The XIVE interrupt controller is the new interrupt controller
found in POWER9. It supports advanced virtualization capabilities
among other things.
Currently we use a set of firmware calls that simulate the old
"XICS" interrupt controller but this is fairly inefficient.
This adds the framework for using XIVE along with a native
backend which OPAL for configuration. Later, a backend allowing
the use in a KVM or PowerVM guest will also be provided.
This disables some fast path for interrupts in KVM when XIVE is
enabled as these rely on the firmware emulation code which is no
longer available when the XIVE is used natively by Linux.
A latter patch will make KVM also directly exploit the XIVE, thus
recovering the lost performance (and more).
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
[mpe: Fixup pr_xxx("XIVE:"...), don't split pr_xxx() strings,
tweak Kconfig so XIVE_NATIVE selects XIVE and depends on POWERNV,
fix build errors when SMP=n, fold in fixes from Ben:
Don't call cpu_online() on an invalid CPU number
Fix irq target selection returning out of bounds cpu#
Extra sanity checks on cpu numbers
]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Most users of this interface just want to use it with the default
GFP_KERNEL flags, but for cases where DMA memory is allocated it may be
called from a different context.
No functional change yet, just passing through the flag to the
underlying alloc_contig_range function.
Link: http://lkml.kernel.org/r/20170127172328.18574-2-l.stach@pengutronix.de
Signed-off-by: Lucas Stach <l.stach@pengutronix.de>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Acked-by: Michal Hocko <mhocko@suse.com>
Cc: Radim Krcmar <rkrcmar@redhat.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Chris Zankel <chris@zankel.net>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Alexander Graf <agraf@suse.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
This merges in a fix which touches both PPC and KVM code,
which was therefore put into a topic branch in the powerpc
tree.
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
All entry points already read the MSR so they can easily do
the right thing.
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
The difference between kvm_alloc_hpt() and kvmppc_alloc_hpt() is not at
all obvious from the name. In practice kvmppc_alloc_hpt() allocates an HPT
by whatever means, and calls kvm_alloc_hpt() which will attempt to allocate
it with CMA only.
To make this less confusing, rename kvm_alloc_hpt() to kvm_alloc_hpt_cma().
Similarly, kvm_release_hpt() is renamed kvm_free_hpt_cma().
Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
Reviewed-by: Thomas Huth <thuth@redhat.com>
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
If we allow LPCR[AIL] to be set for radix guests, then interrupts from
the guest to the host can be delivered by the hardware with relocation
on, and thus the code path starting at kvmppc_interrupt_hv can be
executed in virtual mode (MMU on) for radix guests (previously it was
only ever executed in real mode).
Most of the code is indifferent to whether the MMU is on or off, but
the calls to OPAL that use the real-mode OPAL entry code need to
be switched to use the virtual-mode code instead. The affected
calls are the calls to the OPAL XICS emulation functions in
kvmppc_read_one_intr() and related functions. We test the MSR[IR]
bit to detect whether we are in real or virtual mode, and call the
opal_rm_* or opal_* function as appropriate.
The other place that depends on the MMU being off is the optimization
where the guest exit code jumps to the external interrupt vector or
hypervisor doorbell interrupt vector, or returns to its caller (which
is __kvmppc_vcore_entry). If the MMU is on and we are returning to
the caller, then we don't need to use an rfid instruction since the
MMU is already on; a simple blr suffices. If there is an external
or hypervisor doorbell interrupt to handle, we branch to the
relocation-on version of the interrupt vector.
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
This moves the prototypes for functions that are only called from
assembler code out of asm/asm-prototypes.h into asm/kvm_ppc.h.
The prototypes were added in commit ebe4535fbe ("KVM: PPC:
Book3S HV: sparse: prototypes for functions called from assembler",
2016-10-10), but given that the functions are KVM functions,
having them in a KVM header will be better for long-term
maintenance.
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
This adds the "again" parameter to the dummy version of
kvmppc_check_passthru(), so that it matches the real version.
This fixes compilation with CONFIG_BOOK3S_64_HV set but
CONFIG_KVM_XICS=n.
This includes asm/smp.h in book3s_hv_builtin.c to fix compilation
with CONFIG_SMP=n. The explicit inclusion is necessary to provide
definitions of hard_smp_processor_id() and get_hard_smp_processor_id()
in UP configs.
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
POWER9 includes a new interrupt controller, called XIVE, which is
quite different from the XICS interrupt controller on POWER7 and
POWER8 machines. KVM-HV accesses the XICS directly in several places
in order to send and clear IPIs and handle interrupts from PCI
devices being passed through to the guest.
In order to make the transition to XIVE easier, OPAL firmware will
include an emulation of XICS on top of XIVE. Access to the emulated
XICS is via OPAL calls. The one complication is that the EOI
(end-of-interrupt) function can now return a value indicating that
another interrupt is pending; in this case, the XIVE will not signal
an interrupt in hardware to the CPU, and software is supposed to
acknowledge the new interrupt without waiting for another interrupt
to be delivered in hardware.
This adapts KVM-HV to use the OPAL calls on machines where there is
no XICS hardware. When there is no XICS, we look for a device-tree
node with "ibm,opal-intc" in its compatible property, which is how
OPAL indicates that it provides XICS emulation.
