android_kernel_xiaomi_sm8450/include/linux/pgtable.h
Greg Kroah-Hartman 477f5e6b9e This is the 5.10.188 stable release
-----BEGIN PGP SIGNATURE-----
 
 iQIzBAABCAAdFiEEZH8oZUiU471FcZm+ONu9yGCSaT4FAmTCEmYACgkQONu9yGCS
 aT5ETA/+MGhe+GasO74Gvx1MaSVJrPZgPzInUg5UoYIkf+N3BfNqH9KVrY/zFKfU
 mKNQSQDsli+WG8agHVzoa4lh3ZFHbiUrNx14n+3A8lZ0X5s31fqTLXRvKy9BCu4t
 8OQW6nuMv22SVDd40F5ciroNmAbDquDfUQK4KbETNRPU2Yzvd5VEZiCY9aQAGFbc
 YnqBbx1Qc5EQKmzoBmEiup2j04SWXwMPQERKdFVZ1jrjC3hC8MFmL62YwfbCH4gY
 faDSZPj++/V5c++bP6oG8QhfrQS+WYGwFmEJpf4GUJ8dxxJC9Ao9CwcXbd2jOjfz
 Tk0gNQ9YPs+a2gexAnaHsJqKXn+dcRvkIMzmArApZv73PET0LgMv8N7s3OB5E9ei
 K2ft+nfXs5NCLRjPFCqL9nAeclj8ZX92B4d4mrpbqHZ+fFBiHMb0H/aGxfCAR0MJ
 BuW1dWQJykR2crhzQ1PJr3OthnL9O4Nl+bBAAuOu6NwqiALFW57uKXQ/2xfhPPbI
 qi0cTyXNYYY28kRdprERyV1w4K8W8V6L2YUt3N8LWuPNsI9pHSSQQDKru2JIR1T5
 rHeC41JSR6iw8rBXtkCj1YhGbH5P8CP3fxlikuKo3Q4PHCjVJo8ZpzYU/Ci8FFCL
 g/g6DLb9/AHtIhJ8WgcRcxbRNkdyGUc2w9uh6c3rBVS4gwFm/44=
 =2pvu
 -----END PGP SIGNATURE-----

Merge 5.10.188 into android12-5.10-lts

Changes in 5.10.188
	media: atomisp: fix "variable dereferenced before check 'asd'"
	x86/smp: Use dedicated cache-line for mwait_play_dead()
	can: isotp: isotp_sendmsg(): fix return error fix on TX path
	video: imsttfb: check for ioremap() failures
	fbdev: imsttfb: Fix use after free bug in imsttfb_probe
	HID: wacom: Use ktime_t rather than int when dealing with timestamps
	HID: logitech-hidpp: add HIDPP_QUIRK_DELAYED_INIT for the T651.
	Revert "thermal/drivers/mediatek: Use devm_of_iomap to avoid resource leak in mtk_thermal_probe"
	scripts/tags.sh: Resolve gtags empty index generation
	drm/amdgpu: Validate VM ioctl flags.
	nubus: Partially revert proc_create_single_data() conversion
	fs: pipe: reveal missing function protoypes
	x86/resctrl: Only show tasks' pid in current pid namespace
	blk-iocost: use spin_lock_irqsave in adjust_inuse_and_calc_cost
	md/raid10: check slab-out-of-bounds in md_bitmap_get_counter
	md/raid10: fix overflow of md/safe_mode_delay
	md/raid10: fix wrong setting of max_corr_read_errors
	md/raid10: fix null-ptr-deref of mreplace in raid10_sync_request
	md/raid10: fix io loss while replacement replace rdev
	irqchip/jcore-aic: Kill use of irq_create_strict_mappings()
	irqchip/jcore-aic: Fix missing allocation of IRQ descriptors
	posix-timers: Prevent RT livelock in itimer_delete()
	tracing/timer: Add missing hrtimer modes to decode_hrtimer_mode().
	clocksource/drivers/cadence-ttc: Fix memory leak in ttc_timer_probe
	PM: domains: fix integer overflow issues in genpd_parse_state()
	perf/arm-cmn: Fix DTC reset
	powercap: RAPL: Fix CONFIG_IOSF_MBI dependency
	ARM: 9303/1: kprobes: avoid missing-declaration warnings
	cpufreq: intel_pstate: Fix energy_performance_preference for passive
	thermal/drivers/sun8i: Fix some error handling paths in sun8i_ths_probe()
	rcuscale: Console output claims too few grace periods
	rcuscale: Always log error message
	rcuscale: Move shutdown from wait_event() to wait_event_idle()
	rcu/rcuscale: Move rcu_scale_*() after kfree_scale_cleanup()
	rcu/rcuscale: Stop kfree_scale_thread thread(s) after unloading rcuscale
	perf/ibs: Fix interface via core pmu events
	x86/mm: Fix __swp_entry_to_pte() for Xen PV guests
	evm: Complete description of evm_inode_setattr()
	ima: Fix build warnings
	pstore/ram: Add check for kstrdup
	igc: Enable and fix RX hash usage by netstack
	wifi: ath9k: fix AR9003 mac hardware hang check register offset calculation
	wifi: ath9k: avoid referencing uninit memory in ath9k_wmi_ctrl_rx
	samples/bpf: Fix buffer overflow in tcp_basertt
	spi: spi-geni-qcom: Correct CS_TOGGLE bit in SPI_TRANS_CFG
	wifi: wilc1000: fix for absent RSN capabilities WFA testcase
	wifi: mwifiex: Fix the size of a memory allocation in mwifiex_ret_802_11_scan()
	bpf: Remove extra lock_sock for TCP_ZEROCOPY_RECEIVE
	sctp: add bpf_bypass_getsockopt proto callback
	libbpf: fix offsetof() and container_of() to work with CO-RE
	nfc: constify several pointers to u8, char and sk_buff
	nfc: llcp: fix possible use of uninitialized variable in nfc_llcp_send_connect()
	bpftool: JIT limited misreported as negative value on aarch64
	regulator: core: Fix more error checking for debugfs_create_dir()
	regulator: core: Streamline debugfs operations
	wifi: orinoco: Fix an error handling path in spectrum_cs_probe()
	wifi: orinoco: Fix an error handling path in orinoco_cs_probe()
	wifi: atmel: Fix an error handling path in atmel_probe()
	wl3501_cs: Fix misspelling and provide missing documentation
	net: create netdev->dev_addr assignment helpers
	wl3501_cs: use eth_hw_addr_set()
	wifi: wl3501_cs: Fix an error handling path in wl3501_probe()
	wifi: ray_cs: Utilize strnlen() in parse_addr()
	wifi: ray_cs: Drop useless status variable in parse_addr()
	wifi: ray_cs: Fix an error handling path in ray_probe()
	wifi: ath9k: don't allow to overwrite ENDPOINT0 attributes
	wifi: rsi: Do not configure WoWlan in shutdown hook if not enabled
	wifi: rsi: Do not set MMC_PM_KEEP_POWER in shutdown
	watchdog/perf: define dummy watchdog_update_hrtimer_threshold() on correct config
	watchdog/perf: more properly prevent false positives with turbo modes
	kexec: fix a memory leak in crash_shrink_memory()
	memstick r592: make memstick_debug_get_tpc_name() static
	wifi: ath9k: Fix possible stall on ath9k_txq_list_has_key()
	rtnetlink: extend RTEXT_FILTER_SKIP_STATS to IFLA_VF_INFO
	wifi: iwlwifi: pull from TXQs with softirqs disabled
	wifi: cfg80211: rewrite merging of inherited elements
	wifi: ath9k: convert msecs to jiffies where needed
	igc: Fix race condition in PTP tx code
	net: stmmac: fix double serdes powerdown
	netlink: fix potential deadlock in netlink_set_err()
	netlink: do not hard code device address lenth in fdb dumps
	selftests: rtnetlink: remove netdevsim device after ipsec offload test
	gtp: Fix use-after-free in __gtp_encap_destroy().
	net: axienet: Move reset before 64-bit DMA detection
	sfc: fix crash when reading stats while NIC is resetting
	nfc: llcp: simplify llcp_sock_connect() error paths
	net: nfc: Fix use-after-free caused by nfc_llcp_find_local
	lib/ts_bm: reset initial match offset for every block of text
	netfilter: conntrack: dccp: copy entire header to stack buffer, not just basic one
	netfilter: nf_conntrack_sip: fix the ct_sip_parse_numerical_param() return value.
	ipvlan: Fix return value of ipvlan_queue_xmit()
	netlink: Add __sock_i_ino() for __netlink_diag_dump().
	radeon: avoid double free in ci_dpm_init()
	drm/amd/display: Explicitly specify update type per plane info change
	Input: drv260x - sleep between polling GO bit
	drm/bridge: tc358768: always enable HS video mode
	drm/bridge: tc358768: fix PLL parameters computation
	drm/bridge: tc358768: fix PLL target frequency
	drm/bridge: tc358768: fix TCLK_ZEROCNT computation
	drm/bridge: tc358768: Add atomic_get_input_bus_fmts() implementation
	drm/bridge: tc358768: fix TCLK_TRAILCNT computation
	drm/bridge: tc358768: fix THS_ZEROCNT computation
	drm/bridge: tc358768: fix TXTAGOCNT computation
	drm/bridge: tc358768: fix THS_TRAILCNT computation
	drm/vram-helper: fix function names in vram helper doc
	ARM: dts: BCM5301X: Drop "clock-names" from the SPI node
	ARM: dts: meson8b: correct uart_B and uart_C clock references
	Input: adxl34x - do not hardcode interrupt trigger type
	drm: sun4i_tcon: use devm_clk_get_enabled in `sun4i_tcon_init_clocks`
	drm/panel: sharp-ls043t1le01: adjust mode settings
	ARM: dts: stm32: Move ethernet MAC EEPROM from SoM to carrier boards
	bus: ti-sysc: Fix dispc quirk masking bool variables
	arm64: dts: microchip: sparx5: do not use PSCI on reference boards
	RDMA/bnxt_re: Disable/kill tasklet only if it is enabled
	RDMA/bnxt_re: Fix to remove unnecessary return labels
	RDMA/bnxt_re: Use unique names while registering interrupts
	RDMA/bnxt_re: Remove a redundant check inside bnxt_re_update_gid
	RDMA/bnxt_re: Fix to remove an unnecessary log
	ARM: dts: gta04: Move model property out of pinctrl node
	arm64: dts: qcom: msm8916: correct camss unit address
	arm64: dts: qcom: msm8994: correct SPMI unit address
	arm64: dts: qcom: msm8996: correct camss unit address
	drm/panel: simple: fix active size for Ampire AM-480272H3TMQW-T01H
	ARM: ep93xx: fix missing-prototype warnings
	ARM: omap2: fix missing tick_broadcast() prototype
	arm64: dts: qcom: apq8096: fix fixed regulator name property
	ARM: dts: stm32: Shorten the AV96 HDMI sound card name
	memory: brcmstb_dpfe: fix testing array offset after use
	ASoC: es8316: Increment max value for ALC Capture Target Volume control
	ASoC: es8316: Do not set rate constraints for unsupported MCLKs
	ARM: dts: meson8: correct uart_B and uart_C clock references
	soc/fsl/qe: fix usb.c build errors
	IB/hfi1: Use bitmap_zalloc() when applicable
	IB/hfi1: Fix sdma.h tx->num_descs off-by-one errors
	IB/hfi1: Fix wrong mmu_node used for user SDMA packet after invalidate
	RDMA: Remove uverbs_ex_cmd_mask values that are linked to functions
	RDMA/hns: Fix coding style issues
	RDMA/hns: Use refcount_t APIs for HEM
	RDMA/hns: Clean the hardware related code for HEM
	RDMA/hns: Fix hns_roce_table_get return value
	ARM: dts: iwg20d-q7-common: Fix backlight pwm specifier
	arm64: dts: renesas: ulcb-kf: Remove flow control for SCIF1
	fbdev: omapfb: lcd_mipid: Fix an error handling path in mipid_spi_probe()
	arm64: dts: ti: k3-j7200: Fix physical address of pin
	ARM: dts: stm32: Fix audio routing on STM32MP15xx DHCOM PDK2
	ARM: dts: stm32: fix i2s endpoint format property for stm32mp15xx-dkx
	hwmon: (gsc-hwmon) fix fan pwm temperature scaling
	hwmon: (adm1275) enable adm1272 temperature reporting
	hwmon: (adm1275) Allow setting sample averaging
	hwmon: (pmbus/adm1275) Fix problems with temperature monitoring on ADM1272
	ARM: dts: BCM5301X: fix duplex-full => full-duplex
	drm/amdkfd: Fix potential deallocation of previously deallocated memory.
