| Age | Commit message (Collapse) | Author | Files | Lines |
|---|
|
Remove the RCU-protected attribute from slot->gmem.file. No need to use RCU
primitives rcu_assign_pointer()/synchronize_rcu() to update this pointer.
- slot->gmem.file is updated in 3 places:
kvm_gmem_bind(), kvm_gmem_unbind(), kvm_gmem_release().
All of them are protected by kvm->slots_lock.
- slot->gmem.file is read in 2 paths:
(1) kvm_gmem_populate
kvm_gmem_get_file
__kvm_gmem_get_pfn
(2) kvm_gmem_get_pfn
kvm_gmem_get_file
__kvm_gmem_get_pfn
Path (1) kvm_gmem_populate() requires holding kvm->slots_lock, so
slot->gmem.file is protected by the kvm->slots_lock in this path.
Path (2) kvm_gmem_get_pfn() does not require holding kvm->slots_lock.
However, it's also not guarded by rcu_read_lock() and rcu_read_unlock().
So synchronize_rcu() in kvm_gmem_unbind()/kvm_gmem_release() actually
will not wait for the readers in kvm_gmem_get_pfn() due to lack of RCU
read-side critical section.
The path (2) kvm_gmem_get_pfn() is safe without RCU protection because:
a) kvm_gmem_bind() is called on a new memslot, before the memslot is
visible to kvm_gmem_get_pfn().
b) kvm->srcu ensures that kvm_gmem_unbind() and freeing of a memslot
occur after the memslot is no longer visible to kvm_gmem_get_pfn().
c) get_file_active() ensures that kvm_gmem_get_pfn() will not access the
stale file if kvm_gmem_release() sets it to NULL. This is because if
kvm_gmem_release() occurs before kvm_gmem_get_pfn(), get_file_active()
will return NULL; if get_file_active() does not return NULL,
kvm_gmem_release() should not occur until after kvm_gmem_get_pfn()
releases the file reference.
Signed-off-by: Yan Zhao <yan.y.zhao@intel.com>
Message-ID: <20241104084303.29909-1-yan.y.zhao@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
Rework __kvm_emulate_hypercall() into a macro so that completion of
hypercalls that don't exit to userspace use direct function calls to the
completion helper, i.e. don't trigger a retpoline when RETPOLINE=y.
Opportunistically take the names of the input registers, as opposed to
taking the input values, to preemptively dedup more of the calling code
(TDX needs to use different registers). Use the direct GPR accessors to
read values to avoid the pointless marking of the registers as available
(KVM requires GPRs to always be available).
Signed-off-by: Sean Christopherson <seanjc@google.com>
Reviewed-by: Binbin Wu <binbin.wu@linux.intel.com>
Reviewed-by: Kai Huang <kai.huang@intel.com>
Message-ID: <20241128004344.4072099-7-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
Finish "emulation" of KVM hypercalls by function callback, even when the
hypercall is handled entirely within KVM, i.e. doesn't require an exit to
userspace, and refactor __kvm_emulate_hypercall()'s return value to *only*
communicate whether or not KVM should exit to userspace or resume the
guest.
(Ab)Use vcpu->run->hypercall.ret to propagate the return value to the
callback, purely to avoid having to add a trampoline for every completion
callback.
Using the function return value for KVM's control flow eliminates the
multiplexed return value, where '0' for KVM_HC_MAP_GPA_RANGE (and only
that hypercall) means "exit to userspace".
Note, the unnecessary extra indirect call and thus potential retpoline
will be eliminated in the near future by converting the intermediate layer
to a macro.
Suggested-by: Binbin Wu <binbin.wu@linux.intel.com>
Suggested-by: Kai Huang <kai.huang@intel.com>
Signed-off-by: Sean Christopherson <seanjc@google.com>
Reviewed-by: Kai Huang <kai.huang@intel.com>
Message-ID: <20241128004344.4072099-6-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
Increment the "hypercalls" stat for KVM hypercalls as soon as KVM knows
it will skip the guest instruction, i.e. once KVM is committed to emulating
the hypercall. Waiting until completion adds no known value, and creates a
discrepancy where the stat will be bumped if KVM exits to userspace as a
result of trying to skip the instruction, but not if the hypercall itself
exits.
Handling the stat in common code will also avoid the need for another
helper to dedup code when TDX comes along (TDX needs a separate completion
path due to GPR usage differences).
Signed-off-by: Sean Christopherson <seanjc@google.com>
Reviewed-by: Binbin Wu <binbin.wu@linux.intel.com>
Reviewed-by: Kai Huang <kai.huang@intel.com>
Reviewed-by: Tom Lendacky <thomas.lendacky@amd.com>
Reviewed-by: Xiaoyao Li <xiaoyao.li@intel.com>
Message-ID: <20241128004344.4072099-5-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
Move the declarations for the hypercall emulation APIs to x86.h. While the
helpers are exported, they are intended to be consumed only by KVM vendor
modules, i.e. don't need to be exposed to the kernel at-large.
No functional change intended.
Signed-off-by: Sean Christopherson <seanjc@google.com>
Reviewed-by: Binbin Wu <binbin.wu@linux.intel.com>
Reviewed-by: Kai Huang <kai.huang@intel.com>
Reviewed-by: Tom Lendacky <thomas.lendacky@amd.com>
Reviewed-by: Xiaoyao Li <xiaoyao.li@intel.com>
Message-ID: <20241128004344.4072099-4-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
Add and use user_exit_on_hypercall() to check if userspace wants to handle
a KVM hypercall instead of open-coding the logic everywhere.
No functional change intended.
Signed-off-by: Binbin Wu <binbin.wu@linux.intel.com>
Reviewed-by: Isaku Yamahata <isaku.yamahata@intel.com>
Reviewed-by: Kai Huang <kai.huang@intel.com>
Reviewed-by: Xiaoyao Li <xiaoyao.li@intel.com>
[sean: squash into one patch, keep explicit KVM_HC_MAP_GPA_RANGE check]
Signed-off-by: Sean Christopherson <seanjc@google.com>
Reviewed-by: Tom Lendacky <thomas.lendacky@amd.com>
Message-ID: <20241128004344.4072099-3-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
QEMU up to 9.2.0 is assuming that vcpu->run->hypercall.ret is 0 on exit and
it never modifies it when processing KVM_EXIT_HYPERCALL. Make this explicit
in the code, to avoid breakage when KVM starts modifying that field.
This in principle is not a good idea... It would have been much better if
KVM had set the field to -KVM_ENOSYS from the beginning, so that a dumb
userspace that does nothing on KVM_EXIT_HYPERCALL would tell the guest it
does not support KVM_HC_MAP_GPA_RANGE. However, breaking userspace is
a Very Bad Thing, as everybody should know.
Reported-by: Binbin Wu <binbin.wu@linux.intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
Treat slow-path TDP MMU faults as spurious if the access is allowed given
the existing SPTE to fix a benign warning (other than the WARN itself)
due to replacing a writable SPTE with a read-only SPTE, and to avoid the
unnecessary LOCK CMPXCHG and subsequent TLB flush.
If a read fault races with a write fault, fast GUP fails for any reason
when trying to "promote" the read fault to a writable mapping, and KVM
resolves the write fault first, then KVM will end up trying to install a
read-only SPTE (for a !map_writable fault) overtop a writable SPTE.
