Merge keystone/mirror-android-mainline into keystone/android-mainline-keystone-qcom-dev

* keystone/mirror-android-mainline:
  Revert "ANDROID: cpu-hotplug: Always use real time scheduling when hotplugging a CPU"
  Revert "ANDROID: cpu: Don't prevent hotplug from DL/BATCH/IDLE"
  Revert "ANDROID: timer: Add vendor hook for timer calc index"
  ANDROID: irq-gic-v3: remove all out-of-tree changes
  ANDROID: init_task: Init android vendor and oem data
  ANDROID: uapi: icmp: Bionic compat with __unused
  ANDROID: PCI: dwc: revert dwc 32-bit DMA mask for MSI address requirement
  lockdown: also lock down previous kgdb use
  xtensa: Return true/false (not 1/0) from bool function
  random: check for signals after page of pool writes
  m68k: atari: Make Atari ROM port I/O write macros return void
  io_uring: cleanup handling of the two task_work lists
  EDAC/xgene: Fix typo processsors -> processors
  mtip32xx: fix typo in comment
  blk-mq: fix typo in comment
  arm64/sysreg: Generate definitions for FAR_ELx
  arm64/sysreg: Generate definitions for DACR32_EL2
  arm64/sysreg: Generate definitions for CSSELR_EL1
  arm64/sysreg: Generate definitions for CPACR_ELx
  arm64/sysreg: Generate definitions for CONTEXTIDR_ELx
  arm64/sysreg: Generate definitions for CLIDR_EL1
  random: wire up fops->splice_{read,write}_iter()
  random: convert to using fops->write_iter()
  random: convert to using fops->read_iter()
  nvme: enable uring-passthrough for admin commands
  nvme: helper for uring-passthrough checks
  ARM: 9204/2: module: Add all unwind tables when load module
  ARM: 9206/1: A9: Add ARM ERRATA 764319 workaround (Updated)
  ARM: 9201/1: spectre-bhb: rely on linker to emit cross-section literal loads
  ARM: 9200/1: spectre-bhb: avoid cross-subsection jump using a numbered label
  ARM: 9199/1: spectre-bhb: use local DSB and elide ISB in loop8 sequence
  ARM: 9198/1: spectre-bhb: simplify BPIALL vector macro
  ARM: 9195/1: entry: avoid explicit literal loads
  ARM: 9194/1: assembler: simplify ldr_this_cpu for !SMP builds
  ARM: 9192/1: amba: fix memory leak in amba_device_try_add()
  ARM: 9193/1: amba: Add amba_read_periphid() helper
  x86/tdx: Fix RETs in TDX asm
  objtool: Fix objtool regression on x32 systems
  objtool: Fix symbol creation
  x86: Remove empty files
  x86/entry: Fixup objtool/ibt validation
  x86/microcode: Add explicit CPU vendor dependency
  perf/x86/amd/core: Fix reloading events for SVM
  topology: Remove unused cpu_cluster_mask()
  sched: Reverse sched_class layout
  bug: Use normal relative pointers in 'struct bug_entry'
  sched/clock: Use try_cmpxchg64 in sched_clock_{local,remote}
  x86/entry: Fix register corruption in compat syscall
  nvme: set non-mdts limits in nvme_scan_work
  io_uring: fix incorrect __kernel_rwf_t cast
  platform/x86/intel/ifs: Add CPU_SUP_INTEL dependency
  platform/x86: intel_cht_int33fe: Set driver data
  platform/x86: intel-hid: fix _DSM function index handling
  fs-verity: Use struct_size() helper in enable_verity()
  random: unify batched entropy implementations
  random: move randomize_page() into mm where it belongs
  random: remove mostly unused async readiness notifier
  random: remove get_random_bytes_arch() and add rng_has_arch_random()
  random: move initialization functions out of hot pages
  random: make consistent use of buf and len
  random: use proper return types on get_random_{int,long}_wait()
  random: remove extern from functions in header
  random: use static branch for crng_ready()
  bfq: Remove bfq_requeue_request_body()
  bfq: Remove superfluous conversion from RQ_BIC()
  bfq: Allow current waker to defend against a tentative one
  bfq: Relax waker detection for shared queues
  xen: add support for initializing xenstore later as HVM domain
  xen: sync xs_wire.h header with upstream xen
  x86: xen: remove STACK_FRAME_NON_STANDARD from xen_cpuid
  xen-blk{back,front}: Update contact points for buffer_squeeze_duration_ms and feature_persistent
  fs-writeback: writeback_sb_inodes：Recalculate 'wrote' according skipped pages
  xen/xenbus: eliminate xenbus_grant_ring()
  xen/sndfront: use xenbus_setup_ring() and xenbus_teardown_ring()
  xen/usbfront: use xenbus_setup_ring() and xenbus_teardown_ring()
  xen/scsifront: use xenbus_setup_ring() and xenbus_teardown_ring()
  xen/pcifront: use xenbus_setup_ring() and xenbus_teardown_ring()
  xen/drmfront: use xenbus_setup_ring() and xenbus_teardown_ring()
  xen/tpmfront: use xenbus_setup_ring() and xenbus_teardown_ring()
  xen/netfront: use xenbus_setup_ring() and xenbus_teardown_ring()
  xen/blkfront: use xenbus_setup_ring() and xenbus_teardown_ring()
  xen/xenbus: add xenbus_setup_ring() service function
  xen: update ring.h
  xen/shbuf: switch xen-front-pgdir-shbuf to use INVALID_GRANT_REF
  xen/dmabuf: switch gntdev-dmabuf to use INVALID_GRANT_REF
  xen/sound: switch xen_snd_front to use INVALID_GRANT_REF
  xen/drm: switch xen_drm_front to use INVALID_GRANT_REF
  xen/usb: switch xen-hcd to use INVALID_GRANT_REF
  xen/scsifront: remove unused GRANT_INVALID_REF definition
  xen/netfront: switch netfront to use INVALID_GRANT_REF
  xen/blkfront: switch blkfront to use INVALID_GRANT_REF
  xen/grant-table: never put a reserved grant on the free list
  xen: update grant_table.h
  xen/scsifront: harden driver against malicious backend
  xen/scsifront: use new command result macros
  xen/scsiback: use new command result macros
  xen: update vscsiif.h
  x86/boot: Wrap literal addresses in absolute_pointer()
  x86/sev: Mark the code returning to user space as syscall gap
  riscv/efi_stub: Add support for RISCV_EFI_BOOT_PROTOCOL
  blk-cgroup: delete rcu_read_lock_held() WARN_ON_ONCE()
  io_uring: disallow mixed provided buffer group registrations
  io_uring: initialize io_buffer_list head when shared ring is unregistered
  io_uring: add fully sparse buffer registration
  x86/sev: Annotate stack change in the #VC handler
  fs-verity: remove unused parameter desc_size in fsverity_create_info()
  nvme: add support for TP4084 - Time-to-Ready Enhancements
  random: credit architectural init the exact amount
  random: handle latent entropy and command line from random_init()
  random: use proper jiffies comparison macro
  random: remove ratelimiting for in-kernel unseeded randomness
  random: move initialization out of reseeding hot path
  random: avoid initializing twice in credit race
  random: use symbolic constants for crng_init states
  random32: use real rng for non-deterministic randomness
  siphash: use one source of truth for siphash permutations
  random: help compiler out with fast_mix() by using simpler arguments
  random: do not use input pool from hard IRQs
  arm64/sve: Move sve_free() into SVE code section
  arm64: Kconfig.platforms: Add comments
  arm64: Kconfig: Fix indentation and add comments
  io_uring: use rcu_dereference in io_close
  io_uring: consistently use the EPOLL* defines
  io_uring: make apoll_events a __poll_t
  io_uring: drop a spurious inline on a forward declaration
  io_uring: don't use ERR_PTR for user pointers
  io_uring: use a rwf_t for io_rw.flags
  io_uring: add support for ring mapped supplied buffers
  io_uring: add io_pin_pages() helper
  io_uring: add buffer selection support to IORING_OP_NOP
  io_uring: fix locking state for empty buffer group
  s390/head: get rid of 31 bit leftovers
  blk-throttle: Set BIO_THROTTLED when bio has been throttled
  locking/atomic/x86: Introduce arch_try_cmpxchg64
  locking/atomic: Add generic try_cmpxchg64 support
  perf/x86/amd: Run AMD BRS code only on supported hw
  perf/x86/amd: Fix AMD BRS period adjustment
  EDAC/i5100: Remove unused inline function i5100_nrecmema_dm_buf_id()
  scripts/min-tool-version.sh: raise minimum clang version to 14.0.0 for s390
  s390/boot: do not emit debug info for assembly with llvm's IAS
  s390/boot: workaround llvm IAS bug
  s390/purgatory: workaround llvm's IAS limitations
  s390/entry: workaround llvm's IAS limitations
  s390/alternatives: remove padding generation code
  s390/alternatives: provide identical sized orginal/alternative sequences
  blk-cgroup: Remove unnecessary rcu_read_lock/unlock()
  blk-cgroup: always terminate io.stat lines
  x86/sev: Remove duplicated assignment to variable info
  xtensa: improve call0 ABI probing
  xtensa: support artificial division by 0 exception
  irqchip: Add Kconfig symbols for sunxi drivers
  arm64: mm: avoid writable executable mappings in kexec/hibernate code
  arm64: lds: move special code sections out of kernel exec segment
  x86/nmi: Make register_nmi_handler() more robust
  nvme: split the enum used for various register constants
  loadpin: stop using bdevname
  mm: usercopy: move the virt_addr_valid() below the is_vmalloc_addr()
  gcc-plugins: randstruct: Remove cast exception handling
  af_unix: Silence randstruct GCC plugin warning
  niu: Silence randstruct warnings
  big_keys: Use struct for internal payload
  arm64/hugetlb: Implement arm64 specific huge_ptep_get()
  arm64/hugetlb: Use ptep_get() to get the pte value of a huge page
  x86/sgx: Ensure no data in PCMD page after truncate
  x86/sgx: Fix race between reclaimer and page fault handler
  x86/sgx: Obtain backing storage page with enclave mutex held
  x86/sgx: Mark PCMD page as dirty when modifying contents
  x86/sgx: Disconnect backing page references from dirty status
  arm64: kdump: Do not allocate crash low memory if not needed
  arm64/sve: Generate ZCR definitions
  arm64/sme: Generate defintions for SVCR
  arm64/sme: Generate SMPRI_EL1 definitions
  arm64/sme: Automatically generate SMPRIMAP_EL2 definitions
  arm64/sme: Automatically generate SMIDR_EL1 defines
  arm64/sme: Automatically generate defines for SMCR
  arm64/sysreg: Support generation of RAZ fields
  arm64/sme: Remove _EL0 from name of SVCR - FIXME sysreg.h
  arm64/sme: Standardise bitfield names for SVCR
  arm64/sme: Drop SYS_ from SMIDR_EL1 defines
  arm64/fp: Rename SVE and SME LEN field name to _WIDTH
  arm64/fp: Make SVE and SME length register definition match architecture
  kselftest/arm64: Explicitly build no BTI tests with BTI disabled
  arm64/sve: Make kernel FPU protection RT friendly
  arm64/sve: Delay freeing memory in fpsimd_flush_thread()
  arm64: mm: Make arch_faults_on_old_pte() check for migratability
  arm64: mte: Clean up user tag accessors
  kselftest/arm64: bti: force static linking
  block, bfq: make bfq_has_work() more accurate
  block, bfq: protect 'bfqd->queued' by 'bfqd->lock'
  block: cleanup the VM accounting in submit_bio
  nbd: Fix hung on disconnect request if socket is closed before
  ata: pata_ftide010: Remove unneeded ERROR check before clk_disable_unprepare
  s390/cpumf: add new extended counter set for IBM z16
  m68k: math-emu: Fix dependencies of math emulation support
  nvme-fabrics: add a request timeout helper
  nvme-pci: harden drive presence detect in nvme_dev_disable()
  nvme-pci: fix a NULL pointer dereference in nvme_alloc_admin_tags
  nvme: mark internal passthru request RQF_QUIET
  nvme: remove unneeded include from constants file
  nvme: add missing status values to verbose logging
  nvme: set dma alignment to dword
  nvme: fix interpretation of DMRSL
  cdrom: remove obsolete TODO list
  block: remove last remaining traces of IDE documentation
  cdrom: mark CDROMGETSPINDOWN/CDROMSETSPINDOWN obsolete
  cdrom: remove the unused driver specific disc change ioctl
  cdrom: make EXPORT_SYMBOL follow exported function
  random: order timer entropy functions below interrupt functions
  irqchip/gic-v3: Fix priority mask handling
  irqchip/gic-v3: Refactor ISB + EOIR at ack time
  irqchip/gic-v3: Ensure pseudo-NMIs have an ISB between ack and handling
  random: do not pretend to handle premature next security model
  selftests/arm64: Use switch statements in mte_common_util.c
  selftests/arm64: Remove casts to/from void in check_tags_inclusion
  selftests/arm64: Check failures to set tags in check_tags_inclusion
  selftests/arm64: Allow zero tags in mte_switch_mode()
  selftests/arm64: Log errors in verify_mte_pointer_validity()
  arm64/sysreg: fix odd line spacing
  arm64/sysreg: improve comment for regs without fields
  genirq/irq_sim: Make the irq_work always run in hard irq context
  timers: Provide a better debugobjects hint for delayed works
  io_uring: implement multishot mode for accept
  io_uring: let fast poll support multishot
  io_uring: add REQ_F_APOLL_MULTISHOT for requests
  io_uring: add IORING_ACCEPT_MULTISHOT for accept
  random: use first 128 bits of input as fast init
  random: do not use batches when !crng_ready()
  random: mix in timestamps and reseed on system restore
  random: vary jitter iterations based on cycle counter speed
  random: insist on random_get_entropy() existing in order to simplify
  xtensa: use fallback for random_get_entropy() instead of zero
  sparc: use fallback for random_get_entropy() instead of zero
  um: use fallback for random_get_entropy() instead of zero
  x86/tsc: Use fallback for random_get_entropy() instead of zero
  nios2: use fallback for random_get_entropy() instead of zero
  arm: use fallback for random_get_entropy() instead of zero
  mips: use fallback for random_get_entropy() instead of just c0 random
  riscv: use fallback for random_get_entropy() instead of zero
  m68k: use fallback for random_get_entropy() instead of zero
  timekeeping: Add raw clock fallback for random_get_entropy()
  openrisc: start CPU timer early in boot
  powerpc: define get_cycles macro for arch-override
  alpha: define get_cycles macro for arch-override
  parisc: define get_cycles macro for arch-override
  s390: define get_cycles macro for arch-override
  ia64: define get_cycles macro for arch-override
  init: call time_init() before rand_initialize()
  random: fix sysctl documentation nits
  io_uring: only wake when the correct events are set
  security: declare member holding string literal const
  xtensa: add trap handler for division by zero
  io_uring: avoid io-wq -EAGAIN looping for !IOPOLL
  x86/speculation: Add missing srbds=off to the mitigations= help text
  io_uring: add flag for allocating a fully sparse direct descriptor space
  io_uring: bump max direct descriptor count to 1M
  io_uring: allow allocated fixed files for accept
  io_uring: allow allocated fixed files for openat/openat2
  io_uring: add basic fixed file allocator
  io_uring: track fixed files with a bitmap
  x86/prctl: Remove pointless task argument
  futex: Remove a PREEMPT_RT_FULL reference.
  debugobjects: Convert to SPDX license identifier
  csky: Move $(core-y) into arch/csky/Kbuild
  csky: Remove unused core-y for dts
  csky: Remove unused $(dtb-y) from boot/Makefile
  scripts/faddr2line: Fix overlapping text section failures
  scripts: Create objdump-func helper script
  blk-mq: fix passthrough plugging
  perf/x86/amd: Remove unused variable 'hwc'
  objtool: Remove libsubcmd.a when make clean
  objtool: Remove inat-tables.c when make clean
  platform/x86: toshiba_acpi: use kobj_to_dev()
  platform/x86: samsung-laptop: use kobj_to_dev()
  platform/x86: gigabyte-wmi: Add support for Z490 AORUS ELITE AC and X570 AORUS ELITE WIFI
  tools/power/x86/intel-speed-select: Fix warning for perf_cap.cpu
  tools/power/x86/intel-speed-select: Display error on turbo mode disabled
  Documentation: In-Field Scan
  platform/x86/intel/ifs: add ABI documentation for IFS
  trace: platform/x86/intel/ifs: Add trace point to track Intel IFS operations
  platform/x86/intel/ifs: Add IFS sysfs interface
  platform/x86/intel/ifs: Add scan test support
  platform/x86/intel/ifs: Authenticate and copy to secured memory
  platform/x86/intel/ifs: Check IFS Image sanity
  platform/x86/intel/ifs: Read IFS firmware image
  platform/x86/intel/ifs: Add stub driver for In-Field Scan
  stop_machine: Add stop_core_cpuslocked() for per-core operations
  x86/msr-index: Define INTEGRITY_CAPABILITIES MSR
  x86/microcode/intel: Expose collect_cpu_info_early() for IFS
  platform/x86: asus-nb-wmi: Add keymap for MyASUS key
  platform/x86: asus-wmi: Update unknown code message
  Documentation/ABI: Add new attributes for mlxreg-io sysfs interfaces
  platform/mellanox: Add support for new SN2201 system
  perf/arm-cmn: Decode CAL devices properly in debugfs
  block: Fix the bio.bi_opf comment
  block: reorder the REQ_ flags
  blk-iocost: combine local_stat and desc_stat to stat
  rcu: Move expedited grace period (GP) work to RT kthread_worker
  x86/vsyscall: Remove CONFIG_LEGACY_VSYSCALL_EMULATE
  rcu: Introduce CONFIG_RCU_EXP_CPU_STALL_TIMEOUT
  platform_data/mlxreg: Add field for notification callback
  sched/deadline: Remove superfluous rq clock update in push_dl_task()
  sched/core: Avoid obvious double update_rq_clock warning
  perf/ibs: Fix comment
  perf/amd/ibs: Advertise zen4_ibs_extensions as pmu capability attribute
  perf/amd/ibs: Add support for L3 miss filtering
  perf/amd/ibs: Use ->is_visible callback for dynamic attributes
  perf/amd/ibs: Cascade pmu init functions' return value
  perf/x86/uncore: Add new Alder Lake and Raptor Lake support
  perf/x86/uncore: Clean up uncore_pci_ids[]
  perf/x86/cstate: Add new Alder Lake and Raptor Lake support
  perf/x86/msr: Add new Alder Lake and Raptor Lake support
  perf/x86: Add new Alder Lake and Raptor Lake support
  locking/qrwlock: Change "queue rwlock" to "queued rwlock"
  lockdep: Delete local_irq_enable_in_hardirq()
  nvme: add vectored-io support for uring-cmd
  nvme: wire-up uring-cmd support for io-passthru on char-device.
  nvme: refactor nvme_submit_user_cmd()
  block: wire-up support for passthrough plugging
  fs,io_uring: add infrastructure for uring-cmd
  arm64/hugetlb: Drop TLB flush from get_clear_flush()
  s390/preempt: disable __preempt_count_add() optimization for PROFILE_ALL_BRANCHES
  s390/stp: clock_delta should be signed
  s390/stp: fix todoff size
  arm64: Declare non global symbols as static
  perf/arm-cmn: Fix filter_sel lookup
  xtensa/simdisk: fix proc_read_simdisk()
  xtensa: no need to initialise statics to 0
  gcc-plugins: Change all version strings match kernel
  randomize_kstack: Improve docs on requirements/rationale
  loop: remove most the top-of-file boilerplate comment from the UAPI header
  loop: remove most the top-of-file boilerplate comment
  loop: add a SPDX header
  loop: remove loop.h
  perf/marvell_cn10k: Fix tad_pmu_event_init() to check pmu type first
  perf/amd/ibs: Use interrupt regs ip for stack unwinding
  fscrypt: add new helper functions for test_dummy_encryption
  fscrypt: factor out fscrypt_policy_to_key_spec()
  io_uring: support CQE32 for nop operation
  io_uring: enable CQE32
  io_uring: support CQE32 in /proc info
  io_uring: add tracing for additional CQE32 fields
  io_uring: overflow processing for CQE32
  io_uring: flush completions for CQE32
  io_uring: modify io_get_cqe for CQE32
  io_uring: add CQE32 completion processing
  io_uring: add CQE32 setup processing
  io_uring: change ring size calculation for CQE32
  io_uring: store add. return values for CQE32
  io_uring: support CQE32 in io_uring_cqe
  io_uring: add support for 128-byte SQEs
  io_uring: don't clear req->kbuf when buffer selection is done
  io_uring: eliminate the need to track provided buffer ID separately
  io_uring: move provided buffer state closer to submit state
  io_uring: move provided and fixed buffers into the same io_kiocb area
  io_uring: abstract out provided buffer list selection
  io_uring: never call io_buffer_select() for a buffer re-select
  io_uring: get rid of hashed provided buffer groups
  io_uring: always use req->buf_index for the provided buffer group
  io_uring: ignore ->buf_index if REQ_F_BUFFER_SELECT isn't set
  io_uring: kill io_rw_buffer_select() wrapper
  io_uring: make io_buffer_select() return the user address directly
  doc: admin-guide: Update libata kernel parameters
  ata: libata-core: Allow forcing most horkage flags
  ata: libata-core: Improve link flags forced settings
  ata: libata-core: Refactor force_tbl definition
  ata: libata-core: cleanup ata_device_blacklist
  ata: simplify the return expression of brcm_ahci_remove
  m68k: math-emu: Fix typos in comments
  m68k: Wire up syscall_trace_enter/leave for m68k
  s390/pai: add support for cryptography counters
  entry: Rename arch_check_user_regs() to arch_enter_from_user_mode()
  lkdtm/stackleak: fix CONFIG_GCC_PLUGIN_STACKLEAK=n
  arm64: entry: use stackleak_erase_on_task_stack()
  stackleak: add on/off stack variants
  lkdtm/stackleak: check stack boundaries
  lkdtm/stackleak: prevent unexpected stack usage
  lkdtm/stackleak: rework boundary management
  lkdtm/stackleak: avoid spurious failure
  stackleak: rework poison scanning
  stackleak: rework stack high bound handling
  stackleak: clarify variable names
  stackleak: rework stack low bound handling
  stackleak: remove redundant check
  stackleak: move skip_erasing() check earlier
  arm64: stackleak: fix current_top_of_stack()
  randstruct: Enable Clang support
  randstruct: Move seed generation into scripts/basic/
  randstruct: Split randstruct Makefile and CFLAGS
  randstruct: Reorganize Kconfigs and attribute macros
  sancov: Split plugin build from plugin CFLAGS
  netfs: Eliminate Clang randstruct warning
  docs: kdump: Update the crashkernel description for arm64
  of: Support more than one crash kernel regions for kexec -s
  of: fdt: Add memory for devices by DT property "linux,usable-memory-range"
  arm64: kdump: Reimplement crashkernel=X
  arm64: Use insert_resource() to simplify code
  kdump: return -ENOENT if required cmdline option does not exist
  objtool: Fix STACK_FRAME_NON_STANDARD reloc type
  s390/compat: cleanup compat_linux.h header file
  s390/entry: remove broken and not needed code
  s390/boot: convert parmarea to C
  s390/boot: convert initial lowcore to C
  s390/ptrace: move short psw definitions to ptrace header file
  s390/head: initialize all new psws
  s390/boot: change initial program check handler to disabled wait psw
  s390/head: adjust iplstart entry point
  s390/boot: get rid of startup archive
  s390/vx: remove comments from macros which break LLVM's IAS
  s390/extable: prefer local labels in .set directives
  s390/nospec: prefer local labels in .set directives
  s390/hypfs: fix typos in comments
  s390/crypto: fix typos in comments
  s390/consoles: improve panic notifiers reliability
  arm64/sme: More sensibly define the size for the ZA register set
  drivers/perf: hisi: Add Support for CPA PMU
  drivers/perf: hisi: Associate PMUs in SICL with CPUs online
  drivers/perf: arm_spe: Expose saturating counter to 16-bit
  perf/arm-cmn: Add CMN-700 support
  perf/arm-cmn: Refactor occupancy filter selector
  perf/arm-cmn: Add CMN-650 support
  dt-bindings: perf: arm-cmn: Add CMN-650 and CMN-700
  perf: check return value of armpmu_request_irq()
  linkage: Fix issue with missing symbol size
  x86/entry: Remove skip_r11rcx
  x86/entry: Use PUSH_AND_CLEAR_REGS for compat
  x86/entry: Simplify entry_INT80_compat()
  x86/mm: Simplify RESERVE_BRK()
  perf: RISC-V: Remove non-kernel-doc ** comments
  irqchip/armada-370-xp: Do not touch Performance Counter Overflow on A375, A38x, A39x
  platform/x86: pmc_atom: dont export pmc_atom_read - no modular users
  platform/x86: pmc_atom: remove unused pmc_atom_write()
  platform/x86: amd-pmc: Fix build error unused-function
  platform/surface: aggregator: Fix initialization order when compiling as builtin module
  platform/surface: gpe: Add support for Surface Pro 8
  platform/x86/intel: Fix 'rmmod pmt_telemetry' panic
  platform/x86: thinkpad_acpi: Correct dual fan probe
  platform/x86: thinkpad_acpi: Add a s2idle resume quirk for a number of laptops
  platform/x86: thinkpad_acpi: Convert btusb DMI list to quirks
  efi: stub: prefer mirrored memory for randomized allocations
  io_uring: kill io_recv_buffer_select() wrapper
  io_uring: use 'sr' vs 'req->sr_msg' consistently
  io_uring: add POLL_FIRST support for send/sendmsg and recv/recvmsg
  io_uring: check IOPOLL/ioprio support upfront
  arm64: mm: Cleanup useless parameters in zone_sizes_init()
  block: improve the error message from bio_check_eod
  block: allow passing a NULL bdev to bio_alloc_clone/bio_init_clone
  block: remove superfluous calls to blkcg_bio_issue_init
  selftests/seccomp: Fix spelling mistake "Coud" -> "Could"
  arm64: fix types in copy_highpage()
  arm64/sysreg: Generate definitions for SCTLR_EL1
  x86/mm: Cleanup the control_va_addr_alignment() __setup handler
  irqchip/gic: Improved warning about incorrect type
  irqchip/csky: Return true/false (not 1/0) from bool functions
  irqchip/imx-irqsteer: Add runtime PM support
  irqchip/imx-irqsteer: Constify irq_chip struct
  irqchip/armada-370-xp: Enable MSI affinity configuration
  irqchip/aspeed-scu-ic: Fix irq_of_parse_and_map() return value
  irqchip/aspeed-i2c-ic: Fix irq_of_parse_and_map() return value
  irqchip/sun6i-r: Use NULL for chip_data
  irqchip/xtensa-mx: Fix initial IRQ affinity in non-SMP setup
  arm64: Set ARCH_NR_GPIO to 2048 for ARCH_APPLE
  irqchip/exiu: Fix acknowledgment of edge triggered interrupts
  x86: Fix return value of __setup handlers
  irqchip/gic-v3: Claim iomem resources
  dt-bindings: interrupt-controller: arm,gic-v3: Make the v2 compat requirements explicit
  irqchip/gic-v3: Relax polling of GIC{R,D}_CTLR.RWP
  irqchip/gic-v3: Detect LPI invalidation MMIO registers
  arm64/sysreg: Generate definitions for TTBRn_EL1
  arm64/sysreg: Generate definitions for ID_AA64ISAR0_EL1
  arm64/sysreg: Enable automatic generation of system register definitions
  arm64: Add sysreg header generation scripting
  arm64/sysreg: Standardise ID_AA64ISAR0_EL1 macro names
  arm64: Update name of ID_AA64ISAR0_EL1_ATOMIC to reflect ARM
  arm64/sysreg: Define bits for previously RES1 fields in SCTLR_EL1
  arm64/sysreg: Rename SCTLR_EL1_NTWE/TWI to SCTLR_EL1_nTWE/TWI
  arm64/mte: Make TCF field values and naming more standard
  arm64/mte: Make TCF0 naming and field values more standard
  arm64/sysreg: Introduce helpers for access to sysreg fields
  irqchip/gic-v3: Exposes bit values for GICR_CTLR.{IR, CES}
  block: null_blk: Improve device creation with configfs
  block: null_blk: Cleanup messages
  block: null_blk: Cleanup device creation and deletion
  block: null_blk: Fix code style issues
  xen-blkback: use bdev_discard_alignment
  arm64: cputype: Avoid overflow using MIDR_IMPLEMENTOR_MASK
  x86/split_lock: Enable the split lock feature on Raptor Lake
  perf/x86/amd/core: Add PerfMonV2 overflow handling
  perf/x86/amd/core: Add PerfMonV2 counter control
  perf/x86/amd/core: Detect available counters
  perf/x86/amd/core: Detect PerfMonV2 support
  x86/msr: Add PerfCntrGlobal* registers
  x86/cpufeatures: Add PerfMonV2 feature bit
  kselftest/arm64: Fix ABI header directory location
  selftests/seccomp: Add test for wait killable notifier
  selftests/seccomp: Refactor get_proc_stat to split out file reading code
  seccomp: Add wait_killable semantic to seccomp user notifier
  selinux: log anon inode class name
  selinux: declare data arrays const
  selinux: fix indentation level of mls_ops block
  selinux: include necessary headers in headers
  selinux: avoid extra semicolon
  selinux: update parameter documentation
  selinux: resolve checkpatch errors
  srcu: Drop needless initialization of sdp in srcu_gp_start()
  srcu: Prevent expedited GPs and blocking readers from consuming CPU
  srcu: Add contention check to call_srcu() srcu_data ->lock acquisition
  srcu: Automatically determine size-transition strategy at boot
  tools/memory-model/README: Update klitmus7 compat table
  rnbd-srv: use bdev_discard_alignment
  nvme: remove a spurious clear of discard_alignment
  loop: remove a spurious clear of discard_alignment
  dasd: don't set the discard_alignment queue limit
  raid5: don't set the discard_alignment queue limit
  dm-zoned: don't set the discard_alignment queue limit
  virtio_blk: fix the discard_granularity and discard_alignment queue limits
  null_blk: don't set the discard_alignment queue limit
  nbd: don't set the discard_alignment queue limit
  ubd: don't set the discard_alignment queue limit
  efi/arm64: libstub: run image in place if randomized by the loader
  efi: libstub: pass image handle to handle_kernel_image()
  efi: x86: Set the NX-compatibility flag in the PE header
  efi: libstub: ensure allocated memory to be executable
  efi: libstub: declare DXE services table
  x86/entry: Convert SWAPGS to swapgs and remove the definition of SWAPGS
  x86/entry: Don't call error_entry() for XENPV
  x86/entry: Move CLD to the start of the idtentry macro
  x86/entry: Move PUSH_AND_CLEAR_REGS out of error_entry()
  x86/entry: Switch the stack after error_entry() returns
  x86/traps: Use pt_regs directly in fixup_bad_iret()
  kthread: unexport kthread_blkcg
  blk-cgroup: cleanup blkcg_maybe_throttle_current
  blk-cgroup: cleanup blk_cgroup_congested
  blk-cgroup: move blkcg_css to blk-cgroup.c
  blk-cgroup: remove unneeded includes from <linux/blk-cgroup.h>
  blk-cgroup: remove pointless CONFIG_BLOCK ifdefs
  blk-cgroup: replace bio_blkcg with bio_blkcg_css
  blktrace: cleanup the __trace_note_message interface
  blk-cgroup: move struct blkcg to block/blk-cgroup.h
  blk-cgroup: move blkcg_{pin,unpin}_online out of line
  blk-cgroup: move blk_cgroup_congested out line
  blk-cgroup: move blkcg_{get,set}_fc_appid out of line
  nvme-fc: fold t fc_update_appid into fc_appid_store
  nvme-fc: don't support the appid attribute without CONFIG_BLK_CGROUP_FC_APPID
  blk-cgroup: remove __bio_blkcg
  block: ignore RWF_HIPRI hint for sync dio
  x86/sev: Fix address space sparse warning
  time/sched_clock: Fix formatting of frequency reporting code
  time/sched_clock: Use Hz as the unit for clock rate reporting below 4kHz
  time/sched_clock: Round the frequency reported to nearest rather than down
  genirq: Use pm_runtime_resume_and_get() instead of pm_runtime_get_sync()
  timekeeping: Consolidate fast timekeeper
  timekeeping: Annotate ktime_get_boot_fast_ns() with data_race()
  EDAC: Use kcalloc()
  x86/fpu: Cleanup variable shadowing
  x86/aperfperf: Make it correct on 32bit and UP kernels
  xtensa: clean up labels in the kernel entry assembly
  xtensa: don't leave invalid TLB entry in fast_store_prohibited
  xtensa: fix declaration of _SecondaryResetVector_text_*
  irqchip: irq-xtensa-mx: fix initial IRQ affinity
  xtensa: enable ARCH_HAS_DEBUG_VM_PGTABLE
  xtensa: add hibernation support
  xtensa: support coprocessors on SMP
  xtensa: get rid of stack frame in coprocessor_flush
  xtensa: merge SAVE_CP_REGS_TAB and LOAD_CP_REGS_TAB
  xtensa: add xtensa_xsr macro
  xtensa: handle coprocessor exceptions in kernel mode
  xtensa: use callx0 opcode in fast_coprocessor
  xtensa: clean up excsave1 initialization
  xtensa: clean up declarations in coprocessor.h
  xtensa: clean up exception handler prototypes
  xtensa: clean up function declarations in traps.c
  xtensa: enable KCSAN
  xtensa: enable HAVE_VIRT_CPU_ACCOUNTING_GEN
  xtensa: enable context tracking
  xtensa: use abi_* register names in the kernel exit code
  xtensa: move trace_hardirqs_off call back to entry.S
  xtensa: drop dead code from entry.S
  xtensa: noMMU: allow handling protection faults
  xtensa: extract vmalloc_fault code into a function
  xtensa: move asid_cache from fault.c to mmu.c
  xtensa: iss: extract and constify network callbacks
  xtensa: iss: clean up per-device locking in network driver
  xtensa: iss: replace iss_net_set_mac with eth_mac_addr
  xtensa: iss: drop opened_list logic from the network driver
  xtensa: localize labels used in memmove
  x86/apic: Do apic driver probe for "nosmp" use case
  aoe: Avoid flush_scheduled_work() usage
  smp: Make softirq handling RT safe in flush_smp_call_function_queue()
  smp: Rename flush_smp_call_function_from_idle()
  sched: Fix missing prototype warnings
  io_uring: replace smp_mb() with smp_mb__after_atomic() in io_sq_thread()
  io_uring: add IORING_SETUP_TASKRUN_FLAG
  io_uring: use TWA_SIGNAL_NO_IPI if IORING_SETUP_COOP_TASKRUN is used
  io_uring: set task_work notify method at init time
  io-wq: use __set_notify_signal() to wake workers
  io_uring: serialize ctx->rings->sq_flags with atomic_or/and
  task_work: allow TWA_SIGNAL without a rescheduling IPI
  io_uring: return hint on whether more data is available after receive
  tcp: pass back data left in socket after receive
  selftests/seccomp: Ensure that notifications come in FIFO order
  seccomp: Use FIFO semantics to order notifications
  selftests/seccomp: Add SKIP for failed unshare()
  selftests/seccomp: Test PTRACE_O_SUSPEND_SECCOMP without CAP_SYS_ADMIN
  KVM: arm64: uapi: Add kvm_debug_exit_arch.hsr_high
  KVM: arm64: Treat ESR_EL2 as a 64-bit register
  arm64: Treat ESR_ELx as a 64-bit register
  arm64: compat: Do not treat syscall number as ESR_ELx for a bad syscall
  arm64: Make ESR_ELx_xVC_IMM_MASK compatible with assembly
  arm64/ftrace: Make function graph use ftrace directly
  ftrace: cleanup ftrace_graph_caller enable and disable
  arm64/sme: Fix NULL check after kzalloc
  EDAC/ghes: Change ghes_hw from global to static
  EDAC/armada_xp: Use devm_platform_ioremap_resource()
  sched/fair: Remove cfs_rq_tg_path()
  sched/fair: Remove sched_trace_*() helper functions
  sched/fair: Refactor cpu_util_without()
  io_uring: use the text representation of ops in trace
  selftests/arm64: Fix O= builds for the floating point tests
  selftests/arm64: Clean the fp helper libraries
  selftests/arm64: Define top_srcdir for the fp tests
  selftests/arm64: Use TEST_GEN_PROGS_EXTENDED in the FP Makefile
  kselftest/arm64: fix array_size.cocci warning
  selftests/arm64: Add a testcase for handling of ZA on clone()
  kselftest/arm64: Add SME support to syscall ABI test
  kselftest/arm64: Add coverage for the ZA ptrace interface
  kselftest/arm64: Add streaming SVE to SVE ptrace tests
  kselftest/arm64: signal: Add SME signal handling tests
  kselftest/arm64: Add stress test for SME ZA context switching
  kselftest/arm64: signal: Handle ZA signal context in core code
  kselftest/arm64: sme: Provide streaming mode SVE stress test
  kselftest/arm64: Extend vector configuration API tests to cover SME
  kselftest/arm64: Add tests for TPIDR2
  kselftest/arm64: sme: Add SME support to vlset
  kselftest/arm64: Add manual encodings for SME instructions
  kselftest/arm64: Add simple test for MTE prctl
  kselftest/arm64: Refactor parameter checking in mte_switch_mode()
  kselftest/arm64: Log unexpected asynchronous MTE faults
  kselftest/arm64: Handle more kselftest result codes in MTE helpers
  kselftest/arm64: Validate setting via FPSIMD and read via SVE regsets
  kselftest/arm64: Remove assumption that tasks start FPSIMD only
  kselftest/arm64: Fix comment for ptrace_sve_get_fpsimd_data()
  EDAC/synopsys: Add a SPDX identifier
  EDAC/synopsys: Add driver support for i.MX platforms
  x86/speculation: Add missing prototype for unpriv_ebpf_notify()
  amd_hsmp: Add HSMP protocol version 5 messages
  platform/x86/dell: add buffer allocation/free functions for SMI calls
  x86/aperfmperf: Integrate the fallback code from show_cpuinfo()
  x86/aperfmperf: Replace arch_freq_get_on_cpu()
  x86/aperfmperf: Replace aperfmperf_get_khz()
