Some of our servers spend significant time at kernel boot initializing
memory block sysfs directories and then creating symlinks between them and
the corresponding nodes. The slowness happens because the machines get
stuck with the smallest supported memory block size on x86 (128M), which
results in 16,288 directories to cover the 2T of installed RAM. The
search for each memory block is noticeable even with commit 4fb6eabf10
("drivers/base/memory.c: cache memory blocks in xarray to accelerate
lookup").
Commit 078eb6aa50 ("x86/mm/memory_hotplug: determine block size based on
the end of boot memory") chooses the block size based on alignment with
memory end. That addresses hotplug failures in qemu guests, but for bare
metal systems whose memory end isn't aligned to even the smallest size, it
leaves them at 128M.
Make kernels that aren't running on a hypervisor use the largest supported
size (2G) to minimize overhead on big machines. Kernel boot goes 7%
faster on the aforementioned servers, shaving off half a second.
[daniel.m.jordan@oracle.com: v3]
Link: http://lkml.kernel.org/r/20200714205450.945834-1-daniel.m.jordan@oracle.com
Signed-off-by: Daniel Jordan <daniel.m.jordan@oracle.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Acked-by: David Hildenbrand <david@redhat.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Pavel Tatashin <pasha.tatashin@soleen.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Steven Sistare <steven.sistare@oracle.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/20200609225451.3542648-1-daniel.m.jordan@oracle.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
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.
Cc: <stable@vger.kernel.org> # 4.14+
Signed-off-by: Dave Anglin <dave.anglin@bell.net>
Signed-off-by: Helge Deller <deller@gmx.de>
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
...
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
...
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.
Signed-off-by: Alexander Gordeev <agordeev@linux.ibm.com>
Signed-off-by: Heiko Carstens <hca@linux.ibm.com>
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.
Therefore revert commit 555701a714 ("s390/time: select
CLOCKSOURCE_VALIDATE_LAST_CYCLE").
Fixes: 555701a714 ("s390/time: select CLOCKSOURCE_VALIDATE_LAST_CYCLE")
Reported-by: Sven Schnelle <svens@linux.ibm.com>
Signed-off-by: Heiko Carstens <hca@linux.ibm.com>
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.
Reviewed-by: Heiko Carstens <hca@linux.ibm.com>
Signed-off-by: Mikhail Zaslonko <zaslonko@linux.ibm.com>
Signed-off-by: Heiko Carstens <hca@linux.ibm.com>
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 e93a1695d7 ("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:
ERROR: modpost: "ap_driver_register" [drivers/s390/crypto/vfio_ap.ko] undefined!
ERROR: modpost: "ap_driver_unregister" [drivers/s390/crypto/vfio_ap.ko] undefined!
Reported-by: kernel test robot <lkp@intel.com>
Fixes: e93a1695d7 ("iommu: Enable compile testing for some of drivers")
Signed-off-by: Krzysztof Kozlowski <krzk@kernel.org>
Signed-off-by: Heiko Carstens <hca@linux.ibm.com>
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.
Cc: <stable@vger.kernel.org> # 4.4
Fixes: 3a368f742d ("s390/numa: add core infrastructure")
Signed-off-by: Alexander Gordeev <agordeev@linux.ibm.com>
Signed-off-by: Heiko Carstens <hca@linux.ibm.com>
test_unwind() misses to call kfree(bt) in an error path.
Add the missed function call to fix it.
Fixes: 0610154650 ("s390/test_unwind: print verbose unwinding results")
Reported-by: Hulk Robot <hulkci@huawei.com>
Signed-off-by: Wang Hai <wanghai38@huawei.com>
Acked-by: Ilya Leoshkevich <iii@linux.ibm.com>
Signed-off-by: Heiko Carstens <hca@linux.ibm.com>
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.