Note, it's not entirely clear why fast GUP fails, or if that's even how
KVM ends up with a !map_writable fault with a writable SPTE. If something
else is going awry, e.g. due to a bug in mmu_notifiers, then treating read
faults as spurious in this scenario could effectively mask the underlying
problem.
However, retrying the faulting access instead of overwriting an existing
SPTE is functionally correct and desirable irrespective of the WARN, and
fast GUP _can_ legitimately fail with a writable VMA, e.g. if the Accessed
bit in primary MMU's PTE is toggled and causes a PTE value mismatch. The
WARN was also recently added, specifically to track down scenarios where
KVM is unnecessarily overwrites SPTEs, i.e. treating the fault as spurious
doesn't regress KVM's bug-finding capabilities in any way. In short,
letting the WARN linger because there's a tiny chance it's due to a bug
elsewhere would be excessively paranoid.
Fixes: 1a175082b190 ("KVM: x86/mmu: WARN and flush if resolving a TDP MMU fault clears MMU-writable")
Reported-by: Lei Yang <leiyang@redhat.com>
Closes: https://bugzilla.kernel.org/show_bug.cgi?id=219588
Tested-by: Lei Yang <leiyang@redhat.com>
Link: https://lore.kernel.org/r/20241218213611.3181643-1-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
|
|
Drop KVM's arbitrary behavior of making DE_CFG.LFENCE_SERIALIZE read-only
for the guest, as rejecting writes can lead to guest crashes, e.g. Windows
in particular doesn't gracefully handle unexpected #GPs on the WRMSR, and
nothing in the AMD manuals suggests that LFENCE_SERIALIZE is read-only _if
it exists_.
KVM only allows LFENCE_SERIALIZE to be set, by the guest or host, if the
underlying CPU has X86_FEATURE_LFENCE_RDTSC, i.e. if LFENCE is guaranteed
to be serializing. So if the guest sets LFENCE_SERIALIZE, KVM will provide
the desired/correct behavior without any additional action (the guest's
value is never stuffed into hardware). And having LFENCE be serializing
even when it's not _required_ to be is a-ok from a functional perspective.
Fixes: 74a0e79df68a ("KVM: SVM: Disallow guest from changing userspace's MSR_AMD64_DE_CFG value")
Fixes: d1d93fa90f1a ("KVM: SVM: Add MSR-based feature support for serializing LFENCE")
Reported-by: Simon Pilkington <simonp.git@mailbox.org>
Closes: https://lore.kernel.org/all/52914da7-a97b-45ad-86a0-affdf8266c61@mailbox.org
Cc: Tom Lendacky <thomas.lendacky@amd.com>
Cc: stable@vger.kernel.org
Reviewed-by: Tom Lendacky <thomas.lendacky@amd.com>
Link: https://lore.kernel.org/r/20241211172952.1477605-1-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
|
|
Use is_64_bit_hypercall() instead of is_64_bit_mode() to detect a 64-bit
hypercall when completing said hypercall. For guests with protected state,
e.g. SEV-ES and SEV-SNP, KVM must assume the hypercall was made in 64-bit
mode as the vCPU state needed to detect 64-bit mode is unavailable.
Hacking the sev_smoke_test selftest to generate a KVM_HC_MAP_GPA_RANGE
hypercall via VMGEXIT trips the WARN:
------------[ cut here ]------------
WARNING: CPU: 273 PID: 326626 at arch/x86/kvm/x86.h:180 complete_hypercall_exit+0x44/0xe0 [kvm]
Modules linked in: kvm_amd kvm ... [last unloaded: kvm]
CPU: 273 UID: 0 PID: 326626 Comm: sev_smoke_test Not tainted 6.12.0-smp--392e932fa0f3-feat #470
Hardware name: Google Astoria/astoria, BIOS 0.20240617.0-0 06/17/2024
RIP: 0010:complete_hypercall_exit+0x44/0xe0 [kvm]
Call Trace:
<TASK>
kvm_arch_vcpu_ioctl_run+0x2400/0x2720 [kvm]
kvm_vcpu_ioctl+0x54f/0x630 [kvm]
__se_sys_ioctl+0x6b/0xc0
do_syscall_64+0x83/0x160
entry_SYSCALL_64_after_hwframe+0x76/0x7e
</TASK>
---[ end trace 0000000000000000 ]---
Fixes: b5aead0064f3 ("KVM: x86: Assume a 64-bit hypercall for guests with protected state")
Cc: stable@vger.kernel.org
Cc: Tom Lendacky <thomas.lendacky@amd.com>
Reviewed-by: Xiaoyao Li <xiaoyao.li@intel.com>
Reviewed-by: Nikunj A Dadhania <nikunj@amd.com>
Reviewed-by: Tom Lendacky <thomas.lendacky@amd.com>
Reviewed-by: Binbin Wu <binbin.wu@linux.intel.com>
Reviewed-by: Kai Huang <kai.huang@intel.com>
Link: https://lore.kernel.org/r/20241128004344.4072099-2-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
|
|
On SNP-enabled system, VMRUN marks AVIC Backing Page as in-use while
the guest is running for both secure and non-secure guest. Any hypervisor
write to the in-use vCPU's AVIC backing page (e.g. to inject an interrupt)
will generate unexpected #PF in the host.
Currently, attempt to run AVIC guest would result in the following error:
BUG: unable to handle page fault for address: ff3a442e549cc270
#PF: supervisor write access in kernel mode
#PF: error_code(0x80000003) - RMP violation
PGD b6ee01067 P4D b6ee02067 PUD 10096d063 PMD 11c540063 PTE 80000001149cc163
SEV-SNP: PFN 0x1149cc unassigned, dumping non-zero entries in 2M PFN region: [0x114800 - 0x114a00]
...
Newer AMD system is enhanced to allow hypervisor to modify the backing page
for non-secure guest on SNP-enabled system. This enhancement is available
when the CPUID Fn8000_001F_EAX bit 30 is set (HvInUseWrAllowed).
This table describes AVIC support matrix w.r.t. SNP enablement:
| Non-SNP system | SNP system
-----------------------------------------------------
Non-SNP guest | AVIC Activate | AVIC Activate iff
| | HvInuseWrAllowed=1
-----------------------------------------------------
SNP guest | N/A | Secure AVIC
Therefore, check and disable AVIC in kvm_amd driver when the feature is not
available on SNP-enabled system.
See the AMD64 Architecture Programmer’s Manual (APM) Volume 2 for detail.
(https://www.amd.com/content/dam/amd/en/documents/processor-tech-docs/
programmer-references/40332.pdf)
Fixes: 216d106c7ff7 ("x86/sev: Add SEV-SNP host initialization support")
Signed-off-by: Suravee Suthikulpanit <suravee.suthikulpanit@amd.com>
Link: https://lore.kernel.org/r/20241104075845.7583-1-suravee.suthikulpanit@amd.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
|
|
Now that KVM selftests uses the kernel's canonical arch paths, directly
override ARCH to 'x86' when targeting x86_64 instead of defining ARCH_DIR
to redirect to appropriate paths. ARCH_DIR was originally added to deal
with KVM selftests using the target triple ARCH for directories, e.g.
s390x and aarch64; keeping it around just to deal with the one-off alias
from x86_64=>x86 is unnecessary and confusing.
Note, even when selftests are built from the top-level Makefile, ARCH is
scoped to KVM's makefiles, i.e. overriding ARCH won't trip up some other
selftests that (somehow) expects x86_64 and can't work with x86.