	drm/radeon: fix possible division-by-zero errors
	amdgpu: validate offset_in_bo of drm_amdgpu_gem_va
	RDMA/bnxt_re: wraparound mbox producer index
	RDMA/bnxt_re: Avoid calling wake_up threads from spin_lock context
	clk: imx: clk-imx8mn: fix memory leak in imx8mn_clocks_probe
	clk: imx: clk-imx8mp: improve error handling in imx8mp_clocks_probe()
	clk: tegra: tegra124-emc: Fix potential memory leak
	ALSA: ac97: Fix possible NULL dereference in snd_ac97_mixer
	drm/msm/dpu: do not enable color-management if DSPPs are not available
	drm/msm/dp: Free resources after unregistering them
	clk: vc5: check memory returned by kasprintf()
	clk: cdce925: check return value of kasprintf()
	clk: si5341: Allow different output VDD_SEL values
	clk: si5341: Add sysfs properties to allow checking/resetting device faults
	clk: si5341: return error if one synth clock registration fails
	clk: si5341: check return value of {devm_}kasprintf()
	clk: si5341: free unused memory on probe failure
	clk: keystone: sci-clk: check return value of kasprintf()
	clk: ti: clkctrl: check return value of kasprintf()
	drivers: meson: secure-pwrc: always enable DMA domain
	ovl: update of dentry revalidate flags after copy up
	ASoC: imx-audmix: check return value of devm_kasprintf()
	PCI: cadence: Fix Gen2 Link Retraining process
	scsi: qedf: Fix NULL dereference in error handling
	pinctrl: bcm2835: Handle gpiochip_add_pin_range() errors
	PCI/ASPM: Disable ASPM on MFD function removal to avoid use-after-free
	scsi: 3w-xxxx: Add error handling for initialization failure in tw_probe()
	PCI: pciehp: Cancel bringup sequence if card is not present
	PCI: ftpci100: Release the clock resources
	PCI: Add pci_clear_master() stub for non-CONFIG_PCI
	perf bench: Use unbuffered output when pipe/tee'ing to a file
	perf bench: Add missing setlocale() call to allow usage of %'d style formatting
	pinctrl: cherryview: Return correct value if pin in push-pull mode
	kcsan: Don't expect 64 bits atomic builtins from 32 bits architectures
	perf script: Fixup 'struct evsel_script' method prefix
	perf script: Fix allocation of evsel->priv related to per-event dump files
	perf dwarf-aux: Fix off-by-one in die_get_varname()
	pinctrl: at91-pio4: check return value of devm_kasprintf()
	powerpc/powernv/sriov: perform null check on iov before dereferencing iov
	mm: rename pud_page_vaddr to pud_pgtable and make it return pmd_t *
	mm: rename p4d_page_vaddr to p4d_pgtable and make it return pud_t *
	powerpc/book3s64/mm: Fix DirectMap stats in /proc/meminfo
	powerpc/mm/dax: Fix the condition when checking if altmap vmemap can cross-boundary
	hwrng: virtio - add an internal buffer
	hwrng: virtio - don't wait on cleanup
	hwrng: virtio - don't waste entropy
	hwrng: virtio - always add a pending request
	hwrng: virtio - Fix race on data_avail and actual data
	crypto: nx - fix build warnings when DEBUG_FS is not enabled
	modpost: fix section mismatch message for R_ARM_ABS32
	modpost: fix section mismatch message for R_ARM_{PC24,CALL,JUMP24}
	crypto: marvell/cesa - Fix type mismatch warning
	modpost: fix off by one in is_executable_section()
	ARC: define ASM_NL and __ALIGN(_STR) outside #ifdef __ASSEMBLY__ guard
	NFSv4.1: freeze the session table upon receiving NFS4ERR_BADSESSION
	dax: Fix dax_mapping_release() use after free
	dax: Introduce alloc_dev_dax_id()
	hwrng: st - keep clock enabled while hwrng is registered
	io_uring: ensure IOPOLL locks around deferred work
	USB: serial: option: add LARA-R6 01B PIDs
	usb: dwc3: gadget: Propagate core init errors to UDC during pullup
	phy: tegra: xusb: Clear the driver reference in usb-phy dev
	block: fix signed int overflow in Amiga partition support
	block: change all __u32 annotations to __be32 in affs_hardblocks.h
	SUNRPC: Fix UAF in svc_tcp_listen_data_ready()
	w1: w1_therm: fix locking behavior in convert_t
	w1: fix loop in w1_fini()
	sh: j2: Use ioremap() to translate device tree address into kernel memory
	serial: 8250: omap: Fix freeing of resources on failed register
	clk: qcom: gcc-ipq6018: Use floor ops for sdcc clocks
	media: usb: Check az6007_read() return value
	media: videodev2.h: Fix struct v4l2_input tuner index comment
	media: usb: siano: Fix warning due to null work_func_t function pointer
	clk: qcom: reset: Allow specifying custom reset delay
	clk: qcom: reset: support resetting multiple bits
	clk: qcom: ipq6018: fix networking resets
	usb: dwc3: qcom: Fix potential memory leak
	usb: gadget: u_serial: Add null pointer check in gserial_suspend
	extcon: Fix kernel doc of property fields to avoid warnings
	extcon: Fix kernel doc of property capability fields to avoid warnings
	usb: phy: phy-tahvo: fix memory leak in tahvo_usb_probe()
	usb: hide unused usbfs_notify_suspend/resume functions
	serial: 8250: lock port for stop_rx() in omap8250_irq()
	serial: 8250: lock port for UART_IER access in omap8250_irq()
	kernfs: fix missing kernfs_idr_lock to remove an ID from the IDR
	coresight: Fix loss of connection info when a module is unloaded
	mfd: rt5033: Drop rt5033-battery sub-device
	media: venus: helpers: Fix ALIGN() of non power of two
	media: atomisp: gmin_platform: fix out_len in gmin_get_config_dsm_var()
	KVM: s390: fix KVM_S390_GET_CMMA_BITS for GFNs in memslot holes
	usb: dwc3: qcom: Release the correct resources in dwc3_qcom_remove()
	usb: dwc3: qcom: Fix an error handling path in dwc3_qcom_probe()
	usb: common: usb-conn-gpio: Set last role to unknown before initial detection
	usb: dwc3-meson-g12a: Fix an error handling path in dwc3_meson_g12a_probe()
	mfd: intel-lpss: Add missing check for platform_get_resource
	Revert "usb: common: usb-conn-gpio: Set last role to unknown before initial detection"
	serial: 8250_omap: Use force_suspend and resume for system suspend
	test_firmware: return ENOMEM instead of ENOSPC on failed memory allocation
	mfd: stmfx: Fix error path in stmfx_chip_init
	mfd: stmfx: Nullify stmfx->vdd in case of error
	KVM: s390: vsie: fix the length of APCB bitmap
	mfd: stmpe: Only disable the regulators if they are enabled
	phy: tegra: xusb: check return value of devm_kzalloc()
	pwm: imx-tpm: force 'real_period' to be zero in suspend
	pwm: sysfs: Do not apply state to already disabled PWMs
	rtc: st-lpc: Release some resources in st_rtc_probe() in case of error
	media: cec: i2c: ch7322: also select REGMAP
	sctp: fix potential deadlock on &net->sctp.addr_wq_lock
	Add MODULE_FIRMWARE() for FIRMWARE_TG357766.
	net: dsa: vsc73xx: fix MTU configuration
	spi: bcm-qspi: return error if neither hif_mspi nor mspi is available
	mailbox: ti-msgmgr: Fill non-message tx data fields with 0x0
	f2fs: fix error path handling in truncate_dnode()
	octeontx2-af: Fix mapping for NIX block from CGX connection
	powerpc: allow PPC_EARLY_DEBUG_CPM only when SERIAL_CPM=y
	net: bridge: keep ports without IFF_UNICAST_FLT in BR_PROMISC mode
	tcp: annotate data races in __tcp_oow_rate_limited()
	xsk: Honor SO_BINDTODEVICE on bind
	net/sched: act_pedit: Add size check for TCA_PEDIT_PARMS_EX
	pptp: Fix fib lookup calls.
	net: dsa: tag_sja1105: fix MAC DA patching from meta frames
	s390/qeth: Fix vipa deletion
	sh: dma: Fix DMA channel offset calculation
	apparmor: fix missing error check for rhashtable_insert_fast
	i2c: xiic: Defer xiic_wakeup() and __xiic_start_xfer() in xiic_process()
	i2c: xiic: Don't try to handle more interrupt events after error
	ALSA: jack: Fix mutex call in snd_jack_report()
	i2c: qup: Add missing unwind goto in qup_i2c_probe()
	NFSD: add encoding of op_recall flag for write delegation
	io_uring: wait interruptibly for request completions on exit
	mmc: core: disable TRIM on Kingston EMMC04G-M627
	mmc: core: disable TRIM on Micron MTFC4GACAJCN-1M
	mmc: mmci: Set PROBE_PREFER_ASYNCHRONOUS
	mmc: sdhci: fix DMA configure compatibility issue when 64bit DMA mode is used.
