Paolo Bonzini [Tue, 23 Feb 2016 11:51:19 +0000 (12:51 +0100)]
KVM: MMU: simplify last_pte_bitmap
Branch-free code is fun and everybody knows how much Avi loves it,
but last_pte_bitmap takes it a bit to the extreme. Since the code
is simply doing a range check, like
(level == 1 ||
((gpte & PT_PAGE_SIZE_MASK) && level < N)
we can make it branch-free without storing the entire truth table;
it is enough to cache N.
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Paolo Bonzini [Thu, 25 Feb 2016 09:47:38 +0000 (10:47 +0100)]
KVM: MMU: coalesce more page zapping in mmu_sync_children
mmu_sync_children can only process up to 16 pages at a time. Check
if we need to reschedule, and do not bother zapping the pages until
that happens.
Reviewed-by: Takuya Yoshikawa <yoshikawa_takuya_b1@lab.ntt.co.jp>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Paolo Bonzini [Wed, 24 Feb 2016 10:26:10 +0000 (11:26 +0100)]
KVM: MMU: move zap/flush to kvm_mmu_get_page
kvm_mmu_get_page is the only caller of kvm_sync_page_transient
and kvm_sync_pages. Moving the handling of the invalid_list there
removes the need for the underdocumented kvm_sync_page_transient
function.
Reviewed-by: Takuya Yoshikawa <yoshikawa_takuya_b1@lab.ntt.co.jp>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Paolo Bonzini [Wed, 24 Feb 2016 10:07:14 +0000 (11:07 +0100)]
KVM: MMU: invert return value of mmu.sync_page and *kvm_sync_page*
Return true if the page was synced (and the TLB must be flushed)
and false if the page was zapped.
Reviewed-by: Takuya Yoshikawa <yoshikawa_takuya_b1@lab.ntt.co.jp>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Paolo Bonzini [Wed, 24 Feb 2016 09:28:01 +0000 (10:28 +0100)]
KVM: MMU: cleanup __kvm_sync_page and its callers
Calling kvm_unlink_unsync_page in the middle of __kvm_sync_page makes
things unnecessarily tricky. If kvm_mmu_prepare_zap_page is called,
it will call kvm_unlink_unsync_page too. So kvm_unlink_unsync_page can
be called just as well at the beginning or the end of __kvm_sync_page...
which means that we might do it in kvm_sync_page too and remove the
parameter.
kvm_sync_page ends up being the same code that kvm_sync_pages used
to have before the previous patch.
Reviewed-by: Takuya Yoshikawa <yoshikawa_takuya_b1@lab.ntt.co.jp>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Paolo Bonzini [Wed, 24 Feb 2016 09:19:30 +0000 (10:19 +0100)]
KVM: MMU: use kvm_sync_page in kvm_sync_pages
If the last argument is true, kvm_unlink_unsync_page is called anyway in
__kvm_sync_page (either by kvm_mmu_prepare_zap_page or by __kvm_sync_page
itself). Therefore, kvm_sync_pages can just call kvm_sync_page, instead
of going through kvm_unlink_unsync_page+__kvm_sync_page.
Reviewed-by: Takuya Yoshikawa <yoshikawa_takuya_b1@lab.ntt.co.jp>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Paolo Bonzini [Wed, 24 Feb 2016 09:03:27 +0000 (10:03 +0100)]
KVM: MMU: move TLB flush out of __kvm_sync_page
By doing this, kvm_sync_pages can use __kvm_sync_page instead of
reinventing it. Because of kvm_mmu_flush_or_zap, the code does not
end up being more complex than before, and more cleanups to kvm_sync_pages
will come in the next patches.
Reviewed-by: Takuya Yoshikawa <yoshikawa_takuya_b1@lab.ntt.co.jp>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Paolo Bonzini [Wed, 24 Feb 2016 10:21:55 +0000 (11:21 +0100)]
KVM: MMU: introduce kvm_mmu_flush_or_zap
This is a generalization of mmu_pte_write_flush_tlb, that also
takes care of calling kvm_mmu_commit_zap_page. The next
patches will introduce more uses.
Reviewed-by: Takuya Yoshikawa <yoshikawa_takuya_b1@lab.ntt.co.jp>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Paolo Bonzini [Fri, 4 Mar 2016 08:28:41 +0000 (09:28 +0100)]
KVM: i8254: drop local copy of mul_u64_u32_div
A function that does the same as i8254.c's muldiv64 has been added
(for KVM's own use, in fact!) in include/linux/math64.h. Use it
instead of muldiv64.
Reviewed-by: Radim Krčmář <rkrcmar@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Xiao Guangrong [Wed, 24 Feb 2016 08:46:06 +0000 (09:46 +0100)]
KVM: MMU: check kvm_mmu_pages and mmu_page_path indices
Give a special invalid index to the root of the walk, so that we
can check the consistency of kvm_mmu_pages and mmu_page_path.
Signed-off-by: Xiao Guangrong <guangrong.xiao@linux.intel.com>
[Extracted from a bigger patch proposed by Guangrong. - Paolo]
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Paolo Bonzini [Tue, 23 Feb 2016 12:54:25 +0000 (13:54 +0100)]
KVM: MMU: Fix ubsan warnings
kvm_mmu_pages_init is doing some really yucky stuff. It is setting
up a sentinel for mmu_page_clear_parents; however, because of a) the
way levels are numbered starting from 1 and b) the way mmu_page_path
sizes its arrays with PT64_ROOT_LEVEL-1 elements, the access can be
out of bounds. This is harmless because the code overwrites up to the
first two elements of parents->idx and these are initialized, and
because the sentinel is not needed in this case---mmu_page_clear_parents
exits anyway when it gets to the end of the array. However ubsan
complains, and everyone else should too.
This fix does three things. First it makes the mmu_page_path arrays
PT64_ROOT_LEVEL elements in size, so that we can write to them without
checking the level in advance. Second it disintegrates kvm_mmu_pages_init
between mmu_unsync_walk (to reset the struct kvm_mmu_pages) and
for_each_sp (to place the NULL sentinel at the end of the current path).
This is okay because the mmu_page_path is only used in
mmu_pages_clear_parents; mmu_pages_clear_parents itself is called within
a for_each_sp iterator, and hence always after a call to mmu_pages_next.
Third it changes mmu_pages_clear_parents to just use the sentinel to
stop iteration, without checking the bounds on level.
Reported-by: Sasha Levin <sasha.levin@oracle.com>
Reported-by: Mike Krinkin <krinkin.m.u@gmail.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Paolo Bonzini [Tue, 23 Feb 2016 14:28:51 +0000 (15:28 +0100)]
KVM: MMU: cleanup handle_abnormal_pfn
The goto and temporary variable are unnecessary, just use return
statements.
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Paolo Bonzini [Fri, 26 Feb 2016 11:09:49 +0000 (12:09 +0100)]
KVM: VMX: use vmcs_clear/set_bits for debug register exits
Reviewed-by: Xiao Guangrong <guangrong.xiao@linux.intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Paolo Bonzini [Tue, 23 Feb 2016 14:36:01 +0000 (15:36 +0100)]
KVM: ensure __gfn_to_pfn_memslot initializes *writable
For the kvm_is_error_hva, ubsan complains if the uninitialized writable
is passed to __direct_map, even though the value itself is not used
(__direct_map goes to mmu_set_spte->set_spte->set_mmio_spte but never
looks at that argument).
Ensuring that __gfn_to_pfn_memslot initializes *writable is cheap and
avoids this kind of issue.