Reviewed-by: Muhammad Usama Anjum <usama.anjum@collabora.com>
Link: https://lore.kernel.org/r/20241128005547.4077116-17-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
|
|
Use the kernel's canonical $(ARCH) paths instead of the raw target triple
for KVM selftests directories. KVM selftests are quite nearly the only
place in the entire kernel that using the target triple for directories,
tools/testing/selftests/drivers/s390x being the lone holdout.
Using the kernel's preferred nomenclature eliminates the minor, but
annoying, friction of having to translate to KVM's selftests directories,
e.g. for pattern matching, opening files, running selftests, etc.
Opportunsitically delete file comments that reference the full path of the
file, as they are obviously prone to becoming stale, and serve no known
purpose.
Reviewed-by: Muhammad Usama Anjum <usama.anjum@collabora.com>
Acked-by: Claudio Imbrenda <imbrenda@linux.ibm.com>
Acked-by: Andrew Jones <ajones@ventanamicro.com>
Link: https://lore.kernel.org/r/20241128005547.4077116-16-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
|
|
Provide empty targets for KVM selftests if the target architecture is
unsupported to make it obvious which architectures are supported, and so
that various side effects don't fail and/or do weird things, e.g. as is,
"mkdir -p $(sort $(dir $(TEST_GEN_PROGS)))" fails due to a missing operand,
and conversely, "$(shell mkdir -p $(sort $(OUTPUT)/$(ARCH_DIR) ..." will
create an empty, useless directory for the unsupported architecture.
Move the guts of the Makefile to Makefile.kvm so that it's easier to see
that the if-statement effectively guards all of KVM selftests.
Reported-by: Muhammad Usama Anjum <usama.anjum@collabora.com>
Acked-by: Muhammad Usama Anjum <usama.anjum@collabora.com>
Acked-by: Andrew Jones <ajones@ventanamicro.com>
Link: https://lore.kernel.org/r/20241128005547.4077116-15-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
|
|
Add two phases to mmu_stress_test to verify that KVM correctly handles
guest memory that was writable, and then made read-only in the primary MMU,
and then made writable again.
Add bonus coverage for x86 and arm64 to verify that all of guest memory was
marked read-only. Making forward progress (without making memory writable)
requires arch specific code to skip over the faulting instruction, but the
test can at least verify each vCPU's starting page was made read-only for
other architectures.
Link: https://lore.kernel.org/r/20241128005547.4077116-14-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
|
|
Add a third phase of mmu_stress_test to verify that mprotect()ing guest
memory to make it read-only doesn't cause explosions, e.g. to verify KVM
correctly handles the resulting mmu_notifier invalidations.
Reviewed-by: James Houghton <jthoughton@google.com>
Reviewed-by: Andrew Jones <ajones@ventanamicro.com>
Link: https://lore.kernel.org/r/20241128005547.4077116-13-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
|
|
Run the exact number of guest loops required in mmu_stress_test instead
of looping indefinitely in anticipation of adding more stages that run
different code (e.g. reads instead of writes).
Reviewed-by: James Houghton <jthoughton@google.com>
Reviewed-by: Andrew Jones <ajones@ventanamicro.com>
Link: https://lore.kernel.org/r/20241128005547.4077116-12-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
|
|
Use vcpu_arch_put_guest() to write memory from the guest in
mmu_stress_test as an easy way to provide a bit of extra coverage.
Reviewed-by: James Houghton <jthoughton@google.com>
Reviewed-by: Andrew Jones <ajones@ventanamicro.com>
Link: https://lore.kernel.org/r/20241128005547.4077116-11-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
|
|
Enable the mmu_stress_test on arm64. The intent was to enable the test
across all architectures when it was first added, but a few goofs made it
unrunnable on !x86. Now that those goofs are fixed, at least for arm64,
enable the test.
Cc: Oliver Upton <oliver.upton@linux.dev>
Cc: Marc Zyngier <maz@kernel.org>
Reviewed-by: James Houghton <jthoughton@google.com>
Reviewed-by: Andrew Jones <ajones@ventanamicro.com>
Link: https://lore.kernel.org/r/20241128005547.4077116-10-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
|
|
Explicitly include ucall_common.h in the MMU stress test, as unlike arm64
and x86-64, RISC-V doesn't include ucall_common.h in its processor.h, i.e.
this will allow enabling the test on RISC-V.
Reported-by: Andrew Jones <ajones@ventanamicro.com>
Link: https://lore.kernel.org/r/20241128005547.4077116-9-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
|
|
Create mmu_stress_tests's VM with the correct number of extra pages needed
to map all of memory in the guest. The bug hasn't been noticed before as
the test currently runs only on x86, which maps guest memory with 1GiB
pages, i.e. doesn't need much memory in the guest for page tables.
Reviewed-by: James Houghton <jthoughton@google.com>
Reviewed-by: Andrew Jones <ajones@ventanamicro.com>
Link: https://lore.kernel.org/r/20241128005547.4077116-8-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
|
|
Try to get/set SREGS in mmu_stress_test only when running on x86, as the
ioctls are supported only by x86 and PPC, and the latter doesn't yet
support KVM selftests.
Reviewed-by: James Houghton <jthoughton@google.com>
Reviewed-by: Andrew Jones <ajones@ventanamicro.com>
Link: https://lore.kernel.org/r/20241128005547.4077116-7-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
|
|
Rename max_guest_memory_test to mmu_stress_test so that the name isn't
horribly misleading when future changes extend the test to verify things
like mprotect() interactions, and because the test is useful even when its
configured to populate far less than the maximum amount of guest memory.
Reviewed-by: James Houghton <jthoughton@google.com>
Reviewed-by: Andrew Jones <ajones@ventanamicro.com>
Link: https://lore.kernel.org/r/20241128005547.4077116-6-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
|
|
Don't check for an unhandled exception if KVM_RUN failed, e.g. if it
returned errno=EFAULT, as reporting unhandled exceptions is done via a
ucall, i.e. requires KVM_RUN to exit cleanly. Theoretically, checking
for a ucall on a failed KVM_RUN could get a false positive, e.g. if there
were stale data in vcpu->run from a previous exit.
Reviewed-by: James Houghton <jthoughton@google.com>
Reviewed-by: Andrew Jones <ajones@ventanamicro.com>
Link: https://lore.kernel.org/r/20241128005547.4077116-5-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
|
|
Assert that the register being read/written by vcpu_{g,s}et_reg() is no
larger than a uint64_t, i.e. that a selftest isn't unintentionally
truncating the value being read/written.
Ideally, the assert would be done at compile-time, but that would limit
the checks to hardcoded accesses and/or require fancier compile-time
assertion infrastructure to filter out dynamic usage.
Reviewed-by: Andrew Jones <ajones@ventanamicro.com>
Link: https://lore.kernel.org/r/20241128005547.4077116-4-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
|
|
Return a uint64_t from vcpu_get_reg() instead of having the caller provide
a pointer to storage, as none of the vcpu_get_reg() usage in KVM selftests
accesses a register larger than 64 bits, and vcpu_set_reg() only accepts a
64-bit value. If a use case comes along that needs to get a register that
is larger than 64 bits, then a utility can be added to assert success and
take a void pointer, but until then, forcing an out param yields ugly code
and prevents feeding the output of vcpu_get_reg() into vcpu_set_reg().
