* v4.4-16.09-android-tmp: unsafe_[get|put]_user: change interface to use a error target label usercopy: remove page-spanning test for now usercopy: fix overlap check for kernel text mm/slub: support left redzone Linux 4.4.21 lib/mpi: mpi_write_sgl(): fix skipping of leading zero limbs regulator: anatop: allow regulator to be in bypass mode hwrng: exynos - Disable runtime PM on probe failure cpufreq: Fix GOV_LIMITS handling for the userspace governor metag: Fix atomic_*_return inline asm constraints scsi: fix upper bounds check of sense key in scsi_sense_key_string() ALSA: timer: fix NULL pointer dereference on memory allocation failure ALSA: timer: fix division by zero after SNDRV_TIMER_IOCTL_CONTINUE ALSA: timer: fix NULL pointer dereference in read()/ioctl() race ALSA: hda - Enable subwoofer on Dell Inspiron 7559 ALSA: hda - Add headset mic quirk for Dell Inspiron 5468 ALSA: rawmidi: Fix possible deadlock with virmidi registration ALSA: fireworks: accessing to user space outside spinlock ALSA: firewire-tascam: accessing to user space outside spinlock ALSA: usb-audio: Add sample rate inquiry quirk for B850V3 CP2114 crypto: caam - fix IV loading for authenc (giv)decryption uprobes: Fix the memcg accounting x86/apic: Do not init irq remapping if ioapic is disabled vhost/scsi: fix reuse of &vq->iov[out] in response bcache: RESERVE_PRIO is too small by one when prio_buckets() is a power of two. ubifs: Fix assertion in layout_in_gaps() ovl: fix workdir creation ovl: listxattr: use strnlen() ovl: remove posix_acl_default from workdir ovl: don't copy up opaqueness wrappers for ->i_mutex access lustre: remove unused declaration timekeeping: Avoid taking lock in NMI path with CONFIG_DEBUG_TIMEKEEPING timekeeping: Cap array access in timekeeping_debug xfs: fix superblock inprogress check ASoC: atmel_ssc_dai: Don't unconditionally reset SSC on stream startup drm/msm: fix use of copy_from_user() while holding spinlock drm: Reject page_flip for !DRIVER_MODESET drm/radeon: fix radeon_move_blit on 32bit systems s390/sclp_ctl: fix potential information leak with /dev/sclp rds: fix an infoleak in rds_inc_info_copy powerpc/tm: Avoid SLB faults in treclaim/trecheckpoint when RI=0 nvme: Call pci_disable_device on the error path. cgroup: reduce read locked section of cgroup_threadgroup_rwsem during fork block: make sure a big bio is split into at most 256 bvecs block: Fix race triggered by blk_set_queue_dying() ext4: avoid modifying checksum fields directly during checksum verification ext4: avoid deadlock when expanding inode size ext4: properly align shifted xattrs when expanding inodes ext4: fix xattr shifting when expanding inodes part 2 ext4: fix xattr shifting when expanding inodes ext4: validate that metadata blocks do not overlap superblock net: Use ns_capable_noaudit() when determining net sysctl permissions kernel: Add noaudit variant of ns_capable() KEYS: Fix ASN.1 indefinite length object parsing drivers:hv: Lock access to hyperv_mmio resource tree cxlflash: Move to exponential back-off when cmd_room is not available netfilter: x_tables: check for size overflow drm/amdgpu/cz: enable/disable vce dpm even if vce pg is disabled cred: Reject inodes with invalid ids in set_create_file_as() fs: Check for invalid i_uid in may_follow_link() IB/IPoIB: Do not set skb truesize since using one linearskb udp: properly support MSG_PEEK with truncated buffers crypto: nx-842 - Mask XERS0 bit in return value cxlflash: Fix to avoid virtual LUN failover failure cxlflash: Fix to escalate LINK_RESET also on port 1 tipc: fix nl compat regression for link statistics tipc: fix an infoleak in tipc_nl_compat_link_dump netfilter: x_tables: check for size overflow Bluetooth: Add support for Intel Bluetooth device 8265 [8087:0a2b] drm/i915: Check VBT for port presence in addition to the strap on VLV/CHV drm/i915: Only ignore eDP ports that are connected Input: xpad - move pending clear to the correct location net: thunderx: Fix link status reporting x86/hyperv: Avoid reporting bogus NMI status for Gen2 instances crypto: vmx - IV size failing on skcipher API tda10071: Fix dependency to REGMAP_I2C crypto: vmx - Fix ABI detection crypto: vmx - comply with ABIs that specify vrsave as reserved. HID: core: prevent out-of-bound readings lpfc: Fix DMA faults observed upon plugging loopback connector block: fix blk_rq_get_max_sectors for driver private requests irqchip/gicv3-its: numa: Enable workaround for Cavium thunderx erratum 23144 clocksource: Allow unregistering the watchdog btrfs: Continue write in case of can_not_nocow blk-mq: End unstarted requests on dying queue cxlflash: Fix to resolve dead-lock during EEH recovery drm/radeon/mst: fix regression in lane/link handling. ecryptfs: fix handling of directory opening ALSA: hda: add AMD Polaris-10/11 AZ PCI IDs with proper driver caps drm: Balance error path for GEM handle allocation ntp: Fix ADJ_SETOFFSET being used w/ ADJ_NANO time: Verify time values in adjtimex ADJ_SETOFFSET to avoid overflow Input: xpad - correctly handle concurrent LED and FF requests net: thunderx: Fix receive packet stats net: thunderx: Fix for multiqset not configured upon interface toggle perf/x86/cqm: Fix CQM memory leak and notifier leak perf/x86/cqm: Fix CQM handling of grouping events into a cache_group s390/crypto: provide correct file mode at device register. proc: revert /proc/<pid>/maps [stack:TID] annotation intel_idle: Support for Intel Xeon Phi Processor x200 Product Family cxlflash: Fix to avoid unnecessary scan with internal LUNs Drivers: hv: vmbus: don't manipulate with clocksources on crash Drivers: hv: vmbus: avoid scheduling in interrupt context in vmbus_initiate_unload() Drivers: hv: vmbus: avoid infinite loop in init_vp_index() arcmsr: fixes not release allocated resource arcmsr: fixed getting wrong configuration data s390/pci_dma: fix DMA table corruption with > 4 TB main memory net/mlx5e: Don't modify CQ before it was created net/mlx5e: Don't try to modify CQ moderation if it is not supported mmc: sdhci: Do not BUG on invalid vdd UVC: Add support for R200 depth camera sched/numa: Fix use-after-free bug in the task_numa_compare ALSA: hda - add codec support for Kabylake display audio codec drm/i915: Fix hpd live status bits for g4x tipc: fix nullptr crash during subscription cancel arm64: Add workaround for Cavium erratum 27456 net: thunderx: Fix for Qset error due to CQ full drm/radeon: fix dp link rate selection (v2) drm/amdgpu: fix dp link rate selection (v2) qla2xxx: Use ATIO type to send correct tmr response mmc: sdhci: 64-bit DMA actually has 4-byte alignment drm/atomic: Do not unset crtc when an encoder is stolen drm/i915/skl: Add missing SKL ids drm/i915/bxt: update list of PCIIDs hrtimer: Catch illegal clockids i40e/i40evf: Fix RSS rx-flow-hash configuration through ethtool mpt3sas: Fix for Asynchronous completion of timedout IO and task abort of timedout IO. mpt3sas: A correction in unmap_resources net: cavium: liquidio: fix check for in progress flag arm64: KVM: Configure TCR_EL2.PS at runtime irqchip/gic-v3: Make sure read from ICC_IAR1_EL1 is visible on redestributor pwm: lpc32xx: fix and simplify duty cycle and period calculations pwm: lpc32xx: correct number of PWM channels from 2 to 1 pwm: fsl-ftm: Fix clock enable/disable when using PM megaraid_sas: Add an i/o barrier megaraid_sas: Fix SMAP issue megaraid_sas: Do not allow PCI access during OCR s390/cio: update measurement characteristics s390/cio: ensure consistent measurement state s390/cio: fix measurement characteristics memleak qeth: initialize net_device with carrier off lpfc: Fix external loopback failure. lpfc: Fix mbox reuse in PLOGI completion lpfc: Fix RDP Speed reporting. lpfc: Fix crash in fcp command completion path. lpfc: Fix driver crash when module parameter lpfc_fcp_io_channel set to 16 lpfc: Fix RegLogin failed error seen on Lancer FC during port bounce lpfc: Fix the FLOGI discovery logic to comply with T11 standards lpfc: Fix FCF Infinite loop in lpfc_sli4_fcf_rr_next_index_get. cxl: Enable PCI device ID for future IBM CXL adapter cxl: fix build for GCC 4.6.x cxlflash: Enable device id for future IBM CXL adapter cxlflash: Resolve oops in wait_port_offline cxlflash: Fix to resolve cmd leak after host reset cxl: Fix DSI misses when the context owning task exits cxl: Fix possible idr warning when contexts are released Drivers: hv: vmbus: fix rescind-offer handling for device without a driver Drivers: hv: vmbus: serialize process_chn_event() and vmbus_close_internal() Drivers: hv: vss: run only on supported host versions drivers/hv: cleanup synic msrs if vmbus connect failed Drivers: hv: util: catch allocation errors tools: hv: report ENOSPC errors in hv_fcopy_daemon Drivers: hv: utils: run polling callback always in interrupt context Drivers: hv: util: Increase the timeout for util services lightnvm: fix missing grown bad block type lightnvm: fix locking and mempool in rrpc_lun_gc lightnvm: unlock rq and free ppa_list on submission fail lightnvm: add check after mempool allocation lightnvm: fix incorrect nr_free_blocks stat lightnvm: fix bio submission issue cxlflash: a couple off by one bugs fm10k: Cleanup exception handling for mailbox interrupt fm10k: Cleanup MSI-X interrupts in case of failure fm10k: reinitialize queuing scheme after calling init_hw fm10k: always check init_hw for errors fm10k: reset max_queues on init_hw_vf failure fm10k: Fix handling of NAPI budget when multiple queues are enabled per vector fm10k: Correct MTU for jumbo frames fm10k: do not assume VF always has 1 queue clk: xgene: Fix divider with non-zero shift value e1000e: fix division by zero on jumbo MTUs e1000: fix data race between tx_ring->next_to_clean ixgbe: Fix handling of NAPI budget when multiple queues are enabled per vector igb: fix NULL derefs due to skipped SR-IOV enabling igb: use the correct i210 register for EEMNGCTL igb: don't unmap NULL hw_addr i40e: Fix Rx hash reported to the stack by our driver i40e: clean whole mac filter list i40evf: check rings before freeing resources i40e: don't add zero MAC filter i40e: properly delete VF MAC filters i40e: Fix memory leaks, sideband filter programming i40e: fix: do not sleep in netdev_ops i40e/i40evf: Fix RS bit update in Tx path and disable force WB workaround i40evf: handle many MAC filters correctly i40e: Workaround fix for mss < 256 issue UPSTREAM: audit: fix a double fetch in audit_log_single_execve_arg() UPSTREAM: ARM: 8494/1: mm: Enable PXN when running non-LPAE kernel on LPAE processor FIXUP: sched/tune: update accouting before CPU capacity FIXUP: sched/tune: add fixes missing from a previous patch arm: Fix #if/#ifdef typo in topology.c arm: Fix build error "conflicting types for 'scale_cpu_capacity'" sched/walt: use do_div instead of division operator DEBUG: cpufreq: fix cpu_capacity tracing build for non-smp systems sched/walt: include missing header for arm_timer_read_counter() cpufreq: Kconfig: Fixup incorrect selection by CPU_FREQ_DEFAULT_GOV_SCHED sched/fair: Avoid redundant idle_cpu() call in update_sg_lb_stats() FIXUP: sched: scheduler-driven cpu frequency selection sched/rt: Add Kconfig option to enable panicking for RT throttling sched/rt: print RT tasks when RT throttling is activated UPSTREAM: sched: Fix a race between __kthread_bind() and sched_setaffinity() sched/fair: Favor higher cpus only for boosted tasks vmstat: make vmstat_updater deferrable again and shut down on idle sched/fair: call OPP update when going idle after migration sched/cpufreq_sched: fix thermal capping events sched/fair: Picking cpus with low OPPs for tasks that prefer idle CPUs FIXUP: sched/tune: do initialization as a postcore_initicall DEBUG: sched: add tracepoint for RD overutilized sched/tune: Introducing a new schedtune attribute prefer_idle sched: use util instead of capacity to select busy cpu arch_timer: add error handling when the MPM global timer is cleared FIXUP: sched: Fix double-release of spinlock in move_queued_task FIXUP: sched/fair: Fix hang during suspend in sched_group_energy FIXUP: sched: fix SchedFreq integration for both PELT and WALT sched: EAS: Avoid causing spikes to max-freq unnecessarily FIXUP: sched: fix set_cfs_cpu_capacity when WALT is in use sched/walt: Accounting for number of irqs pending on each core sched: Introduce Window Assisted Load Tracking (WALT) sched/tune: fix PB and PC cuts indexes definition sched/fair: optimize idle cpu selection for boosted tasks FIXUP: sched/tune: fix accounting for runnable tasks sched/tune: use a single initialisation function sched/{fair,tune}: simplify fair.c code FIXUP: sched/tune: fix payoff calculation for boost region sched/tune: Add support for negative boost values FIX: sched/tune: move schedtune_nornalize_energy into fair.c FIX: sched/tune: update usage of boosted task utilisation on CPU selection sched/fair: add tunable to set initial task load sched/fair: add tunable to force selection at cpu granularity sched: EAS: take cstate into account when selecting idle core sched/cpufreq_sched: Consolidated update FIXUP: sched: fix build for non-SMP target DEBUG: sched/tune: add tracepoint on P-E space filtering DEBUG: sched/tune: add tracepoint for energy_diff() values DEBUG: sched/tune: add tracepoint for task boost signal arm: topology: Define TC2 energy and provide it to the scheduler CHROMIUM: sched: update the average of nr_running DEBUG: schedtune: add tracepoint for schedtune_tasks_update() values DEBUG: schedtune: add tracepoint for CPU boost signal DEBUG: schedtune: add tracepoint for SchedTune configuration update DEBUG: sched: add energy procfs interface DEBUG: sched,cpufreq: add cpu_capacity change tracepoint DEBUG: sched: add tracepoint for CPU load/util signals DEBUG: sched: add tracepoint for task load/util signals DEBUG: sched: add tracepoint for cpu/freq scale invariance sched/fair: filter energy_diff() based on energy_payoff value sched/tune: add support to compute normalized energy sched/fair: keep track of energy/capacity variations sched/fair: add boosted task utilization sched/{fair,tune}: track RUNNABLE tasks impact on per CPU boost value sched/tune: compute and keep track of per CPU boost value sched/tune: add initial support for CGroups based boosting sched/fair: add boosted CPU usage sched/fair: add function to convert boost value into "margin" sched/tune: add sysctl interface to define a boost value sched/tune: add detailed documentation fixup! sched/fair: jump to max OPP when crossing UP threshold fixup! sched: scheduler-driven cpu frequency selection sched: rt scheduler sets capacity requirement sched: deadline: use deadline bandwidth in scale_rt_capacity sched: remove call of sched_avg_update from sched_rt_avg_update sched/cpufreq_sched: add trace events sched/fair: jump to max OPP when crossing UP threshold sched/fair: cpufreq_sched triggers for load balancing sched/{core,fair}: trigger OPP change request on fork() sched/fair: add triggers for OPP change requests sched: scheduler-driven cpu frequency selection cpufreq: introduce cpufreq_driver_is_slow sched: Consider misfit tasks when load-balancing sched: Add group_misfit_task load-balance type sched: Add per-cpu max capacity to sched_group_capacity sched: Do eas idle balance regardless of the rq avg idle value arm64: Enable max freq invariant scheduler load-tracking and capacity support arm: Enable max freq invariant scheduler load-tracking and capacity support sched: Update max cpu capacity in case of max frequency constraints cpufreq: Max freq invariant scheduler load-tracking and cpu capacity support arm64, topology: Updates to use DT bindings for EAS costing data sched: Support for extracting EAS energy costs from DT Documentation: DT bindings for energy model cost data required by EAS sched: Disable energy-unfriendly nohz kicks sched: Consider a not over-utilized energy-aware system as balanced sched: Energy-aware wake-up task placement sched: Determine the current sched_group idle-state sched, cpuidle: Track cpuidle state index in the scheduler sched: Add over-utilization/tipping point indicator sched: Estimate energy impact of scheduling decisions sched: Extend sched_group_energy to test load-balancing decisions sched: Calculate energy consumption of sched_group sched: Highest energy aware balancing sched_domain level pointer sched: Relocated cpu_util() and change return type sched: Compute cpu capacity available at current frequency arm64: Cpu invariant scheduler load-tracking and capacity support arm: Cpu invariant scheduler load-tracking and capacity support sched: Introduce SD_SHARE_CAP_STATES sched_domain flag sched: Initialize energy data structures sched: Introduce energy data structures sched: Make energy awareness a sched feature sched: Documentation for scheduler energy cost model sched: Prevent unnecessary active balance of single task in sched group sched: Enable idle balance to pull single task towards cpu with higher capacity sched: Consider spare cpu capacity at task wake-up sched: Add cpu capacity awareness to wakeup balancing sched: Store system-wide maximum cpu capacity in root domain arm: Update arch_scale_cpu_capacity() to reflect change to define arm64: Enable frequency invariant scheduler load-tracking support arm: Enable frequency invariant scheduler load-tracking support cpufreq: Frequency invariant scheduler load-tracking support sched/fair: Fix new task's load avg removed from source CPU in wake_up_new_task() FROMLIST: pstore: drop pmsg bounce buffer UPSTREAM: usercopy: remove page-spanning test for now UPSTREAM: usercopy: force check_object_size() inline BACKPORT: usercopy: fold builtin_const check into inline function UPSTREAM: x86/uaccess: force copy_*_user() to be inlined UPSTREAM: HID: core: prevent out-of-bound readings Android: Fix build breakages. UPSTREAM: tty: Prevent ldisc drivers from re-using stale tty fields UPSTREAM: netfilter: nfnetlink: correctly validate length of batch messages cpuset: Make cpusets restore on hotplug UPSTREAM: mm/slub: support left redzone UPSTREAM: Make the hardened user-copy code depend on having a hardened allocator Android: MMC/UFS IO Latency Histograms. UPSTREAM: usercopy: fix overlap check for kernel text UPSTREAM: usercopy: avoid potentially undefined behavior in pointer math UPSTREAM: unsafe_[get|put]_user: change interface to use a error target label BACKPORT: arm64: mm: fix location of _etext BACKPORT: ARM: 8583/1: mm: fix location of _etext BACKPORT: Don't show empty tag stats for unprivileged uids UPSTREAM: tcp: fix use after free in tcp_xmit_retransmit_queue() ANDROID: base-cfg: drop SECCOMP_FILTER config UPSTREAM: [media] xc2028: unlock on error in xc2028_set_config() UPSTREAM: [media] xc2028: avoid use after free ANDROID: base-cfg: enable SECCOMP config ANDROID: rcu_sync: Export rcu_sync_lockdep_assert RFC: FROMLIST: cgroup: reduce read locked section of cgroup_threadgroup_rwsem during fork RFC: FROMLIST: cgroup: avoid synchronize_sched() in __cgroup_procs_write() RFC: FROMLIST: locking/percpu-rwsem: Optimize readers and reduce global impact net: ipv6: Fix ping to link-local addresses. ipv6: fix endianness error in icmpv6_err ANDROID: dm: android-verity: Allow android-verity to be compiled as an independent module backporting: a brief introduce of backported feautures on 4.4 Linux 4.4.20 sysfs: correctly handle read offset on PREALLOC attrs hwmon: (iio_hwmon) fix memory leak in name attribute ALSA: line6: Fix POD sysfs attributes segfault ALSA: line6: Give up on the lock while URBs are released. ALSA: line6: Remove double line6_pcm_release() after failed acquire. ACPI / SRAT: fix SRAT parsing order with both LAPIC and X2APIC present ACPI / sysfs: fix error code in get_status() ACPI / drivers: replace acpi_probe_lock spinlock with mutex ACPI / drivers: fix typo in ACPI_DECLARE_PROBE_ENTRY macro staging: comedi: ni_mio_common: fix wrong insn_write handler staging: comedi: ni_mio_common: fix AO inttrig backwards compatibility staging: comedi: comedi_test: fix timer race conditions staging: comedi: daqboard2000: bug fix board type matching code USB: serial: option: add WeTelecom 0x6802 and 0x6803 products USB: serial: option: add WeTelecom WM-D200 USB: serial: mos7840: fix non-atomic allocation in write path USB: serial: mos7720: fix non-atomic allocation in write path USB: fix typo in wMaxPacketSize validation usb: chipidea: udc: don't touch DP when controller is in host mode USB: avoid left shift by -1 dmaengine: usb-dmac: check CHCR.DE bit in usb_dmac_isr_channel() crypto: qat - fix aes-xts key sizes crypto: nx - off by one bug in nx_of_update_msc() Input: i8042 - set up shared ps2_cmd_mutex for AUX ports Input: i8042 - break load dependency between atkbd/psmouse and i8042 Input: tegra-kbc - fix inverted reset logic btrfs: properly track when rescan worker is running btrfs: waiting on qgroup rescan should not always be interruptible fs/seq_file: fix out-of-bounds read gpio: Fix OF build problem on UM usb: renesas_usbhs: gadget: fix return value check in usbhs_mod_gadget_probe() megaraid_sas: Fix probing cards without io port mpt3sas: Fix resume on WarpDrive flash cards cdc-acm: fix wrong pipe type on rx interrupt xfers i2c: cros-ec-tunnel: Fix usage of cros_ec_cmd_xfer() mfd: cros_ec: Add cros_ec_cmd_xfer_status() helper aacraid: Check size values after double-fetch from user ARC: Elide redundant setup of DMA callbacks ARC: Call trace_hardirqs_on() before enabling irqs ARC: use correct offset in pt_regs for saving/restoring user mode r25 ARC: build: Better way to detect ISA compatible toolchain drm/i915: fix aliasing_ppgtt leak drm/amdgpu: record error code when ring test failed drm/amd/amdgpu: sdma resume fail during S4 on CI drm/amdgpu: skip TV/CV in display parsing drm/amdgpu: avoid a possible array overflow drm/amdgpu: fix amdgpu_move_blit on 32bit systems drm/amdgpu: Change GART offset to 64-bit iio: fix sched WARNING "do not call blocking ops when !TASK_RUNNING" sched/nohz: Fix affine unpinned timers mess sched/cputime: Fix NO_HZ_FULL getrusage() monotonicity regression of: fix reference counting in of_graph_get_endpoint_by_regs arm64: dts: rockchip: add reset saradc node for rk3368 SoCs mac80211: fix purging multicast PS buffer queue s390/dasd: fix hanging device after clear subchannel EDAC: Increment correct counter in edac_inc_ue_error() pinctrl/amd: Remove the default de-bounce time iommu/arm-smmu: Don't BUG() if we find aborting STEs with disable_bypass iommu/arm-smmu: Fix CMDQ error handling iommu/dma: Don't put uninitialised IOVA domains xhci: Make sure xhci handles USB_SPEED_SUPER_PLUS devices. USB: serial: ftdi_sio: add PIDs for Ivium Technologies devices USB: serial: ftdi_sio: add device ID for WICED USB UART dev board USB: serial: option: add support for Telit LE920A4 USB: serial: option: add D-Link DWM-156/A3 USB: serial: fix memleak in driver-registration error path xhci: don't dereference a xhci member after removing xhci usb: xhci: Fix panic if disconnect xhci: always handle "Command Ring Stopped" events usb/gadget: fix gadgetfs aio support. usb: gadget: fsl_qe_udc: off by one in setup_received_handle() USB: validate wMaxPacketValue entries in endpoint descriptors usb: renesas_usbhs: Use dmac only if the pipe type is bulk usb: renesas_usbhs: clear the BRDYSTS in usbhsg_ep_enable() USB: hub: change the locking in hub_activate USB: hub: fix up early-exit pathway in hub_activate usb: hub: Fix unbalanced reference count/memory leak/deadlocks usb: define USB_SPEED_SUPER_PLUS speed for SuperSpeedPlus USB3.1 devices usb: dwc3: gadget: increment request->actual once usb: dwc3: pci: add Intel Kabylake PCI ID usb: misc: usbtest: add fix for driver hang usb: ehci: change order of register cleanup during shutdown crypto: caam - defer aead_set_sh_desc in case of zero authsize crypto: caam - fix echainiv(authenc) encrypt shared descriptor crypto: caam - fix non-hmac hashes genirq/msi: Make sure PCI MSIs are activated early genirq/msi: Remove unused MSI_FLAG_IDENTITY_MAP um: Don't discard .text.exit section ACPI / CPPC: Prevent cpc_desc_ptr points to the invalid data ACPI: CPPC: Return error if _CPC is invalid on a CPU mmc: sdhci-acpi: Reduce Baytrail eMMC/SD/SDIO hangs PCI: Limit config space size for Netronome NFP4000 PCI: Add Netronome NFP4000 PF device ID PCI: Limit config space size for Netronome NFP6000 family PCI: Add Netronome vendor and device IDs PCI: Support PCIe devices with short cfg_size NVMe: Don't unmap controller registers on reset ALSA: hda - Manage power well properly for resume libnvdimm, nd_blk: mask off reserved status bits perf intel-pt: Fix occasional decoding errors when tracing system-wide vfio/pci: Fix NULL pointer oops in error interrupt setup handling virtio: fix memory leak in virtqueue_add() parisc: Fix order of EREFUSED define in errno.h arm64: Define AT_VECTOR_SIZE_ARCH for ARCH_DLINFO ALSA: usb-audio: Add quirk for ELP HD USB Camera ALSA: usb-audio: Add a sample rate quirk for Creative Live! Cam Socialize HD (VF0610) powerpc/eeh: eeh_pci_enable(): fix checking of post-request state SUNRPC: allow for upcalls for same uid but different gss service SUNRPC: Handle EADDRNOTAVAIL on connection failures tools/testing/nvdimm: fix SIGTERM vs hotplug crash uprobes/x86: Fix RIP-relative handling of EVEX-encoded instructions x86/mm: Disable preemption during CR3 read+write hugetlb: fix nr_pmds accounting with shared page tables mm: SLUB hardened usercopy support mm: SLAB hardened usercopy support s390/uaccess: Enable hardened usercopy sparc/uaccess: Enable hardened usercopy powerpc/uaccess: Enable hardened usercopy ia64/uaccess: Enable hardened usercopy arm64/uaccess: Enable hardened usercopy ARM: uaccess: Enable hardened usercopy x86/uaccess: Enable hardened usercopy x86: remove more uaccess_32.h complexity x86: remove pointless uaccess_32.h complexity x86: fix SMAP in 32-bit environments Use the new batched user accesses in generic user string handling Add 'unsafe' user access functions for batched accesses x86: reorganize SMAP handling in user space accesses mm: Hardened usercopy mm: Implement stack frame object validation mm: Add is_migrate_cma_page Linux 4.4.19 Documentation/module-signing.txt: Note need for version info if reusing a key module: Invalidate signatures on force-loaded modules dm flakey: error READ bios during the down_interval rtc: s3c: Add s3c_rtc_{enable/disable}_clk in s3c_rtc_setfreq() lpfc: fix oops in lpfc_sli4_scmd_to_wqidx_distr() from lpfc_send_taskmgmt() ACPI / EC: Work around method reentrancy limit in ACPICA for _Qxx x86/platform/intel_mid_pci: Rework IRQ0 workaround PCI: Mark Atheros AR9485 and QCA9882 to avoid bus reset MIPS: hpet: Increase HPET_MIN_PROG_DELTA and decrease HPET_MIN_CYCLES MIPS: Don't register r4k sched clock when CPUFREQ enabled MIPS: mm: Fix definition of R6 cache instruction SUNRPC: Don't allocate a full sockaddr_storage for tracing Input: elan_i2c - properly wake up touchpad on ASUS laptops target: Fix ordered task CHECK_CONDITION early exception handling target: Fix max_unmap_lba_count calc overflow target: Fix race between iscsi-target connection shutdown + ABORT_TASK target: Fix missing complete during ABORT_TASK + CMD_T_FABRIC_STOP target: Fix ordered task target_setup_cmd_from_cdb exception hang iscsi-target: Fix panic when adding second TCP connection to iSCSI session ubi: Fix race condition between ubi device creation and udev ubi: Fix early logging ubi: Make volume resize power cut aware of: fix memory leak related to safe_name() IB/mlx4: Fix memory leak if QP creation failed IB/mlx4: Fix error flow when sending mads under SRIOV IB/mlx4: Fix the SQ size of an RC QP IB/IWPM: Fix a potential skb leak IB/IPoIB: Don't update neigh validity for unresolved entries IB/SA: Use correct free function IB/mlx5: Return PORT_ERR in Active to Initializing tranisition IB/mlx5: Fix post send fence logic IB/mlx5: Fix entries check in mlx5_ib_resize_cq IB/mlx5: Fix returned values of query QP IB/mlx5: Fix entries checks in mlx5_ib_create_cq IB/mlx5: Fix MODIFY_QP command input structure ALSA: hda - Fix headset mic detection problem for two dell machines ALSA: hda: add AMD Bonaire AZ PCI ID with proper driver caps ALSA: hda/realtek - Can't adjust speaker's volume on a Dell AIO ALSA: hda: Fix krealloc() with __GFP_ZERO usage mm/hugetlb: avoid soft lockup in set_max_huge_pages() mtd: nand: fix bug writing 1 byte less than page size block: fix bdi vs gendisk lifetime mismatch block: add missing group association in bio-cloning functions metag: Fix __cmpxchg_u32 asm constraint for CMP ftrace/recordmcount: Work around for addition of metag magic but not relocations balloon: check the number of available pages in leak balloon drm/i915/dp: Revert "drm/i915/dp: fall back to 18 bpp when sink capability is unknown" drm/i915: Never fully mask the the EI up rps interrupt on SNB/IVB drm/edid: Add 6 bpc quirk for display AEO model 0. drm: Restore double clflush on the last partial cacheline drm/nouveau/fbcon: fix font width not divisible by 8 drm/nouveau/gr/nv3x: fix instobj write offsets in gr setup drm/nouveau: check for supported chipset before booting fbdev off the hw drm/radeon: support backlight control for UNIPHY3 drm/radeon: fix firmware