Skip to contentSkip to conversation

4.15.4-stable review

PATCH In review Greg Kroah-Hartman 4 participants 209 messages Feb 15, 2018 – Feb 16, 2018 Page 1 of 2

Subsystems (4)
lore
Share & tools
lore

Greg Kroah-Hartman

author maintainer
#0 lore raw

cover 4.15.4-stable review

This is the start of the stable review cycle for the 4.15.4 release. There are 202 patches in this series, all will be posted as a response to this one. If anyone has any issues with these being applied, please let me know.

Responses should be made by Sat Feb 17 15:16:28 UTC 2018. Anything received after that time might be too late.

The whole patch series can be found in one patch at:

	kernel.org/pub/linux/kernel/v4.x/stable-review/patch-4.15.4-rc1.gz

or in the git tree and branch at:
git://git.kernel.org/pub/scm/linux/kernel/git/stable/linux-stable-rc.git linux-4.15.y
and the diffstat can be found below.

thanks,

greg k-h

-------------
Pseudo-Shortlog of commits:

Greg Kroah-Hartman <[email protected]>

    Linux 4.15.4-rc1

Uma Krishnan <[email protected]>
scsi: cxlflash: Reset command ioasc

James Smart <[email protected]>
scsi: lpfc: Fix crash after bad bar setup on driver attachment

Bart Van Assche <[email protected]>
scsi: core: Ensure that the SCSI error handler gets woken up

Steven Rostedt (VMware) <[email protected]>
ftrace: Remove incorrect setting of glob search field

Eric Biggers <[email protected]>
devpts: fix error handling in devpts_mntget()

Eric W. Biederman <[email protected]>
mn10300/misalignment: Use SIGSEGV SEGV_MAPERR to report a failed user copy

Amir Goldstein <[email protected]>
ovl: hash directory inodes for fsnotify

Amir Goldstein <[email protected]>
ovl: take mnt_want_write() for removing impure xattr

Amir Goldstein <[email protected]>
ovl: take mnt_want_write() for work/index dir setup

Amir Goldstein <[email protected]>
ovl: fix failure to fsync lower dir

Amir Goldstein <[email protected]>
ovl: force r/o mount when index dir creation fails

Toshi Kani <[email protected]>
acpi, nfit: fix register dimm error handling

Greg Kroah-Hartman <[email protected]>
ACPI: sbshc: remove raw pointer from printk() message

Imre Deak <[email protected]>
drm/i915: Avoid PPS HW/SW state mismatch due to rounding

Yan Markman <[email protected]>
arm64: dts: marvell: add Ethernet aliases

Peter Zijlstra <[email protected]>
objtool: Fix switch-table detection

Andrey Ryabinin <[email protected]>
lib/ubsan: add type mismatch handler for new GCC/Clang

Andrew Morton <[email protected]>
lib/ubsan.c: s/missaligned/misaligned/

Daniel Lezcano <[email protected]>
clocksource/drivers/stm32: Fix kernel panic with multiple timers

Ming Lei <[email protected]>
blk-mq: quiesce queue before freeing queue

Bart Van Assche <[email protected]>
pktcdvd: Fix a recently introduced NULL pointer dereference

Bart Van Assche <[email protected]>
pktcdvd: Fix pkt_setup_dev() error path

Peter Rosin <[email protected]>

    pinctrl: sx150x: Add a static gpio/pinctrl pin range mapping

Peter Rosin <[email protected]>

    pinctrl: sx150x: Register pinctrl before adding the gpiochip

Peter Rosin <[email protected]>

    pinctrl: sx150x: Unregister the pinctrl on release

Dmitry Mastykin <[email protected]>
pinctrl: mcp23s08: fix irq setup order

Mika Westerberg <[email protected]>
pinctrl: intel: Initialize GPIO properly when used through irqchip

Thomas Gleixner <[email protected]>
genirq: Make legacy autoprobing work again

James Hogan <[email protected]>
EDAC, octeon: Fix an uninitialized variable warning

Max Filippov <[email protected]>
xtensa: fix futex_atomic_cmpxchg_inatomic

Mikulas Patocka <[email protected]>
alpha: fix formating of stack content

Mikulas Patocka <[email protected]>
alpha: fix reboot on Avanti platform

Michael Cree <[email protected]>
alpha: Fix mixed up args in EXC macro in futex operations

Arnd Bergmann <[email protected]>
alpha: osf_sys.c: fix put_tv32 regression

Mikulas Patocka <[email protected]>
alpha: fix crash if pthread_create races with signal delivery

Eric W. Biederman <[email protected]>
signal/sh: Ensure si_signo is initialized in do_divide_error

Eric W. Biederman <[email protected]>
signal/openrisc: Fix do_unaligned_access to send the proper signal

John Garry <[email protected]>
ipmi: use dynamic memory for DMI driver override

Hans de Goede <[email protected]>
Bluetooth: btusb: Restore QCA Rome suspend/resume fix with a "rewritten" version

Kai-Heng Feng <[email protected]>
Revert "Bluetooth: btusb: fix QCA Rome suspend/resume"

Hans de Goede <[email protected]>
Bluetooth: btsdio: Do not bind to non-removable BCM43341

Hans de Goede <[email protected]>
HID: quirks: Fix keyboard + touchpad on Toshiba Click Mini not working

Eric Biggers <[email protected]>
pipe: fix off-by-one error when checking buffer limits

Eric Biggers <[email protected]>
pipe: actually allow root to exceed the pipe buffer limits

Eric Biggers <[email protected]>
kernel/relay.c: revert "kernel/relay.c: fix potential memory leak"

Rasmus Villemoes <[email protected]>
kernel/async.c: revert "async: simplify lowest_in_progress()"

Heiko Carstens <[email protected]>
fs/proc/kcore.c: use probe_kernel_read() instead of memcpy()

Mauro Carvalho Chehab <[email protected]>

    media: cxusb, dib0700: ignore XC2028_I2C_FLUSH

Hans Verkuil <[email protected]>
media: vivid: fix module load error when enabling fb and no_error_inj=1

Mauro Carvalho Chehab <[email protected]>
media: ts2020: avoid integer overflows on 32 bit machines

Hans Verkuil <[email protected]>
media: dt-bindings/media/cec-gpio.txt: mention the CEC/HPD max voltages

Arnd Bergmann <[email protected]>
media: dvb-frontends: fix i2c access helpers for KASAN

Mauro Carvalho Chehab <[email protected]>
media: dvb_frontend: be sure to init dvb_frontend_handle_ioctl() return code

Arnd Bergmann <[email protected]>
kasan: rework Kconfig settings

Andrey Konovalov <[email protected]>
kasan: don't emit builtin calls when sanitization is off

Liu Bo <[email protected]>
Btrfs: raid56: iterate raid56 internal bio with bio_for_each_segment_all

Nikolay Borisov <[email protected]>
btrfs: Handle btrfs_set_extent_delalloc failure in fixup worker

David Howells <[email protected]>
afs: Fix server list handling

David Howells <[email protected]>
afs: Fix missing cursor clearance

David Howells <[email protected]>
afs: Need to clear responded flag in addr cursor

David Howells <[email protected]>
afs: Add missing afs_put_cell()

Martin Kaiser <[email protected]>
watchdog: imx2_wdt: restore previous timeout after suspend+resume

Charles Keepax <[email protected]>
ASoC: compress: Correct handling of copy callback

Takashi Iwai <[email protected]>
ASoC: skl: Fix kernel warning due to zero NHTL entry

John Keeping <[email protected]>
ASoC: rockchip: i2s: fix playback after runtime resume

Pierre-Louis Bossart <[email protected]>
ASoC: acpi: fix machine driver selection based on quirk

Ulf Magnusson <[email protected]>
KVM: PPC: Book3S PR: Fix broken select due to misspelling

James Morse <[email protected]>
KVM: arm/arm64: Handle CPU_PM_ENTER_FAILED

Paul Mackerras <[email protected]>
KVM: PPC: Book3S HV: Drop locks before reading guest memory

Paul Mackerras <[email protected]>
KVM: PPC: Book3S HV: Make sure we don't re-enter guest without XIVE loaded

Liran Alon <[email protected]>
KVM: nVMX: Fix bug of injecting L2 exception into L1

Liran Alon <[email protected]>
KVM: nVMX: Fix races when sending nested PI while dest enters/leaves L2

Marc Zyngier <[email protected]>
arm: KVM: Fix SMCCC handling of unimplemented SMC/HVC calls

LEROY Christophe <[email protected]>
crypto: talitos - fix Kernel Oops on hashing an empty file

Eric Biggers <[email protected]>
crypto: sha512-mb - initialize pending lengths correctly

Horia Geantă <[email protected]>
crypto: caam - fix endless loop when DECO acquire fails

Hans Verkuil <[email protected]>
media: v4l2-compat-ioctl32.c: make ctrl_is_pointer work for subdevs

Daniel Mentz <[email protected]>
media: v4l2-compat-ioctl32.c: refactor compat ioctl32 logic

Hans Verkuil <[email protected]>
media: v4l2-compat-ioctl32.c: don't copy back the result for certain errors

Hans Verkuil <[email protected]>
media: v4l2-compat-ioctl32.c: drop pr_info for unknown buffer type

Hans Verkuil <[email protected]>
media: v4l2-compat-ioctl32.c: copy clip list in put_v4l2_window32

Hans Verkuil <[email protected]>
media: v4l2-compat-ioctl32.c: fix ctrl_is_pointer

Hans Verkuil <[email protected]>
media: v4l2-compat-ioctl32.c: copy m.userptr in put_v4l2_plane32

Hans Verkuil <[email protected]>
media: v4l2-compat-ioctl32.c: avoid sizeof(type)

Hans Verkuil <[email protected]>
media: v4l2-compat-ioctl32.c: move 'helper' functions to __get/put_v4l2_format32

Hans Verkuil <[email protected]>
media: v4l2-compat-ioctl32.c: fix the indentation

Hans Verkuil <[email protected]>
media: v4l2-compat-ioctl32.c: add missing VIDIOC_PREPARE_BUF

Hans Verkuil <[email protected]>
media: v4l2-ioctl.c: don't copy back the result for -ENOTTY

Hans Verkuil <[email protected]>
media: v4l2-ioctl.c: use check_fmt for enum/g/s/try_fmt

Eric Biggers <[email protected]>
crypto: hash - prevent using keyed hashes without setting key

Eric Biggers <[email protected]>
crypto: hash - annotate algorithms taking optional key

Eric Biggers <[email protected]>

    crypto: poly1305 - remove ->setkey() method

Eric Biggers <[email protected]>

    crypto: mcryptd - pass through absence of ->setkey()

Eric Biggers <[email protected]>

    crypto: cryptd - pass through absence of ->setkey()

Eric Biggers <[email protected]>
crypto: hash - introduce crypto_hash_alg_has_setkey()

Mika Westerberg <[email protected]>
ahci: Add Intel Cannon Lake PCH-H PCI ID

Hans de Goede <[email protected]>
ahci: Add PCI ids for Intel Bay Trail, Cherry Trail and Apollo Lake AHCI

Hans de Goede <[email protected]>
ahci: Annotate PCI ids for mobile Intel chipsets as such

Ivan Vecera <[email protected]>
kernfs: fix regression in kernfs_fop_write caused by wrong type

Trond Myklebust <[email protected]>
nfsd: Detect unhashed stids in nfsd4_verify_open_stid()

Trond Myklebust <[email protected]>
NFS: Fix a race between mmap() and O_DIRECT

Eric Biggers <[email protected]>
NFS: reject request for id_legacy key without auxdata

J. Bruce Fields <[email protected]>
NFS: commit direct writes even if they fail partially

Trond Myklebust <[email protected]>
NFS: Fix nfsstat breakage due to LOOKUPP

Trond Myklebust <[email protected]>
NFS: Add a cond_resched() to nfs_commit_release_pages()

Tigran Mkrtchyan <[email protected]>
nfs41: do not return ENOMEM on LAYOUTUNAVAILABLE

Scott Mayhew <[email protected]>
nfs/pnfs: fix nfs_direct_req ref leak when i/o falls back to the mds

Eric Biggers <[email protected]>
ubifs: free the encrypted symlink target

Bradley Bolen <[email protected]>
ubi: block: Fix locking for idr_alloc/idr_remove

Sascha Hauer <[email protected]>
ubi: fastmap: Erase outdated anchor PEBs during attach

Clay McClure <[email protected]>
ubi: Fix race condition between ubi volume creation and udev

Miquel Raynal <[email protected]>
mtd: nand: sunxi: Fix ECC strength choice

Miquel Raynal <[email protected]>
mtd: nand: Fix nand_do_read_oob() return value

Kamal Dasu <[email protected]>
mtd: nand: brcmnand: Disable prefetch by default

Arnd Bergmann <[email protected]>
mtd: cfi: convert inline functions to macros

Marc Zyngier <[email protected]>
arm64: Kill PSCI_GET_VERSION as a variant-2 workaround

Marc Zyngier <[email protected]>
arm64: Add ARM_SMCCC_ARCH_WORKAROUND_1 BP hardening support

Marc Zyngier <[email protected]>
arm/arm64: smccc: Implement SMCCC v1.1 inline primitive

Marc Zyngier <[email protected]>
arm/arm64: smccc: Make function identifiers an unsigned quantity

Marc Zyngier <[email protected]>
firmware/psci: Expose SMCCC version through psci_ops

Marc Zyngier <[email protected]>
firmware/psci: Expose PSCI conduit

Marc Zyngier <[email protected]>
arm64: KVM: Add SMCCC_ARCH_WORKAROUND_1 fast handling

Marc Zyngier <[email protected]>
arm64: KVM: Report SMCCC_ARCH_WORKAROUND_1 BP hardening support

Marc Zyngier <[email protected]>
arm/arm64: KVM: Turn kvm_psci_version into a static inline

Marc Zyngier <[email protected]>
arm64: KVM: Make PSCI_VERSION a fast path

Marc Zyngier <[email protected]>
arm/arm64: KVM: Advertise SMCCC v1.1

Marc Zyngier <[email protected]>
arm/arm64: KVM: Implement PSCI 1.0 support

Marc Zyngier <[email protected]>
arm/arm64: KVM: Add smccc accessors to PSCI code

Marc Zyngier <[email protected]>
arm/arm64: KVM: Add PSCI_VERSION helper

Marc Zyngier <[email protected]>
arm/arm64: KVM: Consolidate the PSCI include files

Marc Zyngier <[email protected]>
arm64: KVM: Increment PC after handling an SMC trap

Jayachandran C <[email protected]>
arm64: Branch predictor hardening for Cavium ThunderX2

Shanker Donthineni <[email protected]>
arm64: Implement branch predictor hardening for Falkor

Will Deacon <[email protected]>
arm64: Implement branch predictor hardening for affected Cortex-A CPUs

Will Deacon <[email protected]>
arm64: cputype: Add missing MIDR values for Cortex-A72 and Cortex-A75

Will Deacon <[email protected]>
arm64: entry: Apply BP hardening for suspicious interrupts from EL0

Will Deacon <[email protected]>
arm64: entry: Apply BP hardening for high-priority synchronous exceptions

Marc Zyngier <[email protected]>
arm64: KVM: Use per-CPU vector when BP hardening is enabled

Marc Zyngier <[email protected]>
arm64: Move BP hardening to check_and_switch_context

Will Deacon <[email protected]>
arm64: Add skeleton to harden the branch predictor against aliasing attacks

Marc Zyngier <[email protected]>
arm64: Move post_ttbr_update_workaround to C code

Will Deacon <[email protected]>
drivers/firmware: Expose psci_get_version through psci_ops structure

Will Deacon <[email protected]>

    arm64: cpufeature: Pass capability structure to ->enable callback

Suzuki K Poulose <[email protected]>
arm64: Run enable method for errata work arounds on late CPUs

James Morse <[email protected]>
arm64: cpufeature: __this_cpu_has_cap() shouldn't stop early

Will Deacon <[email protected]>
arm64: futex: Mask __user pointers prior to dereference

Will Deacon <[email protected]>
arm64: uaccess: Mask __user pointers for __arch_{clear, copy_*}_user

Will Deacon <[email protected]>
arm64: uaccess: Don't bother eliding access_ok checks in __{get, put}_user

Will Deacon <[email protected]>
arm64: uaccess: Prevent speculative use of the current addr_limit

Will Deacon <[email protected]>
arm64: entry: Ensure branch through syscall table is bounded under speculation

Robin Murphy <[email protected]>
arm64: Use pointer masking to limit uaccess speculation

Robin Murphy <[email protected]>
arm64: Make USER_DS an inclusive limit

Robin Murphy <[email protected]>
arm64: Implement array_index_mask_nospec()

Will Deacon <[email protected]>
arm64: barrier: Add CSDB macros to control data-value prediction

Will Deacon <[email protected]>
perf: arm_spe: Fail device probe when arm64_kernel_unmapped_at_el0()

Will Deacon <[email protected]>
arm64: idmap: Use "awx" flags for .idmap.text .pushsection directives

Will Deacon <[email protected]>
arm64: entry: Reword comment about post_ttbr_update_workaround

Marc Zyngier <[email protected]>
arm64: Force KPTI to be disabled on Cavium ThunderX

Will Deacon <[email protected]>

    arm64: kpti: Add ->enable callback to remap swapper using nG mappings

Will Deacon <[email protected]>
arm64: mm: Permit transitioning from Global to Non-Global without BBM

Will Deacon <[email protected]>
arm64: kpti: Make use of nG dependent on arm64_kernel_unmapped_at_el0()

Jayachandran C <[email protected]>
arm64: Turn on KPTI only on CPUs that need it

Jayachandran C <[email protected]>
arm64: cputype: Add MIDR values for Cavium ThunderX2 CPUs

Catalin Marinas <[email protected]>
arm64: kpti: Fix the interaction between ASID switching and software PAN

Will Deacon <[email protected]>
arm64: mm: Introduce TTBR_ASID_MASK for getting at the ASID in the TTBR

Suzuki K Poulose <[email protected]>
arm64: capabilities: Handle duplicate entries for a capability

Will Deacon <[email protected]>
arm64: Take into account ID_AA64PFR0_EL1.CSV3

Will Deacon <[email protected]>
arm64: Kconfig: Reword UNMAP_KERNEL_AT_EL0 kconfig entry

Will Deacon <[email protected]>
arm64: Kconfig: Add CONFIG_UNMAP_KERNEL_AT_EL0

Will Deacon <[email protected]>
arm64: use RET instruction for exiting the trampoline

Will Deacon <[email protected]>
arm64: kaslr: Put kernel vectors address in separate data page

Will Deacon <[email protected]>
arm64: entry: Add fake CPU feature for unmapping the kernel at EL0

Will Deacon <[email protected]>
arm64: tls: Avoid unconditional zeroing of tpidrro_el0 for native tasks

Stephen Boyd <[email protected]>
arm64: cpu_errata: Add Kryo to Falkor 1003 errata

Will Deacon <[email protected]>
arm64: erratum: Work around Falkor erratum #E1003 in trampoline code

Will Deacon <[email protected]>
arm64: entry: Hook up entry trampoline to exception vectors

Will Deacon <[email protected]>
arm64: entry: Explicitly pass exception level to kernel_ventry macro

Will Deacon <[email protected]>
arm64: mm: Map entry trampoline into trampoline and kernel page tables

Will Deacon <[email protected]>
arm64: entry: Add exception trampoline page for exceptions from EL0

Will Deacon <[email protected]>
arm64: mm: Invalidate both kernel and user ASIDs when performing TLBI

Will Deacon <[email protected]>
arm64: mm: Add arm64_kernel_unmapped_at_el0 helper

Will Deacon <[email protected]>
arm64: mm: Allocate ASIDs in pairs

Will Deacon <[email protected]>
arm64: mm: Fix and re-enable ARM64_SW_TTBR0_PAN

Will Deacon <[email protected]>
arm64: mm: Rename post_ttbr0_update_workaround

Will Deacon <[email protected]>
arm64: mm: Remove pre_ttbr0_update_workaround for Falkor erratum #E1003

Will Deacon <[email protected]>
arm64: mm: Move ASID from TTBR0 to TTBR1

Will Deacon <[email protected]>
arm64: mm: Temporarily disable ARM64_SW_TTBR0_PAN

Will Deacon <[email protected]>
arm64: mm: Use non-global mappings for kernel space

Arvind Yadav <[email protected]>
media: hdpvr: Fix an error handling path in hdpvr_probe()

Malcolm Priestley <[email protected]>

    media: dvb-usb-v2: lmedm04: move ts2020 attach to dm04_lme2510_tuner

Malcolm Priestley <[email protected]>
media: dvb-usb-v2: lmedm04: Improve logic checking of warm start

Steven Rostedt (VMware) <[email protected]>
sched/rt: Up the root domain ref count when passing it around via IPIs

Steven Rostedt (VMware) <[email protected]>
sched/rt: Use container_of() to get root domain in rto_push_irq_work_func()

Lionel Landwerlin <[email protected]>
Revert "drm/i915: mark all device info struct with __initconst"

Rasmus Villemoes <[email protected]>
watchdog: gpio_wdt: set WDOG_HW_RUNNING in gpio_wdt_stop

Sven Joachim <[email protected]>
ssb: Do not disable PCI host on non-Mips

Yang Shunyong <[email protected]>
dmaengine: dmatest: fix container_of member in dmatest_callback

Andrew-sh Cheng <[email protected]>
cpufreq: mediatek: add mediatek related projects into blacklist

Aurelien Aptel <[email protected]>
CIFS: zero sensitive data when freeing

Daniel N Pettersson <[email protected]>
cifs: Fix autonegotiate security settings mismatch

Matthew Wilcox <[email protected]>
cifs: Fix missing put_xid in cifs_file_strict_mmap

Matt Redfearn <[email protected]>
watchdog: indydog: Add dependency on SGI_HAS_INDYDOG

-------------

Diffstat:

 Documentation/arm64/silicon-errata.txt             |    2 +-
 .../devicetree/bindings/media/cec-gpio.txt         |    6 +-
 Makefile                                           |    7 +-
 arch/alpha/include/asm/futex.h                     |    8 +-
 arch/alpha/kernel/osf_sys.c                        |    4 +-
 arch/alpha/kernel/pci_impl.h                       |    3 +-
 arch/alpha/kernel/process.c                        |    3 +-
 arch/alpha/kernel/traps.c                          |   13 +-
 arch/arm/crypto/crc32-ce-glue.c                    |    2 +
 arch/arm/include/asm/kvm_host.h                    |    6 +
 arch/arm/include/asm/kvm_mmu.h                     |   10 +
 arch/arm/include/asm/kvm_psci.h                    |   27 -
 arch/arm/kvm/handle_exit.c                         |   17 +-
 arch/arm64/Kconfig                                 |   46 +-
 arch/arm64/boot/dts/marvell/armada-7040-db.dts     |    6 +
 arch/arm64/boot/dts/marvell/armada-8040-db.dts     |    7 +
 arch/arm64/boot/dts/marvell/armada-8040-mcbin.dts  |    6 +
 arch/arm64/crypto/crc32-ce-glue.c                  |    2 +
 arch/arm64/include/asm/asm-uaccess.h               |   36 +-
 arch/arm64/include/asm/assembler.h                 |   54 +-
 arch/arm64/include/asm/barrier.h                   |   22 +
 arch/arm64/include/asm/cpucaps.h                   |    5 +-
 arch/arm64/include/asm/cputype.h                   |    9 +
 arch/arm64/include/asm/efi.h                       |   12 +-
 arch/arm64/include/asm/fixmap.h                    |    5 +
 arch/arm64/include/asm/futex.h                     |    9 +-
 arch/arm64/include/asm/kvm_asm.h                   |    2 +
 arch/arm64/include/asm/kvm_host.h                  |    5 +
 arch/arm64/include/asm/kvm_mmu.h                   |   38 +
 arch/arm64/include/asm/kvm_psci.h                  |   27 -
 arch/arm64/include/asm/mmu.h                       |   48 +
 arch/arm64/include/asm/mmu_context.h               |   12 +-
 arch/arm64/include/asm/pgtable-hwdef.h             |    1 +
 arch/arm64/include/asm/pgtable-prot.h              |   35 +-
 arch/arm64/include/asm/pgtable.h                   |    1 +
 arch/arm64/include/asm/proc-fns.h                  |    6 -
 arch/arm64/include/asm/processor.h                 |    3 +
 arch/arm64/include/asm/sysreg.h                    |    2 +
 arch/arm64/include/asm/tlbflush.h                  |   16 +-
 arch/arm64/include/asm/uaccess.h                   |  181 +++-
 arch/arm64/kernel/Makefile                         |    4 +
 arch/arm64/kernel/arm64ksyms.c                     |    4 +-
 arch/arm64/kernel/asm-offsets.c                    |    6 +-
 arch/arm64/kernel/bpi.S                            |   83 ++
 arch/arm64/kernel/cpu-reset.S                      |    2 +-
 arch/arm64/kernel/cpu_errata.c                     |  239 ++++-
 arch/arm64/kernel/cpufeature.c                     |  138 ++-
 arch/arm64/kernel/entry.S                          |  228 ++++-
 arch/arm64/kernel/head.S                           |    2 +-
 arch/arm64/kernel/process.c                        |   12 +-
 arch/arm64/kernel/sleep.S                          |    2 +-
 arch/arm64/kernel/vmlinux.lds.S                    |   22 +-
 arch/arm64/kvm/handle_exit.c                       |   14 +-
 arch/arm64/kvm/hyp/entry.S                         |   12 +
 arch/arm64/kvm/hyp/hyp-entry.S                     |   20 +-
 arch/arm64/kvm/hyp/switch.c                        |   13 +-
 arch/arm64/lib/clear_user.S                        |   10 +-
 arch/arm64/lib/copy_from_user.S                    |    4 +-
 arch/arm64/lib/copy_in_user.S                      |    9 +-
 arch/arm64/lib/copy_to_user.S                      |    4 +-
 arch/arm64/mm/cache.S                              |    4 +-
 arch/arm64/mm/context.c                            |   48 +-
 arch/arm64/mm/fault.c                              |   36 +-
 arch/arm64/mm/mmu.c                                |   35 +
 arch/arm64/mm/proc.S                               |  224 ++++-
 arch/arm64/xen/hypercall.S                         |    4 +-
 arch/mn10300/mm/misalignment.c                     |    2 +-
 arch/openrisc/kernel/traps.c                       |   10 +-
 arch/powerpc/crypto/crc32c-vpmsum_glue.c           |    1 +
 arch/powerpc/kvm/Kconfig                           |    2 +-
 arch/powerpc/kvm/book3s_hv.c                       |   16 +-
 arch/powerpc/kvm/book3s_hv_rmhandlers.S            |   40 +-
 arch/s390/crypto/crc32-vx.c                        |    3 +
 arch/sh/kernel/traps_32.c                          |    3 +-
 arch/sparc/crypto/crc32c_glue.c                    |    1 +
 arch/x86/crypto/crc32-pclmul_glue.c                |    1 +
 arch/x86/crypto/crc32c-intel_glue.c                |    1 +
 arch/x86/crypto/poly1305_glue.c                    |    1 -
 .../x86/crypto/sha512-mb/sha512_mb_mgr_init_avx2.c |   10 +-
 arch/x86/kvm/vmx.c                                 |    6 +-
 arch/x86/kvm/x86.h                                 |    1 +
 arch/xtensa/include/asm/futex.h                    |   23 +-
 block/blk-core.c                                   |    9 +
 crypto/ahash.c                                     |   33 +-
 crypto/algif_hash.c                                |   52 +-
 crypto/crc32_generic.c                             |    1 +
 crypto/crc32c_generic.c                            |    1 +
 crypto/cryptd.c                                    |   10 +-
 crypto/mcryptd.c                                   |   10 +-
 crypto/poly1305_generic.c                          |   17 +-
 crypto/shash.c                                     |   25 +-
 drivers/acpi/nfit/core.c                           |    3 +
 drivers/acpi/sbshc.c                               |    4 +-
 drivers/ata/ahci.c                                 |   37 +-
 drivers/block/pktcdvd.c                            |   12 +-
 drivers/bluetooth/btsdio.c                         |    9 +
 drivers/bluetooth/btusb.c                          |   20 +-
 drivers/char/ipmi/ipmi_dmi.c                       |    5 +-
 drivers/clocksource/timer-stm32.c                  |    7 +-
 drivers/cpufreq/cpufreq-dt-platdev.c               |    8 +
 drivers/crypto/bfin_crc.c                          |    3 +-
 drivers/crypto/caam/ctrl.c                         |    8 +-
 drivers/crypto/stm32/stm32_crc32.c                 |    2 +
 drivers/crypto/talitos.c                           |    4 +
 drivers/dma/dmatest.c                              |    2 +-
 drivers/edac/octeon_edac-lmc.c                     |    1 +
 drivers/firmware/psci.c                            |   57 +-
 drivers/gpu/drm/i915/i915_pci.c                    |   94 +-
 drivers/gpu/drm/i915/intel_dp.c                    |    6 +
 drivers/hid/hid-core.c                             |   12 +-
 drivers/media/dvb-core/dvb_frontend.c              |    4 +-
 drivers/media/dvb-frontends/ascot2e.c              |    4 +-
 drivers/media/dvb-frontends/cxd2841er.c            |    4 +-
 drivers/media/dvb-frontends/helene.c               |    4 +-
 drivers/media/dvb-frontends/horus3a.c              |    4 +-
 drivers/media/dvb-frontends/itd1000.c              |    5 +-
 drivers/media/dvb-frontends/mt312.c                |    5 +-
 drivers/media/dvb-frontends/stb0899_drv.c          |    3 +-
 drivers/media/dvb-frontends/stb6100.c              |    6 +-
 drivers/media/dvb-frontends/stv0367.c              |    4 +-
 drivers/media/dvb-frontends/stv090x.c              |    4 +-
 drivers/media/dvb-frontends/stv6110x.c             |    4 +-
 drivers/media/dvb-frontends/ts2020.c               |    4 +-
 drivers/media/dvb-frontends/zl10039.c              |    4 +-
 drivers/media/platform/vivid/vivid-core.h          |    1 +
 drivers/media/platform/vivid/vivid-ctrls.c         |   35 +-
 drivers/media/usb/dvb-usb-v2/lmedm04.c             |   39 +-
 drivers/media/usb/dvb-usb/cxusb.c                  |    2 +
 drivers/media/usb/dvb-usb/dib0700_devices.c        |    1 +
 drivers/media/usb/hdpvr/hdpvr-core.c               |   26 +-
 drivers/media/v4l2-core/v4l2-compat-ioctl32.c      | 1032 ++++++++++++--------
 drivers/media/v4l2-core/v4l2-ioctl.c               |  145 ++-
 drivers/mtd/nand/brcmnand/brcmnand.c               |   13 +-
 drivers/mtd/nand/nand_base.c                       |    5 +-
 drivers/mtd/nand/sunxi_nand.c                      |    8 +-
 drivers/mtd/ubi/block.c                            |   42 +-
 drivers/mtd/ubi/vmt.c                              |   15 +-
 drivers/mtd/ubi/wl.c                               |   77 +-
 drivers/perf/arm_spe_pmu.c                         |    9 +
 drivers/pinctrl/intel/pinctrl-intel.c              |   23 +-
 drivers/pinctrl/pinctrl-mcp23s08.c                 |    8 +-
 drivers/pinctrl/pinctrl-sx150x.c                   |   40 +-
 drivers/scsi/cxlflash/main.c                       |    1 +
 drivers/scsi/hosts.c                               |    6 +
 drivers/scsi/lpfc/lpfc_init.c                      |   84 +-
 drivers/scsi/scsi_error.c                          |   18 +-
 drivers/scsi/scsi_lib.c                            |   39 +-
 drivers/ssb/Kconfig                                |    2 +-
 .../lustre/lnet/libcfs/linux/linux-crypto-adler.c  |    1 +
 drivers/watchdog/Kconfig                           |    2 +-
 drivers/watchdog/gpio_wdt.c                        |    3 +-
 drivers/watchdog/imx2_wdt.c                        |   20 +-
 fs/afs/addr_list.c                                 |   13 +-
 fs/afs/rotate.c                                    |   20 +-
 fs/afs/server_list.c                               |    3 +-
 fs/afs/vlclient.c                                  |   10 +-
 fs/afs/volume.c                                    |   47 +-
 fs/btrfs/inode.c                                   |   11 +-
 fs/btrfs/raid56.c                                  |   11 +-
 fs/cifs/cifsencrypt.c                              |    3 +-
 fs/cifs/connect.c                                  |    6 +-
 fs/cifs/file.c                                     |   26 +-
 fs/cifs/misc.c                                     |   14 +-
 fs/cifs/smb2pdu.c                                  |    3 +-
 fs/devpts/inode.c                                  |    4 +-
 fs/kernfs/file.c                                   |    2 +-
 fs/nfs/direct.c                                    |    4 +-
 fs/nfs/filelayout/filelayout.c                     |    4 +-
 fs/nfs/io.c                                        |    2 +-
 fs/nfs/nfs4idmap.c                                 |    6 +-
 fs/nfs/nfs4xdr.c                                   |   64 +-
 fs/nfs/pnfs.c                                      |    4 +-
 fs/nfs/write.c                                     |    2 +
 fs/nfsd/nfs4state.c                                |    1 +
 fs/overlayfs/inode.c                               |   39 +-
 fs/overlayfs/readdir.c                             |   17 +-
 fs/overlayfs/super.c                               |   38 +-
 fs/overlayfs/util.c                                |    4 +-
 fs/pipe.c                                          |   15 +-
 fs/proc/kcore.c                                    |   18 +-
 fs/ubifs/dir.c                                     |   10 +-
 include/crypto/hash.h                              |   34 +-
 include/crypto/internal/hash.h                     |    2 +
 include/crypto/poly1305.h                          |    2 -
 include/kvm/arm_psci.h                             |   51 +
 include/linux/arm-smccc.h                          |  165 +++-
 include/linux/crypto.h                             |    8 +
 include/linux/mtd/map.h                            |  130 ++-
 include/linux/nfs4.h                               |   12 +-
 include/linux/psci.h                               |   14 +
 include/scsi/scsi_host.h                           |    2 +
 include/uapi/linux/psci.h                          |    3 +
 kernel/async.c                                     |   20 +-
 kernel/irq/autoprobe.c                             |    2 +-
 kernel/irq/chip.c                                  |    6 +-
 kernel/irq/internals.h                             |    2 +-
 kernel/relay.c                                     |    1 -
 kernel/sched/rt.c                                  |   24 +-
 kernel/sched/sched.h                               |    2 +
 kernel/sched/topology.c                            |   13 +
 kernel/trace/ftrace.c                              |    1 -
 lib/Kconfig.debug                                  |    2 +-
 lib/Kconfig.kasan                                  |   11 +
 lib/ubsan.c                                        |   50 +-
 lib/ubsan.h                                        |   14 +
 scripts/Makefile.kasan                             |    5 +
 scripts/Makefile.lib                               |    2 +-
 sound/soc/intel/skylake/skl-nhlt.c                 |    3 +-
 sound/soc/rockchip/rockchip_i2s.c                  |    6 +
 sound/soc/soc-acpi.c                               |    8 +-
 sound/soc/soc-compress.c                           |    8 +-
 tools/objtool/check.c                              |   41 +-
 tools/objtool/check.h                              |    1 +
 virt/kvm/arm/arm.c                                 |   11 +-
 virt/kvm/arm/psci.c                                |  143 ++-
 215 files changed, 3788 insertions(+), 1624 deletions(-)
author maintainer
#1 lore raw

PATCH 1/202 watchdog: indydog: Add dependency on SGI_HAS_INDYDOG

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Matt Redfearn <[email protected]>

commit 24f8d233074badd4c18e4dafd2fb97d65838afed upstream.

Commit da2a68b3eb47 ("watchdog: Enable COMPILE_TEST where possible") enabled building the Indy watchdog driver when COMPILE_TEST is enabled. However, the driver makes reference to symbols that are only defined for certain platforms are selected in the config. These platforms select SGI_HAS_INDYDOG. Without this, link time errors result, for example when building a MIPS allyesconfig.

drivers/watchdog/indydog.o: In function `indydog_write':
indydog.c:(.text+0x18): undefined reference to sgimc' indydog.c:(.text+0x1c): undefined reference to sgimc' drivers/watchdog/indydog.o: In function `indydog_start':
indydog.c:(.text+0x54): undefined reference to sgimc' indydog.c:(.text+0x58): undefined reference to sgimc' drivers/watchdog/indydog.o: In function `indydog_stop':
indydog.c:(.text+0xa4): undefined reference to sgimc' drivers/watchdog/indydog.o:indydog.c:(.text+0xa8): more undefined references to sgimc' follow
make: *** [Makefile:1005: vmlinux] Error 1

Fix this by ensuring that CONFIG_INDIDOG can only be selected when the necessary dependent platform symbols are built in.

Fixes da2a68b3eb47 ("watchdog: Enable COMPILE_TEST where possible")
---
 drivers/watchdog/Kconfig |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/watchdog/Kconfig +1 -1
@@ -1451,7 +1451,7 @@ config RC32434_WDT
 
 config INDYDOG
 	tristate "Indy/I2 Hardware Watchdog"
-	depends on SGI_HAS_INDYDOG || (MIPS && COMPILE_TEST)
+	depends on SGI_HAS_INDYDOG
 	help
 	  Hardware driver for the Indy's/I2's watchdog. This is a
 	  watchdog timer that will reboot the machine after a 60 second
author maintainer
#2 lore raw

PATCH 2/202 cifs: Fix missing put_xid in cifs_file_strict_mmap

In reply to Greg Kroah-Hartman

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Matthew Wilcox <[email protected]>

commit f04a703c3d613845ae3141bfaf223489de8ab3eb upstream.

If cifs_zap_mapping() returned an error, we would return without putting the xid that we got earlier. Restructure cifs_file_strict_mmap() and cifs_file_mmap() to be more similar to each other and have a single point of return that always puts the xid.

---
 fs/cifs/file.c |   26 ++++++++++++--------------
 1 file changed, 12 insertions(+), 14 deletions(-)
fs/cifs/file.c +12 -14
@@ -3471,20 +3471,18 @@ static const struct vm_operations_struct
 
 int cifs_file_strict_mmap(struct file *file, struct vm_area_struct *vma)
 {
-	int rc, xid;
+	int xid, rc = 0;
 	struct inode *inode = file_inode(file);
 
 	xid = get_xid();
 
-	if (!CIFS_CACHE_READ(CIFS_I(inode))) {
+	if (!CIFS_CACHE_READ(CIFS_I(inode)))
 		rc = cifs_zap_mapping(inode);
-		if (rc)
-			return rc;
-	}
-
-	rc = generic_file_mmap(file, vma);
-	if (rc == 0)
+	if (!rc)
+		rc = generic_file_mmap(file, vma);
+	if (!rc)
 		vma->vm_ops = &cifs_file_vm_ops;
+
 	free_xid(xid);
 	return rc;
 }
@@ -3494,16 +3492,16 @@ int cifs_file_mmap(struct file *file, st
 	int rc, xid;
 
 	xid = get_xid();
+
 	rc = cifs_revalidate_file(file);
-	if (rc) {
+	if (rc)
 		cifs_dbg(FYI, "Validation prior to mmap failed, error=%d\n",
 			 rc);
-		free_xid(xid);
-		return rc;
-	}
-	rc = generic_file_mmap(file, vma);
-	if (rc == 0)
+	if (!rc)
+		rc = generic_file_mmap(file, vma);
+	if (!rc)
 		vma->vm_ops = &cifs_file_vm_ops;
+
 	free_xid(xid);
 	return rc;
 }
author maintainer
#3 lore raw

PATCH 3/202 cifs: Fix autonegotiate security settings mismatch

In reply to Greg Kroah-Hartman

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Daniel N Pettersson <[email protected]>

commit 9aca7e454415f7878b28524e76bebe1170911a88 upstream.

Autonegotiation gives a security settings mismatch error if the SMB server selects an SMBv3 dialect that isn't SMB3.02. The exact error is "protocol revalidation - security settings mismatch".
This can be tested using Samba v4.2 or by setting the global Samba setting max protocol = SMB3_00.

The check that fails in smb3_validate_negotiate is the dialect verification of the negotiate info response. This is because it tries to verify against the protocol_id in the global smbdefault_values. The protocol_id in smbdefault_values is SMB3.02.
In SMB2_negotiate the protocol_id in smbdefault_values isn't updated, it is global so it probably shouldn't be, but server->dialect is.

This patch changes the check in smb3_validate_negotiate to use server->dialect instead of server->vals->protocol_id. The patch works with autonegotiate and when using a specific version in the vers mount option.

---
 fs/cifs/smb2pdu.c |    3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)
fs/cifs/smb2pdu.c +1 -2
@@ -733,8 +733,7 @@ int smb3_validate_negotiate(const unsign
 	}
 
 	/* check validate negotiate info response matches what we got earlier */
-	if (pneg_rsp->Dialect !=
-			cpu_to_le16(tcon->ses->server->vals->protocol_id))
+	if (pneg_rsp->Dialect != cpu_to_le16(tcon->ses->server->dialect))
 		goto vneg_out;
 
 	if (pneg_rsp->SecurityMode != cpu_to_le16(tcon->ses->server->sec_mode))
author maintainer
#4 lore raw

PATCH 4/202 CIFS: zero sensitive data when freeing

In reply to Greg Kroah-Hartman

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Aurelien Aptel <[email protected]>

commit 97f4b7276b829a8927ac903a119bef2f963ccc58 upstream.

also replaces memset()+kfree() by kzfree().

---
 fs/cifs/cifsencrypt.c |    3 +--
 fs/cifs/connect.c     |    6 +++---
 fs/cifs/misc.c        |   14 ++++----------
 3 files changed, 8 insertions(+), 15 deletions(-)
fs/cifs/cifsencrypt.c +1 -2
@@ -325,9 +325,8 @@ int calc_lanman_hash(const char *passwor
 {
 	int i;
 	int rc;
-	char password_with_pad[CIFS_ENCPWD_SIZE];
+	char password_with_pad[CIFS_ENCPWD_SIZE] = {0};
 
-	memset(password_with_pad, 0, CIFS_ENCPWD_SIZE);
 	if (password)
 		strncpy(password_with_pad, password, CIFS_ENCPWD_SIZE);
 
fs/cifs/connect.c +3 -3
@@ -1707,7 +1707,7 @@ cifs_parse_mount_options(const char *mou
 			tmp_end++;
 			if (!(tmp_end < end && tmp_end[1] == delim)) {
 				/* No it is not. Set the password to NULL */
-				kfree(vol->password);
+				kzfree(vol->password);
 				vol->password = NULL;
 				break;
 			}
@@ -1745,7 +1745,7 @@ cifs_parse_mount_options(const char *mou
 					options = end;
 			}
 
-			kfree(vol->password);
+			kzfree(vol->password);
 			/* Now build new password string */
 			temp_len = strlen(value);
 			vol->password = kzalloc(temp_len+1, GFP_KERNEL);
@@ -4235,7 +4235,7 @@ cifs_construct_tcon(struct cifs_sb_info
 		reset_cifs_unix_caps(0, tcon, NULL, vol_info);
 out:
 	kfree(vol_info->username);
-	kfree(vol_info->password);
+	kzfree(vol_info->password);
 	kfree(vol_info);
 
 	return tcon;
fs/cifs/misc.c +4 -10
@@ -98,14 +98,11 @@ sesInfoFree(struct cifs_ses *buf_to_free
 	kfree(buf_to_free->serverOS);
 	kfree(buf_to_free->serverDomain);
 	kfree(buf_to_free->serverNOS);
-	if (buf_to_free->password) {
-		memset(buf_to_free->password, 0, strlen(buf_to_free->password));
-		kfree(buf_to_free->password);
-	}
+	kzfree(buf_to_free->password);
 	kfree(buf_to_free->user_name);
 	kfree(buf_to_free->domainName);
-	kfree(buf_to_free->auth_key.response);
-	kfree(buf_to_free);
+	kzfree(buf_to_free->auth_key.response);
+	kzfree(buf_to_free);
 }
 
 struct cifs_tcon *
@@ -136,10 +133,7 @@ tconInfoFree(struct cifs_tcon *buf_to_fr
 	}
 	atomic_dec(&tconInfoAllocCount);
 	kfree(buf_to_free->nativeFileSystem);
-	if (buf_to_free->password) {
-		memset(buf_to_free->password, 0, strlen(buf_to_free->password));
-		kfree(buf_to_free->password);
-	}
+	kzfree(buf_to_free->password);
 	kfree(buf_to_free);
 }
 
author maintainer
#5 lore raw

PATCH 5/202 cpufreq: mediatek: add mediatek related projects into blacklist

In reply to Greg Kroah-Hartman

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Andrew-sh Cheng <[email protected]>

commit 6066998cbd2b1012a8d5bc9a2957cfd0ad53150e upstream.

mediatek projects will use mediate-cpufreq.c as cpufreq driver, instead of using cpufreq_dt.c
Add mediatek related projects into cpufreq-dt blacklist

---
 drivers/cpufreq/cpufreq-dt-platdev.c |    8 ++++++++
 1 file changed, 8 insertions(+)
drivers/cpufreq/cpufreq-dt-platdev.c +8 -0
@@ -108,6 +108,14 @@ static const struct of_device_id blackli
 
 	{ .compatible = "marvell,armadaxp", },
 
+	{ .compatible = "mediatek,mt2701", },
+	{ .compatible = "mediatek,mt2712", },
+	{ .compatible = "mediatek,mt7622", },
+	{ .compatible = "mediatek,mt7623", },
+	{ .compatible = "mediatek,mt817x", },
+	{ .compatible = "mediatek,mt8173", },
+	{ .compatible = "mediatek,mt8176", },
+
 	{ .compatible = "nvidia,tegra124", },
 
 	{ .compatible = "st,stih407", },
author maintainer
#6 lore raw

PATCH 6/202 dmaengine: dmatest: fix container_of member in dmatest_callback

In reply to Greg Kroah-Hartman

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Yang Shunyong <[email protected]>

commit 66b3bd2356e0a1531c71a3dcf96944621e25c17c upstream.

The type of arg passed to dmatest_callback is struct dmatest_done. It refers to test_done in struct dmatest_thread, not done_wait.

Fixes 6f6a23a213be ("dmaengine: dmatest: move callback wait ...")
---
 drivers/dma/dmatest.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/dma/dmatest.c +1 -1
@@ -355,7 +355,7 @@ static void dmatest_callback(void *arg)
 {
 	struct dmatest_done *done = arg;
 	struct dmatest_thread *thread =
-		container_of(arg, struct dmatest_thread, done_wait);
+		container_of(done, struct dmatest_thread, test_done);
 	if (!thread->done) {
 		done->done = true;
 		wake_up_all(done->wait);
author maintainer
#7 lore raw

PATCH 7/202 ssb: Do not disable PCI host on non-Mips

In reply to Greg Kroah-Hartman

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Sven Joachim <[email protected]>

commit a9e6d44ddeccd3522670e641f1ed9b068e746ff7 upstream.

After upgrading an old laptop to 4.15-rc9, I found that the eth0 and wlan0 interfaces had disappeared. It turns out that the b43 and b44 drivers require SSB_PCIHOST_POSSIBLE which depends on PCI_DRIVERS_LEGACY, a config option that only exists on Mips.

Fixes 58eae1416b80 ("ssb: Disable PCI host for PCI_DRIVERS_GENERIC")
---
 drivers/ssb/Kconfig |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/ssb/Kconfig +1 -1
@@ -32,7 +32,7 @@ config SSB_BLOCKIO
 
 config SSB_PCIHOST_POSSIBLE
 	bool
-	depends on SSB && (PCI = y || PCI = SSB) && PCI_DRIVERS_LEGACY
+	depends on SSB && (PCI = y || PCI = SSB) && (PCI_DRIVERS_LEGACY || !MIPS)
 	default y
 
 config SSB_PCIHOST
author maintainer
#8 lore raw

PATCH 8/202 watchdog: gpio_wdt: set WDOG_HW_RUNNING in gpio_wdt_stop

In reply to Greg Kroah-Hartman

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Rasmus Villemoes <[email protected]>

commit bc137dfdbec27c0ec5731a89002daded4a4aa1ea upstream.

The first patch above (https://patchwork.kernel.org/patch/9970181/)
makes the oops go away, but it just papers over the problem. The real problem is that the watchdog core clears WDOG_HW_RUNNING in watchdog_stop, and the gpio driver fails to set it in its stop function when it doesn't actually stop it. This means that the core doesn't know that it now has responsibility for petting the device, in turn causing the device to reset the system (I hadn't noticed this because the board I'm working on has that reset logic disabled).

How about this (other drivers may of course have the same problem, I haven't checked). One might say that ->stop should return an error when the device can't be stopped, but OTOH this brings parity between a device without a ->stop method and a GPIO wd that has always-running set. IOW, I think ->stop should only return an error when an actual attempt to stop the hardware failed.

From: Rasmus Villemoes <[email protected]>

The watchdog framework clears WDOG_HW_RUNNING before calling ->stop. If the driver is unable to stop the device, it is supposed to set that bit again so that the watchdog core takes care of sending heart-beats while the device is not open from user-space. Update the gpio_wdt driver to honour that contract (and get rid of the redundant clearing of WDOG_HW_RUNNING).

Fixes 3c10bbde10 ("watchdog: core: Clear WDOG_HW_RUNNING before calling the stop function")
---
 drivers/watchdog/gpio_wdt.c |    3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)
drivers/watchdog/gpio_wdt.c +2 -1
@@ -80,7 +80,8 @@ static int gpio_wdt_stop(struct watchdog
 
 	if (!priv->always_running) {
 		gpio_wdt_disable(priv);
-		clear_bit(WDOG_HW_RUNNING, &wdd->status);
+	} else {
+		set_bit(WDOG_HW_RUNNING, &wdd->status);
 	}
 
 	return 0;
author maintainer
#9 lore raw

PATCH 9/202 Revert "drm/i915: mark all device info struct with __initconst"

In reply to Greg Kroah-Hartman

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Lionel Landwerlin <[email protected]>

commit b5a756a722286af9702d565501e1f690d075d16b upstream.

This reverts commit 5b54eddd3920e9f6f1a6d972454baf350cbae77e.

Conflicts:

	drivers/gpu/drm/i915/i915_pci.c

Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=104805

Fixes 5b54eddd3920 ("drm/i915: mark all device info struct with __initconst")
(cherry picked from commit 5db47e37b38755c5e26e6b8fbc1a32ce73495940)
Cc Ozkan Sezer <[email protected]>
---
 drivers/gpu/drm/i915/i915_pci.c |   94 ++++++++++++++++++++--------------------
 1 file changed, 47 insertions(+), 47 deletions(-)
drivers/gpu/drm/i915/i915_pci.c +47 -47
@@ -74,19 +74,19 @@
 	GEN_DEFAULT_PAGE_SIZES, \
 	CURSOR_OFFSETS
 
-static const struct intel_device_info intel_i830_info __initconst = {
+static const struct intel_device_info intel_i830_info = {
 	GEN2_FEATURES,
 	.platform = INTEL_I830,
 	.is_mobile = 1, .cursor_needs_physical = 1,
 	.num_pipes = 2, /* legal, last one wins */
 };
 
-static const struct intel_device_info intel_i845g_info __initconst = {
+static const struct intel_device_info intel_i845g_info = {
 	GEN2_FEATURES,
 	.platform = INTEL_I845G,
 };
 
-static const struct intel_device_info intel_i85x_info __initconst = {
+static const struct intel_device_info intel_i85x_info = {
 	GEN2_FEATURES,
 	.platform = INTEL_I85X, .is_mobile = 1,
 	.num_pipes = 2, /* legal, last one wins */
@@ -94,7 +94,7 @@ static const struct intel_device_info in
 	.has_fbc = 1,
 };
 
-static const struct intel_device_info intel_i865g_info __initconst = {
+static const struct intel_device_info intel_i865g_info = {
 	GEN2_FEATURES,
 	.platform = INTEL_I865G,
 };
@@ -108,7 +108,7 @@ static const struct intel_device_info in
 	GEN_DEFAULT_PAGE_SIZES, \
 	CURSOR_OFFSETS
 
-static const struct intel_device_info intel_i915g_info __initconst = {
+static const struct intel_device_info intel_i915g_info = {
 	GEN3_FEATURES,
 	.platform = INTEL_I915G, .cursor_needs_physical = 1,
 	.has_overlay = 1, .overlay_needs_physical = 1,
@@ -116,7 +116,7 @@ static const struct intel_device_info in
 	.unfenced_needs_alignment = 1,
 };
 
-static const struct intel_device_info intel_i915gm_info __initconst = {
+static const struct intel_device_info intel_i915gm_info = {
 	GEN3_FEATURES,
 	.platform = INTEL_I915GM,
 	.is_mobile = 1,
@@ -128,7 +128,7 @@ static const struct intel_device_info in
 	.unfenced_needs_alignment = 1,
 };
 
-static const struct intel_device_info intel_i945g_info __initconst = {
+static const struct intel_device_info intel_i945g_info = {
 	GEN3_FEATURES,
 	.platform = INTEL_I945G,
 	.has_hotplug = 1, .cursor_needs_physical = 1,
@@ -137,7 +137,7 @@ static const struct intel_device_info in
 	.unfenced_needs_alignment = 1,
 };
 
-static const struct intel_device_info intel_i945gm_info __initconst = {
+static const struct intel_device_info intel_i945gm_info = {
 	GEN3_FEATURES,
 	.platform = INTEL_I945GM, .is_mobile = 1,
 	.has_hotplug = 1, .cursor_needs_physical = 1,
@@ -148,14 +148,14 @@ static const struct intel_device_info in
 	.unfenced_needs_alignment = 1,
 };
 
-static const struct intel_device_info intel_g33_info __initconst = {
+static const struct intel_device_info intel_g33_info = {
 	GEN3_FEATURES,
 	.platform = INTEL_G33,
 	.has_hotplug = 1,
 	.has_overlay = 1,
 };
 
-static const struct intel_device_info intel_pineview_info __initconst = {
+static const struct intel_device_info intel_pineview_info = {
 	GEN3_FEATURES,
 	.platform = INTEL_PINEVIEW, .is_mobile = 1,
 	.has_hotplug = 1,
@@ -172,7 +172,7 @@ static const struct intel_device_info in
 	GEN_DEFAULT_PAGE_SIZES, \
 	CURSOR_OFFSETS
 
-static const struct intel_device_info intel_i965g_info __initconst = {
+static const struct intel_device_info intel_i965g_info = {
 	GEN4_FEATURES,
 	.platform = INTEL_I965G,
 	.has_overlay = 1,
@@ -180,7 +180,7 @@ static const struct intel_device_info in
 	.has_snoop = false,
 };
 
-static const struct intel_device_info intel_i965gm_info __initconst = {
+static const struct intel_device_info intel_i965gm_info = {
 	GEN4_FEATURES,
 	.platform = INTEL_I965GM,
 	.is_mobile = 1, .has_fbc = 1,
@@ -190,13 +190,13 @@ static const struct intel_device_info in
 	.has_snoop = false,
 };
 
-static const struct intel_device_info intel_g45_info __initconst = {
+static const struct intel_device_info intel_g45_info = {
 	GEN4_FEATURES,
 	.platform = INTEL_G45,
 	.ring_mask = RENDER_RING | BSD_RING,
 };
 
-static const struct intel_device_info intel_gm45_info __initconst = {
+static const struct intel_device_info intel_gm45_info = {
 	GEN4_FEATURES,
 	.platform = INTEL_GM45,
 	.is_mobile = 1, .has_fbc = 1,
@@ -213,12 +213,12 @@ static const struct intel_device_info in
 	GEN_DEFAULT_PAGE_SIZES, \
 	CURSOR_OFFSETS
 
-static const struct intel_device_info intel_ironlake_d_info __initconst = {
+static const struct intel_device_info intel_ironlake_d_info = {
 	GEN5_FEATURES,
 	.platform = INTEL_IRONLAKE,
 };
 
-static const struct intel_device_info intel_ironlake_m_info __initconst = {
+static const struct intel_device_info intel_ironlake_m_info = {
 	GEN5_FEATURES,
 	.platform = INTEL_IRONLAKE,
 	.is_mobile = 1, .has_fbc = 1,
@@ -241,12 +241,12 @@ static const struct intel_device_info in
 	GEN6_FEATURES, \
 	.platform = INTEL_SANDYBRIDGE
 
-static const struct intel_device_info intel_sandybridge_d_gt1_info __initconst = {
+static const struct intel_device_info intel_sandybridge_d_gt1_info = {
 	SNB_D_PLATFORM,
 	.gt = 1,
 };
 
-static const struct intel_device_info intel_sandybridge_d_gt2_info __initconst = {
+static const struct intel_device_info intel_sandybridge_d_gt2_info = {
 	SNB_D_PLATFORM,
 	.gt = 2,
 };
@@ -257,12 +257,12 @@ static const struct intel_device_info in
 	.is_mobile = 1
 
 
-static const struct intel_device_info intel_sandybridge_m_gt1_info __initconst = {
+static const struct intel_device_info intel_sandybridge_m_gt1_info = {
 	SNB_M_PLATFORM,
 	.gt = 1,
 };
 
-static const struct intel_device_info intel_sandybridge_m_gt2_info __initconst = {
+static const struct intel_device_info intel_sandybridge_m_gt2_info = {
 	SNB_M_PLATFORM,
 	.gt = 2,
 };
@@ -286,12 +286,12 @@ static const struct intel_device_info in
 	.platform = INTEL_IVYBRIDGE, \
 	.has_l3_dpf = 1
 
-static const struct intel_device_info intel_ivybridge_d_gt1_info __initconst = {
+static const struct intel_device_info intel_ivybridge_d_gt1_info = {
 	IVB_D_PLATFORM,
 	.gt = 1,
 };
 
-static const struct intel_device_info intel_ivybridge_d_gt2_info __initconst = {
+static const struct intel_device_info intel_ivybridge_d_gt2_info = {
 	IVB_D_PLATFORM,
 	.gt = 2,
 };
@@ -302,17 +302,17 @@ static const struct intel_device_info in
 	.is_mobile = 1, \
 	.has_l3_dpf = 1
 
-static const struct intel_device_info intel_ivybridge_m_gt1_info __initconst = {
+static const struct intel_device_info intel_ivybridge_m_gt1_info = {
 	IVB_M_PLATFORM,
 	.gt = 1,
 };
 
-static const struct intel_device_info intel_ivybridge_m_gt2_info __initconst = {
+static const struct intel_device_info intel_ivybridge_m_gt2_info = {
 	IVB_M_PLATFORM,
 	.gt = 2,
 };
 
-static const struct intel_device_info intel_ivybridge_q_info __initconst = {
+static const struct intel_device_info intel_ivybridge_q_info = {
 	GEN7_FEATURES,
 	.platform = INTEL_IVYBRIDGE,
 	.gt = 2,
@@ -320,7 +320,7 @@ static const struct intel_device_info in
 	.has_l3_dpf = 1,
 };
 
-static const struct intel_device_info intel_valleyview_info __initconst = {
+static const struct intel_device_info intel_valleyview_info = {
 	.platform = INTEL_VALLEYVIEW,
 	.gen = 7,
 	.is_lp = 1,
@@ -356,17 +356,17 @@ static const struct intel_device_info in
 	.platform = INTEL_HASWELL, \
 	.has_l3_dpf = 1
 
-static const struct intel_device_info intel_haswell_gt1_info __initconst = {
+static const struct intel_device_info intel_haswell_gt1_info = {
 	HSW_PLATFORM,
 	.gt = 1,
 };
 
-static const struct intel_device_info intel_haswell_gt2_info __initconst = {
+static const struct intel_device_info intel_haswell_gt2_info = {
 	HSW_PLATFORM,
 	.gt = 2,
 };
 
-static const struct intel_device_info intel_haswell_gt3_info __initconst = {
+static const struct intel_device_info intel_haswell_gt3_info = {
 	HSW_PLATFORM,
 	.gt = 3,
 };
@@ -386,17 +386,17 @@ static const struct intel_device_info in
 	.gen = 8, \
 	.platform = INTEL_BROADWELL
 
-static const struct intel_device_info intel_broadwell_gt1_info __initconst = {
+static const struct intel_device_info intel_broadwell_gt1_info = {
 	BDW_PLATFORM,
 	.gt = 1,
 };
 
-static const struct intel_device_info intel_broadwell_gt2_info __initconst = {
+static const struct intel_device_info intel_broadwell_gt2_info = {
 	BDW_PLATFORM,
 	.gt = 2,
 };
 
-static const struct intel_device_info intel_broadwell_rsvd_info __initconst = {
+static const struct intel_device_info intel_broadwell_rsvd_info = {
 	BDW_PLATFORM,
 	.gt = 3,
 	/* According to the device ID those devices are GT3, they were
@@ -404,13 +404,13 @@ static const struct intel_device_info in
 	 */
 };
 
-static const struct intel_device_info intel_broadwell_gt3_info __initconst = {
+static const struct intel_device_info intel_broadwell_gt3_info = {
 	BDW_PLATFORM,
 	.gt = 3,
 	.ring_mask = RENDER_RING | BSD_RING | BLT_RING | VEBOX_RING | BSD2_RING,
 };
 
-static const struct intel_device_info intel_cherryview_info __initconst = {
+static const struct intel_device_info intel_cherryview_info = {
 	.gen = 8, .num_pipes = 3,
 	.has_hotplug = 1,
 	.is_lp = 1,
@@ -453,12 +453,12 @@ static const struct intel_device_info in
 	.gen = 9, \
 	.platform = INTEL_SKYLAKE
 
-static const struct intel_device_info intel_skylake_gt1_info __initconst = {
+static const struct intel_device_info intel_skylake_gt1_info = {
 	SKL_PLATFORM,
 	.gt = 1,
 };
 
-static const struct intel_device_info intel_skylake_gt2_info __initconst = {
+static const struct intel_device_info intel_skylake_gt2_info = {
 	SKL_PLATFORM,
 	.gt = 2,
 };
@@ -468,12 +468,12 @@ static const struct intel_device_info in
 	.ring_mask = RENDER_RING | BSD_RING | BLT_RING | VEBOX_RING | BSD2_RING
 
 
-static const struct intel_device_info intel_skylake_gt3_info __initconst = {
+static const struct intel_device_info intel_skylake_gt3_info = {
 	SKL_GT3_PLUS_PLATFORM,
 	.gt = 3,
 };
 
-static const struct intel_device_info intel_skylake_gt4_info __initconst = {
+static const struct intel_device_info intel_skylake_gt4_info = {
 	SKL_GT3_PLUS_PLATFORM,
 	.gt = 4,
 };
@@ -509,13 +509,13 @@ static const struct intel_device_info in
 	IVB_CURSOR_OFFSETS, \
 	BDW_COLORS
 
-static const struct intel_device_info intel_broxton_info __initconst = {
+static const struct intel_device_info intel_broxton_info = {
 	GEN9_LP_FEATURES,
 	.platform = INTEL_BROXTON,
 	.ddb_size = 512,
 };
 
-static const struct intel_device_info intel_geminilake_info __initconst = {
+static const struct intel_device_info intel_geminilake_info = {
 	GEN9_LP_FEATURES,
 	.platform = INTEL_GEMINILAKE,
 	.ddb_size = 1024,
@@ -527,17 +527,17 @@ static const struct intel_device_info in
 	.gen = 9, \
 	.platform = INTEL_KABYLAKE
 
-static const struct intel_device_info intel_kabylake_gt1_info __initconst = {
+static const struct intel_device_info intel_kabylake_gt1_info = {
 	KBL_PLATFORM,
 	.gt = 1,
 };
 
-static const struct intel_device_info intel_kabylake_gt2_info __initconst = {
+static const struct intel_device_info intel_kabylake_gt2_info = {
 	KBL_PLATFORM,
 	.gt = 2,
 };
 
-static const struct intel_device_info intel_kabylake_gt3_info __initconst = {
+static const struct intel_device_info intel_kabylake_gt3_info = {
 	KBL_PLATFORM,
 	.gt = 3,
 	.ring_mask = RENDER_RING | BSD_RING | BLT_RING | VEBOX_RING | BSD2_RING,
@@ -548,17 +548,17 @@ static const struct intel_device_info in
 	.gen = 9, \
 	.platform = INTEL_COFFEELAKE
 
-static const struct intel_device_info intel_coffeelake_gt1_info __initconst = {
+static const struct intel_device_info intel_coffeelake_gt1_info = {
 	CFL_PLATFORM,
 	.gt = 1,
 };
 
-static const struct intel_device_info intel_coffeelake_gt2_info __initconst = {
+static const struct intel_device_info intel_coffeelake_gt2_info = {
 	CFL_PLATFORM,
 	.gt = 2,
 };
 
-static const struct intel_device_info intel_coffeelake_gt3_info __initconst = {
+static const struct intel_device_info intel_coffeelake_gt3_info = {
 	CFL_PLATFORM,
 	.gt = 3,
 	.ring_mask = RENDER_RING | BSD_RING | BLT_RING | VEBOX_RING | BSD2_RING,
@@ -569,7 +569,7 @@ static const struct intel_device_info in
 	.ddb_size = 1024, \
 	GLK_COLORS
 
-static const struct intel_device_info intel_cannonlake_gt2_info __initconst = {
+static const struct intel_device_info intel_cannonlake_gt2_info = {
 	GEN10_FEATURES,
 	.is_alpha_support = 1,
 	.platform = INTEL_CANNONLAKE,
author maintainer
#10 lore raw

PATCH 10/202 sched/rt: Use container_of() to get root domain in rto_push_irq_work_func()

In reply to Greg Kroah-Hartman

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Steven Rostedt (VMware) <[email protected]>

commit ad0f1d9d65938aec72a698116cd73a980916895e upstream.

