| Age | Commit message (Collapse) | Author | Files | Lines |
|---|
|
commit 433f4ba1904100da65a311033f17a9bf586b287e upstream.
The bounds check was present in KVM_GET_SUPPORTED_CPUID but not
KVM_GET_EMULATED_CPUID.
Reported-by: syzbot+e3f4897236c4eeb8af4f@syzkaller.appspotmail.com
Fixes: 84cffe499b94 ("kvm: Emulate MOVBE", 2013-10-29)
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Cc: Ben Hutchings <ben@decadent.org.uk>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
commit ad5996d9a0e8019c3ae5151e687939369acfe044 upstream.
Acquire kvm->srcu for the duration of ->set_nested_state() to fix a bug
where nVMX derefences ->memslots without holding ->srcu or ->slots_lock.
The other half of nested migration, ->get_nested_state(), does not need
to acquire ->srcu as it is a purely a dump of internal KVM (and CPU)
state to userspace.
Detected as an RCU lockdep splat that is 100% reproducible by running
KVM's state_test selftest with CONFIG_PROVE_LOCKING=y. Note that the
failing function, kvm_is_visible_gfn(), is only checking the validity of
a gfn, it's not actually accessing guest memory (which is more or less
unsupported during vmx_set_nested_state() due to incorrect MMU state),
i.e. vmx_set_nested_state() itself isn't fundamentally broken. In any
case, setting nested state isn't a fast path so there's no reason to go
out of our way to avoid taking ->srcu.
=============================
WARNING: suspicious RCU usage
5.4.0-rc7+ #94 Not tainted
-----------------------------
include/linux/kvm_host.h:626 suspicious rcu_dereference_check() usage!
other info that might help us debug this:
rcu_scheduler_active = 2, debug_locks = 1
1 lock held by evmcs_test/10939:
#0: ffff88826ffcb800 (&vcpu->mutex){+.+.}, at: kvm_vcpu_ioctl+0x85/0x630 [kvm]
stack backtrace:
CPU: 1 PID: 10939 Comm: evmcs_test Not tainted 5.4.0-rc7+ #94
Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 0.0.0 02/06/2015
Call Trace:
dump_stack+0x68/0x9b
kvm_is_visible_gfn+0x179/0x180 [kvm]
mmu_check_root+0x11/0x30 [kvm]
fast_cr3_switch+0x40/0x120 [kvm]
kvm_mmu_new_cr3+0x34/0x60 [kvm]
nested_vmx_load_cr3+0xbd/0x1f0 [kvm_intel]
nested_vmx_enter_non_root_mode+0xab8/0x1d60 [kvm_intel]
vmx_set_nested_state+0x256/0x340 [kvm_intel]
kvm_arch_vcpu_ioctl+0x491/0x11a0 [kvm]
kvm_vcpu_ioctl+0xde/0x630 [kvm]
do_vfs_ioctl+0xa2/0x6c0
ksys_ioctl+0x66/0x70
__x64_sys_ioctl+0x16/0x20
do_syscall_64+0x54/0x200
entry_SYSCALL_64_after_hwframe+0x49/0xbe
RIP: 0033:0x7f59a2b95f47
Fixes: 8fcc4b5923af5 ("kvm: nVMX: Introduce KVM_CAP_NESTED_STATE")
Cc: stable@vger.kernel.org
Signed-off-by: Sean Christopherson <sean.j.christopherson@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
commit 24885d1d79e2e83d49201aeae0bc59f1402fd4f1 upstream.
A recent change inadvertently exported a static function, which results
in modpost throwing a warning. Fix it.
Fixes: cbbaa2727aa3 ("KVM: x86: fix presentation of TSX feature in ARCH_CAPABILITIES")
Signed-off-by: Sean Christopherson <sean.j.christopherson@intel.com>
Cc: stable@vger.kernel.org
Reviewed-by: Jim Mattson <jmattson@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
commit cbbaa2727aa3ae9e0a844803da7cef7fd3b94f2b upstream.
KVM does not implement MSR_IA32_TSX_CTRL, so it must not be presented
to the guests. It is also confusing to have !ARCH_CAP_TSX_CTRL_MSR &&
!RTM && ARCH_CAP_TAA_NO: lack of MSR_IA32_TSX_CTRL suggests TSX was not
hidden (it actually was), yet the value says that TSX is not vulnerable
to microarchitectural data sampling. Fix both.
Cc: stable@vger.kernel.org
Tested-by: Jim Mattson <jmattson@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
commit de1fca5d6e0105c9d33924e1247e2f386efc3ece upstream.
"Shared MSRs" are guest MSRs that are written to the host MSRs but
keep their value until the next return to userspace. They support
a mask, so that some bits keep the host value, but this mask is
only used to skip an unnecessary MSR write and the value written
to the MSR is always the guest MSR.
Fix this and, while at it, do not update smsr->values[slot].curr if
for whatever reason the wrmsr fails. This should only happen due to
reserved bits, so the value written to smsr->values[slot].curr
will not match when the user-return notifier and the host value will
always be restored. However, it is untidy and in rare cases this
can actually avoid spurious WRMSRs on return to userspace.
Cc: stable@vger.kernel.org
Reviewed-by: Jim Mattson <jmattson@google.com>
Tested-by: Jim Mattson <jmattson@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
commit 04f11ef45810da5ae2542dd78cc353f3761bd2cb upstream.
Write the desired L2 CR3 into vmcs02.GUEST_CR3 during nested VM-Enter
instead of deferring the VMWRITE until vmx_set_cr3(). If the VMWRITE
is deferred, then KVM can consume a stale vmcs02.GUEST_CR3 when it
refreshes vmcs12->guest_cr3 during nested_vmx_vmexit() if the emulated
VM-Exit occurs without actually entering L2, e.g. if the nested run
is squashed because nested VM-Enter (from L1) is putting L2 into HLT.
Note, the above scenario can occur regardless of whether L1 is
intercepting HLT, e.g. L1 can intercept HLT and then re-enter L2 with
vmcs.GUEST_ACTIVITY_STATE=HALTED. But practically speaking, a VMM will
likely put a guest into HALTED if and only if it's not intercepting HLT.
In an ideal world where EPT *requires* unrestricted guest (and vice
versa), VMX could handle CR3 similar to how it handles RSP and RIP,
e.g. mark CR3 dirty and conditionally load it at vmx_vcpu_run(). But
the unrestricted guest silliness complicates the dirty tracking logic
to the point that explicitly handling vmcs02.GUEST_CR3 during nested
VM-Enter is a simpler overall implementation.
Cc: stable@vger.kernel.org
Reported-and-tested-by: Reto Buerki <reet@codelabs.ch>
Tested-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Reviewed-by: Liran Alon <liran.alon@oracle.com>
Signed-off-by: Sean Christopherson <sean.j.christopherson@intel.com>
Reviewed-by: Jim Mattson <jmattson@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
commit e7d71c943040c23f2fd042033d319f56e84f845b upstream.
If we cannot allocate the XIVE VPs in OPAL, the creation of a XIVE or
XICS-on-XIVE device is aborted as expected, but we leave kvm->arch.xive
set forever since the release method isn't called in this case. Any
subsequent tentative to create a XIVE or XICS-on-XIVE for this VM will
thus always fail (DoS). This is a problem for QEMU since it destroys
and re-creates these devices when the VM is reset: the VM would be
restricted to using the much slower emulated XIVE or XICS forever.