Cc: <stable@vger.kernel.org> # v5.4+
Reported-by: Ilya Leoshkevich <iii@linux.ibm.com>
Tested-by: Ilya Leoshkevich <iii@linux.ibm.com>
Acked-by: Christian Borntraeger <borntraeger@de.ibm.com>
Signed-off-by: Gerald Schaefer <gerald.schaefer@linux.ibm.com>
Signed-off-by: Heiko Carstens <hca@linux.ibm.com>
Commit c34b26b98c ("KVM: MIPS: clean up redundant 'kvm_run'
parameters") remove the 'kvm_run' parameter in kvm_vz_gpsi_lwc2.
The following build error:
arch/mips/kvm/vz.c: In function 'kvm_trap_vz_handle_gpsi':
arch/mips/kvm/vz.c:1243:43: error: 'run' undeclared (first use in this function)
er = kvm_vz_gpsi_lwc2(inst, opc, cause, run, vcpu);
^~~
arch/mips/kvm/vz.c:1243:43: note: each undeclared identifier is reported only
once for each function it appears in
scripts/Makefile.build:283: recipe for target 'arch/mips/kvm/vz.o' failed
make[2]: *** [arch/mips/kvm/vz.o] Error 1
scripts/Makefile.build:500: recipe for target 'arch/mips/kvm' failed
make[1]: *** [arch/mips/kvm] Error 2
Makefile:1785: recipe for target 'arch/mips' failed
make: *** [arch/mips] Error 2
Signed-off-by: Xingxing Su <suxingxing@loongson.cn>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
In an effort to enable -Wcast-function-type in the top-level Makefile to
support Control Flow Integrity builds, remove all the function callback
casts.
Co-developed-by: Helge Deller <deller@gmx.de>
Signed-off-by: Oscar Carter <oscar.carter@gmx.com>
Signed-off-by: Helge Deller <deller@gmx.de>
With support for 32-bit pv guests gone pure pv-code no longer needs to
test for highmem. Dropping those tests removes the need for flushing
in some places.
Signed-off-by: Juergen Gross <jgross@suse.com>
Reviewed-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Signed-off-by: Juergen Gross <jgross@suse.com>
With 32-bit pv-guest support removed xen-asm_64.S can be merged with
xen-asm.S
Signed-off-by: Juergen Gross <jgross@suse.com>
Reviewed-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Signed-off-by: Juergen Gross <jgross@suse.com>
Xen is requiring 64-bit machines today and since Xen 4.14 it can be
built without 32-bit PV guest support. There is no need to carry the
burden of 32-bit PV guest support in the kernel any longer, as new
guests can be either HVM or PVH, or they can use a 64 bit kernel.
Remove the 32-bit Xen PV support from the kernel.
Signed-off-by: Juergen Gross <jgross@suse.com>
Reviewed-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Signed-off-by: Juergen Gross <jgross@suse.com>
Pull locking updates from Thomas Gleixner:
"A set of locking fixes and updates:
- Untangle the header spaghetti which causes build failures in
various situations caused by the lockdep additions to seqcount to
validate that the write side critical sections are non-preemptible.
- The seqcount associated lock debug addons which were blocked by the
above fallout.
seqcount writers contrary to seqlock writers must be externally
serialized, which usually happens via locking - except for strict
per CPU seqcounts. As the lock is not part of the seqcount, lockdep
cannot validate that the lock is held.
This new debug mechanism adds the concept of associated locks.
sequence count has now lock type variants and corresponding
initializers which take a pointer to the associated lock used for
writer serialization. If lockdep is enabled the pointer is stored
and write_seqcount_begin() has a lockdep assertion to validate that
the lock is held.
Aside of the type and the initializer no other code changes are
required at the seqcount usage sites. The rest of the seqcount API
is unchanged and determines the type at compile time with the help
of _Generic which is possible now that the minimal GCC version has
been moved up.
Adding this lockdep coverage unearthed a handful of seqcount bugs
which have been addressed already independent of this.
While generally useful this comes with a Trojan Horse twist: On RT
kernels the write side critical section can become preemtible if
the writers are serialized by an associated lock, which leads to
the well known reader preempts writer livelock. RT prevents this by
storing the associated lock pointer independent of lockdep in the
seqcount and changing the reader side to block on the lock when a
reader detects that a writer is in the write side critical section.
