This improves I/O performance for guests using the PAPR
paravirtualization interface by making the H_PUT_TCE hcall faster, by
implementing it in real mode. H_PUT_TCE is used for updating virtual
IOMMU tables, and is used both for virtual I/O and for real I/O in the
PAPR interface.
Since this moves the IOMMU tables into the kernel, we define a new
KVM_CREATE_SPAPR_TCE ioctl to allow qemu to create the tables. The
ioctl returns a file descriptor which can be used to mmap the newly
created table. The qemu driver models use them in the same way as
userspace managed tables, but they can be updated directly by the
guest with a real-mode H_PUT_TCE implementation, reducing the number
of host/guest context switches during guest IO.
There are certain circumstances where it is useful for userland qemu
to write to the TCE table even if the kernel H_PUT_TCE path is used
most of the time. Specifically, allowing this will avoid awkwardness
when we need to reset the table. More importantly, we will in the
future need to write the table in order to restore its state after a
checkpoint resume or migration.
Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
This adds the infrastructure for handling PAPR hcalls in the kernel,
either early in the guest exit path while we are still in real mode,
or later once the MMU has been turned back on and we are in the full
kernel context. The advantage of handling hcalls in real mode if
possible is that we avoid two partition switches -- and this will
become more important when we support SMT4 guests, since a partition
switch means we have to pull all of the threads in the core out of
the guest. The disadvantage is that we can only access the kernel
linear mapping, not anything vmalloced or ioremapped, since the MMU
is off.
This also adds code to handle the following hcalls in real mode:
H_ENTER Add an HPTE to the hashed page table
H_REMOVE Remove an HPTE from the hashed page table
H_READ Read HPTEs from the hashed page table
H_PROTECT Change the protection bits in an HPTE
H_BULK_REMOVE Remove up to 4 HPTEs from the hashed page table
H_SET_DABR Set the data address breakpoint register
Plus code to handle the following hcalls in the kernel:
H_CEDE Idle the vcpu until an interrupt or H_PROD hcall arrives
H_PROD Wake up a ceded vcpu
H_REGISTER_VPA Register a virtual processor area (VPA)
The code that runs in real mode has to be in the base kernel, not in
the module, if KVM is compiled as a module. The real-mode code can
only access the kernel linear mapping, not vmalloc or ioremap space.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
This adds support for KVM running on 64-bit Book 3S processors,
specifically POWER7, in hypervisor mode. Using hypervisor mode means
that the guest can use the processor's supervisor mode. That means
that the guest can execute privileged instructions and access privileged
registers itself without trapping to the host. This gives excellent
performance, but does mean that KVM cannot emulate a processor
architecture other than the one that the hardware implements.
This code assumes that the guest is running paravirtualized using the
PAPR (Power Architecture Platform Requirements) interface, which is the
interface that IBM's PowerVM hypervisor uses. That means that existing
Linux distributions that run on IBM pSeries machines will also run
under KVM without modification. In order to communicate the PAPR
hypercalls to qemu, this adds a new KVM_EXIT_PAPR_HCALL exit code
to include/linux/kvm.h.
Currently the choice between book3s_hv support and book3s_pr support
(i.e. the existing code, which runs the guest in user mode) has to be
made at kernel configuration time, so a given kernel binary can only
do one or the other.
This new book3s_hv code doesn't support MMIO emulation at present.
Since we are running paravirtualized guests, this isn't a serious
restriction.
With the guest running in supervisor mode, most exceptions go straight
to the guest. We will never get data or instruction storage or segment
interrupts, alignment interrupts, decrementer interrupts, program
interrupts, single-step interrupts, etc., coming to the hypervisor from
the guest. Therefore this introduces a new KVMTEST_NONHV macro for the
exception entry path so that we don't have to do the KVM test on entry
to those exception handlers.
We do however get hypervisor decrementer, hypervisor data storage,
hypervisor instruction storage, and hypervisor emulation assist
interrupts, so we have to handle those.
In hypervisor mode, real-mode accesses can access all of RAM, not just
a limited amount. Therefore we put all the guest state in the vcpu.arch
and use the shadow_vcpu in the PACA only for temporary scratch space.
We allocate the vcpu with kzalloc rather than vzalloc, and we don't use
anything in the kvmppc_vcpu_book3s struct, so we don't allocate it.
We don't have a shared page with the guest, but we still need a
kvm_vcpu_arch_shared struct to store the values of various registers,
so we include one in the vcpu_arch struct.