Reviewed-by: Andrew Jones <ajones@ventanamicro.com>
Acked-by: Claudio Imbrenda <imbrenda@linux.ibm.com>
Link: https://lore.kernel.org/r/20241128005547.4077116-3-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
|
|
Define KVM_REG_SIZE() in the common kvm.h header, and delete the arm64 and
RISC-V versions. As evidenced by the surrounding definitions, all aspects
of the register size encoding are generic, i.e. RISC-V should have moved
arm64's definition to common code instead of copy+pasting.
Acked-by: Anup Patel <anup@brainfault.org>
Reviewed-by: Andrew Jones <ajones@ventanamicro.com>
Reviewed-by: Muhammad Usama Anjum <usama.anjum@collabora.com>
Link: https://lore.kernel.org/r/20241128005547.4077116-2-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
|
|
|
|
BPF program types like kprobe and fentry can cause deadlocks in certain
situations. If a function takes a lock and one of these bpf programs is
hooked to some point in the function's critical section, and if the
bpf program tries to call the same function and take the same lock it will
lead to deadlock. These situations have been reported in the following
bug reports.
In percpu_freelist -
Link: https://lore.kernel.org/bpf/CAADnVQLAHwsa+2C6j9+UC6ScrDaN9Fjqv1WjB1pP9AzJLhKuLQ@mail.gmail.com/T/
Link: https://lore.kernel.org/bpf/CAPPBnEYm+9zduStsZaDnq93q1jPLqO-PiKX9jy0MuL8LCXmCrQ@mail.gmail.com/T/
In bpf_lru_list -
Link: https://lore.kernel.org/bpf/CAPPBnEajj+DMfiR_WRWU5=6A7KKULdB5Rob_NJopFLWF+i9gCA@mail.gmail.com/T/
Link: https://lore.kernel.org/bpf/CAPPBnEZQDVN6VqnQXvVqGoB+ukOtHGZ9b9U0OLJJYvRoSsMY_g@mail.gmail.com/T/
Link: https://lore.kernel.org/bpf/CAPPBnEaCB1rFAYU7Wf8UxqcqOWKmRPU1Nuzk3_oLk6qXR7LBOA@mail.gmail.com/T/
Similar bugs have been reported by syzbot.
In queue_stack_maps -
Link: https://lore.kernel.org/lkml/0000000000004c3fc90615f37756@google.com/
Link: https://lore.kernel.org/all/20240418230932.2689-1-hdanton@sina.com/T/
In lpm_trie -
Link: https://lore.kernel.org/linux-kernel/00000000000035168a061a47fa38@google.com/T/
In ringbuf -
Link: https://lore.kernel.org/bpf/20240313121345.2292-1-hdanton@sina.com/T/
Prevent kprobe and fentry bpf programs from attaching to these critical
sections by removing CC_FLAGS_FTRACE for percpu_freelist.o,
bpf_lru_list.o, queue_stack_maps.o, lpm_trie.o, ringbuf.o files.
The bugs reported by syzbot are due to tracepoint bpf programs being
called in the critical sections. This patch does not aim to fix deadlocks
caused by tracepoint programs. However, it does prevent deadlocks from
occurring in similar situations due to kprobe and fentry programs.
Signed-off-by: Priya Bala Govindasamy <pgovind2@uci.edu>
Link: https://lore.kernel.org/r/CAPPBnEZpjGnsuA26Mf9kYibSaGLm=oF6=12L21X1GEQdqjLnzQ@mail.gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
|
|
Add tests to ensure that arguments are correctly marked based on their
specified positions, and whether they get marked correctly as maybe
null. For modules, all tracepoint parameters should be marked
PTR_MAYBE_NULL by default.
Signed-off-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Link: https://lore.kernel.org/r/20241213221929.3495062-4-memxor@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
|
|
Arguments to a raw tracepoint are tagged as trusted, which carries the
semantics that the pointer will be non-NULL. However, in certain cases,
a raw tracepoint argument may end up being NULL. More context about this
issue is available in [0].
Thus, there is a discrepancy between the reality, that raw_tp arguments can
actually be NULL, and the verifier's knowledge, that they are never NULL,
causing explicit NULL check branch to be dead code eliminated.
A previous attempt [1], i.e. the second fixed commit, was made to
simulate symbolic execution as if in most accesses, the argument is a
non-NULL raw_tp, except for conditional jumps. This tried to suppress
branch prediction while preserving compatibility, but surfaced issues
with production programs that were difficult to solve without increasing
verifier complexity. A more complete discussion of issues and fixes is
available at [2].
Fix this by maintaining an explicit list of tracepoints where the
arguments are known to be NULL, and mark the positional arguments as
PTR_MAYBE_NULL. Additionally, capture the tracepoints where arguments
are known to be ERR_PTR, and mark these arguments as scalar values to
prevent potential dereference.
Each hex digit is used to encode NULL-ness (0x1) or ERR_PTR-ness (0x2),
shifted by the zero-indexed argument number x 4. This can be represented
as follows:
1st arg: 0x1
2nd arg: 0x10
3rd arg: 0x100
... and so on (likewise for ERR_PTR case).
In the future, an automated pass will be used to produce such a list, or
insert __nullable annotations automatically for tracepoints. Each
compilation unit will be analyzed and results will be collated to find
whether a tracepoint pointer is definitely not null, maybe null, or an
unknown state where verifier conservatively marks it PTR_MAYBE_NULL.
A proof of concept of this tool from Eduard is available at [3].
Note that in case we don't find a specification in the raw_tp_null_args
array and the tracepoint belongs to a kernel module, we will
conservatively mark the arguments as PTR_MAYBE_NULL. This is because
unlike for in-tree modules, out-of-tree module tracepoints may pass NULL
freely to the tracepoint. We don't protect against such tracepoints
passing ERR_PTR (which is uncommon anyway), lest we mark all such
arguments as SCALAR_VALUE.
While we are it, let's adjust the test raw_tp_null to not perform
dereference of the skb->mark, as that won't be allowed anymore, and make
it more robust by using inline assembly to test the dead code
elimination behavior, which should still stay the same.
[0]: https://lore.kernel.org/bpf/ZrCZS6nisraEqehw@jlelli-thinkpadt14gen4.remote.csb
[1]: https://lore.kernel.org/all/20241104171959.2938862-1-memxor@gmail.com
[2]: https://lore.kernel.org/bpf/20241206161053.809580-1-memxor@gmail.com
[3]: https://github.com/eddyz87/llvm-project/tree/nullness-for-tracepoint-params
Reported-by: Juri Lelli <juri.lelli@redhat.com> # original bug
Reported-by: Manu Bretelle <chantra@meta.com> # bugs in masking fix
Fixes: 3f00c5239344 ("bpf: Allow trusted pointers to be passed to KF_TRUSTED_ARGS kfuncs")
Fixes: cb4158ce8ec8 ("bpf: Mark raw_tp arguments with PTR_MAYBE_NULL")
Reviewed-by: Eduard Zingerman <eddyz87@gmail.com>
Co-developed-by: Jiri Olsa <jolsa@kernel.org>
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Signed-off-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Link: https://lore.kernel.org/r/20241213221929.3495062-3-memxor@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
|
|
This patch reverts commit
cb4158ce8ec8 ("bpf: Mark raw_tp arguments with PTR_MAYBE_NULL"). The
patch was well-intended and meant to be as a stop-gap fixing branch
prediction when the pointer may actually be NULL at runtime. Eventually,
it was supposed to be replaced by an automated script or compiler pass
detecting possibly NULL arguments and marking them accordingly.
