Commit 74e19ef0ff80 ("uaccess: Add speculation barrier to
copy_from_user()") built fine on x86-64 and arm64, and that's the extent
of my local build testing.
It turns out those got the <linux/nospec.h> include incidentally through
other header files (<linux/kvm_host.h> in particular), but that was not
true of other architectures, resulting in build errors
kernel/bpf/core.c: In function ‘___bpf_prog_run’:
kernel/bpf/core.c:1913:3: error: implicit declaration of function ‘barrier_nospec’
so just make sure to explicitly include the proper <linux/nospec.h>
header file to make everybody see it.
The randstruct support released in Clang 15 is unsafe to use due to a
bug that can cause miscompilations: "-frandomize-layout-seed
inconsistently randomizes all-function-pointers structs"
(https://github.com/llvm/llvm-project/issues/60349). It has been fixed
on the Clang 16 release branch, so add a Clang version check.
With clang's kernel control flow integrity (kCFI, CONFIG_CFI_CLANG),
indirect call targets are validated against the expected function
pointer prototype to make sure the call target is valid to help mitigate
ROP attacks. If they are not identical, there is a failure at run time,
which manifests as either a kernel panic or thread getting killed.
ext4_feat_ktype was setting the "release" handler to "kfree", which
doesn't have a matching function prototype. Add a simple wrapper
with the correct prototype.
This was found as a result of Clang's new -Wcast-function-type-strict
flag, which is more sensitive than the simpler -Wcast-function-type,
which only checks for type width mismatches.
Note that this code is only reached when ext4 is a loadable module and
it is being unloaded:
On some Lenovo Legion models, the backlight might be driven by either
one of nvidia_wmi_ec_backlight or amdgpu_bl0 at different times.
When the Nvidia WMI EC backlight interface reports the backlight is
controlled by the EC, the current backlight handling only registers
nvidia_wmi_ec_backlight (and registers no other backlight interfaces).
This hides (never registers) the amdgpu_bl0 interface, where as prior
to 6.1.4 users would have both nvidia_wmi_ec_backlight and amdgpu_bl0
and could work around things in userspace.
Add a force module parameter which can be used with acpi_backlight=native
to restore the old behavior as a workound (for now) by passing:
We've moved the upstream Linux Kernel audit subsystem discussions to
a new mailing list, this patch updates the MAINTAINERS info with the
new list address.
Marking this for stable inclusion to help speed uptake of the new
list across all of the supported kernel releases. This is a doc only
patch so the risk should be close to nil.
Cc: stable@vger.kernel.org Signed-off-by: Paul Moore <paul@paul-moore.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Commit e3fffc1f0b47 ("devicetree: document new marvell-8xxx and
pwrseq-sd8787 options") documented a compatible string for SD8787 in
the devicetree bindings, but neglected to add it to the mwifiex driver.
Fixes: e3fffc1f0b47 ("devicetree: document new marvell-8xxx and pwrseq-sd8787 options") Signed-off-by: Lukas Wunner <lukas@wunner.de> Cc: stable@vger.kernel.org # v4.11+ Cc: Matt Ranostay <mranostay@ti.com> Signed-off-by: Kalle Valo <kvalo@kernel.org> Link: https://lore.kernel.org/r/320de5005ff3b8fd76be2d2b859fd021689c3681.1674827105.git.lukas@wunner.de Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
sh vmlinux fails to link with GNU ld < 2.40 (likely < 2.36) since
commit 99cb0d917ffa ("arch: fix broken BuildID for arm64 and riscv").
This is similar to fixes for powerpc and s390:
commit 4b9880dbf3bd ("powerpc/vmlinux.lds: Define RUNTIME_DISCARD_EXIT").
commit a494398bde27 ("s390: define RUNTIME_DISCARD_EXIT to fix link error
with GNU ld < 2.36").
$ sh4-linux-gnu-ld --version | head -n1
GNU ld (GNU Binutils for Debian) 2.35.2
$ make ARCH=sh CROSS_COMPILE=sh4-linux-gnu- microdev_defconfig
$ make ARCH=sh CROSS_COMPILE=sh4-linux-gnu-
`.exit.text' referenced in section `__bug_table' of crypto/algboss.o:
defined in discarded section `.exit.text' of crypto/algboss.o
`.exit.text' referenced in section `__bug_table' of
drivers/char/hw_random/core.o: defined in discarded section
`.exit.text' of drivers/char/hw_random/core.o
make[2]: *** [scripts/Makefile.vmlinux:34: vmlinux] Error 1
make[1]: *** [Makefile:1252: vmlinux] Error 2
arch/sh/kernel/vmlinux.lds.S keeps EXIT_TEXT:
/*
* .exit.text is discarded at runtime, not link time, to deal with
* references from __bug_table
*/
.exit.text : AT(ADDR(.exit.text)) { EXIT_TEXT }
However, EXIT_TEXT is thrown away by
DISCARD(include/asm-generic/vmlinux.lds.h) because
sh does not define RUNTIME_DISCARD_EXIT.
GNU ld 2.40 does not have this issue and builds fine.
This corresponds with Masahiro's comments in a494398bde27:
"Nathan [Chancellor] also found that binutils
commit 21401fc7bf67 ("Duplicate output sections in scripts") cured this
issue, so we cannot reproduce it with binutils 2.36+, but it is better
to not rely on it."
Link: https://lkml.kernel.org/r/9166a8abdc0f979e50377e61780a4bba1dfa2f52.1674518464.git.tom.saeger@oracle.com Fixes: 99cb0d917ffa ("arch: fix broken BuildID for arm64 and riscv") Link: https://lore.kernel.org/all/Y7Jal56f6UBh1abE@dev-arch.thelio-3990X/ Link: https://lore.kernel.org/all/20230123194218.47ssfzhrpnv3xfez@oracle.com/ Signed-off-by: Tom Saeger <tom.saeger@oracle.com> Tested-by: John Paul Adrian Glaubitz <glaubitz@physik.fu-berlin.de> Cc: Ard Biesheuvel <ardb@kernel.org> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Christoph Hellwig <hch@lst.de> Cc: Dennis Gilmore <dennis@ausil.us> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Masahiro Yamada <masahiroy@kernel.org> Cc: Naresh Kamboju <naresh.kamboju@linaro.org> Cc: Nathan Chancellor <nathan@kernel.org> Cc: Palmer Dabbelt <palmer@rivosinc.com> Cc: Rich Felker <dalias@libc.org> Cc: Yoshinori Sato <ysato@users.sourceforge.jp> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Tom Saeger <tom.saeger@oracle.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Nathan Chancellor reports that the s390 vmlinux fails to link with
GNU ld < 2.36 since commit 99cb0d917ffa ("arch: fix broken BuildID
for arm64 and riscv").
It happens for defconfig, or more specifically for CONFIG_EXPOLINE=y.
$ s390x-linux-gnu-ld --version | head -n1
GNU ld (GNU Binutils for Debian) 2.35.2
$ make -s ARCH=s390 CROSS_COMPILE=s390x-linux-gnu- allnoconfig
$ ./scripts/config -e CONFIG_EXPOLINE
$ make -s ARCH=s390 CROSS_COMPILE=s390x-linux-gnu- olddefconfig
$ make -s ARCH=s390 CROSS_COMPILE=s390x-linux-gnu-
`.exit.text' referenced in section `.s390_return_reg' of drivers/base/dd.o: defined in discarded section `.exit.text' of drivers/base/dd.o
make[1]: *** [scripts/Makefile.vmlinux:34: vmlinux] Error 1
make: *** [Makefile:1252: vmlinux] Error 2
arch/s390/kernel/vmlinux.lds.S wants to keep EXIT_TEXT:
.exit.text : {
EXIT_TEXT
}
But, at the same time, EXIT_TEXT is thrown away by DISCARD because
s390 does not define RUNTIME_DISCARD_EXIT.
I still do not understand why the latter wins after 99cb0d917ffa,
but defining RUNTIME_DISCARD_EXIT seems correct because the comment
line in arch/s390/kernel/vmlinux.lds.S says:
/*
* .exit.text is discarded at runtime, not link time,
* to deal with references from __bug_table
*/
Nathan also found that binutils commit 21401fc7bf67 ("Duplicate output
sections in scripts") cured this issue, so we cannot reproduce it with
binutils 2.36+, but it is better to not rely on it.
Relocatable kernels must not discard relocations, they need to be
processed at runtime. As such they are included for CONFIG_RELOCATABLE
builds in the powerpc linker script (line 340).
However they are also unconditionally discarded later in the
script (line 414). Previously that worked because the earlier inclusion
superseded the discard.
However commit 99cb0d917ffa ("arch: fix broken BuildID for arm64 and
riscv") introduced an earlier use of DISCARD as part of the RO_DATA
macro (line 137). With binutils < 2.36 that causes the DISCARD
directives later in the script to be applied earlier, causing .rela* to
actually be discarded at link time, leading to build warnings and a
kernel that doesn't boot:
The powerpc linker script explicitly includes .exit.text, because
otherwise the link fails due to references from __bug_table and
__ex_table. The code is freed (discarded) at runtime along with
.init.text and data.
That has worked in the past despite powerpc not defining
RUNTIME_DISCARD_EXIT because DISCARDS appears late in the powerpc linker
script (line 410), and the explicit inclusion of .exit.text
earlier (line 280) supersedes the discard.