	bcache: fixup btree_cache_wait list damage
	bcache: Remove unnecessary NULL point check in node allocations
	bcache: Fix __bch_btree_node_alloc to make the failure behavior consistent
	um: Use HOST_DIR for mrproper
	integrity: Fix possible multiple allocation in integrity_inode_get()
	autofs: use flexible array in ioctl structure
	shmem: use ramfs_kill_sb() for kill_sb method of ramfs-based tmpfs
	jffs2: reduce stack usage in jffs2_build_xattr_subsystem()
	fs: avoid empty option when generating legacy mount string
	ext4: Remove ext4 locking of moved directory
	Revert "f2fs: fix potential corruption when moving a directory"
	fs: Establish locking order for unrelated directories
	fs: Lock moved directories
	btrfs: add handling for RAID1C23/DUP to btrfs_reduce_alloc_profile
	btrfs: fix race when deleting quota root from the dirty cow roots list
	ASoC: mediatek: mt8173: Fix irq error path
	ASoC: mediatek: mt8173: Fix snd_soc_component_initialize error path
	ARM: orion5x: fix d2net gpio initialization
	leds: trigger: netdev: Recheck NETDEV_LED_MODE_LINKUP on dev rename
	fs: no need to check source
	fanotify: disallow mount/sb marks on kernel internal pseudo fs
	tpm, tpm_tis: Claim locality in interrupt handler
	selftests/bpf: Add verifier test for PTR_TO_MEM spill
	block: add overflow checks for Amiga partition support
	sh: pgtable-3level: Fix cast to pointer from integer of different size
	netfilter: nf_tables: use net_generic infra for transaction data
	netfilter: nf_tables: add rescheduling points during loop detection walks
	netfilter: nf_tables: incorrect error path handling with NFT_MSG_NEWRULE
	netfilter: nf_tables: fix chain binding transaction logic
	netfilter: nf_tables: add NFT_TRANS_PREPARE_ERROR to deal with bound set/chain
	netfilter: nf_tables: reject unbound anonymous set before commit phase
	netfilter: nf_tables: reject unbound chain set before commit phase
	netfilter: nftables: rename set element data activation/deactivation functions
	netfilter: nf_tables: drop map element references from preparation phase
	netfilter: nf_tables: unbind non-anonymous set if rule construction fails
	netfilter: nf_tables: fix scheduling-while-atomic splat
	netfilter: conntrack: Avoid nf_ct_helper_hash uses after free
	netfilter: nf_tables: do not ignore genmask when looking up chain by id
	netfilter: nf_tables: prevent OOB access in nft_byteorder_eval
	wireguard: queueing: use saner cpu selection wrapping
	wireguard: netlink: send staged packets when setting initial private key
	tty: serial: fsl_lpuart: add earlycon for imx8ulp platform
	rcu-tasks: Mark ->trc_reader_nesting data races
	rcu-tasks: Mark ->trc_reader_special.b.need_qs data races
	rcu-tasks: Simplify trc_read_check_handler() atomic operations
	block/partition: fix signedness issue for Amiga partitions
	io_uring: Use io_schedule* in cqring wait
	io_uring: add reschedule point to handle_tw_list()
	net: lan743x: Don't sleep in atomic context
	workqueue: clean up WORK_* constant types, clarify masking
	drm/panel: simple: Add connector_type for innolux_at043tn24
	drm/panel: simple: Add Powertip PH800480T013 drm_display_mode flags
	igc: Remove delay during TX ring configuration
	net/mlx5e: fix double free in mlx5e_destroy_flow_table
	net/mlx5e: Check for NOT_READY flag state after locking
	igc: set TP bit in 'supported' and 'advertising' fields of ethtool_link_ksettings
	scsi: qla2xxx: Fix error code in qla2x00_start_sp()
	net: mvneta: fix txq_map in case of txq_number==1
	net/sched: cls_fw: Fix improper refcount update leads to use-after-free
	gve: Set default duplex configuration to full
	ionic: remove WARN_ON to prevent panic_on_warn
	net: bgmac: postpone turning IRQs off to avoid SoC hangs
	net: prevent skb corruption on frag list segmentation
	icmp6: Fix null-ptr-deref of ip6_null_entry->rt6i_idev in icmp6_dev().
	udp6: fix udp6_ehashfn() typo
	ntb: idt: Fix error handling in idt_pci_driver_init()
	NTB: amd: Fix error handling in amd_ntb_pci_driver_init()
	ntb: intel: Fix error handling in intel_ntb_pci_driver_init()
	NTB: ntb_transport: fix possible memory leak while device_register() fails
	NTB: ntb_tool: Add check for devm_kcalloc
	ipv6/addrconf: fix a potential refcount underflow for idev
	platform/x86: wmi: remove unnecessary argument
	platform/x86: wmi: use guid_t and guid_equal()
	platform/x86: wmi: move variables
	platform/x86: wmi: Break possible infinite loop when parsing GUID
	igc: Fix launchtime before start of cycle
	igc: Fix inserting of empty frame for launchtime
	riscv: bpf: Move bpf_jit_alloc_exec() and bpf_jit_free_exec() to core
	riscv: bpf: Avoid breaking W^X
	bpf, riscv: Support riscv jit to provide bpf_line_info
	riscv, bpf: Fix inconsistent JIT image generation
	erofs: avoid infinite loop in z_erofs_do_read_page() when reading beyond EOF
	wifi: airo: avoid uninitialized warning in airo_get_rate()
	net/sched: flower: Ensure both minimum and maximum ports are specified
	netdevsim: fix uninitialized data in nsim_dev_trap_fa_cookie_write()
	net/sched: make psched_mtu() RTNL-less safe
	net/sched: sch_qfq: refactor parsing of netlink parameters
	net/sched: sch_qfq: account for stab overhead in qfq_enqueue
	nvme-pci: fix DMA direction of unmapping integrity data
	f2fs: fix to avoid NULL pointer dereference f2fs_write_end_io()
	pinctrl: amd: Fix mistake in handling clearing pins at startup
	pinctrl: amd: Detect internal GPIO0 debounce handling
	pinctrl: amd: Only use special debounce behavior for GPIO 0
	tpm: tpm_vtpm_proxy: fix a race condition in /dev/vtpmx creation
	mtd: rawnand: meson: fix unaligned DMA buffers handling
	net: bcmgenet: Ensure MDIO unregistration has clocks enabled
	powerpc: Fail build if using recordmcount with binutils v2.37
	misc: fastrpc: Create fastrpc scalar with correct buffer count
	erofs: fix compact 4B support for 16k block size
	MIPS: Loongson: Fix cpu_probe_loongson() again
	ext4: Fix reusing stale buffer heads from last failed mounting
	ext4: fix wrong unit use in ext4_mb_clear_bb
	ext4: get block from bh in ext4_free_blocks for fast commit replay
	ext4: fix wrong unit use in ext4_mb_new_blocks
	ext4: only update i_reserved_data_blocks on successful block allocation
	jfs: jfs_dmap: Validate db_l2nbperpage while mounting
	hwrng: imx-rngc - fix the timeout for init and self check
	PCI/PM: Avoid putting EloPOS E2/S2/H2 PCIe Ports in D3cold
	PCI: Add function 1 DMA alias quirk for Marvell 88SE9235
	PCI: qcom: Disable write access to read only registers for IP v2.3.3
	PCI: rockchip: Assert PCI Configuration Enable bit after probe
	PCI: rockchip: Write PCI Device ID to correct register
	PCI: rockchip: Add poll and timeout to wait for PHY PLLs to be locked
	PCI: rockchip: Fix legacy IRQ generation for RK3399 PCIe endpoint core
	PCI: rockchip: Use u32 variable to access 32-bit registers
	PCI: rockchip: Set address alignment for endpoint mode
	misc: pci_endpoint_test: Free IRQs before removing the device
	misc: pci_endpoint_test: Re-init completion for every test
	md/raid0: add discard support for the 'original' layout
	fs: dlm: return positive pid value for F_GETLK
	drm/atomic: Allow vblank-enabled + self-refresh "disable"
	drm/rockchip: vop: Leave vblank enabled in self-refresh
	drm/amd/display: Correct `DMUB_FW_VERSION` macro
	serial: atmel: don't enable IRQs prematurely
	tty: serial: samsung_tty: Fix a memory leak in s3c24xx_serial_getclk() in case of error
	tty: serial: samsung_tty: Fix a memory leak in s3c24xx_serial_getclk() when iterating clk
	firmware: stratix10-svc: Fix a potential resource leak in svc_create_memory_pool()
	ceph: don't let check_caps skip sending responses for revoke msgs
	xhci: Fix resume issue of some ZHAOXIN hosts
	xhci: Fix TRB prefetch issue of ZHAOXIN hosts
	xhci: Show ZHAOXIN xHCI root hub speed correctly
	meson saradc: fix clock divider mask length
	Revert "8250: add support for ASIX devices with a FIFO bug"
	s390/decompressor: fix misaligned symbol build error
	tracing/histograms: Add histograms to hist_vars if they have referenced variables
	samples: ftrace: Save required argument registers in sample trampolines
	net: ena: fix shift-out-of-bounds in exponential backoff
	ring-buffer: Fix deadloop issue on reading trace_pipe
	xtensa: ISS: fix call to split_if_spec
	tracing: Fix null pointer dereference in tracing_err_log_open()
	tracing/probes: Fix not to count error code to total length
	scsi: qla2xxx: Wait for io return on terminate rport
	scsi: qla2xxx: Array index may go out of bound
	scsi: qla2xxx: Fix buffer overrun
	scsi: qla2xxx: Fix potential NULL pointer dereference
	scsi: qla2xxx: Check valid rport returned by fc_bsg_to_rport()
	scsi: qla2xxx: Correct the index of array
	scsi: qla2xxx: Pointer may be dereferenced
	scsi: qla2xxx: Remove unused nvme_ls_waitq wait queue
	net/sched: sch_qfq: reintroduce lmax bound check for MTU
	RDMA/cma: Ensure rdma_addr_cancel() happens before issuing more requests
	drm/atomic: Fix potential use-after-free in nonblocking commits
	ALSA: hda/realtek - remove 3k pull low procedure
	ALSA: hda/realtek: Enable Mute LED on HP Laptop 15s-eq2xxx
	keys: Fix linking a duplicate key to a keyring's assoc_array
	perf probe: Add test for regression introduced by switch to die_get_decl_file()
	btrfs: fix warning when putting transaction with qgroups enabled after abort
	fuse: revalidate: don't invalidate if interrupted
	selftests: tc: set timeout to 15 minutes
	selftests: tc: add 'ct' action kconfig dep
	regmap: Drop initial version of maximum transfer length fixes
	regmap: Account for register length in SMBus I/O limits
	can: bcm: Fix UAF in bcm_proc_show()
	drm/client: Fix memory leak in drm_client_target_cloned
	drm/client: Fix memory leak in drm_client_modeset_probe
	ASoC: fsl_sai: Disable bit clock with transmitter
	ext4: correct inline offset when handling xattrs in inode body
	debugobjects: Recheck debug_objects_enabled before reporting
	nbd: Add the maximum limit of allocated index in nbd_dev_add
	md: fix data corruption for raid456 when reshape restart while grow up
	md/raid10: prevent soft lockup while flush writes
	posix-timers: Ensure timer ID search-loop limit is valid
	btrfs: add xxhash to fast checksum implementations
	ACPI: button: Add lid disable DMI quirk for Nextbook Ares 8A
	ACPI: video: Add backlight=native DMI quirk for Apple iMac11,3
	ACPI: video: Add backlight=native DMI quirk for Lenovo ThinkPad X131e (3371 AMD version)
	arm64: set __exception_irq_entry with __irq_entry as a default
	arm64: mm: fix VA-range sanity check
	sched/fair: Don't balance task to its current running CPU
	wifi: ath11k: fix registration of 6Ghz-only phy without the full channel range
	bpf: Address KCSAN report on bpf_lru_list
	devlink: report devlink_port_type_warn source device
	wifi: wext-core: Fix -Wstringop-overflow warning in ioctl_standard_iw_point()
	wifi: iwlwifi: mvm: avoid baid size integer overflow
	igb: Fix igb_down hung on surprise removal
	spi: bcm63xx: fix max prepend length
	fbdev: imxfb: warn about invalid left/right margin
	pinctrl: amd: Use amd_pinconf_set() for all config options
	net: ethernet: ti: cpsw_ale: Fix cpsw_ale_get_field()/cpsw_ale_set_field()
	bridge: Add extack warning when enabling STP in netns.