  x86/aperfmperf: Store aperf/mperf data for cpu frequency reads
  x86/aperfmperf: Make parts of the frequency invariance code unconditional
  x86/aperfmperf: Restructure arch_scale_freq_tick()
  x86/aperfmperf: Put frequency invariance aperf/mperf data into a struct
  x86/aperfmperf: Untangle Intel and AMD frequency invariance init
  arm64/sme: Add ID_AA64SMFR0_EL1 to __read_sysreg_by_encoding()
  platform/x86: asus-wmi: Use kobj_to_dev()
  platform/x86/intel: pmc/core: Use kobj_to_dev()
  platform/x86/intel: pmc/core: change pmc_lpm_modes to static
  platform/x86/intel/sdsi: Fix bug in multi packet reads
  platform/x86/intel/sdsi: Poll on ready bit for writes
  platform/x86/intel/sdsi: Handle leaky bucket
  platform/x86: intel-uncore-freq: Prevent driver loading in guests
  platform/x86: gigabyte-wmi: added support for B660 GAMING X DDR4 motherboard
  platform/x86: dell-laptop: Add quirk entry for Latitude 7520
  platform/x86: asus-wmi: Fix driver not binding when fan curve control probe fails
  platform/x86: asus-wmi: Potential buffer overflow in asus_wmi_evaluate_method_buf()
  platform/x86: amd-pmc: Shuffle location of amd_pmc_get_smu_version()
  x86/aperfmperf: Separate AP/BP frequency invariance init
  x86/smp: Move APERF/MPERF code where it belongs
  x86/aperfmperf: Dont wake idle CPUs in arch_freq_get_on_cpu()
  x86/split-lock: Remove unused TIF_SLD bit
  x86/split_lock: Make life miserable for split lockers
  x86/pm: Fix false positive kmemleak report in msr_build_context()
  x86/sev: Get the AP jump table address from secrets page
  x86/sev: Add missing __init annotations to SEV init routines
  virt: sevguest: Rename the sevguest dir and files to sev-guest
  s390/irq: utilize RCU instead of irq_lock_sparse() in show_msi_interrupt()
  io_uring: rename op -> opcode
  io_uring: add io_uring_get_opcode
  io_uring: add type to op enum
  documentation: zonefs: Document sysfs attributes
  null-blk: save memory footprint for struct nullb_cmd
  io_uring: fix compile warning for 32-bit builds
  md: Replace role magic numbers with defined constants
  md/raid0: Ignore RAID0 layout if the second zone has only one device
  md/raid5: Annotate functions that hold device_lock with __must_hold
  md/raid5-ppl: Annotate with rcu_dereference_protected()
  md/raid5: Annotate rdev/replacement access when mddev_lock is held
  md/raid5: Annotate rdev/replacement accesses when nr_pending is elevated
  md/raid5: Add __rcu annotation to struct disk_info
  md/raid5: Un-nest struct raid5_percpu definition
  md/raid5: Cleanup setup_conf() error returns
  md: replace deprecated strlcpy & remove duplicated line
  md/bitmap: don't set sb values if can't pass sanity check
  md: fix an incorrect NULL check in md_reload_sb
  md: fix an incorrect NULL check in does_sb_need_changing
  raid5: introduce MD_BROKEN
  md: Set MD_BROKEN for RAID1 and RAID10
  arm64: document the boot requirements for MTE
  x86/fpu/xsave: Support XSAVEC in the kernel
  genirq/matrix: Remove redundant assignment to variable 'end'
  timers/nohz: Switch to ONESHOT_STOPPED in the low-res handler when the tick is stopped
  m68k: defconfig: Update defconfigs for v5.18-rc1
  s390: add KCSAN instrumentation to barriers and spinlocks
  s390/pci: add error record for CC 2 retries
  s390/pci: add PCI access type and length to error records
  s390/pci: don't log availability events as errors
  s390/pci: make better use of zpci_dbg() levels
  s390/vfio-ap: remove superfluous MODULE_DEVICE_TABLE declaration
  s390/vdso: add vdso randomization
  s390/vdso: map vdso above stack
  s390/vdso: move vdso mapping to its own function
  s390/mmap: increase stack/mmap gap to 128MB
  s390/zcrypt: code cleanup
  s390/zcrypt: cleanup CPRB struct definitions
  s390/ap: uevent on apmask/aqpmask change
  s390/cio: simplify the calculation of variables
  s390/smp: sort out physical vs virtual CPU0 lowcore pointer
  s390/zcrypt: add display of ASYM master key verification pattern
  s390/kexec: set end-of-ipl flag in last diag308 call
  s390/sclp: add detection of IPL-complete-control facility
  x86/mce: Add messages for panic errors in AMD's MCE grading
  x86/mce: Simplify AMD severity grading logic
  btrfs: Avoid live-lock in search_ioctl() on hardware with sub-page faults
  arm64: Add support for user sub-page fault probing
  mm: Add fault_in_subpage_writeable() to probe at sub-page granularity
  csky: atomic: Add conditional atomic operations' optimization
  csky: atomic: Add custom atomic.h implementation
  csky: atomic: Optimize cmpxchg with acquire & release
  io_uring: cleanup error-handling around io_req_complete
  io_uring: add socket(2) support
  net: add __sys_socket_file()
  io_uring: fix trace for reduced sqe padding
  io_uring: add fgetxattr and getxattr support
  io_uring: add fsetxattr and setxattr support
  fs: split off do_getxattr from getxattr
  fs: split off setxattr_copy and do_setxattr function from setxattr
  io_uring: return an error when cqe is dropped
  io_uring: use constants for cq_overflow bitfield
  io_uring: rework io_uring_enter to simplify return value
  io_uring: trace cqe overflows
  io_uring: add trace support for CQE overflow
  io_uring: allow re-poll if we made progress
  io_uring: support MSG_WAITALL for IORING_OP_SEND(MSG)
  io_uring: add support for IORING_ASYNC_CANCEL_ANY
  io_uring: allow IORING_OP_ASYNC_CANCEL with 'fd' key
  io_uring: add support for IORING_ASYNC_CANCEL_ALL
  io_uring: pass in struct io_cancel_data consistently
  io_uring: remove dead 'poll_only' argument to io_poll_cancel()
  io_uring: refactor io_disarm_next() locking
  io_uring: move timeout locking in io_timeout_cancel()
  io_uring: store SCM state in io_fixed_file->file_ptr
  io_uring: kill ctx arg from io_req_put_rsrc
  io_uring: add a helper for putting rsrc nodes
  io_uring: store rsrc node in req instead of refs
  io_uring: refactor io_assign_file error path
  io_uring: use right helpers for file assign locking
  io_uring: add data_race annotations
  io_uring: inline io_req_complete_fail_submit()
  io_uring: refactor io_submit_sqe()
  io_uring: refactor lazy link fail
  io_uring: introduce IO_REQ_LINK_FLAGS
  io_uring: refactor io_queue_sqe()
  io_uring: rename io_queue_async_work()
  io_uring: inline io_queue_sqe()
  io_uring: helper for prep+queuing linked timeouts
  io_uring: inline io_free_req()
  io_uring: kill io_put_req_deferred()
  io_uring: minor refactoring for some tw handlers
  io_uring: clean poll tw PF_EXITING handling
  io_uring: optimise io_get_cqe()
  io_uring: optimise submission left counting
  io_uring: optimise submission loop invariant
  io_uring: add helper to return req to cache list
  io_uring: helper for empty req cache checks
  io_uring: inline io_flush_cached_reqs
  io_uring: shrink final link flush
  io_uring: memcpy CQE from req
  io_uring: explicitly keep a CQE in io_kiocb
  io_uring: rename io_sqe_file_register
  io_uring: deduplicate SCM accounting
  io_uring: don't pass around fixed index for scm
  io_uring: refactor __io_sqe_files_scm
  io_uring: uniform SCM accounting
  io_uring: don't scm-account for non af_unix sockets
  io_uring: move finish_wait() outside of loop in cqring_wait()
  io_uring: refactor io_req_add_compl_list()
  io_uring: silence io_for_each_link() warning
  io_uring: partially uninline io_put_task()
  io_uring: cleanup conditional submit locking
  io_uring: optimise mutex locking for submit+iopoll
  io_uring: pre-calculate syscall iopolling decision
  io_uring: split off IOPOLL argument verifiction
  io_uring: clean up io_queue_next()
  io_uring: move poll recycling later in compl flushing
  io_uring: optimise io_free_batch_list
  io_uring: refactor io_req_find_next
  io_uring: remove extra ifs around io_commit_cqring
  io_uring: small optimisation of tctx_task_work
  block/partitions/ldm: Remove redundant assignments
  block/partitions/atari: Remove redundant assignment
  block/partitions/acorn: Remove redundant assignments
  block/blk-map: Remove redundant assignment
  block/badblocks: Remove redundant assignments
  binfmt_flat: Remove shared library support
  arm64/sme: Provide Kconfig for SME
  KVM: arm64: Handle SME host state when running guests
  KVM: arm64: Trap SME usage in guest
  KVM: arm64: Hide SME system registers from guests
  arm64/sme: Save and restore streaming mode over EFI runtime calls
  arm64/sme: Disable streaming mode and ZA when flushing CPU state
  arm64/sme: Add ptrace support for ZA
  arm64/sme: Implement ptrace support for streaming mode SVE registers
  arm64/sme: Implement ZA signal handling
  arm64/sme: Implement streaming SVE signal handling
  arm64/sme: Disable ZA and streaming mode when handling signals
  arm64/sme: Implement traps and syscall handling for SME
  arm64/sme: Implement ZA context switching
  arm64/sme: Implement streaming SVE context switching
  arm64/sme: Implement SVCR context switching
  arm64/sme: Implement support for TPIDR2
  arm64/sme: Implement vector length configuration prctl()s
  arm64/sme: Implement sysctl to set the default vector length
  arm64/sme: Identify supported SME vector lengths at boot
  arm64/sme: Basic enumeration support
  arm64/sme: Early CPU setup for SME
  arm64/sme: Manually encode SME instructions
  arm64/sme: System register and exception syndrome definitions
  arm64/sme: Provide ABI documentation for SME
  arm64: stacktrace: align with common naming
  arm64: stacktrace: rename stackframe to unwind_state
  arm64: stacktrace: rename unwinder functions
  arm64: stacktrace: make struct stackframe private to stacktrace.c
  arm64: stacktrace: delete PCS comment
  arm64: stacktrace: remove NULL task check from unwind_frame()
  arm64/mm: Compute PTRS_PER_[PMD|PUD] independently of PTRS_PER_PTE
  objtool: Update documentation
  objtool: Remove --lto and --vmlinux in favor of --link
  objtool: Add HAVE_NOINSTR_VALIDATION
  objtool: Rename "VMLINUX_VALIDATION" -> "NOINSTR_VALIDATION"
  objtool: Make noinstr hacks optional
  objtool: Make jump label hack optional
  objtool: Make static call annotation optional
  objtool: Make stack validation frame-pointer-specific
  objtool: Add CONFIG_OBJTOOL
  objtool: Extricate sls from stack validation
  objtool: Rework ibt and extricate from stack validation
  objtool: Make stack validation optional
  objtool: Add option to print section addresses
  objtool: Don't print parentheses in function addresses
  objtool: Ditch subcommands
  objtool: Reorganize cmdline options
  libsubcmd: Fix OPTION_GROUP sorting
  sched/fair: Revise comment about lb decision matrix
  sched/psi: report zeroes for CPU full at the system level
  sched/fair: Delete useless condition in tg_unthrottle_up()
  sched/fair: Fix cfs_rq_clock_pelt() for throttled cfs_rq
  sched/fair: Move calculate of avg_load to a better location
  mailmap: Update my email address to @redhat.com
  MAINTAINERS: Add myself as scheduler topology reviewer
  psi: Fix trigger being fired unexpectedly at initial
  signal: Deliver SIGTRAP on perf event asynchronously if blocked
  ata: Make use of the helper function devm_platform_ioremap_resource()
  ata: libata-core: replace "its" with "it is"
  ahci: Add a generic 'controller2' RAID id
  x86/tdx: Annotate a noreturn function
  virt: sevguest: Change driver name to reflect generic SEV support
  tools/nolibc/string: Implement `strdup()` and `strndup()`
  tools/nolibc/string: Implement `strnlen()`
  tools/nolibc/stdlib: Implement `malloc()`, `calloc()`, `realloc()` and `free()`
  tools/nolibc/types: Implement `offsetof()` and `container_of()` macro
  tools/nolibc/sys: Implement `mmap()` and `munmap()`
  tools/nolibc: i386: Implement syscall with 6 arguments
  tools/nolibc: Remove .global _start from the entry point code
  tools/nolibc: Replace `asm` with `__asm__`
  tools/nolibc: x86-64: Update System V ABI document link
  tools/nolibc/stdlib: only reference the external environ when inlined
  tools/nolibc/string: do not use __builtin_strlen() at -O0
  tools/nolibc: add the nolibc subdir to the common Makefile
  tools/nolibc: add a makefile to install headers
  tools/nolibc/types: add poll() and waitpid() flag definitions
  tools/nolibc/sys: add syscall definition for getppid()
  tools/nolibc/string: add strcmp() and strncmp()
  tools/nolibc/stdio: add support for '%p' to vfprintf()
  tools/nolibc/stdlib: add a simple getenv() implementation
  tools/nolibc/stdio: make printf(%s) accept NULL
  tools/nolibc/stdlib: implement abort()
  tools/nolibc: also mention how to build by just setting the include path
  tools/nolibc/time: create time.h with time()
  tools/nolibc/signal: move raise() to signal.h
  tools/nolibc/unistd: add usleep()
  tools/nolibc/unistd: extract msleep(), sleep(), tcsetpgrp() to unistd.h
  tools/nolibc/errno: extract errno.h from sys.h
  tools/nolibc/string: export memset() and memmove()
  tools/nolibc/types: define PATH_MAX and MAXPATHLEN
  tools/nolibc/arch: mark the _start symbol as weak
  tools/nolibc: move exported functions to their own section
  tools/nolibc/string: add tiny versions of strncat() and strlcat()
  tools/nolibc/string: add strncpy() and strlcpy()
  tools/nolibc/string: slightly simplify memmove()
  tools/nolibc/string: use unidirectional variants for memcpy()
  tools/nolibc/sys: make getpgrp(), getpid(), gettid() not set errno
  tools/nolibc/stdlib: make raise() use the lower level syscalls only
  tools/nolibc/stdlib: avoid a 64-bit shift in u64toh_r()
  tools/nolibc/sys: make open() take a vararg on the 3rd argument
  tools/nolibc/stdio: add perror() to report the errno value
  tools/nolibc/types: define EXIT_SUCCESS and EXIT_FAILURE
  tools/nolibc/stdio: add a minimal [vf]printf() implementation
  tools/nolibc/stdio: add fwrite() to stdio
  tools/nolibc/stdio: add stdin/stdout/stderr and fget*/fput* functions
  tools/nolibc/stdio: add a minimal set of stdio functions
  tools/nolibc/stdlib: add utoh() and u64toh()
  tools/nolibc/stdlib: add i64toa() and u64toa()
  tools/nolibc/stdlib: replace the ltoa() function with more efficient ones
  tools/nolibc/stdlib: move ltoa() to stdlib.h
  tools/nolibc/types: move makedev to types.h and make it a macro
  tools/nolibc/types: make FD_SETSIZE configurable
  tools/nolibc/types: move the FD_* functions to macros in types.h
  tools/nolibc/ctype: add the missing is* functions
  tools/nolibc/ctype: split the is* functions to ctype.h
  tools/nolibc/string: split the string functions into string.h
  tools/nolibc/stdlib: extract the stdlib-specific functions to their own file
  tools/nolibc/sys: split the syscall definitions into their own file
  tools/nolibc/arch: split arch-specific code into individual files
  tools/nolibc/types: split syscall-specific definitions into their own files
  tools/nolibc/std: move the standard type definitions to std.h
  rcutorture: Make torture.sh allow for --kasan
  rcutorture: Make torture.sh refscale and rcuscale specify Tasks Trace RCU
  rcutorture: Make kvm.sh allow more memory for --kasan runs
  torture: Save "make allmodconfig" .config file
  scftorture: Remove extraneous "scf" from per_version_boot_params
  rcutorture: Adjust scenarios' Kconfig options for CONFIG_PREEMPT_DYNAMIC
  torture: Enable CSD-lock stall reports for scftorture
  torture: Skip vmlinux check for kvm-again.sh runs
  scftorture: Adjust for TASKS_RCU Kconfig option being selected
  rcuscale: Allow rcuscale without RCU Tasks Rude/Trace
  rcuscale: Allow rcuscale without RCU Tasks
  refscale: Allow refscale without RCU Tasks Rude/Trace
  refscale: Allow refscale without RCU Tasks
  rcutorture: Allow specifying per-scenario stat_interval
  rcutorture: Add CONFIG_PREEMPT_DYNAMIC=n to TASKS02 scenario
  rcutorture: Allow rcutorture without RCU Tasks Rude
  rcutorture: Allow rcutorture without RCU Tasks
  rcutorture: Allow rcutorture without RCU Tasks Trace
  rcu: Make the TASKS_RCU Kconfig option be selected
  rcu: Use IRQ_WORK_INIT_HARD() to avoid rcu_read_unlock() hangs
  rcu_sync: Fix comment to properly reflect rcu_sync_exit() behavior
  rcu: Check for successful spawn of ->boost_kthread_task
  rcu: Fix preemption mode check on synchronize_rcu[_expedited]()
  rcu: Print number of online CPUs in RCU CPU stall-warning messages
  rcu: Add comments to final rcu_gp_cleanup() "if" statement
  kernel/smp: Provide boot-time timeout for CSD lock diagnostics
  documentation: zonefs: Cleanup the mount options section
  zonefs: Add active seq file accounting
  zonefs: Export open zone resource information through sysfs
  zonefs: Always do seq file write open accounting
  zonefs: Rename super block information fields
  zonefs: Fix management of open zones
  zonefs: Clear inode information flags on inode creation
  docs: Update RCU cross-references as suggested in doc-guide
  docs: Add documentation for rude and trace RCU flavors
  x86/boot: Put globals that are accessed early into the .data section
  binfmt_flat: Drop vestiges of coredump support
  x86/mm: Fix spacing within memory encryption features message
  Documentation: Update the recommended pattern for GPIO irqchips
  gpio: Update TODO to mention immutable irq_chip structures
  pinctrl: amd: Make the irqchip immutable
  pinctrl: msmgpio: Make the irqchip immutable
  pinctrl: apple-gpio: Make the irqchip immutable
  gpio: pl061: Make the irqchip immutable
  gpio: tegra186: Make the irqchip immutable
  gpio: Add helpers to ease the transition towards immutable irq_chip
  gpio: Expose the gpiochip_irq_re[ql]res helpers
  gpio: Don't fiddle with irqchips marked as immutable
  EDAC/dmc520: Don't print an error for each unconfigured interrupt line
  binfmt_flat: do not stop relocating GOT entries prematurely on riscv
  block/rnbd-clt: Avoid flush_workqueue(system_long_wq) usage
  csky: optimize memcpy_{from,to}io() and memset_io()
  csky: Add C based string functions
  loop: don't destroy lo->workqueue in __loop_clr_fd
  loop: remove lo_refcount and avoid lo_mutex in ->open / ->release
  loop: avoid loop_validate_mutex/lo_mutex in ->release
  loop: suppress uevents while reconfiguring the device
  loop: implement ->free_disk
  loop: only freeze the queue in __loop_clr_fd when needed
  loop: don't freeze the queue in lo_release
  loop: remove the racy bd_inode->i_mapping->nrpages asserts
  loop: initialize the worker tracking fields once
  loop: de-duplicate the idle worker freeing code
  block: turn bdev->bd_openers into an atomic_t
  block: add a disk_openers helper
  zram: cleanup zram_remove
  zram: cleanup reset_store
  nbd: use the correct block_device in nbd_bdev_reset
  block: change exported IO accounting interface from gendisk to bdev
  drbd: Return true/false (not 1/0) from bool functions
  drdb: Switch to kvfree_rcu() API
  drbd: Replace "unsigned" with "unsigned int"
  drbd: Make use of PFN_UP helper macro
  block: drbd: drbd_receiver: Remove redundant assignment to err
  drbd: address enum mismatch warnings
  drbd: fix duplicate array initializer
  direct-io: remove random prefetches
  block: decouple REQ_OP_SECURE_ERASE from REQ_OP_DISCARD
  block: add a bdev_discard_granularity helper
  block: remove QUEUE_FLAG_DISCARD
  block: add a bdev_max_discard_sectors helper
  block: refactor discard bio size limiting
  block: move {bdev,queue_limit}_discard_alignment out of line
  block: use bdev_discard_alignment in part_discard_alignment_show
  block: remove queue_discard_alignment
  block: move bdev_alignment_offset and queue_limit_alignment_offset out of line
  block: use bdev_alignment_offset in disk_alignment_offset_show
  block: use bdev_alignment_offset in part_alignment_offset_show
  block: add a bdev_max_zone_append_sectors helper
  block: add a bdev_stable_writes helper
  block: add a bdev_fua helper
  block: add a bdev_write_cache helper
  block: add a bdev_nonrot helper
  mm: use bdev_is_zoned in claim_swapfile
  ntfs3: use bdev_logical_block_size instead of open coding it
  btrfs: use bdev_max_active_zones instead of open coding it
  drbd: cleanup decide_on_discard_support
  drbd: use bdev_alignment_offset instead of queue_alignment_offset
  drbd: use bdev based limit helpers in drbd_send_sizes
  drbd: remove assign_p_sizes_qlim
  target: fix discard alignment on partitions
  target: pass a block_device to target_configure_unmap_from_queue
  target: remove an incorrect unmap zeroes data deduction
  bfq: Make sure bfqg for which we are queueing requests is online
  bfq: Get rid of __bio_blkcg() usage
  bfq: Track whether bfq_group is still online
  bfq: Remove pointless bfq_init_rq() calls
  bfq: Drop pointless unlock-lock pair
  bfq: Update cgroup information before merging bio
  bfq: Split shared queues on move between cgroups
  bfq: Avoid merging queues with different parents
  bfq: Avoid false marking of bic as stably merged
  pktcdvd: stop using bio_reset
  block: turn bio_kmalloc into a simple kmalloc wrapper
  target/pscsi: remove pscsi_get_bio
  squashfs: always use bio_kmalloc in squashfs_bio_read
  btrfs: simplify ->flush_bio handling
  block: allow use of per-cpu bio alloc cache by block drivers
  block: allow using the per-cpu bio cache from bio_alloc_bioset
  x86/boot: Add an efi.h header for the decompressor
  selinux: don't sleep when CONFIG_SECURITY_SELINUX_CHECKREQPROT_VALUE is true
  timekeeping: Introduce fast accessor to clock tai
  tracing/timer: Add missing argument documentation of trace points
  genirq: Take the proposed affinity at face value if force==true
  x86/asm: Merge load_gs_index()
  x86/32: Remove lazy GS macros
  ELF: Remove elf_core_copy_kernel_regs()
  virt: sevguest: Fix bool function returning negative value
  x86/process: Fix kernel-doc warning due to a changed function name
  fscrypt: log when starting to use inline encryption
  dt-bindings: ata: renesas,rcar-sata: Add r8a774e1 support
  fscrypt: split up FS_CRYPTO_BLOCK_SIZE
  lib/irq_poll: Prevent softirq pending leak in irq_poll_cpu_dead()
  cpu/hotplug: Initialise all cpuhp_cpu_state structs earlier
  cfi: Use __builtin_function_start
  security: don't treat structure as an array of struct hlist_head
  usercopy: Remove HARDENED_USERCOPY_PAGESPAN
  mm/usercopy: Detect large folio overruns
  mm/usercopy: Detect vmalloc overruns
  mm/usercopy: Check kmap addresses properly
  x86/crash: Fix minor typo/bug in debug message
  efi: Add missing prototype for efi_capsule_setup_info
  docs: security: Add secrets/coco documentation
  efi: Register efi_secret platform device if EFI secret area is declared
  virt: Add efi_secret module to expose confidential computing secrets
  efi: Save location of EFI confidential computing area
  efi: Allow to enable EFI runtime services by default on RT
  x86/apic: Clarify i82489DX bit overlap in APIC_LVT0
  platform/x86: amd-pmc: Avoid reading SMU version at probe time
  platform/x86: amd-pmc: Move FCH init to first use
  platform/x86: amd-pmc: Move SMU logging setup out of init
  platform/x86: hp-wmi: Correct code style related issues
  platform/x86: wmi: replace usage of found with dedicated list iterator variable
  platform/x86: winmate-fm07-keys: Winmate FM07/FM07P buttons
  ata: pata_via: fix sloppy typing in via_do_set_mode()
  ata: pata_sil680: fix result type of sil680_sel{dev|reg}()
  x86/32: Simplify ELF_CORE_COPY_REGS
  cpu/hotplug: Allow the CPU in CPU_UP_PREPARE state to be brought up again.
  x86/xen: Allow to retry if cpu_initialize_context() failed.
  ata: libata-core: fix parameter type in ata_xfer_mode2shift()
  rcu: Check for jiffies going backwards
  rcu: Fix rcu_preempt_deferred_qs_irqrestore() strict QS reporting
  rcu: Clarify fill-the-gap comment in rcu_segcblist_advance()
  tools/nolibc: guard the main file against multiple inclusion
  tools/nolibc: use pselect6 on RISCV
  torture: Make thread detection more robust by using lspcu
  torture: Permit running of experimental torture types
  torture: Use "-o Batchmode=yes" to disable ssh password requests
  torture: Reposition so that $? collects ssh code in torture.sh
  rcu: Make TASKS_RUDE_RCU select IRQ_WORK
  rcutorture: Call preempt_schedule() through static call/key
  rcutorture: Add missing return and use __func__ in warning
  rcutorture: Avoid corner-case #DE with nsynctypes check
  scftorture: Fix distribution of short handler delays
  rcutorture: Suppress debugging grace period delays during flooding
  torture: Add rcu_normal and rcu_expedited runs to torture.sh
  rcu-tasks: Handle sparse cpu_possible_mask in rcu_tasks_invoke_cbs()
  rcu-tasks: Handle sparse cpu_possible_mask
  rcu-tasks: Make show_rcu_tasks_generic_gp_kthread() check all CPUs
  rcu-tasks: Restore use of timers for non-RT kernels
  rcu-tasks: Use schedule_hrtimeout_range() to wait for grace periods
  rcu-tasks: Make Tasks RCU account for userspace execution
  rcu-tasks: Use rcuwait for the rcu_tasks_kthread()
  rcu-tasks: Print pre-stall-warning informational messages
  rcu-tasks: Fix race in schedule and flush work
  rcu/nocb: Initialize nocb kthreads only for boot CPU prior SMP initialization
  rcu: Initialize boost kthread only for boot node prior SMP initialization
  rcu: Assume rcu_init() is called before smp
  rcu/nocb: Move rcu_nocb_is_setup to rcu_state
  rcu: Remove rcu_is_nocb_cpu()
  srcu: Add contention-triggered addition of srcu_node tree
  srcu: Create concurrency-safe helper for initiating size transition
  srcu: Explain srcu_funnel_gp_start() call to list_add() is safe
  srcu: Prevent cleanup_srcu_struct() from freeing non-dynamic ->sda
  srcu: Avoid NULL dereference in srcu_torture_stats_print()
  srcu: Use export for srcu_struct defined by DEFINE_STATIC_SRCU()
  srcu: Add boot-time control over srcu_node array allocation
  srcu: Ensure snp nodes tree is fully initialized before traversal
  srcu: Use invalid initial value for srcu_node GP sequence numbers
  srcu: Compute snp_seq earlier in srcu_funnel_gp_start()
  srcu: Make rcutorture dump the SRCU size state
  srcu: Add size-state transitioning code
  srcu: Dynamically allocate srcu_node array
  srcu: Make Tree SRCU able to operate without snp_node array
  srcu: Make srcu_funnel_gp_start() cache ->mynode in snp_leaf
  srcu: Fix s/is/if/ typo in srcu_node comment
  srcu: Tighten cleanup_srcu_struct() GP checks
  x86: Remove a.out support
  virt: sevguest: Fix return value check in alloc_shared_pages()
  EDAC/mc: Get rid of edac_align_ptr()
  EDAC/device: Sanitize edac_device_alloc_ctl_info() definition
  m68k: Introduce a virtual m68k machine
  clocksource/drivers: Add a goldfish-timer clocksource
  rtc: goldfish: Use gf_ioread32()/gf_iowrite32()
  tty: goldfish: Introduce gf_ioread32()/gf_iowrite32()
  EDAC/device: Get rid of the silly one-shot memory allocation in edac_device_alloc_ctl_info()
  EDAC/pci: Get rid of the silly one-shot memory allocation in edac_pci_alloc_ctl_info()
  EDAC/mc: Get rid of silly one-shot struct allocation in edac_mc_alloc()
  x86/kaslr: Fix build warning in KASLR code in boot stub
  libata: Improve ATA queued command allocation
  ata: pata_mpc52xx: Prepare cleanup of powerpc's asm/prom.h
  x86/mm: Replace nodes_weight() with nodes_empty() where appropriate
  x86: Replace cpumask_weight() with cpumask_empty() where appropriate
  clocksource: Replace cpumask_weight() with cpumask_empty()
  irqchip/bmips: Replace cpumask_weight() with cpumask_empty()
  genirq/affinity: Replace cpumask_weight() with cpumask_empty() where appropriate
  irqchip/gic-v3: Always trust the managed affinity provided by the core code
  genirq: Always limit the affinity to online CPUs
  genirq/msi: Shutdown managed interrupts with unsatifiable affinities
  x86/PCI: Fix coding style in PIRQ table verification
  x86/PCI: Fix ALi M1487 (IBC) PIRQ router link value interpretation
  x86/PCI: Add $IRT PIRQ routing table support
  x86/PCI: Handle PIRQ routing tables with no router device given
  x86/PCI: Add PIRQ routing table range checks
  x86/PCI: Add support for the SiS85C497 PIRQ router
  x86/PCI: Disambiguate SiS85C503 PIRQ router code entities
  x86/PCI: Handle IRQ swizzling with PIRQ routers
  x86/PCI: Also match function number in $PIR table
  x86/PCI: Include function number in $PIR table dump
  x86/PCI: Show the physical address of the $PIR table
  timers: Move timer sysctl into the timer code
  clockevents: Use dedicated list iterator variable
  timers: Simplify calc_index()
  timers: Initialize base::next_expiry_recalc in timers_prepare_cpu()
  Documentation/x86: Document TDX kernel architecture
  efi/cper: Reformat CPER memory error location to more readable
  EDAC/ghes: Unify CPER memory error location reporting
  efi/cper: Add a cper_mem_err_status_str() to decode error description
  x86/sev-es: Replace open-coded hlt-loop with sev_es_terminate()
  csky: Fix versioncheck warnings
  ACPICA: Avoid cache flush inside virtual machines
  x86/tdx/ioapic: Add shared bit for IOAPIC base address
  x86/mm: Make DMA memory shared for TD guest
  x86/mm/cpa: Add support for TDX shared memory
  x86/tdx: Make pages shared in ioremap()
  x86/topology: Disable CPU online/offline control for TDX guests
  x86/boot: Avoid #VE during boot for TDX platforms
  x86/boot: Set CR0.NE early and keep it set during the boot
  x86/acpi/x86/boot: Add multiprocessor wake-up support
  x86/boot: Add a trampoline for booting APs via firmware handoff
  x86/tdx: Wire up KVM hypercalls
  x86/tdx: Port I/O: Add early boot support
  x86/tdx: Port I/O: Add runtime hypercalls
  x86/boot: Port I/O: Add decompression-time support for TDX
  x86/boot: Port I/O: Allow to hook up alternative helpers
  x86: Consolidate port I/O helpers
  x86: Adjust types used in port I/O helpers
  x86/tdx: Detect TDX at early kernel decompression time
  x86/tdx: Handle in-kernel MMIO
  x86/tdx: Handle CPUID via #VE
  x86/tdx: Add MSR support for TDX guests
  x86/tdx: Add HLT support for TDX guests
  x86/traps: Add #VE support for TDX guest
  x86/traps: Refactor exc_general_protection()
  x86/tdx: Exclude shared bit from __PHYSICAL_MASK
  x86/tdx: Extend the confidential computing API to support TDX guests
  x86/tdx: Add __tdx_module_call() and __tdx_hypercall() helper functions
  x86/tdx: Provide common base for SEAMCALL and TDCALL C wrappers
  x86/tdx: Detect running as a TDX guest in early boot
  x86/platform/uv: Log gap hole end size
  x86/platform/uv: Update TSC sync state for UV5
  x86/platform/uv: Update NMI Handler for UV5
  virt: sevguest: Add documentation for SEV-SNP CPUID Enforcement
  virt: sevguest: Add support to get extended report
  virt: sevguest: Add support to derive key
  virt: Add SEV-SNP guest driver
  x86/sev: Register SEV-SNP guest request platform device
  x86/sev: Provide support for SNP guest request NAEs
  x86/sev: Add a sev= cmdline option
  x86/sev: Use firmware-validated CPUID for SEV-SNP guests
  x86/sev: Add SEV-SNP feature detection/setup
  x86/compressed/64: Add identity mapping for Confidential Computing blob
  x86/compressed: Export and rename add_identity_map()
  x86/compressed: Use firmware-validated CPUID leaves for SEV-SNP guests
  x86/compressed: Add SEV-SNP feature detection/setup
  x86/boot: Add a pointer to Confidential Computing blob in bootparams
  x86/compressed/64: Add support for SEV-SNP CPUID table in #VC handlers
  x86/sev: Move MSR-based VMGEXITs for CPUID to helper
  KVM: x86: Move lookup of indexed CPUID leafs to helper
  x86/boot: Add Confidential Computing type to setup_data
  csky: patch_text: Fixup last cpu should be master
  x86/configs: Add x86 debugging Kconfig fragment plus docs
  x86/compressed/acpi: Move EFI kexec handling into common code
  x86/compressed/acpi: Move EFI vendor table lookup to helper
  x86/compressed/acpi: Move EFI config table lookup to helper
  x86/compressed/acpi: Move EFI system table lookup to helper
  x86/compressed/acpi: Move EFI detection to helper
  x86/head/64: Re-enable stack protection
  x86/sev: Use SEV-SNP AP creation to start secondary CPUs
  csky: fix typos in comments
  x86/mm: Validate memory when changing the C-bit
  x86/kernel: Validate ROM memory before accessing when SEV-SNP is active
  x86/kernel: Mark the .bss..decrypted section as shared in the RMP table
  x86/sev: Add helper for validating pages in early enc attribute changes
  x86/sev: Register GHCB memory when SEV-SNP is active
  x86/compressed: Register GHCB memory when SEV-SNP is active
  x86/compressed: Add helper for validating pages in the decompression stage
  x86/sev: Check the VMPL level
  x86/sev: Add a helper for the PVALIDATE instruction
  x86/sev: Check SEV-SNP features support
  x86/sev: Save the negotiated GHCB version
  x86/sev: Define the Linux-specific guest termination reasons
  x86/mm: Extend cc_attr to include AMD SEV-SNP
  x86/sev: Detect/setup SEV/SME features earlier in boot
  x86/compressed/64: Detect/setup SEV/SME features earlier during boot
  x86/boot: Use MSR read/write helpers instead of inline assembly
  x86/boot: Introduce helpers for MSR reads/writes
  KVM: SVM: Update the SEV-ES save area mapping
  KVM: SVM: Create a separate mapping for the GHCB save area
  KVM: SVM: Create a separate mapping for the SEV-ES save area
  powerpc/85xx: Remove fsl,85... bindings
  x86/speculation/srbds: Do not try to turn mitigation off when not supported
  x86/MCE/AMD: Fix memory leak when threshold_create_bank() fails
  x86/mce: Avoid unnecessary padding in struct mce_bank
  x86/delay: Fix the wrong asm constraint in delay_loop()
  x86/amd_nb: Unexport amd_cache_northbridges()
  KVM: SVM: Define sev_features and VMPL field in the VMSA
  ftrace: Use preemption model accessors for trace header printout
  preempt/dynamic: Introduce preemption model accessors
  kcsan: Use preemption model accessors
  perf/x86: Unify format of events sysfs show
  perf/x86/amd: Add idle hooks for branch sampling
  ACPI: Add perf low power callback
  perf/x86/amd: Make Zen3 branch sampling opt-in
  perf/x86/amd: Add AMD branch sampling period adjustment
  perf/x86/amd: Enable branch sampling priv level filtering
  perf/x86/amd: Add branch-brs helper event for Fam19h BRS
  perf/x86/amd: Add AMD Fam19h Branch Sampling support
  locking/mutex: Make contention tracepoints more consistent wrt adaptive spinning
  x86/cpufeatures: Add AMD Fam19h Branch Sampling feature
  perf/core: Add perf_clear_branch_entry_bitfields() helper
  locking: Apply contention tracepoints in the slow path
  locking: Add lock contention tracepoints
  locking/rwsem: Always try to wake waiters in out_nolock path
  locking/rwsem: Conditionally wake waiters in reader/writer slowpaths
  locking/rwsem: No need to check for handoff bit if wait queue empty
  lockdep: Fix -Wunused-parameter for _THIS_IP_
  x86/pkeys: Remove __arch_set_user_pkey_access() declaration
  x86/pkeys: Clean up arch_set_user_pkey_access() declaration
  selinux: checkreqprot is deprecated, add some ssleep() discomfort
  selinux: runtime disable is deprecated, add some ssleep() discomfort
  selinux: Remove redundant assignments
  x86/fault: Cast an argument to the proper address space in prefetch()
  x86/cpu: Remove "noclflush"
  x86/cpu: Remove "noexec"
  x86/cpu: Remove "nosmep"
  x86/cpu: Remove CONFIG_X86_SMAP and "nosmap"
  x86/cpu: Remove "nosep"
  x86/cpu: Allow feature bit names from /proc/cpuinfo in clearcpuid=
  x86/mm: Force-inline __phys_addr_nodebug()
  x86/kvm/svm: Force-inline GHCB accessors
  task_stack, x86/cea: Force-inline stack helpers