As an alternative to adding rollback, do not assign kvm->arch.xive before
making sure the XIVE VPs are allocated in OPAL.
Cc: stable@vger.kernel.org # v5.2
Fixes: 5422e95103cf ("KVM: PPC: Book3S HV: XIVE: Replace the 'destroy' method by a 'release' method")
Signed-off-by: Greg Kurz <groug@kaod.org>
Reviewed-by: Cédric Le Goater <clg@kaod.org>
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
commit 30486e72093ea2e594f44876b7a445c219449bce upstream.
We need to check the host page size is big enough to accomodate the
EQ. Let's do this before taking a reference on the EQ page to avoid
a potential leak if the check fails.
Cc: stable@vger.kernel.org # v5.2
Fixes: 13ce3297c576 ("KVM: PPC: Book3S HV: XIVE: Add controls for the EQ configuration")
Signed-off-by: Greg Kurz <groug@kaod.org>
Reviewed-by: Cédric Le Goater <clg@kaod.org>
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
commit 31a88c82b466d2f31a44e21c479f45b4732ccfd0 upstream.
The EQ page is allocated by the guest and then passed to the hypervisor
with the H_INT_SET_QUEUE_CONFIG hcall. A reference is taken on the page
before handing it over to the HW. This reference is dropped either when
the guest issues the H_INT_RESET hcall or when the KVM device is released.
But, the guest can legitimately call H_INT_SET_QUEUE_CONFIG several times,
either to reset the EQ (vCPU hot unplug) or to set a new EQ (guest reboot).
In both cases the existing EQ page reference is leaked because we simply
overwrite it in the XIVE queue structure without calling put_page().
This is especially visible when the guest memory is backed with huge pages:
start a VM up to the guest userspace, either reboot it or unplug a vCPU,
quit QEMU. The leak is observed by comparing the value of HugePages_Free in
/proc/meminfo before and after the VM is run.
Ideally we'd want the XIVE code to handle the EQ page de-allocation at the
platform level. This isn't the case right now because the various XIVE
drivers have different allocation needs. It could maybe worth introducing
hooks for this purpose instead of exposing XIVE internals to the drivers,
but this is certainly a huge work to be done later.
In the meantime, for easier backport, fix both vCPU unplug and guest reboot
leaks by introducing a wrapper around xive_native_configure_queue() that
does the necessary cleanup.
Reported-by: Satheesh Rajendran <sathnaga@linux.vnet.ibm.com>
Cc: stable@vger.kernel.org # v5.2
Fixes: 13ce3297c576 ("KVM: PPC: Book3S HV: XIVE: Add controls for the EQ configuration")
Signed-off-by: Cédric Le Goater <clg@kaod.org>
Signed-off-by: Greg Kurz <groug@kaod.org>
Tested-by: Lijun Pan <ljp@linux.ibm.com>
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
commit bed903167ae5b5532eda5d7db26de451bd232da5 upstream.
Commit ef72171b3621 ("arm64: dts: exynos: Remove unneeded address space
mapping for soc node") changed the address and size cells in root node from
2 to 1, but /memory nodes for the affected boards were not updated. This
went unnoticed on Exynos5433-based TM2(e) boards, because they use u-boot,
which updates /memory node to the correct values. On the other hand, the
mentioned commit broke boot on Exynos7-based Espresso board, which
bootloader doesn't touch /memory node at all.
This patch reverts commit ef72171b3621 ("arm64: dts: exynos: Remove
unneeded address space mapping for soc node"), so Exynos5433 and Exynos7
SoCs again matches other ARM64 platforms with 64bit mappings in root
node.
Reported-by: Alim Akhtar <alim.akhtar@samsung.com>
Fixes: ef72171b3621 ("arm64: dts: exynos: Remove unneeded address space mapping for soc node")
Signed-off-by: Marek Szyprowski <m.szyprowski@samsung.com>
Cc: <stable@vger.kernel.org> # 5.3.x: 72ddcf6aa224 arm64: dts: exynos: Move GPU under /soc node for Exynos5433
Cc: <stable@vger.kernel.org> # 5.3.x: ede87c3a2bdb arm64: dts: exynos: Move GPU under /soc node for Exynos7
Cc: <stable@vger.kernel.org> # 4.18.x
Tested-by: Alim Akhtar <alim.akhtar@samsung.com>
Signed-off-by: Krzysztof Kozlowski <krzk@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
commit df325e05a682e9c624f471835c35bd3f870d5e8c upstream.
__range_ok(), invoked from access_ok(), clears the tag of the user
address only if CONFIG_ARM64_TAGGED_ADDR_ABI is enabled and the thread
opted in to the relaxed ABI. The latter sets the TIF_TAGGED_ADDR thread
flag. In the case of asynchronous I/O (e.g. io_submit()), the
access_ok() may be called from a kernel thread. Since kernel threads
don't have TIF_TAGGED_ADDR set, access_ok() will fail for valid tagged
user addresses. Example from the ffs_user_copy_worker() thread:
use_mm(io_data->mm);
ret = ffs_copy_to_iter(io_data->buf, ret, &io_data->data);
unuse_mm(io_data->mm);
Relax the __range_ok() check to always untag the user address if called
in the context of a kernel thread. The user pointers would have already
been checked via aio_setup_rw() -> import_{single_range,iovec}() at the
time of the asynchronous I/O request.
Fixes: 63f0c6037965 ("arm64: Introduce prctl() options to control the tagged user addresses ABI")
Cc: <stable@vger.kernel.org> # 5.4.x-
Cc: Will Deacon <will@kernel.org>
Reported-by: Evgenii Stepanov <eugenis@google.com>
Tested-by: Evgenii Stepanov <eugenis@google.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
commit 7e8ce0e2b036dbc6617184317983aea4f2c52099 upstream.
The AMD FCH USB XHCI Controller advertises support for generating PME#
while in D0. When in D0, it does signal PME# for USB 3.0 connect events,
but not for USB 2.0 or USB 1.1 connect events, which means the controller
doesn't wake correctly for those events.
00:10.0 USB controller [0c03]: Advanced Micro Devices, Inc. [AMD] FCH USB XHCI Controller [1022:7914] (rev 20) (prog-if 30 [XHCI])
Subsystem: Dell FCH USB XHCI Controller [1028:087e]
Capabilities: [50] Power Management version 3
Flags: PMEClk- DSI- D1- D2- AuxCurrent=0mA PME(D0+,D1-,D2-,D3hot+,D3cold+)
Clear PCI_PM_CAP_PME_D0 in dev->pme_support to indicate the device will not
assert PME# from D0 so we don't rely on it.
Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=203673
Link: https://lore.kernel.org/r/20190902145252.32111-1-kai.heng.feng@canonical.com
Signed-off-by: Kai-Heng Feng <kai.heng.feng@canonical.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Cc: stable@vger.kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
commit 9a62d20027da3164a22244d9f022c0c987261687 upstream.
The job of vmalloc_sync_all() is to help the lazy freeing of vmalloc()
ranges: before such vmap ranges are reused we make sure that they are
unmapped from every task's page tables.
This is really easy on pagetable setups where the kernel page tables
are shared between all tasks - this is the case on 32-bit kernels
with SHARED_KERNEL_PMD = 1.
But on !SHARED_KERNEL_PMD 32-bit kernels this involves iterating
over the pgd_list and clearing all pmd entries in the pgds that
are cleared in the init_mm.pgd, which is the reference pagetable
that the vmalloc() code uses.
