Wenchao Hao [Wed, 12 Aug 2020 01:31:16 +0000 (18:31 -0700)]
mm/mempolicy.c: check parameters first in kernel_get_mempolicy
Previous implementatoin calls untagged_addr() before error check, while if
the error check failed and return EINVAL, the untagged_addr() call is just
useless work.
mm: mempolicy: fix kerneldoc of numa_map_to_online_node()
Fix W=1 compile warnings (invalid kerneldoc):
mm/mempolicy.c:137: warning: Function parameter or member 'node' not described in 'numa_map_to_online_node'
mm/mempolicy.c:137: warning: Excess function parameter 'nid' description in 'numa_map_to_online_node'
Nitin Gupta [Wed, 12 Aug 2020 01:31:07 +0000 (18:31 -0700)]
mm: use unsigned types for fragmentation score
Proactive compaction uses per-node/zone "fragmentation score" which is
always in range [0, 100], so use unsigned type of these scores as well as
for related constants.
Nitin Gupta [Wed, 12 Aug 2020 01:31:04 +0000 (18:31 -0700)]
mm: fix compile error due to COMPACTION_HPAGE_ORDER
Fix compile error when COMPACTION_HPAGE_ORDER is assigned to
HUGETLB_PAGE_ORDER. The correct way to check if this constant is defined
is to check for CONFIG_HUGETLBFS.
Nitin Gupta [Wed, 12 Aug 2020 01:31:00 +0000 (18:31 -0700)]
mm: proactive compaction
For some applications, we need to allocate almost all memory as hugepages.
However, on a running system, higher-order allocations can fail if the
memory is fragmented. Linux kernel currently does on-demand compaction as
we request more hugepages, but this style of compaction incurs very high
latency. Experiments with one-time full memory compaction (followed by
hugepage allocations) show that kernel is able to restore a highly
fragmented memory state to a fairly compacted memory state within <1 sec
for a 32G system. Such data suggests that a more proactive compaction can
help us allocate a large fraction of memory as hugepages keeping
allocation latencies low.
For a more proactive compaction, the approach taken here is to define a
new sysctl called 'vm.compaction_proactiveness' which dictates bounds for
external fragmentation which kcompactd tries to maintain.
The tunable takes a value in range [0, 100], with a default of 20.
Note that a previous version of this patch [1] was found to introduce too
many tunables (per-order extfrag{low, high}), but this one reduces them to
just one sysctl. Also, the new tunable is an opaque value instead of
asking for specific bounds of "external fragmentation", which would have
been difficult to estimate. The internal interpretation of this opaque
value allows for future fine-tuning.
Currently, we use a simple translation from this tunable to [low, high]
"fragmentation score" thresholds (low=100-proactiveness, high=low+10%).
The score for a node is defined as weighted mean of per-zone external
fragmentation. A zone's present_pages determines its weight.
To periodically check per-node score, we reuse per-node kcompactd threads,
which are woken up every 500 milliseconds to check the same. If a node's
score exceeds its high threshold (as derived from user-provided
proactiveness value), proactive compaction is started until its score
reaches its low threshold value. By default, proactiveness is set to 20,
which implies threshold values of low=80 and high=90.
This patch is largely based on ideas from Michal Hocko [2]. See also the
LWN article [3].
Performance data
================
System: x64_64, 1T RAM, 80 CPU threads.
Kernel: 5.6.0-rc3 + this patch
echo madvise | sudo tee /sys/kernel/mm/transparent_hugepage/enabled
echo madvise | sudo tee /sys/kernel/mm/transparent_hugepage/defrag
Before starting the driver, the system was fragmented from a userspace
program that allocates all memory and then for each 2M aligned section,
frees 3/4 of base pages using munmap. The workload is mainly anonymous
userspace pages, which are easy to move around. I intentionally avoided
unmovable pages in this test to see how much latency we incur when
hugepage allocations hit direct compaction.
1. Kernel hugepage allocation latencies
With the system in such a fragmented state, a kernel driver then allocates
as many hugepages as possible and measures allocation latency:
Total 2M hugepages allocated = 384105 (750G worth of hugepages out of 762G
total free => 98% of free memory could be allocated as hugepages)
2. JAVA heap allocation
In this test, we first fragment memory using the same method as for (1).
Then, we start a Java process with a heap size set to 700G and request the
heap to be allocated with THP hugepages. We also set THP to madvise to
allow hugepage backing of this heap.
The above command allocates 700G of Java heap using hugepages.
- With vanilla 5.6.0-rc3
17.39user 1666.48system 27:37.89elapsed
- With 5.6.0-rc3 + this patch, with proactiveness=20
8.35user 194.58system 3:19.62elapsed
Elapsed time remains around 3:15, as proactiveness is further increased.
Note that proactive compaction happens throughout the runtime of these
workloads. The situation of one-time compaction, sufficient to supply
hugepages for following allocation stream, can probably happen for more
extreme proactiveness values, like 80 or 90.
In the above Java workload, proactiveness is set to 20. The test starts
with a node's score of 80 or higher, depending on the delay between the
fragmentation step and starting the benchmark, which gives more-or-less
time for the initial round of compaction. As t he benchmark consumes
hugepages, node's score quickly rises above the high threshold (90) and
proactive compaction starts again, which brings down the score to the low
threshold level (80). Repeat.
bpftrace also confirms proactive compaction running 20+ times during the
runtime of this Java benchmark. kcompactd threads consume 100% of one of
the CPUs while it tries to bring a node's score within thresholds.
Backoff behavior
================
Above workloads produce a memory state which is easy to compact. However,
if memory is filled with unmovable pages, proactive compaction should
essentially back off. To test this aspect:
- Created a kernel driver that allocates almost all memory as hugepages
followed by freeing first 3/4 of each hugepage.
- Set proactiveness=40
- Note that proactive_compact_node() is deferred maximum number of times
with HPAGE_FRAG_CHECK_INTERVAL_MSEC of wait between each check
(=> ~30 seconds between retries).
Michal Koutný [Wed, 12 Aug 2020 01:30:57 +0000 (18:30 -0700)]
/proc/PID/smaps: consistent whitespace output format
The keys in smaps output are padded to fixed width with spaces. All
except for THPeligible that uses tabs (only since commit c06306696f83
("mm: thp: fix false negative of shmem vma's THP eligibility")).
Unify the output formatting to save time debugging some naïve parsers.
(Part of the unification is also aligning FilePmdMapped with others.)
Joonsoo Kim [Wed, 12 Aug 2020 01:30:54 +0000 (18:30 -0700)]
mm/vmscan: restore active/inactive ratio for anonymous LRU
Now that workingset detection is implemented for anonymous LRU, we don't
need large inactive list to allow detecting frequently accessed pages
before they are reclaimed, anymore. This effectively reverts the
temporary measure put in by commit "mm/vmscan: make active/inactive ratio
as 1:1 for anon lru".