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Radim Krčmář [Wed, 2 Mar 2016 21:56:53 +0000 (22:56 +0100)]
KVM: document KVM_REINJECT_CONTROL ioctl
Signed-off-by: Radim Krčmář <rkrcmar@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Radim Krčmář [Wed, 2 Mar 2016 21:56:52 +0000 (22:56 +0100)]
KVM: i8254: turn kvm_kpit_state.reinject into atomic_t
Document possible races between readers and concurrent update to the
ioctl.
Suggested-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Radim Krčmář <rkrcmar@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Radim Krčmář [Wed, 2 Mar 2016 21:56:51 +0000 (22:56 +0100)]
KVM: i8254: move PIT timer function initialization
We can do it just once.
Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Radim Krčmář <rkrcmar@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Radim Krčmář [Wed, 2 Mar 2016 21:56:50 +0000 (22:56 +0100)]
KVM: i8254: don't assume layout of kvm_kpit_state
channels has offset 0 and correct size now, but that can change.
Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Radim Krčmář <rkrcmar@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Radim Krčmář [Wed, 2 Mar 2016 21:56:49 +0000 (22:56 +0100)]
KVM: i8254: remove pointless dereference of PIT
PIT is known at that point.
Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Radim Krčmář <rkrcmar@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Radim Krčmář [Wed, 2 Mar 2016 21:56:48 +0000 (22:56 +0100)]
KVM: i8254: remove pit and kvm from kvm_kpit_state
kvm isn't ever used and pit can be accessed with container_of.
If you *really* need kvm, pit_state_to_pit(ps)->kvm.
Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Radim Krčmář <rkrcmar@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Radim Krčmář [Wed, 2 Mar 2016 21:56:47 +0000 (22:56 +0100)]
KVM: i8254: refactor kvm_free_pit
Could be easier to read, but git history will become deeper.
Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Radim Krčmář <rkrcmar@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Radim Krčmář [Wed, 2 Mar 2016 21:56:46 +0000 (22:56 +0100)]
KVM: i8254: refactor kvm_create_pit
Locks are gone, so we don't need to duplicate error paths.
Use goto everywhere.
Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Radim Krčmář <rkrcmar@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Radim Krčmář [Wed, 2 Mar 2016 21:56:45 +0000 (22:56 +0100)]
KVM: i8254: remove notifiers from PIT discard policy
Discard policy doesn't rely on information from notifiers, so we don't
need to register notifiers unconditionally. We kept correct counts in
case userspace switched between policies during runtime, but that can be
avoided by reseting the state.
Signed-off-by: Radim Krčmář <rkrcmar@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Radim Krčmář [Wed, 2 Mar 2016 21:56:44 +0000 (22:56 +0100)]
KVM: i8254: remove unnecessary uses of PIT state lock
- kvm_create_pit had to lock only because it exposed kvm->arch.vpit very
early, but initialization doesn't use kvm->arch.vpit since the last
patch, so we can drop locking.
- kvm_free_pit is only run after there are no users of KVM and therefore
is the sole actor.
- Locking in kvm_vm_ioctl_reinject doesn't do anything, because reinject
is only protected at that place.
- kvm_pit_reset isn't used anywhere and its locking can be dropped if we
hide it.
Removing useless locking allows to see what actually is being protected
by PIT state lock (values accessible from the guest).
Signed-off-by: Radim Krčmář <rkrcmar@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Radim Krčmář [Wed, 2 Mar 2016 21:56:43 +0000 (22:56 +0100)]
KVM: i8254: pass struct kvm_pit instead of kvm in PIT
This patch passes struct kvm_pit into internal PIT functions.
Those functions used to get PIT through kvm->arch.vpit, even though most
of them never used *kvm for other purposes. Another benefit is that we
don't need to set kvm->arch.vpit during initialization.
Signed-off-by: Radim Krčmář <rkrcmar@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Radim Krčmář [Wed, 2 Mar 2016 21:56:42 +0000 (22:56 +0100)]
KVM: i8254: tone down WARN_ON pit.state_lock
If the guest could hit this, it would hang the host kernel, bacause of
sheer number of those reports. Internal callers have to be sensible
anyway, so we now only check for it in an API function.
Signed-off-by: Radim Krčmář <rkrcmar@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Radim Krčmář [Wed, 2 Mar 2016 21:56:41 +0000 (22:56 +0100)]
KVM: i8254: use atomic_t instead of pit.inject_lock
The lock was an overkill, the same can be done with atomics.
A mb() was added in kvm_pit_ack_irq, to pair with implicit barrier
between pit_timer_fn and pit_do_work. The mb() prevents a race that
could happen if pending == 0 and irq_ack == 0:
kvm_pit_ack_irq: | pit_timer_fn:
p = atomic_read(&ps->pending); |
| atomic_inc(&ps->pending);
| queue_work(pit_do_work);
| pit_do_work:
| atomic_xchg(&ps->irq_ack, 0);
| return;
atomic_set(&ps->irq_ack, 1); |
if (p == 0) return; |
where the interrupt would not be delivered in this tick of pit_timer_fn.
PIT would have eventually delivered the interrupt, but we sacrifice
perofmance to make sure that interrupts are not needlessly delayed.
sfence isn't enough: atomic_dec_if_positive does atomic_read first and
x86 can reorder loads before stores. lfence isn't enough: store can
pass lfence, turning it into a nop. A compiler barrier would be more
than enough as CPU needs to stall for unbelievably long to use fences.
This patch doesn't do anything in kvm_pit_reset_reinject, because any
order of resets can race, but the result differs by at most one
interrupt, which is ok, because it's the same result as if the reset
happened at a slightly different time. (Original code didn't protect
the reset path with a proper lock, so users have to be robust.)
Signed-off-by: Radim Krčmář <rkrcmar@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Radim Krčmář [Wed, 2 Mar 2016 21:56:40 +0000 (22:56 +0100)]
KVM: i8254: add kvm_pit_reset_reinject
pit_state.pending and pit_state.irq_ack are always reset at the same
time. Create a function for them.
Signed-off-by: Radim Krčmář <rkrcmar@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Radim Krčmář [Wed, 2 Mar 2016 21:56:39 +0000 (22:56 +0100)]
KVM: i8254: simplify atomics in kvm_pit_ack_irq
We already have a helper that does the same thing.
Signed-off-by: Radim Krčmář <rkrcmar@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Radim Krčmář [Wed, 2 Mar 2016 21:56:38 +0000 (22:56 +0100)]
KVM: i8254: change PIT discard tick policy
Discard policy uses ack_notifiers to prevent injection of PIT interrupts
before EOI from the last one.
This patch changes the policy to always try to deliver the interrupt,
which makes a difference when its vector is in ISR.
Old implementation would drop the interrupt, but proposed one injects to
IRR, like real hardware would.
The old policy breaks legacy NMI watchdogs, where PIT is used through
virtual wire (LVT0): PIT never sends an interrupt before receiving EOI,
thus a guest deadlock with disabled interrupts will stop NMIs.
Note that NMI doesn't do EOI, so PIT also had to send a normal interrupt
through IOAPIC. (KVM's PIT is deeply rotten and luckily not used much
in modern systems.)
Even though there is a chance of regressions, I think we can fix the
LVT0 NMI bug without introducing a new tick policy.