However commit 99cb0d917ffa ("arch: fix broken BuildID for arm64 and
riscv") introduced an earlier use of DISCARD as part of the RO_DATA
macro (line 136). With binutils < 2.36 that causes the DISCARD
directives later in the script to be applied earlier [1], causing
.exit.text to actually be discarded at link time, leading to build
errors:
'.exit.text' referenced in section '__bug_table' of crypto/algboss.o: defined in
discarded section '.exit.text' of crypto/algboss.o
'.exit.text' referenced in section '__ex_table' of drivers/nvdimm/core.o: defined in
discarded section '.exit.text' of drivers/nvdimm/core.o
Fix it by defining RUNTIME_DISCARD_EXIT, which causes the generic
DISCARDS macro to not include .exit.text at all.
Dennis Gilmore reports that the BuildID is missing in the arm64 vmlinux
since commit 994b7ac1697b ("arm64: remove special treatment for the
link order of head.o").
The issue is that the type of .notes section, which contains the BuildID,
changed from NOTES to PROGBITS.
Ard Biesheuvel figured out that whichever object gets linked first gets
to decide the type of a section. The PROGBITS type is the result of the
compiler emitting .note.GNU-stack as PROGBITS rather than NOTE.
While Ard provided a fix for arm64, I want to fix this globally because
the same issue is happening on riscv since commit 2348e6bf4421 ("riscv:
remove special treatment for the link order of head.o"). This problem
will happen in general for other architectures if they start to drop
unneeded entries from scripts/head-object-list.txt.
Discard .note.GNU-stack in include/asm-generic/vmlinux.lds.h.
Link: https://lore.kernel.org/lkml/CAABkxwuQoz1CTbyb57n0ZX65eSYiTonFCU8-LCQc=74D=xE=rA@mail.gmail.com/ Fixes: 994b7ac1697b ("arm64: remove special treatment for the link order of head.o") Fixes: 2348e6bf4421 ("riscv: remove special treatment for the link order of head.o") Reported-by: Dennis Gilmore <dennis@ausil.us> Suggested-by: Ard Biesheuvel <ardb@kernel.org> Signed-off-by: Masahiro Yamada <masahiroy@kernel.org> Acked-by: Palmer Dabbelt <palmer@rivosinc.com> Signed-off-by: Tom Saeger <tom.saeger@oracle.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
In the previous discussion (see the Link tag), Ard pointed out that
arm/arm64/kernel/head.o does not need any special treatment - the only
piece that must appear right at the start of the binary image is the
image header which is emitted into .head.text.
The linker script does the right thing to do. The build system does
not need to manipulate the link order of head.o.
arch/riscv/kernel/head.o does not need any special treatment - the only
requirement is the ".head.text" section must be placed before the
normal ".text" section.
The linker script does the right thing to do. The build system does
not need to manipulate the link order of head.o.
Where 0x35d is a static call site that's turned into a conditional
tail-call using the Jcc class of instructions.
Teach the in-line static call text patching about this.
Notably, since there is no conditional-ret, in that case patch the Jcc
to point at an empty stub function that does the ret -- or the return
thunk when needed.
Reported-by: "Erhard F." <erhard_f@mailbox.org> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Signed-off-by: Ingo Molnar <mingo@kernel.org> Reviewed-by: Masami Hiramatsu (Google) <mhiramat@kernel.org> Link: https://lore.kernel.org/r/Y9Kdg9QjHkr9G5b5@hirez.programming.kicks-ass.net
[nathan: Backport to 6.1:
- Use __x86_return_thunk instead of x86_return_thunk for func in
__static_call_transform()
- Remove ASM_FUNC_ALIGN in __static_call_return() asm, as call
depth tracking was merged in 6.2] Signed-off-by: Nathan Chancellor <nathan@kernel.org> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
In order to re-write Jcc.d32 instructions text_poke_bp() needs to be
taught about them.
The biggest hurdle is that the whole machinery is currently made for 5
byte instructions and extending this would grow struct text_poke_loc
which is currently a nice 16 bytes and used in an array.
However, since text_poke_loc contains a full copy of the (s32)
displacement, it is possible to map the Jcc.d32 2 byte opcodes to
Jcc.d8 1 byte opcode for the int3 emulation.
This then leaves the replacement bytes; fudge that by only storing the
last 5 bytes and adding the rule that 'length == 6' instruction will
be prefixed with a 0x0f byte.
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Signed-off-by: Ingo Molnar <mingo@kernel.org> Reviewed-by: Masami Hiramatsu (Google) <mhiramat@kernel.org> Link: https://lore.kernel.org/r/20230123210607.115718513@infradead.org
[nathan: Introduce is_jcc32() as part of this change; upstream
introduced it in 3b6c1747da48] Signed-off-by: Nathan Chancellor <nathan@kernel.org> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
The results of "access_ok()" can be mis-speculated. The result is that
you can end speculatively:
if (access_ok(from, size))
// Right here
even for bad from/size combinations. On first glance, it would be ideal
to just add a speculation barrier to "access_ok()" so that its results
can never be mis-speculated.
But there are lots of system calls just doing access_ok() via
"copy_to_user()" and friends (example: fstat() and friends). Those are
generally not problematic because they do not _consume_ data from
userspace other than the pointer. They are also very quick and common
system calls that should not be needlessly slowed down.
"copy_from_user()" on the other hand uses a user-controller pointer and
is frequently followed up with code that might affect caches. Take
something like this:
if (!copy_from_user(&kernelvar, uptr, size))
do_something_with(kernelvar);
If userspace passes in an evil 'uptr' that *actually* points to a kernel
addresses, and then do_something_with() has cache (or other)
side-effects, it could allow userspace to infer kernel data values.
Add a barrier to the common copy_from_user() code to prevent
mis-speculated values which happen after the copy.
Also add a stub for architectures that do not define barrier_nospec().
This makes the macro usable in generic code.
Since the barrier is now usable in generic code, the x86 #ifdef in the
BPF code can also go away.
Unsupported port speed can be set and cause error. Now fixing it
and return an error if setting unsupported speed.
This fix depends on the following, which was included in v6.2-rc1:
commit a61474c41e8c ("nfp: ethtool: support reporting link modes").
Fixes: 7c698737270f ("nfp: add support for .set_link_ksettings()") Signed-off-by: Yu Xiao <yu.xiao@corigine.com> Signed-off-by: Simon Horman <simon.horman@corigine.com> Signed-off-by: David S. Miller <davem@davemloft.net> Signed-off-by: Sasha Levin <sashal@kernel.org>
Add support for reporting link modes,
including `Supported link modes` and `Advertised link modes`,
via ethtool $DEV.
A new command `SPCODE_READ_MEDIA` is added to read info from
management firmware. Also, the mapping table `nfp_eth_media_table`
associates the link modes between NFP and kernel. Both of them
help to support this ability.
Signed-off-by: Yu Xiao <yu.xiao@corigine.com> Reviewed-by: Louis Peens <louis.peens@corigine.com> Signed-off-by: Simon Horman <simon.horman@corigine.com> Reviewed-by: Alexander Lobakin <alexandr.lobakin@intel.com> Link: https://lore.kernel.org/r/20221125113030.141642-1-simon.horman@corigine.com Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Stable-dep-of: 821de68c1f9c ("nfp: ethtool: fix the bug of setting unsupported port speed") Signed-off-by: Sasha Levin <sashal@kernel.org>
If a relocatable kernel is loaded at a non-zero address and told not to
relocate to zero (kdump or RELOCATABLE_TEST), the mapping of the
interrupt code at zero is left with RWX permissions.
That is a security weakness, and leads to a warning at boot if
CONFIG_DEBUG_WX is enabled:
The fix has two parts. Firstly the pages from zero up to the end of
interrupts need to be marked read-only, so that they are left with R-X
permissions. Secondly the mapping logic needs to be taught to ensure
there is a page boundary at the end of the interrupt region, so that the
permission change only applies to the interrupt text, and not the region
following it.
Fixes: c55d7b5e6426 ("powerpc: Remove STRICT_KERNEL_RWX incompatibility with RELOCATABLE") Reported-by: Sachin Sant <sachinp@linux.ibm.com> Tested-by: Sachin Sant <sachinp@linux.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/r/20230110124753.1325426-2-mpe@ellerman.id.au Signed-off-by: Sasha Levin <sashal@kernel.org>
Placing a declaration of evt_reset is pedantically invalid
according to the C standard. While GCC does not really care
and only warns with -Wpedantic, clang ignores the declaration
altogether with an error:
While KVM_XEN_EVTCHN_RESET is usually called with no vCPUs running,
if that happened it could cause a deadlock. This is due to
kvm_xen_eventfd_reset() doing a synchronize_srcu() inside
a kvm->lock critical section.
To avoid this, first collect all the evtchnfd objects in an
array and free all of them once the kvm->lock critical section
is over and th SRCU grace period has expired.