In that context the current practice of vmalloc_sync_all() iterating
until FIX_ADDR_TOP is buggy:
for (address = VMALLOC_START & PMD_MASK;
address >= TASK_SIZE_MAX && address < FIXADDR_TOP;
address += PMD_SIZE) {
struct page *page;
Because iterating up to FIXADDR_TOP will involve a lot of non-vmalloc
address ranges:
VMALLOC -> PKMAP -> LDT -> CPU_ENTRY_AREA -> FIX_ADDR
This is mostly harmless for the FIX_ADDR and CPU_ENTRY_AREA ranges
that don't clear their pmds, but it's lethal for the LDT range,
which relies on having different mappings in different processes,
and 'synchronizing' them in the vmalloc sense corrupts those
pagetable entries (clearing them).
This got particularly prominent with PTI, which turns SHARED_KERNEL_PMD
off and makes this the dominant mapping mode on 32-bit.
To make LDT working again vmalloc_sync_all() must only iterate over
the volatile parts of the kernel address range that are identical
between all processes.
So the correct check in vmalloc_sync_all() is "address < VMALLOC_END"
to make sure the VMALLOC areas are synchronized and the LDT
mapping is not falsely overwritten.
The CPU_ENTRY_AREA and the FIXMAP area are no longer synced either,
but this is not really a proplem since their PMDs get established
during bootup and never change.
This change fixes the ldt_gdt selftest in my setup.
[ mingo: Fixed up the changelog to explain the logic and modified the
copying to only happen up until VMALLOC_END. ]
Reported-by: Borislav Petkov <bp@suse.de>
Tested-by: Borislav Petkov <bp@suse.de>
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Cc: <stable@vger.kernel.org>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Joerg Roedel <joro@8bytes.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: hpa@zytor.com
Fixes: 7757d607c6b3: ("x86/pti: Allow CONFIG_PAGE_TABLE_ISOLATION for x86_32")
Link: https://lkml.kernel.org/r/20191126111119.GA110513@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
commit 38e45d81d14e5f78cd67922596b1c37b4c22ec74 upstream.
On sparc64, the whole physical IO address space is accessible using
physically addressed loads and stores. *_uc does nothing like the
others.
Cc: <stable@vger.kernel.org> # v4.19+
Reported-by: kbuild test robot <lkp@intel.com>
Signed-off-by: Tuowen Zhao <ztuowen@gmail.com>
Acked-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Lee Jones <lee.jones@linaro.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
commit d440538e5f219900a9fc9d96fd10727b4d2b3c48 upstream.
Commit 4fdbfd60a3a2 ("arm64: tegra: Add PCIe slot supply information
in p2972-0000 platform") added regulators for the PCIe slot on the
Jetson Xavier platform. One of these regulators has an active-low enable
and this commit incorrectly added an active-low specifier for the GPIO
which causes the following warning to occur on boot ...
WARNING KERN regulator@3 GPIO handle specifies active low - ignored
The fixed-regulator binding does not use the active-low flag from the
gpio specifier and purely relies of the presence of the
'enable-active-high' property to determine if it is active high or low
(if this property is omitted). Fix this warning by setting the GPIO
to active-high in the GPIO specifier. Finally, remove the
'enable-active-low' as this is not a valid property.
Fixes: 4fdbfd60a3a2 ("arm64: tegra: Add PCIe slot supply information in p2972-0000 platform")
Signed-off-by: Jon Hunter <jonathanh@nvidia.com>
Signed-off-by: Thierry Reding <treding@nvidia.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
commit 1e5e929c009559bd7e898ac8e17a5d01037cb057 upstream.
Commit 34993594181d ("arm64: tegra: Enable HDMI on Jetson TX1")
added a regulator for HDMI on the Jetson TX1 platform. This regulator
has an active high enable, but the GPIO specifier for enabling the
regulator incorrectly defines it as active-low. This causes the
following warning to occur on boot ...
WARNING KERN regulator@10 GPIO handle specifies active low - ignored
The fixed-regulator binding does not use the active-low flag from the
gpio specifier and purely relies of the presence of the
'enable-active-high' property to determine if it is active high or low
(if this property is omitted). Fix this warning by setting the GPIO
to active-high in the GPIO specifier which aligns with the presense of
the 'enable-active-high' property.
Fixes: 34993594181d ("arm64: tegra: Enable HDMI on Jetson TX1")
Signed-off-by: Jon Hunter <jonathanh@nvidia.com>
Signed-off-by: Thierry Reding <treding@nvidia.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
commit 59c4bd853abcea95eccc167a7d7fd5f1a5f47b98 upstream.
The state/owner of the FPU is saved to fpu_fpregs_owner_ctx by pointing
to the context that is currently loaded. It never changed during the
lifetime of a task - it remained stable/constant.
After deferred FPU registers loading until return to userland was
implemented, the content of fpu_fpregs_owner_ctx may change during
preemption and must not be cached.
This went unnoticed for some time and was now noticed, in particular
since gcc 9 is caching that load in copy_fpstate_to_sigframe() and
reusing it in the retry loop:
copy_fpstate_to_sigframe()
load fpu_fpregs_owner_ctx and save on stack
fpregs_lock()
copy_fpregs_to_sigframe() /* failed */
fpregs_unlock()
*** PREEMPTION, another uses FPU, changes fpu_fpregs_owner_ctx ***
fault_in_pages_writeable() /* succeed, retry */
fpregs_lock()
__fpregs_load_activate()
fpregs_state_valid() /* uses fpu_fpregs_owner_ctx from stack */
copy_fpregs_to_sigframe() /* succeeds, random FPU content */
This is a comparison of the assembly produced by gcc 9, without vs with this
patch:
| # arch/x86/kernel/fpu/signal.c:173: if (!access_ok(buf, size))
| cmpq %rdx, %rax # tmp183, _4
| jb .L190 #,
|-# arch/x86/include/asm/fpu/internal.h:512: return fpu == this_cpu_read_stable(fpu_fpregs_owner_ctx) && cpu == fpu->last_cpu;
|-#APP
|-# 512 "arch/x86/include/asm/fpu/internal.h" 1
|- movq %gs:fpu_fpregs_owner_ctx,%rax #, pfo_ret__
|-# 0 "" 2
|-#NO_APP
|- movq %rax, -88(%rbp) # pfo_ret__, %sfp
…
|-# arch/x86/include/asm/fpu/internal.h:512: return fpu == this_cpu_read_stable(fpu_fpregs_owner_ctx) && cpu == fpu->last_cpu;
|- movq -88(%rbp), %rcx # %sfp, pfo_ret__
|- cmpq %rcx, -64(%rbp) # pfo_ret__, %sfp
|+# arch/x86/include/asm/fpu/internal.h:512: return fpu == this_cpu_read(fpu_fpregs_owner_ctx) && cpu == fpu->last_cpu;
|+#APP
|+# 512 "arch/x86/include/asm/fpu/internal.h" 1
|+ movq %gs:fpu_fpregs_owner_ctx(%rip),%rax # fpu_fpregs_owner_ctx, pfo_ret__
|+# 0 "" 2
|+# arch/x86/include/asm/fpu/internal.h:512: return fpu == this_cpu_read(fpu_fpregs_owner_ctx) && cpu == fpu->last_cpu;
|+#NO_APP
|+ cmpq %rax, -64(%rbp) # pfo_ret__, %sfp
Use this_cpu_read() instead this_cpu_read_stable() to avoid caching of
fpu_fpregs_owner_ctx during preemption points.