Cc: <stable@vger.kernel.org>
Reported-by: Yuki Shibuya <shibuya.yk@ncos.nec.co.jp>
Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Radim Krčmář <rkrcmar@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Xiao Guangrong [Wed, 24 Feb 2016 09:51:16 +0000 (17:51 +0800)]
KVM: MMU: apply page track notifier
Register the notifier to receive write track event so that we can update
our shadow page table
It makes kvm_mmu_pte_write() be the callback of the notifier, no function
is changed
Signed-off-by: Xiao Guangrong <guangrong.xiao@linux.intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Xiao Guangrong [Wed, 24 Feb 2016 09:51:15 +0000 (17:51 +0800)]
KVM: MMU: simplify mmu_need_write_protect
Now, all non-leaf shadow page are page tracked, if gfn is not tracked
there is no non-leaf shadow page of gfn is existed, we can directly
make the shadow page of gfn to unsync
Signed-off-by: Xiao Guangrong <guangrong.xiao@linux.intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Xiao Guangrong [Wed, 24 Feb 2016 09:51:14 +0000 (17:51 +0800)]
KVM: MMU: use page track for non-leaf shadow pages
non-leaf shadow pages are always write protected, it can be the user
of page track
Signed-off-by: Xiao Guangrong <guangrong.xiao@linux.intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Xiao Guangrong [Wed, 24 Feb 2016 09:51:13 +0000 (17:51 +0800)]
KVM: page track: add notifier support
Notifier list is introduced so that any node wants to receive the track
event can register to the list
Two APIs are introduced here:
- kvm_page_track_register_notifier(): register the notifier to receive
track event
- kvm_page_track_unregister_notifier(): stop receiving track event by
unregister the notifier
The callback, node->track_write() is called when a write access on the
write tracked page happens
Signed-off-by: Xiao Guangrong <guangrong.xiao@linux.intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Xiao Guangrong [Wed, 24 Feb 2016 09:51:12 +0000 (17:51 +0800)]
KVM: MMU: clear write-flooding on the fast path of tracked page
If the page fault is caused by write access on write tracked page, the
real shadow page walking is skipped, we lost the chance to clear write
flooding for the page structure current vcpu is using
Fix it by locklessly waking shadow page table to clear write flooding
on the shadow page structure out of mmu-lock. So that we change the
count to atomic_t
Signed-off-by: Xiao Guangrong <guangrong.xiao@linux.intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Xiao Guangrong [Wed, 24 Feb 2016 09:51:11 +0000 (17:51 +0800)]
KVM: MMU: let page fault handler be aware tracked page
The page fault caused by write access on the write tracked page can not
be fixed, it always need to be emulated. page_fault_handle_page_track()
is the fast path we introduce here to skip holding mmu-lock and shadow
page table walking
However, if the page table is not present, it is worth making the page
table entry present and readonly to make the read access happy
mmu_need_write_protect() need to be cooked to avoid page becoming writable
when making page table present or sync/prefetch shadow page table entries
Signed-off-by: Xiao Guangrong <guangrong.xiao@linux.intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Xiao Guangrong [Wed, 24 Feb 2016 09:51:10 +0000 (17:51 +0800)]
KVM: page track: introduce kvm_slot_page_track_{add,remove}_page
These two functions are the user APIs:
- kvm_slot_page_track_add_page(): add the page to the tracking pool
after that later specified access on that page will be tracked
- kvm_slot_page_track_remove_page(): remove the page from the tracking
pool, the specified access on the page is not tracked after the last
user is gone
Both of these are called under the protection both of mmu-lock and
kvm->srcu or kvm->slots_lock
Signed-off-by: Xiao Guangrong <guangrong.xiao@linux.intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Xiao Guangrong [Wed, 24 Feb 2016 09:51:09 +0000 (17:51 +0800)]
KVM: page track: add the framework of guest page tracking
The array, gfn_track[mode][gfn], is introduced in memory slot for every
guest page, this is the tracking count for the gust page on different
modes. If the page is tracked then the count is increased, the page is
not tracked after the count reaches zero
We use 'unsigned short' as the tracking count which should be enough as
shadow page table only can use 2^14 (2^3 for level, 2^1 for cr4_pae, 2^2
for quadrant, 2^3 for access, 2^1 for nxe, 2^1 for cr0_wp, 2^1 for
smep_andnot_wp, 2^1 for smap_andnot_wp, and 2^1 for smm) at most, there
is enough room for other trackers
Two callbacks, kvm_page_track_create_memslot() and
kvm_page_track_free_memslot() are implemented in this patch, they are
internally used to initialize and reclaim the memory of the array
Currently, only write track mode is supported
Signed-off-by: Xiao Guangrong <guangrong.xiao@linux.intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Xiao Guangrong [Wed, 24 Feb 2016 09:51:08 +0000 (17:51 +0800)]
KVM: MMU: introduce kvm_mmu_slot_gfn_write_protect
Split rmap_write_protect() and introduce the function to abstract the write
protection based on the slot
This function will be used in the later patch
Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Xiao Guangrong <guangrong.xiao@linux.intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Xiao Guangrong [Wed, 24 Feb 2016 09:51:07 +0000 (17:51 +0800)]
KVM: MMU: introduce kvm_mmu_gfn_{allow,disallow}_lpage
Abstract the common operations from account_shadowed() and
unaccount_shadowed(), then introduce kvm_mmu_gfn_disallow_lpage()
and kvm_mmu_gfn_allow_lpage()
These two functions will be used by page tracking in the later patch
Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Xiao Guangrong <guangrong.xiao@linux.intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Xiao Guangrong [Wed, 24 Feb 2016 09:51:06 +0000 (17:51 +0800)]
KVM: MMU: rename has_wrprotected_page to mmu_gfn_lpage_is_disallowed
kvm_lpage_info->write_count is used to detect if the large page mapping
for the gfn on the specified level is allowed, rename it to disallow_lpage
to reflect its purpose, also we rename has_wrprotected_page() to
mmu_gfn_lpage_is_disallowed() to make the code more clearer
Later we will extend this mechanism for page tracking: if the gfn is
tracked then large mapping for that gfn on any level is not allowed.
The new name is more straightforward
Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Xiao Guangrong <guangrong.xiao@linux.intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Joerg Roedel [Mon, 29 Feb 2016 15:04:45 +0000 (16:04 +0100)]
kvm: x86: Check dest_map->vector to match eoi signals for rtc
Using the vector stored at interrupt delivery makes the eoi
matching safe agains irq migration in the ioapic.
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Joerg Roedel [Mon, 29 Feb 2016 15:04:44 +0000 (16:04 +0100)]
kvm: x86: Track irq vectors in ioapic->rtc_status.dest_map
This allows backtracking later in case the rtc irq has been
moved to another vcpu/vector.
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Joerg Roedel [Mon, 29 Feb 2016 15:04:43 +0000 (16:04 +0100)]
kvm: x86: Convert ioapic->rtc_status.dest_map to a struct
Currently this is a bitmap which tracks which CPUs we expect
an EOI from. Move this bitmap to a struct so that we can
track additional information there.
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Paolo Bonzini [Thu, 3 Mar 2016 13:35:44 +0000 (14:35 +0100)]
Merge branch 'kvm-ppc-next' of git://git./linux/kernel/git/paulus/powerpc into HEAD
The highlights are:
* Enable VFIO device on PowerPC, from David Gibson
* Optimizations to speed up IPIs between vcpus in HV KVM,
from Suresh Warrier (who is also Suresh E. Warrier)
* In-kernel handling of IOMMU hypercalls, and support for dynamic DMA
windows (DDW), from Alexey Kardashevskiy.
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Alexey Kardashevskiy [Tue, 1 Mar 2016 06:54:40 +0000 (17:54 +1100)]
KVM: PPC: Add support for 64bit TCE windows
The existing KVM_CREATE_SPAPR_TCE only supports 32bit windows which is not
enough for directly mapped windows as the guest can get more than 4GB.