info version checks drm/radeon: Poll for both connect/disconnect on analog connectors drm/radeon: add a delay after ATPX dGPU power off drm/amdgpu/gmc7: add missing mullins case drm/amdgpu: fix firmware info version checks drm/amdgpu: Disable RPM helpers while reprobing connectors on resume drm/amdgpu: support backlight control for UNIPHY3 drm/amdgpu: Poll for both connect/disconnect on analog connectors drm/amdgpu: add a delay after ATPX dGPU power off w1:omap_hdq: fix regression netlabel: add address family checks to netlbl_{sock,req}_delattr() ARM: dts: sunxi: Add a startup delay for fixed regulator enabled phys audit: fix a double fetch in audit_log_single_execve_arg() iommu/amd: Update Alias-DTE in update_device_table() iommu/amd: Init unity mappings only for dma_ops domains iommu/amd: Handle IOMMU_DOMAIN_DMA in ops->domain_free call-back iommu/vt-d: Return error code in domain_context_mapping_one() iommu/exynos: Suppress unbinding to prevent system failure drm/i915: Don't complain about lack of ACPI video bios nfsd: don't return an unhashed lock stateid after taking mutex nfsd: Fix race between FREE_STATEID and LOCK nfs: don't create zero-length requests MIPS: KVM: Propagate kseg0/mapped tlb fault errors MIPS: KVM: Fix gfn range check in kseg0 tlb faults MIPS: KVM: Add missing gfn range check MIPS: KVM: Fix mapped fault broken commpage handling random: add interrupt callback to VMBus IRQ handler random: print a warning for the first ten uninitialized random users random: initialize the non-blocking pool via add_hwgenerator_randomness() CIFS: Fix a possible invalid memory access in smb2_query_symlink() cifs: fix crash due to race in hmac(md5) handling cifs: Check for existing directory when opening file with O_CREAT fs/cifs: make share unaccessible at root level mountable jbd2: make journal y2038 safe ARC: mm: don't loose PTE_SPECIAL in pte_modify() remoteproc: Fix potential race condition in rproc_add ovl: disallow overlayfs as upperdir HID: uhid: fix timeout when probe races with IO EDAC: Correct channel count limit Bluetooth: Fix l2cap_sock_setsockopt() with optname BT_RCVMTU spi: pxa2xx: Clear all RFT bits in reset_sccr1() on Intel Quark i2c: efm32: fix a failure path in efm32_i2c_probe() s5p-mfc: Add release callback for memory region devs s5p-mfc: Set device name for reserved memory region devs hp-wmi: Fix wifi cannot be hard-unblocked dm: set DMF_SUSPENDED* _before_ clearing DMF_NOFLUSH_SUSPENDING sur40: fix occasional oopses on device close sur40: lower poll interval to fix occasional FPS drops to ~56 FPS Fix RC5 decoding with Fintek CIR chipset vb2: core: Skip planes array verification if pb is NULL videobuf2-v4l2: Verify planes array in buffer dequeueing media: dvb_ringbuffer: Add memory barriers media: usbtv: prevent access to free'd resources mfd: qcom_rpm: Parametrize also ack selector size mfd: qcom_rpm: Fix offset error for msm8660 intel_pstate: Fix MSR_CONFIG_TDP_x addressing in core_get_max_pstate() s390/cio: allow to reset channel measurement block KVM: nVMX: Fix memory corruption when using VMCS shadowing KVM: VMX: handle PML full VMEXIT that occurs during event delivery KVM: MTRR: fix kvm_mtrr_check_gfn_range_consistency page fault KVM: PPC: Book3S HV: Save/restore TM state in H_CEDE KVM: PPC: Book3S HV: Pull out TM state save/restore into separate procedures arm64: mm: avoid fdt_check_header() before the FDT is fully mapped arm64: dts: rockchip: fixes the gic400 2nd region size for rk3368 pinctrl: cherryview: prevent concurrent access to GPIO controllers Bluetooth: hci_intel: Fix null gpio desc pointer dereference gpio: intel-mid: Remove potentially harmful code gpio: pca953x: Fix NBANK calculation for PCA9536 tty/serial: atmel: fix RS485 half duplex with DMA serial: samsung: Fix ERR pointer dereference on deferred probe tty: serial: msm: Don't read off end of tx fifo arm64: Fix incorrect per-cpu usage for boot CPU arm64: debug: unmask PSTATE.D earlier arm64: kernel: Save and restore UAO and addr_limit on exception entry USB: usbfs: fix potential infoleak in devio usb: renesas_usbhs: fix NULL pointer dereference in xfer_work() USB: serial: option: add support for Telit LE910 PID 0x1206 usb: dwc3: fix for the isoc transfer EP_BUSY flag usb: quirks: Add no-lpm quirk for Elan usb: renesas_usbhs: protect the CFIFOSEL setting in usbhsg_ep_enable() usb: f_fs: off by one bug in _ffs_func_bind() usb: gadget: avoid exposing kernel stack UPSTREAM: usb: gadget: configfs: add mutex lock before unregister gadget ANDROID: dm-verity: adopt changes made to dm callbacks UPSTREAM: ecryptfs: fix handling of directory opening ANDROID: net: core: fix UID-based routing ANDROID: net: fib: remove duplicate assignment FROMLIST: proc: Fix timerslack_ns CAP_SYS_NICE check when adjusting self ANDROID: dm verity fec: pack the fec_header structure ANDROID: dm: android-verity: Verify header before fetching table ANDROID: dm: allow adb disable-verity only in userdebug ANDROID: dm: mount as linear target if eng build ANDROID: dm: use default verity public key ANDROID: dm: fix signature verification flag ANDROID: dm: use name_to_dev_t ANDROID: dm: rename dm-linear methods for dm-android-verity ANDROID: dm: Minor cleanup ANDROID: dm: Mounting root as linear device when verity disabled ANDROID: dm-android-verity: Rebase on top of 4.1 ANDROID: dm: Add android verity target ANDROID: dm: fix dm_substitute_devices() ANDROID: dm: Rebase on top of 4.1 CHROMIUM: dm: boot time specification of dm= Implement memory_state_time, used by qcom,cpubw Revert "panic: Add board ID to panic output" usb: gadget: f_accessory: remove duplicate endpoint alloc BACKPORT: brcmfmac: defer DPC processing during probe FROMLIST: proc: Add LSM hook checks to /proc/<tid>/timerslack_ns FROMLIST: proc: Relax /proc/<tid>/timerslack_ns capability requirements UPSTREAM: ppp: defer netns reference release for ppp channel cpuset: Add allow_attach hook for cpusets on android. UPSTREAM: KEYS: Fix ASN.1 indefinite length object parsing ANDROID: sdcardfs: fix itnull.cocci warnings android-recommended.cfg: enable fstack-protector-strong Linux 4.4.18 mm: memcontrol: fix memcg id ref counter on swap charge move mm: memcontrol: fix swap counter leak on swapout from offline cgroup mm: memcontrol: fix cgroup creation failure after many small jobs ext4: fix reference counting bug on block allocation error ext4: short-cut orphan cleanup on error ext4: validate s_reserved_gdt_blocks on mount ext4: don't call ext4_should_journal_data() on the journal inode ext4: fix deadlock during page writeback ext4: check for extents that wrap around crypto: scatterwalk - Fix test in scatterwalk_done crypto: gcm - Filter out async ghash if necessary fs/dcache.c: avoid soft-lockup in dput() fuse: fix wrong assignment of ->flags in fuse_send_init() fuse: fuse_flush must check mapping->flags for errors fuse: fsync() did not return IO errors sysv, ipc: fix security-layer leaking block: fix use-after-free in seq file x86/syscalls/64: Add compat_sys_keyctl for 32-bit userspace drm/i915: Pretend cursor is always on for ILK-style WM calculations (v2) x86/mm/pat: Fix BUG_ON() in mmap_mem() on QEMU/i386 x86/pat: Document the PAT initialization sequence x86/xen, pat: Remove PAT table init code from Xen x86/mtrr: Fix PAT init handling when MTRR is disabled x86/mtrr: Fix Xorg crashes in Qemu sessions x86/mm/pat: Replace cpu_has_pat with boot_cpu_has() x86/mm/pat: Add pat_disable() interface x86/mm/pat: Add support of non-default PAT MSR setting devpts: clean up interface to pty drivers random: strengthen input validation for RNDADDTOENTCNT apparmor: fix ref count leak when profile sha1 hash is read Revert "s390/kdump: Clear subchannel ID to signal non-CCW/SCSI IPL" KEYS: 64-bit MIPS needs to use compat_sys_keyctl for 32-bit userspace arm: oabi compat: add missing access checks cdc_ncm: do not call usbnet_link_change from cdc_ncm_bind i2c: i801: Allow ACPI SystemIO OpRegion to conflict with PCI BAR x86/mm/32: Enable full randomization on i386 and X86_32 HID: sony: do not bail out when the sixaxis refuses the output report PNP: Add Broadwell to Intel MCH size workaround PNP: Add Haswell-ULT to Intel MCH size workaround scsi: ignore errors from scsi_dh_add_device() ipath: Restrict use of the write() interface tcp: consider recv buf for the initial window scale qed: Fix setting/clearing bit in completion bitmap net/irda: fix NULL pointer dereference on memory allocation failure net: bgmac: Fix infinite loop in bgmac_dma_tx_add() bonding: set carrier off for devices created through netlink ipv4: reject RTNH_F_DEAD and RTNH_F_LINKDOWN from user space tcp: enable per-socket rate limiting of all 'challenge acks' tcp: make challenge acks less predictable arm64: relocatable: suppress R_AARCH64_ABS64 relocations in vmlinux arm64: vmlinux.lds: make __rela_offset and __dynsym_offset ABSOLUTE Linux 4.4.17 vfs: fix deadlock in file_remove_privs() on overlayfs intel_th: Fix a deadlock in modprobing intel_th: pci: Add Kaby Lake PCH-H support net: mvneta: set real interrupt per packet for tx_done libceph: apply new_state before new_up_client on incrementals libata: LITE-ON CX1-JB256-HP needs lower max_sectors i2c: mux: reg: wrong condition checked for of_address_to_resource return value posix_cpu_timer: Exit early when process has been reaped media: fix airspy usb probe error path ipr: Clear interrupt on croc/crocodile when running with LSI SCSI: fix new bug in scsi_dev_info_list string matching RDS: fix rds_tcp_init() error path can: fix oops caused by wrong rtnl dellink usage can: fix handling of unmodifiable configuration options fix can: c_can: Update D_CAN TX and RX functions to 32 bit - fix Altera Cyclone access can: at91_can: RX queue could get stuck at high bus load perf/x86: fix PEBS issues on Intel Atom/Core2 ovl: handle ATTR_KILL* sched/fair: Fix effective_load() to consistently use smoothed load mmc: block: fix packed command header endianness block: fix use-after-free in sys_ioprio_get() qeth: delete napi struct when removing a qeth device platform/chrome: cros_ec_dev - double fetch bug in ioctl clk: rockchip: initialize flags of clk_init_data in mmc-phase clock spi: sun4i: fix FIFO limit spi: sunxi: fix transfer timeout namespace: update event counter when umounting a deleted dentry 9p: use file_dentry() ext4: verify extent header depth ecryptfs: don't allow mmap when the lower fs doesn't support it Revert "ecryptfs: forbid opening files without mmap handler" locks: use file_inode() power_supply: power_supply_read_temp only if use_cnt > 0 cgroup: set css->id to -1 during init pinctrl: imx: Do not treat a PIN without MUX register as an error pinctrl: single: Fix missing flush of posted write for a wakeirq pvclock: Add CPU barriers to get correct version value Input: tsc200x - report proper input_dev name Input: xpad - validate USB endpoint count during probe Input: wacom_w8001 - w8001_MAX_LENGTH should be 13 Input: xpad - fix oops when attaching an unknown Xbox One gamepad Input: elantech - add more IC body types to the list Input: vmmouse - remove port reservation ALSA: timer: Fix leak in events via snd_timer_user_tinterrupt ALSA: timer: Fix leak in events via snd_timer_user_ccallback ALSA: timer: Fix leak in SNDRV_TIMER_IOCTL_PARAMS xenbus: don't bail early from xenbus_dev_request_and_reply() xenbus: don't BUG() on user mode induced condition xen/pciback: Fix conf_space read/write overlap check. ARC: unwind: ensure that .debug_frame is generated (vs. .eh_frame) arc: unwind: warn only once if DW2_UNWIND is disabled kernel/sysrq, watchdog, sched/core: Reset watchdog on all CPUs while processing sysrq-w pps: do not crash when failed to register vmlinux.lds: account for destructor sections mm, meminit: ensure node is online before checking whether pages are uninitialised mm, meminit: always return a valid node from early_pfn_to_nid mm, compaction: prevent VM_BUG_ON when terminating freeing scanner fs/nilfs2: fix potential underflow in call to crc32_le mm, compaction: abort free scanner if split fails mm, sl[au]b: add __GFP_ATOMIC to the GFP reclaim mask dmaengine: at_xdmac: double FIFO flush needed to compute residue dmaengine: at_xdmac: fix residue corruption dmaengine: at_xdmac: align descriptors on 64 bits x86/quirks: Add early quirk to reset Apple AirPort card x86/quirks: Reintroduce scanning of secondary buses x86/quirks: Apply nvidia_bugs quirk only on root bus USB: OHCI: Don't mark EDs as ED_OPER if scheduling fails Conflicts: arch/arm/kernel/topology.c arch/arm64/include/asm/arch_gicv3.h arch/arm64/kernel/topology.c block/bio.c drivers/cpufreq/Kconfig drivers/md/Makefile drivers/media/dvb-core/dvb_ringbuffer.c drivers/media/tuners/tuner-xc2028.c drivers/misc/Kconfig drivers/misc/Makefile drivers/mmc/core/host.c drivers/scsi/ufs/ufshcd.c drivers/scsi/ufs/ufshcd.h drivers/usb/dwc3/gadget.c drivers/usb/gadget/configfs.c fs/ecryptfs/file.c include/linux/mmc/core.h include/linux/mmc/host.h include/linux/mmzone.h include/linux/sched.h include/linux/sched/sysctl.h include/trace/events/power.h include/trace/events/sched.h init/Kconfig kernel/cpuset.c kernel/exit.c kernel/sched/Makefile kernel/sched/core.c kernel/sched/cputime.c kernel/sched/fair.c kernel/sched/features.h kernel/sched/rt.c kernel/sched/sched.h kernel/sched/stop_task.c kernel/sched/tune.c lib/Kconfig.debug mm/Makefile mm/vmstat.c Change-Id: I243a43231ca56a6362076fa6301827e1b0493be5 Signed-off-by: Runmin Wang <runminw@codeaurora.org>
1788 lines
50 KiB
C
1788 lines
50 KiB
C
#ifndef _LINUX_BLKDEV_H
|
|
#define _LINUX_BLKDEV_H
|
|
|
|
#include <linux/sched.h>
|
|
|
|
#ifdef CONFIG_BLOCK
|
|
|
|
#include <linux/major.h>
|
|
#include <linux/genhd.h>
|
|
#include <linux/list.h>
|
|
#include <linux/llist.h>
|
|
#include <linux/timer.h>
|
|
#include <linux/workqueue.h>
|
|
#include <linux/pagemap.h>
|
|
#include <linux/backing-dev-defs.h>
|
|
#include <linux/wait.h>
|
|
#include <linux/mempool.h>
|
|
#include <linux/bio.h>
|
|
#include <linux/stringify.h>
|
|
#include <linux/gfp.h>
|
|
#include <linux/bsg.h>
|
|
#include <linux/smp.h>
|
|
#include <linux/rcupdate.h>
|
|
#include <linux/percpu-refcount.h>
|
|
#include <linux/scatterlist.h>
|
|
|
|
struct module;
|
|
struct scsi_ioctl_command;
|
|
|
|
struct request_queue;
|
|
struct elevator_queue;
|
|
struct blk_trace;
|
|
struct request;
|
|
struct sg_io_hdr;
|
|
struct bsg_job;
|
|
struct blkcg_gq;
|
|
struct blk_flush_queue;
|
|
struct pr_ops;
|
|
|
|
#define BLKDEV_MIN_RQ 4
|
|
#define BLKDEV_MAX_RQ 128 /* Default maximum */
|
|
|
|
/*
|
|
* Maximum number of blkcg policies allowed to be registered concurrently.
