While not obivous, kvm_vcpu_reset() leaves the nested mode by clearing
'vcpu->arch.hflags' but it does so without all the required housekeeping.
On SVM, it is possible to have a vCPU reset while in guest mode because
unlike VMX, on SVM, INIT's are not latched in SVM non root mode and in
addition to that L1 doesn't have to intercept triple fault, which should
also trigger L1's reset if happens in L2 while L1 didn't intercept it.
If one of the above conditions happen, KVM will continue to use vmcb02
while not having in the guest mode.
Later the IA32_EFER will be cleared which will lead to freeing of the
nested guest state which will (correctly) free the vmcb02, but since
KVM still uses it (incorrectly) this will lead to a use after free
and kernel crash.
This issue is assigned CVE-2022-3344
Cc: stable@vger.kernel.org
Signed-off-by: Maxim Levitsky <mlevitsk@redhat.com>
Message-Id: <20221103141351.50662-5-mlevitsk@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
add kvm_leave_nested which wraps a call to nested_ops->leave_nested
into a function.
Cc: stable@vger.kernel.org
Signed-off-by: Maxim Levitsky <mlevitsk@redhat.com>
Message-Id: <20221103141351.50662-4-mlevitsk@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Make sure that KVM uses vmcb01 before freeing nested state, and warn if
that is not the case.
This is a minimal fix for CVE-2022-3344 making the kernel print a warning
instead of a kernel panic.
Cc: stable@vger.kernel.org
Signed-off-by: Maxim Levitsky <mlevitsk@redhat.com>
Message-Id: <20221103141351.50662-3-mlevitsk@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
If the VM was terminated while nested, we free the nested state
while the vCPU still is in nested mode.
Soon a warning will be added for this condition.
Cc: stable@vger.kernel.org
Signed-off-by: Maxim Levitsky <mlevitsk@redhat.com>
Message-Id: <20221103141351.50662-2-mlevitsk@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Until the very recent commits, many bounded random integers were
calculated using `get_random_u32() % max_plus_one`, which not only
incurs the price of a division -- indicating performance mostly was not
a real issue -- but also does not result in a uniformly distributed
output if max_plus_one is not a power of two. Recent commits moved to
using `prandom_u32_max(max_plus_one)`, which replaces the division with
a faster multiplication, but still does not solve the issue with
non-uniform output.
For some users, maybe this isn't a problem, and for others, maybe it is,
but for the majority of users, probably the question has never been
posed and analyzed, and nobody thought much about it, probably assuming
random is random is random. In other words, the unthinking expectation
of most users is likely that the resultant numbers are uniform.
So we implement here an efficient way of generating uniform bounded
random integers. Through use of compile-time evaluation, and avoiding
divisions as much as possible, this commit introduces no measurable
overhead. At least for hot-path uses tested, any potential difference
was lost in the noise. On both clang and gcc, code generation is pretty
small.
The new function, get_random_u32_below(), lives in random.h, rather than
prandom.h, and has a "get_random_xxx" function name, because it is
suitable for all uses, including cryptography.
In order to be efficient, we implement a kernel-specific variant of
Daniel Lemire's algorithm from "Fast Random Integer Generation in an
Interval", linked below. The kernel's variant takes advantage of
constant folding to avoid divisions entirely in the vast majority of
cases, works on both 32-bit and 64-bit architectures, and requests a
minimal amount of bytes from the RNG.
Link: https://arxiv.org/pdf/1805.10941.pdf
Cc: stable@vger.kernel.org # to ease future backports that use this api
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
The first test of the kcsan selftest appears to test if get_random_u32()
returns two zeros in a row, and requires that it doesn't. This seems
like a bogus criteron. Remove it.
Acked-by: Marco Elver <elver@google.com>
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
Do not recover (i.e. zap) an NX Huge Page that is being dirty tracked,
as it will just be faulted back in at the same 4KiB granularity when
accessed by a vCPU. This may need to be changed if KVM ever supports
2MiB (or larger) dirty tracking granularity, or faulting huge pages
during dirty tracking for reads/executes. However for now, these zaps
are entirely wasteful.
In order to check if this commit increases the CPU usage of the NX
recovery worker thread I used a modified version of execute_perf_test
[1] that supports splitting guest memory into multiple slots and reports
/proc/pid/schedstat:se.sum_exec_runtime for the NX recovery worker just
before tearing down the VM. The goal was to force a large number of NX
Huge Page recoveries and see if the recovery worker used any more CPU.