- Conversion of seqcount usage sites to associated types and
initializers"
* tag 'locking-urgent-2020-08-10' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (25 commits)
locking/seqlock, headers: Untangle the spaghetti monster
locking, arch/ia64: Reduce <asm/smp.h> header dependencies by moving XTP bits into the new <asm/xtp.h> header
x86/headers: Remove APIC headers from <asm/smp.h>
seqcount: More consistent seqprop names
seqcount: Compress SEQCNT_LOCKNAME_ZERO()
seqlock: Fold seqcount_LOCKNAME_init() definition
seqlock: Fold seqcount_LOCKNAME_t definition
seqlock: s/__SEQ_LOCKDEP/__SEQ_LOCK/g
hrtimer: Use sequence counter with associated raw spinlock
kvm/eventfd: Use sequence counter with associated spinlock
userfaultfd: Use sequence counter with associated spinlock
NFSv4: Use sequence counter with associated spinlock
iocost: Use sequence counter with associated spinlock
raid5: Use sequence counter with associated spinlock
vfs: Use sequence counter with associated spinlock
timekeeping: Use sequence counter with associated raw spinlock
xfrm: policy: Use sequence counters with associated lock
netfilter: nft_set_rbtree: Use sequence counter with associated rwlock
netfilter: conntrack: Use sequence counter with associated spinlock
sched: tasks: Use sequence counter with associated spinlock
...
Based on an analysis of the HyperV firmwares (Gen1 and Gen2) it seems
like the SCONTROL is not being set to the ENABLED state as like we have
thought.
Also from a test done by Vitaly Kuznetsov, running a nested HyperV it
was concluded that the first access to the SCONTROL MSR with a read
resulted with the value of 0x1, aka HV_SYNIC_CONTROL_ENABLE.
It's important to note that this diverges from the value states in the
HyperV TLFS of 0.
Signed-off-by: Jon Doron <arilou@gmail.com>
Message-Id: <20200717125238.1103096-2-arilou@gmail.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
There is a fallthrough comment being forgotten,
GCC complains about it:
arch/mips/kvm/emulate.c: In function kvm_mips_emulate_load:
arch/mips/kvm/emulate.c:1936:21: error: this statement may fall through
1936 | vcpu->mmio_needed = 1; /* unsigned */
| ~~~~~~~~~~~~~~~~~~^~~
arch/mips/kvm/emulate.c:1939:2: note: here
1939 | case lw_op:
Just fix it.
Signed-off-by: Jiaxun Yang <jiaxun.yang@flygoat.com>
Reviewed-by: Huacai Chen <chenhc@lemote.com>
Message-Id: <20200810011749.3211128-1-jiaxun.yang@flygoat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Pull Kbuild updates from Masahiro Yamada:
- run the checker (e.g. sparse) after the compiler
- remove unneeded cc-option tests for old compiler flags
- fix tar-pkg to install dtbs
- introduce ccflags-remove-y and asflags-remove-y syntax
- allow to trace functions in sub-directories of lib/
- introduce hostprogs-always-y and userprogs-always-y syntax
- various Makefile cleanups
* tag 'kbuild-v5.9' of git://git.kernel.org/pub/scm/linux/kernel/git/masahiroy/linux-kbuild:
kbuild: stop filtering out $(GCC_PLUGINS_CFLAGS) from cc-option base
kbuild: include scripts/Makefile.* only when relevant CONFIG is enabled
kbuild: introduce hostprogs-always-y and userprogs-always-y
kbuild: sort hostprogs before passing it to ifneq
kbuild: move host .so build rules to scripts/gcc-plugins/Makefile
kbuild: Replace HTTP links with HTTPS ones
kbuild: trace functions in subdirectories of lib/
kbuild: introduce ccflags-remove-y and asflags-remove-y
kbuild: do not export LDFLAGS_vmlinux
kbuild: always create directories of targets
powerpc/boot: add DTB to 'targets'
kbuild: buildtar: add dtbs support
kbuild: remove cc-option test of -ffreestanding
kbuild: remove cc-option test of -fno-stack-protector
Revert "kbuild: Create directory for target DTB"
kbuild: run the checker after the compiler