Joonsoo Kim [Wed, 12 Aug 2020 01:30:50 +0000 (18:30 -0700)]
mm/swap: implement workingset detection for anonymous LRU
This patch implements workingset detection for anonymous LRU. All the
infrastructure is implemented by the previous patches so this patch just
activates the workingset detection by installing/retrieving the shadow
entry and adding refault calculation.
Joonsoo Kim [Wed, 12 Aug 2020 01:30:47 +0000 (18:30 -0700)]
mm/swapcache: support to handle the shadow entries
Workingset detection for anonymous page will be implemented in the
following patch and it requires to store the shadow entries into the
swapcache. This patch implements an infrastructure to store the shadow
entry in the swapcache.
Joonsoo Kim [Wed, 12 Aug 2020 01:30:43 +0000 (18:30 -0700)]
mm/workingset: prepare the workingset detection infrastructure for anon LRU
To prepare the workingset detection for anon LRU, this patch splits
workingset event counters for refault, activate and restore into anon and
file variants, as well as the refaults counter in struct lruvec.
Joonsoo Kim [Wed, 12 Aug 2020 01:30:40 +0000 (18:30 -0700)]
mm/vmscan: protect the workingset on anonymous LRU
In current implementation, newly created or swap-in anonymous page is
started on active list. Growing active list results in rebalancing
active/inactive list so old pages on active list are demoted to inactive
list. Hence, the page on active list isn't protected at all.
Following is an example of this situation.
Assume that 50 hot pages on active list. Numbers denote the number of
pages on active/inactive list (active | inactive).
1. 50 hot pages on active list
50(h) | 0
2. workload: 50 newly created (used-once) pages
50(uo) | 50(h)
3. workload: another 50 newly created (used-once) pages
50(uo) | 50(uo), swap-out 50(h)
This patch tries to fix this issue. Like as file LRU, newly created or
swap-in anonymous pages will be inserted to the inactive list. They are
promoted to active list if enough reference happens. This simple
modification changes the above example as following.
1. 50 hot pages on active list
50(h) | 0
2. workload: 50 newly created (used-once) pages
50(h) | 50(uo)
3. workload: another 50 newly created (used-once) pages
50(h) | 50(uo), swap-out 50(uo)
As you can see, hot pages on active list would be protected.
Note that, this implementation has a drawback that the page cannot be
promoted and will be swapped-out if re-access interval is greater than the
size of inactive list but less than the size of total(active+inactive).
To solve this potential issue, following patch will apply workingset
detection similar to the one that's already applied to file LRU.
Joonsoo Kim [Wed, 12 Aug 2020 01:30:36 +0000 (18:30 -0700)]
mm/vmscan: make active/inactive ratio as 1:1 for anon lru
Patch series "workingset protection/detection on the anonymous LRU list", v7.
* PROBLEM
In current implementation, newly created or swap-in anonymous page is
started on the active list. Growing the active list results in
rebalancing active/inactive list so old pages on the active list are
demoted to the inactive list. Hence, hot page on the active list isn't
protected at all.
Following is an example of this situation.
Assume that 50 hot pages on active list and system can contain total 100
pages. Numbers denote the number of pages on active/inactive list (active
| inactive). (h) stands for hot pages and (uo) stands for used-once
pages.
1. 50 hot pages on active list
50(h) | 0
2. workload: 50 newly created (used-once) pages
50(uo) | 50(h)
3. workload: another 50 newly created (used-once) pages
50(uo) | 50(uo), swap-out 50(h)
As we can see, hot pages are swapped-out and it would cause swap-in later.
* SOLUTION
Since this is what we want to avoid, this patchset implements workingset
protection. Like as the file LRU list, newly created or swap-in anonymous
page is started on the inactive list. Also, like as the file LRU list, if
enough reference happens, the page will be promoted. This simple
modification changes the above example as following.
1. 50 hot pages on active list
50(h) | 0
2. workload: 50 newly created (used-once) pages
50(h) | 50(uo)
3. workload: another 50 newly created (used-once) pages
50(h) | 50(uo), swap-out 50(uo)
hot pages remains in the active list. :)
* EXPERIMENT
I tested this scenario on my test bed and confirmed that this problem
happens on current implementation. I also checked that it is fixed by
this patchset.
* SUBJECT
workingset detection
* PROBLEM
Later part of the patchset implements the workingset detection for the
anonymous LRU list. There is a corner case that workingset protection
could cause thrashing. If we can avoid thrashing by workingset detection,
we can get the better performance.
Following is an example of thrashing due to the workingset protection.
1. 50 hot pages on active list
50(h) | 0
2. workload: 50 newly created (will be hot) pages
50(h) | 50(wh)
3. workload: another 50 newly created (used-once) pages
50(h) | 50(uo), swap-out 50(wh)
5. workload: another 50 newly created (used-once) pages
50(h) | 50(uo), swap-out 50(wh)
6. repeat 4, 5
Without workingset detection, this kind of workload cannot be promoted and
thrashing happens forever.
* SOLUTION
Therefore, this patchset implements workingset detection. All the
infrastructure for workingset detecion is already implemented, so there is
not much work to do. First, extend workingset detection code to deal with
the anonymous LRU list. Then, make swap cache handles the exceptional
value for the shadow entry. Lastly, install/retrieve the shadow value
into/from the swap cache and check the refault distance.
* EXPERIMENT
I made a test program to imitates above scenario and confirmed that
problem exists. Then, I checked that this patchset fixes it.
My test setup is a virtual machine with 8 cpus and 6100MB memory. But,
the amount of the memory that the test program can use is about 280 MB.
This is because the system uses large ram-backed swap and large ramdisk to
capture the trace.
Since hot-1 memory (96MB) is on the active list, the inactive list can
contains roughly 190MB pages. hot-2 memory's re-access interval (96+128
MB) is more 190MB, so it cannot be promoted without workingset detection
and swap-in/out happens repeatedly. With this patchset, workingset
detection works and promotion happens. Therefore, swap-in/out occurs
less.
Here is the result. (average of 5 runs)
type swap-in swap-out
base 863240 989945
patch 681565 809273
As we can see, patched kernel do less swap-in/out.
* OVERALL TEST (ebizzy using modified random function)
ebizzy is the test program that main thread allocates lots of memory and
child threads access them randomly during the given times. Swap-in will
happen if allocated memory is larger than the system memory.
The random function that represents the zipf distribution is used to make
hot/cold memory. Hot/cold ratio is controlled by the parameter. If the
parameter is high, hot memory is accessed much larger than cold one. If
the parameter is low, the number of access on each memory would be
similar. I uses various parameters in order to show the effect of
patchset on various hot/cold ratio workload.
My test setup is a virtual machine with 8 cpus, 1024 MB memory and 5120 MB
ram swap.
Result format is as following.
param: 1-1024-0.1
- 1 (number of thread)
- 1024 (allocated memory size, MB)
- 0.1 (zipf distribution alpha,
0.1 works like as roughly uniform random,
1.3 works like as small portion of memory is hot and the others are cold)
pswpin: smaller is better
std: standard deviation
improvement: negative is better
As we can see, all the cases show improvement. Especially, test case with
zipf distribution 1.3 show more improvements. It means that if there is a
hot/cold tendency in anon pages, this patchset works better.