In order to handle the EOI return value, kvmppc_read_intr() has
become kvmppc_read_one_intr(), with a boolean variable passed by
reference which can be set by the EOI functions to indicate that
another interrupt is pending. The new kvmppc_read_intr() keeps
calling kvmppc_read_one_intr() until there are no more interrupts
to process. The return value from kvmppc_read_intr() is the
largest non-zero value of the returns from kvmppc_read_one_intr().
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
On POWER9, the msgsnd instruction is able to send interrupts to
other cores, as well as other threads on the local core. Since
msgsnd is generally simpler and faster than sending an IPI via the
XICS, we use msgsnd for all IPIs sent by KVM on POWER9.
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
A bunch of KVM functions are only called from assembler.
Give them prototypes in asm-prototypes.h
This reduces sparse warnings.
Signed-off-by: Daniel Axtens <dja@axtens.net>
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
In existing real mode ICP code, when updating the virtual ICP
state, if there is a required action that cannot be completely
handled in real mode, as for instance, a VCPU needs to be woken
up, flags are set in the ICP to indicate the required action.
This is checked when returning from hypercalls to decide whether
the call needs switch back to the host where the action can be
performed in virtual mode. Note that if h_ipi_redirect is enabled,
real mode code will first try to message a free host CPU to
complete this job instead of returning the host to do it ourselves.
Currently, the real mode PCI passthrough interrupt handling code
checks if any of these flags are set and simply returns to the host.
This is not good enough as the trap value (0x500) is treated as an
external interrupt by the host code. It is only when the trap value
is a hypercall that the host code searches for and acts on unfinished
work by calling kvmppc_xics_rm_complete.
This patch introduces a special trap BOOK3S_INTERRUPT_HV_RM_HARD
which is returned by KVM if there is unfinished business to be
completed in host virtual mode after handling a PCI passthrough
interrupt. The host checks for this special interrupt condition
and calls into the kvmppc_xics_rm_complete, which is made an
exported function for this reason.
[paulus@ozlabs.org - moved logic to set r12 to BOOK3S_INTERRUPT_HV_RM_HARD
in book3s_hv_rmhandlers.S into the end of kvmppc_check_wake_reason.]
Signed-off-by: Suresh Warrier <warrier@linux.vnet.ibm.com>
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
Currently, KVM switches back to the host to handle any external
interrupt (when the interrupt is received while running in the
guest). This patch updates real-mode KVM to check if an interrupt
is generated by a passthrough adapter that is owned by this guest.
If so, the real mode KVM will directly inject the corresponding
virtual interrupt to the guest VCPU's ICS and also EOI the interrupt
in hardware. In short, the interrupt is handled entirely in real
mode in the guest context without switching back to the host.
In some rare cases, the interrupt cannot be completely handled in
real mode, for instance, a VCPU that is sleeping needs to be woken
up. In this case, KVM simply switches back to the host with trap
reason set to 0x500. This works, but it is clearly not very efficient.
A following patch will distinguish this case and handle it
correctly in the host. Note that we can use the existing
check_too_hard() routine even though we are not in a hypercall to
determine if there is unfinished business that needs to be
completed in host virtual mode.
The patch assumes that the mapping between hardware interrupt IRQ
and virtual IRQ to be injected to the guest already exists for the
PCI passthrough interrupts that need to be handled in real mode.
If the mapping does not exist, KVM falls back to the default
existing behavior.
The KVM real mode code reads mappings from the mapped array in the
passthrough IRQ map without taking any lock. We carefully order the
loads and stores of the fields in the kvmppc_irq_map data structure
using memory barriers to avoid an inconsistent mapping being seen by
the reader. Thus, although it is possible to miss a map entry, it is
not possible to read a stale value.
[paulus@ozlabs.org - get irq_chip from irq_map rather than pimap,
pulled out powernv eoi change into a separate patch, made
kvmppc_read_intr get the vcpu from the paca rather than being
passed in, rewrote the logic at the end of kvmppc_read_intr to
avoid deep indentation, simplified logic in book3s_hv_rmhandlers.S
since we were always restoring SRR0/1 anyway, get rid of the cached
array (just use the mapped array), removed the kick_all_cpus_sync()
call, clear saved_xirr PACA field when we handle the interrupt in
real mode, fix compilation with CONFIG_KVM_XICS=n.]
Signed-off-by: Suresh Warrier <warrier@linux.vnet.ibm.com>
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
Modify kvmppc_read_intr to make it a C function. Because it is called
from kvmppc_check_wake_reason, any of the assembler code that calls
either kvmppc_read_intr or kvmppc_check_wake_reason now has to assume
that the volatile registers might have been modified.
This also adds in the optimization of clearing saved_xirr in the case
where we completely handle and EOI an IPI. Without this, the next
device interrupt will require two trips through the host interrupt
handling code.
[paulus@ozlabs.org - made kvmppc_check_wake_reason create a stack frame
when it is calling kvmppc_read_intr, which means we can set r12 to
the trap number (0x500) after the call to kvmppc_read_intr, instead
of using r31. Also moved the deliver_guest_interrupt label so as to
restore XER and CTR, plus other minor tweaks.]