Reported-by: Michal Luczaj <mhal@rbox.co> Cc: David Woodhouse <dwmw@amazon.co.uk> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Signed-off-by: Sasha Levin <sashal@kernel.org>
The attribute __maybe_unused should remain only until the respective
info is not in the pciidlist. The info can't be added together
with its definition because that would cause the driver to automatically
probe for the device, while it's still not ready for that. However once
pciidlist contains it, the attribute can be removed.
| drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c:502:65: error:
| array subscript ‘struct kvaser_cmd_ext[0]’ is partly outside array
| bounds of ‘unsigned char[32]’ [-Werror=array-bounds=]
| 502 | ret = le16_to_cpu(((struct kvaser_cmd_ext *)cmd)->len);
kvaser_usb_hydra_cmd_size() returns the size of given command. It
depends on the command number (cmd->header.cmd_no). For extended
commands (cmd->header.cmd_no == CMD_EXTENDED) the above shown code is
executed.
Help gcc to recognize that this code path is not taken in all cases,
by calling kvaser_usb_hydra_cmd_size() directly after assigning the
command number.
Fixes: aec5fb2268b7 ("can: kvaser_usb: Add support for Kvaser USB hydra family") Cc: Jimmy Assarsson <extja@kvaser.com> Cc: Anssi Hannula <anssi.hannula@bitwise.fi> Link: https://lore.kernel.org/all/20221219110104.1073881-1-mkl@pengutronix.de Tested-by: Jimmy Assarsson <extja@kvaser.com> Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de> Signed-off-by: Sasha Levin <sashal@kernel.org>
According to Intel's document on Indirect Branch Restricted
Speculation, "Enabling IBRS does not prevent software from controlling
the predicted targets of indirect branches of unrelated software
executed later at the same predictor mode (for example, between two
different user applications, or two different virtual machines). Such
isolation can be ensured through use of the Indirect Branch Predictor
Barrier (IBPB) command." This applies to both basic and enhanced IBRS.
Since L1 and L2 VMs share hardware predictor modes (guest-user and
guest-kernel), hardware IBRS is not sufficient to virtualize
IBRS. (The way that basic IBRS is implemented on pre-eIBRS parts,
hardware IBRS is actually sufficient in practice, even though it isn't
sufficient architecturally.)
For virtual CPUs that support IBRS, add an indirect branch prediction
barrier on emulated VM-exit, to ensure that the predicted targets of
indirect branches executed in L1 cannot be controlled by software that
was executed in L2.
Since we typically don't intercept guest writes to IA32_SPEC_CTRL,
perform the IBPB at emulated VM-exit regardless of the current
IA32_SPEC_CTRL.IBRS value, even though the IBPB could technically be
deferred until L1 sets IA32_SPEC_CTRL.IBRS, if IA32_SPEC_CTRL.IBRS is
clear at emulated VM-exit.
This is CVE-2022-2196.
Fixes: 5c911beff20a ("KVM: nVMX: Skip IBPB when switching between vmcs01 and vmcs02") Cc: Sean Christopherson <seanjc@google.com> Signed-off-by: Jim Mattson <jmattson@google.com> Reviewed-by: Sean Christopherson <seanjc@google.com> Link: https://lore.kernel.org/r/20221019213620.1953281-3-jmattson@google.com Signed-off-by: Sean Christopherson <seanjc@google.com> Signed-off-by: Sasha Levin <sashal@kernel.org>
Skip the WRMSR fastpath in SVM's VM-Exit handler if the next RIP isn't
valid, e.g. because KVM is running with nrips=false. SVM must decode and
emulate to skip the WRMSR if the CPU doesn't provide the next RIP.
Getting the instruction bytes to decode the WRMSR requires reading guest
memory, which in turn means dereferencing memslots, and that isn't safe
because KVM doesn't hold SRCU when the fastpath runs.
Don't bother trying to enable the fastpath for this case, e.g. by doing
only the WRMSR and leaving the "skip" until later. NRIPS is supported on
all modern CPUs (KVM has considered making it mandatory), and the next
RIP will be valid the vast, vast majority of the time.
=============================
WARNING: suspicious RCU usage
6.0.0-smp--4e557fcd3d80-skip #13 Tainted: G O
-----------------------------
include/linux/kvm_host.h:954 suspicious rcu_dereference_check() usage!
other info that might help us debug this:
rcu_scheduler_active = 2, debug_locks = 1
1 lock held by stable/206475:
#0: ffff9d9dfebcc0f0 (&vcpu->mutex){+.+.}-{3:3}, at: kvm_vcpu_ioctl+0x8b/0x620 [kvm]
Treat any exception during instruction decode for EMULTYPE_SKIP as a
"full" emulation failure, i.e. signal failure instead of queuing the
exception. When decoding purely to skip an instruction, KVM and/or the
CPU has already done some amount of emulation that cannot be unwound,
e.g. on an EPT misconfig VM-Exit KVM has already processeed the emulated
MMIO. KVM already does this if a #UD is encountered, but not for other
exceptions, e.g. if a #PF is encountered during fetch.
In SVM's soft-injection use case, queueing the exception is particularly
problematic as queueing exceptions while injecting events can put KVM
into an infinite loop due to bailing from VM-Enter to service the newly
pending exception. E.g. multiple warnings to detect such behavior fire:
------------[ cut here ]------------
WARNING: CPU: 3 PID: 1017 at arch/x86/kvm/x86.c:9873 kvm_arch_vcpu_ioctl_run+0x1de5/0x20a0 [kvm]
Modules linked in: kvm_amd ccp kvm irqbypass
CPU: 3 PID: 1017 Comm: svm_nested_soft Not tainted 6.0.0-rc1+ #220
Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 0.0.0 02/06/2015
RIP: 0010:kvm_arch_vcpu_ioctl_run+0x1de5/0x20a0 [kvm]
Call Trace:
kvm_vcpu_ioctl+0x223/0x6d0 [kvm]
__x64_sys_ioctl+0x85/0xc0
do_syscall_64+0x2b/0x50
entry_SYSCALL_64_after_hwframe+0x46/0xb0
---[ end trace 0000000000000000 ]---
------------[ cut here ]------------
WARNING: CPU: 3 PID: 1017 at arch/x86/kvm/x86.c:9987 kvm_arch_vcpu_ioctl_run+0x12a3/0x20a0 [kvm]
Modules linked in: kvm_amd ccp kvm irqbypass
CPU: 3 PID: 1017 Comm: svm_nested_soft Tainted: G W 6.0.0-rc1+ #220
Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 0.0.0 02/06/2015
RIP: 0010:kvm_arch_vcpu_ioctl_run+0x12a3/0x20a0 [kvm]
Call Trace:
kvm_vcpu_ioctl+0x223/0x6d0 [kvm]
__x64_sys_ioctl+0x85/0xc0
do_syscall_64+0x2b/0x50
entry_SYSCALL_64_after_hwframe+0x46/0xb0
---[ end trace 0000000000000000 ]---
If the device does not come straight from reset, we might receive an IRQ
before we are ready to handle it.
Fixes:
[ 0.832328] Unable to handle kernel read from unreadable memory at virtual address 0000000000000010
[ 1.040343] Call trace:
[ 1.040347] mtk_spi_can_dma+0xc/0x40
...
[ 1.262265] start_kernel+0x338/0x42c
Signed-off-by: Ricardo Ribalda <ribalda@chromium.org> Reviewed-by: AngeloGioacchino Del Regno <angelogioacchino.delregno@collabora.com> Link: https://lore.kernel.org/r/20221128-spi-mt65xx-v1-0-509266830665@chromium.org Signed-off-by: Mark Brown <broonie@kernel.org> Signed-off-by: Sasha Levin <sashal@kernel.org>
SATA devices on an expander may be removed and not be found again when I_T
nexus reset and revalidation are processed simultaneously.
The issue comes from:
- Revalidation can remove SATA devices in link reset, e.g. in
hisi_sas_clear_nexus_ha().
- However, hisi_sas_debug_I_T_nexus_reset() polls the state of a SATA
device on an expander after sending link_reset, where it calls:
hisi_sas_debug_I_T_nexus_reset
sas_ata_wait_after_reset
ata_wait_after_reset
ata_wait_ready
smp_ata_check_ready
sas_ex_phy_discover
sas_ex_phy_discover_helper
sas_set_ex_phy
The ex_phy's change count is updated in sas_set_ex_phy(), so SATA
devices after a link reset may not be found later through revalidation.
A similar issue was reported in:
commit 0f3fce5cc77e ("[SCSI] libsas: fix ata_eh clobbering ex_phys via
smp_ata_check_ready")
commit 87c8331fcf72 ("[SCSI] libsas: prevent domain rediscovery competing
with ata error handling").
To address this issue, in hisi_sas_debug_I_T_nexus_reset(), we now call
smp_ata_check_ready_type() that only polls the device type while not
updating the ex_phy's data of libsas.
Fixes: 71453bd9d1bf ("scsi: hisi_sas: Use sas_ata_wait_after_reset() in IT nexus reset") Signed-off-by: Jie Zhan <zhanjie9@hisilicon.com> Link: https://lore.kernel.org/r/20221118083714.4034612-5-zhanjie9@hisilicon.com Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com> Signed-off-by: Sasha Levin <sashal@kernel.org>
add_latent_entropy() is called every time a process forks, in
kernel_clone(). This in turn calls add_device_randomness() using the
latent entropy global state. add_device_randomness() does two things:
2) Mixes into the input pool the latent entropy argument passed; and
1) Mixes in a cycle counter, a sort of measurement of when the event
took place, the high precision bits of which are presumably
difficult to predict.