The POWER7 processor has a restriction that all threads in a core have
to be in the same partition. MMU-on kernel code counts as a partition
(partition 0), so we have to do a partition switch on every entry to and
exit from the guest. At present we require the host and guest to run
in single-thread mode because of this hardware restriction.
This code allocates a hashed page table for the guest and initializes
it with HPTEs for the guest's Virtual Real Memory Area (VRMA). We
require that the guest memory is allocated using 16MB huge pages, in
order to simplify the low-level memory management. This also means that
we can get away without tracking paging activity in the host for now,
since huge pages can't be paged or swapped.
This also adds a few new exports needed by the book3s_hv code.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
Instead of doing the kvm_guest_enter/exit() and local_irq_dis/enable()
calls in powerpc.c, this moves them down into the subarch-specific
book3s_pr.c and booke.c. This eliminates an extra local_irq_enable()
call in book3s_pr.c, and will be needed for when we do SMT4 guest
support in the book3s hypervisor mode code.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
This arranges for the top-level arch/powerpc/kvm/powerpc.c file to
pass down some of the calls it gets to the lower-level subarchitecture
specific code. The lower-level implementations (in booke.c and book3s.c)
are no-ops. The coming book3s_hv.c will need this.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
This is a shared page used for paravirtualization. It is always present
in the guest kernel's effective address space at the address indicated
by the hypercall that enables it.
The physical address specified by the hypercall is not used, as
e500 does not have real mode.
Signed-off-by: Scott Wood <scottwood@freescale.com>
Signed-off-by: Alexander Graf <agraf@suse.de>
To communicate with KVM directly we need to plumb some sort of interface
between the guest and KVM. Usually those interfaces use hypercalls.
This hypercall implementation is described in the last patch of the series
in a special documentation file. Please read that for further information.
This patch implements stubs to handle KVM PPC hypercalls on the host and
guest side alike.
Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Avi Kivity <avi@redhat.com>
The host shadow mmu code needs to get initialized. It needs to fetch a
segment it can use to put shadow PTEs into.
That initialization code was in generic code, which is icky. Let's move
it over to the respective MMU file.
Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Avi Kivity <avi@redhat.com>
We already have some inline fuctions we use to access vcpu or svcpu structs,
depending on whether we're on booke or book3s. Since we just put a few more
registers into the svcpu, we also need to make sure the respective callbacks
are available and get used.
So this patch moves direct use of the now in the svcpu struct fields to
inline function calls. While at it, it also moves the definition of those
inline function calls to respective header files for booke and book3s,
greatly improving readability.
Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Avi Kivity <avi@redhat.com>
Userspace can tell us that it wants to trigger an interrupt. But
so far it can't tell us that it wants to stop triggering one.
So let's interpret the parameter to the ioctl that we have anyways
to tell us if we want to raise or lower the interrupt line.
Signed-off-by: Alexander Graf <agraf@suse.de>
v2 -> v3:
- Add CAP for unset irq
Signed-off-by: Avi Kivity <avi@redhat.com>
The PowerPC specification always lists bits from MSB to LSB. That is
really confusing when you're trying to write C code, because it fits
in pretty badly with the normal (1 << xx) schemes.
So I came up with some nice wrappers that allow to get and set fields
in a u64 with bit numbers exactly as given in the spec. That makes the
code in KVM and the spec easier comparable.
Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Avi Kivity <avi@redhat.com>
Emulation of an instruction can have different outcomes. It can succeed,
fail, require MMIO, do funky BookE stuff - or it can just realize something's
odd and will be fixed the next time around.
Exactly that is what EMULATE_AGAIN means. Using that flag we can now tell
the caller that nothing happened, but we still want to go back to the
guest and see what happens next time we come around.
Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Avi Kivity <avi@redhat.com>
The guest I was trying to get to run uses the LHA and LHAU instructions.
Those instructions basically do a load, but also sign extend the result.
Since we need to fill our registers by hand when doing MMIO, we also need
to sign extend manually.
This patch implements sign extended MMIO and the LHA(U) instructions.
Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Avi Kivity <avi@redhat.com>
Right now MMIO access can only happen for GPRs and is at most 32 bit wide.
That's actually enough for almost all types of hardware out there.
Unfortunately, the guest I was using used FPU writes to MMIO regions, so
it ended up writing 64 bit MMIOs using FPRs and QPRs.
So let's add code to handle those odd cases too.
Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Avi Kivity <avi@redhat.com>
Commit 7d01b4c3ed2bb33ceaf2d270cb4831a67a76b51b introduced PACA backed vcpu
values. With this patch, when a userspace app was setting GPRs before it was
actually first loaded, the set values get discarded.
This is because vcpu_load loads them from the vcpu backing store that we use
whenever we're not owning the PACA.
That behavior is not really a major problem, because we don't need it for
qemu. Other users (like kvmctl) do have problems with it though, so let's
better do it right.
Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Avi Kivity <avi@redhat.com>
Book3S needs some flags in SRR1 to get to know details about an interrupt.
One such example is the trap instruction. It tells the guest kernel that
a program interrupt is due to a trap using a bit in SRR1.
This patch implements above behavior, making WARN_ON behave like WARN_ON.
Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Avi Kivity <avi@redhat.com>
We're being horribly racy right now. All the entry and exit code hijacks
random fields from the PACA that could easily be used by different code in
case we get interrupted, for example by a #MC or even page fault.
After discussing this with Ben, we figured it's best to reserve some more
space in the PACA and just shove off some vcpu state to there.
That way we can drastically improve the readability of the code, make it
less racy and less complex.
Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Avi Kivity <avi@redhat.com>
We now have helpers for the GPRs, so let's also add some for CR and XER.
Having them in the PACA simplifies code a lot, as we don't need to care
about where to store CC or not to overflow any integers.
Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Avi Kivity <avi@redhat.com>
All code in PPC KVM currently accesses gprs in the vcpu struct directly.
While there's nothing wrong with that wrt the current way gprs are stored
and loaded, it doesn't suffice for the PACA acceleration that will follow
in this patchset.
So let's just create little wrapper inline functions that we call whenever
a GPR needs to be read from or written to. The compiled code shouldn't really
change at all for now.
Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Avi Kivity <avi@redhat.com>
We treated the DEC interrupt like an edge based one. This is not true for
Book3s. The DEC keeps firing until mtdec is issued again and thus clears
the interrupt line.
So let's implement this logic in KVM too. This patch moves the line clearing
from the firing of the interrupt to the mtdec emulation.
This makes PPC64 guests work without AGGRESSIVE_DEC defined.
Signed-off-by: Alexander Graf <agraf@suse.de>
Acked-by: Acked-by: Hollis Blanchard <hollis@penguinppc.org>
Signed-off-by: Avi Kivity <avi@redhat.com>
This is the of entry / exit code. In order to switch between host and guest
context, we need to switch register state and call the exit code handler on
exit.
This assembly file does exactly that. To finally enter the guest it calls
into book3s_64_slb.S. On exit it gets jumped at from book3s_64_slb.S too.
Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
After the rewrite of KVM's debug support, this code doesn't even build any
more.
Signed-off-by: Hollis Blanchard <hollisb@us.ibm.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
When itlb or dtlb miss happens, E500 needs to update some mmu registers.
So that the auto-load mechanism can work on E500 when write a tlb entry.
Signed-off-by: Liu Yu <yu.liu@freescale.com>
Signed-off-by: Hollis Blanchard <hollisb@us.ibm.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
Passing just the TLB index will ease an e500 implementation.
Signed-off-by: Hollis Blanchard <hollisb@us.ibm.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
Formerly, we used to maintain a per-vcpu shadow TLB and on every entry to the
guest would load this array into the hardware TLB. This consumed 1280 bytes of
memory (64 entries of 16 bytes plus a struct page pointer each), and also
required some assembly to loop over the array on every entry.
Instead of saving a copy in memory, we can just store shadow mappings directly
into the hardware TLB, accepting that the host kernel will clobber these as
part of the normal 440 TLB round robin. When we do that we need less than half
the memory, and we have decreased the exit handling time for all guest exits,
at the cost of increased number of TLB misses because the host overwrites some
guest entries.
These savings will be increased on processors with larger TLBs or which
implement intelligent flush instructions like tlbivax (which will avoid the
need to walk arrays in software).
In addition to that and to the code simplification, we have a greater chance of
leaving other host userspace mappings in the TLB, instead of forcing all
subsequent tasks to re-fault all their mappings.
Signed-off-by: Hollis Blanchard <hollisb@us.ibm.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
KVM on 440 has always been able to handle large guest mappings with 4K host
pages -- we must, since the guest kernel uses 256MB mappings.
This patch makes KVM work when the host has large pages too (tested with 64K).
