Merge 4.9.264 into android-4.9-q
Linux 4.9.264
xen-blkback: don't leak persistent grants from xen_blkbk_map()
mac80211: fix double free in ibss_leave
net: qrtr: fix a kernel-infoleak in qrtr_recvmsg()
net: sched: validate stab values
* can: dev: Move device back to init netns on owning netns delete
include/net/rtnetlink.h
net/core/dev.c
* futex: Handle transient "ownerless" rtmutex state correctly
kernel/futex.c
* futex: Fix incorrect should_fail_futex() handling
kernel/futex.c
* futex: Prevent robust futex exit race
kernel/futex.c
* arm64: futex: Bound number of LDXR/STXR loops in FUTEX_WAKE_OP
arch/arm64/include/asm/futex.h
* locking/futex: Allow low-level atomic operations to return -EAGAIN
kernel/futex.c
* futex: Fix (possible) missed wakeup
kernel/futex.c
* futex: Handle early deadlock return correctly
kernel/futex.c
kernel/locking/rtmutex.c
* futex,rt_mutex: Fix rt_mutex_cleanup_proxy_lock()
kernel/locking/rtmutex.c
* futex: Avoid freeing an active timer
kernel/futex.c
* futex: Drop hb->lock before enqueueing on the rtmutex
kernel/futex.c
kernel/locking/rtmutex.c
kernel/locking/rtmutex_common.h
* futex: Rework futex_lock_pi() to use rt_mutex_*_proxy_lock()
kernel/futex.c
kernel/locking/rtmutex.c
kernel/locking/rtmutex_common.h
* futex,rt_mutex: Introduce rt_mutex_init_waiter()
kernel/futex.c
kernel/locking/rtmutex.c
kernel/locking/rtmutex_common.h
* futex: Use smp_store_release() in mark_wake_futex()
kernel/futex.c
* idr: add ida_is_empty
drivers/usb/gadget/function/f_hid.c
include/linux/idr.h
perf auxtrace: Fix auxtrace queue conflict
ACPI: scan: Use unique number for instance_no
ACPI: scan: Rearrange memory allocation in acpi_device_add()
RDMA/cxgb4: Fix adapter LE hash errors while destroying ipv6 listening server
net: cdc-phonet: fix data-interface release on probe failure
mac80211: fix rate mask reset
can: m_can: m_can_do_rx_poll(): fix extraneous msg loss warning
can: c_can: move runtime PM enable/disable to c_can_platform
can: c_can_pci: c_can_pci_remove(): fix use-after-free
net/qlcnic: Fix a use after free in qlcnic_83xx_get_minidump_template
e1000e: Fix error handling in e1000_set_d0_lplu_state_82571
e1000e: add rtnl_lock() to e1000_reset_task
net: dsa: bcm_sf2: Qualify phydev->dev_flags based on port
* macvlan: macvlan_count_rx() needs to be aware of preemption
include/linux/if_macvlan.h
bus: omap_l3_noc: mark l3 irqs as IRQF_NO_THREAD
arm64: dts: ls1043a: mark crypto engine dma coherent
squashfs: fix xattr id and id lookup sanity checks
* squashfs: fix inode lookup sanity checks
fs/squashfs/squashfs_fs.h
x86/tlb: Flush global mappings when KAISER is disabled
ia64: fix ptrace(PTRACE_SYSCALL_INFO_EXIT) sign
ia64: fix ia64_syscall_get_set_arguments() for break-based syscalls
nfs: we don't support removing system.nfs4_acl
* u64_stats,lockdep: Fix u64_stats_init() vs lockdep
include/linux/u64_stats_sync.h
atm: idt77252: fix null-ptr-dereference
atm: uPD98402: fix incorrect allocation
net: wan: fix error return code of uhdlc_init()
NFS: Correct size calculation for create reply length
* nfs: fix PNFS_FLEXFILE_LAYOUT Kconfig default
fs/nfs/Kconfig
sun/niu: fix wrong RXMAC_BC_FRM_CNT_COUNT count
net: tehuti: fix error return code in bdx_probe()
ixgbe: Fix memleak in ixgbe_configure_clsu32
atm: lanai: dont run lanai_dev_close if not open
atm: eni: dont release is never initialized
powerpc/4xx: Fix build errors from mfdcr()
net: fec: ptp: avoid register access when ipg clock is disabled
ANDROID: Make vsock virtio packet buff size configurable
Merge 4.9.263 into android-4.9-q
Linux 4.9.263
* genirq: Disable interrupts for force threaded handlers
kernel/irq/manage.c
* ext4: fix potential error in ext4_do_update_inode
fs/ext4/inode.c
* ext4: find old entry again if failed to rename whiteout
fs/ext4/namei.c
x86: Introduce TS_COMPAT_RESTART to fix get_nr_restart_syscall()
x86: Move TS_COMPAT back to asm/thread_info.h
* kernel, fs: Introduce and use set_restart_fn() and arch_set_restart_data()
fs/select.c
include/linux/thread_info.h
kernel/futex.c
kernel/time/alarmtimer.c
kernel/time/hrtimer.c
kernel/time/posix-cpu-timers.c
x86/ioapic: Ignore IRQ2 again
perf/x86/intel: Fix a crash caused by zero PEBS status
PCI: rpadlpar: Fix potential drc_name corruption in store functions
iio: adis16400: Fix an error code in adis16400_initial_setup()
* usb: gadget: configfs: Fix KASAN use-after-free
drivers/usb/gadget/configfs.c
* USB: replace hardcode maximum usb string length by definition
drivers/usb/gadget/composite.c
drivers/usb/gadget/configfs.c
drivers/usb/gadget/usbstring.c
include/uapi/linux/usb/ch9.h
scsi: lpfc: Fix some error codes in debugfs
net/qrtr: fix __netdev_alloc_skb call
sunrpc: fix refcount leak for rpc auth modules
svcrdma: disable timeouts on rdma backchannel
NFSD: Repair misuse of sv_lock in 5.10.16-rt30.
nvmet: don't check iosqes,iocqes for discovery controllers
btrfs: fix race when cloning extent buffer during rewind of an old root
ixgbe: prevent ptp_rx_hang from running when in FILTER_ALL mode
ixgbe: check for Tx timestamp timeouts during watchdog
net: dsa: b53: Support setting learning on port
* ext4: check journal inode extents more carefully
fs/ext4/block_validity.c
fs/ext4/ext4.h
fs/ext4/extents.c
fs/ext4/indirect.c
fs/ext4/inode.c
fs/ext4/mballoc.c
* ext4: don't allow overlapping system zones
fs/ext4/block_validity.c
* ext4: handle error of ext4_setup_system_zone() on remount
fs/ext4/super.c
Merge 4.9.262 into android-4.9-q
* FROMGIT: configfs: fix a use-after-free in __configfs_open_file
fs/configfs/file.c
Linux 4.9.262
xen/events: avoid handling the same event on two cpus at the same time
xen/events: don't unmask an event channel when an eoi is pending
xen/events: reset affinity of 2-level event when tearing it down
iio: imu: adis16400: fix memory leak
iio: imu: adis16400: release allocated memory on failure
KVM: arm64: Fix exclusive limit for IPA size
hwmon: (lm90) Fix max6658 sporadic wrong temperature reading
binfmt_misc: fix possible deadlock in bm_register_write
powerpc/64s: Fix instruction encoding for lis in ppc_function_entry()
alpha: switch __copy_user() and __do_clean_user() to normal calling conventions
alpha: Package string routines together
alpha: make short build log available for division routines
alpha: merge build rules of division routines
alpha: add $(src)/ rather than $(obj)/ to make source file path
* configfs: fix a use-after-free in __configfs_open_file
fs/configfs/file.c
block: rsxx: fix error return code of rsxx_pci_probe()
NFSv4.2: fix return value of _nfs4_get_security_label()
sh_eth: fix TRSCER mask for R7S72100
staging: comedi: pcl818: Fix endian problem for AI command data
staging: comedi: pcl711: Fix endian problem for AI command data
staging: comedi: me4000: Fix endian problem for AI command data
staging: comedi: dmm32at: Fix endian problem for AI command data
staging: comedi: das800: Fix endian problem for AI command data
staging: comedi: das6402: Fix endian problem for AI command data
staging: comedi: adv_pci1710: Fix endian problem for AI command data
staging: comedi: addi_apci_1500: Fix endian problem for command sample
staging: comedi: addi_apci_1032: Fix endian problem for COS sample
staging: rtl8192e: Fix possible buffer overflow in _rtl92e_wx_set_scan
staging: rtl8712: Fix possible buffer overflow in r8712_sitesurvey_cmd
staging: ks7010: prevent buffer overflow in ks_wlan_set_scan()
staging: rtl8188eu: fix potential memory corruption in rtw_check_beacon_data()
staging: rtl8712: unterminated string leads to read overflow
staging: rtl8188eu: prevent ->ssid overflow in rtw_wx_set_scan()
staging: rtl8192u: fix ->ssid overflow in r8192_wx_set_scan()
usbip: fix vhci_hcd attach_store() races leading to gpf
usbip: fix stub_dev usbip_sockfd_store() races leading to gpf
usbip: fix vudc to check for stream socket
usbip: fix vhci_hcd to check for stream socket
usbip: fix stub_dev to check for stream socket
USB: serial: cp210x: add some more GE USB IDs
USB: serial: cp210x: add ID for Acuity Brands nLight Air Adapter
USB: serial: ch341: add new Product ID
USB: serial: io_edgeport: fix memory leak in edge_startup
* xhci: Improve detection of device initiated wake signal.