When the rto_push_irq_work_func() is called, it looks at the RT overloaded bitmask in the root domain via the runqueue (rq->rd). The problem is that during CPU up and down, nothing here stops rq->rd from changing between taking the rq->rd->rto_lock and releasing it. That means the lock that is released is not the same lock that was taken.

Instead of using this_rq()->rd to get the root domain, as the irq work is part of the root domain, we can simply get the root domain from the irq work that is passed to the routine:

container_of(work, struct root_domain, rto_push_work)

This keeps the root domain consistent.

---
 kernel/sched/rt.c |   15 ++++++++-------
 1 file changed, 8 insertions(+), 7 deletions(-)
kernel/sched/rt.c +8 -7
@@ -1907,9 +1907,8 @@ static void push_rt_tasks(struct rq *rq)
  * the rt_loop_next will cause the iterator to perform another scan.
  *
  */
-static int rto_next_cpu(struct rq *rq)
+static int rto_next_cpu(struct root_domain *rd)
 {
-	struct root_domain *rd = rq->rd;
 	int next;
 	int cpu;
 
@@ -1985,7 +1984,7 @@ static void tell_cpu_to_push(struct rq *
 	 * Otherwise it is finishing up and an ipi needs to be sent.
 	 */
 	if (rq->rd->rto_cpu < 0)
-		cpu = rto_next_cpu(rq);
+		cpu = rto_next_cpu(rq->rd);
 
 	raw_spin_unlock(&rq->rd->rto_lock);
 
@@ -1998,6 +1997,8 @@ static void tell_cpu_to_push(struct rq *
 /* Called from hardirq context */
 void rto_push_irq_work_func(struct irq_work *work)
 {
+	struct root_domain *rd =
+		container_of(work, struct root_domain, rto_push_work);
 	struct rq *rq;
 	int cpu;
 
@@ -2013,18 +2014,18 @@ void rto_push_irq_work_func(struct irq_w
 		raw_spin_unlock(&rq->lock);
 	}
 
-	raw_spin_lock(&rq->rd->rto_lock);
+	raw_spin_lock(&rd->rto_lock);
 
 	/* Pass the IPI to the next rt overloaded queue */
-	cpu = rto_next_cpu(rq);
+	cpu = rto_next_cpu(rd);
 
-	raw_spin_unlock(&rq->rd->rto_lock);
+	raw_spin_unlock(&rd->rto_lock);
 
 	if (cpu < 0)
 		return;
 
 	/* Try the next RT overloaded CPU */
-	irq_work_queue_on(&rq->rd->rto_push_work, cpu);
+	irq_work_queue_on(&rd->rto_push_work, cpu);
 }
 #endif /* HAVE_RT_PUSH_IPI */
 
author maintainer
#11 lore raw

PATCH 11/202 sched/rt: Up the root domain ref count when passing it around via IPIs

In reply to Greg Kroah-Hartman

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Steven Rostedt (VMware) <[email protected]>

commit 364f56653708ba8bcdefd4f0da2a42904baa8eeb upstream.

When issuing an IPI RT push, where an IPI is sent to each CPU that has more than one RT task scheduled on it, it references the root domain's rto_mask, that contains all the CPUs within the root domain that has more than one RT task in the runable state. The problem is, after the IPIs are initiated, the rq->lock is released. This means that the root domain that is associated to the run queue could be freed while the IPIs are going around.

Add a sched_get_rd() and a sched_put_rd() that will increment and decrement the root domain's ref count respectively. This way when initiating the IPIs, the scheduler will up the root domain's ref count before releasing the rq->lock, ensuring that the root domain does not go away until the IPI round is complete.

---
 kernel/sched/rt.c       |    9 +++++++--
 kernel/sched/sched.h    |    2 ++
 kernel/sched/topology.c |   13 +++++++++++++
 3 files changed, 22 insertions(+), 2 deletions(-)
kernel/sched/rt.c +7 -2
@@ -1990,8 +1990,11 @@ static void tell_cpu_to_push(struct rq *
 
 	rto_start_unlock(&rq->rd->rto_loop_start);
 
-	if (cpu >= 0)
+	if (cpu >= 0) {
+		/* Make sure the rd does not get freed while pushing */
+		sched_get_rd(rq->rd);
 		irq_work_queue_on(&rq->rd->rto_push_work, cpu);
+	}
 }
 
 /* Called from hardirq context */
@@ -2021,8 +2024,10 @@ void rto_push_irq_work_func(struct irq_w
 
 	raw_spin_unlock(&rd->rto_lock);
 
-	if (cpu < 0)
+	if (cpu < 0) {
+		sched_put_rd(rd);
 		return;
+	}
 
 	/* Try the next RT overloaded CPU */
 	irq_work_queue_on(&rd->rto_push_work, cpu);
kernel/sched/sched.h +2 -0
@@ -665,6 +665,8 @@ extern struct mutex sched_domains_mutex;
 extern void init_defrootdomain(void);
 extern int sched_init_domains(const struct cpumask *cpu_map);
 extern void rq_attach_root(struct rq *rq, struct root_domain *rd);
+extern void sched_get_rd(struct root_domain *rd);
+extern void sched_put_rd(struct root_domain *rd);
 
 #ifdef HAVE_RT_PUSH_IPI
 extern void rto_push_irq_work_func(struct irq_work *work);
kernel/sched/topology.c +13 -0
@@ -259,6 +259,19 @@ void rq_attach_root(struct rq *rq, struc
 		call_rcu_sched(&old_rd->rcu, free_rootdomain);
 }
 
+void sched_get_rd(struct root_domain *rd)
+{
+	atomic_inc(&rd->refcount);
+}
+
+void sched_put_rd(struct root_domain *rd)
+{
+	if (!atomic_dec_and_test(&rd->refcount))
+		return;
+
+	call_rcu_sched(&rd->rcu, free_rootdomain);
+}
+
 static int init_rootdomain(struct root_domain *rd)
 {
 	if (!zalloc_cpumask_var(&rd->span, GFP_KERNEL))
author maintainer
#12 lore raw

PATCH 12/202 media: dvb-usb-v2: lmedm04: Improve logic checking of warm start

In reply to Greg Kroah-Hartman

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Malcolm Priestley <[email protected]>

commit 3d932ee27e852e4904647f15b64dedca51187ad7 upstream.

Warm start has no check as whether a genuine device has connected and proceeds to next execution path.

Check device should read 0x47 at offset of 2 on USB descriptor read and it is the amount requested of 6 bytes.

Fix for
kasan: CONFIG_KASAN_INLINE enabled
kasan: GPF could be caused by NULL-ptr deref or user memory access as

---
 drivers/media/usb/dvb-usb-v2/lmedm04.c |   26 ++++++++++++++++++--------
 1 file changed, 18 insertions(+), 8 deletions(-)
drivers/media/usb/dvb-usb-v2/lmedm04.c +18 -8
@@ -494,18 +494,23 @@ static int lme2510_pid_filter(struct dvb
 
 static int lme2510_return_status(struct dvb_usb_device *d)
 {
-	int ret = 0;
+	int ret;
 	u8 *data;
 
-	data = kzalloc(10, GFP_KERNEL);
+	data = kzalloc(6, GFP_KERNEL);
 	if (!data)
 		return -ENOMEM;
 
-	ret |= usb_control_msg(d->udev, usb_rcvctrlpipe(d->udev, 0),
-			0x06, 0x80, 0x0302, 0x00, data, 0x0006, 200);
-	info("Firmware Status: %x (%x)", ret , data[2]);
+	ret = usb_control_msg(d->udev, usb_rcvctrlpipe(d->udev, 0),
+			      0x06, 0x80, 0x0302, 0x00,
+			      data, 0x6, 200);
+	if (ret != 6)
+		ret = -EINVAL;
+	else
+		ret = data[2];
+
+	info("Firmware Status: %6ph", data);
 
-	ret = (ret < 0) ? -ENODEV : data[2];
 	kfree(data);
 	return ret;
 }
@@ -1189,6 +1194,7 @@ static int lme2510_get_adapter_count(str
 static int lme2510_identify_state(struct dvb_usb_device *d, const char **name)
 {
 	struct lme2510_state *st = d->priv;
+	int status;
 
 	usb_reset_configuration(d->udev);
 
@@ -1197,12 +1203,16 @@ static int lme2510_identify_state(struct
 
 	st->dvb_usb_lme2510_firmware = dvb_usb_lme2510_firmware;
 
-	if (lme2510_return_status(d) == 0x44) {
+	status = lme2510_return_status(d);
+	if (status == 0x44) {
 		*name = lme_firmware_switch(d, 0);
 		return COLD;
 	}
 
-	return 0;
+	if (status != 0x47)
+		return -EINVAL;
+
+	return WARM;
 }
 
 static int lme2510_get_stream_config(struct dvb_frontend *fe, u8 *ts_type,
author maintainer
#13 lore raw

PATCH 13/202 media: dvb-usb-v2: lmedm04: move ts2020 attach to dm04_lme2510_tuner

In reply to Greg Kroah-Hartman

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Malcolm Priestley <[email protected]>

commit 7bf7a7116ed313c601307f7e585419369926ab05 upstream.

When the tuner was split from m88rs2000 the attach function is in wrong place.

Move to dm04_lme2510_tuner to trap errors on failure and removing a call to lme_coldreset.

Prevents driver starting up without any tuner connected.

Fixes to trap for ts2020 fail.
LME2510(C): FE Found M88RS2000
ts2020: probe of 0-0060 failed with error -11
...
LME2510(C): TUN Found RS2000 tuner
kasan: CONFIG_KASAN_INLINE enabled
kasan: GPF could be caused by NULL-ptr deref or user memory access

general protection fault: 0000 [#1] PREEMPT SMP KASAN
---
 drivers/media/usb/dvb-usb-v2/lmedm04.c |   13 ++++++-------
 1 file changed, 6 insertions(+), 7 deletions(-)
drivers/media/usb/dvb-usb-v2/lmedm04.c +6 -7
@@ -1076,8 +1076,6 @@ static int dm04_lme2510_frontend_attach(
 
 		if (adap->fe[0]) {
 			info("FE Found M88RS2000");
-			dvb_attach(ts2020_attach, adap->fe[0], &ts2020_config,
-					&d->i2c_adap);
 			st->i2c_tuner_gate_w = 5;
 			st->i2c_tuner_gate_r = 5;
 			st->i2c_tuner_addr = 0x60;
@@ -1143,17 +1141,18 @@ static int dm04_lme2510_tuner(struct dvb
 			ret = st->tuner_config;
 		break;
 	case TUNER_RS2000:
-		ret = st->tuner_config;
+		if (dvb_attach(ts2020_attach, adap->fe[0],
+			       &ts2020_config, &d->i2c_adap))
+			ret = st->tuner_config;
 		break;
 	default:
 		break;
 	}
 
-	if (ret)
+	if (ret) {
 		info("TUN Found %s tuner", tun_msg[ret]);
-	else {
-		info("TUN No tuner found --- resetting device");
-		lme_coldreset(d);
+	} else {
+		info("TUN No tuner found");
 		return -ENODEV;
 	}
 
author maintainer
#14 lore raw

PATCH 14/202 media: hdpvr: Fix an error handling path in hdpvr_probe()

In reply to Greg Kroah-Hartman

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Arvind Yadav <[email protected]>

commit c0f71bbb810237a38734607ca4599632f7f5d47f upstream.

Here, hdpvr_register_videodev() is responsible for setup and register a video device. Also defining and initializing a worker. hdpvr_register_videodev() is calling by hdpvr_probe at last. So no need to flush any work here.
Unregister v4l2, free buffers and memory. If hdpvr_probe() will fail.

---
 drivers/media/usb/hdpvr/hdpvr-core.c |   26 +++++++++++++++-----------
 1 file changed, 15 insertions(+), 11 deletions(-)
drivers/media/usb/hdpvr/hdpvr-core.c +15 -11
@@ -292,7 +292,7 @@ static int hdpvr_probe(struct usb_interf
 	/* register v4l2_device early so it can be used for printks */
 	if (v4l2_device_register(&interface->dev, &dev->v4l2_dev)) {
 		dev_err(&interface->dev, "v4l2_device_register failed\n");
-		goto error;
+		goto error_free_dev;
 	}
 
 	mutex_init(&dev->io_mutex);
@@ -301,7 +301,7 @@ static int hdpvr_probe(struct usb_interf
 	dev->usbc_buf = kmalloc(64, GFP_KERNEL);
 	if (!dev->usbc_buf) {
 		v4l2_err(&dev->v4l2_dev, "Out of memory\n");
-		goto error;
+		goto error_v4l2_unregister;
 	}
 
 	init_waitqueue_head(&dev->wait_buffer);
@@ -339,13 +339,13 @@ static int hdpvr_probe(struct usb_interf
 	}
 	if (!dev->bulk_in_endpointAddr) {
 		v4l2_err(&dev->v4l2_dev, "Could not find bulk-in endpoint\n");
-		goto error;
+		goto error_put_usb;
 	}
 
 	/* init the device */
 	if (hdpvr_device_init(dev)) {
 		v4l2_err(&dev->v4l2_dev, "device init failed\n");
-		goto error;
+		goto error_put_usb;
 	}
 
 	mutex_lock(&dev->io_mutex);
@@ -353,7 +353,7 @@ static int hdpvr_probe(struct usb_interf
 		mutex_unlock(&dev->io_mutex);
 		v4l2_err(&dev->v4l2_dev,
 			 "allocating transfer buffers failed\n");
-		goto error;
+		goto error_put_usb;
 	}
 	mutex_unlock(&dev->io_mutex);
 
@@ -361,7 +361,7 @@ static int hdpvr_probe(struct usb_interf
 	retval = hdpvr_register_i2c_adapter(dev);
 	if (retval < 0) {
 		v4l2_err(&dev->v4l2_dev, "i2c adapter register failed\n");
-		goto error;
+		goto error_free_buffers;
 	}
 
 	client = hdpvr_register_ir_rx_i2c(dev);
@@ -394,13 +394,17 @@ static int hdpvr_probe(struct usb_interf
 reg_fail:
 #if IS_ENABLED(CONFIG_I2C)
 	i2c_del_adapter(&dev->i2c_adapter);
+error_free_buffers:
 #endif
+	hdpvr_free_buffers(dev);
+error_put_usb:
+	usb_put_dev(dev->udev);
+	kfree(dev->usbc_buf);
+error_v4l2_unregister:
+	v4l2_device_unregister(&dev->v4l2_dev);
+error_free_dev:
+	kfree(dev);
 error:
-	if (dev) {
-		flush_work(&dev->worker);
-		/* this frees allocated memory */
-		hdpvr_delete(dev);
-	}
 	return retval;
 }
 
author maintainer
#15 lore raw

PATCH 15/202 arm64: mm: Use non-global mappings for kernel space

In reply to Greg Kroah-Hartman

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Will Deacon <[email protected]>

Commit e046eb0c9bf2 upstream.

In preparation for unmapping the kernel whilst running in userspace, make the kernel mappings non-global so we can avoid expensive TLB invalidation on kernel exit to userspace.

---
 arch/arm64/include/asm/kernel-pgtable.h | 12 ++++++++++--
 arch/arm64/include/asm/pgtable-prot.h   | 21 +++++++++++++++------
 2 files changed, 25 insertions(+), 8 deletions(-)
arch/arm64/include/asm/kernel-pgtable.h +10 -2
index 7803343e5881..77a27af01371 100644
@@ -78,8 +78,16 @@
 /*
  * Initial memory map attributes.
  */
-#define SWAPPER_PTE_FLAGS	(PTE_TYPE_PAGE | PTE_AF | PTE_SHARED)
-#define SWAPPER_PMD_FLAGS	(PMD_TYPE_SECT | PMD_SECT_AF | PMD_SECT_S)
+#define _SWAPPER_PTE_FLAGS	(PTE_TYPE_PAGE | PTE_AF | PTE_SHARED)
+#define _SWAPPER_PMD_FLAGS	(PMD_TYPE_SECT | PMD_SECT_AF | PMD_SECT_S)
+
+#ifdef CONFIG_UNMAP_KERNEL_AT_EL0
+#define SWAPPER_PTE_FLAGS	(_SWAPPER_PTE_FLAGS | PTE_NG)
+#define SWAPPER_PMD_FLAGS	(_SWAPPER_PMD_FLAGS | PMD_SECT_NG)
+#else
+#define SWAPPER_PTE_FLAGS	_SWAPPER_PTE_FLAGS
+#define SWAPPER_PMD_FLAGS	_SWAPPER_PMD_FLAGS
+#endif
 
 #if ARM64_SWAPPER_USES_SECTION_MAPS
 #define SWAPPER_MM_MMUFLAGS	(PMD_ATTRINDX(MT_NORMAL) | SWAPPER_PMD_FLAGS)
arch/arm64/include/asm/pgtable-prot.h +15 -6
index 0a5635fb0ef9..22a926825e3f 100644
@@ -34,8 +34,16 @@
 
 #include <asm/pgtable-types.h>
 
-#define PROT_DEFAULT		(PTE_TYPE_PAGE | PTE_AF | PTE_SHARED)
-#define PROT_SECT_DEFAULT	(PMD_TYPE_SECT | PMD_SECT_AF | PMD_SECT_S)
+#define _PROT_DEFAULT		(PTE_TYPE_PAGE | PTE_AF | PTE_SHARED)
+#define _PROT_SECT_DEFAULT	(PMD_TYPE_SECT | PMD_SECT_AF | PMD_SECT_S)
+
+#ifdef CONFIG_UNMAP_KERNEL_AT_EL0
+#define PROT_DEFAULT		(_PROT_DEFAULT | PTE_NG)
+#define PROT_SECT_DEFAULT	(_PROT_SECT_DEFAULT | PMD_SECT_NG)
+#else
+#define PROT_DEFAULT		_PROT_DEFAULT
+#define PROT_SECT_DEFAULT	_PROT_SECT_DEFAULT
+#endif /* CONFIG_UNMAP_KERNEL_AT_EL0 */
 
 #define PROT_DEVICE_nGnRnE	(PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_WRITE | PTE_ATTRINDX(MT_DEVICE_nGnRnE))
 #define PROT_DEVICE_nGnRE	(PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_WRITE | PTE_ATTRINDX(MT_DEVICE_nGnRE))
@@ -48,6 +56,7 @@
 #define PROT_SECT_NORMAL_EXEC	(PROT_SECT_DEFAULT | PMD_SECT_UXN | PMD_ATTRINDX(MT_NORMAL))
 
 #define _PAGE_DEFAULT		(PROT_DEFAULT | PTE_ATTRINDX(MT_NORMAL))
+#define _HYP_PAGE_DEFAULT	(_PAGE_DEFAULT & ~PTE_NG)
 
 #define PAGE_KERNEL		__pgprot(_PAGE_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_WRITE)
 #define PAGE_KERNEL_RO		__pgprot(_PAGE_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_RDONLY)
@@ -55,15 +64,15 @@
 #define PAGE_KERNEL_EXEC	__pgprot(_PAGE_DEFAULT | PTE_UXN | PTE_DIRTY | PTE_WRITE)
 #define PAGE_KERNEL_EXEC_CONT	__pgprot(_PAGE_DEFAULT | PTE_UXN | PTE_DIRTY | PTE_WRITE | PTE_CONT)
 
-#define PAGE_HYP		__pgprot(_PAGE_DEFAULT | PTE_HYP | PTE_HYP_XN)
-#define PAGE_HYP_EXEC		__pgprot(_PAGE_DEFAULT | PTE_HYP | PTE_RDONLY)
-#define PAGE_HYP_RO		__pgprot(_PAGE_DEFAULT | PTE_HYP | PTE_RDONLY | PTE_HYP_XN)
+#define PAGE_HYP		__pgprot(_HYP_PAGE_DEFAULT | PTE_HYP | PTE_HYP_XN)
+#define PAGE_HYP_EXEC		__pgprot(_HYP_PAGE_DEFAULT | PTE_HYP | PTE_RDONLY)
+#define PAGE_HYP_RO		__pgprot(_HYP_PAGE_DEFAULT | PTE_HYP | PTE_RDONLY | PTE_HYP_XN)
 #define PAGE_HYP_DEVICE		__pgprot(PROT_DEVICE_nGnRE | PTE_HYP)
 
 #define PAGE_S2			__pgprot(PROT_DEFAULT | PTE_S2_MEMATTR(MT_S2_NORMAL) | PTE_S2_RDONLY)
 #define PAGE_S2_DEVICE		__pgprot(PROT_DEFAULT | PTE_S2_MEMATTR(MT_S2_DEVICE_nGnRE) | PTE_S2_RDONLY | PTE_UXN)
 
-#define PAGE_NONE		__pgprot(((_PAGE_DEFAULT) & ~PTE_VALID) | PTE_PROT_NONE | PTE_RDONLY | PTE_PXN | PTE_UXN)
+#define PAGE_NONE		__pgprot(((_PAGE_DEFAULT) & ~PTE_VALID) | PTE_PROT_NONE | PTE_RDONLY | PTE_NG | PTE_PXN | PTE_UXN)
 #define PAGE_SHARED		__pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN | PTE_UXN | PTE_WRITE)
 #define PAGE_SHARED_EXEC	__pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN | PTE_WRITE)
 #define PAGE_READONLY		__pgprot(_PAGE_DEFAULT | PTE_USER | PTE_RDONLY | PTE_NG | PTE_PXN | PTE_UXN)
Signature · 1 line
2.16.1
author maintainer
#16 lore raw

PATCH 16/202 arm64: mm: Temporarily disable ARM64_SW_TTBR0_PAN

In reply to Greg Kroah-Hartman

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Will Deacon <[email protected]>

Commit 376133b7edc2 upstream.

We're about to rework the way ASIDs are allocated, switch_mm is implemented and low-level kernel entry/exit is handled, so keep the ARM64_SW_TTBR0_PAN code out of the way whilst we do the heavy lifting.

It will be re-enabled in a subsequent patch.

---
 arch/arm64/Kconfig |    1 +
 1 file changed, 1 insertion(+)
arch/arm64/Kconfig +1 -0
@@ -920,6 +920,7 @@ endif
 
 config ARM64_SW_TTBR0_PAN
 	bool "Emulate Privileged Access Never using TTBR0_EL1 switching"
+	depends on BROKEN       # Temporary while switch_mm is reworked
 	help
 	  Enabling this option prevents the kernel from accessing
 	  user-space memory directly by pointing TTBR0_EL1 to a reserved
author maintainer
#17 lore raw

PATCH 17/202 arm64: mm: Move ASID from TTBR0 to TTBR1

In reply to Greg Kroah-Hartman

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Will Deacon <[email protected]>

Commit 7655abb95386 upstream.

In preparation for mapping kernelspace and userspace with different ASIDs, move the ASID to TTBR1 and update switch_mm to context-switch TTBR0 via an invalid mapping (the zero page).

---
 arch/arm64/include/asm/mmu_context.h   |    7 +++++++
 arch/arm64/include/asm/pgtable-hwdef.h |    1 +
 arch/arm64/include/asm/proc-fns.h      |    6 ------
 arch/arm64/mm/proc.S                   |    9 ++++++---
 4 files changed, 14 insertions(+), 9 deletions(-)
arch/arm64/include/asm/mmu_context.h +7 -0
@@ -57,6 +57,13 @@ static inline void cpu_set_reserved_ttbr
 	isb();
 }
 
+static inline void cpu_switch_mm(pgd_t *pgd, struct mm_struct *mm)
+{
+	BUG_ON(pgd == swapper_pg_dir);
+	cpu_set_reserved_ttbr0();
+	cpu_do_switch_mm(virt_to_phys(pgd),mm);
+}
+
 /*
  * TCR.T0SZ value to use when the ID map is active. Usually equals
  * TCR_T0SZ(VA_BITS), unless system RAM is positioned very high in
arch/arm64/include/asm/pgtable-hwdef.h +1 -0
@@ -272,6 +272,7 @@
 #define TCR_TG1_4K		(UL(2) << TCR_TG1_SHIFT)
 #define TCR_TG1_64K		(UL(3) << TCR_TG1_SHIFT)
 
+#define TCR_A1			(UL(1) << 22)
 #define TCR_ASID16		(UL(1) << 36)
 #define TCR_TBI0		(UL(1) << 37)
 #define TCR_HA			(UL(1) << 39)
arch/arm64/include/asm/proc-fns.h +0 -6
@@ -35,12 +35,6 @@ extern u64 cpu_do_resume(phys_addr_t ptr
 
 #include <asm/memory.h>
 
-#define cpu_switch_mm(pgd,mm)				\
-do {							\
-	BUG_ON(pgd == swapper_pg_dir);			\
-	cpu_do_switch_mm(virt_to_phys(pgd),mm);		\
-} while (0)
-
 #endif /* __ASSEMBLY__ */
 #endif /* __KERNEL__ */
 #endif /* __ASM_PROCFNS_H */
arch/arm64/mm/proc.S +6 -3
@@ -139,9 +139,12 @@ ENDPROC(cpu_do_resume)
  */
 ENTRY(cpu_do_switch_mm)
 	pre_ttbr0_update_workaround x0, x2, x3
+	mrs	x2, ttbr1_el1
 	mmid	x1, x1				// get mm->context.id
-	bfi	x0, x1, #48, #16		// set the ASID
-	msr	ttbr0_el1, x0			// set TTBR0
+	bfi	x2, x1, #48, #16		// set the ASID
+	msr	ttbr1_el1, x2			// in TTBR1 (since TCR.A1 is set)
+	isb
+	msr	ttbr0_el1, x0			// now update TTBR0
 	isb
 	post_ttbr0_update_workaround
 	ret
@@ -224,7 +227,7 @@ ENTRY(__cpu_setup)
 	 * both user and kernel.
 	 */
 	ldr	x10, =TCR_TxSZ(VA_BITS) | TCR_CACHE_FLAGS | TCR_SMP_FLAGS | \
-			TCR_TG_FLAGS | TCR_ASID16 | TCR_TBI0
+			TCR_TG_FLAGS | TCR_ASID16 | TCR_TBI0 | TCR_A1
 	tcr_set_idmap_t0sz	x10, x9
 
 	/*
author maintainer
#18 lore raw

PATCH 18/202 arm64: mm: Remove pre_ttbr0_update_workaround for Falkor erratum #E1003

In reply to Greg Kroah-Hartman

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Will Deacon <[email protected]>

Commit 85d13c001497 upstream.

The pre_ttbr0_update_workaround hook is called prior to context-switching TTBR0 because Falkor erratum E1003 can cause TLB allocation with the wrong ASID if both the ASID and the base address of the TTBR are updated at the same time.

With the ASID sitting safely in TTBR1, we no longer update things atomically, so we can remove the pre_ttbr0_update_workaround macro as it's no longer required. The erratum infrastructure and documentation is left around for #E1003, as it will be required by the entry trampoline code in a future patch.

---
 arch/arm64/include/asm/assembler.h   |   22 ----------------------
 arch/arm64/include/asm/mmu_context.h |    2 --
 arch/arm64/mm/context.c              |   11 -----------
 arch/arm64/mm/proc.S                 |    1 -
 4 files changed, 36 deletions(-)
arch/arm64/include/asm/assembler.h +0 -22
@@ -26,7 +26,6 @@
 #include <asm/asm-offsets.h>
 #include <asm/cpufeature.h>
 #include <asm/debug-monitors.h>
-#include <asm/mmu_context.h>
 #include <asm/page.h>
 #include <asm/pgtable-hwdef.h>
 #include <asm/ptrace.h>
@@ -478,27 +477,6 @@ alternative_endif
 	.endm
 
 /*
- * Errata workaround prior to TTBR0_EL1 update
- *
- * 	val:	TTBR value with new BADDR, preserved
- * 	tmp0:	temporary register, clobbered
- * 	tmp1:	other temporary register, clobbered
- */
-	.macro	pre_ttbr0_update_workaround, val, tmp0, tmp1
-#ifdef CONFIG_QCOM_FALKOR_ERRATUM_1003
-alternative_if ARM64_WORKAROUND_QCOM_FALKOR_E1003
-	mrs	\tmp0, ttbr0_el1
-	mov	\tmp1, #FALKOR_RESERVED_ASID
-	bfi	\tmp0, \tmp1, #48, #16		// reserved ASID + old BADDR
-	msr	ttbr0_el1, \tmp0
-	isb
-	bfi	\tmp0, \val, #0, #48		// reserved ASID + new BADDR
-	msr	ttbr0_el1, \tmp0
-	isb
-alternative_else_nop_endif
-#endif
-	.endm
-
 /*
  * Errata workaround post TTBR0_EL1 update.
  */
arch/arm64/include/asm/mmu_context.h +0 -2
@@ -19,8 +19,6 @@
 #ifndef __ASM_MMU_CONTEXT_H
 #define __ASM_MMU_CONTEXT_H
 
-#define FALKOR_RESERVED_ASID	1
-
 #ifndef __ASSEMBLY__
 
 #include <linux/compiler.h>
arch/arm64/mm/context.c +0 -11
@@ -79,13 +79,6 @@ void verify_cpu_asid_bits(void)
 	}
 }
 
-static void set_reserved_asid_bits(void)
-{
-	if (IS_ENABLED(CONFIG_QCOM_FALKOR_ERRATUM_1003) &&
-	    cpus_have_const_cap(ARM64_WORKAROUND_QCOM_FALKOR_E1003))
-		__set_bit(FALKOR_RESERVED_ASID, asid_map);
-}
-
 static void flush_context(unsigned int cpu)
 {
 	int i;
@@ -94,8 +87,6 @@ static void flush_context(unsigned int c
 	/* Update the list of reserved ASIDs and the ASID bitmap. */
 	bitmap_clear(asid_map, 0, NUM_USER_ASIDS);
 
-	set_reserved_asid_bits();
-
 	for_each_possible_cpu(i) {
 		asid = atomic64_xchg_relaxed(&per_cpu(active_asids, i), 0);
 		/*
@@ -254,8 +245,6 @@ static int asids_init(void)
 		panic("Failed to allocate bitmap for %lu ASIDs\n",
 		      NUM_USER_ASIDS);
 
-	set_reserved_asid_bits();
-
 	pr_info("ASID allocator initialised with %lu entries\n", NUM_USER_ASIDS);
 	return 0;
 }
arch/arm64/mm/proc.S +0 -1
@@ -138,7 +138,6 @@ ENDPROC(cpu_do_resume)
  *	- pgd_phys - physical address of new TTB
  */
 ENTRY(cpu_do_switch_mm)
-	pre_ttbr0_update_workaround x0, x2, x3
 	mrs	x2, ttbr1_el1
 	mmid	x1, x1				// get mm->context.id
 	bfi	x2, x1, #48, #16		// set the ASID
author maintainer
#19 lore raw

PATCH 19/202 arm64: mm: Rename post_ttbr0_update_workaround

In reply to Greg Kroah-Hartman

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Will Deacon <[email protected]>

Commit 158d495899ce upstream.

The post_ttbr0_update_workaround hook applies to any change to TTBRx_EL1. Since we're using TTBR1 for the ASID, rename the hook to make it clearer as to what it's doing.

---
 arch/arm64/include/asm/assembler.h |    5 ++---
 arch/arm64/kernel/entry.S          |    2 +-
 arch/arm64/mm/proc.S               |    2 +-
 3 files changed, 4 insertions(+), 5 deletions(-)
arch/arm64/include/asm/assembler.h +2 -3
@@ -477,10 +477,9 @@ alternative_endif
 	.endm
 
 /*
-/*
- * Errata workaround post TTBR0_EL1 update.
+ * Errata workaround post TTBRx_EL1 update.
  */
-	.macro	post_ttbr0_update_workaround
+	.macro	post_ttbr_update_workaround
 #ifdef CONFIG_CAVIUM_ERRATUM_27456
 alternative_if ARM64_WORKAROUND_CAVIUM_27456
 	ic	iallu
arch/arm64/kernel/entry.S +1 -1
@@ -257,7 +257,7 @@ alternative_else_nop_endif
 	 * Cavium erratum 27456 (broadcast TLBI instructions may cause I-cache
 	 * corruption).
 	 */
-	post_ttbr0_update_workaround
+	post_ttbr_update_workaround
 	.endif
 1:
 	.if	\el != 0
arch/arm64/mm/proc.S +1 -1
@@ -145,7 +145,7 @@ ENTRY(cpu_do_switch_mm)
 	isb
 	msr	ttbr0_el1, x0			// now update TTBR0
 	isb
-	post_ttbr0_update_workaround
+	post_ttbr_update_workaround
 	ret
 ENDPROC(cpu_do_switch_mm)
 
author maintainer
#20 lore raw

PATCH 20/202 arm64: mm: Fix and re-enable ARM64_SW_TTBR0_PAN

In reply to Greg Kroah-Hartman

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Will Deacon <[email protected]>

Commit 27a921e75711 upstream.

With the ASID now installed in TTBR1, we can re-enable ARM64_SW_TTBR0_PAN by ensuring that we switch to a reserved ASID of zero when disabling user access and restore the active user ASID on the uaccess enable path.

---
 arch/arm64/Kconfig                   |    1 -
 arch/arm64/include/asm/asm-uaccess.h |   25 +++++++++++++++++--------
 arch/arm64/include/asm/uaccess.h     |   21 +++++++++++++++++----
 arch/arm64/kernel/entry.S            |    4 ++--
 arch/arm64/lib/clear_user.S          |    2 +-
 arch/arm64/lib/copy_from_user.S      |    2 +-
 arch/arm64/lib/copy_in_user.S        |    2 +-
 arch/arm64/lib/copy_to_user.S        |    2 +-
 arch/arm64/mm/cache.S                |    2 +-
 arch/arm64/xen/hypercall.S           |    2 +-
 10 files changed, 42 insertions(+), 21 deletions(-)
arch/arm64/Kconfig +0 -1
@@ -920,7 +920,6 @@ endif
 
 config ARM64_SW_TTBR0_PAN
 	bool "Emulate Privileged Access Never using TTBR0_EL1 switching"
-	depends on BROKEN       # Temporary while switch_mm is reworked
 	help
 	  Enabling this option prevents the kernel from accessing
 	  user-space memory directly by pointing TTBR0_EL1 to a reserved
arch/arm64/include/asm/asm-uaccess.h +17 -8
@@ -16,11 +16,20 @@
 	add	\tmp1, \tmp1, #SWAPPER_DIR_SIZE	// reserved_ttbr0 at the end of swapper_pg_dir
 	msr	ttbr0_el1, \tmp1		// set reserved TTBR0_EL1
 	isb
+	sub	\tmp1, \tmp1, #SWAPPER_DIR_SIZE
+	bic	\tmp1, \tmp1, #(0xffff << 48)
+	msr	ttbr1_el1, \tmp1		// set reserved ASID
+	isb
 	.endm
 
-	.macro	__uaccess_ttbr0_enable, tmp1
+	.macro	__uaccess_ttbr0_enable, tmp1, tmp2
 	get_thread_info \tmp1
 	ldr	\tmp1, [\tmp1, #TSK_TI_TTBR0]	// load saved TTBR0_EL1
+	mrs	\tmp2, ttbr1_el1
+	extr    \tmp2, \tmp2, \tmp1, #48
+	ror     \tmp2, \tmp2, #16
+	msr	ttbr1_el1, \tmp2		// set the active ASID
+	isb
 	msr	ttbr0_el1, \tmp1		// set the non-PAN TTBR0_EL1
 	isb
 	.endm
@@ -31,18 +40,18 @@ alternative_if_not ARM64_HAS_PAN
 alternative_else_nop_endif
 	.endm
 
-	.macro	uaccess_ttbr0_enable, tmp1, tmp2
+	.macro	uaccess_ttbr0_enable, tmp1, tmp2, tmp3
 alternative_if_not ARM64_HAS_PAN
-	save_and_disable_irq \tmp2		// avoid preemption
-	__uaccess_ttbr0_enable \tmp1
-	restore_irq \tmp2
+	save_and_disable_irq \tmp3		// avoid preemption
+	__uaccess_ttbr0_enable \tmp1, \tmp2
+	restore_irq \tmp3
 alternative_else_nop_endif
 	.endm
 #else
 	.macro	uaccess_ttbr0_disable, tmp1
 	.endm
 
-	.macro	uaccess_ttbr0_enable, tmp1, tmp2
+	.macro	uaccess_ttbr0_enable, tmp1, tmp2, tmp3
 	.endm
 #endif
 
@@ -56,8 +65,8 @@ alternative_if ARM64_ALT_PAN_NOT_UAO
 alternative_else_nop_endif
 	.endm
 
-	.macro	uaccess_enable_not_uao, tmp1, tmp2
-	uaccess_ttbr0_enable \tmp1, \tmp2
+	.macro	uaccess_enable_not_uao, tmp1, tmp2, tmp3
+	uaccess_ttbr0_enable \tmp1, \tmp2, \tmp3
 alternative_if ARM64_ALT_PAN_NOT_UAO
 	SET_PSTATE_PAN(0)
 alternative_else_nop_endif
arch/arm64/include/asm/uaccess.h +17 -4
@@ -107,15 +107,19 @@ static inline void __uaccess_ttbr0_disab
 {
 	unsigned long ttbr;
 
+	ttbr = read_sysreg(ttbr1_el1);
 	/* reserved_ttbr0 placed at the end of swapper_pg_dir */
-	ttbr = read_sysreg(ttbr1_el1) + SWAPPER_DIR_SIZE;
-	write_sysreg(ttbr, ttbr0_el1);
+	write_sysreg(ttbr + SWAPPER_DIR_SIZE, ttbr0_el1);
+	isb();
+	/* Set reserved ASID */
+	ttbr &= ~(0xffffUL << 48);
+	write_sysreg(ttbr, ttbr1_el1);
 	isb();
 }
 
 static inline void __uaccess_ttbr0_enable(void)
 {
-	unsigned long flags;
+	unsigned long flags, ttbr0, ttbr1;
 
 	/*
 	 * Disable interrupts to avoid preemption between reading the 'ttbr0'
@@ -123,7 +127,16 @@ static inline void __uaccess_ttbr0_enabl
 	 * roll-over and an update of 'ttbr0'.
 	 */
 	local_irq_save(flags);
-	write_sysreg(current_thread_info()->ttbr0, ttbr0_el1);
+	ttbr0 = current_thread_info()->ttbr0;
+
+	/* Restore active ASID */
+	ttbr1 = read_sysreg(ttbr1_el1);
+	ttbr1 |= ttbr0 & (0xffffUL << 48);
+	write_sysreg(ttbr1, ttbr1_el1);
+	isb();
+
+	/* Restore user page table */
+	write_sysreg(ttbr0, ttbr0_el1);
 	isb();
 	local_irq_restore(flags);
 }
arch/arm64/kernel/entry.S +2 -2
@@ -184,7 +184,7 @@ alternative_if ARM64_HAS_PAN
 alternative_else_nop_endif
 
 	.if	\el != 0
-	mrs	x21, ttbr0_el1
+	mrs	x21, ttbr1_el1
 	tst	x21, #0xffff << 48		// Check for the reserved ASID
 	orr	x23, x23, #PSR_PAN_BIT		// Set the emulated PAN in the saved SPSR
 	b.eq	1f				// TTBR0 access already disabled
@@ -248,7 +248,7 @@ alternative_else_nop_endif
 	tbnz	x22, #22, 1f			// Skip re-enabling TTBR0 access if the PSR_PAN_BIT is set
 	.endif
 
-	__uaccess_ttbr0_enable x0
+	__uaccess_ttbr0_enable x0, x1
 
 	.if	\el == 0
 	/*
arch/arm64/lib/clear_user.S +1 -1
@@ -30,7 +30,7 @@
  * Alignment fixed up by hardware.
  */
 ENTRY(__clear_user)
-	uaccess_enable_not_uao x2, x3
+	uaccess_enable_not_uao x2, x3, x4
 	mov	x2, x1			// save the size for fixup return
 	subs	x1, x1, #8
 	b.mi	2f
arch/arm64/lib/copy_from_user.S +1 -1
@@ -64,7 +64,7 @@
 
 end	.req	x5
 ENTRY(__arch_copy_from_user)
-	uaccess_enable_not_uao x3, x4
+	uaccess_enable_not_uao x3, x4, x5
 	add	end, x0, x2
 #include "copy_template.S"
 	uaccess_disable_not_uao x3
arch/arm64/lib/copy_in_user.S +1 -1
@@ -65,7 +65,7 @@
 
 end	.req	x5
 ENTRY(raw_copy_in_user)
-	uaccess_enable_not_uao x3, x4
+	uaccess_enable_not_uao x3, x4, x5
 	add	end, x0, x2
 #include "copy_template.S"
 	uaccess_disable_not_uao x3
arch/arm64/lib/copy_to_user.S +1 -1
@@ -63,7 +63,7 @@
 
 end	.req	x5
 ENTRY(__arch_copy_to_user)
-	uaccess_enable_not_uao x3, x4
+	uaccess_enable_not_uao x3, x4, x5
 	add	end, x0, x2
 #include "copy_template.S"
 	uaccess_disable_not_uao x3
arch/arm64/mm/cache.S +1 -1
@@ -49,7 +49,7 @@ ENTRY(flush_icache_range)
  *	- end     - virtual end address of region
  */
 ENTRY(__flush_cache_user_range)
-	uaccess_ttbr0_enable x2, x3
+	uaccess_ttbr0_enable x2, x3, x4
 	dcache_line_size x2, x3
 	sub	x3, x2, #1
 	bic	x4, x0, x3
arch/arm64/xen/hypercall.S +1 -1
@@ -101,7 +101,7 @@ ENTRY(privcmd_call)
 	 * need the explicit uaccess_enable/disable if the TTBR0 PAN emulation
 	 * is enabled (it implies that hardware UAO and PAN disabled).
 	 */
-	uaccess_ttbr0_enable x6, x7
+	uaccess_ttbr0_enable x6, x7, x8
 	hvc XEN_IMM
 
 	/*
author maintainer
#21 lore raw

PATCH 21/202 arm64: mm: Allocate ASIDs in pairs

In reply to Greg Kroah-Hartman

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Will Deacon <[email protected]>

Commit 0c8ea531b774 upstream.

In preparation for separate kernel/user ASIDs, allocate them in pairs for each mm_struct. The bottom bit distinguishes the two: if it is set, then the ASID will map only userspace.

---
 arch/arm64/include/asm/mmu.h |    1 +
 arch/arm64/mm/context.c      |   25 +++++++++++++++++--------
 2 files changed, 18 insertions(+), 8 deletions(-)
arch/arm64/include/asm/mmu.h +1 -0
@@ -17,6 +17,7 @@
 #define __ASM_MMU_H
 
 #define MMCF_AARCH32	0x1	/* mm context flag for AArch32 executables */
+#define USER_ASID_FLAG	(UL(1) << 48)
 
 typedef struct {
 	atomic64_t	id;
arch/arm64/mm/context.c +17 -8
@@ -39,7 +39,16 @@ static cpumask_t tlb_flush_pending;
 
 #define ASID_MASK		(~GENMASK(asid_bits - 1, 0))
 #define ASID_FIRST_VERSION	(1UL << asid_bits)
-#define NUM_USER_ASIDS		ASID_FIRST_VERSION
+
+#ifdef CONFIG_UNMAP_KERNEL_AT_EL0
+#define NUM_USER_ASIDS		(ASID_FIRST_VERSION >> 1)
+#define asid2idx(asid)		(((asid) & ~ASID_MASK) >> 1)
+#define idx2asid(idx)		(((idx) << 1) & ~ASID_MASK)
+#else
+#define NUM_USER_ASIDS		(ASID_FIRST_VERSION)
+#define asid2idx(asid)		((asid) & ~ASID_MASK)
+#define idx2asid(idx)		asid2idx(idx)
+#endif
 
 /* Get the ASIDBits supported by the current CPU */
 static u32 get_cpu_asid_bits(void)
@@ -98,7 +107,7 @@ static void flush_context(unsigned int c
 		 */
 		if (asid == 0)
 			asid = per_cpu(reserved_asids, i);
-		__set_bit(asid & ~ASID_MASK, asid_map);
+		__set_bit(asid2idx(asid), asid_map);
 		per_cpu(reserved_asids, i) = asid;
 	}
 
@@ -153,16 +162,16 @@ static u64 new_context(struct mm_struct
 		 * We had a valid ASID in a previous life, so try to re-use
 		 * it if possible.
 		 */
-		asid &= ~ASID_MASK;
-		if (!__test_and_set_bit(asid, asid_map))
+		if (!__test_and_set_bit(asid2idx(asid), asid_map))
 			return newasid;
 	}
 
 	/*
 	 * Allocate a free ASID. If we can't find one, take a note of the
-	 * currently active ASIDs and mark the TLBs as requiring flushes.
-	 * We always count from ASID #1, as we use ASID #0 when setting a
-	 * reserved TTBR0 for the init_mm.
+	 * currently active ASIDs and mark the TLBs as requiring flushes.  We
+	 * always count from ASID #2 (index 1), as we use ASID #0 when setting
+	 * a reserved TTBR0 for the init_mm and we allocate ASIDs in even/odd
+	 * pairs.
 	 */
 	asid = find_next_zero_bit(asid_map, NUM_USER_ASIDS, cur_idx);
 	if (asid != NUM_USER_ASIDS)
@@ -179,7 +188,7 @@ static u64 new_context(struct mm_struct
 set_asid:
 	__set_bit(asid, asid_map);
 	cur_idx = asid;
-	return asid | generation;
+	return idx2asid(asid) | generation;
 }
 
 void check_and_switch_context(struct mm_struct *mm, unsigned int cpu)
author maintainer
#22 lore raw

PATCH 22/202 arm64: mm: Add arm64_kernel_unmapped_at_el0 helper

In reply to Greg Kroah-Hartman

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Will Deacon <[email protected]>

Commit fc0e1299da54 upstream.

In order for code such as TLB invalidation to operate efficiently when the decision to map the kernel at EL0 is determined at runtime, this patch introduces a helper function, arm64_kernel_unmapped_at_el0, to determine whether or not the kernel is mapped whilst running in userspace.

Currently, this just reports the value of CONFIG_UNMAP_KERNEL_AT_EL0, but will later be hooked up to a fake CPU capability using a static key.

---
 arch/arm64/include/asm/mmu.h |    8 ++++++++
 1 file changed, 8 insertions(+)
arch/arm64/include/asm/mmu.h +8 -0
@@ -19,6 +19,8 @@
 #define MMCF_AARCH32	0x1	/* mm context flag for AArch32 executables */
 #define USER_ASID_FLAG	(UL(1) << 48)
 
+#ifndef __ASSEMBLY__
+
 typedef struct {
 	atomic64_t	id;
 	void		*vdso;
@@ -32,6 +34,11 @@ typedef struct {
  */
 #define ASID(mm)	((mm)->context.id.counter & 0xffff)
 
+static inline bool arm64_kernel_unmapped_at_el0(void)
+{
+	return IS_ENABLED(CONFIG_UNMAP_KERNEL_AT_EL0);
+}
+
 extern void paging_init(void);
 extern void bootmem_init(void);
 extern void __iomem *early_io_map(phys_addr_t phys, unsigned long virt);
@@ -42,4 +49,5 @@ extern void create_pgd_mapping(struct mm
 extern void *fixmap_remap_fdt(phys_addr_t dt_phys);
 extern void mark_linear_text_alias_ro(void);
 
+#endif	/* !__ASSEMBLY__ */
 #endif
author maintainer
#23 lore raw

PATCH 23/202 arm64: mm: Invalidate both kernel and user ASIDs when performing TLBI

In reply to Greg Kroah-Hartman

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Will Deacon <[email protected]>

Commit 9b0de864b5bc upstream.

Since an mm has both a kernel and a user ASID, we need to ensure that broadcast TLB maintenance targets both address spaces so that things like CoW continue to work with the uaccess primitives in the kernel.

---
 arch/arm64/include/asm/tlbflush.h |   16 ++++++++++++++--
 1 file changed, 14 insertions(+), 2 deletions(-)
arch/arm64/include/asm/tlbflush.h +14 -2
@@ -23,6 +23,7 @@
 
 #include <linux/sched.h>
 #include <asm/cputype.h>
+#include <asm/mmu.h>
 
 /*
  * Raw TLBI operations.
@@ -54,6 +55,11 @@
 
 #define __tlbi(op, ...)		__TLBI_N(op, ##__VA_ARGS__, 1, 0)
 
+#define __tlbi_user(op, arg) do {						\
+	if (arm64_kernel_unmapped_at_el0())					\
+		__tlbi(op, (arg) | USER_ASID_FLAG);				\
+} while (0)
+
 /*
  *	TLB Management
  *	==============
@@ -115,6 +121,7 @@ static inline void flush_tlb_mm(struct m
 
 	dsb(ishst);
 	__tlbi(aside1is, asid);
+	__tlbi_user(aside1is, asid);
 	dsb(ish);
 }
 
@@ -125,6 +132,7 @@ static inline void flush_tlb_page(struct
 
 	dsb(ishst);
 	__tlbi(vale1is, addr);
+	__tlbi_user(vale1is, addr);
 	dsb(ish);
 }
 
@@ -151,10 +159,13 @@ static inline void __flush_tlb_range(str
 
 	dsb(ishst);
 	for (addr = start; addr < end; addr += 1 << (PAGE_SHIFT - 12)) {
-		if (last_level)
+		if (last_level) {
 			__tlbi(vale1is, addr);
-		else
+			__tlbi_user(vale1is, addr);
+		} else {
 			__tlbi(vae1is, addr);
+			__tlbi_user(vae1is, addr);
+		}
 	}
 	dsb(ish);
 }
@@ -194,6 +205,7 @@ static inline void __flush_tlb_pgtable(s
 	unsigned long addr = uaddr >> 12 | (ASID(mm) << 48);
 
 	__tlbi(vae1is, addr);
+	__tlbi_user(vae1is, addr);
 	dsb(ish);
 }
 
author maintainer
#24 lore raw

PATCH 24/202 arm64: entry: Add exception trampoline page for exceptions from EL0

In reply to Greg Kroah-Hartman

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Will Deacon <[email protected]>

Commit c7b9adaf85f8 upstream.

To allow unmapping of the kernel whilst running at EL0, we need to point the exception vectors at an entry trampoline that can map/unmap the kernel on entry/exit respectively.

This patch adds the trampoline page, although it is not yet plugged into the vector table and is therefore unused.

---
 arch/arm64/kernel/entry.S       |   86 ++++++++++++++++++++++++++++++++++++++++
 arch/arm64/kernel/vmlinux.lds.S |   17 +++++++
 2 files changed, 103 insertions(+)
arch/arm64/kernel/entry.S +86 -0
@@ -28,6 +28,8 @@
 #include <asm/errno.h>
 #include <asm/esr.h>
 #include <asm/irq.h>
+#include <asm/memory.h>
+#include <asm/mmu.h>
 #include <asm/processor.h>
 #include <asm/ptrace.h>
 #include <asm/thread_info.h>
@@ -943,6 +945,90 @@ __ni_sys_trace:
 
 	.popsection				// .entry.text
 
+#ifdef CONFIG_UNMAP_KERNEL_AT_EL0
+/*
+ * Exception vectors trampoline.
+ */
+	.pushsection ".entry.tramp.text", "ax"
+
+	.macro tramp_map_kernel, tmp
+	mrs	\tmp, ttbr1_el1
+	sub	\tmp, \tmp, #(SWAPPER_DIR_SIZE + RESERVED_TTBR0_SIZE)
+	bic	\tmp, \tmp, #USER_ASID_FLAG
+	msr	ttbr1_el1, \tmp
+	.endm
+
+	.macro tramp_unmap_kernel, tmp
+	mrs	\tmp, ttbr1_el1
+	add	\tmp, \tmp, #(SWAPPER_DIR_SIZE + RESERVED_TTBR0_SIZE)
+	orr	\tmp, \tmp, #USER_ASID_FLAG
+	msr	ttbr1_el1, \tmp
+	/*
+	 * We avoid running the post_ttbr_update_workaround here because the
+	 * user and kernel ASIDs don't have conflicting mappings, so any
+	 * "blessing" as described in:
+	 *
+	 *   http://lkml.kernel.org/r/[email protected]
+	 *
+	 * will not hurt correctness. Whilst this may partially defeat the
+	 * point of using split ASIDs in the first place, it avoids
+	 * the hit of invalidating the entire I-cache on every return to
+	 * userspace.
+	 */
+	.endm
+
+	.macro tramp_ventry, regsize = 64
+	.align	7
+1:
+	.if	\regsize == 64
+	msr	tpidrro_el0, x30	// Restored in kernel_ventry
+	.endif
+	tramp_map_kernel	x30
+	ldr	x30, =vectors
+	prfm	plil1strm, [x30, #(1b - tramp_vectors)]
+	msr	vbar_el1, x30
+	add	x30, x30, #(1b - tramp_vectors)
+	isb
+	br	x30
+	.endm
+
+	.macro tramp_exit, regsize = 64
+	adr	x30, tramp_vectors
+	msr	vbar_el1, x30
+	tramp_unmap_kernel	x30
+	.if	\regsize == 64
+	mrs	x30, far_el1
+	.endif
+	eret
+	.endm
+
+	.align	11
+ENTRY(tramp_vectors)
+	.space	0x400
+
+	tramp_ventry
+	tramp_ventry
+	tramp_ventry
+	tramp_ventry
+
+	tramp_ventry	32
+	tramp_ventry	32
+	tramp_ventry	32
+	tramp_ventry	32
+END(tramp_vectors)
+
+ENTRY(tramp_exit_native)
+	tramp_exit
+END(tramp_exit_native)
+
+ENTRY(tramp_exit_compat)
+	tramp_exit	32
+END(tramp_exit_compat)
+
+	.ltorg
+	.popsection				// .entry.tramp.text
+#endif /* CONFIG_UNMAP_KERNEL_AT_EL0 */
+
 /*
  * Special system call wrappers.
  */
arch/arm64/kernel/vmlinux.lds.S +17 -0
@@ -57,6 +57,17 @@ jiffies = jiffies_64;
 #define HIBERNATE_TEXT
 #endif
 
+#ifdef CONFIG_UNMAP_KERNEL_AT_EL0
+#define TRAMP_TEXT					\
+	. = ALIGN(PAGE_SIZE);				\
+	VMLINUX_SYMBOL(__entry_tramp_text_start) = .;	\
+	*(.entry.tramp.text)				\
+	. = ALIGN(PAGE_SIZE);				\
+	VMLINUX_SYMBOL(__entry_tramp_text_end) = .;
+#else
+#define TRAMP_TEXT
+#endif
+
 /*
  * The size of the PE/COFF section that covers the kernel image, which
  * runs from stext to _edata, must be a round multiple of the PE/COFF
@@ -113,6 +124,7 @@ SECTIONS
 			HYPERVISOR_TEXT
 			IDMAP_TEXT
 			HIBERNATE_TEXT
+			TRAMP_TEXT
 			*(.fixup)
 			*(.gnu.warning)
 		. = ALIGN(16);
@@ -214,6 +226,11 @@ SECTIONS
 	. += RESERVED_TTBR0_SIZE;
 #endif
 
+#ifdef CONFIG_UNMAP_KERNEL_AT_EL0
+	tramp_pg_dir = .;
+	. += PAGE_SIZE;
+#endif
+
 	__pecoff_data_size = ABSOLUTE(. - __initdata_begin);
 	_end = .;
 
author maintainer
#25 lore raw

PATCH 25/202 arm64: mm: Map entry trampoline into trampoline and kernel page tables

In reply to Greg Kroah-Hartman

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Will Deacon <[email protected]>

Commit 51a0048beb44 upstream.

The exception entry trampoline needs to be mapped at the same virtual address in both the trampoline page table (which maps nothing else) and also the kernel page table, so that we can swizzle TTBR1_EL1 on exceptions from and return to EL0.

This patch maps the trampoline at a fixed virtual address in the fixmap area of the kernel virtual address space, which allows the kernel proper to be randomized with respect to the trampoline when KASLR is enabled.