Bug: 168730134
Bug: 169238689
Bug: 178758017
Bug: 180471389
Bug: 190019968
Bug: 190353898
Bug: 195914333
Bug: 207739506
Bug: 232293973
Bug: 234125788
Change-Id: I3c4e724344271459105a863d12d3a8f96c7373dd
Signed-off-by: jianzhou <quic_jianzhou@quicinc.com>
Signed-off-by: Blagovest Kolenichev <quic_c_bkolen@quicinc.com>

.mailmap

@@ -398,6 +398,7 @@ Vasily Averin <vasily.averin@linux.dev> <vvs@virtuozzo.com>
 Vasily Averin <vasily.averin@linux.dev> <vvs@openvz.org>
 Vasily Averin <vasily.averin@linux.dev> <vvs@parallels.com>
 Vasily Averin <vasily.averin@linux.dev> <vvs@sw.ru>
+Valentin Schneider <vschneid@redhat.com> <valentin.schneider@arm.com>
 Vinod Koul <vkoul@kernel.org> <vinod.koul@intel.com>
 Vinod Koul <vkoul@kernel.org> <vinod.koul@linux.intel.com>
 Vinod Koul <vkoul@kernel.org> <vkoul@infradead.org>

Documentation/ABI/stable/sysfs-driver-mlxreg-io

@@ -467,3 +467,39 @@ Description:	These files provide the maximum powered required for line card
 		feeding and line card configuration Id.
 
 		The files are read only.
+
+What:		/sys/devices/platform/mlxplat/mlxreg-io/hwmon/hwmon*/phy_reset
+Date:		May 2022
+KernelVersion:	5.19
+Contact:	Vadim Pasternak <vadimpmellanox.com>
+Description:	This file allows to reset PHY 88E1548 when attribute is set 0
+		due to some abnormal PHY behavior.
+		Expected behavior:
+		When phy_reset is written 1, all PHY 88E1548 are released
+		from the reset state, when 0 - are hold in reset state.
+
+		The files are read/write.
+
+What:		/sys/devices/platform/mlxplat/mlxreg-io/hwmon/hwmon*/mac_reset
+Date:		May 2022
+KernelVersion:	5.19
+Contact:	Vadim Pasternak <vadimpmellanox.com>
+Description:	This file allows to reset ASIC MT52132 when attribute is set 0
+		due to some abnormal ASIC behavior.
+		Expected behavior:
+		When mac_reset is written 1, the ASIC MT52132 is released
+		from the reset state, when 0 - is hold in reset state.
+
+		The files are read/write.
+
+What:		/sys/devices/platform/mlxplat/mlxreg-io/hwmon/hwmon*/qsfp_pwr_good
+Date:		May 2022
+KernelVersion:	5.19
+Contact:	Vadim Pasternak <vadimpmellanox.com>
+Description:	This file shows QSFP ports power status. The value is set to 0
+		when one of any QSFP ports is plugged. The value is set to 1 when
+		there are no any QSFP ports are plugged.
+		The possible values are:
+		0 - Power good, 1 - Not power good.
+
+		The files are read only.

Documentation/ABI/testing/securityfs-secrets-coco

@@ -0,0 +1,51 @@
+What:		security/secrets/coco
+Date:		February 2022
+Contact:	Dov Murik <dovmurik@linux.ibm.com>
+Description:
+		Exposes confidential computing (coco) EFI secrets to
+		userspace via securityfs.
+
+		EFI can declare memory area used by confidential computing
+		platforms (such as AMD SEV and SEV-ES) for secret injection by
+		the Guest Owner during VM's launch.  The secrets are encrypted
+		by the Guest Owner and decrypted inside the trusted enclave,
+		and therefore are not readable by the untrusted host.
+
+		The efi_secret module exposes the secrets to userspace.  Each
+		secret appears as a file under <securityfs>/secrets/coco,
+		where the filename is the GUID of the entry in the secrets
+		table.  This module is loaded automatically by the EFI driver
+		if the EFI secret area is populated.
+
+		Two operations are supported for the files: read and unlink.
+		Reading the file returns the content of secret entry.
+		Unlinking the file overwrites the secret data with zeroes and
+		removes the entry from the filesystem.  A secret cannot be read
+		after it has been unlinked.
+
+		For example, listing the available secrets::
+
+		  # modprobe efi_secret
+		  # ls -l /sys/kernel/security/secrets/coco
+		  -r--r----- 1 root root 0 Jun 28 11:54 736870e5-84f0-4973-92ec-06879ce3da0b
+		  -r--r----- 1 root root 0 Jun 28 11:54 83c83f7f-1356-4975-8b7e-d3a0b54312c6
+		  -r--r----- 1 root root 0 Jun 28 11:54 9553f55d-3da2-43ee-ab5d-ff17f78864d2
+		  -r--r----- 1 root root 0 Jun 28 11:54 e6f5a162-d67f-4750-a67c-5d065f2a9910
+
+		Reading the secret data by reading a file::
+
+		  # cat /sys/kernel/security/secrets/coco/e6f5a162-d67f-4750-a67c-5d065f2a9910
+		  the-content-of-the-secret-data
+
+		Wiping a secret by unlinking a file::
+
+		  # rm /sys/kernel/security/secrets/coco/e6f5a162-d67f-4750-a67c-5d065f2a9910
+		  # ls -l /sys/kernel/security/secrets/coco
+		  -r--r----- 1 root root 0 Jun 28 11:54 736870e5-84f0-4973-92ec-06879ce3da0b
+		  -r--r----- 1 root root 0 Jun 28 11:54 83c83f7f-1356-4975-8b7e-d3a0b54312c6
+		  -r--r----- 1 root root 0 Jun 28 11:54 9553f55d-3da2-43ee-ab5d-ff17f78864d2
+
+		Note: The binary format of the secrets table injected by the
+		Guest Owner is described in
+		drivers/virt/coco/efi_secret/efi_secret.c under "Structure of
+		the EFI secret area".

Documentation/ABI/testing/sysfs-driver-xen-blkback

@@ -29,7 +29,7 @@ Description:
 What:           /sys/module/xen_blkback/parameters/buffer_squeeze_duration_ms
 Date:           December 2019
 KernelVersion:  5.6
-Contact:        SeongJae Park <sj@kernel.org>
+Contact:        Maximilian Heyne <mheyne@amazon.de>
 Description:
                 When memory pressure is reported to blkback this option
                 controls the duration in milliseconds that blkback will not
@@ -39,7 +39,7 @@ Description:
 What:           /sys/module/xen_blkback/parameters/feature_persistent
 Date:           September 2020
 KernelVersion:  5.10
-Contact:        SeongJae Park <sj@kernel.org>
+Contact:        Maximilian Heyne <mheyne@amazon.de>
 Description:
                 Whether to enable the persistent grants feature or not.  Note
                 that this option only takes effect on newly created backends.

Documentation/ABI/testing/sysfs-driver-xen-blkfront

@@ -12,7 +12,7 @@ Description:
 What:           /sys/module/xen_blkfront/parameters/feature_persistent
 Date:           September 2020
 KernelVersion:  5.10
-Contact:        SeongJae Park <sj@kernel.org>
+Contact:        Maximilian Heyne <mheyne@amazon.de>
 Description:
                 Whether to enable the persistent grants feature or not.  Note
                 that this option only takes effect on newly created frontends.

Documentation/ABI/testing/sysfs-platform-intel-ifs

@@ -0,0 +1,39 @@
+What:		/sys/devices/virtual/misc/intel_ifs_<N>/run_test
+Date:		April 21 2022
+KernelVersion:	5.19
+Contact:	"Jithu Joseph" <jithu.joseph@intel.com>
+Description:	Write <cpu#> to trigger IFS test for one online core.
+		Note that the test is per core. The cpu# can be
+		for any thread on the core. Running on one thread
+		completes the test for the core containing that thread.
+		Example: to test the core containing cpu5: echo 5 >
+		/sys/devices/platform/intel_ifs.<N>/run_test
+
+What:		/sys/devices/virtual/misc/intel_ifs_<N>/status
+Date:		April 21 2022
+KernelVersion:	5.19
+Contact:	"Jithu Joseph" <jithu.joseph@intel.com>
+Description:	The status of the last test. It can be one of "pass", "fail"
+		or "untested".
+
+What:		/sys/devices/virtual/misc/intel_ifs_<N>/details
+Date:		April 21 2022
+KernelVersion:	5.19
+Contact:	"Jithu Joseph" <jithu.joseph@intel.com>
+Description:	Additional information regarding the last test. The details file reports
+		the hex value of the SCAN_STATUS MSR. Note that the error_code field
+		may contain driver defined software code not defined in the Intel SDM.
+
+What:		/sys/devices/virtual/misc/intel_ifs_<N>/image_version
+Date:		April 21 2022
+KernelVersion:	5.19
+Contact:	"Jithu Joseph" <jithu.joseph@intel.com>
+Description:	Version (hexadecimal) of loaded IFS binary image. If no scan image
+		is loaded reports "none".
+
+What:		/sys/devices/virtual/misc/intel_ifs_<N>/reload
+Date:		April 21 2022
+KernelVersion:	5.19
+Contact:	"Jithu Joseph" <jithu.joseph@intel.com>
+Description:	Write "1" (or "y" or "Y") to reload the IFS image from
+		/lib/firmware/intel/ifs/ff-mm-ss.scan.

Documentation/RCU/Design/Data-Structures/Data-Structures.rst

@@ -973,7 +973,7 @@ The ``->dynticks`` field counts the corresponding CPU's transitions to
 and from either dyntick-idle or user mode, so that this counter has an
 even value when the CPU is in dyntick-idle mode or user mode and an odd
 value otherwise. The transitions to/from user mode need to be counted
-for user mode adaptive-ticks support (see timers/NO_HZ.txt).
+for user mode adaptive-ticks support (see Documentation/timers/no_hz.rst).
 
 The ``->rcu_need_heavy_qs`` field is used to record the fact that the
 RCU core code would really like to see a quiescent state from the

Documentation/RCU/Design/Expedited-Grace-Periods/Expedited-Grace-Periods.rst

@@ -406,7 +406,7 @@ In earlier implementations, the task requesting the expedited grace
 period also drove it to completion. This straightforward approach had
 the disadvantage of needing to account for POSIX signals sent to user
 tasks, so more recent implemementations use the Linux kernel's
-`workqueues <https://www.kernel.org/doc/Documentation/core-api/workqueue.rst>`__.
+workqueues (see Documentation/core-api/workqueue.rst).
 
 The requesting task still does counter snapshotting and funnel-lock
 processing, but the task reaching the top of the funnel lock does a

Documentation/RCU/Design/Requirements/Requirements.rst

@@ -370,8 +370,8 @@ pointer fetched by rcu_dereference() may not be used outside of the
 outermost RCU read-side critical section containing that
 rcu_dereference(), unless protection of the corresponding data
 element has been passed from RCU to some other synchronization
-mechanism, most commonly locking or `reference
-counting <https://www.kernel.org/doc/Documentation/RCU/rcuref.txt>`__.
+mechanism, most commonly locking or reference counting
+(see ../../rcuref.rst).
 
 .. |high-quality implementation of C11 memory_order_consume [PDF]| replace:: high-quality implementation of C11 ``memory_order_consume`` [PDF]
 .. _high-quality implementation of C11 memory_order_consume [PDF]: http://www.rdrop.com/users/paulmck/RCU/consume.2015.07.13a.pdf
@@ -2654,6 +2654,38 @@ synchronize_rcu(), and rcu_barrier(), respectively. In
 three APIs are therefore implemented by separate functions that check
 for voluntary context switches.
 
+Tasks Rude RCU
+~~~~~~~~~~~~~~
+
+Some forms of tracing need to wait for all preemption-disabled regions
+of code running on any online CPU, including those executed when RCU is
+not watching.  This means that synchronize_rcu() is insufficient, and
+Tasks Rude RCU must be used instead.  This flavor of RCU does its work by
+forcing a workqueue to be scheduled on each online CPU, hence the "Rude"
+moniker.  And this operation is considered to be quite rude by real-time
+workloads that don't want their ``nohz_full`` CPUs receiving IPIs and
+by battery-powered systems that don't want their idle CPUs to be awakened.
+
+The tasks-rude-RCU API is also reader-marking-free and thus quite compact,
+consisting of call_rcu_tasks_rude(), synchronize_rcu_tasks_rude(),
+and rcu_barrier_tasks_rude().
+
+Tasks Trace RCU
+~~~~~~~~~~~~~~~
+
+Some forms of tracing need to sleep in readers, but cannot tolerate
+SRCU's read-side overhead, which includes a full memory barrier in both
+srcu_read_lock() and srcu_read_unlock().  This need is handled by a
+Tasks Trace RCU that uses scheduler locking and IPIs to synchronize with
+readers.  Real-time systems that cannot tolerate IPIs may build their
+kernels with ``CONFIG_TASKS_TRACE_RCU_READ_MB=y``, which avoids the IPIs at
+the expense of adding full memory barriers to the read-side primitives.
+
+The tasks-trace-RCU API is also reasonably compact,
+consisting of rcu_read_lock_trace(), rcu_read_unlock_trace(),
+rcu_read_lock_trace_held(), call_rcu_tasks_trace(),
+synchronize_rcu_tasks_trace(), and rcu_barrier_tasks_trace().
+
 Possible Future Changes
 -----------------------
 

Documentation/RCU/arrayRCU.rst

@@ -33,8 +33,8 @@ Situation 1: Hash Tables
 
 Hash tables are often implemented as an array, where each array entry
 has a linked-list hash chain.  Each hash chain can be protected by RCU
-as described in the listRCU.txt document.  This approach also applies
-to other array-of-list situations, such as radix trees.
+as described in listRCU.rst.  This approach also applies to other
+array-of-list situations, such as radix trees.
 
 .. _static_arrays:
 

Documentation/RCU/checklist.rst

@@ -140,8 +140,7 @@ over a rather long period of time, but improvements are always welcome!
 		prevents destructive compiler optimizations.  However,
 		with a bit of devious creativity, it is possible to
 		mishandle the return value from rcu_dereference().
-		Please see rcu_dereference.txt in this directory for
-		more information.
+		Please see rcu_dereference.rst for more information.
 
 		The rcu_dereference() primitive is used by the
 		various "_rcu()" list-traversal primitives, such
@@ -151,7 +150,7 @@ over a rather long period of time, but improvements are always welcome!
 		primitives.  This is particularly useful in code that
 		is common to readers and updaters.  However, lockdep
 		will complain if you access rcu_dereference() outside
-		of an RCU read-side critical section.  See lockdep.txt
+		of an RCU read-side critical section.  See lockdep.rst
 		to learn what to do about this.
 
 		Of course, neither rcu_dereference() nor the "_rcu()"
@@ -323,7 +322,7 @@ over a rather long period of time, but improvements are always welcome!
 	primitives when the update-side lock is held is that doing so
 	can be quite helpful in reducing code bloat when common code is
 	shared between readers and updaters.  Additional primitives
-	are provided for this case, as discussed in lockdep.txt.
+	are provided for this case, as discussed in lockdep.rst.
 
 	One exception to this rule is when data is only ever added to
 	the linked data structure, and is never removed during any
@@ -480,4 +479,4 @@ over a rather long period of time, but improvements are always welcome!
 	both rcu_barrier() and synchronize_rcu(), if necessary, using
 	something like workqueues to to execute them concurrently.
 
-	See rcubarrier.txt for more information.
+	See rcubarrier.rst for more information.

Documentation/RCU/rcu.rst

@@ -10,9 +10,8 @@ A "grace period" must elapse between the two parts, and this grace period
 must be long enough that any readers accessing the item being deleted have
 since dropped their references.  For example, an RCU-protected deletion
 from a linked list would first remove the item from the list, wait for
-a grace period to elapse, then free the element.  See the
-:ref:`Documentation/RCU/listRCU.rst <list_rcu_doc>` for more information on
-using RCU with linked lists.
+a grace period to elapse, then free the element.  See listRCU.rst for more
+information on using RCU with linked lists.
 
 Frequently Asked Questions
 --------------------------
@@ -50,7 +49,7 @@ Frequently Asked Questions
 - If I am running on a uniprocessor kernel, which can only do one
   thing at a time, why should I wait for a grace period?
 
-  See :ref:`Documentation/RCU/UP.rst <up_doc>` for more information.
+  See UP.rst for more information.
 
 - How can I see where RCU is currently used in the Linux kernel?
 
@@ -64,13 +63,13 @@ Frequently Asked Questions
 
 - What guidelines should I follow when writing code that uses RCU?
 
-  See the checklist.txt file in this directory.
+  See checklist.rst.
 
 - Why the name "RCU"?
 
   "RCU" stands for "read-copy update".
-  :ref:`Documentation/RCU/listRCU.rst <list_rcu_doc>` has more information on where
-  this name came from, search for "read-copy update" to find it.
+  listRCU.rst has more information on where this name came from, search
+  for "read-copy update" to find it.
 
 - I hear that RCU is patented?  What is with that?
 

Documentation/RCU/rculist_nulls.rst

@@ -8,7 +8,7 @@ This section describes how to use hlist_nulls to
 protect read-mostly linked lists and
 objects using SLAB_TYPESAFE_BY_RCU allocations.
 
-Please read the basics in Documentation/RCU/listRCU.rst
+Please read the basics in listRCU.rst.
 
 Using 'nulls'
 =============

Documentation/RCU/stallwarn.rst

@@ -162,6 +162,26 @@ CONFIG_RCU_CPU_STALL_TIMEOUT
 	Stall-warning messages may be enabled and disabled completely via
 	/sys/module/rcupdate/parameters/rcu_cpu_stall_suppress.
 
+CONFIG_RCU_EXP_CPU_STALL_TIMEOUT
+--------------------------------
+
+	Same as the CONFIG_RCU_CPU_STALL_TIMEOUT parameter but only for
+	the expedited grace period. This parameter defines the period
+	of time that RCU will wait from the beginning of an expedited
+	grace period until it issues an RCU CPU stall warning. This time
+	period is normally 20 milliseconds on Android devices.	A zero
+	value causes the CONFIG_RCU_CPU_STALL_TIMEOUT value to be used,
+	after conversion to milliseconds.
+
+	This configuration parameter may be changed at runtime via the
+	/sys/module/rcupdate/parameters/rcu_exp_cpu_stall_timeout, however
+	this parameter is checked only at the beginning of a cycle. If you
+	are in a current stall cycle, setting it to a new value will change
+	the timeout for the -next- stall.
+
+	Stall-warning messages may be enabled and disabled completely via
+	/sys/module/rcupdate/parameters/rcu_cpu_stall_suppress.
+
 RCU_STALL_DELAY_DELTA
 ---------------------
 

Documentation/RCU/whatisRCU.rst

@@ -224,7 +224,7 @@ synchronize_rcu()
 	be delayed.  This property results in system resilience in face
 	of denial-of-service attacks.  Code using call_rcu() should limit
 	update rate in order to gain this same sort of resilience.  See
-	checklist.txt for some approaches to limiting the update rate.
+	checklist.rst for some approaches to limiting the update rate.
 
 rcu_assign_pointer()
 ^^^^^^^^^^^^^^^^^^^^
@@ -318,7 +318,7 @@ rcu_dereference()
 	must prohibit.	The rcu_dereference_protected() variant takes
 	a lockdep expression to indicate which locks must be acquired
 	by the caller. If the indicated protection is not provided,
-	a lockdep splat is emitted.  See Documentation/RCU/Design/Requirements/Requirements.rst
+	a lockdep splat is emitted.  See Design/Requirements/Requirements.rst
 	and the API's code comments for more details and example usage.
 
 .. 	[2] If the list_for_each_entry_rcu() instance might be used by
@@ -399,8 +399,7 @@ for specialized uses, but are relatively uncommon.
 
 This section shows a simple use of the core RCU API to protect a
 global pointer to a dynamically allocated structure.  More-typical
-uses of RCU may be found in :ref:`listRCU.rst <list_rcu_doc>`,
-:ref:`arrayRCU.rst <array_rcu_doc>`, and :ref:`NMI-RCU.rst <NMI_rcu_doc>`.
+uses of RCU may be found in listRCU.rst, arrayRCU.rst, and NMI-RCU.rst.
 ::
 
 	struct foo {
@@ -482,10 +481,9 @@ So, to sum up:
 	RCU read-side critical sections that might be referencing that
 	data item.
 
-See checklist.txt for additional rules to follow when using RCU.
-And again, more-typical uses of RCU may be found in :ref:`listRCU.rst
-<list_rcu_doc>`, :ref:`arrayRCU.rst <array_rcu_doc>`, and :ref:`NMI-RCU.rst
-<NMI_rcu_doc>`.
+See checklist.rst for additional rules to follow when using RCU.
+And again, more-typical uses of RCU may be found in listRCU.rst,
+arrayRCU.rst, and NMI-RCU.rst.
 
 .. _4_whatisRCU:
 
@@ -579,7 +577,7 @@ to avoid having to write your own callback::
 
 	kfree_rcu(old_fp, rcu);
 
-Again, see checklist.txt for additional rules governing the use of RCU.
+Again, see checklist.rst for additional rules governing the use of RCU.
 
 .. _5_whatisRCU:
 
@@ -663,7 +661,7 @@ been able to write-acquire the lock otherwise.  The smp_mb__after_spinlock()
 promotes synchronize_rcu() to a full memory barrier in compliance with
 the "Memory-Barrier Guarantees" listed in:
 
-	Documentation/RCU/Design/Requirements/Requirements.rst
+	Design/Requirements/Requirements.rst
 
 It is possible to nest rcu_read_lock(), since reader-writer locks may
 be recursively acquired.  Note also that rcu_read_lock() is immune

Documentation/accounting/psi.rst

@@ -37,11 +37,7 @@ Pressure interface
 Pressure information for each resource is exported through the
 respective file in /proc/pressure/ -- cpu, memory, and io.
 
-The format for CPU is as such::
-
-	some avg10=0.00 avg60=0.00 avg300=0.00 total=0
-
-and for memory and IO::
+The format is as such::
 
 	some avg10=0.00 avg60=0.00 avg300=0.00 total=0
 	full avg10=0.00 avg60=0.00 avg300=0.00 total=0
@@ -58,6 +54,9 @@ situation from a state where some tasks are stalled but the CPU is
 still doing productive work. As such, time spent in this subset of the
 stall state is tracked separately and exported in the "full" averages.
 
+CPU full is undefined at the system level, but has been reported
+since 5.13, so it is set to zero for backward compatibility.
+
 The ratios (in %) are tracked as recent trends over ten, sixty, and
 three hundred second windows, which gives insight into short term events
 as well as medium and long term trends. The total absolute stall time

Documentation/admin-guide/kernel-parameters.txt

@@ -631,12 +631,17 @@
 			Defaults to zero when built as a module and to
 			10 seconds when built into the kernel.
 
-	clearcpuid=BITNUM[,BITNUM...] [X86]
+	clearcpuid=X[,X...] [X86]
 			Disable CPUID feature X for the kernel. See
 			arch/x86/include/asm/cpufeatures.h for the valid bit
-			numbers. Note the Linux specific bits are not necessarily
-			stable over kernel options, but the vendor specific
+			numbers X. Note the Linux-specific bits are not necessarily
+			stable over kernel options, but the vendor-specific
 			ones should be.
+			X can also be a string as appearing in the flags: line
+			in /proc/cpuinfo which does not have the above
+			instability issue. However, not all features have names
+			in /proc/cpuinfo.
+			Note that using this option will taint your kernel.
 			Also note that user programs calling CPUID directly
 			or using the feature without checking anything
 			will still see it. This just prevents it from
@@ -808,7 +813,7 @@
 			Documentation/admin-guide/kdump/kdump.rst for an example.
 
 	crashkernel=size[KMG],high
-			[KNL, X86-64] range could be above 4G. Allow kernel
+			[KNL, X86-64, ARM64] range could be above 4G. Allow kernel
 			to allocate physical memory region from top, so could
 			be above 4G if system have more than 4G ram installed.
 			Otherwise memory region will be allocated below 4G, if
@@ -821,14 +826,20 @@
 			that require some amount of low memory, e.g. swiotlb
 			requires at least 64M+32K low memory, also enough extra
 			low memory is needed to make sure DMA buffers for 32-bit
-			devices won't run out. Kernel would try to allocate at
+			devices won't run out. Kernel would try to allocate
 			at least 256M below 4G automatically.
-			This one let user to specify own low range under 4G
+			This one lets the user specify own low range under 4G
 			for second kernel instead.
 			0: to disable low allocation.
 			It will be ignored when crashkernel=X,high is not used
 			or memory reserved is below 4G.
 