(2) is impossible without CONFIG_GCC_PLUGIN_LATENT_ENTROPY=y. But (1) is
always possible. However, currently CONFIG_GCC_PLUGIN_LATENT_ENTROPY=n
disables both (1) and (2), instead of just (2).
This commit causes the CONFIG_GCC_PLUGIN_LATENT_ENTROPY=n case to still
do (1) by passing NULL (len 0) to add_device_randomness() when add_latent_
entropy() is called.
Cc: Dominik Brodowski <linux@dominikbrodowski.net> Cc: PaX Team <pageexec@freemail.hu> Cc: Emese Revfy <re.emese@gmail.com> Fixes: 38addce8b600 ("gcc-plugins: Add latent_entropy plugin") Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com> Signed-off-by: Sasha Levin <sashal@kernel.org>
Psi polling mechanism is trying to minimize the number of wakeups to
run psi_poll_work and is currently relying on timer_pending() to detect
when this work is already scheduled. This provides a window of opportunity
for psi_group_change to schedule an immediate psi_poll_work after
poll_timer_fn got called but before psi_poll_work could reschedule itself.
Below is the depiction of this entire window:
Prior to 461daba06bdc we used to rely on poll_scheduled atomic which was
reset and set back inside psi_poll_work and therefore this race window
was much smaller.
The larger window causes increased number of wakeups and our partners
report visible power regression of ~10mA after applying 461daba06bdc.
Bring back the poll_scheduled atomic and make this race window even
narrower by resetting poll_scheduled only when we reach polling expiration
time. This does not completely eliminate the possibility of extra wakeups
caused by a race with psi_group_change however it will limit it to the
worst case scenario of one extra wakeup per every tracking window (0.5s
in the worst case).
This patch also ensures correct ordering between clearing poll_scheduled
flag and obtaining changed_states using memory barrier. Correct ordering
between updating changed_states and setting poll_scheduled is ensured by
atomic_xchg operation.
By tracing the number of immediate rescheduling attempts performed by
psi_group_change and the number of these attempts being blocked due to
psi monitor being already active, we can assess the effects of this change:
Before the patch:
Run#1 Run#2 Run#3
Immediate reschedules attempted: 684365 13851561261240
Immediate reschedules blocked: 682846 13816541258682
Immediate reschedules (delta): 1519 3502 2558
Immediate reschedules (% of attempted): 0.22% 0.25% 0.20%
The number of non-blocked immediate reschedules dropped from 0.22-0.25%
to 0.03-0.07%. The drop is attributed to the decrease in the race window
size and the fact that we allow this race only when psi monitors reach
polling window expiration time.
Fixes: 461daba06bdc ("psi: eliminate kthread_worker from psi trigger scheduling mechanism") Reported-by: Kathleen Chang <yt.chang@mediatek.com> Reported-by: Wenju Xu <wenju.xu@mediatek.com> Reported-by: Jonathan Chen <jonathan.jmchen@mediatek.com> Signed-off-by: Suren Baghdasaryan <surenb@google.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Reviewed-by: Chengming Zhou <zhouchengming@bytedance.com> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Tested-by: SH Chen <show-hong.chen@mediatek.com> Link: https://lore.kernel.org/r/20221028194541.813985-1-surenb@google.com Signed-off-by: Sasha Levin <sashal@kernel.org>
Commit 036177310bac ("clk: mxl: Switch from direct readl/writel based IO
to regmap based IO") introduced code resulting in below warning issued
by the smatch static checker.
drivers/clk/x86/clk-lgm.c:441 lgm_cgu_probe() warn: passing zero to 'PTR_ERR'
Fix the warning by replacing incorrect IS_ERR_OR_NULL() with IS_ERR().
On the T208X SoCs, MAC1 and MAC2 support XGMII. Add some new MAC dtsi
fragments, and mark the QMAN ports as 10G.
Fixes: da414bb923d9 ("powerpc/mpc85xx: Add FSL QorIQ DPAA FMan support to the SoC device tree(s)") Signed-off-by: Sean Anderson <sean.anderson@seco.com> Signed-off-by: David S. Miller <davem@davemloft.net> Signed-off-by: Sasha Levin <sashal@kernel.org>
One of the clock entry "dcl" clk has some HW limitations. One is that
its rate can only by changed by changing its parent clk's rate & two is
that HW does not support enable/disable for this clk.
Handle above two limitations by adding relevant flags. Add standard flag
CLK_SET_RATE_PARENT to handle rate change and add driver internal flag
DIV_CLK_NO_MASK to handle enable/disable.
In MxL's LGM SoC, gate clocks can be controlled either from CGU clk driver
i.e. this driver or directly from power management driver/daemon. It is
dependent on the power policy/profile requirements of the end product.
To support such use cases, provide option to override gate clks enable/disable
by adding a flag GATE_CLK_HW which controls if these gate clks are controlled
by HW i.e. this driver or overridden in order to allow it to be controlled
by power profiles instead.
Patch 1/4 of this patch series switches from direct readl/writel
based register access to regmap based register access. Instead
of using direct readl/writel, regmap API's are used to read, write
& read-modify-write clk registers. Regmap API's already use their
own spinlocks to serialize the register accesses across multiple
cores in which case additional driver spinlocks becomes redundant.
Hence, remove redundant spinlocks from driver in this patch 2/4.
Earlier version of driver used direct io remapped register read
writes using readl/writel. But we need secure boot access which
is only possible when registers are read & written using regmap.
This is because the security bus/hook is written & coupled only
with regmap layer.
Switch the driver from direct readl/writel based register accesses
to regmap based register accesses.
Additionally, update the license headers to latest status.
Re-enable the function rtl8xxxu_gen2_report_connect.
It informs the firmware when connecting to a network. This makes the
firmware enable the rate control, which makes the upload faster.
It also informs the firmware when disconnecting from a network. In the
past this made reconnecting impossible because it was sending the
auth on queue 0x7 (TXDESC_QUEUE_VO) instead of queue 0x12
(TXDESC_QUEUE_MGNT):
wlp0s20f0u3: send auth to 90:55:de:__:__:__ (try 1/3)
wlp0s20f0u3: send auth to 90:55:de:__:__:__ (try 2/3)
wlp0s20f0u3: send auth to 90:55:de:__:__:__ (try 3/3)
wlp0s20f0u3: authentication with 90:55:de:__:__:__ timed out
Probably the firmware disables the unnecessary TX queues when it
knows it's disconnected.
However, this was fixed in commit edd5747aa12e ("wifi: rtl8xxxu: Fix
skb misuse in TX queue selection").
Fixes: c59f13bbead4 ("rtl8xxxu: Work around issue with 8192eu and 8723bu devices not reconnecting") Signed-off-by: Bitterblue Smith <rtl8821cerfe2@gmail.com> Signed-off-by: Kalle Valo <kvalo@kernel.org> Link: https://lore.kernel.org/r/43200afc-0c65-ee72-48f8-231edd1df493@gmail.com Signed-off-by: Sasha Levin <sashal@kernel.org>
Commit 26f3a021b37c ("ath11k: allocate smaller chunks of memory for
firmware") and commit f6f92968e1e5 ("ath11k: qmi: try to allocate a
big block of DMA memory first") change ath11k to allocate the memory
chunks for target twice while wlan load. It fails for the 1st time
because of large memory and then changed to allocate many small chunks
for the 2nd time sometimes as below log.
1st time failed:
[10411.640620] ath11k_pci 0000:05:00.0: qmi firmware request memory request
[10411.640625] ath11k_pci 0000:05:00.0: qmi mem seg type 1 size 6881280
[10411.640630] ath11k_pci 0000:05:00.0: qmi mem seg type 4 size 3784704
[10411.640658] ath11k_pci 0000:05:00.0: qmi dma allocation failed (6881280 B type 1), will try later with small size
[10411.640671] ath11k_pci 0000:05:00.0: qmi delays mem_request 2
[10411.640677] ath11k_pci 0000:05:00.0: qmi respond memory request delayed 1
2nd time success:
[10411.642004] ath11k_pci 0000:05:00.0: qmi firmware request memory request
[10411.642008] ath11k_pci 0000:05:00.0: qmi mem seg type 1 size 524288
[10411.642012] ath11k_pci 0000:05:00.0: qmi mem seg type 1 size 524288
[10411.642014] ath11k_pci 0000:05:00.0: qmi mem seg type 1 size 524288
[10411.642016] ath11k_pci 0000:05:00.0: qmi mem seg type 1 size 524288
[10411.642018] ath11k_pci 0000:05:00.0: qmi mem seg type 1 size 524288
[10411.642020] ath11k_pci 0000:05:00.0: qmi mem seg type 1 size 524288
[10411.642022] ath11k_pci 0000:05:00.0: qmi mem seg type 1 size 524288
[10411.642024] ath11k_pci 0000:05:00.0: qmi mem seg type 1 size 524288
[10411.642027] ath11k_pci 0000:05:00.0: qmi mem seg type 1 size 524288
[10411.642029] ath11k_pci 0000:05:00.0: qmi mem seg type 1 size 524288
[10411.642031] ath11k_pci 0000:05:00.0: qmi mem seg type 1 size 458752
[10411.642033] ath11k_pci 0000:05:00.0: qmi mem seg type 1 size 131072
[10411.642035] ath11k_pci 0000:05:00.0: qmi mem seg type 4 size 524288
[10411.642037] ath11k_pci 0000:05:00.0: qmi mem seg type 4 size 524288
[10411.642039] ath11k_pci 0000:05:00.0: qmi mem seg type 4 size 524288
[10411.642041] ath11k_pci 0000:05:00.0: qmi mem seg type 4 size 524288
[10411.642043] ath11k_pci 0000:05:00.0: qmi mem seg type 4 size 524288
[10411.642045] ath11k_pci 0000:05:00.0: qmi mem seg type 4 size 524288
[10411.642047] ath11k_pci 0000:05:00.0: qmi mem seg type 4 size 491520
[10411.642049] ath11k_pci 0000:05:00.0: qmi mem seg type 1 size 524288
And then commit 5962f370ce41 ("ath11k: Reuse the available memory after
firmware reload") skip the ath11k_qmi_free_resource() which frees the
memory chunks while recovery, after that, when run recovery test on
WCN6855, a warning happened every time as below and finally leads fail
for recovery.