	iavf: Fix use-after-free in free_netdev
	iavf: Fix out-of-bounds when setting channels on remove
	security: keys: Modify mismatched function name
	octeontx2-pf: Dont allocate BPIDs for LBK interfaces
	tcp: annotate data-races around tcp_rsk(req)->ts_recent
	net: ipv4: Use kfree_sensitive instead of kfree
	net:ipv6: check return value of pskb_trim()
	Revert "tcp: avoid the lookup process failing to get sk in ehash table"
	fbdev: au1200fb: Fix missing IRQ check in au1200fb_drv_probe
	llc: Don't drop packet from non-root netns.
	netfilter: nf_tables: fix spurious set element insertion failure
	netfilter: nf_tables: can't schedule in nft_chain_validate
	netfilter: nft_set_pipapo: fix improper element removal
	netfilter: nf_tables: skip bound chain in netns release path
	netfilter: nf_tables: skip bound chain on rule flush
	tcp: annotate data-races around tp->tcp_tx_delay
	tcp: annotate data-races around tp->keepalive_time
	tcp: annotate data-races around tp->keepalive_intvl
	tcp: annotate data-races around tp->keepalive_probes
	net: Introduce net.ipv4.tcp_migrate_req.
	tcp: Fix data-races around sysctl_tcp_syn(ack)?_retries.
	tcp: annotate data-races around icsk->icsk_syn_retries
	tcp: annotate data-races around tp->linger2
	tcp: annotate data-races around rskq_defer_accept
	tcp: annotate data-races around tp->notsent_lowat
	tcp: annotate data-races around icsk->icsk_user_timeout
	tcp: annotate data-races around fastopenq.max_qlen
	net: phy: prevent stale pointer dereference in phy_init()
	tracing/histograms: Return an error if we fail to add histogram to hist_vars list
	tracing: Fix memory leak of iter->temp when reading trace_pipe
	ftrace: Store the order of pages allocated in ftrace_page
	ftrace: Fix possible warning on checking all pages used in ftrace_process_locs()
	Linux 5.10.188

Change-Id: Ibcc1adc43df5b8f649b12078eedd5d4f57de4578
Signed-off-by: Greg Kroah-Hartman <gregkh@google.com>
2023-08-03 11:23:27 +00:00

1514 lines
41 KiB
C

/* SPDX-License-Identifier: GPL-2.0 */
#ifndef _LINUX_PGTABLE_H
#define _LINUX_PGTABLE_H
#include <linux/pfn.h>
#include <asm/pgtable.h>
#ifndef __ASSEMBLY__
#ifdef CONFIG_MMU
#include <linux/mm_types.h>
#include <linux/bug.h>
#include <linux/errno.h>
#include <asm-generic/pgtable_uffd.h>
#if 5 - defined(__PAGETABLE_P4D_FOLDED) - defined(__PAGETABLE_PUD_FOLDED) - \
defined(__PAGETABLE_PMD_FOLDED) != CONFIG_PGTABLE_LEVELS
#error CONFIG_PGTABLE_LEVELS is not consistent with __PAGETABLE_{P4D,PUD,PMD}_FOLDED
#endif
/*
* On almost all architectures and configurations, 0 can be used as the
* upper ceiling to free_pgtables(): on many architectures it has the same
* effect as using TASK_SIZE. However, there is one configuration which
* must impose a more careful limit, to avoid freeing kernel pgtables.
*/
#ifndef USER_PGTABLES_CEILING
#define USER_PGTABLES_CEILING 0UL
#endif
/*
* A page table page can be thought of an array like this: pXd_t[PTRS_PER_PxD]
*
* The pXx_index() functions return the index of the entry in the page
* table page which would control the given virtual address
*
* As these functions may be used by the same code for different levels of
* the page table folding, they are always available, regardless of
* CONFIG_PGTABLE_LEVELS value. For the folded levels they simply return 0
* because in such cases PTRS_PER_PxD equals 1.
*/
static inline unsigned long pte_index(unsigned long address)
{
return (address >> PAGE_SHIFT) & (PTRS_PER_PTE - 1);
}
#define pte_index pte_index
#ifndef pmd_index
static inline unsigned long pmd_index(unsigned long address)
{
return (address >> PMD_SHIFT) & (PTRS_PER_PMD - 1);
}
#define pmd_index pmd_index
#endif
#ifndef pud_index
static inline unsigned long pud_index(unsigned long address)
{
return (address >> PUD_SHIFT) & (PTRS_PER_PUD - 1);
}
#define pud_index pud_index
#endif
#ifndef pgd_index
/* Must be a compile-time constant, so implement it as a macro */
#define pgd_index(a) (((a) >> PGDIR_SHIFT) & (PTRS_PER_PGD - 1))
#endif
#ifndef pte_offset_kernel
static inline pte_t *pte_offset_kernel(pmd_t *pmd, unsigned long address)
{
return (pte_t *)pmd_page_vaddr(*pmd) + pte_index(address);
}
#define pte_offset_kernel pte_offset_kernel
#endif
#if defined(CONFIG_HIGHPTE)
#define pte_offset_map(dir, address) \
((pte_t *)kmap_atomic(pmd_page(*(dir))) + \
pte_index((address)))
#define pte_unmap(pte) kunmap_atomic((pte))
#else
#define pte_offset_map(dir, address) pte_offset_kernel((dir), (address))
#define pte_unmap(pte) ((void)(pte)) /* NOP */
#endif
/* Find an entry in the second-level page table.. */
#ifndef pmd_offset
static inline pmd_t *pmd_offset(pud_t *pud, unsigned long address)
{
return pud_pgtable(*pud) + pmd_index(address);
}
#define pmd_offset pmd_offset
#endif
#ifndef pud_offset
static inline pud_t *pud_offset(p4d_t *p4d, unsigned long address)
{
return p4d_pgtable(*p4d) + pud_index(address);
}
#define pud_offset pud_offset
#endif
static inline pgd_t *pgd_offset_pgd(pgd_t *pgd, unsigned long address)
{
return (pgd + pgd_index(address));
};
/*
* a shortcut to get a pgd_t in a given mm
*/
#ifndef pgd_offset
#define pgd_offset(mm, address) pgd_offset_pgd((mm)->pgd, (address))
#endif
/*
* a shortcut which implies the use of the kernel's pgd, instead
* of a process's
*/
#ifndef pgd_offset_k
#define pgd_offset_k(address) pgd_offset(&init_mm, (address))
#endif
/*
* In many cases it is known that a virtual address is mapped at PMD or PTE
* level, so instead of traversing all the page table levels, we can get a
* pointer to the PMD entry in user or kernel page table or translate a virtual
* address to the pointer in the PTE in the kernel page tables with simple
* helpers.
