n);
|
|
|
|
/* return true if we're sure that avaiable ring is empty */
|
|
bool vhost_vq_avail_empty(struct vhost_dev *dev, struct vhost_virtqueue *vq)
|
|
{
|
|
__virtio16 avail_idx;
|
|
int r;
|
|
|
|
if (vq->avail_idx != vq->last_avail_idx)
|
|
return false;
|
|
|
|
r = vhost_get_avail_idx(vq, &avail_idx);
|
|
if (unlikely(r))
|
|
return false;
|
|
vq->avail_idx = vhost16_to_cpu(vq, avail_idx);
|
|
|
|
return vq->avail_idx == vq->last_avail_idx;
|
|
}
|
|
EXPORT_SYMBOL_GPL(vhost_vq_avail_empty);
|
|
|
|
/* OK, now we need to know about added descriptors. */
|
|
bool vhost_enable_notify(struct vhost_dev *dev, struct vhost_virtqueue *vq)
|
|
{
|
|
__virtio16 avail_idx;
|
|
int r;
|
|
|
|
if (!(vq->used_flags & VRING_USED_F_NO_NOTIFY))
|
|
return false;
|
|
vq->used_flags &= ~VRING_USED_F_NO_NOTIFY;
|
|
if (!vhost_has_feature(vq, VIRTIO_RING_F_EVENT_IDX)) {
|
|
r = vhost_update_used_flags(vq);
|
|
if (r) {
|
|
vq_err(vq, "Failed to enable notification at %p: %d\n",
|
|
&vq->used->flags, r);
|
|
return false;
|
|
}
|
|
} else {
|
|
r = vhost_update_avail_event(vq, vq->avail_idx);
|
|
if (r) {
|
|
vq_err(vq, "Failed to update avail event index at %p: %d\n",
|
|
vhost_avail_event(vq), r);
|
|
return false;
|
|
}
|
|
}
|
|
/* They could have slipped one in as we were doing that: make
|
|
* sure it's written, then check again. */
|
|
smp_mb();
|
|
r = vhost_get_avail_idx(vq, &avail_idx);
|
|
if (r) {
|
|
vq_err(vq, "Failed to check avail idx at %p: %d\n",
|
|
&vq->avail->idx, r);
|
|
return false;
|
|
}
|
|
|
|
return vhost16_to_cpu(vq, avail_idx) != vq->avail_idx;
|
|
}
|
|
EXPORT_SYMBOL_GPL(vhost_enable_notify);
|
|
|
|
/* We don't need to be notified again. */
|
|
void vhost_disable_notify(struct vhost_dev *dev, struct vhost_virtqueue *vq)
|
|
{
|
|
int r;
|
|
|
|
if (vq->used_flags & VRING_USED_F_NO_NOTIFY)
|
|
return;
|
|
vq->used_flags |= VRING_USED_F_NO_NOTIFY;
|
|
if (!vhost_has_feature(vq, VIRTIO_RING_F_EVENT_IDX)) {
|
|
r = vhost_update_used_flags(vq);
|
|
if (r)
|
|
vq_err(vq, "Failed to enable notification at %p: %d\n",
|
|
&vq->used->flags, r);
|
|
}
|
|
}
|
|
EXPORT_SYMBOL_GPL(vhost_disable_notify);
|
|
|
|
/* Create a new message. */
|
|
struct vhost_msg_node *vhost_new_msg(struct vhost_virtqueue *vq, int type)
|
|
{
|
|
struct vhost_msg_node *node = kmalloc(sizeof *node, GFP_KERNEL);
|
|
if (!node)
|
|
return NULL;
|
|
|
|
/* Make sure all padding within the structure is initialized. */
|
|
memset(&node->msg, 0, sizeof node->msg);
|
|
node->vq = vq;
|
|
node->msg.type = type;
|
|
return node;
|
|
}
|
|
EXPORT_SYMBOL_GPL(vhost_new_msg);
|
|
|
|
void vhost_enqueue_msg(struct vhost_dev *dev, struct list_head *head,
|
|
struct vhost_msg_node *node)
|
|
{
|
|
spin_lock(&dev->iotlb_lock);
|
|
list_add_tail(&node->node, head);
|
|
spin_unlock(&dev->iotlb_lock);
|
|
|
|
wake_up_interruptible_poll(&dev->wait, EPOLLIN | EPOLLRDNORM);
|
|
}
|
|
EXPORT_SYMBOL_GPL(vhost_enqueue_msg);
|
|
|
|
struct vhost_msg_node *vhost_dequeue_msg(struct vhost_dev *dev,
|
|
struct list_head *head)
|
|
{
|
|
struct vhost_msg_node *node = NULL;
|
|
|
|
spin_lock(&dev->iotlb_lock);
|
|
if (!list_empty(head)) {
|
|
node = list_first_entry(head, struct vhost_msg_node,
|
|
node);
|
|
list_del(&node->node);
|
|
}
|
|
spin_unlock(&dev->iotlb_lock);
|
|
|
|
return node;
|
|
}
|
|
EXPORT_SYMBOL_GPL(vhost_dequeue_msg);
|
|
|
|
|
|
static int __init vhost_init(void)
|
|
{
|
|
return 0;
|
|
}
|
|
|
|
static void __exit vhost_exit(void)
|
|
{
|
|
}
|
|
|
|
module_init(vhost_init);
|
|
module_exit(vhost_exit);
|
|
|
|
MODULE_VERSION("0.0.1");
|
|
MODULE_LICENSE("GPL v2");
|
|
MODULE_AUTHOR("Michael S. Tsirkin");
|
|
MODULE_DESCRIPTION("Host kernel accelerator for virtio");
|