---
 arch/arm64/include/asm/fixmap.h  |    4 ++++
 arch/arm64/include/asm/pgtable.h |    1 +
 arch/arm64/kernel/asm-offsets.c  |    6 +++++-
 arch/arm64/mm/mmu.c              |   23 +++++++++++++++++++++++
 4 files changed, 33 insertions(+), 1 deletion(-)
arch/arm64/include/asm/fixmap.h +4 -0
@@ -58,6 +58,10 @@ enum fixed_addresses {
 	FIX_APEI_GHES_NMI,
 #endif /* CONFIG_ACPI_APEI_GHES */
 
+#ifdef CONFIG_UNMAP_KERNEL_AT_EL0
+	FIX_ENTRY_TRAMP_TEXT,
+#define TRAMP_VALIAS		(__fix_to_virt(FIX_ENTRY_TRAMP_TEXT))
+#endif /* CONFIG_UNMAP_KERNEL_AT_EL0 */
 	__end_of_permanent_fixed_addresses,
 
 	/*
arch/arm64/include/asm/pgtable.h +1 -0
@@ -683,6 +683,7 @@ static inline void pmdp_set_wrprotect(st
 
 extern pgd_t swapper_pg_dir[PTRS_PER_PGD];
 extern pgd_t idmap_pg_dir[PTRS_PER_PGD];
+extern pgd_t tramp_pg_dir[PTRS_PER_PGD];
 
 /*
  * Encode and decode a swap entry:
arch/arm64/kernel/asm-offsets.c +5 -1
@@ -24,6 +24,7 @@
 #include <linux/kvm_host.h>
 #include <linux/suspend.h>
 #include <asm/cpufeature.h>
+#include <asm/fixmap.h>
 #include <asm/thread_info.h>
 #include <asm/memory.h>
 #include <asm/smp_plat.h>
@@ -148,11 +149,14 @@ int main(void)
   DEFINE(ARM_SMCCC_RES_X2_OFFS,		offsetof(struct arm_smccc_res, a2));
   DEFINE(ARM_SMCCC_QUIRK_ID_OFFS,	offsetof(struct arm_smccc_quirk, id));
   DEFINE(ARM_SMCCC_QUIRK_STATE_OFFS,	offsetof(struct arm_smccc_quirk, state));
-
   BLANK();
   DEFINE(HIBERN_PBE_ORIG,	offsetof(struct pbe, orig_address));
   DEFINE(HIBERN_PBE_ADDR,	offsetof(struct pbe, address));
   DEFINE(HIBERN_PBE_NEXT,	offsetof(struct pbe, next));
   DEFINE(ARM64_FTR_SYSVAL,	offsetof(struct arm64_ftr_reg, sys_val));
+  BLANK();
+#ifdef CONFIG_UNMAP_KERNEL_AT_EL0
+  DEFINE(TRAMP_VALIAS,		TRAMP_VALIAS);
+#endif
   return 0;
 }
arch/arm64/mm/mmu.c +23 -0
@@ -525,6 +525,29 @@ static int __init parse_rodata(char *arg
 }
 early_param("rodata", parse_rodata);
 
+#ifdef CONFIG_UNMAP_KERNEL_AT_EL0
+static int __init map_entry_trampoline(void)
+{
+	extern char __entry_tramp_text_start[];
+
+	pgprot_t prot = rodata_enabled ? PAGE_KERNEL_ROX : PAGE_KERNEL_EXEC;
+	phys_addr_t pa_start = __pa_symbol(__entry_tramp_text_start);
+
+	/* The trampoline is always mapped and can therefore be global */
+	pgprot_val(prot) &= ~PTE_NG;
+
+	/* Map only the text into the trampoline page table */
+	memset(tramp_pg_dir, 0, PGD_SIZE);
+	__create_pgd_mapping(tramp_pg_dir, pa_start, TRAMP_VALIAS, PAGE_SIZE,
+			     prot, pgd_pgtable_alloc, 0);
+
+	/* ...as well as the kernel page table */
+	__set_fixmap(FIX_ENTRY_TRAMP_TEXT, pa_start, prot);
+	return 0;
+}
+core_initcall(map_entry_trampoline);
+#endif
+
 /*
  * Create fine-grained mappings for the kernel.
  */
author maintainer
#26 lore raw

PATCH 26/202 arm64: entry: Explicitly pass exception level to kernel_ventry macro

In reply to Greg Kroah-Hartman

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Will Deacon <[email protected]>

Commit 5b1f7fe41909 upstream.

We will need to treat exceptions from EL0 differently in kernel_ventry, so rework the macro to take the exception level as an argument and construct the branch target using that.

---
 arch/arm64/kernel/entry.S |   50 +++++++++++++++++++++++-----------------------
 1 file changed, 25 insertions(+), 25 deletions(-)
arch/arm64/kernel/entry.S +25 -25
@@ -71,7 +71,7 @@
 #define BAD_FIQ		2
 #define BAD_ERROR	3
 
-	.macro kernel_ventry	label
+	.macro kernel_ventry, el, label, regsize = 64
 	.align 7
 	sub	sp, sp, #S_FRAME_SIZE
 #ifdef CONFIG_VMAP_STACK
@@ -84,7 +84,7 @@
 	tbnz	x0, #THREAD_SHIFT, 0f
 	sub	x0, sp, x0			// x0'' = sp' - x0' = (sp + x0) - sp = x0
 	sub	sp, sp, x0			// sp'' = sp' - x0 = (sp + x0) - x0 = sp
-	b	\label
+	b	el\()\el\()_\label
 
 0:
 	/*
@@ -116,7 +116,7 @@
 	sub	sp, sp, x0
 	mrs	x0, tpidrro_el0
 #endif
-	b	\label
+	b	el\()\el\()_\label
 	.endm
 
 	.macro	kernel_entry, el, regsize = 64
@@ -369,31 +369,31 @@ tsk	.req	x28		// current thread_info
 
 	.align	11
 ENTRY(vectors)
-	kernel_ventry	el1_sync_invalid		// Synchronous EL1t
-	kernel_ventry	el1_irq_invalid			// IRQ EL1t
-	kernel_ventry	el1_fiq_invalid			// FIQ EL1t
-	kernel_ventry	el1_error_invalid		// Error EL1t
-
-	kernel_ventry	el1_sync			// Synchronous EL1h
-	kernel_ventry	el1_irq				// IRQ EL1h
-	kernel_ventry	el1_fiq_invalid			// FIQ EL1h
-	kernel_ventry	el1_error			// Error EL1h
-
-	kernel_ventry	el0_sync			// Synchronous 64-bit EL0
-	kernel_ventry	el0_irq				// IRQ 64-bit EL0
-	kernel_ventry	el0_fiq_invalid			// FIQ 64-bit EL0
-	kernel_ventry	el0_error			// Error 64-bit EL0
+	kernel_ventry	1, sync_invalid			// Synchronous EL1t
+	kernel_ventry	1, irq_invalid			// IRQ EL1t
+	kernel_ventry	1, fiq_invalid			// FIQ EL1t
+	kernel_ventry	1, error_invalid		// Error EL1t
+
+	kernel_ventry	1, sync				// Synchronous EL1h
+	kernel_ventry	1, irq				// IRQ EL1h
+	kernel_ventry	1, fiq_invalid			// FIQ EL1h
+	kernel_ventry	1, error			// Error EL1h
+
+	kernel_ventry	0, sync				// Synchronous 64-bit EL0
+	kernel_ventry	0, irq				// IRQ 64-bit EL0
+	kernel_ventry	0, fiq_invalid			// FIQ 64-bit EL0
+	kernel_ventry	0, error			// Error 64-bit EL0
 
 #ifdef CONFIG_COMPAT
-	kernel_ventry	el0_sync_compat			// Synchronous 32-bit EL0
-	kernel_ventry	el0_irq_compat			// IRQ 32-bit EL0
-	kernel_ventry	el0_fiq_invalid_compat		// FIQ 32-bit EL0
-	kernel_ventry	el0_error_compat		// Error 32-bit EL0
+	kernel_ventry	0, sync_compat, 32		// Synchronous 32-bit EL0
+	kernel_ventry	0, irq_compat, 32		// IRQ 32-bit EL0
+	kernel_ventry	0, fiq_invalid_compat, 32	// FIQ 32-bit EL0
+	kernel_ventry	0, error_compat, 32		// Error 32-bit EL0
 #else
-	kernel_ventry	el0_sync_invalid		// Synchronous 32-bit EL0
-	kernel_ventry	el0_irq_invalid			// IRQ 32-bit EL0
-	kernel_ventry	el0_fiq_invalid			// FIQ 32-bit EL0
-	kernel_ventry	el0_error_invalid		// Error 32-bit EL0
+	kernel_ventry	0, sync_invalid, 32		// Synchronous 32-bit EL0
+	kernel_ventry	0, irq_invalid, 32		// IRQ 32-bit EL0
+	kernel_ventry	0, fiq_invalid, 32		// FIQ 32-bit EL0
+	kernel_ventry	0, error_invalid, 32		// Error 32-bit EL0
 #endif
 END(vectors)
 
author maintainer
#27 lore raw

PATCH 27/202 arm64: entry: Hook up entry trampoline to exception vectors

In reply to Greg Kroah-Hartman

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Will Deacon <[email protected]>

Commit 4bf3286d29f3 upstream.

Hook up the entry trampoline to our exception vectors so that all exceptions from and returns to EL0 go via the trampoline, which swizzles the vector base register accordingly. Transitioning to and from the kernel clobbers x30, so we use tpidrro_el0 and far_el1 as scratch registers for native tasks.

---
 arch/arm64/kernel/entry.S |   39 ++++++++++++++++++++++++++++++++++++---
 1 file changed, 36 insertions(+), 3 deletions(-)
arch/arm64/kernel/entry.S +36 -3
@@ -73,6 +73,17 @@
 
 	.macro kernel_ventry, el, label, regsize = 64
 	.align 7
+#ifdef CONFIG_UNMAP_KERNEL_AT_EL0
+	.if	\el == 0
+	.if	\regsize == 64
+	mrs	x30, tpidrro_el0
+	msr	tpidrro_el0, xzr
+	.else
+	mov	x30, xzr
+	.endif
+	.endif
+#endif
+
 	sub	sp, sp, #S_FRAME_SIZE
 #ifdef CONFIG_VMAP_STACK
 	/*
@@ -119,6 +130,11 @@
 	b	el\()\el\()_\label
 	.endm
 
+	.macro tramp_alias, dst, sym
+	mov_q	\dst, TRAMP_VALIAS
+	add	\dst, \dst, #(\sym - .entry.tramp.text)
+	.endm
+
 	.macro	kernel_entry, el, regsize = 64
 	.if	\regsize == 32
 	mov	w0, w0				// zero upper 32 bits of x0
@@ -271,18 +287,20 @@ alternative_else_nop_endif
 	.if	\el == 0
 	ldr	x23, [sp, #S_SP]		// load return stack pointer
 	msr	sp_el0, x23
+	tst	x22, #PSR_MODE32_BIT		// native task?
+	b.eq	3f
+
 #ifdef CONFIG_ARM64_ERRATUM_845719
 alternative_if ARM64_WORKAROUND_845719
-	tbz	x22, #4, 1f
 #ifdef CONFIG_PID_IN_CONTEXTIDR
 	mrs	x29, contextidr_el1
 	msr	contextidr_el1, x29
 #else
 	msr contextidr_el1, xzr
 #endif
-1:
 alternative_else_nop_endif
 #endif
+3:
 	.endif
 
 	msr	elr_el1, x21			// set up the return data
@@ -304,7 +322,22 @@ alternative_else_nop_endif
 	ldp	x28, x29, [sp, #16 * 14]
 	ldr	lr, [sp, #S_LR]
 	add	sp, sp, #S_FRAME_SIZE		// restore sp
-	eret					// return to kernel
+
+#ifndef CONFIG_UNMAP_KERNEL_AT_EL0
+	eret
+#else
+	.if	\el == 0
+	bne	4f
+	msr	far_el1, x30
+	tramp_alias	x30, tramp_exit_native
+	br	x30
+4:
+	tramp_alias	x30, tramp_exit_compat
+	br	x30
+	.else
+	eret
+	.endif
+#endif
 	.endm
 
 	.macro	irq_stack_entry
author maintainer
#28 lore raw

PATCH 28/202 arm64: erratum: Work around Falkor erratum #E1003 in trampoline code

In reply to Greg Kroah-Hartman

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Will Deacon <[email protected]>

Commit d1777e686ad1 upstream.

We rely on an atomic swizzling of TTBR1 when transitioning from the entry trampoline to the kernel proper on an exception. We can't rely on this atomicity in the face of Falkor erratum #E1003, so on affected cores we can issue a TLB invalidation to invalidate the walk cache prior to jumping into the kernel. There is still the possibility of a TLB conflict here due to conflicting walk cache entries prior to the invalidation, but this doesn't appear to be the case on these CPUs in practice.

---
 arch/arm64/Kconfig        |   17 +++++------------
 arch/arm64/kernel/entry.S |   12 ++++++++++++
 2 files changed, 17 insertions(+), 12 deletions(-)
arch/arm64/Kconfig +5 -12
@@ -522,20 +522,13 @@ config CAVIUM_ERRATUM_30115
 config QCOM_FALKOR_ERRATUM_1003
 	bool "Falkor E1003: Incorrect translation due to ASID change"
 	default y
-	select ARM64_PAN if ARM64_SW_TTBR0_PAN
 	help
 	  On Falkor v1, an incorrect ASID may be cached in the TLB when ASID
-	  and BADDR are changed together in TTBRx_EL1. The workaround for this
-	  issue is to use a reserved ASID in cpu_do_switch_mm() before
-	  switching to the new ASID. Saying Y here selects ARM64_PAN if
-	  ARM64_SW_TTBR0_PAN is selected. This is done because implementing and
-	  maintaining the E1003 workaround in the software PAN emulation code
-	  would be an unnecessary complication. The affected Falkor v1 CPU
-	  implements ARMv8.1 hardware PAN support and using hardware PAN
-	  support versus software PAN emulation is mutually exclusive at
-	  runtime.
-
-	  If unsure, say Y.
+	  and BADDR are changed together in TTBRx_EL1. Since we keep the ASID
+	  in TTBR1_EL1, this situation only occurs in the entry trampoline and
+	  then only for entries in the walk cache, since the leaf translation
+	  is unchanged. Work around the erratum by invalidating the walk cache
+	  entries for the trampoline before entering the kernel proper.
 
 config QCOM_FALKOR_ERRATUM_1009
 	bool "Falkor E1009: Prematurely complete a DSB after a TLBI"
arch/arm64/kernel/entry.S +12 -0
@@ -989,6 +989,18 @@ __ni_sys_trace:
 	sub	\tmp, \tmp, #(SWAPPER_DIR_SIZE + RESERVED_TTBR0_SIZE)
 	bic	\tmp, \tmp, #USER_ASID_FLAG
 	msr	ttbr1_el1, \tmp
+#ifdef CONFIG_QCOM_FALKOR_ERRATUM_1003
+alternative_if ARM64_WORKAROUND_QCOM_FALKOR_E1003
+	/* ASID already in \tmp[63:48] */
+	movk	\tmp, #:abs_g2_nc:(TRAMP_VALIAS >> 12)
+	movk	\tmp, #:abs_g1_nc:(TRAMP_VALIAS >> 12)
+	/* 2MB boundary containing the vectors, so we nobble the walk cache */
+	movk	\tmp, #:abs_g0_nc:((TRAMP_VALIAS & ~(SZ_2M - 1)) >> 12)
+	isb
+	tlbi	vae1, \tmp
+	dsb	nsh
+alternative_else_nop_endif
+#endif /* CONFIG_QCOM_FALKOR_ERRATUM_1003 */
 	.endm
 
 	.macro tramp_unmap_kernel, tmp
author maintainer
#29 lore raw

PATCH 29/202 arm64: cpu_errata: Add Kryo to Falkor 1003 errata

In reply to Greg Kroah-Hartman

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Stephen Boyd <[email protected]>

Commit bb48711800e6 upstream.

The Kryo CPUs are also affected by the Falkor 1003 errata, so we need to do the same workaround on Kryo CPUs. The MIDR is slightly more complicated here, where the PART number is not always the same when looking at all the bits from 15 to 4. Drop the lower 8 bits and just look at the top 4 to see if it's '2' and then consider those as Kryo CPUs. This covers all the combinations without having to list them all out.

Fixes 38fd94b0275c ("arm64: Work around Falkor erratum 1003")

Conflicts:
arch/arm64/include/asm/cputype.h

---
 Documentation/arm64/silicon-errata.txt |    2 +-
 arch/arm64/include/asm/cputype.h       |    2 ++
 arch/arm64/kernel/cpu_errata.c         |   21 +++++++++++++++++++++
 3 files changed, 24 insertions(+), 1 deletion(-)
Documentation/arm64/silicon-errata.txt +1 -1
@@ -72,7 +72,7 @@ stable kernels.
 | Hisilicon      | Hip0{6,7}       | #161010701      | N/A                         |
 | Hisilicon      | Hip07           | #161600802      | HISILICON_ERRATUM_161600802 |
 |                |                 |                 |                             |
-| Qualcomm Tech. | Falkor v1       | E1003           | QCOM_FALKOR_ERRATUM_1003    |
+| Qualcomm Tech. | Kryo/Falkor v1  | E1003           | QCOM_FALKOR_ERRATUM_1003    |
 | Qualcomm Tech. | Falkor v1       | E1009           | QCOM_FALKOR_ERRATUM_1009    |
 | Qualcomm Tech. | QDF2400 ITS     | E0065           | QCOM_QDF2400_ERRATUM_0065   |
 | Qualcomm Tech. | Falkor v{1,2}   | E1041           | QCOM_FALKOR_ERRATUM_1041    |
arch/arm64/include/asm/cputype.h +2 -0
@@ -92,6 +92,7 @@
 
 #define QCOM_CPU_PART_FALKOR_V1		0x800
 #define QCOM_CPU_PART_FALKOR		0xC00
+#define QCOM_CPU_PART_KRYO		0x200
 
 #define MIDR_CORTEX_A53 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A53)
 #define MIDR_CORTEX_A57 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A57)
@@ -101,6 +102,7 @@
 #define MIDR_THUNDERX_83XX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX_83XX)
 #define MIDR_QCOM_FALKOR_V1 MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_FALKOR_V1)
 #define MIDR_QCOM_FALKOR MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_FALKOR)
+#define MIDR_QCOM_KRYO MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_KRYO)
 
 #ifndef __ASSEMBLY__
 
arch/arm64/kernel/cpu_errata.c +21 -0
@@ -30,6 +30,20 @@ is_affected_midr_range(const struct arm6
 				       entry->midr_range_max);
 }
 
+static bool __maybe_unused
+is_kryo_midr(const struct arm64_cpu_capabilities *entry, int scope)
+{
+	u32 model;
+
+	WARN_ON(scope != SCOPE_LOCAL_CPU || preemptible());
+
+	model = read_cpuid_id();
+	model &= MIDR_IMPLEMENTOR_MASK | (0xf00 << MIDR_PARTNUM_SHIFT) |
+		 MIDR_ARCHITECTURE_MASK;
+
+	return model == entry->midr_model;
+}
+
 static bool
 has_mismatched_cache_line_size(const struct arm64_cpu_capabilities *entry,
 				int scope)
@@ -169,6 +183,13 @@ const struct arm64_cpu_capabilities arm6
 			   MIDR_CPU_VAR_REV(0, 0),
 			   MIDR_CPU_VAR_REV(0, 0)),
 	},
+	{
+		.desc = "Qualcomm Technologies Kryo erratum 1003",
+		.capability = ARM64_WORKAROUND_QCOM_FALKOR_E1003,
+		.def_scope = SCOPE_LOCAL_CPU,
+		.midr_model = MIDR_QCOM_KRYO,
+		.matches = is_kryo_midr,
+	},
 #endif
 #ifdef CONFIG_QCOM_FALKOR_ERRATUM_1009
 	{
author maintainer
#30 lore raw

PATCH 30/202 arm64: tls: Avoid unconditional zeroing of tpidrro_el0 for native tasks

In reply to Greg Kroah-Hartman

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Will Deacon <[email protected]>

Commit 18011eac28c7 upstream.

When unmapping the kernel at EL0, we use tpidrro_el0 as a scratch register during exception entry from native tasks and subsequently zero it in the kernel_ventry macro. We can therefore avoid zeroing tpidrro_el0 in the context-switch path for native tasks using the entry trampoline.

---
 arch/arm64/kernel/process.c |   12 +++++-------
 1 file changed, 5 insertions(+), 7 deletions(-)
arch/arm64/kernel/process.c +5 -7
@@ -370,16 +370,14 @@ void tls_preserve_current_state(void)
 
 static void tls_thread_switch(struct task_struct *next)
 {
-	unsigned long tpidr, tpidrro;
-
 	tls_preserve_current_state();
 
-	tpidr = *task_user_tls(next);
-	tpidrro = is_compat_thread(task_thread_info(next)) ?
-		  next->thread.tp_value : 0;
+	if (is_compat_thread(task_thread_info(next)))
+		write_sysreg(next->thread.tp_value, tpidrro_el0);
+	else if (!arm64_kernel_unmapped_at_el0())
+		write_sysreg(0, tpidrro_el0);
 
-	write_sysreg(tpidr, tpidr_el0);
-	write_sysreg(tpidrro, tpidrro_el0);
+	write_sysreg(*task_user_tls(next), tpidr_el0);
 }
 
 /* Restore the UAO state depending on next's addr_limit */
author maintainer
#31 lore raw

PATCH 31/202 arm64: entry: Add fake CPU feature for unmapping the kernel at EL0

In reply to Greg Kroah-Hartman

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Will Deacon <[email protected]>

Commit ea1e3de85e94 upstream.

Allow explicit disabling of the entry trampoline on the kernel command line (kpti=off) by adding a fake CPU feature (ARM64_UNMAP_KERNEL_AT_EL0) that can be used to toggle the alternative sequences in our entry code and avoid use of the trampoline altogether if desired. This also allows us to make use of a static key in arm64_kernel_unmapped_at_el0().

---
 arch/arm64/include/asm/cpucaps.h |    3 +-
 arch/arm64/include/asm/mmu.h     |    3 +-
 arch/arm64/kernel/cpufeature.c   |   41 +++++++++++++++++++++++++++++++++++++++
 arch/arm64/kernel/entry.S        |    9 ++++----
 4 files changed, 50 insertions(+), 6 deletions(-)
arch/arm64/include/asm/cpucaps.h +2 -1
@@ -41,7 +41,8 @@
 #define ARM64_WORKAROUND_CAVIUM_30115		20
 #define ARM64_HAS_DCPOP				21
 #define ARM64_SVE				22
+#define ARM64_UNMAP_KERNEL_AT_EL0		23
 
-#define ARM64_NCAPS				23
+#define ARM64_NCAPS				24
 
 #endif /* __ASM_CPUCAPS_H */
arch/arm64/include/asm/mmu.h +2 -1
@@ -36,7 +36,8 @@ typedef struct {
 
 static inline bool arm64_kernel_unmapped_at_el0(void)
 {
-	return IS_ENABLED(CONFIG_UNMAP_KERNEL_AT_EL0);
+	return IS_ENABLED(CONFIG_UNMAP_KERNEL_AT_EL0) &&
+	       cpus_have_const_cap(ARM64_UNMAP_KERNEL_AT_EL0);
 }
 
 extern void paging_init(void);
arch/arm64/kernel/cpufeature.c +41 -0

53 lines not on this page · raw message

arch/arm64/kernel/entry.S +5 -4
@@ -74,6 +74,7 @@
 	.macro kernel_ventry, el, label, regsize = 64
 	.align 7
 #ifdef CONFIG_UNMAP_KERNEL_AT_EL0
+alternative_if ARM64_UNMAP_KERNEL_AT_EL0
 	.if	\el == 0
 	.if	\regsize == 64
 	mrs	x30, tpidrro_el0
@@ -82,6 +83,7 @@
 	mov	x30, xzr
 	.endif
 	.endif
+alternative_else_nop_endif
 #endif
 
 	sub	sp, sp, #S_FRAME_SIZE
@@ -323,10 +325,9 @@ alternative_else_nop_endif
 	ldr	lr, [sp, #S_LR]
 	add	sp, sp, #S_FRAME_SIZE		// restore sp
 
-#ifndef CONFIG_UNMAP_KERNEL_AT_EL0
-	eret
-#else
 	.if	\el == 0
+alternative_insn eret, nop, ARM64_UNMAP_KERNEL_AT_EL0
+#ifdef CONFIG_UNMAP_KERNEL_AT_EL0
 	bne	4f
 	msr	far_el1, x30
 	tramp_alias	x30, tramp_exit_native
@@ -334,10 +335,10 @@ alternative_else_nop_endif
 4:
 	tramp_alias	x30, tramp_exit_compat
 	br	x30
+#endif
 	.else
 	eret
 	.endif
-#endif
 	.endm
 
 	.macro	irq_stack_entry
author maintainer
#32 lore raw

PATCH 32/202 arm64: kaslr: Put kernel vectors address in separate data page

In reply to Greg Kroah-Hartman

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Will Deacon <[email protected]>

Commit 6c27c4082f4f upstream.

The literal pool entry for identifying the vectors base is the only piece of information in the trampoline page that identifies the true location of the kernel.

This patch moves it into a page-aligned region of the .rodata section and maps this adjacent to the trampoline text via an additional fixmap entry, which protects against any accidental leakage of the trampoline contents.

---
 arch/arm64/include/asm/fixmap.h |    1 +
 arch/arm64/kernel/entry.S       |   14 ++++++++++++++
 arch/arm64/kernel/vmlinux.lds.S |    5 ++++-
 arch/arm64/mm/mmu.c             |   10 +++++++++-
 4 files changed, 28 insertions(+), 2 deletions(-)
arch/arm64/include/asm/fixmap.h +1 -0
@@ -59,6 +59,7 @@ enum fixed_addresses {
 #endif /* CONFIG_ACPI_APEI_GHES */
 
 #ifdef CONFIG_UNMAP_KERNEL_AT_EL0
+	FIX_ENTRY_TRAMP_DATA,
 	FIX_ENTRY_TRAMP_TEXT,
 #define TRAMP_VALIAS		(__fix_to_virt(FIX_ENTRY_TRAMP_TEXT))
 #endif /* CONFIG_UNMAP_KERNEL_AT_EL0 */
arch/arm64/kernel/entry.S +14 -0
@@ -1030,7 +1030,13 @@ alternative_else_nop_endif
 	msr	tpidrro_el0, x30	// Restored in kernel_ventry
 	.endif
 	tramp_map_kernel	x30
+#ifdef CONFIG_RANDOMIZE_BASE
+	adr	x30, tramp_vectors + PAGE_SIZE
+alternative_insn isb, nop, ARM64_WORKAROUND_QCOM_FALKOR_E1003
+	ldr	x30, [x30]
+#else
 	ldr	x30, =vectors
+#endif
 	prfm	plil1strm, [x30, #(1b - tramp_vectors)]
 	msr	vbar_el1, x30
 	add	x30, x30, #(1b - tramp_vectors)
@@ -1073,6 +1079,14 @@ END(tramp_exit_compat)
 
 	.ltorg
 	.popsection				// .entry.tramp.text
+#ifdef CONFIG_RANDOMIZE_BASE
+	.pushsection ".rodata", "a"
+	.align PAGE_SHIFT
+	.globl	__entry_tramp_data_start
+__entry_tramp_data_start:
+	.quad	vectors
+	.popsection				// .rodata
+#endif /* CONFIG_RANDOMIZE_BASE */
 #endif /* CONFIG_UNMAP_KERNEL_AT_EL0 */
 
 /*
arch/arm64/kernel/vmlinux.lds.S +4 -1
@@ -251,7 +251,10 @@ ASSERT(__idmap_text_end - (__idmap_text_
 ASSERT(__hibernate_exit_text_end - (__hibernate_exit_text_start & ~(SZ_4K - 1))
 	<= SZ_4K, "Hibernate exit text too big or misaligned")
 #endif
-
+#ifdef CONFIG_UNMAP_KERNEL_AT_EL0
+ASSERT((__entry_tramp_text_end - __entry_tramp_text_start) == PAGE_SIZE,
+	"Entry trampoline text too big")
+#endif
 /*
  * If padding is applied before .head.text, virt<->phys conversions will fail.
  */
arch/arm64/mm/mmu.c +9 -1
@@ -541,8 +541,16 @@ static int __init map_entry_trampoline(v
 	__create_pgd_mapping(tramp_pg_dir, pa_start, TRAMP_VALIAS, PAGE_SIZE,
 			     prot, pgd_pgtable_alloc, 0);
 
-	/* ...as well as the kernel page table */
+	/* Map both the text and data into the kernel page table */
 	__set_fixmap(FIX_ENTRY_TRAMP_TEXT, pa_start, prot);
+	if (IS_ENABLED(CONFIG_RANDOMIZE_BASE)) {
+		extern char __entry_tramp_data_start[];
+
+		__set_fixmap(FIX_ENTRY_TRAMP_DATA,
+			     __pa_symbol(__entry_tramp_data_start),
+			     PAGE_KERNEL_RO);
+	}
+
 	return 0;
 }
 core_initcall(map_entry_trampoline);
author maintainer
#33 lore raw

PATCH 33/202 arm64: use RET instruction for exiting the trampoline

In reply to Greg Kroah-Hartman

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Will Deacon <[email protected]>

Commit be04a6d1126b upstream.

Speculation attacks against the entry trampoline can potentially resteer the speculative instruction stream through the indirect branch and into arbitrary gadgets within the kernel.

This patch defends against these attacks by forcing a misprediction through the return stack: a dummy BL instruction loads an entry into the stack, so that the predicted program flow of the subsequent RET instruction is to a branch-to-self instruction which is finally resolved as a branch to the kernel vectors with speculation suppressed.

---
 arch/arm64/kernel/entry.S |   10 +++++++++-
 1 file changed, 9 insertions(+), 1 deletion(-)
arch/arm64/kernel/entry.S +9 -1
@@ -1029,6 +1029,14 @@ alternative_else_nop_endif
 	.if	\regsize == 64
 	msr	tpidrro_el0, x30	// Restored in kernel_ventry
 	.endif
+	/*
+	 * Defend against branch aliasing attacks by pushing a dummy
+	 * entry onto the return stack and using a RET instruction to
+	 * enter the full-fat kernel vectors.
+	 */
+	bl	2f
+	b	.
+2:
 	tramp_map_kernel	x30
 #ifdef CONFIG_RANDOMIZE_BASE
 	adr	x30, tramp_vectors + PAGE_SIZE
@@ -1041,7 +1049,7 @@ alternative_insn isb, nop, ARM64_WORKARO
 	msr	vbar_el1, x30
 	add	x30, x30, #(1b - tramp_vectors)
 	isb
-	br	x30
+	ret
 	.endm
 
 	.macro tramp_exit, regsize = 64
author maintainer
#34 lore raw

PATCH 34/202 arm64: Kconfig: Add CONFIG_UNMAP_KERNEL_AT_EL0

In reply to Greg Kroah-Hartman

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Will Deacon <[email protected]>

Commit 084eb77cd3a8 upstream.

Add a Kconfig entry to control use of the entry trampoline, which allows us to unmap the kernel whilst running in userspace and improve the robustness of KASLR.

---
 arch/arm64/Kconfig |   13 +++++++++++++
 1 file changed, 13 insertions(+)
arch/arm64/Kconfig +13 -0
@@ -843,6 +843,19 @@ config FORCE_MAX_ZONEORDER
 	  However for 4K, we choose a higher default value, 11 as opposed to 10, giving us
 	  4M allocations matching the default size used by generic code.
 
+config UNMAP_KERNEL_AT_EL0
+	bool "Unmap kernel when running in userspace (aka \"KAISER\")"
+	default y
+	help
+	  Some attacks against KASLR make use of the timing difference between
+	  a permission fault which could arise from a page table entry that is
+	  present in the TLB, and a translation fault which always requires a
+	  page table walk. This option defends against these attacks by unmapping
+	  the kernel whilst running in userspace, therefore forcing translation
+	  faults for all of kernel space.
+
+	  If unsure, say Y.
+
 menuconfig ARMV8_DEPRECATED
 	bool "Emulate deprecated/obsolete ARMv8 instructions"
 	depends on COMPAT
author maintainer
#35 lore raw

PATCH 35/202 arm64: Kconfig: Reword UNMAP_KERNEL_AT_EL0 kconfig entry

In reply to Greg Kroah-Hartman

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Will Deacon <[email protected]>

Commit 0617052ddde3 upstream.

Although CONFIG_UNMAP_KERNEL_AT_EL0 does make KASLR more robust, it's actually more useful as a mitigation against speculation attacks that can leak arbitrary kernel data to userspace through speculation.

Reword the Kconfig help message to reflect this, and make the option depend on EXPERT so that it is on by default for the majority of users.

---
 arch/arm64/Kconfig |   13 ++++++-------
 1 file changed, 6 insertions(+), 7 deletions(-)
arch/arm64/Kconfig +6 -7
@@ -844,15 +844,14 @@ config FORCE_MAX_ZONEORDER
 	  4M allocations matching the default size used by generic code.
 
 config UNMAP_KERNEL_AT_EL0
-	bool "Unmap kernel when running in userspace (aka \"KAISER\")"
+	bool "Unmap kernel when running in userspace (aka \"KAISER\")" if EXPERT
 	default y
 	help
-	  Some attacks against KASLR make use of the timing difference between
-	  a permission fault which could arise from a page table entry that is
-	  present in the TLB, and a translation fault which always requires a
-	  page table walk. This option defends against these attacks by unmapping
-	  the kernel whilst running in userspace, therefore forcing translation
-	  faults for all of kernel space.
+	  Speculation attacks against some high-performance processors can
+	  be used to bypass MMU permission checks and leak kernel data to
+	  userspace. This can be defended against by unmapping the kernel
+	  when running in userspace, mapping it back in on exception entry
+	  via a trampoline page in the vector table.
 
 	  If unsure, say Y.
 
author maintainer
#36 lore raw

PATCH 36/202 arm64: Take into account ID_AA64PFR0_EL1.CSV3

In reply to Greg Kroah-Hartman

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Will Deacon <[email protected]>

Commit 179a56f6f9fb upstream.

For non-KASLR kernels where the KPTI behaviour has not been overridden on the command line we can use ID_AA64PFR0_EL1.CSV3 to determine whether or not we should unmap the kernel whilst running at EL0.

Conflicts:
arch/arm64/kernel/cpufeature.c

---
 arch/arm64/include/asm/sysreg.h |    1 +
 arch/arm64/kernel/cpufeature.c  |    8 +++++++-
 2 files changed, 8 insertions(+), 1 deletion(-)
arch/arm64/include/asm/sysreg.h +1 -0
@@ -437,6 +437,7 @@
 #define ID_AA64ISAR1_DPB_SHIFT		0
 
 /* id_aa64pfr0 */
+#define ID_AA64PFR0_CSV3_SHIFT		60
 #define ID_AA64PFR0_SVE_SHIFT		32
 #define ID_AA64PFR0_GIC_SHIFT		24
 #define ID_AA64PFR0_ASIMD_SHIFT		20
arch/arm64/kernel/cpufeature.c +7 -1
@@ -145,6 +145,7 @@ static const struct arm64_ftr_bits ftr_i
 };
 
 static const struct arm64_ftr_bits ftr_id_aa64pfr0[] = {
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64PFR0_CSV3_SHIFT, 4, 0),
 	ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SVE),
 				   FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_SVE_SHIFT, 4, 0),
 	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_GIC_SHIFT, 4, 0),
@@ -852,6 +853,8 @@ static int __kpti_forced; /* 0: not forc
 static bool unmap_kernel_at_el0(const struct arm64_cpu_capabilities *entry,
 				int __unused)
 {
+	u64 pfr0 = read_sanitised_ftr_reg(SYS_ID_AA64PFR0_EL1);
+
 	/* Forced on command line? */
 	if (__kpti_forced) {
 		pr_info_once("kernel page table isolation forced %s by command line option\n",
@@ -863,7 +866,9 @@ static bool unmap_kernel_at_el0(const st
 	if (IS_ENABLED(CONFIG_RANDOMIZE_BASE))
 		return true;
 
-	return false;
+	/* Defer to CPU feature registers */
+	return !cpuid_feature_extract_unsigned_field(pfr0,
+						     ID_AA64PFR0_CSV3_SHIFT);
 }
 
 static int __init parse_kpti(char *str)
@@ -968,6 +973,7 @@ static const struct arm64_cpu_capabiliti
 	},
 #ifdef CONFIG_UNMAP_KERNEL_AT_EL0
 	{
+		.desc = "Kernel page table isolation (KPTI)",
 		.capability = ARM64_UNMAP_KERNEL_AT_EL0,
 		.def_scope = SCOPE_SYSTEM,
 		.matches = unmap_kernel_at_el0,
author maintainer
#37 lore raw

PATCH 37/202 arm64: capabilities: Handle duplicate entries for a capability

In reply to Greg Kroah-Hartman

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Suzuki K Poulose <[email protected]>

Commit 67948af41f2e upstream.

Sometimes a single capability could be listed multiple times with differing matches(), e.g, CPU errata for different MIDR versions. This breaks verify_local_cpu_feature() and this_cpu_has_cap() as we stop checking for a capability on a CPU with the first entry in the given table, which is not sufficient. Make sure we run the checks for all entries of the same capability. We do this by fixing __this_cpu_has_cap() to run through all the entries in the given table for a match and reuse it for verify_local_cpu_feature().

---
 arch/arm64/kernel/cpufeature.c |   44 +++++++++++++++++++++--------------------
 1 file changed, 23 insertions(+), 21 deletions(-)
arch/arm64/kernel/cpufeature.c +23 -21
@@ -1118,6 +1118,26 @@ static void __init setup_elf_hwcaps(cons
 			cap_set_elf_hwcap(hwcaps);
 }
 
+/*
+ * Check if the current CPU has a given feature capability.
+ * Should be called from non-preemptible context.
+ */
+static bool __this_cpu_has_cap(const struct arm64_cpu_capabilities *cap_array,
+			       unsigned int cap)
+{
+	const struct arm64_cpu_capabilities *caps;
+
+	if (WARN_ON(preemptible()))
+		return false;
+
+	for (caps = cap_array; caps->desc; caps++)
+		if (caps->capability == cap &&
+		    caps->matches &&
+		    caps->matches(caps, SCOPE_LOCAL_CPU))
+			return true;
+	return false;
+}
+
 void update_cpu_capabilities(const struct arm64_cpu_capabilities *caps,
 			    const char *info)
 {
@@ -1181,8 +1201,9 @@ verify_local_elf_hwcaps(const struct arm
 }
 
 static void
-verify_local_cpu_features(const struct arm64_cpu_capabilities *caps)
+verify_local_cpu_features(const struct arm64_cpu_capabilities *caps_list)
 {
+	const struct arm64_cpu_capabilities *caps = caps_list;
 	for (; caps->matches; caps++) {
 		if (!cpus_have_cap(caps->capability))
 			continue;
@@ -1190,7 +1211,7 @@ verify_local_cpu_features(const struct a
 		 * If the new CPU misses an advertised feature, we cannot proceed
 		 * further, park the cpu.
 		 */
-		if (!caps->matches(caps, SCOPE_LOCAL_CPU)) {
+		if (!__this_cpu_has_cap(caps_list, caps->capability)) {
 			pr_crit("CPU%d: missing feature: %s\n",
 					smp_processor_id(), caps->desc);
 			cpu_die_early();
@@ -1272,25 +1293,6 @@ static void __init mark_const_caps_ready
 	static_branch_enable(&arm64_const_caps_ready);
 }
 
-/*
- * Check if the current CPU has a given feature capability.
- * Should be called from non-preemptible context.
- */
-static bool __this_cpu_has_cap(const struct arm64_cpu_capabilities *cap_array,
-			       unsigned int cap)
-{
-	const struct arm64_cpu_capabilities *caps;
-
-	if (WARN_ON(preemptible()))
-		return false;
-
-	for (caps = cap_array; caps->desc; caps++)
-		if (caps->capability == cap && caps->matches)
-			return caps->matches(caps, SCOPE_LOCAL_CPU);
-
-	return false;
-}
-
 extern const struct arm64_cpu_capabilities arm64_errata[];
 
 bool this_cpu_has_cap(unsigned int cap)
author maintainer
#38 lore raw

PATCH 38/202 arm64: mm: Introduce TTBR_ASID_MASK for getting at the ASID in the TTBR

In reply to Greg Kroah-Hartman

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Will Deacon <[email protected]>

Commit b519538dfefc upstream.

There are now a handful of open-coded masks to extract the ASID from a TTBR value, so introduce a TTBR_ASID_MASK and use that instead.

---
 arch/arm64/include/asm/asm-uaccess.h |    3 ++-
 arch/arm64/include/asm/mmu.h         |    1 +
 arch/arm64/include/asm/uaccess.h     |    4 ++--
 arch/arm64/kernel/entry.S            |    2 +-
 4 files changed, 6 insertions(+), 4 deletions(-)
arch/arm64/include/asm/asm-uaccess.h +2 -1
@@ -4,6 +4,7 @@
 
 #include <asm/alternative.h>
 #include <asm/kernel-pgtable.h>
+#include <asm/mmu.h>
 #include <asm/sysreg.h>
 #include <asm/assembler.h>
 
@@ -17,7 +18,7 @@
 	msr	ttbr0_el1, \tmp1		// set reserved TTBR0_EL1
 	isb
 	sub	\tmp1, \tmp1, #SWAPPER_DIR_SIZE
-	bic	\tmp1, \tmp1, #(0xffff << 48)
+	bic	\tmp1, \tmp1, #TTBR_ASID_MASK
 	msr	ttbr1_el1, \tmp1		// set reserved ASID
 	isb
 	.endm
arch/arm64/include/asm/mmu.h +1 -0
@@ -18,6 +18,7 @@
 
 #define MMCF_AARCH32	0x1	/* mm context flag for AArch32 executables */
 #define USER_ASID_FLAG	(UL(1) << 48)
+#define TTBR_ASID_MASK	(UL(0xffff) << 48)
 
 #ifndef __ASSEMBLY__
 
arch/arm64/include/asm/uaccess.h +2 -2
@@ -112,7 +112,7 @@ static inline void __uaccess_ttbr0_disab
 	write_sysreg(ttbr + SWAPPER_DIR_SIZE, ttbr0_el1);
 	isb();
 	/* Set reserved ASID */
-	ttbr &= ~(0xffffUL << 48);
+	ttbr &= ~TTBR_ASID_MASK;
 	write_sysreg(ttbr, ttbr1_el1);
 	isb();
 }
@@ -131,7 +131,7 @@ static inline void __uaccess_ttbr0_enabl
 
 	/* Restore active ASID */
 	ttbr1 = read_sysreg(ttbr1_el1);
-	ttbr1 |= ttbr0 & (0xffffUL << 48);
+	ttbr1 |= ttbr0 & TTBR_ASID_MASK;
 	write_sysreg(ttbr1, ttbr1_el1);
 	isb();
 
arch/arm64/kernel/entry.S +1 -1
@@ -205,7 +205,7 @@ alternative_else_nop_endif
 
 	.if	\el != 0
 	mrs	x21, ttbr1_el1
-	tst	x21, #0xffff << 48		// Check for the reserved ASID
+	tst	x21, #TTBR_ASID_MASK		// Check for the reserved ASID
 	orr	x23, x23, #PSR_PAN_BIT		// Set the emulated PAN in the saved SPSR
 	b.eq	1f				// TTBR0 access already disabled
 	and	x23, x23, #~PSR_PAN_BIT		// Clear the emulated PAN in the saved SPSR
author maintainer
#39 lore raw

PATCH 39/202 arm64: kpti: Fix the interaction between ASID switching and software PAN

In reply to Greg Kroah-Hartman

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Catalin Marinas <[email protected]>

Commit 6b88a32c7af6 upstream.

With ARM64_SW_TTBR0_PAN enabled, the exception entry code checks the active ASID to decide whether user access was enabled (non-zero ASID) when the exception was taken. On return from exception, if user access was previously disabled, it re-instates TTBR0_EL1 from the per-thread saved value (updated in switch_mm() or efi_set_pgd()).

Commit 7655abb95386 ("arm64: mm: Move ASID from TTBR0 to TTBR1") makes a TTBR0_EL1 + ASID switching non-atomic. Subsequently, commit 27a921e75711 ("arm64: mm: Fix and re-enable ARM64_SW_TTBR0_PAN") changes the __uaccess_ttbr0_disable() function and asm macro to first write the reserved TTBR0_EL1 followed by the ASID=0 update in TTBR1_EL1. If an exception occurs between these two, the exception return code will re-instate a valid TTBR0_EL1. Similar scenario can happen in cpu_switch_mm() between setting the reserved TTBR0_EL1 and the ASID update in cpu_do_switch_mm().

This patch reverts the entry.S check for ASID == 0 to TTBR0_EL1 and disables the interrupts around the TTBR0_EL1 and ASID switching code in __uaccess_ttbr0_disable(). It also ensures that, when returning from the EFI runtime services, efi_set_pgd() doesn't leave a non-zero ASID in TTBR1_EL1 by using uaccess_ttbr0_{enable,disable}.

The accesses to current_thread_info()->ttbr0 are updated to use READ_ONCE/WRITE_ONCE.

As a safety measure, __uaccess_ttbr0_enable() always masks out any existing non-zero ASID TTBR1_EL1 before writing in the new ASID.

Conflicts:
arch/arm64/include/asm/asm-uaccess.h
arch/arm64/include/asm/uaccess.h

---
 arch/arm64/include/asm/asm-uaccess.h |   12 +++++++-----
 arch/arm64/include/asm/efi.h         |   12 +++++++-----
 arch/arm64/include/asm/mmu_context.h |    3 ++-
 arch/arm64/include/asm/uaccess.h     |    9 ++++++---
 arch/arm64/kernel/entry.S            |    2 +-
 arch/arm64/lib/clear_user.S          |    2 +-
 arch/arm64/lib/copy_from_user.S      |    2 +-
 arch/arm64/lib/copy_in_user.S        |    2 +-
 arch/arm64/lib/copy_to_user.S        |    2 +-
 arch/arm64/mm/cache.S                |    2 +-
 arch/arm64/mm/proc.S                 |    3 +++
 arch/arm64/xen/hypercall.S           |    2 +-
 12 files changed, 32 insertions(+), 21 deletions(-)
arch/arm64/include/asm/asm-uaccess.h +7 -5
@@ -14,11 +14,11 @@
 #ifdef CONFIG_ARM64_SW_TTBR0_PAN
 	.macro	__uaccess_ttbr0_disable, tmp1
 	mrs	\tmp1, ttbr1_el1		// swapper_pg_dir
+	bic	\tmp1, \tmp1, #TTBR_ASID_MASK
 	add	\tmp1, \tmp1, #SWAPPER_DIR_SIZE	// reserved_ttbr0 at the end of swapper_pg_dir
 	msr	ttbr0_el1, \tmp1		// set reserved TTBR0_EL1
 	isb
 	sub	\tmp1, \tmp1, #SWAPPER_DIR_SIZE
-	bic	\tmp1, \tmp1, #TTBR_ASID_MASK
 	msr	ttbr1_el1, \tmp1		// set reserved ASID
 	isb
 	.endm
@@ -35,9 +35,11 @@
 	isb
 	.endm
 
-	.macro	uaccess_ttbr0_disable, tmp1
+	.macro	uaccess_ttbr0_disable, tmp1, tmp2
 alternative_if_not ARM64_HAS_PAN
+	save_and_disable_irq \tmp2		// avoid preemption
 	__uaccess_ttbr0_disable \tmp1
+	restore_irq \tmp2
 alternative_else_nop_endif
 	.endm
 
@@ -49,7 +51,7 @@ alternative_if_not ARM64_HAS_PAN
 alternative_else_nop_endif
 	.endm
 #else
-	.macro	uaccess_ttbr0_disable, tmp1
+	.macro	uaccess_ttbr0_disable, tmp1, tmp2
 	.endm
 
 	.macro	uaccess_ttbr0_enable, tmp1, tmp2, tmp3
@@ -59,8 +61,8 @@ alternative_else_nop_endif
 /*
  * These macros are no-ops when UAO is present.
  */
-	.macro	uaccess_disable_not_uao, tmp1
-	uaccess_ttbr0_disable \tmp1
+	.macro	uaccess_disable_not_uao, tmp1, tmp2
+	uaccess_ttbr0_disable \tmp1, \tmp2
 alternative_if ARM64_ALT_PAN_NOT_UAO
 	SET_PSTATE_PAN(1)
 alternative_else_nop_endif
arch/arm64/include/asm/efi.h +7 -5
@@ -121,19 +121,21 @@ static inline void efi_set_pgd(struct mm
 		if (mm != current->active_mm) {
 			/*
 			 * Update the current thread's saved ttbr0 since it is
-			 * restored as part of a return from exception. Set
-			 * the hardware TTBR0_EL1 using cpu_switch_mm()
-			 * directly to enable potential errata workarounds.
+			 * restored as part of a return from exception. Enable
+			 * access to the valid TTBR0_EL1 and invoke the errata
+			 * workaround directly since there is no return from
+			 * exception when invoking the EFI run-time services.
 			 */
 			update_saved_ttbr0(current, mm);
-			cpu_switch_mm(mm->pgd, mm);
+			uaccess_ttbr0_enable();
+			post_ttbr_update_workaround();
 		} else {
 			/*
 			 * Defer the switch to the current thread's TTBR0_EL1
 			 * until uaccess_enable(). Restore the current
 			 * thread's saved ttbr0 corresponding to its active_mm
 			 */
-			cpu_set_reserved_ttbr0();
+			uaccess_ttbr0_disable();
 			update_saved_ttbr0(current, current->active_mm);
 		}
 	}
arch/arm64/include/asm/mmu_context.h +2 -1
@@ -175,7 +175,7 @@ static inline void update_saved_ttbr0(st
 	else
 		ttbr = virt_to_phys(mm->pgd) | ASID(mm) << 48;
 
-	task_thread_info(tsk)->ttbr0 = ttbr;
+	WRITE_ONCE(task_thread_info(tsk)->ttbr0, ttbr);
 }
 #else
 static inline void update_saved_ttbr0(struct task_struct *tsk,
@@ -230,6 +230,7 @@ switch_mm(struct mm_struct *prev, struct
 #define activate_mm(prev,next)	switch_mm(prev, next, current)
 
 void verify_cpu_asid_bits(void);
+void post_ttbr_update_workaround(void);
 
 #endif /* !__ASSEMBLY__ */
 
arch/arm64/include/asm/uaccess.h +6 -3
@@ -105,16 +105,18 @@ static inline void set_fs(mm_segment_t f
 #ifdef CONFIG_ARM64_SW_TTBR0_PAN
 static inline void __uaccess_ttbr0_disable(void)
 {
-	unsigned long ttbr;
+	unsigned long flags, ttbr;
 
+	local_irq_save(flags);
 	ttbr = read_sysreg(ttbr1_el1);
+	ttbr &= ~TTBR_ASID_MASK;
 	/* reserved_ttbr0 placed at the end of swapper_pg_dir */
 	write_sysreg(ttbr + SWAPPER_DIR_SIZE, ttbr0_el1);
 	isb();
 	/* Set reserved ASID */
-	ttbr &= ~TTBR_ASID_MASK;
 	write_sysreg(ttbr, ttbr1_el1);
 	isb();
+	local_irq_restore(flags);
 }
 
 static inline void __uaccess_ttbr0_enable(void)
@@ -127,10 +129,11 @@ static inline void __uaccess_ttbr0_enabl
 	 * roll-over and an update of 'ttbr0'.
 	 */
 	local_irq_save(flags);
-	ttbr0 = current_thread_info()->ttbr0;
+	ttbr0 = READ_ONCE(current_thread_info()->ttbr0);
 
 	/* Restore active ASID */
 	ttbr1 = read_sysreg(ttbr1_el1);
+	ttbr1 &= ~TTBR_ASID_MASK;		/* safety measure */
 	ttbr1 |= ttbr0 & TTBR_ASID_MASK;
 	write_sysreg(ttbr1, ttbr1_el1);
 	isb();
arch/arm64/kernel/entry.S +1 -1
@@ -204,7 +204,7 @@ alternative_if ARM64_HAS_PAN
 alternative_else_nop_endif
 
 	.if	\el != 0
-	mrs	x21, ttbr1_el1
+	mrs	x21, ttbr0_el1
 	tst	x21, #TTBR_ASID_MASK		// Check for the reserved ASID
 	orr	x23, x23, #PSR_PAN_BIT		// Set the emulated PAN in the saved SPSR
 	b.eq	1f				// TTBR0 access already disabled
arch/arm64/lib/clear_user.S +1 -1
@@ -50,7 +50,7 @@ uao_user_alternative 9f, strh, sttrh, wz
 	b.mi	5f
 uao_user_alternative 9f, strb, sttrb, wzr, x0, 0
 5:	mov	x0, #0
-	uaccess_disable_not_uao x2
+	uaccess_disable_not_uao x2, x3
 	ret
 ENDPROC(__clear_user)
 
arch/arm64/lib/copy_from_user.S +1 -1
@@ -67,7 +67,7 @@ ENTRY(__arch_copy_from_user)
 	uaccess_enable_not_uao x3, x4, x5
 	add	end, x0, x2
 #include "copy_template.S"
-	uaccess_disable_not_uao x3
+	uaccess_disable_not_uao x3, x4
 	mov	x0, #0				// Nothing to copy
 	ret
 ENDPROC(__arch_copy_from_user)
arch/arm64/lib/copy_in_user.S +1 -1
@@ -68,7 +68,7 @@ ENTRY(raw_copy_in_user)
 	uaccess_enable_not_uao x3, x4, x5
 	add	end, x0, x2
 #include "copy_template.S"
-	uaccess_disable_not_uao x3
+	uaccess_disable_not_uao x3, x4
 	mov	x0, #0
 	ret
 ENDPROC(raw_copy_in_user)
arch/arm64/lib/copy_to_user.S +1 -1
@@ -66,7 +66,7 @@ ENTRY(__arch_copy_to_user)
 	uaccess_enable_not_uao x3, x4, x5
 	add	end, x0, x2
 #include "copy_template.S"
-	uaccess_disable_not_uao x3
+	uaccess_disable_not_uao x3, x4
 	mov	x0, #0
 	ret
 ENDPROC(__arch_copy_to_user)
arch/arm64/mm/cache.S +1 -1
@@ -72,7 +72,7 @@ USER(9f, ic	ivau, x4	)		// invalidate I
 	isb
 	mov	x0, #0
 1:
-	uaccess_ttbr0_disable x1
+	uaccess_ttbr0_disable x1, x2
 	ret
 9:
 	mov	x0, #-EFAULT
arch/arm64/mm/proc.S +3 -0
@@ -140,6 +140,9 @@ ENDPROC(cpu_do_resume)
 ENTRY(cpu_do_switch_mm)
 	mrs	x2, ttbr1_el1
 	mmid	x1, x1				// get mm->context.id
+#ifdef CONFIG_ARM64_SW_TTBR0_PAN
+	bfi	x0, x1, #48, #16		// set the ASID field in TTBR0
+#endif
 	bfi	x2, x1, #48, #16		// set the ASID
 	msr	ttbr1_el1, x2			// in TTBR1 (since TCR.A1 is set)
 	isb
arch/arm64/xen/hypercall.S +1 -1
@@ -107,6 +107,6 @@ ENTRY(privcmd_call)
 	/*
 	 * Disable userspace access from kernel once the hyp call completed.
 	 */
-	uaccess_ttbr0_disable x6
+	uaccess_ttbr0_disable x6, x7
 	ret
 ENDPROC(privcmd_call);
author maintainer
#40 lore raw

PATCH 40/202 arm64: cputype: Add MIDR values for Cavium ThunderX2 CPUs

In reply to Greg Kroah-Hartman

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Jayachandran C <[email protected]>

Commit 0d90718871fe upstream.

Add the older Broadcom ID as well as the new Cavium ID for ThunderX2 CPUs.

---
 arch/arm64/include/asm/cputype.h |    3 +++
 1 file changed, 3 insertions(+)
arch/arm64/include/asm/cputype.h +3 -0
@@ -87,6 +87,7 @@
 #define CAVIUM_CPU_PART_THUNDERX	0x0A1
 #define CAVIUM_CPU_PART_THUNDERX_81XX	0x0A2
 #define CAVIUM_CPU_PART_THUNDERX_83XX	0x0A3
+#define CAVIUM_CPU_PART_THUNDERX2	0x0AF
 
 #define BRCM_CPU_PART_VULCAN		0x516
 
@@ -100,6 +101,8 @@
 #define MIDR_THUNDERX	MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX)
 #define MIDR_THUNDERX_81XX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX_81XX)
 #define MIDR_THUNDERX_83XX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX_83XX)
+#define MIDR_CAVIUM_THUNDERX2 MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX2)
+#define MIDR_BRCM_VULCAN MIDR_CPU_MODEL(ARM_CPU_IMP_BRCM, BRCM_CPU_PART_VULCAN)
 #define MIDR_QCOM_FALKOR_V1 MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_FALKOR_V1)
 #define MIDR_QCOM_FALKOR MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_FALKOR)
 #define MIDR_QCOM_KRYO MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_KRYO)
author maintainer
#41 lore raw

PATCH 41/202 arm64: Turn on KPTI only on CPUs that need it

In reply to Greg Kroah-Hartman

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Jayachandran C <[email protected]>

Commit 0ba2e29c7fc1 upstream.

Whitelist Broadcom Vulcan/Cavium ThunderX2 processors in unmap_kernel_at_el0(). These CPUs are not vulnerable to CVE-2017-5754 and do not need KPTI when KASLR is off.

---
 arch/arm64/kernel/cpufeature.c |    7 +++++++
 1 file changed, 7 insertions(+)
arch/arm64/kernel/cpufeature.c +7 -0
@@ -866,6 +866,13 @@ static bool unmap_kernel_at_el0(const st
 	if (IS_ENABLED(CONFIG_RANDOMIZE_BASE))
 		return true;
 
+	/* Don't force KPTI for CPUs that are not vulnerable */
+	switch (read_cpuid_id() & MIDR_CPU_MODEL_MASK) {
+	case MIDR_CAVIUM_THUNDERX2:
+	case MIDR_BRCM_VULCAN:
+		return false;
+	}
+
 	/* Defer to CPU feature registers */
 	return !cpuid_feature_extract_unsigned_field(pfr0,
 						     ID_AA64PFR0_CSV3_SHIFT);
author maintainer
#42 lore raw

PATCH 42/202 arm64: kpti: Make use of nG dependent on arm64_kernel_unmapped_at_el0()

In reply to Greg Kroah-Hartman

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Will Deacon <[email protected]>

Commit 41acec624087 upstream.

To allow systems which do not require kpti to continue running with global kernel mappings (which appears to be a requirement for Cavium ThunderX due to a CPU erratum), make the use of nG in the kernel page tables dependent on arm64_kernel_unmapped_at_el0(), which is resolved at runtime.

---
 arch/arm64/include/asm/kernel-pgtable.h |   12 ++----------
 arch/arm64/include/asm/pgtable-prot.h   |   30 ++++++++++++++----------------
 2 files changed, 16 insertions(+), 26 deletions(-)
arch/arm64/include/asm/kernel-pgtable.h +2 -10
@@ -78,16 +78,8 @@
 /*
  * Initial memory map attributes.
  */
-#define _SWAPPER_PTE_FLAGS	(PTE_TYPE_PAGE | PTE_AF | PTE_SHARED)
-#define _SWAPPER_PMD_FLAGS	(PMD_TYPE_SECT | PMD_SECT_AF | PMD_SECT_S)
-
-#ifdef CONFIG_UNMAP_KERNEL_AT_EL0
-#define SWAPPER_PTE_FLAGS	(_SWAPPER_PTE_FLAGS | PTE_NG)
-#define SWAPPER_PMD_FLAGS	(_SWAPPER_PMD_FLAGS | PMD_SECT_NG)
-#else
-#define SWAPPER_PTE_FLAGS	_SWAPPER_PTE_FLAGS
-#define SWAPPER_PMD_FLAGS	_SWAPPER_PMD_FLAGS
-#endif
+#define SWAPPER_PTE_FLAGS	(PTE_TYPE_PAGE | PTE_AF | PTE_SHARED)
+#define SWAPPER_PMD_FLAGS	(PMD_TYPE_SECT | PMD_SECT_AF | PMD_SECT_S)
 
 #if ARM64_SWAPPER_USES_SECTION_MAPS
 #define SWAPPER_MM_MMUFLAGS	(PMD_ATTRINDX(MT_NORMAL) | SWAPPER_PMD_FLAGS)
arch/arm64/include/asm/pgtable-prot.h +14 -16
@@ -37,13 +37,11 @@
 #define _PROT_DEFAULT		(PTE_TYPE_PAGE | PTE_AF | PTE_SHARED)
 #define _PROT_SECT_DEFAULT	(PMD_TYPE_SECT | PMD_SECT_AF | PMD_SECT_S)
 
-#ifdef CONFIG_UNMAP_KERNEL_AT_EL0
-#define PROT_DEFAULT		(_PROT_DEFAULT | PTE_NG)
-#define PROT_SECT_DEFAULT	(_PROT_SECT_DEFAULT | PMD_SECT_NG)
-#else
-#define PROT_DEFAULT		_PROT_DEFAULT
-#define PROT_SECT_DEFAULT	_PROT_SECT_DEFAULT
-#endif /* CONFIG_UNMAP_KERNEL_AT_EL0 */
+#define PTE_MAYBE_NG		(arm64_kernel_unmapped_at_el0() ? PTE_NG : 0)
+#define PMD_MAYBE_NG		(arm64_kernel_unmapped_at_el0() ? PMD_SECT_NG : 0)
+
+#define PROT_DEFAULT		(_PROT_DEFAULT | PTE_MAYBE_NG)
+#define PROT_SECT_DEFAULT	(_PROT_SECT_DEFAULT | PMD_MAYBE_NG)
 
 #define PROT_DEVICE_nGnRnE	(PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_WRITE | PTE_ATTRINDX(MT_DEVICE_nGnRnE))
 #define PROT_DEVICE_nGnRE	(PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_WRITE | PTE_ATTRINDX(MT_DEVICE_nGnRE))
@@ -55,22 +53,22 @@
 #define PROT_SECT_NORMAL	(PROT_SECT_DEFAULT | PMD_SECT_PXN | PMD_SECT_UXN | PMD_ATTRINDX(MT_NORMAL))
 #define PROT_SECT_NORMAL_EXEC	(PROT_SECT_DEFAULT | PMD_SECT_UXN | PMD_ATTRINDX(MT_NORMAL))
 
-#define _PAGE_DEFAULT		(PROT_DEFAULT | PTE_ATTRINDX(MT_NORMAL))
-#define _HYP_PAGE_DEFAULT	(_PAGE_DEFAULT & ~PTE_NG)
+#define _PAGE_DEFAULT		(_PROT_DEFAULT | PTE_ATTRINDX(MT_NORMAL))
+#define _HYP_PAGE_DEFAULT	_PAGE_DEFAULT
 
-#define PAGE_KERNEL		__pgprot(_PAGE_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_WRITE)
-#define PAGE_KERNEL_RO		__pgprot(_PAGE_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_RDONLY)
-#define PAGE_KERNEL_ROX		__pgprot(_PAGE_DEFAULT | PTE_UXN | PTE_DIRTY | PTE_RDONLY)
-#define PAGE_KERNEL_EXEC	__pgprot(_PAGE_DEFAULT | PTE_UXN | PTE_DIRTY | PTE_WRITE)
-#define PAGE_KERNEL_EXEC_CONT	__pgprot(_PAGE_DEFAULT | PTE_UXN | PTE_DIRTY | PTE_WRITE | PTE_CONT)
+#define PAGE_KERNEL		__pgprot(PROT_NORMAL)
+#define PAGE_KERNEL_RO		__pgprot((PROT_NORMAL & ~PTE_WRITE) | PTE_RDONLY)
+#define PAGE_KERNEL_ROX		__pgprot((PROT_NORMAL & ~(PTE_WRITE | PTE_PXN)) | PTE_RDONLY)
+#define PAGE_KERNEL_EXEC	__pgprot(PROT_NORMAL & ~PTE_PXN)
+#define PAGE_KERNEL_EXEC_CONT	__pgprot((PROT_NORMAL & ~PTE_PXN) | PTE_CONT)
 
 #define PAGE_HYP		__pgprot(_HYP_PAGE_DEFAULT | PTE_HYP | PTE_HYP_XN)
 #define PAGE_HYP_EXEC		__pgprot(_HYP_PAGE_DEFAULT | PTE_HYP | PTE_RDONLY)
 #define PAGE_HYP_RO		__pgprot(_HYP_PAGE_DEFAULT | PTE_HYP | PTE_RDONLY | PTE_HYP_XN)
 #define PAGE_HYP_DEVICE		__pgprot(PROT_DEVICE_nGnRE | PTE_HYP)
 
-#define PAGE_S2			__pgprot(PROT_DEFAULT | PTE_S2_MEMATTR(MT_S2_NORMAL) | PTE_S2_RDONLY)
-#define PAGE_S2_DEVICE		__pgprot(PROT_DEFAULT | PTE_S2_MEMATTR(MT_S2_DEVICE_nGnRE) | PTE_S2_RDONLY | PTE_UXN)
+#define PAGE_S2			__pgprot(_PROT_DEFAULT | PTE_S2_MEMATTR(MT_S2_NORMAL) | PTE_S2_RDONLY)
+#define PAGE_S2_DEVICE		__pgprot(_PROT_DEFAULT | PTE_S2_MEMATTR(MT_S2_DEVICE_nGnRE) | PTE_S2_RDONLY | PTE_UXN)
 
 #define PAGE_NONE		__pgprot(((_PAGE_DEFAULT) & ~PTE_VALID) | PTE_PROT_NONE | PTE_RDONLY | PTE_NG | PTE_PXN | PTE_UXN)
 #define PAGE_SHARED		__pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN | PTE_UXN | PTE_WRITE)
author maintainer
#43 lore raw

PATCH 43/202 arm64: mm: Permit transitioning from Global to Non-Global without BBM

In reply to Greg Kroah-Hartman

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Will Deacon <[email protected]>

Commit 4e6020565596 upstream.