However, it caused two main issues observed for production programs and
failed to preserve backwards compatibility. First, programs relied on
the verifier not exploring == NULL branch when pointer is not NULL, thus
they started failing with a 'dereference of scalar' error. Next,
allowing raw_tp arguments to be modified surfaced the warning in the
verifier that warns against reg->off when PTR_MAYBE_NULL is set.
More information, context, and discusson on both problems is available
in [0]. Overall, this approach had several shortcomings, and the fixes
would further complicate the verifier's logic, and the entire masking
scheme would have to be removed eventually anyway.
Hence, revert the patch in preparation of a better fix avoiding these
issues to replace this commit.
[0]: https://lore.kernel.org/bpf/20241206161053.809580-1-memxor@gmail.com
Reported-by: Manu Bretelle <chantra@meta.com>
Fixes: cb4158ce8ec8 ("bpf: Mark raw_tp arguments with PTR_MAYBE_NULL")
Signed-off-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Link: https://lore.kernel.org/r/20241213221929.3495062-2-memxor@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
|
|
ARC GCC compiler is packaged starting from Fedora 39i and the GCC
variant of cross compile tools has arc-linux-gnu- prefix and not
arc-linux-. This is causing that CROSS_COMPILE variable is left unset.
This change allows builds without need to supply CROSS_COMPILE argument
if distro package is used.
Before this change:
$ make -j 128 ARCH=arc W=1 drivers/infiniband/hw/mlx4/
gcc: warning: ‘-mcpu=’ is deprecated; use ‘-mtune=’ or ‘-march=’ instead
gcc: error: unrecognized command-line option ‘-mmedium-calls’
gcc: error: unrecognized command-line option ‘-mlock’
gcc: error: unrecognized command-line option ‘-munaligned-access’
[1] https://packages.fedoraproject.org/pkgs/cross-gcc/gcc-arc-linux-gnu/index.html
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Vineet Gupta <vgupta@kernel.org>
|
|
Snapshot the output of CPUID.0xD.[1..n] during kvm.ko initiliaization to
avoid the overead of CPUID during runtime. The offset, size, and metadata
for CPUID.0xD.[1..n] sub-leaves does not depend on XCR0 or XSS values, i.e.
is constant for a given CPU, and thus can be cached during module load.
On Intel's Emerald Rapids, CPUID is *wildly* expensive, to the point where
recomputing XSAVE offsets and sizes results in a 4x increase in latency of
nested VM-Enter and VM-Exit (nested transitions can trigger
xstate_required_size() multiple times per transition), relative to using
cached values. The issue is easily visible by running `perf top` while
triggering nested transitions: kvm_update_cpuid_runtime() shows up at a
whopping 50%.
As measured via RDTSC from L2 (using KVM-Unit-Test's CPUID VM-Exit test
and a slightly modified L1 KVM to handle CPUID in the fastpath), a nested
roundtrip to emulate CPUID on Skylake (SKX), Icelake (ICX), and Emerald
Rapids (EMR) takes:
SKX 11650
ICX 22350
EMR 28850
Using cached values, the latency drops to:
SKX 6850
ICX 9000
EMR 7900
The underlying issue is that CPUID itself is slow on ICX, and comically
slow on EMR. The problem is exacerbated on CPUs which support XSAVES
and/or XSAVEC, as KVM invokes xstate_required_size() twice on each
runtime CPUID update, and because there are more supported XSAVE features
(CPUID for supported XSAVE feature sub-leafs is significantly slower).
SKX:
CPUID.0xD.2 = 348 cycles
CPUID.0xD.3 = 400 cycles
CPUID.0xD.4 = 276 cycles
CPUID.0xD.5 = 236 cycles
<other sub-leaves are similar>
EMR:
CPUID.0xD.2 = 1138 cycles
CPUID.0xD.3 = 1362 cycles
CPUID.0xD.4 = 1068 cycles
CPUID.0xD.5 = 910 cycles
CPUID.0xD.6 = 914 cycles
CPUID.0xD.7 = 1350 cycles
CPUID.0xD.8 = 734 cycles
CPUID.0xD.9 = 766 cycles
CPUID.0xD.10 = 732 cycles
CPUID.0xD.11 = 718 cycles
CPUID.0xD.12 = 734 cycles
CPUID.0xD.13 = 1700 cycles
CPUID.0xD.14 = 1126 cycles
CPUID.0xD.15 = 898 cycles
CPUID.0xD.16 = 716 cycles
CPUID.0xD.17 = 748 cycles
CPUID.0xD.18 = 776 cycles
Note, updating runtime CPUID information multiple times per nested
transition is itself a flaw, especially since CPUID is a mandotory
intercept on both Intel and AMD. E.g. KVM doesn't need to ensure emulated
CPUID state is up-to-date while running L2. That flaw will be fixed in a
future patch, as deferring runtime CPUID updates is more subtle than it
appears at first glance, the benefits aren't super critical to have once
the XSAVE issue is resolved, and caching CPUID output is desirable even if
KVM's updates are deferred.
Cc: Jim Mattson <jmattson@google.com>
Cc: stable@vger.kernel.org
Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-ID: <20241211013302.1347853-2-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
For storing a value to a queue attribute, the queue_attr_store function
first freezes the queue (->q_usage_counter(io)) and then acquire
->sysfs_lock. This seems not correct as the usual ordering should be to
acquire ->sysfs_lock before freezing the queue. This incorrect ordering
causes the following lockdep splat which we are able to reproduce always
simply by accessing /sys/kernel/debug file using ls command:
[ 57.597146] WARNING: possible circular locking dependency detected
[ 57.597154] 6.12.0-10553-gb86545e02e8c #20 Tainted: G W
[ 57.597162] ------------------------------------------------------
[ 57.597168] ls/4605 is trying to acquire lock:
[ 57.597176] c00000003eb56710 (&mm->mmap_lock){++++}-{4:4}, at: __might_fault+0x58/0xc0
[ 57.597200]
but task is already holding lock:
[ 57.597207] c0000018e27c6810 (&sb->s_type->i_mutex_key#3){++++}-{4:4}, at: iterate_dir+0x94/0x1d4
[ 57.597226]
which lock already depends on the new lock.