+			[KNL, ARM64] range in low memory.
+			This one lets the user specify a low range in the
+			DMA zone for the crash dump kernel.
+			It will be ignored when crashkernel=X,high is not used
+			or memory reserved is located in the DMA zones.
+
 	cryptomgr.notests
 			[KNL] Disable crypto self-tests
 
@@ -2630,14 +2641,14 @@
 			when set.
 			Format: <int>
 
-	libata.force=	[LIBATA] Force configurations.  The format is comma-
-			separated list of "[ID:]VAL" where ID is
-			PORT[.DEVICE].  PORT and DEVICE are decimal numbers
-			matching port, link or device.  Basically, it matches
-			the ATA ID string printed on console by libata.  If
-			the whole ID part is omitted, the last PORT and DEVICE
-			values are used.  If ID hasn't been specified yet, the
-			configuration applies to all ports, links and devices.
+	libata.force=	[LIBATA] Force configurations.  The format is a comma-
+			separated list of "[ID:]VAL" where ID is PORT[.DEVICE].
+			PORT and DEVICE are decimal numbers matching port, link
+			or device.  Basically, it matches the ATA ID string
+			printed on console by libata.  If the whole ID part is
+			omitted, the last PORT and DEVICE values are used.  If
+			ID hasn't been specified yet, the configuration applies
+			to all ports, links and devices.
 
 			If only DEVICE is omitted, the parameter applies to
 			the port and all links and devices behind it.  DEVICE
@@ -2647,7 +2658,7 @@
 			host link and device attached to it.
 
 			The VAL specifies the configuration to force.  As long
-			as there's no ambiguity shortcut notation is allowed.
+			as there is no ambiguity, shortcut notation is allowed.
 			For example, both 1.5 and 1.5G would work for 1.5Gbps.
 			The following configurations can be forced.
 
@@ -2660,19 +2671,58 @@
 			  udma[/][16,25,33,44,66,100,133] notation is also
 			  allowed.
 
+			* nohrst, nosrst, norst: suppress hard, soft and both
+			  resets.
+
+			* rstonce: only attempt one reset during hot-unplug
+			  link recovery.
+
+			* [no]dbdelay: Enable or disable the extra 200ms delay
+			  before debouncing a link PHY and device presence
+			  detection.
+
 			* [no]ncq: Turn on or off NCQ.
 
-			* [no]ncqtrim: Turn off queued DSM TRIM.
+			* [no]ncqtrim: Enable or disable queued DSM TRIM.
 
-			* nohrst, nosrst, norst: suppress hard, soft
-			  and both resets.
+			* [no]ncqati: Enable or disable NCQ trim on ATI chipset.
 
-			* rstonce: only attempt one reset during
-			  hot-unplug link recovery
+			* [no]trim: Enable or disable (unqueued) TRIM.
 
-			* dump_id: dump IDENTIFY data.
+			* trim_zero: Indicate that TRIM command zeroes data.
 
-			* atapi_dmadir: Enable ATAPI DMADIR bridge support
+			* max_trim_128m: Set 128M maximum trim size limit.
+
+			* [no]dma: Turn on or off DMA transfers.
+
+			* atapi_dmadir: Enable ATAPI DMADIR bridge support.
+
+			* atapi_mod16_dma: Enable the use of ATAPI DMA for
+			  commands that are not a multiple of 16 bytes.
+
+			* [no]dmalog: Enable or disable the use of the
+			  READ LOG DMA EXT command to access logs.
+
+			* [no]iddevlog: Enable or disable access to the
+			  identify device data log.
+
+			* [no]logdir: Enable or disable access to the general
+			  purpose log directory.
+
+			* max_sec_128: Set transfer size limit to 128 sectors.
+
+			* max_sec_1024: Set or clear transfer size limit to
+			  1024 sectors.
+
+			* max_sec_lba48: Set or clear transfer size limit to
+			  65535 sectors.
+
+			* [no]lpm: Enable or disable link power management.
+
+			* [no]setxfer: Indicate if transfer speed mode setting
+			  should be skipped.
+
+			* dump_id: Dump IDENTIFY data.
 
 			* disable: Disable this device.
 
@@ -3111,6 +3161,7 @@
 					       mds=off [X86]
 					       tsx_async_abort=off [X86]
 					       kvm.nx_huge_pages=off [X86]
+					       srbds=off [X86,INTEL]
 					       no_entry_flush [PPC]
 					       no_uaccess_flush [PPC]
 
@@ -3447,8 +3498,6 @@
 
 	nocache		[ARM]
 
-	noclflush	[BUGS=X86] Don't use the CLFLUSH instruction
-
 	delayacct	[KNL] Enable per-task delay accounting
 
 	nodsp		[SH] Disable hardware DSP at boot time.
@@ -3459,16 +3508,11 @@
 
 	noexec		[IA-64]
 
-	noexec		[X86]
-			On X86-32 available only on PAE configured kernels.
-			noexec=on: enable non-executable mappings (default)
-			noexec=off: disable non-executable mappings
-
-	nosmap		[X86,PPC]
+	nosmap		[PPC]
 			Disable SMAP (Supervisor Mode Access Prevention)
 			even if it is supported by processor.
 
-	nosmep		[X86,PPC64s]
+	nosmep		[PPC64s]
 			Disable SMEP (Supervisor Mode Execution Prevention)
 			even if it is supported by processor.
 
@@ -3668,8 +3712,6 @@
 
 	nosbagart	[IA-64]
 
-	nosep		[BUGS=X86-32] Disables x86 SYSENTER/SYSEXIT support.
-
 	nosgx		[X86-64,SGX] Disables Intel SGX kernel support.
 
 	nosmp		[SMP] Tells an SMP kernel to act as a UP kernel,
@@ -4901,6 +4943,18 @@
 
 	rcupdate.rcu_cpu_stall_timeout= [KNL]
 			Set timeout for RCU CPU stall warning messages.
+			The value is in seconds and the maximum allowed
+			value is 300 seconds.
+
+	rcupdate.rcu_exp_cpu_stall_timeout= [KNL]
+			Set timeout for expedited RCU CPU stall warning
+			messages.  The value is in milliseconds
+			and the maximum allowed value is 21000
+			milliseconds. Please note that this value is
+			adjusted to an arch timer tick resolution.
+			Setting this to zero causes the value from
+			rcupdate.rcu_cpu_stall_timeout to be used (after
+			conversion from seconds to milliseconds).
 
 	rcupdate.rcu_expedited= [KNL]
 			Use expedited grace-period primitives, for
@@ -4963,10 +5017,34 @@
 			number avoids disturbing real-time workloads,
 			but lengthens grace periods.
 
+	rcupdate.rcu_task_stall_info= [KNL]
+			Set initial timeout in jiffies for RCU task stall
+			informational messages, which give some indication
+			of the problem for those not patient enough to
+			wait for ten minutes.  Informational messages are
+			only printed prior to the stall-warning message
+			for a given grace period. Disable with a value
+			less than or equal to zero.  Defaults to ten
+			seconds.  A change in value does not take effect
+			until the beginning of the next grace period.
+
+	rcupdate.rcu_task_stall_info_mult= [KNL]
+			Multiplier for time interval between successive
+			RCU task stall informational messages for a given
+			RCU tasks grace period.  This value is clamped
+			to one through ten, inclusive.	It defaults to
+			the value three, so that the first informational
+			message is printed 10 seconds into the grace
+			period, the second at 40 seconds, the third at
+			160 seconds, and then the stall warning at 600
+			seconds would prevent a fourth at 640 seconds.
+
 	rcupdate.rcu_task_stall_timeout= [KNL]
-			Set timeout in jiffies for RCU task stall warning
-			messages.  Disable with a value less than or equal
-			to zero.
+			Set timeout in jiffies for RCU task stall
+			warning messages.  Disable with a value less
+			than or equal to zero.	Defaults to ten minutes.
+			A change in value does not take effect until
+			the beginning of the next grace period.
 
 	rcupdate.rcu_self_test= [KNL]
 			Run the RCU early boot self tests
@@ -5316,6 +5394,8 @@
 
 	serialnumber	[BUGS=X86-32]
 
+	sev=option[,option...] [X86-64] See Documentation/x86/x86_64/boot-options.rst
+
 	shapers=	[NET]
 			Maximal number of shapers.
 
@@ -5385,6 +5465,17 @@
 	smart2=		[HW]
 			Format: <io1>[,<io2>[,...,<io8>]]
 
+	smp.csd_lock_timeout= [KNL]
+			Specify the period of time in milliseconds
+			that smp_call_function() and friends will wait
+			for a CPU to release the CSD lock.  This is
+			useful when diagnosing bugs involving CPUs
+			disabling interrupts for extended periods
+			of time.  Defaults to 5,000 milliseconds, and
+			setting a value of zero disables this feature.
+			This feature may be more efficiently disabled
+			using the csdlock_debug- kernel parameter.
+
 	smsc-ircc2.nopnp	[HW] Don't use PNP to discover SMC devices
 	smsc-ircc2.ircc_cfg=	[HW] Device configuration I/O port
 	smsc-ircc2.ircc_sir=	[HW] SIR base I/O port
@@ -5616,6 +5707,30 @@
 			off:    Disable mitigation and remove
 				performance impact to RDRAND and RDSEED
 
+	srcutree.big_cpu_lim [KNL]
+			Specifies the number of CPUs constituting a
+			large system, such that srcu_struct structures
+			should immediately allocate an srcu_node array.
+			This kernel-boot parameter defaults to 128,
+			but takes effect only when the low-order four
+			bits of srcutree.convert_to_big is equal to 3
+			(decide at boot).
+
+	srcutree.convert_to_big [KNL]
+			Specifies under what conditions an SRCU tree
+			srcu_struct structure will be converted to big
+			form, that is, with an rcu_node tree:
+
+				   0:  Never.
+				   1:  At init_srcu_struct() time.
+				   2:  When rcutorture decides to.
+				   3:  Decide at boot time (default).
+				0x1X:  Above plus if high contention.
+
+			Either way, the srcu_node tree will be sized based
+			on the actual runtime number of CPUs (nr_cpu_ids)
+			instead of the compile-time CONFIG_NR_CPUS.
+
 	srcutree.counter_wrap_check [KNL]
 			Specifies how frequently to check for
 			grace-period sequence counter wrap for the
@@ -5633,6 +5748,14 @@
 			expediting.  Set to zero to disable automatic
 			expediting.
 
+	srcutree.small_contention_lim [KNL]
+			Specifies the number of update-side contention
+			events per jiffy will be tolerated before
+			initiating a conversion of an srcu_struct
+			structure to big form.	Note that the value of
+			srcutree.convert_to_big must have the 0x10 bit
+			set for contention-based conversions to occur.
+
 	ssbd=		[ARM64,HW]
 			Speculative Store Bypass Disable control
 

Documentation/admin-guide/sysctl/kernel.rst

@@ -994,6 +994,9 @@ This is a directory, with the following entries:
 * ``boot_id``: a UUID generated the first time this is retrieved, and
   unvarying after that;
 
+* ``uuid``: a UUID generated every time this is retrieved (this can
+  thus be used to generate UUIDs at will);
+
 * ``entropy_avail``: the pool's entropy count, in bits;
 
 * ``poolsize``: the entropy pool size, in bits;
@@ -1001,10 +1004,7 @@ This is a directory, with the following entries:
 * ``urandom_min_reseed_secs``: obsolete (used to determine the minimum
   number of seconds between urandom pool reseeding). This file is
   writable for compatibility purposes, but writing to it has no effect
-  on any RNG behavior.
-
-* ``uuid``: a UUID generated every time this is retrieved (this can
-  thus be used to generate UUIDs at will);
+  on any RNG behavior;
 
 * ``write_wakeup_threshold``: when the entropy count drops below this
   (as a number of bits), processes waiting to write to ``/dev/random``

Documentation/arm64/booting.rst

@@ -350,6 +350,16 @@ Before jumping into the kernel, the following conditions must be met:
 
     - SMCR_EL2.FA64 (bit 31) must be initialised to 0b1.
 
+  For CPUs with the Memory Tagging Extension feature (FEAT_MTE2):
+
+  - If EL3 is present:
+
+    - SCR_EL3.ATA (bit 26) must be initialised to 0b1.
+
+  - If the kernel is entered at EL1 and EL2 is present:
+
+    - HCR_EL2.ATA (bit 56) must be initialised to 0b1.
+
 The requirements described above for CPU mode, caches, MMUs, architected
 timers, coherency and system registers apply to all CPUs.  All CPUs must
 enter the kernel in the same exception level.  Where the values documented

Documentation/arm64/elf_hwcaps.rst

@@ -264,6 +264,39 @@ HWCAP2_MTE3
     Functionality implied by ID_AA64PFR1_EL1.MTE == 0b0011, as described
     by Documentation/arm64/memory-tagging-extension.rst.
 
+HWCAP2_SME
+
+    Functionality implied by ID_AA64PFR1_EL1.SME == 0b0001, as described
+    by Documentation/arm64/sme.rst.
+
+HWCAP2_SME_I16I64
+
+    Functionality implied by ID_AA64SMFR0_EL1.I16I64 == 0b1111.
+
+HWCAP2_SME_F64F64
+
+    Functionality implied by ID_AA64SMFR0_EL1.F64F64 == 0b1.
+
+HWCAP2_SME_I8I32
+
+    Functionality implied by ID_AA64SMFR0_EL1.I8I32 == 0b1111.
+
+HWCAP2_SME_F16F32
+
+    Functionality implied by ID_AA64SMFR0_EL1.F16F32 == 0b1.
+
+HWCAP2_SME_B16F32
+
+    Functionality implied by ID_AA64SMFR0_EL1.B16F32 == 0b1.
+
+HWCAP2_SME_F32F32
+
+    Functionality implied by ID_AA64SMFR0_EL1.F32F32 == 0b1.
+
+HWCAP2_SME_FA64
+
+    Functionality implied by ID_AA64SMFR0_EL1.FA64 == 0b1.
+
 4. Unused AT_HWCAP bits
 -----------------------
 

Documentation/arm64/index.rst

@@ -21,6 +21,7 @@ ARM64 Architecture
     perf
     pointer-authentication
     silicon-errata
+    sme
     sve
     tagged-address-abi
     tagged-pointers

Documentation/arm64/sme.rst

@@ -0,0 +1,428 @@
+===================================================
+Scalable Matrix Extension support for AArch64 Linux
+===================================================
+
+This document outlines briefly the interface provided to userspace by Linux in
+order to support use of the ARM Scalable Matrix Extension (SME).
+
+This is an outline of the most important features and issues only and not
+intended to be exhaustive.  It should be read in conjunction with the SVE
+documentation in sve.rst which provides details on the Streaming SVE mode
+included in SME.
+
+This document does not aim to describe the SME architecture or programmer's
+model.  To aid understanding, a minimal description of relevant programmer's
+model features for SME is included in Appendix A.
+
+
+1.  General
+-----------
+
+* PSTATE.SM, PSTATE.ZA, the streaming mode vector length, the ZA
+  register state and TPIDR2_EL0 are tracked per thread.
+
+* The presence of SME is reported to userspace via HWCAP2_SME in the aux vector
+  AT_HWCAP2 entry.  Presence of this flag implies the presence of the SME
+  instructions and registers, and the Linux-specific system interfaces
+  described in this document.  SME is reported in /proc/cpuinfo as "sme".
+
+* Support for the execution of SME instructions in userspace can also be
+  detected by reading the CPU ID register ID_AA64PFR1_EL1 using an MRS
+  instruction, and checking that the value of the SME field is nonzero. [3]
+
+  It does not guarantee the presence of the system interfaces described in the
+  following sections: software that needs to verify that those interfaces are
+  present must check for HWCAP2_SME instead.
+
+* There are a number of optional SME features, presence of these is reported
+  through AT_HWCAP2 through:
+
+	HWCAP2_SME_I16I64
+	HWCAP2_SME_F64F64
+	HWCAP2_SME_I8I32
+	HWCAP2_SME_F16F32
+	HWCAP2_SME_B16F32
+	HWCAP2_SME_F32F32
+	HWCAP2_SME_FA64
+
+  This list may be extended over time as the SME architecture evolves.
+
+  These extensions are also reported via the CPU ID register ID_AA64SMFR0_EL1,
+  which userspace can read using an MRS instruction.  See elf_hwcaps.txt and
+  cpu-feature-registers.txt for details.
+
+* Debuggers should restrict themselves to interacting with the target via the
+  NT_ARM_SVE, NT_ARM_SSVE and NT_ARM_ZA regsets.  The recommended way
+  of detecting support for these regsets is to connect to a target process
+  first and then attempt a
+
+	ptrace(PTRACE_GETREGSET, pid, NT_ARM_<regset>, &iov).
+
+* Whenever ZA register values are exchanged in memory between userspace and
+  the kernel, the register value is encoded in memory as a series of horizontal
+  vectors from 0 to VL/8-1 stored in the same endianness invariant format as is
+  used for SVE vectors.
+
+* On thread creation TPIDR2_EL0 is preserved unless CLONE_SETTLS is specified,
+  in which case it is set to 0.
+
+2.  Vector lengths
+------------------
+
+SME defines a second vector length similar to the SVE vector length which is
+controls the size of the streaming mode SVE vectors and the ZA matrix array.
+The ZA matrix is square with each side having as many bytes as a streaming
+mode SVE vector.
+
+
+3.  Sharing of streaming and non-streaming mode SVE state
+---------------------------------------------------------
+
+It is implementation defined which if any parts of the SVE state are shared
+between streaming and non-streaming modes.  When switching between modes
+via software interfaces such as ptrace if no register content is provided as
+part of switching no state will be assumed to be shared and everything will
+be zeroed.
+
+
+4.  System call behaviour
+-------------------------
+
+* On syscall PSTATE.ZA is preserved, if PSTATE.ZA==1 then the contents of the
+  ZA matrix are preserved.
+
+* On syscall PSTATE.SM will be cleared and the SVE registers will be handled
+  as per the standard SVE ABI.
+
+* Neither the SVE registers nor ZA are used to pass arguments to or receive
+  results from any syscall.
+
+* On process creation (eg, clone()) the newly created process will have
+  PSTATE.SM cleared.
+
+* All other SME state of a thread, including the currently configured vector
+  length, the state of the PR_SME_VL_INHERIT flag, and the deferred vector
+  length (if any), is preserved across all syscalls, subject to the specific
+  exceptions for execve() described in section 6.
+
+
+5.  Signal handling
+-------------------
+
+* Signal handlers are invoked with streaming mode and ZA disabled.
+
+* A new signal frame record za_context encodes the ZA register contents on
+  signal delivery. [1]
+
+* The signal frame record for ZA always contains basic metadata, in particular
+  the thread's vector length (in za_context.vl).
+
+* The ZA matrix may or may not be included in the record, depending on
+  the value of PSTATE.ZA.  The registers are present if and only if:
+  za_context.head.size >= ZA_SIG_CONTEXT_SIZE(sve_vq_from_vl(za_context.vl))
+  in which case PSTATE.ZA == 1.
+
+* If matrix data is present, the remainder of the record has a vl-dependent
+  size and layout.  Macros ZA_SIG_* are defined [1] to facilitate access to
+  them.
+
+* The matrix is stored as a series of horizontal vectors in the same format as
+  is used for SVE vectors.
+
+* If the ZA context is too big to fit in sigcontext.__reserved[], then extra
+  space is allocated on the stack, an extra_context record is written in
+  __reserved[] referencing this space.  za_context is then written in the
+  extra space.  Refer to [1] for further details about this mechanism.
+
+
+5.  Signal return
+-----------------
+
+When returning from a signal handler:
+
+* If there is no za_context record in the signal frame, or if the record is
+  present but contains no register data as described in the previous section,
+  then ZA is disabled.
+
+* If za_context is present in the signal frame and contains matrix data then
+  PSTATE.ZA is set to 1 and ZA is populated with the specified data.
+
+* The vector length cannot be changed via signal return.  If za_context.vl in
+  the signal frame does not match the current vector length, the signal return
+  attempt is treated as illegal, resulting in a forced SIGSEGV.
+
+
+6.  prctl extensions
+--------------------
+
+Some new prctl() calls are added to allow programs to manage the SME vector
+length:
+
+prctl(PR_SME_SET_VL, unsigned long arg)
+
+    Sets the vector length of the calling thread and related flags, where
+    arg == vl | flags.  Other threads of the calling process are unaffected.
+
+    vl is the desired vector length, where sve_vl_valid(vl) must be true.
+
+    flags:
+
+	PR_SME_VL_INHERIT
+
+	    Inherit the current vector length across execve().  Otherwise, the
+	    vector length is reset to the system default at execve().  (See
+	    Section 9.)
+
+	PR_SME_SET_VL_ONEXEC
+
+	    Defer the requested vector length change until the next execve()
+	    performed by this thread.
+
+	    The effect is equivalent to implicit execution of the following
+	    call immediately after the next execve() (if any) by the thread:
+
+		prctl(PR_SME_SET_VL, arg & ~PR_SME_SET_VL_ONEXEC)
+
+	    This allows launching of a new program with a different vector
+	    length, while avoiding runtime side effects in the caller.
+
+	    Without PR_SME_SET_VL_ONEXEC, the requested change takes effect
+	    immediately.
+
+
+    Return value: a nonnegative on success, or a negative value on error:
+	EINVAL: SME not supported, invalid vector length requested, or
+	    invalid flags.
+
+
+    On success:
+
+    * Either the calling thread's vector length or the deferred vector length
+      to be applied at the next execve() by the thread (dependent on whether
+      PR_SME_SET_VL_ONEXEC is present in arg), is set to the largest value
+      supported by the system that is less than or equal to vl.  If vl ==
+      SVE_VL_MAX, the value set will be the largest value supported by the
+      system.
+
+    * Any previously outstanding deferred vector length change in the calling
+      thread is cancelled.
+
+    * The returned value describes the resulting configuration, encoded as for
+      PR_SME_GET_VL.  The vector length reported in this value is the new
+      current vector length for this thread if PR_SME_SET_VL_ONEXEC was not
+      present in arg; otherwise, the reported vector length is the deferred
+      vector length that will be applied at the next execve() by the calling
+      thread.
+
+    * Changing the vector length causes all of ZA, P0..P15, FFR and all bits of
+      Z0..Z31 except for Z0 bits [127:0] .. Z31 bits [127:0] to become
+      unspecified, including both streaming and non-streaming SVE state.
+      Calling PR_SME_SET_VL with vl equal to the thread's current vector
+      length, or calling PR_SME_SET_VL with the PR_SVE_SET_VL_ONEXEC flag,
+      does not constitute a change to the vector length for this purpose.
+
+    * Changing the vector length causes PSTATE.ZA and PSTATE.SM to be cleared.
+      Calling PR_SME_SET_VL with vl equal to the thread's current vector
+      length, or calling PR_SME_SET_VL with the PR_SVE_SET_VL_ONEXEC flag,
+      does not constitute a change to the vector length for this purpose.
+
+
+prctl(PR_SME_GET_VL)
+
+    Gets the vector length of the calling thread.
+
+    The following flag may be OR-ed into the result:
+
+	PR_SME_VL_INHERIT
+
+	    Vector length will be inherited across execve().
+
+    There is no way to determine whether there is an outstanding deferred
+    vector length change (which would only normally be the case between a
+    fork() or vfork() and the corresponding execve() in typical use).
+
+    To extract the vector length from the result, bitwise and it with
+    PR_SME_VL_LEN_MASK.
+
+    Return value: a nonnegative value on success, or a negative value on error:
+	EINVAL: SME not supported.
+
+
+7.  ptrace extensions
+---------------------
+
+* A new regset NT_ARM_SSVE is defined for access to streaming mode SVE
+  state via PTRACE_GETREGSET and  PTRACE_SETREGSET, this is documented in
+  sve.rst.
+
+* A new regset NT_ARM_ZA is defined for ZA state for access to ZA state via
+  PTRACE_GETREGSET and PTRACE_SETREGSET.
+
+  Refer to [2] for definitions.
+
+The regset data starts with struct user_za_header, containing:
+
+    size
+
+	Size of the complete regset, in bytes.
+	This depends on vl and possibly on other things in the future.
+
+	If a call to PTRACE_GETREGSET requests less data than the value of
+	size, the caller can allocate a larger buffer and retry in order to
+	read the complete regset.
+
+    max_size
+
+	Maximum size in bytes that the regset can grow to for the target
+	thread.  The regset won't grow bigger than this even if the target
+	thread changes its vector length etc.
+
+    vl
+
+	Target thread's current streaming vector length, in bytes.
+
+    max_vl
+
+	Maximum possible streaming vector length for the target thread.
+
+    flags
+
+	Zero or more of the following flags, which have the same
+	meaning and behaviour as the corresponding PR_SET_VL_* flags:
+
+	    SME_PT_VL_INHERIT
+
+	    SME_PT_VL_ONEXEC (SETREGSET only).
+
+* The effects of changing the vector length and/or flags are equivalent to
+  those documented for PR_SME_SET_VL.
+
+  The caller must make a further GETREGSET call if it needs to know what VL is
+  actually set by SETREGSET, unless is it known in advance that the requested
+  VL is supported.
+
+* The size and layout of the payload depends on the header fields.  The
+  SME_PT_ZA_*() macros are provided to facilitate access to the data.
+
+* In either case, for SETREGSET it is permissible to omit the payload, in which
+  case the vector length and flags are changed and PSTATE.ZA is set to 0
+  (along with any consequences of those changes).  If a payload is provided
+  then PSTATE.ZA will be set to 1.
+
+* For SETREGSET, if the requested VL is not supported, the effect will be the
+  same as if the payload were omitted, except that an EIO error is reported.
+  No attempt is made to translate the payload data to the correct layout
+  for the vector length actually set.  It is up to the caller to translate the
+  payload layout for the actual VL and retry.
+
+* The effect of writing a partial, incomplete payload is unspecified.
+
+
+8.  ELF coredump extensions
+---------------------------
+
+* NT_ARM_SSVE notes will be added to each coredump for
+  each thread of the dumped process.  The contents will be equivalent to the
+  data that would have been read if a PTRACE_GETREGSET of the corresponding
+  type were executed for each thread when the coredump was generated.
+
+* A NT_ARM_ZA note will be added to each coredump for each thread of the
+  dumped process.  The contents will be equivalent to the data that would have
+  been read if a PTRACE_GETREGSET of NT_ARM_ZA were executed for each thread
+  when the coredump was generated.
+
+
+9.  System runtime configuration
+--------------------------------
+
+* To mitigate the ABI impact of expansion of the signal frame, a policy
+  mechanism is provided for administrators, distro maintainers and developers
+  to set the default vector length for userspace processes:
+
+/proc/sys/abi/sme_default_vector_length
+
+    Writing the text representation of an integer to this file sets the system
+    default vector length to the specified value, unless the value is greater
+    than the maximum vector length supported by the system in which case the
+    default vector length is set to that maximum.
+
+    The result can be determined by reopening the file and reading its
+    contents.
+
+    At boot, the default vector length is initially set to 32 or the maximum
+    supported vector length, whichever is smaller and supported.  This
+    determines the initial vector length of the init process (PID 1).
+
+    Reading this file returns the current system default vector length.
+
+* At every execve() call, the new vector length of the new process is set to
+  the system default vector length, unless
+
+    * PR_SME_VL_INHERIT (or equivalently SME_PT_VL_INHERIT) is set for the
+      calling thread, or
+
+    * a deferred vector length change is pending, established via the
+      PR_SME_SET_VL_ONEXEC flag (or SME_PT_VL_ONEXEC).
+
+* Modifying the system default vector length does not affect the vector length
+  of any existing process or thread that does not make an execve() call.
+
+
+Appendix A.  SME programmer's model (informative)
+=================================================
+
+This section provides a minimal description of the additions made by SVE to the
+ARMv8-A programmer's model that are relevant to this document.
+
+Note: This section is for information only and not intended to be complete or
+to replace any architectural specification.
+
+A.1.  Registers
+---------------
+
+In A64 state, SME adds the following:
+
+* A new mode, streaming mode, in which a subset of the normal FPSIMD and SVE
+  features are available.  When supported EL0 software may enter and leave
+  streaming mode at any time.
+
+  For best system performance it is strongly encouraged for software to enable
+  streaming mode only when it is actively being used.
+
+* A new vector length controlling the size of ZA and the Z registers when in
+  streaming mode, separately to the vector length used for SVE when not in
+  streaming mode.  There is no requirement that either the currently selected
+  vector length or the set of vector lengths supported for the two modes in
+  a given system have any relationship.  The streaming mode vector length
+  is referred to as SVL.
+
+* A new ZA matrix register.  This is a square matrix of SVLxSVL bits.  Most
+  operations on ZA require that streaming mode be enabled but ZA can be
+  enabled without streaming mode in order to load, save and retain data.
+
+  For best system performance it is strongly encouraged for software to enable
+  ZA only when it is actively being used.
+
+* Two new 1 bit fields in PSTATE which may be controlled via the SMSTART and
+  SMSTOP instructions or by access to the SVCR system register:
+
+  * PSTATE.ZA, if this is 1 then the ZA matrix is accessible and has valid
+    data while if it is 0 then ZA can not be accessed.  When PSTATE.ZA is
+    changed from 0 to 1 all bits in ZA are cleared.
+
+  * PSTATE.SM, if this is 1 then the PE is in streaming mode.  When the value
+    of PSTATE.SM is changed then it is implementation defined if the subset
+    of the floating point register bits valid in both modes may be retained.
+    Any other bits will be cleared.
+
+
+References
+==========
+
+[1] arch/arm64/include/uapi/asm/sigcontext.h
+    AArch64 Linux signal ABI definitions
+
+[2] arch/arm64/include/uapi/asm/ptrace.h
+    AArch64 Linux ptrace ABI definitions
+
+[3] Documentation/arm64/cpu-feature-registers.rst

Documentation/arm64/sve.rst

@@ -7,7 +7,9 @@ Author: Dave Martin <Dave.Martin@arm.com>
 Date:   4 August 2017
 
 This document outlines briefly the interface provided to userspace by Linux in
-order to support use of the ARM Scalable Vector Extension (SVE).
+order to support use of the ARM Scalable Vector Extension (SVE), including
+interactions with Streaming SVE mode added by the Scalable Matrix Extension
+(SME).
 
 This is an outline of the most important features and issues only and not
 intended to be exhaustive.
@@ -23,6 +25,10 @@ model features for SVE is included in Appendix A.
 * SVE registers Z0..Z31, P0..P15 and FFR and the current vector length VL, are
   tracked per-thread.
 
+* In streaming mode FFR is not accessible unless HWCAP2_SME_FA64 is present
+  in the system, when it is not supported and these interfaces are used to
+  access streaming mode FFR is read and written as zero.
+
 * The presence of SVE is reported to userspace via HWCAP_SVE in the aux vector
   AT_HWCAP entry.  Presence of this flag implies the presence of the SVE
   instructions and registers, and the Linux-specific system interfaces
@@ -53,10 +59,19 @@ model features for SVE is included in Appendix A.
   which userspace can read using an MRS instruction.  See elf_hwcaps.txt and
   cpu-feature-registers.txt for details.
 
+* On hardware that supports the SME extensions, HWCAP2_SME will also be
+  reported in the AT_HWCAP2 aux vector entry.  Among other things SME adds
+  streaming mode which provides a subset of the SVE feature set using a
+  separate SME vector length and the same Z/V registers.  See sme.rst
+  for more details.
+
 * Debuggers should restrict themselves to interacting with the target via the
   NT_ARM_SVE regset.  The recommended way of detecting support for this regset
   is to connect to a target process first and then attempt a
-  ptrace(PTRACE_GETREGSET, pid, NT_ARM_SVE, &iov).
+  ptrace(PTRACE_GETREGSET, pid, NT_ARM_SVE, &iov).  Note that when SME is
+  present and streaming SVE mode is in use the FPSIMD subset of registers
+  will be read via NT_ARM_SVE and NT_ARM_SVE writes will exit streaming mode
+  in the target.
 
 * Whenever SVE scalable register values (Zn, Pn, FFR) are exchanged in memory
   between userspace and the kernel, the register value is encoded in memory in
@@ -126,6 +141,11 @@ the SVE instruction set architecture.
   are only present in fpsimd_context.  For convenience, the content of V0..V31
   is duplicated between sve_context and fpsimd_context.
 
+* The record contains a flag field which includes a flag SVE_SIG_FLAG_SM which
+  if set indicates that the thread is in streaming mode and the vector length
+  and register data (if present) describe the streaming SVE data and vector
+  length.
+
 * The signal frame record for SVE always contains basic metadata, in particular
   the thread's vector length (in sve_context.vl).
 
@@ -170,6 +190,11 @@ When returning from a signal handler:
   the signal frame does not match the current vector length, the signal return
   attempt is treated as illegal, resulting in a forced SIGSEGV.
 
+* It is permitted to enter or leave streaming mode by setting or clearing
+  the SVE_SIG_FLAG_SM flag but applications should take care to ensure that
+  when doing so sve_context.vl and any register data are appropriate for the
+  vector length in the new mode.
+
 
 6.  prctl extensions
 --------------------
@@ -265,8 +290,14 @@ prctl(PR_SVE_GET_VL)
 7.  ptrace extensions
 ---------------------
 
-* A new regset NT_ARM_SVE is defined for use with PTRACE_GETREGSET and
-  PTRACE_SETREGSET.
+* New regsets NT_ARM_SVE and NT_ARM_SSVE are defined for use with
+  PTRACE_GETREGSET and PTRACE_SETREGSET. NT_ARM_SSVE describes the
+  streaming mode SVE registers and NT_ARM_SVE describes the
+  non-streaming mode SVE registers.
+
+  In this description a register set is referred to as being "live" when
+  the target is in the appropriate streaming or non-streaming mode and is
+  using data beyond the subset shared with the FPSIMD Vn registers.
 
   Refer to [2] for definitions.
 