Break-before-make is not needed when transitioning from Global to Non-Global mappings, provided that the contiguous hint is not being used.

---
 arch/arm64/mm/mmu.c |    4 ++++
 1 file changed, 4 insertions(+)
arch/arm64/mm/mmu.c +4 -0
@@ -117,6 +117,10 @@ static bool pgattr_change_is_safe(u64 ol
 	if ((old | new) & PTE_CONT)
 		return false;
 
+	/* Transitioning from Global to Non-Global is safe */
+	if (((old ^ new) == PTE_NG) && (new & PTE_NG))
+		return true;
+
 	return ((old ^ new) & ~mask) == 0;
 }
 
author maintainer
#44 lore raw

PATCH 44/202 arm64: kpti: Add ->enable callback to remap swapper using nG mappings

In reply to Greg Kroah-Hartman

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Will Deacon <[email protected]>

Commit f992b4dfd58b upstream.

Defaulting to global mappings for kernel space is generally good for performance and appears to be necessary for Cavium ThunderX. If we subsequently decide that we need to enable kpti, then we need to rewrite our existing page table entries to be non-global. This is fiddly, and made worse by the possible use of contiguous mappings, which require a strict break-before-make sequence.

Since the enable callback runs on each online CPU from stop_machine context, we can have all CPUs enter the idmap, where secondaries can wait for the primary CPU to rewrite swapper with its MMU off. It's all fairly horrible, but at least it only runs once.

Conflicts:

	arch/arm64/mm/proc.S
---
 arch/arm64/include/asm/assembler.h |    4 
 arch/arm64/kernel/cpufeature.c     |   25 ++++
 arch/arm64/mm/proc.S               |  202 +++++++++++++++++++++++++++++++++++--
 3 files changed, 224 insertions(+), 7 deletions(-)
arch/arm64/include/asm/assembler.h +4 -0
@@ -489,6 +489,10 @@ alternative_else_nop_endif
 #endif
 	.endm
 
+	.macro	pte_to_phys, phys, pte
+	and	\phys, \pte, #(((1 << (48 - PAGE_SHIFT)) - 1) << PAGE_SHIFT)
+	.endm
+
 /**
  * Errata workaround prior to disable MMU. Insert an ISB immediately prior
  * to executing the MSR that will change SCTLR_ELn[M] from a value of 1 to 0.
arch/arm64/kernel/cpufeature.c +25 -0
@@ -878,6 +878,30 @@ static bool unmap_kernel_at_el0(const st
 						     ID_AA64PFR0_CSV3_SHIFT);
 }
 
+static int kpti_install_ng_mappings(void *__unused)
+{
+	typedef void (kpti_remap_fn)(int, int, phys_addr_t);
+	extern kpti_remap_fn idmap_kpti_install_ng_mappings;
+	kpti_remap_fn *remap_fn;
+
+	static bool kpti_applied = false;
+	int cpu = smp_processor_id();
+
+	if (kpti_applied)
+		return 0;
+
+	remap_fn = (void *)__pa_symbol(idmap_kpti_install_ng_mappings);
+
+	cpu_install_idmap();
+	remap_fn(cpu, num_online_cpus(), __pa_symbol(swapper_pg_dir));
+	cpu_uninstall_idmap();
+
+	if (!cpu)
+		kpti_applied = true;
+
+	return 0;
+}
+
 static int __init parse_kpti(char *str)
 {
 	bool enabled;
@@ -984,6 +1008,7 @@ static const struct arm64_cpu_capabiliti
 		.capability = ARM64_UNMAP_KERNEL_AT_EL0,
 		.def_scope = SCOPE_SYSTEM,
 		.matches = unmap_kernel_at_el0,
+		.enable = kpti_install_ng_mappings,
 	},
 #endif
 	{
arch/arm64/mm/proc.S +195 -7

220 lines not on this page · raw message

author maintainer
#45 lore raw

PATCH 45/202 arm64: Force KPTI to be disabled on Cavium ThunderX

In reply to Greg Kroah-Hartman

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Marc Zyngier <[email protected]>

Commit 6dc52b15c4a4 upstream.

Cavium ThunderX's erratum 27456 results in a corruption of icache entries that are loaded from memory that is mapped as non-global (i.e. ASID-tagged).

As KPTI is based on memory being mapped non-global, let's prevent it from kicking in if this erratum is detected.

---
 arch/arm64/kernel/cpufeature.c |   17 ++++++++++++++---
 1 file changed, 14 insertions(+), 3 deletions(-)
arch/arm64/kernel/cpufeature.c +14 -3
@@ -853,12 +853,23 @@ static int __kpti_forced; /* 0: not forc
 static bool unmap_kernel_at_el0(const struct arm64_cpu_capabilities *entry,
 				int __unused)
 {
+	char const *str = "command line option";
 	u64 pfr0 = read_sanitised_ftr_reg(SYS_ID_AA64PFR0_EL1);
 
-	/* Forced on command line? */
+	/*
+	 * For reasons that aren't entirely clear, enabling KPTI on Cavium
+	 * ThunderX leads to apparent I-cache corruption of kernel text, which
+	 * ends as well as you might imagine. Don't even try.
+	 */
+	if (cpus_have_const_cap(ARM64_WORKAROUND_CAVIUM_27456)) {
+		str = "ARM64_WORKAROUND_CAVIUM_27456";
+		__kpti_forced = -1;
+	}
+
+	/* Forced? */
 	if (__kpti_forced) {
-		pr_info_once("kernel page table isolation forced %s by command line option\n",
-			     __kpti_forced > 0 ? "ON" : "OFF");
+		pr_info_once("kernel page table isolation forced %s by %s\n",
+			     __kpti_forced > 0 ? "ON" : "OFF", str);
 		return __kpti_forced > 0;
 	}
 
author maintainer
#46 lore raw

PATCH 46/202 arm64: entry: Reword comment about post_ttbr_update_workaround

In reply to Greg Kroah-Hartman

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Will Deacon <[email protected]>

Commit f167211a93ac upstream.

We don't fully understand the Cavium ThunderX erratum, but it appears that mapping the kernel as nG can lead to horrible consequences such as attempting to execute userspace from kernel context. Since kpti isn't enabled for these CPUs anyway, simplify the comment justifying the lack of post_ttbr_update_workaround in the exception trampoline.

---
 arch/arm64/kernel/entry.S |   13 +++----------
 1 file changed, 3 insertions(+), 10 deletions(-)
arch/arm64/kernel/entry.S +3 -10
@@ -1010,16 +1010,9 @@ alternative_else_nop_endif
 	orr	\tmp, \tmp, #USER_ASID_FLAG
 	msr	ttbr1_el1, \tmp
 	/*
-	 * We avoid running the post_ttbr_update_workaround here because the
-	 * user and kernel ASIDs don't have conflicting mappings, so any
-	 * "blessing" as described in:
-	 *
-	 *   http://lkml.kernel.org/r/[email protected]
-	 *
-	 * will not hurt correctness. Whilst this may partially defeat the
-	 * point of using split ASIDs in the first place, it avoids
-	 * the hit of invalidating the entire I-cache on every return to
-	 * userspace.
+	 * We avoid running the post_ttbr_update_workaround here because
+	 * it's only needed by Cavium ThunderX, which requires KPTI to be
+	 * disabled.
 	 */
 	.endm
 
author maintainer
#47 lore raw

PATCH 47/202 arm64: idmap: Use "awx" flags for .idmap.text .pushsection directives

In reply to Greg Kroah-Hartman

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Will Deacon <[email protected]>

Commit 439e70e27a51 upstream.

The identity map is mapped as both writeable and executable by the SWAPPER_MM_MMUFLAGS and this is relied upon by the kpti code to manage a synchronisation flag. Update the .pushsection flags to reflect the actual mapping attributes.

---
 arch/arm64/kernel/cpu-reset.S |    2 +-
 arch/arm64/kernel/head.S      |    2 +-
 arch/arm64/kernel/sleep.S     |    2 +-
 arch/arm64/mm/proc.S          |    8 ++++----
 4 files changed, 7 insertions(+), 7 deletions(-)
arch/arm64/kernel/cpu-reset.S +1 -1
@@ -16,7 +16,7 @@
 #include <asm/virt.h>
 
 .text
-.pushsection    .idmap.text, "ax"
+.pushsection    .idmap.text, "awx"
 
 /*
  * __cpu_soft_restart(el2_switch, entry, arg0, arg1, arg2) - Helper for
arch/arm64/kernel/head.S +1 -1
@@ -371,7 +371,7 @@ ENDPROC(__primary_switched)
  * end early head section, begin head code that is also used for
  * hotplug and needs to have the same protections as the text region
  */
-	.section ".idmap.text","ax"
+	.section ".idmap.text","awx"
 
 ENTRY(kimage_vaddr)
 	.quad		_text - TEXT_OFFSET
arch/arm64/kernel/sleep.S +1 -1
@@ -96,7 +96,7 @@ ENTRY(__cpu_suspend_enter)
 	ret
 ENDPROC(__cpu_suspend_enter)
 
-	.pushsection ".idmap.text", "ax"
+	.pushsection ".idmap.text", "awx"
 ENTRY(cpu_resume)
 	bl	el2_setup		// if in EL2 drop to EL1 cleanly
 	bl	__cpu_setup
arch/arm64/mm/proc.S +4 -4
@@ -86,7 +86,7 @@ ENDPROC(cpu_do_suspend)
  *
  * x0: Address of context pointer
  */
-	.pushsection ".idmap.text", "ax"
+	.pushsection ".idmap.text", "awx"
 ENTRY(cpu_do_resume)
 	ldp	x2, x3, [x0]
 	ldp	x4, x5, [x0, #16]
@@ -152,7 +152,7 @@ ENTRY(cpu_do_switch_mm)
 	ret
 ENDPROC(cpu_do_switch_mm)
 
-	.pushsection ".idmap.text", "ax"
+	.pushsection ".idmap.text", "awx"
 
 .macro	__idmap_cpu_set_reserved_ttbr1, tmp1, tmp2
 	adrp	\tmp1, empty_zero_page
@@ -184,7 +184,7 @@ ENDPROC(idmap_cpu_replace_ttbr1)
 	.popsection
 
 #ifdef CONFIG_UNMAP_KERNEL_AT_EL0
-	.pushsection ".idmap.text", "ax"
+	.pushsection ".idmap.text", "awx"
 
 	.macro	__idmap_kpti_get_pgtable_ent, type
 	dc	cvac, cur_\()\type\()p		// Ensure any existing dirty
@@ -373,7 +373,7 @@ ENDPROC(idmap_kpti_install_ng_mappings)
  *	Initialise the processor for turning the MMU on.  Return in x0 the
  *	value of the SCTLR_EL1 register.
  */
-	.pushsection ".idmap.text", "ax"
+	.pushsection ".idmap.text", "awx"
 ENTRY(__cpu_setup)
 	tlbi	vmalle1				// Invalidate local TLB
 	dsb	nsh
author maintainer
#48 lore raw

PATCH 48/202 perf: arm_spe: Fail device probe when arm64_kernel_unmapped_at_el0()

In reply to Greg Kroah-Hartman

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Will Deacon <[email protected]>

Commit 7a4a0c1555b8 upstream.

When running with the kernel unmapped whilst at EL0, the virtually-addressed SPE buffer is also unmapped, which can lead to buffer faults if userspace profiling is enabled and potentially also when writing back kernel samples unless an expensive drain operation is performed on exception return.

For now, fail the SPE driver probe when arm64_kernel_unmapped_at_el0().

---
 drivers/perf/arm_spe_pmu.c |    9 +++++++++
 1 file changed, 9 insertions(+)
drivers/perf/arm_spe_pmu.c +9 -0
@@ -1164,6 +1164,15 @@ static int arm_spe_pmu_device_dt_probe(s
 	struct arm_spe_pmu *spe_pmu;
 	struct device *dev = &pdev->dev;
 
+	/*
+	 * If kernelspace is unmapped when running at EL0, then the SPE
+	 * buffer will fault and prematurely terminate the AUX session.
+	 */
+	if (arm64_kernel_unmapped_at_el0()) {
+		dev_warn_once(dev, "profiling buffer inaccessible. Try passing \"kpti=off\" on the kernel command line\n");
+		return -EPERM;
+	}
+
 	spe_pmu = devm_kzalloc(dev, sizeof(*spe_pmu), GFP_KERNEL);
 	if (!spe_pmu) {
 		dev_err(dev, "failed to allocate spe_pmu\n");
author maintainer
#49 lore raw

PATCH 49/202 arm64: barrier: Add CSDB macros to control data-value prediction

In reply to Greg Kroah-Hartman

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Will Deacon <[email protected]>

Commit 669474e772b9 upstream.

For CPUs capable of data value prediction, CSDB waits for any outstanding predictions to architecturally resolve before allowing speculative execution to continue. Provide macros to expose it to the arch code.

Conflicts:
arch/arm64/include/asm/assembler.h

---
 arch/arm64/include/asm/assembler.h |    7 +++++++
 arch/arm64/include/asm/barrier.h   |    1 +
 2 files changed, 8 insertions(+)
arch/arm64/include/asm/assembler.h +7 -0
@@ -109,6 +109,13 @@
 	.endm
 
 /*
+ * Value prediction barrier
+ */
+	.macro	csdb
+	hint	#20
+	.endm
+
+/*
  * NOP sequence
  */
 	.macro	nops, num
arch/arm64/include/asm/barrier.h +1 -0
@@ -32,6 +32,7 @@
 #define dsb(opt)	asm volatile("dsb " #opt : : : "memory")
 
 #define psb_csync()	asm volatile("hint #17" : : : "memory")
+#define csdb()		asm volatile("hint #20" : : : "memory")
 
 #define mb()		dsb(sy)
 #define rmb()		dsb(ld)
author maintainer
#50 lore raw

PATCH 50/202 arm64: Implement array_index_mask_nospec()

In reply to Greg Kroah-Hartman

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Robin Murphy <[email protected]>

Commit 022620eed3d0 upstream.

Provide an optimised, assembly implementation of array_index_mask_nospec() for arm64 so that the compiler is not in a position to transform the code in ways which affect its ability to inhibit speculation (e.g. by introducing conditional branches).

This is similar to the sequence used by x86, modulo architectural differences in the carry/borrow flags.

---
 arch/arm64/include/asm/barrier.h |   21 +++++++++++++++++++++
 1 file changed, 21 insertions(+)
arch/arm64/include/asm/barrier.h +21 -0
@@ -41,6 +41,27 @@
 #define dma_rmb()	dmb(oshld)
 #define dma_wmb()	dmb(oshst)
 
+/*
+ * Generate a mask for array_index__nospec() that is ~0UL when 0 <= idx < sz
+ * and 0 otherwise.
+ */
+#define array_index_mask_nospec array_index_mask_nospec
+static inline unsigned long array_index_mask_nospec(unsigned long idx,
+						    unsigned long sz)
+{
+	unsigned long mask;
+
+	asm volatile(
+	"	cmp	%1, %2\n"
+	"	sbc	%0, xzr, xzr\n"
+	: "=r" (mask)
+	: "r" (idx), "Ir" (sz)
+	: "cc");
+
+	csdb();
+	return mask;
+}
+
 #define __smp_mb()	dmb(ish)
 #define __smp_rmb()	dmb(ishld)
 #define __smp_wmb()	dmb(ishst)
author maintainer
#51 lore raw

PATCH 51/202 arm64: Make USER_DS an inclusive limit

In reply to Greg Kroah-Hartman

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Robin Murphy <[email protected]>

Commit 51369e398d0d upstream.

Currently, USER_DS represents an exclusive limit while KERNEL_DS is inclusive. In order to do some clever trickery for speculation-safe masking, we need them both to behave equivalently - there aren't enough bits to make KERNEL_DS exclusive, so we have precisely one option. This also happens to correct a longstanding false negative for a range ending on the very top byte of kernel memory.

Mark Rutland points out that we've actually got the semantics of addresses vs. segments muddled up in most of the places we need to amend, so shuffle the {USER,KERNEL}_DS definitions around such that we can correct those properly instead of just pasting "-1"s everywhere.

---
 arch/arm64/include/asm/processor.h |    3 ++
 arch/arm64/include/asm/uaccess.h   |   45 +++++++++++++++++++++----------------
 arch/arm64/kernel/entry.S          |    4 +--
 arch/arm64/mm/fault.c              |    4 +--
 4 files changed, 33 insertions(+), 23 deletions(-)
arch/arm64/include/asm/processor.h +3 -0
@@ -21,6 +21,9 @@
 
 #define TASK_SIZE_64		(UL(1) << VA_BITS)
 
+#define KERNEL_DS	UL(-1)
+#define USER_DS		(TASK_SIZE_64 - 1)
+
 #ifndef __ASSEMBLY__
 
 /*
arch/arm64/include/asm/uaccess.h +26 -19

65 lines not on this page · raw message

arch/arm64/kernel/entry.S +2 -2
@@ -167,10 +167,10 @@ alternative_else_nop_endif
 	.else
 	add	x21, sp, #S_FRAME_SIZE
 	get_thread_info tsk
-	/* Save the task's original addr_limit and set USER_DS (TASK_SIZE_64) */
+	/* Save the task's original addr_limit and set USER_DS */
 	ldr	x20, [tsk, #TSK_TI_ADDR_LIMIT]
 	str	x20, [sp, #S_ORIG_ADDR_LIMIT]
-	mov	x20, #TASK_SIZE_64
+	mov	x20, #USER_DS
 	str	x20, [tsk, #TSK_TI_ADDR_LIMIT]
 	/* No need to reset PSTATE.UAO, hardware's already set it to 0 for us */
 	.endif /* \el == 0 */
arch/arm64/mm/fault.c +2 -2
@@ -240,7 +240,7 @@ static inline bool is_permission_fault(u
 	if (fsc_type == ESR_ELx_FSC_PERM)
 		return true;
 
-	if (addr < USER_DS && system_uses_ttbr0_pan())
+	if (addr < TASK_SIZE && system_uses_ttbr0_pan())
 		return fsc_type == ESR_ELx_FSC_FAULT &&
 			(regs->pstate & PSR_PAN_BIT);
 
@@ -414,7 +414,7 @@ static int __kprobes do_page_fault(unsig
 		mm_flags |= FAULT_FLAG_WRITE;
 	}
 
-	if (addr < USER_DS && is_permission_fault(esr, regs, addr)) {
+	if (addr < TASK_SIZE && is_permission_fault(esr, regs, addr)) {
 		/* regs->orig_addr_limit may be 0 if we entered from EL0 */
 		if (regs->orig_addr_limit == KERNEL_DS)
 			die("Accessing user space memory with fs=KERNEL_DS", regs, esr);
author maintainer
#52 lore raw

PATCH 52/202 arm64: Use pointer masking to limit uaccess speculation

In reply to Greg Kroah-Hartman

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Robin Murphy <[email protected]>

Commit 4d8efc2d5ee4 upstream.

Similarly to x86, mitigate speculation past an access_ok() check by masking the pointer against the address limit before use.

Even if we don't expect speculative writes per se, it is plausible that a CPU may still speculate at least as far as fetching a cache line for writing, hence we also harden put_user() and clear_user() for peace of mind.

---
 arch/arm64/include/asm/uaccess.h |   26 +++++++++++++++++++++++---
 1 file changed, 23 insertions(+), 3 deletions(-)
arch/arm64/include/asm/uaccess.h +23 -3
@@ -216,6 +216,26 @@ static inline void uaccess_enable_not_ua
 }
 
 /*
+ * Sanitise a uaccess pointer such that it becomes NULL if above the
+ * current addr_limit.
+ */
+#define uaccess_mask_ptr(ptr) (__typeof__(ptr))__uaccess_mask_ptr(ptr)
+static inline void __user *__uaccess_mask_ptr(const void __user *ptr)
+{
+	void __user *safe_ptr;
+
+	asm volatile(
+	"	bics	xzr, %1, %2\n"
+	"	csel	%0, %1, xzr, eq\n"
+	: "=&r" (safe_ptr)
+	: "r" (ptr), "r" (current_thread_info()->addr_limit)
+	: "cc");
+
+	csdb();
+	return safe_ptr;
+}
+
+/*
  * The "__xxx" versions of the user access functions do not verify the address
  * space - it must have been done previously with a separate "access_ok()"
  * call.
@@ -285,7 +305,7 @@ do {									\
 	__typeof__(*(ptr)) __user *__p = (ptr);				\
 	might_fault();							\
 	access_ok(VERIFY_READ, __p, sizeof(*__p)) ?			\
-		__get_user((x), __p) :					\
+		__p = uaccess_mask_ptr(__p), __get_user((x), __p) :	\
 		((x) = 0, -EFAULT);					\
 })
 
@@ -349,7 +369,7 @@ do {									\
 	__typeof__(*(ptr)) __user *__p = (ptr);				\
 	might_fault();							\
 	access_ok(VERIFY_WRITE, __p, sizeof(*__p)) ?			\
-		__put_user((x), __p) :					\
+		__p = uaccess_mask_ptr(__p), __put_user((x), __p) :	\
 		-EFAULT;						\
 })
 
@@ -365,7 +385,7 @@ extern unsigned long __must_check __clea
 static inline unsigned long __must_check clear_user(void __user *to, unsigned long n)
 {
 	if (access_ok(VERIFY_WRITE, to, n))
-		n = __clear_user(to, n);
+		n = __clear_user(__uaccess_mask_ptr(to), n);
 	return n;
 }
 
author maintainer
#53 lore raw

PATCH 53/202 arm64: entry: Ensure branch through syscall table is bounded under speculation

In reply to Greg Kroah-Hartman

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Will Deacon <[email protected]>

Commit 6314d90e6493 upstream.

In a similar manner to array_index_mask_nospec, this patch introduces an assembly macro (mask_nospec64) which can be used to bound a value under speculation. This macro is then used to ensure that the indirect branch through the syscall table is bounded under speculation, with out-of-range addresses speculating as calls to sys_io_setup (0).

---
 arch/arm64/include/asm/assembler.h |   11 +++++++++++
 arch/arm64/kernel/entry.S          |    2 ++
 2 files changed, 13 insertions(+)
arch/arm64/include/asm/assembler.h +11 -0
@@ -116,6 +116,17 @@
 	.endm
 
 /*
+ * Sanitise a 64-bit bounded index wrt speculation, returning zero if out
+ * of bounds.
+ */
+	.macro	mask_nospec64, idx, limit, tmp
+	sub	\tmp, \idx, \limit
+	bic	\tmp, \tmp, \idx
+	and	\idx, \idx, \tmp, asr #63
+	csdb
+	.endm
+
+/*
  * NOP sequence
  */
 	.macro	nops, num
arch/arm64/kernel/entry.S +2 -0
@@ -378,6 +378,7 @@ alternative_insn eret, nop, ARM64_UNMAP_
  * x7 is reserved for the system call number in 32-bit mode.
  */
 wsc_nr	.req	w25		// number of system calls
+xsc_nr	.req	x25		// number of system calls (zero-extended)
 wscno	.req	w26		// syscall number
 xscno	.req	x26		// syscall number (zero-extended)
 stbl	.req	x27		// syscall table pointer
@@ -932,6 +933,7 @@ el0_svc_naked:					// compat entry point
 	b.ne	__sys_trace
 	cmp     wscno, wsc_nr			// check upper syscall limit
 	b.hs	ni_sys
+	mask_nospec64 xscno, xsc_nr, x19	// enforce bounds for syscall number
 	ldr	x16, [stbl, xscno, lsl #3]	// address in the syscall table
 	blr	x16				// call sys_* routine
 	b	ret_fast_syscall
author maintainer
#54 lore raw

PATCH 54/202 arm64: uaccess: Prevent speculative use of the current addr_limit

In reply to Greg Kroah-Hartman

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Will Deacon <[email protected]>

Commit c2f0ad4fc089 upstream.

A mispredicted conditional call to set_fs could result in the wrong addr_limit being forwarded under speculation to a subsequent access_ok check, potentially forming part of a spectre-v1 attack using uaccess routines.

This patch prevents this forwarding from taking place, but putting heavy barriers in set_fs after writing the addr_limit.

---
 arch/arm64/include/asm/uaccess.h |    7 +++++++
 1 file changed, 7 insertions(+)
arch/arm64/include/asm/uaccess.h +7 -0
@@ -42,6 +42,13 @@ static inline void set_fs(mm_segment_t f
 {
 	current_thread_info()->addr_limit = fs;
 
+	/*
+	 * Prevent a mispredicted conditional call to set_fs from forwarding
+	 * the wrong address limit to access_ok under speculation.
+	 */
+	dsb(nsh);
+	isb();
+
 	/* On user-mode return, check fs is correct */
 	set_thread_flag(TIF_FSCHECK);
 
author maintainer
#55 lore raw

PATCH 55/202 arm64: uaccess: Dont bother eliding access_ok checks in __{get, put}_user

In reply to Greg Kroah-Hartman

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Will Deacon <[email protected]>

Commit 84624087dd7e upstream.

access_ok isn't an expensive operation once the addr_limit for the current thread has been loaded into the cache. Given that the initial access_ok check preceding a sequence of __{get,put}_user operations will take the brunt of the miss, we can make the __* variants identical to the full-fat versions, which brings with it the benefits of address masking.

The likely cost in these sequences will be from toggling PAN/UAO, which we can address later by implementing the *_unsafe versions.

---
 arch/arm64/include/asm/uaccess.h |   54 +++++++++++++++++++++++----------------
 1 file changed, 32 insertions(+), 22 deletions(-)
arch/arm64/include/asm/uaccess.h +32 -22
@@ -294,28 +294,33 @@ do {									\
 	(x) = (__force __typeof__(*(ptr)))__gu_val;			\
 } while (0)
 
-#define __get_user(x, ptr)						\
+#define __get_user_check(x, ptr, err)					\
 ({									\
-	int __gu_err = 0;						\
-	__get_user_err((x), (ptr), __gu_err);				\
-	__gu_err;							\
+	__typeof__(*(ptr)) __user *__p = (ptr);				\
+	might_fault();							\
+	if (access_ok(VERIFY_READ, __p, sizeof(*__p))) {		\
+		__p = uaccess_mask_ptr(__p);				\
+		__get_user_err((x), __p, (err));			\
+	} else {							\
+		(x) = 0; (err) = -EFAULT;				\
+	}								\
 })
 
 #define __get_user_error(x, ptr, err)					\
 ({									\
-	__get_user_err((x), (ptr), (err));				\
+	__get_user_check((x), (ptr), (err));				\
 	(void)0;							\
 })
 
-#define get_user(x, ptr)						\
+#define __get_user(x, ptr)						\
 ({									\
-	__typeof__(*(ptr)) __user *__p = (ptr);				\
-	might_fault();							\
-	access_ok(VERIFY_READ, __p, sizeof(*__p)) ?			\
-		__p = uaccess_mask_ptr(__p), __get_user((x), __p) :	\
-		((x) = 0, -EFAULT);					\
+	int __gu_err = 0;						\
+	__get_user_check((x), (ptr), __gu_err);				\
+	__gu_err;							\
 })
 
+#define get_user	__get_user
+
 #define __put_user_asm(instr, alt_instr, reg, x, addr, err, feature)	\
 	asm volatile(							\
 	"1:"ALTERNATIVE(instr "     " reg "1, [%2]\n",			\
@@ -358,28 +363,33 @@ do {									\
 	uaccess_disable_not_uao();					\
 } while (0)
 
-#define __put_user(x, ptr)						\
+#define __put_user_check(x, ptr, err)					\
 ({									\
-	int __pu_err = 0;						\
-	__put_user_err((x), (ptr), __pu_err);				\
-	__pu_err;							\
+	__typeof__(*(ptr)) __user *__p = (ptr);				\
+	might_fault();							\
+	if (access_ok(VERIFY_WRITE, __p, sizeof(*__p))) {		\
+		__p = uaccess_mask_ptr(__p);				\
+		__put_user_err((x), __p, (err));			\
+	} else	{							\
+		(err) = -EFAULT;					\
+	}								\
 })
 
 #define __put_user_error(x, ptr, err)					\
 ({									\
-	__put_user_err((x), (ptr), (err));				\
+	__put_user_check((x), (ptr), (err));				\
 	(void)0;							\
 })
 
-#define put_user(x, ptr)						\
+#define __put_user(x, ptr)						\
 ({									\
-	__typeof__(*(ptr)) __user *__p = (ptr);				\
-	might_fault();							\
-	access_ok(VERIFY_WRITE, __p, sizeof(*__p)) ?			\
-		__p = uaccess_mask_ptr(__p), __put_user((x), __p) :	\
-		-EFAULT;						\
+	int __pu_err = 0;						\
+	__put_user_check((x), (ptr), __pu_err);				\
+	__pu_err;							\
 })
 
+#define put_user	__put_user
+
 extern unsigned long __must_check __arch_copy_from_user(void *to, const void __user *from, unsigned long n);
 #define raw_copy_from_user __arch_copy_from_user
 extern unsigned long __must_check __arch_copy_to_user(void __user *to, const void *from, unsigned long n);
author maintainer
#56 lore raw

PATCH 56/202 arm64: uaccess: Mask __user pointers for __arch_{clear, copy_*}_user

In reply to Greg Kroah-Hartman

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Will Deacon <[email protected]>

Commit f71c2ffcb20d upstream.

Like we've done for get_user and put_user, ensure that user pointers are masked before invoking the underlying __arch_{clear,copy_*}_user operations.

---
 arch/arm64/include/asm/uaccess.h |   29 ++++++++++++++++++++++-------
 arch/arm64/kernel/arm64ksyms.c   |    4 ++--
 arch/arm64/lib/clear_user.S      |    6 +++---
 arch/arm64/lib/copy_in_user.S    |    5 +++--
 4 files changed, 30 insertions(+), 14 deletions(-)
arch/arm64/include/asm/uaccess.h +22 -7
@@ -391,20 +391,35 @@ do {									\
 #define put_user	__put_user
 
 extern unsigned long __must_check __arch_copy_from_user(void *to, const void __user *from, unsigned long n);
-#define raw_copy_from_user __arch_copy_from_user
+#define raw_copy_from_user(to, from, n)					\
+({									\
+	__arch_copy_from_user((to), __uaccess_mask_ptr(from), (n));	\
+})
+
 extern unsigned long __must_check __arch_copy_to_user(void __user *to, const void *from, unsigned long n);
-#define raw_copy_to_user __arch_copy_to_user
-extern unsigned long __must_check raw_copy_in_user(void __user *to, const void __user *from, unsigned long n);
-extern unsigned long __must_check __clear_user(void __user *addr, unsigned long n);
+#define raw_copy_to_user(to, from, n)					\
+({									\
+	__arch_copy_to_user(__uaccess_mask_ptr(to), (from), (n));	\
+})
+
+extern unsigned long __must_check __arch_copy_in_user(void __user *to, const void __user *from, unsigned long n);
+#define raw_copy_in_user(to, from, n)					\
+({									\
+	__arch_copy_in_user(__uaccess_mask_ptr(to),			\
+			    __uaccess_mask_ptr(from), (n));		\
+})
+
 #define INLINE_COPY_TO_USER
 #define INLINE_COPY_FROM_USER
 
-static inline unsigned long __must_check clear_user(void __user *to, unsigned long n)
+extern unsigned long __must_check __arch_clear_user(void __user *to, unsigned long n);
+static inline unsigned long __must_check __clear_user(void __user *to, unsigned long n)
 {
 	if (access_ok(VERIFY_WRITE, to, n))
-		n = __clear_user(__uaccess_mask_ptr(to), n);
+		n = __arch_clear_user(__uaccess_mask_ptr(to), n);
 	return n;
 }
+#define clear_user	__clear_user
 
 extern long strncpy_from_user(char *dest, const char __user *src, long count);
 
@@ -418,7 +433,7 @@ extern unsigned long __must_check __copy
 static inline int __copy_from_user_flushcache(void *dst, const void __user *src, unsigned size)
 {
 	kasan_check_write(dst, size);
-	return __copy_user_flushcache(dst, src, size);
+	return __copy_user_flushcache(dst, __uaccess_mask_ptr(src), size);
 }
 #endif
 
arch/arm64/kernel/arm64ksyms.c +2 -2
@@ -37,8 +37,8 @@ EXPORT_SYMBOL(clear_page);
 	/* user mem (segment) */
 EXPORT_SYMBOL(__arch_copy_from_user);
 EXPORT_SYMBOL(__arch_copy_to_user);
-EXPORT_SYMBOL(__clear_user);
-EXPORT_SYMBOL(raw_copy_in_user);
+EXPORT_SYMBOL(__arch_clear_user);
+EXPORT_SYMBOL(__arch_copy_in_user);
 
 	/* physical memory */
 EXPORT_SYMBOL(memstart_addr);
arch/arm64/lib/clear_user.S +3 -3
@@ -21,7 +21,7 @@
 
 	.text
 
-/* Prototype: int __clear_user(void *addr, size_t sz)
+/* Prototype: int __arch_clear_user(void *addr, size_t sz)
  * Purpose  : clear some user memory
  * Params   : addr - user memory address to clear
  *          : sz   - number of bytes to clear
@@ -29,7 +29,7 @@
  *
  * Alignment fixed up by hardware.
  */
-ENTRY(__clear_user)
+ENTRY(__arch_clear_user)
 	uaccess_enable_not_uao x2, x3, x4
 	mov	x2, x1			// save the size for fixup return
 	subs	x1, x1, #8
@@ -52,7 +52,7 @@ uao_user_alternative 9f, strb, sttrb, wz
 5:	mov	x0, #0
 	uaccess_disable_not_uao x2, x3
 	ret
-ENDPROC(__clear_user)
+ENDPROC(__arch_clear_user)
 
 	.section .fixup,"ax"
 	.align	2
arch/arm64/lib/copy_in_user.S +3 -2
@@ -64,14 +64,15 @@
 	.endm
 
 end	.req	x5
-ENTRY(raw_copy_in_user)
+
+ENTRY(__arch_copy_in_user)
 	uaccess_enable_not_uao x3, x4, x5
 	add	end, x0, x2
 #include "copy_template.S"
 	uaccess_disable_not_uao x3, x4
 	mov	x0, #0
 	ret
-ENDPROC(raw_copy_in_user)
+ENDPROC(__arch_copy_in_user)
 
 	.section .fixup,"ax"
 	.align	2
author maintainer
#57 lore raw

PATCH 57/202 arm64: futex: Mask __user pointers prior to dereference

In reply to Greg Kroah-Hartman

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Will Deacon <[email protected]>

Commit 91b2d3442f6a upstream.

The arm64 futex code has some explicit dereferencing of user pointers where performing atomic operations in response to a futex command. This patch uses masking to limit any speculative futex operations to within the user address space.

---
 arch/arm64/include/asm/futex.h |    9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)
arch/arm64/include/asm/futex.h +6 -3
@@ -48,9 +48,10 @@ do {									\
 } while (0)
 
 static inline int
-arch_futex_atomic_op_inuser(int op, int oparg, int *oval, u32 __user *uaddr)
+arch_futex_atomic_op_inuser(int op, int oparg, int *oval, u32 __user *_uaddr)
 {
 	int oldval = 0, ret, tmp;
+	u32 __user *uaddr = __uaccess_mask_ptr(_uaddr);
 
 	pagefault_disable();
 
@@ -88,15 +89,17 @@ arch_futex_atomic_op_inuser(int op, int
 }
 
 static inline int
-futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
+futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *_uaddr,
 			      u32 oldval, u32 newval)
 {
 	int ret = 0;
 	u32 val, tmp;
+	u32 __user *uaddr;
 
-	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32)))
+	if (!access_ok(VERIFY_WRITE, _uaddr, sizeof(u32)))
 		return -EFAULT;
 
+	uaddr = __uaccess_mask_ptr(_uaddr);
 	uaccess_enable();
 	asm volatile("// futex_atomic_cmpxchg_inatomic\n"
 "	prfm	pstl1strm, %2\n"
author maintainer
#58 lore raw

PATCH 58/202 arm64: cpufeature: __this_cpu_has_cap() shouldnt stop early

In reply to Greg Kroah-Hartman

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: James Morse <[email protected]>

Commit edf298cfce47 upstream.

this_cpu_has_cap() tests caps->desc not caps->matches, so it stops walking the list when it finds a 'silent' feature, instead of walking to the end of the list.

Prior to v4.6's 644c2ae198412 ("arm64: cpufeature: Test 'matches' pointer to find the end of the list") we always tested desc to find the end of a capability list. This was changed for dubious things like PAN_NOT_UAO. v4.7's e3661b128e53e ("arm64: Allow a capability to be checked on single CPU") added this_cpu_has_cap() using the old desc style test.

---
 arch/arm64/kernel/cpufeature.c |    3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)
arch/arm64/kernel/cpufeature.c +1 -2
@@ -1173,9 +1173,8 @@ static bool __this_cpu_has_cap(const str
 	if (WARN_ON(preemptible()))
 		return false;
 
-	for (caps = cap_array; caps->desc; caps++)
+	for (caps = cap_array; caps->matches; caps++)
 		if (caps->capability == cap &&
-		    caps->matches &&
 		    caps->matches(caps, SCOPE_LOCAL_CPU))
 			return true;
 	return false;
author maintainer
#59 lore raw

PATCH 59/202 arm64: Run enable method for errata work arounds on late CPUs

In reply to Greg Kroah-Hartman

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Suzuki K Poulose <[email protected]>

Commit 55b35d070c25 upstream.

When a CPU is brought up after we have finalised the system wide capabilities (i.e, features and errata), we make sure the new CPU doesn't need a new errata work around which has not been detected already. However we don't run enable() method on the new CPU for the errata work arounds already detected. This could cause the new CPU running without potential work arounds. It is upto the "enable()" method to decide if this CPU should do something about the errata.

Fixes commit 6a6efbb45b7d95c84 ("arm64: Verify CPU errata work arounds on hotplugged CPU")
Cc Will Deacon <[email protected]>
Cc Mark Rutland <[email protected]>
Cc Andre Przywara <[email protected]>
Cc Dave Martin <[email protected]>
---
 arch/arm64/kernel/cpu_errata.c |    9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)
arch/arm64/kernel/cpu_errata.c +6 -3
@@ -221,15 +221,18 @@ void verify_local_cpu_errata_workarounds
 {
 	const struct arm64_cpu_capabilities *caps = arm64_errata;
 
-	for (; caps->matches; caps++)
-		if (!cpus_have_cap(caps->capability) &&
-			caps->matches(caps, SCOPE_LOCAL_CPU)) {
+	for (; caps->matches; caps++) {
+		if (cpus_have_cap(caps->capability)) {
+			if (caps->enable)
+				caps->enable((void *)caps);
+		} else if (caps->matches(caps, SCOPE_LOCAL_CPU)) {
 			pr_crit("CPU%d: Requires work around for %s, not detected"
 					" at boot time\n",
 				smp_processor_id(),
 				caps->desc ? : "an erratum");
 			cpu_die_early();
 		}
+	}
 }
 
 void update_cpu_errata_workarounds(void)
author maintainer
#60 lore raw

PATCH 60/202 arm64: cpufeature: Pass capability structure to ->enable callback

In reply to Greg Kroah-Hartman

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Will Deacon <[email protected]>

Commit 0a0d111d40fd upstream.

In order to invoke the CPU capability ->matches callback from the ->enable callback for applying local-CPU workarounds, we need a handle on the capability structure.

This patch passes a pointer to the capability structure to the ->enable callback.

---
 arch/arm64/kernel/cpufeature.c |    4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)
arch/arm64/kernel/cpufeature.c +2 -2
@@ -1215,7 +1215,7 @@ void __init enable_cpu_capabilities(cons
 			 * uses an IPI, giving us a PSTATE that disappears when
 			 * we return.
 			 */
-			stop_machine(caps->enable, NULL, cpu_online_mask);
+			stop_machine(caps->enable, (void *)caps, cpu_online_mask);
 		}
 	}
 }
@@ -1259,7 +1259,7 @@ verify_local_cpu_features(const struct a
 			cpu_die_early();
 		}
 		if (caps->enable)
-			caps->enable(NULL);
+			caps->enable((void *)caps);
 	}
 }
 
author maintainer
#61 lore raw

PATCH 61/202 drivers/firmware: Expose psci_get_version through psci_ops structure

In reply to Greg Kroah-Hartman

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Will Deacon <[email protected]>

Commit d68e3ba5303f upstream.

Entry into recent versions of ARM Trusted Firmware will invalidate the CPU branch predictor state in order to protect against aliasing attacks.

This patch exposes the PSCI "VERSION" function via psci_ops, so that it can be invoked outside of the PSCI driver where necessary.

---
 drivers/firmware/psci.c |    2 ++
 include/linux/psci.h    |    1 +
 2 files changed, 3 insertions(+)
drivers/firmware/psci.c +2 -0
@@ -496,6 +496,8 @@ static void __init psci_init_migrate(voi
 static void __init psci_0_2_set_functions(void)
 {
 	pr_info("Using standard PSCI v0.2 function IDs\n");
+	psci_ops.get_version = psci_get_version;
+
 	psci_function_id[PSCI_FN_CPU_SUSPEND] =
 					PSCI_FN_NATIVE(0_2, CPU_SUSPEND);
 	psci_ops.cpu_suspend = psci_cpu_suspend;
include/linux/psci.h +1 -0
@@ -26,6 +26,7 @@ int psci_cpu_init_idle(unsigned int cpu)
 int psci_cpu_suspend_enter(unsigned long index);
 
 struct psci_operations {
+	u32 (*get_version)(void);
 	int (*cpu_suspend)(u32 state, unsigned long entry_point);
 	int (*cpu_off)(u32 state);
 	int (*cpu_on)(unsigned long cpuid, unsigned long entry_point);
author maintainer
#62 lore raw

PATCH 62/202 arm64: Move post_ttbr_update_workaround to C code

In reply to Greg Kroah-Hartman

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Marc Zyngier <[email protected]>

Commit 95e3de3590e3 upstream.

We will soon need to invoke a CPU-specific function pointer after changing page tables, so move post_ttbr_update_workaround out into C code to make this possible.

Conflicts:
arch/arm64/include/asm/assembler.h

---
 arch/arm64/include/asm/assembler.h |   13 -------------
 arch/arm64/kernel/entry.S          |    2 +-
 arch/arm64/mm/context.c            |    9 +++++++++
 arch/arm64/mm/proc.S               |    3 +--
 4 files changed, 11 insertions(+), 16 deletions(-)
arch/arm64/include/asm/assembler.h +0 -13
@@ -494,19 +494,6 @@ alternative_endif
 	mrs	\rd, sp_el0
 	.endm
 
-/*
- * Errata workaround post TTBRx_EL1 update.
- */
-	.macro	post_ttbr_update_workaround
-#ifdef CONFIG_CAVIUM_ERRATUM_27456
-alternative_if ARM64_WORKAROUND_CAVIUM_27456
-	ic	iallu
-	dsb	nsh
-	isb
-alternative_else_nop_endif
-#endif
-	.endm
-
 	.macro	pte_to_phys, phys, pte
 	and	\phys, \pte, #(((1 << (48 - PAGE_SHIFT)) - 1) << PAGE_SHIFT)
 	.endm
arch/arm64/kernel/entry.S +1 -1
@@ -277,7 +277,7 @@ alternative_else_nop_endif
 	 * Cavium erratum 27456 (broadcast TLBI instructions may cause I-cache
 	 * corruption).
 	 */
-	post_ttbr_update_workaround
+	bl	post_ttbr_update_workaround
 	.endif
 1:
 	.if	\el != 0
arch/arm64/mm/context.c +9 -0
@@ -239,6 +239,15 @@ switch_mm_fastpath:
 		cpu_switch_mm(mm->pgd, mm);
 }
 
+/* Errata workaround post TTBRx_EL1 update. */
+asmlinkage void post_ttbr_update_workaround(void)
+{
+	asm(ALTERNATIVE("nop; nop; nop",
+			"ic iallu; dsb nsh; isb",
+			ARM64_WORKAROUND_CAVIUM_27456,
+			CONFIG_CAVIUM_ERRATUM_27456));
+}
+
 static int asids_init(void)
 {
 	asid_bits = get_cpu_asid_bits();
arch/arm64/mm/proc.S +1 -2
@@ -148,8 +148,7 @@ ENTRY(cpu_do_switch_mm)
 	isb
 	msr	ttbr0_el1, x0			// now update TTBR0
 	isb
-	post_ttbr_update_workaround
-	ret
+	b	post_ttbr_update_workaround	// Back to C code...
 ENDPROC(cpu_do_switch_mm)
 
 	.pushsection ".idmap.text", "awx"
author maintainer
#63 lore raw

PATCH 63/202 arm64: Add skeleton to harden the branch predictor against aliasing attacks

In reply to Greg Kroah-Hartman

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Will Deacon <[email protected]>

Commit 0f15adbb2861 upstream.

Aliasing attacks against CPU branch predictors can allow an attacker to redirect speculative control flow on some CPUs and potentially divulge information from one context to another.

This patch adds initial skeleton code behind a new Kconfig option to enable implementation-specific mitigations against these attacks for CPUs that are affected.

Conflicts:
arch/arm64/kernel/cpufeature.c

---
 arch/arm64/Kconfig               |   17 ++++++++
 arch/arm64/include/asm/cpucaps.h |    3 +
 arch/arm64/include/asm/mmu.h     |   37 +++++++++++++++++++
 arch/arm64/include/asm/sysreg.h  |    1 
 arch/arm64/kernel/Makefile       |    4 ++
 arch/arm64/kernel/bpi.S          |   55 ++++++++++++++++++++++++++++
 arch/arm64/kernel/cpu_errata.c   |   74 +++++++++++++++++++++++++++++++++++++++
 arch/arm64/kernel/cpufeature.c   |    1 
 arch/arm64/kernel/entry.S        |    7 ++-
 arch/arm64/mm/context.c          |    2 +
 arch/arm64/mm/fault.c            |   17 ++++++++
 11 files changed, 215 insertions(+), 3 deletions(-)
 create mode 100644 arch/arm64/kernel/bpi.S
arch/arm64/Kconfig +17 -0
@@ -855,6 +855,23 @@ config UNMAP_KERNEL_AT_EL0
 
 	  If unsure, say Y.
 
+config HARDEN_BRANCH_PREDICTOR
+	bool "Harden the branch predictor against aliasing attacks" if EXPERT
+	default y
+	help
+	  Speculation attacks against some high-performance processors rely on
+	  being able to manipulate the branch predictor for a victim context by
+	  executing aliasing branches in the attacker context.  Such attacks
+	  can be partially mitigated against by clearing internal branch
+	  predictor state and limiting the prediction logic in some situations.
+
+	  This config option will take CPU-specific actions to harden the
+	  branch predictor against aliasing attacks and may rely on specific
+	  instruction sequences or control bits being set by the system
+	  firmware.
+
+	  If unsure, say Y.
+
 menuconfig ARMV8_DEPRECATED
 	bool "Emulate deprecated/obsolete ARMv8 instructions"
 	depends on COMPAT
arch/arm64/include/asm/cpucaps.h +2 -1
@@ -42,7 +42,8 @@
 #define ARM64_HAS_DCPOP				21
 #define ARM64_SVE				22
 #define ARM64_UNMAP_KERNEL_AT_EL0		23
+#define ARM64_HARDEN_BRANCH_PREDICTOR		24
 
-#define ARM64_NCAPS				24
+#define ARM64_NCAPS				25
 
 #endif /* __ASM_CPUCAPS_H */
arch/arm64/include/asm/mmu.h +37 -0
@@ -41,6 +41,43 @@ static inline bool arm64_kernel_unmapped
 	       cpus_have_const_cap(ARM64_UNMAP_KERNEL_AT_EL0);
 }
 
+typedef void (*bp_hardening_cb_t)(void);
+
+struct bp_hardening_data {
+	int			hyp_vectors_slot;
+	bp_hardening_cb_t	fn;
+};
+
+#ifdef CONFIG_HARDEN_BRANCH_PREDICTOR
+extern char __bp_harden_hyp_vecs_start[], __bp_harden_hyp_vecs_end[];
+
+DECLARE_PER_CPU_READ_MOSTLY(struct bp_hardening_data, bp_hardening_data);
+
+static inline struct bp_hardening_data *arm64_get_bp_hardening_data(void)
+{
+	return this_cpu_ptr(&bp_hardening_data);
+}
+
+static inline void arm64_apply_bp_hardening(void)
+{
+	struct bp_hardening_data *d;
+
+	if (!cpus_have_const_cap(ARM64_HARDEN_BRANCH_PREDICTOR))
+		return;
+
+	d = arm64_get_bp_hardening_data();
+	if (d->fn)
+		d->fn();
+}
+#else
+static inline struct bp_hardening_data *arm64_get_bp_hardening_data(void)
+{
+	return NULL;
+}
+
+static inline void arm64_apply_bp_hardening(void)	{ }
+#endif	/* CONFIG_HARDEN_BRANCH_PREDICTOR */
+
 extern void paging_init(void);
 extern void bootmem_init(void);
 extern void __iomem *early_io_map(phys_addr_t phys, unsigned long virt);
arch/arm64/include/asm/sysreg.h +1 -0
@@ -438,6 +438,7 @@
 
 /* id_aa64pfr0 */
 #define ID_AA64PFR0_CSV3_SHIFT		60
+#define ID_AA64PFR0_CSV2_SHIFT		56
 #define ID_AA64PFR0_SVE_SHIFT		32
 #define ID_AA64PFR0_GIC_SHIFT		24
 #define ID_AA64PFR0_ASIMD_SHIFT		20
arch/arm64/kernel/Makefile +4 -0
@@ -53,6 +53,10 @@ arm64-obj-$(CONFIG_ARM64_RELOC_TEST)	+=
 arm64-reloc-test-y := reloc_test_core.o reloc_test_syms.o
 arm64-obj-$(CONFIG_CRASH_DUMP)		+= crash_dump.o
 
+ifeq ($(CONFIG_KVM),y)
+arm64-obj-$(CONFIG_HARDEN_BRANCH_PREDICTOR)	+= bpi.o
+endif
+
 obj-y					+= $(arm64-obj-y) vdso/ probes/
 obj-m					+= $(arm64-obj-m)
 head-y					:= head.o
arch/arm64/kernel/bpi.S new file +55 -0

55 lines not on this page · raw message

arch/arm64/kernel/cpu_errata.c +74 -0

80 lines not on this page · raw message

arch/arm64/kernel/cpufeature.c +1 -0
@@ -146,6 +146,7 @@ static const struct arm64_ftr_bits ftr_i
 
 static const struct arm64_ftr_bits ftr_id_aa64pfr0[] = {
 	ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64PFR0_CSV3_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64PFR0_CSV2_SHIFT, 4, 0),
 	ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SVE),
 				   FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_SVE_SHIFT, 4, 0),
 	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_GIC_SHIFT, 4, 0),
arch/arm64/kernel/entry.S +5 -2
@@ -722,12 +722,15 @@ el0_ia:
 	 * Instruction abort handling
 	 */
 	mrs	x26, far_el1
-	enable_daif
+	enable_da_f
+#ifdef CONFIG_TRACE_IRQFLAGS
+	bl	trace_hardirqs_off
+#endif
 	ct_user_exit
 	mov	x0, x26
 	mov	x1, x25
 	mov	x2, sp
-	bl	do_mem_abort
+	bl	do_el0_ia_bp_hardening
 	b	ret_to_user
 el0_fpsimd_acc:
 	/*
arch/arm64/mm/context.c +2 -0
@@ -246,6 +246,8 @@ asmlinkage void post_ttbr_update_workaro
 			"ic iallu; dsb nsh; isb",
 			ARM64_WORKAROUND_CAVIUM_27456,
 			CONFIG_CAVIUM_ERRATUM_27456));
+
+	arm64_apply_bp_hardening();
 }
 
 static int asids_init(void)
arch/arm64/mm/fault.c +17 -0
@@ -707,6 +707,23 @@ asmlinkage void __exception do_mem_abort
 	arm64_notify_die("", regs, &info, esr);
 }
 
+asmlinkage void __exception do_el0_ia_bp_hardening(unsigned long addr,
+						   unsigned int esr,
+						   struct pt_regs *regs)
+{
+	/*
+	 * We've taken an instruction abort from userspace and not yet
+	 * re-enabled IRQs. If the address is a kernel address, apply
+	 * BP hardening prior to enabling IRQs and pre-emption.
+	 */
+	if (addr > TASK_SIZE)
+		arm64_apply_bp_hardening();
+
+	local_irq_enable();
+	do_mem_abort(addr, esr, regs);
+}
+
+
 asmlinkage void __exception do_sp_pc_abort(unsigned long addr,
 					   unsigned int esr,
 					   struct pt_regs *regs)
author maintainer
#64 lore raw

PATCH 64/202 arm64: Move BP hardening to check_and_switch_context

In reply to Greg Kroah-Hartman

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Marc Zyngier <[email protected]>

Commit a8e4c0a919ae upstream.

We call arm64_apply_bp_hardening() from post_ttbr_update_workaround, which has the unexpected consequence of being triggered on every exception return to userspace when ARM64_SW_TTBR0_PAN is selected, even if no context switch actually occured.

This is a bit suboptimal, and it would be more logical to only invalidate the branch predictor when we actually switch to a different mm.

In order to solve this, move the call to arm64_apply_bp_hardening() into check_and_switch_context(), where we're guaranteed to pick a different mm context.

---
 arch/arm64/mm/context.c |    5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)
arch/arm64/mm/context.c +3 -2
@@ -231,6 +231,9 @@ void check_and_switch_context(struct mm_
 	raw_spin_unlock_irqrestore(&cpu_asid_lock, flags);
 
 switch_mm_fastpath:
+
+	arm64_apply_bp_hardening();
+
 	/*
 	 * Defer TTBR0_EL1 setting for user threads to uaccess_enable() when
 	 * emulating PAN.
@@ -246,8 +249,6 @@ asmlinkage void post_ttbr_update_workaro
 			"ic iallu; dsb nsh; isb",
 			ARM64_WORKAROUND_CAVIUM_27456,
 			CONFIG_CAVIUM_ERRATUM_27456));
-
-	arm64_apply_bp_hardening();
 }
 
 static int asids_init(void)
author maintainer
#65 lore raw

PATCH 65/202 arm64: KVM: Use per-CPU vector when BP hardening is enabled

In reply to Greg Kroah-Hartman

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Marc Zyngier <[email protected]>

Commit 6840bdd73d07 upstream.

Now that we have per-CPU vectors, let's plug then in the KVM/arm64 code.

Conflicts:
arch/arm/include/asm/kvm_mmu.h
arch/arm64/include/asm/kvm_mmu.h

---
 arch/arm/include/asm/kvm_mmu.h   |   10 ++++++++++
 arch/arm64/include/asm/kvm_mmu.h |   38 ++++++++++++++++++++++++++++++++++++++
 arch/arm64/kvm/hyp/switch.c      |    2 +-
 virt/kvm/arm/arm.c               |    8 +++++++-
 4 files changed, 56 insertions(+), 2 deletions(-)
arch/arm/include/asm/kvm_mmu.h +10 -0
@@ -221,6 +221,16 @@ static inline unsigned int kvm_get_vmid_
 	return 8;
 }
 
+static inline void *kvm_get_hyp_vector(void)
+{
+	return kvm_ksym_ref(__kvm_hyp_vector);
+}
+
+static inline int kvm_map_vectors(void)
+{
+	return 0;
+}
+
 #endif	/* !__ASSEMBLY__ */
 
 #endif /* __ARM_KVM_MMU_H__ */
arch/arm64/include/asm/kvm_mmu.h +38 -0
@@ -309,5 +309,43 @@ static inline unsigned int kvm_get_vmid_
 	return (cpuid_feature_extract_unsigned_field(reg, ID_AA64MMFR1_VMIDBITS_SHIFT) == 2) ? 16 : 8;
 }
 
+#ifdef CONFIG_HARDEN_BRANCH_PREDICTOR
+#include <asm/mmu.h>
+
+static inline void *kvm_get_hyp_vector(void)
+{
+	struct bp_hardening_data *data = arm64_get_bp_hardening_data();
+	void *vect = kvm_ksym_ref(__kvm_hyp_vector);
+
+	if (data->fn) {
+		vect = __bp_harden_hyp_vecs_start +
+		       data->hyp_vectors_slot * SZ_2K;
+
+		if (!has_vhe())
+			vect = lm_alias(vect);
+	}
+
+	return vect;
+}
+
+static inline int kvm_map_vectors(void)
+{
+	return create_hyp_mappings(kvm_ksym_ref(__bp_harden_hyp_vecs_start),
+				   kvm_ksym_ref(__bp_harden_hyp_vecs_end),
+				   PAGE_HYP_EXEC);
+}
+
+#else
+static inline void *kvm_get_hyp_vector(void)
+{
+	return kvm_ksym_ref(__kvm_hyp_vector);
+}
+
+static inline int kvm_map_vectors(void)
+{
+	return 0;
+}
+#endif
+
 #endif /* __ASSEMBLY__ */
 #endif /* __ARM64_KVM_MMU_H__ */
arch/arm64/kvm/hyp/switch.c +1 -1
@@ -52,7 +52,7 @@ static void __hyp_text __activate_traps_
 	val &= ~(CPACR_EL1_FPEN | CPACR_EL1_ZEN);
 	write_sysreg(val, cpacr_el1);
 
-	write_sysreg(__kvm_hyp_vector, vbar_el1);
+	write_sysreg(kvm_get_hyp_vector(), vbar_el1);
 }
 
 static void __hyp_text __activate_traps_nvhe(void)
virt/kvm/arm/arm.c +7 -1
@@ -1158,7 +1158,7 @@ static void cpu_init_hyp_mode(void *dumm
 	pgd_ptr = kvm_mmu_get_httbr();
 	stack_page = __this_cpu_read(kvm_arm_hyp_stack_page);
 	hyp_stack_ptr = stack_page + PAGE_SIZE;
-	vector_ptr = (unsigned long)kvm_ksym_ref(__kvm_hyp_vector);
+	vector_ptr = (unsigned long)kvm_get_hyp_vector();
 
 	__cpu_init_hyp_mode(pgd_ptr, hyp_stack_ptr, vector_ptr);
 	__cpu_init_stage2();
@@ -1403,6 +1403,12 @@ static int init_hyp_mode(void)
 		goto out_err;
 	}
 
+	err = kvm_map_vectors();
+	if (err) {
+		kvm_err("Cannot map vectors\n");
+		goto out_err;
+	}
+
 	/*
 	 * Map the Hyp stack pages
 	 */
author maintainer
#66 lore raw

PATCH 66/202 arm64: entry: Apply BP hardening for high-priority synchronous exceptions

In reply to Greg Kroah-Hartman

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Will Deacon <[email protected]>

Commit 5dfc6ed27710 upstream.