[ 57.597233]
the existing dependency chain (in reverse order) is:
[ 57.597241]
-> #5 (&sb->s_type->i_mutex_key#3){++++}-{4:4}:
[ 57.597255] down_write+0x6c/0x18c
[ 57.597264] start_creating+0xb4/0x24c
[ 57.597274] debugfs_create_dir+0x2c/0x1e8
[ 57.597283] blk_register_queue+0xec/0x294
[ 57.597292] add_disk_fwnode+0x2e4/0x548
[ 57.597302] brd_alloc+0x2c8/0x338
[ 57.597309] brd_init+0x100/0x178
[ 57.597317] do_one_initcall+0x88/0x3e4
[ 57.597326] kernel_init_freeable+0x3cc/0x6e0
[ 57.597334] kernel_init+0x34/0x1cc
[ 57.597342] ret_from_kernel_user_thread+0x14/0x1c
[ 57.597350]
-> #4 (&q->debugfs_mutex){+.+.}-{4:4}:
[ 57.597362] __mutex_lock+0xfc/0x12a0
[ 57.597370] blk_register_queue+0xd4/0x294
[ 57.597379] add_disk_fwnode+0x2e4/0x548
[ 57.597388] brd_alloc+0x2c8/0x338
[ 57.597395] brd_init+0x100/0x178
[ 57.597402] do_one_initcall+0x88/0x3e4
[ 57.597410] kernel_init_freeable+0x3cc/0x6e0
[ 57.597418] kernel_init+0x34/0x1cc
[ 57.597426] ret_from_kernel_user_thread+0x14/0x1c
[ 57.597434]
-> #3 (&q->sysfs_lock){+.+.}-{4:4}:
[ 57.597446] __mutex_lock+0xfc/0x12a0
[ 57.597454] queue_attr_store+0x9c/0x110
[ 57.597462] sysfs_kf_write+0x70/0xb0
[ 57.597471] kernfs_fop_write_iter+0x1b0/0x2ac
[ 57.597480] vfs_write+0x3dc/0x6e8
[ 57.597488] ksys_write+0x84/0x140
[ 57.597495] system_call_exception+0x130/0x360
[ 57.597504] system_call_common+0x160/0x2c4
[ 57.597516]
-> #2 (&q->q_usage_counter(io)#21){++++}-{0:0}:
[ 57.597530] __submit_bio+0x5ec/0x828
[ 57.597538] submit_bio_noacct_nocheck+0x1e4/0x4f0
[ 57.597547] iomap_readahead+0x2a0/0x448
[ 57.597556] xfs_vm_readahead+0x28/0x3c
[ 57.597564] read_pages+0x88/0x41c
[ 57.597571] page_cache_ra_unbounded+0x1ac/0x2d8
[ 57.597580] filemap_get_pages+0x188/0x984
[ 57.597588] filemap_read+0x13c/0x4bc
[ 57.597596] xfs_file_buffered_read+0x88/0x17c
[ 57.597605] xfs_file_read_iter+0xac/0x158
[ 57.597614] vfs_read+0x2d4/0x3b4
[ 57.597622] ksys_read+0x84/0x144
[ 57.597629] system_call_exception+0x130/0x360
[ 57.597637] system_call_common+0x160/0x2c4
[ 57.597647]
-> #1 (mapping.invalidate_lock#2){++++}-{4:4}:
[ 57.597661] down_read+0x6c/0x220
[ 57.597669] filemap_fault+0x870/0x100c
[ 57.597677] xfs_filemap_fault+0xc4/0x18c
[ 57.597684] __do_fault+0x64/0x164
[ 57.597693] __handle_mm_fault+0x1274/0x1dac
[ 57.597702] handle_mm_fault+0x248/0x484
[ 57.597711] ___do_page_fault+0x428/0xc0c
[ 57.597719] hash__do_page_fault+0x30/0x68
[ 57.597727] do_hash_fault+0x90/0x35c
[ 57.597736] data_access_common_virt+0x210/0x220
[ 57.597745] _copy_from_user+0xf8/0x19c
[ 57.597754] sel_write_load+0x178/0xd54
[ 57.597762] vfs_write+0x108/0x6e8
[ 57.597769] ksys_write+0x84/0x140
[ 57.597777] system_call_exception+0x130/0x360
[ 57.597785] system_call_common+0x160/0x2c4
[ 57.597794]
-> #0 (&mm->mmap_lock){++++}-{4:4}:
[ 57.597806] __lock_acquire+0x17cc/0x2330
[ 57.597814] lock_acquire+0x138/0x400
[ 57.597822] __might_fault+0x7c/0xc0
[ 57.597830] filldir64+0xe8/0x390
[ 57.597839] dcache_readdir+0x80/0x2d4
[ 57.597846] iterate_dir+0xd8/0x1d4
[ 57.597855] sys_getdents64+0x88/0x2d4
[ 57.597864] system_call_exception+0x130/0x360
[ 57.597872] system_call_common+0x160/0x2c4
[ 57.597881]
other info that might help us debug this:
[ 57.597888] Chain exists of:
&mm->mmap_lock --> &q->debugfs_mutex --> &sb->s_type->i_mutex_key#3
[ 57.597905] Possible unsafe locking scenario:
[ 57.597911] CPU0 CPU1
[ 57.597917] ---- ----
[ 57.597922] rlock(&sb->s_type->i_mutex_key#3);
[ 57.597932] lock(&q->debugfs_mutex);
[ 57.597940] lock(&sb->s_type->i_mutex_key#3);
[ 57.597950] rlock(&mm->mmap_lock);
[ 57.597958]
*** DEADLOCK ***
[ 57.597965] 2 locks held by ls/4605:
[ 57.597971] #0: c0000000137c12f8 (&f->f_pos_lock){+.+.}-{4:4}, at: fdget_pos+0xcc/0x154
[ 57.597989] #1: c0000018e27c6810 (&sb->s_type->i_mutex_key#3){++++}-{4:4}, at: iterate_dir+0x94/0x1d4
Prevent the above lockdep warning by acquiring ->sysfs_lock before
freezing the queue while storing a queue attribute in queue_attr_store
function. Later, we also found[1] another function __blk_mq_update_nr_
hw_queues where we first freeze queue and then acquire the ->sysfs_lock.
So we've also updated lock ordering in __blk_mq_update_nr_hw_queues
function and ensured that in all code paths we follow the correct lock
ordering i.e. acquire ->sysfs_lock before freezing the queue.
[1] https://lore.kernel.org/all/CAFj5m9Ke8+EHKQBs_Nk6hqd=LGXtk4mUxZUN5==ZcCjnZSBwHw@mail.gmail.com/
Reported-by: kjain@linux.ibm.com
Fixes: af2814149883 ("block: freeze the queue in queue_attr_store")
Tested-by: kjain@linux.ibm.com
Cc: hch@lst.de
Cc: axboe@kernel.dk
Cc: ritesh.list@gmail.com
Cc: ming.lei@redhat.com
Cc: gjoyce@linux.ibm.com
Signed-off-by: Nilay Shroff <nilay@linux.ibm.com>
Reviewed-by: Ming Lei <ming.lei@redhat.com>
Link: https://lore.kernel.org/r/20241210144222.1066229-1-nilay@linux.ibm.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
|
|
It appears that the relatively popular RK3399 SoC has been put together
using a large amount of illicit substances, as experiments reveal that its
integration of GIC500 exposes the *secure* programming interface to
non-secure.
This has some pretty bad effects on the way priorities are handled, and
results in a dead machine if booting with pseudo-NMI enabled
(irqchip.gicv3_pseudo_nmi=1) if the kernel contains 18fdb6348c480 ("arm64:
irqchip/gic-v3: Select priorities at boot time"), which relies on the
priorities being programmed using the NS view.
Let's restore some sanity by going one step further and disable security
altogether in this case. This is not any worse, and puts us in a mode where
priorities actually make some sense.
Huge thanks to Mark Kettenis who initially identified this issue on
OpenBSD, and to Chen-Yu Tsai who reported the problem in Linux.
Fixes: 18fdb6348c480 ("arm64: irqchip/gic-v3: Select priorities at boot time")
Reported-by: Mark Kettenis <mark.kettenis@xs4all.nl>
Reported-by: Chen-Yu Tsai <wens@csie.org>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Chen-Yu Tsai <wens@csie.org>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/all/20241213141037.3995049-1-maz@kernel.org
|
|
percpu_base is used in various percpu functions that expect variable in
__percpu address space. Correct the declaration of percpu_base to
void __iomem * __percpu *percpu_base;
to declare the variable as __percpu pointer.