|
|
* Defined here to simplify include dependency.
|
|
*/
|
|
#define BLKCG_MAX_POLS 2
|
|
|
|
struct request;
|
|
typedef void (rq_end_io_fn)(struct request *, int);
|
|
|
|
#define BLK_RL_SYNCFULL (1U << 0)
|
|
#define BLK_RL_ASYNCFULL (1U << 1)
|
|
|
|
struct request_list {
|
|
struct request_queue *q; /* the queue this rl belongs to */
|
|
#ifdef CONFIG_BLK_CGROUP
|
|
struct blkcg_gq *blkg; /* blkg this request pool belongs to */
|
|
#endif
|
|
/*
|
|
* count[], starved[], and wait[] are indexed by
|
|
* BLK_RW_SYNC/BLK_RW_ASYNC
|
|
*/
|
|
int count[2];
|
|
int starved[2];
|
|
mempool_t *rq_pool;
|
|
wait_queue_head_t wait[2];
|
|
unsigned int flags;
|
|
};
|
|
|
|
/*
|
|
* request command types
|
|
*/
|
|
enum rq_cmd_type_bits {
|
|
REQ_TYPE_FS = 1, /* fs request */
|
|
REQ_TYPE_BLOCK_PC, /* scsi command */
|
|
REQ_TYPE_DRV_PRIV, /* driver defined types from here */
|
|
};
|
|
|
|
#define BLK_MAX_CDB 16
|
|
|
|
/*
|
|
* Try to put the fields that are referenced together in the same cacheline.
|
|
*
|
|
* If you modify this structure, make sure to update blk_rq_init() and
|
|
* especially blk_mq_rq_ctx_init() to take care of the added fields.
|
|
*/
|
|
struct request {
|
|
struct list_head queuelist;
|
|
union {
|
|
struct call_single_data csd;
|
|
unsigned long fifo_time;
|
|
};
|
|
|
|
struct request_queue *q;
|
|
struct blk_mq_ctx *mq_ctx;
|
|
|
|
u64 cmd_flags;
|
|
unsigned cmd_type;
|
|
unsigned long atomic_flags;
|
|
|
|
int cpu;
|
|
|
|
/* the following two fields are internal, NEVER access directly */
|
|
unsigned int __data_len; /* total data len */
|
|
sector_t __sector; /* sector cursor */
|
|
|
|
struct bio *bio;
|
|
struct bio *biotail;
|
|
|
|
/*
|
|
* The hash is used inside the scheduler, and killed once the
|
|
* request reaches the dispatch list. The ipi_list is only used
|
|
* to queue the request for softirq completion, which is long
|
|
* after the request has been unhashed (and even removed from
|
|
* the dispatch list).
|
|
*/
|
|
union {
|
|
struct hlist_node hash; /* merge hash */
|
|
struct list_head ipi_list;
|
|
};
|
|
|
|
/*
|
|
* The rb_node is only used inside the io scheduler, requests
|
|
* are pruned when moved to the dispatch queue. So let the
|
|
* completion_data share space with the rb_node.
|
|
*/
|
|
union {
|
|
struct rb_node rb_node; /* sort/lookup */
|
|
void *completion_data;
|
|
};
|
|
|
|
/*
|
|
* Three pointers are available for the IO schedulers, if they need
|
|
* more they have to dynamically allocate it. Flush requests are
|
|
* never put on the IO scheduler. So let the flush fields share
|
|
* space with the elevator data.
|
|
*/
|
|
union {
|
|
struct {
|
|
struct io_cq *icq;
|
|
void *priv[2];
|
|
} elv;
|
|
|
|
struct {
|
|
unsigned int seq;
|
|
struct list_head list;
|
|
rq_end_io_fn *saved_end_io;
|
|
} flush;
|
|
};
|
|
|
|
struct gendisk *rq_disk;
|
|
struct hd_struct *part;
|
|
unsigned long start_time;
|
|
#ifdef CONFIG_BLK_CGROUP
|
|
struct request_list *rl; /* rl this rq is alloced from */
|
|
unsigned long long start_time_ns;
|
|
unsigned long long io_start_time_ns; /* when passed to hardware */
|
|
#endif
|
|
/* Number of scatter-gather DMA addr+len pairs after
|
|
* physical address coalescing is performed.
|
|
*/
|
|
unsigned short nr_phys_segments;
|
|
#if defined(CONFIG_BLK_DEV_INTEGRITY)
|
|
unsigned short nr_integrity_segments;
|
|
#endif
|
|
|
|
unsigned short ioprio;
|
|
|
|
void *special; /* opaque pointer available for LLD use */
|
|
|
|
int tag;
|
|
int errors;
|
|
|
|
/*
|
|
* when request is used as a packet command carrier
|
|
*/
|
|
unsigned char __cmd[BLK_MAX_CDB];
|
|
unsigned char *cmd;
|
|
unsigned short cmd_len;
|
|
|
|
unsigned int extra_len; /* length of alignment and padding */
|
|
unsigned int sense_len;
|
|
unsigned int resid_len; /* residual count */
|
|
void *sense;
|
|
|
|
unsigned long deadline;
|
|
struct list_head timeout_list;
|
|
unsigned int timeout;
|
|
int retries;
|
|
|
|
/*
|
|
* completion callback.
|
|
*/
|
|
rq_end_io_fn *end_io;
|
|
void *end_io_data;
|
|
|
|
/* for bidi */
|
|
struct request *next_rq;
|
|
|
|
ktime_t lat_hist_io_start;
|
|
int lat_hist_enabled;
|
|
};
|
|
|
|
static inline unsigned short req_get_ioprio(struct request *req)
|
|
{
|
|
return req->ioprio;
|
|
}
|
|
|
|
#include <linux/elevator.h>
|
|
|
|
struct blk_queue_ctx;
|
|
|
|
typedef void (request_fn_proc) (struct request_queue *q);
|
|
typedef blk_qc_t (make_request_fn) (struct request_queue *q, struct bio *bio);
|
|
typedef int (prep_rq_fn) (struct request_queue *, struct request *);
|
|
typedef void (unprep_rq_fn) (struct request_queue *, struct request *);
|
|
|
|
struct bio_vec;
|
|
typedef void (softirq_done_fn)(struct request *);
|
|
typedef int (dma_drain_needed_fn)(struct request *);
|
|
typedef int (lld_busy_fn) (struct request_queue *q);
|
|
typedef int (bsg_job_fn) (struct bsg_job *);
|
|
|
|
enum blk_eh_timer_return {
|
|
BLK_EH_NOT_HANDLED,
|
|
BLK_EH_HANDLED,
|
|
BLK_EH_RESET_TIMER,
|
|
};
|
|
|
|
typedef enum blk_eh_timer_return (rq_timed_out_fn)(struct request *);
|
|
|
|
enum blk_queue_state {
|
|
Queue_down,
|
|
Queue_up,
|
|
};
|
|
|
|
struct blk_queue_tag {
|
|
struct request **tag_index; /* map of busy tags */
|
|
unsigned long *tag_map; /* bit map of free/busy tags */
|
|
int busy; /* current depth */
|
|
int max_depth; /* what we will send to device */
|
|
int real_max_depth; /* what the array can hold */
|
|
atomic_t refcnt; /* map can be shared */
|
|
int alloc_policy; /* tag allocation policy */
|
|
int next_tag; /* next tag */
|
|
};
|
|
#define BLK_TAG_ALLOC_FIFO 0 /* allocate starting from 0 */
|
|
#define BLK_TAG_ALLOC_RR 1 /* allocate starting from last allocated tag */
|
|
|
|
#define BLK_SCSI_MAX_CMDS (256)
|
|
#define BLK_SCSI_CMD_PER_LONG (BLK_SCSI_MAX_CMDS / (sizeof(long) * 8))
|
|
|
|
struct queue_limits {
|
|
unsigned long bounce_pfn;
|
|
unsigned long seg_boundary_mask;
|
|
unsigned long virt_boundary_mask;
|
|
|
|
unsigned int max_hw_sectors;
|
|
unsigned int max_dev_sectors;
|
|
unsigned int chunk_sectors;
|
|
unsigned int max_sectors;
|
|
unsigned int max_segment_size;
|
|
unsigned int physical_block_size;
|
|
unsigned int alignment_offset;
|
|
unsigned int io_min;
|
|
unsigned int io_opt;
|
|
unsigned int max_discard_sectors;
|
|
unsigned int max_hw_discard_sectors;
|
|
unsigned int max_write_same_sectors;
|
|
unsigned int discard_granularity;
|
|
unsigned int discard_alignment;
|
|
|
|
unsigned short logical_block_size;
|
|
unsigned short max_segments;
|
|
unsigned short max_integrity_segments;
|
|
|
|
unsigned char misaligned;
|
|
unsigned char discard_misaligned;
|
|
unsigned char cluster;
|
|
unsigned char discard_zeroes_data;
|
|
unsigned char raid_partial_stripes_expensive;
|
|
};
|
|
|
|
struct request_queue {
|
|
/*
|
|
* Together with queue_head for cacheline sharing
|
|
*/
|
|
struct list_head queue_head;
|
|
struct request *last_merge;
|
|
struct elevator_queue *elevator;
|
|
int nr_rqs[2]; /* # allocated [a]sync rqs */
|
|
int nr_rqs_elvpriv; /* # allocated rqs w/ elvpriv */
|
|
|
|
/*
|
|
* If blkcg is not used, @q->root_rl serves all requests. If blkcg
|
|
* is used, root blkg allocates from @q->root_rl and all other
|
|
* blkgs from their own blkg->rl. Which one to use should be
|
|
* determined using bio_request_list().
|
|
*/
|
|
struct request_list root_rl;
|
|
|
|
request_fn_proc *request_fn;
|
|
make_request_fn *make_request_fn;
|
|
prep_rq_fn *prep_rq_fn;
|
|
unprep_rq_fn *unprep_rq_fn;
|
|
softirq_done_fn *softirq_done_fn;
|
|
rq_timed_out_fn *rq_timed_out_fn;
|
|
dma_drain_needed_fn *dma_drain_needed;
|
|
lld_busy_fn *lld_busy_fn;
|
|
|
|
struct blk_mq_ops *mq_ops;
|
|
|
|
unsigned int *mq_map;
|
|
|
|
/* sw queues */
|
|
struct blk_mq_ctx __percpu *queue_ctx;
|
|
unsigned int nr_queues;
|
|
|
|
/* hw dispatch queues */
|
|
struct blk_mq_hw_ctx **queue_hw_ctx;
|
|
unsigned int nr_hw_queues;
|
|
|
|
/*
|
|
* Dispatch queue sorting
|
|
*/
|
|
sector_t end_sector;
|
|
struct request *boundary_rq;
|
|
|
|
/*
|
|
* Delayed queue handling
|
|
*/
|
|
struct delayed_work delay_work;
|
|
|
|
struct backing_dev_info backing_dev_info;
|
|
|
|
/*
|
|
* The queue owner gets to use this for whatever they like.
|
|
* ll_rw_blk doesn't touch it.
|
|
*/
|
|
void *queuedata;
|
|
|
|
/*
|
|
* various queue flags, see QUEUE_* below
|
|
*/
|
|
unsigned long queue_flags;
|
|
|
|
/*
|
|
* ida allocated id for this queue. Used to index queues from
|
|
* ioctx.
|
|
*/
|
|
int id;
|
|
|
|
/*
|
|
* queue needs bounce pages for pages above this limit
|
|
*/
|
|
gfp_t bounce_gfp;
|
|
|
|
/*
|
|
* protects queue structures from reentrancy. ->__queue_lock should
|
|
* _never_ be used directly, it is queue private. always use
|
|
* ->queue_lock.
|
|
*/
|
|
spinlock_t __queue_lock;
|
|
spinlock_t *queue_lock;
|
|
|
|
/*
|
|
* queue kobject
|
|
*/
|
|
struct kobject kobj;
|
|
|
|
/*
|
|
* mq queue kobject
|
|
*/
|
|
struct kobject mq_kobj;
|
|
|
|
#ifdef CONFIG_BLK_DEV_INTEGRITY
|
|
struct blk_integrity integrity;
|
|
#endif /* CONFIG_BLK_DEV_INTEGRITY */
|
|
|
|
#ifdef CONFIG_PM
|
|
struct device *dev;
|
|
int rpm_status;
|
|
unsigned int nr_pending;
|
|
#endif
|
|
|
|
/*
|
|
* queue settings
|
|
*/
|
|
unsigned long nr_requests; /* Max # of requests */
|
|
unsigned int nr_congestion_on;
|
|
unsigned int nr_congestion_off;
|
|
unsigned int nr_batching;
|
|
|
|
unsigned int dma_drain_size;
|
|
void *dma_drain_buffer;
|
|
unsigned int dma_pad_mask;
|
|
unsigned int dma_alignment;
|
|
|
|
struct blk_queue_tag *queue_tags;
|
|
struct list_head tag_busy_list;
|
|
|
|
unsigned int nr_sorted;
|
|
unsigned int in_flight[2];
|
|
/*
|
|
* Number of active block driver functions for which blk_drain_queue()
|
|
* must wait. Must be incremented around functions that unlock the
|
|
* queue_lock internally, e.g. scsi_request_fn().