@@ -297,7 +328,7 @@ The regset data starts with struct user_sve_header, containing:
 
     flags
 
-	either
+	at most one of
 
 	    SVE_PT_REGS_FPSIMD
 
@@ -331,6 +362,10 @@ The regset data starts with struct user_sve_header, containing:
 
 	    SVE_PT_VL_ONEXEC (SETREGSET only).
 
+	If neither FPSIMD nor SVE flags are provided then no register
+	payload is available, this is only possible when SME is implemented.
+
+
 * The effects of changing the vector length and/or flags are equivalent to
   those documented for PR_SVE_SET_VL.
 
@@ -346,6 +381,13 @@ The regset data starts with struct user_sve_header, containing:
   case only the vector length and flags are changed (along with any
   consequences of those changes).
 
+* In systems supporting SME when in streaming mode a GETREGSET for
+  NT_REG_SVE will return only the user_sve_header with no register data,
+  similarly a GETREGSET for NT_REG_SSVE will not return any register data
+  when not in streaming mode.
+
+* A GETREGSET for NT_ARM_SSVE will never return SVE_PT_REGS_FPSIMD.
+
 * For SETREGSET, if an SVE_PT_REGS_SVE payload is present and the
   requested VL is not supported, the effect will be the same as if the
   payload were omitted, except that an EIO error is reported.  No
@@ -355,17 +397,25 @@ The regset data starts with struct user_sve_header, containing:
   unspecified.  It is up to the caller to translate the payload layout
   for the actual VL and retry.
 
+* Where SME is implemented it is not possible to GETREGSET the register
+  state for normal SVE when in streaming mode, nor the streaming mode
+  register state when in normal mode, regardless of the implementation defined
+  behaviour of the hardware for sharing data between the two modes.
+
+* Any SETREGSET of NT_ARM_SVE will exit streaming mode if the target was in
+  streaming mode and any SETREGSET of NT_ARM_SSVE will enter streaming mode
+  if the target was not in streaming mode.
+
 * The effect of writing a partial, incomplete payload is unspecified.
 
 
 8.  ELF coredump extensions
 ---------------------------
 
-* A NT_ARM_SVE note will be added to each coredump for each thread of the
-  dumped process.  The contents will be equivalent to the data that would have
-  been read if a PTRACE_GETREGSET of NT_ARM_SVE were executed for each thread
-  when the coredump was generated.
-
+* NT_ARM_SVE and NT_ARM_SSVE notes will be added to each coredump for
+  each thread of the dumped process.  The contents will be equivalent to the
+  data that would have been read if a PTRACE_GETREGSET of the corresponding
+  type were executed for each thread when the coredump was generated.
 
 9.  System runtime configuration
 --------------------------------

Documentation/cdrom/cdrom-standard.rst

@@ -218,7 +218,6 @@ current *struct* is::
 		int (*tray_move)(struct cdrom_device_info *, int);
 		int (*lock_door)(struct cdrom_device_info *, int);
 		int (*select_speed)(struct cdrom_device_info *, int);
-		int (*select_disc)(struct cdrom_device_info *, int);
 		int (*get_last_session) (struct cdrom_device_info *,
 					 struct cdrom_multisession *);
 		int (*get_mcn)(struct cdrom_device_info *, struct cdrom_mcn *);
@@ -419,15 +418,6 @@ this `auto-selection` capability, the decision should be made on the
 current disc loaded and the return value should be positive. A negative
 return value indicates an error.
 
-::
-
-	int select_disc(struct cdrom_device_info *cdi, int number)
-
-If the drive can store multiple discs (a juke-box) this function
-will perform disc selection. It should return the number of the
-selected disc on success, a negative value on error. Currently, only
-the ide-cd driver supports this functionality.
-
 ::
 
 	int get_last_session(struct cdrom_device_info *cdi,

Documentation/core-api/timekeeping.rst

@@ -132,6 +132,7 @@ Some additional variants exist for more specialized cases:
 .. c:function:: u64 ktime_get_mono_fast_ns( void )
 		u64 ktime_get_raw_fast_ns( void )
 		u64 ktime_get_boot_fast_ns( void )
+		u64 ktime_get_tai_fast_ns( void )
 		u64 ktime_get_real_fast_ns( void )
 
 	These variants are safe to call from any context, including from

Documentation/devicetree/bindings/ata/renesas,rcar-sata.yaml

@@ -26,6 +26,7 @@ properties:
       - items:
           - enum:
               - renesas,sata-r8a774b1     # RZ/G2N
+              - renesas,sata-r8a774e1     # RZ/G2H
               - renesas,sata-r8a7795      # R-Car H3
               - renesas,sata-r8a77965     # R-Car M3-N
           - const: renesas,rcar-gen3-sata # generic R-Car Gen3 or RZ/G2

Documentation/devicetree/bindings/interrupt-controller/arm,gic-v3.yaml

@@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml#
 title: ARM Generic Interrupt Controller, version 3
 
 maintainers:
-  - Marc Zyngier <marc.zyngier@arm.com>
+  - Marc Zyngier <maz@kernel.org>
 
 description: |
   AArch64 SMP cores are often associated with a GICv3, providing Private
@@ -78,7 +78,11 @@ properties:
       - GIC Hypervisor interface (GICH)
       - GIC Virtual CPU interface (GICV)
 
-      GICC, GICH and GICV are optional.
+      GICC, GICH and GICV are optional, but must be described if the CPUs
+      support them. Examples of such CPUs are ARM's implementations of the
+      ARMv8.0 architecture such as Cortex-A32, A34, A35, A53, A57, A72 and
+      A73 (this list is not exhaustive).
+
     minItems: 2
     maxItems: 4096   # Should be enough?
 

Documentation/devicetree/bindings/memory-controllers/fsl/fsl,ddr.yaml

@@ -25,12 +25,6 @@ properties:
           - const: fsl,qoriq-memory-controller
       - enum:
           - fsl,bsc9132-memory-controller
-          - fsl,8540-memory-controller
-          - fsl,8541-memory-controller
-          - fsl,8544-memory-controller
-          - fsl,8548-memory-controller
-          - fsl,8555-memory-controller
-          - fsl,8568-memory-controller
           - fsl,mpc8536-memory-controller
           - fsl,mpc8540-memory-controller
           - fsl,mpc8541-memory-controller

Documentation/devicetree/bindings/perf/arm,cmn.yaml

@@ -14,6 +14,8 @@ properties:
   compatible:
     enum:
       - arm,cmn-600
+      - arm,cmn-650
+      - arm,cmn-700
       - arm,ci-700
 
   reg:

Documentation/devicetree/bindings/powerpc/fsl/l2cache.txt

@@ -6,12 +6,6 @@ The cache bindings explained below are Devicetree Specification compliant
 Required Properties:
 
 - compatible	: Should include one of the following:
-		  "fsl,8540-l2-cache-controller"
-		  "fsl,8541-l2-cache-controller"
-		  "fsl,8544-l2-cache-controller"
-		  "fsl,8548-l2-cache-controller"
-		  "fsl,8555-l2-cache-controller"
-		  "fsl,8568-l2-cache-controller"
 		  "fsl,b4420-l2-cache-controller"
 		  "fsl,b4860-l2-cache-controller"
 		  "fsl,bsc9131-l2-cache-controller"

Documentation/dontdiff

@@ -211,6 +211,7 @@ r200_reg_safe.h
 r300_reg_safe.h
 r420_reg_safe.h
 r600_reg_safe.h
+randstruct.seed
 randomize_layout_hash.h
 randomize_layout_seed.h
 recordmcount

Documentation/driver-api/gpio/driver.rst

@@ -417,30 +417,66 @@ struct gpio_irq_chip inside struct gpio_chip before adding the gpio_chip.
 If you do this, the additional irq_chip will be set up by gpiolib at the
 same time as setting up the rest of the GPIO functionality. The following
 is a typical example of a chained cascaded interrupt handler using
-the gpio_irq_chip:
+the gpio_irq_chip. Note how the mask/unmask (or disable/enable) functions
+call into the core gpiolib code:
 
 .. code-block:: c
 
-  /* Typical state container with dynamic irqchip */
+  /* Typical state container */
   struct my_gpio {
       struct gpio_chip gc;
-      struct irq_chip irq;
+  };
+
+  static void my_gpio_mask_irq(struct irq_data *d)
+  {
+      struct gpio_chip *gc = irq_desc_get_handler_data(d);
+
+      /*
+       * Perform any necessary action to mask the interrupt,
+       * and then call into the core code to synchronise the
+       * state.
+       */
+
+      gpiochip_disable_irq(gc, d->hwirq);
+  }
+
+  static void my_gpio_unmask_irq(struct irq_data *d)
+  {
+      struct gpio_chip *gc = irq_desc_get_handler_data(d);
+
+      gpiochip_enable_irq(gc, d->hwirq);
+
+      /*
+       * Perform any necessary action to unmask the interrupt,
+       * after having called into the core code to synchronise
+       * the state.
+       */
+  }
+
+  /*
+   * Statically populate the irqchip. Note that it is made const
+   * (further indicated by the IRQCHIP_IMMUTABLE flag), and that
+   * the GPIOCHIP_IRQ_RESOURCE_HELPER macro adds some extra
+   * callbacks to the structure.
+   */
+  static const struct irq_chip my_gpio_irq_chip = {
+      .name		= "my_gpio_irq",
+      .irq_ack		= my_gpio_ack_irq,
+      .irq_mask		= my_gpio_mask_irq,
+      .irq_unmask	= my_gpio_unmask_irq,
+      .irq_set_type	= my_gpio_set_irq_type,
+      .flags		= IRQCHIP_IMMUTABLE,
+      /* Provide the gpio resource callbacks */
+      GPIOCHIP_IRQ_RESOURCE_HELPERS,
   };
 
   int irq; /* from platform etc */
   struct my_gpio *g;
   struct gpio_irq_chip *girq;
 
-  /* Set up the irqchip dynamically */
-  g->irq.name = "my_gpio_irq";
-  g->irq.irq_ack = my_gpio_ack_irq;
-  g->irq.irq_mask = my_gpio_mask_irq;
-  g->irq.irq_unmask = my_gpio_unmask_irq;
-  g->irq.irq_set_type = my_gpio_set_irq_type;
-
   /* Get a pointer to the gpio_irq_chip */
   girq = &g->gc.irq;
-  girq->chip = &g->irq;
+  gpio_irq_chip_set_chip(girq, &my_gpio_irq_chip);
   girq->parent_handler = ftgpio_gpio_irq_handler;
   girq->num_parents = 1;
   girq->parents = devm_kcalloc(dev, 1, sizeof(*girq->parents),
@@ -458,23 +494,58 @@ the interrupt separately and go with it:
 
 .. code-block:: c
 
-  /* Typical state container with dynamic irqchip */
+  /* Typical state container */
   struct my_gpio {
       struct gpio_chip gc;
-      struct irq_chip irq;
+  };
+
+  static void my_gpio_mask_irq(struct irq_data *d)
+  {
+      struct gpio_chip *gc = irq_desc_get_handler_data(d);
+
+      /*
+       * Perform any necessary action to mask the interrupt,
+       * and then call into the core code to synchronise the
+       * state.
+       */
+
+      gpiochip_disable_irq(gc, d->hwirq);
+  }
+
+  static void my_gpio_unmask_irq(struct irq_data *d)
+  {
+      struct gpio_chip *gc = irq_desc_get_handler_data(d);
+
+      gpiochip_enable_irq(gc, d->hwirq);
+
+      /*
+       * Perform any necessary action to unmask the interrupt,
+       * after having called into the core code to synchronise
+       * the state.
+       */
+  }
+
+  /*
+   * Statically populate the irqchip. Note that it is made const
+   * (further indicated by the IRQCHIP_IMMUTABLE flag), and that
+   * the GPIOCHIP_IRQ_RESOURCE_HELPER macro adds some extra
+   * callbacks to the structure.
+   */
+  static const struct irq_chip my_gpio_irq_chip = {
+      .name		= "my_gpio_irq",
+      .irq_ack		= my_gpio_ack_irq,
+      .irq_mask		= my_gpio_mask_irq,
+      .irq_unmask	= my_gpio_unmask_irq,
+      .irq_set_type	= my_gpio_set_irq_type,
+      .flags		= IRQCHIP_IMMUTABLE,
+      /* Provide the gpio resource callbacks */
+      GPIOCHIP_IRQ_RESOURCE_HELPERS,
   };
 
   int irq; /* from platform etc */
   struct my_gpio *g;
   struct gpio_irq_chip *girq;
 
-  /* Set up the irqchip dynamically */
-  g->irq.name = "my_gpio_irq";
-  g->irq.irq_ack = my_gpio_ack_irq;
-  g->irq.irq_mask = my_gpio_mask_irq;
-  g->irq.irq_unmask = my_gpio_unmask_irq;
-  g->irq.irq_set_type = my_gpio_set_irq_type;
-
   ret = devm_request_threaded_irq(dev, irq, NULL,
 		irq_thread_fn, IRQF_ONESHOT, "my-chip", g);
   if (ret < 0)
@@ -482,7 +553,7 @@ the interrupt separately and go with it:
 
   /* Get a pointer to the gpio_irq_chip */
   girq = &g->gc.irq;
-  girq->chip = &g->irq;
+  gpio_irq_chip_set_chip(girq, &my_gpio_irq_chip);
   /* This will let us handle the parent IRQ in the driver */
   girq->parent_handler = NULL;
   girq->num_parents = 0;
@@ -500,24 +571,61 @@ In this case the typical set-up will look like this:
   /* Typical state container with dynamic irqchip */
   struct my_gpio {
       struct gpio_chip gc;
-      struct irq_chip irq;
       struct fwnode_handle *fwnode;
   };
 
-  int irq; /* from platform etc */
+  static void my_gpio_mask_irq(struct irq_data *d)
+  {
+      struct gpio_chip *gc = irq_desc_get_handler_data(d);
+
+      /*
+       * Perform any necessary action to mask the interrupt,
+       * and then call into the core code to synchronise the
+       * state.
+       */
+
+      gpiochip_disable_irq(gc, d->hwirq);
+      irq_mask_mask_parent(d);
+  }
+
+  static void my_gpio_unmask_irq(struct irq_data *d)
+  {
+      struct gpio_chip *gc = irq_desc_get_handler_data(d);
+
+      gpiochip_enable_irq(gc, d->hwirq);
+
+      /*
+       * Perform any necessary action to unmask the interrupt,
+       * after having called into the core code to synchronise
+       * the state.
+       */
+
+      irq_mask_unmask_parent(d);
+  }
+
+  /*
+   * Statically populate the irqchip. Note that it is made const
+   * (further indicated by the IRQCHIP_IMMUTABLE flag), and that
+   * the GPIOCHIP_IRQ_RESOURCE_HELPER macro adds some extra
+   * callbacks to the structure.
+   */
+  static const struct irq_chip my_gpio_irq_chip = {
+      .name		= "my_gpio_irq",
+      .irq_ack		= my_gpio_ack_irq,
+      .irq_mask		= my_gpio_mask_irq,
+      .irq_unmask	= my_gpio_unmask_irq,
+      .irq_set_type	= my_gpio_set_irq_type,
+      .flags		= IRQCHIP_IMMUTABLE,
+      /* Provide the gpio resource callbacks */
+      GPIOCHIP_IRQ_RESOURCE_HELPERS,
+  };
+
   struct my_gpio *g;
   struct gpio_irq_chip *girq;
 
-  /* Set up the irqchip dynamically */
-  g->irq.name = "my_gpio_irq";
-  g->irq.irq_ack = my_gpio_ack_irq;
-  g->irq.irq_mask = my_gpio_mask_irq;
-  g->irq.irq_unmask = my_gpio_unmask_irq;
-  g->irq.irq_set_type = my_gpio_set_irq_type;
-
   /* Get a pointer to the gpio_irq_chip */
   girq = &g->gc.irq;
-  girq->chip = &g->irq;
+  gpio_irq_chip_set_chip(girq, &my_gpio_irq_chip);
   girq->default_type = IRQ_TYPE_NONE;
   girq->handler = handle_bad_irq;
   girq->fwnode = g->fwnode;
@@ -605,8 +713,9 @@ When implementing an irqchip inside a GPIO driver, these two functions should
 typically be called in the .irq_disable() and .irq_enable() callbacks from the
 irqchip.
 
-When using the gpiolib irqchip helpers, these callbacks are automatically
-assigned.
+When IRQCHIP_IMMUTABLE is not advertised by the irqchip, these callbacks
+are automatically assigned. This behaviour is deprecated and on its way
+to be removed from the kernel.
 
 
 Real-Time compliance for GPIO IRQ chips

Documentation/driver-api/libata.rst

@@ -424,12 +424,6 @@ How commands are issued
 -----------------------
 
 Internal commands
-    First, qc is allocated and initialized using :c:func:`ata_qc_new_init`.
-    Although :c:func:`ata_qc_new_init` doesn't implement any wait or retry
-    mechanism when qc is not available, internal commands are currently
-    issued only during initialization and error recovery, so no other
-    command is active and allocation is guaranteed to succeed.
-
     Once allocated qc's taskfile is initialized for the command to be
     executed. qc currently has two mechanisms to notify completion. One
     is via ``qc->complete_fn()`` callback and the other is completion
@@ -447,11 +441,6 @@ SCSI commands
     translated. No qc is involved in processing a simulated scmd. The
     result is computed right away and the scmd is completed.
 
-    For a translated scmd, :c:func:`ata_qc_new_init` is invoked to allocate a
-    qc and the scmd is translated into the qc. SCSI midlayer's
-    completion notification function pointer is stored into
-    ``qc->scsidone``.
-
     ``qc->complete_fn()`` callback is used for completion notification. ATA
     commands use :c:func:`ata_scsi_qc_complete` while ATAPI commands use
     :c:func:`atapi_qc_complete`. Both functions end up calling ``qc->scsidone``

Documentation/features/debug/debug-vm-pgtable/arch-support.txt

@@ -27,5 +27,5 @@
     |       sparc: | TODO |
     |          um: | TODO |
     |         x86: |  ok  |
-    |      xtensa: | TODO |
+    |      xtensa: |  ok  |
     -----------------------

Documentation/features/time/context-tracking/arch-support.txt

@@ -27,5 +27,5 @@
     |       sparc: |  ok  |
     |          um: | TODO |
     |         x86: |  ok  |
-    |      xtensa: | TODO |
+    |      xtensa: |  ok  |
     -----------------------

Documentation/features/time/virt-cpuacct/arch-support.txt

@@ -27,5 +27,5 @@
     |       sparc: |  ok  |
     |          um: | TODO |
     |         x86: |  ok  |
-    |      xtensa: | TODO |
+    |      xtensa: |  ok  |
     -----------------------

Documentation/filesystems/proc.rst

@@ -1183,85 +1183,7 @@ Provides counts of softirq handlers serviced since boot time, for each CPU.
     HRTIMER:         0          0          0          0
 	RCU:      1678       1769       2178       2250
 
-
-1.3 IDE devices in /proc/ide
-----------------------------
-
-The subdirectory /proc/ide contains information about all IDE devices of which
-the kernel  is  aware.  There is one subdirectory for each IDE controller, the
-file drivers  and a link for each IDE device, pointing to the device directory
-in the controller specific subtree.
-
-The file 'drivers' contains general information about the drivers used for the
-IDE devices::
-
-  > cat /proc/ide/drivers
-  ide-cdrom version 4.53
-  ide-disk version 1.08
-
-More detailed  information  can  be  found  in  the  controller  specific
-subdirectories. These  are  named  ide0,  ide1  and  so  on.  Each  of  these
-directories contains the files shown in table 1-6.
-
-
-.. table:: Table 1-6: IDE controller info in  /proc/ide/ide?
-
- ======= =======================================
- File    Content
- ======= =======================================
- channel IDE channel (0 or 1)
- config  Configuration (only for PCI/IDE bridge)
- mate    Mate name
- model   Type/Chipset of IDE controller
- ======= =======================================
-
-Each device  connected  to  a  controller  has  a separate subdirectory in the
-controllers directory.  The  files  listed in table 1-7 are contained in these
-directories.
-
-
-.. table:: Table 1-7: IDE device information
-
- ================ ==========================================
- File             Content
- ================ ==========================================
- cache            The cache
- capacity         Capacity of the medium (in 512Byte blocks)
- driver           driver and version
- geometry         physical and logical geometry
- identify         device identify block
- media            media type
- model            device identifier
- settings         device setup
- smart_thresholds IDE disk management thresholds
- smart_values     IDE disk management values
- ================ ==========================================
-
-The most  interesting  file is ``settings``. This file contains a nice
-overview of the drive parameters::
-
-  # cat /proc/ide/ide0/hda/settings
-  name                    value           min             max             mode
-  ----                    -----           ---             ---             ----
-  bios_cyl                526             0               65535           rw
-  bios_head               255             0               255             rw
-  bios_sect               63              0               63              rw
-  breada_readahead        4               0               127             rw
-  bswap                   0               0               1               r
-  file_readahead          72              0               2097151         rw
-  io_32bit                0               0               3               rw
-  keepsettings            0               0               1               rw
-  max_kb_per_request      122             1               127             rw
-  multcount               0               0               8               rw
-  nice1                   1               0               1               rw
-  nowerr                  0               0               1               rw
-  pio_mode                write-only      0               255             w
-  slow                    0               0               1               rw
-  unmaskirq               0               0               1               rw
-  using_dma               0               0               1               rw
-
-
-1.4 Networking info in /proc/net
+1.3 Networking info in /proc/net
 --------------------------------
 
 The subdirectory  /proc/net  follows  the  usual  pattern. Table 1-8 shows the
@@ -1340,7 +1262,7 @@ It will contain information that is specific to that bond, such as the
 current slaves of the bond, the link status of the slaves, and how
 many times the slaves link has failed.
 
-1.5 SCSI info
+1.4 SCSI info
 -------------
 
 If you  have  a  SCSI  host adapter in your system, you'll find a subdirectory
@@ -1403,7 +1325,7 @@ AHA-2940 SCSI adapter::
     Total transfers 0 (0 reads and 0 writes)
 
 
-1.6 Parallel port info in /proc/parport
+1.5 Parallel port info in /proc/parport
 ---------------------------------------
 
 The directory  /proc/parport  contains information about the parallel ports of
@@ -1428,7 +1350,7 @@ These directories contain the four files shown in Table 1-10.
            number or none).
  ========= ====================================================================
 
-1.7 TTY info in /proc/tty
+1.6 TTY info in /proc/tty
 -------------------------
 
 Information about  the  available  and actually used tty's can be found in the
@@ -1463,7 +1385,7 @@ To see  which  tty's  are  currently in use, you can simply look into the file
   unknown              /dev/tty        4    1-63 console
 
 
-1.8 Miscellaneous kernel statistics in /proc/stat
+1.7 Miscellaneous kernel statistics in /proc/stat
 -------------------------------------------------
 
 Various pieces   of  information about  kernel activity  are  available in the
@@ -1536,7 +1458,7 @@ softirqs serviced; each subsequent column is the total for that particular
 softirq.
 
 
-1.9 Ext4 file system parameters
+1.8 Ext4 file system parameters
 -------------------------------
 
 Information about mounted ext4 file systems can be found in
@@ -1552,7 +1474,7 @@ in Table 1-12, below.
  mb_groups       details of multiblock allocator buddy cache of free blocks
  ==============  ==========================================================
 
-1.10 /proc/consoles
+1.9 /proc/consoles
 -------------------
 Shows registered system console lines.
 

Documentation/filesystems/zonefs.rst

@@ -306,8 +306,15 @@ Further notes:
 Mount options
 -------------
 
-zonefs define the "errors=<behavior>" mount option to allow the user to specify
-zonefs behavior in response to I/O errors, inode size inconsistencies or zone
+zonefs defines several mount options:
+* errors=<behavior>
+* explicit-open
+
+"errors=<behavior>" option
+~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+The "errors=<behavior>" option mount option allows the user to specify zonefs
+behavior in response to I/O errors, inode size inconsistencies or zone
 condition changes. The defined behaviors are as follow:
 
 * remount-ro (default)
@@ -326,6 +333,9 @@ discover the amount of data that has been written to the zone. In the case of a
 read-only zone discovered at run-time, as indicated in the previous section.
 The size of the zone file is left unchanged from its last updated value.
 
+"explicit-open" option
+~~~~~~~~~~~~~~~~~~~~~~
+
 A zoned block device (e.g. an NVMe Zoned Namespace device) may have limits on
 the number of zones that can be active, that is, zones that are in the
 implicit open, explicit open or closed conditions.  This potential limitation
@@ -341,6 +351,44 @@ guaranteed that write requests can be processed. Conversely, the
 to the device on the last close() of a zone file if the zone is not full nor
 empty.
 
+Runtime sysfs attributes
+------------------------
+
+zonefs defines several sysfs attributes for mounted devices.  All attributes
+are user readable and can be found in the directory /sys/fs/zonefs/<dev>/,
+where <dev> is the name of the mounted zoned block device.
+
+The attributes defined are as follows.
+
+* **max_wro_seq_files**:  This attribute reports the maximum number of
+  sequential zone files that can be open for writing.  This number corresponds
+  to the maximum number of explicitly or implicitly open zones that the device
+  supports.  A value of 0 means that the device has no limit and that any zone
+  (any file) can be open for writing and written at any time, regardless of the
+  state of other zones.  When the *explicit-open* mount option is used, zonefs
+  will fail any open() system call requesting to open a sequential zone file for
+  writing when the number of sequential zone files already open for writing has
+  reached the *max_wro_seq_files* limit.
+* **nr_wro_seq_files**:  This attribute reports the current number of sequential
+  zone files open for writing.  When the "explicit-open" mount option is used,
+  this number can never exceed *max_wro_seq_files*.  If the *explicit-open*
+  mount option is not used, the reported number can be greater than
+  *max_wro_seq_files*.  In such case, it is the responsibility of the
+  application to not write simultaneously more than *max_wro_seq_files*
+  sequential zone files.  Failure to do so can result in write errors.
+* **max_active_seq_files**:  This attribute reports the maximum number of
+  sequential zone files that are in an active state, that is, sequential zone
+  files that are partially writen (not empty nor full) or that have a zone that
+  is explicitly open (which happens only if the *explicit-open* mount option is
+  used).  This number is always equal to the maximum number of active zones that
+  the device supports.  A value of 0 means that the mounted device has no limit
+  on the number of sequential zone files that can be active.
+* **nr_active_seq_files**:  This attributes reports the current number of
+  sequential zone files that are active. If *max_active_seq_files* is not 0,
+  then the value of *nr_active_seq_files* can never exceed the value of
+  *nr_active_seq_files*, regardless of the use of the *explicit-open* mount
+  option.
+
 Zonefs User Space Tools
 =======================
 

Documentation/kbuild/reproducible-builds.rst

@@ -99,10 +99,10 @@ unreproducible parts can be treated as sources:
 Structure randomisation
 -----------------------
 
-If you enable ``CONFIG_GCC_PLUGIN_RANDSTRUCT``, you will need to
-pre-generate the random seed in
-``scripts/gcc-plugins/randomize_layout_seed.h`` so the same value
-is used in rebuilds.
+If you enable ``CONFIG_RANDSTRUCT``, you will need to pre-generate
+the random seed in ``scripts/basic/randstruct.seed`` so the same
+value is used by each build. See ``scripts/gen-randstruct-seed.sh``
+for details.
 
 Debug info conflicts
 --------------------

Documentation/process/maintainer-tip.rst

@@ -437,6 +437,20 @@ in a private repository which allows interested people to easily pull the
 series for testing. The usual way to offer this is a git URL in the cover
 letter of the patch series.
 
+Testing
+^^^^^^^
+
+Code should be tested before submitting to the tip maintainers.  Anything
+other than minor changes should be built, booted and tested with
+comprehensive (and heavyweight) kernel debugging options enabled.
+
+These debugging options can be found in kernel/configs/x86_debug.config
+and can be added to an existing kernel config by running:
+
+	make x86_debug.config
+
+Some of these options are x86-specific and can be left out when testing
+on other architectures.
 
 Coding style notes
 ------------------

Documentation/security/index.rst

@@ -17,3 +17,4 @@ Security Documentation
    tpm/index
    digsig
    landlock
+   secrets/index

Documentation/security/secrets/coco.rst

@@ -0,0 +1,103 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+==============================
+Confidential Computing secrets
+==============================
+
+This document describes how Confidential Computing secret injection is handled
+from the firmware to the operating system, in the EFI driver and the efi_secret
+kernel module.
+
+
+Introduction
+============
+
+Confidential Computing (coco) hardware such as AMD SEV (Secure Encrypted
+Virtualization) allows guest owners to inject secrets into the VMs
+memory without the host/hypervisor being able to read them.  In SEV,
+secret injection is performed early in the VM launch process, before the
+guest starts running.
+
+The efi_secret kernel module allows userspace applications to access these
+secrets via securityfs.
+
+
+Secret data flow
+================
+
+The guest firmware may reserve a designated memory area for secret injection,
+and publish its location (base GPA and length) in the EFI configuration table
+under a ``LINUX_EFI_COCO_SECRET_AREA_GUID`` entry
+(``adf956ad-e98c-484c-ae11-b51c7d336447``).  This memory area should be marked
+by the firmware as ``EFI_RESERVED_TYPE``, and therefore the kernel should not
+be use it for its own purposes.
+
+During the VM's launch, the virtual machine manager may inject a secret to that
+area.  In AMD SEV and SEV-ES this is performed using the
+``KVM_SEV_LAUNCH_SECRET`` command (see [sev]_).  The strucutre of the injected
+Guest Owner secret data should be a GUIDed table of secret values; the binary
+format is described in ``drivers/virt/coco/efi_secret/efi_secret.c`` under
+"Structure of the EFI secret area".
+
+On kernel start, the kernel's EFI driver saves the location of the secret area
+(taken from the EFI configuration table) in the ``efi.coco_secret`` field.
+Later it checks if the secret area is populated: it maps the area and checks
+whether its content begins with ``EFI_SECRET_TABLE_HEADER_GUID``
+(``1e74f542-71dd-4d66-963e-ef4287ff173b``).  If the secret area is populated,
+the EFI driver will autoload the efi_secret kernel module, which exposes the
+secrets to userspace applications via securityfs.  The details of the
+efi_secret filesystem interface are in [secrets-coco-abi]_.
+
+
+Application usage example
+=========================
+
+Consider a guest performing computations on encrypted files.  The Guest Owner
+provides the decryption key (= secret) using the secret injection mechanism.
+The guest application reads the secret from the efi_secret filesystem and
+proceeds to decrypt the files into memory and then performs the needed
+computations on the content.
+
+In this example, the host can't read the files from the disk image
+because they are encrypted.  Host can't read the decryption key because
+it is passed using the secret injection mechanism (= secure channel).
+Host can't read the decrypted content from memory because it's a
+confidential (memory-encrypted) guest.
+
+Here is a simple example for usage of the efi_secret module in a guest
+to which an EFI secret area with 4 secrets was injected during launch::
+
+	# ls -la /sys/kernel/security/secrets/coco
+	total 0
+	drwxr-xr-x 2 root root 0 Jun 28 11:54 .
+	drwxr-xr-x 3 root root 0 Jun 28 11:54 ..
+	-r--r----- 1 root root 0 Jun 28 11:54 736870e5-84f0-4973-92ec-06879ce3da0b
+	-r--r----- 1 root root 0 Jun 28 11:54 83c83f7f-1356-4975-8b7e-d3a0b54312c6
+	-r--r----- 1 root root 0 Jun 28 11:54 9553f55d-3da2-43ee-ab5d-ff17f78864d2
+	-r--r----- 1 root root 0 Jun 28 11:54 e6f5a162-d67f-4750-a67c-5d065f2a9910
+
+	# hd /sys/kernel/security/secrets/coco/e6f5a162-d67f-4750-a67c-5d065f2a9910
+	00000000  74 68 65 73 65 2d 61 72  65 2d 74 68 65 2d 6b 61  |these-are-the-ka|
+	00000010  74 61 2d 73 65 63 72 65  74 73 00 01 02 03 04 05  |ta-secrets......|
+	00000020  06 07                                             |..|
+	00000022
+
+	# rm /sys/kernel/security/secrets/coco/e6f5a162-d67f-4750-a67c-5d065f2a9910
+
+	# ls -la /sys/kernel/security/secrets/coco
+	total 0
+	drwxr-xr-x 2 root root 0 Jun 28 11:55 .
+	drwxr-xr-x 3 root root 0 Jun 28 11:54 ..
+	-r--r----- 1 root root 0 Jun 28 11:54 736870e5-84f0-4973-92ec-06879ce3da0b
+	-r--r----- 1 root root 0 Jun 28 11:54 83c83f7f-1356-4975-8b7e-d3a0b54312c6
+	-r--r----- 1 root root 0 Jun 28 11:54 9553f55d-3da2-43ee-ab5d-ff17f78864d2
+
+
+References
+==========
+
+See [sev-api-spec]_ for more info regarding SEV ``LAUNCH_SECRET`` operation.
+
+.. [sev] Documentation/virt/kvm/amd-memory-encryption.rst
+.. [secrets-coco-abi] Documentation/ABI/testing/securityfs-secrets-coco
+.. [sev-api-spec] https://www.amd.com/system/files/TechDocs/55766_SEV-KM_API_Specification.pdf

Documentation/security/secrets/index.rst

@@ -0,0 +1,9 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+=====================
+Secrets documentation
+=====================
+
+.. toctree::
+
+   coco

Documentation/userspace-api/ioctl/cdrom.rst

@@ -718,6 +718,9 @@ CDROMPLAYBLK
 
 
 CDROMGETSPINDOWN
+	Obsolete, was ide-cd only
+
+
 	usage::
 
 	  char spindown;
@@ -736,6 +739,9 @@ CDROMGETSPINDOWN
 
 
 CDROMSETSPINDOWN
+	Obsolete, was ide-cd only
+
+
 	usage::
 
 	  char spindown

Documentation/userspace-api/seccomp_filter.rst

@@ -271,6 +271,16 @@ notifying process it will be replaced. The supervisor can also add an FD, and
 respond atomically by using the ``SECCOMP_ADDFD_FLAG_SEND`` flag and the return
 value will be the injected file descriptor number.
 