This patch (of 6):
Current implementation of LRU management for anonymous page has some
problems. Most important one is that it doesn't protect the workingset,
that is, pages on the active LRU list. Although, this problem will be
fixed in the following patchset, the preparation is required and this
patch does it.
What following patch does is to implement workingset protection. After
the following patchset, newly created or swap-in pages will start their
lifetime on the inactive list. If inactive list is too small, there is
not enough chance to be referenced and the page cannot become the
workingset.
In order to provide the newly anonymous or swap-in pages enough chance to
be referenced again, this patch makes active/inactive LRU ratio as 1:1.
This is just a temporary measure. Later patch in the series introduces
workingset detection for anonymous LRU that will be used to better decide
if pages should start on the active and inactive list. Afterwards this
patch is effectively reverted.
Muchun Song [Wed, 12 Aug 2020 01:30:32 +0000 (18:30 -0700)]
mm/hugetlb: add mempolicy check in the reservation routine
In the reservation routine, we only check whether the cpuset meets the
memory allocation requirements. But we ignore the mempolicy of MPOL_BIND
case. If someone mmap hugetlb succeeds, but the subsequent memory
allocation may fail due to mempolicy restrictions and receives the SIGBUS
signal. This can be reproduced by the follow steps.
1) Compile the test case.
cd tools/testing/selftests/vm/
gcc map_hugetlb.c -o map_hugetlb
2) Pre-allocate huge pages. Suppose there are 2 numa nodes in the
system. Each node will pre-allocate one huge page.
echo 2 > /proc/sys/vm/nr_hugepages
3) Run test case(mmap 4MB). We receive the SIGBUS signal.
numactl --membind=3D0 ./map_hugetlb 4
With this patch applied, the mmap will fail in the step 3) and throw
"mmap: Cannot allocate memory".
Roman Gushchin [Wed, 12 Aug 2020 01:30:29 +0000 (18:30 -0700)]
kselftests: cgroup: add perpcu memory accounting test
Add a simple test to check the percpu memory accounting. The test creates
a cgroup tree with 1000 child cgroups and checks values of memory.current
and memory.stat::percpu.
Roman Gushchin [Wed, 12 Aug 2020 01:30:25 +0000 (18:30 -0700)]
mm: memcg: charge memcg percpu memory to the parent cgroup
Memory cgroups are using large chunks of percpu memory to store vmstat
data. Yet this memory is not accounted at all, so in the case when there
are many (dying) cgroups, it's not exactly clear where all the memory is.
Because the size of memory cgroup internal structures can dramatically
exceed the size of object or page which is pinning it in the memory, it's
not a good idea to simply ignore it. It actually breaks the isolation
between cgroups.
Let's account the consumed percpu memory to the parent cgroup.
Percpu memory can represent a noticeable chunk of the total memory
consumption, especially on big machines with many CPUs. Let's track
percpu memory usage for each memcg and display it in memory.stat.
A percpu allocation is usually scattered over multiple pages (and nodes),
and can be significantly smaller than a page. So let's add a byte-sized
counter on the memcg level: MEMCG_PERCPU_B. Byte-sized vmstat infra
created for slabs can be perfectly reused for percpu case.
Roman Gushchin [Wed, 12 Aug 2020 01:30:17 +0000 (18:30 -0700)]
mm: memcg/percpu: account percpu memory to memory cgroups
Percpu memory is becoming more and more widely used by various subsystems,
and the total amount of memory controlled by the percpu allocator can make
a good part of the total memory.
As an example, bpf maps can consume a lot of percpu memory, and they are
created by a user. Also, some cgroup internals (e.g. memory controller
statistics) can be quite large. On a machine with many CPUs and big
number of cgroups they can consume hundreds of megabytes.
So the lack of memcg accounting is creating a breach in the memory
isolation. Similar to the slab memory, percpu memory should be accounted
by default.
To implement the perpcu accounting it's possible to take the slab memory
accounting as a model to follow. Let's introduce two types of percpu
chunks: root and memcg. What makes memcg chunks different is an
additional space allocated to store memcg membership information. If
__GFP_ACCOUNT is passed on allocation, a memcg chunk should be be used.
If it's possible to charge the corresponding size to the target memory
cgroup, allocation is performed, and the memcg ownership data is recorded.
System-wide allocations are performed using root chunks, so there is no
additional memory overhead.
To implement a fast reparenting of percpu memory on memcg removal, we
don't store mem_cgroup pointers directly: instead we use obj_cgroup API,
introduced for slab accounting.
Roman Gushchin [Wed, 12 Aug 2020 01:30:14 +0000 (18:30 -0700)]
percpu: return number of released bytes from pcpu_free_area()
Patch series "mm: memcg accounting of percpu memory", v3.
This patchset adds percpu memory accounting to memory cgroups. It's based
on the rework of the slab controller and reuses concepts and features
introduced for the per-object slab accounting.
Percpu memory is becoming more and more widely used by various subsystems,
and the total amount of memory controlled by the percpu allocator can make
a good part of the total memory.
As an example, bpf maps can consume a lot of percpu memory, and they are
created by a user. Also, some cgroup internals (e.g. memory controller
statistics) can be quite large. On a machine with many CPUs and big
number of cgroups they can consume hundreds of megabytes.
So the lack of memcg accounting is creating a breach in the memory
isolation. Similar to the slab memory, percpu memory should be accounted
by default.
Percpu allocations by their nature are scattered over multiple pages, so
they can't be tracked on the per-page basis. So the per-object tracking
introduced by the new slab controller is reused.
The patchset implements charging of percpu allocations, adds memcg-level
statistics, enables accounting for percpu allocations made by memory
cgroup internals and provides some basic tests.
To implement the accounting of percpu memory without a significant memory
and performance overhead the following approach is used: all accounted
allocations are placed into a separate percpu chunk (or chunks). These
chunks are similar to default chunks, except that they do have an attached
vector of pointers to obj_cgroup objects, which is big enough to save a
pointer for each allocated object. On the allocation, if the allocation
has to be accounted (__GFP_ACCOUNT is passed, the allocating process
belongs to a non-root memory cgroup, etc), the memory cgroup is getting
charged and if the maximum limit is not exceeded the allocation is
performed using a memcg-aware chunk. Otherwise -ENOMEM is returned or the
allocation is forced over the limit, depending on gfp (as any other kernel
memory allocation). The memory cgroup information is saved in the
obj_cgroup vector at the corresponding offset. On the release time the
memcg information is restored from the vector and the cgroup is getting
uncharged. Unaccounted allocations (at this point the absolute majority
of all percpu allocations) are performed in the old way, so no additional
overhead is expected.