Signed-off-by: Suresh Warrier <warrier@linux.vnet.ibm.com>
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
This patch defines the data structures to support the setting up
of host side operations while running in real mode in the guest,
and also the functions to allocate and free it.
The operations are for now limited to virtual XICS operations.
Currently, we have only defined one operation in the data
structure:
- Wake up a VCPU sleeping in the host when it
receives a virtual interrupt
The operations are assigned at the core level because PowerKVM
requires that the host run in SMT off mode. For each core,
we will need to manage its state atomically - where the state
is defined by:
1. Is the core running in the host?
2. Is there a Real Mode (RM) operation pending on the host?
Currently, core state is only managed at the whole-core level
even when the system is in split-core mode. This just limits
the number of free or "available" cores in the host to perform
any host-side operations.
The kvmppc_host_rm_core.rm_data allows any data to be passed by
KVM in real mode to the host core along with the operation to
be performed.
The kvmppc_host_rm_ops structure is allocated the very first time
a guest VM is started. Initial core state is also set - all online
cores are in the host. This structure is never deleted, not even
when there are no active guests. However, it needs to be freed
when the module is unloaded because the kvmppc_host_rm_ops_hv
can contain function pointers to kvm-hv.ko functions for the
different supported host operations.
Signed-off-by: Suresh Warrier <warrier@linux.vnet.ibm.com>
Signed-off-by: Paul Mackerras <paulus@samba.org>
This builds on the ability to run more than one vcore on a physical
core by using the micro-threading (split-core) modes of the POWER8
chip. Previously, only vcores from the same VM could be run together,
and (on POWER8) only if they had just one thread per core. With the
ability to split the core on guest entry and unsplit it on guest exit,
we can run up to 8 vcpu threads from up to 4 different VMs, and we can
run multiple vcores with 2 or 4 vcpus per vcore.
Dynamic micro-threading is only available if the static configuration
of the cores is whole-core mode (unsplit), and only on POWER8.
To manage this, we introduce a new kvm_split_mode struct which is
shared across all of the subcores in the core, with a pointer in the
paca on each thread. In addition we extend the core_info struct to
have information on each subcore. When deciding whether to add a
vcore to the set already on the core, we now have two possibilities:
(a) piggyback the vcore onto an existing subcore, or (b) start a new
subcore.
Currently, when any vcpu needs to exit the guest and switch to host
virtual mode, we interrupt all the threads in all subcores and switch
the core back to whole-core mode. It may be possible in future to
allow some of the subcores to keep executing in the guest while
subcore 0 switches to the host, but that is not implemented in this
patch.
This adds a module parameter called dynamic_mt_modes which controls
which micro-threading (split-core) modes the code will consider, as a
bitmap. In other words, if it is 0, no micro-threading mode is
considered; if it is 2, only 2-way micro-threading is considered; if
it is 4, only 4-way, and if it is 6, both 2-way and 4-way
micro-threading mode will be considered. The default is 6.
With this, we now have secondary threads which are the primary thread
for their subcore and therefore need to do the MMU switch. These
threads will need to be started even if they have no vcpu to run, so
we use the vcore pointer in the PACA rather than the vcpu pointer to
trigger them.
It is now possible for thread 0 to find that an exit has been
requested before it gets to switch the subcore state to the guest. In
that case we haven't added the guest's timebase offset to the
timebase, so we need to be careful not to subtract the offset in the
guest exit path. In fact we just skip the whole path that switches
back to host context, since we haven't switched to the guest context.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
When running a virtual core of a guest that is configured with fewer
threads per core than the physical cores have, the extra physical
threads are currently unused. This makes it possible to use them to
run one or more other virtual cores from the same guest when certain
conditions are met. This applies on POWER7, and on POWER8 to guests
with one thread per virtual core. (It doesn't apply to POWER8 guests
with multiple threads per vcore because they require a 1-1 virtual to
physical thread mapping in order to be able to use msgsndp and the
TIR.)
The idea is that we maintain a list of preempted vcores for each
physical cpu (i.e. each core, since the host runs single-threaded).
Then, when a vcore is about to run, it checks to see if there are
any vcores on the list for its physical cpu that could be
piggybacked onto this vcore's execution. If so, those additional
vcores are put into state VCORE_PIGGYBACK and their runnable VCPU
threads are started as well as the original vcore, which is called
the master vcore.
After the vcores have exited the guest, the extra ones are put back
onto the preempted list if any of their VCPUs are still runnable and
not idle.
This means that vcpu->arch.ptid is no longer necessarily the same as
the physical thread that the vcpu runs on. In order to make it easier
for code that wants to send an IPI to know which CPU to target, we
now store that in a new field in struct vcpu_arch, called thread_cpu.
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
Tested-by: Laurent Vivier <lvivier@redhat.com>
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
This uses msgsnd where possible for signalling other threads within
the same core on POWER8 systems, rather than IPIs through the XICS
interrupt controller. This includes waking secondary threads to run
the guest, the interrupts generated by the virtual XICS, and the
interrupts to bring the other threads out of the guest when exiting.