This adds KVM_CREATE_SPAPR_TCE_64 ioctl and advertises it
via KVM_CAP_SPAPR_TCE_64 capability. The table size is checked against
the locked memory limit.
Since 64bit windows are to support Dynamic DMA windows (DDW), let's add
@bus_offset and @page_shift which are also required by DDW.
Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
Signed-off-by: Paul Mackerras <paulus@samba.org>
Alexey Kardashevskiy [Tue, 1 Mar 2016 06:54:39 +0000 (17:54 +1100)]
KVM: PPC: Add @offset to kvmppc_spapr_tce_table
This enables userspace view of TCE tables to start from non-zero offset
on a bus. This will be used for huge DMA windows.
This only changes the internal structure, the user interface needs to
change in order to use an offset.
Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Paul Mackerras <paulus@samba.org>
Alexey Kardashevskiy [Tue, 1 Mar 2016 06:54:38 +0000 (17:54 +1100)]
KVM: PPC: Add @page_shift to kvmppc_spapr_tce_table
At the moment the kvmppc_spapr_tce_table struct can only describe
4GB windows and handle fixed size (4K) pages. Dynamic DMA windows
support more so these limits need to be extended.
This replaces window_size (in bytes, 4GB max) with page_shift (32bit)
and size (64bit, in pages).
This should cause no behavioural change as this is changing
the internal structures only - the user interface still only
allows one to create a 32-bit table with 4KiB pages at this stage.
Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Paul Mackerras <paulus@samba.org>
Alexey Kardashevskiy [Tue, 1 Mar 2016 06:54:37 +0000 (17:54 +1100)]
KVM: PPC: Reserve KVM_CAP_SPAPR_TCE_64 capability number
This adds a capability number for 64-bit TCE tables support.
Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
Signed-off-by: Paul Mackerras <paulus@samba.org>
Suresh E. Warrier [Mon, 21 Dec 2015 22:33:57 +0000 (16:33 -0600)]
KVM: PPC: Book3S HV: Add tunable to control H_IPI redirection
Redirecting the wakeup of a VCPU from the H_IPI hypercall to
a core running in the host is usually a good idea, most workloads
seemed to benefit. However, in one heavily interrupt-driven SMT1
workload, some regression was observed. This patch adds a kvm_hv
module parameter called h_ipi_redirect to control this feature.
The default value for this tunable is 1 - that is enable the feature.
Signed-off-by: Suresh Warrier <warrier@linux.vnet.ibm.com>
Signed-off-by: Paul Mackerras <paulus@samba.org>
Suresh E. Warrier [Mon, 21 Dec 2015 22:22:51 +0000 (16:22 -0600)]
KVM: PPC: Book3S HV: Send IPI to host core to wake VCPU
This patch adds support to real-mode KVM to search for a core
running in the host partition and send it an IPI message with
VCPU to be woken. This avoids having to switch to the host
partition to complete an H_IPI hypercall when the VCPU which
is the target of the the H_IPI is not loaded (is not running
in the guest).
The patch also includes the support in the IPI handler running
in the host to do the wakeup by calling kvmppc_xics_ipi_action
for the PPC_MSG_RM_HOST_ACTION message.
When a guest is being destroyed, we need to ensure that there
are no pending IPIs waiting to wake up a VCPU before we free
the VCPUs of the guest. This is accomplished by:
- Forces a PPC_MSG_CALL_FUNCTION IPI to be completed by all CPUs
before freeing any VCPUs in kvm_arch_destroy_vm().
- Any PPC_MSG_RM_HOST_ACTION messages must be executed first
before any other PPC_MSG_CALL_FUNCTION messages.
Signed-off-by: Suresh Warrier <warrier@linux.vnet.ibm.com>
Acked-by: Michael Ellerman <mpe@ellerman.id.au>
Signed-off-by: Paul Mackerras <paulus@samba.org>
Suresh Warrier [Thu, 17 Dec 2015 20:59:09 +0000 (14:59 -0600)]
KVM: PPC: Book3S HV: Host side kick VCPU when poked by real-mode KVM
This patch adds the support for the kick VCPU operation for
kvmppc_host_rm_ops. The kvmppc_xics_ipi_action() function
provides the function to be invoked for a host side operation
when poked by the real mode KVM. This is initiated by KVM by
sending an IPI to any free host core.
KVM real mode must set the rm_action to XICS_RM_KICK_VCPU and
rm_data to point to the VCPU to be woken up before sending the IPI.
Note that we have allocated one kvmppc_host_rm_core structure
per core. The above values need to be set in the structure
corresponding to the core to which the IPI will be sent.
Signed-off-by: Suresh Warrier <warrier@linux.vnet.ibm.com>
Signed-off-by: Paul Mackerras <paulus@samba.org>
Suresh Warrier [Thu, 17 Dec 2015 20:59:08 +0000 (14:59 -0600)]
KVM: PPC: Book3S HV: kvmppc_host_rm_ops - handle offlining CPUs
The kvmppc_host_rm_ops structure keeps track of which cores are
are in the host by maintaining a bitmask of active/runnable
online CPUs that have not entered the guest. This patch adds
support to manage the bitmask when a CPU is offlined or onlined
in the host.
Signed-off-by: Suresh Warrier <warrier@linux.vnet.ibm.com>
Signed-off-by: Paul Mackerras <paulus@samba.org>
Suresh Warrier [Thu, 17 Dec 2015 20:59:07 +0000 (14:59 -0600)]
KVM: PPC: Book3S HV: Manage core host state
Update the core host state in kvmppc_host_rm_ops whenever
the primary thread of the core enters the guest or returns
back.
Signed-off-by: Suresh Warrier <warrier@linux.vnet.ibm.com>
Signed-off-by: Paul Mackerras <paulus@samba.org>
Suresh Warrier [Thu, 17 Dec 2015 20:59:06 +0000 (14:59 -0600)]
KVM: PPC: Book3S HV: Host-side RM data structures
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>
Suresh Warrier [Thu, 17 Dec 2015 20:59:05 +0000 (14:59 -0600)]
powerpc/xics: Add icp_native_cause_ipi_rm
Function to cause an IPI by directly updating the MFFR register
in the XICS. The function is meant for real-mode callers since
they cannot use the smp_ops->cause_ipi function which uses an
ioremapped address.
Normal usage is for the the KVM real mode code to set the IPI message
using smp_muxed_ipi_message_pass and then invoke icp_native_cause_ipi_rm
to cause the actual IPI.
The function requires kvm_hstate.xics_phys to have been initialized
with the physical address of XICS.
Signed-off-by: Suresh Warrier <warrier@linux.vnet.ibm.com>
Acked-by: Michael Ellerman <mpe@ellerman.id.au>
Signed-off-by: Paul Mackerras <paulus@samba.org>
Suresh Warrier [Thu, 17 Dec 2015 20:59:04 +0000 (14:59 -0600)]
powerpc/smp: Add smp_muxed_ipi_set_message
smp_muxed_ipi_message_pass() invokes smp_ops->cause_ipi, which
uses an ioremapped address to access registers on the XICS
interrupt controller to cause the IPI. Because of this real
mode callers cannot call smp_muxed_ipi_message_pass() for IPI
messaging.
This patch creates a separate function smp_muxed_ipi_set_message
just to set the IPI message without the cause_ipi routine.
After calling this function to set the IPI message, real
mode callers must cause the IPI by writing to the XICS registers
directly.
As part of this, we also change smp_muxed_ipi_message_pass
to call smp_muxed_ipi_set_message to set the message instead
of doing it directly inside the routine.