To avoid pinning dying memory cgroups by outstanding allocations,
obj_cgroup API is used instead of directly saving memory cgroup pointers.
obj_cgroup is basically a pointer to a memory cgroup with a standalone
reference counter. The trick is that it can be atomically swapped to
point at the parent cgroup, so that the original memory cgroup can be
released prior to all objects, which has been charged to it. Because all
charges and statistics are fully recursive, it's perfectly correct to
uncharge the parent cgroup instead. This scheme is used in the slab
memory accounting, and percpu memory can just follow the scheme.
This patch (of 5):
To implement accounting of percpu memory we need the information about the
size of freed object. Return it from pcpu_free_area().
Trond Myklebust [Tue, 11 Aug 2020 17:36:32 +0000 (13:36 -0400)]
NFS: Fix flexfiles read failover
The current mirrored read failover code is correctly resetting the mirror
index between failed reads, however it is not able to actually flip the
RPC call over to the next RPC client.
The end result is that we keep resending the RPC call to the same client
over and over.
The fix is to use the pnfs_read_resend_pnfs() mechanism to schedule a
new RPC call, but we need to add the ability to pass in a mirror
index so that we always retry the next mirror in the list.
Jens Axboe [Tue, 11 Aug 2020 15:50:19 +0000 (09:50 -0600)]
io_uring: fail poll arm on queue proc failure
Check the ipt.error value, it must have been either cleared to zero or
set to another error than the default -EINVAL if we don't go through the
waitqueue proc addition. Just give up on poll at that point and return
failure, this will fallback to async work.
io_poll_add() doesn't suffer from this failure case, as it returns the
error value directly.
Trond Myklebust [Wed, 5 Aug 2020 13:03:56 +0000 (09:03 -0400)]
NFS: Don't return layout segments that are in use
If the NFS_LAYOUT_RETURN_REQUESTED flag is set, we want to return the
layout as soon as possible, meaning that the affected layout segments
should be marked as invalid, and should no longer be in use for I/O.
Trond Myklebust [Tue, 4 Aug 2020 20:30:30 +0000 (16:30 -0400)]
NFS: Don't move layouts to plh_return_segs list while in use
If the layout segment is still in use for a read or a write, we should
not move it to the layout plh_return_segs list. If we do, we can end
up returning the layout while I/O is still in progress.
Fixes: e0b7d420f72a ("pNFS: Don't discard layout segments that are marked for return") Cc: [email protected] # v4.19+ Signed-off-by: Trond Myklebust <[email protected]>
parisc: Implement __smp_store_release and __smp_load_acquire barriers
This patch implements the __smp_store_release and __smp_load_acquire barriers
using ordered stores and loads. This avoids the sync instruction present in
the generic implementation.
Standard benchmark names let users know the tests specifics. For
example "2x1-bw-process" name tells that two processes one thread each
are run and the RAM bandwidth is measured.
Several benchmarks names do not correspond to their actual running
configuration. Fix that and also some whitespace and comment
inconsistencies.
tools headers UAPI: Sync kvm.h headers with the kernel sources
To pick the changes in:
3edd68399dc1 ("KVM: x86: Add a capability for GUEST_MAXPHYADDR < HOST_MAXPHYADDR support") 1aa561b1a4c0 ("kvm: x86: Add "last CPU" to some KVM_EXIT information") 23a60f834406 ("s390/kvm: diagnose 0x318 sync and reset")
That do not result in any change in tooling, as the additions are not
being used in any table generator.
This silences these perf build warning:
Warning: Kernel ABI header at 'tools/include/uapi/linux/kvm.h' differs from latest version at 'include/uapi/linux/kvm.h'
diff -u tools/include/uapi/linux/kvm.h include/uapi/linux/kvm.h
tools include UAPI: Sync linux/vhost.h with the kernel sources
To get the changes in:
25abc060d282 ("vhost-vdpa: support IOTLB batching hints")
This doesn't result in any changes in tooling, no new ioctls to be
picked up by the id->string table generators, etc.
Silencing this perf build warning:
Warning: Kernel ABI header at 'tools/include/uapi/linux/vhost.h' differs from latest version at 'include/uapi/linux/vhost.h'
diff -u tools/include/uapi/linux/vhost.h include/uapi/linux/vhost.h
tools headers kvm s390: Sync headers with the kernel sources
To pick the changes in:
23a60f834406 ("s390/kvm: diagnose 0x318 sync and reset")
None of them trigger any changes in tooling, this time this is just to silence
these perf build warnings:
Warning: Kernel ABI header at 'tools/arch/s390/include/uapi/asm/kvm.h' differs from latest version at 'arch/s390/include/uapi/asm/kvm.h'
diff -u tools/arch/s390/include/uapi/asm/kvm.h arch/s390/include/uapi/asm/kvm.h
I.e. to allow for modifiers to follow the syscall name and for logical
expressions to be accepted as filters to use with that syscall, be it as
trace event filters or BPF based ones.
Using -v we can see how the trace event filter is built:
This uses a copy of include/linux/socket.h that is kept in a directory
to be used just for these table generation scripts and for checking if
the kernel has a new file that maybe gets something new for these
tables.
This allows us to:
- Avoid accessing files outside tools/, in the kernel sources, that may
be changed in unexpected ways and thus break these scripts.
- Notice when those files change and thus check if the changes don't
break those scripts, update them to automatically get the new
definitions, a new socket family, for instance.
- Not add then to the tools/include/ where it may end up used while
building the tools and end up requiring dragging yet more stuff from
the kernel or plain break the build in some of the myriad environments
where perf may be built.
This will replace the previous static array in tools/perf/ that was
dated and was already missing the AF_KCM, AF_QIPCRTR, AF_SMC and AF_XDP
families.
The next cset will wire this up to the perf build process.
At some point this must be made into a library to be used in places such
as libtraceevent, bpftrace, etc.
Fix multiple issues when handling alarms:
- Use threaded interrupt to avoid scheduling when atomic
- Stop matching on week day as it may not be set correctly
- Avoid parsing the DT interrupt and use what is provided by the i2c or
spi subsystem
- Avoid returning IRQ_NONE in case of error in the interrupt handler
- Never write WDTF as specified in the datasheet
- Set uie_unsupported, as for the pcf85063, setting alarms every seconds
is not working correctly and confuses the RTC.
[CAUSE]
Since commit 929be17a9b49 ("btrfs: Switch btrfs_trim_free_extents to
find_first_clear_extent_bit"), we try to avoid trimming ranges that's
already trimmed.
So we check device->alloc_state by finding the first range which doesn't
have CHUNK_TRIMMED and CHUNK_ALLOCATED not set.
But if we shrunk the device, that bits are not cleared, thus we could
easily got a range starts beyond the shrunk device size.
This results the returned @start and @end are all beyond device size,
then we call "end = min(end, device->total_bytes -1);" making @end
smaller than device size.
Then finally we goes "len = end - start + 1", totally underflow the
result, and lead to the beyond-device-boundary access.