Test Setup:
echo 1000 > /sys/module/kvm/parameters/nx_huge_pages_recovery_period_ms
echo 10 > /sys/module/kvm/parameters/nx_huge_pages_recovery_ratio
Test Command:
./execute_perf_test -v64 -s anonymous_hugetlb_1gb -x 16 -o
| kvm-nx-lpage-re:se.sum_exec_runtime |
| ---------------------------------------- |
Run | Before | After |
------- | ------------------ | ------------------- |
1 | 730.084105 | 724.375314 |
2 | 728.751339 | 740.581988 |
3 | 736.264720 | 757.078163 |
Comparing the median results, this commit results in about a 1% increase
CPU usage of the NX recovery worker when testing a VM with 16 slots.
However, the effect is negligible with the default halving time of NX
pages, which is 1 hour rather than 10 seconds given by period_ms = 1000,
ratio = 10.
[1] https://lore.kernel.org/kvm/20221019234050.3919566-2-dmatlack@google.com/
Signed-off-by: David Matlack <dmatlack@google.com>
Message-Id: <20221103204421.1146958-1-dmatlack@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Currently bpf_map_do_batch() first invokes fdget(batch.map_fd) to get
the target map file, then it invokes generic_map_update_batch() to do
batch update. generic_map_update_batch() will get the target map file
by using fdget(batch.map_fd) again and pass it to bpf_map_update_value().
The problem is map file returned by the second fdget() may be NULL or a
totally different file compared by map file in bpf_map_do_batch(). The
reason is that the first fdget() only guarantees the liveness of struct
file instead of file descriptor and the file description may be released
by concurrent close() through pick_file().
It doesn't incur any problem as for now, because maps with batch update
support don't use map file in .map_fd_get_ptr() ops. But it is better to
fix the potential access of an invalid map file.
Using __bpf_map_get() again in generic_map_update_batch() can not fix
the problem, because batch.map_fd may be closed and reopened, and the
returned map file may be different with map file got in
bpf_map_do_batch(), so just passing the map file directly to
.map_update_batch() in bpf_map_do_batch().
Signed-off-by: Hou Tao <houtao1@huawei.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Yonghong Song <yhs@fb.com>
Link: https://lore.kernel.org/bpf/20221116075059.1551277-1-houtao@huaweicloud.com
A removed SPTE is never present, hence the "if" in kvm_tdp_mmu_map
only fails in the exact same conditions that the earlier loop
tested in order to issue a "break". So, instead of checking twice the
condition (upper level SPTEs could not be created or was frozen), just
exit the loop with a goto---the usual poor-man C replacement for RAII
early returns.
While at it, do not use the "ret" variable for return values of
functions that do not return a RET_PF_* enum. This is clearer
and also makes it possible to initialize ret to RET_PF_RETRY.
Suggested-by: Robert Hoo <robert.hu@linux.intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Make fb_modesetting_disabled() a static-inline function when it is
defined in the header file. Avoid the linker error shown below.
ld: drivers/video/fbdev/core/fbmon.o: in function `fb_modesetting_disabled':
fbmon.c:(.text+0x1e4): multiple definition of `fb_modesetting_disabled'; drivers/video/fbdev/core/fbmem.o:fbmem.c:(.text+0x1bac): first defined here
A bug report is at [1].
Reported-by: Stephen Rothwell <sfr@canb.auug.org.au>
Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: Thomas Zimmermann <tzimmermann@suse.de>
Reviewed-by: Javier Martinez Canillas <javierm@redhat.com>
Fixes: 0ba2fa8cbd ("fbdev: Add support for the nomodeset kernel parameter")
Cc: Javier Martinez Canillas <javierm@redhat.com>
Cc: Daniel Vetter <daniel@ffwll.ch>
Cc: Helge Deller <deller@gmx.de>
Cc: linux-fbdev@vger.kernel.org
Cc: dri-devel@lists.freedesktop.org
Link: https://lore.kernel.org/dri-devel/20221117183214.2473e745@canb.auug.org.au/T/#u # 1
Link: https://patchwork.freedesktop.org/patch/msgid/20221117114729.7570-1-tzimmermann@suse.de
Cezanne platforms under the right circumstances have a synchronization
problem where attempting to enter s2idle may fail if the x86 cores are
put into HLT before hardware resume from the previous attempt has
completed.