|
|
*/
|
|
unsigned int request_fn_active;
|
|
|
|
unsigned int rq_timeout;
|
|
struct timer_list timeout;
|
|
struct list_head timeout_list;
|
|
|
|
struct list_head icq_list;
|
|
#ifdef CONFIG_BLK_CGROUP
|
|
DECLARE_BITMAP (blkcg_pols, BLKCG_MAX_POLS);
|
|
struct blkcg_gq *root_blkg;
|
|
struct list_head blkg_list;
|
|
#endif
|
|
|
|
struct queue_limits limits;
|
|
|
|
/*
|
|
* sg stuff
|
|
*/
|
|
unsigned int sg_timeout;
|
|
unsigned int sg_reserved_size;
|
|
int node;
|
|
#ifdef CONFIG_BLK_DEV_IO_TRACE
|
|
struct blk_trace *blk_trace;
|
|
#endif
|
|
/*
|
|
* for flush operations
|
|
*/
|
|
unsigned int flush_flags;
|
|
unsigned int flush_not_queueable:1;
|
|
struct blk_flush_queue *fq;
|
|
|
|
struct list_head requeue_list;
|
|
spinlock_t requeue_lock;
|
|
struct work_struct requeue_work;
|
|
|
|
struct mutex sysfs_lock;
|
|
|
|
int bypass_depth;
|
|
atomic_t mq_freeze_depth;
|
|
|
|
#if defined(CONFIG_BLK_DEV_BSG)
|
|
bsg_job_fn *bsg_job_fn;
|
|
int bsg_job_size;
|
|
struct bsg_class_device bsg_dev;
|
|
#endif
|
|
|
|
#ifdef CONFIG_BLK_DEV_THROTTLING
|
|
/* Throttle data */
|
|
struct throtl_data *td;
|
|
#endif
|
|
struct rcu_head rcu_head;
|
|
wait_queue_head_t mq_freeze_wq;
|
|
struct percpu_ref q_usage_counter;
|
|
struct list_head all_q_node;
|
|
|
|
struct blk_mq_tag_set *tag_set;
|
|
struct list_head tag_set_list;
|
|
struct bio_set *bio_split;
|
|
|
|
bool mq_sysfs_init_done;
|
|
};
|
|
|
|
#define QUEUE_FLAG_QUEUED 1 /* uses generic tag queueing */
|
|
#define QUEUE_FLAG_STOPPED 2 /* queue is stopped */
|
|
#define QUEUE_FLAG_SYNCFULL 3 /* read queue has been filled */
|
|
#define QUEUE_FLAG_ASYNCFULL 4 /* write queue has been filled */
|
|
#define QUEUE_FLAG_DYING 5 /* queue being torn down */
|
|
#define QUEUE_FLAG_BYPASS 6 /* act as dumb FIFO queue */
|
|
#define QUEUE_FLAG_BIDI 7 /* queue supports bidi requests */
|
|
#define QUEUE_FLAG_NOMERGES 8 /* disable merge attempts */
|
|
#define QUEUE_FLAG_SAME_COMP 9 /* complete on same CPU-group */
|
|
#define QUEUE_FLAG_FAIL_IO 10 /* fake timeout */
|
|
#define QUEUE_FLAG_STACKABLE 11 /* supports request stacking */
|
|
#define QUEUE_FLAG_NONROT 12 /* non-rotational device (SSD) */
|
|
#define QUEUE_FLAG_VIRT QUEUE_FLAG_NONROT /* paravirt device */
|
|
#define QUEUE_FLAG_IO_STAT 13 /* do IO stats */
|
|
#define QUEUE_FLAG_DISCARD 14 /* supports DISCARD */
|
|
#define QUEUE_FLAG_NOXMERGES 15 /* No extended merges */
|
|
#define QUEUE_FLAG_ADD_RANDOM 16 /* Contributes to random pool */
|
|
#define QUEUE_FLAG_SECDISCARD 17 /* supports SECDISCARD */
|
|
#define QUEUE_FLAG_SAME_FORCE 18 /* force complete on same CPU */
|
|
#define QUEUE_FLAG_DEAD 19 /* queue tear-down finished */
|
|
#define QUEUE_FLAG_INIT_DONE 20 /* queue is initialized */
|
|
#define QUEUE_FLAG_NO_SG_MERGE 21 /* don't attempt to merge SG segments*/
|
|
#define QUEUE_FLAG_POLL 22 /* IO polling enabled if set */
|
|
#define QUEUE_FLAG_FAST 23 /* fast block device (e.g. ram based) */
|
|
|
|
#define QUEUE_FLAG_DEFAULT ((1 << QUEUE_FLAG_IO_STAT) | \
|
|
(1 << QUEUE_FLAG_STACKABLE) | \
|
|
(1 << QUEUE_FLAG_SAME_COMP) | \
|
|
(1 << QUEUE_FLAG_ADD_RANDOM))
|
|
|
|
#define QUEUE_FLAG_MQ_DEFAULT ((1 << QUEUE_FLAG_IO_STAT) | \
|
|
(1 << QUEUE_FLAG_STACKABLE) | \
|
|
(1 << QUEUE_FLAG_SAME_COMP))
|
|
|
|
static inline void queue_lockdep_assert_held(struct request_queue *q)
|
|
{
|
|
if (q->queue_lock)
|
|
lockdep_assert_held(q->queue_lock);
|
|
}
|
|
|
|
static inline void queue_flag_set_unlocked(unsigned int flag,
|
|
struct request_queue *q)
|
|
{
|
|
__set_bit(flag, &q->queue_flags);
|
|
}
|
|
|
|
static inline int queue_flag_test_and_clear(unsigned int flag,
|
|
struct request_queue *q)
|
|
{
|
|
queue_lockdep_assert_held(q);
|
|
|
|
if (test_bit(flag, &q->queue_flags)) {
|
|
__clear_bit(flag, &q->queue_flags);
|
|
return 1;
|
|
}
|
|
|
|
return 0;
|
|
}
|
|
|
|
static inline int queue_flag_test_and_set(unsigned int flag,
|
|
struct request_queue *q)
|
|
{
|
|
queue_lockdep_assert_held(q);
|
|
|
|
if (!test_bit(flag, &q->queue_flags)) {
|
|
__set_bit(flag, &q->queue_flags);
|
|
return 0;
|
|
}
|
|
|
|
return 1;
|
|
}
|
|
|
|
static inline void queue_flag_set(unsigned int flag, struct request_queue *q)
|
|
{
|
|
queue_lockdep_assert_held(q);
|
|
__set_bit(flag, &q->queue_flags);
|
|
}
|
|
|
|
static inline void queue_flag_clear_unlocked(unsigned int flag,
|
|
struct request_queue *q)
|
|
{
|
|
__clear_bit(flag, &q->queue_flags);
|
|
}
|
|
|
|
static inline int queue_in_flight(struct request_queue *q)
|
|
{
|
|
return q->in_flight[0] + q->in_flight[1];
|
|
}
|
|
|
|
static inline void queue_flag_clear(unsigned int flag, struct request_queue *q)
|
|
{
|
|
queue_lockdep_assert_held(q);
|
|
__clear_bit(flag, &q->queue_flags);
|
|
}
|
|
|
|
#define blk_queue_tagged(q) test_bit(QUEUE_FLAG_QUEUED, &(q)->queue_flags)
|
|
#define blk_queue_stopped(q) test_bit(QUEUE_FLAG_STOPPED, &(q)->queue_flags)
|
|
#define blk_queue_dying(q) test_bit(QUEUE_FLAG_DYING, &(q)->queue_flags)
|
|
#define blk_queue_dead(q) test_bit(QUEUE_FLAG_DEAD, &(q)->queue_flags)
|
|
#define blk_queue_bypass(q) test_bit(QUEUE_FLAG_BYPASS, &(q)->queue_flags)
|
|
#define blk_queue_init_done(q) test_bit(QUEUE_FLAG_INIT_DONE, &(q)->queue_flags)
|
|
#define blk_queue_nomerges(q) test_bit(QUEUE_FLAG_NOMERGES, &(q)->queue_flags)
|
|
#define blk_queue_noxmerges(q) \
|
|
test_bit(QUEUE_FLAG_NOXMERGES, &(q)->queue_flags)
|
|
#define blk_queue_nonrot(q) test_bit(QUEUE_FLAG_NONROT, &(q)->queue_flags)
|
|
#define blk_queue_io_stat(q) test_bit(QUEUE_FLAG_IO_STAT, &(q)->queue_flags)
|
|
#define blk_queue_add_random(q) test_bit(QUEUE_FLAG_ADD_RANDOM, &(q)->queue_flags)
|
|
#define blk_queue_stackable(q) \
|
|
test_bit(QUEUE_FLAG_STACKABLE, &(q)->queue_flags)
|
|
#define blk_queue_discard(q) test_bit(QUEUE_FLAG_DISCARD, &(q)->queue_flags)
|
|
#define blk_queue_secdiscard(q) (blk_queue_discard(q) && \
|
|
test_bit(QUEUE_FLAG_SECDISCARD, &(q)->queue_flags))
|
|
#define blk_queue_fast(q) test_bit(QUEUE_FLAG_FAST, &(q)->queue_flags)
|
|
|
|
#define blk_noretry_request(rq) \
|
|
((rq)->cmd_flags & (REQ_FAILFAST_DEV|REQ_FAILFAST_TRANSPORT| \
|
|
REQ_FAILFAST_DRIVER))
|
|
|
|
#define blk_account_rq(rq) \
|
|
(((rq)->cmd_flags & REQ_STARTED) && \
|
|
((rq)->cmd_type == REQ_TYPE_FS))
|
|
|
|
#define blk_rq_cpu_valid(rq) ((rq)->cpu != -1)
|
|
#define blk_bidi_rq(rq) ((rq)->next_rq != NULL)
|
|
/* rq->queuelist of dequeued request must be list_empty() */
|
|
#define blk_queued_rq(rq) (!list_empty(&(rq)->queuelist))
|
|
|
|
#define list_entry_rq(ptr) list_entry((ptr), struct request, queuelist)
|
|
|
|
#define rq_data_dir(rq) ((int)((rq)->cmd_flags & 1))
|
|
|
|
/*
|
|
* Driver can handle struct request, if it either has an old style
|
|
* request_fn defined, or is blk-mq based.