+The notifying process can be preempted, resulting in the notification being
+aborted. This can be problematic when trying to take actions on behalf of the
+notifying process that are long-running and typically retryable (mounting a
+filesytem). Alternatively, at filter installation time, the
+``SECCOMP_FILTER_FLAG_WAIT_KILLABLE_RECV`` flag can be set. This flag makes it
+such that when a user notification is received by the supervisor, the notifying
+process will ignore non-fatal signals until the response is sent. Signals that
+are sent prior to the notification being received by userspace are handled
+normally.
+
 It is worth noting that ``struct seccomp_data`` contains the values of register
 arguments to the syscall, but does not contain pointers to memory. The task's
 memory is accessible to suitably privileged traces via ``ptrace()`` or

Documentation/virt/coco/sev-guest.rst

@@ -0,0 +1,155 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+===================================================================
+The Definitive SEV Guest API Documentation
+===================================================================
+
+1. General description
+======================
+
+The SEV API is a set of ioctls that are used by the guest or hypervisor
+to get or set a certain aspect of the SEV virtual machine. The ioctls belong
+to the following classes:
+
+ - Hypervisor ioctls: These query and set global attributes which affect the
+   whole SEV firmware.  These ioctl are used by platform provisioning tools.
+
+ - Guest ioctls: These query and set attributes of the SEV virtual machine.
+
+2. API description
+==================
+
+This section describes ioctls that is used for querying the SEV guest report
+from the SEV firmware. For each ioctl, the following information is provided
+along with a description:
+
+  Technology:
+      which SEV technology provides this ioctl. SEV, SEV-ES, SEV-SNP or all.
+
+  Type:
+      hypervisor or guest. The ioctl can be used inside the guest or the
+      hypervisor.
+
+  Parameters:
+      what parameters are accepted by the ioctl.
+
+  Returns:
+      the return value.  General error numbers (-ENOMEM, -EINVAL)
+      are not detailed, but errors with specific meanings are.
+
+The guest ioctl should be issued on a file descriptor of the /dev/sev-guest device.
+The ioctl accepts struct snp_user_guest_request. The input and output structure is
+specified through the req_data and resp_data field respectively. If the ioctl fails
+to execute due to a firmware error, then fw_err code will be set otherwise the
+fw_err will be set to 0x00000000000000ff.
+
+The firmware checks that the message sequence counter is one greater than
+the guests message sequence counter. If guest driver fails to increment message
+counter (e.g. counter overflow), then -EIO will be returned.
+
+::
+
+        struct snp_guest_request_ioctl {
+                /* Message version number */
+                __u32 msg_version;
+
+                /* Request and response structure address */
+                __u64 req_data;
+                __u64 resp_data;
+
+                /* firmware error code on failure (see psp-sev.h) */
+                __u64 fw_err;
+        };
+
+2.1 SNP_GET_REPORT
+------------------
+
+:Technology: sev-snp
+:Type: guest ioctl
+:Parameters (in): struct snp_report_req
+:Returns (out): struct snp_report_resp on success, -negative on error
+
+The SNP_GET_REPORT ioctl can be used to query the attestation report from the
+SEV-SNP firmware. The ioctl uses the SNP_GUEST_REQUEST (MSG_REPORT_REQ) command
+provided by the SEV-SNP firmware to query the attestation report.
+
+On success, the snp_report_resp.data will contains the report. The report
+contain the format described in the SEV-SNP specification. See the SEV-SNP
+specification for further details.
+
+2.2 SNP_GET_DERIVED_KEY
+-----------------------
+:Technology: sev-snp
+:Type: guest ioctl
+:Parameters (in): struct snp_derived_key_req
+:Returns (out): struct snp_derived_key_resp on success, -negative on error
+
+The SNP_GET_DERIVED_KEY ioctl can be used to get a key derive from a root key.
+The derived key can be used by the guest for any purpose, such as sealing keys
+or communicating with external entities.
+
+The ioctl uses the SNP_GUEST_REQUEST (MSG_KEY_REQ) command provided by the
+SEV-SNP firmware to derive the key. See SEV-SNP specification for further details
+on the various fields passed in the key derivation request.
+
+On success, the snp_derived_key_resp.data contains the derived key value. See
+the SEV-SNP specification for further details.
+
+
+2.3 SNP_GET_EXT_REPORT
+----------------------
+:Technology: sev-snp
+:Type: guest ioctl
+:Parameters (in/out): struct snp_ext_report_req
+:Returns (out): struct snp_report_resp on success, -negative on error
+
+The SNP_GET_EXT_REPORT ioctl is similar to the SNP_GET_REPORT. The difference is
+related to the additional certificate data that is returned with the report.
+The certificate data returned is being provided by the hypervisor through the
+SNP_SET_EXT_CONFIG.
+
+The ioctl uses the SNP_GUEST_REQUEST (MSG_REPORT_REQ) command provided by the SEV-SNP
+firmware to get the attestation report.
+
+On success, the snp_ext_report_resp.data will contain the attestation report
+and snp_ext_report_req.certs_address will contain the certificate blob. If the
+length of the blob is smaller than expected then snp_ext_report_req.certs_len will
+be updated with the expected value.
+
+See GHCB specification for further detail on how to parse the certificate blob.
+
+3. SEV-SNP CPUID Enforcement
+============================
+
+SEV-SNP guests can access a special page that contains a table of CPUID values
+that have been validated by the PSP as part of the SNP_LAUNCH_UPDATE firmware
+command. It provides the following assurances regarding the validity of CPUID
+values:
+
+ - Its address is obtained via bootloader/firmware (via CC blob), and those
+   binaries will be measured as part of the SEV-SNP attestation report.
+ - Its initial state will be encrypted/pvalidated, so attempts to modify
+   it during run-time will result in garbage being written, or #VC exceptions
+   being generated due to changes in validation state if the hypervisor tries
+   to swap the backing page.
+ - Attempts to bypass PSP checks by the hypervisor by using a normal page, or
+   a non-CPUID encrypted page will change the measurement provided by the
+   SEV-SNP attestation report.
+ - The CPUID page contents are *not* measured, but attempts to modify the
+   expected contents of a CPUID page as part of guest initialization will be
+   gated by the PSP CPUID enforcement policy checks performed on the page
+   during SNP_LAUNCH_UPDATE, and noticeable later if the guest owner
+   implements their own checks of the CPUID values.
+
+It is important to note that this last assurance is only useful if the kernel
+has taken care to make use of the SEV-SNP CPUID throughout all stages of boot.
+Otherwise, guest owner attestation provides no assurance that the kernel wasn't
+fed incorrect values at some point during boot.
+
+
+Reference
+---------
+
+SEV-SNP and GHCB specification: developer.amd.com/sev
+
+The driver is based on SEV-SNP firmware spec 0.9 and GHCB spec version 2.0.

Documentation/virt/index.rst

@@ -13,6 +13,7 @@ Linux Virtualization Support
    guest-halt-polling
    ne_overview
    acrn/index
+   coco/sev-guest
 
 .. only:: html and subproject
 

Documentation/virt/kvm/api.rst

@@ -5713,6 +5713,8 @@ affect the device's behavior. Current defined flags::
   #define KVM_RUN_X86_SMM     (1 << 0)
   /* x86, set if bus lock detected in VM */
   #define KVM_RUN_BUS_LOCK    (1 << 1)
+  /* arm64, set for KVM_EXIT_DEBUG */
+  #define KVM_DEBUG_ARCH_HSR_HIGH_VALID  (1 << 0)
 
 ::
 

Documentation/x86/cpuinfo.rst

@@ -140,9 +140,8 @@ from #define X86_FEATURE_UMIP (16*32 + 2).
 
 In addition, there exists a variety of custom command-line parameters that
 disable specific features. The list of parameters includes, but is not limited
-to, nofsgsbase, nosmap, and nosmep. 5-level paging can also be disabled using
-"no5lvl". SMAP and SMEP are disabled with the aforementioned parameters,
-respectively.
+to, nofsgsbase, nosgx, noxsave, etc. 5-level paging can also be disabled using
+"no5lvl".
 
 e: The feature was known to be non-functional.
 ----------------------------------------------

Documentation/x86/ifs.rst

@@ -0,0 +1,2 @@
+.. SPDX-License-Identifier: GPL-2.0
+.. kernel-doc:: drivers/platform/x86/intel/ifs/ifs.h

Documentation/x86/index.rst

@@ -26,6 +26,7 @@ x86-specific Documentation
    intel_txt
    amd-memory-encryption
    amd_hsmp
+   tdx
    pti
    mds
    microcode
@@ -35,6 +36,7 @@ x86-specific Documentation
    usb-legacy-support
    i386/index
    x86_64/index
+   ifs
    sva
    sgx
    features

Documentation/x86/tdx.rst

@@ -0,0 +1,218 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+=====================================
+Intel Trust Domain Extensions (TDX)
+=====================================
+
+Intel's Trust Domain Extensions (TDX) protect confidential guest VMs from
+the host and physical attacks by isolating the guest register state and by
+encrypting the guest memory. In TDX, a special module running in a special
+mode sits between the host and the guest and manages the guest/host
+separation.
+
+Since the host cannot directly access guest registers or memory, much
+normal functionality of a hypervisor must be moved into the guest. This is
+implemented using a Virtualization Exception (#VE) that is handled by the
+guest kernel. A #VE is handled entirely inside the guest kernel, but some
+require the hypervisor to be consulted.
+
+TDX includes new hypercall-like mechanisms for communicating from the
+guest to the hypervisor or the TDX module.
+
+New TDX Exceptions
+==================
+
+TDX guests behave differently from bare-metal and traditional VMX guests.
+In TDX guests, otherwise normal instructions or memory accesses can cause
+#VE or #GP exceptions.
+
+Instructions marked with an '*' conditionally cause exceptions.  The
+details for these instructions are discussed below.
+
+Instruction-based #VE
+---------------------
+
+- Port I/O (INS, OUTS, IN, OUT)
+- HLT
+- MONITOR, MWAIT
+- WBINVD, INVD
+- VMCALL
+- RDMSR*,WRMSR*
+- CPUID*
+
+Instruction-based #GP
+---------------------
+
+- All VMX instructions: INVEPT, INVVPID, VMCLEAR, VMFUNC, VMLAUNCH,
+  VMPTRLD, VMPTRST, VMREAD, VMRESUME, VMWRITE, VMXOFF, VMXON
+- ENCLS, ENCLU
+- GETSEC
+- RSM
+- ENQCMD
+- RDMSR*,WRMSR*
+
+RDMSR/WRMSR Behavior
+--------------------
+
+MSR access behavior falls into three categories:
+
+- #GP generated
+- #VE generated
+- "Just works"
+
+In general, the #GP MSRs should not be used in guests.  Their use likely
+indicates a bug in the guest.  The guest may try to handle the #GP with a
+hypercall but it is unlikely to succeed.
+
+The #VE MSRs are typically able to be handled by the hypervisor.  Guests
+can make a hypercall to the hypervisor to handle the #VE.
+
+The "just works" MSRs do not need any special guest handling.  They might
+be implemented by directly passing through the MSR to the hardware or by
+trapping and handling in the TDX module.  Other than possibly being slow,
+these MSRs appear to function just as they would on bare metal.
+
+CPUID Behavior
+--------------
+
+For some CPUID leaves and sub-leaves, the virtualized bit fields of CPUID
+return values (in guest EAX/EBX/ECX/EDX) are configurable by the
+hypervisor. For such cases, the Intel TDX module architecture defines two
+virtualization types:
+
+- Bit fields for which the hypervisor controls the value seen by the guest
+  TD.
+
+- Bit fields for which the hypervisor configures the value such that the
+  guest TD either sees their native value or a value of 0.  For these bit
+  fields, the hypervisor can mask off the native values, but it can not
+  turn *on* values.
+
+A #VE is generated for CPUID leaves and sub-leaves that the TDX module does
+not know how to handle. The guest kernel may ask the hypervisor for the
+value with a hypercall.
+
+#VE on Memory Accesses
+======================
+
+There are essentially two classes of TDX memory: private and shared.
+Private memory receives full TDX protections.  Its content is protected
+against access from the hypervisor.  Shared memory is expected to be
+shared between guest and hypervisor and does not receive full TDX
+protections.
+
+A TD guest is in control of whether its memory accesses are treated as
+private or shared.  It selects the behavior with a bit in its page table
+entries.  This helps ensure that a guest does not place sensitive
+information in shared memory, exposing it to the untrusted hypervisor.
+
+#VE on Shared Memory
+--------------------
+
+Access to shared mappings can cause a #VE.  The hypervisor ultimately
+controls whether a shared memory access causes a #VE, so the guest must be
+careful to only reference shared pages it can safely handle a #VE.  For
+instance, the guest should be careful not to access shared memory in the
+#VE handler before it reads the #VE info structure (TDG.VP.VEINFO.GET).
+
+Shared mapping content is entirely controlled by the hypervisor. The guest
+should only use shared mappings for communicating with the hypervisor.
+Shared mappings must never be used for sensitive memory content like kernel
+stacks.  A good rule of thumb is that hypervisor-shared memory should be
+treated the same as memory mapped to userspace.  Both the hypervisor and
+userspace are completely untrusted.
+
+MMIO for virtual devices is implemented as shared memory.  The guest must
+be careful not to access device MMIO regions unless it is also prepared to
+handle a #VE.
+
+#VE on Private Pages
+--------------------
+
+An access to private mappings can also cause a #VE.  Since all kernel
+memory is also private memory, the kernel might theoretically need to
+handle a #VE on arbitrary kernel memory accesses.  This is not feasible, so
+TDX guests ensure that all guest memory has been "accepted" before memory
+is used by the kernel.
+
+A modest amount of memory (typically 512M) is pre-accepted by the firmware
+before the kernel runs to ensure that the kernel can start up without
+being subjected to a #VE.
+
+The hypervisor is permitted to unilaterally move accepted pages to a
+"blocked" state. However, if it does this, page access will not generate a
+#VE.  It will, instead, cause a "TD Exit" where the hypervisor is required
+to handle the exception.
+
+Linux #VE handler
+=================
+
+Just like page faults or #GP's, #VE exceptions can be either handled or be
+fatal.  Typically, an unhandled userspace #VE results in a SIGSEGV.
+An unhandled kernel #VE results in an oops.
+
+Handling nested exceptions on x86 is typically nasty business.  A #VE
+could be interrupted by an NMI which triggers another #VE and hilarity
+ensues.  The TDX #VE architecture anticipated this scenario and includes a
+feature to make it slightly less nasty.
+
+During #VE handling, the TDX module ensures that all interrupts (including
+NMIs) are blocked.  The block remains in place until the guest makes a
+TDG.VP.VEINFO.GET TDCALL.  This allows the guest to control when interrupts
+or a new #VE can be delivered.
+
+However, the guest kernel must still be careful to avoid potential
+#VE-triggering actions (discussed above) while this block is in place.
+While the block is in place, any #VE is elevated to a double fault (#DF)
+which is not recoverable.
+
+MMIO handling
+=============
+
+In non-TDX VMs, MMIO is usually implemented by giving a guest access to a
+mapping which will cause a VMEXIT on access, and then the hypervisor
+emulates the access.  That is not possible in TDX guests because VMEXIT
+will expose the register state to the host. TDX guests don't trust the host
+and can't have their state exposed to the host.
+
+In TDX, MMIO regions typically trigger a #VE exception in the guest.  The
+guest #VE handler then emulates the MMIO instruction inside the guest and
+converts it into a controlled TDCALL to the host, rather than exposing
+guest state to the host.
+
+MMIO addresses on x86 are just special physical addresses. They can
+theoretically be accessed with any instruction that accesses memory.
+However, the kernel instruction decoding method is limited. It is only
+designed to decode instructions like those generated by io.h macros.
+
+MMIO access via other means (like structure overlays) may result in an
+oops.
+
+Shared Memory Conversions
+=========================
+
+All TDX guest memory starts out as private at boot.  This memory can not
+be accessed by the hypervisor.  However, some kernel users like device
+drivers might have a need to share data with the hypervisor.  To do this,
+memory must be converted between shared and private.  This can be
+accomplished using some existing memory encryption helpers:
+
+ * set_memory_decrypted() converts a range of pages to shared.
+ * set_memory_encrypted() converts memory back to private.
+
+Device drivers are the primary user of shared memory, but there's no need
+to touch every driver. DMA buffers and ioremap() do the conversions
+automatically.
+
+TDX uses SWIOTLB for most DMA allocations. The SWIOTLB buffer is
+converted to shared on boot.
+
+For coherent DMA allocation, the DMA buffer gets converted on the
+allocation. Check force_dma_unencrypted() for details.
+
+References
+==========
+
+TDX reference material is collected here:
+
+https://www.intel.com/content/www/us/en/developer/articles/technical/intel-trust-domain-extensions.html

Documentation/x86/x86_64/boot-options.rst

@@ -157,15 +157,6 @@ Rebooting
      newer BIOS, or newer board) using this option will ignore the built-in
      quirk table, and use the generic default reboot actions.
 
-Non Executable Mappings
-=======================
-
-  noexec=on|off
-    on
-      Enable(default)
-    off
-      Disable
-
 NUMA
 ====
 
@@ -310,3 +301,17 @@ Miscellaneous
     Do not use GB pages for kernel direct mappings.
   gbpages
     Use GB pages for kernel direct mappings.
+
+
+AMD SEV (Secure Encrypted Virtualization)
+=========================================
+Options relating to AMD SEV, specified via the following format:
+
+::
+
+   sev=option1[,option2]
+
+The available options are:
+
+   debug
+     Enable debug messages.

Documentation/x86/zero-page.rst

@@ -19,6 +19,7 @@ Offset/Size	Proto	Name			Meaning
 058/008		ALL	tboot_addr      	Physical address of tboot shared page
 060/010		ALL	ist_info		Intel SpeedStep (IST) BIOS support information
 						(struct ist_info)
+070/008		ALL	acpi_rsdp_addr		Physical address of ACPI RSDP table
 080/010		ALL	hd0_info		hd0 disk parameter, OBSOLETE!!
 090/010		ALL	hd1_info		hd1 disk parameter, OBSOLETE!!
 0A0/010		ALL	sys_desc_table		System description table (struct sys_desc_table),
@@ -27,6 +28,7 @@ Offset/Size	Proto	Name			Meaning
 0C0/004		ALL	ext_ramdisk_image	ramdisk_image high 32bits
 0C4/004		ALL	ext_ramdisk_size	ramdisk_size high 32bits
 0C8/004		ALL	ext_cmd_line_ptr	cmd_line_ptr high 32bits
+13C/004		ALL	cc_blob_address		Physical address of Confidential Computing blob
 140/080		ALL	edid_info		Video mode setup (struct edid_info)
 1C0/020		ALL	efi_info		EFI 32 information (struct efi_info)
 1E0/004		ALL	alt_mem_k		Alternative mem check, in KB

MAINTAINERS

@@ -7385,7 +7385,6 @@ L:	linux-mm@kvack.org
 S:	Supported
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/kees/linux.git for-next/execve
 F:	arch/alpha/kernel/binfmt_loader.c
-F:	arch/x86/ia32/ia32_aout.c
 F:	fs/*binfmt_*.c
 F:	fs/exec.c
 F:	include/linux/binfmts.h
@@ -9871,6 +9870,14 @@ B:	https://bugzilla.kernel.org
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/lenb/linux.git
 F:	drivers/idle/intel_idle.c
 
+INTEL IN FIELD SCAN (IFS) DEVICE
+M:	Jithu Joseph <jithu.joseph@intel.com>
+R:	Ashok Raj <ashok.raj@intel.com>
+R:	Tony Luck <tony.luck@intel.com>
+S:	Maintained
+F:	drivers/platform/x86/intel/ifs
+F:	include/trace/events/intel_ifs.h
+
 INTEL INTEGRATED SENSOR HUB DRIVER
 M:	Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
 M:	Jiri Kosina <jikos@kernel.org>
@@ -17524,6 +17531,7 @@ R:	Steven Rostedt <rostedt@goodmis.org> (SCHED_FIFO/SCHED_RR)
 R:	Ben Segall <bsegall@google.com> (CONFIG_CFS_BANDWIDTH)
 R:	Mel Gorman <mgorman@suse.de> (CONFIG_NUMA_BALANCING)
 R:	Daniel Bristot de Oliveira <bristot@redhat.com> (SCHED_DEADLINE)
+R:	Valentin Schneider <vschneid@redhat.com> (TOPOLOGY)
 L:	linux-kernel@vger.kernel.org
 S:	Maintained
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git sched/core

Makefile

@@ -1037,6 +1037,7 @@ include-$(CONFIG_KASAN)		+= scripts/Makefile.kasan
 include-$(CONFIG_KCSAN)		+= scripts/Makefile.kcsan
 include-$(CONFIG_UBSAN)		+= scripts/Makefile.ubsan
 include-$(CONFIG_KCOV)		+= scripts/Makefile.kcov
+include-$(CONFIG_RANDSTRUCT)	+= scripts/Makefile.randstruct
 include-$(CONFIG_GCC_PLUGINS)	+= scripts/Makefile.gcc-plugins
 
 include $(addprefix $(srctree)/, $(include-y))
@@ -1339,7 +1340,7 @@ install: sub_make_done :=
 # ---------------------------------------------------------------------------
 # Tools
 
-ifdef CONFIG_STACK_VALIDATION
+ifdef CONFIG_OBJTOOL
 prepare: tools/objtool
 endif
 

arch/Kconfig

@@ -24,6 +24,13 @@ config KEXEC_ELF
 config HAVE_IMA_KEXEC
 	bool
 
+config ARCH_HAS_SUBPAGE_FAULTS
+	bool
+	help
+	  Select if the architecture can check permissions at sub-page
+	  granularity (e.g. arm64 MTE). The probe_user_*() functions
+	  must be implemented.
+
 config HOTPLUG_SMT
 	bool
 
@@ -35,6 +42,7 @@ config KPROBES
 	depends on MODULES
 	depends on HAVE_KPROBES
 	select KALLSYMS
+	select TASKS_RCU if PREEMPTION
 	help
 	  Kprobes allows you to trap at almost any kernel address and
 	  execute a callback function.  register_kprobe() establishes
@@ -46,6 +54,7 @@ config JUMP_LABEL
 	bool "Optimize very unlikely/likely branches"
 	depends on HAVE_ARCH_JUMP_LABEL
 	depends on CC_HAS_ASM_GOTO
+	select OBJTOOL if HAVE_JUMP_LABEL_HACK
 	help
 	 This option enables a transparent branch optimization that
 	 makes certain almost-always-true or almost-always-false branch
@@ -723,10 +732,7 @@ config ARCH_SUPPORTS_CFI_CLANG
 config CFI_CLANG
 	bool "Use Clang's Control Flow Integrity (CFI)"
 	depends on LTO_CLANG && ARCH_SUPPORTS_CFI_CLANG
-	# Clang >= 12:
-	# - https://bugs.llvm.org/show_bug.cgi?id=46258
-	# - https://bugs.llvm.org/show_bug.cgi?id=47479
-	depends on CLANG_VERSION >= 120000
+	depends on CLANG_VERSION >= 140000
 	select KALLSYMS
 	help
 	  This option enables Clang’s forward-edge Control Flow Integrity
@@ -1026,11 +1032,23 @@ config ARCH_WANT_DEFAULT_TOPDOWN_MMAP_LAYOUT
 	depends on MMU
 	select ARCH_HAS_ELF_RANDOMIZE
 
+config HAVE_OBJTOOL
+	bool
+
+config HAVE_JUMP_LABEL_HACK
+	bool
+
+config HAVE_NOINSTR_HACK
+	bool
+
+config HAVE_NOINSTR_VALIDATION
+	bool
+
 config HAVE_STACK_VALIDATION
 	bool
 	help
-	  Architecture supports the 'objtool check' host tool command, which
-	  performs compile-time stack metadata validation.
+	  Architecture supports objtool compile-time frame pointer rule
+	  validation.
 
 config HAVE_RELIABLE_STACKTRACE
 	bool
@@ -1300,6 +1318,7 @@ config HAVE_STATIC_CALL
 config HAVE_STATIC_CALL_INLINE
 	bool
 	depends on HAVE_STATIC_CALL
+	select OBJTOOL
 
 config HAVE_PREEMPT_DYNAMIC
 	bool

arch/alpha/include/asm/timex.h

@@ -28,5 +28,6 @@ static inline cycles_t get_cycles (void)
 	__asm__ __volatile__ ("rpcc %0" : "=r"(ret));
 	return ret;
 }
+#define get_cycles get_cycles
 
 #endif

arch/arm/Kconfig

@@ -972,6 +972,17 @@ config ARM_ERRATA_764369
 	  relevant cache maintenance functions and sets a specific bit
 	  in the diagnostic control register of the SCU.
 
+config ARM_ERRATA_764319
+	bool "ARM errata: Read to DBGPRSR and DBGOSLSR may generate Undefined instruction"
+	depends on CPU_V7
+	help
+	  This option enables the workaround for the 764319 Cortex A-9 erratum.
+	  CP14 read accesses to the DBGPRSR and DBGOSLSR registers generate an
+	  unexpected Undefined Instruction exception when the DBGSWENABLE
+	  external pin is set to 0, even when the CP14 accesses are performed
+	  from a privileged mode. This work around catches the exception in a
+	  way the kernel does not stop execution.
+
 config ARM_ERRATA_775420
        bool "ARM errata: A data cache maintenance operation which aborts, might lead to deadlock"
        depends on CPU_V7

arch/arm/configs/lpc18xx_defconfig

@@ -30,7 +30,6 @@ CONFIG_ARM_APPENDED_DTB=y
 # CONFIG_BLK_DEV_BSG is not set
 CONFIG_BINFMT_FLAT=y
 CONFIG_BINFMT_ZFLAT=y
-CONFIG_BINFMT_SHARED_FLAT=y
 # CONFIG_COREDUMP is not set
 CONFIG_NET=y
 CONFIG_PACKET=y

arch/arm/configs/mps2_defconfig

@@ -23,7 +23,6 @@ CONFIG_PREEMPT_VOLUNTARY=y
 CONFIG_ZBOOT_ROM_TEXT=0x0
 CONFIG_ZBOOT_ROM_BSS=0x0
 CONFIG_BINFMT_FLAT=y
-CONFIG_BINFMT_SHARED_FLAT=y
 # CONFIG_COREDUMP is not set
 # CONFIG_SUSPEND is not set
 CONFIG_NET=y

arch/arm/configs/stm32_defconfig

@@ -28,7 +28,6 @@ CONFIG_ZBOOT_ROM_BSS=0x0
 CONFIG_XIP_KERNEL=y
 CONFIG_XIP_PHYS_ADDR=0x08008000
 CONFIG_BINFMT_FLAT=y
-CONFIG_BINFMT_SHARED_FLAT=y
 # CONFIG_COREDUMP is not set
 CONFIG_DEVTMPFS=y
 CONFIG_DEVTMPFS_MOUNT=y

arch/arm/configs/vf610m4_defconfig

@@ -18,7 +18,6 @@ CONFIG_XIP_KERNEL=y
 CONFIG_XIP_PHYS_ADDR=0x0f000080
 CONFIG_BINFMT_FLAT=y
 CONFIG_BINFMT_ZFLAT=y
-CONFIG_BINFMT_SHARED_FLAT=y
 # CONFIG_SUSPEND is not set
 # CONFIG_UEVENT_HELPER is not set
 # CONFIG_STANDALONE is not set

arch/arm/include/asm/arch_gicv3.h

@@ -48,6 +48,7 @@ static inline u32 read_ ## a64(void)		\
 	return read_sysreg(a32); 		\
 }						\
 
+CPUIF_MAP(ICC_EOIR1, ICC_EOIR1_EL1)
 CPUIF_MAP(ICC_PMR, ICC_PMR_EL1)
 CPUIF_MAP(ICC_AP0R0, ICC_AP0R0_EL1)
 CPUIF_MAP(ICC_AP0R1, ICC_AP0R1_EL1)
@@ -63,12 +64,6 @@ CPUIF_MAP(ICC_AP1R3, ICC_AP1R3_EL1)
 
 /* Low-level accessors */
 
-static inline void gic_write_eoir(u32 irq)
-{
-	write_sysreg(irq, ICC_EOIR1);
-	isb();
-}
-
 static inline void gic_write_dir(u32 val)
 {
 	write_sysreg(val, ICC_DIR);

arch/arm/include/asm/assembler.h

@@ -666,12 +666,11 @@ THUMB(	orr	\reg , \reg , #PSR_T_BIT	)
 	__adldst_l	str, \src, \sym, \tmp, \cond
 	.endm
 
-	.macro		__ldst_va, op, reg, tmp, sym, cond
+	.macro		__ldst_va, op, reg, tmp, sym, cond, offset
 #if __LINUX_ARM_ARCH__ >= 7 || \
     !defined(CONFIG_ARM_HAS_GROUP_RELOCS) || \
     (defined(MODULE) && defined(CONFIG_ARM_MODULE_PLTS))
 	mov_l		\tmp, \sym, \cond
-	\op\cond	\reg, [\tmp]
 #else
 	/*
 	 * Avoid a literal load, by emitting a sequence of ADD/LDR instructions
@@ -683,24 +682,29 @@ THUMB(	orr	\reg , \reg , #PSR_T_BIT	)
 	.reloc		.L0_\@, R_ARM_ALU_PC_G0_NC, \sym
 	.reloc		.L1_\@, R_ARM_ALU_PC_G1_NC, \sym
 	.reloc		.L2_\@, R_ARM_LDR_PC_G2, \sym
-.L0_\@: sub\cond	\tmp, pc, #8
-.L1_\@: sub\cond	\tmp, \tmp, #4
-.L2_\@: \op\cond	\reg, [\tmp, #0]
+.L0_\@: sub\cond	\tmp, pc, #8 - \offset
+.L1_\@: sub\cond	\tmp, \tmp, #4 - \offset
+.L2_\@:
 #endif
+	\op\cond	\reg, [\tmp, #\offset]
 	.endm
 
 	/*
 	 * ldr_va - load a 32-bit word from the virtual address of \sym
 	 */
-	.macro		ldr_va, rd:req, sym:req, cond
-	__ldst_va	ldr, \rd, \rd, \sym, \cond
+	.macro		ldr_va, rd:req, sym:req, cond, tmp, offset=0
+	.ifnb		\tmp
+	__ldst_va	ldr, \rd, \tmp, \sym, \cond, \offset
+	.else
+	__ldst_va	ldr, \rd, \rd, \sym, \cond, \offset
+	.endif
 	.endm
 
 	/*
 	 * str_va - store a 32-bit word to the virtual address of \sym
 	 */
 	.macro		str_va, rn:req, sym:req, tmp:req, cond
-	__ldst_va	str, \rn, \tmp, \sym, \cond
+	__ldst_va	str, \rn, \tmp, \sym, \cond, 0
 	.endm
 
 	/*
@@ -727,9 +731,11 @@ THUMB(	orr	\reg , \reg , #PSR_T_BIT	)
 	 *		  are permitted to overlap with 'rd' if != sp
 	 */
 	.macro		ldr_this_cpu, rd:req, sym:req, t1:req, t2:req
-#if __LINUX_ARM_ARCH__ >= 7 || \
-    !defined(CONFIG_ARM_HAS_GROUP_RELOCS) || \
-    (defined(MODULE) && defined(CONFIG_ARM_MODULE_PLTS))
+#ifndef CONFIG_SMP
+	ldr_va		\rd, \sym, tmp=\t1
+#elif __LINUX_ARM_ARCH__ >= 7 || \
+      !defined(CONFIG_ARM_HAS_GROUP_RELOCS) || \
+      (defined(MODULE) && defined(CONFIG_ARM_MODULE_PLTS))
 	this_cpu_offset	\t1
 	mov_l		\t2, \sym
 	ldr		\rd, [\t1, \t2]

arch/arm/include/asm/module.h

@@ -3,20 +3,10 @@
 #define _ASM_ARM_MODULE_H
 
 #include <asm-generic/module.h>
-
-struct unwind_table;
+#include <asm/unwind.h>
 
 #ifdef CONFIG_ARM_UNWIND
-enum {
-	ARM_SEC_INIT,
-	ARM_SEC_DEVINIT,
-	ARM_SEC_CORE,
-	ARM_SEC_EXIT,
-	ARM_SEC_DEVEXIT,
-	ARM_SEC_HOT,
-	ARM_SEC_UNLIKELY,
-	ARM_SEC_MAX,
-};
+#define ELF_SECTION_UNWIND 0x70000001
 #endif
 
 #define PLT_ENT_STRIDE		L1_CACHE_BYTES
@@ -36,7 +26,8 @@ struct mod_plt_sec {
 
 struct mod_arch_specific {
 #ifdef CONFIG_ARM_UNWIND
-	struct unwind_table *unwind[ARM_SEC_MAX];
+	struct list_head unwind_list;
+	struct unwind_table *init_table;
 #endif
 #ifdef CONFIG_ARM_MODULE_PLTS
 	struct mod_plt_sec	core;

arch/arm/include/asm/timex.h

@@ -11,5 +11,6 @@
 
 typedef unsigned long cycles_t;
 #define get_cycles()	({ cycles_t c; read_current_timer(&c) ? 0 : c; })
+#define random_get_entropy() (((unsigned long)get_cycles()) ?: random_get_entropy_fallback())
 