Signed-off-by: Suresh Warrier <warrier@linux.vnet.ibm.com>
Acked-by: Michael Ellerman <mpe@ellerman.id.au>
Signed-off-by: Paul Mackerras <paulus@samba.org>
Suresh Warrier [Thu, 17 Dec 2015 20:59:03 +0000 (14:59 -0600)]
powerpc/smp: Support more IPI messages
This patch increases the number of demuxed messages for a
controller with a single ipi to 8 for 64-bit systems.
This is required because we want to use the IPI mechanism
to send messages from a CPU running in KVM real mode in a
guest to a CPU in the host to take some action. Currently,
we only support 4 messages and all 4 are already taken.
Define a fifth message PPC_MSG_RM_HOST_ACTION for this
purpose.
Signed-off-by: Suresh Warrier <warrier@linux.vnet.ibm.com>
Acked-by: Michael Ellerman <mpe@ellerman.id.au>
Signed-off-by: Paul Mackerras <paulus@samba.org>
Geliang Tang [Fri, 1 Jan 2016 11:47:15 +0000 (19:47 +0800)]
KVM: async_pf: use list_first_entry
To make the intention clearer, use list_first_entry instead of
list_entry.
Signed-off-by: Geliang Tang <geliangtang@163.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Geliang Tang [Fri, 1 Jan 2016 11:47:14 +0000 (19:47 +0800)]
KVM: x86: use list_last_entry
To make the intention clearer, use list_last_entry instead of
list_entry.
Signed-off-by: Geliang Tang <geliangtang@163.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Geliang Tang [Fri, 1 Jan 2016 11:47:13 +0000 (19:47 +0800)]
KVM: x86: use list_for_each_entry*
Use list_for_each_entry*() instead of list_for_each*() to simplify
the code.
Signed-off-by: Geliang Tang <geliangtang@163.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Geliang Tang [Fri, 1 Jan 2016 11:47:12 +0000 (19:47 +0800)]
KVM: use list_for_each_entry_safe
Use list_for_each_entry_safe() instead of list_for_each_safe() to
simplify the code.
Signed-off-by: Geliang Tang <geliangtang@163.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Takuya Yoshikawa [Mon, 22 Feb 2016 08:23:41 +0000 (17:23 +0900)]
KVM: x86: MMU: Move handle_mmio_page_fault() call to kvm_mmu_page_fault()
Rather than placing a handle_mmio_page_fault() call in each
vcpu->arch.mmu.page_fault() handler, moving it up to
kvm_mmu_page_fault() makes the code better:
- avoids code duplication
- for kvm_arch_async_page_ready(), which is the other caller of
vcpu->arch.mmu.page_fault(), removes an extra error_code check
- avoids returning both RET_MMIO_PF_* values and raw integer values
from vcpu->arch.mmu.page_fault()
Signed-off-by: Takuya Yoshikawa <yoshikawa_takuya_b1@lab.ntt.co.jp>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Takuya Yoshikawa [Mon, 22 Feb 2016 08:23:40 +0000 (17:23 +0900)]
KVM: x86: MMU: Consolidate quickly_check_mmio_pf() and is_mmio_page_fault()
These two have only slight differences:
- whether 'addr' is of type u64 or of type gva_t
- whether they have 'direct' parameter or not
Concerning the former, quickly_check_mmio_pf()'s u64 is better because
'addr' needs to be able to have both a guest physical address and a
guest virtual address.
The latter is just a stylistic issue as we can always calculate the mode
from the 'vcpu' as is_mmio_page_fault() does. This patch keeps the
parameter to make the following patch cleaner.
In addition, the patch renames the function to mmio_info_in_cache() to
make it clear what it actually checks for.
Signed-off-by: Takuya Yoshikawa <yoshikawa_takuya_b1@lab.ntt.co.jp>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Paolo Bonzini [Mon, 8 Feb 2016 14:11:15 +0000 (15:11 +0100)]
KVM: x86: pass kvm_get_time_scale arguments in hertz
Prepare for improving the precision in the next patch.
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Andrey Smetanin [Thu, 11 Feb 2016 13:45:01 +0000 (16:45 +0300)]
kvm/x86: Hyper-V VMBus hypercall userspace exit
The patch implements KVM_EXIT_HYPERV userspace exit
functionality for Hyper-V VMBus hypercalls:
HV_X64_HCALL_POST_MESSAGE, HV_X64_HCALL_SIGNAL_EVENT.
Changes v3:
* use vcpu->arch.complete_userspace_io to setup hypercall
result
Changes v2:
* use KVM_EXIT_HYPERV for hypercalls
Signed-off-by: Andrey Smetanin <asmetanin@virtuozzo.com>
Reviewed-by: Roman Kagan <rkagan@virtuozzo.com>
CC: Gleb Natapov <gleb@kernel.org>
CC: Paolo Bonzini <pbonzini@redhat.com>
CC: Joerg Roedel <joro@8bytes.org>
CC: "K. Y. Srinivasan" <kys@microsoft.com>
CC: Haiyang Zhang <haiyangz@microsoft.com>
CC: Roman Kagan <rkagan@virtuozzo.com>
CC: Denis V. Lunev <den@openvz.org>
CC: qemu-devel@nongnu.org
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Andrey Smetanin [Thu, 11 Feb 2016 13:45:00 +0000 (16:45 +0300)]
kvm/x86: Reject Hyper-V hypercall continuation
Currently we do not support Hyper-V hypercall continuation
so reject it.
Signed-off-by: Andrey Smetanin <asmetanin@virtuozzo.com>
Reviewed-by: Roman Kagan <rkagan@virtuozzo.com>
CC: Gleb Natapov <gleb@kernel.org>
CC: Paolo Bonzini <pbonzini@redhat.com>
CC: Joerg Roedel <joro@8bytes.org>
CC: "K. Y. Srinivasan" <kys@microsoft.com>
CC: Haiyang Zhang <haiyangz@microsoft.com>
CC: Roman Kagan <rkagan@virtuozzo.com>
CC: Denis V. Lunev <den@openvz.org>
CC: qemu-devel@nongnu.org
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Andrey Smetanin [Thu, 11 Feb 2016 13:44:59 +0000 (16:44 +0300)]
kvm/x86: Pass return code of kvm_emulate_hypercall
Pass the return code from kvm_emulate_hypercall on to the caller,
in order to allow it to indicate to the userspace that
the hypercall has to be handled there.
Also adjust all the existing code paths to return 1 to make sure the
hypercall isn't passed to the userspace without setting kvm_run
appropriately.
Signed-off-by: Andrey Smetanin <asmetanin@virtuozzo.com>
Reviewed-by: Roman Kagan <rkagan@virtuozzo.com>
CC: Gleb Natapov <gleb@kernel.org>
CC: Paolo Bonzini <pbonzini@redhat.com>
CC: Joerg Roedel <joro@8bytes.org>
CC: "K. Y. Srinivasan" <kys@microsoft.com>
CC: Haiyang Zhang <haiyangz@microsoft.com>
CC: Roman Kagan <rkagan@virtuozzo.com>
CC: Denis V. Lunev <den@openvz.org>
CC: qemu-devel@nongnu.org
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Andrey Smetanin [Thu, 11 Feb 2016 13:44:58 +0000 (16:44 +0300)]
drivers/hv: Move VMBus hypercall codes into Hyper-V UAPI header
VMBus hypercall codes inside Hyper-V UAPI header will
be used by QEMU to implement VMBus host devices support.