*/
static inline pmd_t *pmd_off(struct mm_struct *mm, unsigned long va)
{
return pmd_offset(pud_offset(p4d_offset(pgd_offset(mm, va), va), va), va);
}
static inline pmd_t *pmd_off_k(unsigned long va)
{
return pmd_offset(pud_offset(p4d_offset(pgd_offset_k(va), va), va), va);
}
static inline pte_t *virt_to_kpte(unsigned long vaddr)
{
pmd_t *pmd = pmd_off_k(vaddr);
return pmd_none(*pmd) ? NULL : pte_offset_kernel(pmd, vaddr);
}
#ifndef __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS
extern int ptep_set_access_flags(struct vm_area_struct *vma,
unsigned long address, pte_t *ptep,
pte_t entry, int dirty);
#endif
#ifndef __HAVE_ARCH_PMDP_SET_ACCESS_FLAGS
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
extern int pmdp_set_access_flags(struct vm_area_struct *vma,
unsigned long address, pmd_t *pmdp,
pmd_t entry, int dirty);
extern int pudp_set_access_flags(struct vm_area_struct *vma,
unsigned long address, pud_t *pudp,
pud_t entry, int dirty);
#else
static inline int pmdp_set_access_flags(struct vm_area_struct *vma,
unsigned long address, pmd_t *pmdp,
pmd_t entry, int dirty)
{
BUILD_BUG();
return 0;
}
static inline int pudp_set_access_flags(struct vm_area_struct *vma,
unsigned long address, pud_t *pudp,
pud_t entry, int dirty)
{
BUILD_BUG();
return 0;
}
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
#endif
#ifndef __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG
static inline int ptep_test_and_clear_young(struct vm_area_struct *vma,
unsigned long address,
pte_t *ptep)
{
pte_t pte = *ptep;
int r = 1;
if (!pte_young(pte))
r = 0;
else
set_pte_at(vma->vm_mm, address, ptep, pte_mkold(pte));
return r;
}
#endif
#ifndef __HAVE_ARCH_PMDP_TEST_AND_CLEAR_YOUNG
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
static inline int pmdp_test_and_clear_young(struct vm_area_struct *vma,
unsigned long address,
pmd_t *pmdp)
{
pmd_t pmd = *pmdp;
int r = 1;
if (!pmd_young(pmd))
r = 0;
else
set_pmd_at(vma->vm_mm, address, pmdp, pmd_mkold(pmd));
return r;
}
#else
static inline int pmdp_test_and_clear_young(struct vm_area_struct *vma,
unsigned long address,
pmd_t *pmdp)
{
BUILD_BUG();
return 0;
}
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
#endif
#ifndef __HAVE_ARCH_PTEP_CLEAR_YOUNG_FLUSH
int ptep_clear_flush_young(struct vm_area_struct *vma,
unsigned long address, pte_t *ptep);
#endif
#ifndef __HAVE_ARCH_PMDP_CLEAR_YOUNG_FLUSH
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
extern int pmdp_clear_flush_young(struct vm_area_struct *vma,
unsigned long address, pmd_t *pmdp);
#else
/*
* Despite relevant to THP only, this API is called from generic rmap code
* under PageTransHuge(), hence needs a dummy implementation for !THP
*/
static inline int pmdp_clear_flush_young(struct vm_area_struct *vma,
unsigned long address, pmd_t *pmdp)
{
BUILD_BUG();
return 0;
}
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
#endif
#ifndef __HAVE_ARCH_PTEP_GET_AND_CLEAR
static inline pte_t ptep_get_and_clear(struct mm_struct *mm,
unsigned long address,
pte_t *ptep)
{
pte_t pte = *ptep;
pte_clear(mm, address, ptep);
return pte;
}
#endif
#ifndef __HAVE_ARCH_PTEP_GET
static inline pte_t ptep_get(pte_t *ptep)
{
return READ_ONCE(*ptep);
}
#endif
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
#ifndef __HAVE_ARCH_PMDP_HUGE_GET_AND_CLEAR
static inline pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm,
unsigned long address,
pmd_t *pmdp)
{
pmd_t pmd = *pmdp;
pmd_clear(pmdp);
return pmd;
}
#endif /* __HAVE_ARCH_PMDP_HUGE_GET_AND_CLEAR */
#ifndef __HAVE_ARCH_PUDP_HUGE_GET_AND_CLEAR
static inline pud_t pudp_huge_get_and_clear(struct mm_struct *mm,
unsigned long address,
pud_t *pudp)
{
pud_t pud = *pudp;
pud_clear(pudp);
return pud;
}
#endif /* __HAVE_ARCH_PUDP_HUGE_GET_AND_CLEAR */
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
#ifndef __HAVE_ARCH_PMDP_HUGE_GET_AND_CLEAR_FULL
static inline pmd_t pmdp_huge_get_and_clear_full(struct vm_area_struct *vma,
unsigned long address, pmd_t *pmdp,
int full)
{
return pmdp_huge_get_and_clear(vma->vm_mm, address, pmdp);
}
#endif
#ifndef __HAVE_ARCH_PUDP_HUGE_GET_AND_CLEAR_FULL
static inline pud_t pudp_huge_get_and_clear_full(struct mm_struct *mm,
unsigned long address, pud_t *pudp,
int full)
{
return pudp_huge_get_and_clear(mm, address, pudp);
}
#endif
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
#ifndef __HAVE_ARCH_PTEP_GET_AND_CLEAR_FULL
static inline pte_t ptep_get_and_clear_full(struct mm_struct *mm,
unsigned long address, pte_t *ptep,
int full)
{
pte_t pte;
pte = ptep_get_and_clear(mm, address, ptep);
return pte;
}
#endif
/*
* If two threads concurrently fault at the same page, the thread that
* won the race updates the PTE and its local TLB/Cache. The other thread
* gives up, simply does nothing, and continues; on architectures where
* software can update TLB, local TLB can be updated here to avoid next page
* fault. This function updates TLB only, do nothing with cache or others.
* It is the difference with function update_mmu_cache.
*/
#ifndef __HAVE_ARCH_UPDATE_MMU_TLB
static inline void update_mmu_tlb(struct vm_area_struct *vma,
unsigned long address, pte_t *ptep)
{
}
#define __HAVE_ARCH_UPDATE_MMU_TLB
#endif
/*
* Some architectures may be able to avoid expensive synchronization
* primitives when modifications are made to PTE's which are already
* not present, or in the process of an address space destruction.
*/
#ifndef __HAVE_ARCH_PTE_CLEAR_NOT_PRESENT_FULL
static inline void pte_clear_not_present_full(struct mm_struct *mm,
unsigned long address,
pte_t *ptep,
int full)
{
pte_clear(mm, address, ptep);
}
#endif
#ifndef __HAVE_ARCH_PTEP_CLEAR_FLUSH
extern pte_t ptep_clear_flush(struct vm_area_struct *vma,
unsigned long address,
pte_t *ptep);
#endif
#ifndef __HAVE_ARCH_PMDP_HUGE_CLEAR_FLUSH
extern pmd_t pmdp_huge_clear_flush(struct vm_area_struct *vma,
unsigned long address,
pmd_t *pmdp);
extern pud_t pudp_huge_clear_flush(struct vm_area_struct *vma,
unsigned long address,
pud_t *pudp);
#endif
#ifndef __HAVE_ARCH_PTEP_SET_WRPROTECT
struct mm_struct;
static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long address, pte_t *ptep)
{
pte_t old_pte = *ptep;
set_pte_at(mm, address, ptep, pte_wrprotect(old_pte));
}
#endif
/*
* On some architectures hardware does not set page access bit when accessing
* memory page, it is responsibilty of software setting this bit. It brings
* out extra page fault penalty to track page access bit. For optimization page
* access bit can be set during all page fault flow on these arches.
* To be differentiate with macro pte_mkyoung, this macro is used on platforms
* where software maintains page access bit.
*/
#ifndef pte_sw_mkyoung
static inline pte_t pte_sw_mkyoung(pte_t pte)
{
return pte;
}
#define pte_sw_mkyoung pte_sw_mkyoung
#endif
#ifndef pte_savedwrite
#define pte_savedwrite pte_write
#endif
#ifndef pte_mk_savedwrite
#define pte_mk_savedwrite pte_mkwrite
#endif
#ifndef pte_clear_savedwrite
#define pte_clear_savedwrite pte_wrprotect
#endif
#ifndef pmd_savedwrite
#define pmd_savedwrite pmd_write
#endif
#ifndef pmd_mk_savedwrite
#define pmd_mk_savedwrite pmd_mkwrite
#endif
#ifndef pmd_clear_savedwrite
#define pmd_clear_savedwrite pmd_wrprotect
#endif
#ifndef __HAVE_ARCH_PMDP_SET_WRPROTECT
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
static inline void pmdp_set_wrprotect(struct mm_struct *mm,
unsigned long address, pmd_t *pmdp)
{
pmd_t old_pmd = *pmdp;
set_pmd_at(mm, address, pmdp, pmd_wrprotect(old_pmd));
}
#else
static inline void pmdp_set_wrprotect(struct mm_struct *mm,
unsigned long address, pmd_t *pmdp)
{
BUILD_BUG();
}
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
#endif
#ifndef __HAVE_ARCH_PUDP_SET_WRPROTECT
#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
static inline void pudp_set_wrprotect(struct mm_struct *mm,
unsigned long address, pud_t *pudp)
{
pud_t old_pud = *pudp;
set_pud_at(mm, address, pudp, pud_wrprotect(old_pud));
}
#else
static inline void pudp_set_wrprotect(struct mm_struct *mm,
unsigned long address, pud_t *pudp)
{
BUILD_BUG();
}
#endif /* CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */
#endif
#ifndef pmdp_collapse_flush
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
extern pmd_t pmdp_collapse_flush(struct vm_area_struct *vma,
unsigned long address, pmd_t *pmdp);
#else
static inline pmd_t pmdp_collapse_flush(struct vm_area_struct *vma,
unsigned long address,
pmd_t *pmdp)
{
BUILD_BUG();
return *pmdp;
}
#define pmdp_collapse_flush pmdp_collapse_flush
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
#endif
#ifndef __HAVE_ARCH_PGTABLE_DEPOSIT
extern void pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp,
pgtable_t pgtable);
#endif
#ifndef __HAVE_ARCH_PGTABLE_WITHDRAW
extern pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp);
#endif
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
/*
* This is an implementation of pmdp_establish() that is only suitable for an
* architecture that doesn't have hardware dirty/accessed bits. In this case we
* can't race with CPU which sets these bits and non-atomic aproach is fine.
*/
static inline pmd_t generic_pmdp_establish(struct vm_area_struct *vma,
unsigned long address, pmd_t *pmdp, pmd_t pmd)
{
pmd_t old_pmd = *pmdp;
set_pmd_at(vma->vm_mm, address, pmdp, pmd);
return old_pmd;
}
#endif
#ifndef __HAVE_ARCH_PMDP_INVALIDATE
extern pmd_t pmdp_invalidate(struct vm_area_struct *vma, unsigned long address,
pmd_t *pmdp);
#endif
#ifndef __HAVE_ARCH_PTE_SAME
static inline int pte_same(pte_t pte_a, pte_t pte_b)
{
return pte_val(pte_a) == pte_val(pte_b);
}
#endif
#ifndef __HAVE_ARCH_PTE_UNUSED
/*
* Some architectures provide facilities to virtualization guests
* so that they can flag allocated pages as unused. This allows the
* host to transparently reclaim unused pages. This function returns
* whether the pte's page is unused.