drivers/usb/host/xhci.c
usb: renesas_usbhs: Clear PIPECFG for re-enabling pipe with other EPNUM
usb: gadget: f_uac2: always increase endpoint max_packet_size by one audio slot
Goodix Fingerprint device is not a modem
scripts/recordmcount.{c,pl}: support -ffunction-sections .text.* section names
* mmc: core: Fix partition switch time for eMMC
drivers/mmc/core/mmc.c
s390/dasd: fix hanging DASD driver unbind
* ALSA: usb-audio: Fix "cannot get freq eq" errors on Dell AE515 sound bar
sound/usb/quirks.c
ALSA: hda: Avoid spurious unsol event handling during S3/S4
ALSA: hda/hdmi: Cancel pending works before suspend
scsi: libiscsi: Fix iscsi_prep_scsi_cmd_pdu() error handling
s390/smp: __smp_rescan_cpus() - move cpumask away from stack
PCI: xgene-msi: Fix race in installing chained irq handler
powerpc/perf: Record counter overflow always if SAMPLE_IP is unset
mmc: mediatek: fix race condition between msdc_request_timeout and irq
mmc: mxs-mmc: Fix a resource leak in an error handling path in 'mxs_mmc_probe()'
udf: fix silent AED tagLocation corruption
media: usbtv: Fix deadlock on suspend
net: davicom: Fix regulator not turned off on driver removal
net: davicom: Fix regulator not turned off on failed probe
net: lapbether: Remove netif_start_queue / netif_stop_queue
* net: sched: avoid duplicates in classes dump
net/sched/sch_api.c
net/mlx4_en: update moderation when config reset
* Revert "mm, slub: consider rest of partial list if acquire_slab() fails"
mm/slub.c
cifs: return proper error code in statfs(2)
* netfilter: x_tables: gpf inside xt_find_revision()
net/netfilter/x_tables.c
can: flexcan: enable RX FIFO after FRZ/HALT valid
can: flexcan: assert FRZ bit in flexcan_chip_freeze()
can: skb: can_skb_set_owner(): fix ref counting if socket was closed before setting skb ownership
net: avoid infinite loop in mpls_gso_segment when mpls_hlen == 0
* net: Fix gro aggregation for udp encaps with zero csum
net/ipv4/udp_offload.c
ath9k: fix transmitting to stations in dynamic SMPS mode
ethernet: alx: fix order of calls on resume
uapi: nfnetlink_cthelper.h: fix userspace compilation error
Merge 4.9.261 into android-4.9-q
Linux 4.9.261
misc: eeprom_93xx46: Add quirk to support Microchip 93LC46B eeprom
* PCI: Add function 1 DMA alias quirk for Marvell 9215 SATA controller
drivers/pci/quirks.c
platform/x86: acer-wmi: Add new force_caps module parameter
iommu/amd: Fix sleeping in atomic in increase_address_space()
* dm table: fix DAX iterate_devices based device capability checks
drivers/md/dm-table.c
* dm table: fix iterate_devices based device capability checks
drivers/md/dm-table.c
rsxx: Return -EFAULT if copy_to_user() fails
ALSA: ctxfi: cthw20k2: fix mask on conf to allow 4 bits
usbip: tools: fix build error for multiple definition
btrfs: fix raid6 qstripe kmap
btrfs: raid56: simplify tracking of Q stripe presence
Merge 4.9.260 into android-4.9-q
Linux 4.9.260
* media: v4l: ioctl: Fix memory leak in video_usercopy
drivers/media/v4l2-core/v4l2-ioctl.c
* swap: fix swapfile read/write offset
mm/page_io.c
mm/swapfile.c
* zsmalloc: account the number of compacted pages correctly
drivers/block/zram/zram_drv.c
include/linux/zsmalloc.h
mm/zsmalloc.c
xen-netback: respect gnttab_map_refs()'s return value
Xen/gnttab: handle p2m update errors on a per-slot basis
scsi: iscsi: Verify lengths on passthrough PDUs
scsi: iscsi: Ensure sysfs attributes are limited to PAGE_SIZE
* sysfs: Add sysfs_emit and sysfs_emit_at to format sysfs output
fs/sysfs/file.c
include/linux/sysfs.h
scsi: iscsi: Restrict sessions and handles to admin capabilities
media: uvcvideo: Allow entities with no pads
staging: most: sound: add sanity check for function argument
* Bluetooth: Fix null pointer dereference in amp_read_loc_assoc_final_data
net/bluetooth/amp.c
x86/build: Treat R_386_PLT32 relocation as R_386_PC32
ath10k: fix wmi mgmt tx queue full due to race condition
pktgen: fix misuse of BUG_ON() in pktgen_thread_worker()
wlcore: Fix command execute failure 19 for wl12xx
* vt/consolemap: do font sum unsigned
drivers/tty/vt/consolemap.c
x86/reboot: Add Zotac ZBOX CI327 nano PCI reboot quirk
staging: fwserial: Fix error handling in fwserial_create
mm/hugetlb.c: fix unnecessary address expansion of pmd sharing
* net: fix up truesize of cloned skb in skb_prepare_for_shift()
net/core/skbuff.c
* smackfs: restrict bytes count in smackfs write functions
security/smack/smackfs.c
xfs: Fix assert failure in xfs_setattr_size()
JFS: more checks for invalid superblock
* arm64: Use correct ll/sc atomic constraints
arch/arm64/include/asm/atomic_ll_sc.h
* arm64: cmpxchg: Use "K" instead of "L" for ll/sc immediate constraint
arch/arm64/include/asm/atomic_ll_sc.h
* arm64: Avoid redundant type conversions in xchg() and cmpxchg()
arch/arm64/include/asm/atomic_ll_sc.h
arch/arm64/include/asm/cmpxchg.h
* arm64: Remove redundant mov from LL/SC cmpxchg
arch/arm64/include/asm/atomic_ll_sc.h
printk: fix deadlock when kernel panic
hugetlb: fix update_and_free_page contig page struct assumption
* scripts: set proper OpenSSL include dir also for sign-file
scripts/Makefile
* scripts: use pkg-config to locate libcrypto
scripts/Makefile
arm: kprobes: Allow to handle reentered kprobe on single-stepping
net: usb: qmi_wwan: support ZTE P685M modem
* futex: Don't enable IRQs unconditionally in put_pi_state()
kernel/futex.c
* futex: Fix more put_pi_state() vs. exit_pi_state_list() races
kernel/futex.c
* futex: Fix pi_state->owner serialization
kernel/futex.c
* futex: Futex_unlock_pi() determinism
kernel/futex.c
* futex: Pull rt_mutex_futex_unlock() out from under hb->lock
kernel/futex.c
* futex: Cleanup refcounting
kernel/futex.c
* futex: Cleanup variable names for futex_top_waiter()
kernel/futex.c
Merge 4.9.259 into android-4.9-q
Linux 4.9.259
dm era: Update in-core bitset after committing the metadata
* net: icmp: pass zeroed opts from icmp{,v6}_ndo_send before sending
include/linux/icmpv6.h
include/linux/ipv6.h
include/net/icmp.h
net/ipv4/icmp.c
net/ipv6/icmp.c
net/ipv6/ip6_icmp.c
* ipv6: silence compilation warning for non-IPV6 builds
include/linux/icmpv6.h
* ipv6: icmp6: avoid indirect call for icmpv6_send()
include/linux/icmpv6.h
net/ipv6/icmp.c
net/ipv6/ip6_icmp.c
sunvnet: use icmp_ndo_send helper
gtp: use icmp_ndo_send helper
* icmp: allow icmpv6_ndo_send to work with CONFIG_IPV6=n
include/linux/icmpv6.h
* icmp: introduce helper for nat'd source address in network device context
include/linux/icmpv6.h
include/net/icmp.h
net/ipv4/icmp.c
net/ipv6/ip6_icmp.c
* futex: fix dead code in attach_to_pi_owner()
kernel/futex.c
* futex: Fix OWNER_DEAD fixup
kernel/futex.c
dm era: only resize metadata in preresume
dm era: Reinitialize bitset cache before digesting a new writeset
dm era: Use correct value size in equality function of writeset tree
dm era: Fix bitset memory leaks
dm era: Verify the data block size hasn't changed
dm era: Recover committed writeset after crash
gfs2: Don't skip dlm unlock if glock has an lvb