To avoid this issue add a 10-20ms delay before entering s2idle another
time. This workaround will only be applied on interrupts that wake the
hardware but don't break the s2idle loop.
Cc: stable@vger.kernel.org # 6.1
Cc: "Mahapatra, Rajib" <Rajib.Mahapatra@amd.com>
Cc: "Raul Rangel" <rrangel@chromium.org>
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Link: https://lore.kernel.org/r/20221116154341.13382-1-mario.limonciello@amd.com
Reviewed-by: Hans de Goede <hdegoede@redhat.com>
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Now that the TDP MMU has a mechanism to split huge pages, use it in the
fault path when a huge page needs to be replaced with a mapping at a
lower level.
This change reduces the negative performance impact of NX HugePages.
Prior to this change if a vCPU executed from a huge page and NX
HugePages was enabled, the vCPU would take a fault, zap the huge page,
and mapping the faulting address at 4KiB with execute permissions
enabled. The rest of the memory would be left *unmapped* and have to be
faulted back in by the guest upon access (read, write, or execute). If
guest is backed by 1GiB, a single execute instruction can zap an entire
GiB of its physical address space.
For example, it can take a VM longer to execute from its memory than to
populate that memory in the first place:
$ ./execute_perf_test -s anonymous_hugetlb_1gb -v96
Populating memory : 2.748378795s
Executing from memory : 2.899670885s
With this change, such faults split the huge page instead of zapping it,
which avoids the non-present faults on the rest of the huge page:
$ ./execute_perf_test -s anonymous_hugetlb_1gb -v96
Populating memory : 2.729544474s
Executing from memory : 0.111965688s <---
This change also reduces the performance impact of dirty logging when
eager_page_split=N. eager_page_split=N (abbreviated "eps=N" below) can
be desirable for read-heavy workloads, as it avoids allocating memory to
split huge pages that are never written and avoids increasing the TLB
miss cost on reads of those pages.
| Config: ept=Y, tdp_mmu=Y, 5% writes |
| Iteration 1 dirty memory time |
| --------------------------------------------- |
vCPU Count | eps=N (Before) | eps=N (After) | eps=Y |
------------ | -------------- | ------------- | ------------ |
2 | 0.332305091s | 0.019615027s | 0.006108211s |
4 | 0.353096020s | 0.019452131s | 0.006214670s |
8 | 0.453938562s | 0.019748246s | 0.006610997s |
16 | 0.719095024s | 0.019972171s | 0.007757889s |
32 | 1.698727124s | 0.021361615s | 0.012274432s |
64 | 2.630673582s | 0.031122014s | 0.016994683s |
96 | 3.016535213s | 0.062608739s | 0.044760838s |
Eager page splitting remains beneficial for write-heavy workloads, but
the gap is now reduced.
| Config: ept=Y, tdp_mmu=Y, 100% writes |
| Iteration 1 dirty memory time |
| --------------------------------------------- |
vCPU Count | eps=N (Before) | eps=N (After) | eps=Y |
------------ | -------------- | ------------- | ------------ |
2 | 0.317710329s | 0.296204596s | 0.058689782s |
4 | 0.337102375s | 0.299841017s | 0.060343076s |
8 | 0.386025681s | 0.297274460s | 0.060399702s |
16 | 0.791462524s | 0.298942578s | 0.062508699s |
32 | 1.719646014s | 0.313101996s | 0.075984855s |
64 | 2.527973150s | 0.455779206s | 0.079789363s |
96 | 2.681123208s | 0.673778787s | 0.165386739s |
Further study is needed to determine if the remaining gap is acceptable
for customer workloads or if eager_page_split=N still requires a-priori
knowledge of the VM workload, especially when considering these costs
extrapolated out to large VMs with e.g. 416 vCPUs and 12TB RAM.
Signed-off-by: David Matlack <dmatlack@google.com>
Reviewed-by: Mingwei Zhang <mizhang@google.com>
Message-Id: <20221109185905.486172-3-dmatlack@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
The workaround was initially necessary due to dma_resv having only a
single exclusive fence slot, yet whe don't necessarily know what order
the gpu scheduler will schedule jobs. Unfortunately this workaround
also has the result of forcing implicit sync, even when userspace does
not want it.