*/
static inline int pte_unused(pte_t pte)
{
return 0;
}
#endif
#ifndef pte_access_permitted
#define pte_access_permitted(pte, write) \
(pte_present(pte) && (!(write) || pte_write(pte)))
#endif
#ifndef pmd_access_permitted
#define pmd_access_permitted(pmd, write) \
(pmd_present(pmd) && (!(write) || pmd_write(pmd)))
#endif
#ifndef pud_access_permitted
#define pud_access_permitted(pud, write) \
(pud_present(pud) && (!(write) || pud_write(pud)))
#endif
#ifndef p4d_access_permitted
#define p4d_access_permitted(p4d, write) \
(p4d_present(p4d) && (!(write) || p4d_write(p4d)))
#endif
#ifndef pgd_access_permitted
#define pgd_access_permitted(pgd, write) \
(pgd_present(pgd) && (!(write) || pgd_write(pgd)))
#endif
#ifndef __HAVE_ARCH_PMD_SAME
static inline int pmd_same(pmd_t pmd_a, pmd_t pmd_b)
{
return pmd_val(pmd_a) == pmd_val(pmd_b);
}
static inline int pud_same(pud_t pud_a, pud_t pud_b)
{
return pud_val(pud_a) == pud_val(pud_b);
}
#endif
#ifndef __HAVE_ARCH_P4D_SAME
static inline int p4d_same(p4d_t p4d_a, p4d_t p4d_b)
{
return p4d_val(p4d_a) == p4d_val(p4d_b);
}
#endif
#ifndef __HAVE_ARCH_PGD_SAME
static inline int pgd_same(pgd_t pgd_a, pgd_t pgd_b)
{
return pgd_val(pgd_a) == pgd_val(pgd_b);
}
#endif
/*
* Use set_p*_safe(), and elide TLB flushing, when confident that *no*
* TLB flush will be required as a result of the "set". For example, use
* in scenarios where it is known ahead of time that the routine is
* setting non-present entries, or re-setting an existing entry to the
* same value. Otherwise, use the typical "set" helpers and flush the
* TLB.
*/
#define set_pte_safe(ptep, pte) \
({ \
WARN_ON_ONCE(pte_present(*ptep) && !pte_same(*ptep, pte)); \
set_pte(ptep, pte); \
})
#define set_pmd_safe(pmdp, pmd) \
({ \
WARN_ON_ONCE(pmd_present(*pmdp) && !pmd_same(*pmdp, pmd)); \
set_pmd(pmdp, pmd); \
})
#define set_pud_safe(pudp, pud) \
({ \
WARN_ON_ONCE(pud_present(*pudp) && !pud_same(*pudp, pud)); \
set_pud(pudp, pud); \
})
#define set_p4d_safe(p4dp, p4d) \
({ \
WARN_ON_ONCE(p4d_present(*p4dp) && !p4d_same(*p4dp, p4d)); \
set_p4d(p4dp, p4d); \
})
#define set_pgd_safe(pgdp, pgd) \
({ \
WARN_ON_ONCE(pgd_present(*pgdp) && !pgd_same(*pgdp, pgd)); \
set_pgd(pgdp, pgd); \
})
#ifndef __HAVE_ARCH_DO_SWAP_PAGE
/*
* Some architectures support metadata associated with a page. When a
* page is being swapped out, this metadata must be saved so it can be
* restored when the page is swapped back in. SPARC M7 and newer
* processors support an ADI (Application Data Integrity) tag for the
* page as metadata for the page. arch_do_swap_page() can restore this
* metadata when a page is swapped back in.
*/
static inline void arch_do_swap_page(struct mm_struct *mm,
struct vm_area_struct *vma,
unsigned long addr,
pte_t pte, pte_t oldpte)
{
}
#endif
#ifndef __HAVE_ARCH_UNMAP_ONE
/*
* Some architectures support metadata associated with a page. When a
* page is being swapped out, this metadata must be saved so it can be
* restored when the page is swapped back in. SPARC M7 and newer
* processors support an ADI (Application Data Integrity) tag for the
* page as metadata for the page. arch_unmap_one() can save this
* metadata on a swap-out of a page.
*/
static inline int arch_unmap_one(struct mm_struct *mm,
struct vm_area_struct *vma,
unsigned long addr,
pte_t orig_pte)
{
return 0;
}
#endif
/*
* Allow architectures to preserve additional metadata associated with
* swapped-out pages. The corresponding __HAVE_ARCH_SWAP_* macros and function
* prototypes must be defined in the arch-specific asm/pgtable.h file.
*/
#ifndef __HAVE_ARCH_PREPARE_TO_SWAP
static inline int arch_prepare_to_swap(struct page *page)
{
return 0;
}
#endif
#ifndef __HAVE_ARCH_SWAP_INVALIDATE
static inline void arch_swap_invalidate_page(int type, pgoff_t offset)
{
}
static inline void arch_swap_invalidate_area(int type)
{
}
#endif
#ifndef __HAVE_ARCH_SWAP_RESTORE
static inline void arch_swap_restore(swp_entry_t entry, struct page *page)
{
}
#endif
#ifndef __HAVE_ARCH_PGD_OFFSET_GATE
#define pgd_offset_gate(mm, addr) pgd_offset(mm, addr)
#endif
#ifndef __HAVE_ARCH_MOVE_PTE
#define move_pte(pte, prot, old_addr, new_addr) (pte)
#endif
#ifndef pte_accessible
# define pte_accessible(mm, pte) ((void)(pte), 1)
#endif
#ifndef flush_tlb_fix_spurious_fault
#define flush_tlb_fix_spurious_fault(vma, address) flush_tlb_page(vma, address)
#endif
/*
* When walking page tables, get the address of the next boundary,
* or the end address of the range if that comes earlier. Although no
* vma end wraps to 0, rounded up __boundary may wrap to 0 throughout.
*/
#define pgd_addr_end(addr, end) \
({ unsigned long __boundary = ((addr) + PGDIR_SIZE) & PGDIR_MASK; \
(__boundary - 1 < (end) - 1)? __boundary: (end); \
})
#ifndef p4d_addr_end
#define p4d_addr_end(addr, end) \
({ unsigned long __boundary = ((addr) + P4D_SIZE) & P4D_MASK; \
(__boundary - 1 < (end) - 1)? __boundary: (end); \
})
#endif
#ifndef pud_addr_end
#define pud_addr_end(addr, end) \
({ unsigned long __boundary = ((addr) + PUD_SIZE) & PUD_MASK; \
(__boundary - 1 < (end) - 1)? __boundary: (end); \
})
#endif
#ifndef pmd_addr_end
#define pmd_addr_end(addr, end) \
({ unsigned long __boundary = ((addr) + PMD_SIZE) & PMD_MASK; \
(__boundary - 1 < (end) - 1)? __boundary: (end); \
})
#endif
/*
* When walking page tables, we usually want to skip any p?d_none entries;
* and any p?d_bad entries - reporting the error before resetting to none.
* Do the tests inline, but report and clear the bad entry in mm/memory.c.
*/
void pgd_clear_bad(pgd_t *);
#ifndef __PAGETABLE_P4D_FOLDED
void p4d_clear_bad(p4d_t *);
#else
#define p4d_clear_bad(p4d) do { } while (0)
#endif
#ifndef __PAGETABLE_PUD_FOLDED
void pud_clear_bad(pud_t *);
#else
#define pud_clear_bad(p4d) do { } while (0)
#endif
void pmd_clear_bad(pmd_t *);
static inline int pgd_none_or_clear_bad(pgd_t *pgd)
{
if (pgd_none(*pgd))
return 1;
if (unlikely(pgd_bad(*pgd))) {
pgd_clear_bad(pgd);
return 1;
}
return 0;
}
static inline int p4d_none_or_clear_bad(p4d_t *p4d)
{
if (p4d_none(*p4d))
return 1;
if (unlikely(p4d_bad(*p4d))) {
p4d_clear_bad(p4d);
return 1;
}
return 0;
}
static inline int pud_none_or_clear_bad(pud_t *pud)
{
if (pud_none(*pud))
return 1;
if (unlikely(pud_bad(*pud))) {
pud_clear_bad(pud);
return 1;
}
return 0;
}
static inline int pmd_none_or_clear_bad(pmd_t *pmd)
{
if (pmd_none(*pmd))
return 1;
if (unlikely(pmd_bad(*pmd))) {
pmd_clear_bad(pmd);
return 1;
}
return 0;
}
static inline pte_t __ptep_modify_prot_start(struct vm_area_struct *vma,
unsigned long addr,
pte_t *ptep)
{
/*
* Get the current pte state, but zero it out to make it
* non-present, preventing the hardware from asynchronously
* updating it.
*/
return ptep_get_and_clear(vma->vm_mm, addr, ptep);
}
static inline void __ptep_modify_prot_commit(struct vm_area_struct *vma,
unsigned long addr,
pte_t *ptep, pte_t pte)
{
/*
* The pte is non-present, so there's no hardware state to
* preserve.
*/
set_pte_at(vma->vm_mm, addr, ptep, pte);
}
#ifndef __HAVE_ARCH_PTEP_MODIFY_PROT_TRANSACTION
/*
* Start a pte protection read-modify-write transaction, which
* protects against asynchronous hardware modifications to the pte.
* The intention is not to prevent the hardware from making pte
* updates, but to prevent any updates it may make from being lost.
*
* This does not protect against other software modifications of the
* pte; the appropriate pte lock must be held over the transation.
*
* Note that this interface is intended to be batchable, meaning that
* ptep_modify_prot_commit may not actually update the pte, but merely
* queue the update to be done at some later time. The update must be
* actually committed before the pte lock is released, however.
*/
static inline pte_t ptep_modify_prot_start(struct vm_area_struct *vma,
unsigned long addr,
pte_t *ptep)
{
return __ptep_modify_prot_start(vma, addr, ptep);
}
/*
* Commit an update to a pte, leaving any hardware-controlled bits in
* the PTE unmodified.
*/
static inline void ptep_modify_prot_commit(struct vm_area_struct *vma,
unsigned long addr,
pte_t *ptep, pte_t old_pte, pte_t pte)
{
__ptep_modify_prot_commit(vma, addr, ptep, pte);
}
#endif /* __HAVE_ARCH_PTEP_MODIFY_PROT_TRANSACTION */
#endif /* CONFIG_MMU */
/*
* No-op macros that just return the current protection value. Defined here
* because these macros can be used even if CONFIG_MMU is not defined.