sparc32: fix a user-triggerable oops in clear_user()
* f2fs: fix out-of-repair __setattr_copy()
fs/f2fs/file.c
gpio: pcf857x: Fix missing first interrupt
mmc: sdhci-esdhc-imx: fix kernel panic when remove module
* module: Ignore _GLOBAL_OFFSET_TABLE_ when warning for undefined symbols
kernel/module.c
libnvdimm/dimm: Avoid race between probe and available_slots_show()
usb: renesas_usbhs: Clear pipe running flag in usbhs_pkt_pop()
mm: hugetlb: fix a race between freeing and dissolving the page
mtd: spi-nor: hisi-sfc: Put child node np on error path
floppy: reintroduce O_NDELAY fix
x86/reboot: Force all cpus to exit VMX root if VMX is supported
staging: rtl8188eu: Add Edimax EW-7811UN V2 to device table
drivers/misc/vmw_vmci: restrict too big queue size in qp_host_alloc_queue
* seccomp: Add missing return in non-void function
kernel/seccomp.c
btrfs: fix extent buffer leak on failure to copy root
btrfs: fix reloc root leak with 0 ref reloc roots on recovery
btrfs: abort the transaction if we fail to inc ref in btrfs_copy_root
KEYS: trusted: Fix migratable=1 failing
* usb: dwc3: gadget: Fix dep->interval for fullspeed interrupt
drivers/usb/dwc3/gadget.c
* usb: dwc3: gadget: Fix setting of DEPCFG.bInterval_m1
drivers/usb/dwc3/gadget.c
USB: serial: mos7720: fix error code in mos7720_write()
USB: serial: mos7840: fix error code in mos7840_write()
usb: musb: Fix runtime PM race in musb_queue_resume_work
USB: serial: option: update interface mapping for ZTE P685M
Input: i8042 - add ASUS Zenbook Flip to noselftest list
Input: joydev - prevent potential read overflow in ioctl
* Input: xpad - add support for PowerA Enhanced Wired Controller for Xbox Series X|S
drivers/input/joystick/xpad.c
Input: raydium_ts_i2c - do not send zero length
ACPI: configfs: add missing check after configfs_register_default_group()
* blk-settings: align max_sectors on "logical_block_size" boundary
block/blk-settings.c
* scsi: bnx2fc: Fix Kconfig warning & CNIC build errors
drivers/scsi/bnx2fc/Kconfig
i2c: brcmstb: Fix brcmstd_send_i2c_cmd condition
* arm64: Add missing ISB after invalidating TLB in __primary_switch
arch/arm64/kernel/head.S
mm/hugetlb: fix potential double free in hugetlb_register_node() error path
* mm/memory.c: fix potential pte_unmap_unlock pte error
mm/memory.c
ocfs2: fix a use after free on error
net/mlx4_core: Add missed mlx4_free_cmd_mailbox()
i40e: Fix flow for IPv6 next header (extension header)
drm/msm/dsi: Correct io_start for MSM8994 (20nm PHY)
* PCI: Align checking of syscall user config accessors
drivers/pci/syscall.c
VMCI: Use set_page_dirty_lock() when unregistering guest memory
pwm: rockchip: rockchip_pwm_probe(): Remove superfluous clk_unprepare()
misc: eeprom_93xx46: Add module alias to avoid breaking support for non device tree users
misc: eeprom_93xx46: Fix module alias to enable module autoprobe
sparc64: only select COMPAT_BINFMT_ELF if BINFMT_ELF is set
Input: elo - fix an error code in elo_connect()
perf test: Fix unaligned access in sample parsing test
perf intel-pt: Fix missing CYC processing in PSB
spi: pxa2xx: Fix the controller numbering for Wildcat Point
powerpc/pseries/dlpar: handle ibm, configure-connector delay status
mfd: wm831x-auxadc: Prevent use after free in wm831x_auxadc_read_irq()
RDMA/rxe: Fix coding error in rxe_recv.c
perf tools: Fix DSO filtering when not finding a map for a sampled address
* tracepoint: Do not fail unregistering a probe due to memory failure
kernel/tracepoint.c
* amba: Fix resource leak for drivers without .remove
drivers/amba/bus.c
ARM: 9046/1: decompressor: Do not clear SCTLR.nTLSMD for ARMv7+ cores
mmc: usdhi6rol0: Fix a resource leak in the error handling path of the probe
powerpc/47x: Disable 256k page size
IB/umad: Return EIO in case of when device disassociated
isofs: release buffer head before return
regulator: axp20x: Fix reference cout leak
clocksource/drivers/mxs_timer: Add missing semicolon when DEBUG is defined
power: reset: at91-sama5d2_shdwc: fix wkupdbc mask
* of/fdt: Make sure no-map does not remove already reserved regions
drivers/of/fdt.c
* fdt: Properly handle "no-map" field in the memory region
drivers/of/fdt.c
dmaengine: fsldma: Fix a resource leak in an error handling path of the probe function
dmaengine: fsldma: Fix a resource leak in the remove function
* HID: core: detect and skip invalid inputs to snto32()
drivers/hid/hid-core.c
spi: cadence-quadspi: Abort read if dummy cycles required are too many
clk: meson: clk-pll: fix initializing the old rate (fallback) for a PLL
jffs2: fix use after free in jffs2_sum_write_data()
fs/jfs: fix potential integer overflow on shift of a int
crypto: ecdh_helper - Ensure 'len >= secret.len' in decode_key()
btrfs: clarify error returns values in __load_free_space_cache
ata: ahci_brcm: Add back regulators management
media: uvcvideo: Accept invalid bFormatIndex and bFrameIndex values
media: pxa_camera: declare variable when DEBUG is defined
media: cx25821: Fix a bug when reallocating some dma memory
media: qm1d1c0042: fix error return code in qm1d1c0042_init()
media: lmedm04: Fix misuse of comma
ASoC: cs42l56: fix up error handling in probe
media: tm6000: Fix memleak in tm6000_start_stream
media: media/pci: Fix memleak in empress_init
media: vsp1: Fix an error handling path in the probe function
MIPS: lantiq: Explicitly compare LTQ_EBU_PCC_ISTAT against 0
MIPS: c-r4k: Fix section mismatch for loongson2_sc_init
gma500: clean up error handling in init
drm/gma500: Fix error return code in psb_driver_load()
* fbdev: aty: SPARC64 requires FB_ATY_CT
drivers/video/fbdev/Kconfig
b43: N-PHY: Fix the update of coef for the PHY revision >= 3case
mac80211: fix potential overflow when multiplying to u32 integers
xen/netback: fix spurious event detection for common event case
bnxt_en: reverse order of TX disable and carrier off
ARM: s3c: fix fiq for clang IAS
arm64: dts: msm8916: Fix reserved and rfsa nodes unit address
usb: dwc2: Make "trimming xfer length" a debug message
usb: dwc2: Abort transaction after errors with unknown reason
usb: dwc2: Do not update data length if it is 0 on inbound transfers
ARM: dts: Configure missing thermal interrupt for 4430
* Bluetooth: Put HCI device if inquiry procedure interrupts
net/bluetooth/hci_core.c
* Bluetooth: drop HCI device reference before return
net/bluetooth/a2mp.c
arm64: dts: exynos: correct PMIC interrupt trigger level on Espresso
ARM: dts: exynos: correct PMIC interrupt trigger level on Arndale Octa
ARM: dts: exynos: correct PMIC interrupt trigger level on Spring
* Bluetooth: Fix initializing response id after clearing struct
net/bluetooth/a2mp.c
mm, thp: make do_huge_pmd_wp_page() lock page for testing mapcount
* random: fix the RNDRESEEDCRNG ioctl
drivers/char/random.c
MIPS: vmlinux.lds.S: add missing PAGE_ALIGNED_DATA() section
* kdb: Make memory allocations more robust
kernel/debug/kdb/kdb_private.h
scripts/recordmcount.pl: support big endian for ARCH sh
cifs: Set CIFS_MOUNT_USE_PREFIX_PATH flag on setting cifs_sb->prepath.