|
|
*/
|
|
static inline bool queue_is_rq_based(struct request_queue *q)
|
|
{
|
|
return q->request_fn || q->mq_ops;
|
|
}
|
|
|
|
static inline unsigned int blk_queue_cluster(struct request_queue *q)
|
|
{
|
|
return q->limits.cluster;
|
|
}
|
|
|
|
/*
|
|
* We regard a request as sync, if either a read or a sync write
|
|
*/
|
|
static inline bool rw_is_sync(unsigned int rw_flags)
|
|
{
|
|
return !(rw_flags & REQ_WRITE) || (rw_flags & REQ_SYNC);
|
|
}
|
|
|
|
static inline bool rq_is_sync(struct request *rq)
|
|
{
|
|
return rw_is_sync(rq->cmd_flags);
|
|
}
|
|
|
|
static inline bool blk_rl_full(struct request_list *rl, bool sync)
|
|
{
|
|
unsigned int flag = sync ? BLK_RL_SYNCFULL : BLK_RL_ASYNCFULL;
|
|
|
|
return rl->flags & flag;
|
|
}
|
|
|
|
static inline void blk_set_rl_full(struct request_list *rl, bool sync)
|
|
{
|
|
unsigned int flag = sync ? BLK_RL_SYNCFULL : BLK_RL_ASYNCFULL;
|
|
|
|
rl->flags |= flag;
|
|
}
|
|
|
|
static inline void blk_clear_rl_full(struct request_list *rl, bool sync)
|
|
{
|
|
unsigned int flag = sync ? BLK_RL_SYNCFULL : BLK_RL_ASYNCFULL;
|
|
|
|
rl->flags &= ~flag;
|
|
}
|
|
|
|
static inline bool rq_mergeable(struct request *rq)
|
|
{
|
|
if (rq->cmd_type != REQ_TYPE_FS)
|
|
return false;
|
|
|
|
if (rq->cmd_flags & REQ_NOMERGE_FLAGS)
|
|
return false;
|
|
|
|
return true;
|
|
}
|
|
|
|
static inline bool blk_check_merge_flags(unsigned int flags1,
|
|
unsigned int flags2)
|
|
{
|
|
if ((flags1 & REQ_DISCARD) != (flags2 & REQ_DISCARD))
|
|
return false;
|
|
|
|
if ((flags1 & REQ_SECURE) != (flags2 & REQ_SECURE))
|
|
return false;
|
|
|
|
if ((flags1 & REQ_WRITE_SAME) != (flags2 & REQ_WRITE_SAME))
|
|
return false;
|
|
|
|
return true;
|
|
}
|
|
|
|
static inline bool blk_write_same_mergeable(struct bio *a, struct bio *b)
|
|
{
|
|
if (bio_data(a) == bio_data(b))
|
|
return true;
|
|
|
|
return false;
|
|
}
|
|
|
|
/*
|
|
* q->prep_rq_fn return values
|
|
*/
|
|
#define BLKPREP_OK 0 /* serve it */
|
|
#define BLKPREP_KILL 1 /* fatal error, kill */
|
|
#define BLKPREP_DEFER 2 /* leave on queue */
|
|
|
|
extern unsigned long blk_max_low_pfn, blk_max_pfn;
|
|
|
|
/*
|
|
* standard bounce addresses:
|
|
*
|
|
* BLK_BOUNCE_HIGH : bounce all highmem pages
|
|
* BLK_BOUNCE_ANY : don't bounce anything
|
|
* BLK_BOUNCE_ISA : bounce pages above ISA DMA boundary
|
|
*/
|
|
|
|
#if BITS_PER_LONG == 32
|
|
#define BLK_BOUNCE_HIGH ((u64)blk_max_low_pfn << PAGE_SHIFT)
|
|
#else
|
|
#define BLK_BOUNCE_HIGH -1ULL
|
|
#endif
|
|
#define BLK_BOUNCE_ANY (-1ULL)
|
|
#define BLK_BOUNCE_ISA (DMA_BIT_MASK(24))
|
|
|
|
/*
|
|
* default timeout for SG_IO if none specified
|
|
*/
|
|
#define BLK_DEFAULT_SG_TIMEOUT (60 * HZ)
|
|
#define BLK_MIN_SG_TIMEOUT (7 * HZ)
|
|
|
|
#ifdef CONFIG_BOUNCE
|
|
extern int init_emergency_isa_pool(void);
|
|
extern void blk_queue_bounce(struct request_queue *q, struct bio **bio);
|
|
#else
|
|
static inline int init_emergency_isa_pool(void)
|
|
{
|
|
return 0;
|
|
}
|
|
static inline void blk_queue_bounce(struct request_queue *q, struct bio **bio)
|
|
{
|
|
}
|
|
#endif /* CONFIG_MMU */
|
|
|
|
struct rq_map_data {
|
|
struct page **pages;
|
|
int page_order;
|
|
int nr_entries;
|
|
unsigned long offset;
|
|
int null_mapped;
|
|
int from_user;
|
|
};
|
|
|
|
struct req_iterator {
|
|
struct bvec_iter iter;
|
|
struct bio *bio;
|
|
};
|
|
|
|
/* This should not be used directly - use rq_for_each_segment */
|
|
#define for_each_bio(_bio) \
|
|
for (; _bio; _bio = _bio->bi_next)
|
|
#define __rq_for_each_bio(_bio, rq) \
|
|
if ((rq->bio)) \
|
|
for (_bio = (rq)->bio; _bio; _bio = _bio->bi_next)
|
|
|
|
#define rq_for_each_segment(bvl, _rq, _iter) \
|
|
__rq_for_each_bio(_iter.bio, _rq) \
|
|
bio_for_each_segment(bvl, _iter.bio, _iter.iter)
|
|
|
|
#define rq_iter_last(bvec, _iter) \
|
|
(_iter.bio->bi_next == NULL && \
|
|
bio_iter_last(bvec, _iter.iter))
|
|
|
|
#ifndef ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE
|
|
# error "You should define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE for your platform"
|
|
#endif
|
|
#if ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE
|
|
extern void rq_flush_dcache_pages(struct request *rq);
|
|
#else
|
|
static inline void rq_flush_dcache_pages(struct request *rq)
|
|
{
|
|
}
|
|
#endif
|
|
|
|
extern int blk_register_queue(struct gendisk *disk);
|
|
extern void blk_unregister_queue(struct gendisk *disk);
|
|
extern blk_qc_t generic_make_request(struct bio *bio);
|
|
extern void blk_rq_init(struct request_queue *q, struct request *rq);
|
|
extern void blk_put_request(struct request *);
|
|
extern void __blk_put_request(struct request_queue *, struct request *);
|
|
extern struct request *blk_get_request(struct request_queue *, int, gfp_t);
|
|
extern struct request *blk_make_request(struct request_queue *, struct bio *,
|
|
gfp_t);
|
|
extern void blk_rq_set_block_pc(struct request *);
|
|
extern void blk_requeue_request(struct request_queue *, struct request *);
|
|
extern void blk_add_request_payload(struct request *rq, struct page *page,
|
|
unsigned int len);
|
|
extern int blk_lld_busy(struct request_queue *q);
|
|
extern int blk_rq_prep_clone(struct request *rq, struct request *rq_src,
|
|
struct bio_set *bs, gfp_t gfp_mask,
|
|
int (*bio_ctr)(struct bio *, struct bio *, void *),
|
|
void *data);
|
|
extern void blk_rq_unprep_clone(struct request *rq);
|
|
extern int blk_insert_cloned_request(struct request_queue *q,
|
|
struct request *rq);
|
|
extern void blk_delay_queue(struct request_queue *, unsigned long);
|
|
extern void blk_queue_split(struct request_queue *, struct bio **,
|
|
struct bio_set *);
|
|
extern void blk_recount_segments(struct request_queue *, struct bio *);
|
|
extern int scsi_verify_blk_ioctl(struct block_device *, unsigned int);
|
|
extern int scsi_cmd_blk_ioctl(struct block_device *, fmode_t,
|
|
unsigned int, void __user *);
|
|
extern int scsi_cmd_ioctl(struct request_queue *, struct gendisk *, fmode_t,
|
|
unsigned int, void __user *);
|
|
extern int sg_scsi_ioctl(struct request_queue *, struct gendisk *, fmode_t,
|
|
struct scsi_ioctl_command __user *);
|
|
|
|
extern void blk_recalc_rq_segments(struct request *rq);
|
|
extern int blk_queue_enter(struct request_queue *q, gfp_t gfp);
|
|
extern void blk_queue_exit(struct request_queue *q);
|
|
extern void blk_start_queue(struct request_queue *q);
|
|
extern void blk_start_queue_async(struct request_queue *q);
|
|
extern void blk_stop_queue(struct request_queue *q);
|
|
extern void blk_sync_queue(struct request_queue *q);
|
|
extern void __blk_stop_queue(struct request_queue *q);
|
|
extern void __blk_run_queue(struct request_queue *q);
|
|
extern void __blk_run_queue_uncond(struct request_queue *q);
|
|
extern void blk_run_queue(struct request_queue *);
|
|
extern void blk_run_queue_async(struct request_queue *q);
|
|
extern int blk_rq_map_user(struct request_queue *, struct request *,
|
|
struct rq_map_data *, void __user *, unsigned long,
|
|
gfp_t);
|
|
extern int blk_rq_unmap_user(struct bio *);
|
|
extern int blk_rq_map_kern(struct request_queue *, struct request *, void *, unsigned int, gfp_t);
|
|
extern int blk_rq_map_user_iov(struct request_queue *, struct request *,
|
|
struct rq_map_data *, const struct iov_iter *,
|
|
gfp_t);
|
|
extern int blk_execute_rq(struct request_queue *, struct gendisk *,
|
|
struct request *, int);
|
|
extern void blk_execute_rq_nowait(struct request_queue *, struct gendisk *,
|
|
struct request *, int, rq_end_io_fn *);
|
|
|
|
bool blk_poll(struct request_queue *q, blk_qc_t cookie);
|
|
|
|
static inline struct request_queue *bdev_get_queue(struct block_device *bdev)
|
|
{
|
|
return bdev->bd_disk->queue; /* this is never NULL */
|
|
}
|
|
|
|
/*
|
|
* blk_rq_pos() : the current sector
|
|
* blk_rq_bytes() : bytes left in the entire request
|
|
* blk_rq_cur_bytes() : bytes left in the current segment
|
|
* blk_rq_err_bytes() : bytes left till the next error boundary
|
|
* blk_rq_sectors() : sectors left in the entire request
|
|
* blk_rq_cur_sectors() : sectors left in the current segment
|
|
*/
|
|
static inline sector_t blk_rq_pos(const struct request *rq)
|
|
{
|
|
return rq->__sector;
|
|
}
|
|
|
|
static inline unsigned int blk_rq_bytes(const struct request *rq)
|
|
{
|
|
return rq->__data_len;
|
|
}
|
|
|
|
static inline int blk_rq_cur_bytes(const struct request *rq)
|
|
{
|
|
return rq->bio ? bio_cur_bytes(rq->bio) : 0;
|
|
}
|
|
|
|
extern unsigned int blk_rq_err_bytes(const struct request *rq);
|
|
|
|
static inline unsigned int blk_rq_sectors(const struct request *rq)
|
|
{
|
|
return blk_rq_bytes(rq) >> 9;
|
|
}
|
|
|
|
static inline unsigned int blk_rq_cur_sectors(const struct request *rq)
|
|
{
|
|
return blk_rq_cur_bytes(rq) >> 9;
|
|
}
|
|
|
|
static inline unsigned int blk_queue_get_max_sectors(struct request_queue *q,
|
|
unsigned int cmd_flags)
|
|
{
|
|
if (unlikely(cmd_flags & REQ_DISCARD))
|
|
return min(q->limits.max_discard_sectors, UINT_MAX >> 9);
|
|
|
|
if (unlikely(cmd_flags & REQ_WRITE_SAME))
|
|
return q->limits.max_write_same_sectors;
|
|
|
|
return q->limits.max_sectors;
|
|
}
|
|
|
|
/*
|
|
* Return maximum size of a request at given offset. Only valid for
|
|
* file system requests.
|
|
*/
|
|
static inline unsigned int blk_max_size_offset(struct request_queue *q,
|
|
sector_t offset)
|
|
{
|
|
if (!q->limits.chunk_sectors)
|
|
return q->limits.max_sectors;
|
|
|
|
return q->limits.chunk_sectors -
|
|
(offset & (q->limits.chunk_sectors - 1));
|
|
}
|
|
|
|
static inline unsigned int blk_rq_get_max_sectors(struct request *rq)
|
|
{
|
|
struct request_queue *q = rq->q;
|
|
|
|
if (unlikely(rq->cmd_type != REQ_TYPE_FS))
|
|
return q->limits.max_hw_sectors;
|
|
|
|
if (!q->limits.chunk_sectors || (rq->cmd_flags & REQ_DISCARD))
|
|
return blk_queue_get_max_sectors(q, rq->cmd_flags);
|
|
|
|
return min(blk_max_size_offset(q, blk_rq_pos(rq)),
|
|
blk_queue_get_max_sectors(q, rq->cmd_flags));
|
|
}
|
|
|
|
static inline unsigned int blk_rq_count_bios(struct request *rq)
|
|
{
|
|
unsigned int nr_bios = 0;
|
|
struct bio *bio;
|
|
|
|
__rq_for_each_bio(bio, rq)
|
|
nr_bios++;
|
|
|
|
return nr_bios;
|
|
}
|
|
|
|
/*
|
|
* Request issue related functions.
|
|
*/
|
|
extern struct request *blk_peek_request(struct request_queue *q);
|
|
extern void blk_start_request(struct request *rq);
|
|
extern struct request *blk_fetch_request(struct request_queue *q);
|
|
|
|
/*
|
|
* Request completion related functions.
|
|
*
|
|
* blk_update_request() completes given number of bytes and updates
|
|
* the request without completing it.
|
|
*
|
|
* blk_end_request() and friends. __blk_end_request() must be called
|
|
* with the request queue spinlock acquired.
|
|
*
|
|
* Several drivers define their own end_request and call
|
|
* blk_end_request() for parts of the original function.
|
|
* This prevents code duplication in drivers.
|
|
*/
|
|
extern bool blk_update_request(struct request *rq, int error,
|
|
unsigned int nr_bytes);
|
|
extern void blk_finish_request(struct request *rq, int error);
|
|
extern bool blk_end_request(struct request *rq, int error,
|
|
unsigned int nr_bytes);
|
|
extern void blk_end_request_all(struct request *rq, int error);
|
|
extern bool blk_end_request_cur(struct request *rq, int error);
|
|
extern bool blk_end_request_err(struct request *rq, int error);
|
|
extern bool __blk_end_request(struct request *rq, int error,
|
|
unsigned int nr_bytes);
|
|
extern void __blk_end_request_all(struct request *rq, int error);
|
|
extern bool __blk_end_request_cur(struct request *rq, int error);
|
|
extern bool __blk_end_request_err(struct request *rq, int error);
|
|
|
|
extern void blk_complete_request(struct request *);
|
|
extern void __blk_complete_request(struct request *);
|
|
extern void blk_abort_request(struct request *);
|
|
extern void blk_unprep_request(struct request *);
|
|
|
|
/*
|
|
* Access functions for manipulating queue properties
|
|
*/
|
|
extern struct request_queue *blk_init_queue_node(request_fn_proc *rfn,
|
|
spinlock_t *lock, int node_id);
|
|
extern struct request_queue *blk_init_queue(request_fn_proc *, spinlock_t *);
|
|
extern struct request_queue *blk_init_allocated_queue(struct request_queue *,
|
|
request_fn_proc *, spinlock_t *);
|
|
extern void blk_cleanup_queue(struct request_queue *);
|
|
extern void blk_queue_make_request(struct request_queue *, make_request_fn *);
|
|
extern void blk_queue_bounce_limit(struct request_queue *, u64);
|
|
extern void blk_queue_max_hw_sectors(struct request_queue *, unsigned int);
|
|
extern void blk_queue_chunk_sectors(struct request_queue *, unsigned int);
|
|
extern void blk_queue_max_segments(struct request_queue *, unsigned short);
|
|
extern void blk_queue_max_segment_size(struct request_queue *, unsigned int);
|
|
extern void blk_queue_max_discard_sectors(struct request_queue *q,
|
|
unsigned int max_discard_sectors);
|
|
extern void blk_queue_max_write_same_sectors(struct request_queue *q,
|
|
unsigned int max_write_same_sectors);
|
|
extern void blk_queue_logical_block_size(struct request_queue *, unsigned short);
|
|
extern void blk_queue_physical_block_size(struct request_queue *, unsigned int);
|
|
extern void blk_queue_alignment_offset(struct request_queue *q,
|
|
unsigned int alignment);
|
|
extern void blk_limits_io_min(struct queue_limits *limits, unsigned int min);
|
|
extern void blk_queue_io_min(struct request_queue *q, unsigned int min);
|
|
extern void blk_limits_io_opt(struct queue_limits *limits, unsigned int opt);
|
|
extern void blk_queue_io_opt(struct request_queue *q, unsigned int opt);
|
|
extern void blk_set_default_limits(struct queue_limits *lim);
|
|
extern void blk_set_stacking_limits(struct queue_limits *lim);
|
|
extern int blk_stack_limits(struct queue_limits *t, struct queue_limits *b,
|
|
sector_t offset);
|
|
extern int bdev_stack_limits(struct queue_limits *t, struct block_device *bdev,
|
|
sector_t offset);
|
|
extern void disk_stack_limits(struct gendisk *disk, struct block_device *bdev,
|
|
sector_t offset);
|
|
extern void blk_queue_stack_limits(struct request_queue *t, struct request_queue *b);
|
|
extern void blk_queue_dma_pad(struct request_queue *, unsigned int);
|
|
extern void blk_queue_update_dma_pad(struct request_queue *, unsigned int);
|
|
extern int blk_queue_dma_drain(struct request_queue *q,
|
|
dma_drain_needed_fn *dma_drain_needed,
|
|
void *buf, unsigned int size);
|
|
extern void blk_queue_lld_busy(struct request_queue *q, lld_busy_fn *fn);
|
|
extern void blk_queue_segment_boundary(struct request_queue *, unsigned long);
|
|
extern void blk_queue_virt_boundary(struct request_queue *, unsigned long);
|
|
extern void blk_queue_prep_rq(struct request_queue *, prep_rq_fn *pfn);
|
|
extern void blk_queue_unprep_rq(struct request_queue *, unprep_rq_fn *ufn);
|
|
extern void blk_queue_dma_alignment(struct request_queue *, int);
|
|
extern void blk_queue_update_dma_alignment(struct request_queue *, int);
|
|
extern void blk_queue_softirq_done(struct request_queue *, softirq_done_fn *);
|
|
extern void blk_queue_rq_timed_out(struct request_queue *, rq_timed_out_fn *);
|
|
extern void blk_queue_rq_timeout(struct request_queue *, unsigned int);
|
|
extern void blk_queue_flush(struct request_queue *q, unsigned int flush);
|
|
extern void blk_queue_flush_queueable(struct request_queue *q, bool queueable);
|
|
extern struct backing_dev_info *blk_get_backing_dev_info(struct block_device *bdev);
|
|
|
|
extern int blk_rq_map_sg(struct request_queue *, struct request *, struct scatterlist *);
|
|
extern int blk_rq_map_sg_no_cluster
|
|
(struct request_queue *, struct request *, struct scatterlist *);
|
|
extern void blk_dump_rq_flags(struct request *, char *);
|
|
extern long nr_blockdev_pages(void);
|
|
|
|
bool __must_check blk_get_queue(struct request_queue *);
|
|
struct request_queue *blk_alloc_queue(gfp_t);
|
|
struct request_queue *blk_alloc_queue_node(gfp_t, int);
|
|
extern void blk_put_queue(struct request_queue *);
|
|
extern void blk_set_queue_dying(struct request_queue *);
|
|
|
|
/*
|
|
* block layer runtime pm functions
|
|
*/
|
|
#ifdef CONFIG_PM
|
|
extern void blk_pm_runtime_init(struct request_queue *q, struct device *dev);
|
|
extern int blk_pre_runtime_suspend(struct request_queue *q);
|
|
extern void blk_post_runtime_suspend(struct request_queue *q, int err);
|
|
extern void blk_pre_runtime_resume(struct request_queue *q);
|
|
extern void blk_post_runtime_resume(struct request_queue *q, int err);
|
|
#else
|
|
static inline void blk_pm_runtime_init(struct request_queue *q,
|
|
struct device *dev) {}
|
|
static inline int blk_pre_runtime_suspend(struct request_queue *q)
|
|
{
|
|
return -ENOSYS;
|
|
}
|
|
static inline void blk_post_runtime_suspend(struct request_queue *q, int err) {}
|
|
static inline void blk_pre_runtime_resume(struct request_queue *q) {}
|
|
static inline void blk_post_runtime_resume(struct request_queue *q, int err) {}
|
|
#endif
|
|
|
|
/*
|
|
* blk_plug permits building a queue of related requests by holding the I/O
|
|
* fragments for a short period. This allows merging of sequential requests
|
|
* into single larger request. As the requests are moved from a per-task list to
|
|
* the device's request_queue in a batch, this results in improved scalability
|
|
* as the lock contention for request_queue lock is reduced.