Signed-off-by: Andrey Smetanin <asmetanin@virtuozzo.com>
Acked-by: K. Y. Srinivasan <kys@microsoft.com>
Reviewed-by: Roman Kagan <rkagan@virtuozzo.com>
CC: Gleb Natapov <gleb@kernel.org>
CC: Paolo Bonzini <pbonzini@redhat.com>
CC: Joerg Roedel <joro@8bytes.org>
CC: "K. Y. Srinivasan" <kys@microsoft.com>
CC: Haiyang Zhang <haiyangz@microsoft.com>
CC: Roman Kagan <rkagan@virtuozzo.com>
CC: Denis V. Lunev <den@openvz.org>
CC: qemu-devel@nongnu.org
[Do not rename the constant at the same time as moving it, as that
would cause semantic conflicts with the Hyper-V tree. - Paolo]
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Andrey Smetanin [Thu, 11 Feb 2016 13:44:57 +0000 (16:44 +0300)]
kvm/x86: Rename Hyper-V long spin wait hypercall
Rename HV_X64_HV_NOTIFY_LONG_SPIN_WAIT by HVCALL_NOTIFY_LONG_SPIN_WAIT,
so the name is more consistent with the other hypercalls.
Signed-off-by: Andrey Smetanin <asmetanin@virtuozzo.com>
Reviewed-by: Roman Kagan <rkagan@virtuozzo.com>
CC: Gleb Natapov <gleb@kernel.org>
CC: Paolo Bonzini <pbonzini@redhat.com>
CC: Joerg Roedel <joro@8bytes.org>
CC: "K. Y. Srinivasan" <kys@microsoft.com>
CC: Haiyang Zhang <haiyangz@microsoft.com>
CC: Roman Kagan <rkagan@virtuozzo.com>
CC: Denis V. Lunev <den@openvz.org>
CC: qemu-devel@nongnu.org
[Change name, Andrey used HV_X64_HCALL_NOTIFY_LONG_SPIN_WAIT. - Paolo]
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Paolo Bonzini [Wed, 10 Feb 2016 16:50:23 +0000 (17:50 +0100)]
KVM: x86: fix missed hardware breakpoints
Sometimes when setting a breakpoint a process doesn't stop on it.
This is because the debug registers are not loaded correctly on
VCPU load.
The following simple reproducer from Oleg Nesterov tries using debug
registers in both the host and the guest, for example by running "./bp
0 1" on the host and "./bp 14 15" under QEMU.
#include <unistd.h>
#include <signal.h>
#include <stdlib.h>
#include <stdio.h>
#include <sys/wait.h>
#include <sys/ptrace.h>
#include <sys/user.h>
#include <asm/debugreg.h>
#include <assert.h>
#define offsetof(TYPE, MEMBER) ((size_t) &((TYPE *)0)->MEMBER)
unsigned long encode_dr7(int drnum, int enable, unsigned int type, unsigned int len)
{
unsigned long dr7;
dr7 = ((len | type) & 0xf)
<< (DR_CONTROL_SHIFT + drnum * DR_CONTROL_SIZE);
if (enable)
dr7 |= (DR_GLOBAL_ENABLE << (drnum * DR_ENABLE_SIZE));
return dr7;
}
int write_dr(int pid, int dr, unsigned long val)
{
return ptrace(PTRACE_POKEUSER, pid,
offsetof (struct user, u_debugreg[dr]),
val);
}
void set_bp(pid_t pid, void *addr)
{
unsigned long dr7;
assert(write_dr(pid, 0, (long)addr) == 0);
dr7 = encode_dr7(0, 1, DR_RW_EXECUTE, DR_LEN_1);
assert(write_dr(pid, 7, dr7) == 0);
}
void *get_rip(int pid)
{
return (void*)ptrace(PTRACE_PEEKUSER, pid,
offsetof(struct user, regs.rip), 0);
}
void test(int nr)
{
void *bp_addr = &&label + nr, *bp_hit;
int pid;
printf("test bp %d\n", nr);
assert(nr < 16); // see 16 asm nops below
pid = fork();
if (!pid) {
assert(ptrace(PTRACE_TRACEME, 0,0,0) == 0);
kill(getpid(), SIGSTOP);
for (;;) {
label: asm (
"nop; nop; nop; nop;"
"nop; nop; nop; nop;"
"nop; nop; nop; nop;"
"nop; nop; nop; nop;"
);
}
}
assert(pid == wait(NULL));
set_bp(pid, bp_addr);
for (;;) {
assert(ptrace(PTRACE_CONT, pid, 0, 0) == 0);
assert(pid == wait(NULL));
bp_hit = get_rip(pid);
if (bp_hit != bp_addr)
fprintf(stderr, "ERR!! hit wrong bp %ld != %d\n",
bp_hit - &&label, nr);
}
}
int main(int argc, const char *argv[])
{
while (--argc) {
int nr = atoi(*++argv);
if (!fork())
test(nr);
}
while (wait(NULL) > 0)
;
return 0;
}
Cc: stable@vger.kernel.org
Suggested-by: Nadadv Amit <namit@cs.technion.ac.il>
Reported-by: Andrey Wagin <avagin@gmail.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Radim Krčmář [Fri, 12 Feb 2016 14:00:15 +0000 (15:00 +0100)]
KVM: x86: fix *NULL on invalid low-prio irq
Smatch noticed a NULL dereference in kvm_intr_is_single_vcpu_fast that
happens if VM already warned about invalid lowest-priority interrupt.
Create a function for common code while fixing it.
Fixes:
6228a0da8057 ("KVM: x86: Add lowest-priority support for vt-d posted-interrupts")
Reported-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Radim Krčmář <rkrcmar@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Paolo Bonzini [Mon, 8 Feb 2016 13:51:40 +0000 (14:51 +0100)]
KVM: x86: rewrite handling of scaled TSC for kvmclock
This is the same as before:
kvm_scale_tsc(tgt_tsc_khz)
= tgt_tsc_khz * ratio
= tgt_tsc_khz * user_tsc_khz / tsc_khz (see set_tsc_khz)
= user_tsc_khz (see kvm_guest_time_update)
= vcpu->arch.virtual_tsc_khz (see kvm_set_tsc_khz)
However, computing it through kvm_scale_tsc will make it possible
to include the NTP correction in tgt_tsc_khz.
Reviewed-by: Marcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Paolo Bonzini [Mon, 8 Feb 2016 13:51:12 +0000 (14:51 +0100)]
KVM: x86: rename argument to kvm_set_tsc_khz
This refers to the desired (scaled) frequency, which is called
user_tsc_khz in the rest of the file.
Reviewed-by: Marcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Jan Kiszka [Tue, 9 Feb 2016 19:15:18 +0000 (20:15 +0100)]
KVM: VMX: Fix guest debugging while in L2
When we take a #DB or #BP vmexit while in guest mode, we first of all
need to check if there is ongoing guest debugging that might be
interested in the event. Currently, we unconditionally leave L2 and
inject the event into L1 if it is intercepting the exceptions. That
breaks things marvelously.
Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Jan Kiszka [Tue, 9 Feb 2016 19:14:21 +0000 (20:14 +0100)]
KVM: VMX: Factor out is_exception_n helper
There is quite some common code in all these is_<exception>() helpers.
Factor it out before adding even more of them.
Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Christian Borntraeger [Tue, 9 Feb 2016 12:47:55 +0000 (13:47 +0100)]
KVM: halt_polling: improve grow/shrink settings
Right now halt_poll_ns can be change during runtime. The
grow and shrink factors can only be set during module load.