The reason is because when wlan start to recovery, the type, size and
count is not same for the 1st and 2nd QMI_WLFW_REQUEST_MEM_IND message,
Then it leads the parameter size is not correct for the dma_free_coherent().
For the chunk[1], the actual dma size is 524288 which allocate in the
2nd time of the initial wlan load phase, and the size which pass to
dma_free_coherent() is 3784704 which is got in the 1st time of recovery
phase, then warning above happened.
Change to use prev_size of struct target_mem_chunk for the paramter of
dma_free_coherent() since prev_size is the real size of last load/recovery.
Also change to check both type and size of struct target_mem_chunk to
reuse the memory to avoid mismatch buffer size for target. Then the
warning disappear and recovery success. When the 1st QMI_WLFW_REQUEST_MEM_IND
for recovery arrived, the trunk[0] is freed in ath11k_qmi_alloc_target_mem_chunk()
and then dma_alloc_coherent() failed caused by large size, and then
trunk[1] is freed in ath11k_qmi_free_target_mem_chunk(), the left 18
trunks will be reuse for the 2nd QMI_WLFW_REQUEST_MEM_IND message.
Fixes: 5962f370ce41 ("ath11k: Reuse the available memory after firmware reload") Signed-off-by: Wen Gong <quic_wgong@quicinc.com> Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com> Link: https://lore.kernel.org/r/20220928073832.16251-1-quic_wgong@quicinc.com Signed-off-by: Sasha Levin <sashal@kernel.org>
While the interface for the MMU mapping takes phys_addr_t to hold a
full 64bit address when necessary and MMUv2 is able to map physical
addresses with up to 40bit, etnaviv_iommu_map() truncates the address
to 32bits. Fix this by using the correct type.
Fixes: 931e97f3afd8 ("drm/etnaviv: mmuv2: support 40 bit phys address") Signed-off-by: Lucas Stach <l.stach@pengutronix.de> Reviewed-by: Philipp Zabel <p.zabel@pengutronix.de> Signed-off-by: Sasha Levin <sashal@kernel.org>
The HDaudio stream allocation is done first, and in a second step the
LOSIDV parameter is programmed for the multi-link used by a codec.
This leads to a possible stream_tag leak, e.g. if a DisplayAudio link
is not used. This would happen when a non-Intel graphics card is used
and userspace unconditionally uses the Intel Display Audio PCMs without
checking if they are connected to a receiver with jack controls.
We should first check that there is a valid multi-link entry to
configure before allocating a stream_tag. This change aligns the
dma_assign and dma_cleanup phases.
Complements: b0cd60f3e9f5 ("ALSA/ASoC: hda: clarify bus_get_link() and bus_link_get() helpers") Link: https://github.com/thesofproject/linux/issues/4151 Signed-off-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com> Reviewed-by: Ranjani Sridharan <ranjani.sridharan@linux.intel.com> Reviewed-by: Rander Wang <rander.wang@intel.com> Reviewed-by: Bard Liao <yung-chuan.liao@linux.intel.com> Signed-off-by: Peter Ujfalusi <peter.ujfalusi@linux.intel.com> Link: https://lore.kernel.org/r/20230216162340.19480-1-peter.ujfalusi@linux.intel.com Signed-off-by: Mark Brown <broonie@kernel.org> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
The sysfs group containing the cmb attributes is registered before the
driver knows if they need to be visible or not. Update the group when
cmb attributes are known to exist so the visibility setting is correct.
Link: https://bugzilla.kernel.org/show_bug.cgi?id=217037 Fixes: 86adbf0cdb9ec65 ("nvme: simplify transport specific device attribute handling") Signed-off-by: Keith Busch <kbusch@kernel.org> Reviewed-by: Sagi Grimberg <sagi@grimberg.me> Signed-off-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
syzbot reported a RCU stall which is caused by setting up an alarmtimer
with a very small interval and ignoring the signal. The reproducer arms the
alarm timer with a relative expiry of 8ns and an interval of 9ns. Not a
problem per se, but that's an issue when the signal is ignored because then
the timer is immediately rearmed because there is no way to delay that
rearming to the signal delivery path. See posix_timer_fn() and commit 58229a189942 ("posix-timers: Prevent softirq starvation by small intervals
and SIG_IGN") for details.
The reproducer does not set SIG_IGN explicitely, but it sets up the timers
signal with SIGCONT. That has the same effect as explicitely setting
SIG_IGN for a signal as SIGCONT is ignored if there is no handler set and
the task is not ptraced.
It works because the tasks are traced and therefore the signal is queued so
the tracer can see it, which delays the restart of the timer to the signal
delivery path. But then the tracer is killed:
syzkaller login: [ 79.439102][ C0] hrtimer: interrupt took 68471 ns
[ 184.460538][ C1] rcu: INFO: rcu_preempt detected stalls on CPUs/tasks:
...
[ 184.658237][ C1] rcu: Stack dump where RCU GP kthread last ran:
[ 184.664574][ C1] Sending NMI from CPU 1 to CPUs 0:
[ 184.669821][ C0] NMI backtrace for cpu 0
[ 184.669831][ C0] CPU: 0 PID: 5108 Comm: syz-executor192 Not tainted 6.2.0-rc6-next-20230203-syzkaller #0
...
[ 184.670036][ C0] Call Trace:
[ 184.670041][ C0] <IRQ>
[ 184.670045][ C0] alarmtimer_fired+0x327/0x670
posix_timer_fn() prevents that by checking whether the interval for
timers which have the signal ignored is smaller than a jiffie and
artifically delay it by shifting the next expiry out by a jiffie. That's
accurate vs. the overrun accounting, but slightly inaccurate
vs. timer_gettimer(2).
The comment in that function says what needs to be done and there was a fix
available for the regular userspace induced SIG_IGN mechanism, but that did
not work due to the implicit ignore for SIGCONT and similar signals. This
needs to be worked on, but for now the only available workaround is to do
exactly what posix_timer_fn() does:
Increase the interval of self-rearming timers, which have their signal
ignored, to at least a jiffie.
Interestingly this has been fixed before via commit ff86bf0c65f1
("alarmtimer: Rate limit periodic intervals") already, but that fix got
lost in a later rework.
Reported-by: syzbot+b9564ba6e8e00694511b@syzkaller.appspotmail.com Fixes: f2c45807d399 ("alarmtimer: Switch over to generic set/get/rearm routine") Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Acked-by: John Stultz <jstultz@google.com> Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/87k00q1no2.ffs@tglx Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Now that KVM disables vPMU support on hybrid CPUs, WARN and return zeros
if perf_get_x86_pmu_capability() is invoked on a hybrid CPU. The helper
doesn't provide an accurate accounting of the PMU capabilities for hybrid
CPUs and needs to be enhanced if KVM, or anything else outside of perf,
wants to act on the PMU capabilities.
Cc: stable@vger.kernel.org Cc: Andrew Cooper <Andrew.Cooper3@citrix.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Link: https://lore.kernel.org/all/20220818181530.2355034-1-kan.liang@linux.intel.com Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-Id: <20230208204230.1360502-3-seanjc@google.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
When calling the KVM_GET_DEBUGREGS ioctl, on some configurations, there
might be some unitialized portions of the kvm_debugregs structure that
could be copied to userspace. Prevent this as is done in the other kvm
ioctls, by setting the whole structure to 0 before copying anything into
it.
Bonus is that this reduces the lines of code as the explicit flag
setting and reserved space zeroing out can be removed.
Cc: Sean Christopherson <seanjc@google.com> Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@redhat.com> Cc: Borislav Petkov <bp@alien8.de> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: <x86@kernel.org> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: stable <stable@kernel.org> Reported-by: Xingyuan Mo <hdthky0@gmail.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Message-Id: <20230214103304.3689213-1-gregkh@linuxfoundation.org> Tested-by: Xingyuan Mo <hdthky0@gmail.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Disable KVM support for virtualizing PMUs on hosts with hybrid PMUs until
KVM gains a sane way to enumeration the hybrid vPMU to userspace and/or
gains a mechanism to let userspace opt-in to the dangers of exposing a
hybrid vPMU to KVM guests. Virtualizing a hybrid PMU, or at least part of
a hybrid PMU, is possible, but it requires careful, deliberate
configuration from userspace.