However, since commit 047a1b877e ("dma-buf & drm/amdgpu: remove
dma_resv workaround") the workaround is no longer needed. So remove
it. This effectively reverts commit f1b3f696a0 ("drm/msm: Don't
break exclusive fence ordering")
Signed-off-by: Rob Clark <robdclark@chromium.org>
Patchwork: https://patchwork.freedesktop.org/patch/509457/
Link: https://lore.kernel.org/r/20221101214051.159988-1-robdclark@gmail.com
Obey kvm.halt_poll_ns in VMs not using KVM_CAP_HALT_POLL on every halt,
rather than just sampling the module parameter when the VM is first
created. This restore the original behavior of kvm.halt_poll_ns for VMs
that have not opted into KVM_CAP_HALT_POLL.
Notably, this change restores the ability for admins to disable or
change the maximum halt-polling time system wide for VMs not using
KVM_CAP_HALT_POLL.
Reported-by: Christian Borntraeger <borntraeger@de.ibm.com>
Fixes: acd05785e4 ("kvm: add capability for halt polling")
Signed-off-by: David Matlack <dmatlack@google.com>
Message-Id: <20221117001657.1067231-4-dmatlack@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Avoid re-reading kvm->max_halt_poll_ns multiple times during
halt-polling except when it is explicitly useful, e.g. to check if the
max time changed across a halt. kvm->max_halt_poll_ns can be changed at
any time by userspace via KVM_CAP_HALT_POLL.
This bug is unlikely to cause any serious side-effects. In the worst
case one halt polls for shorter or longer than it should, and then is
fixed up on the next halt. Furthmore, this is still possible since
kvm->max_halt_poll_ns are not synchronized with halts.
Fixes: acd05785e4 ("kvm: add capability for halt polling")
Signed-off-by: David Matlack <dmatlack@google.com>
Message-Id: <20221117001657.1067231-3-dmatlack@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Cap vcpu->halt_poll_ns based on the max halt polling time just before
halting, rather than after the last halt. This arguably provides better
accuracy if an admin disables halt polling in between halts, although
the improvement is nominal.
A side-effect of this change is that grow_halt_poll_ns() no longer needs
to access vcpu->kvm->max_halt_poll_ns, which will be useful in a future
commit where the max halt polling time can come from the module parameter
halt_poll_ns instead.
Signed-off-by: David Matlack <dmatlack@google.com>
Message-Id: <20221117001657.1067231-2-dmatlack@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Add support for C6 residency and C state type for MTL SAMedia. Also add
mtl_drpc.
v2: Fixed review comments (Ashutosh)
v3: Sort registers and fix whitespace errors in intel_gt_regs.h (Matt R)
Remove MTL_CC_SHIFT (Ashutosh)
Adapt to RC6 residency register code refactor (Jani N)
v4: Move MTL branch to top in drpc_show
v5: Use FORCEWAKE_MT identical to gen6_drpc (Ashutosh)
v6: Add MISSING_CASE for gt_core_status switch statement (Rodrigo)
Change state name for MTL_CC0 to C0 (from "on") (Rodrigo)
v7: Change state name for MTL_CC0 to RC0 (Rodrigo)
Signed-off-by: Ashutosh Dixit <ashutosh.dixit@intel.com>
Signed-off-by: Badal Nilawar <badal.nilawar@intel.com>
Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20221114123348.3474216-6-badal.nilawar@intel.com
Previously RC6 residency functions directly accepted RC6 residency register
MMIO offsets (there are four RC6 residency registers). This worked but
required an assumption on the residency register layout so was not future
proof.
Therefore change RC6 residency functions to accept RC6 residency types
instead of register MMIO offsets. The knowledge of register offsets as well
as ID to offset mapping is now maintained solely in intel_rc6 and can be
tailored for different platforms and different register layouts as need
arises.
v2: Address review comments by Jani N
- Change residency functions to accept RC6 residency types instead of
register ID's
- s/intel_rc6_print_rc5_res/intel_rc6_print_residency/
- Remove "const enum" in function arguments
- Naming: intel_rc6_* for enum
- Use INTEL_RC6_RES_MAX and other minor changes
v3: Don't include intel_rc6_types.h in intel_rc6.h (Jani)
Suggested-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Suggested-by: Jani Nikula <jani.nikula@linux.intel.com>
Reported-by: Jani Nikula <jani.nikula@linux.intel.com>
Signed-off-by: Ashutosh Dixit <ashutosh.dixit@intel.com>
Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Signed-off-by: Badal Nilawar <badal.nilawar@intel.com>
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20221114123348.3474216-5-badal.nilawar@intel.com
Update CAGF functions for MTL to get actual resolved frequency of 3D and
SAMedia.