Lets fix several aspects of grow shrink:
- make grow/shrink changeable by root
- make all variables unsigned int
- read the variables once to prevent races
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Paolo Bonzini [Tue, 16 Feb 2016 17:48:14 +0000 (18:48 +0100)]
Merge tag 'kvm-s390-next-4.6-1' of git://git./linux/kernel/git/kvms390/linux into HEAD
KVM: s390: Fixes and features for kvm/next (4.6)
1. also provide the floating point registers via sync regs
2. Separate out intruction vs. data accesses
3. Fix program interrupts in some cases
4. Documentation fixes
5. dirty log improvements for huge guests
Alexey Kardashevskiy [Mon, 15 Feb 2016 01:55:09 +0000 (12:55 +1100)]
KVM: PPC: Add support for multiple-TCE hcalls
This adds real and virtual mode handlers for the H_PUT_TCE_INDIRECT and
H_STUFF_TCE hypercalls for user space emulated devices such as IBMVIO
devices or emulated PCI. These calls allow adding multiple entries
(up to 512) into the TCE table in one call which saves time on
transition between kernel and user space.
The current implementation of kvmppc_h_stuff_tce() allows it to be
executed in both real and virtual modes so there is one helper.
The kvmppc_rm_h_put_tce_indirect() needs to translate the guest address
to the host address and since the translation is different, there are
2 helpers - one for each mode.
This implements the KVM_CAP_PPC_MULTITCE capability. When present,
the kernel will try handling H_PUT_TCE_INDIRECT and H_STUFF_TCE if these
are enabled by the userspace via KVM_CAP_PPC_ENABLE_HCALL.
If they can not be handled by the kernel, they are passed on to
the user space. The user space still has to have an implementation
for these.
Both HV and PR-syle KVM are supported.
Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Paul Mackerras <paulus@samba.org>
Alexey Kardashevskiy [Mon, 15 Feb 2016 01:55:08 +0000 (12:55 +1100)]
KVM: PPC: Move reusable bits of H_PUT_TCE handler to helpers
Upcoming multi-tce support (H_PUT_TCE_INDIRECT/H_STUFF_TCE hypercalls)
will validate TCE (not to have unexpected bits) and IO address
(to be within the DMA window boundaries).
This introduces helpers to validate TCE and IO address. The helpers are
exported as they compile into vmlinux (to work in realmode) and will be
used later by KVM kernel module in virtual mode.
Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Paul Mackerras <paulus@samba.org>
Alexey Kardashevskiy [Mon, 15 Feb 2016 01:55:07 +0000 (12:55 +1100)]
KVM: PPC: Replace SPAPR_TCE_SHIFT with IOMMU_PAGE_SHIFT_4K
SPAPR_TCE_SHIFT is used in few places only and since IOMMU_PAGE_SHIFT_4K
can be easily used instead, remove SPAPR_TCE_SHIFT.
Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Paul Mackerras <paulus@samba.org>
Alexey Kardashevskiy [Mon, 15 Feb 2016 01:55:06 +0000 (12:55 +1100)]
KVM: PPC: Account TCE-containing pages in locked_vm
At the moment pages used for TCE tables (in addition to pages addressed
by TCEs) are not counted in locked_vm counter so a malicious userspace
tool can call ioctl(KVM_CREATE_SPAPR_TCE) as many times as
RLIMIT_NOFILE and lock a lot of memory.
This adds counting for pages used for TCE tables.
This counts the number of pages required for a table plus pages for
the kvmppc_spapr_tce_table struct (TCE table descriptor) itself.
This changes release_spapr_tce_table() to store @npages on stack to
avoid calling kvmppc_stt_npages() in the loop (tiny optimization,
probably).
This does not change the amount of used memory.
Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Paul Mackerras <paulus@samba.org>
Alexey Kardashevskiy [Mon, 15 Feb 2016 01:55:05 +0000 (12:55 +1100)]
KVM: PPC: Use RCU for arch.spapr_tce_tables
At the moment only spapr_tce_tables updates are protected against races
but not lookups. This fixes missing protection by using RCU for the list.
As lookups also happen in real mode, this uses
list_for_each_entry_lockless() (which is expected not to access any
vmalloc'd memory).
This converts release_spapr_tce_table() to a RCU scheduled handler.
Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Paul Mackerras <paulus@samba.org>
Alexey Kardashevskiy [Mon, 15 Feb 2016 01:55:04 +0000 (12:55 +1100)]
KVM: PPC: Rework H_PUT_TCE/H_GET_TCE handlers
This reworks the existing H_PUT_TCE/H_GET_TCE handlers to have following
patches applied nicer.
This moves the ioba boundaries check to a helper and adds a check for
least bits which have to be zeros.
The patch is pretty mechanical (only check for least ioba bits is added)
so no change in behaviour is expected.
Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Paul Mackerras <paulus@samba.org>
Alexey Kardashevskiy [Mon, 15 Feb 2016 01:55:03 +0000 (12:55 +1100)]
powerpc: Make vmalloc_to_phys() public
This makes vmalloc_to_phys() public as there will be another user
(KVM in-kernel VFIO acceleration) for it soon. As this new user
can be compiled as a module, this exports the symbol.
As a little optimization, this changes the helper to call
vmalloc_to_pfn() instead of vmalloc_to_page() as the size of the
struct page may not be power-of-two aligned which will make gcc use
multiply instructions instead of shifts.
Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
Acked-by: Michael Ellerman <mpe@ellerman.id.au>
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Paul Mackerras <paulus@samba.org>
David Gibson [Mon, 1 Feb 2016 00:14:15 +0000 (11:14 +1100)]
vfio: Enable VFIO device for powerpc
ec53500f "kvm: Add VFIO device" added a special KVM pseudo-device which is
used to handle any necessary interactions between KVM and VFIO.
Currently that device is built on x86 and ARM, but not powerpc, although
powerpc does support both KVM and VFIO. This makes things awkward in
userspace
Currently qemu prints an alarming error message if you attempt to use VFIO
and it can't initialize the KVM VFIO device. We don't want to remove the
warning, because lack of the KVM VFIO device could mean coherency problems
on x86. On powerpc, however, the error is harmless but looks disturbing,
and a test based on host architecture in qemu would be ugly, and break if
we do need the KVM VFIO device for something important in future.
There's nothing preventing the KVM VFIO device from being built for
powerpc, so this patch turns it on. It won't actually do anything, since
we don't define any of the arch_*() hooks, but it will make qemu happy and
we can extend it in future if we need to.
Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
Reviewed-by: Eric Auger <eric.auger@linaro.org>
Signed-off-by: Paul Mackerras <paulus@samba.org>
Christian Borntraeger [Wed, 3 Feb 2016 10:12:34 +0000 (11:12 +0100)]
KVM: s390: bail out early on fatal signal in dirty logging
A KVM_GET_DIRTY_LOG ioctl might take a long time.
This can result in fatal signals seemingly being ignored.
Lets bail out during the dirty bit sync, if a fatal signal
is pending.