The Fixes: tag points to the commit where deferred FPU loading was
added. Since this commit, the compiler is no longer allowed to move the
load of fpu_fpregs_owner_ctx somewhere else / outside of the locked
section. A task preemption will change its value and stale content will
be observed.
[ bp: Massage. ]
Debugged-by: Austin Clements <austin@google.com>
Debugged-by: David Chase <drchase@golang.org>
Debugged-by: Ian Lance Taylor <ian@airs.com>
Fixes: 5f409e20b7945 ("x86/fpu: Defer FPU state load until return to userspace")
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Borislav Petkov <bp@suse.de>
Reviewed-by: Rik van Riel <riel@surriel.com>
Tested-by: Borislav Petkov <bp@suse.de>
Cc: Aubrey Li <aubrey.li@intel.com>
Cc: Austin Clements <austin@google.com>
Cc: Barret Rhoden <brho@google.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: David Chase <drchase@golang.org>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: ian@airs.com
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Josh Bleecher Snyder <josharian@gmail.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: x86-ml <x86@kernel.org>
Link: https://lkml.kernel.org/r/20191128085306.hxfa2o3knqtu4wfn@linutronix.de
Link: https://bugzilla.kernel.org/show_bug.cgi?id=205663
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
commit af2e8c68b9c5403f77096969c516f742f5bb29e0 upstream.
On some systems that are vulnerable to Spectre v2, it is up to
software to flush the link stack (return address stack), in order to
protect against Spectre-RSB.
When exiting from a guest we do some house keeping and then
potentially exit to C code which is several stack frames deep in the
host kernel. We will then execute a series of returns without
preceeding calls, opening up the possiblity that the guest could have
poisoned the link stack, and direct speculative execution of the host
to a gadget of some sort.
To prevent this we add a flush of the link stack on exit from a guest.
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
commit 39e72bf96f5847ba87cc5bd7a3ce0fed813dc9ad upstream.
In commit ee13cb249fab ("powerpc/64s: Add support for software count
cache flush"), I added support for software to flush the count
cache (indirect branch cache) on context switch if firmware told us
that was the required mitigation for Spectre v2.
As part of that code we also added a software flush of the link
stack (return address stack), which protects against Spectre-RSB
between user processes.
That is all correct for CPUs that activate that mitigation, which is
currently Power9 Nimbus DD2.3.
What I got wrong is that on older CPUs, where firmware has disabled
the count cache, we also need to flush the link stack on context
switch.
To fix it we create a new feature bit which is not set by firmware,
which tells us we need to flush the link stack. We set that when
firmware tells us that either of the existing Spectre v2 mitigations
are enabled.
Then we adjust the patching code so that if we see that feature bit we
enable the link stack flush. If we're also told to flush the count
cache in software then we fall through and do that also.
On the older CPUs we don't need to do do the software count cache
flush, firmware has disabled it, so in that case we patch in an early
return after the link stack flush.
The naming of some of the functions is awkward after this patch,
because they're called "count cache" but they also do link stack. But
we'll fix that up in a later commit to ease backporting.
This is the fix for CVE-2019-18660.
Reported-by: Anthony Steinhauser <asteinhauser@google.com>
Fixes: ee13cb249fab ("powerpc/64s: Add support for software count cache flush")
Cc: stable@vger.kernel.org # v4.4+
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
commit 4a13b0e3e10996b9aa0b45a764ecfe49f6fcd360 upstream.
UNWIND_ESPFIX_STACK needs to read the GDT, and the GDT mapping that
can be accessed via %fs is not mapped in the user pagetables. Use
SGDT to find the cpu_entry_area mapping and read the espfix offset
from that instead.
Reported-and-tested-by: Borislav Petkov <bp@alien8.de>
Signed-off-by: Andy Lutomirski <luto@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: <stable@vger.kernel.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
the CPU_ENTRY_AREA_PAGES assert precise
commit 05b042a1944322844eaae7ea596d5f154166d68a upstream.
When two recent commits that increased the size of the 'struct cpu_entry_area'
were merged in -tip, the 32-bit defconfig build started failing on the following
build time assert:
./include/linux/compiler.h:391:38: error: call to ‘__compiletime_assert_189’ declared with attribute error: BUILD_BUG_ON failed: CPU_ENTRY_AREA_PAGES * PAGE_SIZE < CPU_ENTRY_AREA_MAP_SIZE
arch/x86/mm/cpu_entry_area.c:189:2: note: in expansion of macro ‘BUILD_BUG_ON’
In function ‘setup_cpu_entry_area_ptes’,
Which corresponds to the following build time assert:
BUILD_BUG_ON(CPU_ENTRY_AREA_PAGES * PAGE_SIZE < CPU_ENTRY_AREA_MAP_SIZE);
The purpose of this assert is to sanity check the fixed-value definition of
CPU_ENTRY_AREA_PAGES arch/x86/include/asm/pgtable_32_types.h:
#define CPU_ENTRY_AREA_PAGES (NR_CPUS * 41)
The '41' is supposed to match sizeof(struct cpu_entry_area)/PAGE_SIZE, which value
we didn't want to define in such a low level header, because it would cause
dependency hell.
Every time the size of cpu_entry_area is changed, we have to adjust CPU_ENTRY_AREA_PAGES
accordingly - and this assert is checking that constraint.
But the assert is both imprecise and buggy, primarily because it doesn't
include the single readonly IDT page that is mapped at CPU_ENTRY_AREA_BASE
(which begins at a PMD boundary).
This bug was hidden by the fact that by accident CPU_ENTRY_AREA_PAGES is defined
too large upstream (v5.4-rc8):
#define CPU_ENTRY_AREA_PAGES (NR_CPUS * 40)
While 'struct cpu_entry_area' is 155648 bytes, or 38 pages. So we had two extra
pages, which hid the bug.
The following commit (not yet upstream) increased the size to 40 pages:
x86/iopl: ("Restrict iopl() permission scope")
... but increased CPU_ENTRY_AREA_PAGES only 41 - i.e. shortening the gap
to just 1 extra page.
Then another not-yet-upstream commit changed the size again:
880a98c33996: ("x86/cpu_entry_area: Add guard page for entry stack on 32bit")
Which increased the cpu_entry_area size from 38 to 39 pages, but
didn't change CPU_ENTRY_AREA_PAGES (kept it at 40). This worked
fine, because we still had a page left from the accidental 'reserve'.
But when these two commits were merged into the same tree, the
combined size of cpu_entry_area grew from 38 to 40 pages, while
CPU_ENTRY_AREA_PAGES finally caught up to 40 as well.
Which is fine in terms of functionality, but the assert broke:
BUILD_BUG_ON(CPU_ENTRY_AREA_PAGES * PAGE_SIZE < CPU_ENTRY_AREA_MAP_SIZE);
because CPU_ENTRY_AREA_MAP_SIZE is the total size of the area,
which is 1 page larger due to the IDT page.
To fix all this, change the assert to two precise asserts:
BUILD_BUG_ON((CPU_ENTRY_AREA_PAGES+1)*PAGE_SIZE != CPU_ENTRY_AREA_MAP_SIZE);
BUILD_BUG_ON(CPU_ENTRY_AREA_TOTAL_SIZE != CPU_ENTRY_AREA_MAP_SIZE);
This takes the IDT page into account, and also connects the size-based
define of CPU_ENTRY_AREA_TOTAL_SIZE with the address-subtraction based
define of CPU_ENTRY_AREA_MAP_SIZE.