NET: usb: qmi_wwan: Adding support for Cinterion MV31
arm64: tegra: Add power-domain for Tegra210 HDA
igb: Remove incorrect "unexpected SYS WRAP" log message
ntfs: check for valid standard information attribute
* usb: quirks: add quirk to start video capture on ELMO L-12F document camera reliable
drivers/usb/core/quirks.c
* HID: make arrays usage and value to be the same
drivers/hid/hid-core.c
Bug: 184596728
Change-Id: I50e867d3e8d2d62938b73e54b8d6e614bb3f2d1b
Signed-off-by: Lucas Wei <lucaswei@google.com>
877 lines
28 KiB
C
877 lines
28 KiB
C
/*
|
|
* Functions related to setting various queue properties from drivers
|
|
*/
|
|
#include <linux/kernel.h>
|
|
#include <linux/module.h>
|
|
#include <linux/init.h>
|
|
#include <linux/bio.h>
|
|
#include <linux/blkdev.h>
|
|
#include <linux/bootmem.h> /* for max_pfn/max_low_pfn */
|
|
#include <linux/gcd.h>
|
|
#include <linux/lcm.h>
|
|
#include <linux/jiffies.h>
|
|
#include <linux/gfp.h>
|
|
|
|
#include "blk.h"
|
|
|
|
unsigned long blk_max_low_pfn;
|
|
EXPORT_SYMBOL(blk_max_low_pfn);
|
|
|
|
unsigned long blk_max_pfn;
|
|
|
|
/**
|
|
* blk_queue_prep_rq - set a prepare_request function for queue
|
|
* @q: queue
|
|
* @pfn: prepare_request function
|
|
*
|
|
* It's possible for a queue to register a prepare_request callback which
|
|
* is invoked before the request is handed to the request_fn. The goal of
|
|
* the function is to prepare a request for I/O, it can be used to build a
|
|
* cdb from the request data for instance.
|
|
*
|
|
*/
|
|
void blk_queue_prep_rq(struct request_queue *q, prep_rq_fn *pfn)
|
|
{
|
|
q->prep_rq_fn = pfn;
|
|
}
|
|
EXPORT_SYMBOL(blk_queue_prep_rq);
|
|
|
|
/**
|
|
* blk_queue_unprep_rq - set an unprepare_request function for queue
|
|
* @q: queue
|
|
* @ufn: unprepare_request function
|
|
*
|
|
* It's possible for a queue to register an unprepare_request callback
|
|
* which is invoked before the request is finally completed. The goal
|
|
* of the function is to deallocate any data that was allocated in the
|
|
* prepare_request callback.
|
|
*
|
|
*/
|
|
void blk_queue_unprep_rq(struct request_queue *q, unprep_rq_fn *ufn)
|
|
{
|
|
q->unprep_rq_fn = ufn;
|
|
}
|
|
EXPORT_SYMBOL(blk_queue_unprep_rq);
|
|
|
|
void blk_queue_softirq_done(struct request_queue *q, softirq_done_fn *fn)
|
|
{
|
|
q->softirq_done_fn = fn;
|
|
}
|
|
EXPORT_SYMBOL(blk_queue_softirq_done);
|
|
|
|
void blk_queue_rq_timeout(struct request_queue *q, unsigned int timeout)
|
|
{
|
|
q->rq_timeout = timeout;
|
|
}
|
|
EXPORT_SYMBOL_GPL(blk_queue_rq_timeout);
|
|
|
|
void blk_queue_rq_timed_out(struct request_queue *q, rq_timed_out_fn *fn)
|
|
{
|
|
q->rq_timed_out_fn = fn;
|
|
}
|
|
EXPORT_SYMBOL_GPL(blk_queue_rq_timed_out);
|
|
|
|
void blk_queue_lld_busy(struct request_queue *q, lld_busy_fn *fn)
|
|
{
|
|
q->lld_busy_fn = fn;
|
|
}
|
|
EXPORT_SYMBOL_GPL(blk_queue_lld_busy);
|
|
|
|
/**
|
|
* blk_set_default_limits - reset limits to default values
|
|
* @lim: the queue_limits structure to reset
|
|
*
|
|
* Description:
|
|
* Returns a queue_limit struct to its default state.
|
|
*/
|
|
void blk_set_default_limits(struct queue_limits *lim)
|
|
{
|
|
lim->max_segments = BLK_MAX_SEGMENTS;
|
|
lim->max_integrity_segments = 0;
|
|
lim->seg_boundary_mask = BLK_SEG_BOUNDARY_MASK;
|
|
lim->virt_boundary_mask = 0;
|
|
lim->max_segment_size = BLK_MAX_SEGMENT_SIZE;
|
|
lim->max_sectors = lim->max_hw_sectors = BLK_SAFE_MAX_SECTORS;
|
|
lim->max_dev_sectors = 0;
|
|
lim->chunk_sectors = 0;
|
|
lim->max_write_same_sectors = 0;
|
|
lim->max_discard_sectors = 0;
|
|
lim->max_hw_discard_sectors = 0;
|
|
lim->discard_granularity = 0;
|
|
lim->discard_alignment = 0;
|
|
lim->discard_misaligned = 0;
|
|
lim->discard_zeroes_data = 0;
|
|
lim->logical_block_size = lim->physical_block_size = lim->io_min = 512;
|
|
lim->bounce_pfn = (unsigned long)(BLK_BOUNCE_ANY >> PAGE_SHIFT);
|
|
lim->alignment_offset = 0;
|
|
lim->io_opt = 0;
|
|
lim->misaligned = 0;
|
|
lim->cluster = 1;
|
|
}
|
|
EXPORT_SYMBOL(blk_set_default_limits);
|
|
|
|
/**
|
|
* blk_set_stacking_limits - set default limits for stacking devices
|
|
* @lim: the queue_limits structure to reset
|
|
*
|
|
* Description:
|
|
* Returns a queue_limit struct to its default state. Should be used
|
|
* by stacking drivers like DM that have no internal limits.