E.g. to expose full functionality, vCPUs need to be pinned to pCPUs to
prevent migrating a vCPU between a big core and a little core, userspace
must enumerate a reasonable topology to the guest, and guest CPUID must be
curated per vCPU to enumerate accurate vPMU capabilities.
The last point is especially problematic, as KVM doesn't control which
pCPU it runs on when enumerating KVM's vPMU capabilities to userspace,
i.e. userspace can't rely on KVM_GET_SUPPORTED_CPUID in it's current form.
Alternatively, userspace could enable vPMU support by enumerating the
set of features that are common and coherent across all cores, e.g. by
filtering PMU events and restricting guest capabilities. But again, that
requires userspace to take action far beyond reflecting KVM's supported
feature set into the guest.
For now, simply disable vPMU support on hybrid CPUs to avoid inducing
seemingly random #GPs in guests, and punt support for hybrid CPUs to a
future enabling effort.
Reported-by: Jianfeng Gao <jianfeng.gao@intel.com> Cc: stable@vger.kernel.org Cc: Andrew Cooper <Andrew.Cooper3@citrix.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Link: https://lore.kernel.org/all/20220818181530.2355034-1-kan.liang@linux.intel.com Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-Id: <20230208204230.1360502-2-seanjc@google.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
when starting error recovery there might be a authentication work
running, and it involves I/O commands. Given the controller is tearing
down there is no chance for the I/O to complete other than timing out
which may unnecessarily take a full io timeout.
So first tear down the queues, fail/cancel all inflight I/O (including
potentially authentication) and only then stop authentication. This
ensures that failover is not stalled due to blocked authentication I/O.
when starting error recovery there might be a authentication work
running, and it involves I/O commands. Given the controller is tearing
down there is no chance for the I/O to complete other than timing out
which may unnecessarily take a full io timeout.
So first tear down the queues, fail/cancel all inflight I/O (including
potentially authentication) and only then stop authentication. This
ensures that failover is not stalled due to blocked authentication I/O.
The result of nlmsg_find_attr() 'br_spec' is dereferenced in
nla_for_each_nested(), but it can take NULL value in nla_find() function,
which will result in an error.
Found by Linux Verification Center (linuxtesting.org) with SVACE.
Fixes: 51616018dd1b ("i40e: Add support for getlink, setlink ndo ops") Signed-off-by: Natalia Petrova <n.petrova@fintech.ru> Reviewed-by: Jesse Brandeburg <jesse.brandeburg@intel.com> Tested-by: Gurucharan G <gurucharanx.g@intel.com> (A Contingent worker at Intel) Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com> Link: https://lore.kernel.org/r/20230209172833.3596034-1-anthony.l.nguyen@intel.com Signed-off-by: Jakub Kicinski <kuba@kernel.org> Signed-off-by: Sasha Levin <sashal@kernel.org>
After x86 enabled support for KMSAN, it has become possible to have larger
'struct page' than was expected when commit 5470dea49f53 ("mm: use
mm_zero_struct_page from SPARC on all 64b architectures") was merged:
include/linux/mm.h:156:10: warning: no case matching constant switch condition '96'
switch (sizeof(struct page)) {
Extend the maximum accordingly.
Link: https://lkml.kernel.org/r/20230130130739.563628-1-arnd@kernel.org Fixes: 5470dea49f53 ("mm: use mm_zero_struct_page from SPARC on all 64b architectures") Fixes: 4ca8cc8d1bbe ("x86: kmsan: enable KMSAN builds for x86") Fixes: f80be4571b19 ("kmsan: add KMSAN runtime core") Signed-off-by: Arnd Bergmann <arnd@arndb.de> Acked-by: Michal Hocko <mhocko@suse.com> Reviewed-by: Pasha Tatashin <pasha.tatashin@soleen.com> Cc: Alexander Duyck <alexander.h.duyck@linux.intel.com> Cc: Alexander Potapenko <glider@google.com> Cc: Alex Sierra <alex.sierra@amd.com> Cc: David Hildenbrand <david@redhat.com> Cc: Hugh Dickins <hughd@google.com> Cc: John Hubbard <jhubbard@nvidia.com> Cc: Liam R. Howlett <Liam.Howlett@Oracle.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Naoya Horiguchi <naoya.horiguchi@nec.com> Cc: Suren Baghdasaryan <surenb@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Take into account the IPV6_TCLASS socket option (DSCP) in
tcp_v6_connect(). Otherwise fib6_rule_match() can't properly
match the DSCP value, resulting in invalid route lookup.
For example:
ip route add unreachable table main 2001:db8::10/124
ip route add table 100 2001:db8::10/124 dev eth0
ip -6 rule add dsfield 0x04 table 100
echo test | socat - TCP6:[2001:db8::11]:54321,ipv6-tclass=0x04
Without this patch, socat fails at connect() time ("No route to host")
because the fib-rule doesn't jump to table 100 and the lookup ends up
being done in the main table.
Fixes: 2cc67cc731d9 ("[IPV6] ROUTE: Routing by Traffic Class.") Signed-off-by: Guillaume Nault <gnault@redhat.com> Reviewed-by: Eric Dumazet <edumazet@google.com> Reviewed-by: David Ahern <dsahern@kernel.org> Signed-off-by: Jakub Kicinski <kuba@kernel.org> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Take into account the IPV6_TCLASS socket option (DSCP) in
ip6_datagram_flow_key_init(). Otherwise fib6_rule_match() can't
properly match the DSCP value, resulting in invalid route lookup.
For example:
ip route add unreachable table main 2001:db8::10/124
ip route add table 100 2001:db8::10/124 dev eth0
ip -6 rule add dsfield 0x04 table 100
echo test | socat - UDP6:[2001:db8::11]:54321,ipv6-tclass=0x04
Without this patch, socat fails at connect() time ("No route to host")
because the fib-rule doesn't jump to table 100 and the lookup ends up
being done in the main table.
Fixes: 2cc67cc731d9 ("[IPV6] ROUTE: Routing by Traffic Class.") Signed-off-by: Guillaume Nault <gnault@redhat.com> Reviewed-by: Eric Dumazet <edumazet@google.com> Reviewed-by: David Ahern <dsahern@kernel.org> Signed-off-by: Jakub Kicinski <kuba@kernel.org> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Fix handling of the tsync interrupt to compare the pin number with
IGB_N_SDP instead of IGB_N_EXTTS/IGB_N_PEROUT and fix the indexing to
the perout array.
Fixes: cf99c1dd7b77 ("igb: move PEROUT and EXTTS isr logic to separate functions") Reported-by: Matt Corallo <ntp-lists@mattcorallo.com> Signed-off-by: Miroslav Lichvar <mlichvar@redhat.com> Reviewed-by: Jacob Keller <jacob.e.keller@intel.com> Tested-by: Gurucharan G <gurucharanx.g@intel.com> (A Contingent worker at Intel) Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com> Link: https://lore.kernel.org/r/20230213185822.3960072-1-anthony.l.nguyen@intel.com Signed-off-by: Jakub Kicinski <kuba@kernel.org> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
the SFP NICs no longer get link at all. Reverting commit a97f8783a937
or switching to the Intel out-of-tree driver both fix the problem.
Per the igb out-of-tree driver, I2C bit banging on i350 depends on
support for an external thermal sensor (ETS). However, commit a97f8783a937 added bit banging unconditionally. Additionally, the
out-of-tree driver always calls init_thermal_sensor_thresh on probe,
while our driver only calls init_thermal_sensor_thresh only in
igb_reset(), and only if an ETS is present, ignoring the internal
thermal sensor. The affected SFPs don't provide an ETS. Per Intel,
the behaviour is a result of i350 firmware requirements.
This patch fixes the problem by aligning the behaviour to the
out-of-tree driver:
- split igb_init_i2c() into two functions:
- igb_init_i2c() only performs the basic I2C initialization.
- igb_set_i2c_bb() makes sure that E1000_CTRL_I2C_ENA is set
and enables bit-banging.
- igb_probe() only calls igb_set_i2c_bb() if an ETS is present.
- igb_reset() aligns its behaviour to igb_probe(), i. e., call
igb_set_i2c_bb() if an ETS is present and call
init_thermal_sensor_thresh() unconditionally.
lianhui reports that when MPLS fails to register the sysctl table
under new location (during device rename) the old pointers won't
get overwritten and may be freed again (double free).
Handle this gracefully. The best option would be unregistering
the MPLS from the device completely on failure, but unfortunately
mpls_ifdown() can fail. So failing fully is also unreliable.
Another option is to register the new table first then only
remove old one if the new one succeeds. That requires more
code, changes order of notifications and two tables may be
visible at the same time.
sysctl point is not used in the rest of the code - set to NULL
on failures and skip unregister if already NULL.
Reported-by: lianhui tang <bluetlh@gmail.com> Fixes: 0fae3bf018d9 ("mpls: handle device renames for per-device sysctls") Signed-off-by: Jakub Kicinski <kuba@kernel.org> Signed-off-by: David S. Miller <davem@davemloft.net> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
It is because commit a41dad905e5a ("iov_iter: saner checks for attempt
to copy to/from iterator") has introduced sanity check for copying
from/to iov iterator. Lacking of copy direction from the iterator
viewpoint would lead to kernel stack trace like above.