Also clean up some of the names which made it rather confusing:
- 'CPU_ENTRY_AREA_TOT_SIZE' wasn't actually the 'total' size of
the cpu-entry-area, but the per-cpu array size, so rename this
to CPU_ENTRY_AREA_ARRAY_SIZE.
- Introduce CPU_ENTRY_AREA_TOTAL_SIZE that _is_ the total mapping
size, with the IDT included.
- Add comments where '+1' denotes the IDT mapping - it wasn't
obvious and took me about 3 hours to decode...
Finally, because this particular commit is actually applied after
this patch:
880a98c33996: ("x86/cpu_entry_area: Add guard page for entry stack on 32bit")
Fix the CPU_ENTRY_AREA_PAGES value from 40 pages to the correct 39 pages.
All future commits that change cpu_entry_area will have to adjust
this value precisely.
As a side note, we should probably attempt to remove CPU_ENTRY_AREA_PAGES
and derive its value directly from the structure, without causing
header hell - but that is an adventure for another day! :-)
Fixes: 880a98c33996: ("x86/cpu_entry_area: Add guard page for entry stack on 32bit")
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: stable@kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
commit 895429076512e9d1cf5428181076299c90713159 upstream.
When the NMI lands on an ESPFIX_SS, we are on the entry stack and must
swizzle, otherwise we'll run do_nmi() on the entry stack, which is
BAD.
Also, similar to the normal exception path, we need to correct the
ESPFIX magic before leaving the entry stack, otherwise pt_regs will
present a non-flat stack pointer.
Tested by running sigreturn_32 concurrent with perf-record.
Fixes: e5862d0515ad ("x86/entry/32: Leave the kernel via trampoline stack")
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Andy Lutomirski <luto@kernel.org>
Cc: stable@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
commit a1a338e5b6fe9e0a39c57c232dc96c198bb53e47 upstream.
Right now, we do some fancy parts of the exception entry path while SS
might have a nonzero base: we fill in regs->ss and regs->sp, and we
consider switching to the kernel stack. This results in regs->ss and
regs->sp referring to a non-flat stack and it may result in
overflowing the entry stack. The former issue means that we can try to
call iret_exc on a non-flat stack, which doesn't work.
Tested with selftests/x86/sigreturn_32.
Fixes: 45d7b255747c ("x86/entry/32: Enter the kernel via trampoline stack")
Signed-off-by: Andy Lutomirski <luto@kernel.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: stable@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
commit 82cb8a0b1d8d07817b5d59f7fa1438e1fceafab2 upstream.
This will allow us to get percpu access working before FIXUP_FRAME,
which will allow us to unwind ESPFIX earlier.
Signed-off-by: Andy Lutomirski <luto@kernel.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: stable@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
commit 4c4fd55d3d59a41ddfa6ecba7e76928921759f43 upstream.
When re-building the IRET frame we use %eax as an destination %esp,
make sure to then also match the segment for when there is a nonzero
SS base (ESPFIX).
[peterz: Changelog and minor edits]
Fixes: 3c88c692c287 ("x86/stackframe/32: Provide consistent pt_regs")
Signed-off-by: Andy Lutomirski <luto@kernel.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: stable@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
commit 40ad2199580e248dce2a2ebb722854180c334b9e upstream.
As reported by Lai, the commit 3c88c692c287 ("x86/stackframe/32:
Provide consistent pt_regs") wrecked the IRET EXTABLE entry by making
.Lirq_return not point at IRET.
Fix this by placing IRET_FRAME in RESTORE_REGS, to mirror how
FIXUP_FRAME is part of SAVE_ALL.
Fixes: 3c88c692c287 ("x86/stackframe/32: Provide consistent pt_regs")
Reported-by: Lai Jiangshan <laijs@linux.alibaba.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Andy Lutomirski <luto@kernel.org>
Cc: stable@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
commit 880a98c339961eaa074393e3a2117cbe9125b8bb upstream.
The entry stack in the cpu entry area is protected against overflow by the
readonly GDT on 64-bit, but on 32-bit the GDT needs to be writeable and
therefore does not trigger a fault on stack overflow.
Add a guard page.
Fixes: c482feefe1ae ("x86/entry/64: Make cpu_entry_area.tss read-only")
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: stable@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
commit f490e07c53d66045d9d739e134145ec9b38653d3 upstream.
Commit 945fd17ab6ba ("x86/cpu_entry_area: Sync cpu_entry_area to
initial_page_table") introduced the sync for the initial page table for
32bit.
sync_initial_page_table() uses clone_pgd_range() which does the update for
the kernel page table. If PTI is enabled it also updates the user space
page table counterpart, which is assumed to be in the next page after the
target PGD.
At this point in time 32-bit did not have PTI support, so the user space
page table update was not taking place.
The support for PTI on 32-bit which was introduced later on, did not take
that into account and missed to add the user space counter part for the
initial page table.
As a consequence sync_initial_page_table() overwrites any data which is
located in the page behing initial_page_table causing random failures,
e.g. by corrupting doublefault_tss and wreckaging the doublefault handler
on 32bit.
Fix it by adding a "user" page table right after initial_page_table.
Fixes: 7757d607c6b3 ("x86/pti: Allow CONFIG_PAGE_TABLE_ISOLATION for x86_32")
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Joerg Roedel <jroedel@suse.de>
Cc: stable@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
commit 3580d0b29cab08483f84a16ce6a1151a1013695f upstream.
The double fault TSS was missing GS setup, which is needed for stack
canaries to work.
Signed-off-by: Andy Lutomirski <luto@kernel.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: stable@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
commit 922eea2ce5c799228d9ff1be9890e6873ce8fff6 upstream.
This can be had with two instead of six insns, by just checking the high
CS.RPL bit.
Also adjust the comment - there would be no #GP in the mentioned cases, as
there's no segment limit violation or alike. Instead there'd be #PF, but
that one reports the target EIP of said branch, not the address of the
branch insn itself.
Signed-off-by: Jan Beulich <jbeulich@suse.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Juergen Gross <jgross@suse.com>
Link: https://lkml.kernel.org/r/a5986837-01eb-7bf8-bf42-4d3084d6a1f5@suse.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
commit 29b810f5a5ec127d3143770098e05981baa3eb77 upstream.
Now that SS:ESP always get saved by SAVE_ALL, this also needs to be
accounted for in xen_iret_crit_fixup(). Otherwise the old_ax value gets
interpreted as EFLAGS, and hence VM86 mode appears to be active all the
time, leading to random "vm86_32: no user_vm86: BAD" log messages alongside
processes randomly crashing.
Since following the previous model (sitting after SAVE_ALL) would further
complicate the code _and_ retain the dependency of xen_iret_crit_fixup() on
frame manipulations done by entry_32.S, switch things around and do the
adjustment ahead of SAVE_ALL.
Fixes: 3c88c692c287 ("x86/stackframe/32: Provide consistent pt_regs")
Signed-off-by: Jan Beulich <jbeulich@suse.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Juergen Gross <jgross@suse.com>
Cc: Stable Team <stable@vger.kernel.org>
Link: https://lkml.kernel.org/r/32d8713d-25a7-84ab-b74b-aa3e88abce6b@suse.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
commit 81ff2c37f9e5d77593928df0536d86443195fd64 upstream.