|
|
*/
|
|
void blk_set_stacking_limits(struct queue_limits *lim)
|
|
{
|
|
blk_set_default_limits(lim);
|
|
|
|
/* Inherit limits from component devices */
|
|
lim->discard_zeroes_data = 1;
|
|
lim->max_segments = USHRT_MAX;
|
|
lim->max_hw_sectors = UINT_MAX;
|
|
lim->max_segment_size = UINT_MAX;
|
|
lim->max_sectors = UINT_MAX;
|
|
lim->max_dev_sectors = UINT_MAX;
|
|
lim->max_write_same_sectors = UINT_MAX;
|
|
}
|
|
EXPORT_SYMBOL(blk_set_stacking_limits);
|
|
|
|
/**
|
|
* blk_queue_make_request - define an alternate make_request function for a device
|
|
* @q: the request queue for the device to be affected
|
|
* @mfn: the alternate make_request function
|
|
*
|
|
* Description:
|
|
* The normal way for &struct bios to be passed to a device
|
|
* driver is for them to be collected into requests on a request
|
|
* queue, and then to allow the device driver to select requests
|
|
* off that queue when it is ready. This works well for many block
|
|
* devices. However some block devices (typically virtual devices
|
|
* such as md or lvm) do not benefit from the processing on the
|
|
* request queue, and are served best by having the requests passed
|
|
* directly to them. This can be achieved by providing a function
|
|
* to blk_queue_make_request().
|
|
*
|
|
* Caveat:
|
|
* The driver that does this *must* be able to deal appropriately
|
|
* with buffers in "highmemory". This can be accomplished by either calling
|
|
* __bio_kmap_atomic() to get a temporary kernel mapping, or by calling
|
|
* blk_queue_bounce() to create a buffer in normal memory.
|
|
**/
|
|
void blk_queue_make_request(struct request_queue *q, make_request_fn *mfn)
|
|
{
|
|
/*
|
|
* set defaults
|
|
*/
|
|
q->nr_requests = BLKDEV_MAX_RQ;
|
|
|
|
q->make_request_fn = mfn;
|
|
blk_queue_dma_alignment(q, 511);
|
|
blk_queue_congestion_threshold(q);
|
|
q->nr_batching = BLK_BATCH_REQ;
|
|
|
|
blk_set_default_limits(&q->limits);
|
|
|
|
/*
|
|
* by default assume old behaviour and bounce for any highmem page
|
|
*/
|
|
blk_queue_bounce_limit(q, BLK_BOUNCE_HIGH);
|
|
}
|
|
EXPORT_SYMBOL(blk_queue_make_request);
|
|
|
|
/**
|
|
* blk_queue_bounce_limit - set bounce buffer limit for queue
|
|
* @q: the request queue for the device
|
|
* @max_addr: the maximum address the device can handle
|
|
*
|
|
* Description:
|
|
* Different hardware can have different requirements as to what pages
|
|
* it can do I/O directly to. A low level driver can call
|
|
* blk_queue_bounce_limit to have lower memory pages allocated as bounce
|
|
* buffers for doing I/O to pages residing above @max_addr.
|
|
**/
|
|
void blk_queue_bounce_limit(struct request_queue *q, u64 max_addr)
|
|
{
|
|
unsigned long b_pfn = max_addr >> PAGE_SHIFT;
|
|
int dma = 0;
|
|
|
|
q->bounce_gfp = GFP_NOIO;
|
|
#if BITS_PER_LONG == 64
|
|
/*
|
|
* Assume anything <= 4GB can be handled by IOMMU. Actually
|
|
* some IOMMUs can handle everything, but I don't know of a
|
|
* way to test this here.
|
|
*/
|
|
if (b_pfn < (min_t(u64, 0xffffffffUL, BLK_BOUNCE_HIGH) >> PAGE_SHIFT))
|
|
dma = 1;
|
|
q->limits.bounce_pfn = max(max_low_pfn, b_pfn);
|
|
#else
|
|
if (b_pfn < blk_max_low_pfn)
|
|
dma = 1;
|
|
q->limits.bounce_pfn = b_pfn;
|
|
#endif
|
|
if (dma) {
|
|
init_emergency_isa_pool();
|
|
q->bounce_gfp = GFP_NOIO | GFP_DMA;
|
|
q->limits.bounce_pfn = b_pfn;
|
|
}
|
|
}
|
|
EXPORT_SYMBOL(blk_queue_bounce_limit);
|
|
|
|
/**
|
|
* blk_queue_max_hw_sectors - set max sectors for a request for this queue
|
|
* @q: the request queue for the device
|
|
* @max_hw_sectors: max hardware sectors in the usual 512b unit
|
|
*
|
|
* Description:
|
|
* Enables a low level driver to set a hard upper limit,
|
|
* max_hw_sectors, on the size of requests. max_hw_sectors is set by
|
|
* the device driver based upon the capabilities of the I/O
|
|
* controller.
|
|
*
|
|
* max_dev_sectors is a hard limit imposed by the storage device for
|
|
* READ/WRITE requests. It is set by the disk driver.
|
|
*
|
|
* max_sectors is a soft limit imposed by the block layer for
|
|
* filesystem type requests. This value can be overridden on a
|
|
* per-device basis in /sys/block/<device>/queue/max_sectors_kb.
|
|
* The soft limit can not exceed max_hw_sectors.
|
|
**/
|
|
void blk_queue_max_hw_sectors(struct request_queue *q, unsigned int max_hw_sectors)
|
|
{
|
|
struct queue_limits *limits = &q->limits;
|
|
unsigned int max_sectors;
|
|
|
|
if ((max_hw_sectors << 9) < PAGE_SIZE) {
|
|
max_hw_sectors = 1 << (PAGE_SHIFT - 9);
|
|
printk(KERN_INFO "%s: set to minimum %d\n",
|
|
__func__, max_hw_sectors);
|
|
}
|
|
|
|
limits->max_hw_sectors = max_hw_sectors;
|
|
max_sectors = min_not_zero(max_hw_sectors, limits->max_dev_sectors);
|
|
max_sectors = min_t(unsigned int, max_sectors, BLK_DEF_MAX_SECTORS);
|
|
limits->max_sectors = max_sectors;
|
|
q->backing_dev_info->io_pages = max_sectors >> (PAGE_SHIFT - 9);
|
|
}
|
|
EXPORT_SYMBOL(blk_queue_max_hw_sectors);
|
|
|
|
/**
|
|
* blk_queue_chunk_sectors - set size of the chunk for this queue
|
|
* @q: the request queue for the device
|
|
* @chunk_sectors: chunk sectors in the usual 512b unit
|
|
*
|
|
* Description:
|
|
* If a driver doesn't want IOs to cross a given chunk size, it can set
|
|
* this limit and prevent merging across chunks. Note that the chunk size
|
|
* must currently be a power-of-2 in sectors. Also note that the block
|
|
* layer must accept a page worth of data at any offset. So if the
|
|
* crossing of chunks is a hard limitation in the driver, it must still be
|
|
* prepared to split single page bios.
|
|
**/
|
|
void blk_queue_chunk_sectors(struct request_queue *q, unsigned int chunk_sectors)
|
|
{
|
|
BUG_ON(!is_power_of_2(chunk_sectors));
|
|
q->limits.chunk_sectors = chunk_sectors;
|
|
}
|
|
EXPORT_SYMBOL(blk_queue_chunk_sectors);
|
|
|
|
/**
|
|
* blk_queue_max_discard_sectors - set max sectors for a single discard
|
|
* @q: the request queue for the device
|
|
* @max_discard_sectors: maximum number of sectors to discard
|
|
**/
|
|
void blk_queue_max_discard_sectors(struct request_queue *q,
|
|
unsigned int max_discard_sectors)
|
|
{
|
|
q->limits.max_hw_discard_sectors = max_discard_sectors;
|
|
q->limits.max_discard_sectors = max_discard_sectors;
|
|
}
|
|
EXPORT_SYMBOL(blk_queue_max_discard_sectors);
|
|
|
|
/**
|
|
* blk_queue_max_write_same_sectors - set max sectors for a single write same
|
|
* @q: the request queue for the device
|
|
* @max_write_same_sectors: maximum number of sectors to write per command
|
|
**/
|
|
void blk_queue_max_write_same_sectors(struct request_queue *q,
|
|
unsigned int max_write_same_sectors)
|
|
{
|
|
q->limits.max_write_same_sectors = max_write_same_sectors;
|
|
}
|
|
EXPORT_SYMBOL(blk_queue_max_write_same_sectors);
|
|
|
|
/**
|
|
* blk_queue_max_segments - set max hw segments for a request for this queue
|
|
* @q: the request queue for the device
|
|
* @max_segments: max number of segments
|
|
*
|
|
* Description:
|
|
* Enables a low level driver to set an upper limit on the number of
|
|
* hw data segments in a request.