 #endif

arch/arm/include/asm/unwind.h

@@ -24,6 +24,7 @@ struct unwind_idx {
 
 struct unwind_table {
 	struct list_head list;
+	struct list_head mod_list;
 	const struct unwind_idx *start;
 	const struct unwind_idx *origin;
 	const struct unwind_idx *stop;

arch/arm/kernel/entry-armv.S

@@ -61,9 +61,8 @@
 	.macro	pabt_helper
 	@ PABORT handler takes pt_regs in r2, fault address in r4 and psr in r5
 #ifdef MULTI_PABORT
-	ldr	ip, .LCprocfns
-	mov	lr, pc
-	ldr	pc, [ip, #PROCESSOR_PABT_FUNC]
+	ldr_va	ip, processor, offset=PROCESSOR_PABT_FUNC
+	bl_r	ip
 #else
 	bl	CPU_PABORT_HANDLER
 #endif
@@ -82,9 +81,8 @@
 	@ the fault status register in r1.  r9 must be preserved.
 	@
 #ifdef MULTI_DABORT
-	ldr	ip, .LCprocfns
-	mov	lr, pc
-	ldr	pc, [ip, #PROCESSOR_DABT_FUNC]
+	ldr_va	ip, processor, offset=PROCESSOR_DABT_FUNC
+	bl_r	ip
 #else
 	bl	CPU_DABORT_HANDLER
 #endif
@@ -302,16 +300,6 @@ __fiq_svc:
  UNWIND(.fnend		)
 ENDPROC(__fiq_svc)
 
-	.align	5
-.LCcralign:
-	.word	cr_alignment
-#ifdef MULTI_DABORT
-.LCprocfns:
-	.word	processor
-#endif
-.LCfp:
-	.word	fp_enter
-
 /*
  * Abort mode handlers
  */
@@ -370,7 +358,7 @@ ENDPROC(__fiq_abt)
  THUMB(	stmia	sp, {r0 - r12}	)
 
  ATRAP(	mrc	p15, 0, r7, c1, c0, 0)
- ATRAP(	ldr	r8, .LCcralign)
+ ATRAP(	ldr_va	r8, cr_alignment)
 
 	ldmia	r0, {r3 - r5}
 	add	r0, sp, #S_PC		@ here for interlock avoidance
@@ -379,8 +367,6 @@ ENDPROC(__fiq_abt)
 	str	r3, [sp]		@ save the "real" r0 copied
 					@ from the exception stack
 
- ATRAP(	ldr	r8, [r8, #0])
-
 	@
 	@ We are now ready to fill in the remaining blanks on the stack:
 	@
@@ -505,9 +491,7 @@ __und_usr_thumb:
  */
 #if __LINUX_ARM_ARCH__ < 7
 /* If the target CPU may not be Thumb-2-capable, a run-time check is needed: */
-#define NEED_CPU_ARCHITECTURE
-	ldr	r5, .LCcpu_architecture
-	ldr	r5, [r5]
+	ldr_va	r5, cpu_architecture
 	cmp	r5, #CPU_ARCH_ARMv7
 	blo	__und_usr_fault_16		@ 16bit undefined instruction
 /*
@@ -654,12 +638,6 @@ call_fpe:
 	ret.w	lr				@ CP#14 (Debug)
 	ret.w	lr				@ CP#15 (Control)
 
-#ifdef NEED_CPU_ARCHITECTURE
-	.align	2
-.LCcpu_architecture:
-	.word	__cpu_architecture
-#endif
-
 #ifdef CONFIG_NEON
 	.align	6
 
@@ -685,9 +663,8 @@ call_fpe:
 #endif
 
 do_fpe:
-	ldr	r4, .LCfp
 	add	r10, r10, #TI_FPSTATE		@ r10 = workspace
-	ldr	pc, [r4]			@ Call FP module USR entry point
+	ldr_va	pc, fp_enter, tmp=r4		@ Call FP module USR entry point
 
 /*
  * The FP module is called with these registers set:
@@ -1101,6 +1078,12 @@ __kuser_helper_end:
  */
 	.macro	vector_stub, name, mode, correction=0
 	.align	5
+#ifdef CONFIG_HARDEN_BRANCH_HISTORY
+vector_bhb_bpiall_\name:
+	mcr	p15, 0, r0, c7, c5, 6	@ BPIALL
+	@ isb not needed due to "movs pc, lr" in the vector stub
+	@ which gives a "context synchronisation".
+#endif
 
 vector_\name:
 	.if \correction
@@ -1111,7 +1094,8 @@ vector_\name:
 	stmia	sp, {r0, lr}		@ save r0, lr
 
 	@ Save spsr_<exception> (parent CPSR)
-2:	mrs	lr, spsr
+.Lvec_\name:
+	mrs	lr, spsr
 	str	lr, [sp, #8]		@ save spsr
 
 	@
@@ -1148,25 +1132,11 @@ vector_bhb_loop8_\name:
 3:	W(b)	. + 4
 	subs	r0, r0, #1
 	bne	3b
-	dsb
-	isb
-	b	2b
-ENDPROC(vector_bhb_loop8_\name)
-
-vector_bhb_bpiall_\name:
-	.if \correction
-	sub	lr, lr, #\correction
-	.endif
-
-	@ Save r0, lr_<exception> (parent PC)
-	stmia	sp, {r0, lr}
-
-	@ bhb workaround
-	mcr	p15, 0, r0, c7, c5, 6	@ BPIALL
+	dsb	nsh
 	@ isb not needed due to "movs pc, lr" in the vector stub
 	@ which gives a "context synchronisation".
-	b	2b
-ENDPROC(vector_bhb_bpiall_\name)
+	b	.Lvec_\name
+ENDPROC(vector_bhb_loop8_\name)
 	.previous
 #endif
 
@@ -1176,10 +1146,15 @@ ENDPROC(vector_bhb_bpiall_\name)
 	.endm
 
 	.section .stubs, "ax", %progbits
-	@ This must be the first word
+	@ These need to remain at the start of the section so that
+	@ they are in range of the 'SWI' entries in the vector tables
+	@ located 4k down.
+.L__vector_swi:
 	.word	vector_swi
 #ifdef CONFIG_HARDEN_BRANCH_HISTORY
+.L__vector_bhb_loop8_swi:
 	.word	vector_bhb_loop8_swi
+.L__vector_bhb_bpiall_swi:
 	.word	vector_bhb_bpiall_swi
 #endif
 
@@ -1322,10 +1297,11 @@ vector_addrexcptn:
 	.globl	vector_fiq
 
 	.section .vectors, "ax", %progbits
-.L__vectors_start:
 	W(b)	vector_rst
 	W(b)	vector_und
-	W(ldr)	pc, .L__vectors_start + 0x1000
+ARM(	.reloc	., R_ARM_LDR_PC_G0, .L__vector_swi		)
+THUMB(	.reloc	., R_ARM_THM_PC12, .L__vector_swi		)
+	W(ldr)	pc, .
 	W(b)	vector_pabt
 	W(b)	vector_dabt
 	W(b)	vector_addrexcptn
@@ -1334,10 +1310,11 @@ vector_addrexcptn:
 
 #ifdef CONFIG_HARDEN_BRANCH_HISTORY
 	.section .vectors.bhb.loop8, "ax", %progbits
-.L__vectors_bhb_loop8_start:
 	W(b)	vector_rst
 	W(b)	vector_bhb_loop8_und
-	W(ldr)	pc, .L__vectors_bhb_loop8_start + 0x1004
+ARM(	.reloc	., R_ARM_LDR_PC_G0, .L__vector_bhb_loop8_swi	)
+THUMB(	.reloc	., R_ARM_THM_PC12, .L__vector_bhb_loop8_swi	)
+	W(ldr)	pc, .
 	W(b)	vector_bhb_loop8_pabt
 	W(b)	vector_bhb_loop8_dabt
 	W(b)	vector_addrexcptn
@@ -1345,10 +1322,11 @@ vector_addrexcptn:
 	W(b)	vector_bhb_loop8_fiq
 
 	.section .vectors.bhb.bpiall, "ax", %progbits
-.L__vectors_bhb_bpiall_start:
 	W(b)	vector_rst
 	W(b)	vector_bhb_bpiall_und
-	W(ldr)	pc, .L__vectors_bhb_bpiall_start + 0x1008
+ARM(	.reloc	., R_ARM_LDR_PC_G0, .L__vector_bhb_bpiall_swi	)
+THUMB(	.reloc	., R_ARM_THM_PC12, .L__vector_bhb_bpiall_swi	)
+	W(ldr)	pc, .
 	W(b)	vector_bhb_bpiall_pabt
 	W(b)	vector_bhb_bpiall_dabt
 	W(b)	vector_addrexcptn

arch/arm/kernel/entry-common.S

@@ -164,7 +164,7 @@ ENTRY(vector_bhb_loop8_swi)
 1:	b	2f
 2:	subs	r8, r8, #1
 	bne	1b
-	dsb
+	dsb	nsh
 	isb
 	b	3f
 ENDPROC(vector_bhb_loop8_swi)
@@ -198,7 +198,7 @@ ENTRY(vector_swi)
 #endif
 	reload_current r10, ip
 	zero_fp
-	alignment_trap r10, ip, __cr_alignment
+	alignment_trap r10, ip, cr_alignment
 	asm_trace_hardirqs_on save=0
 	enable_irq_notrace
 	ct_user_exit save=0
@@ -328,14 +328,6 @@ __sys_trace_return:
 	bl	syscall_trace_exit
 	b	ret_slow_syscall
 
-	.align	5
-#ifdef CONFIG_ALIGNMENT_TRAP
-	.type	__cr_alignment, #object
-__cr_alignment:
-	.word	cr_alignment
-#endif
-	.ltorg
-
 	.macro	syscall_table_start, sym
 	.equ	__sys_nr, 0
 	.type	\sym, #object

arch/arm/kernel/entry-header.S

@@ -48,8 +48,7 @@
 	.macro	alignment_trap, rtmp1, rtmp2, label
 #ifdef CONFIG_ALIGNMENT_TRAP
 	mrc	p15, 0, \rtmp2, c1, c0, 0
-	ldr	\rtmp1, \label
-	ldr	\rtmp1, [\rtmp1]
+	ldr_va	\rtmp1, \label
 	teq	\rtmp1, \rtmp2
 	mcrne	p15, 0, \rtmp1, c1, c0, 0
 #endif

arch/arm/kernel/hw_breakpoint.c

@@ -941,6 +941,23 @@ static int hw_breakpoint_pending(unsigned long addr, unsigned int fsr,
 	return ret;
 }
 
+#ifdef CONFIG_ARM_ERRATA_764319
+static int oslsr_fault;
+
+static int debug_oslsr_trap(struct pt_regs *regs, unsigned int instr)
+{
+	oslsr_fault = 1;
+	instruction_pointer(regs) += 4;
+	return 0;
+}
+
+static struct undef_hook debug_oslsr_hook = {
+	.instr_mask  = 0xffffffff,
+	.instr_val = 0xee115e91,
+	.fn = debug_oslsr_trap,
+};
+#endif
+
 /*
  * One-time initialisation.
  */
@@ -974,7 +991,16 @@ static bool core_has_os_save_restore(void)
 	case ARM_DEBUG_ARCH_V7_1:
 		return true;
 	case ARM_DEBUG_ARCH_V7_ECP14:
+#ifdef CONFIG_ARM_ERRATA_764319
+		oslsr_fault = 0;
+		register_undef_hook(&debug_oslsr_hook);
 		ARM_DBG_READ(c1, c1, 4, oslsr);
+		unregister_undef_hook(&debug_oslsr_hook);
+		if (oslsr_fault)
+			return false;
+#else
+		ARM_DBG_READ(c1, c1, 4, oslsr);
+#endif
 		if (oslsr & ARM_OSLSR_OSLM0)
 			return true;
 		fallthrough;

arch/arm/kernel/module.c

@@ -459,46 +459,40 @@ int module_finalize(const Elf32_Ehdr *hdr, const Elf_Shdr *sechdrs,
 #ifdef CONFIG_ARM_UNWIND
 	const char *secstrs = (void *)hdr + sechdrs[hdr->e_shstrndx].sh_offset;
 	const Elf_Shdr *sechdrs_end = sechdrs + hdr->e_shnum;
-	struct mod_unwind_map maps[ARM_SEC_MAX];
-	int i;
+	struct list_head *unwind_list = &mod->arch.unwind_list;
 
-	memset(maps, 0, sizeof(maps));
+	INIT_LIST_HEAD(unwind_list);
+	mod->arch.init_table = NULL;
 
 	for (s = sechdrs; s < sechdrs_end; s++) {
 		const char *secname = secstrs + s->sh_name;
+		const char *txtname;
+		const Elf_Shdr *txt_sec;
 
-		if (!(s->sh_flags & SHF_ALLOC))
+		if (!(s->sh_flags & SHF_ALLOC) ||
+		    s->sh_type != ELF_SECTION_UNWIND)
 			continue;
 
-		if (strcmp(".ARM.exidx.init.text", secname) == 0)
-			maps[ARM_SEC_INIT].unw_sec = s;
-		else if (strcmp(".ARM.exidx", secname) == 0)
-			maps[ARM_SEC_CORE].unw_sec = s;
-		else if (strcmp(".ARM.exidx.exit.text", secname) == 0)
-			maps[ARM_SEC_EXIT].unw_sec = s;
-		else if (strcmp(".ARM.exidx.text.unlikely", secname) == 0)
-			maps[ARM_SEC_UNLIKELY].unw_sec = s;
-		else if (strcmp(".ARM.exidx.text.hot", secname) == 0)
-			maps[ARM_SEC_HOT].unw_sec = s;
-		else if (strcmp(".init.text", secname) == 0)
-			maps[ARM_SEC_INIT].txt_sec = s;
-		else if (strcmp(".text", secname) == 0)
-			maps[ARM_SEC_CORE].txt_sec = s;
-		else if (strcmp(".exit.text", secname) == 0)
-			maps[ARM_SEC_EXIT].txt_sec = s;
-		else if (strcmp(".text.unlikely", secname) == 0)
-			maps[ARM_SEC_UNLIKELY].txt_sec = s;
-		else if (strcmp(".text.hot", secname) == 0)
-			maps[ARM_SEC_HOT].txt_sec = s;
-	}
+		if (!strcmp(".ARM.exidx", secname))
+			txtname = ".text";
+		else
+			txtname = secname + strlen(".ARM.exidx");
+		txt_sec = find_mod_section(hdr, sechdrs, txtname);
 
-	for (i = 0; i < ARM_SEC_MAX; i++)
-		if (maps[i].unw_sec && maps[i].txt_sec)
-			mod->arch.unwind[i] =
-				unwind_table_add(maps[i].unw_sec->sh_addr,
-					         maps[i].unw_sec->sh_size,
-					         maps[i].txt_sec->sh_addr,
-					         maps[i].txt_sec->sh_size);
+		if (txt_sec) {
+			struct unwind_table *table =
+				unwind_table_add(s->sh_addr,
+						s->sh_size,
+						txt_sec->sh_addr,
+						txt_sec->sh_size);
+
+			list_add(&table->mod_list, unwind_list);
+
+			/* save init table for module_arch_freeing_init */
+			if (strcmp(".ARM.exidx.init.text", secname) == 0)
+				mod->arch.init_table = table;
+		}
+	}
 #endif
 #ifdef CONFIG_ARM_PATCH_PHYS_VIRT
 	s = find_mod_section(hdr, sechdrs, ".pv_table");
@@ -519,19 +513,27 @@ void
 module_arch_cleanup(struct module *mod)
 {
 #ifdef CONFIG_ARM_UNWIND
-	int i;
+	struct unwind_table *tmp;
+	struct unwind_table *n;
 
-	for (i = 0; i < ARM_SEC_MAX; i++) {
-		unwind_table_del(mod->arch.unwind[i]);
-		mod->arch.unwind[i] = NULL;
+	list_for_each_entry_safe(tmp, n,
+			&mod->arch.unwind_list, mod_list) {
+		list_del(&tmp->mod_list);
+		unwind_table_del(tmp);
 	}
+	mod->arch.init_table = NULL;
 #endif
 }
 
 void __weak module_arch_freeing_init(struct module *mod)
 {
 #ifdef CONFIG_ARM_UNWIND
-	unwind_table_del(mod->arch.unwind[ARM_SEC_INIT]);
-	mod->arch.unwind[ARM_SEC_INIT] = NULL;
+	struct unwind_table *init = mod->arch.init_table;
+
+	if (init) {
+		mod->arch.init_table = NULL;
+		list_del(&init->mod_list);
+		unwind_table_del(init);
+	}
 #endif
 }

arch/arm/kernel/signal.c

@@ -708,6 +708,7 @@ static_assert(offsetof(siginfo_t, si_upper)	== 0x18);
 static_assert(offsetof(siginfo_t, si_pkey)	== 0x14);
 static_assert(offsetof(siginfo_t, si_perf_data)	== 0x10);
 static_assert(offsetof(siginfo_t, si_perf_type)	== 0x14);
+static_assert(offsetof(siginfo_t, si_perf_flags) == 0x18);
 static_assert(offsetof(siginfo_t, si_band)	== 0x0c);
 static_assert(offsetof(siginfo_t, si_fd)	== 0x10);
 static_assert(offsetof(siginfo_t, si_call_addr)	== 0x0c);

arch/arm/mach-sunxi/Kconfig

@@ -4,10 +4,7 @@ menuconfig ARCH_SUNXI
 	depends on ARCH_MULTI_V5 || ARCH_MULTI_V7
 	select ARCH_HAS_RESET_CONTROLLER
 	select CLKSRC_MMIO
-	select GENERIC_IRQ_CHIP
 	select GPIOLIB
-	select IRQ_DOMAIN_HIERARCHY
-	select IRQ_FASTEOI_HIERARCHY_HANDLERS
 	select PINCTRL
 	select PM_OPP
 	select SUN4I_TIMER
@@ -22,10 +19,12 @@ if ARCH_MULTI_V7
 config MACH_SUN4I
 	bool "Allwinner A10 (sun4i) SoCs support"
 	default ARCH_SUNXI
+	select SUN4I_INTC
 
 config MACH_SUN5I
 	bool "Allwinner A10s / A13 (sun5i) SoCs support"
 	default ARCH_SUNXI
+	select SUN4I_INTC
 	select SUN5I_HSTIMER
 
 config MACH_SUN6I
@@ -34,6 +33,8 @@ config MACH_SUN6I
 	select ARM_GIC
 	select MFD_SUN6I_PRCM
 	select SUN5I_HSTIMER
+	select SUN6I_R_INTC
+	select SUNXI_NMI_INTC
 
 config MACH_SUN7I
 	bool "Allwinner A20 (sun7i) SoCs support"
@@ -43,17 +44,21 @@ config MACH_SUN7I
 	select ARCH_SUPPORTS_BIG_ENDIAN
 	select HAVE_ARM_ARCH_TIMER
 	select SUN5I_HSTIMER
+	select SUNXI_NMI_INTC
 
 config MACH_SUN8I
 	bool "Allwinner sun8i Family SoCs support"
 	default ARCH_SUNXI
 	select ARM_GIC
 	select MFD_SUN6I_PRCM
+	select SUN6I_R_INTC
+	select SUNXI_NMI_INTC
 
 config MACH_SUN9I
 	bool "Allwinner (sun9i) SoCs support"
 	default ARCH_SUNXI
 	select ARM_GIC
+	select SUNXI_NMI_INTC
 
 config ARCH_SUNXI_MC_SMP
 	bool
@@ -69,6 +74,7 @@ if ARCH_MULTI_V5
 config MACH_SUNIV
 	bool "Allwinner ARMv5 F-series (suniv) SoCs support"
 	default ARCH_SUNXI
+	select SUN4I_INTC
 	help
 	  Support for Allwinner suniv ARMv5 SoCs.
 	  (F1C100A, F1C100s, F1C200s, F1C500, F1C600)

arch/arm/vdso/Makefile

@@ -28,7 +28,7 @@ CPPFLAGS_vdso.lds += -P -C -U$(ARCH)
 CFLAGS_REMOVE_vdso.o = -pg
 
 # Force -O2 to avoid libgcc dependencies
-CFLAGS_REMOVE_vgettimeofday.o = -pg -Os $(GCC_PLUGINS_CFLAGS)
+CFLAGS_REMOVE_vgettimeofday.o = -pg -Os $(RANDSTRUCT_CFLAGS) $(GCC_PLUGINS_CFLAGS)
 ifeq ($(c-gettimeofday-y),)
 CFLAGS_vgettimeofday.o = -O2
 else

arch/arm64/Kconfig

@@ -262,31 +262,31 @@ config ARM64_CONT_PMD_SHIFT
 	default 4
 
 config ARCH_MMAP_RND_BITS_MIN
-       default 14 if ARM64_64K_PAGES
-       default 16 if ARM64_16K_PAGES
-       default 18
+	default 14 if ARM64_64K_PAGES
+	default 16 if ARM64_16K_PAGES
+	default 18
 
 # max bits determined by the following formula:
 #  VA_BITS - PAGE_SHIFT - 3
 config ARCH_MMAP_RND_BITS_MAX
-       default 19 if ARM64_VA_BITS=36
-       default 24 if ARM64_VA_BITS=39
-       default 27 if ARM64_VA_BITS=42
-       default 30 if ARM64_VA_BITS=47
-       default 29 if ARM64_VA_BITS=48 && ARM64_64K_PAGES
-       default 31 if ARM64_VA_BITS=48 && ARM64_16K_PAGES
-       default 33 if ARM64_VA_BITS=48
-       default 14 if ARM64_64K_PAGES
-       default 16 if ARM64_16K_PAGES
-       default 18
+	default 19 if ARM64_VA_BITS=36
+	default 24 if ARM64_VA_BITS=39
+	default 27 if ARM64_VA_BITS=42
+	default 30 if ARM64_VA_BITS=47
+	default 29 if ARM64_VA_BITS=48 && ARM64_64K_PAGES
+	default 31 if ARM64_VA_BITS=48 && ARM64_16K_PAGES
+	default 33 if ARM64_VA_BITS=48
+	default 14 if ARM64_64K_PAGES
+	default 16 if ARM64_16K_PAGES
+	default 18
 
 config ARCH_MMAP_RND_COMPAT_BITS_MIN
-       default 7 if ARM64_64K_PAGES
-       default 9 if ARM64_16K_PAGES
-       default 11
+	default 7 if ARM64_64K_PAGES
+	default 9 if ARM64_16K_PAGES
+	default 11
 
 config ARCH_MMAP_RND_COMPAT_BITS_MAX
-       default 16
+	default 16
 
 config NO_IOPORT_MAP
 	def_bool y if !PCI
@@ -313,7 +313,7 @@ config GENERIC_HWEIGHT
 	def_bool y
 
 config GENERIC_CSUM
-        def_bool y
+	def_bool y
 
 config GENERIC_CALIBRATE_DELAY
 	def_bool y
@@ -1046,8 +1046,7 @@ config SOCIONEXT_SYNQUACER_PREITS
 
 	  If unsure, say Y.
 
-endmenu
-
+endmenu # "ARM errata workarounds via the alternatives framework"
 
 choice
 	prompt "Page size"
@@ -1575,9 +1574,9 @@ config SETEND_EMULATION
 	  be unexpected results in the applications.
 
 	  If unsure, say Y
-endif
+endif # ARMV8_DEPRECATED
 
-endif
+endif # COMPAT
 
 menu "ARMv8.1 architectural features"
 
@@ -1602,15 +1601,15 @@ config ARM64_PAN
 	bool "Enable support for Privileged Access Never (PAN)"
 	default y
 	help
-	 Privileged Access Never (PAN; part of the ARMv8.1 Extensions)
-	 prevents the kernel or hypervisor from accessing user-space (EL0)
-	 memory directly.
+	  Privileged Access Never (PAN; part of the ARMv8.1 Extensions)
+	  prevents the kernel or hypervisor from accessing user-space (EL0)
+	  memory directly.
 
-	 Choosing this option will cause any unprotected (not using
-	 copy_to_user et al) memory access to fail with a permission fault.
+	  Choosing this option will cause any unprotected (not using
+	  copy_to_user et al) memory access to fail with a permission fault.
 
-	 The feature is detected at runtime, and will remain as a 'nop'
-	 instruction if the cpu does not implement the feature.
+	  The feature is detected at runtime, and will remain as a 'nop'
+	  instruction if the cpu does not implement the feature.
 
 config AS_HAS_LDAPR
 	def_bool $(as-instr,.arch_extension rcpc)
@@ -1638,15 +1637,15 @@ config ARM64_USE_LSE_ATOMICS
 	  built with binutils >= 2.25 in order for the new instructions
 	  to be used.
 
-endmenu
+endmenu # "ARMv8.1 architectural features"
 
 menu "ARMv8.2 architectural features"
 
 config AS_HAS_ARMV8_2
-       def_bool $(cc-option,-Wa$(comma)-march=armv8.2-a)
+	def_bool $(cc-option,-Wa$(comma)-march=armv8.2-a)
 
 config AS_HAS_SHA3
-       def_bool $(as-instr,.arch armv8.2-a+sha3)
+	def_bool $(as-instr,.arch armv8.2-a+sha3)
 
 config ARM64_PMEM
 	bool "Enable support for persistent memory"
@@ -1690,7 +1689,7 @@ config ARM64_CNP
 	  at runtime, and does not affect PEs that do not implement
 	  this feature.
 
-endmenu
+endmenu # "ARMv8.2 architectural features"
 
 menu "ARMv8.3 architectural features"
 
@@ -1753,7 +1752,7 @@ config AS_HAS_PAC
 config AS_HAS_CFI_NEGATE_RA_STATE
 	def_bool $(as-instr,.cfi_startproc\n.cfi_negate_ra_state\n.cfi_endproc\n)
 
-endmenu
+endmenu # "ARMv8.3 architectural features"
 
 menu "ARMv8.4 architectural features"
 
@@ -1794,7 +1793,7 @@ config ARM64_TLB_RANGE
 	  The feature introduces new assembly instructions, and they were
 	  support when binutils >= 2.30.
 
-endmenu
+endmenu # "ARMv8.4 architectural features"
 
 menu "ARMv8.5 architectural features"
 
@@ -1880,6 +1879,7 @@ config ARM64_MTE
 	depends on AS_HAS_LSE_ATOMICS
 	# Required for tag checking in the uaccess routines
 	depends on ARM64_PAN
+	select ARCH_HAS_SUBPAGE_FAULTS
 	select ARCH_USES_HIGH_VMA_FLAGS
 	help
 	  Memory Tagging (part of the ARMv8.5 Extensions) provides
@@ -1901,7 +1901,7 @@ config ARM64_MTE
 
 	  Documentation/arm64/memory-tagging-extension.rst.
 
-endmenu
+endmenu # "ARMv8.5 architectural features"
 
 menu "ARMv8.7 architectural features"
 
@@ -1910,12 +1910,12 @@ config ARM64_EPAN
 	default y
 	depends on ARM64_PAN
 	help
-	 Enhanced Privileged Access Never (EPAN) allows Privileged
-	 Access Never to be used with Execute-only mappings.
+	  Enhanced Privileged Access Never (EPAN) allows Privileged
+	  Access Never to be used with Execute-only mappings.
 
-	 The feature is detected at runtime, and will remain disabled
-	 if the cpu does not implement the feature.
-endmenu
+	  The feature is detected at runtime, and will remain disabled
+	  if the cpu does not implement the feature.
+endmenu # "ARMv8.7 architectural features"
 
 config ARM64_SVE
 	bool "ARM Scalable Vector Extension support"
@@ -1948,6 +1948,17 @@ config ARM64_SVE
 	  booting the kernel.  If unsure and you are not observing these
 	  symptoms, you should assume that it is safe to say Y.
 
+config ARM64_SME
+	bool "ARM Scalable Matrix Extension support"
+	default y
+	depends on ARM64_SVE
+	help
+	  The Scalable Matrix Extension (SME) is an extension to the AArch64
+	  execution state which utilises a substantial subset of the SVE
+	  instruction set, together with the addition of new architectural
+	  register state capable of holding two dimensional matrix tiles to
+	  enable various matrix operations.
+
 config ARM64_MODULE_PLTS
 	bool "Use PLTs to allow module memory to spill over into vmalloc area"
 	depends on MODULES
@@ -1991,7 +2002,7 @@ config ARM64_DEBUG_PRIORITY_MASKING
 	  the validity of ICC_PMR_EL1 when calling concerned functions.
 
 	  If unsure, say N
-endif
+endif # ARM64_PSEUDO_NMI
 
 config RELOCATABLE
 	bool "Build a relocatable kernel image" if EXPERT
@@ -2050,7 +2061,19 @@ config STACKPROTECTOR_PER_TASK
 	def_bool y
 	depends on STACKPROTECTOR && CC_HAVE_STACKPROTECTOR_SYSREG
 
-endmenu
+# The GPIO number here must be sorted by descending number. In case of
+# a multiplatform kernel, we just want the highest value required by the
+# selected platforms.
+config ARCH_NR_GPIO
+        int
+        default 2048 if ARCH_APPLE
+        default 0
+        help
+          Maximum number of GPIOs in the system.
+
+          If unsure, leave the default value.
+
+endmenu # "Kernel Features"
 
 menu "Boot options"
 
@@ -2114,7 +2137,7 @@ config EFI
 	help
 	  This option provides support for runtime services provided
 	  by UEFI firmware (such as non-volatile variables, realtime
-          clock, and platform reset). A UEFI stub is also provided to
+	  clock, and platform reset). A UEFI stub is also provided to
 	  allow the kernel to be booted as an EFI application. This
 	  is only useful on systems that have UEFI firmware.
 
@@ -2129,7 +2152,7 @@ config DMI
 	  However, even with this option, the resultant kernel should
 	  continue to boot on existing non-UEFI platforms.
 
-endmenu
+endmenu # "Boot options"
 
 config SYSVIPC_COMPAT
 	def_bool y
@@ -2150,7 +2173,7 @@ config ARCH_HIBERNATION_HEADER
 config ARCH_SUSPEND_POSSIBLE
 	def_bool y
 
-endmenu
+endmenu # "Power management options"
 
 menu "CPU Power Management"
 
@@ -2158,7 +2181,7 @@ source "drivers/cpuidle/Kconfig"
 
 source "drivers/cpufreq/Kconfig"
 
-endmenu
+endmenu # "CPU Power Management"
 
 source "drivers/acpi/Kconfig"
 
@@ -2166,4 +2189,4 @@ source "arch/arm64/kvm/Kconfig"
 
 if CRYPTO
 source "arch/arm64/crypto/Kconfig"
-endif
+endif # CRYPTO

arch/arm64/Kconfig.platforms

@@ -11,12 +11,11 @@ config ARCH_ACTIONS
 config ARCH_SUNXI
 	bool "Allwinner sunxi 64-bit SoC Family"
 	select ARCH_HAS_RESET_CONTROLLER
-	select GENERIC_IRQ_CHIP
-	select IRQ_DOMAIN_HIERARCHY
-	select IRQ_FASTEOI_HIERARCHY_HANDLERS
 	select PINCTRL
 	select RESET_CONTROLLER
 	select SUN4I_TIMER
+	select SUN6I_R_INTC
+	select SUNXI_NMI_INTC
 	help
 	  This enables support for Allwinner sunxi based SoCs like the A64.
 