[FIX]
This patch will fix the problem in two ways:
- Clear CHUNK_TRIMMED | CHUNK_ALLOCATED bits when shrinking device
This is the root fix
- Add extra safety check when trimming free device extents
We check and warn if the returned range is already beyond current
device.
Takashi Iwai [Wed, 12 Aug 2020 07:02:56 +0000 (09:02 +0200)]
ALSA: hda/realtek - Fix unused variable warning
The previous fix forgot to remove the unused variable that triggers a
compile warning now:
sound/pci/hda/patch_realtek.c: In function 'alc285_fixup_hp_gpio_led':
sound/pci/hda/patch_realtek.c:4163:19: warning: unused variable 'spec' [-Wunused-variable]
Dave Airlie [Wed, 12 Aug 2020 02:58:19 +0000 (12:58 +1000)]
Merge branch 'vmwgfx-next-5.9' of git://people.freedesktop.org/~sroland/linux into drm-next
The drm_mode_config_reset patches are very important fixing a recently
introduced kernel crash, the others fix various older issues which are
a bit less serious in practice.
Sven Schnelle [Tue, 11 Aug 2020 16:19:19 +0000 (18:19 +0200)]
parisc: mask out enable and reserved bits from sba imask
When using kexec the SBA IOMMU IBASE might still have the RE
bit set. This triggers a WARN_ON when trying to write back the
IBASE register later, and it also makes some mask calculations fail.
Linus Torvalds [Wed, 12 Aug 2020 00:08:11 +0000 (17:08 -0700)]
Merge tag 'for-linus-5.9-ofs1' of git://git.kernel.org/pub/scm/linux/kernel/git/hubcap/linux
Pull orangefs updates from Mike Marshall:
"A fix and a cleanup...
The fix: Al Viro pointed out that I had broken some acl functionality
with one of my previous patches.
And the cleanup: Jing Xiangfeng found and removed a needless variable
assignment"
* tag 'for-linus-5.9-ofs1' of git://git.kernel.org/pub/scm/linux/kernel/git/hubcap/linux:
orangefs: remove unnecessary assignment to variable ret
orangefs: posix acl fix...
Linus Torvalds [Wed, 12 Aug 2020 00:05:55 +0000 (17:05 -0700)]
Merge tag 'zonefs-5.9-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/dlemoal/zonefs
Pull zonefs update from Damien Le Moal:
"A single change for this cycle adding support for zone capacities
smaller than the zone size, from Johannes"
* tag 'zonefs-5.9-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/dlemoal/zonefs:
zonefs: update documentation to reflect zone size vs capacity
zonefs: add zone-capacity support
MediaFailure and VolumeDirty should be retained if these are set before
mounting.
In '3.1.13.3 Media Failure Field' of exfat specification describe:
If, upon mounting a volume, the value of this field is 1,
implementations which scan the entire volume for media failures and
record all failures as "bad" clusters in the FAT (or otherwise resolve
media failures) may clear the value of this field to 0.
Therefore, We should not clear MediaFailure without scanning volume.
In '8.1 Recommended Write Ordering' of exfat specification describe:
Clear the value of the VolumeDirty field to 0, if its value prior to
the first step was 0.
Therefore, We should not clear VolumeDirty after mounting.
Also rename ERR_MEDIUM to MEDIA_FAILURE.
Tetsuhiro Kohada [Tue, 23 Jun 2020 06:22:19 +0000 (15:22 +0900)]
exfat: write multiple sectors at once
Write multiple sectors at once when updating dir-entries.
Add exfat_update_bhs() for that. It wait for write completion once
instead of sector by sector.
It's only effective if sync enabled.
Tetsuhiro Kohada [Tue, 16 Jun 2020 02:18:07 +0000 (11:18 +0900)]
exfat: remove EXFAT_SB_DIRTY flag
This flag is set/reset in exfat_put_super()/exfat_sync_fs()
to avoid sync_blockdev().
- exfat_put_super():
Before calling this, the VFS has already called sync_filesystem(),
so sync is never performed here.
- exfat_sync_fs():
After calling this, the VFS calls sync_blockdev(), so, it is meaningless
to check EXFAT_SB_DIRTY or to bypass sync_blockdev() here.
Remove the EXFAT_SB_DIRTY check to ensure synchronization.
And remove the code related to the flag.
====================
net: initialize fastreuse on inet_inherit_port
In the case of TPROXY, bind_conflict optimizations for SO_REUSEADDR or
SO_REUSEPORT are broken, possibly resulting in O(n) instead of O(1) bind
behaviour or in the incorrect reuse of a bind.
the kernel keeps track for each bind_bucket if all sockets in the
bind_bucket support SO_REUSEADDR or SO_REUSEPORT in two fastreuse flags.
These flags allow skipping the costly bind_conflict check when possible
(meaning when all sockets have the proper SO_REUSE option).
For every socket added to a bind_bucket, these flags need to be updated.
As soon as a socket that does not support reuse is added, the flag is
set to false and will never go back to true, unless the bind_bucket is
deleted.
Note that there is no mechanism to re-evaluate these flags when a socket
is removed (this might make sense when removing a socket that would not
allow reuse; this leaves room for a future patch).
For this optimization to work, it is mandatory that these flags are
properly initialized and updated.
When a child socket is created from a listen socket in
__inet_inherit_port, the TPROXY case could create a new bind bucket
without properly initializing these flags, thus preventing the
optimization to work. Alternatively, a socket not allowing reuse could
be added to an existing bind bucket without updating the flags, causing
bind_conflict to never be called as it should.
Patch 1/2 refactors the fastreuse update code in inet_csk_get_port into a
small helper function, making the actual fix tiny and easier to understand.
Patch 2/2 calls this new helper when __inet_inherit_port decides to create
a new bind_bucket or use a different bind_bucket than the one of the listen
socket.
v4: - rebase on latest linux/net master branch
v3: - remove company disclaimer from automatic signature
v2: - remove unnecessary cast
====================
Tim Froidcoeur [Tue, 11 Aug 2020 18:33:24 +0000 (20:33 +0200)]
net: initialize fastreuse on inet_inherit_port
In the case of TPROXY, bind_conflict optimizations for SO_REUSEADDR or
SO_REUSEPORT are broken, possibly resulting in O(n) instead of O(1) bind
behaviour or in the incorrect reuse of a bind.
the kernel keeps track for each bind_bucket if all sockets in the
bind_bucket support SO_REUSEADDR or SO_REUSEPORT in two fastreuse flags.
These flags allow skipping the costly bind_conflict check when possible
(meaning when all sockets have the proper SO_REUSE option).
For every socket added to a bind_bucket, these flags need to be updated.
As soon as a socket that does not support reuse is added, the flag is
set to false and will never go back to true, unless the bind_bucket is
deleted.
Note that there is no mechanism to re-evaluate these flags when a socket
is removed (this might make sense when removing a socket that would not
allow reuse; this leaves room for a future patch).
For this optimization to work, it is mandatory that these flags are
properly initialized and updated.