|
|
**/
|
|
void blk_queue_max_segments(struct request_queue *q, unsigned short max_segments)
|
|
{
|
|
if (!max_segments) {
|
|
max_segments = 1;
|
|
printk(KERN_INFO "%s: set to minimum %d\n",
|
|
__func__, max_segments);
|
|
}
|
|
|
|
q->limits.max_segments = max_segments;
|
|
}
|
|
EXPORT_SYMBOL(blk_queue_max_segments);
|
|
|
|
/**
|
|
* blk_queue_max_segment_size - set max segment size for blk_rq_map_sg
|
|
* @q: the request queue for the device
|
|
* @max_size: max size of segment in bytes
|
|
*
|
|
* Description:
|
|
* Enables a low level driver to set an upper limit on the size of a
|
|
* coalesced segment
|
|
**/
|
|
void blk_queue_max_segment_size(struct request_queue *q, unsigned int max_size)
|
|
{
|
|
if (max_size < PAGE_SIZE) {
|
|
max_size = PAGE_SIZE;
|
|
printk(KERN_INFO "%s: set to minimum %d\n",
|
|
__func__, max_size);
|
|
}
|
|
|
|
q->limits.max_segment_size = max_size;
|
|
}
|
|
EXPORT_SYMBOL(blk_queue_max_segment_size);
|
|
|
|
/**
|
|
* blk_queue_logical_block_size - set logical block size for the queue
|
|
* @q: the request queue for the device
|
|
* @size: the logical block size, in bytes
|
|
*
|
|
* Description:
|
|
* This should be set to the lowest possible block size that the
|
|
* storage device can address. The default of 512 covers most
|
|
* hardware.
|
|
**/
|
|
void blk_queue_logical_block_size(struct request_queue *q, unsigned int size)
|
|
{
|
|
q->limits.logical_block_size = size;
|
|
|
|
if (q->limits.physical_block_size < size)
|
|
q->limits.physical_block_size = size;
|
|
|
|
if (q->limits.io_min < q->limits.physical_block_size)
|
|
q->limits.io_min = q->limits.physical_block_size;
|
|
}
|
|
EXPORT_SYMBOL(blk_queue_logical_block_size);
|
|
|
|
/**
|
|
* blk_queue_physical_block_size - set physical block size for the queue
|
|
* @q: the request queue for the device
|
|
* @size: the physical block size, in bytes
|
|
*
|
|
* Description:
|
|
* This should be set to the lowest possible sector size that the
|
|
* hardware can operate on without reverting to read-modify-write
|
|
* operations.
|
|
*/
|
|
void blk_queue_physical_block_size(struct request_queue *q, unsigned int size)
|
|
{
|
|
q->limits.physical_block_size = size;
|
|
|
|
if (q->limits.physical_block_size < q->limits.logical_block_size)
|
|
q->limits.physical_block_size = q->limits.logical_block_size;
|
|
|
|
if (q->limits.io_min < q->limits.physical_block_size)
|
|
q->limits.io_min = q->limits.physical_block_size;
|
|
}
|
|
EXPORT_SYMBOL(blk_queue_physical_block_size);
|
|
|
|
/**
|
|
* blk_queue_alignment_offset - set physical block alignment offset
|
|
* @q: the request queue for the device
|
|
* @offset: alignment offset in bytes
|
|
*
|
|
* Description:
|
|
* Some devices are naturally misaligned to compensate for things like
|
|
* the legacy DOS partition table 63-sector offset. Low-level drivers
|
|
* should call this function for devices whose first sector is not
|
|
* naturally aligned.
|
|
*/
|
|
void blk_queue_alignment_offset(struct request_queue *q, unsigned int offset)
|
|
{
|
|
q->limits.alignment_offset =
|
|
offset & (q->limits.physical_block_size - 1);
|
|
q->limits.misaligned = 0;
|
|
}
|
|
EXPORT_SYMBOL(blk_queue_alignment_offset);
|
|
|
|
/**
|
|
* blk_limits_io_min - set minimum request size for a device
|
|
* @limits: the queue limits
|
|
* @min: smallest I/O size in bytes
|
|
*
|
|
* Description:
|
|
* Some devices have an internal block size bigger than the reported
|
|
* hardware sector size. This function can be used to signal the
|
|
* smallest I/O the device can perform without incurring a performance
|
|
* penalty.
|
|
*/
|
|
void blk_limits_io_min(struct queue_limits *limits, unsigned int min)
|
|
{
|
|
limits->io_min = min;
|
|
|
|
if (limits->io_min < limits->logical_block_size)
|
|
limits->io_min = limits->logical_block_size;
|
|
|
|
if (limits->io_min < limits->physical_block_size)
|
|
limits->io_min = limits->physical_block_size;
|
|
}
|
|
EXPORT_SYMBOL(blk_limits_io_min);
|
|
|
|
/**
|
|
* blk_queue_io_min - set minimum request size for the queue
|
|
* @q: the request queue for the device
|
|
* @min: smallest I/O size in bytes
|
|
*
|
|
* Description:
|
|
* Storage devices may report a granularity or preferred minimum I/O
|
|
* size which is the smallest request the device can perform without
|
|
* incurring a performance penalty. For disk drives this is often the
|
|
* physical block size. For RAID arrays it is often the stripe chunk
|
|
* size. A properly aligned multiple of minimum_io_size is the
|
|
* preferred request size for workloads where a high number of I/O
|
|
* operations is desired.
|
|
*/
|
|
void blk_queue_io_min(struct request_queue *q, unsigned int min)
|
|
{
|
|
blk_limits_io_min(&q->limits, min);
|
|
}
|
|
EXPORT_SYMBOL(blk_queue_io_min);
|
|
|
|
/**
|
|
* blk_limits_io_opt - set optimal request size for a device
|
|
* @limits: the queue limits
|
|
* @opt: smallest I/O size in bytes
|
|
*
|
|
* Description:
|
|
* Storage devices may report an optimal I/O size, which is the
|
|
* device's preferred unit for sustained I/O. This is rarely reported
|
|
* for disk drives. For RAID arrays it is usually the stripe width or
|
|
* the internal track size. A properly aligned multiple of
|
|
* optimal_io_size is the preferred request size for workloads where
|
|
* sustained throughput is desired.
|
|
*/
|
|
void blk_limits_io_opt(struct queue_limits *limits, unsigned int opt)
|
|
{
|
|
limits->io_opt = opt;
|
|
}
|
|
EXPORT_SYMBOL(blk_limits_io_opt);
|
|
|
|
/**
|
|
* blk_queue_io_opt - set optimal request size for the queue
|
|
* @q: the request queue for the device
|
|
* @opt: optimal request size in bytes
|
|
*
|
|
* Description:
|
|
* Storage devices may report an optimal I/O size, which is the
|
|
* device's preferred unit for sustained I/O. This is rarely reported
|
|
* for disk drives. For RAID arrays it is usually the stripe width or
|
|
* the internal track size. A properly aligned multiple of
|
|
* optimal_io_size is the preferred request size for workloads where
|
|
* sustained throughput is desired.
|
|
*/
|
|
void blk_queue_io_opt(struct request_queue *q, unsigned int opt)
|
|
{
|
|
blk_limits_io_opt(&q->limits, opt);
|
|
}
|
|
EXPORT_SYMBOL(blk_queue_io_opt);
|
|
|
|
/**
|
|
* blk_queue_stack_limits - inherit underlying queue limits for stacked drivers
|
|
* @t: the stacking driver (top)
|
|
* @b: the underlying device (bottom)
|
|
**/
|
|
void blk_queue_stack_limits(struct request_queue *t, struct request_queue *b)
|
|
{
|
|
blk_stack_limits(&t->limits, &b->limits, 0);
|
|
}
|
|
EXPORT_SYMBOL(blk_queue_stack_limits);
|
|
|
|
static unsigned int blk_round_down_sectors(unsigned int sectors, unsigned int lbs)
|
|
{
|
|
sectors = round_down(sectors, lbs >> SECTOR_SHIFT);
|
|
if (sectors < PAGE_SIZE >> SECTOR_SHIFT)
|
|
sectors = PAGE_SIZE >> SECTOR_SHIFT;
|
|
return sectors;
|
|
}
|
|
|
|
/**
|
|
* blk_stack_limits - adjust queue_limits for stacked devices
|
|
* @t: the stacking driver limits (top device)
|
|
* @b: the underlying queue limits (bottom, component device)
|
|
* @start: first data sector within component device
|
|
*
|
|
* Description:
|
|
* This function is used by stacking drivers like MD and DM to ensure
|
|
* that all component devices have compatible block sizes and
|
|
* alignments. The stacking driver must provide a queue_limits
|
|
* struct (top) and then iteratively call the stacking function for
|
|
* all component (bottom) devices. The stacking function will
|
|
* attempt to combine the values and ensure proper alignment.