Aggregated statistics from debugfs across vcpus for a guest with 32
vcpus, 8 threads/vcore, running on a POWER8, show this before the
change:
rm_entry: 3387.6ns (228 - 86600, 1008969 samples)
rm_exit: 4561.5ns (12 - 3477452, 1009402 samples)
rm_intr: 1660.0ns (12 - 553050, 3600051 samples)
and this after the change:
rm_entry: 3060.1ns (212 - 65138, 953873 samples)
rm_exit: 4244.1ns (12 - 9693408, 954331 samples)
rm_intr: 1342.3ns (12 - 1104718, 3405326 samples)
for a test of booting Fedora 20 big-endian to the login prompt.
The time taken for a H_PROD hcall (which is handled in the host
kernel) went down from about 35 microseconds to about 16 microseconds
with this change.
The noinline added to kvmppc_run_core turned out to be necessary for
good performance, at least with gcc 4.9.2 as packaged with Fedora 21
and a little-endian POWER8 host.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
This replaces the assembler code for kvmhv_commence_exit() with C code
in book3s_hv_builtin.c. It also moves the IPI sending code that was
in book3s_hv_rm_xics.c into a new kvmhv_rm_send_ipi() function so it
can be used by kvmhv_commence_exit() as well as icp_rm_set_vcpu_irq().
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
Currently, the entry_exit_count field in the kvmppc_vcore struct
contains two 8-bit counts, one of the threads that have started entering
the guest, and one of the threads that have started exiting the guest.
This changes it to an entry_exit_map field which contains two bitmaps
of 8 bits each. The advantage of doing this is that it gives us a
bitmap of which threads need to be signalled when exiting the guest.
That means that we no longer need to use the trick of setting the
HDEC to 0 to pull the other threads out of the guest, which led in
some cases to a spurious HDEC interrupt on the next guest entry.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
Some PowerNV systems include a hardware random-number generator.
This HWRNG is present on POWER7+ and POWER8 chips and is capable of
generating one 64-bit random number every microsecond. The random
numbers are produced by sampling a set of 64 unstable high-frequency
oscillators and are almost completely entropic.
PAPR defines an H_RANDOM hypercall which guests can use to obtain one
64-bit random sample from the HWRNG. This adds a real-mode
implementation of the H_RANDOM hypercall. This hypercall was
implemented in real mode because the latency of reading the HWRNG is
generally small compared to the latency of a guest exit and entry for
all the threads in the same virtual core.
Userspace can detect the presence of the HWRNG and the H_RANDOM
implementation by querying the KVM_CAP_PPC_HWRNG capability. The
H_RANDOM hypercall implementation will only be invoked when the guest
does an H_RANDOM hypercall if userspace first enables the in-kernel
H_RANDOM implementation using the KVM_CAP_PPC_ENABLE_HCALL capability.
Signed-off-by: Michael Ellerman <michael@ellerman.id.au>
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
- spring cleaning: removed support for IA64, and for hardware-assisted
virtualization on the PPC970
- ARM, PPC, s390 all had only small fixes
For x86:
- small performance improvements (though only on weird guests)
- usual round of hardware-compliancy fixes from Nadav
- APICv fixes
- XSAVES support for hosts and guests. XSAVES hosts were broken because
the (non-KVM) XSAVES patches inadvertently changed the KVM userspace
ABI whenever XSAVES was enabled; hence, this part is going to stable.
Guest support is just a matter of exposing the feature and CPUID leaves
support.
Right now KVM is broken for PPC BookE in your tree (doesn't compile).
I'll reply to the pull request with a patch, please apply it either
before the pull request or in the merge commit, in order to preserve
bisectability somewhat.
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v2.0.22 (GNU/Linux)
iQEcBAABAgAGBQJUkpg+AAoJEL/70l94x66DUmoH/jzXYkptSW9NGgm79KqxGJlD
lzLnLBkitVvx++Mz5YBhdJEhKKLUlCtifFT1zPJQ/pthQhIRSaaAwZyNGgUs5w5x
yMGKHiPQFyZRbmQtZhCInW0BftJoYHHciO3nUfHCZnp34My9MP2D55W7/z+fYFfQ
DuqBSE9ThyZJtZ4zh8NRA9fCOeuqwVYRyoBs820Wbsh4cpIBoIK63Dg7k+CLE+ZV
MZa/mRL6bAfsn9W5bnOUAgHJ3SPznnWbO3/g0aV+roL/5pffblprJx9lKNR08xUM
6hDFLop2gDehDJesDkY/o8Ckp1hEouvfsVpSShry4vcgtn0hgh2O5/6Orbmj6vE=
=Zwq1
-----END PGP SIGNATURE-----
Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm
Pull KVM update from Paolo Bonzini:
"3.19 changes for KVM:
- spring cleaning: removed support for IA64, and for hardware-
assisted virtualization on the PPC970
- ARM, PPC, s390 all had only small fixes
For x86:
- small performance improvements (though only on weird guests)
- usual round of hardware-compliancy fixes from Nadav
- APICv fixes
- XSAVES support for hosts and guests. XSAVES hosts were broken
because the (non-KVM) XSAVES patches inadvertently changed the KVM
userspace ABI whenever XSAVES was enabled; hence, this part is
going to stable. Guest support is just a matter of exposing the
feature and CPUID leaves support"
* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (179 commits)
KVM: move APIC types to arch/x86/
KVM: PPC: Book3S: Enable in-kernel XICS emulation by default
KVM: PPC: Book3S HV: Improve H_CONFER implementation