When a child socket is created from a listen socket in
__inet_inherit_port, the TPROXY case could create a new bind bucket
without properly initializing these flags, thus preventing the
optimization to work. Alternatively, a socket not allowing reuse could
be added to an existing bind bucket without updating the flags, causing
bind_conflict to never be called as it should.
Call inet_csk_update_fastreuse when __inet_inherit_port decides to create
a new bind_bucket or use a different bind_bucket than the one of the
listen socket.
Fixes: 093d282321da ("tproxy: fix hash locking issue when using port redirection in __inet_inherit_port()") Acked-by: Matthieu Baerts <[email protected]> Signed-off-by: Tim Froidcoeur <[email protected]> Signed-off-by: David S. Miller <[email protected]>
Commit c3e302edca24 ("net: phy: marvell10g: fix temperature sensor on 2110")
added a check for PHY ID via phydev->drv->phy_id in a function which is
called by devres at a time when phydev->drv is already set to null by
phy_remove function.
This null pointer dereference can be triggered via SFP subsystem with a
SFP module containing this Marvell PHY. When the SFP interface is put
down, the SFP subsystem removes the PHY.
Miaohe Lin [Mon, 10 Aug 2020 12:16:58 +0000 (08:16 -0400)]
net: Fix potential memory leak in proto_register()
If we failed to assign proto idx, we free the twsk_slab_name but forget to
free the twsk_slab. Add a helper function tw_prot_cleanup() to free these
together and also use this helper function in proto_unregister().
Fixes: b45ce32135d1 ("sock: fix potential memory leak in proto_register()") Signed-off-by: Miaohe Lin <[email protected]> Signed-off-by: David S. Miller <[email protected]>
Linus Torvalds [Tue, 11 Aug 2020 21:34:17 +0000 (14:34 -0700)]
Merge tag 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mst/vhost
Pull virtio updates from Michael Tsirkin:
- IRQ bypass support for vdpa and IFC
- MLX5 vdpa driver
- Endianness fixes for virtio drivers
- Misc other fixes
* tag 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mst/vhost: (71 commits)
vdpa/mlx5: fix up endian-ness for mtu
vdpa: Fix pointer math bug in vdpasim_get_config()
vdpa/mlx5: Fix pointer math in mlx5_vdpa_get_config()
vdpa/mlx5: fix memory allocation failure checks
vdpa/mlx5: Fix uninitialised variable in core/mr.c
vdpa_sim: init iommu lock
virtio_config: fix up warnings on parisc
vdpa/mlx5: Add VDPA driver for supported mlx5 devices
vdpa/mlx5: Add shared memory registration code
vdpa/mlx5: Add support library for mlx5 VDPA implementation
vdpa/mlx5: Add hardware descriptive header file
vdpa: Modify get_vq_state() to return error code
net/vdpa: Use struct for set/get vq state
vdpa: remove hard coded virtq num
vdpasim: support batch updating
vhost-vdpa: support IOTLB batching hints
vhost-vdpa: support get/set backend features
vhost: generialize backend features setting/getting
vhost-vdpa: refine ioctl pre-processing
vDPA: dont change vq irq after DRIVER_OK
...
Linus Torvalds [Tue, 11 Aug 2020 21:30:36 +0000 (14:30 -0700)]
Merge tag 'for-v5.9' of git://git.kernel.org/pub/scm/linux/kernel/git/jmorris/linux-security
Pull security subsystem updates from James Morris:
"A couple of minor documentation updates only for this release"
* tag 'for-v5.9' of git://git.kernel.org/pub/scm/linux/kernel/git/jmorris/linux-security:
LSM: drop duplicated words in header file comments
Replace HTTP links with HTTPS ones: security
Linus Torvalds [Tue, 11 Aug 2020 21:13:24 +0000 (14:13 -0700)]
Merge tag 'iommu-updates-v5.9' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu
Pull iommu updates from Joerg Roedel:
- Remove of the dev->archdata.iommu (or similar) pointers from most
architectures. Only Sparc is left, but this is private to Sparc as
their drivers don't use the IOMMU-API.
- ARM-SMMU updates from Will Deacon:
- Support for SMMU-500 implementation in Marvell Armada-AP806 SoC
- Support for SMMU-500 implementation in NVIDIA Tegra194 SoC
- DT compatible string updates
- Remove unused IOMMU_SYS_CACHE_ONLY flag
- Move ARM-SMMU drivers into their own subdirectory
- Intel VT-d updates from Lu Baolu:
- Misc tweaks and fixes for vSVA
- Report/response page request events
- Cleanups
- Move the Kconfig and Makefile bits for the AMD and Intel drivers into
their respective subdirectory.
- MT6779 IOMMU Support
- Support for new chipsets in the Renesas IOMMU driver
- Other misc cleanups and fixes (e.g. to improve compile test coverage)
* tag 'iommu-updates-v5.9' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu: (77 commits)
iommu/amd: Move Kconfig and Makefile bits down into amd directory
iommu/vt-d: Move Kconfig and Makefile bits down into intel directory
iommu/arm-smmu: Move Arm SMMU drivers into their own subdirectory
iommu/vt-d: Skip TE disabling on quirky gfx dedicated iommu
iommu: Add gfp parameter to io_pgtable_ops->map()
iommu: Mark __iommu_map_sg() as static
iommu/vt-d: Rename intel-pasid.h to pasid.h
iommu/vt-d: Add page response ops support
iommu/vt-d: Report page request faults for guest SVA
iommu/vt-d: Add a helper to get svm and sdev for pasid
iommu/vt-d: Refactor device_to_iommu() helper
iommu/vt-d: Disable multiple GPASID-dev bind
iommu/vt-d: Warn on out-of-range invalidation address
iommu/vt-d: Fix devTLB flush for vSVA
iommu/vt-d: Handle non-page aligned address
iommu/vt-d: Fix PASID devTLB invalidation
iommu/vt-d: Remove global page support in devTLB flush
iommu/vt-d: Enforce PASID devTLB field mask
iommu: Make some functions static
iommu/amd: Remove double zero check
...