Software-step and PC alignment fault exceptions have higher priority than instruction abort exceptions, so apply the BP hardening hooks there too if the user PC appears to reside in kernel space.

---
 arch/arm64/kernel/entry.S |    5 ++++-
 arch/arm64/mm/fault.c     |    9 +++++++++
 2 files changed, 13 insertions(+), 1 deletion(-)
arch/arm64/kernel/entry.S +4 -1
@@ -767,7 +767,10 @@ el0_sp_pc:
 	 * Stack or PC alignment exception handling
 	 */
 	mrs	x26, far_el1
-	enable_daif
+	enable_da_f
+#ifdef CONFIG_TRACE_IRQFLAGS
+	bl	trace_hardirqs_off
+#endif
 	ct_user_exit
 	mov	x0, x26
 	mov	x1, x25
arch/arm64/mm/fault.c +9 -0
@@ -731,6 +731,12 @@ asmlinkage void __exception do_sp_pc_abo
 	struct siginfo info;
 	struct task_struct *tsk = current;
 
+	if (user_mode(regs)) {
+		if (instruction_pointer(regs) > TASK_SIZE)
+			arm64_apply_bp_hardening();
+		local_irq_enable();
+	}
+
 	if (show_unhandled_signals && unhandled_signal(tsk, SIGBUS))
 		pr_info_ratelimited("%s[%d]: %s exception: pc=%p sp=%p\n",
 				    tsk->comm, task_pid_nr(tsk),
@@ -790,6 +796,9 @@ asmlinkage int __exception do_debug_exce
 	if (interrupts_enabled(regs))
 		trace_hardirqs_off();
 
+	if (user_mode(regs) && instruction_pointer(regs) > TASK_SIZE)
+		arm64_apply_bp_hardening();
+
 	if (!inf->fn(addr, esr, regs)) {
 		rv = 1;
 	} else {
author maintainer
#67 lore raw

PATCH 67/202 arm64: entry: Apply BP hardening for suspicious interrupts from EL0

In reply to Greg Kroah-Hartman

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Will Deacon <[email protected]>

Commit 30d88c0e3ace upstream.

It is possible to take an IRQ from EL0 following a branch to a kernel address in such a way that the IRQ is prioritised over the instruction abort. Whilst an attacker would need to get the stars to align here, it might be sufficient with enough calibration so perform BP hardening in the rare case that we see a kernel address in the ELR when handling an IRQ from EL0.

---
 arch/arm64/kernel/entry.S |    5 +++++
 arch/arm64/mm/fault.c     |    6 ++++++
 2 files changed, 11 insertions(+)
arch/arm64/kernel/entry.S +5 -0
@@ -828,6 +828,11 @@ el0_irq_naked:
 #endif
 
 	ct_user_exit
+#ifdef CONFIG_HARDEN_BRANCH_PREDICTOR
+	tbz	x22, #55, 1f
+	bl	do_el0_irq_bp_hardening
+1:
+#endif
 	irq_handler
 
 #ifdef CONFIG_TRACE_IRQFLAGS
arch/arm64/mm/fault.c +6 -0
@@ -707,6 +707,12 @@ asmlinkage void __exception do_mem_abort
 	arm64_notify_die("", regs, &info, esr);
 }
 
+asmlinkage void __exception do_el0_irq_bp_hardening(void)
+{
+	/* PC has already been checked in entry.S */
+	arm64_apply_bp_hardening();
+}
+
 asmlinkage void __exception do_el0_ia_bp_hardening(unsigned long addr,
 						   unsigned int esr,
 						   struct pt_regs *regs)
author maintainer
#68 lore raw

PATCH 68/202 arm64: cputype: Add missing MIDR values for Cortex-A72 and Cortex-A75

In reply to Greg Kroah-Hartman

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Will Deacon <[email protected]>

Commit a65d219fe5dc upstream.

Hook up MIDR values for the Cortex-A72 and Cortex-A75 CPUs, since they will soon need MIDR matches for hardening the branch predictor.

---
 arch/arm64/include/asm/cputype.h |    4 ++++
 1 file changed, 4 insertions(+)
arch/arm64/include/asm/cputype.h +4 -0
@@ -79,8 +79,10 @@
 #define ARM_CPU_PART_AEM_V8		0xD0F
 #define ARM_CPU_PART_FOUNDATION		0xD00
 #define ARM_CPU_PART_CORTEX_A57		0xD07
+#define ARM_CPU_PART_CORTEX_A72		0xD08
 #define ARM_CPU_PART_CORTEX_A53		0xD03
 #define ARM_CPU_PART_CORTEX_A73		0xD09
+#define ARM_CPU_PART_CORTEX_A75		0xD0A
 
 #define APM_CPU_PART_POTENZA		0x000
 
@@ -97,7 +99,9 @@
 
 #define MIDR_CORTEX_A53 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A53)
 #define MIDR_CORTEX_A57 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A57)
+#define MIDR_CORTEX_A72 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A72)
 #define MIDR_CORTEX_A73 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A73)
+#define MIDR_CORTEX_A75 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A75)
 #define MIDR_THUNDERX	MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX)
 #define MIDR_THUNDERX_81XX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX_81XX)
 #define MIDR_THUNDERX_83XX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX_83XX)
author maintainer
#69 lore raw

PATCH 69/202 arm64: Implement branch predictor hardening for affected Cortex-A CPUs

In reply to Greg Kroah-Hartman

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Will Deacon <[email protected]>

Commit aa6acde65e03 upstream.

Cortex-A57, A72, A73 and A75 are susceptible to branch predictor aliasing and can theoretically be attacked by malicious code.

This patch implements a PSCI-based mitigation for these CPUs when available. The call into firmware will invalidate the branch predictor state, preventing any malicious entries from affecting other victim contexts.

---
 arch/arm64/kernel/bpi.S        |   24 +++++++++++++++++++++++
 arch/arm64/kernel/cpu_errata.c |   42 +++++++++++++++++++++++++++++++++++++++++
 2 files changed, 66 insertions(+)
arch/arm64/kernel/bpi.S +24 -0
@@ -53,3 +53,27 @@ ENTRY(__bp_harden_hyp_vecs_start)
 	vectors __kvm_hyp_vector
 	.endr
 ENTRY(__bp_harden_hyp_vecs_end)
+ENTRY(__psci_hyp_bp_inval_start)
+	sub	sp, sp, #(8 * 18)
+	stp	x16, x17, [sp, #(16 * 0)]
+	stp	x14, x15, [sp, #(16 * 1)]
+	stp	x12, x13, [sp, #(16 * 2)]
+	stp	x10, x11, [sp, #(16 * 3)]
+	stp	x8, x9, [sp, #(16 * 4)]
+	stp	x6, x7, [sp, #(16 * 5)]
+	stp	x4, x5, [sp, #(16 * 6)]
+	stp	x2, x3, [sp, #(16 * 7)]
+	stp	x0, x1, [sp, #(16 * 8)]
+	mov	x0, #0x84000000
+	smc	#0
+	ldp	x16, x17, [sp, #(16 * 0)]
+	ldp	x14, x15, [sp, #(16 * 1)]
+	ldp	x12, x13, [sp, #(16 * 2)]
+	ldp	x10, x11, [sp, #(16 * 3)]
+	ldp	x8, x9, [sp, #(16 * 4)]
+	ldp	x6, x7, [sp, #(16 * 5)]
+	ldp	x4, x5, [sp, #(16 * 6)]
+	ldp	x2, x3, [sp, #(16 * 7)]
+	ldp	x0, x1, [sp, #(16 * 8)]
+	add	sp, sp, #(8 * 18)
+ENTRY(__psci_hyp_bp_inval_end)
arch/arm64/kernel/cpu_errata.c +42 -0

66 lines not on this page · raw message

author maintainer
#70 lore raw

PATCH 70/202 arm64: Implement branch predictor hardening for Falkor

In reply to Greg Kroah-Hartman

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Shanker Donthineni <[email protected]>

Commit ec82b567a74f upstream.

Falkor is susceptible to branch predictor aliasing and can theoretically be attacked by malicious code. This patch implements a mitigation for these attacks, preventing any malicious entries from affecting other victim contexts.

[will: fix label name when !CONFIG_KVM and remove references to MIDR_FALKOR]
---
 arch/arm64/include/asm/cpucaps.h |    3 +-
 arch/arm64/include/asm/kvm_asm.h |    2 +
 arch/arm64/kernel/bpi.S          |    8 +++++++
 arch/arm64/kernel/cpu_errata.c   |   40 +++++++++++++++++++++++++++++++++++++--
 arch/arm64/kvm/hyp/entry.S       |   12 +++++++++++
 arch/arm64/kvm/hyp/switch.c      |    8 +++++++
 6 files changed, 70 insertions(+), 3 deletions(-)
arch/arm64/include/asm/cpucaps.h +2 -1
@@ -43,7 +43,8 @@
 #define ARM64_SVE				22
 #define ARM64_UNMAP_KERNEL_AT_EL0		23
 #define ARM64_HARDEN_BRANCH_PREDICTOR		24
+#define ARM64_HARDEN_BP_POST_GUEST_EXIT		25
 
-#define ARM64_NCAPS				25
+#define ARM64_NCAPS				26
 
 #endif /* __ASM_CPUCAPS_H */
arch/arm64/include/asm/kvm_asm.h +2 -0
@@ -68,6 +68,8 @@ extern u32 __kvm_get_mdcr_el2(void);
 
 extern u32 __init_stage2_translation(void);
 
+extern void __qcom_hyp_sanitize_btac_predictors(void);
+
 #endif
 
 #endif /* __ARM_KVM_ASM_H__ */
arch/arm64/kernel/bpi.S +8 -0
@@ -77,3 +77,11 @@ ENTRY(__psci_hyp_bp_inval_start)
 	ldp	x0, x1, [sp, #(16 * 8)]
 	add	sp, sp, #(8 * 18)
 ENTRY(__psci_hyp_bp_inval_end)
+
+ENTRY(__qcom_hyp_sanitize_link_stack_start)
+	stp     x29, x30, [sp, #-16]!
+	.rept	16
+	bl	. + 4
+	.endr
+	ldp	x29, x30, [sp], #16
+ENTRY(__qcom_hyp_sanitize_link_stack_end)
arch/arm64/kernel/cpu_errata.c +38 -2
@@ -68,6 +68,8 @@ DEFINE_PER_CPU_READ_MOSTLY(struct bp_har
 
 #ifdef CONFIG_KVM
 extern char __psci_hyp_bp_inval_start[], __psci_hyp_bp_inval_end[];
+extern char __qcom_hyp_sanitize_link_stack_start[];
+extern char __qcom_hyp_sanitize_link_stack_end[];
 
 static void __copy_hyp_vect_bpi(int slot, const char *hyp_vecs_start,
 				const char *hyp_vecs_end)
@@ -110,8 +112,10 @@ static void __install_bp_hardening_cb(bp
 	spin_unlock(&bp_lock);
 }
 #else
-#define __psci_hyp_bp_inval_start	NULL
-#define __psci_hyp_bp_inval_end		NULL
+#define __psci_hyp_bp_inval_start		NULL
+#define __psci_hyp_bp_inval_end			NULL
+#define __qcom_hyp_sanitize_link_stack_start	NULL
+#define __qcom_hyp_sanitize_link_stack_end	NULL
 
 static void __install_bp_hardening_cb(bp_hardening_cb_t fn,
 				      const char *hyp_vecs_start,
@@ -152,6 +156,29 @@ static int enable_psci_bp_hardening(void
 
 	return 0;
 }
+
+static void qcom_link_stack_sanitization(void)
+{
+	u64 tmp;
+
+	asm volatile("mov	%0, x30		\n"
+		     ".rept	16		\n"
+		     "bl	. + 4		\n"
+		     ".endr			\n"
+		     "mov	x30, %0		\n"
+		     : "=&r" (tmp));
+}
+
+static int qcom_enable_link_stack_sanitization(void *data)
+{
+	const struct arm64_cpu_capabilities *entry = data;
+
+	install_bp_hardening_cb(entry, qcom_link_stack_sanitization,
+				__qcom_hyp_sanitize_link_stack_start,
+				__qcom_hyp_sanitize_link_stack_end);
+
+	return 0;
+}
 #endif	/* CONFIG_HARDEN_BRANCH_PREDICTOR */
 
 #define MIDR_RANGE(model, min, max) \
@@ -323,6 +350,15 @@ const struct arm64_cpu_capabilities arm6
 		MIDR_ALL_VERSIONS(MIDR_CORTEX_A75),
 		.enable = enable_psci_bp_hardening,
 	},
+	{
+		.capability = ARM64_HARDEN_BRANCH_PREDICTOR,
+		MIDR_ALL_VERSIONS(MIDR_QCOM_FALKOR_V1),
+		.enable = qcom_enable_link_stack_sanitization,
+	},
+	{
+		.capability = ARM64_HARDEN_BP_POST_GUEST_EXIT,
+		MIDR_ALL_VERSIONS(MIDR_QCOM_FALKOR_V1),
+	},
 #endif
 	{
 	}
arch/arm64/kvm/hyp/entry.S +12 -0
@@ -196,3 +196,15 @@ alternative_endif
 
 	eret
 ENDPROC(__fpsimd_guest_restore)
+
+ENTRY(__qcom_hyp_sanitize_btac_predictors)
+	/**
+	 * Call SMC64 with Silicon provider serviceID 23<<8 (0xc2001700)
+	 * 0xC2000000-0xC200FFFF: assigned to SiP Service Calls
+	 * b15-b0: contains SiP functionID
+	 */
+	movz    x0, #0x1700
+	movk    x0, #0xc200, lsl #16
+	smc     #0
+	ret
+ENDPROC(__qcom_hyp_sanitize_btac_predictors)
arch/arm64/kvm/hyp/switch.c +8 -0
@@ -393,6 +393,14 @@ again:
 		/* 0 falls through to be handled out of EL2 */
 	}
 
+	if (cpus_have_const_cap(ARM64_HARDEN_BP_POST_GUEST_EXIT)) {
+		u32 midr = read_cpuid_id();
+
+		/* Apply BTAC predictors mitigation to all Falkor chips */
+		if ((midr & MIDR_CPU_MODEL_MASK) == MIDR_QCOM_FALKOR_V1)
+			__qcom_hyp_sanitize_btac_predictors();
+	}
+
 	fp_enabled = __fpsimd_enabled();
 
 	__sysreg_save_guest_state(guest_ctxt);
author maintainer
#71 lore raw

PATCH 71/202 arm64: Branch predictor hardening for Cavium ThunderX2

In reply to Greg Kroah-Hartman

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Jayachandran C <[email protected]>

Commit f3d795d9b360 upstream.

Use PSCI based mitigation for speculative execution attacks targeting the branch predictor. We use the same mechanism as the one used for Cortex-A CPUs, we expect the PSCI version call to have a side effect of clearing the BTBs.

---
 arch/arm64/kernel/cpu_errata.c |   10 ++++++++++
 1 file changed, 10 insertions(+)
arch/arm64/kernel/cpu_errata.c +10 -0
@@ -359,6 +359,16 @@ const struct arm64_cpu_capabilities arm6
 		.capability = ARM64_HARDEN_BP_POST_GUEST_EXIT,
 		MIDR_ALL_VERSIONS(MIDR_QCOM_FALKOR_V1),
 	},
+	{
+		.capability = ARM64_HARDEN_BRANCH_PREDICTOR,
+		MIDR_ALL_VERSIONS(MIDR_BRCM_VULCAN),
+		.enable = enable_psci_bp_hardening,
+	},
+	{
+		.capability = ARM64_HARDEN_BRANCH_PREDICTOR,
+		MIDR_ALL_VERSIONS(MIDR_CAVIUM_THUNDERX2),
+		.enable = enable_psci_bp_hardening,
+	},
 #endif
 	{
 	}
author maintainer
#72 lore raw

PATCH 72/202 arm64: KVM: Increment PC after handling an SMC trap

In reply to Greg Kroah-Hartman

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Marc Zyngier <[email protected]>

Commit f5115e8869e1 upstream.

When handling an SMC trap, the "preferred return address" is set to that of the SMC, and not the next PC (which is a departure from the behaviour of an SMC that isn't trapped).

Increment PC in the handler, as the guest is otherwise forever stuck...

Fixes acfb3b883f6d ("arm64: KVM: Fix SMCCC handling of unimplemented SMC/HVC calls")
---
 arch/arm64/kvm/handle_exit.c |    9 +++++++++
 1 file changed, 9 insertions(+)
arch/arm64/kvm/handle_exit.c +9 -0
@@ -54,7 +54,16 @@ static int handle_hvc(struct kvm_vcpu *v
 
 static int handle_smc(struct kvm_vcpu *vcpu, struct kvm_run *run)
 {
+	/*
+	 * "If an SMC instruction executed at Non-secure EL1 is
+	 * trapped to EL2 because HCR_EL2.TSC is 1, the exception is a
+	 * Trap exception, not a Secure Monitor Call exception [...]"
+	 *
+	 * We need to advance the PC after the trap, as it would
+	 * otherwise return to the same address...
+	 */
 	vcpu_set_reg(vcpu, 0, ~0UL);
+	kvm_skip_instr(vcpu, kvm_vcpu_trap_il_is32bit(vcpu));
 	return 1;
 }
 
author maintainer
#73 lore raw

PATCH 73/202 arm/arm64: KVM: Consolidate the PSCI include files

In reply to Greg Kroah-Hartman

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Marc Zyngier <[email protected]>

Commit 1a2fb94e6a77 upstream.

As we're about to update the PSCI support, and because I'm lazy, let's move the PSCI include file to include/kvm so that both ARM architectures can find it.

---
 arch/arm/include/asm/kvm_psci.h   |   27 ---------------------------
 arch/arm/kvm/handle_exit.c        |    2 +-
 arch/arm64/include/asm/kvm_psci.h |   27 ---------------------------
 arch/arm64/kvm/handle_exit.c      |    3 ++-
 include/kvm/arm_psci.h            |   27 +++++++++++++++++++++++++++
 virt/kvm/arm/arm.c                |    2 +-
 virt/kvm/arm/psci.c               |    3 ++-
 7 files changed, 33 insertions(+), 58 deletions(-)
 delete mode 100644 arch/arm/include/asm/kvm_psci.h
 rename arch/arm64/include/asm/kvm_psci.h => include/kvm/arm_psci.h (89%)
arch/arm/include/asm/kvm_psci.h deleted +0 -27
@@ -1,27 +0,0 @@
-/*
- * Copyright (C) 2012 - ARM Ltd
- * Author: Marc Zyngier <[email protected]>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program.  If not, see <http://www.gnu.org/licenses/>.
- */
-
-#ifndef __ARM_KVM_PSCI_H__
-#define __ARM_KVM_PSCI_H__
-
-#define KVM_ARM_PSCI_0_1	1
-#define KVM_ARM_PSCI_0_2	2
-
-int kvm_psci_version(struct kvm_vcpu *vcpu);
-int kvm_psci_call(struct kvm_vcpu *vcpu);
-
-#endif /* __ARM_KVM_PSCI_H__ */
arch/arm/kvm/handle_exit.c +1 -1
@@ -21,7 +21,7 @@
 #include <asm/kvm_emulate.h>
 #include <asm/kvm_coproc.h>
 #include <asm/kvm_mmu.h>
-#include <asm/kvm_psci.h>
+#include <kvm/arm_psci.h>
 #include <trace/events/kvm.h>
 
 #include "trace.h"
arch/arm64/include/asm/kvm_psci.h deleted +0 -27
@@ -1,27 +0,0 @@
-/*
- * Copyright (C) 2012,2013 - ARM Ltd
- * Author: Marc Zyngier <[email protected]>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program.  If not, see <http://www.gnu.org/licenses/>.
- */
-
-#ifndef __ARM64_KVM_PSCI_H__
-#define __ARM64_KVM_PSCI_H__
-
-#define KVM_ARM_PSCI_0_1	1
-#define KVM_ARM_PSCI_0_2	2
-
-int kvm_psci_version(struct kvm_vcpu *vcpu);
-int kvm_psci_call(struct kvm_vcpu *vcpu);
-
-#endif /* __ARM64_KVM_PSCI_H__ */
arch/arm64/kvm/handle_exit.c +2 -1
@@ -22,12 +22,13 @@
 #include <linux/kvm.h>
 #include <linux/kvm_host.h>
 
+#include <kvm/arm_psci.h>
+
 #include <asm/esr.h>
 #include <asm/kvm_asm.h>
 #include <asm/kvm_coproc.h>
 #include <asm/kvm_emulate.h>
 #include <asm/kvm_mmu.h>
-#include <asm/kvm_psci.h>
 #include <asm/debug-monitors.h>
 
 #define CREATE_TRACE_POINTS
include/kvm/arm_psci.h new file +27 -0
@@ -0,0 +1,27 @@
+/*
+ * Copyright (C) 2012,2013 - ARM Ltd
+ * Author: Marc Zyngier <[email protected]>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifndef __KVM_ARM_PSCI_H__
+#define __KVM_ARM_PSCI_H__
+
+#define KVM_ARM_PSCI_0_1	1
+#define KVM_ARM_PSCI_0_2	2
+
+int kvm_psci_version(struct kvm_vcpu *vcpu);
+int kvm_psci_call(struct kvm_vcpu *vcpu);
+
+#endif /* __KVM_ARM_PSCI_H__ */
virt/kvm/arm/arm.c +1 -1
@@ -31,6 +31,7 @@
 #include <linux/irqbypass.h>
 #include <trace/events/kvm.h>
 #include <kvm/arm_pmu.h>
+#include <kvm/arm_psci.h>
 
 #define CREATE_TRACE_POINTS
 #include "trace.h"
@@ -46,7 +47,6 @@
 #include <asm/kvm_mmu.h>
 #include <asm/kvm_emulate.h>
 #include <asm/kvm_coproc.h>
-#include <asm/kvm_psci.h>
 #include <asm/sections.h>
 
 #ifdef REQUIRES_VIRT
virt/kvm/arm/psci.c +2 -1
@@ -21,9 +21,10 @@
 
 #include <asm/cputype.h>
 #include <asm/kvm_emulate.h>
-#include <asm/kvm_psci.h>
 #include <asm/kvm_host.h>
 
+#include <kvm/arm_psci.h>
+
 #include <uapi/linux/psci.h>
 
 /*
author maintainer
#74 lore raw

PATCH 74/202 arm/arm64: KVM: Add PSCI_VERSION helper

In reply to Greg Kroah-Hartman

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Marc Zyngier <[email protected]>

Commit d0a144f12a7c upstream.

As we're about to trigger a PSCI version explosion, it doesn't hurt to introduce a PSCI_VERSION helper that is going to be used everywhere.

---
 include/kvm/arm_psci.h    |    6 ++++--
 include/uapi/linux/psci.h |    3 +++
 virt/kvm/arm/psci.c       |    4 +---
 3 files changed, 8 insertions(+), 5 deletions(-)
include/kvm/arm_psci.h +4 -2
@@ -18,8 +18,10 @@
 #ifndef __KVM_ARM_PSCI_H__
 #define __KVM_ARM_PSCI_H__
 
-#define KVM_ARM_PSCI_0_1	1
-#define KVM_ARM_PSCI_0_2	2
+#include <uapi/linux/psci.h>
+
+#define KVM_ARM_PSCI_0_1	PSCI_VERSION(0, 1)
+#define KVM_ARM_PSCI_0_2	PSCI_VERSION(0, 2)
 
 int kvm_psci_version(struct kvm_vcpu *vcpu);
 int kvm_psci_call(struct kvm_vcpu *vcpu);
include/uapi/linux/psci.h +3 -0
@@ -88,6 +88,9 @@
 		(((ver) & PSCI_VERSION_MAJOR_MASK) >> PSCI_VERSION_MAJOR_SHIFT)
 #define PSCI_VERSION_MINOR(ver)			\
 		((ver) & PSCI_VERSION_MINOR_MASK)
+#define PSCI_VERSION(maj, min)						\
+	((((maj) << PSCI_VERSION_MAJOR_SHIFT) & PSCI_VERSION_MAJOR_MASK) | \
+	 ((min) & PSCI_VERSION_MINOR_MASK))
 
 /* PSCI features decoding (>=1.0) */
 #define PSCI_1_0_FEATURES_CPU_SUSPEND_PF_SHIFT	1
virt/kvm/arm/psci.c +1 -3
@@ -25,8 +25,6 @@
 
 #include <kvm/arm_psci.h>
 
-#include <uapi/linux/psci.h>
-
 /*
  * This is an implementation of the Power State Coordination Interface
  * as described in ARM document number ARM DEN 0022A.
@@ -222,7 +220,7 @@ static int kvm_psci_0_2_call(struct kvm_
 		 * Bits[31:16] = Major Version = 0
 		 * Bits[15:0] = Minor Version = 2
 		 */
-		val = 2;
+		val = KVM_ARM_PSCI_0_2;
 		break;
 	case PSCI_0_2_FN_CPU_SUSPEND:
 	case PSCI_0_2_FN64_CPU_SUSPEND:
author maintainer
#75 lore raw

PATCH 75/202 arm/arm64: KVM: Add smccc accessors to PSCI code

In reply to Greg Kroah-Hartman

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Marc Zyngier <[email protected]>

Commit 84684fecd7ea upstream.

Instead of open coding the accesses to the various registers, let's add explicit SMCCC accessors.

---
 virt/kvm/arm/psci.c |   52 ++++++++++++++++++++++++++++++++++++++++++----------
 1 file changed, 42 insertions(+), 10 deletions(-)
virt/kvm/arm/psci.c +42 -10
@@ -32,6 +32,38 @@
 
 #define AFFINITY_MASK(level)	~((0x1UL << ((level) * MPIDR_LEVEL_BITS)) - 1)
 
+static u32 smccc_get_function(struct kvm_vcpu *vcpu)
+{
+	return vcpu_get_reg(vcpu, 0);
+}
+
+static unsigned long smccc_get_arg1(struct kvm_vcpu *vcpu)
+{
+	return vcpu_get_reg(vcpu, 1);
+}
+
+static unsigned long smccc_get_arg2(struct kvm_vcpu *vcpu)
+{
+	return vcpu_get_reg(vcpu, 2);
+}
+
+static unsigned long smccc_get_arg3(struct kvm_vcpu *vcpu)
+{
+	return vcpu_get_reg(vcpu, 3);
+}
+
+static void smccc_set_retval(struct kvm_vcpu *vcpu,
+			     unsigned long a0,
+			     unsigned long a1,
+			     unsigned long a2,
+			     unsigned long a3)
+{
+	vcpu_set_reg(vcpu, 0, a0);
+	vcpu_set_reg(vcpu, 1, a1);
+	vcpu_set_reg(vcpu, 2, a2);
+	vcpu_set_reg(vcpu, 3, a3);
+}
+
 static unsigned long psci_affinity_mask(unsigned long affinity_level)
 {
 	if (affinity_level <= 3)
@@ -77,7 +109,7 @@ static unsigned long kvm_psci_vcpu_on(st
 	unsigned long context_id;
 	phys_addr_t target_pc;
 
-	cpu_id = vcpu_get_reg(source_vcpu, 1) & MPIDR_HWID_BITMASK;
+	cpu_id = smccc_get_arg1(source_vcpu) & MPIDR_HWID_BITMASK;
 	if (vcpu_mode_is_32bit(source_vcpu))
 		cpu_id &= ~((u32) 0);
 
@@ -96,8 +128,8 @@ static unsigned long kvm_psci_vcpu_on(st
 			return PSCI_RET_INVALID_PARAMS;
 	}
 
-	target_pc = vcpu_get_reg(source_vcpu, 2);
-	context_id = vcpu_get_reg(source_vcpu, 3);
+	target_pc = smccc_get_arg2(source_vcpu);
+	context_id = smccc_get_arg3(source_vcpu);
 
 	kvm_reset_vcpu(vcpu);
 
@@ -116,7 +148,7 @@ static unsigned long kvm_psci_vcpu_on(st
 	 * NOTE: We always update r0 (or x0) because for PSCI v0.1
 	 * the general puspose registers are undefined upon CPU_ON.
 	 */
-	vcpu_set_reg(vcpu, 0, context_id);
+	smccc_set_retval(vcpu, context_id, 0, 0, 0);
 	vcpu->arch.power_off = false;
 	smp_mb();		/* Make sure the above is visible */
 
@@ -136,8 +168,8 @@ static unsigned long kvm_psci_vcpu_affin
 	struct kvm *kvm = vcpu->kvm;
 	struct kvm_vcpu *tmp;
 
-	target_affinity = vcpu_get_reg(vcpu, 1);
-	lowest_affinity_level = vcpu_get_reg(vcpu, 2);
+	target_affinity = smccc_get_arg1(vcpu);
+	lowest_affinity_level = smccc_get_arg2(vcpu);
 
 	/* Determine target affinity mask */
 	target_affinity_mask = psci_affinity_mask(lowest_affinity_level);
@@ -210,7 +242,7 @@ int kvm_psci_version(struct kvm_vcpu *vc
 static int kvm_psci_0_2_call(struct kvm_vcpu *vcpu)
 {
 	struct kvm *kvm = vcpu->kvm;
-	unsigned long psci_fn = vcpu_get_reg(vcpu, 0) & ~((u32) 0);
+	u32 psci_fn = smccc_get_function(vcpu);
 	unsigned long val;
 	int ret = 1;
 
@@ -277,14 +309,14 @@ static int kvm_psci_0_2_call(struct kvm_
 		break;
 	}
 
-	vcpu_set_reg(vcpu, 0, val);
+	smccc_set_retval(vcpu, val, 0, 0, 0);
 	return ret;
 }
 
 static int kvm_psci_0_1_call(struct kvm_vcpu *vcpu)
 {
 	struct kvm *kvm = vcpu->kvm;
-	unsigned long psci_fn = vcpu_get_reg(vcpu, 0) & ~((u32) 0);
+	u32 psci_fn = smccc_get_function(vcpu);
 	unsigned long val;
 
 	switch (psci_fn) {
@@ -302,7 +334,7 @@ static int kvm_psci_0_1_call(struct kvm_
 		break;
 	}
 
-	vcpu_set_reg(vcpu, 0, val);
+	smccc_set_retval(vcpu, val, 0, 0, 0);
 	return 1;
 }
 
author maintainer
#76 lore raw

PATCH 76/202 arm/arm64: KVM: Implement PSCI 1.0 support

In reply to Greg Kroah-Hartman

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Marc Zyngier <[email protected]>

Commit 58e0b2239a4d upstream.

PSCI 1.0 can be trivially implemented by providing the FEATURES call on top of PSCI 0.2 and returning 1.0 as the PSCI version.

We happily ignore everything else, as they are either optional or are clarifications that do not require any additional change.

PSCI 1.0 is now the default until we decide to add a userspace selection API.

---
 include/kvm/arm_psci.h |    3 +++
 virt/kvm/arm/psci.c    |   45 ++++++++++++++++++++++++++++++++++++++++++++-
 2 files changed, 47 insertions(+), 1 deletion(-)
include/kvm/arm_psci.h +3 -0
@@ -22,6 +22,9 @@
 
 #define KVM_ARM_PSCI_0_1	PSCI_VERSION(0, 1)
 #define KVM_ARM_PSCI_0_2	PSCI_VERSION(0, 2)
+#define KVM_ARM_PSCI_1_0	PSCI_VERSION(1, 0)
+
+#define KVM_ARM_PSCI_LATEST	KVM_ARM_PSCI_1_0
 
 int kvm_psci_version(struct kvm_vcpu *vcpu);
 int kvm_psci_call(struct kvm_vcpu *vcpu);
virt/kvm/arm/psci.c +44 -1

63 lines not on this page · raw message

author maintainer
#77 lore raw

PATCH 77/202 arm/arm64: KVM: Advertise SMCCC v1.1

In reply to Greg Kroah-Hartman

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Marc Zyngier <[email protected]>

Commit 09e6be12effd upstream.

The new SMC Calling Convention (v1.1) allows for a reduced overhead when calling into the firmware, and provides a new feature discovery mechanism.

Make it visible to KVM guests.

---
 arch/arm/kvm/handle_exit.c   |    2 +-
 arch/arm64/kvm/handle_exit.c |    2 +-
 include/kvm/arm_psci.h       |    2 +-
 include/linux/arm-smccc.h    |   13 +++++++++++++
 virt/kvm/arm/psci.c          |   24 +++++++++++++++++++++++-
 5 files changed, 39 insertions(+), 4 deletions(-)
arch/arm/kvm/handle_exit.c +1 -1
@@ -36,7 +36,7 @@ static int handle_hvc(struct kvm_vcpu *v
 		      kvm_vcpu_hvc_get_imm(vcpu));
 	vcpu->stat.hvc_exit_stat++;
 
-	ret = kvm_psci_call(vcpu);
+	ret = kvm_hvc_call_handler(vcpu);
 	if (ret < 0) {
 		kvm_inject_undefined(vcpu);
 		return 1;
arch/arm64/kvm/handle_exit.c +1 -1
@@ -44,7 +44,7 @@ static int handle_hvc(struct kvm_vcpu *v
 			    kvm_vcpu_hvc_get_imm(vcpu));
 	vcpu->stat.hvc_exit_stat++;
 
-	ret = kvm_psci_call(vcpu);
+	ret = kvm_hvc_call_handler(vcpu);
 	if (ret < 0) {
 		vcpu_set_reg(vcpu, 0, ~0UL);
 		return 1;
include/kvm/arm_psci.h +1 -1
@@ -27,6 +27,6 @@
 #define KVM_ARM_PSCI_LATEST	KVM_ARM_PSCI_1_0
 
 int kvm_psci_version(struct kvm_vcpu *vcpu);
-int kvm_psci_call(struct kvm_vcpu *vcpu);
+int kvm_hvc_call_handler(struct kvm_vcpu *vcpu);
 
 #endif /* __KVM_ARM_PSCI_H__ */
include/linux/arm-smccc.h +13 -0
@@ -60,6 +60,19 @@
 #define ARM_SMCCC_QUIRK_NONE		0
 #define ARM_SMCCC_QUIRK_QCOM_A6		1 /* Save/restore register a6 */
 
+#define ARM_SMCCC_VERSION_1_0		0x10000
+#define ARM_SMCCC_VERSION_1_1		0x10001
+
+#define ARM_SMCCC_VERSION_FUNC_ID					\
+	ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL,				\
+			   ARM_SMCCC_SMC_32,				\
+			   0, 0)
+
+#define ARM_SMCCC_ARCH_FEATURES_FUNC_ID					\
+	ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL,				\
+			   ARM_SMCCC_SMC_32,				\
+			   0, 1)
+
 #ifndef __ASSEMBLY__
 
 #include <linux/linkage.h>
virt/kvm/arm/psci.c +23 -1
@@ -15,6 +15,7 @@
  * along with this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
+#include <linux/arm-smccc.h>
 #include <linux/preempt.h>
 #include <linux/kvm_host.h>
 #include <linux/wait.h>
@@ -339,6 +340,7 @@ static int kvm_psci_1_0_call(struct kvm_
 		case PSCI_0_2_FN_SYSTEM_OFF:
 		case PSCI_0_2_FN_SYSTEM_RESET:
 		case PSCI_1_0_FN_PSCI_FEATURES:
+		case ARM_SMCCC_VERSION_FUNC_ID:
 			val = 0;
 			break;
 		default:
@@ -393,7 +395,7 @@ static int kvm_psci_0_1_call(struct kvm_
  * Errors:
  * -EINVAL: Unrecognized PSCI function
  */
-int kvm_psci_call(struct kvm_vcpu *vcpu)
+static int kvm_psci_call(struct kvm_vcpu *vcpu)
 {
 	switch (kvm_psci_version(vcpu)) {
 	case KVM_ARM_PSCI_1_0:
@@ -406,3 +408,23 @@ int kvm_psci_call(struct kvm_vcpu *vcpu)
 		return -EINVAL;
 	};
 }
+
+int kvm_hvc_call_handler(struct kvm_vcpu *vcpu)
+{
+	u32 func_id = smccc_get_function(vcpu);
+	u32 val = PSCI_RET_NOT_SUPPORTED;
+
+	switch (func_id) {
+	case ARM_SMCCC_VERSION_FUNC_ID:
+		val = ARM_SMCCC_VERSION_1_1;
+		break;
+	case ARM_SMCCC_ARCH_FEATURES_FUNC_ID:
+		/* Nothing supported yet */
+		break;
+	default:
+		return kvm_psci_call(vcpu);
+	}
+
+	smccc_set_retval(vcpu, val, 0, 0, 0);
+	return 1;
+}
author maintainer
#78 lore raw

PATCH 78/202 arm64: KVM: Make PSCI_VERSION a fast path

In reply to Greg Kroah-Hartman

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Marc Zyngier <[email protected]>

Commit 90348689d500 upstream.

For those CPUs that require PSCI to perform a BP invalidation, going all the way to the PSCI code for not much is a waste of precious cycles. Let's terminate that call as early as possible.

---
 arch/arm64/kvm/hyp/switch.c |   13 +++++++++++++
 1 file changed, 13 insertions(+)
arch/arm64/kvm/hyp/switch.c +13 -0
@@ -17,6 +17,7 @@
 
 #include <linux/types.h>
 #include <linux/jump_label.h>
+#include <uapi/linux/psci.h>
 
 #include <asm/kvm_asm.h>
 #include <asm/kvm_emulate.h>
@@ -341,6 +342,18 @@ again:
 	if (exit_code == ARM_EXCEPTION_TRAP && !__populate_fault_info(vcpu))
 		goto again;
 
+	if (exit_code == ARM_EXCEPTION_TRAP &&
+	    (kvm_vcpu_trap_get_class(vcpu) == ESR_ELx_EC_HVC64 ||
+	     kvm_vcpu_trap_get_class(vcpu) == ESR_ELx_EC_HVC32) &&
+	    vcpu_get_reg(vcpu, 0) == PSCI_0_2_FN_PSCI_VERSION) {
+		u64 val = PSCI_RET_NOT_SUPPORTED;
+		if (test_bit(KVM_ARM_VCPU_PSCI_0_2, vcpu->arch.features))
+			val = 2;
+
+		vcpu_set_reg(vcpu, 0, val);
+		goto again;
+	}
+
 	if (static_branch_unlikely(&vgic_v2_cpuif_trap) &&
 	    exit_code == ARM_EXCEPTION_TRAP) {
 		bool valid;
author maintainer
#79 lore raw

PATCH 79/202 arm/arm64: KVM: Turn kvm_psci_version into a static inline

In reply to Greg Kroah-Hartman

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Marc Zyngier <[email protected]>

Commit a4097b351118 upstream.

We're about to need kvm_psci_version in HYP too. So let's turn it into a static inline, and pass the kvm structure as a second parameter (so that HYP can do a kern_hyp_va on it).

---
 arch/arm64/kvm/hyp/switch.c |   18 +++++++++++-------
 include/kvm/arm_psci.h      |   21 ++++++++++++++++++++-
 virt/kvm/arm/psci.c         |   12 ++----------
 3 files changed, 33 insertions(+), 18 deletions(-)
arch/arm64/kvm/hyp/switch.c +11 -7
@@ -19,6 +19,8 @@
 #include <linux/jump_label.h>
 #include <uapi/linux/psci.h>
 
+#include <kvm/arm_psci.h>
+
 #include <asm/kvm_asm.h>
 #include <asm/kvm_emulate.h>
 #include <asm/kvm_hyp.h>
@@ -344,14 +346,16 @@ again:
 
 	if (exit_code == ARM_EXCEPTION_TRAP &&
 	    (kvm_vcpu_trap_get_class(vcpu) == ESR_ELx_EC_HVC64 ||
-	     kvm_vcpu_trap_get_class(vcpu) == ESR_ELx_EC_HVC32) &&
-	    vcpu_get_reg(vcpu, 0) == PSCI_0_2_FN_PSCI_VERSION) {
-		u64 val = PSCI_RET_NOT_SUPPORTED;
-		if (test_bit(KVM_ARM_VCPU_PSCI_0_2, vcpu->arch.features))
-			val = 2;
+	     kvm_vcpu_trap_get_class(vcpu) == ESR_ELx_EC_HVC32)) {
+		u32 val = vcpu_get_reg(vcpu, 0);
 
-		vcpu_set_reg(vcpu, 0, val);
-		goto again;
+		if (val == PSCI_0_2_FN_PSCI_VERSION) {
+			val = kvm_psci_version(vcpu, kern_hyp_va(vcpu->kvm));
+			if (unlikely(val == KVM_ARM_PSCI_0_1))
+				val = PSCI_RET_NOT_SUPPORTED;
+			vcpu_set_reg(vcpu, 0, val);
+			goto again;
+		}
 	}
 
 	if (static_branch_unlikely(&vgic_v2_cpuif_trap) &&
include/kvm/arm_psci.h +20 -1
@@ -18,6 +18,7 @@
 #ifndef __KVM_ARM_PSCI_H__
 #define __KVM_ARM_PSCI_H__
 
+#include <linux/kvm_host.h>
 #include <uapi/linux/psci.h>
 
 #define KVM_ARM_PSCI_0_1	PSCI_VERSION(0, 1)
@@ -26,7 +27,25 @@
 
 #define KVM_ARM_PSCI_LATEST	KVM_ARM_PSCI_1_0
 
-int kvm_psci_version(struct kvm_vcpu *vcpu);
+/*
+ * We need the KVM pointer independently from the vcpu as we can call
+ * this from HYP, and need to apply kern_hyp_va on it...
+ */
+static inline int kvm_psci_version(struct kvm_vcpu *vcpu, struct kvm *kvm)
+{
+	/*
+	 * Our PSCI implementation stays the same across versions from
+	 * v0.2 onward, only adding the few mandatory functions (such
+	 * as FEATURES with 1.0) that are required by newer
+	 * revisions. It is thus safe to return the latest.
+	 */
+	if (test_bit(KVM_ARM_VCPU_PSCI_0_2, vcpu->arch.features))
+		return KVM_ARM_PSCI_LATEST;
+
+	return KVM_ARM_PSCI_0_1;
+}
+
+
 int kvm_hvc_call_handler(struct kvm_vcpu *vcpu);
 
 #endif /* __KVM_ARM_PSCI_H__ */
virt/kvm/arm/psci.c +2 -10
@@ -123,7 +123,7 @@ static unsigned long kvm_psci_vcpu_on(st
 	if (!vcpu)
 		return PSCI_RET_INVALID_PARAMS;
 	if (!vcpu->arch.power_off) {
-		if (kvm_psci_version(source_vcpu) != KVM_ARM_PSCI_0_1)
+		if (kvm_psci_version(source_vcpu, kvm) != KVM_ARM_PSCI_0_1)
 			return PSCI_RET_ALREADY_ON;
 		else
 			return PSCI_RET_INVALID_PARAMS;
@@ -232,14 +232,6 @@ static void kvm_psci_system_reset(struct
 	kvm_prepare_system_event(vcpu, KVM_SYSTEM_EVENT_RESET);
 }
 
-int kvm_psci_version(struct kvm_vcpu *vcpu)
-{
-	if (test_bit(KVM_ARM_VCPU_PSCI_0_2, vcpu->arch.features))
-		return KVM_ARM_PSCI_LATEST;
-
-	return KVM_ARM_PSCI_0_1;
-}
-
 static int kvm_psci_0_2_call(struct kvm_vcpu *vcpu)
 {
 	struct kvm *kvm = vcpu->kvm;
@@ -397,7 +389,7 @@ static int kvm_psci_0_1_call(struct kvm_
  */
 static int kvm_psci_call(struct kvm_vcpu *vcpu)
 {
-	switch (kvm_psci_version(vcpu)) {
+	switch (kvm_psci_version(vcpu, vcpu->kvm)) {
 	case KVM_ARM_PSCI_1_0:
 		return kvm_psci_1_0_call(vcpu);
 	case KVM_ARM_PSCI_0_2:
author maintainer
#80 lore raw

PATCH 80/202 arm64: KVM: Report SMCCC_ARCH_WORKAROUND_1 BP hardening support

In reply to Greg Kroah-Hartman

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Marc Zyngier <[email protected]>

Commit 6167ec5c9145 upstream.

A new feature of SMCCC 1.1 is that it offers firmware-based CPU workarounds. In particular, SMCCC_ARCH_WORKAROUND_1 provides BP hardening for CVE-2017-5715.

If the host has some mitigation for this issue, report that we deal with it using SMCCC_ARCH_WORKAROUND_1, as we apply the host workaround on every guest exit.

Conflicts:
arch/arm/include/asm/kvm_host.h
arch/arm64/include/asm/kvm_host.h

---
 arch/arm/include/asm/kvm_host.h   |    6 ++++++
 arch/arm64/include/asm/kvm_host.h |    5 +++++
 include/linux/arm-smccc.h         |    5 +++++
 virt/kvm/arm/psci.c               |    9 ++++++++-
 4 files changed, 24 insertions(+), 1 deletion(-)
arch/arm/include/asm/kvm_host.h +6 -0
@@ -301,4 +301,10 @@ int kvm_arm_vcpu_arch_has_attr(struct kv
 /* All host FP/SIMD state is restored on guest exit, so nothing to save: */
 static inline void kvm_fpsimd_flush_cpu_state(void) {}
 
+static inline bool kvm_arm_harden_branch_predictor(void)
+{
+	/* No way to detect it yet, pretend it is not there. */
+	return false;
+}
+
 #endif /* __ARM_KVM_HOST_H__ */
arch/arm64/include/asm/kvm_host.h +5 -0
@@ -396,4 +396,9 @@ static inline void kvm_fpsimd_flush_cpu_
 		sve_flush_cpu_state();
 }
 
+static inline bool kvm_arm_harden_branch_predictor(void)
+{
+	return cpus_have_const_cap(ARM64_HARDEN_BRANCH_PREDICTOR);
+}
+
 #endif /* __ARM64_KVM_HOST_H__ */
include/linux/arm-smccc.h +5 -0
@@ -73,6 +73,11 @@
 			   ARM_SMCCC_SMC_32,				\
 			   0, 1)
 
+#define ARM_SMCCC_ARCH_WORKAROUND_1					\
+	ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL,				\
+			   ARM_SMCCC_SMC_32,				\
+			   0, 0x8000)
+
 #ifndef __ASSEMBLY__
 
 #include <linux/linkage.h>
virt/kvm/arm/psci.c +8 -1
@@ -405,13 +405,20 @@ int kvm_hvc_call_handler(struct kvm_vcpu
 {
 	u32 func_id = smccc_get_function(vcpu);
 	u32 val = PSCI_RET_NOT_SUPPORTED;
+	u32 feature;
 
 	switch (func_id) {
 	case ARM_SMCCC_VERSION_FUNC_ID:
 		val = ARM_SMCCC_VERSION_1_1;
 		break;
 	case ARM_SMCCC_ARCH_FEATURES_FUNC_ID:
-		/* Nothing supported yet */
+		feature = smccc_get_arg1(vcpu);
+		switch(feature) {
+		case ARM_SMCCC_ARCH_WORKAROUND_1:
+			if (kvm_arm_harden_branch_predictor())
+				val = 0;
+			break;
+		}
 		break;
 	default:
 		return kvm_psci_call(vcpu);
author maintainer
#81 lore raw

PATCH 81/202 arm64: KVM: Add SMCCC_ARCH_WORKAROUND_1 fast handling

In reply to Greg Kroah-Hartman

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Marc Zyngier <[email protected]>

Commit f72af90c3783 upstream.

We want SMCCC_ARCH_WORKAROUND_1 to be fast. As fast as possible. So let's intercept it as early as we can by testing for the function call number as soon as we've identified a HVC call coming from the guest.

---
 arch/arm64/kvm/hyp/hyp-entry.S |   20 ++++++++++++++++++--
 1 file changed, 18 insertions(+), 2 deletions(-)
arch/arm64/kvm/hyp/hyp-entry.S +18 -2
@@ -15,6 +15,7 @@
  * along with this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
+#include <linux/arm-smccc.h>
 #include <linux/linkage.h>
 
 #include <asm/alternative.h>
@@ -64,10 +65,11 @@ alternative_endif
 	lsr	x0, x1, #ESR_ELx_EC_SHIFT
 
 	cmp	x0, #ESR_ELx_EC_HVC64
+	ccmp	x0, #ESR_ELx_EC_HVC32, #4, ne
 	b.ne	el1_trap
 
-	mrs	x1, vttbr_el2		// If vttbr is valid, the 64bit guest
-	cbnz	x1, el1_trap		// called HVC
+	mrs	x1, vttbr_el2		// If vttbr is valid, the guest
+	cbnz	x1, el1_hvc_guest	// called HVC
 
 	/* Here, we're pretty sure the host called HVC. */
 	ldp	x0, x1, [sp], #16
@@ -100,6 +102,20 @@ alternative_endif
 
 	eret
 
+el1_hvc_guest:
+	/*
+	 * Fastest possible path for ARM_SMCCC_ARCH_WORKAROUND_1.
+	 * The workaround has already been applied on the host,
+	 * so let's quickly get back to the guest. We don't bother
+	 * restoring x1, as it can be clobbered anyway.
+	 */
+	ldr	x1, [sp]				// Guest's x0
+	eor	w1, w1, #ARM_SMCCC_ARCH_WORKAROUND_1
+	cbnz	w1, el1_trap
+	mov	x0, x1
+	add	sp, sp, #16
+	eret
+
 el1_trap:
 	/*
 	 * x0: ESR_EC
author maintainer
#82 lore raw

PATCH 82/202 firmware/psci: Expose PSCI conduit

In reply to Greg Kroah-Hartman

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Marc Zyngier <[email protected]>

Commit 09a8d6d48499 upstream.

In order to call into the firmware to apply workarounds, it is useful to find out whether we're using HVC or SMC. Let's expose this through the psci_ops.

---
 drivers/firmware/psci.c |   28 +++++++++++++++++++++++-----
 include/linux/psci.h    |    7 +++++++
 2 files changed, 30 insertions(+), 5 deletions(-)
drivers/firmware/psci.c +23 -5
@@ -59,7 +59,9 @@ bool psci_tos_resident_on(int cpu)
 	return cpu == resident_cpu;
 }
 
-struct psci_operations psci_ops;
+struct psci_operations psci_ops = {
+	.conduit = PSCI_CONDUIT_NONE,
+};
 
 typedef unsigned long (psci_fn)(unsigned long, unsigned long,
 				unsigned long, unsigned long);
@@ -210,6 +212,22 @@ static unsigned long psci_migrate_info_u
 			      0, 0, 0);
 }
 
+static void set_conduit(enum psci_conduit conduit)
+{
+	switch (conduit) {
+	case PSCI_CONDUIT_HVC:
+		invoke_psci_fn = __invoke_psci_fn_hvc;
+		break;
+	case PSCI_CONDUIT_SMC:
+		invoke_psci_fn = __invoke_psci_fn_smc;
+		break;
+	default:
+		WARN(1, "Unexpected PSCI conduit %d\n", conduit);
+	}
+
+	psci_ops.conduit = conduit;
+}
+
 static int get_set_conduit_method(struct device_node *np)
 {
 	const char *method;
@@ -222,9 +240,9 @@ static int get_set_conduit_method(struct
 	}
 
 	if (!strcmp("hvc", method)) {
-		invoke_psci_fn = __invoke_psci_fn_hvc;
+		set_conduit(PSCI_CONDUIT_HVC);
 	} else if (!strcmp("smc", method)) {
-		invoke_psci_fn = __invoke_psci_fn_smc;
+		set_conduit(PSCI_CONDUIT_SMC);
 	} else {
 		pr_warn("invalid \"method\" property: %s\n", method);
 		return -EINVAL;
@@ -654,9 +672,9 @@ int __init psci_acpi_init(void)
 	pr_info("probing for conduit method from ACPI.\n");
 
 	if (acpi_psci_use_hvc())
-		invoke_psci_fn = __invoke_psci_fn_hvc;
+		set_conduit(PSCI_CONDUIT_HVC);
 	else
-		invoke_psci_fn = __invoke_psci_fn_smc;
+		set_conduit(PSCI_CONDUIT_SMC);
 
 	return psci_probe();
 }
include/linux/psci.h +7 -0
@@ -25,6 +25,12 @@ bool psci_tos_resident_on(int cpu);
 int psci_cpu_init_idle(unsigned int cpu);
 int psci_cpu_suspend_enter(unsigned long index);
 
+enum psci_conduit {
+	PSCI_CONDUIT_NONE,
+	PSCI_CONDUIT_SMC,
+	PSCI_CONDUIT_HVC,
+};
+
 struct psci_operations {
 	u32 (*get_version)(void);
 	int (*cpu_suspend)(u32 state, unsigned long entry_point);
@@ -34,6 +40,7 @@ struct psci_operations {
 	int (*affinity_info)(unsigned long target_affinity,
 			unsigned long lowest_affinity_level);
 	int (*migrate_info_type)(void);
+	enum psci_conduit conduit;
 };
 
 extern struct psci_operations psci_ops;
author maintainer
#83 lore raw

PATCH 83/202 firmware/psci: Expose SMCCC version through psci_ops

In reply to Greg Kroah-Hartman

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Marc Zyngier <[email protected]>

Commit e78eef554a91 upstream.

Since PSCI 1.0 allows the SMCCC version to be (indirectly) probed, let's do that at boot time, and expose the version of the calling convention as part of the psci_ops structure.

---
 drivers/firmware/psci.c |   27 +++++++++++++++++++++++++++
 include/linux/psci.h    |    6 ++++++
 2 files changed, 33 insertions(+)
drivers/firmware/psci.c +27 -0
@@ -61,6 +61,7 @@ bool psci_tos_resident_on(int cpu)
 
 struct psci_operations psci_ops = {
 	.conduit = PSCI_CONDUIT_NONE,
+	.smccc_version = SMCCC_VERSION_1_0,
 };
 
 typedef unsigned long (psci_fn)(unsigned long, unsigned long,
@@ -511,6 +512,31 @@ static void __init psci_init_migrate(voi
 	pr_info("Trusted OS resident on physical CPU 0x%lx\n", cpuid);
 }
 
+static void __init psci_init_smccc(void)
+{
+	u32 ver = ARM_SMCCC_VERSION_1_0;
+	int feature;
+
+	feature = psci_features(ARM_SMCCC_VERSION_FUNC_ID);
+
+	if (feature != PSCI_RET_NOT_SUPPORTED) {
+		u32 ret;
+		ret = invoke_psci_fn(ARM_SMCCC_VERSION_FUNC_ID, 0, 0, 0);
+		if (ret == ARM_SMCCC_VERSION_1_1) {
+			psci_ops.smccc_version = SMCCC_VERSION_1_1;
+			ver = ret;
+		}
+	}
+
+	/*
+	 * Conveniently, the SMCCC and PSCI versions are encoded the
+	 * same way. No, this isn't accidental.
+	 */
+	pr_info("SMC Calling Convention v%d.%d\n",
+		PSCI_VERSION_MAJOR(ver), PSCI_VERSION_MINOR(ver));
+
+}
+
 static void __init psci_0_2_set_functions(void)
 {
 	pr_info("Using standard PSCI v0.2 function IDs\n");
@@ -559,6 +585,7 @@ static int __init psci_probe(void)
 	psci_init_migrate();
 
 	if (PSCI_VERSION_MAJOR(ver) >= 1) {
+		psci_init_smccc();
 		psci_init_cpu_suspend();
 		psci_init_system_suspend();
 	}
include/linux/psci.h +6 -0
@@ -31,6 +31,11 @@ enum psci_conduit {
 	PSCI_CONDUIT_HVC,
 };
 
+enum smccc_version {
+	SMCCC_VERSION_1_0,
+	SMCCC_VERSION_1_1,
+};
+
 struct psci_operations {
 	u32 (*get_version)(void);
 	int (*cpu_suspend)(u32 state, unsigned long entry_point);
@@ -41,6 +46,7 @@ struct psci_operations {
 			unsigned long lowest_affinity_level);
 	int (*migrate_info_type)(void);
 	enum psci_conduit conduit;
+	enum smccc_version smccc_version;
 };
 
 extern struct psci_operations psci_ops;
author maintainer
#84 lore raw

PATCH 84/202 arm/arm64: smccc: Make function identifiers an unsigned quantity

In reply to Greg Kroah-Hartman

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Marc Zyngier <[email protected]>

Commit ded4c39e93f3 upstream.

Function identifiers are a 32bit, unsigned quantity. But we never tell so to the compiler, resulting in the following:

4ac: b26187e0 mov x0, #0xffffffff80000001

We thus rely on the firmware narrowing it for us, which is not always a reasonable expectation.

---
 include/linux/arm-smccc.h |    6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)
include/linux/arm-smccc.h +4 -2
@@ -14,14 +14,16 @@
 #ifndef __LINUX_ARM_SMCCC_H
 #define __LINUX_ARM_SMCCC_H
 
+#include <uapi/linux/const.h>
+
 /*
  * This file provides common defines for ARM SMC Calling Convention as
  * specified in
  * http://infocenter.arm.com/help/topic/com.arm.doc.den0028a/index.html
  */
 
-#define ARM_SMCCC_STD_CALL		0
-#define ARM_SMCCC_FAST_CALL		1
+#define ARM_SMCCC_STD_CALL	        _AC(0,U)
+#define ARM_SMCCC_FAST_CALL	        _AC(1,U)
 #define ARM_SMCCC_TYPE_SHIFT		31
 
 #define ARM_SMCCC_SMC_32		0
author maintainer
#85 lore raw

PATCH 85/202 arm/arm64: smccc: Implement SMCCC v1.1 inline primitive

In reply to Greg Kroah-Hartman

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Marc Zyngier <[email protected]>

Commit f2d3b2e8759a upstream.

One of the major improvement of SMCCC v1.1 is that it only clobbers the first 4 registers, both on 32 and 64bit. This means that it becomes very easy to provide an inline version of the SMC call primitive, and avoid performing a function call to stash the registers that would otherwise be clobbered by SMCCC v1.0.

---
 include/linux/arm-smccc.h |  141 ++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 141 insertions(+)
include/linux/arm-smccc.h +141 -0
@@ -150,5 +150,146 @@ asmlinkage void __arm_smccc_hvc(unsigned
 
 #define arm_smccc_hvc_quirk(...) __arm_smccc_hvc(__VA_ARGS__)
 
+/* SMCCC v1.1 implementation madness follows */
+#ifdef CONFIG_ARM64
+
+#define SMCCC_SMC_INST	"smc	#0"
+#define SMCCC_HVC_INST	"hvc	#0"
+
+#elif defined(CONFIG_ARM)
+#include <asm/opcodes-sec.h>
+#include <asm/opcodes-virt.h>
+
+#define SMCCC_SMC_INST	__SMC(0)
+#define SMCCC_HVC_INST	__HVC(0)
+
+#endif
+
+#define ___count_args(_0, _1, _2, _3, _4, _5, _6, _7, _8, x, ...) x
+
+#define __count_args(...)						\
+	___count_args(__VA_ARGS__, 7, 6, 5, 4, 3, 2, 1, 0)
+
+#define __constraint_write_0						\
+	"+r" (r0), "=&r" (r1), "=&r" (r2), "=&r" (r3)
+#define __constraint_write_1						\
+	"+r" (r0), "+r" (r1), "=&r" (r2), "=&r" (r3)
+#define __constraint_write_2						\
+	"+r" (r0), "+r" (r1), "+r" (r2), "=&r" (r3)
+#define __constraint_write_3						\
+	"+r" (r0), "+r" (r1), "+r" (r2), "+r" (r3)
+#define __constraint_write_4	__constraint_write_3
+#define __constraint_write_5	__constraint_write_4
+#define __constraint_write_6	__constraint_write_5
+#define __constraint_write_7	__constraint_write_6
+
+#define __constraint_read_0
+#define __constraint_read_1
+#define __constraint_read_2
+#define __constraint_read_3
+#define __constraint_read_4	"r" (r4)
+#define __constraint_read_5	__constraint_read_4, "r" (r5)
+#define __constraint_read_6	__constraint_read_5, "r" (r6)
+#define __constraint_read_7	__constraint_read_6, "r" (r7)
+
+#define __declare_arg_0(a0, res)					\
+	struct arm_smccc_res   *___res = res;				\
+	register u32           r0 asm("r0") = a0;			\
+	register unsigned long r1 asm("r1");				\
+	register unsigned long r2 asm("r2");				\
+	register unsigned long r3 asm("r3")
+
+#define __declare_arg_1(a0, a1, res)					\
+	struct arm_smccc_res   *___res = res;				\
+	register u32           r0 asm("r0") = a0;			\
+	register typeof(a1)    r1 asm("r1") = a1;			\
+	register unsigned long r2 asm("r2");				\
+	register unsigned long r3 asm("r3")
+
+#define __declare_arg_2(a0, a1, a2, res)				\
+	struct arm_smccc_res   *___res = res;				\
+	register u32           r0 asm("r0") = a0;			\
+	register typeof(a1)    r1 asm("r1") = a1;			\
+	register typeof(a2)    r2 asm("r2") = a2;			\
+	register unsigned long r3 asm("r3")
+
+#define __declare_arg_3(a0, a1, a2, a3, res)				\
+	struct arm_smccc_res   *___res = res;				\
+	register u32           r0 asm("r0") = a0;			\
+	register typeof(a1)    r1 asm("r1") = a1;			\
+	register typeof(a2)    r2 asm("r2") = a2;			\
+	register typeof(a3)    r3 asm("r3") = a3
+
+#define __declare_arg_4(a0, a1, a2, a3, a4, res)			\
+	__declare_arg_3(a0, a1, a2, a3, res);				\
+	register typeof(a4) r4 asm("r4") = a4
+
+#define __declare_arg_5(a0, a1, a2, a3, a4, a5, res)			\
+	__declare_arg_4(a0, a1, a2, a3, a4, res);			\
+	register typeof(a5) r5 asm("r5") = a5
+
+#define __declare_arg_6(a0, a1, a2, a3, a4, a5, a6, res)		\
+	__declare_arg_5(a0, a1, a2, a3, a4, a5, res);			\
+	register typeof(a6) r6 asm("r6") = a6
+
+#define __declare_arg_7(a0, a1, a2, a3, a4, a5, a6, a7, res)		\
+	__declare_arg_6(a0, a1, a2, a3, a4, a5, a6, res);		\
+	register typeof(a7) r7 asm("r7") = a7
+
+#define ___declare_args(count, ...) __declare_arg_ ## count(__VA_ARGS__)
+#define __declare_args(count, ...)  ___declare_args(count, __VA_ARGS__)
+
+#define ___constraints(count)						\
+	: __constraint_write_ ## count					\
+	: __constraint_read_ ## count					\
+	: "memory"
+#define __constraints(count)	___constraints(count)
+
+/*
+ * We have an output list that is not necessarily used, and GCC feels
+ * entitled to optimise the whole sequence away. "volatile" is what
+ * makes it stick.
+ */
+#define __arm_smccc_1_1(inst, ...)					\
+	do {								\
+		__declare_args(__count_args(__VA_ARGS__), __VA_ARGS__);	\
+		asm volatile(inst "\n"					\
+			     __constraints(__count_args(__VA_ARGS__)));	\
+		if (___res)						\
+			*___res = (typeof(*___res)){r0, r1, r2, r3};	\
+	} while (0)
+
+/*
+ * arm_smccc_1_1_smc() - make an SMCCC v1.1 compliant SMC call
+ *
+ * This is a variadic macro taking one to eight source arguments, and
+ * an optional return structure.
+ *
+ * @a0-a7: arguments passed in registers 0 to 7
+ * @res: result values from registers 0 to 3
+ *
+ * This macro is used to make SMC calls following SMC Calling Convention v1.1.
+ * The content of the supplied param are copied to registers 0 to 7 prior
+ * to the SMC instruction. The return values are updated with the content
+ * from register 0 to 3 on return from the SMC instruction if not NULL.
+ */
+#define arm_smccc_1_1_smc(...)	__arm_smccc_1_1(SMCCC_SMC_INST, __VA_ARGS__)
+
+/*
+ * arm_smccc_1_1_hvc() - make an SMCCC v1.1 compliant HVC call
+ *
+ * This is a variadic macro taking one to eight source arguments, and
+ * an optional return structure.
+ *
+ * @a0-a7: arguments passed in registers 0 to 7
+ * @res: result values from registers 0 to 3
+ *
+ * This macro is used to make HVC calls following SMC Calling Convention v1.1.
+ * The content of the supplied param are copied to registers 0 to 7 prior
+ * to the HVC instruction. The return values are updated with the content
+ * from register 0 to 3 on return from the HVC instruction if not NULL.
+ */
+#define arm_smccc_1_1_hvc(...)	__arm_smccc_1_1(SMCCC_HVC_INST, __VA_ARGS__)
+
 #endif /*__ASSEMBLY__*/
 #endif /*__LINUX_ARM_SMCCC_H*/
author maintainer
#86 lore raw

PATCH 86/202 arm64: Add ARM_SMCCC_ARCH_WORKAROUND_1 BP hardening support

In reply to Greg Kroah-Hartman

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Marc Zyngier <[email protected]>

Commit b092201e0020 upstream.