This commit fixes this issue by initializing the iov iterator with
the correct copy direction when sending SYN or ACK without data.
syzbot found arm64 builds would crash in sock_recv_mark()
when CONFIG_HARDENED_USERCOPY=y
x86 and powerpc are not detecting the issue because
they define user_access_begin.
This will be handled in a different patch,
because a check_object_size() is missing.
Only data from skb->cb[] can be copied directly to/from user space,
as explained in commit 79a8a642bf05 ("net: Whitelist
the skbuff_head_cache "cb" field")
When setting 'snps,force_thresh_dma_mode' DT property, the following
warning is always emitted, regardless the status of force_sf_dma_mode:
dwmac-starfive 10020000.ethernet: force_sf_dma_mode is ignored if force_thresh_dma_mode is set.
Do not print the rather misleading message when DMA store and forward
mode is already disabled.
Fixes: e2a240c7d3bc ("driver:net:stmmac: Disable DMA store and forward mode if platform data force_thresh_dma_mode is set.") Signed-off-by: Cristian Ciocaltea <cristian.ciocaltea@collabora.com> Link: https://lore.kernel.org/r/20230210202126.877548-1-cristian.ciocaltea@collabora.com Signed-off-by: Paolo Abeni <pabeni@redhat.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
In bnxt_reserve_rings(), there is logic to check that the number of TX
rings reserved is enough to cover all the mqprio TCs, but it fails to
account for the TX XDP rings. So the check will always fail if there
are mqprio TCs and TX XDP rings. As a result, the driver always fails
to initialize after the XDP program is attached and the device will be
brought down. A subsequent ifconfig up will also fail because the
number of TX rings is set to an inconsistent number. Fix the check to
properly account for TX XDP rings. If the check fails, set the number
of TX rings back to a consistent number after calling netdev_reset_tc().
Fixes: 674f50a5b026 ("bnxt_en: Implement new method to reserve rings.") Reviewed-by: Hongguang Gao <hongguang.gao@broadcom.com> Signed-off-by: Michael Chan <michael.chan@broadcom.com> Signed-off-by: David S. Miller <davem@davemloft.net> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
The tc action act_ctinfo was using shared stats, fix it to use percpu stats
since bstats_update() must be called with locks or with a percpu pointer argument.
tdc results:
1..12
ok 1 c826 - Add ctinfo action with default setting
ok 2 0286 - Add ctinfo action with dscp
ok 3 4938 - Add ctinfo action with valid cpmark and zone
ok 4 7593 - Add ctinfo action with drop control
ok 5 2961 - Replace ctinfo action zone and action control
ok 6 e567 - Delete ctinfo action with valid index
ok 7 6a91 - Delete ctinfo action with invalid index
ok 8 5232 - List ctinfo actions
ok 9 7702 - Flush ctinfo actions
ok 10 3201 - Add ctinfo action with duplicate index
ok 11 8295 - Add ctinfo action with invalid index
ok 12 3964 - Replace ctinfo action with invalid goto_chain control
Fixes: 24ec483cec98 ("net: sched: Introduce act_ctinfo action") Reviewed-by: Jamal Hadi Salim <jhs@mojatatu.com> Signed-off-by: Pedro Tammela <pctammela@mojatatu.com> Reviewed-by: Larysa Zaremba <larysa.zaremba@intel.com> Link: https://lore.kernel.org/r/20230210200824.444856-1-pctammela@mojatatu.com Signed-off-by: Jakub Kicinski <kuba@kernel.org> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
syzbot reported that act_len in kalmia_send_init_packet() is
uninitialized when passing it to the first usb_bulk_msg error path. Jiri
Pirko noted that it's pointless to pass it in the error path, and that
the value that would be printed in the second error path would be the
value of act_len from the first call to usb_bulk_msg.[1]
With this in mind, let's just not pass act_len to the usb_bulk_msg error
paths.
Eric Dumazet pointed out [0] that when we call skb_set_owner_r()
for ipv6_pinfo.pktoptions, sk_rmem_schedule() has not been called,
resulting in a negative sk_forward_alloc.
We add a new helper which clones a skb and sets its owner only
when sk_rmem_schedule() succeeds.
Note that we move skb_set_owner_r() forward in (dccp|tcp)_v6_do_rcv()
because tcp_send_synack() can make sk_forward_alloc negative before
ipv6_opt_accepted() in the crossed SYN-ACK or self-connect() cases.
The imperfect hash area can be updated while packets are traversing,
which will cause a use-after-free when 'tcf_exts_exec()' is called
with the destroyed tcf_ext.
CPU 0: CPU 1:
tcindex_set_parms tcindex_classify
tcindex_lookup
tcindex_lookup
tcf_exts_change
tcf_exts_exec [UAF]
Stop operating on the shared area directly, by using a local copy,
and update the filter with 'rcu_replace_pointer()'. Delete the old
filter version only after a rcu grace period elapsed.
Fixes: 9b0d4446b569 ("net: sched: avoid atomic swap in tcf_exts_change") Reported-by: valis <sec@valis.email> Suggested-by: valis <sec@valis.email> Signed-off-by: Jamal Hadi Salim <jhs@mojatatu.com> Signed-off-by: Pedro Tammela <pctammela@mojatatu.com> Link: https://lore.kernel.org/r/20230209143739.279867-1-pctammela@mojatatu.com Signed-off-by: Jakub Kicinski <kuba@kernel.org> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
In TI's AM62x/AM64x SoCs, successful teardown of RX DMA Channel raises an
interrupt. The process of servicing this interrupt involves flushing all
pending RX DMA descriptors and clearing the teardown completion marker
(TDCM). The am65_cpsw_nuss_rx_packets() function invoked from the RX
NAPI callback services the interrupt. Thus, it is necessary to wait for
this handler to run, drain all packets and clear TDCM, before calling
napi_disable() in am65_cpsw_nuss_common_stop() function post channel
teardown. If napi_disable() executes before ensuring that TDCM is
cleared, the TDCM remains set when the interfaces are down, resulting in
an interrupt storm when the interfaces are brought up again.
Since the interrupt raised to indicate the RX DMA Channel teardown is
specific to the AM62x and AM64x SoCs, add a quirk for it.
Fixes: 4f7cce272403 ("net: ethernet: ti: am65-cpsw: add support for am64x cpsw3g") Co-developed-by: Vignesh Raghavendra <vigneshr@ti.com> Signed-off-by: Vignesh Raghavendra <vigneshr@ti.com> Signed-off-by: Siddharth Vadapalli <s-vadapalli@ti.com> Reviewed-by: Roger Quadros <rogerq@kernel.org> Link: https://lore.kernel.org/r/20230209084432.189222-1-s-vadapalli@ti.com Signed-off-by: Jakub Kicinski <kuba@kernel.org> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Code blocks handling BCMA_CHIP_ID_BCM5357 and BCMA_CHIP_ID_BCM53572 were
incorrectly unified. Chip package values are not unique and cannot be
checked independently. They are meaningful only in a context of a given
chip.
Packages BCM5358 and BCM47188 share the same value but then belong to
different chips. Code unification resulted in treating BCM5358 as
BCM47188 and broke its initialization.
Link: https://github.com/openwrt/openwrt/issues/8278 Fixes: cb1b0f90acfe ("net: ethernet: bgmac: unify code of the same family") Cc: Jon Mason <jdmason@kudzu.us> Signed-off-by: Rafał Miłecki <rafal@milecki.pl> Reviewed-by: Florian Fainelli <f.fainelli@gmail.com> Link: https://lore.kernel.org/r/20230208091637.16291-1-zajec5@gmail.com Signed-off-by: Jakub Kicinski <kuba@kernel.org> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Include the second VLAN HLEN into account when computing the maximum
MTU size as other drivers do.
Fixes: 0c8493d90b6b ("i40e: add XDP support for pass and drop actions") Signed-off-by: Jason Xing <kernelxing@tencent.com> Reviewed-by: Alexander Duyck <alexanderduyck@fb.com> Tested-by: Chandan Kumar Rout <chandanx.rout@intel.com> (A Contingent Worker at Intel) Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Recently I encountered one case where I cannot increase the MTU size
directly from 1500 to a much bigger value with XDP enabled if the
server is equipped with IXGBE card, which happened on thousands of
servers in production environment. After applying the current patch,
we can set the maximum MTU size to 3K.
This patch follows the behavior of changing MTU as i40e/ice does.
References:
[1] commit 23b44513c3e6 ("ice: allow 3k MTU for XDP")
[2] commit 0c8493d90b6b ("i40e: add XDP support for pass and drop actions")
Fixes: fabf1bce103a ("ixgbe: Prevent unsupported configurations with XDP") Signed-off-by: Jason Xing <kernelxing@tencent.com> Reviewed-by: Alexander Duyck <alexanderduyck@fb.com> Tested-by: Chandan Kumar Rout <chandanx.rout@intel.com> (A Contingent Worker at Intel) Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
There was a problem reported to us where the addition of a VF with an IPv6
address ending with a particular sequence would cause the parent device on
the PF to no longer be able to respond to neighbor discovery packets.
In this case, we had an ovs-bridge device living on top of a VLAN, which
was on top of a PF, and it would not be able to talk anymore (the neighbor
entry would expire and couldn't be restored).
