linux-toradex.git/virt/kvm/async_pf.c, branch v3.14.8

KVM: async_pf: mm->mm_users can not pin apf->mm

2014-05-13T11:32:47+00:00

commit 41c22f626254b9dc0376928cae009e73d1b6a49a upstream.

get_user_pages(mm) is simply wrong if mm->mm_users == 0 and exit_mmap/etc
was already called (or is in progress), mm->mm_count can only pin mm->pgd
and mm_struct itself.

Change kvm_setup_async_pf/async_pf_execute to inc/dec mm->mm_users.

kvm_create_vm/kvm_destroy_vm play with ->mm_count too but this case looks
fine at first glance, it seems that this ->mm is only used to verify that
current->mm == kvm->mm.

Signed-off-by: Oleg Nesterov 
Signed-off-by: Paolo Bonzini 
Signed-off-by: Greg Kroah-Hartman

KVM: Drop FOLL_GET in GUP when doing async page fault

2013-10-15T10:43:37+00:00

Page pinning is not mandatory in kvm async page fault processing since
after async page fault event is delivered to a guest it accesses page once
again and does its own GUP.  Drop the FOLL_GET flag in GUP in async_pf
code, and do some simplifying in check/clear processing.

Suggested-by: Gleb Natapov 
Signed-off-by: Gu zheng 
Signed-off-by: chai wen 
Signed-off-by: Gleb Natapov

kvm: remove .done from struct kvm_async_pf

2013-09-24T17:12:12+00:00

'.done' is used to mark the completion of 'async_pf_execute()', but
'cancel_work_sync()' returns true when the work was canceled, so we
use it instead.

Signed-off-by: Radim Krčmář 
Reviewed-by: Paolo Bonzini 
Reviewed-by: Gleb Natapov 
Signed-off-by: Paolo Bonzini

kvm: free resources after canceling async_pf

2013-09-17T09:53:15+00:00

When we cancel 'async_pf_execute()', we should behave as if the work was
never scheduled in 'kvm_setup_async_pf()'.
Fixes a bug when we can't unload module because the vm wasn't destroyed.

Signed-off-by: Radim Krčmář 
Reviewed-by: Paolo Bonzini 
Reviewed-by: Gleb Natapov 
Signed-off-by: Paolo Bonzini

KVM: do not release the error page

2012-08-06T13:04:58+00:00

After commit a2766325cf9f9, the error page is replaced by the
error code, it need not be released anymore

[ The patch has been compiling tested for powerpc ]

Signed-off-by: Xiao Guangrong 
Signed-off-by: Avi Kivity

KVM: introduce KVM_ERR_PTR_BAD_PAGE

2012-08-06T13:04:55+00:00

It is used to eliminate the overload of function call and cleanup
the code

Signed-off-by: Xiao Guangrong 
Signed-off-by: Avi Kivity

KVM: remove dummy pages

2012-07-26T08:55:34+00:00

Currently, kvm allocates some pages and use them as error indicators,
it wastes memory and is not good for scalability

Base on Avi's suggestion, we use the error codes instead of these pages
to indicate the error conditions

Signed-off-by: Xiao Guangrong 
Signed-off-by: Avi Kivity

KVM: use kvm_release_page_clean to release the page

2012-07-26T08:55:31+00:00

In kvm_async_pf_wakeup_all, it uses bad_page to generate broadcast wakeup,
and uses put_page to release bad_page, the work depends on the fact that
bad_page is the normal page. But we will use the error code instead of
bad_page, so use kvm_release_page_clean to release the page which will
release the error code properly

Signed-off-by: Xiao Guangrong 
Signed-off-by: Avi Kivity

KVM: fix the race while wakeup all pv guest

2011-01-12T09:29:03+00:00

In kvm_async_pf_wakeup_all(), we add a dummy apf to vcpu->async_pf.done
without holding vcpu->async_pf.lock, it will break if we are handling apfs
at this time.

Also use 'list_empty_careful()' instead of 'list_empty()'

Signed-off-by: Xiao Guangrong 
Acked-by: Gleb Natapov 
Signed-off-by: Marcelo Tosatti

KVM: handle more completed apfs if possible

2011-01-12T09:29:01+00:00

If it's no need to inject async #PF to PV guest we can handle
more completed apfs at one time, so we can retry guest #PF
as early as possible

Signed-off-by: Xiao Guangrong 
Acked-by: Gleb Natapov 
Signed-off-by: Marcelo Tosatti