Add the detection and runtime code for ARM_SMCCC_ARCH_WORKAROUND_1. It is lovely. Really.

---
 arch/arm64/kernel/bpi.S        |   20 ++++++++++++
 arch/arm64/kernel/cpu_errata.c |   68 ++++++++++++++++++++++++++++++++++++++++-
 2 files changed, 87 insertions(+), 1 deletion(-)
arch/arm64/kernel/bpi.S +20 -0
@@ -17,6 +17,7 @@
  */
 
 #include <linux/linkage.h>
+#include <linux/arm-smccc.h>
 
 .macro ventry target
 	.rept 31
@@ -85,3 +86,22 @@ ENTRY(__qcom_hyp_sanitize_link_stack_sta
 	.endr
 	ldp	x29, x30, [sp], #16
 ENTRY(__qcom_hyp_sanitize_link_stack_end)
+
+.macro smccc_workaround_1 inst
+	sub	sp, sp, #(8 * 4)
+	stp	x2, x3, [sp, #(8 * 0)]
+	stp	x0, x1, [sp, #(8 * 2)]
+	mov	w0, #ARM_SMCCC_ARCH_WORKAROUND_1
+	\inst	#0
+	ldp	x2, x3, [sp, #(8 * 0)]
+	ldp	x0, x1, [sp, #(8 * 2)]
+	add	sp, sp, #(8 * 4)
+.endm
+
+ENTRY(__smccc_workaround_1_smc_start)
+	smccc_workaround_1	smc
+ENTRY(__smccc_workaround_1_smc_end)
+
+ENTRY(__smccc_workaround_1_hvc_start)
+	smccc_workaround_1	hvc
+ENTRY(__smccc_workaround_1_hvc_end)
arch/arm64/kernel/cpu_errata.c +67 -1

96 lines not on this page · raw message

author maintainer
#87 lore raw

PATCH 87/202 arm64: Kill PSCI_GET_VERSION as a variant-2 workaround

In reply to Greg Kroah-Hartman

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Marc Zyngier <[email protected]>

Commit 3a0a397ff5ff upstream.

Now that we've standardised on SMCCC v1.1 to perform the branch prediction invalidation, let's drop the previous band-aid. If vendors haven't updated their firmware to do SMCCC 1.1, they haven't updated PSCI either, so we don't loose anything.

---
 arch/arm64/kernel/bpi.S        |   24 ---------------------
 arch/arm64/kernel/cpu_errata.c |   45 +++++++++++------------------------------
 arch/arm64/kvm/hyp/switch.c    |   14 ------------
 3 files changed, 13 insertions(+), 70 deletions(-)
arch/arm64/kernel/bpi.S +0 -24
@@ -54,30 +54,6 @@ ENTRY(__bp_harden_hyp_vecs_start)
 	vectors __kvm_hyp_vector
 	.endr
 ENTRY(__bp_harden_hyp_vecs_end)
-ENTRY(__psci_hyp_bp_inval_start)
-	sub	sp, sp, #(8 * 18)
-	stp	x16, x17, [sp, #(16 * 0)]
-	stp	x14, x15, [sp, #(16 * 1)]
-	stp	x12, x13, [sp, #(16 * 2)]
-	stp	x10, x11, [sp, #(16 * 3)]
-	stp	x8, x9, [sp, #(16 * 4)]
-	stp	x6, x7, [sp, #(16 * 5)]
-	stp	x4, x5, [sp, #(16 * 6)]
-	stp	x2, x3, [sp, #(16 * 7)]
-	stp	x0, x1, [sp, #(16 * 8)]
-	mov	x0, #0x84000000
-	smc	#0
-	ldp	x16, x17, [sp, #(16 * 0)]
-	ldp	x14, x15, [sp, #(16 * 1)]
-	ldp	x12, x13, [sp, #(16 * 2)]
-	ldp	x10, x11, [sp, #(16 * 3)]
-	ldp	x8, x9, [sp, #(16 * 4)]
-	ldp	x6, x7, [sp, #(16 * 5)]
-	ldp	x4, x5, [sp, #(16 * 6)]
-	ldp	x2, x3, [sp, #(16 * 7)]
-	ldp	x0, x1, [sp, #(16 * 8)]
-	add	sp, sp, #(8 * 18)
-ENTRY(__psci_hyp_bp_inval_end)
 
 ENTRY(__qcom_hyp_sanitize_link_stack_start)
 	stp     x29, x30, [sp, #-16]!
arch/arm64/kernel/cpu_errata.c +13 -32

121 lines not on this page · raw message

arch/arm64/kvm/hyp/switch.c +0 -14
@@ -344,20 +344,6 @@ again:
 	if (exit_code == ARM_EXCEPTION_TRAP && !__populate_fault_info(vcpu))
 		goto again;
 
-	if (exit_code == ARM_EXCEPTION_TRAP &&
-	    (kvm_vcpu_trap_get_class(vcpu) == ESR_ELx_EC_HVC64 ||
-	     kvm_vcpu_trap_get_class(vcpu) == ESR_ELx_EC_HVC32)) {
-		u32 val = vcpu_get_reg(vcpu, 0);
-
-		if (val == PSCI_0_2_FN_PSCI_VERSION) {
-			val = kvm_psci_version(vcpu, kern_hyp_va(vcpu->kvm));
-			if (unlikely(val == KVM_ARM_PSCI_0_1))
-				val = PSCI_RET_NOT_SUPPORTED;
-			vcpu_set_reg(vcpu, 0, val);
-			goto again;
-		}
-	}
-
 	if (static_branch_unlikely(&vgic_v2_cpuif_trap) &&
 	    exit_code == ARM_EXCEPTION_TRAP) {
 		bool valid;
author maintainer
#88 lore raw

PATCH 88/202 mtd: cfi: convert inline functions to macros

In reply to Greg Kroah-Hartman

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Arnd Bergmann <[email protected]>

commit 9e343e87d2c4c707ef8fae2844864d4dde3a2d13 upstream.

The map_word_() functions, dating back to linux-2.6.8, try to perform bitwise operations on a 'map_word' structure. This may have worked with compilers that were current then (gcc-3.4 or earlier), but end up being rather inefficient on any version I could try now (gcc-4.4 or higher). Specifically we hit a problem analyzed in gcc PR81715 where we fail to reuse the stack space for local variables.

This can be seen immediately in the stack consumption for cfi_staa_erase_varsize() and other functions that (with CONFIG_KASAN) can be up to 2200 bytes. Changing the inline functions into macros brings this down to 1280 bytes. Without KASAN, the same problem exists, but the stack consumption is lower to start with, my patch shrinks it from 920 to 496 bytes on with arm-linux-gnueabi-gcc-5.4, and saves around 1KB in .text size for cfi_cmdset_0020.c, as it avoids copying map_word structures for each call to one of these helpers.

With the latest gcc-8 snapshot, the problem is fixed in upstream gcc, but nobody uses that yet, so we should still work around it in mainline kernels and probably backport the workaround to stable kernels as well. We had a couple of other functions that suffered from the same gcc bug, and all of those had a simpler workaround involving dummy variables in the inline function. Unfortunately that did not work here, the macro hack was the best I could come up with.

It would also be helpful to have someone to a little performance testing on the patch, to see how much it helps in terms of CPU utilitzation.

---
 include/linux/mtd/map.h |  130 ++++++++++++++++++++++--------------------------
 1 file changed, 61 insertions(+), 69 deletions(-)
include/linux/mtd/map.h +61 -69
@@ -270,75 +270,67 @@ void map_destroy(struct mtd_info *mtd);
 #define INVALIDATE_CACHED_RANGE(map, from, size) \
 	do { if (map->inval_cache) map->inval_cache(map, from, size); } while (0)
 
-
-static inline int map_word_equal(struct map_info *map, map_word val1, map_word val2)
-{
-	int i;
-
-	for (i = 0; i < map_words(map); i++) {
-		if (val1.x[i] != val2.x[i])
-			return 0;
-	}
-
-	return 1;
-}
-
-static inline map_word map_word_and(struct map_info *map, map_word val1, map_word val2)
-{
-	map_word r;
-	int i;
-
-	for (i = 0; i < map_words(map); i++)
-		r.x[i] = val1.x[i] & val2.x[i];
-
-	return r;
-}
-
-static inline map_word map_word_clr(struct map_info *map, map_word val1, map_word val2)
-{
-	map_word r;
-	int i;
-
-	for (i = 0; i < map_words(map); i++)
-		r.x[i] = val1.x[i] & ~val2.x[i];
-
-	return r;
-}
-
-static inline map_word map_word_or(struct map_info *map, map_word val1, map_word val2)
-{
-	map_word r;
-	int i;
-
-	for (i = 0; i < map_words(map); i++)
-		r.x[i] = val1.x[i] | val2.x[i];
-
-	return r;
-}
-
-static inline int map_word_andequal(struct map_info *map, map_word val1, map_word val2, map_word val3)
-{
-	int i;
-
-	for (i = 0; i < map_words(map); i++) {
-		if ((val1.x[i] & val2.x[i]) != val3.x[i])
-			return 0;
-	}
-
-	return 1;
-}
-
-static inline int map_word_bitsset(struct map_info *map, map_word val1, map_word val2)
-{
-	int i;
-
-	for (i = 0; i < map_words(map); i++) {
-		if (val1.x[i] & val2.x[i])
-			return 1;
-	}
-
-	return 0;
-}
+#define map_word_equal(map, val1, val2)					\
+({									\
+	int i, ret = 1;							\
+	for (i = 0; i < map_words(map); i++)				\
+		if ((val1).x[i] != (val2).x[i]) {			\
+			ret = 0;					\
+			break;						\
+		}							\
+	ret;								\
+})
+
+#define map_word_and(map, val1, val2)					\
+({									\
+	map_word r;							\
+	int i;								\
+	for (i = 0; i < map_words(map); i++)				\
+		r.x[i] = (val1).x[i] & (val2).x[i];			\
+	r;								\
+})
+
+#define map_word_clr(map, val1, val2)					\
+({									\
+	map_word r;							\
+	int i;								\
+	for (i = 0; i < map_words(map); i++)				\
+		r.x[i] = (val1).x[i] & ~(val2).x[i];			\
+	r;								\
+})
+
+#define map_word_or(map, val1, val2)					\
+({									\
+	map_word r;							\
+	int i;								\
+	for (i = 0; i < map_words(map); i++)				\
+		r.x[i] = (val1).x[i] | (val2).x[i];			\
+	r;								\
+})
+
+#define map_word_andequal(map, val1, val2, val3)			\
+({									\
+	int i, ret = 1;							\
+	for (i = 0; i < map_words(map); i++) {				\
+		if (((val1).x[i] & (val2).x[i]) != (val2).x[i]) {	\
+			ret = 0;					\
+			break;						\
+		}							\
+	}								\
+	ret;								\
+})
+
+#define map_word_bitsset(map, val1, val2)				\
+({									\
+	int i, ret = 0;							\
+	for (i = 0; i < map_words(map); i++) {				\
+		if ((val1).x[i] & (val2).x[i]) {			\
+			ret = 1;					\
+			break;						\
+		}							\
+	}								\
+	ret;								\
+})
 
 static inline map_word map_word_load(struct map_info *map, const void *ptr)
 {
author maintainer
#89 lore raw

PATCH 89/202 mtd: nand: brcmnand: Disable prefetch by default

In reply to Greg Kroah-Hartman

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Kamal Dasu <[email protected]>

commit f953f0f89663c39f08f4baaa8a4a881401b65654 upstream.

Brcm nand controller prefetch feature needs to be disabled by default. Enabling affects performance on random reads as well as dma reads.

Fixes 27c5b17cd1b1 ("mtd: nand: add NAND driver "library" for Broadcom STB NAND controller")
---
 drivers/mtd/nand/brcmnand/brcmnand.c |   13 +++----------
 1 file changed, 3 insertions(+), 10 deletions(-)
drivers/mtd/nand/brcmnand/brcmnand.c +3 -10
@@ -2193,16 +2193,9 @@ static int brcmnand_setup_dev(struct brc
 	if (ctrl->nand_version >= 0x0702)
 		tmp |= ACC_CONTROL_RD_ERASED;
 	tmp &= ~ACC_CONTROL_FAST_PGM_RDIN;
-	if (ctrl->features & BRCMNAND_HAS_PREFETCH) {
-		/*
-		 * FIXME: Flash DMA + prefetch may see spurious erased-page ECC
-		 * errors
-		 */
-		if (has_flash_dma(ctrl))
-			tmp &= ~ACC_CONTROL_PREFETCH;
-		else
-			tmp |= ACC_CONTROL_PREFETCH;
-	}
+	if (ctrl->features & BRCMNAND_HAS_PREFETCH)
+		tmp &= ~ACC_CONTROL_PREFETCH;
+
 	nand_writereg(ctrl, offs, tmp);
 
 	return 0;
author maintainer
#90 lore raw

PATCH 90/202 mtd: nand: Fix nand_do_read_oob() return value

In reply to Greg Kroah-Hartman

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Miquel Raynal <[email protected]>

commit 87e89ce8d0d14f573c068c61bec2117751fb5103 upstream.

Starting from commit 041e4575f034 ("mtd: nand: handle ECC errors in OOB"), nand_do_read_oob() (from the NAND core) did return 0 or a negative error, and the MTD layer expected it.

However, the trend for the NAND layer is now to return an error or a positive number of bitflips. Deciding which status to return to the user belongs to the MTD layer.

Commit e47f68587b82 ("mtd: check for max_bitflips in mtd_read_oob()") brought this logic to the mtd_read_oob() function while the return value coming from nand_do_read_oob() (called by the ->_read_oob() hook) was left unchanged.

Fixes e47f68587b82 ("mtd: check for max_bitflips in mtd_read_oob()")
---
 drivers/mtd/nand/nand_base.c |    5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)
drivers/mtd/nand/nand_base.c +4 -1
@@ -2199,6 +2199,7 @@ EXPORT_SYMBOL(nand_write_oob_syndrome);
 static int nand_do_read_oob(struct mtd_info *mtd, loff_t from,
 			    struct mtd_oob_ops *ops)
 {
+	unsigned int max_bitflips = 0;
 	int page, realpage, chipnr;
 	struct nand_chip *chip = mtd_to_nand(mtd);
 	struct mtd_ecc_stats stats;
@@ -2256,6 +2257,8 @@ static int nand_do_read_oob(struct mtd_i
 				nand_wait_ready(mtd);
 		}
 
+		max_bitflips = max_t(unsigned int, max_bitflips, ret);
+
 		readlen -= len;
 		if (!readlen)
 			break;
@@ -2281,7 +2284,7 @@ static int nand_do_read_oob(struct mtd_i
 	if (mtd->ecc_stats.failed - stats.failed)
 		return -EBADMSG;
 
-	return  mtd->ecc_stats.corrected - stats.corrected ? -EUCLEAN : 0;
+	return max_bitflips;
 }
 
 /**
author maintainer
#91 lore raw

PATCH 91/202 mtd: nand: sunxi: Fix ECC strength choice

In reply to Greg Kroah-Hartman

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Miquel Raynal <[email protected]>

commit f4c6cd1a7f2275d5bc0e494b21fff26f8dde80f0 upstream.

When the requested ECC strength does not exactly match the strengths supported by the ECC engine, the driver is selecting the closest strength meeting the 'selected_strength > requested_strength' constraint. Fix the fact that, in this particular case, ecc->strength value was not updated to match the 'selected_strength'.

For instance, one can encounter this issue when no ECC requirement is filled in the device tree while the NAND chip minimum requirement is not a strength/step_size combo natively supported by the ECC engine.

Fixes 1fef62c1423b ("mtd: nand: add sunxi NAND flash controller support")
---
 drivers/mtd/nand/sunxi_nand.c |    8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)
drivers/mtd/nand/sunxi_nand.c +7 -1
@@ -1853,8 +1853,14 @@ static int sunxi_nand_hw_common_ecc_ctrl
 
 	/* Add ECC info retrieval from DT */
 	for (i = 0; i < ARRAY_SIZE(strengths); i++) {
-		if (ecc->strength <= strengths[i])
+		if (ecc->strength <= strengths[i]) {
+			/*
+			 * Update ecc->strength value with the actual strength
+			 * that will be used by the ECC engine.
+			 */
+			ecc->strength = strengths[i];
 			break;
+		}
 	}
 
 	if (i >= ARRAY_SIZE(strengths)) {
author maintainer
#92 lore raw

PATCH 92/202 ubi: Fix race condition between ubi volume creation and udev

In reply to Greg Kroah-Hartman

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Clay McClure <[email protected]>

commit a51a0c8d213594bc094cb8e54aad0cb6d7f7b9a6 upstream.

Similar to commit 714fb87e8bc0 ("ubi: Fix race condition between ubi device creation and udev"), we should make the volume active before registering it.

---
 drivers/mtd/ubi/vmt.c |   15 ++++++++++-----
 1 file changed, 10 insertions(+), 5 deletions(-)
drivers/mtd/ubi/vmt.c +10 -5
@@ -270,6 +270,12 @@ int ubi_create_volume(struct ubi_device
 			vol->last_eb_bytes = vol->usable_leb_size;
 	}
 
+	/* Make volume "available" before it becomes accessible via sysfs */
+	spin_lock(&ubi->volumes_lock);
+	ubi->volumes[vol_id] = vol;
+	ubi->vol_count += 1;
+	spin_unlock(&ubi->volumes_lock);
+
 	/* Register character device for the volume */
 	cdev_init(&vol->cdev, &ubi_vol_cdev_operations);
 	vol->cdev.owner = THIS_MODULE;
@@ -298,11 +304,6 @@ int ubi_create_volume(struct ubi_device
 	if (err)
 		goto out_sysfs;
 
-	spin_lock(&ubi->volumes_lock);
-	ubi->volumes[vol_id] = vol;
-	ubi->vol_count += 1;
-	spin_unlock(&ubi->volumes_lock);
-
 	ubi_volume_notify(ubi, vol, UBI_VOLUME_ADDED);
 	self_check_volumes(ubi);
 	return err;
@@ -315,6 +316,10 @@ out_sysfs:
 	 */
 	cdev_device_del(&vol->cdev, &vol->dev);
 out_mapping:
+	spin_lock(&ubi->volumes_lock);
+	ubi->volumes[vol_id] = NULL;
+	ubi->vol_count -= 1;
+	spin_unlock(&ubi->volumes_lock);
 	ubi_eba_destroy_table(eba_tbl);
 out_acc:
 	spin_lock(&ubi->volumes_lock);
author maintainer
#93 lore raw

PATCH 93/202 ubi: fastmap: Erase outdated anchor PEBs during attach

In reply to Greg Kroah-Hartman

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Sascha Hauer <[email protected]>

commit f78e5623f45bab2b726eec29dc5cefbbab2d0b1c upstream.

The fastmap update code might erase the current fastmap anchor PEB in case it doesn't find any new free PEB. When a power cut happens in this situation we must not have any outdated fastmap anchor PEB on the device, because that would be used to attach during next boot.
The easiest way to make that sure is to erase all outdated fastmap anchor PEBs synchronously during attach.

---
 drivers/mtd/ubi/wl.c |   77 +++++++++++++++++++++++++++++++++++++--------------
 1 file changed, 57 insertions(+), 20 deletions(-)
drivers/mtd/ubi/wl.c +57 -20
@@ -1529,6 +1529,46 @@ static void shutdown_work(struct ubi_dev
 }
 
 /**
+ * erase_aeb - erase a PEB given in UBI attach info PEB
+ * @ubi: UBI device description object
+ * @aeb: UBI attach info PEB
+ * @sync: If true, erase synchronously. Otherwise schedule for erasure
+ */
+static int erase_aeb(struct ubi_device *ubi, struct ubi_ainf_peb *aeb, bool sync)
+{
+	struct ubi_wl_entry *e;
+	int err;
+
+	e = kmem_cache_alloc(ubi_wl_entry_slab, GFP_KERNEL);
+	if (!e)
+		return -ENOMEM;
+
+	e->pnum = aeb->pnum;
+	e->ec = aeb->ec;
+	ubi->lookuptbl[e->pnum] = e;
+
+	if (sync) {
+		err = sync_erase(ubi, e, false);
+		if (err)
+			goto out_free;
+
+		wl_tree_add(e, &ubi->free);
+		ubi->free_count++;
+	} else {
+		err = schedule_erase(ubi, e, aeb->vol_id, aeb->lnum, 0, false);
+		if (err)
+			goto out_free;
+	}
+
+	return 0;
+
+out_free:
+	wl_entry_destroy(ubi, e);
+
+	return err;
+}
+
+/**
  * ubi_wl_init - initialize the WL sub-system using attaching information.
  * @ubi: UBI device description object
  * @ai: attaching information
@@ -1566,17 +1606,9 @@ int ubi_wl_init(struct ubi_device *ubi,
 	list_for_each_entry_safe(aeb, tmp, &ai->erase, u.list) {
 		cond_resched();
 
-		e = kmem_cache_alloc(ubi_wl_entry_slab, GFP_KERNEL);
-		if (!e)
-			goto out_free;
-
-		e->pnum = aeb->pnum;
-		e->ec = aeb->ec;
-		ubi->lookuptbl[e->pnum] = e;
-		if (schedule_erase(ubi, e, aeb->vol_id, aeb->lnum, 0, false)) {
-			wl_entry_destroy(ubi, e);
+		err = erase_aeb(ubi, aeb, false);
+		if (err)
 			goto out_free;
-		}
 
 		found_pebs++;
 	}
@@ -1635,6 +1667,8 @@ int ubi_wl_init(struct ubi_device *ubi,
 			ubi_assert(!ubi->lookuptbl[e->pnum]);
 			ubi->lookuptbl[e->pnum] = e;
 		} else {
+			bool sync = false;
+
 			/*
 			 * Usually old Fastmap PEBs are scheduled for erasure
 			 * and we don't have to care about them but if we face
@@ -1644,18 +1678,21 @@ int ubi_wl_init(struct ubi_device *ubi,
 			if (ubi->lookuptbl[aeb->pnum])
 				continue;
 
-			e = kmem_cache_alloc(ubi_wl_entry_slab, GFP_KERNEL);
-			if (!e)
-				goto out_free;
+			/*
+			 * The fastmap update code might not find a free PEB for
+			 * writing the fastmap anchor to and then reuses the
+			 * current fastmap anchor PEB. When this PEB gets erased
+			 * and a power cut happens before it is written again we
+			 * must make sure that the fastmap attach code doesn't
+			 * find any outdated fastmap anchors, hence we erase the
+			 * outdated fastmap anchor PEBs synchronously here.
+			 */
+			if (aeb->vol_id == UBI_FM_SB_VOLUME_ID)
+				sync = true;
 
-			e->pnum = aeb->pnum;
-			e->ec = aeb->ec;
-			ubi_assert(!ubi->lookuptbl[e->pnum]);
-			ubi->lookuptbl[e->pnum] = e;
-			if (schedule_erase(ubi, e, aeb->vol_id, aeb->lnum, 0, false)) {
-				wl_entry_destroy(ubi, e);
+			err = erase_aeb(ubi, aeb, sync);
+			if (err)
 				goto out_free;
-			}
 		}
 
 		found_pebs++;
author maintainer
#94 lore raw

PATCH 94/202 ubi: block: Fix locking for idr_alloc/idr_remove

In reply to Greg Kroah-Hartman

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Bradley Bolen <[email protected]>

commit 7f29ae9f977bcdc3654e68bc36d170223c52fd48 upstream.

This fixes a race with idr_alloc where gd->first_minor can be set to the same value for two simultaneous calls to ubiblock_create. Each instance calls device_add_disk with the same first_minor. device_add_disk calls bdi_register_owner which generates several warnings.

WARNING: CPU: 1 PID: 179 at kernel-source/fs/sysfs/dir.c:31
sysfs_warn_dup+0x68/0x88

sysfs: cannot create duplicate filename '/devices/virtual/bdi/252:2'

WARNING: CPU: 1 PID: 179 at kernel-source/lib/kobject.c:240
kobject_add_internal+0x1ec/0x2f8

kobject_add_internal failed for 252:2 with -EEXIST, don't try to register things with the same name in the same directory

WARNING: CPU: 1 PID: 179 at kernel-source/fs/sysfs/dir.c:31
sysfs_warn_dup+0x68/0x88

sysfs: cannot create duplicate filename '/dev/block/252:2'

However, device_add_disk does not error out when bdi_register_owner returns an error. Control continues until reaching blk_register_queue. It then BUGs.

kernel BUG at kernel-source/fs/sysfs/group.c:113! [<c01e26cc>] (internal_create_group) from [<c01e2950>] (sysfs_create_group+0x20/0x24)
[<c01e2950>] (sysfs_create_group) from [<c00e3d38>] (blk_trace_init_sysfs+0x18/0x20)
[<c00e3d38>] (blk_trace_init_sysfs) from [<c02bdfbc>] (blk_register_queue+0xd8/0x154)
[<c02bdfbc>] (blk_register_queue) from [<c02cec84>] (device_add_disk+0x194/0x44c)
[<c02cec84>] (device_add_disk) from [<c0436ec8>] (ubiblock_create+0x284/0x2e0)
[<c0436ec8>] (ubiblock_create) from [<c0427bb8>] (vol_cdev_ioctl+0x450/0x554)
[<c0427bb8>] (vol_cdev_ioctl) from [<c0189110>] (vfs_ioctl+0x30/0x44) [<c0189110>] (vfs_ioctl) from [<c01892e0>] (do_vfs_ioctl+0xa0/0x790) [<c01892e0>] (do_vfs_ioctl) from [<c0189a14>] (SyS_ioctl+0x44/0x68) [<c0189a14>] (SyS_ioctl) from [<c0010640>] (ret_fast_syscall+0x0/0x34)

Locking idr_alloc/idr_remove removes the race and keeps gd->first_minor unique.

Fixes 2bf50d42f3a4 ("UBI: block: Dynamically allocate minor numbers")
---
 drivers/mtd/ubi/block.c |   42 ++++++++++++++++++++++++++----------------
 1 file changed, 26 insertions(+), 16 deletions(-)
drivers/mtd/ubi/block.c +26 -16
@@ -99,6 +99,8 @@ struct ubiblock {
 
 /* Linked list of all ubiblock instances */
 static LIST_HEAD(ubiblock_devices);
+static DEFINE_IDR(ubiblock_minor_idr);
+/* Protects ubiblock_devices and ubiblock_minor_idr */
 static DEFINE_MUTEX(devices_mutex);
 static int ubiblock_major;
 
@@ -351,8 +353,6 @@ static const struct blk_mq_ops ubiblock_
 	.init_request	= ubiblock_init_request,
 };
 
-static DEFINE_IDR(ubiblock_minor_idr);
-
 int ubiblock_create(struct ubi_volume_info *vi)
 {
 	struct ubiblock *dev;
@@ -365,14 +365,15 @@ int ubiblock_create(struct ubi_volume_in
 	/* Check that the volume isn't already handled */
 	mutex_lock(&devices_mutex);
 	if (find_dev_nolock(vi->ubi_num, vi->vol_id)) {
-		mutex_unlock(&devices_mutex);
-		return -EEXIST;
+		ret = -EEXIST;
+		goto out_unlock;
 	}
-	mutex_unlock(&devices_mutex);
 
 	dev = kzalloc(sizeof(struct ubiblock), GFP_KERNEL);
-	if (!dev)
-		return -ENOMEM;
+	if (!dev) {
+		ret = -ENOMEM;
+		goto out_unlock;
+	}
 
 	mutex_init(&dev->dev_mutex);
 
@@ -437,14 +438,13 @@ int ubiblock_create(struct ubi_volume_in
 		goto out_free_queue;
 	}
 
-	mutex_lock(&devices_mutex);
 	list_add_tail(&dev->list, &ubiblock_devices);
-	mutex_unlock(&devices_mutex);
 
 	/* Must be the last step: anyone can call file ops from now on */
 	add_disk(dev->gd);
 	dev_info(disk_to_dev(dev->gd), "created from ubi%d:%d(%s)",
 		 dev->ubi_num, dev->vol_id, vi->name);
+	mutex_unlock(&devices_mutex);
 	return 0;
 
 out_free_queue:
@@ -457,6 +457,8 @@ out_put_disk:
 	put_disk(dev->gd);
 out_free_dev:
 	kfree(dev);
+out_unlock:
+	mutex_unlock(&devices_mutex);
 
 	return ret;
 }
@@ -478,30 +480,36 @@ static void ubiblock_cleanup(struct ubib
 int ubiblock_remove(struct ubi_volume_info *vi)
 {
 	struct ubiblock *dev;
+	int ret;
 
 	mutex_lock(&devices_mutex);
 	dev = find_dev_nolock(vi->ubi_num, vi->vol_id);
 	if (!dev) {
-		mutex_unlock(&devices_mutex);
-		return -ENODEV;
+		ret = -ENODEV;
+		goto out_unlock;
 	}
 
 	/* Found a device, let's lock it so we can check if it's busy */
 	mutex_lock(&dev->dev_mutex);
 	if (dev->refcnt > 0) {
-		mutex_unlock(&dev->dev_mutex);
-		mutex_unlock(&devices_mutex);
-		return -EBUSY;
+		ret = -EBUSY;
+		goto out_unlock_dev;
 	}
 
 	/* Remove from device list */
 	list_del(&dev->list);
-	mutex_unlock(&devices_mutex);
-
 	ubiblock_cleanup(dev);
 	mutex_unlock(&dev->dev_mutex);
+	mutex_unlock(&devices_mutex);
+
 	kfree(dev);
 	return 0;
+
+out_unlock_dev:
+	mutex_unlock(&dev->dev_mutex);
+out_unlock:
+	mutex_unlock(&devices_mutex);
+	return ret;
 }
 
 static int ubiblock_resize(struct ubi_volume_info *vi)
@@ -630,6 +638,7 @@ static void ubiblock_remove_all(void)
 	struct ubiblock *next;
 	struct ubiblock *dev;
 
+	mutex_lock(&devices_mutex);
 	list_for_each_entry_safe(dev, next, &ubiblock_devices, list) {
 		/* The module is being forcefully removed */
 		WARN_ON(dev->desc);
@@ -638,6 +647,7 @@ static void ubiblock_remove_all(void)
 		ubiblock_cleanup(dev);
 		kfree(dev);
 	}
+	mutex_unlock(&devices_mutex);
 }
 
 int __init ubiblock_init(void)
author maintainer
#95 lore raw

PATCH 95/202 ubifs: free the encrypted symlink target

In reply to Greg Kroah-Hartman

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Eric Biggers <[email protected]>

commit 6b46d444146eb8d0b99562795cea8086639d7282 upstream.

ubifs_symlink() forgot to free the kmalloc()'ed buffer holding the encrypted symlink target, creating a memory leak. Fix it.

(UBIFS could actually encrypt directly into ui->data, removing the temporary buffer, but that is left for the patch that switches to use the symlink helper functions.)

Fixes ca7f85be8d6c ("ubifs: Add support for encrypted symlinks")
---
 fs/ubifs/dir.c |   10 ++++------
 1 file changed, 4 insertions(+), 6 deletions(-)
fs/ubifs/dir.c +4 -6
@@ -1216,10 +1216,8 @@ static int ubifs_symlink(struct inode *d
 		ostr.len = disk_link.len;
 
 		err = fscrypt_fname_usr_to_disk(inode, &istr, &ostr);
-		if (err) {
-			kfree(sd);
+		if (err)
 			goto out_inode;
-		}
 
 		sd->len = cpu_to_le16(ostr.len);
 		disk_link.name = (char *)sd;
@@ -1251,11 +1249,10 @@ static int ubifs_symlink(struct inode *d
 		goto out_cancel;
 	mutex_unlock(&dir_ui->ui_mutex);
 
-	ubifs_release_budget(c, &req);
 	insert_inode_hash(inode);
 	d_instantiate(dentry, inode);
-	fscrypt_free_filename(&nm);
-	return 0;
+	err = 0;
+	goto out_fname;
 
 out_cancel:
 	dir->i_size -= sz_change;
@@ -1268,6 +1265,7 @@ out_fname:
 	fscrypt_free_filename(&nm);
 out_budg:
 	ubifs_release_budget(c, &req);
+	kfree(sd);
 	return err;
 }
 
author maintainer
#96 lore raw

PATCH 96/202 nfs/pnfs: fix nfs_direct_req ref leak when i/o falls back to the mds

In reply to Greg Kroah-Hartman

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Scott Mayhew <[email protected]>

commit ba4a76f703ab7eb72941fdaac848502073d6e9ee upstream.

Currently when falling back to doing I/O through the MDS (via pnfs_{read|write}_through_mds), the client frees the nfs_pgio_header without releasing the reference taken on the dreq
via pnfs_generic_pg_{read|write}pages -> nfs_pgheader_init -> nfs_direct_pgio_init. It then takes another reference on the dreq via nfs_generic_pg_pgios -> nfs_pgheader_init -> nfs_direct_pgio_init and as a result the requester will become stuck in inode_dio_wait. Once that happens, other processes accessing the inode will become stuck as well.

Ensure that pnfs_read_through_mds() and pnfs_write_through_mds() clean up correctly by calling hdr->completion_ops->completion() instead of calling hdr->release() directly.

This can be reproduced (sometimes) by performing "storage failover takeover" commands on NetApp filer while doing direct I/O from a client.

This can also be reproduced using SystemTap to simulate a failure while doing direct I/O from a client (from Dave Wysochanski <[email protected]>):

stap -v -g -e 'probe module("nfs_layout_nfsv41_files").function("nfs4_fl_prepare_ds").return { $return=NULL; exit(); }'

Fixes 1ca018d28d ("pNFS: Fix a memory leak when attempted pnfs fails")
---
 fs/nfs/pnfs.c |    4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)
fs/nfs/pnfs.c +2 -2
@@ -2255,7 +2255,7 @@ pnfs_write_through_mds(struct nfs_pageio
 		nfs_pageio_reset_write_mds(desc);
 		mirror->pg_recoalesce = 1;
 	}
-	hdr->release(hdr);
+	hdr->completion_ops->completion(hdr);
 }
 
 static enum pnfs_try_status
@@ -2378,7 +2378,7 @@ pnfs_read_through_mds(struct nfs_pageio_
 		nfs_pageio_reset_read_mds(desc);
 		mirror->pg_recoalesce = 1;
 	}
-	hdr->release(hdr);
+	hdr->completion_ops->completion(hdr);
 }
 
 /*
author maintainer
#97 lore raw

PATCH 97/202 nfs41: do not return ENOMEM on LAYOUTUNAVAILABLE

In reply to Greg Kroah-Hartman

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Tigran Mkrtchyan <[email protected]>

commit 7ff4cff637aa0bd2abbd81f53b2a6206c50afd95 upstream.

A pNFS server may return LAYOUTUNAVAILABLE error on LAYOUTGET for files which don't have any layout. In this situation pnfs_update_layout currently returns NULL. As this NULL is converted into ENOMEM, IO requests fails instead of falling back to MDS.

Do not return ENOMEM on LAYOUTUNAVAILABLE and let client retry through MDS.

Fixes 8d40b0f14846f. I will suggest to backport this fix to affected stable branches.

[trondmy: Use IS_ERR_OR_NULL()]
Fixes 8d40b0f14846 ("NFS filelayout:call GETDEVICEINFO after...")
---
 fs/nfs/filelayout/filelayout.c |    4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)
fs/nfs/filelayout/filelayout.c +1 -3
@@ -895,9 +895,7 @@ fl_pnfs_update_layout(struct inode *ino,
 
 	lseg = pnfs_update_layout(ino, ctx, pos, count, iomode, strict_iomode,
 				  gfp_flags);
-	if (!lseg)
-		lseg = ERR_PTR(-ENOMEM);
-	if (IS_ERR(lseg))
+	if (IS_ERR_OR_NULL(lseg))
 		goto out;
 
 	lo = NFS_I(ino)->layout;
author maintainer
#98 lore raw

PATCH 98/202 NFS: Add a cond_resched() to nfs_commit_release_pages()

In reply to Greg Kroah-Hartman

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Trond Myklebust <[email protected]>

commit 7f1bda447c9bd48b415acedba6b830f61591601f upstream.

The commit list can get very large, and so we need a cond_resched() in nfs_commit_release_pages() in order to ensure we don't hog the CPU for excessive periods of time.

---
 fs/nfs/write.c |    2 ++
 1 file changed, 2 insertions(+)
fs/nfs/write.c +2 -0
@@ -1837,6 +1837,8 @@ static void nfs_commit_release_pages(str
 		set_bit(NFS_CONTEXT_RESEND_WRITES, &req->wb_context->flags);
 	next:
 		nfs_unlock_and_release_request(req);
+		/* Latency breaker */
+		cond_resched();
 	}
 	nfss = NFS_SERVER(data->inode);
 	if (atomic_long_read(&nfss->writeback) < NFS_CONGESTION_OFF_THRESH)
author maintainer
#99 lore raw

PATCH 99/202 NFS: Fix nfsstat breakage due to LOOKUPP

In reply to Greg Kroah-Hartman

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Trond Myklebust <[email protected]>

commit 8634ef5e05311f32d7f2aee06f6b27a8834a3bd6 upstream.

The LOOKUPP operation was inserted into the nfs4_procedures array rather than being appended, which put /proc/net/rpc/nfs out of whack, and broke the nfsstat utility.
Fix by moving the LOOKUPP operation to the end of the array, and by ensuring that it keeps the same length whether or not NFSV4.1 and NFSv4.2 are compiled in.

Fixes 5b5faaf6df734 ("nfs4: add NFSv4 LOOKUPP handlers")
---
 fs/nfs/nfs4xdr.c     |   64 ++++++++++++++++++++++++++++++---------------------
 include/linux/nfs4.h |   12 ++++++---
 2 files changed, 46 insertions(+), 30 deletions(-)
fs/nfs/nfs4xdr.c +38 -26
@@ -7678,6 +7678,22 @@ nfs4_stat_to_errno(int stat)
 	.p_name = #proc,	\
 }
 
+#if defined(CONFIG_NFS_V4_1)
+#define PROC41(proc, argtype, restype)				\
+	PROC(proc, argtype, restype)
+#else
+#define PROC41(proc, argtype, restype)				\
+	STUB(proc)
+#endif
+
+#if defined(CONFIG_NFS_V4_2)
+#define PROC42(proc, argtype, restype)				\
+	PROC(proc, argtype, restype)
+#else
+#define PROC42(proc, argtype, restype)				\
+	STUB(proc)
+#endif
+
 const struct rpc_procinfo nfs4_procedures[] = {
 	PROC(READ,		enc_read,		dec_read),
 	PROC(WRITE,		enc_write,		dec_write),
@@ -7698,7 +7714,6 @@ const struct rpc_procinfo nfs4_procedure
 	PROC(ACCESS,		enc_access,		dec_access),
 	PROC(GETATTR,		enc_getattr,		dec_getattr),
 	PROC(LOOKUP,		enc_lookup,		dec_lookup),
-	PROC(LOOKUPP,		enc_lookupp,		dec_lookupp),
 	PROC(LOOKUP_ROOT,	enc_lookup_root,	dec_lookup_root),
 	PROC(REMOVE,		enc_remove,		dec_remove),
 	PROC(RENAME,		enc_rename,		dec_rename),
@@ -7717,33 +7732,30 @@ const struct rpc_procinfo nfs4_procedure
 	PROC(RELEASE_LOCKOWNER,	enc_release_lockowner,	dec_release_lockowner),
 	PROC(SECINFO,		enc_secinfo,		dec_secinfo),
 	PROC(FSID_PRESENT,	enc_fsid_present,	dec_fsid_present),
-#if defined(CONFIG_NFS_V4_1)
-	PROC(EXCHANGE_ID,	enc_exchange_id,	dec_exchange_id),
-	PROC(CREATE_SESSION,	enc_create_session,	dec_create_session),
-	PROC(DESTROY_SESSION,	enc_destroy_session,	dec_destroy_session),
-	PROC(SEQUENCE,		enc_sequence,		dec_sequence),
-	PROC(GET_LEASE_TIME,	enc_get_lease_time,	dec_get_lease_time),
-	PROC(RECLAIM_COMPLETE,	enc_reclaim_complete,	dec_reclaim_complete),
-	PROC(GETDEVICEINFO,	enc_getdeviceinfo,	dec_getdeviceinfo),
-	PROC(LAYOUTGET,		enc_layoutget,		dec_layoutget),
-	PROC(LAYOUTCOMMIT,	enc_layoutcommit,	dec_layoutcommit),
-	PROC(LAYOUTRETURN,	enc_layoutreturn,	dec_layoutreturn),
-	PROC(SECINFO_NO_NAME,	enc_secinfo_no_name,	dec_secinfo_no_name),
-	PROC(TEST_STATEID,	enc_test_stateid,	dec_test_stateid),
-	PROC(FREE_STATEID,	enc_free_stateid,	dec_free_stateid),
+	PROC41(EXCHANGE_ID,	enc_exchange_id,	dec_exchange_id),
+	PROC41(CREATE_SESSION,	enc_create_session,	dec_create_session),
+	PROC41(DESTROY_SESSION,	enc_destroy_session,	dec_destroy_session),
+	PROC41(SEQUENCE,	enc_sequence,		dec_sequence),
+	PROC41(GET_LEASE_TIME,	enc_get_lease_time,	dec_get_lease_time),
+	PROC41(RECLAIM_COMPLETE,enc_reclaim_complete,	dec_reclaim_complete),
+	PROC41(GETDEVICEINFO,	enc_getdeviceinfo,	dec_getdeviceinfo),
+	PROC41(LAYOUTGET,	enc_layoutget,		dec_layoutget),
+	PROC41(LAYOUTCOMMIT,	enc_layoutcommit,	dec_layoutcommit),
+	PROC41(LAYOUTRETURN,	enc_layoutreturn,	dec_layoutreturn),
+	PROC41(SECINFO_NO_NAME,	enc_secinfo_no_name,	dec_secinfo_no_name),
+	PROC41(TEST_STATEID,	enc_test_stateid,	dec_test_stateid),
+	PROC41(FREE_STATEID,	enc_free_stateid,	dec_free_stateid),
 	STUB(GETDEVICELIST),
-	PROC(BIND_CONN_TO_SESSION,
+	PROC41(BIND_CONN_TO_SESSION,
 			enc_bind_conn_to_session, dec_bind_conn_to_session),
-	PROC(DESTROY_CLIENTID,	enc_destroy_clientid,	dec_destroy_clientid),
-#endif /* CONFIG_NFS_V4_1 */
-#ifdef CONFIG_NFS_V4_2
-	PROC(SEEK,		enc_seek,		dec_seek),
-	PROC(ALLOCATE,		enc_allocate,		dec_allocate),
-	PROC(DEALLOCATE,	enc_deallocate,		dec_deallocate),
-	PROC(LAYOUTSTATS,	enc_layoutstats,	dec_layoutstats),
-	PROC(CLONE,		enc_clone,		dec_clone),
-	PROC(COPY,		enc_copy,		dec_copy),
-#endif /* CONFIG_NFS_V4_2 */
+	PROC41(DESTROY_CLIENTID,enc_destroy_clientid,	dec_destroy_clientid),
+	PROC42(SEEK,		enc_seek,		dec_seek),
+	PROC42(ALLOCATE,	enc_allocate,		dec_allocate),
+	PROC42(DEALLOCATE,	enc_deallocate,		dec_deallocate),
+	PROC42(LAYOUTSTATS,	enc_layoutstats,	dec_layoutstats),
+	PROC42(CLONE,		enc_clone,		dec_clone),
+	PROC42(COPY,		enc_copy,		dec_copy),
+	PROC(LOOKUPP,		enc_lookupp,		dec_lookupp),
 };
 
 static unsigned int nfs_version4_counts[ARRAY_SIZE(nfs4_procedures)];
include/linux/nfs4.h +8 -4
@@ -457,7 +457,12 @@ enum lock_type4 {
 
 #define NFS4_DEBUG 1
 
-/* Index of predefined Linux client operations */
+/*
+ * Index of predefined Linux client operations
+ *
+ * To ensure that /proc/net/rpc/nfs remains correctly ordered, please
+ * append only to this enum when adding new client operations.
+ */
 
 enum {
 	NFSPROC4_CLNT_NULL = 0,		/* Unused */
@@ -480,7 +485,6 @@ enum {
 	NFSPROC4_CLNT_ACCESS,
 	NFSPROC4_CLNT_GETATTR,
 	NFSPROC4_CLNT_LOOKUP,
-	NFSPROC4_CLNT_LOOKUPP,
 	NFSPROC4_CLNT_LOOKUP_ROOT,
 	NFSPROC4_CLNT_REMOVE,
 	NFSPROC4_CLNT_RENAME,
@@ -500,7 +504,6 @@ enum {
 	NFSPROC4_CLNT_SECINFO,
 	NFSPROC4_CLNT_FSID_PRESENT,
 
-	/* nfs41 */
 	NFSPROC4_CLNT_EXCHANGE_ID,
 	NFSPROC4_CLNT_CREATE_SESSION,
 	NFSPROC4_CLNT_DESTROY_SESSION,
@@ -518,13 +521,14 @@ enum {
 	NFSPROC4_CLNT_BIND_CONN_TO_SESSION,
 	NFSPROC4_CLNT_DESTROY_CLIENTID,
 
-	/* nfs42 */
 	NFSPROC4_CLNT_SEEK,
 	NFSPROC4_CLNT_ALLOCATE,
 	NFSPROC4_CLNT_DEALLOCATE,
 	NFSPROC4_CLNT_LAYOUTSTATS,
 	NFSPROC4_CLNT_CLONE,
 	NFSPROC4_CLNT_COPY,
+
+	NFSPROC4_CLNT_LOOKUPP,
 };
 
 /* nfs41 types */
author maintainer
#100 lore raw

PATCH 100/202 NFS: commit direct writes even if they fail partially

In reply to Greg Kroah-Hartman

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: J. Bruce Fields <[email protected]>

commit 1b8d97b0a837beaf48a8449955b52c650a7114b4 upstream.

If some of the WRITE calls making up an O_DIRECT write syscall fail, we neglect to commit, even if some of the WRITEs succeed.

We also depend on the commit code to free the reference count on the nfs_page taken in the "if (request_commit)" case at the end of nfs_direct_write_completion(). The problem was originally noticed because ENOSPC's encountered partway through a write would result in a closed file being sillyrenamed when it should have been unlinked.

---
 fs/nfs/direct.c |    4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)
fs/nfs/direct.c +1 -3
@@ -775,10 +775,8 @@ static void nfs_direct_write_completion(
 
 	spin_lock(&dreq->lock);
 
-	if (test_bit(NFS_IOHDR_ERROR, &hdr->flags)) {
-		dreq->flags = 0;
+	if (test_bit(NFS_IOHDR_ERROR, &hdr->flags))
 		dreq->error = hdr->error;
-	}
 	if (dreq->error == 0) {
 		nfs_direct_good_bytes(dreq, hdr);
 		if (nfs_write_need_commit(hdr)) {
author maintainer
#101 lore raw

PATCH 101/202 NFS: reject request for id_legacy key without auxdata

In reply to Greg Kroah-Hartman

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Eric Biggers <[email protected]>

commit 49686cbbb3ebafe42e63868222f269d8053ead00 upstream.

nfs_idmap_legacy_upcall() is supposed to be called with 'aux' pointing to a 'struct idmap', via the call to request_key_with_auxdata() in nfs_idmap_request_key().

However it can also be reached via the request_key() system call in which case 'aux' will be NULL, causing a NULL pointer dereference in nfs_idmap_prepare_pipe_upcall(), assuming that the key description is valid enough to get that far.

Fix this by making nfs_idmap_legacy_upcall() negate the key if no auxdata is provided.

As usual, this bug was found by syzkaller. A simple reproducer using the command-line keyctl program is:

keyctl request2 id_legacy uid:0 '' @s

Fixes 57e62324e469 ("NFS: Store the legacy idmapper result in the keyring")
Reported-by [email protected]
---
 fs/nfs/nfs4idmap.c |    6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)
fs/nfs/nfs4idmap.c +5 -1
@@ -568,9 +568,13 @@ static int nfs_idmap_legacy_upcall(struc
 	struct idmap_msg *im;
 	struct idmap *idmap = (struct idmap *)aux;
 	struct key *key = cons->key;
-	int ret = -ENOMEM;
+	int ret = -ENOKEY;
+
+	if (!aux)
+		goto out1;
 
 	/* msg and im are freed in idmap_pipe_destroy_msg */
+	ret = -ENOMEM;
 	data = kzalloc(sizeof(*data), GFP_KERNEL);
 	if (!data)
 		goto out1;
author maintainer
#102 lore raw

PATCH 102/202 NFS: Fix a race between mmap() and O_DIRECT

In reply to Greg Kroah-Hartman

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Trond Myklebust <[email protected]>

commit e231c6879cfd44e4fffd384bb6dd7d313249a523 upstream.

When locking the file in order to do O_DIRECT on it, we must unmap any mmapped ranges on the pagecache so that we can flush out the dirty data.

Fixes a5864c999de67 ("NFS: Do not serialise O_DIRECT reads and writes")
---
 fs/nfs/io.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
fs/nfs/io.c +1 -1
@@ -99,7 +99,7 @@ static void nfs_block_buffered(struct nf
 {
 	if (!test_bit(NFS_INO_ODIRECT, &nfsi->flags)) {
 		set_bit(NFS_INO_ODIRECT, &nfsi->flags);
-		nfs_wb_all(inode);
+		nfs_sync_mapping(inode->i_mapping);
 	}
 }
 
author maintainer
#103 lore raw

PATCH 103/202 nfsd: Detect unhashed stids in nfsd4_verify_open_stid()

In reply to Greg Kroah-Hartman

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Trond Myklebust <[email protected]>

commit 4f1764172a0aa7395d12b96cae640ca1438c5085 upstream.

The state of the stid is guaranteed by 2 locks:
- The nfs4_client 'cl_lock' spinlock
- The nfs4_ol_stateid 'st_mutex' mutex

so it is quite possible for the stid to be unhashed after lookup, but before calling nfsd4_lock_ol_stateid(). So we do need to check for a zero value for 'sc_type' in nfsd4_verify_open_stid().

Fixes 659aefb68eca "nfsd: Ensure we don't recognise lock stateids..."
---
 fs/nfsd/nfs4state.c |    1 +
 1 file changed, 1 insertion(+)
fs/nfsd/nfs4state.c +1 -0
@@ -3590,6 +3590,7 @@ nfsd4_verify_open_stid(struct nfs4_stid
 	switch (s->sc_type) {
 	default:
 		break;
+	case 0:
 	case NFS4_CLOSED_STID:
 	case NFS4_CLOSED_DELEG_STID:
 		ret = nfserr_bad_stateid;
author maintainer
#104 lore raw

PATCH 104/202 kernfs: fix regression in kernfs_fop_write caused by wrong type

In reply to Greg Kroah-Hartman

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Ivan Vecera <[email protected]>

commit ba87977a49913129962af8ac35b0e13e0fa4382d upstream.

Commit b7ce40cff0b9 ("kernfs: cache atomic_write_len in kernfs_open_file") changes type of local variable 'len' from ssize_t to size_t. This change caused that the *ppos value is updated also when the previous write callback failed.

Mentioned snippet:
...
len = ops->write(...); <- return value can be negative
...
if (len > 0) <- true here in this case

        *ppos += len;

...

Fixes b7ce40cff0b9 ("kernfs: cache atomic_write_len in kernfs_open_file")
---
 fs/kernfs/file.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
fs/kernfs/file.c +1 -1
@@ -275,7 +275,7 @@ static ssize_t kernfs_fop_write(struct f
 {
 	struct kernfs_open_file *of = kernfs_of(file);
 	const struct kernfs_ops *ops;
-	size_t len;
+	ssize_t len;
 	char *buf;
 
 	if (of->atomic_write_len) {
author maintainer
#105 lore raw

PATCH 105/202 ahci: Annotate PCI ids for mobile Intel chipsets as such

In reply to Greg Kroah-Hartman

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Hans de Goede <[email protected]>

commit ca1b4974bd237f2373b0e980b11957aac3499b56 upstream.

Intel uses different SATA PCI ids for the Desktop and Mobile SKUs of their chipsets. For older models the comment describing which chipset the PCI id is for, aksi indicates when we're dealing with a mobile SKU. Extend the comments for recent chipsets to also indicate mobile SKUs.

The information this commit adds comes from Intel's chipset datasheets.

This commit is a preparation patch for allowing a different default sata link powermanagement policy for mobile chipsets.

---
 drivers/ata/ahci.c |   32 ++++++++++++++++----------------
 1 file changed, 16 insertions(+), 16 deletions(-)
drivers/ata/ahci.c +16 -16
@@ -268,9 +268,9 @@ static const struct pci_device_id ahci_p
 	{ PCI_VDEVICE(INTEL, 0x3b23), board_ahci }, /* PCH AHCI */
 	{ PCI_VDEVICE(INTEL, 0x3b24), board_ahci }, /* PCH RAID */
 	{ PCI_VDEVICE(INTEL, 0x3b25), board_ahci }, /* PCH RAID */
-	{ PCI_VDEVICE(INTEL, 0x3b29), board_ahci }, /* PCH AHCI */
+	{ PCI_VDEVICE(INTEL, 0x3b29), board_ahci }, /* PCH M AHCI */
 	{ PCI_VDEVICE(INTEL, 0x3b2b), board_ahci }, /* PCH RAID */
-	{ PCI_VDEVICE(INTEL, 0x3b2c), board_ahci }, /* PCH RAID */
+	{ PCI_VDEVICE(INTEL, 0x3b2c), board_ahci }, /* PCH M RAID */
 	{ PCI_VDEVICE(INTEL, 0x3b2f), board_ahci }, /* PCH AHCI */
 	{ PCI_VDEVICE(INTEL, 0x19b0), board_ahci }, /* DNV AHCI */
 	{ PCI_VDEVICE(INTEL, 0x19b1), board_ahci }, /* DNV AHCI */
@@ -293,9 +293,9 @@ static const struct pci_device_id ahci_p
 	{ PCI_VDEVICE(INTEL, 0x19cE), board_ahci }, /* DNV AHCI */
 	{ PCI_VDEVICE(INTEL, 0x19cF), board_ahci }, /* DNV AHCI */
 	{ PCI_VDEVICE(INTEL, 0x1c02), board_ahci }, /* CPT AHCI */
-	{ PCI_VDEVICE(INTEL, 0x1c03), board_ahci }, /* CPT AHCI */
+	{ PCI_VDEVICE(INTEL, 0x1c03), board_ahci }, /* CPT M AHCI */
 	{ PCI_VDEVICE(INTEL, 0x1c04), board_ahci }, /* CPT RAID */
-	{ PCI_VDEVICE(INTEL, 0x1c05), board_ahci }, /* CPT RAID */
+	{ PCI_VDEVICE(INTEL, 0x1c05), board_ahci }, /* CPT M RAID */
 	{ PCI_VDEVICE(INTEL, 0x1c06), board_ahci }, /* CPT RAID */
 	{ PCI_VDEVICE(INTEL, 0x1c07), board_ahci }, /* CPT RAID */
 	{ PCI_VDEVICE(INTEL, 0x1d02), board_ahci }, /* PBG AHCI */
@@ -304,20 +304,20 @@ static const struct pci_device_id ahci_p
 	{ PCI_VDEVICE(INTEL, 0x2826), board_ahci }, /* PBG RAID */
 	{ PCI_VDEVICE(INTEL, 0x2323), board_ahci }, /* DH89xxCC AHCI */
 	{ PCI_VDEVICE(INTEL, 0x1e02), board_ahci }, /* Panther Point AHCI */
-	{ PCI_VDEVICE(INTEL, 0x1e03), board_ahci }, /* Panther Point AHCI */
+	{ PCI_VDEVICE(INTEL, 0x1e03), board_ahci }, /* Panther Point M AHCI */
 	{ PCI_VDEVICE(INTEL, 0x1e04), board_ahci }, /* Panther Point RAID */
 	{ PCI_VDEVICE(INTEL, 0x1e05), board_ahci }, /* Panther Point RAID */
 	{ PCI_VDEVICE(INTEL, 0x1e06), board_ahci }, /* Panther Point RAID */
-	{ PCI_VDEVICE(INTEL, 0x1e07), board_ahci }, /* Panther Point RAID */
+	{ PCI_VDEVICE(INTEL, 0x1e07), board_ahci }, /* Panther Point M RAID */
 	{ PCI_VDEVICE(INTEL, 0x1e0e), board_ahci }, /* Panther Point RAID */
 	{ PCI_VDEVICE(INTEL, 0x8c02), board_ahci }, /* Lynx Point AHCI */
-	{ PCI_VDEVICE(INTEL, 0x8c03), board_ahci }, /* Lynx Point AHCI */
+	{ PCI_VDEVICE(INTEL, 0x8c03), board_ahci }, /* Lynx Point M AHCI */
 	{ PCI_VDEVICE(INTEL, 0x8c04), board_ahci }, /* Lynx Point RAID */
-	{ PCI_VDEVICE(INTEL, 0x8c05), board_ahci }, /* Lynx Point RAID */
+	{ PCI_VDEVICE(INTEL, 0x8c05), board_ahci }, /* Lynx Point M RAID */
 	{ PCI_VDEVICE(INTEL, 0x8c06), board_ahci }, /* Lynx Point RAID */
-	{ PCI_VDEVICE(INTEL, 0x8c07), board_ahci }, /* Lynx Point RAID */
+	{ PCI_VDEVICE(INTEL, 0x8c07), board_ahci }, /* Lynx Point M RAID */
 	{ PCI_VDEVICE(INTEL, 0x8c0e), board_ahci }, /* Lynx Point RAID */
-	{ PCI_VDEVICE(INTEL, 0x8c0f), board_ahci }, /* Lynx Point RAID */
+	{ PCI_VDEVICE(INTEL, 0x8c0f), board_ahci }, /* Lynx Point M RAID */
 	{ PCI_VDEVICE(INTEL, 0x9c02), board_ahci }, /* Lynx Point-LP AHCI */
 	{ PCI_VDEVICE(INTEL, 0x9c03), board_ahci }, /* Lynx Point-LP AHCI */
 	{ PCI_VDEVICE(INTEL, 0x9c04), board_ahci }, /* Lynx Point-LP RAID */
@@ -358,21 +358,21 @@ static const struct pci_device_id ahci_p
 	{ PCI_VDEVICE(INTEL, 0x9c87), board_ahci }, /* Wildcat Point-LP RAID */
 	{ PCI_VDEVICE(INTEL, 0x9c8f), board_ahci }, /* Wildcat Point-LP RAID */
 	{ PCI_VDEVICE(INTEL, 0x8c82), board_ahci }, /* 9 Series AHCI */
-	{ PCI_VDEVICE(INTEL, 0x8c83), board_ahci }, /* 9 Series AHCI */
+	{ PCI_VDEVICE(INTEL, 0x8c83), board_ahci }, /* 9 Series M AHCI */
 	{ PCI_VDEVICE(INTEL, 0x8c84), board_ahci }, /* 9 Series RAID */
-	{ PCI_VDEVICE(INTEL, 0x8c85), board_ahci }, /* 9 Series RAID */
+	{ PCI_VDEVICE(INTEL, 0x8c85), board_ahci }, /* 9 Series M RAID */
 	{ PCI_VDEVICE(INTEL, 0x8c86), board_ahci }, /* 9 Series RAID */
-	{ PCI_VDEVICE(INTEL, 0x8c87), board_ahci }, /* 9 Series RAID */
+	{ PCI_VDEVICE(INTEL, 0x8c87), board_ahci }, /* 9 Series M RAID */
 	{ PCI_VDEVICE(INTEL, 0x8c8e), board_ahci }, /* 9 Series RAID */
-	{ PCI_VDEVICE(INTEL, 0x8c8f), board_ahci }, /* 9 Series RAID */
+	{ PCI_VDEVICE(INTEL, 0x8c8f), board_ahci }, /* 9 Series M RAID */
 	{ PCI_VDEVICE(INTEL, 0x9d03), board_ahci }, /* Sunrise Point-LP AHCI */
 	{ PCI_VDEVICE(INTEL, 0x9d05), board_ahci }, /* Sunrise Point-LP RAID */
 	{ PCI_VDEVICE(INTEL, 0x9d07), board_ahci }, /* Sunrise Point-LP RAID */
 	{ PCI_VDEVICE(INTEL, 0xa102), board_ahci }, /* Sunrise Point-H AHCI */
-	{ PCI_VDEVICE(INTEL, 0xa103), board_ahci }, /* Sunrise Point-H AHCI */
+	{ PCI_VDEVICE(INTEL, 0xa103), board_ahci }, /* Sunrise Point-H M AHCI */
 	{ PCI_VDEVICE(INTEL, 0xa105), board_ahci }, /* Sunrise Point-H RAID */
 	{ PCI_VDEVICE(INTEL, 0xa106), board_ahci }, /* Sunrise Point-H RAID */
-	{ PCI_VDEVICE(INTEL, 0xa107), board_ahci }, /* Sunrise Point-H RAID */
+	{ PCI_VDEVICE(INTEL, 0xa107), board_ahci }, /* Sunrise Point-H M RAID */
 	{ PCI_VDEVICE(INTEL, 0xa10f), board_ahci }, /* Sunrise Point-H RAID */
 	{ PCI_VDEVICE(INTEL, 0x2822), board_ahci }, /* Lewisburg RAID*/
 	{ PCI_VDEVICE(INTEL, 0x2823), board_ahci }, /* Lewisburg AHCI*/
author maintainer
#106 lore raw

PATCH 106/202 ahci: Add PCI ids for Intel Bay Trail, Cherry Trail and Apollo Lake AHCI

In reply to Greg Kroah-Hartman

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Hans de Goede <[email protected]>

commit 998008b779e424bd7513c434d0ab9c1268459009 upstream.