|
|
*
|
|
* It is ok not to disable preemption when adding the request to the plug list
|
|
* or when attempting a merge, because blk_schedule_flush_list() will only flush
|
|
* the plug list when the task sleeps by itself. For details, please see
|
|
* schedule() where blk_schedule_flush_plug() is called.
|
|
*/
|
|
struct blk_plug {
|
|
struct list_head list; /* requests */
|
|
struct list_head mq_list; /* blk-mq requests */
|
|
struct list_head cb_list; /* md requires an unplug callback */
|
|
};
|
|
#define BLK_MAX_REQUEST_COUNT 16
|
|
|
|
struct blk_plug_cb;
|
|
typedef void (*blk_plug_cb_fn)(struct blk_plug_cb *, bool);
|
|
struct blk_plug_cb {
|
|
struct list_head list;
|
|
blk_plug_cb_fn callback;
|
|
void *data;
|
|
};
|
|
extern struct blk_plug_cb *blk_check_plugged(blk_plug_cb_fn unplug,
|
|
void *data, int size);
|
|
extern void blk_start_plug(struct blk_plug *);
|
|
extern void blk_finish_plug(struct blk_plug *);
|
|
extern void blk_flush_plug_list(struct blk_plug *, bool);
|
|
|
|
static inline void blk_flush_plug(struct task_struct *tsk)
|
|
{
|
|
struct blk_plug *plug = tsk->plug;
|
|
|
|
if (plug)
|
|
blk_flush_plug_list(plug, false);
|
|
}
|
|
|
|
static inline void blk_schedule_flush_plug(struct task_struct *tsk)
|
|
{
|
|
struct blk_plug *plug = tsk->plug;
|
|
|
|
if (plug)
|
|
blk_flush_plug_list(plug, true);
|
|
}
|
|
|
|
static inline bool blk_needs_flush_plug(struct task_struct *tsk)
|
|
{
|
|
struct blk_plug *plug = tsk->plug;
|
|
|
|
return plug &&
|
|
(!list_empty(&plug->list) ||
|
|
!list_empty(&plug->mq_list) ||
|
|
!list_empty(&plug->cb_list));
|
|
}
|
|
|
|
/*
|
|
* tag stuff
|
|
*/
|
|
extern int blk_queue_start_tag(struct request_queue *, struct request *);
|
|
extern struct request *blk_queue_find_tag(struct request_queue *, int);
|
|
extern void blk_queue_end_tag(struct request_queue *, struct request *);
|
|
extern int blk_queue_init_tags(struct request_queue *, int, struct blk_queue_tag *, int);
|
|
extern void blk_queue_free_tags(struct request_queue *);
|
|
extern int blk_queue_resize_tags(struct request_queue *, int);
|
|
extern void blk_queue_invalidate_tags(struct request_queue *);
|
|
extern struct blk_queue_tag *blk_init_tags(int, int);
|
|
extern void blk_free_tags(struct blk_queue_tag *);
|
|
|
|
static inline struct request *blk_map_queue_find_tag(struct blk_queue_tag *bqt,
|
|
int tag)
|
|
{
|
|
if (unlikely(bqt == NULL || tag >= bqt->real_max_depth))
|
|
return NULL;
|
|
return bqt->tag_index[tag];
|
|
}
|
|
|
|
#define BLKDEV_DISCARD_SECURE 0x01 /* secure discard */
|
|
|
|
extern int blkdev_issue_flush(struct block_device *, gfp_t, sector_t *);
|
|
extern int blkdev_issue_barrier(struct block_device *, gfp_t, sector_t *);
|
|
extern int blkdev_issue_discard(struct block_device *bdev, sector_t sector,
|
|
sector_t nr_sects, gfp_t gfp_mask, unsigned long flags);
|
|
extern int blkdev_issue_write_same(struct block_device *bdev, sector_t sector,
|
|
sector_t nr_sects, gfp_t gfp_mask, struct page *page);
|
|
extern int blkdev_issue_zeroout(struct block_device *bdev, sector_t sector,
|
|
sector_t nr_sects, gfp_t gfp_mask, bool discard);
|
|
static inline int sb_issue_discard(struct super_block *sb, sector_t block,
|
|
sector_t nr_blocks, gfp_t gfp_mask, unsigned long flags)
|
|
{
|
|
return blkdev_issue_discard(sb->s_bdev, block << (sb->s_blocksize_bits - 9),
|
|
nr_blocks << (sb->s_blocksize_bits - 9),
|
|
gfp_mask, flags);
|
|
}
|
|
static inline int sb_issue_zeroout(struct super_block *sb, sector_t block,
|
|
sector_t nr_blocks, gfp_t gfp_mask)
|
|
{
|
|
return blkdev_issue_zeroout(sb->s_bdev,
|
|
block << (sb->s_blocksize_bits - 9),
|
|
nr_blocks << (sb->s_blocksize_bits - 9),
|
|
gfp_mask, true);
|
|
}
|
|
|
|
extern int blk_verify_command(unsigned char *cmd, fmode_t has_write_perm);
|
|
|
|
enum blk_default_limits {
|
|
BLK_MAX_SEGMENTS = 128,
|
|
BLK_SAFE_MAX_SECTORS = 255,
|
|
BLK_DEF_MAX_SECTORS = 2560,
|
|
BLK_MAX_SEGMENT_SIZE = 65536,
|
|
BLK_SEG_BOUNDARY_MASK = 0xFFFFFFFFUL,
|
|
};
|
|
|
|
#define blkdev_entry_to_request(entry) list_entry((entry), struct request, queuelist)
|
|
|
|
static inline unsigned long queue_bounce_pfn(struct request_queue *q)
|
|
{
|
|
return q->limits.bounce_pfn;
|
|
}
|
|
|
|
static inline unsigned long queue_segment_boundary(struct request_queue *q)
|
|
{
|
|
return q->limits.seg_boundary_mask;
|
|
}
|
|
|
|
static inline unsigned long queue_virt_boundary(struct request_queue *q)
|
|
{
|
|
return q->limits.virt_boundary_mask;
|
|
}
|
|
|
|
static inline unsigned int queue_max_sectors(struct request_queue *q)
|
|
{
|
|
return q->limits.max_sectors;
|
|
}
|
|
|
|
static inline unsigned int queue_max_hw_sectors(struct request_queue *q)
|
|
{
|
|
return q->limits.max_hw_sectors;
|
|
}
|
|
|
|
static inline unsigned short queue_max_segments(struct request_queue *q)
|
|
{
|
|
return q->limits.max_segments;
|
|
}
|
|
|
|
static inline unsigned int queue_max_segment_size(struct request_queue *q)
|
|
{
|
|
return q->limits.max_segment_size;
|
|
}
|
|
|
|
static inline unsigned short queue_logical_block_size(struct request_queue *q)
|
|
{
|
|
int retval = 512;
|
|
|
|
if (q && q->limits.logical_block_size)
|
|
retval = q->limits.logical_block_size;
|
|
|
|
return retval;
|
|
}
|
|
|
|
static inline unsigned short bdev_logical_block_size(struct block_device *bdev)
|
|
{
|
|
return queue_logical_block_size(bdev_get_queue(bdev));
|
|
}
|
|
|
|
static inline unsigned int queue_physical_block_size(struct request_queue *q)
|
|
{
|
|
return q->limits.physical_block_size;
|
|
}
|
|
|
|
static inline unsigned int bdev_physical_block_size(struct block_device *bdev)
|
|
{
|
|
return queue_physical_block_size(bdev_get_queue(bdev));
|
|
}
|
|
|
|
static inline unsigned int queue_io_min(struct request_queue *q)
|
|
{
|
|
return q->limits.io_min;
|
|
}
|
|
|
|
static inline int bdev_io_min(struct block_device *bdev)
|
|
{
|
|
return queue_io_min(bdev_get_queue(bdev));
|
|
}
|
|
|
|
static inline unsigned int queue_io_opt(struct request_queue *q)
|
|
{
|
|
return q->limits.io_opt;
|
|
}
|
|
|
|
static inline int bdev_io_opt(struct block_device *bdev)
|
|
{
|
|
return queue_io_opt(bdev_get_queue(bdev));
|
|
}
|
|
|
|
static inline int queue_alignment_offset(struct request_queue *q)
|
|
{
|
|
if (q->limits.misaligned)
|
|
return -1;
|
|
|
|
return q->limits.alignment_offset;
|
|
}
|
|
|
|
static inline int queue_limit_alignment_offset(struct queue_limits *lim, sector_t sector)
|
|
{
|
|
unsigned int granularity = max(lim->physical_block_size, lim->io_min);
|
|
unsigned int alignment = sector_div(sector, granularity >> 9) << 9;
|
|
|
|
return (granularity + lim->alignment_offset - alignment) % granularity;
|
|
}
|
|
|
|
static inline int bdev_alignment_offset(struct block_device *bdev)
|
|
{
|
|
struct request_queue *q = bdev_get_queue(bdev);
|
|
|
|
if (q->limits.misaligned)
|
|
return -1;
|
|
|
|
if (bdev != bdev->bd_contains)
|
|
return bdev->bd_part->alignment_offset;
|
|
|
|
return q->limits.alignment_offset;
|
|
}
|
|
|
|
static inline int queue_discard_alignment(struct request_queue *q)
|
|
{
|
|
if (q->limits.discard_misaligned)
|
|
return -1;
|
|
|
|
return q->limits.discard_alignment;
|
|
}
|
|
|
|
static inline int queue_limit_discard_alignment(struct queue_limits *lim, sector_t sector)
|
|
{
|
|
unsigned int alignment, granularity, offset;
|
|
|
|
if (!lim->max_discard_sectors)
|
|
return 0;
|
|
|
|
/* Why are these in bytes, not sectors? */
|
|
alignment = lim->discard_alignment >> 9;
|
|
granularity = lim->discard_granularity >> 9;
|
|
if (!granularity)
|
|
return 0;
|
|
|
|
/* Offset of the partition start in 'granularity' sectors */
|
|
offset = sector_div(sector, granularity);
|
|
|
|
/* And why do we do this modulus *again* in blkdev_issue_discard()? */
|
|
offset = (granularity + alignment - offset) % granularity;
|
|
|
|
/* Turn it back into bytes, gaah */
|
|
return offset << 9;
|
|
}
|
|
|
|
static inline int bdev_discard_alignment(struct block_device *bdev)
|
|
{
|
|
struct request_queue *q = bdev_get_queue(bdev);
|
|
|
|
if (bdev != bdev->bd_contains)
|
|
return bdev->bd_part->discard_alignment;
|
|
|
|
return q->limits.discard_alignment;
|
|
}
|
|
|
|
static inline unsigned int queue_discard_zeroes_data(struct request_queue *q)
|
|
{
|
|
if (q->limits.max_discard_sectors && q->limits.discard_zeroes_data == 1)
|
|
return 1;
|
|
|
|
return 0;
|
|
}
|
|
|
|
static inline unsigned int bdev_discard_zeroes_data(struct block_device *bdev)
|
|
{
|
|
return queue_discard_zeroes_data(bdev_get_queue(bdev));
|
|
}
|
|
|
|
static inline unsigned int bdev_write_same(struct block_device *bdev)
|
|
{
|
|
struct request_queue *q = bdev_get_queue(bdev);
|
|
|
|
if (q)
|
|
return q->limits.max_write_same_sectors;
|
|
|
|
return 0;
|
|
}
|
|
|
|
static inline int queue_dma_alignment(struct request_queue *q)
|
|
{
|
|
return q ? q->dma_alignment : 511;
|
|
}
|
|
|
|
static inline int blk_rq_aligned(struct request_queue *q, unsigned long addr,
|
|
unsigned int len)
|
|
{
|
|
unsigned int alignment = queue_dma_alignment(q) | q->dma_pad_mask;
|
|
return !(addr & alignment) && !(len & alignment);
|
|
}
|
|
|
|
/* assumes size > 256 */
|
|
static inline unsigned int blksize_bits(unsigned int size)
|
|
{
|
|
unsigned int bits = 8;
|
|
do {
|
|
bits++;
|
|
size >>= 1;
|
|
} while (size > 256);
|
|
return bits;
|
|
}
|
|
|
|
static inline unsigned int block_size(struct block_device *bdev)
|
|
{
|
|
return bdev->bd_block_size;
|
|
}
|
|
|
|
static inline bool queue_flush_queueable(struct request_queue *q)
|
|
{
|
|
return !q->flush_not_queueable;
|
|
}
|
|
|
|
typedef struct {struct page *v;} Sector;
|
|
|
|
unsigned char *read_dev_sector(struct block_device *, sector_t, Sector *);
|
|
|
|
static inline void put_dev_sector(Sector p)
|
|
{
|
|
page_cache_release(p.v);
|
|
}
|
|
|
|
static inline bool __bvec_gap_to_prev(struct request_queue *q,
|
|
struct bio_vec *bprv, unsigned int offset)
|
|
{
|
|
return offset ||
|
|
((bprv->bv_offset + bprv->bv_len) & queue_virt_boundary(q));
|
|
}
|
|
|
|
/*
|
|
* Check if adding a bio_vec after bprv with offset would create a gap in
|
|
* the SG list. Most drivers don't care about this, but some do.