KVM: PPC: Book3S HV: Fix endianness of instruction obtained from HEIR register
KVM: PPC: Book3S HV: Remove code for PPC970 processors
KVM: PPC: Book3S HV: Tracepoints for KVM HV guest interactions
KVM: PPC: Book3S HV: Simplify locking around stolen time calculations
arch: powerpc: kvm: book3s_paired_singles.c: Remove unused function
arch: powerpc: kvm: book3s_pr.c: Remove unused function
arch: powerpc: kvm: book3s.c: Remove some unused functions
arch: powerpc: kvm: book3s_32_mmu.c: Remove unused function
KVM: PPC: Book3S HV: Check wait conditions before sleeping in kvmppc_vcore_blocked
KVM: PPC: Book3S HV: ptes are big endian
KVM: PPC: Book3S HV: Fix inaccuracies in ICP emulation for H_IPI
KVM: PPC: Book3S HV: Fix KSM memory corruption
KVM: PPC: Book3S HV: Fix an issue where guest is paused on receiving HMI
KVM: PPC: Book3S HV: Fix computation of tlbie operand
KVM: PPC: Book3S HV: Add missing HPTE unlock
KVM: PPC: BookE: Improve irq inject tracepoint
arm/arm64: KVM: Require in-kernel vgic for the arch timers
...
Currently the H_CONFER hcall is implemented in kernel virtual mode,
meaning that whenever a guest thread does an H_CONFER, all the threads
in that virtual core have to exit the guest. This is bad for
performance because it interrupts the other threads even if they
are doing useful work.
The H_CONFER hcall is called by a guest VCPU when it is spinning on a
spinlock and it detects that the spinlock is held by a guest VCPU that
is currently not running on a physical CPU. The idea is to give this
VCPU's time slice to the holder VCPU so that it can make progress
towards releasing the lock.
To avoid having the other threads exit the guest unnecessarily,
we add a real-mode implementation of H_CONFER that checks whether
the other threads are doing anything. If all the other threads
are idle (i.e. in H_CEDE) or trying to confer (i.e. in H_CONFER),
it returns H_TOO_HARD which causes a guest exit and allows the
H_CONFER to be handled in virtual mode.
Otherwise it spins for a short time (up to 10 microseconds) to give
other threads the chance to observe that this thread is trying to
confer. The spin loop also terminates when any thread exits the guest
or when all other threads are idle or trying to confer. If the
timeout is reached, the H_CONFER returns H_SUCCESS. In this case the
guest VCPU will recheck the spinlock word and most likely call
H_CONFER again.
This also improves the implementation of the H_CONFER virtual mode
handler. If the VCPU is part of a virtual core (vcore) which is
runnable, there will be a 'runner' VCPU which has taken responsibility
for running the vcore. In this case we yield to the runner VCPU
rather than the target VCPU.
We also introduce a check on the target VCPU's yield count: if it
differs from the yield count passed to H_CONFER, the target VCPU
has run since H_CONFER was called and may have already released
the lock. This check is required by PAPR.
Signed-off-by: Sam Bobroff <sam.bobroff@au1.ibm.com>
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
This removes the code that was added to enable HV KVM to work
on PPC970 processors. The PPC970 is an old CPU that doesn't
support virtualizing guest memory. Removing PPC970 support also
lets us remove the code for allocating and managing contiguous
real-mode areas, the code for the !kvm->arch.using_mmu_notifiers
case, the code for pinning pages of guest memory when first
accessed and keeping track of which pages have been pinned, and
the code for handling H_ENTER hypercalls in virtual mode.
Book3S HV KVM is now supported only on POWER7 and POWER8 processors.
The KVM_CAP_PPC_RMA capability now always returns 0.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
Lots of places included bootmem.h even when not using bootmem.
Signed-off-by: Anton Blanchard <anton@samba.org>
Tested-by: Emil Medve <Emilian.Medve@Freescale.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Now bootmem is gone from powerpc we can remove comments mentioning it.
Signed-off-by: Anton Blanchard <anton@samba.org>
Tested-by: Emil Medve <Emilian.Medve@Freescale.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
We use cma reserved area for creating guest hash page table.
Don't do the reservation in non-hypervisor mode. This avoids unnecessary
CMA reservation when booting with limited memory configs like
fadump and kdump.
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Reviewed-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
fc95ca7284 claims that there is no
functional change but this is not true as it calls get_order() (which
takes bytes) where it should have called order_base_2() and the kernel
stops on VM_BUG_ON().
This replaces get_order() with order_base_2() (round-up version of ilog2).
Suggested-by: Paul Mackerras <paulus@samba.org>
Cc: Alexander Graf <agraf@suse.de>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Reviewed-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
they had small conflicts (respectively within KVM documentation,
and with 3.16-rc changes). Since they were all within the subsystem,
I took care of them.
Stephen Rothwell reported some snags in PPC builds, but they are all
fixed now; the latest linux-next report was clean.