The patch fixes several sparse warnings:
irq-gic.c:1172:44: warning: incorrect type in assignment (different address spaces)
irq-gic.c:1172:44: expected void [noderef] __percpu *[noderef] __iomem *percpu_base
irq-gic.c:1172:44: got void [noderef] __iomem *[noderef] __percpu *
...
irq-gic.c:1231:43: warning: incorrect type in argument 1 (different address spaces)
irq-gic.c:1231:43: expected void [noderef] __percpu *__pdata
irq-gic.c:1231:43: got void [noderef] __percpu *[noderef] __iomem *percpu_base
There were no changes in the resulting object files.
Signed-off-by: Uros Bizjak <ubizjak@gmail.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/all/20241213145809.2918-2-ubizjak@gmail.com
|
|
Make queue_iostats_passthrough_show() report 0/1 in sysfs instead of 0/4.
This patch fixes the following sparse warning:
block/blk-sysfs.c:266:31: warning: incorrect type in argument 1 (different base types)
block/blk-sysfs.c:266:31: expected unsigned long var
block/blk-sysfs.c:266:31: got restricted blk_flags_t
Cc: Keith Busch <kbusch@kernel.org>
Cc: Christoph Hellwig <hch@lst.de>
Fixes: 110234da18ab ("block: enable passthrough command statistics")
Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Link: https://lore.kernel.org/r/20241212212941.1268662-4-bvanassche@acm.org
Signed-off-by: Jens Axboe <axboe@kernel.dk>
|
|
Move a statement that occurs in both branches of an if-statement in front
of the if-statement. Fix a typo in a source code comment. No functionality
has been changed.
Reviewed-by: Damien Le Moal <dlemoal@kernel.org>
Cc: Christoph Hellwig <hch@lst.de>
Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Nitesh Shetty <nj.shetty@samsung.com>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Link: https://lore.kernel.org/r/20241212212941.1268662-3-bvanassche@acm.org
Signed-off-by: Jens Axboe <axboe@kernel.dk>
|
|
Since commit fde02699c242 ("block: mq-deadline: Remove support for zone
write locking"), the local variable 'insert_before' is assigned once and
is used once. Hence remove this local variable.
Reviewed-by: Damien Le Moal <dlemoal@kernel.org>
Cc: Christoph Hellwig <hch@lst.de>
Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Nitesh Shetty <nj.shetty@samsung.com>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Link: https://lore.kernel.org/r/20241212212941.1268662-2-bvanassche@acm.org
Signed-off-by: Jens Axboe <axboe@kernel.dk>
|
|
When using svcr_in to check ZA and Streaming Mode, we should make sure
that the value in x2 is correct, otherwise it may trigger an Illegal
instruction if FEAT_SVE and !FEAT_SME.
Fixes: 43e3f85523e4 ("kselftest/arm64: Add SME support to syscall ABI test")
Signed-off-by: Weizhao Ouyang <o451686892@gmail.com>
Reviewed-by: Mark Brown <broonie@kernel.org>
Link: https://lore.kernel.org/r/20241211111639.12344-1-o451686892@gmail.com
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
|
|
When a PASID is used for SVA by a device, it's possible that the PASID
entry is cleared before the device flushes all ongoing DMA requests and
removes the SVA domain. This can occur when an exception happens and the
process terminates before the device driver stops DMA and calls the
iommu driver to unbind the PASID.
There's no need to drain the PRQ in the mm release path. Instead, the PRQ
will be drained in the SVA unbind path.
Unfortunately, commit c43e1ccdebf2 ("iommu/vt-d: Drain PRQs when domain
removed from RID") changed this behavior by unconditionally draining the
PRQ in intel_pasid_tear_down_entry(). This can lead to a potential
sleeping-in-atomic-context issue.
Smatch static checker warning:
drivers/iommu/intel/prq.c:95 intel_iommu_drain_pasid_prq()
warn: sleeping in atomic context
To avoid this issue, prevent draining the PRQ in the SVA mm release path
and restore the previous behavior.
Fixes: c43e1ccdebf2 ("iommu/vt-d: Drain PRQs when domain removed from RID")
Reported-by: Dan Carpenter <dan.carpenter@linaro.org>
Closes: https://lore.kernel.org/linux-iommu/c5187676-2fa2-4e29-94e0-4a279dc88b49@stanley.mountain/
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Link: https://lore.kernel.org/r/20241212021529.1104745-1-baolu.lu@linux.intel.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
|
|
The qi_batch is allocated when assigning cache tag for a domain. While
for nested parent domain, it is missed. Hence, when trying to map pages
to the nested parent, NULL dereference occurred. Also, there is potential
memleak since there is no lock around domain->qi_batch allocation.
To solve it, add a helper for qi_batch allocation, and call it in both
the __cache_tag_assign_domain() and __cache_tag_assign_parent_domain().
BUG: kernel NULL pointer dereference, address: 0000000000000200
#PF: supervisor read access in kernel mode
#PF: error_code(0x0000) - not-present page
PGD 8104795067 P4D 0
Oops: Oops: 0000 [#1] PREEMPT SMP NOPTI
CPU: 223 UID: 0 PID: 4357 Comm: qemu-system-x86 Not tainted 6.13.0-rc1-00028-g4b50c3c3b998-dirty #2632
Call Trace:
? __die+0x24/0x70
? page_fault_oops+0x80/0x150
? do_user_addr_fault+0x63/0x7b0
? exc_page_fault+0x7c/0x220
? asm_exc_page_fault+0x26/0x30
? cache_tag_flush_range_np+0x13c/0x260
intel_iommu_iotlb_sync_map+0x1a/0x30
iommu_map+0x61/0xf0
batch_to_domain+0x188/0x250
iopt_area_fill_domains+0x125/0x320
? rcu_is_watching+0x11/0x50
iopt_map_pages+0x63/0x100
iopt_map_common.isra.0+0xa7/0x190
iopt_map_user_pages+0x6a/0x80
iommufd_ioas_map+0xcd/0x1d0
iommufd_fops_ioctl+0x118/0x1c0
__x64_sys_ioctl+0x93/0xc0
do_syscall_64+0x71/0x140
entry_SYSCALL_64_after_hwframe+0x76/0x7e
Fixes: 705c1cdf1e73 ("iommu/vt-d: Introduce batched cache invalidation")
Cc: stable@vger.kernel.org
Co-developed-by: Lu Baolu <baolu.lu@linux.intel.com>
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Signed-off-by: Yi Liu <yi.l.liu@intel.com>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Link: https://lore.kernel.org/r/20241210130322.17175-1-yi.l.liu@intel.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
|
|
The current implementation removes cache tags after disabling ATS,
leading to potential memory leaks and kernel crashes. Specifically,
CACHE_TAG_DEVTLB type cache tags may still remain in the list even
after the domain is freed, causing a use-after-free condition.
This issue really shows up when multiple VFs from different PFs
passed through to a single user-space process via vfio-pci. In such
cases, the kernel may crash with kernel messages like:
BUG: kernel NULL pointer dereference, address: 0000000000000014
PGD 19036a067 P4D 1940a3067 PUD 136c9b067 PMD 0
Oops: Oops: 0000 [#1] PREEMPT SMP NOPTI
CPU: 74 UID: 0 PID: 3183 Comm: testCli Not tainted 6.11.9 #2
RIP: 0010:cache_tag_flush_range+0x9b/0x250
Call Trace:
<TASK>
? __die+0x1f/0x60
? page_fault_oops+0x163/0x590
? exc_page_fault+0x72/0x190
? asm_exc_page_fault+0x22/0x30
? cache_tag_flush_range+0x9b/0x250
? cache_tag_flush_range+0x5d/0x250
intel_iommu_tlb_sync+0x29/0x40
intel_iommu_unmap_pages+0xfe/0x160
__iommu_unmap+0xd8/0x1a0
vfio_unmap_unpin+0x182/0x340 [vfio_iommu_type1]
vfio_remove_dma+0x2a/0xb0 [vfio_iommu_type1]
vfio_iommu_type1_ioctl+0xafa/0x18e0 [vfio_iommu_type1]
Move cache_tag_unassign_domain() before iommu_disable_pci_caps() to fix
it.