Add PCI ids for Intel Bay Trail, Cherry Trail and Apollo Lake AHCI SATA controllers. This commit is a preparation patch for allowing a different default sata link powermanagement policy for mobile chipsets.

---
 drivers/ata/ahci.c |    4 ++++
 1 file changed, 4 insertions(+)
drivers/ata/ahci.c +4 -0
@@ -386,6 +386,10 @@ static const struct pci_device_id ahci_p
 	{ PCI_VDEVICE(INTEL, 0xa206), board_ahci }, /* Lewisburg RAID*/
 	{ PCI_VDEVICE(INTEL, 0xa252), board_ahci }, /* Lewisburg RAID*/
 	{ PCI_VDEVICE(INTEL, 0xa256), board_ahci }, /* Lewisburg RAID*/
+	{ PCI_VDEVICE(INTEL, 0x0f22), board_ahci }, /* Bay Trail AHCI */
+	{ PCI_VDEVICE(INTEL, 0x0f23), board_ahci }, /* Bay Trail AHCI */
+	{ PCI_VDEVICE(INTEL, 0x22a3), board_ahci }, /* Cherry Trail AHCI */
+	{ PCI_VDEVICE(INTEL, 0x5ae3), board_ahci }, /* Apollo Lake AHCI */
 
 	/* JMicron 360/1/3/5/6, match class to avoid IDE function */
 	{ PCI_VENDOR_ID_JMICRON, PCI_ANY_ID, PCI_ANY_ID, PCI_ANY_ID,
author maintainer
#107 lore raw

PATCH 107/202 ahci: Add Intel Cannon Lake PCH-H PCI ID

In reply to Greg Kroah-Hartman

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Mika Westerberg <[email protected]>

commit f919dde0772a894c693a1eeabc77df69d6a9b937 upstream.

Add Intel Cannon Lake PCH-H PCI ID to the list of supported controllers.

---
 drivers/ata/ahci.c |    1 +
 1 file changed, 1 insertion(+)
drivers/ata/ahci.c +1 -0
@@ -386,6 +386,7 @@ static const struct pci_device_id ahci_p
 	{ PCI_VDEVICE(INTEL, 0xa206), board_ahci }, /* Lewisburg RAID*/
 	{ PCI_VDEVICE(INTEL, 0xa252), board_ahci }, /* Lewisburg RAID*/
 	{ PCI_VDEVICE(INTEL, 0xa256), board_ahci }, /* Lewisburg RAID*/
+	{ PCI_VDEVICE(INTEL, 0xa356), board_ahci }, /* Cannon Lake PCH-H RAID */
 	{ PCI_VDEVICE(INTEL, 0x0f22), board_ahci }, /* Bay Trail AHCI */
 	{ PCI_VDEVICE(INTEL, 0x0f23), board_ahci }, /* Bay Trail AHCI */
 	{ PCI_VDEVICE(INTEL, 0x22a3), board_ahci }, /* Cherry Trail AHCI */
author maintainer
#108 lore raw

PATCH 108/202 crypto: hash - introduce crypto_hash_alg_has_setkey()

In reply to Greg Kroah-Hartman

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Eric Biggers <[email protected]>

commit cd6ed77ad5d223dc6299fb58f62e0f5267f7e2ba upstream.

Templates that use an shash spawn can use crypto_shash_alg_has_setkey() to determine whether the underlying algorithm requires a key or not. But there was no corresponding function for ahash spawns. Add it.

Note that the new function actually has to support both shash and ahash algorithms, since the ahash API can be used with either.

---
 crypto/ahash.c                 |   11 +++++++++++
 include/crypto/internal/hash.h |    2 ++
 2 files changed, 13 insertions(+)
crypto/ahash.c +11 -0
@@ -649,5 +649,16 @@ struct hash_alg_common *ahash_attr_alg(s
 }
 EXPORT_SYMBOL_GPL(ahash_attr_alg);
 
+bool crypto_hash_alg_has_setkey(struct hash_alg_common *halg)
+{
+	struct crypto_alg *alg = &halg->base;
+
+	if (alg->cra_type != &crypto_ahash_type)
+		return crypto_shash_alg_has_setkey(__crypto_shash_alg(alg));
+
+	return __crypto_ahash_alg(alg)->setkey != NULL;
+}
+EXPORT_SYMBOL_GPL(crypto_hash_alg_has_setkey);
+
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("Asynchronous cryptographic hash type");
include/crypto/internal/hash.h +2 -0
@@ -90,6 +90,8 @@ static inline bool crypto_shash_alg_has_
 	return alg->setkey != shash_no_setkey;
 }
 
+bool crypto_hash_alg_has_setkey(struct hash_alg_common *halg);
+
 int crypto_init_ahash_spawn(struct crypto_ahash_spawn *spawn,
 			    struct hash_alg_common *alg,
 			    struct crypto_instance *inst);
author maintainer
#109 lore raw

PATCH 109/202 crypto: cryptd - pass through absence of ->setkey()

In reply to Greg Kroah-Hartman

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Eric Biggers <[email protected]>

commit 841a3ff329713f796a63356fef6e2f72e4a3f6a3 upstream.

When the cryptd template is used to wrap an unkeyed hash algorithm, don't install a ->setkey() method to the cryptd instance. This change is necessary for cryptd to keep working with unkeyed hash algorithms once we start enforcing that ->setkey() is called when present.

---
 crypto/cryptd.c |    3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)
crypto/cryptd.c +2 -1
@@ -911,7 +911,8 @@ static int cryptd_create_hash(struct cry
 	inst->alg.finup  = cryptd_hash_finup_enqueue;
 	inst->alg.export = cryptd_hash_export;
 	inst->alg.import = cryptd_hash_import;
-	inst->alg.setkey = cryptd_hash_setkey;
+	if (crypto_shash_alg_has_setkey(salg))
+		inst->alg.setkey = cryptd_hash_setkey;
 	inst->alg.digest = cryptd_hash_digest_enqueue;
 
 	err = ahash_register_instance(tmpl, inst);
author maintainer
#110 lore raw

PATCH 110/202 crypto: mcryptd - pass through absence of ->setkey()

In reply to Greg Kroah-Hartman

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Eric Biggers <[email protected]>

commit fa59b92d299f2787e6bae1ff078ee0982e80211f upstream.

When the mcryptd template is used to wrap an unkeyed hash algorithm, don't install a ->setkey() method to the mcryptd instance. This change is necessary for mcryptd to keep working with unkeyed hash algorithms once we start enforcing that ->setkey() is called when present.

---
 crypto/mcryptd.c |    3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)
crypto/mcryptd.c +2 -1
@@ -535,7 +535,8 @@ static int mcryptd_create_hash(struct cr
 	inst->alg.finup  = mcryptd_hash_finup_enqueue;
 	inst->alg.export = mcryptd_hash_export;
 	inst->alg.import = mcryptd_hash_import;
-	inst->alg.setkey = mcryptd_hash_setkey;
+	if (crypto_hash_alg_has_setkey(halg))
+		inst->alg.setkey = mcryptd_hash_setkey;
 	inst->alg.digest = mcryptd_hash_digest_enqueue;
 
 	err = ahash_register_instance(tmpl, inst);
author maintainer
#111 lore raw

PATCH 111/202 crypto: poly1305 - remove ->setkey() method

In reply to Greg Kroah-Hartman

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Eric Biggers <[email protected]>

commit a16e772e664b9a261424107784804cffc8894977 upstream.

Since Poly1305 requires a nonce per invocation, the Linux kernel implementations of Poly1305 don't use the crypto API's keying mechanism and instead expect the key and nonce as the first 32 bytes of the data. But ->setkey() is still defined as a stub returning an error code. This prevents Poly1305 from being used through AF_ALG and will also break it completely once we start enforcing that all crypto API users (not just AF_ALG) call ->setkey() if present.

Fix it by removing crypto_poly1305_setkey(), leaving ->setkey as NULL.

---
 arch/x86/crypto/poly1305_glue.c |    1 -
 crypto/poly1305_generic.c       |   17 +++++------------
 include/crypto/poly1305.h       |    2 --
 3 files changed, 5 insertions(+), 15 deletions(-)
arch/x86/crypto/poly1305_glue.c +0 -1
@@ -164,7 +164,6 @@ static struct shash_alg alg = {
 	.init		= poly1305_simd_init,
 	.update		= poly1305_simd_update,
 	.final		= crypto_poly1305_final,
-	.setkey		= crypto_poly1305_setkey,
 	.descsize	= sizeof(struct poly1305_simd_desc_ctx),
 	.base		= {
 		.cra_name		= "poly1305",
crypto/poly1305_generic.c +5 -12
@@ -47,17 +47,6 @@ int crypto_poly1305_init(struct shash_de
 }
 EXPORT_SYMBOL_GPL(crypto_poly1305_init);
 
-int crypto_poly1305_setkey(struct crypto_shash *tfm,
-			   const u8 *key, unsigned int keylen)
-{
-	/* Poly1305 requires a unique key for each tag, which implies that
-	 * we can't set it on the tfm that gets accessed by multiple users
-	 * simultaneously. Instead we expect the key as the first 32 bytes in
-	 * the update() call. */
-	return -ENOTSUPP;
-}
-EXPORT_SYMBOL_GPL(crypto_poly1305_setkey);
-
 static void poly1305_setrkey(struct poly1305_desc_ctx *dctx, const u8 *key)
 {
 	/* r &= 0xffffffc0ffffffc0ffffffc0fffffff */
@@ -76,6 +65,11 @@ static void poly1305_setskey(struct poly
 	dctx->s[3] = get_unaligned_le32(key + 12);
 }
 
+/*
+ * Poly1305 requires a unique key for each tag, which implies that we can't set
+ * it on the tfm that gets accessed by multiple users simultaneously. Instead we
+ * expect the key as the first 32 bytes in the update() call.
+ */
 unsigned int crypto_poly1305_setdesckey(struct poly1305_desc_ctx *dctx,
 					const u8 *src, unsigned int srclen)
 {
@@ -281,7 +275,6 @@ static struct shash_alg poly1305_alg = {
 	.init		= crypto_poly1305_init,
 	.update		= crypto_poly1305_update,
 	.final		= crypto_poly1305_final,
-	.setkey		= crypto_poly1305_setkey,
 	.descsize	= sizeof(struct poly1305_desc_ctx),
 	.base		= {
 		.cra_name		= "poly1305",
include/crypto/poly1305.h +0 -2
@@ -31,8 +31,6 @@ struct poly1305_desc_ctx {
 };
 
 int crypto_poly1305_init(struct shash_desc *desc);
-int crypto_poly1305_setkey(struct crypto_shash *tfm,
-			   const u8 *key, unsigned int keylen);
 unsigned int crypto_poly1305_setdesckey(struct poly1305_desc_ctx *dctx,
 					const u8 *src, unsigned int srclen);
 int crypto_poly1305_update(struct shash_desc *desc,
author maintainer
#112 lore raw

PATCH 112/202 crypto: hash - annotate algorithms taking optional key

In reply to Greg Kroah-Hartman

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Eric Biggers <[email protected]>

commit a208fa8f33031b9e0aba44c7d1b7e68eb0cbd29e upstream.

We need to consistently enforce that keyed hashes cannot be used without setting the key. To do this we need a reliable way to determine whether a given hash algorithm is keyed or not. AF_ALG currently does this by checking for the presence of a ->setkey() method. However, this is actually slightly broken because the CRC-32 algorithms implement ->setkey() but can also be used without a key. (The CRC-32 "key" is not actually a cryptographic key but rather represents the initial state. If not overridden, then a default initial state is used.)

Prepare to fix this by introducing a flag CRYPTO_ALG_OPTIONAL_KEY which indicates that the algorithm has a ->setkey() method, but it is not required to be called. Then set it on all the CRC-32 algorithms.

The same also applies to the Adler-32 implementation in Lustre.

Also, the cryptd and mcryptd templates have to pass through the flag from their underlying algorithm.

---
 arch/arm/crypto/crc32-ce-glue.c                               |    2 ++
 arch/arm64/crypto/crc32-ce-glue.c                             |    2 ++
 arch/powerpc/crypto/crc32c-vpmsum_glue.c                      |    1 +
 arch/s390/crypto/crc32-vx.c                                   |    3 +++
 arch/sparc/crypto/crc32c_glue.c                               |    1 +
 arch/x86/crypto/crc32-pclmul_glue.c                           |    1 +
 arch/x86/crypto/crc32c-intel_glue.c                           |    1 +
 crypto/crc32_generic.c                                        |    1 +
 crypto/crc32c_generic.c                                       |    1 +
 crypto/cryptd.c                                               |    7 +++----
 crypto/mcryptd.c                                              |    7 +++----
 drivers/crypto/bfin_crc.c                                     |    3 ++-
 drivers/crypto/stm32/stm32_crc32.c                            |    2 ++
 drivers/staging/lustre/lnet/libcfs/linux/linux-crypto-adler.c |    1 +
 include/linux/crypto.h                                        |    6 ++++++
 15 files changed, 30 insertions(+), 9 deletions(-)
arch/arm/crypto/crc32-ce-glue.c +2 -0
@@ -188,6 +188,7 @@ static struct shash_alg crc32_pmull_algs
 	.base.cra_name		= "crc32",
 	.base.cra_driver_name	= "crc32-arm-ce",
 	.base.cra_priority	= 200,
+	.base.cra_flags		= CRYPTO_ALG_OPTIONAL_KEY,
 	.base.cra_blocksize	= 1,
 	.base.cra_module	= THIS_MODULE,
 }, {
@@ -203,6 +204,7 @@ static struct shash_alg crc32_pmull_algs
 	.base.cra_name		= "crc32c",
 	.base.cra_driver_name	= "crc32c-arm-ce",
 	.base.cra_priority	= 200,
+	.base.cra_flags		= CRYPTO_ALG_OPTIONAL_KEY,
 	.base.cra_blocksize	= 1,
 	.base.cra_module	= THIS_MODULE,
 } };
arch/arm64/crypto/crc32-ce-glue.c +2 -0
@@ -185,6 +185,7 @@ static struct shash_alg crc32_pmull_algs
 	.base.cra_name		= "crc32",
 	.base.cra_driver_name	= "crc32-arm64-ce",
 	.base.cra_priority	= 200,
+	.base.cra_flags		= CRYPTO_ALG_OPTIONAL_KEY,
 	.base.cra_blocksize	= 1,
 	.base.cra_module	= THIS_MODULE,
 }, {
@@ -200,6 +201,7 @@ static struct shash_alg crc32_pmull_algs
 	.base.cra_name		= "crc32c",
 	.base.cra_driver_name	= "crc32c-arm64-ce",
 	.base.cra_priority	= 200,
+	.base.cra_flags		= CRYPTO_ALG_OPTIONAL_KEY,
 	.base.cra_blocksize	= 1,
 	.base.cra_module	= THIS_MODULE,
 } };
arch/powerpc/crypto/crc32c-vpmsum_glue.c +1 -0
@@ -141,6 +141,7 @@ static struct shash_alg alg = {
 		.cra_name		= "crc32c",
 		.cra_driver_name	= "crc32c-vpmsum",
 		.cra_priority		= 200,
+		.cra_flags		= CRYPTO_ALG_OPTIONAL_KEY,
 		.cra_blocksize		= CHKSUM_BLOCK_SIZE,
 		.cra_ctxsize		= sizeof(u32),
 		.cra_module		= THIS_MODULE,
arch/s390/crypto/crc32-vx.c +3 -0
@@ -239,6 +239,7 @@ static struct shash_alg crc32_vx_algs[]
 			.cra_name	 = "crc32",
 			.cra_driver_name = "crc32-vx",
 			.cra_priority	 = 200,
+			.cra_flags	 = CRYPTO_ALG_OPTIONAL_KEY,
 			.cra_blocksize	 = CRC32_BLOCK_SIZE,
 			.cra_ctxsize	 = sizeof(struct crc_ctx),
 			.cra_module	 = THIS_MODULE,
@@ -259,6 +260,7 @@ static struct shash_alg crc32_vx_algs[]
 			.cra_name	 = "crc32be",
 			.cra_driver_name = "crc32be-vx",
 			.cra_priority	 = 200,
+			.cra_flags	 = CRYPTO_ALG_OPTIONAL_KEY,
 			.cra_blocksize	 = CRC32_BLOCK_SIZE,
 			.cra_ctxsize	 = sizeof(struct crc_ctx),
 			.cra_module	 = THIS_MODULE,
@@ -279,6 +281,7 @@ static struct shash_alg crc32_vx_algs[]
 			.cra_name	 = "crc32c",
 			.cra_driver_name = "crc32c-vx",
 			.cra_priority	 = 200,
+			.cra_flags	 = CRYPTO_ALG_OPTIONAL_KEY,
 			.cra_blocksize	 = CRC32_BLOCK_SIZE,
 			.cra_ctxsize	 = sizeof(struct crc_ctx),
 			.cra_module	 = THIS_MODULE,
arch/sparc/crypto/crc32c_glue.c +1 -0
@@ -133,6 +133,7 @@ static struct shash_alg alg = {
 		.cra_name		=	"crc32c",
 		.cra_driver_name	=	"crc32c-sparc64",
 		.cra_priority		=	SPARC_CR_OPCODE_PRIORITY,
+		.cra_flags		=	CRYPTO_ALG_OPTIONAL_KEY,
 		.cra_blocksize		=	CHKSUM_BLOCK_SIZE,
 		.cra_ctxsize		=	sizeof(u32),
 		.cra_alignmask		=	7,
arch/x86/crypto/crc32-pclmul_glue.c +1 -0
@@ -162,6 +162,7 @@ static struct shash_alg alg = {
 			.cra_name		= "crc32",
 			.cra_driver_name	= "crc32-pclmul",
 			.cra_priority		= 200,
+			.cra_flags		= CRYPTO_ALG_OPTIONAL_KEY,
 			.cra_blocksize		= CHKSUM_BLOCK_SIZE,
 			.cra_ctxsize		= sizeof(u32),
 			.cra_module		= THIS_MODULE,
arch/x86/crypto/crc32c-intel_glue.c +1 -0
@@ -226,6 +226,7 @@ static struct shash_alg alg = {
 		.cra_name		=	"crc32c",
 		.cra_driver_name	=	"crc32c-intel",
 		.cra_priority		=	200,
+		.cra_flags		=	CRYPTO_ALG_OPTIONAL_KEY,
 		.cra_blocksize		=	CHKSUM_BLOCK_SIZE,
 		.cra_ctxsize		=	sizeof(u32),
 		.cra_module		=	THIS_MODULE,
crypto/crc32_generic.c +1 -0
@@ -133,6 +133,7 @@ static struct shash_alg alg = {
 		.cra_name		= "crc32",
 		.cra_driver_name	= "crc32-generic",
 		.cra_priority		= 100,
+		.cra_flags		= CRYPTO_ALG_OPTIONAL_KEY,
 		.cra_blocksize		= CHKSUM_BLOCK_SIZE,
 		.cra_ctxsize		= sizeof(u32),
 		.cra_module		= THIS_MODULE,
crypto/crc32c_generic.c +1 -0
@@ -146,6 +146,7 @@ static struct shash_alg alg = {
 		.cra_name		=	"crc32c",
 		.cra_driver_name	=	"crc32c-generic",
 		.cra_priority		=	100,
+		.cra_flags		=	CRYPTO_ALG_OPTIONAL_KEY,
 		.cra_blocksize		=	CHKSUM_BLOCK_SIZE,
 		.cra_alignmask		=	3,
 		.cra_ctxsize		=	sizeof(struct chksum_ctx),
crypto/cryptd.c +3 -4
@@ -893,10 +893,9 @@ static int cryptd_create_hash(struct cry
 	if (err)
 		goto out_free_inst;
 
-	type = CRYPTO_ALG_ASYNC;
-	if (alg->cra_flags & CRYPTO_ALG_INTERNAL)
-		type |= CRYPTO_ALG_INTERNAL;
-	inst->alg.halg.base.cra_flags = type;
+	inst->alg.halg.base.cra_flags = CRYPTO_ALG_ASYNC |
+		(alg->cra_flags & (CRYPTO_ALG_INTERNAL |
+				   CRYPTO_ALG_OPTIONAL_KEY));
 
 	inst->alg.halg.digestsize = salg->digestsize;
 	inst->alg.halg.statesize = salg->statesize;
crypto/mcryptd.c +3 -4
@@ -517,10 +517,9 @@ static int mcryptd_create_hash(struct cr
 	if (err)
 		goto out_free_inst;
 
-	type = CRYPTO_ALG_ASYNC;
-	if (alg->cra_flags & CRYPTO_ALG_INTERNAL)
-		type |= CRYPTO_ALG_INTERNAL;
-	inst->alg.halg.base.cra_flags = type;
+	inst->alg.halg.base.cra_flags = CRYPTO_ALG_ASYNC |
+		(alg->cra_flags & (CRYPTO_ALG_INTERNAL |
+				   CRYPTO_ALG_OPTIONAL_KEY));
 
 	inst->alg.halg.digestsize = halg->digestsize;
 	inst->alg.halg.statesize = halg->statesize;
drivers/crypto/bfin_crc.c +2 -1
@@ -494,7 +494,8 @@ static struct ahash_alg algs = {
 		.cra_driver_name	= DRIVER_NAME,
 		.cra_priority		= 100,
 		.cra_flags		= CRYPTO_ALG_TYPE_AHASH |
-						CRYPTO_ALG_ASYNC,
+						CRYPTO_ALG_ASYNC |
+						CRYPTO_ALG_OPTIONAL_KEY,
 		.cra_blocksize		= CHKSUM_BLOCK_SIZE,
 		.cra_ctxsize		= sizeof(struct bfin_crypto_crc_ctx),
 		.cra_alignmask		= 3,
drivers/crypto/stm32/stm32_crc32.c +2 -0
@@ -208,6 +208,7 @@ static struct shash_alg algs[] = {
 			.cra_name               = "crc32",
 			.cra_driver_name        = DRIVER_NAME,
 			.cra_priority           = 200,
+			.cra_flags		= CRYPTO_ALG_OPTIONAL_KEY,
 			.cra_blocksize          = CHKSUM_BLOCK_SIZE,
 			.cra_alignmask          = 3,
 			.cra_ctxsize            = sizeof(struct stm32_crc_ctx),
@@ -229,6 +230,7 @@ static struct shash_alg algs[] = {
 			.cra_name               = "crc32c",
 			.cra_driver_name        = DRIVER_NAME,
 			.cra_priority           = 200,
+			.cra_flags		= CRYPTO_ALG_OPTIONAL_KEY,
 			.cra_blocksize          = CHKSUM_BLOCK_SIZE,
 			.cra_alignmask          = 3,
 			.cra_ctxsize            = sizeof(struct stm32_crc_ctx),
drivers/staging/lustre/lnet/libcfs/linux/linux-crypto-adler.c +1 -0
@@ -120,6 +120,7 @@ static struct shash_alg alg = {
 		.cra_name		= "adler32",
 		.cra_driver_name	= "adler32-zlib",
 		.cra_priority		= 100,
+		.cra_flags		= CRYPTO_ALG_OPTIONAL_KEY,
 		.cra_blocksize		= CHKSUM_BLOCK_SIZE,
 		.cra_ctxsize		= sizeof(u32),
 		.cra_module		= THIS_MODULE,
include/linux/crypto.h +6 -0
@@ -107,6 +107,12 @@
 #define CRYPTO_ALG_INTERNAL		0x00002000
 
 /*
+ * Set if the algorithm has a ->setkey() method but can be used without
+ * calling it first, i.e. there is a default key.
+ */
+#define CRYPTO_ALG_OPTIONAL_KEY		0x00004000
+
+/*
  * Transform masks and values (for crt_flags).
  */
 #define CRYPTO_TFM_REQ_MASK		0x000fff00
author maintainer
#113 lore raw

PATCH 113/202 crypto: hash - prevent using keyed hashes without setting key

In reply to Greg Kroah-Hartman

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Eric Biggers <[email protected]>

commit 9fa68f620041be04720d0cbfb1bd3ddfc6310b24 upstream.

Currently, almost none of the keyed hash algorithms check whether a key has been set before proceeding. Some algorithms are okay with this and will effectively just use a key of all 0's or some other bogus default. However, others will severely break, as demonstrated using "hmac(sha3-512-generic)", the unkeyed use of which causes a kernel crash via a (potentially exploitable) stack buffer overflow.

A while ago, this problem was solved for AF_ALG by pairing each hash transform with a 'has_key' bool. However, there are still other places in the kernel where userspace can specify an arbitrary hash algorithm by name, and the kernel uses it as unkeyed hash without checking whether it is really unkeyed. Examples of this include:

- KEYCTL_DH_COMPUTE, via the KDF extension
- dm-verity
- dm-crypt, via the ESSIV support
- dm-integrity, via the "internal hash" mode with no key given
- drbd (Distributed Replicated Block Device)

This bug is especially bad for KEYCTL_DH_COMPUTE as that requires no privileges to call.

Fix the bug for all users by adding a flag CRYPTO_TFM_NEED_KEY to the ->crt_flags of each hash transform that indicates whether the transform still needs to be keyed or not. Then, make the hash init, import, and digest functions return -ENOKEY if the key is still needed.

The new flag also replaces the 'has_key' bool which algif_hash was previously using, thereby simplifying the algif_hash implementation.

---
 crypto/ahash.c         |   22 ++++++++++++++++----
 crypto/algif_hash.c    |   52 ++++++++++---------------------------------------
 crypto/shash.c         |   25 +++++++++++++++++++----
 include/crypto/hash.h  |   34 ++++++++++++++++++++++----------
 include/linux/crypto.h |    2 +
 5 files changed, 75 insertions(+), 60 deletions(-)
crypto/ahash.c +17 -5
@@ -193,11 +193,18 @@ int crypto_ahash_setkey(struct crypto_ah
 			unsigned int keylen)
 {
 	unsigned long alignmask = crypto_ahash_alignmask(tfm);
+	int err;
 
 	if ((unsigned long)key & alignmask)
-		return ahash_setkey_unaligned(tfm, key, keylen);
+		err = ahash_setkey_unaligned(tfm, key, keylen);
+	else
+		err = tfm->setkey(tfm, key, keylen);
+
+	if (err)
+		return err;
 
-	return tfm->setkey(tfm, key, keylen);
+	crypto_ahash_clear_flags(tfm, CRYPTO_TFM_NEED_KEY);
+	return 0;
 }
 EXPORT_SYMBOL_GPL(crypto_ahash_setkey);
 
@@ -368,7 +375,12 @@ EXPORT_SYMBOL_GPL(crypto_ahash_finup);
 
 int crypto_ahash_digest(struct ahash_request *req)
 {
-	return crypto_ahash_op(req, crypto_ahash_reqtfm(req)->digest);
+	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
+
+	if (crypto_ahash_get_flags(tfm) & CRYPTO_TFM_NEED_KEY)
+		return -ENOKEY;
+
+	return crypto_ahash_op(req, tfm->digest);
 }
 EXPORT_SYMBOL_GPL(crypto_ahash_digest);
 
@@ -450,7 +462,6 @@ static int crypto_ahash_init_tfm(struct
 	struct ahash_alg *alg = crypto_ahash_alg(hash);
 
 	hash->setkey = ahash_nosetkey;
-	hash->has_setkey = false;
 	hash->export = ahash_no_export;
 	hash->import = ahash_no_import;
 
@@ -465,7 +476,8 @@ static int crypto_ahash_init_tfm(struct
 
 	if (alg->setkey) {
 		hash->setkey = alg->setkey;
-		hash->has_setkey = true;
+		if (!(alg->halg.base.cra_flags & CRYPTO_ALG_OPTIONAL_KEY))
+			crypto_ahash_set_flags(hash, CRYPTO_TFM_NEED_KEY);
 	}
 	if (alg->export)
 		hash->export = alg->export;
crypto/algif_hash.c +11 -41

104 lines not on this page · raw message

crypto/shash.c +21 -4
@@ -58,11 +58,18 @@ int crypto_shash_setkey(struct crypto_sh
 {
 	struct shash_alg *shash = crypto_shash_alg(tfm);
 	unsigned long alignmask = crypto_shash_alignmask(tfm);
+	int err;
 
 	if ((unsigned long)key & alignmask)
-		return shash_setkey_unaligned(tfm, key, keylen);
+		err = shash_setkey_unaligned(tfm, key, keylen);
+	else
+		err = shash->setkey(tfm, key, keylen);
+
+	if (err)
+		return err;
 
-	return shash->setkey(tfm, key, keylen);
+	crypto_shash_clear_flags(tfm, CRYPTO_TFM_NEED_KEY);
+	return 0;
 }
 EXPORT_SYMBOL_GPL(crypto_shash_setkey);
 
@@ -181,6 +188,9 @@ int crypto_shash_digest(struct shash_des
 	struct shash_alg *shash = crypto_shash_alg(tfm);
 	unsigned long alignmask = crypto_shash_alignmask(tfm);
 
+	if (crypto_shash_get_flags(tfm) & CRYPTO_TFM_NEED_KEY)
+		return -ENOKEY;
+
 	if (((unsigned long)data | (unsigned long)out) & alignmask)
 		return shash_digest_unaligned(desc, data, len, out);
 
@@ -360,7 +370,8 @@ int crypto_init_shash_ops_async(struct c
 	crt->digest = shash_async_digest;
 	crt->setkey = shash_async_setkey;
 
-	crt->has_setkey = alg->setkey != shash_no_setkey;
+	crypto_ahash_set_flags(crt, crypto_shash_get_flags(shash) &
+				    CRYPTO_TFM_NEED_KEY);
 
 	if (alg->export)
 		crt->export = shash_async_export;
@@ -375,8 +386,14 @@ int crypto_init_shash_ops_async(struct c
 static int crypto_shash_init_tfm(struct crypto_tfm *tfm)
 {
 	struct crypto_shash *hash = __crypto_shash_cast(tfm);
+	struct shash_alg *alg = crypto_shash_alg(hash);
+
+	hash->descsize = alg->descsize;
+
+	if (crypto_shash_alg_has_setkey(alg) &&
+	    !(alg->base.cra_flags & CRYPTO_ALG_OPTIONAL_KEY))
+		crypto_shash_set_flags(hash, CRYPTO_TFM_NEED_KEY);
 
-	hash->descsize = crypto_shash_alg(hash)->descsize;
 	return 0;
 }
 
include/crypto/hash.h +24 -10
@@ -210,7 +210,6 @@ struct crypto_ahash {
 		      unsigned int keylen);
 
 	unsigned int reqsize;
-	bool has_setkey;
 	struct crypto_tfm base;
 };
 
@@ -410,11 +409,6 @@ static inline void *ahash_request_ctx(st
 int crypto_ahash_setkey(struct crypto_ahash *tfm, const u8 *key,
 			unsigned int keylen);
 
-static inline bool crypto_ahash_has_setkey(struct crypto_ahash *tfm)
-{
-	return tfm->has_setkey;
-}
-
 /**
  * crypto_ahash_finup() - update and finalize message digest
  * @req: reference to the ahash_request handle that holds all information
@@ -487,7 +481,12 @@ static inline int crypto_ahash_export(st
  */
 static inline int crypto_ahash_import(struct ahash_request *req, const void *in)
 {
-	return crypto_ahash_reqtfm(req)->import(req, in);
+	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
+
+	if (crypto_ahash_get_flags(tfm) & CRYPTO_TFM_NEED_KEY)
+		return -ENOKEY;
+
+	return tfm->import(req, in);
 }
 
 /**
@@ -503,7 +502,12 @@ static inline int crypto_ahash_import(st
  */
 static inline int crypto_ahash_init(struct ahash_request *req)
 {
-	return crypto_ahash_reqtfm(req)->init(req);
+	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
+
+	if (crypto_ahash_get_flags(tfm) & CRYPTO_TFM_NEED_KEY)
+		return -ENOKEY;
+
+	return tfm->init(req);
 }
 
 /**
@@ -855,7 +859,12 @@ static inline int crypto_shash_export(st
  */
 static inline int crypto_shash_import(struct shash_desc *desc, const void *in)
 {
-	return crypto_shash_alg(desc->tfm)->import(desc, in);
+	struct crypto_shash *tfm = desc->tfm;
+
+	if (crypto_shash_get_flags(tfm) & CRYPTO_TFM_NEED_KEY)
+		return -ENOKEY;
+
+	return crypto_shash_alg(tfm)->import(desc, in);
 }
 
 /**
@@ -871,7 +880,12 @@ static inline int crypto_shash_import(st
  */
 static inline int crypto_shash_init(struct shash_desc *desc)
 {
-	return crypto_shash_alg(desc->tfm)->init(desc);
+	struct crypto_shash *tfm = desc->tfm;
+
+	if (crypto_shash_get_flags(tfm) & CRYPTO_TFM_NEED_KEY)
+		return -ENOKEY;
+
+	return crypto_shash_alg(tfm)->init(desc);
 }
 
 /**
include/linux/crypto.h +2 -0
@@ -115,6 +115,8 @@
 /*
  * Transform masks and values (for crt_flags).
  */
+#define CRYPTO_TFM_NEED_KEY		0x00000001
+
 #define CRYPTO_TFM_REQ_MASK		0x000fff00
 #define CRYPTO_TFM_RES_MASK		0xfff00000
 
author maintainer
#114 lore raw

PATCH 114/202 media: v4l2-ioctl.c: use check_fmt for enum/g/s/try_fmt

In reply to Greg Kroah-Hartman

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Hans Verkuil <[email protected]>

commit b2469c814fbc8f1f19676dd4912717b798df511e upstream.

Don't duplicate the buffer type checks in enum/g/s/try_fmt. The check_fmt function does that already.

It is hard to keep the checks in sync for all these functions and in fact the check for VBI was wrong in the _fmt functions as it allowed SDR types as well. This caused a v4l2-compliance failure for /dev/swradio0 using vivid.

This simplifies the code and keeps the check in one place and fixes the SDR/VBI bug.

---
 drivers/media/v4l2-core/v4l2-ioctl.c |  140 +++++++++++++----------------------
 1 file changed, 54 insertions(+), 86 deletions(-)
drivers/media/v4l2-core/v4l2-ioctl.c +54 -86
@@ -1311,52 +1311,50 @@ static int v4l_enum_fmt(const struct v4l
 				struct file *file, void *fh, void *arg)
 {
 	struct v4l2_fmtdesc *p = arg;
-	struct video_device *vfd = video_devdata(file);
-	bool is_vid = vfd->vfl_type == VFL_TYPE_GRABBER;
-	bool is_sdr = vfd->vfl_type == VFL_TYPE_SDR;
-	bool is_tch = vfd->vfl_type == VFL_TYPE_TOUCH;
-	bool is_rx = vfd->vfl_dir != VFL_DIR_TX;
-	bool is_tx = vfd->vfl_dir != VFL_DIR_RX;
-	int ret = -EINVAL;
+	int ret = check_fmt(file, p->type);
+
+	if (ret)
+		return ret;
+	ret = -EINVAL;
 
 	switch (p->type) {
 	case V4L2_BUF_TYPE_VIDEO_CAPTURE:
-		if (unlikely(!is_rx || (!is_vid && !is_tch) || !ops->vidioc_enum_fmt_vid_cap))
+		if (unlikely(!ops->vidioc_enum_fmt_vid_cap))
 			break;
 		ret = ops->vidioc_enum_fmt_vid_cap(file, fh, arg);
 		break;
 	case V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE:
-		if (unlikely(!is_rx || !is_vid || !ops->vidioc_enum_fmt_vid_cap_mplane))
+		if (unlikely(!ops->vidioc_enum_fmt_vid_cap_mplane))
 			break;
 		ret = ops->vidioc_enum_fmt_vid_cap_mplane(file, fh, arg);
 		break;
 	case V4L2_BUF_TYPE_VIDEO_OVERLAY:
-		if (unlikely(!is_rx || !is_vid || !ops->vidioc_enum_fmt_vid_overlay))
+		if (unlikely(!ops->vidioc_enum_fmt_vid_overlay))
 			break;
 		ret = ops->vidioc_enum_fmt_vid_overlay(file, fh, arg);
 		break;
 	case V4L2_BUF_TYPE_VIDEO_OUTPUT:
-		if (unlikely(!is_tx || !is_vid || !ops->vidioc_enum_fmt_vid_out))
+		if (unlikely(!ops->vidioc_enum_fmt_vid_out))
 			break;
 		ret = ops->vidioc_enum_fmt_vid_out(file, fh, arg);
 		break;
 	case V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE:
-		if (unlikely(!is_tx || !is_vid || !ops->vidioc_enum_fmt_vid_out_mplane))
+		if (unlikely(!ops->vidioc_enum_fmt_vid_out_mplane))
 			break;
 		ret = ops->vidioc_enum_fmt_vid_out_mplane(file, fh, arg);
 		break;
 	case V4L2_BUF_TYPE_SDR_CAPTURE:
-		if (unlikely(!is_rx || !is_sdr || !ops->vidioc_enum_fmt_sdr_cap))
+		if (unlikely(!ops->vidioc_enum_fmt_sdr_cap))
 			break;
 		ret = ops->vidioc_enum_fmt_sdr_cap(file, fh, arg);
 		break;
 	case V4L2_BUF_TYPE_SDR_OUTPUT:
-		if (unlikely(!is_tx || !is_sdr || !ops->vidioc_enum_fmt_sdr_out))
+		if (unlikely(!ops->vidioc_enum_fmt_sdr_out))
 			break;
 		ret = ops->vidioc_enum_fmt_sdr_out(file, fh, arg);
 		break;
 	case V4L2_BUF_TYPE_META_CAPTURE:
-		if (unlikely(!is_rx || !is_vid || !ops->vidioc_enum_fmt_meta_cap))
+		if (unlikely(!ops->vidioc_enum_fmt_meta_cap))
 			break;
 		ret = ops->vidioc_enum_fmt_meta_cap(file, fh, arg);
 		break;
@@ -1370,13 +1368,10 @@ static int v4l_g_fmt(const struct v4l2_i
 				struct file *file, void *fh, void *arg)
 {
 	struct v4l2_format *p = arg;
-	struct video_device *vfd = video_devdata(file);
-	bool is_vid = vfd->vfl_type == VFL_TYPE_GRABBER;
-	bool is_sdr = vfd->vfl_type == VFL_TYPE_SDR;
-	bool is_tch = vfd->vfl_type == VFL_TYPE_TOUCH;
-	bool is_rx = vfd->vfl_dir != VFL_DIR_TX;
-	bool is_tx = vfd->vfl_dir != VFL_DIR_RX;
-	int ret;
+	int ret = check_fmt(file, p->type);
+
+	if (ret)
+		return ret;
 
 	/*
 	 * fmt can't be cleared for these overlay types due to the 'clips'
@@ -1404,7 +1399,7 @@ static int v4l_g_fmt(const struct v4l2_i
 
 	switch (p->type) {
 	case V4L2_BUF_TYPE_VIDEO_CAPTURE:
-		if (unlikely(!is_rx || (!is_vid && !is_tch) || !ops->vidioc_g_fmt_vid_cap))
+		if (unlikely(!ops->vidioc_g_fmt_vid_cap))
 			break;
 		p->fmt.pix.priv = V4L2_PIX_FMT_PRIV_MAGIC;
 		ret = ops->vidioc_g_fmt_vid_cap(file, fh, arg);
@@ -1412,23 +1407,15 @@ static int v4l_g_fmt(const struct v4l2_i
 		p->fmt.pix.priv = V4L2_PIX_FMT_PRIV_MAGIC;
 		return ret;
 	case V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE:
-		if (unlikely(!is_rx || !is_vid || !ops->vidioc_g_fmt_vid_cap_mplane))
-			break;
 		return ops->vidioc_g_fmt_vid_cap_mplane(file, fh, arg);
 	case V4L2_BUF_TYPE_VIDEO_OVERLAY:
-		if (unlikely(!is_rx || !is_vid || !ops->vidioc_g_fmt_vid_overlay))
-			break;
 		return ops->vidioc_g_fmt_vid_overlay(file, fh, arg);
 	case V4L2_BUF_TYPE_VBI_CAPTURE:
-		if (unlikely(!is_rx || is_vid || !ops->vidioc_g_fmt_vbi_cap))
-			break;
 		return ops->vidioc_g_fmt_vbi_cap(file, fh, arg);
 	case V4L2_BUF_TYPE_SLICED_VBI_CAPTURE:
-		if (unlikely(!is_rx || is_vid || !ops->vidioc_g_fmt_sliced_vbi_cap))
-			break;
 		return ops->vidioc_g_fmt_sliced_vbi_cap(file, fh, arg);
 	case V4L2_BUF_TYPE_VIDEO_OUTPUT:
-		if (unlikely(!is_tx || !is_vid || !ops->vidioc_g_fmt_vid_out))
+		if (unlikely(!ops->vidioc_g_fmt_vid_out))
 			break;
 		p->fmt.pix.priv = V4L2_PIX_FMT_PRIV_MAGIC;
 		ret = ops->vidioc_g_fmt_vid_out(file, fh, arg);
@@ -1436,32 +1423,18 @@ static int v4l_g_fmt(const struct v4l2_i
 		p->fmt.pix.priv = V4L2_PIX_FMT_PRIV_MAGIC;
 		return ret;
 	case V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE:
-		if (unlikely(!is_tx || !is_vid || !ops->vidioc_g_fmt_vid_out_mplane))
-			break;
 		return ops->vidioc_g_fmt_vid_out_mplane(file, fh, arg);
 	case V4L2_BUF_TYPE_VIDEO_OUTPUT_OVERLAY:
-		if (unlikely(!is_tx || !is_vid || !ops->vidioc_g_fmt_vid_out_overlay))
-			break;
 		return ops->vidioc_g_fmt_vid_out_overlay(file, fh, arg);
 	case V4L2_BUF_TYPE_VBI_OUTPUT:
-		if (unlikely(!is_tx || is_vid || !ops->vidioc_g_fmt_vbi_out))
-			break;
 		return ops->vidioc_g_fmt_vbi_out(file, fh, arg);
 	case V4L2_BUF_TYPE_SLICED_VBI_OUTPUT:
-		if (unlikely(!is_tx || is_vid || !ops->vidioc_g_fmt_sliced_vbi_out))
-			break;
 		return ops->vidioc_g_fmt_sliced_vbi_out(file, fh, arg);
 	case V4L2_BUF_TYPE_SDR_CAPTURE:
-		if (unlikely(!is_rx || !is_sdr || !ops->vidioc_g_fmt_sdr_cap))
-			break;
 		return ops->vidioc_g_fmt_sdr_cap(file, fh, arg);
 	case V4L2_BUF_TYPE_SDR_OUTPUT:
-		if (unlikely(!is_tx || !is_sdr || !ops->vidioc_g_fmt_sdr_out))
-			break;
 		return ops->vidioc_g_fmt_sdr_out(file, fh, arg);
 	case V4L2_BUF_TYPE_META_CAPTURE:
-		if (unlikely(!is_rx || !is_vid || !ops->vidioc_g_fmt_meta_cap))
-			break;
 		return ops->vidioc_g_fmt_meta_cap(file, fh, arg);
 	}
 	return -EINVAL;
@@ -1487,12 +1460,10 @@ static int v4l_s_fmt(const struct v4l2_i
 {
 	struct v4l2_format *p = arg;
 	struct video_device *vfd = video_devdata(file);
-	bool is_vid = vfd->vfl_type == VFL_TYPE_GRABBER;
-	bool is_sdr = vfd->vfl_type == VFL_TYPE_SDR;
-	bool is_tch = vfd->vfl_type == VFL_TYPE_TOUCH;
-	bool is_rx = vfd->vfl_dir != VFL_DIR_TX;
-	bool is_tx = vfd->vfl_dir != VFL_DIR_RX;
-	int ret;
+	int ret = check_fmt(file, p->type);
+
+	if (ret)
+		return ret;
 
 	ret = v4l_enable_media_source(vfd);
 	if (ret)
@@ -1501,37 +1472,37 @@ static int v4l_s_fmt(const struct v4l2_i
 
 	switch (p->type) {
 	case V4L2_BUF_TYPE_VIDEO_CAPTURE:
-		if (unlikely(!is_rx || (!is_vid && !is_tch) || !ops->vidioc_s_fmt_vid_cap))
+		if (unlikely(!ops->vidioc_s_fmt_vid_cap))
 			break;
 		CLEAR_AFTER_FIELD(p, fmt.pix);
 		ret = ops->vidioc_s_fmt_vid_cap(file, fh, arg);
 		/* just in case the driver zeroed it again */
 		p->fmt.pix.priv = V4L2_PIX_FMT_PRIV_MAGIC;
-		if (is_tch)
+		if (vfd->vfl_type == VFL_TYPE_TOUCH)
 			v4l_pix_format_touch(&p->fmt.pix);
 		return ret;
 	case V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE:
-		if (unlikely(!is_rx || !is_vid || !ops->vidioc_s_fmt_vid_cap_mplane))
+		if (unlikely(!ops->vidioc_s_fmt_vid_cap_mplane))
 			break;
 		CLEAR_AFTER_FIELD(p, fmt.pix_mp.xfer_func);
 		return ops->vidioc_s_fmt_vid_cap_mplane(file, fh, arg);
 	case V4L2_BUF_TYPE_VIDEO_OVERLAY:
-		if (unlikely(!is_rx || !is_vid || !ops->vidioc_s_fmt_vid_overlay))
+		if (unlikely(!ops->vidioc_s_fmt_vid_overlay))
 			break;
 		CLEAR_AFTER_FIELD(p, fmt.win);
 		return ops->vidioc_s_fmt_vid_overlay(file, fh, arg);
 	case V4L2_BUF_TYPE_VBI_CAPTURE:
-		if (unlikely(!is_rx || is_vid || !ops->vidioc_s_fmt_vbi_cap))
+		if (unlikely(!ops->vidioc_s_fmt_vbi_cap))
 			break;
 		CLEAR_AFTER_FIELD(p, fmt.vbi);
 		return ops->vidioc_s_fmt_vbi_cap(file, fh, arg);
 	case V4L2_BUF_TYPE_SLICED_VBI_CAPTURE:
-		if (unlikely(!is_rx || is_vid || !ops->vidioc_s_fmt_sliced_vbi_cap))
+		if (unlikely(!ops->vidioc_s_fmt_sliced_vbi_cap))
 			break;
 		CLEAR_AFTER_FIELD(p, fmt.sliced);
 		return ops->vidioc_s_fmt_sliced_vbi_cap(file, fh, arg);
 	case V4L2_BUF_TYPE_VIDEO_OUTPUT:
-		if (unlikely(!is_tx || !is_vid || !ops->vidioc_s_fmt_vid_out))
+		if (unlikely(!ops->vidioc_s_fmt_vid_out))
 			break;
 		CLEAR_AFTER_FIELD(p, fmt.pix);
 		ret = ops->vidioc_s_fmt_vid_out(file, fh, arg);
@@ -1539,37 +1510,37 @@ static int v4l_s_fmt(const struct v4l2_i
 		p->fmt.pix.priv = V4L2_PIX_FMT_PRIV_MAGIC;
 		return ret;
 	case V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE:
-		if (unlikely(!is_tx || !is_vid || !ops->vidioc_s_fmt_vid_out_mplane))
+		if (unlikely(!ops->vidioc_s_fmt_vid_out_mplane))
 			break;
 		CLEAR_AFTER_FIELD(p, fmt.pix_mp.xfer_func);
 		return ops->vidioc_s_fmt_vid_out_mplane(file, fh, arg);
 	case V4L2_BUF_TYPE_VIDEO_OUTPUT_OVERLAY:
-		if (unlikely(!is_tx || !is_vid || !ops->vidioc_s_fmt_vid_out_overlay))
+		if (unlikely(!ops->vidioc_s_fmt_vid_out_overlay))
 			break;
 		CLEAR_AFTER_FIELD(p, fmt.win);
 		return ops->vidioc_s_fmt_vid_out_overlay(file, fh, arg);
 	case V4L2_BUF_TYPE_VBI_OUTPUT:
-		if (unlikely(!is_tx || is_vid || !ops->vidioc_s_fmt_vbi_out))
+		if (unlikely(!ops->vidioc_s_fmt_vbi_out))
 			break;
 		CLEAR_AFTER_FIELD(p, fmt.vbi);
 		return ops->vidioc_s_fmt_vbi_out(file, fh, arg);
 	case V4L2_BUF_TYPE_SLICED_VBI_OUTPUT:
-		if (unlikely(!is_tx || is_vid || !ops->vidioc_s_fmt_sliced_vbi_out))
+		if (unlikely(!ops->vidioc_s_fmt_sliced_vbi_out))
 			break;
 		CLEAR_AFTER_FIELD(p, fmt.sliced);
 		return ops->vidioc_s_fmt_sliced_vbi_out(file, fh, arg);
 	case V4L2_BUF_TYPE_SDR_CAPTURE:
-		if (unlikely(!is_rx || !is_sdr || !ops->vidioc_s_fmt_sdr_cap))
+		if (unlikely(!ops->vidioc_s_fmt_sdr_cap))
 			break;
 		CLEAR_AFTER_FIELD(p, fmt.sdr);
 		return ops->vidioc_s_fmt_sdr_cap(file, fh, arg);
 	case V4L2_BUF_TYPE_SDR_OUTPUT:
-		if (unlikely(!is_tx || !is_sdr || !ops->vidioc_s_fmt_sdr_out))
+		if (unlikely(!ops->vidioc_s_fmt_sdr_out))
 			break;
 		CLEAR_AFTER_FIELD(p, fmt.sdr);
 		return ops->vidioc_s_fmt_sdr_out(file, fh, arg);
 	case V4L2_BUF_TYPE_META_CAPTURE:
-		if (unlikely(!is_rx || !is_vid || !ops->vidioc_s_fmt_meta_cap))
+		if (unlikely(!ops->vidioc_s_fmt_meta_cap))
 			break;
 		CLEAR_AFTER_FIELD(p, fmt.meta);
 		return ops->vidioc_s_fmt_meta_cap(file, fh, arg);
@@ -1581,19 +1552,16 @@ static int v4l_try_fmt(const struct v4l2
 				struct file *file, void *fh, void *arg)
 {
 	struct v4l2_format *p = arg;
-	struct video_device *vfd = video_devdata(file);
-	bool is_vid = vfd->vfl_type == VFL_TYPE_GRABBER;
-	bool is_sdr = vfd->vfl_type == VFL_TYPE_SDR;
-	bool is_tch = vfd->vfl_type == VFL_TYPE_TOUCH;
-	bool is_rx = vfd->vfl_dir != VFL_DIR_TX;
-	bool is_tx = vfd->vfl_dir != VFL_DIR_RX;
-	int ret;
+	int ret = check_fmt(file, p->type);
+
+	if (ret)
+		return ret;
 
 	v4l_sanitize_format(p);
 
 	switch (p->type) {
 	case V4L2_BUF_TYPE_VIDEO_CAPTURE:
-		if (unlikely(!is_rx || (!is_vid && !is_tch) || !ops->vidioc_try_fmt_vid_cap))
+		if (unlikely(!ops->vidioc_try_fmt_vid_cap))
 			break;
 		CLEAR_AFTER_FIELD(p, fmt.pix);
 		ret = ops->vidioc_try_fmt_vid_cap(file, fh, arg);
@@ -1601,27 +1569,27 @@ static int v4l_try_fmt(const struct v4l2
 		p->fmt.pix.priv = V4L2_PIX_FMT_PRIV_MAGIC;
 		return ret;
 	case V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE:
-		if (unlikely(!is_rx || !is_vid || !ops->vidioc_try_fmt_vid_cap_mplane))
+		if (unlikely(!ops->vidioc_try_fmt_vid_cap_mplane))
 			break;
 		CLEAR_AFTER_FIELD(p, fmt.pix_mp.xfer_func);
 		return ops->vidioc_try_fmt_vid_cap_mplane(file, fh, arg);
 	case V4L2_BUF_TYPE_VIDEO_OVERLAY:
-		if (unlikely(!is_rx || !is_vid || !ops->vidioc_try_fmt_vid_overlay))
+		if (unlikely(!ops->vidioc_try_fmt_vid_overlay))
 			break;
 		CLEAR_AFTER_FIELD(p, fmt.win);
 		return ops->vidioc_try_fmt_vid_overlay(file, fh, arg);
 	case V4L2_BUF_TYPE_VBI_CAPTURE:
-		if (unlikely(!is_rx || is_vid || !ops->vidioc_try_fmt_vbi_cap))
+		if (unlikely(!ops->vidioc_try_fmt_vbi_cap))
 			break;
 		CLEAR_AFTER_FIELD(p, fmt.vbi);
 		return ops->vidioc_try_fmt_vbi_cap(file, fh, arg);
 	case V4L2_BUF_TYPE_SLICED_VBI_CAPTURE:
-		if (unlikely(!is_rx || is_vid || !ops->vidioc_try_fmt_sliced_vbi_cap))
+		if (unlikely(!ops->vidioc_try_fmt_sliced_vbi_cap))
 			break;
 		CLEAR_AFTER_FIELD(p, fmt.sliced);
 		return ops->vidioc_try_fmt_sliced_vbi_cap(file, fh, arg);
 	case V4L2_BUF_TYPE_VIDEO_OUTPUT:
-		if (unlikely(!is_tx || !is_vid || !ops->vidioc_try_fmt_vid_out))
+		if (unlikely(!ops->vidioc_try_fmt_vid_out))
 			break;
 		CLEAR_AFTER_FIELD(p, fmt.pix);
 		ret = ops->vidioc_try_fmt_vid_out(file, fh, arg);
@@ -1629,37 +1597,37 @@ static int v4l_try_fmt(const struct v4l2
 		p->fmt.pix.priv = V4L2_PIX_FMT_PRIV_MAGIC;
 		return ret;
 	case V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE:
-		if (unlikely(!is_tx || !is_vid || !ops->vidioc_try_fmt_vid_out_mplane))
+		if (unlikely(!ops->vidioc_try_fmt_vid_out_mplane))
 			break;
 		CLEAR_AFTER_FIELD(p, fmt.pix_mp.xfer_func);
 		return ops->vidioc_try_fmt_vid_out_mplane(file, fh, arg);
 	case V4L2_BUF_TYPE_VIDEO_OUTPUT_OVERLAY:
-		if (unlikely(!is_tx || !is_vid || !ops->vidioc_try_fmt_vid_out_overlay))
+		if (unlikely(!ops->vidioc_try_fmt_vid_out_overlay))
 			break;
 		CLEAR_AFTER_FIELD(p, fmt.win);
 		return ops->vidioc_try_fmt_vid_out_overlay(file, fh, arg);
 	case V4L2_BUF_TYPE_VBI_OUTPUT:
-		if (unlikely(!is_tx || is_vid || !ops->vidioc_try_fmt_vbi_out))
+		if (unlikely(!ops->vidioc_try_fmt_vbi_out))
 			break;
 		CLEAR_AFTER_FIELD(p, fmt.vbi);
 		return ops->vidioc_try_fmt_vbi_out(file, fh, arg);
 	case V4L2_BUF_TYPE_SLICED_VBI_OUTPUT:
-		if (unlikely(!is_tx || is_vid || !ops->vidioc_try_fmt_sliced_vbi_out))
+		if (unlikely(!ops->vidioc_try_fmt_sliced_vbi_out))
 			break;
 		CLEAR_AFTER_FIELD(p, fmt.sliced);
 		return ops->vidioc_try_fmt_sliced_vbi_out(file, fh, arg);
 	case V4L2_BUF_TYPE_SDR_CAPTURE:
-		if (unlikely(!is_rx || !is_sdr || !ops->vidioc_try_fmt_sdr_cap))
+		if (unlikely(!ops->vidioc_try_fmt_sdr_cap))
 			break;
 		CLEAR_AFTER_FIELD(p, fmt.sdr);
 		return ops->vidioc_try_fmt_sdr_cap(file, fh, arg);
 	case V4L2_BUF_TYPE_SDR_OUTPUT:
-		if (unlikely(!is_tx || !is_sdr || !ops->vidioc_try_fmt_sdr_out))
+		if (unlikely(!ops->vidioc_try_fmt_sdr_out))
 			break;
 		CLEAR_AFTER_FIELD(p, fmt.sdr);
 		return ops->vidioc_try_fmt_sdr_out(file, fh, arg);
 	case V4L2_BUF_TYPE_META_CAPTURE:
-		if (unlikely(!is_rx || !is_vid || !ops->vidioc_try_fmt_meta_cap))
+		if (unlikely(!ops->vidioc_try_fmt_meta_cap))
 			break;
 		CLEAR_AFTER_FIELD(p, fmt.meta);
 		return ops->vidioc_try_fmt_meta_cap(file, fh, arg);
author maintainer
#115 lore raw

PATCH 115/202 media: v4l2-ioctl.c: dont copy back the result for -ENOTTY

In reply to Greg Kroah-Hartman

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Hans Verkuil <[email protected]>

commit 181a4a2d5a0a7b43cab08a70710d727e7764ccdd upstream.

If the ioctl returned -ENOTTY, then don't bother copying back the result as there is no point.

---
 drivers/media/v4l2-core/v4l2-ioctl.c |    5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)
drivers/media/v4l2-core/v4l2-ioctl.c +4 -1
@@ -2895,8 +2895,11 @@ video_usercopy(struct file *file, unsign
 
 	/* Handles IOCTL */
 	err = func(file, cmd, parg);
-	if (err == -ENOIOCTLCMD)
+	if (err == -ENOTTY || err == -ENOIOCTLCMD) {
 		err = -ENOTTY;
+		goto out;
+	}
+
 	if (err == 0) {
 		if (cmd == VIDIOC_DQBUF)
 			trace_v4l2_dqbuf(video_devdata(file)->minor, parg);
author maintainer
#116 lore raw

PATCH 116/202 media: v4l2-compat-ioctl32.c: add missing VIDIOC_PREPARE_BUF

In reply to Greg Kroah-Hartman

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Hans Verkuil <[email protected]>

commit 3ee6d040719ae09110e5cdf24d5386abe5d1b776 upstream.

The result of the VIDIOC_PREPARE_BUF ioctl was never copied back to userspace since it was missing in the switch.