New features for ARM include:
- KVM VGIC v2 emulation on GICv3 hardware
- Big-Endian support for arm/arm64 (guest and host)
- Debug Architecture support for arm64 (arm32 is on Christoffer's todo list)
And for PPC:
- Book3S: Good number of LE host fixes, enable HV on LE
- Book3S HV: Add in-guest debug support
This release drops support for KVM on the PPC440. As a result, the
PPC merge removes more lines than it adds. :)
I also included an x86 change, since Davidlohr tied it to an independent
bug report and the reporter quickly provided a Tested-by; there was no
reason to wait for -rc2.
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v2.0.22 (GNU/Linux)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=hyQP
-----END PGP SIGNATURE-----
Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm
Pull second round of KVM changes from Paolo Bonzini:
"Here are the PPC and ARM changes for KVM, which I separated because
they had small conflicts (respectively within KVM documentation, and
with 3.16-rc changes). Since they were all within the subsystem, I
took care of them.
Stephen Rothwell reported some snags in PPC builds, but they are all
fixed now; the latest linux-next report was clean.
New features for ARM include:
- KVM VGIC v2 emulation on GICv3 hardware
- Big-Endian support for arm/arm64 (guest and host)
- Debug Architecture support for arm64 (arm32 is on Christoffer's todo list)
And for PPC:
- Book3S: Good number of LE host fixes, enable HV on LE
- Book3S HV: Add in-guest debug support
This release drops support for KVM on the PPC440. As a result, the
PPC merge removes more lines than it adds. :)
I also included an x86 change, since Davidlohr tied it to an
independent bug report and the reporter quickly provided a Tested-by;
there was no reason to wait for -rc2"
* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (122 commits)
KVM: Move more code under CONFIG_HAVE_KVM_IRQFD
KVM: nVMX: fix "acknowledge interrupt on exit" when APICv is in use
KVM: nVMX: Fix nested vmexit ack intr before load vmcs01
KVM: PPC: Enable IRQFD support for the XICS interrupt controller
KVM: Give IRQFD its own separate enabling Kconfig option
KVM: Move irq notifier implementation into eventfd.c
KVM: Move all accesses to kvm::irq_routing into irqchip.c
KVM: irqchip: Provide and use accessors for irq routing table
KVM: Don't keep reference to irq routing table in irqfd struct
KVM: PPC: drop duplicate tracepoint
arm64: KVM: fix 64bit CP15 VM access for 32bit guests
KVM: arm64: GICv3: mandate page-aligned GICV region
arm64: KVM: GICv3: move system register access to msr_s/mrs_s
KVM: PPC: PR: Handle FSCR feature deselects
KVM: PPC: HV: Remove generic instruction emulation
KVM: PPC: BOOKEHV: rename e500hv_spr to bookehv_spr
KVM: PPC: Remove DCR handling
KVM: PPC: Expose helper functions for data/inst faults
KVM: PPC: Separate loadstore emulation from priv emulation
KVM: PPC: Handle magic page in kvmppc_ld/st
...
Conventionally, we put output param to the end of param list and put the
'base' ahead of 'size', but cma_declare_contiguous() doesn't look like
that, so change it.
Additionally, move down cma_areas reference code to the position where
it is really needed.
Signed-off-by: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Acked-by: Michal Nazarewicz <mina86@mina86.com>
Reviewed-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Cc: Alexander Graf <agraf@suse.de>
Cc: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Cc: Gleb Natapov <gleb@kernel.org>
Acked-by: Marek Szyprowski <m.szyprowski@samsung.com>
Tested-by: Marek Szyprowski <m.szyprowski@samsung.com>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Zhang Yanfei <zhangyanfei@cn.fujitsu.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Paul Mackerras <paulus@samba.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Now, we have general CMA reserved area management framework, so use it
for future maintainabilty. There is no functional change.
Signed-off-by: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Acked-by: Michal Nazarewicz <mina86@mina86.com>
Acked-by: Paolo Bonzini <pbonzini@redhat.com>
Tested-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Cc: Alexander Graf <agraf@suse.de>
Cc: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Cc: Gleb Natapov <gleb@kernel.org>
Acked-by: Marek Szyprowski <m.szyprowski@samsung.com>
Tested-by: Marek Szyprowski <m.szyprowski@samsung.com>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Zhang Yanfei <zhangyanfei@cn.fujitsu.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Paul Mackerras <paulus@samba.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
This adds code to check that when the KVM_CAP_PPC_ENABLE_HCALL
capability is used to enable or disable in-kernel handling of an
hcall, that the hcall is actually implemented by the kernel.
If not an EINVAL error is returned.
This also checks the default-enabled list of hcalls and prints a
warning if any hcall there is not actually implemented.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
As part of the support for split core on POWER8, we want to be able to
block splitting of the core while KVM VMs are active.
The logic to do that would be exactly the same as the code we currently
have for inhibiting onlining of secondaries.
Instead of adding an identical mechanism to block split core, rework the
secondary inhibit code to be a "HV KVM is active" check. We can then use
that in both the cpu hotplug code and the upcoming split core code.