Linus Torvalds [Tue, 11 Aug 2020 20:48:02 +0000 (13:48 -0700)]
Merge tag 'backlight-next-5.9' of git://git.kernel.org/pub/scm/linux/kernel/git/lee/backlight
Pull backlight updates from Lee Jones:
"Core Framework:
- Trivial: Code refactoring
- New API backlight_is_blank()
- New API backlight_get_brightness()
- Additional/reworked documentation
- Remove 'extern' labels from prototypes
- Drop backlight_put()
- Staticify of_find_backlight()
Driver Removal:
- Removal of unused OT200 driver
- Removal of unused Generic Backlight driver
Fix-ups
- Bunch of W=1 warning fixes
- Convert to GPIO descriptors; sky81452
- Move platform data handling into driver; sky81452
- Remove superfluous code; lms501kf03
- Many instances of using new APIs"
* tag 'backlight-next-5.9' of git://git.kernel.org/pub/scm/linux/kernel/git/lee/backlight: (34 commits)
video: backlight: cr_bllcd: Remove unused variable 'intensity'
backlight: backlight: Make of_find_backlight static
backlight: backlight: Drop backlight_put()
backlight: Use backlight_get_brightness() throughout
backlight: jornada720_bl: Introduce backlight_is_blank()
backlight: gpio_backlight: Simplify update_status()
backlight: cr_bllcd: Introduce gpio-backlight semantics
backlight: as3711_bl: Simplify update_status
backlight: backlight: Introduce backlight_get_brightness()
doc-rst: Wire-up Backlight kernel-doc documentation
backlight: backlight: Add overview and update existing doc
backlight: backlight: Drop extern from prototypes
backlight: generic_bl: Remove this driver as it is unused
backlight: backlight: Document enums in backlight.h
backlight: backlight: Document inline functions in backlight.h
backlight: backlight: Improve backlight_device documentation
backlight: backlight: Improve backlight_properties documentation
backlight: backlight: Improve backlight_ops documentation
backlight: backlight: Add backlight_is_blank()
backlight: backlight: Refactor fb_notifier_callback()
...
Ming Lei [Mon, 10 Aug 2020 03:59:50 +0000 (11:59 +0800)]
block: fix double account of flush request's driver tag
In case of none scheduler, we share data request's driver tag for
flush request, so have to mark the flush request as INFLIGHT for
avoiding double account of this driver tag.
Linus Torvalds [Tue, 11 Aug 2020 18:53:34 +0000 (11:53 -0700)]
Merge tag 'hwlock-v5.9' of git://git.kernel.org/pub/scm/linux/kernel/git/andersson/remoteproc
Pull hwspinlock updates from Bjorn Andersson:
"This introduces a new DT binding format to describe the Qualcomm
hardware mutex block and deprecates the old, invalid, one.
It also cleans up the Kconfig slightly"
* tag 'hwlock-v5.9' of git://git.kernel.org/pub/scm/linux/kernel/git/andersson/remoteproc:
dt-bindings: hwlock: qcom: Remove invalid binding
hwspinlock: qcom: Allow mmio usage in addition to syscon
dt-bindings: hwlock: qcom: Allow device on mmio bus
dt-bindings: hwlock: qcom: Migrate binding to YAML
hwspinlock: Simplify Kconfig
Linus Torvalds [Tue, 11 Aug 2020 18:17:45 +0000 (11:17 -0700)]
Merge tag 'rproc-v5.9' of git://git.kernel.org/pub/scm/linux/kernel/git/andersson/remoteproc
Pull remoteproc updates from Bjorn Andersson:
"This introduces a new "detached" state for remote processors that are
deemed to be running at the time Linux boots and the infrastructure
for "attaching" to these. It then introduces the support for
performing this operation for the STM32 platform.
The coredump functionality is moved out from the core file and gains
support for an optional mode where the recovery phase awaits the
notification from devcoredump that the dump should be released. This
allows userspace to grab the coredump in scenarios where vmalloc space
is too low for creating a complete copy of the coredump before handing
this to devcoredump.
A new character device based interface is introduced to allow tying
the stoppage of a remote processor to the termination of a user space
process. This is useful in situations when such process provides
crucial resources/operations for the firmware running on the remote
processor.
The Texas Instrument K3 driver gains support for the C66x and C71x
DSPs.
Qualcomm remoteprocs gains support for stashing relocation information
in IMEM, to aid post mortem debugging and the crash notification
mechanism is generalized to be reusable in cases where loosely coupled
drivers needs to know about the status of a remote processor. One such
example is the IPA hardware block, which is jointly owned with the
modem and migrated to this improved interface.
It also introduces a number of bug fixes and debug improvements for
the Qualcomm modem remoteproc driver.
And it cleans up the inconsistent interface for remoteproc drivers to
implement power management"
* tag 'rproc-v5.9' of git://git.kernel.org/pub/scm/linux/kernel/git/andersson/remoteproc: (56 commits)
remoteproc: core: Register the character device interface
remoteproc: Add remoteproc character device interface
remoteproc: kill IPA notify code
net: ipa: new notification infrastructure
remoteproc: k3-dsp: Add support for C71x DSPs
dt-bindings: remoteproc: k3-dsp: Update bindings for C71x DSPs
remoteproc: k3-dsp: Add support for L2RAM loading on C66x DSPs
remoteproc: k3-dsp: Add a remoteproc driver of K3 C66x DSPs
dt-bindings: remoteproc: Add bindings for C66x DSPs on TI K3 SoCs
remoteproc: k3: Add TI-SCI processor control helper functions
remoteproc: Introduce rproc_of_parse_firmware() helper
dt-bindings: arm: keystone: Add common TI SCI bindings
remoteproc: qcom_q6v5_mss: Remove redundant running state
remoteproc: qcom: q6v5: Update running state before requesting stop
remoteproc: qcom_q6v5_mss: Add modem debug policy support
remoteproc: qcom_q6v5_mss: Validate modem blob firmware size before load
remoteproc: qcom_q6v5_mss: Validate MBA firmware size before load
rpmsg: update documentation
remoteproc: qcom_q6v5_mss: Add MBA log extraction support
remoteproc: Add coredump debugfs entry
...
Linus Torvalds [Tue, 11 Aug 2020 17:59:19 +0000 (10:59 -0700)]
Merge tag 'libnvdimm-for-5.9' of git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm
Pull libnvdimm updayes from Vishal Verma:
"You'd normally receive this pull request from Dan Williams, but he's
busy watching a newborn (Congrats Dan!), so I'm watching libnvdimm
this cycle.
This adds a new feature in libnvdimm - 'Runtime Firmware Activation',
and a few small cleanups and fixes in libnvdimm and DAX. I'd
originally intended to make separate topic-based pull requests - one
for libnvdimm, and one for DAX, but some of the DAX material fell out
since it wasn't quite ready.
Summary:
- add 'Runtime Firmware Activation' support for NVDIMMs that
advertise the relevant capability
- misc libnvdimm and DAX cleanups"
* tag 'libnvdimm-for-5.9' of git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm:
libnvdimm/security: ensure sysfs poll thread woke up and fetch updated attr
libnvdimm/security: the 'security' attr never show 'overwrite' state
libnvdimm/security: fix a typo
ACPI: NFIT: Fix ARS zero-sized allocation
dax: Fix incorrect argument passed to xas_set_err()
ACPI: NFIT: Add runtime firmware activate support
PM, libnvdimm: Add runtime firmware activation support
libnvdimm: Convert to DEVICE_ATTR_ADMIN_RO()
drivers/dax: Expand lock scope to cover the use of addresses
fs/dax: Remove unused size parameter
dax: print error message by pr_info() in __generic_fsdax_supported()
driver-core: Introduce DEVICE_ATTR_ADMIN_{RO,RW}
tools/testing/nvdimm: Emulate firmware activation commands
tools/testing/nvdimm: Prepare nfit_ctl_test() for ND_CMD_CALL emulation
tools/testing/nvdimm: Add command debug messages
tools/testing/nvdimm: Cleanup dimm index passing
ACPI: NFIT: Define runtime firmware activation commands
ACPI: NFIT: Move bus_dsm_mask out of generic nvdimm_bus_descriptor
libnvdimm: Validate command family indices
Xu Wang [Mon, 10 Aug 2020 02:38:07 +0000 (02:38 +0000)]
ionic_lif: Use devm_kcalloc() in ionic_qcq_alloc()
A multiplication for the size determination of a memory allocation
indicated that an array data structure should be processed.