The root cause of the issue is that if the PF is asked to be in IFF_PROMISC
mode (promiscuous mode) and it had an ipv6 address that needed the
33:33:ff:00:00:04 multicast address to work, then when the VF was added
with the need for the same multicast address, the VF would steal all the
traffic destined for that address.
The ice driver didn't auto-subscribe a request of IFF_PROMISC to the
"multicast replication from other port's traffic" meaning that it won't get
for instance, packets with an exact destination in the VF, as above.
The VF's IPv6 address, which adds a "perfect filter" for 33:33:ff:00:00:04,
results in no packets for that multicast address making it to the PF (which
is in promisc but NOT "multicast replication").
The fix is to enable "multicast promiscuous" whenever the driver is asked
to enable IFF_PROMISC, and make sure to disable it when appropriate.
The UNSLICE_UNIT_LEVEL_CLKGATE register programmed by this workaround
has 'BUS' style reset, indicating that it does not lose its value on
engine resets. Furthermore, this register is part of the GT forcewake
domain rather than the RENDER domain, so it should not be impacted by
RCS engine resets. As such, we should implement this on the GT
workaround list rather than an engine list.
YUV images can either be presented as one allocation with offsets
for the different planes, or multiple allocations with 0 offsets.
The driver only ever calls drm_fb_[dma|cma]_get_gem_obj with plane
index 0, therefore any application using the second approach was
incorrectly rendered.
Correctly determine the address for each plane, removing the
assumption that the base address is the same for each.
The formula that determines the core clock requirement based on pixel
clock and blanking has been determined experimentally to minimise the
clock while supporting all modes we've seen.
A new reduced blanking mode (4kp60 at 533MHz rather than the standard
594MHz) has been seen that doesn't produce a high enough clock and
results in "flip_done timed out" error.
Increase the setup cost in the formula to make this work. The result is
a reduced blanking mode increases by up to 7MHz while leaving the
standard timing
mode untouched
When converting net_device_stats to rtnl_link_stats64 sign extension
is triggered on ILP32 machines as 6c1c509778 changed the previous
"ulong -> u64" conversion to "long -> u64" by accessing the
net_device_stats fields through a (signed) atomic_long_t.
This causes for example the received bytes counter to jump to 16EiB after
having received 2^31 bytes. Casting the atomic value to "unsigned long"
beforehand converting it into u64 avoids this.
Fixes: 6c1c5097781f ("net: add atomic_long_t to net_device_stats fields") Signed-off-by: Felix Riemann <felix.riemann@sma.de> Reviewed-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
The pages being freed by memblock_free_late() have already been
initialized, but if they are in the deferred init range,
__free_one_page() might access nearby uninitialized pages when trying to
coalesce buddies. This can, for example, trigger this BUG:
BUG: unable to handle page fault for address: ffffe964c02580c8
RIP: 0010:__list_del_entry_valid+0x3f/0x70
<TASK>
__free_one_page+0x139/0x410
__free_pages_ok+0x21d/0x450
memblock_free_late+0x8c/0xb9
efi_free_boot_services+0x16b/0x25c
efi_enter_virtual_mode+0x403/0x446
start_kernel+0x678/0x714
secondary_startup_64_no_verify+0xd2/0xdb
</TASK>
A proper fix will be more involved so revert this change for the time
being.
Fixes: 115d9d77bb0f ("mm: Always release pages to the buddy allocator in memblock_free_late().") Signed-off-by: Aaron Thompson <dev@aaront.org> Link: https://lore.kernel.org/r/20230207082151.1303-1-dev@aaront.org Signed-off-by: Mike Rapoport (IBM) <rppt@kernel.org> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
fs/coredump.c:835:12: error: ‘dump_emit_page’ defined but not used [-Werror=unused-function]
835 | static int dump_emit_page(struct coredump_params *cprm, struct page *page)
| ^~~~~~~~~~~~~~
Fix this by moving dump_emit_page() inside the existing section
protected by #ifdef CONFIG_ELF_CORE.
Fixes: 06bbaa6dc53cb720 ("[coredump] don't use __kernel_write() on kmap_local_page()") Signed-off-by: Geert Uytterhoeven <geert@linux-m68k.org> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Tetsuo-San noted that commit f5d39b020809 ("freezer,sched: Rewrite
core freezer logic") broke call_usermodehelper_exec() for the KILLABLE
case.
Specifically it was missed that the second, unconditional,
wait_for_completion() was not optional and ensures the on-stack
completion is unused before going out-of-scope.
Nick Bowler reported another sparc64 breakage after the young/dirty
persistent work for page migration (per "Link:" below). That's after a
similar report [2].
It turns out page migration was overlooked, and it wasn't failing before
because page migration was not enabled in the initial report test
environment.
David proposed another way [2] to fix this from sparc64 side, but that
patch didn't land somehow. Neither did I check whether there's any other
arch that has similar issues.
Let's fix it for now as simple as moving the write bit handling to be
after dirty, like what we did before.
Note: this is based on mm-unstable, because the breakage was since 6.1 and
we're at a very late stage of 6.2 (-rc8), so I assume for this specific
case we should target this at 6.3.
I was running traces of the read code against an RAID storage system to
understand why read requests were being misaligned against the underlying
RAID strips. I found that the page end offset calculation in
filemap_get_read_batch() was off by one.
When a read is submitted with end offset 1048575, then it calculates the
end page for read of 256 when it should be 255. "last_index" is the index
of the page beyond the end of the read and it should be skipped when get a
batch of pages for read in @filemap_get_read_batch().
The below simple patch fixes the problem. This code was introduced in
kernel 5.12.
Link: https://lkml.kernel.org/r/20230208022400.28962-1-coolqyj@163.com Fixes: cbd59c48ae2b ("mm/filemap: use head pages in generic_file_buffered_read") Signed-off-by: Qian Yingjin <qian@ddn.com> Reviewed-by: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
During collapse, in a few places we check to see if a given small page has
any unaccounted references. If the refcount on the page doesn't match our
expectations, it must be there is an unknown user concurrently interested
in the page, and so it's not safe to move the contents elsewhere.
However, the unaccounted pins are likely an ephemeral state.
In this situation, MADV_COLLAPSE returns -EINVAL when it should return
-EAGAIN. This could cause userspace to conclude that the syscall
failed, when it in fact could succeed by retrying.
Macro NILFS_SB2_OFFSET_BYTES, which computes the position of the second
superblock, underflows when the argument device size is less than 4096
bytes. Therefore, when using this macro, it is necessary to check in
advance that the device size is not less than a lower limit, or at least
that underflow does not occur.
The current nilfs2 implementation lacks this check, causing out-of-bound
block access when mounting devices smaller than 4096 bytes:
I/O error, dev loop0, sector 36028797018963960 op 0x0:(READ) flags 0x0
phys_seg 1 prio class 2
NILFS (loop0): unable to read secondary superblock (blocksize = 1024)
In addition, when trying to resize the filesystem to a size below 4096
bytes, this underflow occurs in nilfs_resize_fs(), passing a huge number
of segments to nilfs_sufile_resize(), corrupting parameters such as the
number of segments in superblocks. This causes excessive loop iterations
in nilfs_sufile_resize() during a subsequent resize ioctl, causing
semaphore ns_segctor_sem to block for a long time and hang the writer
thread:
Users can specify the hugetlb page size in the mmap, shmget and
memfd_create system calls. This is done by using 6 bits within the flags
argument to encode the base-2 logarithm of the desired page size. The
routine hstate_sizelog() uses the log2 value to find the corresponding
hugetlb hstate structure. Converting the log2 value (page_size_log) to
potential hugetlb page size is the simple statement:
1UL << page_size_log
Because only 6 bits are used for page_size_log, the left shift can not be
greater than 63. This is fine on 64 bit architectures where a long is 64
bits. However, if a value greater than 31 is passed on a 32 bit
architecture (where long is 32 bits) the shift will result in undefined
behavior. This was generally not an issue as the result of the undefined
shift had to exactly match hugetlb page size to proceed.
Recent improvements in runtime checking have resulted in this undefined
behavior throwing errors such as reported below.
Fix by comparing page_size_log to BITS_PER_LONG before doing shift.
Link: https://lkml.kernel.org/r/20230216013542.138708-1-mike.kravetz@oracle.com Link: https://lore.kernel.org/lkml/CA+G9fYuei_Tr-vN9GS7SfFyU1y9hNysnf=PB7kT0=yv4MiPgVg@mail.gmail.com/ Fixes: 42d7395feb56 ("mm: support more pagesizes for MAP_HUGETLB/SHM_HUGETLB") Signed-off-by: Mike Kravetz <mike.kravetz@oracle.com> Reported-by: Naresh Kamboju <naresh.kamboju@linaro.org> Reviewed-by: Jesper Juhl <jesperjuhl76@gmail.com> Acked-by: Muchun Song <songmuchun@bytedance.com> Tested-by: Linux Kernel Functional Testing <lkft@linaro.org> Tested-by: Naresh Kamboju <naresh.kamboju@linaro.org> Cc: Anders Roxell <anders.roxell@linaro.org> Cc: Andi Kleen <ak@linux.intel.com> Cc: Sasha Levin <sashal@kernel.org> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>