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Signed-off-by: Michael Neuling <mikey@neuling.org>
Acked-by: Alexander Graf <agraf@suse.de>
Acked-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Older version of power architecture use Real Mode Offset register and Real Mode Limit
Selector for mapping guest Real Mode Area. The guest RMA should be physically
contigous since we use the range when address translation is not enabled.
This patch switch RMA allocation code to use contigous memory allocator. The patch
also remove the the linear allocator which not used any more
Acked-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Signed-off-by: Alexander Graf <agraf@suse.de>
Powerpc architecture uses a hash based page table mechanism for mapping virtual
addresses to physical address. The architecture require this hash page table to
be physically contiguous. With KVM on Powerpc currently we use early reservation
mechanism for allocating guest hash page table. This implies that we need to
reserve a big memory region to ensure we can create large number of guest
simultaneously with KVM on Power. Another disadvantage is that the reserved memory
is not available to rest of the subsystems and and that implies we limit the total
available memory in the host.
This patch series switch the guest hash page table allocation to use
contiguous memory allocator.
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Acked-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
This is printed once for every RMA or HPT region that get
preallocated. If one preallocates hundreds of such regions
(in order to run hundreds of KVM guests), that gets rather
painful, so make it a bit quieter.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
This adds a new ioctl to enable userspace to control the size of the guest
hashed page table (HPT) and to clear it out when resetting the guest.
The KVM_PPC_ALLOCATE_HTAB ioctl is a VM ioctl and takes as its parameter
a pointer to a u32 containing the desired order of the HPT (log base 2
of the size in bytes), which is updated on successful return to the
actual order of the HPT which was allocated.
There must be no vcpus running at the time of this ioctl. To enforce
this, we now keep a count of the number of vcpus running in
kvm->arch.vcpus_running.
If the ioctl is called when a HPT has already been allocated, we don't
reallocate the HPT but just clear it out. We first clear the
kvm->arch.rma_setup_done flag, which has two effects: (a) since we hold
the kvm->lock mutex, it will prevent any vcpus from starting to run until
we're done, and (b) it means that the first vcpu to run after we're done
will re-establish the VRMA if necessary.
If userspace doesn't call this ioctl before running the first vcpu, the
kernel will allocate a default-sized HPT at that point. We do it then
rather than when creating the VM, as the code did previously, so that
userspace has a chance to do the ioctl if it wants.
When allocating the HPT, we can allocate either from the kernel page
allocator, or from the preallocated pool. If userspace is asking for
a different size from the preallocated HPTs, we first try to allocate
using the kernel page allocator. Then we try to allocate from the
preallocated pool, and then if that fails, we try allocating decreasing
sizes from the kernel page allocator, down to the minimum size allowed
(256kB). Note that the kernel page allocator limits allocations to
1 << CONFIG_FORCE_MAX_ZONEORDER pages, which by default corresponds to
16MB (on 64-bit powerpc, at least).
Signed-off-by: Paul Mackerras <paulus@samba.org>
[agraf: fix module compilation]
Signed-off-by: Alexander Graf <agraf@suse.de>
In kvm_alloc_linear we were using and deferencing ri after the
list_for_each_entry had come to the end of the list. In that
situation, ri is not really defined and probably points to the
list head. This will happen every time if the free_linears list
is empty, for instance. This led to a NULL pointer dereference
crash in memset on POWER7 while trying to allocate an HPT in the
case where no HPTs were preallocated.
This fixes it by using a separate variable for the return value
from the loop iterator.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Paul Mackerras <paulus@samba.org>
We're currently allocating 16MB of linear memory on demand when creating
a guest. That does work some times, but finding 16MB of linear memory
available in the system at runtime is definitely not a given.
So let's add another command line option similar to the RMA preallocator,
that we can use to keep a pool of page tables around. Now, when a guest
gets created it has a pretty low chance of receiving an OOM.
Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Avi Kivity <avi@redhat.com>
RMAs and HPT preallocated spaces should be zeroed, so we don't accidently
leak information from previous VM executions.
Signed-off-by: Alexander Graf <agraf@suse.de>
Acked-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Avi Kivity <avi@redhat.com>
We have code to allocate big chunks of linear memory on bootup for later use.
This code is currently used for RMA allocation, but can be useful beyond that
extent.
Make it generic so we can reuse it for other stuff later.
Signed-off-by: Alexander Graf <agraf@suse.de>
Acked-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Avi Kivity <avi@redhat.com>
kvm_rma_init() is only called at boot-time, by setup_arch, which is also __init.
Signed-off-by: Nishanth Aravamudan <nacc@us.ibm.com>
Signed-off-by: Alexander Graf <agraf@suse.de>
With module.h being implicitly everywhere via device.h, the absence
of explicitly including something for EXPORT_SYMBOL went unnoticed.
Since we are heading to fix things up and clean module.h from the
device.h file, we need to explicitly include these files now.
Signed-off-by: Paul Gortmaker <paul.gortmaker@windriver.com>
This adds support for running KVM guests in supervisor mode on those
PPC970 processors that have a usable hypervisor mode. Unfortunately,
Apple G5 machines have supervisor mode disabled (MSR[HV] is forced to
1), but the YDL PowerStation does have a usable hypervisor mode.