*/
#ifndef pgprot_nx
#define pgprot_nx(prot) (prot)
#endif
#ifndef pgprot_noncached
#define pgprot_noncached(prot) (prot)
#endif
#ifndef pgprot_writecombine
#define pgprot_writecombine pgprot_noncached
#endif
#ifndef pgprot_writethrough
#define pgprot_writethrough pgprot_noncached
#endif
#ifndef pgprot_device
#define pgprot_device pgprot_noncached
#endif
#ifndef pgprot_mhp
#define pgprot_mhp(prot) (prot)
#endif
#ifdef CONFIG_MMU
#ifndef pgprot_modify
#define pgprot_modify pgprot_modify
static inline pgprot_t pgprot_modify(pgprot_t oldprot, pgprot_t newprot)
{
if (pgprot_val(oldprot) == pgprot_val(pgprot_noncached(oldprot)))
newprot = pgprot_noncached(newprot);
if (pgprot_val(oldprot) == pgprot_val(pgprot_writecombine(oldprot)))
newprot = pgprot_writecombine(newprot);
if (pgprot_val(oldprot) == pgprot_val(pgprot_device(oldprot)))
newprot = pgprot_device(newprot);
return newprot;
}
#endif
#endif /* CONFIG_MMU */
#ifndef pgprot_encrypted
#define pgprot_encrypted(prot) (prot)
#endif
#ifndef pgprot_decrypted
#define pgprot_decrypted(prot) (prot)
#endif
/*
* A facility to provide lazy MMU batching. This allows PTE updates and
* page invalidations to be delayed until a call to leave lazy MMU mode
* is issued. Some architectures may benefit from doing this, and it is
* beneficial for both shadow and direct mode hypervisors, which may batch
* the PTE updates which happen during this window. Note that using this
* interface requires that read hazards be removed from the code. A read
* hazard could result in the direct mode hypervisor case, since the actual
* write to the page tables may not yet have taken place, so reads though
* a raw PTE pointer after it has been modified are not guaranteed to be
* up to date. This mode can only be entered and left under the protection of
* the page table locks for all page tables which may be modified. In the UP
* case, this is required so that preemption is disabled, and in the SMP case,
* it must synchronize the delayed page table writes properly on other CPUs.
*/
#ifndef __HAVE_ARCH_ENTER_LAZY_MMU_MODE
#define arch_enter_lazy_mmu_mode() do {} while (0)
#define arch_leave_lazy_mmu_mode() do {} while (0)
#define arch_flush_lazy_mmu_mode() do {} while (0)
#endif
/*
* A facility to provide batching of the reload of page tables and
* other process state with the actual context switch code for
* paravirtualized guests. By convention, only one of the batched
* update (lazy) modes (CPU, MMU) should be active at any given time,
* entry should never be nested, and entry and exits should always be
* paired. This is for sanity of maintaining and reasoning about the
* kernel code. In this case, the exit (end of the context switch) is
* in architecture-specific code, and so doesn't need a generic
* definition.
*/
#ifndef __HAVE_ARCH_START_CONTEXT_SWITCH
#define arch_start_context_switch(prev) do {} while (0)
#endif
#ifdef CONFIG_HAVE_ARCH_SOFT_DIRTY
#ifndef CONFIG_ARCH_ENABLE_THP_MIGRATION
static inline pmd_t pmd_swp_mksoft_dirty(pmd_t pmd)
{
return pmd;
}
static inline int pmd_swp_soft_dirty(pmd_t pmd)
{
return 0;
}
static inline pmd_t pmd_swp_clear_soft_dirty(pmd_t pmd)
{
return pmd;
}
#endif
#else /* !CONFIG_HAVE_ARCH_SOFT_DIRTY */
static inline int pte_soft_dirty(pte_t pte)
{
return 0;
}
static inline int pmd_soft_dirty(pmd_t pmd)
{
return 0;
}
static inline pte_t pte_mksoft_dirty(pte_t pte)
{
return pte;
}
static inline pmd_t pmd_mksoft_dirty(pmd_t pmd)
{
return pmd;
}
static inline pte_t pte_clear_soft_dirty(pte_t pte)
{
return pte;
}
static inline pmd_t pmd_clear_soft_dirty(pmd_t pmd)
{
return pmd;
}
static inline pte_t pte_swp_mksoft_dirty(pte_t pte)
{
return pte;
}
static inline int pte_swp_soft_dirty(pte_t pte)
{
return 0;
}
static inline pte_t pte_swp_clear_soft_dirty(pte_t pte)
{
return pte;
}
static inline pmd_t pmd_swp_mksoft_dirty(pmd_t pmd)
{
return pmd;
}
static inline int pmd_swp_soft_dirty(pmd_t pmd)
{
return 0;
}
static inline pmd_t pmd_swp_clear_soft_dirty(pmd_t pmd)
{
return pmd;
}
#endif
#ifndef __HAVE_PFNMAP_TRACKING
/*
* Interfaces that can be used by architecture code to keep track of
* memory type of pfn mappings specified by the remap_pfn_range,
* vmf_insert_pfn.
*/
/*
* track_pfn_remap is called when a _new_ pfn mapping is being established
* by remap_pfn_range() for physical range indicated by pfn and size.
*/
static inline int track_pfn_remap(struct vm_area_struct *vma, pgprot_t *prot,
unsigned long pfn, unsigned long addr,
unsigned long size)
{
return 0;
}
/*
* track_pfn_insert is called when a _new_ single pfn is established
* by vmf_insert_pfn().
*/
static inline void track_pfn_insert(struct vm_area_struct *vma, pgprot_t *prot,
pfn_t pfn)
{
}
/*
* track_pfn_copy is called when vma that is covering the pfnmap gets
* copied through copy_page_range().
*/
static inline int track_pfn_copy(struct vm_area_struct *vma)
{
return 0;
}
/*
* untrack_pfn is called while unmapping a pfnmap for a region.
* untrack can be called for a specific region indicated by pfn and size or
* can be for the entire vma (in which case pfn, size are zero).
*/
static inline void untrack_pfn(struct vm_area_struct *vma,
unsigned long pfn, unsigned long size)
{
}
/*
* untrack_pfn_moved is called while mremapping a pfnmap for a new region.
*/
static inline void untrack_pfn_moved(struct vm_area_struct *vma)
{
}
#else
extern int track_pfn_remap(struct vm_area_struct *vma, pgprot_t *prot,
unsigned long pfn, unsigned long addr,
unsigned long size);
extern void track_pfn_insert(struct vm_area_struct *vma, pgprot_t *prot,
pfn_t pfn);
extern int track_pfn_copy(struct vm_area_struct *vma);
extern void untrack_pfn(struct vm_area_struct *vma, unsigned long pfn,
unsigned long size);
extern void untrack_pfn_moved(struct vm_area_struct *vma);
#endif
#ifdef __HAVE_COLOR_ZERO_PAGE
static inline int is_zero_pfn(unsigned long pfn)
{
extern unsigned long zero_pfn;
unsigned long offset_from_zero_pfn = pfn - zero_pfn;
return offset_from_zero_pfn <= (zero_page_mask >> PAGE_SHIFT);
}
#define my_zero_pfn(addr) page_to_pfn(ZERO_PAGE(addr))
#else
static inline int is_zero_pfn(unsigned long pfn)
{
extern unsigned long zero_pfn;
return pfn == zero_pfn;
}
static inline unsigned long my_zero_pfn(unsigned long addr)
{
extern unsigned long zero_pfn;
return zero_pfn;
}
#endif
#ifdef CONFIG_MMU
#ifndef CONFIG_TRANSPARENT_HUGEPAGE
static inline int pmd_trans_huge(pmd_t pmd)
{
return 0;
}
#ifndef pmd_write
static inline int pmd_write(pmd_t pmd)
{
BUG();
return 0;
}
#endif /* pmd_write */
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
#ifndef pud_write
static inline int pud_write(pud_t pud)
{
BUG();
return 0;
}
#endif /* pud_write */
#if !defined(CONFIG_ARCH_HAS_PTE_DEVMAP) || !defined(CONFIG_TRANSPARENT_HUGEPAGE)
static inline int pmd_devmap(pmd_t pmd)
{
return 0;
}
static inline int pud_devmap(pud_t pud)
{
return 0;
}
static inline int pgd_devmap(pgd_t pgd)
{
return 0;
}
#endif
#if !defined(CONFIG_TRANSPARENT_HUGEPAGE) || \
(defined(CONFIG_TRANSPARENT_HUGEPAGE) && \
!defined(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD))
static inline int pud_trans_huge(pud_t pud)
{
return 0;
}
#endif
/* See pmd_none_or_trans_huge_or_clear_bad for discussion. */
static inline int pud_none_or_trans_huge_or_dev_or_clear_bad(pud_t *pud)
{
pud_t pudval = READ_ONCE(*pud);
if (pud_none(pudval) || pud_trans_huge(pudval) || pud_devmap(pudval))
return 1;
if (unlikely(pud_bad(pudval))) {
pud_clear_bad(pud);
return 1;
}
return 0;
}
/* See pmd_trans_unstable for discussion. */
static inline int pud_trans_unstable(pud_t *pud)
{
#if defined(CONFIG_TRANSPARENT_HUGEPAGE) && \
defined(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD)
return pud_none_or_trans_huge_or_dev_or_clear_bad(pud);
#else
return 0;
#endif
}
#ifndef pmd_read_atomic
static inline pmd_t pmd_read_atomic(pmd_t *pmdp)
{
/*
* Depend on compiler for an atomic pmd read. NOTE: this is
* only going to work, if the pmdval_t isn't larger than
* an unsigned long.
*/
return *pmdp;
}
#endif
#ifndef arch_needs_pgtable_deposit
#define arch_needs_pgtable_deposit() (false)
#endif
/*
* This function is meant to be used by sites walking pagetables with
* the mmap_lock held in read mode to protect against MADV_DONTNEED and
* transhuge page faults. MADV_DONTNEED can convert a transhuge pmd
* into a null pmd and the transhuge page fault can convert a null pmd
* into an hugepmd or into a regular pmd (if the hugepage allocation
* fails). While holding the mmap_lock in read mode the pmd becomes
* stable and stops changing under us only if it's not null and not a
* transhuge pmd. When those races occurs and this function makes a
* difference vs the standard pmd_none_or_clear_bad, the result is
* undefined so behaving like if the pmd was none is safe (because it
* can return none anyway). The compiler level barrier() is critically
* important to compute the two checks atomically on the same pmdval.
*
* For 32bit kernels with a 64bit large pmd_t this automatically takes
* care of reading the pmd atomically to avoid SMP race conditions
* against pmd_populate() when the mmap_lock is hold for reading by the
* caller (a special atomic read not done by "gcc" as in the generic
* version above, is also needed when THP is disabled because the page
* fault can populate the pmd from under us).
*/
static inline int pmd_none_or_trans_huge_or_clear_bad(pmd_t *pmd)
{
pmd_t pmdval = pmd_read_atomic(pmd);
/*
* The barrier will stabilize the pmdval in a register or on
* the stack so that it will stop changing under the code.
*
* When CONFIG_TRANSPARENT_HUGEPAGE=y on x86 32bit PAE,
* pmd_read_atomic is allowed to return a not atomic pmdval
* (for example pointing to an hugepage that has never been
* mapped in the pmd). The below checks will only care about
* the low part of the pmd with 32bit PAE x86 anyway, with the
* exception of pmd_none(). So the important thing is that if
* the low part of the pmd is found null, the high part will
* be also null or the pmd_none() check below would be
* confused.