|
|
*
|
|
* Returns 0 if the top and bottom queue_limits are compatible. The
|
|
* top device's block sizes and alignment offsets may be adjusted to
|
|
* ensure alignment with the bottom device. If no compatible sizes
|
|
* and alignments exist, -1 is returned and the resulting top
|
|
* queue_limits will have the misaligned flag set to indicate that
|
|
* the alignment_offset is undefined.
|
|
*/
|
|
int blk_stack_limits(struct queue_limits *t, struct queue_limits *b,
|
|
sector_t start)
|
|
{
|
|
unsigned int top, bottom, alignment, ret = 0;
|
|
|
|
t->max_sectors = min_not_zero(t->max_sectors, b->max_sectors);
|
|
t->max_hw_sectors = min_not_zero(t->max_hw_sectors, b->max_hw_sectors);
|
|
t->max_dev_sectors = min_not_zero(t->max_dev_sectors, b->max_dev_sectors);
|
|
t->max_write_same_sectors = min(t->max_write_same_sectors,
|
|
b->max_write_same_sectors);
|
|
t->bounce_pfn = min_not_zero(t->bounce_pfn, b->bounce_pfn);
|
|
|
|
t->seg_boundary_mask = min_not_zero(t->seg_boundary_mask,
|
|
b->seg_boundary_mask);
|
|
t->virt_boundary_mask = min_not_zero(t->virt_boundary_mask,
|
|
b->virt_boundary_mask);
|
|
|
|
t->max_segments = min_not_zero(t->max_segments, b->max_segments);
|
|
t->max_integrity_segments = min_not_zero(t->max_integrity_segments,
|
|
b->max_integrity_segments);
|
|
|
|
t->max_segment_size = min_not_zero(t->max_segment_size,
|
|
b->max_segment_size);
|
|
|
|
t->misaligned |= b->misaligned;
|
|
|
|
alignment = queue_limit_alignment_offset(b, start);
|
|
|
|
/* Bottom device has different alignment. Check that it is
|
|
* compatible with the current top alignment.
|
|
*/
|
|
if (t->alignment_offset != alignment) {
|
|
|
|
top = max(t->physical_block_size, t->io_min)
|
|
+ t->alignment_offset;
|
|
bottom = max(b->physical_block_size, b->io_min) + alignment;
|
|
|
|
/* Verify that top and bottom intervals line up */
|
|
if (max(top, bottom) % min(top, bottom)) {
|
|
t->misaligned = 1;
|
|
ret = -1;
|
|
}
|
|
}
|
|
|
|
t->logical_block_size = max(t->logical_block_size,
|
|
b->logical_block_size);
|
|
|
|
t->physical_block_size = max(t->physical_block_size,
|
|
b->physical_block_size);
|
|
|
|
t->io_min = max(t->io_min, b->io_min);
|
|
t->io_opt = lcm_not_zero(t->io_opt, b->io_opt);
|
|
|
|
t->cluster &= b->cluster;
|
|
t->discard_zeroes_data &= b->discard_zeroes_data;
|
|
|
|
/* Physical block size a multiple of the logical block size? */
|
|
if (t->physical_block_size & (t->logical_block_size - 1)) {
|
|
t->physical_block_size = t->logical_block_size;
|
|
t->misaligned = 1;
|
|
ret = -1;
|
|
}
|
|
|
|
/* Minimum I/O a multiple of the physical block size? */
|
|
if (t->io_min & (t->physical_block_size - 1)) {
|
|
t->io_min = t->physical_block_size;
|
|
t->misaligned = 1;
|
|
ret = -1;
|
|
}
|
|
|
|
/* Optimal I/O a multiple of the physical block size? */
|
|
if (t->io_opt & (t->physical_block_size - 1)) {
|
|
t->io_opt = 0;
|
|
t->misaligned = 1;
|
|
ret = -1;
|
|
}
|
|
|
|
t->raid_partial_stripes_expensive =
|
|
max(t->raid_partial_stripes_expensive,
|
|
b->raid_partial_stripes_expensive);
|
|
|
|
/* Find lowest common alignment_offset */
|
|
t->alignment_offset = lcm_not_zero(t->alignment_offset, alignment)
|
|
% max(t->physical_block_size, t->io_min);
|
|
|
|
/* Verify that new alignment_offset is on a logical block boundary */
|
|
if (t->alignment_offset & (t->logical_block_size - 1)) {
|
|
t->misaligned = 1;
|
|
ret = -1;
|
|
}
|
|
|
|
t->max_sectors = blk_round_down_sectors(t->max_sectors, t->logical_block_size);
|
|
t->max_hw_sectors = blk_round_down_sectors(t->max_hw_sectors, t->logical_block_size);
|
|
t->max_dev_sectors = blk_round_down_sectors(t->max_dev_sectors, t->logical_block_size);
|
|
|
|
/* Discard alignment and granularity */
|
|
if (b->discard_granularity) {
|
|
alignment = queue_limit_discard_alignment(b, start);
|
|
|
|
if (t->discard_granularity != 0 &&
|
|
t->discard_alignment != alignment) {
|
|
top = t->discard_granularity + t->discard_alignment;
|
|
bottom = b->discard_granularity + alignment;
|
|
|
|
/* Verify that top and bottom intervals line up */
|
|
if ((max(top, bottom) % min(top, bottom)) != 0)
|
|
t->discard_misaligned = 1;
|
|
}
|
|
|
|
t->max_discard_sectors = min_not_zero(t->max_discard_sectors,
|
|
b->max_discard_sectors);
|
|
t->max_hw_discard_sectors = min_not_zero(t->max_hw_discard_sectors,
|
|
b->max_hw_discard_sectors);
|
|
t->discard_granularity = max(t->discard_granularity,
|
|
b->discard_granularity);
|
|
t->discard_alignment = lcm_not_zero(t->discard_alignment, alignment) %
|
|
t->discard_granularity;
|
|
}
|
|
|
|
return ret;
|
|
}
|
|
EXPORT_SYMBOL(blk_stack_limits);
|
|
|
|
/**
|
|
* bdev_stack_limits - adjust queue limits for stacked drivers
|
|
* @t: the stacking driver limits (top device)
|
|
* @bdev: the component block_device (bottom)
|
|
* @start: first data sector within component device
|
|
*
|
|
* Description:
|
|
* Merges queue limits for a top device and a block_device. Returns
|
|
* 0 if alignment didn't change. Returns -1 if adding the bottom
|
|
* device caused misalignment.
|
|
*/
|
|
int bdev_stack_limits(struct queue_limits *t, struct block_device *bdev,
|
|
sector_t start)
|
|
{
|
|
struct request_queue *bq = bdev_get_queue(bdev);
|
|
|
|
start += get_start_sect(bdev);
|
|
|
|
return blk_stack_limits(t, &bq->limits, start);
|
|
}
|
|
EXPORT_SYMBOL(bdev_stack_limits);
|
|
|
|
/**
|
|
* disk_stack_limits - adjust queue limits for stacked drivers
|
|
* @disk: MD/DM gendisk (top)
|
|
* @bdev: the underlying block device (bottom)
|
|
* @offset: offset to beginning of data within component device
|
|
*
|
|
* Description:
|
|
* Merges the limits for a top level gendisk and a bottom level
|
|
* block_device.