There are several differences between the PPC970 and POWER7 in how
guests are managed. These differences are accommodated using the
CPU_FTR_ARCH_201 (PPC970) and CPU_FTR_ARCH_206 (POWER7) CPU feature
bits. Notably, on PPC970:
* The LPCR, LPID or RMOR registers don't exist, and the functions of
those registers are provided by bits in HID4 and one bit in HID0.
* External interrupts can be directed to the hypervisor, but unlike
POWER7 they are masked by MSR[EE] in non-hypervisor modes and use
SRR0/1 not HSRR0/1.
* There is no virtual RMA (VRMA) mode; the guest must use an RMO
(real mode offset) area.
* The TLB entries are not tagged with the LPID, so it is necessary to
flush the whole TLB on partition switch. Furthermore, when switching
partitions we have to ensure that no other CPU is executing the tlbie
or tlbsync instructions in either the old or the new partition,
otherwise undefined behaviour can occur.
* The PMU has 8 counters (PMC registers) rather than 6.
* The DSCR, PURR, SPURR, AMR, AMOR, UAMOR registers don't exist.
* The SLB has 64 entries rather than 32.
* There is no mediated external interrupt facility, so if we switch to
a guest that has a virtual external interrupt pending but the guest
has MSR[EE] = 0, we have to arrange to have an interrupt pending for
it so that we can get control back once it re-enables interrupts. We
do that by sending ourselves an IPI with smp_send_reschedule after
hard-disabling interrupts.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
This replaces the single CPU_FTR_HVMODE_206 bit with two bits, one to
indicate that we have a usable hypervisor mode, and another to indicate
that the processor conforms to PowerISA version 2.06. We also add
another bit to indicate that the processor conforms to ISA version 2.01
and set that for PPC970 and derivatives.
Some PPC970 chips (specifically those in Apple machines) have a
hypervisor mode in that MSR[HV] is always 1, but the hypervisor mode
is not useful in the sense that there is no way to run any code in
supervisor mode (HV=0 PR=0). On these processors, the LPES0 and LPES1
bits in HID4 are always 0, and we use that as a way of detecting that
hypervisor mode is not useful.
Where we have a feature section in assembly code around code that
only applies on POWER7 in hypervisor mode, we use a construct like
END_FTR_SECTION_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206)
The definition of END_FTR_SECTION_IFSET is such that the code will
be enabled (not overwritten with nops) only if all bits in the
provided mask are set.
Note that the CPU feature check in __tlbie() only needs to check the
ARCH_206 bit, not the HVMODE bit, because __tlbie() can only get called
if we are running bare-metal, i.e. in hypervisor mode.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
This adds infrastructure which will be needed to allow book3s_hv KVM to
run on older POWER processors, including PPC970, which don't support
the Virtual Real Mode Area (VRMA) facility, but only the Real Mode
Offset (RMO) facility. These processors require a physically
contiguous, aligned area of memory for each guest. When the guest does
an access in real mode (MMU off), the address is compared against a
limit value, and if it is lower, the address is ORed with an offset
value (from the Real Mode Offset Register (RMOR)) and the result becomes
the real address for the access. The size of the RMA has to be one of
a set of supported values, which usually includes 64MB, 128MB, 256MB
and some larger powers of 2.
Since we are unlikely to be able to allocate 64MB or more of physically
contiguous memory after the kernel has been running for a while, we
allocate a pool of RMAs at boot time using the bootmem allocator. The
size and number of the RMAs can be set using the kvm_rma_size=xx and
kvm_rma_count=xx kernel command line options.
KVM exports a new capability, KVM_CAP_PPC_RMA, to signal the availability
of the pool of preallocated RMAs. The capability value is 1 if the
processor can use an RMA but doesn't require one (because it supports
the VRMA facility), or 2 if the processor requires an RMA for each guest.
This adds a new ioctl, KVM_ALLOCATE_RMA, which allocates an RMA from the
pool and returns a file descriptor which can be used to map the RMA. It
also returns the size of the RMA in the argument structure.
Having an RMA means we will get multiple KMV_SET_USER_MEMORY_REGION
ioctl calls from userspace. To cope with this, we now preallocate the
kvm->arch.ram_pginfo array when the VM is created with a size sufficient
for up to 64GB of guest memory. Subsequently we will get rid of this
array and use memory associated with each memslot instead.
This moves most of the code that translates the user addresses into
host pfns (page frame numbers) out of kvmppc_prepare_vrma up one level
to kvmppc_core_prepare_memory_region. Also, instead of having to look
up the VMA for each page in order to check the page size, we now check
that the pages we get are compound pages of 16MB. However, if we are
adding memory that is mapped to an RMA, we don't bother with calling
get_user_pages_fast and instead just offset from the base pfn for the
RMA.
Typically the RMA gets added after vcpus are created, which makes it
inconvenient to have the LPCR (logical partition control register) value
in the vcpu->arch struct, since the LPCR controls whether the processor
uses RMA or VRMA for the guest. This moves the LPCR value into the
kvm->arch struct and arranges for the MER (mediated external request)
bit, which is the only bit that varies between vcpus, to be set in
assembly code when going into the guest if there is a pending external
interrupt request.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
Benjamin Herrenschmidt