---
 drivers/media/v4l2-core/v4l2-compat-ioctl32.c |    1 +
 1 file changed, 1 insertion(+)
drivers/media/v4l2-core/v4l2-compat-ioctl32.c +1 -0
@@ -1052,6 +1052,7 @@ static long do_video_ioctl(struct file *
 		err = put_v4l2_create32(&karg.v2crt, up);
 		break;
 
+	case VIDIOC_PREPARE_BUF:
 	case VIDIOC_QUERYBUF:
 	case VIDIOC_QBUF:
 	case VIDIOC_DQBUF:
author maintainer
#117 lore raw

PATCH 117/202 media: v4l2-compat-ioctl32.c: fix the indentation

In reply to Greg Kroah-Hartman

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Hans Verkuil <[email protected]>

commit b7b957d429f601d6d1942122b339474f31191d75 upstream.

The indentation of this source is all over the place. Fix this. This patch only changes whitespace.

---
 drivers/media/v4l2-core/v4l2-compat-ioctl32.c |  212 +++++++++++++-------------
 1 file changed, 107 insertions(+), 105 deletions(-)
drivers/media/v4l2-core/v4l2-compat-ioctl32.c +107 -105
@@ -49,12 +49,12 @@ struct v4l2_window32 {
 static int get_v4l2_window32(struct v4l2_window *kp, struct v4l2_window32 __user *up)
 {
 	if (!access_ok(VERIFY_READ, up, sizeof(struct v4l2_window32)) ||
-		copy_from_user(&kp->w, &up->w, sizeof(up->w)) ||
-		get_user(kp->field, &up->field) ||
-		get_user(kp->chromakey, &up->chromakey) ||
-		get_user(kp->clipcount, &up->clipcount) ||
-		get_user(kp->global_alpha, &up->global_alpha))
-			return -EFAULT;
+	    copy_from_user(&kp->w, &up->w, sizeof(up->w)) ||
+	    get_user(kp->field, &up->field) ||
+	    get_user(kp->chromakey, &up->chromakey) ||
+	    get_user(kp->clipcount, &up->clipcount) ||
+	    get_user(kp->global_alpha, &up->global_alpha))
+		return -EFAULT;
 	if (kp->clipcount > 2048)
 		return -EINVAL;
 	if (kp->clipcount) {
@@ -84,11 +84,11 @@ static int get_v4l2_window32(struct v4l2
 static int put_v4l2_window32(struct v4l2_window *kp, struct v4l2_window32 __user *up)
 {
 	if (copy_to_user(&up->w, &kp->w, sizeof(kp->w)) ||
-		put_user(kp->field, &up->field) ||
-		put_user(kp->chromakey, &up->chromakey) ||
-		put_user(kp->clipcount, &up->clipcount) ||
-		put_user(kp->global_alpha, &up->global_alpha))
-			return -EFAULT;
+	    put_user(kp->field, &up->field) ||
+	    put_user(kp->chromakey, &up->chromakey) ||
+	    put_user(kp->clipcount, &up->clipcount) ||
+	    put_user(kp->global_alpha, &up->global_alpha))
+		return -EFAULT;
 	return 0;
 }
 
@@ -100,7 +100,7 @@ static inline int get_v4l2_pix_format(st
 }
 
 static inline int get_v4l2_pix_format_mplane(struct v4l2_pix_format_mplane *kp,
-				struct v4l2_pix_format_mplane __user *up)
+					     struct v4l2_pix_format_mplane __user *up)
 {
 	if (copy_from_user(kp, up, sizeof(struct v4l2_pix_format_mplane)))
 		return -EFAULT;
@@ -115,7 +115,7 @@ static inline int put_v4l2_pix_format(st
 }
 
 static inline int put_v4l2_pix_format_mplane(struct v4l2_pix_format_mplane *kp,
-				struct v4l2_pix_format_mplane __user *up)
+					     struct v4l2_pix_format_mplane __user *up)
 {
 	if (copy_to_user(up, kp, sizeof(struct v4l2_pix_format_mplane)))
 		return -EFAULT;
@@ -238,7 +238,7 @@ static int __get_v4l2_format32(struct v4
 		return get_v4l2_meta_format(&kp->fmt.meta, &up->fmt.meta);
 	default:
 		pr_info("compat_ioctl32: unexpected VIDIOC_FMT type %d\n",
-								kp->type);
+			kp->type);
 		return -EINVAL;
 	}
 }
@@ -287,7 +287,7 @@ static int __put_v4l2_format32(struct v4
 		return put_v4l2_meta_format(&kp->fmt.meta, &up->fmt.meta);
 	default:
 		pr_info("compat_ioctl32: unexpected VIDIOC_FMT type %d\n",
-								kp->type);
+			kp->type);
 		return -EINVAL;
 	}
 }
@@ -321,7 +321,7 @@ static int get_v4l2_standard32(struct v4
 {
 	/* other fields are not set by the user, nor used by the driver */
 	if (!access_ok(VERIFY_READ, up, sizeof(struct v4l2_standard32)) ||
-		get_user(kp->index, &up->index))
+	    get_user(kp->index, &up->index))
 		return -EFAULT;
 	return 0;
 }
@@ -329,13 +329,14 @@ static int get_v4l2_standard32(struct v4
 static int put_v4l2_standard32(struct v4l2_standard *kp, struct v4l2_standard32 __user *up)
 {
 	if (!access_ok(VERIFY_WRITE, up, sizeof(struct v4l2_standard32)) ||
-		put_user(kp->index, &up->index) ||
-		put_user(kp->id, &up->id) ||
-		copy_to_user(up->name, kp->name, 24) ||
-		copy_to_user(&up->frameperiod, &kp->frameperiod, sizeof(kp->frameperiod)) ||
-		put_user(kp->framelines, &up->framelines) ||
-		copy_to_user(up->reserved, kp->reserved, 4 * sizeof(__u32)))
-			return -EFAULT;
+	    put_user(kp->index, &up->index) ||
+	    put_user(kp->id, &up->id) ||
+	    copy_to_user(up->name, kp->name, 24) ||
+	    copy_to_user(&up->frameperiod, &kp->frameperiod,
+			 sizeof(kp->frameperiod)) ||
+	    put_user(kp->framelines, &up->framelines) ||
+	    copy_to_user(up->reserved, kp->reserved, 4 * sizeof(__u32)))
+		return -EFAULT;
 	return 0;
 }
 
@@ -375,14 +376,14 @@ struct v4l2_buffer32 {
 };
 
 static int get_v4l2_plane32(struct v4l2_plane __user *up, struct v4l2_plane32 __user *up32,
-				enum v4l2_memory memory)
+			    enum v4l2_memory memory)
 {
 	void __user *up_pln;
 	compat_long_t p;
 
 	if (copy_in_user(up, up32, 2 * sizeof(__u32)) ||
-		copy_in_user(&up->data_offset, &up32->data_offset,
-				sizeof(__u32)))
+	    copy_in_user(&up->data_offset, &up32->data_offset,
+			 sizeof(__u32)))
 		return -EFAULT;
 
 	if (memory == V4L2_MEMORY_USERPTR) {
@@ -396,7 +397,7 @@ static int get_v4l2_plane32(struct v4l2_
 			return -EFAULT;
 	} else {
 		if (copy_in_user(&up->m.mem_offset, &up32->m.mem_offset,
-					sizeof(__u32)))
+				 sizeof(__u32)))
 			return -EFAULT;
 	}
 
@@ -404,23 +405,23 @@ static int get_v4l2_plane32(struct v4l2_
 }
 
 static int put_v4l2_plane32(struct v4l2_plane __user *up, struct v4l2_plane32 __user *up32,
-				enum v4l2_memory memory)
+			    enum v4l2_memory memory)
 {
 	if (copy_in_user(up32, up, 2 * sizeof(__u32)) ||
-		copy_in_user(&up32->data_offset, &up->data_offset,
-				sizeof(__u32)))
+	    copy_in_user(&up32->data_offset, &up->data_offset,
+			 sizeof(__u32)))
 		return -EFAULT;
 
 	/* For MMAP, driver might've set up the offset, so copy it back.
 	 * USERPTR stays the same (was userspace-provided), so no copying. */
 	if (memory == V4L2_MEMORY_MMAP)
 		if (copy_in_user(&up32->m.mem_offset, &up->m.mem_offset,
-					sizeof(__u32)))
+				 sizeof(__u32)))
 			return -EFAULT;
 	/* For DMABUF, driver might've set up the fd, so copy it back. */
 	if (memory == V4L2_MEMORY_DMABUF)
 		if (copy_in_user(&up32->m.fd, &up->m.fd,
-					sizeof(int)))
+				 sizeof(int)))
 			return -EFAULT;
 
 	return 0;
@@ -434,19 +435,19 @@ static int get_v4l2_buffer32(struct v4l2
 	int ret;
 
 	if (!access_ok(VERIFY_READ, up, sizeof(struct v4l2_buffer32)) ||
-		get_user(kp->index, &up->index) ||
-		get_user(kp->type, &up->type) ||
-		get_user(kp->flags, &up->flags) ||
-		get_user(kp->memory, &up->memory) ||
-		get_user(kp->length, &up->length))
-			return -EFAULT;
+	    get_user(kp->index, &up->index) ||
+	    get_user(kp->type, &up->type) ||
+	    get_user(kp->flags, &up->flags) ||
+	    get_user(kp->memory, &up->memory) ||
+	    get_user(kp->length, &up->length))
+		return -EFAULT;
 
 	if (V4L2_TYPE_IS_OUTPUT(kp->type))
 		if (get_user(kp->bytesused, &up->bytesused) ||
-			get_user(kp->field, &up->field) ||
-			get_user(kp->timestamp.tv_sec, &up->timestamp.tv_sec) ||
-			get_user(kp->timestamp.tv_usec,
-					&up->timestamp.tv_usec))
+		    get_user(kp->field, &up->field) ||
+		    get_user(kp->timestamp.tv_sec, &up->timestamp.tv_sec) ||
+		    get_user(kp->timestamp.tv_usec,
+			     &up->timestamp.tv_usec))
 			return -EFAULT;
 
 	if (V4L2_TYPE_IS_MULTIPLANAR(kp->type)) {
@@ -466,7 +467,7 @@ static int get_v4l2_buffer32(struct v4l2
 
 		uplane32 = compat_ptr(p);
 		if (!access_ok(VERIFY_READ, uplane32,
-				kp->length * sizeof(struct v4l2_plane32)))
+			       kp->length * sizeof(struct v4l2_plane32)))
 			return -EFAULT;
 
 		/* We don't really care if userspace decides to kill itself
@@ -490,12 +491,12 @@ static int get_v4l2_buffer32(struct v4l2
 			break;
 		case V4L2_MEMORY_USERPTR:
 			{
-			compat_long_t tmp;
+				compat_long_t tmp;
 
-			if (get_user(tmp, &up->m.userptr))
-				return -EFAULT;
+				if (get_user(tmp, &up->m.userptr))
+					return -EFAULT;
 
-			kp->m.userptr = (unsigned long)compat_ptr(tmp);
+				kp->m.userptr = (unsigned long)compat_ptr(tmp);
 			}
 			break;
 		case V4L2_MEMORY_OVERLAY:
@@ -521,22 +522,23 @@ static int put_v4l2_buffer32(struct v4l2
 	int ret;
 
 	if (!access_ok(VERIFY_WRITE, up, sizeof(struct v4l2_buffer32)) ||
-		put_user(kp->index, &up->index) ||
-		put_user(kp->type, &up->type) ||
-		put_user(kp->flags, &up->flags) ||
-		put_user(kp->memory, &up->memory))
-			return -EFAULT;
+	    put_user(kp->index, &up->index) ||
+	    put_user(kp->type, &up->type) ||
+	    put_user(kp->flags, &up->flags) ||
+	    put_user(kp->memory, &up->memory))
+		return -EFAULT;
 
 	if (put_user(kp->bytesused, &up->bytesused) ||
-		put_user(kp->field, &up->field) ||
-		put_user(kp->timestamp.tv_sec, &up->timestamp.tv_sec) ||
-		put_user(kp->timestamp.tv_usec, &up->timestamp.tv_usec) ||
-		copy_to_user(&up->timecode, &kp->timecode, sizeof(struct v4l2_timecode)) ||
-		put_user(kp->sequence, &up->sequence) ||
-		put_user(kp->reserved2, &up->reserved2) ||
-		put_user(kp->reserved, &up->reserved) ||
-		put_user(kp->length, &up->length))
-			return -EFAULT;
+	    put_user(kp->field, &up->field) ||
+	    put_user(kp->timestamp.tv_sec, &up->timestamp.tv_sec) ||
+	    put_user(kp->timestamp.tv_usec, &up->timestamp.tv_usec) ||
+	    copy_to_user(&up->timecode, &kp->timecode,
+			 sizeof(struct v4l2_timecode)) ||
+	    put_user(kp->sequence, &up->sequence) ||
+	    put_user(kp->reserved2, &up->reserved2) ||
+	    put_user(kp->reserved, &up->reserved) ||
+	    put_user(kp->length, &up->length))
+		return -EFAULT;
 
 	if (V4L2_TYPE_IS_MULTIPLANAR(kp->type)) {
 		num_planes = kp->length;
@@ -600,11 +602,11 @@ static int get_v4l2_framebuffer32(struct
 	u32 tmp;
 
 	if (!access_ok(VERIFY_READ, up, sizeof(struct v4l2_framebuffer32)) ||
-		get_user(tmp, &up->base) ||
-		get_user(kp->capability, &up->capability) ||
-		get_user(kp->flags, &up->flags) ||
-		copy_from_user(&kp->fmt, &up->fmt, sizeof(up->fmt)))
-			return -EFAULT;
+	    get_user(tmp, &up->base) ||
+	    get_user(kp->capability, &up->capability) ||
+	    get_user(kp->flags, &up->flags) ||
+	    copy_from_user(&kp->fmt, &up->fmt, sizeof(up->fmt)))
+		return -EFAULT;
 	kp->base = (__force void *)compat_ptr(tmp);
 	return 0;
 }
@@ -614,11 +616,11 @@ static int put_v4l2_framebuffer32(struct
 	u32 tmp = (u32)((unsigned long)kp->base);
 
 	if (!access_ok(VERIFY_WRITE, up, sizeof(struct v4l2_framebuffer32)) ||
-		put_user(tmp, &up->base) ||
-		put_user(kp->capability, &up->capability) ||
-		put_user(kp->flags, &up->flags) ||
-		copy_to_user(&up->fmt, &kp->fmt, sizeof(up->fmt)))
-			return -EFAULT;
+	    put_user(tmp, &up->base) ||
+	    put_user(kp->capability, &up->capability) ||
+	    put_user(kp->flags, &up->flags) ||
+	    copy_to_user(&up->fmt, &kp->fmt, sizeof(up->fmt)))
+		return -EFAULT;
 	return 0;
 }
 
@@ -694,12 +696,12 @@ static int get_v4l2_ext_controls32(struc
 	compat_caddr_t p;
 
 	if (!access_ok(VERIFY_READ, up, sizeof(struct v4l2_ext_controls32)) ||
-		get_user(kp->which, &up->which) ||
-		get_user(kp->count, &up->count) ||
-		get_user(kp->error_idx, &up->error_idx) ||
-		copy_from_user(kp->reserved, up->reserved,
-			       sizeof(kp->reserved)))
-			return -EFAULT;
+	    get_user(kp->which, &up->which) ||
+	    get_user(kp->count, &up->count) ||
+	    get_user(kp->error_idx, &up->error_idx) ||
+	    copy_from_user(kp->reserved, up->reserved,
+			   sizeof(kp->reserved)))
+		return -EFAULT;
 	if (kp->count == 0) {
 		kp->controls = NULL;
 		return 0;
@@ -710,7 +712,7 @@ static int get_v4l2_ext_controls32(struc
 		return -EFAULT;
 	ucontrols = compat_ptr(p);
 	if (!access_ok(VERIFY_READ, ucontrols,
-			kp->count * sizeof(struct v4l2_ext_control32)))
+		       kp->count * sizeof(struct v4l2_ext_control32)))
 		return -EFAULT;
 	kcontrols = compat_alloc_user_space(kp->count *
 					    sizeof(struct v4l2_ext_control));
@@ -746,11 +748,11 @@ static int put_v4l2_ext_controls32(struc
 	compat_caddr_t p;
 
 	if (!access_ok(VERIFY_WRITE, up, sizeof(struct v4l2_ext_controls32)) ||
-		put_user(kp->which, &up->which) ||
-		put_user(kp->count, &up->count) ||
-		put_user(kp->error_idx, &up->error_idx) ||
-		copy_to_user(up->reserved, kp->reserved, sizeof(up->reserved)))
-			return -EFAULT;
+	    put_user(kp->which, &up->which) ||
+	    put_user(kp->count, &up->count) ||
+	    put_user(kp->error_idx, &up->error_idx) ||
+	    copy_to_user(up->reserved, kp->reserved, sizeof(up->reserved)))
+		return -EFAULT;
 	if (!kp->count)
 		return 0;
 
@@ -758,7 +760,7 @@ static int put_v4l2_ext_controls32(struc
 		return -EFAULT;
 	ucontrols = compat_ptr(p);
 	if (!access_ok(VERIFY_WRITE, ucontrols,
-			n * sizeof(struct v4l2_ext_control32)))
+		       n * sizeof(struct v4l2_ext_control32)))
 		return -EFAULT;
 
 	while (--n >= 0) {
@@ -796,15 +798,15 @@ struct v4l2_event32 {
 static int put_v4l2_event32(struct v4l2_event *kp, struct v4l2_event32 __user *up)
 {
 	if (!access_ok(VERIFY_WRITE, up, sizeof(struct v4l2_event32)) ||
-		put_user(kp->type, &up->type) ||
-		copy_to_user(&up->u, &kp->u, sizeof(kp->u)) ||
-		put_user(kp->pending, &up->pending) ||
-		put_user(kp->sequence, &up->sequence) ||
-		put_user(kp->timestamp.tv_sec, &up->timestamp.tv_sec) ||
-		put_user(kp->timestamp.tv_nsec, &up->timestamp.tv_nsec) ||
-		put_user(kp->id, &up->id) ||
-		copy_to_user(up->reserved, kp->reserved, 8 * sizeof(__u32)))
-			return -EFAULT;
+	    put_user(kp->type, &up->type) ||
+	    copy_to_user(&up->u, &kp->u, sizeof(kp->u)) ||
+	    put_user(kp->pending, &up->pending) ||
+	    put_user(kp->sequence, &up->sequence) ||
+	    put_user(kp->timestamp.tv_sec, &up->timestamp.tv_sec) ||
+	    put_user(kp->timestamp.tv_nsec, &up->timestamp.tv_nsec) ||
+	    put_user(kp->id, &up->id) ||
+	    copy_to_user(up->reserved, kp->reserved, 8 * sizeof(__u32)))
+		return -EFAULT;
 	return 0;
 }
 
@@ -821,12 +823,12 @@ static int get_v4l2_edid32(struct v4l2_e
 	u32 tmp;
 
 	if (!access_ok(VERIFY_READ, up, sizeof(struct v4l2_edid32)) ||
-		get_user(kp->pad, &up->pad) ||
-		get_user(kp->start_block, &up->start_block) ||
-		get_user(kp->blocks, &up->blocks) ||
-		get_user(tmp, &up->edid) ||
-		copy_from_user(kp->reserved, up->reserved, sizeof(kp->reserved)))
-			return -EFAULT;
+	    get_user(kp->pad, &up->pad) ||
+	    get_user(kp->start_block, &up->start_block) ||
+	    get_user(kp->blocks, &up->blocks) ||
+	    get_user(tmp, &up->edid) ||
+	    copy_from_user(kp->reserved, up->reserved, sizeof(kp->reserved)))
+		return -EFAULT;
 	kp->edid = (__force u8 *)compat_ptr(tmp);
 	return 0;
 }
@@ -836,12 +838,12 @@ static int put_v4l2_edid32(struct v4l2_e
 	u32 tmp = (u32)((unsigned long)kp->edid);
 
 	if (!access_ok(VERIFY_WRITE, up, sizeof(struct v4l2_edid32)) ||
-		put_user(kp->pad, &up->pad) ||
-		put_user(kp->start_block, &up->start_block) ||
-		put_user(kp->blocks, &up->blocks) ||
-		put_user(tmp, &up->edid) ||
-		copy_to_user(up->reserved, kp->reserved, sizeof(up->reserved)))
-			return -EFAULT;
+	    put_user(kp->pad, &up->pad) ||
+	    put_user(kp->start_block, &up->start_block) ||
+	    put_user(kp->blocks, &up->blocks) ||
+	    put_user(tmp, &up->edid) ||
+	    copy_to_user(up->reserved, kp->reserved, sizeof(up->reserved)))
+		return -EFAULT;
 	return 0;
 }
 
author maintainer
#118 lore raw

PATCH 118/202 media: v4l2-compat-ioctl32.c: move helper functions to __get/put_v4l2_format32

In reply to Greg Kroah-Hartman

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Hans Verkuil <[email protected]>

commit 486c521510c44a04cd756a9267e7d1e271c8a4ba upstream.

These helper functions do not really help. Move the code to the __get/put_v4l2_format32 functions.

---
 drivers/media/v4l2-core/v4l2-compat-ioctl32.c |  124 +++++---------------------
 1 file changed, 24 insertions(+), 100 deletions(-)
drivers/media/v4l2-core/v4l2-compat-ioctl32.c +24 -100
@@ -92,92 +92,6 @@ static int put_v4l2_window32(struct v4l2
 	return 0;
 }
 
-static inline int get_v4l2_pix_format(struct v4l2_pix_format *kp, struct v4l2_pix_format __user *up)
-{
-	if (copy_from_user(kp, up, sizeof(struct v4l2_pix_format)))
-		return -EFAULT;
-	return 0;
-}
-
-static inline int get_v4l2_pix_format_mplane(struct v4l2_pix_format_mplane *kp,
-					     struct v4l2_pix_format_mplane __user *up)
-{
-	if (copy_from_user(kp, up, sizeof(struct v4l2_pix_format_mplane)))
-		return -EFAULT;
-	return 0;
-}
-
-static inline int put_v4l2_pix_format(struct v4l2_pix_format *kp, struct v4l2_pix_format __user *up)
-{
-	if (copy_to_user(up, kp, sizeof(struct v4l2_pix_format)))
-		return -EFAULT;
-	return 0;
-}
-
-static inline int put_v4l2_pix_format_mplane(struct v4l2_pix_format_mplane *kp,
-					     struct v4l2_pix_format_mplane __user *up)
-{
-	if (copy_to_user(up, kp, sizeof(struct v4l2_pix_format_mplane)))
-		return -EFAULT;
-	return 0;
-}
-
-static inline int get_v4l2_vbi_format(struct v4l2_vbi_format *kp, struct v4l2_vbi_format __user *up)
-{
-	if (copy_from_user(kp, up, sizeof(struct v4l2_vbi_format)))
-		return -EFAULT;
-	return 0;
-}
-
-static inline int put_v4l2_vbi_format(struct v4l2_vbi_format *kp, struct v4l2_vbi_format __user *up)
-{
-	if (copy_to_user(up, kp, sizeof(struct v4l2_vbi_format)))
-		return -EFAULT;
-	return 0;
-}
-
-static inline int get_v4l2_sliced_vbi_format(struct v4l2_sliced_vbi_format *kp, struct v4l2_sliced_vbi_format __user *up)
-{
-	if (copy_from_user(kp, up, sizeof(struct v4l2_sliced_vbi_format)))
-		return -EFAULT;
-	return 0;
-}
-
-static inline int put_v4l2_sliced_vbi_format(struct v4l2_sliced_vbi_format *kp, struct v4l2_sliced_vbi_format __user *up)
-{
-	if (copy_to_user(up, kp, sizeof(struct v4l2_sliced_vbi_format)))
-		return -EFAULT;
-	return 0;
-}
-
-static inline int get_v4l2_sdr_format(struct v4l2_sdr_format *kp, struct v4l2_sdr_format __user *up)
-{
-	if (copy_from_user(kp, up, sizeof(struct v4l2_sdr_format)))
-		return -EFAULT;
-	return 0;
-}
-
-static inline int put_v4l2_sdr_format(struct v4l2_sdr_format *kp, struct v4l2_sdr_format __user *up)
-{
-	if (copy_to_user(up, kp, sizeof(struct v4l2_sdr_format)))
-		return -EFAULT;
-	return 0;
-}
-
-static inline int get_v4l2_meta_format(struct v4l2_meta_format *kp, struct v4l2_meta_format __user *up)
-{
-	if (copy_from_user(kp, up, sizeof(struct v4l2_meta_format)))
-		return -EFAULT;
-	return 0;
-}
-
-static inline int put_v4l2_meta_format(struct v4l2_meta_format *kp, struct v4l2_meta_format __user *up)
-{
-	if (copy_to_user(up, kp, sizeof(struct v4l2_meta_format)))
-		return -EFAULT;
-	return 0;
-}
-
 struct v4l2_format32 {
 	__u32	type;	/* enum v4l2_buf_type */
 	union {
@@ -217,25 +131,30 @@ static int __get_v4l2_format32(struct v4
 	switch (kp->type) {
 	case V4L2_BUF_TYPE_VIDEO_CAPTURE:
 	case V4L2_BUF_TYPE_VIDEO_OUTPUT:
-		return get_v4l2_pix_format(&kp->fmt.pix, &up->fmt.pix);
+		return copy_from_user(&kp->fmt.pix, &up->fmt.pix,
+				      sizeof(kp->fmt.pix)) ? -EFAULT : 0;
 	case V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE:
 	case V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE:
-		return get_v4l2_pix_format_mplane(&kp->fmt.pix_mp,
-						  &up->fmt.pix_mp);
+		return copy_from_user(&kp->fmt.pix_mp, &up->fmt.pix_mp,
+				      sizeof(kp->fmt.pix_mp)) ? -EFAULT : 0;
 	case V4L2_BUF_TYPE_VIDEO_OVERLAY:
 	case V4L2_BUF_TYPE_VIDEO_OUTPUT_OVERLAY:
 		return get_v4l2_window32(&kp->fmt.win, &up->fmt.win);
 	case V4L2_BUF_TYPE_VBI_CAPTURE:
 	case V4L2_BUF_TYPE_VBI_OUTPUT:
-		return get_v4l2_vbi_format(&kp->fmt.vbi, &up->fmt.vbi);
+		return copy_from_user(&kp->fmt.vbi, &up->fmt.vbi,
+				      sizeof(kp->fmt.vbi)) ? -EFAULT : 0;
 	case V4L2_BUF_TYPE_SLICED_VBI_CAPTURE:
 	case V4L2_BUF_TYPE_SLICED_VBI_OUTPUT:
-		return get_v4l2_sliced_vbi_format(&kp->fmt.sliced, &up->fmt.sliced);
+		return copy_from_user(&kp->fmt.sliced, &up->fmt.sliced,
+				      sizeof(kp->fmt.sliced)) ? -EFAULT : 0;
 	case V4L2_BUF_TYPE_SDR_CAPTURE:
 	case V4L2_BUF_TYPE_SDR_OUTPUT:
-		return get_v4l2_sdr_format(&kp->fmt.sdr, &up->fmt.sdr);
+		return copy_from_user(&kp->fmt.sdr, &up->fmt.sdr,
+				      sizeof(kp->fmt.sdr)) ? -EFAULT : 0;
 	case V4L2_BUF_TYPE_META_CAPTURE:
-		return get_v4l2_meta_format(&kp->fmt.meta, &up->fmt.meta);
+		return copy_from_user(&kp->fmt.meta, &up->fmt.meta,
+				      sizeof(kp->fmt.meta)) ? -EFAULT : 0;
 	default:
 		pr_info("compat_ioctl32: unexpected VIDIOC_FMT type %d\n",
 			kp->type);
@@ -266,25 +185,30 @@ static int __put_v4l2_format32(struct v4
 	switch (kp->type) {
 	case V4L2_BUF_TYPE_VIDEO_CAPTURE:
 	case V4L2_BUF_TYPE_VIDEO_OUTPUT:
-		return put_v4l2_pix_format(&kp->fmt.pix, &up->fmt.pix);
+		return copy_to_user(&up->fmt.pix, &kp->fmt.pix,
+				    sizeof(kp->fmt.pix)) ? -EFAULT : 0;
 	case V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE:
 	case V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE:
-		return put_v4l2_pix_format_mplane(&kp->fmt.pix_mp,
-						  &up->fmt.pix_mp);
+		return copy_to_user(&up->fmt.pix_mp, &kp->fmt.pix_mp,
+				    sizeof(kp->fmt.pix_mp)) ? -EFAULT : 0;
 	case V4L2_BUF_TYPE_VIDEO_OVERLAY:
 	case V4L2_BUF_TYPE_VIDEO_OUTPUT_OVERLAY:
 		return put_v4l2_window32(&kp->fmt.win, &up->fmt.win);
 	case V4L2_BUF_TYPE_VBI_CAPTURE:
 	case V4L2_BUF_TYPE_VBI_OUTPUT:
-		return put_v4l2_vbi_format(&kp->fmt.vbi, &up->fmt.vbi);
+		return copy_to_user(&up->fmt.vbi, &kp->fmt.vbi,
+				    sizeof(kp->fmt.vbi)) ? -EFAULT : 0;
 	case V4L2_BUF_TYPE_SLICED_VBI_CAPTURE:
 	case V4L2_BUF_TYPE_SLICED_VBI_OUTPUT:
-		return put_v4l2_sliced_vbi_format(&kp->fmt.sliced, &up->fmt.sliced);
+		return copy_to_user(&up->fmt.sliced, &kp->fmt.sliced,
+				    sizeof(kp->fmt.sliced)) ? -EFAULT : 0;
 	case V4L2_BUF_TYPE_SDR_CAPTURE:
 	case V4L2_BUF_TYPE_SDR_OUTPUT:
-		return put_v4l2_sdr_format(&kp->fmt.sdr, &up->fmt.sdr);
+		return copy_to_user(&up->fmt.sdr, &kp->fmt.sdr,
+				    sizeof(kp->fmt.sdr)) ? -EFAULT : 0;
 	case V4L2_BUF_TYPE_META_CAPTURE:
-		return put_v4l2_meta_format(&kp->fmt.meta, &up->fmt.meta);
+		return copy_to_user(&up->fmt.meta, &kp->fmt.meta,
+				    sizeof(kp->fmt.meta)) ? -EFAULT : 0;
 	default:
 		pr_info("compat_ioctl32: unexpected VIDIOC_FMT type %d\n",
 			kp->type);
author maintainer
#119 lore raw

PATCH 119/202 media: v4l2-compat-ioctl32.c: avoid sizeof(type)

In reply to Greg Kroah-Hartman

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Hans Verkuil <[email protected]>

commit 333b1e9f96ce05f7498b581509bb30cde03018bf upstream.

Instead of doing sizeof(struct foo) use sizeof(*up). There even were cases where 4 * sizeof(__u32) was used instead of sizeof(kp->reserved), which is very dangerous when the size of the reserved array changes.

---
 drivers/media/v4l2-core/v4l2-compat-ioctl32.c |   79 +++++++++++---------------
 1 file changed, 36 insertions(+), 43 deletions(-)
drivers/media/v4l2-core/v4l2-compat-ioctl32.c +36 -43
@@ -48,7 +48,7 @@ struct v4l2_window32 {
 
 static int get_v4l2_window32(struct v4l2_window *kp, struct v4l2_window32 __user *up)
 {
-	if (!access_ok(VERIFY_READ, up, sizeof(struct v4l2_window32)) ||
+	if (!access_ok(VERIFY_READ, up, sizeof(*up)) ||
 	    copy_from_user(&kp->w, &up->w, sizeof(up->w)) ||
 	    get_user(kp->field, &up->field) ||
 	    get_user(kp->chromakey, &up->chromakey) ||
@@ -66,7 +66,7 @@ static int get_v4l2_window32(struct v4l2
 		if (get_user(p, &up->clips))
 			return -EFAULT;
 		uclips = compat_ptr(p);
-		kclips = compat_alloc_user_space(n * sizeof(struct v4l2_clip));
+		kclips = compat_alloc_user_space(n * sizeof(*kclips));
 		kp->clips = kclips;
 		while (--n >= 0) {
 			if (copy_in_user(&kclips->c, &uclips->c, sizeof(uclips->c)))
@@ -164,14 +164,14 @@ static int __get_v4l2_format32(struct v4
 
 static int get_v4l2_format32(struct v4l2_format *kp, struct v4l2_format32 __user *up)
 {
-	if (!access_ok(VERIFY_READ, up, sizeof(struct v4l2_format32)))
+	if (!access_ok(VERIFY_READ, up, sizeof(*up)))
 		return -EFAULT;
 	return __get_v4l2_format32(kp, up);
 }
 
 static int get_v4l2_create32(struct v4l2_create_buffers *kp, struct v4l2_create_buffers32 __user *up)
 {
-	if (!access_ok(VERIFY_READ, up, sizeof(struct v4l2_create_buffers32)) ||
+	if (!access_ok(VERIFY_READ, up, sizeof(*up)) ||
 	    copy_from_user(kp, up, offsetof(struct v4l2_create_buffers32, format)))
 		return -EFAULT;
 	return __get_v4l2_format32(&kp->format, &up->format);
@@ -218,14 +218,14 @@ static int __put_v4l2_format32(struct v4
 
 static int put_v4l2_format32(struct v4l2_format *kp, struct v4l2_format32 __user *up)
 {
-	if (!access_ok(VERIFY_WRITE, up, sizeof(struct v4l2_format32)))
+	if (!access_ok(VERIFY_WRITE, up, sizeof(*up)))
 		return -EFAULT;
 	return __put_v4l2_format32(kp, up);
 }
 
 static int put_v4l2_create32(struct v4l2_create_buffers *kp, struct v4l2_create_buffers32 __user *up)
 {
-	if (!access_ok(VERIFY_WRITE, up, sizeof(struct v4l2_create_buffers32)) ||
+	if (!access_ok(VERIFY_WRITE, up, sizeof(*up)) ||
 	    copy_to_user(up, kp, offsetof(struct v4l2_create_buffers32, format)) ||
 	    copy_to_user(up->reserved, kp->reserved, sizeof(kp->reserved)))
 		return -EFAULT;
@@ -244,7 +244,7 @@ struct v4l2_standard32 {
 static int get_v4l2_standard32(struct v4l2_standard *kp, struct v4l2_standard32 __user *up)
 {
 	/* other fields are not set by the user, nor used by the driver */
-	if (!access_ok(VERIFY_READ, up, sizeof(struct v4l2_standard32)) ||
+	if (!access_ok(VERIFY_READ, up, sizeof(*up)) ||
 	    get_user(kp->index, &up->index))
 		return -EFAULT;
 	return 0;
@@ -252,14 +252,14 @@ static int get_v4l2_standard32(struct v4
 
 static int put_v4l2_standard32(struct v4l2_standard *kp, struct v4l2_standard32 __user *up)
 {
-	if (!access_ok(VERIFY_WRITE, up, sizeof(struct v4l2_standard32)) ||
+	if (!access_ok(VERIFY_WRITE, up, sizeof(*up)) ||
 	    put_user(kp->index, &up->index) ||
 	    put_user(kp->id, &up->id) ||
-	    copy_to_user(up->name, kp->name, 24) ||
+	    copy_to_user(up->name, kp->name, sizeof(up->name)) ||
 	    copy_to_user(&up->frameperiod, &kp->frameperiod,
 			 sizeof(kp->frameperiod)) ||
 	    put_user(kp->framelines, &up->framelines) ||
-	    copy_to_user(up->reserved, kp->reserved, 4 * sizeof(__u32)))
+	    copy_to_user(up->reserved, kp->reserved, sizeof(kp->reserved)))
 		return -EFAULT;
 	return 0;
 }
@@ -307,7 +307,7 @@ static int get_v4l2_plane32(struct v4l2_
 
 	if (copy_in_user(up, up32, 2 * sizeof(__u32)) ||
 	    copy_in_user(&up->data_offset, &up32->data_offset,
-			 sizeof(__u32)))
+			 sizeof(up->data_offset)))
 		return -EFAULT;
 
 	if (memory == V4L2_MEMORY_USERPTR) {
@@ -317,11 +317,11 @@ static int get_v4l2_plane32(struct v4l2_
 		if (put_user((unsigned long)up_pln, &up->m.userptr))
 			return -EFAULT;
 	} else if (memory == V4L2_MEMORY_DMABUF) {
-		if (copy_in_user(&up->m.fd, &up32->m.fd, sizeof(int)))
+		if (copy_in_user(&up->m.fd, &up32->m.fd, sizeof(up32->m.fd)))
 			return -EFAULT;
 	} else {
 		if (copy_in_user(&up->m.mem_offset, &up32->m.mem_offset,
-				 sizeof(__u32)))
+				 sizeof(up32->m.mem_offset)))
 			return -EFAULT;
 	}
 
@@ -333,19 +333,19 @@ static int put_v4l2_plane32(struct v4l2_
 {
 	if (copy_in_user(up32, up, 2 * sizeof(__u32)) ||
 	    copy_in_user(&up32->data_offset, &up->data_offset,
-			 sizeof(__u32)))
+			 sizeof(up->data_offset)))
 		return -EFAULT;
 
 	/* For MMAP, driver might've set up the offset, so copy it back.
 	 * USERPTR stays the same (was userspace-provided), so no copying. */
 	if (memory == V4L2_MEMORY_MMAP)
 		if (copy_in_user(&up32->m.mem_offset, &up->m.mem_offset,
-				 sizeof(__u32)))
+				 sizeof(up->m.mem_offset)))
 			return -EFAULT;
 	/* For DMABUF, driver might've set up the fd, so copy it back. */
 	if (memory == V4L2_MEMORY_DMABUF)
 		if (copy_in_user(&up32->m.fd, &up->m.fd,
-				 sizeof(int)))
+				 sizeof(up->m.fd)))
 			return -EFAULT;
 
 	return 0;
@@ -358,7 +358,7 @@ static int get_v4l2_buffer32(struct v4l2
 	compat_caddr_t p;
 	int ret;
 
-	if (!access_ok(VERIFY_READ, up, sizeof(struct v4l2_buffer32)) ||
+	if (!access_ok(VERIFY_READ, up, sizeof(*up)) ||
 	    get_user(kp->index, &up->index) ||
 	    get_user(kp->type, &up->type) ||
 	    get_user(kp->flags, &up->flags) ||
@@ -370,8 +370,7 @@ static int get_v4l2_buffer32(struct v4l2
 		if (get_user(kp->bytesused, &up->bytesused) ||
 		    get_user(kp->field, &up->field) ||
 		    get_user(kp->timestamp.tv_sec, &up->timestamp.tv_sec) ||
-		    get_user(kp->timestamp.tv_usec,
-			     &up->timestamp.tv_usec))
+		    get_user(kp->timestamp.tv_usec, &up->timestamp.tv_usec))
 			return -EFAULT;
 
 	if (V4L2_TYPE_IS_MULTIPLANAR(kp->type)) {
@@ -391,13 +390,12 @@ static int get_v4l2_buffer32(struct v4l2
 
 		uplane32 = compat_ptr(p);
 		if (!access_ok(VERIFY_READ, uplane32,
-			       kp->length * sizeof(struct v4l2_plane32)))
+			       kp->length * sizeof(*uplane32)))
 			return -EFAULT;
 
 		/* We don't really care if userspace decides to kill itself
 		 * by passing a very big num_planes value */
-		uplane = compat_alloc_user_space(kp->length *
-						 sizeof(struct v4l2_plane));
+		uplane = compat_alloc_user_space(kp->length * sizeof(*uplane));
 		kp->m.planes = (__force struct v4l2_plane *)uplane;
 
 		for (num_planes = 0; num_planes < kp->length; num_planes++) {
@@ -445,7 +443,7 @@ static int put_v4l2_buffer32(struct v4l2
 	int num_planes;
 	int ret;
 
-	if (!access_ok(VERIFY_WRITE, up, sizeof(struct v4l2_buffer32)) ||
+	if (!access_ok(VERIFY_WRITE, up, sizeof(*up)) ||
 	    put_user(kp->index, &up->index) ||
 	    put_user(kp->type, &up->type) ||
 	    put_user(kp->flags, &up->flags) ||
@@ -456,8 +454,7 @@ static int put_v4l2_buffer32(struct v4l2
 	    put_user(kp->field, &up->field) ||
 	    put_user(kp->timestamp.tv_sec, &up->timestamp.tv_sec) ||
 	    put_user(kp->timestamp.tv_usec, &up->timestamp.tv_usec) ||
-	    copy_to_user(&up->timecode, &kp->timecode,
-			 sizeof(struct v4l2_timecode)) ||
+	    copy_to_user(&up->timecode, &kp->timecode, sizeof(kp->timecode)) ||
 	    put_user(kp->sequence, &up->sequence) ||
 	    put_user(kp->reserved2, &up->reserved2) ||
 	    put_user(kp->reserved, &up->reserved) ||
@@ -525,7 +522,7 @@ static int get_v4l2_framebuffer32(struct
 {
 	u32 tmp;
 
-	if (!access_ok(VERIFY_READ, up, sizeof(struct v4l2_framebuffer32)) ||
+	if (!access_ok(VERIFY_READ, up, sizeof(*up)) ||
 	    get_user(tmp, &up->base) ||
 	    get_user(kp->capability, &up->capability) ||
 	    get_user(kp->flags, &up->flags) ||
@@ -539,7 +536,7 @@ static int put_v4l2_framebuffer32(struct
 {
 	u32 tmp = (u32)((unsigned long)kp->base);
 
-	if (!access_ok(VERIFY_WRITE, up, sizeof(struct v4l2_framebuffer32)) ||
+	if (!access_ok(VERIFY_WRITE, up, sizeof(*up)) ||
 	    put_user(tmp, &up->base) ||
 	    put_user(kp->capability, &up->capability) ||
 	    put_user(kp->flags, &up->flags) ||
@@ -564,14 +561,14 @@ struct v4l2_input32 {
    Otherwise it is identical to the 32-bit version. */
 static inline int get_v4l2_input32(struct v4l2_input *kp, struct v4l2_input32 __user *up)
 {
-	if (copy_from_user(kp, up, sizeof(struct v4l2_input32)))
+	if (copy_from_user(kp, up, sizeof(*up)))
 		return -EFAULT;
 	return 0;
 }
 
 static inline int put_v4l2_input32(struct v4l2_input *kp, struct v4l2_input32 __user *up)
 {
-	if (copy_to_user(up, kp, sizeof(struct v4l2_input32)))
+	if (copy_to_user(up, kp, sizeof(*up)))
 		return -EFAULT;
 	return 0;
 }
@@ -619,12 +616,11 @@ static int get_v4l2_ext_controls32(struc
 	unsigned int n;
 	compat_caddr_t p;
 
-	if (!access_ok(VERIFY_READ, up, sizeof(struct v4l2_ext_controls32)) ||
+	if (!access_ok(VERIFY_READ, up, sizeof(*up)) ||
 	    get_user(kp->which, &up->which) ||
 	    get_user(kp->count, &up->count) ||
 	    get_user(kp->error_idx, &up->error_idx) ||
-	    copy_from_user(kp->reserved, up->reserved,
-			   sizeof(kp->reserved)))
+	    copy_from_user(kp->reserved, up->reserved, sizeof(kp->reserved)))
 		return -EFAULT;
 	if (kp->count == 0) {
 		kp->controls = NULL;
@@ -635,11 +631,9 @@ static int get_v4l2_ext_controls32(struc
 	if (get_user(p, &up->controls))
 		return -EFAULT;
 	ucontrols = compat_ptr(p);
-	if (!access_ok(VERIFY_READ, ucontrols,
-		       kp->count * sizeof(struct v4l2_ext_control32)))
+	if (!access_ok(VERIFY_READ, ucontrols, kp->count * sizeof(*ucontrols)))
 		return -EFAULT;
-	kcontrols = compat_alloc_user_space(kp->count *
-					    sizeof(struct v4l2_ext_control));
+	kcontrols = compat_alloc_user_space(kp->count * sizeof(*kcontrols));
 	kp->controls = (__force struct v4l2_ext_control *)kcontrols;
 	for (n = 0; n < kp->count; n++) {
 		u32 id;
@@ -671,7 +665,7 @@ static int put_v4l2_ext_controls32(struc
 	int n = kp->count;
 	compat_caddr_t p;
 
-	if (!access_ok(VERIFY_WRITE, up, sizeof(struct v4l2_ext_controls32)) ||
+	if (!access_ok(VERIFY_WRITE, up, sizeof(*up)) ||
 	    put_user(kp->which, &up->which) ||
 	    put_user(kp->count, &up->count) ||
 	    put_user(kp->error_idx, &up->error_idx) ||
@@ -683,8 +677,7 @@ static int put_v4l2_ext_controls32(struc
 	if (get_user(p, &up->controls))
 		return -EFAULT;
 	ucontrols = compat_ptr(p);
-	if (!access_ok(VERIFY_WRITE, ucontrols,
-		       n * sizeof(struct v4l2_ext_control32)))
+	if (!access_ok(VERIFY_WRITE, ucontrols, n * sizeof(*ucontrols)))
 		return -EFAULT;
 
 	while (--n >= 0) {
@@ -721,7 +714,7 @@ struct v4l2_event32 {
 
 static int put_v4l2_event32(struct v4l2_event *kp, struct v4l2_event32 __user *up)
 {
-	if (!access_ok(VERIFY_WRITE, up, sizeof(struct v4l2_event32)) ||
+	if (!access_ok(VERIFY_WRITE, up, sizeof(*up)) ||
 	    put_user(kp->type, &up->type) ||
 	    copy_to_user(&up->u, &kp->u, sizeof(kp->u)) ||
 	    put_user(kp->pending, &up->pending) ||
@@ -729,7 +722,7 @@ static int put_v4l2_event32(struct v4l2_
 	    put_user(kp->timestamp.tv_sec, &up->timestamp.tv_sec) ||
 	    put_user(kp->timestamp.tv_nsec, &up->timestamp.tv_nsec) ||
 	    put_user(kp->id, &up->id) ||
-	    copy_to_user(up->reserved, kp->reserved, 8 * sizeof(__u32)))
+	    copy_to_user(up->reserved, kp->reserved, sizeof(kp->reserved)))
 		return -EFAULT;
 	return 0;
 }
@@ -746,7 +739,7 @@ static int get_v4l2_edid32(struct v4l2_e
 {
 	u32 tmp;
 
-	if (!access_ok(VERIFY_READ, up, sizeof(struct v4l2_edid32)) ||
+	if (!access_ok(VERIFY_READ, up, sizeof(*up)) ||
 	    get_user(kp->pad, &up->pad) ||
 	    get_user(kp->start_block, &up->start_block) ||
 	    get_user(kp->blocks, &up->blocks) ||
@@ -761,7 +754,7 @@ static int put_v4l2_edid32(struct v4l2_e
 {
 	u32 tmp = (u32)((unsigned long)kp->edid);
 
-	if (!access_ok(VERIFY_WRITE, up, sizeof(struct v4l2_edid32)) ||
+	if (!access_ok(VERIFY_WRITE, up, sizeof(*up)) ||
 	    put_user(kp->pad, &up->pad) ||
 	    put_user(kp->start_block, &up->start_block) ||
 	    put_user(kp->blocks, &up->blocks) ||
author maintainer
#120 lore raw

PATCH 120/202 media: v4l2-compat-ioctl32.c: copy m.userptr in put_v4l2_plane32

In reply to Greg Kroah-Hartman

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Hans Verkuil <[email protected]>

commit 8ed5a59dcb47a6f76034ee760b36e089f3e82529 upstream.

The struct v4l2_plane32 should set m.userptr as well. The same happens in v4l2_buffer32 and v4l2-compliance tests for this.

---
 drivers/media/v4l2-core/v4l2-compat-ioctl32.c |   47 +++++++++++++++-----------
 1 file changed, 28 insertions(+), 19 deletions(-)
drivers/media/v4l2-core/v4l2-compat-ioctl32.c +28 -19
@@ -310,19 +310,24 @@ static int get_v4l2_plane32(struct v4l2_
 			 sizeof(up->data_offset)))
 		return -EFAULT;
 
-	if (memory == V4L2_MEMORY_USERPTR) {
+	switch (memory) {
+	case V4L2_MEMORY_MMAP:
+	case V4L2_MEMORY_OVERLAY:
+		if (copy_in_user(&up->m.mem_offset, &up32->m.mem_offset,
+				 sizeof(up32->m.mem_offset)))
+			return -EFAULT;
+		break;
+	case V4L2_MEMORY_USERPTR:
 		if (get_user(p, &up32->m.userptr))
 			return -EFAULT;
 		up_pln = compat_ptr(p);
 		if (put_user((unsigned long)up_pln, &up->m.userptr))
 			return -EFAULT;
-	} else if (memory == V4L2_MEMORY_DMABUF) {
+		break;
+	case V4L2_MEMORY_DMABUF:
 		if (copy_in_user(&up->m.fd, &up32->m.fd, sizeof(up32->m.fd)))
 			return -EFAULT;
-	} else {
-		if (copy_in_user(&up->m.mem_offset, &up32->m.mem_offset,
-				 sizeof(up32->m.mem_offset)))
-			return -EFAULT;
+		break;
 	}
 
 	return 0;
@@ -331,22 +336,32 @@ static int get_v4l2_plane32(struct v4l2_
 static int put_v4l2_plane32(struct v4l2_plane __user *up, struct v4l2_plane32 __user *up32,
 			    enum v4l2_memory memory)
 {
+	unsigned long p;
+
 	if (copy_in_user(up32, up, 2 * sizeof(__u32)) ||
 	    copy_in_user(&up32->data_offset, &up->data_offset,
 			 sizeof(up->data_offset)))
 		return -EFAULT;
 
-	/* For MMAP, driver might've set up the offset, so copy it back.
-	 * USERPTR stays the same (was userspace-provided), so no copying. */
-	if (memory == V4L2_MEMORY_MMAP)
+	switch (memory) {
+	case V4L2_MEMORY_MMAP:
+	case V4L2_MEMORY_OVERLAY:
 		if (copy_in_user(&up32->m.mem_offset, &up->m.mem_offset,
 				 sizeof(up->m.mem_offset)))
 			return -EFAULT;
-	/* For DMABUF, driver might've set up the fd, so copy it back. */
-	if (memory == V4L2_MEMORY_DMABUF)
+		break;
+	case V4L2_MEMORY_USERPTR:
+		if (get_user(p, &up->m.userptr) ||
+		    put_user((compat_ulong_t)ptr_to_compat((__force void *)p),
+			     &up32->m.userptr))
+			return -EFAULT;
+		break;
+	case V4L2_MEMORY_DMABUF:
 		if (copy_in_user(&up32->m.fd, &up->m.fd,
 				 sizeof(up->m.fd)))
 			return -EFAULT;
+		break;
+	}
 
 	return 0;
 }
@@ -408,6 +423,7 @@ static int get_v4l2_buffer32(struct v4l2
 	} else {
 		switch (kp->memory) {
 		case V4L2_MEMORY_MMAP:
+		case V4L2_MEMORY_OVERLAY:
 			if (get_user(kp->m.offset, &up->m.offset))
 				return -EFAULT;
 			break;
@@ -421,10 +437,6 @@ static int get_v4l2_buffer32(struct v4l2
 				kp->m.userptr = (unsigned long)compat_ptr(tmp);
 			}
 			break;
-		case V4L2_MEMORY_OVERLAY:
-			if (get_user(kp->m.offset, &up->m.offset))
-				return -EFAULT;
-			break;
 		case V4L2_MEMORY_DMABUF:
 			if (get_user(kp->m.fd, &up->m.fd))
 				return -EFAULT;
@@ -481,6 +493,7 @@ static int put_v4l2_buffer32(struct v4l2
 	} else {
 		switch (kp->memory) {
 		case V4L2_MEMORY_MMAP:
+		case V4L2_MEMORY_OVERLAY:
 			if (put_user(kp->m.offset, &up->m.offset))
 				return -EFAULT;
 			break;
@@ -488,10 +501,6 @@ static int put_v4l2_buffer32(struct v4l2
 			if (put_user(kp->m.userptr, &up->m.userptr))
 				return -EFAULT;
 			break;
-		case V4L2_MEMORY_OVERLAY:
-			if (put_user(kp->m.offset, &up->m.offset))
-				return -EFAULT;
-			break;
 		case V4L2_MEMORY_DMABUF:
 			if (put_user(kp->m.fd, &up->m.fd))
 				return -EFAULT;
author maintainer
#121 lore raw

PATCH 121/202 media: v4l2-compat-ioctl32.c: fix ctrl_is_pointer

In reply to Greg Kroah-Hartman

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Hans Verkuil <[email protected]>

commit b8c601e8af2d08f733d74defa8465303391bb930 upstream.

ctrl_is_pointer just hardcoded two known string controls, but that caused problems when using e.g. custom controls that use a pointer for the payload.

Reimplement this function: it now finds the v4l2_ctrl (if the driver uses the control framework) or it calls vidioc_query_ext_ctrl (if the driver implements that directly).

In both cases it can now check if the control is a pointer control or not.

---
 drivers/media/v4l2-core/v4l2-compat-ioctl32.c |   59 +++++++++++++++++---------
 1 file changed, 39 insertions(+), 20 deletions(-)
drivers/media/v4l2-core/v4l2-compat-ioctl32.c +39 -20
@@ -18,6 +18,8 @@
 #include <linux/videodev2.h>
 #include <linux/v4l2-subdev.h>
 #include <media/v4l2-dev.h>
+#include <media/v4l2-fh.h>
+#include <media/v4l2-ctrls.h>
 #include <media/v4l2-ioctl.h>
 
 static long native_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
@@ -601,24 +603,39 @@ struct v4l2_ext_control32 {
 	};
 } __attribute__ ((packed));
 
-/* The following function really belong in v4l2-common, but that causes
-   a circular dependency between modules. We need to think about this, but
-   for now this will do. */
-
-/* Return non-zero if this control is a pointer type. Currently only
-   type STRING is a pointer type. */
-static inline int ctrl_is_pointer(u32 id)
-{
-	switch (id) {
-	case V4L2_CID_RDS_TX_PS_NAME:
-	case V4L2_CID_RDS_TX_RADIO_TEXT:
-		return 1;
-	default:
-		return 0;
+/* Return true if this control is a pointer type. */
+static inline bool ctrl_is_pointer(struct file *file, u32 id)
+{
+	struct video_device *vdev = video_devdata(file);
+	struct v4l2_fh *fh = NULL;
+	struct v4l2_ctrl_handler *hdl = NULL;
+	struct v4l2_query_ext_ctrl qec = { id };
+	const struct v4l2_ioctl_ops *ops = vdev->ioctl_ops;
+
+	if (test_bit(V4L2_FL_USES_V4L2_FH, &vdev->flags))
+		fh = file->private_data;
+
+	if (fh && fh->ctrl_handler)
+		hdl = fh->ctrl_handler;
+	else if (vdev->ctrl_handler)
+		hdl = vdev->ctrl_handler;
+
+	if (hdl) {
+		struct v4l2_ctrl *ctrl = v4l2_ctrl_find(hdl, id);
+
+		return ctrl && ctrl->is_ptr;
 	}
+
+	if (!ops->vidioc_query_ext_ctrl)
+		return false;
+
+	return !ops->vidioc_query_ext_ctrl(file, fh, &qec) &&
+		(qec.flags & V4L2_CTRL_FLAG_HAS_PAYLOAD);
 }
 
-static int get_v4l2_ext_controls32(struct v4l2_ext_controls *kp, struct v4l2_ext_controls32 __user *up)
+static int get_v4l2_ext_controls32(struct file *file,
+				   struct v4l2_ext_controls *kp,
+				   struct v4l2_ext_controls32 __user *up)
 {
 	struct v4l2_ext_control32 __user *ucontrols;
 	struct v4l2_ext_control __user *kcontrols;
@@ -651,7 +668,7 @@ static int get_v4l2_ext_controls32(struc
 			return -EFAULT;
 		if (get_user(id, &kcontrols->id))
 			return -EFAULT;
-		if (ctrl_is_pointer(id)) {
+		if (ctrl_is_pointer(file, id)) {
 			void __user *s;
 
 			if (get_user(p, &ucontrols->string))
@@ -666,7 +683,9 @@ static int get_v4l2_ext_controls32(struc
 	return 0;
 }
 
-static int put_v4l2_ext_controls32(struct v4l2_ext_controls *kp, struct v4l2_ext_controls32 __user *up)
+static int put_v4l2_ext_controls32(struct file *file,
+				   struct v4l2_ext_controls *kp,
+				   struct v4l2_ext_controls32 __user *up)
 {
 	struct v4l2_ext_control32 __user *ucontrols;
 	struct v4l2_ext_control __user *kcontrols =
@@ -698,7 +717,7 @@ static int put_v4l2_ext_controls32(struc
 		/* Do not modify the pointer when copying a pointer control.
 		   The contents of the pointer was changed, not the pointer
 		   itself. */
-		if (ctrl_is_pointer(id))
+		if (ctrl_is_pointer(file, id))
 			size -= sizeof(ucontrols->value64);
 		if (copy_in_user(ucontrols, kcontrols, size))
 			return -EFAULT;
@@ -912,7 +931,7 @@ static long do_video_ioctl(struct file *
 	case VIDIOC_G_EXT_CTRLS:
 	case VIDIOC_S_EXT_CTRLS:
 	case VIDIOC_TRY_EXT_CTRLS:
-		err = get_v4l2_ext_controls32(&karg.v2ecs, up);
+		err = get_v4l2_ext_controls32(file, &karg.v2ecs, up);
 		compatible_arg = 0;
 		break;
 	case VIDIOC_DQEVENT:
@@ -939,7 +958,7 @@ static long do_video_ioctl(struct file *
 	case VIDIOC_G_EXT_CTRLS:
 	case VIDIOC_S_EXT_CTRLS:
 	case VIDIOC_TRY_EXT_CTRLS:
-		if (put_v4l2_ext_controls32(&karg.v2ecs, up))
+		if (put_v4l2_ext_controls32(file, &karg.v2ecs, up))
 			err = -EFAULT;
 		break;
 	case VIDIOC_S_EDID:
author maintainer
#122 lore raw

PATCH 122/202 media: v4l2-compat-ioctl32.c: copy clip list in put_v4l2_window32

In reply to Greg Kroah-Hartman

4.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Hans Verkuil <[email protected]>

commit a751be5b142ef6bcbbb96d9899516f4d9c8d0ef4 upstream.

put_v4l2_window32() didn't copy back the clip list to userspace. Drivers can update the clip rectangles, so this should be done.

---
 drivers/media/v4l2-core/v4l2-compat-ioctl32.c |   59 +++++++++++++++++---------
 1 file changed, 40 insertions(+), 19 deletions(-)
drivers/media/v4l2-core/v4l2-compat-ioctl32.c +40 -19
@@ -50,6 +50,11 @@ struct v4l2_window32 {
 
 static int get_v4l2_window32(struct v4l2_window *kp, struct v4l2_window32 __user *up)
 {
+	struct v4l2_clip32 __user *uclips;
+	struct v4l2_clip __user *kclips;
+	compat_caddr_t p;
+	u32 n;
+
 	if (!access_ok(VERIFY_READ, up, sizeof(*up)) ||
 	    copy_from_user(&kp->w, &up->w, sizeof(up->w)) ||
 	    get_user(kp->field, &up->field) ||
@@ -59,38 +64,54 @@ static int get_v4l2_window32(struct v4l2
 		return -EFAULT;
 	if (kp->clipcount > 2048)
 		return -EINVAL;
-	if (kp->clipcount) {
-		struct v4l2_clip32 __user *uclips;
-		struct v4l2_clip __user *kclips;
-		int n = kp->clipcount;
-		compat_caddr_t p;
+	if (!kp->clipcount) {
+		kp->clips = NULL;
+		return 0;
+	}
 
-		if (get_user(p, &up->clips))
+	n = kp->clipcount;
+	if (get_user(p, &up->clips))
+		return -EFAULT;
+	uclips = compat_ptr(p);
+	kclips = compat_alloc_user_space(n * sizeof(*kclips));
+	kp->clips = kclips;
+	while (n--) {
+		if (copy_in_user(&kclips->c, &uclips->c, sizeof(uclips->c)))
 			return -EFAULT;
-		uclips = compat_ptr(p);
-		kclips = compat_alloc_user_space(n * sizeof(*kclips));
-		kp->clips = kclips;
-		while (--n >= 0) {
-			if (copy_in_user(&kclips->c, &uclips->c, sizeof(uclips->c)))
-				return -EFAULT;
-			if (put_user(n ? kclips + 1 : NULL, &kclips->next))
-				return -EFAULT;
-			uclips += 1;
-			kclips += 1;
-		}
-	} else
-		kp->clips = NULL;
+		if (put_user(n ? kclips + 1 : NULL, &kclips->next))
+			return -EFAULT;
+		uclips++;
+		kclips++;
+	}
 	return 0;
 }
 
 static int put_v4l2_window32(struct v4l2_window *kp, struct v4l2_window32 __user *up)
 {
+	struct v4l2_clip __user *kclips = kp->clips;
+	struct v4l2_clip32 __user *uclips;
+	u32 n = kp->clipcount;
+	compat_caddr_t p;
+
 	if (copy_to_user(&up->w, &kp->w, sizeof(kp->w)) ||
 	    put_user(kp->field, &up->field) ||
 	    put_user(kp->chromakey, &up->chromakey) ||
 	    put_user(kp->clipcount, &up->clipcount) ||
 	    put_user(kp->global_alpha, &up->global_alpha))
 		return -EFAULT;
+
+	if (!kp->clipcount)
+		return 0;
+
+	if (get_user(p, &up->clips))
+		return -EFAULT;
+	uclips = compat_ptr(p);
+	while (n--) {
+		if (copy_in_user(&uclips->c, &kclips->c, sizeof(uclips->c)))
+			return -EFAULT;
+		uclips++;
+		kclips++;
+	}
 	return 0;
 }