Once again RPL checks have been introduced which don't account for a 32-bit
kernel living in ring 1 when running in a PV Xen domain. The case in
FIXUP_FRAME has been preventing boot.
Adjust BUG_IF_WRONG_CR3 as well to guard against future uses of the macro
on a code path reachable when running in PV mode under Xen; I have to admit
that I stopped at a certain point trying to figure out whether there are
present ones.
Fixes: 3c88c692c287 ("x86/stackframe/32: Provide consistent pt_regs")
Signed-off-by: Jan Beulich <jbeulich@suse.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Stable Team <stable@vger.kernel.org>
Link: https://lore.kernel.org/r/0fad341f-b7f5-f859-d55d-f0084ee7087e@suse.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
commit cd5a2aa89e847bdda7b62029d94e95488d73f6b2 upstream.
Since MDS and TAA mitigations are inter-related for processors that are
affected by both vulnerabilities, the followiing confusing messages can
be printed in the kernel log:
MDS: Vulnerable
MDS: Mitigation: Clear CPU buffers
To avoid the first incorrect message, defer the printing of MDS
mitigation after the TAA mitigation selection has been done. However,
that has the side effect of printing TAA mitigation first before MDS
mitigation.
[ bp: Check box is affected/mitigations are disabled first before
printing and massage. ]
Suggested-by: Pawan Gupta <pawan.kumar.gupta@linux.intel.com>
Signed-off-by: Waiman Long <longman@redhat.com>
Signed-off-by: Borislav Petkov <bp@suse.de>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Mark Gross <mgross@linux.intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Tim Chen <tim.c.chen@linux.intel.com>
Cc: Tony Luck <tony.luck@intel.com>
Cc: Tyler Hicks <tyhicks@canonical.com>
Cc: x86-ml <x86@kernel.org>
Link: https://lkml.kernel.org/r/20191115161445.30809-3-longman@redhat.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
commit 64870ed1b12e235cfca3f6c6da75b542c973ff78 upstream.
For MDS vulnerable processors with TSX support, enabling either MDS or
TAA mitigations will enable the use of VERW to flush internal processor
buffers at the right code path. IOW, they are either both mitigated
or both not. However, if the command line options are inconsistent,
the vulnerabilites sysfs files may not report the mitigation status
correctly.
For example, with only the "mds=off" option:
vulnerabilities/mds:Vulnerable; SMT vulnerable
vulnerabilities/tsx_async_abort:Mitigation: Clear CPU buffers; SMT vulnerable
The mds vulnerabilities file has wrong status in this case. Similarly,
the taa vulnerability file will be wrong with mds mitigation on, but
taa off.
Change taa_select_mitigation() to sync up the two mitigation status
and have them turned off if both "mds=off" and "tsx_async_abort=off"
are present.
Update documentation to emphasize the fact that both "mds=off" and
"tsx_async_abort=off" have to be specified together for processors that
are affected by both TAA and MDS to be effective.
[ bp: Massage and add kernel-parameters.txt change too. ]
Fixes: 1b42f017415b ("x86/speculation/taa: Add mitigation for TSX Async Abort")
Signed-off-by: Waiman Long <longman@redhat.com>
Signed-off-by: Borislav Petkov <bp@suse.de>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Kosina <jkosina@suse.cz>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: linux-doc@vger.kernel.org
Cc: Mark Gross <mgross@linux.intel.com>
Cc: <stable@vger.kernel.org>
Cc: Pawan Gupta <pawan.kumar.gupta@linux.intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Tim Chen <tim.c.chen@linux.intel.com>
Cc: Tony Luck <tony.luck@intel.com>
Cc: Tyler Hicks <tyhicks@canonical.com>
Cc: x86-ml <x86@kernel.org>
Link: https://lkml.kernel.org/r/20191115161445.30809-2-longman@redhat.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
commit 700c1018b86d0d4b3f1f2d459708c0cdf42b521d upstream.
gawk 5.0.1 generates the following regexp warnings:
GEN /home/sasha/torvalds/tools/objtool/arch/x86/lib/inat-tables.c
awk: ../arch/x86/tools/gen-insn-attr-x86.awk:260: warning: regexp escape sequence `\:' is not a known regexp operator
awk: ../arch/x86/tools/gen-insn-attr-x86.awk:350: (FILENAME=../arch/x86/lib/x86-opcode-map.txt FNR=41) warning: regexp escape sequence `\&' is not a known regexp operator
Ealier versions of gawk are not known to generate these warnings. The
gawk manual referenced below does not list characters ':' and '&' as
needing escaping, so 'unescape' them. See
https://www.gnu.org/software/gawk/manual/html_node/Escape-Sequences.html
for more info.
Running diff on the output generated by the script before and after
applying the patch reported no differences.
[ bp: Massage commit message. ]
[ Caught the respective tools header discrepancy. ]
Reported-by: kbuild test robot <lkp@intel.com>
Signed-off-by: Alexander Kapshuk <alexander.kapshuk@gmail.com>
Signed-off-by: Borislav Petkov <bp@suse.de>
Acked-by: Masami Hiramatsu <mhiramat@kernel.org>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: "Peter Zijlstra (Intel)" <peterz@infradead.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: x86-ml <x86@kernel.org>
Link: https://lkml.kernel.org/r/20190924044659.3785-1-alexander.kapshuk@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux
Pull arm64 fix from Will Deacon:
"Ensure PAN is re-enabled following user fault in uaccess routines.
After I thought we were done for 5.4, we had a report this week of a
nasty issue that has been shown to leak data between different user
address spaces thanks to corruption of entries in the TLB. In
hindsight, we should have spotted this in review when the PAN code was
merged back in v4.3, but hindsight is 20/20 and I'm trying not to beat
myself up too much about it despite being fairly miserable.
Anyway, the fix is "obvious" but the actual failure is more more
subtle, and is described in the commit message. I've included a fairly
mechanical follow-up patch here as well, which moves this checking out
into the C wrappers which is what we do for {get,put}_user() already
and allows us to remove these bloody assembly macros entirely. The
patches have passed kernelci [1] [2] [3] and CKI [4] tests over night,
as well as some targetted testing [5] for this particular issue.
The first patch is tagged for stable and should be applied to 4.14,
4.19 and 5.3. I have separate backports for 4.4 and 4.9, which I'll
send out once this has landed in your tree (although the original
patch applies cleanly, it won't build for those two trees).
Thanks to Pavel Tatashin for reporting this and Mark Rutland for
helping to diagnose the issue and review/test the solution"
* tag 'arm64-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux:
arm64: uaccess: Remove uaccess_*_not_uao asm macros
arm64: uaccess: Ensure PAN is re-enabled after unhandled uaccess fault
|
|
It is safer and simpler to drop the uaccess assembly macros in favour of
inline C functions. Although this bloats the Image size slightly, it
aligns our user copy routines with '{get,put}_user()' and generally
makes the code a lot easier to reason about.
Cc: Catalin Marinas <catalin.marinas@arm.com>
Reviewed-by: Mark Rutland <mark.rutland@arm.com>
Tested-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Pavel Tatashin <pasha.tatashin@soleen.com>
[will: tweaked commit message and changed temporary variable names]
Signed-off-by: Will Deacon <will@kernel.org>
|
|
A number of our uaccess routines ('__arch_clear_user()' and
'__arch_copy_{in,from,to}_user()') fail to re-enable PAN if they
encounter an unhandled fault whilst accessing userspace.