|
|
*/
|
|
void disk_stack_limits(struct gendisk *disk, struct block_device *bdev,
|
|
sector_t offset)
|
|
{
|
|
struct request_queue *t = disk->queue;
|
|
|
|
if (bdev_stack_limits(&t->limits, bdev, offset >> 9) < 0) {
|
|
char top[BDEVNAME_SIZE], bottom[BDEVNAME_SIZE];
|
|
|
|
disk_name(disk, 0, top);
|
|
bdevname(bdev, bottom);
|
|
|
|
printk(KERN_NOTICE "%s: Warning: Device %s is misaligned\n",
|
|
top, bottom);
|
|
}
|
|
}
|
|
EXPORT_SYMBOL(disk_stack_limits);
|
|
|
|
/**
|
|
* blk_queue_dma_pad - set pad mask
|
|
* @q: the request queue for the device
|
|
* @mask: pad mask
|
|
*
|
|
* Set dma pad mask.
|
|
*
|
|
* Appending pad buffer to a request modifies the last entry of a
|
|
* scatter list such that it includes the pad buffer.
|
|
**/
|
|
void blk_queue_dma_pad(struct request_queue *q, unsigned int mask)
|
|
{
|
|
q->dma_pad_mask = mask;
|
|
}
|
|
EXPORT_SYMBOL(blk_queue_dma_pad);
|
|
|
|
/**
|
|
* blk_queue_update_dma_pad - update pad mask
|
|
* @q: the request queue for the device
|
|
* @mask: pad mask
|
|
*
|
|
* Update dma pad mask.
|
|
*
|
|
* Appending pad buffer to a request modifies the last entry of a
|
|
* scatter list such that it includes the pad buffer.
|
|
**/
|
|
void blk_queue_update_dma_pad(struct request_queue *q, unsigned int mask)
|
|
{
|
|
if (mask > q->dma_pad_mask)
|
|
q->dma_pad_mask = mask;
|
|
}
|
|
EXPORT_SYMBOL(blk_queue_update_dma_pad);
|
|
|
|
/**
|
|
* blk_queue_dma_drain - Set up a drain buffer for excess dma.
|
|
* @q: the request queue for the device
|
|
* @dma_drain_needed: fn which returns non-zero if drain is necessary
|
|
* @buf: physically contiguous buffer
|
|
* @size: size of the buffer in bytes
|
|
*
|
|
* Some devices have excess DMA problems and can't simply discard (or
|
|
* zero fill) the unwanted piece of the transfer. They have to have a
|
|
* real area of memory to transfer it into. The use case for this is
|
|
* ATAPI devices in DMA mode. If the packet command causes a transfer
|
|
* bigger than the transfer size some HBAs will lock up if there
|
|
* aren't DMA elements to contain the excess transfer. What this API
|
|
* does is adjust the queue so that the buf is always appended
|
|
* silently to the scatterlist.
|
|
*
|
|
* Note: This routine adjusts max_hw_segments to make room for appending
|
|
* the drain buffer. If you call blk_queue_max_segments() after calling
|
|
* this routine, you must set the limit to one fewer than your device
|
|
* can support otherwise there won't be room for the drain buffer.
|
|
*/
|
|
int blk_queue_dma_drain(struct request_queue *q,
|
|
dma_drain_needed_fn *dma_drain_needed,
|
|
void *buf, unsigned int size)
|
|
{
|
|
if (queue_max_segments(q) < 2)
|
|
return -EINVAL;
|
|
/* make room for appending the drain */
|
|
blk_queue_max_segments(q, queue_max_segments(q) - 1);
|
|
q->dma_drain_needed = dma_drain_needed;
|
|
q->dma_drain_buffer = buf;
|
|
q->dma_drain_size = size;
|
|
|
|
return 0;
|
|
}
|
|
EXPORT_SYMBOL_GPL(blk_queue_dma_drain);
|
|
|
|
/**
|
|
* blk_queue_segment_boundary - set boundary rules for segment merging
|
|
* @q: the request queue for the device
|
|
* @mask: the memory boundary mask
|
|
**/
|
|
void blk_queue_segment_boundary(struct request_queue *q, unsigned long mask)
|
|
{
|
|
if (mask < PAGE_SIZE - 1) {
|
|
mask = PAGE_SIZE - 1;
|
|
printk(KERN_INFO "%s: set to minimum %lx\n",
|
|
__func__, mask);
|
|
}
|
|
|
|
q->limits.seg_boundary_mask = mask;
|
|
}
|
|
EXPORT_SYMBOL(blk_queue_segment_boundary);
|
|
|
|
/**
|
|
* blk_queue_virt_boundary - set boundary rules for bio merging
|
|
* @q: the request queue for the device
|
|
* @mask: the memory boundary mask
|
|
**/
|
|
void blk_queue_virt_boundary(struct request_queue *q, unsigned long mask)
|
|
{
|
|
q->limits.virt_boundary_mask = mask;
|
|
}
|
|
EXPORT_SYMBOL(blk_queue_virt_boundary);
|
|
|
|
/**
|
|
* blk_queue_dma_alignment - set dma length and memory alignment
|
|
* @q: the request queue for the device
|
|
* @mask: alignment mask
|
|
*
|
|
* description:
|
|
* set required memory and length alignment for direct dma transactions.
|
|
* this is used when building direct io requests for the queue.
|
|
*
|
|
**/
|
|
void blk_queue_dma_alignment(struct request_queue *q, int mask)
|
|
{
|
|
q->dma_alignment = mask;
|
|
}
|
|
EXPORT_SYMBOL(blk_queue_dma_alignment);
|
|
|
|
/**
|
|
* blk_queue_update_dma_alignment - update dma length and memory alignment
|
|
* @q: the request queue for the device
|
|
* @mask: alignment mask
|
|
*
|
|
* description:
|
|
* update required memory and length alignment for direct dma transactions.
|
|
* If the requested alignment is larger than the current alignment, then
|
|
* the current queue alignment is updated to the new value, otherwise it
|
|
* is left alone. The design of this is to allow multiple objects
|
|
* (driver, device, transport etc) to set their respective
|
|
* alignments without having them interfere.
|
|
*
|
|
**/
|
|
void blk_queue_update_dma_alignment(struct request_queue *q, int mask)
|
|
{
|
|
BUG_ON(mask > PAGE_SIZE);
|
|
|
|
if (mask > q->dma_alignment)
|
|
q->dma_alignment = mask;
|
|
}
|
|
EXPORT_SYMBOL(blk_queue_update_dma_alignment);
|
|
|
|
void blk_queue_flush_queueable(struct request_queue *q, bool queueable)
|
|
{
|
|
spin_lock_irq(q->queue_lock);
|
|
if (queueable)
|
|
clear_bit(QUEUE_FLAG_FLUSH_NQ, &q->queue_flags);
|
|
else
|
|
set_bit(QUEUE_FLAG_FLUSH_NQ, &q->queue_flags);
|
|
spin_unlock_irq(q->queue_lock);
|
|
}
|
|
EXPORT_SYMBOL_GPL(blk_queue_flush_queueable);
|
|
|
|
/**
|
|
* blk_queue_write_cache - configure queue's write cache
|
|
* @q: the request queue for the device
|
|
* @wc: write back cache on or off
|
|
* @fua: device supports FUA writes, if true
|
|
*
|
|
* Tell the block layer about the write cache of @q.
|
|
*/
|
|
void blk_queue_write_cache(struct request_queue *q, bool wc, bool fua)
|
|
{
|
|
spin_lock_irq(q->queue_lock);
|
|
if (wc)
|
|
queue_flag_set(QUEUE_FLAG_WC, q);
|
|
else
|
|
queue_flag_clear(QUEUE_FLAG_WC, q);
|
|
if (fua)
|
|
queue_flag_set(QUEUE_FLAG_FUA, q);
|
|
else
|
|
queue_flag_clear(QUEUE_FLAG_FUA, q);
|
|
spin_unlock_irq(q->queue_lock);
|
|
}
|
|
EXPORT_SYMBOL_GPL(blk_queue_write_cache);
|
|
|
|
static int __init blk_settings_init(void)
|
|
{
|
|
blk_max_low_pfn = max_low_pfn - 1;
|
|
blk_max_pfn = max_pfn - 1;
|
|
return 0;
|
|
}
|
|
subsys_initcall(blk_settings_init);
|