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
Reviewed-by: David Hildenbrand <dahi@linux.vnet.ibm.com>
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
Christian Borntraeger [Tue, 2 Feb 2016 14:15:56 +0000 (15:15 +0100)]
KVM: s390: do not block CPU on dirty logging
When doing dirty logging on huge guests (e.g.600GB) we sometimes
get rcu stall timeouts with backtraces like
[ 2753.194083] ([<
0000000000112fb2>] show_trace+0x12a/0x130)
[ 2753.194092] [<
0000000000113024>] show_stack+0x6c/0xe8
[ 2753.194094] [<
00000000001ee6a8>] rcu_pending+0x358/0xa48
[ 2753.194099] [<
00000000001f20cc>] rcu_check_callbacks+0x84/0x168
[ 2753.194102] [<
0000000000167654>] update_process_times+0x54/0x80
[ 2753.194107] [<
00000000001bdb5c>] tick_sched_handle.isra.16+0x4c/0x60
[ 2753.194113] [<
00000000001bdbd8>] tick_sched_timer+0x68/0x90
[ 2753.194115] [<
0000000000182a88>] __run_hrtimer+0x88/0x1f8
[ 2753.194119] [<
00000000001838ba>] hrtimer_interrupt+0x122/0x2b0
[ 2753.194121] [<
000000000010d034>] do_extint+0x16c/0x170
[ 2753.194123] [<
00000000005e206e>] ext_skip+0x38/0x3e
[ 2753.194129] [<
000000000012157c>] gmap_test_and_clear_dirty+0xcc/0x118
[ 2753.194134] ([<
00000000001214ea>] gmap_test_and_clear_dirty+0x3a/0x118)
[ 2753.194137] [<
0000000000132da4>] kvm_vm_ioctl_get_dirty_log+0xd4/0x1b0
[ 2753.194143] [<
000000000012ac12>] kvm_vm_ioctl+0x21a/0x548
[ 2753.194146] [<
00000000002b57f6>] do_vfs_ioctl+0x30e/0x518
[ 2753.194149] [<
00000000002b5a9c>] SyS_ioctl+0x9c/0xb0
[ 2753.194151] [<
00000000005e1ae6>] sysc_tracego+0x14/0x1a
[ 2753.194153] [<
000003ffb75f3972>] 0x3ffb75f3972
We should do a cond_resched in here.
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
Reviewed-by: David Hildenbrand <dahi@linux.vnet.ibm.com>
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
Christian Borntraeger [Wed, 3 Feb 2016 09:18:41 +0000 (10:18 +0100)]
KVM: s390: do not take mmap_sem on dirty log query
Dirty log query can take a long time for huge guests.
Holding the mmap_sem for very long times can cause some unwanted
latencies.
Turns out that we do not need to hold the mmap semaphore.
We hold the slots_lock for gfn->hva translation and walk the page
tables with that address, so no need to look at the VMAs. KVM also
holds a reference to the mm, which should prevent other things
going away. During the walk we take the necessary ptl locks.
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
Reviewed-by: David Hildenbrand <dahi@linux.vnet.ibm.com>
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
Cornelia Huck [Tue, 26 Jan 2016 09:48:59 +0000 (10:48 +0100)]
KVM: s390: usage hint for adapter mappings
The interface for adapter mappings was designed with code in mind
that maps each address only once; let's document this.
Otherwise, duplicate mappings are added to the list, which makes
the code ineffective and uses up the limited amount of mapping
needlessly.
Signed-off-by: Cornelia Huck <cornelia.huck@de.ibm.com>
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
David Hildenbrand [Thu, 21 Jan 2016 12:45:50 +0000 (13:45 +0100)]
KVM: s390: add documentation of KVM_S390_VM_CRYPTO
Let's properly document KVM_S390_VM_CRYPTO and its attributes.
Signed-off-by: David Hildenbrand <dahi@linux.vnet.ibm.com>
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
David Hildenbrand [Thu, 21 Jan 2016 12:39:14 +0000 (13:39 +0100)]
KVM: s390: add documentation of KVM_S390_VM_TOD
Let's properly document KVM_S390_VM_TOD and its attributes.
Reviewed-by: Cornelia Huck <cornelia.huck@de.ibm.com>
Signed-off-by: David Hildenbrand <dahi@linux.vnet.ibm.com>
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
David Hildenbrand [Thu, 14 Jan 2016 21:15:08 +0000 (22:15 +0100)]
KVM: s390: remove old fragment of vector registers
Since commit
9977e886cbbc ("s390/kernel: lazy restore fpu registers"),
vregs in struct sie_page is unsed. We can safely remove the field and
the definition.
Signed-off-by: David Hildenbrand <dahi@linux.vnet.ibm.com>
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
David Hildenbrand [Tue, 12 Jan 2016 16:40:54 +0000 (17:40 +0100)]
KVM: s390: instruction-fetching exceptions on SIE faults
On instruction-fetch exceptions, we have to forward the PSW by any
valid ilc and correctly use that ilc when injecting the irq. Injection
will already take care of rewinding the PSW if we injected a nullifying
program irq, so we don't need special handling prior to injection.
Until now, autodetection would have guessed an ilc of 0.
Reviewed-by: Christian Borntraeger <borntraeger@de.ibm.com>
Signed-off-by: David Hildenbrand <dahi@linux.vnet.ibm.com>
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
David Hildenbrand [Tue, 12 Jan 2016 16:37:58 +0000 (17:37 +0100)]
KVM: s390: provide prog irq ilc on SIE faults
On SIE faults, the ilc cannot be detected automatically, as the icptcode
is 0. The ilc indicated in the program irq will always be 0. Therefore we
have to manually specify the ilc in order to tell the guest which ilen was
used when forwarding the PSW.
Reviewed-by: Christian Borntraeger <borntraeger@de.ibm.com>
Signed-off-by: David Hildenbrand <dahi@linux.vnet.ibm.com>
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
David Hildenbrand [Wed, 4 Nov 2015 15:46:55 +0000 (16:46 +0100)]
KVM: s390: irq delivery should not rely on icptcode
Program irq injection during program irq intercepts is the last candidates
that injects nullifying irqs and relies on delivery to do the right thing.
As we should not rely on the icptcode during any delivery (because that
value will not be migrated), let's add a flag, telling prog IRQ delivery
to not rewind the PSW in case of nullifying prog IRQs.
Signed-off-by: David Hildenbrand <dahi@linux.vnet.ibm.com>
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
David Hildenbrand [Wed, 4 Nov 2015 15:22:19 +0000 (16:22 +0100)]
KVM: s390: clean up prog irq injection on prog irq icpts
__extract_prog_irq() is used only once for getting the program check data
in one place. Let's combine it with an injection function to avoid a memset
and to prevent misuse on injection by simplifying the interface to only
have the VCPU as parameter.
Reviewed-by: Christian Borntraeger <borntraeger@de.ibm.com>
Signed-off-by: David Hildenbrand <dahi@linux.vnet.ibm.com>
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
David Hildenbrand [Mon, 16 Nov 2015 15:17:45 +0000 (16:17 +0100)]
KVM: s390: read the correct opcode on SIE faults
Let's use our fresh new function read_guest_instr() to access
guest storage via the correct addressing schema.
Reviewed-by: Christian Borntraeger <borntraeger@de.ibm.com>
Signed-off-by: David Hildenbrand <dahi@linux.vnet.ibm.com>
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
David Hildenbrand [Mon, 16 Nov 2015 14:48:59 +0000 (15:48 +0100)]
KVM: s390: gaccess: implement instruction fetching mode
When an instruction is to be fetched, special handling applies to
secondary-space mode and access-register mode. The instruction is to be
fetched from primary space.
We can easily support this by selecting the right asce for translation.
Access registers will never be used during translation, so don't
include them in the interface. As we only want to read from the current
PSW address for now, let's also hide that detail.
Reviewed-by: Christian Borntraeger <borntraeger@de.ibm.com>
Signed-off-by: David Hildenbrand <dahi@linux.vnet.ibm.com>
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
David Hildenbrand [Mon, 16 Nov 2015 14:42:11 +0000 (15:42 +0100)]
KVM: s390: gaccess: introduce access modes
We will need special handling when fetching instructions, so let's
introduce new guest access modes GACC_FETCH and GACC_STORE instead
of a write flag. An additional patch will then introduce GACC_IFETCH.
Reviewed-by: Christian Borntraeger <borntraeger@de.ibm.com>
Signed-off-by: David Hildenbrand <dahi@linux.vnet.ibm.com>
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>