*/
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
barrier();
#endif
/*
* !pmd_present() checks for pmd migration entries
*
* The complete check uses is_pmd_migration_entry() in linux/swapops.h
* But using that requires moving current function and pmd_trans_unstable()
* to linux/swapops.h to resovle dependency, which is too much code move.
*
* !pmd_present() is equivalent to is_pmd_migration_entry() currently,
* because !pmd_present() pages can only be under migration not swapped
* out.
*
* pmd_none() is preseved for future condition checks on pmd migration
* entries and not confusing with this function name, although it is
* redundant with !pmd_present().
*/
if (pmd_none(pmdval) || pmd_trans_huge(pmdval) ||
(IS_ENABLED(CONFIG_ARCH_ENABLE_THP_MIGRATION) && !pmd_present(pmdval)))
return 1;
if (unlikely(pmd_bad(pmdval))) {
pmd_clear_bad(pmd);
return 1;
}
return 0;
}
/*
* This is a noop if Transparent Hugepage Support is not built into
* the kernel. Otherwise it is equivalent to
* pmd_none_or_trans_huge_or_clear_bad(), and shall only be called in
* places that already verified the pmd is not none and they want to
* walk ptes while holding the mmap sem in read mode (write mode don't
* need this). If THP is not enabled, the pmd can't go away under the
* code even if MADV_DONTNEED runs, but if THP is enabled we need to
* run a pmd_trans_unstable before walking the ptes after
* split_huge_pmd returns (because it may have run when the pmd become
* null, but then a page fault can map in a THP and not a regular page).
*/
static inline int pmd_trans_unstable(pmd_t *pmd)
{
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
return pmd_none_or_trans_huge_or_clear_bad(pmd);
#else
return 0;
#endif
}
/*
* the ordering of these checks is important for pmds with _page_devmap set.
* if we check pmd_trans_unstable() first we will trip the bad_pmd() check
* inside of pmd_none_or_trans_huge_or_clear_bad(). this will end up correctly
* returning 1 but not before it spams dmesg with the pmd_clear_bad() output.
*/
static inline int pmd_devmap_trans_unstable(pmd_t *pmd)
{
return pmd_devmap(*pmd) || pmd_trans_unstable(pmd);
}
#ifndef CONFIG_NUMA_BALANCING
/*
* Technically a PTE can be PROTNONE even when not doing NUMA balancing but
* the only case the kernel cares is for NUMA balancing and is only ever set
* when the VMA is accessible. For PROT_NONE VMAs, the PTEs are not marked
* _PAGE_PROTNONE so by default, implement the helper as "always no". It
* is the responsibility of the caller to distinguish between PROT_NONE
* protections and NUMA hinting fault protections.
*/
static inline int pte_protnone(pte_t pte)
{
return 0;
}
static inline int pmd_protnone(pmd_t pmd)
{
return 0;
}
#endif /* CONFIG_NUMA_BALANCING */
#endif /* CONFIG_MMU */
#ifdef CONFIG_HAVE_ARCH_HUGE_VMAP
#ifndef __PAGETABLE_P4D_FOLDED
int p4d_set_huge(p4d_t *p4d, phys_addr_t addr, pgprot_t prot);
int p4d_clear_huge(p4d_t *p4d);
#else
static inline int p4d_set_huge(p4d_t *p4d, phys_addr_t addr, pgprot_t prot)
{
return 0;
}
static inline int p4d_clear_huge(p4d_t *p4d)
{
return 0;
}
#endif /* !__PAGETABLE_P4D_FOLDED */
int pud_set_huge(pud_t *pud, phys_addr_t addr, pgprot_t prot);
int pmd_set_huge(pmd_t *pmd, phys_addr_t addr, pgprot_t prot);
int pud_clear_huge(pud_t *pud);
int pmd_clear_huge(pmd_t *pmd);
int p4d_free_pud_page(p4d_t *p4d, unsigned long addr);
int pud_free_pmd_page(pud_t *pud, unsigned long addr);
int pmd_free_pte_page(pmd_t *pmd, unsigned long addr);
#else /* !CONFIG_HAVE_ARCH_HUGE_VMAP */
static inline int p4d_set_huge(p4d_t *p4d, phys_addr_t addr, pgprot_t prot)
{
return 0;
}
static inline int pud_set_huge(pud_t *pud, phys_addr_t addr, pgprot_t prot)
{
return 0;
}
static inline int pmd_set_huge(pmd_t *pmd, phys_addr_t addr, pgprot_t prot)
{
return 0;
}
static inline int p4d_clear_huge(p4d_t *p4d)
{
return 0;
}
static inline int pud_clear_huge(pud_t *pud)
{
return 0;
}
static inline int pmd_clear_huge(pmd_t *pmd)
{
return 0;
}
static inline int p4d_free_pud_page(p4d_t *p4d, unsigned long addr)
{
return 0;
}
static inline int pud_free_pmd_page(pud_t *pud, unsigned long addr)
{
return 0;
}
static inline int pmd_free_pte_page(pmd_t *pmd, unsigned long addr)
{
return 0;
}
#endif /* CONFIG_HAVE_ARCH_HUGE_VMAP */
#ifndef __HAVE_ARCH_FLUSH_PMD_TLB_RANGE
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
/*
* ARCHes with special requirements for evicting THP backing TLB entries can
* implement this. Otherwise also, it can help optimize normal TLB flush in
* THP regime. Stock flush_tlb_range() typically has optimization to nuke the
* entire TLB if flush span is greater than a threshold, which will
* likely be true for a single huge page. Thus a single THP flush will
* invalidate the entire TLB which is not desirable.
* e.g. see arch/arc: flush_pmd_tlb_range
*/
#define flush_pmd_tlb_range(vma, addr, end) flush_tlb_range(vma, addr, end)
#define flush_pud_tlb_range(vma, addr, end) flush_tlb_range(vma, addr, end)
#else
#define flush_pmd_tlb_range(vma, addr, end) BUILD_BUG()
#define flush_pud_tlb_range(vma, addr, end) BUILD_BUG()
#endif
#endif
struct file;
int phys_mem_access_prot_allowed(struct file *file, unsigned long pfn,
unsigned long size, pgprot_t *vma_prot);
#ifndef CONFIG_X86_ESPFIX64
static inline void init_espfix_bsp(void) { }
#endif
extern void __init pgtable_cache_init(void);
#ifndef __HAVE_ARCH_PFN_MODIFY_ALLOWED
static inline bool pfn_modify_allowed(unsigned long pfn, pgprot_t prot)
{
return true;
}
static inline bool arch_has_pfn_modify_check(void)
{
return false;
}
#endif /* !_HAVE_ARCH_PFN_MODIFY_ALLOWED */
/*
* Architecture PAGE_KERNEL_* fallbacks
*
* Some architectures don't define certain PAGE_KERNEL_* flags. This is either
* because they really don't support them, or the port needs to be updated to
* reflect the required functionality. Below are a set of relatively safe
* fallbacks, as best effort, which we can count on in lieu of the architectures
* not defining them on their own yet.
*/
#ifndef PAGE_KERNEL_RO
# define PAGE_KERNEL_RO PAGE_KERNEL
#endif
#ifndef PAGE_KERNEL_EXEC
# define PAGE_KERNEL_EXEC PAGE_KERNEL
#endif
/*
* Page Table Modification bits for pgtbl_mod_mask.
*
* These are used by the p?d_alloc_track*() set of functions an in the generic
* vmalloc/ioremap code to track at which page-table levels entries have been
* modified. Based on that the code can better decide when vmalloc and ioremap
* mapping changes need to be synchronized to other page-tables in the system.
*/
#define __PGTBL_PGD_MODIFIED 0
#define __PGTBL_P4D_MODIFIED 1
#define __PGTBL_PUD_MODIFIED 2
#define __PGTBL_PMD_MODIFIED 3
#define __PGTBL_PTE_MODIFIED 4
#define PGTBL_PGD_MODIFIED BIT(__PGTBL_PGD_MODIFIED)
#define PGTBL_P4D_MODIFIED BIT(__PGTBL_P4D_MODIFIED)
#define PGTBL_PUD_MODIFIED BIT(__PGTBL_PUD_MODIFIED)
#define PGTBL_PMD_MODIFIED BIT(__PGTBL_PMD_MODIFIED)
#define PGTBL_PTE_MODIFIED BIT(__PGTBL_PTE_MODIFIED)
/* Page-Table Modification Mask */
typedef unsigned int pgtbl_mod_mask;
#endif /* !__ASSEMBLY__ */
#if !defined(MAX_POSSIBLE_PHYSMEM_BITS) && !defined(CONFIG_64BIT)
#ifdef CONFIG_PHYS_ADDR_T_64BIT
/*
* ZSMALLOC needs to know the highest PFN on 32-bit architectures
* with physical address space extension, but falls back to
* BITS_PER_LONG otherwise.
*/
#error Missing MAX_POSSIBLE_PHYSMEM_BITS definition
#else
#define MAX_POSSIBLE_PHYSMEM_BITS 32
#endif
#endif
#ifndef has_transparent_hugepage
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
#define has_transparent_hugepage() 1
#else
#define has_transparent_hugepage() 0
#endif
#endif
/*
* On some architectures it depends on the mm if the p4d/pud or pmd
* layer of the page table hierarchy is folded or not.
*/
#ifndef mm_p4d_folded
#define mm_p4d_folded(mm) __is_defined(__PAGETABLE_P4D_FOLDED)
#endif
#ifndef mm_pud_folded
#define mm_pud_folded(mm) __is_defined(__PAGETABLE_PUD_FOLDED)
#endif
#ifndef mm_pmd_folded
#define mm_pmd_folded(mm) __is_defined(__PAGETABLE_PMD_FOLDED)
#endif
#ifndef p4d_offset_lockless
#define p4d_offset_lockless(pgdp, pgd, address) p4d_offset(&(pgd), address)
#endif
#ifndef pud_offset_lockless
#define pud_offset_lockless(p4dp, p4d, address) pud_offset(&(p4d), address)
#endif
#ifndef pmd_offset_lockless
#define pmd_offset_lockless(pudp, pud, address) pmd_offset(&(pud), address)
#endif
/*
* p?d_leaf() - true if this entry is a final mapping to a physical address.
* This differs from p?d_huge() by the fact that they are always available (if
* the architecture supports large pages at the appropriate level) even
* if CONFIG_HUGETLB_PAGE is not defined.
* Only meaningful when called on a valid entry.
*/
#ifndef pgd_leaf
#define pgd_leaf(x) 0
#endif
#ifndef p4d_leaf
#define p4d_leaf(x) 0
#endif
#ifndef pud_leaf
#define pud_leaf(x) 0
#endif
#ifndef pmd_leaf
#define pmd_leaf(x) 0
#endif
#endif /* _LINUX_PGTABLE_H */