For CPUs implementing both hardware PAN and UAO, this bug has no effect
when both extensions are in use by the kernel.
For CPUs implementing hardware PAN but not UAO, this means that a kernel
using hardware PAN may execute portions of code with PAN inadvertently
disabled, opening us up to potential security vulnerabilities that rely
on userspace access from within the kernel which would usually be
prevented by this mechanism. In other words, parts of the kernel run the
same way as they would on a CPU without PAN implemented/emulated at all.
For CPUs not implementing hardware PAN and instead relying on software
emulation via 'CONFIG_ARM64_SW_TTBR0_PAN=y', the impact is unfortunately
much worse. Calling 'schedule()' with software PAN disabled means that
the next task will execute in the kernel using the page-table and ASID
of the previous process even after 'switch_mm()', since the actual
hardware switch is deferred until return to userspace. At this point, or
if there is a intermediate call to 'uaccess_enable()', the page-table
and ASID of the new process are installed. Sadly, due to the changes
introduced by KPTI, this is not an atomic operation and there is a very
small window (two instructions) where the CPU is configured with the
page-table of the old task and the ASID of the new task; a speculative
access in this state is disastrous because it would corrupt the TLB
entries for the new task with mappings from the previous address space.
As Pavel explains:
| I was able to reproduce memory corruption problem on Broadcom's SoC
| ARMv8-A like this:
|
| Enable software perf-events with PERF_SAMPLE_CALLCHAIN so userland's
| stack is accessed and copied.
|
| The test program performed the following on every CPU and forking
| many processes:
|
| unsigned long *map = mmap(NULL, PAGE_SIZE, PROT_READ|PROT_WRITE,
| MAP_SHARED | MAP_ANONYMOUS, -1, 0);
| map[0] = getpid();
| sched_yield();
| if (map[0] != getpid()) {
| fprintf(stderr, "Corruption detected!");
| }
| munmap(map, PAGE_SIZE);
|
| From time to time I was getting map[0] to contain pid for a
| different process.
Ensure that PAN is re-enabled when returning after an unhandled user
fault from our uaccess routines.
Cc: Catalin Marinas <catalin.marinas@arm.com>
Reviewed-by: Mark Rutland <mark.rutland@arm.com>
Tested-by: Mark Rutland <mark.rutland@arm.com>
Cc: <stable@vger.kernel.org>
Fixes: 338d4f49d6f7 ("arm64: kernel: Add support for Privileged Access Never")
Signed-off-by: Pavel Tatashin <pasha.tatashin@soleen.com>
[will: rewrote commit message]
Signed-off-by: Will Deacon <will@kernel.org>
|
|
git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull x86 fixes from Ingo Molnar:
"Two fixes: disable unreliable HPET on Intel Coffe Lake platforms, and
fix a lockdep splat in the resctrl code"
* 'x86-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
x86/resctrl: Fix potential lockdep warning
x86/quirks: Disable HPET on Intel Coffe Lake platforms
|
|
git://git.kernel.org/pub/scm/linux/kernel/git/mips/linux
Pull MIPS fixes from Paul Burton:
"A fix and simplification for SGI IP27 exception handlers, and a small
MAINTAINERS update for Broadcom MIPS systems"
* tag 'mips_fixes_5.4_4' of git://git.kernel.org/pub/scm/linux/kernel/git/mips/linux:
MAINTAINERS: Remove Kevin as maintainer of BMIPS generic platforms
MIPS: SGI-IP27: fix exception handler replication
|
|
Pull more KVM fixes from Paolo Bonzini:
- fixes for CONFIG_KVM_COMPAT=n
- two updates to the IFU erratum
- selftests build fix
- brown paper bag fix
* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm:
KVM: Add a comment describing the /dev/kvm no_compat handling
KVM: x86/mmu: Take slots_lock when using kvm_mmu_zap_all_fast()
KVM: Forbid /dev/kvm being opened by a compat task when CONFIG_KVM_COMPAT=n
KVM: X86: Reset the three MSR list number variables to 0 in kvm_init_msr_list()
selftests: kvm: fix build with glibc >= 2.30
kvm: x86: disable shattered huge page recovery for PREEMPT_RT.
|
|
git://git.kernel.org/pub/scm/linux/kernel/git/masahiroy/linux-kbuild
Pull Kbuild fixes from Masahiro Yamada:
- fix build error when compiling SPARC VDSO with CONFIG_COMPAT=y
- pass correct --arch option to Sparse
* tag 'kbuild-fixes-v5.4-3' of git://git.kernel.org/pub/scm/linux/kernel/git/masahiroy/linux-kbuild:
kbuild: tell sparse about the $ARCH
sparc: vdso: fix build error of vdso32
|
|
Acquire the per-VM slots_lock when zapping all shadow pages as part of
toggling nx_huge_pages. The fast zap algorithm relies on exclusivity
(via slots_lock) to identify obsolete vs. valid shadow pages, because it
uses a single bit for its generation number. Holding slots_lock also
obviates the need to acquire a read lock on the VM's srcu.
Failing to take slots_lock when toggling nx_huge_pages allows multiple
instances of kvm_mmu_zap_all_fast() to run concurrently, as the other
user, KVM_SET_USER_MEMORY_REGION, does not take the global kvm_lock.
(kvm_mmu_zap_all_fast() does take kvm->mmu_lock, but it can be
temporarily dropped by kvm_zap_obsolete_pages(), so it is not enough
to enforce exclusivity).
Concurrent fast zap instances causes obsolete shadow pages to be
incorrectly identified as valid due to the single bit generation number
wrapping, which results in stale shadow pages being left in KVM's MMU
and leads to all sorts of undesirable behavior.
The bug is easily confirmed by running with CONFIG_PROVE_LOCKING and
toggling nx_huge_pages via its module param.
Note, until commit 4ae5acbc4936 ("KVM: x86/mmu: Take slots_lock when
using kvm_mmu_zap_all_fast()", 2019-11-13) the fast zap algorithm used
an ulong-sized generation instead of relying on exclusivity for
correctness, but all callers except the recently added set_nx_huge_pages()
needed to hold slots_lock anyways. Therefore, this patch does not have
to be backported to stable kernels.
Given that toggling nx_huge_pages is by no means a fast path, force it
to conform to the current approach instead of reintroducing the previous
generation count.
Fixes: b8e8c8303ff28 ("kvm: mmu: ITLB_MULTIHIT mitigation", but NOT FOR STABLE)
Signed-off-by: Sean Christopherson <sean.j.christopherson@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
Since commit 54b8ae66ae1a ("kbuild: change *FLAGS_<basetarget>.o to
take the path relative to $(obj)"), sparc allmodconfig fails to build
as follows:
CC arch/sparc/vdso/vdso32/vclock_gettime.o
unrecognized e_machine 18 arch/sparc/vdso/vdso32/vclock_gettime.o
arch/sparc/vdso/vdso32/vclock_gettime.o: failed
The cause of the breakage is that -pg flag not being dropped.
The vdso32 files are located in the vdso32/ subdirectory, but I missed
to update the Makefile.