v2: Update MTL_MIRROR_TARGET_WP1 position/formatting (MattR)
Move MTL branches in cagf functions to top (MattR)
Fix commit message (Andi)
v3: Added comment about registers not needing forcewake for Gen12+ and
returning 0 freq in RC6
v4: Use REG_FIELD_GET and uncore (Rodrigo)
Bspec: 66300
Signed-off-by: Ashutosh Dixit <ashutosh.dixit@intel.com>
Signed-off-by: Badal Nilawar <badal.nilawar@intel.com>
Reviewed-by: Ashutosh Dixit <ashutosh.dixit@intel.com>
Acked-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20221114123348.3474216-4-badal.nilawar@intel.com
On GEN12+ use GEN12_RPSTAT register to get actual resolved GT
freq. GEN12_RPSTAT does not require a forcewake and will return 0 freq if
GT is in RC6.
v2:
- Fixed review comments(Ashutosh)
- Added function intel_rps_read_rpstat_fw to read RPSTAT without
forcewake, required especially for GEN6_RPSTAT1 (Ashutosh, Tvrtko)
v3:
- Updated commit title and message for more clarity (Ashutosh)
- Replaced intel_rps_read_rpstat with direct read to GEN12_RPSTAT1 in
read_cagf (Ashutosh)
v4: Remove GEN12_CAGF_SHIFT and use REG_FIELD_GET (Rodrigo)
Cc: Don Hiatt <donhiatt@gmail.com>
Cc: Andi Shyti <andi.shyti@intel.com>
Signed-off-by: Don Hiatt <don.hiatt@intel.com>
Signed-off-by: Badal Nilawar <badal.nilawar@intel.com>
Signed-off-by: Ashutosh Dixit <ashutosh.dixit@intel.com>
Reviewed-by: Andi Shyti <andi.shyti@linux.intel.com>
Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20221114123348.3474216-3-badal.nilawar@intel.com
Instead of masks/shifts settle on REG_FIELD_GET as the standard way to
extract reg fields. This allows future patches touching this code to also
consistently use REG_FIELD_GET and friends.
Suggested-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Signed-off-by: Ashutosh Dixit <ashutosh.dixit@intel.com>
Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Signed-off-by: Badal Nilawar <badal.nilawar@intel.com>
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20221114123348.3474216-2-badal.nilawar@intel.com
The SC8280XP currently shows depressing results in memory benchmarks.
Fix this by introducing support for the platform in the OSM (and EPSS)
L3 driver and support for the platform in the bwmon binding.
Link: https://lore.kernel.org/r/20221111032515.3460-1-quic_bjorande@quicinc.com
Signed-off-by: Georgi Djakov <djakov@kernel.org>
kvm_pmu_set_counter_value() is pretty odd, as it tries to update
the counter value while taking into account the value that is
currently held by the running perf counter.
This is not only complicated, this is quite wrong. Nowhere in
the architecture is it said that the counter would be offset
by something that is pending. The counter should be updated
with the value set by SW, and start counting from there if
required.
Remove the odd computation and just assign the provided value
after having released the perf event (which is then restarted).
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20221113163832.3154370-9-maz@kernel.org
In order to reduce the boilerplate code, add two helpers returning
the counter register index (resp. the event register) in the vcpu
register file from the counter index.
Reviewed-by: Oliver Upton <oliver.upton@linux.dev>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20221113163832.3154370-8-maz@kernel.org
The current PMU emulation sometimes narrows counters to 32bit
if the counter isn't the cycle counter. As this is going to
change with PMUv3p5 where the counters are all 64bit, fix
the couple of cases where this happens unconditionally.
Signed-off-by: Marc Zyngier <maz@kernel.org>
Reviewed-by: Reiji Watanabe <reijiw@google.com>
Link: https://lore.kernel.org/r/20221113163832.3154370-7-maz@kernel.org
For 64bit counters that overflow on a 32bit boundary, make
sure we only check the bottom 32bit to generate a CHAIN event.