Fixes: 3b1d9e2b2d68 ("iommu/vt-d: Add cache tag assignment interface")
Cc: stable@vger.kernel.org
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Link: https://lore.kernel.org/r/20241129020506.576413-1-baolu.lu@linux.intel.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
|
|
Commit eaf62ce1563b ("arm64/signal: Set up and restore the GCS
context for signal handlers") introduced a potential failure point
at the end of setup_return(). This is unfortunate as it is too late
to deliver a SIGSEGV: if that SIGSEGV is handled, the subsequent
sigreturn will end up returning to the original handler, which is
not the intention (since we failed to deliver that signal).
Make sure this does not happen by calling gcs_signal_entry()
at the very beginning of setup_return(), and add a comment just
after to discourage error cases being introduced from that point
onwards.
While at it, also take care of copy_siginfo_to_user(): since it may
fail, we shouldn't be calling it after setup_return() either. Call
it before setup_return() instead, and move the setting of X1/X2
inside setup_return() where it belongs (after the "point of no
failure").
Background: the first part of setup_rt_frame(), including
setup_sigframe(), has no impact on the execution of the interrupted
thread. The signal frame is written to the stack, but the stack
pointer remains unchanged. Failure at this stage can be recovered by
a SIGSEGV handler, and sigreturn will restore the original context,
at the point where the original signal occurred. On the other hand,
once setup_return() has updated registers including SP, the thread's
control flow has been modified and we must deliver the original
signal.
Fixes: eaf62ce1563b ("arm64/signal: Set up and restore the GCS context for signal handlers")
Signed-off-by: Kevin Brodsky <kevin.brodsky@arm.com>
Reviewed-by: Dave Martin <Dave.Martin@arm.com>
Reviewed-by: Mark Brown <broonie@kernel.org>
Link: https://lore.kernel.org/r/20241210160940.2031997-1-kevin.brodsky@arm.com
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
|
|
dlserver time is accounted when:
- dlserver is active and the dlserver proxies the cfs task.
- dlserver is active but deferred and cfs task runs after being picked
through the normal fair class pick.
dl_server_update is called in two places to make sure that both the
above times are accounted for. But it doesn't check if dlserver is
active or not. Now that we have this dl_server_active flag, we can
consolidate dl_server_update into one place and all we need to check is
whether dlserver is active or not. When dlserver is active there is only
two possible conditions:
- dlserver is deferred.
- cfs task is running on behalf of dlserver.
Fixes: a110a81c52a9 ("sched/deadline: Deferrable dl server")
Signed-off-by: "Vineeth Pillai (Google)" <vineeth@bitbyteword.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Tested-by: Marcel Ziswiler <marcel.ziswiler@codethink.co.uk> # ROCK 5B
Link: https://lore.kernel.org/r/20241213032244.877029-2-vineeth@bitbyteword.org
|
|
dlserver can get dequeued during a dlserver pick_task due to the delayed
deueue feature and this can lead to issues with dlserver logic as it
still thinks that dlserver is on the runqueue. The dlserver throttling
and replenish logic gets confused and can lead to double enqueue of
dlserver.
Double enqueue of dlserver could happend due to couple of reasons:
Case 1
------
Delayed dequeue feature[1] can cause dlserver being stopped during a
pick initiated by dlserver:
__pick_next_task
pick_task_dl -> server_pick_task
pick_task_fair
pick_next_entity (if (sched_delayed))
dequeue_entities
dl_server_stop
server_pick_task goes ahead with update_curr_dl_se without knowing that
dlserver is dequeued and this confuses the logic and may lead to
unintended enqueue while the server is stopped.
Case 2
------
A race condition between a task dequeue on one cpu and same task's enqueue
on this cpu by a remote cpu while the lock is released causing dlserver
double enqueue.
One cpu would be in the schedule() and releasing RQ-lock:
current->state = TASK_INTERRUPTIBLE();
schedule();
deactivate_task()
dl_stop_server();
pick_next_task()
pick_next_task_fair()
sched_balance_newidle()
rq_unlock(this_rq)
at which point another CPU can take our RQ-lock and do:
try_to_wake_up()
ttwu_queue()
rq_lock()
...
activate_task()
dl_server_start() --> first enqueue
wakeup_preempt() := check_preempt_wakeup_fair()
update_curr()
update_curr_task()
if (current->dl_server)
dl_server_update()
enqueue_dl_entity() --> second enqueue
This bug was not apparent as the enqueue in dl_server_start doesn't
usually happen because of the defer logic. But as a side effect of the
first case(dequeue during dlserver pick), dl_throttled and dl_yield will
be set and this causes the time accounting of dlserver to messup and
then leading to a enqueue in dl_server_start.
Have an explicit flag representing the status of dlserver to avoid the
confusion. This is set in dl_server_start and reset in dlserver_stop.
Fixes: 63ba8422f876 ("sched/deadline: Introduce deadline servers")
Suggested-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: "Vineeth Pillai (Google)" <vineeth@bitbyteword.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Tested-by: Marcel Ziswiler <marcel.ziswiler@codethink.co.uk> # ROCK 5B
Link: https://lkml.kernel.org/r/20241213032244.877029-1-vineeth@bitbyteword.org
|
|
esre_attribute::store() is not needed since commit af97a77bc01c (efi:
Move some sysfs files to be read-only by root). Drop it.
Found by https://github.com/jirislaby/clang-struct.
Signed-off-by: Jiri Slaby (SUSE) <jirislaby@kernel.org>
Cc: Ard Biesheuvel <ardb@kernel.org>
Cc: linux-efi@vger.kernel.org
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
|
|
Take advantage of the multigrain timestamp APIs to ensure that nobody
can sneak in and write things to a file between starting a file update
operation and committing the results. This should have been part of the
multigrain timestamp merge, but I forgot to fling it at jlayton when he
resubmitted the patchset due to developer bandwidth problems.
Cc: <stable@vger.kernel.org> # v6.13-rc1
Fixes: 4e40eff0b5737c ("fs: add infrastructure for multigrain timestamps")
Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
|
|
V4 symlink blocks didn't have headers, so return early if this is a V4
filesystem.
Cc: <stable@vger.kernel.org> # v5.1
Fixes: 39708c20ab5133 ("xfs: miscellaneous verifier magic value fixups")
Signed-off-by: "Darrick J. Wong" <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
|
Yan Zhao
Paolo Bonzini
Sean Christopherson
Binbin Wu
Suravee Suthikulpanit
Linus Torvalds
Priya Bala Govindasamy
Kumar Kartikeya Dwivedi
Leon Romanovsky
Nilay Shroff
Marc Zyngier
Uros Bizjak
Bart Van Assche
Weizhao Ouyang
Lu Baolu
Yi Liu
Kevin Brodsky
Vineeth Pillai (Google)
Jiri Slaby (SUSE)
Darrick J. Wong