I removed the meaningless CFLAGS_REMOVE_vdso-note.o since it is only
effective for C file.
vdso-note.o is compiled from assembly file:
arch/sparc/vdso/vdso-note.S
arch/sparc/vdso/vdso32/vdso-note.S
Fixes: 54b8ae66ae1a ("kbuild: change *FLAGS_<basetarget>.o to take the path relative to $(obj)")
Reported-by: Anatoly Pugachev <matorola@gmail.com>
Reported-by: Guenter Roeck <linux@roeck-us.net>
Signed-off-by: Masahiro Yamada <yamada.masahiro@socionext.com>
Tested-by: Anatoly Pugachev <matorola@gmail.com>
Acked-by: David S. Miller <davem@davemloft.net>
|
|
When applying commit 7a5ee6edb42e ("KVM: X86: Fix initialization of MSR
lists"), it forgot to reset the three MSR lists number varialbes to 0
while removing the useless conditionals.
Fixes: 7a5ee6edb42e (KVM: X86: Fix initialization of MSR lists)
Signed-off-by: Xiaoyao Li <xiaoyao.li@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
If a huge page is recovered (and becomes no executable) while another
thread is executing it, the resulting contention on mmu_lock can cause
latency spikes. Disabling recovery for PREEMPT_RT kernels fixes this
issue.
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
rdtgroup_cpus_write() and mkdir_rdt_prepare() call
rdtgroup_kn_lock_live() -> kernfs_to_rdtgroup() to get 'rdtgrp', and
then call the rdt_last_cmd_{clear,puts,...}() functions which will check
if rdtgroup_mutex is held/requires its caller to hold rdtgroup_mutex.
But if 'rdtgrp' returned from kernfs_to_rdtgroup() is NULL,
rdtgroup_mutex is not held and calling rdt_last_cmd_{clear,puts,...}()
will result in a self-incurred, potential lockdep warning.
Remove the rdt_last_cmd_{clear,puts,...}() calls in these two paths.
Just returning error should be sufficient to report to the user that the
entry doesn't exist any more.
[ bp: Massage. ]
Fixes: 94457b36e8a5 ("x86/intel_rdt: Add diagnostics when writing the cpus file")
Fixes: cfd0f34e4cd5 ("x86/intel_rdt: Add diagnostics when making directories")
Signed-off-by: Xiaochen Shen <xiaochen.shen@intel.com>
Signed-off-by: Borislav Petkov <bp@suse.de>
Reviewed-by: Tony Luck <tony.luck@intel.com>
Reviewed-by: Fenghua Yu <fenghua.yu@intel.com>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: pei.p.jia@intel.com
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: x86-ml <x86@kernel.org>
Link: https://lkml.kernel.org/r/1573079796-11713-1-git-send-email-xiaochen.shen@intel.com
|
|
Pull kvm fixes from Paolo Bonzini:
"Fix unwinding of KVM_CREATE_VM failure, VT-d posted interrupts,
DAX/ZONE_DEVICE, and module unload/reload"
* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm:
KVM: MMU: Do not treat ZONE_DEVICE pages as being reserved
KVM: VMX: Introduce pi_is_pir_empty() helper
KVM: VMX: Do not change PID.NDST when loading a blocked vCPU
KVM: VMX: Consider PID.PIR to determine if vCPU has pending interrupts
KVM: VMX: Fix comment to specify PID.ON instead of PIR.ON
KVM: X86: Fix initialization of MSR lists
KVM: fix placement of refcount initialization
KVM: Fix NULL-ptr deref after kvm_create_vm fails
|
|
git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull x86 TSX Async Abort and iTLB Multihit mitigations from Thomas Gleixner:
"The performance deterioration departement is not proud at all of
presenting the seventh installment of speculation mitigations and
hardware misfeature workarounds:
1) TSX Async Abort (TAA) - 'The Annoying Affair'
TAA is a hardware vulnerability that allows unprivileged
speculative access to data which is available in various CPU
internal buffers by using asynchronous aborts within an Intel TSX
transactional region.
The mitigation depends on a microcode update providing a new MSR
which allows to disable TSX in the CPU. CPUs which have no
microcode update can be mitigated by disabling TSX in the BIOS if
the BIOS provides a tunable.
Newer CPUs will have a bit set which indicates that the CPU is not
vulnerable, but the MSR to disable TSX will be available
nevertheless as it is an architected MSR. That means the kernel
provides the ability to disable TSX on the kernel command line,
which is useful as TSX is a truly useful mechanism to accelerate
side channel attacks of all sorts.
2) iITLB Multihit (NX) - 'No eXcuses'
iTLB Multihit is an erratum where some Intel processors may incur
a machine check error, possibly resulting in an unrecoverable CPU
lockup, when an instruction fetch hits multiple entries in the
instruction TLB. This can occur when the page size is changed
along with either the physical address or cache type. A malicious
guest running on a virtualized system can exploit this erratum to
perform a denial of service attack.
The workaround is that KVM marks huge pages in the extended page
tables as not executable (NX). If the guest attempts to execute in
such a page, the page is broken down into 4k pages which are
marked executable. The workaround comes with a mechanism to
recover these shattered huge pages over time.
Both issues come with full documentation in the hardware
vulnerabilities section of the Linux kernel user's and administrator's
guide.
Thanks to all patch authors and reviewers who had the extraordinary
priviledge to be exposed to this nuisance.
Special thanks to Borislav Petkov for polishing the final TAA patch
set and to Paolo Bonzini for shepherding the KVM iTLB workarounds and
providing also the backports to stable kernels for those!"
* 'x86-pti-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
x86/speculation/taa: Fix printing of TAA_MSG_SMT on IBRS_ALL CPUs
Documentation: Add ITLB_MULTIHIT documentation
kvm: x86: mmu: Recovery of shattered NX large pages
kvm: Add helper function for creating VM worker threads
kvm: mmu: ITLB_MULTIHIT mitigation
cpu/speculation: Uninline and export CPU mitigations helpers
x86/cpu: Add Tremont to the cpu vulnerability whitelist
x86/bugs: Add ITLB_MULTIHIT bug infrastructure
x86/tsx: Add config options to set tsx=on|off|auto
x86/speculation/taa: Add documentation for TSX Async Abort
x86/tsx: Add "auto" option to the tsx= cmdline parameter
kvm/x86: Export MDS_NO=0 to guests when TSX is enabled
x86/speculation/taa: Add sysfs reporting for TSX Async Abort
x86/speculation/taa: Add mitigation for TSX Async Abort
x86/cpu: Add a "tsx=" cmdline option with TSX disabled by default
x86/cpu: Add a helper function x86_read_arch_cap_msr()
x86/msr: Add the IA32_TSX_CTRL MSR
|
|
Some Coffee Lake platforms have a skewed HPET timer once the SoCs entered
PC10, which in consequence marks TSC as unstable because HPET is used as
watchdog clocksource for TSC.
Harry Pan tried to work around it in the clocksource watchdog code [1]
thereby creating a circular dependency between HPET and TSC. This also
ignores the fact, that HPET is not only unsuitable as watchdog clocksource
on these systems, it becomes unusable in general.
Disable HPET on affected platforms.
Suggested-by: Feng Tang <feng.tang@intel.com>
Signed-off-by: Kai-Heng Feng <kai.heng.feng@canonical.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: stable@vger.kernel.org
Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=203183
Link: https://lore.kernel.org/lkml/20190516090651.1396-1-harry.pan@intel.com/ [1]
Link: https://lkml.kernel.org/r/20191016103816.30650-1-kai.heng.feng@canonical.com
|