Signed-off-by: Marc Zyngier <maz@kernel.org>
Reviewed-by: Reiji Watanabe <reijiw@google.com>
Link: https://lore.kernel.org/r/20221113163832.3154370-6-maz@kernel.org
The PMU architecture makes a subtle difference between a 64bit
counter and a counter that has a 64bit overflow. This is for example
the case of the cycle counter, which can generate an overflow on
a 32bit boundary if PMCR_EL0.LC==0 despite the accumulation being
done on 64 bits.
Use this distinction in the few cases where it matters in the code,
as we will reuse this with PMUv3p5 long counters.
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20221113163832.3154370-5-maz@kernel.org
Even when the underlying HW doesn't offer the CHAIN event
(which happens with QEMU), we can always support it as we're
in control of the counter overflow.
Always advertise the event via PMCEID0_EL0.
Reviewed-by: Reiji Watanabe <reijiw@google.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20221113163832.3154370-4-maz@kernel.org
devm_ioremap_resource() prints error message in itself. Remove the
dev_err call to avoid redundant error message.
Signed-off-by: Shang XiaoJing <shangxiaojing@huawei.com>
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/r/20220924015043.25130-1-shangxiaojing@huawei.com
Signed-off-by: Georgi Djakov <djakov@kernel.org>
Ricardo recently pointed out that the PMU chained counter emulation
in KVM wasn't quite behaving like the one on actual hardware, in
the sense that a chained counter would expose an overflow on
both halves of a chained counter, while KVM would only expose the
overflow on the top half.
The difference is subtle, but significant. What does the architecture
say (DDI0087 H.a):
- Up to PMUv3p4, all counters but the cycle counter are 32bit
- A 32bit counter that overflows generates a CHAIN event on the
adjacent counter after exposing its own overflow status
- The CHAIN event is accounted if the counter is correctly
configured (CHAIN event selected and counter enabled)
This all means that our current implementation (which uses 64bit
perf events) prevents us from emulating this overflow on the lower half.
How to fix this? By implementing the above, to the letter.
This largely results in code deletion, removing the notions of
"counter pair", "chained counters", and "canonical counter".
The code is further restructured to make the CHAIN handling similar
to SWINC, as the two are now extremely similar in behaviour.
Reported-by: Ricardo Koller <ricarkol@google.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Reviewed-by: Reiji Watanabe <reijiw@google.com>
Link: https://lore.kernel.org/r/20221113163832.3154370-3-maz@kernel.org
Commit 26a9b433cf ("bpf/docs: Document how to run CI without patch
submission") caused a warning to be generated when compiling the
documentation:
> bpf_devel_QA.rst:55: WARNING: Unexpected indentation.
> bpf_devel_QA.rst:56: WARNING: Block quote ends without a blank line
This change fixes the problem by inserting the required blank lines.
Fixes: 26a9b433cf ("bpf/docs: Document how to run CI without patch submission")
Reported-by: Akira Yokosawa <akiyks@gmail.com>
Signed-off-by: Daniel Müller <deso@posteo.net>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Akira Yokosawa <akiyks@gmail.com>
Link: https://lore.kernel.org/bpf/20221116174358.2744613-1-deso@posteo.net
The sc8280xp platform has two BWMON instances, one v4 and one v5. Extend
the existing qcom,msm8998-bwmon and qcom,sc7280-llcc-bwmon to describe
these.
Signed-off-by: Bjorn Andersson <quic_bjorande@quicinc.com>
Tested-by: Steev Klimaszewski <steev@kali.org>
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Reviewed-by: Sibi Sankar <quic_sibis@quicinc.com>
Link: https://lore.kernel.org/r/20221111032515.3460-10-quic_bjorande@quicinc.com
Signed-off-by: Georgi Djakov <djakov@kernel.org>
Add EPSS L3 compatibles for sm8350 and sc8280xp, but while at it also
introduce generic compatible for both qcom,osm-l3 and qcom,epss-l3.
Signed-off-by: Bjorn Andersson <quic_bjorande@quicinc.com>
Tested-by: Steev Klimaszewski <steev@kali.org>
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Reviewed-by: Sibi Sankar <quic_sibis@quicinc.com>
Link: https://lore.kernel.org/r/20221111032515.3460-6-quic_bjorande@quicinc.com
Signed-off-by: Georgi Djakov <djakov@kernel.org>
Now that the PCI/MSI core code does early checking for multi-MSI support
X86_IRQ_ALLOC_CONTIGUOUS_VECTORS is not required anymore.