Signed-off-by: Hollis Blanchard <hollisb@us.ibm.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
In kvmppc_deliver_interrupt is just one case left in the switch and it is a
rare one (less than 8%) when looking at the exit numbers. Therefore we can
at least drop the switch/case and if an if. I inserted an unlikely too, but
that's open for discussion.
In kvmppc_can_deliver_interrupt all frequent cases are in the default case.
I know compilers are smart but we can make it easier for them. By writing
down all options and removing the default case combined with the fact that
ithe values are constants 0..15 should allow the compiler to write an easy
jump table.
Modifying kvmppc_can_deliver_interrupt pointed me to the fact that gcc seems
to be unable to reduce priority_exception[x] to a build time constant.
Therefore I changed the usage of the translation arrays in the interrupt
delivery path completely. It is now using priority without translation to irq
on the full irq delivery path.
To be able to do that ivpr regs are stored by their priority now.
Additionally the decision made in kvmppc_can_deliver_interrupt is already
sufficient to get the value of interrupt_msr_mask[x]. Therefore we can replace
the 16x4byte array used here with a single 4byte variable (might still be one
miss, but the chance to find this in cache should be better than the right
entry of the whole array).
Signed-off-by: Christian Ehrhardt <ehrhardt@linux.vnet.ibm.com>
Signed-off-by: Hollis Blanchard <hollisb@us.ibm.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
This patch doesn't yet move all 44x-specific data into the new structure, but
is the first step down that path. In the future we may also want to create a
struct kvm_vcpu_booke.
Based on patch from Liu Yu <yu.liu@freescale.com>.
Signed-off-by: Hollis Blanchard <hollisb@us.ibm.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
Cores provide 3 emulation hooks, implemented for example in the new
4xx_emulate.c:
kvmppc_core_emulate_op
kvmppc_core_emulate_mtspr
kvmppc_core_emulate_mfspr
Strictly speaking the last two aren't necessary, but provide for more
informative error reporting ("unknown SPR").
Long term I'd like to have instruction decoding autogenerated from tables of
opcodes, and that way we could aggregate universal, Book E, and core-specific
instructions more easily and without redundant switch statements.
Signed-off-by: Hollis Blanchard <hollisb@us.ibm.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
This introduces a set of core-provided hooks. For 440, some of these are
implemented by booke.c, with the rest in (the new) 44x.c.
Note that these hooks are link-time, not run-time. Since it is not possible to
build a single kernel for both e500 and 440 (for example), using function
pointers would only add overhead.
Signed-off-by: Hollis Blanchard <hollisb@us.ibm.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
This will ease ports to other cores.
Also remove unused "struct kvm_tlb" while we're at it.
Signed-off-by: Hollis Blanchard <hollisb@us.ibm.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
This will make it easier to provide implementations for other cores.
Signed-off-by: Hollis Blanchard <hollisb@us.ibm.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
When the VM exits, we must call put_page() for every page referenced in the
shadow TLB.
Without this patch, we usually leak 30-50 host pages (120 - 200 KiB with 4 KiB
pages). The maximum number of pages leaked is the size of our shadow TLB, 64
pages.
Signed-off-by: Hollis Blanchard <hollisb@us.ibm.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
When we use TID=N userspace mappings, we must ensure that kernel mappings have
been destroyed when entering userspace. Using TID=1/TID=0 for kernel/user
mappings and running userspace with PID=0 means that userspace can't access the
kernel mappings, but the kernel can directly access userspace.
The net is that we don't need to flush the TLB on privilege switches, but we do
on guest context switches (which are far more infrequent). Guest boot time
performance improvement: about 30%.
Signed-off-by: Hollis Blanchard <hollisb@us.ibm.com>
Signed-off-by: Avi Kivity <avi@qumranet.com>
Track which TLB entries need to be written, instead of overwriting everything
below the high water mark. Typically only a single guest TLB entry will be
modified in a single exit.
Guest boot time performance improvement: about 15%.
Signed-off-by: Hollis Blanchard <hollisb@us.ibm.com>
Signed-off-by: Avi Kivity <avi@qumranet.com>
from include/asm-powerpc. This is the result of a
mkdir arch/powerpc/include/asm
git mv include/asm-powerpc/* arch/powerpc/include/asm
Followed by a few documentation/comment fixups and a couple of places
where <asm-powepc/...> was being used explicitly. Of the latter only
one was outside the arch code and it is a driver only built for powerpc.
Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: Paul Mackerras <paulus@samba.org>