|
|
*/
|
|
static inline bool bvec_gap_to_prev(struct request_queue *q,
|
|
struct bio_vec *bprv, unsigned int offset)
|
|
{
|
|
if (!queue_virt_boundary(q))
|
|
return false;
|
|
return __bvec_gap_to_prev(q, bprv, offset);
|
|
}
|
|
|
|
static inline bool bio_will_gap(struct request_queue *q, struct bio *prev,
|
|
struct bio *next)
|
|
{
|
|
if (bio_has_data(prev) && queue_virt_boundary(q)) {
|
|
struct bio_vec pb, nb;
|
|
|
|
bio_get_last_bvec(prev, &pb);
|
|
bio_get_first_bvec(next, &nb);
|
|
|
|
return __bvec_gap_to_prev(q, &pb, nb.bv_offset);
|
|
}
|
|
|
|
return false;
|
|
}
|
|
|
|
static inline bool req_gap_back_merge(struct request *req, struct bio *bio)
|
|
{
|
|
return bio_will_gap(req->q, req->biotail, bio);
|
|
}
|
|
|
|
static inline bool req_gap_front_merge(struct request *req, struct bio *bio)
|
|
{
|
|
return bio_will_gap(req->q, bio, req->bio);
|
|
}
|
|
|
|
struct work_struct;
|
|
int kblockd_schedule_work(struct work_struct *work);
|
|
int kblockd_schedule_delayed_work(struct delayed_work *dwork, unsigned long delay);
|
|
int kblockd_schedule_delayed_work_on(int cpu, struct delayed_work *dwork, unsigned long delay);
|
|
|
|
#ifdef CONFIG_BLK_CGROUP
|
|
/*
|
|
* This should not be using sched_clock(). A real patch is in progress
|
|
* to fix this up, until that is in place we need to disable preemption
|
|
* around sched_clock() in this function and set_io_start_time_ns().
|
|
*/
|
|
static inline void set_start_time_ns(struct request *req)
|
|
{
|
|
preempt_disable();
|
|
req->start_time_ns = sched_clock();
|
|
preempt_enable();
|
|
}
|
|
|
|
static inline void set_io_start_time_ns(struct request *req)
|
|
{
|
|
preempt_disable();
|
|
req->io_start_time_ns = sched_clock();
|
|
preempt_enable();
|
|
}
|
|
|
|
static inline uint64_t rq_start_time_ns(struct request *req)
|
|
{
|
|
return req->start_time_ns;
|
|
}
|
|
|
|
static inline uint64_t rq_io_start_time_ns(struct request *req)
|
|
{
|
|
return req->io_start_time_ns;
|
|
}
|
|
#else
|
|
static inline void set_start_time_ns(struct request *req) {}
|
|
static inline void set_io_start_time_ns(struct request *req) {}
|
|
static inline uint64_t rq_start_time_ns(struct request *req)
|
|
{
|
|
return 0;
|
|
}
|
|
static inline uint64_t rq_io_start_time_ns(struct request *req)
|
|
{
|
|
return 0;
|
|
}
|
|
#endif
|
|
|
|
#define MODULE_ALIAS_BLOCKDEV(major,minor) \
|
|
MODULE_ALIAS("block-major-" __stringify(major) "-" __stringify(minor))
|
|
#define MODULE_ALIAS_BLOCKDEV_MAJOR(major) \
|
|
MODULE_ALIAS("block-major-" __stringify(major) "-*")
|
|
|
|
#if defined(CONFIG_BLK_DEV_INTEGRITY)
|
|
|
|
enum blk_integrity_flags {
|
|
BLK_INTEGRITY_VERIFY = 1 << 0,
|
|
BLK_INTEGRITY_GENERATE = 1 << 1,
|
|
BLK_INTEGRITY_DEVICE_CAPABLE = 1 << 2,
|
|
BLK_INTEGRITY_IP_CHECKSUM = 1 << 3,
|
|
};
|
|
|
|
struct blk_integrity_iter {
|
|
void *prot_buf;
|
|
void *data_buf;
|
|
sector_t seed;
|
|
unsigned int data_size;
|
|
unsigned short interval;
|
|
const char *disk_name;
|
|
};
|
|
|
|
typedef int (integrity_processing_fn) (struct blk_integrity_iter *);
|
|
|
|
struct blk_integrity_profile {
|
|
integrity_processing_fn *generate_fn;
|
|
integrity_processing_fn *verify_fn;
|
|
const char *name;
|
|
};
|
|
|
|
extern void blk_integrity_register(struct gendisk *, struct blk_integrity *);
|
|
extern void blk_integrity_unregister(struct gendisk *);
|
|
extern int blk_integrity_compare(struct gendisk *, struct gendisk *);
|
|
extern int blk_rq_map_integrity_sg(struct request_queue *, struct bio *,
|
|
struct scatterlist *);
|
|
extern int blk_rq_count_integrity_sg(struct request_queue *, struct bio *);
|
|
extern bool blk_integrity_merge_rq(struct request_queue *, struct request *,
|
|
struct request *);
|
|
extern bool blk_integrity_merge_bio(struct request_queue *, struct request *,
|
|
struct bio *);
|
|
|
|
static inline struct blk_integrity *blk_get_integrity(struct gendisk *disk)
|
|
{
|
|
struct blk_integrity *bi = &disk->queue->integrity;
|
|
|
|
if (!bi->profile)
|
|
return NULL;
|
|
|
|
return bi;
|
|
}
|
|
|
|
static inline
|
|
struct blk_integrity *bdev_get_integrity(struct block_device *bdev)
|
|
{
|
|
return blk_get_integrity(bdev->bd_disk);
|
|
}
|
|
|
|
static inline bool blk_integrity_rq(struct request *rq)
|
|
{
|
|
return rq->cmd_flags & REQ_INTEGRITY;
|
|
}
|
|
|
|
static inline void blk_queue_max_integrity_segments(struct request_queue *q,
|
|
unsigned int segs)
|
|
{
|
|
q->limits.max_integrity_segments = segs;
|
|
}
|
|
|
|
static inline unsigned short
|
|
queue_max_integrity_segments(struct request_queue *q)
|
|
{
|
|
return q->limits.max_integrity_segments;
|
|
}
|
|
|
|
static inline bool integrity_req_gap_back_merge(struct request *req,
|
|
struct bio *next)
|
|
{
|
|
struct bio_integrity_payload *bip = bio_integrity(req->bio);
|
|
struct bio_integrity_payload *bip_next = bio_integrity(next);
|
|
|
|
return bvec_gap_to_prev(req->q, &bip->bip_vec[bip->bip_vcnt - 1],
|
|
bip_next->bip_vec[0].bv_offset);
|
|
}
|
|
|
|
static inline bool integrity_req_gap_front_merge(struct request *req,
|
|
struct bio *bio)
|
|
{
|
|
struct bio_integrity_payload *bip = bio_integrity(bio);
|
|
struct bio_integrity_payload *bip_next = bio_integrity(req->bio);
|
|
|
|
return bvec_gap_to_prev(req->q, &bip->bip_vec[bip->bip_vcnt - 1],
|
|
bip_next->bip_vec[0].bv_offset);
|
|
}
|
|
|
|
#else /* CONFIG_BLK_DEV_INTEGRITY */
|
|
|
|
struct bio;
|
|
struct block_device;
|
|
struct gendisk;
|
|
struct blk_integrity;
|
|
|
|
static inline int blk_integrity_rq(struct request *rq)
|
|
{
|
|
return 0;
|
|
}
|
|
static inline int blk_rq_count_integrity_sg(struct request_queue *q,
|
|
struct bio *b)
|
|
{
|
|
return 0;
|
|
}
|
|
static inline int blk_rq_map_integrity_sg(struct request_queue *q,
|
|
struct bio *b,
|
|
struct scatterlist *s)
|
|
{
|
|
return 0;
|
|
}
|
|
static inline struct blk_integrity *bdev_get_integrity(struct block_device *b)
|
|
{
|
|
return NULL;
|
|
}
|
|
static inline struct blk_integrity *blk_get_integrity(struct gendisk *disk)
|
|
{
|
|
return NULL;
|
|
}
|
|
static inline int blk_integrity_compare(struct gendisk *a, struct gendisk *b)
|
|
{
|
|
return 0;
|
|
}
|
|
static inline void blk_integrity_register(struct gendisk *d,
|
|
struct blk_integrity *b)
|
|
{
|
|
}
|
|
static inline void blk_integrity_unregister(struct gendisk *d)
|
|
{
|
|
}
|
|
static inline void blk_queue_max_integrity_segments(struct request_queue *q,
|
|
unsigned int segs)
|
|
{
|
|
}
|
|
static inline unsigned short queue_max_integrity_segments(struct request_queue *q)
|
|
{
|
|
return 0;
|
|
}
|
|
static inline bool blk_integrity_merge_rq(struct request_queue *rq,
|
|
struct request *r1,
|
|
struct request *r2)
|
|
{
|
|
return true;
|
|
}
|
|
static inline bool blk_integrity_merge_bio(struct request_queue *rq,
|
|
struct request *r,
|
|
struct bio *b)
|
|
{
|
|
return true;
|
|
}
|
|
|
|
static inline bool integrity_req_gap_back_merge(struct request *req,
|
|
struct bio *next)
|
|
{
|
|
return false;
|
|
}
|
|
static inline bool integrity_req_gap_front_merge(struct request *req,
|
|
struct bio *bio)
|
|
{
|
|
return false;
|
|
}
|
|
|
|
#endif /* CONFIG_BLK_DEV_INTEGRITY */
|
|
|
|
struct block_device_operations {
|
|
int (*open) (struct block_device *, fmode_t);
|
|
void (*release) (struct gendisk *, fmode_t);
|
|
int (*rw_page)(struct block_device *, sector_t, struct page *, int rw);
|
|
int (*ioctl) (struct block_device *, fmode_t, unsigned, unsigned long);
|
|
int (*compat_ioctl) (struct block_device *, fmode_t, unsigned, unsigned long);
|
|
long (*direct_access)(struct block_device *, sector_t, void __pmem **,
|
|
unsigned long *pfn);
|
|
unsigned int (*check_events) (struct gendisk *disk,
|
|
unsigned int clearing);
|
|
/* ->media_changed() is DEPRECATED, use ->check_events() instead */
|
|
int (*media_changed) (struct gendisk *);
|
|
void (*unlock_native_capacity) (struct gendisk *);
|
|
int (*revalidate_disk) (struct gendisk *);
|
|
int (*getgeo)(struct block_device *, struct hd_geometry *);
|
|
/* this callback is with swap_lock and sometimes page table lock held */
|
|
void (*swap_slot_free_notify) (struct block_device *, unsigned long);
|
|
struct module *owner;
|
|
const struct pr_ops *pr_ops;
|
|
};
|
|
|
|
extern int __blkdev_driver_ioctl(struct block_device *, fmode_t, unsigned int,
|
|
unsigned long);
|
|
extern int bdev_read_page(struct block_device *, sector_t, struct page *);
|
|
extern int bdev_write_page(struct block_device *, sector_t, struct page *,
|
|
struct writeback_control *);
|
|
extern long bdev_direct_access(struct block_device *, sector_t,
|
|
void __pmem **addr, unsigned long *pfn, long size);
|
|
|
|
/*
|
|
* X-axis for IO latency histogram support.
|
|
*/
|
|
static const u_int64_t latency_x_axis_us[] = {
|
|
100,
|
|
200,
|
|
300,
|
|
400,
|
|
500,
|
|
600,
|
|
700,
|
|
800,
|
|
900,
|
|
1000,
|
|
1200,
|
|
1400,
|
|
1600,
|
|
1800,
|
|
2000,
|
|
2500,
|
|
3000,
|
|
4000,
|
|
5000,
|
|
6000,
|
|
7000,
|
|
9000,
|
|
10000
|
|
};
|
|
|
|
#define BLK_IO_LAT_HIST_DISABLE 0
|
|
#define BLK_IO_LAT_HIST_ENABLE 1
|
|
#define BLK_IO_LAT_HIST_ZERO 2
|
|
|
|
struct io_latency_state {
|
|
u_int64_t latency_y_axis_read[ARRAY_SIZE(latency_x_axis_us) + 1];
|
|
u_int64_t latency_reads_elems;
|
|
u_int64_t latency_y_axis_write[ARRAY_SIZE(latency_x_axis_us) + 1];
|
|
u_int64_t latency_writes_elems;
|
|
};
|
|
|
|
static inline void
|
|
blk_update_latency_hist(struct io_latency_state *s,
|
|
int read,
|
|
u_int64_t delta_us)
|
|
{
|
|
int i;
|
|
|
|
for (i = 0; i < ARRAY_SIZE(latency_x_axis_us); i++) {
|
|
if (delta_us < (u_int64_t)latency_x_axis_us[i]) {
|
|
if (read)
|
|
s->latency_y_axis_read[i]++;
|
|
else
|
|
s->latency_y_axis_write[i]++;
|
|
break;
|
|
}
|
|
}
|
|
if (i == ARRAY_SIZE(latency_x_axis_us)) {
|
|
/* Overflowed the histogram */
|
|
if (read)
|
|
s->latency_y_axis_read[i]++;
|
|
else
|
|
s->latency_y_axis_write[i]++;
|
|
}
|
|
if (read)
|
|
s->latency_reads_elems++;
|
|
else
|
|
s->latency_writes_elems++;
|
|
}
|
|
|
|
void blk_zero_latency_hist(struct io_latency_state *s);
|
|
ssize_t blk_latency_hist_show(struct io_latency_state *s, char *buf);
|
|
|
|
#else /* CONFIG_BLOCK */
|
|
|
|
struct block_device;
|
|
|
|
/*
|
|
* stubs for when the block layer is configured out
|
|
*/
|
|
#define buffer_heads_over_limit 0
|
|
|
|
static inline long nr_blockdev_pages(void)
|
|
{
|
|
return 0;
|
|
}
|
|
|
|
struct blk_plug {
|
|
};
|
|
|
|
static inline void blk_start_plug(struct blk_plug *plug)
|
|
{
|
|
}
|
|
|
|
static inline void blk_finish_plug(struct blk_plug *plug)
|
|
{
|
|
}
|
|
|
|
static inline void blk_flush_plug(struct task_struct *task)
|
|
{
|
|
}
|
|
|
|
static inline void blk_schedule_flush_plug(struct task_struct *task)
|
|
{
|
|
}
|
|
|
|
|
|
static inline bool blk_needs_flush_plug(struct task_struct *tsk)
|
|
{
|
|
return false;
|
|
}
|
|
|
|
static inline int blkdev_issue_flush(struct block_device *bdev, gfp_t gfp_mask,
|
|
sector_t *error_sector)
|
|
{
|
|
return 0;
|
|
}
|
|
|
|
#endif /* CONFIG_BLOCK */
|
|
|
|
#endif
|