Remove the flag and rely on MSI_FLAG_MULTI_PCI_MSI.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Link: https://lore.kernel.org/r/20221111122015.865042356@linutronix.de
All these sanity checks are now done _before_ any allocation work
happens. No point in doing it twice.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Acked-by: Bjorn Helgaas <bhelgaas@google.com>
Link: https://lore.kernel.org/r/20221111122015.749446904@linutronix.de
With interrupt domains the sanity check for MSI-X vector validation can be
done _before_ any allocation happens. The sanity check only applies to the
allocation functions which have an 'entries' array argument. The entries
array is filled by the caller with the requested MSI-X indices. Some drivers
have gaps in the index space which is not supported on all architectures.
The PCI/MSI irq domain has a 'feature' bit to enforce this validation late
during the allocation phase.
Just do it right away before doing any other work along with the other
sanity checks on that array.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Acked-by: Bjorn Helgaas <bhelgaas@google.com>
Link: https://lore.kernel.org/r/20221111122015.691357406@linutronix.de
Similar to PCI multi-MSI reject MSI-X enablement when a irq domain is
attached to the device which does not support MSI-X.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Acked-by: Bjorn Helgaas <bhelgaas@google.com>
Link: https://lore.kernel.org/r/20221111122015.631728309@linutronix.de
When hierarchical MSI interrupt domains are enabled then there is no point
to do tons of work and detect the missing support for multi-MSI late in the
allocation path.
Just query the domain feature flags right away. The query function is going
to be used for other purposes later and has a mode argument which influences
the result:
ALLOW_LEGACY returns true when:
- there is no irq domain attached (legacy support)
- there is a irq domain attached which has the feature flag set
DENY_LEGACY returns only true when:
- there is a irq domain attached which has the feature flag set
This allows to use the function universally without ifdeffery in the
calling code.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Acked-by: Bjorn Helgaas <bhelgaas@google.com>
Link: https://lore.kernel.org/r/20221111122015.574339988@linutronix.de
There is no point in doing the same sanity checks over and over in a loop
during MSI-X enablement. Put them in front of the loop and return early
when they fail.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Acked-by: Bjorn Helgaas <bhelgaas@google.com>
Link: https://lore.kernel.org/r/20221111122015.516946468@linutronix.de
There is no way to navigate msi.c without banging the head against the wall
every now and then because MSI and MSI-X specific functions are
intermingled and the code flow is completely non-obvious.
Reorder everthing so common helpers, MSI and MSI-X specific functions are
grouped together.
Suggested-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Ahmed S. Darwish <darwi@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Bjorn Helgaas <bhelgaas@google.com>
Link: https://lore.kernel.org/r/20221111122015.459089736@linutronix.de
All exported device-driver MSI APIs are now grouped in one place at
drivers/pci/msi/api.c with comprehensive kernel-docs added.
Reference these kernel-docs in the official PCI/MSI howto.
Signed-off-by: Ahmed S. Darwish <darwi@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Acked-by: Bjorn Helgaas <bhelgaas@google.com>
Link: https://lore.kernel.org/r/20221111122015.397739421@linutronix.de
To disentangle the maze in msi.c, all exported device-driver MSI APIs are
now to be grouped in one file, api.c.
Move pci_msi_enabled() and add kernel-doc for the function.
Signed-off-by: Ahmed S. Darwish <darwi@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Bjorn Helgaas <bhelgaas@google.com>
Link: https://lore.kernel.org/r/20221111122015.331584998@linutronix.de
To disentangle the maze in msi.c, all exported device-driver MSI APIs are
now to be grouped in one file, api.c.
Move pci_msi_enabled() and make its kernel-doc comprehensive.
Signed-off-by: Ahmed S. Darwish <darwi@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Bjorn Helgaas <bhelgaas@google.com>
Link: https://lore.kernel.org/r/20221111122015.271447896@linutronix.de
To disentangle the maze in msi.c, all exported device-driver MSI APIs are
now to be grouped in one file, api.c.
Move pci_irq_get_affinity() and let its kernel-doc match rest of the
file.
Signed-off-by: Ahmed S. Darwish <darwi@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Bjorn Helgaas <bhelgaas@google.com>
Link: https://lore.kernel.org/r/20221111122015.214792769@linutronix.de