@@ -253,6 +252,7 @@ config ARCH_INTEL_SOCFPGA
 
 config ARCH_SYNQUACER
 	bool "Socionext SynQuacer SoC Family"
+	select IRQ_FASTEOI_HIERARCHY_HANDLERS
 
 config ARCH_TEGRA
 	bool "NVIDIA Tegra SoC Family"
@@ -325,4 +325,4 @@ config ARCH_ZYNQMP
 	help
 	  This enables support for Xilinx ZynqMP Family
 
-endmenu
+endmenu # "Platform selection"

arch/arm64/include/asm/Kbuild

@@ -7,3 +7,4 @@ generic-y += parport.h
 generic-y += user.h
 
 generated-y += cpucaps.h
+generated-y += sysreg-defs.h

arch/arm64/include/asm/arch_gicv3.h

@@ -26,12 +26,6 @@
  * sets the GP register's most significant bits to 0 with an explicit cast.
  */
 
-static inline void gic_write_eoir(u32 irq)
-{
-	write_sysreg_s(irq, SYS_ICC_EOIR1_EL1);
-	isb();
-}
-
 static __always_inline void gic_write_dir(u32 irq)
 {
 	write_sysreg_s(irq, SYS_ICC_DIR_EL1);

arch/arm64/include/asm/archrandom.h

@@ -142,7 +142,7 @@ static inline bool __init __early_cpu_has_rndr(void)
 {
 	/* Open code as we run prior to the first call to cpufeature. */
 	unsigned long ftr = read_sysreg_s(SYS_ID_AA64ISAR0_EL1);
-	return (ftr >> ID_AA64ISAR0_RNDR_SHIFT) & 0xf;
+	return (ftr >> ID_AA64ISAR0_EL1_RNDR_SHIFT) & 0xf;
 }
 
 static inline bool __init __must_check

arch/arm64/include/asm/asm-bug.h

@@ -14,7 +14,7 @@
 	14472:	.string file;					\
 		.popsection;					\
 								\
-		.long 14472b - 14470b;				\
+		.long 14472b - .;				\
 		.short line;
 #else
 #define _BUGVERBOSE_LOCATION(file, line)
@@ -25,7 +25,7 @@
 #define __BUG_ENTRY(flags) 				\
 		.pushsection __bug_table,"aw";		\
 		.align 2;				\
-	14470:	.long 14471f - 14470b;			\
+	14470:	.long 14471f - .;			\
 _BUGVERBOSE_LOCATION(__FILE__, __LINE__)		\
 		.short flags; 				\
 		.popsection;				\

arch/arm64/include/asm/compiler.h

@@ -23,20 +23,4 @@
 #define __builtin_return_address(val)					\
 	(void *)(ptrauth_clear_pac((unsigned long)__builtin_return_address(val)))
 
-#ifdef CONFIG_CFI_CLANG
-/*
- * With CONFIG_CFI_CLANG, the compiler replaces function address
- * references with the address of the function's CFI jump table
- * entry. The function_nocfi macro always returns the address of the
- * actual function instead.
- */
-#define function_nocfi(x) ({						\
-	void *addr;							\
-	asm("adrp %0, " __stringify(x) "\n\t"				\
-	    "add  %0, %0, :lo12:" __stringify(x)			\
-	    : "=r" (addr));						\
-	addr;								\
-})
-#endif
-
 #endif /* __ASM_COMPILER_H */

arch/arm64/include/asm/cpu.h

@@ -58,11 +58,15 @@ struct cpuinfo_arm64 {
 	u64		reg_id_aa64pfr0;
 	u64		reg_id_aa64pfr1;
 	u64		reg_id_aa64zfr0;
+	u64		reg_id_aa64smfr0;
 
 	struct cpuinfo_32bit	aarch32;
 
 	/* pseudo-ZCR for recording maximum ZCR_EL1 LEN value: */
 	u64		reg_zcr;
+
+	/* pseudo-SMCR for recording maximum SMCR_EL1 LEN value: */
+	u64		reg_smcr;
 };
 
 DECLARE_PER_CPU(struct cpuinfo_arm64, cpu_data);

arch/arm64/include/asm/cpufeature.h

@@ -622,6 +622,13 @@ static inline bool id_aa64pfr0_sve(u64 pfr0)
 	return val > 0;
 }
 
+static inline bool id_aa64pfr1_sme(u64 pfr1)
+{
+	u32 val = cpuid_feature_extract_unsigned_field(pfr1, ID_AA64PFR1_SME_SHIFT);
+
+	return val > 0;
+}
+
 static inline bool id_aa64pfr1_mte(u64 pfr1)
 {
 	u32 val = cpuid_feature_extract_unsigned_field(pfr1, ID_AA64PFR1_MTE_SHIFT);
@@ -759,6 +766,23 @@ static __always_inline bool system_supports_sve(void)
 		cpus_have_const_cap(ARM64_SVE);
 }
 
+static __always_inline bool system_supports_sme(void)
+{
+	return IS_ENABLED(CONFIG_ARM64_SME) &&
+		cpus_have_const_cap(ARM64_SME);
+}
+
+static __always_inline bool system_supports_fa64(void)
+{
+	return IS_ENABLED(CONFIG_ARM64_SME) &&
+		cpus_have_const_cap(ARM64_SME_FA64);
+}
+
+static __always_inline bool system_supports_tpidr2(void)
+{
+	return system_supports_sme();
+}
+
 static __always_inline bool system_supports_cnp(void)
 {
 	return IS_ENABLED(CONFIG_ARM64_CNP) &&

arch/arm64/include/asm/cputype.h

@@ -36,7 +36,7 @@
 #define MIDR_VARIANT(midr)	\
 	(((midr) & MIDR_VARIANT_MASK) >> MIDR_VARIANT_SHIFT)
 #define MIDR_IMPLEMENTOR_SHIFT	24
-#define MIDR_IMPLEMENTOR_MASK	(0xff << MIDR_IMPLEMENTOR_SHIFT)
+#define MIDR_IMPLEMENTOR_MASK	(0xffU << MIDR_IMPLEMENTOR_SHIFT)
 #define MIDR_IMPLEMENTOR(midr)	\
 	(((midr) & MIDR_IMPLEMENTOR_MASK) >> MIDR_IMPLEMENTOR_SHIFT)
 

arch/arm64/include/asm/debug-monitors.h

@@ -64,7 +64,7 @@ struct task_struct;
 
 struct step_hook {
 	struct list_head node;
-	int (*fn)(struct pt_regs *regs, unsigned int esr);
+	int (*fn)(struct pt_regs *regs, unsigned long esr);
 };
 
 void register_user_step_hook(struct step_hook *hook);
@@ -75,7 +75,7 @@ void unregister_kernel_step_hook(struct step_hook *hook);
 
 struct break_hook {
 	struct list_head node;
-	int (*fn)(struct pt_regs *regs, unsigned int esr);
+	int (*fn)(struct pt_regs *regs, unsigned long esr);
 	u16 imm;
 	u16 mask; /* These bits are ignored when comparing with imm */
 };

arch/arm64/include/asm/el2_setup.h

@@ -143,6 +143,50 @@
 .Lskip_sve_\@:
 .endm
 
+/* SME register access and priority mapping */
+.macro __init_el2_nvhe_sme
+	mrs	x1, id_aa64pfr1_el1
+	ubfx	x1, x1, #ID_AA64PFR1_SME_SHIFT, #4
+	cbz	x1, .Lskip_sme_\@
+
+	bic	x0, x0, #CPTR_EL2_TSM		// Also disable SME traps
+	msr	cptr_el2, x0			// Disable copro. traps to EL2
+	isb
+
+	mrs	x1, sctlr_el2
+	orr	x1, x1, #SCTLR_ELx_ENTP2	// Disable TPIDR2 traps
+	msr	sctlr_el2, x1
+	isb
+
+	mov	x1, #0				// SMCR controls
+
+	mrs_s	x2, SYS_ID_AA64SMFR0_EL1
+	ubfx	x2, x2, #ID_AA64SMFR0_FA64_SHIFT, #1 // Full FP in SM?
+	cbz	x2, .Lskip_sme_fa64_\@
+
+	orr	x1, x1, SMCR_ELx_FA64_MASK
+.Lskip_sme_fa64_\@:
+
+	orr	x1, x1, #SMCR_ELx_LEN_MASK	// Enable full SME vector
+	msr_s	SYS_SMCR_EL2, x1		// length for EL1.
+
+	mrs_s	x1, SYS_SMIDR_EL1		// Priority mapping supported?
+	ubfx    x1, x1, #SMIDR_EL1_SMPS_SHIFT, #1
+	cbz     x1, .Lskip_sme_\@
+
+	msr_s	SYS_SMPRIMAP_EL2, xzr		// Make all priorities equal
+
+	mrs	x1, id_aa64mmfr1_el1		// HCRX_EL2 present?
+	ubfx	x1, x1, #ID_AA64MMFR1_HCX_SHIFT, #4
+	cbz	x1, .Lskip_sme_\@
+
+	mrs_s	x1, SYS_HCRX_EL2
+	orr	x1, x1, #HCRX_EL2_SMPME_MASK	// Enable priority mapping
+	msr_s	SYS_HCRX_EL2, x1
+
+.Lskip_sme_\@:
+.endm
+
 /* Disable any fine grained traps */
 .macro __init_el2_fgt
 	mrs	x1, id_aa64mmfr0_el1
@@ -153,15 +197,26 @@
 	mrs	x1, id_aa64dfr0_el1
 	ubfx	x1, x1, #ID_AA64DFR0_PMSVER_SHIFT, #4
 	cmp	x1, #3
-	b.lt	.Lset_fgt_\@
+	b.lt	.Lset_debug_fgt_\@
 	/* Disable PMSNEVFR_EL1 read and write traps */
 	orr	x0, x0, #(1 << 62)
 
-.Lset_fgt_\@:
+.Lset_debug_fgt_\@:
 	msr_s	SYS_HDFGRTR_EL2, x0
 	msr_s	SYS_HDFGWTR_EL2, x0
-	msr_s	SYS_HFGRTR_EL2, xzr
-	msr_s	SYS_HFGWTR_EL2, xzr
+
+	mov	x0, xzr
+	mrs	x1, id_aa64pfr1_el1
+	ubfx	x1, x1, #ID_AA64PFR1_SME_SHIFT, #4
+	cbz	x1, .Lset_fgt_\@
+
+	/* Disable nVHE traps of TPIDR2 and SMPRI */
+	orr	x0, x0, #HFGxTR_EL2_nSMPRI_EL1_MASK
+	orr	x0, x0, #HFGxTR_EL2_nTPIDR2_EL0_MASK
+
+.Lset_fgt_\@:
+	msr_s	SYS_HFGRTR_EL2, x0
+	msr_s	SYS_HFGWTR_EL2, x0
 	msr_s	SYS_HFGITR_EL2, xzr
 
 	mrs	x1, id_aa64pfr0_el1		// AMU traps UNDEF without AMU
@@ -196,6 +251,7 @@
 	__init_el2_nvhe_idregs
 	__init_el2_nvhe_cptr
 	__init_el2_nvhe_sve
+	__init_el2_nvhe_sme
 	__init_el2_fgt
 	__init_el2_nvhe_prepare_eret
 .endm

arch/arm64/include/asm/esr.h

@@ -37,7 +37,8 @@
 #define ESR_ELx_EC_ERET		(0x1a)	/* EL2 only */
 /* Unallocated EC: 0x1B */
 #define ESR_ELx_EC_FPAC		(0x1C)	/* EL1 and above */
-/* Unallocated EC: 0x1D - 0x1E */
+#define ESR_ELx_EC_SME		(0x1D)
+/* Unallocated EC: 0x1E */
 #define ESR_ELx_EC_IMP_DEF	(0x1f)	/* EL3 only */
 #define ESR_ELx_EC_IABT_LOW	(0x20)
 #define ESR_ELx_EC_IABT_CUR	(0x21)
@@ -75,6 +76,7 @@
 #define ESR_ELx_IL_SHIFT	(25)
 #define ESR_ELx_IL		(UL(1) << ESR_ELx_IL_SHIFT)
 #define ESR_ELx_ISS_MASK	(ESR_ELx_IL - 1)
+#define ESR_ELx_ISS(esr)	((esr) & ESR_ELx_ISS_MASK)
 
 /* ISS field definitions shared by different classes */
 #define ESR_ELx_WNR_SHIFT	(6)
@@ -136,7 +138,7 @@
 #define ESR_ELx_WFx_ISS_TI	(UL(1) << 0)
 #define ESR_ELx_WFx_ISS_WFI	(UL(0) << 0)
 #define ESR_ELx_WFx_ISS_WFE	(UL(1) << 0)
-#define ESR_ELx_xVC_IMM_MASK	((1UL << 16) - 1)
+#define ESR_ELx_xVC_IMM_MASK	((UL(1) << 16) - 1)
 
 #define DISR_EL1_IDS		(UL(1) << 24)
 /*
@@ -327,17 +329,26 @@
 #define ESR_ELx_CP15_32_ISS_SYS_CNTFRQ	(ESR_ELx_CP15_32_ISS_SYS_VAL(0, 0, 14, 0) |\
 					 ESR_ELx_CP15_32_ISS_DIR_READ)
 
+/*
+ * ISS values for SME traps
+ */
+
+#define ESR_ELx_SME_ISS_SME_DISABLED	0
+#define ESR_ELx_SME_ISS_ILL		1
+#define ESR_ELx_SME_ISS_SM_DISABLED	2
+#define ESR_ELx_SME_ISS_ZA_DISABLED	3
+
 #ifndef __ASSEMBLY__
 #include <asm/types.h>
 
-static inline bool esr_is_data_abort(u32 esr)
+static inline bool esr_is_data_abort(unsigned long esr)
 {
-	const u32 ec = ESR_ELx_EC(esr);
+	const unsigned long ec = ESR_ELx_EC(esr);
 
 	return ec == ESR_ELx_EC_DABT_LOW || ec == ESR_ELx_EC_DABT_CUR;
 }
 
-const char *esr_get_class_string(u32 esr);
+const char *esr_get_class_string(unsigned long esr);
 #endif /* __ASSEMBLY */
 
 #endif /* __ASM_ESR_H */

arch/arm64/include/asm/exception.h

@@ -19,9 +19,9 @@
 #define __exception_irq_entry	__kprobes
 #endif
 
-static inline u32 disr_to_esr(u64 disr)
+static inline unsigned long disr_to_esr(u64 disr)
 {
-	unsigned int esr = ESR_ELx_EC_SERROR << ESR_ELx_EC_SHIFT;
+	unsigned long esr = ESR_ELx_EC_SERROR << ESR_ELx_EC_SHIFT;
 
 	if ((disr & DISR_EL1_IDS) == 0)
 		esr |= (disr & DISR_EL1_ESR_MASK);
@@ -57,23 +57,24 @@ asmlinkage void call_on_irq_stack(struct pt_regs *regs,
 				  void (*func)(struct pt_regs *));
 asmlinkage void asm_exit_to_user_mode(struct pt_regs *regs);
 
-void do_mem_abort(unsigned long far, unsigned int esr, struct pt_regs *regs);
+void do_mem_abort(unsigned long far, unsigned long esr, struct pt_regs *regs);
 void do_undefinstr(struct pt_regs *regs);
 void do_bti(struct pt_regs *regs);
-void do_debug_exception(unsigned long addr_if_watchpoint, unsigned int esr,
+void do_debug_exception(unsigned long addr_if_watchpoint, unsigned long esr,
 			struct pt_regs *regs);
-void do_fpsimd_acc(unsigned int esr, struct pt_regs *regs);
-void do_sve_acc(unsigned int esr, struct pt_regs *regs);
-void do_fpsimd_exc(unsigned int esr, struct pt_regs *regs);
-void do_sysinstr(unsigned int esr, struct pt_regs *regs);
-void do_sp_pc_abort(unsigned long addr, unsigned int esr, struct pt_regs *regs);
-void bad_el0_sync(struct pt_regs *regs, int reason, unsigned int esr);
-void do_cp15instr(unsigned int esr, struct pt_regs *regs);
+void do_fpsimd_acc(unsigned long esr, struct pt_regs *regs);
+void do_sve_acc(unsigned long esr, struct pt_regs *regs);
+void do_sme_acc(unsigned long esr, struct pt_regs *regs);
+void do_fpsimd_exc(unsigned long esr, struct pt_regs *regs);
+void do_sysinstr(unsigned long esr, struct pt_regs *regs);
+void do_sp_pc_abort(unsigned long addr, unsigned long esr, struct pt_regs *regs);
+void bad_el0_sync(struct pt_regs *regs, int reason, unsigned long esr);
+void do_cp15instr(unsigned long esr, struct pt_regs *regs);
 void do_el0_svc(struct pt_regs *regs);
 void do_el0_svc_compat(struct pt_regs *regs);
-void do_ptrauth_fault(struct pt_regs *regs, unsigned int esr);
-void do_serror(struct pt_regs *regs, unsigned int esr);
+void do_ptrauth_fault(struct pt_regs *regs, unsigned long esr);
+void do_serror(struct pt_regs *regs, unsigned long esr);
 void do_notify_resume(struct pt_regs *regs, unsigned long thread_flags);
 
-void panic_bad_stack(struct pt_regs *regs, unsigned int esr, unsigned long far);
+void panic_bad_stack(struct pt_regs *regs, unsigned long esr, unsigned long far);
 #endif	/* __ASM_EXCEPTION_H */

arch/arm64/include/asm/fpsimd.h

@@ -32,6 +32,18 @@
 #define VFP_STATE_SIZE		((32 * 8) + 4)
 #endif
 
+/*
+ * When we defined the maximum SVE vector length we defined the ABI so
+ * that the maximum vector length included all the reserved for future
+ * expansion bits in ZCR rather than those just currently defined by
+ * the architecture. While SME follows a similar pattern the fact that
+ * it includes a square matrix means that any allocations that attempt
+ * to cover the maximum potential vector length (such as happen with
+ * the regset used for ptrace) end up being extremely large. Define
+ * the much lower actual limit for use in such situations.
+ */
+#define SME_VQ_MAX	16
+
 struct task_struct;
 
 extern void fpsimd_save_state(struct user_fpsimd_state *state);
@@ -46,11 +58,23 @@ extern void fpsimd_restore_current_state(void);
 extern void fpsimd_update_current_state(struct user_fpsimd_state const *state);
 
 extern void fpsimd_bind_state_to_cpu(struct user_fpsimd_state *state,
-				     void *sve_state, unsigned int sve_vl);
+				     void *sve_state, unsigned int sve_vl,
+				     void *za_state, unsigned int sme_vl,
+				     u64 *svcr);
 
 extern void fpsimd_flush_task_state(struct task_struct *target);
 extern void fpsimd_save_and_flush_cpu_state(void);
 
+static inline bool thread_sm_enabled(struct thread_struct *thread)
+{
+	return system_supports_sme() && (thread->svcr & SVCR_SM_MASK);
+}
+
+static inline bool thread_za_enabled(struct thread_struct *thread)
+{
+	return system_supports_sme() && (thread->svcr & SVCR_ZA_MASK);
+}
+
 /* Maximum VL that SVE/SME VL-agnostic software can transparently support */
 #define VL_ARCH_MAX 0x100
 
@@ -62,7 +86,14 @@ static inline size_t sve_ffr_offset(int vl)
 
 static inline void *sve_pffr(struct thread_struct *thread)
 {
-	return (char *)thread->sve_state + sve_ffr_offset(thread_get_sve_vl(thread));
+	unsigned int vl;
+
+	if (system_supports_sme() && thread_sm_enabled(thread))
+		vl = thread_get_sme_vl(thread);
+	else
+		vl = thread_get_sve_vl(thread);
+
+	return (char *)thread->sve_state + sve_ffr_offset(vl);
 }
 
 extern void sve_save_state(void *state, u32 *pfpsr, int save_ffr);
@@ -71,11 +102,17 @@ extern void sve_load_state(void const *state, u32 const *pfpsr,
 extern void sve_flush_live(bool flush_ffr, unsigned long vq_minus_1);
 extern unsigned int sve_get_vl(void);
 extern void sve_set_vq(unsigned long vq_minus_1);
+extern void sme_set_vq(unsigned long vq_minus_1);
+extern void za_save_state(void *state);
+extern void za_load_state(void const *state);
 
 struct arm64_cpu_capabilities;
 extern void sve_kernel_enable(const struct arm64_cpu_capabilities *__unused);
+extern void sme_kernel_enable(const struct arm64_cpu_capabilities *__unused);
+extern void fa64_kernel_enable(const struct arm64_cpu_capabilities *__unused);
 
 extern u64 read_zcr_features(void);
+extern u64 read_smcr_features(void);
 
 /*
  * Helpers to translate bit indices in sve_vq_map to VQ values (and
@@ -119,6 +156,7 @@ struct vl_info {
 extern void sve_alloc(struct task_struct *task);
 extern void fpsimd_release_task(struct task_struct *task);
 extern void fpsimd_sync_to_sve(struct task_struct *task);
+extern void fpsimd_force_sync_to_sve(struct task_struct *task);
 extern void sve_sync_to_fpsimd(struct task_struct *task);
 extern void sve_sync_from_fpsimd_zeropad(struct task_struct *task);
 
@@ -170,6 +208,12 @@ static inline void write_vl(enum vec_type type, u64 val)
 		tmp = read_sysreg_s(SYS_ZCR_EL1) & ~ZCR_ELx_LEN_MASK;
 		write_sysreg_s(tmp | val, SYS_ZCR_EL1);
 		break;
+#endif
+#ifdef CONFIG_ARM64_SME
+	case ARM64_VEC_SME:
+		tmp = read_sysreg_s(SYS_SMCR_EL1) & ~SMCR_ELx_LEN_MASK;
+		write_sysreg_s(tmp | val, SYS_SMCR_EL1);
+		break;
 #endif
 	default:
 		WARN_ON_ONCE(1);
@@ -208,6 +252,8 @@ static inline bool sve_vq_available(unsigned int vq)
 	return vq_available(ARM64_VEC_SVE, vq);
 }
 
+size_t sve_state_size(struct task_struct const *task);
+
 #else /* ! CONFIG_ARM64_SVE */
 
 static inline void sve_alloc(struct task_struct *task) { }
@@ -247,8 +293,93 @@ static inline void vec_update_vq_map(enum vec_type t) { }
 static inline int vec_verify_vq_map(enum vec_type t) { return 0; }
 static inline void sve_setup(void) { }
 
+static inline size_t sve_state_size(struct task_struct const *task)
+{
+	return 0;
+}
+
 #endif /* ! CONFIG_ARM64_SVE */
 
+#ifdef CONFIG_ARM64_SME
+
+static inline void sme_user_disable(void)
+{
+	sysreg_clear_set(cpacr_el1, CPACR_EL1_SMEN_EL0EN, 0);
+}
+
+static inline void sme_user_enable(void)
+{
+	sysreg_clear_set(cpacr_el1, 0, CPACR_EL1_SMEN_EL0EN);
+}
+
+static inline void sme_smstart_sm(void)
+{
+	asm volatile(__msr_s(SYS_SVCR_SMSTART_SM_EL0, "xzr"));
+}
+
+static inline void sme_smstop_sm(void)
+{
+	asm volatile(__msr_s(SYS_SVCR_SMSTOP_SM_EL0, "xzr"));
+}
+
+static inline void sme_smstop(void)
+{
+	asm volatile(__msr_s(SYS_SVCR_SMSTOP_SMZA_EL0, "xzr"));
+}
+
+extern void __init sme_setup(void);
+
+static inline int sme_max_vl(void)
+{
+	return vec_max_vl(ARM64_VEC_SME);
+}
+
+static inline int sme_max_virtualisable_vl(void)
+{
+	return vec_max_virtualisable_vl(ARM64_VEC_SME);
+}
+
+extern void sme_alloc(struct task_struct *task);
+extern unsigned int sme_get_vl(void);
+extern int sme_set_current_vl(unsigned long arg);
+extern int sme_get_current_vl(void);
+
+/*
+ * Return how many bytes of memory are required to store the full SME
+ * specific state (currently just ZA) for task, given task's currently
+ * configured vector length.
+ */
+static inline size_t za_state_size(struct task_struct const *task)
+{
+	unsigned int vl = task_get_sme_vl(task);
+
+	return ZA_SIG_REGS_SIZE(sve_vq_from_vl(vl));
+}
+
+#else
+
+static inline void sme_user_disable(void) { BUILD_BUG(); }
+static inline void sme_user_enable(void) { BUILD_BUG(); }
+
+static inline void sme_smstart_sm(void) { }
+static inline void sme_smstop_sm(void) { }
+static inline void sme_smstop(void) { }
+
+static inline void sme_alloc(struct task_struct *task) { }
+static inline void sme_setup(void) { }
+static inline unsigned int sme_get_vl(void) { return 0; }
+static inline int sme_max_vl(void) { return 0; }
+static inline int sme_max_virtualisable_vl(void) { return 0; }
+static inline int sme_set_current_vl(unsigned long arg) { return -EINVAL; }
+static inline int sme_get_current_vl(void) { return -EINVAL; }
+
+static inline size_t za_state_size(struct task_struct const *task)
+{
+	return 0;
+}
+
+#endif /* ! CONFIG_ARM64_SME */
+
 /* For use by EFI runtime services calls only */
 extern void __efi_fpsimd_begin(void);
 extern void __efi_fpsimd_end(void);

arch/arm64/include/asm/fpsimdmacros.h

@@ -93,6 +93,12 @@
 	.endif
 .endm
 
+.macro _sme_check_wv v
+	.if (\v) < 12 || (\v) > 15
+		.error "Bad vector select register \v."
+	.endif
+.endm
+
 /* SVE instruction encodings for non-SVE-capable assemblers */
 /* (pre binutils 2.28, all kernel capable clang versions support SVE) */
 
@@ -174,6 +180,54 @@
 		| (\np)
 .endm
 
+/* SME instruction encodings for non-SME-capable assemblers */
+/* (pre binutils 2.38/LLVM 13) */
+
+/* RDSVL X\nx, #\imm */
+.macro _sme_rdsvl nx, imm
+	_check_general_reg \nx
+	_check_num (\imm), -0x20, 0x1f
+	.inst	0x04bf5800			\
+		| (\nx)				\
+		| (((\imm) & 0x3f) << 5)
+.endm
+
+/*
+ * STR (vector from ZA array):
+ *	STR ZA[\nw, #\offset], [X\nxbase, #\offset, MUL VL]
+ */
+.macro _sme_str_zav nw, nxbase, offset=0
+	_sme_check_wv \nw
+	_check_general_reg \nxbase
+	_check_num (\offset), -0x100, 0xff
+	.inst	0xe1200000			\
+		| (((\nw) & 3) << 13)		\
+		| ((\nxbase) << 5)		\
+		| ((\offset) & 7)
+.endm
+
+/*
+ * LDR (vector to ZA array):
+ *	LDR ZA[\nw, #\offset], [X\nxbase, #\offset, MUL VL]
+ */
+.macro _sme_ldr_zav nw, nxbase, offset=0
+	_sme_check_wv \nw
+	_check_general_reg \nxbase
+	_check_num (\offset), -0x100, 0xff
+	.inst	0xe1000000			\
+		| (((\nw) & 3) << 13)		\
+		| ((\nxbase) << 5)		\
+		| ((\offset) & 7)
+.endm
+
+/*
+ * Zero the entire ZA array
+ *	ZERO ZA
+ */
+.macro zero_za
+	.inst 0xc00800ff
+.endm
+
 .macro __for from:req, to:req
 	.if (\from) == (\to)
 		_for__body %\from
@@ -208,6 +262,17 @@
 921:
 .endm
 
+/* Update SMCR_EL1.LEN with the new VQ */
+.macro sme_load_vq xvqminus1, xtmp, xtmp2
+		mrs_s		\xtmp, SYS_SMCR_EL1
+		bic		\xtmp2, \xtmp, SMCR_ELx_LEN_MASK
+		orr		\xtmp2, \xtmp2, \xvqminus1
+		cmp		\xtmp2, \xtmp
+		b.eq		921f
+		msr_s		SYS_SMCR_EL1, \xtmp2	//self-synchronising
+921:
+.endm
+
 /* Preserve the first 128-bits of Znz and zero the rest. */
 .macro _sve_flush_z nz
 	_sve_check_zreg \nz
@@ -254,3 +319,25 @@
 		ldr		w\nxtmp, [\xpfpsr, #4]
 		msr		fpcr, x\nxtmp
 .endm
+
+.macro sme_save_za nxbase, xvl, nw
+	mov	w\nw, #0
+
+423:
+	_sme_str_zav \nw, \nxbase
+	add	x\nxbase, x\nxbase, \xvl
+	add	x\nw, x\nw, #1
+	cmp	\xvl, x\nw
+	bne	423b
+.endm
+
+.macro sme_load_za nxbase, xvl, nw
+	mov	w\nw, #0
+
+423:
+	_sme_ldr_zav \nw, \nxbase
+	add	x\nxbase, x\nxbase, \xvl
+	add	x\nw, x\nw, #1
+	cmp	\xvl, x\nw
+	bne	423b
+.endm

arch/arm64/include/asm/ftrace.h

@@ -80,8 +80,15 @@ static inline unsigned long ftrace_call_adjust(unsigned long addr)
 
 #ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
 struct dyn_ftrace;
+struct ftrace_ops;
+struct ftrace_regs;
+
 int ftrace_init_nop(struct module *mod, struct dyn_ftrace *rec);
 #define ftrace_init_nop ftrace_init_nop
+
+void ftrace_graph_func(unsigned long ip, unsigned long parent_ip,
+		       struct ftrace_ops *op, struct ftrace_regs *fregs);
+#define ftrace_graph_func ftrace_graph_func
 #endif
 
 #define ftrace_return_address(n) return_address(n)

arch/arm64/include/asm/hugetlb.h

@@ -44,6 +44,8 @@ extern void huge_ptep_clear_flush(struct vm_area_struct *vma,
 #define __HAVE_ARCH_HUGE_PTE_CLEAR
 extern void huge_pte_clear(struct mm_struct *mm, unsigned long addr,
 			   pte_t *ptep, unsigned long sz);
+#define __HAVE_ARCH_HUGE_PTEP_GET
+extern pte_t huge_ptep_get(pte_t *ptep);
 extern void set_huge_swap_pte_at(struct mm_struct *mm, unsigned long addr,
 				 pte_t *ptep, pte_t pte, unsigned long sz);
 #define set_huge_swap_pte_at set_huge_swap_pte_at

arch/arm64/include/asm/hwcap.h

@@ -109,6 +109,14 @@
 #define KERNEL_HWCAP_AFP		__khwcap2_feature(AFP)
 #define KERNEL_HWCAP_RPRES		__khwcap2_feature(RPRES)
 #define KERNEL_HWCAP_MTE3		__khwcap2_feature(MTE3)
+#define KERNEL_HWCAP_SME		__khwcap2_feature(SME)
+#define KERNEL_HWCAP_SME_I16I64		__khwcap2_feature(SME_I16I64)
+#define KERNEL_HWCAP_SME_F64F64		__khwcap2_feature(SME_F64F64)
+#define KERNEL_HWCAP_SME_I8I32		__khwcap2_feature(SME_I8I32)
+#define KERNEL_HWCAP_SME_F16F32		__khwcap2_feature(SME_F16F32)
+#define KERNEL_HWCAP_SME_B16F32		__khwcap2_feature(SME_B16F32)
+#define KERNEL_HWCAP_SME_F32F32		__khwcap2_feature(SME_F32F32)
+#define KERNEL_HWCAP_SME_FA64		__khwcap2_feature(SME_FA64)
 
 /*
  * This yields a mask that user programs can use to figure out what

arch/arm64/include/asm/kvm_arm.h

@@ -279,6 +279,7 @@
 #define CPTR_EL2_TCPAC	(1U << 31)
 #define CPTR_EL2_TAM	(1 << 30)
 #define CPTR_EL2_TTA	(1 << 20)
+#define CPTR_EL2_TSM	(1 << 12)
 #define CPTR_EL2_TFP	(1 << CPTR_EL2_TFP_SHIFT)
 #define CPTR_EL2_TZ	(1 << 8)
 #define CPTR_NVHE_EL2_RES1	0x000032ff /* known RES1 bits in CPTR_EL2 (nVHE) */

arch/arm64/include/asm/kvm_emulate.h

@@ -236,14 +236,14 @@ static inline bool vcpu_mode_priv(const struct kvm_vcpu *vcpu)
 	return mode != PSR_MODE_EL0t;
 }
 
-static __always_inline u32 kvm_vcpu_get_esr(const struct kvm_vcpu *vcpu)
+static __always_inline u64 kvm_vcpu_get_esr(const struct kvm_vcpu *vcpu)
 {
 	return vcpu->arch.fault.esr_el2;
 }
 
 static __always_inline int kvm_vcpu_get_condition(const struct kvm_vcpu *vcpu)
 {
-	u32 esr = kvm_vcpu_get_esr(vcpu);
+	u64 esr = kvm_vcpu_get_esr(vcpu);
 
 	if (esr & ESR_ELx_CV)
 		return (esr & ESR_ELx_COND_MASK) >> ESR_ELx_COND_SHIFT;
@@ -374,7 +374,7 @@ static __always_inline bool kvm_vcpu_abt_issea(const struct kvm_vcpu *vcpu)
 
 static __always_inline int kvm_vcpu_sys_get_rt(struct kvm_vcpu *vcpu)
 {
-	u32 esr = kvm_vcpu_get_esr(vcpu);
+	u64 esr = kvm_vcpu_get_esr(vcpu);
 	return ESR_ELx_SYS64_ISS_RT(esr);
 }
 

arch/arm64/include/asm/kvm_host.h

@@ -153,7 +153,7 @@ struct kvm_arch {
 };
 
 struct kvm_vcpu_fault_info {
-	u32 esr_el2;		/* Hyp Syndrom Register */
+	u64 esr_el2;		/* Hyp Syndrom Register */
 	u64 far_el2;		/* Hyp Fault Address Register */
 	u64 hpfar_el2;		/* Hyp IPA Fault Address Register */
 	u64 disr_el1;		/* Deferred [SError] Status Register */
@@ -295,8 +295,11 @@ struct vcpu_reset_state {
 
 struct kvm_vcpu_arch {
 	struct kvm_cpu_context ctxt;
+
+	/* Guest floating point state */
 	void *sve_state;
 	unsigned int sve_max_vl;
+	u64 svcr;
 
 	/* Stage 2 paging state used by the hardware on next switch */
 	struct kvm_s2_mmu *hw_mmu;
@@ -451,6 +454,7 @@ struct kvm_vcpu_arch {
 #define KVM_ARM64_DEBUG_STATE_SAVE_TRBE	(1 << 13) /* Save TRBE context if active  */
 #define KVM_ARM64_FP_FOREIGN_FPSTATE	(1 << 14)
 #define KVM_ARM64_ON_UNSUPPORTED_CPU	(1 << 15) /* Physical CPU not in supported_cpus */
+#define KVM_ARM64_HOST_SME_ENABLED	(1 << 16) /* SME enabled for EL0 */
 
 #define KVM_GUESTDBG_VALID_MASK (KVM_GUESTDBG_ENABLE | \
 				 KVM_GUESTDBG_USE_SW_BP | \

arch/arm64/include/asm/kvm_ras.h

@@ -14,7 +14,7 @@
  * Was this synchronous external abort a RAS notification?
  * Returns '0' for errors handled by some RAS subsystem, or -ENOENT.
  */
-static inline int kvm_handle_guest_sea(phys_addr_t addr, unsigned int esr)
+static inline int kvm_handle_guest_sea(phys_addr_t addr, u64 esr)
 {
 	/* apei_claim_sea(NULL) expects to mask interrupts itself */
 	lockdep_assert_irqs_enabled();

arch/arm64/include/asm/mte.h

@@ -47,6 +47,7 @@ long set_mte_ctrl(struct task_struct *task, unsigned long arg);
 long get_mte_ctrl(struct task_struct *task);
 int mte_ptrace_copy_tags(struct task_struct *child, long request,
 			 unsigned long addr, unsigned long data);
+size_t mte_probe_user_range(const char __user *uaddr, size_t size);
 
 #else /* CONFIG_ARM64_MTE */