Thus use the corresponding function "devm_kcalloc".
Xie He [Sun, 9 Aug 2020 02:35:48 +0000 (19:35 -0700)]
drivers/net/wan/x25_asy: Added needed_headroom and a skb->len check
1. Added a skb->len check
This driver expects upper layers to include a pseudo header of 1 byte
when passing down a skb for transmission. This driver will read this
1-byte header. This patch added a skb->len check before reading the
header to make sure the header exists.
2. Added needed_headroom
When this driver transmits data,
first this driver will remove a pseudo header of 1 byte,
then the lapb module will prepend the LAPB header of 2 or 3 bytes.
So the value of needed_headroom in this driver should be 3 - 1.
Ira Weiny [Tue, 11 Aug 2020 00:02:58 +0000 (17:02 -0700)]
net/tls: Fix kmap usage
When MSG_OOB is specified to tls_device_sendpage() the mapped page is
never unmapped.
Hold off mapping the page until after the flags are checked and the page
is actually needed.
Fixes: e8f69799810c ("net/tls: Add generic NIC offload infrastructure") Signed-off-by: Ira Weiny <[email protected]> Reviewed-by: Jakub Kicinski <[email protected]> Signed-off-by: David S. Miller <[email protected]>
Billy Wilson [Thu, 6 Aug 2020 23:17:54 +0000 (17:17 -0600)]
docs: Correct the release date of 5.2 stable
A table lists the 5.2 stable release date as September 15, but it was
released on July 7. This may confuse a reader who is trying to
understand the stable update release cycle.
Kees Cook [Sat, 8 Aug 2020 07:14:36 +0000 (00:14 -0700)]
mailmap: Update comments for with format and more detalis
Without having first read the git-shortlog man-page, the format
of .mailmap may not be immediately obvious. Add comments with pointers
to the man-page, along with other details.
Randy Dunlap [Mon, 10 Aug 2020 02:49:41 +0000 (19:49 -0700)]
Doc: admin-guide: use correct legends in kernel-parameters.txt
Documentation/admin-guide/kernel-parameters.rst includes a legend
telling us what configurations or hardware platforms are relevant
for certain boot options. For X86, it is spelled "X86" and for
x86_64, it is spelled "X86-64", so make corrections for those.
Move all code from arch/s390/numa/ to arch/s390/kernel/
since numa.c is the only source file and all others were
deleted with the fake NUMA support removal.
Heiko Carstens [Wed, 5 Aug 2020 12:50:41 +0000 (14:50 +0200)]
s390/time: remove select CLOCKSOURCE_VALIDATE_LAST_CYCLE again
Sven Schnelle reported that setting CLOCKSOURCE_VALIDATE_LAST_CYCLE
doesn't make sense: even if our tod clock overflows delta calculation
(now - last) with unsigned 64 bit values will still be correct.
Change __debug_entry structure in the following way:
- remove redundant union
- Field containing cpuid is expanded to 16 bits. 8-bit width was not
enough since we already support up to 512 cpus.
- Field containing the timestamp is expanded to 60 bits. The timestamp
itself is now stored in the absolute Unix time format in microseconds
taking the Epoch Index into acount.
Adjust default header for debug entries by setting minimum width for cpuid
to 4 digits.
s390/Kconfig: add missing ZCRYPT dependency to VFIO_AP
The VFIO_AP uses ap_driver_register() (and deregister) functions
implemented in ap_bus.c (compiled into ap.o). However the ap.o will be
built only if CONFIG_ZCRYPT is selected.
This was not visible before commit e93a1695d7fb ("iommu: Enable compile
testing for some of drivers") because the CONFIG_VFIO_AP depends on
CONFIG_S390_AP_IOMMU which depends on the missing CONFIG_ZCRYPT. After
adding COMPILE_TEST, it is possible to select a configuration with
VFIO_AP and S390_AP_IOMMU but without the ZCRYPT.
Add proper dependency to the VFIO_AP to fix build errors:
The node distance is hardcoded to 0, which causes a trouble
for some user-level applications. In particular, "libnuma"
expects the distance of a node to itself as LOCAL_DISTANCE.
This update removes the offending node distance override.
In the first place, the initialization value of `rc` is wrong.
It is unnecessary to initialize `rc` variables, so remove their
initialization operation.
During s390_enable_sie(), we need to take care of splitting all qemu user
process THP mappings. This is currently done with follow_page(FOLL_SPLIT),
by simply iterating over all vma ranges, with PAGE_SIZE increment.
This logic is sub-optimal and can result in a lot of unnecessary overhead,
especially when using qemu and ASAN with large shadow map. Ilya reported
significant system slow-down with one CPU busy for a long time and overall
unresponsiveness.
Fix this by using walk_page_vma() and directly calling split_huge_pmd()
only for present pmds, which greatly reduces overhead.
cpufreq: intel_pstate: Implement passive mode with HWP enabled
Allow intel_pstate to work in the passive mode with HWP enabled and
make it set the HWP minimum performance limit (HWP floor) to the
P-state value given by the target frequency supplied by the cpufreq
governor, so as to prevent the HWP algorithm and the CPU scheduler
from working against each other, at least when the schedutil governor
is in use, and update the intel_pstate documentation accordingly.
Among other things, this allows utilization clamps to be taken
into account, at least to a certain extent, when intel_pstate is
in use and makes it more likely that sufficient capacity for
deadline tasks will be provided.
After this change, the resulting behavior of an HWP system with
intel_pstate in the passive mode should be close to the behavior
of the analogous non-HWP system with intel_pstate in the passive
mode, except that the HWP algorithm is generally allowed to make the
CPU run at a frequency above the floor P-state set by intel_pstate in
the entire available range of P-states, while without HWP a CPU can
run in a P-state above the requested one if the latter falls into the
range of turbo P-states (referred to as the turbo range) or if the
P-states of all CPUs in one package are coordinated with each other
at the hardware level.
[Note that in principle the HWP floor may not be taken into account
by the processor if it falls into the turbo range, in which case the
processor has a license to choose any P-state, either below or above
the HWP floor, just like a non-HWP processor in the case when the
target P-state falls into the turbo range.]
With this change applied, intel_pstate in the passive mode assumes
complete control over the HWP request MSR and concurrent changes of
that MSR (eg. via the direct MSR access interface) are overridden by
it.
projects / linux.git / log